Command that produces this log: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> trigger_label_ffn.layers.0.weight: torch.Size([450, 1024])
>>> trigger_label_ffn.layers.0.bias: torch.Size([450])
>>> trigger_label_ffn.layers.1.weight: torch.Size([233, 450])
>>> trigger_label_ffn.layers.1.bias: torch.Size([233])
>>> trigger_crf.transition: torch.Size([235, 235])
n_trainable_params: 560511990, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:22:34.035009: step: 4/529, loss: 3.621532440185547
2023-01-22 23:22:35.166340: step: 8/529, loss: 13.542070388793945
2023-01-22 23:22:36.296016: step: 12/529, loss: 3.117363929748535
2023-01-22 23:22:37.443150: step: 16/529, loss: 4.673288822174072
2023-01-22 23:22:38.617951: step: 20/529, loss: 5.232785224914551
2023-01-22 23:22:39.785419: step: 24/529, loss: 12.63650894165039
2023-01-22 23:22:40.881381: step: 28/529, loss: 2.595937728881836
2023-01-22 23:22:42.011978: step: 32/529, loss: 14.397211074829102
2023-01-22 23:22:43.145557: step: 36/529, loss: 16.40961265563965
2023-01-22 23:22:44.269410: step: 40/529, loss: 16.237842559814453
2023-01-22 23:22:45.393415: step: 44/529, loss: 9.762625694274902
2023-01-22 23:22:46.537844: step: 48/529, loss: 19.22272300720215
2023-01-22 23:22:47.657805: step: 52/529, loss: 14.365507125854492
2023-01-22 23:22:48.786426: step: 56/529, loss: 10.777974128723145
2023-01-22 23:22:49.942986: step: 60/529, loss: 21.444992065429688
2023-01-22 23:22:51.045763: step: 64/529, loss: 2.9161853790283203
2023-01-22 23:22:52.194714: step: 68/529, loss: 12.690162658691406
2023-01-22 23:22:53.290725: step: 72/529, loss: 4.3046112060546875
2023-01-22 23:22:54.411039: step: 76/529, loss: 2.0277481079101562
2023-01-22 23:22:55.535593: step: 80/529, loss: 13.829889297485352
2023-01-22 23:22:56.663585: step: 84/529, loss: 16.591564178466797
2023-01-22 23:22:57.798161: step: 88/529, loss: 3.896984338760376
2023-01-22 23:22:58.924493: step: 92/529, loss: 25.74120330810547
2023-01-22 23:23:00.061770: step: 96/529, loss: 2.3117856979370117
2023-01-22 23:23:01.174923: step: 100/529, loss: 2.5821826457977295
2023-01-22 23:23:02.313291: step: 104/529, loss: 3.8382575511932373
2023-01-22 23:23:03.443568: step: 108/529, loss: 4.201536178588867
2023-01-22 23:23:04.614766: step: 112/529, loss: 3.37551212310791
2023-01-22 23:23:05.767736: step: 116/529, loss: 11.776656150817871
2023-01-22 23:23:06.877659: step: 120/529, loss: 7.709282875061035
2023-01-22 23:23:08.023939: step: 124/529, loss: 33.39939498901367
2023-01-22 23:23:09.164286: step: 128/529, loss: 14.534605026245117
2023-01-22 23:23:10.330817: step: 132/529, loss: 3.7271571159362793
2023-01-22 23:23:11.466786: step: 136/529, loss: 3.990236520767212
2023-01-22 23:23:12.608657: step: 140/529, loss: 2.5393314361572266
2023-01-22 23:23:13.725040: step: 144/529, loss: 3.369417428970337
2023-01-22 23:23:14.837197: step: 148/529, loss: 17.484071731567383
2023-01-22 23:23:15.991145: step: 152/529, loss: 17.277616500854492
2023-01-22 23:23:17.127273: step: 156/529, loss: 15.19094467163086
2023-01-22 23:23:18.275025: step: 160/529, loss: 3.8732707500457764
2023-01-22 23:23:19.457368: step: 164/529, loss: 18.729747772216797
2023-01-22 23:23:20.588600: step: 168/529, loss: 7.309647083282471
2023-01-22 23:23:21.699584: step: 172/529, loss: 12.084159851074219
2023-01-22 23:23:22.844913: step: 176/529, loss: 17.671701431274414
2023-01-22 23:23:24.036675: step: 180/529, loss: 3.7090930938720703
2023-01-22 23:23:25.190065: step: 184/529, loss: 7.771060943603516
2023-01-22 23:23:26.325760: step: 188/529, loss: 11.59591293334961
2023-01-22 23:23:27.481125: step: 192/529, loss: 17.572521209716797
2023-01-22 23:23:28.604161: step: 196/529, loss: 12.50350570678711
2023-01-22 23:23:29.719000: step: 200/529, loss: 2.356724500656128
2023-01-22 23:23:30.860746: step: 204/529, loss: 3.408334493637085
2023-01-22 23:23:32.034210: step: 208/529, loss: 7.889789581298828
2023-01-22 23:23:33.155528: step: 212/529, loss: 2.3980212211608887
2023-01-22 23:23:34.284229: step: 216/529, loss: 3.275615930557251
2023-01-22 23:23:35.418172: step: 220/529, loss: 3.4327845573425293
2023-01-22 23:23:36.559782: step: 224/529, loss: 3.4952778816223145
2023-01-22 23:23:37.740467: step: 228/529, loss: 15.922210693359375
2023-01-22 23:23:38.874995: step: 232/529, loss: 3.977330207824707
2023-01-22 23:23:40.034090: step: 236/529, loss: 16.399816513061523
2023-01-22 23:23:41.167725: step: 240/529, loss: 3.9154746532440186
2023-01-22 23:23:42.307193: step: 244/529, loss: 6.403435707092285
2023-01-22 23:23:43.481084: step: 248/529, loss: 22.584266662597656
2023-01-22 23:23:44.600988: step: 252/529, loss: 3.6529977321624756
2023-01-22 23:23:45.748252: step: 256/529, loss: 4.413402557373047
2023-01-22 23:23:46.889064: step: 260/529, loss: 11.04973030090332
2023-01-22 23:23:48.023557: step: 264/529, loss: 13.011677742004395
2023-01-22 23:23:49.207868: step: 268/529, loss: 21.92221450805664
2023-01-22 23:23:50.360121: step: 272/529, loss: 3.4088897705078125
2023-01-22 23:23:51.491843: step: 276/529, loss: 9.868379592895508
2023-01-22 23:23:52.652682: step: 280/529, loss: 7.998035907745361
2023-01-22 23:23:53.819139: step: 284/529, loss: 7.747998237609863
2023-01-22 23:23:54.943696: step: 288/529, loss: 10.487600326538086
2023-01-22 23:23:56.055565: step: 292/529, loss: 2.0814990997314453
2023-01-22 23:23:57.205750: step: 296/529, loss: 19.663665771484375
2023-01-22 23:23:58.326016: step: 300/529, loss: 18.744508743286133
2023-01-22 23:23:59.478908: step: 304/529, loss: 15.447212219238281
2023-01-22 23:24:00.631989: step: 308/529, loss: 3.228632926940918
2023-01-22 23:24:01.799795: step: 312/529, loss: 9.735000610351562
2023-01-22 23:24:02.938124: step: 316/529, loss: 8.61428451538086
2023-01-22 23:24:04.046722: step: 320/529, loss: 2.3212857246398926
2023-01-22 23:24:05.203442: step: 324/529, loss: 3.5599350929260254
2023-01-22 23:24:06.334978: step: 328/529, loss: 25.49233627319336
2023-01-22 23:24:07.489699: step: 332/529, loss: 14.523412704467773
2023-01-22 23:24:08.635395: step: 336/529, loss: 15.256505966186523
2023-01-22 23:24:09.790280: step: 340/529, loss: 4.101177215576172
2023-01-22 23:24:10.941740: step: 344/529, loss: 13.484951972961426
2023-01-22 23:24:12.040169: step: 348/529, loss: 12.421173095703125
2023-01-22 23:24:13.220160: step: 352/529, loss: 20.946449279785156
2023-01-22 23:24:14.344438: step: 356/529, loss: 5.729172229766846
2023-01-22 23:24:15.510687: step: 360/529, loss: 4.24559211730957
2023-01-22 23:24:16.683148: step: 364/529, loss: 15.634750366210938
2023-01-22 23:24:17.805987: step: 368/529, loss: 3.1929025650024414
2023-01-22 23:24:18.974402: step: 372/529, loss: 4.050047874450684
2023-01-22 23:24:20.096792: step: 376/529, loss: 6.843565940856934
2023-01-22 23:24:21.232564: step: 380/529, loss: 6.251766681671143
2023-01-22 23:24:22.397262: step: 384/529, loss: 2.5218305587768555
2023-01-22 23:24:23.535190: step: 388/529, loss: 4.976187705993652
2023-01-22 23:24:24.679833: step: 392/529, loss: 14.570524215698242
2023-01-22 23:24:25.827645: step: 396/529, loss: 2.7670998573303223
2023-01-22 23:24:26.971106: step: 400/529, loss: 2.284353733062744
2023-01-22 23:24:28.111307: step: 404/529, loss: 2.0368025302886963
2023-01-22 23:24:29.258518: step: 408/529, loss: 11.088184356689453
2023-01-22 23:24:30.425278: step: 412/529, loss: 8.588536262512207
2023-01-22 23:24:31.588083: step: 416/529, loss: 15.744332313537598
2023-01-22 23:24:32.715157: step: 420/529, loss: 2.5162558555603027
2023-01-22 23:24:33.868522: step: 424/529, loss: 12.147928237915039
2023-01-22 23:24:35.006409: step: 428/529, loss: 16.330371856689453
2023-01-22 23:24:36.132861: step: 432/529, loss: 2.4632058143615723
2023-01-22 23:24:37.279619: step: 436/529, loss: 9.33383560180664
2023-01-22 23:24:38.415929: step: 440/529, loss: 10.591821670532227
2023-01-22 23:24:39.573580: step: 444/529, loss: 1.8141107559204102
2023-01-22 23:24:40.709351: step: 448/529, loss: 4.411225318908691
2023-01-22 23:24:41.814368: step: 452/529, loss: 1.4334101676940918
2023-01-22 23:24:42.958447: step: 456/529, loss: 3.184615135192871
2023-01-22 23:24:44.074437: step: 460/529, loss: 4.646284103393555
2023-01-22 23:24:45.195183: step: 464/529, loss: 1.6411666870117188
2023-01-22 23:24:46.337137: step: 468/529, loss: 6.401620864868164
2023-01-22 23:24:47.526661: step: 472/529, loss: 5.5645294189453125
2023-01-22 23:24:48.672180: step: 476/529, loss: 2.019742250442505
2023-01-22 23:24:49.816973: step: 480/529, loss: 1.4654401540756226
2023-01-22 23:24:50.934792: step: 484/529, loss: 1.5957221984863281
2023-01-22 23:24:52.092093: step: 488/529, loss: 11.635149002075195
2023-01-22 23:24:53.227585: step: 492/529, loss: 3.5896639823913574
2023-01-22 23:24:54.391962: step: 496/529, loss: 20.204261779785156
2023-01-22 23:24:55.520471: step: 500/529, loss: 1.2019952535629272
2023-01-22 23:24:56.662391: step: 504/529, loss: 9.574487686157227
2023-01-22 23:24:57.786220: step: 508/529, loss: 1.0506038665771484
2023-01-22 23:24:58.908286: step: 512/529, loss: 1.271968960762024
2023-01-22 23:25:00.043029: step: 516/529, loss: 7.965608596801758
2023-01-22 23:25:01.184208: step: 520/529, loss: 1.824202537536621
2023-01-22 23:25:02.347617: step: 524/529, loss: 1.1979656219482422
2023-01-22 23:25:03.461930: step: 528/529, loss: 0.8139227628707886
2023-01-22 23:25:04.612093: step: 532/529, loss: 5.290958881378174
2023-01-22 23:25:05.742621: step: 536/529, loss: 7.221170902252197
2023-01-22 23:25:06.889764: step: 540/529, loss: 5.015775203704834
2023-01-22 23:25:08.022489: step: 544/529, loss: 3.8171215057373047
2023-01-22 23:25:09.158830: step: 548/529, loss: 1.9852263927459717
2023-01-22 23:25:10.308592: step: 552/529, loss: 1.1681818962097168
2023-01-22 23:25:11.424760: step: 556/529, loss: 0.9781670570373535
2023-01-22 23:25:12.568938: step: 560/529, loss: 1.547278642654419
2023-01-22 23:25:13.716908: step: 564/529, loss: 2.165371894836426
2023-01-22 23:25:14.840980: step: 568/529, loss: 3.466583251953125
2023-01-22 23:25:15.986073: step: 572/529, loss: 2.0548954010009766
2023-01-22 23:25:17.110798: step: 576/529, loss: 1.2156181335449219
2023-01-22 23:25:18.244585: step: 580/529, loss: 1.1908199787139893
2023-01-22 23:25:19.359025: step: 584/529, loss: 3.61586856842041
2023-01-22 23:25:20.510436: step: 588/529, loss: 5.851022720336914
2023-01-22 23:25:21.625496: step: 592/529, loss: 1.3916974067687988
2023-01-22 23:25:22.781014: step: 596/529, loss: 4.2090373039245605
2023-01-22 23:25:23.904555: step: 600/529, loss: 1.3879903554916382
2023-01-22 23:25:25.029062: step: 604/529, loss: 0.8362724781036377
2023-01-22 23:25:26.171346: step: 608/529, loss: 0.513518214225769
2023-01-22 23:25:27.279975: step: 612/529, loss: 1.4912546873092651
2023-01-22 23:25:28.371986: step: 616/529, loss: 10.108013153076172
2023-01-22 23:25:29.540374: step: 620/529, loss: 3.1758322715759277
2023-01-22 23:25:30.660256: step: 624/529, loss: 0.7201522588729858
2023-01-22 23:25:31.826223: step: 628/529, loss: 3.003248929977417
2023-01-22 23:25:32.986141: step: 632/529, loss: 0.8918566703796387
2023-01-22 23:25:34.136789: step: 636/529, loss: 3.295438528060913
2023-01-22 23:25:35.283285: step: 640/529, loss: 3.516563892364502
2023-01-22 23:25:36.409077: step: 644/529, loss: 2.8429579734802246
2023-01-22 23:25:37.555071: step: 648/529, loss: 0.42065197229385376
2023-01-22 23:25:38.704587: step: 652/529, loss: 0.626232922077179
2023-01-22 23:25:39.836810: step: 656/529, loss: 1.2756016254425049
2023-01-22 23:25:40.962663: step: 660/529, loss: 0.5550310611724854
2023-01-22 23:25:42.084477: step: 664/529, loss: 1.5328176021575928
2023-01-22 23:25:43.204504: step: 668/529, loss: 1.6487457752227783
2023-01-22 23:25:44.356662: step: 672/529, loss: 2.7514681816101074
2023-01-22 23:25:45.508986: step: 676/529, loss: 4.128016471862793
2023-01-22 23:25:46.639667: step: 680/529, loss: 0.6200653314590454
2023-01-22 23:25:47.775682: step: 684/529, loss: 3.6971468925476074
2023-01-22 23:25:48.904079: step: 688/529, loss: 0.7104389667510986
2023-01-22 23:25:50.044197: step: 692/529, loss: 0.9314755797386169
2023-01-22 23:25:51.141839: step: 696/529, loss: 1.1598939895629883
2023-01-22 23:25:52.295005: step: 700/529, loss: 0.8454206585884094
2023-01-22 23:25:53.430541: step: 704/529, loss: 1.9795746803283691
2023-01-22 23:25:54.625105: step: 708/529, loss: 1.7655086517333984
2023-01-22 23:25:55.785646: step: 712/529, loss: 0.9487324953079224
2023-01-22 23:25:56.920692: step: 716/529, loss: 1.832971215248108
2023-01-22 23:25:58.036178: step: 720/529, loss: 1.7045546770095825
2023-01-22 23:25:59.169194: step: 724/529, loss: 1.2064987421035767
2023-01-22 23:26:00.282005: step: 728/529, loss: 3.393432378768921
2023-01-22 23:26:01.416014: step: 732/529, loss: 0.3778058886528015
2023-01-22 23:26:02.559091: step: 736/529, loss: 0.8241660594940186
2023-01-22 23:26:03.671808: step: 740/529, loss: 0.511652410030365
2023-01-22 23:26:04.831187: step: 744/529, loss: 3.5488650798797607
2023-01-22 23:26:05.976487: step: 748/529, loss: 1.674997329711914
2023-01-22 23:26:07.110104: step: 752/529, loss: 3.3751368522644043
2023-01-22 23:26:08.254988: step: 756/529, loss: 0.5803846120834351
2023-01-22 23:26:09.399547: step: 760/529, loss: 0.4445878863334656
2023-01-22 23:26:10.526306: step: 764/529, loss: 0.9939770698547363
2023-01-22 23:26:11.646072: step: 768/529, loss: 0.36156535148620605
2023-01-22 23:26:12.818796: step: 772/529, loss: 3.4489002227783203
2023-01-22 23:26:13.947745: step: 776/529, loss: 4.135929584503174
2023-01-22 23:26:15.075196: step: 780/529, loss: 2.089932918548584
2023-01-22 23:26:16.212026: step: 784/529, loss: 0.4640917181968689
2023-01-22 23:26:17.396749: step: 788/529, loss: 1.1669062376022339
2023-01-22 23:26:18.555102: step: 792/529, loss: 0.9698988199234009
2023-01-22 23:26:19.693823: step: 796/529, loss: 1.3405826091766357
2023-01-22 23:26:20.846942: step: 800/529, loss: 2.5966296195983887
2023-01-22 23:26:21.973719: step: 804/529, loss: 0.779301106929779
2023-01-22 23:26:23.099099: step: 808/529, loss: 2.9553210735321045
2023-01-22 23:26:24.236679: step: 812/529, loss: 0.5742433071136475
2023-01-22 23:26:25.365333: step: 816/529, loss: 1.4621717929840088
2023-01-22 23:26:26.506486: step: 820/529, loss: 0.5653336644172668
2023-01-22 23:26:27.641690: step: 824/529, loss: 0.357096791267395
2023-01-22 23:26:28.789885: step: 828/529, loss: 2.403977394104004
2023-01-22 23:26:29.919035: step: 832/529, loss: 3.190617561340332
2023-01-22 23:26:31.083062: step: 836/529, loss: 1.0175585746765137
2023-01-22 23:26:32.202876: step: 840/529, loss: 1.1468260288238525
2023-01-22 23:26:33.339111: step: 844/529, loss: 1.7973920106887817
2023-01-22 23:26:34.475317: step: 848/529, loss: 0.7385352849960327
2023-01-22 23:26:35.621675: step: 852/529, loss: 1.0770177841186523
2023-01-22 23:26:36.740829: step: 856/529, loss: 3.0698933601379395
2023-01-22 23:26:37.874643: step: 860/529, loss: 0.4015979766845703
2023-01-22 23:26:39.036335: step: 864/529, loss: 2.0169858932495117
2023-01-22 23:26:40.159609: step: 868/529, loss: 1.0402926206588745
2023-01-22 23:26:41.302219: step: 872/529, loss: 1.6893560886383057
2023-01-22 23:26:42.468115: step: 876/529, loss: 0.6583280563354492
2023-01-22 23:26:43.620116: step: 880/529, loss: 0.29671764373779297
2023-01-22 23:26:44.753922: step: 884/529, loss: 1.7505154609680176
2023-01-22 23:26:45.886153: step: 888/529, loss: 1.2750203609466553
2023-01-22 23:26:47.052571: step: 892/529, loss: 2.740898609161377
2023-01-22 23:26:48.184575: step: 896/529, loss: 0.40280312299728394
2023-01-22 23:26:49.306408: step: 900/529, loss: 0.29644542932510376
2023-01-22 23:26:50.430431: step: 904/529, loss: 2.701512336730957
2023-01-22 23:26:51.561072: step: 908/529, loss: 0.23906993865966797
2023-01-22 23:26:52.696125: step: 912/529, loss: 0.5065438747406006
2023-01-22 23:26:53.827977: step: 916/529, loss: 0.23993238806724548
2023-01-22 23:26:54.951787: step: 920/529, loss: 1.8112282752990723
2023-01-22 23:26:56.102851: step: 924/529, loss: 0.3414899408817291
2023-01-22 23:26:57.247819: step: 928/529, loss: 0.6074423789978027
2023-01-22 23:26:58.424925: step: 932/529, loss: 0.819431722164154
2023-01-22 23:26:59.531283: step: 936/529, loss: 1.5271637439727783
2023-01-22 23:27:00.659110: step: 940/529, loss: 2.2112016677856445
2023-01-22 23:27:01.781459: step: 944/529, loss: 1.2948899269104004
2023-01-22 23:27:02.931593: step: 948/529, loss: 0.5799522399902344
2023-01-22 23:27:04.088940: step: 952/529, loss: 3.5372352600097656
2023-01-22 23:27:05.224324: step: 956/529, loss: 5.067075729370117
2023-01-22 23:27:06.375917: step: 960/529, loss: 1.584993839263916
2023-01-22 23:27:07.508165: step: 964/529, loss: 0.9113391041755676
2023-01-22 23:27:08.637166: step: 968/529, loss: 3.3932623863220215
2023-01-22 23:27:09.762916: step: 972/529, loss: 1.536823034286499
2023-01-22 23:27:10.899524: step: 976/529, loss: 1.6471267938613892
2023-01-22 23:27:12.059809: step: 980/529, loss: 5.270932197570801
2023-01-22 23:27:13.205879: step: 984/529, loss: 0.5724227428436279
2023-01-22 23:27:14.363327: step: 988/529, loss: 1.2616477012634277
2023-01-22 23:27:15.480325: step: 992/529, loss: 1.6249890327453613
2023-01-22 23:27:16.633939: step: 996/529, loss: 1.4779839515686035
2023-01-22 23:27:17.781327: step: 1000/529, loss: 0.3906409442424774
2023-01-22 23:27:18.901284: step: 1004/529, loss: 2.9598405361175537
2023-01-22 23:27:20.018909: step: 1008/529, loss: 2.644022226333618
2023-01-22 23:27:21.190473: step: 1012/529, loss: 3.001842975616455
2023-01-22 23:27:22.305852: step: 1016/529, loss: 2.463235855102539
2023-01-22 23:27:23.433337: step: 1020/529, loss: 0.45442572236061096
2023-01-22 23:27:24.564358: step: 1024/529, loss: 0.30489426851272583
2023-01-22 23:27:25.704324: step: 1028/529, loss: 0.5068156719207764
2023-01-22 23:27:26.838257: step: 1032/529, loss: 1.2137457132339478
2023-01-22 23:27:27.991835: step: 1036/529, loss: 6.931217193603516
2023-01-22 23:27:29.117677: step: 1040/529, loss: 0.32786035537719727
2023-01-22 23:27:30.238661: step: 1044/529, loss: 2.5096447467803955
2023-01-22 23:27:31.386029: step: 1048/529, loss: 0.4271506667137146
2023-01-22 23:27:32.492991: step: 1052/529, loss: 3.0060503482818604
2023-01-22 23:27:33.642690: step: 1056/529, loss: 0.6822559833526611
2023-01-22 23:27:34.776146: step: 1060/529, loss: 0.718085527420044
2023-01-22 23:27:35.899091: step: 1064/529, loss: 1.7505027055740356
2023-01-22 23:27:37.035063: step: 1068/529, loss: 0.655796229839325
2023-01-22 23:27:38.178015: step: 1072/529, loss: 0.716809868812561
2023-01-22 23:27:39.358993: step: 1076/529, loss: 4.08268928527832
2023-01-22 23:27:40.507353: step: 1080/529, loss: 0.26747018098831177
2023-01-22 23:27:41.631218: step: 1084/529, loss: 0.5302784442901611
2023-01-22 23:27:42.764313: step: 1088/529, loss: 2.5076818466186523
2023-01-22 23:27:43.918150: step: 1092/529, loss: 9.097386360168457
2023-01-22 23:27:45.062341: step: 1096/529, loss: 3.2745413780212402
2023-01-22 23:27:46.199927: step: 1100/529, loss: 2.0416064262390137
2023-01-22 23:27:47.329707: step: 1104/529, loss: 0.5942925214767456
2023-01-22 23:27:48.465213: step: 1108/529, loss: 0.6088376045227051
2023-01-22 23:27:49.594017: step: 1112/529, loss: 1.2197341918945312
2023-01-22 23:27:50.745480: step: 1116/529, loss: 0.43286314606666565
2023-01-22 23:27:51.889157: step: 1120/529, loss: 0.23642738163471222
2023-01-22 23:27:52.999205: step: 1124/529, loss: 2.0354673862457275
2023-01-22 23:27:54.138141: step: 1128/529, loss: 0.7759148478507996
2023-01-22 23:27:55.257140: step: 1132/529, loss: 0.6867160797119141
2023-01-22 23:27:56.400091: step: 1136/529, loss: 0.33035534620285034
2023-01-22 23:27:57.523871: step: 1140/529, loss: 0.30516648292541504
2023-01-22 23:27:58.675122: step: 1144/529, loss: 1.8776904344558716
2023-01-22 23:27:59.805399: step: 1148/529, loss: 1.650612235069275
2023-01-22 23:28:00.939702: step: 1152/529, loss: 0.38097113370895386
2023-01-22 23:28:02.074605: step: 1156/529, loss: 0.5021973848342896
2023-01-22 23:28:03.204359: step: 1160/529, loss: 8.511953353881836
2023-01-22 23:28:04.347881: step: 1164/529, loss: 1.480036735534668
2023-01-22 23:28:05.483376: step: 1168/529, loss: 1.989585041999817
2023-01-22 23:28:06.641830: step: 1172/529, loss: 5.852951526641846
2023-01-22 23:28:07.772458: step: 1176/529, loss: 0.9966527223587036
2023-01-22 23:28:08.898732: step: 1180/529, loss: 2.0300960540771484
2023-01-22 23:28:10.036311: step: 1184/529, loss: 0.49075227975845337
2023-01-22 23:28:11.161933: step: 1188/529, loss: 0.5505347847938538
2023-01-22 23:28:12.311788: step: 1192/529, loss: 1.1302720308303833
2023-01-22 23:28:13.449978: step: 1196/529, loss: 1.0865519046783447
2023-01-22 23:28:14.588396: step: 1200/529, loss: 0.7182204127311707
2023-01-22 23:28:15.723173: step: 1204/529, loss: 1.036863923072815
2023-01-22 23:28:16.864698: step: 1208/529, loss: 1.3710113763809204
2023-01-22 23:28:18.012674: step: 1212/529, loss: 0.3698939383029938
2023-01-22 23:28:19.166859: step: 1216/529, loss: 0.5071775317192078
2023-01-22 23:28:20.312585: step: 1220/529, loss: 2.9697458744049072
2023-01-22 23:28:21.442713: step: 1224/529, loss: 0.794247031211853
2023-01-22 23:28:22.558892: step: 1228/529, loss: 0.8224543333053589
2023-01-22 23:28:23.695891: step: 1232/529, loss: 0.21337567269802094
2023-01-22 23:28:24.850721: step: 1236/529, loss: 0.4057280421257019
2023-01-22 23:28:25.976562: step: 1240/529, loss: 0.4606713354587555
2023-01-22 23:28:27.134652: step: 1244/529, loss: 0.38343098759651184
2023-01-22 23:28:28.273315: step: 1248/529, loss: 0.5494058132171631
2023-01-22 23:28:29.387538: step: 1252/529, loss: 0.7290338277816772
2023-01-22 23:28:30.512239: step: 1256/529, loss: 1.510838508605957
2023-01-22 23:28:31.618182: step: 1260/529, loss: 3.643113374710083
2023-01-22 23:28:32.745177: step: 1264/529, loss: 1.732445240020752
2023-01-22 23:28:33.860389: step: 1268/529, loss: 0.40447598695755005
2023-01-22 23:28:34.977362: step: 1272/529, loss: 0.8668304085731506
2023-01-22 23:28:36.118270: step: 1276/529, loss: 0.25786638259887695
2023-01-22 23:28:37.281897: step: 1280/529, loss: 0.8625131845474243
2023-01-22 23:28:38.438305: step: 1284/529, loss: 0.3239728808403015
2023-01-22 23:28:39.559802: step: 1288/529, loss: 1.5239778757095337
2023-01-22 23:28:40.691358: step: 1292/529, loss: 1.7557837963104248
2023-01-22 23:28:41.843367: step: 1296/529, loss: 1.75142240524292
2023-01-22 23:28:42.966317: step: 1300/529, loss: 0.9475021362304688
2023-01-22 23:28:44.100079: step: 1304/529, loss: 1.3006868362426758
2023-01-22 23:28:45.229063: step: 1308/529, loss: 0.5015181303024292
2023-01-22 23:28:46.385476: step: 1312/529, loss: 1.085694432258606
2023-01-22 23:28:47.504392: step: 1316/529, loss: 0.35742467641830444
2023-01-22 23:28:48.629640: step: 1320/529, loss: 1.0509415864944458
2023-01-22 23:28:49.739168: step: 1324/529, loss: 0.3264305889606476
2023-01-22 23:28:50.869873: step: 1328/529, loss: 0.5333709716796875
2023-01-22 23:28:52.025563: step: 1332/529, loss: 0.4387022852897644
2023-01-22 23:28:53.170459: step: 1336/529, loss: 0.4024922251701355
2023-01-22 23:28:54.296739: step: 1340/529, loss: 1.852999210357666
2023-01-22 23:28:55.400658: step: 1344/529, loss: 0.7516586780548096
2023-01-22 23:28:56.544720: step: 1348/529, loss: 2.232771873474121
2023-01-22 23:28:57.667295: step: 1352/529, loss: 0.2666875720024109
2023-01-22 23:28:58.787194: step: 1356/529, loss: 0.33623045682907104
2023-01-22 23:28:59.915520: step: 1360/529, loss: 0.5571774244308472
2023-01-22 23:29:01.048103: step: 1364/529, loss: 0.48473238945007324
2023-01-22 23:29:02.217781: step: 1368/529, loss: 0.17340508103370667
2023-01-22 23:29:03.349598: step: 1372/529, loss: 0.4033452272415161
2023-01-22 23:29:04.486983: step: 1376/529, loss: 0.6019673347473145
2023-01-22 23:29:05.622788: step: 1380/529, loss: 1.0341713428497314
2023-01-22 23:29:06.736631: step: 1384/529, loss: 0.286648154258728
2023-01-22 23:29:07.869228: step: 1388/529, loss: 4.122661590576172
2023-01-22 23:29:08.978493: step: 1392/529, loss: 0.7338075637817383
2023-01-22 23:29:10.138246: step: 1396/529, loss: 0.6949564218521118
2023-01-22 23:29:11.249203: step: 1400/529, loss: 0.525062620639801
2023-01-22 23:29:12.387278: step: 1404/529, loss: 6.894042015075684
2023-01-22 23:29:13.544907: step: 1408/529, loss: 1.2990083694458008
2023-01-22 23:29:14.678555: step: 1412/529, loss: 2.1497371196746826
2023-01-22 23:29:15.823954: step: 1416/529, loss: 1.2402030229568481
2023-01-22 23:29:16.938602: step: 1420/529, loss: 0.5442218780517578
2023-01-22 23:29:18.125264: step: 1424/529, loss: 2.8404784202575684
2023-01-22 23:29:19.258375: step: 1428/529, loss: 0.2555355131626129
2023-01-22 23:29:20.395759: step: 1432/529, loss: 0.7639809846878052
2023-01-22 23:29:21.527934: step: 1436/529, loss: 1.7471200227737427
2023-01-22 23:29:22.651143: step: 1440/529, loss: 0.23662137985229492
2023-01-22 23:29:23.754856: step: 1444/529, loss: 0.40045350790023804
2023-01-22 23:29:24.908427: step: 1448/529, loss: 1.1397353410720825
2023-01-22 23:29:26.042184: step: 1452/529, loss: 0.4629027545452118
2023-01-22 23:29:27.181872: step: 1456/529, loss: 0.9567396640777588
2023-01-22 23:29:28.337856: step: 1460/529, loss: 0.341137558221817
2023-01-22 23:29:29.451640: step: 1464/529, loss: 0.4640963077545166
2023-01-22 23:29:30.555870: step: 1468/529, loss: 2.211867332458496
2023-01-22 23:29:31.679410: step: 1472/529, loss: 0.585845947265625
2023-01-22 23:29:32.801772: step: 1476/529, loss: 0.4816916882991791
2023-01-22 23:29:33.919849: step: 1480/529, loss: 1.4729294776916504
2023-01-22 23:29:35.043592: step: 1484/529, loss: 0.4252338409423828
2023-01-22 23:29:36.199434: step: 1488/529, loss: 5.345481872558594
2023-01-22 23:29:37.354390: step: 1492/529, loss: 0.8776652812957764
2023-01-22 23:29:38.504550: step: 1496/529, loss: 0.29841554164886475
2023-01-22 23:29:39.645922: step: 1500/529, loss: 0.5287191271781921
2023-01-22 23:29:40.764250: step: 1504/529, loss: 0.5562278628349304
2023-01-22 23:29:41.927196: step: 1508/529, loss: 2.2081239223480225
2023-01-22 23:29:43.052421: step: 1512/529, loss: 0.37848329544067383
2023-01-22 23:29:44.197665: step: 1516/529, loss: 1.870319128036499
2023-01-22 23:29:45.345204: step: 1520/529, loss: 0.24362607300281525
2023-01-22 23:29:46.475872: step: 1524/529, loss: 0.47149384021759033
2023-01-22 23:29:47.637943: step: 1528/529, loss: 0.6378626823425293
2023-01-22 23:29:48.760791: step: 1532/529, loss: 0.5113728046417236
2023-01-22 23:29:49.915419: step: 1536/529, loss: 3.1645052433013916
2023-01-22 23:29:51.042195: step: 1540/529, loss: 1.1048482656478882
2023-01-22 23:29:52.183256: step: 1544/529, loss: 0.9618955850601196
2023-01-22 23:29:53.335418: step: 1548/529, loss: 0.6876150965690613
2023-01-22 23:29:54.451107: step: 1552/529, loss: 0.2438717484474182
2023-01-22 23:29:55.617699: step: 1556/529, loss: 7.936010360717773
2023-01-22 23:29:56.765913: step: 1560/529, loss: 1.4922549724578857
2023-01-22 23:29:57.946855: step: 1564/529, loss: 0.27962514758110046
2023-01-22 23:29:59.089703: step: 1568/529, loss: 7.159943103790283
2023-01-22 23:30:00.215496: step: 1572/529, loss: 1.120267629623413
2023-01-22 23:30:01.359075: step: 1576/529, loss: 0.41146671772003174
2023-01-22 23:30:02.476989: step: 1580/529, loss: 2.4651637077331543
2023-01-22 23:30:03.606859: step: 1584/529, loss: 0.8812049627304077
2023-01-22 23:30:04.725286: step: 1588/529, loss: 0.20512624084949493
2023-01-22 23:30:05.881240: step: 1592/529, loss: 1.12703537940979
2023-01-22 23:30:07.007468: step: 1596/529, loss: 7.471231460571289
2023-01-22 23:30:08.191361: step: 1600/529, loss: 1.0049278736114502
2023-01-22 23:30:09.341040: step: 1604/529, loss: 1.0047423839569092
2023-01-22 23:30:10.481085: step: 1608/529, loss: 0.7438883781433105
2023-01-22 23:30:11.589209: step: 1612/529, loss: 1.006537914276123
2023-01-22 23:30:12.735746: step: 1616/529, loss: 1.6063528060913086
2023-01-22 23:30:13.915425: step: 1620/529, loss: 0.975894570350647
2023-01-22 23:30:15.076213: step: 1624/529, loss: 1.0521715879440308
2023-01-22 23:30:16.181638: step: 1628/529, loss: 1.572803020477295
2023-01-22 23:30:17.309077: step: 1632/529, loss: 0.5591209530830383
2023-01-22 23:30:18.458873: step: 1636/529, loss: 1.0661540031433105
2023-01-22 23:30:19.633405: step: 1640/529, loss: 0.5868942141532898
2023-01-22 23:30:20.763627: step: 1644/529, loss: 1.431801438331604
2023-01-22 23:30:21.908988: step: 1648/529, loss: 1.76229989528656
2023-01-22 23:30:23.057491: step: 1652/529, loss: 0.37676024436950684
2023-01-22 23:30:24.174909: step: 1656/529, loss: 0.30986320972442627
2023-01-22 23:30:25.341321: step: 1660/529, loss: 0.912360668182373
2023-01-22 23:30:26.484854: step: 1664/529, loss: 0.8488156795501709
2023-01-22 23:30:27.654924: step: 1668/529, loss: 0.8135032653808594
2023-01-22 23:30:28.796301: step: 1672/529, loss: 0.07859086990356445
2023-01-22 23:30:29.926592: step: 1676/529, loss: 0.22118231654167175
2023-01-22 23:30:31.052582: step: 1680/529, loss: 0.6065610647201538
2023-01-22 23:30:32.203958: step: 1684/529, loss: 0.18476100265979767
2023-01-22 23:30:33.334433: step: 1688/529, loss: 0.4858241677284241
2023-01-22 23:30:34.487208: step: 1692/529, loss: 0.550195574760437
2023-01-22 23:30:35.631615: step: 1696/529, loss: 0.34195661544799805
2023-01-22 23:30:36.758602: step: 1700/529, loss: 0.7902202606201172
2023-01-22 23:30:37.918247: step: 1704/529, loss: 0.1298881471157074
2023-01-22 23:30:39.066683: step: 1708/529, loss: 0.6398295164108276
2023-01-22 23:30:40.258369: step: 1712/529, loss: 0.20396332442760468
2023-01-22 23:30:41.413707: step: 1716/529, loss: 0.2997762858867645
2023-01-22 23:30:42.589065: step: 1720/529, loss: 1.7543193101882935
2023-01-22 23:30:43.732208: step: 1724/529, loss: 3.327333688735962
2023-01-22 23:30:44.838467: step: 1728/529, loss: 0.3710118532180786
2023-01-22 23:30:45.993970: step: 1732/529, loss: 0.5208996534347534
2023-01-22 23:30:47.113109: step: 1736/529, loss: 0.3774925768375397
2023-01-22 23:30:48.220389: step: 1740/529, loss: 0.5465073585510254
2023-01-22 23:30:49.373044: step: 1744/529, loss: 0.4329710006713867
2023-01-22 23:30:50.497896: step: 1748/529, loss: 0.5405237078666687
2023-01-22 23:30:51.650222: step: 1752/529, loss: 1.8058745861053467
2023-01-22 23:30:52.773345: step: 1756/529, loss: 0.5758148431777954
2023-01-22 23:30:53.891754: step: 1760/529, loss: 0.43531861901283264
2023-01-22 23:30:55.011217: step: 1764/529, loss: 0.37160149216651917
2023-01-22 23:30:56.148940: step: 1768/529, loss: 0.566301167011261
2023-01-22 23:30:57.285987: step: 1772/529, loss: 0.18470755219459534
2023-01-22 23:30:58.414394: step: 1776/529, loss: 0.44613516330718994
2023-01-22 23:30:59.556908: step: 1780/529, loss: 1.723960280418396
2023-01-22 23:31:00.698760: step: 1784/529, loss: 0.4782143831253052
2023-01-22 23:31:01.841874: step: 1788/529, loss: 0.22105231881141663
2023-01-22 23:31:02.968063: step: 1792/529, loss: 0.10841484367847443
2023-01-22 23:31:04.100118: step: 1796/529, loss: 3.045856475830078
2023-01-22 23:31:05.248905: step: 1800/529, loss: 0.6988542675971985
2023-01-22 23:31:06.396585: step: 1804/529, loss: 0.8430399894714355
2023-01-22 23:31:07.550089: step: 1808/529, loss: 0.25225868821144104
2023-01-22 23:31:08.670826: step: 1812/529, loss: 0.5378435850143433
2023-01-22 23:31:09.816638: step: 1816/529, loss: 2.1167407035827637
2023-01-22 23:31:10.911023: step: 1820/529, loss: 0.4301365911960602
2023-01-22 23:31:12.040816: step: 1824/529, loss: 0.14607305824756622
2023-01-22 23:31:13.200555: step: 1828/529, loss: 2.0961008071899414
2023-01-22 23:31:14.352213: step: 1832/529, loss: 2.315335512161255
2023-01-22 23:31:15.480433: step: 1836/529, loss: 0.4069212079048157
2023-01-22 23:31:16.610049: step: 1840/529, loss: 0.12884049117565155
2023-01-22 23:31:17.743414: step: 1844/529, loss: 0.8808757662773132
2023-01-22 23:31:18.866261: step: 1848/529, loss: 0.6215300559997559
2023-01-22 23:31:20.002338: step: 1852/529, loss: 0.3097376227378845
2023-01-22 23:31:21.121379: step: 1856/529, loss: 0.5453568696975708
2023-01-22 23:31:22.248561: step: 1860/529, loss: 0.3228136897087097
2023-01-22 23:31:23.385521: step: 1864/529, loss: 3.5696210861206055
2023-01-22 23:31:24.511287: step: 1868/529, loss: 0.21188050508499146
2023-01-22 23:31:25.660996: step: 1872/529, loss: 1.728649377822876
2023-01-22 23:31:26.799623: step: 1876/529, loss: 1.2658092975616455
2023-01-22 23:31:27.910245: step: 1880/529, loss: 0.8763715028762817
2023-01-22 23:31:29.061103: step: 1884/529, loss: 0.4274565577507019
2023-01-22 23:31:30.261447: step: 1888/529, loss: 0.8709762692451477
2023-01-22 23:31:31.398500: step: 1892/529, loss: 1.7838966846466064
2023-01-22 23:31:32.505748: step: 1896/529, loss: 0.22778764367103577
2023-01-22 23:31:33.648534: step: 1900/529, loss: 2.0915491580963135
2023-01-22 23:31:34.796846: step: 1904/529, loss: 0.33962053060531616
2023-01-22 23:31:35.917250: step: 1908/529, loss: 0.45984387397766113
2023-01-22 23:31:37.068085: step: 1912/529, loss: 2.1153433322906494
2023-01-22 23:31:38.209855: step: 1916/529, loss: 0.30112916231155396
2023-01-22 23:31:39.363352: step: 1920/529, loss: 0.39301174879074097
2023-01-22 23:31:40.514633: step: 1924/529, loss: 0.21990787982940674
2023-01-22 23:31:41.660013: step: 1928/529, loss: 0.30765199661254883
2023-01-22 23:31:42.806261: step: 1932/529, loss: 0.4110768437385559
2023-01-22 23:31:43.913311: step: 1936/529, loss: 1.0211756229400635
2023-01-22 23:31:45.040824: step: 1940/529, loss: 0.8921117782592773
2023-01-22 23:31:46.204287: step: 1944/529, loss: 0.6786177158355713
2023-01-22 23:31:47.340354: step: 1948/529, loss: 0.532731831073761
2023-01-22 23:31:48.477246: step: 1952/529, loss: 0.2940041124820709
2023-01-22 23:31:49.599766: step: 1956/529, loss: 1.8261213302612305
2023-01-22 23:31:50.731556: step: 1960/529, loss: 0.15733389556407928
2023-01-22 23:31:51.882093: step: 1964/529, loss: 0.7331670522689819
2023-01-22 23:31:53.012488: step: 1968/529, loss: 0.8912182450294495
2023-01-22 23:31:54.184206: step: 1972/529, loss: 1.4951698780059814
2023-01-22 23:31:55.360074: step: 1976/529, loss: 0.49952155351638794
2023-01-22 23:31:56.527859: step: 1980/529, loss: 1.2072674036026
2023-01-22 23:31:57.658811: step: 1984/529, loss: 0.20373401045799255
2023-01-22 23:31:58.788798: step: 1988/529, loss: 1.7011696100234985
2023-01-22 23:31:59.907257: step: 1992/529, loss: 0.6681041717529297
2023-01-22 23:32:01.040249: step: 1996/529, loss: 0.22191476821899414
2023-01-22 23:32:02.205462: step: 2000/529, loss: 0.7241841554641724
2023-01-22 23:32:03.334357: step: 2004/529, loss: 1.2355533838272095
2023-01-22 23:32:04.476151: step: 2008/529, loss: 0.36321955919265747
2023-01-22 23:32:05.629589: step: 2012/529, loss: 1.7107552289962769
2023-01-22 23:32:06.761957: step: 2016/529, loss: 1.6967189311981201
2023-01-22 23:32:07.904047: step: 2020/529, loss: 1.6046949625015259
2023-01-22 23:32:09.043963: step: 2024/529, loss: 0.25262928009033203
2023-01-22 23:32:10.183068: step: 2028/529, loss: 0.43971705436706543
2023-01-22 23:32:11.354242: step: 2032/529, loss: 0.12725749611854553
2023-01-22 23:32:12.477064: step: 2036/529, loss: 0.4302833676338196
2023-01-22 23:32:13.644219: step: 2040/529, loss: 0.8647814989089966
2023-01-22 23:32:14.780652: step: 2044/529, loss: 0.7444102764129639
2023-01-22 23:32:15.920706: step: 2048/529, loss: 0.2606492042541504
2023-01-22 23:32:17.054833: step: 2052/529, loss: 0.8823707699775696
2023-01-22 23:32:18.198078: step: 2056/529, loss: 1.8375400304794312
2023-01-22 23:32:19.346694: step: 2060/529, loss: 0.30606240034103394
2023-01-22 23:32:20.499735: step: 2064/529, loss: 0.8164175152778625
2023-01-22 23:32:21.634551: step: 2068/529, loss: 0.25308284163475037
2023-01-22 23:32:22.777413: step: 2072/529, loss: 0.23977404832839966
2023-01-22 23:32:23.899185: step: 2076/529, loss: 0.2210439145565033
2023-01-22 23:32:25.018302: step: 2080/529, loss: 0.463204026222229
2023-01-22 23:32:26.176057: step: 2084/529, loss: 1.7650251388549805
2023-01-22 23:32:27.318539: step: 2088/529, loss: 6.856368064880371
2023-01-22 23:32:28.453395: step: 2092/529, loss: 1.110244870185852
2023-01-22 23:32:29.577753: step: 2096/529, loss: 0.3843016028404236
2023-01-22 23:32:30.693105: step: 2100/529, loss: 0.9868789911270142
2023-01-22 23:32:31.844635: step: 2104/529, loss: 0.808090329170227
2023-01-22 23:32:32.984212: step: 2108/529, loss: 0.1819995492696762
2023-01-22 23:32:34.133020: step: 2112/529, loss: 0.7787676453590393
2023-01-22 23:32:35.276372: step: 2116/529, loss: 2.5226590633392334
==================================================
Loss: 3.208
--------------------
Dev: {'event': {'p': 0.5862068965517241, 'r': 0.5432756324900133, 'f1': 0.5639253628196268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.4797191887675507, 'r': 0.3563151796060255, 'f1': 0.4089095744680851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.42592592592592593, 'f1': 0.4842105263157895}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.6923076923076923, 'r': 0.2857142857142857, 'f1': 0.4044943820224719}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.375, 'r': 0.16666666666666666, 'f1': 0.23076923076923078}, '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': 0.5862068965517241, 'r': 0.5432756324900133, 'f1': 0.5639253628196268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.4797191887675507, 'r': 0.3563151796060255, 'f1': 0.4089095744680851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.42592592592592593, 'f1': 0.4842105263157895}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5862068965517241, 'r': 0.5432756324900133, 'f1': 0.5639253628196268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.4797191887675507, 'r': 0.3563151796060255, 'f1': 0.4089095744680851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.6923076923076923, 'r': 0.2857142857142857, 'f1': 0.4044943820224719}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862068965517241, 'r': 0.5432756324900133, 'f1': 0.5639253628196268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.4797191887675507, 'r': 0.3563151796060255, 'f1': 0.4089095744680851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.375, 'r': 0.16666666666666666, 'f1': 0.23076923076923078}, '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 23:33:40.017031: step: 4/529, loss: 2.938530921936035
2023-01-22 23:33:41.144894: step: 8/529, loss: 0.35229891538619995
2023-01-22 23:33:42.287776: step: 12/529, loss: 1.1775540113449097
2023-01-22 23:33:43.476882: step: 16/529, loss: 1.7110569477081299
2023-01-22 23:33:44.625595: step: 20/529, loss: 1.1641806364059448
2023-01-22 23:33:45.784582: step: 24/529, loss: 0.19667291641235352
2023-01-22 23:33:46.958221: step: 28/529, loss: 0.8878239393234253
2023-01-22 23:33:48.081740: step: 32/529, loss: 4.964476585388184
2023-01-22 23:33:49.244986: step: 36/529, loss: 1.4169527292251587
2023-01-22 23:33:50.389095: step: 40/529, loss: 1.3267056941986084
2023-01-22 23:33:51.557802: step: 44/529, loss: 0.9741167426109314
2023-01-22 23:33:52.689415: step: 48/529, loss: 0.9785480499267578
2023-01-22 23:33:53.838844: step: 52/529, loss: 6.838603973388672
2023-01-22 23:33:54.988897: step: 56/529, loss: 0.42646974325180054
2023-01-22 23:33:56.129537: step: 60/529, loss: 1.7733484506607056
2023-01-22 23:33:57.276558: step: 64/529, loss: 0.8867408633232117
2023-01-22 23:33:58.435808: step: 68/529, loss: 1.1831772327423096
2023-01-22 23:33:59.591985: step: 72/529, loss: 0.2452596127986908
2023-01-22 23:34:00.733524: step: 76/529, loss: 2.0087647438049316
2023-01-22 23:34:01.884036: step: 80/529, loss: 0.6992994546890259
2023-01-22 23:34:03.007688: step: 84/529, loss: 0.3327838182449341
2023-01-22 23:34:04.158896: step: 88/529, loss: 0.2657693922519684
2023-01-22 23:34:05.315612: step: 92/529, loss: 0.5083276033401489
2023-01-22 23:34:06.456164: step: 96/529, loss: 1.513451099395752
2023-01-22 23:34:07.565829: step: 100/529, loss: 0.8501608967781067
2023-01-22 23:34:08.703273: step: 104/529, loss: 11.079312324523926
2023-01-22 23:34:09.847630: step: 108/529, loss: 0.18545770645141602
2023-01-22 23:34:11.009558: step: 112/529, loss: 0.13908815383911133
2023-01-22 23:34:12.179083: step: 116/529, loss: 0.6973282694816589
2023-01-22 23:34:13.360579: step: 120/529, loss: 0.29902762174606323
2023-01-22 23:34:14.485830: step: 124/529, loss: 0.905144214630127
2023-01-22 23:34:15.604411: step: 128/529, loss: 0.9375255107879639
2023-01-22 23:34:16.733360: step: 132/529, loss: 0.30079782009124756
2023-01-22 23:34:17.910223: step: 136/529, loss: 1.599959135055542
2023-01-22 23:34:19.048883: step: 140/529, loss: 0.6238815784454346
2023-01-22 23:34:20.170722: step: 144/529, loss: 0.9514894485473633
2023-01-22 23:34:21.295958: step: 148/529, loss: 0.25117167830467224
2023-01-22 23:34:22.426554: step: 152/529, loss: 1.3730931282043457
2023-01-22 23:34:23.576338: step: 156/529, loss: 0.5314227342605591
2023-01-22 23:34:24.695508: step: 160/529, loss: 1.093907117843628
2023-01-22 23:34:25.829231: step: 164/529, loss: 0.21213456988334656
2023-01-22 23:34:26.948363: step: 168/529, loss: 0.34765952825546265
2023-01-22 23:34:28.094184: step: 172/529, loss: 0.19783231616020203
2023-01-22 23:34:29.227782: step: 176/529, loss: 1.2791751623153687
2023-01-22 23:34:30.369754: step: 180/529, loss: 0.326324462890625
2023-01-22 23:34:31.525300: step: 184/529, loss: 0.37679052352905273
2023-01-22 23:34:32.654276: step: 188/529, loss: 2.1085660457611084
2023-01-22 23:34:33.779939: step: 192/529, loss: 0.64113450050354
2023-01-22 23:34:34.912937: step: 196/529, loss: 0.4685416519641876
2023-01-22 23:34:36.061407: step: 200/529, loss: 0.49039435386657715
2023-01-22 23:34:37.201572: step: 204/529, loss: 0.23786889016628265
2023-01-22 23:34:38.334748: step: 208/529, loss: 0.3385983407497406
2023-01-22 23:34:39.462803: step: 212/529, loss: 0.40551871061325073
2023-01-22 23:34:40.594845: step: 216/529, loss: 0.9544097781181335
2023-01-22 23:34:41.724946: step: 220/529, loss: 0.3216747045516968
2023-01-22 23:34:42.886005: step: 224/529, loss: 1.4213862419128418
2023-01-22 23:34:44.045326: step: 228/529, loss: 0.3096015155315399
2023-01-22 23:34:45.154474: step: 232/529, loss: 0.7316606044769287
2023-01-22 23:34:46.298891: step: 236/529, loss: 0.821317195892334
2023-01-22 23:34:47.411387: step: 240/529, loss: 0.4682171940803528
2023-01-22 23:34:48.566597: step: 244/529, loss: 0.15753412246704102
2023-01-22 23:34:49.705250: step: 248/529, loss: 0.16952915489673615
2023-01-22 23:34:50.852671: step: 252/529, loss: 2.312734365463257
2023-01-22 23:34:52.013798: step: 256/529, loss: 0.39927130937576294
2023-01-22 23:34:53.133124: step: 260/529, loss: 0.14115343987941742
2023-01-22 23:34:54.280633: step: 264/529, loss: 0.1422864943742752
2023-01-22 23:34:55.429177: step: 268/529, loss: 0.5056096911430359
2023-01-22 23:34:56.543846: step: 272/529, loss: 0.18460464477539062
2023-01-22 23:34:57.688212: step: 276/529, loss: 0.32110393047332764
2023-01-22 23:34:58.838467: step: 280/529, loss: 0.37311363220214844
2023-01-22 23:34:59.969603: step: 284/529, loss: 2.1574289798736572
2023-01-22 23:35:01.098394: step: 288/529, loss: 0.9065800905227661
2023-01-22 23:35:02.236588: step: 292/529, loss: 0.18569979071617126
2023-01-22 23:35:03.375652: step: 296/529, loss: 0.12617188692092896
2023-01-22 23:35:04.501476: step: 300/529, loss: 0.18380004167556763
2023-01-22 23:35:05.637917: step: 304/529, loss: 0.5336170196533203
2023-01-22 23:35:06.787270: step: 308/529, loss: 0.48369672894477844
2023-01-22 23:35:07.943408: step: 312/529, loss: 0.7249584197998047
2023-01-22 23:35:09.119204: step: 316/529, loss: 0.8844048380851746
2023-01-22 23:35:10.250997: step: 320/529, loss: 0.3962167799472809
2023-01-22 23:35:11.404899: step: 324/529, loss: 0.41168874502182007
2023-01-22 23:35:12.516772: step: 328/529, loss: 0.9417327642440796
2023-01-22 23:35:13.661816: step: 332/529, loss: 1.018467664718628
2023-01-22 23:35:14.784479: step: 336/529, loss: 0.09948311001062393
2023-01-22 23:35:15.926073: step: 340/529, loss: 0.11509513854980469
2023-01-22 23:35:17.065485: step: 344/529, loss: 0.8259420394897461
2023-01-22 23:35:18.213901: step: 348/529, loss: 0.4823358654975891
2023-01-22 23:35:19.364311: step: 352/529, loss: 0.5422476530075073
2023-01-22 23:35:20.537635: step: 356/529, loss: 0.7489575147628784
2023-01-22 23:35:21.674225: step: 360/529, loss: 0.7969327569007874
2023-01-22 23:35:22.813844: step: 364/529, loss: 1.4077816009521484
2023-01-22 23:35:23.958656: step: 368/529, loss: 0.323464959859848
2023-01-22 23:35:25.102648: step: 372/529, loss: 0.15628428757190704
2023-01-22 23:35:26.275555: step: 376/529, loss: 0.45432502031326294
2023-01-22 23:35:27.422077: step: 380/529, loss: 0.3573431372642517
2023-01-22 23:35:28.572411: step: 384/529, loss: 1.9641146659851074
2023-01-22 23:35:29.718368: step: 388/529, loss: 0.45423832535743713
2023-01-22 23:35:30.851133: step: 392/529, loss: 0.8016027212142944
2023-01-22 23:35:32.033284: step: 396/529, loss: 0.6931349039077759
2023-01-22 23:35:33.178400: step: 400/529, loss: 7.130451679229736
2023-01-22 23:35:34.309558: step: 404/529, loss: 0.9619883894920349
2023-01-22 23:35:35.454194: step: 408/529, loss: 0.17553609609603882
2023-01-22 23:35:36.582474: step: 412/529, loss: 0.5371543169021606
2023-01-22 23:35:37.760066: step: 416/529, loss: 6.35456657409668
2023-01-22 23:35:38.944283: step: 420/529, loss: 1.8735235929489136
2023-01-22 23:35:40.101705: step: 424/529, loss: 0.31495970487594604
2023-01-22 23:35:41.271368: step: 428/529, loss: 3.0553712844848633
2023-01-22 23:35:42.411422: step: 432/529, loss: 0.32576435804367065
2023-01-22 23:35:43.532263: step: 436/529, loss: 0.578923225402832
2023-01-22 23:35:44.646194: step: 440/529, loss: 0.2525663375854492
2023-01-22 23:35:45.786015: step: 444/529, loss: 0.15729370713233948
2023-01-22 23:35:46.919265: step: 448/529, loss: 0.8245846033096313
2023-01-22 23:35:48.046502: step: 452/529, loss: 0.27101975679397583
2023-01-22 23:35:49.171257: step: 456/529, loss: 0.19498157501220703
2023-01-22 23:35:50.305563: step: 460/529, loss: 0.5603306293487549
2023-01-22 23:35:51.464717: step: 464/529, loss: 0.19061031937599182
2023-01-22 23:35:52.601302: step: 468/529, loss: 0.34526732563972473
2023-01-22 23:35:53.739471: step: 472/529, loss: 0.2579323649406433
2023-01-22 23:35:54.892722: step: 476/529, loss: 0.5323038101196289
2023-01-22 23:35:56.050823: step: 480/529, loss: 1.062608242034912
2023-01-22 23:35:57.193681: step: 484/529, loss: 1.7276530265808105
2023-01-22 23:35:58.337323: step: 488/529, loss: 2.9541053771972656
2023-01-22 23:35:59.468042: step: 492/529, loss: 0.38564595580101013
2023-01-22 23:36:00.592841: step: 496/529, loss: 0.35428586602211
2023-01-22 23:36:01.738597: step: 500/529, loss: 0.7991260886192322
2023-01-22 23:36:02.884591: step: 504/529, loss: 0.7846972942352295
2023-01-22 23:36:03.990940: step: 508/529, loss: 0.6294810771942139
2023-01-22 23:36:05.121223: step: 512/529, loss: 0.8370799422264099
2023-01-22 23:36:06.273543: step: 516/529, loss: 0.34018832445144653
2023-01-22 23:36:07.438237: step: 520/529, loss: 0.8810480237007141
2023-01-22 23:36:08.576321: step: 524/529, loss: 0.3134942948818207
2023-01-22 23:36:09.689009: step: 528/529, loss: 0.29537904262542725
2023-01-22 23:36:10.808498: step: 532/529, loss: 1.2235320806503296
2023-01-22 23:36:11.916564: step: 536/529, loss: 0.9157170653343201
2023-01-22 23:36:13.078186: step: 540/529, loss: 0.9095420241355896
2023-01-22 23:36:14.209243: step: 544/529, loss: 0.38371741771698
2023-01-22 23:36:15.337192: step: 548/529, loss: 0.26568323373794556
2023-01-22 23:36:16.496245: step: 552/529, loss: 0.7462350726127625
2023-01-22 23:36:17.632754: step: 556/529, loss: 0.2976147532463074
2023-01-22 23:36:18.776454: step: 560/529, loss: 0.2737061679363251
2023-01-22 23:36:19.921075: step: 564/529, loss: 6.999796390533447
2023-01-22 23:36:21.069587: step: 568/529, loss: 0.24717697501182556
2023-01-22 23:36:22.208373: step: 572/529, loss: 0.3453161120414734
2023-01-22 23:36:23.315204: step: 576/529, loss: 0.2021385133266449
2023-01-22 23:36:24.446577: step: 580/529, loss: 0.14663821458816528
2023-01-22 23:36:25.584713: step: 584/529, loss: 2.5010900497436523
2023-01-22 23:36:26.692718: step: 588/529, loss: 0.14363646507263184
2023-01-22 23:36:27.835551: step: 592/529, loss: 0.22648312151432037
2023-01-22 23:36:28.980419: step: 596/529, loss: 0.7444033622741699
2023-01-22 23:36:30.112189: step: 600/529, loss: 0.5878614783287048
2023-01-22 23:36:31.235404: step: 604/529, loss: 0.35113203525543213
2023-01-22 23:36:32.364050: step: 608/529, loss: 1.207403302192688
2023-01-22 23:36:33.550867: step: 612/529, loss: 0.9373064041137695
2023-01-22 23:36:34.692792: step: 616/529, loss: 0.3856774568557739
2023-01-22 23:36:35.844998: step: 620/529, loss: 1.5732369422912598
2023-01-22 23:36:36.994124: step: 624/529, loss: 1.8320481777191162
2023-01-22 23:36:38.136722: step: 628/529, loss: 0.4988988935947418
2023-01-22 23:36:39.280748: step: 632/529, loss: 0.2700865864753723
2023-01-22 23:36:40.420036: step: 636/529, loss: 0.9359628558158875
2023-01-22 23:36:41.577384: step: 640/529, loss: 1.0615077018737793
2023-01-22 23:36:42.705466: step: 644/529, loss: 0.056235421448946
2023-01-22 23:36:43.817768: step: 648/529, loss: 0.5603745579719543
2023-01-22 23:36:44.954065: step: 652/529, loss: 0.3206295967102051
2023-01-22 23:36:46.080840: step: 656/529, loss: 1.1626073122024536
2023-01-22 23:36:47.193143: step: 660/529, loss: 0.2522863745689392
2023-01-22 23:36:48.329123: step: 664/529, loss: 0.1974714696407318
2023-01-22 23:36:49.465980: step: 668/529, loss: 0.6952510476112366
2023-01-22 23:36:50.603367: step: 672/529, loss: 0.32597237825393677
2023-01-22 23:36:51.745123: step: 676/529, loss: 0.2884550094604492
2023-01-22 23:36:52.904401: step: 680/529, loss: 2.3008382320404053
2023-01-22 23:36:54.011742: step: 684/529, loss: 1.3631598949432373
2023-01-22 23:36:55.159415: step: 688/529, loss: 1.0244896411895752
2023-01-22 23:36:56.328863: step: 692/529, loss: 1.0603013038635254
2023-01-22 23:36:57.442087: step: 696/529, loss: 0.06894628703594208
2023-01-22 23:36:58.589199: step: 700/529, loss: 2.2512283325195312
2023-01-22 23:36:59.712705: step: 704/529, loss: 0.34750068187713623
2023-01-22 23:37:00.869525: step: 708/529, loss: 0.49512797594070435
2023-01-22 23:37:02.058005: step: 712/529, loss: 1.5319430828094482
2023-01-22 23:37:03.215059: step: 716/529, loss: 0.5386723875999451
2023-01-22 23:37:04.357535: step: 720/529, loss: 0.08035726845264435
2023-01-22 23:37:05.491763: step: 724/529, loss: 0.32039251923561096
2023-01-22 23:37:06.628056: step: 728/529, loss: 0.9971221685409546
2023-01-22 23:37:07.770456: step: 732/529, loss: 0.25700846314430237
2023-01-22 23:37:08.886965: step: 736/529, loss: 0.2144605666399002
2023-01-22 23:37:10.052354: step: 740/529, loss: 2.633221387863159
2023-01-22 23:37:11.184812: step: 744/529, loss: 0.8342758417129517
2023-01-22 23:37:12.329463: step: 748/529, loss: 0.6564019322395325
2023-01-22 23:37:13.465099: step: 752/529, loss: 0.36439400911331177
2023-01-22 23:37:14.598545: step: 756/529, loss: 0.1734904646873474
2023-01-22 23:37:15.743182: step: 760/529, loss: 2.699251174926758
2023-01-22 23:37:16.890085: step: 764/529, loss: 1.4306433200836182
2023-01-22 23:37:18.078365: step: 768/529, loss: 1.356773018836975
2023-01-22 23:37:19.186654: step: 772/529, loss: 0.7788138389587402
2023-01-22 23:37:20.331893: step: 776/529, loss: 0.48847952485084534
2023-01-22 23:37:21.469533: step: 780/529, loss: 0.9458274841308594
2023-01-22 23:37:22.608211: step: 784/529, loss: 0.39781731367111206
2023-01-22 23:37:23.690751: step: 788/529, loss: 0.7113245129585266
2023-01-22 23:37:24.803425: step: 792/529, loss: 0.3420921564102173
2023-01-22 23:37:25.923786: step: 796/529, loss: 0.8405942916870117
2023-01-22 23:37:27.076116: step: 800/529, loss: 0.12295912206172943
2023-01-22 23:37:28.244160: step: 804/529, loss: 0.49430298805236816
2023-01-22 23:37:29.396225: step: 808/529, loss: 0.8668269515037537
2023-01-22 23:37:30.519891: step: 812/529, loss: 0.827810525894165
2023-01-22 23:37:31.623215: step: 816/529, loss: 0.2077282965183258
2023-01-22 23:37:32.761661: step: 820/529, loss: 0.8789294362068176
2023-01-22 23:37:33.914046: step: 824/529, loss: 0.508680522441864
2023-01-22 23:37:35.037619: step: 828/529, loss: 6.765714645385742
2023-01-22 23:37:36.153615: step: 832/529, loss: 0.8015994429588318
2023-01-22 23:37:37.290379: step: 836/529, loss: 0.11436138302087784
2023-01-22 23:37:38.432033: step: 840/529, loss: 0.26067009568214417
2023-01-22 23:37:39.587763: step: 844/529, loss: 0.23226170241832733
2023-01-22 23:37:40.719734: step: 848/529, loss: 0.8968196511268616
2023-01-22 23:37:41.897977: step: 852/529, loss: 0.2878015637397766
2023-01-22 23:37:43.033825: step: 856/529, loss: 6.6833086013793945
2023-01-22 23:37:44.168748: step: 860/529, loss: 0.543400764465332
2023-01-22 23:37:45.265664: step: 864/529, loss: 2.3582990169525146
2023-01-22 23:37:46.393274: step: 868/529, loss: 0.17841282486915588
2023-01-22 23:37:47.507312: step: 872/529, loss: 0.7141642570495605
2023-01-22 23:37:48.633515: step: 876/529, loss: 1.2771152257919312
2023-01-22 23:37:49.776142: step: 880/529, loss: 0.4982832670211792
2023-01-22 23:37:50.958658: step: 884/529, loss: 0.40006905794143677
2023-01-22 23:37:52.078825: step: 888/529, loss: 0.2375883013010025
2023-01-22 23:37:53.198435: step: 892/529, loss: 1.8226087093353271
2023-01-22 23:37:54.332429: step: 896/529, loss: 0.2102208137512207
2023-01-22 23:37:55.457272: step: 900/529, loss: 0.3662320077419281
2023-01-22 23:37:56.577112: step: 904/529, loss: 0.11506939679384232
2023-01-22 23:37:57.696322: step: 908/529, loss: 0.8001874089241028
2023-01-22 23:37:58.800093: step: 912/529, loss: 0.12894801795482635
2023-01-22 23:37:59.938769: step: 916/529, loss: 0.18576350808143616
2023-01-22 23:38:01.069453: step: 920/529, loss: 0.10321883857250214
2023-01-22 23:38:02.177234: step: 924/529, loss: 0.2037675827741623
2023-01-22 23:38:03.310462: step: 928/529, loss: 0.21415062248706818
2023-01-22 23:38:04.402093: step: 932/529, loss: 0.3335719108581543
2023-01-22 23:38:05.574578: step: 936/529, loss: 1.5137025117874146
2023-01-22 23:38:06.712824: step: 940/529, loss: 0.22497105598449707
2023-01-22 23:38:07.820223: step: 944/529, loss: 0.2935396134853363
2023-01-22 23:38:08.967488: step: 948/529, loss: 1.4770570993423462
2023-01-22 23:38:10.116345: step: 952/529, loss: 0.23993521928787231
2023-01-22 23:38:11.249174: step: 956/529, loss: 0.7086160778999329
2023-01-22 23:38:12.393436: step: 960/529, loss: 0.05982933193445206
2023-01-22 23:38:13.541708: step: 964/529, loss: 0.06373167037963867
2023-01-22 23:38:14.671336: step: 968/529, loss: 0.17378145456314087
2023-01-22 23:38:15.811003: step: 972/529, loss: 0.24838675558567047
2023-01-22 23:38:16.952140: step: 976/529, loss: 0.8171840906143188
2023-01-22 23:38:18.096465: step: 980/529, loss: 0.9138569831848145
2023-01-22 23:38:19.233282: step: 984/529, loss: 1.0758111476898193
2023-01-22 23:38:20.374956: step: 988/529, loss: 0.19634565711021423
2023-01-22 23:38:21.513287: step: 992/529, loss: 0.21462908387184143
2023-01-22 23:38:22.645653: step: 996/529, loss: 0.9129133224487305
2023-01-22 23:38:23.753286: step: 1000/529, loss: 2.635676383972168
2023-01-22 23:38:24.899981: step: 1004/529, loss: 1.3215116262435913
2023-01-22 23:38:26.038445: step: 1008/529, loss: 0.224347785115242
2023-01-22 23:38:27.188389: step: 1012/529, loss: 0.718658983707428
2023-01-22 23:38:28.361717: step: 1016/529, loss: 0.24458342790603638
2023-01-22 23:38:29.510019: step: 1020/529, loss: 0.16220471262931824
2023-01-22 23:38:30.675532: step: 1024/529, loss: 0.12832693755626678
2023-01-22 23:38:31.794335: step: 1028/529, loss: 0.17081347107887268
2023-01-22 23:38:32.933145: step: 1032/529, loss: 0.3509206175804138
2023-01-22 23:38:34.102745: step: 1036/529, loss: 0.2427106350660324
2023-01-22 23:38:35.260355: step: 1040/529, loss: 0.18622225522994995
2023-01-22 23:38:36.390429: step: 1044/529, loss: 0.2536700367927551
2023-01-22 23:38:37.525234: step: 1048/529, loss: 0.7693371176719666
2023-01-22 23:38:38.667871: step: 1052/529, loss: 0.24589061737060547
2023-01-22 23:38:39.804755: step: 1056/529, loss: 0.2053605169057846
2023-01-22 23:38:40.948554: step: 1060/529, loss: 0.05548463016748428
2023-01-22 23:38:42.066084: step: 1064/529, loss: 1.7561016082763672
2023-01-22 23:38:43.208880: step: 1068/529, loss: 1.046337604522705
2023-01-22 23:38:44.342276: step: 1072/529, loss: 1.5373632907867432
2023-01-22 23:38:45.465891: step: 1076/529, loss: 1.1018669605255127
2023-01-22 23:38:46.599124: step: 1080/529, loss: 1.7216929197311401
2023-01-22 23:38:47.751236: step: 1084/529, loss: 1.964949607849121
2023-01-22 23:38:48.868899: step: 1088/529, loss: 0.8232311010360718
2023-01-22 23:38:50.054491: step: 1092/529, loss: 0.3604514002799988
2023-01-22 23:38:51.198554: step: 1096/529, loss: 0.8829132318496704
2023-01-22 23:38:52.325989: step: 1100/529, loss: 2.215179443359375
2023-01-22 23:38:53.473807: step: 1104/529, loss: 0.10780338943004608
2023-01-22 23:38:54.610854: step: 1108/529, loss: 0.2431640625
2023-01-22 23:38:55.750032: step: 1112/529, loss: 0.08399734646081924
2023-01-22 23:38:56.903417: step: 1116/529, loss: 1.0450273752212524
2023-01-22 23:38:58.097867: step: 1120/529, loss: 1.693611741065979
2023-01-22 23:38:59.222857: step: 1124/529, loss: 0.597059428691864
2023-01-22 23:39:00.383221: step: 1128/529, loss: 0.8682540059089661
2023-01-22 23:39:01.481104: step: 1132/529, loss: 0.14875009655952454
2023-01-22 23:39:02.646783: step: 1136/529, loss: 0.1848442256450653
2023-01-22 23:39:03.773330: step: 1140/529, loss: 0.5265677571296692
2023-01-22 23:39:04.913813: step: 1144/529, loss: 1.4149702787399292
2023-01-22 23:39:06.054360: step: 1148/529, loss: 0.5851609110832214
2023-01-22 23:39:07.194347: step: 1152/529, loss: 1.226862907409668
2023-01-22 23:39:08.348587: step: 1156/529, loss: 0.3521884083747864
2023-01-22 23:39:09.496971: step: 1160/529, loss: 0.2268299162387848
2023-01-22 23:39:10.608720: step: 1164/529, loss: 1.445133090019226
2023-01-22 23:39:11.760640: step: 1168/529, loss: 1.6017242670059204
2023-01-22 23:39:12.935539: step: 1172/529, loss: 0.2239668071269989
2023-01-22 23:39:14.085345: step: 1176/529, loss: 0.08118319511413574
2023-01-22 23:39:15.241619: step: 1180/529, loss: 0.35108959674835205
2023-01-22 23:39:16.340279: step: 1184/529, loss: 1.0763485431671143
2023-01-22 23:39:17.481318: step: 1188/529, loss: 0.34547722339630127
2023-01-22 23:39:18.625316: step: 1192/529, loss: 0.1340794563293457
2023-01-22 23:39:19.757006: step: 1196/529, loss: 0.22881336510181427
2023-01-22 23:39:20.879899: step: 1200/529, loss: 0.16314508020877838
2023-01-22 23:39:22.030710: step: 1204/529, loss: 0.6221767663955688
2023-01-22 23:39:23.183765: step: 1208/529, loss: 0.18148942291736603
2023-01-22 23:39:24.298783: step: 1212/529, loss: 1.5709794759750366
2023-01-22 23:39:25.424693: step: 1216/529, loss: 0.7450945377349854
2023-01-22 23:39:26.561319: step: 1220/529, loss: 0.5750439763069153
2023-01-22 23:39:27.721970: step: 1224/529, loss: 0.8094569444656372
2023-01-22 23:39:28.852374: step: 1228/529, loss: 0.48620858788490295
2023-01-22 23:39:29.994512: step: 1232/529, loss: 0.25180378556251526
2023-01-22 23:39:31.140174: step: 1236/529, loss: 0.4793487787246704
2023-01-22 23:39:32.286145: step: 1240/529, loss: 0.21152149140834808
2023-01-22 23:39:33.398719: step: 1244/529, loss: 0.26250505447387695
2023-01-22 23:39:34.537692: step: 1248/529, loss: 0.17898836731910706
2023-01-22 23:39:35.648132: step: 1252/529, loss: 0.09999523311853409
2023-01-22 23:39:36.772524: step: 1256/529, loss: 0.1858902871608734
2023-01-22 23:39:37.910295: step: 1260/529, loss: 0.5422772169113159
2023-01-22 23:39:39.067382: step: 1264/529, loss: 0.33639851212501526
2023-01-22 23:39:40.197572: step: 1268/529, loss: 0.9363800883293152
2023-01-22 23:39:41.313093: step: 1272/529, loss: 0.14035215973854065
2023-01-22 23:39:42.463868: step: 1276/529, loss: 1.1116856336593628
2023-01-22 23:39:43.622600: step: 1280/529, loss: 0.9366650581359863
2023-01-22 23:39:44.825834: step: 1284/529, loss: 0.21494418382644653
2023-01-22 23:39:45.981445: step: 1288/529, loss: 0.3201838731765747
2023-01-22 23:39:47.090285: step: 1292/529, loss: 0.4720112681388855
2023-01-22 23:39:48.226210: step: 1296/529, loss: 0.8141045570373535
2023-01-22 23:39:49.342412: step: 1300/529, loss: 0.44637930393218994
2023-01-22 23:39:50.507600: step: 1304/529, loss: 0.1693161129951477
2023-01-22 23:39:51.616645: step: 1308/529, loss: 0.46504440903663635
2023-01-22 23:39:52.760106: step: 1312/529, loss: 0.5144976377487183
2023-01-22 23:39:53.888081: step: 1316/529, loss: 6.5810418128967285
2023-01-22 23:39:55.043146: step: 1320/529, loss: 0.5250568389892578
2023-01-22 23:39:56.158636: step: 1324/529, loss: 0.10729971528053284
2023-01-22 23:39:57.315818: step: 1328/529, loss: 1.054152250289917
2023-01-22 23:39:58.434842: step: 1332/529, loss: 1.365271806716919
2023-01-22 23:39:59.560098: step: 1336/529, loss: 1.442115306854248
2023-01-22 23:40:00.688342: step: 1340/529, loss: 0.20402908325195312
2023-01-22 23:40:01.789917: step: 1344/529, loss: 0.14029577374458313
2023-01-22 23:40:02.918333: step: 1348/529, loss: 0.9411318898200989
2023-01-22 23:40:04.065017: step: 1352/529, loss: 0.1641758531332016
2023-01-22 23:40:05.228501: step: 1356/529, loss: 0.22643594443798065
2023-01-22 23:40:06.341144: step: 1360/529, loss: 0.9889498353004456
2023-01-22 23:40:07.452070: step: 1364/529, loss: 0.2504335343837738
2023-01-22 23:40:08.572631: step: 1368/529, loss: 1.7736448049545288
2023-01-22 23:40:09.683983: step: 1372/529, loss: 0.04648590087890625
2023-01-22 23:40:10.825367: step: 1376/529, loss: 0.5473880171775818
2023-01-22 23:40:11.945097: step: 1380/529, loss: 0.3631100654602051
2023-01-22 23:40:13.110577: step: 1384/529, loss: 0.24835491180419922
2023-01-22 23:40:14.340938: step: 1388/529, loss: 0.11867466568946838
2023-01-22 23:40:15.441776: step: 1392/529, loss: 0.2440529465675354
2023-01-22 23:40:16.574353: step: 1396/529, loss: 0.7663075923919678
2023-01-22 23:40:17.717034: step: 1400/529, loss: 1.7392289638519287
2023-01-22 23:40:18.847906: step: 1404/529, loss: 0.19356174767017365
2023-01-22 23:40:19.985738: step: 1408/529, loss: 0.24853840470314026
2023-01-22 23:40:21.120521: step: 1412/529, loss: 1.6402099132537842
2023-01-22 23:40:22.253761: step: 1416/529, loss: 0.6658819317817688
2023-01-22 23:40:23.389437: step: 1420/529, loss: 0.4736892580986023
2023-01-22 23:40:24.536453: step: 1424/529, loss: 0.31594592332839966
2023-01-22 23:40:25.680249: step: 1428/529, loss: 0.4358847737312317
2023-01-22 23:40:26.813919: step: 1432/529, loss: 1.840773344039917
2023-01-22 23:40:27.957846: step: 1436/529, loss: 0.26872050762176514
2023-01-22 23:40:29.105021: step: 1440/529, loss: 0.09251470863819122
2023-01-22 23:40:30.234565: step: 1444/529, loss: 0.23535729944705963
2023-01-22 23:40:31.389477: step: 1448/529, loss: 0.5126436948776245
2023-01-22 23:40:32.530877: step: 1452/529, loss: 0.15987567603588104
2023-01-22 23:40:33.659197: step: 1456/529, loss: 0.06912603229284286
2023-01-22 23:40:34.777938: step: 1460/529, loss: 1.303166151046753
2023-01-22 23:40:35.942409: step: 1464/529, loss: 0.8047708868980408
2023-01-22 23:40:37.082477: step: 1468/529, loss: 0.31621819734573364
2023-01-22 23:40:38.210089: step: 1472/529, loss: 0.08525316417217255
2023-01-22 23:40:39.326975: step: 1476/529, loss: 6.623735427856445
2023-01-22 23:40:40.453163: step: 1480/529, loss: 0.9232900738716125
2023-01-22 23:40:41.588204: step: 1484/529, loss: 0.4921996295452118
2023-01-22 23:40:42.733480: step: 1488/529, loss: 0.23620501160621643
2023-01-22 23:40:43.890222: step: 1492/529, loss: 0.7446185350418091
2023-01-22 23:40:45.004711: step: 1496/529, loss: 0.7989373207092285
2023-01-22 23:40:46.147440: step: 1500/529, loss: 0.07127318531274796
2023-01-22 23:40:47.289811: step: 1504/529, loss: 0.30706846714019775
2023-01-22 23:40:48.429747: step: 1508/529, loss: 1.816852331161499
2023-01-22 23:40:49.566369: step: 1512/529, loss: 0.8129447102546692
2023-01-22 23:40:50.693886: step: 1516/529, loss: 0.8326485753059387
2023-01-22 23:40:51.822006: step: 1520/529, loss: 0.8802800178527832
2023-01-22 23:40:52.980860: step: 1524/529, loss: 0.2800569534301758
2023-01-22 23:40:54.096538: step: 1528/529, loss: 0.20654058456420898
2023-01-22 23:40:55.225929: step: 1532/529, loss: 0.09551505744457245
2023-01-22 23:40:56.329674: step: 1536/529, loss: 0.08555688709020615
2023-01-22 23:40:57.476960: step: 1540/529, loss: 1.3692773580551147
2023-01-22 23:40:58.592090: step: 1544/529, loss: 1.1589257717132568
2023-01-22 23:40:59.706504: step: 1548/529, loss: 0.7796484231948853
2023-01-22 23:41:00.823752: step: 1552/529, loss: 0.7295999526977539
2023-01-22 23:41:01.955323: step: 1556/529, loss: 0.18316173553466797
2023-01-22 23:41:03.086113: step: 1560/529, loss: 0.6112227439880371
2023-01-22 23:41:04.224324: step: 1564/529, loss: 0.10929808765649796
2023-01-22 23:41:05.361054: step: 1568/529, loss: 6.765477180480957
2023-01-22 23:41:06.509425: step: 1572/529, loss: 1.2350817918777466
2023-01-22 23:41:07.653147: step: 1576/529, loss: 0.07628726959228516
2023-01-22 23:41:08.777550: step: 1580/529, loss: 0.8256204128265381
2023-01-22 23:41:09.925527: step: 1584/529, loss: 0.26255807280540466
2023-01-22 23:41:11.053533: step: 1588/529, loss: 0.2382659912109375
2023-01-22 23:41:12.197141: step: 1592/529, loss: 0.8648579120635986
2023-01-22 23:41:13.357438: step: 1596/529, loss: 0.6343369483947754
2023-01-22 23:41:14.499986: step: 1600/529, loss: 0.8459938764572144
2023-01-22 23:41:15.657264: step: 1604/529, loss: 0.7642489671707153
2023-01-22 23:41:16.778506: step: 1608/529, loss: 0.7206225395202637
2023-01-22 23:41:17.904113: step: 1612/529, loss: 0.5299168825149536
2023-01-22 23:41:19.067510: step: 1616/529, loss: 1.0863205194473267
2023-01-22 23:41:20.192544: step: 1620/529, loss: 0.5170079469680786
2023-01-22 23:41:21.332447: step: 1624/529, loss: 0.5441691279411316
2023-01-22 23:41:22.481647: step: 1628/529, loss: 0.06420707702636719
2023-01-22 23:41:23.641526: step: 1632/529, loss: 6.329038619995117
2023-01-22 23:41:24.749515: step: 1636/529, loss: 0.13987036049365997
2023-01-22 23:41:25.890532: step: 1640/529, loss: 0.12047194689512253
2023-01-22 23:41:26.997393: step: 1644/529, loss: 1.3959094285964966
2023-01-22 23:41:28.137819: step: 1648/529, loss: 0.1417022943496704
2023-01-22 23:41:29.254197: step: 1652/529, loss: 0.26220405101776123
2023-01-22 23:41:30.371010: step: 1656/529, loss: 0.09691682457923889
2023-01-22 23:41:31.525252: step: 1660/529, loss: 0.5304877758026123
2023-01-22 23:41:32.648416: step: 1664/529, loss: 0.8642672300338745
2023-01-22 23:41:33.766745: step: 1668/529, loss: 1.105774164199829
2023-01-22 23:41:34.907647: step: 1672/529, loss: 0.11097776889801025
2023-01-22 23:41:36.038530: step: 1676/529, loss: 0.39009782671928406
2023-01-22 23:41:37.167711: step: 1680/529, loss: 0.9966732263565063
2023-01-22 23:41:38.320263: step: 1684/529, loss: 0.3803766965866089
2023-01-22 23:41:39.474632: step: 1688/529, loss: 0.35071516036987305
2023-01-22 23:41:40.599307: step: 1692/529, loss: 1.15390145778656
2023-01-22 23:41:41.717901: step: 1696/529, loss: 1.5842915773391724
2023-01-22 23:41:42.858164: step: 1700/529, loss: 0.20530223846435547
2023-01-22 23:41:43.946285: step: 1704/529, loss: 0.41568660736083984
2023-01-22 23:41:45.115285: step: 1708/529, loss: 0.4050375819206238
2023-01-22 23:41:46.303967: step: 1712/529, loss: 0.7066041231155396
2023-01-22 23:41:47.455909: step: 1716/529, loss: 0.3591589033603668
2023-01-22 23:41:48.591357: step: 1720/529, loss: 0.1619473397731781
2023-01-22 23:41:49.742421: step: 1724/529, loss: 0.22097691893577576
2023-01-22 23:41:50.875175: step: 1728/529, loss: 0.3964705467224121
2023-01-22 23:41:52.021647: step: 1732/529, loss: 0.19676485657691956
2023-01-22 23:41:53.171736: step: 1736/529, loss: 0.7947767972946167
2023-01-22 23:41:54.283043: step: 1740/529, loss: 0.5161329507827759
2023-01-22 23:41:55.413418: step: 1744/529, loss: 0.8569895625114441
2023-01-22 23:41:56.554833: step: 1748/529, loss: 0.8217809200286865
2023-01-22 23:41:57.690460: step: 1752/529, loss: 1.4282824993133545
2023-01-22 23:41:58.843031: step: 1756/529, loss: 0.6928896903991699
2023-01-22 23:41:59.944824: step: 1760/529, loss: 0.12821082770824432
2023-01-22 23:42:01.044685: step: 1764/529, loss: 7.222170829772949
2023-01-22 23:42:02.185625: step: 1768/529, loss: 0.2352183312177658
2023-01-22 23:42:03.307990: step: 1772/529, loss: 7.337364196777344
2023-01-22 23:42:04.442606: step: 1776/529, loss: 0.10053012520074844
2023-01-22 23:42:05.620106: step: 1780/529, loss: 0.22173920273780823
2023-01-22 23:42:06.757177: step: 1784/529, loss: 0.7717358469963074
2023-01-22 23:42:07.895259: step: 1788/529, loss: 0.150108203291893
2023-01-22 23:42:09.030624: step: 1792/529, loss: 0.2151103913784027
2023-01-22 23:42:10.178907: step: 1796/529, loss: 0.27949219942092896
2023-01-22 23:42:11.308957: step: 1800/529, loss: 0.6257975101470947
2023-01-22 23:42:12.447522: step: 1804/529, loss: 0.6478987336158752
2023-01-22 23:42:13.582232: step: 1808/529, loss: 1.05632746219635
2023-01-22 23:42:14.727237: step: 1812/529, loss: 0.9121267199516296
2023-01-22 23:42:15.914219: step: 1816/529, loss: 0.17341919243335724
2023-01-22 23:42:17.045665: step: 1820/529, loss: 0.7128279209136963
2023-01-22 23:42:18.157429: step: 1824/529, loss: 0.9977483153343201
2023-01-22 23:42:19.316106: step: 1828/529, loss: 1.5038676261901855
2023-01-22 23:42:20.454056: step: 1832/529, loss: 0.9541134834289551
2023-01-22 23:42:21.618121: step: 1836/529, loss: 0.2863430380821228
2023-01-22 23:42:22.750554: step: 1840/529, loss: 0.06166362762451172
2023-01-22 23:42:23.915700: step: 1844/529, loss: 0.17570121586322784
2023-01-22 23:42:25.075256: step: 1848/529, loss: 0.4174157977104187
2023-01-22 23:42:26.240869: step: 1852/529, loss: 1.4150358438491821
2023-01-22 23:42:27.408508: step: 1856/529, loss: 0.8669883012771606
2023-01-22 23:42:28.537723: step: 1860/529, loss: 0.2999749183654785
2023-01-22 23:42:29.693636: step: 1864/529, loss: 0.9722987413406372
2023-01-22 23:42:30.835340: step: 1868/529, loss: 0.18898595869541168
2023-01-22 23:42:31.982250: step: 1872/529, loss: 0.4102143943309784
2023-01-22 23:42:33.111118: step: 1876/529, loss: 0.7225392460823059
2023-01-22 23:42:34.240184: step: 1880/529, loss: 0.6729050874710083
2023-01-22 23:42:35.384079: step: 1884/529, loss: 1.8289964199066162
2023-01-22 23:42:36.536772: step: 1888/529, loss: 0.9194282293319702
2023-01-22 23:42:37.682737: step: 1892/529, loss: 0.14319868385791779
2023-01-22 23:42:38.806515: step: 1896/529, loss: 0.5910947322845459
2023-01-22 23:42:39.959220: step: 1900/529, loss: 1.8206111192703247
2023-01-22 23:42:41.068392: step: 1904/529, loss: 0.12756066024303436
2023-01-22 23:42:42.182043: step: 1908/529, loss: 1.415897250175476
2023-01-22 23:42:43.362242: step: 1912/529, loss: 2.8653218746185303
2023-01-22 23:42:44.491952: step: 1916/529, loss: 0.8677077293395996
2023-01-22 23:42:45.651710: step: 1920/529, loss: 0.42419806122779846
2023-01-22 23:42:46.783554: step: 1924/529, loss: 0.1219908744096756
2023-01-22 23:42:47.922172: step: 1928/529, loss: 0.2571730613708496
2023-01-22 23:42:49.039763: step: 1932/529, loss: 0.7489161491394043
2023-01-22 23:42:50.181801: step: 1936/529, loss: 0.18201252818107605
2023-01-22 23:42:51.335675: step: 1940/529, loss: 3.432046413421631
2023-01-22 23:42:52.488904: step: 1944/529, loss: 0.17417903244495392
2023-01-22 23:42:53.628883: step: 1948/529, loss: 0.45939940214157104
2023-01-22 23:42:54.779353: step: 1952/529, loss: 1.9692161083221436
2023-01-22 23:42:55.919279: step: 1956/529, loss: 0.1637752503156662
2023-01-22 23:42:57.021850: step: 1960/529, loss: 0.2635403871536255
2023-01-22 23:42:58.155456: step: 1964/529, loss: 6.100759506225586
2023-01-22 23:42:59.294559: step: 1968/529, loss: 0.6198025345802307
2023-01-22 23:43:00.428597: step: 1972/529, loss: 0.23389548063278198
2023-01-22 23:43:01.581384: step: 1976/529, loss: 0.2064833641052246
2023-01-22 23:43:02.744309: step: 1980/529, loss: 0.16781291365623474
2023-01-22 23:43:03.877481: step: 1984/529, loss: 0.2910175323486328
2023-01-22 23:43:05.000087: step: 1988/529, loss: 7.207370281219482
2023-01-22 23:43:06.152455: step: 1992/529, loss: 0.35911956429481506
2023-01-22 23:43:07.288404: step: 1996/529, loss: 0.27823057770729065
2023-01-22 23:43:08.437526: step: 2000/529, loss: 0.3757549524307251
2023-01-22 23:43:09.616329: step: 2004/529, loss: 1.7029109001159668
2023-01-22 23:43:10.771768: step: 2008/529, loss: 0.2338418960571289
2023-01-22 23:43:11.918947: step: 2012/529, loss: 0.5623645782470703
2023-01-22 23:43:13.105558: step: 2016/529, loss: 0.3921836018562317
2023-01-22 23:43:14.242860: step: 2020/529, loss: 0.2561310827732086
2023-01-22 23:43:15.374699: step: 2024/529, loss: 1.0950664281845093
2023-01-22 23:43:16.529870: step: 2028/529, loss: 0.35538214445114136
2023-01-22 23:43:17.688146: step: 2032/529, loss: 0.4026249051094055
2023-01-22 23:43:18.820665: step: 2036/529, loss: 0.156175896525383
2023-01-22 23:43:19.972764: step: 2040/529, loss: 1.4233074188232422
2023-01-22 23:43:21.112121: step: 2044/529, loss: 0.4461545944213867
2023-01-22 23:43:22.241980: step: 2048/529, loss: 0.1356600821018219
2023-01-22 23:43:23.395982: step: 2052/529, loss: 0.618218183517456
2023-01-22 23:43:24.548230: step: 2056/529, loss: 1.7878608703613281
2023-01-22 23:43:25.664934: step: 2060/529, loss: 0.48725080490112305
2023-01-22 23:43:26.773110: step: 2064/529, loss: 0.09457807242870331
2023-01-22 23:43:27.900045: step: 2068/529, loss: 0.21639785170555115
2023-01-22 23:43:29.036430: step: 2072/529, loss: 0.37085646390914917
2023-01-22 23:43:30.171418: step: 2076/529, loss: 0.17226460576057434
2023-01-22 23:43:31.299247: step: 2080/529, loss: 0.736858069896698
2023-01-22 23:43:32.446942: step: 2084/529, loss: 1.7456613779067993
2023-01-22 23:43:33.594676: step: 2088/529, loss: 0.16766414046287537
2023-01-22 23:43:34.745577: step: 2092/529, loss: 0.11730727553367615
2023-01-22 23:43:35.889523: step: 2096/529, loss: 0.34722986817359924
2023-01-22 23:43:37.025017: step: 2100/529, loss: 0.12117743492126465
2023-01-22 23:43:38.139286: step: 2104/529, loss: 0.3582167625427246
2023-01-22 23:43:39.268996: step: 2108/529, loss: 0.20710162818431854
2023-01-22 23:43:40.399166: step: 2112/529, loss: 0.06176753342151642
2023-01-22 23:43:41.528881: step: 2116/529, loss: 0.7002752423286438
==================================================
Loss: 0.846
--------------------
Dev: {'event': {'p': 0.5645677694770544, 'r': 0.7043941411451398, 'f1': 0.6267772511848342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5636722606120435, 'r': 0.6616454229432214, 'f1': 0.6087420042643923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5135135135135135, 'r': 0.7037037037037037, 'f1': 0.59375}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.6086956521739131, 'r': 0.4444444444444444, 'f1': 0.5137614678899082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.5, 'r': 0.4444444444444444, 'f1': 0.47058823529411764}, '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': 0.5645677694770544, 'r': 0.7043941411451398, 'f1': 0.6267772511848342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5636722606120435, 'r': 0.6616454229432214, 'f1': 0.6087420042643923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5135135135135135, 'r': 0.7037037037037037, 'f1': 0.59375}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5645677694770544, 'r': 0.7043941411451398, 'f1': 0.6267772511848342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5636722606120435, 'r': 0.6616454229432214, 'f1': 0.6087420042643923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6086956521739131, 'r': 0.4444444444444444, 'f1': 0.5137614678899082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5645677694770544, 'r': 0.7043941411451398, 'f1': 0.6267772511848342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5636722606120435, 'r': 0.6616454229432214, 'f1': 0.6087420042643923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.5, 'r': 0.4444444444444444, 'f1': 0.47058823529411764}, '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 23:44:46.020445: step: 4/529, loss: 0.16011753678321838
2023-01-22 23:44:47.178551: step: 8/529, loss: 0.3136522173881531
2023-01-22 23:44:48.306986: step: 12/529, loss: 0.5542739033699036
2023-01-22 23:44:49.465985: step: 16/529, loss: 0.12885847687721252
2023-01-22 23:44:50.621661: step: 20/529, loss: 0.17488440871238708
2023-01-22 23:44:51.740709: step: 24/529, loss: 0.16168662905693054
2023-01-22 23:44:52.852113: step: 28/529, loss: 0.12315917015075684
2023-01-22 23:44:53.984138: step: 32/529, loss: 0.6722848415374756
2023-01-22 23:44:55.102164: step: 36/529, loss: 0.5296027064323425
2023-01-22 23:44:56.241903: step: 40/529, loss: 0.2444693148136139
2023-01-22 23:44:57.371881: step: 44/529, loss: 0.6960229277610779
2023-01-22 23:44:58.551614: step: 48/529, loss: 1.7689166069030762
2023-01-22 23:44:59.674664: step: 52/529, loss: 0.17338839173316956
2023-01-22 23:45:00.802766: step: 56/529, loss: 0.11341724544763565
2023-01-22 23:45:01.925208: step: 60/529, loss: 0.13741794228553772
2023-01-22 23:45:03.096363: step: 64/529, loss: 0.13269048929214478
2023-01-22 23:45:04.273517: step: 68/529, loss: 0.17899766564369202
2023-01-22 23:45:05.398260: step: 72/529, loss: 0.6834906339645386
2023-01-22 23:45:06.552425: step: 76/529, loss: 0.23811855912208557
2023-01-22 23:45:07.694260: step: 80/529, loss: 0.21603471040725708
2023-01-22 23:45:08.820469: step: 84/529, loss: 2.2758147716522217
2023-01-22 23:45:09.960271: step: 88/529, loss: 0.26220351457595825
2023-01-22 23:45:11.083736: step: 92/529, loss: 0.16112929582595825
2023-01-22 23:45:12.231362: step: 96/529, loss: 0.12959790229797363
2023-01-22 23:45:13.408635: step: 100/529, loss: 0.7131268978118896
2023-01-22 23:45:14.568326: step: 104/529, loss: 0.23847992718219757
2023-01-22 23:45:15.703711: step: 108/529, loss: 1.1560603380203247
2023-01-22 23:45:16.853316: step: 112/529, loss: 0.32345473766326904
2023-01-22 23:45:18.016231: step: 116/529, loss: 0.17514057457447052
2023-01-22 23:45:19.178082: step: 120/529, loss: 0.7883058786392212
2023-01-22 23:45:20.303609: step: 124/529, loss: 0.3674681782722473
2023-01-22 23:45:21.469927: step: 128/529, loss: 0.9620416760444641
2023-01-22 23:45:22.628671: step: 132/529, loss: 1.2430660724639893
2023-01-22 23:45:23.761162: step: 136/529, loss: 6.324300289154053
2023-01-22 23:45:24.906184: step: 140/529, loss: 0.22229023277759552
2023-01-22 23:45:26.056906: step: 144/529, loss: 0.7625331878662109
2023-01-22 23:45:27.202771: step: 148/529, loss: 0.3625265955924988
2023-01-22 23:45:28.356801: step: 152/529, loss: 0.1423037052154541
2023-01-22 23:45:29.509305: step: 156/529, loss: 0.4354117512702942
2023-01-22 23:45:30.678823: step: 160/529, loss: 0.7554001212120056
2023-01-22 23:45:31.819406: step: 164/529, loss: 0.8097216486930847
2023-01-22 23:45:32.971509: step: 168/529, loss: 0.33486807346343994
2023-01-22 23:45:34.111722: step: 172/529, loss: 0.2294527143239975
2023-01-22 23:45:35.263508: step: 176/529, loss: 0.12679247558116913
2023-01-22 23:45:36.392194: step: 180/529, loss: 0.08267946541309357
2023-01-22 23:45:37.556685: step: 184/529, loss: 0.225310280919075
2023-01-22 23:45:38.712046: step: 188/529, loss: 0.3811991810798645
2023-01-22 23:45:39.873487: step: 192/529, loss: 0.25362318754196167
2023-01-22 23:45:41.004002: step: 196/529, loss: 1.0539844036102295
2023-01-22 23:45:42.156950: step: 200/529, loss: 0.4539848566055298
2023-01-22 23:45:43.328910: step: 204/529, loss: 0.17168235778808594
2023-01-22 23:45:44.482579: step: 208/529, loss: 0.6570345163345337
2023-01-22 23:45:45.603300: step: 212/529, loss: 1.1744686365127563
2023-01-22 23:45:46.735962: step: 216/529, loss: 0.29787909984588623
2023-01-22 23:45:47.879412: step: 220/529, loss: 0.20865727961063385
2023-01-22 23:45:49.029336: step: 224/529, loss: 0.19810311496257782
2023-01-22 23:45:50.176961: step: 228/529, loss: 0.18043336272239685
2023-01-22 23:45:51.338340: step: 232/529, loss: 1.6988426446914673
2023-01-22 23:45:52.508290: step: 236/529, loss: 0.3392007350921631
2023-01-22 23:45:53.663525: step: 240/529, loss: 0.3021160364151001
2023-01-22 23:45:54.799118: step: 244/529, loss: 1.0553247928619385
2023-01-22 23:45:55.971770: step: 248/529, loss: 0.28210583329200745
2023-01-22 23:45:57.115487: step: 252/529, loss: 1.4673709869384766
2023-01-22 23:45:58.270313: step: 256/529, loss: 0.29661792516708374
2023-01-22 23:45:59.415216: step: 260/529, loss: 0.2706844210624695
2023-01-22 23:46:00.519252: step: 264/529, loss: 0.7277727127075195
2023-01-22 23:46:01.646372: step: 268/529, loss: 0.6652582287788391
2023-01-22 23:46:02.815846: step: 272/529, loss: 6.562233924865723
2023-01-22 23:46:03.952191: step: 276/529, loss: 1.0673260688781738
2023-01-22 23:46:05.102464: step: 280/529, loss: 0.10092764347791672
2023-01-22 23:46:06.280008: step: 284/529, loss: 0.4907453656196594
2023-01-22 23:46:07.413418: step: 288/529, loss: 0.09231443703174591
2023-01-22 23:46:08.549372: step: 292/529, loss: 1.4154690504074097
2023-01-22 23:46:09.687724: step: 296/529, loss: 0.11383305490016937
2023-01-22 23:46:10.815497: step: 300/529, loss: 1.0224688053131104
2023-01-22 23:46:11.962955: step: 304/529, loss: 0.1355007290840149
2023-01-22 23:46:13.096652: step: 308/529, loss: 0.682678759098053
2023-01-22 23:46:14.227538: step: 312/529, loss: 1.8023496866226196
2023-01-22 23:46:15.358190: step: 316/529, loss: 0.3560555577278137
2023-01-22 23:46:16.489817: step: 320/529, loss: 0.1748853325843811
2023-01-22 23:46:17.634293: step: 324/529, loss: 0.6619178056716919
2023-01-22 23:46:18.773678: step: 328/529, loss: 0.36525458097457886
2023-01-22 23:46:19.936414: step: 332/529, loss: 1.289191484451294
2023-01-22 23:46:21.077219: step: 336/529, loss: 0.14037008583545685
2023-01-22 23:46:22.226895: step: 340/529, loss: 7.26772403717041
2023-01-22 23:46:23.376768: step: 344/529, loss: 2.330707550048828
2023-01-22 23:46:24.531722: step: 348/529, loss: 1.4237453937530518
2023-01-22 23:46:25.647979: step: 352/529, loss: 0.3275485038757324
2023-01-22 23:46:26.786916: step: 356/529, loss: 0.26687249541282654
2023-01-22 23:46:27.920396: step: 360/529, loss: 0.6357746124267578
2023-01-22 23:46:29.061484: step: 364/529, loss: 0.17802830040454865
2023-01-22 23:46:30.177060: step: 368/529, loss: 0.7167764902114868
2023-01-22 23:46:31.339659: step: 372/529, loss: 0.24290715157985687
2023-01-22 23:46:32.526122: step: 376/529, loss: 0.28208112716674805
2023-01-22 23:46:33.651424: step: 380/529, loss: 0.3086233139038086
2023-01-22 23:46:34.810434: step: 384/529, loss: 0.7601917386054993
2023-01-22 23:46:35.948624: step: 388/529, loss: 0.3973931074142456
2023-01-22 23:46:37.092426: step: 392/529, loss: 0.2916305661201477
2023-01-22 23:46:38.245694: step: 396/529, loss: 0.18600140511989594
2023-01-22 23:46:39.417473: step: 400/529, loss: 0.554033100605011
2023-01-22 23:46:40.577877: step: 404/529, loss: 0.43686628341674805
2023-01-22 23:46:41.706080: step: 408/529, loss: 0.8465619683265686
2023-01-22 23:46:42.872143: step: 412/529, loss: 1.2262346744537354
2023-01-22 23:46:44.017528: step: 416/529, loss: 0.2643786370754242
2023-01-22 23:46:45.152472: step: 420/529, loss: 1.0234525203704834
2023-01-22 23:46:46.312059: step: 424/529, loss: 0.35052046179771423
2023-01-22 23:46:47.471241: step: 428/529, loss: 1.3906512260437012
2023-01-22 23:46:48.612185: step: 432/529, loss: 0.5203295946121216
2023-01-22 23:46:49.727658: step: 436/529, loss: 0.4099210798740387
2023-01-22 23:46:50.842168: step: 440/529, loss: 0.018064402043819427
2023-01-22 23:46:51.968305: step: 444/529, loss: 0.252826988697052
2023-01-22 23:46:53.098104: step: 448/529, loss: 0.159762442111969
2023-01-22 23:46:54.250754: step: 452/529, loss: 0.12250981479883194
2023-01-22 23:46:55.393247: step: 456/529, loss: 0.21491505205631256
2023-01-22 23:46:56.528944: step: 460/529, loss: 0.22326365113258362
2023-01-22 23:46:57.678503: step: 464/529, loss: 1.591773271560669
2023-01-22 23:46:58.856933: step: 468/529, loss: 0.6827014684677124
2023-01-22 23:46:59.998215: step: 472/529, loss: 0.3413742780685425
2023-01-22 23:47:01.139532: step: 476/529, loss: 0.08217153698205948
2023-01-22 23:47:02.311770: step: 480/529, loss: 0.17546749114990234
2023-01-22 23:47:03.467995: step: 484/529, loss: 1.4722208976745605
2023-01-22 23:47:04.620750: step: 488/529, loss: 0.3064320981502533
2023-01-22 23:47:05.762182: step: 492/529, loss: 0.11648903787136078
2023-01-22 23:47:06.924287: step: 496/529, loss: 0.6317901611328125
2023-01-22 23:47:08.080309: step: 500/529, loss: 0.5103319883346558
2023-01-22 23:47:09.205029: step: 504/529, loss: 0.673570454120636
2023-01-22 23:47:10.314533: step: 508/529, loss: 0.6077795028686523
2023-01-22 23:47:11.428600: step: 512/529, loss: 0.10362100601196289
2023-01-22 23:47:12.550212: step: 516/529, loss: 0.1989048421382904
2023-01-22 23:47:13.679569: step: 520/529, loss: 0.15940414369106293
2023-01-22 23:47:14.819511: step: 524/529, loss: 0.49244728684425354
2023-01-22 23:47:15.945495: step: 528/529, loss: 0.11199302226305008
2023-01-22 23:47:17.107099: step: 532/529, loss: 0.35654306411743164
2023-01-22 23:47:18.249888: step: 536/529, loss: 0.38375359773635864
2023-01-22 23:47:19.357218: step: 540/529, loss: 0.2046581357717514
2023-01-22 23:47:20.521449: step: 544/529, loss: 0.2462368756532669
2023-01-22 23:47:21.647858: step: 548/529, loss: 0.730583667755127
2023-01-22 23:47:22.792941: step: 552/529, loss: 1.0266247987747192
2023-01-22 23:47:23.936005: step: 556/529, loss: 0.784329891204834
2023-01-22 23:47:25.055348: step: 560/529, loss: 0.9169520735740662
2023-01-22 23:47:26.214540: step: 564/529, loss: 0.5217580795288086
2023-01-22 23:47:27.360793: step: 568/529, loss: 1.5671823024749756
2023-01-22 23:47:28.525295: step: 572/529, loss: 0.19533872604370117
2023-01-22 23:47:29.646144: step: 576/529, loss: 0.5604658722877502
2023-01-22 23:47:30.772547: step: 580/529, loss: 0.11667013168334961
2023-01-22 23:47:31.918551: step: 584/529, loss: 0.5202959775924683
2023-01-22 23:47:33.059555: step: 588/529, loss: 0.3391176164150238
2023-01-22 23:47:34.192682: step: 592/529, loss: 0.8964076638221741
2023-01-22 23:47:35.309773: step: 596/529, loss: 0.657941997051239
2023-01-22 23:47:36.467540: step: 600/529, loss: 0.588658332824707
2023-01-22 23:47:37.615349: step: 604/529, loss: 0.21640311181545258
2023-01-22 23:47:38.770985: step: 608/529, loss: 0.20219768583774567
2023-01-22 23:47:39.920183: step: 612/529, loss: 0.29336604475975037
2023-01-22 23:47:41.056531: step: 616/529, loss: 0.2765015661716461
2023-01-22 23:47:42.199120: step: 620/529, loss: 0.5687368512153625
2023-01-22 23:47:43.339071: step: 624/529, loss: 0.15059643983840942
2023-01-22 23:47:44.507414: step: 628/529, loss: 0.5599428415298462
2023-01-22 23:47:45.615690: step: 632/529, loss: 0.7464699745178223
2023-01-22 23:47:46.751197: step: 636/529, loss: 1.5670126676559448
2023-01-22 23:47:47.878112: step: 640/529, loss: 0.05278778076171875
2023-01-22 23:47:49.035657: step: 644/529, loss: 0.2779834270477295
2023-01-22 23:47:50.185098: step: 648/529, loss: 0.18645945191383362
2023-01-22 23:47:51.311859: step: 652/529, loss: 0.7625888586044312
2023-01-22 23:47:52.455466: step: 656/529, loss: 0.2967225909233093
2023-01-22 23:47:53.588932: step: 660/529, loss: 0.21448002755641937
2023-01-22 23:47:54.714776: step: 664/529, loss: 0.2279062271118164
2023-01-22 23:47:55.895806: step: 668/529, loss: 0.12128783017396927
2023-01-22 23:47:57.046313: step: 672/529, loss: 1.1565241813659668
2023-01-22 23:47:58.170453: step: 676/529, loss: 0.23948058485984802
2023-01-22 23:47:59.298423: step: 680/529, loss: 0.30275630950927734
2023-01-22 23:48:00.452675: step: 684/529, loss: 0.19882088899612427
2023-01-22 23:48:01.580391: step: 688/529, loss: 0.7269073724746704
2023-01-22 23:48:02.721496: step: 692/529, loss: 0.098810575902462
2023-01-22 23:48:03.834293: step: 696/529, loss: 0.5192068815231323
2023-01-22 23:48:04.997205: step: 700/529, loss: 0.8430692553520203
2023-01-22 23:48:06.157352: step: 704/529, loss: 0.4456140995025635
2023-01-22 23:48:07.290937: step: 708/529, loss: 0.22368068993091583
2023-01-22 23:48:08.437761: step: 712/529, loss: 0.3451046049594879
2023-01-22 23:48:09.557249: step: 716/529, loss: 0.33338505029678345
2023-01-22 23:48:10.655211: step: 720/529, loss: 0.7560536861419678
2023-01-22 23:48:11.784478: step: 724/529, loss: 0.7425456047058105
2023-01-22 23:48:12.912451: step: 728/529, loss: 0.689315676689148
2023-01-22 23:48:14.059461: step: 732/529, loss: 0.31961071491241455
2023-01-22 23:48:15.170344: step: 736/529, loss: 0.08549609035253525
2023-01-22 23:48:16.295608: step: 740/529, loss: 0.4769206643104553
2023-01-22 23:48:17.415232: step: 744/529, loss: 0.1587519347667694
2023-01-22 23:48:18.543053: step: 748/529, loss: 0.28562304377555847
2023-01-22 23:48:19.693735: step: 752/529, loss: 0.4195876121520996
2023-01-22 23:48:20.849599: step: 756/529, loss: 0.13163384795188904
2023-01-22 23:48:21.978379: step: 760/529, loss: 0.07811227440834045
2023-01-22 23:48:23.115803: step: 764/529, loss: 0.23471862077713013
2023-01-22 23:48:24.226041: step: 768/529, loss: 0.503345787525177
2023-01-22 23:48:25.324641: step: 772/529, loss: 0.1733681708574295
2023-01-22 23:48:26.466012: step: 776/529, loss: 0.8007156252861023
2023-01-22 23:48:27.570801: step: 780/529, loss: 0.7773919105529785
2023-01-22 23:48:28.711102: step: 784/529, loss: 0.09906230121850967
2023-01-22 23:48:29.820101: step: 788/529, loss: 0.0492280013859272
2023-01-22 23:48:30.993223: step: 792/529, loss: 0.16614651679992676
2023-01-22 23:48:32.144943: step: 796/529, loss: 0.12801270186901093
2023-01-22 23:48:33.258420: step: 800/529, loss: 0.17420612275600433
2023-01-22 23:48:34.400319: step: 804/529, loss: 0.9932152628898621
2023-01-22 23:48:35.518709: step: 808/529, loss: 0.7149071097373962
2023-01-22 23:48:36.675825: step: 812/529, loss: 0.24240341782569885
2023-01-22 23:48:37.825039: step: 816/529, loss: 0.8995043635368347
2023-01-22 23:48:38.962164: step: 820/529, loss: 0.4197057783603668
2023-01-22 23:48:40.097601: step: 824/529, loss: 0.37795573472976685
2023-01-22 23:48:41.250609: step: 828/529, loss: 0.5616082549095154
2023-01-22 23:48:42.396447: step: 832/529, loss: 0.662162721157074
2023-01-22 23:48:43.533312: step: 836/529, loss: 0.19101658463478088
2023-01-22 23:48:44.677627: step: 840/529, loss: 0.10286326706409454
2023-01-22 23:48:45.803990: step: 844/529, loss: 0.3165660798549652
2023-01-22 23:48:46.943669: step: 848/529, loss: 0.15785284340381622
2023-01-22 23:48:48.074737: step: 852/529, loss: 0.07431665062904358
2023-01-22 23:48:49.179347: step: 856/529, loss: 0.23629015684127808
2023-01-22 23:48:50.307015: step: 860/529, loss: 0.21047420799732208
2023-01-22 23:48:51.434809: step: 864/529, loss: 0.08362946659326553
2023-01-22 23:48:52.563780: step: 868/529, loss: 0.12692776322364807
2023-01-22 23:48:53.684413: step: 872/529, loss: 0.09655408561229706
2023-01-22 23:48:54.812005: step: 876/529, loss: 0.4454402029514313
2023-01-22 23:48:55.954307: step: 880/529, loss: 0.25781354308128357
2023-01-22 23:48:57.110190: step: 884/529, loss: 0.8869230151176453
2023-01-22 23:48:58.219002: step: 888/529, loss: 0.05918631702661514
2023-01-22 23:48:59.326364: step: 892/529, loss: 0.5052001476287842
2023-01-22 23:49:00.504327: step: 896/529, loss: 0.9153575301170349
2023-01-22 23:49:01.638142: step: 900/529, loss: 0.14046001434326172
2023-01-22 23:49:02.765610: step: 904/529, loss: 0.09355268627405167
2023-01-22 23:49:03.928531: step: 908/529, loss: 1.9980554580688477
2023-01-22 23:49:05.069601: step: 912/529, loss: 0.488818883895874
2023-01-22 23:49:06.204439: step: 916/529, loss: 0.13364887237548828
2023-01-22 23:49:07.338069: step: 920/529, loss: 0.8750467896461487
2023-01-22 23:49:08.482258: step: 924/529, loss: 0.5229588747024536
2023-01-22 23:49:09.595803: step: 928/529, loss: 0.6437985301017761
2023-01-22 23:49:10.721784: step: 932/529, loss: 0.17561788856983185
2023-01-22 23:49:11.884675: step: 936/529, loss: 1.4316258430480957
2023-01-22 23:49:13.031118: step: 940/529, loss: 0.09925102442502975
2023-01-22 23:49:14.164085: step: 944/529, loss: 0.13579416275024414
2023-01-22 23:49:15.292107: step: 948/529, loss: 0.21429473161697388
2023-01-22 23:49:16.425963: step: 952/529, loss: 0.2562198340892792
2023-01-22 23:49:17.545956: step: 956/529, loss: 1.0596842765808105
2023-01-22 23:49:18.699055: step: 960/529, loss: 0.26569002866744995
2023-01-22 23:49:19.846205: step: 964/529, loss: 0.17212048172950745
2023-01-22 23:49:20.983435: step: 968/529, loss: 0.3943077027797699
2023-01-22 23:49:22.131068: step: 972/529, loss: 0.9857510328292847
2023-01-22 23:49:23.276736: step: 976/529, loss: 0.8594427108764648
2023-01-22 23:49:24.407837: step: 980/529, loss: 0.75419682264328
2023-01-22 23:49:25.529688: step: 984/529, loss: 2.1439573764801025
2023-01-22 23:49:26.657284: step: 988/529, loss: 0.22956937551498413
2023-01-22 23:49:27.788097: step: 992/529, loss: 0.9550902247428894
2023-01-22 23:49:28.971760: step: 996/529, loss: 0.23789557814598083
2023-01-22 23:49:30.102627: step: 1000/529, loss: 0.7501827478408813
2023-01-22 23:49:31.242109: step: 1004/529, loss: 1.0087507963180542
2023-01-22 23:49:32.370228: step: 1008/529, loss: 0.166591078042984
2023-01-22 23:49:33.504469: step: 1012/529, loss: 0.14258627593517303
2023-01-22 23:49:34.641436: step: 1016/529, loss: 0.3370937407016754
2023-01-22 23:49:35.812695: step: 1020/529, loss: 0.13173122704029083
2023-01-22 23:49:36.926214: step: 1024/529, loss: 0.6296415328979492
2023-01-22 23:49:38.038043: step: 1028/529, loss: 0.02834026701748371
2023-01-22 23:49:39.254813: step: 1032/529, loss: 0.19032001495361328
2023-01-22 23:49:40.383933: step: 1036/529, loss: 0.06784754246473312
2023-01-22 23:49:41.542326: step: 1040/529, loss: 0.35349151492118835
2023-01-22 23:49:42.677413: step: 1044/529, loss: 0.4109952747821808
2023-01-22 23:49:43.809499: step: 1048/529, loss: 0.3357512354850769
2023-01-22 23:49:44.924102: step: 1052/529, loss: 1.1619939804077148
2023-01-22 23:49:46.063180: step: 1056/529, loss: 0.13449373841285706
2023-01-22 23:49:47.227893: step: 1060/529, loss: 0.771314263343811
2023-01-22 23:49:48.386835: step: 1064/529, loss: 1.1261049509048462
2023-01-22 23:49:49.527066: step: 1068/529, loss: 0.6880071759223938
2023-01-22 23:49:50.652989: step: 1072/529, loss: 0.3649477958679199
2023-01-22 23:49:51.810638: step: 1076/529, loss: 1.7755614519119263
2023-01-22 23:49:52.947250: step: 1080/529, loss: 0.1534440666437149
2023-01-22 23:49:54.116186: step: 1084/529, loss: 0.4672432839870453
2023-01-22 23:49:55.253715: step: 1088/529, loss: 0.2176845520734787
2023-01-22 23:49:56.412922: step: 1092/529, loss: 0.23515939712524414
2023-01-22 23:49:57.541663: step: 1096/529, loss: 0.3562561273574829
2023-01-22 23:49:58.647198: step: 1100/529, loss: 0.18892565369606018
2023-01-22 23:49:59.823044: step: 1104/529, loss: 0.24174949526786804
2023-01-22 23:50:00.926023: step: 1108/529, loss: 0.03390555456280708
2023-01-22 23:50:02.039184: step: 1112/529, loss: 0.17155544459819794
2023-01-22 23:50:03.168726: step: 1116/529, loss: 1.00954270362854
2023-01-22 23:50:04.329482: step: 1120/529, loss: 0.2654804289340973
2023-01-22 23:50:05.444189: step: 1124/529, loss: 0.23189465701580048
2023-01-22 23:50:06.559479: step: 1128/529, loss: 0.5436960458755493
2023-01-22 23:50:07.687423: step: 1132/529, loss: 0.30535823106765747
2023-01-22 23:50:08.805286: step: 1136/529, loss: 0.13110123574733734
2023-01-22 23:50:09.944514: step: 1140/529, loss: 0.059475041925907135
2023-01-22 23:50:11.076605: step: 1144/529, loss: 0.14658494293689728
2023-01-22 23:50:12.186780: step: 1148/529, loss: 0.1200718879699707
2023-01-22 23:50:13.330796: step: 1152/529, loss: 0.3168865144252777
2023-01-22 23:50:14.479487: step: 1156/529, loss: 0.6561247110366821
2023-01-22 23:50:15.616542: step: 1160/529, loss: 0.302634060382843
2023-01-22 23:50:16.772578: step: 1164/529, loss: 0.19865378737449646
2023-01-22 23:50:17.917785: step: 1168/529, loss: 0.4789091944694519
2023-01-22 23:50:19.014188: step: 1172/529, loss: 0.8969265222549438
2023-01-22 23:50:20.165222: step: 1176/529, loss: 1.3511192798614502
2023-01-22 23:50:21.276276: step: 1180/529, loss: 0.03264591842889786
2023-01-22 23:50:22.419813: step: 1184/529, loss: 0.25470343232154846
2023-01-22 23:50:23.545526: step: 1188/529, loss: 7.005441188812256
2023-01-22 23:50:24.683154: step: 1192/529, loss: 1.1059383153915405
2023-01-22 23:50:25.812121: step: 1196/529, loss: 0.22476397454738617
2023-01-22 23:50:26.953182: step: 1200/529, loss: 0.8762972354888916
2023-01-22 23:50:28.082397: step: 1204/529, loss: 0.23472939431667328
2023-01-22 23:50:29.220972: step: 1208/529, loss: 0.2966242730617523
2023-01-22 23:50:30.337725: step: 1212/529, loss: 0.22277450561523438
2023-01-22 23:50:31.446603: step: 1216/529, loss: 0.6476133465766907
2023-01-22 23:50:32.614105: step: 1220/529, loss: 0.16679368913173676
2023-01-22 23:50:33.742302: step: 1224/529, loss: 0.2518458962440491
2023-01-22 23:50:34.860986: step: 1228/529, loss: 0.5916452407836914
2023-01-22 23:50:35.978460: step: 1232/529, loss: 0.37040069699287415
2023-01-22 23:50:37.114806: step: 1236/529, loss: 0.1746373176574707
2023-01-22 23:50:38.242820: step: 1240/529, loss: 0.8113880157470703
2023-01-22 23:50:39.381681: step: 1244/529, loss: 0.3751646876335144
2023-01-22 23:50:40.517231: step: 1248/529, loss: 0.5634957551956177
2023-01-22 23:50:41.650299: step: 1252/529, loss: 0.6778720617294312
2023-01-22 23:50:42.797423: step: 1256/529, loss: 0.19265109300613403
2023-01-22 23:50:43.926495: step: 1260/529, loss: 0.18457737565040588
2023-01-22 23:50:45.111016: step: 1264/529, loss: 0.3128463625907898
2023-01-22 23:50:46.284898: step: 1268/529, loss: 0.1766294538974762
2023-01-22 23:50:47.424573: step: 1272/529, loss: 0.27493372559547424
2023-01-22 23:50:48.557026: step: 1276/529, loss: 0.5111462473869324
2023-01-22 23:50:49.693141: step: 1280/529, loss: 0.4772043228149414
2023-01-22 23:50:50.806354: step: 1284/529, loss: 0.10342197865247726
2023-01-22 23:50:51.966135: step: 1288/529, loss: 0.2782687246799469
2023-01-22 23:50:53.107391: step: 1292/529, loss: 0.8069081902503967
2023-01-22 23:50:54.251090: step: 1296/529, loss: 1.9833240509033203
2023-01-22 23:50:55.400903: step: 1300/529, loss: 0.049399662762880325
2023-01-22 23:50:56.568633: step: 1304/529, loss: 0.3477020263671875
2023-01-22 23:50:57.706860: step: 1308/529, loss: 0.5692951083183289
2023-01-22 23:50:58.871237: step: 1312/529, loss: 6.946808338165283
2023-01-22 23:51:00.013505: step: 1316/529, loss: 0.8236302137374878
2023-01-22 23:51:01.152846: step: 1320/529, loss: 0.35909515619277954
2023-01-22 23:51:02.287899: step: 1324/529, loss: 0.1959819793701172
2023-01-22 23:51:03.440568: step: 1328/529, loss: 0.7148933410644531
2023-01-22 23:51:04.583075: step: 1332/529, loss: 0.3113003969192505
2023-01-22 23:51:05.775908: step: 1336/529, loss: 0.12670226395130157
2023-01-22 23:51:06.936766: step: 1340/529, loss: 0.24998851120471954
2023-01-22 23:51:08.070182: step: 1344/529, loss: 1.0941404104232788
2023-01-22 23:51:09.194904: step: 1348/529, loss: 0.8368428349494934
2023-01-22 23:51:10.348633: step: 1352/529, loss: 0.5432189702987671
2023-01-22 23:51:11.511084: step: 1356/529, loss: 1.8350986242294312
2023-01-22 23:51:12.628169: step: 1360/529, loss: 0.18263152241706848
2023-01-22 23:51:13.751889: step: 1364/529, loss: 0.06184806674718857
2023-01-22 23:51:14.868502: step: 1368/529, loss: 1.4730383157730103
2023-01-22 23:51:15.979347: step: 1372/529, loss: 0.1663825958967209
2023-01-22 23:51:17.117292: step: 1376/529, loss: 0.08552595973014832
2023-01-22 23:51:18.245901: step: 1380/529, loss: 0.8457716703414917
2023-01-22 23:51:19.368000: step: 1384/529, loss: 0.8865984082221985
2023-01-22 23:51:20.500063: step: 1388/529, loss: 0.9729822278022766
2023-01-22 23:51:21.616370: step: 1392/529, loss: 0.2225530594587326
2023-01-22 23:51:22.770509: step: 1396/529, loss: 0.23109284043312073
2023-01-22 23:51:23.904576: step: 1400/529, loss: 0.23125630617141724
2023-01-22 23:51:25.046433: step: 1404/529, loss: 0.22260676324367523
2023-01-22 23:51:26.188750: step: 1408/529, loss: 0.2076948583126068
2023-01-22 23:51:27.336835: step: 1412/529, loss: 0.21892911195755005
2023-01-22 23:51:28.499541: step: 1416/529, loss: 1.2129038572311401
2023-01-22 23:51:29.627429: step: 1420/529, loss: 0.14834395051002502
2023-01-22 23:51:30.770807: step: 1424/529, loss: 0.23918914794921875
2023-01-22 23:51:31.886696: step: 1428/529, loss: 0.35814207792282104
2023-01-22 23:51:33.003410: step: 1432/529, loss: 0.8250369429588318
2023-01-22 23:51:34.177800: step: 1436/529, loss: 3.754572868347168
2023-01-22 23:51:35.297698: step: 1440/529, loss: 7.024494171142578
2023-01-22 23:51:36.478888: step: 1444/529, loss: 1.5178947448730469
2023-01-22 23:51:37.579793: step: 1448/529, loss: 0.0458315871655941
2023-01-22 23:51:38.753428: step: 1452/529, loss: 0.22355583310127258
2023-01-22 23:51:39.870142: step: 1456/529, loss: 0.764581561088562
2023-01-22 23:51:41.056994: step: 1460/529, loss: 2.560023307800293
2023-01-22 23:51:42.175686: step: 1464/529, loss: 2.1982405185699463
2023-01-22 23:51:43.342375: step: 1468/529, loss: 0.18284812569618225
2023-01-22 23:51:44.460442: step: 1472/529, loss: 0.22098904848098755
2023-01-22 23:51:45.567555: step: 1476/529, loss: 0.3310770094394684
2023-01-22 23:51:46.737874: step: 1480/529, loss: 0.21488434076309204
2023-01-22 23:51:47.859705: step: 1484/529, loss: 0.24475297331809998
2023-01-22 23:51:49.000594: step: 1488/529, loss: 0.7137027382850647
2023-01-22 23:51:50.129030: step: 1492/529, loss: 0.3269401788711548
2023-01-22 23:51:51.240843: step: 1496/529, loss: 0.2582850456237793
2023-01-22 23:51:52.386033: step: 1500/529, loss: 0.08873625099658966
2023-01-22 23:51:53.516367: step: 1504/529, loss: 0.517112135887146
2023-01-22 23:51:54.636308: step: 1508/529, loss: 0.6780310273170471
2023-01-22 23:51:55.774763: step: 1512/529, loss: 0.19513577222824097
2023-01-22 23:51:56.934952: step: 1516/529, loss: 0.2572776675224304
2023-01-22 23:51:58.034370: step: 1520/529, loss: 1.0514582395553589
2023-01-22 23:51:59.137625: step: 1524/529, loss: 0.19755320250988007
2023-01-22 23:52:00.279980: step: 1528/529, loss: 0.26384878158569336
2023-01-22 23:52:01.401243: step: 1532/529, loss: 0.16261273622512817
2023-01-22 23:52:02.517383: step: 1536/529, loss: 0.1483904868364334
2023-01-22 23:52:03.652128: step: 1540/529, loss: 0.1921371966600418
2023-01-22 23:52:04.809091: step: 1544/529, loss: 1.8900600671768188
2023-01-22 23:52:05.938152: step: 1548/529, loss: 0.16470623016357422
2023-01-22 23:52:07.079619: step: 1552/529, loss: 0.17478471994400024
2023-01-22 23:52:08.184210: step: 1556/529, loss: 0.06803274154663086
2023-01-22 23:52:09.315666: step: 1560/529, loss: 0.18762320280075073
2023-01-22 23:52:10.459310: step: 1564/529, loss: 0.11039657890796661
2023-01-22 23:52:11.599894: step: 1568/529, loss: 0.12208385765552521
2023-01-22 23:52:12.756679: step: 1572/529, loss: 0.18015176057815552
2023-01-22 23:52:13.924801: step: 1576/529, loss: 1.9510889053344727
2023-01-22 23:52:15.049915: step: 1580/529, loss: 0.07773247361183167
2023-01-22 23:52:16.189093: step: 1584/529, loss: 1.0601160526275635
2023-01-22 23:52:17.320573: step: 1588/529, loss: 0.8043298125267029
2023-01-22 23:52:18.446604: step: 1592/529, loss: 0.25013047456741333
2023-01-22 23:52:19.587448: step: 1596/529, loss: 0.5774046778678894
2023-01-22 23:52:20.734197: step: 1600/529, loss: 6.909578323364258
2023-01-22 23:52:21.880369: step: 1604/529, loss: 0.24420300126075745
2023-01-22 23:52:23.006135: step: 1608/529, loss: 0.15039558708667755
2023-01-22 23:52:24.118142: step: 1612/529, loss: 0.6981691122055054
2023-01-22 23:52:25.238600: step: 1616/529, loss: 0.1107785701751709
2023-01-22 23:52:26.358879: step: 1620/529, loss: 0.6491174697875977
2023-01-22 23:52:27.482096: step: 1624/529, loss: 0.14282435178756714
2023-01-22 23:52:28.620344: step: 1628/529, loss: 0.04771938547492027
2023-01-22 23:52:29.760513: step: 1632/529, loss: 0.1727065145969391
2023-01-22 23:52:30.896234: step: 1636/529, loss: 0.37428656220436096
2023-01-22 23:52:32.021376: step: 1640/529, loss: 0.7700635194778442
2023-01-22 23:52:33.143847: step: 1644/529, loss: 0.639403760433197
2023-01-22 23:52:34.303060: step: 1648/529, loss: 0.11602506041526794
2023-01-22 23:52:35.448623: step: 1652/529, loss: 0.8400684595108032
2023-01-22 23:52:36.575660: step: 1656/529, loss: 0.13578824698925018
2023-01-22 23:52:37.716297: step: 1660/529, loss: 0.8040549159049988
2023-01-22 23:52:38.848868: step: 1664/529, loss: 0.0938500389456749
2023-01-22 23:52:39.984959: step: 1668/529, loss: 0.26375675201416016
2023-01-22 23:52:41.098239: step: 1672/529, loss: 0.6129226684570312
2023-01-22 23:52:42.261681: step: 1676/529, loss: 0.06168346479535103
2023-01-22 23:52:43.416695: step: 1680/529, loss: 1.5032662153244019
2023-01-22 23:52:44.544733: step: 1684/529, loss: 0.40120744705200195
2023-01-22 23:52:45.684628: step: 1688/529, loss: 0.5830522775650024
2023-01-22 23:52:46.903593: step: 1692/529, loss: 2.0823144912719727
2023-01-22 23:52:48.049336: step: 1696/529, loss: 0.20201969146728516
2023-01-22 23:52:49.158509: step: 1700/529, loss: 0.1854238510131836
2023-01-22 23:52:50.299192: step: 1704/529, loss: 0.12755604088306427
2023-01-22 23:52:51.424424: step: 1708/529, loss: 0.1539296656847
2023-01-22 23:52:52.574341: step: 1712/529, loss: 0.9455440640449524
2023-01-22 23:52:53.702855: step: 1716/529, loss: 0.44399499893188477
2023-01-22 23:52:54.813366: step: 1720/529, loss: 0.0912221223115921
2023-01-22 23:52:55.956793: step: 1724/529, loss: 0.46971315145492554
2023-01-22 23:52:57.092668: step: 1728/529, loss: 1.4169028997421265
2023-01-22 23:52:58.229051: step: 1732/529, loss: 0.11658430099487305
2023-01-22 23:52:59.379212: step: 1736/529, loss: 0.3496878743171692
2023-01-22 23:53:00.509848: step: 1740/529, loss: 0.08327837288379669
2023-01-22 23:53:01.675548: step: 1744/529, loss: 0.8752743601799011
2023-01-22 23:53:02.829504: step: 1748/529, loss: 0.2983238101005554
2023-01-22 23:53:03.950070: step: 1752/529, loss: 0.11087103188037872
2023-01-22 23:53:05.073977: step: 1756/529, loss: 0.24697303771972656
2023-01-22 23:53:06.220485: step: 1760/529, loss: 0.19345569610595703
2023-01-22 23:53:07.341045: step: 1764/529, loss: 0.9849398136138916
2023-01-22 23:53:08.507665: step: 1768/529, loss: 0.2449812889099121
2023-01-22 23:53:09.656833: step: 1772/529, loss: 0.18153142929077148
2023-01-22 23:53:10.826601: step: 1776/529, loss: 0.27847251296043396
2023-01-22 23:53:11.958734: step: 1780/529, loss: 0.7282560467720032
2023-01-22 23:53:13.112701: step: 1784/529, loss: 0.04258241504430771
2023-01-22 23:53:14.259605: step: 1788/529, loss: 0.22480377554893494
2023-01-22 23:53:15.401417: step: 1792/529, loss: 0.9145678281784058
2023-01-22 23:53:16.525448: step: 1796/529, loss: 2.241812229156494
2023-01-22 23:53:17.673289: step: 1800/529, loss: 0.16483697295188904
2023-01-22 23:53:18.806882: step: 1804/529, loss: 0.1204107254743576
2023-01-22 23:53:19.955444: step: 1808/529, loss: 0.6715775728225708
2023-01-22 23:53:21.109224: step: 1812/529, loss: 0.35002368688583374
2023-01-22 23:53:22.255770: step: 1816/529, loss: 0.7887779474258423
2023-01-22 23:53:23.404861: step: 1820/529, loss: 0.08474154770374298
2023-01-22 23:53:24.555525: step: 1824/529, loss: 0.7663998603820801
2023-01-22 23:53:25.713235: step: 1828/529, loss: 0.23556175827980042
2023-01-22 23:53:26.852017: step: 1832/529, loss: 0.0884857177734375
2023-01-22 23:53:27.984476: step: 1836/529, loss: 0.6963865756988525
2023-01-22 23:53:29.133539: step: 1840/529, loss: 0.5266475677490234
2023-01-22 23:53:30.293617: step: 1844/529, loss: 1.689920425415039
2023-01-22 23:53:31.439443: step: 1848/529, loss: 0.47878068685531616
2023-01-22 23:53:32.592241: step: 1852/529, loss: 0.6409839391708374
2023-01-22 23:53:33.705085: step: 1856/529, loss: 0.7571682333946228
2023-01-22 23:53:34.838129: step: 1860/529, loss: 0.14327040314674377
2023-01-22 23:53:35.964540: step: 1864/529, loss: 0.22532731294631958
2023-01-22 23:53:37.115768: step: 1868/529, loss: 0.7403206825256348
2023-01-22 23:53:38.263917: step: 1872/529, loss: 0.08780007809400558
2023-01-22 23:53:39.371938: step: 1876/529, loss: 0.8261210918426514
2023-01-22 23:53:40.518643: step: 1880/529, loss: 0.42685550451278687
2023-01-22 23:53:41.660121: step: 1884/529, loss: 0.12489864230155945
2023-01-22 23:53:42.823593: step: 1888/529, loss: 0.08488745987415314
2023-01-22 23:53:43.976918: step: 1892/529, loss: 0.17247600853443146
2023-01-22 23:53:45.087771: step: 1896/529, loss: 0.3552228510379791
2023-01-22 23:53:46.204478: step: 1900/529, loss: 0.05527188628911972
2023-01-22 23:53:47.349643: step: 1904/529, loss: 0.1169508546590805
2023-01-22 23:53:48.482567: step: 1908/529, loss: 0.08105888962745667
2023-01-22 23:53:49.627848: step: 1912/529, loss: 0.3276294469833374
2023-01-22 23:53:50.772954: step: 1916/529, loss: 0.7120423316955566
2023-01-22 23:53:51.917000: step: 1920/529, loss: 0.3325200080871582
2023-01-22 23:53:53.047847: step: 1924/529, loss: 0.22089600563049316
2023-01-22 23:53:54.196791: step: 1928/529, loss: 0.12485527992248535
2023-01-22 23:53:55.346405: step: 1932/529, loss: 8.238045692443848
2023-01-22 23:53:56.484602: step: 1936/529, loss: 0.7729694843292236
2023-01-22 23:53:57.610146: step: 1940/529, loss: 0.13526931405067444
2023-01-22 23:53:58.748566: step: 1944/529, loss: 1.0348960161209106
2023-01-22 23:53:59.919835: step: 1948/529, loss: 0.2054780125617981
2023-01-22 23:54:01.063821: step: 1952/529, loss: 0.8352066278457642
2023-01-22 23:54:02.195887: step: 1956/529, loss: 0.8822604417800903
2023-01-22 23:54:03.361080: step: 1960/529, loss: 0.7498101592063904
2023-01-22 23:54:04.504288: step: 1964/529, loss: 6.706881046295166
2023-01-22 23:54:05.625136: step: 1968/529, loss: 0.3287595808506012
2023-01-22 23:54:06.749541: step: 1972/529, loss: 0.15849485993385315
2023-01-22 23:54:07.914832: step: 1976/529, loss: 0.1749209463596344
2023-01-22 23:54:09.057565: step: 1980/529, loss: 0.050691843032836914
2023-01-22 23:54:10.196280: step: 1984/529, loss: 0.14543476700782776
2023-01-22 23:54:11.376307: step: 1988/529, loss: 0.11504574120044708
2023-01-22 23:54:12.492228: step: 1992/529, loss: 0.2853316366672516
2023-01-22 23:54:13.639003: step: 1996/529, loss: 0.9961269497871399
2023-01-22 23:54:14.774524: step: 2000/529, loss: 0.07696647942066193
2023-01-22 23:54:15.904430: step: 2004/529, loss: 0.7733392119407654
2023-01-22 23:54:17.063885: step: 2008/529, loss: 0.6258556246757507
2023-01-22 23:54:18.188156: step: 2012/529, loss: 0.5575348734855652
2023-01-22 23:54:19.312925: step: 2016/529, loss: 0.07689771801233292
2023-01-22 23:54:20.472839: step: 2020/529, loss: 0.11228857189416885
2023-01-22 23:54:21.586927: step: 2024/529, loss: 0.18749314546585083
2023-01-22 23:54:22.730951: step: 2028/529, loss: 0.2973749041557312
2023-01-22 23:54:23.878524: step: 2032/529, loss: 0.12729129195213318
2023-01-22 23:54:25.040280: step: 2036/529, loss: 0.11492805182933807
2023-01-22 23:54:26.165008: step: 2040/529, loss: 0.022746801376342773
2023-01-22 23:54:27.288269: step: 2044/529, loss: 0.2855968475341797
2023-01-22 23:54:28.429829: step: 2048/529, loss: 0.1572956144809723
2023-01-22 23:54:29.578487: step: 2052/529, loss: 1.50773286819458
2023-01-22 23:54:30.707393: step: 2056/529, loss: 0.18963176012039185
2023-01-22 23:54:31.854190: step: 2060/529, loss: 0.13837838172912598
2023-01-22 23:54:32.991532: step: 2064/529, loss: 0.061939336359500885
2023-01-22 23:54:34.152360: step: 2068/529, loss: 0.855870246887207
2023-01-22 23:54:35.318322: step: 2072/529, loss: 1.0453215837478638
2023-01-22 23:54:36.457935: step: 2076/529, loss: 1.4882158041000366
2023-01-22 23:54:37.655911: step: 2080/529, loss: 2.292067050933838
2023-01-22 23:54:38.801562: step: 2084/529, loss: 0.5006760358810425
2023-01-22 23:54:39.912937: step: 2088/529, loss: 0.03980712965130806
2023-01-22 23:54:41.027733: step: 2092/529, loss: 0.14607982337474823
2023-01-22 23:54:42.155806: step: 2096/529, loss: 1.2448679208755493
2023-01-22 23:54:43.295362: step: 2100/529, loss: 0.10721039772033691
2023-01-22 23:54:44.427199: step: 2104/529, loss: 0.7397187948226929
2023-01-22 23:54:45.530854: step: 2108/529, loss: 1.00004243850708
2023-01-22 23:54:46.667111: step: 2112/529, loss: 0.19689975678920746
2023-01-22 23:54:47.847881: step: 2116/529, loss: 0.7404813766479492
==================================================
Loss: 0.603
--------------------
Dev: {'event': {'p': 0.574869109947644, 'r': 0.7310252996005326, 'f1': 0.6436107854630715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.5623836126629422, 'r': 0.6998841251448435, 'f1': 0.6236448115642746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5238095238095238, 'r': 0.8148148148148148, 'f1': 0.6376811594202898}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7142857142857143, 'r': 0.47619047619047616, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.525, 'r': 0.5833333333333334, 'f1': 0.5526315789473685}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574869109947644, 'r': 0.7310252996005326, 'f1': 0.6436107854630715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.5623836126629422, 'r': 0.6998841251448435, 'f1': 0.6236448115642746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5238095238095238, 'r': 0.8148148148148148, 'f1': 0.6376811594202898}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.574869109947644, 'r': 0.7310252996005326, 'f1': 0.6436107854630715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.5623836126629422, 'r': 0.6998841251448435, 'f1': 0.6236448115642746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7142857142857143, 'r': 0.47619047619047616, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.574869109947644, 'r': 0.7310252996005326, 'f1': 0.6436107854630715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Russian: {'event': {'p': 0.5623836126629422, 'r': 0.6998841251448435, 'f1': 0.6236448115642746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Russian: {'event': {'p': 0.525, 'r': 0.5833333333333334, 'f1': 0.5526315789473685}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
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 23:55:54.872164: step: 4/529, loss: 0.1127520501613617
2023-01-22 23:55:56.002161: step: 8/529, loss: 0.432242214679718
2023-01-22 23:55:57.124910: step: 12/529, loss: 0.15021859109401703
2023-01-22 23:55:58.243775: step: 16/529, loss: 0.1918453723192215
2023-01-22 23:55:59.366651: step: 20/529, loss: 0.10688343644142151
2023-01-22 23:56:00.482725: step: 24/529, loss: 0.1043185293674469
2023-01-22 23:56:01.604361: step: 28/529, loss: 0.26591378450393677
2023-01-22 23:56:02.742149: step: 32/529, loss: 0.7260921597480774
2023-01-22 23:56:03.888985: step: 36/529, loss: 0.32221031188964844
2023-01-22 23:56:05.024697: step: 40/529, loss: 0.18153077363967896
2023-01-22 23:56:06.136714: step: 44/529, loss: 0.0676766186952591
2023-01-22 23:56:07.258229: step: 48/529, loss: 0.4816628694534302
2023-01-22 23:56:08.382386: step: 52/529, loss: 0.18099379539489746
2023-01-22 23:56:09.522482: step: 56/529, loss: 1.011576771736145
2023-01-22 23:56:10.662810: step: 60/529, loss: 0.383029580116272
2023-01-22 23:56:11.779610: step: 64/529, loss: 0.9920968413352966
2023-01-22 23:56:12.945157: step: 68/529, loss: 0.05940570682287216
2023-01-22 23:56:14.083861: step: 72/529, loss: 0.17299515008926392
2023-01-22 23:56:15.219102: step: 76/529, loss: 0.9448099136352539
2023-01-22 23:56:16.358177: step: 80/529, loss: 0.16690778732299805
2023-01-22 23:56:17.498202: step: 84/529, loss: 0.0600038543343544
2023-01-22 23:56:18.665354: step: 88/529, loss: 0.22403989732265472
2023-01-22 23:56:19.805570: step: 92/529, loss: 0.3614594042301178
2023-01-22 23:56:20.932514: step: 96/529, loss: 0.04655952751636505
2023-01-22 23:56:22.063712: step: 100/529, loss: 6.479700565338135
2023-01-22 23:56:23.192603: step: 104/529, loss: 0.23768778145313263
2023-01-22 23:56:24.344872: step: 108/529, loss: 0.41127586364746094
2023-01-22 23:56:25.476185: step: 112/529, loss: 0.08945274353027344
2023-01-22 23:56:26.621560: step: 116/529, loss: 0.0813365951180458
2023-01-22 23:56:27.773697: step: 120/529, loss: 0.11603689193725586
2023-01-22 23:56:28.901106: step: 124/529, loss: 1.1029725074768066
2023-01-22 23:56:30.035525: step: 128/529, loss: 6.2161865234375
2023-01-22 23:56:31.180094: step: 132/529, loss: 1.9589625597000122
2023-01-22 23:56:32.359098: step: 136/529, loss: 0.19591423869132996
2023-01-22 23:56:33.504097: step: 140/529, loss: 7.002114295959473
2023-01-22 23:56:34.641464: step: 144/529, loss: 1.5503019094467163
2023-01-22 23:56:35.748862: step: 148/529, loss: 6.921739101409912
2023-01-22 23:56:36.866472: step: 152/529, loss: 0.1581367552280426
2023-01-22 23:56:37.994948: step: 156/529, loss: 0.3111073076725006
2023-01-22 23:56:39.124635: step: 160/529, loss: 0.5508758425712585
2023-01-22 23:56:40.258479: step: 164/529, loss: 0.2559228837490082
2023-01-22 23:56:41.389462: step: 168/529, loss: 0.658478319644928
2023-01-22 23:56:42.541573: step: 172/529, loss: 0.445242702960968
2023-01-22 23:56:43.680003: step: 176/529, loss: 0.08531536906957626
2023-01-22 23:56:44.789057: step: 180/529, loss: 0.185246080160141
2023-01-22 23:56:45.929121: step: 184/529, loss: 0.18567711114883423
2023-01-22 23:56:47.105600: step: 188/529, loss: 0.32176923751831055
2023-01-22 23:56:48.217246: step: 192/529, loss: 0.05649113655090332
2023-01-22 23:56:49.380250: step: 196/529, loss: 0.0940040647983551
2023-01-22 23:56:50.515309: step: 200/529, loss: 0.19925037026405334
2023-01-22 23:56:51.648278: step: 204/529, loss: 6.022089958190918
2023-01-22 23:56:52.796739: step: 208/529, loss: 0.7966360449790955
2023-01-22 23:56:53.923046: step: 212/529, loss: 0.16041961312294006
2023-01-22 23:56:55.054168: step: 216/529, loss: 0.7453233003616333
2023-01-22 23:56:56.193346: step: 220/529, loss: 0.046007610857486725
2023-01-22 23:56:57.330480: step: 224/529, loss: 0.07042908668518066
2023-01-22 23:56:58.461273: step: 228/529, loss: 0.25191402435302734
2023-01-22 23:56:59.585675: step: 232/529, loss: 0.03773627430200577
2023-01-22 23:57:00.719293: step: 236/529, loss: 0.25366511940956116
2023-01-22 23:57:01.875998: step: 240/529, loss: 0.22157259285449982
2023-01-22 23:57:03.016456: step: 244/529, loss: 0.3382606506347656
2023-01-22 23:57:04.126818: step: 248/529, loss: 0.353292852640152
2023-01-22 23:57:05.246663: step: 252/529, loss: 0.25949347019195557
2023-01-22 23:57:06.423918: step: 256/529, loss: 0.4028354287147522
2023-01-22 23:57:07.573151: step: 260/529, loss: 0.2683922052383423
2023-01-22 23:57:08.715912: step: 264/529, loss: 0.1497069150209427
2023-01-22 23:57:09.876463: step: 268/529, loss: 0.11594495922327042
2023-01-22 23:57:11.034951: step: 272/529, loss: 0.1656152307987213
2023-01-22 23:57:12.160153: step: 276/529, loss: 0.22007064521312714
2023-01-22 23:57:13.311957: step: 280/529, loss: 0.5109320282936096
2023-01-22 23:57:14.463775: step: 284/529, loss: 0.305112361907959
2023-01-22 23:57:15.603657: step: 288/529, loss: 0.9760399460792542
2023-01-22 23:57:16.750620: step: 292/529, loss: 0.29509663581848145
2023-01-22 23:57:17.966489: step: 296/529, loss: 0.06189975515007973
2023-01-22 23:57:19.106486: step: 300/529, loss: 2.9684865474700928
2023-01-22 23:57:20.246667: step: 304/529, loss: 0.4282251298427582
2023-01-22 23:57:21.404552: step: 308/529, loss: 0.1137821227312088
2023-01-22 23:57:22.536056: step: 312/529, loss: 0.24588042497634888
2023-01-22 23:57:23.686396: step: 316/529, loss: 0.1399907022714615
2023-01-22 23:57:24.816203: step: 320/529, loss: 0.41705432534217834
2023-01-22 23:57:25.982721: step: 324/529, loss: 0.28086891770362854
2023-01-22 23:57:27.139671: step: 328/529, loss: 0.6341606974601746
2023-01-22 23:57:28.265540: step: 332/529, loss: 2.945425033569336
2023-01-22 23:57:29.411892: step: 336/529, loss: 1.951957106590271
2023-01-22 23:57:30.535355: step: 340/529, loss: 0.5843101739883423
2023-01-22 23:57:31.682253: step: 344/529, loss: 0.0877981185913086
2023-01-22 23:57:32.819524: step: 348/529, loss: 0.23725710809230804
2023-01-22 23:57:33.952825: step: 352/529, loss: 0.19671788811683655
2023-01-22 23:57:35.133077: step: 356/529, loss: 0.259087473154068
2023-01-22 23:57:36.296544: step: 360/529, loss: 0.09261293709278107
2023-01-22 23:57:37.438816: step: 364/529, loss: 0.17963162064552307
2023-01-22 23:57:38.571066: step: 368/529, loss: 0.06281280517578125
2023-01-22 23:57:39.706797: step: 372/529, loss: 0.026651956140995026
2023-01-22 23:57:40.855360: step: 376/529, loss: 0.5319308042526245
2023-01-22 23:57:42.005131: step: 380/529, loss: 0.5862182378768921
2023-01-22 23:57:43.161142: step: 384/529, loss: 6.4143524169921875
2023-01-22 23:57:44.307882: step: 388/529, loss: 0.1870521605014801
2023-01-22 23:57:45.427513: step: 392/529, loss: 0.07262754440307617
2023-01-22 23:57:46.576389: step: 396/529, loss: 0.7711917161941528
2023-01-22 23:57:47.730166: step: 400/529, loss: 0.3445551097393036
2023-01-22 23:57:48.887767: step: 404/529, loss: 0.05444631725549698
2023-01-22 23:57:50.040239: step: 408/529, loss: 0.31717413663864136
2023-01-22 23:57:51.196712: step: 412/529, loss: 0.46483713388442993
2023-01-22 23:57:52.321142: step: 416/529, loss: 0.06532096862792969
2023-01-22 23:57:53.440797: step: 420/529, loss: 0.21404992043972015
2023-01-22 23:57:54.584766: step: 424/529, loss: 0.29162129759788513
2023-01-22 23:57:55.752764: step: 428/529, loss: 0.14978857338428497
2023-01-22 23:57:56.887989: step: 432/529, loss: 0.4147473871707916
2023-01-22 23:57:58.014079: step: 436/529, loss: 0.34247875213623047
2023-01-22 23:57:59.143541: step: 440/529, loss: 0.28635191917419434
2023-01-22 23:58:00.301717: step: 444/529, loss: 0.274493545293808
2023-01-22 23:58:01.459308: step: 448/529, loss: 0.1970309317111969
2023-01-22 23:58:02.634894: step: 452/529, loss: 0.20057940483093262
2023-01-22 23:58:03.814140: step: 456/529, loss: 0.10596227645874023
2023-01-22 23:58:04.989517: step: 460/529, loss: 1.2692768573760986
2023-01-22 23:58:06.134368: step: 464/529, loss: 0.32083916664123535
2023-01-22 23:58:07.286863: step: 468/529, loss: 0.16598376631736755
2023-01-22 23:58:08.445324: step: 472/529, loss: 0.1347036361694336
2023-01-22 23:58:09.589051: step: 476/529, loss: 0.4680764079093933
2023-01-22 23:58:10.744966: step: 480/529, loss: 0.19098129868507385
2023-01-22 23:58:11.885445: step: 484/529, loss: 0.15129438042640686
2023-01-22 23:58:12.999836: step: 488/529, loss: 0.1173185333609581
2023-01-22 23:58:14.156785: step: 492/529, loss: 0.15769940614700317
2023-01-22 23:58:15.289520: step: 496/529, loss: 0.13384681940078735
2023-01-22 23:58:16.449403: step: 500/529, loss: 0.08125276863574982
2023-01-22 23:58:17.595423: step: 504/529, loss: 0.15946227312088013
2023-01-22 23:58:18.732711: step: 508/529, loss: 0.09619312733411789
2023-01-22 23:58:19.866086: step: 512/529, loss: 0.5139181613922119
2023-01-22 23:58:21.004855: step: 516/529, loss: 0.18244200944900513
2023-01-22 23:58:22.171922: step: 520/529, loss: 0.6223430633544922
2023-01-22 23:58:23.333540: step: 524/529, loss: 0.328574001789093
2023-01-22 23:58:24.476613: step: 528/529, loss: 0.08651085197925568
2023-01-22 23:58:25.651053: step: 532/529, loss: 0.45230740308761597
2023-01-22 23:58:26.806600: step: 536/529, loss: 0.9030293226242065
2023-01-22 23:58:27.987160: step: 540/529, loss: 0.9087143540382385
2023-01-22 23:58:29.108595: step: 544/529, loss: 0.3730502128601074
2023-01-22 23:58:30.278459: step: 548/529, loss: 0.09509558975696564
2023-01-22 23:58:31.407950: step: 552/529, loss: 0.7257412672042847
2023-01-22 23:58:32.546844: step: 556/529, loss: 0.5058338046073914
2023-01-22 23:58:33.684239: step: 560/529, loss: 0.15334831178188324
2023-01-22 23:58:34.792788: step: 564/529, loss: 0.16440238058567047
2023-01-22 23:58:35.908793: step: 568/529, loss: 1.058837890625
2023-01-22 23:58:37.067764: step: 572/529, loss: 0.31908196210861206
2023-01-22 23:58:38.206084: step: 576/529, loss: 0.13805875182151794
2023-01-22 23:58:39.377534: step: 580/529, loss: 0.9343050122261047
2023-01-22 23:58:40.507952: step: 584/529, loss: 0.7799698710441589
2023-01-22 23:58:41.630275: step: 588/529, loss: 0.08400693535804749
2023-01-22 23:58:42.753062: step: 592/529, loss: 0.19094926118850708
2023-01-22 23:58:43.927641: step: 596/529, loss: 0.2239713817834854
2023-01-22 23:58:45.032484: step: 600/529, loss: 0.19903230667114258
2023-01-22 23:58:46.169048: step: 604/529, loss: 0.07337456196546555
2023-01-22 23:58:47.306147: step: 608/529, loss: 1.0952904224395752
2023-01-22 23:58:48.457653: step: 612/529, loss: 0.061934471130371094
2023-01-22 23:58:49.604765: step: 616/529, loss: 0.02922229841351509
2023-01-22 23:58:50.777776: step: 620/529, loss: 0.07398152351379395
2023-01-22 23:58:51.934821: step: 624/529, loss: 0.6863476037979126
2023-01-22 23:58:53.055003: step: 628/529, loss: 0.10770788043737411
2023-01-22 23:58:54.204976: step: 632/529, loss: 0.14766426384449005
2023-01-22 23:58:55.345269: step: 636/529, loss: 0.5057401657104492
2023-01-22 23:58:56.501831: step: 640/529, loss: 0.17820319533348083
2023-01-22 23:58:57.606506: step: 644/529, loss: 0.08456039428710938
2023-01-22 23:58:58.721570: step: 648/529, loss: 0.8642090559005737
2023-01-22 23:58:59.861725: step: 652/529, loss: 0.13768067955970764
2023-01-22 23:59:01.003062: step: 656/529, loss: 0.3024471402168274
2023-01-22 23:59:02.103459: step: 660/529, loss: 0.14301714301109314
2023-01-22 23:59:03.242210: step: 664/529, loss: 0.9911198019981384
2023-01-22 23:59:04.392635: step: 668/529, loss: 6.947729110717773
2023-01-22 23:59:05.526331: step: 672/529, loss: 0.6631352305412292
2023-01-22 23:59:06.679474: step: 676/529, loss: 0.7771148681640625
2023-01-22 23:59:07.808970: step: 680/529, loss: 1.2801828384399414
2023-01-22 23:59:08.977601: step: 684/529, loss: 0.8821722269058228
2023-01-22 23:59:10.115304: step: 688/529, loss: 0.6851043701171875
2023-01-22 23:59:11.273154: step: 692/529, loss: 0.19688820838928223
2023-01-22 23:59:12.430414: step: 696/529, loss: 0.11057816445827484
2023-01-22 23:59:13.571066: step: 700/529, loss: 0.6198978424072266
2023-01-22 23:59:14.712399: step: 704/529, loss: 6.326823711395264
2023-01-22 23:59:15.855755: step: 708/529, loss: 0.37878283858299255
2023-01-22 23:59:16.975481: step: 712/529, loss: 0.16252851486206055
2023-01-22 23:59:18.081161: step: 716/529, loss: 0.959736704826355
2023-01-22 23:59:19.220106: step: 720/529, loss: 0.6077576279640198
2023-01-22 23:59:20.347210: step: 724/529, loss: 0.5647670030593872
2023-01-22 23:59:21.508501: step: 728/529, loss: 0.24695168435573578
2023-01-22 23:59:22.653832: step: 732/529, loss: 0.7023944854736328
2023-01-22 23:59:23.808524: step: 736/529, loss: 0.15500479936599731
2023-01-22 23:59:24.958166: step: 740/529, loss: 0.47891730070114136
2023-01-22 23:59:26.064507: step: 744/529, loss: 0.6409094929695129
2023-01-22 23:59:27.211129: step: 748/529, loss: 0.7811018228530884
2023-01-22 23:59:28.348774: step: 752/529, loss: 0.8542653322219849
2023-01-22 23:59:29.462856: step: 756/529, loss: 0.4607399106025696
2023-01-22 23:59:30.598612: step: 760/529, loss: 0.7185568809509277
2023-01-22 23:59:31.745984: step: 764/529, loss: 0.4659437835216522
2023-01-22 23:59:32.879293: step: 768/529, loss: 0.09852056205272675
2023-01-22 23:59:33.984969: step: 772/529, loss: 0.4453864097595215
2023-01-22 23:59:35.097920: step: 776/529, loss: 1.1008559465408325
2023-01-22 23:59:36.249390: step: 780/529, loss: 0.13033896684646606
2023-01-22 23:59:37.379908: step: 784/529, loss: 0.9933927655220032
2023-01-22 23:59:38.492400: step: 788/529, loss: 0.47975999116897583
2023-01-22 23:59:39.643117: step: 792/529, loss: 0.08241887390613556
2023-01-22 23:59:40.755544: step: 796/529, loss: 0.18805037438869476
2023-01-22 23:59:41.898172: step: 800/529, loss: 0.1067572683095932
2023-01-22 23:59:43.021659: step: 804/529, loss: 0.6861340999603271
2023-01-22 23:59:44.164030: step: 808/529, loss: 0.7667003870010376
2023-01-22 23:59:45.304857: step: 812/529, loss: 0.07227583229541779
2023-01-22 23:59:46.444408: step: 816/529, loss: 1.3184375762939453
2023-01-22 23:59:47.601803: step: 820/529, loss: 0.06064195558428764
2023-01-22 23:59:48.732678: step: 824/529, loss: 0.11673454940319061
2023-01-22 23:59:49.846372: step: 828/529, loss: 0.08390478789806366
2023-01-22 23:59:50.962404: step: 832/529, loss: 0.19092312455177307
2023-01-22 23:59:52.107116: step: 836/529, loss: 0.7027814984321594
2023-01-22 23:59:53.240907: step: 840/529, loss: 0.1882866770029068
2023-01-22 23:59:54.344548: step: 844/529, loss: 0.12573833763599396
2023-01-22 23:59:55.487801: step: 848/529, loss: 0.40620365738868713
2023-01-22 23:59:56.640811: step: 852/529, loss: 0.07022324204444885
2023-01-22 23:59:57.784535: step: 856/529, loss: 0.2873774766921997
2023-01-22 23:59:58.922420: step: 860/529, loss: 0.6653907299041748
2023-01-23 00:00:00.056043: step: 864/529, loss: 0.16346341371536255
2023-01-23 00:00:01.184577: step: 868/529, loss: 0.054229069501161575
2023-01-23 00:00:02.311411: step: 872/529, loss: 0.1588718444108963
2023-01-23 00:00:03.435607: step: 876/529, loss: 0.09767427295446396
2023-01-23 00:00:04.579254: step: 880/529, loss: 0.9408793449401855
2023-01-23 00:00:05.711851: step: 884/529, loss: 0.1131628081202507
2023-01-23 00:00:06.871787: step: 888/529, loss: 0.5475469827651978
2023-01-23 00:00:07.990502: step: 892/529, loss: 0.8748939633369446
2023-01-23 00:00:09.124379: step: 896/529, loss: 0.14808779954910278
2023-01-23 00:00:10.256460: step: 900/529, loss: 0.8827480673789978
2023-01-23 00:00:11.379763: step: 904/529, loss: 0.6642062664031982
2023-01-23 00:00:12.514401: step: 908/529, loss: 0.1711595058441162
2023-01-23 00:00:13.645905: step: 912/529, loss: 0.2882459759712219
2023-01-23 00:00:14.791365: step: 916/529, loss: 0.16212357580661774
2023-01-23 00:00:15.912344: step: 920/529, loss: 0.08147764205932617
2023-01-23 00:00:17.029390: step: 924/529, loss: 0.15510712563991547
2023-01-23 00:00:18.189504: step: 928/529, loss: 0.5895828604698181
2023-01-23 00:00:19.293624: step: 932/529, loss: 0.28344759345054626
2023-01-23 00:00:20.407787: step: 936/529, loss: 0.1728839874267578
2023-01-23 00:00:21.538557: step: 940/529, loss: 0.7093252539634705
2023-01-23 00:00:22.705630: step: 944/529, loss: 0.49861180782318115
2023-01-23 00:00:23.814321: step: 948/529, loss: 0.4498213827610016
2023-01-23 00:00:24.967531: step: 952/529, loss: 0.13618993759155273
2023-01-23 00:00:26.114573: step: 956/529, loss: 0.07919006794691086
2023-01-23 00:00:27.297879: step: 960/529, loss: 0.4718391001224518
2023-01-23 00:00:28.450993: step: 964/529, loss: 0.24556908011436462
2023-01-23 00:00:29.590735: step: 968/529, loss: 0.16113919019699097
2023-01-23 00:00:30.752278: step: 972/529, loss: 0.3961173892021179
2023-01-23 00:00:31.883761: step: 976/529, loss: 0.10006770491600037
2023-01-23 00:00:33.019946: step: 980/529, loss: 0.8665919303894043
2023-01-23 00:00:34.142901: step: 984/529, loss: 0.16403932869434357
2023-01-23 00:00:35.303335: step: 988/529, loss: 0.20638760924339294
2023-01-23 00:00:36.462540: step: 992/529, loss: 0.45358705520629883
2023-01-23 00:00:37.643813: step: 996/529, loss: 0.10458078980445862
2023-01-23 00:00:38.796320: step: 1000/529, loss: 0.7031070590019226
2023-01-23 00:00:39.921687: step: 1004/529, loss: 0.28158989548683167
2023-01-23 00:00:41.052693: step: 1008/529, loss: 0.20380783081054688
2023-01-23 00:00:42.174925: step: 1012/529, loss: 6.5429277420043945
2023-01-23 00:00:43.308852: step: 1016/529, loss: 0.36283808946609497
2023-01-23 00:00:44.461398: step: 1020/529, loss: 0.2250961810350418
2023-01-23 00:00:45.602246: step: 1024/529, loss: 0.4927643835544586
2023-01-23 00:00:46.746823: step: 1028/529, loss: 0.08336491882801056
2023-01-23 00:00:47.863536: step: 1032/529, loss: 0.13230600953102112
2023-01-23 00:00:48.978145: step: 1036/529, loss: 0.7081431150436401
2023-01-23 00:00:50.122295: step: 1040/529, loss: 0.004212379455566406
2023-01-23 00:00:51.259552: step: 1044/529, loss: 0.1725786179304123
2023-01-23 00:00:52.394714: step: 1048/529, loss: 0.5279135704040527
2023-01-23 00:00:53.521949: step: 1052/529, loss: 0.6752395629882812
2023-01-23 00:00:54.636615: step: 1056/529, loss: 0.20082946121692657
2023-01-23 00:00:55.797665: step: 1060/529, loss: 6.2498459815979
2023-01-23 00:00:56.919356: step: 1064/529, loss: 0.07474994659423828
2023-01-23 00:00:58.024075: step: 1068/529, loss: 0.1972431242465973
2023-01-23 00:00:59.166455: step: 1072/529, loss: 0.04951906204223633
2023-01-23 00:01:00.319215: step: 1076/529, loss: 0.37428781390190125
2023-01-23 00:01:01.448636: step: 1080/529, loss: 0.13798211514949799
2023-01-23 00:01:02.568412: step: 1084/529, loss: 1.4594587087631226
2023-01-23 00:01:03.715563: step: 1088/529, loss: 0.36609047651290894
2023-01-23 00:01:04.827178: step: 1092/529, loss: 0.06333620846271515
2023-01-23 00:01:05.956044: step: 1096/529, loss: 0.3570215702056885
2023-01-23 00:01:07.118423: step: 1100/529, loss: 0.4960615038871765
2023-01-23 00:01:08.284211: step: 1104/529, loss: 0.040868185460567474
2023-01-23 00:01:09.421165: step: 1108/529, loss: 0.1393783688545227
2023-01-23 00:01:10.583060: step: 1112/529, loss: 0.5948085784912109
2023-01-23 00:01:11.745777: step: 1116/529, loss: 0.11437148600816727
2023-01-23 00:01:12.885791: step: 1120/529, loss: 0.7754427194595337
2023-01-23 00:01:14.005269: step: 1124/529, loss: 0.3609389066696167
2023-01-23 00:01:15.133828: step: 1128/529, loss: 0.10810461640357971
2023-01-23 00:01:16.272919: step: 1132/529, loss: 0.8239008784294128
2023-01-23 00:01:17.400823: step: 1136/529, loss: 0.24920830130577087
2023-01-23 00:01:18.551130: step: 1140/529, loss: 0.13289594650268555
2023-01-23 00:01:19.668479: step: 1144/529, loss: 0.16481778025627136
2023-01-23 00:01:20.812364: step: 1148/529, loss: 0.09337092190980911
2023-01-23 00:01:21.937881: step: 1152/529, loss: 7.192674160003662
2023-01-23 00:01:23.078000: step: 1156/529, loss: 0.36509427428245544
2023-01-23 00:01:24.201904: step: 1160/529, loss: 1.1140697002410889
2023-01-23 00:01:25.408132: step: 1164/529, loss: 0.04064493253827095
2023-01-23 00:01:26.560047: step: 1168/529, loss: 0.2842632234096527
2023-01-23 00:01:27.682448: step: 1172/529, loss: 0.20427417755126953
2023-01-23 00:01:28.816597: step: 1176/529, loss: 0.7634838223457336
2023-01-23 00:01:29.925439: step: 1180/529, loss: 0.28395357728004456
2023-01-23 00:01:31.071409: step: 1184/529, loss: 0.21039456129074097
2023-01-23 00:01:32.201634: step: 1188/529, loss: 0.4592967927455902
2023-01-23 00:01:33.313747: step: 1192/529, loss: 0.10056066513061523
2023-01-23 00:01:34.484753: step: 1196/529, loss: 0.4734603762626648
2023-01-23 00:01:35.642926: step: 1200/529, loss: 0.1483844816684723
2023-01-23 00:01:36.785027: step: 1204/529, loss: 0.8957277536392212
2023-01-23 00:01:37.898857: step: 1208/529, loss: 0.8649401664733887
2023-01-23 00:01:39.030570: step: 1212/529, loss: 1.3796403408050537
2023-01-23 00:01:40.144366: step: 1216/529, loss: 0.5873506665229797
2023-01-23 00:01:41.290449: step: 1220/529, loss: 0.37370890378952026
2023-01-23 00:01:42.412422: step: 1224/529, loss: 0.27227482199668884
2023-01-23 00:01:43.525607: step: 1228/529, loss: 0.15552778542041779
2023-01-23 00:01:44.635297: step: 1232/529, loss: 0.12194252014160156
2023-01-23 00:01:45.772254: step: 1236/529, loss: 1.2321577072143555
2023-01-23 00:01:46.900277: step: 1240/529, loss: 0.062488533556461334
2023-01-23 00:01:48.009283: step: 1244/529, loss: 0.1309993863105774
2023-01-23 00:01:49.126767: step: 1248/529, loss: 0.3407500982284546
2023-01-23 00:01:50.248752: step: 1252/529, loss: 1.0729297399520874
2023-01-23 00:01:51.376878: step: 1256/529, loss: 0.6232610940933228
2023-01-23 00:01:52.525095: step: 1260/529, loss: 1.2132762670516968
2023-01-23 00:01:53.670298: step: 1264/529, loss: 0.16887111961841583
2023-01-23 00:01:54.794688: step: 1268/529, loss: 0.13054580986499786
2023-01-23 00:01:55.938397: step: 1272/529, loss: 0.1171242743730545
2023-01-23 00:01:57.086376: step: 1276/529, loss: 0.07810792326927185
2023-01-23 00:01:58.243887: step: 1280/529, loss: 1.12432062625885
2023-01-23 00:01:59.367778: step: 1284/529, loss: 0.7599477767944336
2023-01-23 00:02:00.520803: step: 1288/529, loss: 0.10164737701416016
2023-01-23 00:02:01.647710: step: 1292/529, loss: 1.122117280960083
2023-01-23 00:02:02.816123: step: 1296/529, loss: 0.23339280486106873
2023-01-23 00:02:03.970644: step: 1300/529, loss: 0.825629472732544
2023-01-23 00:02:05.140903: step: 1304/529, loss: 0.26286134123802185
2023-01-23 00:02:06.285249: step: 1308/529, loss: 0.1601598709821701
2023-01-23 00:02:07.416208: step: 1312/529, loss: 0.10929213464260101
2023-01-23 00:02:08.549607: step: 1316/529, loss: 0.6846439242362976
2023-01-23 00:02:09.656429: step: 1320/529, loss: 0.20264720916748047
2023-01-23 00:02:10.798218: step: 1324/529, loss: 0.043024733662605286
2023-01-23 00:02:11.915480: step: 1328/529, loss: 0.08657798916101456
2023-01-23 00:02:13.044941: step: 1332/529, loss: 0.11942777782678604
2023-01-23 00:02:14.182671: step: 1336/529, loss: 0.07697949558496475
2023-01-23 00:02:15.315699: step: 1340/529, loss: 0.07051143795251846
2023-01-23 00:02:16.428840: step: 1344/529, loss: 0.03893470764160156
2023-01-23 00:02:17.582359: step: 1348/529, loss: 0.17344561219215393
2023-01-23 00:02:18.729533: step: 1352/529, loss: 0.19600439071655273
2023-01-23 00:02:19.842705: step: 1356/529, loss: 0.1965889036655426
2023-01-23 00:02:20.991725: step: 1360/529, loss: 0.23195305466651917
2023-01-23 00:02:22.148608: step: 1364/529, loss: 0.5283797383308411
2023-01-23 00:02:23.312192: step: 1368/529, loss: 0.12434768676757812
2023-01-23 00:02:24.444109: step: 1372/529, loss: 0.14588089287281036
2023-01-23 00:02:25.589165: step: 1376/529, loss: 0.12842664122581482
2023-01-23 00:02:26.730220: step: 1380/529, loss: 1.1464896202087402
2023-01-23 00:02:27.860589: step: 1384/529, loss: 0.6363987922668457
2023-01-23 00:02:28.994701: step: 1388/529, loss: 0.3084859848022461
2023-01-23 00:02:30.139513: step: 1392/529, loss: 0.06737995147705078
2023-01-23 00:02:31.288862: step: 1396/529, loss: 1.9096086025238037
2023-01-23 00:02:32.431527: step: 1400/529, loss: 0.14616060256958008
2023-01-23 00:02:33.611786: step: 1404/529, loss: 0.9278597831726074
2023-01-23 00:02:34.737537: step: 1408/529, loss: 0.32750579714775085
2023-01-23 00:02:35.879054: step: 1412/529, loss: 3.3215439319610596
2023-01-23 00:02:36.997465: step: 1416/529, loss: 0.11584663391113281
2023-01-23 00:02:38.120290: step: 1420/529, loss: 0.4824641942977905
2023-01-23 00:02:39.259172: step: 1424/529, loss: 1.3737637996673584
2023-01-23 00:02:40.420780: step: 1428/529, loss: 0.2705325186252594
2023-01-23 00:02:41.544966: step: 1432/529, loss: 0.9200029969215393
2023-01-23 00:02:42.686655: step: 1436/529, loss: 0.05270242691040039
2023-01-23 00:02:43.881200: step: 1440/529, loss: 0.6112867593765259
2023-01-23 00:02:45.004411: step: 1444/529, loss: 0.5234668850898743
2023-01-23 00:02:46.152341: step: 1448/529, loss: 0.8266826868057251
2023-01-23 00:02:47.304444: step: 1452/529, loss: 1.4764163494110107
2023-01-23 00:02:48.440827: step: 1456/529, loss: 0.25212153792381287
2023-01-23 00:02:49.575137: step: 1460/529, loss: 0.1477159559726715
2023-01-23 00:02:50.683986: step: 1464/529, loss: 0.10954266041517258
2023-01-23 00:02:51.853876: step: 1468/529, loss: 0.7533424496650696
2023-01-23 00:02:52.987123: step: 1472/529, loss: 0.6905034184455872
2023-01-23 00:02:54.136408: step: 1476/529, loss: 0.8208313584327698
2023-01-23 00:02:55.290370: step: 1480/529, loss: 0.6493015885353088
2023-01-23 00:02:56.416270: step: 1484/529, loss: 0.3004302978515625
2023-01-23 00:02:57.516725: step: 1488/529, loss: 0.19165191054344177
2023-01-23 00:02:58.661746: step: 1492/529, loss: 0.5054263472557068
2023-01-23 00:02:59.788486: step: 1496/529, loss: 0.1792614907026291
2023-01-23 00:03:00.923352: step: 1500/529, loss: 0.5962066054344177
2023-01-23 00:03:02.076528: step: 1504/529, loss: 1.348507285118103
2023-01-23 00:03:03.218890: step: 1508/529, loss: 0.07748661190271378
2023-01-23 00:03:04.340292: step: 1512/529, loss: 0.5533306002616882
2023-01-23 00:03:05.477796: step: 1516/529, loss: 1.0416698455810547
2023-01-23 00:03:06.611359: step: 1520/529, loss: 0.14721174538135529
2023-01-23 00:03:07.755671: step: 1524/529, loss: 1.5281424522399902
2023-01-23 00:03:08.880419: step: 1528/529, loss: 0.7640345096588135
2023-01-23 00:03:10.027823: step: 1532/529, loss: 0.05257921293377876
2023-01-23 00:03:11.157334: step: 1536/529, loss: 0.1727236807346344
2023-01-23 00:03:12.276781: step: 1540/529, loss: 0.11017632484436035
2023-01-23 00:03:13.415744: step: 1544/529, loss: 1.6037763357162476
2023-01-23 00:03:14.574480: step: 1548/529, loss: 0.3284495770931244
2023-01-23 00:03:15.721527: step: 1552/529, loss: 0.8090665340423584
2023-01-23 00:03:16.868850: step: 1556/529, loss: 0.042127083986997604
2023-01-23 00:03:18.008336: step: 1560/529, loss: 0.14104318618774414
2023-01-23 00:03:19.150525: step: 1564/529, loss: 0.11853523552417755
2023-01-23 00:03:20.310543: step: 1568/529, loss: 0.13271060585975647
2023-01-23 00:03:21.445548: step: 1572/529, loss: 0.20564812421798706
2023-01-23 00:03:22.588249: step: 1576/529, loss: 0.083777517080307
2023-01-23 00:03:23.705092: step: 1580/529, loss: 0.11326833069324493
2023-01-23 00:03:24.862335: step: 1584/529, loss: 0.23062877357006073
2023-01-23 00:03:25.986885: step: 1588/529, loss: 0.13704939186573029
2023-01-23 00:03:27.091659: step: 1592/529, loss: 0.09096350520849228
2023-01-23 00:03:28.255595: step: 1596/529, loss: 0.07349219918251038
2023-01-23 00:03:29.386670: step: 1600/529, loss: 0.09050159901380539
2023-01-23 00:03:30.542665: step: 1604/529, loss: 0.12973442673683167
