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 23:22:33.084311: step: 4/529, loss: 12.749869346618652
2023-01-22 23:22:34.297758: step: 8/529, loss: 15.06234359741211
2023-01-22 23:22:35.478012: step: 12/529, loss: 3.739328384399414
2023-01-22 23:22:36.650316: step: 16/529, loss: 3.6788172721862793
2023-01-22 23:22:37.850290: step: 20/529, loss: 4.1812567710876465
2023-01-22 23:22:39.004455: step: 24/529, loss: 3.3902077674865723
2023-01-22 23:22:40.196230: step: 28/529, loss: 12.677481651306152
2023-01-22 23:22:41.377742: step: 32/529, loss: 3.1846489906311035
2023-01-22 23:22:42.551805: step: 36/529, loss: 18.274188995361328
2023-01-22 23:22:43.723057: step: 40/529, loss: 2.864719867706299
2023-01-22 23:22:44.928981: step: 44/529, loss: 19.781169891357422
2023-01-22 23:22:46.128366: step: 48/529, loss: 8.725495338439941
2023-01-22 23:22:47.293197: step: 52/529, loss: 18.469144821166992
2023-01-22 23:22:48.456277: step: 56/529, loss: 2.492431163787842
2023-01-22 23:22:49.650140: step: 60/529, loss: 13.137426376342773
2023-01-22 23:22:50.857270: step: 64/529, loss: 18.803770065307617
2023-01-22 23:22:52.025281: step: 68/529, loss: 17.356889724731445
2023-01-22 23:22:53.222177: step: 72/529, loss: 6.832083225250244
2023-01-22 23:22:54.394061: step: 76/529, loss: 12.855040550231934
2023-01-22 23:22:55.568680: step: 80/529, loss: 4.13387393951416
2023-01-22 23:22:56.758368: step: 84/529, loss: 8.929308891296387
2023-01-22 23:22:57.940349: step: 88/529, loss: 8.180465698242188
2023-01-22 23:22:59.135529: step: 92/529, loss: 3.007103204727173
2023-01-22 23:23:00.295217: step: 96/529, loss: 3.807387113571167
2023-01-22 23:23:01.466072: step: 100/529, loss: 22.779010772705078
2023-01-22 23:23:02.726363: step: 104/529, loss: 12.340360641479492
2023-01-22 23:23:03.939635: step: 108/529, loss: 15.410866737365723
2023-01-22 23:23:05.121567: step: 112/529, loss: 20.466880798339844
2023-01-22 23:23:06.267494: step: 116/529, loss: 3.780665159225464
2023-01-22 23:23:07.463896: step: 120/529, loss: 2.9077563285827637
2023-01-22 23:23:08.720221: step: 124/529, loss: 21.12575340270996
2023-01-22 23:23:09.934791: step: 128/529, loss: 18.735261917114258
2023-01-22 23:23:11.140798: step: 132/529, loss: 24.76099395751953
2023-01-22 23:23:12.354866: step: 136/529, loss: 6.642233848571777
2023-01-22 23:23:13.537179: step: 140/529, loss: 7.240755081176758
2023-01-22 23:23:14.746422: step: 144/529, loss: 13.34777545928955
2023-01-22 23:23:15.912633: step: 148/529, loss: 12.940428733825684
2023-01-22 23:23:17.111094: step: 152/529, loss: 32.486122131347656
2023-01-22 23:23:18.292500: step: 156/529, loss: 11.29046630859375
2023-01-22 23:23:19.467247: step: 160/529, loss: 18.595088958740234
2023-01-22 23:23:20.655904: step: 164/529, loss: 22.335182189941406
2023-01-22 23:23:21.838040: step: 168/529, loss: 2.133139133453369
2023-01-22 23:23:23.011349: step: 172/529, loss: 4.195262908935547
2023-01-22 23:23:24.230414: step: 176/529, loss: 6.215989112854004
2023-01-22 23:23:25.442719: step: 180/529, loss: 12.389152526855469
2023-01-22 23:23:26.640102: step: 184/529, loss: 21.475690841674805
2023-01-22 23:23:27.856288: step: 188/529, loss: 6.198763847351074
2023-01-22 23:23:29.090328: step: 192/529, loss: 21.22145652770996
2023-01-22 23:23:30.313459: step: 196/529, loss: 4.188440322875977
2023-01-22 23:23:31.512300: step: 200/529, loss: 6.47695255279541
2023-01-22 23:23:32.688584: step: 204/529, loss: 2.6838021278381348
2023-01-22 23:23:33.867349: step: 208/529, loss: 2.681820869445801
2023-01-22 23:23:35.082717: step: 212/529, loss: 3.313990592956543
2023-01-22 23:23:36.322950: step: 216/529, loss: 8.061814308166504
2023-01-22 23:23:37.506535: step: 220/529, loss: 3.0597293376922607
2023-01-22 23:23:38.744295: step: 224/529, loss: 3.2819080352783203
2023-01-22 23:23:39.997691: step: 228/529, loss: 25.673660278320312
2023-01-22 23:23:41.192564: step: 232/529, loss: 17.186492919921875
2023-01-22 23:23:42.397719: step: 236/529, loss: 24.30300521850586
2023-01-22 23:23:43.619171: step: 240/529, loss: 25.181787490844727
2023-01-22 23:23:44.810421: step: 244/529, loss: 3.3175296783447266
2023-01-22 23:23:46.027276: step: 248/529, loss: 16.950958251953125
2023-01-22 23:23:47.219011: step: 252/529, loss: 16.225004196166992
2023-01-22 23:23:48.386162: step: 256/529, loss: 2.3727657794952393
2023-01-22 23:23:49.558498: step: 260/529, loss: 3.617187976837158
2023-01-22 23:23:50.811184: step: 264/529, loss: 12.824539184570312
2023-01-22 23:23:52.017833: step: 268/529, loss: 17.41595458984375
2023-01-22 23:23:53.257302: step: 272/529, loss: 3.492107629776001
2023-01-22 23:23:54.483426: step: 276/529, loss: 7.402348518371582
2023-01-22 23:23:55.660706: step: 280/529, loss: 2.952519655227661
2023-01-22 23:23:56.873386: step: 284/529, loss: 8.797836303710938
2023-01-22 23:23:58.102438: step: 288/529, loss: 14.972488403320312
2023-01-22 23:23:59.293995: step: 292/529, loss: 4.770545482635498
2023-01-22 23:24:00.472421: step: 296/529, loss: 9.256494522094727
2023-01-22 23:24:01.658664: step: 300/529, loss: 3.4210028648376465
2023-01-22 23:24:02.902035: step: 304/529, loss: 2.9110093116760254
2023-01-22 23:24:04.119014: step: 308/529, loss: 3.7728018760681152
2023-01-22 23:24:05.345754: step: 312/529, loss: 3.450716733932495
2023-01-22 23:24:06.538181: step: 316/529, loss: 12.856974601745605
2023-01-22 23:24:07.741872: step: 320/529, loss: 11.36719799041748
2023-01-22 23:24:08.988254: step: 324/529, loss: 3.657066583633423
2023-01-22 23:24:10.186842: step: 328/529, loss: 10.196720123291016
2023-01-22 23:24:11.352660: step: 332/529, loss: 4.825366020202637
2023-01-22 23:24:12.573585: step: 336/529, loss: 8.756556510925293
2023-01-22 23:24:13.779358: step: 340/529, loss: 17.305171966552734
2023-01-22 23:24:15.006338: step: 344/529, loss: 30.628881454467773
2023-01-22 23:24:16.183664: step: 348/529, loss: 2.285128593444824
2023-01-22 23:24:17.386144: step: 352/529, loss: 2.856727123260498
2023-01-22 23:24:18.578809: step: 356/529, loss: 15.390984535217285
2023-01-22 23:24:19.747200: step: 360/529, loss: 11.84009075164795
2023-01-22 23:24:20.931928: step: 364/529, loss: 2.512152671813965
2023-01-22 23:24:22.131336: step: 368/529, loss: 11.980447769165039
2023-01-22 23:24:23.344053: step: 372/529, loss: 10.839179039001465
2023-01-22 23:24:24.513787: step: 376/529, loss: 3.08955979347229
2023-01-22 23:24:25.709285: step: 380/529, loss: 21.360130310058594
2023-01-22 23:24:26.870687: step: 384/529, loss: 1.0728583335876465
2023-01-22 23:24:28.066863: step: 388/529, loss: 15.276307106018066
2023-01-22 23:24:29.239601: step: 392/529, loss: 17.153968811035156
2023-01-22 23:24:30.441898: step: 396/529, loss: 1.5041100978851318
2023-01-22 23:24:31.656578: step: 400/529, loss: 3.5005576610565186
2023-01-22 23:24:32.858250: step: 404/529, loss: 11.276963233947754
2023-01-22 23:24:34.065451: step: 408/529, loss: 6.307821273803711
2023-01-22 23:24:35.281634: step: 412/529, loss: 9.759897232055664
2023-01-22 23:24:36.476956: step: 416/529, loss: 10.426053047180176
2023-01-22 23:24:37.655794: step: 420/529, loss: 11.970014572143555
2023-01-22 23:24:38.851957: step: 424/529, loss: 4.747678756713867
2023-01-22 23:24:40.064467: step: 428/529, loss: 12.482945442199707
2023-01-22 23:24:41.269753: step: 432/529, loss: 17.28499984741211
2023-01-22 23:24:42.470868: step: 436/529, loss: 7.931006908416748
2023-01-22 23:24:43.632834: step: 440/529, loss: 4.634056568145752
2023-01-22 23:24:44.802844: step: 444/529, loss: 2.4623448848724365
2023-01-22 23:24:46.045526: step: 448/529, loss: 3.8997740745544434
2023-01-22 23:24:47.262033: step: 452/529, loss: 10.992735862731934
2023-01-22 23:24:48.474522: step: 456/529, loss: 3.3993771076202393
2023-01-22 23:24:49.667458: step: 460/529, loss: 2.355959892272949
2023-01-22 23:24:50.859526: step: 464/529, loss: 17.227130889892578
2023-01-22 23:24:52.081827: step: 468/529, loss: 3.8131279945373535
2023-01-22 23:24:53.283201: step: 472/529, loss: 1.347888469696045
2023-01-22 23:24:54.474427: step: 476/529, loss: 10.548364639282227
2023-01-22 23:24:55.669779: step: 480/529, loss: 2.078490972518921
2023-01-22 23:24:56.888006: step: 484/529, loss: 7.301095962524414
2023-01-22 23:24:58.079511: step: 488/529, loss: 12.59904670715332
2023-01-22 23:24:59.288889: step: 492/529, loss: 13.853641510009766
2023-01-22 23:25:00.524896: step: 496/529, loss: 5.629919052124023
2023-01-22 23:25:01.787848: step: 500/529, loss: 5.239670276641846
2023-01-22 23:25:02.940085: step: 504/529, loss: 4.342263698577881
2023-01-22 23:25:04.107890: step: 508/529, loss: 1.4194350242614746
2023-01-22 23:25:05.315705: step: 512/529, loss: 4.309412002563477
2023-01-22 23:25:06.527485: step: 516/529, loss: 6.315372943878174
2023-01-22 23:25:07.769952: step: 520/529, loss: 1.605266809463501
2023-01-22 23:25:08.958447: step: 524/529, loss: 1.7205760478973389
2023-01-22 23:25:10.180883: step: 528/529, loss: 4.640732765197754
2023-01-22 23:25:11.344537: step: 532/529, loss: 4.062249660491943
2023-01-22 23:25:12.543803: step: 536/529, loss: 0.7312127947807312
2023-01-22 23:25:13.716824: step: 540/529, loss: 1.187849760055542
2023-01-22 23:25:14.881621: step: 544/529, loss: 1.3783167600631714
2023-01-22 23:25:16.077695: step: 548/529, loss: 3.480274200439453
2023-01-22 23:25:17.278701: step: 552/529, loss: 1.71378755569458
2023-01-22 23:25:18.459019: step: 556/529, loss: 3.9147372245788574
2023-01-22 23:25:19.698248: step: 560/529, loss: 0.8801016211509705
2023-01-22 23:25:20.891755: step: 564/529, loss: 2.5718111991882324
2023-01-22 23:25:22.082309: step: 568/529, loss: 3.6981399059295654
2023-01-22 23:25:23.302033: step: 572/529, loss: 10.200998306274414
2023-01-22 23:25:24.500480: step: 576/529, loss: 0.8777449131011963
2023-01-22 23:25:25.676427: step: 580/529, loss: 1.061792016029358
2023-01-22 23:25:26.861203: step: 584/529, loss: 4.125081539154053
2023-01-22 23:25:28.077875: step: 588/529, loss: 0.5751572847366333
2023-01-22 23:25:29.283961: step: 592/529, loss: 0.34267377853393555
2023-01-22 23:25:30.475656: step: 596/529, loss: 0.7616095542907715
2023-01-22 23:25:31.614732: step: 600/529, loss: 1.309316635131836
2023-01-22 23:25:32.819507: step: 604/529, loss: 2.819707155227661
2023-01-22 23:25:34.080039: step: 608/529, loss: 4.250582218170166
2023-01-22 23:25:35.278721: step: 612/529, loss: 0.4889598786830902
2023-01-22 23:25:36.447135: step: 616/529, loss: 0.5848647952079773
2023-01-22 23:25:37.650731: step: 620/529, loss: 2.201519727706909
2023-01-22 23:25:38.843503: step: 624/529, loss: 1.4721647500991821
2023-01-22 23:25:40.016262: step: 628/529, loss: 0.5933083295822144
2023-01-22 23:25:41.191851: step: 632/529, loss: 6.337012767791748
2023-01-22 23:25:42.388551: step: 636/529, loss: 3.5360021591186523
2023-01-22 23:25:43.628232: step: 640/529, loss: 0.5196281671524048
2023-01-22 23:25:44.796231: step: 644/529, loss: 3.1214585304260254
2023-01-22 23:25:45.975602: step: 648/529, loss: 0.7267407178878784
2023-01-22 23:25:47.207610: step: 652/529, loss: 2.674508810043335
2023-01-22 23:25:48.399700: step: 656/529, loss: 0.6259007453918457
2023-01-22 23:25:49.591971: step: 660/529, loss: 1.703769564628601
2023-01-22 23:25:50.775968: step: 664/529, loss: 2.3324241638183594
2023-01-22 23:25:51.946568: step: 668/529, loss: 5.2529215812683105
2023-01-22 23:25:53.119039: step: 672/529, loss: 2.914316415786743
2023-01-22 23:25:54.287795: step: 676/529, loss: 3.5068469047546387
2023-01-22 23:25:55.483042: step: 680/529, loss: 0.3638465404510498
2023-01-22 23:25:56.700057: step: 684/529, loss: 1.2935245037078857
2023-01-22 23:25:57.895335: step: 688/529, loss: 2.0234553813934326
2023-01-22 23:25:59.060597: step: 692/529, loss: 0.3249831199645996
2023-01-22 23:26:00.280377: step: 696/529, loss: 0.5393751859664917
2023-01-22 23:26:01.451147: step: 700/529, loss: 1.056457757949829
2023-01-22 23:26:02.680325: step: 704/529, loss: 0.29491373896598816
2023-01-22 23:26:03.837242: step: 708/529, loss: 0.6376936435699463
2023-01-22 23:26:05.098409: step: 712/529, loss: 0.7085771560668945
2023-01-22 23:26:06.298658: step: 716/529, loss: 0.9203178882598877
2023-01-22 23:26:07.451072: step: 720/529, loss: 2.2862708568573
2023-01-22 23:26:08.684443: step: 724/529, loss: 1.162123441696167
2023-01-22 23:26:09.921591: step: 728/529, loss: 5.987920761108398
2023-01-22 23:26:11.111737: step: 732/529, loss: 1.1734355688095093
2023-01-22 23:26:12.286001: step: 736/529, loss: 0.4497973620891571
2023-01-22 23:26:13.467116: step: 740/529, loss: 4.0211100578308105
2023-01-22 23:26:14.697638: step: 744/529, loss: 3.999445676803589
2023-01-22 23:26:15.886695: step: 748/529, loss: 0.9228594899177551
2023-01-22 23:26:17.064898: step: 752/529, loss: 3.7844667434692383
2023-01-22 23:26:18.242380: step: 756/529, loss: 1.117471694946289
2023-01-22 23:26:19.446151: step: 760/529, loss: 0.5585752725601196
2023-01-22 23:26:20.614358: step: 764/529, loss: 3.0315425395965576
2023-01-22 23:26:21.838267: step: 768/529, loss: 0.6082629561424255
2023-01-22 23:26:23.021908: step: 772/529, loss: 1.1708859205245972
2023-01-22 23:26:24.193974: step: 776/529, loss: 1.9448699951171875
2023-01-22 23:26:25.358964: step: 780/529, loss: 1.0008831024169922
2023-01-22 23:26:26.567871: step: 784/529, loss: 0.40201902389526367
2023-01-22 23:26:27.743079: step: 788/529, loss: 0.5174985527992249
2023-01-22 23:26:28.931498: step: 792/529, loss: 0.4186003804206848
2023-01-22 23:26:30.127134: step: 796/529, loss: 0.17413930594921112
2023-01-22 23:26:31.305379: step: 800/529, loss: 0.8548687100410461
2023-01-22 23:26:32.463316: step: 804/529, loss: 0.6543086767196655
2023-01-22 23:26:33.660223: step: 808/529, loss: 1.0080170631408691
2023-01-22 23:26:34.859934: step: 812/529, loss: 0.7564957141876221
2023-01-22 23:26:36.028626: step: 816/529, loss: 0.8593447208404541
2023-01-22 23:26:37.234285: step: 820/529, loss: 1.6572167873382568
2023-01-22 23:26:38.465501: step: 824/529, loss: 0.639053463935852
2023-01-22 23:26:39.656207: step: 828/529, loss: 2.0464696884155273
2023-01-22 23:26:40.856244: step: 832/529, loss: 0.535546064376831
2023-01-22 23:26:42.048557: step: 836/529, loss: 2.7077503204345703
2023-01-22 23:26:43.230682: step: 840/529, loss: 0.6438050866127014
2023-01-22 23:26:44.409594: step: 844/529, loss: 0.9946825504302979