2023-01-23 00:03:31.685428: step: 1608/529, loss: 0.22155389189720154
2023-01-23 00:03:32.824402: step: 1612/529, loss: 0.10656996071338654
2023-01-23 00:03:33.985785: step: 1616/529, loss: 0.1378362774848938
2023-01-23 00:03:35.107557: step: 1620/529, loss: 0.10250511765480042
2023-01-23 00:03:36.226149: step: 1624/529, loss: 0.8444705605506897
2023-01-23 00:03:37.353524: step: 1628/529, loss: 0.10342703014612198
2023-01-23 00:03:38.480177: step: 1632/529, loss: 0.4166475236415863
2023-01-23 00:03:39.624964: step: 1636/529, loss: 0.15266117453575134
2023-01-23 00:03:40.722782: step: 1640/529, loss: 0.3019540309906006
2023-01-23 00:03:41.867367: step: 1644/529, loss: 0.1784309446811676
2023-01-23 00:03:43.037081: step: 1648/529, loss: 0.43192481994628906
2023-01-23 00:03:44.149570: step: 1652/529, loss: 0.2244025319814682
2023-01-23 00:03:45.282580: step: 1656/529, loss: 0.06013345718383789
2023-01-23 00:03:46.475568: step: 1660/529, loss: 0.0564112663269043
2023-01-23 00:03:47.621150: step: 1664/529, loss: 0.2510750889778137
2023-01-23 00:03:48.787383: step: 1668/529, loss: 0.11374817043542862
2023-01-23 00:03:49.916755: step: 1672/529, loss: 0.11951828002929688
2023-01-23 00:03:51.064992: step: 1676/529, loss: 0.18748603761196136
2023-01-23 00:03:52.230826: step: 1680/529, loss: 0.43095022439956665
2023-01-23 00:03:53.367325: step: 1684/529, loss: 0.7503036260604858
2023-01-23 00:03:54.506676: step: 1688/529, loss: 0.8607301115989685
2023-01-23 00:03:55.622317: step: 1692/529, loss: 0.025034546852111816
2023-01-23 00:03:56.787657: step: 1696/529, loss: 0.11721468716859818
2023-01-23 00:03:57.923545: step: 1700/529, loss: 0.4294639229774475
2023-01-23 00:03:59.068198: step: 1704/529, loss: 0.668768584728241
2023-01-23 00:04:00.223420: step: 1708/529, loss: 0.11543674767017365
2023-01-23 00:04:01.344635: step: 1712/529, loss: 0.23011913895606995
2023-01-23 00:04:02.483420: step: 1716/529, loss: 1.3662277460098267
2023-01-23 00:04:03.631915: step: 1720/529, loss: 0.04422121122479439
2023-01-23 00:04:04.789741: step: 1724/529, loss: 0.14086276292800903
2023-01-23 00:04:05.925910: step: 1728/529, loss: 0.11898299306631088
2023-01-23 00:04:07.065424: step: 1732/529, loss: 0.07863965630531311
2023-01-23 00:04:08.180506: step: 1736/529, loss: 0.17624256014823914
2023-01-23 00:04:09.352728: step: 1740/529, loss: 0.436884343624115
2023-01-23 00:04:10.501174: step: 1744/529, loss: 0.4204428195953369
2023-01-23 00:04:11.629704: step: 1748/529, loss: 0.11820783466100693
2023-01-23 00:04:12.760772: step: 1752/529, loss: 0.14672546088695526
2023-01-23 00:04:13.936875: step: 1756/529, loss: 0.6049914360046387
2023-01-23 00:04:15.061977: step: 1760/529, loss: 0.13614541292190552
2023-01-23 00:04:16.193946: step: 1764/529, loss: 0.2935635447502136
2023-01-23 00:04:17.341762: step: 1768/529, loss: 0.5210188031196594
2023-01-23 00:04:18.463048: step: 1772/529, loss: 0.1947949230670929
2023-01-23 00:04:19.650000: step: 1776/529, loss: 1.035811185836792
2023-01-23 00:04:20.801345: step: 1780/529, loss: 0.8085301518440247
2023-01-23 00:04:21.932772: step: 1784/529, loss: 0.39702004194259644
2023-01-23 00:04:23.067021: step: 1788/529, loss: 0.7795924544334412
2023-01-23 00:04:24.205276: step: 1792/529, loss: 0.17830868065357208
2023-01-23 00:04:25.336121: step: 1796/529, loss: 0.2492694854736328
2023-01-23 00:04:26.451259: step: 1800/529, loss: 0.09401115775108337
2023-01-23 00:04:27.580501: step: 1804/529, loss: 0.18963509798049927
2023-01-23 00:04:28.746989: step: 1808/529, loss: 0.24590949714183807
2023-01-23 00:04:29.910272: step: 1812/529, loss: 0.9545996785163879
2023-01-23 00:04:31.037021: step: 1816/529, loss: 0.3508211374282837
2023-01-23 00:04:32.182092: step: 1820/529, loss: 0.1993359625339508
2023-01-23 00:04:33.317359: step: 1824/529, loss: 0.2797101140022278
2023-01-23 00:04:34.439813: step: 1828/529, loss: 0.30427980422973633
2023-01-23 00:04:35.591601: step: 1832/529, loss: 0.3970484137535095
2023-01-23 00:04:36.735399: step: 1836/529, loss: 0.28484582901000977
2023-01-23 00:04:37.871753: step: 1840/529, loss: 0.09865588694810867
2023-01-23 00:04:38.997922: step: 1844/529, loss: 0.39399316906929016
2023-01-23 00:04:40.127792: step: 1848/529, loss: 0.11836538463830948
2023-01-23 00:04:41.308844: step: 1852/529, loss: 0.2808743119239807
2023-01-23 00:04:42.450683: step: 1856/529, loss: 1.8474198579788208
2023-01-23 00:04:43.592034: step: 1860/529, loss: 0.08241195976734161
2023-01-23 00:04:44.725454: step: 1864/529, loss: 0.45600995421409607
2023-01-23 00:04:45.881780: step: 1868/529, loss: 0.07925812900066376
2023-01-23 00:04:47.012924: step: 1872/529, loss: 0.12548808753490448
2023-01-23 00:04:48.122819: step: 1876/529, loss: 0.2866532802581787
2023-01-23 00:04:49.284788: step: 1880/529, loss: 1.063374400138855
2023-01-23 00:04:50.440721: step: 1884/529, loss: 0.23573750257492065
2023-01-23 00:04:51.606299: step: 1888/529, loss: 0.37855157256126404
2023-01-23 00:04:52.748857: step: 1892/529, loss: 0.6805038452148438
2023-01-23 00:04:53.879620: step: 1896/529, loss: 0.11260871589183807
2023-01-23 00:04:55.030580: step: 1900/529, loss: 0.31062474846839905
2023-01-23 00:04:56.169131: step: 1904/529, loss: 0.7683759331703186
2023-01-23 00:04:57.302732: step: 1908/529, loss: 0.17898626625537872
2023-01-23 00:04:58.437021: step: 1912/529, loss: 0.15403634309768677
2023-01-23 00:04:59.564766: step: 1916/529, loss: 1.7226102352142334
2023-01-23 00:05:00.693496: step: 1920/529, loss: 0.09516830742359161
2023-01-23 00:05:01.836672: step: 1924/529, loss: 0.24629083275794983
2023-01-23 00:05:02.997852: step: 1928/529, loss: 1.373489260673523
2023-01-23 00:05:04.159408: step: 1932/529, loss: 1.7580018043518066
2023-01-23 00:05:05.299760: step: 1936/529, loss: 0.23545204102993011
2023-01-23 00:05:06.426013: step: 1940/529, loss: 0.13541316986083984
2023-01-23 00:05:07.548378: step: 1944/529, loss: 0.1970551609992981
2023-01-23 00:05:08.680847: step: 1948/529, loss: 1.1924164295196533
2023-01-23 00:05:09.815976: step: 1952/529, loss: 0.6954349279403687
2023-01-23 00:05:10.990450: step: 1956/529, loss: 0.11528763920068741
2023-01-23 00:05:12.163507: step: 1960/529, loss: 0.1927940398454666
2023-01-23 00:05:13.319695: step: 1964/529, loss: 0.21880188584327698
2023-01-23 00:05:14.453550: step: 1968/529, loss: 0.19161270558834076
2023-01-23 00:05:15.609073: step: 1972/529, loss: 0.049072980880737305
2023-01-23 00:05:16.723656: step: 1976/529, loss: 0.21237002313137054
2023-01-23 00:05:17.862128: step: 1980/529, loss: 0.7952540516853333
2023-01-23 00:05:18.999246: step: 1984/529, loss: 0.6937505006790161
2023-01-23 00:05:20.123246: step: 1988/529, loss: 0.8313053846359253
2023-01-23 00:05:21.251688: step: 1992/529, loss: 0.5270646810531616
2023-01-23 00:05:22.441315: step: 1996/529, loss: 6.488864421844482
2023-01-23 00:05:23.592729: step: 2000/529, loss: 0.2873687148094177
2023-01-23 00:05:24.742321: step: 2004/529, loss: 0.98978590965271
2023-01-23 00:05:25.904656: step: 2008/529, loss: 0.23303309082984924
2023-01-23 00:05:27.021809: step: 2012/529, loss: 0.2435900717973709
2023-01-23 00:05:28.174709: step: 2016/529, loss: 0.1796712875366211
2023-01-23 00:05:29.313751: step: 2020/529, loss: 2.326051950454712
2023-01-23 00:05:30.465488: step: 2024/529, loss: 0.18379679322242737
2023-01-23 00:05:31.627113: step: 2028/529, loss: 0.09204272925853729
2023-01-23 00:05:32.781768: step: 2032/529, loss: 1.51820969581604
2023-01-23 00:05:33.951267: step: 2036/529, loss: 1.0125430822372437
2023-01-23 00:05:35.101742: step: 2040/529, loss: 0.3211841583251953
2023-01-23 00:05:36.237887: step: 2044/529, loss: 0.21571610867977142
2023-01-23 00:05:37.390124: step: 2048/529, loss: 0.07568865269422531
2023-01-23 00:05:38.520436: step: 2052/529, loss: 0.055057816207408905
2023-01-23 00:05:39.657432: step: 2056/529, loss: 0.9104283452033997
2023-01-23 00:05:40.764072: step: 2060/529, loss: 0.8375106453895569
2023-01-23 00:05:41.925844: step: 2064/529, loss: 0.045627787709236145
2023-01-23 00:05:43.134223: step: 2068/529, loss: 1.3845282793045044
2023-01-23 00:05:44.276649: step: 2072/529, loss: 0.37636032700538635
2023-01-23 00:05:45.415836: step: 2076/529, loss: 0.15654096007347107
2023-01-23 00:05:46.544033: step: 2080/529, loss: 0.7759748101234436
2023-01-23 00:05:47.663636: step: 2084/529, loss: 0.19368892908096313
2023-01-23 00:05:48.802420: step: 2088/529, loss: 0.13523884117603302
2023-01-23 00:05:49.941578: step: 2092/529, loss: 1.2407002449035645
2023-01-23 00:05:51.053689: step: 2096/529, loss: 0.23802976310253143
2023-01-23 00:05:52.178646: step: 2100/529, loss: 0.09033231437206268
2023-01-23 00:05:53.334701: step: 2104/529, loss: 1.3069990873336792
2023-01-23 00:05:54.459636: step: 2108/529, loss: 0.18443596363067627
2023-01-23 00:05:55.601373: step: 2112/529, loss: 0.10947924107313156
2023-01-23 00:05:56.730609: step: 2116/529, loss: 1.9434700012207031
==================================================
Loss: 0.557
--------------------
Dev: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.6301369863013698, 'r': 0.8518518518518519, 'f1': 0.7244094488188976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6304347826086957, 'r': 0.4603174603174603, 'f1': 0.5321100917431192}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.5135135135135135, 'r': 0.5277777777777778, 'f1': 0.5205479452054794}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.6301369863013698, 'r': 0.8518518518518519, 'f1': 0.7244094488188976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.574869109947644, 'r': 0.7310252996005326, 'f1': 0.6436107854630715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.5623836126629422, 'r': 0.6998841251448435, 'f1': 0.6236448115642746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7142857142857143, 'r': 0.47619047619047616, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5135135135135135, 'r': 0.5277777777777778, 'f1': 0.5205479452054794}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:06:55.931379: step: 4/529, loss: 0.24466048181056976
2023-01-23 00:06:57.065026: step: 8/529, loss: 0.11129050701856613
2023-01-23 00:06:58.192358: step: 12/529, loss: 0.16316938400268555
2023-01-23 00:06:59.331972: step: 16/529, loss: 0.3817647695541382
2023-01-23 00:07:00.457883: step: 20/529, loss: 0.1378255933523178
2023-01-23 00:07:01.597322: step: 24/529, loss: 0.3425389230251312
2023-01-23 00:07:02.911875: step: 28/529, loss: 0.17779813706874847
2023-01-23 00:07:04.027044: step: 32/529, loss: 1.1851680278778076
2023-01-23 00:07:05.155352: step: 36/529, loss: 0.16075149178504944
2023-01-23 00:07:06.285433: step: 40/529, loss: 0.12994928658008575
2023-01-23 00:07:07.429125: step: 44/529, loss: 0.17955541610717773
2023-01-23 00:07:08.591522: step: 48/529, loss: 0.12387075275182724
2023-01-23 00:07:09.749767: step: 52/529, loss: 0.11709528416395187
2023-01-23 00:07:10.886566: step: 56/529, loss: 0.2231781929731369
2023-01-23 00:07:12.020332: step: 60/529, loss: 1.452794075012207
2023-01-23 00:07:13.141197: step: 64/529, loss: 0.05014796555042267
2023-01-23 00:07:14.258601: step: 68/529, loss: 0.06693992763757706
2023-01-23 00:07:15.376581: step: 72/529, loss: 0.1076974868774414
2023-01-23 00:07:16.497700: step: 76/529, loss: 0.1814381182193756
2023-01-23 00:07:17.638358: step: 80/529, loss: 0.14542865753173828
2023-01-23 00:07:18.787378: step: 84/529, loss: 0.0811973586678505
2023-01-23 00:07:19.884914: step: 88/529, loss: 0.1084100529551506
2023-01-23 00:07:21.027930: step: 92/529, loss: 0.22772979736328125
2023-01-23 00:07:22.161943: step: 96/529, loss: 0.021969128400087357
2023-01-23 00:07:23.301602: step: 100/529, loss: 0.1365947723388672
2023-01-23 00:07:24.423943: step: 104/529, loss: 0.10780796408653259
2023-01-23 00:07:25.526373: step: 108/529, loss: 0.45810508728027344
2023-01-23 00:07:26.707079: step: 112/529, loss: 0.39113712310791016
2023-01-23 00:07:27.847545: step: 116/529, loss: 1.3864153623580933
2023-01-23 00:07:28.954767: step: 120/529, loss: 0.3315982222557068
2023-01-23 00:07:30.093209: step: 124/529, loss: 0.6596972346305847
2023-01-23 00:07:31.248683: step: 128/529, loss: 0.21459154784679413
2023-01-23 00:07:32.406170: step: 132/529, loss: 0.4117923676967621
2023-01-23 00:07:33.547740: step: 136/529, loss: 0.14763402938842773
2023-01-23 00:07:34.698037: step: 140/529, loss: 0.657440721988678
2023-01-23 00:07:35.824231: step: 144/529, loss: 0.6973082423210144
2023-01-23 00:07:36.987955: step: 148/529, loss: 0.7258090972900391
2023-01-23 00:07:38.118999: step: 152/529, loss: 0.12133245170116425
2023-01-23 00:07:39.217278: step: 156/529, loss: 0.11962912231683731
2023-01-23 00:07:40.359860: step: 160/529, loss: 0.09799843281507492
2023-01-23 00:07:41.482147: step: 164/529, loss: 0.16272759437561035
2023-01-23 00:07:42.615379: step: 168/529, loss: 1.2910672426223755
2023-01-23 00:07:43.775288: step: 172/529, loss: 0.6917350888252258
2023-01-23 00:07:44.916606: step: 176/529, loss: 0.16712398827075958
2023-01-23 00:07:46.067260: step: 180/529, loss: 0.18724757432937622
2023-01-23 00:07:47.209460: step: 184/529, loss: 0.0921320915222168
2023-01-23 00:07:48.373171: step: 188/529, loss: 0.2076890468597412
2023-01-23 00:07:49.542510: step: 192/529, loss: 0.1354234665632248
2023-01-23 00:07:50.685823: step: 196/529, loss: 0.20211133360862732
2023-01-23 00:07:51.832598: step: 200/529, loss: 1.0623573064804077
2023-01-23 00:07:52.963483: step: 204/529, loss: 0.44535207748413086
2023-01-23 00:07:54.110926: step: 208/529, loss: 0.17244748771190643
2023-01-23 00:07:55.256801: step: 212/529, loss: 0.6709588170051575
2023-01-23 00:07:56.422851: step: 216/529, loss: 0.07567596435546875
2023-01-23 00:07:57.565480: step: 220/529, loss: 0.0934787467122078
2023-01-23 00:07:58.689924: step: 224/529, loss: 0.07409334182739258
2023-01-23 00:07:59.840026: step: 228/529, loss: 0.24432912468910217
2023-01-23 00:08:00.994048: step: 232/529, loss: 0.21654443442821503
2023-01-23 00:08:02.124653: step: 236/529, loss: 0.06525573879480362
2023-01-23 00:08:03.271073: step: 240/529, loss: 0.09920063614845276
2023-01-23 00:08:04.444669: step: 244/529, loss: 0.0917000100016594
2023-01-23 00:08:05.593708: step: 248/529, loss: 0.06005983427166939
2023-01-23 00:08:06.727419: step: 252/529, loss: 1.3319963216781616
2023-01-23 00:08:07.850823: step: 256/529, loss: 0.6950969099998474
2023-01-23 00:08:08.988178: step: 260/529, loss: 0.7448029518127441
2023-01-23 00:08:10.135675: step: 264/529, loss: 0.7736472487449646
2023-01-23 00:08:11.261881: step: 268/529, loss: 0.28931865096092224
2023-01-23 00:08:12.412858: step: 272/529, loss: 0.13168630003929138
2023-01-23 00:08:13.569088: step: 276/529, loss: 0.8730499148368835
2023-01-23 00:08:14.710787: step: 280/529, loss: 0.2902229428291321
2023-01-23 00:08:15.846086: step: 284/529, loss: 0.18720950186252594
2023-01-23 00:08:16.975480: step: 288/529, loss: 0.15021830797195435
2023-01-23 00:08:18.145073: step: 292/529, loss: 0.3634463846683502
2023-01-23 00:08:19.312124: step: 296/529, loss: 0.3067096769809723
2023-01-23 00:08:20.446067: step: 300/529, loss: 0.08461332321166992
2023-01-23 00:08:21.579373: step: 304/529, loss: 0.08676118403673172
2023-01-23 00:08:22.702156: step: 308/529, loss: 0.08008575439453125
2023-01-23 00:08:23.827356: step: 312/529, loss: 0.11048805713653564
2023-01-23 00:08:24.977792: step: 316/529, loss: 0.1701037436723709
2023-01-23 00:08:26.138110: step: 320/529, loss: 0.23445215821266174
2023-01-23 00:08:27.283100: step: 324/529, loss: 0.12070250511169434
2023-01-23 00:08:28.413684: step: 328/529, loss: 0.16680152714252472
2023-01-23 00:08:29.612629: step: 332/529, loss: 0.38611292839050293
2023-01-23 00:08:30.756341: step: 336/529, loss: 0.07200375199317932
2023-01-23 00:08:31.927444: step: 340/529, loss: 0.6658762097358704
2023-01-23 00:08:33.155928: step: 344/529, loss: 0.33177271485328674
2023-01-23 00:08:34.309241: step: 348/529, loss: 0.4771179258823395
2023-01-23 00:08:35.458473: step: 352/529, loss: 0.16518573462963104
2023-01-23 00:08:36.609475: step: 356/529, loss: 0.07805061340332031
2023-01-23 00:08:37.754715: step: 360/529, loss: 0.5546988248825073
2023-01-23 00:08:38.876448: step: 364/529, loss: 0.11429693549871445
2023-01-23 00:08:40.022012: step: 368/529, loss: 0.08749409019947052
2023-01-23 00:08:41.190450: step: 372/529, loss: 0.0869588851928711
2023-01-23 00:08:42.315208: step: 376/529, loss: 0.17761069536209106
2023-01-23 00:08:43.460802: step: 380/529, loss: 0.08462834358215332
2023-01-23 00:08:44.590055: step: 384/529, loss: 0.06631775200366974
2023-01-23 00:08:45.738973: step: 388/529, loss: 0.18535280227661133
2023-01-23 00:08:46.887707: step: 392/529, loss: 0.7874088287353516
2023-01-23 00:08:48.039754: step: 396/529, loss: 0.05974102020263672
2023-01-23 00:08:49.205809: step: 400/529, loss: 0.1407126486301422
2023-01-23 00:08:50.343900: step: 404/529, loss: 0.09984250366687775
2023-01-23 00:08:51.476236: step: 408/529, loss: 0.0883147269487381
2023-01-23 00:08:52.628437: step: 412/529, loss: 0.31385642290115356
2023-01-23 00:08:53.760520: step: 416/529, loss: 0.05303812026977539
2023-01-23 00:08:54.883680: step: 420/529, loss: 0.10931988060474396
2023-01-23 00:08:56.033952: step: 424/529, loss: 0.8752502202987671
2023-01-23 00:08:57.154613: step: 428/529, loss: 0.02527799643576145
2023-01-23 00:08:58.303250: step: 432/529, loss: 0.24102745950222015
2023-01-23 00:08:59.445844: step: 436/529, loss: 0.09306631237268448
2023-01-23 00:09:00.597110: step: 440/529, loss: 0.9254924058914185
2023-01-23 00:09:01.742411: step: 444/529, loss: 0.74078369140625
2023-01-23 00:09:02.880169: step: 448/529, loss: 0.29278564453125
2023-01-23 00:09:04.013632: step: 452/529, loss: 0.8850492238998413
2023-01-23 00:09:05.152788: step: 456/529, loss: 0.16823837161064148
2023-01-23 00:09:06.281843: step: 460/529, loss: 0.41014689207077026
2023-01-23 00:09:07.414694: step: 464/529, loss: 0.017510438337922096
2023-01-23 00:09:08.544116: step: 468/529, loss: 0.47500133514404297
2023-01-23 00:09:09.694576: step: 472/529, loss: 0.6120018362998962
2023-01-23 00:09:10.822777: step: 476/529, loss: 0.08728199452161789
2023-01-23 00:09:11.967765: step: 480/529, loss: 0.11671486496925354
2023-01-23 00:09:13.123726: step: 484/529, loss: 0.6810390949249268
2023-01-23 00:09:14.251828: step: 488/529, loss: 0.0753626823425293
2023-01-23 00:09:15.385422: step: 492/529, loss: 0.787083625793457
2023-01-23 00:09:16.512856: step: 496/529, loss: 0.5044618248939514
2023-01-23 00:09:17.638422: step: 500/529, loss: 0.7071605324745178
2023-01-23 00:09:18.766349: step: 504/529, loss: 0.6244059205055237
2023-01-23 00:09:19.890001: step: 508/529, loss: 0.2614052891731262
2023-01-23 00:09:21.005921: step: 512/529, loss: 0.5192671418190002
2023-01-23 00:09:22.145508: step: 516/529, loss: 0.1447453796863556
2023-01-23 00:09:23.281914: step: 520/529, loss: 0.25025472044944763
2023-01-23 00:09:24.435145: step: 524/529, loss: 0.4523128271102905
2023-01-23 00:09:25.561592: step: 528/529, loss: 0.0843936949968338
2023-01-23 00:09:26.703452: step: 532/529, loss: 0.2642250955104828
2023-01-23 00:09:27.865393: step: 536/529, loss: 0.5646122694015503
2023-01-23 00:09:29.003059: step: 540/529, loss: 0.3771764039993286
2023-01-23 00:09:30.131979: step: 544/529, loss: 0.3648337423801422
2023-01-23 00:09:31.273468: step: 548/529, loss: 0.0735812783241272
2023-01-23 00:09:32.409470: step: 552/529, loss: 0.10009908676147461
2023-01-23 00:09:33.556562: step: 556/529, loss: 0.8021878600120544
2023-01-23 00:09:34.711411: step: 560/529, loss: 0.13122233748435974
2023-01-23 00:09:35.841068: step: 564/529, loss: 0.6014177799224854
2023-01-23 00:09:36.982488: step: 568/529, loss: 0.1372823715209961
2023-01-23 00:09:38.128147: step: 572/529, loss: 0.13991041481494904
2023-01-23 00:09:39.263519: step: 576/529, loss: 0.1183624267578125
2023-01-23 00:09:40.390842: step: 580/529, loss: 0.07020334899425507
2023-01-23 00:09:41.520883: step: 584/529, loss: 0.11784706264734268
2023-01-23 00:09:42.645852: step: 588/529, loss: 0.8573439717292786
2023-01-23 00:09:43.782543: step: 592/529, loss: 0.8647388219833374
2023-01-23 00:09:44.923829: step: 596/529, loss: 0.1837974637746811
2023-01-23 00:09:46.040662: step: 600/529, loss: 0.3412172794342041
2023-01-23 00:09:47.210531: step: 604/529, loss: 0.12396860122680664
2023-01-23 00:09:48.342806: step: 608/529, loss: 0.06313876807689667
2023-01-23 00:09:49.459438: step: 612/529, loss: 0.08566518127918243
2023-01-23 00:09:50.599395: step: 616/529, loss: 0.43108296394348145
2023-01-23 00:09:51.715659: step: 620/529, loss: 0.18287301063537598
2023-01-23 00:09:52.868362: step: 624/529, loss: 0.15974578261375427
2023-01-23 00:09:54.011598: step: 628/529, loss: 0.13344326615333557
2023-01-23 00:09:55.200478: step: 632/529, loss: 0.09007206559181213
2023-01-23 00:09:56.349774: step: 636/529, loss: 0.15565833449363708
2023-01-23 00:09:57.491871: step: 640/529, loss: 0.25013208389282227
2023-01-23 00:09:58.618988: step: 644/529, loss: 5.261640548706055
2023-01-23 00:09:59.774628: step: 648/529, loss: 0.29935896396636963
2023-01-23 00:10:00.901390: step: 652/529, loss: 6.333972454071045
2023-01-23 00:10:02.042538: step: 656/529, loss: 0.08399935066699982
2023-01-23 00:10:03.148094: step: 660/529, loss: 0.08417835831642151
2023-01-23 00:10:04.283637: step: 664/529, loss: 0.5735808610916138
2023-01-23 00:10:05.412363: step: 668/529, loss: 0.21012167632579803
2023-01-23 00:10:06.559401: step: 672/529, loss: 0.18438653647899628
2023-01-23 00:10:07.714642: step: 676/529, loss: 0.07517824321985245
2023-01-23 00:10:08.826409: step: 680/529, loss: 0.25263285636901855
2023-01-23 00:10:09.959852: step: 684/529, loss: 0.19530019164085388
2023-01-23 00:10:11.097527: step: 688/529, loss: 0.153814896941185
2023-01-23 00:10:12.247410: step: 692/529, loss: 0.17285394668579102
2023-01-23 00:10:13.384134: step: 696/529, loss: 0.21799883246421814
2023-01-23 00:10:14.527902: step: 700/529, loss: 0.14127960801124573
2023-01-23 00:10:15.664031: step: 704/529, loss: 0.2035275399684906
2023-01-23 00:10:16.795833: step: 708/529, loss: 0.05994949862360954
2023-01-23 00:10:17.950033: step: 712/529, loss: 0.4114479124546051
2023-01-23 00:10:19.066014: step: 716/529, loss: 0.4014359712600708
2023-01-23 00:10:20.212587: step: 720/529, loss: 1.0294115543365479
2023-01-23 00:10:21.357942: step: 724/529, loss: 0.876505970954895
2023-01-23 00:10:22.492335: step: 728/529, loss: 0.23265314102172852
2023-01-23 00:10:23.624812: step: 732/529, loss: 0.08632984757423401
2023-01-23 00:10:24.755470: step: 736/529, loss: 1.0822360515594482
2023-01-23 00:10:25.930126: step: 740/529, loss: 0.1900378167629242
2023-01-23 00:10:27.049844: step: 744/529, loss: 0.19116735458374023
2023-01-23 00:10:28.181005: step: 748/529, loss: 0.7378531098365784
2023-01-23 00:10:29.349742: step: 752/529, loss: 0.09987787902355194
2023-01-23 00:10:30.489584: step: 756/529, loss: 0.17485705018043518
2023-01-23 00:10:31.660929: step: 760/529, loss: 0.10996036231517792
2023-01-23 00:10:32.806199: step: 764/529, loss: 0.20369598269462585
2023-01-23 00:10:33.966821: step: 768/529, loss: 0.11662064492702484
2023-01-23 00:10:35.089164: step: 772/529, loss: 0.10381467640399933
2023-01-23 00:10:36.202131: step: 776/529, loss: 0.22626467049121857
2023-01-23 00:10:37.338655: step: 780/529, loss: 0.29835304617881775
2023-01-23 00:10:38.468356: step: 784/529, loss: 0.1822047233581543
2023-01-23 00:10:39.636090: step: 788/529, loss: 0.2610871195793152
2023-01-23 00:10:40.793541: step: 792/529, loss: 0.26282861828804016
2023-01-23 00:10:41.947600: step: 796/529, loss: 0.08006184548139572
2023-01-23 00:10:43.125624: step: 800/529, loss: 0.7551807761192322
2023-01-23 00:10:44.262989: step: 804/529, loss: 0.12836794555187225
2023-01-23 00:10:45.393001: step: 808/529, loss: 0.13698796927928925
2023-01-23 00:10:46.542303: step: 812/529, loss: 0.9885527491569519
2023-01-23 00:10:47.692429: step: 816/529, loss: 0.20509730279445648
2023-01-23 00:10:48.823034: step: 820/529, loss: 0.14692345261573792
2023-01-23 00:10:49.969017: step: 824/529, loss: 0.3278070092201233
2023-01-23 00:10:51.107561: step: 828/529, loss: 0.27918368577957153
2023-01-23 00:10:52.275499: step: 832/529, loss: 0.03283729776740074
2023-01-23 00:10:53.405259: step: 836/529, loss: 1.1109706163406372
2023-01-23 00:10:54.533477: step: 840/529, loss: 0.11066427826881409
2023-01-23 00:10:55.677735: step: 844/529, loss: 0.20504646003246307
2023-01-23 00:10:56.817570: step: 848/529, loss: 5.909251689910889
2023-01-23 00:10:57.931508: step: 852/529, loss: 0.6502519249916077
2023-01-23 00:10:59.048772: step: 856/529, loss: 0.14182119071483612
2023-01-23 00:11:00.218433: step: 860/529, loss: 0.09417720139026642
2023-01-23 00:11:01.348958: step: 864/529, loss: 0.7739275097846985
2023-01-23 00:11:02.546657: step: 868/529, loss: 0.1988564431667328
2023-01-23 00:11:03.662626: step: 872/529, loss: 0.09548965096473694
2023-01-23 00:11:04.783183: step: 876/529, loss: 0.0929441973567009
2023-01-23 00:11:05.918406: step: 880/529, loss: 0.10891647636890411
2023-01-23 00:11:07.053765: step: 884/529, loss: 0.6041755676269531
2023-01-23 00:11:08.192356: step: 888/529, loss: 0.7679823637008667
2023-01-23 00:11:09.336353: step: 892/529, loss: 0.19759735465049744
2023-01-23 00:11:10.475762: step: 896/529, loss: 0.20988713204860687
2023-01-23 00:11:11.615146: step: 900/529, loss: 0.929301381111145
2023-01-23 00:11:12.744498: step: 904/529, loss: 0.07646217197179794
2023-01-23 00:11:13.888790: step: 908/529, loss: 1.0134717226028442
2023-01-23 00:11:15.012945: step: 912/529, loss: 0.1411271095275879
2023-01-23 00:11:16.133194: step: 916/529, loss: 0.09640460461378098
2023-01-23 00:11:17.280883: step: 920/529, loss: 0.1452304869890213
2023-01-23 00:11:18.452650: step: 924/529, loss: 0.264639288187027
2023-01-23 00:11:19.605440: step: 928/529, loss: 0.02313246577978134
2023-01-23 00:11:20.755108: step: 932/529, loss: 0.11836281418800354
2023-01-23 00:11:21.883847: step: 936/529, loss: 0.2608543336391449
2023-01-23 00:11:23.023470: step: 940/529, loss: 0.19579553604125977
2023-01-23 00:11:24.141084: step: 944/529, loss: 0.07904257625341415
2023-01-23 00:11:25.280457: step: 948/529, loss: 0.10473886132240295
2023-01-23 00:11:26.435370: step: 952/529, loss: 0.17764106392860413
2023-01-23 00:11:27.603188: step: 956/529, loss: 0.132731631398201
2023-01-23 00:11:28.738078: step: 960/529, loss: 0.18035712838172913
2023-01-23 00:11:29.858299: step: 964/529, loss: 0.14639359712600708
2023-01-23 00:11:30.970613: step: 968/529, loss: 0.18622994422912598
2023-01-23 00:11:32.119739: step: 972/529, loss: 0.266743928194046
2023-01-23 00:11:33.289271: step: 976/529, loss: 0.08481035381555557
2023-01-23 00:11:34.414360: step: 980/529, loss: 0.16922646760940552
2023-01-23 00:11:35.541234: step: 984/529, loss: 0.15957021713256836
2023-01-23 00:11:36.662194: step: 988/529, loss: 0.10932941734790802
2023-01-23 00:11:37.817531: step: 992/529, loss: 0.5267252922058105
2023-01-23 00:11:38.963857: step: 996/529, loss: 0.08189411461353302
2023-01-23 00:11:40.098126: step: 1000/529, loss: 0.09332104027271271
2023-01-23 00:11:41.260600: step: 1004/529, loss: 1.0411455631256104
2023-01-23 00:11:42.373830: step: 1008/529, loss: 0.2185802459716797
2023-01-23 00:11:43.511921: step: 1012/529, loss: 0.10366229712963104
2023-01-23 00:11:44.665990: step: 1016/529, loss: 0.20752954483032227
2023-01-23 00:11:45.800482: step: 1020/529, loss: 0.1996767520904541
2023-01-23 00:11:46.920365: step: 1024/529, loss: 0.8366801738739014
2023-01-23 00:11:48.065486: step: 1028/529, loss: 0.05245428532361984
2023-01-23 00:11:49.174997: step: 1032/529, loss: 0.1484830379486084
2023-01-23 00:11:50.330054: step: 1036/529, loss: 0.10129952430725098
2023-01-23 00:11:51.474801: step: 1040/529, loss: 0.5959730744361877
2023-01-23 00:11:52.620110: step: 1044/529, loss: 0.12547464668750763
2023-01-23 00:11:53.767520: step: 1048/529, loss: 0.8448886871337891
2023-01-23 00:11:54.896993: step: 1052/529, loss: 0.05065946653485298
2023-01-23 00:11:56.051798: step: 1056/529, loss: 0.36637231707572937
2023-01-23 00:11:57.157223: step: 1060/529, loss: 0.5167497396469116
2023-01-23 00:11:58.319423: step: 1064/529, loss: 0.4764404296875
2023-01-23 00:11:59.427084: step: 1068/529, loss: 0.08988809585571289
2023-01-23 00:12:00.561056: step: 1072/529, loss: 0.01889929734170437
2023-01-23 00:12:01.672425: step: 1076/529, loss: 0.1427462249994278
2023-01-23 00:12:02.825040: step: 1080/529, loss: 0.7212098836898804
2023-01-23 00:12:03.943747: step: 1084/529, loss: 0.5810263156890869
2023-01-23 00:12:05.082815: step: 1088/529, loss: 0.33085861802101135
2023-01-23 00:12:06.235184: step: 1092/529, loss: 0.11662331223487854
2023-01-23 00:12:07.363158: step: 1096/529, loss: 0.42196404933929443
2023-01-23 00:12:08.503234: step: 1100/529, loss: 0.7228653430938721
2023-01-23 00:12:09.638676: step: 1104/529, loss: 0.09744454175233841
2023-01-23 00:12:10.783678: step: 1108/529, loss: 0.6256855130195618
2023-01-23 00:12:11.922140: step: 1112/529, loss: 0.05705108493566513
2023-01-23 00:12:13.051565: step: 1116/529, loss: 0.06933460384607315
2023-01-23 00:12:14.179376: step: 1120/529, loss: 5.567978858947754
2023-01-23 00:12:15.335095: step: 1124/529, loss: 0.12601642310619354
2023-01-23 00:12:16.486258: step: 1128/529, loss: 0.06533446162939072
2023-01-23 00:12:17.635874: step: 1132/529, loss: 0.4048699736595154
2023-01-23 00:12:18.779954: step: 1136/529, loss: 0.3857220709323883
2023-01-23 00:12:19.902973: step: 1140/529, loss: 0.0532347671687603
2023-01-23 00:12:21.056729: step: 1144/529, loss: 0.09898900985717773
2023-01-23 00:12:22.184023: step: 1148/529, loss: 0.06811871379613876
2023-01-23 00:12:23.322783: step: 1152/529, loss: 1.375936508178711
2023-01-23 00:12:24.469742: step: 1156/529, loss: 0.07062454521656036
2023-01-23 00:12:25.597862: step: 1160/529, loss: 0.2772492468357086
2023-01-23 00:12:26.753275: step: 1164/529, loss: 0.4373779296875
2023-01-23 00:12:27.888998: step: 1168/529, loss: 0.5396996736526489
2023-01-23 00:12:29.033374: step: 1172/529, loss: 0.5175167322158813
2023-01-23 00:12:30.181021: step: 1176/529, loss: 0.1952734887599945
2023-01-23 00:12:31.330139: step: 1180/529, loss: 0.10334673523902893
2023-01-23 00:12:32.461152: step: 1184/529, loss: 0.16952762007713318
2023-01-23 00:12:33.599401: step: 1188/529, loss: 0.4987879693508148
2023-01-23 00:12:34.750930: step: 1192/529, loss: 0.06664963066577911
2023-01-23 00:12:35.884386: step: 1196/529, loss: 0.552270770072937
2023-01-23 00:12:37.049081: step: 1200/529, loss: 0.39646783471107483
2023-01-23 00:12:38.216562: step: 1204/529, loss: 0.6991478204727173
2023-01-23 00:12:39.365290: step: 1208/529, loss: 0.13083943724632263
2023-01-23 00:12:40.523219: step: 1212/529, loss: 0.0903620719909668
2023-01-23 00:12:41.656853: step: 1216/529, loss: 0.058579400181770325
2023-01-23 00:12:42.785516: step: 1220/529, loss: 0.4212229251861572
2023-01-23 00:12:43.934019: step: 1224/529, loss: 0.042082786560058594
2023-01-23 00:12:45.115334: step: 1228/529, loss: 0.9738116264343262
2023-01-23 00:12:46.264432: step: 1232/529, loss: 0.10584497451782227
2023-01-23 00:12:47.392760: step: 1236/529, loss: 0.5029982924461365
2023-01-23 00:12:48.556999: step: 1240/529, loss: 0.10875015705823898
2023-01-23 00:12:49.694308: step: 1244/529, loss: 0.10504321753978729
2023-01-23 00:12:50.824991: step: 1248/529, loss: 0.18976612389087677
2023-01-23 00:12:51.977011: step: 1252/529, loss: 0.15540161728858948
2023-01-23 00:12:53.098273: step: 1256/529, loss: 0.09569196403026581
2023-01-23 00:12:54.253482: step: 1260/529, loss: 0.05697832256555557
2023-01-23 00:12:55.406252: step: 1264/529, loss: 0.18261757493019104
2023-01-23 00:12:56.526083: step: 1268/529, loss: 0.4580424427986145
2023-01-23 00:12:57.683449: step: 1272/529, loss: 0.058217622339725494
2023-01-23 00:12:58.820953: step: 1276/529, loss: 0.1900755912065506
2023-01-23 00:12:59.975144: step: 1280/529, loss: 0.19807033240795135
2023-01-23 00:13:01.094310: step: 1284/529, loss: 0.23657692968845367
2023-01-23 00:13:02.229339: step: 1288/529, loss: 0.7006770968437195
2023-01-23 00:13:03.379875: step: 1292/529, loss: 0.1827041208744049
2023-01-23 00:13:04.498356: step: 1296/529, loss: 0.5632963180541992
2023-01-23 00:13:05.664027: step: 1300/529, loss: 0.189055398106575
2023-01-23 00:13:06.795492: step: 1304/529, loss: 0.1618351936340332
2023-01-23 00:13:07.955623: step: 1308/529, loss: 0.024189185351133347
2023-01-23 00:13:09.103996: step: 1312/529, loss: 0.21861210465431213
2023-01-23 00:13:10.220088: step: 1316/529, loss: 0.18013858795166016
2023-01-23 00:13:11.398123: step: 1320/529, loss: 0.22302323579788208
2023-01-23 00:13:12.533228: step: 1324/529, loss: 0.07286234200000763
2023-01-23 00:13:13.676502: step: 1328/529, loss: 0.1516880989074707
2023-01-23 00:13:14.800335: step: 1332/529, loss: 0.026779651641845703
2023-01-23 00:13:15.937515: step: 1336/529, loss: 0.19312362372875214
2023-01-23 00:13:17.067099: step: 1340/529, loss: 0.024222230538725853
2023-01-23 00:13:18.199679: step: 1344/529, loss: 0.5090200304985046
2023-01-23 00:13:19.350227: step: 1348/529, loss: 0.1182275339961052
2023-01-23 00:13:20.517748: step: 1352/529, loss: 1.2169787883758545
2023-01-23 00:13:21.672677: step: 1356/529, loss: 1.5662081241607666
2023-01-23 00:13:22.814973: step: 1360/529, loss: 0.854303777217865
2023-01-23 00:13:23.972382: step: 1364/529, loss: 0.09669408947229385
2023-01-23 00:13:25.122288: step: 1368/529, loss: 0.2680419087409973
2023-01-23 00:13:26.286118: step: 1372/529, loss: 0.22132301330566406
2023-01-23 00:13:27.425647: step: 1376/529, loss: 0.08938374370336533
2023-01-23 00:13:28.550696: step: 1380/529, loss: 0.0645257979631424
2023-01-23 00:13:29.697422: step: 1384/529, loss: 0.7656015157699585
2023-01-23 00:13:30.813663: step: 1388/529, loss: 0.08659515529870987
2023-01-23 00:13:31.954282: step: 1392/529, loss: 0.24602393805980682
2023-01-23 00:13:33.081925: step: 1396/529, loss: 0.12929227948188782
2023-01-23 00:13:34.221263: step: 1400/529, loss: 0.09883227944374084
2023-01-23 00:13:35.361276: step: 1404/529, loss: 0.03693590313196182
2023-01-23 00:13:36.473400: step: 1408/529, loss: 0.14979323744773865
2023-01-23 00:13:37.647445: step: 1412/529, loss: 0.27159959077835083
2023-01-23 00:13:38.772242: step: 1416/529, loss: 0.06096029281616211
2023-01-23 00:13:39.890324: step: 1420/529, loss: 0.2789209485054016
2023-01-23 00:13:41.003198: step: 1424/529, loss: 0.13256461918354034
2023-01-23 00:13:42.135367: step: 1428/529, loss: 0.13757982850074768
2023-01-23 00:13:43.268155: step: 1432/529, loss: 0.09792099893093109
2023-01-23 00:13:44.434959: step: 1436/529, loss: 1.123103141784668
2023-01-23 00:13:45.587912: step: 1440/529, loss: 0.5919109582901001
2023-01-23 00:13:46.729114: step: 1444/529, loss: 0.6940789818763733
2023-01-23 00:13:47.906282: step: 1448/529, loss: 0.4919891357421875
2023-01-23 00:13:49.040861: step: 1452/529, loss: 0.1172342374920845
2023-01-23 00:13:50.180740: step: 1456/529, loss: 0.06498537212610245
2023-01-23 00:13:51.341235: step: 1460/529, loss: 0.1114787608385086
2023-01-23 00:13:52.477526: step: 1464/529, loss: 0.29998978972435
2023-01-23 00:13:53.635349: step: 1468/529, loss: 0.12245502322912216
2023-01-23 00:13:54.788838: step: 1472/529, loss: 0.17830339074134827
2023-01-23 00:13:55.937709: step: 1476/529, loss: 1.1929702758789062
2023-01-23 00:13:57.055624: step: 1480/529, loss: 0.5831903219223022
2023-01-23 00:13:58.207608: step: 1484/529, loss: 0.13941699266433716
2023-01-23 00:13:59.349097: step: 1488/529, loss: 0.17368373274803162
2023-01-23 00:14:00.534041: step: 1492/529, loss: 0.6343552470207214
2023-01-23 00:14:01.672129: step: 1496/529, loss: 0.4606724679470062
2023-01-23 00:14:02.829571: step: 1500/529, loss: 0.299577534198761
2023-01-23 00:14:03.996215: step: 1504/529, loss: 0.15684852004051208
2023-01-23 00:14:05.182948: step: 1508/529, loss: 0.04608802869915962
2023-01-23 00:14:06.365904: step: 1512/529, loss: 0.262067049741745
2023-01-23 00:14:07.534844: step: 1516/529, loss: 0.11879158765077591
2023-01-23 00:14:08.678297: step: 1520/529, loss: 0.3135489523410797
2023-01-23 00:14:09.827873: step: 1524/529, loss: 0.1385493278503418
2023-01-23 00:14:10.967607: step: 1528/529, loss: 4.754935264587402
2023-01-23 00:14:12.112390: step: 1532/529, loss: 0.05047278478741646
2023-01-23 00:14:13.237019: step: 1536/529, loss: 0.2229703962802887
2023-01-23 00:14:14.372187: step: 1540/529, loss: 0.1779649704694748
2023-01-23 00:14:15.507155: step: 1544/529, loss: 0.14939361810684204
2023-01-23 00:14:16.672261: step: 1548/529, loss: 0.03045635297894478
2023-01-23 00:14:17.852450: step: 1552/529, loss: 0.2526680827140808
2023-01-23 00:14:18.987215: step: 1556/529, loss: 0.32061004638671875
2023-01-23 00:14:20.138673: step: 1560/529, loss: 0.31971797347068787
2023-01-23 00:14:21.272719: step: 1564/529, loss: 0.8463422656059265
2023-01-23 00:14:22.421669: step: 1568/529, loss: 0.04594426229596138
2023-01-23 00:14:23.555081: step: 1572/529, loss: 0.13086232542991638
2023-01-23 00:14:24.703902: step: 1576/529, loss: 0.18717403709888458
2023-01-23 00:14:25.828158: step: 1580/529, loss: 0.05564568191766739
2023-01-23 00:14:26.999517: step: 1584/529, loss: 0.022755956277251244
2023-01-23 00:14:28.129543: step: 1588/529, loss: 0.5509677529335022
2023-01-23 00:14:29.260877: step: 1592/529, loss: 0.5876039266586304
2023-01-23 00:14:30.407276: step: 1596/529, loss: 0.4976891279220581
2023-01-23 00:14:31.546788: step: 1600/529, loss: 0.7775392532348633
2023-01-23 00:14:32.670460: step: 1604/529, loss: 0.2504066526889801
2023-01-23 00:14:33.798461: step: 1608/529, loss: 0.2704865038394928
2023-01-23 00:14:34.888032: step: 1612/529, loss: 0.1411399394273758
2023-01-23 00:14:36.024927: step: 1616/529, loss: 0.0903095081448555
2023-01-23 00:14:37.141249: step: 1620/529, loss: 0.1270519196987152
2023-01-23 00:14:38.299509: step: 1624/529, loss: 0.2893911302089691
2023-01-23 00:14:39.472056: step: 1628/529, loss: 0.43057534098625183
2023-01-23 00:14:40.612970: step: 1632/529, loss: 0.4903358817100525
2023-01-23 00:14:41.744607: step: 1636/529, loss: 0.04562988132238388
2023-01-23 00:14:42.880525: step: 1640/529, loss: 0.08480499684810638
2023-01-23 00:14:44.012734: step: 1644/529, loss: 0.31595534086227417
2023-01-23 00:14:45.159076: step: 1648/529, loss: 0.1193302646279335
2023-01-23 00:14:46.337832: step: 1652/529, loss: 0.28404197096824646
2023-01-23 00:14:47.493809: step: 1656/529, loss: 0.24520379304885864
2023-01-23 00:14:48.629341: step: 1660/529, loss: 0.09461050480604172
2023-01-23 00:14:49.766129: step: 1664/529, loss: 0.05453546345233917
2023-01-23 00:14:50.880192: step: 1668/529, loss: 0.4951627850532532
2023-01-23 00:14:52.016709: step: 1672/529, loss: 0.3646741807460785
2023-01-23 00:14:53.169900: step: 1676/529, loss: 0.2803020179271698
2023-01-23 00:14:54.332800: step: 1680/529, loss: 0.17202310264110565
2023-01-23 00:14:55.469570: step: 1684/529, loss: 0.1145220696926117
2023-01-23 00:14:56.601952: step: 1688/529, loss: 0.28769055008888245
2023-01-23 00:14:57.749826: step: 1692/529, loss: 0.13950395584106445
2023-01-23 00:14:58.905666: step: 1696/529, loss: 0.934943437576294
2023-01-23 00:15:00.066114: step: 1700/529, loss: 0.06297507882118225
2023-01-23 00:15:01.212672: step: 1704/529, loss: 0.28420257568359375
2023-01-23 00:15:02.340181: step: 1708/529, loss: 0.05071087181568146
2023-01-23 00:15:03.475565: step: 1712/529, loss: 0.23099786043167114
2023-01-23 00:15:04.639061: step: 1716/529, loss: 0.10282459110021591
2023-01-23 00:15:05.775609: step: 1720/529, loss: 0.24735870957374573
2023-01-23 00:15:06.903385: step: 1724/529, loss: 2.310133695602417
2023-01-23 00:15:08.025274: step: 1728/529, loss: 0.10250245034694672
2023-01-23 00:15:09.161903: step: 1732/529, loss: 0.10065250843763351
2023-01-23 00:15:10.315535: step: 1736/529, loss: 0.04280738905072212
2023-01-23 00:15:11.460313: step: 1740/529, loss: 0.5495694875717163
2023-01-23 00:15:12.602165: step: 1744/529, loss: 0.1267234832048416
2023-01-23 00:15:13.747746: step: 1748/529, loss: 0.4049305021762848
2023-01-23 00:15:14.882957: step: 1752/529, loss: 0.18132664263248444
2023-01-23 00:15:15.990344: step: 1756/529, loss: 0.7158254981040955
2023-01-23 00:15:17.121563: step: 1760/529, loss: 0.06081700325012207
2023-01-23 00:15:18.269583: step: 1764/529, loss: 0.14400339126586914
2023-01-23 00:15:19.367246: step: 1768/529, loss: 0.15114939212799072
2023-01-23 00:15:20.497518: step: 1772/529, loss: 0.12647433578968048
2023-01-23 00:15:21.643281: step: 1776/529, loss: 0.19220593571662903
2023-01-23 00:15:22.789537: step: 1780/529, loss: 0.03862974792718887
2023-01-23 00:15:23.941528: step: 1784/529, loss: 0.034238241612911224
2023-01-23 00:15:25.052058: step: 1788/529, loss: 0.39714276790618896
2023-01-23 00:15:26.186892: step: 1792/529, loss: 0.6737889051437378
2023-01-23 00:15:27.317545: step: 1796/529, loss: 0.1121646910905838
2023-01-23 00:15:28.481890: step: 1800/529, loss: 0.24534845352172852
2023-01-23 00:15:29.604108: step: 1804/529, loss: 0.1764148771762848
2023-01-23 00:15:30.727680: step: 1808/529, loss: 0.2621656358242035
2023-01-23 00:15:31.870714: step: 1812/529, loss: 0.3271993398666382
2023-01-23 00:15:33.013095: step: 1816/529, loss: 0.35607290267944336
2023-01-23 00:15:34.147238: step: 1820/529, loss: 0.05315547436475754
2023-01-23 00:15:35.264258: step: 1824/529, loss: 0.15396633744239807
2023-01-23 00:15:36.415546: step: 1828/529, loss: 0.1048869639635086
2023-01-23 00:15:37.542107: step: 1832/529, loss: 0.08683881908655167
2023-01-23 00:15:38.685991: step: 1836/529, loss: 0.4033700227737427
2023-01-23 00:15:39.802893: step: 1840/529, loss: 0.18419551849365234
2023-01-23 00:15:40.972338: step: 1844/529, loss: 0.09755392372608185
2023-01-23 00:15:42.102349: step: 1848/529, loss: 0.34812992811203003
2023-01-23 00:15:43.266191: step: 1852/529, loss: 0.05299287289381027
2023-01-23 00:15:44.389246: step: 1856/529, loss: 0.10171431303024292
2023-01-23 00:15:45.522221: step: 1860/529, loss: 0.08608823269605637
2023-01-23 00:15:46.673902: step: 1864/529, loss: 0.161363422870636
2023-01-23 00:15:47.786633: step: 1868/529, loss: 0.1409951150417328
2023-01-23 00:15:48.909202: step: 1872/529, loss: 0.7660082578659058
2023-01-23 00:15:50.048584: step: 1876/529, loss: 0.15494881570339203
2023-01-23 00:15:51.166668: step: 1880/529, loss: 0.33420228958129883
2023-01-23 00:15:52.317019: step: 1884/529, loss: 0.22919301688671112
2023-01-23 00:15:53.479244: step: 1888/529, loss: 0.07616036385297775
2023-01-23 00:15:54.584115: step: 1892/529, loss: 0.10895605385303497
2023-01-23 00:15:55.721371: step: 1896/529, loss: 0.22049346566200256
2023-01-23 00:15:56.869285: step: 1900/529, loss: 0.0726408064365387
2023-01-23 00:15:57.998199: step: 1904/529, loss: 0.041957952082157135
2023-01-23 00:15:59.127396: step: 1908/529, loss: 0.33600637316703796
2023-01-23 00:16:00.266107: step: 1912/529, loss: 0.27662912011146545
2023-01-23 00:16:01.386993: step: 1916/529, loss: 0.27566593885421753
2023-01-23 00:16:02.538097: step: 1920/529, loss: 0.14633388817310333
2023-01-23 00:16:03.705202: step: 1924/529, loss: 0.14777374267578125
2023-01-23 00:16:04.872411: step: 1928/529, loss: 0.2467377781867981
2023-01-23 00:16:06.001957: step: 1932/529, loss: 0.3071153163909912
2023-01-23 00:16:07.180960: step: 1936/529, loss: 0.0790814459323883
2023-01-23 00:16:08.338599: step: 1940/529, loss: 0.39208564162254333
2023-01-23 00:16:09.470128: step: 1944/529, loss: 0.09246049076318741
2023-01-23 00:16:10.624970: step: 1948/529, loss: 0.15102358162403107
2023-01-23 00:16:11.728644: step: 1952/529, loss: 0.050856590270996094
2023-01-23 00:16:12.885802: step: 1956/529, loss: 0.22097045183181763
2023-01-23 00:16:14.030076: step: 1960/529, loss: 0.7996987104415894
2023-01-23 00:16:15.153895: step: 1964/529, loss: 0.09530887752771378
2023-01-23 00:16:16.310260: step: 1968/529, loss: 0.039115048944950104
2023-01-23 00:16:17.451234: step: 1972/529, loss: 0.24181966483592987
2023-01-23 00:16:18.562505: step: 1976/529, loss: 0.06567387282848358
2023-01-23 00:16:19.711680: step: 1980/529, loss: 0.5974474549293518
2023-01-23 00:16:20.858030: step: 1984/529, loss: 0.2725328505039215
2023-01-23 00:16:21.984094: step: 1988/529, loss: 0.16146451234817505
2023-01-23 00:16:23.155815: step: 1992/529, loss: 0.261522114276886
2023-01-23 00:16:24.297089: step: 1996/529, loss: 0.25922155380249023
2023-01-23 00:16:25.427635: step: 2000/529, loss: 0.37495356798171997
2023-01-23 00:16:26.577101: step: 2004/529, loss: 1.3707140684127808
2023-01-23 00:16:27.746350: step: 2008/529, loss: 6.217792987823486
2023-01-23 00:16:28.863434: step: 2012/529, loss: 0.3286910653114319
2023-01-23 00:16:30.000167: step: 2016/529, loss: 0.22771930694580078
2023-01-23 00:16:31.108799: step: 2020/529, loss: 0.15865278244018555
2023-01-23 00:16:32.229217: step: 2024/529, loss: 0.26538124680519104
2023-01-23 00:16:33.356275: step: 2028/529, loss: 0.0401032455265522
2023-01-23 00:16:34.550223: step: 2032/529, loss: 0.17519842088222504
2023-01-23 00:16:35.683249: step: 2036/529, loss: 0.1319824755191803
2023-01-23 00:16:36.826983: step: 2040/529, loss: 0.12547016143798828
2023-01-23 00:16:37.968231: step: 2044/529, loss: 0.6281712055206299
2023-01-23 00:16:39.095370: step: 2048/529, loss: 0.07938146591186523
2023-01-23 00:16:40.215546: step: 2052/529, loss: 0.0992530807852745
2023-01-23 00:16:41.358421: step: 2056/529, loss: 0.1517200469970703
2023-01-23 00:16:42.485142: step: 2060/529, loss: 0.6488975286483765
2023-01-23 00:16:43.633626: step: 2064/529, loss: 0.111371710896492
2023-01-23 00:16:44.782319: step: 2068/529, loss: 0.4982793927192688
2023-01-23 00:16:45.907036: step: 2072/529, loss: 0.08705510944128036
2023-01-23 00:16:47.005696: step: 2076/529, loss: 0.19659142196178436
2023-01-23 00:16:48.126556: step: 2080/529, loss: 0.11851692199707031
2023-01-23 00:16:49.256557: step: 2084/529, loss: 0.18685206770896912
2023-01-23 00:16:50.371738: step: 2088/529, loss: 0.22805020213127136
2023-01-23 00:16:51.538019: step: 2092/529, loss: 1.03988778591156
2023-01-23 00:16:52.684322: step: 2096/529, loss: 0.23737582564353943
2023-01-23 00:16:53.832327: step: 2100/529, loss: 0.054612256586551666
2023-01-23 00:16:54.999190: step: 2104/529, loss: 0.20533724129199982
2023-01-23 00:16:56.141480: step: 2108/529, loss: 0.25845497846603394
2023-01-23 00:16:57.264114: step: 2112/529, loss: 0.07220889627933502
2023-01-23 00:16:58.414377: step: 2116/529, loss: 0.26004448533058167
==================================================
Loss: 0.354
--------------------
Dev: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6956521739130435, 'r': 0.5079365079365079, 'f1': 0.5871559633027522}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.5428571428571428, 'r': 0.5277777777777778, 'f1': 0.5352112676056338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.6301369863013698, 'r': 0.8518518518518519, 'f1': 0.7244094488188976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6956521739130435, 'r': 0.5079365079365079, 'f1': 0.5871559633027522}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5428571428571428, 'r': 0.5277777777777778, 'f1': 0.5352112676056338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:17:51.925613: step: 4/529, loss: 0.22427862882614136
2023-01-23 00:17:53.089905: step: 8/529, loss: 0.10048151016235352
2023-01-23 00:17:54.199521: step: 12/529, loss: 0.06975755840539932
2023-01-23 00:17:55.316509: step: 16/529, loss: 0.07934622466564178
2023-01-23 00:17:56.428772: step: 20/529, loss: 0.11244344711303711
2023-01-23 00:17:57.523942: step: 24/529, loss: 0.21492882072925568
2023-01-23 00:17:58.651448: step: 28/529, loss: 0.08214688301086426
2023-01-23 00:17:59.786672: step: 32/529, loss: 0.14411644637584686
2023-01-23 00:18:00.934532: step: 36/529, loss: 0.06832685321569443
2023-01-23 00:18:02.085030: step: 40/529, loss: 0.9251334071159363
2023-01-23 00:18:03.216964: step: 44/529, loss: 0.05976181477308273
2023-01-23 00:18:04.338499: step: 48/529, loss: 0.08708854019641876
2023-01-23 00:18:05.452680: step: 52/529, loss: 0.06360912322998047
2023-01-23 00:18:06.583346: step: 56/529, loss: 0.08166372776031494
2023-01-23 00:18:07.722368: step: 60/529, loss: 0.22660627961158752
2023-01-23 00:18:08.867251: step: 64/529, loss: 0.1092415452003479
2023-01-23 00:18:09.998662: step: 68/529, loss: 0.15970100462436676
2023-01-23 00:18:11.140104: step: 72/529, loss: 0.149301216006279
2023-01-23 00:18:12.306439: step: 76/529, loss: 0.24440088868141174
2023-01-23 00:18:13.480910: step: 80/529, loss: 0.20189151167869568
2023-01-23 00:18:14.608782: step: 84/529, loss: 0.10554523766040802
2023-01-23 00:18:15.747113: step: 88/529, loss: 0.14898566901683807
2023-01-23 00:18:16.862281: step: 92/529, loss: 0.17725713551044464
2023-01-23 00:18:18.002127: step: 96/529, loss: 0.17440198361873627
2023-01-23 00:18:19.159933: step: 100/529, loss: 0.2739085555076599
2023-01-23 00:18:20.268056: step: 104/529, loss: 0.5840579867362976
2023-01-23 00:18:21.391307: step: 108/529, loss: 0.6455684900283813
2023-01-23 00:18:22.522439: step: 112/529, loss: 0.30396878719329834
2023-01-23 00:18:23.656060: step: 116/529, loss: 0.17748594284057617
2023-01-23 00:18:24.811106: step: 120/529, loss: 0.39729365706443787
2023-01-23 00:18:25.938669: step: 124/529, loss: 0.07466993480920792
2023-01-23 00:18:27.076626: step: 128/529, loss: 0.8461507558822632
2023-01-23 00:18:28.205661: step: 132/529, loss: 0.18433362245559692
2023-01-23 00:18:29.354034: step: 136/529, loss: 0.19498604536056519
2023-01-23 00:18:30.488971: step: 140/529, loss: 0.22603902220726013
2023-01-23 00:18:31.618672: step: 144/529, loss: 0.20145784318447113
2023-01-23 00:18:32.748648: step: 148/529, loss: 0.13971567153930664
2023-01-23 00:18:33.887174: step: 152/529, loss: 0.3831354081630707
2023-01-23 00:18:35.044042: step: 156/529, loss: 0.07915820926427841
2023-01-23 00:18:36.151857: step: 160/529, loss: 0.3496702313423157
2023-01-23 00:18:37.287621: step: 164/529, loss: 0.4002492427825928
2023-01-23 00:18:38.402901: step: 168/529, loss: 0.05228271335363388
2023-01-23 00:18:39.518078: step: 172/529, loss: 0.03417503833770752
2023-01-23 00:18:40.644277: step: 176/529, loss: 0.13278627395629883
2023-01-23 00:18:41.777121: step: 180/529, loss: 0.06800059974193573
2023-01-23 00:18:42.915109: step: 184/529, loss: 0.4448899030685425
2023-01-23 00:18:44.059195: step: 188/529, loss: 0.11199875175952911
2023-01-23 00:18:45.193198: step: 192/529, loss: 0.02708606794476509
2023-01-23 00:18:46.336885: step: 196/529, loss: 0.047673940658569336
2023-01-23 00:18:47.447036: step: 200/529, loss: 0.09937945008277893
2023-01-23 00:18:48.603420: step: 204/529, loss: 0.13282537460327148
2023-01-23 00:18:49.777753: step: 208/529, loss: 0.09272298961877823
2023-01-23 00:18:50.904421: step: 212/529, loss: 0.10857147723436356
2023-01-23 00:18:52.062271: step: 216/529, loss: 0.020266152918338776
2023-01-23 00:18:53.182328: step: 220/529, loss: 0.08863510936498642
2023-01-23 00:18:54.320531: step: 224/529, loss: 0.20711678266525269
2023-01-23 00:18:55.473612: step: 228/529, loss: 0.08193827420473099
2023-01-23 00:18:56.599592: step: 232/529, loss: 0.08115196228027344
2023-01-23 00:18:57.737456: step: 236/529, loss: 0.7200329899787903
2023-01-23 00:18:58.881839: step: 240/529, loss: 0.26839351654052734
2023-01-23 00:19:00.027988: step: 244/529, loss: 0.11625099927186966
2023-01-23 00:19:01.175574: step: 248/529, loss: 0.02670593373477459
2023-01-23 00:19:02.317856: step: 252/529, loss: 0.3011418282985687
2023-01-23 00:19:03.482337: step: 256/529, loss: 0.7763880491256714
2023-01-23 00:19:04.613355: step: 260/529, loss: 0.08882975578308105
2023-01-23 00:19:05.747924: step: 264/529, loss: 0.24912786483764648
2023-01-23 00:19:06.893471: step: 268/529, loss: 0.2661977708339691
2023-01-23 00:19:08.020596: step: 272/529, loss: 0.053052619099617004
2023-01-23 00:19:09.133610: step: 276/529, loss: 0.060025885701179504
2023-01-23 00:19:10.312463: step: 280/529, loss: 0.0874544158577919
2023-01-23 00:19:11.435995: step: 284/529, loss: 0.18547393381595612
2023-01-23 00:19:12.557708: step: 288/529, loss: 0.5351834893226624
2023-01-23 00:19:13.666355: step: 292/529, loss: 0.06581669300794601
2023-01-23 00:19:14.780055: step: 296/529, loss: 0.22228574752807617
2023-01-23 00:19:15.929106: step: 300/529, loss: 0.8187047839164734
2023-01-23 00:19:17.058342: step: 304/529, loss: 0.04924288019537926
2023-01-23 00:19:18.182560: step: 308/529, loss: 0.1315666288137436
2023-01-23 00:19:19.316225: step: 312/529, loss: 0.03098888508975506
2023-01-23 00:19:20.473581: step: 316/529, loss: 0.4047360420227051
2023-01-23 00:19:21.602434: step: 320/529, loss: 0.047917917370796204
2023-01-23 00:19:22.736273: step: 324/529, loss: 0.11188822239637375
2023-01-23 00:19:23.866832: step: 328/529, loss: 0.38239985704421997
2023-01-23 00:19:24.973007: step: 332/529, loss: 0.15101128816604614
2023-01-23 00:19:26.075798: step: 336/529, loss: 0.05776116997003555
2023-01-23 00:19:27.213804: step: 340/529, loss: 0.15691126883029938
2023-01-23 00:19:28.349876: step: 344/529, loss: 0.7498137354850769
2023-01-23 00:19:29.495288: step: 348/529, loss: 0.09618520736694336
2023-01-23 00:19:30.627256: step: 352/529, loss: 0.40496835112571716
2023-01-23 00:19:31.740519: step: 356/529, loss: 0.10190154612064362
2023-01-23 00:19:32.875991: step: 360/529, loss: 0.017052555456757545
2023-01-23 00:19:34.020979: step: 364/529, loss: 0.05175848305225372
2023-01-23 00:19:35.150522: step: 368/529, loss: 0.6044270396232605
2023-01-23 00:19:36.283543: step: 372/529, loss: 0.1350676566362381
2023-01-23 00:19:37.435536: step: 376/529, loss: 0.19380322098731995
2023-01-23 00:19:38.586529: step: 380/529, loss: 0.27833104133605957
2023-01-23 00:19:39.713951: step: 384/529, loss: 1.098759651184082
2023-01-23 00:19:40.854653: step: 388/529, loss: 0.27214139699935913
2023-01-23 00:19:41.996834: step: 392/529, loss: 0.3750571310520172
2023-01-23 00:19:43.157717: step: 396/529, loss: 0.3386901915073395
2023-01-23 00:19:44.305814: step: 400/529, loss: 0.11729726940393448
2023-01-23 00:19:45.422561: step: 404/529, loss: 0.2177065908908844
2023-01-23 00:19:46.591563: step: 408/529, loss: 0.508978545665741
2023-01-23 00:19:47.717103: step: 412/529, loss: 0.051433611661195755
2023-01-23 00:19:48.888517: step: 416/529, loss: 0.37486132979393005
2023-01-23 00:19:50.009691: step: 420/529, loss: 0.42103490233421326
2023-01-23 00:19:51.186144: step: 424/529, loss: 0.863083004951477
2023-01-23 00:19:52.315823: step: 428/529, loss: 0.6344043612480164
2023-01-23 00:19:53.464570: step: 432/529, loss: 0.6767671704292297
2023-01-23 00:19:54.614499: step: 436/529, loss: 0.55816251039505
2023-01-23 00:19:55.762868: step: 440/529, loss: 0.14557896554470062
2023-01-23 00:19:56.888833: step: 444/529, loss: 0.2398478388786316
2023-01-23 00:19:58.006518: step: 448/529, loss: 0.0840398296713829
2023-01-23 00:19:59.109750: step: 452/529, loss: 0.04188041761517525
2023-01-23 00:20:00.240332: step: 456/529, loss: 0.1442861557006836
2023-01-23 00:20:01.371885: step: 460/529, loss: 0.06053047627210617
2023-01-23 00:20:02.534302: step: 464/529, loss: 0.01460943277925253
2023-01-23 00:20:03.649708: step: 468/529, loss: 0.35192325711250305
2023-01-23 00:20:04.777600: step: 472/529, loss: 0.07562866806983948
2023-01-23 00:20:05.926200: step: 476/529, loss: 0.22201451659202576
2023-01-23 00:20:07.064327: step: 480/529, loss: 0.33580923080444336
2023-01-23 00:20:08.230740: step: 484/529, loss: 0.48352259397506714
2023-01-23 00:20:09.366149: step: 488/529, loss: 0.06163311004638672
2023-01-23 00:20:10.497716: step: 492/529, loss: 0.09614791721105576
2023-01-23 00:20:11.640642: step: 496/529, loss: 0.1638510823249817
2023-01-23 00:20:12.803433: step: 500/529, loss: 0.05747361481189728
2023-01-23 00:20:13.973121: step: 504/529, loss: 0.08745288848876953
2023-01-23 00:20:15.139904: step: 508/529, loss: 0.1919899880886078
2023-01-23 00:20:16.280113: step: 512/529, loss: 0.04347677156329155
2023-01-23 00:20:17.443114: step: 516/529, loss: 0.062215328216552734
2023-01-23 00:20:18.576329: step: 520/529, loss: 0.18911391496658325
2023-01-23 00:20:19.727717: step: 524/529, loss: 0.5368407368659973
2023-01-23 00:20:20.893393: step: 528/529, loss: 0.32455766201019287
2023-01-23 00:20:22.009476: step: 532/529, loss: 0.18294811248779297
2023-01-23 00:20:23.133371: step: 536/529, loss: 0.12199468910694122
2023-01-23 00:20:24.249317: step: 540/529, loss: 0.4287474751472473
2023-01-23 00:20:25.356296: step: 544/529, loss: 0.5247993469238281
2023-01-23 00:20:26.502194: step: 548/529, loss: 0.09729328006505966
2023-01-23 00:20:27.626978: step: 552/529, loss: 0.09226283431053162
2023-01-23 00:20:28.775725: step: 556/529, loss: 0.05288305506110191
2023-01-23 00:20:29.906475: step: 560/529, loss: 0.3276095390319824
2023-01-23 00:20:31.059911: step: 564/529, loss: 0.026784610003232956
2023-01-23 00:20:32.199021: step: 568/529, loss: 0.0736333355307579
2023-01-23 00:20:33.357426: step: 572/529, loss: 0.7001714110374451
2023-01-23 00:20:34.477457: step: 576/529, loss: 0.1079442948102951
2023-01-23 00:20:35.610831: step: 580/529, loss: 0.14818096160888672
2023-01-23 00:20:36.733601: step: 584/529, loss: 0.09834060072898865
2023-01-23 00:20:37.873304: step: 588/529, loss: 0.40732526779174805
2023-01-23 00:20:39.013467: step: 592/529, loss: 0.3458413779735565
2023-01-23 00:20:40.138341: step: 596/529, loss: 0.2152392864227295
2023-01-23 00:20:41.299462: step: 600/529, loss: 0.2431774139404297
2023-01-23 00:20:42.394517: step: 604/529, loss: 0.04874591529369354
2023-01-23 00:20:43.511562: step: 608/529, loss: 0.14137907326221466
2023-01-23 00:20:44.667554: step: 612/529, loss: 0.05199284479022026
2023-01-23 00:20:45.804391: step: 616/529, loss: 0.1299666464328766
2023-01-23 00:20:46.920352: step: 620/529, loss: 0.06879501044750214
2023-01-23 00:20:48.048231: step: 624/529, loss: 0.4626198709011078
2023-01-23 00:20:49.188520: step: 628/529, loss: 0.40443477034568787
2023-01-23 00:20:50.336647: step: 632/529, loss: 0.0699642151594162
2023-01-23 00:20:51.491360: step: 636/529, loss: 0.6595377922058105
2023-01-23 00:20:52.638583: step: 640/529, loss: 0.2773308753967285
2023-01-23 00:20:53.760527: step: 644/529, loss: 0.19436411559581757
2023-01-23 00:20:54.901934: step: 648/529, loss: 0.38811931014060974
2023-01-23 00:20:56.045569: step: 652/529, loss: 0.13943955302238464
2023-01-23 00:20:57.199932: step: 656/529, loss: 0.03386202082037926
2023-01-23 00:20:58.376534: step: 660/529, loss: 0.06380109488964081
2023-01-23 00:20:59.549508: step: 664/529, loss: 0.10193099826574326
2023-01-23 00:21:00.686166: step: 668/529, loss: 0.3615955114364624
2023-01-23 00:21:01.855680: step: 672/529, loss: 0.06915836036205292
2023-01-23 00:21:02.989104: step: 676/529, loss: 0.026192951947450638
2023-01-23 00:21:04.107257: step: 680/529, loss: 0.16068187355995178
2023-01-23 00:21:05.262018: step: 684/529, loss: 0.9120908975601196
2023-01-23 00:21:06.410812: step: 688/529, loss: 0.18342283368110657
2023-01-23 00:21:07.557739: step: 692/529, loss: 0.09877967834472656
2023-01-23 00:21:08.681614: step: 696/529, loss: 0.4771346151828766
2023-01-23 00:21:09.806342: step: 700/529, loss: 1.077742576599121
2023-01-23 00:21:10.946068: step: 704/529, loss: 1.4014058113098145
2023-01-23 00:21:12.089487: step: 708/529, loss: 0.16131535172462463
2023-01-23 00:21:13.211826: step: 712/529, loss: 0.09649448096752167
2023-01-23 00:21:14.341500: step: 716/529, loss: 0.4106588363647461
2023-01-23 00:21:15.475048: step: 720/529, loss: 0.08541478961706161
2023-01-23 00:21:16.600863: step: 724/529, loss: 0.05950794368982315
2023-01-23 00:21:17.750312: step: 728/529, loss: 0.06594400852918625
2023-01-23 00:21:18.882000: step: 732/529, loss: 0.32339897751808167
2023-01-23 00:21:19.982482: step: 736/529, loss: 0.028058623895049095
2023-01-23 00:21:21.135466: step: 740/529, loss: 0.7276901006698608
2023-01-23 00:21:22.328628: step: 744/529, loss: 0.09411649405956268
2023-01-23 00:21:23.464409: step: 748/529, loss: 0.07759447395801544
2023-01-23 00:21:24.612155: step: 752/529, loss: 0.21213531494140625
2023-01-23 00:21:25.756733: step: 756/529, loss: 0.17913202941417694
2023-01-23 00:21:26.904495: step: 760/529, loss: 0.23558884859085083
2023-01-23 00:21:28.023403: step: 764/529, loss: 0.5390642285346985
2023-01-23 00:21:29.166074: step: 768/529, loss: 0.1820848435163498
2023-01-23 00:21:30.338401: step: 772/529, loss: 0.3198251724243164
2023-01-23 00:21:31.541666: step: 776/529, loss: 0.38268783688545227
2023-01-23 00:21:32.698829: step: 780/529, loss: 0.12136220932006836
2023-01-23 00:21:33.813449: step: 784/529, loss: 0.45440828800201416
2023-01-23 00:21:34.937956: step: 788/529, loss: 0.17436981201171875
2023-01-23 00:21:36.084409: step: 792/529, loss: 0.46746596693992615
2023-01-23 00:21:37.267860: step: 796/529, loss: 0.7969484329223633
2023-01-23 00:21:38.425777: step: 800/529, loss: 0.05847759172320366
2023-01-23 00:21:39.587623: step: 804/529, loss: 0.17216472327709198
2023-01-23 00:21:40.741519: step: 808/529, loss: 0.07059316337108612
2023-01-23 00:21:41.844852: step: 812/529, loss: 0.1346181333065033
2023-01-23 00:21:43.001480: step: 816/529, loss: 0.10951745510101318
2023-01-23 00:21:44.119187: step: 820/529, loss: 0.13720086216926575
2023-01-23 00:21:45.259172: step: 824/529, loss: 0.08416938781738281
2023-01-23 00:21:46.401981: step: 828/529, loss: 0.11608610302209854
2023-01-23 00:21:47.563288: step: 832/529, loss: 0.05738382041454315
2023-01-23 00:21:48.677752: step: 836/529, loss: 0.19938774406909943
2023-01-23 00:21:49.813309: step: 840/529, loss: 0.13680848479270935
2023-01-23 00:21:50.942943: step: 844/529, loss: 0.6348241567611694
2023-01-23 00:21:52.063682: step: 848/529, loss: 0.28561049699783325
2023-01-23 00:21:53.228659: step: 852/529, loss: 0.11899995803833008
2023-01-23 00:21:54.367008: step: 856/529, loss: 0.6188222765922546
2023-01-23 00:21:55.520936: step: 860/529, loss: 0.15651655197143555
2023-01-23 00:21:56.662486: step: 864/529, loss: 0.3003966212272644
2023-01-23 00:21:57.810297: step: 868/529, loss: 0.2617243826389313
2023-01-23 00:21:58.937016: step: 872/529, loss: 0.16764774918556213
2023-01-23 00:22:00.112131: step: 876/529, loss: 0.2268868088722229
2023-01-23 00:22:01.245810: step: 880/529, loss: 0.05832281336188316
2023-01-23 00:22:02.425779: step: 884/529, loss: 0.16580167412757874
2023-01-23 00:22:03.533287: step: 888/529, loss: 0.8168898820877075
2023-01-23 00:22:04.662542: step: 892/529, loss: 0.10663219541311264
2023-01-23 00:22:05.761567: step: 896/529, loss: 0.023827457800507545
2023-01-23 00:22:06.919465: step: 900/529, loss: 0.4531335234642029
2023-01-23 00:22:08.065376: step: 904/529, loss: 0.06965355575084686
2023-01-23 00:22:09.164538: step: 908/529, loss: 0.10445914417505264
2023-01-23 00:22:10.311687: step: 912/529, loss: 0.820561408996582
2023-01-23 00:22:11.419030: step: 916/529, loss: 0.018340062350034714
2023-01-23 00:22:12.584104: step: 920/529, loss: 0.1836930811405182
2023-01-23 00:22:13.738261: step: 924/529, loss: 0.24556264281272888
2023-01-23 00:22:14.840227: step: 928/529, loss: 0.007442331872880459
2023-01-23 00:22:15.990168: step: 932/529, loss: 0.17948399484157562
2023-01-23 00:22:17.126157: step: 936/529, loss: 0.16641484200954437
2023-01-23 00:22:18.266798: step: 940/529, loss: 0.492008775472641
2023-01-23 00:22:19.396190: step: 944/529, loss: 3.918454170227051
2023-01-23 00:22:20.526834: step: 948/529, loss: 0.137139230966568
2023-01-23 00:22:21.662255: step: 952/529, loss: 0.14130143821239471
2023-01-23 00:22:22.806766: step: 956/529, loss: 0.09719114005565643
2023-01-23 00:22:23.948665: step: 960/529, loss: 0.06868916004896164
2023-01-23 00:22:25.104741: step: 964/529, loss: 0.27867984771728516
2023-01-23 00:22:26.267991: step: 968/529, loss: 0.1194157600402832
2023-01-23 00:22:27.393386: step: 972/529, loss: 0.11559510231018066
2023-01-23 00:22:28.535184: step: 976/529, loss: 0.15028801560401917
2023-01-23 00:22:29.693217: step: 980/529, loss: 0.09685392677783966
2023-01-23 00:22:30.832510: step: 984/529, loss: 0.4270941913127899
2023-01-23 00:22:31.972404: step: 988/529, loss: 0.30056682229042053
2023-01-23 00:22:33.082406: step: 992/529, loss: 0.547038197517395
2023-01-23 00:22:34.193654: step: 996/529, loss: 0.12587013840675354
2023-01-23 00:22:35.317702: step: 1000/529, loss: 0.5889007449150085
2023-01-23 00:22:36.467082: step: 1004/529, loss: 0.1895991861820221
2023-01-23 00:22:37.583569: step: 1008/529, loss: 0.08883605152368546
2023-01-23 00:22:38.721763: step: 1012/529, loss: 0.08840571343898773
2023-01-23 00:22:39.894962: step: 1016/529, loss: 1.289722204208374
2023-01-23 00:22:41.045338: step: 1020/529, loss: 0.25252074003219604
2023-01-23 00:22:42.167991: step: 1024/529, loss: 0.06562743335962296
2023-01-23 00:22:43.279519: step: 1028/529, loss: 0.05796804279088974
2023-01-23 00:22:44.398667: step: 1032/529, loss: 1.5989314317703247
2023-01-23 00:22:45.524449: step: 1036/529, loss: 0.09847583621740341
2023-01-23 00:22:46.632947: step: 1040/529, loss: 0.12631091475486755
2023-01-23 00:22:47.781757: step: 1044/529, loss: 0.1590011715888977
2023-01-23 00:22:48.920258: step: 1048/529, loss: 0.03858909755945206
2023-01-23 00:22:50.071760: step: 1052/529, loss: 0.11746521294116974
2023-01-23 00:22:51.223925: step: 1056/529, loss: 0.26975998282432556
2023-01-23 00:22:52.379835: step: 1060/529, loss: 0.15761476755142212
2023-01-23 00:22:53.502785: step: 1064/529, loss: 0.1558375358581543
2023-01-23 00:22:54.661481: step: 1068/529, loss: 0.16191354393959045
2023-01-23 00:22:55.803512: step: 1072/529, loss: 0.16426125168800354
2023-01-23 00:22:56.927490: step: 1076/529, loss: 0.10819950699806213
2023-01-23 00:22:58.062516: step: 1080/529, loss: 0.2586577236652374
2023-01-23 00:22:59.218902: step: 1084/529, loss: 0.1367994248867035
2023-01-23 00:23:00.368778: step: 1088/529, loss: 0.11013297736644745
2023-01-23 00:23:01.514920: step: 1092/529, loss: 0.23391591012477875
2023-01-23 00:23:02.709232: step: 1096/529, loss: 0.1418527215719223
2023-01-23 00:23:03.833174: step: 1100/529, loss: 0.05804424360394478
2023-01-23 00:23:04.969187: step: 1104/529, loss: 0.3440670371055603
2023-01-23 00:23:06.114792: step: 1108/529, loss: 0.10559874027967453
2023-01-23 00:23:07.235908: step: 1112/529, loss: 0.6162834167480469
2023-01-23 00:23:08.385570: step: 1116/529, loss: 0.034951020032167435
2023-01-23 00:23:09.546246: step: 1120/529, loss: 0.056363776326179504
2023-01-23 00:23:10.672128: step: 1124/529, loss: 0.10268769413232803
2023-01-23 00:23:11.808668: step: 1128/529, loss: 0.1996818482875824
2023-01-23 00:23:12.952351: step: 1132/529, loss: 0.4804918169975281
2023-01-23 00:23:14.089576: step: 1136/529, loss: 0.30917951464653015
2023-01-23 00:23:15.231442: step: 1140/529, loss: 0.01994924619793892
2023-01-23 00:23:16.377550: step: 1144/529, loss: 0.08589410781860352
2023-01-23 00:23:17.546084: step: 1148/529, loss: 0.20463895797729492
2023-01-23 00:23:18.693181: step: 1152/529, loss: 0.5892337560653687
2023-01-23 00:23:19.838801: step: 1156/529, loss: 0.15211649239063263
2023-01-23 00:23:21.009938: step: 1160/529, loss: 0.5815248489379883
2023-01-23 00:23:22.160672: step: 1164/529, loss: 0.24427394568920135
2023-01-23 00:23:23.297193: step: 1168/529, loss: 0.05843021720647812
2023-01-23 00:23:24.407008: step: 1172/529, loss: 0.03600635752081871
2023-01-23 00:23:25.559886: step: 1176/529, loss: 1.3941996097564697
2023-01-23 00:23:26.675567: step: 1180/529, loss: 0.08063025772571564
2023-01-23 00:23:27.779841: step: 1184/529, loss: 0.0839991569519043
2023-01-23 00:23:28.944445: step: 1188/529, loss: 0.06887964904308319
2023-01-23 00:23:30.106795: step: 1192/529, loss: 0.17440348863601685
2023-01-23 00:23:31.297499: step: 1196/529, loss: 0.09976129233837128
2023-01-23 00:23:32.427084: step: 1200/529, loss: 0.04871072620153427
2023-01-23 00:23:33.573922: step: 1204/529, loss: 0.08659162372350693
2023-01-23 00:23:34.753915: step: 1208/529, loss: 0.35692697763442993
2023-01-23 00:23:35.899098: step: 1212/529, loss: 0.314456582069397
2023-01-23 00:23:37.048354: step: 1216/529, loss: 0.04938311129808426
2023-01-23 00:23:38.175654: step: 1220/529, loss: 0.39713582396507263
2023-01-23 00:23:39.289844: step: 1224/529, loss: 0.23301349580287933
2023-01-23 00:23:40.433930: step: 1228/529, loss: 0.058625318109989166
2023-01-23 00:23:41.580991: step: 1232/529, loss: 0.2063652127981186
2023-01-23 00:23:42.724976: step: 1236/529, loss: 0.2320031225681305
2023-01-23 00:23:43.885355: step: 1240/529, loss: 0.21889905631542206
2023-01-23 00:23:45.014984: step: 1244/529, loss: 0.10784120857715607
2023-01-23 00:23:46.159574: step: 1248/529, loss: 0.25295644998550415
2023-01-23 00:23:47.328546: step: 1252/529, loss: 0.1691589057445526
2023-01-23 00:23:48.451549: step: 1256/529, loss: 0.5489426255226135
2023-01-23 00:23:49.608135: step: 1260/529, loss: 0.06394462287425995
2023-01-23 00:23:50.756348: step: 1264/529, loss: 0.273446261882782
2023-01-23 00:23:51.893756: step: 1268/529, loss: 0.1923009753227234
2023-01-23 00:23:53.016863: step: 1272/529, loss: 0.15968474745750427
2023-01-23 00:23:54.155416: step: 1276/529, loss: 0.056958820670843124
2023-01-23 00:23:55.298324: step: 1280/529, loss: 1.2160197496414185
2023-01-23 00:23:56.465015: step: 1284/529, loss: 1.1465739011764526
2023-01-23 00:23:57.603868: step: 1288/529, loss: 0.04865061491727829
2023-01-23 00:23:58.733520: step: 1292/529, loss: 0.042046401649713516
2023-01-23 00:23:59.850089: step: 1296/529, loss: 0.014796162024140358
2023-01-23 00:24:01.015473: step: 1300/529, loss: 0.04874224588274956
2023-01-23 00:24:02.166138: step: 1304/529, loss: 0.664114236831665
2023-01-23 00:24:03.337870: step: 1308/529, loss: 0.3814714252948761
2023-01-23 00:24:04.522370: step: 1312/529, loss: 0.07547149807214737
2023-01-23 00:24:05.655590: step: 1316/529, loss: 0.2374231219291687
2023-01-23 00:24:06.803844: step: 1320/529, loss: 0.09163355827331543
2023-01-23 00:24:07.956953: step: 1324/529, loss: 0.1001967042684555
2023-01-23 00:24:09.108620: step: 1328/529, loss: 0.09128275513648987
2023-01-23 00:24:10.262374: step: 1332/529, loss: 0.11172228306531906
2023-01-23 00:24:11.419311: step: 1336/529, loss: 0.18540725111961365
2023-01-23 00:24:12.566653: step: 1340/529, loss: 0.35773998498916626
2023-01-23 00:24:13.721313: step: 1344/529, loss: 0.1189003735780716
2023-01-23 00:24:14.869628: step: 1348/529, loss: 0.12460193037986755
2023-01-23 00:24:15.996880: step: 1352/529, loss: 0.10962381213903427
2023-01-23 00:24:17.134363: step: 1356/529, loss: 0.4055734872817993
2023-01-23 00:24:18.283615: step: 1360/529, loss: 0.14154282212257385
2023-01-23 00:24:19.424844: step: 1364/529, loss: 0.07836923748254776
2023-01-23 00:24:20.582498: step: 1368/529, loss: 0.4551607072353363
2023-01-23 00:24:21.739787: step: 1372/529, loss: 0.0414639450609684
2023-01-23 00:24:22.866688: step: 1376/529, loss: 0.29673391580581665
2023-01-23 00:24:24.014167: step: 1380/529, loss: 0.1371878832578659
2023-01-23 00:24:25.194816: step: 1384/529, loss: 0.11697244644165039
2023-01-23 00:24:26.353961: step: 1388/529, loss: 0.5230741500854492
2023-01-23 00:24:27.502874: step: 1392/529, loss: 0.32486194372177124
2023-01-23 00:24:28.666732: step: 1396/529, loss: 0.21487733721733093
2023-01-23 00:24:29.819292: step: 1400/529, loss: 0.18460053205490112
2023-01-23 00:24:30.919982: step: 1404/529, loss: 0.04629088565707207
2023-01-23 00:24:32.044935: step: 1408/529, loss: 0.29455748200416565
2023-01-23 00:24:33.179783: step: 1412/529, loss: 0.20230531692504883
2023-01-23 00:24:34.310938: step: 1416/529, loss: 0.13287538290023804
2023-01-23 00:24:35.481826: step: 1420/529, loss: 0.6037986874580383
2023-01-23 00:24:36.601871: step: 1424/529, loss: 0.044907521456480026
2023-01-23 00:24:37.738021: step: 1428/529, loss: 0.28747427463531494
2023-01-23 00:24:38.871415: step: 1432/529, loss: 0.08556830883026123
2023-01-23 00:24:40.015211: step: 1436/529, loss: 0.22988833487033844
2023-01-23 00:24:41.163675: step: 1440/529, loss: 0.48885446786880493
2023-01-23 00:24:42.316838: step: 1444/529, loss: 0.2024051696062088
2023-01-23 00:24:43.460489: step: 1448/529, loss: 0.42543095350265503
2023-01-23 00:24:44.566683: step: 1452/529, loss: 0.09166135638952255
2023-01-23 00:24:45.680788: step: 1456/529, loss: 0.2525315284729004
2023-01-23 00:24:46.807811: step: 1460/529, loss: 0.04898281395435333
2023-01-23 00:24:47.932283: step: 1464/529, loss: 0.11130361258983612
2023-01-23 00:24:49.065925: step: 1468/529, loss: 0.11058778315782547
2023-01-23 00:24:50.209525: step: 1472/529, loss: 0.0893896147608757
2023-01-23 00:24:51.330439: step: 1476/529, loss: 0.07288694381713867
2023-01-23 00:24:52.463031: step: 1480/529, loss: 0.06834030151367188
2023-01-23 00:24:53.621356: step: 1484/529, loss: 0.02478962019085884
2023-01-23 00:24:54.787229: step: 1488/529, loss: 0.1446254700422287
2023-01-23 00:24:55.948687: step: 1492/529, loss: 0.45494937896728516
2023-01-23 00:24:57.108856: step: 1496/529, loss: 1.6910068988800049
2023-01-23 00:24:58.278967: step: 1500/529, loss: 0.132727712392807
2023-01-23 00:24:59.421567: step: 1504/529, loss: 0.1272542029619217
2023-01-23 00:25:00.551078: step: 1508/529, loss: 0.2846756875514984
2023-01-23 00:25:01.679402: step: 1512/529, loss: 0.814903736114502
2023-01-23 00:25:02.851622: step: 1516/529, loss: 0.24233828485012054
2023-01-23 00:25:03.979198: step: 1520/529, loss: 0.4306846559047699
2023-01-23 00:25:05.109523: step: 1524/529, loss: 0.054372213780879974
2023-01-23 00:25:06.230191: step: 1528/529, loss: 0.32174140214920044
2023-01-23 00:25:07.360784: step: 1532/529, loss: 0.12267415970563889
2023-01-23 00:25:08.498537: step: 1536/529, loss: 0.07979068905115128
2023-01-23 00:25:09.651414: step: 1540/529, loss: 0.09366913139820099
2023-01-23 00:25:10.797695: step: 1544/529, loss: 0.12291507422924042
2023-01-23 00:25:11.958593: step: 1548/529, loss: 0.854139506816864
2023-01-23 00:25:13.117969: step: 1552/529, loss: 0.23747539520263672
2023-01-23 00:25:14.259175: step: 1556/529, loss: 0.0986103042960167
2023-01-23 00:25:15.406543: step: 1560/529, loss: 0.07693271338939667
2023-01-23 00:25:16.574598: step: 1564/529, loss: 0.02435903623700142
2023-01-23 00:25:17.749374: step: 1568/529, loss: 0.19802474975585938
2023-01-23 00:25:18.888695: step: 1572/529, loss: 0.11087074875831604
2023-01-23 00:25:20.056320: step: 1576/529, loss: 0.14248834550380707
2023-01-23 00:25:21.176394: step: 1580/529, loss: 0.023084450513124466
2023-01-23 00:25:22.293652: step: 1584/529, loss: 0.15884724259376526
2023-01-23 00:25:23.457366: step: 1588/529, loss: 0.06725578755140305
2023-01-23 00:25:24.597330: step: 1592/529, loss: 0.44117504358291626
2023-01-23 00:25:25.702195: step: 1596/529, loss: 0.1392897665500641
2023-01-23 00:25:26.828484: step: 1600/529, loss: 0.08854389190673828
2023-01-23 00:25:27.986163: step: 1604/529, loss: 0.20504769682884216
2023-01-23 00:25:29.131660: step: 1608/529, loss: 1.0618385076522827
2023-01-23 00:25:30.267063: step: 1612/529, loss: 0.2695992887020111
2023-01-23 00:25:31.392007: step: 1616/529, loss: 0.16080017387866974
2023-01-23 00:25:32.566808: step: 1620/529, loss: 0.48127710819244385
2023-01-23 00:25:33.706230: step: 1624/529, loss: 2.445857524871826
2023-01-23 00:25:34.844768: step: 1628/529, loss: 0.05478806793689728
2023-01-23 00:25:35.995542: step: 1632/529, loss: 0.07957783341407776
2023-01-23 00:25:37.118330: step: 1636/529, loss: 0.45860737562179565
2023-01-23 00:25:38.258940: step: 1640/529, loss: 0.15542663633823395
2023-01-23 00:25:39.437325: step: 1644/529, loss: 1.3824344873428345
2023-01-23 00:25:40.609438: step: 1648/529, loss: 0.2135431319475174
2023-01-23 00:25:41.749466: step: 1652/529, loss: 0.08407983183860779
2023-01-23 00:25:42.890709: step: 1656/529, loss: 0.04255995899438858
2023-01-23 00:25:44.017761: step: 1660/529, loss: 0.10629893094301224
2023-01-23 00:25:45.173028: step: 1664/529, loss: 0.18027277290821075
2023-01-23 00:25:46.302022: step: 1668/529, loss: 0.1216583251953125
2023-01-23 00:25:47.427432: step: 1672/529, loss: 0.10211792588233948
2023-01-23 00:25:48.558842: step: 1676/529, loss: 0.23892784118652344
2023-01-23 00:25:49.744067: step: 1680/529, loss: 0.0686337947845459
2023-01-23 00:25:50.897045: step: 1684/529, loss: 0.07210950553417206
2023-01-23 00:25:52.028237: step: 1688/529, loss: 0.3025897741317749
2023-01-23 00:25:53.189103: step: 1692/529, loss: 0.15028133988380432
2023-01-23 00:25:54.338987: step: 1696/529, loss: 0.13339270651340485
2023-01-23 00:25:55.483443: step: 1700/529, loss: 0.10011950135231018
2023-01-23 00:25:56.612154: step: 1704/529, loss: 0.14445707201957703
2023-01-23 00:25:57.749392: step: 1708/529, loss: 0.29445910453796387
2023-01-23 00:25:58.921668: step: 1712/529, loss: 0.3250378668308258
2023-01-23 00:26:00.054073: step: 1716/529, loss: 0.9704848527908325
2023-01-23 00:26:01.175651: step: 1720/529, loss: 0.20039625465869904
2023-01-23 00:26:02.314694: step: 1724/529, loss: 0.08942041546106339
2023-01-23 00:26:03.473460: step: 1728/529, loss: 0.0853240042924881
2023-01-23 00:26:04.620721: step: 1732/529, loss: 0.35689955949783325
2023-01-23 00:26:05.765741: step: 1736/529, loss: 0.5217226147651672
2023-01-23 00:26:06.889192: step: 1740/529, loss: 0.23207783699035645
2023-01-23 00:26:08.043619: step: 1744/529, loss: 0.18612231314182281
2023-01-23 00:26:09.193836: step: 1748/529, loss: 0.13245268166065216
2023-01-23 00:26:10.336895: step: 1752/529, loss: 0.10207509994506836
2023-01-23 00:26:11.503892: step: 1756/529, loss: 0.12094831466674805
2023-01-23 00:26:12.661415: step: 1760/529, loss: 0.27033597230911255
2023-01-23 00:26:13.821567: step: 1764/529, loss: 0.19553199410438538
2023-01-23 00:26:14.987113: step: 1768/529, loss: 1.1943162679672241
2023-01-23 00:26:16.115930: step: 1772/529, loss: 0.07562501728534698
2023-01-23 00:26:17.292116: step: 1776/529, loss: 0.37366580963134766
2023-01-23 00:26:18.425345: step: 1780/529, loss: 0.3176751732826233
2023-01-23 00:26:19.545783: step: 1784/529, loss: 0.08720416575670242
2023-01-23 00:26:20.684764: step: 1788/529, loss: 0.09665494412183762
2023-01-23 00:26:21.835343: step: 1792/529, loss: 0.10573120415210724
2023-01-23 00:26:22.970723: step: 1796/529, loss: 0.09265251457691193
2023-01-23 00:26:24.095032: step: 1800/529, loss: 0.5216751098632812
2023-01-23 00:26:25.207475: step: 1804/529, loss: 0.0836523100733757
2023-01-23 00:26:26.340690: step: 1808/529, loss: 0.0906444564461708
2023-01-23 00:26:27.471427: step: 1812/529, loss: 0.3712461590766907
2023-01-23 00:26:28.616356: step: 1816/529, loss: 0.6995339393615723
2023-01-23 00:26:29.768625: step: 1820/529, loss: 0.11586017161607742
2023-01-23 00:26:30.919886: step: 1824/529, loss: 0.02235245704650879
2023-01-23 00:26:32.078031: step: 1828/529, loss: 0.07299160957336426
2023-01-23 00:26:33.202521: step: 1832/529, loss: 0.7483769655227661
2023-01-23 00:26:34.322089: step: 1836/529, loss: 0.08506083488464355
2023-01-23 00:26:35.485359: step: 1840/529, loss: 0.16500243544578552
2023-01-23 00:26:36.613778: step: 1844/529, loss: 0.16785374283790588
2023-01-23 00:26:37.754759: step: 1848/529, loss: 0.8889985084533691
2023-01-23 00:26:38.909976: step: 1852/529, loss: 0.09586697071790695
2023-01-23 00:26:40.062222: step: 1856/529, loss: 0.16931210458278656
2023-01-23 00:26:41.275422: step: 1860/529, loss: 0.5723984837532043
2023-01-23 00:26:42.463252: step: 1864/529, loss: 0.6708760261535645
2023-01-23 00:26:43.598857: step: 1868/529, loss: 0.11356306076049805
2023-01-23 00:26:44.743165: step: 1872/529, loss: 0.4433327913284302
2023-01-23 00:26:45.917125: step: 1876/529, loss: 0.12220098823308945
2023-01-23 00:26:47.082979: step: 1880/529, loss: 0.25582271814346313
2023-01-23 00:26:48.243471: step: 1884/529, loss: 0.031248951330780983
2023-01-23 00:26:49.357957: step: 1888/529, loss: 0.10533743351697922
2023-01-23 00:26:50.473218: step: 1892/529, loss: 0.07743396610021591
2023-01-23 00:26:51.616882: step: 1896/529, loss: 0.08821959793567657
2023-01-23 00:26:52.752966: step: 1900/529, loss: 0.23253564536571503
2023-01-23 00:26:53.921786: step: 1904/529, loss: 0.09577665477991104
2023-01-23 00:26:55.075302: step: 1908/529, loss: 0.10028591006994247
2023-01-23 00:26:56.201197: step: 1912/529, loss: 0.07080264389514923
2023-01-23 00:26:57.318882: step: 1916/529, loss: 0.30206307768821716
2023-01-23 00:26:58.475195: step: 1920/529, loss: 3.4601290225982666
2023-01-23 00:26:59.604334: step: 1924/529, loss: 0.4781244397163391
2023-01-23 00:27:00.756367: step: 1928/529, loss: 0.1625032126903534
2023-01-23 00:27:01.889122: step: 1932/529, loss: 0.05069418251514435
2023-01-23 00:27:03.029322: step: 1936/529, loss: 0.15439115464687347
2023-01-23 00:27:04.148275: step: 1940/529, loss: 0.06670689582824707
2023-01-23 00:27:05.257878: step: 1944/529, loss: 0.0798218697309494
2023-01-23 00:27:06.372218: step: 1948/529, loss: 0.04812512546777725
2023-01-23 00:27:07.548508: step: 1952/529, loss: 0.314921498298645
2023-01-23 00:27:08.680435: step: 1956/529, loss: 0.053060341626405716
2023-01-23 00:27:09.829417: step: 1960/529, loss: 0.19245347380638123
2023-01-23 00:27:10.956307: step: 1964/529, loss: 0.08722953498363495
2023-01-23 00:27:12.076517: step: 1968/529, loss: 0.1384839415550232
2023-01-23 00:27:13.195596: step: 1972/529, loss: 0.04252929612994194
2023-01-23 00:27:14.353836: step: 1976/529, loss: 0.3670635223388672
2023-01-23 00:27:15.490496: step: 1980/529, loss: 0.03096799924969673
2023-01-23 00:27:16.604365: step: 1984/529, loss: 0.055448152124881744
2023-01-23 00:27:17.748968: step: 1988/529, loss: 0.14109449088573456
2023-01-23 00:27:18.906051: step: 1992/529, loss: 0.1049683541059494
2023-01-23 00:27:20.026538: step: 1996/529, loss: 0.05912170559167862
2023-01-23 00:27:21.188408: step: 2000/529, loss: 0.29120540618896484
2023-01-23 00:27:22.345335: step: 2004/529, loss: 0.7962394952774048
2023-01-23 00:27:23.477420: step: 2008/529, loss: 0.2000894546508789
2023-01-23 00:27:24.595265: step: 2012/529, loss: 0.18997983634471893
2023-01-23 00:27:25.718930: step: 2016/529, loss: 0.16265468299388885
2023-01-23 00:27:26.843302: step: 2020/529, loss: 0.04038066789507866
2023-01-23 00:27:27.955963: step: 2024/529, loss: 0.0757012888789177
2023-01-23 00:27:29.112526: step: 2028/529, loss: 0.2071550041437149
2023-01-23 00:27:30.280425: step: 2032/529, loss: 0.14090615510940552
2023-01-23 00:27:31.446902: step: 2036/529, loss: 0.15868401527404785
2023-01-23 00:27:32.563765: step: 2040/529, loss: 0.12236276268959045
2023-01-23 00:27:33.700390: step: 2044/529, loss: 0.15578851103782654
2023-01-23 00:27:34.814453: step: 2048/529, loss: 0.060861311852931976
2023-01-23 00:27:35.965803: step: 2052/529, loss: 0.03957071527838707
2023-01-23 00:27:37.126377: step: 2056/529, loss: 0.4482616186141968
2023-01-23 00:27:38.265287: step: 2060/529, loss: 0.797402024269104
2023-01-23 00:27:39.387928: step: 2064/529, loss: 0.8909168243408203
2023-01-23 00:27:40.531201: step: 2068/529, loss: 0.07186398655176163
2023-01-23 00:27:41.687004: step: 2072/529, loss: 0.6693910360336304
2023-01-23 00:27:42.817644: step: 2076/529, loss: 2.4048049449920654
2023-01-23 00:27:43.977866: step: 2080/529, loss: 0.23566734790802002
2023-01-23 00:27:45.171753: step: 2084/529, loss: 0.7993472814559937
2023-01-23 00:27:46.311764: step: 2088/529, loss: 0.1624138355255127
2023-01-23 00:27:47.456698: step: 2092/529, loss: 0.19414672255516052
2023-01-23 00:27:48.577397: step: 2096/529, loss: 0.12755393981933594
2023-01-23 00:27:49.723225: step: 2100/529, loss: 0.12087831646203995
2023-01-23 00:27:50.854665: step: 2104/529, loss: 0.09632611274719238
2023-01-23 00:27:52.027077: step: 2108/529, loss: 0.15626157820224762
2023-01-23 00:27:53.164720: step: 2112/529, loss: 0.9749086499214172
2023-01-23 00:27:54.341347: step: 2116/529, loss: 0.05219235271215439
==================================================
Loss: 0.265
--------------------
Dev: {'event': {'p': 0.5289256198347108, 'r': 0.7669773635153129, 'f1': 0.6260869565217392}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.5726122982991714, 'r': 0.7607184241019699, 'f1': 0.6533963672555362}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.4835164835164835, 'r': 0.8148148148148148, 'f1': 0.6068965517241379}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.5, 'r': 0.5238095238095238, 'f1': 0.5116279069767442}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.4107142857142857, 'r': 0.6388888888888888, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.6301369863013698, 'r': 0.8518518518518519, 'f1': 0.7244094488188976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6956521739130435, 'r': 0.5079365079365079, 'f1': 0.5871559633027522}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5428571428571428, 'r': 0.5277777777777778, 'f1': 0.5352112676056338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 6
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:28:36.243236: step: 4/529, loss: 0.1470019519329071
2023-01-23 00:28:37.391586: step: 8/529, loss: 0.15354004502296448
2023-01-23 00:28:38.515281: step: 12/529, loss: 0.07719042152166367
2023-01-23 00:28:39.644364: step: 16/529, loss: 0.43562179803848267
2023-01-23 00:28:40.803560: step: 20/529, loss: 0.11794624477624893
2023-01-23 00:28:41.939739: step: 24/529, loss: 0.018527984619140625
2023-01-23 00:28:43.098613: step: 28/529, loss: 0.2061825692653656
2023-01-23 00:28:44.212364: step: 32/529, loss: 0.021318960934877396
2023-01-23 00:28:45.335144: step: 36/529, loss: 0.05560178682208061
2023-01-23 00:28:46.496895: step: 40/529, loss: 0.3228421211242676
2023-01-23 00:28:47.633362: step: 44/529, loss: 0.2062358856201172
2023-01-23 00:28:48.772965: step: 48/529, loss: 0.06267385929822922
2023-01-23 00:28:49.955475: step: 52/529, loss: 0.21166104078292847
2023-01-23 00:28:51.066880: step: 56/529, loss: 0.07229993492364883
2023-01-23 00:28:52.211999: step: 60/529, loss: 0.06668376922607422
2023-01-23 00:28:53.350374: step: 64/529, loss: 0.15439891815185547
2023-01-23 00:28:54.482091: step: 68/529, loss: 0.5146299600601196
2023-01-23 00:28:55.596998: step: 72/529, loss: 0.085711769759655
2023-01-23 00:28:56.718770: step: 76/529, loss: 0.3377135694026947
2023-01-23 00:28:57.901938: step: 80/529, loss: 0.4217444360256195
2023-01-23 00:28:59.058053: step: 84/529, loss: 0.17859764397144318
2023-01-23 00:29:00.167133: step: 88/529, loss: 0.03776540607213974
2023-01-23 00:29:01.335943: step: 92/529, loss: 0.3045387268066406
2023-01-23 00:29:02.475464: step: 96/529, loss: 0.11409024894237518
2023-01-23 00:29:03.610899: step: 100/529, loss: 0.234690859913826
2023-01-23 00:29:04.770882: step: 104/529, loss: 0.19339197874069214
2023-01-23 00:29:05.941270: step: 108/529, loss: 0.3174059987068176
2023-01-23 00:29:07.071156: step: 112/529, loss: 0.03271510452032089
2023-01-23 00:29:08.239247: step: 116/529, loss: 0.12669047713279724
2023-01-23 00:29:09.403265: step: 120/529, loss: 0.10272550582885742
2023-01-23 00:29:10.528800: step: 124/529, loss: 0.5136853456497192
2023-01-23 00:29:11.673698: step: 128/529, loss: 0.2828788757324219
2023-01-23 00:29:12.818543: step: 132/529, loss: 0.02475113235414028
2023-01-23 00:29:13.957346: step: 136/529, loss: 0.01852746121585369
2023-01-23 00:29:15.102658: step: 140/529, loss: 0.2424711287021637
2023-01-23 00:29:16.231310: step: 144/529, loss: 0.19414682686328888
2023-01-23 00:29:17.379747: step: 148/529, loss: 0.12833824753761292
2023-01-23 00:29:18.513833: step: 152/529, loss: 0.028827380388975143
2023-01-23 00:29:19.644343: step: 156/529, loss: 0.20758502185344696
2023-01-23 00:29:20.765464: step: 160/529, loss: 0.06466741859912872
2023-01-23 00:29:21.895841: step: 164/529, loss: 0.041637469083070755
2023-01-23 00:29:23.029294: step: 168/529, loss: 0.12986308336257935
2023-01-23 00:29:24.152680: step: 172/529, loss: 0.6346961855888367
2023-01-23 00:29:25.290510: step: 176/529, loss: 0.15828584134578705
2023-01-23 00:29:26.424487: step: 180/529, loss: 0.48843392729759216
2023-01-23 00:29:27.550538: step: 184/529, loss: 0.47235769033432007
2023-01-23 00:29:28.695821: step: 188/529, loss: 0.0854257270693779
2023-01-23 00:29:29.824396: step: 192/529, loss: 0.44334205985069275
2023-01-23 00:29:30.957236: step: 196/529, loss: 0.0744076743721962
2023-01-23 00:29:32.093181: step: 200/529, loss: 0.04431162029504776
2023-01-23 00:29:33.257024: step: 204/529, loss: 0.31575697660446167
2023-01-23 00:29:34.444328: step: 208/529, loss: 0.1267659217119217
2023-01-23 00:29:35.565433: step: 212/529, loss: 0.22790119051933289
2023-01-23 00:29:36.693635: step: 216/529, loss: 0.027790643274784088
2023-01-23 00:29:37.837139: step: 220/529, loss: 0.34567898511886597
2023-01-23 00:29:38.960787: step: 224/529, loss: 0.35775792598724365
2023-01-23 00:29:40.087405: step: 228/529, loss: 0.17790432274341583
2023-01-23 00:29:41.256598: step: 232/529, loss: 0.1421743929386139
2023-01-23 00:29:42.409462: step: 236/529, loss: 0.11125729978084564
2023-01-23 00:29:43.548362: step: 240/529, loss: 0.23817892372608185
2023-01-23 00:29:44.709490: step: 244/529, loss: 1.199149250984192
2023-01-23 00:29:45.839920: step: 248/529, loss: 0.1931035965681076
2023-01-23 00:29:46.970021: step: 252/529, loss: 0.029933644458651543
2023-01-23 00:29:48.092460: step: 256/529, loss: 0.1190594732761383
2023-01-23 00:29:49.220793: step: 260/529, loss: 0.17947152256965637
2023-01-23 00:29:50.358348: step: 264/529, loss: 0.08676370978355408
2023-01-23 00:29:51.504293: step: 268/529, loss: 0.05386481434106827
2023-01-23 00:29:52.679567: step: 272/529, loss: 0.3328613340854645
2023-01-23 00:29:53.826996: step: 276/529, loss: 0.17038804292678833
2023-01-23 00:29:54.959705: step: 280/529, loss: 0.16274502873420715
2023-01-23 00:29:56.128974: step: 284/529, loss: 0.20642271637916565
2023-01-23 00:29:57.231665: step: 288/529, loss: 0.13507691025733948
2023-01-23 00:29:58.365071: step: 292/529, loss: 0.08156852424144745
2023-01-23 00:29:59.479501: step: 296/529, loss: 0.0426325798034668
2023-01-23 00:30:00.602200: step: 300/529, loss: 0.051397159695625305
2023-01-23 00:30:01.776524: step: 304/529, loss: 0.21066169440746307
2023-01-23 00:30:02.936589: step: 308/529, loss: 0.03730187565088272
2023-01-23 00:30:04.088238: step: 312/529, loss: 0.10313472896814346
2023-01-23 00:30:05.217555: step: 316/529, loss: 0.07313623279333115
2023-01-23 00:30:06.329464: step: 320/529, loss: 0.085165835916996
2023-01-23 00:30:07.532091: step: 324/529, loss: 0.10756182670593262
2023-01-23 00:30:08.701342: step: 328/529, loss: 0.09438561648130417
2023-01-23 00:30:09.814087: step: 332/529, loss: 0.038346484303474426
2023-01-23 00:30:10.940508: step: 336/529, loss: 0.02523212507367134
2023-01-23 00:30:12.058274: step: 340/529, loss: 0.11392489075660706
2023-01-23 00:30:13.195364: step: 344/529, loss: 0.08156931400299072
2023-01-23 00:30:14.362550: step: 348/529, loss: 0.16472864151000977
2023-01-23 00:30:15.513059: step: 352/529, loss: 0.20975056290626526
2023-01-23 00:30:16.663912: step: 356/529, loss: 0.042269516736269
2023-01-23 00:30:17.817803: step: 360/529, loss: 0.2373577058315277
2023-01-23 00:30:19.011440: step: 364/529, loss: 0.07121773064136505
2023-01-23 00:30:20.159945: step: 368/529, loss: 0.07017125934362411
2023-01-23 00:30:21.357550: step: 372/529, loss: 0.21531495451927185
2023-01-23 00:30:22.481652: step: 376/529, loss: 0.04931068792939186
2023-01-23 00:30:23.629750: step: 380/529, loss: 0.08102398365736008
2023-01-23 00:30:24.781618: step: 384/529, loss: 0.11685208976268768
2023-01-23 00:30:25.932718: step: 388/529, loss: 0.03999481350183487
2023-01-23 00:30:27.100097: step: 392/529, loss: 0.08942137658596039
2023-01-23 00:30:28.239708: step: 396/529, loss: 0.06027255207300186
2023-01-23 00:30:29.380124: step: 400/529, loss: 0.3250984847545624
2023-01-23 00:30:30.553115: step: 404/529, loss: 0.4859161376953125
2023-01-23 00:30:31.723274: step: 408/529, loss: 0.21767020225524902
2023-01-23 00:30:32.848238: step: 412/529, loss: 0.02526264265179634
2023-01-23 00:30:33.944338: step: 416/529, loss: 0.17558957636356354
2023-01-23 00:30:35.063268: step: 420/529, loss: 0.1540956050157547
2023-01-23 00:30:36.214811: step: 424/529, loss: 0.24311915040016174
2023-01-23 00:30:37.357468: step: 428/529, loss: 0.055359553545713425
2023-01-23 00:30:38.498296: step: 432/529, loss: 0.08109503239393234
2023-01-23 00:30:39.660330: step: 436/529, loss: 0.7565504312515259
2023-01-23 00:30:40.818561: step: 440/529, loss: 0.9818193316459656
2023-01-23 00:30:41.949971: step: 444/529, loss: 0.49908995628356934
2023-01-23 00:30:43.103559: step: 448/529, loss: 0.13468456268310547
2023-01-23 00:30:44.245416: step: 452/529, loss: 0.09451542049646378
2023-01-23 00:30:45.371506: step: 456/529, loss: 0.05398140847682953
2023-01-23 00:30:46.514274: step: 460/529, loss: 0.062566377222538
2023-01-23 00:30:47.668254: step: 464/529, loss: 0.13144922256469727
2023-01-23 00:30:48.823982: step: 468/529, loss: 0.25995445251464844
2023-01-23 00:30:49.942818: step: 472/529, loss: 0.0994727611541748
2023-01-23 00:30:51.078923: step: 476/529, loss: 0.1284542977809906
2023-01-23 00:30:52.229665: step: 480/529, loss: 0.15237684547901154
2023-01-23 00:30:53.340674: step: 484/529, loss: 0.13454779982566833
2023-01-23 00:30:54.461627: step: 488/529, loss: 0.49535244703292847
2023-01-23 00:30:55.603077: step: 492/529, loss: 0.1663494110107422
2023-01-23 00:30:56.761628: step: 496/529, loss: 0.4106990098953247
2023-01-23 00:30:57.900352: step: 500/529, loss: 0.12006096541881561
2023-01-23 00:30:59.020242: step: 504/529, loss: 0.03542385250329971
2023-01-23 00:31:00.168741: step: 508/529, loss: 0.0414612777531147
2023-01-23 00:31:01.322394: step: 512/529, loss: 0.5257449150085449
2023-01-23 00:31:02.452652: step: 516/529, loss: 0.21701198816299438
2023-01-23 00:31:03.595245: step: 520/529, loss: 0.12552958726882935
2023-01-23 00:31:04.732954: step: 524/529, loss: 0.1172323226928711
2023-01-23 00:31:05.880659: step: 528/529, loss: 2.761033535003662
2023-01-23 00:31:07.032912: step: 532/529, loss: 0.27108487486839294
2023-01-23 00:31:08.158969: step: 536/529, loss: 0.17586469650268555
2023-01-23 00:31:09.316212: step: 540/529, loss: 0.043247416615486145
2023-01-23 00:31:10.432919: step: 544/529, loss: 0.018515586853027344
2023-01-23 00:31:11.567657: step: 548/529, loss: 0.02021508291363716
2023-01-23 00:31:12.718299: step: 552/529, loss: 0.0851355567574501
2023-01-23 00:31:13.849026: step: 556/529, loss: 0.17973260581493378
2023-01-23 00:31:14.979502: step: 560/529, loss: 0.4213048815727234
2023-01-23 00:31:16.154625: step: 564/529, loss: 0.17982031404972076
2023-01-23 00:31:17.297937: step: 568/529, loss: 0.12651550769805908
2023-01-23 00:31:18.424261: step: 572/529, loss: 0.09167223423719406
2023-01-23 00:31:19.573418: step: 576/529, loss: 0.08841677010059357
2023-01-23 00:31:20.706170: step: 580/529, loss: 0.18619662523269653
2023-01-23 00:31:21.853535: step: 584/529, loss: 0.5100477933883667
2023-01-23 00:31:22.977578: step: 588/529, loss: 0.09792108088731766
2023-01-23 00:31:24.144764: step: 592/529, loss: 0.09741516411304474
2023-01-23 00:31:25.294230: step: 596/529, loss: 0.015562344342470169
2023-01-23 00:31:26.439976: step: 600/529, loss: 0.15650692582130432
2023-01-23 00:31:27.614087: step: 604/529, loss: 0.19272108376026154
2023-01-23 00:31:28.746517: step: 608/529, loss: 1.4801222085952759
2023-01-23 00:31:29.914118: step: 612/529, loss: 0.263576865196228
2023-01-23 00:31:31.069100: step: 616/529, loss: 0.005211162380874157
2023-01-23 00:31:32.222313: step: 620/529, loss: 0.07423782348632812
2023-01-23 00:31:33.381211: step: 624/529, loss: 0.04071540758013725
2023-01-23 00:31:34.543413: step: 628/529, loss: 0.051209352910518646
2023-01-23 00:31:35.692493: step: 632/529, loss: 0.013059521093964577
2023-01-23 00:31:36.857457: step: 636/529, loss: 0.2136402130126953
2023-01-23 00:31:38.022486: step: 640/529, loss: 0.08834586292505264
2023-01-23 00:31:39.148879: step: 644/529, loss: 0.7316094040870667
2023-01-23 00:31:40.285280: step: 648/529, loss: 0.1162010207772255
2023-01-23 00:31:41.441874: step: 652/529, loss: 0.16994495689868927
2023-01-23 00:31:42.575006: step: 656/529, loss: 0.13997697830200195
2023-01-23 00:31:43.711443: step: 660/529, loss: 0.030808638781309128
2023-01-23 00:31:44.868032: step: 664/529, loss: 0.04116683080792427
2023-01-23 00:31:46.005148: step: 668/529, loss: 0.03182578086853027
2023-01-23 00:31:47.126667: step: 672/529, loss: 0.08994419872760773
2023-01-23 00:31:48.286952: step: 676/529, loss: 0.11245398223400116
2023-01-23 00:31:49.418142: step: 680/529, loss: 0.5464494824409485
2023-01-23 00:31:50.574568: step: 684/529, loss: 0.051720716059207916
2023-01-23 00:31:51.707753: step: 688/529, loss: 0.2325720489025116
2023-01-23 00:31:52.827964: step: 692/529, loss: 0.2228042036294937
2023-01-23 00:31:53.960375: step: 696/529, loss: 0.043380022048950195
2023-01-23 00:31:55.082440: step: 700/529, loss: 0.09498069435358047
2023-01-23 00:31:56.243725: step: 704/529, loss: 0.13558922708034515
2023-01-23 00:31:57.380907: step: 708/529, loss: 0.07393055409193039
2023-01-23 00:31:58.541089: step: 712/529, loss: 0.06666383892297745
2023-01-23 00:31:59.690272: step: 716/529, loss: 0.16336464881896973
2023-01-23 00:32:00.830521: step: 720/529, loss: 0.10356657207012177
2023-01-23 00:32:01.966853: step: 724/529, loss: 0.06547460705041885
2023-01-23 00:32:03.107988: step: 728/529, loss: 0.13290682435035706
2023-01-23 00:32:04.231141: step: 732/529, loss: 0.09052858501672745
2023-01-23 00:32:05.362782: step: 736/529, loss: 0.396187424659729
2023-01-23 00:32:06.506315: step: 740/529, loss: 0.6283569931983948
2023-01-23 00:32:07.661561: step: 744/529, loss: 0.009532547555863857
2023-01-23 00:32:08.839225: step: 748/529, loss: 0.42701712250709534
2023-01-23 00:32:09.956229: step: 752/529, loss: 0.032381534576416016
2023-01-23 00:32:11.118648: step: 756/529, loss: 0.023659182712435722
2023-01-23 00:32:12.265614: step: 760/529, loss: 0.053922273218631744
2023-01-23 00:32:13.463384: step: 764/529, loss: 0.7633985280990601
2023-01-23 00:32:14.612143: step: 768/529, loss: 0.05611744523048401
2023-01-23 00:32:15.777857: step: 772/529, loss: 0.12910637259483337
2023-01-23 00:32:16.919689: step: 776/529, loss: 0.1542777568101883
2023-01-23 00:32:18.073345: step: 780/529, loss: 0.1200251579284668
2023-01-23 00:32:19.213605: step: 784/529, loss: 0.04896056652069092
2023-01-23 00:32:20.366365: step: 788/529, loss: 0.008860170841217041
2023-01-23 00:32:21.518495: step: 792/529, loss: 0.14046001434326172
2023-01-23 00:32:22.641547: step: 796/529, loss: 0.24559718370437622
2023-01-23 00:32:23.779435: step: 800/529, loss: 0.4521062672138214
2023-01-23 00:32:24.916320: step: 804/529, loss: 0.16702929139137268
2023-01-23 00:32:26.067355: step: 808/529, loss: 0.052259065210819244
2023-01-23 00:32:27.199837: step: 812/529, loss: 3.2721288204193115
2023-01-23 00:32:28.353765: step: 816/529, loss: 0.1798514425754547
2023-01-23 00:32:29.482318: step: 820/529, loss: 0.15131349861621857
2023-01-23 00:32:30.603165: step: 824/529, loss: 0.4318869709968567
2023-01-23 00:32:31.768564: step: 828/529, loss: 0.02573556825518608
2023-01-23 00:32:32.916825: step: 832/529, loss: 0.04328899458050728
2023-01-23 00:32:34.073896: step: 836/529, loss: 0.1388297975063324
2023-01-23 00:32:35.260478: step: 840/529, loss: 0.12231426686048508
2023-01-23 00:32:36.411207: step: 844/529, loss: 0.08716468513011932
2023-01-23 00:32:37.575911: step: 848/529, loss: 0.12824907898902893
2023-01-23 00:32:38.707434: step: 852/529, loss: 0.09431162476539612
2023-01-23 00:32:39.825417: step: 856/529, loss: 0.058193303644657135
2023-01-23 00:32:41.014814: step: 860/529, loss: 0.11723414063453674
2023-01-23 00:32:42.167841: step: 864/529, loss: 0.10897369682788849
2023-01-23 00:32:43.302460: step: 868/529, loss: 0.11294145882129669
2023-01-23 00:32:44.424266: step: 872/529, loss: 0.06196422502398491
2023-01-23 00:32:45.578893: step: 876/529, loss: 0.06574240326881409
2023-01-23 00:32:46.734691: step: 880/529, loss: 0.0637269988656044
2023-01-23 00:32:47.865996: step: 884/529, loss: 0.19259533286094666
2023-01-23 00:32:49.005098: step: 888/529, loss: 0.16550368070602417
2023-01-23 00:32:50.129487: step: 892/529, loss: 0.13171425461769104
2023-01-23 00:32:51.281272: step: 896/529, loss: 0.005716037470847368
2023-01-23 00:32:52.431887: step: 900/529, loss: 0.015420913696289062
2023-01-23 00:32:53.540479: step: 904/529, loss: 0.04086365923285484
2023-01-23 00:32:54.674939: step: 908/529, loss: 0.12154017388820648
2023-01-23 00:32:55.813423: step: 912/529, loss: 0.14820271730422974
2023-01-23 00:32:56.943867: step: 916/529, loss: 0.03450622782111168
2023-01-23 00:32:58.075940: step: 920/529, loss: 0.12771210074424744
2023-01-23 00:32:59.204056: step: 924/529, loss: 0.06066742166876793
2023-01-23 00:33:00.355199: step: 928/529, loss: 0.03146343305706978
2023-01-23 00:33:01.481360: step: 932/529, loss: 0.22619009017944336
2023-01-23 00:33:02.609520: step: 936/529, loss: 0.10137005150318146
2023-01-23 00:33:03.758076: step: 940/529, loss: 0.03821449354290962
2023-01-23 00:33:04.881081: step: 944/529, loss: 0.10627007484436035
2023-01-23 00:33:05.990425: step: 948/529, loss: 0.033090949058532715
2023-01-23 00:33:07.111605: step: 952/529, loss: 0.4556516706943512
2023-01-23 00:33:08.253657: step: 956/529, loss: 0.07339987903833389
2023-01-23 00:33:09.438348: step: 960/529, loss: 0.05294237285852432
2023-01-23 00:33:10.559458: step: 964/529, loss: 0.583365797996521
2023-01-23 00:33:11.722108: step: 968/529, loss: 0.03099527209997177
2023-01-23 00:33:12.885957: step: 972/529, loss: 1.66312837600708
2023-01-23 00:33:14.019427: step: 976/529, loss: 0.17345017194747925
2023-01-23 00:33:15.153014: step: 980/529, loss: 0.1968173086643219
2023-01-23 00:33:16.364317: step: 984/529, loss: 0.6370856761932373
2023-01-23 00:33:17.478068: step: 988/529, loss: 0.08437786251306534
2023-01-23 00:33:18.634570: step: 992/529, loss: 0.02574920654296875
2023-01-23 00:33:19.781472: step: 996/529, loss: 0.07056809216737747
2023-01-23 00:33:20.916212: step: 1000/529, loss: 0.2804013192653656
2023-01-23 00:33:22.067151: step: 1004/529, loss: 0.09528064727783203
2023-01-23 00:33:23.191993: step: 1008/529, loss: 0.5438389182090759
2023-01-23 00:33:24.308323: step: 1012/529, loss: 0.12470737099647522
2023-01-23 00:33:25.439097: step: 1016/529, loss: 0.45941734313964844
2023-01-23 00:33:26.567613: step: 1020/529, loss: 0.340905100107193
2023-01-23 00:33:27.693827: step: 1024/529, loss: 0.5324832201004028
2023-01-23 00:33:28.810321: step: 1028/529, loss: 0.0022804916370660067
2023-01-23 00:33:29.961268: step: 1032/529, loss: 0.023268794640898705
2023-01-23 00:33:31.100006: step: 1036/529, loss: 0.20383435487747192
2023-01-23 00:33:32.239978: step: 1040/529, loss: 0.17854785919189453
2023-01-23 00:33:33.399069: step: 1044/529, loss: 0.12450919300317764
2023-01-23 00:33:34.532510: step: 1048/529, loss: 0.1918668895959854
2023-01-23 00:33:35.675193: step: 1052/529, loss: 0.032587431371212006
2023-01-23 00:33:36.821540: step: 1056/529, loss: 0.07682953029870987
2023-01-23 00:33:37.967462: step: 1060/529, loss: 0.7495388984680176
2023-01-23 00:33:39.106702: step: 1064/529, loss: 0.11987963318824768
2023-01-23 00:33:40.249936: step: 1068/529, loss: 0.22625942528247833
2023-01-23 00:33:41.390380: step: 1072/529, loss: 0.021382426843047142
2023-01-23 00:33:42.535533: step: 1076/529, loss: 0.12423534691333771
2023-01-23 00:33:43.651449: step: 1080/529, loss: 0.1948629915714264
2023-01-23 00:33:44.836572: step: 1084/529, loss: 0.1633104383945465
2023-01-23 00:33:45.978599: step: 1088/529, loss: 0.1142793670296669
2023-01-23 00:33:47.079722: step: 1092/529, loss: 0.10774402320384979
2023-01-23 00:33:48.212661: step: 1096/529, loss: 0.13552847504615784
2023-01-23 00:33:49.360088: step: 1100/529, loss: 0.04751596599817276
2023-01-23 00:33:50.487629: step: 1104/529, loss: 0.04301629215478897
2023-01-23 00:33:51.625515: step: 1108/529, loss: 0.2184770554304123
2023-01-23 00:33:52.795539: step: 1112/529, loss: 0.295999139547348
2023-01-23 00:33:53.944171: step: 1116/529, loss: 0.06016087904572487
2023-01-23 00:33:55.102199: step: 1120/529, loss: 0.09768819808959961
2023-01-23 00:33:56.245473: step: 1124/529, loss: 0.13039502501487732
2023-01-23 00:33:57.378310: step: 1128/529, loss: 0.05840778350830078
2023-01-23 00:33:58.522778: step: 1132/529, loss: 0.20190268754959106
2023-01-23 00:33:59.690627: step: 1136/529, loss: 0.08311748504638672
2023-01-23 00:34:00.833291: step: 1140/529, loss: 0.2716061770915985
2023-01-23 00:34:01.986310: step: 1144/529, loss: 0.03608150780200958
2023-01-23 00:34:03.140370: step: 1148/529, loss: 0.12211474031209946
2023-01-23 00:34:04.296421: step: 1152/529, loss: 0.21685010194778442
2023-01-23 00:34:05.427624: step: 1156/529, loss: 0.10879373550415039
2023-01-23 00:34:06.579681: step: 1160/529, loss: 0.1112680435180664
2023-01-23 00:34:07.723555: step: 1164/529, loss: 0.05439148098230362
2023-01-23 00:34:08.856813: step: 1168/529, loss: 0.8142209053039551
2023-01-23 00:34:09.984307: step: 1172/529, loss: 0.042769573628902435
2023-01-23 00:34:11.135284: step: 1176/529, loss: 0.11595716327428818
2023-01-23 00:34:12.288516: step: 1180/529, loss: 0.05971822887659073
2023-01-23 00:34:13.471623: step: 1184/529, loss: 0.17592830955982208
2023-01-23 00:34:14.626021: step: 1188/529, loss: 0.159053236246109
2023-01-23 00:34:15.749782: step: 1192/529, loss: 0.009970713406801224
2023-01-23 00:34:16.929341: step: 1196/529, loss: 0.2734020948410034
2023-01-23 00:34:18.083803: step: 1200/529, loss: 0.41264763474464417
2023-01-23 00:34:19.215193: step: 1204/529, loss: 0.2158103883266449
2023-01-23 00:34:20.364197: step: 1208/529, loss: 0.1070350706577301
2023-01-23 00:34:21.493564: step: 1212/529, loss: 0.09604816883802414
2023-01-23 00:34:22.641482: step: 1216/529, loss: 0.13412058353424072
2023-01-23 00:34:23.780375: step: 1220/529, loss: 0.13900576531887054
2023-01-23 00:34:24.935008: step: 1224/529, loss: 0.17343321442604065
2023-01-23 00:34:26.056536: step: 1228/529, loss: 0.11591120064258575
2023-01-23 00:34:27.179847: step: 1232/529, loss: 1.3875800371170044
2023-01-23 00:34:28.304632: step: 1236/529, loss: 0.3283710479736328
2023-01-23 00:34:29.428806: step: 1240/529, loss: 0.25912365317344666
2023-01-23 00:34:30.559968: step: 1244/529, loss: 0.1069006696343422
2023-01-23 00:34:31.704690: step: 1248/529, loss: 0.52838134765625
2023-01-23 00:34:32.844656: step: 1252/529, loss: 0.1586301177740097
2023-01-23 00:34:33.952883: step: 1256/529, loss: 0.08219738304615021
2023-01-23 00:34:35.105427: step: 1260/529, loss: 0.20823365449905396
2023-01-23 00:34:36.251570: step: 1264/529, loss: 0.13486385345458984
2023-01-23 00:34:37.378569: step: 1268/529, loss: 0.5196982622146606
2023-01-23 00:34:38.548390: step: 1272/529, loss: 0.10855884850025177
2023-01-23 00:34:39.683285: step: 1276/529, loss: 1.1849353313446045
2023-01-23 00:34:40.826676: step: 1280/529, loss: 0.03606891632080078
2023-01-23 00:34:41.953910: step: 1284/529, loss: 0.30629798769950867
2023-01-23 00:34:43.109630: step: 1288/529, loss: 0.16889868676662445
2023-01-23 00:34:44.266095: step: 1292/529, loss: 0.14534083008766174
2023-01-23 00:34:45.396898: step: 1296/529, loss: 0.0436803363263607
2023-01-23 00:34:46.525402: step: 1300/529, loss: 0.05636334419250488
2023-01-23 00:34:47.678583: step: 1304/529, loss: 0.09943743050098419
2023-01-23 00:34:48.817851: step: 1308/529, loss: 0.1236240416765213
2023-01-23 00:34:49.957880: step: 1312/529, loss: 0.7554237246513367
2023-01-23 00:34:51.081329: step: 1316/529, loss: 0.15680323541164398
2023-01-23 00:34:52.234868: step: 1320/529, loss: 0.3036162555217743
2023-01-23 00:34:53.381827: step: 1324/529, loss: 0.13943703472614288
2023-01-23 00:34:54.527232: step: 1328/529, loss: 0.010088921524584293
2023-01-23 00:34:55.671402: step: 1332/529, loss: 0.2421044409275055
2023-01-23 00:34:56.844809: step: 1336/529, loss: 0.022925235331058502
2023-01-23 00:34:57.981476: step: 1340/529, loss: 0.1155308336019516
2023-01-23 00:34:59.154010: step: 1344/529, loss: 0.002062034560367465
2023-01-23 00:35:00.275248: step: 1348/529, loss: 0.17157764732837677
2023-01-23 00:35:01.425527: step: 1352/529, loss: 0.15530209243297577
2023-01-23 00:35:02.567901: step: 1356/529, loss: 0.09535965323448181
2023-01-23 00:35:03.734936: step: 1360/529, loss: 0.0919216126203537
2023-01-23 00:35:04.893909: step: 1364/529, loss: 0.13834786415100098
2023-01-23 00:35:06.052002: step: 1368/529, loss: 0.3966245651245117
2023-01-23 00:35:07.180776: step: 1372/529, loss: 0.2716043293476105
2023-01-23 00:35:08.331182: step: 1376/529, loss: 0.05550813674926758
2023-01-23 00:35:09.465391: step: 1380/529, loss: 0.079542376101017
2023-01-23 00:35:10.604313: step: 1384/529, loss: 0.10487575829029083
2023-01-23 00:35:11.736056: step: 1388/529, loss: 0.20975279808044434
2023-01-23 00:35:12.891652: step: 1392/529, loss: 0.07599058747291565
2023-01-23 00:35:14.006522: step: 1396/529, loss: 0.05106344074010849
2023-01-23 00:35:15.179645: step: 1400/529, loss: 0.5079331994056702
2023-01-23 00:35:16.314110: step: 1404/529, loss: 0.07319359481334686
2023-01-23 00:35:17.444982: step: 1408/529, loss: 0.16860371828079224
2023-01-23 00:35:18.597707: step: 1412/529, loss: 0.14180158078670502
2023-01-23 00:35:19.720928: step: 1416/529, loss: 0.11361794173717499
2023-01-23 00:35:20.869542: step: 1420/529, loss: 0.0701180025935173
2023-01-23 00:35:22.015691: step: 1424/529, loss: 0.0807436928153038
2023-01-23 00:35:23.157211: step: 1428/529, loss: 0.12773476541042328
2023-01-23 00:35:24.284804: step: 1432/529, loss: 0.2757173478603363
2023-01-23 00:35:25.407491: step: 1436/529, loss: 0.03978696092963219
2023-01-23 00:35:26.545911: step: 1440/529, loss: 0.126498281955719
2023-01-23 00:35:27.708532: step: 1444/529, loss: 0.3003924489021301
2023-01-23 00:35:28.842613: step: 1448/529, loss: 0.14830370247364044
2023-01-23 00:35:29.982041: step: 1452/529, loss: 0.17213058471679688
2023-01-23 00:35:31.152415: step: 1456/529, loss: 0.16140413284301758
2023-01-23 00:35:32.290985: step: 1460/529, loss: 0.0833822712302208
2023-01-23 00:35:33.426743: step: 1464/529, loss: 0.4955655038356781
2023-01-23 00:35:34.554677: step: 1468/529, loss: 0.0634758472442627
2023-01-23 00:35:35.710300: step: 1472/529, loss: 0.4631425142288208
2023-01-23 00:35:36.838795: step: 1476/529, loss: 0.3466726243495941
2023-01-23 00:35:37.975238: step: 1480/529, loss: 0.1507301926612854
2023-01-23 00:35:39.112036: step: 1484/529, loss: 0.11795787513256073
2023-01-23 00:35:40.239857: step: 1488/529, loss: 0.13609285652637482
2023-01-23 00:35:41.372865: step: 1492/529, loss: 0.1769440621137619
2023-01-23 00:35:42.490904: step: 1496/529, loss: 0.0699739009141922
2023-01-23 00:35:43.656139: step: 1500/529, loss: 0.3907044231891632
2023-01-23 00:35:44.789507: step: 1504/529, loss: 0.24156685173511505
2023-01-23 00:35:45.949713: step: 1508/529, loss: 0.14699365198612213
2023-01-23 00:35:47.088941: step: 1512/529, loss: 0.38158854842185974
2023-01-23 00:35:48.205399: step: 1516/529, loss: 0.09126892685890198
2023-01-23 00:35:49.326107: step: 1520/529, loss: 0.4601791501045227
2023-01-23 00:35:50.487254: step: 1524/529, loss: 0.12492237240076065
2023-01-23 00:35:51.607970: step: 1528/529, loss: 0.04337163269519806
2023-01-23 00:35:52.748451: step: 1532/529, loss: 0.20987573266029358
2023-01-23 00:35:53.891530: step: 1536/529, loss: 0.09402570873498917
2023-01-23 00:35:55.045064: step: 1540/529, loss: 0.033980369567871094
2023-01-23 00:35:56.178100: step: 1544/529, loss: 0.6974887847900391
2023-01-23 00:35:57.307910: step: 1548/529, loss: 0.35368672013282776
2023-01-23 00:35:58.439462: step: 1552/529, loss: 0.09562735259532928
2023-01-23 00:35:59.575831: step: 1556/529, loss: 0.42046844959259033
2023-01-23 00:36:00.733094: step: 1560/529, loss: 0.625869870185852
2023-01-23 00:36:01.870995: step: 1564/529, loss: 0.6839299201965332
2023-01-23 00:36:03.044027: step: 1568/529, loss: 0.2801129221916199
2023-01-23 00:36:04.186099: step: 1572/529, loss: 0.8438965082168579
2023-01-23 00:36:05.343092: step: 1576/529, loss: 0.12409190833568573
2023-01-23 00:36:06.486221: step: 1580/529, loss: 0.36157163977622986
2023-01-23 00:36:07.641981: step: 1584/529, loss: 0.0032471180893480778
2023-01-23 00:36:08.765708: step: 1588/529, loss: 0.0833933874964714
2023-01-23 00:36:09.916453: step: 1592/529, loss: 0.1490146666765213
2023-01-23 00:36:11.081487: step: 1596/529, loss: 0.2304130494594574
2023-01-23 00:36:12.226105: step: 1600/529, loss: 0.026635361835360527
2023-01-23 00:36:13.353001: step: 1604/529, loss: 0.11579003930091858
2023-01-23 00:36:14.484976: step: 1608/529, loss: 0.06304445117712021
2023-01-23 00:36:15.643135: step: 1612/529, loss: 0.9998999834060669
2023-01-23 00:36:16.777086: step: 1616/529, loss: 0.2079617977142334
2023-01-23 00:36:17.910646: step: 1620/529, loss: 0.3229769766330719
2023-01-23 00:36:19.042693: step: 1624/529, loss: 0.0373837985098362
2023-01-23 00:36:20.174420: step: 1628/529, loss: 0.056791115552186966
2023-01-23 00:36:21.309932: step: 1632/529, loss: 0.08234858512878418
2023-01-23 00:36:22.436267: step: 1636/529, loss: 0.22209934890270233
2023-01-23 00:36:23.586786: step: 1640/529, loss: 0.3499147295951843
2023-01-23 00:36:24.776182: step: 1644/529, loss: 0.018796682357788086
2023-01-23 00:36:25.897618: step: 1648/529, loss: 0.04752139747142792
2023-01-23 00:36:27.051473: step: 1652/529, loss: 0.3127335011959076
2023-01-23 00:36:28.221604: step: 1656/529, loss: 0.0968031957745552
2023-01-23 00:36:29.360606: step: 1660/529, loss: 0.08821725845336914
2023-01-23 00:36:30.477215: step: 1664/529, loss: 0.04978980869054794
2023-01-23 00:36:31.610328: step: 1668/529, loss: 0.42310333251953125
2023-01-23 00:36:32.757069: step: 1672/529, loss: 0.43186110258102417
2023-01-23 00:36:33.917760: step: 1676/529, loss: 0.10648288577795029
2023-01-23 00:36:35.048840: step: 1680/529, loss: 0.11094231903553009
2023-01-23 00:36:36.178107: step: 1684/529, loss: 0.05051689222455025
2023-01-23 00:36:37.319642: step: 1688/529, loss: 0.10724658519029617
2023-01-23 00:36:38.458490: step: 1692/529, loss: 0.6355093121528625
2023-01-23 00:36:39.585220: step: 1696/529, loss: 0.11709442734718323
2023-01-23 00:36:40.719688: step: 1700/529, loss: 0.08421077579259872
2023-01-23 00:36:41.834399: step: 1704/529, loss: 0.057763874530792236
2023-01-23 00:36:42.951333: step: 1708/529, loss: 0.17214146256446838
2023-01-23 00:36:44.086775: step: 1712/529, loss: 0.26311343908309937
2023-01-23 00:36:45.235381: step: 1716/529, loss: 0.5882684588432312
2023-01-23 00:36:46.387015: step: 1720/529, loss: 0.06975355744361877
2023-01-23 00:36:47.577556: step: 1724/529, loss: 0.2308824360370636
2023-01-23 00:36:48.720353: step: 1728/529, loss: 0.06496963649988174
2023-01-23 00:36:49.868085: step: 1732/529, loss: 0.25633737444877625
2023-01-23 00:36:51.008264: step: 1736/529, loss: 0.33822715282440186
2023-01-23 00:36:52.159914: step: 1740/529, loss: 0.2473660111427307
2023-01-23 00:36:53.303117: step: 1744/529, loss: 0.7095004320144653
2023-01-23 00:36:54.422889: step: 1748/529, loss: 0.18230445683002472
2023-01-23 00:36:55.560217: step: 1752/529, loss: 0.21284739673137665
2023-01-23 00:36:56.683008: step: 1756/529, loss: 0.8302550315856934
2023-01-23 00:36:57.813090: step: 1760/529, loss: 0.038268186151981354
2023-01-23 00:36:58.986380: step: 1764/529, loss: 0.05125870928168297
2023-01-23 00:37:00.132402: step: 1768/529, loss: 0.16092367470264435
2023-01-23 00:37:01.264544: step: 1772/529, loss: 0.08133144676685333
2023-01-23 00:37:02.402737: step: 1776/529, loss: 0.11688362061977386
2023-01-23 00:37:03.555253: step: 1780/529, loss: 0.45523911714553833
2023-01-23 00:37:04.699613: step: 1784/529, loss: 0.028124429285526276
2023-01-23 00:37:05.840763: step: 1788/529, loss: 0.06494168937206268
2023-01-23 00:37:06.952199: step: 1792/529, loss: 0.026015616953372955
2023-01-23 00:37:08.078870: step: 1796/529, loss: 0.09396862983703613
2023-01-23 00:37:09.222313: step: 1800/529, loss: 0.17881089448928833
2023-01-23 00:37:10.400505: step: 1804/529, loss: 0.04808454588055611
2023-01-23 00:37:11.548132: step: 1808/529, loss: 0.09634856879711151
2023-01-23 00:37:12.668705: step: 1812/529, loss: 0.03631029278039932
2023-01-23 00:37:13.808894: step: 1816/529, loss: 0.1206122413277626
2023-01-23 00:37:14.998984: step: 1820/529, loss: 0.24403706192970276
2023-01-23 00:37:16.137407: step: 1824/529, loss: 0.1272398978471756
2023-01-23 00:37:17.263151: step: 1828/529, loss: 0.08723344653844833
2023-01-23 00:37:18.388062: step: 1832/529, loss: 0.04036426544189453
2023-01-23 00:37:19.546924: step: 1836/529, loss: 0.04338674619793892
2023-01-23 00:37:20.687807: step: 1840/529, loss: 0.9547991752624512
2023-01-23 00:37:21.843245: step: 1844/529, loss: 0.06135311350226402
2023-01-23 00:37:22.988328: step: 1848/529, loss: 0.14369043707847595
2023-01-23 00:37:24.085373: step: 1852/529, loss: 0.015814971178770065
2023-01-23 00:37:25.228306: step: 1856/529, loss: 0.14163294434547424
2023-01-23 00:37:26.339203: step: 1860/529, loss: 0.020140409469604492
2023-01-23 00:37:27.469049: step: 1864/529, loss: 0.07844791561365128
2023-01-23 00:37:28.608365: step: 1868/529, loss: 0.10875293612480164
2023-01-23 00:37:29.729631: step: 1872/529, loss: 0.352674663066864
2023-01-23 00:37:30.846046: step: 1876/529, loss: 0.05489597097039223
2023-01-23 00:37:31.963975: step: 1880/529, loss: 0.19982747733592987
2023-01-23 00:37:33.109114: step: 1884/529, loss: 0.5023584961891174
2023-01-23 00:37:34.249816: step: 1888/529, loss: 0.1934628039598465
2023-01-23 00:37:35.387575: step: 1892/529, loss: 0.11241722106933594
2023-01-23 00:37:36.541524: step: 1896/529, loss: 0.12496557831764221
2023-01-23 00:37:37.680963: step: 1900/529, loss: 0.8799470663070679
2023-01-23 00:37:38.799343: step: 1904/529, loss: 0.14097614586353302
2023-01-23 00:37:39.948957: step: 1908/529, loss: 0.7329250574111938
2023-01-23 00:37:41.070336: step: 1912/529, loss: 0.04732117801904678
2023-01-23 00:37:42.214801: step: 1916/529, loss: 0.021816158667206764
2023-01-23 00:37:43.373910: step: 1920/529, loss: 0.08509254455566406
2023-01-23 00:37:44.524653: step: 1924/529, loss: 0.09246654808521271
2023-01-23 00:37:45.664220: step: 1928/529, loss: 0.159480482339859
2023-01-23 00:37:46.784351: step: 1932/529, loss: 0.8304230570793152
2023-01-23 00:37:47.921265: step: 1936/529, loss: 0.0987558364868164
2023-01-23 00:37:49.086466: step: 1940/529, loss: 0.480537474155426
2023-01-23 00:37:50.215702: step: 1944/529, loss: 0.05770282447338104
2023-01-23 00:37:51.357832: step: 1948/529, loss: 0.23431549966335297
2023-01-23 00:37:52.518611: step: 1952/529, loss: 0.08774594962596893
2023-01-23 00:37:53.659179: step: 1956/529, loss: 0.09121169149875641
2023-01-23 00:37:54.808317: step: 1960/529, loss: 0.38218921422958374
2023-01-23 00:37:55.963700: step: 1964/529, loss: 0.04716808721423149
2023-01-23 00:37:57.092152: step: 1968/529, loss: 0.11767492443323135
2023-01-23 00:37:58.249972: step: 1972/529, loss: 0.11477241665124893
2023-01-23 00:37:59.418340: step: 1976/529, loss: 1.535006046295166
2023-01-23 00:38:00.541997: step: 1980/529, loss: 0.07560023665428162
2023-01-23 00:38:01.722741: step: 1984/529, loss: 0.3149995803833008
2023-01-23 00:38:02.858902: step: 1988/529, loss: 0.6757254600524902
2023-01-23 00:38:03.999803: step: 1992/529, loss: 1.0960496664047241
2023-01-23 00:38:05.184366: step: 1996/529, loss: 0.13806819915771484
2023-01-23 00:38:06.336139: step: 2000/529, loss: 0.3999154269695282
2023-01-23 00:38:07.468780: step: 2004/529, loss: 0.05291027948260307
2023-01-23 00:38:08.618683: step: 2008/529, loss: 0.1192389503121376
2023-01-23 00:38:09.749985: step: 2012/529, loss: 0.2540108561515808
2023-01-23 00:38:10.887980: step: 2016/529, loss: 0.1288958042860031
2023-01-23 00:38:12.020691: step: 2020/529, loss: 0.04929985851049423
2023-01-23 00:38:13.141182: step: 2024/529, loss: 0.12469659000635147
2023-01-23 00:38:14.308512: step: 2028/529, loss: 1.9697210788726807
2023-01-23 00:38:15.454894: step: 2032/529, loss: 0.14989744126796722
2023-01-23 00:38:16.580824: step: 2036/529, loss: 0.11352329701185226
2023-01-23 00:38:17.749098: step: 2040/529, loss: 0.18717674911022186
2023-01-23 00:38:18.875508: step: 2044/529, loss: 0.023313332349061966
2023-01-23 00:38:20.058183: step: 2048/529, loss: 0.06607413291931152
2023-01-23 00:38:21.176063: step: 2052/529, loss: 0.4923926889896393
2023-01-23 00:38:22.335238: step: 2056/529, loss: 0.2689165771007538
2023-01-23 00:38:23.515165: step: 2060/529, loss: 0.1502152532339096
2023-01-23 00:38:24.648366: step: 2064/529, loss: 0.006889152340590954
2023-01-23 00:38:25.773503: step: 2068/529, loss: 0.6686629056930542
2023-01-23 00:38:26.944473: step: 2072/529, loss: 0.08644552528858185
2023-01-23 00:38:28.093508: step: 2076/529, loss: 0.0826151892542839
2023-01-23 00:38:29.238602: step: 2080/529, loss: 0.09907140582799911
2023-01-23 00:38:30.419822: step: 2084/529, loss: 0.10432948917150497
2023-01-23 00:38:31.553522: step: 2088/529, loss: 0.15374603867530823
2023-01-23 00:38:32.727521: step: 2092/529, loss: 0.04619045555591583
2023-01-23 00:38:33.859490: step: 2096/529, loss: 0.029952311888337135
2023-01-23 00:38:34.984758: step: 2100/529, loss: 0.29914793372154236
2023-01-23 00:38:36.104213: step: 2104/529, loss: 0.14015436172485352
2023-01-23 00:38:37.242500: step: 2108/529, loss: 0.0412413626909256
2023-01-23 00:38:38.392177: step: 2112/529, loss: 0.08781389892101288
2023-01-23 00:38:39.573540: step: 2116/529, loss: 0.06290626525878906
==================================================
Loss: 0.212
--------------------
Dev: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.5818181818181818, 'r': 0.5079365079365079, 'f1': 0.5423728813559321}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6427718040621266, 'r': 0.7163781624500666, 'f1': 0.6775818639798489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6065822784810126, 'r': 0.694090382387022, 'f1': 0.6473925965955147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.6301369863013698, 'r': 0.8518518518518519, 'f1': 0.7244094488188976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6956521739130435, 'r': 0.5079365079365079, 'f1': 0.5871559633027522}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:39:27.477432: step: 4/529, loss: 0.042563535273075104
2023-01-23 00:39:28.625650: step: 8/529, loss: 0.039869122207164764
2023-01-23 00:39:29.749652: step: 12/529, loss: 0.1457923948764801
2023-01-23 00:39:30.881602: step: 16/529, loss: 0.10531263798475266
2023-01-23 00:39:31.992003: step: 20/529, loss: 0.00659990357235074
2023-01-23 00:39:33.107264: step: 24/529, loss: 0.03553485870361328
2023-01-23 00:39:34.233113: step: 28/529, loss: 0.19160613417625427
2023-01-23 00:39:35.380069: step: 32/529, loss: 0.14029160141944885
2023-01-23 00:39:36.532762: step: 36/529, loss: 0.8193327188491821
2023-01-23 00:39:37.647206: step: 40/529, loss: 0.05508880689740181
2023-01-23 00:39:38.763867: step: 44/529, loss: 0.20330199599266052
2023-01-23 00:39:39.944968: step: 48/529, loss: 0.07096557319164276
2023-01-23 00:39:41.052893: step: 52/529, loss: 0.2691882252693176
2023-01-23 00:39:42.197809: step: 56/529, loss: 0.2167079895734787
2023-01-23 00:39:43.367373: step: 60/529, loss: 0.2393827736377716
2023-01-23 00:39:44.488612: step: 64/529, loss: 0.08929280936717987
2023-01-23 00:39:45.599222: step: 68/529, loss: 0.24706554412841797
2023-01-23 00:39:46.733330: step: 72/529, loss: 0.04640159755945206
2023-01-23 00:39:47.856674: step: 76/529, loss: 0.15074601769447327
2023-01-23 00:39:48.972946: step: 80/529, loss: 0.13661418855190277
2023-01-23 00:39:50.093819: step: 84/529, loss: 0.23108814656734467
2023-01-23 00:39:51.242634: step: 88/529, loss: 0.053687382489442825
2023-01-23 00:39:52.384149: step: 92/529, loss: 0.08737733960151672
2023-01-23 00:39:53.545299: step: 96/529, loss: 0.07151909172534943
2023-01-23 00:39:54.676059: step: 100/529, loss: 0.052175235003232956
2023-01-23 00:39:55.779392: step: 104/529, loss: 0.1434159278869629
2023-01-23 00:39:56.930854: step: 108/529, loss: 0.06303472816944122
2023-01-23 00:39:58.085365: step: 112/529, loss: 0.08998637646436691
2023-01-23 00:39:59.214148: step: 116/529, loss: 0.08417949825525284
2023-01-23 00:40:00.357708: step: 120/529, loss: 0.020761489868164062
2023-01-23 00:40:01.506353: step: 124/529, loss: 0.016847802326083183
2023-01-23 00:40:02.634323: step: 128/529, loss: 0.07435612380504608
2023-01-23 00:40:03.792638: step: 132/529, loss: 0.28077831864356995
2023-01-23 00:40:04.920539: step: 136/529, loss: 1.048264503479004
2023-01-23 00:40:06.037508: step: 140/529, loss: 0.06646700203418732
2023-01-23 00:40:07.175891: step: 144/529, loss: 0.07954072952270508
2023-01-23 00:40:08.341435: step: 148/529, loss: 0.11353912204504013
2023-01-23 00:40:09.478017: step: 152/529, loss: 0.1407584249973297
2023-01-23 00:40:10.626765: step: 156/529, loss: 0.0325779914855957
2023-01-23 00:40:11.742487: step: 160/529, loss: 0.1824987530708313
2023-01-23 00:40:12.915218: step: 164/529, loss: 0.027321243658661842
2023-01-23 00:40:14.049492: step: 168/529, loss: 0.13722367584705353
2023-01-23 00:40:15.210700: step: 172/529, loss: 0.047692012041807175
2023-01-23 00:40:16.351409: step: 176/529, loss: 0.24363203346729279
2023-01-23 00:40:17.489670: step: 180/529, loss: 0.01588892936706543
2023-01-23 00:40:18.627887: step: 184/529, loss: 0.12598839402198792
2023-01-23 00:40:19.780374: step: 188/529, loss: 0.21481962502002716
2023-01-23 00:40:20.938069: step: 192/529, loss: 0.7324357032775879
2023-01-23 00:40:22.077329: step: 196/529, loss: 0.07340145111083984
2023-01-23 00:40:23.218840: step: 200/529, loss: 0.15468549728393555
2023-01-23 00:40:24.386068: step: 204/529, loss: 0.025687791407108307
2023-01-23 00:40:25.528152: step: 208/529, loss: 0.058331869542598724
2023-01-23 00:40:26.664003: step: 212/529, loss: 0.1435280740261078
2023-01-23 00:40:27.814855: step: 216/529, loss: 0.15259627997875214
2023-01-23 00:40:28.930398: step: 220/529, loss: 0.34549087285995483
2023-01-23 00:40:30.065442: step: 224/529, loss: 0.11227608472108841
2023-01-23 00:40:31.203665: step: 228/529, loss: 0.14857101440429688
2023-01-23 00:40:32.340180: step: 232/529, loss: 0.008654308505356312
2023-01-23 00:40:33.441209: step: 236/529, loss: 0.12001033127307892
2023-01-23 00:40:34.566090: step: 240/529, loss: 0.03143613412976265
2023-01-23 00:40:35.692706: step: 244/529, loss: 0.40172329545021057
2023-01-23 00:40:36.927900: step: 248/529, loss: 0.14287033677101135
2023-01-23 00:40:38.058542: step: 252/529, loss: 0.02498483844101429
2023-01-23 00:40:39.219806: step: 256/529, loss: 0.11949684470891953
2023-01-23 00:40:40.332843: step: 260/529, loss: 0.1006307601928711
2023-01-23 00:40:41.473914: step: 264/529, loss: 0.041253700852394104
2023-01-23 00:40:42.609015: step: 268/529, loss: 0.041181087493896484
2023-01-23 00:40:43.795091: step: 272/529, loss: 0.04162292554974556
2023-01-23 00:40:44.911640: step: 276/529, loss: 0.04879941791296005
2023-01-23 00:40:46.046603: step: 280/529, loss: 0.038159750401973724
2023-01-23 00:40:47.199817: step: 284/529, loss: 0.060675811022520065
2023-01-23 00:40:48.343051: step: 288/529, loss: 0.18230067193508148
2023-01-23 00:40:49.495279: step: 292/529, loss: 0.1592148244380951
2023-01-23 00:40:50.615227: step: 296/529, loss: 0.020122099667787552
2023-01-23 00:40:51.752045: step: 300/529, loss: 0.06520567089319229
2023-01-23 00:40:52.864823: step: 304/529, loss: 0.06264705955982208
2023-01-23 00:40:53.991712: step: 308/529, loss: 0.1522393673658371
2023-01-23 00:40:55.145579: step: 312/529, loss: 0.07093029469251633
2023-01-23 00:40:56.288997: step: 316/529, loss: 0.08137550204992294
2023-01-23 00:40:57.433646: step: 320/529, loss: 0.07664747536182404
2023-01-23 00:40:58.573817: step: 324/529, loss: 0.03860750049352646
2023-01-23 00:40:59.745824: step: 328/529, loss: 0.41961613297462463
2023-01-23 00:41:00.876444: step: 332/529, loss: 0.02822551690042019
2023-01-23 00:41:02.022571: step: 336/529, loss: 0.2965034544467926
2023-01-23 00:41:03.147217: step: 340/529, loss: 0.09459743648767471
2023-01-23 00:41:04.285305: step: 344/529, loss: 0.08964033424854279
2023-01-23 00:41:05.423907: step: 348/529, loss: 0.17884483933448792
2023-01-23 00:41:06.573621: step: 352/529, loss: 0.1376895010471344
2023-01-23 00:41:07.740858: step: 356/529, loss: 0.03124542161822319
2023-01-23 00:41:08.894432: step: 360/529, loss: 0.05669746547937393
2023-01-23 00:41:10.039326: step: 364/529, loss: 0.13595418632030487
2023-01-23 00:41:11.215768: step: 368/529, loss: 0.08331713825464249
2023-01-23 00:41:12.365852: step: 372/529, loss: 0.06101689487695694
2023-01-23 00:41:13.519332: step: 376/529, loss: 0.06221456825733185
2023-01-23 00:41:14.652270: step: 380/529, loss: 0.14734864234924316
2023-01-23 00:41:15.801151: step: 384/529, loss: 0.16810818016529083
2023-01-23 00:41:16.975765: step: 388/529, loss: 0.12999382615089417
2023-01-23 00:41:18.137818: step: 392/529, loss: 0.007696962915360928
2023-01-23 00:41:19.291763: step: 396/529, loss: 0.02716522291302681
2023-01-23 00:41:20.453927: step: 400/529, loss: 0.13542616367340088
2023-01-23 00:41:21.575829: step: 404/529, loss: 0.057915713638067245
2023-01-23 00:41:22.727125: step: 408/529, loss: 0.17980174720287323
2023-01-23 00:41:23.874942: step: 412/529, loss: 0.02211456373333931
2023-01-23 00:41:25.037270: step: 416/529, loss: 0.05041904374957085
2023-01-23 00:41:26.192596: step: 420/529, loss: 0.12386885285377502
2023-01-23 00:41:27.323223: step: 424/529, loss: 0.09354014694690704
2023-01-23 00:41:28.463894: step: 428/529, loss: 0.03186183050274849
2023-01-23 00:41:29.581691: step: 432/529, loss: 0.1892780363559723
2023-01-23 00:41:30.764318: step: 436/529, loss: 0.03945617750287056
2023-01-23 00:41:31.891350: step: 440/529, loss: 0.21628212928771973
2023-01-23 00:41:33.024622: step: 444/529, loss: 0.024228597059845924
2023-01-23 00:41:34.158137: step: 448/529, loss: 0.19096116721630096
2023-01-23 00:41:35.315573: step: 452/529, loss: 0.05030279606580734
2023-01-23 00:41:36.480059: step: 456/529, loss: 0.035592157393693924
2023-01-23 00:41:37.613055: step: 460/529, loss: 0.06591042876243591
2023-01-23 00:41:38.741346: step: 464/529, loss: 0.08670230209827423
2023-01-23 00:41:39.896274: step: 468/529, loss: 0.01954355277121067
2023-01-23 00:41:41.004666: step: 472/529, loss: 0.25123530626296997
2023-01-23 00:41:42.163171: step: 476/529, loss: 0.026798725128173828
2023-01-23 00:41:43.317455: step: 480/529, loss: 0.10264835506677628
2023-01-23 00:41:44.443679: step: 484/529, loss: 0.23255595564842224
2023-01-23 00:41:45.582749: step: 488/529, loss: 0.05419750139117241
2023-01-23 00:41:46.730952: step: 492/529, loss: 0.09384670853614807
2023-01-23 00:41:47.872570: step: 496/529, loss: 0.07152791321277618
2023-01-23 00:41:49.009874: step: 500/529, loss: 0.027454353868961334
2023-01-23 00:41:50.173712: step: 504/529, loss: 0.0911775603890419
2023-01-23 00:41:51.323840: step: 508/529, loss: 0.11702613532543182
2023-01-23 00:41:52.492583: step: 512/529, loss: 0.16320085525512695
2023-01-23 00:41:53.601235: step: 516/529, loss: 0.3054993152618408
2023-01-23 00:41:54.735666: step: 520/529, loss: 0.09896469116210938
2023-01-23 00:41:55.889899: step: 524/529, loss: 0.09951867908239365
2023-01-23 00:41:57.036548: step: 528/529, loss: 0.284894198179245
2023-01-23 00:41:58.154289: step: 532/529, loss: 0.16384926438331604
2023-01-23 00:41:59.297872: step: 536/529, loss: 0.017270183190703392
2023-01-23 00:42:00.432081: step: 540/529, loss: 0.15269556641578674
2023-01-23 00:42:01.599637: step: 544/529, loss: 0.02434062771499157
2023-01-23 00:42:02.739244: step: 548/529, loss: 0.07973742485046387
2023-01-23 00:42:03.889867: step: 552/529, loss: 0.07940101623535156
2023-01-23 00:42:05.050624: step: 556/529, loss: 0.29565659165382385
2023-01-23 00:42:06.235873: step: 560/529, loss: 0.25998440384864807
2023-01-23 00:42:07.396591: step: 564/529, loss: 0.012747240252792835
2023-01-23 00:42:08.540165: step: 568/529, loss: 0.1795019656419754
2023-01-23 00:42:09.673366: step: 572/529, loss: 0.05109043046832085
2023-01-23 00:42:10.797354: step: 576/529, loss: 0.09165702015161514
2023-01-23 00:42:11.938606: step: 580/529, loss: 0.25682029128074646
2023-01-23 00:42:13.096846: step: 584/529, loss: 0.031218720600008965
2023-01-23 00:42:14.229914: step: 588/529, loss: 0.18826337158679962
2023-01-23 00:42:15.348830: step: 592/529, loss: 0.13673192262649536
2023-01-23 00:42:16.493749: step: 596/529, loss: 0.09707927703857422
2023-01-23 00:42:17.648247: step: 600/529, loss: 0.09904041141271591
2023-01-23 00:42:18.762873: step: 604/529, loss: 0.10942697525024414
2023-01-23 00:42:19.895926: step: 608/529, loss: 0.7978367805480957
2023-01-23 00:42:21.052990: step: 612/529, loss: 0.2259882688522339
2023-01-23 00:42:22.211020: step: 616/529, loss: 0.06765404343605042
2023-01-23 00:42:23.355424: step: 620/529, loss: 0.4739961624145508
2023-01-23 00:42:24.508371: step: 624/529, loss: 0.11198749393224716
2023-01-23 00:42:25.658235: step: 628/529, loss: 0.3723900318145752
2023-01-23 00:42:26.791418: step: 632/529, loss: 0.02120819129049778
2023-01-23 00:42:27.935910: step: 636/529, loss: 0.011112213134765625
2023-01-23 00:42:29.089781: step: 640/529, loss: 0.6732972860336304
2023-01-23 00:42:30.245442: step: 644/529, loss: 0.05375304073095322
2023-01-23 00:42:31.369343: step: 648/529, loss: 0.05211582034826279
2023-01-23 00:42:32.521385: step: 652/529, loss: 0.10294894874095917
2023-01-23 00:42:33.674286: step: 656/529, loss: 0.06932105869054794
2023-01-23 00:42:34.789497: step: 660/529, loss: 1.161803960800171
2023-01-23 00:42:35.914215: step: 664/529, loss: 0.11703729629516602
2023-01-23 00:42:37.055288: step: 668/529, loss: 0.19213466346263885
2023-01-23 00:42:38.193881: step: 672/529, loss: 0.19419851899147034
2023-01-23 00:42:39.328911: step: 676/529, loss: 0.05112151801586151
2023-01-23 00:42:40.474912: step: 680/529, loss: 0.11244416236877441
2023-01-23 00:42:41.619639: step: 684/529, loss: 0.15277761220932007
2023-01-23 00:42:42.757164: step: 688/529, loss: 0.07526111602783203
2023-01-23 00:42:43.908764: step: 692/529, loss: 0.23086854815483093
2023-01-23 00:42:45.057748: step: 696/529, loss: 0.14803822338581085
2023-01-23 00:42:46.209498: step: 700/529, loss: 0.10436268150806427
2023-01-23 00:42:47.369731: step: 704/529, loss: 0.028618240728974342
2023-01-23 00:42:48.511821: step: 708/529, loss: 0.10217809677124023
2023-01-23 00:42:49.636866: step: 712/529, loss: 0.08290252834558487
2023-01-23 00:42:50.776016: step: 716/529, loss: 0.21745462715625763
2023-01-23 00:42:51.915026: step: 720/529, loss: 0.34703075885772705
2023-01-23 00:42:53.050072: step: 724/529, loss: 0.14654918015003204
2023-01-23 00:42:54.194682: step: 728/529, loss: 0.21568042039871216
2023-01-23 00:42:55.291871: step: 732/529, loss: 0.08602862805128098
2023-01-23 00:42:56.434168: step: 736/529, loss: 0.040395356714725494
2023-01-23 00:42:57.603660: step: 740/529, loss: 0.09341306984424591
2023-01-23 00:42:58.731117: step: 744/529, loss: 0.06264495849609375
2023-01-23 00:42:59.868949: step: 748/529, loss: 0.1596328765153885
2023-01-23 00:43:00.986261: step: 752/529, loss: 0.17639192938804626
2023-01-23 00:43:02.139895: step: 756/529, loss: 0.533918559551239
2023-01-23 00:43:03.272217: step: 760/529, loss: 0.06819219887256622
2023-01-23 00:43:04.407966: step: 764/529, loss: 0.0642085075378418
2023-01-23 00:43:05.540767: step: 768/529, loss: 0.031195450574159622
2023-01-23 00:43:06.683408: step: 772/529, loss: 0.08208828419446945
2023-01-23 00:43:07.850176: step: 776/529, loss: 0.08131522685289383
2023-01-23 00:43:09.021948: step: 780/529, loss: 0.052170418202877045
2023-01-23 00:43:10.190719: step: 784/529, loss: 0.18491744995117188
2023-01-23 00:43:11.385281: step: 788/529, loss: 0.07410116493701935
2023-01-23 00:43:12.536476: step: 792/529, loss: 0.09056082367897034
2023-01-23 00:43:13.697044: step: 796/529, loss: 0.2675556242465973
2023-01-23 00:43:14.824346: step: 800/529, loss: 0.4297499656677246
2023-01-23 00:43:15.944418: step: 804/529, loss: 0.12766046822071075
2023-01-23 00:43:17.082582: step: 808/529, loss: 0.13021984696388245
2023-01-23 00:43:18.228030: step: 812/529, loss: 0.7451604604721069
2023-01-23 00:43:19.385192: step: 816/529, loss: 0.15032804012298584
2023-01-23 00:43:20.544370: step: 820/529, loss: 0.0913359671831131
2023-01-23 00:43:21.676898: step: 824/529, loss: 0.0726165845990181
2023-01-23 00:43:22.836454: step: 828/529, loss: 0.016353178769350052
2023-01-23 00:43:23.998000: step: 832/529, loss: 0.14222213625907898
2023-01-23 00:43:25.127144: step: 836/529, loss: 0.060122109949588776
2023-01-23 00:43:26.255482: step: 840/529, loss: 0.09133853763341904
2023-01-23 00:43:27.391807: step: 844/529, loss: 0.08547191321849823
2023-01-23 00:43:28.591649: step: 848/529, loss: 0.5536893010139465
2023-01-23 00:43:29.721343: step: 852/529, loss: 0.042575884610414505
2023-01-23 00:43:30.911302: step: 856/529, loss: 0.03320198133587837
2023-01-23 00:43:32.044409: step: 860/529, loss: 0.6481418609619141
2023-01-23 00:43:33.158868: step: 864/529, loss: 0.1351698935031891
2023-01-23 00:43:34.267914: step: 868/529, loss: 0.0561734214425087
2023-01-23 00:43:35.408832: step: 872/529, loss: 0.44409817457199097
2023-01-23 00:43:36.540992: step: 876/529, loss: 0.05455455929040909
2023-01-23 00:43:37.716531: step: 880/529, loss: 0.41209110617637634
2023-01-23 00:43:38.879507: step: 884/529, loss: 0.18684768676757812
2023-01-23 00:43:40.032532: step: 888/529, loss: 0.043112851679325104
2023-01-23 00:43:41.187964: step: 892/529, loss: 0.0607968345284462
2023-01-23 00:43:42.344693: step: 896/529, loss: 0.3999425172805786
2023-01-23 00:43:43.488458: step: 900/529, loss: 0.11191777884960175
2023-01-23 00:43:44.696577: step: 904/529, loss: 0.13103695213794708
2023-01-23 00:43:45.849537: step: 908/529, loss: 0.051504041999578476
2023-01-23 00:43:46.967036: step: 912/529, loss: 0.016675090417265892
2023-01-23 00:43:48.119500: step: 916/529, loss: 0.039655208587646484
2023-01-23 00:43:49.264349: step: 920/529, loss: 0.3030610978603363
2023-01-23 00:43:50.402171: step: 924/529, loss: 0.8533024787902832
2023-01-23 00:43:51.517285: step: 928/529, loss: 0.0611872673034668
2023-01-23 00:43:52.665398: step: 932/529, loss: 0.16871222853660583
2023-01-23 00:43:53.803521: step: 936/529, loss: 0.170294851064682
2023-01-23 00:43:54.951396: step: 940/529, loss: 0.0599120631814003
2023-01-23 00:43:56.088467: step: 944/529, loss: 0.015521145425736904
2023-01-23 00:43:57.224406: step: 948/529, loss: 0.11492423713207245
2023-01-23 00:43:58.338376: step: 952/529, loss: 0.09835801273584366
2023-01-23 00:43:59.488387: step: 956/529, loss: 0.03549613803625107
2023-01-23 00:44:00.637870: step: 960/529, loss: 0.026025010272860527
2023-01-23 00:44:01.778192: step: 964/529, loss: 0.03955962881445885
2023-01-23 00:44:02.921796: step: 968/529, loss: 0.283291220664978
2023-01-23 00:44:04.054661: step: 972/529, loss: 0.06722621619701385
2023-01-23 00:44:05.189893: step: 976/529, loss: 0.13107609748840332
2023-01-23 00:44:06.329391: step: 980/529, loss: 0.2288549542427063
2023-01-23 00:44:07.480115: step: 984/529, loss: 0.07444553822278976
2023-01-23 00:44:08.612799: step: 988/529, loss: 0.07134180516004562
2023-01-23 00:44:09.749352: step: 992/529, loss: 0.8081989884376526
2023-01-23 00:44:10.879334: step: 996/529, loss: 0.07223998010158539
2023-01-23 00:44:12.029582: step: 1000/529, loss: 0.015805674716830254
2023-01-23 00:44:13.152064: step: 1004/529, loss: 0.13688930869102478
2023-01-23 00:44:14.302999: step: 1008/529, loss: 1.0747992992401123
2023-01-23 00:44:15.439181: step: 1012/529, loss: 0.03820457309484482
2023-01-23 00:44:16.590525: step: 1016/529, loss: 0.114777572453022
2023-01-23 00:44:17.755316: step: 1020/529, loss: 0.04070005193352699
2023-01-23 00:44:18.913284: step: 1024/529, loss: 0.12567424774169922
2023-01-23 00:44:20.058325: step: 1028/529, loss: 0.04873304441571236
2023-01-23 00:44:21.187361: step: 1032/529, loss: 0.09399242699146271
2023-01-23 00:44:22.340872: step: 1036/529, loss: 0.04477892071008682
2023-01-23 00:44:23.488180: step: 1040/529, loss: 0.2507326006889343
2023-01-23 00:44:24.596667: step: 1044/529, loss: 0.05149943754076958
2023-01-23 00:44:25.724211: step: 1048/529, loss: 0.10164327919483185
2023-01-23 00:44:26.861118: step: 1052/529, loss: 0.03725767135620117
2023-01-23 00:44:28.015570: step: 1056/529, loss: 0.12715959548950195
2023-01-23 00:44:29.144717: step: 1060/529, loss: 0.1448778212070465
2023-01-23 00:44:30.287996: step: 1064/529, loss: 0.03995705023407936
2023-01-23 00:44:31.421646: step: 1068/529, loss: 0.8035299777984619
2023-01-23 00:44:32.555817: step: 1072/529, loss: 0.07350502163171768
2023-01-23 00:44:33.704824: step: 1076/529, loss: 0.10941322147846222
2023-01-23 00:44:34.851448: step: 1080/529, loss: 0.07037315517663956
2023-01-23 00:44:36.000825: step: 1084/529, loss: 0.31369680166244507
2023-01-23 00:44:37.121939: step: 1088/529, loss: 0.04736471176147461
2023-01-23 00:44:38.250851: step: 1092/529, loss: 0.02118206024169922
2023-01-23 00:44:39.384037: step: 1096/529, loss: 0.22719049453735352
2023-01-23 00:44:40.530500: step: 1100/529, loss: 0.03657474368810654
2023-01-23 00:44:41.664004: step: 1104/529, loss: 0.04487466812133789
2023-01-23 00:44:42.791150: step: 1108/529, loss: 0.035875797271728516
2023-01-23 00:44:43.933859: step: 1112/529, loss: 0.2374078780412674
2023-01-23 00:44:45.090644: step: 1116/529, loss: 0.10019969940185547
2023-01-23 00:44:46.212605: step: 1120/529, loss: 0.025711774826049805
2023-01-23 00:44:47.363327: step: 1124/529, loss: 0.3841056525707245
2023-01-23 00:44:48.510293: step: 1128/529, loss: 0.10552720725536346
2023-01-23 00:44:49.662388: step: 1132/529, loss: 0.031164171174168587
2023-01-23 00:44:50.811048: step: 1136/529, loss: 0.11592216789722443
2023-01-23 00:44:51.929753: step: 1140/529, loss: 0.036431025713682175
2023-01-23 00:44:53.063043: step: 1144/529, loss: 0.12117863446474075
2023-01-23 00:44:54.204596: step: 1148/529, loss: 0.08418798446655273
2023-01-23 00:44:55.363052: step: 1152/529, loss: 0.0654185563325882
2023-01-23 00:44:56.518758: step: 1156/529, loss: 0.17068414390087128
2023-01-23 00:44:57.696622: step: 1160/529, loss: 0.025050830096006393
2023-01-23 00:44:58.829630: step: 1164/529, loss: 0.01633739471435547
2023-01-23 00:44:59.981977: step: 1168/529, loss: 0.13830961287021637
2023-01-23 00:45:01.121286: step: 1172/529, loss: 0.09134463965892792
2023-01-23 00:45:02.254354: step: 1176/529, loss: 0.05947933346033096
2023-01-23 00:45:03.415428: step: 1180/529, loss: 0.3574865460395813
2023-01-23 00:45:04.530051: step: 1184/529, loss: 0.07889652997255325
2023-01-23 00:45:05.644043: step: 1188/529, loss: 0.06050758436322212
2023-01-23 00:45:06.769803: step: 1192/529, loss: 0.03741293027997017
2023-01-23 00:45:07.867054: step: 1196/529, loss: 0.3063947856426239
2023-01-23 00:45:09.028266: step: 1200/529, loss: 0.17077618837356567
2023-01-23 00:45:10.182937: step: 1204/529, loss: 0.30345994234085083
2023-01-23 00:45:11.310237: step: 1208/529, loss: 0.4140658378601074
2023-01-23 00:45:12.440391: step: 1212/529, loss: 0.1676034927368164
2023-01-23 00:45:13.593960: step: 1216/529, loss: 0.49675828218460083
2023-01-23 00:45:14.731024: step: 1220/529, loss: 0.14764443039894104
2023-01-23 00:45:15.854055: step: 1224/529, loss: 0.02834343910217285
2023-01-23 00:45:16.975135: step: 1228/529, loss: 0.14538101851940155
2023-01-23 00:45:18.119325: step: 1232/529, loss: 0.6591930985450745
2023-01-23 00:45:19.247219: step: 1236/529, loss: 0.13059931993484497
2023-01-23 00:45:20.386309: step: 1240/529, loss: 0.11616416275501251
2023-01-23 00:45:21.508811: step: 1244/529, loss: 0.11457046866416931
2023-01-23 00:45:22.644274: step: 1248/529, loss: 1.0732479095458984
2023-01-23 00:45:23.763623: step: 1252/529, loss: 0.018082572147250175
2023-01-23 00:45:24.904059: step: 1256/529, loss: 0.054738424718379974
2023-01-23 00:45:26.039071: step: 1260/529, loss: 0.06846165657043457
2023-01-23 00:45:27.164847: step: 1264/529, loss: 0.027254248037934303
2023-01-23 00:45:28.325274: step: 1268/529, loss: 0.11909093707799911
2023-01-23 00:45:29.459355: step: 1272/529, loss: 1.4714410305023193
2023-01-23 00:45:30.581255: step: 1276/529, loss: 0.06743469834327698
2023-01-23 00:45:31.712872: step: 1280/529, loss: 0.08549775928258896
2023-01-23 00:45:32.857302: step: 1284/529, loss: 0.13805027306079865
2023-01-23 00:45:34.047332: step: 1288/529, loss: 0.09634530544281006
2023-01-23 00:45:35.219766: step: 1292/529, loss: 0.08727006614208221
2023-01-23 00:45:36.356839: step: 1296/529, loss: 0.10100764781236649
2023-01-23 00:45:37.510576: step: 1300/529, loss: 0.07968340069055557
2023-01-23 00:45:38.637643: step: 1304/529, loss: 0.0658191666007042
2023-01-23 00:45:39.768547: step: 1308/529, loss: 0.11240248382091522
2023-01-23 00:45:40.913208: step: 1312/529, loss: 0.150920107960701
2023-01-23 00:45:42.081984: step: 1316/529, loss: 0.015492726117372513
2023-01-23 00:45:43.240517: step: 1320/529, loss: 0.12983761727809906
2023-01-23 00:45:44.389985: step: 1324/529, loss: 0.12339344620704651
2023-01-23 00:45:45.573568: step: 1328/529, loss: 1.1393409967422485
2023-01-23 00:45:46.714642: step: 1332/529, loss: 0.26907700300216675
2023-01-23 00:45:47.851095: step: 1336/529, loss: 0.27794188261032104
2023-01-23 00:45:49.008414: step: 1340/529, loss: 0.0393255241215229
2023-01-23 00:45:50.128051: step: 1344/529, loss: 0.08656424283981323
2023-01-23 00:45:51.291047: step: 1348/529, loss: 0.015587425790727139
2023-01-23 00:45:52.406972: step: 1352/529, loss: 0.1288565695285797
2023-01-23 00:45:53.550090: step: 1356/529, loss: 0.02566203847527504
2023-01-23 00:45:54.693629: step: 1360/529, loss: 0.3174566328525543
2023-01-23 00:45:55.830573: step: 1364/529, loss: 0.12984704971313477
2023-01-23 00:45:56.981195: step: 1368/529, loss: 0.11874476075172424
2023-01-23 00:45:58.105231: step: 1372/529, loss: 0.0717153549194336
2023-01-23 00:45:59.224376: step: 1376/529, loss: 0.11055093258619308
2023-01-23 00:46:00.338051: step: 1380/529, loss: 0.16246142983436584
2023-01-23 00:46:01.504523: step: 1384/529, loss: 0.05267667770385742
2023-01-23 00:46:02.687607: step: 1388/529, loss: 0.3214760720729828
2023-01-23 00:46:03.823272: step: 1392/529, loss: 0.0080725671723485
2023-01-23 00:46:04.987120: step: 1396/529, loss: 0.16526928544044495
2023-01-23 00:46:06.124936: step: 1400/529, loss: 0.17696905136108398
2023-01-23 00:46:07.259791: step: 1404/529, loss: 0.1043233871459961
2023-01-23 00:46:08.399137: step: 1408/529, loss: 0.34566959738731384
2023-01-23 00:46:09.599072: step: 1412/529, loss: 0.15531301498413086
2023-01-23 00:46:10.743872: step: 1416/529, loss: 0.12357378005981445
2023-01-23 00:46:11.896099: step: 1420/529, loss: 0.1280101239681244
2023-01-23 00:46:13.085139: step: 1424/529, loss: 0.07814846187829971
2023-01-23 00:46:14.238171: step: 1428/529, loss: 0.23037277162075043
2023-01-23 00:46:15.410536: step: 1432/529, loss: 0.08404131233692169
2023-01-23 00:46:16.555652: step: 1436/529, loss: 1.2264775037765503
2023-01-23 00:46:17.708515: step: 1440/529, loss: 0.1733301281929016
2023-01-23 00:46:18.866482: step: 1444/529, loss: 0.4530996084213257
2023-01-23 00:46:20.079345: step: 1448/529, loss: 0.15931062400341034
2023-01-23 00:46:21.205897: step: 1452/529, loss: 0.03198566287755966
2023-01-23 00:46:22.335040: step: 1456/529, loss: 0.05705156549811363
2023-01-23 00:46:23.455293: step: 1460/529, loss: 0.13826751708984375
2023-01-23 00:46:24.576971: step: 1464/529, loss: 0.07437744736671448
2023-01-23 00:46:25.694760: step: 1468/529, loss: 0.09493550658226013
2023-01-23 00:46:26.833321: step: 1472/529, loss: 0.1000904068350792
2023-01-23 00:46:27.961345: step: 1476/529, loss: 0.013208961114287376
2023-01-23 00:46:29.090645: step: 1480/529, loss: 0.045256901532411575
2023-01-23 00:46:30.236607: step: 1484/529, loss: 0.14116841554641724
2023-01-23 00:46:31.363659: step: 1488/529, loss: 0.055004313588142395
2023-01-23 00:46:32.497606: step: 1492/529, loss: 0.12032108008861542
2023-01-23 00:46:33.617016: step: 1496/529, loss: 0.11526477336883545
2023-01-23 00:46:34.737342: step: 1500/529, loss: 0.10058292746543884
2023-01-23 00:46:35.879927: step: 1504/529, loss: 0.14667540788650513
2023-01-23 00:46:37.006438: step: 1508/529, loss: 0.09236583858728409
2023-01-23 00:46:38.143383: step: 1512/529, loss: 0.13801270723342896
2023-01-23 00:46:39.296265: step: 1516/529, loss: 0.13479165732860565
2023-01-23 00:46:40.436647: step: 1520/529, loss: 0.7682908177375793
2023-01-23 00:46:41.581127: step: 1524/529, loss: 0.14104799926280975
2023-01-23 00:46:42.703702: step: 1528/529, loss: 0.22073164582252502
2023-01-23 00:46:43.827168: step: 1532/529, loss: 0.06504352390766144
2023-01-23 00:46:44.944878: step: 1536/529, loss: 0.10310936719179153
2023-01-23 00:46:46.083464: step: 1540/529, loss: 0.07471437007188797
2023-01-23 00:46:47.204215: step: 1544/529, loss: 0.04968462139368057
2023-01-23 00:46:48.352564: step: 1548/529, loss: 0.10697784274816513
2023-01-23 00:46:49.499110: step: 1552/529, loss: 0.10752282291650772
2023-01-23 00:46:50.614240: step: 1556/529, loss: 0.08000221103429794
2023-01-23 00:46:51.753511: step: 1560/529, loss: 0.12828406691551208
2023-01-23 00:46:52.895923: step: 1564/529, loss: 0.08738312870264053
2023-01-23 00:46:54.022852: step: 1568/529, loss: 0.643318772315979
2023-01-23 00:46:55.146299: step: 1572/529, loss: 0.10045900195837021
2023-01-23 00:46:56.298483: step: 1576/529, loss: 0.06383457034826279
2023-01-23 00:46:57.425465: step: 1580/529, loss: 0.0026175023522228003
2023-01-23 00:46:58.554983: step: 1584/529, loss: 0.14141488075256348
2023-01-23 00:46:59.714904: step: 1588/529, loss: 0.1619626134634018
2023-01-23 00:47:00.863696: step: 1592/529, loss: 0.08035793155431747
2023-01-23 00:47:01.991791: step: 1596/529, loss: 0.1018514633178711
2023-01-23 00:47:03.130969: step: 1600/529, loss: 0.05981726944446564
2023-01-23 00:47:04.277602: step: 1604/529, loss: 0.08651790767908096
2023-01-23 00:47:05.410045: step: 1608/529, loss: 0.08780994266271591
2023-01-23 00:47:06.568155: step: 1612/529, loss: 0.5993364453315735
2023-01-23 00:47:07.698142: step: 1616/529, loss: 0.12241001427173615
2023-01-23 00:47:08.854962: step: 1620/529, loss: 0.08432440459728241
2023-01-23 00:47:09.991533: step: 1624/529, loss: 0.19328823685646057
2023-01-23 00:47:11.133610: step: 1628/529, loss: 0.06647606194019318
2023-01-23 00:47:12.293341: step: 1632/529, loss: 0.27084845304489136
2023-01-23 00:47:13.418784: step: 1636/529, loss: 0.38451796770095825
2023-01-23 00:47:14.601660: step: 1640/529, loss: 0.9823002815246582
2023-01-23 00:47:15.737246: step: 1644/529, loss: 0.10056290775537491
2023-01-23 00:47:16.903467: step: 1648/529, loss: 0.025450706481933594
2023-01-23 00:47:18.059026: step: 1652/529, loss: 0.06078185886144638
2023-01-23 00:47:19.238784: step: 1656/529, loss: 0.34959831833839417
2023-01-23 00:47:20.356227: step: 1660/529, loss: 0.06246213614940643
2023-01-23 00:47:21.510799: step: 1664/529, loss: 0.10400734096765518
2023-01-23 00:47:22.643720: step: 1668/529, loss: 0.14536552131175995
2023-01-23 00:47:23.811393: step: 1672/529, loss: 0.2501552402973175
2023-01-23 00:47:24.958389: step: 1676/529, loss: 0.02607426606118679
2023-01-23 00:47:26.095458: step: 1680/529, loss: 0.11617942154407501
2023-01-23 00:47:27.240319: step: 1684/529, loss: 0.043949078768491745
2023-01-23 00:47:28.409772: step: 1688/529, loss: 0.020086385309696198
2023-01-23 00:47:29.543802: step: 1692/529, loss: 0.15174122154712677
2023-01-23 00:47:30.717350: step: 1696/529, loss: 0.08995270729064941
2023-01-23 00:47:31.867717: step: 1700/529, loss: 0.12455320358276367
2023-01-23 00:47:33.026140: step: 1704/529, loss: 0.023541593924164772
2023-01-23 00:47:34.184190: step: 1708/529, loss: 0.02675476111471653
2023-01-23 00:47:35.306279: step: 1712/529, loss: 0.0025634765625
2023-01-23 00:47:36.448530: step: 1716/529, loss: 0.14679060876369476
2023-01-23 00:47:37.586881: step: 1720/529, loss: 0.1373869925737381
2023-01-23 00:47:38.719590: step: 1724/529, loss: 0.09653063118457794
2023-01-23 00:47:39.871594: step: 1728/529, loss: 0.23379340767860413
2023-01-23 00:47:41.000671: step: 1732/529, loss: 0.3909895122051239
2023-01-23 00:47:42.150984: step: 1736/529, loss: 0.13762784004211426
2023-01-23 00:47:43.287139: step: 1740/529, loss: 0.030368424952030182
2023-01-23 00:47:44.432612: step: 1744/529, loss: 0.11322517693042755
2023-01-23 00:47:45.602864: step: 1748/529, loss: 0.08092860877513885
2023-01-23 00:47:46.724872: step: 1752/529, loss: 0.03083205223083496
2023-01-23 00:47:47.865428: step: 1756/529, loss: 0.1130671501159668
2023-01-23 00:47:49.016197: step: 1760/529, loss: 0.08137166500091553
2023-01-23 00:47:50.157268: step: 1764/529, loss: 0.18223676085472107
2023-01-23 00:47:51.287098: step: 1768/529, loss: 0.1380632519721985
2023-01-23 00:47:52.421096: step: 1772/529, loss: 0.07590857148170471
2023-01-23 00:47:53.533574: step: 1776/529, loss: 0.06209617853164673
2023-01-23 00:47:54.680996: step: 1780/529, loss: 0.037247609347105026
2023-01-23 00:47:55.854359: step: 1784/529, loss: 0.33542293310165405
2023-01-23 00:47:57.023470: step: 1788/529, loss: 0.17589330673217773
2023-01-23 00:47:58.202360: step: 1792/529, loss: 0.15250429511070251
2023-01-23 00:47:59.345481: step: 1796/529, loss: 0.13087502121925354
2023-01-23 00:48:00.519560: step: 1800/529, loss: 0.06590089946985245
2023-01-23 00:48:01.682083: step: 1804/529, loss: 0.4045642018318176
2023-01-23 00:48:02.838175: step: 1808/529, loss: 0.12438926845788956
2023-01-23 00:48:04.011893: step: 1812/529, loss: 0.20083141326904297
2023-01-23 00:48:05.140418: step: 1816/529, loss: 0.07120934128761292
2023-01-23 00:48:06.304118: step: 1820/529, loss: 0.08995237946510315
2023-01-23 00:48:07.433561: step: 1824/529, loss: 0.06654606014490128
2023-01-23 00:48:08.592009: step: 1828/529, loss: 0.10235595703125
2023-01-23 00:48:09.722390: step: 1832/529, loss: 0.1309341937303543
2023-01-23 00:48:10.850404: step: 1836/529, loss: 0.1873556226491928
2023-01-23 00:48:11.984354: step: 1840/529, loss: 0.10164289176464081
2023-01-23 00:48:13.143855: step: 1844/529, loss: 0.6633205413818359
2023-01-23 00:48:14.272846: step: 1848/529, loss: 0.04476223140954971
2023-01-23 00:48:15.405284: step: 1852/529, loss: 0.04623117670416832
2023-01-23 00:48:16.538383: step: 1856/529, loss: 0.09150433540344238
2023-01-23 00:48:17.681827: step: 1860/529, loss: 0.39013785123825073
2023-01-23 00:48:18.841500: step: 1864/529, loss: 0.15161553025245667
2023-01-23 00:48:19.994527: step: 1868/529, loss: 0.054671287536621094
2023-01-23 00:48:21.117943: step: 1872/529, loss: 0.11773681640625
2023-01-23 00:48:22.257570: step: 1876/529, loss: 0.2029450386762619
2023-01-23 00:48:23.393772: step: 1880/529, loss: 0.08829344809055328
2023-01-23 00:48:24.526442: step: 1884/529, loss: 0.09330368041992188
2023-01-23 00:48:25.665261: step: 1888/529, loss: 0.174309641122818
2023-01-23 00:48:26.797910: step: 1892/529, loss: 0.10527510941028595
2023-01-23 00:48:27.943812: step: 1896/529, loss: 0.1252739429473877
2023-01-23 00:48:29.132994: step: 1900/529, loss: 0.1409069001674652
2023-01-23 00:48:30.305141: step: 1904/529, loss: 0.1402646154165268
2023-01-23 00:48:31.470409: step: 1908/529, loss: 0.2022300660610199
2023-01-23 00:48:32.610825: step: 1912/529, loss: 0.036243438720703125
2023-01-23 00:48:33.759419: step: 1916/529, loss: 0.12417373061180115
2023-01-23 00:48:34.922665: step: 1920/529, loss: 0.3375236392021179
2023-01-23 00:48:36.073939: step: 1924/529, loss: 0.11629372090101242
2023-01-23 00:48:37.230090: step: 1928/529, loss: 0.10912533104419708
2023-01-23 00:48:38.382982: step: 1932/529, loss: 0.03679618984460831
2023-01-23 00:48:39.528612: step: 1936/529, loss: 0.06200075149536133
2023-01-23 00:48:40.656057: step: 1940/529, loss: 0.0762210339307785
2023-01-23 00:48:41.800356: step: 1944/529, loss: 0.04805798828601837
2023-01-23 00:48:42.938208: step: 1948/529, loss: 0.08847646415233612
2023-01-23 00:48:44.070482: step: 1952/529, loss: 0.09774451702833176
2023-01-23 00:48:45.213452: step: 1956/529, loss: 0.024759482592344284
2023-01-23 00:48:46.388547: step: 1960/529, loss: 0.1670069694519043
2023-01-23 00:48:47.544569: step: 1964/529, loss: 0.1777803897857666
2023-01-23 00:48:48.690559: step: 1968/529, loss: 0.04754888266324997
2023-01-23 00:48:49.833923: step: 1972/529, loss: 0.08843345195055008
2023-01-23 00:48:50.984133: step: 1976/529, loss: 0.055100034922361374
2023-01-23 00:48:52.154172: step: 1980/529, loss: 0.0917171984910965
2023-01-23 00:48:53.300764: step: 1984/529, loss: 0.7161492109298706
2023-01-23 00:48:54.446618: step: 1988/529, loss: 0.19107218086719513
2023-01-23 00:48:55.589401: step: 1992/529, loss: 0.04111886024475098
2023-01-23 00:48:56.741266: step: 1996/529, loss: 0.09747834503650665
2023-01-23 00:48:57.879225: step: 2000/529, loss: 0.06688375771045685
2023-01-23 00:48:59.026192: step: 2004/529, loss: 0.0905034989118576
2023-01-23 00:49:00.170592: step: 2008/529, loss: 0.023035384714603424
2023-01-23 00:49:01.322832: step: 2012/529, loss: 0.09108586609363556
2023-01-23 00:49:02.477529: step: 2016/529, loss: 0.13962984085083008
2023-01-23 00:49:03.610390: step: 2020/529, loss: 0.05945110321044922
2023-01-23 00:49:04.741796: step: 2024/529, loss: 0.004268026445060968
2023-01-23 00:49:05.906438: step: 2028/529, loss: 0.1306636929512024
2023-01-23 00:49:07.032202: step: 2032/529, loss: 0.01739818975329399
2023-01-23 00:49:08.172343: step: 2036/529, loss: 0.13418646156787872
2023-01-23 00:49:09.281737: step: 2040/529, loss: 0.032872725278139114
2023-01-23 00:49:10.454069: step: 2044/529, loss: 0.21858596801757812
2023-01-23 00:49:11.597497: step: 2048/529, loss: 0.04718789830803871
2023-01-23 00:49:12.755143: step: 2052/529, loss: 0.25042039155960083
2023-01-23 00:49:13.917546: step: 2056/529, loss: 0.029134273529052734
2023-01-23 00:49:15.054462: step: 2060/529, loss: 0.08246364444494247
2023-01-23 00:49:16.181251: step: 2064/529, loss: 0.04234304651618004
2023-01-23 00:49:17.336248: step: 2068/529, loss: 0.45850732922554016
2023-01-23 00:49:18.502507: step: 2072/529, loss: 0.1547883152961731
2023-01-23 00:49:19.678191: step: 2076/529, loss: 0.07652082294225693
2023-01-23 00:49:20.812474: step: 2080/529, loss: 0.18373946845531464
2023-01-23 00:49:21.947263: step: 2084/529, loss: 0.0656876415014267
2023-01-23 00:49:23.060432: step: 2088/529, loss: 0.022410297766327858
2023-01-23 00:49:24.194784: step: 2092/529, loss: 0.1502913534641266
2023-01-23 00:49:25.334873: step: 2096/529, loss: 0.18248087167739868
2023-01-23 00:49:26.480289: step: 2100/529, loss: 0.08375997841358185
2023-01-23 00:49:27.662400: step: 2104/529, loss: 0.353262335062027
2023-01-23 00:49:28.784237: step: 2108/529, loss: 0.040602684020996094
2023-01-23 00:49:29.919915: step: 2112/529, loss: 0.09877309948205948
2023-01-23 00:49:31.033223: step: 2116/529, loss: 0.07686974853277206
==================================================
Loss: 0.153
--------------------
Dev: {'event': {'p': 0.5991561181434599, 'r': 0.7563249001331558, 'f1': 0.6686286050618011}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6213733075435203, 'r': 0.7444959443800695, 'f1': 0.6773853452820242}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
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': 7}
Korean: {'event': {'p': 0.6, 'r': 0.47619047619047616, 'f1': 0.5309734513274337}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.3684210526315789, 'r': 0.3888888888888889, 'f1': 0.37837837837837834}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5991561181434599, 'r': 0.7563249001331558, 'f1': 0.6686286050618011}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Chinese: {'event': {'p': 0.6213733075435203, 'r': 0.7444959443800695, 'f1': 0.6773853452820242}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5926622765757291, 'r': 0.7300115874855156, 'f1': 0.6542056074766356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6956521739130435, 'r': 0.5079365079365079, 'f1': 0.5871559633027522}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:50:17.288444: step: 4/529, loss: 0.05318479612469673
2023-01-23 00:50:18.405737: step: 8/529, loss: 0.1949097216129303
2023-01-23 00:50:19.514929: step: 12/529, loss: 0.023500585928559303
2023-01-23 00:50:20.649830: step: 16/529, loss: 0.3665791451931
2023-01-23 00:50:21.782551: step: 20/529, loss: 0.29152393341064453
2023-01-23 00:50:22.907772: step: 24/529, loss: 0.01975259743630886
2023-01-23 00:50:24.072432: step: 28/529, loss: 0.10723571479320526
2023-01-23 00:50:25.215497: step: 32/529, loss: 0.04829874262213707
2023-01-23 00:50:26.357131: step: 36/529, loss: 0.2006334811449051
2023-01-23 00:50:27.509938: step: 40/529, loss: 0.1003212034702301
2023-01-23 00:50:28.652195: step: 44/529, loss: 0.03500232473015785
2023-01-23 00:50:29.769850: step: 48/529, loss: 0.13632678985595703
2023-01-23 00:50:30.924256: step: 52/529, loss: 0.1662098914384842
2023-01-23 00:50:32.031539: step: 56/529, loss: 0.19724826514720917
2023-01-23 00:50:33.165356: step: 60/529, loss: 0.14256420731544495
2023-01-23 00:50:34.315910: step: 64/529, loss: 1.071069359779358
2023-01-23 00:50:35.469825: step: 68/529, loss: 0.09685635566711426
2023-01-23 00:50:36.603638: step: 72/529, loss: 0.3655296266078949
2023-01-23 00:50:37.753509: step: 76/529, loss: 0.04453172907233238
2023-01-23 00:50:38.873792: step: 80/529, loss: 0.3913934826850891
2023-01-23 00:50:40.007939: step: 84/529, loss: 0.07473363727331161
2023-01-23 00:50:41.173289: step: 88/529, loss: 0.08572244644165039
2023-01-23 00:50:42.312348: step: 92/529, loss: 0.03197994455695152
2023-01-23 00:50:43.462829: step: 96/529, loss: 0.12795200943946838
2023-01-23 00:50:44.610940: step: 100/529, loss: 0.11406002193689346
2023-01-23 00:50:45.745478: step: 104/529, loss: 0.12601271271705627
2023-01-23 00:50:46.888645: step: 108/529, loss: 0.04080963134765625
2023-01-23 00:50:48.049121: step: 112/529, loss: 0.002889442490413785
2023-01-23 00:50:49.178552: step: 116/529, loss: 0.09884748607873917
2023-01-23 00:50:50.305737: step: 120/529, loss: 0.24842369556427002
2023-01-23 00:50:51.434442: step: 124/529, loss: 0.04914894327521324
2023-01-23 00:50:52.572124: step: 128/529, loss: 0.03499181196093559
2023-01-23 00:50:53.697701: step: 132/529, loss: 0.2525457441806793
2023-01-23 00:50:54.831136: step: 136/529, loss: 0.038802146911621094
2023-01-23 00:50:55.954196: step: 140/529, loss: 0.1172059029340744
2023-01-23 00:50:57.104731: step: 144/529, loss: 0.05616440623998642
2023-01-23 00:50:58.255500: step: 148/529, loss: 0.05729561299085617
2023-01-23 00:50:59.447873: step: 152/529, loss: 0.21257629990577698
2023-01-23 00:51:00.612665: step: 156/529, loss: 0.16854453086853027
2023-01-23 00:51:01.753394: step: 160/529, loss: 0.1114848181605339
2023-01-23 00:51:02.908594: step: 164/529, loss: 0.9672426581382751
2023-01-23 00:51:04.030696: step: 168/529, loss: 0.12714210152626038
2023-01-23 00:51:05.166146: step: 172/529, loss: 0.023979663848876953
2023-01-23 00:51:06.294978: step: 176/529, loss: 0.040175821632146835
2023-01-23 00:51:07.424294: step: 180/529, loss: 0.04639720916748047
2023-01-23 00:51:08.547490: step: 184/529, loss: 0.09676265716552734
2023-01-23 00:51:09.713989: step: 188/529, loss: 0.23949480056762695
2023-01-23 00:51:10.839365: step: 192/529, loss: 0.09937691688537598
2023-01-23 00:51:11.967034: step: 196/529, loss: 0.04111146926879883
2023-01-23 00:51:13.112777: step: 200/529, loss: 0.03849754482507706
2023-01-23 00:51:14.230017: step: 204/529, loss: 0.05183448642492294
2023-01-23 00:51:15.375279: step: 208/529, loss: 0.1392926275730133
2023-01-23 00:51:16.511387: step: 212/529, loss: 0.022698592394590378
2023-01-23 00:51:17.643929: step: 216/529, loss: 0.09227676689624786
2023-01-23 00:51:18.781084: step: 220/529, loss: 0.08268661797046661
2023-01-23 00:51:19.908673: step: 224/529, loss: 0.05050544813275337
2023-01-23 00:51:21.028604: step: 228/529, loss: 1.5040233135223389
2023-01-23 00:51:22.142942: step: 232/529, loss: 0.032087456434965134
2023-01-23 00:51:23.285697: step: 236/529, loss: 0.2216595709323883
2023-01-23 00:51:24.399937: step: 240/529, loss: 0.06133265793323517
2023-01-23 00:51:25.546467: step: 244/529, loss: 0.14863300323486328
2023-01-23 00:51:26.679975: step: 248/529, loss: 0.13959331810474396
2023-01-23 00:51:27.840834: step: 252/529, loss: 0.05861089378595352
2023-01-23 00:51:28.983089: step: 256/529, loss: 0.023376846686005592
2023-01-23 00:51:30.143924: step: 260/529, loss: 0.14258232712745667
2023-01-23 00:51:31.277261: step: 264/529, loss: 0.015352893620729446
2023-01-23 00:51:32.440067: step: 268/529, loss: 0.4317781329154968
2023-01-23 00:51:33.565528: step: 272/529, loss: 0.008370732888579369
2023-01-23 00:51:34.719881: step: 276/529, loss: 0.09130898118019104
2023-01-23 00:51:35.862128: step: 280/529, loss: 0.043993424624204636
2023-01-23 00:51:36.989126: step: 284/529, loss: 0.032162856310606
2023-01-23 00:51:38.135514: step: 288/529, loss: 0.005527496337890625
2023-01-23 00:51:39.247895: step: 292/529, loss: 0.13753624260425568
2023-01-23 00:51:40.402472: step: 296/529, loss: 0.07669506222009659
2023-01-23 00:51:41.544345: step: 300/529, loss: 0.0482851043343544
2023-01-23 00:51:42.700571: step: 304/529, loss: 0.030687524005770683
2023-01-23 00:51:43.865655: step: 308/529, loss: 0.06084032356739044
2023-01-23 00:51:45.005872: step: 312/529, loss: 0.0035672190133482218
2023-01-23 00:51:46.139867: step: 316/529, loss: 0.024836160242557526
2023-01-23 00:51:47.283865: step: 320/529, loss: 0.03090486489236355
2023-01-23 00:51:48.425973: step: 324/529, loss: 0.053237106651067734
2023-01-23 00:51:49.585291: step: 328/529, loss: 0.20230978727340698
2023-01-23 00:51:50.747715: step: 332/529, loss: 0.06596565246582031
2023-01-23 00:51:51.900705: step: 336/529, loss: 0.12374744564294815
2023-01-23 00:51:53.051794: step: 340/529, loss: 0.2253352254629135
2023-01-23 00:51:54.187747: step: 344/529, loss: 0.09065189212560654
2023-01-23 00:51:55.342685: step: 348/529, loss: 0.005558634176850319
2023-01-23 00:51:56.493627: step: 352/529, loss: 0.10750294476747513
2023-01-23 00:51:57.621168: step: 356/529, loss: 0.04743318259716034
2023-01-23 00:51:58.764380: step: 360/529, loss: 0.18426036834716797
2023-01-23 00:51:59.930494: step: 364/529, loss: 0.1449565887451172
2023-01-23 00:52:01.070385: step: 368/529, loss: 0.07447991520166397
2023-01-23 00:52:02.203168: step: 372/529, loss: 0.07435961067676544
2023-01-23 00:52:03.359615: step: 376/529, loss: 0.08984804153442383
2023-01-23 00:52:04.504368: step: 380/529, loss: 0.12104926258325577
2023-01-23 00:52:05.628225: step: 384/529, loss: 0.011165762320160866
2023-01-23 00:52:06.776715: step: 388/529, loss: 0.029711389914155006
2023-01-23 00:52:07.883196: step: 392/529, loss: 0.18595843017101288
2023-01-23 00:52:09.044759: step: 396/529, loss: 0.15950337052345276
2023-01-23 00:52:10.204017: step: 400/529, loss: 0.03425941616296768
2023-01-23 00:52:11.386318: step: 404/529, loss: 0.03351545333862305
2023-01-23 00:52:12.528479: step: 408/529, loss: 0.06853863596916199
2023-01-23 00:52:13.689849: step: 412/529, loss: 0.17024406790733337
2023-01-23 00:52:14.851480: step: 416/529, loss: 0.03452186658978462
2023-01-23 00:52:16.006390: step: 420/529, loss: 0.41898632049560547
2023-01-23 00:52:17.159186: step: 424/529, loss: 0.19416266679763794
2023-01-23 00:52:18.281628: step: 428/529, loss: 0.03100604936480522
2023-01-23 00:52:19.447062: step: 432/529, loss: 0.2522452473640442
2023-01-23 00:52:20.589858: step: 436/529, loss: 0.08203506469726562
2023-01-23 00:52:21.730854: step: 440/529, loss: 0.047330476343631744
2023-01-23 00:52:22.846839: step: 444/529, loss: 0.04445610195398331
2023-01-23 00:52:23.967042: step: 448/529, loss: 0.25001177191734314
2023-01-23 00:52:25.102689: step: 452/529, loss: 0.086267851293087
2023-01-23 00:52:26.222753: step: 456/529, loss: 0.14265404641628265
2023-01-23 00:52:27.383319: step: 460/529, loss: 0.07036981731653214
2023-01-23 00:52:28.546950: step: 464/529, loss: 0.18255801498889923
2023-01-23 00:52:29.691146: step: 468/529, loss: 0.135430246591568
2023-01-23 00:52:30.845026: step: 472/529, loss: 0.09917138516902924
2023-01-23 00:52:31.987202: step: 476/529, loss: 0.05850672721862793
2023-01-23 00:52:33.162584: step: 480/529, loss: 0.09747008979320526
2023-01-23 00:52:34.339343: step: 484/529, loss: 0.10258684307336807
2023-01-23 00:52:35.460074: step: 488/529, loss: 0.03634071350097656
2023-01-23 00:52:36.586408: step: 492/529, loss: 0.021259833127260208
2023-01-23 00:52:37.722638: step: 496/529, loss: 0.16468815505504608
2023-01-23 00:52:38.865479: step: 500/529, loss: 0.18522053956985474
2023-01-23 00:52:39.990139: step: 504/529, loss: 0.2683284878730774
2023-01-23 00:52:41.143229: step: 508/529, loss: 0.041706085205078125
2023-01-23 00:52:42.285762: step: 512/529, loss: 0.044283390045166016
2023-01-23 00:52:43.460139: step: 516/529, loss: 0.05767402797937393
2023-01-23 00:52:44.574618: step: 520/529, loss: 0.06858015060424805
2023-01-23 00:52:45.685595: step: 524/529, loss: 0.17204904556274414
2023-01-23 00:52:46.808451: step: 528/529, loss: 0.03605666384100914
2023-01-23 00:52:47.939545: step: 532/529, loss: 0.12136439979076385
2023-01-23 00:52:49.089668: step: 536/529, loss: 0.15342359244823456
2023-01-23 00:52:50.208907: step: 540/529, loss: 0.05116262659430504
2023-01-23 00:52:51.334589: step: 544/529, loss: 0.20479270815849304
2023-01-23 00:52:52.461316: step: 548/529, loss: 0.10099725425243378
2023-01-23 00:52:53.605101: step: 552/529, loss: 0.021530630066990852
2023-01-23 00:52:54.725820: step: 556/529, loss: 0.07126083970069885
2023-01-23 00:52:55.879970: step: 560/529, loss: 0.05545482784509659
2023-01-23 00:52:57.035506: step: 564/529, loss: 0.04364471137523651
2023-01-23 00:52:58.140203: step: 568/529, loss: 0.10060080885887146
2023-01-23 00:52:59.294547: step: 572/529, loss: 0.1453665792942047
2023-01-23 00:53:00.425453: step: 576/529, loss: 0.06455536186695099
2023-01-23 00:53:01.572306: step: 580/529, loss: 0.21362534165382385
2023-01-23 00:53:02.706385: step: 584/529, loss: 0.6793594360351562
2023-01-23 00:53:03.824776: step: 588/529, loss: 0.016106892377138138
2023-01-23 00:53:04.996679: step: 592/529, loss: 0.01707904413342476
2023-01-23 00:53:06.132592: step: 596/529, loss: 0.16646508872509003
2023-01-23 00:53:07.257784: step: 600/529, loss: 0.08240914344787598
2023-01-23 00:53:08.386880: step: 604/529, loss: 0.29609212279319763
2023-01-23 00:53:09.517562: step: 608/529, loss: 0.447531133890152
2023-01-23 00:53:10.650244: step: 612/529, loss: 0.12447375804185867
2023-01-23 00:53:11.783414: step: 616/529, loss: 0.016482163220643997
2023-01-23 00:53:12.937858: step: 620/529, loss: 0.05028257519006729
2023-01-23 00:53:14.084374: step: 624/529, loss: 0.08668084442615509
2023-01-23 00:53:15.215221: step: 628/529, loss: 0.05309438705444336
2023-01-23 00:53:16.333156: step: 632/529, loss: 0.1840221881866455
2023-01-23 00:53:17.455175: step: 636/529, loss: 0.036759376525878906
2023-01-23 00:53:18.559184: step: 640/529, loss: 0.08736486732959747
2023-01-23 00:53:19.677839: step: 644/529, loss: 0.5296918749809265
2023-01-23 00:53:20.823552: step: 648/529, loss: 0.07456312328577042
2023-01-23 00:53:21.959413: step: 652/529, loss: 0.01911679469048977
2023-01-23 00:53:23.065439: step: 656/529, loss: 0.08950238674879074
2023-01-23 00:53:24.216557: step: 660/529, loss: 0.08298883587121964
2023-01-23 00:53:25.358109: step: 664/529, loss: 0.26108962297439575
2023-01-23 00:53:26.509743: step: 668/529, loss: 0.03059511072933674
2023-01-23 00:53:27.632070: step: 672/529, loss: 0.518105685710907
2023-01-23 00:53:28.773843: step: 676/529, loss: 1.171210527420044
2023-01-23 00:53:29.936361: step: 680/529, loss: 0.29627352952957153
2023-01-23 00:53:31.115612: step: 684/529, loss: 0.04069194942712784
2023-01-23 00:53:32.239120: step: 688/529, loss: 0.20056581497192383
2023-01-23 00:53:33.395088: step: 692/529, loss: 0.5721842646598816
2023-01-23 00:53:34.513800: step: 696/529, loss: 0.023599527776241302
2023-01-23 00:53:35.643363: step: 700/529, loss: 0.8086647987365723
2023-01-23 00:53:36.776207: step: 704/529, loss: 0.1393848955631256
2023-01-23 00:53:37.939516: step: 708/529, loss: 0.2550451159477234
2023-01-23 00:53:39.072618: step: 712/529, loss: 0.046225450932979584
2023-01-23 00:53:40.225681: step: 716/529, loss: 0.0578191764652729
2023-01-23 00:53:41.368631: step: 720/529, loss: 0.12173286080360413
2023-01-23 00:53:42.502815: step: 724/529, loss: 0.10239486396312714
2023-01-23 00:53:43.662488: step: 728/529, loss: 0.18153181672096252
2023-01-23 00:53:44.795083: step: 732/529, loss: 0.026910115033388138
2023-01-23 00:53:45.988547: step: 736/529, loss: 0.24620114266872406
2023-01-23 00:53:47.141672: step: 740/529, loss: 0.04441988468170166
2023-01-23 00:53:48.293867: step: 744/529, loss: 0.0939784049987793
2023-01-23 00:53:49.452722: step: 748/529, loss: 0.4313790500164032
2023-01-23 00:53:50.591876: step: 752/529, loss: 0.04972870647907257
2023-01-23 00:53:51.725294: step: 756/529, loss: 0.039792679250240326
2023-01-23 00:53:52.866818: step: 760/529, loss: 0.04780202358961105
2023-01-23 00:53:53.998910: step: 764/529, loss: 0.04972591623663902
2023-01-23 00:53:55.128806: step: 768/529, loss: 0.07703933864831924
2023-01-23 00:53:56.261273: step: 772/529, loss: 0.08703837543725967
2023-01-23 00:53:57.409180: step: 776/529, loss: 0.10489273071289062
2023-01-23 00:53:58.592877: step: 780/529, loss: 0.09100428223609924
2023-01-23 00:53:59.732866: step: 784/529, loss: 0.06083212047815323
2023-01-23 00:54:00.854745: step: 788/529, loss: 0.086255744099617
2023-01-23 00:54:01.978419: step: 792/529, loss: 0.05362110212445259
2023-01-23 00:54:03.150785: step: 796/529, loss: 0.17210140824317932
2023-01-23 00:54:04.273734: step: 800/529, loss: 0.0892024040222168
2023-01-23 00:54:05.388509: step: 804/529, loss: 0.2554086446762085
2023-01-23 00:54:06.523268: step: 808/529, loss: 0.29440221190452576
2023-01-23 00:54:07.675620: step: 812/529, loss: 0.08527612686157227
2023-01-23 00:54:08.844016: step: 816/529, loss: 0.048023417592048645
2023-01-23 00:54:10.014418: step: 820/529, loss: 0.1514115333557129
2023-01-23 00:54:11.149932: step: 824/529, loss: 0.03909330442547798
2023-01-23 00:54:12.303203: step: 828/529, loss: 0.2097305804491043
2023-01-23 00:54:13.494944: step: 832/529, loss: 0.06543455272912979
2023-01-23 00:54:14.628677: step: 836/529, loss: 0.10457348078489304
2023-01-23 00:54:15.799893: step: 840/529, loss: 0.0517488494515419
2023-01-23 00:54:16.918467: step: 844/529, loss: 0.056903742253780365
2023-01-23 00:54:18.044753: step: 848/529, loss: 0.09288758784532547
2023-01-23 00:54:19.178149: step: 852/529, loss: 0.02783241495490074
2023-01-23 00:54:20.308894: step: 856/529, loss: 0.11873073130846024
2023-01-23 00:54:21.440056: step: 860/529, loss: 0.18188077211380005
2023-01-23 00:54:22.570225: step: 864/529, loss: 0.07721786201000214
2023-01-23 00:54:23.751933: step: 868/529, loss: 0.161095529794693
2023-01-23 00:54:24.894760: step: 872/529, loss: 0.11576557159423828
2023-01-23 00:54:26.034537: step: 876/529, loss: 0.044678784906864166
2023-01-23 00:54:27.188077: step: 880/529, loss: 0.14981861412525177
2023-01-23 00:54:28.298208: step: 884/529, loss: 0.01584150828421116
2023-01-23 00:54:29.449803: step: 888/529, loss: 0.05137233808636665
2023-01-23 00:54:30.623327: step: 892/529, loss: 0.013538789004087448
2023-01-23 00:54:31.760121: step: 896/529, loss: 0.056047774851322174
2023-01-23 00:54:32.878047: step: 900/529, loss: 0.02088337019085884
2023-01-23 00:54:34.004029: step: 904/529, loss: 0.05288701504468918
2023-01-23 00:54:35.130723: step: 908/529, loss: 0.03825350105762482
2023-01-23 00:54:36.273315: step: 912/529, loss: 0.09216120839118958
2023-01-23 00:54:37.388019: step: 916/529, loss: 0.037940215319395065
2023-01-23 00:54:38.535372: step: 920/529, loss: 0.07928531616926193
2023-01-23 00:54:39.718537: step: 924/529, loss: 0.186113640666008
2023-01-23 00:54:40.850986: step: 928/529, loss: 0.0708475112915039
2023-01-23 00:54:42.014448: step: 932/529, loss: 0.09119148552417755
2023-01-23 00:54:43.146420: step: 936/529, loss: 0.045620083808898926
2023-01-23 00:54:44.303216: step: 940/529, loss: 1.0741746425628662
2023-01-23 00:54:45.437190: step: 944/529, loss: 0.09215126931667328
2023-01-23 00:54:46.552163: step: 948/529, loss: 0.04115419462323189
2023-01-23 00:54:47.686520: step: 952/529, loss: 0.028416156768798828
2023-01-23 00:54:48.828060: step: 956/529, loss: 0.2806165814399719
2023-01-23 00:54:49.948038: step: 960/529, loss: 0.03901674970984459
2023-01-23 00:54:51.092107: step: 964/529, loss: 0.045200541615486145
2023-01-23 00:54:52.245745: step: 968/529, loss: 0.12343569099903107
2023-01-23 00:54:53.364257: step: 972/529, loss: 0.1250072568655014
2023-01-23 00:54:54.522062: step: 976/529, loss: 0.10300364345312119
2023-01-23 00:54:55.646203: step: 980/529, loss: 0.04640607535839081
2023-01-23 00:54:56.771947: step: 984/529, loss: 0.33151257038116455
2023-01-23 00:54:57.873710: step: 988/529, loss: 0.02757744863629341
2023-01-23 00:54:59.016399: step: 992/529, loss: 0.03221692889928818
2023-01-23 00:55:00.147556: step: 996/529, loss: 0.03503725677728653
2023-01-23 00:55:01.272240: step: 1000/529, loss: 0.4943471848964691
2023-01-23 00:55:02.406906: step: 1004/529, loss: 0.48283347487449646
2023-01-23 00:55:03.536843: step: 1008/529, loss: 0.06921110302209854
2023-01-23 00:55:04.668337: step: 1012/529, loss: 0.019154738634824753
2023-01-23 00:55:05.793715: step: 1016/529, loss: 0.08541993796825409
2023-01-23 00:55:06.905735: step: 1020/529, loss: 0.3570098876953125
2023-01-23 00:55:08.047563: step: 1024/529, loss: 0.09803364425897598
2023-01-23 00:55:09.216388: step: 1028/529, loss: 0.026587389409542084
2023-01-23 00:55:10.342008: step: 1032/529, loss: 0.10580854117870331
2023-01-23 00:55:11.476516: step: 1036/529, loss: 0.17923840880393982
2023-01-23 00:55:12.640882: step: 1040/529, loss: 0.09724769741296768
2023-01-23 00:55:13.751179: step: 1044/529, loss: 0.0658857598900795
2023-01-23 00:55:14.929652: step: 1048/529, loss: 0.66107577085495
2023-01-23 00:55:16.076186: step: 1052/529, loss: 0.07817935943603516
2023-01-23 00:55:17.203959: step: 1056/529, loss: 0.07002381980419159
2023-01-23 00:55:18.334235: step: 1060/529, loss: 0.10745124518871307
2023-01-23 00:55:19.494125: step: 1064/529, loss: 0.05089931935071945
2023-01-23 00:55:20.656723: step: 1068/529, loss: 0.04335417598485947
2023-01-23 00:55:21.764729: step: 1072/529, loss: 0.03953962028026581
2023-01-23 00:55:22.892146: step: 1076/529, loss: 0.021099664270877838
2023-01-23 00:55:24.016104: step: 1080/529, loss: 0.05591411888599396
2023-01-23 00:55:25.158434: step: 1084/529, loss: 0.07288141548633575
2023-01-23 00:55:26.286385: step: 1088/529, loss: 0.02204909361898899
2023-01-23 00:55:27.438629: step: 1092/529, loss: 0.22917665541172028
2023-01-23 00:55:28.574538: step: 1096/529, loss: 0.43293654918670654
2023-01-23 00:55:29.718539: step: 1100/529, loss: 0.09718716144561768
2023-01-23 00:55:30.839198: step: 1104/529, loss: 0.18410708010196686
2023-01-23 00:55:31.973242: step: 1108/529, loss: 0.24055281281471252
2023-01-23 00:55:33.120710: step: 1112/529, loss: 0.0636385902762413
2023-01-23 00:55:34.256113: step: 1116/529, loss: 0.03886529058218002
2023-01-23 00:55:35.385100: step: 1120/529, loss: 0.6433650255203247
2023-01-23 00:55:36.521142: step: 1124/529, loss: 0.1143740639090538
2023-01-23 00:55:37.665067: step: 1128/529, loss: 0.05895862728357315
2023-01-23 00:55:38.805470: step: 1132/529, loss: 0.008826113305985928
2023-01-23 00:55:39.984236: step: 1136/529, loss: 0.11787395924329758
2023-01-23 00:55:41.110020: step: 1140/529, loss: 0.42764148116111755
2023-01-23 00:55:42.249533: step: 1144/529, loss: 0.11822395771741867
2023-01-23 00:55:43.382398: step: 1148/529, loss: 0.06025657802820206
2023-01-23 00:55:44.511913: step: 1152/529, loss: 0.05768585205078125
2023-01-23 00:55:45.651759: step: 1156/529, loss: 0.06109189987182617
2023-01-23 00:55:46.800394: step: 1160/529, loss: 0.40720662474632263
2023-01-23 00:55:47.958792: step: 1164/529, loss: 0.03205518797039986
2023-01-23 00:55:49.090278: step: 1168/529, loss: 0.12144317477941513
2023-01-23 00:55:50.217325: step: 1172/529, loss: 0.06864538788795471
2023-01-23 00:55:51.394816: step: 1176/529, loss: 0.9421911239624023
2023-01-23 00:55:52.535065: step: 1180/529, loss: 0.024359513074159622
2023-01-23 00:55:53.680720: step: 1184/529, loss: 0.1171969398856163
2023-01-23 00:55:54.788696: step: 1188/529, loss: 0.05607500299811363
2023-01-23 00:55:55.933551: step: 1192/529, loss: 0.06799764931201935
2023-01-23 00:55:57.055466: step: 1196/529, loss: 0.5128872990608215
2023-01-23 00:55:58.179101: step: 1200/529, loss: 0.05003919452428818
2023-01-23 00:55:59.327167: step: 1204/529, loss: 0.4062836468219757
2023-01-23 00:56:00.458538: step: 1208/529, loss: 0.11244507133960724
2023-01-23 00:56:01.572349: step: 1212/529, loss: 0.08958905190229416
2023-01-23 00:56:02.706549: step: 1216/529, loss: 0.02769956737756729
2023-01-23 00:56:03.848021: step: 1220/529, loss: 0.28001290559768677
2023-01-23 00:56:05.007673: step: 1224/529, loss: 0.008771037682890892
2023-01-23 00:56:06.115474: step: 1228/529, loss: 0.11592188477516174
2023-01-23 00:56:07.235749: step: 1232/529, loss: 0.009035897441208363
2023-01-23 00:56:08.358175: step: 1236/529, loss: 0.04196319729089737
2023-01-23 00:56:09.483522: step: 1240/529, loss: 0.03999403864145279
2023-01-23 00:56:10.632961: step: 1244/529, loss: 0.09356927871704102
2023-01-23 00:56:11.778103: step: 1248/529, loss: 0.0769878402352333
2023-01-23 00:56:12.941328: step: 1252/529, loss: 0.13391000032424927
2023-01-23 00:56:14.112944: step: 1256/529, loss: 0.11210170388221741
2023-01-23 00:56:15.231167: step: 1260/529, loss: 0.18320532143115997
2023-01-23 00:56:16.366655: step: 1264/529, loss: 0.13048622012138367
2023-01-23 00:56:17.494764: step: 1268/529, loss: 0.03078451193869114
2023-01-23 00:56:18.616312: step: 1272/529, loss: 0.038887396454811096
2023-01-23 00:56:19.745742: step: 1276/529, loss: 0.11737289279699326
2023-01-23 00:56:20.865101: step: 1280/529, loss: 0.06679253280162811
2023-01-23 00:56:21.984192: step: 1284/529, loss: 0.07098370045423508
2023-01-23 00:56:23.136787: step: 1288/529, loss: 0.25798606872558594
2023-01-23 00:56:24.235388: step: 1292/529, loss: 0.02176227606832981
2023-01-23 00:56:25.380412: step: 1296/529, loss: 0.6038552522659302
2023-01-23 00:56:26.524133: step: 1300/529, loss: 0.10248793661594391
2023-01-23 00:56:27.678353: step: 1304/529, loss: 0.05112873390316963
2023-01-23 00:56:28.806392: step: 1308/529, loss: 0.19271716475486755
2023-01-23 00:56:29.962122: step: 1312/529, loss: 0.0049221995286643505
2023-01-23 00:56:31.086312: step: 1316/529, loss: 0.04891491308808327
2023-01-23 00:56:32.239049: step: 1320/529, loss: 0.00672416714951396
2023-01-23 00:56:33.372985: step: 1324/529, loss: 0.19254112243652344
2023-01-23 00:56:34.508677: step: 1328/529, loss: 0.06768903881311417
2023-01-23 00:56:35.638171: step: 1332/529, loss: 0.08918926864862442
2023-01-23 00:56:36.768722: step: 1336/529, loss: 0.12589283287525177
2023-01-23 00:56:37.896960: step: 1340/529, loss: 0.1547192633152008
2023-01-23 00:56:39.024080: step: 1344/529, loss: 0.013988470658659935
2023-01-23 00:56:40.161304: step: 1348/529, loss: 0.0335942767560482
2023-01-23 00:56:41.276196: step: 1352/529, loss: 0.12018919736146927
2023-01-23 00:56:42.407542: step: 1356/529, loss: 0.11278744041919708
2023-01-23 00:56:43.531923: step: 1360/529, loss: 0.06362161040306091
2023-01-23 00:56:44.681971: step: 1364/529, loss: 0.6211714148521423
2023-01-23 00:56:45.826945: step: 1368/529, loss: 0.10992946475744247
2023-01-23 00:56:46.955529: step: 1372/529, loss: 0.0833558514714241
2023-01-23 00:56:48.125036: step: 1376/529, loss: 0.088636115193367
2023-01-23 00:56:49.247791: step: 1380/529, loss: 0.013067150488495827
2023-01-23 00:56:50.402188: step: 1384/529, loss: 0.2268669158220291
2023-01-23 00:56:51.546532: step: 1388/529, loss: 0.025382185354828835
2023-01-23 00:56:52.689084: step: 1392/529, loss: 0.04205169528722763
2023-01-23 00:56:53.843024: step: 1396/529, loss: 0.11921052634716034
2023-01-23 00:56:54.971489: step: 1400/529, loss: 0.13757380843162537
2023-01-23 00:56:56.097195: step: 1404/529, loss: 0.21393270790576935
2023-01-23 00:56:57.251145: step: 1408/529, loss: 0.5535637736320496
2023-01-23 00:56:58.393627: step: 1412/529, loss: 0.052686452865600586
2023-01-23 00:56:59.523339: step: 1416/529, loss: 0.12932290136814117
2023-01-23 00:57:00.676178: step: 1420/529, loss: 0.0324755422770977
2023-01-23 00:57:01.810463: step: 1424/529, loss: 0.039873696863651276
2023-01-23 00:57:02.951390: step: 1428/529, loss: 0.06404171139001846
2023-01-23 00:57:04.096760: step: 1432/529, loss: 0.026835300028324127
2023-01-23 00:57:05.234343: step: 1436/529, loss: 0.06509961932897568
2023-01-23 00:57:06.379802: step: 1440/529, loss: 0.042978666722774506
2023-01-23 00:57:07.505916: step: 1444/529, loss: 0.049712374806404114
2023-01-23 00:57:08.629875: step: 1448/529, loss: 0.03558788448572159
2023-01-23 00:57:09.783861: step: 1452/529, loss: 0.13023605942726135
2023-01-23 00:57:10.934959: step: 1456/529, loss: 0.418692946434021
2023-01-23 00:57:12.083618: step: 1460/529, loss: 0.18764762580394745
2023-01-23 00:57:13.249720: step: 1464/529, loss: 0.05810079723596573
2023-01-23 00:57:14.389711: step: 1468/529, loss: 0.1285969763994217
2023-01-23 00:57:15.543434: step: 1472/529, loss: 0.08018741756677628
2023-01-23 00:57:16.660896: step: 1476/529, loss: 0.07754955440759659
2023-01-23 00:57:17.778932: step: 1480/529, loss: 0.08813085407018661
2023-01-23 00:57:18.916948: step: 1484/529, loss: 0.08301258087158203
2023-01-23 00:57:20.049198: step: 1488/529, loss: 0.11304989457130432
2023-01-23 00:57:21.197769: step: 1492/529, loss: 0.4508059024810791
2023-01-23 00:57:22.324817: step: 1496/529, loss: 0.012687206268310547
2023-01-23 00:57:23.474851: step: 1500/529, loss: 0.1006084457039833
2023-01-23 00:57:24.664756: step: 1504/529, loss: 0.5418062210083008
2023-01-23 00:57:25.817250: step: 1508/529, loss: 0.04585056006908417
2023-01-23 00:57:26.983404: step: 1512/529, loss: 0.04876108095049858
2023-01-23 00:57:28.158621: step: 1516/529, loss: 0.07245712727308273
2023-01-23 00:57:29.316348: step: 1520/529, loss: 0.08835025131702423
2023-01-23 00:57:30.466382: step: 1524/529, loss: 0.09246230125427246
2023-01-23 00:57:31.630954: step: 1528/529, loss: 0.4610868990421295
2023-01-23 00:57:32.781776: step: 1532/529, loss: 0.04692067950963974
2023-01-23 00:57:33.925406: step: 1536/529, loss: 0.02602415159344673
2023-01-23 00:57:35.064935: step: 1540/529, loss: 0.19669437408447266
2023-01-23 00:57:36.191255: step: 1544/529, loss: 0.2208385467529297
2023-01-23 00:57:37.366980: step: 1548/529, loss: 0.04646854102611542
2023-01-23 00:57:38.491799: step: 1552/529, loss: 0.08519373089075089
2023-01-23 00:57:39.605800: step: 1556/529, loss: 0.1493523269891739
2023-01-23 00:57:40.745423: step: 1560/529, loss: 0.15319472551345825
2023-01-23 00:57:41.918357: step: 1564/529, loss: 0.43943822383880615
2023-01-23 00:57:43.052402: step: 1568/529, loss: 0.04767151176929474
2023-01-23 00:57:44.235375: step: 1572/529, loss: 0.10989365726709366
2023-01-23 00:57:45.395758: step: 1576/529, loss: 0.14813171327114105
2023-01-23 00:57:46.524817: step: 1580/529, loss: 0.08882666379213333
2023-01-23 00:57:47.679768: step: 1584/529, loss: 0.6751924753189087
2023-01-23 00:57:48.820598: step: 1588/529, loss: 0.13727807998657227
2023-01-23 00:57:49.941312: step: 1592/529, loss: 0.3277858793735504
2023-01-23 00:57:51.064873: step: 1596/529, loss: 0.035420991480350494
2023-01-23 00:57:52.195665: step: 1600/529, loss: 0.058509137481451035
2023-01-23 00:57:53.355298: step: 1604/529, loss: 0.03420314937829971
2023-01-23 00:57:54.488263: step: 1608/529, loss: 0.12462940067052841
2023-01-23 00:57:55.625029: step: 1612/529, loss: 0.0929853692650795
2023-01-23 00:57:56.745772: step: 1616/529, loss: 0.1898341327905655
2023-01-23 00:57:57.888360: step: 1620/529, loss: 0.11131754517555237
2023-01-23 00:57:59.033559: step: 1624/529, loss: 0.052225757390260696
2023-01-23 00:58:00.163060: step: 1628/529, loss: 0.03277263790369034
2023-01-23 00:58:01.283886: step: 1632/529, loss: 0.012453724630177021
2023-01-23 00:58:02.430657: step: 1636/529, loss: 0.1413319706916809
2023-01-23 00:58:03.556827: step: 1640/529, loss: 0.06446418166160583
2023-01-23 00:58:04.761484: step: 1644/529, loss: 0.0094451904296875
2023-01-23 00:58:05.891209: step: 1648/529, loss: 0.3612396717071533
2023-01-23 00:58:07.023947: step: 1652/529, loss: 0.07011563330888748
2023-01-23 00:58:08.172653: step: 1656/529, loss: 0.07222671806812286
2023-01-23 00:58:09.295972: step: 1660/529, loss: 0.11896353214979172
2023-01-23 00:58:10.504018: step: 1664/529, loss: 0.1331164389848709
2023-01-23 00:58:11.656865: step: 1668/529, loss: 0.2884250581264496
2023-01-23 00:58:12.789026: step: 1672/529, loss: 0.0808897539973259
2023-01-23 00:58:13.953992: step: 1676/529, loss: 0.07857723534107208
2023-01-23 00:58:15.080608: step: 1680/529, loss: 0.16002291440963745
2023-01-23 00:58:16.233579: step: 1684/529, loss: 0.20574329793453217
2023-01-23 00:58:17.371389: step: 1688/529, loss: 0.022405290976166725
2023-01-23 00:58:18.485916: step: 1692/529, loss: 0.05014238506555557
2023-01-23 00:58:19.610694: step: 1696/529, loss: 0.028252029791474342
2023-01-23 00:58:20.747372: step: 1700/529, loss: 0.0632355734705925
2023-01-23 00:58:21.887378: step: 1704/529, loss: 0.10403050482273102
2023-01-23 00:58:23.019598: step: 1708/529, loss: 0.027089595794677734
2023-01-23 00:58:24.153059: step: 1712/529, loss: 0.22194623947143555
2023-01-23 00:58:25.306432: step: 1716/529, loss: 0.10052306950092316
2023-01-23 00:58:26.472143: step: 1720/529, loss: 0.12119140475988388
2023-01-23 00:58:27.615390: step: 1724/529, loss: 0.10400199890136719
2023-01-23 00:58:28.751086: step: 1728/529, loss: 0.12181172519922256
2023-01-23 00:58:29.859781: step: 1732/529, loss: 0.05166090652346611
2023-01-23 00:58:31.051373: step: 1736/529, loss: 0.06643734127283096
2023-01-23 00:58:32.182521: step: 1740/529, loss: 0.05976066738367081
2023-01-23 00:58:33.319317: step: 1744/529, loss: 0.05646400526165962
2023-01-23 00:58:34.456909: step: 1748/529, loss: 0.23236894607543945
2023-01-23 00:58:35.582459: step: 1752/529, loss: 0.24543443322181702
2023-01-23 00:58:36.729919: step: 1756/529, loss: 0.031052017584443092
2023-01-23 00:58:37.879406: step: 1760/529, loss: 0.06249818950891495
2023-01-23 00:58:39.004751: step: 1764/529, loss: 0.04362058639526367
2023-01-23 00:58:40.122016: step: 1768/529, loss: 0.042107775807380676
2023-01-23 00:58:41.254940: step: 1772/529, loss: 0.18370705842971802
2023-01-23 00:58:42.388520: step: 1776/529, loss: 0.16098804771900177
2023-01-23 00:58:43.513072: step: 1780/529, loss: 0.05587730556726456
2023-01-23 00:58:44.660425: step: 1784/529, loss: 0.14834336936473846
2023-01-23 00:58:45.768482: step: 1788/529, loss: 0.0771198719739914
2023-01-23 00:58:46.875671: step: 1792/529, loss: 0.03963589668273926
2023-01-23 00:58:47.997157: step: 1796/529, loss: 0.05296192318201065
2023-01-23 00:58:49.151626: step: 1800/529, loss: 0.03234367445111275
2023-01-23 00:58:50.306790: step: 1804/529, loss: 0.13179749250411987
2023-01-23 00:58:51.422334: step: 1808/529, loss: 0.05174579471349716
2023-01-23 00:58:52.547882: step: 1812/529, loss: 0.01923990249633789
2023-01-23 00:58:53.686352: step: 1816/529, loss: 0.048125553876161575
2023-01-23 00:58:54.820070: step: 1820/529, loss: 0.042542293667793274
2023-01-23 00:58:55.947247: step: 1824/529, loss: 0.044344425201416016
2023-01-23 00:58:57.097365: step: 1828/529, loss: 0.10813198238611221
2023-01-23 00:58:58.231758: step: 1832/529, loss: 0.08128070831298828
2023-01-23 00:58:59.371953: step: 1836/529, loss: 0.08430986106395721
2023-01-23 00:59:00.497739: step: 1840/529, loss: 0.1343776285648346
2023-01-23 00:59:01.664238: step: 1844/529, loss: 0.08498091995716095
2023-01-23 00:59:02.802455: step: 1848/529, loss: 0.07745161652565002
2023-01-23 00:59:03.962022: step: 1852/529, loss: 0.10018501430749893
2023-01-23 00:59:05.086307: step: 1856/529, loss: 0.0638589859008789
2023-01-23 00:59:06.221880: step: 1860/529, loss: 0.077477365732193
2023-01-23 00:59:07.334364: step: 1864/529, loss: 0.03726239129900932
2023-01-23 00:59:08.506965: step: 1868/529, loss: 0.16419890522956848
2023-01-23 00:59:09.669085: step: 1872/529, loss: 0.07609482109546661
2023-01-23 00:59:10.796539: step: 1876/529, loss: 0.55999755859375
2023-01-23 00:59:11.940626: step: 1880/529, loss: 0.09526167064905167
2023-01-23 00:59:13.137658: step: 1884/529, loss: 0.04246530681848526
2023-01-23 00:59:14.277583: step: 1888/529, loss: 0.03554539754986763
2023-01-23 00:59:15.394890: step: 1892/529, loss: 0.26806288957595825
2023-01-23 00:59:16.541514: step: 1896/529, loss: 0.04108457639813423
2023-01-23 00:59:17.720447: step: 1900/529, loss: 0.020398426800966263
2023-01-23 00:59:18.862550: step: 1904/529, loss: 0.026177596300840378
2023-01-23 00:59:20.016636: step: 1908/529, loss: 0.10287800431251526
2023-01-23 00:59:21.153053: step: 1912/529, loss: 0.10997362434864044
2023-01-23 00:59:22.293125: step: 1916/529, loss: 0.03597879409790039
2023-01-23 00:59:23.439796: step: 1920/529, loss: 0.08412304520606995
2023-01-23 00:59:24.598298: step: 1924/529, loss: 0.049201205372810364
2023-01-23 00:59:25.744807: step: 1928/529, loss: 0.07876729965209961
2023-01-23 00:59:26.906521: step: 1932/529, loss: 0.11989942193031311
2023-01-23 00:59:28.045513: step: 1936/529, loss: 0.009969890117645264
2023-01-23 00:59:29.185404: step: 1940/529, loss: 0.00480041466653347
2023-01-23 00:59:30.319842: step: 1944/529, loss: 0.28289785981178284
2023-01-23 00:59:31.472118: step: 1948/529, loss: 0.27803611755371094
2023-01-23 00:59:32.601234: step: 1952/529, loss: 0.025960635393857956
2023-01-23 00:59:33.778877: step: 1956/529, loss: 0.22723540663719177
2023-01-23 00:59:34.924063: step: 1960/529, loss: 0.05281104892492294
2023-01-23 00:59:36.051716: step: 1964/529, loss: 0.023982621729373932
2023-01-23 00:59:37.185472: step: 1968/529, loss: 0.015401411801576614
2023-01-23 00:59:38.333818: step: 1972/529, loss: 0.03710746765136719
2023-01-23 00:59:39.453709: step: 1976/529, loss: 0.11982041597366333
2023-01-23 00:59:40.620012: step: 1980/529, loss: 0.09672613441944122
2023-01-23 00:59:41.749615: step: 1984/529, loss: 0.018486738204956055
2023-01-23 00:59:42.913819: step: 1988/529, loss: 0.06714914739131927
2023-01-23 00:59:44.032288: step: 1992/529, loss: 0.07497940212488174
2023-01-23 00:59:45.151882: step: 1996/529, loss: 0.1743757277727127
2023-01-23 00:59:46.269660: step: 2000/529, loss: 0.4676494598388672
2023-01-23 00:59:47.418311: step: 2004/529, loss: 0.12826529145240784
2023-01-23 00:59:48.564251: step: 2008/529, loss: 0.016652679070830345
2023-01-23 00:59:49.715345: step: 2012/529, loss: 0.14339298009872437
2023-01-23 00:59:50.864613: step: 2016/529, loss: 0.23808622360229492
2023-01-23 00:59:52.034855: step: 2020/529, loss: 0.1738269329071045
2023-01-23 00:59:53.170934: step: 2024/529, loss: 0.033908870071172714
2023-01-23 00:59:54.316113: step: 2028/529, loss: 0.13454551994800568
2023-01-23 00:59:55.442994: step: 2032/529, loss: 0.26784712076187134
2023-01-23 00:59:56.580150: step: 2036/529, loss: 0.007646751590073109
2023-01-23 00:59:57.713333: step: 2040/529, loss: 0.027662038803100586
2023-01-23 00:59:58.891006: step: 2044/529, loss: 0.19166623055934906
2023-01-23 01:00:00.010259: step: 2048/529, loss: 0.021297072991728783
2023-01-23 01:00:01.185094: step: 2052/529, loss: 0.11430978775024414
2023-01-23 01:00:02.300573: step: 2056/529, loss: 0.13252010941505432
2023-01-23 01:00:03.441136: step: 2060/529, loss: 0.09151826053857803
2023-01-23 01:00:04.574246: step: 2064/529, loss: 0.0400049202144146
2023-01-23 01:00:05.743752: step: 2068/529, loss: 0.06467743217945099
2023-01-23 01:00:06.907954: step: 2072/529, loss: 0.45453158020973206
2023-01-23 01:00:08.039394: step: 2076/529, loss: 0.020348738878965378
2023-01-23 01:00:09.153630: step: 2080/529, loss: 0.08773956447839737
2023-01-23 01:00:10.283212: step: 2084/529, loss: 0.05284789949655533
2023-01-23 01:00:11.440912: step: 2088/529, loss: 0.3052424490451813
2023-01-23 01:00:12.585093: step: 2092/529, loss: 0.09540295600891113
2023-01-23 01:00:13.729019: step: 2096/529, loss: 0.08626031875610352
2023-01-23 01:00:14.882700: step: 2100/529, loss: 0.03313612937927246
2023-01-23 01:00:16.026583: step: 2104/529, loss: 0.03666281700134277
2023-01-23 01:00:17.167302: step: 2108/529, loss: 0.20233607292175293
2023-01-23 01:00:18.290459: step: 2112/529, loss: 0.023164652287960052
2023-01-23 01:00:19.424851: step: 2116/529, loss: 0.012871170416474342
==================================================
Loss: 0.132
--------------------
Dev: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
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': 8}
Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
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': 8}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:01:17.412662: step: 4/529, loss: 0.024635886773467064
2023-01-23 01:01:18.547793: step: 8/529, loss: 0.12102871388196945
2023-01-23 01:01:19.656196: step: 12/529, loss: 0.024912506341934204
2023-01-23 01:01:20.769680: step: 16/529, loss: 0.1407354325056076
2023-01-23 01:01:21.893560: step: 20/529, loss: 0.8606937527656555
2023-01-23 01:01:23.042224: step: 24/529, loss: 0.03574056550860405
2023-01-23 01:01:24.177466: step: 28/529, loss: 0.02708921581506729
2023-01-23 01:01:25.306056: step: 32/529, loss: 0.08230924606323242
2023-01-23 01:01:26.453092: step: 36/529, loss: 0.05329904705286026
2023-01-23 01:01:27.577399: step: 40/529, loss: 0.06985016167163849
2023-01-23 01:01:28.741190: step: 44/529, loss: 0.005886650178581476
2023-01-23 01:01:29.864425: step: 48/529, loss: 0.10070696473121643
2023-01-23 01:01:31.013934: step: 52/529, loss: 0.04015941545367241
2023-01-23 01:01:32.139067: step: 56/529, loss: 0.09081902354955673
2023-01-23 01:01:33.283448: step: 60/529, loss: 0.0830882117152214
2023-01-23 01:01:34.415158: step: 64/529, loss: 0.10325441509485245
2023-01-23 01:01:35.538561: step: 68/529, loss: 0.047469139099121094
2023-01-23 01:01:36.654769: step: 72/529, loss: 0.002521228976547718
2023-01-23 01:01:37.780366: step: 76/529, loss: 0.008720017038285732
2023-01-23 01:01:38.926094: step: 80/529, loss: 0.09637127071619034
2023-01-23 01:01:40.085611: step: 84/529, loss: 0.0161316879093647
2023-01-23 01:01:41.201770: step: 88/529, loss: 0.0007552146562375128
2023-01-23 01:01:42.301501: step: 92/529, loss: 0.00423774728551507
2023-01-23 01:01:43.405916: step: 96/529, loss: 0.10617323219776154
2023-01-23 01:01:44.553284: step: 100/529, loss: 0.07259197533130646
2023-01-23 01:01:45.689681: step: 104/529, loss: 0.172722727060318
2023-01-23 01:01:46.835105: step: 108/529, loss: 0.07465362548828125
2023-01-23 01:01:47.961993: step: 112/529, loss: 0.04421424865722656
2023-01-23 01:01:49.103258: step: 116/529, loss: 0.19773635268211365
2023-01-23 01:01:50.276852: step: 120/529, loss: 0.6913812160491943
2023-01-23 01:01:51.442925: step: 124/529, loss: 0.19183094799518585
2023-01-23 01:01:52.591265: step: 128/529, loss: 0.1485912799835205
2023-01-23 01:01:53.762572: step: 132/529, loss: 0.005334615707397461
2023-01-23 01:01:54.904181: step: 136/529, loss: 0.0032499313820153475
2023-01-23 01:01:56.054269: step: 140/529, loss: 0.12808199226856232
2023-01-23 01:01:57.176570: step: 144/529, loss: 0.16091834008693695
2023-01-23 01:01:58.305768: step: 148/529, loss: 0.22805194556713104
2023-01-23 01:01:59.458716: step: 152/529, loss: 0.04231410101056099
2023-01-23 01:02:00.586478: step: 156/529, loss: 0.09192819893360138
2023-01-23 01:02:01.701737: step: 160/529, loss: 0.1499231457710266
2023-01-23 01:02:02.866103: step: 164/529, loss: 0.1801927089691162
2023-01-23 01:02:03.993025: step: 168/529, loss: 0.015019417740404606
2023-01-23 01:02:05.156799: step: 172/529, loss: 0.08351421356201172
2023-01-23 01:02:06.314660: step: 176/529, loss: 0.17925682663917542
2023-01-23 01:02:07.464159: step: 180/529, loss: 0.02656717225909233
2023-01-23 01:02:08.611657: step: 184/529, loss: 0.05475788190960884
2023-01-23 01:02:09.814635: step: 188/529, loss: 0.08898897469043732
2023-01-23 01:02:10.995310: step: 192/529, loss: 0.3894866108894348
2023-01-23 01:02:12.123002: step: 196/529, loss: 0.0421941764652729
2023-01-23 01:02:13.238374: step: 200/529, loss: 0.0024327754508703947
2023-01-23 01:02:14.394045: step: 204/529, loss: 0.14827638864517212
2023-01-23 01:02:15.556286: step: 208/529, loss: 0.12349166721105576
2023-01-23 01:02:16.693549: step: 212/529, loss: 0.002152395434677601
2023-01-23 01:02:17.850277: step: 216/529, loss: 0.022513294592499733
2023-01-23 01:02:18.969379: step: 220/529, loss: 0.07244625687599182
2023-01-23 01:02:20.091675: step: 224/529, loss: 0.027306701987981796
2023-01-23 01:02:21.256915: step: 228/529, loss: 0.13446694612503052
2023-01-23 01:02:22.409556: step: 232/529, loss: 0.09044504910707474
2023-01-23 01:02:23.527591: step: 236/529, loss: 0.0581950917840004
2023-01-23 01:02:24.643477: step: 240/529, loss: 0.016605664044618607
2023-01-23 01:02:25.792878: step: 244/529, loss: 0.047232963144779205
2023-01-23 01:02:26.959165: step: 248/529, loss: 0.10404881089925766
2023-01-23 01:02:28.097121: step: 252/529, loss: 0.03578891605138779
2023-01-23 01:02:29.256844: step: 256/529, loss: 0.07694482803344727
2023-01-23 01:02:30.399813: step: 260/529, loss: 0.37140488624572754
2023-01-23 01:02:31.538399: step: 264/529, loss: 1.439310073852539
2023-01-23 01:02:32.682139: step: 268/529, loss: 0.02712078206241131
2023-01-23 01:02:33.803694: step: 272/529, loss: 0.034998226910829544
2023-01-23 01:02:34.936489: step: 276/529, loss: 0.011753225699067116
2023-01-23 01:02:36.066150: step: 280/529, loss: 0.21423006057739258
2023-01-23 01:02:37.230179: step: 284/529, loss: 0.1374889314174652
2023-01-23 01:02:38.327599: step: 288/529, loss: 0.024491310119628906
2023-01-23 01:02:39.473656: step: 292/529, loss: 0.005165863316506147
2023-01-23 01:02:40.614582: step: 296/529, loss: 0.1666305661201477
2023-01-23 01:02:41.734243: step: 300/529, loss: 0.012852216139435768
2023-01-23 01:02:42.885922: step: 304/529, loss: 0.03822169452905655
2023-01-23 01:02:44.024268: step: 308/529, loss: 0.06178493797779083
2023-01-23 01:02:45.184087: step: 312/529, loss: 0.04464082792401314
2023-01-23 01:02:46.355733: step: 316/529, loss: 0.03887185826897621
2023-01-23 01:02:47.523110: step: 320/529, loss: 0.07088928669691086
2023-01-23 01:02:48.658867: step: 324/529, loss: 0.06082601472735405
2023-01-23 01:02:49.810483: step: 328/529, loss: 0.6549112200737
2023-01-23 01:02:50.954687: step: 332/529, loss: 0.34678858518600464
2023-01-23 01:02:52.075943: step: 336/529, loss: 0.041258908808231354
2023-01-23 01:02:53.226561: step: 340/529, loss: 0.08799009025096893
2023-01-23 01:02:54.355774: step: 344/529, loss: 0.15504541993141174
2023-01-23 01:02:55.500869: step: 348/529, loss: 0.13681164383888245
2023-01-23 01:02:56.676720: step: 352/529, loss: 0.05576801300048828
2023-01-23 01:02:57.791570: step: 356/529, loss: 0.1775272786617279
2023-01-23 01:02:58.937087: step: 360/529, loss: 0.07686281204223633
2023-01-23 01:03:00.092372: step: 364/529, loss: 0.03118123859167099
2023-01-23 01:03:01.236847: step: 368/529, loss: 0.5335355997085571
2023-01-23 01:03:02.399387: step: 372/529, loss: 0.13557516038417816
2023-01-23 01:03:03.573761: step: 376/529, loss: 1.4577245712280273
2023-01-23 01:03:04.707965: step: 380/529, loss: 0.004966163542121649
2023-01-23 01:03:05.858893: step: 384/529, loss: 0.05156436562538147
2023-01-23 01:03:07.015042: step: 388/529, loss: 0.07223444432020187
2023-01-23 01:03:08.143043: step: 392/529, loss: 0.05274343490600586
2023-01-23 01:03:09.276421: step: 396/529, loss: 0.11118907481431961
2023-01-23 01:03:10.414216: step: 400/529, loss: 0.010439014062285423
2023-01-23 01:03:11.564205: step: 404/529, loss: 0.05379696190357208
2023-01-23 01:03:12.699568: step: 408/529, loss: 0.02378091961145401
2023-01-23 01:03:13.871705: step: 412/529, loss: 0.08376821875572205
2023-01-23 01:03:15.031410: step: 416/529, loss: 0.08409491181373596
2023-01-23 01:03:16.166693: step: 420/529, loss: 0.04938249662518501
2023-01-23 01:03:17.310773: step: 424/529, loss: 0.09655790030956268
2023-01-23 01:03:18.482482: step: 428/529, loss: 0.075322724878788
2023-01-23 01:03:19.599541: step: 432/529, loss: 0.15176595747470856
2023-01-23 01:03:20.742572: step: 436/529, loss: 0.04056701809167862
2023-01-23 01:03:21.907829: step: 440/529, loss: 0.08368691802024841
2023-01-23 01:03:23.051875: step: 444/529, loss: 0.01739966869354248
2023-01-23 01:03:24.217788: step: 448/529, loss: 0.029403090476989746
2023-01-23 01:03:25.340436: step: 452/529, loss: 0.07746572047472
2023-01-23 01:03:26.475938: step: 456/529, loss: 0.025560760870575905
2023-01-23 01:03:27.588386: step: 460/529, loss: 0.056169889867305756
2023-01-23 01:03:28.709546: step: 464/529, loss: 0.07014112174510956
2023-01-23 01:03:29.851415: step: 468/529, loss: 0.06594792008399963
2023-01-23 01:03:30.994006: step: 472/529, loss: 0.02782931551337242
2023-01-23 01:03:32.141344: step: 476/529, loss: 0.06167278066277504
2023-01-23 01:03:33.309169: step: 480/529, loss: 0.03837576135993004
2023-01-23 01:03:34.451485: step: 484/529, loss: 0.09715328365564346
2023-01-23 01:03:35.585357: step: 488/529, loss: 0.19760794937610626
2023-01-23 01:03:36.714830: step: 492/529, loss: 0.08687610924243927
2023-01-23 01:03:37.866829: step: 496/529, loss: 0.010358810424804688
2023-01-23 01:03:38.980912: step: 500/529, loss: 0.05630359798669815
2023-01-23 01:03:40.119468: step: 504/529, loss: 0.014113283716142178
2023-01-23 01:03:41.252298: step: 508/529, loss: 0.11378459632396698
2023-01-23 01:03:42.375238: step: 512/529, loss: 0.09627313911914825
2023-01-23 01:03:43.507151: step: 516/529, loss: 0.06669721752405167
2023-01-23 01:03:44.634172: step: 520/529, loss: 0.004662740044295788
2023-01-23 01:03:45.780412: step: 524/529, loss: 0.09451689571142197
2023-01-23 01:03:46.922266: step: 528/529, loss: 0.0363583080470562
2023-01-23 01:03:48.046359: step: 532/529, loss: 0.04375305026769638
2023-01-23 01:03:49.231826: step: 536/529, loss: 0.67576003074646
2023-01-23 01:03:50.345811: step: 540/529, loss: 0.10921287536621094
2023-01-23 01:03:51.469496: step: 544/529, loss: 0.05100860819220543
2023-01-23 01:03:52.589928: step: 548/529, loss: 0.0291900634765625
2023-01-23 01:03:53.719731: step: 552/529, loss: 0.048766233026981354
2023-01-23 01:03:54.863481: step: 556/529, loss: 1.0434304475784302
2023-01-23 01:03:56.015565: step: 560/529, loss: 0.018218040466308594
2023-01-23 01:03:57.175989: step: 564/529, loss: 0.04148721694946289
2023-01-23 01:03:58.290004: step: 568/529, loss: 0.06952936947345734
2023-01-23 01:03:59.464136: step: 572/529, loss: 0.07440491020679474
2023-01-23 01:04:00.597657: step: 576/529, loss: 0.2156505584716797
2023-01-23 01:04:01.747739: step: 580/529, loss: 0.07615752518177032
2023-01-23 01:04:02.890364: step: 584/529, loss: 0.08578047901391983
2023-01-23 01:04:04.049968: step: 588/529, loss: 0.061104025691747665
2023-01-23 01:04:05.197643: step: 592/529, loss: 0.5516277551651001
2023-01-23 01:04:06.335885: step: 596/529, loss: 0.05072822794318199
2023-01-23 01:04:07.468593: step: 600/529, loss: 0.09885187447071075
2023-01-23 01:04:08.614103: step: 604/529, loss: 0.015060711652040482
2023-01-23 01:04:09.756448: step: 608/529, loss: 0.0293439868837595
2023-01-23 01:04:10.926074: step: 612/529, loss: 0.08143343776464462
2023-01-23 01:04:12.044497: step: 616/529, loss: 0.03999634087085724
2023-01-23 01:04:13.192022: step: 620/529, loss: 0.19652004539966583
2023-01-23 01:04:14.346103: step: 624/529, loss: 0.06015019491314888
2023-01-23 01:04:15.472857: step: 628/529, loss: 0.13016852736473083
2023-01-23 01:04:16.608209: step: 632/529, loss: 0.19950413703918457
2023-01-23 01:04:17.750458: step: 636/529, loss: 0.01291036605834961
2023-01-23 01:04:18.879185: step: 640/529, loss: 0.0941803902387619
2023-01-23 01:04:19.998079: step: 644/529, loss: 0.16976594924926758
2023-01-23 01:04:21.109687: step: 648/529, loss: 0.08327942341566086
2023-01-23 01:04:22.253341: step: 652/529, loss: 0.12168264389038086
2023-01-23 01:04:23.387980: step: 656/529, loss: 0.41181421279907227
2023-01-23 01:04:24.535732: step: 660/529, loss: 0.11356215178966522
2023-01-23 01:04:25.690723: step: 664/529, loss: 0.21660451591014862
2023-01-23 01:04:26.820981: step: 668/529, loss: 0.11194296181201935
2023-01-23 01:04:27.954285: step: 672/529, loss: 0.021971512585878372
2023-01-23 01:04:29.096802: step: 676/529, loss: 0.19974097609519958
2023-01-23 01:04:30.250774: step: 680/529, loss: 0.07890134304761887
2023-01-23 01:04:31.385878: step: 684/529, loss: 0.03074016608297825
2023-01-23 01:04:32.508367: step: 688/529, loss: 0.0827782154083252
2023-01-23 01:04:33.677256: step: 692/529, loss: 0.004318189341574907
2023-01-23 01:04:34.828631: step: 696/529, loss: 0.009356451220810413
2023-01-23 01:04:35.950363: step: 700/529, loss: 0.035997629165649414
2023-01-23 01:04:37.078113: step: 704/529, loss: 0.030234530568122864
2023-01-23 01:04:38.196478: step: 708/529, loss: 0.11812038719654083
2023-01-23 01:04:39.358438: step: 712/529, loss: 0.0879218652844429
2023-01-23 01:04:40.505957: step: 716/529, loss: 0.09496765583753586
2023-01-23 01:04:41.670714: step: 720/529, loss: 0.017397737130522728
2023-01-23 01:04:42.793734: step: 724/529, loss: 0.018061447888612747
2023-01-23 01:04:43.932448: step: 728/529, loss: 0.16862984001636505
2023-01-23 01:04:45.069885: step: 732/529, loss: 0.1033288985490799
2023-01-23 01:04:46.222950: step: 736/529, loss: 0.07814265042543411
2023-01-23 01:04:47.351259: step: 740/529, loss: 0.0056092264130711555
2023-01-23 01:04:48.567684: step: 744/529, loss: 0.10409178584814072
2023-01-23 01:04:49.693796: step: 748/529, loss: 0.2466103583574295
2023-01-23 01:04:50.817128: step: 752/529, loss: 0.05389976501464844
2023-01-23 01:04:51.929261: step: 756/529, loss: 0.02763204649090767
2023-01-23 01:04:53.083455: step: 760/529, loss: 0.014043103903532028
2023-01-23 01:04:54.228737: step: 764/529, loss: 0.03315000608563423
2023-01-23 01:04:55.344648: step: 768/529, loss: 0.045502278953790665
2023-01-23 01:04:56.470707: step: 772/529, loss: 0.004908704664558172
2023-01-23 01:04:57.597356: step: 776/529, loss: 0.1298997849225998
2023-01-23 01:04:58.712512: step: 780/529, loss: 0.14381685853004456
2023-01-23 01:04:59.879025: step: 784/529, loss: 0.23429670929908752
2023-01-23 01:05:01.016992: step: 788/529, loss: 0.1267426460981369
2023-01-23 01:05:02.197167: step: 792/529, loss: 0.16323474049568176
2023-01-23 01:05:03.314219: step: 796/529, loss: 0.07715859264135361
2023-01-23 01:05:04.478079: step: 800/529, loss: 0.19973106682300568
2023-01-23 01:05:05.638681: step: 804/529, loss: 0.06991338729858398
2023-01-23 01:05:06.790772: step: 808/529, loss: 0.1399039775133133
2023-01-23 01:05:07.931249: step: 812/529, loss: 0.06861171871423721
2023-01-23 01:05:09.059555: step: 816/529, loss: 0.011025072075426579
2023-01-23 01:05:10.181506: step: 820/529, loss: 0.26301050186157227
2023-01-23 01:05:11.289515: step: 824/529, loss: 0.1727457046508789
2023-01-23 01:05:12.419496: step: 828/529, loss: 0.20113487541675568
2023-01-23 01:05:13.569496: step: 832/529, loss: 0.0834382027387619
2023-01-23 01:05:14.712184: step: 836/529, loss: 0.045196499675512314
2023-01-23 01:05:15.862920: step: 840/529, loss: 0.0984107106924057
2023-01-23 01:05:16.969090: step: 844/529, loss: 0.0543401725590229
2023-01-23 01:05:18.118898: step: 848/529, loss: 0.08001022785902023
2023-01-23 01:05:19.246366: step: 852/529, loss: 0.12925682961940765
2023-01-23 01:05:20.366203: step: 856/529, loss: 0.014968682080507278
2023-01-23 01:05:21.496990: step: 860/529, loss: 0.026435567066073418
2023-01-23 01:05:22.636223: step: 864/529, loss: 0.14768782258033752
2023-01-23 01:05:23.764121: step: 868/529, loss: 0.14447613060474396
2023-01-23 01:05:24.925748: step: 872/529, loss: 0.056848764419555664
2023-01-23 01:05:26.077003: step: 876/529, loss: 0.05720815435051918
2023-01-23 01:05:27.226462: step: 880/529, loss: 0.029929781332612038
2023-01-23 01:05:28.384098: step: 884/529, loss: 0.06685766577720642
2023-01-23 01:05:29.532254: step: 888/529, loss: 0.15352869033813477
2023-01-23 01:05:30.666190: step: 892/529, loss: 0.08006639778614044
2023-01-23 01:05:31.794441: step: 896/529, loss: 0.0016183853149414062
2023-01-23 01:05:32.918795: step: 900/529, loss: 0.043326523154973984
2023-01-23 01:05:34.032220: step: 904/529, loss: 0.12937259674072266
2023-01-23 01:05:35.186485: step: 908/529, loss: 0.06569299101829529
2023-01-23 01:05:36.376746: step: 912/529, loss: 0.016637422144412994
2023-01-23 01:05:37.511407: step: 916/529, loss: 0.08480334281921387
2023-01-23 01:05:38.658142: step: 920/529, loss: 0.05195445939898491
2023-01-23 01:05:39.783379: step: 924/529, loss: 0.028085611760616302
2023-01-23 01:05:40.944220: step: 928/529, loss: 0.023533152416348457
2023-01-23 01:05:42.089931: step: 932/529, loss: 0.017978288233280182
2023-01-23 01:05:43.274907: step: 936/529, loss: 0.02107391320168972
2023-01-23 01:05:44.397346: step: 940/529, loss: 0.046195317059755325
2023-01-23 01:05:45.528721: step: 944/529, loss: 0.004907131195068359
2023-01-23 01:05:46.669835: step: 948/529, loss: 0.08358898013830185
2023-01-23 01:05:47.815925: step: 952/529, loss: 0.04867877811193466
2023-01-23 01:05:48.935604: step: 956/529, loss: 0.1325804740190506
2023-01-23 01:05:50.075500: step: 960/529, loss: 0.2596103549003601
2023-01-23 01:05:51.223940: step: 964/529, loss: 0.10032215714454651
2023-01-23 01:05:52.352076: step: 968/529, loss: 0.01120071392506361
2023-01-23 01:05:53.505710: step: 972/529, loss: 0.141401007771492
2023-01-23 01:05:54.627365: step: 976/529, loss: 0.20454931259155273
2023-01-23 01:05:55.751134: step: 980/529, loss: 0.00998315867036581
2023-01-23 01:05:56.872633: step: 984/529, loss: 0.024337315931916237
2023-01-23 01:05:58.012476: step: 988/529, loss: 0.21922969818115234
2023-01-23 01:05:59.159325: step: 992/529, loss: 0.016145039349794388
2023-01-23 01:06:00.283841: step: 996/529, loss: 0.04762573540210724
2023-01-23 01:06:01.429195: step: 1000/529, loss: 0.0537199042737484
2023-01-23 01:06:02.560029: step: 1004/529, loss: 0.04943258687853813
2023-01-23 01:06:03.702736: step: 1008/529, loss: 0.028740502893924713
2023-01-23 01:06:04.827449: step: 1012/529, loss: 0.21890640258789062
2023-01-23 01:06:05.978805: step: 1016/529, loss: 0.13252533972263336
2023-01-23 01:06:07.133794: step: 1020/529, loss: 0.05497632175683975
2023-01-23 01:06:08.283033: step: 1024/529, loss: 0.07800378650426865
2023-01-23 01:06:09.432656: step: 1028/529, loss: 0.02326517179608345
2023-01-23 01:06:10.567453: step: 1032/529, loss: 0.00707588205114007
2023-01-23 01:06:11.696118: step: 1036/529, loss: 0.2861449718475342
2023-01-23 01:06:12.828257: step: 1040/529, loss: 0.020989418029785156
2023-01-23 01:06:13.962000: step: 1044/529, loss: 0.07055123150348663
2023-01-23 01:06:15.094118: step: 1048/529, loss: 0.10883531719446182
2023-01-23 01:06:16.217713: step: 1052/529, loss: 0.018304063007235527
2023-01-23 01:06:17.364815: step: 1056/529, loss: 0.7230802774429321
2023-01-23 01:06:18.490574: step: 1060/529, loss: 0.14433537423610687
2023-01-23 01:06:19.600701: step: 1064/529, loss: 0.0849699079990387
2023-01-23 01:06:20.709359: step: 1068/529, loss: 0.2437925785779953
2023-01-23 01:06:21.845071: step: 1072/529, loss: 0.09633298218250275
2023-01-23 01:06:22.998047: step: 1076/529, loss: 0.0748809278011322
2023-01-23 01:06:24.133162: step: 1080/529, loss: 0.051718711853027344
2023-01-23 01:06:25.271811: step: 1084/529, loss: 0.1578083038330078
2023-01-23 01:06:26.405194: step: 1088/529, loss: 0.01725740358233452
2023-01-23 01:06:27.551802: step: 1092/529, loss: 0.1236649602651596
2023-01-23 01:06:28.698500: step: 1096/529, loss: 0.0022564411628991365
2023-01-23 01:06:29.816906: step: 1100/529, loss: 0.03927011415362358
2023-01-23 01:06:30.947140: step: 1104/529, loss: 0.12160759419202805
2023-01-23 01:06:32.066810: step: 1108/529, loss: 0.013162421993911266
2023-01-23 01:06:33.231960: step: 1112/529, loss: 0.045484352856874466
2023-01-23 01:06:34.339484: step: 1116/529, loss: 0.04290657117962837
2023-01-23 01:06:35.468401: step: 1120/529, loss: 0.08926299214363098
2023-01-23 01:06:36.611336: step: 1124/529, loss: 0.04589691385626793
2023-01-23 01:06:37.743419: step: 1128/529, loss: 0.05873260274529457
2023-01-23 01:06:38.891056: step: 1132/529, loss: 0.4263211190700531
2023-01-23 01:06:40.041936: step: 1136/529, loss: 0.022725248709321022
2023-01-23 01:06:41.194556: step: 1140/529, loss: 0.08342447131872177
2023-01-23 01:06:42.309387: step: 1144/529, loss: 0.05119381099939346
2023-01-23 01:06:43.445860: step: 1148/529, loss: 0.0746581107378006
2023-01-23 01:06:44.575008: step: 1152/529, loss: 0.012243843637406826
2023-01-23 01:06:45.692087: step: 1156/529, loss: 0.017125988379120827
2023-01-23 01:06:46.851642: step: 1160/529, loss: 0.12133846431970596
2023-01-23 01:06:47.983730: step: 1164/529, loss: 0.1178840696811676
2023-01-23 01:06:49.133024: step: 1168/529, loss: 0.028528405353426933
2023-01-23 01:06:50.275810: step: 1172/529, loss: 0.11759261786937714
2023-01-23 01:06:51.396071: step: 1176/529, loss: 0.003613757900893688
2023-01-23 01:06:52.544048: step: 1180/529, loss: 0.049944546073675156
2023-01-23 01:06:53.685523: step: 1184/529, loss: 0.023375703021883965
2023-01-23 01:06:54.817591: step: 1188/529, loss: 0.10626917332410812
2023-01-23 01:06:55.948925: step: 1192/529, loss: 0.32783156633377075
2023-01-23 01:06:57.077731: step: 1196/529, loss: 0.0784115344285965
2023-01-23 01:06:58.235856: step: 1200/529, loss: 0.3225267231464386
2023-01-23 01:06:59.357665: step: 1204/529, loss: 0.04196042940020561
2023-01-23 01:07:00.491934: step: 1208/529, loss: 0.10783758759498596
2023-01-23 01:07:01.634665: step: 1212/529, loss: 0.035337068140506744
2023-01-23 01:07:02.770741: step: 1216/529, loss: 0.37195196747779846
2023-01-23 01:07:03.896775: step: 1220/529, loss: 0.11980586498975754
2023-01-23 01:07:05.052143: step: 1224/529, loss: 0.09923744201660156
2023-01-23 01:07:06.196832: step: 1228/529, loss: 0.05331268534064293
2023-01-23 01:07:07.294263: step: 1232/529, loss: 0.06574630737304688
2023-01-23 01:07:08.416873: step: 1236/529, loss: 0.12260589748620987
2023-01-23 01:07:09.524091: step: 1240/529, loss: 0.14013658463954926
2023-01-23 01:07:10.647929: step: 1244/529, loss: 0.10244853794574738
2023-01-23 01:07:11.781223: step: 1248/529, loss: 0.05360110104084015
2023-01-23 01:07:12.937665: step: 1252/529, loss: 0.11024399101734161
2023-01-23 01:07:14.069105: step: 1256/529, loss: 0.10939264297485352
2023-01-23 01:07:15.195685: step: 1260/529, loss: 0.2813161015510559
2023-01-23 01:07:16.344073: step: 1264/529, loss: 0.4367527961730957
2023-01-23 01:07:17.490850: step: 1268/529, loss: 0.14290466904640198
2023-01-23 01:07:18.631057: step: 1272/529, loss: 0.08297085762023926
2023-01-23 01:07:19.784485: step: 1276/529, loss: 0.06573257595300674
2023-01-23 01:07:20.964783: step: 1280/529, loss: 0.11522331833839417
2023-01-23 01:07:22.118365: step: 1284/529, loss: 0.09795427322387695
2023-01-23 01:07:23.249668: step: 1288/529, loss: 0.02776818349957466
2023-01-23 01:07:24.393707: step: 1292/529, loss: 0.0947689414024353
2023-01-23 01:07:25.517135: step: 1296/529, loss: 0.169599249958992
2023-01-23 01:07:26.628135: step: 1300/529, loss: 0.04477834701538086
2023-01-23 01:07:27.771031: step: 1304/529, loss: 0.0932869017124176
2023-01-23 01:07:28.904772: step: 1308/529, loss: 0.00855474453419447
2023-01-23 01:07:30.054332: step: 1312/529, loss: 0.028590798377990723
2023-01-23 01:07:31.232188: step: 1316/529, loss: 0.08530931919813156
2023-01-23 01:07:32.377103: step: 1320/529, loss: 0.020514965057373047
2023-01-23 01:07:33.528254: step: 1324/529, loss: 0.045728109776973724
2023-01-23 01:07:34.669381: step: 1328/529, loss: 0.07422919571399689
2023-01-23 01:07:35.799482: step: 1332/529, loss: 0.027492430061101913
2023-01-23 01:07:36.927245: step: 1336/529, loss: 0.16383209824562073
2023-01-23 01:07:38.045661: step: 1340/529, loss: 0.034011900424957275
2023-01-23 01:07:39.191924: step: 1344/529, loss: 0.04374532774090767
2023-01-23 01:07:40.314869: step: 1348/529, loss: 0.06766939163208008
2023-01-23 01:07:41.454225: step: 1352/529, loss: 0.043773747980594635
2023-01-23 01:07:42.594774: step: 1356/529, loss: 0.08694286644458771
2023-01-23 01:07:43.722819: step: 1360/529, loss: 0.05438380315899849
2023-01-23 01:07:44.865236: step: 1364/529, loss: 0.05547008663415909
2023-01-23 01:07:46.018633: step: 1368/529, loss: 0.07337551563978195
2023-01-23 01:07:47.175704: step: 1372/529, loss: 0.05067472532391548
2023-01-23 01:07:48.294448: step: 1376/529, loss: 0.03581256791949272
2023-01-23 01:07:49.440752: step: 1380/529, loss: 0.009047317318618298
2023-01-23 01:07:50.565623: step: 1384/529, loss: 0.01960754580795765
2023-01-23 01:07:51.698313: step: 1388/529, loss: 0.07275829464197159
2023-01-23 01:07:52.816940: step: 1392/529, loss: 0.04798593744635582
2023-01-23 01:07:53.956605: step: 1396/529, loss: 0.08816394954919815
2023-01-23 01:07:55.098701: step: 1400/529, loss: 0.15449228882789612
2023-01-23 01:07:56.222440: step: 1404/529, loss: 0.02014179341495037
2023-01-23 01:07:57.357994: step: 1408/529, loss: 0.10159559547901154
2023-01-23 01:07:58.500257: step: 1412/529, loss: 0.026207923889160156
2023-01-23 01:07:59.630061: step: 1416/529, loss: 0.03822488710284233
2023-01-23 01:08:00.762124: step: 1420/529, loss: 0.16318555176258087
2023-01-23 01:08:01.903723: step: 1424/529, loss: 0.009918594732880592
2023-01-23 01:08:03.035424: step: 1428/529, loss: 0.026558782905340195
2023-01-23 01:08:04.146879: step: 1432/529, loss: 0.03461778163909912
2023-01-23 01:08:05.264253: step: 1436/529, loss: 0.11733609437942505
2023-01-23 01:08:06.386394: step: 1440/529, loss: 0.07947101444005966
2023-01-23 01:08:07.539092: step: 1444/529, loss: 0.0937531441450119
2023-01-23 01:08:08.688750: step: 1448/529, loss: 0.08047189563512802
2023-01-23 01:08:09.821314: step: 1452/529, loss: 0.007455253973603249
2023-01-23 01:08:10.974327: step: 1456/529, loss: 0.15630942583084106
2023-01-23 01:08:12.132591: step: 1460/529, loss: 0.09452686458826065
2023-01-23 01:08:13.279560: step: 1464/529, loss: 0.0605742409825325
2023-01-23 01:08:14.392341: step: 1468/529, loss: 0.10759225487709045
2023-01-23 01:08:15.516155: step: 1472/529, loss: 0.4065554141998291
2023-01-23 01:08:16.649643: step: 1476/529, loss: 0.08842973411083221
2023-01-23 01:08:17.761715: step: 1480/529, loss: 0.6630769371986389
2023-01-23 01:08:18.909268: step: 1484/529, loss: 0.01212625578045845
2023-01-23 01:08:20.017081: step: 1488/529, loss: 0.07003974914550781
2023-01-23 01:08:21.164979: step: 1492/529, loss: 0.06025858223438263
2023-01-23 01:08:22.300033: step: 1496/529, loss: 0.08622658252716064
2023-01-23 01:08:23.448238: step: 1500/529, loss: 0.010400105267763138
2023-01-23 01:08:24.602450: step: 1504/529, loss: 0.4117165803909302
2023-01-23 01:08:25.733583: step: 1508/529, loss: 0.028048038482666016
2023-01-23 01:08:26.893136: step: 1512/529, loss: 0.09052066504955292
2023-01-23 01:08:27.992607: step: 1516/529, loss: 0.02193927764892578
2023-01-23 01:08:29.150353: step: 1520/529, loss: 0.027385331690311432
2023-01-23 01:08:30.278981: step: 1524/529, loss: 0.0029133083298802376
2023-01-23 01:08:31.420577: step: 1528/529, loss: 0.10590820014476776
2023-01-23 01:08:32.518899: step: 1532/529, loss: 0.0780634880065918
2023-01-23 01:08:33.634731: step: 1536/529, loss: 0.007105112075805664
2023-01-23 01:08:34.772335: step: 1540/529, loss: 0.06804361194372177
2023-01-23 01:08:35.905782: step: 1544/529, loss: 0.08576307445764542
2023-01-23 01:08:37.040061: step: 1548/529, loss: 0.042864322662353516
2023-01-23 01:08:38.199949: step: 1552/529, loss: 0.0626750960946083
2023-01-23 01:08:39.332141: step: 1556/529, loss: 0.058167554438114166
2023-01-23 01:08:40.469487: step: 1560/529, loss: 0.03959827497601509
2023-01-23 01:08:41.588598: step: 1564/529, loss: 0.009998607449233532
2023-01-23 01:08:42.737910: step: 1568/529, loss: 0.16010750830173492
2023-01-23 01:08:43.913883: step: 1572/529, loss: 0.05658111721277237
2023-01-23 01:08:45.032246: step: 1576/529, loss: 0.0739203467965126
2023-01-23 01:08:46.167839: step: 1580/529, loss: 0.10778641700744629
2023-01-23 01:08:47.288044: step: 1584/529, loss: 0.0023717046715319157
2023-01-23 01:08:48.430365: step: 1588/529, loss: 0.0529102087020874
2023-01-23 01:08:49.554966: step: 1592/529, loss: 0.09331293404102325
2023-01-23 01:08:50.700598: step: 1596/529, loss: 0.036615852266550064
2023-01-23 01:08:51.834926: step: 1600/529, loss: 0.0989147201180458
2023-01-23 01:08:52.967858: step: 1604/529, loss: 0.14255276322364807
2023-01-23 01:08:54.118105: step: 1608/529, loss: 0.11164913326501846
2023-01-23 01:08:55.275702: step: 1612/529, loss: 0.36577796936035156
2023-01-23 01:08:56.416279: step: 1616/529, loss: 0.27770549058914185
2023-01-23 01:08:57.558720: step: 1620/529, loss: 0.07905597239732742
2023-01-23 01:08:58.672395: step: 1624/529, loss: 0.11833696067333221
2023-01-23 01:08:59.809284: step: 1628/529, loss: 0.06645546108484268
2023-01-23 01:09:00.945930: step: 1632/529, loss: 0.01667703501880169
2023-01-23 01:09:02.052852: step: 1636/529, loss: 0.04961814731359482
2023-01-23 01:09:03.165177: step: 1640/529, loss: 0.028949355706572533
2023-01-23 01:09:04.289849: step: 1644/529, loss: 0.5641604661941528
2023-01-23 01:09:05.440098: step: 1648/529, loss: 0.0822833999991417
2023-01-23 01:09:06.608018: step: 1652/529, loss: 0.12084569782018661
2023-01-23 01:09:07.766037: step: 1656/529, loss: 0.08424148708581924
2023-01-23 01:09:08.931444: step: 1660/529, loss: 0.24304667115211487
2023-01-23 01:09:10.093499: step: 1664/529, loss: 0.04488034173846245
2023-01-23 01:09:11.228461: step: 1668/529, loss: 0.030668700113892555
2023-01-23 01:09:12.392602: step: 1672/529, loss: 0.11166906356811523
2023-01-23 01:09:13.520916: step: 1676/529, loss: 0.05258913338184357
2023-01-23 01:09:14.647709: step: 1680/529, loss: 0.03966110944747925
2023-01-23 01:09:15.766996: step: 1684/529, loss: 0.05706949159502983
2023-01-23 01:09:16.902703: step: 1688/529, loss: 0.08502653241157532
2023-01-23 01:09:18.035575: step: 1692/529, loss: 0.012454413808882236
2023-01-23 01:09:19.165396: step: 1696/529, loss: 0.12608790397644043
2023-01-23 01:09:20.328322: step: 1700/529, loss: 0.062413401901721954
2023-01-23 01:09:21.482439: step: 1704/529, loss: 0.012491869740188122
2023-01-23 01:09:22.609594: step: 1708/529, loss: 0.06444601714611053
2023-01-23 01:09:23.752495: step: 1712/529, loss: 0.10224554687738419
2023-01-23 01:09:24.918558: step: 1716/529, loss: 0.2857908308506012
2023-01-23 01:09:26.087293: step: 1720/529, loss: 0.02364215813577175
2023-01-23 01:09:27.322504: step: 1724/529, loss: 0.050722405314445496
2023-01-23 01:09:28.475631: step: 1728/529, loss: 0.05851469188928604
2023-01-23 01:09:29.621845: step: 1732/529, loss: 0.036136794835329056
2023-01-23 01:09:30.770192: step: 1736/529, loss: 0.005303668789565563
2023-01-23 01:09:31.895805: step: 1740/529, loss: 0.07457681000232697
2023-01-23 01:09:33.045400: step: 1744/529, loss: 0.018906213343143463
2023-01-23 01:09:34.208631: step: 1748/529, loss: 0.10388734191656113
2023-01-23 01:09:35.337269: step: 1752/529, loss: 0.04726286232471466
2023-01-23 01:09:36.461111: step: 1756/529, loss: 0.01022949256002903
2023-01-23 01:09:37.602240: step: 1760/529, loss: 0.06159830093383789
2023-01-23 01:09:38.727692: step: 1764/529, loss: 0.1197529286146164
2023-01-23 01:09:39.854204: step: 1768/529, loss: 0.0792245864868164
2023-01-23 01:09:40.982604: step: 1772/529, loss: 0.02394075319170952
2023-01-23 01:09:42.132430: step: 1776/529, loss: 0.08460597693920135
2023-01-23 01:09:43.249120: step: 1780/529, loss: 0.04512443393468857
2023-01-23 01:09:44.403684: step: 1784/529, loss: 0.05376272276043892
2023-01-23 01:09:45.567348: step: 1788/529, loss: 0.10175077617168427
2023-01-23 01:09:46.714315: step: 1792/529, loss: 0.006239033304154873
2023-01-23 01:09:47.826695: step: 1796/529, loss: 0.024085475131869316
2023-01-23 01:09:49.005287: step: 1800/529, loss: 0.12385706603527069
2023-01-23 01:09:50.169336: step: 1804/529, loss: 0.1836889386177063
2023-01-23 01:09:51.285253: step: 1808/529, loss: 0.013002490624785423
2023-01-23 01:09:52.417716: step: 1812/529, loss: 0.2278801053762436
2023-01-23 01:09:53.568656: step: 1816/529, loss: 0.07473068684339523
2023-01-23 01:09:54.725110: step: 1820/529, loss: 0.16262513399124146
2023-01-23 01:09:55.879112: step: 1824/529, loss: 0.031132889911532402
2023-01-23 01:09:57.018139: step: 1828/529, loss: 0.018962860107421875
2023-01-23 01:09:58.142273: step: 1832/529, loss: 0.1415359079837799
2023-01-23 01:09:59.273226: step: 1836/529, loss: 0.011631202884018421
2023-01-23 01:10:00.418626: step: 1840/529, loss: 0.009527111425995827
2023-01-23 01:10:01.580874: step: 1844/529, loss: 0.06211052089929581
2023-01-23 01:10:02.712039: step: 1848/529, loss: 0.02534055896103382
2023-01-23 01:10:03.855179: step: 1852/529, loss: 0.056978702545166016
2023-01-23 01:10:04.987072: step: 1856/529, loss: 0.03632063791155815
2023-01-23 01:10:06.148490: step: 1860/529, loss: 0.6903088688850403
2023-01-23 01:10:07.268890: step: 1864/529, loss: 0.13236571848392487
2023-01-23 01:10:08.410452: step: 1868/529, loss: 0.04093503952026367
2023-01-23 01:10:09.529077: step: 1872/529, loss: 0.09035070240497589
2023-01-23 01:10:10.674585: step: 1876/529, loss: 0.1581283062696457
2023-01-23 01:10:11.810749: step: 1880/529, loss: 0.025211524218320847
2023-01-23 01:10:12.940825: step: 1884/529, loss: 0.26080742478370667
2023-01-23 01:10:14.085365: step: 1888/529, loss: 0.5973278880119324
2023-01-23 01:10:15.223461: step: 1892/529, loss: 0.04400506243109703
2023-01-23 01:10:16.383009: step: 1896/529, loss: 0.05986309424042702
2023-01-23 01:10:17.506294: step: 1900/529, loss: 0.051085613667964935
2023-01-23 01:10:18.659044: step: 1904/529, loss: 0.011987018398940563
2023-01-23 01:10:19.791419: step: 1908/529, loss: 0.15386730432510376
2023-01-23 01:10:20.940764: step: 1912/529, loss: 0.01692638359963894
2023-01-23 01:10:22.077843: step: 1916/529, loss: 0.12070226669311523
2023-01-23 01:10:23.220720: step: 1920/529, loss: 0.016756916418671608
2023-01-23 01:10:24.369917: step: 1924/529, loss: 0.022647477686405182
2023-01-23 01:10:25.551876: step: 1928/529, loss: 0.13211488723754883
2023-01-23 01:10:26.650238: step: 1932/529, loss: 0.01573462411761284
2023-01-23 01:10:27.759703: step: 1936/529, loss: 0.039135657250881195
2023-01-23 01:10:28.895001: step: 1940/529, loss: 0.18346408009529114
2023-01-23 01:10:30.032840: step: 1944/529, loss: 0.12774324417114258
2023-01-23 01:10:31.176738: step: 1948/529, loss: 0.003621053881943226
2023-01-23 01:10:32.362576: step: 1952/529, loss: 0.06587381660938263
2023-01-23 01:10:33.522020: step: 1956/529, loss: 0.0050697922706604
2023-01-23 01:10:34.689887: step: 1960/529, loss: 0.05135393515229225
2023-01-23 01:10:35.848969: step: 1964/529, loss: 0.0958009734749794
2023-01-23 01:10:36.974542: step: 1968/529, loss: 0.0972389206290245
2023-01-23 01:10:38.111748: step: 1972/529, loss: 0.02541046030819416
2023-01-23 01:10:39.261065: step: 1976/529, loss: 0.22043271362781525
2023-01-23 01:10:40.400804: step: 1980/529, loss: 0.1106606274843216
2023-01-23 01:10:41.540363: step: 1984/529, loss: 0.020216751843690872
2023-01-23 01:10:42.692862: step: 1988/529, loss: 0.02553238905966282
2023-01-23 01:10:43.824459: step: 1992/529, loss: 0.13589835166931152
2023-01-23 01:10:44.996589: step: 1996/529, loss: 0.07527312636375427
2023-01-23 01:10:46.128160: step: 2000/529, loss: 0.010635661892592907
2023-01-23 01:10:47.242136: step: 2004/529, loss: 0.06710109859704971
2023-01-23 01:10:48.378569: step: 2008/529, loss: 0.04665551334619522
2023-01-23 01:10:49.544398: step: 2012/529, loss: 0.00983352679759264
2023-01-23 01:10:50.710006: step: 2016/529, loss: 0.12732791900634766
2023-01-23 01:10:51.871152: step: 2020/529, loss: 0.038633156567811966
2023-01-23 01:10:53.031293: step: 2024/529, loss: 0.023262787610292435
2023-01-23 01:10:54.168695: step: 2028/529, loss: 0.06486359238624573
2023-01-23 01:10:55.320117: step: 2032/529, loss: 0.029662322252988815
2023-01-23 01:10:56.470797: step: 2036/529, loss: 0.08603730797767639
2023-01-23 01:10:57.609126: step: 2040/529, loss: 0.050253868103027344
2023-01-23 01:10:58.740296: step: 2044/529, loss: 0.06838864833116531
2023-01-23 01:10:59.898536: step: 2048/529, loss: 0.18926943838596344
2023-01-23 01:11:01.070151: step: 2052/529, loss: 0.05205736309289932
2023-01-23 01:11:02.186834: step: 2056/529, loss: 0.051969338208436966
2023-01-23 01:11:03.312955: step: 2060/529, loss: 0.014870643615722656
2023-01-23 01:11:04.444828: step: 2064/529, loss: 0.027440406382083893
2023-01-23 01:11:05.586523: step: 2068/529, loss: 0.004777717869728804
2023-01-23 01:11:06.756483: step: 2072/529, loss: 0.17016807198524475
2023-01-23 01:11:07.923797: step: 2076/529, loss: 0.244316965341568
2023-01-23 01:11:09.102475: step: 2080/529, loss: 0.04060692712664604
2023-01-23 01:11:10.270512: step: 2084/529, loss: 0.05943470075726509
2023-01-23 01:11:11.425448: step: 2088/529, loss: 0.1215766966342926
2023-01-23 01:11:12.555480: step: 2092/529, loss: 0.05379905924201012
2023-01-23 01:11:13.691589: step: 2096/529, loss: 0.008314895443618298
2023-01-23 01:11:14.843497: step: 2100/529, loss: 0.005596065428107977
2023-01-23 01:11:16.034048: step: 2104/529, loss: 0.08714733272790909
2023-01-23 01:11:17.214170: step: 2108/529, loss: 0.16617390513420105
2023-01-23 01:11:18.332849: step: 2112/529, loss: 0.03994948789477348
2023-01-23 01:11:19.489041: step: 2116/529, loss: 0.055564116686582565
==================================================
Loss: 0.102
--------------------
Dev: {'event': {'p': 0.6336633663366337, 'r': 0.7669773635153129, 'f1': 0.6939759036144578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6261325703385789, 'r': 0.7607184241019699, 'f1': 0.686895108553492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6458333333333334, 'r': 0.49206349206349204, 'f1': 0.5585585585585586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.5, 'r': 0.5277777777777778, 'f1': 0.5135135135135136}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:12:00.960019: step: 4/529, loss: 0.06526575237512589
2023-01-23 01:12:02.126783: step: 8/529, loss: 0.05167045444250107
2023-01-23 01:12:03.278337: step: 12/529, loss: 0.034413862973451614
2023-01-23 01:12:04.394331: step: 16/529, loss: 0.1399787962436676
2023-01-23 01:12:05.550329: step: 20/529, loss: 0.024865586310625076
2023-01-23 01:12:06.715632: step: 24/529, loss: 0.014812469482421875
2023-01-23 01:12:07.898462: step: 28/529, loss: 0.07330341637134552
2023-01-23 01:12:09.018821: step: 32/529, loss: 0.007396126165986061
2023-01-23 01:12:10.146390: step: 36/529, loss: 0.008503532037138939
2023-01-23 01:12:11.264983: step: 40/529, loss: 0.001967144198715687
2023-01-23 01:12:12.381270: step: 44/529, loss: 0.049854375422000885
2023-01-23 01:12:13.493844: step: 48/529, loss: 0.03765811771154404
2023-01-23 01:12:14.636439: step: 52/529, loss: 0.025577712804079056
2023-01-23 01:12:15.780030: step: 56/529, loss: 0.21424388885498047
2023-01-23 01:12:16.897217: step: 60/529, loss: 0.021035075187683105
2023-01-23 01:12:18.034524: step: 64/529, loss: 0.010951709933578968
2023-01-23 01:12:19.141663: step: 68/529, loss: 0.0076386453583836555
2023-01-23 01:12:20.280951: step: 72/529, loss: 0.07369747757911682
2023-01-23 01:12:21.411123: step: 76/529, loss: 0.02851381152868271
2023-01-23 01:12:22.537910: step: 80/529, loss: 0.6189826130867004
2023-01-23 01:12:23.659990: step: 84/529, loss: 0.04281141981482506
2023-01-23 01:12:24.837920: step: 88/529, loss: 0.14122648537158966
2023-01-23 01:12:25.963237: step: 92/529, loss: 0.1223832219839096
2023-01-23 01:12:27.093898: step: 96/529, loss: 0.07379761338233948
2023-01-23 01:12:28.230869: step: 100/529, loss: 0.06322650611400604
2023-01-23 01:12:29.343120: step: 104/529, loss: 0.1651563197374344
2023-01-23 01:12:30.450658: step: 108/529, loss: 0.08313963562250137
2023-01-23 01:12:31.596710: step: 112/529, loss: 0.5426965951919556
2023-01-23 01:12:32.774592: step: 116/529, loss: 0.046189069747924805
2023-01-23 01:12:33.898723: step: 120/529, loss: 0.0735151618719101
2023-01-23 01:12:35.053784: step: 124/529, loss: 0.11353117227554321
2023-01-23 01:12:36.200119: step: 128/529, loss: 0.048750780522823334
2023-01-23 01:12:37.357045: step: 132/529, loss: 0.015401840209960938
2023-01-23 01:12:38.468492: step: 136/529, loss: 0.06352796405553818
2023-01-23 01:12:39.615584: step: 140/529, loss: 0.03906898573040962
2023-01-23 01:12:40.762846: step: 144/529, loss: 0.12227649986743927
2023-01-23 01:12:41.907829: step: 148/529, loss: 0.07670503109693527
2023-01-23 01:12:43.051370: step: 152/529, loss: 0.004206561949104071
2023-01-23 01:12:44.193545: step: 156/529, loss: 0.40554171800613403
2023-01-23 01:12:45.359884: step: 160/529, loss: 0.018439387902617455
2023-01-23 01:12:46.477121: step: 164/529, loss: 0.06138668209314346
2023-01-23 01:12:47.642203: step: 168/529, loss: 0.023206520825624466
2023-01-23 01:12:48.758600: step: 172/529, loss: 9.193420555675402e-05
2023-01-23 01:12:49.910452: step: 176/529, loss: 0.07504411041736603
2023-01-23 01:12:51.031796: step: 180/529, loss: 0.07717952877283096
2023-01-23 01:12:52.166285: step: 184/529, loss: 0.004258966539055109
2023-01-23 01:12:53.313955: step: 188/529, loss: 0.0023467065766453743
2023-01-23 01:12:54.456524: step: 192/529, loss: 0.056708622723817825
2023-01-23 01:12:55.603110: step: 196/529, loss: 0.08248114585876465
2023-01-23 01:12:56.750317: step: 200/529, loss: 0.08621253818273544
2023-01-23 01:12:57.904988: step: 204/529, loss: 0.09565964341163635
2023-01-23 01:12:59.013421: step: 208/529, loss: 0.14741650223731995
2023-01-23 01:13:00.126933: step: 212/529, loss: 0.03267812728881836
2023-01-23 01:13:01.261960: step: 216/529, loss: 0.10312697291374207
2023-01-23 01:13:02.423168: step: 220/529, loss: 0.0288193728774786
2023-01-23 01:13:03.534573: step: 224/529, loss: 0.03588409349322319
2023-01-23 01:13:04.664558: step: 228/529, loss: 0.021371817216277122
2023-01-23 01:13:05.817694: step: 232/529, loss: 0.040978334844112396
2023-01-23 01:13:06.992229: step: 236/529, loss: 0.0374603271484375
2023-01-23 01:13:08.128428: step: 240/529, loss: 0.08695602416992188
2023-01-23 01:13:09.269632: step: 244/529, loss: 0.03203125298023224
2023-01-23 01:13:10.426643: step: 248/529, loss: 0.012463569641113281
2023-01-23 01:13:11.568926: step: 252/529, loss: 0.10618915408849716
2023-01-23 01:13:12.710009: step: 256/529, loss: 0.11084241420030594
2023-01-23 01:13:13.836935: step: 260/529, loss: 0.059847354888916016
2023-01-23 01:13:14.931418: step: 264/529, loss: 0.7478528022766113
2023-01-23 01:13:16.071128: step: 268/529, loss: 0.21398086845874786
2023-01-23 01:13:17.207599: step: 272/529, loss: 0.055710986256599426
2023-01-23 01:13:18.351233: step: 276/529, loss: 0.07299118489027023
2023-01-23 01:13:19.479247: step: 280/529, loss: 0.03334188461303711
2023-01-23 01:13:20.616994: step: 284/529, loss: 0.038349542766809464
2023-01-23 01:13:21.757083: step: 288/529, loss: 0.09635090827941895
2023-01-23 01:13:22.907838: step: 292/529, loss: 0.0373292937874794
2023-01-23 01:13:24.056605: step: 296/529, loss: 0.12191420048475266
2023-01-23 01:13:25.197500: step: 300/529, loss: 0.07888355106115341
2023-01-23 01:13:26.328335: step: 304/529, loss: 0.8172504305839539
2023-01-23 01:13:27.457140: step: 308/529, loss: 0.030851364135742188
2023-01-23 01:13:28.575126: step: 312/529, loss: 0.03205299377441406
2023-01-23 01:13:29.699112: step: 316/529, loss: 0.10401568561792374
2023-01-23 01:13:30.865474: step: 320/529, loss: 0.11300201714038849
2023-01-23 01:13:32.012189: step: 324/529, loss: 0.034682657569646835
2023-01-23 01:13:33.162926: step: 328/529, loss: 0.02340526506304741
2023-01-23 01:13:34.326997: step: 332/529, loss: 0.1827675849199295
2023-01-23 01:13:35.472219: step: 336/529, loss: 0.0405457504093647
2023-01-23 01:13:36.607865: step: 340/529, loss: 0.026951981708407402
2023-01-23 01:13:37.744898: step: 344/529, loss: 0.05903301388025284
2023-01-23 01:13:38.897971: step: 348/529, loss: 0.06084003672003746
2023-01-23 01:13:40.055568: step: 352/529, loss: 0.3267245292663574
2023-01-23 01:13:41.207147: step: 356/529, loss: 0.02098846435546875
2023-01-23 01:13:42.341627: step: 360/529, loss: 0.06029319763183594
2023-01-23 01:13:43.484512: step: 364/529, loss: 0.08244076371192932
2023-01-23 01:13:44.647816: step: 368/529, loss: 0.0160688403993845
2023-01-23 01:13:45.810548: step: 372/529, loss: 0.06547784805297852
2023-01-23 01:13:46.939341: step: 376/529, loss: 0.006495666690170765
2023-01-23 01:13:48.054552: step: 380/529, loss: 0.04197130352258682
2023-01-23 01:13:49.191065: step: 384/529, loss: 0.025869369506835938
2023-01-23 01:13:50.363357: step: 388/529, loss: 0.0416143462061882
2023-01-23 01:13:51.485311: step: 392/529, loss: 0.03596305847167969
2023-01-23 01:13:52.611636: step: 396/529, loss: 0.12299247086048126
2023-01-23 01:13:53.790012: step: 400/529, loss: 0.11730728298425674
2023-01-23 01:13:54.923358: step: 404/529, loss: 0.1666286438703537
2023-01-23 01:13:56.085683: step: 408/529, loss: 0.01699056662619114
2023-01-23 01:13:57.212786: step: 412/529, loss: 0.13448619842529297
2023-01-23 01:13:58.331535: step: 416/529, loss: 0.05790691450238228
2023-01-23 01:13:59.495692: step: 420/529, loss: 0.0315336212515831
2023-01-23 01:14:00.624268: step: 424/529, loss: 0.022933436557650566
2023-01-23 01:14:01.761262: step: 428/529, loss: 0.035239316523075104
2023-01-23 01:14:02.895786: step: 432/529, loss: 0.03359203413128853
2023-01-23 01:14:04.024106: step: 436/529, loss: 0.07688503712415695
2023-01-23 01:14:05.149785: step: 440/529, loss: 0.002285003662109375
2023-01-23 01:14:06.283355: step: 444/529, loss: 0.022823907434940338
2023-01-23 01:14:07.413671: step: 448/529, loss: 0.45081567764282227
2023-01-23 01:14:08.549018: step: 452/529, loss: 1.2924983501434326
2023-01-23 01:14:09.665430: step: 456/529, loss: 0.05244283378124237
2023-01-23 01:14:10.796852: step: 460/529, loss: 0.030366992577910423
2023-01-23 01:14:11.948558: step: 464/529, loss: 0.11951503902673721
2023-01-23 01:14:13.114253: step: 468/529, loss: 0.019057750701904297
2023-01-23 01:14:14.215082: step: 472/529, loss: 0.00408825883641839
2023-01-23 01:14:15.362316: step: 476/529, loss: 0.02265291102230549
2023-01-23 01:14:16.482256: step: 480/529, loss: 0.09745602309703827
2023-01-23 01:14:17.646352: step: 484/529, loss: 0.06776171177625656
2023-01-23 01:14:18.791590: step: 488/529, loss: 0.03466839715838432
2023-01-23 01:14:19.962769: step: 492/529, loss: 0.0844636932015419
2023-01-23 01:14:21.092944: step: 496/529, loss: 0.04363875836133957
2023-01-23 01:14:22.230153: step: 500/529, loss: 0.09243683516979218
2023-01-23 01:14:23.397084: step: 504/529, loss: 0.13318701088428497
2023-01-23 01:14:24.551540: step: 508/529, loss: 0.015395975671708584
2023-01-23 01:14:25.687816: step: 512/529, loss: 0.0700516328215599
2023-01-23 01:14:26.840623: step: 516/529, loss: 0.05809517204761505
2023-01-23 01:14:27.983321: step: 520/529, loss: 0.05484752357006073
2023-01-23 01:14:29.112653: step: 524/529, loss: 0.030734922736883163
2023-01-23 01:14:30.222910: step: 528/529, loss: 0.1467321515083313
2023-01-23 01:14:31.389943: step: 532/529, loss: 0.029723817482590675
2023-01-23 01:14:32.508976: step: 536/529, loss: 0.04259147495031357
2023-01-23 01:14:33.674044: step: 540/529, loss: 0.05704698711633682
2023-01-23 01:14:34.806058: step: 544/529, loss: 0.4296625256538391
2023-01-23 01:14:35.961455: step: 548/529, loss: 0.1550310254096985
2023-01-23 01:14:37.094099: step: 552/529, loss: 0.09001141041517258
2023-01-23 01:14:38.242870: step: 556/529, loss: 0.1141211986541748
2023-01-23 01:14:39.388453: step: 560/529, loss: 0.029521655291318893
2023-01-23 01:14:40.516429: step: 564/529, loss: 0.00520715769380331
2023-01-23 01:14:41.649922: step: 568/529, loss: 0.007484960835427046
2023-01-23 01:14:42.808247: step: 572/529, loss: 0.12971477210521698
2023-01-23 01:14:43.946227: step: 576/529, loss: 0.058158110827207565
2023-01-23 01:14:45.082398: step: 580/529, loss: 0.006542682647705078
2023-01-23 01:14:46.213921: step: 584/529, loss: 0.028951240703463554
2023-01-23 01:14:47.345213: step: 588/529, loss: 0.09232206642627716
2023-01-23 01:14:48.489061: step: 592/529, loss: 0.05073648318648338
2023-01-23 01:14:49.639061: step: 596/529, loss: 0.05542507395148277
2023-01-23 01:14:50.792187: step: 600/529, loss: 0.04432716593146324
2023-01-23 01:14:51.947121: step: 604/529, loss: 0.014589262194931507
2023-01-23 01:14:53.105565: step: 608/529, loss: 0.20675840973854065
2023-01-23 01:14:54.223410: step: 612/529, loss: 0.002327871508896351
2023-01-23 01:14:55.369752: step: 616/529, loss: 0.0313684456050396
2023-01-23 01:14:56.519071: step: 620/529, loss: 1.0805071592330933
2023-01-23 01:14:57.630332: step: 624/529, loss: 0.001956033753231168
2023-01-23 01:14:58.773712: step: 628/529, loss: 0.0279464740306139
2023-01-23 01:14:59.937574: step: 632/529, loss: 0.0613618865609169
2023-01-23 01:15:01.074696: step: 636/529, loss: 0.13872985541820526
2023-01-23 01:15:02.228688: step: 640/529, loss: 0.05197715759277344
2023-01-23 01:15:03.351995: step: 644/529, loss: 0.041597843170166016
2023-01-23 01:15:04.479796: step: 648/529, loss: 0.04060318320989609
2023-01-23 01:15:05.623834: step: 652/529, loss: 0.033745717257261276
2023-01-23 01:15:06.758988: step: 656/529, loss: 0.002406215760856867
2023-01-23 01:15:07.882771: step: 660/529, loss: 0.0020011900924146175
2023-01-23 01:15:09.030092: step: 664/529, loss: 0.0461977943778038
2023-01-23 01:15:10.161134: step: 668/529, loss: 0.024914361536502838
2023-01-23 01:15:11.305302: step: 672/529, loss: 0.11208336055278778
2023-01-23 01:15:12.431370: step: 676/529, loss: 0.022490788251161575
2023-01-23 01:15:13.553599: step: 680/529, loss: 0.003051948733627796
2023-01-23 01:15:14.716276: step: 684/529, loss: 0.03430178388953209
2023-01-23 01:15:15.846035: step: 688/529, loss: 0.0536319725215435
2023-01-23 01:15:17.010603: step: 692/529, loss: 0.017032720148563385
2023-01-23 01:15:18.141024: step: 696/529, loss: 0.015553189441561699
2023-01-23 01:15:19.261312: step: 700/529, loss: 0.08068780601024628
2023-01-23 01:15:20.419721: step: 704/529, loss: 0.14039373397827148
2023-01-23 01:15:21.579293: step: 708/529, loss: 0.021083546802401543
2023-01-23 01:15:22.724071: step: 712/529, loss: 0.06777191162109375
2023-01-23 01:15:23.856993: step: 716/529, loss: 0.03463554382324219
2023-01-23 01:15:25.005995: step: 720/529, loss: 0.023313330486416817
2023-01-23 01:15:26.153559: step: 724/529, loss: 0.2650325894355774
2023-01-23 01:15:27.299046: step: 728/529, loss: 0.02833719365298748
2023-01-23 01:15:28.451506: step: 732/529, loss: 0.038880396634340286
2023-01-23 01:15:29.598388: step: 736/529, loss: 0.10498104989528656
2023-01-23 01:15:30.752891: step: 740/529, loss: 0.08159196376800537
2023-01-23 01:15:31.888648: step: 744/529, loss: 0.0482330322265625
2023-01-23 01:15:33.007272: step: 748/529, loss: 0.20723971724510193
2023-01-23 01:15:34.159883: step: 752/529, loss: 0.04625587537884712
2023-01-23 01:15:35.279512: step: 756/529, loss: 0.007816123776137829
2023-01-23 01:15:36.408942: step: 760/529, loss: 0.03884997218847275
2023-01-23 01:15:37.522704: step: 764/529, loss: 0.012987899594008923
2023-01-23 01:15:38.680864: step: 768/529, loss: 0.20532551407814026
2023-01-23 01:15:39.822900: step: 772/529, loss: 0.11797638237476349
2023-01-23 01:15:40.958400: step: 776/529, loss: 0.05479174107313156
2023-01-23 01:15:42.119134: step: 780/529, loss: 0.08997063338756561
2023-01-23 01:15:43.246523: step: 784/529, loss: 0.09629566967487335
2023-01-23 01:15:44.389635: step: 788/529, loss: 0.12250480055809021
2023-01-23 01:15:45.530657: step: 792/529, loss: 0.18010644614696503
2023-01-23 01:15:46.658789: step: 796/529, loss: 0.49465686082839966
2023-01-23 01:15:47.761928: step: 800/529, loss: 0.030751466751098633
2023-01-23 01:15:48.909770: step: 804/529, loss: 0.10435283929109573
2023-01-23 01:15:50.069012: step: 808/529, loss: 0.13514499366283417
2023-01-23 01:15:51.213366: step: 812/529, loss: 0.036295510828495026
2023-01-23 01:15:52.354508: step: 816/529, loss: 0.03746400028467178
2023-01-23 01:15:53.502350: step: 820/529, loss: 0.026634838432073593
2023-01-23 01:15:54.664845: step: 824/529, loss: 0.157756045460701
2023-01-23 01:15:55.820468: step: 828/529, loss: 0.018427561968564987
2023-01-23 01:15:56.956094: step: 832/529, loss: 0.009665250778198242
2023-01-23 01:15:58.095347: step: 836/529, loss: 0.02650909498333931
2023-01-23 01:15:59.233523: step: 840/529, loss: 0.007261467166244984
2023-01-23 01:16:00.357122: step: 844/529, loss: 0.003098106477409601
2023-01-23 01:16:01.481547: step: 848/529, loss: 0.11651191860437393
2023-01-23 01:16:02.637321: step: 852/529, loss: 0.1394055187702179
2023-01-23 01:16:03.819733: step: 856/529, loss: 0.08608122169971466
2023-01-23 01:16:04.950408: step: 860/529, loss: 0.06292672455310822
2023-01-23 01:16:06.084260: step: 864/529, loss: 0.09668950736522675
2023-01-23 01:16:07.236021: step: 868/529, loss: 0.021326828747987747
2023-01-23 01:16:08.385742: step: 872/529, loss: 0.07423420250415802
2023-01-23 01:16:09.550619: step: 876/529, loss: 0.08232231438159943
2023-01-23 01:16:10.688450: step: 880/529, loss: 0.05654726177453995
2023-01-23 01:16:11.858177: step: 884/529, loss: 0.03529674932360649
2023-01-23 01:16:12.991680: step: 888/529, loss: 0.010225963778793812
2023-01-23 01:16:14.153846: step: 892/529, loss: 0.0780513808131218
2023-01-23 01:16:15.322927: step: 896/529, loss: 0.06091899797320366
2023-01-23 01:16:16.477275: step: 900/529, loss: 0.05104684829711914
2023-01-23 01:16:17.617864: step: 904/529, loss: 0.04106760025024414
2023-01-23 01:16:18.768275: step: 908/529, loss: 0.06950192898511887
2023-01-23 01:16:19.916719: step: 912/529, loss: 0.028328705579042435
2023-01-23 01:16:21.049985: step: 916/529, loss: 0.09161491692066193
2023-01-23 01:16:22.214626: step: 920/529, loss: 0.12742692232131958
2023-01-23 01:16:23.370370: step: 924/529, loss: 0.02413802035152912
2023-01-23 01:16:24.505553: step: 928/529, loss: 0.014517117291688919
2023-01-23 01:16:25.660133: step: 932/529, loss: 0.06157340854406357
2023-01-23 01:16:26.802861: step: 936/529, loss: 0.0881475955247879
2023-01-23 01:16:27.941252: step: 940/529, loss: 0.2531529366970062
2023-01-23 01:16:29.079047: step: 944/529, loss: 0.010202598758041859
2023-01-23 01:16:30.199881: step: 948/529, loss: 0.022090911865234375
2023-01-23 01:16:31.330884: step: 952/529, loss: 0.05865836516022682
2023-01-23 01:16:32.482702: step: 956/529, loss: 0.06268072128295898
2023-01-23 01:16:33.613204: step: 960/529, loss: 0.015076875686645508
2023-01-23 01:16:34.749670: step: 964/529, loss: 0.06994371116161346
2023-01-23 01:16:35.891651: step: 968/529, loss: 0.02480478212237358
2023-01-23 01:16:37.040261: step: 972/529, loss: 0.032300855964422226
2023-01-23 01:16:38.189230: step: 976/529, loss: 0.01724104955792427
2023-01-23 01:16:39.342301: step: 980/529, loss: 0.044585611671209335
2023-01-23 01:16:40.487701: step: 984/529, loss: 0.09066153317689896
2023-01-23 01:16:41.632450: step: 988/529, loss: 0.01212616078555584
2023-01-23 01:16:42.787908: step: 992/529, loss: 0.10081902146339417
2023-01-23 01:16:43.937764: step: 996/529, loss: 0.03439655154943466
2023-01-23 01:16:45.076764: step: 1000/529, loss: 0.015155363827943802
2023-01-23 01:16:46.202383: step: 1004/529, loss: 0.044470883905887604
2023-01-23 01:16:47.327089: step: 1008/529, loss: 0.43867626786231995
2023-01-23 01:16:48.476059: step: 1012/529, loss: 0.05597391352057457
2023-01-23 01:16:49.621601: step: 1016/529, loss: 0.021386291831731796
2023-01-23 01:16:50.776366: step: 1020/529, loss: 0.058826547116041183
2023-01-23 01:16:51.936784: step: 1024/529, loss: 0.09164562076330185
2023-01-23 01:16:53.056110: step: 1028/529, loss: 0.016368960961699486
2023-01-23 01:16:54.216688: step: 1032/529, loss: 0.05447404459118843
2023-01-23 01:16:55.377342: step: 1036/529, loss: 0.10788127779960632
2023-01-23 01:16:56.497753: step: 1040/529, loss: 0.03672537952661514
2023-01-23 01:16:57.656676: step: 1044/529, loss: 0.04853649437427521
2023-01-23 01:16:58.821278: step: 1048/529, loss: 0.022081661969423294
2023-01-23 01:17:00.027259: step: 1052/529, loss: 0.05111103132367134
2023-01-23 01:17:01.193123: step: 1056/529, loss: 0.41411569714546204
2023-01-23 01:17:02.330588: step: 1060/529, loss: 0.02478158473968506
2023-01-23 01:17:03.458566: step: 1064/529, loss: 0.07401961833238602
2023-01-23 01:17:04.599165: step: 1068/529, loss: 0.09418430179357529
2023-01-23 01:17:05.747128: step: 1072/529, loss: 0.01998300477862358
2023-01-23 01:17:06.884781: step: 1076/529, loss: 0.018085192888975143
2023-01-23 01:17:07.994060: step: 1080/529, loss: 0.02526579052209854
2023-01-23 01:17:09.125200: step: 1084/529, loss: 0.009394549764692783
2023-01-23 01:17:10.269338: step: 1088/529, loss: 0.008757686242461205
2023-01-23 01:17:11.408333: step: 1092/529, loss: 0.08566398918628693
2023-01-23 01:17:12.548076: step: 1096/529, loss: 0.027594996616244316
2023-01-23 01:17:13.697811: step: 1100/529, loss: 0.02775411680340767
2023-01-23 01:17:14.849872: step: 1104/529, loss: 0.039984896779060364
2023-01-23 01:17:16.026537: step: 1108/529, loss: 0.022752225399017334
2023-01-23 01:17:17.179740: step: 1112/529, loss: 0.1442001312971115
2023-01-23 01:17:18.285383: step: 1116/529, loss: 0.03279523923993111
2023-01-23 01:17:19.427181: step: 1120/529, loss: 0.05236015468835831
2023-01-23 01:17:20.556008: step: 1124/529, loss: 0.018459510058164597
2023-01-23 01:17:21.714399: step: 1128/529, loss: 0.02420501783490181
2023-01-23 01:17:22.855112: step: 1132/529, loss: 0.10935159027576447
2023-01-23 01:17:24.033432: step: 1136/529, loss: 0.10718335956335068
2023-01-23 01:17:25.172801: step: 1140/529, loss: 0.060411833226680756
2023-01-23 01:17:26.303450: step: 1144/529, loss: 0.03718376159667969
2023-01-23 01:17:27.403567: step: 1148/529, loss: 0.13251176476478577
2023-01-23 01:17:28.546159: step: 1152/529, loss: 0.01127004623413086
2023-01-23 01:17:29.663157: step: 1156/529, loss: 0.09124326705932617
2023-01-23 01:17:30.798046: step: 1160/529, loss: 0.02315673977136612
2023-01-23 01:17:31.956452: step: 1164/529, loss: 0.03303088992834091
2023-01-23 01:17:33.110595: step: 1168/529, loss: 0.1468932330608368
2023-01-23 01:17:34.241982: step: 1172/529, loss: 0.08278445899486542
2023-01-23 01:17:35.398221: step: 1176/529, loss: 0.09086084365844727
2023-01-23 01:17:36.534197: step: 1180/529, loss: 0.06497984379529953
2023-01-23 01:17:37.672586: step: 1184/529, loss: 0.08080454170703888
2023-01-23 01:17:38.831122: step: 1188/529, loss: 0.07291407883167267
2023-01-23 01:17:39.973000: step: 1192/529, loss: 0.18544892966747284
2023-01-23 01:17:41.109583: step: 1196/529, loss: 0.06635923683643341
2023-01-23 01:17:42.232591: step: 1200/529, loss: 0.014287185855209827
2023-01-23 01:17:43.378911: step: 1204/529, loss: 0.007806397043168545
2023-01-23 01:17:44.477961: step: 1208/529, loss: 0.04401030391454697
2023-01-23 01:17:45.616200: step: 1212/529, loss: 0.12251091748476028
2023-01-23 01:17:46.748331: step: 1216/529, loss: 0.10045633465051651
2023-01-23 01:17:47.885653: step: 1220/529, loss: 0.10395517945289612
2023-01-23 01:17:49.026437: step: 1224/529, loss: 0.0873747318983078
2023-01-23 01:17:50.164468: step: 1228/529, loss: 0.05305042862892151
2023-01-23 01:17:51.303779: step: 1232/529, loss: 0.1095348373055458
2023-01-23 01:17:52.441555: step: 1236/529, loss: 0.3450354337692261
2023-01-23 01:17:53.576922: step: 1240/529, loss: 0.0362754724919796
2023-01-23 01:17:54.717293: step: 1244/529, loss: 0.5497283935546875
2023-01-23 01:17:55.836761: step: 1248/529, loss: 0.06034679710865021
2023-01-23 01:17:56.965159: step: 1252/529, loss: 0.10291165858507156
2023-01-23 01:17:58.099516: step: 1256/529, loss: 0.012968205846846104
2023-01-23 01:17:59.259578: step: 1260/529, loss: 1.0556843280792236
2023-01-23 01:18:00.386369: step: 1264/529, loss: 0.11362943798303604
2023-01-23 01:18:01.515657: step: 1268/529, loss: 0.05350985378026962
2023-01-23 01:18:02.668248: step: 1272/529, loss: 0.1688673496246338
2023-01-23 01:18:03.854671: step: 1276/529, loss: 0.4436616897583008
2023-01-23 01:18:04.975398: step: 1280/529, loss: 0.028574658557772636
2023-01-23 01:18:06.091275: step: 1284/529, loss: 0.054915525019168854
2023-01-23 01:18:07.257091: step: 1288/529, loss: 0.19133606553077698
2023-01-23 01:18:08.377622: step: 1292/529, loss: 0.10890035331249237
2023-01-23 01:18:09.497131: step: 1296/529, loss: 0.03509059175848961
2023-01-23 01:18:10.662059: step: 1300/529, loss: 0.003997898194938898
2023-01-23 01:18:11.805678: step: 1304/529, loss: 0.05790267139673233
2023-01-23 01:18:12.937841: step: 1308/529, loss: 0.05169752612709999
2023-01-23 01:18:14.086158: step: 1312/529, loss: 0.04183614253997803
2023-01-23 01:18:15.215970: step: 1316/529, loss: 0.03798015043139458
2023-01-23 01:18:16.377864: step: 1320/529, loss: 0.1893543154001236
2023-01-23 01:18:17.528523: step: 1324/529, loss: 0.09197287261486053
2023-01-23 01:18:18.667559: step: 1328/529, loss: 0.04724083095788956
2023-01-23 01:18:19.816007: step: 1332/529, loss: 0.02349853515625
2023-01-23 01:18:20.968452: step: 1336/529, loss: 0.01756155490875244
2023-01-23 01:18:22.127228: step: 1340/529, loss: 0.0781540647149086
2023-01-23 01:18:23.262946: step: 1344/529, loss: 0.5248399972915649
2023-01-23 01:18:24.396583: step: 1348/529, loss: 0.05299682915210724
2023-01-23 01:18:25.553397: step: 1352/529, loss: 0.018192388117313385
2023-01-23 01:18:26.692320: step: 1356/529, loss: 0.12810096144676208
2023-01-23 01:18:27.828945: step: 1360/529, loss: 0.07665862888097763
2023-01-23 01:18:28.975945: step: 1364/529, loss: 0.04927987977862358
2023-01-23 01:18:30.106487: step: 1368/529, loss: 0.03404684364795685
2023-01-23 01:18:31.236228: step: 1372/529, loss: 0.014595890417695045
2023-01-23 01:18:32.387134: step: 1376/529, loss: 0.17629805207252502
2023-01-23 01:18:33.538305: step: 1380/529, loss: 0.10727634280920029
2023-01-23 01:18:34.675342: step: 1384/529, loss: 0.006274843588471413
2023-01-23 01:18:35.832222: step: 1388/529, loss: 0.13010425865650177
2023-01-23 01:18:37.003314: step: 1392/529, loss: 0.20049165189266205
2023-01-23 01:18:38.107447: step: 1396/529, loss: 0.0012710571754723787
2023-01-23 01:18:39.254213: step: 1400/529, loss: 0.10759425163269043
2023-01-23 01:18:40.421219: step: 1404/529, loss: 0.10323648154735565
2023-01-23 01:18:41.558616: step: 1408/529, loss: 0.029401589184999466
2023-01-23 01:18:42.687942: step: 1412/529, loss: 0.012305354699492455
2023-01-23 01:18:43.823464: step: 1416/529, loss: 0.06985431164503098
2023-01-23 01:18:44.957113: step: 1420/529, loss: 0.04644613340497017
2023-01-23 01:18:46.099451: step: 1424/529, loss: 0.03849058225750923
2023-01-23 01:18:47.238941: step: 1428/529, loss: 0.16459780931472778
2023-01-23 01:18:48.382868: step: 1432/529, loss: 0.20758318901062012
2023-01-23 01:18:49.510369: step: 1436/529, loss: 0.09304933249950409
2023-01-23 01:18:50.637818: step: 1440/529, loss: 0.01618170738220215
2023-01-23 01:18:51.761509: step: 1444/529, loss: 0.029584791511297226
2023-01-23 01:18:52.899645: step: 1448/529, loss: 0.19560737907886505
2023-01-23 01:18:54.030685: step: 1452/529, loss: 0.14860764145851135
2023-01-23 01:18:55.161489: step: 1456/529, loss: 0.024477459490299225
2023-01-23 01:18:56.288814: step: 1460/529, loss: 0.09299030900001526
2023-01-23 01:18:57.447018: step: 1464/529, loss: 0.06084957346320152
2023-01-23 01:18:58.604372: step: 1468/529, loss: 0.09184026718139648
2023-01-23 01:18:59.746121: step: 1472/529, loss: 0.02703237533569336
2023-01-23 01:19:00.902828: step: 1476/529, loss: 0.0022878171876072884
2023-01-23 01:19:02.051585: step: 1480/529, loss: 0.09968023747205734
2023-01-23 01:19:03.173300: step: 1484/529, loss: 0.0010515212779864669
2023-01-23 01:19:04.342389: step: 1488/529, loss: 0.19247189164161682
2023-01-23 01:19:05.490114: step: 1492/529, loss: 0.048993803560733795
2023-01-23 01:19:06.635351: step: 1496/529, loss: 0.059478189796209335
2023-01-23 01:19:07.760374: step: 1500/529, loss: 0.32829493284225464
2023-01-23 01:19:08.914194: step: 1504/529, loss: 0.12595443427562714
2023-01-23 01:19:10.100428: step: 1508/529, loss: 1.102855920791626
2023-01-23 01:19:11.229531: step: 1512/529, loss: 0.03773389011621475
2023-01-23 01:19:12.433901: step: 1516/529, loss: 0.006098154000937939
2023-01-23 01:19:13.562782: step: 1520/529, loss: 0.03117676079273224
2023-01-23 01:19:14.730827: step: 1524/529, loss: 0.009250831790268421
2023-01-23 01:19:15.874376: step: 1528/529, loss: 0.0743291899561882
2023-01-23 01:19:17.028799: step: 1532/529, loss: 0.13249903917312622
2023-01-23 01:19:18.177510: step: 1536/529, loss: 0.7494790554046631
2023-01-23 01:19:19.285040: step: 1540/529, loss: 0.005266284570097923
2023-01-23 01:19:20.383502: step: 1544/529, loss: 0.0011754035949707031
2023-01-23 01:19:21.530402: step: 1548/529, loss: 0.13013802468776703
2023-01-23 01:19:22.664935: step: 1552/529, loss: 0.12646155059337616
2023-01-23 01:19:23.816453: step: 1556/529, loss: 0.02957763522863388
2023-01-23 01:19:24.932040: step: 1560/529, loss: 0.1027521938085556
2023-01-23 01:19:26.085472: step: 1564/529, loss: 0.05476560443639755
2023-01-23 01:19:27.219667: step: 1568/529, loss: 0.046015169471502304
2023-01-23 01:19:28.386164: step: 1572/529, loss: 0.06575965881347656
2023-01-23 01:19:29.534441: step: 1576/529, loss: 0.14659033715724945
2023-01-23 01:19:30.698768: step: 1580/529, loss: 0.259303480386734
2023-01-23 01:19:31.817822: step: 1584/529, loss: 0.021404456347227097
2023-01-23 01:19:32.965574: step: 1588/529, loss: 0.04481077566742897
2023-01-23 01:19:34.106066: step: 1592/529, loss: 0.043441012501716614
2023-01-23 01:19:35.252032: step: 1596/529, loss: 0.05086226761341095
2023-01-23 01:19:36.392302: step: 1600/529, loss: 0.06997766345739365
2023-01-23 01:19:37.504731: step: 1604/529, loss: 0.0350494384765625
2023-01-23 01:19:38.669935: step: 1608/529, loss: 0.02022533491253853
2023-01-23 01:19:39.817136: step: 1612/529, loss: 0.04236030578613281
2023-01-23 01:19:40.959668: step: 1616/529, loss: 0.1416357159614563
2023-01-23 01:19:42.116022: step: 1620/529, loss: 0.03966255113482475
2023-01-23 01:19:43.269744: step: 1624/529, loss: 0.0459684357047081
2023-01-23 01:19:44.415423: step: 1628/529, loss: 0.02164764329791069
2023-01-23 01:19:45.545623: step: 1632/529, loss: 0.043527986854314804
2023-01-23 01:19:46.685376: step: 1636/529, loss: 0.042981650680303574
2023-01-23 01:19:47.827145: step: 1640/529, loss: 0.04893989861011505
2023-01-23 01:19:48.980515: step: 1644/529, loss: 0.3489700257778168
2023-01-23 01:19:50.116647: step: 1648/529, loss: 0.020563887432217598
2023-01-23 01:19:51.224667: step: 1652/529, loss: 0.10988236218690872
2023-01-23 01:19:52.375915: step: 1656/529, loss: 0.0028249742463231087
2023-01-23 01:19:53.500349: step: 1660/529, loss: 0.06804027408361435
2023-01-23 01:19:54.634990: step: 1664/529, loss: 0.07805585861206055
2023-01-23 01:19:55.767638: step: 1668/529, loss: 1.7727779150009155
2023-01-23 01:19:56.908021: step: 1672/529, loss: 0.027508163824677467
2023-01-23 01:19:58.026402: step: 1676/529, loss: 0.030366133898496628
2023-01-23 01:19:59.166476: step: 1680/529, loss: 0.014676189050078392
2023-01-23 01:20:00.308320: step: 1684/529, loss: 0.07325849682092667
2023-01-23 01:20:01.449951: step: 1688/529, loss: 0.0035275935661047697
2023-01-23 01:20:02.617209: step: 1692/529, loss: 0.0010804652702063322
2023-01-23 01:20:03.751013: step: 1696/529, loss: 0.08370047062635422
2023-01-23 01:20:04.868558: step: 1700/529, loss: 0.02211475372314453
2023-01-23 01:20:05.978282: step: 1704/529, loss: 0.03272400051355362
2023-01-23 01:20:07.140482: step: 1708/529, loss: 0.04789257049560547
2023-01-23 01:20:08.313536: step: 1712/529, loss: 0.03433294966816902
2023-01-23 01:20:09.443983: step: 1716/529, loss: 0.035271503031253815
2023-01-23 01:20:10.618988: step: 1720/529, loss: 0.01615114137530327
2023-01-23 01:20:11.748304: step: 1724/529, loss: 0.04921875149011612
2023-01-23 01:20:12.937965: step: 1728/529, loss: 0.3380189836025238
2023-01-23 01:20:14.121612: step: 1732/529, loss: 0.06096029281616211
2023-01-23 01:20:15.317403: step: 1736/529, loss: 0.16447143256664276
2023-01-23 01:20:16.458955: step: 1740/529, loss: 0.015569686889648438
2023-01-23 01:20:17.604296: step: 1744/529, loss: 0.04421548917889595
2023-01-23 01:20:18.762671: step: 1748/529, loss: 0.1116512268781662
2023-01-23 01:20:19.879567: step: 1752/529, loss: 0.03895087167620659
2023-01-23 01:20:21.024569: step: 1756/529, loss: 0.26146629452705383
2023-01-23 01:20:22.168587: step: 1760/529, loss: 0.0629245787858963
2023-01-23 01:20:23.342987: step: 1764/529, loss: 0.0997367799282074
2023-01-23 01:20:24.483810: step: 1768/529, loss: 0.018084336072206497
2023-01-23 01:20:25.626386: step: 1772/529, loss: 0.021899128332734108
2023-01-23 01:20:26.804421: step: 1776/529, loss: 0.11147318035364151
2023-01-23 01:20:27.978477: step: 1780/529, loss: 0.07213706523180008
2023-01-23 01:20:29.133367: step: 1784/529, loss: 0.028705166652798653
2023-01-23 01:20:30.265455: step: 1788/529, loss: 0.14554014801979065
2023-01-23 01:20:31.408572: step: 1792/529, loss: 0.10406913608312607
2023-01-23 01:20:32.591858: step: 1796/529, loss: 0.04659681394696236
2023-01-23 01:20:33.757975: step: 1800/529, loss: 0.1068873405456543
2023-01-23 01:20:34.902710: step: 1804/529, loss: 0.011534976772964
2023-01-23 01:20:36.033789: step: 1808/529, loss: 0.053809307515621185
2023-01-23 01:20:37.174071: step: 1812/529, loss: 0.04740581288933754
2023-01-23 01:20:38.282281: step: 1816/529, loss: 0.03465624153614044
2023-01-23 01:20:39.449569: step: 1820/529, loss: 0.12698392570018768
2023-01-23 01:20:40.600836: step: 1824/529, loss: 0.003928279969841242
2023-01-23 01:20:41.773066: step: 1828/529, loss: 0.08658495545387268
2023-01-23 01:20:42.937881: step: 1832/529, loss: 0.029357576742768288
2023-01-23 01:20:44.066011: step: 1836/529, loss: 0.0035843849182128906
2023-01-23 01:20:45.191440: step: 1840/529, loss: 0.03657648339867592
2023-01-23 01:20:46.335245: step: 1844/529, loss: 0.23565292358398438
2023-01-23 01:20:47.481949: step: 1848/529, loss: 0.06023597717285156
2023-01-23 01:20:48.630782: step: 1852/529, loss: 0.0174531452357769
2023-01-23 01:20:49.783518: step: 1856/529, loss: 0.17921113967895508
2023-01-23 01:20:50.932447: step: 1860/529, loss: 0.024892425164580345
2023-01-23 01:20:52.082795: step: 1864/529, loss: 0.47402411699295044
2023-01-23 01:20:53.250097: step: 1868/529, loss: 0.10864716023206711
2023-01-23 01:20:54.390767: step: 1872/529, loss: 0.0034317015670239925
2023-01-23 01:20:55.520456: step: 1876/529, loss: 0.006154841743409634
2023-01-23 01:20:56.650759: step: 1880/529, loss: 0.20169925689697266
2023-01-23 01:20:57.752926: step: 1884/529, loss: 0.0027984618209302425
2023-01-23 01:20:58.892921: step: 1888/529, loss: 0.026531364768743515
2023-01-23 01:21:00.030451: step: 1892/529, loss: 0.09096936881542206
2023-01-23 01:21:01.178156: step: 1896/529, loss: 0.2370111495256424
2023-01-23 01:21:02.302975: step: 1900/529, loss: 0.007167292293161154
2023-01-23 01:21:03.424497: step: 1904/529, loss: 0.042585086077451706
2023-01-23 01:21:04.602198: step: 1908/529, loss: 0.039690397679805756
2023-01-23 01:21:05.730108: step: 1912/529, loss: 0.0035885809920728207
2023-01-23 01:21:06.832114: step: 1916/529, loss: 0.3277645707130432
2023-01-23 01:21:08.004494: step: 1920/529, loss: 0.09594707190990448
2023-01-23 01:21:09.138986: step: 1924/529, loss: 0.03206615522503853
2023-01-23 01:21:10.284832: step: 1928/529, loss: 0.08674336224794388
2023-01-23 01:21:11.419449: step: 1932/529, loss: 0.011665034107863903
2023-01-23 01:21:12.549697: step: 1936/529, loss: 0.051511384546756744
2023-01-23 01:21:13.705488: step: 1940/529, loss: 0.0838102400302887
2023-01-23 01:21:14.867184: step: 1944/529, loss: 0.05924806743860245
2023-01-23 01:21:16.035948: step: 1948/529, loss: 0.03266000747680664
2023-01-23 01:21:17.176610: step: 1952/529, loss: 0.1516532003879547
2023-01-23 01:21:18.322888: step: 1956/529, loss: 0.09760494530200958
2023-01-23 01:21:19.465449: step: 1960/529, loss: 0.13171225786209106
2023-01-23 01:21:20.604401: step: 1964/529, loss: 0.04678545147180557
2023-01-23 01:21:21.739456: step: 1968/529, loss: 0.08297538757324219
2023-01-23 01:21:22.892143: step: 1972/529, loss: 0.03066234476864338
2023-01-23 01:21:24.037914: step: 1976/529, loss: 0.054668523371219635
2023-01-23 01:21:25.162096: step: 1980/529, loss: 0.09990043938159943
2023-01-23 01:21:26.314070: step: 1984/529, loss: 0.06002431362867355
2023-01-23 01:21:27.458338: step: 1988/529, loss: 0.013646173290908337
2023-01-23 01:21:28.631926: step: 1992/529, loss: 0.09699364006519318
2023-01-23 01:21:29.774457: step: 1996/529, loss: 0.00797348003834486
2023-01-23 01:21:30.913301: step: 2000/529, loss: 0.052484966814517975
2023-01-23 01:21:32.066479: step: 2004/529, loss: 0.17032918334007263
2023-01-23 01:21:33.216898: step: 2008/529, loss: 0.05007191002368927
2023-01-23 01:21:34.371555: step: 2012/529, loss: 0.0706019401550293
2023-01-23 01:21:35.520022: step: 2016/529, loss: 0.012638043612241745
2023-01-23 01:21:36.669590: step: 2020/529, loss: 0.16289833188056946
2023-01-23 01:21:37.810248: step: 2024/529, loss: 0.023499298840761185
2023-01-23 01:21:38.914235: step: 2028/529, loss: 0.02674427069723606
2023-01-23 01:21:40.077249: step: 2032/529, loss: 1.3728324174880981
2023-01-23 01:21:41.209431: step: 2036/529, loss: 0.02027606964111328
2023-01-23 01:21:42.341253: step: 2040/529, loss: 0.0457921028137207
2023-01-23 01:21:43.486620: step: 2044/529, loss: 0.027369117364287376
2023-01-23 01:21:44.605106: step: 2048/529, loss: 0.0031394334509968758
2023-01-23 01:21:45.744964: step: 2052/529, loss: 0.012844085693359375
2023-01-23 01:21:46.870633: step: 2056/529, loss: 0.08121900260448456
2023-01-23 01:21:47.995742: step: 2060/529, loss: 0.09306765347719193
2023-01-23 01:21:49.121603: step: 2064/529, loss: 0.06612720340490341
2023-01-23 01:21:50.280010: step: 2068/529, loss: 0.043155863881111145
2023-01-23 01:21:51.405318: step: 2072/529, loss: 0.11836127936840057
2023-01-23 01:21:52.558974: step: 2076/529, loss: 0.08553294837474823
2023-01-23 01:21:53.718334: step: 2080/529, loss: 0.065460205078125
2023-01-23 01:21:54.862748: step: 2084/529, loss: 0.0066121225245296955
2023-01-23 01:21:56.037957: step: 2088/529, loss: 0.06153126060962677
2023-01-23 01:21:57.197688: step: 2092/529, loss: 0.012886285781860352
2023-01-23 01:21:58.291805: step: 2096/529, loss: 0.1644933670759201
2023-01-23 01:21:59.447443: step: 2100/529, loss: 0.09799116104841232
2023-01-23 01:22:00.593069: step: 2104/529, loss: 0.09508619457483292
2023-01-23 01:22:01.728992: step: 2108/529, loss: 0.171131893992424
2023-01-23 01:22:02.889266: step: 2112/529, loss: 0.07161112129688263
2023-01-23 01:22:04.021904: step: 2116/529, loss: 0.06396923214197159
==================================================
Loss: 0.094
--------------------
Dev: {'event': {'p': 0.5991649269311065, 'r': 0.7643142476697736, 'f1': 0.6717378583967233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6037822878228782, 'r': 0.7584009269988412, 'f1': 0.6723163841807909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
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': 10}
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': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:22:45.462029: step: 4/529, loss: 0.059105969965457916
2023-01-23 01:22:46.608788: step: 8/529, loss: 0.0645173043012619
2023-01-23 01:22:47.721314: step: 12/529, loss: 0.04948629438877106
2023-01-23 01:22:48.842513: step: 16/529, loss: 0.009715271182358265
2023-01-23 01:22:49.996267: step: 20/529, loss: 0.023418236523866653
2023-01-23 01:22:51.133115: step: 24/529, loss: 0.056659817695617676
2023-01-23 01:22:52.297095: step: 28/529, loss: 0.08656396716833115
2023-01-23 01:22:53.435935: step: 32/529, loss: 0.049924638122320175
2023-01-23 01:22:54.555764: step: 36/529, loss: 0.04948770999908447
2023-01-23 01:22:55.708182: step: 40/529, loss: 0.06343088299036026
2023-01-23 01:22:56.845169: step: 44/529, loss: 0.015443230047821999
2023-01-23 01:22:57.992065: step: 48/529, loss: 0.15336580574512482
2023-01-23 01:22:59.115851: step: 52/529, loss: 0.020012950524687767
2023-01-23 01:23:00.248235: step: 56/529, loss: 0.026934243738651276
2023-01-23 01:23:01.379564: step: 60/529, loss: 0.046183157712221146
2023-01-23 01:23:02.503381: step: 64/529, loss: 0.027323054149746895
2023-01-23 01:23:03.684089: step: 68/529, loss: 0.060655929148197174
2023-01-23 01:23:04.846063: step: 72/529, loss: 0.023775674402713776
2023-01-23 01:23:05.981387: step: 76/529, loss: 0.07388029247522354
2023-01-23 01:23:07.121433: step: 80/529, loss: 0.12838220596313477
2023-01-23 01:23:08.260595: step: 84/529, loss: 0.0717768669128418
2023-01-23 01:23:09.373330: step: 88/529, loss: 0.0027473450172692537
2023-01-23 01:23:10.516093: step: 92/529, loss: 0.04699058458209038
2023-01-23 01:23:11.647430: step: 96/529, loss: 0.08606776595115662
2023-01-23 01:23:12.783878: step: 100/529, loss: 0.043141745030879974
2023-01-23 01:23:13.963054: step: 104/529, loss: 0.09770040214061737
2023-01-23 01:23:15.098442: step: 108/529, loss: 0.05930342525243759
2023-01-23 01:23:16.274018: step: 112/529, loss: 0.16444511711597443
2023-01-23 01:23:17.395529: step: 116/529, loss: 0.045732785016298294
2023-01-23 01:23:18.503876: step: 120/529, loss: 0.12604545056819916
2023-01-23 01:23:19.685572: step: 124/529, loss: 0.013486290350556374
2023-01-23 01:23:20.839443: step: 128/529, loss: 0.04182462766766548
2023-01-23 01:23:21.977304: step: 132/529, loss: 0.05329122394323349
2023-01-23 01:23:23.156832: step: 136/529, loss: 0.08341045677661896
2023-01-23 01:23:24.297470: step: 140/529, loss: 0.014041328802704811
2023-01-23 01:23:25.432767: step: 144/529, loss: 0.02705674059689045
2023-01-23 01:23:26.563627: step: 148/529, loss: 0.04370150715112686
2023-01-23 01:23:27.715615: step: 152/529, loss: 0.010295487008988857
2023-01-23 01:23:28.849033: step: 156/529, loss: 0.02036895789206028
2023-01-23 01:23:29.982786: step: 160/529, loss: 0.016992950811982155
2023-01-23 01:23:31.100945: step: 164/529, loss: 0.020859908312559128
2023-01-23 01:23:32.231578: step: 168/529, loss: 0.07204189151525497
2023-01-23 01:23:33.387128: step: 172/529, loss: 0.02249589003622532
2023-01-23 01:23:34.558308: step: 176/529, loss: 0.02533874660730362
2023-01-23 01:23:35.717313: step: 180/529, loss: 0.08395090699195862
2023-01-23 01:23:36.889702: step: 184/529, loss: 0.010426384396851063
2023-01-23 01:23:38.012194: step: 188/529, loss: 0.03150737285614014
2023-01-23 01:23:39.130335: step: 192/529, loss: 0.042586516588926315
2023-01-23 01:23:40.298349: step: 196/529, loss: 0.04754199832677841
2023-01-23 01:23:41.460560: step: 200/529, loss: 0.008863067254424095
2023-01-23 01:23:42.612012: step: 204/529, loss: 0.005052757449448109
2023-01-23 01:23:43.763746: step: 208/529, loss: 0.04658851400017738
2023-01-23 01:23:44.920519: step: 212/529, loss: 0.0265120267868042
2023-01-23 01:23:46.046894: step: 216/529, loss: 0.0661783218383789
2023-01-23 01:23:47.181817: step: 220/529, loss: 0.032805442810058594
2023-01-23 01:23:48.333387: step: 224/529, loss: 0.06348991394042969
2023-01-23 01:23:49.461934: step: 228/529, loss: 0.035439252853393555
2023-01-23 01:23:50.600580: step: 232/529, loss: 0.2851695716381073
2023-01-23 01:23:51.749345: step: 236/529, loss: 0.04455013573169708
2023-01-23 01:23:52.917615: step: 240/529, loss: 0.0759057104587555
2023-01-23 01:23:54.069392: step: 244/529, loss: 0.06230630725622177
2023-01-23 01:23:55.194694: step: 248/529, loss: 0.05028343200683594
2023-01-23 01:23:56.343319: step: 252/529, loss: 0.025524521246552467
2023-01-23 01:23:57.492789: step: 256/529, loss: 0.10955486446619034
2023-01-23 01:23:58.645590: step: 260/529, loss: 0.048208095133304596
2023-01-23 01:23:59.774572: step: 264/529, loss: 0.033761024475097656
2023-01-23 01:24:00.921958: step: 268/529, loss: 0.057462021708488464
2023-01-23 01:24:02.072369: step: 272/529, loss: 0.06448125839233398
2023-01-23 01:24:03.261217: step: 276/529, loss: 0.04942522197961807
2023-01-23 01:24:04.416373: step: 280/529, loss: 0.00915985181927681
2023-01-23 01:24:05.594330: step: 284/529, loss: 0.024196816608309746
2023-01-23 01:24:06.704348: step: 288/529, loss: 0.060741715133190155
2023-01-23 01:24:07.855765: step: 292/529, loss: 0.03851795196533203
2023-01-23 01:24:08.999043: step: 296/529, loss: 0.055022433400154114
2023-01-23 01:24:10.145393: step: 300/529, loss: 0.004605770111083984
2023-01-23 01:24:11.315380: step: 304/529, loss: 0.04043159633874893
2023-01-23 01:24:12.462761: step: 308/529, loss: 0.046128083020448685
2023-01-23 01:24:13.646691: step: 312/529, loss: 0.010307692922651768
2023-01-23 01:24:14.814386: step: 316/529, loss: 0.5625835657119751
2023-01-23 01:24:15.950187: step: 320/529, loss: 0.040352363139390945
2023-01-23 01:24:17.085644: step: 324/529, loss: 0.018245507031679153
2023-01-23 01:24:18.226675: step: 328/529, loss: 0.03461475297808647
2023-01-23 01:24:19.355810: step: 332/529, loss: 0.04432697221636772
2023-01-23 01:24:20.483373: step: 336/529, loss: 0.033873941749334335
2023-01-23 01:24:21.612436: step: 340/529, loss: 0.06554307788610458
2023-01-23 01:24:22.790540: step: 344/529, loss: 0.09892864525318146
2023-01-23 01:24:23.931570: step: 348/529, loss: 0.04830008000135422
2023-01-23 01:24:25.068688: step: 352/529, loss: 0.0764305591583252
2023-01-23 01:24:26.209430: step: 356/529, loss: 0.003944301512092352
2023-01-23 01:24:27.347024: step: 360/529, loss: 0.11398305743932724
2023-01-23 01:24:28.510681: step: 364/529, loss: 0.05307529866695404
2023-01-23 01:24:29.641412: step: 368/529, loss: 0.04363727569580078
2023-01-23 01:24:30.796425: step: 372/529, loss: 0.061898425221443176
2023-01-23 01:24:31.944949: step: 376/529, loss: 0.0026102066040039062
2023-01-23 01:24:33.055631: step: 380/529, loss: 0.0448877327144146
2023-01-23 01:24:34.181246: step: 384/529, loss: 0.029390431940555573
2023-01-23 01:24:35.311340: step: 388/529, loss: 0.06987170875072479
2023-01-23 01:24:36.445418: step: 392/529, loss: 0.04736804962158203
2023-01-23 01:24:37.588684: step: 396/529, loss: 0.0361480712890625
2023-01-23 01:24:38.709690: step: 400/529, loss: 0.023975946009159088
2023-01-23 01:24:39.866148: step: 404/529, loss: 0.03843478858470917
2023-01-23 01:24:41.000641: step: 408/529, loss: 0.04291677474975586
2023-01-23 01:24:42.164086: step: 412/529, loss: 0.00771255511790514
2023-01-23 01:24:43.329433: step: 416/529, loss: 0.0485166534781456
2023-01-23 01:24:44.454928: step: 420/529, loss: 0.04470081254839897
2023-01-23 01:24:45.674034: step: 424/529, loss: 0.02491469494998455
2023-01-23 01:24:46.799960: step: 428/529, loss: 0.059216879308223724
2023-01-23 01:24:47.938158: step: 432/529, loss: 0.02149954065680504
2023-01-23 01:24:49.085136: step: 436/529, loss: 0.030137062072753906
2023-01-23 01:24:50.202869: step: 440/529, loss: 0.02650637738406658
2023-01-23 01:24:51.366718: step: 444/529, loss: 0.15329113602638245
2023-01-23 01:24:52.512731: step: 448/529, loss: 0.024412918835878372
2023-01-23 01:24:53.674591: step: 452/529, loss: 0.5086908340454102
2023-01-23 01:24:54.802975: step: 456/529, loss: 0.007043266203254461
2023-01-23 01:24:55.923575: step: 460/529, loss: 0.06777582317590714
2023-01-23 01:24:57.064860: step: 464/529, loss: 0.1480318009853363
2023-01-23 01:24:58.168120: step: 468/529, loss: 0.026124000549316406
2023-01-23 01:24:59.305584: step: 472/529, loss: 0.4231296181678772
2023-01-23 01:25:00.436605: step: 476/529, loss: 0.0619107261300087
2023-01-23 01:25:01.589952: step: 480/529, loss: 0.020137976855039597
2023-01-23 01:25:02.722582: step: 484/529, loss: 0.006447935476899147
2023-01-23 01:25:03.834908: step: 488/529, loss: 0.038645461201667786
2023-01-23 01:25:04.976494: step: 492/529, loss: 0.02344489097595215
2023-01-23 01:25:06.108806: step: 496/529, loss: 0.066119484603405
2023-01-23 01:25:07.237824: step: 500/529, loss: 0.014425469562411308
2023-01-23 01:25:08.400722: step: 504/529, loss: 0.08803434669971466
2023-01-23 01:25:09.536433: step: 508/529, loss: 0.0633271262049675
2023-01-23 01:25:10.683443: step: 512/529, loss: 0.029651260003447533
2023-01-23 01:25:11.836170: step: 516/529, loss: 0.019073868170380592
2023-01-23 01:25:12.963052: step: 520/529, loss: 0.06599827110767365
2023-01-23 01:25:14.124151: step: 524/529, loss: 0.02843942679464817
2023-01-23 01:25:15.268743: step: 528/529, loss: 0.0077641489915549755
2023-01-23 01:25:16.427813: step: 532/529, loss: 0.009955024346709251
2023-01-23 01:25:17.581943: step: 536/529, loss: 0.022554589435458183
2023-01-23 01:25:18.728487: step: 540/529, loss: 0.14339271187782288
2023-01-23 01:25:19.867755: step: 544/529, loss: 0.48264798521995544
2023-01-23 01:25:21.012797: step: 548/529, loss: 0.008354758843779564
2023-01-23 01:25:22.125079: step: 552/529, loss: 0.04884080961346626
2023-01-23 01:25:23.238682: step: 556/529, loss: 0.05390520021319389
2023-01-23 01:25:24.373288: step: 560/529, loss: 0.04314251244068146
2023-01-23 01:25:25.505859: step: 564/529, loss: 0.08556537330150604
2023-01-23 01:25:26.659742: step: 568/529, loss: 0.024846553802490234
2023-01-23 01:25:27.794150: step: 572/529, loss: 0.04279651865363121
2023-01-23 01:25:28.956919: step: 576/529, loss: 0.03595714643597603
2023-01-23 01:25:30.088523: step: 580/529, loss: 0.08370581269264221
2023-01-23 01:25:31.240938: step: 584/529, loss: 0.005891323555260897
2023-01-23 01:25:32.364093: step: 588/529, loss: 0.02362527884542942
2023-01-23 01:25:33.486988: step: 592/529, loss: 0.0581483393907547
2023-01-23 01:25:34.629918: step: 596/529, loss: 0.01826615259051323
2023-01-23 01:25:35.755105: step: 600/529, loss: 0.04715690761804581
2023-01-23 01:25:36.909259: step: 604/529, loss: 0.06747522205114365
2023-01-23 01:25:38.034413: step: 608/529, loss: 0.08730635792016983
2023-01-23 01:25:39.158464: step: 612/529, loss: 0.026374198496341705
2023-01-23 01:25:40.295620: step: 616/529, loss: 0.017811108380556107
2023-01-23 01:25:41.468633: step: 620/529, loss: 1.7652653455734253
2023-01-23 01:25:42.638671: step: 624/529, loss: 0.054247546941041946
2023-01-23 01:25:43.797260: step: 628/529, loss: 0.018061399459838867
2023-01-23 01:25:44.930291: step: 632/529, loss: 0.09570875763893127
2023-01-23 01:25:46.053289: step: 636/529, loss: 0.0214083194732666
2023-01-23 01:25:47.181389: step: 640/529, loss: 0.07457075268030167
2023-01-23 01:25:48.322882: step: 644/529, loss: 0.04270830377936363
2023-01-23 01:25:49.461687: step: 648/529, loss: 0.0673549622297287
2023-01-23 01:25:50.607370: step: 652/529, loss: 0.25669556856155396
2023-01-23 01:25:51.759186: step: 656/529, loss: 0.08315477520227432
2023-01-23 01:25:52.897804: step: 660/529, loss: 0.011950301937758923
2023-01-23 01:25:54.037801: step: 664/529, loss: 0.013238906860351562
2023-01-23 01:25:55.204541: step: 668/529, loss: 0.013357162475585938
2023-01-23 01:25:56.383233: step: 672/529, loss: 0.02165069617331028
2023-01-23 01:25:57.529032: step: 676/529, loss: 0.001606035279110074
2023-01-23 01:25:58.666686: step: 680/529, loss: 0.051695965230464935
2023-01-23 01:25:59.827130: step: 684/529, loss: 0.05854034423828125
2023-01-23 01:26:00.954479: step: 688/529, loss: 0.02282686159014702
2023-01-23 01:26:02.106090: step: 692/529, loss: 0.06225090101361275
2023-01-23 01:26:03.258720: step: 696/529, loss: 0.07593603432178497
2023-01-23 01:26:04.386671: step: 700/529, loss: 0.04264011234045029
2023-01-23 01:26:05.527014: step: 704/529, loss: 0.06381864845752716
2023-01-23 01:26:06.665764: step: 708/529, loss: 0.0481809601187706
2023-01-23 01:26:07.796940: step: 712/529, loss: 0.01950225792825222
2023-01-23 01:26:08.951573: step: 716/529, loss: 0.024835586547851562
2023-01-23 01:26:10.084723: step: 720/529, loss: 0.04066123813390732
2023-01-23 01:26:11.245035: step: 724/529, loss: 0.07068872451782227