2023-01-22 23:26:45.598012: step: 848/529, loss: 0.47921955585479736
2023-01-22 23:26:46.762178: step: 852/529, loss: 1.7623847723007202
2023-01-22 23:26:47.981633: step: 856/529, loss: 2.768583297729492
2023-01-22 23:26:49.191746: step: 860/529, loss: 10.428298950195312
2023-01-22 23:26:50.397336: step: 864/529, loss: 6.824013710021973
2023-01-22 23:26:51.577504: step: 868/529, loss: 1.9721920490264893
2023-01-22 23:26:52.789849: step: 872/529, loss: 2.8358988761901855
2023-01-22 23:26:53.927204: step: 876/529, loss: 0.11737990379333496
2023-01-22 23:26:55.101084: step: 880/529, loss: 0.35182350873947144
2023-01-22 23:26:56.300162: step: 884/529, loss: 0.21775510907173157
2023-01-22 23:26:57.517710: step: 888/529, loss: 0.48986291885375977
2023-01-22 23:26:58.698230: step: 892/529, loss: 0.4439157247543335
2023-01-22 23:26:59.908340: step: 896/529, loss: 1.2020750045776367
2023-01-22 23:27:01.110672: step: 900/529, loss: 0.6157292723655701
2023-01-22 23:27:02.382304: step: 904/529, loss: 1.170060396194458
2023-01-22 23:27:03.543496: step: 908/529, loss: 0.5921035408973694
2023-01-22 23:27:04.777954: step: 912/529, loss: 1.0608599185943604
2023-01-22 23:27:05.978042: step: 916/529, loss: 2.3250577449798584
2023-01-22 23:27:07.183382: step: 920/529, loss: 5.517724990844727
2023-01-22 23:27:08.356863: step: 924/529, loss: 1.0833771228790283
2023-01-22 23:27:09.503575: step: 928/529, loss: 0.7859120965003967
2023-01-22 23:27:10.715183: step: 932/529, loss: 0.740260124206543
2023-01-22 23:27:11.906025: step: 936/529, loss: 0.5986397862434387
2023-01-22 23:27:13.090683: step: 940/529, loss: 2.626059055328369
2023-01-22 23:27:14.292975: step: 944/529, loss: 0.9404835104942322
2023-01-22 23:27:15.463364: step: 948/529, loss: 2.2421154975891113
2023-01-22 23:27:16.677284: step: 952/529, loss: 0.9911721348762512
2023-01-22 23:27:17.872087: step: 956/529, loss: 2.63169264793396
2023-01-22 23:27:19.102879: step: 960/529, loss: 0.5073085427284241
2023-01-22 23:27:20.277000: step: 964/529, loss: 2.324716329574585
2023-01-22 23:27:21.439454: step: 968/529, loss: 2.047309398651123
2023-01-22 23:27:22.637886: step: 972/529, loss: 4.869109153747559
2023-01-22 23:27:23.819645: step: 976/529, loss: 0.9011397957801819
2023-01-22 23:27:25.049189: step: 980/529, loss: 2.1416425704956055
2023-01-22 23:27:26.281173: step: 984/529, loss: 3.2345199584960938
2023-01-22 23:27:27.460764: step: 988/529, loss: 0.2511562705039978
2023-01-22 23:27:28.619847: step: 992/529, loss: 0.3559562861919403
2023-01-22 23:27:29.816483: step: 996/529, loss: 1.0940420627593994
2023-01-22 23:27:30.959043: step: 1000/529, loss: 1.4848049879074097
2023-01-22 23:27:32.111623: step: 1004/529, loss: 2.4509477615356445
2023-01-22 23:27:33.279242: step: 1008/529, loss: 1.0848877429962158
2023-01-22 23:27:34.498177: step: 1012/529, loss: 1.456751823425293
2023-01-22 23:27:35.683170: step: 1016/529, loss: 0.43307602405548096
2023-01-22 23:27:36.908083: step: 1020/529, loss: 1.3844835758209229
2023-01-22 23:27:38.085293: step: 1024/529, loss: 0.38100549578666687
2023-01-22 23:27:39.304238: step: 1028/529, loss: 0.9712100028991699
2023-01-22 23:27:40.509036: step: 1032/529, loss: 1.7322989702224731
2023-01-22 23:27:41.687396: step: 1036/529, loss: 1.124739170074463
2023-01-22 23:27:42.972778: step: 1040/529, loss: 0.41187784075737
2023-01-22 23:27:44.249528: step: 1044/529, loss: 1.361517071723938
2023-01-22 23:27:45.394884: step: 1048/529, loss: 1.112091064453125
2023-01-22 23:27:46.580221: step: 1052/529, loss: 0.3043155074119568
2023-01-22 23:27:47.800905: step: 1056/529, loss: 0.4209948778152466
2023-01-22 23:27:48.980347: step: 1060/529, loss: 0.9845127463340759
2023-01-22 23:27:50.171107: step: 1064/529, loss: 0.36977529525756836
2023-01-22 23:27:51.379601: step: 1068/529, loss: 0.7348709106445312
2023-01-22 23:27:52.587434: step: 1072/529, loss: 0.35695570707321167
2023-01-22 23:27:53.768926: step: 1076/529, loss: 2.1273000240325928
2023-01-22 23:27:54.995566: step: 1080/529, loss: 1.4644229412078857
2023-01-22 23:27:56.195649: step: 1084/529, loss: 0.829424262046814
2023-01-22 23:27:57.411093: step: 1088/529, loss: 0.5012081265449524
2023-01-22 23:27:58.604468: step: 1092/529, loss: 8.467086791992188
2023-01-22 23:27:59.818830: step: 1096/529, loss: 2.9554128646850586
2023-01-22 23:28:01.014346: step: 1100/529, loss: 0.7192343473434448
2023-01-22 23:28:02.221249: step: 1104/529, loss: 1.7786085605621338
2023-01-22 23:28:03.452311: step: 1108/529, loss: 0.4857497811317444
2023-01-22 23:28:04.623988: step: 1112/529, loss: 0.77387934923172
2023-01-22 23:28:05.789254: step: 1116/529, loss: 1.4289132356643677
2023-01-22 23:28:06.988770: step: 1120/529, loss: 0.43532103300094604
2023-01-22 23:28:08.167499: step: 1124/529, loss: 2.104881525039673
2023-01-22 23:28:09.397837: step: 1128/529, loss: 0.6311591267585754
2023-01-22 23:28:10.567428: step: 1132/529, loss: 2.038137912750244
2023-01-22 23:28:11.748950: step: 1136/529, loss: 1.050110101699829
2023-01-22 23:28:12.978832: step: 1140/529, loss: 1.4612703323364258
2023-01-22 23:28:14.153404: step: 1144/529, loss: 0.8107897043228149
2023-01-22 23:28:15.361573: step: 1148/529, loss: 2.7279953956604004
2023-01-22 23:28:16.562535: step: 1152/529, loss: 0.9125210642814636
2023-01-22 23:28:17.770691: step: 1156/529, loss: 0.7746531963348389
2023-01-22 23:28:19.056948: step: 1160/529, loss: 2.0470569133758545
2023-01-22 23:28:20.243316: step: 1164/529, loss: 2.166719436645508
2023-01-22 23:28:21.432097: step: 1168/529, loss: 6.890704154968262
2023-01-22 23:28:22.670898: step: 1172/529, loss: 1.9865775108337402
2023-01-22 23:28:23.855821: step: 1176/529, loss: 0.26850149035453796
2023-01-22 23:28:25.066490: step: 1180/529, loss: 0.5415112972259521
2023-01-22 23:28:26.281017: step: 1184/529, loss: 2.698915958404541
2023-01-22 23:28:27.434975: step: 1188/529, loss: 3.7939517498016357
2023-01-22 23:28:28.637983: step: 1192/529, loss: 0.6123003363609314
2023-01-22 23:28:29.798472: step: 1196/529, loss: 1.086844563484192
2023-01-22 23:28:30.999798: step: 1200/529, loss: 2.7950470447540283
2023-01-22 23:28:32.222490: step: 1204/529, loss: 1.1869001388549805
2023-01-22 23:28:33.415659: step: 1208/529, loss: 0.4582124948501587
2023-01-22 23:28:34.603849: step: 1212/529, loss: 1.6696866750717163
2023-01-22 23:28:35.799807: step: 1216/529, loss: 0.6265381574630737
2023-01-22 23:28:37.025736: step: 1220/529, loss: 0.604323148727417
2023-01-22 23:28:38.251101: step: 1224/529, loss: 3.478773593902588
2023-01-22 23:28:39.464578: step: 1228/529, loss: 0.2246539145708084
2023-01-22 23:28:40.631230: step: 1232/529, loss: 0.44249528646469116
2023-01-22 23:28:41.835801: step: 1236/529, loss: 1.106412410736084
2023-01-22 23:28:43.025670: step: 1240/529, loss: 0.1966862678527832
2023-01-22 23:28:44.180623: step: 1244/529, loss: 0.4916536509990692
2023-01-22 23:28:45.386552: step: 1248/529, loss: 7.338951110839844
2023-01-22 23:28:46.557563: step: 1252/529, loss: 0.18807964026927948
2023-01-22 23:28:47.765641: step: 1256/529, loss: 1.0040178298950195
2023-01-22 23:28:48.968274: step: 1260/529, loss: 0.4104175567626953
2023-01-22 23:28:50.184643: step: 1264/529, loss: 0.6464443206787109
2023-01-22 23:28:51.385928: step: 1268/529, loss: 1.4857327938079834
2023-01-22 23:28:52.556537: step: 1272/529, loss: 0.4584709107875824
2023-01-22 23:28:53.730894: step: 1276/529, loss: 0.2848011255264282
2023-01-22 23:28:54.934547: step: 1280/529, loss: 0.7101318836212158
2023-01-22 23:28:56.130715: step: 1284/529, loss: 0.8263359069824219
2023-01-22 23:28:57.353442: step: 1288/529, loss: 0.5674878358840942
2023-01-22 23:28:58.527353: step: 1292/529, loss: 0.4534398317337036
2023-01-22 23:28:59.720963: step: 1296/529, loss: 0.7932007312774658
2023-01-22 23:29:00.906135: step: 1300/529, loss: 0.3314913511276245
2023-01-22 23:29:02.073018: step: 1304/529, loss: 3.8802387714385986
2023-01-22 23:29:03.310515: step: 1308/529, loss: 0.36882850527763367
2023-01-22 23:29:04.508612: step: 1312/529, loss: 0.40705710649490356
2023-01-22 23:29:05.709181: step: 1316/529, loss: 0.439749538898468
2023-01-22 23:29:06.883848: step: 1320/529, loss: 0.7902179956436157
2023-01-22 23:29:08.093735: step: 1324/529, loss: 0.16738028824329376
2023-01-22 23:29:09.291105: step: 1328/529, loss: 0.39321136474609375
2023-01-22 23:29:10.528755: step: 1332/529, loss: 1.1230003833770752
2023-01-22 23:29:11.759631: step: 1336/529, loss: 2.9127755165100098
2023-01-22 23:29:12.970051: step: 1340/529, loss: 2.699781894683838
2023-01-22 23:29:14.135250: step: 1344/529, loss: 1.6985002756118774
2023-01-22 23:29:15.314508: step: 1348/529, loss: 1.84834623336792
2023-01-22 23:29:16.547182: step: 1352/529, loss: 3.946357250213623
2023-01-22 23:29:17.785366: step: 1356/529, loss: 0.4236244559288025
2023-01-22 23:29:18.992749: step: 1360/529, loss: 0.9585791826248169
2023-01-22 23:29:20.158095: step: 1364/529, loss: 1.753646969795227
2023-01-22 23:29:21.310785: step: 1368/529, loss: 0.43207404017448425
2023-01-22 23:29:22.493486: step: 1372/529, loss: 1.5062307119369507
2023-01-22 23:29:23.691978: step: 1376/529, loss: 0.12238531559705734
2023-01-22 23:29:24.856392: step: 1380/529, loss: 1.0887718200683594
2023-01-22 23:29:26.052470: step: 1384/529, loss: 0.5628679394721985
2023-01-22 23:29:27.267430: step: 1388/529, loss: 4.088003158569336
2023-01-22 23:29:28.472025: step: 1392/529, loss: 1.3439148664474487
2023-01-22 23:29:29.703395: step: 1396/529, loss: 1.5312730073928833
2023-01-22 23:29:30.898274: step: 1400/529, loss: 0.7861891984939575
2023-01-22 23:29:32.123312: step: 1404/529, loss: 0.25290799140930176
2023-01-22 23:29:33.339025: step: 1408/529, loss: 0.28866657614707947
2023-01-22 23:29:34.517542: step: 1412/529, loss: 0.42304468154907227
2023-01-22 23:29:35.694908: step: 1416/529, loss: 1.8015735149383545
2023-01-22 23:29:36.880694: step: 1420/529, loss: 2.2703049182891846
2023-01-22 23:29:38.055547: step: 1424/529, loss: 0.1433177888393402
2023-01-22 23:29:39.225695: step: 1428/529, loss: 0.2984890937805176
2023-01-22 23:29:40.437112: step: 1432/529, loss: 0.4579434394836426
2023-01-22 23:29:41.658709: step: 1436/529, loss: 1.3581758737564087
2023-01-22 23:29:42.829285: step: 1440/529, loss: 0.5189139246940613
2023-01-22 23:29:43.994225: step: 1444/529, loss: 0.43071165680885315
2023-01-22 23:29:45.197084: step: 1448/529, loss: 2.156521797180176
2023-01-22 23:29:46.445354: step: 1452/529, loss: 0.5254663228988647
2023-01-22 23:29:47.622619: step: 1456/529, loss: 1.1736807823181152
2023-01-22 23:29:48.798822: step: 1460/529, loss: 0.4148498475551605
2023-01-22 23:29:50.022445: step: 1464/529, loss: 0.8098351955413818
2023-01-22 23:29:51.174021: step: 1468/529, loss: 0.5285078287124634
2023-01-22 23:29:52.421210: step: 1472/529, loss: 0.3717874586582184
2023-01-22 23:29:53.583176: step: 1476/529, loss: 0.45098644495010376
2023-01-22 23:29:54.783486: step: 1480/529, loss: 0.9672597646713257
2023-01-22 23:29:56.009417: step: 1484/529, loss: 0.5948973894119263
2023-01-22 23:29:57.179406: step: 1488/529, loss: 0.47759419679641724
2023-01-22 23:29:58.381535: step: 1492/529, loss: 1.4880621433258057
2023-01-22 23:29:59.575938: step: 1496/529, loss: 0.18346476554870605
2023-01-22 23:30:00.816571: step: 1500/529, loss: 0.3813942074775696
2023-01-22 23:30:02.027022: step: 1504/529, loss: 1.7668808698654175
2023-01-22 23:30:03.224140: step: 1508/529, loss: 0.24518389999866486
2023-01-22 23:30:04.414495: step: 1512/529, loss: 0.26255813241004944
2023-01-22 23:30:05.595361: step: 1516/529, loss: 0.5573141574859619
2023-01-22 23:30:06.838221: step: 1520/529, loss: 2.8365182876586914
2023-01-22 23:30:08.032651: step: 1524/529, loss: 0.8681997656822205
2023-01-22 23:30:09.250638: step: 1528/529, loss: 0.3937135636806488
2023-01-22 23:30:10.434270: step: 1532/529, loss: 2.150111675262451
2023-01-22 23:30:11.631391: step: 1536/529, loss: 2.356813430786133
2023-01-22 23:30:12.821745: step: 1540/529, loss: 7.773714542388916
2023-01-22 23:30:14.007059: step: 1544/529, loss: 0.4997863173484802
2023-01-22 23:30:15.211025: step: 1548/529, loss: 0.2765703499317169
2023-01-22 23:30:16.431922: step: 1552/529, loss: 3.496220827102661
2023-01-22 23:30:17.636199: step: 1556/529, loss: 0.8893903493881226
2023-01-22 23:30:18.822262: step: 1560/529, loss: 0.4950907826423645
2023-01-22 23:30:20.003121: step: 1564/529, loss: 0.3308749198913574
2023-01-22 23:30:21.207684: step: 1568/529, loss: 0.3531980514526367
2023-01-22 23:30:22.386770: step: 1572/529, loss: 0.32358330488204956
2023-01-22 23:30:23.631735: step: 1576/529, loss: 1.8346972465515137
2023-01-22 23:30:24.836740: step: 1580/529, loss: 0.9833787679672241
2023-01-22 23:30:26.077574: step: 1584/529, loss: 0.31879687309265137
2023-01-22 23:30:27.302563: step: 1588/529, loss: 1.6434193849563599
2023-01-22 23:30:28.514971: step: 1592/529, loss: 0.46918296813964844
2023-01-22 23:30:29.720031: step: 1596/529, loss: 0.42517009377479553
2023-01-22 23:30:30.963656: step: 1600/529, loss: 0.6232078671455383
2023-01-22 23:30:32.123018: step: 1604/529, loss: 1.3762348890304565
2023-01-22 23:30:33.331449: step: 1608/529, loss: 1.7724915742874146
2023-01-22 23:30:34.503495: step: 1612/529, loss: 0.4551715850830078
2023-01-22 23:30:35.707174: step: 1616/529, loss: 2.9664227962493896
2023-01-22 23:30:36.891253: step: 1620/529, loss: 0.6250960826873779
2023-01-22 23:30:38.058235: step: 1624/529, loss: 0.12852254509925842
2023-01-22 23:30:39.300494: step: 1628/529, loss: 0.408147931098938
2023-01-22 23:30:40.475145: step: 1632/529, loss: 0.5588890314102173
2023-01-22 23:30:41.696859: step: 1636/529, loss: 0.3242533802986145
2023-01-22 23:30:42.853630: step: 1640/529, loss: 1.6165903806686401
2023-01-22 23:30:44.081717: step: 1644/529, loss: 0.3288017511367798
2023-01-22 23:30:45.299514: step: 1648/529, loss: 0.45196086168289185
2023-01-22 23:30:46.498130: step: 1652/529, loss: 0.8736375570297241
2023-01-22 23:30:47.706585: step: 1656/529, loss: 0.4038153290748596
2023-01-22 23:30:48.883502: step: 1660/529, loss: 1.762068271636963
2023-01-22 23:30:50.098180: step: 1664/529, loss: 1.0941978693008423
2023-01-22 23:30:51.323974: step: 1668/529, loss: 1.5832854509353638
2023-01-22 23:30:52.551119: step: 1672/529, loss: 1.5226056575775146
2023-01-22 23:30:53.709981: step: 1676/529, loss: 0.5419333577156067