2023-01-23 01:26:12.378594: step: 728/529, loss: 0.004130077548325062
2023-01-23 01:26:13.521300: step: 732/529, loss: 0.04898247867822647
2023-01-23 01:26:14.652626: step: 736/529, loss: 0.04032273590564728
2023-01-23 01:26:15.791142: step: 740/529, loss: 0.10968603938817978
2023-01-23 01:26:16.964842: step: 744/529, loss: 6.086958408355713
2023-01-23 01:26:18.104546: step: 748/529, loss: 0.10305681079626083
2023-01-23 01:26:19.279264: step: 752/529, loss: 0.06556110084056854
2023-01-23 01:26:20.432036: step: 756/529, loss: 0.03654296323657036
2023-01-23 01:26:21.580748: step: 760/529, loss: 0.03674917295575142
2023-01-23 01:26:22.728084: step: 764/529, loss: 0.10063209384679794
2023-01-23 01:26:23.906357: step: 768/529, loss: 0.01710643619298935
2023-01-23 01:26:25.051140: step: 772/529, loss: 0.009410286322236061
2023-01-23 01:26:26.236899: step: 776/529, loss: 0.034612275660037994
2023-01-23 01:26:27.367540: step: 780/529, loss: 0.012948036193847656
2023-01-23 01:26:28.511219: step: 784/529, loss: 0.009429693222045898
2023-01-23 01:26:29.646031: step: 788/529, loss: 0.03881826624274254
2023-01-23 01:26:30.766525: step: 792/529, loss: 0.39961832761764526
2023-01-23 01:26:31.913181: step: 796/529, loss: 0.028296278789639473
2023-01-23 01:26:33.054991: step: 800/529, loss: 0.2209060788154602
2023-01-23 01:26:34.254350: step: 804/529, loss: 0.02661895751953125
2023-01-23 01:26:35.419071: step: 808/529, loss: 0.008953286334872246
2023-01-23 01:26:36.554418: step: 812/529, loss: 0.12106628715991974
2023-01-23 01:26:37.709656: step: 816/529, loss: 0.008331775665283203
2023-01-23 01:26:38.850792: step: 820/529, loss: 0.002130711218342185
2023-01-23 01:26:39.960509: step: 824/529, loss: 0.08493924140930176
2023-01-23 01:26:41.103698: step: 828/529, loss: 0.006622696295380592
2023-01-23 01:26:42.246282: step: 832/529, loss: 0.07141521573066711
2023-01-23 01:26:43.384148: step: 836/529, loss: 0.12237599492073059
2023-01-23 01:26:44.567636: step: 840/529, loss: 0.05327673256397247
2023-01-23 01:26:45.691551: step: 844/529, loss: 0.01591324806213379
2023-01-23 01:26:46.838244: step: 848/529, loss: 0.05979042127728462
2023-01-23 01:26:47.984101: step: 852/529, loss: 0.08037286251783371
2023-01-23 01:26:49.124428: step: 856/529, loss: 0.02086477354168892
2023-01-23 01:26:50.262856: step: 860/529, loss: 0.0671960860490799
2023-01-23 01:26:51.410647: step: 864/529, loss: 0.062377430498600006
2023-01-23 01:26:52.567222: step: 868/529, loss: 0.04353771358728409
2023-01-23 01:26:53.722434: step: 872/529, loss: 0.02901592291891575
2023-01-23 01:26:54.850903: step: 876/529, loss: 0.012292003259062767
2023-01-23 01:26:56.023562: step: 880/529, loss: 0.00787963904440403
2023-01-23 01:26:57.174142: step: 884/529, loss: 0.007695913314819336
2023-01-23 01:26:58.282897: step: 888/529, loss: 0.03949563577771187
2023-01-23 01:26:59.399930: step: 892/529, loss: 0.07749109715223312
2023-01-23 01:27:00.538697: step: 896/529, loss: 0.01820545271039009
2023-01-23 01:27:01.657335: step: 900/529, loss: 0.004364109132438898
2023-01-23 01:27:02.798713: step: 904/529, loss: 0.09595232456922531
2023-01-23 01:27:03.958571: step: 908/529, loss: 0.03320474550127983
2023-01-23 01:27:05.100850: step: 912/529, loss: 0.16649967432022095
2023-01-23 01:27:06.240753: step: 916/529, loss: 0.18315038084983826
2023-01-23 01:27:07.376337: step: 920/529, loss: 0.07141990959644318
2023-01-23 01:27:08.534838: step: 924/529, loss: 0.037522315979003906
2023-01-23 01:27:09.667419: step: 928/529, loss: 0.12246754765510559
2023-01-23 01:27:10.831895: step: 932/529, loss: 0.028950978070497513
2023-01-23 01:27:12.015707: step: 936/529, loss: 0.0023561001289635897
2023-01-23 01:27:13.156306: step: 940/529, loss: 0.10039768368005753
2023-01-23 01:27:14.271356: step: 944/529, loss: 0.4176711142063141
2023-01-23 01:27:15.403192: step: 948/529, loss: 0.04866151884198189
2023-01-23 01:27:16.542431: step: 952/529, loss: 0.01057291030883789
2023-01-23 01:27:17.677402: step: 956/529, loss: 0.07761001586914062
2023-01-23 01:27:18.812379: step: 960/529, loss: 0.02510242536664009
2023-01-23 01:27:19.949202: step: 964/529, loss: 0.007092857733368874
2023-01-23 01:27:21.111785: step: 968/529, loss: 0.22311726212501526
2023-01-23 01:27:22.232852: step: 972/529, loss: 0.05343981087207794
2023-01-23 01:27:23.380026: step: 976/529, loss: 0.014866352081298828
2023-01-23 01:27:24.504828: step: 980/529, loss: 0.12448649853467941
2023-01-23 01:27:25.660715: step: 984/529, loss: 0.018642805516719818
2023-01-23 01:27:26.786789: step: 988/529, loss: 0.013216591440141201
2023-01-23 01:27:27.923758: step: 992/529, loss: 0.009308052249252796
2023-01-23 01:27:29.067663: step: 996/529, loss: 0.052773188799619675
2023-01-23 01:27:30.185436: step: 1000/529, loss: 0.021493911743164062
2023-01-23 01:27:31.353319: step: 1004/529, loss: 0.021619463339447975
2023-01-23 01:27:32.501745: step: 1008/529, loss: 0.008909416384994984
2023-01-23 01:27:33.607617: step: 1012/529, loss: 0.03968324884772301
2023-01-23 01:27:34.736413: step: 1016/529, loss: 0.01737501472234726
2023-01-23 01:27:35.883411: step: 1020/529, loss: 0.08769450336694717
2023-01-23 01:27:37.039017: step: 1024/529, loss: 0.06746683269739151
2023-01-23 01:27:38.190696: step: 1028/529, loss: 0.04657325893640518
2023-01-23 01:27:39.320588: step: 1032/529, loss: 0.0790410041809082
2023-01-23 01:27:40.484964: step: 1036/529, loss: 0.0008233592379838228
2023-01-23 01:27:41.647806: step: 1040/529, loss: 0.027800561860203743
2023-01-23 01:27:42.777175: step: 1044/529, loss: 0.012504386715590954
2023-01-23 01:27:43.955335: step: 1048/529, loss: 0.14007015526294708
2023-01-23 01:27:45.111776: step: 1052/529, loss: 0.017615031450986862
2023-01-23 01:27:46.265589: step: 1056/529, loss: 0.03188290819525719
2023-01-23 01:27:47.427214: step: 1060/529, loss: 0.03685960918664932
2023-01-23 01:27:48.569168: step: 1064/529, loss: 0.01133031863719225
2023-01-23 01:27:49.749396: step: 1068/529, loss: 0.12951403856277466
2023-01-23 01:27:50.862608: step: 1072/529, loss: 0.13424329459667206
2023-01-23 01:27:51.986193: step: 1076/529, loss: 0.010524488054215908
2023-01-23 01:27:53.112361: step: 1080/529, loss: 0.05392765998840332
2023-01-23 01:27:54.235526: step: 1084/529, loss: 0.1908133625984192
2023-01-23 01:27:55.372652: step: 1088/529, loss: 0.0072705745697021484
2023-01-23 01:27:56.520235: step: 1092/529, loss: 0.9742828607559204
2023-01-23 01:27:57.662485: step: 1096/529, loss: 0.042876627296209335
2023-01-23 01:27:58.820272: step: 1100/529, loss: 0.02855663374066353
2023-01-23 01:27:59.950625: step: 1104/529, loss: 0.010004043579101562
2023-01-23 01:28:01.065641: step: 1108/529, loss: 0.03783893957734108
2023-01-23 01:28:02.195428: step: 1112/529, loss: 0.027332782745361328
2023-01-23 01:28:03.342359: step: 1116/529, loss: 0.026285268366336823
2023-01-23 01:28:04.470717: step: 1120/529, loss: 0.021649695932865143
2023-01-23 01:28:05.614860: step: 1124/529, loss: 0.0799618735909462
2023-01-23 01:28:06.762819: step: 1128/529, loss: 0.11349983513355255
2023-01-23 01:28:07.897478: step: 1132/529, loss: 0.06392087787389755
2023-01-23 01:28:09.030959: step: 1136/529, loss: 0.02036123350262642
2023-01-23 01:28:10.169537: step: 1140/529, loss: 0.009700584225356579
2023-01-23 01:28:11.304168: step: 1144/529, loss: 0.008136940188705921
2023-01-23 01:28:12.458563: step: 1148/529, loss: 0.04749260097742081
2023-01-23 01:28:13.656026: step: 1152/529, loss: 0.036373041570186615
2023-01-23 01:28:14.806577: step: 1156/529, loss: 0.05070476233959198
2023-01-23 01:28:15.940605: step: 1160/529, loss: 0.08789065480232239
2023-01-23 01:28:17.092126: step: 1164/529, loss: 0.015475083142518997
2023-01-23 01:28:18.259092: step: 1168/529, loss: 0.09388384968042374
2023-01-23 01:28:19.410273: step: 1172/529, loss: 0.02700061909854412
2023-01-23 01:28:20.590975: step: 1176/529, loss: 0.03811941295862198
2023-01-23 01:28:21.767474: step: 1180/529, loss: 0.18512848019599915
2023-01-23 01:28:22.958203: step: 1184/529, loss: 0.08280449360609055
2023-01-23 01:28:24.128246: step: 1188/529, loss: 0.2402186393737793
2023-01-23 01:28:25.258448: step: 1192/529, loss: 0.049204353243112564
2023-01-23 01:28:26.379859: step: 1196/529, loss: 0.026955604553222656
2023-01-23 01:28:27.515311: step: 1200/529, loss: 0.035355761647224426
2023-01-23 01:28:28.680889: step: 1204/529, loss: 0.019194602966308594
2023-01-23 01:28:29.826523: step: 1208/529, loss: 0.019014250487089157
2023-01-23 01:28:30.988694: step: 1212/529, loss: 0.07572594285011292
2023-01-23 01:28:32.168583: step: 1216/529, loss: 0.026965808123350143
2023-01-23 01:28:33.297771: step: 1220/529, loss: 0.057595252990722656
2023-01-23 01:28:34.423724: step: 1224/529, loss: 0.07913951575756073
2023-01-23 01:28:35.585672: step: 1228/529, loss: 0.05920295789837837
2023-01-23 01:28:36.739129: step: 1232/529, loss: 0.3227514922618866
2023-01-23 01:28:37.887849: step: 1236/529, loss: 0.04816637188196182
2023-01-23 01:28:39.005970: step: 1240/529, loss: 0.09544067084789276
2023-01-23 01:28:40.139025: step: 1244/529, loss: 0.04865531995892525
2023-01-23 01:28:41.301265: step: 1248/529, loss: 0.05016060173511505
2023-01-23 01:28:42.447878: step: 1252/529, loss: 0.07657375931739807
2023-01-23 01:28:43.588716: step: 1256/529, loss: 0.06572751700878143
2023-01-23 01:28:44.730614: step: 1260/529, loss: 0.021331120282411575
2023-01-23 01:28:45.859776: step: 1264/529, loss: 0.11602268368005753
2023-01-23 01:28:47.018648: step: 1268/529, loss: 0.020692825317382812
2023-01-23 01:28:48.174125: step: 1272/529, loss: 0.06271343678236008
2023-01-23 01:28:49.325513: step: 1276/529, loss: 0.019038628786802292
2023-01-23 01:28:50.456768: step: 1280/529, loss: 0.031415559351444244
2023-01-23 01:28:51.589597: step: 1284/529, loss: 0.11527501046657562
2023-01-23 01:28:52.726145: step: 1288/529, loss: 0.06377792358398438
2023-01-23 01:28:53.871503: step: 1292/529, loss: 0.05818531662225723
2023-01-23 01:28:54.997682: step: 1296/529, loss: 0.0839502364397049
2023-01-23 01:28:56.131139: step: 1300/529, loss: 0.013971042819321156
2023-01-23 01:28:57.275325: step: 1304/529, loss: 0.05349111557006836
2023-01-23 01:28:58.401415: step: 1308/529, loss: 0.07636123150587082
2023-01-23 01:28:59.550299: step: 1312/529, loss: 0.013654423877596855
2023-01-23 01:29:00.685354: step: 1316/529, loss: 0.046025846153497696
2023-01-23 01:29:01.812835: step: 1320/529, loss: 0.08206848800182343
2023-01-23 01:29:02.938330: step: 1324/529, loss: 0.021786976605653763
2023-01-23 01:29:04.100789: step: 1328/529, loss: 0.017472337931394577
2023-01-23 01:29:05.233768: step: 1332/529, loss: 0.00736546516418457
2023-01-23 01:29:06.380644: step: 1336/529, loss: 0.04738273471593857
2023-01-23 01:29:07.502065: step: 1340/529, loss: 0.011144256219267845
2023-01-23 01:29:08.633420: step: 1344/529, loss: 0.013173866085708141
2023-01-23 01:29:09.782850: step: 1348/529, loss: 0.0019618987571448088
2023-01-23 01:29:10.889750: step: 1352/529, loss: 0.03924417495727539
2023-01-23 01:29:12.047830: step: 1356/529, loss: 0.008240891620516777
2023-01-23 01:29:13.208804: step: 1360/529, loss: 0.01332874409854412
2023-01-23 01:29:14.341624: step: 1364/529, loss: 0.012959122657775879
2023-01-23 01:29:15.487534: step: 1368/529, loss: 0.2457553893327713
2023-01-23 01:29:16.636396: step: 1372/529, loss: 0.008721256628632545
2023-01-23 01:29:17.786556: step: 1376/529, loss: 0.06694066524505615
2023-01-23 01:29:18.905464: step: 1380/529, loss: 0.05604109913110733
2023-01-23 01:29:20.043778: step: 1384/529, loss: 0.009931516833603382
2023-01-23 01:29:21.206941: step: 1388/529, loss: 0.045420125126838684
2023-01-23 01:29:22.326471: step: 1392/529, loss: 0.057488251477479935
2023-01-23 01:29:23.439609: step: 1396/529, loss: 0.030385855585336685
2023-01-23 01:29:24.606497: step: 1400/529, loss: 0.03591332212090492
2023-01-23 01:29:25.755586: step: 1404/529, loss: 0.005641937255859375
2023-01-23 01:29:26.913318: step: 1408/529, loss: 0.06142731010913849
2023-01-23 01:29:28.067810: step: 1412/529, loss: 0.03171978145837784
2023-01-23 01:29:29.201982: step: 1416/529, loss: 0.15856285393238068
2023-01-23 01:29:30.342525: step: 1420/529, loss: 0.019669247791171074
2023-01-23 01:29:31.476076: step: 1424/529, loss: 0.00806207675486803
2023-01-23 01:29:32.611642: step: 1428/529, loss: 0.020203400403261185
2023-01-23 01:29:33.734233: step: 1432/529, loss: 0.1023469865322113
2023-01-23 01:29:34.858039: step: 1436/529, loss: 0.09445791691541672
2023-01-23 01:29:36.005279: step: 1440/529, loss: 0.08383483439683914
2023-01-23 01:29:37.126095: step: 1444/529, loss: 2.042593002319336
2023-01-23 01:29:38.263265: step: 1448/529, loss: 0.0007819652673788369
2023-01-23 01:29:39.380120: step: 1452/529, loss: 0.0836271345615387
2023-01-23 01:29:40.506538: step: 1456/529, loss: 0.07840938866138458
2023-01-23 01:29:41.667889: step: 1460/529, loss: 0.05001964420080185
2023-01-23 01:29:42.830254: step: 1464/529, loss: 0.0506071113049984
2023-01-23 01:29:44.013983: step: 1468/529, loss: 0.09818859398365021
2023-01-23 01:29:45.152842: step: 1472/529, loss: 0.03470568731427193
2023-01-23 01:29:46.287722: step: 1476/529, loss: 0.04303798824548721
2023-01-23 01:29:47.405594: step: 1480/529, loss: 0.007410717196762562
2023-01-23 01:29:48.524550: step: 1484/529, loss: 0.03707394376397133
2023-01-23 01:29:49.664052: step: 1488/529, loss: 0.010460233315825462
2023-01-23 01:29:50.793259: step: 1492/529, loss: 0.02482910268008709
2023-01-23 01:29:51.927182: step: 1496/529, loss: 0.1253221482038498
2023-01-23 01:29:53.067001: step: 1500/529, loss: 0.11007185280323029
2023-01-23 01:29:54.222095: step: 1504/529, loss: 0.06298866868019104
2023-01-23 01:29:55.355670: step: 1508/529, loss: 0.013941287994384766
2023-01-23 01:29:56.502458: step: 1512/529, loss: 0.032973095774650574
2023-01-23 01:29:57.627500: step: 1516/529, loss: 0.006217336747795343
2023-01-23 01:29:58.766810: step: 1520/529, loss: 0.02469329908490181
2023-01-23 01:29:59.908514: step: 1524/529, loss: 0.06664124131202698
2023-01-23 01:30:01.054896: step: 1528/529, loss: 0.04446103423833847
2023-01-23 01:30:02.203208: step: 1532/529, loss: 0.055391646921634674
2023-01-23 01:30:03.356329: step: 1536/529, loss: 0.0877685546875
2023-01-23 01:30:04.515457: step: 1540/529, loss: 0.04209556430578232
2023-01-23 01:30:05.634014: step: 1544/529, loss: 0.007458257954567671
2023-01-23 01:30:06.771830: step: 1548/529, loss: 0.05372180789709091
2023-01-23 01:30:07.891005: step: 1552/529, loss: 0.08323769271373749
2023-01-23 01:30:09.043963: step: 1556/529, loss: 0.02480611763894558
2023-01-23 01:30:10.186793: step: 1560/529, loss: 0.03324947506189346
2023-01-23 01:30:11.331163: step: 1564/529, loss: 0.08538541942834854
2023-01-23 01:30:12.486736: step: 1568/529, loss: 0.04229292646050453
2023-01-23 01:30:13.648830: step: 1572/529, loss: 0.047565557062625885
2023-01-23 01:30:14.780536: step: 1576/529, loss: 0.19779334962368011
2023-01-23 01:30:15.920800: step: 1580/529, loss: 0.04985647648572922
2023-01-23 01:30:17.043260: step: 1584/529, loss: 0.26626014709472656
2023-01-23 01:30:18.153297: step: 1588/529, loss: 0.01124420203268528
2023-01-23 01:30:19.312960: step: 1592/529, loss: 0.017621994018554688
2023-01-23 01:30:20.446708: step: 1596/529, loss: 0.004379463382065296
2023-01-23 01:30:21.613968: step: 1600/529, loss: 0.054818347096443176
2023-01-23 01:30:22.748236: step: 1604/529, loss: 0.015379572287201881
2023-01-23 01:30:23.901655: step: 1608/529, loss: 0.028466034680604935
2023-01-23 01:30:24.998424: step: 1612/529, loss: 0.09541749954223633
2023-01-23 01:30:26.135817: step: 1616/529, loss: 0.040041591972112656
2023-01-23 01:30:27.299462: step: 1620/529, loss: 0.17233572900295258
2023-01-23 01:30:28.443902: step: 1624/529, loss: 0.4602371156215668
2023-01-23 01:30:29.592594: step: 1628/529, loss: 0.026013899594545364
2023-01-23 01:30:30.739637: step: 1632/529, loss: 0.1623372584581375
2023-01-23 01:30:31.863488: step: 1636/529, loss: 0.008664751425385475
2023-01-23 01:30:32.990917: step: 1640/529, loss: 0.11099891364574432
2023-01-23 01:30:34.133352: step: 1644/529, loss: 0.025978660210967064
2023-01-23 01:30:35.292192: step: 1648/529, loss: 0.3354078531265259
2023-01-23 01:30:36.446217: step: 1652/529, loss: 0.03018779866397381
2023-01-23 01:30:37.573366: step: 1656/529, loss: 0.004010963253676891
2023-01-23 01:30:38.715343: step: 1660/529, loss: 0.8976025581359863
2023-01-23 01:30:39.829769: step: 1664/529, loss: 0.004965687170624733
2023-01-23 01:30:40.982445: step: 1668/529, loss: 0.10575437545776367
2023-01-23 01:30:42.119419: step: 1672/529, loss: 0.04000701755285263
2023-01-23 01:30:43.268896: step: 1676/529, loss: 0.050385523587465286
2023-01-23 01:30:44.420456: step: 1680/529, loss: 0.022879745811223984
2023-01-23 01:30:45.549668: step: 1684/529, loss: 0.08208112418651581
2023-01-23 01:30:46.684679: step: 1688/529, loss: 0.03307771682739258
2023-01-23 01:30:47.829011: step: 1692/529, loss: 0.07761363685131073
2023-01-23 01:30:48.957551: step: 1696/529, loss: 0.05516853183507919
2023-01-23 01:30:50.074340: step: 1700/529, loss: 0.027624012902379036
2023-01-23 01:30:51.248280: step: 1704/529, loss: 0.016211509704589844
2023-01-23 01:30:52.361692: step: 1708/529, loss: 0.017551232129335403
2023-01-23 01:30:53.483493: step: 1712/529, loss: 0.008517026901245117
2023-01-23 01:30:54.636879: step: 1716/529, loss: 0.05596160888671875
2023-01-23 01:30:55.789313: step: 1720/529, loss: 0.03875589370727539
2023-01-23 01:30:56.941188: step: 1724/529, loss: 0.15320034325122833
2023-01-23 01:30:58.095123: step: 1728/529, loss: 0.07086601853370667
2023-01-23 01:30:59.225952: step: 1732/529, loss: 0.021431587636470795
2023-01-23 01:31:00.359112: step: 1736/529, loss: 0.06189604103565216
2023-01-23 01:31:01.539845: step: 1740/529, loss: 0.05914762616157532
2023-01-23 01:31:02.717978: step: 1744/529, loss: 0.08634558320045471
2023-01-23 01:31:03.850143: step: 1748/529, loss: 0.037447355687618256
2023-01-23 01:31:05.006153: step: 1752/529, loss: 0.085790254175663
2023-01-23 01:31:06.144850: step: 1756/529, loss: 0.02508225478231907
2023-01-23 01:31:07.280144: step: 1760/529, loss: 0.012481116689741611
2023-01-23 01:31:08.413578: step: 1764/529, loss: 0.1250247359275818
2023-01-23 01:31:09.537427: step: 1768/529, loss: 0.01087942160665989
2023-01-23 01:31:10.661936: step: 1772/529, loss: 0.19690103828907013
2023-01-23 01:31:11.797456: step: 1776/529, loss: 0.07402630150318146
2023-01-23 01:31:12.938155: step: 1780/529, loss: 0.07241058349609375
2023-01-23 01:31:14.070422: step: 1784/529, loss: 0.026280594989657402
2023-01-23 01:31:15.198993: step: 1788/529, loss: 0.13185958564281464
2023-01-23 01:31:16.334544: step: 1792/529, loss: 0.06563983112573624
2023-01-23 01:31:17.468225: step: 1796/529, loss: 0.00043745042057707906
2023-01-23 01:31:18.625035: step: 1800/529, loss: 0.02372722700238228
2023-01-23 01:31:19.805288: step: 1804/529, loss: 0.021540069952607155
2023-01-23 01:31:20.955176: step: 1808/529, loss: 0.07707672566175461
2023-01-23 01:31:22.116709: step: 1812/529, loss: 0.02854936011135578
2023-01-23 01:31:23.260458: step: 1816/529, loss: 0.037993669509887695
2023-01-23 01:31:24.400137: step: 1820/529, loss: 0.08730325847864151
2023-01-23 01:31:25.545476: step: 1824/529, loss: 0.05254373699426651
2023-01-23 01:31:26.697576: step: 1828/529, loss: 0.13970327377319336
2023-01-23 01:31:27.835005: step: 1832/529, loss: 0.02880268171429634
2023-01-23 01:31:28.975256: step: 1836/529, loss: 0.008268028497695923
2023-01-23 01:31:30.111161: step: 1840/529, loss: 0.10478801280260086
2023-01-23 01:31:31.283914: step: 1844/529, loss: 0.04279174655675888
2023-01-23 01:31:32.458564: step: 1848/529, loss: 0.12447204440832138
2023-01-23 01:31:33.592058: step: 1852/529, loss: 0.00900888442993164
2023-01-23 01:31:34.726534: step: 1856/529, loss: 0.015284538269042969
2023-01-23 01:31:35.859163: step: 1860/529, loss: 0.0898069441318512
2023-01-23 01:31:37.012859: step: 1864/529, loss: 0.11184167861938477
2023-01-23 01:31:38.161784: step: 1868/529, loss: 0.03919639438390732
2023-01-23 01:31:39.301027: step: 1872/529, loss: 0.03649768978357315
2023-01-23 01:31:40.448135: step: 1876/529, loss: 0.01764148473739624
2023-01-23 01:31:41.605527: step: 1880/529, loss: 0.44543614983558655
2023-01-23 01:31:42.747001: step: 1884/529, loss: 0.0774996280670166
2023-01-23 01:31:43.892719: step: 1888/529, loss: 0.05189252272248268
2023-01-23 01:31:45.120532: step: 1892/529, loss: 0.08855752646923065
2023-01-23 01:31:46.246553: step: 1896/529, loss: 0.04244070127606392
2023-01-23 01:31:47.394315: step: 1900/529, loss: 0.0645488053560257
2023-01-23 01:31:48.511931: step: 1904/529, loss: 0.033716440200805664
2023-01-23 01:31:49.675027: step: 1908/529, loss: 0.012368488125503063
2023-01-23 01:31:50.801650: step: 1912/529, loss: 0.04617509990930557
2023-01-23 01:31:51.917098: step: 1916/529, loss: 0.0032367706298828125
2023-01-23 01:31:53.063819: step: 1920/529, loss: 0.031805798411369324
2023-01-23 01:31:54.206822: step: 1924/529, loss: 0.1205202117562294
2023-01-23 01:31:55.346557: step: 1928/529, loss: 0.024872303009033203
2023-01-23 01:31:56.467186: step: 1932/529, loss: 0.0014486312866210938
2023-01-23 01:31:57.625608: step: 1936/529, loss: 0.009503459557890892
2023-01-23 01:31:58.740305: step: 1940/529, loss: 0.12899132072925568
2023-01-23 01:31:59.860677: step: 1944/529, loss: 0.004157447721809149
2023-01-23 01:32:00.999705: step: 1948/529, loss: 0.0014079094398766756
2023-01-23 01:32:02.115290: step: 1952/529, loss: 0.011880159378051758
2023-01-23 01:32:03.276959: step: 1956/529, loss: 0.025216009467840195
2023-01-23 01:32:04.425026: step: 1960/529, loss: 0.09297056496143341
2023-01-23 01:32:05.549345: step: 1964/529, loss: 0.0857691764831543
2023-01-23 01:32:06.681113: step: 1968/529, loss: 0.9529792666435242
2023-01-23 01:32:07.804272: step: 1972/529, loss: 0.27082690596580505
2023-01-23 01:32:08.941056: step: 1976/529, loss: 0.06855086982250214
2023-01-23 01:32:10.094236: step: 1980/529, loss: 0.2497449815273285
2023-01-23 01:32:11.261322: step: 1984/529, loss: 0.008680534549057484
2023-01-23 01:32:12.401495: step: 1988/529, loss: 0.27282285690307617
2023-01-23 01:32:13.572585: step: 1992/529, loss: 0.04147171974182129
2023-01-23 01:32:14.721951: step: 1996/529, loss: 0.015248488634824753
2023-01-23 01:32:15.883424: step: 2000/529, loss: 0.0354703888297081
2023-01-23 01:32:17.004333: step: 2004/529, loss: 0.0023620130959898233
2023-01-23 01:32:18.208120: step: 2008/529, loss: 0.024892903864383698
2023-01-23 01:32:19.363322: step: 2012/529, loss: 0.0019614219199866056
2023-01-23 01:32:20.506974: step: 2016/529, loss: 0.011834239587187767
2023-01-23 01:32:21.670085: step: 2020/529, loss: 0.014704895205795765
2023-01-23 01:32:22.823744: step: 2024/529, loss: 0.11264859139919281
2023-01-23 01:32:23.980087: step: 2028/529, loss: 0.13860435783863068
2023-01-23 01:32:25.116399: step: 2032/529, loss: 0.14688043296337128
2023-01-23 01:32:26.249009: step: 2036/529, loss: 0.05584259331226349
2023-01-23 01:32:27.403048: step: 2040/529, loss: 0.11217594146728516
2023-01-23 01:32:28.545755: step: 2044/529, loss: 0.1956554353237152
2023-01-23 01:32:29.692305: step: 2048/529, loss: 0.10633993148803711
2023-01-23 01:32:30.826030: step: 2052/529, loss: 0.0359223373234272
2023-01-23 01:32:31.955809: step: 2056/529, loss: 0.011312102898955345
2023-01-23 01:32:33.087791: step: 2060/529, loss: 0.11122951656579971
2023-01-23 01:32:34.230563: step: 2064/529, loss: 0.057933416217565536
2023-01-23 01:32:35.385061: step: 2068/529, loss: 0.019565392285585403
2023-01-23 01:32:36.555108: step: 2072/529, loss: 0.07759909331798553
2023-01-23 01:32:37.718738: step: 2076/529, loss: 0.05175838619470596
2023-01-23 01:32:38.837892: step: 2080/529, loss: 0.010888171382248402
2023-01-23 01:32:39.981277: step: 2084/529, loss: 0.05133819580078125
2023-01-23 01:32:41.109937: step: 2088/529, loss: 0.03733024373650551
2023-01-23 01:32:42.242408: step: 2092/529, loss: 0.015604972839355469
2023-01-23 01:32:43.381884: step: 2096/529, loss: 0.03483233600854874
2023-01-23 01:32:44.527426: step: 2100/529, loss: 0.0181745532900095
2023-01-23 01:32:45.656178: step: 2104/529, loss: 0.012670159339904785
2023-01-23 01:32:46.789413: step: 2108/529, loss: 0.0547761432826519
2023-01-23 01:32:47.948959: step: 2112/529, loss: 0.009130263701081276
2023-01-23 01:32:49.102566: step: 2116/529, loss: 0.11732816696166992
==================================================
Loss: 0.084
--------------------
Dev: {'event': {'p': 0.6038500506585613, 'r': 0.7936085219707057, 'f1': 0.6858457997698505}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6094974642692486, 'r': 0.7659327925840093, 'f1': 0.6788189987163029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5517241379310345, 'r': 0.8888888888888888, 'f1': 0.6808510638297872}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
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': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:33:30.838441: step: 4/529, loss: 0.009599877521395683
2023-01-23 01:33:31.963214: step: 8/529, loss: 0.05222933366894722
2023-01-23 01:33:33.089714: step: 12/529, loss: 0.06327927112579346
2023-01-23 01:33:34.213402: step: 16/529, loss: 0.055777840316295624
2023-01-23 01:33:35.367633: step: 20/529, loss: 0.00335693359375
2023-01-23 01:33:36.495168: step: 24/529, loss: 0.06440359354019165
2023-01-23 01:33:37.646632: step: 28/529, loss: 0.04398956149816513
2023-01-23 01:33:38.793222: step: 32/529, loss: 0.05248670652508736
2023-01-23 01:33:39.900578: step: 36/529, loss: 0.0849311351776123
2023-01-23 01:33:41.050551: step: 40/529, loss: 0.02024099975824356
2023-01-23 01:33:42.191126: step: 44/529, loss: 0.01705489121377468
2023-01-23 01:33:43.372397: step: 48/529, loss: 0.0442129410803318
2023-01-23 01:33:44.498230: step: 52/529, loss: 0.05578432232141495
2023-01-23 01:33:45.632232: step: 56/529, loss: 0.030672885477542877
2023-01-23 01:33:46.773213: step: 60/529, loss: 0.1617903858423233
2023-01-23 01:33:47.930882: step: 64/529, loss: 0.0031072618439793587
2023-01-23 01:33:49.097467: step: 68/529, loss: 0.10301484912633896
2023-01-23 01:33:50.227058: step: 72/529, loss: 0.005670642480254173
2023-01-23 01:33:51.356540: step: 76/529, loss: 0.09278325736522675
2023-01-23 01:33:52.504563: step: 80/529, loss: 0.0005670547834597528
2023-01-23 01:33:53.618454: step: 84/529, loss: 0.03500165790319443
2023-01-23 01:33:54.769703: step: 88/529, loss: 0.09778013825416565
2023-01-23 01:33:55.909896: step: 92/529, loss: 0.08888387680053711
2023-01-23 01:33:57.064857: step: 96/529, loss: 0.03051605261862278
2023-01-23 01:33:58.185747: step: 100/529, loss: 0.0037838458083570004
2023-01-23 01:33:59.305671: step: 104/529, loss: 0.04044532775878906
2023-01-23 01:34:00.450519: step: 108/529, loss: 0.0709843635559082
2023-01-23 01:34:01.577911: step: 112/529, loss: 0.03643383830785751
2023-01-23 01:34:02.704035: step: 116/529, loss: 0.0047227381728589535
2023-01-23 01:34:03.853673: step: 120/529, loss: 0.03100304678082466
2023-01-23 01:34:05.012239: step: 124/529, loss: 0.025669338181614876
2023-01-23 01:34:06.129078: step: 128/529, loss: 0.04012279585003853
2023-01-23 01:34:07.261695: step: 132/529, loss: 0.08746547996997833
2023-01-23 01:34:08.384464: step: 136/529, loss: 0.007591248024255037
2023-01-23 01:34:09.521150: step: 140/529, loss: 0.16226130723953247
2023-01-23 01:34:10.666716: step: 144/529, loss: 0.08277511596679688
2023-01-23 01:34:11.821890: step: 148/529, loss: 0.09894141554832458
2023-01-23 01:34:12.960901: step: 152/529, loss: 0.03770933300256729
2023-01-23 01:34:14.077946: step: 156/529, loss: 0.036876678466796875
2023-01-23 01:34:15.219300: step: 160/529, loss: 0.011736870743334293
2023-01-23 01:34:16.357659: step: 164/529, loss: 0.03053007274866104
2023-01-23 01:34:17.478549: step: 168/529, loss: 0.02890167199075222
2023-01-23 01:34:18.609633: step: 172/529, loss: 0.005604791454970837
2023-01-23 01:34:19.741725: step: 176/529, loss: 0.04822740703821182
2023-01-23 01:34:20.864044: step: 180/529, loss: 0.02780008316040039
2023-01-23 01:34:22.000056: step: 184/529, loss: 0.05961675941944122
2023-01-23 01:34:23.170687: step: 188/529, loss: 0.05668621137738228
2023-01-23 01:34:24.295027: step: 192/529, loss: 0.08477868884801865
2023-01-23 01:34:25.408009: step: 196/529, loss: 0.05289297178387642
2023-01-23 01:34:26.550476: step: 200/529, loss: 0.006886291783303022
2023-01-23 01:34:27.704182: step: 204/529, loss: 0.07418803870677948
2023-01-23 01:34:28.843005: step: 208/529, loss: 0.004151248838752508
2023-01-23 01:34:29.964805: step: 212/529, loss: 0.02871112897992134
2023-01-23 01:34:31.093856: step: 216/529, loss: 0.019187163561582565
2023-01-23 01:34:32.249229: step: 220/529, loss: 0.04193706437945366
2023-01-23 01:34:33.397664: step: 224/529, loss: 0.012210512533783913
2023-01-23 01:34:34.542376: step: 228/529, loss: 0.005512523930519819
2023-01-23 01:34:35.688464: step: 232/529, loss: 0.04316416010260582
2023-01-23 01:34:36.825120: step: 236/529, loss: 0.037366341799497604
2023-01-23 01:34:37.970299: step: 240/529, loss: 0.03855609893798828
2023-01-23 01:34:39.142698: step: 244/529, loss: 0.09604892134666443
2023-01-23 01:34:40.274328: step: 248/529, loss: 0.07038488239049911
2023-01-23 01:34:41.443573: step: 252/529, loss: 0.055687904357910156
2023-01-23 01:34:42.601625: step: 256/529, loss: 0.0026640892028808594
2023-01-23 01:34:43.748420: step: 260/529, loss: 0.06011056900024414
2023-01-23 01:34:44.883211: step: 264/529, loss: 0.026077603921294212
2023-01-23 01:34:46.038980: step: 268/529, loss: 0.027528000995516777
2023-01-23 01:34:47.187990: step: 272/529, loss: 0.17011794447898865
2023-01-23 01:34:48.313268: step: 276/529, loss: 0.012026202864944935
2023-01-23 01:34:49.447066: step: 280/529, loss: 0.047213364392519
2023-01-23 01:34:50.596233: step: 284/529, loss: 0.08218078315258026
2023-01-23 01:34:51.752633: step: 288/529, loss: 0.004873848054558039
2023-01-23 01:34:52.878894: step: 292/529, loss: 0.08538713306188583
2023-01-23 01:34:54.013772: step: 296/529, loss: 0.058156393468379974
2023-01-23 01:34:55.145535: step: 300/529, loss: 0.001339817070402205
2023-01-23 01:34:56.298846: step: 304/529, loss: 0.02874293550848961
2023-01-23 01:34:57.428661: step: 308/529, loss: 0.0029857635963708162
2023-01-23 01:34:58.588257: step: 312/529, loss: 0.009916496463119984
2023-01-23 01:34:59.742385: step: 316/529, loss: 0.08734360337257385
2023-01-23 01:35:00.907918: step: 320/529, loss: 0.05480532720685005
2023-01-23 01:35:02.072744: step: 324/529, loss: 0.008849096484482288
2023-01-23 01:35:03.267231: step: 328/529, loss: 0.01684398576617241
2023-01-23 01:35:04.407580: step: 332/529, loss: 0.006241226103156805
2023-01-23 01:35:05.515471: step: 336/529, loss: 0.007660579867660999
2023-01-23 01:35:06.712112: step: 340/529, loss: 0.0035522461403161287
2023-01-23 01:35:07.851316: step: 344/529, loss: 0.11639384925365448
2023-01-23 01:35:08.994270: step: 348/529, loss: 0.045095253735780716
2023-01-23 01:35:10.127314: step: 352/529, loss: 0.024739742279052734
2023-01-23 01:35:11.269563: step: 356/529, loss: 0.10741166770458221
2023-01-23 01:35:12.427918: step: 360/529, loss: 0.0057547567412257195
2023-01-23 01:35:13.559186: step: 364/529, loss: 0.03356199339032173
2023-01-23 01:35:14.712493: step: 368/529, loss: 0.052814170718193054
2023-01-23 01:35:15.849973: step: 372/529, loss: 0.008664015680551529
2023-01-23 01:35:16.987993: step: 376/529, loss: 0.01374511793255806
2023-01-23 01:35:18.147671: step: 380/529, loss: 0.017842482775449753
2023-01-23 01:35:19.293343: step: 384/529, loss: 0.06266383826732635
2023-01-23 01:35:20.460446: step: 388/529, loss: 0.0030565261840820312
2023-01-23 01:35:21.602933: step: 392/529, loss: 0.005564498715102673
2023-01-23 01:35:22.758324: step: 396/529, loss: 0.0850488692522049
2023-01-23 01:35:23.862091: step: 400/529, loss: 0.008472156710922718
2023-01-23 01:35:25.002899: step: 404/529, loss: 0.032532740384340286
2023-01-23 01:35:26.163764: step: 408/529, loss: 0.04038968309760094
2023-01-23 01:35:27.269085: step: 412/529, loss: 0.04558210074901581
2023-01-23 01:35:28.395653: step: 416/529, loss: 0.10349903255701065
2023-01-23 01:35:29.542250: step: 420/529, loss: 0.003133487654849887
2023-01-23 01:35:30.676929: step: 424/529, loss: 0.06093263626098633
2023-01-23 01:35:31.804413: step: 428/529, loss: 0.007752132602035999
2023-01-23 01:35:32.913289: step: 432/529, loss: 0.007301974575966597
2023-01-23 01:35:34.023798: step: 436/529, loss: 0.04609117656946182
2023-01-23 01:35:35.143007: step: 440/529, loss: 0.00887289084494114
2023-01-23 01:35:36.288901: step: 444/529, loss: 0.010225106030702591
2023-01-23 01:35:37.447308: step: 448/529, loss: 0.010163498111069202
2023-01-23 01:35:38.575745: step: 452/529, loss: 0.032201290130615234
2023-01-23 01:35:39.698375: step: 456/529, loss: 0.07714233547449112
2023-01-23 01:35:40.829083: step: 460/529, loss: 0.050862789154052734
2023-01-23 01:35:41.971975: step: 464/529, loss: 0.16744364798069
2023-01-23 01:35:43.123417: step: 468/529, loss: 0.06182861328125
2023-01-23 01:35:44.279999: step: 472/529, loss: 0.0007011413690634072
2023-01-23 01:35:45.409271: step: 476/529, loss: 0.010732650756835938
2023-01-23 01:35:46.553160: step: 480/529, loss: 0.03118162415921688
2023-01-23 01:35:47.697183: step: 484/529, loss: 0.028308773413300514
2023-01-23 01:35:48.840821: step: 488/529, loss: 0.031081723049283028
2023-01-23 01:35:49.963826: step: 492/529, loss: 0.018332291394472122
2023-01-23 01:35:51.188768: step: 496/529, loss: 0.0164140947163105
2023-01-23 01:35:52.348421: step: 500/529, loss: 0.0637664794921875
2023-01-23 01:35:53.484348: step: 504/529, loss: 0.10507993400096893
2023-01-23 01:35:54.635511: step: 508/529, loss: 0.017353488132357597
2023-01-23 01:35:55.789766: step: 512/529, loss: 0.005373883061110973
2023-01-23 01:35:56.932239: step: 516/529, loss: 0.08379878848791122
2023-01-23 01:35:58.064721: step: 520/529, loss: 0.10570697486400604
2023-01-23 01:35:59.217104: step: 524/529, loss: 0.023064803332090378
2023-01-23 01:36:00.327029: step: 528/529, loss: 0.019742680713534355
2023-01-23 01:36:01.435637: step: 532/529, loss: 0.0810873731970787
2023-01-23 01:36:02.577248: step: 536/529, loss: 0.043680526316165924
2023-01-23 01:36:03.698640: step: 540/529, loss: 0.04802761226892471
2023-01-23 01:36:04.876507: step: 544/529, loss: 0.06572437286376953
2023-01-23 01:36:06.017274: step: 548/529, loss: 0.003919410519301891
2023-01-23 01:36:07.142857: step: 552/529, loss: 0.013157462701201439
2023-01-23 01:36:08.296071: step: 556/529, loss: 0.2778494954109192
2023-01-23 01:36:09.452178: step: 560/529, loss: 0.09738927334547043
2023-01-23 01:36:10.625439: step: 564/529, loss: 0.0027718544006347656
2023-01-23 01:36:11.760158: step: 568/529, loss: 0.07343816757202148
2023-01-23 01:36:12.926120: step: 572/529, loss: 0.06742553412914276
2023-01-23 01:36:14.070920: step: 576/529, loss: 0.03533611074090004
2023-01-23 01:36:15.227680: step: 580/529, loss: 0.0640086680650711
2023-01-23 01:36:16.339224: step: 584/529, loss: 0.012063790112733841
2023-01-23 01:36:17.479270: step: 588/529, loss: 0.03139467537403107
2023-01-23 01:36:18.633954: step: 592/529, loss: 0.023262416943907738
2023-01-23 01:36:19.767156: step: 596/529, loss: 0.019202329218387604
2023-01-23 01:36:20.931061: step: 600/529, loss: 0.015586710534989834
2023-01-23 01:36:22.090622: step: 604/529, loss: 0.047947682440280914
2023-01-23 01:36:23.243088: step: 608/529, loss: 0.11125669628381729
2023-01-23 01:36:24.423259: step: 612/529, loss: 0.005725288297981024
2023-01-23 01:36:25.579670: step: 616/529, loss: 0.10224466770887375
2023-01-23 01:36:26.732581: step: 620/529, loss: 0.03097229078412056
2023-01-23 01:36:27.879320: step: 624/529, loss: 0.0586116798222065
2023-01-23 01:36:28.997623: step: 628/529, loss: 0.03724556043744087
2023-01-23 01:36:30.135551: step: 632/529, loss: 0.004291534423828125
2023-01-23 01:36:31.262868: step: 636/529, loss: 0.07390899211168289
2023-01-23 01:36:32.406588: step: 640/529, loss: 0.06829357147216797
2023-01-23 01:36:33.574558: step: 644/529, loss: 0.04636736214160919
2023-01-23 01:36:34.692781: step: 648/529, loss: 0.01751413382589817
2023-01-23 01:36:35.838609: step: 652/529, loss: 0.017524385824799538
2023-01-23 01:36:36.984336: step: 656/529, loss: 0.009670840576291084
2023-01-23 01:36:38.104235: step: 660/529, loss: 0.014430809766054153
2023-01-23 01:36:39.242321: step: 664/529, loss: 0.021681498736143112
2023-01-23 01:36:40.378169: step: 668/529, loss: 0.06616697460412979
2023-01-23 01:36:41.521966: step: 672/529, loss: 0.06775989383459091
2023-01-23 01:36:42.660352: step: 676/529, loss: 0.051607392728328705
2023-01-23 01:36:43.785673: step: 680/529, loss: 0.05058612674474716
2023-01-23 01:36:44.901667: step: 684/529, loss: 0.002528333803638816
2023-01-23 01:36:46.099687: step: 688/529, loss: 0.09183569252490997
2023-01-23 01:36:47.225385: step: 692/529, loss: 0.08151645958423615
2023-01-23 01:36:48.407560: step: 696/529, loss: 0.02961273491382599
2023-01-23 01:36:49.532537: step: 700/529, loss: 0.0008846282726153731
2023-01-23 01:36:50.696793: step: 704/529, loss: 0.15756511688232422
2023-01-23 01:36:51.846145: step: 708/529, loss: 0.06086301803588867
2023-01-23 01:36:53.000866: step: 712/529, loss: 0.01701936684548855
2023-01-23 01:36:54.146397: step: 716/529, loss: 0.0008195400005206466
2023-01-23 01:36:55.305002: step: 720/529, loss: 0.025336647406220436
2023-01-23 01:36:56.440950: step: 724/529, loss: 0.02629675902426243
2023-01-23 01:36:57.589647: step: 728/529, loss: 0.017276477068662643
2023-01-23 01:36:58.712552: step: 732/529, loss: 0.019921448081731796
2023-01-23 01:36:59.812113: step: 736/529, loss: 0.0005456447834149003
2023-01-23 01:37:00.947762: step: 740/529, loss: 0.030028486624360085
2023-01-23 01:37:02.104463: step: 744/529, loss: 0.09304457157850266
2023-01-23 01:37:03.263317: step: 748/529, loss: 0.03932990878820419
2023-01-23 01:37:04.384455: step: 752/529, loss: 0.06434869766235352
2023-01-23 01:37:05.539416: step: 756/529, loss: 0.06484080106019974
2023-01-23 01:37:06.652712: step: 760/529, loss: 0.05992784723639488
2023-01-23 01:37:07.796577: step: 764/529, loss: 0.027353955432772636
2023-01-23 01:37:08.973941: step: 768/529, loss: 0.05796634033322334
2023-01-23 01:37:10.110065: step: 772/529, loss: 0.0020380974747240543
2023-01-23 01:37:11.282869: step: 776/529, loss: 0.014320945367217064
2023-01-23 01:37:12.417840: step: 780/529, loss: 0.029306985437870026
2023-01-23 01:37:13.545172: step: 784/529, loss: 0.045825958251953125
2023-01-23 01:37:14.713984: step: 788/529, loss: 0.006955146789550781
2023-01-23 01:37:15.862739: step: 792/529, loss: 0.03657341003417969
2023-01-23 01:37:16.963204: step: 796/529, loss: 0.011964459903538227
2023-01-23 01:37:18.114186: step: 800/529, loss: 0.05966358631849289
2023-01-23 01:37:19.257822: step: 804/529, loss: 0.002954536583274603
2023-01-23 01:37:20.400776: step: 808/529, loss: 0.00522656412795186
2023-01-23 01:37:21.562077: step: 812/529, loss: 0.002196025801822543
2023-01-23 01:37:22.715785: step: 816/529, loss: 0.0021085739135742188
2023-01-23 01:37:23.840263: step: 820/529, loss: 0.16720938682556152
2023-01-23 01:37:24.966125: step: 824/529, loss: 0.0009832382202148438
2023-01-23 01:37:26.129536: step: 828/529, loss: 0.011444663628935814
2023-01-23 01:37:27.243378: step: 832/529, loss: 0.02932109870016575
2023-01-23 01:37:28.415457: step: 836/529, loss: 0.016179466620087624
2023-01-23 01:37:29.578055: step: 840/529, loss: 0.45787420868873596
2023-01-23 01:37:30.715406: step: 844/529, loss: 0.14280928671360016
2023-01-23 01:37:31.843880: step: 848/529, loss: 0.05953960120677948
2023-01-23 01:37:33.012206: step: 852/529, loss: 0.05152187496423721
2023-01-23 01:37:34.140641: step: 856/529, loss: 0.09777195751667023
2023-01-23 01:37:35.282314: step: 860/529, loss: 0.09475746005773544
2023-01-23 01:37:36.418589: step: 864/529, loss: 0.005778599064797163
2023-01-23 01:37:37.547606: step: 868/529, loss: 0.0038797378074377775
2023-01-23 01:37:38.680984: step: 872/529, loss: 0.0001352310209767893
2023-01-23 01:37:39.831643: step: 876/529, loss: 0.004854965023696423
2023-01-23 01:37:40.955765: step: 880/529, loss: 0.043163299560546875
2023-01-23 01:37:42.098749: step: 884/529, loss: 0.1254405975341797
2023-01-23 01:37:43.242901: step: 888/529, loss: 0.00938568077981472
2023-01-23 01:37:44.376907: step: 892/529, loss: 0.0840395987033844
2023-01-23 01:37:45.484091: step: 896/529, loss: 0.01646900177001953
2023-01-23 01:37:46.667250: step: 900/529, loss: 0.0025002004113048315
2023-01-23 01:37:47.810758: step: 904/529, loss: 0.01778726652264595
2023-01-23 01:37:48.958088: step: 908/529, loss: 0.014309407211840153
2023-01-23 01:37:50.109893: step: 912/529, loss: 0.14741039276123047
2023-01-23 01:37:51.259486: step: 916/529, loss: 0.04818916320800781
2023-01-23 01:37:52.403724: step: 920/529, loss: 0.005638504400849342
2023-01-23 01:37:53.561087: step: 924/529, loss: 0.06700392067432404
2023-01-23 01:37:54.685256: step: 928/529, loss: 0.011551285162568092
2023-01-23 01:37:55.858015: step: 932/529, loss: 0.009420013055205345
2023-01-23 01:37:57.000222: step: 936/529, loss: 0.03510008007287979
2023-01-23 01:37:58.170544: step: 940/529, loss: 0.04221782460808754
2023-01-23 01:37:59.318612: step: 944/529, loss: 0.045285772532224655
2023-01-23 01:38:00.440548: step: 948/529, loss: 0.022705204784870148
2023-01-23 01:38:01.576419: step: 952/529, loss: 0.035432007163763046
2023-01-23 01:38:02.704371: step: 956/529, loss: 0.013840675354003906
2023-01-23 01:38:03.863434: step: 960/529, loss: 0.04016897827386856
2023-01-23 01:38:05.001254: step: 964/529, loss: 0.0026357651222497225
2023-01-23 01:38:06.118770: step: 968/529, loss: 0.06760015338659286
2023-01-23 01:38:07.307346: step: 972/529, loss: 0.04548444598913193
2023-01-23 01:38:08.425518: step: 976/529, loss: 0.06658191233873367
2023-01-23 01:38:09.573695: step: 980/529, loss: 0.024829866364598274
2023-01-23 01:38:10.692528: step: 984/529, loss: 0.06164813041687012
2023-01-23 01:38:11.845230: step: 988/529, loss: 0.03172893822193146
2023-01-23 01:38:12.978774: step: 992/529, loss: 0.03628425672650337
2023-01-23 01:38:14.099831: step: 996/529, loss: 0.012101937085390091
2023-01-23 01:38:15.272573: step: 1000/529, loss: 0.0015178680187091231
2023-01-23 01:38:16.420011: step: 1004/529, loss: 0.0031326294410973787
2023-01-23 01:38:17.562084: step: 1008/529, loss: 0.0817171111702919
2023-01-23 01:38:18.720867: step: 1012/529, loss: 0.04501743242144585
2023-01-23 01:38:19.855724: step: 1016/529, loss: 0.007783698849380016
2023-01-23 01:38:20.987439: step: 1020/529, loss: 0.00141820905264467
2023-01-23 01:38:22.148703: step: 1024/529, loss: 0.03396713733673096
2023-01-23 01:38:23.307802: step: 1028/529, loss: 0.08785443007946014
2023-01-23 01:38:24.453188: step: 1032/529, loss: 0.005506038665771484
2023-01-23 01:38:25.651731: step: 1036/529, loss: 0.7554685473442078
2023-01-23 01:38:26.813078: step: 1040/529, loss: 0.10742369294166565
2023-01-23 01:38:27.939711: step: 1044/529, loss: 0.042765043675899506
2023-01-23 01:38:29.116348: step: 1048/529, loss: 0.010907554998993874
2023-01-23 01:38:30.231454: step: 1052/529, loss: 0.09366540610790253
2023-01-23 01:38:31.391653: step: 1056/529, loss: 0.0018295288318768144
2023-01-23 01:38:32.532964: step: 1060/529, loss: 0.03758659586310387
2023-01-23 01:38:33.676943: step: 1064/529, loss: 0.0420774444937706
2023-01-23 01:38:34.799247: step: 1068/529, loss: 0.03819551318883896
2023-01-23 01:38:35.934433: step: 1072/529, loss: 0.022656060755252838
2023-01-23 01:38:37.073471: step: 1076/529, loss: 0.004863167181611061
2023-01-23 01:38:38.215465: step: 1080/529, loss: 0.003184795379638672
2023-01-23 01:38:39.375899: step: 1084/529, loss: 0.009426689706742764
2023-01-23 01:38:40.507190: step: 1088/529, loss: 0.060143519192934036
2023-01-23 01:38:41.629982: step: 1092/529, loss: 0.0052474020048975945
2023-01-23 01:38:42.764666: step: 1096/529, loss: 0.007507228758186102
2023-01-23 01:38:43.909993: step: 1100/529, loss: 0.034093573689460754
2023-01-23 01:38:45.085806: step: 1104/529, loss: 0.039986610412597656
2023-01-23 01:38:46.221782: step: 1108/529, loss: 0.027509402483701706
2023-01-23 01:38:47.374613: step: 1112/529, loss: 0.013420677743852139
2023-01-23 01:38:48.519215: step: 1116/529, loss: 0.024685287848114967
2023-01-23 01:38:49.644949: step: 1120/529, loss: 0.05600138008594513
2023-01-23 01:38:50.773225: step: 1124/529, loss: 0.1418040245771408
2023-01-23 01:38:51.904766: step: 1128/529, loss: 0.01038274820894003
2023-01-23 01:38:53.065745: step: 1132/529, loss: 0.036375001072883606
2023-01-23 01:38:54.223467: step: 1136/529, loss: 0.01700592041015625
2023-01-23 01:38:55.345158: step: 1140/529, loss: 0.0056282044388353825
2023-01-23 01:38:56.492464: step: 1144/529, loss: 0.006110859103500843
2023-01-23 01:38:57.625020: step: 1148/529, loss: 0.06296902149915695
2023-01-23 01:38:58.756650: step: 1152/529, loss: 0.11532774567604065
2023-01-23 01:38:59.879404: step: 1156/529, loss: 0.0735454112291336
2023-01-23 01:39:01.022994: step: 1160/529, loss: 0.2641119062900543
2023-01-23 01:39:02.178381: step: 1164/529, loss: 0.0187851432710886
2023-01-23 01:39:03.313987: step: 1168/529, loss: 0.018866728991270065
2023-01-23 01:39:04.433385: step: 1172/529, loss: 0.04534149542450905
2023-01-23 01:39:05.602372: step: 1176/529, loss: 0.037976741790771484
2023-01-23 01:39:06.767486: step: 1180/529, loss: 0.03110940381884575
2023-01-23 01:39:07.916143: step: 1184/529, loss: 0.043977927416563034
2023-01-23 01:39:09.051814: step: 1188/529, loss: 0.016446590423583984
2023-01-23 01:39:10.190451: step: 1192/529, loss: 0.009401321411132812
2023-01-23 01:39:11.322893: step: 1196/529, loss: 0.005697441287338734
2023-01-23 01:39:12.477515: step: 1200/529, loss: 0.054293442517519
2023-01-23 01:39:13.649832: step: 1204/529, loss: 0.02964916080236435
2023-01-23 01:39:14.756007: step: 1208/529, loss: 0.07031688839197159
2023-01-23 01:39:15.913429: step: 1212/529, loss: 0.049356937408447266
2023-01-23 01:39:17.058976: step: 1216/529, loss: 0.017296219244599342
2023-01-23 01:39:18.192676: step: 1220/529, loss: 0.006849432364106178
2023-01-23 01:39:19.352255: step: 1224/529, loss: 0.007527542300522327
2023-01-23 01:39:20.503360: step: 1228/529, loss: 0.06866807490587234
2023-01-23 01:39:21.639788: step: 1232/529, loss: 0.18938341736793518
2023-01-23 01:39:22.795798: step: 1236/529, loss: 0.08155861496925354
2023-01-23 01:39:23.938932: step: 1240/529, loss: 0.029927443712949753
2023-01-23 01:39:25.063705: step: 1244/529, loss: 0.051896288990974426
2023-01-23 01:39:26.192506: step: 1248/529, loss: 0.024506758898496628
2023-01-23 01:39:27.349344: step: 1252/529, loss: 0.05853986740112305
2023-01-23 01:39:28.488787: step: 1256/529, loss: 0.001984023954719305
2023-01-23 01:39:29.628011: step: 1260/529, loss: 0.04619855806231499
2023-01-23 01:39:30.769313: step: 1264/529, loss: 0.047243308275938034
2023-01-23 01:39:31.907164: step: 1268/529, loss: 0.04430665820837021
2023-01-23 01:39:33.028545: step: 1272/529, loss: 0.01496591605246067
2023-01-23 01:39:34.165541: step: 1276/529, loss: 0.09296198189258575
2023-01-23 01:39:35.312504: step: 1280/529, loss: 0.0359838493168354
2023-01-23 01:39:36.453468: step: 1284/529, loss: 0.029023757204413414
2023-01-23 01:39:37.626872: step: 1288/529, loss: 0.9746854901313782
2023-01-23 01:39:38.766922: step: 1292/529, loss: 0.18511143326759338
2023-01-23 01:39:39.925995: step: 1296/529, loss: 0.04672403261065483
2023-01-23 01:39:41.078406: step: 1300/529, loss: 0.03355436399579048
2023-01-23 01:39:42.214564: step: 1304/529, loss: 0.023637771606445312
2023-01-23 01:39:43.404578: step: 1308/529, loss: 0.12433824688196182
2023-01-23 01:39:44.563227: step: 1312/529, loss: 0.0066044810228049755
2023-01-23 01:39:45.713543: step: 1316/529, loss: 0.0436527244746685
2023-01-23 01:39:46.831730: step: 1320/529, loss: 0.0006201743963174522
2023-01-23 01:39:47.951795: step: 1324/529, loss: 0.024755384773015976
2023-01-23 01:39:49.120562: step: 1328/529, loss: 0.07917232811450958
2023-01-23 01:39:50.299549: step: 1332/529, loss: 0.013935089111328125
2023-01-23 01:39:51.442955: step: 1336/529, loss: 0.05790986865758896
2023-01-23 01:39:52.579915: step: 1340/529, loss: 0.013862133957445621
2023-01-23 01:39:53.720622: step: 1344/529, loss: 0.01408529281616211
2023-01-23 01:39:54.840279: step: 1348/529, loss: 0.019444739446043968
2023-01-23 01:39:55.983282: step: 1352/529, loss: 0.06703615188598633
2023-01-23 01:39:57.139095: step: 1356/529, loss: 0.14207935333251953
2023-01-23 01:39:58.300521: step: 1360/529, loss: 0.0772436112165451
2023-01-23 01:39:59.446973: step: 1364/529, loss: 0.047171495854854584
2023-01-23 01:40:00.622517: step: 1368/529, loss: 0.005540227983146906
2023-01-23 01:40:01.786731: step: 1372/529, loss: 0.040296077728271484
2023-01-23 01:40:02.953448: step: 1376/529, loss: 0.007160187233239412
2023-01-23 01:40:04.057863: step: 1380/529, loss: 0.008231687359511852
2023-01-23 01:40:05.188025: step: 1384/529, loss: 0.013277912512421608
2023-01-23 01:40:06.298247: step: 1388/529, loss: 0.23824390769004822
2023-01-23 01:40:07.438806: step: 1392/529, loss: 0.006083154585212469
2023-01-23 01:40:08.567896: step: 1396/529, loss: 0.03039703331887722
2023-01-23 01:40:09.684869: step: 1400/529, loss: 0.040851689875125885
2023-01-23 01:40:10.864307: step: 1404/529, loss: 0.013806152157485485
2023-01-23 01:40:12.034043: step: 1408/529, loss: 0.12582091987133026
2023-01-23 01:40:13.159901: step: 1412/529, loss: 0.04688234254717827
2023-01-23 01:40:14.314692: step: 1416/529, loss: 0.014122772961854935
2023-01-23 01:40:15.416264: step: 1420/529, loss: 0.15463829040527344
2023-01-23 01:40:16.567891: step: 1424/529, loss: 0.06169462203979492
2023-01-23 01:40:17.697064: step: 1428/529, loss: 0.1042117103934288
2023-01-23 01:40:18.851585: step: 1432/529, loss: 0.7648319602012634
2023-01-23 01:40:19.990886: step: 1436/529, loss: 0.006183910649269819
2023-01-23 01:40:21.121186: step: 1440/529, loss: 0.13220424950122833
2023-01-23 01:40:22.256569: step: 1444/529, loss: 0.47135886549949646
2023-01-23 01:40:23.379523: step: 1448/529, loss: 0.3208070695400238
2023-01-23 01:40:24.522886: step: 1452/529, loss: 0.05192179977893829
2023-01-23 01:40:25.684053: step: 1456/529, loss: 0.11350338160991669
2023-01-23 01:40:26.818826: step: 1460/529, loss: 0.023944854736328125
2023-01-23 01:40:27.931183: step: 1464/529, loss: 0.006532740779221058
2023-01-23 01:40:29.088843: step: 1468/529, loss: 0.025796595960855484
2023-01-23 01:40:30.271339: step: 1472/529, loss: 0.01515111979097128
2023-01-23 01:40:31.421743: step: 1476/529, loss: 0.006575917825102806
2023-01-23 01:40:32.584039: step: 1480/529, loss: 0.0012142182094976306
2023-01-23 01:40:33.737871: step: 1484/529, loss: 0.0015543936751782894
2023-01-23 01:40:34.896546: step: 1488/529, loss: 0.6960460543632507
2023-01-23 01:40:36.079827: step: 1492/529, loss: 0.13783079385757446
2023-01-23 01:40:37.226537: step: 1496/529, loss: 0.002954196883365512
2023-01-23 01:40:38.359287: step: 1500/529, loss: 0.04598264768719673
2023-01-23 01:40:39.521111: step: 1504/529, loss: 0.04302208125591278
2023-01-23 01:40:40.664003: step: 1508/529, loss: 0.13760700821876526
2023-01-23 01:40:41.806502: step: 1512/529, loss: 0.08358879387378693
2023-01-23 01:40:42.953623: step: 1516/529, loss: 0.03550577163696289
2023-01-23 01:40:44.052341: step: 1520/529, loss: 0.05867529287934303
2023-01-23 01:40:45.186069: step: 1524/529, loss: 0.015043259598314762
2023-01-23 01:40:46.331161: step: 1528/529, loss: 0.049494028091430664
2023-01-23 01:40:47.488371: step: 1532/529, loss: 0.058661751449108124
2023-01-23 01:40:48.636345: step: 1536/529, loss: 0.0775054469704628
2023-01-23 01:40:49.777849: step: 1540/529, loss: 0.40463846921920776
2023-01-23 01:40:50.889055: step: 1544/529, loss: 0.12960176169872284
2023-01-23 01:40:52.025736: step: 1548/529, loss: 0.11314563453197479
2023-01-23 01:40:53.150219: step: 1552/529, loss: 0.008826208300888538
2023-01-23 01:40:54.306555: step: 1556/529, loss: 0.018711376935243607
2023-01-23 01:40:55.471911: step: 1560/529, loss: 0.4075283110141754
2023-01-23 01:40:56.627823: step: 1564/529, loss: 0.4174271523952484
2023-01-23 01:40:57.798181: step: 1568/529, loss: 0.0032883407548069954
2023-01-23 01:40:58.927359: step: 1572/529, loss: 0.028062917292118073
2023-01-23 01:41:00.091991: step: 1576/529, loss: 0.06418509781360626
2023-01-23 01:41:01.251169: step: 1580/529, loss: 0.39848265051841736
2023-01-23 01:41:02.376444: step: 1584/529, loss: 0.03924448415637016
2023-01-23 01:41:03.517396: step: 1588/529, loss: 0.014502717182040215
2023-01-23 01:41:04.675890: step: 1592/529, loss: 0.023236466571688652
2023-01-23 01:41:05.797877: step: 1596/529, loss: 0.36373335123062134
2023-01-23 01:41:06.987085: step: 1600/529, loss: 0.06777782738208771
2023-01-23 01:41:08.138576: step: 1604/529, loss: 0.05396628752350807
2023-01-23 01:41:09.284613: step: 1608/529, loss: 0.03881688043475151
2023-01-23 01:41:10.439485: step: 1612/529, loss: 0.02200622670352459
2023-01-23 01:41:11.592602: step: 1616/529, loss: 0.04023432731628418
2023-01-23 01:41:12.716906: step: 1620/529, loss: 0.06971673667430878
2023-01-23 01:41:13.827559: step: 1624/529, loss: 0.08448925614356995
2023-01-23 01:41:14.951689: step: 1628/529, loss: 0.04024811089038849
2023-01-23 01:41:16.098181: step: 1632/529, loss: 0.024126671254634857
2023-01-23 01:41:17.224685: step: 1636/529, loss: 0.0516846664249897
2023-01-23 01:41:18.355647: step: 1640/529, loss: 0.04051714017987251
2023-01-23 01:41:19.508003: step: 1644/529, loss: 0.009109973907470703
2023-01-23 01:41:20.664206: step: 1648/529, loss: 0.03788652643561363
2023-01-23 01:41:21.835699: step: 1652/529, loss: 0.011710261926054955
2023-01-23 01:41:22.982966: step: 1656/529, loss: 0.02306833304464817
2023-01-23 01:41:24.165016: step: 1660/529, loss: 0.04119815677404404
2023-01-23 01:41:25.321981: step: 1664/529, loss: 0.0015746117569506168
2023-01-23 01:41:26.445909: step: 1668/529, loss: 0.017468642443418503
2023-01-23 01:41:27.562116: step: 1672/529, loss: 0.002208232879638672
2023-01-23 01:41:28.687344: step: 1676/529, loss: 0.017556989565491676
2023-01-23 01:41:29.827657: step: 1680/529, loss: 0.08904094994068146
2023-01-23 01:41:30.963613: step: 1684/529, loss: 0.02933357283473015
2023-01-23 01:41:32.091183: step: 1688/529, loss: 0.07072000950574875
2023-01-23 01:41:33.215619: step: 1692/529, loss: 0.011268901638686657
2023-01-23 01:41:34.314430: step: 1696/529, loss: 0.06895160675048828
2023-01-23 01:41:35.508815: step: 1700/529, loss: 0.028394699096679688
2023-01-23 01:41:36.696712: step: 1704/529, loss: 1.0956612825393677
2023-01-23 01:41:37.840593: step: 1708/529, loss: 0.042693473398685455
2023-01-23 01:41:39.006430: step: 1712/529, loss: 0.106645368039608
2023-01-23 01:41:40.173664: step: 1716/529, loss: 0.01604471169412136
2023-01-23 01:41:41.318600: step: 1720/529, loss: 0.006686401553452015
2023-01-23 01:41:42.470065: step: 1724/529, loss: 0.19760455191135406
2023-01-23 01:41:43.654240: step: 1728/529, loss: 0.04504687711596489
2023-01-23 01:41:44.810067: step: 1732/529, loss: 0.029277395457029343
2023-01-23 01:41:45.951779: step: 1736/529, loss: 0.05705766752362251
2023-01-23 01:41:47.107282: step: 1740/529, loss: 0.13684529066085815
2023-01-23 01:41:48.266845: step: 1744/529, loss: 0.03550753742456436
2023-01-23 01:41:49.405901: step: 1748/529, loss: 0.04758463054895401
2023-01-23 01:41:50.532318: step: 1752/529, loss: 0.012179756537079811
2023-01-23 01:41:51.655987: step: 1756/529, loss: 0.02662181854248047
2023-01-23 01:41:52.810493: step: 1760/529, loss: 0.08154463768005371
2023-01-23 01:41:53.951496: step: 1764/529, loss: 0.08133916556835175
2023-01-23 01:41:55.082600: step: 1768/529, loss: 0.00993881281465292
2023-01-23 01:41:56.237101: step: 1772/529, loss: 0.06253661960363388
2023-01-23 01:41:57.344161: step: 1776/529, loss: 0.01262588519603014
2023-01-23 01:41:58.496327: step: 1780/529, loss: 0.01673126220703125
2023-01-23 01:41:59.612963: step: 1784/529, loss: 0.015593529678881168
2023-01-23 01:42:00.780259: step: 1788/529, loss: 0.07304706424474716
2023-01-23 01:42:01.894193: step: 1792/529, loss: 0.19124622642993927
2023-01-23 01:42:03.054689: step: 1796/529, loss: 0.04656529426574707
2023-01-23 01:42:04.182985: step: 1800/529, loss: 0.0666409507393837
2023-01-23 01:42:05.344985: step: 1804/529, loss: 0.12291279435157776
2023-01-23 01:42:06.494447: step: 1808/529, loss: 0.03063497692346573
2023-01-23 01:42:07.660686: step: 1812/529, loss: 0.010074997320771217
2023-01-23 01:42:08.816651: step: 1816/529, loss: 0.04221305996179581
2023-01-23 01:42:09.951912: step: 1820/529, loss: 0.04090938717126846
2023-01-23 01:42:11.086730: step: 1824/529, loss: 0.10782096534967422
2023-01-23 01:42:12.242839: step: 1828/529, loss: 0.04785943031311035
2023-01-23 01:42:13.369003: step: 1832/529, loss: 0.00011295080184936523
2023-01-23 01:42:14.501976: step: 1836/529, loss: 0.579179584980011
2023-01-23 01:42:15.677285: step: 1840/529, loss: 0.04755387455224991
2023-01-23 01:42:16.823712: step: 1844/529, loss: 0.013316750526428223
2023-01-23 01:42:17.991345: step: 1848/529, loss: 0.03761430084705353
2023-01-23 01:42:19.143945: step: 1852/529, loss: 0.0030691148713231087
2023-01-23 01:42:20.261335: step: 1856/529, loss: 0.036391064524650574
2023-01-23 01:42:21.396414: step: 1860/529, loss: 0.004856681916862726
2023-01-23 01:42:22.523389: step: 1864/529, loss: 0.039927005767822266
2023-01-23 01:42:23.682484: step: 1868/529, loss: 0.05290422588586807
2023-01-23 01:42:24.818848: step: 1872/529, loss: 0.09407234191894531
2023-01-23 01:42:25.927424: step: 1876/529, loss: 0.024172117933630943
2023-01-23 01:42:27.049724: step: 1880/529, loss: 0.032428935170173645
2023-01-23 01:42:28.158859: step: 1884/529, loss: 0.04099474102258682
2023-01-23 01:42:29.304247: step: 1888/529, loss: 0.0036382675170898438
2023-01-23 01:42:30.428560: step: 1892/529, loss: 0.02134869061410427
2023-01-23 01:42:31.571125: step: 1896/529, loss: 0.02146444469690323
2023-01-23 01:42:32.752324: step: 1900/529, loss: 0.0011233330005779862
2023-01-23 01:42:33.914598: step: 1904/529, loss: 0.14567409455776215
2023-01-23 01:42:35.073615: step: 1908/529, loss: 0.015575027093291283
2023-01-23 01:42:36.192707: step: 1912/529, loss: 0.0479520782828331
2023-01-23 01:42:37.314625: step: 1916/529, loss: 0.02944030798971653
2023-01-23 01:42:38.450443: step: 1920/529, loss: 0.016190147027373314
2023-01-23 01:42:39.581710: step: 1924/529, loss: 0.037545107305049896
2023-01-23 01:42:40.722134: step: 1928/529, loss: 0.02879791334271431
2023-01-23 01:42:41.853336: step: 1932/529, loss: 0.01570892333984375
2023-01-23 01:42:43.015868: step: 1936/529, loss: 0.06906204670667648
2023-01-23 01:42:44.165110: step: 1940/529, loss: 0.023740483447909355
2023-01-23 01:42:45.316850: step: 1944/529, loss: 0.07427291572093964
2023-01-23 01:42:46.453974: step: 1948/529, loss: 0.023793792352080345
2023-01-23 01:42:47.572278: step: 1952/529, loss: 0.027672769501805305
2023-01-23 01:42:48.722160: step: 1956/529, loss: 0.024505263194441795
2023-01-23 01:42:49.868126: step: 1960/529, loss: 0.012414837256073952
2023-01-23 01:42:51.011563: step: 1964/529, loss: 0.026230812072753906
2023-01-23 01:42:52.151118: step: 1968/529, loss: 0.018483638763427734
2023-01-23 01:42:53.277092: step: 1972/529, loss: 9.117127046920359e-05
2023-01-23 01:42:54.426550: step: 1976/529, loss: 0.12292156368494034
2023-01-23 01:42:55.572702: step: 1980/529, loss: 0.013800477609038353
2023-01-23 01:42:56.724744: step: 1984/529, loss: 0.01651925966143608
2023-01-23 01:42:57.857605: step: 1988/529, loss: 0.02746448665857315
2023-01-23 01:42:58.996909: step: 1992/529, loss: 0.20702160894870758
2023-01-23 01:43:00.140781: step: 1996/529, loss: 0.06955838203430176
2023-01-23 01:43:01.256207: step: 2000/529, loss: 0.048099711537361145
2023-01-23 01:43:02.376426: step: 2004/529, loss: 0.0075654988177120686
2023-01-23 01:43:03.520222: step: 2008/529, loss: 0.06574840843677521
2023-01-23 01:43:04.683708: step: 2012/529, loss: 0.01720752939581871
2023-01-23 01:43:05.837952: step: 2016/529, loss: 0.03441762924194336
2023-01-23 01:43:06.958737: step: 2020/529, loss: 0.0008242607582360506
2023-01-23 01:43:08.100223: step: 2024/529, loss: 0.07475261390209198
2023-01-23 01:43:09.231832: step: 2028/529, loss: 0.09648562222719193
2023-01-23 01:43:10.384247: step: 2032/529, loss: 0.03050060383975506
2023-01-23 01:43:11.528772: step: 2036/529, loss: 0.020706940442323685
2023-01-23 01:43:12.686346: step: 2040/529, loss: 0.03740882873535156
2023-01-23 01:43:13.857621: step: 2044/529, loss: 0.047423794865608215
2023-01-23 01:43:15.006426: step: 2048/529, loss: 0.054579734802246094
2023-01-23 01:43:16.130612: step: 2052/529, loss: 0.006700319238007069
2023-01-23 01:43:17.253214: step: 2056/529, loss: 0.00593195017427206
2023-01-23 01:43:18.383060: step: 2060/529, loss: 0.9261052012443542
2023-01-23 01:43:19.554597: step: 2064/529, loss: 0.010789108462631702
2023-01-23 01:43:20.674663: step: 2068/529, loss: 0.01773672178387642
2023-01-23 01:43:21.813262: step: 2072/529, loss: 0.025397587567567825
2023-01-23 01:43:22.941268: step: 2076/529, loss: 0.017604541033506393
2023-01-23 01:43:24.048826: step: 2080/529, loss: 0.0047149658203125
2023-01-23 01:43:25.199438: step: 2084/529, loss: 0.09763198345899582
2023-01-23 01:43:26.346235: step: 2088/529, loss: 0.22763033211231232
2023-01-23 01:43:27.495547: step: 2092/529, loss: 0.12451066821813583
2023-01-23 01:43:28.637717: step: 2096/529, loss: 0.0216109286993742
2023-01-23 01:43:29.763507: step: 2100/529, loss: 0.05923175811767578
2023-01-23 01:43:30.895730: step: 2104/529, loss: 0.08895035088062286
2023-01-23 01:43:32.028210: step: 2108/529, loss: 0.4702809751033783
2023-01-23 01:43:33.197333: step: 2112/529, loss: 0.03024921379983425
2023-01-23 01:43:34.331585: step: 2116/529, loss: 0.03227867931127548
==================================================
Loss: 0.061
--------------------
Dev: {'event': {'p': 0.6184782608695653, 'r': 0.7576564580559254, 'f1': 0.6810293237582286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6239924134660977, 'r': 0.7624565469293163, 'f1': 0.6863102998696219}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5348837209302325, 'r': 0.8518518518518519, 'f1': 0.6571428571428571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.5128205128205128, 'r': 0.5555555555555556, 'f1': 0.5333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:44:15.753372: step: 4/529, loss: 0.019993305206298828
2023-01-23 01:44:16.903515: step: 8/529, loss: 0.02758360095322132
2023-01-23 01:44:18.038618: step: 12/529, loss: 0.0386652834713459
2023-01-23 01:44:19.185526: step: 16/529, loss: 0.04045925289392471
2023-01-23 01:44:20.313074: step: 20/529, loss: 0.005299663636833429
2023-01-23 01:44:21.448669: step: 24/529, loss: 0.03268828243017197
2023-01-23 01:44:22.615413: step: 28/529, loss: 0.006821060553193092
2023-01-23 01:44:23.758055: step: 32/529, loss: 0.060141950845718384
2023-01-23 01:44:24.887965: step: 36/529, loss: 0.08947410434484482
2023-01-23 01:44:26.030709: step: 40/529, loss: 0.005906868260353804
2023-01-23 01:44:27.187206: step: 44/529, loss: 0.005701541900634766
2023-01-23 01:44:28.346369: step: 48/529, loss: 0.05475273355841637
2023-01-23 01:44:29.470776: step: 52/529, loss: 0.049897994846105576
2023-01-23 01:44:30.608114: step: 56/529, loss: 0.0092627527192235
2023-01-23 01:44:31.750087: step: 60/529, loss: 0.003398799803107977
2023-01-23 01:44:32.901816: step: 64/529, loss: 0.04215526580810547
2023-01-23 01:44:34.071797: step: 68/529, loss: 0.0023714066483080387
2023-01-23 01:44:35.248371: step: 72/529, loss: 0.02426781691610813
2023-01-23 01:44:36.371556: step: 76/529, loss: 0.058391764760017395
2023-01-23 01:44:37.482834: step: 80/529, loss: 0.05724773555994034
2023-01-23 01:44:38.602949: step: 84/529, loss: 0.014653205871582031
2023-01-23 01:44:39.772665: step: 88/529, loss: 0.04702577739953995
2023-01-23 01:44:40.919435: step: 92/529, loss: 0.12947197258472443
2023-01-23 01:44:42.093654: step: 96/529, loss: 0.012953282333910465
2023-01-23 01:44:43.268800: step: 100/529, loss: 0.04952354356646538
2023-01-23 01:44:44.415591: step: 104/529, loss: 0.0255808774381876
2023-01-23 01:44:45.581209: step: 108/529, loss: 0.04384269565343857
2023-01-23 01:44:46.711770: step: 112/529, loss: 0.0018137454753741622
2023-01-23 01:44:47.829867: step: 116/529, loss: 0.04469194635748863
2023-01-23 01:44:49.019364: step: 120/529, loss: 0.05742548406124115
2023-01-23 01:44:50.157822: step: 124/529, loss: 0.003180885221809149
2023-01-23 01:44:51.291584: step: 128/529, loss: 0.054470207542181015
2023-01-23 01:44:52.440590: step: 132/529, loss: 0.07437200844287872
2023-01-23 01:44:53.578046: step: 136/529, loss: 0.042356204241514206
2023-01-23 01:44:54.722436: step: 140/529, loss: 0.2078346312046051
2023-01-23 01:44:55.864022: step: 144/529, loss: 0.18840885162353516
2023-01-23 01:44:56.992193: step: 148/529, loss: 0.013764859177172184
2023-01-23 01:44:58.111951: step: 152/529, loss: 0.019231222569942474
2023-01-23 01:44:59.240401: step: 156/529, loss: 0.061971474438905716
2023-01-23 01:45:00.384616: step: 160/529, loss: 0.12830591201782227
2023-01-23 01:45:01.546299: step: 164/529, loss: 0.033579349517822266
2023-01-23 01:45:02.686912: step: 168/529, loss: 0.030616380274295807
2023-01-23 01:45:03.841007: step: 172/529, loss: 0.015859533101320267
2023-01-23 01:45:04.980823: step: 176/529, loss: 0.0979946106672287
2023-01-23 01:45:06.174266: step: 180/529, loss: 0.019607067108154297
2023-01-23 01:45:07.311674: step: 184/529, loss: 0.047873977571725845
2023-01-23 01:45:08.458179: step: 188/529, loss: 0.055992770940065384
2023-01-23 01:45:09.603037: step: 192/529, loss: 0.07307066768407822
2023-01-23 01:45:10.718659: step: 196/529, loss: 0.0008630752563476562
2023-01-23 01:45:11.884429: step: 200/529, loss: 0.02937774732708931
2023-01-23 01:45:13.041122: step: 204/529, loss: 0.07343216240406036
2023-01-23 01:45:14.161743: step: 208/529, loss: 0.014411927200853825
2023-01-23 01:45:15.302088: step: 212/529, loss: 0.05884857103228569
2023-01-23 01:45:16.420744: step: 216/529, loss: 0.004012203309684992
2023-01-23 01:45:17.520128: step: 220/529, loss: 0.05199480056762695
2023-01-23 01:45:18.675464: step: 224/529, loss: 0.031542565673589706
2023-01-23 01:45:19.817155: step: 228/529, loss: 0.0015168190002441406
2023-01-23 01:45:20.968114: step: 232/529, loss: 0.005208874121308327
2023-01-23 01:45:22.120070: step: 236/529, loss: 0.05750169977545738
2023-01-23 01:45:23.239146: step: 240/529, loss: 0.0014677047729492188
2023-01-23 01:45:24.410815: step: 244/529, loss: 0.0011476516956463456
2023-01-23 01:45:25.560861: step: 248/529, loss: 0.06792517006397247
2023-01-23 01:45:26.706684: step: 252/529, loss: 0.0019504786469042301
2023-01-23 01:45:27.850410: step: 256/529, loss: 0.0005694389110431075
2023-01-23 01:45:28.980480: step: 260/529, loss: 0.0578581839799881
2023-01-23 01:45:30.155715: step: 264/529, loss: 0.007916033267974854
2023-01-23 01:45:31.300164: step: 268/529, loss: 0.030933380126953125
2023-01-23 01:45:32.411038: step: 272/529, loss: 0.00893621426075697
2023-01-23 01:45:33.546874: step: 276/529, loss: 0.07375459372997284
2023-01-23 01:45:34.678088: step: 280/529, loss: 0.009297228418290615
2023-01-23 01:45:35.825390: step: 284/529, loss: 0.004671478644013405
2023-01-23 01:45:36.974577: step: 288/529, loss: 0.05834665521979332
2023-01-23 01:45:38.092909: step: 292/529, loss: 0.00677533121779561
2023-01-23 01:45:39.231543: step: 296/529, loss: 0.20710425078868866
2023-01-23 01:45:40.369480: step: 300/529, loss: 0.02287016063928604
2023-01-23 01:45:41.507937: step: 304/529, loss: 0.0005518913385458291
2023-01-23 01:45:42.647785: step: 308/529, loss: 0.06621570885181427
2023-01-23 01:45:43.785515: step: 312/529, loss: 0.01689929887652397
2023-01-23 01:45:44.923884: step: 316/529, loss: 0.09396085143089294
2023-01-23 01:45:46.075553: step: 320/529, loss: 0.012692594900727272
2023-01-23 01:45:47.206442: step: 324/529, loss: 0.0017153739463537931
2023-01-23 01:45:48.346414: step: 328/529, loss: 0.034481048583984375
2023-01-23 01:45:49.465461: step: 332/529, loss: 0.02468099445104599
2023-01-23 01:45:50.595392: step: 336/529, loss: 0.05512991175055504
2023-01-23 01:45:51.729527: step: 340/529, loss: 0.015399790368974209
2023-01-23 01:45:52.877814: step: 344/529, loss: 0.028708746656775475
2023-01-23 01:45:54.012230: step: 348/529, loss: 3.5144460201263428
2023-01-23 01:45:55.140610: step: 352/529, loss: 0.0008200168376788497
2023-01-23 01:45:56.263939: step: 356/529, loss: 0.02463064342737198
2023-01-23 01:45:57.362395: step: 360/529, loss: 0.004363822750747204
2023-01-23 01:45:58.476317: step: 364/529, loss: 0.010788536630570889
2023-01-23 01:45:59.618543: step: 368/529, loss: 0.01725492626428604
2023-01-23 01:46:00.770754: step: 372/529, loss: 0.04038182646036148
2023-01-23 01:46:01.903330: step: 376/529, loss: 0.07231082767248154
2023-01-23 01:46:03.021099: step: 380/529, loss: 0.012486457824707031
2023-01-23 01:46:04.161884: step: 384/529, loss: 0.0014396667247638106
2023-01-23 01:46:05.292443: step: 388/529, loss: 0.021851444616913795
2023-01-23 01:46:06.410536: step: 392/529, loss: 0.021245192736387253
2023-01-23 01:46:07.555680: step: 396/529, loss: 0.08244087547063828
2023-01-23 01:46:08.694151: step: 400/529, loss: 0.04936408996582031
2023-01-23 01:46:09.847192: step: 404/529, loss: 0.00750045757740736
2023-01-23 01:46:10.986077: step: 408/529, loss: 0.017092514783143997
2023-01-23 01:46:12.105315: step: 412/529, loss: 0.03356580808758736
2023-01-23 01:46:13.260680: step: 416/529, loss: 0.01418156735599041
2023-01-23 01:46:14.396032: step: 420/529, loss: 0.03341960906982422
2023-01-23 01:46:15.526370: step: 424/529, loss: 0.2953829765319824
2023-01-23 01:46:16.657427: step: 428/529, loss: 0.0011455535423010588
2023-01-23 01:46:17.816532: step: 432/529, loss: 0.01996469683945179
2023-01-23 01:46:18.988592: step: 436/529, loss: 0.0800243392586708
2023-01-23 01:46:20.124495: step: 440/529, loss: 0.06483154743909836
2023-01-23 01:46:21.251325: step: 444/529, loss: 0.03417787700891495
2023-01-23 01:46:22.394498: step: 448/529, loss: 0.09809355437755585
2023-01-23 01:46:23.529361: step: 452/529, loss: 0.025599099695682526
2023-01-23 01:46:24.668491: step: 456/529, loss: 0.0006878852727822959
2023-01-23 01:46:25.814003: step: 460/529, loss: 0.0422239787876606
2023-01-23 01:46:26.955195: step: 464/529, loss: 0.0010572910541668534
2023-01-23 01:46:28.100368: step: 468/529, loss: 0.024126624688506126
2023-01-23 01:46:29.212186: step: 472/529, loss: 0.016437530517578125
2023-01-23 01:46:30.374333: step: 476/529, loss: 0.09520583599805832
2023-01-23 01:46:31.490274: step: 480/529, loss: 0.008626163005828857
2023-01-23 01:46:32.624315: step: 484/529, loss: 0.19090357422828674
2023-01-23 01:46:33.810793: step: 488/529, loss: 0.00013589859008789062
2023-01-23 01:46:34.972335: step: 492/529, loss: 0.00926132220774889
2023-01-23 01:46:36.088258: step: 496/529, loss: 0.0018499374855309725
2023-01-23 01:46:37.221115: step: 500/529, loss: 0.13141241669654846
2023-01-23 01:46:38.363421: step: 504/529, loss: 0.008917713537812233
2023-01-23 01:46:39.521273: step: 508/529, loss: 0.04187174141407013
2023-01-23 01:46:40.653645: step: 512/529, loss: 0.004901218693703413
2023-01-23 01:46:41.781125: step: 516/529, loss: 0.04365139082074165
2023-01-23 01:46:42.938131: step: 520/529, loss: 0.09695301204919815
2023-01-23 01:46:44.068235: step: 524/529, loss: 0.13254258036613464
2023-01-23 01:46:45.209515: step: 528/529, loss: 0.028083277866244316
2023-01-23 01:46:46.353644: step: 532/529, loss: 0.5566078424453735
2023-01-23 01:46:47.488040: step: 536/529, loss: 0.007655620574951172
2023-01-23 01:46:48.621505: step: 540/529, loss: 0.01911487616598606
2023-01-23 01:46:49.761996: step: 544/529, loss: 0.04500117525458336
2023-01-23 01:46:50.892277: step: 548/529, loss: 0.08489380031824112
2023-01-23 01:46:52.036348: step: 552/529, loss: 0.01476287841796875
2023-01-23 01:46:53.207481: step: 556/529, loss: 0.024106120690703392
2023-01-23 01:46:54.329813: step: 560/529, loss: 0.030239392071962357
2023-01-23 01:46:55.464399: step: 564/529, loss: 0.0031176568008959293
2023-01-23 01:46:56.588016: step: 568/529, loss: 0.07796774059534073
2023-01-23 01:46:57.748033: step: 572/529, loss: 0.026243021711707115
2023-01-23 01:46:58.914928: step: 576/529, loss: 0.02004070207476616
2023-01-23 01:47:00.062641: step: 580/529, loss: 0.008266258984804153
2023-01-23 01:47:01.196101: step: 584/529, loss: 0.011605835519731045
2023-01-23 01:47:02.343882: step: 588/529, loss: 0.0015160085167735815
2023-01-23 01:47:03.504168: step: 592/529, loss: 0.001451778458431363
2023-01-23 01:47:04.648164: step: 596/529, loss: 0.04489459842443466
2023-01-23 01:47:05.762336: step: 600/529, loss: 0.010213185101747513
2023-01-23 01:47:06.945310: step: 604/529, loss: 0.05307454988360405
2023-01-23 01:47:08.087672: step: 608/529, loss: 0.013193107210099697
2023-01-23 01:47:09.221935: step: 612/529, loss: 0.0022746205795556307
2023-01-23 01:47:10.380150: step: 616/529, loss: 0.005787753965705633
2023-01-23 01:47:11.509514: step: 620/529, loss: 0.09382744133472443
2023-01-23 01:47:12.619429: step: 624/529, loss: 0.006672095973044634
2023-01-23 01:47:13.754808: step: 628/529, loss: 0.02024865336716175
2023-01-23 01:47:14.870903: step: 632/529, loss: 0.006074261851608753
2023-01-23 01:47:16.053365: step: 636/529, loss: 0.026778221130371094
2023-01-23 01:47:17.218520: step: 640/529, loss: 0.019365500658750534
2023-01-23 01:47:18.310570: step: 644/529, loss: 0.01812162436544895
2023-01-23 01:47:19.469623: step: 648/529, loss: 0.03174591064453125
2023-01-23 01:47:20.610518: step: 652/529, loss: 0.009531021118164062
2023-01-23 01:47:21.732165: step: 656/529, loss: 0.0018622399074956775
2023-01-23 01:47:22.833145: step: 660/529, loss: 0.01842517778277397
2023-01-23 01:47:23.970271: step: 664/529, loss: 0.008487224578857422
2023-01-23 01:47:25.079665: step: 668/529, loss: 0.00127496721688658
2023-01-23 01:47:26.228157: step: 672/529, loss: 0.08787160366773605
2023-01-23 01:47:27.370141: step: 676/529, loss: 0.0006636619800701737
2023-01-23 01:47:28.512945: step: 680/529, loss: 0.03404254838824272
2023-01-23 01:47:29.665743: step: 684/529, loss: 0.3431926965713501
2023-01-23 01:47:30.843364: step: 688/529, loss: 0.0643855556845665
2023-01-23 01:47:32.008376: step: 692/529, loss: 0.01131210383027792
2023-01-23 01:47:33.161391: step: 696/529, loss: 0.010996866039931774
2023-01-23 01:47:34.323601: step: 700/529, loss: 0.021298695355653763
2023-01-23 01:47:35.471863: step: 704/529, loss: 0.040885165333747864
2023-01-23 01:47:36.596620: step: 708/529, loss: 0.06747809052467346
2023-01-23 01:47:37.731008: step: 712/529, loss: 0.0776216983795166
2023-01-23 01:47:38.868775: step: 716/529, loss: 0.018359661102294922
2023-01-23 01:47:40.021708: step: 720/529, loss: 0.07620649039745331
2023-01-23 01:47:41.162473: step: 724/529, loss: 0.05436286702752113
2023-01-23 01:47:42.315706: step: 728/529, loss: 0.005736351013183594
2023-01-23 01:47:43.465371: step: 732/529, loss: 0.02626323699951172
2023-01-23 01:47:44.627260: step: 736/529, loss: 0.030824948102235794
2023-01-23 01:47:45.777329: step: 740/529, loss: 0.05275621637701988
2023-01-23 01:47:46.915854: step: 744/529, loss: 0.0042005060240626335
2023-01-23 01:47:48.061445: step: 748/529, loss: 0.028584908694028854
2023-01-23 01:47:49.178972: step: 752/529, loss: 0.019593620672822
2023-01-23 01:47:50.327646: step: 756/529, loss: 0.11598511040210724
2023-01-23 01:47:51.476760: step: 760/529, loss: 0.019463349133729935
2023-01-23 01:47:52.615291: step: 764/529, loss: 0.002620697021484375
2023-01-23 01:47:53.744887: step: 768/529, loss: 0.017252827063202858
2023-01-23 01:47:54.887418: step: 772/529, loss: 0.051537707448005676
2023-01-23 01:47:56.014963: step: 776/529, loss: 0.4955669641494751
2023-01-23 01:47:57.159733: step: 780/529, loss: 0.04112367704510689
2023-01-23 01:47:58.343637: step: 784/529, loss: 0.04253892973065376
2023-01-23 01:47:59.502261: step: 788/529, loss: 0.18894128501415253
2023-01-23 01:48:00.631188: step: 792/529, loss: 0.007572841830551624
2023-01-23 01:48:01.763065: step: 796/529, loss: 0.01739196851849556
2023-01-23 01:48:02.923001: step: 800/529, loss: 0.11712293326854706
2023-01-23 01:48:04.062064: step: 804/529, loss: 0.028022432699799538
2023-01-23 01:48:05.178494: step: 808/529, loss: 0.010631752200424671
2023-01-23 01:48:06.302148: step: 812/529, loss: 0.01587390899658203
2023-01-23 01:48:07.476586: step: 816/529, loss: 0.025449277833104134
2023-01-23 01:48:08.643607: step: 820/529, loss: 0.04334645718336105
2023-01-23 01:48:09.788538: step: 824/529, loss: 0.01745166815817356
2023-01-23 01:48:10.907995: step: 828/529, loss: 0.026250077411532402
2023-01-23 01:48:12.025455: step: 832/529, loss: 0.08116170763969421
2023-01-23 01:48:13.205798: step: 836/529, loss: 0.018582439050078392
2023-01-23 01:48:14.352054: step: 840/529, loss: 0.010861778631806374
2023-01-23 01:48:15.471647: step: 844/529, loss: 0.13930387794971466
2023-01-23 01:48:16.627931: step: 848/529, loss: 0.1266312599182129
2023-01-23 01:48:17.751603: step: 852/529, loss: 0.0019449234241619706
2023-01-23 01:48:18.909930: step: 856/529, loss: 0.01752759888768196
2023-01-23 01:48:20.039101: step: 860/529, loss: 0.004564667120575905
2023-01-23 01:48:21.168872: step: 864/529, loss: 0.033022690564394
2023-01-23 01:48:22.304978: step: 868/529, loss: 0.01507644634693861
2023-01-23 01:48:23.454782: step: 872/529, loss: 0.006407356355339289
2023-01-23 01:48:24.585243: step: 876/529, loss: 0.013100052252411842
2023-01-23 01:48:25.742717: step: 880/529, loss: 0.0013195992214605212
2023-01-23 01:48:26.918210: step: 884/529, loss: 0.02054414711892605
2023-01-23 01:48:28.062172: step: 888/529, loss: 0.000996494316495955
2023-01-23 01:48:29.214887: step: 892/529, loss: 0.015393257141113281
2023-01-23 01:48:30.345429: step: 896/529, loss: 0.010095691308379173
2023-01-23 01:48:31.486765: step: 900/529, loss: 0.061825837939977646
2023-01-23 01:48:32.609999: step: 904/529, loss: 0.02988128736615181
2023-01-23 01:48:33.737337: step: 908/529, loss: 0.010990714654326439
2023-01-23 01:48:34.861979: step: 912/529, loss: 0.05737915262579918
2023-01-23 01:48:35.990931: step: 916/529, loss: 0.07438087463378906
2023-01-23 01:48:37.160233: step: 920/529, loss: 0.08790607750415802
2023-01-23 01:48:38.290610: step: 924/529, loss: 0.01807727850973606
2023-01-23 01:48:39.438988: step: 928/529, loss: 0.07593412697315216
2023-01-23 01:48:40.582902: step: 932/529, loss: 0.016252517700195312
2023-01-23 01:48:41.721597: step: 936/529, loss: 0.015817834064364433
2023-01-23 01:48:42.876324: step: 940/529, loss: 0.021053221076726913
2023-01-23 01:48:44.028288: step: 944/529, loss: 0.3982565999031067
2023-01-23 01:48:45.166988: step: 948/529, loss: 0.208054780960083
2023-01-23 01:48:46.285490: step: 952/529, loss: 0.05603466182947159
2023-01-23 01:48:47.382394: step: 956/529, loss: 0.011123323813080788
2023-01-23 01:48:48.550430: step: 960/529, loss: 0.003956890199333429
2023-01-23 01:48:49.676849: step: 964/529, loss: 0.005530357826501131
2023-01-23 01:48:50.816729: step: 968/529, loss: 0.00014495849609375
2023-01-23 01:48:51.980070: step: 972/529, loss: 0.026345601305365562
2023-01-23 01:48:53.146197: step: 976/529, loss: 0.13561353087425232
2023-01-23 01:48:54.295795: step: 980/529, loss: 0.05152587965130806
2023-01-23 01:48:55.426995: step: 984/529, loss: 0.028082944452762604
2023-01-23 01:48:56.584609: step: 988/529, loss: 0.028377152979373932
2023-01-23 01:48:57.751661: step: 992/529, loss: 0.04860544204711914
2023-01-23 01:48:58.911153: step: 996/529, loss: 0.9132544994354248
2023-01-23 01:49:00.043585: step: 1000/529, loss: 0.021569300442934036
2023-01-23 01:49:01.206388: step: 1004/529, loss: 0.08717389404773712
2023-01-23 01:49:02.377722: step: 1008/529, loss: 0.11046136915683746
2023-01-23 01:49:03.514654: step: 1012/529, loss: 0.04021396487951279
2023-01-23 01:49:04.670309: step: 1016/529, loss: 0.006649589631706476
2023-01-23 01:49:05.848058: step: 1020/529, loss: 0.0011124610900878906
2023-01-23 01:49:06.986337: step: 1024/529, loss: 0.06144142150878906
2023-01-23 01:49:08.159956: step: 1028/529, loss: 0.06999292224645615
2023-01-23 01:49:09.276234: step: 1032/529, loss: 0.023520182818174362
2023-01-23 01:49:10.406538: step: 1036/529, loss: 0.058330535888671875
2023-01-23 01:49:11.533559: step: 1040/529, loss: 0.011556053534150124
2023-01-23 01:49:12.678689: step: 1044/529, loss: 0.004688453860580921
2023-01-23 01:49:13.831784: step: 1048/529, loss: 0.03973636403679848
2023-01-23 01:49:14.986494: step: 1052/529, loss: 1.2408208847045898
2023-01-23 01:49:16.130137: step: 1056/529, loss: 0.0006423950544558465
2023-01-23 01:49:17.257860: step: 1060/529, loss: 0.03664274513721466
2023-01-23 01:49:18.382557: step: 1064/529, loss: 0.022694967687129974
2023-01-23 01:49:19.514660: step: 1068/529, loss: 0.0499635711312294
2023-01-23 01:49:20.675147: step: 1072/529, loss: 0.006103706546127796
2023-01-23 01:49:21.797879: step: 1076/529, loss: 0.005550098605453968
2023-01-23 01:49:22.926511: step: 1080/529, loss: 0.04679050296545029
2023-01-23 01:49:24.098183: step: 1084/529, loss: 0.01918802224099636
2023-01-23 01:49:25.232143: step: 1088/529, loss: 0.016031265258789062
2023-01-23 01:49:26.400124: step: 1092/529, loss: 0.20714177191257477
2023-01-23 01:49:27.538760: step: 1096/529, loss: 0.04801655188202858
2023-01-23 01:49:28.671796: step: 1100/529, loss: 0.0032142880372703075
2023-01-23 01:49:29.803899: step: 1104/529, loss: 0.009187364019453526
2023-01-23 01:49:30.991109: step: 1108/529, loss: 0.09246368706226349
2023-01-23 01:49:32.132998: step: 1112/529, loss: 0.02632179483771324
2023-01-23 01:49:33.273135: step: 1116/529, loss: 0.04905581474304199
2023-01-23 01:49:34.434929: step: 1120/529, loss: 0.013914108276367188
2023-01-23 01:49:35.581050: step: 1124/529, loss: 6.427765038097277e-05
2023-01-23 01:49:36.738589: step: 1128/529, loss: 0.0027844428550451994
2023-01-23 01:49:37.879760: step: 1132/529, loss: 0.11400279402732849
2023-01-23 01:49:39.070494: step: 1136/529, loss: 0.0089332340285182
2023-01-23 01:49:40.201725: step: 1140/529, loss: 0.04021177813410759
2023-01-23 01:49:41.324444: step: 1144/529, loss: 0.05507812649011612
2023-01-23 01:49:42.459629: step: 1148/529, loss: 0.0202270969748497
2023-01-23 01:49:43.626802: step: 1152/529, loss: 0.03666200488805771
2023-01-23 01:49:44.745206: step: 1156/529, loss: 0.001990842865779996
2023-01-23 01:49:45.876335: step: 1160/529, loss: 0.04222536459565163
2023-01-23 01:49:47.028259: step: 1164/529, loss: 0.06465263664722443
2023-01-23 01:49:48.194283: step: 1168/529, loss: 0.02528991736471653
2023-01-23 01:49:49.340500: step: 1172/529, loss: 0.10889530181884766
2023-01-23 01:49:50.509477: step: 1176/529, loss: 0.12215165793895721
2023-01-23 01:49:51.647547: step: 1180/529, loss: 0.007244729902595282
2023-01-23 01:49:52.778275: step: 1184/529, loss: 0.11880825459957123
2023-01-23 01:49:53.902904: step: 1188/529, loss: 0.09156408905982971
2023-01-23 01:49:55.044744: step: 1192/529, loss: 0.04717455059289932
2023-01-23 01:49:56.177685: step: 1196/529, loss: 0.04629569128155708
2023-01-23 01:49:57.320589: step: 1200/529, loss: 0.047486212104558945
2023-01-23 01:49:58.497713: step: 1204/529, loss: 0.23759636282920837
2023-01-23 01:49:59.646085: step: 1208/529, loss: 0.03310270234942436
2023-01-23 01:50:00.801413: step: 1212/529, loss: 0.4257963299751282
2023-01-23 01:50:01.913020: step: 1216/529, loss: 0.08411683887243271
2023-01-23 01:50:03.054799: step: 1220/529, loss: 0.06458492577075958
2023-01-23 01:50:04.181182: step: 1224/529, loss: 0.01833038404583931
2023-01-23 01:50:05.316409: step: 1228/529, loss: 0.0045150755904614925
2023-01-23 01:50:06.453386: step: 1232/529, loss: 0.1313977837562561
2023-01-23 01:50:07.612595: step: 1236/529, loss: 0.06871018558740616
2023-01-23 01:50:08.823706: step: 1240/529, loss: 0.014271451160311699
2023-01-23 01:50:09.947646: step: 1244/529, loss: 0.04798565059900284
2023-01-23 01:50:11.089207: step: 1248/529, loss: 0.005623340606689453
2023-01-23 01:50:12.248972: step: 1252/529, loss: 0.04986229166388512
2023-01-23 01:50:13.387713: step: 1256/529, loss: 0.005147885996848345
2023-01-23 01:50:14.500767: step: 1260/529, loss: 0.005708837881684303
2023-01-23 01:50:15.657132: step: 1264/529, loss: 0.013275910168886185
2023-01-23 01:50:16.785381: step: 1268/529, loss: 0.013947105966508389
2023-01-23 01:50:17.920737: step: 1272/529, loss: 0.008233213797211647
2023-01-23 01:50:19.052812: step: 1276/529, loss: 0.010438251309096813
2023-01-23 01:50:20.175747: step: 1280/529, loss: 0.006468772888183594
2023-01-23 01:50:21.327219: step: 1284/529, loss: 0.04680328071117401
2023-01-23 01:50:22.440801: step: 1288/529, loss: 0.0008646011119708419
2023-01-23 01:50:23.566803: step: 1292/529, loss: 0.0692012831568718
2023-01-23 01:50:24.694496: step: 1296/529, loss: 0.02568512037396431
2023-01-23 01:50:25.838927: step: 1300/529, loss: 0.025310229510068893
2023-01-23 01:50:26.984328: step: 1304/529, loss: 0.05374126881361008
2023-01-23 01:50:28.119623: step: 1308/529, loss: 0.007646418176591396
2023-01-23 01:50:29.285403: step: 1312/529, loss: 0.5259893536567688
2023-01-23 01:50:30.419311: step: 1316/529, loss: 0.007978057488799095
2023-01-23 01:50:31.577034: step: 1320/529, loss: 0.09202414005994797
2023-01-23 01:50:32.741807: step: 1324/529, loss: 0.0008187771309167147
2023-01-23 01:50:33.877411: step: 1328/529, loss: 0.010210538282990456
2023-01-23 01:50:35.027094: step: 1332/529, loss: 0.009675407782196999
2023-01-23 01:50:36.152008: step: 1336/529, loss: 0.4917963147163391
2023-01-23 01:50:37.280533: step: 1340/529, loss: 0.02311873435974121
2023-01-23 01:50:38.416601: step: 1344/529, loss: 0.020246410742402077
2023-01-23 01:50:39.558726: step: 1348/529, loss: 0.008223408833146095
2023-01-23 01:50:40.705572: step: 1352/529, loss: 0.024042226374149323
2023-01-23 01:50:41.852999: step: 1356/529, loss: 0.003786277724429965
2023-01-23 01:50:42.972042: step: 1360/529, loss: 0.01281118392944336
2023-01-23 01:50:44.126374: step: 1364/529, loss: 0.10583677142858505
2023-01-23 01:50:45.285186: step: 1368/529, loss: 0.005557632073760033
2023-01-23 01:50:46.433475: step: 1372/529, loss: 0.24628451466560364
2023-01-23 01:50:47.576010: step: 1376/529, loss: 0.029894256964325905
2023-01-23 01:50:48.741994: step: 1380/529, loss: 0.002945518586784601
2023-01-23 01:50:49.883595: step: 1384/529, loss: 0.03356170654296875
2023-01-23 01:50:51.035774: step: 1388/529, loss: 0.1352996826171875
2023-01-23 01:50:52.219059: step: 1392/529, loss: 0.10184673964977264
2023-01-23 01:50:53.349781: step: 1396/529, loss: 0.5471808910369873
2023-01-23 01:50:54.524109: step: 1400/529, loss: 0.0005770206335000694
2023-01-23 01:50:55.700642: step: 1404/529, loss: 0.00571861257776618
2023-01-23 01:50:56.848579: step: 1408/529, loss: 0.02298908121883869
2023-01-23 01:50:57.995267: step: 1412/529, loss: 0.02575836144387722
2023-01-23 01:50:59.140466: step: 1416/529, loss: 0.002178239868953824
2023-01-23 01:51:00.292576: step: 1420/529, loss: 0.1595216691493988
2023-01-23 01:51:01.402127: step: 1424/529, loss: 0.008147621527314186
2023-01-23 01:51:02.525826: step: 1428/529, loss: 0.025105096399784088
2023-01-23 01:51:03.667818: step: 1432/529, loss: 0.8444983959197998
2023-01-23 01:51:04.808680: step: 1436/529, loss: 0.01779031753540039
2023-01-23 01:51:06.001142: step: 1440/529, loss: 0.031321004033088684
2023-01-23 01:51:07.170636: step: 1444/529, loss: 0.08353462815284729
2023-01-23 01:51:08.297129: step: 1448/529, loss: 0.00377235421910882
2023-01-23 01:51:09.405907: step: 1452/529, loss: 0.012806129641830921
2023-01-23 01:51:10.542761: step: 1456/529, loss: 0.011811209842562675
2023-01-23 01:51:11.677616: step: 1460/529, loss: 0.07190532982349396
2023-01-23 01:51:12.812055: step: 1464/529, loss: 0.02921276167035103
2023-01-23 01:51:13.941258: step: 1468/529, loss: 0.02391042746603489
2023-01-23 01:51:15.078084: step: 1472/529, loss: 0.0103295324370265
2023-01-23 01:51:16.238786: step: 1476/529, loss: 0.10181155055761337
2023-01-23 01:51:17.386204: step: 1480/529, loss: 0.019657611846923828
2023-01-23 01:51:18.518490: step: 1484/529, loss: 0.0474882610142231
2023-01-23 01:51:19.641145: step: 1488/529, loss: 0.0377744697034359
2023-01-23 01:51:20.779334: step: 1492/529, loss: 0.01982865482568741
2023-01-23 01:51:21.932447: step: 1496/529, loss: 0.05767975002527237
2023-01-23 01:51:23.067646: step: 1500/529, loss: 0.6384870409965515
2023-01-23 01:51:24.199515: step: 1504/529, loss: 0.008641624823212624
2023-01-23 01:51:25.315839: step: 1508/529, loss: 0.05865902826189995
2023-01-23 01:51:26.488165: step: 1512/529, loss: 0.01728830300271511
2023-01-23 01:51:27.645665: step: 1516/529, loss: 0.030413534492254257
2023-01-23 01:51:28.763694: step: 1520/529, loss: 0.005578422918915749
2023-01-23 01:51:29.919432: step: 1524/529, loss: 0.0035753785632550716
2023-01-23 01:51:31.105190: step: 1528/529, loss: 0.27121925354003906
2023-01-23 01:51:32.242825: step: 1532/529, loss: 0.07558765262365341
2023-01-23 01:51:33.360411: step: 1536/529, loss: 0.018369674682617188
2023-01-23 01:51:34.503348: step: 1540/529, loss: 0.01779937744140625
2023-01-23 01:51:35.624717: step: 1544/529, loss: 0.11485147476196289
2023-01-23 01:51:36.783875: step: 1548/529, loss: 0.009597969241440296
2023-01-23 01:51:37.920441: step: 1552/529, loss: 0.04382495954632759
2023-01-23 01:51:39.068445: step: 1556/529, loss: 0.01810441166162491
2023-01-23 01:51:40.251320: step: 1560/529, loss: 1.122008204460144
2023-01-23 01:51:41.383617: step: 1564/529, loss: 0.0633401870727539
2023-01-23 01:51:42.537071: step: 1568/529, loss: 0.022121049463748932
2023-01-23 01:51:43.668357: step: 1572/529, loss: 0.02047419361770153
2023-01-23 01:51:44.813243: step: 1576/529, loss: 0.013487149029970169
2023-01-23 01:51:45.961556: step: 1580/529, loss: 0.04717302322387695
2023-01-23 01:51:47.125678: step: 1584/529, loss: 0.05500049889087677
2023-01-23 01:51:48.277020: step: 1588/529, loss: 0.013088608160614967
2023-01-23 01:51:49.402555: step: 1592/529, loss: 0.05883502960205078
2023-01-23 01:51:50.562463: step: 1596/529, loss: 0.11016788333654404
2023-01-23 01:51:51.684117: step: 1600/529, loss: 0.10014276206493378
2023-01-23 01:51:52.842664: step: 1604/529, loss: 0.001014757202938199
2023-01-23 01:51:53.984487: step: 1608/529, loss: 0.018223382532596588
2023-01-23 01:51:55.124861: step: 1612/529, loss: 0.010668945498764515
2023-01-23 01:51:56.265992: step: 1616/529, loss: 0.08153381198644638
2023-01-23 01:51:57.409391: step: 1620/529, loss: 0.008607864379882812
2023-01-23 01:51:58.547395: step: 1624/529, loss: 0.05545301362872124
2023-01-23 01:51:59.692259: step: 1628/529, loss: 0.05251751095056534
2023-01-23 01:52:00.804916: step: 1632/529, loss: 0.0032676695846021175
2023-01-23 01:52:01.939070: step: 1636/529, loss: 0.012538433074951172
2023-01-23 01:52:03.082856: step: 1640/529, loss: 0.0659894049167633
2023-01-23 01:52:04.240837: step: 1644/529, loss: 0.026009656488895416
2023-01-23 01:52:05.367782: step: 1648/529, loss: 0.022279931232333183
2023-01-23 01:52:06.519454: step: 1652/529, loss: 0.062365058809518814
2023-01-23 01:52:07.654612: step: 1656/529, loss: 0.049483396112918854
2023-01-23 01:52:08.800923: step: 1660/529, loss: 0.026654861867427826
2023-01-23 01:52:09.960397: step: 1664/529, loss: 0.01733558252453804
2023-01-23 01:52:11.124416: step: 1668/529, loss: 0.06093359366059303
2023-01-23 01:52:12.256696: step: 1672/529, loss: 0.02612752839922905
2023-01-23 01:52:13.405933: step: 1676/529, loss: 0.12475338578224182
2023-01-23 01:52:14.549922: step: 1680/529, loss: 0.047333717346191406
2023-01-23 01:52:15.691647: step: 1684/529, loss: 0.003857517149299383
2023-01-23 01:52:16.846611: step: 1688/529, loss: 0.00394363421946764
2023-01-23 01:52:17.996791: step: 1692/529, loss: 0.03974476084113121
2023-01-23 01:52:19.114947: step: 1696/529, loss: 0.03626508638262749
2023-01-23 01:52:20.264116: step: 1700/529, loss: 0.007637977600097656
2023-01-23 01:52:21.401759: step: 1704/529, loss: 0.01441192626953125
2023-01-23 01:52:22.545867: step: 1708/529, loss: 0.2278156280517578
2023-01-23 01:52:23.652131: step: 1712/529, loss: 0.005734110251069069
2023-01-23 01:52:24.814111: step: 1716/529, loss: 0.08266372978687286
2023-01-23 01:52:25.963076: step: 1720/529, loss: 0.032337188720703125
2023-01-23 01:52:27.089416: step: 1724/529, loss: 0.08831825852394104
2023-01-23 01:52:28.216287: step: 1728/529, loss: 0.0772031769156456
2023-01-23 01:52:29.344393: step: 1732/529, loss: 0.021537208929657936
2023-01-23 01:52:30.485981: step: 1736/529, loss: 0.08185596764087677
2023-01-23 01:52:31.613954: step: 1740/529, loss: 0.0002483367861714214
2023-01-23 01:52:32.748219: step: 1744/529, loss: 0.04616403579711914
2023-01-23 01:52:33.879786: step: 1748/529, loss: 0.0072168828919529915
2023-01-23 01:52:35.028921: step: 1752/529, loss: 0.10313248634338379
2023-01-23 01:52:36.168987: step: 1756/529, loss: 0.041164495050907135
2023-01-23 01:52:37.291885: step: 1760/529, loss: 0.05121174082159996
2023-01-23 01:52:38.436251: step: 1764/529, loss: 0.010016155429184437
2023-01-23 01:52:39.572815: step: 1768/529, loss: 0.003292560577392578
2023-01-23 01:52:40.709770: step: 1772/529, loss: 0.04646673426032066
2023-01-23 01:52:41.846365: step: 1776/529, loss: 0.005523967556655407
2023-01-23 01:52:42.985553: step: 1780/529, loss: 0.15123902261257172
2023-01-23 01:52:44.122162: step: 1784/529, loss: 0.04751448705792427
2023-01-23 01:52:45.306082: step: 1788/529, loss: 0.0642232894897461
2023-01-23 01:52:46.482821: step: 1792/529, loss: 0.028957748785614967
2023-01-23 01:52:47.620947: step: 1796/529, loss: 0.034417059272527695
2023-01-23 01:52:48.763457: step: 1800/529, loss: 0.06205263361334801
2023-01-23 01:52:49.902132: step: 1804/529, loss: 0.006472969427704811
2023-01-23 01:52:51.009517: step: 1808/529, loss: 0.09211353957653046
2023-01-23 01:52:52.138562: step: 1812/529, loss: 0.007915687747299671
2023-01-23 01:52:53.279222: step: 1816/529, loss: 0.06450091302394867
2023-01-23 01:52:54.442498: step: 1820/529, loss: 0.02703409269452095
2023-01-23 01:52:55.583437: step: 1824/529, loss: 0.00462155370041728
2023-01-23 01:52:56.758142: step: 1828/529, loss: 0.5667726397514343
2023-01-23 01:52:57.909407: step: 1832/529, loss: 0.0026515007484704256
2023-01-23 01:52:59.021379: step: 1836/529, loss: 0.0011473179329186678
2023-01-23 01:53:00.138837: step: 1840/529, loss: 0.09822896122932434
2023-01-23 01:53:01.302639: step: 1844/529, loss: 0.0019580840598791838
2023-01-23 01:53:02.459297: step: 1848/529, loss: 0.12257274985313416
2023-01-23 01:53:03.587101: step: 1852/529, loss: 0.014573573134839535
2023-01-23 01:53:04.717602: step: 1856/529, loss: 0.022257328033447266
2023-01-23 01:53:05.847700: step: 1860/529, loss: 0.011684035882353783
2023-01-23 01:53:06.995179: step: 1864/529, loss: 0.03660747408866882
2023-01-23 01:53:08.129506: step: 1868/529, loss: 0.04032135009765625
2023-01-23 01:53:09.263067: step: 1872/529, loss: 0.15340514481067657
2023-01-23 01:53:10.419028: step: 1876/529, loss: 0.017031574621796608
2023-01-23 01:53:11.562269: step: 1880/529, loss: 0.02414569817483425
2023-01-23 01:53:12.701546: step: 1884/529, loss: 0.21909034252166748
2023-01-23 01:53:13.834666: step: 1888/529, loss: 0.052767373621463776
2023-01-23 01:53:14.969121: step: 1892/529, loss: 0.026542089879512787
2023-01-23 01:53:16.141939: step: 1896/529, loss: 0.10610581189393997
2023-01-23 01:53:17.265697: step: 1900/529, loss: 0.01424565352499485
2023-01-23 01:53:18.416629: step: 1904/529, loss: 0.44736775755882263
2023-01-23 01:53:19.584367: step: 1908/529, loss: 0.01866903342306614
2023-01-23 01:53:20.714713: step: 1912/529, loss: 0.06140518561005592
2023-01-23 01:53:21.836124: step: 1916/529, loss: 0.03488168865442276
2023-01-23 01:53:22.996024: step: 1920/529, loss: 0.044077496975660324
2023-01-23 01:53:24.137165: step: 1924/529, loss: 0.045752812176942825
2023-01-23 01:53:25.250968: step: 1928/529, loss: 0.02935056760907173
2023-01-23 01:53:26.400412: step: 1932/529, loss: 0.009860992431640625
2023-01-23 01:53:27.574118: step: 1936/529, loss: 0.1397884339094162
2023-01-23 01:53:28.713894: step: 1940/529, loss: 0.031992532312870026
2023-01-23 01:53:29.897302: step: 1944/529, loss: 0.08644180744886398
2023-01-23 01:53:31.057311: step: 1948/529, loss: 0.04606590420007706
2023-01-23 01:53:32.207897: step: 1952/529, loss: 0.005463266745209694
2023-01-23 01:53:33.309660: step: 1956/529, loss: 0.0010972976451739669
2023-01-23 01:53:34.456338: step: 1960/529, loss: 0.005159950349479914
2023-01-23 01:53:35.604711: step: 1964/529, loss: 0.03960418701171875
2023-01-23 01:53:36.748848: step: 1968/529, loss: 0.017051314935088158
2023-01-23 01:53:37.907607: step: 1972/529, loss: 0.07580963522195816
2023-01-23 01:53:39.033281: step: 1976/529, loss: 0.028292130678892136
2023-01-23 01:53:40.188354: step: 1980/529, loss: 0.004938411992043257
2023-01-23 01:53:41.350731: step: 1984/529, loss: 0.02169984206557274
2023-01-23 01:53:42.509806: step: 1988/529, loss: 0.004240894224494696
2023-01-23 01:53:43.639508: step: 1992/529, loss: 0.06446247547864914
2023-01-23 01:53:44.776060: step: 1996/529, loss: 0.005039024632424116
2023-01-23 01:53:45.928518: step: 2000/529, loss: 0.03675718232989311
2023-01-23 01:53:47.076596: step: 2004/529, loss: 0.1637801229953766
2023-01-23 01:53:48.243708: step: 2008/529, loss: 0.016495706513524055
2023-01-23 01:53:49.376427: step: 2012/529, loss: 0.04091978073120117
2023-01-23 01:53:50.512347: step: 2016/529, loss: 0.08089341968297958
2023-01-23 01:53:51.673864: step: 2020/529, loss: 0.026083802804350853
2023-01-23 01:53:52.792627: step: 2024/529, loss: 0.0022251398768275976
2023-01-23 01:53:53.936623: step: 2028/529, loss: 0.08772774040699005
2023-01-23 01:53:55.062089: step: 2032/529, loss: 0.026732444763183594
2023-01-23 01:53:56.188117: step: 2036/529, loss: 0.016544677317142487
2023-01-23 01:53:57.333560: step: 2040/529, loss: 0.0016375065315514803
2023-01-23 01:53:58.507599: step: 2044/529, loss: 0.011168288998305798
2023-01-23 01:53:59.637700: step: 2048/529, loss: 0.0015014648670330644
2023-01-23 01:54:00.791617: step: 2052/529, loss: 0.23055382072925568
2023-01-23 01:54:01.922783: step: 2056/529, loss: 0.017482947558164597
2023-01-23 01:54:03.059697: step: 2060/529, loss: 0.00787048414349556
2023-01-23 01:54:04.197672: step: 2064/529, loss: 0.08394412696361542
2023-01-23 01:54:05.346857: step: 2068/529, loss: 1.5620718002319336
2023-01-23 01:54:06.458737: step: 2072/529, loss: 0.01348123513162136
2023-01-23 01:54:07.592393: step: 2076/529, loss: 0.020075369626283646
2023-01-23 01:54:08.700836: step: 2080/529, loss: 0.06412658840417862
2023-01-23 01:54:09.899664: step: 2084/529, loss: 0.0004307747003622353
2023-01-23 01:54:11.059493: step: 2088/529, loss: 0.015450209379196167
2023-01-23 01:54:12.166183: step: 2092/529, loss: 0.016770077869296074
2023-01-23 01:54:13.283750: step: 2096/529, loss: 0.1123904213309288
2023-01-23 01:54:14.415715: step: 2100/529, loss: 0.09366931766271591
2023-01-23 01:54:15.563598: step: 2104/529, loss: 0.04261951521039009
2023-01-23 01:54:16.694210: step: 2108/529, loss: 0.028529644012451172
2023-01-23 01:54:17.840602: step: 2112/529, loss: 0.5548986196517944
2023-01-23 01:54:18.994369: step: 2116/529, loss: 0.0037319185212254524
==================================================
Loss: 0.068
--------------------
Dev: {'event': {'p': 0.5853174603174603, 'r': 0.7856191744340879, 'f1': 0.670835702103468}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6082845565060784, 'r': 0.7827346465816918, 'f1': 0.6845705599189258}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5268817204301075, 'r': 0.9074074074074074, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.5555555555555556, 'r': 0.5555555555555556, 'f1': 0.5555555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
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': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:55:00.602812: step: 4/529, loss: 0.013891411013901234
2023-01-23 01:55:01.744904: step: 8/529, loss: 0.041683390736579895
2023-01-23 01:55:02.882329: step: 12/529, loss: 0.011958027258515358
2023-01-23 01:55:04.007794: step: 16/529, loss: 0.00681457482278347
2023-01-23 01:55:05.161627: step: 20/529, loss: 0.13926096260547638
2023-01-23 01:55:06.302561: step: 24/529, loss: 0.02781384252011776
2023-01-23 01:55:07.431231: step: 28/529, loss: 0.04537608101963997
2023-01-23 01:55:08.549327: step: 32/529, loss: 0.013766097836196423
2023-01-23 01:55:09.667871: step: 36/529, loss: 0.020801449194550514
2023-01-23 01:55:10.822564: step: 40/529, loss: 0.0009093284606933594
2023-01-23 01:55:11.969400: step: 44/529, loss: 0.014041900634765625
2023-01-23 01:55:13.129239: step: 48/529, loss: 0.006550979800522327
2023-01-23 01:55:14.262103: step: 52/529, loss: 0.02831106260418892
2023-01-23 01:55:15.384662: step: 56/529, loss: 0.6888611912727356
2023-01-23 01:55:16.522826: step: 60/529, loss: 0.009065628051757812
2023-01-23 01:55:17.689121: step: 64/529, loss: 0.0005560875288210809
2023-01-23 01:55:18.807553: step: 68/529, loss: 0.054268453270196915
2023-01-23 01:55:19.948990: step: 72/529, loss: 0.03435225412249565
2023-01-23 01:55:21.073957: step: 76/529, loss: 0.009554672054946423
2023-01-23 01:55:22.253010: step: 80/529, loss: 0.022829245775938034
2023-01-23 01:55:23.391775: step: 84/529, loss: 0.04375457763671875
2023-01-23 01:55:24.543082: step: 88/529, loss: 0.05114898830652237
2023-01-23 01:55:25.678074: step: 92/529, loss: 6.201476097106934
2023-01-23 01:55:26.829020: step: 96/529, loss: 0.008097457699477673
2023-01-23 01:55:27.955915: step: 100/529, loss: 0.03678007051348686
2023-01-23 01:55:29.076512: step: 104/529, loss: 0.023497773334383965
2023-01-23 01:55:30.233319: step: 108/529, loss: 0.01891956478357315
2023-01-23 01:55:31.378771: step: 112/529, loss: 0.05131816864013672
2023-01-23 01:55:32.525643: step: 116/529, loss: 0.05701904371380806
2023-01-23 01:55:33.671209: step: 120/529, loss: 0.0013956070179119706
2023-01-23 01:55:34.795246: step: 124/529, loss: 0.0012221336364746094
2023-01-23 01:55:35.920082: step: 128/529, loss: 0.0005672932020388544
2023-01-23 01:55:37.042756: step: 132/529, loss: 0.012733984738588333
2023-01-23 01:55:38.203134: step: 136/529, loss: 0.020636605098843575
2023-01-23 01:55:39.327585: step: 140/529, loss: 0.024883698672056198
2023-01-23 01:55:40.487668: step: 144/529, loss: 0.009672450833022594
2023-01-23 01:55:41.590897: step: 148/529, loss: 0.014662360772490501
2023-01-23 01:55:42.752360: step: 152/529, loss: 0.03758711740374565
2023-01-23 01:55:43.933216: step: 156/529, loss: 0.1078585609793663
2023-01-23 01:55:45.146886: step: 160/529, loss: 0.036435458809137344
2023-01-23 01:55:46.336720: step: 164/529, loss: 0.058748628944158554
2023-01-23 01:55:47.464280: step: 168/529, loss: 0.011932754889130592
2023-01-23 01:55:48.580285: step: 172/529, loss: 0.005487346556037664
2023-01-23 01:55:49.717916: step: 176/529, loss: 0.060613345354795456
2023-01-23 01:55:50.852476: step: 180/529, loss: 0.024787425994873047
2023-01-23 01:55:52.000462: step: 184/529, loss: 0.12951135635375977
2023-01-23 01:55:53.169132: step: 188/529, loss: 0.0011964798904955387
2023-01-23 01:55:54.309612: step: 192/529, loss: 0.03510608524084091
2023-01-23 01:55:55.465995: step: 196/529, loss: 0.06786441802978516
2023-01-23 01:55:56.590546: step: 200/529, loss: 0.023728180676698685
2023-01-23 01:55:57.706528: step: 204/529, loss: 0.005610323511064053
2023-01-23 01:55:58.821603: step: 208/529, loss: 0.33244168758392334
2023-01-23 01:55:59.962595: step: 212/529, loss: 0.03986950218677521
2023-01-23 01:56:01.062529: step: 216/529, loss: 0.0499635711312294
2023-01-23 01:56:02.216991: step: 220/529, loss: 0.018599702045321465
2023-01-23 01:56:03.363412: step: 224/529, loss: 0.004405784886330366
2023-01-23 01:56:04.484834: step: 228/529, loss: 0.0024839877150952816
2023-01-23 01:56:05.615280: step: 232/529, loss: 0.0013145447010174394
2023-01-23 01:56:06.750400: step: 236/529, loss: 0.005399561021476984
2023-01-23 01:56:07.888526: step: 240/529, loss: 0.005805349443107843
2023-01-23 01:56:09.039605: step: 244/529, loss: 0.0017516136867925525
2023-01-23 01:56:10.190856: step: 248/529, loss: 0.01354761142283678
2023-01-23 01:56:11.331681: step: 252/529, loss: 0.014997268095612526
2023-01-23 01:56:12.442921: step: 256/529, loss: 0.0028181076049804688
2023-01-23 01:56:13.604905: step: 260/529, loss: 0.05532827600836754
2023-01-23 01:56:14.738637: step: 264/529, loss: 0.04148883745074272
2023-01-23 01:56:15.917510: step: 268/529, loss: 0.0029524145647883415
2023-01-23 01:56:17.040296: step: 272/529, loss: 0.01788921281695366
2023-01-23 01:56:18.167505: step: 276/529, loss: 0.017932604998350143
2023-01-23 01:56:19.318137: step: 280/529, loss: 0.013398361392319202
2023-01-23 01:56:20.481712: step: 284/529, loss: 0.003225231310352683
2023-01-23 01:56:21.638506: step: 288/529, loss: 0.012411355972290039
2023-01-23 01:56:22.781627: step: 292/529, loss: 0.04199790954589844
2023-01-23 01:56:23.922255: step: 296/529, loss: 0.008658528327941895
2023-01-23 01:56:25.088394: step: 300/529, loss: 0.010313463397324085
2023-01-23 01:56:26.197060: step: 304/529, loss: 0.002655506134033203
2023-01-23 01:56:27.357235: step: 308/529, loss: 0.027561664581298828
2023-01-23 01:56:28.517077: step: 312/529, loss: 0.0014448165893554688
2023-01-23 01:56:29.638786: step: 316/529, loss: 0.006081891246140003
2023-01-23 01:56:30.769199: step: 320/529, loss: 0.04324827343225479
2023-01-23 01:56:31.906327: step: 324/529, loss: 0.013394307345151901
2023-01-23 01:56:33.029796: step: 328/529, loss: 0.014495849609375
2023-01-23 01:56:34.158814: step: 332/529, loss: 0.012241745367646217
2023-01-23 01:56:35.331833: step: 336/529, loss: 0.005948448553681374
2023-01-23 01:56:36.477474: step: 340/529, loss: 0.015468978323042393
2023-01-23 01:56:37.630911: step: 344/529, loss: 0.011286593042314053
2023-01-23 01:56:38.818576: step: 348/529, loss: 0.020523834973573685
2023-01-23 01:56:39.942519: step: 352/529, loss: 0.04298458248376846
2023-01-23 01:56:41.110042: step: 356/529, loss: 0.04024963825941086
2023-01-23 01:56:42.242436: step: 360/529, loss: 5.0354006816633046e-05
2023-01-23 01:56:43.400881: step: 364/529, loss: 0.01866731606423855
2023-01-23 01:56:44.522177: step: 368/529, loss: 0.007298565004020929
2023-01-23 01:56:45.682137: step: 372/529, loss: 0.0024089813232421875
2023-01-23 01:56:46.834169: step: 376/529, loss: 0.04795151203870773
2023-01-23 01:56:47.965259: step: 380/529, loss: 0.0008177757263183594
2023-01-23 01:56:49.092795: step: 384/529, loss: 0.007581877522170544
2023-01-23 01:56:50.211374: step: 388/529, loss: 0.029965687543153763
2023-01-23 01:56:51.340290: step: 392/529, loss: 0.033069707453250885
2023-01-23 01:56:52.538001: step: 396/529, loss: 0.060196854174137115
2023-01-23 01:56:53.666823: step: 400/529, loss: 0.0030612945556640625
2023-01-23 01:56:54.813631: step: 404/529, loss: 0.007460355758666992
2023-01-23 01:56:55.964757: step: 408/529, loss: 0.001958560897037387
2023-01-23 01:56:57.086853: step: 412/529, loss: 0.025990676134824753
2023-01-23 01:56:58.208078: step: 416/529, loss: 0.004959297366440296
2023-01-23 01:56:59.353730: step: 420/529, loss: 0.0011463165283203125
2023-01-23 01:57:00.477454: step: 424/529, loss: 0.03199481964111328
2023-01-23 01:57:01.599437: step: 428/529, loss: 0.018511200323700905
2023-01-23 01:57:02.750107: step: 432/529, loss: 0.11543647199869156
2023-01-23 01:57:03.880152: step: 436/529, loss: 0.08503293991088867
2023-01-23 01:57:05.020500: step: 440/529, loss: 0.00580596923828125
2023-01-23 01:57:06.156251: step: 444/529, loss: 0.14231853187084198
2023-01-23 01:57:07.281126: step: 448/529, loss: 0.05593481287360191
2023-01-23 01:57:08.435390: step: 452/529, loss: 0.03409595414996147
2023-01-23 01:57:09.584790: step: 456/529, loss: 0.005191040225327015
2023-01-23 01:57:10.707406: step: 460/529, loss: 0.003504848573356867
2023-01-23 01:57:11.835415: step: 464/529, loss: 0.0076157571747899055
2023-01-23 01:57:12.990099: step: 468/529, loss: 0.002480888506397605
2023-01-23 01:57:14.113784: step: 472/529, loss: 0.025597095489501953
2023-01-23 01:57:15.285241: step: 476/529, loss: 0.07940158993005753
2023-01-23 01:57:16.411356: step: 480/529, loss: 0.02297048643231392
2023-01-23 01:57:17.564113: step: 484/529, loss: 0.004005551338195801
2023-01-23 01:57:18.696579: step: 488/529, loss: 0.3205123841762543
2023-01-23 01:57:19.846773: step: 492/529, loss: 0.0022920609917491674
2023-01-23 01:57:21.002799: step: 496/529, loss: 0.07876396179199219
2023-01-23 01:57:22.126912: step: 500/529, loss: 0.000438690185546875
2023-01-23 01:57:23.285011: step: 504/529, loss: 0.0026340484619140625
2023-01-23 01:57:24.449255: step: 508/529, loss: 0.06593503803014755
2023-01-23 01:57:25.592492: step: 512/529, loss: 0.03384266048669815
2023-01-23 01:57:26.723682: step: 516/529, loss: 0.05515794828534126
2023-01-23 01:57:27.880717: step: 520/529, loss: 0.030569840222597122
2023-01-23 01:57:29.021693: step: 524/529, loss: 0.010356427170336246
2023-01-23 01:57:30.158098: step: 528/529, loss: 0.0026908398140221834
2023-01-23 01:57:31.314553: step: 532/529, loss: 0.0008689880487509072
2023-01-23 01:57:32.471797: step: 536/529, loss: 0.044808197766542435
2023-01-23 01:57:33.605388: step: 540/529, loss: 0.046677686274051666
2023-01-23 01:57:34.751439: step: 544/529, loss: 0.06704635918140411
2023-01-23 01:57:35.882868: step: 548/529, loss: 0.0769743025302887
2023-01-23 01:57:37.049916: step: 552/529, loss: 0.034835245460271835
2023-01-23 01:57:38.200054: step: 556/529, loss: 0.17201557755470276
2023-01-23 01:57:39.335901: step: 560/529, loss: 0.004364967346191406
2023-01-23 01:57:40.516843: step: 564/529, loss: 0.0031766891479492188
2023-01-23 01:57:41.632957: step: 568/529, loss: 0.08495932072401047
2023-01-23 01:57:42.809245: step: 572/529, loss: 0.05210399627685547
2023-01-23 01:57:43.936742: step: 576/529, loss: 0.12970809638500214
2023-01-23 01:57:45.088764: step: 580/529, loss: 0.022859763354063034
2023-01-23 01:57:46.241620: step: 584/529, loss: 0.0030261040665209293
2023-01-23 01:57:47.371803: step: 588/529, loss: 0.0009380817646160722
2023-01-23 01:57:48.513127: step: 592/529, loss: 0.22260628640651703
2023-01-23 01:57:49.676340: step: 596/529, loss: 0.02772378921508789
2023-01-23 01:57:50.809463: step: 600/529, loss: 0.0002532959042582661
2023-01-23 01:57:51.941278: step: 604/529, loss: 0.04819688946008682
2023-01-23 01:57:53.071978: step: 608/529, loss: 0.0017631531227380037
2023-01-23 01:57:54.218416: step: 612/529, loss: 0.0020809173583984375
2023-01-23 01:57:55.366394: step: 616/529, loss: 0.0010547637939453125
2023-01-23 01:57:56.508841: step: 620/529, loss: 0.020159149542450905
2023-01-23 01:57:57.671666: step: 624/529, loss: 0.02003917656838894
2023-01-23 01:57:58.780308: step: 628/529, loss: 0.0022153854370117188
2023-01-23 01:57:59.939121: step: 632/529, loss: 0.015769682824611664
2023-01-23 01:58:01.080489: step: 636/529, loss: 0.03011493571102619
2023-01-23 01:58:02.226927: step: 640/529, loss: 0.009197044186294079
2023-01-23 01:58:03.401444: step: 644/529, loss: 0.022007372230291367
2023-01-23 01:58:04.520558: step: 648/529, loss: 0.15374240279197693
2023-01-23 01:58:05.671192: step: 652/529, loss: 0.025133132934570312
2023-01-23 01:58:06.799695: step: 656/529, loss: 0.06175212934613228
2023-01-23 01:58:07.958919: step: 660/529, loss: 0.040116310119628906
2023-01-23 01:58:09.144453: step: 664/529, loss: 0.11048908531665802
2023-01-23 01:58:10.291788: step: 668/529, loss: 0.07229853421449661
2023-01-23 01:58:11.446382: step: 672/529, loss: 0.019942903891205788
2023-01-23 01:58:12.539752: step: 676/529, loss: 0.005787563510239124
2023-01-23 01:58:13.690903: step: 680/529, loss: 0.07249470055103302
2023-01-23 01:58:14.835100: step: 684/529, loss: 0.03927869722247124
2023-01-23 01:58:15.977197: step: 688/529, loss: 0.0736946165561676
2023-01-23 01:58:17.106370: step: 692/529, loss: 0.0028409003280103207
2023-01-23 01:58:18.234212: step: 696/529, loss: 0.0024815560318529606
2023-01-23 01:58:19.392849: step: 700/529, loss: 0.05633602291345596
2023-01-23 01:58:20.527803: step: 704/529, loss: 0.02580423466861248
2023-01-23 01:58:21.690545: step: 708/529, loss: 0.05776557698845863
2023-01-23 01:58:22.820044: step: 712/529, loss: 0.6596037149429321
2023-01-23 01:58:23.948775: step: 716/529, loss: 0.0180421844124794
2023-01-23 01:58:25.089802: step: 720/529, loss: 0.033204078674316406
2023-01-23 01:58:26.277816: step: 724/529, loss: 0.013104247860610485
2023-01-23 01:58:27.418257: step: 728/529, loss: 0.04937624931335449
2023-01-23 01:58:28.566564: step: 732/529, loss: 0.005064773838967085
2023-01-23 01:58:29.696356: step: 736/529, loss: 0.11554157733917236
2023-01-23 01:58:30.830886: step: 740/529, loss: 0.0070552825927734375
2023-01-23 01:58:31.945503: step: 744/529, loss: 0.004991054534912109
2023-01-23 01:58:33.089104: step: 748/529, loss: 0.0004006386152468622
2023-01-23 01:58:34.255309: step: 752/529, loss: 0.003079700516536832
2023-01-23 01:58:35.404673: step: 756/529, loss: 0.006748390384018421
2023-01-23 01:58:36.545752: step: 760/529, loss: 0.007106590084731579
2023-01-23 01:58:37.677342: step: 764/529, loss: 0.009605009108781815
2023-01-23 01:58:38.815046: step: 768/529, loss: 0.012813187204301357
2023-01-23 01:58:39.924558: step: 772/529, loss: 0.008759260177612305
2023-01-23 01:58:41.056639: step: 776/529, loss: 0.011754417791962624
2023-01-23 01:58:42.216708: step: 780/529, loss: 0.13001365959644318
2023-01-23 01:58:43.375105: step: 784/529, loss: 0.03844747692346573
2023-01-23 01:58:44.497343: step: 788/529, loss: 0.02269592322409153
2023-01-23 01:58:45.641662: step: 792/529, loss: 0.032015420496463776
2023-01-23 01:58:46.800560: step: 796/529, loss: 0.009649276733398438
2023-01-23 01:58:47.972433: step: 800/529, loss: 0.0011268615489825606
2023-01-23 01:58:49.132075: step: 804/529, loss: 0.05411524698138237
2023-01-23 01:58:50.299506: step: 808/529, loss: 0.006265067961066961
2023-01-23 01:58:51.464723: step: 812/529, loss: 0.10088777542114258
2023-01-23 01:58:52.601658: step: 816/529, loss: 0.00819706916809082
2023-01-23 01:58:53.737260: step: 820/529, loss: 0.06826849281787872
2023-01-23 01:58:54.872565: step: 824/529, loss: 0.005083942320197821
2023-01-23 01:58:56.015598: step: 828/529, loss: 0.013431024737656116
2023-01-23 01:58:57.128623: step: 832/529, loss: 0.04371538385748863
2023-01-23 01:58:58.241273: step: 836/529, loss: 0.0521882027387619
2023-01-23 01:58:59.381959: step: 840/529, loss: 0.014702796936035156
2023-01-23 01:59:00.547766: step: 844/529, loss: 0.010171031579375267
2023-01-23 01:59:01.693615: step: 848/529, loss: 0.144450381398201
2023-01-23 01:59:02.812028: step: 852/529, loss: 4.5490265620173886e-05
2023-01-23 01:59:03.943108: step: 856/529, loss: 0.029668809846043587
2023-01-23 01:59:05.078166: step: 860/529, loss: 0.008723735809326172
2023-01-23 01:59:06.242563: step: 864/529, loss: 0.0061460500583052635
2023-01-23 01:59:07.399853: step: 868/529, loss: 0.003956222906708717
2023-01-23 01:59:08.558335: step: 872/529, loss: 0.05649156495928764
2023-01-23 01:59:09.693760: step: 876/529, loss: 0.008920669555664062
2023-01-23 01:59:10.811833: step: 880/529, loss: 0.08269424736499786
2023-01-23 01:59:11.937015: step: 884/529, loss: 0.0009930611122399569
2023-01-23 01:59:13.101024: step: 888/529, loss: 0.010860348120331764
2023-01-23 01:59:14.243068: step: 892/529, loss: 0.41957569122314453
2023-01-23 01:59:15.389894: step: 896/529, loss: 0.004673862364143133
2023-01-23 01:59:16.527204: step: 900/529, loss: 0.21123036742210388
2023-01-23 01:59:17.660382: step: 904/529, loss: 0.05917511135339737
2023-01-23 01:59:18.790193: step: 908/529, loss: 0.0036683082580566406
2023-01-23 01:59:19.945285: step: 912/529, loss: 0.00275042955763638
2023-01-23 01:59:21.108616: step: 916/529, loss: 0.005301475524902344
2023-01-23 01:59:22.238022: step: 920/529, loss: 0.01792621612548828
2023-01-23 01:59:23.390812: step: 924/529, loss: 0.0310866367071867
2023-01-23 01:59:24.534075: step: 928/529, loss: 0.011602211743593216
2023-01-23 01:59:25.686524: step: 932/529, loss: 0.06785359233617783
2023-01-23 01:59:26.830655: step: 936/529, loss: 0.27556121349334717
2023-01-23 01:59:27.958144: step: 940/529, loss: 0.04063882678747177
2023-01-23 01:59:29.086610: step: 944/529, loss: 0.007766342256218195
2023-01-23 01:59:30.239309: step: 948/529, loss: 0.012747096829116344
2023-01-23 01:59:31.406864: step: 952/529, loss: 0.4037269055843353
2023-01-23 01:59:32.536881: step: 956/529, loss: 0.06459865719079971
2023-01-23 01:59:33.652257: step: 960/529, loss: 0.03466486930847168
2023-01-23 01:59:34.787079: step: 964/529, loss: 0.017555857077240944
2023-01-23 01:59:35.923316: step: 968/529, loss: 0.036191560328006744
2023-01-23 01:59:37.067866: step: 972/529, loss: 0.017478371039032936
2023-01-23 01:59:38.208244: step: 976/529, loss: 0.0012299061054363847
2023-01-23 01:59:39.353656: step: 980/529, loss: 0.00601587351411581
2023-01-23 01:59:40.473604: step: 984/529, loss: 0.051186561584472656
2023-01-23 01:59:41.580107: step: 988/529, loss: 0.012828731909394264
2023-01-23 01:59:42.730595: step: 992/529, loss: 0.01859283447265625
2023-01-23 01:59:43.891468: step: 996/529, loss: 0.04816108196973801
2023-01-23 01:59:45.038637: step: 1000/529, loss: 0.07851681858301163
2023-01-23 01:59:46.172296: step: 1004/529, loss: 0.022362638264894485
2023-01-23 01:59:47.301895: step: 1008/529, loss: 0.015149594284594059
2023-01-23 01:59:48.438522: step: 1012/529, loss: 0.0010516643524169922
2023-01-23 01:59:49.575879: step: 1016/529, loss: 0.04691944271326065
2023-01-23 01:59:50.725897: step: 1020/529, loss: 0.02227654494345188
2023-01-23 01:59:51.860871: step: 1024/529, loss: 0.02096710354089737
2023-01-23 01:59:53.000687: step: 1028/529, loss: 0.048047445714473724
2023-01-23 01:59:54.126779: step: 1032/529, loss: 0.0027255534660071135
2023-01-23 01:59:55.275093: step: 1036/529, loss: 0.1443762332201004
2023-01-23 01:59:56.412611: step: 1040/529, loss: 0.10750333964824677
2023-01-23 01:59:57.581650: step: 1044/529, loss: 0.0056348321959376335
2023-01-23 01:59:58.723500: step: 1048/529, loss: 0.00713119562715292
2023-01-23 01:59:59.895984: step: 1052/529, loss: 0.009885597974061966
2023-01-23 02:00:01.050136: step: 1056/529, loss: 0.02140035666525364
2023-01-23 02:00:02.180943: step: 1060/529, loss: 0.0005970955244265497
2023-01-23 02:00:03.351675: step: 1064/529, loss: 0.03064143657684326
2023-01-23 02:00:04.485253: step: 1068/529, loss: 0.010861778631806374
2023-01-23 02:00:05.633515: step: 1072/529, loss: 0.01453475933521986
2023-01-23 02:00:06.777040: step: 1076/529, loss: 0.02284078672528267
2023-01-23 02:00:07.905150: step: 1080/529, loss: 0.005233383271843195
2023-01-23 02:00:09.029619: step: 1084/529, loss: 0.05689802020788193
2023-01-23 02:00:10.173009: step: 1088/529, loss: 0.006886959075927734
2023-01-23 02:00:11.348501: step: 1092/529, loss: 0.017435455694794655
2023-01-23 02:00:12.518635: step: 1096/529, loss: 0.06448850780725479
2023-01-23 02:00:13.664367: step: 1100/529, loss: 0.004688596818596125
2023-01-23 02:00:14.775894: step: 1104/529, loss: 0.07476458698511124
2023-01-23 02:00:15.916952: step: 1108/529, loss: 0.0071928976103663445
2023-01-23 02:00:17.056056: step: 1112/529, loss: 0.003978443332016468
2023-01-23 02:00:18.212689: step: 1116/529, loss: 0.03825988993048668
2023-01-23 02:00:19.360339: step: 1120/529, loss: 0.009201622568070889
2023-01-23 02:00:20.488847: step: 1124/529, loss: 0.11412010341882706
2023-01-23 02:00:21.629569: step: 1128/529, loss: 0.04814338684082031
2023-01-23 02:00:22.791840: step: 1132/529, loss: 0.37667930126190186
2023-01-23 02:00:23.918975: step: 1136/529, loss: 0.07248277962207794
2023-01-23 02:00:25.041815: step: 1140/529, loss: 0.005755329038947821
2023-01-23 02:00:26.162665: step: 1144/529, loss: 0.01786527782678604
2023-01-23 02:00:27.274898: step: 1148/529, loss: 0.0021076202392578125
2023-01-23 02:00:28.396458: step: 1152/529, loss: 0.01595510169863701
2023-01-23 02:00:29.567060: step: 1156/529, loss: 0.021775150671601295
2023-01-23 02:00:30.688088: step: 1160/529, loss: 0.008389472961425781
2023-01-23 02:00:31.816795: step: 1164/529, loss: 0.007810688111931086
2023-01-23 02:00:32.980832: step: 1168/529, loss: 0.06326351314783096
2023-01-23 02:00:34.160082: step: 1172/529, loss: 0.013787174597382545
2023-01-23 02:00:35.305461: step: 1176/529, loss: 0.025340938940644264
2023-01-23 02:00:36.459945: step: 1180/529, loss: 0.035582639276981354
2023-01-23 02:00:37.636394: step: 1184/529, loss: 0.02855520322918892
2023-01-23 02:00:38.774373: step: 1188/529, loss: 0.05001568794250488
2023-01-23 02:00:39.925323: step: 1192/529, loss: 0.00042896269587799907
2023-01-23 02:00:41.074047: step: 1196/529, loss: 0.06171979755163193
2023-01-23 02:00:42.198523: step: 1200/529, loss: 0.0286375992000103
2023-01-23 02:00:43.375236: step: 1204/529, loss: 0.003940582275390625
2023-01-23 02:00:44.531135: step: 1208/529, loss: 0.0458616241812706
2023-01-23 02:00:45.662451: step: 1212/529, loss: 0.04186258465051651
2023-01-23 02:00:46.821602: step: 1216/529, loss: 0.02067112922668457
2023-01-23 02:00:47.973180: step: 1220/529, loss: 0.0646023228764534
2023-01-23 02:00:49.105667: step: 1224/529, loss: 0.005819129757583141
2023-01-23 02:00:50.263371: step: 1228/529, loss: 0.010585689917206764
2023-01-23 02:00:51.413286: step: 1232/529, loss: 0.01636333577334881
2023-01-23 02:00:52.533228: step: 1236/529, loss: 0.09576711803674698
2023-01-23 02:00:53.679181: step: 1240/529, loss: 0.004456424620002508
2023-01-23 02:00:54.830349: step: 1244/529, loss: 0.009386253543198109
2023-01-23 02:00:55.945763: step: 1248/529, loss: 0.001676368759945035
2023-01-23 02:00:57.093093: step: 1252/529, loss: 0.0812651664018631
2023-01-23 02:00:58.244929: step: 1256/529, loss: 0.02503356896340847
2023-01-23 02:00:59.386145: step: 1260/529, loss: 0.011914395727217197
2023-01-23 02:01:00.543144: step: 1264/529, loss: 0.04774303734302521
2023-01-23 02:01:01.681164: step: 1268/529, loss: 0.0016178131336346269
2023-01-23 02:01:02.817957: step: 1272/529, loss: 0.1578844040632248
2023-01-23 02:01:03.964422: step: 1276/529, loss: 0.01888093911111355
2023-01-23 02:01:05.089795: step: 1280/529, loss: 0.09535980224609375
2023-01-23 02:01:06.248829: step: 1284/529, loss: 0.0023229599464684725
2023-01-23 02:01:07.407429: step: 1288/529, loss: 0.028337908908724785
2023-01-23 02:01:08.545283: step: 1292/529, loss: 0.002019214676693082
2023-01-23 02:01:09.697311: step: 1296/529, loss: 0.008580779656767845
2023-01-23 02:01:10.853880: step: 1300/529, loss: 0.030537987127900124
2023-01-23 02:01:11.971172: step: 1304/529, loss: 0.030974293127655983
2023-01-23 02:01:13.142195: step: 1308/529, loss: 0.04489422217011452
2023-01-23 02:01:14.303028: step: 1312/529, loss: 0.00021810531325172633
2023-01-23 02:01:15.459504: step: 1316/529, loss: 0.0043315887451171875
2023-01-23 02:01:16.628213: step: 1320/529, loss: 0.04198741912841797
2023-01-23 02:01:17.779912: step: 1324/529, loss: 0.004833888728171587
2023-01-23 02:01:18.904516: step: 1328/529, loss: 0.00950317457318306
2023-01-23 02:01:20.045051: step: 1332/529, loss: 0.07978996634483337
2023-01-23 02:01:21.159212: step: 1336/529, loss: 0.0001537799835205078
2023-01-23 02:01:22.322409: step: 1340/529, loss: 0.03995666652917862
2023-01-23 02:01:23.457167: step: 1344/529, loss: 0.0014316558372229338
2023-01-23 02:01:24.622627: step: 1348/529, loss: 0.07693634182214737
2023-01-23 02:01:25.747605: step: 1352/529, loss: 0.006489467807114124
2023-01-23 02:01:26.879132: step: 1356/529, loss: 0.006716489791870117
2023-01-23 02:01:28.011590: step: 1360/529, loss: 0.010333252139389515
2023-01-23 02:01:29.154677: step: 1364/529, loss: 0.007012748625129461
2023-01-23 02:01:30.304771: step: 1368/529, loss: 0.03144798427820206
2023-01-23 02:01:31.458309: step: 1372/529, loss: 0.021324826404452324
2023-01-23 02:01:32.611344: step: 1376/529, loss: 0.05162010341882706
2023-01-23 02:01:33.756030: step: 1380/529, loss: 0.009546756744384766
2023-01-23 02:01:34.871319: step: 1384/529, loss: 0.005966758821159601
2023-01-23 02:01:35.998821: step: 1388/529, loss: 0.028606224805116653
2023-01-23 02:01:37.143911: step: 1392/529, loss: 0.009893418289721012
2023-01-23 02:01:38.298011: step: 1396/529, loss: 0.003786468645557761
2023-01-23 02:01:39.458129: step: 1400/529, loss: 0.01431961078196764
2023-01-23 02:01:40.569749: step: 1404/529, loss: 0.027814865112304688
2023-01-23 02:01:41.707180: step: 1408/529, loss: 0.056890297681093216
2023-01-23 02:01:42.886508: step: 1412/529, loss: 0.07930316776037216
2023-01-23 02:01:44.022864: step: 1416/529, loss: 0.08392544090747833
2023-01-23 02:01:45.153225: step: 1420/529, loss: 0.030322551727294922
2023-01-23 02:01:46.280220: step: 1424/529, loss: 0.04663574695587158
2023-01-23 02:01:47.449202: step: 1428/529, loss: 0.08130503445863724
2023-01-23 02:01:48.612074: step: 1432/529, loss: 0.008636855520308018
2023-01-23 02:01:49.741128: step: 1436/529, loss: 0.003972244448959827
2023-01-23 02:01:50.860984: step: 1440/529, loss: 0.016019249334931374
2023-01-23 02:01:52.026482: step: 1444/529, loss: 0.0065202717669308186
2023-01-23 02:01:53.179781: step: 1448/529, loss: 0.03464512899518013
2023-01-23 02:01:54.308160: step: 1452/529, loss: 0.020255088806152344
2023-01-23 02:01:55.427934: step: 1456/529, loss: 0.03506002575159073
2023-01-23 02:01:56.567411: step: 1460/529, loss: 0.0009643555385991931
2023-01-23 02:01:57.694409: step: 1464/529, loss: 0.0051961299031972885
2023-01-23 02:01:58.828895: step: 1468/529, loss: 0.035044290125370026
2023-01-23 02:01:59.990707: step: 1472/529, loss: 0.03768463060259819
2023-01-23 02:02:01.118513: step: 1476/529, loss: 0.4639724791049957
2023-01-23 02:02:02.267270: step: 1480/529, loss: 0.04469423368573189
2023-01-23 02:02:03.406982: step: 1484/529, loss: 0.01664752885699272
2023-01-23 02:02:04.538736: step: 1488/529, loss: 0.00614585867151618
2023-01-23 02:02:05.688805: step: 1492/529, loss: 0.02300853654742241
2023-01-23 02:02:06.819546: step: 1496/529, loss: 0.05658302083611488
2023-01-23 02:02:08.016265: step: 1500/529, loss: 0.2596409022808075
2023-01-23 02:02:09.203206: step: 1504/529, loss: 0.04389248043298721
2023-01-23 02:02:10.343668: step: 1508/529, loss: 0.07749929279088974
2023-01-23 02:02:11.458489: step: 1512/529, loss: 0.023305749520659447
2023-01-23 02:02:12.620126: step: 1516/529, loss: 0.023348616436123848
2023-01-23 02:02:13.742367: step: 1520/529, loss: 0.00030350685119628906
2023-01-23 02:02:14.876550: step: 1524/529, loss: 0.0035295486450195312
2023-01-23 02:02:16.045505: step: 1528/529, loss: 0.0034933090209960938
2023-01-23 02:02:17.196910: step: 1532/529, loss: 0.019969414919614792
2023-01-23 02:02:18.328610: step: 1536/529, loss: 0.02688765525817871
2023-01-23 02:02:19.474705: step: 1540/529, loss: 0.04217548668384552
2023-01-23 02:02:20.611360: step: 1544/529, loss: 0.0020812987349927425
2023-01-23 02:02:21.772534: step: 1548/529, loss: 0.08510151505470276
2023-01-23 02:02:22.907394: step: 1552/529, loss: 0.019606687128543854
2023-01-23 02:02:24.041407: step: 1556/529, loss: 0.0450017936527729
2023-01-23 02:02:25.180638: step: 1560/529, loss: 0.01704845391213894
2023-01-23 02:02:26.334768: step: 1564/529, loss: 0.0031768563203513622
2023-01-23 02:02:27.477830: step: 1568/529, loss: 0.01782960817217827
2023-01-23 02:02:28.606865: step: 1572/529, loss: 0.0015869140625
2023-01-23 02:02:29.778205: step: 1576/529, loss: 0.08877535164356232
2023-01-23 02:02:30.930032: step: 1580/529, loss: 0.0011180877918377519
2023-01-23 02:02:32.064108: step: 1584/529, loss: 0.008982563391327858
2023-01-23 02:02:33.238412: step: 1588/529, loss: 0.012991905212402344
2023-01-23 02:02:34.393712: step: 1592/529, loss: 0.07841567695140839
2023-01-23 02:02:35.545654: step: 1596/529, loss: 0.012593078427016735
2023-01-23 02:02:36.676927: step: 1600/529, loss: 0.04396235942840576
2023-01-23 02:02:37.839810: step: 1604/529, loss: 0.007347392849624157
2023-01-23 02:02:38.996920: step: 1608/529, loss: 0.11661539226770401
2023-01-23 02:02:40.149509: step: 1612/529, loss: 0.13773012161254883
2023-01-23 02:02:41.270328: step: 1616/529, loss: 0.08009806275367737
2023-01-23 02:02:42.413883: step: 1620/529, loss: 0.011623095721006393
2023-01-23 02:02:43.544384: step: 1624/529, loss: 0.0416659377515316
2023-01-23 02:02:44.657292: step: 1628/529, loss: 0.04001579433679581
2023-01-23 02:02:45.802346: step: 1632/529, loss: 0.05554688721895218
2023-01-23 02:02:46.916811: step: 1636/529, loss: 0.04513001814484596
2023-01-23 02:02:48.062070: step: 1640/529, loss: 0.01767749898135662
2023-01-23 02:02:49.174278: step: 1644/529, loss: 0.7634038925170898
2023-01-23 02:02:50.301742: step: 1648/529, loss: 0.005371284671127796
2023-01-23 02:02:51.445281: step: 1652/529, loss: 0.004937505815178156
2023-01-23 02:02:52.596504: step: 1656/529, loss: 0.005384254269301891
2023-01-23 02:02:53.733020: step: 1660/529, loss: 0.05162429437041283
2023-01-23 02:02:54.879601: step: 1664/529, loss: 0.00018367767916060984
2023-01-23 02:02:56.014003: step: 1668/529, loss: 0.008079337887465954
2023-01-23 02:02:57.184460: step: 1672/529, loss: 0.11684408783912659
2023-01-23 02:02:58.317973: step: 1676/529, loss: 0.025528907775878906
2023-01-23 02:02:59.466518: step: 1680/529, loss: 0.0022632598411291838
2023-01-23 02:03:00.584046: step: 1684/529, loss: 0.03894843906164169
2023-01-23 02:03:01.729866: step: 1688/529, loss: 0.01730175130069256
2023-01-23 02:03:02.899714: step: 1692/529, loss: 0.019917108118534088
2023-01-23 02:03:04.011665: step: 1696/529, loss: 0.023000001907348633
2023-01-23 02:03:05.159885: step: 1700/529, loss: 0.010028553195297718
2023-01-23 02:03:06.264364: step: 1704/529, loss: 0.1472880244255066
2023-01-23 02:03:07.414862: step: 1708/529, loss: 0.01743769645690918
2023-01-23 02:03:08.551972: step: 1712/529, loss: 0.00885009765625
2023-01-23 02:03:09.702335: step: 1716/529, loss: 0.02431316487491131
2023-01-23 02:03:10.819895: step: 1720/529, loss: 0.09490552544593811
2023-01-23 02:03:11.919109: step: 1724/529, loss: 0.00895319040864706
2023-01-23 02:03:13.055751: step: 1728/529, loss: 0.2750937044620514
2023-01-23 02:03:14.215022: step: 1732/529, loss: 0.03558792918920517
2023-01-23 02:03:15.360843: step: 1736/529, loss: 0.050969600677490234
2023-01-23 02:03:16.479541: step: 1740/529, loss: 0.011721134185791016
2023-01-23 02:03:17.633855: step: 1744/529, loss: 0.023114491254091263
2023-01-23 02:03:18.789250: step: 1748/529, loss: 0.001452541328035295
2023-01-23 02:03:19.899137: step: 1752/529, loss: 0.03354015201330185
2023-01-23 02:03:21.078879: step: 1756/529, loss: 0.08127937465906143
2023-01-23 02:03:22.211388: step: 1760/529, loss: 0.019754886627197266
2023-01-23 02:03:23.356457: step: 1764/529, loss: 0.03828897699713707
2023-01-23 02:03:24.458599: step: 1768/529, loss: 0.010671710595488548
2023-01-23 02:03:25.576149: step: 1772/529, loss: 0.01685638353228569
2023-01-23 02:03:26.704089: step: 1776/529, loss: 0.01693294383585453
2023-01-23 02:03:27.846731: step: 1780/529, loss: 0.00014791489229537547
2023-01-23 02:03:28.974907: step: 1784/529, loss: 0.03846006467938423
2023-01-23 02:03:30.176637: step: 1788/529, loss: 0.6008392572402954
2023-01-23 02:03:31.308928: step: 1792/529, loss: 0.023286307230591774
2023-01-23 02:03:32.446023: step: 1796/529, loss: 0.07066001743078232
2023-01-23 02:03:33.586769: step: 1800/529, loss: 0.016535472124814987
2023-01-23 02:03:34.727569: step: 1804/529, loss: 0.3201374113559723
2023-01-23 02:03:35.894808: step: 1808/529, loss: 0.0007961273076944053
2023-01-23 02:03:37.029903: step: 1812/529, loss: 0.05725574493408203
2023-01-23 02:03:38.163110: step: 1816/529, loss: 0.0387762077152729
2023-01-23 02:03:39.296389: step: 1820/529, loss: 0.0030109407380223274
2023-01-23 02:03:40.446137: step: 1824/529, loss: 0.03799133375287056
2023-01-23 02:03:41.584571: step: 1828/529, loss: 0.01337509136646986
2023-01-23 02:03:42.737475: step: 1832/529, loss: 0.016776561737060547
2023-01-23 02:03:43.885708: step: 1836/529, loss: 0.0409914031624794
2023-01-23 02:03:45.012214: step: 1840/529, loss: 0.000979948090389371
2023-01-23 02:03:46.137331: step: 1844/529, loss: 0.04781847447156906
2023-01-23 02:03:47.289680: step: 1848/529, loss: 0.35043296217918396
2023-01-23 02:03:48.448174: step: 1852/529, loss: 0.013577461242675781
2023-01-23 02:03:49.591278: step: 1856/529, loss: 0.013792228884994984
2023-01-23 02:03:50.717640: step: 1860/529, loss: 0.02039957046508789
2023-01-23 02:03:51.875545: step: 1864/529, loss: 0.022695161402225494
2023-01-23 02:03:53.015237: step: 1868/529, loss: 0.5700778961181641
2023-01-23 02:03:54.155531: step: 1872/529, loss: 0.05107765272259712
2023-01-23 02:03:55.263821: step: 1876/529, loss: 0.03049449995160103
2023-01-23 02:03:56.420359: step: 1880/529, loss: 0.01476974505931139
2023-01-23 02:03:57.533773: step: 1884/529, loss: 0.0025437355507165194
2023-01-23 02:03:58.653086: step: 1888/529, loss: 0.009549331851303577
2023-01-23 02:03:59.809497: step: 1892/529, loss: 0.005546092987060547
2023-01-23 02:04:00.943865: step: 1896/529, loss: 0.004867935553193092
2023-01-23 02:04:02.070088: step: 1900/529, loss: 0.017035389319062233
2023-01-23 02:04:03.205889: step: 1904/529, loss: 0.01043329294770956
2023-01-23 02:04:04.355344: step: 1908/529, loss: 0.0014803409576416016
2023-01-23 02:04:05.514307: step: 1912/529, loss: 0.09273986518383026
2023-01-23 02:04:06.652368: step: 1916/529, loss: 0.015713995322585106
2023-01-23 02:04:07.792341: step: 1920/529, loss: 0.014237403869628906
2023-01-23 02:04:08.955052: step: 1924/529, loss: 0.046131327748298645
2023-01-23 02:04:10.101283: step: 1928/529, loss: 0.05037422105669975
2023-01-23 02:04:11.265310: step: 1932/529, loss: 0.04351005703210831
2023-01-23 02:04:12.414657: step: 1936/529, loss: 0.002090549562126398
2023-01-23 02:04:13.571365: step: 1940/529, loss: 0.10046205669641495
2023-01-23 02:04:14.697562: step: 1944/529, loss: 0.03925180435180664
2023-01-23 02:04:15.870361: step: 1948/529, loss: 0.018270110711455345
2023-01-23 02:04:16.992065: step: 1952/529, loss: 0.002542448230087757
2023-01-23 02:04:18.130166: step: 1956/529, loss: 0.01734628714621067
2023-01-23 02:04:19.311425: step: 1960/529, loss: 0.04117755964398384
2023-01-23 02:04:20.440757: step: 1964/529, loss: 0.024634741246700287
2023-01-23 02:04:21.573304: step: 1968/529, loss: 0.001993560930714011
2023-01-23 02:04:22.746946: step: 1972/529, loss: 0.02664492093026638
2023-01-23 02:04:23.900941: step: 1976/529, loss: 0.21703921258449554
2023-01-23 02:04:25.046365: step: 1980/529, loss: 0.07699108123779297
2023-01-23 02:04:26.184794: step: 1984/529, loss: 0.0547727607190609
2023-01-23 02:04:27.352223: step: 1988/529, loss: 0.07107200473546982
2023-01-23 02:04:28.483789: step: 1992/529, loss: 0.00813512783497572
2023-01-23 02:04:29.636822: step: 1996/529, loss: 0.03665969520807266
2023-01-23 02:04:30.752416: step: 2000/529, loss: 0.013404274359345436
2023-01-23 02:04:31.879536: step: 2004/529, loss: 0.018314838409423828
2023-01-23 02:04:33.044544: step: 2008/529, loss: 0.036168672144412994
2023-01-23 02:04:34.159704: step: 2012/529, loss: 0.04513759911060333
2023-01-23 02:04:35.278089: step: 2016/529, loss: 0.06351499259471893
2023-01-23 02:04:36.426334: step: 2020/529, loss: 0.013169956393539906
2023-01-23 02:04:37.550485: step: 2024/529, loss: 0.0058501241728663445
2023-01-23 02:04:38.697723: step: 2028/529, loss: 0.03847971186041832
2023-01-23 02:04:39.817672: step: 2032/529, loss: 0.08768733590841293
2023-01-23 02:04:40.969077: step: 2036/529, loss: 0.035093024373054504
2023-01-23 02:04:42.075794: step: 2040/529, loss: 0.00420115003362298
2023-01-23 02:04:43.232767: step: 2044/529, loss: 0.0059295655228197575
2023-01-23 02:04:44.364209: step: 2048/529, loss: 0.011991972103714943
2023-01-23 02:04:45.520606: step: 2052/529, loss: 0.03097086027264595
2023-01-23 02:04:46.654692: step: 2056/529, loss: 0.051961518824100494
2023-01-23 02:04:47.816498: step: 2060/529, loss: 0.005309009924530983
2023-01-23 02:04:48.928331: step: 2064/529, loss: 0.04272814095020294
2023-01-23 02:04:50.051659: step: 2068/529, loss: 0.04711475223302841
2023-01-23 02:04:51.188068: step: 2072/529, loss: 0.015694905072450638
2023-01-23 02:04:52.347047: step: 2076/529, loss: 0.012761592864990234
2023-01-23 02:04:53.495465: step: 2080/529, loss: 0.0014646290801465511
2023-01-23 02:04:54.630373: step: 2084/529, loss: 0.050594329833984375
2023-01-23 02:04:55.765429: step: 2088/529, loss: 0.0034246444702148438
2023-01-23 02:04:56.906766: step: 2092/529, loss: 0.5826783776283264
2023-01-23 02:04:58.045236: step: 2096/529, loss: 0.01982097700238228
2023-01-23 02:04:59.218233: step: 2100/529, loss: 0.05595235899090767
2023-01-23 02:05:00.346363: step: 2104/529, loss: 0.049640558660030365
2023-01-23 02:05:01.482160: step: 2108/529, loss: 0.039298154413700104
2023-01-23 02:05:02.616132: step: 2112/529, loss: 0.003610137151554227
2023-01-23 02:05:03.774146: step: 2116/529, loss: 0.039118196815252304
==================================================
Loss: 0.056
--------------------
Dev: {'event': {'p': 0.5752741774675972, 'r': 0.7683089214380826, 'f1': 0.6579247434435577}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6139944392956441, 'r': 0.7676709154113557, 'f1': 0.6822863027806385}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.5757575757575758, 'r': 0.6031746031746031, 'f1': 0.5891472868217055}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.4772727272727273, 'r': 0.5833333333333334, 'f1': 0.5250000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:05:45.651853: step: 4/529, loss: 0.16996756196022034
2023-01-23 02:05:46.789087: step: 8/529, loss: 0.005076599307358265
2023-01-23 02:05:47.924149: step: 12/529, loss: 0.007590484339743853
2023-01-23 02:05:49.062077: step: 16/529, loss: 0.03187151253223419
2023-01-23 02:05:50.204824: step: 20/529, loss: 0.0015483855968341231
2023-01-23 02:05:51.325578: step: 24/529, loss: 0.0004878044128417969
2023-01-23 02:05:52.437764: step: 28/529, loss: 0.026233481243252754
2023-01-23 02:05:53.588162: step: 32/529, loss: 0.006692695897072554
2023-01-23 02:05:54.722678: step: 36/529, loss: 0.02227935940027237
2023-01-23 02:05:55.880610: step: 40/529, loss: 0.042588043957948685
2023-01-23 02:05:57.035297: step: 44/529, loss: 0.02246375009417534
2023-01-23 02:05:58.170557: step: 48/529, loss: 0.009333801455795765
2023-01-23 02:05:59.301205: step: 52/529, loss: 9.773074998520315e-05
2023-01-23 02:06:00.401527: step: 56/529, loss: 6.961822691664565e-06
2023-01-23 02:06:01.544720: step: 60/529, loss: 0.011077404022216797
2023-01-23 02:06:02.666289: step: 64/529, loss: 0.010853481478989124
2023-01-23 02:06:03.813583: step: 68/529, loss: 0.07768469303846359
2023-01-23 02:06:04.966502: step: 72/529, loss: 0.05700492858886719
2023-01-23 02:06:06.096943: step: 76/529, loss: 0.0006534576532430947
2023-01-23 02:06:07.282446: step: 80/529, loss: 0.01553564053028822
2023-01-23 02:06:08.433500: step: 84/529, loss: 0.02438812330365181
2023-01-23 02:06:09.551743: step: 88/529, loss: 0.00216846470721066
2023-01-23 02:06:10.705444: step: 92/529, loss: 0.0062614441849291325
2023-01-23 02:06:11.846637: step: 96/529, loss: 0.05970897525548935
2023-01-23 02:06:12.990287: step: 100/529, loss: 0.005962848663330078
2023-01-23 02:06:14.169145: step: 104/529, loss: 0.0027582645416259766
2023-01-23 02:06:15.308585: step: 108/529, loss: 0.013190556317567825
2023-01-23 02:06:16.442935: step: 112/529, loss: 0.08990192413330078
2023-01-23 02:06:17.548848: step: 116/529, loss: 0.01794157177209854
2023-01-23 02:06:18.691626: step: 120/529, loss: 0.0024349212180823088
2023-01-23 02:06:19.832913: step: 124/529, loss: 0.01016225852072239
2023-01-23 02:06:20.989526: step: 128/529, loss: 0.007003259379416704
2023-01-23 02:06:22.105240: step: 132/529, loss: 0.010140038095414639
2023-01-23 02:06:23.254629: step: 136/529, loss: 0.05052977055311203
2023-01-23 02:06:24.396044: step: 140/529, loss: 0.6274555325508118
2023-01-23 02:06:25.557626: step: 144/529, loss: 0.00042402741382829845
2023-01-23 02:06:26.680767: step: 148/529, loss: 0.0008934021461755037
2023-01-23 02:06:27.815540: step: 152/529, loss: 0.046714212745428085
2023-01-23 02:06:28.948198: step: 156/529, loss: 0.05329084396362305
2023-01-23 02:06:30.070703: step: 160/529, loss: 0.7044841647148132
2023-01-23 02:06:31.221971: step: 164/529, loss: 0.06576278060674667
2023-01-23 02:06:32.376098: step: 168/529, loss: 0.0871133804321289
2023-01-23 02:06:33.497793: step: 172/529, loss: 0.008204365149140358
2023-01-23 02:06:34.669207: step: 176/529, loss: 0.031652070581912994
2023-01-23 02:06:35.798288: step: 180/529, loss: 0.0943388044834137
2023-01-23 02:06:36.947983: step: 184/529, loss: 0.006318187806755304
2023-01-23 02:06:38.063165: step: 188/529, loss: 0.012644767761230469
2023-01-23 02:06:39.230664: step: 192/529, loss: 0.019297409802675247
2023-01-23 02:06:40.386251: step: 196/529, loss: 0.020193099975585938
2023-01-23 02:06:41.535799: step: 200/529, loss: 0.06245727464556694
2023-01-23 02:06:42.696559: step: 204/529, loss: 0.007662010379135609
2023-01-23 02:06:43.828369: step: 208/529, loss: 0.002058363053947687
2023-01-23 02:06:44.979449: step: 212/529, loss: 0.022742461413145065
2023-01-23 02:06:46.183742: step: 216/529, loss: 0.03687229007482529
2023-01-23 02:06:47.300817: step: 220/529, loss: 0.0328306183218956
2023-01-23 02:06:48.431330: step: 224/529, loss: 0.002059746067970991
2023-01-23 02:06:49.588474: step: 228/529, loss: 0.03150958940386772
2023-01-23 02:06:50.714548: step: 232/529, loss: 0.0026178359985351562
2023-01-23 02:06:51.845347: step: 236/529, loss: 0.04283933714032173
2023-01-23 02:06:52.988323: step: 240/529, loss: 0.08069400489330292
2023-01-23 02:06:54.114738: step: 244/529, loss: 0.05912809073925018
2023-01-23 02:06:55.244278: step: 248/529, loss: 0.008021831512451172
2023-01-23 02:06:56.380207: step: 252/529, loss: 0.03494071960449219
2023-01-23 02:06:57.523854: step: 256/529, loss: 0.06016801297664642
2023-01-23 02:06:58.668989: step: 260/529, loss: 0.0014163017040118575
2023-01-23 02:06:59.840060: step: 264/529, loss: 0.029808808118104935
2023-01-23 02:07:00.976226: step: 268/529, loss: 0.027716446667909622
2023-01-23 02:07:02.123382: step: 272/529, loss: 0.02725806273519993
2023-01-23 02:07:03.261824: step: 276/529, loss: 0.018924428150057793
2023-01-23 02:07:04.385672: step: 280/529, loss: 0.01695718802511692
2023-01-23 02:07:05.524307: step: 284/529, loss: 0.07867870479822159
2023-01-23 02:07:06.663154: step: 288/529, loss: 0.007264202460646629
2023-01-23 02:07:07.804559: step: 292/529, loss: 0.0009866715408861637
2023-01-23 02:07:08.957076: step: 296/529, loss: 0.11060390621423721
2023-01-23 02:07:10.088760: step: 300/529, loss: 0.03944873809814453
2023-01-23 02:07:11.272364: step: 304/529, loss: 0.009007835760712624
2023-01-23 02:07:12.398438: step: 308/529, loss: 0.00017089843458961695
2023-01-23 02:07:13.530202: step: 312/529, loss: 0.02495289035141468
2023-01-23 02:07:14.684257: step: 316/529, loss: 0.008362198248505592
2023-01-23 02:07:15.842065: step: 320/529, loss: 0.04006824642419815
2023-01-23 02:07:16.978555: step: 324/529, loss: 0.2926328480243683
2023-01-23 02:07:18.121057: step: 328/529, loss: 0.0011467934818938375
2023-01-23 02:07:19.264313: step: 332/529, loss: 0.08258338272571564
2023-01-23 02:07:20.387082: step: 336/529, loss: 0.009478378109633923
2023-01-23 02:07:21.526444: step: 340/529, loss: 0.012785816565155983
2023-01-23 02:07:22.705900: step: 344/529, loss: 0.008547211065888405
2023-01-23 02:07:23.837371: step: 348/529, loss: 0.30324259400367737
2023-01-23 02:07:24.967535: step: 352/529, loss: 0.005092620849609375
2023-01-23 02:07:26.124281: step: 356/529, loss: 0.058544449508190155
2023-01-23 02:07:27.236995: step: 360/529, loss: 0.010987663641571999
2023-01-23 02:07:28.373606: step: 364/529, loss: 0.04443359375
2023-01-23 02:07:29.525468: step: 368/529, loss: 0.038179781287908554
2023-01-23 02:07:30.684549: step: 372/529, loss: 0.0011805534595623612
2023-01-23 02:07:31.839777: step: 376/529, loss: 0.012799929827451706
2023-01-23 02:07:32.979672: step: 380/529, loss: 0.002487563993781805
2023-01-23 02:07:34.103693: step: 384/529, loss: 0.016067029908299446
2023-01-23 02:07:35.251705: step: 388/529, loss: 0.0014701009495183825
2023-01-23 02:07:36.415846: step: 392/529, loss: 0.3104632794857025
2023-01-23 02:07:37.568200: step: 396/529, loss: 0.020148087292909622
2023-01-23 02:07:38.702374: step: 400/529, loss: 0.0029549598693847656
2023-01-23 02:07:39.856057: step: 404/529, loss: 0.008225655183196068
2023-01-23 02:07:41.016902: step: 408/529, loss: 0.026165008544921875
2023-01-23 02:07:42.160459: step: 412/529, loss: 0.005286216735839844
2023-01-23 02:07:43.284547: step: 416/529, loss: 0.006191444583237171
2023-01-23 02:07:44.426428: step: 420/529, loss: 0.0009723663097247481
2023-01-23 02:07:45.578934: step: 424/529, loss: 0.018939495086669922
2023-01-23 02:07:46.705684: step: 428/529, loss: 0.01410207711160183
2023-01-23 02:07:47.840453: step: 432/529, loss: 0.020436527207493782
2023-01-23 02:07:49.002360: step: 436/529, loss: 0.08088894188404083
2023-01-23 02:07:50.143089: step: 440/529, loss: 0.004369902890175581
2023-01-23 02:07:51.306407: step: 444/529, loss: 0.007995223626494408
2023-01-23 02:07:52.424757: step: 448/529, loss: 0.000412178022088483
2023-01-23 02:07:53.562221: step: 452/529, loss: 0.055826760828495026
2023-01-23 02:07:54.698488: step: 456/529, loss: 0.030097246170043945
2023-01-23 02:07:55.823865: step: 460/529, loss: 0.7274318337440491
2023-01-23 02:07:56.971174: step: 464/529, loss: 0.002973270369693637
2023-01-23 02:07:58.132916: step: 468/529, loss: 0.012209320440888405
2023-01-23 02:07:59.261589: step: 472/529, loss: 0.03964290767908096
2023-01-23 02:08:00.386414: step: 476/529, loss: 0.0015967368381097913
2023-01-23 02:08:01.544178: step: 480/529, loss: 0.029360389336943626
2023-01-23 02:08:02.695485: step: 484/529, loss: 0.03325538709759712
2023-01-23 02:08:03.865470: step: 488/529, loss: 0.0014679909218102694
2023-01-23 02:08:05.017346: step: 492/529, loss: 0.00027151108952239156
2023-01-23 02:08:06.170885: step: 496/529, loss: 0.0003137588792014867
2023-01-23 02:08:07.314320: step: 500/529, loss: 0.1130281463265419
2023-01-23 02:08:08.464179: step: 504/529, loss: 0.0010694622760638595
2023-01-23 02:08:09.586694: step: 508/529, loss: 0.005390739534050226
2023-01-23 02:08:10.731135: step: 512/529, loss: 0.003537750570103526
2023-01-23 02:08:11.866215: step: 516/529, loss: 0.0022899149917066097
2023-01-23 02:08:12.995631: step: 520/529, loss: 0.012795163318514824
2023-01-23 02:08:14.166054: step: 524/529, loss: 0.023830413818359375
2023-01-23 02:08:15.307469: step: 528/529, loss: 0.08153896033763885
2023-01-23 02:08:16.459979: step: 532/529, loss: 0.003934192471206188
2023-01-23 02:08:17.611666: step: 536/529, loss: 0.04983186721801758
2023-01-23 02:08:18.746717: step: 540/529, loss: 0.024060631170868874
2023-01-23 02:08:19.896321: step: 544/529, loss: 0.00870666466653347
2023-01-23 02:08:21.065845: step: 548/529, loss: 0.0002626419300213456
2023-01-23 02:08:22.212982: step: 552/529, loss: 0.01973896101117134
2023-01-23 02:08:23.353855: step: 556/529, loss: 0.11025281250476837
2023-01-23 02:08:24.494481: step: 560/529, loss: 0.0601528063416481
2023-01-23 02:08:25.637697: step: 564/529, loss: 0.004730796907097101
2023-01-23 02:08:26.789095: step: 568/529, loss: 0.001201629638671875
2023-01-23 02:08:27.931121: step: 572/529, loss: 0.005031776614487171
2023-01-23 02:08:29.078732: step: 576/529, loss: 0.012799644842743874
2023-01-23 02:08:30.209314: step: 580/529, loss: 0.04560399055480957
2023-01-23 02:08:31.344730: step: 584/529, loss: 0.002846240997314453
2023-01-23 02:08:32.493190: step: 588/529, loss: 0.010749626904726028
2023-01-23 02:08:33.644937: step: 592/529, loss: 0.004678439814597368
2023-01-23 02:08:34.757543: step: 596/529, loss: 0.024710988625884056
2023-01-23 02:08:35.904651: step: 600/529, loss: 0.008387947455048561
2023-01-23 02:08:37.030451: step: 604/529, loss: 0.10133734345436096
2023-01-23 02:08:38.152554: step: 608/529, loss: 0.0006291388999670744
2023-01-23 02:08:39.312846: step: 612/529, loss: 0.008056163787841797
2023-01-23 02:08:40.441512: step: 616/529, loss: 0.015163994394242764
2023-01-23 02:08:41.569370: step: 620/529, loss: 0.005123329348862171
2023-01-23 02:08:42.677695: step: 624/529, loss: 0.032633017748594284
2023-01-23 02:08:43.851992: step: 628/529, loss: 0.22910137474536896
2023-01-23 02:08:45.022282: step: 632/529, loss: 0.031112540513277054
2023-01-23 02:08:46.126130: step: 636/529, loss: 0.009467506781220436
2023-01-23 02:08:47.277356: step: 640/529, loss: 0.013737487606704235
2023-01-23 02:08:48.421416: step: 644/529, loss: 0.03164634481072426
2023-01-23 02:08:49.556105: step: 648/529, loss: 0.02077159844338894
2023-01-23 02:08:50.707669: step: 652/529, loss: 0.05575375631451607
2023-01-23 02:08:51.819874: step: 656/529, loss: 0.00039901735726743937
2023-01-23 02:08:52.952838: step: 660/529, loss: 0.005500936880707741
2023-01-23 02:08:54.102803: step: 664/529, loss: 0.0033428191673010588
2023-01-23 02:08:55.281462: step: 668/529, loss: 0.0009239197243005037
2023-01-23 02:08:56.429239: step: 672/529, loss: 0.0018924714531749487
2023-01-23 02:08:57.553585: step: 676/529, loss: 0.008203268051147461
2023-01-23 02:08:58.707505: step: 680/529, loss: 0.021155167371034622
2023-01-23 02:08:59.853696: step: 684/529, loss: 0.10065823048353195
2023-01-23 02:09:01.012975: step: 688/529, loss: 0.04441213980317116
2023-01-23 02:09:02.154966: step: 692/529, loss: 0.09707680344581604
2023-01-23 02:09:03.293902: step: 696/529, loss: 0.014704705215990543
2023-01-23 02:09:04.421044: step: 700/529, loss: 0.006220054812729359
2023-01-23 02:09:05.553367: step: 704/529, loss: 0.04774494096636772
2023-01-23 02:09:06.700940: step: 708/529, loss: 0.0047775269486010075
2023-01-23 02:09:07.831685: step: 712/529, loss: 0.055693067610263824
2023-01-23 02:09:08.990316: step: 716/529, loss: 0.006354904267936945
2023-01-23 02:09:10.125684: step: 720/529, loss: 0.02730097621679306
2023-01-23 02:09:11.250682: step: 724/529, loss: 0.0012255669571459293
2023-01-23 02:09:12.421368: step: 728/529, loss: 0.019093705341219902
2023-01-23 02:09:13.585000: step: 732/529, loss: 0.03645744174718857
2023-01-23 02:09:14.745280: step: 736/529, loss: 0.0029304504860192537
2023-01-23 02:09:15.878877: step: 740/529, loss: 0.012084770947694778
2023-01-23 02:09:17.037247: step: 744/529, loss: 0.017528818920254707
2023-01-23 02:09:18.181496: step: 748/529, loss: 0.06217384338378906
2023-01-23 02:09:19.340438: step: 752/529, loss: 0.1284852921962738
2023-01-23 02:09:20.503777: step: 756/529, loss: 0.053660109639167786
2023-01-23 02:09:21.645297: step: 760/529, loss: 0.08294791728258133
2023-01-23 02:09:22.786074: step: 764/529, loss: 0.08515243977308273
2023-01-23 02:09:23.941520: step: 768/529, loss: 0.02444629743695259
2023-01-23 02:09:25.051781: step: 772/529, loss: 0.01609659381210804
2023-01-23 02:09:26.156868: step: 776/529, loss: 0.003753805300220847
2023-01-23 02:09:27.332931: step: 780/529, loss: 0.8426268100738525
2023-01-23 02:09:28.482661: step: 784/529, loss: 0.011741161346435547
2023-01-23 02:09:29.641030: step: 788/529, loss: 0.016111088916659355
2023-01-23 02:09:30.781281: step: 792/529, loss: 0.10392117500305176
2023-01-23 02:09:31.903264: step: 796/529, loss: 0.004294014070183039
2023-01-23 02:09:33.056748: step: 800/529, loss: 0.04252567142248154
2023-01-23 02:09:34.223576: step: 804/529, loss: 0.03582897037267685
2023-01-23 02:09:35.401998: step: 808/529, loss: 0.003137016436085105
2023-01-23 02:09:36.523759: step: 812/529, loss: 0.00883330125361681
2023-01-23 02:09:37.643633: step: 816/529, loss: 0.0005880355602130294
2023-01-23 02:09:38.769791: step: 820/529, loss: 0.04645185545086861
2023-01-23 02:09:39.899355: step: 824/529, loss: 0.029874280095100403
2023-01-23 02:09:41.025956: step: 828/529, loss: 0.0016699791885912418
2023-01-23 02:09:42.157530: step: 832/529, loss: 0.0007974624750204384
2023-01-23 02:09:43.295825: step: 836/529, loss: 0.04726262018084526
2023-01-23 02:09:44.455066: step: 840/529, loss: 0.004408645443618298
2023-01-23 02:09:45.587584: step: 844/529, loss: 0.011714362539350986
2023-01-23 02:09:46.726397: step: 848/529, loss: 0.027034951373934746
2023-01-23 02:09:47.871508: step: 852/529, loss: 0.07254581898450851
2023-01-23 02:09:48.985343: step: 856/529, loss: 0.023009682074189186
2023-01-23 02:09:50.126924: step: 860/529, loss: 0.041849710047245026
2023-01-23 02:09:51.287910: step: 864/529, loss: 0.0442989356815815
2023-01-23 02:09:52.426681: step: 868/529, loss: 0.025445176288485527
2023-01-23 02:09:53.569732: step: 872/529, loss: 0.13881874084472656
2023-01-23 02:09:54.723141: step: 876/529, loss: 0.07557277381420135
2023-01-23 02:09:55.846551: step: 880/529, loss: 0.005017471499741077
2023-01-23 02:09:56.977110: step: 884/529, loss: 0.01241073664277792
2023-01-23 02:09:58.159132: step: 888/529, loss: 0.017607688903808594
2023-01-23 02:09:59.311540: step: 892/529, loss: 0.00048313141451217234
2023-01-23 02:10:00.462987: step: 896/529, loss: 0.05135700851678848
2023-01-23 02:10:01.580972: step: 900/529, loss: 0.005811596289277077
2023-01-23 02:10:02.766198: step: 904/529, loss: 0.0035961628891527653
2023-01-23 02:10:03.888411: step: 908/529, loss: 0.002309179399162531
2023-01-23 02:10:05.034805: step: 912/529, loss: 0.025805141776800156
2023-01-23 02:10:06.156126: step: 916/529, loss: 0.0017173767555505037
2023-01-23 02:10:07.280184: step: 920/529, loss: 0.002993965055793524
2023-01-23 02:10:08.425814: step: 924/529, loss: 0.054241180419921875
2023-01-23 02:10:09.606468: step: 928/529, loss: 0.017448045313358307
2023-01-23 02:10:10.746606: step: 932/529, loss: 0.007323741912841797
2023-01-23 02:10:11.909034: step: 936/529, loss: 0.00948710460215807
2023-01-23 02:10:13.059177: step: 940/529, loss: 0.31747865676879883
2023-01-23 02:10:14.198912: step: 944/529, loss: 0.08458757400512695
2023-01-23 02:10:15.359219: step: 948/529, loss: 0.22754301130771637
2023-01-23 02:10:16.473229: step: 952/529, loss: 0.03138537332415581
2023-01-23 02:10:17.627877: step: 956/529, loss: 0.02237720601260662
2023-01-23 02:10:18.811052: step: 960/529, loss: 0.13312724232673645
2023-01-23 02:10:19.960363: step: 964/529, loss: 0.057062432169914246
2023-01-23 02:10:21.097192: step: 968/529, loss: 0.01851635053753853
2023-01-23 02:10:22.255821: step: 972/529, loss: 0.0032947540748864412
2023-01-23 02:10:23.416079: step: 976/529, loss: 8.287429955089465e-05
2023-01-23 02:10:24.567024: step: 980/529, loss: 0.00848779734224081
2023-01-23 02:10:25.710645: step: 984/529, loss: 0.000860536121763289
2023-01-23 02:10:26.811418: step: 988/529, loss: 0.06617279350757599
2023-01-23 02:10:27.921427: step: 992/529, loss: 0.03181810677051544
2023-01-23 02:10:29.042669: step: 996/529, loss: 0.19051896035671234
2023-01-23 02:10:30.192587: step: 1000/529, loss: 0.005600929260253906
2023-01-23 02:10:31.328507: step: 1004/529, loss: 0.03881397098302841
2023-01-23 02:10:32.456360: step: 1008/529, loss: 0.04361448436975479
2023-01-23 02:10:33.560787: step: 1012/529, loss: 0.013620281592011452
2023-01-23 02:10:34.737494: step: 1016/529, loss: 0.012393188662827015
2023-01-23 02:10:35.885951: step: 1020/529, loss: 0.023893356323242188
2023-01-23 02:10:36.995653: step: 1024/529, loss: 0.006225681398063898
2023-01-23 02:10:38.139688: step: 1028/529, loss: 0.002750969026237726
2023-01-23 02:10:39.283130: step: 1032/529, loss: 0.00141735072247684
2023-01-23 02:10:40.447155: step: 1036/529, loss: 0.0636373981833458
2023-01-23 02:10:41.585707: step: 1040/529, loss: 0.0546053871512413
2023-01-23 02:10:42.710652: step: 1044/529, loss: 0.0020420073997229338
2023-01-23 02:10:43.835334: step: 1048/529, loss: 0.00898046512156725
2023-01-23 02:10:44.978462: step: 1052/529, loss: 0.004096698481589556
2023-01-23 02:10:46.093440: step: 1056/529, loss: 0.03249092027544975
2023-01-23 02:10:47.244449: step: 1060/529, loss: 0.015903044492006302
2023-01-23 02:10:48.375522: step: 1064/529, loss: 0.013583565130829811
2023-01-23 02:10:49.541961: step: 1068/529, loss: 0.06061878055334091
2023-01-23 02:10:50.685114: step: 1072/529, loss: 0.04557066038250923
2023-01-23 02:10:51.839299: step: 1076/529, loss: 0.09788218140602112
2023-01-23 02:10:52.976785: step: 1080/529, loss: 0.003725338028743863
2023-01-23 02:10:54.120034: step: 1084/529, loss: 0.007439231500029564
2023-01-23 02:10:55.283740: step: 1088/529, loss: 0.002645206404849887
2023-01-23 02:10:56.442051: step: 1092/529, loss: 0.009668922051787376
2023-01-23 02:10:57.585448: step: 1096/529, loss: 0.04261379316449165
2023-01-23 02:10:58.721976: step: 1100/529, loss: 0.10369786620140076
2023-01-23 02:10:59.866132: step: 1104/529, loss: 0.04311056062579155
2023-01-23 02:11:01.064636: step: 1108/529, loss: 0.05699528753757477
2023-01-23 02:11:02.196533: step: 1112/529, loss: 0.013989115133881569
2023-01-23 02:11:03.329040: step: 1116/529, loss: 0.008242416195571423
2023-01-23 02:11:04.492429: step: 1120/529, loss: 0.022354699671268463
2023-01-23 02:11:05.624282: step: 1124/529, loss: 0.006768512539565563
2023-01-23 02:11:06.760436: step: 1128/529, loss: 0.0567021369934082
2023-01-23 02:11:07.857131: step: 1132/529, loss: 0.008379554376006126
2023-01-23 02:11:09.012619: step: 1136/529, loss: 0.021453000605106354
2023-01-23 02:11:10.129052: step: 1140/529, loss: 0.004947090521454811
2023-01-23 02:11:11.265119: step: 1144/529, loss: 0.005310439970344305
2023-01-23 02:11:12.396823: step: 1148/529, loss: 0.01039657648652792
2023-01-23 02:11:13.550974: step: 1152/529, loss: 0.0004621505504474044
2023-01-23 02:11:14.696037: step: 1156/529, loss: 0.017467260360717773
2023-01-23 02:11:15.814176: step: 1160/529, loss: 0.0006465911865234375
2023-01-23 02:11:16.950657: step: 1164/529, loss: 0.03760728985071182
2023-01-23 02:11:18.091229: step: 1168/529, loss: 0.04383974149823189
2023-01-23 02:11:19.248288: step: 1172/529, loss: 0.027658557519316673
2023-01-23 02:11:20.377298: step: 1176/529, loss: 0.03648385778069496
2023-01-23 02:11:21.512315: step: 1180/529, loss: 0.05360241234302521
2023-01-23 02:11:22.632748: step: 1184/529, loss: 0.014761734753847122
2023-01-23 02:11:23.769666: step: 1188/529, loss: 0.015715884044766426
2023-01-23 02:11:24.901681: step: 1192/529, loss: 0.02530203014612198
2023-01-23 02:11:26.030558: step: 1196/529, loss: 0.06698932498693466
2023-01-23 02:11:27.176067: step: 1200/529, loss: 0.04981184005737305
2023-01-23 02:11:28.320199: step: 1204/529, loss: 0.005845737177878618
2023-01-23 02:11:29.453323: step: 1208/529, loss: 0.01490030251443386
2023-01-23 02:11:30.590063: step: 1212/529, loss: 0.017954446375370026
2023-01-23 02:11:31.725744: step: 1216/529, loss: 0.016650009900331497
2023-01-23 02:11:32.873847: step: 1220/529, loss: 0.030155181884765625
2023-01-23 02:11:34.009347: step: 1224/529, loss: 0.003593230154365301
2023-01-23 02:11:35.134763: step: 1228/529, loss: 0.012989449314773083
2023-01-23 02:11:36.267068: step: 1232/529, loss: 0.04081685468554497
2023-01-23 02:11:37.416119: step: 1236/529, loss: 0.0027082921005785465
2023-01-23 02:11:38.641213: step: 1240/529, loss: 0.003213500836864114
2023-01-23 02:11:39.781317: step: 1244/529, loss: 0.016209697350859642
2023-01-23 02:11:40.952568: step: 1248/529, loss: 0.03333749994635582
2023-01-23 02:11:42.101373: step: 1252/529, loss: 0.04004526138305664
2023-01-23 02:11:43.248298: step: 1256/529, loss: 0.05194530636072159
2023-01-23 02:11:44.397081: step: 1260/529, loss: 0.010418986901640892
2023-01-23 02:11:45.556985: step: 1264/529, loss: 0.0014635085826739669
2023-01-23 02:11:46.692082: step: 1268/529, loss: 0.01530599594116211
2023-01-23 02:11:47.840930: step: 1272/529, loss: 0.006389713380485773
2023-01-23 02:11:48.978062: step: 1276/529, loss: 0.18706876039505005
2023-01-23 02:11:50.110122: step: 1280/529, loss: 0.04842853546142578
2023-01-23 02:11:51.259430: step: 1284/529, loss: 0.001101589179597795
2023-01-23 02:11:52.374042: step: 1288/529, loss: 0.1895170956850052
2023-01-23 02:11:53.497440: step: 1292/529, loss: 0.004184150602668524
2023-01-23 02:11:54.621440: step: 1296/529, loss: 0.004011726006865501
2023-01-23 02:11:55.759353: step: 1300/529, loss: 0.029828930273652077
2023-01-23 02:11:56.910355: step: 1304/529, loss: 0.09407033771276474
2023-01-23 02:11:58.053609: step: 1308/529, loss: 0.0029435157775878906
2023-01-23 02:11:59.183574: step: 1312/529, loss: 0.03441968187689781
2023-01-23 02:12:00.328407: step: 1316/529, loss: 0.0010502338409423828
2023-01-23 02:12:01.480283: step: 1320/529, loss: 0.006374835968017578
2023-01-23 02:12:02.613047: step: 1324/529, loss: 0.0007005095249041915
2023-01-23 02:12:03.776320: step: 1328/529, loss: 0.01744675636291504
2023-01-23 02:12:04.882677: step: 1332/529, loss: 0.02995932474732399
2023-01-23 02:12:06.022366: step: 1336/529, loss: 0.012354278936982155
2023-01-23 02:12:07.173692: step: 1340/529, loss: 0.00022754669771529734
2023-01-23 02:12:08.335612: step: 1344/529, loss: 0.00383758544921875
2023-01-23 02:12:09.498823: step: 1348/529, loss: 0.008125782012939453
2023-01-23 02:12:10.649988: step: 1352/529, loss: 0.3304021656513214
2023-01-23 02:12:11.794544: step: 1356/529, loss: 0.02353649027645588
2023-01-23 02:12:12.939604: step: 1360/529, loss: 0.04986514896154404
2023-01-23 02:12:14.081340: step: 1364/529, loss: 0.0038272857200354338
2023-01-23 02:12:15.228708: step: 1368/529, loss: 0.0012815475929528475
2023-01-23 02:12:16.412065: step: 1372/529, loss: 0.0014628410572186112
2023-01-23 02:12:17.549680: step: 1376/529, loss: 0.0026388170663267374
2023-01-23 02:12:18.702915: step: 1380/529, loss: 0.052590563893318176
2023-01-23 02:12:19.839684: step: 1384/529, loss: 0.003288173582404852
2023-01-23 02:12:20.985665: step: 1388/529, loss: 0.01676187478005886
2023-01-23 02:12:22.121523: step: 1392/529, loss: 0.04448271170258522
2023-01-23 02:12:23.276425: step: 1396/529, loss: 0.0007320403819903731
2023-01-23 02:12:24.381964: step: 1400/529, loss: 7.095337059581652e-05
2023-01-23 02:12:25.525596: step: 1404/529, loss: 0.016016578301787376
2023-01-23 02:12:26.671898: step: 1408/529, loss: 0.0011569024063646793
2023-01-23 02:12:27.799883: step: 1412/529, loss: 0.031043626368045807
2023-01-23 02:12:28.924760: step: 1416/529, loss: 0.05520286783576012
2023-01-23 02:12:30.059284: step: 1420/529, loss: 0.022416209802031517
2023-01-23 02:12:31.229917: step: 1424/529, loss: 0.0023966075386852026
2023-01-23 02:12:32.383866: step: 1428/529, loss: 0.0006723403930664062
2023-01-23 02:12:33.533822: step: 1432/529, loss: 0.02556753344833851
2023-01-23 02:12:34.686836: step: 1436/529, loss: 0.00012383461580611765
2023-01-23 02:12:35.821174: step: 1440/529, loss: 0.06725616753101349
2023-01-23 02:12:36.962983: step: 1444/529, loss: 0.08004990220069885
2023-01-23 02:12:38.086903: step: 1448/529, loss: 0.006039905361831188
2023-01-23 02:12:39.247808: step: 1452/529, loss: 0.022419167682528496
2023-01-23 02:12:40.426732: step: 1456/529, loss: 0.008258628658950329
2023-01-23 02:12:41.577233: step: 1460/529, loss: 0.013870335184037685
2023-01-23 02:12:42.732801: step: 1464/529, loss: 0.036595914512872696
2023-01-23 02:12:43.938138: step: 1468/529, loss: 0.005097007844597101
2023-01-23 02:12:45.080209: step: 1472/529, loss: 0.010624503716826439
2023-01-23 02:12:46.224467: step: 1476/529, loss: 0.0012076377170160413
2023-01-23 02:12:47.385414: step: 1480/529, loss: 0.019147682934999466
2023-01-23 02:12:48.517029: step: 1484/529, loss: 0.050473593175411224
2023-01-23 02:12:49.647422: step: 1488/529, loss: 0.0036925317253917456
2023-01-23 02:12:50.754993: step: 1492/529, loss: 0.012013006024062634
2023-01-23 02:12:51.946752: step: 1496/529, loss: 0.04311714321374893
2023-01-23 02:12:53.093175: step: 1500/529, loss: 0.0006580352783203125
2023-01-23 02:12:54.244166: step: 1504/529, loss: 0.043698880821466446
2023-01-23 02:12:55.376459: step: 1508/529, loss: 0.013142204843461514
2023-01-23 02:12:56.540632: step: 1512/529, loss: 0.07252349704504013
2023-01-23 02:12:57.650888: step: 1516/529, loss: 0.04689350351691246
2023-01-23 02:12:58.807788: step: 1520/529, loss: 0.049704551696777344
2023-01-23 02:12:59.946633: step: 1524/529, loss: 0.002729797502979636
2023-01-23 02:13:01.091707: step: 1528/529, loss: 0.021985625848174095
2023-01-23 02:13:02.244846: step: 1532/529, loss: 0.040839388966560364
2023-01-23 02:13:03.411155: step: 1536/529, loss: 0.019243812188506126
2023-01-23 02:13:04.573938: step: 1540/529, loss: 0.03152446821331978
2023-01-23 02:13:05.734527: step: 1544/529, loss: 0.08307524025440216
2023-01-23 02:13:06.866670: step: 1548/529, loss: 0.057274628430604935
2023-01-23 02:13:08.033514: step: 1552/529, loss: 0.027982329949736595
2023-01-23 02:13:09.174814: step: 1556/529, loss: 0.020365620031952858
2023-01-23 02:13:10.319800: step: 1560/529, loss: 0.058455564081668854
2023-01-23 02:13:11.471790: step: 1564/529, loss: 0.015607072040438652
2023-01-23 02:13:12.597370: step: 1568/529, loss: 0.02716102823615074
2023-01-23 02:13:13.746177: step: 1572/529, loss: 0.0123648876324296
2023-01-23 02:13:14.880180: step: 1576/529, loss: 0.011349297128617764
2023-01-23 02:13:16.022971: step: 1580/529, loss: 0.014312363229691982
2023-01-23 02:13:17.174673: step: 1584/529, loss: 0.019231844693422318
2023-01-23 02:13:18.319338: step: 1588/529, loss: 0.0054531097412109375
2023-01-23 02:13:19.425114: step: 1592/529, loss: 0.07473921775817871
2023-01-23 02:13:20.578259: step: 1596/529, loss: 0.029568098485469818
2023-01-23 02:13:21.763421: step: 1600/529, loss: 0.016063785180449486
2023-01-23 02:13:22.893591: step: 1604/529, loss: 0.017739344388246536
2023-01-23 02:13:24.041224: step: 1608/529, loss: 0.028479887172579765
2023-01-23 02:13:25.186689: step: 1612/529, loss: 0.01737537421286106
2023-01-23 02:13:26.325418: step: 1616/529, loss: 0.06229591369628906
2023-01-23 02:13:27.467951: step: 1620/529, loss: 0.009745597839355469
2023-01-23 02:13:28.620988: step: 1624/529, loss: 0.037886809557676315
2023-01-23 02:13:29.781518: step: 1628/529, loss: 0.021085739135742188
2023-01-23 02:13:30.929471: step: 1632/529, loss: 0.062497518956661224
2023-01-23 02:13:32.095990: step: 1636/529, loss: 0.0496278777718544
2023-01-23 02:13:33.231179: step: 1640/529, loss: 0.026555635035037994
2023-01-23 02:13:34.354969: step: 1644/529, loss: 0.016200972720980644
2023-01-23 02:13:35.516730: step: 1648/529, loss: 0.009702110663056374
2023-01-23 02:13:36.642925: step: 1652/529, loss: 0.024866199120879173
2023-01-23 02:13:37.773046: step: 1656/529, loss: 0.00010375976853538305
2023-01-23 02:13:38.915491: step: 1660/529, loss: 0.02479419857263565
2023-01-23 02:13:40.057287: step: 1664/529, loss: 0.005896473303437233
2023-01-23 02:13:41.177617: step: 1668/529, loss: 0.004992770962417126
2023-01-23 02:13:42.311965: step: 1672/529, loss: 0.0034923553466796875
2023-01-23 02:13:43.482965: step: 1676/529, loss: 0.03645153343677521
2023-01-23 02:13:44.626798: step: 1680/529, loss: 0.12226153165102005
2023-01-23 02:13:45.764813: step: 1684/529, loss: 0.004172611515969038
2023-01-23 02:13:46.931711: step: 1688/529, loss: 0.11449889838695526
2023-01-23 02:13:48.059659: step: 1692/529, loss: 0.04302450641989708
2023-01-23 02:13:49.225787: step: 1696/529, loss: 0.016445159912109375
2023-01-23 02:13:50.366302: step: 1700/529, loss: 0.01430602092295885
2023-01-23 02:13:51.557832: step: 1704/529, loss: 0.022727251052856445
2023-01-23 02:13:52.705997: step: 1708/529, loss: 0.0005927563179284334
2023-01-23 02:13:53.838092: step: 1712/529, loss: 0.06709681451320648
2023-01-23 02:13:54.993688: step: 1716/529, loss: 0.08925037086009979
2023-01-23 02:13:56.137930: step: 1720/529, loss: 0.010358238592743874
2023-01-23 02:13:57.246612: step: 1724/529, loss: 0.0007161140674725175
2023-01-23 02:13:58.426268: step: 1728/529, loss: 0.018272781744599342
2023-01-23 02:13:59.560582: step: 1732/529, loss: 0.0007228851318359375
2023-01-23 02:14:00.743780: step: 1736/529, loss: 0.037283290177583694
2023-01-23 02:14:01.885020: step: 1740/529, loss: 0.00985937099903822
2023-01-23 02:14:03.009858: step: 1744/529, loss: 0.019458914175629616
2023-01-23 02:14:04.124979: step: 1748/529, loss: 0.0015424728626385331
2023-01-23 02:14:05.262028: step: 1752/529, loss: 0.03205299377441406
2023-01-23 02:14:06.395646: step: 1756/529, loss: 0.040040016174316406
2023-01-23 02:14:07.516140: step: 1760/529, loss: 0.12323351204395294
2023-01-23 02:14:08.649042: step: 1764/529, loss: 0.019593574106693268
2023-01-23 02:14:09.772547: step: 1768/529, loss: 0.04877519607543945
2023-01-23 02:14:10.913183: step: 1772/529, loss: 0.0030515671242028475
2023-01-23 02:14:12.034718: step: 1776/529, loss: 0.2574901878833771
2023-01-23 02:14:13.170672: step: 1780/529, loss: 0.004457664210349321
2023-01-23 02:14:14.325353: step: 1784/529, loss: 0.038317110389471054
2023-01-23 02:14:15.478536: step: 1788/529, loss: 0.007608700077980757
2023-01-23 02:14:16.617696: step: 1792/529, loss: 0.009356451220810413
2023-01-23 02:14:17.770273: step: 1796/529, loss: 0.014154816046357155
2023-01-23 02:14:18.910515: step: 1800/529, loss: 0.003493881318718195
2023-01-23 02:14:20.056393: step: 1804/529, loss: 0.018837666139006615
2023-01-23 02:14:21.203098: step: 1808/529, loss: 0.004622268490493298
2023-01-23 02:14:22.321773: step: 1812/529, loss: 0.006932544521987438
2023-01-23 02:14:23.426400: step: 1816/529, loss: 0.020758438855409622
2023-01-23 02:14:24.562274: step: 1820/529, loss: 0.0020929337479174137
2023-01-23 02:14:25.685826: step: 1824/529, loss: 0.006173992529511452
2023-01-23 02:14:26.833621: step: 1828/529, loss: 0.0010514259338378906
2023-01-23 02:14:27.961428: step: 1832/529, loss: 0.0023732902482151985
2023-01-23 02:14:29.099932: step: 1836/529, loss: 0.007515525911003351
2023-01-23 02:14:30.210963: step: 1840/529, loss: 0.06514782458543777
2023-01-23 02:14:31.348367: step: 1844/529, loss: 0.03289084881544113
2023-01-23 02:14:32.467834: step: 1848/529, loss: 0.01877593994140625
2023-01-23 02:14:33.595400: step: 1852/529, loss: 0.011627770029008389
2023-01-23 02:14:34.733059: step: 1856/529, loss: 0.0002834320184774697
2023-01-23 02:14:35.880189: step: 1860/529, loss: 0.05669088289141655
2023-01-23 02:14:37.020178: step: 1864/529, loss: 0.023387527093291283
2023-01-23 02:14:38.142166: step: 1868/529, loss: 0.059326935559511185
2023-01-23 02:14:39.281713: step: 1872/529, loss: 0.0014371873112395406
2023-01-23 02:14:40.401851: step: 1876/529, loss: 0.005904007237404585
2023-01-23 02:14:41.542009: step: 1880/529, loss: 0.010495376773178577
2023-01-23 02:14:42.726939: step: 1884/529, loss: 0.02429637871682644
2023-01-23 02:14:43.894932: step: 1888/529, loss: 0.030131960287690163
2023-01-23 02:14:45.052926: step: 1892/529, loss: 0.11261577904224396
2023-01-23 02:14:46.199347: step: 1896/529, loss: 0.13868561387062073
2023-01-23 02:14:47.338524: step: 1900/529, loss: 0.05415001139044762
2023-01-23 02:14:48.476208: step: 1904/529, loss: 0.05102949216961861
2023-01-23 02:14:49.607384: step: 1908/529, loss: 0.024415969848632812
2023-01-23 02:14:50.760558: step: 1912/529, loss: 0.03174114227294922
2023-01-23 02:14:51.903507: step: 1916/529, loss: 0.004187393467873335
2023-01-23 02:14:53.016358: step: 1920/529, loss: 0.028246738016605377
2023-01-23 02:14:54.159645: step: 1924/529, loss: 0.0053529744036495686
2023-01-23 02:14:55.285713: step: 1928/529, loss: 0.0418216697871685
2023-01-23 02:14:56.448879: step: 1932/529, loss: 0.030275821685791016
2023-01-23 02:14:57.589701: step: 1936/529, loss: 0.0005325317615643144
2023-01-23 02:14:58.763421: step: 1940/529, loss: 0.00972747802734375
2023-01-23 02:14:59.914010: step: 1944/529, loss: 0.020929764956235886
2023-01-23 02:15:01.068738: step: 1948/529, loss: 0.6107298135757446
2023-01-23 02:15:02.210485: step: 1952/529, loss: 0.0022125244140625
2023-01-23 02:15:03.353693: step: 1956/529, loss: 0.06037025526165962
2023-01-23 02:15:04.490563: step: 1960/529, loss: 0.20495624840259552
2023-01-23 02:15:05.626126: step: 1964/529, loss: 0.06659393012523651
2023-01-23 02:15:06.742907: step: 1968/529, loss: 0.015048789791762829
2023-01-23 02:15:07.885078: step: 1972/529, loss: 0.05694231390953064
2023-01-23 02:15:09.044735: step: 1976/529, loss: 0.05497036129236221
2023-01-23 02:15:10.193899: step: 1980/529, loss: 0.013063526712357998
2023-01-23 02:15:11.316327: step: 1984/529, loss: 0.014065265655517578
2023-01-23 02:15:12.468374: step: 1988/529, loss: 0.030993271619081497
2023-01-23 02:15:13.648721: step: 1992/529, loss: 0.006761837285012007
2023-01-23 02:15:14.795128: step: 1996/529, loss: 0.0004570961173158139
2023-01-23 02:15:15.923780: step: 2000/529, loss: 0.0019927024841308594
2023-01-23 02:15:17.045912: step: 2004/529, loss: 0.01276693306863308
2023-01-23 02:15:18.181579: step: 2008/529, loss: 0.036294981837272644
2023-01-23 02:15:19.362995: step: 2012/529, loss: 0.07033786177635193
2023-01-23 02:15:20.509635: step: 2016/529, loss: 0.004414939787238836
2023-01-23 02:15:21.640731: step: 2020/529, loss: 0.0027147294022142887
2023-01-23 02:15:22.785400: step: 2024/529, loss: 0.04505958408117294
2023-01-23 02:15:23.941983: step: 2028/529, loss: 0.022596361115574837
2023-01-23 02:15:25.108759: step: 2032/529, loss: 0.013995361514389515
2023-01-23 02:15:26.228199: step: 2036/529, loss: 0.0021209716796875
2023-01-23 02:15:27.388489: step: 2040/529, loss: 0.030959319323301315
2023-01-23 02:15:28.535488: step: 2044/529, loss: 0.0828220322728157
2023-01-23 02:15:29.675072: step: 2048/529, loss: 0.01774454116821289
2023-01-23 02:15:30.845304: step: 2052/529, loss: 0.21185509860515594
2023-01-23 02:15:32.004550: step: 2056/529, loss: 0.018067264929413795
2023-01-23 02:15:33.129490: step: 2060/529, loss: 0.014842080883681774
2023-01-23 02:15:34.268715: step: 2064/529, loss: 0.0048958780243992805
2023-01-23 02:15:35.400791: step: 2068/529, loss: 0.04531888663768768
2023-01-23 02:15:36.522663: step: 2072/529, loss: 0.040624428540468216
2023-01-23 02:15:37.676355: step: 2076/529, loss: 0.035187624394893646
2023-01-23 02:15:38.823324: step: 2080/529, loss: 0.023624802008271217
2023-01-23 02:15:39.958383: step: 2084/529, loss: 0.00090875627938658
2023-01-23 02:15:41.115246: step: 2088/529, loss: 0.08014983683824539
2023-01-23 02:15:42.236542: step: 2092/529, loss: 0.03574104607105255
2023-01-23 02:15:43.375816: step: 2096/529, loss: 0.0019851685501635075
2023-01-23 02:15:44.506119: step: 2100/529, loss: 0.027103662490844727
2023-01-23 02:15:45.646757: step: 2104/529, loss: 0.007000541780143976
2023-01-23 02:15:46.779922: step: 2108/529, loss: 0.008797550573945045
2023-01-23 02:15:47.901304: step: 2112/529, loss: 0.00836801528930664
2023-01-23 02:15:49.039465: step: 2116/529, loss: 0.013452769257128239
==================================================
Loss: 0.038
--------------------
Dev: {'event': {'p': 0.6070686070686071, 'r': 0.7776298268974701, 'f1': 0.6818447168709866}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.613290263036456, 'r': 0.7699884125144844, 'f1': 0.6827639352684306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5813953488372093, 'r': 0.9259259259259259, 'f1': 0.7142857142857142}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.578125, 'r': 0.5873015873015873, 'f1': 0.5826771653543307}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4358974358974359, 'r': 0.4722222222222222, 'f1': 0.45333333333333337}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:16:30.548519: step: 4/529, loss: 0.001281786011531949
2023-01-23 02:16:31.668669: step: 8/529, loss: 0.0014184952015057206
2023-01-23 02:16:32.788638: step: 12/529, loss: 0.02671823650598526
2023-01-23 02:16:33.902957: step: 16/529, loss: 0.002808952471241355
2023-01-23 02:16:35.024524: step: 20/529, loss: 0.0007003784412518144
2023-01-23 02:16:36.140137: step: 24/529, loss: 0.006023192312568426
2023-01-23 02:16:37.316972: step: 28/529, loss: 0.055132679641246796
2023-01-23 02:16:38.455688: step: 32/529, loss: 0.029755974188447
2023-01-23 02:16:39.599458: step: 36/529, loss: 0.02724306657910347
2023-01-23 02:16:40.717400: step: 40/529, loss: 0.29437941312789917
2023-01-23 02:16:41.832429: step: 44/529, loss: 0.05317831039428711
2023-01-23 02:16:42.977922: step: 48/529, loss: 0.014949607662856579
2023-01-23 02:16:44.104855: step: 52/529, loss: 0.037228774279356
2023-01-23 02:16:45.245854: step: 56/529, loss: 0.027472306042909622
2023-01-23 02:16:46.355113: step: 60/529, loss: 0.05710430070757866
2023-01-23 02:16:47.512309: step: 64/529, loss: 0.05984363704919815
2023-01-23 02:16:48.621268: step: 68/529, loss: 0.818611204624176
2023-01-23 02:16:49.741362: step: 72/529, loss: 0.012174416333436966
2023-01-23 02:16:50.875594: step: 76/529, loss: 0.010378837585449219
2023-01-23 02:16:52.044075: step: 80/529, loss: 0.015028666704893112
2023-01-23 02:16:53.157024: step: 84/529, loss: 0.04272763803601265
2023-01-23 02:16:54.285845: step: 88/529, loss: 0.020542336627840996
2023-01-23 02:16:55.431575: step: 92/529, loss: 0.002444410463795066
2023-01-23 02:16:56.585571: step: 96/529, loss: 0.03330212086439133
2023-01-23 02:16:57.706576: step: 100/529, loss: 0.029061317443847656
2023-01-23 02:16:58.826678: step: 104/529, loss: 0.01877441443502903
2023-01-23 02:16:59.945941: step: 108/529, loss: 0.017064666375517845
2023-01-23 02:17:01.096353: step: 112/529, loss: 0.005825853440910578
2023-01-23 02:17:02.229815: step: 116/529, loss: 0.010346747003495693
2023-01-23 02:17:03.368538: step: 120/529, loss: 0.017881011590361595
2023-01-23 02:17:04.506378: step: 124/529, loss: 0.013179779052734375
2023-01-23 02:17:05.639655: step: 128/529, loss: 0.0008934021461755037
2023-01-23 02:17:06.787694: step: 132/529, loss: 0.008393668569624424
2023-01-23 02:17:07.943711: step: 136/529, loss: 0.020969772711396217
2023-01-23 02:17:09.088432: step: 140/529, loss: 0.0016659736866131425
2023-01-23 02:17:10.244277: step: 144/529, loss: 0.04127998277544975
2023-01-23 02:17:11.396138: step: 148/529, loss: 0.015370846726000309
2023-01-23 02:17:12.544016: step: 152/529, loss: 0.005079889204353094
2023-01-23 02:17:13.699289: step: 156/529, loss: 0.0354466438293457
2023-01-23 02:17:14.847476: step: 160/529, loss: 0.015561294741928577
2023-01-23 02:17:15.964166: step: 164/529, loss: 0.019716214388608932
2023-01-23 02:17:17.076670: step: 168/529, loss: 0.039950087666511536
2023-01-23 02:17:18.260519: step: 172/529, loss: 0.0864294022321701
2023-01-23 02:17:19.413179: step: 176/529, loss: 0.01704864576458931
2023-01-23 02:17:20.553676: step: 180/529, loss: 0.0011204719776287675
2023-01-23 02:17:21.674040: step: 184/529, loss: 0.022375011816620827
2023-01-23 02:17:22.818069: step: 188/529, loss: 0.023101806640625
2023-01-23 02:17:23.985687: step: 192/529, loss: 0.013962794095277786
2023-01-23 02:17:25.138758: step: 196/529, loss: 0.0011806488037109375
2023-01-23 02:17:26.276898: step: 200/529, loss: 0.00344600691460073
2023-01-23 02:17:27.398203: step: 204/529, loss: 0.019872188568115234
2023-01-23 02:17:28.525779: step: 208/529, loss: 0.040847018361091614
2023-01-23 02:17:29.679759: step: 212/529, loss: 0.031068801879882812
2023-01-23 02:17:30.837128: step: 216/529, loss: 0.2228774130344391
2023-01-23 02:17:32.010468: step: 220/529, loss: 0.0023597716353833675
2023-01-23 02:17:33.159682: step: 224/529, loss: 0.049439672380685806
2023-01-23 02:17:34.277236: step: 228/529, loss: 0.12172757089138031
2023-01-23 02:17:35.451334: step: 232/529, loss: 0.0013475418090820312
2023-01-23 02:17:36.564631: step: 236/529, loss: 0.0004077911435160786
2023-01-23 02:17:37.730594: step: 240/529, loss: 0.0029257775750011206
2023-01-23 02:17:38.890693: step: 244/529, loss: 0.0007245540618896484
2023-01-23 02:17:40.041488: step: 248/529, loss: 0.027238082140684128
2023-01-23 02:17:41.162168: step: 252/529, loss: 0.017442703247070312
2023-01-23 02:17:42.316496: step: 256/529, loss: 0.0006719589000567794
2023-01-23 02:17:43.459378: step: 260/529, loss: 0.0037513733841478825
2023-01-23 02:17:44.573016: step: 264/529, loss: 0.0024683952797204256
2023-01-23 02:17:45.750473: step: 268/529, loss: 0.0041824341751635075
2023-01-23 02:17:46.875106: step: 272/529, loss: 0.05124969780445099
2023-01-23 02:17:48.013109: step: 276/529, loss: 0.03738613426685333
2023-01-23 02:17:49.179623: step: 280/529, loss: 0.20684003829956055
2023-01-23 02:17:50.304832: step: 284/529, loss: 0.01148614939302206
2023-01-23 02:17:51.427314: step: 288/529, loss: 0.007374573033303022
2023-01-23 02:17:52.558855: step: 292/529, loss: 0.0002853400947060436
2023-01-23 02:17:53.707132: step: 296/529, loss: 0.010897351428866386
2023-01-23 02:17:54.852505: step: 300/529, loss: 0.004628848750144243
2023-01-23 02:17:55.981313: step: 304/529, loss: 0.030051900073885918
2023-01-23 02:17:57.101322: step: 308/529, loss: 0.03163433074951172
2023-01-23 02:17:58.256720: step: 312/529, loss: 0.0016204833518713713
2023-01-23 02:17:59.439804: step: 316/529, loss: 0.0462338924407959
2023-01-23 02:18:00.578589: step: 320/529, loss: 0.007203841581940651
2023-01-23 02:18:01.734492: step: 324/529, loss: 0.027962829917669296
2023-01-23 02:18:02.869766: step: 328/529, loss: 0.025838088244199753
2023-01-23 02:18:04.017621: step: 332/529, loss: 0.0007618904346600175
2023-01-23 02:18:05.154215: step: 336/529, loss: 0.02007732354104519
2023-01-23 02:18:06.307028: step: 340/529, loss: 0.010866357013583183
2023-01-23 02:18:07.461748: step: 344/529, loss: 0.021649742498993874
2023-01-23 02:18:08.598819: step: 348/529, loss: 0.1568128615617752
2023-01-23 02:18:09.746971: step: 352/529, loss: 0.007755470462143421
2023-01-23 02:18:10.897702: step: 356/529, loss: 0.01465530414134264
2023-01-23 02:18:12.046231: step: 360/529, loss: 0.003658866975456476
2023-01-23 02:18:13.203753: step: 364/529, loss: 0.03625817596912384
2023-01-23 02:18:14.348795: step: 368/529, loss: 0.010960579849779606
2023-01-23 02:18:15.517108: step: 372/529, loss: 0.10849571228027344
2023-01-23 02:18:16.657445: step: 376/529, loss: 0.01132059097290039
2023-01-23 02:18:17.775373: step: 380/529, loss: 0.015038777142763138
2023-01-23 02:18:18.920678: step: 384/529, loss: 0.01786346361041069
2023-01-23 02:18:20.037890: step: 388/529, loss: 0.15416479110717773
2023-01-23 02:18:21.188177: step: 392/529, loss: 0.004218196962028742
2023-01-23 02:18:22.346492: step: 396/529, loss: 0.006312168203294277
2023-01-23 02:18:23.474573: step: 400/529, loss: 0.05187266319990158
2023-01-23 02:18:24.620411: step: 404/529, loss: 0.02471904829144478
2023-01-23 02:18:25.747052: step: 408/529, loss: 0.024489115923643112
2023-01-23 02:18:26.893376: step: 412/529, loss: 0.03293609619140625
2023-01-23 02:18:28.008583: step: 416/529, loss: 0.06496404111385345
2023-01-23 02:18:29.139339: step: 420/529, loss: 0.05026718229055405
2023-01-23 02:18:30.258079: step: 424/529, loss: 0.007446670439094305
2023-01-23 02:18:31.413284: step: 428/529, loss: 0.0482393279671669
2023-01-23 02:18:32.543307: step: 432/529, loss: 0.00011339187767589465
2023-01-23 02:18:33.709422: step: 436/529, loss: 0.016169849783182144
2023-01-23 02:18:34.839082: step: 440/529, loss: 0.0003383636358194053
2023-01-23 02:18:35.978163: step: 444/529, loss: 0.012859517708420753
2023-01-23 02:18:37.131550: step: 448/529, loss: 0.019469834864139557
2023-01-23 02:18:38.276498: step: 452/529, loss: 0.03647594526410103
2023-01-23 02:18:39.393301: step: 456/529, loss: 0.028537657111883163
2023-01-23 02:18:40.541059: step: 460/529, loss: 0.01862783543765545
2023-01-23 02:18:41.659434: step: 464/529, loss: 0.02925877645611763
2023-01-23 02:18:42.794550: step: 468/529, loss: 0.0005485534784384072
2023-01-23 02:18:43.939805: step: 472/529, loss: 0.014030457474291325
2023-01-23 02:18:45.075501: step: 476/529, loss: 0.045073606073856354
2023-01-23 02:18:46.219817: step: 480/529, loss: 0.010161971673369408
2023-01-23 02:18:47.384460: step: 484/529, loss: 2.371072696405463e-05
2023-01-23 02:18:48.523742: step: 488/529, loss: 0.017067719250917435
2023-01-23 02:18:49.628770: step: 492/529, loss: 0.027418233454227448
2023-01-23 02:18:50.771922: step: 496/529, loss: 0.009294891729950905
2023-01-23 02:18:51.887919: step: 500/529, loss: 0.005720901302993298
2023-01-23 02:18:53.042537: step: 504/529, loss: 0.0652192085981369
2023-01-23 02:18:54.203800: step: 508/529, loss: 0.10440702736377716
2023-01-23 02:18:55.377355: step: 512/529, loss: 0.04993128776550293
2023-01-23 02:18:56.551158: step: 516/529, loss: 0.006574440281838179
2023-01-23 02:18:57.698944: step: 520/529, loss: 0.002021408174186945
2023-01-23 02:18:58.813486: step: 524/529, loss: 0.01113739050924778
2023-01-23 02:18:59.971866: step: 528/529, loss: 0.023603392764925957
2023-01-23 02:19:01.106120: step: 532/529, loss: 0.02385425753891468
2023-01-23 02:19:02.211981: step: 536/529, loss: 0.03247556835412979
2023-01-23 02:19:03.359335: step: 540/529, loss: 0.03999767452478409
2023-01-23 02:19:04.511177: step: 544/529, loss: 0.09994792938232422
2023-01-23 02:19:05.664179: step: 548/529, loss: 0.015366173349320889
2023-01-23 02:19:06.793389: step: 552/529, loss: 0.0015928269131109118
2023-01-23 02:19:07.926169: step: 556/529, loss: 0.016782188788056374
2023-01-23 02:19:09.060055: step: 560/529, loss: 0.00019073486328125
2023-01-23 02:19:10.186576: step: 564/529, loss: 0.015441703610122204
2023-01-23 02:19:11.343292: step: 568/529, loss: 0.02672004885971546
2023-01-23 02:19:12.463385: step: 572/529, loss: 7.219314284157008e-05
2023-01-23 02:19:13.554416: step: 576/529, loss: 0.01328277587890625
2023-01-23 02:19:14.690545: step: 580/529, loss: 0.010341835208237171
2023-01-23 02:19:15.830665: step: 584/529, loss: 0.011991810984909534
2023-01-23 02:19:16.984373: step: 588/529, loss: 0.009359002113342285
2023-01-23 02:19:18.117807: step: 592/529, loss: 0.06405448913574219
2023-01-23 02:19:19.268175: step: 596/529, loss: 0.011866187676787376
2023-01-23 02:19:20.410137: step: 600/529, loss: 0.004872036166489124
2023-01-23 02:19:21.505508: step: 604/529, loss: 0.0012449742062017322
2023-01-23 02:19:22.626540: step: 608/529, loss: 0.010881043039262295
2023-01-23 02:19:23.785740: step: 612/529, loss: 0.04543018713593483
2023-01-23 02:19:24.935910: step: 616/529, loss: 0.031232308596372604
2023-01-23 02:19:26.099141: step: 620/529, loss: 0.011626816354691982
2023-01-23 02:19:27.241154: step: 624/529, loss: 6.079673767089844e-05
2023-01-23 02:19:28.402672: step: 628/529, loss: 0.01129298284649849
2023-01-23 02:19:29.540140: step: 632/529, loss: 0.06663388758897781
2023-01-23 02:19:30.693733: step: 636/529, loss: 0.002163791796192527
2023-01-23 02:19:31.839372: step: 640/529, loss: 0.023525238037109375
2023-01-23 02:19:32.954845: step: 644/529, loss: 0.003359127091243863
2023-01-23 02:19:34.095713: step: 648/529, loss: 0.0018508911598473787
2023-01-23 02:19:35.222037: step: 652/529, loss: 0.00677757291123271
2023-01-23 02:19:36.348233: step: 656/529, loss: 0.0023449896834790707
2023-01-23 02:19:37.478902: step: 660/529, loss: 0.0024999617598950863
2023-01-23 02:19:38.607969: step: 664/529, loss: 0.003799057099968195
2023-01-23 02:19:39.757818: step: 668/529, loss: 0.01631317101418972
2023-01-23 02:19:40.928679: step: 672/529, loss: 0.023102665320038795
2023-01-23 02:19:42.067325: step: 676/529, loss: 0.0014797747135162354
2023-01-23 02:19:43.198248: step: 680/529, loss: 0.0326116569340229
2023-01-23 02:19:44.391873: step: 684/529, loss: 0.005245017819106579
2023-01-23 02:19:45.524885: step: 688/529, loss: 0.011355400085449219
2023-01-23 02:19:46.655563: step: 692/529, loss: 0.010459757409989834
2023-01-23 02:19:47.792330: step: 696/529, loss: 0.006140995305031538
2023-01-23 02:19:48.922831: step: 700/529, loss: 0.0497777946293354
2023-01-23 02:19:50.060926: step: 704/529, loss: 0.057834457606077194
2023-01-23 02:19:51.203911: step: 708/529, loss: 0.04412546381354332
2023-01-23 02:19:52.342878: step: 712/529, loss: 0.022747039794921875
2023-01-23 02:19:53.525321: step: 716/529, loss: 0.05197286605834961
2023-01-23 02:19:54.648903: step: 720/529, loss: 0.006995964329689741
2023-01-23 02:19:55.786845: step: 724/529, loss: 0.011628532782196999
2023-01-23 02:19:56.940135: step: 728/529, loss: 0.0024467469193041325
2023-01-23 02:19:58.063189: step: 732/529, loss: 0.012562013231217861
2023-01-23 02:19:59.183382: step: 736/529, loss: 0.03850231319665909
2023-01-23 02:20:00.320181: step: 740/529, loss: 0.019614219665527344
2023-01-23 02:20:01.439415: step: 744/529, loss: 0.0022322656586766243
2023-01-23 02:20:02.586645: step: 748/529, loss: 0.05734901875257492
2023-01-23 02:20:03.719873: step: 752/529, loss: 0.0025336265098303556
2023-01-23 02:20:04.880637: step: 756/529, loss: 0.041613198816776276
2023-01-23 02:20:06.041473: step: 760/529, loss: 0.002742481417953968
2023-01-23 02:20:07.160675: step: 764/529, loss: 0.04124489054083824
2023-01-23 02:20:08.272525: step: 768/529, loss: 0.013933181762695312
2023-01-23 02:20:09.412202: step: 772/529, loss: 0.12521381676197052
2023-01-23 02:20:10.540432: step: 776/529, loss: 0.029155541211366653
2023-01-23 02:20:11.692309: step: 780/529, loss: 0.15854930877685547
2023-01-23 02:20:12.885960: step: 784/529, loss: 0.04188594967126846
2023-01-23 02:20:14.014894: step: 788/529, loss: 0.011525154113769531
2023-01-23 02:20:15.183969: step: 792/529, loss: 0.007031917572021484
2023-01-23 02:20:16.308024: step: 796/529, loss: 0.016255665570497513
2023-01-23 02:20:17.446758: step: 800/529, loss: 0.021538352593779564
2023-01-23 02:20:18.617180: step: 804/529, loss: 0.014235210604965687
2023-01-23 02:20:19.754152: step: 808/529, loss: 0.0015422821743413806
2023-01-23 02:20:20.906973: step: 812/529, loss: 0.0009525298955850303
2023-01-23 02:20:22.050058: step: 816/529, loss: 0.014393424615263939
2023-01-23 02:20:23.167507: step: 820/529, loss: 0.025265691801905632
2023-01-23 02:20:24.299735: step: 824/529, loss: 0.014307593926787376
2023-01-23 02:20:25.445628: step: 828/529, loss: 0.040863037109375
2023-01-23 02:20:26.573365: step: 832/529, loss: 0.06160621717572212
2023-01-23 02:20:27.760754: step: 836/529, loss: 0.039519503712654114
2023-01-23 02:20:28.882467: step: 840/529, loss: 0.04864306375384331
2023-01-23 02:20:29.992893: step: 844/529, loss: 0.006793022155761719
2023-01-23 02:20:31.143044: step: 848/529, loss: 0.028392599895596504
2023-01-23 02:20:32.299492: step: 852/529, loss: 0.04839162901043892
2023-01-23 02:20:33.428456: step: 856/529, loss: 0.025597859174013138
2023-01-23 02:20:34.590135: step: 860/529, loss: 0.011329174041748047
2023-01-23 02:20:35.733508: step: 864/529, loss: 0.05792341008782387
2023-01-23 02:20:36.894982: step: 868/529, loss: 0.0001806020736694336
2023-01-23 02:20:38.012694: step: 872/529, loss: 0.00564651470631361
2023-01-23 02:20:39.165890: step: 876/529, loss: 0.0024355887435376644
2023-01-23 02:20:40.280942: step: 880/529, loss: 0.003887748811393976
2023-01-23 02:20:41.405664: step: 884/529, loss: 0.041213274002075195
2023-01-23 02:20:42.512576: step: 888/529, loss: 0.0001218795805471018
2023-01-23 02:20:43.643542: step: 892/529, loss: 0.02173767238855362
2023-01-23 02:20:44.785829: step: 896/529, loss: 0.00775833148509264
2023-01-23 02:20:45.940893: step: 900/529, loss: 0.01319589652121067
2023-01-23 02:20:47.073120: step: 904/529, loss: 0.08747310936450958
2023-01-23 02:20:48.209061: step: 908/529, loss: 0.04705953598022461
2023-01-23 02:20:49.318150: step: 912/529, loss: 0.00038928986759856343
2023-01-23 02:20:50.458135: step: 916/529, loss: 0.0011153221130371094
2023-01-23 02:20:51.643568: step: 920/529, loss: 0.02843475341796875
2023-01-23 02:20:52.781811: step: 924/529, loss: 0.0027133941184729338
2023-01-23 02:20:53.929160: step: 928/529, loss: 0.003977918531745672
2023-01-23 02:20:55.035693: step: 932/529, loss: 0.014071177691221237
2023-01-23 02:20:56.191584: step: 936/529, loss: 0.00036373137845657766
2023-01-23 02:20:57.332291: step: 940/529, loss: 0.07526607811450958
2023-01-23 02:20:58.504107: step: 944/529, loss: 0.06381382793188095
2023-01-23 02:20:59.649960: step: 948/529, loss: 0.022525405511260033
2023-01-23 02:21:00.795925: step: 952/529, loss: 0.022205352783203125
2023-01-23 02:21:01.967959: step: 956/529, loss: 0.002408695174381137
2023-01-23 02:21:03.106130: step: 960/529, loss: 0.0003517150762490928
2023-01-23 02:21:04.251095: step: 964/529, loss: 0.040834810584783554
2023-01-23 02:21:05.373487: step: 968/529, loss: 0.0012203216319903731
2023-01-23 02:21:06.483804: step: 972/529, loss: 0.0014957428211346269
2023-01-23 02:21:07.656174: step: 976/529, loss: 0.03419971093535423
2023-01-23 02:21:08.794570: step: 980/529, loss: 0.013865947723388672
2023-01-23 02:21:09.911636: step: 984/529, loss: 0.020564651116728783
2023-01-23 02:21:11.021377: step: 988/529, loss: 0.09808731079101562
2023-01-23 02:21:12.173591: step: 992/529, loss: 0.06164246052503586
2023-01-23 02:21:13.314378: step: 996/529, loss: 0.02040834352374077
2023-01-23 02:21:14.430471: step: 1000/529, loss: 0.0250641368329525
2023-01-23 02:21:15.565346: step: 1004/529, loss: 0.008885860443115234
2023-01-23 02:21:16.718077: step: 1008/529, loss: 0.022706128656864166
2023-01-23 02:21:17.860426: step: 1012/529, loss: 0.0010701239807531238
2023-01-23 02:21:18.989593: step: 1016/529, loss: 0.01834726333618164
2023-01-23 02:21:20.132277: step: 1020/529, loss: 0.02515435218811035
2023-01-23 02:21:21.284062: step: 1024/529, loss: 0.04207124933600426
2023-01-23 02:21:22.402392: step: 1028/529, loss: 0.006293106358498335
2023-01-23 02:21:23.572084: step: 1032/529, loss: 0.005190277472138405
2023-01-23 02:21:24.701848: step: 1036/529, loss: 0.0027791978791356087
2023-01-23 02:21:25.821453: step: 1040/529, loss: 0.0037404061295092106
2023-01-23 02:21:26.965683: step: 1044/529, loss: 0.016967011615633965
2023-01-23 02:21:28.114326: step: 1048/529, loss: 0.0010066032409667969
2023-01-23 02:21:29.268117: step: 1052/529, loss: 0.0013590813614428043
2023-01-23 02:21:30.435427: step: 1056/529, loss: 0.028480149805545807
2023-01-23 02:21:31.543165: step: 1060/529, loss: 0.0007292270893231034
2023-01-23 02:21:32.674899: step: 1064/529, loss: 0.021309280768036842
2023-01-23 02:21:33.835384: step: 1068/529, loss: 0.008470727130770683
2023-01-23 02:21:35.069441: step: 1072/529, loss: 0.010136699303984642
2023-01-23 02:21:36.195965: step: 1076/529, loss: 0.013977620750665665
2023-01-23 02:21:37.345031: step: 1080/529, loss: 0.028240211308002472
2023-01-23 02:21:38.466849: step: 1084/529, loss: 0.006890487857162952
2023-01-23 02:21:39.614778: step: 1088/529, loss: 0.0545470267534256
2023-01-23 02:21:40.780976: step: 1092/529, loss: 0.033797264099121094
2023-01-23 02:21:41.891497: step: 1096/529, loss: 0.025826359167695045
2023-01-23 02:21:43.030184: step: 1100/529, loss: 0.02433023601770401
2023-01-23 02:21:44.165698: step: 1104/529, loss: 0.041450027376413345
2023-01-23 02:21:45.315524: step: 1108/529, loss: 0.02288188971579075
2023-01-23 02:21:46.432667: step: 1112/529, loss: 0.00238380441442132
2023-01-23 02:21:47.579786: step: 1116/529, loss: 1.104986310005188
2023-01-23 02:21:48.739463: step: 1120/529, loss: 0.07848186790943146
2023-01-23 02:21:49.869811: step: 1124/529, loss: 0.0017284393543377519
2023-01-23 02:21:51.003155: step: 1128/529, loss: 0.07091350853443146
2023-01-23 02:21:52.128624: step: 1132/529, loss: 0.07041201740503311
2023-01-23 02:21:53.252265: step: 1136/529, loss: 3.9434431528206915e-05
2023-01-23 02:21:54.376007: step: 1140/529, loss: 0.010570049285888672
2023-01-23 02:21:55.531640: step: 1144/529, loss: 0.049651291221380234
2023-01-23 02:21:56.661930: step: 1148/529, loss: 0.04151783138513565
2023-01-23 02:21:57.813852: step: 1152/529, loss: 0.005554008297622204
2023-01-23 02:21:58.926015: step: 1156/529, loss: 0.03578986972570419
2023-01-23 02:22:00.073819: step: 1160/529, loss: 0.01227722130715847
2023-01-23 02:22:01.205114: step: 1164/529, loss: 0.02663097344338894
2023-01-23 02:22:02.354906: step: 1168/529, loss: 0.0036211013793945312
2023-01-23 02:22:03.499628: step: 1172/529, loss: 0.20060434937477112
2023-01-23 02:22:04.634977: step: 1176/529, loss: 0.03645477443933487
2023-01-23 02:22:05.795451: step: 1180/529, loss: 0.0031021118629723787
2023-01-23 02:22:06.932009: step: 1184/529, loss: 0.05019417032599449
2023-01-23 02:22:08.077102: step: 1188/529, loss: 0.01927957497537136
2023-01-23 02:22:09.223588: step: 1192/529, loss: 0.0033814432099461555
2023-01-23 02:22:10.352288: step: 1196/529, loss: 0.00040349960909225047
2023-01-23 02:22:11.491280: step: 1200/529, loss: 0.02581195905804634
2023-01-23 02:22:12.621865: step: 1204/529, loss: 0.28841090202331543
2023-01-23 02:22:13.770506: step: 1208/529, loss: 0.005242729559540749
2023-01-23 02:22:14.910223: step: 1212/529, loss: 0.00017042159743141383
2023-01-23 02:22:16.048528: step: 1216/529, loss: 0.009722709655761719
2023-01-23 02:22:17.173263: step: 1220/529, loss: 0.0021661759819835424
2023-01-23 02:22:18.353398: step: 1224/529, loss: 0.03922243043780327
2023-01-23 02:22:19.481286: step: 1228/529, loss: 0.006839179899543524
2023-01-23 02:22:20.620252: step: 1232/529, loss: 0.0016073227161541581
2023-01-23 02:22:21.786074: step: 1236/529, loss: 0.010824967175722122
2023-01-23 02:22:22.932198: step: 1240/529, loss: 0.03457050397992134
2023-01-23 02:22:24.092036: step: 1244/529, loss: 0.02587719075381756
2023-01-23 02:22:25.245523: step: 1248/529, loss: 0.02059345319867134
2023-01-23 02:22:26.409367: step: 1252/529, loss: 0.3758808672428131
2023-01-23 02:22:27.561167: step: 1256/529, loss: 0.057457152754068375
2023-01-23 02:22:28.726636: step: 1260/529, loss: 0.019969655200839043
2023-01-23 02:22:29.862214: step: 1264/529, loss: 0.0007939815404824913
2023-01-23 02:22:31.004165: step: 1268/529, loss: 0.024445246905088425
2023-01-23 02:22:32.146684: step: 1272/529, loss: 0.008227348327636719
2023-01-23 02:22:33.313682: step: 1276/529, loss: 0.02775583229959011
2023-01-23 02:22:34.472600: step: 1280/529, loss: 0.037984464317560196
2023-01-23 02:22:35.623266: step: 1284/529, loss: 0.0016654968494549394
2023-01-23 02:22:36.748875: step: 1288/529, loss: 0.0008003234979696572
2023-01-23 02:22:37.883489: step: 1292/529, loss: 0.006765366066247225
2023-01-23 02:22:39.020363: step: 1296/529, loss: 0.04855833202600479
2023-01-23 02:22:40.162134: step: 1300/529, loss: 0.020854951813817024
2023-01-23 02:22:41.339254: step: 1304/529, loss: 0.03893337398767471
2023-01-23 02:22:42.457834: step: 1308/529, loss: 0.005517005920410156
2023-01-23 02:22:43.609868: step: 1312/529, loss: 0.0022008896339684725
2023-01-23 02:22:44.792143: step: 1316/529, loss: 0.004822349641472101
2023-01-23 02:22:45.946948: step: 1320/529, loss: 0.009962749667465687
2023-01-23 02:22:47.133950: step: 1324/529, loss: 0.01456222590059042
2023-01-23 02:22:48.250373: step: 1328/529, loss: 0.03274068981409073
2023-01-23 02:22:49.396525: step: 1332/529, loss: 0.010128498077392578
2023-01-23 02:22:50.565790: step: 1336/529, loss: 0.28467294573783875
2023-01-23 02:22:51.729103: step: 1340/529, loss: 0.016507340595126152
2023-01-23 02:22:52.860467: step: 1344/529, loss: 0.03522081300616264
2023-01-23 02:22:54.000330: step: 1348/529, loss: 0.00025696755619719625
2023-01-23 02:22:55.128196: step: 1352/529, loss: 0.0002065070002572611
2023-01-23 02:22:56.291661: step: 1356/529, loss: 0.03253822401165962
2023-01-23 02:22:57.410855: step: 1360/529, loss: 0.020462609827518463
2023-01-23 02:22:58.530789: step: 1364/529, loss: 0.09718303382396698
2023-01-23 02:22:59.652717: step: 1368/529, loss: 0.026201914995908737
2023-01-23 02:23:00.794064: step: 1372/529, loss: 0.001691627549007535
2023-01-23 02:23:01.888707: step: 1376/529, loss: 0.0019495964515954256
2023-01-23 02:23:03.018484: step: 1380/529, loss: 0.0007335662958212197
2023-01-23 02:23:04.153236: step: 1384/529, loss: 0.052747536450624466
2023-01-23 02:23:05.295497: step: 1388/529, loss: 0.06004119664430618
2023-01-23 02:23:06.440248: step: 1392/529, loss: 0.013131809420883656
2023-01-23 02:23:07.569223: step: 1396/529, loss: 0.002691173693165183
2023-01-23 02:23:08.686842: step: 1400/529, loss: 0.015098286792635918
2023-01-23 02:23:09.814099: step: 1404/529, loss: 0.03063373640179634
2023-01-23 02:23:10.936722: step: 1408/529, loss: 0.0003714561462402344
2023-01-23 02:23:12.088385: step: 1412/529, loss: 0.00010094643221236765
2023-01-23 02:23:13.218094: step: 1416/529, loss: 0.0002612113894429058
2023-01-23 02:23:14.373575: step: 1420/529, loss: 0.010074520483613014
2023-01-23 02:23:15.467932: step: 1424/529, loss: 0.008118915371596813
2023-01-23 02:23:16.634550: step: 1428/529, loss: 0.0013757705455645919
2023-01-23 02:23:17.773327: step: 1432/529, loss: 0.0011120797134935856
2023-01-23 02:23:18.898957: step: 1436/529, loss: 0.0006565094226971269
2023-01-23 02:23:20.024375: step: 1440/529, loss: 0.021738719195127487
2023-01-23 02:23:21.144020: step: 1444/529, loss: 0.0002754211309365928
2023-01-23 02:23:22.266156: step: 1448/529, loss: 0.0031210898887366056
2023-01-23 02:23:23.404267: step: 1452/529, loss: 0.06607885658740997
2023-01-23 02:23:24.532864: step: 1456/529, loss: 0.0023772241547703743
2023-01-23 02:23:25.703912: step: 1460/529, loss: 0.0004784107441082597
2023-01-23 02:23:26.820610: step: 1464/529, loss: 0.12763424217700958
2023-01-23 02:23:27.961058: step: 1468/529, loss: 0.0265871062874794
2023-01-23 02:23:29.095645: step: 1472/529, loss: 0.02527751959860325
2023-01-23 02:23:30.222408: step: 1476/529, loss: 0.03329315036535263
2023-01-23 02:23:31.384498: step: 1480/529, loss: 0.10500279068946838
2023-01-23 02:23:32.530671: step: 1484/529, loss: 0.009329795837402344
2023-01-23 02:23:33.659370: step: 1488/529, loss: 0.017876578494906425
2023-01-23 02:23:34.797545: step: 1492/529, loss: 0.0744309350848198
2023-01-23 02:23:35.967634: step: 1496/529, loss: 0.10974683612585068
2023-01-23 02:23:37.110020: step: 1500/529, loss: 0.04722023010253906
2023-01-23 02:23:38.271146: step: 1504/529, loss: 0.002580833388492465
2023-01-23 02:23:39.416283: step: 1508/529, loss: 0.003114557359367609
2023-01-23 02:23:40.543417: step: 1512/529, loss: 0.2487998902797699
2023-01-23 02:23:41.723766: step: 1516/529, loss: 0.7010349035263062
2023-01-23 02:23:42.892714: step: 1520/529, loss: 0.018754005432128906
2023-01-23 02:23:44.015786: step: 1524/529, loss: 0.02645101398229599
2023-01-23 02:23:45.185993: step: 1528/529, loss: 0.01490316353738308
2023-01-23 02:23:46.336642: step: 1532/529, loss: 0.003131866455078125
2023-01-23 02:23:47.470148: step: 1536/529, loss: 0.027715682983398438
2023-01-23 02:23:48.595872: step: 1540/529, loss: 0.0011343001388013363
2023-01-23 02:23:49.735379: step: 1544/529, loss: 0.022390365600585938
2023-01-23 02:23:50.902792: step: 1548/529, loss: 0.01876678504049778
2023-01-23 02:23:52.046976: step: 1552/529, loss: 0.004564475733786821
2023-01-23 02:23:53.181687: step: 1556/529, loss: 0.024617576971650124
2023-01-23 02:23:54.357910: step: 1560/529, loss: 0.00028591154841706157
2023-01-23 02:23:55.489846: step: 1564/529, loss: 0.013111305423080921
2023-01-23 02:23:56.640557: step: 1568/529, loss: 0.008581352420151234
2023-01-23 02:23:57.767685: step: 1572/529, loss: 0.014995861798524857
2023-01-23 02:23:58.882094: step: 1576/529, loss: 0.04624929279088974
2023-01-23 02:24:00.038713: step: 1580/529, loss: 0.06347541511058807
2023-01-23 02:24:01.210320: step: 1584/529, loss: 0.013006210327148438
2023-01-23 02:24:02.356104: step: 1588/529, loss: 0.0006497383583337069
2023-01-23 02:24:03.509527: step: 1592/529, loss: 0.0072428700514137745
2023-01-23 02:24:04.663233: step: 1596/529, loss: 0.002002525143325329
2023-01-23 02:24:05.785575: step: 1600/529, loss: 0.0663658007979393
2023-01-23 02:24:06.925991: step: 1604/529, loss: 0.00048828125
2023-01-23 02:24:08.060800: step: 1608/529, loss: 0.025282716378569603
2023-01-23 02:24:09.248804: step: 1612/529, loss: 0.023212242871522903
2023-01-23 02:24:10.416560: step: 1616/529, loss: 0.01238784845918417
2023-01-23 02:24:11.567619: step: 1620/529, loss: 0.06938133388757706
2023-01-23 02:24:12.719530: step: 1624/529, loss: 0.0457189567387104
2023-01-23 02:24:13.873560: step: 1628/529, loss: 0.00818624533712864
2023-01-23 02:24:15.010543: step: 1632/529, loss: 0.04999618977308273
2023-01-23 02:24:16.157279: step: 1636/529, loss: 0.0023382187355309725
2023-01-23 02:24:17.275504: step: 1640/529, loss: 0.014842129312455654
2023-01-23 02:24:18.428420: step: 1644/529, loss: 0.008029174990952015
2023-01-23 02:24:19.541334: step: 1648/529, loss: 0.008969116024672985
2023-01-23 02:24:20.703088: step: 1652/529, loss: 0.03575191646814346
2023-01-23 02:24:21.871679: step: 1656/529, loss: 0.037931445986032486
2023-01-23 02:24:23.003262: step: 1660/529, loss: 0.029606247320771217
2023-01-23 02:24:24.164052: step: 1664/529, loss: 0.056976318359375
2023-01-23 02:24:25.285162: step: 1668/529, loss: 0.003731155302375555
2023-01-23 02:24:26.451257: step: 1672/529, loss: 0.049599841237068176
2023-01-23 02:24:27.598993: step: 1676/529, loss: 0.020070362836122513
2023-01-23 02:24:28.765932: step: 1680/529, loss: 0.056424617767333984
2023-01-23 02:24:29.925113: step: 1684/529, loss: 0.04691801220178604
2023-01-23 02:24:31.092631: step: 1688/529, loss: 0.0008308410178869963
2023-01-23 02:24:32.232662: step: 1692/529, loss: 0.000640916870906949
2023-01-23 02:24:33.388914: step: 1696/529, loss: 0.010032462887465954
2023-01-23 02:24:34.528700: step: 1700/529, loss: 0.013447379693388939
2023-01-23 02:24:35.671341: step: 1704/529, loss: 0.036274053156375885
2023-01-23 02:24:36.795510: step: 1708/529, loss: 0.5931419134140015
2023-01-23 02:24:37.932751: step: 1712/529, loss: 0.032277777791023254
2023-01-23 02:24:39.031977: step: 1716/529, loss: 0.009038066491484642
2023-01-23 02:24:40.182640: step: 1720/529, loss: 0.010699844919145107
2023-01-23 02:24:41.327915: step: 1724/529, loss: 0.007488823030143976
2023-01-23 02:24:42.467903: step: 1728/529, loss: 0.005389595404267311
2023-01-23 02:24:43.617336: step: 1732/529, loss: 0.023988818749785423
2023-01-23 02:24:44.763558: step: 1736/529, loss: 0.0010326385963708162
2023-01-23 02:24:45.908112: step: 1740/529, loss: 0.1594664603471756
2023-01-23 02:24:47.040546: step: 1744/529, loss: 0.052855681627988815
2023-01-23 02:24:48.183527: step: 1748/529, loss: 0.006522479932755232
2023-01-23 02:24:49.311882: step: 1752/529, loss: 0.013235759921371937
2023-01-23 02:24:50.420648: step: 1756/529, loss: 0.02443857304751873
2023-01-23 02:24:51.532289: step: 1760/529, loss: 0.008518275804817677
2023-01-23 02:24:52.655709: step: 1764/529, loss: 0.004141808021813631
2023-01-23 02:24:53.820075: step: 1768/529, loss: 0.047465730458498
2023-01-23 02:24:54.949035: step: 1772/529, loss: 0.02482481114566326
2023-01-23 02:24:56.129827: step: 1776/529, loss: 0.023076439276337624
2023-01-23 02:24:57.262089: step: 1780/529, loss: 0.02016582526266575
2023-01-23 02:24:58.439228: step: 1784/529, loss: 0.11726856231689453
2023-01-23 02:24:59.591731: step: 1788/529, loss: 0.00041370390681549907
2023-01-23 02:25:00.746111: step: 1792/529, loss: 0.01807870902121067
2023-01-23 02:25:01.887099: step: 1796/529, loss: 0.003523159073665738
2023-01-23 02:25:03.093545: step: 1800/529, loss: 0.024566078558564186
2023-01-23 02:25:04.218740: step: 1804/529, loss: 0.0014314651489257812
2023-01-23 02:25:05.353019: step: 1808/529, loss: 0.09362497925758362
2023-01-23 02:25:06.510946: step: 1812/529, loss: 0.004131317138671875
2023-01-23 02:25:07.662385: step: 1816/529, loss: 0.013601303100585938
2023-01-23 02:25:08.788861: step: 1820/529, loss: 0.028903769329190254
2023-01-23 02:25:09.924640: step: 1824/529, loss: 0.05010054260492325
2023-01-23 02:25:11.086620: step: 1828/529, loss: 0.012841988354921341
2023-01-23 02:25:12.227465: step: 1832/529, loss: 0.04880065843462944
2023-01-23 02:25:13.374402: step: 1836/529, loss: 0.00017623903113417327
2023-01-23 02:25:14.498056: step: 1840/529, loss: 0.037212345749139786
2023-01-23 02:25:15.629112: step: 1844/529, loss: 0.005331802647560835
2023-01-23 02:25:16.780596: step: 1848/529, loss: 0.011832189746201038
2023-01-23 02:25:17.905848: step: 1852/529, loss: 0.19008304178714752
2023-01-23 02:25:19.038601: step: 1856/529, loss: 0.033326104283332825
2023-01-23 02:25:20.183345: step: 1860/529, loss: 0.0009250640869140625
2023-01-23 02:25:21.345836: step: 1864/529, loss: 0.007072639651596546
2023-01-23 02:25:22.473853: step: 1868/529, loss: 0.013271331787109375
2023-01-23 02:25:23.601373: step: 1872/529, loss: 0.018895339220762253
2023-01-23 02:25:24.755693: step: 1876/529, loss: 0.010406112298369408
2023-01-23 02:25:25.902034: step: 1880/529, loss: 0.018147850409150124
2023-01-23 02:25:27.039068: step: 1884/529, loss: 0.00739631662145257
2023-01-23 02:25:28.195054: step: 1888/529, loss: 0.004591751378029585
2023-01-23 02:25:29.345143: step: 1892/529, loss: 0.0007364749908447266
2023-01-23 02:25:30.469452: step: 1896/529, loss: 0.019927598536014557
2023-01-23 02:25:31.630585: step: 1900/529, loss: 0.005155086982995272
2023-01-23 02:25:32.838206: step: 1904/529, loss: 0.013299942016601562
2023-01-23 02:25:34.014234: step: 1908/529, loss: 0.038001637905836105
2023-01-23 02:25:35.172615: step: 1912/529, loss: 0.046645261347293854
2023-01-23 02:25:36.302706: step: 1916/529, loss: 0.0026298523880541325
2023-01-23 02:25:37.470246: step: 1920/529, loss: 0.0358491912484169
2023-01-23 02:25:38.617126: step: 1924/529, loss: 0.05771274492144585
2023-01-23 02:25:39.752356: step: 1928/529, loss: 7.724761962890625e-05
2023-01-23 02:25:40.886176: step: 1932/529, loss: 0.0052055357955396175
2023-01-23 02:25:42.041543: step: 1936/529, loss: 0.0002552032528910786
2023-01-23 02:25:43.181467: step: 1940/529, loss: 0.0004426002560649067
2023-01-23 02:25:44.307400: step: 1944/529, loss: 0.07954387366771698
2023-01-23 02:25:45.455502: step: 1948/529, loss: 0.010173988528549671
2023-01-23 02:25:46.576431: step: 1952/529, loss: 0.10088739544153214
2023-01-23 02:25:47.724093: step: 1956/529, loss: 0.034436989575624466
2023-01-23 02:25:48.873613: step: 1960/529, loss: 0.006924915127456188
2023-01-23 02:25:49.999626: step: 1964/529, loss: 0.016892993822693825
2023-01-23 02:25:51.195268: step: 1968/529, loss: 0.16579914093017578
2023-01-23 02:25:52.364474: step: 1972/529, loss: 0.04669789969921112
2023-01-23 02:25:53.482633: step: 1976/529, loss: 0.028626490384340286
2023-01-23 02:25:54.648959: step: 1980/529, loss: 0.008643150329589844
2023-01-23 02:25:55.789722: step: 1984/529, loss: 0.003363037249073386
2023-01-23 02:25:56.941245: step: 1988/529, loss: 0.03058185614645481
2023-01-23 02:25:58.075090: step: 1992/529, loss: 0.09120196104049683
2023-01-23 02:25:59.217967: step: 1996/529, loss: 0.013782501220703125
2023-01-23 02:26:00.361583: step: 2000/529, loss: 0.06439408659934998
2023-01-23 02:26:01.534118: step: 2004/529, loss: 0.02214536815881729
2023-01-23 02:26:02.689330: step: 2008/529, loss: 0.04889526218175888
2023-01-23 02:26:03.875151: step: 2012/529, loss: 0.0643530860543251
2023-01-23 02:26:05.013911: step: 2016/529, loss: 0.006801176350563765
2023-01-23 02:26:06.164629: step: 2020/529, loss: 0.005294132046401501
2023-01-23 02:26:07.296093: step: 2024/529, loss: 0.005389213562011719
2023-01-23 02:26:08.410944: step: 2028/529, loss: 0.024183249101042747
2023-01-23 02:26:09.575599: step: 2032/529, loss: 0.016169453039765358
2023-01-23 02:26:10.754014: step: 2036/529, loss: 0.01381683349609375
2023-01-23 02:26:11.890944: step: 2040/529, loss: 0.000222945207497105
2023-01-23 02:26:13.038045: step: 2044/529, loss: 0.019466400146484375
2023-01-23 02:26:14.192161: step: 2048/529, loss: 0.008198071271181107
2023-01-23 02:26:15.320543: step: 2052/529, loss: 0.03301544114947319
2023-01-23 02:26:16.457876: step: 2056/529, loss: 0.015151405707001686
2023-01-23 02:26:17.596340: step: 2060/529, loss: 0.07522258907556534
2023-01-23 02:26:18.749571: step: 2064/529, loss: 0.0515805259346962
2023-01-23 02:26:19.913066: step: 2068/529, loss: 0.03762846440076828
2023-01-23 02:26:21.037030: step: 2072/529, loss: 0.0026432513259351254
2023-01-23 02:26:22.164543: step: 2076/529, loss: 0.028045939281582832
2023-01-23 02:26:23.325033: step: 2080/529, loss: 0.0003803253057412803
2023-01-23 02:26:24.451958: step: 2084/529, loss: 0.004448986612260342
2023-01-23 02:26:25.604819: step: 2088/529, loss: 0.005446815863251686
2023-01-23 02:26:26.740182: step: 2092/529, loss: 0.022199535742402077
2023-01-23 02:26:27.864496: step: 2096/529, loss: 0.8220190405845642
2023-01-23 02:26:28.992396: step: 2100/529, loss: 0.01908578909933567
2023-01-23 02:26:30.144389: step: 2104/529, loss: 0.0033995630219578743
2023-01-23 02:26:31.276388: step: 2108/529, loss: 0.002408313797786832
2023-01-23 02:26:32.411044: step: 2112/529, loss: 0.004783153533935547
2023-01-23 02:26:33.556952: step: 2116/529, loss: 0.0001625060976948589
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6213592233009708, 'r': 0.7669773635153129, 'f1': 0.6865315852205005}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6436274509803922, 'r': 0.7607184241019699, 'f1': 0.6972915560276155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.625, 'r': 0.5555555555555556, 'f1': 0.5882352941176471}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.5555555555555556, 'f1': 0.49382716049382713}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:27:14.764182: step: 4/529, loss: 0.00980291422456503
2023-01-23 02:27:15.892567: step: 8/529, loss: 0.03227834776043892
2023-01-23 02:27:17.017827: step: 12/529, loss: 0.004454899113625288
2023-01-23 02:27:18.141003: step: 16/529, loss: 0.0016155242919921875
2023-01-23 02:27:19.278770: step: 20/529, loss: 0.005145454313606024
2023-01-23 02:27:20.408585: step: 24/529, loss: 0.020261382684111595
2023-01-23 02:27:21.544950: step: 28/529, loss: 0.0001310348598053679
2023-01-23 02:27:22.672639: step: 32/529, loss: 0.06226807087659836
2023-01-23 02:27:23.818529: step: 36/529, loss: 0.008191203698515892
2023-01-23 02:27:24.961738: step: 40/529, loss: 0.002740478375926614
2023-01-23 02:27:26.080601: step: 44/529, loss: 0.024071503430604935
2023-01-23 02:27:27.239761: step: 48/529, loss: 0.014621258713304996
2023-01-23 02:27:28.391469: step: 52/529, loss: 0.03954477235674858
2023-01-23 02:27:29.525472: step: 56/529, loss: 0.3380860686302185
2023-01-23 02:27:30.670765: step: 60/529, loss: 0.0024174691643565893
2023-01-23 02:27:31.809497: step: 64/529, loss: 0.08009643852710724
2023-01-23 02:27:32.930914: step: 68/529, loss: 0.005244204308837652
2023-01-23 02:27:34.101206: step: 72/529, loss: 0.006070995237678289
2023-01-23 02:27:35.237608: step: 76/529, loss: 0.0014183043967932463
2023-01-23 02:27:36.377035: step: 80/529, loss: 0.005898761563003063
2023-01-23 02:27:37.543438: step: 84/529, loss: 0.00016880035400390625
2023-01-23 02:27:38.682351: step: 88/529, loss: 0.012494374066591263
2023-01-23 02:27:39.809127: step: 92/529, loss: 0.18097858130931854
2023-01-23 02:27:40.939147: step: 96/529, loss: 0.04884052276611328
2023-01-23 02:27:42.097385: step: 100/529, loss: 0.004426002502441406
2023-01-23 02:27:43.245221: step: 104/529, loss: 0.01939554139971733
2023-01-23 02:27:44.398293: step: 108/529, loss: 0.022711850702762604
2023-01-23 02:27:45.522625: step: 112/529, loss: 0.003566932864487171
2023-01-23 02:27:46.655820: step: 116/529, loss: 0.012328815646469593
2023-01-23 02:27:47.796845: step: 120/529, loss: 0.07349672168493271
2023-01-23 02:27:48.943274: step: 124/529, loss: 0.02655172534286976
2023-01-23 02:27:50.058653: step: 128/529, loss: 0.000664138759020716
2023-01-23 02:27:51.219462: step: 132/529, loss: 0.02839946746826172
2023-01-23 02:27:52.363445: step: 136/529, loss: 0.0016240120166912675
2023-01-23 02:27:53.489398: step: 140/529, loss: 0.07888088375329971
2023-01-23 02:27:54.619796: step: 144/529, loss: 0.0017282485496252775
2023-01-23 02:27:55.770841: step: 148/529, loss: 0.0030162811744958162
2023-01-23 02:27:56.910329: step: 152/529, loss: 0.026589393615722656
2023-01-23 02:27:58.048709: step: 156/529, loss: 0.06963425129652023
2023-01-23 02:27:59.172847: step: 160/529, loss: 0.001889991806820035
2023-01-23 02:28:00.290716: step: 164/529, loss: 0.0028238771483302116
2023-01-23 02:28:01.446431: step: 168/529, loss: 0.007329368963837624
2023-01-23 02:28:02.577274: step: 172/529, loss: 0.01625976525247097
2023-01-23 02:28:03.725938: step: 176/529, loss: 0.02523813210427761
2023-01-23 02:28:04.875007: step: 180/529, loss: 0.0008698463207110763
2023-01-23 02:28:05.974288: step: 184/529, loss: 0.003505134489387274
2023-01-23 02:28:07.102637: step: 188/529, loss: 0.09457750618457794
2023-01-23 02:28:08.253159: step: 192/529, loss: 0.03552980348467827
2023-01-23 02:28:09.389122: step: 196/529, loss: 0.013662147335708141
2023-01-23 02:28:10.522313: step: 200/529, loss: 0.07314208149909973
2023-01-23 02:28:11.658106: step: 204/529, loss: 0.002875042147934437
2023-01-23 02:28:12.800923: step: 208/529, loss: 0.017232514917850494
2023-01-23 02:28:13.932104: step: 212/529, loss: 0.00427322369068861
2023-01-23 02:28:15.065853: step: 216/529, loss: 0.04822085052728653
2023-01-23 02:28:16.214206: step: 220/529, loss: 9.384155418956652e-05
2023-01-23 02:28:17.354911: step: 224/529, loss: 0.006916237063705921
2023-01-23 02:28:18.494357: step: 228/529, loss: 0.001729774521663785
2023-01-23 02:28:19.649560: step: 232/529, loss: 0.00023651123046875
2023-01-23 02:28:20.800726: step: 236/529, loss: 0.004020023625344038
2023-01-23 02:28:21.942057: step: 240/529, loss: 0.004679298494011164
2023-01-23 02:28:23.071413: step: 244/529, loss: 4.0626528061693534e-05
2023-01-23 02:28:24.235692: step: 248/529, loss: 0.09011640399694443
2023-01-23 02:28:25.354052: step: 252/529, loss: 0.05582733079791069
2023-01-23 02:28:26.478670: step: 256/529, loss: 0.02553529664874077
2023-01-23 02:28:27.645595: step: 260/529, loss: 0.029871942475438118
2023-01-23 02:28:28.756675: step: 264/529, loss: 0.001834773924201727
2023-01-23 02:28:29.899082: step: 268/529, loss: 0.041945457458496094
2023-01-23 02:28:31.020764: step: 272/529, loss: 0.026454783976078033
2023-01-23 02:28:32.149425: step: 276/529, loss: 0.04946298897266388
2023-01-23 02:28:33.308823: step: 280/529, loss: 0.0064636231400072575
2023-01-23 02:28:34.449653: step: 284/529, loss: 0.05516119301319122
2023-01-23 02:28:35.568889: step: 288/529, loss: 0.018744850531220436
2023-01-23 02:28:36.694714: step: 292/529, loss: 0.0003684043767862022
2023-01-23 02:28:37.814661: step: 296/529, loss: 0.00012865067401435226
2023-01-23 02:28:38.963425: step: 300/529, loss: 0.04284706339240074
2023-01-23 02:28:40.081309: step: 304/529, loss: 0.02588510513305664
2023-01-23 02:28:41.238409: step: 308/529, loss: 0.002304458525031805
2023-01-23 02:28:42.383076: step: 312/529, loss: 0.044738009572029114
2023-01-23 02:28:43.486890: step: 316/529, loss: 0.012210655026137829
2023-01-23 02:28:44.641720: step: 320/529, loss: 0.019185829907655716
2023-01-23 02:28:45.772579: step: 324/529, loss: 0.04814085736870766
2023-01-23 02:28:46.917214: step: 328/529, loss: 0.011650276370346546
2023-01-23 02:28:48.056630: step: 332/529, loss: 0.021657563745975494
2023-01-23 02:28:49.199303: step: 336/529, loss: 0.00460438709706068
2023-01-23 02:28:50.332677: step: 340/529, loss: 0.003719830419868231
2023-01-23 02:28:51.488275: step: 344/529, loss: 0.04912605881690979
2023-01-23 02:28:52.626736: step: 348/529, loss: 0.06083059683442116
2023-01-23 02:28:53.773674: step: 352/529, loss: 0.04420957714319229
2023-01-23 02:28:54.903600: step: 356/529, loss: 0.0010129929287359118
2023-01-23 02:28:56.030493: step: 360/529, loss: 0.0008832931634970009
2023-01-23 02:28:57.175424: step: 364/529, loss: 0.002809906145557761
2023-01-23 02:28:58.332675: step: 368/529, loss: 0.07935362309217453
2023-01-23 02:28:59.475617: step: 372/529, loss: 0.0003561020130291581
2023-01-23 02:29:00.616416: step: 376/529, loss: 0.030472850427031517
2023-01-23 02:29:01.758628: step: 380/529, loss: 0.004821205511689186
2023-01-23 02:29:02.868461: step: 384/529, loss: 0.0731317549943924
2023-01-23 02:29:03.995426: step: 388/529, loss: 0.0010470390552654862
2023-01-23 02:29:05.151548: step: 392/529, loss: 0.015868186950683594
2023-01-23 02:29:06.311243: step: 396/529, loss: 0.00107488629873842
2023-01-23 02:29:07.437311: step: 400/529, loss: 0.012009715661406517
2023-01-23 02:29:08.584502: step: 404/529, loss: 0.0049270628951489925
2023-01-23 02:29:09.726130: step: 408/529, loss: 0.0009677887428551912
2023-01-23 02:29:10.876359: step: 412/529, loss: 0.006442260928452015
2023-01-23 02:29:11.986830: step: 416/529, loss: 0.03438606113195419
2023-01-23 02:29:13.128566: step: 420/529, loss: 0.0003637791087385267
2023-01-23 02:29:14.224420: step: 424/529, loss: 0.00032358168391510844
2023-01-23 02:29:15.376034: step: 428/529, loss: 0.005825805943459272
2023-01-23 02:29:16.488801: step: 432/529, loss: 0.0033159255981445312
2023-01-23 02:29:17.668858: step: 436/529, loss: 0.000827789306640625
2023-01-23 02:29:18.816689: step: 440/529, loss: 0.019193649291992188
2023-01-23 02:29:19.987700: step: 444/529, loss: 0.05843019485473633
2023-01-23 02:29:21.106182: step: 448/529, loss: 0.02928762510418892
2023-01-23 02:29:22.265209: step: 452/529, loss: 0.03692684322595596
2023-01-23 02:29:23.433350: step: 456/529, loss: 0.007652568630874157
2023-01-23 02:29:24.569982: step: 460/529, loss: 0.0006719589000567794
2023-01-23 02:29:25.709391: step: 464/529, loss: 0.014843559823930264
2023-01-23 02:29:26.853371: step: 468/529, loss: 0.029177237302064896
2023-01-23 02:29:27.991154: step: 472/529, loss: 0.021376824006438255
2023-01-23 02:29:29.127619: step: 476/529, loss: 0.06917037814855576
2023-01-23 02:29:30.263120: step: 480/529, loss: 0.023467255756258965
2023-01-23 02:29:31.397746: step: 484/529, loss: 0.022478677332401276
2023-01-23 02:29:32.514512: step: 488/529, loss: 0.0926908552646637
2023-01-23 02:29:33.636434: step: 492/529, loss: 0.0012767792213708162
2023-01-23 02:29:34.769886: step: 496/529, loss: 0.028953934088349342
2023-01-23 02:29:35.927779: step: 500/529, loss: 0.01389245968312025
2023-01-23 02:29:37.089592: step: 504/529, loss: 0.013598919846117496
2023-01-23 02:29:38.253327: step: 508/529, loss: 0.0002747535763774067
2023-01-23 02:29:39.417462: step: 512/529, loss: 0.0010767936473712325
2023-01-23 02:29:40.573081: step: 516/529, loss: 0.0036822319962084293
2023-01-23 02:29:41.723286: step: 520/529, loss: 0.02061338536441326
2023-01-23 02:29:42.883527: step: 524/529, loss: 0.0012369155883789062
2023-01-23 02:29:44.011305: step: 528/529, loss: 0.00026416778564453125
2023-01-23 02:29:45.188935: step: 532/529, loss: 0.0058189393021166325
2023-01-23 02:29:46.338376: step: 536/529, loss: 0.01992187462747097
2023-01-23 02:29:47.455308: step: 540/529, loss: 0.0005779266939498484
2023-01-23 02:29:48.621525: step: 544/529, loss: 0.0041221617721021175
2023-01-23 02:29:49.793473: step: 548/529, loss: 0.00023622512526344508
2023-01-23 02:29:50.941345: step: 552/529, loss: 0.004508304409682751
2023-01-23 02:29:52.078246: step: 556/529, loss: 0.03316173702478409
2023-01-23 02:29:53.227963: step: 560/529, loss: 0.004639816470444202
2023-01-23 02:29:54.365797: step: 564/529, loss: 0.004973125644028187
2023-01-23 02:29:55.490632: step: 568/529, loss: 0.04298343509435654
2023-01-23 02:29:56.649281: step: 572/529, loss: 0.0038782120682299137
2023-01-23 02:29:57.746764: step: 576/529, loss: 0.007598876953125
2023-01-23 02:29:58.882811: step: 580/529, loss: 0.09616661071777344
2023-01-23 02:30:00.005882: step: 584/529, loss: 0.010191250592470169
2023-01-23 02:30:01.154490: step: 588/529, loss: 0.033980607986450195
2023-01-23 02:30:02.287818: step: 592/529, loss: 0.07082367688417435
2023-01-23 02:30:03.453776: step: 596/529, loss: 0.011842155829071999
2023-01-23 02:30:04.607234: step: 600/529, loss: 0.003889370011165738
2023-01-23 02:30:05.744857: step: 604/529, loss: 0.01498708687722683
2023-01-23 02:30:06.878756: step: 608/529, loss: 0.004042625427246094
2023-01-23 02:30:08.033758: step: 612/529, loss: 0.010221290402114391
2023-01-23 02:30:09.155477: step: 616/529, loss: 0.0005509377224370837
2023-01-23 02:30:10.295894: step: 620/529, loss: 0.0004811286926269531
2023-01-23 02:30:11.438745: step: 624/529, loss: 0.01910400390625
2023-01-23 02:30:12.567047: step: 628/529, loss: 0.008157063275575638
2023-01-23 02:30:13.728084: step: 632/529, loss: 0.024146152660250664
2023-01-23 02:30:14.852663: step: 636/529, loss: 0.03137988969683647
2023-01-23 02:30:16.015402: step: 640/529, loss: 0.0002980232238769531
2023-01-23 02:30:17.176443: step: 644/529, loss: 0.0009495735284872353
2023-01-23 02:30:18.323964: step: 648/529, loss: 7.381439354503527e-05
2023-01-23 02:30:19.499133: step: 652/529, loss: 0.030804958194494247
2023-01-23 02:30:20.625498: step: 656/529, loss: 0.001996326493099332
2023-01-23 02:30:21.759038: step: 660/529, loss: 0.05277710035443306
2023-01-23 02:30:22.899031: step: 664/529, loss: 0.043516673147678375
2023-01-23 02:30:24.075417: step: 668/529, loss: 0.052054502069950104
2023-01-23 02:30:25.248496: step: 672/529, loss: 0.04818020015954971
2023-01-23 02:30:26.408533: step: 676/529, loss: 0.001868820283561945
2023-01-23 02:30:27.539843: step: 680/529, loss: 0.0366579070687294
2023-01-23 02:30:28.689322: step: 684/529, loss: 0.0008013725164346397
2023-01-23 02:30:29.842436: step: 688/529, loss: 0.02044367790222168
2023-01-23 02:30:30.965463: step: 692/529, loss: 0.002616023877635598
2023-01-23 02:30:32.109047: step: 696/529, loss: 0.023929595947265625
2023-01-23 02:30:33.239649: step: 700/529, loss: 0.03232889249920845
2023-01-23 02:30:34.351533: step: 704/529, loss: 0.0035856247413903475
2023-01-23 02:30:35.507773: step: 708/529, loss: 0.01963496208190918
2023-01-23 02:30:36.659890: step: 712/529, loss: 0.1837204098701477
2023-01-23 02:30:37.779938: step: 716/529, loss: 0.009389782324433327
2023-01-23 02:30:38.942166: step: 720/529, loss: 0.027189921587705612
2023-01-23 02:30:40.068290: step: 724/529, loss: 0.12962722778320312
2023-01-23 02:30:41.210407: step: 728/529, loss: 0.016514873132109642
2023-01-23 02:30:42.353606: step: 732/529, loss: 9.298324584960938e-05
2023-01-23 02:30:43.482403: step: 736/529, loss: 0.012986088171601295
2023-01-23 02:30:44.625132: step: 740/529, loss: 0.003890013787895441
2023-01-23 02:30:45.787359: step: 744/529, loss: 0.0001510620058979839
2023-01-23 02:30:46.932219: step: 748/529, loss: 1.9741059077205136e-05
2023-01-23 02:30:48.064234: step: 752/529, loss: 0.059157274663448334
2023-01-23 02:30:49.215187: step: 756/529, loss: 0.003543091006577015
2023-01-23 02:30:50.363348: step: 760/529, loss: 0.0038873672019690275
2023-01-23 02:30:51.517318: step: 764/529, loss: 0.13239344954490662
2023-01-23 02:30:52.710183: step: 768/529, loss: 0.014187430962920189
2023-01-23 02:30:53.830749: step: 772/529, loss: 0.011584663763642311
2023-01-23 02:30:54.973010: step: 776/529, loss: 0.009246778674423695
2023-01-23 02:30:56.094895: step: 780/529, loss: 0.033936403691768646
2023-01-23 02:30:57.201049: step: 784/529, loss: 0.0004646301094908267
2023-01-23 02:30:58.338182: step: 788/529, loss: 0.021702958270907402
2023-01-23 02:30:59.465443: step: 792/529, loss: 0.031316231936216354
2023-01-23 02:31:00.618474: step: 796/529, loss: 0.05794792249798775
2023-01-23 02:31:01.764602: step: 800/529, loss: 0.03635444492101669
2023-01-23 02:31:02.915248: step: 804/529, loss: 0.04673881456255913
2023-01-23 02:31:04.104818: step: 808/529, loss: 0.008633327670395374
2023-01-23 02:31:05.227563: step: 812/529, loss: 0.006572866812348366
2023-01-23 02:31:06.384520: step: 816/529, loss: 0.016468429937958717
2023-01-23 02:31:07.494011: step: 820/529, loss: 0.034932807087898254
2023-01-23 02:31:08.620770: step: 824/529, loss: 0.014830934815108776
2023-01-23 02:31:09.760120: step: 828/529, loss: 0.005287742707878351
2023-01-23 02:31:10.896635: step: 832/529, loss: 0.07670764625072479
2023-01-23 02:31:12.012964: step: 836/529, loss: 0.005574226379394531
2023-01-23 02:31:13.149226: step: 840/529, loss: 0.019486570730805397
2023-01-23 02:31:14.307115: step: 844/529, loss: 0.010714912787079811
2023-01-23 02:31:15.463420: step: 848/529, loss: 0.0005819320795126259
2023-01-23 02:31:16.614382: step: 852/529, loss: 0.019542885944247246
2023-01-23 02:31:17.736941: step: 856/529, loss: 0.04361124336719513
2023-01-23 02:31:18.864746: step: 860/529, loss: 0.06918258965015411
2023-01-23 02:31:20.042815: step: 864/529, loss: 0.03521308675408363
2023-01-23 02:31:21.189629: step: 868/529, loss: 0.0021944046020507812
2023-01-23 02:31:22.345677: step: 872/529, loss: 0.03416891023516655
2023-01-23 02:31:23.474409: step: 876/529, loss: 0.009745406918227673
2023-01-23 02:31:24.624898: step: 880/529, loss: 0.00012369155592750758
2023-01-23 02:31:25.776835: step: 884/529, loss: 0.001563263009302318
2023-01-23 02:31:26.915946: step: 888/529, loss: 0.007650995627045631
2023-01-23 02:31:28.015655: step: 892/529, loss: 0.004489421844482422
2023-01-23 02:31:29.134770: step: 896/529, loss: 0.032956384122371674
2023-01-23 02:31:30.304853: step: 900/529, loss: 0.2825174331665039
2023-01-23 02:31:31.417825: step: 904/529, loss: 0.019931888207793236
2023-01-23 02:31:32.532061: step: 908/529, loss: 0.005643606185913086
2023-01-23 02:31:33.654280: step: 912/529, loss: 0.0011617183918133378
2023-01-23 02:31:34.772299: step: 916/529, loss: 0.0005805015680380166
2023-01-23 02:31:35.914715: step: 920/529, loss: 0.024542905390262604
2023-01-23 02:31:37.049568: step: 924/529, loss: 0.008698082529008389
2023-01-23 02:31:38.206775: step: 928/529, loss: 0.0010606765281409025
2023-01-23 02:31:39.333721: step: 932/529, loss: 0.0008480072137899697
2023-01-23 02:31:40.473465: step: 936/529, loss: 0.04472217708826065
2023-01-23 02:31:41.606873: step: 940/529, loss: 3.333091444801539e-05
2023-01-23 02:31:42.754562: step: 944/529, loss: 0.37310677766799927
2023-01-23 02:31:43.921948: step: 948/529, loss: 0.0001680374116403982
2023-01-23 02:31:45.073355: step: 952/529, loss: 0.004506015684455633
2023-01-23 02:31:46.206651: step: 956/529, loss: 0.020349882543087006
2023-01-23 02:31:47.359144: step: 960/529, loss: 0.0869840607047081
2023-01-23 02:31:48.505898: step: 964/529, loss: 0.18192100524902344
2023-01-23 02:31:49.654299: step: 968/529, loss: 0.0008014679187908769
2023-01-23 02:31:50.786342: step: 972/529, loss: 0.009219598956406116
2023-01-23 02:31:51.956396: step: 976/529, loss: 0.0006784438737668097
2023-01-23 02:31:53.104684: step: 980/529, loss: 0.06420622020959854
2023-01-23 02:31:54.230305: step: 984/529, loss: 0.010016536340117455
2023-01-23 02:31:55.369328: step: 988/529, loss: 0.019565392285585403
2023-01-23 02:31:56.516815: step: 992/529, loss: 0.012001228518784046
2023-01-23 02:31:57.679671: step: 996/529, loss: 0.00846109353005886
2023-01-23 02:31:58.854395: step: 1000/529, loss: 0.015276432037353516
2023-01-23 02:31:59.977324: step: 1004/529, loss: 0.0004455566522665322
2023-01-23 02:32:01.120436: step: 1008/529, loss: 0.0019134521717205644
2023-01-23 02:32:02.276367: step: 1012/529, loss: 0.09234543144702911
2023-01-23 02:32:03.465599: step: 1016/529, loss: 0.04788951948285103
2023-01-23 02:32:04.606492: step: 1020/529, loss: 0.025681018829345703
2023-01-23 02:32:05.748333: step: 1024/529, loss: 0.00454216031357646
2023-01-23 02:32:06.889938: step: 1028/529, loss: 0.008239269256591797
2023-01-23 02:32:08.024786: step: 1032/529, loss: 0.029389668256044388
2023-01-23 02:32:09.157474: step: 1036/529, loss: 0.003059768583625555
2023-01-23 02:32:10.302028: step: 1040/529, loss: 0.007839965634047985
2023-01-23 02:32:11.462853: step: 1044/529, loss: 0.03391628339886665
2023-01-23 02:32:12.595025: step: 1048/529, loss: 0.018726253882050514
2023-01-23 02:32:13.734684: step: 1052/529, loss: 0.00048160552978515625
2023-01-23 02:32:14.860752: step: 1056/529, loss: 0.0026079178787767887
2023-01-23 02:32:16.027501: step: 1060/529, loss: 0.011533737182617188
2023-01-23 02:32:17.137253: step: 1064/529, loss: 0.0816609188914299
2023-01-23 02:32:18.269010: step: 1068/529, loss: 0.010011862963438034
2023-01-23 02:32:19.447400: step: 1072/529, loss: 0.01912817917764187
2023-01-23 02:32:20.577100: step: 1076/529, loss: 0.003060912946239114
2023-01-23 02:32:21.714657: step: 1080/529, loss: 0.027090836316347122
2023-01-23 02:32:22.844254: step: 1084/529, loss: 0.00986633263528347
2023-01-23 02:32:24.005256: step: 1088/529, loss: 0.0008974075317382812
2023-01-23 02:32:25.155618: step: 1092/529, loss: 0.1181427463889122
2023-01-23 02:32:26.332938: step: 1096/529, loss: 0.0059570311568677425
2023-01-23 02:32:27.504150: step: 1100/529, loss: 0.01003274880349636
2023-01-23 02:32:28.664713: step: 1104/529, loss: 0.0009575844742357731
2023-01-23 02:32:29.795284: step: 1108/529, loss: 0.0012995719444006681
2023-01-23 02:32:30.926551: step: 1112/529, loss: 0.028218938037753105
2023-01-23 02:32:32.084924: step: 1116/529, loss: 0.01837439462542534
2023-01-23 02:32:33.221908: step: 1120/529, loss: 0.04990367963910103
2023-01-23 02:32:34.365391: step: 1124/529, loss: 0.03256044536828995
2023-01-23 02:32:35.497441: step: 1128/529, loss: 0.006563139148056507
2023-01-23 02:32:36.629809: step: 1132/529, loss: 0.008784675970673561
2023-01-23 02:32:37.788579: step: 1136/529, loss: 0.014457417652010918
2023-01-23 02:32:38.944723: step: 1140/529, loss: 0.01504430826753378
2023-01-23 02:32:40.074497: step: 1144/529, loss: 0.14821308851242065
2023-01-23 02:32:41.216954: step: 1148/529, loss: 0.11262250691652298
2023-01-23 02:32:42.353515: step: 1152/529, loss: 0.0006557464366778731
2023-01-23 02:32:43.523724: step: 1156/529, loss: 0.02716846391558647
2023-01-23 02:32:44.659549: step: 1160/529, loss: 0.0027498246636241674
2023-01-23 02:32:45.809697: step: 1164/529, loss: 0.004001808352768421
2023-01-23 02:32:46.933025: step: 1168/529, loss: 0.032067395746707916
2023-01-23 02:32:48.079943: step: 1172/529, loss: 0.023300744593143463
2023-01-23 02:32:49.227627: step: 1176/529, loss: 6.742477125953883e-05
2023-01-23 02:32:50.373855: step: 1180/529, loss: 0.004763603676110506
2023-01-23 02:32:51.515646: step: 1184/529, loss: 0.001458454062230885
2023-01-23 02:32:52.677752: step: 1188/529, loss: 0.00858993548899889
2023-01-23 02:32:53.800198: step: 1192/529, loss: 0.011379241943359375
2023-01-23 02:32:54.932297: step: 1196/529, loss: 0.004339694976806641
2023-01-23 02:32:56.046801: step: 1200/529, loss: 0.004261398687958717
2023-01-23 02:32:57.192859: step: 1204/529, loss: 0.001772975898347795
2023-01-23 02:32:58.318998: step: 1208/529, loss: 0.0007111548911780119
2023-01-23 02:32:59.450210: step: 1212/529, loss: 0.009340333752334118
2023-01-23 02:33:00.587904: step: 1216/529, loss: 0.01994762197136879
2023-01-23 02:33:01.724972: step: 1220/529, loss: 0.011604642495512962
2023-01-23 02:33:02.891487: step: 1224/529, loss: 0.031477831304073334
2023-01-23 02:33:04.001617: step: 1228/529, loss: 0.0039580343291163445
2023-01-23 02:33:05.173244: step: 1232/529, loss: 0.010865307413041592
2023-01-23 02:33:06.290481: step: 1236/529, loss: 0.04174976423382759
2023-01-23 02:33:07.415972: step: 1240/529, loss: 0.005619239993393421
2023-01-23 02:33:08.562925: step: 1244/529, loss: 0.001994228456169367
2023-01-23 02:33:09.665807: step: 1248/529, loss: 0.00259323138743639
2023-01-23 02:33:10.800352: step: 1252/529, loss: 0.047060441225767136
2023-01-23 02:33:11.972782: step: 1256/529, loss: 0.037805747240781784
2023-01-23 02:33:13.111301: step: 1260/529, loss: 0.02530183643102646
2023-01-23 02:33:14.256153: step: 1264/529, loss: 0.01933145523071289
2023-01-23 02:33:15.410319: step: 1268/529, loss: 0.1589651107788086
2023-01-23 02:33:16.586743: step: 1272/529, loss: 0.021904945373535156
2023-01-23 02:33:17.714826: step: 1276/529, loss: 0.034422971308231354
2023-01-23 02:33:18.859913: step: 1280/529, loss: 0.015123940072953701
2023-01-23 02:33:20.012363: step: 1284/529, loss: 0.055373094975948334
2023-01-23 02:33:21.132616: step: 1288/529, loss: 0.0031748772598803043
2023-01-23 02:33:22.246780: step: 1292/529, loss: 0.002681779908016324
2023-01-23 02:33:23.400235: step: 1296/529, loss: 0.013304234482347965
2023-01-23 02:33:24.525383: step: 1300/529, loss: 0.001902771065942943
2023-01-23 02:33:25.655587: step: 1304/529, loss: 0.0015788078308105469
2023-01-23 02:33:26.861312: step: 1308/529, loss: 0.5124379396438599
2023-01-23 02:33:28.015324: step: 1312/529, loss: 0.0031995773315429688
2023-01-23 02:33:29.175717: step: 1316/529, loss: 0.004222059156745672
2023-01-23 02:33:30.290356: step: 1320/529, loss: 0.0001715660182526335
2023-01-23 02:33:31.423987: step: 1324/529, loss: 0.04402942955493927
2023-01-23 02:33:32.561498: step: 1328/529, loss: 0.02411935292184353
2023-01-23 02:33:33.682257: step: 1332/529, loss: 0.0003262519894633442
2023-01-23 02:33:34.834102: step: 1336/529, loss: 0.058582305908203125
2023-01-23 02:33:35.989382: step: 1340/529, loss: 0.0057294368743896484
2023-01-23 02:33:37.146334: step: 1344/529, loss: 0.044020652770996094
2023-01-23 02:33:38.294467: step: 1348/529, loss: 0.0038466453552246094
2023-01-23 02:33:39.436342: step: 1352/529, loss: 6.456374831032008e-05
2023-01-23 02:33:40.558612: step: 1356/529, loss: 0.0012562752235680819
2023-01-23 02:33:41.700482: step: 1360/529, loss: 0.07114791870117188
2023-01-23 02:33:42.872094: step: 1364/529, loss: 0.03284282982349396
2023-01-23 02:33:43.993721: step: 1368/529, loss: 0.06797914206981659
2023-01-23 02:33:45.119883: step: 1372/529, loss: 0.0006488800281658769
2023-01-23 02:33:46.219598: step: 1376/529, loss: 0.045902520418167114
2023-01-23 02:33:47.359326: step: 1380/529, loss: 0.008991813287138939
2023-01-23 02:33:48.523552: step: 1384/529, loss: 0.00012581348710227758
2023-01-23 02:33:49.678890: step: 1388/529, loss: 0.048009779304265976
2023-01-23 02:33:50.859286: step: 1392/529, loss: 0.0002168655482819304
2023-01-23 02:33:51.987473: step: 1396/529, loss: 0.05149250105023384
2023-01-23 02:33:53.125381: step: 1400/529, loss: 0.03655543178319931
2023-01-23 02:33:54.252037: step: 1404/529, loss: 0.011797333136200905
2023-01-23 02:33:55.397650: step: 1408/529, loss: 0.0029134750366210938
2023-01-23 02:33:56.569110: step: 1412/529, loss: 0.024343110620975494
2023-01-23 02:33:57.744818: step: 1416/529, loss: 0.004498195834457874
2023-01-23 02:33:58.882659: step: 1420/529, loss: 0.00016536115435883403
2023-01-23 02:34:00.021708: step: 1424/529, loss: 0.001154828118160367
2023-01-23 02:34:01.151148: step: 1428/529, loss: 0.0027225492522120476
2023-01-23 02:34:02.303120: step: 1432/529, loss: 0.03768548741936684
2023-01-23 02:34:03.447639: step: 1436/529, loss: 0.0017038345104083419
2023-01-23 02:34:04.576863: step: 1440/529, loss: 0.15786190330982208
2023-01-23 02:34:05.715371: step: 1444/529, loss: 0.0014646649360656738
2023-01-23 02:34:06.851844: step: 1448/529, loss: 0.048471398651599884
2023-01-23 02:34:07.996092: step: 1452/529, loss: 0.018179655075073242
2023-01-23 02:34:09.155340: step: 1456/529, loss: 0.0007168054580688477
2023-01-23 02:34:10.281221: step: 1460/529, loss: 0.0009873866802081466
2023-01-23 02:34:11.417477: step: 1464/529, loss: 0.020849037915468216
2023-01-23 02:34:12.599836: step: 1468/529, loss: 0.00379009242169559
2023-01-23 02:34:13.732987: step: 1472/529, loss: 0.007500267121940851
2023-01-23 02:34:14.869035: step: 1476/529, loss: 0.013592339120805264
2023-01-23 02:34:16.015430: step: 1480/529, loss: 0.018526267260313034
2023-01-23 02:34:17.138562: step: 1484/529, loss: 0.001071929931640625
2023-01-23 02:34:18.287668: step: 1488/529, loss: 0.04881887510418892
2023-01-23 02:34:19.406618: step: 1492/529, loss: 0.001932763960212469
2023-01-23 02:34:20.519481: step: 1496/529, loss: 0.00630607595667243
2023-01-23 02:34:21.664330: step: 1500/529, loss: 0.0009374618530273438
2023-01-23 02:34:22.793735: step: 1504/529, loss: 0.02255268208682537
2023-01-23 02:34:23.900279: step: 1508/529, loss: 0.0019861222244799137
2023-01-23 02:34:25.031098: step: 1512/529, loss: 0.028542710468173027
2023-01-23 02:34:26.162011: step: 1516/529, loss: 0.0031071186531335115
2023-01-23 02:34:27.319075: step: 1520/529, loss: 0.008000754751265049
2023-01-23 02:34:28.444620: step: 1524/529, loss: 0.053278446197509766
2023-01-23 02:34:29.577160: step: 1528/529, loss: 0.004903316497802734
2023-01-23 02:34:30.734176: step: 1532/529, loss: 0.03112621419131756
2023-01-23 02:34:31.905261: step: 1536/529, loss: 0.14855670928955078
2023-01-23 02:34:33.050090: step: 1540/529, loss: 0.004803466610610485
2023-01-23 02:34:34.173056: step: 1544/529, loss: 0.001744222710840404
2023-01-23 02:34:35.308931: step: 1548/529, loss: 0.0007801532628946006
2023-01-23 02:34:36.467730: step: 1552/529, loss: 0.0017047881847247481
2023-01-23 02:34:37.606189: step: 1556/529, loss: 0.020837783813476562
2023-01-23 02:34:38.759454: step: 1560/529, loss: 0.0008647918584756553
2023-01-23 02:34:39.905613: step: 1564/529, loss: 0.012898826971650124
2023-01-23 02:34:41.027123: step: 1568/529, loss: 0.005711174104362726
2023-01-23 02:34:42.193920: step: 1572/529, loss: 0.006619644351303577
2023-01-23 02:34:43.362798: step: 1576/529, loss: 0.011004924774169922
2023-01-23 02:34:44.502459: step: 1580/529, loss: 0.07417793571949005
2023-01-23 02:34:45.663271: step: 1584/529, loss: 0.009404182434082031
2023-01-23 02:34:46.844159: step: 1588/529, loss: 0.01302499882876873
2023-01-23 02:34:47.977544: step: 1592/529, loss: 0.009563923813402653
2023-01-23 02:34:49.097751: step: 1596/529, loss: 0.06909974664449692
2023-01-23 02:34:50.228979: step: 1600/529, loss: 0.006190919782966375
2023-01-23 02:34:51.381485: step: 1604/529, loss: 0.00837564468383789
2023-01-23 02:34:52.558893: step: 1608/529, loss: 0.0008972167852334678
2023-01-23 02:34:53.693517: step: 1612/529, loss: 0.008368909358978271
2023-01-23 02:34:54.891594: step: 1616/529, loss: 0.0001574277994222939
2023-01-23 02:34:56.016615: step: 1620/529, loss: 0.0008803367963992059
2023-01-23 02:34:57.159809: step: 1624/529, loss: 0.013638115487992764
2023-01-23 02:34:58.267139: step: 1628/529, loss: 0.007931900210678577
2023-01-23 02:34:59.414940: step: 1632/529, loss: 0.032462313771247864
2023-01-23 02:35:00.588489: step: 1636/529, loss: 0.01355667132884264
2023-01-23 02:35:01.724679: step: 1640/529, loss: 0.0021865845192223787
2023-01-23 02:35:02.859206: step: 1644/529, loss: 0.031923867762088776
2023-01-23 02:35:04.004147: step: 1648/529, loss: 0.0026908875443041325
2023-01-23 02:35:05.146686: step: 1652/529, loss: 3.15189354296308e-05
2023-01-23 02:35:06.293077: step: 1656/529, loss: 0.009342193603515625
2023-01-23 02:35:07.442045: step: 1660/529, loss: 0.06308746337890625
2023-01-23 02:35:08.579129: step: 1664/529, loss: 0.004986322019249201
2023-01-23 02:35:09.733552: step: 1668/529, loss: 0.03224611654877663
2023-01-23 02:35:10.868712: step: 1672/529, loss: 0.014443683438003063
2023-01-23 02:35:12.007772: step: 1676/529, loss: 2.8705597287626006e-05
2023-01-23 02:35:13.164655: step: 1680/529, loss: 0.007191276643425226
2023-01-23 02:35:14.296320: step: 1684/529, loss: 0.02531290054321289
2023-01-23 02:35:15.415825: step: 1688/529, loss: 0.0535762794315815
2023-01-23 02:35:16.590813: step: 1692/529, loss: 0.018215704709291458
2023-01-23 02:35:17.712394: step: 1696/529, loss: 0.03373556211590767
2023-01-23 02:35:18.862368: step: 1700/529, loss: 0.059294700622558594
2023-01-23 02:35:20.003839: step: 1704/529, loss: 0.0002349853457417339
2023-01-23 02:35:21.131886: step: 1708/529, loss: 0.053058624267578125
2023-01-23 02:35:22.277781: step: 1712/529, loss: 0.07703609764575958
2023-01-23 02:35:23.419860: step: 1716/529, loss: 0.00021595954603981227
2023-01-23 02:35:24.539256: step: 1720/529, loss: 0.00013513564772438258
2023-01-23 02:35:25.663205: step: 1724/529, loss: 0.2744404077529907
2023-01-23 02:35:26.799758: step: 1728/529, loss: 0.038552094250917435
2023-01-23 02:35:27.946970: step: 1732/529, loss: 0.00014696121797896922
2023-01-23 02:35:29.085334: step: 1736/529, loss: 0.00348587054759264
2023-01-23 02:35:30.245672: step: 1740/529, loss: 0.021732330322265625
2023-01-23 02:35:31.370229: step: 1744/529, loss: 0.034837912768125534
2023-01-23 02:35:32.520602: step: 1748/529, loss: 0.004411506932228804
2023-01-23 02:35:33.660585: step: 1752/529, loss: 0.029863454401493073
2023-01-23 02:35:34.804226: step: 1756/529, loss: 0.013660240918397903
2023-01-23 02:35:35.933128: step: 1760/529, loss: 0.0025158883072435856
2023-01-23 02:35:37.089771: step: 1764/529, loss: 0.022594833746552467
2023-01-23 02:35:38.243085: step: 1768/529, loss: 0.006878662388771772
2023-01-23 02:35:39.353500: step: 1772/529, loss: 0.06906967610120773
2023-01-23 02:35:40.497433: step: 1776/529, loss: 0.08014822006225586
2023-01-23 02:35:41.657167: step: 1780/529, loss: 0.017841434106230736
2023-01-23 02:35:42.778434: step: 1784/529, loss: 0.005183410830795765
2023-01-23 02:35:43.910477: step: 1788/529, loss: 0.006915092468261719
2023-01-23 02:35:45.045913: step: 1792/529, loss: 0.0016990662552416325
2023-01-23 02:35:46.208621: step: 1796/529, loss: 0.001139736152254045
2023-01-23 02:35:47.358450: step: 1800/529, loss: 0.03249001502990723
2023-01-23 02:35:48.527459: step: 1804/529, loss: 0.04183673858642578
2023-01-23 02:35:49.686802: step: 1808/529, loss: 0.023811722174286842
2023-01-23 02:35:50.799774: step: 1812/529, loss: 0.01132826879620552
2023-01-23 02:35:51.927121: step: 1816/529, loss: 0.020188618451356888
2023-01-23 02:35:53.107965: step: 1820/529, loss: 0.01529989205300808
2023-01-23 02:35:54.258848: step: 1824/529, loss: 0.0002399444638285786
2023-01-23 02:35:55.396766: step: 1828/529, loss: 0.0646999403834343
2023-01-23 02:35:56.530323: step: 1832/529, loss: 0.0010093450546264648
2023-01-23 02:35:57.649286: step: 1836/529, loss: 0.005635166075080633
2023-01-23 02:35:58.805871: step: 1840/529, loss: 0.04038562998175621
2023-01-23 02:35:59.960269: step: 1844/529, loss: 0.0016530990833416581
2023-01-23 02:36:01.067498: step: 1848/529, loss: 0.08726216107606888
2023-01-23 02:36:02.236086: step: 1852/529, loss: 0.008583259768784046
2023-01-23 02:36:03.395108: step: 1856/529, loss: 0.029050350189208984
2023-01-23 02:36:04.537372: step: 1860/529, loss: 0.00017480850510764867
2023-01-23 02:36:05.661280: step: 1864/529, loss: 0.0016067505348473787
2023-01-23 02:36:06.809739: step: 1868/529, loss: 0.02288360521197319
2023-01-23 02:36:07.943057: step: 1872/529, loss: 0.004376411437988281
2023-01-23 02:36:09.074778: step: 1876/529, loss: 0.0039520263671875
2023-01-23 02:36:10.219788: step: 1880/529, loss: 0.005800056271255016
2023-01-23 02:36:11.352781: step: 1884/529, loss: 0.0042896270751953125
2023-01-23 02:36:12.470101: step: 1888/529, loss: 0.007916641421616077
2023-01-23 02:36:13.641304: step: 1892/529, loss: 0.027043821290135384
2023-01-23 02:36:14.794042: step: 1896/529, loss: 0.033438730984926224
2023-01-23 02:36:15.929593: step: 1900/529, loss: 0.02346782758831978
2023-01-23 02:36:17.059527: step: 1904/529, loss: 0.0004980087396688759
2023-01-23 02:36:18.207971: step: 1908/529, loss: 0.027830936014652252
2023-01-23 02:36:19.352572: step: 1912/529, loss: 0.003227424807846546
2023-01-23 02:36:20.500876: step: 1916/529, loss: 0.1706605702638626
2023-01-23 02:36:21.621836: step: 1920/529, loss: 0.004867172334343195
2023-01-23 02:36:22.750835: step: 1924/529, loss: 0.04011125490069389
2023-01-23 02:36:23.925679: step: 1928/529, loss: 0.032246481627225876
2023-01-23 02:36:25.069390: step: 1932/529, loss: 0.002513313200324774
2023-01-23 02:36:26.202634: step: 1936/529, loss: 0.0019401074387133121
2023-01-23 02:36:27.341528: step: 1940/529, loss: 0.009066772647202015
2023-01-23 02:36:28.477494: step: 1944/529, loss: 0.8269193768501282
2023-01-23 02:36:29.624306: step: 1948/529, loss: 0.04860830307006836
2023-01-23 02:36:30.742573: step: 1952/529, loss: 0.001714420272037387
2023-01-23 02:36:31.879438: step: 1956/529, loss: 0.10605239868164062
2023-01-23 02:36:33.026530: step: 1960/529, loss: 0.045519448816776276
2023-01-23 02:36:34.164502: step: 1964/529, loss: 0.008381461724638939
2023-01-23 02:36:35.286969: step: 1968/529, loss: 0.0006935119745321572
2023-01-23 02:36:36.446954: step: 1972/529, loss: 0.03565178066492081
2023-01-23 02:36:37.582240: step: 1976/529, loss: 0.01486358605325222
2023-01-23 02:36:38.708408: step: 1980/529, loss: 0.019589710980653763
2023-01-23 02:36:39.831622: step: 1984/529, loss: 0.05921641364693642
2023-01-23 02:36:40.954394: step: 1988/529, loss: 0.012999439612030983
2023-01-23 02:36:42.088581: step: 1992/529, loss: 0.004659461788833141
2023-01-23 02:36:43.220753: step: 1996/529, loss: 0.000274658203125
2023-01-23 02:36:44.355048: step: 2000/529, loss: 0.021384811028838158
2023-01-23 02:36:45.506510: step: 2004/529, loss: 0.012132071889936924
2023-01-23 02:36:46.656410: step: 2008/529, loss: 0.004119968507438898
2023-01-23 02:36:47.803517: step: 2012/529, loss: 0.014011621475219727
2023-01-23 02:36:48.948258: step: 2016/529, loss: 0.008139420300722122
2023-01-23 02:36:50.110855: step: 2020/529, loss: 0.004028892610222101
2023-01-23 02:36:51.263194: step: 2024/529, loss: 0.01865110546350479
2023-01-23 02:36:52.378964: step: 2028/529, loss: 0.008967304602265358
2023-01-23 02:36:53.557335: step: 2032/529, loss: 0.00047512055607512593
2023-01-23 02:36:54.714634: step: 2036/529, loss: 0.0005553245428018272
2023-01-23 02:36:55.851384: step: 2040/529, loss: 0.015929032117128372
2023-01-23 02:36:57.006439: step: 2044/529, loss: 0.00013046264939475805
2023-01-23 02:36:58.146310: step: 2048/529, loss: 0.004607581999152899
2023-01-23 02:36:59.274283: step: 2052/529, loss: 0.026881981641054153
2023-01-23 02:37:00.426466: step: 2056/529, loss: 0.014725113287568092
2023-01-23 02:37:01.552750: step: 2060/529, loss: 0.04262485355138779
2023-01-23 02:37:02.732130: step: 2064/529, loss: 0.019208144396543503
2023-01-23 02:37:03.875496: step: 2068/529, loss: 0.0010837555164471269
2023-01-23 02:37:05.011401: step: 2072/529, loss: 0.027039146050810814
2023-01-23 02:37:06.176127: step: 2076/529, loss: 0.00471839914098382
2023-01-23 02:37:07.336126: step: 2080/529, loss: 0.00048236845759674907
2023-01-23 02:37:08.492887: step: 2084/529, loss: 0.003652381943538785
2023-01-23 02:37:09.650801: step: 2088/529, loss: 0.039153292775154114
2023-01-23 02:37:10.804161: step: 2092/529, loss: 0.025563431903719902
2023-01-23 02:37:11.921097: step: 2096/529, loss: 0.005202865693718195
2023-01-23 02:37:13.056845: step: 2100/529, loss: 0.0768117904663086
2023-01-23 02:37:14.201641: step: 2104/529, loss: 0.036226749420166016
2023-01-23 02:37:15.361675: step: 2108/529, loss: 0.050469204783439636
2023-01-23 02:37:16.536790: step: 2112/529, loss: 0.017507268115878105
2023-01-23 02:37:17.657765: step: 2116/529, loss: 0.0002964019658975303
==================================================
Loss: 0.027
--------------------
Dev: {'event': {'p': 0.6127659574468085, 'r': 0.7669773635153129, 'f1': 0.6812536960378475}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6105165193113076, 'r': 0.7601390498261877, 'f1': 0.6771612903225807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.6, 'r': 0.8888888888888888, 'f1': 0.7164179104477612}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.6153846153846154, 'r': 0.5079365079365079, 'f1': 0.5565217391304348}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.4358974358974359, 'r': 0.4722222222222222, 'f1': 0.45333333333333337}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5733722060252673, 'r': 0.7856191744340879, 'f1': 0.6629213483146068}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.5876334519572953, 'r': 0.7653534183082271, 'f1': 0.6648213387015602}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5365853658536586, 'r': 0.6111111111111112, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:37:59.290077: step: 4/529, loss: 0.006241417024284601
2023-01-23 02:38:00.419146: step: 8/529, loss: 0.0061032772064208984
2023-01-23 02:38:01.542562: step: 12/529, loss: 0.03459692373871803
2023-01-23 02:38:02.654730: step: 16/529, loss: 0.003876555012539029
2023-01-23 02:38:03.810249: step: 20/529, loss: 0.0016886235680431128
2023-01-23 02:38:04.948603: step: 24/529, loss: 0.0014074802165850997
2023-01-23 02:38:06.072835: step: 28/529, loss: 0.005291938781738281
2023-01-23 02:38:07.195019: step: 32/529, loss: 0.00221672048792243
2023-01-23 02:38:08.326869: step: 36/529, loss: 0.009729958139359951
2023-01-23 02:38:09.474557: step: 40/529, loss: 0.005330181214958429
2023-01-23 02:38:10.606661: step: 44/529, loss: 0.01841764524579048
2023-01-23 02:38:11.726208: step: 48/529, loss: 0.006722688674926758
2023-01-23 02:38:12.930018: step: 52/529, loss: 0.06309223175048828
2023-01-23 02:38:14.066084: step: 56/529, loss: 0.001050758408382535
2023-01-23 02:38:15.194960: step: 60/529, loss: 0.00201759347692132
2023-01-23 02:38:16.339180: step: 64/529, loss: 0.0302263256162405
2023-01-23 02:38:17.480997: step: 68/529, loss: 0.002188778016716242
2023-01-23 02:38:18.621572: step: 72/529, loss: 0.0032983780838549137
2023-01-23 02:38:19.763442: step: 76/529, loss: 0.00020647048950195312
2023-01-23 02:38:20.895488: step: 80/529, loss: 0.00017786026000976562
2023-01-23 02:38:22.039548: step: 84/529, loss: 0.008201408199965954
2023-01-23 02:38:23.156801: step: 88/529, loss: 0.030338671058416367
2023-01-23 02:38:24.258733: step: 92/529, loss: 0.03889918327331543
2023-01-23 02:38:25.377556: step: 96/529, loss: 0.01790752448141575
2023-01-23 02:38:26.537771: step: 100/529, loss: 0.005992889404296875
2023-01-23 02:38:27.711066: step: 104/529, loss: 0.010418891906738281
2023-01-23 02:38:28.815297: step: 108/529, loss: 0.007765770424157381
2023-01-23 02:38:29.978970: step: 112/529, loss: 0.008222723379731178
2023-01-23 02:38:31.120236: step: 116/529, loss: 0.0582612045109272
2023-01-23 02:38:32.274081: step: 120/529, loss: 0.3211834132671356
2023-01-23 02:38:33.414921: step: 124/529, loss: 0.019330216571688652
2023-01-23 02:38:34.573519: step: 128/529, loss: 0.00024390222097281367
2023-01-23 02:38:35.729871: step: 132/529, loss: 0.026429081335663795
2023-01-23 02:38:36.871905: step: 136/529, loss: 0.010874176397919655
2023-01-23 02:38:38.028468: step: 140/529, loss: 0.0034130574204027653
2023-01-23 02:38:39.189678: step: 144/529, loss: 0.0002536773681640625
2023-01-23 02:38:40.316135: step: 148/529, loss: 0.00011529921903274953
2023-01-23 02:38:41.485557: step: 152/529, loss: 0.015891456976532936
2023-01-23 02:38:42.628445: step: 156/529, loss: 1.773834264895413e-05
2023-01-23 02:38:43.758406: step: 160/529, loss: 0.0013849259121343493
2023-01-23 02:38:44.871579: step: 164/529, loss: 0.0010476828319951892
2023-01-23 02:38:46.035119: step: 168/529, loss: 0.0007966518169268966
2023-01-23 02:38:47.203359: step: 172/529, loss: 0.18595227599143982
2023-01-23 02:38:48.335075: step: 176/529, loss: 0.009113120846450329
2023-01-23 02:38:49.475291: step: 180/529, loss: 0.013454628176987171
2023-01-23 02:38:50.604028: step: 184/529, loss: 0.04678931459784508
2023-01-23 02:38:51.740381: step: 188/529, loss: 0.0010718345874920487
2023-01-23 02:38:52.905858: step: 192/529, loss: 0.02949066273868084
2023-01-23 02:38:54.046253: step: 196/529, loss: 0.11929173767566681
2023-01-23 02:38:55.174648: step: 200/529, loss: 3.147125244140625e-05
2023-01-23 02:38:56.303354: step: 204/529, loss: 0.02879619598388672
2023-01-23 02:38:57.435645: step: 208/529, loss: 0.000569248222745955
2023-01-23 02:38:58.545964: step: 212/529, loss: 0.008686209097504616
2023-01-23 02:38:59.687823: step: 216/529, loss: 0.0018167495727539062
2023-01-23 02:39:00.827326: step: 220/529, loss: 0.008172071538865566
2023-01-23 02:39:01.967124: step: 224/529, loss: 0.1416267305612564
2023-01-23 02:39:03.092445: step: 228/529, loss: 0.018035221844911575
2023-01-23 02:39:04.236356: step: 232/529, loss: 0.006991481874138117
2023-01-23 02:39:05.342672: step: 236/529, loss: 0.004014301113784313
2023-01-23 02:39:06.472650: step: 240/529, loss: 0.0028782845474779606
2023-01-23 02:39:07.603749: step: 244/529, loss: 0.035027600824832916
2023-01-23 02:39:08.737369: step: 248/529, loss: 0.0024260522332042456
2023-01-23 02:39:09.858303: step: 252/529, loss: 0.001992130186408758
2023-01-23 02:39:10.989782: step: 256/529, loss: 0.002309418050572276
2023-01-23 02:39:12.129410: step: 260/529, loss: 0.00019178391085006297
2023-01-23 02:39:13.264840: step: 264/529, loss: 0.001349115394987166
2023-01-23 02:39:14.393496: step: 268/529, loss: 0.013648604974150658
2023-01-23 02:39:15.557834: step: 272/529, loss: 0.018121814355254173
2023-01-23 02:39:16.739852: step: 276/529, loss: 0.02869129180908203
2023-01-23 02:39:17.908670: step: 280/529, loss: 0.0020410537254065275
2023-01-23 02:39:19.030928: step: 284/529, loss: 0.005939770024269819
2023-01-23 02:39:20.264788: step: 288/529, loss: 0.03592319414019585
2023-01-23 02:39:21.447997: step: 292/529, loss: 0.023594284430146217
2023-01-23 02:39:22.584166: step: 296/529, loss: 0.014547920785844326
2023-01-23 02:39:23.731391: step: 300/529, loss: 0.006482887081801891
2023-01-23 02:39:24.878630: step: 304/529, loss: 0.00036687852116301656
2023-01-23 02:39:26.024560: step: 308/529, loss: 0.00682144146412611
2023-01-23 02:39:27.147011: step: 312/529, loss: 0.009296512231230736
2023-01-23 02:39:28.292692: step: 316/529, loss: 0.031868934631347656
2023-01-23 02:39:29.448877: step: 320/529, loss: 0.005333900451660156
2023-01-23 02:39:30.550854: step: 324/529, loss: 0.0007100105285644531
2023-01-23 02:39:31.703277: step: 328/529, loss: 0.010809993371367455
2023-01-23 02:39:32.835341: step: 332/529, loss: 0.0008709907415322959
2023-01-23 02:39:33.989188: step: 336/529, loss: 0.04710130766034126
2023-01-23 02:39:35.172835: step: 340/529, loss: 0.0024326324928551912
2023-01-23 02:39:36.338360: step: 344/529, loss: 0.003944873809814453
2023-01-23 02:39:37.519589: step: 348/529, loss: 0.04175719991326332
2023-01-23 02:39:38.662429: step: 352/529, loss: 0.019383490085601807
2023-01-23 02:39:39.808338: step: 356/529, loss: 0.005240630824118853
2023-01-23 02:39:40.945139: step: 360/529, loss: 0.006787300109863281
2023-01-23 02:39:42.047723: step: 364/529, loss: 0.005274200811982155
2023-01-23 02:39:43.178185: step: 368/529, loss: 0.0012506485218182206
2023-01-23 02:39:44.350763: step: 372/529, loss: 0.024988461285829544
2023-01-23 02:39:45.497475: step: 376/529, loss: 0.006541252136230469
2023-01-23 02:39:46.621559: step: 380/529, loss: 0.008476734161376953
2023-01-23 02:39:47.747211: step: 384/529, loss: 0.0029168606270104647
2023-01-23 02:39:48.861189: step: 388/529, loss: 0.010167121887207031
2023-01-23 02:39:50.015218: step: 392/529, loss: 0.05649566650390625
2023-01-23 02:39:51.163019: step: 396/529, loss: 0.0014757156604900956
2023-01-23 02:39:52.308853: step: 400/529, loss: 2.212524486822076e-05
2023-01-23 02:39:53.438347: step: 404/529, loss: 0.026470374315977097
2023-01-23 02:39:54.597295: step: 408/529, loss: 0.001718807267025113
2023-01-23 02:39:55.741033: step: 412/529, loss: 0.02577686496078968
2023-01-23 02:39:56.886846: step: 416/529, loss: 0.011780737899243832
2023-01-23 02:39:58.041603: step: 420/529, loss: 0.004677534103393555
2023-01-23 02:39:59.187249: step: 424/529, loss: 0.4459524154663086
2023-01-23 02:40:00.315552: step: 428/529, loss: 0.01160652656108141
2023-01-23 02:40:01.481558: step: 432/529, loss: 0.004642319865524769
2023-01-23 02:40:02.638261: step: 436/529, loss: 0.037483979016542435
2023-01-23 02:40:03.772747: step: 440/529, loss: 0.012015819549560547
2023-01-23 02:40:04.902439: step: 444/529, loss: 0.018959617242217064
2023-01-23 02:40:06.049382: step: 448/529, loss: 0.0028689384926110506
2023-01-23 02:40:07.203919: step: 452/529, loss: 0.00026264190091751516
2023-01-23 02:40:08.325459: step: 456/529, loss: 0.01378555316478014
2023-01-23 02:40:09.463348: step: 460/529, loss: 0.02205219306051731
2023-01-23 02:40:10.659572: step: 464/529, loss: 0.5884515643119812
2023-01-23 02:40:11.803417: step: 468/529, loss: 0.07545318454504013
2023-01-23 02:40:12.971885: step: 472/529, loss: 0.007654380984604359
2023-01-23 02:40:14.107125: step: 476/529, loss: 0.0004050426068715751
2023-01-23 02:40:15.272868: step: 480/529, loss: 0.04496908187866211
2023-01-23 02:40:16.409028: step: 484/529, loss: 0.07120780646800995
2023-01-23 02:40:17.529030: step: 488/529, loss: 0.0014478684170171618
2023-01-23 02:40:18.662850: step: 492/529, loss: 0.01540532149374485
2023-01-23 02:40:19.789865: step: 496/529, loss: 0.03237638622522354
2023-01-23 02:40:20.948047: step: 500/529, loss: 0.027593422681093216
2023-01-23 02:40:22.073202: step: 504/529, loss: 0.06308670341968536
2023-01-23 02:40:23.205199: step: 508/529, loss: 0.02149190939962864
2023-01-23 02:40:24.375974: step: 512/529, loss: 0.02747969701886177
2023-01-23 02:40:25.515234: step: 516/529, loss: 0.008552360348403454
2023-01-23 02:40:26.648708: step: 520/529, loss: 0.0007078170892782509
2023-01-23 02:40:27.810918: step: 524/529, loss: 0.0004834175342693925
2023-01-23 02:40:28.949389: step: 528/529, loss: 0.000329864036757499
2023-01-23 02:40:30.065102: step: 532/529, loss: 0.0024454593658447266
2023-01-23 02:40:31.217892: step: 536/529, loss: 0.02578124962747097
2023-01-23 02:40:32.384902: step: 540/529, loss: 0.08916592597961426
2023-01-23 02:40:33.511583: step: 544/529, loss: 0.003316497663035989
2023-01-23 02:40:34.636678: step: 548/529, loss: 0.037149809300899506
2023-01-23 02:40:35.773790: step: 552/529, loss: 0.016155825927853584
2023-01-23 02:40:36.874762: step: 556/529, loss: 0.003591919085010886
2023-01-23 02:40:38.044449: step: 560/529, loss: 0.010695266537368298
2023-01-23 02:40:39.197582: step: 564/529, loss: 0.0005551338545046747
2023-01-23 02:40:40.344494: step: 568/529, loss: 0.06317882984876633
2023-01-23 02:40:41.466158: step: 572/529, loss: 0.06723079830408096
2023-01-23 02:40:42.607527: step: 576/529, loss: 0.04876995086669922
2023-01-23 02:40:43.784984: step: 580/529, loss: 0.001155090401880443
2023-01-23 02:40:44.911549: step: 584/529, loss: 0.005017089657485485
2023-01-23 02:40:46.058465: step: 588/529, loss: 0.026406003162264824
2023-01-23 02:40:47.180777: step: 592/529, loss: 0.023432351648807526
2023-01-23 02:40:48.272866: step: 596/529, loss: 0.00027790068998001516
2023-01-23 02:40:49.422973: step: 600/529, loss: 0.011398602277040482
2023-01-23 02:40:50.556450: step: 604/529, loss: 0.0027114988770335913
2023-01-23 02:40:51.685388: step: 608/529, loss: 0.030648041516542435
2023-01-23 02:40:52.813345: step: 612/529, loss: 0.0653233528137207
2023-01-23 02:40:53.960674: step: 616/529, loss: 0.0022360801231116056
2023-01-23 02:40:55.076987: step: 620/529, loss: 0.06946296244859695
2023-01-23 02:40:56.219885: step: 624/529, loss: 0.0036852839402854443
2023-01-23 02:40:57.372883: step: 628/529, loss: 0.030469607561826706
2023-01-23 02:40:58.525442: step: 632/529, loss: 0.00042304996168240905
2023-01-23 02:40:59.678609: step: 636/529, loss: 0.010606765747070312
2023-01-23 02:41:00.822261: step: 640/529, loss: 0.005016613285988569
2023-01-23 02:41:01.951035: step: 644/529, loss: 0.0085289953276515
2023-01-23 02:41:03.088819: step: 648/529, loss: 0.04410257190465927
2023-01-23 02:41:04.257685: step: 652/529, loss: 0.018637657165527344
2023-01-23 02:41:05.432286: step: 656/529, loss: 0.028317928314208984
2023-01-23 02:41:06.586928: step: 660/529, loss: 0.0003578185860533267
2023-01-23 02:41:07.762484: step: 664/529, loss: 0.03711872175335884
2023-01-23 02:41:08.894502: step: 668/529, loss: 0.00867323949933052
2023-01-23 02:41:10.053802: step: 672/529, loss: 0.0015787124866619706
2023-01-23 02:41:11.189051: step: 676/529, loss: 0.0031977654434740543
2023-01-23 02:41:12.346734: step: 680/529, loss: 0.04297066107392311
2023-01-23 02:41:13.487874: step: 684/529, loss: 7.22885160939768e-05
2023-01-23 02:41:14.630992: step: 688/529, loss: 0.0002624511835165322
2023-01-23 02:41:15.762560: step: 692/529, loss: 0.024991370737552643
2023-01-23 02:41:16.906361: step: 696/529, loss: 0.07466640323400497
2023-01-23 02:41:18.048374: step: 700/529, loss: 0.0002079010009765625
2023-01-23 02:41:19.178946: step: 704/529, loss: 0.000599384366068989
2023-01-23 02:41:20.342254: step: 708/529, loss: 0.0005156517145223916
2023-01-23 02:41:21.509656: step: 712/529, loss: 0.03506955876946449
2023-01-23 02:41:22.672525: step: 716/529, loss: -1.602172778802924e-05
2023-01-23 02:41:23.819236: step: 720/529, loss: 5.3215029765851796e-05
2023-01-23 02:41:24.944962: step: 724/529, loss: 0.019298363476991653
2023-01-23 02:41:26.090306: step: 728/529, loss: 0.016275787726044655
2023-01-23 02:41:27.225602: step: 732/529, loss: 0.006672763731330633
2023-01-23 02:41:28.362611: step: 736/529, loss: 0.0016570091247558594
2023-01-23 02:41:29.489644: step: 740/529, loss: 0.018860816955566406
2023-01-23 02:41:30.636359: step: 744/529, loss: 0.011258983984589577
2023-01-23 02:41:31.790932: step: 748/529, loss: 0.004781436640769243
2023-01-23 02:41:32.956000: step: 752/529, loss: 0.00012254714965820312
2023-01-23 02:41:34.087944: step: 756/529, loss: 0.019025038927793503
2023-01-23 02:41:35.225048: step: 760/529, loss: 0.03364739567041397
2023-01-23 02:41:36.353026: step: 764/529, loss: 0.00016317368135787547
2023-01-23 02:41:37.495225: step: 768/529, loss: 0.015932131558656693
2023-01-23 02:41:38.630626: step: 772/529, loss: 0.03281116485595703
2023-01-23 02:41:39.783626: step: 776/529, loss: 0.014200402423739433
2023-01-23 02:41:40.914577: step: 780/529, loss: 0.013457298278808594
2023-01-23 02:41:42.037542: step: 784/529, loss: 0.0076507567428052425
2023-01-23 02:41:43.188894: step: 788/529, loss: 0.08912134170532227
2023-01-23 02:41:44.339999: step: 792/529, loss: 0.04129061847925186
2023-01-23 02:41:45.515190: step: 796/529, loss: 0.005247974302619696
2023-01-23 02:41:46.652001: step: 800/529, loss: 0.0007427216041833162
2023-01-23 02:41:47.797897: step: 804/529, loss: 0.031065750867128372
2023-01-23 02:41:48.943314: step: 808/529, loss: 0.00010566711716819555
2023-01-23 02:41:50.056952: step: 812/529, loss: 0.005059433169662952
2023-01-23 02:41:51.198794: step: 816/529, loss: 0.7163230776786804
2023-01-23 02:41:52.351237: step: 820/529, loss: 0.09655914455652237
2023-01-23 02:41:53.478240: step: 824/529, loss: 0.016176700592041016
2023-01-23 02:41:54.581023: step: 828/529, loss: 0.011141777038574219
2023-01-23 02:41:55.737718: step: 832/529, loss: 0.004449653439223766
2023-01-23 02:41:56.878603: step: 836/529, loss: 0.007259320933371782
2023-01-23 02:41:58.040064: step: 840/529, loss: 0.026501012966036797
2023-01-23 02:41:59.194986: step: 844/529, loss: 0.00048131943913176656
2023-01-23 02:42:00.316674: step: 848/529, loss: 0.24736252427101135
2023-01-23 02:42:01.460735: step: 852/529, loss: 0.0014541626442223787
2023-01-23 02:42:02.608252: step: 856/529, loss: 0.0007814407581463456
2023-01-23 02:42:03.765852: step: 860/529, loss: 0.031156539916992188
2023-01-23 02:42:04.925324: step: 864/529, loss: 0.03480873256921768
2023-01-23 02:42:06.050924: step: 868/529, loss: 0.1090371161699295
2023-01-23 02:42:07.194316: step: 872/529, loss: 0.0026908875443041325
2023-01-23 02:42:08.355244: step: 876/529, loss: 0.05614016205072403
2023-01-23 02:42:09.457048: step: 880/529, loss: 0.012283611111342907
2023-01-23 02:42:10.601489: step: 884/529, loss: 0.003698110580444336
2023-01-23 02:42:11.731313: step: 888/529, loss: 0.009189414791762829
2023-01-23 02:42:12.885943: step: 892/529, loss: 0.06579875946044922
2023-01-23 02:42:14.028253: step: 896/529, loss: 0.042984578758478165
2023-01-23 02:42:15.151757: step: 900/529, loss: 0.009263229556381702
2023-01-23 02:42:16.310340: step: 904/529, loss: 0.06771078705787659
2023-01-23 02:42:17.487858: step: 908/529, loss: 0.019165420904755592
2023-01-23 02:42:18.648649: step: 912/529, loss: 0.08352375030517578
2023-01-23 02:42:19.757569: step: 916/529, loss: 0.0021211623679846525
2023-01-23 02:42:20.917790: step: 920/529, loss: 0.009473037905991077
2023-01-23 02:42:22.062151: step: 924/529, loss: 0.007779979612678289
2023-01-23 02:42:23.246217: step: 928/529, loss: 0.021114541217684746
2023-01-23 02:42:24.396566: step: 932/529, loss: 0.04826173931360245
2023-01-23 02:42:25.544178: step: 936/529, loss: 0.011199855245649815
2023-01-23 02:42:26.682731: step: 940/529, loss: 0.05464959144592285
2023-01-23 02:42:27.810808: step: 944/529, loss: 0.42306995391845703
2023-01-23 02:42:28.971350: step: 948/529, loss: 0.006498241331428289
2023-01-23 02:42:30.095127: step: 952/529, loss: 0.0058394428342580795
2023-01-23 02:42:31.243373: step: 956/529, loss: 0.0027633667923510075
2023-01-23 02:42:32.388051: step: 960/529, loss: 0.00011596679541980848
2023-01-23 02:42:33.540033: step: 964/529, loss: 0.009939479641616344
2023-01-23 02:42:34.672998: step: 968/529, loss: 0.7047474980354309
2023-01-23 02:42:35.830259: step: 972/529, loss: 0.0026189805939793587
2023-01-23 02:42:36.948872: step: 976/529, loss: 0.05056390538811684
2023-01-23 02:42:38.090330: step: 980/529, loss: 0.007739257998764515
2023-01-23 02:42:39.234225: step: 984/529, loss: 0.024247217923402786
2023-01-23 02:42:40.353791: step: 988/529, loss: 0.0012052536476403475
2023-01-23 02:42:41.526206: step: 992/529, loss: 0.0018032074440270662
2023-01-23 02:42:42.675836: step: 996/529, loss: 0.00206336984410882
2023-01-23 02:42:43.810875: step: 1000/529, loss: 0.001304531004279852
2023-01-23 02:42:44.965134: step: 1004/529, loss: 0.03158550336956978
2023-01-23 02:42:46.098694: step: 1008/529, loss: 0.00036458970862440765
2023-01-23 02:42:47.232889: step: 1012/529, loss: 0.010820102877914906
2023-01-23 02:42:48.366787: step: 1016/529, loss: 0.0028075575828552246
2023-01-23 02:42:49.515009: step: 1020/529, loss: 0.02905893325805664
2023-01-23 02:42:50.685657: step: 1024/529, loss: 0.0280793197453022
2023-01-23 02:42:51.825021: step: 1028/529, loss: 0.03313121944665909
2023-01-23 02:42:52.986505: step: 1032/529, loss: 0.07287998497486115
2023-01-23 02:42:54.128802: step: 1036/529, loss: 0.043039895594120026
2023-01-23 02:42:55.300796: step: 1040/529, loss: 0.019349049776792526
2023-01-23 02:42:56.447706: step: 1044/529, loss: 0.005201817024499178
2023-01-23 02:42:57.591212: step: 1048/529, loss: 0.024669744074344635
2023-01-23 02:42:58.702098: step: 1052/529, loss: 0.01853400468826294
2023-01-23 02:42:59.822553: step: 1056/529, loss: 0.07856402546167374
2023-01-23 02:43:00.972222: step: 1060/529, loss: 0.34706515073776245
2023-01-23 02:43:02.098844: step: 1064/529, loss: 0.02746281772851944
2023-01-23 02:43:03.239324: step: 1068/529, loss: 0.015646077692508698
2023-01-23 02:43:04.368377: step: 1072/529, loss: 0.005643940065056086
2023-01-23 02:43:05.490132: step: 1076/529, loss: 0.0016124725807458162
2023-01-23 02:43:06.617110: step: 1080/529, loss: 0.00021800995455123484
2023-01-23 02:43:07.813968: step: 1084/529, loss: 0.012498665601015091
2023-01-23 02:43:08.961857: step: 1088/529, loss: 0.008881950750946999
2023-01-23 02:43:10.087036: step: 1092/529, loss: 0.002604580018669367
2023-01-23 02:43:11.247577: step: 1096/529, loss: 0.07128524780273438
2023-01-23 02:43:12.416219: step: 1100/529, loss: 0.016475200653076172
2023-01-23 02:43:13.537701: step: 1104/529, loss: 0.009147453121840954
2023-01-23 02:43:14.633873: step: 1108/529, loss: 0.03231959417462349
2023-01-23 02:43:15.744798: step: 1112/529, loss: 0.00045847895671613514
2023-01-23 02:43:16.910705: step: 1116/529, loss: 0.007363033480942249
2023-01-23 02:43:18.059137: step: 1120/529, loss: 0.01332855224609375
2023-01-23 02:43:19.207318: step: 1124/529, loss: 0.019433021545410156
2023-01-23 02:43:20.335289: step: 1128/529, loss: 0.0306535717099905
2023-01-23 02:43:21.496197: step: 1132/529, loss: 0.0385868065059185
2023-01-23 02:43:22.621037: step: 1136/529, loss: 0.013625050894916058
2023-01-23 02:43:23.767498: step: 1140/529, loss: 0.1016455665230751
2023-01-23 02:43:24.884698: step: 1144/529, loss: 0.00783233717083931
2023-01-23 02:43:26.042632: step: 1148/529, loss: 0.012146568857133389
2023-01-23 02:43:27.176975: step: 1152/529, loss: 0.0011615753173828125
2023-01-23 02:43:28.335997: step: 1156/529, loss: 0.01069488562643528
2023-01-23 02:43:29.468053: step: 1160/529, loss: 0.003141212509945035
2023-01-23 02:43:30.579827: step: 1164/529, loss: 0.00011200904555153102
2023-01-23 02:43:31.728860: step: 1168/529, loss: 0.013946629129350185
2023-01-23 02:43:32.862796: step: 1172/529, loss: 0.011359596624970436
2023-01-23 02:43:34.014180: step: 1176/529, loss: 0.06890201568603516
2023-01-23 02:43:35.146052: step: 1180/529, loss: 0.00794219970703125
2023-01-23 02:43:36.279358: step: 1184/529, loss: 0.015289593487977982
2023-01-23 02:43:37.435465: step: 1188/529, loss: 0.000607347465120256
2023-01-23 02:43:38.572488: step: 1192/529, loss: 0.0034267425071448088
2023-01-23 02:43:39.718182: step: 1196/529, loss: 8.468628220725805e-05
2023-01-23 02:43:40.855525: step: 1200/529, loss: 1.7029756307601929
2023-01-23 02:43:41.983489: step: 1204/529, loss: 0.6506485939025879
2023-01-23 02:43:43.119640: step: 1208/529, loss: 0.004114913754165173
2023-01-23 02:43:44.251018: step: 1212/529, loss: 0.03726482391357422
2023-01-23 02:43:45.373301: step: 1216/529, loss: 0.034063052386045456
2023-01-23 02:43:46.510940: step: 1220/529, loss: 0.011377430520951748
2023-01-23 02:43:47.664491: step: 1224/529, loss: 0.002095699543133378
2023-01-23 02:43:48.802710: step: 1228/529, loss: 0.0007552147144451737
2023-01-23 02:43:49.944103: step: 1232/529, loss: 0.002673411276191473
2023-01-23 02:43:51.099564: step: 1236/529, loss: 0.00013017654418945312
2023-01-23 02:43:52.221420: step: 1240/529, loss: 0.010288620367646217
2023-01-23 02:43:53.391554: step: 1244/529, loss: 0.00025959016056731343
2023-01-23 02:43:54.520717: step: 1248/529, loss: 0.0037863284815102816
2023-01-23 02:43:55.646878: step: 1252/529, loss: 0.016154861077666283
2023-01-23 02:43:56.804301: step: 1256/529, loss: 0.006078529637306929
2023-01-23 02:43:57.945624: step: 1260/529, loss: 0.007026052568107843
2023-01-23 02:43:59.105043: step: 1264/529, loss: 1.4209747860149946e-05
2023-01-23 02:44:00.254107: step: 1268/529, loss: 0.0015303611289709806
2023-01-23 02:44:01.362537: step: 1272/529, loss: 0.0051552774384617805
2023-01-23 02:44:02.499314: step: 1276/529, loss: 0.012936593033373356
2023-01-23 02:44:03.646005: step: 1280/529, loss: 0.011408329010009766
2023-01-23 02:44:04.826936: step: 1284/529, loss: 0.031004048883914948
2023-01-23 02:44:05.968620: step: 1288/529, loss: 0.0012442589504644275
2023-01-23 02:44:07.116612: step: 1292/529, loss: 0.007152080535888672
2023-01-23 02:44:08.294037: step: 1296/529, loss: 0.1203855499625206
2023-01-23 02:44:09.419901: step: 1300/529, loss: 0.00018138886662200093
2023-01-23 02:44:10.575489: step: 1304/529, loss: 0.0509122833609581
2023-01-23 02:44:11.732351: step: 1308/529, loss: 0.04141216352581978
2023-01-23 02:44:12.881172: step: 1312/529, loss: 0.037805940955877304
2023-01-23 02:44:14.013211: step: 1316/529, loss: 0.024106694385409355
2023-01-23 02:44:15.206992: step: 1320/529, loss: 1.8596649169921875e-05
2023-01-23 02:44:16.337843: step: 1324/529, loss: 0.05854291841387749
2023-01-23 02:44:17.458361: step: 1328/529, loss: 0.03648886829614639
2023-01-23 02:44:18.609986: step: 1332/529, loss: 0.0053764344193041325
2023-01-23 02:44:19.751886: step: 1336/529, loss: 0.004661750514060259
2023-01-23 02:44:20.894792: step: 1340/529, loss: 0.019359208643436432
2023-01-23 02:44:22.043944: step: 1344/529, loss: 0.005584716796875
2023-01-23 02:44:23.182124: step: 1348/529, loss: 0.0011871815659105778
2023-01-23 02:44:24.319763: step: 1352/529, loss: 1.5544890629826114e-05
2023-01-23 02:44:25.451762: step: 1356/529, loss: 0.014545058831572533
2023-01-23 02:44:26.598160: step: 1360/529, loss: 0.0009807586902752519
2023-01-23 02:44:27.748834: step: 1364/529, loss: 0.0021584511268883944
2023-01-23 02:44:28.894041: step: 1368/529, loss: 0.004087543580681086
2023-01-23 02:44:30.009689: step: 1372/529, loss: 0.0004984855768270791
2023-01-23 02:44:31.154634: step: 1376/529, loss: 0.004062843509018421
2023-01-23 02:44:32.324406: step: 1380/529, loss: 0.004050254821777344
2023-01-23 02:44:33.452650: step: 1384/529, loss: 0.02704143524169922
2023-01-23 02:44:34.569139: step: 1388/529, loss: 0.032195284962654114
2023-01-23 02:44:35.688415: step: 1392/529, loss: 0.06419945508241653
2023-01-23 02:44:36.799551: step: 1396/529, loss: 0.0022810937371104956
2023-01-23 02:44:37.933990: step: 1400/529, loss: 0.0012201309436932206
2023-01-23 02:44:39.062958: step: 1404/529, loss: 0.0005521774291992188
2023-01-23 02:44:40.225532: step: 1408/529, loss: 0.017676925286650658
2023-01-23 02:44:41.368914: step: 1412/529, loss: 0.06240854412317276
2023-01-23 02:44:42.530868: step: 1416/529, loss: 0.0006165981176309288
2023-01-23 02:44:43.686987: step: 1420/529, loss: 0.017447376623749733
2023-01-23 02:44:44.799891: step: 1424/529, loss: 0.00034370424691587687
2023-01-23 02:44:45.945717: step: 1428/529, loss: 0.0044151307083666325
2023-01-23 02:44:47.075232: step: 1432/529, loss: 0.027493858709931374
2023-01-23 02:44:48.214651: step: 1436/529, loss: 0.09043464809656143
2023-01-23 02:44:49.368653: step: 1440/529, loss: 0.04465799406170845
2023-01-23 02:44:50.493086: step: 1444/529, loss: 0.007709980010986328
2023-01-23 02:44:51.697700: step: 1448/529, loss: 0.00026607513427734375
2023-01-23 02:44:52.841907: step: 1452/529, loss: 0.00015840530977584422
2023-01-23 02:44:53.967966: step: 1456/529, loss: 0.0013560295337811112
2023-01-23 02:44:55.109848: step: 1460/529, loss: 0.0003067016659770161
2023-01-23 02:44:56.222708: step: 1464/529, loss: 0.004874229431152344
2023-01-23 02:44:57.352752: step: 1468/529, loss: 0.00027561187744140625
2023-01-23 02:44:58.484994: step: 1472/529, loss: 0.004246044438332319
2023-01-23 02:44:59.620236: step: 1476/529, loss: 0.004613971803337336
2023-01-23 02:45:00.742406: step: 1480/529, loss: 0.024268915876746178
2023-01-23 02:45:01.909373: step: 1484/529, loss: 0.00043144228402525187
2023-01-23 02:45:03.039249: step: 1488/529, loss: 0.115624338388443
2023-01-23 02:45:04.149900: step: 1492/529, loss: 0.0001656532404012978
2023-01-23 02:45:05.298796: step: 1496/529, loss: 0.0018731595482677221
2023-01-23 02:45:06.444951: step: 1500/529, loss: 0.005102920811623335
2023-01-23 02:45:07.564704: step: 1504/529, loss: 0.014412689954042435
2023-01-23 02:45:08.728881: step: 1508/529, loss: 7.486343383789062e-05
2023-01-23 02:45:09.856341: step: 1512/529, loss: 0.039426807314157486
2023-01-23 02:45:10.995042: step: 1516/529, loss: 0.0012891768710687757
2023-01-23 02:45:12.133793: step: 1520/529, loss: 0.013417769223451614
2023-01-23 02:45:13.298366: step: 1524/529, loss: 0.00032291412935592234
2023-01-23 02:45:14.420334: step: 1528/529, loss: 0.04516134411096573
2023-01-23 02:45:15.586053: step: 1532/529, loss: 0.028725624084472656
2023-01-23 02:45:16.737345: step: 1536/529, loss: 0.01963825337588787
2023-01-23 02:45:17.857964: step: 1540/529, loss: 0.0003147602255921811
2023-01-23 02:45:19.018752: step: 1544/529, loss: 0.39326995611190796
2023-01-23 02:45:20.162982: step: 1548/529, loss: 0.09417486190795898
2023-01-23 02:45:21.309119: step: 1552/529, loss: 0.012935166247189045
2023-01-23 02:45:22.480114: step: 1556/529, loss: 0.046253204345703125
2023-01-23 02:45:23.603509: step: 1560/529, loss: 0.025860263034701347
2023-01-23 02:45:24.720017: step: 1564/529, loss: 0.04771614074707031
2023-01-23 02:45:25.850119: step: 1568/529, loss: 1.1444091796875e-05
2023-01-23 02:45:27.010125: step: 1572/529, loss: 0.05708504095673561
2023-01-23 02:45:28.175472: step: 1576/529, loss: 0.00832824781537056
2023-01-23 02:45:29.302165: step: 1580/529, loss: 0.009956836700439453
2023-01-23 02:45:30.446314: step: 1584/529, loss: 0.013566303998231888
2023-01-23 02:45:31.596265: step: 1588/529, loss: 0.05560264736413956
2023-01-23 02:45:32.759816: step: 1592/529, loss: 0.051306914538145065
2023-01-23 02:45:33.914490: step: 1596/529, loss: 0.020345641300082207
2023-01-23 02:45:35.064346: step: 1600/529, loss: 0.00832357443869114
2023-01-23 02:45:36.174736: step: 1604/529, loss: 0.008730125613510609
2023-01-23 02:45:37.343914: step: 1608/529, loss: 0.0159741397947073
2023-01-23 02:45:38.496500: step: 1612/529, loss: 0.02404160611331463
2023-01-23 02:45:39.629420: step: 1616/529, loss: 0.24515514075756073
2023-01-23 02:45:40.780350: step: 1620/529, loss: 0.00027379990206100047
2023-01-23 02:45:41.892169: step: 1624/529, loss: 0.002193927764892578
2023-01-23 02:45:43.036100: step: 1628/529, loss: 0.0055561065673828125
2023-01-23 02:45:44.184707: step: 1632/529, loss: 0.0007213592762127519
2023-01-23 02:45:45.343651: step: 1636/529, loss: 0.018894100561738014
2023-01-23 02:45:46.520886: step: 1640/529, loss: 0.009850788861513138
2023-01-23 02:45:47.661550: step: 1644/529, loss: 0.0034782409202307463
2023-01-23 02:45:48.795677: step: 1648/529, loss: 0.0008298158645629883
2023-01-23 02:45:49.952262: step: 1652/529, loss: 0.0031703950371593237
2023-01-23 02:45:51.077570: step: 1656/529, loss: 0.03525600582361221
2023-01-23 02:45:52.202395: step: 1660/529, loss: 0.027184296399354935
2023-01-23 02:45:53.376672: step: 1664/529, loss: 0.06109027937054634
2023-01-23 02:45:54.511376: step: 1668/529, loss: 0.04244265705347061
2023-01-23 02:45:55.648721: step: 1672/529, loss: 0.0003202170191798359
2023-01-23 02:45:56.767140: step: 1676/529, loss: 0.00039196014404296875
2023-01-23 02:45:57.886288: step: 1680/529, loss: 9.90867629298009e-05
2023-01-23 02:45:59.024474: step: 1684/529, loss: 0.036699675023555756
2023-01-23 02:46:00.168691: step: 1688/529, loss: 0.0035342215560376644
2023-01-23 02:46:01.312726: step: 1692/529, loss: 0.02523527294397354
2023-01-23 02:46:02.465019: step: 1696/529, loss: 0.14827804267406464
2023-01-23 02:46:03.600803: step: 1700/529, loss: 0.016812516376376152
2023-01-23 02:46:04.734762: step: 1704/529, loss: 0.007227111142128706
2023-01-23 02:46:05.858602: step: 1708/529, loss: 0.06744912266731262
2023-01-23 02:46:06.981677: step: 1712/529, loss: 0.0082855224609375
2023-01-23 02:46:08.116505: step: 1716/529, loss: 0.05597548559308052
2023-01-23 02:46:09.249817: step: 1720/529, loss: 0.0076354979537427425
2023-01-23 02:46:10.401801: step: 1724/529, loss: 0.013385677710175514
2023-01-23 02:46:11.526768: step: 1728/529, loss: 0.14796094596385956
2023-01-23 02:46:12.662328: step: 1732/529, loss: 0.03515832498669624
2023-01-23 02:46:13.799088: step: 1736/529, loss: 0.01655750349164009
2023-01-23 02:46:14.980443: step: 1740/529, loss: 0.0011521339183673263
2023-01-23 02:46:16.110353: step: 1744/529, loss: 0.06231732666492462
2023-01-23 02:46:17.242872: step: 1748/529, loss: 0.002077388809993863
2023-01-23 02:46:18.400722: step: 1752/529, loss: 0.030359555035829544
2023-01-23 02:46:19.510492: step: 1756/529, loss: 0.016997702419757843
2023-01-23 02:46:20.640871: step: 1760/529, loss: 0.054388999938964844
2023-01-23 02:46:21.774954: step: 1764/529, loss: 0.03872261196374893
2023-01-23 02:46:22.899050: step: 1768/529, loss: 0.00091552734375
2023-01-23 02:46:24.047546: step: 1772/529, loss: 3.80516066798009e-05
2023-01-23 02:46:25.220285: step: 1776/529, loss: 0.008639144711196423
2023-01-23 02:46:26.366819: step: 1780/529, loss: 0.0003904342884197831
2023-01-23 02:46:27.504112: step: 1784/529, loss: 0.012933206744492054
2023-01-23 02:46:28.630462: step: 1788/529, loss: 0.03966650739312172
2023-01-23 02:46:29.785696: step: 1792/529, loss: 0.02050151862204075
2023-01-23 02:46:30.894826: step: 1796/529, loss: 0.0016991615993902087
2023-01-23 02:46:32.047012: step: 1800/529, loss: 0.05046787112951279
2023-01-23 02:46:33.197497: step: 1804/529, loss: 0.058178067207336426
2023-01-23 02:46:34.322716: step: 1808/529, loss: 0.004039192106574774
2023-01-23 02:46:35.461950: step: 1812/529, loss: 0.04495878145098686
2023-01-23 02:46:36.571935: step: 1816/529, loss: 3.2711028325138614e-05
2023-01-23 02:46:37.690481: step: 1820/529, loss: 0.0004555195337161422
2023-01-23 02:46:38.836250: step: 1824/529, loss: 0.014361239038407803
2023-01-23 02:46:39.982605: step: 1828/529, loss: 0.006221866235136986
2023-01-23 02:46:41.101602: step: 1832/529, loss: 0.0017052650218829513
2023-01-23 02:46:42.223347: step: 1836/529, loss: 0.011165808886289597
2023-01-23 02:46:43.380667: step: 1840/529, loss: 0.07832060009241104
2023-01-23 02:46:44.538844: step: 1844/529, loss: 0.010797119699418545
2023-01-23 02:46:45.688415: step: 1848/529, loss: 0.03523902967572212
2023-01-23 02:46:46.840252: step: 1852/529, loss: 0.04129810631275177
2023-01-23 02:46:47.992064: step: 1856/529, loss: 0.016043759882450104
2023-01-23 02:46:49.136798: step: 1860/529, loss: 0.020298006013035774
2023-01-23 02:46:50.295274: step: 1864/529, loss: 0.007849693298339844