2023-01-22 23:30:54.872201: step: 1680/529, loss: 0.2136530876159668
2023-01-22 23:30:56.077086: step: 1684/529, loss: 3.474647045135498
2023-01-22 23:30:57.282912: step: 1688/529, loss: 1.676355004310608
2023-01-22 23:30:58.494530: step: 1692/529, loss: 0.3030652105808258
2023-01-22 23:30:59.697772: step: 1696/529, loss: 0.5344671010971069
2023-01-22 23:31:00.893994: step: 1700/529, loss: 0.5074743628501892
2023-01-22 23:31:02.143402: step: 1704/529, loss: 0.30652475357055664
2023-01-22 23:31:03.328279: step: 1708/529, loss: 0.42206335067749023
2023-01-22 23:31:04.516011: step: 1712/529, loss: 0.6886497735977173
2023-01-22 23:31:05.706895: step: 1716/529, loss: 0.36699724197387695
2023-01-22 23:31:06.951130: step: 1720/529, loss: 0.5546180009841919
2023-01-22 23:31:08.170189: step: 1724/529, loss: 1.0773897171020508
2023-01-22 23:31:09.314065: step: 1728/529, loss: 0.47667115926742554
2023-01-22 23:31:10.496201: step: 1732/529, loss: 0.1742452085018158
2023-01-22 23:31:11.700845: step: 1736/529, loss: 0.48943957686424255
2023-01-22 23:31:12.881338: step: 1740/529, loss: 0.5446436405181885
2023-01-22 23:31:14.075787: step: 1744/529, loss: 3.94978666305542
2023-01-22 23:31:15.323052: step: 1748/529, loss: 1.9191770553588867
2023-01-22 23:31:16.541072: step: 1752/529, loss: 7.2219061851501465
2023-01-22 23:31:17.719410: step: 1756/529, loss: 0.9037526845932007
2023-01-22 23:31:18.897804: step: 1760/529, loss: 1.1580250263214111
2023-01-22 23:31:20.110945: step: 1764/529, loss: 0.5487180948257446
2023-01-22 23:31:21.285235: step: 1768/529, loss: 0.6091910004615784
2023-01-22 23:31:22.482556: step: 1772/529, loss: 0.5213258862495422
2023-01-22 23:31:23.672861: step: 1776/529, loss: 0.14984159171581268
2023-01-22 23:31:24.862010: step: 1780/529, loss: 0.5182837247848511
2023-01-22 23:31:26.062998: step: 1784/529, loss: 0.4881172180175781
2023-01-22 23:31:27.222422: step: 1788/529, loss: 1.3183894157409668
2023-01-22 23:31:28.436171: step: 1792/529, loss: 0.8680009841918945
2023-01-22 23:31:29.637873: step: 1796/529, loss: 0.9324303269386292
2023-01-22 23:31:30.854675: step: 1800/529, loss: 0.2602888345718384
2023-01-22 23:31:32.049164: step: 1804/529, loss: 1.0053061246871948
2023-01-22 23:31:33.221871: step: 1808/529, loss: 0.6792802810668945
2023-01-22 23:31:34.390672: step: 1812/529, loss: 0.9812270998954773
2023-01-22 23:31:35.595738: step: 1816/529, loss: 0.8634405732154846
2023-01-22 23:31:36.802982: step: 1820/529, loss: 1.580744743347168
2023-01-22 23:31:38.016964: step: 1824/529, loss: 0.3972037732601166
2023-01-22 23:31:39.230151: step: 1828/529, loss: 0.5509463548660278
2023-01-22 23:31:40.427534: step: 1832/529, loss: 0.16157567501068115
2023-01-22 23:31:41.598731: step: 1836/529, loss: 1.9963773488998413
2023-01-22 23:31:42.789606: step: 1840/529, loss: 1.3623301982879639
2023-01-22 23:31:43.967345: step: 1844/529, loss: 0.1316138356924057
2023-01-22 23:31:45.193064: step: 1848/529, loss: 0.5144818425178528
2023-01-22 23:31:46.387852: step: 1852/529, loss: 0.579322338104248
2023-01-22 23:31:47.578783: step: 1856/529, loss: 2.6421186923980713
2023-01-22 23:31:48.770036: step: 1860/529, loss: 3.7761054039001465
2023-01-22 23:31:49.983710: step: 1864/529, loss: 0.9291985630989075
2023-01-22 23:31:51.212803: step: 1868/529, loss: 0.21208734810352325
2023-01-22 23:31:52.376280: step: 1872/529, loss: 6.948488712310791
2023-01-22 23:31:53.544220: step: 1876/529, loss: 0.29366040229797363
2023-01-22 23:31:54.744613: step: 1880/529, loss: 1.0625988245010376
2023-01-22 23:31:55.905640: step: 1884/529, loss: 0.9475798606872559
2023-01-22 23:31:57.087401: step: 1888/529, loss: 0.20837651193141937
2023-01-22 23:31:58.285746: step: 1892/529, loss: 1.3488779067993164
2023-01-22 23:31:59.509050: step: 1896/529, loss: 0.2797640562057495
2023-01-22 23:32:00.715342: step: 1900/529, loss: 1.3218498229980469
2023-01-22 23:32:01.924050: step: 1904/529, loss: 0.5894363522529602
2023-01-22 23:32:03.139362: step: 1908/529, loss: 1.4543956518173218
2023-01-22 23:32:04.294287: step: 1912/529, loss: 0.4089512825012207
2023-01-22 23:32:05.481799: step: 1916/529, loss: 3.1534934043884277
2023-01-22 23:32:06.633152: step: 1920/529, loss: 0.39066389203071594
2023-01-22 23:32:07.817742: step: 1924/529, loss: 0.8841107487678528
2023-01-22 23:32:09.076574: step: 1928/529, loss: 0.5840445756912231
2023-01-22 23:32:10.322154: step: 1932/529, loss: 3.8740904331207275
2023-01-22 23:32:11.545484: step: 1936/529, loss: 1.0114915370941162
2023-01-22 23:32:12.805543: step: 1940/529, loss: 0.9592664837837219
2023-01-22 23:32:14.025067: step: 1944/529, loss: 0.6349629163742065
2023-01-22 23:32:15.254983: step: 1948/529, loss: 0.7871348261833191
2023-01-22 23:32:16.438446: step: 1952/529, loss: 3.2203218936920166
2023-01-22 23:32:17.641131: step: 1956/529, loss: 0.26926127076148987
2023-01-22 23:32:18.830948: step: 1960/529, loss: 0.09062681347131729
2023-01-22 23:32:20.030492: step: 1964/529, loss: 0.575076699256897
2023-01-22 23:32:21.235197: step: 1968/529, loss: 0.22789162397384644
2023-01-22 23:32:22.396813: step: 1972/529, loss: 0.9957990050315857
2023-01-22 23:32:23.577044: step: 1976/529, loss: 0.19148635864257812
2023-01-22 23:32:24.766059: step: 1980/529, loss: 0.3897726237773895
2023-01-22 23:32:25.989267: step: 1984/529, loss: 0.4202050566673279
2023-01-22 23:32:27.178699: step: 1988/529, loss: 1.2259410619735718
2023-01-22 23:32:28.370619: step: 1992/529, loss: 1.153421401977539
2023-01-22 23:32:29.567279: step: 1996/529, loss: 0.9048040509223938
2023-01-22 23:32:30.747071: step: 2000/529, loss: 0.8668357729911804
2023-01-22 23:32:31.952072: step: 2004/529, loss: 1.147754430770874
2023-01-22 23:32:33.168812: step: 2008/529, loss: 0.3463985025882721
2023-01-22 23:32:34.356685: step: 2012/529, loss: 0.4243202805519104
2023-01-22 23:32:35.567595: step: 2016/529, loss: 2.1583595275878906
2023-01-22 23:32:36.758136: step: 2020/529, loss: 0.2030327320098877
2023-01-22 23:32:37.962684: step: 2024/529, loss: 1.4683680534362793
2023-01-22 23:32:39.208335: step: 2028/529, loss: 0.38081997632980347
2023-01-22 23:32:40.391810: step: 2032/529, loss: 0.27679815888404846
2023-01-22 23:32:41.595748: step: 2036/529, loss: 1.3873214721679688
2023-01-22 23:32:42.788472: step: 2040/529, loss: 0.5157045125961304
2023-01-22 23:32:44.002671: step: 2044/529, loss: 1.4614315032958984
2023-01-22 23:32:45.229841: step: 2048/529, loss: 0.8679043054580688
2023-01-22 23:32:46.427065: step: 2052/529, loss: 0.2709521949291229
2023-01-22 23:32:47.588497: step: 2056/529, loss: 0.2642352283000946
2023-01-22 23:32:48.769024: step: 2060/529, loss: 1.4407376050949097
2023-01-22 23:32:49.996825: step: 2064/529, loss: 0.4164312481880188
2023-01-22 23:32:51.186362: step: 2068/529, loss: 0.34282445907592773
2023-01-22 23:32:52.383245: step: 2072/529, loss: 0.7626917958259583
2023-01-22 23:32:53.621241: step: 2076/529, loss: 2.033196449279785
2023-01-22 23:32:54.888621: step: 2080/529, loss: 3.6910836696624756
2023-01-22 23:32:56.141513: step: 2084/529, loss: 0.5010618567466736
2023-01-22 23:32:57.349868: step: 2088/529, loss: 0.6785228848457336
2023-01-22 23:32:58.552430: step: 2092/529, loss: 0.3297010064125061
2023-01-22 23:32:59.740237: step: 2096/529, loss: 0.8777534365653992
2023-01-22 23:33:00.966264: step: 2100/529, loss: 0.5245559215545654
2023-01-22 23:33:02.173097: step: 2104/529, loss: 2.2352466583251953
2023-01-22 23:33:03.399437: step: 2108/529, loss: 0.39593085646629333
2023-01-22 23:33:04.578124: step: 2112/529, loss: 0.20904827117919922
2023-01-22 23:33:05.780750: step: 2116/529, loss: 0.5683928728103638
==================================================
Loss: 3.433
--------------------
Dev: {'event': {'p': 0.5544692737430168, 'r': 0.5286284953395473, 'f1': 0.5412406271301976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.4727408513816281, 'r': 0.3792690233672858, 'f1': 0.4208776595744681}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5, 'r': 0.4074074074074074, 'f1': 0.44897959183673464}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.7307692307692307, 'r': 0.30158730158730157, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.47058823529411764, 'r': 0.2222222222222222, 'f1': 0.3018867924528302}, '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': 0.5544692737430168, 'r': 0.5286284953395473, 'f1': 0.5412406271301976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.4727408513816281, 'r': 0.3792690233672858, 'f1': 0.4208776595744681}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5, 'r': 0.4074074074074074, 'f1': 0.44897959183673464}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5544692737430168, 'r': 0.5286284953395473, 'f1': 0.5412406271301976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.4727408513816281, 'r': 0.3792690233672858, 'f1': 0.4208776595744681}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.7307692307692307, 'r': 0.30158730158730157, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5544692737430168, 'r': 0.5286284953395473, 'f1': 0.5412406271301976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.4727408513816281, 'r': 0.3792690233672858, 'f1': 0.4208776595744681}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.47058823529411764, 'r': 0.2222222222222222, 'f1': 0.3018867924528302}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:34:12.007777: step: 4/529, loss: 0.5469247102737427
2023-01-22 23:34:13.207962: step: 8/529, loss: 0.29029884934425354
2023-01-22 23:34:14.421481: step: 12/529, loss: 2.2856011390686035
2023-01-22 23:34:15.577002: step: 16/529, loss: 0.26024913787841797
2023-01-22 23:34:16.754140: step: 20/529, loss: 0.2523704171180725
2023-01-22 23:34:17.968329: step: 24/529, loss: 0.7009915709495544
2023-01-22 23:34:19.139072: step: 28/529, loss: 0.6086962819099426
2023-01-22 23:34:20.381890: step: 32/529, loss: 1.2982348203659058
2023-01-22 23:34:21.544594: step: 36/529, loss: 1.8348171710968018
2023-01-22 23:34:22.723220: step: 40/529, loss: 0.47031474113464355
2023-01-22 23:34:23.919584: step: 44/529, loss: 0.9115546941757202
2023-01-22 23:34:25.109299: step: 48/529, loss: 0.38211649656295776
2023-01-22 23:34:26.292452: step: 52/529, loss: 0.13293424248695374
2023-01-22 23:34:27.525820: step: 56/529, loss: 0.26782137155532837
2023-01-22 23:34:28.746906: step: 60/529, loss: 0.33807554841041565
2023-01-22 23:34:29.980661: step: 64/529, loss: 0.5734786987304688
2023-01-22 23:34:31.161257: step: 68/529, loss: 0.2140342742204666
2023-01-22 23:34:32.312213: step: 72/529, loss: 0.21558427810668945
2023-01-22 23:34:33.532756: step: 76/529, loss: 0.17573431134223938
2023-01-22 23:34:34.693533: step: 80/529, loss: 0.955725908279419
2023-01-22 23:34:35.923141: step: 84/529, loss: 0.5600137710571289
2023-01-22 23:34:37.101185: step: 88/529, loss: 0.39307862520217896
2023-01-22 23:34:38.339373: step: 92/529, loss: 0.8976966738700867
2023-01-22 23:34:39.536779: step: 96/529, loss: 0.7666264176368713
2023-01-22 23:34:40.723043: step: 100/529, loss: 0.31468749046325684
2023-01-22 23:34:41.945416: step: 104/529, loss: 0.6417840123176575
2023-01-22 23:34:43.129899: step: 108/529, loss: 0.30608415603637695
2023-01-22 23:34:44.338154: step: 112/529, loss: 2.5712764263153076
2023-01-22 23:34:45.636798: step: 116/529, loss: 0.40532737970352173
2023-01-22 23:34:46.823852: step: 120/529, loss: 0.3818085789680481
2023-01-22 23:34:48.034853: step: 124/529, loss: 0.28497064113616943
2023-01-22 23:34:49.251433: step: 128/529, loss: 0.6045374274253845
2023-01-22 23:34:50.430670: step: 132/529, loss: 0.35619086027145386
2023-01-22 23:34:51.612235: step: 136/529, loss: 0.13047190010547638
2023-01-22 23:34:52.840338: step: 140/529, loss: 1.2081345319747925
2023-01-22 23:34:54.052458: step: 144/529, loss: 1.1790626049041748
2023-01-22 23:34:55.243996: step: 148/529, loss: 1.0163335800170898
2023-01-22 23:34:56.443321: step: 152/529, loss: 1.6506152153015137
2023-01-22 23:34:57.639694: step: 156/529, loss: 0.5505706071853638
2023-01-22 23:34:58.845907: step: 160/529, loss: 0.4442530870437622
2023-01-22 23:35:00.036994: step: 164/529, loss: 0.21369346976280212
2023-01-22 23:35:01.236854: step: 168/529, loss: 0.2938529849052429
2023-01-22 23:35:02.387210: step: 172/529, loss: 0.1406106948852539
2023-01-22 23:35:03.566018: step: 176/529, loss: 0.2674335539340973
2023-01-22 23:35:04.752168: step: 180/529, loss: 0.7235414385795593
2023-01-22 23:35:05.964866: step: 184/529, loss: 0.2027774453163147
2023-01-22 23:35:07.175272: step: 188/529, loss: 2.71345591545105
2023-01-22 23:35:08.426353: step: 192/529, loss: 1.8358243703842163
2023-01-22 23:35:09.645172: step: 196/529, loss: 1.1490973234176636
2023-01-22 23:35:10.856019: step: 200/529, loss: 0.7929194569587708
2023-01-22 23:35:12.058603: step: 204/529, loss: 0.24325361847877502
2023-01-22 23:35:13.255550: step: 208/529, loss: 0.8279992341995239
2023-01-22 23:35:14.480682: step: 212/529, loss: 1.5655983686447144
2023-01-22 23:35:15.681754: step: 216/529, loss: 0.5837101936340332
2023-01-22 23:35:16.869495: step: 220/529, loss: 0.2387804090976715
2023-01-22 23:35:18.056486: step: 224/529, loss: 0.9586046934127808
2023-01-22 23:35:19.248122: step: 228/529, loss: 1.573075294494629
2023-01-22 23:35:20.435106: step: 232/529, loss: 0.8786381483078003
2023-01-22 23:35:21.619908: step: 236/529, loss: 0.30920690298080444
2023-01-22 23:35:22.883841: step: 240/529, loss: 0.8637639284133911
2023-01-22 23:35:24.063718: step: 244/529, loss: 1.4042590856552124
2023-01-22 23:35:25.226459: step: 248/529, loss: 0.7386443614959717
2023-01-22 23:35:26.414047: step: 252/529, loss: 0.8712807893753052
2023-01-22 23:35:27.584803: step: 256/529, loss: 0.4034702777862549
2023-01-22 23:35:28.811749: step: 260/529, loss: 0.3156128525733948
2023-01-22 23:35:30.046638: step: 264/529, loss: 0.7282426357269287
2023-01-22 23:35:31.270040: step: 268/529, loss: 0.10016379505395889
2023-01-22 23:35:32.494716: step: 272/529, loss: 0.3434237539768219
2023-01-22 23:35:33.683376: step: 276/529, loss: 0.30866673588752747
2023-01-22 23:35:34.889910: step: 280/529, loss: 0.130573570728302
2023-01-22 23:35:36.126177: step: 284/529, loss: 1.5664870738983154
2023-01-22 23:35:37.295159: step: 288/529, loss: 0.7725616693496704
2023-01-22 23:35:38.507594: step: 292/529, loss: 0.2995683550834656
2023-01-22 23:35:39.742038: step: 296/529, loss: 0.28513187170028687
2023-01-22 23:35:41.029315: step: 300/529, loss: 8.51626968383789
2023-01-22 23:35:42.228598: step: 304/529, loss: 1.3881690502166748
2023-01-22 23:35:43.401610: step: 308/529, loss: 0.319705605506897
2023-01-22 23:35:44.609230: step: 312/529, loss: 0.7271748781204224
2023-01-22 23:35:45.804001: step: 316/529, loss: 0.39506995677948
2023-01-22 23:35:47.016648: step: 320/529, loss: 1.8276278972625732
2023-01-22 23:35:48.198591: step: 324/529, loss: 0.4516967833042145
2023-01-22 23:35:49.365673: step: 328/529, loss: 0.7862209677696228
2023-01-22 23:35:50.564492: step: 332/529, loss: 0.7785571813583374
2023-01-22 23:35:51.771858: step: 336/529, loss: 0.9727303981781006
2023-01-22 23:35:52.955928: step: 340/529, loss: 2.3505945205688477
2023-01-22 23:35:54.115052: step: 344/529, loss: 0.4268733263015747
2023-01-22 23:35:55.312689: step: 348/529, loss: 0.4842044711112976
2023-01-22 23:35:56.513420: step: 352/529, loss: 0.08876566588878632
2023-01-22 23:35:57.712736: step: 356/529, loss: 0.8700810670852661
2023-01-22 23:35:58.915485: step: 360/529, loss: 0.7326598167419434
2023-01-22 23:36:00.115359: step: 364/529, loss: 0.4604230225086212
2023-01-22 23:36:01.348306: step: 368/529, loss: 0.29568353295326233
2023-01-22 23:36:02.506872: step: 372/529, loss: 0.6302188634872437
2023-01-22 23:36:03.669722: step: 376/529, loss: 0.6179839372634888
2023-01-22 23:36:04.849430: step: 380/529, loss: 0.2163233757019043
2023-01-22 23:36:06.073712: step: 384/529, loss: 1.1559795141220093
2023-01-22 23:36:07.271774: step: 388/529, loss: 1.140015721321106
2023-01-22 23:36:08.455661: step: 392/529, loss: 0.9983171224594116
2023-01-22 23:36:09.663322: step: 396/529, loss: 0.29577934741973877
2023-01-22 23:36:10.876406: step: 400/529, loss: 0.16053524613380432
2023-01-22 23:36:12.070569: step: 404/529, loss: 0.29787904024124146
2023-01-22 23:36:13.250981: step: 408/529, loss: 8.647085189819336
2023-01-22 23:36:14.432019: step: 412/529, loss: 0.2223643809556961
2023-01-22 23:36:15.627570: step: 416/529, loss: 0.5561660528182983
2023-01-22 23:36:16.864019: step: 420/529, loss: 0.4473477602005005
2023-01-22 23:36:18.043131: step: 424/529, loss: 0.18202051520347595
2023-01-22 23:36:19.223837: step: 428/529, loss: 0.3774683177471161
2023-01-22 23:36:20.427816: step: 432/529, loss: 1.8667852878570557
2023-01-22 23:36:21.678972: step: 436/529, loss: 0.22732192277908325
2023-01-22 23:36:22.901440: step: 440/529, loss: 1.1841437816619873
2023-01-22 23:36:24.122257: step: 444/529, loss: 0.7162110805511475
2023-01-22 23:36:25.315909: step: 448/529, loss: 0.19190216064453125
2023-01-22 23:36:26.489980: step: 452/529, loss: 0.13999691605567932
2023-01-22 23:36:27.669942: step: 456/529, loss: 0.7005730271339417
2023-01-22 23:36:28.875351: step: 460/529, loss: 1.731724500656128
2023-01-22 23:36:30.067107: step: 464/529, loss: 0.2750546336174011
2023-01-22 23:36:31.256937: step: 468/529, loss: 1.6575648784637451
2023-01-22 23:36:32.441533: step: 472/529, loss: 0.2552250921726227
2023-01-22 23:36:33.646124: step: 476/529, loss: 1.4123848676681519
2023-01-22 23:36:34.874195: step: 480/529, loss: 1.641983985900879
2023-01-22 23:36:36.047280: step: 484/529, loss: 0.21824704110622406
2023-01-22 23:36:37.237239: step: 488/529, loss: 0.4703761339187622
2023-01-22 23:36:38.414892: step: 492/529, loss: 0.29395991563796997
2023-01-22 23:36:39.593873: step: 496/529, loss: 0.3383379578590393
2023-01-22 23:36:40.808104: step: 500/529, loss: 0.40370863676071167
2023-01-22 23:36:41.982850: step: 504/529, loss: 0.9405983090400696
2023-01-22 23:36:43.204401: step: 508/529, loss: 0.6169747114181519
2023-01-22 23:36:44.401295: step: 512/529, loss: 1.9449288845062256
2023-01-22 23:36:45.555167: step: 516/529, loss: 0.20881938934326172
2023-01-22 23:36:46.746665: step: 520/529, loss: 0.22269250452518463
2023-01-22 23:36:47.924494: step: 524/529, loss: 0.4363614320755005
2023-01-22 23:36:49.106809: step: 528/529, loss: 0.11099929362535477
2023-01-22 23:36:50.322573: step: 532/529, loss: 0.24352195858955383
2023-01-22 23:36:51.509610: step: 536/529, loss: 0.4304102957248688
2023-01-22 23:36:52.725796: step: 540/529, loss: 0.8257529735565186
2023-01-22 23:36:53.886439: step: 544/529, loss: 0.261637419462204
2023-01-22 23:36:55.213491: step: 548/529, loss: 1.3856748342514038
2023-01-22 23:36:56.427550: step: 552/529, loss: 0.07403989136219025
2023-01-22 23:36:57.593740: step: 556/529, loss: 0.1703689694404602
2023-01-22 23:36:58.816815: step: 560/529, loss: 0.32421523332595825
2023-01-22 23:37:00.044096: step: 564/529, loss: 0.3813760280609131
2023-01-22 23:37:01.282587: step: 568/529, loss: 2.0316994190216064
2023-01-22 23:37:02.468116: step: 572/529, loss: 0.6919819712638855
2023-01-22 23:37:03.717960: step: 576/529, loss: 0.2741979658603668
2023-01-22 23:37:04.902025: step: 580/529, loss: 0.18556852638721466
2023-01-22 23:37:06.100721: step: 584/529, loss: 3.65915584564209
2023-01-22 23:37:07.281391: step: 588/529, loss: 2.030156135559082
2023-01-22 23:37:08.465664: step: 592/529, loss: 0.41374799609184265
2023-01-22 23:37:09.654281: step: 596/529, loss: 1.6483994722366333
2023-01-22 23:37:10.885517: step: 600/529, loss: 0.37363871932029724
2023-01-22 23:37:12.063602: step: 604/529, loss: 0.2248472273349762
2023-01-22 23:37:13.291298: step: 608/529, loss: 0.4030396342277527
2023-01-22 23:37:14.529913: step: 612/529, loss: 0.703781008720398
2023-01-22 23:37:15.790194: step: 616/529, loss: 0.8241526484489441
2023-01-22 23:37:16.973646: step: 620/529, loss: 1.5269960165023804
2023-01-22 23:37:18.166182: step: 624/529, loss: 0.3522728979587555
2023-01-22 23:37:19.356671: step: 628/529, loss: 0.10946894437074661
2023-01-22 23:37:20.562492: step: 632/529, loss: 0.14697766304016113
2023-01-22 23:37:21.754891: step: 636/529, loss: 0.795026957988739
2023-01-22 23:37:22.946549: step: 640/529, loss: 0.2673977017402649
2023-01-22 23:37:24.114407: step: 644/529, loss: 1.2692445516586304
2023-01-22 23:37:25.311576: step: 648/529, loss: 1.2542775869369507
2023-01-22 23:37:26.515346: step: 652/529, loss: 2.4184679985046387
2023-01-22 23:37:27.716732: step: 656/529, loss: 0.8977761268615723
2023-01-22 23:37:28.888030: step: 660/529, loss: 0.1103479415178299
2023-01-22 23:37:30.147993: step: 664/529, loss: 7.595412254333496
2023-01-22 23:37:31.356060: step: 668/529, loss: 2.7754533290863037
2023-01-22 23:37:32.550688: step: 672/529, loss: 1.4375044107437134
2023-01-22 23:37:33.761582: step: 676/529, loss: 0.2556249499320984
2023-01-22 23:37:34.980086: step: 680/529, loss: 8.585527420043945
2023-01-22 23:37:36.195277: step: 684/529, loss: 0.3497764766216278
2023-01-22 23:37:37.381471: step: 688/529, loss: 0.8973914384841919
2023-01-22 23:37:38.612779: step: 692/529, loss: 7.146213054656982
2023-01-22 23:37:39.782434: step: 696/529, loss: 0.44740742444992065
2023-01-22 23:37:40.965937: step: 700/529, loss: 0.4297164976596832
2023-01-22 23:37:42.182807: step: 704/529, loss: 0.2591429352760315
2023-01-22 23:37:43.343014: step: 708/529, loss: 0.08609075844287872
2023-01-22 23:37:44.553516: step: 712/529, loss: 0.29313117265701294
2023-01-22 23:37:45.729069: step: 716/529, loss: 0.40758365392684937
2023-01-22 23:37:46.916537: step: 720/529, loss: 0.20712977647781372
2023-01-22 23:37:48.161309: step: 724/529, loss: 0.4123830795288086
2023-01-22 23:37:49.329280: step: 728/529, loss: 2.760382652282715
2023-01-22 23:37:50.506846: step: 732/529, loss: 0.32448187470436096
2023-01-22 23:37:51.680890: step: 736/529, loss: 0.24875859916210175
2023-01-22 23:37:52.884354: step: 740/529, loss: 2.406853675842285
2023-01-22 23:37:54.037171: step: 744/529, loss: 0.7407734990119934
2023-01-22 23:37:55.246908: step: 748/529, loss: 1.4668359756469727
2023-01-22 23:37:56.437780: step: 752/529, loss: 0.8690974712371826
2023-01-22 23:37:57.589430: step: 756/529, loss: 2.563384532928467
2023-01-22 23:37:58.766376: step: 760/529, loss: 1.0204862356185913
2023-01-22 23:37:59.993269: step: 764/529, loss: 0.36617690324783325
2023-01-22 23:38:01.198106: step: 768/529, loss: 0.5697610974311829
2023-01-22 23:38:02.392024: step: 772/529, loss: 0.23933817446231842
2023-01-22 23:38:03.594904: step: 776/529, loss: 0.2333511859178543
2023-01-22 23:38:04.798038: step: 780/529, loss: 0.5242372751235962
2023-01-22 23:38:05.997043: step: 784/529, loss: 0.5164096355438232
2023-01-22 23:38:07.181919: step: 788/529, loss: 0.3202282786369324
2023-01-22 23:38:08.370971: step: 792/529, loss: 1.4534978866577148
2023-01-22 23:38:09.594768: step: 796/529, loss: 0.8111439943313599
2023-01-22 23:38:10.797159: step: 800/529, loss: 0.34762126207351685
2023-01-22 23:38:12.026693: step: 804/529, loss: 0.4840986430644989
2023-01-22 23:38:13.184265: step: 808/529, loss: 0.6049836874008179
2023-01-22 23:38:14.390261: step: 812/529, loss: 0.23891717195510864
2023-01-22 23:38:15.607228: step: 816/529, loss: 0.5742517709732056
2023-01-22 23:38:16.844243: step: 820/529, loss: 0.33200645446777344
2023-01-22 23:38:17.998874: step: 824/529, loss: 0.2666700482368469
2023-01-22 23:38:19.258827: step: 828/529, loss: 2.03470516204834
2023-01-22 23:38:20.500474: step: 832/529, loss: 6.3137359619140625
2023-01-22 23:38:21.708282: step: 836/529, loss: 2.77896785736084
2023-01-22 23:38:22.914398: step: 840/529, loss: 0.08535037189722061
2023-01-22 23:38:24.092348: step: 844/529, loss: 0.9909968972206116
2023-01-22 23:38:25.292468: step: 848/529, loss: 1.377442717552185
2023-01-22 23:38:26.480107: step: 852/529, loss: 0.8108502626419067
2023-01-22 23:38:27.694570: step: 856/529, loss: 0.8727612495422363
2023-01-22 23:38:28.905588: step: 860/529, loss: 0.20590420067310333
2023-01-22 23:38:30.079096: step: 864/529, loss: 0.1079469695687294
2023-01-22 23:38:31.256349: step: 868/529, loss: 0.2608259916305542
2023-01-22 23:38:32.451101: step: 872/529, loss: 1.2493480443954468
2023-01-22 23:38:33.678940: step: 876/529, loss: 2.429363250732422
2023-01-22 23:38:34.930823: step: 880/529, loss: 0.3172902464866638
2023-01-22 23:38:36.164594: step: 884/529, loss: 0.3162820041179657
2023-01-22 23:38:37.368684: step: 888/529, loss: 1.5097625255584717
2023-01-22 23:38:38.553163: step: 892/529, loss: 0.16014719009399414
2023-01-22 23:38:39.743466: step: 896/529, loss: 1.0490915775299072
2023-01-22 23:38:40.921421: step: 900/529, loss: 0.20512184500694275
2023-01-22 23:38:42.105910: step: 904/529, loss: 0.623953104019165
2023-01-22 23:38:43.293016: step: 908/529, loss: 0.6367088556289673
2023-01-22 23:38:44.443921: step: 912/529, loss: 0.15613150596618652
2023-01-22 23:38:45.683390: step: 916/529, loss: 0.5094121694564819
2023-01-22 23:38:46.877918: step: 920/529, loss: 1.450291395187378
2023-01-22 23:38:48.099760: step: 924/529, loss: 0.6057009696960449
2023-01-22 23:38:49.289709: step: 928/529, loss: 1.3076021671295166
2023-01-22 23:38:50.491111: step: 932/529, loss: 2.4547219276428223
2023-01-22 23:38:51.715183: step: 936/529, loss: 1.0458277463912964
2023-01-22 23:38:52.927497: step: 940/529, loss: 0.7264676094055176
2023-01-22 23:38:54.116213: step: 944/529, loss: 0.4123757481575012
2023-01-22 23:38:55.285470: step: 948/529, loss: 0.18185758590698242
2023-01-22 23:38:56.489356: step: 952/529, loss: 0.3374711871147156
2023-01-22 23:38:57.678000: step: 956/529, loss: 0.4082280993461609
2023-01-22 23:38:58.857583: step: 960/529, loss: 0.5859688520431519
2023-01-22 23:39:00.107951: step: 964/529, loss: 0.5211753249168396
2023-01-22 23:39:01.282650: step: 968/529, loss: 0.7855747938156128
2023-01-22 23:39:02.485111: step: 972/529, loss: 0.5818166732788086
2023-01-22 23:39:03.687167: step: 976/529, loss: 0.434374064207077
2023-01-22 23:39:04.889720: step: 980/529, loss: 7.275872230529785
2023-01-22 23:39:06.143347: step: 984/529, loss: 0.47187793254852295
2023-01-22 23:39:07.362144: step: 988/529, loss: 1.1535205841064453
2023-01-22 23:39:08.567380: step: 992/529, loss: 1.2490960359573364
2023-01-22 23:39:09.741679: step: 996/529, loss: 0.25483590364456177
2023-01-22 23:39:10.958233: step: 1000/529, loss: 0.15983963012695312
2023-01-22 23:39:12.163994: step: 1004/529, loss: 2.033478021621704
2023-01-22 23:39:13.384788: step: 1008/529, loss: 1.1238760948181152
2023-01-22 23:39:14.562126: step: 1012/529, loss: 0.43764179944992065
2023-01-22 23:39:15.821596: step: 1016/529, loss: 1.9681974649429321
2023-01-22 23:39:17.060446: step: 1020/529, loss: 1.421175241470337
2023-01-22 23:39:18.264293: step: 1024/529, loss: 0.14086714386940002
2023-01-22 23:39:19.480362: step: 1028/529, loss: 0.26029786467552185
2023-01-22 23:39:20.636853: step: 1032/529, loss: 0.48388442397117615
2023-01-22 23:39:21.896744: step: 1036/529, loss: 0.12781819701194763
2023-01-22 23:39:23.069624: step: 1040/529, loss: 0.980811595916748
2023-01-22 23:39:24.252800: step: 1044/529, loss: 0.5740975737571716
2023-01-22 23:39:25.409575: step: 1048/529, loss: 1.688405156135559
2023-01-22 23:39:26.592005: step: 1052/529, loss: 0.18498817086219788
2023-01-22 23:39:27.756736: step: 1056/529, loss: 0.8830058574676514
2023-01-22 23:39:28.943660: step: 1060/529, loss: 0.7573413848876953
2023-01-22 23:39:30.149467: step: 1064/529, loss: 0.11612348258495331
2023-01-22 23:39:31.338753: step: 1068/529, loss: 0.5016762018203735
2023-01-22 23:39:32.562401: step: 1072/529, loss: 1.8578795194625854
2023-01-22 23:39:33.770961: step: 1076/529, loss: 1.0674693584442139
2023-01-22 23:39:34.942671: step: 1080/529, loss: 0.7718737721443176
2023-01-22 23:39:36.215043: step: 1084/529, loss: 0.20034612715244293
2023-01-22 23:39:37.414834: step: 1088/529, loss: 0.12779387831687927
2023-01-22 23:39:38.602748: step: 1092/529, loss: 0.9483867287635803
2023-01-22 23:39:39.812267: step: 1096/529, loss: 1.1970624923706055
2023-01-22 23:39:41.047620: step: 1100/529, loss: 0.26124781370162964
2023-01-22 23:39:42.254526: step: 1104/529, loss: 0.34428417682647705
2023-01-22 23:39:43.446876: step: 1108/529, loss: 0.23632851243019104
2023-01-22 23:39:44.641156: step: 1112/529, loss: 1.1896905899047852
2023-01-22 23:39:45.798668: step: 1116/529, loss: 0.10548386722803116
2023-01-22 23:39:46.977261: step: 1120/529, loss: 0.30458417534828186
2023-01-22 23:39:48.167734: step: 1124/529, loss: 0.14331656694412231
2023-01-22 23:39:49.355405: step: 1128/529, loss: 0.2040661871433258
2023-01-22 23:39:50.562201: step: 1132/529, loss: 0.23754163086414337