2023-01-23 02:46:51.423308: step: 1868/529, loss: 0.07497768849134445
2023-01-23 02:46:52.578599: step: 1872/529, loss: 0.01386184711009264
2023-01-23 02:46:53.695633: step: 1876/529, loss: 0.0025489807594567537
2023-01-23 02:46:54.846193: step: 1880/529, loss: 0.034453582018613815
2023-01-23 02:46:55.966250: step: 1884/529, loss: 0.017970848828554153
2023-01-23 02:46:57.100097: step: 1888/529, loss: 0.04123726114630699
2023-01-23 02:46:58.235833: step: 1892/529, loss: 0.004308212082833052
2023-01-23 02:46:59.353233: step: 1896/529, loss: 0.004065132234245539
2023-01-23 02:47:00.509408: step: 1900/529, loss: 0.2575257122516632
2023-01-23 02:47:01.657554: step: 1904/529, loss: 0.034539032727479935
2023-01-23 02:47:02.770321: step: 1908/529, loss: 0.0095246322453022
2023-01-23 02:47:03.909897: step: 1912/529, loss: 0.10999203473329544
2023-01-23 02:47:05.076369: step: 1916/529, loss: 0.004568958189338446
2023-01-23 02:47:06.220458: step: 1920/529, loss: 0.006252670660614967
2023-01-23 02:47:07.367655: step: 1924/529, loss: 0.0017265320057049394
2023-01-23 02:47:08.533958: step: 1928/529, loss: 0.015929508954286575
2023-01-23 02:47:09.658736: step: 1932/529, loss: 0.013738633133471012
2023-01-23 02:47:10.820506: step: 1936/529, loss: 0.04503937065601349
2023-01-23 02:47:11.958419: step: 1940/529, loss: 0.16811342537403107
2023-01-23 02:47:13.109693: step: 1944/529, loss: 0.01735210418701172
2023-01-23 02:47:14.220637: step: 1948/529, loss: 0.017446376383304596
2023-01-23 02:47:15.346298: step: 1952/529, loss: 0.0003025055048055947
2023-01-23 02:47:16.481515: step: 1956/529, loss: 0.06208610534667969
2023-01-23 02:47:17.612704: step: 1960/529, loss: 0.039640095084905624
2023-01-23 02:47:18.738714: step: 1964/529, loss: 0.21908530592918396
2023-01-23 02:47:19.894601: step: 1968/529, loss: 0.011944960802793503
2023-01-23 02:47:21.003862: step: 1972/529, loss: 0.02257833629846573
2023-01-23 02:47:22.132916: step: 1976/529, loss: 0.0003666877746582031
2023-01-23 02:47:23.295002: step: 1980/529, loss: 0.05057945102453232
2023-01-23 02:47:24.436684: step: 1984/529, loss: 0.007708358578383923
2023-01-23 02:47:25.596520: step: 1988/529, loss: 0.0019529343117028475
2023-01-23 02:47:26.743935: step: 1992/529, loss: 0.02591877058148384
2023-01-23 02:47:27.888660: step: 1996/529, loss: 0.0037382126320153475
2023-01-23 02:47:29.024984: step: 2000/529, loss: 0.01462850533425808
2023-01-23 02:47:30.170085: step: 2004/529, loss: 0.05969696491956711
2023-01-23 02:47:31.362576: step: 2008/529, loss: 0.009320450015366077
2023-01-23 02:47:32.512802: step: 2012/529, loss: 0.008641052059829235
2023-01-23 02:47:33.679427: step: 2016/529, loss: 0.016835499554872513
2023-01-23 02:47:34.819944: step: 2020/529, loss: 0.01511244848370552
2023-01-23 02:47:35.991824: step: 2024/529, loss: 0.03141536936163902
2023-01-23 02:47:37.136134: step: 2028/529, loss: 0.006036281585693359
2023-01-23 02:47:38.297616: step: 2032/529, loss: 0.0009674073080532253
2023-01-23 02:47:39.417980: step: 2036/529, loss: 0.001789951347745955
2023-01-23 02:47:40.589349: step: 2040/529, loss: 0.02393512800335884
2023-01-23 02:47:41.756610: step: 2044/529, loss: 0.0005800247308798134
2023-01-23 02:47:42.892554: step: 2048/529, loss: 0.007439422886818647
2023-01-23 02:47:44.009691: step: 2052/529, loss: 0.00880889967083931
2023-01-23 02:47:45.154965: step: 2056/529, loss: 0.0017215729458257556
2023-01-23 02:47:46.291036: step: 2060/529, loss: 0.0005592346424236894
2023-01-23 02:47:47.424047: step: 2064/529, loss: 0.028040220960974693
2023-01-23 02:47:48.568269: step: 2068/529, loss: 0.04548969492316246
2023-01-23 02:47:49.697955: step: 2072/529, loss: 0.00485496548935771
2023-01-23 02:47:50.843771: step: 2076/529, loss: 0.007137966342270374
2023-01-23 02:47:51.973034: step: 2080/529, loss: 0.08839602023363113
2023-01-23 02:47:53.106205: step: 2084/529, loss: 0.12057837843894958
2023-01-23 02:47:54.247524: step: 2088/529, loss: 0.05204325169324875
2023-01-23 02:47:55.411025: step: 2092/529, loss: 0.0008857727516442537
2023-01-23 02:47:56.538602: step: 2096/529, loss: 0.04516306146979332
2023-01-23 02:47:57.727720: step: 2100/529, loss: 0.07876624912023544
2023-01-23 02:47:58.857675: step: 2104/529, loss: 0.020334243774414062
2023-01-23 02:48:00.002361: step: 2108/529, loss: -3.910064606316155e-06
2023-01-23 02:48:01.122404: step: 2112/529, loss: 0.022933006286621094
2023-01-23 02:48:02.298213: step: 2116/529, loss: 0.006758618168532848
==================================================
Loss: 0.034
--------------------
Dev: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.6071428571428571, 'r': 0.9444444444444444, 'f1': 0.7391304347826088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 02:48:48.781799: step: 4/529, loss: 0.0017229558434337378
2023-01-23 02:48:49.921968: step: 8/529, loss: 0.00012750625319313258
2023-01-23 02:48:51.036625: step: 12/529, loss: 0.0063738347962498665
2023-01-23 02:48:52.177947: step: 16/529, loss: 0.016020966693758965
2023-01-23 02:48:53.329204: step: 20/529, loss: 0.004394107963889837
2023-01-23 02:48:54.482132: step: 24/529, loss: 0.2875579595565796
2023-01-23 02:48:55.611277: step: 28/529, loss: 0.0014423370594158769
2023-01-23 02:48:56.795908: step: 32/529, loss: 0.026410864666104317
2023-01-23 02:48:57.958068: step: 36/529, loss: 0.058995820581912994
2023-01-23 02:48:59.118410: step: 40/529, loss: 0.022314071655273438
2023-01-23 02:49:00.291664: step: 44/529, loss: 0.011196709237992764
2023-01-23 02:49:01.415676: step: 48/529, loss: 0.0017934800125658512
2023-01-23 02:49:02.562102: step: 52/529, loss: 0.0030163764022290707
2023-01-23 02:49:03.710967: step: 56/529, loss: 0.014001942239701748
2023-01-23 02:49:04.805004: step: 60/529, loss: 0.0009846300818026066
2023-01-23 02:49:05.909025: step: 64/529, loss: 0.00209465017542243
2023-01-23 02:49:07.047966: step: 68/529, loss: 0.03479714319109917
2023-01-23 02:49:08.182685: step: 72/529, loss: 0.00035190582275390625
2023-01-23 02:49:09.323959: step: 76/529, loss: 0.0031116483733057976
2023-01-23 02:49:10.453806: step: 80/529, loss: 0.00028715134249068797
2023-01-23 02:49:11.602805: step: 84/529, loss: 0.00045452118501998484
2023-01-23 02:49:12.744533: step: 88/529, loss: 0.03635597229003906
2023-01-23 02:49:13.902939: step: 92/529, loss: 0.03024139441549778
2023-01-23 02:49:15.049990: step: 96/529, loss: 0.013460826128721237
2023-01-23 02:49:16.176127: step: 100/529, loss: 0.0026773454155772924
2023-01-23 02:49:17.321633: step: 104/529, loss: 0.007898807525634766
2023-01-23 02:49:18.480011: step: 108/529, loss: 0.0016506194369867444
2023-01-23 02:49:19.636610: step: 112/529, loss: 0.010470437817275524
2023-01-23 02:49:20.802358: step: 116/529, loss: 0.00010795594425871968
2023-01-23 02:49:21.921506: step: 120/529, loss: 8.926391456043348e-05
2023-01-23 02:49:23.039368: step: 124/529, loss: 0.04072628170251846
2023-01-23 02:49:24.191181: step: 128/529, loss: 0.029494667425751686
2023-01-23 02:49:25.318801: step: 132/529, loss: 0.0008565902826376259
2023-01-23 02:49:26.462179: step: 136/529, loss: 3.4046173823298886e-05
2023-01-23 02:49:27.577964: step: 140/529, loss: 0.016927719116210938
2023-01-23 02:49:28.736282: step: 144/529, loss: 0.10821304470300674
2023-01-23 02:49:29.857190: step: 148/529, loss: 0.035622384399175644
2023-01-23 02:49:31.026403: step: 152/529, loss: 0.04031829908490181
2023-01-23 02:49:32.156647: step: 156/529, loss: 0.017365645617246628
2023-01-23 02:49:33.312785: step: 160/529, loss: 0.035645198076963425
2023-01-23 02:49:34.463853: step: 164/529, loss: 0.00818481482565403
2023-01-23 02:49:35.609004: step: 168/529, loss: 0.010926151648163795
2023-01-23 02:49:36.761047: step: 172/529, loss: 0.06105957180261612
2023-01-23 02:49:37.910784: step: 176/529, loss: 0.01154251117259264
2023-01-23 02:49:39.062059: step: 180/529, loss: 0.00013365744962356985
2023-01-23 02:49:40.192768: step: 184/529, loss: 0.00179967877920717
2023-01-23 02:49:41.307885: step: 188/529, loss: 3.337860107421875e-05
2023-01-23 02:49:42.457505: step: 192/529, loss: 0.045339204370975494
2023-01-23 02:49:43.614278: step: 196/529, loss: 0.012264168821275234
2023-01-23 02:49:44.740175: step: 200/529, loss: 0.026839256286621094
2023-01-23 02:49:45.865479: step: 204/529, loss: 0.00029506682767532766
2023-01-23 02:49:46.987738: step: 208/529, loss: 0.011596537195146084
2023-01-23 02:49:48.146440: step: 212/529, loss: 0.004087972454726696
2023-01-23 02:49:49.297508: step: 216/529, loss: 0.01124496478587389
2023-01-23 02:49:50.469147: step: 220/529, loss: 0.06577281653881073
2023-01-23 02:49:51.599910: step: 224/529, loss: 0.0023153305519372225
2023-01-23 02:49:52.746912: step: 228/529, loss: 0.008156394585967064
2023-01-23 02:49:53.892766: step: 232/529, loss: 0.01878051646053791
2023-01-23 02:49:55.012273: step: 236/529, loss: 0.012361167930066586
2023-01-23 02:49:56.165028: step: 240/529, loss: 0.010026931762695312
2023-01-23 02:49:57.331792: step: 244/529, loss: 0.0016252041095867753
2023-01-23 02:49:58.472099: step: 248/529, loss: 0.02277221716940403
2023-01-23 02:49:59.661694: step: 252/529, loss: 0.013946819119155407
2023-01-23 02:50:00.834103: step: 256/529, loss: 0.021763229742646217
2023-01-23 02:50:01.962594: step: 260/529, loss: 0.020238209515810013
2023-01-23 02:50:03.096590: step: 264/529, loss: 0.002921962644904852
2023-01-23 02:50:04.235980: step: 268/529, loss: 0.0015006065368652344
2023-01-23 02:50:05.390831: step: 272/529, loss: 0.004385757260024548
2023-01-23 02:50:06.528624: step: 276/529, loss: 0.00016307830810546875
2023-01-23 02:50:07.649191: step: 280/529, loss: 0.010633468627929688
2023-01-23 02:50:08.792888: step: 284/529, loss: 1.3256072634248994e-05
2023-01-23 02:50:09.959032: step: 288/529, loss: 0.01273269671946764
2023-01-23 02:50:11.076630: step: 292/529, loss: 0.0026335238944739103
2023-01-23 02:50:12.205577: step: 296/529, loss: 0.019414758309721947
2023-01-23 02:50:13.335498: step: 300/529, loss: 0.00013175011554267257
2023-01-23 02:50:14.479838: step: 304/529, loss: 0.018715476617217064
2023-01-23 02:50:15.601806: step: 308/529, loss: 0.028333188965916634
2023-01-23 02:50:16.754574: step: 312/529, loss: 0.0027208328247070312
2023-01-23 02:50:17.903147: step: 316/529, loss: 0.005942726042121649
2023-01-23 02:50:19.058792: step: 320/529, loss: 0.028026580810546875
2023-01-23 02:50:20.206149: step: 324/529, loss: 0.00010776520502986386
2023-01-23 02:50:21.356309: step: 328/529, loss: 0.00025968553381972015
2023-01-23 02:50:22.494767: step: 332/529, loss: 5.645752389682457e-05
2023-01-23 02:50:23.641027: step: 336/529, loss: 0.005469226744025946
2023-01-23 02:50:24.793713: step: 340/529, loss: 0.00493278494104743
2023-01-23 02:50:25.927356: step: 344/529, loss: 0.0223814956843853
2023-01-23 02:50:27.054403: step: 348/529, loss: 0.04321708530187607
2023-01-23 02:50:28.186258: step: 352/529, loss: 0.007588577456772327
2023-01-23 02:50:29.351388: step: 356/529, loss: 0.0003215789911337197
2023-01-23 02:50:30.507289: step: 360/529, loss: 0.00026835798053070903
2023-01-23 02:50:31.626059: step: 364/529, loss: 0.029219914227724075
2023-01-23 02:50:32.738861: step: 368/529, loss: 0.0019974708557128906
2023-01-23 02:50:33.850507: step: 372/529, loss: 0.0020823481027036905
2023-01-23 02:50:35.028129: step: 376/529, loss: 0.0012748718727380037
2023-01-23 02:50:36.178519: step: 380/529, loss: 0.010187816806137562
2023-01-23 02:50:37.310218: step: 384/529, loss: 0.011214351281523705
2023-01-23 02:50:38.442063: step: 388/529, loss: 0.007705736439675093
2023-01-23 02:50:39.582395: step: 392/529, loss: 0.11236324161291122
2023-01-23 02:50:40.761899: step: 396/529, loss: 0.020964432507753372
2023-01-23 02:50:41.925179: step: 400/529, loss: 0.029291262850165367
2023-01-23 02:50:43.086782: step: 404/529, loss: 0.042046405375003815
2023-01-23 02:50:44.209701: step: 408/529, loss: 0.001918792724609375
2023-01-23 02:50:45.336828: step: 412/529, loss: 0.044573210179805756
2023-01-23 02:50:46.466747: step: 416/529, loss: 0.00019841194443870336
2023-01-23 02:50:47.580759: step: 420/529, loss: 0.015165758319199085
2023-01-23 02:50:48.672753: step: 424/529, loss: 3.0326844353112392e-05
2023-01-23 02:50:49.828569: step: 428/529, loss: 0.003480339189991355
2023-01-23 02:50:50.939223: step: 432/529, loss: 0.015481377020478249
2023-01-23 02:50:52.087650: step: 436/529, loss: 0.052968598902225494
2023-01-23 02:50:53.241521: step: 440/529, loss: 0.0530790314078331
2023-01-23 02:50:54.392457: step: 444/529, loss: 0.017420196905732155
2023-01-23 02:50:55.547438: step: 448/529, loss: 0.0022007941734045744
2023-01-23 02:50:56.706097: step: 452/529, loss: 0.06569195538759232
2023-01-23 02:50:57.841683: step: 456/529, loss: 0.0030723572708666325
2023-01-23 02:50:59.008139: step: 460/529, loss: 0.0022013664711266756
2023-01-23 02:51:00.137489: step: 464/529, loss: 0.0004341602325439453
2023-01-23 02:51:01.268640: step: 468/529, loss: 0.015452575869858265
2023-01-23 02:51:02.368629: step: 472/529, loss: 0.00043087004451081157
2023-01-23 02:51:03.497920: step: 476/529, loss: 0.00425376882776618
2023-01-23 02:51:04.632931: step: 480/529, loss: 0.02633051946759224
2023-01-23 02:51:05.750602: step: 484/529, loss: 0.0038394927978515625
2023-01-23 02:51:06.897298: step: 488/529, loss: 0.00047283171443268657
2023-01-23 02:51:08.029976: step: 492/529, loss: 0.12710438668727875
2023-01-23 02:51:09.169493: step: 496/529, loss: 0.0012802124256268144
2023-01-23 02:51:10.302319: step: 500/529, loss: 0.06940305233001709
2023-01-23 02:51:11.443556: step: 504/529, loss: 0.010061264038085938
2023-01-23 02:51:12.561967: step: 508/529, loss: 0.020330429077148438
2023-01-23 02:51:13.705774: step: 512/529, loss: 0.006386184599250555
2023-01-23 02:51:14.807423: step: 516/529, loss: 2.384185791015625e-05
2023-01-23 02:51:15.939479: step: 520/529, loss: 0.002096462296321988
2023-01-23 02:51:17.102817: step: 524/529, loss: 0.013880539685487747
2023-01-23 02:51:18.206910: step: 528/529, loss: 0.0001996994105866179
2023-01-23 02:51:19.332572: step: 532/529, loss: 0.005055236630141735
2023-01-23 02:51:20.490257: step: 536/529, loss: 0.04180869832634926
2023-01-23 02:51:21.626154: step: 540/529, loss: 6.442070298362523e-05
2023-01-23 02:51:22.848954: step: 544/529, loss: 0.039975740015506744
2023-01-23 02:51:23.998926: step: 548/529, loss: 0.0005557060358114541
2023-01-23 02:51:25.122717: step: 552/529, loss: 0.01630993001163006
2023-01-23 02:51:26.274172: step: 556/529, loss: 0.0002898216189350933
2023-01-23 02:51:27.423668: step: 560/529, loss: 0.0024632455315440893
2023-01-23 02:51:28.561743: step: 564/529, loss: 0.028363991528749466
2023-01-23 02:51:29.699721: step: 568/529, loss: 0.0022933962754905224
2023-01-23 02:51:30.836691: step: 572/529, loss: 0.0013566971756517887
2023-01-23 02:51:32.002544: step: 576/529, loss: 0.00023632051306776702
2023-01-23 02:51:33.144144: step: 580/529, loss: 0.0027883530128747225
2023-01-23 02:51:34.281359: step: 584/529, loss: 0.00439796457067132
2023-01-23 02:51:35.420775: step: 588/529, loss: 0.0018667221302166581
2023-01-23 02:51:36.532078: step: 592/529, loss: 0.0052741048857569695
2023-01-23 02:51:37.726223: step: 596/529, loss: 0.005711555480957031
2023-01-23 02:51:38.867923: step: 600/529, loss: 0.0007303237798623741
2023-01-23 02:51:39.999791: step: 604/529, loss: 0.0024530410300940275
2023-01-23 02:51:41.139820: step: 608/529, loss: 0.0002964019950013608
2023-01-23 02:51:42.275168: step: 612/529, loss: 0.0032460212241858244
2023-01-23 02:51:43.404862: step: 616/529, loss: 0.0027873993385583162
2023-01-23 02:51:44.533736: step: 620/529, loss: 0.0004849433898925781
2023-01-23 02:51:45.677515: step: 624/529, loss: 0.13007669150829315
2023-01-23 02:51:46.811130: step: 628/529, loss: 0.0013151407474651933
2023-01-23 02:51:47.957636: step: 632/529, loss: 0.0029778482858091593
2023-01-23 02:51:49.081486: step: 636/529, loss: 0.0012725830310955644
2023-01-23 02:51:50.220682: step: 640/529, loss: 0.0347936637699604
2023-01-23 02:51:51.407664: step: 644/529, loss: 0.018931293860077858
2023-01-23 02:51:52.551317: step: 648/529, loss: 9.536756806483027e-08
2023-01-23 02:51:53.704672: step: 652/529, loss: 0.027465151622891426
2023-01-23 02:51:54.841176: step: 656/529, loss: 0.0004594326310325414
2023-01-23 02:51:55.964282: step: 660/529, loss: 0.005196523852646351
2023-01-23 02:51:57.116516: step: 664/529, loss: 0.048226453363895416
2023-01-23 02:51:58.236747: step: 668/529, loss: 0.027511024847626686
2023-01-23 02:51:59.404803: step: 672/529, loss: 0.02921733818948269
2023-01-23 02:52:00.568594: step: 676/529, loss: 0.00010108948481502011
2023-01-23 02:52:01.705804: step: 680/529, loss: 0.03141040727496147
2023-01-23 02:52:02.847982: step: 684/529, loss: 0.03327608108520508
2023-01-23 02:52:03.990603: step: 688/529, loss: 0.004957771860063076
2023-01-23 02:52:05.108509: step: 692/529, loss: 0.0009335517534054816
2023-01-23 02:52:06.262103: step: 696/529, loss: 0.0051246643997728825
2023-01-23 02:52:07.443481: step: 700/529, loss: 0.047982312738895416
2023-01-23 02:52:08.571382: step: 704/529, loss: 0.01125488243997097
2023-01-23 02:52:09.719218: step: 708/529, loss: 0.00027751922607421875
2023-01-23 02:52:10.825596: step: 712/529, loss: 0.14670322835445404
2023-01-23 02:52:11.967922: step: 716/529, loss: 0.0011331557761877775
2023-01-23 02:52:13.110897: step: 720/529, loss: 0.0857355147600174
2023-01-23 02:52:14.241480: step: 724/529, loss: 0.0027174949645996094
2023-01-23 02:52:15.379204: step: 728/529, loss: 0.4464663565158844
2023-01-23 02:52:16.548960: step: 732/529, loss: 0.016971588134765625
2023-01-23 02:52:17.702207: step: 736/529, loss: 0.09289821982383728
2023-01-23 02:52:18.846772: step: 740/529, loss: 0.015959572046995163
2023-01-23 02:52:20.020667: step: 744/529, loss: 0.043720148503780365
2023-01-23 02:52:21.154037: step: 748/529, loss: 2.822876012942288e-05
2023-01-23 02:52:22.314554: step: 752/529, loss: 0.0005828857538290322
2023-01-23 02:52:23.458276: step: 756/529, loss: 0.07199706882238388
2023-01-23 02:52:24.599975: step: 760/529, loss: 0.03749069944024086
2023-01-23 02:52:25.752348: step: 764/529, loss: 0.09189119189977646
2023-01-23 02:52:26.869153: step: 768/529, loss: 1.544952465337701e-05
2023-01-23 02:52:28.009923: step: 772/529, loss: 0.03544311970472336
2023-01-23 02:52:29.195005: step: 776/529, loss: 0.004003333859145641
2023-01-23 02:52:30.318736: step: 780/529, loss: 0.007344531826674938
2023-01-23 02:52:31.440986: step: 784/529, loss: 0.0013620376121252775
2023-01-23 02:52:32.617072: step: 788/529, loss: 0.06679697334766388
2023-01-23 02:52:33.784859: step: 792/529, loss: 0.006496143061667681
2023-01-23 02:52:34.920364: step: 796/529, loss: 0.001853132271207869
2023-01-23 02:52:36.062920: step: 800/529, loss: 0.0025047301314771175
2023-01-23 02:52:37.211534: step: 804/529, loss: 0.01312112808227539
2023-01-23 02:52:38.350658: step: 808/529, loss: 0.0004287719784770161
2023-01-23 02:52:39.494569: step: 812/529, loss: 0.03422670438885689
2023-01-23 02:52:40.626661: step: 816/529, loss: 0.0035051347222179174
2023-01-23 02:52:41.755450: step: 820/529, loss: 0.005028247833251953
2023-01-23 02:52:42.885952: step: 824/529, loss: 5.817413330078125e-05
2023-01-23 02:52:44.003570: step: 828/529, loss: 0.021057654172182083
2023-01-23 02:52:45.126550: step: 832/529, loss: 0.878865122795105
2023-01-23 02:52:46.271511: step: 836/529, loss: 0.00186500558629632
2023-01-23 02:52:47.398270: step: 840/529, loss: 0.12342415004968643
2023-01-23 02:52:48.527133: step: 844/529, loss: 0.020163346081972122
2023-01-23 02:52:49.649076: step: 848/529, loss: 0.0003006935294251889
2023-01-23 02:52:50.790377: step: 852/529, loss: 0.01709880866110325
2023-01-23 02:52:51.940456: step: 856/529, loss: 0.00023312569828704
2023-01-23 02:52:53.096141: step: 860/529, loss: 0.00040693284245207906
2023-01-23 02:52:54.217810: step: 864/529, loss: 0.015584086999297142
2023-01-23 02:52:55.390748: step: 868/529, loss: 0.0018819809192791581
2023-01-23 02:52:56.528489: step: 872/529, loss: 0.038526538759469986
2023-01-23 02:52:57.660154: step: 876/529, loss: 0.00029811859712935984
2023-01-23 02:52:58.787327: step: 880/529, loss: 0.008828258141875267
2023-01-23 02:52:59.914314: step: 884/529, loss: 7.171630568336695e-05
2023-01-23 02:53:01.043710: step: 888/529, loss: 0.0012014388339594007
2023-01-23 02:53:02.199436: step: 892/529, loss: 0.0314946174621582
2023-01-23 02:53:03.334081: step: 896/529, loss: 0.0072608948685228825
2023-01-23 02:53:04.480754: step: 900/529, loss: 0.004921531770378351
2023-01-23 02:53:05.630061: step: 904/529, loss: 0.0023704529739916325
2023-01-23 02:53:06.784897: step: 908/529, loss: 0.00011987685866188258
2023-01-23 02:53:07.910232: step: 912/529, loss: 0.005391979124397039
2023-01-23 02:53:09.017609: step: 916/529, loss: 0.015199804678559303
2023-01-23 02:53:10.113023: step: 920/529, loss: 4.705586910247803
2023-01-23 02:53:11.238403: step: 924/529, loss: 0.00301532750017941
2023-01-23 02:53:12.355919: step: 928/529, loss: 0.06875982880592346
2023-01-23 02:53:13.484510: step: 932/529, loss: 0.2977858781814575
2023-01-23 02:53:14.609146: step: 936/529, loss: 0.002957821125164628
2023-01-23 02:53:15.738282: step: 940/529, loss: 0.005190849304199219
2023-01-23 02:53:16.859712: step: 944/529, loss: 0.005279255099594593
2023-01-23 02:53:18.003918: step: 948/529, loss: 0.01789245568215847
2023-01-23 02:53:19.134143: step: 952/529, loss: 0.00038733481778763235
2023-01-23 02:53:20.274369: step: 956/529, loss: 0.00030231475830078125
2023-01-23 02:53:21.394873: step: 960/529, loss: 0.005360794253647327
2023-01-23 02:53:22.522668: step: 964/529, loss: 0.03072347678244114
2023-01-23 02:53:23.661464: step: 968/529, loss: 0.029320908710360527
2023-01-23 02:53:24.815852: step: 972/529, loss: 0.17129193246364594
2023-01-23 02:53:25.936482: step: 976/529, loss: 0.0044345855712890625
2023-01-23 02:53:27.110255: step: 980/529, loss: 0.05413408204913139
2023-01-23 02:53:28.239125: step: 984/529, loss: 0.021362684667110443
2023-01-23 02:53:29.383208: step: 988/529, loss: 0.0007761955494061112
2023-01-23 02:53:30.504324: step: 992/529, loss: 0.0004703521844930947
2023-01-23 02:53:31.631963: step: 996/529, loss: 0.006201458163559437
2023-01-23 02:53:32.751458: step: 1000/529, loss: 0.002151393797248602
2023-01-23 02:53:33.908987: step: 1004/529, loss: 0.02366781234741211
2023-01-23 02:53:35.053006: step: 1008/529, loss: 8.029938180698082e-05
2023-01-23 02:53:36.190812: step: 1012/529, loss: 0.0004131317255087197
2023-01-23 02:53:37.348141: step: 1016/529, loss: 0.019981957972049713
2023-01-23 02:53:38.495558: step: 1020/529, loss: 0.10239439457654953
2023-01-23 02:53:39.611675: step: 1024/529, loss: 1.316070574830519e-05
2023-01-23 02:53:40.748253: step: 1028/529, loss: 8.249282836914062e-05
2023-01-23 02:53:41.914919: step: 1032/529, loss: 0.020923709496855736
2023-01-23 02:53:43.057407: step: 1036/529, loss: 0.00030660632182843983
2023-01-23 02:53:44.201854: step: 1040/529, loss: 0.006591606419533491
2023-01-23 02:53:45.338327: step: 1044/529, loss: 0.04016093909740448
2023-01-23 02:53:46.482997: step: 1048/529, loss: 0.032352447509765625
2023-01-23 02:53:47.617991: step: 1052/529, loss: 0.07407794147729874
2023-01-23 02:53:48.745048: step: 1056/529, loss: 0.00048093797522597015
2023-01-23 02:53:49.890073: step: 1060/529, loss: 0.012898826040327549
2023-01-23 02:53:51.085919: step: 1064/529, loss: 0.006937217898666859
2023-01-23 02:53:52.252922: step: 1068/529, loss: 0.0030711174476891756
2023-01-23 02:53:53.387793: step: 1072/529, loss: 0.010633469559252262
2023-01-23 02:53:54.526484: step: 1076/529, loss: 0.08028993755578995
2023-01-23 02:53:55.677080: step: 1080/529, loss: 0.025843143463134766
2023-01-23 02:53:56.831834: step: 1084/529, loss: 0.011153602972626686
2023-01-23 02:53:57.977639: step: 1088/529, loss: 0.9641178846359253
2023-01-23 02:53:59.135605: step: 1092/529, loss: 0.0005270004039630294
2023-01-23 02:54:00.294294: step: 1096/529, loss: 0.009481240063905716
2023-01-23 02:54:01.422169: step: 1100/529, loss: 0.0016740323044359684
2023-01-23 02:54:02.548357: step: 1104/529, loss: 0.0005876540672034025
2023-01-23 02:54:03.687802: step: 1108/529, loss: 0.0004922866937704384
2023-01-23 02:54:04.808260: step: 1112/529, loss: 0.0013348580105230212
2023-01-23 02:54:05.949377: step: 1116/529, loss: 0.09525832533836365
2023-01-23 02:54:07.097586: step: 1120/529, loss: 0.0009435653919354081
2023-01-23 02:54:08.235065: step: 1124/529, loss: 0.00011196135892532766
2023-01-23 02:54:09.408603: step: 1128/529, loss: 0.014861107803881168
2023-01-23 02:54:10.539065: step: 1132/529, loss: 0.013185501098632812
2023-01-23 02:54:11.679538: step: 1136/529, loss: 0.018764592707157135
2023-01-23 02:54:12.803083: step: 1140/529, loss: 0.05502796545624733
2023-01-23 02:54:13.954809: step: 1144/529, loss: 0.03473053127527237
2023-01-23 02:54:15.074430: step: 1148/529, loss: 0.05977487564086914
2023-01-23 02:54:16.275204: step: 1152/529, loss: 0.0037065506912767887
2023-01-23 02:54:17.422615: step: 1156/529, loss: 0.00016288757615257055
2023-01-23 02:54:18.574390: step: 1160/529, loss: 3.0517578125e-05
2023-01-23 02:54:19.715796: step: 1164/529, loss: 0.014849090948700905
2023-01-23 02:54:20.855975: step: 1168/529, loss: 0.00044116974459029734
2023-01-23 02:54:22.030731: step: 1172/529, loss: 0.016167735680937767
2023-01-23 02:54:23.187869: step: 1176/529, loss: 0.004170751664787531
2023-01-23 02:54:24.373132: step: 1180/529, loss: 0.0013672829372808337
2023-01-23 02:54:25.505752: step: 1184/529, loss: 0.00926055945456028
2023-01-23 02:54:26.646216: step: 1188/529, loss: 0.0036658288445323706
2023-01-23 02:54:27.802446: step: 1192/529, loss: 0.15600451827049255
2023-01-23 02:54:28.940894: step: 1196/529, loss: 0.04693803936243057
2023-01-23 02:54:30.062220: step: 1200/529, loss: 0.31173840165138245
2023-01-23 02:54:31.212423: step: 1204/529, loss: 0.007909155450761318
2023-01-23 02:54:32.341151: step: 1208/529, loss: 0.00023279190645553172
2023-01-23 02:54:33.449888: step: 1212/529, loss: 0.0025196552742272615
2023-01-23 02:54:34.573935: step: 1216/529, loss: 0.01823749579489231
2023-01-23 02:54:35.710035: step: 1220/529, loss: 0.005439949221909046
2023-01-23 02:54:36.827291: step: 1224/529, loss: 0.0027477266266942024
2023-01-23 02:54:37.973305: step: 1228/529, loss: 0.026699256151914597
2023-01-23 02:54:39.127352: step: 1232/529, loss: 0.0008554458618164062
2023-01-23 02:54:40.264658: step: 1236/529, loss: 0.0007020949851721525
2023-01-23 02:54:41.381538: step: 1240/529, loss: 0.0002577781560830772
2023-01-23 02:54:42.488558: step: 1244/529, loss: 0.00034332275390625
2023-01-23 02:54:43.644446: step: 1248/529, loss: 0.02109546773135662
2023-01-23 02:54:44.766406: step: 1252/529, loss: 0.009605121798813343
2023-01-23 02:54:45.943173: step: 1256/529, loss: 0.2840808928012848
2023-01-23 02:54:47.102243: step: 1260/529, loss: 0.002441597171127796
2023-01-23 02:54:48.253506: step: 1264/529, loss: 0.02648944780230522
2023-01-23 02:54:49.396257: step: 1268/529, loss: 9.441375732421875e-05
2023-01-23 02:54:50.556433: step: 1272/529, loss: 0.00016117095947265625
2023-01-23 02:54:51.732340: step: 1276/529, loss: 0.0028770449571311474
2023-01-23 02:54:52.877840: step: 1280/529, loss: 0.002125263214111328
2023-01-23 02:54:54.015613: step: 1284/529, loss: 0.00380706787109375
2023-01-23 02:54:55.145621: step: 1288/529, loss: 0.0012969970703125
2023-01-23 02:54:56.290873: step: 1292/529, loss: 0.0019219398964196444
2023-01-23 02:54:57.427652: step: 1296/529, loss: 0.030411623418331146
2023-01-23 02:54:58.587980: step: 1300/529, loss: 0.024067021906375885
2023-01-23 02:54:59.715974: step: 1304/529, loss: 0.009385108947753906
2023-01-23 02:55:00.834141: step: 1308/529, loss: 0.00565834017470479
2023-01-23 02:55:01.949696: step: 1312/529, loss: 0.006525897886604071
2023-01-23 02:55:03.065834: step: 1316/529, loss: 0.0001958847133209929
2023-01-23 02:55:04.223110: step: 1320/529, loss: 0.11978740990161896
2023-01-23 02:55:05.357400: step: 1324/529, loss: 0.044416047632694244
2023-01-23 02:55:06.498183: step: 1328/529, loss: 0.06220836937427521
2023-01-23 02:55:07.636847: step: 1332/529, loss: 0.0038527490105479956
2023-01-23 02:55:08.757376: step: 1336/529, loss: 0.001304245088249445
2023-01-23 02:55:09.904725: step: 1340/529, loss: 0.0003205776447430253
2023-01-23 02:55:11.057548: step: 1344/529, loss: 0.00019922255887649953
2023-01-23 02:55:12.192777: step: 1348/529, loss: 4.4441225327318534e-05
2023-01-23 02:55:13.332163: step: 1352/529, loss: 0.06800708919763565
2023-01-23 02:55:14.483789: step: 1356/529, loss: 0.028739355504512787
2023-01-23 02:55:15.636934: step: 1360/529, loss: 0.024689961224794388
2023-01-23 02:55:16.777739: step: 1364/529, loss: 0.012892341241240501
2023-01-23 02:55:17.895320: step: 1368/529, loss: 0.021869372576475143
2023-01-23 02:55:19.074910: step: 1372/529, loss: 0.0013822675682604313
2023-01-23 02:55:20.212271: step: 1376/529, loss: 0.006617831997573376
2023-01-23 02:55:21.364926: step: 1380/529, loss: 0.057739924639463425
2023-01-23 02:55:22.496080: step: 1384/529, loss: 0.02259845845401287
2023-01-23 02:55:23.628581: step: 1388/529, loss: 0.023250199854373932
2023-01-23 02:55:24.758662: step: 1392/529, loss: 0.006877136416733265
2023-01-23 02:55:25.882651: step: 1396/529, loss: 0.02518177032470703
2023-01-23 02:55:27.017590: step: 1400/529, loss: 0.0035586003214120865
2023-01-23 02:55:28.161043: step: 1404/529, loss: 0.04266529157757759
2023-01-23 02:55:29.317178: step: 1408/529, loss: 0.002956867218017578
2023-01-23 02:55:30.459405: step: 1412/529, loss: 0.015162426978349686
2023-01-23 02:55:31.553811: step: 1416/529, loss: 0.0006565094226971269
2023-01-23 02:55:32.710129: step: 1420/529, loss: 0.0005176544073037803
2023-01-23 02:55:33.842494: step: 1424/529, loss: 0.006370067596435547
2023-01-23 02:55:34.971072: step: 1428/529, loss: 0.04891815409064293
2023-01-23 02:55:36.092930: step: 1432/529, loss: 0.024137306958436966
2023-01-23 02:55:37.261637: step: 1436/529, loss: 0.0005458355299197137
2023-01-23 02:55:38.403600: step: 1440/529, loss: 0.004716396797448397
2023-01-23 02:55:39.554449: step: 1444/529, loss: 0.0007860183832235634
2023-01-23 02:55:40.709411: step: 1448/529, loss: 0.034719087183475494
2023-01-23 02:55:41.845851: step: 1452/529, loss: 0.01760726049542427
2023-01-23 02:55:42.997081: step: 1456/529, loss: 0.003089523408561945
2023-01-23 02:55:44.134450: step: 1460/529, loss: 0.003487443784251809
2023-01-23 02:55:45.303296: step: 1464/529, loss: 0.012828350998461246
2023-01-23 02:55:46.444073: step: 1468/529, loss: 0.007272911258041859
2023-01-23 02:55:47.579255: step: 1472/529, loss: 0.0628393143415451
2023-01-23 02:55:48.805305: step: 1476/529, loss: 0.0005155563121661544
2023-01-23 02:55:49.924283: step: 1480/529, loss: 0.004618645180016756
2023-01-23 02:55:51.081053: step: 1484/529, loss: 0.0005880832322873175
2023-01-23 02:55:52.234598: step: 1488/529, loss: 0.0013024808140471578
2023-01-23 02:55:53.346321: step: 1492/529, loss: 0.04302950203418732
2023-01-23 02:55:54.484104: step: 1496/529, loss: 0.0036716461181640625
2023-01-23 02:55:55.630366: step: 1500/529, loss: 0.00414619455114007
2023-01-23 02:55:56.776373: step: 1504/529, loss: 0.00033607485238462687
2023-01-23 02:55:57.905519: step: 1508/529, loss: 0.06471367180347443
2023-01-23 02:55:59.040473: step: 1512/529, loss: 0.0039650918915867805
2023-01-23 02:56:00.155131: step: 1516/529, loss: 0.008624029345810413
2023-01-23 02:56:01.297130: step: 1520/529, loss: 0.0003334045468363911
2023-01-23 02:56:02.422612: step: 1524/529, loss: 0.04535217210650444
2023-01-23 02:56:03.589527: step: 1528/529, loss: 0.0048965453170239925
2023-01-23 02:56:04.725692: step: 1532/529, loss: 0.0308137908577919
2023-01-23 02:56:05.855885: step: 1536/529, loss: 0.03395118936896324
2023-01-23 02:56:07.022643: step: 1540/529, loss: 0.03233480453491211
2023-01-23 02:56:08.158358: step: 1544/529, loss: 0.009851264767348766
2023-01-23 02:56:09.308134: step: 1548/529, loss: 0.005098151974380016
2023-01-23 02:56:10.440892: step: 1552/529, loss: 0.009525108151137829
2023-01-23 02:56:11.589991: step: 1556/529, loss: 0.013803482055664062
2023-01-23 02:56:12.764441: step: 1560/529, loss: 0.005675602238625288
2023-01-23 02:56:13.890868: step: 1564/529, loss: 0.00043172837467864156
2023-01-23 02:56:15.014271: step: 1568/529, loss: 0.009839248843491077
2023-01-23 02:56:16.191485: step: 1572/529, loss: 0.09858636558055878
2023-01-23 02:56:17.344931: step: 1576/529, loss: 0.0009611130226403475
2023-01-23 02:56:18.537261: step: 1580/529, loss: 0.4569973051548004
2023-01-23 02:56:19.662677: step: 1584/529, loss: 0.022182513028383255
2023-01-23 02:56:20.781830: step: 1588/529, loss: 0.0006231308216229081
2023-01-23 02:56:21.908682: step: 1592/529, loss: 0.001380109810270369
2023-01-23 02:56:23.031836: step: 1596/529, loss: 0.002073192736133933
2023-01-23 02:56:24.158202: step: 1600/529, loss: 0.0012027740012854338
2023-01-23 02:56:25.268513: step: 1604/529, loss: 0.0012117385631427169
2023-01-23 02:56:26.421513: step: 1608/529, loss: 0.021396446973085403
2023-01-23 02:56:27.557265: step: 1612/529, loss: 0.0024911880027502775
2023-01-23 02:56:28.689123: step: 1616/529, loss: 0.0030375956557691097
2023-01-23 02:56:29.860754: step: 1620/529, loss: 0.01107335090637207
2023-01-23 02:56:31.028210: step: 1624/529, loss: 0.0019267082680016756
2023-01-23 02:56:32.161803: step: 1628/529, loss: 0.0006121635669842362
2023-01-23 02:56:33.299413: step: 1632/529, loss: 0.05602245032787323
2023-01-23 02:56:34.424242: step: 1636/529, loss: 0.007361126132309437
2023-01-23 02:56:35.575450: step: 1640/529, loss: 0.006140708923339844
2023-01-23 02:56:36.737854: step: 1644/529, loss: 0.011189651675522327
2023-01-23 02:56:37.876477: step: 1648/529, loss: 0.0018308639992028475
2023-01-23 02:56:39.025664: step: 1652/529, loss: 0.045818231999874115
2023-01-23 02:56:40.157479: step: 1656/529, loss: 0.00015935898409225047
2023-01-23 02:56:41.289036: step: 1660/529, loss: 0.11245336383581161
2023-01-23 02:56:42.420628: step: 1664/529, loss: 0.0027372362092137337
2023-01-23 02:56:43.522624: step: 1668/529, loss: 0.010306263342499733
2023-01-23 02:56:44.655385: step: 1672/529, loss: 0.0013591767055913806
2023-01-23 02:56:45.799642: step: 1676/529, loss: 0.0006219864590093493
2023-01-23 02:56:46.952077: step: 1680/529, loss: 0.0009169578552246094
2023-01-23 02:56:48.101055: step: 1684/529, loss: 0.04617347940802574
2023-01-23 02:56:49.224514: step: 1688/529, loss: 0.29647645354270935
2023-01-23 02:56:50.337938: step: 1692/529, loss: 0.03921337425708771
2023-01-23 02:56:51.465525: step: 1696/529, loss: 0.12983036041259766
2023-01-23 02:56:52.631150: step: 1700/529, loss: 0.00022926331439521164
2023-01-23 02:56:53.785593: step: 1704/529, loss: 0.020938683301210403
2023-01-23 02:56:54.941362: step: 1708/529, loss: 0.03709878772497177
2023-01-23 02:56:56.077472: step: 1712/529, loss: 0.011890649795532227
2023-01-23 02:56:57.235744: step: 1716/529, loss: 0.0007921218639239669
2023-01-23 02:56:58.379770: step: 1720/529, loss: 0.004993248265236616
2023-01-23 02:56:59.502710: step: 1724/529, loss: 0.1916790008544922
2023-01-23 02:57:00.640530: step: 1728/529, loss: 0.0020202635787427425
2023-01-23 02:57:01.769679: step: 1732/529, loss: 0.0537593849003315
2023-01-23 02:57:02.914087: step: 1736/529, loss: 0.014293670654296875
2023-01-23 02:57:04.063642: step: 1740/529, loss: 0.04201831668615341
2023-01-23 02:57:05.222638: step: 1744/529, loss: 0.03522996976971626
2023-01-23 02:57:06.344271: step: 1748/529, loss: 0.005183362867683172
2023-01-23 02:57:07.480457: step: 1752/529, loss: 0.003144502639770508
2023-01-23 02:57:08.592967: step: 1756/529, loss: 0.00644760113209486
2023-01-23 02:57:09.714106: step: 1760/529, loss: 0.012038993649184704
2023-01-23 02:57:10.879028: step: 1764/529, loss: 0.01338181458413601
2023-01-23 02:57:12.007496: step: 1768/529, loss: 0.010101891122758389
2023-01-23 02:57:13.142780: step: 1772/529, loss: 0.02355017699301243
2023-01-23 02:57:14.276774: step: 1776/529, loss: 0.06967373192310333
2023-01-23 02:57:15.417422: step: 1780/529, loss: 0.004602814093232155
2023-01-23 02:57:16.537183: step: 1784/529, loss: 0.00010795592970680445
2023-01-23 02:57:17.690300: step: 1788/529, loss: 0.0015532494289800525
2023-01-23 02:57:18.806454: step: 1792/529, loss: 0.02895355224609375
2023-01-23 02:57:19.956678: step: 1796/529, loss: 0.0024499893188476562
2023-01-23 02:57:21.105824: step: 1800/529, loss: 0.0002652168332133442
2023-01-23 02:57:22.235868: step: 1804/529, loss: 0.00024118424335028976
2023-01-23 02:57:23.367342: step: 1808/529, loss: 0.0008556366083212197
2023-01-23 02:57:24.548328: step: 1812/529, loss: 0.040833473205566406
2023-01-23 02:57:25.662169: step: 1816/529, loss: 0.00027952194795943797
2023-01-23 02:57:26.824652: step: 1820/529, loss: 0.023070333525538445
2023-01-23 02:57:27.943717: step: 1824/529, loss: 0.0003982544003520161
2023-01-23 02:57:29.101512: step: 1828/529, loss: 8.640289161121473e-05
2023-01-23 02:57:30.288136: step: 1832/529, loss: 0.027905656024813652
2023-01-23 02:57:31.429778: step: 1836/529, loss: 4.763603283208795e-05
2023-01-23 02:57:32.589071: step: 1840/529, loss: 0.008761310018599033
2023-01-23 02:57:33.749382: step: 1844/529, loss: 0.00010185241990257055
2023-01-23 02:57:34.890025: step: 1848/529, loss: 0.0023704529739916325
2023-01-23 02:57:36.005340: step: 1852/529, loss: 0.0010433197021484375
2023-01-23 02:57:37.147715: step: 1856/529, loss: 0.03183021396398544
2023-01-23 02:57:38.278934: step: 1860/529, loss: 0.00014452934556175023
2023-01-23 02:57:39.411683: step: 1864/529, loss: 0.003361320588737726
2023-01-23 02:57:40.543322: step: 1868/529, loss: 0.037209652364254
2023-01-23 02:57:41.683270: step: 1872/529, loss: 0.006120109464973211
2023-01-23 02:57:42.825356: step: 1876/529, loss: 0.10689258575439453
2023-01-23 02:57:43.973705: step: 1880/529, loss: 0.010372161865234375
2023-01-23 02:57:45.113685: step: 1884/529, loss: 0.004285621456801891
2023-01-23 02:57:46.248295: step: 1888/529, loss: 0.03818473964929581
2023-01-23 02:57:47.366158: step: 1892/529, loss: 0.0001446724054403603
2023-01-23 02:57:48.539823: step: 1896/529, loss: 0.03526516258716583
2023-01-23 02:57:49.698096: step: 1900/529, loss: 0.0015977859729900956
2023-01-23 02:57:50.820452: step: 1904/529, loss: 0.007211733143776655
2023-01-23 02:57:51.962007: step: 1908/529, loss: 0.049468230456113815
2023-01-23 02:57:53.107079: step: 1912/529, loss: 0.015325259417295456
2023-01-23 02:57:54.259796: step: 1916/529, loss: 0.02558603323996067
2023-01-23 02:57:55.380764: step: 1920/529, loss: 0.004660940263420343
2023-01-23 02:57:56.498868: step: 1924/529, loss: 0.03502912446856499
2023-01-23 02:57:57.588522: step: 1928/529, loss: 0.00011463165719760582
2023-01-23 02:57:58.718360: step: 1932/529, loss: 0.0035083771217614412
2023-01-23 02:57:59.834220: step: 1936/529, loss: 0.044994208961725235
2023-01-23 02:58:01.003451: step: 1940/529, loss: 0.013011455535888672
2023-01-23 02:58:02.173065: step: 1944/529, loss: 0.0690038651227951
2023-01-23 02:58:03.328973: step: 1948/529, loss: 0.021395491436123848
2023-01-23 02:58:04.480348: step: 1952/529, loss: 0.1346874237060547
2023-01-23 02:58:05.625501: step: 1956/529, loss: 0.0006036758422851562
2023-01-23 02:58:06.779511: step: 1960/529, loss: 0.002509689424186945
2023-01-23 02:58:07.914169: step: 1964/529, loss: 0.0053873066790401936
2023-01-23 02:58:09.037838: step: 1968/529, loss: 0.00026035308837890625
2023-01-23 02:58:10.215767: step: 1972/529, loss: 0.0001183509812108241
2023-01-23 02:58:11.357989: step: 1976/529, loss: 0.009867191314697266
2023-01-23 02:58:12.524443: step: 1980/529, loss: 0.0022149085998535156
2023-01-23 02:58:13.679935: step: 1984/529, loss: 8.39233416627394e-06
2023-01-23 02:58:14.798166: step: 1988/529, loss: 0.019773198291659355
2023-01-23 02:58:15.953082: step: 1992/529, loss: 0.03413581848144531
2023-01-23 02:58:17.094631: step: 1996/529, loss: 0.0015562057960778475
2023-01-23 02:58:18.256501: step: 2000/529, loss: 0.06823521107435226
2023-01-23 02:58:19.437329: step: 2004/529, loss: 0.016434289515018463
2023-01-23 02:58:20.568363: step: 2008/529, loss: 0.0008293151622638106
2023-01-23 02:58:21.705703: step: 2012/529, loss: 0.0006480216979980469
2023-01-23 02:58:22.818892: step: 2016/529, loss: 0.010793304070830345
2023-01-23 02:58:23.971998: step: 2020/529, loss: 0.006809521000832319
2023-01-23 02:58:25.125284: step: 2024/529, loss: 0.0006639480707235634
2023-01-23 02:58:26.268688: step: 2028/529, loss: 0.0005534171941690147
2023-01-23 02:58:27.424106: step: 2032/529, loss: 0.023509599268436432
2023-01-23 02:58:28.570688: step: 2036/529, loss: 0.0009523392072878778
2023-01-23 02:58:29.737310: step: 2040/529, loss: 0.03637246787548065
2023-01-23 02:58:30.903952: step: 2044/529, loss: 0.02288341522216797
2023-01-23 02:58:32.023182: step: 2048/529, loss: 0.056105807423591614
2023-01-23 02:58:33.178974: step: 2052/529, loss: 0.014925575815141201
2023-01-23 02:58:34.306872: step: 2056/529, loss: 0.011881733313202858
2023-01-23 02:58:35.454419: step: 2060/529, loss: 0.003666400909423828
2023-01-23 02:58:36.603029: step: 2064/529, loss: 0.0021726610139012337
2023-01-23 02:58:37.754348: step: 2068/529, loss: 0.035338688641786575
2023-01-23 02:58:38.918371: step: 2072/529, loss: 0.0012248515849933028
2023-01-23 02:58:40.059077: step: 2076/529, loss: 0.0005747318500652909
2023-01-23 02:58:41.207515: step: 2080/529, loss: 0.0023475647903978825
2023-01-23 02:58:42.375894: step: 2084/529, loss: 0.00099945068359375
2023-01-23 02:58:43.499386: step: 2088/529, loss: 0.0014196396805346012
2023-01-23 02:58:44.633128: step: 2092/529, loss: 0.010527086444199085
2023-01-23 02:58:45.779519: step: 2096/529, loss: 0.009007644839584827
2023-01-23 02:58:46.898773: step: 2100/529, loss: 0.06700649112462997
2023-01-23 02:58:48.016878: step: 2104/529, loss: 0.021753691136837006
2023-01-23 02:58:49.149023: step: 2108/529, loss: 0.019083648920059204
2023-01-23 02:58:50.294183: step: 2112/529, loss: 0.023957347497344017
2023-01-23 02:58:51.420454: step: 2116/529, loss: 2.6226043701171875e-06
==================================================
Loss: 0.034
--------------------
Dev: {'event': {'p': 0.581532416502947, 'r': 0.7882822902796272, 'f1': 0.6693046919163369}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6024150268336315, 'r': 0.7804171494785631, 'f1': 0.6799596163553759}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.5444444444444444, 'r': 0.9074074074074074, 'f1': 0.6805555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.5967741935483871, 'r': 0.5873015873015873, 'f1': 0.592}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.5555555555555556, 'f1': 0.49382716049382713}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 02:59:33.345424: step: 4/529, loss: 0.014572334475815296
2023-01-23 02:59:34.470247: step: 8/529, loss: 0.00015687942504882812
2023-01-23 02:59:35.643267: step: 12/529, loss: 0.031372833997011185
2023-01-23 02:59:36.774536: step: 16/529, loss: 0.04549608379602432
2023-01-23 02:59:37.910343: step: 20/529, loss: 0.005827045533806086
2023-01-23 02:59:39.030695: step: 24/529, loss: 0.0014043807750567794
2023-01-23 02:59:40.160659: step: 28/529, loss: 0.008192635141313076
2023-01-23 02:59:41.285489: step: 32/529, loss: 0.005195140838623047
2023-01-23 02:59:42.412837: step: 36/529, loss: 0.00022268295288085938
2023-01-23 02:59:43.587000: step: 40/529, loss: 0.008117484860122204
2023-01-23 02:59:44.735646: step: 44/529, loss: 0.0619657076895237
2023-01-23 02:59:45.897126: step: 48/529, loss: 0.0008929252508096397
2023-01-23 02:59:47.036103: step: 52/529, loss: 0.004566192626953125
2023-01-23 02:59:48.192226: step: 56/529, loss: 0.0005871772882528603
2023-01-23 02:59:49.322270: step: 60/529, loss: 0.010891533456742764
2023-01-23 02:59:50.469787: step: 64/529, loss: 0.0003082275507040322
2023-01-23 02:59:51.619190: step: 68/529, loss: 0.006340503692626953
2023-01-23 02:59:52.823108: step: 72/529, loss: 6.532669067382812e-05
2023-01-23 02:59:53.987139: step: 76/529, loss: 0.044126369059085846
2023-01-23 02:59:55.165120: step: 80/529, loss: 0.03161201626062393
2023-01-23 02:59:56.312211: step: 84/529, loss: 0.04349403455853462
2023-01-23 02:59:57.446736: step: 88/529, loss: 0.004472637083381414
2023-01-23 02:59:58.568762: step: 92/529, loss: 0.0007043838268145919
2023-01-23 02:59:59.703278: step: 96/529, loss: 0.00051965715829283
2023-01-23 03:00:00.883102: step: 100/529, loss: 0.018740464001893997
2023-01-23 03:00:02.037545: step: 104/529, loss: 0.005173110868781805
2023-01-23 03:00:03.196918: step: 108/529, loss: 0.003543853759765625
2023-01-23 03:00:04.331139: step: 112/529, loss: 0.005423164460808039
2023-01-23 03:00:05.448102: step: 116/529, loss: 0.0014303206698969007
2023-01-23 03:00:06.596386: step: 120/529, loss: 1.1219558715820312
2023-01-23 03:00:07.711743: step: 124/529, loss: 0.00016241073899436742
2023-01-23 03:00:08.864527: step: 128/529, loss: 0.0008438110817223787
2023-01-23 03:00:09.984777: step: 132/529, loss: 0.002221775008365512
2023-01-23 03:00:11.114691: step: 136/529, loss: 0.025299929082393646
2023-01-23 03:00:12.289100: step: 140/529, loss: 0.024934101849794388
2023-01-23 03:00:13.430040: step: 144/529, loss: 0.00021629335242323577
2023-01-23 03:00:14.551459: step: 148/529, loss: 0.05854148790240288
2023-01-23 03:00:15.689653: step: 152/529, loss: 0.0031544207595288754
2023-01-23 03:00:16.808099: step: 156/529, loss: 0.006803989876061678
2023-01-23 03:00:17.934695: step: 160/529, loss: 0.008624744601547718
2023-01-23 03:00:19.053768: step: 164/529, loss: 0.0027171135880053043
2023-01-23 03:00:20.169337: step: 168/529, loss: 0.011455345898866653
2023-01-23 03:00:21.293488: step: 172/529, loss: 0.001856040908023715
2023-01-23 03:00:22.425790: step: 176/529, loss: 0.06771411746740341
2023-01-23 03:00:23.591584: step: 180/529, loss: 0.009473037905991077
2023-01-23 03:00:24.749942: step: 184/529, loss: 0.24229221045970917
2023-01-23 03:00:25.878241: step: 188/529, loss: 0.004801750183105469
2023-01-23 03:00:27.072322: step: 192/529, loss: 0.005550098605453968
2023-01-23 03:00:28.203593: step: 196/529, loss: 4.024505687993951e-05
2023-01-23 03:00:29.348508: step: 200/529, loss: 0.024713803082704544
2023-01-23 03:00:30.479925: step: 204/529, loss: 0.03115091286599636
2023-01-23 03:00:31.650705: step: 208/529, loss: 0.006118202582001686
2023-01-23 03:00:32.783951: step: 212/529, loss: 0.023369980975985527
2023-01-23 03:00:33.892682: step: 216/529, loss: 0.000720977783203125
2023-01-23 03:00:35.051181: step: 220/529, loss: 0.003168296767398715
2023-01-23 03:00:36.182031: step: 224/529, loss: 0.00013551712618209422
2023-01-23 03:00:37.314330: step: 228/529, loss: 0.0326593779027462
2023-01-23 03:00:38.472673: step: 232/529, loss: 0.02245769463479519
2023-01-23 03:00:39.599111: step: 236/529, loss: 0.046436309814453125
2023-01-23 03:00:40.755973: step: 240/529, loss: 0.0004540443478617817
2023-01-23 03:00:41.887345: step: 244/529, loss: 0.048932984471321106
2023-01-23 03:00:43.009274: step: 248/529, loss: 0.00019569398136809468
2023-01-23 03:00:44.175546: step: 252/529, loss: 0.04384374991059303
2023-01-23 03:00:45.302262: step: 256/529, loss: 0.0011034011840820312
2023-01-23 03:00:46.439113: step: 260/529, loss: 0.27853965759277344
2023-01-23 03:00:47.603298: step: 264/529, loss: 0.012395954690873623
2023-01-23 03:00:48.761529: step: 268/529, loss: 0.028108788654208183
2023-01-23 03:00:49.886506: step: 272/529, loss: 0.0011301040649414062
2023-01-23 03:00:51.031906: step: 276/529, loss: 0.0002620697196107358
2023-01-23 03:00:52.191363: step: 280/529, loss: 0.0031561851501464844
2023-01-23 03:00:53.344313: step: 284/529, loss: 0.016859054565429688
2023-01-23 03:00:54.479629: step: 288/529, loss: 0.0010635375510901213
2023-01-23 03:00:55.632125: step: 292/529, loss: 0.028599359095096588
2023-01-23 03:00:56.747062: step: 296/529, loss: 0.008155345916748047
2023-01-23 03:00:57.888220: step: 300/529, loss: 0.004108619876205921
2023-01-23 03:00:58.981107: step: 304/529, loss: 4.5585635234601796e-05
2023-01-23 03:01:00.142449: step: 308/529, loss: 0.0002601623709779233
2023-01-23 03:01:01.267415: step: 312/529, loss: 0.012130547314882278
2023-01-23 03:01:02.422887: step: 316/529, loss: 0.0016498565673828125
2023-01-23 03:01:03.554206: step: 320/529, loss: 5.073547436040826e-05
2023-01-23 03:01:04.696350: step: 324/529, loss: 8.888245065463707e-05
2023-01-23 03:01:05.826016: step: 328/529, loss: 0.018139267340302467
2023-01-23 03:01:06.975846: step: 332/529, loss: 0.01211319025605917
2023-01-23 03:01:08.143287: step: 336/529, loss: 0.020360421389341354
2023-01-23 03:01:09.284114: step: 340/529, loss: 0.005267334170639515
2023-01-23 03:01:10.409912: step: 344/529, loss: 0.0009886741172522306
2023-01-23 03:01:11.556945: step: 348/529, loss: 0.0011377334594726562
2023-01-23 03:01:12.681033: step: 352/529, loss: 0.003307342529296875
2023-01-23 03:01:13.823939: step: 356/529, loss: 0.06897401809692383
2023-01-23 03:01:14.925592: step: 360/529, loss: 0.0003910541709046811
2023-01-23 03:01:16.063231: step: 364/529, loss: 0.013899422250688076
2023-01-23 03:01:17.199115: step: 368/529, loss: 0.011314105242490768
2023-01-23 03:01:18.317173: step: 372/529, loss: 0.0009882927406579256
2023-01-23 03:01:19.453082: step: 376/529, loss: 0.010402584448456764
2023-01-23 03:01:20.618514: step: 380/529, loss: 0.00013828277587890625
2023-01-23 03:01:21.707995: step: 384/529, loss: 0.0003765106375794858
2023-01-23 03:01:22.881604: step: 388/529, loss: 0.01226730365306139
2023-01-23 03:01:24.013033: step: 392/529, loss: 0.005211162846535444
2023-01-23 03:01:25.155507: step: 396/529, loss: 0.03441572189331055
2023-01-23 03:01:26.318221: step: 400/529, loss: 6.732941255904734e-05
2023-01-23 03:01:27.445743: step: 404/529, loss: 2.1457672119140625e-05
2023-01-23 03:01:28.593470: step: 408/529, loss: 0.024457359686493874
2023-01-23 03:01:29.732492: step: 412/529, loss: 0.013788414187729359
2023-01-23 03:01:30.871793: step: 416/529, loss: 0.011552381329238415
2023-01-23 03:01:32.017769: step: 420/529, loss: 0.0007276535034179688
2023-01-23 03:01:33.145272: step: 424/529, loss: 0.0019419670570641756
2023-01-23 03:01:34.274038: step: 428/529, loss: 0.0018526078201830387
2023-01-23 03:01:35.421095: step: 432/529, loss: 0.012841415591537952
2023-01-23 03:01:36.561769: step: 436/529, loss: 0.0014563561417162418
2023-01-23 03:01:37.703782: step: 440/529, loss: 0.0023183822631835938
2023-01-23 03:01:38.858471: step: 444/529, loss: 1.392364538332913e-05
2023-01-23 03:01:40.004100: step: 448/529, loss: 0.001147461007349193
2023-01-23 03:01:41.155065: step: 452/529, loss: 0.0017309188842773438
2023-01-23 03:01:42.280899: step: 456/529, loss: 0.00011940002877963707
2023-01-23 03:01:43.431724: step: 460/529, loss: 0.000778579676989466
2023-01-23 03:01:44.548097: step: 464/529, loss: 0.0028966425452381372
2023-01-23 03:01:45.687373: step: 468/529, loss: 0.006875229068100452
2023-01-23 03:01:46.855816: step: 472/529, loss: 0.00010414123244117945
2023-01-23 03:01:47.968435: step: 476/529, loss: 0.00557289132848382
2023-01-23 03:01:49.096626: step: 480/529, loss: 0.024851465597748756
2023-01-23 03:01:50.253892: step: 484/529, loss: 0.00038242340087890625
2023-01-23 03:01:51.399517: step: 488/529, loss: 0.0017158507835119963
2023-01-23 03:01:52.564315: step: 492/529, loss: 1.3351443612918956e-06
2023-01-23 03:01:53.710822: step: 496/529, loss: 0.007054328918457031
2023-01-23 03:01:54.835421: step: 500/529, loss: 1.5163421267061494e-05
2023-01-23 03:01:55.972066: step: 504/529, loss: 0.032987404614686966
2023-01-23 03:01:57.083496: step: 508/529, loss: 0.005805682856589556
2023-01-23 03:01:58.235795: step: 512/529, loss: 4.081726001459174e-05
2023-01-23 03:01:59.377214: step: 516/529, loss: 0.008034229278564453
2023-01-23 03:02:00.517454: step: 520/529, loss: 0.0009360313415527344
2023-01-23 03:02:01.629739: step: 524/529, loss: 0.00223121652379632
2023-01-23 03:02:02.750953: step: 528/529, loss: 0.0037462234031409025
2023-01-23 03:02:03.911505: step: 532/529, loss: 0.01670379750430584
2023-01-23 03:02:05.040581: step: 536/529, loss: 0.07366657257080078
2023-01-23 03:02:06.179871: step: 540/529, loss: 0.02952442318201065
2023-01-23 03:02:07.328787: step: 544/529, loss: 0.020560646429657936
2023-01-23 03:02:08.488044: step: 548/529, loss: 0.0035467147827148438
2023-01-23 03:02:09.638302: step: 552/529, loss: 0.01634988747537136
2023-01-23 03:02:10.763805: step: 556/529, loss: 0.004773521330207586
2023-01-23 03:02:11.911654: step: 560/529, loss: 0.0002556085819378495
2023-01-23 03:02:13.082595: step: 564/529, loss: 0.05723247677087784
2023-01-23 03:02:14.240919: step: 568/529, loss: 0.002836227649822831
2023-01-23 03:02:15.394775: step: 572/529, loss: 0.0002426147402729839
2023-01-23 03:02:16.537671: step: 576/529, loss: 0.020611191168427467
2023-01-23 03:02:17.675553: step: 580/529, loss: 0.08501420170068741
2023-01-23 03:02:18.816940: step: 584/529, loss: 0.00020275116548873484
2023-01-23 03:02:19.914754: step: 588/529, loss: 0.004576015751808882
2023-01-23 03:02:21.057665: step: 592/529, loss: 0.0013484954833984375
2023-01-23 03:02:22.188179: step: 596/529, loss: 0.0008884907001629472
2023-01-23 03:02:23.326334: step: 600/529, loss: 0.0037179947830736637
2023-01-23 03:02:24.435176: step: 604/529, loss: 0.0022679329849779606
2023-01-23 03:02:25.569901: step: 608/529, loss: 0.00551948556676507
2023-01-23 03:02:26.721152: step: 612/529, loss: 0.029462814331054688
2023-01-23 03:02:27.857696: step: 616/529, loss: 0.0009654999012127519
2023-01-23 03:02:28.988246: step: 620/529, loss: 0.00010318757267668843
2023-01-23 03:02:30.114451: step: 624/529, loss: 0.003912544343620539
2023-01-23 03:02:31.247786: step: 628/529, loss: 0.0024280548095703125
2023-01-23 03:02:32.381696: step: 632/529, loss: 0.0032265663612633944
2023-01-23 03:02:33.512895: step: 636/529, loss: 0.010932350531220436
2023-01-23 03:02:34.640389: step: 640/529, loss: 0.01750502735376358
2023-01-23 03:02:35.787443: step: 644/529, loss: 0.036095716059207916
2023-01-23 03:02:36.945622: step: 648/529, loss: 0.009757328778505325
2023-01-23 03:02:38.106515: step: 652/529, loss: 5.7411190937273204e-05
2023-01-23 03:02:39.285630: step: 656/529, loss: 0.012451362796127796
2023-01-23 03:02:40.430529: step: 660/529, loss: 0.0005082368734292686
2023-01-23 03:02:41.559580: step: 664/529, loss: 0.0015271187294274569
2023-01-23 03:02:42.702154: step: 668/529, loss: 0.014600562863051891
2023-01-23 03:02:43.847497: step: 672/529, loss: 0.028201866894960403
2023-01-23 03:02:44.974872: step: 676/529, loss: 0.0005444526905193925
2023-01-23 03:02:46.113242: step: 680/529, loss: 0.0003059387090615928
2023-01-23 03:02:47.260060: step: 684/529, loss: 0.047283269464969635
2023-01-23 03:02:48.391434: step: 688/529, loss: 0.0043516638688743114
2023-01-23 03:02:49.562068: step: 692/529, loss: 0.0015348434681072831
2023-01-23 03:02:50.705898: step: 696/529, loss: 0.0014476776123046875
2023-01-23 03:02:51.827840: step: 700/529, loss: 0.0035474777687340975
2023-01-23 03:02:52.965258: step: 704/529, loss: 0.002964592073112726
2023-01-23 03:02:54.105159: step: 708/529, loss: 0.0007718086126260459
2023-01-23 03:02:55.244194: step: 712/529, loss: 0.009532356634736061
2023-01-23 03:02:56.407261: step: 716/529, loss: 0.00044918060302734375
2023-01-23 03:02:57.551895: step: 720/529, loss: 0.0024585723876953125
2023-01-23 03:02:58.696550: step: 724/529, loss: 0.0013605117565020919
2023-01-23 03:02:59.852947: step: 728/529, loss: 0.00160818116273731
2023-01-23 03:03:00.979788: step: 732/529, loss: 0.02752971649169922
2023-01-23 03:03:02.120435: step: 736/529, loss: 0.011965370737016201
2023-01-23 03:03:03.284631: step: 740/529, loss: 0.0008462906116619706
2023-01-23 03:03:04.420453: step: 744/529, loss: 3.156661841785535e-05
2023-01-23 03:03:05.561030: step: 748/529, loss: 0.0010281563736498356
2023-01-23 03:03:06.700662: step: 752/529, loss: 0.6975657939910889
2023-01-23 03:03:07.839464: step: 756/529, loss: 0.0001426696835551411
2023-01-23 03:03:08.950701: step: 760/529, loss: 0.00016217232041526586
2023-01-23 03:03:10.086082: step: 764/529, loss: 0.0007642746204510331
2023-01-23 03:03:11.218925: step: 768/529, loss: 0.0023048401344567537
2023-01-23 03:03:12.352967: step: 772/529, loss: 0.12246724218130112
2023-01-23 03:03:13.489933: step: 776/529, loss: 0.009594726376235485
2023-01-23 03:03:14.616861: step: 780/529, loss: 0.0011806489201262593
2023-01-23 03:03:15.749814: step: 784/529, loss: 9.51766996877268e-05
2023-01-23 03:03:16.901976: step: 788/529, loss: 0.0018289090367034078
2023-01-23 03:03:18.049608: step: 792/529, loss: 0.029907381162047386
2023-01-23 03:03:19.196379: step: 796/529, loss: 0.030140208080410957
2023-01-23 03:03:20.341096: step: 800/529, loss: 0.00010604858107399195
2023-01-23 03:03:21.476079: step: 804/529, loss: 0.001104068709537387
2023-01-23 03:03:22.611436: step: 808/529, loss: 3.919601658708416e-05
2023-01-23 03:03:23.721348: step: 812/529, loss: 0.00020470618619583547
2023-01-23 03:03:24.853664: step: 816/529, loss: 0.07751578837633133
2023-01-23 03:03:25.993199: step: 820/529, loss: 0.055478475987911224
2023-01-23 03:03:27.149679: step: 824/529, loss: 0.0002076149103231728
2023-01-23 03:03:28.277760: step: 828/529, loss: 0.0015285492409020662
2023-01-23 03:03:29.411820: step: 832/529, loss: 0.0005379676586017013
2023-01-23 03:03:30.555104: step: 836/529, loss: 5.185840606689453
2023-01-23 03:03:31.668113: step: 840/529, loss: 0.06187605857849121
2023-01-23 03:03:32.809250: step: 844/529, loss: 0.01474685687571764
2023-01-23 03:03:33.949863: step: 848/529, loss: 0.00047321320744231343
2023-01-23 03:03:35.086576: step: 852/529, loss: 0.0045833587646484375
2023-01-23 03:03:36.218349: step: 856/529, loss: 0.04401881620287895
2023-01-23 03:03:37.363195: step: 860/529, loss: 0.0010614395141601562
2023-01-23 03:03:38.487887: step: 864/529, loss: 0.0009538650629110634
2023-01-23 03:03:39.610544: step: 868/529, loss: 0.020210839807987213
2023-01-23 03:03:40.731378: step: 872/529, loss: 0.046051979064941406
2023-01-23 03:03:41.931233: step: 876/529, loss: 0.017238711938261986
2023-01-23 03:03:43.104860: step: 880/529, loss: 0.03224611282348633
2023-01-23 03:03:44.262574: step: 884/529, loss: 0.026822710409760475
2023-01-23 03:03:45.392553: step: 888/529, loss: 0.021601391956210136
2023-01-23 03:03:46.510459: step: 892/529, loss: 0.002486324403434992
2023-01-23 03:03:47.671176: step: 896/529, loss: 0.0012258529895916581
2023-01-23 03:03:48.804588: step: 900/529, loss: 0.03464663028717041
2023-01-23 03:03:49.942672: step: 904/529, loss: 0.025440216064453125
2023-01-23 03:03:51.091573: step: 908/529, loss: 0.00488514918833971
2023-01-23 03:03:52.238056: step: 912/529, loss: 0.05924968793988228
2023-01-23 03:03:53.372394: step: 916/529, loss: 0.011789608746767044
2023-01-23 03:03:54.551244: step: 920/529, loss: 0.039760712534189224
2023-01-23 03:03:55.705742: step: 924/529, loss: 0.005775547120720148
2023-01-23 03:03:56.840113: step: 928/529, loss: 0.0044307708740234375
2023-01-23 03:03:57.963864: step: 932/529, loss: 0.2582445740699768
2023-01-23 03:03:59.083036: step: 936/529, loss: 0.010762214660644531
2023-01-23 03:04:00.230326: step: 940/529, loss: 0.05814332887530327
2023-01-23 03:04:01.361991: step: 944/529, loss: 0.4702529311180115
2023-01-23 03:04:02.477517: step: 948/529, loss: 0.14858825504779816
2023-01-23 03:04:03.618675: step: 952/529, loss: 0.004035663791000843
2023-01-23 03:04:04.790098: step: 956/529, loss: 0.0032676695846021175
2023-01-23 03:04:05.897703: step: 960/529, loss: 0.03535151854157448
2023-01-23 03:04:06.995705: step: 964/529, loss: 0.0012454986572265625
2023-01-23 03:04:08.129257: step: 968/529, loss: 0.005442905239760876
2023-01-23 03:04:09.276807: step: 972/529, loss: 0.002786731580272317
2023-01-23 03:04:10.445603: step: 976/529, loss: 0.005497360602021217
2023-01-23 03:04:11.579823: step: 980/529, loss: 0.02868823893368244
2023-01-23 03:04:12.715220: step: 984/529, loss: 0.001906967256218195
2023-01-23 03:04:13.884406: step: 988/529, loss: 0.00047397613525390625
2023-01-23 03:04:15.041193: step: 992/529, loss: 0.005586051847785711
2023-01-23 03:04:16.185209: step: 996/529, loss: 0.0027933118399232626
2023-01-23 03:04:17.341174: step: 1000/529, loss: 0.009168493561446667
2023-01-23 03:04:18.491107: step: 1004/529, loss: 0.01244125422090292
2023-01-23 03:04:19.659359: step: 1008/529, loss: 0.00011668205115711316
2023-01-23 03:04:20.795671: step: 1012/529, loss: 0.00028285980806685984
2023-01-23 03:04:21.932827: step: 1016/529, loss: 0.05203742906451225
2023-01-23 03:04:23.078377: step: 1020/529, loss: 0.014027118682861328
2023-01-23 03:04:24.207981: step: 1024/529, loss: 0.013417815789580345
2023-01-23 03:04:25.340920: step: 1028/529, loss: 0.014138412661850452
2023-01-23 03:04:26.471896: step: 1032/529, loss: 0.0002900123654399067
2023-01-23 03:04:27.634119: step: 1036/529, loss: 0.013271331787109375
2023-01-23 03:04:28.782551: step: 1040/529, loss: 0.0005670070531778038
2023-01-23 03:04:29.917307: step: 1044/529, loss: 0.0016752242809161544
2023-01-23 03:04:31.065303: step: 1048/529, loss: 0.02094888687133789
2023-01-23 03:04:32.207721: step: 1052/529, loss: 0.00692825298756361
2023-01-23 03:04:33.349169: step: 1056/529, loss: 0.015047455206513405
2023-01-23 03:04:34.492474: step: 1060/529, loss: 0.016508102416992188
2023-01-23 03:04:35.625602: step: 1064/529, loss: 0.015811825171113014
2023-01-23 03:04:36.782398: step: 1068/529, loss: 0.009197711944580078
2023-01-23 03:04:37.937943: step: 1072/529, loss: 0.0005840301746502519
2023-01-23 03:04:39.091757: step: 1076/529, loss: 0.05636577680706978
2023-01-23 03:04:40.269397: step: 1080/529, loss: 0.0032368660904467106
2023-01-23 03:04:41.431431: step: 1084/529, loss: 0.04805965721607208
2023-01-23 03:04:42.531600: step: 1088/529, loss: 0.008366644382476807
2023-01-23 03:04:43.698779: step: 1092/529, loss: 0.0026272772811353207
2023-01-23 03:04:44.846397: step: 1096/529, loss: 0.004409313201904297
2023-01-23 03:04:45.962969: step: 1100/529, loss: 0.0015930174849927425
2023-01-23 03:04:47.108536: step: 1104/529, loss: 0.004221916198730469
2023-01-23 03:04:48.263042: step: 1108/529, loss: 0.0007401466718874872
2023-01-23 03:04:49.394787: step: 1112/529, loss: 0.007759476080536842
2023-01-23 03:04:50.504847: step: 1116/529, loss: 0.010179519653320312
2023-01-23 03:04:51.664073: step: 1120/529, loss: 0.011844921857118607
2023-01-23 03:04:52.790284: step: 1124/529, loss: 0.004370689392089844
2023-01-23 03:04:53.939706: step: 1128/529, loss: 0.010753441601991653
2023-01-23 03:04:55.067312: step: 1132/529, loss: 0.002340126084163785
2023-01-23 03:04:56.230436: step: 1136/529, loss: 0.023742008954286575
2023-01-23 03:04:57.353194: step: 1140/529, loss: 0.0017427444690838456
2023-01-23 03:04:58.485325: step: 1144/529, loss: 0.0019750595092773438
2023-01-23 03:04:59.597452: step: 1148/529, loss: 0.02421693690121174
2023-01-23 03:05:00.754341: step: 1152/529, loss: 0.0011692047119140625
2023-01-23 03:05:01.925864: step: 1156/529, loss: 0.017490768805146217
2023-01-23 03:05:03.060435: step: 1160/529, loss: 0.00044231413630768657
2023-01-23 03:05:04.185969: step: 1164/529, loss: 0.004469490610063076
2023-01-23 03:05:05.316347: step: 1168/529, loss: 0.010682106018066406
2023-01-23 03:05:06.463890: step: 1172/529, loss: 0.04354462772607803
2023-01-23 03:05:07.620136: step: 1176/529, loss: 0.0017967225285246968
2023-01-23 03:05:08.754314: step: 1180/529, loss: 0.0011360167991369963
2023-01-23 03:05:09.879151: step: 1184/529, loss: 0.00029926298884674907
2023-01-23 03:05:11.030866: step: 1188/529, loss: 0.005479144863784313
2023-01-23 03:05:12.164572: step: 1192/529, loss: 0.06189250946044922
2023-01-23 03:05:13.307587: step: 1196/529, loss: 0.0006612300639972091
2023-01-23 03:05:14.435158: step: 1200/529, loss: 0.03426055982708931
2023-01-23 03:05:15.594417: step: 1204/529, loss: 0.0020305158104747534
2023-01-23 03:05:16.702685: step: 1208/529, loss: 0.0006325722206383944
2023-01-23 03:05:17.886406: step: 1212/529, loss: 0.022826479747891426
2023-01-23 03:05:19.031131: step: 1216/529, loss: 0.004124545957893133
2023-01-23 03:05:20.199779: step: 1220/529, loss: 0.09534435719251633
2023-01-23 03:05:21.345539: step: 1224/529, loss: 0.0014231681125238538
2023-01-23 03:05:22.507600: step: 1228/529, loss: 3.900528099620715e-05
2023-01-23 03:05:23.638799: step: 1232/529, loss: 0.03799267113208771
2023-01-23 03:05:24.786206: step: 1236/529, loss: 0.0035696029663085938
2023-01-23 03:05:25.914158: step: 1240/529, loss: 0.00010929107520496473
2023-01-23 03:05:27.060412: step: 1244/529, loss: 0.052858833223581314
2023-01-23 03:05:28.189407: step: 1248/529, loss: 0.008006763644516468
2023-01-23 03:05:29.352980: step: 1252/529, loss: 0.032919932156801224
2023-01-23 03:05:30.482157: step: 1256/529, loss: 0.02332305908203125
2023-01-23 03:05:31.639452: step: 1260/529, loss: 0.06275387108325958
2023-01-23 03:05:32.760490: step: 1264/529, loss: 0.033109571784734726
2023-01-23 03:05:33.911190: step: 1268/529, loss: 0.04139823839068413
2023-01-23 03:05:35.041496: step: 1272/529, loss: 0.10718798637390137
2023-01-23 03:05:36.177141: step: 1276/529, loss: 0.07257866859436035
2023-01-23 03:05:37.327518: step: 1280/529, loss: 0.0015145301586017013
2023-01-23 03:05:38.467481: step: 1284/529, loss: 0.004060077480971813
2023-01-23 03:05:39.608188: step: 1288/529, loss: 0.006896257400512695
2023-01-23 03:05:40.794400: step: 1292/529, loss: 0.00709037808701396
2023-01-23 03:05:41.939282: step: 1296/529, loss: 0.044680021703243256
2023-01-23 03:05:43.092210: step: 1300/529, loss: 0.05229535326361656
2023-01-23 03:05:44.255265: step: 1304/529, loss: 0.03190222010016441
2023-01-23 03:05:45.406393: step: 1308/529, loss: 4.00543212890625e-05
2023-01-23 03:05:46.591888: step: 1312/529, loss: 0.017056657001376152
2023-01-23 03:05:47.722136: step: 1316/529, loss: 0.020643234252929688
2023-01-23 03:05:48.841299: step: 1320/529, loss: -1.5258790426742053e-06
2023-01-23 03:05:49.955444: step: 1324/529, loss: -8.01086389401462e-06
2023-01-23 03:05:51.112141: step: 1328/529, loss: 0.003177070524543524
2023-01-23 03:05:52.263906: step: 1332/529, loss: 0.01180648896843195
2023-01-23 03:05:53.410561: step: 1336/529, loss: 0.013173295184969902
2023-01-23 03:05:54.535035: step: 1340/529, loss: 0.02430706098675728
2023-01-23 03:05:55.677603: step: 1344/529, loss: 0.03292083740234375
2023-01-23 03:05:56.793272: step: 1348/529, loss: 0.0043885232880711555
2023-01-23 03:05:57.927469: step: 1352/529, loss: 0.04280147701501846
2023-01-23 03:05:59.032619: step: 1356/529, loss: 0.011481190100312233
2023-01-23 03:06:00.154196: step: 1360/529, loss: 0.00034751894418150187
2023-01-23 03:06:01.274559: step: 1364/529, loss: 0.006107655353844166
2023-01-23 03:06:02.448139: step: 1368/529, loss: 0.009689903818070889
2023-01-23 03:06:03.568739: step: 1372/529, loss: 1.8596649169921875e-05
2023-01-23 03:06:04.721151: step: 1376/529, loss: 0.03760051727294922
2023-01-23 03:06:05.844696: step: 1380/529, loss: 0.010795784182846546
2023-01-23 03:06:06.986038: step: 1384/529, loss: 0.012355995364487171
2023-01-23 03:06:08.146362: step: 1388/529, loss: 0.002890014788135886
2023-01-23 03:06:09.296524: step: 1392/529, loss: 0.004197883419692516
2023-01-23 03:06:10.451128: step: 1396/529, loss: 0.003769779345020652
2023-01-23 03:06:11.572160: step: 1400/529, loss: 9.193420555675402e-05
2023-01-23 03:06:12.710812: step: 1404/529, loss: 0.0003452301025390625
2023-01-23 03:06:13.843757: step: 1408/529, loss: 0.00027046201284974813
2023-01-23 03:06:14.977493: step: 1412/529, loss: 0.022012829780578613
2023-01-23 03:06:16.082003: step: 1416/529, loss: 0.00020923613919876516
2023-01-23 03:06:17.211782: step: 1420/529, loss: 0.0612335205078125
2023-01-23 03:06:18.381948: step: 1424/529, loss: 0.0005936623201705515
2023-01-23 03:06:19.537876: step: 1428/529, loss: 0.0163332000374794
2023-01-23 03:06:20.680229: step: 1432/529, loss: 0.009732437320053577
2023-01-23 03:06:21.821262: step: 1436/529, loss: 0.0014553071232512593
2023-01-23 03:06:22.962364: step: 1440/529, loss: 0.04503779485821724
2023-01-23 03:06:24.109096: step: 1444/529, loss: 0.00019503833027556539
2023-01-23 03:06:25.254811: step: 1448/529, loss: 0.0036336900666356087
2023-01-23 03:06:26.405362: step: 1452/529, loss: 0.005965232849121094
2023-01-23 03:06:27.540966: step: 1456/529, loss: 0.002640151884406805
2023-01-23 03:06:28.684301: step: 1460/529, loss: 0.12068986892700195
2023-01-23 03:06:29.823894: step: 1464/529, loss: 0.009997272863984108
2023-01-23 03:06:30.968816: step: 1468/529, loss: 0.06069488823413849
2023-01-23 03:06:32.112738: step: 1472/529, loss: 6.351471529342234e-05
2023-01-23 03:06:33.286939: step: 1476/529, loss: 0.0010111809242516756
2023-01-23 03:06:34.423050: step: 1480/529, loss: 0.07010859996080399
2023-01-23 03:06:35.555013: step: 1484/529, loss: 0.007163238245993853
2023-01-23 03:06:36.685628: step: 1488/529, loss: 0.00947561301290989
2023-01-23 03:06:37.829651: step: 1492/529, loss: 0.038003161549568176
2023-01-23 03:06:38.983983: step: 1496/529, loss: 0.013702679425477982
2023-01-23 03:06:40.127887: step: 1500/529, loss: 0.03276081383228302
2023-01-23 03:06:41.265348: step: 1504/529, loss: 0.42165660858154297
2023-01-23 03:06:42.414232: step: 1508/529, loss: 0.0001623153657419607
2023-01-23 03:06:43.554671: step: 1512/529, loss: 0.06620216369628906
2023-01-23 03:06:44.695323: step: 1516/529, loss: 0.00433802604675293
2023-01-23 03:06:45.866401: step: 1520/529, loss: 0.0019710541237145662
2023-01-23 03:06:47.026593: step: 1524/529, loss: 0.09248819202184677
2023-01-23 03:06:48.166989: step: 1528/529, loss: 0.0026967048179358244
2023-01-23 03:06:49.294235: step: 1532/529, loss: 0.02864818647503853
2023-01-23 03:06:50.409539: step: 1536/529, loss: 0.0017695426940917969
2023-01-23 03:06:51.535300: step: 1540/529, loss: 0.011477851308882236
2023-01-23 03:06:52.673629: step: 1544/529, loss: 0.0023189543280750513
2023-01-23 03:06:53.813754: step: 1548/529, loss: 0.009379958733916283
2023-01-23 03:06:54.942225: step: 1552/529, loss: 0.011292267590761185
2023-01-23 03:06:56.053407: step: 1556/529, loss: 0.021019697189331055
2023-01-23 03:06:57.168789: step: 1560/529, loss: 0.004131889436393976
2023-01-23 03:06:58.323932: step: 1564/529, loss: 0.0018106460338458419
2023-01-23 03:06:59.453925: step: 1568/529, loss: 0.001531314803287387
2023-01-23 03:07:00.605406: step: 1572/529, loss: 0.05347738042473793
2023-01-23 03:07:01.747208: step: 1576/529, loss: 0.0026765824295580387
2023-01-23 03:07:02.926656: step: 1580/529, loss: 0.02463665045797825
2023-01-23 03:07:04.093785: step: 1584/529, loss: 0.022698307409882545
2023-01-23 03:07:05.235111: step: 1588/529, loss: 0.0006662369123660028
2023-01-23 03:07:06.396681: step: 1592/529, loss: 0.00033886433811858296
2023-01-23 03:07:07.561108: step: 1596/529, loss: 0.04249248653650284
2023-01-23 03:07:08.696188: step: 1600/529, loss: 0.010273169726133347
2023-01-23 03:07:09.836848: step: 1604/529, loss: 0.003914594650268555
2023-01-23 03:07:10.973894: step: 1608/529, loss: 0.010500717908143997
2023-01-23 03:07:12.118280: step: 1612/529, loss: 0.03784504160284996
2023-01-23 03:07:13.283353: step: 1616/529, loss: 0.029215574264526367
2023-01-23 03:07:14.412605: step: 1620/529, loss: 0.007312011905014515
2023-01-23 03:07:15.534315: step: 1624/529, loss: 0.001105880830436945
2023-01-23 03:07:16.688196: step: 1628/529, loss: 0.0091393468901515
2023-01-23 03:07:17.838120: step: 1632/529, loss: 0.0004163742414675653
2023-01-23 03:07:19.005506: step: 1636/529, loss: 0.025879859924316406
2023-01-23 03:07:20.151966: step: 1640/529, loss: 0.007389450445771217
2023-01-23 03:07:21.297542: step: 1644/529, loss: 0.05246887356042862
2023-01-23 03:07:22.434114: step: 1648/529, loss: 0.00019731521024368703
2023-01-23 03:07:23.569748: step: 1652/529, loss: 0.03374490886926651
2023-01-23 03:07:24.715244: step: 1656/529, loss: 0.008224106393754482
2023-01-23 03:07:25.827569: step: 1660/529, loss: 0.004824733827263117
2023-01-23 03:07:26.981850: step: 1664/529, loss: 0.0060592652298510075
2023-01-23 03:07:28.092761: step: 1668/529, loss: 0.8607851266860962
2023-01-23 03:07:29.210177: step: 1672/529, loss: 0.006881999783217907
2023-01-23 03:07:30.291593: step: 1676/529, loss: 0.0006945609929971397
2023-01-23 03:07:31.401928: step: 1680/529, loss: 0.025945473462343216
2023-01-23 03:07:32.544967: step: 1684/529, loss: 0.008211707696318626
2023-01-23 03:07:33.684390: step: 1688/529, loss: 0.022715091705322266
2023-01-23 03:07:34.826696: step: 1692/529, loss: 0.011531829833984375
2023-01-23 03:07:35.941668: step: 1696/529, loss: 0.009366989135742188
2023-01-23 03:07:37.057953: step: 1700/529, loss: 0.033548545092344284
2023-01-23 03:07:38.197202: step: 1704/529, loss: 0.0002498626708984375
2023-01-23 03:07:39.323768: step: 1708/529, loss: 0.006572151090949774
2023-01-23 03:07:40.450938: step: 1712/529, loss: 0.009911156259477139
2023-01-23 03:07:41.576447: step: 1716/529, loss: 0.028431225568056107
2023-01-23 03:07:42.722849: step: 1720/529, loss: 0.11921444535255432
2023-01-23 03:07:43.900645: step: 1724/529, loss: 0.0007851601112633944
2023-01-23 03:07:45.029723: step: 1728/529, loss: 0.002255010651424527
2023-01-23 03:07:46.172145: step: 1732/529, loss: 0.0001012802094919607
2023-01-23 03:07:47.291531: step: 1736/529, loss: 0.011163998395204544
2023-01-23 03:07:48.414299: step: 1740/529, loss: 0.00021929740614723414
2023-01-23 03:07:49.534753: step: 1744/529, loss: 0.0036584853660315275
2023-01-23 03:07:50.664510: step: 1748/529, loss: 9.746551950229332e-05
2023-01-23 03:07:51.840913: step: 1752/529, loss: 0.0025769234634935856
2023-01-23 03:07:52.966223: step: 1756/529, loss: 0.010653305798768997
2023-01-23 03:07:54.081093: step: 1760/529, loss: 0.0016676426166668534
2023-01-23 03:07:55.231247: step: 1764/529, loss: 0.014390897937119007
2023-01-23 03:07:56.364455: step: 1768/529, loss: 0.016907215118408203
2023-01-23 03:07:57.500538: step: 1772/529, loss: 0.00181837088894099
2023-01-23 03:07:58.649156: step: 1776/529, loss: 0.02114715427160263
2023-01-23 03:07:59.793787: step: 1780/529, loss: 0.0076562403701245785
2023-01-23 03:08:00.939625: step: 1784/529, loss: 0.013175916858017445
2023-01-23 03:08:02.071040: step: 1788/529, loss: 0.008378982543945312
2023-01-23 03:08:03.227788: step: 1792/529, loss: 0.0009254455799236894
2023-01-23 03:08:04.337082: step: 1796/529, loss: 3.719329833984375e-05
2023-01-23 03:08:05.470633: step: 1800/529, loss: 0.005161189939826727
2023-01-23 03:08:06.586481: step: 1804/529, loss: 0.005507952068001032
2023-01-23 03:08:07.703340: step: 1808/529, loss: 6.432532973121852e-05
2023-01-23 03:08:08.840780: step: 1812/529, loss: 0.013687323778867722
2023-01-23 03:08:09.989021: step: 1816/529, loss: 0.01939830742776394
2023-01-23 03:08:11.120100: step: 1820/529, loss: 0.012773562222719193
2023-01-23 03:08:12.266220: step: 1824/529, loss: 0.014494610950350761
2023-01-23 03:08:13.405724: step: 1828/529, loss: 0.013984155841171741
2023-01-23 03:08:14.540077: step: 1832/529, loss: 0.0008624077308923006
2023-01-23 03:08:15.647938: step: 1836/529, loss: 0.0001469850685680285
2023-01-23 03:08:16.809541: step: 1840/529, loss: 0.0025678633246570826
2023-01-23 03:08:17.981184: step: 1844/529, loss: 0.0008081913110800087
2023-01-23 03:08:19.143707: step: 1848/529, loss: 0.0008213043329305947
2023-01-23 03:08:20.295585: step: 1852/529, loss: 0.0001049041748046875
2023-01-23 03:08:21.429076: step: 1856/529, loss: 0.026462554931640625
2023-01-23 03:08:22.602675: step: 1860/529, loss: 0.0002541542053222656
2023-01-23 03:08:23.772704: step: 1864/529, loss: 0.0042692190036177635
2023-01-23 03:08:24.897411: step: 1868/529, loss: 0.0003243446699343622
2023-01-23 03:08:26.032606: step: 1872/529, loss: 0.050055406987667084
2023-01-23 03:08:27.188069: step: 1876/529, loss: 0.004984998609870672
2023-01-23 03:08:28.330980: step: 1880/529, loss: 0.009220505133271217
2023-01-23 03:08:29.484452: step: 1884/529, loss: 0.008108139038085938
2023-01-23 03:08:30.610546: step: 1888/529, loss: 0.013308144174516201
2023-01-23 03:08:31.748224: step: 1892/529, loss: 0.0006589888944290578
2023-01-23 03:08:32.910826: step: 1896/529, loss: 0.06773176044225693
2023-01-23 03:08:34.042739: step: 1900/529, loss: 1.068115216185106e-05
2023-01-23 03:08:35.187584: step: 1904/529, loss: 0.04861483350396156
2023-01-23 03:08:36.329801: step: 1908/529, loss: 0.040887072682380676
2023-01-23 03:08:37.479341: step: 1912/529, loss: 0.00913095474243164
2023-01-23 03:08:38.617964: step: 1916/529, loss: -1.4972686585679185e-05
2023-01-23 03:08:39.747007: step: 1920/529, loss: 0.00932455062866211
2023-01-23 03:08:40.889440: step: 1924/529, loss: 0.002048921538516879
2023-01-23 03:08:42.059448: step: 1928/529, loss: 7.524490501964465e-05
2023-01-23 03:08:43.209924: step: 1932/529, loss: 0.004367828369140625
2023-01-23 03:08:44.364477: step: 1936/529, loss: 0.019753647968173027
2023-01-23 03:08:45.545519: step: 1940/529, loss: 0.17170429229736328
2023-01-23 03:08:46.691870: step: 1944/529, loss: 0.0036743164528161287
2023-01-23 03:08:47.863741: step: 1948/529, loss: 0.014732170850038528
2023-01-23 03:08:49.089956: step: 1952/529, loss: 0.0004589080926962197
2023-01-23 03:08:50.239695: step: 1956/529, loss: 0.0001373291015625
2023-01-23 03:08:51.401411: step: 1960/529, loss: 2.222557783126831
2023-01-23 03:08:52.539264: step: 1964/529, loss: 0.0262908935546875
2023-01-23 03:08:53.673919: step: 1968/529, loss: 0.09304027259349823
2023-01-23 03:08:54.869614: step: 1972/529, loss: 0.0005405425908975303
2023-01-23 03:08:56.000119: step: 1976/529, loss: 3.4904482163256034e-05
2023-01-23 03:08:57.106119: step: 1980/529, loss: 0.0441831573843956
2023-01-23 03:08:58.231860: step: 1984/529, loss: 0.0041325571946799755
2023-01-23 03:08:59.373981: step: 1988/529, loss: 0.055832672864198685
2023-01-23 03:09:00.523837: step: 1992/529, loss: 0.01119308453053236
2023-01-23 03:09:01.667681: step: 1996/529, loss: 0.002911376766860485
2023-01-23 03:09:02.781384: step: 2000/529, loss: 0.034895945340394974
2023-01-23 03:09:03.911371: step: 2004/529, loss: 0.00010619163367664441
2023-01-23 03:09:05.019131: step: 2008/529, loss: 0.0012832642532885075
2023-01-23 03:09:06.126572: step: 2012/529, loss: 0.06861686706542969
2023-01-23 03:09:07.275050: step: 2016/529, loss: 2.8896332878503017e-05
2023-01-23 03:09:08.430873: step: 2020/529, loss: 0.007028484251350164
2023-01-23 03:09:09.560527: step: 2024/529, loss: 2.5081633793888614e-05
2023-01-23 03:09:10.680118: step: 2028/529, loss: 0.00206584925763309
2023-01-23 03:09:11.820620: step: 2032/529, loss: 0.00129871373064816
2023-01-23 03:09:12.943085: step: 2036/529, loss: 0.010124778375029564
2023-01-23 03:09:14.067533: step: 2040/529, loss: 0.0001924514799611643
2023-01-23 03:09:15.187713: step: 2044/529, loss: 0.006847286596894264
2023-01-23 03:09:16.332459: step: 2048/529, loss: 0.03153085708618164
2023-01-23 03:09:17.486039: step: 2052/529, loss: 0.000244140625
2023-01-23 03:09:18.620979: step: 2056/529, loss: 0.005618286319077015
2023-01-23 03:09:19.764789: step: 2060/529, loss: 0.004194832406938076
2023-01-23 03:09:20.904442: step: 2064/529, loss: 0.0020910261664539576
2023-01-23 03:09:22.039540: step: 2068/529, loss: 0.002396106719970703
2023-01-23 03:09:23.189363: step: 2072/529, loss: 0.0002865791320800781
2023-01-23 03:09:24.339191: step: 2076/529, loss: 0.002443695208057761
2023-01-23 03:09:25.507094: step: 2080/529, loss: 0.00046138762263581157
2023-01-23 03:09:26.620852: step: 2084/529, loss: 0.0004123687685932964
2023-01-23 03:09:27.743950: step: 2088/529, loss: 0.0017341614002361894
2023-01-23 03:09:28.889826: step: 2092/529, loss: 0.0003719329833984375
2023-01-23 03:09:30.037610: step: 2096/529, loss: 0.004864406771957874
2023-01-23 03:09:31.199648: step: 2100/529, loss: 0.0026886940468102694
2023-01-23 03:09:32.319407: step: 2104/529, loss: 0.033385373651981354
2023-01-23 03:09:33.440565: step: 2108/529, loss: 0.018949126824736595
2023-01-23 03:09:34.593019: step: 2112/529, loss: 5.569458153331652e-05
2023-01-23 03:09:35.736937: step: 2116/529, loss: 0.0035600662231445312
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.6273022751895991, 'r': 0.7709720372836218, 'f1': 0.6917562724014338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6206896551724138, 'r': 0.7717265353418308, 'f1': 0.6880165289256198}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5930232558139535, 'r': 0.9444444444444444, 'f1': 0.7285714285714286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.625, 'r': 0.5555555555555556, 'f1': 0.5882352941176471}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
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': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 03:10:17.225949: step: 4/529, loss: 0.003976917359977961
2023-01-23 03:10:18.371771: step: 8/529, loss: 0.0007116317865438759
2023-01-23 03:10:19.502222: step: 12/529, loss: 9.403229341842234e-05
2023-01-23 03:10:20.637748: step: 16/529, loss: 0.0007730484358035028
2023-01-23 03:10:21.781101: step: 20/529, loss: 0.01691007800400257
2023-01-23 03:10:22.927002: step: 24/529, loss: 0.00024003982252907008
2023-01-23 03:10:24.065556: step: 28/529, loss: 0.001754379365593195
2023-01-23 03:10:25.179346: step: 32/529, loss: 7.877349707996473e-05
2023-01-23 03:10:26.302058: step: 36/529, loss: 0.0045642852783203125
2023-01-23 03:10:27.446297: step: 40/529, loss: 0.0006595611339434981
2023-01-23 03:10:28.584087: step: 44/529, loss: 0.0001396715670125559
2023-01-23 03:10:29.728444: step: 48/529, loss: 0.03726153448224068
2023-01-23 03:10:30.879207: step: 52/529, loss: 0.004734421148896217
2023-01-23 03:10:31.992937: step: 56/529, loss: 3.910065061063506e-06
2023-01-23 03:10:33.173433: step: 60/529, loss: 0.0041914465837180614
2023-01-23 03:10:34.350473: step: 64/529, loss: 0.042818259447813034
2023-01-23 03:10:35.520037: step: 68/529, loss: 0.0004276275576557964
2023-01-23 03:10:36.637991: step: 72/529, loss: 0.0005197286955080926
2023-01-23 03:10:37.766494: step: 76/529, loss: 0.0005234241834841669
2023-01-23 03:10:38.894593: step: 80/529, loss: 3.4046173823298886e-05
2023-01-23 03:10:40.017939: step: 84/529, loss: 0.06422004848718643
2023-01-23 03:10:41.177406: step: 88/529, loss: -6.961822691664565e-06
2023-01-23 03:10:42.336657: step: 92/529, loss: 0.6131331920623779
2023-01-23 03:10:43.465624: step: 96/529, loss: 0.0006634712335653603
2023-01-23 03:10:44.637632: step: 100/529, loss: 0.020165253430604935
2023-01-23 03:10:45.801811: step: 104/529, loss: 0.008333302102982998
2023-01-23 03:10:46.981570: step: 108/529, loss: 0.0014547348255291581
2023-01-23 03:10:48.121916: step: 112/529, loss: 0.0008433342445641756
2023-01-23 03:10:49.230535: step: 116/529, loss: 0.0036572455428540707
2023-01-23 03:10:50.391434: step: 120/529, loss: 0.016436384990811348
2023-01-23 03:10:51.533381: step: 124/529, loss: 0.0006477356655523181
2023-01-23 03:10:52.659796: step: 128/529, loss: 0.008415688760578632
2023-01-23 03:10:53.769933: step: 132/529, loss: 0.06058826297521591
2023-01-23 03:10:54.906957: step: 136/529, loss: 0.1271534115076065
2023-01-23 03:10:56.027598: step: 140/529, loss: 1.8882754375226796e-05
2023-01-23 03:10:57.204677: step: 144/529, loss: 0.01803712733089924
2023-01-23 03:10:58.349995: step: 148/529, loss: 0.0022476196754723787
2023-01-23 03:10:59.502517: step: 152/529, loss: 0.025887491181492805
2023-01-23 03:11:00.675796: step: 156/529, loss: 0.003461647080257535
2023-01-23 03:11:01.808106: step: 160/529, loss: 4.692077709478326e-05
2023-01-23 03:11:02.946405: step: 164/529, loss: 0.0012077331775799394
2023-01-23 03:11:04.098975: step: 168/529, loss: 0.0024536133278161287
2023-01-23 03:11:05.225137: step: 172/529, loss: 0.0021148682571947575
2023-01-23 03:11:06.346432: step: 176/529, loss: 0.024805927649140358
2023-01-23 03:11:07.505581: step: 180/529, loss: 0.0050389766693115234
2023-01-23 03:11:08.636751: step: 184/529, loss: 0.008747505955398083
2023-01-23 03:11:09.763073: step: 188/529, loss: 0.010238075628876686
2023-01-23 03:11:10.909466: step: 192/529, loss: 0.00833969097584486
2023-01-23 03:11:12.025775: step: 196/529, loss: 0.0011187553172931075
2023-01-23 03:11:13.159709: step: 200/529, loss: 0.0023651123046875
2023-01-23 03:11:14.285334: step: 204/529, loss: 0.0006448745843954384
2023-01-23 03:11:15.412065: step: 208/529, loss: 0.007282924838364124
2023-01-23 03:11:16.535136: step: 212/529, loss: 0.01189346332103014
2023-01-23 03:11:17.687358: step: 216/529, loss: 0.00533142127096653
2023-01-23 03:11:18.822806: step: 220/529, loss: 3.0517576306010596e-06
2023-01-23 03:11:19.955465: step: 224/529, loss: 0.02095642127096653
2023-01-23 03:11:21.078138: step: 228/529, loss: 0.015183067880570889
2023-01-23 03:11:22.246725: step: 232/529, loss: 0.0008382797823287547
2023-01-23 03:11:23.360105: step: 236/529, loss: 0.0733637809753418
2023-01-23 03:11:24.498545: step: 240/529, loss: 3.5977365769213066e-05
2023-01-23 03:11:25.653426: step: 244/529, loss: 0.0012701033847406507
2023-01-23 03:11:26.792495: step: 248/529, loss: 0.06110992282629013
2023-01-23 03:11:27.918936: step: 252/529, loss: 0.02470588870346546
2023-01-23 03:11:29.059941: step: 256/529, loss: 0.00014648436626885086
2023-01-23 03:11:30.216877: step: 260/529, loss: 0.0009017467382363975
2023-01-23 03:11:31.378740: step: 264/529, loss: 0.00015544891357421875
2023-01-23 03:11:32.513250: step: 268/529, loss: 0.023493194952607155
2023-01-23 03:11:33.672931: step: 272/529, loss: 0.00033969880314543843
2023-01-23 03:11:34.821685: step: 276/529, loss: 0.05209064856171608
2023-01-23 03:11:36.011153: step: 280/529, loss: 0.2062522917985916
2023-01-23 03:11:37.173827: step: 284/529, loss: 0.014591837301850319
2023-01-23 03:11:38.320249: step: 288/529, loss: 0.02383279800415039
2023-01-23 03:11:39.494411: step: 292/529, loss: 0.008657360449433327
2023-01-23 03:11:40.638100: step: 296/529, loss: 8.873939805198461e-05
2023-01-23 03:11:41.768276: step: 300/529, loss: 0.014673185534775257
2023-01-23 03:11:42.937977: step: 304/529, loss: 0.010455131530761719
2023-01-23 03:11:44.073005: step: 308/529, loss: 0.011625290848314762
2023-01-23 03:11:45.202667: step: 312/529, loss: 0.029275894165039062
2023-01-23 03:11:46.363652: step: 316/529, loss: 0.010558987967669964
2023-01-23 03:11:47.502664: step: 320/529, loss: 0.07185535132884979
2023-01-23 03:11:48.655553: step: 324/529, loss: 0.06779918074607849
2023-01-23 03:11:49.775306: step: 328/529, loss: 0.0048233033157885075
2023-01-23 03:11:50.914464: step: 332/529, loss: 0.0001733779936330393
2023-01-23 03:11:52.038648: step: 336/529, loss: 0.000358390825567767
2023-01-23 03:11:53.182873: step: 340/529, loss: 0.00010032653517555445
2023-01-23 03:11:54.336431: step: 344/529, loss: 0.0033226015511900187
2023-01-23 03:11:55.454960: step: 348/529, loss: 0.0001926422119140625
2023-01-23 03:11:56.591146: step: 352/529, loss: 0.0001847267267294228
2023-01-23 03:11:57.739809: step: 356/529, loss: 0.002921485807746649
2023-01-23 03:11:58.874128: step: 360/529, loss: 0.0011449814774096012
2023-01-23 03:12:00.029540: step: 364/529, loss: 1.831054760259576e-05
2023-01-23 03:12:01.232949: step: 368/529, loss: 0.0016298294067382812
2023-01-23 03:12:02.377639: step: 372/529, loss: 7.228850881801918e-05
2023-01-23 03:12:03.501368: step: 376/529, loss: 1.373290979245212e-05
2023-01-23 03:12:04.669505: step: 380/529, loss: 0.0043497090227901936
2023-01-23 03:12:05.826093: step: 384/529, loss: 0.026889802888035774
2023-01-23 03:12:06.965161: step: 388/529, loss: 0.0010818481678143144
2023-01-23 03:12:08.110065: step: 392/529, loss: 0.004097366705536842
2023-01-23 03:12:09.251856: step: 396/529, loss: 0.022572899237275124
2023-01-23 03:12:10.402070: step: 400/529, loss: 0.002540969755500555
2023-01-23 03:12:11.526375: step: 404/529, loss: 0.006014490034431219
2023-01-23 03:12:12.673123: step: 408/529, loss: 0.0003115653817076236
2023-01-23 03:12:13.788691: step: 412/529, loss: 0.002440929412841797
2023-01-23 03:12:14.926399: step: 416/529, loss: 0.0684998482465744
2023-01-23 03:12:16.065336: step: 420/529, loss: 0.061145883053541183
2023-01-23 03:12:17.209737: step: 424/529, loss: 0.003925133030861616
2023-01-23 03:12:18.370832: step: 428/529, loss: 0.0005898475646972656
2023-01-23 03:12:19.519053: step: 432/529, loss: 0.000568389892578125
2023-01-23 03:12:20.638095: step: 436/529, loss: 0.0006813049549236894
2023-01-23 03:12:21.751309: step: 440/529, loss: 0.00014905929856467992
2023-01-23 03:12:22.912105: step: 444/529, loss: 0.00042982102604582906
2023-01-23 03:12:24.035062: step: 448/529, loss: 0.0012778282398357987
2023-01-23 03:12:25.186146: step: 452/529, loss: 0.03290600702166557
2023-01-23 03:12:26.334739: step: 456/529, loss: 0.008971787057816982
2023-01-23 03:12:27.481973: step: 460/529, loss: 0.0010578155051916838
2023-01-23 03:12:28.626133: step: 464/529, loss: 0.00021486282639671117
2023-01-23 03:12:29.778144: step: 468/529, loss: 0.01743030734360218
2023-01-23 03:12:30.927000: step: 472/529, loss: 0.03139457851648331
2023-01-23 03:12:32.056747: step: 476/529, loss: 0.00033626556978560984
2023-01-23 03:12:33.203767: step: 480/529, loss: 0.0017955780494958162
2023-01-23 03:12:34.323979: step: 484/529, loss: 0.0002829551522154361
2023-01-23 03:12:35.456564: step: 488/529, loss: 0.01783580705523491
2023-01-23 03:12:36.590302: step: 492/529, loss: 0.01042957417666912
2023-01-23 03:12:37.689555: step: 496/529, loss: 0.00020550489716697484
2023-01-23 03:12:38.811649: step: 500/529, loss: 0.0010252000065520406
2023-01-23 03:12:39.958095: step: 504/529, loss: 0.02346658706665039
2023-01-23 03:12:41.100603: step: 508/529, loss: 0.000286275171674788
2023-01-23 03:12:42.242258: step: 512/529, loss: 0.005281639285385609
2023-01-23 03:12:43.409721: step: 516/529, loss: 0.010306740179657936
2023-01-23 03:12:44.507718: step: 520/529, loss: 0.00015897752018645406
2023-01-23 03:12:45.670084: step: 524/529, loss: 0.02437725104391575
2023-01-23 03:12:46.788296: step: 528/529, loss: 0.0004380226309876889
2023-01-23 03:12:47.933381: step: 532/529, loss: 0.00303914537653327
2023-01-23 03:12:49.042982: step: 536/529, loss: 0.0004276275576557964
2023-01-23 03:12:50.184697: step: 540/529, loss: 0.00116815569344908
2023-01-23 03:12:51.326325: step: 544/529, loss: 0.0029674528632313013
2023-01-23 03:12:52.478633: step: 548/529, loss: 0.05657081678509712
2023-01-23 03:12:53.628663: step: 552/529, loss: 0.0002506732998881489
2023-01-23 03:12:54.755287: step: 556/529, loss: 0.004369258880615234
2023-01-23 03:12:55.879405: step: 560/529, loss: 0.03371744230389595
2023-01-23 03:12:57.017226: step: 564/529, loss: 0.013393736444413662
2023-01-23 03:12:58.141757: step: 568/529, loss: 0.022926712408661842
2023-01-23 03:12:59.283311: step: 572/529, loss: 0.021451378241181374
2023-01-23 03:13:00.418935: step: 576/529, loss: 0.040910910815000534
2023-01-23 03:13:01.568865: step: 580/529, loss: 0.0003177642938680947
2023-01-23 03:13:02.719474: step: 584/529, loss: 0.0004455089510884136
2023-01-23 03:13:03.846308: step: 588/529, loss: 0.06816544383764267
2023-01-23 03:13:05.011526: step: 592/529, loss: 0.018665695562958717
2023-01-23 03:13:06.188813: step: 596/529, loss: 0.007628059946000576
2023-01-23 03:13:07.330621: step: 600/529, loss: 0.026865579187870026
2023-01-23 03:13:08.478319: step: 604/529, loss: 0.03370781987905502
2023-01-23 03:13:09.622800: step: 608/529, loss: 0.6259747743606567
2023-01-23 03:13:10.762918: step: 612/529, loss: 0.028895188122987747
2023-01-23 03:13:11.911630: step: 616/529, loss: 6.103515625e-05
2023-01-23 03:13:13.035071: step: 620/529, loss: 0.027737855911254883
2023-01-23 03:13:14.167153: step: 624/529, loss: 0.013202572241425514
2023-01-23 03:13:15.308307: step: 628/529, loss: 1.4925002687959932e-05
2023-01-23 03:13:16.462591: step: 632/529, loss: 0.019480038434267044
2023-01-23 03:13:17.603412: step: 636/529, loss: 0.002047896385192871
2023-01-23 03:13:18.741962: step: 640/529, loss: 3.80516066798009e-05
2023-01-23 03:13:19.907818: step: 644/529, loss: 0.0040798187255859375
2023-01-23 03:13:21.033802: step: 648/529, loss: 0.06549052894115448
2023-01-23 03:13:22.182692: step: 652/529, loss: 0.0027616501320153475
2023-01-23 03:13:23.326508: step: 656/529, loss: 0.001287317369133234
2023-01-23 03:13:24.452665: step: 660/529, loss: 0.0009366989252157509
2023-01-23 03:13:25.656298: step: 664/529, loss: 6.027221752447076e-05
2023-01-23 03:13:26.777346: step: 668/529, loss: 0.005042982287704945
2023-01-23 03:13:27.910173: step: 672/529, loss: 0.0068329814821481705
2023-01-23 03:13:29.049304: step: 676/529, loss: 0.007976150140166283
2023-01-23 03:13:30.169698: step: 680/529, loss: 3.471374657237902e-05
2023-01-23 03:13:31.322356: step: 684/529, loss: 0.0006537437438964844
2023-01-23 03:13:32.492822: step: 688/529, loss: 0.004265117924660444
2023-01-23 03:13:33.646390: step: 692/529, loss: 0.009064865298569202
2023-01-23 03:13:34.768830: step: 696/529, loss: 0.0008216142887249589
2023-01-23 03:13:35.896352: step: 700/529, loss: 0.0013271331554278731
2023-01-23 03:13:37.040414: step: 704/529, loss: 6.461143493652344e-05
2023-01-23 03:13:38.198210: step: 708/529, loss: 2.47955322265625e-05
2023-01-23 03:13:39.343550: step: 712/529, loss: 0.06059322506189346
2023-01-23 03:13:40.516460: step: 716/529, loss: 0.0009393692016601562
2023-01-23 03:13:41.661575: step: 720/529, loss: 0.013641834259033203
2023-01-23 03:13:42.797869: step: 724/529, loss: 0.005165958311408758
2023-01-23 03:13:43.955773: step: 728/529, loss: 0.021885670721530914
2023-01-23 03:13:45.112583: step: 732/529, loss: 0.0003195345343556255
2023-01-23 03:13:46.276418: step: 736/529, loss: 2.5653840566519648e-05
2023-01-23 03:13:47.416249: step: 740/529, loss: 5.154609971214086e-05
2023-01-23 03:13:48.576948: step: 744/529, loss: 0.013858318328857422
2023-01-23 03:13:49.699037: step: 748/529, loss: 0.04328355938196182
2023-01-23 03:13:50.838162: step: 752/529, loss: 0.00010395050048828125
2023-01-23 03:13:51.979781: step: 756/529, loss: 0.055783748626708984
2023-01-23 03:13:53.115546: step: 760/529, loss: 0.005009269807487726
2023-01-23 03:13:54.245928: step: 764/529, loss: 0.02104063145816326
2023-01-23 03:13:55.381436: step: 768/529, loss: 0.009302712045609951
2023-01-23 03:13:56.520056: step: 772/529, loss: 0.00038337710429914296
2023-01-23 03:13:57.656501: step: 776/529, loss: 0.0026230812072753906
2023-01-23 03:13:58.800992: step: 780/529, loss: 0.00015726088895462453
2023-01-23 03:13:59.947270: step: 784/529, loss: 0.0016744614113122225
2023-01-23 03:14:01.069303: step: 788/529, loss: 0.0002925872977357358
2023-01-23 03:14:02.206704: step: 792/529, loss: 0.0008006095886230469
2023-01-23 03:14:03.331566: step: 796/529, loss: 0.00017790794663596898
2023-01-23 03:14:04.480525: step: 800/529, loss: 0.00040311814518645406
2023-01-23 03:14:05.628790: step: 804/529, loss: 1.7353135347366333
2023-01-23 03:14:06.735642: step: 808/529, loss: 0.0259794220328331
2023-01-23 03:14:07.899623: step: 812/529, loss: 0.016849517822265625
2023-01-23 03:14:09.012099: step: 816/529, loss: 0.00044155120849609375
2023-01-23 03:14:10.152149: step: 820/529, loss: 0.08364319801330566
2023-01-23 03:14:11.321962: step: 824/529, loss: 0.00048542022705078125
2023-01-23 03:14:12.455715: step: 828/529, loss: 0.0005571842193603516
2023-01-23 03:14:13.614749: step: 832/529, loss: 0.015031195245683193
2023-01-23 03:14:14.748425: step: 836/529, loss: 0.026267431676387787
2023-01-23 03:14:15.887117: step: 840/529, loss: 1.0108947208209429e-05
2023-01-23 03:14:16.979634: step: 844/529, loss: 0.00038313865661621094
2023-01-23 03:14:18.139111: step: 848/529, loss: 0.006134796421974897
2023-01-23 03:14:19.289913: step: 852/529, loss: 0.0001253128139069304
2023-01-23 03:14:20.404588: step: 856/529, loss: 0.0006963729974813759
2023-01-23 03:14:21.522769: step: 860/529, loss: 0.0036382675170898438
2023-01-23 03:14:22.644589: step: 864/529, loss: 4.386901309771929e-06
2023-01-23 03:14:23.814392: step: 868/529, loss: 0.006336594000458717
2023-01-23 03:14:24.924926: step: 872/529, loss: 0.0009226799593307078
2023-01-23 03:14:26.064659: step: 876/529, loss: 0.0299332607537508
2023-01-23 03:14:27.213956: step: 880/529, loss: 0.04130411148071289
2023-01-23 03:14:28.346095: step: 884/529, loss: 0.0034194947220385075
2023-01-23 03:14:29.500227: step: 888/529, loss: 0.0030481338035315275
2023-01-23 03:14:30.621778: step: 892/529, loss: 0.0015429496997967362
2023-01-23 03:14:31.788655: step: 896/529, loss: 0.02643413655459881
2023-01-23 03:14:32.912282: step: 900/529, loss: 0.0004451751592569053
2023-01-23 03:14:34.062148: step: 904/529, loss: 0.07229682058095932
2023-01-23 03:14:35.199938: step: 908/529, loss: 0.007631492801010609
2023-01-23 03:14:36.323203: step: 912/529, loss: 0.005826759152114391
2023-01-23 03:14:37.494831: step: 916/529, loss: 0.00020294189744163305
2023-01-23 03:14:38.654877: step: 920/529, loss: 0.04877859726548195
2023-01-23 03:14:39.789937: step: 924/529, loss: 0.0048805237747728825
2023-01-23 03:14:40.909717: step: 928/529, loss: 0.00014190674119163305
2023-01-23 03:14:42.029813: step: 932/529, loss: 0.0009296417119912803
2023-01-23 03:14:43.190975: step: 936/529, loss: 0.011898231692612171
2023-01-23 03:14:44.361802: step: 940/529, loss: 0.0026494981721043587
2023-01-23 03:14:45.511171: step: 944/529, loss: 0.0008689879905432463
2023-01-23 03:14:46.661856: step: 948/529, loss: 0.00023279190645553172
2023-01-23 03:14:47.797588: step: 952/529, loss: 0.0005958557012490928
2023-01-23 03:14:48.941192: step: 956/529, loss: 0.0007064819219522178
2023-01-23 03:14:50.088643: step: 960/529, loss: 0.00023002624220680445
2023-01-23 03:14:51.207434: step: 964/529, loss: 5.807876732433215e-05
2023-01-23 03:14:52.375235: step: 968/529, loss: 0.5852420926094055
2023-01-23 03:14:53.483750: step: 972/529, loss: 1.3828278042637976e-06
2023-01-23 03:14:54.649017: step: 976/529, loss: 0.010821724310517311
2023-01-23 03:14:55.764029: step: 980/529, loss: 0.0022260667756199837
2023-01-23 03:14:56.905048: step: 984/529, loss: 0.0006770610925741494
2023-01-23 03:14:58.032287: step: 988/529, loss: 0.04202480614185333
2023-01-23 03:14:59.176775: step: 992/529, loss: 0.0030164720956236124
2023-01-23 03:15:00.339040: step: 996/529, loss: 0.0007476806640625
2023-01-23 03:15:01.474468: step: 1000/529, loss: 0.03749847412109375
2023-01-23 03:15:02.600271: step: 1004/529, loss: 0.0014341354835778475
2023-01-23 03:15:03.763754: step: 1008/529, loss: 0.030923843383789062
2023-01-23 03:15:04.868002: step: 1012/529, loss: 0.0007534027099609375
2023-01-23 03:15:06.002532: step: 1016/529, loss: 0.03112630732357502
2023-01-23 03:15:07.188494: step: 1020/529, loss: 0.030054474249482155
2023-01-23 03:15:08.351451: step: 1024/529, loss: 0.0100892074406147
2023-01-23 03:15:09.475359: step: 1028/529, loss: 0.00301532750017941
2023-01-23 03:15:10.630165: step: 1032/529, loss: 0.007128524594008923
2023-01-23 03:15:11.782345: step: 1036/529, loss: 0.00010027885582530871
2023-01-23 03:15:12.954343: step: 1040/529, loss: 0.06332512199878693
2023-01-23 03:15:14.076765: step: 1044/529, loss: 0.0002983570157084614
2023-01-23 03:15:15.235278: step: 1048/529, loss: 2.441406286379788e-05
2023-01-23 03:15:16.378744: step: 1052/529, loss: 0.00030736924964003265
2023-01-23 03:15:17.516677: step: 1056/529, loss: 0.00013723372831009328
2023-01-23 03:15:18.676292: step: 1060/529, loss: 0.009287262335419655
2023-01-23 03:15:19.808968: step: 1064/529, loss: 4.0721897676121444e-05
2023-01-23 03:15:20.967222: step: 1068/529, loss: 0.0005447387811727822
2023-01-23 03:15:22.100696: step: 1072/529, loss: 0.01667480543255806
2023-01-23 03:15:23.233334: step: 1076/529, loss: 0.00048708918620832264
2023-01-23 03:15:24.356180: step: 1080/529, loss: 0.006722068879753351
2023-01-23 03:15:25.561015: step: 1084/529, loss: 0.0016569137806072831
2023-01-23 03:15:26.704449: step: 1088/529, loss: 1.296997106692288e-05
2023-01-23 03:15:27.836363: step: 1092/529, loss: 0.007367610931396484
2023-01-23 03:15:28.970927: step: 1096/529, loss: 0.0014804840320721269
2023-01-23 03:15:30.105187: step: 1100/529, loss: 0.0068183899857103825
2023-01-23 03:15:31.261154: step: 1104/529, loss: 0.00018205643573310226
2023-01-23 03:15:32.383492: step: 1108/529, loss: 0.009785271249711514
2023-01-23 03:15:33.520864: step: 1112/529, loss: 0.0004044056113343686
2023-01-23 03:15:34.646890: step: 1116/529, loss: 0.008419417776167393
2023-01-23 03:15:35.780630: step: 1120/529, loss: 0.002857733052223921
2023-01-23 03:15:36.927967: step: 1124/529, loss: 0.0010179519886150956
2023-01-23 03:15:38.088079: step: 1128/529, loss: 0.018828105181455612
2023-01-23 03:15:39.248118: step: 1132/529, loss: 0.00017976760864257812
2023-01-23 03:15:40.402743: step: 1136/529, loss: 0.032177068293094635
2023-01-23 03:15:41.547929: step: 1140/529, loss: 0.019377898424863815
2023-01-23 03:15:42.702568: step: 1144/529, loss: 0.05404262617230415
2023-01-23 03:15:43.877540: step: 1148/529, loss: 0.0038116932846605778
2023-01-23 03:15:44.997413: step: 1152/529, loss: 0.030964471399784088
2023-01-23 03:15:46.140738: step: 1156/529, loss: 0.011748981662094593
2023-01-23 03:15:47.305301: step: 1160/529, loss: 0.0012697220081463456
2023-01-23 03:15:48.495886: step: 1164/529, loss: 0.005949640180915594
2023-01-23 03:15:49.614597: step: 1168/529, loss: 0.001901340438053012
2023-01-23 03:15:50.750111: step: 1172/529, loss: 0.012233162298798561
2023-01-23 03:15:51.889104: step: 1176/529, loss: 0.012092018499970436
2023-01-23 03:15:53.018248: step: 1180/529, loss: 1.635551598155871e-05
2023-01-23 03:15:54.110722: step: 1184/529, loss: 0.01755847968161106
2023-01-23 03:15:55.238467: step: 1188/529, loss: 0.00023651123046875
2023-01-23 03:15:56.384703: step: 1192/529, loss: 0.0073566436767578125
2023-01-23 03:15:57.486808: step: 1196/529, loss: 0.006438589189201593
2023-01-23 03:15:58.599533: step: 1200/529, loss: 0.0003258705255575478
2023-01-23 03:15:59.740063: step: 1204/529, loss: 0.03811035305261612
2023-01-23 03:16:00.873106: step: 1208/529, loss: 0.013130568899214268
2023-01-23 03:16:01.982439: step: 1212/529, loss: 0.021236037835478783
2023-01-23 03:16:03.116386: step: 1216/529, loss: 0.0031888962257653475
2023-01-23 03:16:04.264112: step: 1220/529, loss: 0.10588055104017258
2023-01-23 03:16:05.412045: step: 1224/529, loss: 0.006593131925910711
2023-01-23 03:16:06.533664: step: 1228/529, loss: 0.030215073376893997
2023-01-23 03:16:07.661486: step: 1232/529, loss: 0.00016098022751975805
2023-01-23 03:16:08.791846: step: 1236/529, loss: 0.051476430147886276
2023-01-23 03:16:09.885884: step: 1240/529, loss: 0.0008342743385583162
2023-01-23 03:16:11.002491: step: 1244/529, loss: 0.03817396238446236
2023-01-23 03:16:12.139032: step: 1248/529, loss: 0.003032875247299671
2023-01-23 03:16:13.275755: step: 1252/529, loss: 0.0049485210329294205
2023-01-23 03:16:14.425170: step: 1256/529, loss: 7.05719003235572e-06
2023-01-23 03:16:15.564831: step: 1260/529, loss: 0.03828296810388565
2023-01-23 03:16:16.717206: step: 1264/529, loss: 0.00037994387093931437
2023-01-23 03:16:17.833516: step: 1268/529, loss: 0.0001733779936330393
2023-01-23 03:16:18.990850: step: 1272/529, loss: 0.014648723416030407
2023-01-23 03:16:20.098937: step: 1276/529, loss: 0.0009513854747638106
2023-01-23 03:16:21.207120: step: 1280/529, loss: 5.9521196817513555e-05
2023-01-23 03:16:22.353934: step: 1284/529, loss: 0.0001517772616352886
2023-01-23 03:16:23.476664: step: 1288/529, loss: 0.02330961264669895
2023-01-23 03:16:24.609178: step: 1292/529, loss: 0.025935126468539238
2023-01-23 03:16:25.750065: step: 1296/529, loss: 0.07380924373865128
2023-01-23 03:16:26.863460: step: 1300/529, loss: 0.000289726274786517
2023-01-23 03:16:28.004858: step: 1304/529, loss: 0.010420035570859909
2023-01-23 03:16:29.148431: step: 1308/529, loss: 0.0023464204277843237
2023-01-23 03:16:30.284102: step: 1312/529, loss: 0.06412182003259659
2023-01-23 03:16:31.437147: step: 1316/529, loss: 0.0025056840386241674
2023-01-23 03:16:32.556060: step: 1320/529, loss: 0.0003246903361286968
2023-01-23 03:16:33.709270: step: 1324/529, loss: 0.0019264222355559468
2023-01-23 03:16:34.832416: step: 1328/529, loss: 1.0251998901367188e-05
2023-01-23 03:16:35.973361: step: 1332/529, loss: 0.004190540406852961
2023-01-23 03:16:37.115672: step: 1336/529, loss: 0.0263349786400795
2023-01-23 03:16:38.263313: step: 1340/529, loss: 0.00012922286987304688
2023-01-23 03:16:39.414798: step: 1344/529, loss: 1.2588501704158261e-05
2023-01-23 03:16:40.544933: step: 1348/529, loss: 0.0010848998790606856
2023-01-23 03:16:41.698419: step: 1352/529, loss: 0.06205024942755699
2023-01-23 03:16:42.867886: step: 1356/529, loss: 0.0017721176845952868
2023-01-23 03:16:43.988188: step: 1360/529, loss: 0.00556449918076396
2023-01-23 03:16:45.101578: step: 1364/529, loss: 0.016636276617646217
2023-01-23 03:16:46.267272: step: 1368/529, loss: 0.00018901826115325093
2023-01-23 03:16:47.418933: step: 1372/529, loss: 0.004513740539550781
2023-01-23 03:16:48.554519: step: 1376/529, loss: 0.00034399033756926656
2023-01-23 03:16:49.750704: step: 1380/529, loss: 0.00011663437180686742
2023-01-23 03:16:50.868062: step: 1384/529, loss: 0.0010886192321777344
2023-01-23 03:16:51.987641: step: 1388/529, loss: 0.0024131773971021175
2023-01-23 03:16:53.144393: step: 1392/529, loss: 0.008314704522490501
2023-01-23 03:16:54.285733: step: 1396/529, loss: 0.0014326096279546618
2023-01-23 03:16:55.449946: step: 1400/529, loss: 0.002627086825668812
2023-01-23 03:16:56.610423: step: 1404/529, loss: 0.0030498504638671875
2023-01-23 03:16:57.744117: step: 1408/529, loss: 0.0010994315380230546
2023-01-23 03:16:58.867698: step: 1412/529, loss: 0.026863574981689453
2023-01-23 03:17:00.007352: step: 1416/529, loss: 0.006167411804199219
2023-01-23 03:17:01.151179: step: 1420/529, loss: 0.004493999294936657
2023-01-23 03:17:02.306642: step: 1424/529, loss: 3.826618012681138e-06
2023-01-23 03:17:03.479094: step: 1428/529, loss: 0.0033059597481042147
2023-01-23 03:17:04.623997: step: 1432/529, loss: 0.02643613889813423
2023-01-23 03:17:05.765554: step: 1436/529, loss: 0.014071083627641201
2023-01-23 03:17:06.908459: step: 1440/529, loss: 0.009051084518432617
2023-01-23 03:17:08.028612: step: 1444/529, loss: 0.04303565248847008
2023-01-23 03:17:09.158743: step: 1448/529, loss: 0.08850689232349396
2023-01-23 03:17:10.288876: step: 1452/529, loss: 0.0008841037633828819
2023-01-23 03:17:11.396811: step: 1456/529, loss: 6.69479341013357e-05
2023-01-23 03:17:12.552934: step: 1460/529, loss: 0.0007533550960943103
2023-01-23 03:17:13.697235: step: 1464/529, loss: 0.002031183335930109
2023-01-23 03:17:14.861555: step: 1468/529, loss: 0.04259643703699112
2023-01-23 03:17:16.007473: step: 1472/529, loss: 0.0010677337413653731
2023-01-23 03:17:17.172708: step: 1476/529, loss: 0.004445266909897327
2023-01-23 03:17:18.311339: step: 1480/529, loss: 0.0008053779602050781
2023-01-23 03:17:19.442153: step: 1484/529, loss: 0.008470630273222923
2023-01-23 03:17:20.565939: step: 1488/529, loss: 0.005029773339629173
2023-01-23 03:17:21.700898: step: 1492/529, loss: 0.026469040662050247
2023-01-23 03:17:22.836243: step: 1496/529, loss: 0.004339504521340132
2023-01-23 03:17:23.988724: step: 1500/529, loss: 0.04278764873743057
2023-01-23 03:17:25.151224: step: 1504/529, loss: 0.09206171333789825
2023-01-23 03:17:26.285303: step: 1508/529, loss: 0.049345873296260834
2023-01-23 03:17:27.450967: step: 1512/529, loss: 0.05683489143848419
2023-01-23 03:17:28.594014: step: 1516/529, loss: 0.009336471557617188
2023-01-23 03:17:29.714432: step: 1520/529, loss: 0.01987314224243164
2023-01-23 03:17:30.834375: step: 1524/529, loss: 0.00692405691370368
2023-01-23 03:17:31.977678: step: 1528/529, loss: 0.059420399367809296
2023-01-23 03:17:33.114072: step: 1532/529, loss: 0.009808255359530449
2023-01-23 03:17:34.268232: step: 1536/529, loss: 0.0006288528093136847
2023-01-23 03:17:35.377640: step: 1540/529, loss: 0.0033903121948242188
2023-01-23 03:17:36.507256: step: 1544/529, loss: 0.004057502839714289
2023-01-23 03:17:37.684997: step: 1548/529, loss: 0.0006958961603231728
2023-01-23 03:17:38.806240: step: 1552/529, loss: 0.0012894630199298263
2023-01-23 03:17:39.932482: step: 1556/529, loss: 0.0383269302546978
2023-01-23 03:17:41.073129: step: 1560/529, loss: 0.00046415330143645406
2023-01-23 03:17:42.214256: step: 1564/529, loss: 0.015267753973603249
2023-01-23 03:17:43.374390: step: 1568/529, loss: 0.024472331628203392
2023-01-23 03:17:44.554364: step: 1572/529, loss: 0.003404522081837058
2023-01-23 03:17:45.687120: step: 1576/529, loss: 0.021689655259251595
2023-01-23 03:17:46.829359: step: 1580/529, loss: 0.0005347728729248047
2023-01-23 03:17:47.950126: step: 1584/529, loss: 0.03808346018195152
2023-01-23 03:17:49.058088: step: 1588/529, loss: 0.0006064891931600869
2023-01-23 03:17:50.169740: step: 1592/529, loss: 0.00553164491429925
2023-01-23 03:17:51.297619: step: 1596/529, loss: 0.007785034365952015
2023-01-23 03:17:52.420657: step: 1600/529, loss: 0.04555225372314453
2023-01-23 03:17:53.554914: step: 1604/529, loss: 0.0019316673278808594
2023-01-23 03:17:54.653142: step: 1608/529, loss: 0.04235520213842392
2023-01-23 03:17:55.791857: step: 1612/529, loss: 0.0020699501037597656
2023-01-23 03:17:56.928873: step: 1616/529, loss: 0.0003566741943359375
2023-01-23 03:17:58.057969: step: 1620/529, loss: 0.06817102432250977
2023-01-23 03:17:59.238619: step: 1624/529, loss: 0.0009162425994873047
2023-01-23 03:18:00.388885: step: 1628/529, loss: 0.002708053681999445
2023-01-23 03:18:01.516015: step: 1632/529, loss: 0.001903533935546875
2023-01-23 03:18:02.645186: step: 1636/529, loss: 0.0016307830810546875
2023-01-23 03:18:03.743820: step: 1640/529, loss: 0.026835203170776367
2023-01-23 03:18:04.869364: step: 1644/529, loss: 0.000567579292692244
2023-01-23 03:18:06.020761: step: 1648/529, loss: 0.0003002166631631553
2023-01-23 03:18:07.170893: step: 1652/529, loss: 0.003636646317318082
2023-01-23 03:18:08.300363: step: 1656/529, loss: 0.049230292439460754
2023-01-23 03:18:09.395560: step: 1660/529, loss: 0.05169343948364258
2023-01-23 03:18:10.548739: step: 1664/529, loss: 0.002552127931267023
2023-01-23 03:18:11.687518: step: 1668/529, loss: 0.007974052801728249
2023-01-23 03:18:12.825084: step: 1672/529, loss: 0.000599765800870955
2023-01-23 03:18:13.982141: step: 1676/529, loss: 0.6159076690673828
2023-01-23 03:18:15.132234: step: 1680/529, loss: 0.009006691165268421
2023-01-23 03:18:16.254225: step: 1684/529, loss: 0.001956081483513117
2023-01-23 03:18:17.419361: step: 1688/529, loss: 0.1901434063911438
2023-01-23 03:18:18.551162: step: 1692/529, loss: 0.001997661776840687
2023-01-23 03:18:19.681390: step: 1696/529, loss: 0.0021135329734534025
2023-01-23 03:18:20.856962: step: 1700/529, loss: 0.03945045545697212
2023-01-23 03:18:22.007887: step: 1704/529, loss: 0.0002437591610942036
2023-01-23 03:18:23.173944: step: 1708/529, loss: 0.0026149749755859375
2023-01-23 03:18:24.338450: step: 1712/529, loss: 0.04519524797797203
2023-01-23 03:18:25.502015: step: 1716/529, loss: 0.005949783604592085
2023-01-23 03:18:26.632082: step: 1720/529, loss: 0.0793725997209549
2023-01-23 03:18:27.773180: step: 1724/529, loss: 0.02308826334774494
2023-01-23 03:18:28.910533: step: 1728/529, loss: 0.0018892288208007812
2023-01-23 03:18:30.057647: step: 1732/529, loss: 0.019918251782655716
2023-01-23 03:18:31.244167: step: 1736/529, loss: 0.00215834379196167
2023-01-23 03:18:32.380523: step: 1740/529, loss: 4.025680065155029
2023-01-23 03:18:33.505148: step: 1744/529, loss: 0.014436721801757812
2023-01-23 03:18:34.638011: step: 1748/529, loss: 0.01016922015696764
2023-01-23 03:18:35.801772: step: 1752/529, loss: 4.2343137465650216e-05
2023-01-23 03:18:36.954406: step: 1756/529, loss: 0.014159775339066982
2023-01-23 03:18:38.097221: step: 1760/529, loss: 0.018416594713926315
2023-01-23 03:18:39.239875: step: 1764/529, loss: 3.929138256353326e-05
2023-01-23 03:18:40.418597: step: 1768/529, loss: 0.33783960342407227
2023-01-23 03:18:41.556262: step: 1772/529, loss: 0.0008186817285604775
2023-01-23 03:18:42.684956: step: 1776/529, loss: 0.015990637242794037
2023-01-23 03:18:43.817768: step: 1780/529, loss: 0.014895057305693626
2023-01-23 03:18:44.938773: step: 1784/529, loss: 0.00017471313185524195
2023-01-23 03:18:46.082431: step: 1788/529, loss: 0.00138597481418401
2023-01-23 03:18:47.235418: step: 1792/529, loss: 0.20976239442825317
2023-01-23 03:18:48.370546: step: 1796/529, loss: 0.00028362273587845266
2023-01-23 03:18:49.506041: step: 1800/529, loss: 3.395080420887098e-05
2023-01-23 03:18:50.651124: step: 1804/529, loss: 0.0013628959422931075
2023-01-23 03:18:51.781475: step: 1808/529, loss: 0.00021014214144088328
2023-01-23 03:18:52.891423: step: 1812/529, loss: 0.00016026497178245336
2023-01-23 03:18:54.033526: step: 1816/529, loss: 0.02072782628238201
2023-01-23 03:18:55.164040: step: 1820/529, loss: 0.001722145127132535
2023-01-23 03:18:56.298530: step: 1824/529, loss: 0.01542973518371582
2023-01-23 03:18:57.490955: step: 1828/529, loss: 0.0018113136757165194
2023-01-23 03:18:58.620790: step: 1832/529, loss: 0.0002037048398051411
2023-01-23 03:18:59.769922: step: 1836/529, loss: 0.004458618350327015
2023-01-23 03:19:00.929564: step: 1840/529, loss: 0.005287551786750555
2023-01-23 03:19:02.082144: step: 1844/529, loss: 0.0004940032958984375
2023-01-23 03:19:03.237952: step: 1848/529, loss: 0.00474472064524889
2023-01-23 03:19:04.357803: step: 1852/529, loss: 1.773834264895413e-05
2023-01-23 03:19:05.525564: step: 1856/529, loss: 0.065185546875
2023-01-23 03:19:06.663546: step: 1860/529, loss: 0.05085029453039169
2023-01-23 03:19:07.794095: step: 1864/529, loss: 0.004641437437385321
2023-01-23 03:19:08.915569: step: 1868/529, loss: 0.0006619930500164628
2023-01-23 03:19:10.036763: step: 1872/529, loss: 2.4795535864541307e-06
2023-01-23 03:19:11.220246: step: 1876/529, loss: 0.060254864394664764
2023-01-23 03:19:12.355378: step: 1880/529, loss: 0.0017715455032885075
2023-01-23 03:19:13.494697: step: 1884/529, loss: 0.0027696609031409025
2023-01-23 03:19:14.625868: step: 1888/529, loss: 0.00237789168022573
2023-01-23 03:19:15.760940: step: 1892/529, loss: 0.01651782914996147
2023-01-23 03:19:16.887565: step: 1896/529, loss: 6.4849853515625e-05
2023-01-23 03:19:18.042454: step: 1900/529, loss: 0.002273178193718195
2023-01-23 03:19:19.194334: step: 1904/529, loss: 0.003034830093383789
2023-01-23 03:19:20.319622: step: 1908/529, loss: 0.0002570629003457725
2023-01-23 03:19:21.484501: step: 1912/529, loss: 0.0035238265991210938
2023-01-23 03:19:22.630511: step: 1916/529, loss: 0.046530820429325104
2023-01-23 03:19:23.775796: step: 1920/529, loss: 0.08855066448450089
2023-01-23 03:19:24.899644: step: 1924/529, loss: 0.00024657248286530375
2023-01-23 03:19:26.053505: step: 1928/529, loss: 0.03462934494018555
2023-01-23 03:19:27.184558: step: 1932/529, loss: 0.018462801352143288
2023-01-23 03:19:28.319371: step: 1936/529, loss: 0.0017685890197753906
2023-01-23 03:19:29.477308: step: 1940/529, loss: 0.0233930591493845
2023-01-23 03:19:30.617827: step: 1944/529, loss: 0.008492564782500267
2023-01-23 03:19:31.780155: step: 1948/529, loss: 0.00037288665771484375
2023-01-23 03:19:32.917324: step: 1952/529, loss: 0.012282943353056908
2023-01-23 03:19:34.047865: step: 1956/529, loss: 0.0009721756214275956
2023-01-23 03:19:35.170156: step: 1960/529, loss: 0.00583572406321764
2023-01-23 03:19:36.293831: step: 1964/529, loss: 0.08711566776037216
2023-01-23 03:19:37.473202: step: 1968/529, loss: 0.01244430523365736
2023-01-23 03:19:38.605389: step: 1972/529, loss: 0.03322754055261612
2023-01-23 03:19:39.723344: step: 1976/529, loss: 0.03882112726569176
2023-01-23 03:19:40.876716: step: 1980/529, loss: 0.0075327870436012745
2023-01-23 03:19:42.000299: step: 1984/529, loss: 0.0005918502574786544
2023-01-23 03:19:43.119260: step: 1988/529, loss: 0.0001316070556640625
2023-01-23 03:19:44.254764: step: 1992/529, loss: 0.006556892301887274
2023-01-23 03:19:45.416938: step: 1996/529, loss: 0.003131103701889515
2023-01-23 03:19:46.602845: step: 2000/529, loss: 0.005212068557739258
2023-01-23 03:19:47.765255: step: 2004/529, loss: 0.008368587121367455
2023-01-23 03:19:48.915076: step: 2008/529, loss: 0.0014554978115484118
2023-01-23 03:19:50.062571: step: 2012/529, loss: 0.0007446288946084678
2023-01-23 03:19:51.193704: step: 2016/529, loss: 0.015977095812559128
2023-01-23 03:19:52.307582: step: 2020/529, loss: 0.04450549930334091
2023-01-23 03:19:53.443965: step: 2024/529, loss: 0.00022735596576239914
2023-01-23 03:19:54.567901: step: 2028/529, loss: 0.00783395767211914
2023-01-23 03:19:55.742491: step: 2032/529, loss: 0.003346347715705633
2023-01-23 03:19:56.871934: step: 2036/529, loss: 0.00032558440580032766
2023-01-23 03:19:58.000679: step: 2040/529, loss: 0.0001697540283203125
2023-01-23 03:19:59.153903: step: 2044/529, loss: 0.06764717400074005
2023-01-23 03:20:00.301946: step: 2048/529, loss: 0.1772165298461914
2023-01-23 03:20:01.431033: step: 2052/529, loss: 0.0019796371925622225
2023-01-23 03:20:02.556536: step: 2056/529, loss: 0.004189491271972656
2023-01-23 03:20:03.668866: step: 2060/529, loss: 0.0007213592762127519
2023-01-23 03:20:04.824185: step: 2064/529, loss: 0.5605897903442383
2023-01-23 03:20:05.937223: step: 2068/529, loss: 0.016448400914669037
2023-01-23 03:20:07.058262: step: 2072/529, loss: 0.00016870499530341476
2023-01-23 03:20:08.210572: step: 2076/529, loss: 0.011147118173539639
2023-01-23 03:20:09.405863: step: 2080/529, loss: 0.0062665934674441814
2023-01-23 03:20:10.548010: step: 2084/529, loss: 0.004565429873764515
2023-01-23 03:20:11.702128: step: 2088/529, loss: 0.48561668395996094
2023-01-23 03:20:12.832159: step: 2092/529, loss: 0.011810111813247204
2023-01-23 03:20:14.009769: step: 2096/529, loss: 0.0024503706954419613
2023-01-23 03:20:15.157195: step: 2100/529, loss: 0.0017020226223394275
2023-01-23 03:20:16.296448: step: 2104/529, loss: 0.0039160726591944695
2023-01-23 03:20:17.437059: step: 2108/529, loss: 0.0016578674549236894
2023-01-23 03:20:18.564333: step: 2112/529, loss: 0.0037282942794263363
2023-01-23 03:20:19.706643: step: 2116/529, loss: 0.08283558487892151
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.6409691629955947, 'r': 0.7749667110519307, 'f1': 0.701627486437613}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6427525622254758, 'r': 0.7630359212050984, 'f1': 0.6977483443708609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.6727272727272727, 'r': 0.5873015873015873, 'f1': 0.6271186440677966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.5, 'r': 0.5277777777777778, 'f1': 0.5135135135135136}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 03:21:00.799209: step: 4/529, loss: 0.012122249230742455
2023-01-23 03:21:01.890722: step: 8/529, loss: 0.0017339707119390368
2023-01-23 03:21:03.034173: step: 12/529, loss: 0.018571853637695312
2023-01-23 03:21:04.183511: step: 16/529, loss: 0.0002926826709881425
2023-01-23 03:21:05.315012: step: 20/529, loss: 0.0009027480846270919
2023-01-23 03:21:06.417190: step: 24/529, loss: 0.007097435183823109
2023-01-23 03:21:07.542427: step: 28/529, loss: 0.37966862320899963
2023-01-23 03:21:08.646590: step: 32/529, loss: 0.009923267178237438
2023-01-23 03:21:09.775526: step: 36/529, loss: 0.018733788281679153
2023-01-23 03:21:10.902510: step: 40/529, loss: 0.013580131344497204
2023-01-23 03:21:12.051417: step: 44/529, loss: 0.017580604180693626
2023-01-23 03:21:13.192377: step: 48/529, loss: 0.011322021484375
2023-01-23 03:21:14.335313: step: 52/529, loss: 0.0021246911492198706
2023-01-23 03:21:15.466635: step: 56/529, loss: 0.00020723343186546117
2023-01-23 03:21:16.590755: step: 60/529, loss: 0.00550422677770257
2023-01-23 03:21:17.746699: step: 64/529, loss: 0.07198028266429901
2023-01-23 03:21:18.860711: step: 68/529, loss: 0.004307484719902277
2023-01-23 03:21:20.020605: step: 72/529, loss: 0.003279400058090687
2023-01-23 03:21:21.184223: step: 76/529, loss: 0.0037776471581310034
2023-01-23 03:21:22.306209: step: 80/529, loss: 0.0004974365583620965
2023-01-23 03:21:23.441535: step: 84/529, loss: 0.0011445998679846525
2023-01-23 03:21:24.592633: step: 88/529, loss: 0.009108353406190872
2023-01-23 03:21:25.726255: step: 92/529, loss: 0.00018730164447333664
2023-01-23 03:21:26.914569: step: 96/529, loss: 0.0016743660671636462
2023-01-23 03:21:28.059485: step: 100/529, loss: 0.0030121803283691406
2023-01-23 03:21:29.224836: step: 104/529, loss: 0.012143135070800781
2023-01-23 03:21:30.372372: step: 108/529, loss: 0.0001581192045705393
2023-01-23 03:21:31.541440: step: 112/529, loss: 0.0008585453033447266
2023-01-23 03:21:32.686975: step: 116/529, loss: 0.0999293327331543
2023-01-23 03:21:33.834108: step: 120/529, loss: 0.0001371383696096018
2023-01-23 03:21:34.966829: step: 124/529, loss: 0.0008690833928994834
2023-01-23 03:21:36.106859: step: 128/529, loss: 0.008140373043715954
2023-01-23 03:21:37.236188: step: 132/529, loss: 0.013624383136630058
2023-01-23 03:21:38.381097: step: 136/529, loss: 4.1675568354548886e-05
2023-01-23 03:21:39.496963: step: 140/529, loss: 0.00470733642578125
2023-01-23 03:21:40.616910: step: 144/529, loss: 0.004238796420395374
2023-01-23 03:21:41.772060: step: 148/529, loss: 0.029905272647738457
2023-01-23 03:21:42.888209: step: 152/529, loss: 0.00018134116544388235
2023-01-23 03:21:44.008904: step: 156/529, loss: 0.004186582285910845
2023-01-23 03:21:45.136927: step: 160/529, loss: 0.012182379141449928
2023-01-23 03:21:46.258414: step: 164/529, loss: 0.00018320084200240672
2023-01-23 03:21:47.412410: step: 168/529, loss: 0.006047630216926336
2023-01-23 03:21:48.570574: step: 172/529, loss: 0.01682748831808567
2023-01-23 03:21:49.728042: step: 176/529, loss: 0.09782848507165909
2023-01-23 03:21:50.839538: step: 180/529, loss: 0.003018188290297985
2023-01-23 03:21:51.998820: step: 184/529, loss: 0.00026841164799407125
2023-01-23 03:21:53.127388: step: 188/529, loss: 0.0029460906516760588
2023-01-23 03:21:54.291799: step: 192/529, loss: 0.013586235232651234
2023-01-23 03:21:55.444179: step: 196/529, loss: 0.00010070800635730848
2023-01-23 03:21:56.614500: step: 200/529, loss: 0.00012636184692382812
2023-01-23 03:21:57.792255: step: 204/529, loss: 0.01437072828412056
2023-01-23 03:21:58.938281: step: 208/529, loss: 0.0004572868347167969
2023-01-23 03:22:00.055162: step: 212/529, loss: 0.0013071059947833419
2023-01-23 03:22:01.177098: step: 216/529, loss: 3.3903121220646426e-05
2023-01-23 03:22:02.323598: step: 220/529, loss: 0.005053901579231024
2023-01-23 03:22:03.444387: step: 224/529, loss: 8.535384949936997e-06
2023-01-23 03:22:04.587089: step: 228/529, loss: 0.005337000358849764
2023-01-23 03:22:05.722459: step: 232/529, loss: 0.0026384354569017887
2023-01-23 03:22:06.876024: step: 236/529, loss: 6.828307959949598e-05
2023-01-23 03:22:08.031329: step: 240/529, loss: 0.003358841175213456
2023-01-23 03:22:09.154708: step: 244/529, loss: 0.0003646850527729839
2023-01-23 03:22:10.303598: step: 248/529, loss: 0.0006046295166015625
2023-01-23 03:22:11.446100: step: 252/529, loss: -1.735687328618951e-05
2023-01-23 03:22:12.574360: step: 256/529, loss: 0.01948099210858345
2023-01-23 03:22:13.743802: step: 260/529, loss: 0.022429944947361946
2023-01-23 03:22:14.884139: step: 264/529, loss: 2.913475145760458e-05
2023-01-23 03:22:16.026543: step: 268/529, loss: 8.678436643094756e-06
2023-01-23 03:22:17.131521: step: 272/529, loss: 0.0376923568546772
2023-01-23 03:22:18.282805: step: 276/529, loss: 0.0718500167131424
2023-01-23 03:22:19.409777: step: 280/529, loss: 0.050713252276182175
2023-01-23 03:22:20.579188: step: 284/529, loss: 0.0017803192604333162
2023-01-23 03:22:21.745131: step: 288/529, loss: 0.042156413197517395
2023-01-23 03:22:22.863949: step: 292/529, loss: 0.00011577606346691027
2023-01-23 03:22:24.005135: step: 296/529, loss: 0.00672836322337389
2023-01-23 03:22:25.152207: step: 300/529, loss: -1.6689300537109375e-06
2023-01-23 03:22:26.296654: step: 304/529, loss: 8.94546537892893e-05
2023-01-23 03:22:27.419170: step: 308/529, loss: 0.15695782005786896
2023-01-23 03:22:28.561340: step: 312/529, loss: 0.00039477349491789937
2023-01-23 03:22:29.704996: step: 316/529, loss: 0.6103473901748657
2023-01-23 03:22:30.883161: step: 320/529, loss: 0.0002446174621582031
2023-01-23 03:22:32.022228: step: 324/529, loss: 0.000648879969958216
2023-01-23 03:22:33.142946: step: 328/529, loss: 0.013531113043427467
2023-01-23 03:22:34.309023: step: 332/529, loss: 0.006122589111328125
2023-01-23 03:22:35.465023: step: 336/529, loss: 0.004767417907714844
2023-01-23 03:22:36.585353: step: 340/529, loss: 0.006417084019631147
2023-01-23 03:22:37.716127: step: 344/529, loss: 0.09183750301599503
2023-01-23 03:22:38.865597: step: 348/529, loss: 0.0003725052229128778
2023-01-23 03:22:40.035165: step: 352/529, loss: 0.0028888701926916838
2023-01-23 03:22:41.197112: step: 356/529, loss: 0.003117561573162675
2023-01-23 03:22:42.326352: step: 360/529, loss: 0.0002739906485658139
2023-01-23 03:22:43.463616: step: 364/529, loss: 0.03527984768152237
2023-01-23 03:22:44.586841: step: 368/529, loss: 7.724761962890625e-05
2023-01-23 03:22:45.701875: step: 372/529, loss: 0.014986039139330387
2023-01-23 03:22:46.837596: step: 376/529, loss: 0.003082370851188898
2023-01-23 03:22:47.990639: step: 380/529, loss: 4.5776364459015895e-06
2023-01-23 03:22:49.130236: step: 384/529, loss: 3.2091142202261835e-05
2023-01-23 03:22:50.265778: step: 388/529, loss: 2.422332727292087e-05
2023-01-23 03:22:51.418983: step: 392/529, loss: 0.05735492706298828
2023-01-23 03:22:52.512877: step: 396/529, loss: 0.1433638632297516
2023-01-23 03:22:53.631400: step: 400/529, loss: 0.0004175186331849545
2023-01-23 03:22:54.783036: step: 404/529, loss: 0.0009712219471111894
2023-01-23 03:22:55.909351: step: 408/529, loss: 9.298920485889539e-05
2023-01-23 03:22:57.035060: step: 412/529, loss: 0.03572253882884979
2023-01-23 03:22:58.160195: step: 416/529, loss: 1.9931794668082148e-05
2023-01-23 03:22:59.336701: step: 420/529, loss: 0.005035782232880592
2023-01-23 03:23:00.510277: step: 424/529, loss: 0.00011863708641612902
2023-01-23 03:23:01.650525: step: 428/529, loss: 0.0044644358567893505
2023-01-23 03:23:02.791494: step: 432/529, loss: 0.00063748360844329
2023-01-23 03:23:03.940882: step: 436/529, loss: 4.9304962885798886e-05
2023-01-23 03:23:05.092144: step: 440/529, loss: 0.0005977631080895662
2023-01-23 03:23:06.214480: step: 444/529, loss: 0.0001125335693359375
2023-01-23 03:23:07.351941: step: 448/529, loss: 0.0006055831909179688
2023-01-23 03:23:08.471344: step: 452/529, loss: 7.381439354503527e-05
2023-01-23 03:23:09.610749: step: 456/529, loss: 0.011651611886918545
2023-01-23 03:23:10.725339: step: 460/529, loss: 0.03778381273150444
2023-01-23 03:23:11.861913: step: 464/529, loss: 0.006230163853615522
2023-01-23 03:23:13.011743: step: 468/529, loss: 5.91278057981981e-06
2023-01-23 03:23:14.145145: step: 472/529, loss: 0.0003252982860431075
2023-01-23 03:23:15.318125: step: 476/529, loss: 9.298324584960938e-05
2023-01-23 03:23:16.443544: step: 480/529, loss: 0.0015970231033861637
2023-01-23 03:23:17.568003: step: 484/529, loss: 0.007323837373405695
2023-01-23 03:23:18.696980: step: 488/529, loss: 7.43865966796875e-05
2023-01-23 03:23:19.813252: step: 492/529, loss: 0.028985215350985527
2023-01-23 03:23:20.954155: step: 496/529, loss: 0.05895958095788956
2023-01-23 03:23:22.106176: step: 500/529, loss: 0.00012083054025424644
2023-01-23 03:23:23.246852: step: 504/529, loss: 0.000110626220703125
2023-01-23 03:23:24.352589: step: 508/529, loss: 0.002862358232960105
2023-01-23 03:23:25.464575: step: 512/529, loss: 0.00020904542179778218
2023-01-23 03:23:26.597801: step: 516/529, loss: 0.026233388110995293
2023-01-23 03:23:27.744142: step: 520/529, loss: 0.0008932113414630294
2023-01-23 03:23:28.892319: step: 524/529, loss: 0.00119609828107059
2023-01-23 03:23:30.055116: step: 528/529, loss: 0.0008561611175537109
2023-01-23 03:23:31.195465: step: 532/529, loss: 0.046364977955818176
2023-01-23 03:23:32.341884: step: 536/529, loss: 0.0003383159637451172
2023-01-23 03:23:33.502913: step: 540/529, loss: 0.006731224246323109
2023-01-23 03:23:34.615577: step: 544/529, loss: 8.735657320357859e-05
2023-01-23 03:23:35.724881: step: 548/529, loss: 0.002952385228127241
2023-01-23 03:23:36.868905: step: 552/529, loss: 0.0008687973022460938
2023-01-23 03:23:38.025498: step: 556/529, loss: 0.0007780074956826866
2023-01-23 03:23:39.162175: step: 560/529, loss: 0.00423774728551507
2023-01-23 03:23:40.306046: step: 564/529, loss: 0.000526809657458216
2023-01-23 03:23:41.423583: step: 568/529, loss: 0.00021219253540039062
2023-01-23 03:23:42.593079: step: 572/529, loss: 0.02101736143231392
2023-01-23 03:23:43.735766: step: 576/529, loss: 0.00578761100769043
2023-01-23 03:23:44.881508: step: 580/529, loss: 0.04334073141217232
2023-01-23 03:23:46.029155: step: 584/529, loss: 0.00902633648365736
2023-01-23 03:23:47.169846: step: 588/529, loss: 0.00021696090698242188
2023-01-23 03:23:48.306817: step: 592/529, loss: 0.006221580319106579
2023-01-23 03:23:49.423700: step: 596/529, loss: 0.0004119873046875
2023-01-23 03:23:50.550989: step: 600/529, loss: 1.838056206703186
2023-01-23 03:23:51.705891: step: 604/529, loss: 6.69479341013357e-05
2023-01-23 03:23:52.833666: step: 608/529, loss: 0.000965976738370955
2023-01-23 03:23:53.987802: step: 612/529, loss: 0.10055360943078995
2023-01-23 03:23:55.117088: step: 616/529, loss: 0.000614166259765625
2023-01-23 03:23:56.290846: step: 620/529, loss: 0.01166625041514635
2023-01-23 03:23:57.405264: step: 624/529, loss: 0.0032042504753917456
2023-01-23 03:23:58.544974: step: 628/529, loss: 0.0014080047840252519
2023-01-23 03:23:59.684696: step: 632/529, loss: 0.08251648396253586
2023-01-23 03:24:00.781739: step: 636/529, loss: 8.20159948489163e-06
2023-01-23 03:24:01.923747: step: 640/529, loss: 0.011662102304399014
2023-01-23 03:24:03.061564: step: 644/529, loss: 0.00038566591683775187
2023-01-23 03:24:04.207123: step: 648/529, loss: 0.010095500387251377
2023-01-23 03:24:05.375427: step: 652/529, loss: 0.0009060860029421747
2023-01-23 03:24:06.504564: step: 656/529, loss: 0.002723598387092352
2023-01-23 03:24:07.646665: step: 660/529, loss: 3.352165367687121e-05
2023-01-23 03:24:08.772836: step: 664/529, loss: 0.13838224112987518
2023-01-23 03:24:09.915265: step: 668/529, loss: 0.0010177611839026213
2023-01-23 03:24:11.056060: step: 672/529, loss: 0.006105995271354914
2023-01-23 03:24:12.203740: step: 676/529, loss: 7.114410982467234e-05
2023-01-23 03:24:13.401830: step: 680/529, loss: 0.028000831604003906
2023-01-23 03:24:14.544221: step: 684/529, loss: 0.011997699737548828
2023-01-23 03:24:15.691805: step: 688/529, loss: 0.05275878682732582
2023-01-23 03:24:16.822835: step: 692/529, loss: 0.009086799807846546
2023-01-23 03:24:17.948110: step: 696/529, loss: 0.0004677772521972656
2023-01-23 03:24:19.080950: step: 700/529, loss: 0.00010404586646473035
2023-01-23 03:24:20.222024: step: 704/529, loss: 0.03290243446826935
2023-01-23 03:24:21.374530: step: 708/529, loss: 0.0022081376519054174
2023-01-23 03:24:22.523606: step: 712/529, loss: 1.1730194273695815e-05
2023-01-23 03:24:23.670992: step: 716/529, loss: 0.02408619038760662
2023-01-23 03:24:24.805261: step: 720/529, loss: 0.0021425248123705387
2023-01-23 03:24:25.946735: step: 724/529, loss: 0.00099439627956599
2023-01-23 03:24:27.073003: step: 728/529, loss: 0.03503723070025444
2023-01-23 03:24:28.184434: step: 732/529, loss: 0.0015258790226653218
2023-01-23 03:24:29.349384: step: 736/529, loss: 0.005784893408417702
2023-01-23 03:24:30.497662: step: 740/529, loss: 0.0034919262398034334
2023-01-23 03:24:31.672878: step: 744/529, loss: 0.011863135732710361
2023-01-23 03:24:32.829624: step: 748/529, loss: 0.01698136329650879
2023-01-23 03:24:33.965609: step: 752/529, loss: 0.0012704849941655993
2023-01-23 03:24:35.094541: step: 756/529, loss: 0.00010528563871048391
2023-01-23 03:24:36.225859: step: 760/529, loss: 2.899169885495212e-05
2023-01-23 03:24:37.374998: step: 764/529, loss: 0.0042091370560228825
2023-01-23 03:24:38.526415: step: 768/529, loss: 0.0036523817107081413
2023-01-23 03:24:39.664511: step: 772/529, loss: 0.02281961590051651
2023-01-23 03:24:40.785810: step: 776/529, loss: 0.0006132125854492188
2023-01-23 03:24:41.953883: step: 780/529, loss: -8.20159948489163e-06
2023-01-23 03:24:43.115426: step: 784/529, loss: 0.0001070022553903982
2023-01-23 03:24:44.237532: step: 788/529, loss: 0.0035590173210948706
2023-01-23 03:24:45.376623: step: 792/529, loss: 0.013995361514389515
2023-01-23 03:24:46.517868: step: 796/529, loss: 0.0015935420524328947
2023-01-23 03:24:47.671481: step: 800/529, loss: 0.03227977827191353
2023-01-23 03:24:48.810822: step: 804/529, loss: 0.09013023972511292
2023-01-23 03:24:49.927319: step: 808/529, loss: 0.0013823509216308594
2023-01-23 03:24:51.059744: step: 812/529, loss: 0.027702046558260918
2023-01-23 03:24:52.206820: step: 816/529, loss: 0.03227744251489639
2023-01-23 03:24:53.358155: step: 820/529, loss: 0.001745033310726285
2023-01-23 03:24:54.499571: step: 824/529, loss: 0.007443809416145086
2023-01-23 03:24:55.629347: step: 828/529, loss: 0.006693935487419367
2023-01-23 03:24:56.765455: step: 832/529, loss: 0.006846142001450062
2023-01-23 03:24:57.900987: step: 836/529, loss: 0.0009369850158691406
2023-01-23 03:24:59.029467: step: 840/529, loss: 0.01755070686340332
2023-01-23 03:25:00.175439: step: 844/529, loss: 0.00886230543255806
2023-01-23 03:25:01.322378: step: 848/529, loss: 0.02380330115556717
2023-01-23 03:25:02.474549: step: 852/529, loss: 7.381439354503527e-05
2023-01-23 03:25:03.623238: step: 856/529, loss: 2.098083541568485e-06
2023-01-23 03:25:04.757151: step: 860/529, loss: 0.005394172854721546
2023-01-23 03:25:05.888595: step: 864/529, loss: 6.022453453624621e-05
2023-01-23 03:25:07.041340: step: 868/529, loss: 0.003189659211784601
2023-01-23 03:25:08.163666: step: 872/529, loss: 3.185272362316027e-05
2023-01-23 03:25:09.289968: step: 876/529, loss: -4.7683716530855236e-08
2023-01-23 03:25:10.449505: step: 880/529, loss: 1.23977656585339e-06
2023-01-23 03:25:11.594339: step: 884/529, loss: 4.749298022943549e-05
2023-01-23 03:25:12.732449: step: 888/529, loss: 0.0707613006234169
2023-01-23 03:25:13.910422: step: 892/529, loss: 0.014056872576475143
2023-01-23 03:25:15.029011: step: 896/529, loss: 0.0010799408191815019
2023-01-23 03:25:16.191114: step: 900/529, loss: 0.003029441926628351
2023-01-23 03:25:17.327810: step: 904/529, loss: 0.0001663207949604839
2023-01-23 03:25:18.466252: step: 908/529, loss: 2.403259350103326e-05
2023-01-23 03:25:19.632167: step: 912/529, loss: 0.01768665201961994
2023-01-23 03:25:20.770593: step: 916/529, loss: 0.0015914917457848787
2023-01-23 03:25:21.917919: step: 920/529, loss: 0.00318145751953125
2023-01-23 03:25:23.041613: step: 924/529, loss: 4.014969090349041e-05
2023-01-23 03:25:24.194255: step: 928/529, loss: 0.010680390521883965
2023-01-23 03:25:25.356294: step: 932/529, loss: 6.580352783203125e-05
2023-01-23 03:25:26.496921: step: 936/529, loss: 0.0017225266201421618
2023-01-23 03:25:27.624765: step: 940/529, loss: 0.00531086977571249
2023-01-23 03:25:28.789315: step: 944/529, loss: 0.00135889055673033
2023-01-23 03:25:29.884804: step: 948/529, loss: 0.0004180431133136153
2023-01-23 03:25:30.999459: step: 952/529, loss: 0.006670856382697821
2023-01-23 03:25:32.129928: step: 956/529, loss: 0.012012672610580921
2023-01-23 03:25:33.263256: step: 960/529, loss: 0.00032844545785337687
2023-01-23 03:25:34.371357: step: 964/529, loss: 0.0008128166082315147
2023-01-23 03:25:35.506156: step: 968/529, loss: 0.0012675761245191097
2023-01-23 03:25:36.661863: step: 972/529, loss: 0.0002422332763671875
2023-01-23 03:25:37.783052: step: 976/529, loss: 0.0014566422905772924
2023-01-23 03:25:38.916350: step: 980/529, loss: 0.0017336368327960372
2023-01-23 03:25:40.062652: step: 984/529, loss: 0.00020017623319290578
2023-01-23 03:25:41.192781: step: 988/529, loss: 3.886222839355469e-05
2023-01-23 03:25:42.317082: step: 992/529, loss: 0.0005237102741375566
2023-01-23 03:25:43.468169: step: 996/529, loss: 0.009807873517274857
2023-01-23 03:25:44.593580: step: 1000/529, loss: 3.24249267578125e-05
2023-01-23 03:25:45.725948: step: 1004/529, loss: 0.00832066498696804
2023-01-23 03:25:46.885230: step: 1008/529, loss: 0.0005116462707519531
2023-01-23 03:25:48.007200: step: 1012/529, loss: 2.0408631826285273e-05
2023-01-23 03:25:49.169039: step: 1016/529, loss: 0.033586978912353516
2023-01-23 03:25:50.300901: step: 1020/529, loss: 0.0008363723754882812
2023-01-23 03:25:51.413601: step: 1024/529, loss: 0.0017265318892896175
2023-01-23 03:25:52.522604: step: 1028/529, loss: 0.0013116359477862716
2023-01-23 03:25:53.613988: step: 1032/529, loss: 0.0001892089785542339
2023-01-23 03:25:54.779716: step: 1036/529, loss: 0.0021267891861498356
2023-01-23 03:25:55.883849: step: 1040/529, loss: 0.07324304431676865
2023-01-23 03:25:57.042377: step: 1044/529, loss: 0.08907298743724823
2023-01-23 03:25:58.155682: step: 1048/529, loss: 0.00023002624220680445
2023-01-23 03:25:59.309053: step: 1052/529, loss: 0.07630138099193573
2023-01-23 03:26:00.467846: step: 1056/529, loss: 0.010723686777055264
2023-01-23 03:26:01.588552: step: 1060/529, loss: 0.017180634662508965
2023-01-23 03:26:02.718692: step: 1064/529, loss: 0.06581058353185654
2023-01-23 03:26:03.866833: step: 1068/529, loss: 0.00010347366333007812
2023-01-23 03:26:05.001375: step: 1072/529, loss: 0.021439744159579277
2023-01-23 03:26:06.140936: step: 1076/529, loss: 0.01027059555053711
2023-01-23 03:26:07.279131: step: 1080/529, loss: 0.001177978585474193
2023-01-23 03:26:08.416892: step: 1084/529, loss: 0.0034956932067871094
2023-01-23 03:26:09.562127: step: 1088/529, loss: 0.00027532578678801656
2023-01-23 03:26:10.705786: step: 1092/529, loss: 0.003433704376220703
2023-01-23 03:26:11.834393: step: 1096/529, loss: 0.09546375274658203
2023-01-23 03:26:12.997462: step: 1100/529, loss: 8.649825758766383e-05
2023-01-23 03:26:14.140652: step: 1104/529, loss: 0.0017650604713708162
2023-01-23 03:26:15.275803: step: 1108/529, loss: 0.006481361575424671
2023-01-23 03:26:16.405972: step: 1112/529, loss: 0.05636923015117645
2023-01-23 03:26:17.574893: step: 1116/529, loss: 0.002726268721744418
2023-01-23 03:26:18.710672: step: 1120/529, loss: 0.0010936737526208162
2023-01-23 03:26:19.819811: step: 1124/529, loss: 0.001168537070043385
2023-01-23 03:26:20.934406: step: 1128/529, loss: 7.739067223155871e-05
2023-01-23 03:26:22.082368: step: 1132/529, loss: 0.0013621330726891756
2023-01-23 03:26:23.221283: step: 1136/529, loss: 0.2411360740661621
2023-01-23 03:26:24.378928: step: 1140/529, loss: 1.888275073724799e-05
2023-01-23 03:26:25.543919: step: 1144/529, loss: 0.05358944088220596
2023-01-23 03:26:26.683995: step: 1148/529, loss: 0.014494705013930798
2023-01-23 03:26:27.823160: step: 1152/529, loss: 0.0008991241920739412
2023-01-23 03:26:28.963764: step: 1156/529, loss: 7.114410254871473e-05
2023-01-23 03:26:30.105433: step: 1160/529, loss: 0.00054168701171875
2023-01-23 03:26:31.260324: step: 1164/529, loss: 0.00783319491893053
2023-01-23 03:26:32.385483: step: 1168/529, loss: 0.02441844902932644
2023-01-23 03:26:33.545475: step: 1172/529, loss: 0.002945852465927601
2023-01-23 03:26:34.672936: step: 1176/529, loss: 0.019594382494688034
2023-01-23 03:26:35.819485: step: 1180/529, loss: 0.02733621746301651
2023-01-23 03:26:36.948233: step: 1184/529, loss: 4.892349534202367e-05
2023-01-23 03:26:38.097586: step: 1188/529, loss: 0.03534355014562607
2023-01-23 03:26:39.207071: step: 1192/529, loss: 0.0004415988805703819
2023-01-23 03:26:40.337166: step: 1196/529, loss: 0.05653982236981392
2023-01-23 03:26:41.489725: step: 1200/529, loss: 0.0002679348108358681
2023-01-23 03:26:42.624248: step: 1204/529, loss: 0.009637976065278053
2023-01-23 03:26:43.759740: step: 1208/529, loss: 0.009605693630874157
2023-01-23 03:26:44.892761: step: 1212/529, loss: 0.00013618469529319555
2023-01-23 03:26:46.066741: step: 1216/529, loss: 5.292892819852568e-05
2023-01-23 03:26:47.214481: step: 1220/529, loss: 0.03351764753460884
2023-01-23 03:26:48.358387: step: 1224/529, loss: 0.0004139900556765497
2023-01-23 03:26:49.499327: step: 1228/529, loss: 1.0013580322265625e-05
2023-01-23 03:26:50.650206: step: 1232/529, loss: 0.000308990478515625
2023-01-23 03:26:51.816427: step: 1236/529, loss: 0.005173587705940008
2023-01-23 03:26:52.971182: step: 1240/529, loss: 0.006445026490837336
2023-01-23 03:26:54.100265: step: 1244/529, loss: 0.0062697408720850945
2023-01-23 03:26:55.266899: step: 1248/529, loss: 0.0017696380382403731
2023-01-23 03:26:56.420075: step: 1252/529, loss: 0.0006448745843954384
2023-01-23 03:26:57.529956: step: 1256/529, loss: 0.04432172700762749
2023-01-23 03:26:58.656904: step: 1260/529, loss: 0.0018756865756586194
2023-01-23 03:26:59.771588: step: 1264/529, loss: 0.0027548314537853003
2023-01-23 03:27:00.953036: step: 1268/529, loss: 0.01964740827679634
2023-01-23 03:27:02.123882: step: 1272/529, loss: 0.00234298687428236
2023-01-23 03:27:03.247124: step: 1276/529, loss: 0.0043801311403512955
2023-01-23 03:27:04.422064: step: 1280/529, loss: 0.00016851426335051656
2023-01-23 03:27:05.585422: step: 1284/529, loss: 0.005230331793427467
2023-01-23 03:27:06.715163: step: 1288/529, loss: 0.0008947372552938759
2023-01-23 03:27:07.840642: step: 1292/529, loss: 0.0004623413260560483
2023-01-23 03:27:08.997327: step: 1296/529, loss: 0.022509528324007988
2023-01-23 03:27:10.118839: step: 1300/529, loss: 0.00602989224717021
2023-01-23 03:27:11.271638: step: 1304/529, loss: 0.0015788078308105469
2023-01-23 03:27:12.453563: step: 1308/529, loss: 0.02596607245504856
2023-01-23 03:27:13.624294: step: 1312/529, loss: 0.0008823395473882556
2023-01-23 03:27:14.779081: step: 1316/529, loss: 0.008840465918183327
2023-01-23 03:27:15.923579: step: 1320/529, loss: 6.361008126987144e-05
2023-01-23 03:27:17.090760: step: 1324/529, loss: 0.0007719993591308594
2023-01-23 03:27:18.228222: step: 1328/529, loss: 0.03787994384765625
2023-01-23 03:27:19.399216: step: 1332/529, loss: 0.00713882502168417