2023-01-22 23:39:51.779823: step: 1136/529, loss: 3.95654559135437
2023-01-22 23:39:52.956913: step: 1140/529, loss: 0.19373951852321625
2023-01-22 23:39:54.184854: step: 1144/529, loss: 1.4854968786239624
2023-01-22 23:39:55.357670: step: 1148/529, loss: 0.18933773040771484
2023-01-22 23:39:56.565189: step: 1152/529, loss: 0.37844783067703247
2023-01-22 23:39:57.741436: step: 1156/529, loss: 0.4130516052246094
2023-01-22 23:39:58.913542: step: 1160/529, loss: 1.2527437210083008
2023-01-22 23:40:00.118332: step: 1164/529, loss: 0.1148277297616005
2023-01-22 23:40:01.330290: step: 1168/529, loss: 1.7610738277435303
2023-01-22 23:40:02.510526: step: 1172/529, loss: 0.6940605640411377
2023-01-22 23:40:03.718001: step: 1176/529, loss: 3.0194191932678223
2023-01-22 23:40:04.900560: step: 1180/529, loss: 0.13224294781684875
2023-01-22 23:40:06.131745: step: 1184/529, loss: 0.19396701455116272
2023-01-22 23:40:07.331002: step: 1188/529, loss: 0.2696632742881775
2023-01-22 23:40:08.533409: step: 1192/529, loss: 0.336747407913208
2023-01-22 23:40:09.783338: step: 1196/529, loss: 1.589300513267517
2023-01-22 23:40:10.988075: step: 1200/529, loss: 0.06356213241815567
2023-01-22 23:40:12.225932: step: 1204/529, loss: 0.15005962550640106
2023-01-22 23:40:13.400792: step: 1208/529, loss: 0.27747613191604614
2023-01-22 23:40:14.589212: step: 1212/529, loss: 0.12508916854858398
2023-01-22 23:40:15.782093: step: 1216/529, loss: 0.24230414628982544
2023-01-22 23:40:16.951530: step: 1220/529, loss: 0.5309888124465942
2023-01-22 23:40:18.135363: step: 1224/529, loss: 0.8018829226493835
2023-01-22 23:40:19.325258: step: 1228/529, loss: 0.6966332197189331
2023-01-22 23:40:20.516478: step: 1232/529, loss: 0.8874320387840271
2023-01-22 23:40:21.731812: step: 1236/529, loss: 1.4590981006622314
2023-01-22 23:40:22.923740: step: 1240/529, loss: 0.6870986223220825
2023-01-22 23:40:24.093639: step: 1244/529, loss: 0.4094250798225403
2023-01-22 23:40:25.274278: step: 1248/529, loss: 0.6817470788955688
2023-01-22 23:40:26.490870: step: 1252/529, loss: 0.12213325500488281
2023-01-22 23:40:27.688333: step: 1256/529, loss: 1.6356189250946045
2023-01-22 23:40:28.888172: step: 1260/529, loss: 0.211894229054451
2023-01-22 23:40:30.070772: step: 1264/529, loss: 0.10953550785779953
2023-01-22 23:40:31.242806: step: 1268/529, loss: 0.661410927772522
2023-01-22 23:40:32.428595: step: 1272/529, loss: 0.852221667766571
2023-01-22 23:40:33.615401: step: 1276/529, loss: 0.17647600173950195
2023-01-22 23:40:34.822535: step: 1280/529, loss: 0.289465993642807
2023-01-22 23:40:36.014402: step: 1284/529, loss: 0.623895525932312
2023-01-22 23:40:37.237271: step: 1288/529, loss: 0.2133682519197464
2023-01-22 23:40:38.473691: step: 1292/529, loss: 2.2674007415771484
2023-01-22 23:40:39.685274: step: 1296/529, loss: 1.1101926565170288
2023-01-22 23:40:40.877313: step: 1300/529, loss: 1.4672174453735352
2023-01-22 23:40:42.077398: step: 1304/529, loss: 0.30789339542388916
2023-01-22 23:40:43.241571: step: 1308/529, loss: 0.8448333144187927
2023-01-22 23:40:44.448336: step: 1312/529, loss: 0.7105619311332703
2023-01-22 23:40:45.644078: step: 1316/529, loss: 0.4730682969093323
2023-01-22 23:40:46.872859: step: 1320/529, loss: 0.2151210904121399
2023-01-22 23:40:48.073116: step: 1324/529, loss: 0.7272160649299622
2023-01-22 23:40:49.286668: step: 1328/529, loss: 0.8214249610900879
2023-01-22 23:40:50.474297: step: 1332/529, loss: 0.6123987436294556
2023-01-22 23:40:51.673817: step: 1336/529, loss: 0.25961440801620483
2023-01-22 23:40:52.860855: step: 1340/529, loss: 0.3758208155632019
2023-01-22 23:40:54.064035: step: 1344/529, loss: 0.14473819732666016
2023-01-22 23:40:55.276531: step: 1348/529, loss: 0.18829727172851562
2023-01-22 23:40:56.439948: step: 1352/529, loss: 0.6719884872436523
2023-01-22 23:40:57.660102: step: 1356/529, loss: 0.1795245260000229
2023-01-22 23:40:58.859600: step: 1360/529, loss: 0.8639701008796692
2023-01-22 23:41:00.058436: step: 1364/529, loss: 1.3646658658981323
2023-01-22 23:41:01.250017: step: 1368/529, loss: 0.35387736558914185
2023-01-22 23:41:02.440058: step: 1372/529, loss: 0.682648777961731
2023-01-22 23:41:03.616074: step: 1376/529, loss: 0.27142849564552307
2023-01-22 23:41:04.813444: step: 1380/529, loss: 0.2741974890232086
2023-01-22 23:41:06.002966: step: 1384/529, loss: 0.15044985711574554
2023-01-22 23:41:07.216502: step: 1388/529, loss: 0.5265138745307922
2023-01-22 23:41:08.482578: step: 1392/529, loss: 0.16304011642932892
2023-01-22 23:41:09.684151: step: 1396/529, loss: 0.06310291588306427
2023-01-22 23:41:10.855155: step: 1400/529, loss: 0.17664042115211487
2023-01-22 23:41:12.061192: step: 1404/529, loss: 0.6299788951873779
2023-01-22 23:41:13.239409: step: 1408/529, loss: 0.7734225988388062
2023-01-22 23:41:14.413748: step: 1412/529, loss: 0.49233388900756836
2023-01-22 23:41:15.591081: step: 1416/529, loss: 0.3346596360206604
2023-01-22 23:41:16.785030: step: 1420/529, loss: 4.376696586608887
2023-01-22 23:41:17.995042: step: 1424/529, loss: 0.05406666174530983
2023-01-22 23:41:19.222963: step: 1428/529, loss: 0.24404850602149963
2023-01-22 23:41:20.400939: step: 1432/529, loss: 0.13517819344997406
2023-01-22 23:41:21.563757: step: 1436/529, loss: 0.10635744035243988
2023-01-22 23:41:22.764171: step: 1440/529, loss: 0.11953391879796982
2023-01-22 23:41:23.956501: step: 1444/529, loss: 2.097682237625122
2023-01-22 23:41:25.139752: step: 1448/529, loss: 0.07378740608692169
2023-01-22 23:41:26.390244: step: 1452/529, loss: 0.3262103199958801
2023-01-22 23:41:27.571359: step: 1456/529, loss: 0.13043051958084106
2023-01-22 23:41:28.768938: step: 1460/529, loss: 0.09592628479003906
2023-01-22 23:41:29.952791: step: 1464/529, loss: 0.3350904583930969
2023-01-22 23:41:31.146960: step: 1468/529, loss: 0.7176365852355957
2023-01-22 23:41:32.325607: step: 1472/529, loss: 0.32632073760032654
2023-01-22 23:41:33.496515: step: 1476/529, loss: 0.13802537322044373
2023-01-22 23:41:34.708621: step: 1480/529, loss: 0.2311009019613266
2023-01-22 23:41:35.933578: step: 1484/529, loss: 0.4850480258464813
2023-01-22 23:41:37.141965: step: 1488/529, loss: 0.9704471826553345
2023-01-22 23:41:38.308709: step: 1492/529, loss: 1.374579668045044
2023-01-22 23:41:39.489901: step: 1496/529, loss: 0.9018918871879578
2023-01-22 23:41:40.694509: step: 1500/529, loss: 0.07233548164367676
2023-01-22 23:41:41.911154: step: 1504/529, loss: 0.1383988857269287
2023-01-22 23:41:43.052215: step: 1508/529, loss: 1.6935938596725464
2023-01-22 23:41:44.253041: step: 1512/529, loss: 0.8001202940940857
2023-01-22 23:41:45.425481: step: 1516/529, loss: 0.27359557151794434
2023-01-22 23:41:46.587546: step: 1520/529, loss: 0.4031650722026825
2023-01-22 23:41:47.821706: step: 1524/529, loss: 0.1616169959306717
2023-01-22 23:41:49.015685: step: 1528/529, loss: 0.14935246109962463
2023-01-22 23:41:50.192781: step: 1532/529, loss: 0.8295471668243408
2023-01-22 23:41:51.357619: step: 1536/529, loss: 0.25358933210372925
2023-01-22 23:41:52.539005: step: 1540/529, loss: 0.11138921231031418
2023-01-22 23:41:53.779576: step: 1544/529, loss: 0.17383775115013123
2023-01-22 23:41:54.954211: step: 1548/529, loss: 0.5011741518974304
2023-01-22 23:41:56.154187: step: 1552/529, loss: 0.1803244650363922
2023-01-22 23:41:57.319817: step: 1556/529, loss: 0.9834560751914978
2023-01-22 23:41:58.498091: step: 1560/529, loss: 0.17623892426490784
2023-01-22 23:41:59.705350: step: 1564/529, loss: 0.15104246139526367
2023-01-22 23:42:00.893283: step: 1568/529, loss: 0.19454827904701233
2023-01-22 23:42:02.113783: step: 1572/529, loss: 0.3268570899963379
2023-01-22 23:42:03.283047: step: 1576/529, loss: 0.2185623198747635
2023-01-22 23:42:04.472116: step: 1580/529, loss: 1.2287840843200684
2023-01-22 23:42:05.697597: step: 1584/529, loss: 0.18187841773033142
2023-01-22 23:42:06.875027: step: 1588/529, loss: 0.13649415969848633
2023-01-22 23:42:08.080290: step: 1592/529, loss: 0.799708366394043
2023-01-22 23:42:09.261679: step: 1596/529, loss: 0.2217964082956314
2023-01-22 23:42:10.445626: step: 1600/529, loss: 0.02056713029742241
2023-01-22 23:42:11.641766: step: 1604/529, loss: 1.126817226409912
2023-01-22 23:42:12.843937: step: 1608/529, loss: 0.2664267420768738
2023-01-22 23:42:14.040449: step: 1612/529, loss: 0.7710850238800049
2023-01-22 23:42:15.257042: step: 1616/529, loss: 0.7347552180290222
2023-01-22 23:42:16.473476: step: 1620/529, loss: 0.22203917801380157
2023-01-22 23:42:17.666588: step: 1624/529, loss: 0.07638435810804367
2023-01-22 23:42:18.900356: step: 1628/529, loss: 0.07383427768945694
2023-01-22 23:42:20.125748: step: 1632/529, loss: 0.244424968957901
2023-01-22 23:42:21.313687: step: 1636/529, loss: 0.8498695492744446
2023-01-22 23:42:22.520666: step: 1640/529, loss: 0.369972825050354
2023-01-22 23:42:23.714002: step: 1644/529, loss: 0.5501283407211304
2023-01-22 23:42:24.939458: step: 1648/529, loss: 0.9238247871398926
2023-01-22 23:42:26.112427: step: 1652/529, loss: 0.3014441132545471
2023-01-22 23:42:27.277779: step: 1656/529, loss: 0.10882674157619476
2023-01-22 23:42:28.456463: step: 1660/529, loss: 0.2592444121837616
2023-01-22 23:42:29.657844: step: 1664/529, loss: 0.5186513662338257
2023-01-22 23:42:30.846604: step: 1668/529, loss: 0.3612937927246094
2023-01-22 23:42:32.037161: step: 1672/529, loss: 0.1474134474992752
2023-01-22 23:42:33.283238: step: 1676/529, loss: 0.4401039183139801
2023-01-22 23:42:34.459605: step: 1680/529, loss: 0.2526678442955017
2023-01-22 23:42:35.676328: step: 1684/529, loss: 0.2809045910835266
2023-01-22 23:42:36.880965: step: 1688/529, loss: 1.2654640674591064
2023-01-22 23:42:38.067487: step: 1692/529, loss: 0.22502213716506958
2023-01-22 23:42:39.243163: step: 1696/529, loss: 0.639827311038971
2023-01-22 23:42:40.449598: step: 1700/529, loss: 0.8159974813461304
2023-01-22 23:42:41.672983: step: 1704/529, loss: 0.5960533022880554
2023-01-22 23:42:42.881893: step: 1708/529, loss: 0.1602187156677246
2023-01-22 23:42:44.120394: step: 1712/529, loss: 0.21204166114330292
2023-01-22 23:42:45.360581: step: 1716/529, loss: 0.046489618718624115
2023-01-22 23:42:46.550327: step: 1720/529, loss: 0.8839322924613953
2023-01-22 23:42:47.733194: step: 1724/529, loss: 0.3805540204048157
2023-01-22 23:42:48.905311: step: 1728/529, loss: 0.13201037049293518
2023-01-22 23:42:50.080062: step: 1732/529, loss: 0.10013015568256378
2023-01-22 23:42:51.285536: step: 1736/529, loss: 0.12067604809999466
2023-01-22 23:42:52.495770: step: 1740/529, loss: 0.1981954574584961
2023-01-22 23:42:53.665481: step: 1744/529, loss: 0.15985354781150818
2023-01-22 23:42:54.860487: step: 1748/529, loss: 0.02093651331961155
2023-01-22 23:42:56.048823: step: 1752/529, loss: 1.675818920135498
2023-01-22 23:42:57.272553: step: 1756/529, loss: 0.1608387529850006
2023-01-22 23:42:58.464821: step: 1760/529, loss: 0.6206117272377014
2023-01-22 23:42:59.666833: step: 1764/529, loss: 1.0477927923202515
2023-01-22 23:43:00.916996: step: 1768/529, loss: 0.2547837793827057
2023-01-22 23:43:02.144304: step: 1772/529, loss: 0.8503913879394531
2023-01-22 23:43:03.367982: step: 1776/529, loss: 0.19042368233203888
2023-01-22 23:43:04.551677: step: 1780/529, loss: 0.6307576894760132
2023-01-22 23:43:05.776703: step: 1784/529, loss: 2.148552179336548
2023-01-22 23:43:06.947552: step: 1788/529, loss: 0.8480708003044128
2023-01-22 23:43:08.136925: step: 1792/529, loss: 0.04899773746728897
2023-01-22 23:43:09.333221: step: 1796/529, loss: 0.4089071750640869
2023-01-22 23:43:10.538554: step: 1800/529, loss: 1.2604007720947266
2023-01-22 23:43:11.754322: step: 1804/529, loss: 1.228386640548706
2023-01-22 23:43:12.983388: step: 1808/529, loss: 0.2881526052951813
2023-01-22 23:43:14.185872: step: 1812/529, loss: 0.2277495414018631
2023-01-22 23:43:15.356120: step: 1816/529, loss: 0.9178861379623413
2023-01-22 23:43:16.527631: step: 1820/529, loss: 0.14514775574207306
2023-01-22 23:43:17.710557: step: 1824/529, loss: 0.19144979119300842
2023-01-22 23:43:18.896993: step: 1828/529, loss: 0.2163538932800293
2023-01-22 23:43:20.069275: step: 1832/529, loss: 14.092599868774414
2023-01-22 23:43:21.262564: step: 1836/529, loss: 0.1104976162314415
2023-01-22 23:43:22.431540: step: 1840/529, loss: 1.156100869178772
2023-01-22 23:43:23.592074: step: 1844/529, loss: 0.9208877682685852
2023-01-22 23:43:24.815298: step: 1848/529, loss: 0.5374807119369507
2023-01-22 23:43:25.999996: step: 1852/529, loss: 0.26244187355041504
2023-01-22 23:43:27.217698: step: 1856/529, loss: 0.2787407636642456
2023-01-22 23:43:28.424409: step: 1860/529, loss: 0.26392149925231934
2023-01-22 23:43:29.667441: step: 1864/529, loss: 0.39164304733276367
2023-01-22 23:43:30.845286: step: 1868/529, loss: 0.1400972455739975
2023-01-22 23:43:32.046383: step: 1872/529, loss: 0.0908488780260086
2023-01-22 23:43:33.302005: step: 1876/529, loss: 0.32914039492607117
2023-01-22 23:43:34.468725: step: 1880/529, loss: 0.2589985728263855
2023-01-22 23:43:35.642141: step: 1884/529, loss: 0.12929029762744904
2023-01-22 23:43:36.869853: step: 1888/529, loss: 0.25012731552124023
2023-01-22 23:43:38.034922: step: 1892/529, loss: 0.20882892608642578
2023-01-22 23:43:39.291132: step: 1896/529, loss: 1.1133434772491455
2023-01-22 23:43:40.459447: step: 1900/529, loss: 0.5980363488197327
2023-01-22 23:43:41.706784: step: 1904/529, loss: 0.4736517071723938
2023-01-22 23:43:42.924225: step: 1908/529, loss: 1.8925607204437256
2023-01-22 23:43:44.128222: step: 1912/529, loss: 0.2998947203159332
2023-01-22 23:43:45.345042: step: 1916/529, loss: 0.23366856575012207
2023-01-22 23:43:46.544829: step: 1920/529, loss: 0.279222697019577
2023-01-22 23:43:47.752202: step: 1924/529, loss: 0.21860238909721375
2023-01-22 23:43:48.943898: step: 1928/529, loss: 0.1360282003879547
2023-01-22 23:43:50.118788: step: 1932/529, loss: 0.24403348565101624
2023-01-22 23:43:51.299770: step: 1936/529, loss: 0.21614505350589752
2023-01-22 23:43:52.487307: step: 1940/529, loss: 0.2609427571296692
2023-01-22 23:43:53.723584: step: 1944/529, loss: 0.34300652146339417
2023-01-22 23:43:54.909467: step: 1948/529, loss: 0.49694690108299255
2023-01-22 23:43:56.089492: step: 1952/529, loss: 0.22034835815429688
2023-01-22 23:43:57.289434: step: 1956/529, loss: 0.13345685601234436