2023-01-23 03:27:20.556187: step: 1336/529, loss: 0.008744621649384499
2023-01-23 03:27:21.679482: step: 1340/529, loss: 0.0284592155367136
2023-01-23 03:27:22.787397: step: 1344/529, loss: 0.0049797059036791325
2023-01-23 03:27:23.924064: step: 1348/529, loss: 0.000581932021304965
2023-01-23 03:27:25.059799: step: 1352/529, loss: 0.038088131695985794
2023-01-23 03:27:26.233245: step: 1356/529, loss: 0.0025080679915845394
2023-01-23 03:27:27.411483: step: 1360/529, loss: 0.008681297302246094
2023-01-23 03:27:28.552715: step: 1364/529, loss: 0.00630421657115221
2023-01-23 03:27:29.719348: step: 1368/529, loss: 0.04978370666503906
2023-01-23 03:27:30.840294: step: 1372/529, loss: 0.0004442215140443295
2023-01-23 03:27:31.979555: step: 1376/529, loss: 0.0031043528579175472
2023-01-23 03:27:33.149389: step: 1380/529, loss: 0.09928111732006073
2023-01-23 03:27:34.302642: step: 1384/529, loss: 0.006635615136474371
2023-01-23 03:27:35.481256: step: 1388/529, loss: 0.0027212142013013363
2023-01-23 03:27:36.600558: step: 1392/529, loss: 4.224777512717992e-05
2023-01-23 03:27:37.751473: step: 1396/529, loss: 0.016762161627411842
2023-01-23 03:27:38.883420: step: 1400/529, loss: 0.06715116649866104
2023-01-23 03:27:40.002575: step: 1404/529, loss: 0.002013635588809848
2023-01-23 03:27:41.156019: step: 1408/529, loss: 0.035502053797245026
2023-01-23 03:27:42.291051: step: 1412/529, loss: 0.002112960908561945
2023-01-23 03:27:43.442221: step: 1416/529, loss: 0.0013929844135418534
2023-01-23 03:27:44.545419: step: 1420/529, loss: 0.00018458366685081273
2023-01-23 03:27:45.684835: step: 1424/529, loss: 0.004747653380036354
2023-01-23 03:27:46.818598: step: 1428/529, loss: 0.006683158688247204
2023-01-23 03:27:47.986307: step: 1432/529, loss: 0.0011385440593585372
2023-01-23 03:27:49.129719: step: 1436/529, loss: 0.017820073291659355
2023-01-23 03:27:50.252710: step: 1440/529, loss: 0.01777510531246662
2023-01-23 03:27:51.431016: step: 1444/529, loss: 0.0003845214960165322
2023-01-23 03:27:52.565464: step: 1448/529, loss: 0.010808277875185013
2023-01-23 03:27:53.731469: step: 1452/529, loss: 1.821518162614666e-05
2023-01-23 03:27:54.850696: step: 1456/529, loss: 0.008607101626694202
2023-01-23 03:27:56.006070: step: 1460/529, loss: 0.00011177062697242945
2023-01-23 03:27:57.131828: step: 1464/529, loss: 0.012480735778808594
2023-01-23 03:27:58.277611: step: 1468/529, loss: 0.0021741867531090975
2023-01-23 03:27:59.432146: step: 1472/529, loss: 2.918243444582913e-05
2023-01-23 03:28:00.571015: step: 1476/529, loss: 0.01189580000936985
2023-01-23 03:28:01.693010: step: 1480/529, loss: 0.0013535498874261975
2023-01-23 03:28:02.802345: step: 1484/529, loss: 0.0054073333740234375
2023-01-23 03:28:03.950061: step: 1488/529, loss: 0.011902237311005592
2023-01-23 03:28:05.075206: step: 1492/529, loss: 0.0004708290216512978
2023-01-23 03:28:06.198413: step: 1496/529, loss: 7.171630568336695e-05
2023-01-23 03:28:07.342238: step: 1500/529, loss: 0.021419046446681023
2023-01-23 03:28:08.490418: step: 1504/529, loss: 0.01244669035077095
2023-01-23 03:28:09.617325: step: 1508/529, loss: 0.023098565638065338
2023-01-23 03:28:10.746970: step: 1512/529, loss: 0.2991792559623718
2023-01-23 03:28:11.871523: step: 1516/529, loss: 6.27517729299143e-05
2023-01-23 03:28:12.999712: step: 1520/529, loss: 0.005256080999970436
2023-01-23 03:28:14.124892: step: 1524/529, loss: 0.026103878393769264
2023-01-23 03:28:15.290679: step: 1528/529, loss: 0.009510422125458717
2023-01-23 03:28:16.410637: step: 1532/529, loss: 0.0006998926401138306
2023-01-23 03:28:17.583052: step: 1536/529, loss: 2.489090184099041e-05
2023-01-23 03:28:18.765466: step: 1540/529, loss: 0.00039548875065520406
2023-01-23 03:28:19.918741: step: 1544/529, loss: 0.2413882166147232
2023-01-23 03:28:21.085551: step: 1548/529, loss: 0.0030515671242028475
2023-01-23 03:28:22.228077: step: 1552/529, loss: 0.0025078775361180305
2023-01-23 03:28:23.349670: step: 1556/529, loss: 7.152557827794226e-06
2023-01-23 03:28:24.494571: step: 1560/529, loss: 0.026714039966464043
2023-01-23 03:28:25.618067: step: 1564/529, loss: 6.942749314475805e-05
2023-01-23 03:28:26.721194: step: 1568/529, loss: 0.0024944304022938013
2023-01-23 03:28:27.883156: step: 1572/529, loss: 0.0001884460507426411
2023-01-23 03:28:29.005663: step: 1576/529, loss: 0.004269408993422985
2023-01-23 03:28:30.176007: step: 1580/529, loss: 0.048248291015625
2023-01-23 03:28:31.328931: step: 1584/529, loss: 0.0060249329544603825
2023-01-23 03:28:32.481996: step: 1588/529, loss: 0.0058532715775072575
2023-01-23 03:28:33.648060: step: 1592/529, loss: 0.0030053136870265007
2023-01-23 03:28:34.789748: step: 1596/529, loss: 0.001884555909782648
2023-01-23 03:28:35.926618: step: 1600/529, loss: 0.015384435653686523
2023-01-23 03:28:37.109180: step: 1604/529, loss: 0.006488037295639515
2023-01-23 03:28:38.268735: step: 1608/529, loss: 7.2479248046875e-05
2023-01-23 03:28:39.409945: step: 1612/529, loss: 2.3937225705594756e-05
2023-01-23 03:28:40.553236: step: 1616/529, loss: 0.0009454727405682206
2023-01-23 03:28:41.706545: step: 1620/529, loss: 4.596710277837701e-05
2023-01-23 03:28:42.871886: step: 1624/529, loss: 0.00010433197167003527
2023-01-23 03:28:44.014508: step: 1628/529, loss: 0.01026377733796835
2023-01-23 03:28:45.175887: step: 1632/529, loss: 0.01127481460571289
2023-01-23 03:28:46.328849: step: 1636/529, loss: 0.013681793585419655
2023-01-23 03:28:47.469777: step: 1640/529, loss: 0.005292415618896484
2023-01-23 03:28:48.592337: step: 1644/529, loss: 0.04929952695965767
2023-01-23 03:28:49.739546: step: 1648/529, loss: -8.678436643094756e-06
2023-01-23 03:28:50.877116: step: 1652/529, loss: 0.00047740936861373484
2023-01-23 03:28:51.993823: step: 1656/529, loss: 0.00239906320348382
2023-01-23 03:28:53.151425: step: 1660/529, loss: 0.046666525304317474
2023-01-23 03:28:54.288076: step: 1664/529, loss: 0.013225173577666283
2023-01-23 03:28:55.438825: step: 1668/529, loss: 0.004532432183623314
2023-01-23 03:28:56.543809: step: 1672/529, loss: 5.834102921653539e-05
2023-01-23 03:28:57.664937: step: 1676/529, loss: 5.264282299322076e-05
2023-01-23 03:28:58.811295: step: 1680/529, loss: 0.02164936065673828
2023-01-23 03:28:59.959753: step: 1684/529, loss: 0.0037299632094800472
2023-01-23 03:29:01.106648: step: 1688/529, loss: 0.00605010986328125
2023-01-23 03:29:02.228322: step: 1692/529, loss: 0.007861089892685413
2023-01-23 03:29:03.340562: step: 1696/529, loss: 0.0046967025846242905
2023-01-23 03:29:04.474299: step: 1700/529, loss: 4.711151632363908e-05
2023-01-23 03:29:05.592205: step: 1704/529, loss: 0.1127108559012413
2023-01-23 03:29:06.711738: step: 1708/529, loss: 0.08870165050029755
2023-01-23 03:29:07.868317: step: 1712/529, loss: 0.0024352073669433594
2023-01-23 03:29:09.010457: step: 1716/529, loss: 0.006780385971069336
2023-01-23 03:29:10.133382: step: 1720/529, loss: 0.00016927719116210938
2023-01-23 03:29:11.262094: step: 1724/529, loss: 0.0030871392227709293
2023-01-23 03:29:12.431304: step: 1728/529, loss: 8.611679368186742e-05
2023-01-23 03:29:13.574815: step: 1732/529, loss: 0.028707217425107956
2023-01-23 03:29:14.748826: step: 1736/529, loss: 0.01104354951530695
2023-01-23 03:29:15.890087: step: 1740/529, loss: 0.13848638534545898
2023-01-23 03:29:17.005238: step: 1744/529, loss: 0.014813710004091263
2023-01-23 03:29:18.161500: step: 1748/529, loss: 2.1648407710017636e-05
2023-01-23 03:29:19.309093: step: 1752/529, loss: 0.020134640857577324
2023-01-23 03:29:20.447842: step: 1756/529, loss: 0.0006126403459347785
2023-01-23 03:29:21.579794: step: 1760/529, loss: 0.008276558481156826
2023-01-23 03:29:22.696112: step: 1764/529, loss: 0.0077707297168672085
2023-01-23 03:29:23.834038: step: 1768/529, loss: 0.03609352186322212
2023-01-23 03:29:24.965875: step: 1772/529, loss: 0.0002729416301008314
2023-01-23 03:29:26.109395: step: 1776/529, loss: 0.00041415690793655813
2023-01-23 03:29:27.243302: step: 1780/529, loss: 0.01828022114932537
2023-01-23 03:29:28.375129: step: 1784/529, loss: 0.0008789062849245965
2023-01-23 03:29:29.540637: step: 1788/529, loss: 0.0016079902416095138
2023-01-23 03:29:30.670490: step: 1792/529, loss: 0.033232927322387695
2023-01-23 03:29:31.775760: step: 1796/529, loss: 9.679794311523438e-05
2023-01-23 03:29:32.911254: step: 1800/529, loss: 2.593994213384576e-05
2023-01-23 03:29:34.032577: step: 1804/529, loss: 9.31739850784652e-05
2023-01-23 03:29:35.161065: step: 1808/529, loss: 0.007866382598876953
2023-01-23 03:29:36.271981: step: 1812/529, loss: 0.006460762117058039
2023-01-23 03:29:37.403667: step: 1816/529, loss: 0.00035295484121888876
2023-01-23 03:29:38.549106: step: 1820/529, loss: 0.0003211021248716861
2023-01-23 03:29:39.705140: step: 1824/529, loss: 0.022278403863310814
2023-01-23 03:29:40.848584: step: 1828/529, loss: 0.02132449299097061
2023-01-23 03:29:41.981740: step: 1832/529, loss: 0.0002819538349285722
2023-01-23 03:29:43.126631: step: 1836/529, loss: 7.390975952148438e-05
2023-01-23 03:29:44.280455: step: 1840/529, loss: 0.006366729736328125
2023-01-23 03:29:45.439192: step: 1844/529, loss: 0.0022705078590661287
2023-01-23 03:29:46.569144: step: 1848/529, loss: 0.01170973852276802
2023-01-23 03:29:47.690534: step: 1852/529, loss: 0.000561618828214705
2023-01-23 03:29:48.870812: step: 1856/529, loss: 0.0003860473516397178
2023-01-23 03:29:50.017931: step: 1860/529, loss: 0.009035635739564896
2023-01-23 03:29:51.133096: step: 1864/529, loss: 0.0010900550987571478
2023-01-23 03:29:52.257484: step: 1868/529, loss: 1.711845470708795e-05
2023-01-23 03:29:53.401106: step: 1872/529, loss: 0.05508995056152344
2023-01-23 03:29:54.548470: step: 1876/529, loss: 2.3746491933707148e-05
2023-01-23 03:29:55.694289: step: 1880/529, loss: 0.0018678664928302169
2023-01-23 03:29:56.820446: step: 1884/529, loss: 0.0012666701804846525
2023-01-23 03:29:57.962605: step: 1888/529, loss: 0.00551528949290514
2023-01-23 03:29:59.083388: step: 1892/529, loss: 0.0016518592601642013
2023-01-23 03:30:00.212184: step: 1896/529, loss: 0.00233974470756948
2023-01-23 03:30:01.360056: step: 1900/529, loss: 0.00015149115642998368
2023-01-23 03:30:02.528135: step: 1904/529, loss: 0.014877939596772194
2023-01-23 03:30:03.668774: step: 1908/529, loss: 0.00535507220774889
2023-01-23 03:30:04.819094: step: 1912/529, loss: 4.7492983867414296e-05
2023-01-23 03:30:05.958419: step: 1916/529, loss: 0.0003095626598224044
2023-01-23 03:30:07.145475: step: 1920/529, loss: 0.06734533607959747
2023-01-23 03:30:08.302351: step: 1924/529, loss: 0.00812997855246067
2023-01-23 03:30:09.439911: step: 1928/529, loss: 0.0054565430618822575
2023-01-23 03:30:10.586880: step: 1932/529, loss: 0.010118294507265091
2023-01-23 03:30:11.718396: step: 1936/529, loss: 0.01666870154440403
2023-01-23 03:30:12.866503: step: 1940/529, loss: 0.0016904831863939762
2023-01-23 03:30:14.005572: step: 1944/529, loss: 0.0338054895401001
2023-01-23 03:30:15.145042: step: 1948/529, loss: 0.007516384124755859
2023-01-23 03:30:16.263600: step: 1952/529, loss: 0.028334714472293854
2023-01-23 03:30:17.419526: step: 1956/529, loss: 0.023342037573456764
2023-01-23 03:30:18.583803: step: 1960/529, loss: 0.008712577633559704
2023-01-23 03:30:19.707675: step: 1964/529, loss: 0.0016159057850018144
2023-01-23 03:30:20.838656: step: 1968/529, loss: 0.009116077795624733
2023-01-23 03:30:21.976261: step: 1972/529, loss: 0.06287412345409393
2023-01-23 03:30:23.122165: step: 1976/529, loss: 0.021939467638731003
2023-01-23 03:30:24.290217: step: 1980/529, loss: 0.016839217394590378
2023-01-23 03:30:25.435022: step: 1984/529, loss: 0.16899852454662323
2023-01-23 03:30:26.565474: step: 1988/529, loss: 0.00038166047306731343
2023-01-23 03:30:27.702230: step: 1992/529, loss: 6.09397902735509e-05
2023-01-23 03:30:28.852784: step: 1996/529, loss: 0.003913116175681353
2023-01-23 03:30:30.047460: step: 2000/529, loss: 0.0010168076260015368
2023-01-23 03:30:31.192215: step: 2004/529, loss: 0.001932048937305808
2023-01-23 03:30:32.341873: step: 2008/529, loss: 0.01073470152914524
2023-01-23 03:30:33.482968: step: 2012/529, loss: 3.62396240234375e-05
2023-01-23 03:30:34.611737: step: 2016/529, loss: 0.0009984970092773438
2023-01-23 03:30:35.759340: step: 2020/529, loss: 0.014743566513061523
2023-01-23 03:30:36.924935: step: 2024/529, loss: 0.01982126198709011
2023-01-23 03:30:38.055595: step: 2028/529, loss: 0.0001123428373830393
2023-01-23 03:30:39.218278: step: 2032/529, loss: 5.6076052715070546e-05
2023-01-23 03:30:40.334213: step: 2036/529, loss: 1.3256072634248994e-05
2023-01-23 03:30:41.451618: step: 2040/529, loss: 0.0021954537369310856
2023-01-23 03:30:42.630365: step: 2044/529, loss: 0.001407623291015625
2023-01-23 03:30:43.761352: step: 2048/529, loss: 0.006967353634536266
2023-01-23 03:30:44.899475: step: 2052/529, loss: 0.020756341516971588
2023-01-23 03:30:46.030323: step: 2056/529, loss: 0.01763630099594593
2023-01-23 03:30:47.156301: step: 2060/529, loss: 0.012850750237703323
2023-01-23 03:30:48.287223: step: 2064/529, loss: 0.0027101514860987663
2023-01-23 03:30:49.405701: step: 2068/529, loss: 0.012981010600924492
2023-01-23 03:30:50.569820: step: 2072/529, loss: 0.004489326383918524
2023-01-23 03:30:51.701475: step: 2076/529, loss: 0.011792373843491077
2023-01-23 03:30:52.819453: step: 2080/529, loss: 0.002345276065170765
2023-01-23 03:30:53.952362: step: 2084/529, loss: 0.003320694202557206
2023-01-23 03:30:55.128282: step: 2088/529, loss: 0.04024448245763779
2023-01-23 03:30:56.302414: step: 2092/529, loss: 0.016018344089388847
2023-01-23 03:30:57.448234: step: 2096/529, loss: 3.0803679692326114e-05
2023-01-23 03:30:58.586013: step: 2100/529, loss: 7.095336331985891e-05
2023-01-23 03:30:59.733735: step: 2104/529, loss: 0.0070673939771950245
2023-01-23 03:31:00.874283: step: 2108/529, loss: 0.08051382005214691
2023-01-23 03:31:02.031289: step: 2112/529, loss: 0.0003147602255921811
2023-01-23 03:31:03.169692: step: 2116/529, loss: 0.005423259921371937
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.6186895810955961, 'r': 0.7669773635153129, 'f1': 0.6848989298454221}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6382775119617224, 'r': 0.7728852838933952, 'f1': 0.69916142557652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
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': 22}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 03:31:44.699596: step: 4/529, loss: 0.012882137671113014
2023-01-23 03:31:45.829190: step: 8/529, loss: 0.048334553837776184
2023-01-23 03:31:46.965099: step: 12/529, loss: 0.006993246264755726
2023-01-23 03:31:48.110490: step: 16/529, loss: 0.006013012025505304
2023-01-23 03:31:49.229470: step: 20/529, loss: 6.737709190929309e-05
2023-01-23 03:31:50.358321: step: 24/529, loss: 0.0003803253348451108
2023-01-23 03:31:51.478503: step: 28/529, loss: 3.185272362316027e-05
2023-01-23 03:31:52.643379: step: 32/529, loss: 0.015850448980927467
2023-01-23 03:31:53.794511: step: 36/529, loss: 0.0028118134941905737
2023-01-23 03:31:54.951101: step: 40/529, loss: 0.008745861239731312
2023-01-23 03:31:56.108593: step: 44/529, loss: 0.003170585725456476
2023-01-23 03:31:57.332910: step: 48/529, loss: 0.017382431775331497
2023-01-23 03:31:58.469273: step: 52/529, loss: 0.00034341809805482626
2023-01-23 03:31:59.625275: step: 56/529, loss: 0.009341764263808727
2023-01-23 03:32:00.740096: step: 60/529, loss: 0.0009114264976233244
2023-01-23 03:32:01.855685: step: 64/529, loss: 0.026303337886929512
2023-01-23 03:32:02.984032: step: 68/529, loss: 0.000392723100958392
2023-01-23 03:32:04.156840: step: 72/529, loss: 0.021758748218417168
2023-01-23 03:32:05.295850: step: 76/529, loss: 0.0533016175031662
2023-01-23 03:32:06.436123: step: 80/529, loss: 0.0008165359613485634
2023-01-23 03:32:07.608212: step: 84/529, loss: 0.025231456384062767
2023-01-23 03:32:08.731920: step: 88/529, loss: 0.003562021302059293
2023-01-23 03:32:09.872718: step: 92/529, loss: 0.008714770898222923
2023-01-23 03:32:11.028181: step: 96/529, loss: 7.791518874000758e-05
2023-01-23 03:32:12.152457: step: 100/529, loss: 0.0015239715576171875
2023-01-23 03:32:13.306419: step: 104/529, loss: 0.007922744378447533
2023-01-23 03:32:14.443286: step: 108/529, loss: 0.024698639288544655
2023-01-23 03:32:15.582793: step: 112/529, loss: 0.011738014407455921
2023-01-23 03:32:16.715192: step: 116/529, loss: 0.0028238536324352026
2023-01-23 03:32:17.854212: step: 120/529, loss: 0.008063125424087048
2023-01-23 03:32:19.014808: step: 124/529, loss: 0.0003464698966126889
2023-01-23 03:32:20.200142: step: 128/529, loss: 0.0007472991710528731
2023-01-23 03:32:21.334455: step: 132/529, loss: 0.030215872451663017
2023-01-23 03:32:22.477587: step: 136/529, loss: 0.028722573071718216
2023-01-23 03:32:23.601693: step: 140/529, loss: 0.0021591188851743937
2023-01-23 03:32:24.757193: step: 144/529, loss: 0.05266590043902397
2023-01-23 03:32:25.920741: step: 148/529, loss: 0.0004047393740620464
2023-01-23 03:32:27.076312: step: 152/529, loss: 0.06136741489171982
2023-01-23 03:32:28.218365: step: 156/529, loss: 0.009961318224668503
2023-01-23 03:32:29.344086: step: 160/529, loss: 2.079009937006049e-05
2023-01-23 03:32:30.487632: step: 164/529, loss: 0.0032651901710778475
2023-01-23 03:32:31.645741: step: 168/529, loss: 0.014388656243681908
2023-01-23 03:32:32.771915: step: 172/529, loss: 0.0002536773681640625
2023-01-23 03:32:33.904311: step: 176/529, loss: 0.002376270480453968
2023-01-23 03:32:35.050551: step: 180/529, loss: 0.00013895034499000758
2023-01-23 03:32:36.189615: step: 184/529, loss: 0.054497767239809036
2023-01-23 03:32:37.311526: step: 188/529, loss: 0.0149962417781353
2023-01-23 03:32:38.429122: step: 192/529, loss: 0.0007214546203613281
2023-01-23 03:32:39.579419: step: 196/529, loss: 0.0009597778553143144
2023-01-23 03:32:40.716150: step: 200/529, loss: 0.013955306261777878
2023-01-23 03:32:41.849087: step: 204/529, loss: 0.010005999356508255
2023-01-23 03:32:43.008909: step: 208/529, loss: 0.002341651823371649
2023-01-23 03:32:44.141083: step: 212/529, loss: 0.00018601419287733734
2023-01-23 03:32:45.284374: step: 216/529, loss: 0.011185312643647194
2023-01-23 03:32:46.399824: step: 220/529, loss: 2.956390380859375e-05
2023-01-23 03:32:47.537904: step: 224/529, loss: 0.00118427281267941
2023-01-23 03:32:48.697251: step: 228/529, loss: 0.01641826704144478
2023-01-23 03:32:49.835409: step: 232/529, loss: 0.08445654064416885
2023-01-23 03:32:50.993716: step: 236/529, loss: 0.0006719589582644403
2023-01-23 03:32:52.124606: step: 240/529, loss: 7.247925168485381e-06
2023-01-23 03:32:53.276488: step: 244/529, loss: 0.0007128715515136719
2023-01-23 03:32:54.404816: step: 248/529, loss: 6.28471389063634e-05
2023-01-23 03:32:55.524899: step: 252/529, loss: 0.004500961396843195
2023-01-23 03:32:56.641139: step: 256/529, loss: 0.00037956240703351796
2023-01-23 03:32:57.799643: step: 260/529, loss: 2.269744800287299e-05
2023-01-23 03:32:58.927652: step: 264/529, loss: 0.0006556510925292969
2023-01-23 03:33:00.058265: step: 268/529, loss: 0.03521137312054634
2023-01-23 03:33:01.184623: step: 272/529, loss: 0.02560262754559517
2023-01-23 03:33:02.332118: step: 276/529, loss: 0.003953170962631702
2023-01-23 03:33:03.492591: step: 280/529, loss: 0.008655357174575329
2023-01-23 03:33:04.618295: step: 284/529, loss: 0.024987315759062767
2023-01-23 03:33:05.770606: step: 288/529, loss: 0.009451293386518955
2023-01-23 03:33:06.892052: step: 292/529, loss: 0.0004525184631347656
2023-01-23 03:33:08.033689: step: 296/529, loss: 0.011457539163529873
2023-01-23 03:33:09.179062: step: 300/529, loss: 0.009892558678984642
2023-01-23 03:33:10.306633: step: 304/529, loss: 0.00036964414175599813
2023-01-23 03:33:11.449246: step: 308/529, loss: 0.0017229079967364669
2023-01-23 03:33:12.554292: step: 312/529, loss: 1.7976761228055693e-05
2023-01-23 03:33:13.711475: step: 316/529, loss: 0.0034877776633948088
2023-01-23 03:33:14.860264: step: 320/529, loss: 0.25906485319137573
2023-01-23 03:33:15.986990: step: 324/529, loss: 0.006595802493393421
2023-01-23 03:33:17.127951: step: 328/529, loss: 0.06577229499816895
2023-01-23 03:33:18.271943: step: 332/529, loss: 0.01117486972361803
2023-01-23 03:33:19.407855: step: 336/529, loss: 7.247925168485381e-06
2023-01-23 03:33:20.551743: step: 340/529, loss: 0.32857057452201843
2023-01-23 03:33:21.676428: step: 344/529, loss: 0.0018787384033203125
2023-01-23 03:33:22.815085: step: 348/529, loss: 0.0004990339512005448
2023-01-23 03:33:23.959459: step: 352/529, loss: 2.193450927734375e-05
2023-01-23 03:33:25.099744: step: 356/529, loss: 0.002851295517757535
2023-01-23 03:33:26.215814: step: 360/529, loss: 0.00017371178546454757
2023-01-23 03:33:27.375877: step: 364/529, loss: 0.05306658893823624
2023-01-23 03:33:28.513765: step: 368/529, loss: 0.0007446289528161287
2023-01-23 03:33:29.622809: step: 372/529, loss: 0.0009305953863076866
2023-01-23 03:33:30.738313: step: 376/529, loss: 0.0002480983966961503
2023-01-23 03:33:31.935547: step: 380/529, loss: 0.001983690308406949
2023-01-23 03:33:33.116516: step: 384/529, loss: 8.37326078908518e-05
2023-01-23 03:33:34.241908: step: 388/529, loss: 0.0003231048467569053
2023-01-23 03:33:35.357150: step: 392/529, loss: 1.602172778802924e-05
2023-01-23 03:33:36.508357: step: 396/529, loss: 0.06917381286621094
2023-01-23 03:33:37.654816: step: 400/529, loss: 0.0008682251209393144
2023-01-23 03:33:38.767167: step: 404/529, loss: 0.04975871741771698
2023-01-23 03:33:39.907665: step: 408/529, loss: 0.0004084586980752647
2023-01-23 03:33:41.049183: step: 412/529, loss: 0.005503273103386164
2023-01-23 03:33:42.166173: step: 416/529, loss: 0.001552581787109375
2023-01-23 03:33:43.302345: step: 420/529, loss: 0.024096298962831497
2023-01-23 03:33:44.426653: step: 424/529, loss: 0.0010208130115643144
2023-01-23 03:33:45.563423: step: 428/529, loss: 0.020763827487826347
2023-01-23 03:33:46.690954: step: 432/529, loss: 0.004187298007309437
2023-01-23 03:33:47.826924: step: 436/529, loss: 0.004733562469482422
2023-01-23 03:33:48.942182: step: 440/529, loss: 8.96453857421875e-05
2023-01-23 03:33:50.078505: step: 444/529, loss: 0.020523834973573685
2023-01-23 03:33:51.208720: step: 448/529, loss: 0.014217520132660866
2023-01-23 03:33:52.383835: step: 452/529, loss: 0.0004267692565917969
2023-01-23 03:33:53.515159: step: 456/529, loss: 0.00015325545973610133
2023-01-23 03:33:54.657956: step: 460/529, loss: 0.00027151702670380473
2023-01-23 03:33:55.832368: step: 464/529, loss: 1.4470517271547578e-05
2023-01-23 03:33:56.952990: step: 468/529, loss: 0.06356659531593323
2023-01-23 03:33:58.107204: step: 472/529, loss: 0.010550403967499733
2023-01-23 03:33:59.225960: step: 476/529, loss: 0.0013629914028570056
2023-01-23 03:34:00.334113: step: 480/529, loss: 0.041469767689704895
2023-01-23 03:34:01.478742: step: 484/529, loss: 0.0012273788452148438
2023-01-23 03:34:02.609252: step: 488/529, loss: 0.006653976161032915
2023-01-23 03:34:03.741770: step: 492/529, loss: 0.004865646827965975
2023-01-23 03:34:04.881519: step: 496/529, loss: 0.21770639717578888
2023-01-23 03:34:06.042237: step: 500/529, loss: 0.2050682157278061
2023-01-23 03:34:07.189748: step: 504/529, loss: 8.926392183639109e-05
2023-01-23 03:34:08.359077: step: 508/529, loss: 0.004333019256591797
2023-01-23 03:34:09.519943: step: 512/529, loss: 0.0018676758045330644
2023-01-23 03:34:10.650047: step: 516/529, loss: 0.010727119632065296
2023-01-23 03:34:11.800857: step: 520/529, loss: 0.0009628295665606856
2023-01-23 03:34:12.937829: step: 524/529, loss: 8.296967280330136e-06
2023-01-23 03:34:14.066280: step: 528/529, loss: 0.0008838653448037803
2023-01-23 03:34:15.186715: step: 532/529, loss: 0.013854789547622204
2023-01-23 03:34:16.300048: step: 536/529, loss: 4.310607982915826e-05
2023-01-23 03:34:17.434836: step: 540/529, loss: 9.15527380129788e-06
2023-01-23 03:34:18.576205: step: 544/529, loss: 0.00039014816866256297
2023-01-23 03:34:19.741048: step: 548/529, loss: 0.02130408212542534
2023-01-23 03:34:20.880860: step: 552/529, loss: 0.000251579302130267
2023-01-23 03:34:22.077630: step: 556/529, loss: 0.0018236159812659025
2023-01-23 03:34:23.203279: step: 560/529, loss: 0.0002956390380859375
2023-01-23 03:34:24.311980: step: 564/529, loss: 0.025072097778320312
2023-01-23 03:34:25.454020: step: 568/529, loss: 0.015985680744051933
2023-01-23 03:34:26.577033: step: 572/529, loss: 0.00033359526423737407
2023-01-23 03:34:27.700909: step: 576/529, loss: -5.722044988942798e-07
2023-01-23 03:34:28.828463: step: 580/529, loss: 0.0002017974911723286
2023-01-23 03:34:29.966425: step: 584/529, loss: 1.487731969973538e-05
2023-01-23 03:34:31.085420: step: 588/529, loss: 0.0006965161301195621
2023-01-23 03:34:32.221064: step: 592/529, loss: 0.00042514799861237407
2023-01-23 03:34:33.351317: step: 596/529, loss: 0.00014047621516510844
2023-01-23 03:34:34.472641: step: 600/529, loss: 1.4019013178767636e-05
2023-01-23 03:34:35.631950: step: 604/529, loss: 0.0005537032848224044
2023-01-23 03:34:36.787901: step: 608/529, loss: 0.00769310025498271
2023-01-23 03:34:37.913774: step: 612/529, loss: 0.0006879806751385331
2023-01-23 03:34:39.036970: step: 616/529, loss: 0.001835298608057201
2023-01-23 03:34:40.177754: step: 620/529, loss: 0.005445671267807484
2023-01-23 03:34:41.330139: step: 624/529, loss: 0.0006382942083291709
2023-01-23 03:34:42.454568: step: 628/529, loss: 0.00039935109089128673
2023-01-23 03:34:43.610740: step: 632/529, loss: 3.719329833984375e-05
2023-01-23 03:34:44.763375: step: 636/529, loss: 0.0002956390380859375
2023-01-23 03:34:45.899430: step: 640/529, loss: 0.0010980607476085424
2023-01-23 03:34:47.015172: step: 644/529, loss: 0.002021980471909046
2023-01-23 03:34:48.176310: step: 648/529, loss: 9.307861910201609e-05
2023-01-23 03:34:49.324430: step: 652/529, loss: 0.00014057158841751516
2023-01-23 03:34:50.461405: step: 656/529, loss: 0.0010408401722088456
2023-01-23 03:34:51.608229: step: 660/529, loss: 1.792907642084174e-05
2023-01-23 03:34:52.750206: step: 664/529, loss: 0.0005223274347372353
2023-01-23 03:34:53.892204: step: 668/529, loss: 0.002431964734569192
2023-01-23 03:34:55.025388: step: 672/529, loss: 0.046492960304021835
2023-01-23 03:34:56.207145: step: 676/529, loss: 0.002403831575065851
2023-01-23 03:34:57.373103: step: 680/529, loss: 0.010167312808334827
2023-01-23 03:34:58.510714: step: 684/529, loss: 0.0009099007002077997
2023-01-23 03:34:59.679881: step: 688/529, loss: 0.004207420628517866
2023-01-23 03:35:00.791733: step: 692/529, loss: 0.04148273542523384
2023-01-23 03:35:01.921021: step: 696/529, loss: 0.0002237796870758757
2023-01-23 03:35:03.052702: step: 700/529, loss: 0.0004596710205078125
2023-01-23 03:35:04.222770: step: 704/529, loss: 0.015514945611357689
2023-01-23 03:35:05.333321: step: 708/529, loss: 0.006739520933479071
2023-01-23 03:35:06.445199: step: 712/529, loss: 0.006988429930061102
2023-01-23 03:35:07.624973: step: 716/529, loss: 0.06101221963763237
2023-01-23 03:35:08.792166: step: 720/529, loss: 0.0013698578113690019
2023-01-23 03:35:09.926374: step: 724/529, loss: 7.934570749057457e-05
2023-01-23 03:35:11.068813: step: 728/529, loss: 2.8038026357535273e-05
2023-01-23 03:35:12.240912: step: 732/529, loss: 0.0002007007715292275
2023-01-23 03:35:13.371977: step: 736/529, loss: 0.003244781633839011
2023-01-23 03:35:14.494245: step: 740/529, loss: 0.0007438659085892141
2023-01-23 03:35:15.648260: step: 744/529, loss: 0.06237611547112465
2023-01-23 03:35:16.781507: step: 748/529, loss: 0.0011137009132653475
2023-01-23 03:35:17.932218: step: 752/529, loss: 0.1900525987148285
2023-01-23 03:35:19.082320: step: 756/529, loss: 0.0007118224748410285
2023-01-23 03:35:20.213737: step: 760/529, loss: 3.070831371587701e-05
2023-01-23 03:35:21.347838: step: 764/529, loss: 0.00010261535499012098
2023-01-23 03:35:22.522593: step: 768/529, loss: 0.008781243115663528
2023-01-23 03:35:23.681186: step: 772/529, loss: 0.0004192352353129536
2023-01-23 03:35:24.839463: step: 776/529, loss: 0.005642509553581476
2023-01-23 03:35:25.989555: step: 780/529, loss: 3.585815284168348e-05
2023-01-23 03:35:27.148321: step: 784/529, loss: 0.05169963836669922
2023-01-23 03:35:28.289982: step: 788/529, loss: 0.00028996466426178813
2023-01-23 03:35:29.391374: step: 792/529, loss: 0.00020322800264693797
2023-01-23 03:35:30.554309: step: 796/529, loss: 3.1256677175406367e-05
2023-01-23 03:35:31.708138: step: 800/529, loss: 0.008978747762739658
2023-01-23 03:35:32.830993: step: 804/529, loss: 0.012032079510390759
2023-01-23 03:35:33.938697: step: 808/529, loss: 0.0001898527261801064
2023-01-23 03:35:35.054559: step: 812/529, loss: 0.0015240252250805497
2023-01-23 03:35:36.157199: step: 816/529, loss: 0.01431417465209961
2023-01-23 03:35:37.309094: step: 820/529, loss: 0.015032864175736904
2023-01-23 03:35:38.421609: step: 824/529, loss: 0.005633163265883923
2023-01-23 03:35:39.545489: step: 828/529, loss: 6.151199340820312e-05
2023-01-23 03:35:40.693899: step: 832/529, loss: 0.00212268834002316
2023-01-23 03:35:41.810363: step: 836/529, loss: 0.00031828880310058594
2023-01-23 03:35:42.935717: step: 840/529, loss: 0.0003203391970600933
2023-01-23 03:35:44.072328: step: 844/529, loss: 0.0004020690976176411
2023-01-23 03:35:45.205270: step: 848/529, loss: 0.0007855416042730212
2023-01-23 03:35:46.340544: step: 852/529, loss: 1.5258789289873675e-06
2023-01-23 03:35:47.475419: step: 856/529, loss: 0.0020596503745764494
2023-01-23 03:35:48.645469: step: 860/529, loss: 0.007476329803466797
2023-01-23 03:35:49.767302: step: 864/529, loss: 7.286071922862902e-05
2023-01-23 03:35:50.898603: step: 868/529, loss: 0.008346081711351871
2023-01-23 03:35:52.042929: step: 872/529, loss: 0.004449081607162952
2023-01-23 03:35:53.174833: step: 876/529, loss: 0.0017236232524737716
2023-01-23 03:35:54.318116: step: 880/529, loss: 0.010668945498764515
2023-01-23 03:35:55.465409: step: 884/529, loss: 0.0004935223842039704
2023-01-23 03:35:56.588290: step: 888/529, loss: 0.0005986213800497353
2023-01-23 03:35:57.733417: step: 892/529, loss: 0.0002609252987895161
2023-01-23 03:35:58.899015: step: 896/529, loss: 0.006785011384636164
2023-01-23 03:36:00.026091: step: 900/529, loss: 0.0016184330452233553
2023-01-23 03:36:01.146768: step: 904/529, loss: 6.880760338390246e-05
2023-01-23 03:36:02.304385: step: 908/529, loss: 0.00557708740234375
2023-01-23 03:36:03.485107: step: 912/529, loss: 0.0028951645363122225
2023-01-23 03:36:04.621631: step: 916/529, loss: 0.006602478213608265
2023-01-23 03:36:05.738057: step: 920/529, loss: 6.0558319091796875e-05
2023-01-23 03:36:06.871302: step: 924/529, loss: 0.06734314560890198
2023-01-23 03:36:08.004276: step: 928/529, loss: 0.00024752618628554046
2023-01-23 03:36:09.142375: step: 932/529, loss: 0.014574432745575905
2023-01-23 03:36:10.275921: step: 936/529, loss: 0.021332740783691406
2023-01-23 03:36:11.425140: step: 940/529, loss: 0.0013212204212322831
2023-01-23 03:36:12.569940: step: 944/529, loss: 0.07049636542797089
2023-01-23 03:36:13.708583: step: 948/529, loss: 0.0006916046841070056
2023-01-23 03:36:14.840193: step: 952/529, loss: 3.948211815441027e-05
2023-01-23 03:36:15.970325: step: 956/529, loss: 4.806519064004533e-05
2023-01-23 03:36:17.108839: step: 960/529, loss: 0.00018720627122092992
2023-01-23 03:36:18.258499: step: 964/529, loss: 0.003830146975815296
2023-01-23 03:36:19.384070: step: 968/529, loss: 0.0006706237909384072
2023-01-23 03:36:20.508801: step: 972/529, loss: 0.03444795683026314
2023-01-23 03:36:21.645508: step: 976/529, loss: 0.0001558303920319304
2023-01-23 03:36:22.791931: step: 980/529, loss: 0.02129383198916912
2023-01-23 03:36:23.965787: step: 984/529, loss: 0.020460795611143112
2023-01-23 03:36:25.104856: step: 988/529, loss: 0.0044920919463038445
2023-01-23 03:36:26.223209: step: 992/529, loss: 3.3664702641544864e-05
2023-01-23 03:36:27.355298: step: 996/529, loss: 0.0010754584800451994
2023-01-23 03:36:28.497435: step: 1000/529, loss: 0.039188578724861145
2023-01-23 03:36:29.652102: step: 1004/529, loss: 2.6702882678364404e-05
2023-01-23 03:36:30.782342: step: 1008/529, loss: 0.006126213353127241
2023-01-23 03:36:31.922397: step: 1012/529, loss: 0.0001625060976948589
2023-01-23 03:36:33.091870: step: 1016/529, loss: 0.0007300376892089844
2023-01-23 03:36:34.227765: step: 1020/529, loss: 0.0005289077525958419
2023-01-23 03:36:35.366235: step: 1024/529, loss: 5.683899507857859e-05
2023-01-23 03:36:36.486197: step: 1028/529, loss: 0.021750641986727715
2023-01-23 03:36:37.619679: step: 1032/529, loss: 0.0009449959034100175
2023-01-23 03:36:38.753000: step: 1036/529, loss: 0.0005115509266033769
2023-01-23 03:36:39.894444: step: 1040/529, loss: 0.006106376647949219
2023-01-23 03:36:41.038702: step: 1044/529, loss: 0.0032206536270678043
2023-01-23 03:36:42.155598: step: 1048/529, loss: 0.0008114815573208034
2023-01-23 03:36:43.246318: step: 1052/529, loss: 0.6567395329475403
2023-01-23 03:36:44.396332: step: 1056/529, loss: 0.020140837877988815
2023-01-23 03:36:45.539093: step: 1060/529, loss: 0.0006835937965661287
2023-01-23 03:36:46.662295: step: 1064/529, loss: 0.012934398837387562
2023-01-23 03:36:47.812091: step: 1068/529, loss: 0.19415606558322906
2023-01-23 03:36:48.945733: step: 1072/529, loss: 0.013765716925263405
2023-01-23 03:36:50.073570: step: 1076/529, loss: 0.004931545350700617
2023-01-23 03:36:51.217090: step: 1080/529, loss: 0.0013827324146404862
2023-01-23 03:36:52.348050: step: 1084/529, loss: 0.00039777756319381297
2023-01-23 03:36:53.491216: step: 1088/529, loss: 0.001670456025749445
2023-01-23 03:36:54.654615: step: 1092/529, loss: 0.025157928466796875
2023-01-23 03:36:55.774562: step: 1096/529, loss: 0.0002342224179301411
2023-01-23 03:36:56.937430: step: 1100/529, loss: 0.007592892739921808
2023-01-23 03:36:58.087250: step: 1104/529, loss: 0.014551926404237747
2023-01-23 03:36:59.203386: step: 1108/529, loss: 1.634371042251587
2023-01-23 03:37:00.383732: step: 1112/529, loss: 1.8739699953584932e-05
2023-01-23 03:37:01.520087: step: 1116/529, loss: 0.0014375686878338456
2023-01-23 03:37:02.632770: step: 1120/529, loss: 0.029003240168094635
2023-01-23 03:37:03.783700: step: 1124/529, loss: 0.00012493133544921875
2023-01-23 03:37:04.920631: step: 1128/529, loss: 0.00037021638127043843
2023-01-23 03:37:06.050812: step: 1132/529, loss: 0.0034265518188476562
2023-01-23 03:37:07.186800: step: 1136/529, loss: 0.09349896013736725
2023-01-23 03:37:08.323756: step: 1140/529, loss: 0.009424782358109951
2023-01-23 03:37:09.494329: step: 1144/529, loss: 0.0001985549897653982
2023-01-23 03:37:10.624174: step: 1148/529, loss: 0.07612569630146027
2023-01-23 03:37:11.793651: step: 1152/529, loss: 0.030254008248448372
2023-01-23 03:37:12.946510: step: 1156/529, loss: 0.0068933009169995785
2023-01-23 03:37:14.093392: step: 1160/529, loss: 0.0003364086151123047
2023-01-23 03:37:15.231444: step: 1164/529, loss: 0.08749179542064667
2023-01-23 03:37:16.353573: step: 1168/529, loss: 0.0007830619579181075
2023-01-23 03:37:17.512048: step: 1172/529, loss: 0.0009251594892702997
2023-01-23 03:37:18.632798: step: 1176/529, loss: 0.00047969818115234375
2023-01-23 03:37:19.801543: step: 1180/529, loss: 0.003381919814273715
2023-01-23 03:37:20.977763: step: 1184/529, loss: 0.01605110429227352
2023-01-23 03:37:22.153697: step: 1188/529, loss: 0.009189128875732422
2023-01-23 03:37:23.296754: step: 1192/529, loss: 0.00719528179615736
2023-01-23 03:37:24.439989: step: 1196/529, loss: 0.09588488936424255
2023-01-23 03:37:25.583657: step: 1200/529, loss: 6.599425978492945e-05
2023-01-23 03:37:26.693236: step: 1204/529, loss: 0.0011001586681231856
2023-01-23 03:37:27.817671: step: 1208/529, loss: 0.0010382651817053556
2023-01-23 03:37:28.972791: step: 1212/529, loss: 0.00047712327796034515
2023-01-23 03:37:30.108009: step: 1216/529, loss: 0.0001516819029347971
2023-01-23 03:37:31.261331: step: 1220/529, loss: 0.002011299366131425
2023-01-23 03:37:32.394963: step: 1224/529, loss: 0.0009478569263592362
2023-01-23 03:37:33.536377: step: 1228/529, loss: 0.004867363255470991
2023-01-23 03:37:34.660730: step: 1232/529, loss: 0.0034030915703624487
2023-01-23 03:37:35.800177: step: 1236/529, loss: 0.001762819243595004
2023-01-23 03:37:36.975544: step: 1240/529, loss: 0.002093506045639515
2023-01-23 03:37:38.130533: step: 1244/529, loss: 0.00010175704665016383
2023-01-23 03:37:39.269210: step: 1248/529, loss: 3.6811830796068534e-05
2023-01-23 03:37:40.385087: step: 1252/529, loss: 4.329681542003527e-05
2023-01-23 03:37:41.528336: step: 1256/529, loss: 0.00011024475679732859
2023-01-23 03:37:42.699495: step: 1260/529, loss: 0.15667057037353516
2023-01-23 03:37:43.846103: step: 1264/529, loss: -1.5640260244254023e-05
2023-01-23 03:37:44.998167: step: 1268/529, loss: 0.07108354568481445
2023-01-23 03:37:46.136270: step: 1272/529, loss: 0.0019440652104094625
2023-01-23 03:37:47.287081: step: 1276/529, loss: 0.0006957054138183594
2023-01-23 03:37:48.428185: step: 1280/529, loss: 1.859665098891128e-05
2023-01-23 03:37:49.567191: step: 1284/529, loss: 0.02098236046731472
2023-01-23 03:37:50.716473: step: 1288/529, loss: 0.10217314213514328
2023-01-23 03:37:51.831267: step: 1292/529, loss: 2.6130677724722773e-05
2023-01-23 03:37:52.951487: step: 1296/529, loss: 0.21503810584545135
2023-01-23 03:37:54.131855: step: 1300/529, loss: 0.4905174672603607
2023-01-23 03:37:55.265589: step: 1304/529, loss: 0.014315987005829811
2023-01-23 03:37:56.386944: step: 1308/529, loss: 0.035672761499881744
2023-01-23 03:37:57.492183: step: 1312/529, loss: 0.010269737802445889
2023-01-23 03:37:58.647958: step: 1316/529, loss: 0.0024518966674804688
2023-01-23 03:37:59.775729: step: 1320/529, loss: 0.002910614013671875
2023-01-23 03:38:00.914737: step: 1324/529, loss: 0.0022567748092114925
2023-01-23 03:38:02.047137: step: 1328/529, loss: 5.340576171875e-05
2023-01-23 03:38:03.185295: step: 1332/529, loss: 4.024505687993951e-05
2023-01-23 03:38:04.323402: step: 1336/529, loss: 0.005511855706572533
2023-01-23 03:38:05.449371: step: 1340/529, loss: 0.0011119365226477385
2023-01-23 03:38:06.609269: step: 1344/529, loss: 0.15271367132663727
2023-01-23 03:38:07.791962: step: 1348/529, loss: 0.0032224655151367188
2023-01-23 03:38:08.915573: step: 1352/529, loss: 0.0020291327964514494
2023-01-23 03:38:10.050499: step: 1356/529, loss: 0.0032241821754723787
2023-01-23 03:38:11.189775: step: 1360/529, loss: 1.0585785275907256e-05
2023-01-23 03:38:12.333788: step: 1364/529, loss: 0.0847620964050293
2023-01-23 03:38:13.520888: step: 1368/529, loss: 0.00219554896466434
2023-01-23 03:38:14.656748: step: 1372/529, loss: 1.0251998901367188e-05
2023-01-23 03:38:15.820711: step: 1376/529, loss: 0.0014752388233318925
2023-01-23 03:38:17.008498: step: 1380/529, loss: 0.003334236331284046
2023-01-23 03:38:18.134336: step: 1384/529, loss: 0.030622007325291634
2023-01-23 03:38:19.298748: step: 1388/529, loss: 0.00020895004854537547
2023-01-23 03:38:20.455146: step: 1392/529, loss: 0.027738571166992188
2023-01-23 03:38:21.619872: step: 1396/529, loss: 0.0002605438057798892
2023-01-23 03:38:22.758531: step: 1400/529, loss: 0.015262985602021217
2023-01-23 03:38:23.907573: step: 1404/529, loss: 0.009144115261733532
2023-01-23 03:38:25.057893: step: 1408/529, loss: 8.678436643094756e-06
2023-01-23 03:38:26.217462: step: 1412/529, loss: 0.0011796951293945312
2023-01-23 03:38:27.379721: step: 1416/529, loss: 4.1484832763671875e-05
2023-01-23 03:38:28.534881: step: 1420/529, loss: 0.03665952757000923
2023-01-23 03:38:29.706709: step: 1424/529, loss: 0.017798423767089844
2023-01-23 03:38:30.860034: step: 1428/529, loss: 0.2316930741071701
2023-01-23 03:38:31.982769: step: 1432/529, loss: 0.0008451461908407509
2023-01-23 03:38:33.122028: step: 1436/529, loss: 0.00020847321138717234
2023-01-23 03:38:34.242802: step: 1440/529, loss: 0.01667856052517891
2023-01-23 03:38:35.372501: step: 1444/529, loss: 8.077621896518394e-05
2023-01-23 03:38:36.517729: step: 1448/529, loss: 3.912448664777912e-05
2023-01-23 03:38:37.693571: step: 1452/529, loss: 0.020384978502988815
2023-01-23 03:38:38.841561: step: 1456/529, loss: 0.002882003551349044
2023-01-23 03:38:39.957920: step: 1460/529, loss: 0.022124910727143288
2023-01-23 03:38:41.086298: step: 1464/529, loss: 0.5624160170555115
2023-01-23 03:38:42.216594: step: 1468/529, loss: 0.007760906592011452
2023-01-23 03:38:43.345912: step: 1472/529, loss: 0.000457572954474017
2023-01-23 03:38:44.482015: step: 1476/529, loss: 0.0004424095095600933
2023-01-23 03:38:45.613559: step: 1480/529, loss: 2.574920654296875e-05
2023-01-23 03:38:46.778124: step: 1484/529, loss: 0.019994543865323067
2023-01-23 03:38:47.943408: step: 1488/529, loss: 0.004147720523178577
2023-01-23 03:38:49.059613: step: 1492/529, loss: 0.01243824977427721
2023-01-23 03:38:50.213653: step: 1496/529, loss: 0.12420777976512909
2023-01-23 03:38:51.355814: step: 1500/529, loss: 0.006187248043715954
2023-01-23 03:38:52.526481: step: 1504/529, loss: 0.00045223237248137593
2023-01-23 03:38:53.701144: step: 1508/529, loss: 0.021202564239501953
2023-01-23 03:38:54.824243: step: 1512/529, loss: 0.06444673985242844
2023-01-23 03:38:55.996113: step: 1516/529, loss: 0.002732944441959262
2023-01-23 03:38:57.109804: step: 1520/529, loss: 0.007241630461066961
2023-01-23 03:38:58.228572: step: 1524/529, loss: 0.0011219263542443514
2023-01-23 03:38:59.357300: step: 1528/529, loss: 5.8746340073412284e-05
2023-01-23 03:39:00.513692: step: 1532/529, loss: 2.4890898203011602e-05
2023-01-23 03:39:01.655186: step: 1536/529, loss: 4.6062468754826114e-05
2023-01-23 03:39:02.782344: step: 1540/529, loss: 0.00015048979548737407
2023-01-23 03:39:03.944758: step: 1544/529, loss: 0.002295875456184149
2023-01-23 03:39:05.066601: step: 1548/529, loss: 0.00024538038996979594
2023-01-23 03:39:06.190817: step: 1552/529, loss: 0.01145162619650364
2023-01-23 03:39:07.349802: step: 1556/529, loss: 4.6348573960131034e-05
2023-01-23 03:39:08.471370: step: 1560/529, loss: 0.005608749110251665
2023-01-23 03:39:09.598227: step: 1564/529, loss: 0.0028388977516442537
2023-01-23 03:39:10.712434: step: 1568/529, loss: 0.03195914998650551
2023-01-23 03:39:11.821071: step: 1572/529, loss: 0.007009029388427734
2023-01-23 03:39:12.942719: step: 1576/529, loss: 0.0004108428838662803
2023-01-23 03:39:14.096948: step: 1580/529, loss: 0.005553627386689186
2023-01-23 03:39:15.254487: step: 1584/529, loss: 0.0016283990116789937
2023-01-23 03:39:16.379338: step: 1588/529, loss: 0.010003376752138138
2023-01-23 03:39:17.513587: step: 1592/529, loss: 0.00010910033597610891
2023-01-23 03:39:18.663588: step: 1596/529, loss: 0.012080764397978783
2023-01-23 03:39:19.798743: step: 1600/529, loss: 0.00033059119596146047
2023-01-23 03:39:20.943636: step: 1604/529, loss: 0.002101039979606867
2023-01-23 03:39:22.070303: step: 1608/529, loss: 0.006660080049186945
2023-01-23 03:39:23.233005: step: 1612/529, loss: 0.0007124424446374178
2023-01-23 03:39:24.357309: step: 1616/529, loss: 0.00019922257342841476
2023-01-23 03:39:25.514188: step: 1620/529, loss: 0.007243060972541571
2023-01-23 03:39:26.672725: step: 1624/529, loss: 0.0008311271667480469
2023-01-23 03:39:27.793036: step: 1628/529, loss: 0.00033082961454056203
2023-01-23 03:39:28.910300: step: 1632/529, loss: 0.01825103722512722
2023-01-23 03:39:30.033392: step: 1636/529, loss: 0.010642719455063343
2023-01-23 03:39:31.155096: step: 1640/529, loss: 0.003831291338428855
2023-01-23 03:39:32.325798: step: 1644/529, loss: 0.009654616937041283
2023-01-23 03:39:33.460239: step: 1648/529, loss: 0.0029598234687000513
2023-01-23 03:39:34.617133: step: 1652/529, loss: 0.03948516771197319
2023-01-23 03:39:35.765272: step: 1656/529, loss: 0.00042591095552779734
2023-01-23 03:39:36.903128: step: 1660/529, loss: 0.002352428622543812
2023-01-23 03:39:38.069920: step: 1664/529, loss: 0.006963538937270641
2023-01-23 03:39:39.214066: step: 1668/529, loss: 0.018339253962039948
2023-01-23 03:39:40.378266: step: 1672/529, loss: 0.007504081819206476
2023-01-23 03:39:41.526386: step: 1676/529, loss: 0.0008610725635662675
2023-01-23 03:39:42.673270: step: 1680/529, loss: 0.005444335751235485
2023-01-23 03:39:43.798794: step: 1684/529, loss: 4.186630030744709e-05
2023-01-23 03:39:44.942046: step: 1688/529, loss: 0.026473140344023705
2023-01-23 03:39:46.096188: step: 1692/529, loss: 9.632110595703125e-05
2023-01-23 03:39:47.219780: step: 1696/529, loss: 0.020908165723085403
2023-01-23 03:39:48.330510: step: 1700/529, loss: 0.0003749847528524697
2023-01-23 03:39:49.475315: step: 1704/529, loss: 0.010650825686752796
2023-01-23 03:39:50.596441: step: 1708/529, loss: -1.239776111106039e-06
2023-01-23 03:39:51.771974: step: 1712/529, loss: 0.007590102963149548
2023-01-23 03:39:52.899362: step: 1716/529, loss: 0.03956222906708717
2023-01-23 03:39:54.022266: step: 1720/529, loss: 0.0017209530342370272
2023-01-23 03:39:55.194026: step: 1724/529, loss: 0.00017280578322242945
2023-01-23 03:39:56.342465: step: 1728/529, loss: -1.792907642084174e-05
2023-01-23 03:39:57.485226: step: 1732/529, loss: 0.00018224716768600047
2023-01-23 03:39:58.620385: step: 1736/529, loss: 0.0002305984526174143
2023-01-23 03:39:59.769692: step: 1740/529, loss: 0.001506853150203824
2023-01-23 03:40:00.914070: step: 1744/529, loss: 0.014883900061249733
2023-01-23 03:40:02.053265: step: 1748/529, loss: 0.025953389704227448
2023-01-23 03:40:03.210827: step: 1752/529, loss: 0.0035105706192553043
2023-01-23 03:40:04.360899: step: 1756/529, loss: 0.006053662393242121
2023-01-23 03:40:05.527434: step: 1760/529, loss: 0.0061754705384373665
2023-01-23 03:40:06.679225: step: 1764/529, loss: 0.09113350510597229
2023-01-23 03:40:07.791413: step: 1768/529, loss: 0.024425029754638672
2023-01-23 03:40:08.932278: step: 1772/529, loss: 0.010309219360351562
2023-01-23 03:40:10.059309: step: 1776/529, loss: 0.00047364237252622843
2023-01-23 03:40:11.167010: step: 1780/529, loss: 0.0006474495166912675
2023-01-23 03:40:12.320884: step: 1784/529, loss: 0.004006385803222656
2023-01-23 03:40:13.459251: step: 1788/529, loss: 0.0003407478507142514
2023-01-23 03:40:14.585065: step: 1792/529, loss: 0.011897278018295765
2023-01-23 03:40:15.711637: step: 1796/529, loss: 0.022905731573700905
2023-01-23 03:40:16.835035: step: 1800/529, loss: 0.0003079414600506425
2023-01-23 03:40:17.994235: step: 1804/529, loss: 0.0005990982172079384
2023-01-23 03:40:19.151325: step: 1808/529, loss: 0.0005940438131801784
2023-01-23 03:40:20.299818: step: 1812/529, loss: 0.00010051726712845266
2023-01-23 03:40:21.416025: step: 1816/529, loss: 0.000255393999395892
2023-01-23 03:40:22.532489: step: 1820/529, loss: 0.0005625725025311112
2023-01-23 03:40:23.689566: step: 1824/529, loss: 0.013180064968764782
2023-01-23 03:40:24.822342: step: 1828/529, loss: 3.566294981283136e-05
2023-01-23 03:40:25.989725: step: 1832/529, loss: 0.017393684014678
2023-01-23 03:40:27.127841: step: 1836/529, loss: 0.019994545727968216
2023-01-23 03:40:28.256350: step: 1840/529, loss: -1.106262243411038e-05
2023-01-23 03:40:29.381779: step: 1844/529, loss: 0.00133857736364007
2023-01-23 03:40:30.524042: step: 1848/529, loss: 0.0010074615711346269
2023-01-23 03:40:31.668689: step: 1852/529, loss: 0.0013295174576342106
2023-01-23 03:40:32.853348: step: 1856/529, loss: 0.000559949898160994
2023-01-23 03:40:34.011672: step: 1860/529, loss: 0.0001224517764057964
2023-01-23 03:40:35.123119: step: 1864/529, loss: 0.024665452539920807
2023-01-23 03:40:36.247938: step: 1868/529, loss: 0.0014485359424725175
2023-01-23 03:40:37.393462: step: 1872/529, loss: 0.00034694670466706157
2023-01-23 03:40:38.520697: step: 1876/529, loss: 0.013160753063857555
2023-01-23 03:40:39.647442: step: 1880/529, loss: 3.814697265625e-06
2023-01-23 03:40:40.783858: step: 1884/529, loss: 0.018774986267089844
2023-01-23 03:40:41.912093: step: 1888/529, loss: 0.012254858389496803
2023-01-23 03:40:43.041740: step: 1892/529, loss: 0.007096671964973211
2023-01-23 03:40:44.154481: step: 1896/529, loss: 0.002977705094963312
2023-01-23 03:40:45.281183: step: 1900/529, loss: 0.0007457733154296875
2023-01-23 03:40:46.447966: step: 1904/529, loss: 0.000501442002132535
2023-01-23 03:40:47.592427: step: 1908/529, loss: 0.011918258853256702
2023-01-23 03:40:48.702038: step: 1912/529, loss: 0.0003729343297891319
2023-01-23 03:40:49.831376: step: 1916/529, loss: 3.24249267578125e-05
2023-01-23 03:40:50.966075: step: 1920/529, loss: -1.1229514711885713e-05
2023-01-23 03:40:52.102260: step: 1924/529, loss: 0.0013481139903888106
2023-01-23 03:40:53.266492: step: 1928/529, loss: 0.005128288641571999
2023-01-23 03:40:54.398050: step: 1932/529, loss: 0.00969762820750475
2023-01-23 03:40:55.535228: step: 1936/529, loss: 0.0006916046258993447
2023-01-23 03:40:56.676928: step: 1940/529, loss: 0.005804634187370539
2023-01-23 03:40:57.816414: step: 1944/529, loss: 0.0015323639381676912
2023-01-23 03:40:58.957458: step: 1948/529, loss: 0.0004495620960369706
2023-01-23 03:41:00.098793: step: 1952/529, loss: 0.06397495418787003
2023-01-23 03:41:01.246594: step: 1956/529, loss: 0.00016584395780228078
2023-01-23 03:41:02.369216: step: 1960/529, loss: 0.010841942392289639
2023-01-23 03:41:03.500281: step: 1964/529, loss: 0.0727274939417839
2023-01-23 03:41:04.651200: step: 1968/529, loss: 0.002363014267757535
2023-01-23 03:41:05.790487: step: 1972/529, loss: 0.005018997006118298
2023-01-23 03:41:06.937901: step: 1976/529, loss: 0.0017253876430913806
2023-01-23 03:41:08.085691: step: 1980/529, loss: 0.001307678292505443
2023-01-23 03:41:09.208574: step: 1984/529, loss: 0.0013345718616619706
2023-01-23 03:41:10.353368: step: 1988/529, loss: 0.007514762692153454
2023-01-23 03:41:11.473797: step: 1992/529, loss: 0.00115289690438658
2023-01-23 03:41:12.627226: step: 1996/529, loss: 0.01179647445678711
2023-01-23 03:41:13.801544: step: 2000/529, loss: 0.10675173252820969
2023-01-23 03:41:14.938261: step: 2004/529, loss: 0.0003572463756427169
2023-01-23 03:41:16.069482: step: 2008/529, loss: 0.006406307686120272
2023-01-23 03:41:17.195234: step: 2012/529, loss: 0.013830756768584251
2023-01-23 03:41:18.398187: step: 2016/529, loss: 0.0017137527465820312
2023-01-23 03:41:19.536225: step: 2020/529, loss: 0.005376243963837624
2023-01-23 03:41:20.690899: step: 2024/529, loss: 0.030878830701112747
2023-01-23 03:41:21.852371: step: 2028/529, loss: 0.25017786026000977
2023-01-23 03:41:23.011868: step: 2032/529, loss: 0.0047931671142578125
2023-01-23 03:41:24.138334: step: 2036/529, loss: 4.863739013671875e-05
2023-01-23 03:41:25.261361: step: 2040/529, loss: 0.018825722858309746
2023-01-23 03:41:26.375391: step: 2044/529, loss: 0.022179795429110527
2023-01-23 03:41:27.537132: step: 2048/529, loss: 0.005130005069077015
2023-01-23 03:41:28.678168: step: 2052/529, loss: 0.0025697709061205387
2023-01-23 03:41:29.841187: step: 2056/529, loss: 0.014226055704057217
2023-01-23 03:41:30.964924: step: 2060/529, loss: 0.005357170011848211
2023-01-23 03:41:32.092266: step: 2064/529, loss: 0.05276503413915634
2023-01-23 03:41:33.227434: step: 2068/529, loss: 0.0840001180768013
2023-01-23 03:41:34.353241: step: 2072/529, loss: 0.004636287689208984
2023-01-23 03:41:35.471662: step: 2076/529, loss: 0.0019740702118724585
2023-01-23 03:41:36.607724: step: 2080/529, loss: 0.000949859619140625
2023-01-23 03:41:37.749724: step: 2084/529, loss: 0.0011232375400140882
2023-01-23 03:41:38.929373: step: 2088/529, loss: 0.004808330442756414
2023-01-23 03:41:40.067198: step: 2092/529, loss: 0.0001665592280915007
2023-01-23 03:41:41.200140: step: 2096/529, loss: 0.02196826972067356
2023-01-23 03:41:42.335573: step: 2100/529, loss: 4.229545811540447e-05
2023-01-23 03:41:43.470406: step: 2104/529, loss: 0.02030634880065918
2023-01-23 03:41:44.617177: step: 2108/529, loss: 0.0010421753395348787
2023-01-23 03:41:45.742328: step: 2112/529, loss: 0.011526776477694511
2023-01-23 03:41:46.869628: step: 2116/529, loss: 0.00022633076878264546
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.617740232312566, 'r': 0.7789613848202397, 'f1': 0.6890459363957597}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6130374479889042, 'r': 0.7682502896871379, 'f1': 0.6819233736178967}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.625, 'r': 0.9259259259259259, 'f1': 0.7462686567164178}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.5517241379310345, 'r': 0.5079365079365079, 'f1': 0.5289256198347106}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.425, 'r': 0.4722222222222222, 'f1': 0.4473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 03:42:28.299664: step: 4/529, loss: 0.016735076904296875
2023-01-23 03:42:29.428146: step: 8/529, loss: 0.0003046035999432206
2023-01-23 03:42:30.551313: step: 12/529, loss: 0.00016117095947265625
2023-01-23 03:42:31.682569: step: 16/529, loss: 0.0005403042305260897
2023-01-23 03:42:32.823159: step: 20/529, loss: 8.468628220725805e-05
2023-01-23 03:42:33.951906: step: 24/529, loss: 0.0004939079517498612
2023-01-23 03:42:35.122983: step: 28/529, loss: 0.0001625060976948589
2023-01-23 03:42:36.225079: step: 32/529, loss: 0.0026155950035899878
2023-01-23 03:42:37.341608: step: 36/529, loss: 4.882812572759576e-05
2023-01-23 03:42:38.475876: step: 40/529, loss: 8.535384949936997e-06
2023-01-23 03:42:39.601218: step: 44/529, loss: 1.9073513612966053e-07
2023-01-23 03:42:40.700184: step: 48/529, loss: 1.5258789289873675e-06
2023-01-23 03:42:41.814960: step: 52/529, loss: 0.001263427664525807
2023-01-23 03:42:42.959126: step: 56/529, loss: 0.009744835086166859
2023-01-23 03:42:44.107394: step: 60/529, loss: 0.005537509918212891
2023-01-23 03:42:45.258907: step: 64/529, loss: 0.03282728046178818
2023-01-23 03:42:46.393603: step: 68/529, loss: 0.007790184114128351
2023-01-23 03:42:47.546591: step: 72/529, loss: 0.03408775478601456
2023-01-23 03:42:48.685282: step: 76/529, loss: 0.04925575107336044
2023-01-23 03:42:49.832072: step: 80/529, loss: 0.0003067493671551347
2023-01-23 03:42:51.010285: step: 84/529, loss: 0.005382537841796875
2023-01-23 03:42:52.139488: step: 88/529, loss: 0.002236104104667902
2023-01-23 03:42:53.255305: step: 92/529, loss: 0.004925775341689587
2023-01-23 03:42:54.366029: step: 96/529, loss: 0.003086090087890625
2023-01-23 03:42:55.518890: step: 100/529, loss: 0.004764556884765625
2023-01-23 03:42:56.677324: step: 104/529, loss: 2.670288495210116e-06
2023-01-23 03:42:57.805690: step: 108/529, loss: 0.0032699585426598787
2023-01-23 03:42:58.915626: step: 112/529, loss: 0.013358878903090954
2023-01-23 03:43:00.048154: step: 116/529, loss: 0.0001672744838288054
2023-01-23 03:43:01.216911: step: 120/529, loss: 5.531311398954131e-05
2023-01-23 03:43:02.352342: step: 124/529, loss: 0.02824885956943035
2023-01-23 03:43:03.477365: step: 128/529, loss: 1.182556115963962e-05
2023-01-23 03:43:04.616810: step: 132/529, loss: 0.004144859034568071
2023-01-23 03:43:05.742678: step: 136/529, loss: 0.0004817962762899697
2023-01-23 03:43:06.898070: step: 140/529, loss: 0.0010352134704589844
2023-01-23 03:43:08.020496: step: 144/529, loss: 5.5694577895337716e-05
2023-01-23 03:43:09.195757: step: 148/529, loss: 0.007573366165161133
2023-01-23 03:43:10.340700: step: 152/529, loss: 3.43322744811303e-06
2023-01-23 03:43:11.480837: step: 156/529, loss: 1.8119810647476697e-06
2023-01-23 03:43:12.627145: step: 160/529, loss: 0.003052663756534457
2023-01-23 03:43:13.775103: step: 164/529, loss: 0.06635075062513351
2023-01-23 03:43:14.928314: step: 168/529, loss: 0.00048704148503020406
2023-01-23 03:43:16.070938: step: 172/529, loss: 0.6253318786621094
2023-01-23 03:43:17.212096: step: 176/529, loss: 0.001586103462614119
2023-01-23 03:43:18.355964: step: 180/529, loss: 0.013029813766479492
2023-01-23 03:43:19.482607: step: 184/529, loss: 0.03591776266694069
2023-01-23 03:43:20.640375: step: 188/529, loss: 0.0006441115983761847
2023-01-23 03:43:21.766614: step: 192/529, loss: 0.0005155563121661544
2023-01-23 03:43:22.905217: step: 196/529, loss: 0.01294403150677681
2023-01-23 03:43:24.050122: step: 200/529, loss: 0.0015408515464514494
2023-01-23 03:43:25.196413: step: 204/529, loss: 0.00023283959308173507
2023-01-23 03:43:26.346788: step: 208/529, loss: 0.02212676964700222
2023-01-23 03:43:27.467293: step: 212/529, loss: 0.008818721398711205
2023-01-23 03:43:28.608088: step: 216/529, loss: 0.004449843894690275
2023-01-23 03:43:29.736738: step: 220/529, loss: 0.000255393999395892
2023-01-23 03:43:30.923306: step: 224/529, loss: 0.0005142689333297312
2023-01-23 03:43:32.038384: step: 228/529, loss: 0.00025081634521484375
2023-01-23 03:43:33.189206: step: 232/529, loss: 0.00059595110360533
2023-01-23 03:43:34.322518: step: 236/529, loss: 0.010797691531479359
2023-01-23 03:43:35.437994: step: 240/529, loss: 0.0006122589111328125
2023-01-23 03:43:36.585158: step: 244/529, loss: 0.004810523707419634
2023-01-23 03:43:37.757701: step: 248/529, loss: 0.00010070800635730848
2023-01-23 03:43:38.873765: step: 252/529, loss: 3.051757857974735e-06
2023-01-23 03:43:40.028144: step: 256/529, loss: 0.0003528594970703125
2023-01-23 03:43:41.142897: step: 260/529, loss: 0.0048877401277422905
2023-01-23 03:43:42.275912: step: 264/529, loss: 0.005888843908905983
2023-01-23 03:43:43.403094: step: 268/529, loss: 0.0011059760581701994
2023-01-23 03:43:44.553166: step: 272/529, loss: 0.0018854141235351562
2023-01-23 03:43:45.678629: step: 276/529, loss: 0.001800537109375
2023-01-23 03:43:46.805836: step: 280/529, loss: 0.014523983001708984
2023-01-23 03:43:47.946580: step: 284/529, loss: 0.006717491429299116
2023-01-23 03:43:49.089192: step: 288/529, loss: 0.0014739991165697575
2023-01-23 03:43:50.244077: step: 292/529, loss: 3.24249267578125e-05
2023-01-23 03:43:51.385511: step: 296/529, loss: 1.908540798467584e-05
2023-01-23 03:43:52.551911: step: 300/529, loss: 0.02439298667013645
2023-01-23 03:43:53.664458: step: 304/529, loss: 0.019907474517822266
2023-01-23 03:43:54.834471: step: 308/529, loss: 0.003631591796875
2023-01-23 03:43:55.961219: step: 312/529, loss: 0.0022954940795898438
2023-01-23 03:43:57.056532: step: 316/529, loss: 0.0010959625942632556
2023-01-23 03:43:58.178690: step: 320/529, loss: 0.00017099380784202367
2023-01-23 03:43:59.343186: step: 324/529, loss: 0.005465173628181219
2023-01-23 03:44:00.461736: step: 328/529, loss: 3.938675217796117e-05
2023-01-23 03:44:01.590785: step: 332/529, loss: 0.0010619163513183594
2023-01-23 03:44:02.724694: step: 336/529, loss: 0.00025305748567916453
2023-01-23 03:44:03.884261: step: 340/529, loss: 0.04783010482788086
2023-01-23 03:44:05.021016: step: 344/529, loss: -9.34600848268019e-06
2023-01-23 03:44:06.135131: step: 348/529, loss: 0.00017452241445425898
2023-01-23 03:44:07.285862: step: 352/529, loss: 0.00254058837890625
2023-01-23 03:44:08.421653: step: 356/529, loss: 0.00018424988957121968
2023-01-23 03:44:09.557446: step: 360/529, loss: 7.286071922862902e-05
2023-01-23 03:44:10.700267: step: 364/529, loss: 0.06492900848388672
2023-01-23 03:44:11.828331: step: 368/529, loss: 0.0008711814880371094
2023-01-23 03:44:12.955302: step: 372/529, loss: 0.024489879608154297
2023-01-23 03:44:14.101392: step: 376/529, loss: 8.850097947288305e-05
2023-01-23 03:44:15.247447: step: 380/529, loss: 0.01964578591287136
2023-01-23 03:44:16.354995: step: 384/529, loss: -1.697540210443549e-05
2023-01-23 03:44:17.502001: step: 388/529, loss: 9.384155418956652e-05
2023-01-23 03:44:18.659095: step: 392/529, loss: 0.005912399385124445
2023-01-23 03:44:19.819585: step: 396/529, loss: 0.030942726880311966
2023-01-23 03:44:20.958425: step: 400/529, loss: 0.0001846313534770161
2023-01-23 03:44:22.122599: step: 404/529, loss: 0.47950154542922974
2023-01-23 03:44:23.309596: step: 408/529, loss: 0.002935123397037387
2023-01-23 03:44:24.433431: step: 412/529, loss: 0.0002761363866738975
2023-01-23 03:44:25.545422: step: 416/529, loss: 0.019716359674930573
2023-01-23 03:44:26.705619: step: 420/529, loss: 0.025677969679236412
2023-01-23 03:44:27.866168: step: 424/529, loss: 0.16553755104541779
2023-01-23 03:44:29.013743: step: 428/529, loss: 0.003288078587502241
2023-01-23 03:44:30.126599: step: 432/529, loss: 0.0010836601722985506
2023-01-23 03:44:31.268612: step: 436/529, loss: 0.005914879031479359
2023-01-23 03:44:32.390294: step: 440/529, loss: 0.0001415252627339214
2023-01-23 03:44:33.536222: step: 444/529, loss: 0.018170548602938652
2023-01-23 03:44:34.680466: step: 448/529, loss: 0.0002191543608205393
2023-01-23 03:44:35.822264: step: 452/529, loss: 0.8585755228996277
2023-01-23 03:44:36.947174: step: 456/529, loss: 0.00054426200222224
2023-01-23 03:44:38.077078: step: 460/529, loss: 0.0030008316971361637
2023-01-23 03:44:39.200964: step: 464/529, loss: 1.411438006471144e-05
2023-01-23 03:44:40.328285: step: 468/529, loss: 5.257129487290513e-06
2023-01-23 03:44:41.481983: step: 472/529, loss: 0.014207884669303894
2023-01-23 03:44:42.657078: step: 476/529, loss: 0.016267204657197
2023-01-23 03:44:43.787989: step: 480/529, loss: 0.00076718331547454
2023-01-23 03:44:44.955993: step: 484/529, loss: 0.018243027850985527
2023-01-23 03:44:46.105286: step: 488/529, loss: 2.6702882678364404e-05
2023-01-23 03:44:47.271307: step: 492/529, loss: 0.4671728014945984
2023-01-23 03:44:48.387816: step: 496/529, loss: 0.0017086028819903731
2023-01-23 03:44:49.501553: step: 500/529, loss: 0.006110477726906538
2023-01-23 03:44:50.647494: step: 504/529, loss: 0.06197643280029297
2023-01-23 03:44:51.810781: step: 508/529, loss: 0.002379798796027899
2023-01-23 03:44:52.931197: step: 512/529, loss: 0.00022730827913619578
2023-01-23 03:44:54.107745: step: 516/529, loss: 0.0006975174183025956
2023-01-23 03:44:55.215648: step: 520/529, loss: 0.0005310773849487305
2023-01-23 03:44:56.329258: step: 524/529, loss: 0.005242586135864258
2023-01-23 03:44:57.458428: step: 528/529, loss: 0.02395658567547798
2023-01-23 03:44:58.558043: step: 532/529, loss: 0.0016062736976891756
2023-01-23 03:44:59.684031: step: 536/529, loss: 0.00571098318323493
2023-01-23 03:45:00.821474: step: 540/529, loss: 0.0012387275928631425
2023-01-23 03:45:01.975718: step: 544/529, loss: 0.11403026431798935
2023-01-23 03:45:03.114608: step: 548/529, loss: 0.0005660057067871094
2023-01-23 03:45:04.259710: step: 552/529, loss: 0.010829925537109375
2023-01-23 03:45:05.372447: step: 556/529, loss: 0.0021503448951989412
2023-01-23 03:45:06.531478: step: 560/529, loss: 0.002021694090217352
2023-01-23 03:45:07.674278: step: 564/529, loss: 8.471011824440211e-05
2023-01-23 03:45:08.851604: step: 568/529, loss: 0.008575248531997204
2023-01-23 03:45:09.971189: step: 572/529, loss: 0.0007753372774459422
2023-01-23 03:45:11.100543: step: 576/529, loss: 0.0674201026558876
2023-01-23 03:45:12.238978: step: 580/529, loss: 0.005821323487907648
2023-01-23 03:45:13.391013: step: 584/529, loss: 0.03056478500366211
2023-01-23 03:45:14.509474: step: 588/529, loss: 0.0003113746643066406
2023-01-23 03:45:15.649163: step: 592/529, loss: 0.0001746654452290386
2023-01-23 03:45:16.785092: step: 596/529, loss: 2.5320052372990176e-05
2023-01-23 03:45:17.939153: step: 600/529, loss: 0.04817180708050728
2023-01-23 03:45:19.090718: step: 604/529, loss: 0.021023273468017578
2023-01-23 03:45:20.231405: step: 608/529, loss: 0.008202552795410156
2023-01-23 03:45:21.358766: step: 612/529, loss: 0.018994808197021484
2023-01-23 03:45:22.497774: step: 616/529, loss: 0.004295063205063343
2023-01-23 03:45:23.637947: step: 620/529, loss: 0.017871476709842682
2023-01-23 03:45:24.786616: step: 624/529, loss: 0.018616868183016777
2023-01-23 03:45:25.923135: step: 628/529, loss: 0.0038326263893395662
2023-01-23 03:45:27.070160: step: 632/529, loss: 0.00198612199164927
2023-01-23 03:45:28.233223: step: 636/529, loss: 0.009025477804243565
2023-01-23 03:45:29.376716: step: 640/529, loss: 0.0007748603820800781
2023-01-23 03:45:30.524381: step: 644/529, loss: 0.005166816990822554
2023-01-23 03:45:31.677963: step: 648/529, loss: 0.001348209334537387
2023-01-23 03:45:32.817634: step: 652/529, loss: 6.160736666060984e-05
2023-01-23 03:45:33.957572: step: 656/529, loss: 0.0026733397971838713
2023-01-23 03:45:35.095837: step: 660/529, loss: 1.1634827387752011e-05
2023-01-23 03:45:36.241594: step: 664/529, loss: 5.2928924560546875e-05
2023-01-23 03:45:37.396854: step: 668/529, loss: -4.76837158203125e-06
2023-01-23 03:45:38.526471: step: 672/529, loss: 0.15119494497776031
2023-01-23 03:45:39.678908: step: 676/529, loss: 0.009927129372954369
2023-01-23 03:45:40.835280: step: 680/529, loss: 0.005011940374970436
2023-01-23 03:45:41.991389: step: 684/529, loss: 0.00017652512178756297
2023-01-23 03:45:43.117636: step: 688/529, loss: 0.002528286073356867
2023-01-23 03:45:44.252776: step: 692/529, loss: 0.0009696959750726819
2023-01-23 03:45:45.387106: step: 696/529, loss: 3.800392369157635e-05
2023-01-23 03:45:46.551636: step: 700/529, loss: 0.0009294509654864669
2023-01-23 03:45:47.688532: step: 704/529, loss: 0.01226959191262722
2023-01-23 03:45:48.850169: step: 708/529, loss: 0.006658363621681929
2023-01-23 03:45:49.979393: step: 712/529, loss: 0.057465553283691406
2023-01-23 03:45:51.109556: step: 716/529, loss: 0.0003197670157533139
2023-01-23 03:45:52.272010: step: 720/529, loss: 0.02584371529519558
2023-01-23 03:45:53.404873: step: 724/529, loss: 0.00026450157747603953
2023-01-23 03:45:54.552617: step: 728/529, loss: 0.00086383824236691
2023-01-23 03:45:55.674811: step: 732/529, loss: 0.00013346671767067164
2023-01-23 03:45:56.811346: step: 736/529, loss: 0.0002896309015341103
2023-01-23 03:45:57.970164: step: 740/529, loss: 0.03700866922736168
2023-01-23 03:45:59.082178: step: 744/529, loss: 8.02993745310232e-05
2023-01-23 03:46:00.239136: step: 748/529, loss: 0.02893218956887722
2023-01-23 03:46:01.364118: step: 752/529, loss: 0.00023608207993675023
2023-01-23 03:46:02.489232: step: 756/529, loss: 0.003627300262451172
2023-01-23 03:46:03.609877: step: 760/529, loss: 0.00026617050752975047
2023-01-23 03:46:04.728999: step: 764/529, loss: 0.000696372939273715
2023-01-23 03:46:05.860316: step: 768/529, loss: -6.628036317124497e-06
2023-01-23 03:46:07.024963: step: 772/529, loss: 0.00017399787611793727
2023-01-23 03:46:08.153343: step: 776/529, loss: 0.0005844116094522178
2023-01-23 03:46:09.273335: step: 780/529, loss: 0.5288364291191101
2023-01-23 03:46:10.393361: step: 784/529, loss: 0.001960658933967352
2023-01-23 03:46:11.515533: step: 788/529, loss: 0.00046401022700592875
2023-01-23 03:46:12.652413: step: 792/529, loss: 0.00016288757615257055
2023-01-23 03:46:13.797544: step: 796/529, loss: 0.0033720016945153475
2023-01-23 03:46:15.013731: step: 800/529, loss: 0.0031495571602135897
2023-01-23 03:46:16.141724: step: 804/529, loss: 0.012894725427031517
2023-01-23 03:46:17.288650: step: 808/529, loss: 0.004593467339873314
2023-01-23 03:46:18.414652: step: 812/529, loss: 1.5544892448815517e-05
2023-01-23 03:46:19.538262: step: 816/529, loss: 0.002072238828986883
2023-01-23 03:46:20.662286: step: 820/529, loss: 0.0011301040649414062
2023-01-23 03:46:21.790982: step: 824/529, loss: 0.0159822478890419
2023-01-23 03:46:22.911405: step: 828/529, loss: 0.02233438566327095
2023-01-23 03:46:24.033694: step: 832/529, loss: 0.005690193269401789
2023-01-23 03:46:25.169002: step: 836/529, loss: 0.0003026008780580014
2023-01-23 03:46:26.322350: step: 840/529, loss: 0.00027122499886900187
2023-01-23 03:46:27.469061: step: 844/529, loss: 0.0023713114205747843
2023-01-23 03:46:28.587410: step: 848/529, loss: 0.0025087357498705387
2023-01-23 03:46:29.715992: step: 852/529, loss: 0.01297693233937025
2023-01-23 03:46:30.834914: step: 856/529, loss: 0.0004116535419598222
2023-01-23 03:46:31.997130: step: 860/529, loss: 0.005075645633041859
2023-01-23 03:46:33.129361: step: 864/529, loss: 0.0013816833961755037
2023-01-23 03:46:34.276155: step: 868/529, loss: 0.009405974298715591
2023-01-23 03:46:35.425178: step: 872/529, loss: 0.06452655792236328
2023-01-23 03:46:36.564083: step: 876/529, loss: 6.723403657815652e-06
2023-01-23 03:46:37.711681: step: 880/529, loss: 0.00450897216796875
2023-01-23 03:46:38.844877: step: 884/529, loss: 0.02373971976339817
2023-01-23 03:46:39.962517: step: 888/529, loss: 0.04092784225940704
2023-01-23 03:46:41.089638: step: 892/529, loss: 0.008195591159164906
2023-01-23 03:46:42.212700: step: 896/529, loss: 0.3558819890022278
2023-01-23 03:46:43.410997: step: 900/529, loss: 0.00039167405338957906
2023-01-23 03:46:44.571857: step: 904/529, loss: 0.00016107558622024953
2023-01-23 03:46:45.722209: step: 908/529, loss: 0.0002172470121877268
2023-01-23 03:46:46.842619: step: 912/529, loss: 6.580352874152595e-06
2023-01-23 03:46:47.998708: step: 916/529, loss: 0.00269145960919559
2023-01-23 03:46:49.125464: step: 920/529, loss: 0.0008691787952557206
2023-01-23 03:46:50.235498: step: 924/529, loss: 0.00017051697068382055
2023-01-23 03:46:51.379890: step: 928/529, loss: 0.6793000102043152
2023-01-23 03:46:52.499352: step: 932/529, loss: 0.0004522323433775455
2023-01-23 03:46:53.675117: step: 936/529, loss: 0.000759124755859375
2023-01-23 03:46:54.869296: step: 940/529, loss: 0.0019077302422374487
2023-01-23 03:46:55.999158: step: 944/529, loss: 4.317760613048449e-05
2023-01-23 03:46:57.137010: step: 948/529, loss: 0.002985382219776511
2023-01-23 03:46:58.263331: step: 952/529, loss: 0.00032787321833893657
2023-01-23 03:46:59.409593: step: 956/529, loss: 0.011626770719885826
2023-01-23 03:47:00.556389: step: 960/529, loss: 5.1307681133039296e-05
2023-01-23 03:47:01.718429: step: 964/529, loss: 0.03523445129394531
2023-01-23 03:47:02.840616: step: 968/529, loss: 0.009836768731474876
2023-01-23 03:47:03.957440: step: 972/529, loss: 1.9073485191256623e-07
2023-01-23 03:47:05.095670: step: 976/529, loss: 0.00022172927856445312
2023-01-23 03:47:06.240012: step: 980/529, loss: 0.00026364324730820954
2023-01-23 03:47:07.420656: step: 984/529, loss: 0.000995635986328125
2023-01-23 03:47:08.586370: step: 988/529, loss: 0.0017072678310796618
2023-01-23 03:47:09.727839: step: 992/529, loss: 0.00033626556978560984
2023-01-23 03:47:10.860516: step: 996/529, loss: 0.00811758078634739
2023-01-23 03:47:12.003784: step: 1000/529, loss: 0.0019409179221838713
2023-01-23 03:47:13.173668: step: 1004/529, loss: 0.05268058925867081
2023-01-23 03:47:14.405296: step: 1008/529, loss: 0.0003059387090615928
2023-01-23 03:47:15.562687: step: 1012/529, loss: 0.047658536583185196
2023-01-23 03:47:16.695846: step: 1016/529, loss: 0.008768654428422451
2023-01-23 03:47:17.856859: step: 1020/529, loss: 0.05646724998950958
2023-01-23 03:47:19.012981: step: 1024/529, loss: -8.01086389401462e-06
2023-01-23 03:47:20.155783: step: 1028/529, loss: 0.00038971900357864797
2023-01-23 03:47:21.298673: step: 1032/529, loss: 0.009548378176987171
2023-01-23 03:47:22.424441: step: 1036/529, loss: 0.06464119255542755
2023-01-23 03:47:23.552926: step: 1040/529, loss: 0.000858783780131489
2023-01-23 03:47:24.700523: step: 1044/529, loss: 5.626678466796875e-05
2023-01-23 03:47:25.827207: step: 1048/529, loss: 0.02667827531695366
2023-01-23 03:47:26.947490: step: 1052/529, loss: 3.156662205583416e-05
2023-01-23 03:47:28.071618: step: 1056/529, loss: 0.020381735637784004
2023-01-23 03:47:29.209988: step: 1060/529, loss: 0.004177475348114967
2023-01-23 03:47:30.377641: step: 1064/529, loss: 5.817413330078125e-05
2023-01-23 03:47:31.541181: step: 1068/529, loss: 0.0014999390114098787
2023-01-23 03:47:32.670889: step: 1072/529, loss: 0.01082911528646946
2023-01-23 03:47:33.816864: step: 1076/529, loss: 1.220703143189894e-05
2023-01-23 03:47:34.948784: step: 1080/529, loss: 0.01040344312787056
2023-01-23 03:47:36.082045: step: 1084/529, loss: 0.0007085800170898438
2023-01-23 03:47:37.189723: step: 1088/529, loss: 0.0016246795421466231
2023-01-23 03:47:38.325383: step: 1092/529, loss: 0.00043020248995162547
2023-01-23 03:47:39.503202: step: 1096/529, loss: 0.0033636093139648438
2023-01-23 03:47:40.641583: step: 1100/529, loss: 0.0005567550542764366
2023-01-23 03:47:41.750712: step: 1104/529, loss: 0.11901941150426865
2023-01-23 03:47:42.888029: step: 1108/529, loss: 0.008436488918960094
2023-01-23 03:47:44.023084: step: 1112/529, loss: 9.822845640883315e-06
2023-01-23 03:47:45.179619: step: 1116/529, loss: 0.0013326645130291581
2023-01-23 03:47:46.339709: step: 1120/529, loss: 7.400512549793348e-05
2023-01-23 03:47:47.500744: step: 1124/529, loss: 7.114410982467234e-05
2023-01-23 03:47:48.608513: step: 1128/529, loss: 0.0004428386746440083
2023-01-23 03:47:49.756610: step: 1132/529, loss: 0.11768370121717453
2023-01-23 03:47:50.874739: step: 1136/529, loss: 0.0034254074562340975
2023-01-23 03:47:51.975968: step: 1140/529, loss: 0.04099302366375923
2023-01-23 03:47:53.117240: step: 1144/529, loss: 4.100799560546875e-05
2023-01-23 03:47:54.264500: step: 1148/529, loss: 0.009046555496752262
2023-01-23 03:47:55.400799: step: 1152/529, loss: 0.026387309655547142
2023-01-23 03:47:56.546833: step: 1156/529, loss: 7.324219041038305e-05
2023-01-23 03:47:57.674857: step: 1160/529, loss: 0.015204811468720436
2023-01-23 03:47:58.832724: step: 1164/529, loss: 0.07096929848194122
2023-01-23 03:47:59.960438: step: 1168/529, loss: 0.002702140947803855
2023-01-23 03:48:01.110541: step: 1172/529, loss: 5.283355858409777e-05
2023-01-23 03:48:02.270854: step: 1176/529, loss: 0.0001697540283203125
2023-01-23 03:48:03.411762: step: 1180/529, loss: 0.005737018771469593
2023-01-23 03:48:04.531386: step: 1184/529, loss: 0.0004400253528729081
2023-01-23 03:48:05.636242: step: 1188/529, loss: 0.00013427734666038305
2023-01-23 03:48:06.795772: step: 1192/529, loss: 0.0003814697265625
2023-01-23 03:48:07.928215: step: 1196/529, loss: 0.015169811435043812
2023-01-23 03:48:09.064743: step: 1200/529, loss: 0.0001317977876169607
2023-01-23 03:48:10.187625: step: 1204/529, loss: 0.0026090622413903475
2023-01-23 03:48:11.304973: step: 1208/529, loss: 0.001383018447086215
2023-01-23 03:48:12.439776: step: 1212/529, loss: 5.722044988942798e-07
2023-01-23 03:48:13.587570: step: 1216/529, loss: 0.01858210563659668
2023-01-23 03:48:14.713748: step: 1220/529, loss: 0.0005140304565429688
2023-01-23 03:48:15.853478: step: 1224/529, loss: -1.71661376953125e-05
2023-01-23 03:48:16.969462: step: 1228/529, loss: 0.0018571853870525956
2023-01-23 03:48:18.085808: step: 1232/529, loss: 0.0011067390441894531
2023-01-23 03:48:19.245789: step: 1236/529, loss: 0.0008175373659469187
2023-01-23 03:48:20.383946: step: 1240/529, loss: 0.01364278793334961
2023-01-23 03:48:21.541259: step: 1244/529, loss: 0.04728398472070694
2023-01-23 03:48:22.697603: step: 1248/529, loss: 0.005242061801254749
2023-01-23 03:48:23.842695: step: 1252/529, loss: 0.22273731231689453
2023-01-23 03:48:24.972540: step: 1256/529, loss: 0.00027217864408157766
2023-01-23 03:48:26.085910: step: 1260/529, loss: 2.2983551389188506e-05
2023-01-23 03:48:27.242008: step: 1264/529, loss: 0.0019635679200291634
2023-01-23 03:48:28.384809: step: 1268/529, loss: 0.006431865505874157
2023-01-23 03:48:29.549741: step: 1272/529, loss: 0.014790821820497513
2023-01-23 03:48:30.693863: step: 1276/529, loss: 0.0005578040727414191
2023-01-23 03:48:31.806366: step: 1280/529, loss: 0.004365062806755304
2023-01-23 03:48:32.938978: step: 1284/529, loss: 0.0003487587091512978
2023-01-23 03:48:34.077754: step: 1288/529, loss: 0.008034419268369675
2023-01-23 03:48:35.207971: step: 1292/529, loss: 0.018192673102021217
2023-01-23 03:48:36.337237: step: 1296/529, loss: 0.0025106428656727076
2023-01-23 03:48:37.493361: step: 1300/529, loss: 0.02113189734518528
2023-01-23 03:48:38.635133: step: 1304/529, loss: 0.0002846717834472656
2023-01-23 03:48:39.767335: step: 1308/529, loss: 0.17111073434352875
2023-01-23 03:48:40.903479: step: 1312/529, loss: 0.0045678140595555305
2023-01-23 03:48:42.022534: step: 1316/529, loss: 0.0003182411310262978
2023-01-23 03:48:43.152837: step: 1320/529, loss: 0.020606422796845436
2023-01-23 03:48:44.321409: step: 1324/529, loss: 0.0359928123652935
2023-01-23 03:48:45.434176: step: 1328/529, loss: 1.6069412595243193e-05
2023-01-23 03:48:46.608346: step: 1332/529, loss: 0.0014671325916424394
2023-01-23 03:48:47.753109: step: 1336/529, loss: 0.007130575366318226
2023-01-23 03:48:48.864871: step: 1340/529, loss: 2.632141149661038e-05
2023-01-23 03:48:50.020969: step: 1344/529, loss: 0.09547348320484161
2023-01-23 03:48:51.153487: step: 1348/529, loss: 0.0024971961975097656
2023-01-23 03:48:52.310072: step: 1352/529, loss: 1.697540210443549e-05
2023-01-23 03:48:53.424039: step: 1356/529, loss: 0.00036420824471861124
2023-01-23 03:48:54.572089: step: 1360/529, loss: 0.03777885437011719
2023-01-23 03:48:55.733878: step: 1364/529, loss: 0.016987131908535957
2023-01-23 03:48:56.865375: step: 1368/529, loss: 0.004500960931181908
2023-01-23 03:48:57.990335: step: 1372/529, loss: 0.011851596646010876
2023-01-23 03:48:59.126107: step: 1376/529, loss: 0.00048122406587935984
2023-01-23 03:49:00.265387: step: 1380/529, loss: 0.0009137153974734247
2023-01-23 03:49:01.395151: step: 1384/529, loss: 0.005162620916962624
2023-01-23 03:49:02.530914: step: 1388/529, loss: 9.15527380129788e-06
2023-01-23 03:49:03.669862: step: 1392/529, loss: 0.00013872981071472168
2023-01-23 03:49:04.821876: step: 1396/529, loss: 0.003924655728042126
2023-01-23 03:49:05.964145: step: 1400/529, loss: 0.0004564285045489669
2023-01-23 03:49:07.107587: step: 1404/529, loss: 0.009838689118623734
2023-01-23 03:49:08.234595: step: 1408/529, loss: 0.0010721206199377775
2023-01-23 03:49:09.366823: step: 1412/529, loss: 0.039681438356637955
2023-01-23 03:49:10.525117: step: 1416/529, loss: 1.258850079466356e-05
2023-01-23 03:49:11.632880: step: 1420/529, loss: 0.0007408141973428428
2023-01-23 03:49:12.803477: step: 1424/529, loss: 0.0016587257850915194
2023-01-23 03:49:13.941544: step: 1428/529, loss: 0.005351162049919367
2023-01-23 03:49:15.131629: step: 1432/529, loss: 1.2006261348724365
2023-01-23 03:49:16.272576: step: 1436/529, loss: 0.03083324432373047
2023-01-23 03:49:17.397299: step: 1440/529, loss: 0.014517402276396751
2023-01-23 03:49:18.518535: step: 1444/529, loss: 2.9659271604032256e-05
2023-01-23 03:49:19.685753: step: 1448/529, loss: 0.011948967352509499
2023-01-23 03:49:20.803559: step: 1452/529, loss: 0.0023942948319017887
2023-01-23 03:49:21.954330: step: 1456/529, loss: 0.00017585755267646164
2023-01-23 03:49:23.078588: step: 1460/529, loss: 0.0011234760750085115
2023-01-23 03:49:24.193326: step: 1464/529, loss: 0.00020284653874114156
2023-01-23 03:49:25.358042: step: 1468/529, loss: 5.549192428588867e-05
2023-01-23 03:49:26.516260: step: 1472/529, loss: -2.2411345526052173e-06
2023-01-23 03:49:27.643369: step: 1476/529, loss: 0.010947560891509056
2023-01-23 03:49:28.760180: step: 1480/529, loss: 0.02134866639971733
2023-01-23 03:49:29.910061: step: 1484/529, loss: 0.04446563497185707
2023-01-23 03:49:31.041043: step: 1488/529, loss: 6.542205665027723e-05
2023-01-23 03:49:32.188942: step: 1492/529, loss: 0.015706205740571022
2023-01-23 03:49:33.345768: step: 1496/529, loss: 0.2147197723388672
2023-01-23 03:49:34.477946: step: 1500/529, loss: 0.005993532948195934
2023-01-23 03:49:35.616247: step: 1504/529, loss: 0.0005027771112509072
2023-01-23 03:49:36.752516: step: 1508/529, loss: 5.4168704082258046e-05
2023-01-23 03:49:37.874735: step: 1512/529, loss: 7.581710815429688e-05
2023-01-23 03:49:39.047994: step: 1516/529, loss: 2.174377368646674e-05
2023-01-23 03:49:40.169032: step: 1520/529, loss: 0.0012263774406164885
2023-01-23 03:49:41.327708: step: 1524/529, loss: 0.00014729499525856227
2023-01-23 03:49:42.469807: step: 1528/529, loss: 0.00019006729417014867
2023-01-23 03:49:43.671988: step: 1532/529, loss: 0.013119888491928577
2023-01-23 03:49:44.783990: step: 1536/529, loss: 0.0004646301385946572
2023-01-23 03:49:45.935766: step: 1540/529, loss: 0.009221267886459827
2023-01-23 03:49:47.069945: step: 1544/529, loss: 0.0016561507945880294
2023-01-23 03:49:48.196126: step: 1548/529, loss: 0.007258796598762274
2023-01-23 03:49:49.377745: step: 1552/529, loss: 0.006394767668098211
2023-01-23 03:49:50.548196: step: 1556/529, loss: 0.0008476257207803428
2023-01-23 03:49:51.680731: step: 1560/529, loss: 0.6624734997749329
2023-01-23 03:49:52.797513: step: 1564/529, loss: 0.014646196737885475
2023-01-23 03:49:53.952578: step: 1568/529, loss: 0.6264400482177734
2023-01-23 03:49:55.107526: step: 1572/529, loss: 0.004799270536750555
2023-01-23 03:49:56.257792: step: 1576/529, loss: 0.03553476184606552
2023-01-23 03:49:57.436177: step: 1580/529, loss: 0.0050566671416163445
2023-01-23 03:49:58.551673: step: 1584/529, loss: 0.007789802737534046
2023-01-23 03:49:59.674626: step: 1588/529, loss: 0.0031312943901866674
2023-01-23 03:50:00.835976: step: 1592/529, loss: 0.027535725384950638
2023-01-23 03:50:01.984093: step: 1596/529, loss: 0.00347480783239007
2023-01-23 03:50:03.151622: step: 1600/529, loss: 0.01957111246883869
2023-01-23 03:50:04.297219: step: 1604/529, loss: 0.005470586009323597
2023-01-23 03:50:05.417823: step: 1608/529, loss: 0.0021026614122092724
2023-01-23 03:50:06.577085: step: 1612/529, loss: 0.01912364922463894
2023-01-23 03:50:07.712579: step: 1616/529, loss: 0.0017991543281823397
2023-01-23 03:50:08.867331: step: 1620/529, loss: 0.0031447410583496094
2023-01-23 03:50:09.998839: step: 1624/529, loss: 5.459785461425781e-05
2023-01-23 03:50:11.149242: step: 1628/529, loss: 0.00010395050048828125
2023-01-23 03:50:12.280880: step: 1632/529, loss: 0.0017313957214355469
2023-01-23 03:50:13.411939: step: 1636/529, loss: 1.2389501333236694
2023-01-23 03:50:14.585531: step: 1640/529, loss: 0.00022821426682639867
2023-01-23 03:50:15.718244: step: 1644/529, loss: 0.000545501708984375
2023-01-23 03:50:16.850843: step: 1648/529, loss: 0.04394121095538139
2023-01-23 03:50:18.026723: step: 1652/529, loss: 0.002732658525928855
2023-01-23 03:50:19.144901: step: 1656/529, loss: 0.0035509110894054174
2023-01-23 03:50:20.282488: step: 1660/529, loss: 2.765655608527595e-06
2023-01-23 03:50:21.418806: step: 1664/529, loss: 0.0003696441708598286
2023-01-23 03:50:22.567145: step: 1668/529, loss: 0.0013166428543627262
2023-01-23 03:50:23.690752: step: 1672/529, loss: 6.189346458995715e-05
2023-01-23 03:50:24.812820: step: 1676/529, loss: 0.00555343646556139
2023-01-23 03:50:25.960102: step: 1680/529, loss: 4.634857032215223e-05
2023-01-23 03:50:27.110883: step: 1684/529, loss: 0.00014719963655807078
2023-01-23 03:50:28.257683: step: 1688/529, loss: 0.024477005004882812
2023-01-23 03:50:29.390613: step: 1692/529, loss: 0.03810019791126251
2023-01-23 03:50:30.519418: step: 1696/529, loss: 0.0006124496576376259
2023-01-23 03:50:31.623485: step: 1700/529, loss: 0.0006933212280273438
2023-01-23 03:50:32.753190: step: 1704/529, loss: 0.06569556891918182
2023-01-23 03:50:33.891128: step: 1708/529, loss: 0.00969705544412136
2023-01-23 03:50:34.999095: step: 1712/529, loss: 0.00046415330143645406
2023-01-23 03:50:36.130777: step: 1716/529, loss: 0.024320030584931374
2023-01-23 03:50:37.292340: step: 1720/529, loss: 0.01116476021707058
2023-01-23 03:50:38.419248: step: 1724/529, loss: 0.027220536023378372
2023-01-23 03:50:39.556709: step: 1728/529, loss: 0.0036932947114109993
2023-01-23 03:50:40.691519: step: 1732/529, loss: 2.913475145760458e-05
2023-01-23 03:50:41.801741: step: 1736/529, loss: 0.0012719155056402087
2023-01-23 03:50:42.934000: step: 1740/529, loss: 0.022940635681152344
2023-01-23 03:50:44.051525: step: 1744/529, loss: 0.00013027191744185984
2023-01-23 03:50:45.209753: step: 1748/529, loss: 0.025810621678829193
2023-01-23 03:50:46.330942: step: 1752/529, loss: 0.0021206140518188477
2023-01-23 03:50:47.487506: step: 1756/529, loss: 0.0001560211239848286
2023-01-23 03:50:48.595320: step: 1760/529, loss: 9.613037400413305e-05
2023-01-23 03:50:49.740016: step: 1764/529, loss: 0.0020975114312022924
2023-01-23 03:50:50.882284: step: 1768/529, loss: 0.0005016326904296875
2023-01-23 03:50:52.034493: step: 1772/529, loss: 0.00112152099609375
2023-01-23 03:50:53.168517: step: 1776/529, loss: 0.00016994477482512593
2023-01-23 03:50:54.346873: step: 1780/529, loss: 0.024969100952148438
2023-01-23 03:50:55.494128: step: 1784/529, loss: 0.0065469746477901936
2023-01-23 03:50:56.663056: step: 1788/529, loss: 0.04405250772833824
2023-01-23 03:50:57.773612: step: 1792/529, loss: 0.0012364387512207031
2023-01-23 03:50:58.938046: step: 1796/529, loss: 7.514953904319555e-05
2023-01-23 03:51:00.052389: step: 1800/529, loss: 6.246566772460938e-05
2023-01-23 03:51:01.210108: step: 1804/529, loss: 0.05991210788488388
2023-01-23 03:51:02.349961: step: 1808/529, loss: 0.00048513413639739156
2023-01-23 03:51:03.484151: step: 1812/529, loss: 0.07357731461524963
2023-01-23 03:51:04.617196: step: 1816/529, loss: 0.013456725515425205
2023-01-23 03:51:05.755670: step: 1820/529, loss: 1.52587890625e-05
2023-01-23 03:51:06.917229: step: 1824/529, loss: 0.00155725481454283
2023-01-23 03:51:08.045267: step: 1828/529, loss: 0.02734222449362278
2023-01-23 03:51:09.195415: step: 1832/529, loss: 0.02555208094418049
2023-01-23 03:51:10.346135: step: 1836/529, loss: 0.00018491744413040578
2023-01-23 03:51:11.477353: step: 1840/529, loss: 0.00638313265517354
2023-01-23 03:51:12.617814: step: 1844/529, loss: 0.00017032623873092234
2023-01-23 03:51:13.751564: step: 1848/529, loss: 0.0005761146894656122
2023-01-23 03:51:14.916008: step: 1852/529, loss: 0.0024094581604003906
2023-01-23 03:51:16.052803: step: 1856/529, loss: 0.001040983246639371
2023-01-23 03:51:17.201933: step: 1860/529, loss: 0.00175647740252316
2023-01-23 03:51:18.353749: step: 1864/529, loss: 0.005059623625129461
2023-01-23 03:51:19.516392: step: 1868/529, loss: 0.04588184133172035
2023-01-23 03:51:20.650812: step: 1872/529, loss: 0.004602909088134766
2023-01-23 03:51:21.772493: step: 1876/529, loss: 0.012368394061923027
2023-01-23 03:51:22.902853: step: 1880/529, loss: 0.007129574194550514
2023-01-23 03:51:24.028456: step: 1884/529, loss: 0.02068462409079075
2023-01-23 03:51:25.146136: step: 1888/529, loss: 0.005769253242760897
2023-01-23 03:51:26.299843: step: 1892/529, loss: 0.0006010055658407509
2023-01-23 03:51:27.412367: step: 1896/529, loss: 0.016878414899110794
2023-01-23 03:51:28.618331: step: 1900/529, loss: 0.018114661797881126
2023-01-23 03:51:29.765506: step: 1904/529, loss: 0.0034267425071448088
2023-01-23 03:51:30.918246: step: 1908/529, loss: 0.0016595841152593493
2023-01-23 03:51:32.036609: step: 1912/529, loss: 0.00011882781836902723
2023-01-23 03:51:33.177670: step: 1916/529, loss: 0.0007312774541787803
2023-01-23 03:51:34.290013: step: 1920/529, loss: 0.00044541360693983734
2023-01-23 03:51:35.430311: step: 1924/529, loss: 5.197525297262473e-06
2023-01-23 03:51:36.594288: step: 1928/529, loss: -1.1920928955078125e-05
2023-01-23 03:51:37.740406: step: 1932/529, loss: 0.031696319580078125
2023-01-23 03:51:38.902364: step: 1936/529, loss: 0.00727801350876689
2023-01-23 03:51:40.047743: step: 1940/529, loss: 0.0265673641115427
2023-01-23 03:51:41.207344: step: 1944/529, loss: 0.0005628585931845009
2023-01-23 03:51:42.355442: step: 1948/529, loss: 1.4626979464082979e-05
2023-01-23 03:51:43.508029: step: 1952/529, loss: 0.0024222375359386206
2023-01-23 03:51:44.644682: step: 1956/529, loss: 0.0003109932004008442
2023-01-23 03:51:45.798270: step: 1960/529, loss: 0.05009441450238228
2023-01-23 03:51:46.921477: step: 1964/529, loss: 0.0002948761102743447
2023-01-23 03:51:48.039685: step: 1968/529, loss: 0.00027446745662018657
2023-01-23 03:51:49.201148: step: 1972/529, loss: 0.0025302888825535774
2023-01-23 03:51:50.355935: step: 1976/529, loss: 0.0003734588681254536
2023-01-23 03:51:51.509071: step: 1980/529, loss: 0.0026082515250891447
2023-01-23 03:51:52.640331: step: 1984/529, loss: 1.506805438111769e-05
2023-01-23 03:51:53.745261: step: 1988/529, loss: 0.004876136779785156
2023-01-23 03:51:54.891950: step: 1992/529, loss: 0.05193672329187393
2023-01-23 03:51:56.068286: step: 1996/529, loss: 4.901886131847277e-05
2023-01-23 03:51:57.184575: step: 2000/529, loss: 0.004590416327118874
2023-01-23 03:51:58.329410: step: 2004/529, loss: 0.0017933845520019531
2023-01-23 03:51:59.443159: step: 2008/529, loss: 1.3351440202313825e-06
2023-01-23 03:52:00.569397: step: 2012/529, loss: 0.00017604828462935984
2023-01-23 03:52:01.727493: step: 2016/529, loss: 0.00034208298893645406
2023-01-23 03:52:02.903818: step: 2020/529, loss: 3.147125244140625e-05
2023-01-23 03:52:04.023866: step: 2024/529, loss: 0.000743865966796875
2023-01-23 03:52:05.151632: step: 2028/529, loss: 0.09983968734741211
2023-01-23 03:52:06.298739: step: 2032/529, loss: 0.006250858306884766
2023-01-23 03:52:07.483009: step: 2036/529, loss: 0.0001996994105866179
2023-01-23 03:52:08.640096: step: 2040/529, loss: -1.5497207641601562e-05
2023-01-23 03:52:09.783746: step: 2044/529, loss: 0.01919403113424778
2023-01-23 03:52:10.914726: step: 2048/529, loss: 0.00012168884859420359
2023-01-23 03:52:12.066615: step: 2052/529, loss: 0.00235824566334486
2023-01-23 03:52:13.209232: step: 2056/529, loss: 5.4359438763640355e-06
2023-01-23 03:52:14.363566: step: 2060/529, loss: 0.0008721351623535156
2023-01-23 03:52:15.485120: step: 2064/529, loss: 0.00018768310837913305
2023-01-23 03:52:16.600477: step: 2068/529, loss: 0.0955018624663353
2023-01-23 03:52:17.743697: step: 2072/529, loss: 0.006647014524787664
2023-01-23 03:52:18.860156: step: 2076/529, loss: 0.003270912216976285
2023-01-23 03:52:19.961923: step: 2080/529, loss: 0.008613205514848232
2023-01-23 03:52:21.113538: step: 2084/529, loss: 0.040334321558475494
2023-01-23 03:52:22.234895: step: 2088/529, loss: 0.02104778215289116
2023-01-23 03:52:23.421760: step: 2092/529, loss: 0.03226776421070099
2023-01-23 03:52:24.548265: step: 2096/529, loss: 0.03032503090798855
2023-01-23 03:52:25.736732: step: 2100/529, loss: 0.0033143998589366674
2023-01-23 03:52:26.864711: step: 2104/529, loss: 0.0003887176571879536
2023-01-23 03:52:28.027165: step: 2108/529, loss: 0.0028007030487060547
2023-01-23 03:52:29.181191: step: 2112/529, loss: 3.2138825190486386e-05
2023-01-23 03:52:30.356104: step: 2116/529, loss: 0.0011140824062749743
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.6008230452674898, 'r': 0.7776298268974701, 'f1': 0.677887405687754}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.614115490375802, 'r': 0.776361529548088, 'f1': 0.6857727737973388}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5647058823529412, 'r': 0.8888888888888888, 'f1': 0.6906474820143885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6290322580645161, 'r': 0.6190476190476191, 'f1': 0.6240000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.40425531914893614, 'r': 0.5277777777777778, 'f1': 0.45783132530120485}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 03:53:11.903005: step: 4/529, loss: 0.001013946603052318
2023-01-23 03:53:13.109417: step: 8/529, loss: 0.0014806747203692794
2023-01-23 03:53:14.238486: step: 12/529, loss: 1.0967254638671875e-05
2023-01-23 03:53:15.392398: step: 16/529, loss: 0.04911251366138458
2023-01-23 03:53:16.521460: step: 20/529, loss: 0.010462189093232155
2023-01-23 03:53:17.679792: step: 24/529, loss: 0.0006329536554403603
2023-01-23 03:53:18.795841: step: 28/529, loss: 0.0020308971870690584
2023-01-23 03:53:19.929879: step: 32/529, loss: 0.0007181167602539062
2023-01-23 03:53:21.117815: step: 36/529, loss: 0.000355434458469972
2023-01-23 03:53:22.262956: step: 40/529, loss: 0.01822490617632866
2023-01-23 03:53:23.397252: step: 44/529, loss: 0.004099845886230469
2023-01-23 03:53:24.519980: step: 48/529, loss: 5.05924217577558e-05
2023-01-23 03:53:25.656266: step: 52/529, loss: 0.0006593704456463456
2023-01-23 03:53:26.788755: step: 56/529, loss: 0.0023607255425304174
2023-01-23 03:53:27.952101: step: 60/529, loss: 0.00033893584623001516
2023-01-23 03:53:29.055802: step: 64/529, loss: 0.0007385254139080644
2023-01-23 03:53:30.207600: step: 68/529, loss: 0.00047130585880950093
2023-01-23 03:53:31.328497: step: 72/529, loss: 0.00011682510375976562
2023-01-23 03:53:32.493072: step: 76/529, loss: 4.9352649512002245e-05
2023-01-23 03:53:33.641654: step: 80/529, loss: 0.035765647888183594
2023-01-23 03:53:34.787050: step: 84/529, loss: 0.0018444061279296875
2023-01-23 03:53:35.927964: step: 88/529, loss: 0.0009490966913290322
2023-01-23 03:53:37.063327: step: 92/529, loss: 0.17182083427906036
2023-01-23 03:53:38.208348: step: 96/529, loss: 0.0010110378498211503
2023-01-23 03:53:39.339734: step: 100/529, loss: 0.00028457643929868937
2023-01-23 03:53:40.482333: step: 104/529, loss: 0.05334491655230522
2023-01-23 03:53:41.619544: step: 108/529, loss: 0.0011515617370605469
2023-01-23 03:53:42.740687: step: 112/529, loss: 0.023218251764774323
2023-01-23 03:53:43.912162: step: 116/529, loss: 0.03040294721722603
2023-01-23 03:53:45.046367: step: 120/529, loss: 0.0005878448719158769
2023-01-23 03:53:46.169804: step: 124/529, loss: 0.0004543304385151714
2023-01-23 03:53:47.293037: step: 128/529, loss: 0.001139402505941689
2023-01-23 03:53:48.444707: step: 132/529, loss: 0.0005869865417480469
2023-01-23 03:53:49.571285: step: 136/529, loss: 0.0009716033819131553
2023-01-23 03:53:50.689541: step: 140/529, loss: 0.01589231565594673
2023-01-23 03:53:51.829218: step: 144/529, loss: 0.00355033902451396
2023-01-23 03:53:52.979650: step: 148/529, loss: 0.005140400025993586
2023-01-23 03:53:54.101050: step: 152/529, loss: 3.776550147449598e-05
2023-01-23 03:53:55.232158: step: 156/529, loss: 0.0007276535616256297
2023-01-23 03:53:56.388510: step: 160/529, loss: 0.025597669184207916
2023-01-23 03:53:57.509301: step: 164/529, loss: 0.0008609771612100303
2023-01-23 03:53:58.632466: step: 168/529, loss: -1.5258789289873675e-06
2023-01-23 03:53:59.751109: step: 172/529, loss: 0.0009891510708257556
2023-01-23 03:54:00.903705: step: 176/529, loss: 3.376007225597277e-05
2023-01-23 03:54:02.049342: step: 180/529, loss: 0.00047426222590729594
2023-01-23 03:54:03.188719: step: 184/529, loss: 0.0013746261829510331
2023-01-23 03:54:04.323594: step: 188/529, loss: 1.296997106692288e-05
2023-01-23 03:54:05.489920: step: 192/529, loss: 0.019568586722016335
2023-01-23 03:54:06.663767: step: 196/529, loss: 0.01928405836224556
2023-01-23 03:54:07.787433: step: 200/529, loss: 5.6743621826171875e-05
2023-01-23 03:54:08.948319: step: 204/529, loss: 1.2991780042648315
2023-01-23 03:54:10.114224: step: 208/529, loss: 0.02201652340590954
2023-01-23 03:54:11.299393: step: 212/529, loss: 0.01048126257956028
2023-01-23 03:54:12.443944: step: 216/529, loss: 0.0033668517135083675
2023-01-23 03:54:13.527416: step: 220/529, loss: 0.0005156517145223916
2023-01-23 03:54:14.676323: step: 224/529, loss: 0.0027120590675622225
2023-01-23 03:54:15.832345: step: 228/529, loss: 0.07571563869714737
2023-01-23 03:54:16.972262: step: 232/529, loss: 0.001874733017757535
2023-01-23 03:54:18.141948: step: 236/529, loss: 0.0017540991539135575
2023-01-23 03:54:19.284865: step: 240/529, loss: 0.1379198133945465
2023-01-23 03:54:20.433899: step: 244/529, loss: 0.0015982151962816715
2023-01-23 03:54:21.565607: step: 248/529, loss: 0.0008983612060546875
2023-01-23 03:54:22.688951: step: 252/529, loss: 0.012747693806886673
2023-01-23 03:54:23.855167: step: 256/529, loss: 0.06093959882855415
2023-01-23 03:54:24.969330: step: 260/529, loss: 1.6450882185381488e-06
2023-01-23 03:54:26.121294: step: 264/529, loss: 0.0004726409970317036
2023-01-23 03:54:27.261873: step: 268/529, loss: 0.04040488973259926
2023-01-23 03:54:28.409246: step: 272/529, loss: 0.0008518219110555947
2023-01-23 03:54:29.541335: step: 276/529, loss: 0.06798019260168076
2023-01-23 03:54:30.674684: step: 280/529, loss: 4.382133556646295e-05
2023-01-23 03:54:31.779960: step: 284/529, loss: 0.0037672999314963818
2023-01-23 03:54:32.935166: step: 288/529, loss: 0.0003046989440917969
2023-01-23 03:54:34.051246: step: 292/529, loss: 0.001876449678093195
2023-01-23 03:54:35.228502: step: 296/529, loss: 0.001920413924381137
2023-01-23 03:54:36.382272: step: 300/529, loss: 0.00024356841458939016
2023-01-23 03:54:37.503385: step: 304/529, loss: 3.051757857974735e-06
2023-01-23 03:54:38.618321: step: 308/529, loss: 0.014220619574189186
2023-01-23 03:54:39.759625: step: 312/529, loss: 0.026253510266542435
2023-01-23 03:54:40.896934: step: 316/529, loss: 0.0007222175481729209
2023-01-23 03:54:42.037232: step: 320/529, loss: 0.017185306176543236
2023-01-23 03:54:43.176498: step: 324/529, loss: 1.8596649169921875e-05
2023-01-23 03:54:44.293249: step: 328/529, loss: 4.415512375999242e-05
2023-01-23 03:54:45.419536: step: 332/529, loss: 0.00037369728670455515
2023-01-23 03:54:46.561296: step: 336/529, loss: 0.000602674437686801
2023-01-23 03:54:47.706891: step: 340/529, loss: 0.00016145706467796117
2023-01-23 03:54:48.807616: step: 344/529, loss: 0.009807157330214977
2023-01-23 03:54:49.944563: step: 348/529, loss: 0.0002236366126453504
2023-01-23 03:54:51.097224: step: 352/529, loss: 7.152557373046875e-05
2023-01-23 03:54:52.259423: step: 356/529, loss: 0.0069252969697117805
2023-01-23 03:54:53.406427: step: 360/529, loss: 0.003307914827018976
2023-01-23 03:54:54.550061: step: 364/529, loss: 0.0007120132795535028
2023-01-23 03:54:55.680319: step: 368/529, loss: 0.0014183997409418225
2023-01-23 03:54:56.816496: step: 372/529, loss: 0.01787404902279377
2023-01-23 03:54:57.961719: step: 376/529, loss: 0.0011308669345453382
2023-01-23 03:54:59.106443: step: 380/529, loss: 0.01737823523581028
2023-01-23 03:55:00.246925: step: 384/529, loss: 0.00014543533325195312
2023-01-23 03:55:01.394475: step: 388/529, loss: 0.015139603987336159
2023-01-23 03:55:02.526987: step: 392/529, loss: 0.0008463859558105469
2023-01-23 03:55:03.665468: step: 396/529, loss: 0.0147552490234375
2023-01-23 03:55:04.798027: step: 400/529, loss: 0.00144872663076967
2023-01-23 03:55:05.923220: step: 404/529, loss: 6.0081479205109645e-06
2023-01-23 03:55:07.073989: step: 408/529, loss: 5.8841709687840194e-05
2023-01-23 03:55:08.194746: step: 412/529, loss: 0.023936079815030098
2023-01-23 03:55:09.288364: step: 416/529, loss: 0.00039892198401503265
2023-01-23 03:55:10.426580: step: 420/529, loss: 0.00295085902325809
2023-01-23 03:55:11.605917: step: 424/529, loss: 0.002486991696059704
2023-01-23 03:55:12.771810: step: 428/529, loss: 0.0019152641762048006
2023-01-23 03:55:13.914338: step: 432/529, loss: 0.0036919116973876953
2023-01-23 03:55:15.055867: step: 436/529, loss: 0.0011075973743572831
2023-01-23 03:55:16.201389: step: 440/529, loss: 0.00022335053654387593
2023-01-23 03:55:17.354143: step: 444/529, loss: 0.028205109760165215
2023-01-23 03:55:18.504593: step: 448/529, loss: 0.0006905078771524131
2023-01-23 03:55:19.671032: step: 452/529, loss: 0.002415561582893133
2023-01-23 03:55:20.799829: step: 456/529, loss: 0.000102996826171875
2023-01-23 03:55:21.931248: step: 460/529, loss: 3.62396240234375e-05
2023-01-23 03:55:23.069527: step: 464/529, loss: 0.004718208219856024
2023-01-23 03:55:24.214374: step: 468/529, loss: 0.004766655154526234
2023-01-23 03:55:25.335649: step: 472/529, loss: 0.00042591095552779734
2023-01-23 03:55:26.508634: step: 476/529, loss: 0.016556359827518463
2023-01-23 03:55:27.658241: step: 480/529, loss: 0.021502207964658737
2023-01-23 03:55:28.793860: step: 484/529, loss: 0.008498096838593483
2023-01-23 03:55:29.932191: step: 488/529, loss: 0.031981468200683594
2023-01-23 03:55:31.044287: step: 492/529, loss: 0.0004113197501283139
2023-01-23 03:55:32.154151: step: 496/529, loss: 0.004234504885971546
2023-01-23 03:55:33.280717: step: 500/529, loss: 7.905960228526965e-05
2023-01-23 03:55:34.415541: step: 504/529, loss: 0.002686119172722101
2023-01-23 03:55:35.538796: step: 508/529, loss: 0.0034885406494140625
2023-01-23 03:55:36.668101: step: 512/529, loss: 0.20905399322509766
2023-01-23 03:55:37.782155: step: 516/529, loss: 0.006168842315673828
2023-01-23 03:55:38.928123: step: 520/529, loss: 0.0006644249078817666
2023-01-23 03:55:40.047506: step: 524/529, loss: 0.019455863162875175
2023-01-23 03:55:41.193527: step: 528/529, loss: 0.014922523871064186
2023-01-23 03:55:42.318763: step: 532/529, loss: 0.002437591552734375
2023-01-23 03:55:43.444936: step: 536/529, loss: 0.01637725718319416
2023-01-23 03:55:44.570970: step: 540/529, loss: 9.946823411155492e-05
2023-01-23 03:55:45.708622: step: 544/529, loss: 4.5239925384521484e-05
2023-01-23 03:55:46.880928: step: 548/529, loss: 1.23977656585339e-06
2023-01-23 03:55:48.081433: step: 552/529, loss: 6.752014451194555e-05
2023-01-23 03:55:49.236427: step: 556/529, loss: 0.003042602678760886
2023-01-23 03:55:50.396148: step: 560/529, loss: 0.0006097793811932206
2023-01-23 03:55:51.534452: step: 564/529, loss: 0.004331398289650679
2023-01-23 03:55:52.670853: step: 568/529, loss: 0.0007318496936932206
2023-01-23 03:55:53.816631: step: 572/529, loss: 0.00024309157743118703
2023-01-23 03:55:54.962499: step: 576/529, loss: 0.05574455112218857
2023-01-23 03:55:56.091401: step: 580/529, loss: 8.726119995117188e-05
2023-01-23 03:55:57.221599: step: 584/529, loss: 9.241104271495715e-05
2023-01-23 03:55:58.360047: step: 588/529, loss: 2.0599367417162284e-05
2023-01-23 03:55:59.505446: step: 592/529, loss: 0.0001791000395314768
2023-01-23 03:56:00.685109: step: 596/529, loss: 0.00029177666874602437
2023-01-23 03:56:01.815752: step: 600/529, loss: 0.007574653718620539
2023-01-23 03:56:02.961007: step: 604/529, loss: 0.00065784459002316
2023-01-23 03:56:04.072586: step: 608/529, loss: 0.00047807692317292094
2023-01-23 03:56:05.236098: step: 612/529, loss: 0.0003779649850912392
2023-01-23 03:56:06.353633: step: 616/529, loss: 6.599426706088707e-05
2023-01-23 03:56:07.488981: step: 620/529, loss: 0.02099933661520481
2023-01-23 03:56:08.623241: step: 624/529, loss: 0.00035381317138671875
2023-01-23 03:56:09.757662: step: 628/529, loss: 0.0005969524499960244
2023-01-23 03:56:10.875147: step: 632/529, loss: 0.0008316040621139109
2023-01-23 03:56:12.019298: step: 636/529, loss: 0.0018774032359942794
2023-01-23 03:56:13.154481: step: 640/529, loss: 0.029640579596161842
2023-01-23 03:56:14.278053: step: 644/529, loss: 0.5012916326522827
2023-01-23 03:56:15.405797: step: 648/529, loss: 3.509521411615424e-05
2023-01-23 03:56:16.496195: step: 652/529, loss: 0.003305673599243164
2023-01-23 03:56:17.658326: step: 656/529, loss: 0.026328660547733307
2023-01-23 03:56:18.775702: step: 660/529, loss: 0.026063919067382812
2023-01-23 03:56:19.921549: step: 664/529, loss: 0.00020313262939453125
2023-01-23 03:56:21.071239: step: 668/529, loss: 0.0005033016204833984
2023-01-23 03:56:22.207995: step: 672/529, loss: 0.03033750131726265
2023-01-23 03:56:23.360091: step: 676/529, loss: 0.022629834711551666
2023-01-23 03:56:24.511072: step: 680/529, loss: 0.0004142284451518208
2023-01-23 03:56:25.652851: step: 684/529, loss: 0.002850341610610485
2023-01-23 03:56:26.815402: step: 688/529, loss: 0.0006895065307617188
2023-01-23 03:56:27.961907: step: 692/529, loss: 0.004275131039321423
2023-01-23 03:56:29.076821: step: 696/529, loss: 5.53131121705519e-06
2023-01-23 03:56:30.254987: step: 700/529, loss: 0.015840720385313034
2023-01-23 03:56:31.394417: step: 704/529, loss: 0.0015626907115802169
2023-01-23 03:56:32.525238: step: 708/529, loss: 4.4059750507585704e-05
2023-01-23 03:56:33.675587: step: 712/529, loss: 0.0018787384033203125
2023-01-23 03:56:34.803463: step: 716/529, loss: 0.014497852884232998
2023-01-23 03:56:35.937973: step: 720/529, loss: 0.00018768310837913305
2023-01-23 03:56:37.066846: step: 724/529, loss: 2.86102294921875e-06
2023-01-23 03:56:38.200998: step: 728/529, loss: 0.0003380775451660156
2023-01-23 03:56:39.363073: step: 732/529, loss: -4.873275611316785e-05
2023-01-23 03:56:40.500580: step: 736/529, loss: 0.012883090414106846
2023-01-23 03:56:41.632656: step: 740/529, loss: 0.029575729742646217
2023-01-23 03:56:42.785646: step: 744/529, loss: 0.009055329486727715
2023-01-23 03:56:43.897620: step: 748/529, loss: 0.003642844967544079
2023-01-23 03:56:45.070404: step: 752/529, loss: 0.0011959075927734375
2023-01-23 03:56:46.218753: step: 756/529, loss: 0.0010707855690270662
2023-01-23 03:56:47.342482: step: 760/529, loss: 0.011237716302275658
2023-01-23 03:56:48.513204: step: 764/529, loss: 0.023442650213837624
2023-01-23 03:56:49.646314: step: 768/529, loss: 0.0003484726184979081
2023-01-23 03:56:50.775882: step: 772/529, loss: 0.00029983522836118937
2023-01-23 03:56:51.938411: step: 776/529, loss: 2.7847288947668858e-05
2023-01-23 03:56:53.082492: step: 780/529, loss: 0.002143478486686945
2023-01-23 03:56:54.186049: step: 784/529, loss: 0.029391765594482422
2023-01-23 03:56:55.338167: step: 788/529, loss: 2.5606155759305693e-05
2023-01-23 03:56:56.494027: step: 792/529, loss: 0.0021522522438317537
2023-01-23 03:56:57.629921: step: 796/529, loss: 0.00026187897310592234
2023-01-23 03:56:58.771482: step: 800/529, loss: 0.0777493491768837
2023-01-23 03:56:59.922294: step: 804/529, loss: 0.010334014892578125
2023-01-23 03:57:01.045874: step: 808/529, loss: 0.0003005981561727822
2023-01-23 03:57:02.188088: step: 812/529, loss: 0.005246162414550781
2023-01-23 03:57:03.329513: step: 816/529, loss: 6.923676119185984e-05
2023-01-23 03:57:04.459664: step: 820/529, loss: 0.030755234882235527
2023-01-23 03:57:05.583238: step: 824/529, loss: 0.025723746046423912
2023-01-23 03:57:06.721966: step: 828/529, loss: 0.4868951737880707
2023-01-23 03:57:07.839833: step: 832/529, loss: 0.07975530624389648
2023-01-23 03:57:08.983691: step: 836/529, loss: 5.7697296142578125e-05
2023-01-23 03:57:10.121962: step: 840/529, loss: 0.00030241013155318797
2023-01-23 03:57:11.252919: step: 844/529, loss: 0.0010480880737304688
2023-01-23 03:57:12.417287: step: 848/529, loss: 0.00161323556676507
2023-01-23 03:57:13.568604: step: 852/529, loss: 0.0004894256708212197
2023-01-23 03:57:14.671374: step: 856/529, loss: 0.0001163482666015625
2023-01-23 03:57:15.804425: step: 860/529, loss: 2.0408631826285273e-05
2023-01-23 03:57:16.949581: step: 864/529, loss: 2.28881845032447e-06
2023-01-23 03:57:18.069488: step: 868/529, loss: 1.0967254638671875e-05
2023-01-23 03:57:19.228748: step: 872/529, loss: 0.02040095254778862
2023-01-23 03:57:20.360183: step: 876/529, loss: 0.0025188445579260588
2023-01-23 03:57:21.501935: step: 880/529, loss: 0.00023384093947242945
2023-01-23 03:57:22.659612: step: 884/529, loss: 0.17876902222633362
2023-01-23 03:57:23.809354: step: 888/529, loss: 0.0006556510925292969
2023-01-23 03:57:24.933025: step: 892/529, loss: 0.00018453598022460938
2023-01-23 03:57:26.068535: step: 896/529, loss: 0.02855224721133709
2023-01-23 03:57:27.187175: step: 900/529, loss: 0.0027256966568529606
2023-01-23 03:57:28.355380: step: 904/529, loss: 0.009267712011933327
2023-01-23 03:57:29.529941: step: 908/529, loss: 0.01761026307940483
2023-01-23 03:57:30.688323: step: 912/529, loss: 5.7649613154353574e-05
2023-01-23 03:57:31.852539: step: 916/529, loss: 0.00031566619873046875
2023-01-23 03:57:32.974641: step: 920/529, loss: 0.015160655602812767
2023-01-23 03:57:34.134256: step: 924/529, loss: 0.07174129784107208
2023-01-23 03:57:35.257982: step: 928/529, loss: 4.3201445805607364e-05
2023-01-23 03:57:36.409668: step: 932/529, loss: 0.00011310577247058973
2023-01-23 03:57:37.546927: step: 936/529, loss: 0.00039958953857421875
2023-01-23 03:57:38.677010: step: 940/529, loss: 0.08551912754774094
2023-01-23 03:57:39.830369: step: 944/529, loss: 0.1024555191397667
2023-01-23 03:57:40.975311: step: 948/529, loss: 0.008458327502012253
2023-01-23 03:57:42.117270: step: 952/529, loss: 7.209777686512098e-05
2023-01-23 03:57:43.288396: step: 956/529, loss: 0.025521088391542435
2023-01-23 03:57:44.404712: step: 960/529, loss: 4.520416405284777e-05
2023-01-23 03:57:45.532693: step: 964/529, loss: 0.0006912231328897178
2023-01-23 03:57:46.655493: step: 968/529, loss: 0.0019927024841308594
2023-01-23 03:57:47.788929: step: 972/529, loss: 0.005639934912323952
2023-01-23 03:57:48.949232: step: 976/529, loss: 0.004732894711196423
2023-01-23 03:57:50.079239: step: 980/529, loss: 0.00022478103346657008
2023-01-23 03:57:51.213941: step: 984/529, loss: 0.0009107113000936806
2023-01-23 03:57:52.366529: step: 988/529, loss: 0.01344447210431099
2023-01-23 03:57:53.508123: step: 992/529, loss: 0.005950737278908491
2023-01-23 03:57:54.641292: step: 996/529, loss: 1.5735627130197827e-06
2023-01-23 03:57:55.783311: step: 1000/529, loss: 3.080368333030492e-05
2023-01-23 03:57:56.899672: step: 1004/529, loss: 0.022426128387451172
2023-01-23 03:57:58.071126: step: 1008/529, loss: 5.817413239128655e-06
2023-01-23 03:57:59.204035: step: 1012/529, loss: 0.004836845677345991
2023-01-23 03:58:00.363308: step: 1016/529, loss: 0.01833801344037056
2023-01-23 03:58:01.498063: step: 1020/529, loss: 0.0005708694225177169
2023-01-23 03:58:02.618119: step: 1024/529, loss: 0.0004096984921488911
2023-01-23 03:58:03.739904: step: 1028/529, loss: 2.956390289909905e-06
2023-01-23 03:58:04.844404: step: 1032/529, loss: 0.000637912773527205
2023-01-23 03:58:05.973105: step: 1036/529, loss: 0.00017151833162643015
2023-01-23 03:58:07.122403: step: 1040/529, loss: 0.013858413323760033
2023-01-23 03:58:08.249397: step: 1044/529, loss: 2.193450927734375e-05
2023-01-23 03:58:09.410034: step: 1048/529, loss: -3.6239621294953395e-06
2023-01-23 03:58:10.528185: step: 1052/529, loss: 0.0003209591086488217
2023-01-23 03:58:11.667695: step: 1056/529, loss: 1.277923547604587e-05
2023-01-23 03:58:12.831187: step: 1060/529, loss: 7.123947580112144e-05
2023-01-23 03:58:13.990851: step: 1064/529, loss: 0.029862498864531517
2023-01-23 03:58:15.160244: step: 1068/529, loss: 0.00033655168954283
2023-01-23 03:58:16.308904: step: 1072/529, loss: 0.000215435036807321
2023-01-23 03:58:17.487706: step: 1076/529, loss: 0.00070872314972803
2023-01-23 03:58:18.588559: step: 1080/529, loss: 0.043189048767089844
2023-01-23 03:58:19.719834: step: 1084/529, loss: 0.0008001327514648438
2023-01-23 03:58:20.877472: step: 1088/529, loss: 0.011207198724150658
2023-01-23 03:58:22.011252: step: 1092/529, loss: 0.00025463104248046875
2023-01-23 03:58:23.180388: step: 1096/529, loss: 0.014928244985640049
2023-01-23 03:58:24.347350: step: 1100/529, loss: 0.0008836746565066278
2023-01-23 03:58:25.533714: step: 1104/529, loss: 0.0008476257207803428
2023-01-23 03:58:26.688346: step: 1108/529, loss: 0.0005447387811727822
2023-01-23 03:58:27.816530: step: 1112/529, loss: 0.012865448370575905
2023-01-23 03:58:28.957091: step: 1116/529, loss: 0.006090450566262007
2023-01-23 03:58:30.100463: step: 1120/529, loss: 3.452301098150201e-05
2023-01-23 03:58:31.230772: step: 1124/529, loss: 0.0001719355641398579
2023-01-23 03:58:32.366414: step: 1128/529, loss: 0.001524257706478238
2023-01-23 03:58:33.483506: step: 1132/529, loss: 0.0004589080926962197
2023-01-23 03:58:34.636618: step: 1136/529, loss: 0.02356262318789959
2023-01-23 03:58:35.788691: step: 1140/529, loss: 0.0019364356994628906
2023-01-23 03:58:36.939177: step: 1144/529, loss: 7.343292054429185e-06
2023-01-23 03:58:38.076231: step: 1148/529, loss: 6.265639967750758e-05
2023-01-23 03:58:39.215611: step: 1152/529, loss: 0.000568008457776159
2023-01-23 03:58:40.374540: step: 1156/529, loss: 4.520416405284777e-05
2023-01-23 03:58:41.525920: step: 1160/529, loss: 0.006527900695800781
2023-01-23 03:58:42.666265: step: 1164/529, loss: 0.0015972137916833162
2023-01-23 03:58:43.796239: step: 1168/529, loss: 0.0838109478354454
2023-01-23 03:58:44.927676: step: 1172/529, loss: 0.010888099670410156
2023-01-23 03:58:46.048631: step: 1176/529, loss: 0.018135881051421165
2023-01-23 03:58:47.194931: step: 1180/529, loss: 0.015790175646543503
2023-01-23 03:58:48.322592: step: 1184/529, loss: 2.3651124138268642e-05
2023-01-23 03:58:49.436296: step: 1188/529, loss: 0.00017004013352561742
2023-01-23 03:58:50.535623: step: 1192/529, loss: 0.0024940490256994963
2023-01-23 03:58:51.714332: step: 1196/529, loss: 0.027503585442900658
2023-01-23 03:58:52.871412: step: 1200/529, loss: 0.022104360163211823
2023-01-23 03:58:54.023403: step: 1204/529, loss: 0.005454540252685547
2023-01-23 03:58:55.189949: step: 1208/529, loss: 9.536745437799254e-08
2023-01-23 03:58:56.340029: step: 1212/529, loss: 0.003224658779799938
2023-01-23 03:58:57.473453: step: 1216/529, loss: 0.011770820245146751
2023-01-23 03:58:58.606631: step: 1220/529, loss: 0.003178215119987726
2023-01-23 03:58:59.730272: step: 1224/529, loss: 0.0016875267028808594
2023-01-23 03:59:00.847306: step: 1228/529, loss: 0.010014343075454235
2023-01-23 03:59:01.979718: step: 1232/529, loss: 0.00030155183048918843
2023-01-23 03:59:03.139107: step: 1236/529, loss: 2.9850005375919864e-05
2023-01-23 03:59:04.259192: step: 1240/529, loss: 0.05257682874798775
2023-01-23 03:59:05.369854: step: 1244/529, loss: 7.286071922862902e-05
2023-01-23 03:59:06.497765: step: 1248/529, loss: 0.024857331067323685
2023-01-23 03:59:07.610469: step: 1252/529, loss: 5.407333082985133e-05
2023-01-23 03:59:08.742575: step: 1256/529, loss: 0.03173065185546875
2023-01-23 03:59:09.921724: step: 1260/529, loss: 0.00028362273587845266
2023-01-23 03:59:11.042810: step: 1264/529, loss: 7.82012939453125e-05
2023-01-23 03:59:12.162983: step: 1268/529, loss: 0.007254886440932751
2023-01-23 03:59:13.313404: step: 1272/529, loss: 0.02992229536175728
2023-01-23 03:59:14.460353: step: 1276/529, loss: 0.012044524773955345
2023-01-23 03:59:15.605526: step: 1280/529, loss: 8.583069757150952e-06
2023-01-23 03:59:16.736370: step: 1284/529, loss: 0.006409454625099897
2023-01-23 03:59:17.897025: step: 1288/529, loss: 0.0036017419770359993
2023-01-23 03:59:19.032489: step: 1292/529, loss: 0.060391616076231
2023-01-23 03:59:20.162179: step: 1296/529, loss: 0.023407461121678352
2023-01-23 03:59:21.303870: step: 1300/529, loss: 0.0007427216041833162
2023-01-23 03:59:22.453842: step: 1304/529, loss: 4.787445141118951e-05
2023-01-23 03:59:23.615134: step: 1308/529, loss: 9.250641596736386e-06
2023-01-23 03:59:24.783366: step: 1312/529, loss: 0.01085739117115736
2023-01-23 03:59:25.908749: step: 1316/529, loss: 0.0005583763704635203
2023-01-23 03:59:27.012546: step: 1320/529, loss: 0.0003733634948730469
2023-01-23 03:59:28.159050: step: 1324/529, loss: 0.00016384123591706157
2023-01-23 03:59:29.290814: step: 1328/529, loss: -5.078316007711692e-06
2023-01-23 03:59:30.399384: step: 1332/529, loss: 0.00017313957505393773
2023-01-23 03:59:31.513444: step: 1336/529, loss: 0.0031850815284997225
2023-01-23 03:59:32.647526: step: 1340/529, loss: 5.016326758777723e-05
2023-01-23 03:59:33.783775: step: 1344/529, loss: 0.00014157296391204
2023-01-23 03:59:34.930528: step: 1348/529, loss: 0.00375537876971066
2023-01-23 03:59:36.067692: step: 1352/529, loss: 0.00039844511775299907
2023-01-23 03:59:37.205929: step: 1356/529, loss: 3.843307786155492e-05
2023-01-23 03:59:38.355396: step: 1360/529, loss: 0.0011050999164581299
2023-01-23 03:59:39.470497: step: 1364/529, loss: 0.005911063868552446
2023-01-23 03:59:40.635993: step: 1368/529, loss: 7.781982276355848e-05
2023-01-23 03:59:41.793747: step: 1372/529, loss: 0.04933986812829971
2023-01-23 03:59:42.937951: step: 1376/529, loss: 0.0006162644131109118
2023-01-23 03:59:44.066744: step: 1380/529, loss: 0.013153172098100185
2023-01-23 03:59:45.160485: step: 1384/529, loss: 0.00022001266188453883
2023-01-23 03:59:46.278186: step: 1388/529, loss: 0.0002662658807821572
2023-01-23 03:59:47.418636: step: 1392/529, loss: 3.8814545405330136e-05
2023-01-23 03:59:48.555712: step: 1396/529, loss: 0.00038909912109375
2023-01-23 03:59:49.711086: step: 1400/529, loss: 0.0007755279657430947
2023-01-23 03:59:50.842062: step: 1404/529, loss: -9.5367431640625e-07
2023-01-23 03:59:51.955644: step: 1408/529, loss: 0.00013246535672806203
2023-01-23 03:59:53.109670: step: 1412/529, loss: 5.149841854290571e-06
2023-01-23 03:59:54.236433: step: 1416/529, loss: 0.0003727913135662675
2023-01-23 03:59:55.366931: step: 1420/529, loss: 0.031937409192323685
2023-01-23 03:59:56.487618: step: 1424/529, loss: 0.00014982224092818797
2023-01-23 03:59:57.641872: step: 1428/529, loss: 0.0013782501919195056
2023-01-23 03:59:58.769586: step: 1432/529, loss: 0.01560354232788086
2023-01-23 03:59:59.921834: step: 1436/529, loss: 0.010646057315170765
2023-01-23 04:00:01.030276: step: 1440/529, loss: 0.0003925800265278667
2023-01-23 04:00:02.137359: step: 1444/529, loss: 0.0003275871276855469
2023-01-23 04:00:03.272016: step: 1448/529, loss: 0.0013589859008789062
2023-01-23 04:00:04.408749: step: 1452/529, loss: 0.0010542869567871094
2023-01-23 04:00:05.529677: step: 1456/529, loss: 0.0009743691189214587
2023-01-23 04:00:06.659011: step: 1460/529, loss: 0.0018149376846849918
2023-01-23 04:00:07.797439: step: 1464/529, loss: 4.234314110362902e-05
2023-01-23 04:00:08.954792: step: 1468/529, loss: 0.013597773388028145
2023-01-23 04:00:10.097233: step: 1472/529, loss: 0.001113987062126398
2023-01-23 04:00:11.238204: step: 1476/529, loss: 0.018045520409941673
2023-01-23 04:00:12.391829: step: 1480/529, loss: 0.00022363664174918085
2023-01-23 04:00:13.536297: step: 1484/529, loss: 0.0009395600063726306
2023-01-23 04:00:14.666787: step: 1488/529, loss: 2.0694731574621983e-05
2023-01-23 04:00:15.805725: step: 1492/529, loss: 0.005797672085464001
2023-01-23 04:00:16.938363: step: 1496/529, loss: 0.0010786056518554688
2023-01-23 04:00:18.070642: step: 1500/529, loss: 2.8198955988045782e-05
2023-01-23 04:00:19.177907: step: 1504/529, loss: 0.00015583037748001516
2023-01-23 04:00:20.338635: step: 1508/529, loss: 0.05582170560956001
2023-01-23 04:00:21.469003: step: 1512/529, loss: 0.00010457039024913684
2023-01-23 04:00:22.603543: step: 1516/529, loss: 0.008766270242631435
2023-01-23 04:00:23.735136: step: 1520/529, loss: 0.00030136111308820546
2023-01-23 04:00:24.895719: step: 1524/529, loss: 0.005076408386230469
2023-01-23 04:00:26.043070: step: 1528/529, loss: 0.023174572736024857
2023-01-23 04:00:27.158898: step: 1532/529, loss: 0.0015774727798998356
2023-01-23 04:00:28.295747: step: 1536/529, loss: 0.0013002395862713456
2023-01-23 04:00:29.434973: step: 1540/529, loss: 3.967285010730848e-05
2023-01-23 04:00:30.572561: step: 1544/529, loss: 0.006561290938407183
2023-01-23 04:00:31.713177: step: 1548/529, loss: 0.00968628004193306
2023-01-23 04:00:32.843199: step: 1552/529, loss: 0.00025920866755768657
2023-01-23 04:00:33.984530: step: 1556/529, loss: 9.222030348610133e-05
2023-01-23 04:00:35.118522: step: 1560/529, loss: 0.0006708145374432206
2023-01-23 04:00:36.259756: step: 1564/529, loss: 0.017557907849550247
2023-01-23 04:00:37.403498: step: 1568/529, loss: 4.510879807639867e-05
2023-01-23 04:00:38.596766: step: 1572/529, loss: 0.0346345417201519
2023-01-23 04:00:39.737327: step: 1576/529, loss: 0.0022831440437585115
2023-01-23 04:00:40.916139: step: 1580/529, loss: 5.474090721691027e-05
2023-01-23 04:00:42.068712: step: 1584/529, loss: 0.023574447259306908
2023-01-23 04:00:43.210217: step: 1588/529, loss: 0.0004336357524152845
2023-01-23 04:00:44.328803: step: 1592/529, loss: 6.361008126987144e-05
2023-01-23 04:00:45.495600: step: 1596/529, loss: 0.00021452904911711812
2023-01-23 04:00:46.611548: step: 1600/529, loss: 6.365776062011719e-05
2023-01-23 04:00:47.754799: step: 1604/529, loss: 0.000492095947265625
2023-01-23 04:00:48.885987: step: 1608/529, loss: 0.0033493044320493937
2023-01-23 04:00:50.011582: step: 1612/529, loss: 0.0005512237548828125
2023-01-23 04:00:51.156531: step: 1616/529, loss: 0.0008112907526083291
2023-01-23 04:00:52.273267: step: 1620/529, loss: 5.187988426769152e-05
2023-01-23 04:00:53.384423: step: 1624/529, loss: 0.0016328812343999743
2023-01-23 04:00:54.520598: step: 1628/529, loss: 0.014824867248535156
2023-01-23 04:00:55.688259: step: 1632/529, loss: 0.0015411376953125
2023-01-23 04:00:56.815795: step: 1636/529, loss: 0.00016584395780228078
2023-01-23 04:00:57.949688: step: 1640/529, loss: 0.020351506769657135
2023-01-23 04:00:59.086839: step: 1644/529, loss: 5.340576535672881e-06
2023-01-23 04:01:00.227749: step: 1648/529, loss: 0.030076026916503906
2023-01-23 04:01:01.363954: step: 1652/529, loss: 1.6880036127986386e-05
2023-01-23 04:01:02.518393: step: 1656/529, loss: 0.0028074264992028475
2023-01-23 04:01:03.681648: step: 1660/529, loss: 0.0017692565452307463
2023-01-23 04:01:04.827625: step: 1664/529, loss: 0.0008330822456628084
2023-01-23 04:01:05.995725: step: 1668/529, loss: 4.520416405284777e-05
2023-01-23 04:01:07.135399: step: 1672/529, loss: 0.0011369704734534025
2023-01-23 04:01:08.268171: step: 1676/529, loss: 0.0015088021755218506
2023-01-23 04:01:09.404435: step: 1680/529, loss: 0.003866863204166293
2023-01-23 04:01:10.521556: step: 1684/529, loss: 0.0014294624561443925
2023-01-23 04:01:11.640666: step: 1688/529, loss: 0.00011692046973621473
2023-01-23 04:01:12.831800: step: 1692/529, loss: 0.04233064502477646
2023-01-23 04:01:14.019264: step: 1696/529, loss: 7.019639451755211e-05
2023-01-23 04:01:15.133707: step: 1700/529, loss: 2.47955313170678e-06
2023-01-23 04:01:16.250182: step: 1704/529, loss: 0.003833484835922718
2023-01-23 04:01:17.385459: step: 1708/529, loss: 0.0008071899646893144
2023-01-23 04:01:18.579068: step: 1712/529, loss: 0.031946755945682526
2023-01-23 04:01:19.741307: step: 1716/529, loss: 0.00388755789026618
2023-01-23 04:01:20.887660: step: 1720/529, loss: 0.000125885009765625
2023-01-23 04:01:22.009831: step: 1724/529, loss: 0.017482567578554153
2023-01-23 04:01:23.159316: step: 1728/529, loss: 3.309249586891383e-05
2023-01-23 04:01:24.363289: step: 1732/529, loss: 0.021950339898467064
2023-01-23 04:01:25.480053: step: 1736/529, loss: 0.020756147801876068
2023-01-23 04:01:26.621814: step: 1740/529, loss: 0.007392740808427334
2023-01-23 04:01:27.745733: step: 1744/529, loss: 0.0001312255917582661
2023-01-23 04:01:28.895975: step: 1748/529, loss: 0.0014501571422442794
2023-01-23 04:01:30.036399: step: 1752/529, loss: 0.0005636215792037547
2023-01-23 04:01:31.172828: step: 1756/529, loss: 1.630783299333416e-05
2023-01-23 04:01:32.347375: step: 1760/529, loss: 0.0012319564120844007
2023-01-23 04:01:33.486756: step: 1764/529, loss: 2.5272369384765625e-05
2023-01-23 04:01:34.633575: step: 1768/529, loss: 0.0031745911110192537
2023-01-23 04:01:35.761607: step: 1772/529, loss: 0.05386314541101456
2023-01-23 04:01:36.894348: step: 1776/529, loss: 0.00989675521850586
2023-01-23 04:01:38.051810: step: 1780/529, loss: 7.057189577608369e-06
2023-01-23 04:01:39.174578: step: 1784/529, loss: 1.913309097290039e-05
2023-01-23 04:01:40.294439: step: 1788/529, loss: 0.0403226837515831
2023-01-23 04:01:41.428498: step: 1792/529, loss: 0.0128027917817235
2023-01-23 04:01:42.543646: step: 1796/529, loss: 0.00035600661067292094
2023-01-23 04:01:43.650104: step: 1800/529, loss: 4.76837158203125e-07
2023-01-23 04:01:44.770488: step: 1804/529, loss: 3.6239625842426904e-06
2023-01-23 04:01:45.902044: step: 1808/529, loss: 0.0009952544933184981
2023-01-23 04:01:47.008351: step: 1812/529, loss: 1.0204315913142636e-05
2023-01-23 04:01:48.177731: step: 1816/529, loss: 0.0016179084777832031
2023-01-23 04:01:49.348884: step: 1820/529, loss: 0.00019531250291038305
2023-01-23 04:01:50.456018: step: 1824/529, loss: 0.0003185272216796875
2023-01-23 04:01:51.592977: step: 1828/529, loss: 0.04625721275806427
2023-01-23 04:01:52.723180: step: 1832/529, loss: 0.001628112862817943
2023-01-23 04:01:53.863222: step: 1836/529, loss: 0.0002382278471486643
2023-01-23 04:01:54.998656: step: 1840/529, loss: 0.0005735397571697831
2023-01-23 04:01:56.125519: step: 1844/529, loss: 0.004591417498886585
2023-01-23 04:01:57.221689: step: 1848/529, loss: 0.0018312096362933517
2023-01-23 04:01:58.380253: step: 1852/529, loss: 0.011274718679487705
2023-01-23 04:01:59.526210: step: 1856/529, loss: 0.20404338836669922
2023-01-23 04:02:00.641071: step: 1860/529, loss: 0.00748634384945035
2023-01-23 04:02:01.795508: step: 1864/529, loss: 0.003515625139698386
2023-01-23 04:02:02.915912: step: 1868/529, loss: 0.004873943515121937
2023-01-23 04:02:04.034116: step: 1872/529, loss: 0.09463195502758026
2023-01-23 04:02:05.187332: step: 1876/529, loss: 0.00016899108595680445
2023-01-23 04:02:06.324477: step: 1880/529, loss: 0.005844330880790949
2023-01-23 04:02:07.439286: step: 1884/529, loss: 0.012272643856704235
2023-01-23 04:02:08.592699: step: 1888/529, loss: 0.0001358032168354839
2023-01-23 04:02:09.724490: step: 1892/529, loss: 0.000583267246838659
2023-01-23 04:02:10.840503: step: 1896/529, loss: 0.00044279100256972015
2023-01-23 04:02:12.001160: step: 1900/529, loss: 0.005678749177604914
2023-01-23 04:02:13.175594: step: 1904/529, loss: 0.06716375052928925
2023-01-23 04:02:14.305113: step: 1908/529, loss: 0.0012897491687908769
2023-01-23 04:02:15.446976: step: 1912/529, loss: 7.629394644936838e-07
2023-01-23 04:02:16.606238: step: 1916/529, loss: 0.003146457951515913
2023-01-23 04:02:17.748381: step: 1920/529, loss: 0.017220117151737213
2023-01-23 04:02:18.901817: step: 1924/529, loss: 0.025179291144013405
2023-01-23 04:02:20.048163: step: 1928/529, loss: 0.01859769970178604
2023-01-23 04:02:21.205294: step: 1932/529, loss: 0.00045080186100676656
2023-01-23 04:02:22.353235: step: 1936/529, loss: 0.00013189316086936742
2023-01-23 04:02:23.458192: step: 1940/529, loss: 0.0013317108387127519
2023-01-23 04:02:24.609220: step: 1944/529, loss: 8.01086389401462e-06
2023-01-23 04:02:25.787559: step: 1948/529, loss: 0.003793192096054554
2023-01-23 04:02:26.936176: step: 1952/529, loss: 0.0007216691737994552
2023-01-23 04:02:28.108689: step: 1956/529, loss: 0.0025382996536791325
2023-01-23 04:02:29.240157: step: 1960/529, loss: 0.011472892947494984
2023-01-23 04:02:30.350498: step: 1964/529, loss: 0.00029506682767532766
2023-01-23 04:02:31.500001: step: 1968/529, loss: 0.02381540648639202
2023-01-23 04:02:32.635006: step: 1972/529, loss: 0.004935312084853649
2023-01-23 04:02:33.780894: step: 1976/529, loss: 0.03358879312872887
2023-01-23 04:02:34.907550: step: 1980/529, loss: 7.653236389160156e-05
2023-01-23 04:02:36.024560: step: 1984/529, loss: 0.00019989012798760086
2023-01-23 04:02:37.176949: step: 1988/529, loss: 0.03326358646154404
2023-01-23 04:02:38.323028: step: 1992/529, loss: 7.495880709029734e-05
2023-01-23 04:02:39.483544: step: 1996/529, loss: 0.01268157921731472
2023-01-23 04:02:40.626930: step: 2000/529, loss: 0.0002911090850830078
2023-01-23 04:02:41.777932: step: 2004/529, loss: 3.099441755693988e-06
2023-01-23 04:02:42.937870: step: 2008/529, loss: 0.04755115509033203
2023-01-23 04:02:44.052039: step: 2012/529, loss: 0.00027958155260421336
2023-01-23 04:02:45.192881: step: 2016/529, loss: 0.00018339157395530492
2023-01-23 04:02:46.301227: step: 2020/529, loss: 0.004827404394745827
2023-01-23 04:02:47.473874: step: 2024/529, loss: 0.010423803701996803
2023-01-23 04:02:48.615767: step: 2028/529, loss: 0.004334449768066406
2023-01-23 04:02:49.745581: step: 2032/529, loss: 0.0029649734497070312
2023-01-23 04:02:50.873862: step: 2036/529, loss: 0.000263214111328125
2023-01-23 04:02:52.010247: step: 2040/529, loss: 0.0004093170282430947
2023-01-23 04:02:53.191516: step: 2044/529, loss: 0.011854076758027077
2023-01-23 04:02:54.309285: step: 2048/529, loss: 0.011608600616455078
2023-01-23 04:02:55.436227: step: 2052/529, loss: 0.1497991681098938
2023-01-23 04:02:56.605741: step: 2056/529, loss: 0.006811714265495539
2023-01-23 04:02:57.746053: step: 2060/529, loss: 0.0003196716425009072
2023-01-23 04:02:58.905547: step: 2064/529, loss: 0.08308602124452591
2023-01-23 04:03:00.047542: step: 2068/529, loss: 0.012317419052124023
2023-01-23 04:03:01.216459: step: 2072/529, loss: 0.00596199044957757
2023-01-23 04:03:02.370325: step: 2076/529, loss: 0.00810022372752428
2023-01-23 04:03:03.498317: step: 2080/529, loss: 0.0073060994036495686
2023-01-23 04:03:04.612679: step: 2084/529, loss: 5.6982044043252245e-05
2023-01-23 04:03:05.747043: step: 2088/529, loss: 0.0009246825939044356
2023-01-23 04:03:06.877440: step: 2092/529, loss: 2.632141149661038e-05
2023-01-23 04:03:08.060535: step: 2096/529, loss: 0.002387619111686945
2023-01-23 04:03:09.211215: step: 2100/529, loss: 0.42215338349342346
2023-01-23 04:03:10.329553: step: 2104/529, loss: 2.822876012942288e-05
2023-01-23 04:03:11.454288: step: 2108/529, loss: 0.00105705251917243
2023-01-23 04:03:12.584399: step: 2112/529, loss: 0.00037355421227402985
2023-01-23 04:03:13.722607: step: 2116/529, loss: 2.288818359375e-05
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.6153846153846154, 'r': 0.7776298268974701, 'f1': 0.6870588235294117}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6281622911694511, 'r': 0.7624565469293163, 'f1': 0.688824914943732}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.6071428571428571, 'r': 0.9444444444444444, 'f1': 0.7391304347826088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6346153846153846, 'r': 0.5238095238095238, 'f1': 0.5739130434782609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.45, 'r': 0.5, 'f1': 0.4736842105263158}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample 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': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 26
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:03:55.418938: step: 4/529, loss: 8.96453821042087e-06
2023-01-23 04:03:56.548338: step: 8/529, loss: 4.4488908315543085e-05
2023-01-23 04:03:57.705249: step: 12/529, loss: 0.002907657530158758
2023-01-23 04:03:58.822417: step: 16/529, loss: 0.00037097930908203125
2023-01-23 04:03:59.977908: step: 20/529, loss: 0.004302501678466797
2023-01-23 04:04:01.088645: step: 24/529, loss: 0.30834951996803284
2023-01-23 04:04:02.230953: step: 28/529, loss: 0.00033321380033157766
2023-01-23 04:04:03.353665: step: 32/529, loss: 3.261566234868951e-05
2023-01-23 04:04:04.464883: step: 36/529, loss: 0.09074363857507706
2023-01-23 04:04:05.577961: step: 40/529, loss: 0.0003279685915913433
2023-01-23 04:04:06.697453: step: 44/529, loss: 0.0006367683527059853
2023-01-23 04:04:07.824927: step: 48/529, loss: 0.00043802260188385844
2023-01-23 04:04:08.951980: step: 52/529, loss: 3.1471254260395654e-06
2023-01-23 04:04:10.109473: step: 56/529, loss: 0.006996059790253639
2023-01-23 04:04:11.244196: step: 60/529, loss: 0.019316673278808594
2023-01-23 04:04:12.363236: step: 64/529, loss: 3.24249276673072e-06
2023-01-23 04:04:13.528573: step: 68/529, loss: 0.0003741264226846397
2023-01-23 04:04:14.694098: step: 72/529, loss: 0.0005276203155517578
2023-01-23 04:04:15.809083: step: 76/529, loss: 0.055098723620176315
2023-01-23 04:04:16.928695: step: 80/529, loss: 0.002068138215690851
2023-01-23 04:04:18.066600: step: 84/529, loss: 0.027022553607821465
2023-01-23 04:04:19.191132: step: 88/529, loss: 0.0007644862052984536
2023-01-23 04:04:20.324189: step: 92/529, loss: 0.0041280267760157585
2023-01-23 04:04:21.506715: step: 96/529, loss: 0.0018192291026934981
2023-01-23 04:04:22.650601: step: 100/529, loss: 0.00018129349336959422
2023-01-23 04:04:23.792540: step: 104/529, loss: 0.01891937293112278
2023-01-23 04:04:24.938569: step: 108/529, loss: 1.2207032341393642e-05
2023-01-23 04:04:26.093314: step: 112/529, loss: 0.03567390888929367
2023-01-23 04:04:27.217052: step: 116/529, loss: 0.007838440127670765
2023-01-23 04:04:28.370725: step: 120/529, loss: 0.004745387937873602
2023-01-23 04:04:29.501475: step: 124/529, loss: 0.08916740864515305
2023-01-23 04:04:30.661985: step: 128/529, loss: 0.00011096000525867566
2023-01-23 04:04:31.784918: step: 132/529, loss: 0.003695583436638117
2023-01-23 04:04:32.918106: step: 136/529, loss: 0.0042276387102901936
2023-01-23 04:04:34.087519: step: 140/529, loss: 0.00316448207013309
2023-01-23 04:04:35.242617: step: 144/529, loss: 1.33514404296875e-05
2023-01-23 04:04:36.389938: step: 148/529, loss: -5.53131121705519e-06
2023-01-23 04:04:37.512151: step: 152/529, loss: 0.012916945852339268
2023-01-23 04:04:38.671905: step: 156/529, loss: 0.01326827984303236
2023-01-23 04:04:39.791433: step: 160/529, loss: 0.005604743957519531
2023-01-23 04:04:40.940503: step: 164/529, loss: 8.535384949936997e-06
2023-01-23 04:04:42.056635: step: 168/529, loss: 0.00024299621873069555
2023-01-23 04:04:43.156434: step: 172/529, loss: 0.1924852430820465
2023-01-23 04:04:44.267933: step: 176/529, loss: 0.010990954004228115
2023-01-23 04:04:45.392703: step: 180/529, loss: 0.0005296707386150956
2023-01-23 04:04:46.553349: step: 184/529, loss: 0.0011724472278729081
2023-01-23 04:04:47.675190: step: 188/529, loss: 0.06467151641845703
2023-01-23 04:04:48.823392: step: 192/529, loss: 0.016022492200136185
2023-01-23 04:04:49.961153: step: 196/529, loss: 9.536745437799254e-08
2023-01-23 04:04:51.110062: step: 200/529, loss: 0.004081535153090954
2023-01-23 04:04:52.235933: step: 204/529, loss: -8.583068620282575e-07
2023-01-23 04:04:53.357762: step: 208/529, loss: 1.792907642084174e-05
2023-01-23 04:04:54.505643: step: 212/529, loss: 0.0718531683087349
2023-01-23 04:04:55.630219: step: 216/529, loss: 0.00038776398287154734
2023-01-23 04:04:56.753694: step: 220/529, loss: 2.174377368646674e-05
2023-01-23 04:04:57.901242: step: 224/529, loss: 0.044367216527462006
2023-01-23 04:04:59.035928: step: 228/529, loss: 2.250671423098538e-05
2023-01-23 04:05:00.163760: step: 232/529, loss: 4.024505687993951e-05
2023-01-23 04:05:01.284070: step: 236/529, loss: -3.24249276673072e-06
2023-01-23 04:05:02.421294: step: 240/529, loss: 0.006203079596161842
2023-01-23 04:05:03.537465: step: 244/529, loss: 0.0977473333477974
2023-01-23 04:05:04.713960: step: 248/529, loss: 0.021058129146695137
2023-01-23 04:05:05.850578: step: 252/529, loss: 5.340576171875e-05
2023-01-23 04:05:07.025771: step: 256/529, loss: 0.0009552002302370965
2023-01-23 04:05:08.163664: step: 260/529, loss: 5.3739546274300665e-05
2023-01-23 04:05:09.312653: step: 264/529, loss: 0.0010913849109783769
2023-01-23 04:05:10.426773: step: 268/529, loss: 0.012735843658447266
2023-01-23 04:05:11.564269: step: 272/529, loss: 0.00018100737361237407
2023-01-23 04:05:12.694409: step: 276/529, loss: 0.030130673199892044
2023-01-23 04:05:13.828858: step: 280/529, loss: 0.0010991096496582031
2023-01-23 04:05:14.960388: step: 284/529, loss: 0.001411533448845148
2023-01-23 04:05:16.101914: step: 288/529, loss: 0.001535916468128562
2023-01-23 04:05:17.238136: step: 292/529, loss: 0.0002761840878520161
2023-01-23 04:05:18.380414: step: 296/529, loss: 0.00039272307185456157
2023-01-23 04:05:19.505354: step: 300/529, loss: 0.0019807815551757812
2023-01-23 04:05:20.673216: step: 304/529, loss: 0.009366036392748356
2023-01-23 04:05:21.822505: step: 308/529, loss: 0.010482979007065296
2023-01-23 04:05:22.961893: step: 312/529, loss: -1.239776611328125e-05
2023-01-23 04:05:24.109647: step: 316/529, loss: 3.051757857974735e-06
2023-01-23 04:05:25.261166: step: 320/529, loss: 0.00038471221341751516
2023-01-23 04:05:26.374846: step: 324/529, loss: 0.09281168133020401
2023-01-23 04:05:27.503674: step: 328/529, loss: 0.0006923199398443103
2023-01-23 04:05:28.654032: step: 332/529, loss: 0.040256500244140625
2023-01-23 04:05:29.775841: step: 336/529, loss: 0.0006785392761230469
2023-01-23 04:05:30.911837: step: 340/529, loss: 4.291534423828125e-06
2023-01-23 04:05:32.059035: step: 344/529, loss: 0.00109691615216434
2023-01-23 04:05:33.214429: step: 348/529, loss: 0.006427288055419922
2023-01-23 04:05:34.356415: step: 352/529, loss: 3.24249276673072e-06
2023-01-23 04:05:35.495842: step: 356/529, loss: 0.03780064731836319
2023-01-23 04:05:36.655857: step: 360/529, loss: 0.5025267004966736
2023-01-23 04:05:37.789580: step: 364/529, loss: 9.059906005859375e-06
2023-01-23 04:05:38.928016: step: 368/529, loss: 0.00015249251737259328
2023-01-23 04:05:40.048086: step: 372/529, loss: 0.00033359526423737407
2023-01-23 04:05:41.170823: step: 376/529, loss: 0.00014324189396575093
2023-01-23 04:05:42.358478: step: 380/529, loss: 0.003743934677913785
2023-01-23 04:05:43.491206: step: 384/529, loss: 2.77042381640058e-05
2023-01-23 04:05:44.646287: step: 388/529, loss: 0.0007335662958212197
2023-01-23 04:05:45.790274: step: 392/529, loss: 1.296997106692288e-05
2023-01-23 04:05:46.961790: step: 396/529, loss: 0.0031459808815270662
2023-01-23 04:05:48.102526: step: 400/529, loss: 0.05556111037731171
2023-01-23 04:05:49.224755: step: 404/529, loss: 1.2351150512695312
2023-01-23 04:05:50.364672: step: 408/529, loss: 9.098052396439016e-05
2023-01-23 04:05:51.497969: step: 412/529, loss: 0.00017623901658225805
2023-01-23 04:05:52.666845: step: 416/529, loss: 0.00036535263643600047
2023-01-23 04:05:53.803778: step: 420/529, loss: 0.00022583008103538305
2023-01-23 04:05:54.954202: step: 424/529, loss: 3.910065061063506e-05
2023-01-23 04:05:56.103870: step: 428/529, loss: 0.000933742499910295
2023-01-23 04:05:57.231217: step: 432/529, loss: 3.0265749956015497e-05
2023-01-23 04:05:58.368447: step: 436/529, loss: 0.0075724124908447266
2023-01-23 04:05:59.510662: step: 440/529, loss: 0.7691519856452942
2023-01-23 04:06:00.675091: step: 444/529, loss: 0.001775455428287387
2023-01-23 04:06:01.837740: step: 448/529, loss: 0.034665536135435104
2023-01-23 04:06:02.991110: step: 452/529, loss: 1.3256072634248994e-05
2023-01-23 04:06:04.146708: step: 456/529, loss: 0.024933243170380592
2023-01-23 04:06:05.307421: step: 460/529, loss: 0.04186420515179634
2023-01-23 04:06:06.424620: step: 464/529, loss: 0.009877776727080345
2023-01-23 04:06:07.575969: step: 468/529, loss: 6.237030902411789e-05
2023-01-23 04:06:08.725052: step: 472/529, loss: 0.001939964247867465
2023-01-23 04:06:09.885103: step: 476/529, loss: 0.0004507065168581903
2023-01-23 04:06:11.032561: step: 480/529, loss: 3.1185150874080136e-05
2023-01-23 04:06:12.150853: step: 484/529, loss: 0.00043935776920989156
2023-01-23 04:06:13.276870: step: 488/529, loss: 0.004915905185043812
2023-01-23 04:06:14.448074: step: 492/529, loss: 0.0007184982532635331
2023-01-23 04:06:15.600537: step: 496/529, loss: 0.00047335628187283874
2023-01-23 04:06:16.759781: step: 500/529, loss: 0.08391036838293076
2023-01-23 04:06:17.921691: step: 504/529, loss: 5.9127810345671605e-06
2023-01-23 04:06:19.050304: step: 508/529, loss: 0.010232162661850452
2023-01-23 04:06:20.180597: step: 512/529, loss: 0.056586649268865585
2023-01-23 04:06:21.348403: step: 516/529, loss: 0.0015436173416674137
2023-01-23 04:06:22.495942: step: 520/529, loss: 0.0031437876168638468
2023-01-23 04:06:23.630640: step: 524/529, loss: 0.06874551624059677
2023-01-23 04:06:24.768123: step: 528/529, loss: 4.6348573960131034e-05
2023-01-23 04:06:25.905003: step: 532/529, loss: 6.146430678199977e-05
2023-01-23 04:06:27.056080: step: 536/529, loss: 0.04005012661218643
2023-01-23 04:06:28.246368: step: 540/529, loss: 0.0006504058837890625
2023-01-23 04:06:29.390909: step: 544/529, loss: 8.42094377730973e-05
2023-01-23 04:06:30.532519: step: 548/529, loss: 0.0010725021129474044
2023-01-23 04:06:31.699156: step: 552/529, loss: 0.021811293438076973
2023-01-23 04:06:32.830114: step: 556/529, loss: 3.4618376957951114e-05
2023-01-23 04:06:33.996346: step: 560/529, loss: 0.02456836774945259
2023-01-23 04:06:35.132568: step: 564/529, loss: 0.0021480561699718237
2023-01-23 04:06:36.259610: step: 568/529, loss: 0.025208855047822
2023-01-23 04:06:37.429589: step: 572/529, loss: 2.346038854739163e-05
2023-01-23 04:06:38.584847: step: 576/529, loss: 0.056058503687381744
2023-01-23 04:06:39.723951: step: 580/529, loss: 0.00014934540376998484
2023-01-23 04:06:40.850524: step: 584/529, loss: 0.006783866789191961
2023-01-23 04:06:41.971984: step: 588/529, loss: 0.022428322583436966
2023-01-23 04:06:43.116669: step: 592/529, loss: 0.0047227381728589535
2023-01-23 04:06:44.251512: step: 596/529, loss: 2.0313262211857364e-05
2023-01-23 04:06:45.402318: step: 600/529, loss: 0.013123512268066406
2023-01-23 04:06:46.568798: step: 604/529, loss: 0.0038618086837232113
2023-01-23 04:06:47.714199: step: 608/529, loss: 1.1873245057358872e-05
2023-01-23 04:06:48.843735: step: 612/529, loss: 0.0003950119426008314
2023-01-23 04:06:50.008307: step: 616/529, loss: 0.0004839897155761719
2023-01-23 04:06:51.196580: step: 620/529, loss: 0.0001333236723439768
2023-01-23 04:06:52.344426: step: 624/529, loss: 0.0266297347843647
2023-01-23 04:06:53.486274: step: 628/529, loss: 0.0013212204212322831
2023-01-23 04:06:54.624715: step: 632/529, loss: 3.24249276673072e-06
2023-01-23 04:06:55.774385: step: 636/529, loss: 7.886887033237144e-05
2023-01-23 04:06:56.932393: step: 640/529, loss: 0.0001672267826506868
2023-01-23 04:06:58.081069: step: 644/529, loss: 0.09417933970689774
2023-01-23 04:06:59.197516: step: 648/529, loss: 0.4512098431587219
2023-01-23 04:07:00.331993: step: 652/529, loss: 1.1157989320054185e-05
2023-01-23 04:07:01.459765: step: 656/529, loss: 0.0016958237392827868
2023-01-23 04:07:02.596672: step: 660/529, loss: 0.009069633670151234
2023-01-23 04:07:03.749543: step: 664/529, loss: 0.0366973876953125
2023-01-23 04:07:04.896400: step: 668/529, loss: 0.01766986958682537
2023-01-23 04:07:06.041530: step: 672/529, loss: 0.17697934806346893
2023-01-23 04:07:07.188561: step: 676/529, loss: 0.0019632340408861637
2023-01-23 04:07:08.356133: step: 680/529, loss: 0.00139617919921875
2023-01-23 04:07:09.486446: step: 684/529, loss: 0.0015018463600426912
2023-01-23 04:07:10.624499: step: 688/529, loss: 0.0141334543004632
2023-01-23 04:07:11.741568: step: 692/529, loss: 0.0002841949462890625
2023-01-23 04:07:12.886032: step: 696/529, loss: 0.24535417556762695
2023-01-23 04:07:13.985054: step: 700/529, loss: 0.000568008457776159
2023-01-23 04:07:15.122403: step: 704/529, loss: 0.004303932189941406
2023-01-23 04:07:16.254750: step: 708/529, loss: 2.727508581301663e-05
2023-01-23 04:07:17.380226: step: 712/529, loss: 0.0004912376753054559
2023-01-23 04:07:18.510961: step: 716/529, loss: 0.016112612560391426
2023-01-23 04:07:19.650095: step: 720/529, loss: 0.00021057129197288305
2023-01-23 04:07:20.783096: step: 724/529, loss: 1.735687328618951e-05
2023-01-23 04:07:21.887421: step: 728/529, loss: 0.03154563903808594
2023-01-23 04:07:23.036678: step: 732/529, loss: 1.0681153071345761e-05
2023-01-23 04:07:24.193994: step: 736/529, loss: 3.166198803228326e-05
2023-01-23 04:07:25.332636: step: 740/529, loss: 0.01360998209565878
2023-01-23 04:07:26.488115: step: 744/529, loss: 0.00011034011549782008
2023-01-23 04:07:27.657141: step: 748/529, loss: 8.769035048317164e-05
2023-01-23 04:07:28.813059: step: 752/529, loss: 0.0005148887867107987