2023-01-22 23:43:58.470210: step: 1960/529, loss: 0.26830148696899414
2023-01-22 23:43:59.630859: step: 1964/529, loss: 1.3214449882507324
2023-01-22 23:44:00.840627: step: 1968/529, loss: 0.8397705554962158
2023-01-22 23:44:02.015276: step: 1972/529, loss: 1.6396328210830688
2023-01-22 23:44:03.215391: step: 1976/529, loss: 1.3403518199920654
2023-01-22 23:44:04.432704: step: 1980/529, loss: 0.3076045513153076
2023-01-22 23:44:05.588658: step: 1984/529, loss: 0.2148914337158203
2023-01-22 23:44:06.754367: step: 1988/529, loss: 0.05349435657262802
2023-01-22 23:44:07.969363: step: 1992/529, loss: 0.16458760201931
2023-01-22 23:44:09.145461: step: 1996/529, loss: 0.44762229919433594
2023-01-22 23:44:10.345034: step: 2000/529, loss: 0.32211047410964966
2023-01-22 23:44:11.558888: step: 2004/529, loss: 0.3049635887145996
2023-01-22 23:44:12.784295: step: 2008/529, loss: 1.9458744525909424
2023-01-22 23:44:14.003432: step: 2012/529, loss: 0.5219520330429077
2023-01-22 23:44:15.199503: step: 2016/529, loss: 0.2289627194404602
2023-01-22 23:44:16.409976: step: 2020/529, loss: 0.19515438377857208
2023-01-22 23:44:17.573823: step: 2024/529, loss: 0.8890830874443054
2023-01-22 23:44:18.783350: step: 2028/529, loss: 0.6588819622993469
2023-01-22 23:44:19.953704: step: 2032/529, loss: 0.2609597444534302
2023-01-22 23:44:21.196890: step: 2036/529, loss: 0.5175431370735168
2023-01-22 23:44:22.380564: step: 2040/529, loss: 0.8420371413230896
2023-01-22 23:44:23.613938: step: 2044/529, loss: 1.3401002883911133
2023-01-22 23:44:24.893802: step: 2048/529, loss: 0.9962199926376343
2023-01-22 23:44:26.092041: step: 2052/529, loss: 0.15557122230529785
2023-01-22 23:44:27.277935: step: 2056/529, loss: 0.3028806746006012
2023-01-22 23:44:28.516720: step: 2060/529, loss: 0.18216124176979065
2023-01-22 23:44:29.722542: step: 2064/529, loss: 0.2800995707511902
2023-01-22 23:44:30.950824: step: 2068/529, loss: 0.5926333665847778
2023-01-22 23:44:32.124544: step: 2072/529, loss: 1.703115701675415
2023-01-22 23:44:33.357998: step: 2076/529, loss: 0.30661749839782715
2023-01-22 23:44:34.588355: step: 2080/529, loss: 0.27016106247901917
2023-01-22 23:44:35.817315: step: 2084/529, loss: 0.22211942076683044
2023-01-22 23:44:37.051488: step: 2088/529, loss: 0.6704018115997314
2023-01-22 23:44:38.295482: step: 2092/529, loss: 0.8512510061264038
2023-01-22 23:44:39.539797: step: 2096/529, loss: 0.4487777054309845
2023-01-22 23:44:40.737848: step: 2100/529, loss: 0.667074978351593
2023-01-22 23:44:41.979796: step: 2104/529, loss: 0.19050435721874237
2023-01-22 23:44:43.176062: step: 2108/529, loss: 0.6942664384841919
2023-01-22 23:44:44.350652: step: 2112/529, loss: 0.518520176410675
2023-01-22 23:44:45.563899: step: 2116/529, loss: 0.5513672828674316
==================================================
Loss: 0.767
--------------------
Dev: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.4675324675324675, 'r': 0.6666666666666666, 'f1': 0.549618320610687}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, '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': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.4675324675324675, 'r': 0.6666666666666666, 'f1': 0.549618320610687}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:45:56.114015: step: 4/529, loss: 0.3145027756690979
2023-01-22 23:45:57.296827: step: 8/529, loss: 0.3824879825115204
2023-01-22 23:45:58.487284: step: 12/529, loss: 0.21834233403205872
2023-01-22 23:45:59.657612: step: 16/529, loss: 0.1918337345123291
2023-01-22 23:46:00.819797: step: 20/529, loss: 0.32676324248313904
2023-01-22 23:46:02.047420: step: 24/529, loss: 0.3381422162055969
2023-01-22 23:46:03.244605: step: 28/529, loss: 0.19183596968650818
2023-01-22 23:46:04.434019: step: 32/529, loss: 0.213566392660141
2023-01-22 23:46:05.623078: step: 36/529, loss: 0.1891981065273285
2023-01-22 23:46:06.784525: step: 40/529, loss: 0.2683035731315613
2023-01-22 23:46:07.994916: step: 44/529, loss: 0.21231085062026978
2023-01-22 23:46:09.186167: step: 48/529, loss: 0.7255871295928955
2023-01-22 23:46:10.366026: step: 52/529, loss: 0.6977856755256653
2023-01-22 23:46:11.542606: step: 56/529, loss: 0.4053492546081543
2023-01-22 23:46:12.742081: step: 60/529, loss: 0.2516906261444092
2023-01-22 23:46:13.942192: step: 64/529, loss: 0.19978752732276917
2023-01-22 23:46:15.183388: step: 68/529, loss: 0.7886441946029663
2023-01-22 23:46:16.347740: step: 72/529, loss: 1.855760097503662
2023-01-22 23:46:17.529006: step: 76/529, loss: 0.18097572028636932
2023-01-22 23:46:18.703494: step: 80/529, loss: 1.7791774272918701
2023-01-22 23:46:19.892409: step: 84/529, loss: 0.48580026626586914
2023-01-22 23:46:21.112556: step: 88/529, loss: 6.689284324645996
2023-01-22 23:46:22.313181: step: 92/529, loss: 0.10029307007789612
2023-01-22 23:46:23.483645: step: 96/529, loss: 0.211774542927742
2023-01-22 23:46:24.727321: step: 100/529, loss: 0.18067194521427155
2023-01-22 23:46:25.941723: step: 104/529, loss: 0.22729197144508362
2023-01-22 23:46:27.155437: step: 108/529, loss: 0.13150405883789062
2023-01-22 23:46:28.306059: step: 112/529, loss: 0.8847576379776001
2023-01-22 23:46:29.550802: step: 116/529, loss: 0.08883801102638245
2023-01-22 23:46:30.715479: step: 120/529, loss: 0.6762876510620117
2023-01-22 23:46:31.896446: step: 124/529, loss: 0.39829427003860474
2023-01-22 23:46:33.082086: step: 128/529, loss: 0.04410243034362793
2023-01-22 23:46:34.230424: step: 132/529, loss: 0.7645156979560852
2023-01-22 23:46:35.472190: step: 136/529, loss: 0.6208375692367554
2023-01-22 23:46:36.676259: step: 140/529, loss: 0.45884692668914795
2023-01-22 23:46:37.857246: step: 144/529, loss: 1.2470149993896484
2023-01-22 23:46:39.033763: step: 148/529, loss: 0.28963661193847656
2023-01-22 23:46:40.253328: step: 152/529, loss: 0.3370674252510071
2023-01-22 23:46:41.430714: step: 156/529, loss: 1.81912362575531
2023-01-22 23:46:42.641411: step: 160/529, loss: 0.46266573667526245
2023-01-22 23:46:43.814330: step: 164/529, loss: 0.2175680249929428
2023-01-22 23:46:45.022724: step: 168/529, loss: 0.26922425627708435
2023-01-22 23:46:46.241505: step: 172/529, loss: 0.41409599781036377
2023-01-22 23:46:47.443058: step: 176/529, loss: 0.1715511977672577
2023-01-22 23:46:48.659029: step: 180/529, loss: 0.7273315191268921
2023-01-22 23:46:49.844119: step: 184/529, loss: 0.2191057801246643
2023-01-22 23:46:51.025572: step: 188/529, loss: 0.586996853351593
2023-01-22 23:46:52.223167: step: 192/529, loss: 0.15371084213256836
2023-01-22 23:46:53.424701: step: 196/529, loss: 0.49319761991500854
2023-01-22 23:46:54.575111: step: 200/529, loss: 6.446598052978516
2023-01-22 23:46:55.753974: step: 204/529, loss: 0.2858756482601166
2023-01-22 23:46:56.931338: step: 208/529, loss: 0.17778797447681427
2023-01-22 23:46:58.173751: step: 212/529, loss: 0.9940707087516785
2023-01-22 23:46:59.363336: step: 216/529, loss: 0.21211454272270203
2023-01-22 23:47:00.546921: step: 220/529, loss: 0.6821246147155762
2023-01-22 23:47:01.758597: step: 224/529, loss: 0.37775611877441406
2023-01-22 23:47:02.954589: step: 228/529, loss: 0.1789262741804123
2023-01-22 23:47:04.145734: step: 232/529, loss: 0.6681526303291321
2023-01-22 23:47:05.344560: step: 236/529, loss: 0.16765213012695312
2023-01-22 23:47:06.523866: step: 240/529, loss: 0.18701642751693726
2023-01-22 23:47:07.697243: step: 244/529, loss: 0.18661737442016602
2023-01-22 23:47:08.914221: step: 248/529, loss: 0.38548851013183594
2023-01-22 23:47:10.114038: step: 252/529, loss: 0.7864240407943726
2023-01-22 23:47:11.279622: step: 256/529, loss: 0.1659766286611557
2023-01-22 23:47:12.471458: step: 260/529, loss: 0.7087134122848511
2023-01-22 23:47:13.721521: step: 264/529, loss: 6.761756896972656
2023-01-22 23:47:14.914779: step: 268/529, loss: 0.04154014587402344
2023-01-22 23:47:16.094743: step: 272/529, loss: 0.18368521332740784
2023-01-22 23:47:17.288229: step: 276/529, loss: 0.35539257526397705
2023-01-22 23:47:18.470303: step: 280/529, loss: 0.6105610728263855
2023-01-22 23:47:19.663155: step: 284/529, loss: 0.24418431520462036
2023-01-22 23:47:20.869408: step: 288/529, loss: 0.42339026927948
2023-01-22 23:47:22.087848: step: 292/529, loss: 0.11974182724952698
2023-01-22 23:47:23.268334: step: 296/529, loss: 0.14005470275878906
2023-01-22 23:47:24.470967: step: 300/529, loss: 1.0959142446517944
2023-01-22 23:47:25.661245: step: 304/529, loss: 0.37148499488830566
2023-01-22 23:47:26.846705: step: 308/529, loss: 0.7891260981559753
2023-01-22 23:47:28.118557: step: 312/529, loss: 1.8357021808624268
2023-01-22 23:47:29.275109: step: 316/529, loss: 0.08673782646656036
2023-01-22 23:47:30.567101: step: 320/529, loss: 2.700627326965332
2023-01-22 23:47:31.764096: step: 324/529, loss: 0.08230238407850266
2023-01-22 23:47:32.973132: step: 328/529, loss: 0.3465553820133209
2023-01-22 23:47:34.133740: step: 332/529, loss: 0.343706876039505
2023-01-22 23:47:35.309127: step: 336/529, loss: 0.05547685548663139
2023-01-22 23:47:36.489222: step: 340/529, loss: 0.4214421212673187
2023-01-22 23:47:37.646853: step: 344/529, loss: 0.07134180516004562
2023-01-22 23:47:38.835689: step: 348/529, loss: 0.23021790385246277
2023-01-22 23:47:40.021802: step: 352/529, loss: 0.15429440140724182
2023-01-22 23:47:41.270242: step: 356/529, loss: 0.21846051514148712
2023-01-22 23:47:42.474268: step: 360/529, loss: 0.07128031551837921
2023-01-22 23:47:43.647492: step: 364/529, loss: 0.2953076958656311
2023-01-22 23:47:44.842008: step: 368/529, loss: 0.6530542373657227
2023-01-22 23:47:46.029390: step: 372/529, loss: 0.4478347897529602
2023-01-22 23:47:47.222390: step: 376/529, loss: 0.24450521171092987
2023-01-22 23:47:48.433805: step: 380/529, loss: 0.3753108084201813
2023-01-22 23:47:49.593495: step: 384/529, loss: 0.11954517662525177
2023-01-22 23:47:50.760794: step: 388/529, loss: 0.38516682386398315
2023-01-22 23:47:51.929595: step: 392/529, loss: 0.2172565460205078
2023-01-22 23:47:53.136006: step: 396/529, loss: 0.24366196990013123
2023-01-22 23:47:54.344837: step: 400/529, loss: 0.1932273805141449
2023-01-22 23:47:55.615468: step: 404/529, loss: 1.0306894779205322
2023-01-22 23:47:56.775706: step: 408/529, loss: 1.2246931791305542
2023-01-22 23:47:57.952064: step: 412/529, loss: 0.15378323197364807
2023-01-22 23:47:59.183604: step: 416/529, loss: 0.3526252806186676
2023-01-22 23:48:00.357932: step: 420/529, loss: 0.5678306818008423
2023-01-22 23:48:01.576606: step: 424/529, loss: 0.41032248735427856
2023-01-22 23:48:02.752821: step: 428/529, loss: 0.8143123984336853
2023-01-22 23:48:03.952072: step: 432/529, loss: 0.16842976212501526
2023-01-22 23:48:05.169507: step: 436/529, loss: 0.09926962107419968
2023-01-22 23:48:06.378315: step: 440/529, loss: 0.09357257187366486
2023-01-22 23:48:07.546116: step: 444/529, loss: 0.17700693011283875
2023-01-22 23:48:08.767244: step: 448/529, loss: 1.9232968091964722
2023-01-22 23:48:09.922672: step: 452/529, loss: 0.11117162555456161
2023-01-22 23:48:11.115995: step: 456/529, loss: 0.17162255942821503
2023-01-22 23:48:12.342171: step: 460/529, loss: 0.8817241787910461
2023-01-22 23:48:13.551358: step: 464/529, loss: 0.6451841592788696
2023-01-22 23:48:14.774790: step: 468/529, loss: 0.6476221084594727
2023-01-22 23:48:16.032166: step: 472/529, loss: 0.397754967212677
2023-01-22 23:48:17.216230: step: 476/529, loss: 0.2320270538330078
2023-01-22 23:48:18.406338: step: 480/529, loss: 0.32145872712135315
2023-01-22 23:48:19.601435: step: 484/529, loss: 1.3022773265838623
2023-01-22 23:48:20.800622: step: 488/529, loss: 0.18829499185085297
2023-01-22 23:48:22.005469: step: 492/529, loss: 0.15562638640403748
2023-01-22 23:48:23.185245: step: 496/529, loss: 0.17442092299461365
2023-01-22 23:48:24.405021: step: 500/529, loss: 0.24912777543067932
2023-01-22 23:48:25.647631: step: 504/529, loss: 0.8057572245597839
2023-01-22 23:48:26.812232: step: 508/529, loss: 0.7955676317214966
2023-01-22 23:48:27.984133: step: 512/529, loss: 0.32331976294517517
2023-01-22 23:48:29.206671: step: 516/529, loss: 0.6123404502868652
2023-01-22 23:48:30.397855: step: 520/529, loss: 0.1517670750617981
2023-01-22 23:48:31.566474: step: 524/529, loss: 0.6838817000389099
2023-01-22 23:48:32.802284: step: 528/529, loss: 0.21943378448486328
2023-01-22 23:48:34.021086: step: 532/529, loss: 0.38667726516723633
2023-01-22 23:48:35.204875: step: 536/529, loss: 0.0918995812535286
2023-01-22 23:48:36.406554: step: 540/529, loss: 0.1284637451171875
2023-01-22 23:48:37.642339: step: 544/529, loss: 0.6208086609840393
2023-01-22 23:48:38.862935: step: 548/529, loss: 0.08790130913257599
2023-01-22 23:48:40.040522: step: 552/529, loss: 0.7548690438270569
2023-01-22 23:48:41.248140: step: 556/529, loss: 1.6029006242752075
2023-01-22 23:48:42.430155: step: 560/529, loss: 0.2915436923503876
2023-01-22 23:48:43.591649: step: 564/529, loss: 0.08351273834705353
2023-01-22 23:48:44.831264: step: 568/529, loss: 0.9850178360939026
2023-01-22 23:48:46.044638: step: 572/529, loss: 0.07333894073963165
2023-01-22 23:48:47.227137: step: 576/529, loss: 1.386325478553772
2023-01-22 23:48:48.468573: step: 580/529, loss: 0.22081860899925232
2023-01-22 23:48:49.654336: step: 584/529, loss: 0.1628166139125824
2023-01-22 23:48:50.906160: step: 588/529, loss: 0.21540433168411255
2023-01-22 23:48:52.125809: step: 592/529, loss: 0.06566419452428818
2023-01-22 23:48:53.340669: step: 596/529, loss: 0.6674219369888306
2023-01-22 23:48:54.523120: step: 600/529, loss: 6.23017692565918
2023-01-22 23:48:55.758631: step: 604/529, loss: 0.8146122097969055
2023-01-22 23:48:56.925399: step: 608/529, loss: 0.05529747158288956
2023-01-22 23:48:58.079929: step: 612/529, loss: 0.23919087648391724
2023-01-22 23:48:59.279187: step: 616/529, loss: 0.2634842097759247
2023-01-22 23:49:00.478705: step: 620/529, loss: 0.6310187578201294
2023-01-22 23:49:01.661289: step: 624/529, loss: 0.6703919172286987
2023-01-22 23:49:02.824656: step: 628/529, loss: 1.0428012609481812
2023-01-22 23:49:04.005537: step: 632/529, loss: 2.3234193325042725
2023-01-22 23:49:05.197368: step: 636/529, loss: 0.3630928099155426
2023-01-22 23:49:06.413979: step: 640/529, loss: 0.33125293254852295
2023-01-22 23:49:07.591940: step: 644/529, loss: 0.2506866157054901
2023-01-22 23:49:08.791265: step: 648/529, loss: 1.1564433574676514
2023-01-22 23:49:10.064804: step: 652/529, loss: 0.18596597015857697
2023-01-22 23:49:11.231297: step: 656/529, loss: 0.1827954351902008
2023-01-22 23:49:12.451666: step: 660/529, loss: 0.6522228717803955
2023-01-22 23:49:13.626480: step: 664/529, loss: 0.11323872208595276
2023-01-22 23:49:14.844401: step: 668/529, loss: 0.4669274389743805
2023-01-22 23:49:16.088725: step: 672/529, loss: 0.8580198287963867
2023-01-22 23:49:17.323796: step: 676/529, loss: 0.6306808590888977
2023-01-22 23:49:18.496371: step: 680/529, loss: 0.6906743049621582
2023-01-22 23:49:19.717385: step: 684/529, loss: 0.2813708186149597
2023-01-22 23:49:20.973141: step: 688/529, loss: 0.22030572593212128
2023-01-22 23:49:22.183048: step: 692/529, loss: 0.22473736107349396
2023-01-22 23:49:23.339696: step: 696/529, loss: 0.9583730101585388
2023-01-22 23:49:24.531694: step: 700/529, loss: 0.10873080044984818
2023-01-22 23:49:25.704780: step: 704/529, loss: 0.21155062317848206
2023-01-22 23:49:26.894506: step: 708/529, loss: 6.62742280960083
2023-01-22 23:49:28.122773: step: 712/529, loss: 0.6515638828277588
2023-01-22 23:49:29.338868: step: 716/529, loss: 0.2883855998516083
2023-01-22 23:49:30.505185: step: 720/529, loss: 0.27828481793403625
2023-01-22 23:49:31.732324: step: 724/529, loss: 1.0037860870361328
2023-01-22 23:49:32.995439: step: 728/529, loss: 0.7955505847930908
2023-01-22 23:49:34.178677: step: 732/529, loss: 0.11061549186706543
2023-01-22 23:49:35.416297: step: 736/529, loss: 0.6887736916542053
2023-01-22 23:49:36.639656: step: 740/529, loss: 0.31038370728492737
2023-01-22 23:49:37.837100: step: 744/529, loss: 0.7637366056442261
2023-01-22 23:49:39.022986: step: 748/529, loss: 0.6992408633232117
2023-01-22 23:49:40.211882: step: 752/529, loss: 0.23954148590564728
2023-01-22 23:49:41.431284: step: 756/529, loss: 0.7993958592414856
2023-01-22 23:49:42.627196: step: 760/529, loss: 0.100660540163517
2023-01-22 23:49:43.810175: step: 764/529, loss: 0.20956745743751526
2023-01-22 23:49:45.097607: step: 768/529, loss: 0.34549540281295776
2023-01-22 23:49:46.300094: step: 772/529, loss: 0.3190248906612396
2023-01-22 23:49:47.457402: step: 776/529, loss: 0.07983627915382385
2023-01-22 23:49:48.632473: step: 780/529, loss: 0.18287816643714905
2023-01-22 23:49:49.819778: step: 784/529, loss: 0.1891632080078125
2023-01-22 23:49:50.996929: step: 788/529, loss: 0.7350719571113586
2023-01-22 23:49:52.191484: step: 792/529, loss: 1.3146165609359741
2023-01-22 23:49:53.352942: step: 796/529, loss: 0.6332480311393738
2023-01-22 23:49:54.531870: step: 800/529, loss: 0.19985853135585785
2023-01-22 23:49:55.722027: step: 804/529, loss: 0.3407343029975891
2023-01-22 23:49:56.882798: step: 808/529, loss: 0.09236927330493927
2023-01-22 23:49:58.095892: step: 812/529, loss: 1.0310064554214478
2023-01-22 23:49:59.252486: step: 816/529, loss: 0.49313926696777344
2023-01-22 23:50:00.480217: step: 820/529, loss: 0.8960789442062378
2023-01-22 23:50:01.666541: step: 824/529, loss: 0.22117196023464203
2023-01-22 23:50:02.840649: step: 828/529, loss: 0.5449997186660767
2023-01-22 23:50:04.030697: step: 832/529, loss: 0.3623240888118744
2023-01-22 23:50:05.242146: step: 836/529, loss: 0.3891538381576538
2023-01-22 23:50:06.460430: step: 840/529, loss: 0.20476743578910828
2023-01-22 23:50:07.709053: step: 844/529, loss: 0.321729838848114
2023-01-22 23:50:08.906928: step: 848/529, loss: 0.951215386390686
2023-01-22 23:50:10.099822: step: 852/529, loss: 0.18274226784706116
2023-01-22 23:50:11.317580: step: 856/529, loss: 0.6644158363342285
2023-01-22 23:50:12.484683: step: 860/529, loss: 0.230614572763443
2023-01-22 23:50:13.697013: step: 864/529, loss: 1.8907235860824585
2023-01-22 23:50:14.923183: step: 868/529, loss: 0.32483169436454773
2023-01-22 23:50:16.136999: step: 872/529, loss: 0.23649196326732635
2023-01-22 23:50:17.328480: step: 876/529, loss: 0.37153130769729614
2023-01-22 23:50:18.508787: step: 880/529, loss: 1.2816922664642334
2023-01-22 23:50:19.716977: step: 884/529, loss: 0.22412481904029846
2023-01-22 23:50:20.947467: step: 888/529, loss: 0.6680564880371094
2023-01-22 23:50:22.117604: step: 892/529, loss: 0.17364007234573364
2023-01-22 23:50:23.315628: step: 896/529, loss: 0.26113802194595337
2023-01-22 23:50:24.495705: step: 900/529, loss: 0.11926255375146866
2023-01-22 23:50:25.658957: step: 904/529, loss: 0.9900862574577332
2023-01-22 23:50:26.818816: step: 908/529, loss: 0.10782718658447266
2023-01-22 23:50:27.993741: step: 912/529, loss: 0.8222464323043823
2023-01-22 23:50:29.180890: step: 916/529, loss: 0.11105190217494965
2023-01-22 23:50:30.382119: step: 920/529, loss: 0.06733784824609756
2023-01-22 23:50:31.612597: step: 924/529, loss: 0.2141837179660797
2023-01-22 23:50:32.804893: step: 928/529, loss: 0.2782951295375824
2023-01-22 23:50:33.969215: step: 932/529, loss: 0.3528013229370117
2023-01-22 23:50:35.140321: step: 936/529, loss: 0.3250707983970642
2023-01-22 23:50:36.333539: step: 940/529, loss: 0.7469584941864014
2023-01-22 23:50:37.503389: step: 944/529, loss: 0.44888103008270264
2023-01-22 23:50:38.687381: step: 948/529, loss: 0.0593172088265419
2023-01-22 23:50:39.880641: step: 952/529, loss: 0.12156205624341965
2023-01-22 23:50:41.092404: step: 956/529, loss: 0.17953495681285858
2023-01-22 23:50:42.302371: step: 960/529, loss: 0.8286677598953247
2023-01-22 23:50:43.526914: step: 964/529, loss: 0.7979264855384827
2023-01-22 23:50:44.721575: step: 968/529, loss: 0.4452919065952301
2023-01-22 23:50:45.904287: step: 972/529, loss: 0.06292891502380371
2023-01-22 23:50:47.076165: step: 976/529, loss: 0.234127476811409
2023-01-22 23:50:48.269619: step: 980/529, loss: 0.3322582244873047
2023-01-22 23:50:49.431535: step: 984/529, loss: 0.6477928757667542
2023-01-22 23:50:50.611948: step: 988/529, loss: 0.18503180146217346
2023-01-22 23:50:51.789654: step: 992/529, loss: 0.4200851619243622
2023-01-22 23:50:53.009259: step: 996/529, loss: 0.8120313882827759
2023-01-22 23:50:54.205389: step: 1000/529, loss: 0.17442971467971802
2023-01-22 23:50:55.398452: step: 1004/529, loss: 0.23557721078395844
2023-01-22 23:50:56.623816: step: 1008/529, loss: 1.2806655168533325
2023-01-22 23:50:57.790719: step: 1012/529, loss: 0.8511902689933777
2023-01-22 23:50:58.963012: step: 1016/529, loss: 0.11861763149499893
2023-01-22 23:51:00.193063: step: 1020/529, loss: 0.07488727569580078
2023-01-22 23:51:01.430430: step: 1024/529, loss: 0.22666026651859283
2023-01-22 23:51:02.667680: step: 1028/529, loss: 0.18276947736740112
2023-01-22 23:51:03.843624: step: 1032/529, loss: 0.20344991981983185
2023-01-22 23:51:04.998697: step: 1036/529, loss: 0.7284892797470093
2023-01-22 23:51:06.210913: step: 1040/529, loss: 0.1279032826423645
2023-01-22 23:51:07.439015: step: 1044/529, loss: 1.3013429641723633
2023-01-22 23:51:08.636021: step: 1048/529, loss: 0.4718008041381836
2023-01-22 23:51:09.858917: step: 1052/529, loss: 0.5408033132553101
2023-01-22 23:51:11.022803: step: 1056/529, loss: 0.15192851424217224
2023-01-22 23:51:12.195822: step: 1060/529, loss: 0.13008061051368713
2023-01-22 23:51:13.399368: step: 1064/529, loss: 0.4026821255683899
2023-01-22 23:51:14.588393: step: 1068/529, loss: 0.14857178926467896
2023-01-22 23:51:15.810177: step: 1072/529, loss: 0.11449375003576279
2023-01-22 23:51:16.990549: step: 1076/529, loss: 0.27501630783081055
2023-01-22 23:51:18.196516: step: 1080/529, loss: 0.9491043090820312
2023-01-22 23:51:19.388571: step: 1084/529, loss: 0.6536704897880554
2023-01-22 23:51:20.568661: step: 1088/529, loss: 0.2978436350822449
2023-01-22 23:51:21.747880: step: 1092/529, loss: 0.16854123771190643
2023-01-22 23:51:22.971292: step: 1096/529, loss: 0.21513214707374573
2023-01-22 23:51:24.195089: step: 1100/529, loss: 0.9925499558448792
2023-01-22 23:51:25.391281: step: 1104/529, loss: 0.10279889404773712
2023-01-22 23:51:26.546404: step: 1108/529, loss: 0.241289421916008
2023-01-22 23:51:27.725450: step: 1112/529, loss: 0.271989643573761
2023-01-22 23:51:28.911317: step: 1116/529, loss: 0.27203720808029175
2023-01-22 23:51:30.105109: step: 1120/529, loss: 0.06574294716119766
2023-01-22 23:51:31.274063: step: 1124/529, loss: 1.1330227851867676
2023-01-22 23:51:32.530011: step: 1128/529, loss: 0.17437037825584412
2023-01-22 23:51:33.762878: step: 1132/529, loss: 0.13036957383155823
2023-01-22 23:51:34.965263: step: 1136/529, loss: 0.23241043090820312
2023-01-22 23:51:36.160474: step: 1140/529, loss: 1.4849367141723633
2023-01-22 23:51:37.367290: step: 1144/529, loss: 0.22056794166564941
2023-01-22 23:51:38.595923: step: 1148/529, loss: 0.225905179977417
2023-01-22 23:51:39.804572: step: 1152/529, loss: 0.2188694030046463
2023-01-22 23:51:41.013936: step: 1156/529, loss: 0.38801446557044983
2023-01-22 23:51:42.207086: step: 1160/529, loss: 0.3670467734336853
2023-01-22 23:51:43.436236: step: 1164/529, loss: 7.1593804359436035
2023-01-22 23:51:44.644604: step: 1168/529, loss: 0.3402881622314453
2023-01-22 23:51:45.832207: step: 1172/529, loss: 0.3054807782173157
2023-01-22 23:51:47.024155: step: 1176/529, loss: 0.6274528503417969
2023-01-22 23:51:48.172981: step: 1180/529, loss: 0.7883661985397339
2023-01-22 23:51:49.342892: step: 1184/529, loss: 0.10384626686573029
2023-01-22 23:51:50.548057: step: 1188/529, loss: 1.4313936233520508
2023-01-22 23:51:51.695287: step: 1192/529, loss: 0.25158172845840454
2023-01-22 23:51:52.910334: step: 1196/529, loss: 0.28510063886642456
2023-01-22 23:51:54.053354: step: 1200/529, loss: 0.10683298856019974
2023-01-22 23:51:55.269476: step: 1204/529, loss: 1.1170963048934937
2023-01-22 23:51:56.459584: step: 1208/529, loss: 0.19515009224414825
2023-01-22 23:51:57.692228: step: 1212/529, loss: 1.0336393117904663
2023-01-22 23:51:58.875751: step: 1216/529, loss: 3.859346389770508
2023-01-22 23:52:00.108721: step: 1220/529, loss: 0.31862545013427734
2023-01-22 23:52:01.298297: step: 1224/529, loss: 0.1679462492465973
2023-01-22 23:52:02.498420: step: 1228/529, loss: 0.10264472663402557
2023-01-22 23:52:03.657894: step: 1232/529, loss: 1.085010290145874
2023-01-22 23:52:04.862074: step: 1236/529, loss: 0.24031372368335724
2023-01-22 23:52:06.115223: step: 1240/529, loss: 0.3001592755317688
2023-01-22 23:52:07.340077: step: 1244/529, loss: 3.470602512359619
2023-01-22 23:52:08.527928: step: 1248/529, loss: 0.23282481729984283
2023-01-22 23:52:09.731404: step: 1252/529, loss: 0.0997127816081047
2023-01-22 23:52:10.934641: step: 1256/529, loss: 0.059206150472164154
2023-01-22 23:52:12.132948: step: 1260/529, loss: 7.076552867889404
2023-01-22 23:52:13.328688: step: 1264/529, loss: 0.33907976746559143
2023-01-22 23:52:14.550558: step: 1268/529, loss: 0.6730745434761047
2023-01-22 23:52:15.758366: step: 1272/529, loss: 0.12665286660194397
2023-01-22 23:52:16.992312: step: 1276/529, loss: 0.3525141477584839
2023-01-22 23:52:18.160902: step: 1280/529, loss: 0.875916600227356
2023-01-22 23:52:19.342595: step: 1284/529, loss: 0.21333380043506622
2023-01-22 23:52:20.548107: step: 1288/529, loss: 0.1325697898864746
2023-01-22 23:52:21.738111: step: 1292/529, loss: 0.5195043683052063
2023-01-22 23:52:22.977744: step: 1296/529, loss: 0.16322728991508484
2023-01-22 23:52:24.166484: step: 1300/529, loss: 0.162730410695076
2023-01-22 23:52:25.356511: step: 1304/529, loss: 0.7093981504440308
2023-01-22 23:52:26.534903: step: 1308/529, loss: 0.3268682360649109
2023-01-22 23:52:27.737195: step: 1312/529, loss: 0.08718939125537872
2023-01-22 23:52:28.943533: step: 1316/529, loss: 6.731115818023682
2023-01-22 23:52:30.155994: step: 1320/529, loss: 2.189631223678589
2023-01-22 23:52:31.337536: step: 1324/529, loss: 0.12101832032203674
2023-01-22 23:52:32.523013: step: 1328/529, loss: 0.8480373620986938
2023-01-22 23:52:33.742607: step: 1332/529, loss: 0.26181966066360474
2023-01-22 23:52:34.912546: step: 1336/529, loss: 0.2927878499031067
2023-01-22 23:52:36.131667: step: 1340/529, loss: 0.37417975068092346
2023-01-22 23:52:37.365674: step: 1344/529, loss: 0.11520853638648987
2023-01-22 23:52:38.531890: step: 1348/529, loss: 0.07925625145435333
2023-01-22 23:52:39.717040: step: 1352/529, loss: 0.0692962259054184
2023-01-22 23:52:40.920858: step: 1356/529, loss: 0.9576336741447449
2023-01-22 23:52:42.130409: step: 1360/529, loss: 0.7248705625534058
2023-01-22 23:52:43.357496: step: 1364/529, loss: 0.4641962945461273
2023-01-22 23:52:44.572042: step: 1368/529, loss: 0.5704681277275085
2023-01-22 23:52:45.795235: step: 1372/529, loss: 0.4670063257217407
2023-01-22 23:52:47.002163: step: 1376/529, loss: 0.16036167740821838
2023-01-22 23:52:48.169215: step: 1380/529, loss: 0.20905956625938416
2023-01-22 23:52:49.407457: step: 1384/529, loss: 0.49120253324508667
2023-01-22 23:52:50.552112: step: 1388/529, loss: 0.8013932704925537
2023-01-22 23:52:51.753503: step: 1392/529, loss: 0.23077034950256348
2023-01-22 23:52:52.962507: step: 1396/529, loss: 0.15353356301784515
2023-01-22 23:52:54.146784: step: 1400/529, loss: 0.5879707932472229
2023-01-22 23:52:55.341802: step: 1404/529, loss: 0.18980297446250916
2023-01-22 23:52:56.568281: step: 1408/529, loss: 0.3202105760574341
2023-01-22 23:52:57.730374: step: 1412/529, loss: 1.3615949153900146
2023-01-22 23:52:58.888997: step: 1416/529, loss: 0.0819651186466217
2023-01-22 23:53:00.072459: step: 1420/529, loss: 0.12039222568273544
2023-01-22 23:53:01.303589: step: 1424/529, loss: 0.6147060394287109
2023-01-22 23:53:02.493523: step: 1428/529, loss: 0.393871009349823
2023-01-22 23:53:03.692183: step: 1432/529, loss: 0.27766990661621094
2023-01-22 23:53:04.904562: step: 1436/529, loss: 0.7187163233757019
2023-01-22 23:53:06.161671: step: 1440/529, loss: 0.23915091156959534
2023-01-22 23:53:07.327404: step: 1444/529, loss: 6.786542892456055
2023-01-22 23:53:08.532765: step: 1448/529, loss: 0.32126158475875854
2023-01-22 23:53:09.721675: step: 1452/529, loss: 0.6184698939323425
2023-01-22 23:53:10.903874: step: 1456/529, loss: 0.20836858451366425
2023-01-22 23:53:12.074381: step: 1460/529, loss: 0.11626176536083221
2023-01-22 23:53:13.258821: step: 1464/529, loss: 0.09093180298805237
2023-01-22 23:53:14.478974: step: 1468/529, loss: 0.35342901945114136
2023-01-22 23:53:15.649691: step: 1472/529, loss: 0.14807267487049103
2023-01-22 23:53:16.834965: step: 1476/529, loss: 0.935273289680481
2023-01-22 23:53:17.986667: step: 1480/529, loss: 0.9925022125244141