2023-01-23 04:07:29.970252: step: 756/529, loss: 0.02043437957763672
2023-01-23 04:07:31.149862: step: 760/529, loss: 0.00034484866773709655
2023-01-23 04:07:32.313535: step: 764/529, loss: 0.0001930236758198589
2023-01-23 04:07:33.466572: step: 768/529, loss: 0.0018659591441974044
2023-01-23 04:07:34.573336: step: 772/529, loss: 0.00015707017155364156
2023-01-23 04:07:35.721046: step: 776/529, loss: 0.0005457877996377647
2023-01-23 04:07:36.854242: step: 780/529, loss: 0.015224170871078968
2023-01-23 04:07:37.988334: step: 784/529, loss: 0.00010557175119174644
2023-01-23 04:07:39.118993: step: 788/529, loss: 0.0006026267656125128
2023-01-23 04:07:40.281390: step: 792/529, loss: 0.1750757247209549
2023-01-23 04:07:41.424139: step: 796/529, loss: 0.012186002917587757
2023-01-23 04:07:42.598055: step: 800/529, loss: 0.0015291214222088456
2023-01-23 04:07:43.772914: step: 804/529, loss: 0.00023746490478515625
2023-01-23 04:07:44.916133: step: 808/529, loss: 0.001124477363191545
2023-01-23 04:07:46.028196: step: 812/529, loss: 0.006601524073630571
2023-01-23 04:07:47.155741: step: 816/529, loss: 0.01242895144969225
2023-01-23 04:07:48.317677: step: 820/529, loss: 0.009865950793027878
2023-01-23 04:07:49.440393: step: 824/529, loss: 0.0004544258408714086
2023-01-23 04:07:50.571381: step: 828/529, loss: 0.0067078592255711555
2023-01-23 04:07:51.756845: step: 832/529, loss: 0.00017529279284644872
2023-01-23 04:07:52.856550: step: 836/529, loss: 6.256103370105848e-05
2023-01-23 04:07:54.019493: step: 840/529, loss: 0.0012102127075195312
2023-01-23 04:07:55.162285: step: 844/529, loss: 0.0049002645537257195
2023-01-23 04:07:56.302966: step: 848/529, loss: 0.009509658440947533
2023-01-23 04:07:57.424396: step: 852/529, loss: 1.1920928955078125e-05
2023-01-23 04:07:58.566960: step: 856/529, loss: 0.00020799637422896922
2023-01-23 04:07:59.706482: step: 860/529, loss: 0.00026636122493073344
2023-01-23 04:08:00.834662: step: 864/529, loss: 0.0007151603931561112
2023-01-23 04:08:01.990167: step: 868/529, loss: 3.156662205583416e-05
2023-01-23 04:08:03.152249: step: 872/529, loss: 0.0005590915679931641
2023-01-23 04:08:04.305344: step: 876/529, loss: 0.005429076962172985
2023-01-23 04:08:05.446022: step: 880/529, loss: 0.005028152372688055
2023-01-23 04:08:06.560338: step: 884/529, loss: 0.007692909333854914
2023-01-23 04:08:07.695445: step: 888/529, loss: 0.0010052680736407638
2023-01-23 04:08:08.836986: step: 892/529, loss: 7.32898770365864e-05
2023-01-23 04:08:09.984054: step: 896/529, loss: 0.0015866756439208984
2023-01-23 04:08:11.121015: step: 900/529, loss: 0.0001235961972270161
2023-01-23 04:08:12.238708: step: 904/529, loss: 0.00016899110050871968
2023-01-23 04:08:13.386998: step: 908/529, loss: 0.034955691546201706
2023-01-23 04:08:14.540759: step: 912/529, loss: 5.9127810345671605e-06
2023-01-23 04:08:15.711476: step: 916/529, loss: 0.0010168076260015368
2023-01-23 04:08:16.840672: step: 920/529, loss: 0.010859775356948376
2023-01-23 04:08:17.973184: step: 924/529, loss: 6.532669431180693e-06
2023-01-23 04:08:19.099579: step: 928/529, loss: 0.0006397724500857294
2023-01-23 04:08:20.207256: step: 932/529, loss: 0.0002849578741006553
2023-01-23 04:08:21.345952: step: 936/529, loss: 0.0031124113593250513
2023-01-23 04:08:22.489721: step: 940/529, loss: 0.0004236697859596461
2023-01-23 04:08:23.654228: step: 944/529, loss: 0.0029403686057776213
2023-01-23 04:08:24.822604: step: 948/529, loss: 4.0626528061693534e-05
2023-01-23 04:08:25.967850: step: 952/529, loss: 0.0004571914905682206
2023-01-23 04:08:27.092188: step: 956/529, loss: 4.539489600574598e-05
2023-01-23 04:08:28.222065: step: 960/529, loss: 0.017323875799775124
2023-01-23 04:08:29.347724: step: 964/529, loss: 0.004857063293457031
2023-01-23 04:08:30.478742: step: 968/529, loss: 0.018172835931181908
2023-01-23 04:08:31.610896: step: 972/529, loss: 0.00021157265291549265
2023-01-23 04:08:32.734722: step: 976/529, loss: 3.070831371587701e-05
2023-01-23 04:08:33.836183: step: 980/529, loss: 0.00037059784517623484
2023-01-23 04:08:34.954858: step: 984/529, loss: 0.04704561084508896
2023-01-23 04:08:36.066438: step: 988/529, loss: 0.00142078404314816
2023-01-23 04:08:37.205493: step: 992/529, loss: 0.0006403445731848478
2023-01-23 04:08:38.359252: step: 996/529, loss: 0.04136943817138672
2023-01-23 04:08:39.501539: step: 1000/529, loss: 0.08497877418994904
2023-01-23 04:08:40.665808: step: 1004/529, loss: 0.021245384588837624
2023-01-23 04:08:41.842018: step: 1008/529, loss: 0.0018030166393145919
2023-01-23 04:08:42.966136: step: 1012/529, loss: 0.0008520125993527472
2023-01-23 04:08:44.129308: step: 1016/529, loss: 0.0025169372092932463
2023-01-23 04:08:45.269463: step: 1020/529, loss: 0.0009592533460818231
2023-01-23 04:08:46.388337: step: 1024/529, loss: 0.0011817931663244963
2023-01-23 04:08:47.548617: step: 1028/529, loss: 0.06252622604370117
2023-01-23 04:08:48.704437: step: 1032/529, loss: 0.012900067493319511
2023-01-23 04:08:49.860343: step: 1036/529, loss: 4.8160552978515625e-05
2023-01-23 04:08:50.980327: step: 1040/529, loss: 0.00027866364689543843
2023-01-23 04:08:52.153585: step: 1044/529, loss: 0.000592136406339705
2023-01-23 04:08:53.372730: step: 1048/529, loss: 0.001291465712711215
2023-01-23 04:08:54.527035: step: 1052/529, loss: 0.0004100799560546875
2023-01-23 04:08:55.692035: step: 1056/529, loss: 7.152557373046875e-07
2023-01-23 04:08:56.842765: step: 1060/529, loss: 0.008410071954131126
2023-01-23 04:08:57.991120: step: 1064/529, loss: 0.04589061811566353
2023-01-23 04:08:59.123493: step: 1068/529, loss: 0.010752486996352673
2023-01-23 04:09:00.253985: step: 1072/529, loss: 0.0020864487159997225
2023-01-23 04:09:01.389702: step: 1076/529, loss: 0.002227210905402899
2023-01-23 04:09:02.514557: step: 1080/529, loss: 0.00018053055100608617
2023-01-23 04:09:03.645159: step: 1084/529, loss: 0.005826139822602272
2023-01-23 04:09:04.807491: step: 1088/529, loss: 0.005850601010024548
2023-01-23 04:09:05.951149: step: 1092/529, loss: 2.784729076665826e-05
2023-01-23 04:09:07.090165: step: 1096/529, loss: 0.0032237053383141756
2023-01-23 04:09:08.228537: step: 1100/529, loss: 0.03524189069867134
2023-01-23 04:09:09.358483: step: 1104/529, loss: 0.0002799004432745278
2023-01-23 04:09:10.499243: step: 1108/529, loss: 0.021262170746922493
2023-01-23 04:09:11.644676: step: 1112/529, loss: 0.00638999929651618
2023-01-23 04:09:12.794086: step: 1116/529, loss: 0.002037906553596258
2023-01-23 04:09:13.917885: step: 1120/529, loss: 0.0007957458728924394
2023-01-23 04:09:15.054823: step: 1124/529, loss: 0.43960848450660706
2023-01-23 04:09:16.188950: step: 1128/529, loss: 1.258850079466356e-05
2023-01-23 04:09:17.362853: step: 1132/529, loss: 0.004829979036003351
2023-01-23 04:09:18.505389: step: 1136/529, loss: 0.016794968396425247
2023-01-23 04:09:19.639899: step: 1140/529, loss: 0.00046176911564543843
2023-01-23 04:09:20.833380: step: 1144/529, loss: 0.022540664300322533
2023-01-23 04:09:21.979724: step: 1148/529, loss: 0.0004364013730082661
2023-01-23 04:09:23.129152: step: 1152/529, loss: 0.0005045891157351434
2023-01-23 04:09:24.256098: step: 1156/529, loss: 0.002950024791061878
2023-01-23 04:09:25.414890: step: 1160/529, loss: 0.0016188144218176603
2023-01-23 04:09:26.555902: step: 1164/529, loss: 0.03747672960162163
2023-01-23 04:09:27.689572: step: 1168/529, loss: 0.015600014477968216
2023-01-23 04:09:28.818797: step: 1172/529, loss: 0.0008846282726153731
2023-01-23 04:09:29.943000: step: 1176/529, loss: 0.009301901794970036
2023-01-23 04:09:31.077007: step: 1180/529, loss: 0.002321624895557761
2023-01-23 04:09:32.209358: step: 1184/529, loss: 0.00018367767916060984
2023-01-23 04:09:33.362694: step: 1188/529, loss: 0.031671904027462006
2023-01-23 04:09:34.521941: step: 1192/529, loss: 0.004562854766845703
2023-01-23 04:09:35.645169: step: 1196/529, loss: 0.0003017425478901714
2023-01-23 04:09:36.815249: step: 1200/529, loss: 0.09037017822265625
2023-01-23 04:09:37.979898: step: 1204/529, loss: 0.00662574777379632
2023-01-23 04:09:39.119134: step: 1208/529, loss: 8.98361176950857e-05
2023-01-23 04:09:40.245459: step: 1212/529, loss: 0.0009596825111657381
2023-01-23 04:09:41.381998: step: 1216/529, loss: 0.0002099037083098665
2023-01-23 04:09:42.521791: step: 1220/529, loss: 0.2793978750705719
2023-01-23 04:09:43.664539: step: 1224/529, loss: 3.14712519866589e-06
2023-01-23 04:09:44.806293: step: 1228/529, loss: 0.001050710678100586
2023-01-23 04:09:45.955670: step: 1232/529, loss: 0.03034496307373047
2023-01-23 04:09:47.136040: step: 1236/529, loss: 0.2675352096557617
2023-01-23 04:09:48.305927: step: 1240/529, loss: 0.00013446807861328125
2023-01-23 04:09:49.470404: step: 1244/529, loss: 0.0014706611400470138
2023-01-23 04:09:50.598169: step: 1248/529, loss: 3.6907196772517636e-05
2023-01-23 04:09:51.725376: step: 1252/529, loss: 0.0008793831220827997
2023-01-23 04:09:52.861579: step: 1256/529, loss: 0.0881032943725586
2023-01-23 04:09:53.963032: step: 1260/529, loss: 2.4938583010225557e-05
2023-01-23 04:09:55.147581: step: 1264/529, loss: 0.011941909790039062
2023-01-23 04:09:56.295878: step: 1268/529, loss: 0.010002613067626953
2023-01-23 04:09:57.431692: step: 1272/529, loss: 0.0001237869291799143
2023-01-23 04:09:58.572159: step: 1276/529, loss: 0.0019558907952159643
2023-01-23 04:09:59.686498: step: 1280/529, loss: 0.031830836087465286
2023-01-23 04:10:00.793652: step: 1284/529, loss: 9.002684964798391e-05
2023-01-23 04:10:01.940596: step: 1288/529, loss: 4.76837158203125e-07
2023-01-23 04:10:03.089572: step: 1292/529, loss: 0.00022544861712958664
2023-01-23 04:10:04.224988: step: 1296/529, loss: 1.7833710444392636e-05
2023-01-23 04:10:05.362022: step: 1300/529, loss: 0.03179354593157768
2023-01-23 04:10:06.475395: step: 1304/529, loss: 0.004338455386459827
2023-01-23 04:10:07.610624: step: 1308/529, loss: 0.1165735274553299
2023-01-23 04:10:08.758198: step: 1312/529, loss: 0.005232191178947687
2023-01-23 04:10:09.909054: step: 1316/529, loss: 0.001739120576530695
2023-01-23 04:10:11.039273: step: 1320/529, loss: 0.046267319470644
2023-01-23 04:10:12.183581: step: 1324/529, loss: 0.0024361610412597656
2023-01-23 04:10:13.317055: step: 1328/529, loss: 0.003507423447445035
2023-01-23 04:10:14.464051: step: 1332/529, loss: 0.014626026153564453
2023-01-23 04:10:15.626483: step: 1336/529, loss: 0.004086542408913374
2023-01-23 04:10:16.795857: step: 1340/529, loss: 9.727478754939511e-06
2023-01-23 04:10:17.957422: step: 1344/529, loss: 6.65664701955393e-05
2023-01-23 04:10:19.096014: step: 1348/529, loss: 0.00417251605540514
2023-01-23 04:10:20.246155: step: 1352/529, loss: 0.0012601851485669613
2023-01-23 04:10:21.389974: step: 1356/529, loss: 7.3909759521484375e-06
2023-01-23 04:10:22.551982: step: 1360/529, loss: 0.016218949109315872
2023-01-23 04:10:23.694895: step: 1364/529, loss: 0.0018317223293706775
2023-01-23 04:10:24.829101: step: 1368/529, loss: 0.00023431777663063258
2023-01-23 04:10:25.971970: step: 1372/529, loss: 0.0007516384357586503
2023-01-23 04:10:27.090273: step: 1376/529, loss: 0.0014029026497155428
2023-01-23 04:10:28.212068: step: 1380/529, loss: 0.0012340785469859838
2023-01-23 04:10:29.325738: step: 1384/529, loss: 7.98225446487777e-05
2023-01-23 04:10:30.457165: step: 1388/529, loss: 0.000264072441495955
2023-01-23 04:10:31.605104: step: 1392/529, loss: 0.00384101876989007
2023-01-23 04:10:32.745076: step: 1396/529, loss: 8.77380352903856e-06
2023-01-23 04:10:33.884231: step: 1400/529, loss: 0.031851768493652344
2023-01-23 04:10:35.053494: step: 1404/529, loss: 0.0003501892206259072
2023-01-23 04:10:36.231195: step: 1408/529, loss: 5.035400317865424e-05
2023-01-23 04:10:37.379513: step: 1412/529, loss: 0.024449730291962624
2023-01-23 04:10:38.520201: step: 1416/529, loss: 6.675720669591101e-07
2023-01-23 04:10:39.647195: step: 1420/529, loss: 0.0012067795032635331
2023-01-23 04:10:40.790977: step: 1424/529, loss: 0.024570656940340996
2023-01-23 04:10:41.966562: step: 1428/529, loss: 0.05239295959472656
2023-01-23 04:10:43.128376: step: 1432/529, loss: 0.014387321658432484
2023-01-23 04:10:44.279526: step: 1436/529, loss: 0.03099660947918892
2023-01-23 04:10:45.431690: step: 1440/529, loss: 0.02800159528851509
2023-01-23 04:10:46.547278: step: 1444/529, loss: 0.001612854073755443
2023-01-23 04:10:47.672967: step: 1448/529, loss: 0.2234325408935547
2023-01-23 04:10:48.834542: step: 1452/529, loss: 0.02595958672463894
2023-01-23 04:10:49.986545: step: 1456/529, loss: 0.00014762878709007055
2023-01-23 04:10:51.126314: step: 1460/529, loss: 0.006358528509736061
2023-01-23 04:10:52.299148: step: 1464/529, loss: 0.0019478797912597656
2023-01-23 04:10:53.437815: step: 1468/529, loss: 8.60214204294607e-05
2023-01-23 04:10:54.559722: step: 1472/529, loss: 0.042075347155332565
2023-01-23 04:10:55.713185: step: 1476/529, loss: 5.726814197259955e-05
2023-01-23 04:10:56.856932: step: 1480/529, loss: 0.0007891893037594855
2023-01-23 04:10:57.982437: step: 1484/529, loss: 0.004864311311393976
2023-01-23 04:10:59.126280: step: 1488/529, loss: 0.6411482691764832
2023-01-23 04:11:00.249601: step: 1492/529, loss: 0.0012891769874840975
2023-01-23 04:11:01.414304: step: 1496/529, loss: 0.004120063968002796
2023-01-23 04:11:02.581880: step: 1500/529, loss: 0.026310063898563385
2023-01-23 04:11:03.710874: step: 1504/529, loss: 0.00031447410583496094
2023-01-23 04:11:04.844500: step: 1508/529, loss: 0.000286960625089705
2023-01-23 04:11:06.010542: step: 1512/529, loss: 0.0010220528347417712
2023-01-23 04:11:07.164995: step: 1516/529, loss: 0.005054282955825329
2023-01-23 04:11:08.320646: step: 1520/529, loss: 0.038840580731630325
2023-01-23 04:11:09.478776: step: 1524/529, loss: 0.0013293266529217362
2023-01-23 04:11:10.611361: step: 1528/529, loss: 6.86645489622606e-06
2023-01-23 04:11:11.753081: step: 1532/529, loss: 0.020098304376006126
2023-01-23 04:11:12.886063: step: 1536/529, loss: 4.57763690064894e-06
2023-01-23 04:11:14.030608: step: 1540/529, loss: 9.70840483205393e-05
2023-01-23 04:11:15.161173: step: 1544/529, loss: 0.008495330810546875
2023-01-23 04:11:16.350955: step: 1548/529, loss: 0.0585138313472271
2023-01-23 04:11:17.523488: step: 1552/529, loss: 8.993149094749242e-05
2023-01-23 04:11:18.659912: step: 1556/529, loss: 0.0025121690705418587
2023-01-23 04:11:19.858992: step: 1560/529, loss: 0.008127069100737572
2023-01-23 04:11:21.014796: step: 1564/529, loss: 0.005356073845177889
2023-01-23 04:11:22.166063: step: 1568/529, loss: 3.409385681152344e-05
2023-01-23 04:11:23.280617: step: 1572/529, loss: 0.00020461082749534398
2023-01-23 04:11:24.429140: step: 1576/529, loss: 0.001741170883178711
2023-01-23 04:11:25.532047: step: 1580/529, loss: 0.0009002685546875
2023-01-23 04:11:26.646394: step: 1584/529, loss: 0.00589942978695035
2023-01-23 04:11:27.809971: step: 1588/529, loss: 0.015538979321718216
2023-01-23 04:11:28.968587: step: 1592/529, loss: 0.0016294480301439762
2023-01-23 04:11:30.092995: step: 1596/529, loss: 1.883506956801284e-05
2023-01-23 04:11:31.213381: step: 1600/529, loss: 0.0008074759971350431
2023-01-23 04:11:32.361283: step: 1604/529, loss: 0.0193954948335886
2023-01-23 04:11:33.497406: step: 1608/529, loss: 0.00011940002877963707
2023-01-23 04:11:34.683945: step: 1612/529, loss: 8.39233416627394e-06
2023-01-23 04:11:35.809688: step: 1616/529, loss: 0.007128715515136719
2023-01-23 04:11:36.953967: step: 1620/529, loss: 0.0029812813736498356
2023-01-23 04:11:38.081159: step: 1624/529, loss: 0.0038179398979991674
2023-01-23 04:11:39.223616: step: 1628/529, loss: 0.3166733682155609
2023-01-23 04:11:40.360205: step: 1632/529, loss: 0.00024018288240768015
2023-01-23 04:11:41.517666: step: 1636/529, loss: 0.00017385483079124242
2023-01-23 04:11:42.637046: step: 1640/529, loss: 9.412765211891383e-05
2023-01-23 04:11:43.784257: step: 1644/529, loss: 0.07429618388414383
2023-01-23 04:11:44.919998: step: 1648/529, loss: 0.14327794313430786
2023-01-23 04:11:46.052708: step: 1652/529, loss: 0.007124996278434992
2023-01-23 04:11:47.186265: step: 1656/529, loss: 0.01361846923828125
2023-01-23 04:11:48.344600: step: 1660/529, loss: 0.0011077881790697575
2023-01-23 04:11:49.501463: step: 1664/529, loss: 0.0008556365501135588
2023-01-23 04:11:50.644037: step: 1668/529, loss: 0.0033148766960948706
2023-01-23 04:11:51.818277: step: 1672/529, loss: 0.001680564833804965
2023-01-23 04:11:52.930813: step: 1676/529, loss: 0.00018877982802223414
2023-01-23 04:11:54.075769: step: 1680/529, loss: 0.0029356004670262337
2023-01-23 04:11:55.196020: step: 1684/529, loss: 0.021885110065340996
2023-01-23 04:11:56.333165: step: 1688/529, loss: 0.0006837845430709422
2023-01-23 04:11:57.469040: step: 1692/529, loss: 0.057054709643125534
2023-01-23 04:11:58.588179: step: 1696/529, loss: 0.0024429322220385075
2023-01-23 04:11:59.753360: step: 1700/529, loss: 4.234314110362902e-05
2023-01-23 04:12:00.914523: step: 1704/529, loss: 0.021677494049072266
2023-01-23 04:12:02.016041: step: 1708/529, loss: 0.0029172897338867188
2023-01-23 04:12:03.144796: step: 1712/529, loss: 6.942749314475805e-05
2023-01-23 04:12:04.321325: step: 1716/529, loss: 5.168914867681451e-05
2023-01-23 04:12:05.479438: step: 1720/529, loss: 0.001136875245720148
2023-01-23 04:12:06.618202: step: 1724/529, loss: 0.06153149902820587
2023-01-23 04:12:07.736455: step: 1728/529, loss: 0.052689552307128906
2023-01-23 04:12:08.880406: step: 1732/529, loss: 0.00362396240234375
2023-01-23 04:12:10.012304: step: 1736/529, loss: 0.017075633630156517
2023-01-23 04:12:11.156016: step: 1740/529, loss: 6.27517729299143e-05
2023-01-23 04:12:12.294539: step: 1744/529, loss: 0.00016860960749909282
2023-01-23 04:12:13.462729: step: 1748/529, loss: 0.0006542205810546875
2023-01-23 04:12:14.623445: step: 1752/529, loss: 3.738403393072076e-05
2023-01-23 04:12:15.757235: step: 1756/529, loss: 0.00019721986609511077
2023-01-23 04:12:16.867982: step: 1760/529, loss: 0.00017056464275810868
2023-01-23 04:12:18.014645: step: 1764/529, loss: 1.4781950994802173e-05
2023-01-23 04:12:19.182604: step: 1768/529, loss: 0.0031566619873046875
2023-01-23 04:12:20.301751: step: 1772/529, loss: 2.3746490114717744e-05
2023-01-23 04:12:21.434730: step: 1776/529, loss: 0.0035467150155454874
2023-01-23 04:12:22.599005: step: 1780/529, loss: 0.005482482723891735
2023-01-23 04:12:23.721379: step: 1784/529, loss: 0.0015802383422851562
2023-01-23 04:12:24.890800: step: 1788/529, loss: 0.05314197763800621
2023-01-23 04:12:26.052169: step: 1792/529, loss: 0.00035266875056549907
2023-01-23 04:12:27.185327: step: 1796/529, loss: 0.0001321792515227571
2023-01-23 04:12:28.304720: step: 1800/529, loss: 0.06937695294618607
2023-01-23 04:12:29.403363: step: 1804/529, loss: 0.0022573471069335938
2023-01-23 04:12:30.553711: step: 1808/529, loss: 0.0017583847511559725
2023-01-23 04:12:31.671314: step: 1812/529, loss: 0.00016269684419967234
2023-01-23 04:12:32.826092: step: 1816/529, loss: 0.0035915374755859375
2023-01-23 04:12:33.955410: step: 1820/529, loss: 0.04482555389404297
2023-01-23 04:12:35.084860: step: 1824/529, loss: 1.2588501704158261e-05
2023-01-23 04:12:36.210656: step: 1828/529, loss: 7.200241270766128e-06
2023-01-23 04:12:37.350580: step: 1832/529, loss: 1.010894811770413e-05
2023-01-23 04:12:38.485088: step: 1836/529, loss: 0.006625365931540728
2023-01-23 04:12:39.607367: step: 1840/529, loss: 0.0014390945434570312
2023-01-23 04:12:40.742819: step: 1844/529, loss: 7.905960228526965e-05
2023-01-23 04:12:41.890518: step: 1848/529, loss: 0.022931288927793503
2023-01-23 04:12:43.044124: step: 1852/529, loss: 6.29425048828125e-05
2023-01-23 04:12:44.181595: step: 1856/529, loss: 4.539489600574598e-05
2023-01-23 04:12:45.324282: step: 1860/529, loss: 0.002043819520622492
2023-01-23 04:12:46.488745: step: 1864/529, loss: 0.020247364416718483
2023-01-23 04:12:47.615258: step: 1868/529, loss: 0.0005067826132290065
2023-01-23 04:12:48.764774: step: 1872/529, loss: 0.0029332160484045744
2023-01-23 04:12:49.886111: step: 1876/529, loss: 0.0002668410597834736
2023-01-23 04:12:51.009654: step: 1880/529, loss: 0.00011348724365234375
2023-01-23 04:12:52.173205: step: 1884/529, loss: 0.01920933648943901
2023-01-23 04:12:53.332463: step: 1888/529, loss: 0.0016807080246508121
2023-01-23 04:12:54.484602: step: 1892/529, loss: 0.00021810531325172633
2023-01-23 04:12:55.645805: step: 1896/529, loss: 0.014886093325912952
2023-01-23 04:12:56.817773: step: 1900/529, loss: 0.01766815222799778
2023-01-23 04:12:57.984042: step: 1904/529, loss: 0.00021224022202659398
2023-01-23 04:12:59.099213: step: 1908/529, loss: 0.011406040750443935
2023-01-23 04:13:00.247489: step: 1912/529, loss: -1.2302398317842744e-05
2023-01-23 04:13:01.385735: step: 1916/529, loss: 0.0007192611810751259
2023-01-23 04:13:02.519197: step: 1920/529, loss: 0.011962317861616611
2023-01-23 04:13:03.660859: step: 1924/529, loss: 0.0008192062377929688
2023-01-23 04:13:04.773064: step: 1928/529, loss: 0.0005619526491500437
2023-01-23 04:13:05.931398: step: 1932/529, loss: 0.0021730423904955387
2023-01-23 04:13:07.090952: step: 1936/529, loss: 0.0028985978569835424
2023-01-23 04:13:08.233550: step: 1940/529, loss: 7.328986976062879e-05
2023-01-23 04:13:09.420703: step: 1944/529, loss: 0.0033998489379882812
2023-01-23 04:13:10.558751: step: 1948/529, loss: 0.0002611160452943295
2023-01-23 04:13:11.718100: step: 1952/529, loss: 0.0026807785034179688
2023-01-23 04:13:12.872434: step: 1956/529, loss: 2.0027162008773303e-06
2023-01-23 04:13:14.010095: step: 1960/529, loss: 5.702972339349799e-05
2023-01-23 04:13:15.158224: step: 1964/529, loss: 0.0003987312666140497
2023-01-23 04:13:16.325888: step: 1968/529, loss: 0.0005405425908975303
2023-01-23 04:13:17.457234: step: 1972/529, loss: 0.056925203651189804
2023-01-23 04:13:18.607754: step: 1976/529, loss: 0.003406715579330921
2023-01-23 04:13:19.736144: step: 1980/529, loss: 7.543563697254285e-05
2023-01-23 04:13:20.848890: step: 1984/529, loss: 0.004996395204216242
2023-01-23 04:13:21.983498: step: 1988/529, loss: 0.005165576934814453
2023-01-23 04:13:23.156783: step: 1992/529, loss: 0.12199898064136505
2023-01-23 04:13:24.258726: step: 1996/529, loss: 0.0004701971774920821
2023-01-23 04:13:25.396190: step: 2000/529, loss: 0.042629048228263855
2023-01-23 04:13:26.522818: step: 2004/529, loss: 0.07139568030834198
2023-01-23 04:13:27.652420: step: 2008/529, loss: 0.0044276234693825245
2023-01-23 04:13:28.812747: step: 2012/529, loss: 0.0021921158768236637
2023-01-23 04:13:29.943206: step: 2016/529, loss: 0.0017807483673095703
2023-01-23 04:13:31.063793: step: 2020/529, loss: 0.013555336743593216
2023-01-23 04:13:32.197950: step: 2024/529, loss: 0.001087188720703125
2023-01-23 04:13:33.347086: step: 2028/529, loss: 0.01615452766418457
2023-01-23 04:13:34.467719: step: 2032/529, loss: 0.0007308006170205772
2023-01-23 04:13:35.576332: step: 2036/529, loss: 0.0006583214271813631
2023-01-23 04:13:36.732232: step: 2040/529, loss: 6.237030174816027e-05
2023-01-23 04:13:37.850274: step: 2044/529, loss: 0.04879894480109215
2023-01-23 04:13:38.967922: step: 2048/529, loss: 2.746581958490424e-05
2023-01-23 04:13:40.113175: step: 2052/529, loss: 0.0022540094796568155
2023-01-23 04:13:41.289149: step: 2056/529, loss: 0.001861619995906949
2023-01-23 04:13:42.414260: step: 2060/529, loss: 0.01276102103292942
2023-01-23 04:13:43.556295: step: 2064/529, loss: 0.00034198761568404734
2023-01-23 04:13:44.688510: step: 2068/529, loss: 6.675720669591101e-07
2023-01-23 04:13:45.803988: step: 2072/529, loss: 0.00024704934912733734
2023-01-23 04:13:46.940113: step: 2076/529, loss: 3.9863589336164296e-05
2023-01-23 04:13:48.062069: step: 2080/529, loss: 0.001080417656339705
2023-01-23 04:13:49.194644: step: 2084/529, loss: 0.02632465399801731
2023-01-23 04:13:50.311294: step: 2088/529, loss: 0.0032678607385605574
2023-01-23 04:13:51.442286: step: 2092/529, loss: 0.017656518146395683
2023-01-23 04:13:52.596039: step: 2096/529, loss: 2.0134873390197754
2023-01-23 04:13:53.724903: step: 2100/529, loss: 0.004620742984116077
2023-01-23 04:13:54.877440: step: 2104/529, loss: 0.0014112471835687757
2023-01-23 04:13:56.017195: step: 2108/529, loss: 3.290176755399443e-05
2023-01-23 04:13:57.157783: step: 2112/529, loss: 0.0011428833240643144
2023-01-23 04:13:58.310531: step: 2116/529, loss: 0.0002211570827057585
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.6096033402922756, 'r': 0.7776298268974701, 'f1': 0.6834406085430076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6149954001839927, 'r': 0.7746234067207416, 'f1': 0.6856410256410257}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.6375, 'r': 0.9444444444444444, 'f1': 0.7611940298507462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.6078431372549019, 'r': 0.49206349206349204, 'f1': 0.543859649122807}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.3953488372093023, 'r': 0.4722222222222222, 'f1': 0.43037974683544306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6096033402922756, 'r': 0.7776298268974701, 'f1': 0.6834406085430076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6149954001839927, 'r': 0.7746234067207416, 'f1': 0.6856410256410257}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6375, 'r': 0.9444444444444444, 'f1': 0.7611940298507462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6123535676251332, 'r': 0.7656458055925432, 'f1': 0.6804733727810652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6227824463118581, 'r': 0.7728852838933952, 'f1': 0.6897621509824199}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.74, 'r': 0.5873015873015873, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 04:14:44.794633: step: 4/529, loss: 0.01877613179385662
2023-01-23 04:14:45.936177: step: 8/529, loss: 0.0045996191911399364
2023-01-23 04:14:47.071187: step: 12/529, loss: 0.024889184162020683
2023-01-23 04:14:48.175326: step: 16/529, loss: 0.0029392242431640625
2023-01-23 04:14:49.346526: step: 20/529, loss: 0.005602359771728516
2023-01-23 04:14:50.511105: step: 24/529, loss: 0.0003555297735147178
2023-01-23 04:14:51.626120: step: 28/529, loss: 0.005156993865966797
2023-01-23 04:14:52.792925: step: 32/529, loss: 0.006790542975068092
2023-01-23 04:14:53.910442: step: 36/529, loss: 0.00028667450533248484
2023-01-23 04:14:55.035863: step: 40/529, loss: 0.010752296075224876
2023-01-23 04:14:56.146671: step: 44/529, loss: 0.0002865791320800781
2023-01-23 04:14:57.296682: step: 48/529, loss: 1.1444091796875e-05
2023-01-23 04:14:58.442143: step: 52/529, loss: 5.1975250244140625e-05
2023-01-23 04:14:59.546226: step: 56/529, loss: 0.002250194549560547
2023-01-23 04:15:00.674032: step: 60/529, loss: 0.014471721835434437
2023-01-23 04:15:01.812902: step: 64/529, loss: 3.533363633323461e-05
2023-01-23 04:15:02.958559: step: 68/529, loss: 0.00017604828462935984
2023-01-23 04:15:04.092893: step: 72/529, loss: 0.0006144524086266756
2023-01-23 04:15:05.206057: step: 76/529, loss: 0.002903461456298828
2023-01-23 04:15:06.342229: step: 80/529, loss: 0.029028989374637604
2023-01-23 04:15:07.467391: step: 84/529, loss: 0.007819557562470436
2023-01-23 04:15:08.601273: step: 88/529, loss: 0.0008594513055868447
2023-01-23 04:15:09.768065: step: 92/529, loss: 0.0024612427223473787
2023-01-23 04:15:10.888427: step: 96/529, loss: 0.0023249625228345394
2023-01-23 04:15:12.000596: step: 100/529, loss: 0.0005080223199911416
2023-01-23 04:15:13.138054: step: 104/529, loss: 0.00034351350041106343
2023-01-23 04:15:14.305585: step: 108/529, loss: 0.009500122629106045
2023-01-23 04:15:15.432536: step: 112/529, loss: 1.621246337890625e-05
2023-01-23 04:15:16.564413: step: 116/529, loss: 0.03311539068818092
2023-01-23 04:15:17.738743: step: 120/529, loss: 3.5715103877009824e-05
2023-01-23 04:15:18.877859: step: 124/529, loss: 0.0008008956792764366
2023-01-23 04:15:20.000886: step: 128/529, loss: 0.03768310323357582
2023-01-23 04:15:21.162091: step: 132/529, loss: 4.310607982915826e-05
2023-01-23 04:15:22.302368: step: 136/529, loss: 0.015679167583584785
2023-01-23 04:15:23.412423: step: 140/529, loss: 0.00017795563326217234
2023-01-23 04:15:24.559644: step: 144/529, loss: 0.00023899078951217234
2023-01-23 04:15:25.687934: step: 148/529, loss: 0.00026454924955032766
2023-01-23 04:15:26.817209: step: 152/529, loss: 0.014461660757660866
2023-01-23 04:15:27.995834: step: 156/529, loss: 0.02699088864028454
2023-01-23 04:15:29.104764: step: 160/529, loss: 0.0017379760975018144
2023-01-23 04:15:30.247148: step: 164/529, loss: 0.006054020021110773
2023-01-23 04:15:31.389400: step: 168/529, loss: 0.023838043212890625
2023-01-23 04:15:32.555702: step: 172/529, loss: 0.0016600609524175525
2023-01-23 04:15:33.676326: step: 176/529, loss: 0.0006956100114621222
2023-01-23 04:15:34.867690: step: 180/529, loss: 0.008653211407363415
2023-01-23 04:15:36.010428: step: 184/529, loss: 0.0007164000999182463
2023-01-23 04:15:37.161163: step: 188/529, loss: 0.021378088742494583
2023-01-23 04:15:38.320602: step: 192/529, loss: 0.009367180988192558
2023-01-23 04:15:39.437010: step: 196/529, loss: 0.004074192140251398
2023-01-23 04:15:40.593759: step: 200/529, loss: 0.05244855582714081
2023-01-23 04:15:41.726707: step: 204/529, loss: 0.0002850055752787739
2023-01-23 04:15:42.882442: step: 208/529, loss: 0.0032117844093590975
2023-01-23 04:15:43.994337: step: 212/529, loss: 0.0041141510009765625
2023-01-23 04:15:45.121579: step: 216/529, loss: 2.7990341550321318e-05
2023-01-23 04:15:46.265166: step: 220/529, loss: 0.01878166012465954
2023-01-23 04:15:47.368108: step: 224/529, loss: 0.0006101608742028475
2023-01-23 04:15:48.495779: step: 228/529, loss: 7.247925168485381e-06
2023-01-23 04:15:49.639905: step: 232/529, loss: 5.273819260764867e-05
2023-01-23 04:15:50.769321: step: 236/529, loss: 0.0005838394281454384
2023-01-23 04:15:51.875370: step: 240/529, loss: 0.007197141647338867
2023-01-23 04:15:52.992888: step: 244/529, loss: 0.03648977354168892
2023-01-23 04:15:54.112446: step: 248/529, loss: -2.0456314814509824e-05
2023-01-23 04:15:55.264958: step: 252/529, loss: 0.008053970523178577
2023-01-23 04:15:56.397215: step: 256/529, loss: 3.814697265625e-05
2023-01-23 04:15:57.542552: step: 260/529, loss: 0.10630855709314346
2023-01-23 04:15:58.704602: step: 264/529, loss: 0.00013952255540061742
2023-01-23 04:15:59.847592: step: 268/529, loss: 0.0020471573807299137
2023-01-23 04:16:00.995827: step: 272/529, loss: 1.52587890625e-05
2023-01-23 04:16:02.135903: step: 276/529, loss: 0.05373058468103409
2023-01-23 04:16:03.301748: step: 280/529, loss: 3.461838059592992e-05
2023-01-23 04:16:04.445631: step: 284/529, loss: 0.009411811828613281
2023-01-23 04:16:05.606703: step: 288/529, loss: 0.0004093170282430947
2023-01-23 04:16:06.729576: step: 292/529, loss: -4.291534423828125e-06
2023-01-23 04:16:07.884179: step: 296/529, loss: 0.010420894250273705
2023-01-23 04:16:09.016020: step: 300/529, loss: 0.0005058288807049394
2023-01-23 04:16:10.146206: step: 304/529, loss: 0.0002392292080912739
2023-01-23 04:16:11.284041: step: 308/529, loss: 0.004777717404067516
2023-01-23 04:16:12.411924: step: 312/529, loss: 4.9114227294921875e-05
2023-01-23 04:16:13.558042: step: 316/529, loss: 0.0011608123313635588
2023-01-23 04:16:14.704047: step: 320/529, loss: 0.0007036208990029991
2023-01-23 04:16:15.848266: step: 324/529, loss: 0.014149094000458717
2023-01-23 04:16:16.951492: step: 328/529, loss: 0.00208702078089118
2023-01-23 04:16:18.092042: step: 332/529, loss: 0.0010094642639160156
2023-01-23 04:16:19.251433: step: 336/529, loss: 0.003392982529476285
2023-01-23 04:16:20.408125: step: 340/529, loss: 0.0889488235116005
2023-01-23 04:16:21.543164: step: 344/529, loss: 0.0003709793381858617
2023-01-23 04:16:22.696332: step: 348/529, loss: 0.00039014816866256297
2023-01-23 04:16:23.860012: step: 352/529, loss: 0.018527794629335403
2023-01-23 04:16:24.996327: step: 356/529, loss: 7.433891732944176e-05
2023-01-23 04:16:26.121803: step: 360/529, loss: 0.0016128539573401213
2023-01-23 04:16:27.242191: step: 364/529, loss: 0.0012690543662756681
2023-01-23 04:16:28.342912: step: 368/529, loss: 0.0034369470085948706
2023-01-23 04:16:29.505062: step: 372/529, loss: 0.019535206258296967
2023-01-23 04:16:30.636456: step: 376/529, loss: 0.0009048461797647178
2023-01-23 04:16:31.769178: step: 380/529, loss: 9.91821252682712e-06
2023-01-23 04:16:32.917879: step: 384/529, loss: 0.12987442314624786
2023-01-23 04:16:34.058026: step: 388/529, loss: 3.886222839355469e-05
2023-01-23 04:16:35.194525: step: 392/529, loss: 0.004604244604706764
2023-01-23 04:16:36.314939: step: 396/529, loss: 0.0010246277088299394
2023-01-23 04:16:37.468523: step: 400/529, loss: 0.009026146493852139
2023-01-23 04:16:38.608825: step: 404/529, loss: 0.002623939421027899
2023-01-23 04:16:39.761227: step: 408/529, loss: 0.0002058029203908518
2023-01-23 04:16:40.894671: step: 412/529, loss: 0.01665782928466797
2023-01-23 04:16:42.013411: step: 416/529, loss: 5.578995114774443e-05
2023-01-23 04:16:43.198013: step: 420/529, loss: 0.0038452150765806437
2023-01-23 04:16:44.380058: step: 424/529, loss: 0.000984668848104775
2023-01-23 04:16:45.520070: step: 428/529, loss: 0.00011081695993198082
2023-01-23 04:16:46.630459: step: 432/529, loss: -1.1777878171415068e-05
2023-01-23 04:16:47.780499: step: 436/529, loss: 0.0004066467226948589
2023-01-23 04:16:48.948963: step: 440/529, loss: 0.029067421332001686
2023-01-23 04:16:50.096259: step: 444/529, loss: 5.119443085277453e-05
2023-01-23 04:16:51.220063: step: 448/529, loss: 4.5776364459015895e-06
2023-01-23 04:16:52.377642: step: 452/529, loss: 0.017982101067900658
2023-01-23 04:16:53.492908: step: 456/529, loss: 0.0021360397804528475
2023-01-23 04:16:54.636474: step: 460/529, loss: 0.04451503977179527
2023-01-23 04:16:55.760114: step: 464/529, loss: 0.03155536949634552
2023-01-23 04:16:56.926124: step: 468/529, loss: 0.025257302448153496
2023-01-23 04:16:58.075889: step: 472/529, loss: 0.0005167007329873741
2023-01-23 04:16:59.184324: step: 476/529, loss: 0.32609355449676514
2023-01-23 04:17:00.315687: step: 480/529, loss: 0.00048446658183820546
2023-01-23 04:17:01.424604: step: 484/529, loss: 0.0002944946463685483
2023-01-23 04:17:02.551203: step: 488/529, loss: 0.00026035308837890625
2023-01-23 04:17:03.703016: step: 492/529, loss: 3.600120544433594e-05
2023-01-23 04:17:04.845914: step: 496/529, loss: 0.0007471084827557206
2023-01-23 04:17:06.008299: step: 500/529, loss: 0.07924485206604004
2023-01-23 04:17:07.158603: step: 504/529, loss: 0.05313320457935333
2023-01-23 04:17:08.285476: step: 508/529, loss: 4.580021050060168e-05
2023-01-23 04:17:09.413516: step: 512/529, loss: 0.0015383244026452303
2023-01-23 04:17:10.568628: step: 516/529, loss: 0.039701513946056366
2023-01-23 04:17:11.699530: step: 520/529, loss: 0.02309436909854412
2023-01-23 04:17:12.835612: step: 524/529, loss: 0.012848759070038795
2023-01-23 04:17:13.971845: step: 528/529, loss: 7.953643944347277e-05
2023-01-23 04:17:15.113219: step: 532/529, loss: 0.00240497593767941
2023-01-23 04:17:16.268506: step: 536/529, loss: 0.04354157671332359
2023-01-23 04:17:17.413856: step: 540/529, loss: 0.024097824469208717
2023-01-23 04:17:18.559967: step: 544/529, loss: 0.11643514782190323
2023-01-23 04:17:19.700977: step: 548/529, loss: 1.354217511106981e-05
2023-01-23 04:17:20.840906: step: 552/529, loss: 0.0005895614740438759
2023-01-23 04:17:21.970553: step: 556/529, loss: 0.0022148131392896175
2023-01-23 04:17:23.085531: step: 560/529, loss: 1.1634827387752011e-05
2023-01-23 04:17:24.212858: step: 564/529, loss: 0.00010156631469726562
2023-01-23 04:17:25.373886: step: 568/529, loss: 0.0015079498989507556
2023-01-23 04:17:26.538933: step: 572/529, loss: 0.027283288538455963
2023-01-23 04:17:27.691227: step: 576/529, loss: 0.004084968473762274
2023-01-23 04:17:28.845057: step: 580/529, loss: 0.0007440135232172906
2023-01-23 04:17:29.988591: step: 584/529, loss: 0.001910400460474193
2023-01-23 04:17:31.094717: step: 588/529, loss: 0.0008209228399209678
2023-01-23 04:17:32.211652: step: 592/529, loss: 0.011160850524902344
2023-01-23 04:17:33.340313: step: 596/529, loss: 2.86102294921875e-05
2023-01-23 04:17:34.509868: step: 600/529, loss: 0.0006711006280966103
2023-01-23 04:17:35.668469: step: 604/529, loss: 0.0004781723255291581
2023-01-23 04:17:36.776936: step: 608/529, loss: 0.02392597310245037
2023-01-23 04:17:37.920041: step: 612/529, loss: 0.004221725277602673
2023-01-23 04:17:39.071317: step: 616/529, loss: 0.006194591522216797
2023-01-23 04:17:40.200920: step: 620/529, loss: 4.243850526108872e-06
2023-01-23 04:17:41.346574: step: 624/529, loss: 0.06521406769752502
2023-01-23 04:17:42.493183: step: 628/529, loss: 0.00603065500035882
2023-01-23 04:17:43.613515: step: 632/529, loss: 0.00013961792865302414
2023-01-23 04:17:44.782113: step: 636/529, loss: 0.007125282660126686
2023-01-23 04:17:45.919161: step: 640/529, loss: 1.811981201171875e-05
2023-01-23 04:17:47.059274: step: 644/529, loss: -5.435942512121983e-06
2023-01-23 04:17:48.160382: step: 648/529, loss: 2.86102294921875e-05
2023-01-23 04:17:49.311643: step: 652/529, loss: 3.261566234868951e-05
2023-01-23 04:17:50.467990: step: 656/529, loss: 3.147125607938506e-05
2023-01-23 04:17:51.603555: step: 660/529, loss: 0.0734824389219284
2023-01-23 04:17:52.754482: step: 664/529, loss: 0.0017293930286541581
2023-01-23 04:17:53.901309: step: 668/529, loss: 0.0008948325994424522
2023-01-23 04:17:55.028183: step: 672/529, loss: 0.0018323898548260331
2023-01-23 04:17:56.160072: step: 676/529, loss: 3.7765505112474784e-05
2023-01-23 04:17:57.321641: step: 680/529, loss: 5.5789947509765625e-05
2023-01-23 04:17:58.451860: step: 684/529, loss: 9.493828110862523e-05
2023-01-23 04:17:59.615637: step: 688/529, loss: 0.0031824109610170126
2023-01-23 04:18:00.751228: step: 692/529, loss: 0.0001234054652741179
2023-01-23 04:18:01.904996: step: 696/529, loss: 0.01739940606057644
2023-01-23 04:18:03.045593: step: 700/529, loss: 5.064010838395916e-05
2023-01-23 04:18:04.178064: step: 704/529, loss: 0.01585989072918892
2023-01-23 04:18:05.330109: step: 708/529, loss: 0.0009117603185586631
2023-01-23 04:18:06.481894: step: 712/529, loss: 0.01773970201611519
2023-01-23 04:18:07.620385: step: 716/529, loss: 0.0016792297828942537
2023-01-23 04:18:08.758213: step: 720/529, loss: 0.002284812740981579
2023-01-23 04:18:09.901535: step: 724/529, loss: 0.0020591735374182463
2023-01-23 04:18:11.044098: step: 728/529, loss: 0.03585081174969673
2023-01-23 04:18:12.156644: step: 732/529, loss: -6.198883056640625e-06
2023-01-23 04:18:13.270294: step: 736/529, loss: 0.03481331095099449
2023-01-23 04:18:14.412863: step: 740/529, loss: 0.3417752981185913
2023-01-23 04:18:15.541116: step: 744/529, loss: 0.00028705596923828125
2023-01-23 04:18:16.683335: step: 748/529, loss: 1.76429750808893e-06
2023-01-23 04:18:17.787391: step: 752/529, loss: 0.00616798410192132
2023-01-23 04:18:18.905612: step: 756/529, loss: 0.028513241559267044
2023-01-23 04:18:20.027056: step: 760/529, loss: 1.1539460501808207e-05
2023-01-23 04:18:21.167901: step: 764/529, loss: 0.004114341922104359
2023-01-23 04:18:22.322198: step: 768/529, loss: 0.008676767349243164
2023-01-23 04:18:23.473636: step: 772/529, loss: 0.0022975921165198088
2023-01-23 04:18:24.630362: step: 776/529, loss: 0.05476045608520508
2023-01-23 04:18:25.784314: step: 780/529, loss: 0.00019664765568450093
2023-01-23 04:18:26.908854: step: 784/529, loss: 1.449584942747606e-05
2023-01-23 04:18:28.059538: step: 788/529, loss: 6.103516352595761e-05
2023-01-23 04:18:29.158970: step: 792/529, loss: 0.00016412737022619694
2023-01-23 04:18:30.330916: step: 796/529, loss: 0.0017936707008630037
2023-01-23 04:18:31.491554: step: 800/529, loss: 0.0012067795032635331
2023-01-23 04:18:32.668100: step: 804/529, loss: 0.00033178331796079874
2023-01-23 04:18:33.765423: step: 808/529, loss: 4.959106809110381e-05
2023-01-23 04:18:34.883802: step: 812/529, loss: 0.0001415252627339214
2023-01-23 04:18:36.033520: step: 816/529, loss: 0.0259381290525198
2023-01-23 04:18:37.181418: step: 820/529, loss: 0.00010719299461925402
2023-01-23 04:18:38.315262: step: 824/529, loss: 0.00014090538024902344
2023-01-23 04:18:39.459147: step: 828/529, loss: 0.03328676521778107
2023-01-23 04:18:40.581655: step: 832/529, loss: 0.0008338928455486894
2023-01-23 04:18:41.730627: step: 836/529, loss: 0.4863090515136719
2023-01-23 04:18:42.886334: step: 840/529, loss: 0.008635140024125576
2023-01-23 04:18:44.017660: step: 844/529, loss: 0.01300191879272461
2023-01-23 04:18:45.149230: step: 848/529, loss: 4.1770937968976796e-05
2023-01-23 04:18:46.265090: step: 852/529, loss: 3.5285952435515355e-06
2023-01-23 04:18:47.405785: step: 856/529, loss: 0.004270744509994984
2023-01-23 04:18:48.551045: step: 860/529, loss: 2.918243444582913e-05
2023-01-23 04:18:49.697650: step: 864/529, loss: 0.00195140833966434
2023-01-23 04:18:50.860181: step: 868/529, loss: 0.00493545550853014
2023-01-23 04:18:51.968296: step: 872/529, loss: 2.5272369384765625e-05
2023-01-23 04:18:53.084360: step: 876/529, loss: 0.0014650345547124743
2023-01-23 04:18:54.214863: step: 880/529, loss: 0.0003293991321697831
2023-01-23 04:18:55.341115: step: 884/529, loss: 0.0555514320731163
2023-01-23 04:18:56.485371: step: 888/529, loss: 8.1062319168268e-07
2023-01-23 04:18:57.606394: step: 892/529, loss: 0.020026778802275658
2023-01-23 04:18:58.757785: step: 896/529, loss: 0.0020479203667491674
2023-01-23 04:18:59.890205: step: 900/529, loss: 0.0001936435728566721
2023-01-23 04:19:01.016821: step: 904/529, loss: 0.10913264006376266
2023-01-23 04:19:02.187698: step: 908/529, loss: 0.0008628845680505037
2023-01-23 04:19:03.301397: step: 912/529, loss: 1.125335711549269e-05
2023-01-23 04:19:04.468396: step: 916/529, loss: 7.371902756858617e-05
2023-01-23 04:19:05.594897: step: 920/529, loss: 0.0010141372913494706
2023-01-23 04:19:06.767126: step: 924/529, loss: 0.0001165389985544607
2023-01-23 04:19:07.912623: step: 928/529, loss: 0.03232503682374954
2023-01-23 04:19:09.081111: step: 932/529, loss: 0.0846710205078125
2023-01-23 04:19:10.213974: step: 936/529, loss: 0.00018634795560501516
2023-01-23 04:19:11.320482: step: 940/529, loss: 5.455017526401207e-05
2023-01-23 04:19:12.485603: step: 944/529, loss: 0.00016307830810546875
2023-01-23 04:19:13.657134: step: 948/529, loss: 0.0007653236389160156
2023-01-23 04:19:14.791852: step: 952/529, loss: 0.0009449005592614412
2023-01-23 04:19:15.912943: step: 956/529, loss: 3.80516066798009e-05
2023-01-23 04:19:17.050883: step: 960/529, loss: 0.000457763671875
2023-01-23 04:19:18.197103: step: 964/529, loss: 5.340575626178179e-06
2023-01-23 04:19:19.344878: step: 968/529, loss: 0.0009399413829669356
2023-01-23 04:19:20.504069: step: 972/529, loss: 1.926422191900201e-05
2023-01-23 04:19:21.627056: step: 976/529, loss: 0.21249523758888245
2023-01-23 04:19:22.752928: step: 980/529, loss: 0.00044312476529739797
2023-01-23 04:19:23.900736: step: 984/529, loss: 0.12654857337474823
2023-01-23 04:19:25.051943: step: 988/529, loss: 0.0014652252430096269
2023-01-23 04:19:26.180887: step: 992/529, loss: 0.0030826570000499487
2023-01-23 04:19:27.328560: step: 996/529, loss: 1.0108947208209429e-05
2023-01-23 04:19:28.468300: step: 1000/529, loss: 0.0001900673087220639
2023-01-23 04:19:29.593361: step: 1004/529, loss: 2.117157055181451e-05
2023-01-23 04:19:30.746133: step: 1008/529, loss: 0.00432434119284153
2023-01-23 04:19:31.899842: step: 1012/529, loss: 0.02536649815738201
2023-01-23 04:19:33.033041: step: 1016/529, loss: 8.583068620282575e-07
2023-01-23 04:19:34.171155: step: 1020/529, loss: 0.007507228758186102
2023-01-23 04:19:35.308259: step: 1024/529, loss: 0.003591442247852683
2023-01-23 04:19:36.433648: step: 1028/529, loss: 0.0001751899835653603
2023-01-23 04:19:37.570006: step: 1032/529, loss: 0.00323486328125
2023-01-23 04:19:38.695278: step: 1036/529, loss: -1.0490416570974048e-06
2023-01-23 04:19:39.795062: step: 1040/529, loss: 8.630753654870205e-06
2023-01-23 04:19:40.935550: step: 1044/529, loss: 7.743835158180445e-05
2023-01-23 04:19:42.075930: step: 1048/529, loss: 0.004591560456901789
2023-01-23 04:19:43.242142: step: 1052/529, loss: -2.365112231927924e-05
2023-01-23 04:19:44.388118: step: 1056/529, loss: 4.348754737293348e-05
2023-01-23 04:19:45.554828: step: 1060/529, loss: 0.0002006530703511089
2023-01-23 04:19:46.745938: step: 1064/529, loss: 0.00022516251192428172
2023-01-23 04:19:47.877936: step: 1068/529, loss: 0.037786293774843216
2023-01-23 04:19:48.987448: step: 1072/529, loss: 0.0012212276924401522
2023-01-23 04:19:50.116878: step: 1076/529, loss: 0.00016450881958007812
2023-01-23 04:19:51.241921: step: 1080/529, loss: 0.0004562377871479839
2023-01-23 04:19:52.439553: step: 1084/529, loss: 7.82012921263231e-06
2023-01-23 04:19:53.577452: step: 1088/529, loss: 3.5095217754133046e-05
2023-01-23 04:19:54.717240: step: 1092/529, loss: 0.017914295196533203
2023-01-23 04:19:55.850847: step: 1096/529, loss: -8.58306884765625e-06
2023-01-23 04:19:56.987066: step: 1100/529, loss: 9.32693510549143e-05
2023-01-23 04:19:58.116989: step: 1104/529, loss: 0.0004447936953511089
2023-01-23 04:19:59.268201: step: 1108/529, loss: 0.00035190582275390625
2023-01-23 04:20:00.423292: step: 1112/529, loss: -1.7499924069852568e-05
2023-01-23 04:20:01.580447: step: 1116/529, loss: -3.814697322468419e-07
2023-01-23 04:20:02.744275: step: 1120/529, loss: 0.00222187046892941
2023-01-23 04:20:03.882772: step: 1124/529, loss: 0.014529800973832607
2023-01-23 04:20:05.024802: step: 1128/529, loss: -9.91821252682712e-06
2023-01-23 04:20:06.138783: step: 1132/529, loss: 1.4972687495173886e-05
2023-01-23 04:20:07.294802: step: 1136/529, loss: 0.01158981304615736
2023-01-23 04:20:08.415101: step: 1140/529, loss: 0.012137985788285732
2023-01-23 04:20:09.581771: step: 1144/529, loss: 0.00037975312443450093
2023-01-23 04:20:10.752277: step: 1148/529, loss: 0.0024137496948242188
2023-01-23 04:20:11.906419: step: 1152/529, loss: 0.00871572457253933
2023-01-23 04:20:13.090478: step: 1156/529, loss: 0.0002229690580861643
2023-01-23 04:20:14.223895: step: 1160/529, loss: 0.0304107666015625
2023-01-23 04:20:15.365585: step: 1164/529, loss: 1.3637542906508315e-05
2023-01-23 04:20:16.496033: step: 1168/529, loss: 5.14984139954322e-06
2023-01-23 04:20:17.655519: step: 1172/529, loss: 8.611679368186742e-05
2023-01-23 04:20:18.802832: step: 1176/529, loss: 1.4591216313419864e-05
2023-01-23 04:20:19.976447: step: 1180/529, loss: 2.6226043701171875e-05
2023-01-23 04:20:21.124841: step: 1184/529, loss: 0.0064296722412109375
2023-01-23 04:20:22.275004: step: 1188/529, loss: 0.009478569030761719
2023-01-23 04:20:23.417798: step: 1192/529, loss: 7.667541649425402e-05
2023-01-23 04:20:24.546696: step: 1196/529, loss: 0.03364238515496254
2023-01-23 04:20:25.730530: step: 1200/529, loss: 4.014969090349041e-05
2023-01-23 04:20:26.881075: step: 1204/529, loss: 0.0008069992181845009
2023-01-23 04:20:28.030563: step: 1208/529, loss: 0.057192422449588776
2023-01-23 04:20:29.155649: step: 1212/529, loss: 0.05859978124499321
2023-01-23 04:20:30.288154: step: 1216/529, loss: 0.0009019851568154991
2023-01-23 04:20:31.419321: step: 1220/529, loss: 0.0013179780216887593
2023-01-23 04:20:32.564384: step: 1224/529, loss: 3.814697265625e-06
2023-01-23 04:20:33.687272: step: 1228/529, loss: 0.01581592671573162
2023-01-23 04:20:34.796761: step: 1232/529, loss: -2.8610230629055877e-07
2023-01-23 04:20:35.951715: step: 1236/529, loss: 0.13412819802761078
2023-01-23 04:20:37.090562: step: 1240/529, loss: 0.016009999439120293
2023-01-23 04:20:38.195147: step: 1244/529, loss: -3.910064697265625e-05
2023-01-23 04:20:39.328340: step: 1248/529, loss: 0.0004861831839662045
2023-01-23 04:20:40.479195: step: 1252/529, loss: 0.00756072998046875
2023-01-23 04:20:41.604886: step: 1256/529, loss: 0.1195463165640831
2023-01-23 04:20:42.738672: step: 1260/529, loss: 0.013532351702451706
2023-01-23 04:20:43.905239: step: 1264/529, loss: 3.814697265625e-06
2023-01-23 04:20:45.040448: step: 1268/529, loss: 0.00022134781465865672
2023-01-23 04:20:46.187215: step: 1272/529, loss: 0.002338123507797718
2023-01-23 04:20:47.327209: step: 1276/529, loss: 0.0007865905645303428
2023-01-23 04:20:48.460995: step: 1280/529, loss: 0.006599903106689453
2023-01-23 04:20:49.585713: step: 1284/529, loss: 0.00030765534029342234
2023-01-23 04:20:50.737187: step: 1288/529, loss: 0.09362554550170898
2023-01-23 04:20:51.874398: step: 1292/529, loss: 0.011049842461943626
2023-01-23 04:20:53.026630: step: 1296/529, loss: 0.003641319228336215
2023-01-23 04:20:54.149443: step: 1300/529, loss: 2.1934511096333154e-06
2023-01-23 04:20:55.294226: step: 1304/529, loss: 0.002183532575145364
2023-01-23 04:20:56.422073: step: 1308/529, loss: 0.00498809851706028
2023-01-23 04:20:57.589969: step: 1312/529, loss: 6.65664701955393e-05
2023-01-23 04:20:58.716011: step: 1316/529, loss: 5.626678557746345e-06
2023-01-23 04:20:59.827229: step: 1320/529, loss: 0.042349621653556824
2023-01-23 04:21:00.968030: step: 1324/529, loss: 0.0400175079703331
2023-01-23 04:21:02.132467: step: 1328/529, loss: 0.0001619339018361643
2023-01-23 04:21:03.305976: step: 1332/529, loss: 0.00034494398278184235
2023-01-23 04:21:04.417096: step: 1336/529, loss: 0.0008558273548260331
2023-01-23 04:21:05.538610: step: 1340/529, loss: 0.00022430421086028218
2023-01-23 04:21:06.671997: step: 1344/529, loss: 7.514953904319555e-05
2023-01-23 04:21:07.809381: step: 1348/529, loss: 0.01218109205365181
2023-01-23 04:21:08.945965: step: 1352/529, loss: 0.003837204072624445
2023-01-23 04:21:10.089134: step: 1356/529, loss: 7.314682443393394e-05
2023-01-23 04:21:11.243903: step: 1360/529, loss: 0.00014553070650435984
2023-01-23 04:21:12.367234: step: 1364/529, loss: 0.0011056900257244706
2023-01-23 04:21:13.548491: step: 1368/529, loss: 0.007794762030243874
2023-01-23 04:21:14.702139: step: 1372/529, loss: 0.033864784985780716
2023-01-23 04:21:15.857314: step: 1376/529, loss: 0.0004436493036337197
2023-01-23 04:21:16.975767: step: 1380/529, loss: 0.0004638671816792339
2023-01-23 04:21:18.125509: step: 1384/529, loss: 0.0018686294788494706
2023-01-23 04:21:19.249927: step: 1388/529, loss: 0.029398633167147636
2023-01-23 04:21:20.365063: step: 1392/529, loss: 3.509521411615424e-05
2023-01-23 04:21:21.476627: step: 1396/529, loss: 0.009296417236328125
2023-01-23 04:21:22.585342: step: 1400/529, loss: 0.00023374556622002274
2023-01-23 04:21:23.736366: step: 1404/529, loss: 0.0009126663790084422
2023-01-23 04:21:24.858471: step: 1408/529, loss: 0.0002902984560932964
2023-01-23 04:21:26.012601: step: 1412/529, loss: 0.0008914947393350303
2023-01-23 04:21:27.149104: step: 1416/529, loss: 0.36139461398124695
2023-01-23 04:21:28.250065: step: 1420/529, loss: 0.00016822815814521164
2023-01-23 04:21:29.393671: step: 1424/529, loss: 0.2363910675048828
2023-01-23 04:21:30.523690: step: 1428/529, loss: 0.000152587890625
2023-01-23 04:21:31.674503: step: 1432/529, loss: 0.01467132568359375
2023-01-23 04:21:32.788652: step: 1436/529, loss: 0.0033197880256921053
2023-01-23 04:21:33.907678: step: 1440/529, loss: 0.0002608299255371094
2023-01-23 04:21:35.057947: step: 1444/529, loss: 0.001408481621183455
2023-01-23 04:21:36.194550: step: 1448/529, loss: 0.0007710456848144531
2023-01-23 04:21:37.336200: step: 1452/529, loss: 0.00029544829158112407
2023-01-23 04:21:38.457651: step: 1456/529, loss: 3.3950807846849784e-05
2023-01-23 04:21:39.598671: step: 1460/529, loss: 6.723403930664062e-05
2023-01-23 04:21:40.749234: step: 1464/529, loss: 1.144409225162235e-06
2023-01-23 04:21:41.880585: step: 1468/529, loss: 0.012156200595200062
2023-01-23 04:21:43.024117: step: 1472/529, loss: 0.0005641937023028731
2023-01-23 04:21:44.170470: step: 1476/529, loss: 4.1675568354548886e-05
2023-01-23 04:21:45.310020: step: 1480/529, loss: 0.00102148053701967
2023-01-23 04:21:46.473154: step: 1484/529, loss: 0.004835319705307484
2023-01-23 04:21:47.590566: step: 1488/529, loss: 0.003568506333976984
2023-01-23 04:21:48.729177: step: 1492/529, loss: 0.04547462239861488
2023-01-23 04:21:49.853031: step: 1496/529, loss: 5.130767749506049e-05
2023-01-23 04:21:50.974891: step: 1500/529, loss: 5.054473876953125e-05
2023-01-23 04:21:52.098175: step: 1504/529, loss: 0.00032062531681731343
2023-01-23 04:21:53.271029: step: 1508/529, loss: 2.7704239982995205e-05
2023-01-23 04:21:54.413776: step: 1512/529, loss: 0.0053046224638819695
2023-01-23 04:21:55.585969: step: 1516/529, loss: 0.00011329651169944555
2023-01-23 04:21:56.718133: step: 1520/529, loss: 0.003033256623893976
2023-01-23 04:21:57.884308: step: 1524/529, loss: 0.002505683805793524
2023-01-23 04:21:59.031530: step: 1528/529, loss: 0.0015397071838378906
2023-01-23 04:22:00.187553: step: 1532/529, loss: 0.04596518352627754
2023-01-23 04:22:01.314693: step: 1536/529, loss: 0.0005479812389239669
2023-01-23 04:22:02.475545: step: 1540/529, loss: 0.0005599975702352822
2023-01-23 04:22:03.607369: step: 1544/529, loss: 0.010690880008041859
2023-01-23 04:22:04.753350: step: 1548/529, loss: 0.00918655376881361
2023-01-23 04:22:05.906770: step: 1552/529, loss: 0.004045295994728804
2023-01-23 04:22:07.065784: step: 1556/529, loss: 0.00359001150354743
2023-01-23 04:22:08.214334: step: 1560/529, loss: 0.00015907287888694555
2023-01-23 04:22:09.343318: step: 1564/529, loss: 0.001544094062410295
2023-01-23 04:22:10.507769: step: 1568/529, loss: 0.0002754211309365928
2023-01-23 04:22:11.642336: step: 1572/529, loss: 0.012155341915786266
2023-01-23 04:22:12.806456: step: 1576/529, loss: 0.008628081530332565
2023-01-23 04:22:13.962092: step: 1580/529, loss: 0.0001415252627339214
2023-01-23 04:22:15.093372: step: 1584/529, loss: 7.057189577608369e-06
2023-01-23 04:22:16.265950: step: 1588/529, loss: 9.117127046920359e-05
2023-01-23 04:22:17.398823: step: 1592/529, loss: 0.0012561797630041838
2023-01-23 04:22:18.549756: step: 1596/529, loss: 0.004355430603027344
2023-01-23 04:22:19.698472: step: 1600/529, loss: 0.014101123437285423
2023-01-23 04:22:20.831699: step: 1604/529, loss: 2.269744800287299e-05
2023-01-23 04:22:21.988397: step: 1608/529, loss: 0.001446199486963451
2023-01-23 04:22:23.131542: step: 1612/529, loss: 0.0010208607418462634
2023-01-23 04:22:24.287497: step: 1616/529, loss: 8.39233416627394e-06
2023-01-23 04:22:25.413247: step: 1620/529, loss: 0.00016055107698775828
2023-01-23 04:22:26.544618: step: 1624/529, loss: 0.00603408832103014
2023-01-23 04:22:27.677103: step: 1628/529, loss: -1.3351441339182202e-06
2023-01-23 04:22:28.828664: step: 1632/529, loss: 0.010101891122758389
2023-01-23 04:22:29.974832: step: 1636/529, loss: 4.8255922592943534e-05
2023-01-23 04:22:31.108685: step: 1640/529, loss: 0.09000034630298615
2023-01-23 04:22:32.247694: step: 1644/529, loss: 1.2683868590102065e-05
2023-01-23 04:22:33.380235: step: 1648/529, loss: 0.020532798022031784
2023-01-23 04:22:34.487058: step: 1652/529, loss: 0.00018777848163153976
2023-01-23 04:22:35.629601: step: 1656/529, loss: 0.018397904932498932
2023-01-23 04:22:36.753689: step: 1660/529, loss: 0.00014038087101653218
2023-01-23 04:22:37.886959: step: 1664/529, loss: 0.00021247864060569555
2023-01-23 04:22:39.070538: step: 1668/529, loss: 4.596710277837701e-05
2023-01-23 04:22:40.236019: step: 1672/529, loss: 0.0013607979053631425
2023-01-23 04:22:41.366767: step: 1676/529, loss: 0.004532814025878906
2023-01-23 04:22:42.506628: step: 1680/529, loss: 0.04919777065515518
2023-01-23 04:22:43.658778: step: 1684/529, loss: 5.950927879894152e-05
2023-01-23 04:22:44.786506: step: 1688/529, loss: 0.005524826236069202
2023-01-23 04:22:45.929386: step: 1692/529, loss: 0.00240249652415514
2023-01-23 04:22:47.065341: step: 1696/529, loss: 0.05209184065461159
2023-01-23 04:22:48.205295: step: 1700/529, loss: 1.0395049685030244e-05
2023-01-23 04:22:49.378312: step: 1704/529, loss: 0.00014963149442337453
2023-01-23 04:22:50.494102: step: 1708/529, loss: 0.005444812588393688
2023-01-23 04:22:51.654944: step: 1712/529, loss: 2.517700158932712e-05
2023-01-23 04:22:52.799891: step: 1716/529, loss: 0.0003444671747274697
2023-01-23 04:22:53.924854: step: 1720/529, loss: 0.0006761550903320312
2023-01-23 04:22:55.073669: step: 1724/529, loss: 0.00900116004049778
2023-01-23 04:22:56.215161: step: 1728/529, loss: 4.291534423828125e-06
2023-01-23 04:22:57.362657: step: 1732/529, loss: 0.01634521596133709
2023-01-23 04:22:58.494215: step: 1736/529, loss: 0.00071125035174191
2023-01-23 04:22:59.668079: step: 1740/529, loss: 0.04398870840668678
2023-01-23 04:23:00.806839: step: 1744/529, loss: 0.030103780329227448
2023-01-23 04:23:01.929793: step: 1748/529, loss: 0.14822901785373688
2023-01-23 04:23:03.048421: step: 1752/529, loss: 5.722046353184851e-06
2023-01-23 04:23:04.214360: step: 1756/529, loss: 0.00106048583984375
2023-01-23 04:23:05.361458: step: 1760/529, loss: 0.0007371903047896922
2023-01-23 04:23:06.486087: step: 1764/529, loss: 0.0029416086617857218
2023-01-23 04:23:07.621659: step: 1768/529, loss: 0.00013074875460006297
2023-01-23 04:23:08.789820: step: 1772/529, loss: 0.0026731491088867188
2023-01-23 04:23:09.936240: step: 1776/529, loss: 4.00543194700731e-06
2023-01-23 04:23:11.067172: step: 1780/529, loss: 0.0009098052978515625
2023-01-23 04:23:12.194143: step: 1784/529, loss: 0.011314011178910732
2023-01-23 04:23:13.304704: step: 1788/529, loss: 0.0007757187122479081
2023-01-23 04:23:14.447619: step: 1792/529, loss: 0.00011749268014682457
2023-01-23 04:23:15.578635: step: 1796/529, loss: 0.0004980087396688759
2023-01-23 04:23:16.713552: step: 1800/529, loss: 0.00014314652071334422
2023-01-23 04:23:17.870548: step: 1804/529, loss: 2.250671423098538e-05
2023-01-23 04:23:19.017116: step: 1808/529, loss: 7.047652616165578e-05
2023-01-23 04:23:20.172627: step: 1812/529, loss: 0.0013103485107421875
2023-01-23 04:23:21.294761: step: 1816/529, loss: 1.773834264895413e-05
2023-01-23 04:23:22.423556: step: 1820/529, loss: -3.7670135952794226e-06
2023-01-23 04:23:23.577868: step: 1824/529, loss: 0.08901538699865341
2023-01-23 04:23:24.707336: step: 1828/529, loss: 0.00022029878164175898
2023-01-23 04:23:25.859056: step: 1832/529, loss: 0.00161914830096066
2023-01-23 04:23:27.022988: step: 1836/529, loss: 7.648468454135582e-05
2023-01-23 04:23:28.166803: step: 1840/529, loss: 0.024843288585543633
2023-01-23 04:23:29.329440: step: 1844/529, loss: 3.2997133530443534e-05
2023-01-23 04:23:30.453166: step: 1848/529, loss: 0.0012079238658770919
2023-01-23 04:23:31.574211: step: 1852/529, loss: 0.00011940002150367945
2023-01-23 04:23:32.732172: step: 1856/529, loss: 0.0010656357044354081
2023-01-23 04:23:33.904823: step: 1860/529, loss: 1.3949804306030273
2023-01-23 04:23:35.042392: step: 1864/529, loss: 0.000669288681820035
2023-01-23 04:23:36.214584: step: 1868/529, loss: 0.0031375885009765625
2023-01-23 04:23:37.352787: step: 1872/529, loss: 0.031613539904356
2023-01-23 04:23:38.486401: step: 1876/529, loss: 3.623962356869015e-06
2023-01-23 04:23:39.613905: step: 1880/529, loss: 0.0003383636649232358
2023-01-23 04:23:40.731622: step: 1884/529, loss: 0.00025238993111997843
2023-01-23 04:23:41.877749: step: 1888/529, loss: 0.0007088661659508944
2023-01-23 04:23:43.014605: step: 1892/529, loss: 0.0006690025329589844
2023-01-23 04:23:44.174895: step: 1896/529, loss: 0.0005206108326092362
2023-01-23 04:23:45.293315: step: 1900/529, loss: 5.064010474598035e-05
2023-01-23 04:23:46.416187: step: 1904/529, loss: 1.0165572348341811e-05
2023-01-23 04:23:47.571059: step: 1908/529, loss: 0.0011874199844896793
2023-01-23 04:23:48.708554: step: 1912/529, loss: 0.0009941102471202612
2023-01-23 04:23:49.853076: step: 1916/529, loss: 0.00010929107520496473
2023-01-23 04:23:50.988471: step: 1920/529, loss: 0.00044016839819960296
2023-01-23 04:23:52.143015: step: 1924/529, loss: 0.0017185211181640625
2023-01-23 04:23:53.282522: step: 1928/529, loss: 0.0020595071837306023
2023-01-23 04:23:54.429859: step: 1932/529, loss: 3.728866431629285e-05
2023-01-23 04:23:55.567212: step: 1936/529, loss: 1.8453598386258818e-05
2023-01-23 04:23:56.702858: step: 1940/529, loss: 0.0010535240871831775
2023-01-23 04:23:57.830145: step: 1944/529, loss: 0.011309958063066006
2023-01-23 04:23:58.954630: step: 1948/529, loss: 0.004026985261589289
2023-01-23 04:24:00.115405: step: 1952/529, loss: 0.00011882782564498484
2023-01-23 04:24:01.295413: step: 1956/529, loss: 6.31332368357107e-05
2023-01-23 04:24:02.442392: step: 1960/529, loss: 8.0108642578125e-05
2023-01-23 04:24:03.576259: step: 1964/529, loss: 0.001093912054784596
2023-01-23 04:24:04.714542: step: 1968/529, loss: 0.14452219009399414
2023-01-23 04:24:05.866285: step: 1972/529, loss: 0.02083406411111355
2023-01-23 04:24:07.025216: step: 1976/529, loss: 0.016637230291962624
2023-01-23 04:24:08.160039: step: 1980/529, loss: 0.032593440264463425
2023-01-23 04:24:09.305312: step: 1984/529, loss: 0.0014526366721838713
2023-01-23 04:24:10.443607: step: 1988/529, loss: 0.009725459851324558
2023-01-23 04:24:11.597043: step: 1992/529, loss: 0.00320606236346066
2023-01-23 04:24:12.724307: step: 1996/529, loss: 0.010757159441709518
2023-01-23 04:24:13.910441: step: 2000/529, loss: 0.03268565982580185
2023-01-23 04:24:15.057499: step: 2004/529, loss: 0.0001977920619538054
2023-01-23 04:24:16.199722: step: 2008/529, loss: 0.04256686940789223
2023-01-23 04:24:17.352972: step: 2012/529, loss: 0.039610959589481354
2023-01-23 04:24:18.474200: step: 2016/529, loss: 0.003604888916015625
2023-01-23 04:24:19.632962: step: 2020/529, loss: 1.621246337890625e-05
2023-01-23 04:24:20.800493: step: 2024/529, loss: 0.0339779369533062
2023-01-23 04:24:21.961469: step: 2028/529, loss: 7.390976679744199e-05
2023-01-23 04:24:23.095734: step: 2032/529, loss: 0.010361862368881702
2023-01-23 04:24:24.224917: step: 2036/529, loss: 0.11191482841968536
2023-01-23 04:24:25.325164: step: 2040/529, loss: 0.00010452271089889109
2023-01-23 04:24:26.459392: step: 2044/529, loss: 0.013841485604643822
2023-01-23 04:24:27.593362: step: 2048/529, loss: 0.0001349449303233996
2023-01-23 04:24:28.744252: step: 2052/529, loss: 0.0004261970752850175
2023-01-23 04:24:29.867165: step: 2056/529, loss: 0.06896381080150604
2023-01-23 04:24:31.022803: step: 2060/529, loss: 5.0926206313306466e-05
2023-01-23 04:24:32.161375: step: 2064/529, loss: 0.0013132095336914062
2023-01-23 04:24:33.276897: step: 2068/529, loss: 6.29425048828125e-05
2023-01-23 04:24:34.413116: step: 2072/529, loss: 0.012125778011977673
2023-01-23 04:24:35.559720: step: 2076/529, loss: 0.012499809265136719
2023-01-23 04:24:36.712650: step: 2080/529, loss: 0.00036907196044921875
2023-01-23 04:24:37.889545: step: 2084/529, loss: 0.00013608932204078883
2023-01-23 04:24:39.023109: step: 2088/529, loss: 0.03581704944372177
2023-01-23 04:24:40.172468: step: 2092/529, loss: 0.018338393419981003
2023-01-23 04:24:41.302708: step: 2096/529, loss: 0.00014157296391204
2023-01-23 04:24:42.434218: step: 2100/529, loss: 0.0076236724853515625
2023-01-23 04:24:43.577866: step: 2104/529, loss: 8.0108642578125e-05
2023-01-23 04:24:44.704266: step: 2108/529, loss: 0.00025405886117368937
2023-01-23 04:24:45.810421: step: 2112/529, loss: 2.47955313170678e-06
2023-01-23 04:24:46.939747: step: 2116/529, loss: 0.00010061264038085938
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.6104944500504541, 'r': 0.8055925432756325, 'f1': 0.6946039035591274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.61996336996337, 'r': 0.7844727694090382, 'f1': 0.6925831202046036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
Russian: {'event': {'p': 0.45652173913043476, 'r': 0.5833333333333334, 'f1': 0.5121951219512195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6096033402922756, 'r': 0.7776298268974701, 'f1': 0.6834406085430076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6149954001839927, 'r': 0.7746234067207416, 'f1': 0.6856410256410257}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6375, 'r': 0.9444444444444444, 'f1': 0.7611940298507462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6104944500504541, 'r': 0.8055925432756325, 'f1': 0.6946039035591274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Korean: {'event': {'p': 0.61996336996337, 'r': 0.7844727694090382, 'f1': 0.6925831202046036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 04:25:34.641517: step: 4/529, loss: 0.0021514892578125
2023-01-23 04:25:35.786562: step: 8/529, loss: 0.009921645745635033
2023-01-23 04:25:36.929989: step: 12/529, loss: 0.00017242431931663305
2023-01-23 04:25:38.037432: step: 16/529, loss: 0.0006539822206832469
2023-01-23 04:25:39.139686: step: 20/529, loss: 0.005362081807106733
2023-01-23 04:25:40.298255: step: 24/529, loss: -4.76837158203125e-06
2023-01-23 04:25:41.407751: step: 28/529, loss: 4.1961669921875e-05
2023-01-23 04:25:42.540526: step: 32/529, loss: 0.00027360915555618703
2023-01-23 04:25:43.700418: step: 36/529, loss: 0.0034100532066076994
2023-01-23 04:25:44.828107: step: 40/529, loss: 8.964539119915571e-06
2023-01-23 04:25:45.950994: step: 44/529, loss: 0.0014062882401049137
2023-01-23 04:25:47.132927: step: 48/529, loss: 6.67572021484375e-06
2023-01-23 04:25:48.279676: step: 52/529, loss: 3.547668529790826e-05
2023-01-23 04:25:49.412856: step: 56/529, loss: 0.01944456249475479
2023-01-23 04:25:50.536166: step: 60/529, loss: 0.6814148426055908
2023-01-23 04:25:51.668305: step: 64/529, loss: 0.00012073517427779734
2023-01-23 04:25:52.811274: step: 68/529, loss: 0.0006240844959393144
2023-01-23 04:25:53.949530: step: 72/529, loss: 0.0010915755992755294
2023-01-23 04:25:55.053725: step: 76/529, loss: 0.003563118167221546
2023-01-23 04:25:56.183021: step: 80/529, loss: 6.0844424297101796e-05
2023-01-23 04:25:57.320905: step: 84/529, loss: 4.472732689464465e-05
2023-01-23 04:25:58.457222: step: 88/529, loss: 5.34057608092553e-06
2023-01-23 04:25:59.606356: step: 92/529, loss: 0.0015334129566326737
2023-01-23 04:26:00.777455: step: 96/529, loss: 0.07135754078626633
2023-01-23 04:26:01.892595: step: 100/529, loss: 8.96453821042087e-06
2023-01-23 04:26:03.051532: step: 104/529, loss: 1.8501283193472773e-05
2023-01-23 04:26:04.184387: step: 108/529, loss: 0.00018301009549759328
2023-01-23 04:26:05.321612: step: 112/529, loss: 1.33514404296875e-05
2023-01-23 04:26:06.496535: step: 116/529, loss: 4.138946678722277e-05
2023-01-23 04:26:07.673207: step: 120/529, loss: 0.003964233677834272
2023-01-23 04:26:08.816466: step: 124/529, loss: 0.0011302947532385588
2023-01-23 04:26:09.961999: step: 128/529, loss: 0.0023619653657078743
2023-01-23 04:26:11.088900: step: 132/529, loss: 0.0006250381702557206
2023-01-23 04:26:12.225766: step: 136/529, loss: -1.0776519957289565e-05
2023-01-23 04:26:13.414282: step: 140/529, loss: 0.0015142441261559725
2023-01-23 04:26:14.533073: step: 144/529, loss: 0.00010986327833961695
2023-01-23 04:26:15.696380: step: 148/529, loss: 0.0003440856817178428
2023-01-23 04:26:16.809546: step: 152/529, loss: 4.186630030744709e-05
2023-01-23 04:26:17.930661: step: 156/529, loss: 0.006328677758574486
2023-01-23 04:26:19.084709: step: 160/529, loss: 0.00047912599984556437
2023-01-23 04:26:20.233507: step: 164/529, loss: 3.0517578125e-05
2023-01-23 04:26:21.364026: step: 168/529, loss: 0.20622768998146057
2023-01-23 04:26:22.515007: step: 172/529, loss: 0.0017513275379315019
2023-01-23 04:26:23.686688: step: 176/529, loss: 3.0946732294978574e-05
2023-01-23 04:26:24.844325: step: 180/529, loss: 0.0010950089199468493
2023-01-23 04:26:25.995791: step: 184/529, loss: 0.009531163610517979
2023-01-23 04:26:27.131969: step: 188/529, loss: 9.822845458984375e-05
2023-01-23 04:26:28.282477: step: 192/529, loss: 0.0005132675287313759
2023-01-23 04:26:29.413192: step: 196/529, loss: 3.4809112548828125e-05
2023-01-23 04:26:30.546658: step: 200/529, loss: 0.024631166830658913
2023-01-23 04:26:31.687775: step: 204/529, loss: 0.0006175994640216231
2023-01-23 04:26:32.863184: step: 208/529, loss: 0.0007814407581463456
2023-01-23 04:26:33.997478: step: 212/529, loss: 0.013393021188676357
2023-01-23 04:26:35.118879: step: 216/529, loss: 0.0008969306945800781
2023-01-23 04:26:36.276236: step: 220/529, loss: 8.106231689453125e-05
2023-01-23 04:26:37.429222: step: 224/529, loss: 0.000736236572265625
2023-01-23 04:26:38.561886: step: 228/529, loss: 9.04560147318989e-05
2023-01-23 04:26:39.677839: step: 232/529, loss: 0.003286171006038785
2023-01-23 04:26:40.817254: step: 236/529, loss: 0.0001070022553903982
2023-01-23 04:26:41.945834: step: 240/529, loss: 0.0008007049327716231
2023-01-23 04:26:43.105679: step: 244/529, loss: 0.00014510155597236007
2023-01-23 04:26:44.225446: step: 248/529, loss: 0.0048881531693041325
2023-01-23 04:26:45.374423: step: 252/529, loss: 0.014361190609633923
2023-01-23 04:26:46.514935: step: 256/529, loss: 1.125335711549269e-05
2023-01-23 04:26:47.681410: step: 260/529, loss: 0.568461000919342
2023-01-23 04:26:48.810498: step: 264/529, loss: 1.3160706657799892e-05
2023-01-23 04:26:49.952577: step: 268/529, loss: 0.0057701109908521175
2023-01-23 04:26:51.086210: step: 272/529, loss: 9.250640869140625e-05
2023-01-23 04:26:52.217645: step: 276/529, loss: 0.0020244598854333162
2023-01-23 04:26:53.394492: step: 280/529, loss: 0.012895154766738415
2023-01-23 04:26:54.528352: step: 284/529, loss: 0.03386859968304634
2023-01-23 04:26:55.656213: step: 288/529, loss: 0.01651744917035103
2023-01-23 04:26:56.782245: step: 292/529, loss: 0.04547891393303871
2023-01-23 04:26:57.917465: step: 296/529, loss: 4.215240551275201e-05
2023-01-23 04:26:59.058737: step: 300/529, loss: 0.010183095932006836
2023-01-23 04:27:00.213349: step: 304/529, loss: 0.001212692353874445
2023-01-23 04:27:01.357304: step: 308/529, loss: 0.032172299921512604
2023-01-23 04:27:02.501704: step: 312/529, loss: 0.0002727508544921875
2023-01-23 04:27:03.652116: step: 316/529, loss: 0.07113972306251526
2023-01-23 04:27:04.844685: step: 320/529, loss: 0.00016460419283248484
2023-01-23 04:27:05.993583: step: 324/529, loss: 0.005909538362175226
2023-01-23 04:27:07.110608: step: 328/529, loss: 0.2711924612522125
2023-01-23 04:27:08.234623: step: 332/529, loss: 3.8337704609148204e-05
2023-01-23 04:27:09.416058: step: 336/529, loss: 0.004338264465332031
2023-01-23 04:27:10.563583: step: 340/529, loss: -4.00543194700731e-06
2023-01-23 04:27:11.691005: step: 344/529, loss: -3.14712519866589e-06
2023-01-23 04:27:12.801898: step: 348/529, loss: 0.007489395327866077
2023-01-23 04:27:13.919064: step: 352/529, loss: -1.5258789289873675e-06
2023-01-23 04:27:15.021266: step: 356/529, loss: 0.0009853363735601306
2023-01-23 04:27:16.161048: step: 360/529, loss: 0.0005168914794921875
2023-01-23 04:27:17.291311: step: 364/529, loss: 0.009820557199418545
2023-01-23 04:27:18.429480: step: 368/529, loss: 0.005489349365234375
2023-01-23 04:27:19.577803: step: 372/529, loss: 0.002441024873405695
2023-01-23 04:27:20.692810: step: 376/529, loss: 0.0020363808143883944
2023-01-23 04:27:21.872800: step: 380/529, loss: 0.00018877982802223414
2023-01-23 04:27:22.999669: step: 384/529, loss: 0.0001125335693359375
2023-01-23 04:27:24.155343: step: 388/529, loss: 0.0017709732055664062
2023-01-23 04:27:25.287464: step: 392/529, loss: 0.000159788120072335
2023-01-23 04:27:26.407229: step: 396/529, loss: 0.0001983642578125
2023-01-23 04:27:27.525428: step: 400/529, loss: 1.9464597702026367
2023-01-23 04:27:28.661491: step: 404/529, loss: 0.0001008987455861643
2023-01-23 04:27:29.784181: step: 408/529, loss: -8.20159948489163e-06
2023-01-23 04:27:30.900202: step: 412/529, loss: 0.0005866051069460809
2023-01-23 04:27:32.008180: step: 416/529, loss: 0.005843830294907093
2023-01-23 04:27:33.173770: step: 420/529, loss: 0.017465878278017044
2023-01-23 04:27:34.300953: step: 424/529, loss: 2.250671423098538e-05
2023-01-23 04:27:35.438956: step: 428/529, loss: 0.0001617431698832661
2023-01-23 04:27:36.552403: step: 432/529, loss: 3.43322744811303e-06
2023-01-23 04:27:37.665213: step: 436/529, loss: 0.0490659698843956
2023-01-23 04:27:38.822879: step: 440/529, loss: 4.000663830083795e-05
2023-01-23 04:27:39.951075: step: 444/529, loss: 0.015586186200380325
2023-01-23 04:27:41.074889: step: 448/529, loss: 0.004702854435890913
2023-01-23 04:27:42.243701: step: 452/529, loss: 0.0007944107055664062
2023-01-23 04:27:43.392715: step: 456/529, loss: 0.00414962787181139
2023-01-23 04:27:44.591850: step: 460/529, loss: 0.0032614709343761206
2023-01-23 04:27:45.718161: step: 464/529, loss: 0.007906246930360794
2023-01-23 04:27:46.858365: step: 468/529, loss: 0.0007512092124670744
2023-01-23 04:27:47.959304: step: 472/529, loss: 0.0030537606216967106
2023-01-23 04:27:49.102403: step: 476/529, loss: 0.008762264624238014
2023-01-23 04:27:50.241731: step: 480/529, loss: 0.0009031295776367188
2023-01-23 04:27:51.374269: step: 484/529, loss: 0.0018049241043627262
2023-01-23 04:27:52.524265: step: 488/529, loss: 0.020003559067845345
2023-01-23 04:27:53.652574: step: 492/529, loss: 0.02207164652645588
2023-01-23 04:27:54.834444: step: 496/529, loss: 0.00011959076073253527
2023-01-23 04:27:55.979626: step: 500/529, loss: 5.14984139954322e-06
2023-01-23 04:27:57.092316: step: 504/529, loss: 0.06974411010742188
2023-01-23 04:27:58.233151: step: 508/529, loss: 0.004493141081184149
2023-01-23 04:27:59.371447: step: 512/529, loss: 0.00010161400132346898
2023-01-23 04:28:00.531098: step: 516/529, loss: 0.005316448397934437
2023-01-23 04:28:01.656784: step: 520/529, loss: 2.0313262211857364e-05
2023-01-23 04:28:02.803037: step: 524/529, loss: 1.392364538332913e-05
2023-01-23 04:28:03.959962: step: 528/529, loss: 4.100799742445815e-06
2023-01-23 04:28:05.123458: step: 532/529, loss: 0.018885230645537376
2023-01-23 04:28:06.261007: step: 536/529, loss: 0.0001813888520700857
2023-01-23 04:28:07.394313: step: 540/529, loss: 0.00017070770263671875
2023-01-23 04:28:08.541460: step: 544/529, loss: 0.0009386062738485634
2023-01-23 04:28:09.673032: step: 548/529, loss: 0.00023727417283225805
2023-01-23 04:28:10.825216: step: 552/529, loss: 0.0032910346053540707
2023-01-23 04:28:11.968107: step: 556/529, loss: 0.06110534816980362
2023-01-23 04:28:13.136563: step: 560/529, loss: 0.0006925583002157509
2023-01-23 04:28:14.268261: step: 564/529, loss: 3.910064606316155e-06
2023-01-23 04:28:15.412613: step: 568/529, loss: 0.004631233401596546
2023-01-23 04:28:16.560954: step: 572/529, loss: 0.018642233684659004
2023-01-23 04:28:17.709142: step: 576/529, loss: 7.62939453125e-05
2023-01-23 04:28:18.826550: step: 580/529, loss: 0.00036258698673918843
2023-01-23 04:28:19.982530: step: 584/529, loss: 0.00038814544677734375
2023-01-23 04:28:21.168755: step: 588/529, loss: 0.00036115647526457906
2023-01-23 04:28:22.331704: step: 592/529, loss: 0.0002307891845703125
2023-01-23 04:28:23.478467: step: 596/529, loss: 0.004060172941535711
2023-01-23 04:28:24.614049: step: 600/529, loss: 0.5602739453315735
2023-01-23 04:28:25.745406: step: 604/529, loss: -3.52859501617786e-06
2023-01-23 04:28:26.909763: step: 608/529, loss: 0.0010477066971361637
2023-01-23 04:28:28.042253: step: 612/529, loss: 0.0002510070917196572
2023-01-23 04:28:29.178535: step: 616/529, loss: 0.005847168155014515
2023-01-23 04:28:30.312696: step: 620/529, loss: 3.814697265625e-06
2023-01-23 04:28:31.454066: step: 624/529, loss: 0.00115623464807868
2023-01-23 04:28:32.587786: step: 628/529, loss: 0.0001163482666015625
2023-01-23 04:28:33.733334: step: 632/529, loss: 0.0206132885068655
2023-01-23 04:28:34.854720: step: 636/529, loss: 5.092620995128527e-05
2023-01-23 04:28:36.020164: step: 640/529, loss: 0.006295967381447554
2023-01-23 04:28:37.191646: step: 644/529, loss: 0.00027112962561659515
2023-01-23 04:28:38.348840: step: 648/529, loss: 0.0006616592290811241
2023-01-23 04:28:39.478029: step: 652/529, loss: 0.030700301751494408
2023-01-23 04:28:40.643645: step: 656/529, loss: 0.0003421783621888608
2023-01-23 04:28:41.780739: step: 660/529, loss: -3.2901763916015625e-05
2023-01-23 04:28:42.941790: step: 664/529, loss: 0.0029228210914880037
2023-01-23 04:28:44.122170: step: 668/529, loss: 0.015261746011674404
2023-01-23 04:28:45.251481: step: 672/529, loss: 7.62939453125e-05
2023-01-23 04:28:46.395072: step: 676/529, loss: 0.04491777718067169
2023-01-23 04:28:47.543457: step: 680/529, loss: 0.0007167339790612459
2023-01-23 04:28:48.683138: step: 684/529, loss: 4.6157834731275216e-05
2023-01-23 04:28:49.817099: step: 688/529, loss: 9.331703768111765e-05
2023-01-23 04:28:50.962270: step: 692/529, loss: 0.0006875991821289062
2023-01-23 04:28:52.134892: step: 696/529, loss: 0.0033746720291674137
2023-01-23 04:28:53.292207: step: 700/529, loss: 0.00663800211623311
2023-01-23 04:28:54.393490: step: 704/529, loss: 0.0011798858176916838
2023-01-23 04:28:55.524057: step: 708/529, loss: 0.008669758215546608
2023-01-23 04:28:56.694407: step: 712/529, loss: 0.0008595467079430819
2023-01-23 04:28:57.846988: step: 716/529, loss: 0.05906028673052788
2023-01-23 04:28:58.982190: step: 720/529, loss: 1.5354156857938506e-05
2023-01-23 04:29:00.138257: step: 724/529, loss: 0.06484727561473846
2023-01-23 04:29:01.265711: step: 728/529, loss: 0.0010814666748046875
2023-01-23 04:29:02.395206: step: 732/529, loss: 7.433891005348414e-05
2023-01-23 04:29:03.527371: step: 736/529, loss: 0.005944633856415749
2023-01-23 04:29:04.690091: step: 740/529, loss: 0.0698789581656456
2023-01-23 04:29:05.825229: step: 744/529, loss: 5.779266211902723e-05
2023-01-23 04:29:06.944197: step: 748/529, loss: 2.1934511096333154e-06
2023-01-23 04:29:08.085578: step: 752/529, loss: 0.008106708526611328
2023-01-23 04:29:09.226934: step: 756/529, loss: 0.006346511654555798
2023-01-23 04:29:10.361438: step: 760/529, loss: 0.0013070106506347656
2023-01-23 04:29:11.502771: step: 764/529, loss: 0.0001321792515227571
2023-01-23 04:29:12.662635: step: 768/529, loss: 0.03649485111236572
2023-01-23 04:29:13.787848: step: 772/529, loss: 3.623962356869015e-06
2023-01-23 04:29:14.957772: step: 776/529, loss: 0.006076431833207607
2023-01-23 04:29:16.124829: step: 780/529, loss: 0.00015039443678688258
2023-01-23 04:29:17.291029: step: 784/529, loss: 2.708435022213962e-05
2023-01-23 04:29:18.434621: step: 788/529, loss: 0.00036296845064498484
2023-01-23 04:29:19.572331: step: 792/529, loss: 1.1207162970094942e-05
2023-01-23 04:29:20.669093: step: 796/529, loss: 0.01554346177726984
2023-01-23 04:29:21.797704: step: 800/529, loss: 0.0014945983421057463
2023-01-23 04:29:22.963134: step: 804/529, loss: 1.1920928955078125e-05
2023-01-23 04:29:24.121368: step: 808/529, loss: 0.0004927635309286416
2023-01-23 04:29:25.268826: step: 812/529, loss: 0.012382506392896175
2023-01-23 04:29:26.379631: step: 816/529, loss: 4.863739377469756e-06
2023-01-23 04:29:27.533731: step: 820/529, loss: 0.0037783621810376644
2023-01-23 04:29:28.674220: step: 824/529, loss: 0.0007633209461346269
2023-01-23 04:29:29.813933: step: 828/529, loss: 0.00011577607074286789
2023-01-23 04:29:30.953711: step: 832/529, loss: 0.027956390753388405
2023-01-23 04:29:32.075347: step: 836/529, loss: 0.010231208987534046
2023-01-23 04:29:33.217849: step: 840/529, loss: 0.0005560875288210809
2023-01-23 04:29:34.358142: step: 844/529, loss: 0.014875221066176891
2023-01-23 04:29:35.516547: step: 848/529, loss: 0.02590932883322239
2023-01-23 04:29:36.648838: step: 852/529, loss: 0.02759408950805664
2023-01-23 04:29:37.786410: step: 856/529, loss: 0.0012287141289561987
2023-01-23 04:29:38.934830: step: 860/529, loss: 0.0002777099725790322
2023-01-23 04:29:40.060535: step: 864/529, loss: 0.002498817630112171
2023-01-23 04:29:41.212771: step: 868/529, loss: 0.006489372346550226
2023-01-23 04:29:42.383883: step: 872/529, loss: 0.0006650924915447831
2023-01-23 04:29:43.556525: step: 876/529, loss: 0.015350342728197575
2023-01-23 04:29:44.699362: step: 880/529, loss: 0.0015981674659997225
2023-01-23 04:29:45.825801: step: 884/529, loss: 0.0019067764515057206
2023-01-23 04:29:46.982711: step: 888/529, loss: 0.0013967513805255294
2023-01-23 04:29:48.113392: step: 892/529, loss: 0.00019989012798760086
2023-01-23 04:29:49.251208: step: 896/529, loss: 0.001756954239681363
2023-01-23 04:29:50.374000: step: 900/529, loss: 6.179809861350805e-05
2023-01-23 04:29:51.525930: step: 904/529, loss: 0.0001277923583984375
2023-01-23 04:29:52.671815: step: 908/529, loss: 1.52587890625e-05
2023-01-23 04:29:53.803858: step: 912/529, loss: 0.003928565885871649
2023-01-23 04:29:54.964152: step: 916/529, loss: 7.629394644936838e-07
2023-01-23 04:29:56.093923: step: 920/529, loss: 0.017749978229403496
2023-01-23 04:29:57.215749: step: 924/529, loss: 2.3698807126493193e-05
2023-01-23 04:29:58.371817: step: 928/529, loss: 0.0006034850957803428
2023-01-23 04:29:59.534137: step: 932/529, loss: 0.019618988037109375
2023-01-23 04:30:00.686250: step: 936/529, loss: 0.029285335913300514
2023-01-23 04:30:01.828413: step: 940/529, loss: 0.0013185502029955387
2023-01-23 04:30:02.998358: step: 944/529, loss: 0.0022099497728049755
2023-01-23 04:30:04.148049: step: 948/529, loss: 2.8753280275850557e-05
2023-01-23 04:30:05.259446: step: 952/529, loss: 4.682540748035535e-05
2023-01-23 04:30:06.374198: step: 956/529, loss: 0.02216968685388565
2023-01-23 04:30:07.533218: step: 960/529, loss: 0.013094902038574219
2023-01-23 04:30:08.685567: step: 964/529, loss: 0.0041100503876805305
2023-01-23 04:30:09.824839: step: 968/529, loss: 0.0008859634399414062
2023-01-23 04:30:10.945499: step: 972/529, loss: 0.0006857395055703819
2023-01-23 04:30:12.098388: step: 976/529, loss: 0.0002868652227334678
2023-01-23 04:30:13.229903: step: 980/529, loss: 0.0003831863577943295
2023-01-23 04:30:14.391246: step: 984/529, loss: 0.0009023667080327868
2023-01-23 04:30:15.502618: step: 988/529, loss: 0.00024120807938743383
2023-01-23 04:30:16.645713: step: 992/529, loss: 0.0002884388086386025
2023-01-23 04:30:17.752090: step: 996/529, loss: 1.2254715329618193e-05
2023-01-23 04:30:18.897885: step: 1000/529, loss: 1.2683868590102065e-05
2023-01-23 04:30:20.039918: step: 1004/529, loss: 0.0004634857177734375
2023-01-23 04:30:21.169921: step: 1008/529, loss: 0.025662995874881744
2023-01-23 04:30:22.341115: step: 1012/529, loss: 0.008013153448700905
2023-01-23 04:30:23.487234: step: 1016/529, loss: 0.0005756377940997481
2023-01-23 04:30:24.617278: step: 1020/529, loss: 2.4890900022001006e-05
2023-01-23 04:30:25.740610: step: 1024/529, loss: 0.0002533912775106728
2023-01-23 04:30:26.862130: step: 1028/529, loss: 0.00010900497727561742
2023-01-23 04:30:27.977033: step: 1032/529, loss: 0.041082192212343216
2023-01-23 04:30:29.152675: step: 1036/529, loss: 0.1614711731672287
2023-01-23 04:30:30.276396: step: 1040/529, loss: 0.03937234729528427
2023-01-23 04:30:31.430519: step: 1044/529, loss: 0.029336929321289062
2023-01-23 04:30:32.554989: step: 1048/529, loss: 3.376007225597277e-05
2023-01-23 04:30:33.676675: step: 1052/529, loss: 0.0004026412789244205
2023-01-23 04:30:34.821716: step: 1056/529, loss: 3.9386748539982364e-05
2023-01-23 04:30:35.963364: step: 1060/529, loss: 0.048660848289728165
2023-01-23 04:30:37.098670: step: 1064/529, loss: 0.0009765148861333728
2023-01-23 04:30:38.223213: step: 1068/529, loss: 3.166198803228326e-05
2023-01-23 04:30:39.378260: step: 1072/529, loss: 4.997253563487902e-05
2023-01-23 04:30:40.509529: step: 1076/529, loss: 0.0034602168016135693
2023-01-23 04:30:41.649470: step: 1080/529, loss: 8.068085298873484e-05
2023-01-23 04:30:42.787109: step: 1084/529, loss: 9.088516526389867e-05
2023-01-23 04:30:43.917510: step: 1088/529, loss: 0.004467296879738569
2023-01-23 04:30:45.043289: step: 1092/529, loss: 2.1171568732825108e-05
2023-01-23 04:30:46.179195: step: 1096/529, loss: 0.00025653839111328125
2023-01-23 04:30:47.331882: step: 1100/529, loss: 0.05918290466070175
2023-01-23 04:30:48.449180: step: 1104/529, loss: 0.0006971359252929688
2023-01-23 04:30:49.574527: step: 1108/529, loss: 0.00013809204392600805
2023-01-23 04:30:50.708595: step: 1112/529, loss: 0.002896976424381137
2023-01-23 04:30:51.838898: step: 1116/529, loss: 4.806518700206652e-05
2023-01-23 04:30:52.939220: step: 1120/529, loss: 0.00015306472778320312
2023-01-23 04:30:54.069338: step: 1124/529, loss: 8.20159912109375e-05
2023-01-23 04:30:55.241459: step: 1128/529, loss: 0.18203915655612946
2023-01-23 04:30:56.388893: step: 1132/529, loss: 0.016922760754823685
2023-01-23 04:30:57.542838: step: 1136/529, loss: 0.00048408505972474813
2023-01-23 04:30:58.685717: step: 1140/529, loss: 0.010960960760712624
2023-01-23 04:30:59.859561: step: 1144/529, loss: 1.3685226804227568e-05
2023-01-23 04:31:00.985869: step: 1148/529, loss: 0.0016571045853197575
2023-01-23 04:31:02.099018: step: 1152/529, loss: 1.392364538332913e-05
2023-01-23 04:31:03.227811: step: 1156/529, loss: 7.786750938976184e-05
2023-01-23 04:31:04.365686: step: 1160/529, loss: 0.021187974140048027
2023-01-23 04:31:05.527857: step: 1164/529, loss: 4.806518700206652e-05
2023-01-23 04:31:06.665402: step: 1168/529, loss: 0.00065698625985533
2023-01-23 04:31:07.811036: step: 1172/529, loss: 0.0008242607582360506
2023-01-23 04:31:08.945971: step: 1176/529, loss: 0.0015277862548828125
2023-01-23 04:31:10.090008: step: 1180/529, loss: 0.006106281187385321
2023-01-23 04:31:11.280176: step: 1184/529, loss: 0.0004264831659384072
2023-01-23 04:31:12.452379: step: 1188/529, loss: 0.0009979248279705644
2023-01-23 04:31:13.658774: step: 1192/529, loss: 3.5667417250806466e-05
2023-01-23 04:31:14.771515: step: 1196/529, loss: 0.0024368285667151213
2023-01-23 04:31:15.909905: step: 1200/529, loss: 0.1896514892578125
2023-01-23 04:31:17.024460: step: 1204/529, loss: 1.544952465337701e-05
2023-01-23 04:31:18.156080: step: 1208/529, loss: 0.024172021076083183
2023-01-23 04:31:19.294372: step: 1212/529, loss: 0.07178258895874023
2023-01-23 04:31:20.443848: step: 1216/529, loss: 0.020547199994325638
2023-01-23 04:31:21.610062: step: 1220/529, loss: 0.0056362152099609375
2023-01-23 04:31:22.756608: step: 1224/529, loss: 0.022477244958281517
2023-01-23 04:31:23.897897: step: 1228/529, loss: 0.0005513191572390497
2023-01-23 04:31:25.073829: step: 1232/529, loss: 0.0011640548473224044
2023-01-23 04:31:26.184681: step: 1236/529, loss: 0.00029783250647597015
2023-01-23 04:31:27.349282: step: 1240/529, loss: 0.0050369263626635075
2023-01-23 04:31:28.529624: step: 1244/529, loss: 0.00013179780216887593
2023-01-23 04:31:29.677185: step: 1248/529, loss: 0.0027900696732103825
2023-01-23 04:31:30.805950: step: 1252/529, loss: 0.00015907287888694555
2023-01-23 04:31:31.929160: step: 1256/529, loss: 3.5858156479662284e-05
2023-01-23 04:31:33.052504: step: 1260/529, loss: 0.00011272430856479332
2023-01-23 04:31:34.173247: step: 1264/529, loss: 0.0013935089809820056
2023-01-23 04:31:35.303807: step: 1268/529, loss: 0.0035043240059167147
2023-01-23 04:31:36.427967: step: 1272/529, loss: 0.006024742033332586
2023-01-23 04:31:37.559788: step: 1276/529, loss: 3.051757857974735e-06
2023-01-23 04:31:38.715129: step: 1280/529, loss: 6.570816185558215e-05
2023-01-23 04:31:39.863899: step: 1284/529, loss: 0.01336746197193861
2023-01-23 04:31:41.012783: step: 1288/529, loss: 0.00023536682419944555
2023-01-23 04:31:42.167544: step: 1292/529, loss: 0.00289497384801507
2023-01-23 04:31:43.305204: step: 1296/529, loss: 4.9400332500226796e-05
2023-01-23 04:31:44.439601: step: 1300/529, loss: 8.77380352903856e-06
2023-01-23 04:31:45.577393: step: 1304/529, loss: 2.975463939947076e-05
2023-01-23 04:31:46.679413: step: 1308/529, loss: 3.4618376957951114e-05
2023-01-23 04:31:47.825399: step: 1312/529, loss: 2.727508581301663e-05
2023-01-23 04:31:48.969915: step: 1316/529, loss: 5.445480201160535e-05
2023-01-23 04:31:50.103337: step: 1320/529, loss: 1.0490421118447557e-06
2023-01-23 04:31:51.234279: step: 1324/529, loss: 0.006299972999840975
2023-01-23 04:31:52.413304: step: 1328/529, loss: 0.0010353088146075606
2023-01-23 04:31:53.546259: step: 1332/529, loss: 6.532669431180693e-06
2023-01-23 04:31:54.701075: step: 1336/529, loss: 7.80105619924143e-05
2023-01-23 04:31:55.832109: step: 1340/529, loss: 0.0023738862946629524
2023-01-23 04:31:56.960813: step: 1344/529, loss: 0.002029991243034601
2023-01-23 04:31:58.074815: step: 1348/529, loss: 3.4809113458322827e-06
2023-01-23 04:31:59.227612: step: 1352/529, loss: 3.4713742934400216e-05
2023-01-23 04:32:00.357988: step: 1356/529, loss: 0.0023852349258959293
2023-01-23 04:32:01.524631: step: 1360/529, loss: 0.017384052276611328
2023-01-23 04:32:02.655113: step: 1364/529, loss: 7.143020775401965e-05
2023-01-23 04:32:03.777445: step: 1368/529, loss: 0.041935063898563385
2023-01-23 04:32:04.905524: step: 1372/529, loss: 0.00025157927302643657
2023-01-23 04:32:06.038764: step: 1376/529, loss: 0.005435562692582607
2023-01-23 04:32:07.168808: step: 1380/529, loss: 8.268356759799644e-05
2023-01-23 04:32:08.289476: step: 1384/529, loss: 5.340576535672881e-06
2023-01-23 04:32:09.418552: step: 1388/529, loss: 0.011392593383789062
2023-01-23 04:32:10.542345: step: 1392/529, loss: 0.01087112445384264
2023-01-23 04:32:11.664501: step: 1396/529, loss: 0.0008609771612100303
2023-01-23 04:32:12.823270: step: 1400/529, loss: -1.754760705807712e-05
2023-01-23 04:32:13.956690: step: 1404/529, loss: 1.773834264895413e-05
2023-01-23 04:32:15.107448: step: 1408/529, loss: 0.04037752002477646
2023-01-23 04:32:16.233074: step: 1412/529, loss: 0.1447887420654297
2023-01-23 04:32:17.361622: step: 1416/529, loss: 0.0012201310601085424
2023-01-23 04:32:18.504223: step: 1420/529, loss: 0.0497930534183979
2023-01-23 04:32:19.646941: step: 1424/529, loss: 0.0015901564620435238
2023-01-23 04:32:20.742522: step: 1428/529, loss: 0.0003097534354310483
2023-01-23 04:32:21.875693: step: 1432/529, loss: 0.02193136140704155
2023-01-23 04:32:23.001141: step: 1436/529, loss: 0.018889809027314186
2023-01-23 04:32:24.135015: step: 1440/529, loss: 0.00017223358736373484
2023-01-23 04:32:25.270486: step: 1444/529, loss: 1.125335711549269e-05
2023-01-23 04:32:26.400989: step: 1448/529, loss: 0.008352279663085938
2023-01-23 04:32:27.528365: step: 1452/529, loss: 0.0004635810910258442
2023-01-23 04:32:28.681781: step: 1456/529, loss: 0.000211620339541696
2023-01-23 04:32:29.833391: step: 1460/529, loss: 0.005231666378676891
2023-01-23 04:32:30.964572: step: 1464/529, loss: 0.0028430940583348274
2023-01-23 04:32:32.093316: step: 1468/529, loss: 0.014341259375214577
2023-01-23 04:32:33.208951: step: 1472/529, loss: 0.01955385133624077
2023-01-23 04:32:34.334792: step: 1476/529, loss: 6.041527012712322e-05
2023-01-23 04:32:35.461812: step: 1480/529, loss: 1.3351436791708693e-06
2023-01-23 04:32:36.566774: step: 1484/529, loss: 0.0025349617935717106
2023-01-23 04:32:37.671256: step: 1488/529, loss: 0.0002658367156982422
2023-01-23 04:32:38.819604: step: 1492/529, loss: 0.002275657607242465
2023-01-23 04:32:39.973278: step: 1496/529, loss: 0.0009624481317587197
2023-01-23 04:32:41.101063: step: 1500/529, loss: 0.0010394096607342362
2023-01-23 04:32:42.295999: step: 1504/529, loss: 0.00041666030301712453
2023-01-23 04:32:43.437721: step: 1508/529, loss: 0.0063919066451489925
2023-01-23 04:32:44.559556: step: 1512/529, loss: -1.697540210443549e-05
2023-01-23 04:32:45.705498: step: 1516/529, loss: 0.0012765884166583419
2023-01-23 04:32:46.838963: step: 1520/529, loss: 0.041562844067811966
2023-01-23 04:32:47.960696: step: 1524/529, loss: 7.82012921263231e-06
2023-01-23 04:32:49.091565: step: 1528/529, loss: 0.000408172607421875
2023-01-23 04:32:50.231723: step: 1532/529, loss: -2.479552676959429e-06
2023-01-23 04:32:51.347673: step: 1536/529, loss: 0.0003198623890057206
2023-01-23 04:32:52.468307: step: 1540/529, loss: 0.003070882288739085
2023-01-23 04:32:53.641166: step: 1544/529, loss: 0.0013587952125817537
2023-01-23 04:32:54.757378: step: 1548/529, loss: 6.637573824264109e-05
2023-01-23 04:32:55.918580: step: 1552/529, loss: 0.04584341123700142
2023-01-23 04:32:57.089390: step: 1556/529, loss: 0.004402923863381147
2023-01-23 04:32:58.199575: step: 1560/529, loss: 0.018163301050662994
2023-01-23 04:32:59.356486: step: 1564/529, loss: 0.005459404084831476
2023-01-23 04:33:00.496238: step: 1568/529, loss: 0.0016266345046460629
2023-01-23 04:33:01.595804: step: 1572/529, loss: 0.000804042792879045
2023-01-23 04:33:02.711734: step: 1576/529, loss: 0.00014543533325195312
2023-01-23 04:33:03.843282: step: 1580/529, loss: 0.001674652099609375
2023-01-23 04:33:04.994342: step: 1584/529, loss: 0.006045246031135321
2023-01-23 04:33:06.193901: step: 1588/529, loss: 0.000324058550177142
2023-01-23 04:33:07.335637: step: 1592/529, loss: 0.000911712646484375
2023-01-23 04:33:08.483585: step: 1596/529, loss: 0.002735328860580921
2023-01-23 04:33:09.608375: step: 1600/529, loss: 4.291534423828125e-06
2023-01-23 04:33:10.769845: step: 1604/529, loss: 0.0002971649228129536
2023-01-23 04:33:11.938786: step: 1608/529, loss: 0.00019931793212890625
2023-01-23 04:33:13.093906: step: 1612/529, loss: 0.0013868332607671618
2023-01-23 04:33:14.198754: step: 1616/529, loss: 0.0015884817112237215
2023-01-23 04:33:15.364205: step: 1620/529, loss: 0.0009127617231570184
2023-01-23 04:33:16.482130: step: 1624/529, loss: 0.00016679764667060226
2023-01-23 04:33:17.621460: step: 1628/529, loss: 0.0013290405040606856
2023-01-23 04:33:18.754032: step: 1632/529, loss: 0.06161098554730415
2023-01-23 04:33:19.895199: step: 1636/529, loss: 3.356933666509576e-05
2023-01-23 04:33:21.026464: step: 1640/529, loss: 5.8746340073412284e-05
2023-01-23 04:33:22.161277: step: 1644/529, loss: 3.43322744811303e-06
2023-01-23 04:33:23.258735: step: 1648/529, loss: 0.0005939721595495939
2023-01-23 04:33:24.376242: step: 1652/529, loss: 6.32286028121598e-05
2023-01-23 04:33:25.511739: step: 1656/529, loss: 0.00811462476849556
2023-01-23 04:33:26.629008: step: 1660/529, loss: 3.046989513677545e-05
2023-01-23 04:33:27.767220: step: 1664/529, loss: 0.0068115233443677425
2023-01-23 04:33:28.905558: step: 1668/529, loss: 7.677078247070312e-05
2023-01-23 04:33:30.060014: step: 1672/529, loss: 0.00017452239990234375
2023-01-23 04:33:31.184003: step: 1676/529, loss: -1.144409225162235e-06
2023-01-23 04:33:32.337165: step: 1680/529, loss: 4.601478576660156e-05
2023-01-23 04:33:33.460296: step: 1684/529, loss: 0.00011558533151401207
2023-01-23 04:33:34.587977: step: 1688/529, loss: 0.010588455945253372
2023-01-23 04:33:35.746669: step: 1692/529, loss: 0.02328033559024334
2023-01-23 04:33:36.897055: step: 1696/529, loss: 0.00018939972505904734
2023-01-23 04:33:38.042384: step: 1700/529, loss: 5.3882598876953125e-05
2023-01-23 04:33:39.176085: step: 1704/529, loss: 4.696846008300781e-05
2023-01-23 04:33:40.332478: step: 1708/529, loss: 0.0001966476411325857
2023-01-23 04:33:41.491650: step: 1712/529, loss: 0.024821758270263672
2023-01-23 04:33:42.609865: step: 1716/529, loss: 0.00035004617529921234
2023-01-23 04:33:43.749338: step: 1720/529, loss: 0.0013475418090820312
2023-01-23 04:33:44.893853: step: 1724/529, loss: 0.0004724502796307206
2023-01-23 04:33:46.007886: step: 1728/529, loss: 0.0009954451816156507
2023-01-23 04:33:47.164991: step: 1732/529, loss: 0.0014881135430186987
2023-01-23 04:33:48.309206: step: 1736/529, loss: 0.014658165164291859
2023-01-23 04:33:49.433090: step: 1740/529, loss: 0.43324583768844604
2023-01-23 04:33:50.577021: step: 1744/529, loss: 0.0011410177685320377
2023-01-23 04:33:51.747222: step: 1748/529, loss: 0.0013059616321697831
2023-01-23 04:33:52.895255: step: 1752/529, loss: -3.814697322468419e-07
2023-01-23 04:33:54.064381: step: 1756/529, loss: 0.025440694764256477
2023-01-23 04:33:55.208072: step: 1760/529, loss: 0.0010429382091388106
2023-01-23 04:33:56.341646: step: 1764/529, loss: 0.011001873761415482
2023-01-23 04:33:57.498504: step: 1768/529, loss: 0.00017170906357932836
2023-01-23 04:33:58.649543: step: 1772/529, loss: 0.0002925872686319053
2023-01-23 04:33:59.775395: step: 1776/529, loss: 0.005158424377441406
2023-01-23 04:34:00.957360: step: 1780/529, loss: 2.4223329091910273e-05
2023-01-23 04:34:02.078215: step: 1784/529, loss: 0.00024366378784179688
2023-01-23 04:34:03.258552: step: 1788/529, loss: 0.006735706701874733
2023-01-23 04:34:04.390597: step: 1792/529, loss: 0.00011568069749046117
2023-01-23 04:34:05.520748: step: 1796/529, loss: 0.005925369448959827
2023-01-23 04:34:06.649847: step: 1800/529, loss: 0.00017452239990234375
2023-01-23 04:34:07.798319: step: 1804/529, loss: 0.002086067106574774
2023-01-23 04:34:08.938664: step: 1808/529, loss: 0.03179149702191353
2023-01-23 04:34:10.078887: step: 1812/529, loss: 0.03338279947638512
2023-01-23 04:34:11.214090: step: 1816/529, loss: 0.0031040192116051912
2023-01-23 04:34:12.332224: step: 1820/529, loss: 0.005063438322395086
2023-01-23 04:34:13.446186: step: 1824/529, loss: -0.0
2023-01-23 04:34:14.556659: step: 1828/529, loss: 2.231597864010837e-05
2023-01-23 04:34:15.700482: step: 1832/529, loss: -1.7166134966828395e-06
2023-01-23 04:34:16.878169: step: 1836/529, loss: 2.6464462280273438e-05
2023-01-23 04:34:18.042354: step: 1840/529, loss: 0.00030012131901457906
2023-01-23 04:34:19.211346: step: 1844/529, loss: 0.00018959045701194555
2023-01-23 04:34:20.338379: step: 1848/529, loss: 3.1948089599609375e-05
2023-01-23 04:34:21.465256: step: 1852/529, loss: 0.00029621124849654734
2023-01-23 04:34:22.640588: step: 1856/529, loss: 0.023758413270115852
2023-01-23 04:34:23.759860: step: 1860/529, loss: 0.0006875992403365672
2023-01-23 04:34:24.875016: step: 1864/529, loss: 0.0006736755603924394
2023-01-23 04:34:26.015074: step: 1868/529, loss: 0.00376987480558455
2023-01-23 04:34:27.114644: step: 1872/529, loss: 1.5735626220703125e-05
2023-01-23 04:34:28.237689: step: 1876/529, loss: 6.732941255904734e-05
2023-01-23 04:34:29.371676: step: 1880/529, loss: 0.09929961711168289
2023-01-23 04:34:30.484695: step: 1884/529, loss: 0.003735494799911976
2023-01-23 04:34:31.605614: step: 1888/529, loss: 0.00010643005225574598
2023-01-23 04:34:32.743984: step: 1892/529, loss: 0.013337898068130016
2023-01-23 04:34:33.875935: step: 1896/529, loss: 0.00020556450181175023
2023-01-23 04:34:35.048254: step: 1900/529, loss: 2.956390380859375e-05
2023-01-23 04:34:36.186035: step: 1904/529, loss: 0.06222815439105034
2023-01-23 04:34:37.351094: step: 1908/529, loss: 0.007288932800292969
2023-01-23 04:34:38.476061: step: 1912/529, loss: 0.00010604858107399195
2023-01-23 04:34:39.661603: step: 1916/529, loss: -1.544952465337701e-05
2023-01-23 04:34:40.820007: step: 1920/529, loss: 0.00024127960205078125
2023-01-23 04:34:41.940166: step: 1924/529, loss: 0.03608379513025284
2023-01-23 04:34:43.071675: step: 1928/529, loss: 0.3224422335624695
2023-01-23 04:34:44.203144: step: 1932/529, loss: 0.0006774902576580644
2023-01-23 04:34:45.346283: step: 1936/529, loss: 0.0008180618169717491
2023-01-23 04:34:46.485353: step: 1940/529, loss: 0.0015459060668945312
2023-01-23 04:34:47.616174: step: 1944/529, loss: 0.0005205154302529991
2023-01-23 04:34:48.780246: step: 1948/529, loss: 0.010601806454360485
2023-01-23 04:34:49.918589: step: 1952/529, loss: 0.034684088081121445
2023-01-23 04:34:51.048005: step: 1956/529, loss: 0.0008123397710733116
2023-01-23 04:34:52.171112: step: 1960/529, loss: 0.002321911044418812
2023-01-23 04:34:53.309435: step: 1964/529, loss: 0.0009657859918661416
2023-01-23 04:34:54.471264: step: 1968/529, loss: 0.00589942978695035
2023-01-23 04:34:55.599825: step: 1972/529, loss: 0.008754539303481579
2023-01-23 04:34:56.744306: step: 1976/529, loss: 0.002149295760318637
2023-01-23 04:34:57.875214: step: 1980/529, loss: 0.0008223534096032381
2023-01-23 04:34:59.009801: step: 1984/529, loss: 0.09383898228406906
2023-01-23 04:35:00.164212: step: 1988/529, loss: 0.1353701502084732
2023-01-23 04:35:01.287889: step: 1992/529, loss: 0.0041592600755393505
2023-01-23 04:35:02.462147: step: 1996/529, loss: 0.004723262973129749
2023-01-23 04:35:03.573210: step: 2000/529, loss: 0.00025300978450104594
2023-01-23 04:35:04.716338: step: 2004/529, loss: 0.0002091407950501889
2023-01-23 04:35:05.895157: step: 2008/529, loss: 9.250640869140625e-05
2023-01-23 04:35:07.008499: step: 2012/529, loss: 4.6443939936580136e-05
2023-01-23 04:35:08.117092: step: 2016/529, loss: 0.0003479004080872983
2023-01-23 04:35:09.225178: step: 2020/529, loss: 9.341239638160914e-05
2023-01-23 04:35:10.366426: step: 2024/529, loss: 0.0008009910816326737
2023-01-23 04:35:11.520869: step: 2028/529, loss: 0.0006376266246661544
2023-01-23 04:35:12.648946: step: 2032/529, loss: 0.005684280302375555
2023-01-23 04:35:13.763127: step: 2036/529, loss: 0.0003005981561727822
2023-01-23 04:35:14.854279: step: 2040/529, loss: 0.00034513475839048624
2023-01-23 04:35:15.985293: step: 2044/529, loss: 9.15527380129788e-06
2023-01-23 04:35:17.119169: step: 2048/529, loss: 0.0018419264815747738
2023-01-23 04:35:18.248949: step: 2052/529, loss: 0.0013955116737633944
2023-01-23 04:35:19.398036: step: 2056/529, loss: 1.3780594599666074e-05
2023-01-23 04:35:20.526123: step: 2060/529, loss: 0.004334306810051203
2023-01-23 04:35:21.676892: step: 2064/529, loss: 0.00029973985510878265
2023-01-23 04:35:22.822158: step: 2068/529, loss: 0.000598526035901159
2023-01-23 04:35:23.960496: step: 2072/529, loss: 0.00211677560582757
2023-01-23 04:35:25.092782: step: 2076/529, loss: 3.5858156479662284e-05
2023-01-23 04:35:26.246193: step: 2080/529, loss: 0.0006576538435183465
2023-01-23 04:35:27.404892: step: 2084/529, loss: 4.863738922722405e-06
2023-01-23 04:35:28.537492: step: 2088/529, loss: 0.9498537182807922
2023-01-23 04:35:29.662111: step: 2092/529, loss: 0.046903230249881744
2023-01-23 04:35:30.795670: step: 2096/529, loss: 0.0009557724115438759
2023-01-23 04:35:31.923979: step: 2100/529, loss: 0.0024808882735669613
2023-01-23 04:35:33.102570: step: 2104/529, loss: 2.918243444582913e-05
2023-01-23 04:35:34.222723: step: 2108/529, loss: 0.007530784700065851
2023-01-23 04:35:35.343312: step: 2112/529, loss: 0.00777969416230917
2023-01-23 04:35:36.479067: step: 2116/529, loss: 0.007008171174675226
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.5850956696878147, 'r': 0.7736351531291611, 'f1': 0.6662844036697246}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6100316312697696, 'r': 0.7821552723059096, 'f1': 0.6854531607006854}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6049382716049383, 'r': 0.9074074074074074, 'f1': 0.725925925925926}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.546875, 'r': 0.5555555555555556, 'f1': 0.5511811023622047}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.3695652173913043, 'r': 0.4722222222222222, 'f1': 0.41463414634146345}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6096033402922756, 'r': 0.7776298268974701, 'f1': 0.6834406085430076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6149954001839927, 'r': 0.7746234067207416, 'f1': 0.6856410256410257}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6375, 'r': 0.9444444444444444, 'f1': 0.7611940298507462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6104944500504541, 'r': 0.8055925432756325, 'f1': 0.6946039035591274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Korean: {'event': {'p': 0.61996336996337, 'r': 0.7844727694090382, 'f1': 0.6925831202046036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
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 04:36:18.344975: step: 4/529, loss: 2.3460386728402227e-05
2023-01-23 04:36:19.483204: step: 8/529, loss: 0.00029935839120298624
2023-01-23 04:36:20.637198: step: 12/529, loss: 0.014672184363007545
2023-01-23 04:36:21.764035: step: 16/529, loss: 5.7220458984375e-05
2023-01-23 04:36:22.881826: step: 20/529, loss: 9.5367431640625e-07
2023-01-23 04:36:24.021937: step: 24/529, loss: 0.004786873236298561
2023-01-23 04:36:25.141600: step: 28/529, loss: 0.00012731552124023438
2023-01-23 04:36:26.303095: step: 32/529, loss: 0.0003940582391805947
2023-01-23 04:36:27.439825: step: 36/529, loss: -2.47955313170678e-06
2023-01-23 04:36:28.571916: step: 40/529, loss: 0.0008508205064572394
2023-01-23 04:36:29.722503: step: 44/529, loss: 0.006895923521369696
2023-01-23 04:36:30.849842: step: 48/529, loss: 2.0503998712229077e-06
2023-01-23 04:36:31.970678: step: 52/529, loss: 0.0001802921324269846
2023-01-23 04:36:33.095674: step: 56/529, loss: 0.00015592575073242188
2023-01-23 04:36:34.227086: step: 60/529, loss: 0.00083751673810184
2023-01-23 04:36:35.353770: step: 64/529, loss: 0.5032185316085815
2023-01-23 04:36:36.504517: step: 68/529, loss: 0.0005693435668945312
2023-01-23 04:36:37.634197: step: 72/529, loss: 0.0004905700916424394
2023-01-23 04:36:38.783657: step: 76/529, loss: 0.2699142396450043
2023-01-23 04:36:39.928378: step: 80/529, loss: 9.584427061781753e-06
2023-01-23 04:36:41.058129: step: 84/529, loss: 0.0004817962762899697
2023-01-23 04:36:42.220023: step: 88/529, loss: 0.0006841659778729081
2023-01-23 04:36:43.355629: step: 92/529, loss: 0.007121467962861061
2023-01-23 04:36:44.503457: step: 96/529, loss: 4.9877166020451114e-05
2023-01-23 04:36:45.633546: step: 100/529, loss: 8.659363084007055e-05
2023-01-23 04:36:46.785463: step: 104/529, loss: 0.0076386453583836555
2023-01-23 04:36:47.914576: step: 108/529, loss: 0.009651850908994675
2023-01-23 04:36:49.045752: step: 112/529, loss: 0.0008951186900958419
2023-01-23 04:36:50.172712: step: 116/529, loss: 0.0006156921153888106
2023-01-23 04:36:51.312927: step: 120/529, loss: 0.14990416169166565
2023-01-23 04:36:52.462002: step: 124/529, loss: 0.0014657974243164062
2023-01-23 04:36:53.606994: step: 128/529, loss: 0.00019092560978606343
2023-01-23 04:36:54.720072: step: 132/529, loss: 0.00017852784367278218
2023-01-23 04:36:55.851916: step: 136/529, loss: 0.014473057352006435
2023-01-23 04:36:56.969566: step: 140/529, loss: 2.365112231927924e-05
2023-01-23 04:36:58.115982: step: 144/529, loss: 3.700256274896674e-05
2023-01-23 04:36:59.237588: step: 148/529, loss: 0.0011466980213299394
2023-01-23 04:37:00.383158: step: 152/529, loss: 0.00042872430640272796
2023-01-23 04:37:01.501854: step: 156/529, loss: 0.0023859022185206413
2023-01-23 04:37:02.612152: step: 160/529, loss: 0.0006986618391238153
2023-01-23 04:37:03.761099: step: 164/529, loss: 0.003813839051872492
2023-01-23 04:37:04.880368: step: 168/529, loss: 5.53131121705519e-06
2023-01-23 04:37:06.015500: step: 172/529, loss: 7.247925168485381e-06
2023-01-23 04:37:07.155401: step: 176/529, loss: 0.00010890961129916832
2023-01-23 04:37:08.291742: step: 180/529, loss: 0.0056404112838208675
2023-01-23 04:37:09.441096: step: 184/529, loss: 0.0022989274002611637
2023-01-23 04:37:10.608119: step: 188/529, loss: -1.754760705807712e-05
2023-01-23 04:37:11.705537: step: 192/529, loss: 0.002397251082584262
2023-01-23 04:37:12.817519: step: 196/529, loss: 0.009088468737900257
2023-01-23 04:37:13.945836: step: 200/529, loss: 0.00033540723961777985
2023-01-23 04:37:15.084261: step: 204/529, loss: 0.0004325866757426411
2023-01-23 04:37:16.226202: step: 208/529, loss: 0.04682159423828125
2023-01-23 04:37:17.367393: step: 212/529, loss: 1.888275073724799e-05
2023-01-23 04:37:18.479129: step: 216/529, loss: 0.0016709327464923263
2023-01-23 04:37:19.612876: step: 220/529, loss: 0.053383637219667435
2023-01-23 04:37:20.744771: step: 224/529, loss: 0.00042934418888762593
2023-01-23 04:37:21.896143: step: 228/529, loss: 0.0007314682006835938
2023-01-23 04:37:23.019569: step: 232/529, loss: 0.0005847931606695056
2023-01-23 04:37:24.139858: step: 236/529, loss: 4.596710277837701e-05
2023-01-23 04:37:25.249717: step: 240/529, loss: 5.073547436040826e-05
2023-01-23 04:37:26.378532: step: 244/529, loss: 0.004123473074287176
2023-01-23 04:37:27.533095: step: 248/529, loss: 0.010294127278029919
2023-01-23 04:37:28.681079: step: 252/529, loss: -1.9073486328125e-06
2023-01-23 04:37:29.817480: step: 256/529, loss: 0.00010976791236316785
2023-01-23 04:37:30.945107: step: 260/529, loss: 3.24249267578125e-05
2023-01-23 04:37:32.053064: step: 264/529, loss: 0.01105346716940403
2023-01-23 04:37:33.195680: step: 268/529, loss: 7.343292963923886e-05
2023-01-23 04:37:34.376585: step: 272/529, loss: 0.07409544289112091
2023-01-23 04:37:35.510188: step: 276/529, loss: 0.00010738372657215223
2023-01-23 04:37:36.645770: step: 280/529, loss: 0.0003066062927246094
2023-01-23 04:37:37.786579: step: 284/529, loss: -1.5258810890372843e-06
2023-01-23 04:37:38.926461: step: 288/529, loss: 0.014914512634277344
2023-01-23 04:37:40.047331: step: 292/529, loss: -4.768378403241513e-08
2023-01-23 04:37:41.180524: step: 296/529, loss: 0.014096450991928577
2023-01-23 04:37:42.331442: step: 300/529, loss: 0.0008718490717001259
2023-01-23 04:37:43.458949: step: 304/529, loss: 1.8596649169921875e-05
2023-01-23 04:37:44.597526: step: 308/529, loss: 0.002388572786003351
2023-01-23 04:37:45.744950: step: 312/529, loss: 0.005264568608254194
2023-01-23 04:37:46.864566: step: 316/529, loss: 3.6048892070539296e-05
2023-01-23 04:37:47.989761: step: 320/529, loss: 0.020990561693906784
2023-01-23 04:37:49.150474: step: 324/529, loss: 0.0017747879028320312
2023-01-23 04:37:50.279039: step: 328/529, loss: 0.00013570785813499242
2023-01-23 04:37:51.417988: step: 332/529, loss: 9.307861182605848e-05
2023-01-23 04:37:52.519229: step: 336/529, loss: 0.28476542234420776
2023-01-23 04:37:53.672798: step: 340/529, loss: 0.00011329650442348793
2023-01-23 04:37:54.831817: step: 344/529, loss: 0.0011203765170648694
2023-01-23 04:37:55.999680: step: 348/529, loss: 0.019318770617246628
2023-01-23 04:37:57.121442: step: 352/529, loss: 0.01470184326171875
2023-01-23 04:37:58.232797: step: 356/529, loss: 0.0005246639484539628
2023-01-23 04:37:59.379275: step: 360/529, loss: 0.002130126813426614
2023-01-23 04:38:00.549052: step: 364/529, loss: 8.296967280330136e-05
2023-01-23 04:38:01.691012: step: 368/529, loss: 0.0001904487726278603
2023-01-23 04:38:02.814014: step: 372/529, loss: 0.0015802383422851562
2023-01-23 04:38:03.984892: step: 376/529, loss: 0.03137655556201935
2023-01-23 04:38:05.117449: step: 380/529, loss: 0.00015354156494140625
2023-01-23 04:38:06.251238: step: 384/529, loss: 7.81059279688634e-05
2023-01-23 04:38:07.354069: step: 388/529, loss: 3.1280520488508046e-05
2023-01-23 04:38:08.507425: step: 392/529, loss: 0.005615520756691694
2023-01-23 04:38:09.656736: step: 396/529, loss: 0.02689342573285103
2023-01-23 04:38:10.775669: step: 400/529, loss: 0.0017635822296142578
2023-01-23 04:38:11.906457: step: 404/529, loss: 1.3732910701946821e-05
2023-01-23 04:38:13.038098: step: 408/529, loss: 6.990432302700356e-05
2023-01-23 04:38:14.161491: step: 412/529, loss: 5.684341886080802e-14
2023-01-23 04:38:15.315332: step: 416/529, loss: 0.004117202945053577
2023-01-23 04:38:16.416730: step: 420/529, loss: 0.04629566892981529
2023-01-23 04:38:17.542236: step: 424/529, loss: 0.01478795986622572
2023-01-23 04:38:18.674875: step: 428/529, loss: 0.0011396408081054688
2023-01-23 04:38:19.811374: step: 432/529, loss: 0.00019121170043945312
2023-01-23 04:38:20.939855: step: 436/529, loss: 0.002372837159782648
2023-01-23 04:38:22.086248: step: 440/529, loss: 0.0002368926943745464
2023-01-23 04:38:23.252483: step: 444/529, loss: 0.02082247845828533
2023-01-23 04:38:24.366119: step: 448/529, loss: 0.004999017808586359
2023-01-23 04:38:25.505414: step: 452/529, loss: 3.261566234868951e-05
2023-01-23 04:38:26.630187: step: 456/529, loss: 0.0018061638111248612
2023-01-23 04:38:27.780162: step: 460/529, loss: 0.0003569602849893272
2023-01-23 04:38:28.915609: step: 464/529, loss: 0.0007804393535479903
2023-01-23 04:38:30.034020: step: 468/529, loss: 0.0010192871559411287
2023-01-23 04:38:31.177314: step: 472/529, loss: 1.9073486328125e-05
2023-01-23 04:38:32.288052: step: 476/529, loss: 0.0007602691766805947
2023-01-23 04:38:33.443258: step: 480/529, loss: 0.0001371383696096018
2023-01-23 04:38:34.566851: step: 484/529, loss: 0.0013807296054437757
2023-01-23 04:38:35.670690: step: 488/529, loss: 0.00026416778564453125
2023-01-23 04:38:36.796503: step: 492/529, loss: 0.0008924484718590975
2023-01-23 04:38:37.915448: step: 496/529, loss: 5.1021575927734375e-05
2023-01-23 04:38:39.024136: step: 500/529, loss: 0.021207714453339577
2023-01-23 04:38:40.167935: step: 504/529, loss: 0.005426979158073664
2023-01-23 04:38:41.278120: step: 508/529, loss: 0.00489354133605957
2023-01-23 04:38:42.413379: step: 512/529, loss: 0.00035858154296875
2023-01-23 04:38:43.539184: step: 516/529, loss: 0.0008200645679607987
2023-01-23 04:38:44.680479: step: 520/529, loss: 1.316070574830519e-05
2023-01-23 04:38:45.803932: step: 524/529, loss: 0.002777671907097101
2023-01-23 04:38:46.943894: step: 528/529, loss: 4.596710277837701e-05
2023-01-23 04:38:48.062624: step: 532/529, loss: 0.0003758430539164692
2023-01-23 04:38:49.208732: step: 536/529, loss: 0.0016123296227306128
2023-01-23 04:38:50.364491: step: 540/529, loss: 2.6607513063936494e-05
2023-01-23 04:38:51.463260: step: 544/529, loss: 3.890991138177924e-05
2023-01-23 04:38:52.613270: step: 548/529, loss: 0.00042486193706281483
2023-01-23 04:38:53.759063: step: 552/529, loss: 0.004232645500451326
2023-01-23 04:38:54.896882: step: 556/529, loss: -4.9591067181609105e-06
2023-01-23 04:38:56.027808: step: 560/529, loss: 2.059936559817288e-05
2023-01-23 04:38:57.156324: step: 564/529, loss: 0.053559113293886185
2023-01-23 04:38:58.289056: step: 568/529, loss: 0.008004474453628063
2023-01-23 04:38:59.450019: step: 572/529, loss: -3.862380708596902e-06
2023-01-23 04:39:00.572042: step: 576/529, loss: 0.00014247893705032766
2023-01-23 04:39:01.711061: step: 580/529, loss: 0.06905770301818848
2023-01-23 04:39:02.850669: step: 584/529, loss: 0.0037467957008630037
2023-01-23 04:39:03.994748: step: 588/529, loss: 0.00011959076800849289
2023-01-23 04:39:05.146725: step: 592/529, loss: 8.773804438533261e-06
2023-01-23 04:39:06.278769: step: 596/529, loss: 0.00252361292950809
2023-01-23 04:39:07.411646: step: 600/529, loss: 0.004902648739516735
2023-01-23 04:39:08.556676: step: 604/529, loss: 1.3542176020564511e-05
2023-01-23 04:39:09.723081: step: 608/529, loss: 0.0007461548084393144
2023-01-23 04:39:10.889704: step: 612/529, loss: 0.0007884979131631553
2023-01-23 04:39:12.035657: step: 616/529, loss: 2.2268293832894415e-05
2023-01-23 04:39:13.188741: step: 620/529, loss: 0.0004235267697367817
2023-01-23 04:39:14.307743: step: 624/529, loss: 0.00041961669921875
2023-01-23 04:39:15.432810: step: 628/529, loss: 5.817413693876006e-05
2023-01-23 04:39:16.581853: step: 632/529, loss: -3.814693627646193e-07
2023-01-23 04:39:17.740612: step: 636/529, loss: 0.000263214111328125
2023-01-23 04:39:18.885247: step: 640/529, loss: 0.0021175385918468237
2023-01-23 04:39:20.020280: step: 644/529, loss: 0.028862619772553444
2023-01-23 04:39:21.157109: step: 648/529, loss: 0.00018520356388762593
2023-01-23 04:39:22.280298: step: 652/529, loss: 6.361007399391383e-05
2023-01-23 04:39:23.426934: step: 656/529, loss: 0.0072679524309933186
2023-01-23 04:39:24.566767: step: 660/529, loss: 5.683898780262098e-05
2023-01-23 04:39:25.703860: step: 664/529, loss: 0.0001659393310546875
2023-01-23 04:39:26.814992: step: 668/529, loss: 1.8739699953584932e-05
2023-01-23 04:39:27.917529: step: 672/529, loss: 0.0007623672718182206
2023-01-23 04:39:29.056828: step: 676/529, loss: 7.457733590854332e-05
2023-01-23 04:39:30.195806: step: 680/529, loss: 0.00019531250291038305
2023-01-23 04:39:31.317299: step: 684/529, loss: 0.0016321182483807206
2023-01-23 04:39:32.426750: step: 688/529, loss: 0.0650150328874588
2023-01-23 04:39:33.589236: step: 692/529, loss: 0.056092265993356705
2023-01-23 04:39:34.728756: step: 696/529, loss: 0.004901600535959005
2023-01-23 04:39:35.880479: step: 700/529, loss: 0.006706810090690851
2023-01-23 04:39:37.019618: step: 704/529, loss: 2.384185791015625e-05
2023-01-23 04:39:38.134099: step: 708/529, loss: 0.0006958008161745965
2023-01-23 04:39:39.262162: step: 712/529, loss: 0.004782963078469038
2023-01-23 04:39:40.396739: step: 716/529, loss: 0.011318016797304153
2023-01-23 04:39:41.542617: step: 720/529, loss: 0.03778582066297531
2023-01-23 04:39:42.657856: step: 724/529, loss: 0.00013236999802757055
2023-01-23 04:39:43.793137: step: 728/529, loss: 3.337860471219756e-05
2023-01-23 04:39:44.931316: step: 732/529, loss: 0.014777183532714844
2023-01-23 04:39:46.062283: step: 736/529, loss: 0.0031271218322217464
2023-01-23 04:39:47.193489: step: 740/529, loss: 9.202957153320312e-05
2023-01-23 04:39:48.368668: step: 744/529, loss: 0.0004380226309876889
2023-01-23 04:39:49.507450: step: 748/529, loss: 0.0006619453779421747
2023-01-23 04:39:50.669467: step: 752/529, loss: -1.8119812921213452e-06
2023-01-23 04:39:51.844092: step: 756/529, loss: 5.245208740234375e-06
2023-01-23 04:39:52.985910: step: 760/529, loss: 9.698867506813258e-05
2023-01-23 04:39:54.141977: step: 764/529, loss: 1.926422191900201e-05
2023-01-23 04:39:55.315058: step: 768/529, loss: 0.0018943786853924394
2023-01-23 04:39:56.479334: step: 772/529, loss: 0.005262661259621382
2023-01-23 04:39:57.620669: step: 776/529, loss: -3.814697322468419e-07
2023-01-23 04:39:58.763394: step: 780/529, loss: 0.000484466552734375
2023-01-23 04:39:59.873592: step: 784/529, loss: -4.19616708313697e-06
2023-01-23 04:40:01.019825: step: 788/529, loss: 0.0003603935183491558
2023-01-23 04:40:02.158473: step: 792/529, loss: 0.023030854761600494
2023-01-23 04:40:03.290825: step: 796/529, loss: 0.0053886412642896175
2023-01-23 04:40:04.447197: step: 800/529, loss: 7.24792471373803e-06
2023-01-23 04:40:05.568325: step: 804/529, loss: 0.033295489847660065
2023-01-23 04:40:06.696703: step: 808/529, loss: 1.869201696536038e-05
2023-01-23 04:40:07.818590: step: 812/529, loss: 0.0011773109436035156
2023-01-23 04:40:08.935819: step: 816/529, loss: 0.003726184368133545
2023-01-23 04:40:10.066814: step: 820/529, loss: 2.8467178708524443e-05
2023-01-23 04:40:11.189396: step: 824/529, loss: 0.00016708373732399195
2023-01-23 04:40:12.330067: step: 828/529, loss: 0.0010879039764404297
2023-01-23 04:40:13.476355: step: 832/529, loss: 3.795623706537299e-05
2023-01-23 04:40:14.583527: step: 836/529, loss: 4.668235487770289e-05
2023-01-23 04:40:15.731914: step: 840/529, loss: 0.033077385276556015
2023-01-23 04:40:16.879560: step: 844/529, loss: 0.007237625308334827
2023-01-23 04:40:18.039206: step: 848/529, loss: 0.0013727188343182206
2023-01-23 04:40:19.166486: step: 852/529, loss: 0.0005105972522869706
2023-01-23 04:40:20.320967: step: 856/529, loss: 0.03170204162597656
2023-01-23 04:40:21.474771: step: 860/529, loss: 0.00256690988317132
2023-01-23 04:40:22.633631: step: 864/529, loss: 0.0013068198459222913
2023-01-23 04:40:23.797135: step: 868/529, loss: 0.00027236941969022155
2023-01-23 04:40:24.942438: step: 872/529, loss: 0.05469665676355362
2023-01-23 04:40:26.055830: step: 876/529, loss: 1.9454957509879023e-05
2023-01-23 04:40:27.160255: step: 880/529, loss: 1.964569128176663e-05
2023-01-23 04:40:28.312002: step: 884/529, loss: 0.00011425017873989418
2023-01-23 04:40:29.454525: step: 888/529, loss: 0.006271743681281805
2023-01-23 04:40:30.571262: step: 892/529, loss: 1.621246337890625e-05
2023-01-23 04:40:31.778864: step: 896/529, loss: 0.00096044538076967
2023-01-23 04:40:32.909803: step: 900/529, loss: 0.005579191725701094
2023-01-23 04:40:34.029197: step: 904/529, loss: 0.0014452934265136719
2023-01-23 04:40:35.185024: step: 908/529, loss: 0.023462487384676933
2023-01-23 04:40:36.327607: step: 912/529, loss: 0.0772615447640419
2023-01-23 04:40:37.478854: step: 916/529, loss: 0.00016660690016578883
2023-01-23 04:40:38.607963: step: 920/529, loss: 0.006028270814567804
2023-01-23 04:40:39.735217: step: 924/529, loss: 0.0023314475547522306
2023-01-23 04:40:40.900427: step: 928/529, loss: 2.193450927734375e-05
2023-01-23 04:40:42.010675: step: 932/529, loss: 5.14984139954322e-06
2023-01-23 04:40:43.165443: step: 936/529, loss: 0.00025196076603606343
2023-01-23 04:40:44.304825: step: 940/529, loss: 0.05692453682422638
2023-01-23 04:40:45.459900: step: 944/529, loss: 0.000346946733770892
2023-01-23 04:40:46.619761: step: 948/529, loss: 0.00018634795560501516
2023-01-23 04:40:47.773953: step: 952/529, loss: 0.00021378994279075414
2023-01-23 04:40:48.923948: step: 956/529, loss: 3.4809113458322827e-06
2023-01-23 04:40:50.067177: step: 960/529, loss: 1.926422191900201e-05
2023-01-23 04:40:51.225625: step: 964/529, loss: 0.0012403487926349044
2023-01-23 04:40:52.368942: step: 968/529, loss: 0.023621369153261185
2023-01-23 04:40:53.504536: step: 972/529, loss: 0.0001446724054403603
2023-01-23 04:40:54.647341: step: 976/529, loss: 0.00833206158131361
2023-01-23 04:40:55.786519: step: 980/529, loss: 0.025003530085086823
2023-01-23 04:40:56.925527: step: 984/529, loss: 0.04435539245605469
2023-01-23 04:40:58.084444: step: 988/529, loss: 7.686615572310984e-05
2023-01-23 04:40:59.236617: step: 992/529, loss: 0.00627479562535882
2023-01-23 04:41:00.389956: step: 996/529, loss: 0.0008912086486816406
2023-01-23 04:41:01.542913: step: 1000/529, loss: 0.0004402160702738911
2023-01-23 04:41:02.665673: step: 1004/529, loss: 0.0003693580802064389
2023-01-23 04:41:03.831923: step: 1008/529, loss: 0.0011402606032788754
2023-01-23 04:41:04.962363: step: 1012/529, loss: 0.12761488556861877
2023-01-23 04:41:06.095852: step: 1016/529, loss: 0.0008741378551349044
2023-01-23 04:41:07.259930: step: 1020/529, loss: 1.4781952813791577e-05
2023-01-23 04:41:08.391350: step: 1024/529, loss: 0.0065240864641964436
2023-01-23 04:41:09.557615: step: 1028/529, loss: 0.02981739118695259
2023-01-23 04:41:10.689858: step: 1032/529, loss: 0.00018424987501930445
2023-01-23 04:41:11.800523: step: 1036/529, loss: 0.017676925286650658
2023-01-23 04:41:12.948191: step: 1040/529, loss: 0.00027637480525299907
2023-01-23 04:41:14.077050: step: 1044/529, loss: 3.538131932145916e-05
2023-01-23 04:41:15.223762: step: 1048/529, loss: 0.00035533905611373484
2023-01-23 04:41:16.355752: step: 1052/529, loss: 0.0002127170591847971
2023-01-23 04:41:17.483994: step: 1056/529, loss: 7.591248140670359e-05
2023-01-23 04:41:18.620693: step: 1060/529, loss: 3.7622452509822324e-05
2023-01-23 04:41:19.763629: step: 1064/529, loss: 0.002129149390384555
2023-01-23 04:41:20.903200: step: 1068/529, loss: 7.43865984986769e-06
2023-01-23 04:41:22.036182: step: 1072/529, loss: 0.00011397599882911891
2023-01-23 04:41:23.166773: step: 1076/529, loss: 0.00026998520479537547
2023-01-23 04:41:24.301686: step: 1080/529, loss: 5.33103957423009e-05
2023-01-23 04:41:25.441470: step: 1084/529, loss: 0.01102142408490181
2023-01-23 04:41:26.601169: step: 1088/529, loss: 0.012543297372758389
2023-01-23 04:41:27.738290: step: 1092/529, loss: 0.0003061771276406944
2023-01-23 04:41:28.938814: step: 1096/529, loss: 0.0028985501267015934
2023-01-23 04:41:30.052305: step: 1100/529, loss: 0.00029082296532578766
2023-01-23 04:41:31.182105: step: 1104/529, loss: 0.00033473968505859375
2023-01-23 04:41:32.315797: step: 1108/529, loss: 0.0009959221351891756
2023-01-23 04:41:33.469102: step: 1112/529, loss: 3.910064606316155e-06
2023-01-23 04:41:34.626751: step: 1116/529, loss: 0.001818847726099193
2023-01-23 04:41:35.751006: step: 1120/529, loss: 7.915497008070815e-06
2023-01-23 04:41:36.880200: step: 1124/529, loss: 0.0004977226490154862
2023-01-23 04:41:38.000256: step: 1128/529, loss: 0.0020755769219249487
2023-01-23 04:41:39.139917: step: 1132/529, loss: 0.0018720626831054688
2023-01-23 04:41:40.283855: step: 1136/529, loss: 1.4257430848374497e-05
2023-01-23 04:41:41.427505: step: 1140/529, loss: 0.003218937199562788
2023-01-23 04:41:42.569831: step: 1144/529, loss: 6.508827027573716e-06
2023-01-23 04:41:43.720655: step: 1148/529, loss: 0.0028348921332508326
2023-01-23 04:41:44.859647: step: 1152/529, loss: 0.0027710916474461555
2023-01-23 04:41:45.997372: step: 1156/529, loss: 0.0001966476411325857
2023-01-23 04:41:47.087995: step: 1160/529, loss: 0.00021901130094192922
2023-01-23 04:41:48.237144: step: 1164/529, loss: 4.863738922722405e-06
2023-01-23 04:41:49.353403: step: 1168/529, loss: 0.0004108429129701108
2023-01-23 04:41:50.506528: step: 1172/529, loss: 0.001256656600162387
2023-01-23 04:41:51.633242: step: 1176/529, loss: 0.00730056781321764
2023-01-23 04:41:52.731539: step: 1180/529, loss: 0.003490447998046875
2023-01-23 04:41:53.918014: step: 1184/529, loss: 0.025895357131958008
2023-01-23 04:41:55.046227: step: 1188/529, loss: 0.0071398732252418995
2023-01-23 04:41:56.165325: step: 1192/529, loss: 0.024666596204042435
2023-01-23 04:41:57.336648: step: 1196/529, loss: 0.00036582950269803405
2023-01-23 04:41:58.468263: step: 1200/529, loss: 0.00165901193395257
2023-01-23 04:41:59.610237: step: 1204/529, loss: 3.62396240234375e-05
2023-01-23 04:42:00.752281: step: 1208/529, loss: 0.5964565873146057
2023-01-23 04:42:01.852713: step: 1212/529, loss: 0.00023236274137161672
2023-01-23 04:42:02.978674: step: 1216/529, loss: 0.00144109723623842
2023-01-23 04:42:04.072664: step: 1220/529, loss: 3.662109520519152e-05
2023-01-23 04:42:05.195118: step: 1224/529, loss: 0.005763912573456764
2023-01-23 04:42:06.326764: step: 1228/529, loss: 0.07522864639759064
2023-01-23 04:42:07.493828: step: 1232/529, loss: 0.0003174305020365864
2023-01-23 04:42:08.639137: step: 1236/529, loss: 3.070831371587701e-05
2023-01-23 04:42:09.762067: step: 1240/529, loss: 7.410049147438258e-05
2023-01-23 04:42:10.896350: step: 1244/529, loss: 7.591248140670359e-05
2023-01-23 04:42:12.019201: step: 1248/529, loss: 6.389617738022935e-06
2023-01-23 04:42:13.208217: step: 1252/529, loss: 1.9073486612342094e-07
2023-01-23 04:42:14.353163: step: 1256/529, loss: 2.0827352273045108e-05
2023-01-23 04:42:15.483416: step: 1260/529, loss: 0.09041042625904083
2023-01-23 04:42:16.620743: step: 1264/529, loss: 0.004899788182228804
2023-01-23 04:42:17.754810: step: 1268/529, loss: 0.0001458644837839529
2023-01-23 04:42:18.899162: step: 1272/529, loss: 0.7516994476318359
2023-01-23 04:42:20.036561: step: 1276/529, loss: 0.023574162274599075
2023-01-23 04:42:21.204856: step: 1280/529, loss: 0.004985761363059282
2023-01-23 04:42:22.369384: step: 1284/529, loss: 0.012679862789809704
2023-01-23 04:42:23.501984: step: 1288/529, loss: 0.028561020269989967
2023-01-23 04:42:24.664170: step: 1292/529, loss: 0.0013056754833087325
2023-01-23 04:42:25.789706: step: 1296/529, loss: 9.784699068404734e-05
2023-01-23 04:42:26.934600: step: 1300/529, loss: 0.02716655842959881
2023-01-23 04:42:28.072775: step: 1304/529, loss: 0.0332736037671566
2023-01-23 04:42:29.235711: step: 1308/529, loss: 0.00038585663423873484
2023-01-23 04:42:30.390078: step: 1312/529, loss: 0.03784656524658203
2023-01-23 04:42:31.538020: step: 1316/529, loss: 0.0308977123349905
2023-01-23 04:42:32.682854: step: 1320/529, loss: 0.019786834716796875
2023-01-23 04:42:33.789507: step: 1324/529, loss: 0.0004259109846316278
2023-01-23 04:42:34.951424: step: 1328/529, loss: 0.036594390869140625
2023-01-23 04:42:36.112072: step: 1332/529, loss: 7.057189577608369e-06
2023-01-23 04:42:37.233350: step: 1336/529, loss: 0.0019504546653479338
2023-01-23 04:42:38.371959: step: 1340/529, loss: 0.017937278375029564
2023-01-23 04:42:39.511844: step: 1344/529, loss: 0.008871365338563919
2023-01-23 04:42:40.652996: step: 1348/529, loss: 0.08070297539234161
2023-01-23 04:42:41.805487: step: 1352/529, loss: 0.0002893448108807206
2023-01-23 04:42:42.951247: step: 1356/529, loss: 8.02993745310232e-05
2023-01-23 04:42:44.104772: step: 1360/529, loss: 0.003805828047916293
2023-01-23 04:42:45.244547: step: 1364/529, loss: 8.811950829112902e-05
2023-01-23 04:42:46.374556: step: 1368/529, loss: 0.024486638605594635
2023-01-23 04:42:47.531250: step: 1372/529, loss: 6.46591215627268e-05
2023-01-23 04:42:48.633506: step: 1376/529, loss: 0.013908577151596546
2023-01-23 04:42:49.787664: step: 1380/529, loss: 0.0063065532594919205
2023-01-23 04:42:50.916936: step: 1384/529, loss: 0.00014247893705032766
2023-01-23 04:42:52.063618: step: 1388/529, loss: 0.0030319690704345703
2023-01-23 04:42:53.210868: step: 1392/529, loss: 0.013313484378159046
2023-01-23 04:42:54.347141: step: 1396/529, loss: 0.006332111544907093
2023-01-23 04:42:55.453394: step: 1400/529, loss: 0.003944015596061945
2023-01-23 04:42:56.634071: step: 1404/529, loss: 3.843307786155492e-05
2023-01-23 04:42:57.770837: step: 1408/529, loss: 0.0009023666498251259
2023-01-23 04:42:58.922698: step: 1412/529, loss: 0.015327262692153454
2023-01-23 04:43:00.062086: step: 1416/529, loss: 0.00046062469482421875
2023-01-23 04:43:01.205477: step: 1420/529, loss: 0.0008195877308025956
2023-01-23 04:43:02.356551: step: 1424/529, loss: 0.03784484788775444
2023-01-23 04:43:03.456481: step: 1428/529, loss: 2.2888182229507947e-06
2023-01-23 04:43:04.613691: step: 1432/529, loss: 0.0006546020740643144
2023-01-23 04:43:05.821185: step: 1436/529, loss: 0.0011878968216478825
2023-01-23 04:43:06.959879: step: 1440/529, loss: 0.031148720532655716
2023-01-23 04:43:08.104704: step: 1444/529, loss: 0.001228809473104775
2023-01-23 04:43:09.231478: step: 1448/529, loss: 0.000751876796130091
2023-01-23 04:43:10.395353: step: 1452/529, loss: 0.03620429337024689
2023-01-23 04:43:11.555839: step: 1456/529, loss: 0.002294826554134488
2023-01-23 04:43:12.714551: step: 1460/529, loss: 0.10650186240673065
2023-01-23 04:43:13.878329: step: 1464/529, loss: 0.06921463459730148
2023-01-23 04:43:15.006492: step: 1468/529, loss: 0.0002173423854401335
2023-01-23 04:43:16.168975: step: 1472/529, loss: 0.0038563727866858244
2023-01-23 04:43:17.324868: step: 1476/529, loss: 2.09808349609375e-05
2023-01-23 04:43:18.467372: step: 1480/529, loss: 0.0002063751162495464
2023-01-23 04:43:19.620573: step: 1484/529, loss: 0.00020675660925917327
2023-01-23 04:43:20.734048: step: 1488/529, loss: 0.0016550064319744706
2023-01-23 04:43:21.877408: step: 1492/529, loss: 3.2901763916015625e-05
2023-01-23 04:43:23.009193: step: 1496/529, loss: 4.119873119634576e-05
2023-01-23 04:43:24.156279: step: 1500/529, loss: 0.0003685951232910156
2023-01-23 04:43:25.326171: step: 1504/529, loss: 3.06129441014491e-05
2023-01-23 04:43:26.456228: step: 1508/529, loss: 1.0967251000693068e-06
2023-01-23 04:43:27.635436: step: 1512/529, loss: 0.00045871734619140625
2023-01-23 04:43:28.770964: step: 1516/529, loss: 0.024495983496308327
2023-01-23 04:43:29.927412: step: 1520/529, loss: 8.60214204294607e-05
2023-01-23 04:43:31.064134: step: 1524/529, loss: 0.051072120666503906
2023-01-23 04:43:32.192090: step: 1528/529, loss: 9.765625145519152e-05
2023-01-23 04:43:33.324700: step: 1532/529, loss: 0.024402141571044922
2023-01-23 04:43:34.480867: step: 1536/529, loss: 0.23023644089698792
2023-01-23 04:43:35.597450: step: 1540/529, loss: 0.007288933265954256
2023-01-23 04:43:36.745600: step: 1544/529, loss: 0.00013408661470748484
2023-01-23 04:43:37.888257: step: 1548/529, loss: 0.0003101348993368447
2023-01-23 04:43:39.025461: step: 1552/529, loss: 0.019306089729070663
2023-01-23 04:43:40.127798: step: 1556/529, loss: 0.00035858154296875
2023-01-23 04:43:41.272982: step: 1560/529, loss: 2.346038854739163e-05
2023-01-23 04:43:42.401011: step: 1564/529, loss: 0.0006791114574298263
2023-01-23 04:43:43.563337: step: 1568/529, loss: 0.04008903726935387
2023-01-23 04:43:44.695348: step: 1572/529, loss: 0.0009317398071289062
2023-01-23 04:43:45.848902: step: 1576/529, loss: 1.2683869499596767e-05
2023-01-23 04:43:46.994494: step: 1580/529, loss: 0.04442129284143448
2023-01-23 04:43:48.146566: step: 1584/529, loss: 0.0014568328624591231
2023-01-23 04:43:49.257044: step: 1588/529, loss: 0.0013950347201898694
2023-01-23 04:43:50.382320: step: 1592/529, loss: 0.015591430477797985
2023-01-23 04:43:51.493703: step: 1596/529, loss: 4.7683710135970614e-07
2023-01-23 04:43:52.630151: step: 1600/529, loss: 0.0007187843439169228
2023-01-23 04:43:53.761506: step: 1604/529, loss: 4.291534423828125e-06
2023-01-23 04:43:54.890848: step: 1608/529, loss: 0.0032068253494799137
2023-01-23 04:43:56.037023: step: 1612/529, loss: 1.2588501704158261e-05
2023-01-23 04:43:57.188815: step: 1616/529, loss: 1.1396408808650449e-05
2023-01-23 04:43:58.334419: step: 1620/529, loss: 0.00022563934908248484
2023-01-23 04:43:59.496592: step: 1624/529, loss: 0.0004671096976380795
2023-01-23 04:44:00.659620: step: 1628/529, loss: 0.00029478073702193797
2023-01-23 04:44:01.801656: step: 1632/529, loss: 4.901886131847277e-05
2023-01-23 04:44:02.927807: step: 1636/529, loss: 0.0856361836194992
2023-01-23 04:44:04.115089: step: 1640/529, loss: 0.0035624506417661905
2023-01-23 04:44:05.258532: step: 1644/529, loss: 0.00023083687119651586
2023-01-23 04:44:06.372063: step: 1648/529, loss: 3.318786548334174e-05
2023-01-23 04:44:07.506243: step: 1652/529, loss: 9.441375368623994e-06
2023-01-23 04:44:08.635732: step: 1656/529, loss: 1.659393274167087e-05
2023-01-23 04:44:09.774832: step: 1660/529, loss: 0.013043785467743874
2023-01-23 04:44:10.898775: step: 1664/529, loss: 0.00016469955153297633
2023-01-23 04:44:12.036278: step: 1668/529, loss: 0.04447536543011665
2023-01-23 04:44:13.197894: step: 1672/529, loss: 0.0002231597900390625
2023-01-23 04:44:14.351024: step: 1676/529, loss: -3.719329924933845e-06
2023-01-23 04:44:15.502015: step: 1680/529, loss: 0.0025533675216138363
2023-01-23 04:44:16.628575: step: 1684/529, loss: 9.975433931685984e-05
2023-01-23 04:44:17.764532: step: 1688/529, loss: 0.0004222869756631553
2023-01-23 04:44:18.896167: step: 1692/529, loss: 0.011151027865707874
2023-01-23 04:44:20.041067: step: 1696/529, loss: 0.00291023263707757
2023-01-23 04:44:21.160109: step: 1700/529, loss: 0.0002573966921772808
2023-01-23 04:44:22.297354: step: 1704/529, loss: 0.0005517005920410156
2023-01-23 04:44:23.444407: step: 1708/529, loss: 1.2874604180979077e-05
2023-01-23 04:44:24.564033: step: 1712/529, loss: 2.28881845032447e-06
2023-01-23 04:44:25.745482: step: 1716/529, loss: 0.02035699039697647
2023-01-23 04:44:26.854096: step: 1720/529, loss: -3.8146970382513246e-07
2023-01-23 04:44:27.988601: step: 1724/529, loss: 0.00012292862811591476
2023-01-23 04:44:29.116802: step: 1728/529, loss: 3.14712519866589e-06
2023-01-23 04:44:30.238156: step: 1732/529, loss: 6.351470801746473e-05
2023-01-23 04:44:31.371609: step: 1736/529, loss: 8.7738037109375e-05
2023-01-23 04:44:32.450110: step: 1740/529, loss: 1.8882752556237392e-05
2023-01-23 04:44:33.582430: step: 1744/529, loss: 8.239746239269152e-05
2023-01-23 04:44:34.716104: step: 1748/529, loss: 0.00829000398516655
2023-01-23 04:44:35.886547: step: 1752/529, loss: 0.0005329132545739412
2023-01-23 04:44:37.011379: step: 1756/529, loss: 0.08768520504236221
2023-01-23 04:44:38.160171: step: 1760/529, loss: 0.0005876541254110634
2023-01-23 04:44:39.296478: step: 1764/529, loss: 2.6321413315599784e-05
2023-01-23 04:44:40.443725: step: 1768/529, loss: 0.020531844347715378
2023-01-23 04:44:41.580814: step: 1772/529, loss: 0.00024600030155852437
2023-01-23 04:44:42.714938: step: 1776/529, loss: -6.580352874152595e-06
2023-01-23 04:44:43.861783: step: 1780/529, loss: 0.008731079287827015
2023-01-23 04:44:44.981559: step: 1784/529, loss: 0.0001260757417185232
2023-01-23 04:44:46.102311: step: 1788/529, loss: 1.3828278497385327e-05
2023-01-23 04:44:47.250023: step: 1792/529, loss: 0.0009692192543298006
2023-01-23 04:44:48.387000: step: 1796/529, loss: 0.0007339477888308465
2023-01-23 04:44:49.518344: step: 1800/529, loss: 0.006910133641213179
2023-01-23 04:44:50.681380: step: 1804/529, loss: 0.0007410050020553172
2023-01-23 04:44:51.817318: step: 1808/529, loss: 1.621246337890625e-05
2023-01-23 04:44:52.962331: step: 1812/529, loss: 6.2227250055002514e-06
2023-01-23 04:44:54.106279: step: 1816/529, loss: 0.000681972480379045
2023-01-23 04:44:55.280653: step: 1820/529, loss: 3.604888843256049e-05
2023-01-23 04:44:56.449362: step: 1824/529, loss: 0.00016946792311500758
2023-01-23 04:44:57.589184: step: 1828/529, loss: 2.632141149661038e-05
2023-01-23 04:44:58.732317: step: 1832/529, loss: 0.0004347801150288433
2023-01-23 04:44:59.875983: step: 1836/529, loss: 1.0633469173626509e-05
2023-01-23 04:45:01.020758: step: 1840/529, loss: 7.3432925091765355e-06
2023-01-23 04:45:02.140382: step: 1844/529, loss: 8.487701961712446e-06
2023-01-23 04:45:03.278588: step: 1848/529, loss: 1.6880036127986386e-05
2023-01-23 04:45:04.427167: step: 1852/529, loss: 0.013188933953642845
2023-01-23 04:45:05.596921: step: 1856/529, loss: 0.0029180527199059725
2023-01-23 04:45:06.738555: step: 1860/529, loss: 0.0033987045753747225
2023-01-23 04:45:07.859929: step: 1864/529, loss: 0.0032112121116369963
2023-01-23 04:45:09.006746: step: 1868/529, loss: 0.00013217926607467234
2023-01-23 04:45:10.115479: step: 1872/529, loss: 8.869170414982364e-06
2023-01-23 04:45:11.252545: step: 1876/529, loss: 0.04085225984454155
2023-01-23 04:45:12.403725: step: 1880/529, loss: 0.0005708694225177169
2023-01-23 04:45:13.540865: step: 1884/529, loss: 3.8623809814453125e-05
2023-01-23 04:45:14.689572: step: 1888/529, loss: 0.00015745163545943797
2023-01-23 04:45:15.810092: step: 1892/529, loss: 1.0490417707842425e-06
2023-01-23 04:45:16.943989: step: 1896/529, loss: 0.012462044134736061
2023-01-23 04:45:18.073853: step: 1900/529, loss: 0.0053730015642941
2023-01-23 04:45:19.211716: step: 1904/529, loss: 0.0001237869291799143
2023-01-23 04:45:20.338076: step: 1908/529, loss: 0.011725139804184437
2023-01-23 04:45:21.458538: step: 1912/529, loss: 0.01125650480389595
2023-01-23 04:45:22.575004: step: 1916/529, loss: 6.723403930664062e-05
2023-01-23 04:45:23.738466: step: 1920/529, loss: 0.04301281273365021
2023-01-23 04:45:24.889154: step: 1924/529, loss: 0.01636066474020481
2023-01-23 04:45:26.038922: step: 1928/529, loss: 0.000640058540739119
2023-01-23 04:45:27.244189: step: 1932/529, loss: 0.00029277801513671875
2023-01-23 04:45:28.407432: step: 1936/529, loss: 0.0030913352966308594
2023-01-23 04:45:29.594237: step: 1940/529, loss: 2.2602082026423886e-05
2023-01-23 04:45:30.742351: step: 1944/529, loss: 1.4591216313419864e-05
2023-01-23 04:45:31.902386: step: 1948/529, loss: 5.2738188969669864e-05
2023-01-23 04:45:33.047772: step: 1952/529, loss: 0.00028896331787109375
2023-01-23 04:45:34.194926: step: 1956/529, loss: 0.00011730194091796875
2023-01-23 04:45:35.317546: step: 1960/529, loss: 0.00019721985154319555
2023-01-23 04:45:36.466971: step: 1964/529, loss: 0.0011264801723882556
2023-01-23 04:45:37.590625: step: 1968/529, loss: 3.719329924933845e-06
2023-01-23 04:45:38.724520: step: 1972/529, loss: 0.00028676987858489156
2023-01-23 04:45:39.850009: step: 1976/529, loss: 8.487701052217744e-06
2023-01-23 04:45:40.992845: step: 1980/529, loss: 8.77380352903856e-06
2023-01-23 04:45:42.132485: step: 1984/529, loss: 0.00012969972158316523
2023-01-23 04:45:43.278193: step: 1988/529, loss: -1.716613724056515e-06
2023-01-23 04:45:44.407179: step: 1992/529, loss: 0.005074310582131147
2023-01-23 04:45:45.523100: step: 1996/529, loss: 1.6498564946232364e-05
2023-01-23 04:45:46.662605: step: 2000/529, loss: 0.00019345282635185868
2023-01-23 04:45:47.783338: step: 2004/529, loss: 1.850128137448337e-05
2023-01-23 04:45:48.948633: step: 2008/529, loss: 0.004309940617531538
2023-01-23 04:45:50.080924: step: 2012/529, loss: 0.0011140822898596525
2023-01-23 04:45:51.200984: step: 2016/529, loss: 0.00025830266531556845
2023-01-23 04:45:52.356285: step: 2020/529, loss: 0.02773265913128853
2023-01-23 04:45:53.492831: step: 2024/529, loss: 0.011422920972108841
2023-01-23 04:45:54.619970: step: 2028/529, loss: 5.435943603515625e-05
2023-01-23 04:45:55.767294: step: 2032/529, loss: 9.15527380129788e-06
2023-01-23 04:45:56.902595: step: 2036/529, loss: 0.0007202148553915322
2023-01-23 04:45:58.048198: step: 2040/529, loss: 0.0003040313604287803
2023-01-23 04:45:59.177731: step: 2044/529, loss: 0.003810310270637274
2023-01-23 04:46:00.302677: step: 2048/529, loss: 0.0016807556385174394
2023-01-23 04:46:01.445973: step: 2052/529, loss: 0.00011568069749046117
2023-01-23 04:46:02.602053: step: 2056/529, loss: 4.625320343620842e-06
2023-01-23 04:46:03.766059: step: 2060/529, loss: 0.007999802008271217
2023-01-23 04:46:04.924914: step: 2064/529, loss: 0.0006359100807458162
2023-01-23 04:46:06.078193: step: 2068/529, loss: 0.001352024031803012
2023-01-23 04:46:07.211316: step: 2072/529, loss: 0.08775339275598526
2023-01-23 04:46:08.376798: step: 2076/529, loss: 5.05924217577558e-05
2023-01-23 04:46:09.544851: step: 2080/529, loss: 0.0003522873157635331
2023-01-23 04:46:10.690028: step: 2084/529, loss: 0.01676921918988228
2023-01-23 04:46:11.809897: step: 2088/529, loss: 9.90867629298009e-05
2023-01-23 04:46:12.942780: step: 2092/529, loss: 0.00012645722017623484
2023-01-23 04:46:14.060271: step: 2096/529, loss: 0.06145744025707245
2023-01-23 04:46:15.202484: step: 2100/529, loss: 0.0030261995270848274
2023-01-23 04:46:16.383266: step: 2104/529, loss: 0.001667976495809853
2023-01-23 04:46:17.540732: step: 2108/529, loss: 0.00508427619934082
2023-01-23 04:46:18.625320: step: 2112/529, loss: 6.67572021484375e-06
2023-01-23 04:46:19.809133: step: 2116/529, loss: 0.0004968643188476562
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.6272824919441461, 'r': 0.7776298268974701, 'f1': 0.6944114149821642}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6351028216164515, 'r': 0.7694090382387022, 'f1': 0.6958344249410533}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
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': 29}
Russian: {'event': {'p': 0.46511627906976744, 'r': 0.5555555555555556, 'f1': 0.5063291139240507}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6096033402922756, 'r': 0.7776298268974701, 'f1': 0.6834406085430076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6149954001839927, 'r': 0.7746234067207416, 'f1': 0.6856410256410257}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6375, 'r': 0.9444444444444444, 'f1': 0.7611940298507462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6104944500504541, 'r': 0.8055925432756325, 'f1': 0.6946039035591274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Korean: {'event': {'p': 0.61996336996337, 'r': 0.7844727694090382, 'f1': 0.6925831202046036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6103092783505155, 'r': 0.7882822902796272, 'f1': 0.6879721092388147}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.6224677716390423, 'r': 0.7833140208574739, 'f1': 0.693689071318625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}