2023-01-22 23:53:19.159936: step: 1484/529, loss: 0.5748090744018555
2023-01-22 23:53:20.357088: step: 1488/529, loss: 0.1639421582221985
2023-01-22 23:53:21.546418: step: 1492/529, loss: 0.24910077452659607
2023-01-22 23:53:22.744564: step: 1496/529, loss: 0.11983104050159454
2023-01-22 23:53:23.939703: step: 1500/529, loss: 0.2815249562263489
2023-01-22 23:53:25.154446: step: 1504/529, loss: 0.10525989532470703
2023-01-22 23:53:26.312755: step: 1508/529, loss: 0.08625535666942596
2023-01-22 23:53:27.482103: step: 1512/529, loss: 0.7407762408256531
2023-01-22 23:53:28.705793: step: 1516/529, loss: 6.597129821777344
2023-01-22 23:53:29.897834: step: 1520/529, loss: 0.4166269898414612
2023-01-22 23:53:31.173189: step: 1524/529, loss: 0.17616614699363708
2023-01-22 23:53:32.420460: step: 1528/529, loss: 0.15646935999393463
2023-01-22 23:53:33.617638: step: 1532/529, loss: 0.7311524152755737
2023-01-22 23:53:34.795065: step: 1536/529, loss: 0.2112540304660797
2023-01-22 23:53:35.998001: step: 1540/529, loss: 0.18518924713134766
2023-01-22 23:53:37.189936: step: 1544/529, loss: 0.3983272612094879
2023-01-22 23:53:38.384494: step: 1548/529, loss: 0.17392587661743164
2023-01-22 23:53:39.559971: step: 1552/529, loss: 0.10151156783103943
2023-01-22 23:53:40.835162: step: 1556/529, loss: 0.23852606117725372
2023-01-22 23:53:42.005794: step: 1560/529, loss: 0.25653284788131714
2023-01-22 23:53:43.224509: step: 1564/529, loss: 0.39179837703704834
2023-01-22 23:53:44.425116: step: 1568/529, loss: 0.11140461266040802
2023-01-22 23:53:45.667144: step: 1572/529, loss: 0.9269602298736572
2023-01-22 23:53:46.855188: step: 1576/529, loss: 0.8949348330497742
2023-01-22 23:53:48.080761: step: 1580/529, loss: 0.18786931037902832
2023-01-22 23:53:49.289568: step: 1584/529, loss: 0.9753708243370056
2023-01-22 23:53:50.460705: step: 1588/529, loss: 0.06753573566675186
2023-01-22 23:53:51.647782: step: 1592/529, loss: 0.8378344774246216
2023-01-22 23:53:52.812868: step: 1596/529, loss: 0.12011952698230743
2023-01-22 23:53:54.005717: step: 1600/529, loss: 0.243224635720253
2023-01-22 23:53:55.226762: step: 1604/529, loss: 0.04439534991979599
2023-01-22 23:53:56.407365: step: 1608/529, loss: 0.32140398025512695
2023-01-22 23:53:57.574076: step: 1612/529, loss: 0.9675464034080505
2023-01-22 23:53:58.820502: step: 1616/529, loss: 0.8656686544418335
2023-01-22 23:54:00.010737: step: 1620/529, loss: 0.32668519020080566
2023-01-22 23:54:01.232193: step: 1624/529, loss: 0.13679972290992737
2023-01-22 23:54:02.395066: step: 1628/529, loss: 0.2460399568080902
2023-01-22 23:54:03.574616: step: 1632/529, loss: 0.5962568521499634
2023-01-22 23:54:04.798055: step: 1636/529, loss: 0.2564878463745117
2023-01-22 23:54:06.054007: step: 1640/529, loss: 0.16419373452663422
2023-01-22 23:54:07.256610: step: 1644/529, loss: 0.6162596940994263
2023-01-22 23:54:08.469426: step: 1648/529, loss: 0.32858067750930786
2023-01-22 23:54:09.648986: step: 1652/529, loss: 0.3730602264404297
2023-01-22 23:54:10.852391: step: 1656/529, loss: 0.13982048630714417
2023-01-22 23:54:12.045529: step: 1660/529, loss: 0.14858514070510864
2023-01-22 23:54:13.265101: step: 1664/529, loss: 0.3491641879081726
2023-01-22 23:54:14.471222: step: 1668/529, loss: 0.5224711298942566
2023-01-22 23:54:15.691810: step: 1672/529, loss: 0.8076386451721191
2023-01-22 23:54:16.892280: step: 1676/529, loss: 0.028235293924808502
2023-01-22 23:54:18.107653: step: 1680/529, loss: 0.6606581211090088
2023-01-22 23:54:19.297749: step: 1684/529, loss: 0.14222599565982819
2023-01-22 23:54:20.485940: step: 1688/529, loss: 1.2723143100738525
2023-01-22 23:54:21.681247: step: 1692/529, loss: 0.16839638352394104
2023-01-22 23:54:22.848693: step: 1696/529, loss: 0.5446098446846008
2023-01-22 23:54:24.064224: step: 1700/529, loss: 0.10425370186567307
2023-01-22 23:54:25.291651: step: 1704/529, loss: 1.117645263671875
2023-01-22 23:54:26.565561: step: 1708/529, loss: 0.5030900835990906
2023-01-22 23:54:27.735594: step: 1712/529, loss: 0.11759386211633682
2023-01-22 23:54:28.926583: step: 1716/529, loss: 0.0623415969312191
2023-01-22 23:54:30.130965: step: 1720/529, loss: 0.17961858212947845
2023-01-22 23:54:31.311420: step: 1724/529, loss: 0.702845573425293
2023-01-22 23:54:32.537827: step: 1728/529, loss: 0.26210615038871765
2023-01-22 23:54:33.712914: step: 1732/529, loss: 0.24270649254322052
2023-01-22 23:54:34.899798: step: 1736/529, loss: 0.16498994827270508
2023-01-22 23:54:36.155274: step: 1740/529, loss: 0.4635719358921051
2023-01-22 23:54:37.348287: step: 1744/529, loss: 0.23091131448745728
2023-01-22 23:54:38.565457: step: 1748/529, loss: 0.2698693871498108
2023-01-22 23:54:39.726468: step: 1752/529, loss: 0.03807687759399414
2023-01-22 23:54:40.906757: step: 1756/529, loss: 0.1386251002550125
2023-01-22 23:54:42.077330: step: 1760/529, loss: 0.3056437373161316
2023-01-22 23:54:43.268565: step: 1764/529, loss: 1.1966632604599
2023-01-22 23:54:44.479650: step: 1768/529, loss: 0.1674070805311203
2023-01-22 23:54:45.734378: step: 1772/529, loss: 0.3627280592918396
2023-01-22 23:54:46.932360: step: 1776/529, loss: 0.10936679691076279
2023-01-22 23:54:48.141100: step: 1780/529, loss: 0.14010506868362427
2023-01-22 23:54:49.318159: step: 1784/529, loss: 0.5304542779922485
2023-01-22 23:54:50.502548: step: 1788/529, loss: 0.1013612300157547
2023-01-22 23:54:51.713162: step: 1792/529, loss: 0.15223565697669983
2023-01-22 23:54:52.918879: step: 1796/529, loss: 0.1163141280412674
2023-01-22 23:54:54.136378: step: 1800/529, loss: 0.38689059019088745
2023-01-22 23:54:55.314865: step: 1804/529, loss: 0.15308718383312225
2023-01-22 23:54:56.522234: step: 1808/529, loss: 0.29952287673950195
2023-01-22 23:54:57.704493: step: 1812/529, loss: 1.1570935249328613
2023-01-22 23:54:58.878188: step: 1816/529, loss: 0.11791582405567169
2023-01-22 23:55:00.086878: step: 1820/529, loss: 0.9169925451278687
2023-01-22 23:55:01.302268: step: 1824/529, loss: 0.6506383419036865
2023-01-22 23:55:02.508854: step: 1828/529, loss: 0.14234380424022675
2023-01-22 23:55:03.702724: step: 1832/529, loss: 0.4231431484222412
2023-01-22 23:55:04.875534: step: 1836/529, loss: 0.9142149090766907
2023-01-22 23:55:06.068971: step: 1840/529, loss: 0.17554154992103577
2023-01-22 23:55:07.291572: step: 1844/529, loss: 0.07488904148340225
2023-01-22 23:55:08.465346: step: 1848/529, loss: 0.2322222888469696
2023-01-22 23:55:09.643828: step: 1852/529, loss: 0.1308133602142334
2023-01-22 23:55:10.852807: step: 1856/529, loss: 0.37691235542297363
2023-01-22 23:55:12.095326: step: 1860/529, loss: 0.15815718472003937
2023-01-22 23:55:13.323027: step: 1864/529, loss: 0.14444312453269958
2023-01-22 23:55:14.631301: step: 1868/529, loss: 0.18990585207939148
2023-01-22 23:55:15.822080: step: 1872/529, loss: 0.18873673677444458
2023-01-22 23:55:17.049815: step: 1876/529, loss: 0.3121578097343445
2023-01-22 23:55:18.272868: step: 1880/529, loss: 0.37086376547813416
2023-01-22 23:55:19.486257: step: 1884/529, loss: 0.5689072608947754
2023-01-22 23:55:20.714985: step: 1888/529, loss: 1.9780168533325195
2023-01-22 23:55:21.928060: step: 1892/529, loss: 0.42991095781326294
2023-01-22 23:55:23.105626: step: 1896/529, loss: 1.3082197904586792
2023-01-22 23:55:24.339775: step: 1900/529, loss: 0.331615149974823
2023-01-22 23:55:25.522982: step: 1904/529, loss: 0.8489152789115906
2023-01-22 23:55:26.752406: step: 1908/529, loss: 0.17250938713550568
2023-01-22 23:55:27.949303: step: 1912/529, loss: 0.6576183438301086
2023-01-22 23:55:29.155874: step: 1916/529, loss: 0.7333192825317383
2023-01-22 23:55:30.315383: step: 1920/529, loss: 0.037929631769657135
2023-01-22 23:55:31.529856: step: 1924/529, loss: 0.2748446464538574
2023-01-22 23:55:32.699252: step: 1928/529, loss: 0.15305586159229279
2023-01-22 23:55:33.923787: step: 1932/529, loss: 0.6235495805740356
2023-01-22 23:55:35.103158: step: 1936/529, loss: 0.16210369765758514
2023-01-22 23:55:36.349889: step: 1940/529, loss: 0.6080190539360046
2023-01-22 23:55:37.550942: step: 1944/529, loss: 0.029820919036865234
2023-01-22 23:55:38.747313: step: 1948/529, loss: 0.3276333808898926
2023-01-22 23:55:39.947521: step: 1952/529, loss: 0.7028959393501282
2023-01-22 23:55:41.110652: step: 1956/529, loss: 0.2764837145805359
2023-01-22 23:55:42.302038: step: 1960/529, loss: 0.11809177696704865
2023-01-22 23:55:43.515765: step: 1964/529, loss: 0.33259010314941406
2023-01-22 23:55:44.733093: step: 1968/529, loss: 0.08955440670251846
2023-01-22 23:55:45.933675: step: 1972/529, loss: 0.2231583595275879
2023-01-22 23:55:47.168123: step: 1976/529, loss: 0.1280420422554016
2023-01-22 23:55:48.357353: step: 1980/529, loss: 0.7044577598571777
2023-01-22 23:55:49.545794: step: 1984/529, loss: 1.7870354652404785
2023-01-22 23:55:50.774095: step: 1988/529, loss: 0.7346959114074707
2023-01-22 23:55:51.980889: step: 1992/529, loss: 0.15680542588233948
2023-01-22 23:55:53.207883: step: 1996/529, loss: 6.2414374351501465
2023-01-22 23:55:54.428692: step: 2000/529, loss: 6.797178745269775
2023-01-22 23:55:55.618924: step: 2004/529, loss: 0.9583694934844971
2023-01-22 23:55:56.812876: step: 2008/529, loss: 0.15111970901489258
2023-01-22 23:55:58.026623: step: 2012/529, loss: 0.21521183848381042
2023-01-22 23:55:59.249372: step: 2016/529, loss: 0.2288244366645813
2023-01-22 23:56:00.477389: step: 2020/529, loss: 0.3413427472114563
2023-01-22 23:56:01.671923: step: 2024/529, loss: 0.20657825469970703
2023-01-22 23:56:02.894172: step: 2028/529, loss: 0.6548783183097839
2023-01-22 23:56:04.084039: step: 2032/529, loss: 0.23776665329933167
2023-01-22 23:56:05.330927: step: 2036/529, loss: 1.865551233291626
2023-01-22 23:56:06.530359: step: 2040/529, loss: 2.972569465637207
2023-01-22 23:56:07.742802: step: 2044/529, loss: 0.3656849265098572
2023-01-22 23:56:08.933384: step: 2048/529, loss: 0.3478592038154602
2023-01-22 23:56:10.118938: step: 2052/529, loss: 0.6147340536117554
2023-01-22 23:56:11.327725: step: 2056/529, loss: 0.21546894311904907
2023-01-22 23:56:12.591162: step: 2060/529, loss: 0.7534360289573669
2023-01-22 23:56:13.795516: step: 2064/529, loss: 0.18866434693336487
2023-01-22 23:56:14.971769: step: 2068/529, loss: 1.1781119108200073
2023-01-22 23:56:16.148800: step: 2072/529, loss: 0.19519153237342834
2023-01-22 23:56:17.357348: step: 2076/529, loss: 0.7405006885528564
2023-01-22 23:56:18.598207: step: 2080/529, loss: 0.15303802490234375
2023-01-22 23:56:19.786218: step: 2084/529, loss: 0.11230993270874023
2023-01-22 23:56:20.963510: step: 2088/529, loss: 2.185525894165039
2023-01-22 23:56:22.133495: step: 2092/529, loss: 0.1410335898399353
2023-01-22 23:56:23.342828: step: 2096/529, loss: 0.10806441307067871
2023-01-22 23:56:24.537654: step: 2100/529, loss: 0.3362579345703125
2023-01-22 23:56:25.736588: step: 2104/529, loss: 1.2092134952545166
2023-01-22 23:56:26.978771: step: 2108/529, loss: 0.45085421204566956
2023-01-22 23:56:28.186806: step: 2112/529, loss: 0.5155454874038696
2023-01-22 23:56:29.373148: step: 2116/529, loss: 1.3302206993103027
==================================================
Loss: 0.602
--------------------
Dev: {'event': {'p': 0.5331491712707183, 'r': 0.7709720372836218, 'f1': 0.6303756124115406}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.538004246284501, 'r': 0.7591372079089275, 'f1': 0.6297216699801192}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5632183908045977, 'r': 0.9074074074074074, 'f1': 0.6950354609929078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.625, 'r': 0.47619047619047616, 'f1': 0.5405405405405405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.4722222222222222, 'r': 0.4722222222222222, 'f1': 0.4722222222222222}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5331491712707183, 'r': 0.7709720372836218, 'f1': 0.6303756124115406}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.538004246284501, 'r': 0.7591372079089275, 'f1': 0.6297216699801192}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5632183908045977, 'r': 0.9074074074074074, 'f1': 0.6950354609929078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:57:22.426440: step: 4/529, loss: 0.5109049081802368
2023-01-22 23:57:23.690523: step: 8/529, loss: 0.5732133984565735
2023-01-22 23:57:24.885811: step: 12/529, loss: 0.34648609161376953
2023-01-22 23:57:26.100167: step: 16/529, loss: 6.525545120239258
2023-01-22 23:57:27.304762: step: 20/529, loss: 0.314157634973526
2023-01-22 23:57:28.452945: step: 24/529, loss: 0.016307448968291283
2023-01-22 23:57:29.617360: step: 28/529, loss: 0.15647979080677032
2023-01-22 23:57:30.802591: step: 32/529, loss: 0.12410131096839905
2023-01-22 23:57:31.989087: step: 36/529, loss: 0.02915172651410103
2023-01-22 23:57:33.222030: step: 40/529, loss: 0.11873731017112732
2023-01-22 23:57:34.425339: step: 44/529, loss: 0.7078371047973633
2023-01-22 23:57:35.668505: step: 48/529, loss: 0.2989673912525177
2023-01-22 23:57:36.838643: step: 52/529, loss: 0.46930694580078125
2023-01-22 23:57:38.044137: step: 56/529, loss: 0.4022432565689087
2023-01-22 23:57:39.252546: step: 60/529, loss: 0.2874813973903656
2023-01-22 23:57:40.491620: step: 64/529, loss: 0.9133665561676025
2023-01-22 23:57:41.731430: step: 68/529, loss: 0.4046599268913269
2023-01-22 23:57:42.922130: step: 72/529, loss: 0.24358081817626953
2023-01-22 23:57:44.153872: step: 76/529, loss: 0.09161201119422913
2023-01-22 23:57:45.325220: step: 80/529, loss: 0.4488402009010315
2023-01-22 23:57:46.495178: step: 84/529, loss: 0.22898206114768982
2023-01-22 23:57:47.692830: step: 88/529, loss: 1.3305326700210571
2023-01-22 23:57:48.918792: step: 92/529, loss: 0.5690761804580688
2023-01-22 23:57:50.084998: step: 96/529, loss: 0.7966560125350952
2023-01-22 23:57:51.297765: step: 100/529, loss: 1.448947548866272
2023-01-22 23:57:52.515642: step: 104/529, loss: 0.5288487672805786
2023-01-22 23:57:53.702422: step: 108/529, loss: 1.1439018249511719
2023-01-22 23:57:54.951339: step: 112/529, loss: 6.854997634887695
2023-01-22 23:57:56.180510: step: 116/529, loss: 0.464391827583313
2023-01-22 23:57:57.369992: step: 120/529, loss: 0.14924831688404083
2023-01-22 23:57:58.538470: step: 124/529, loss: 0.08640303462743759
2023-01-22 23:57:59.729028: step: 128/529, loss: 0.6751454472541809
2023-01-22 23:58:00.967980: step: 132/529, loss: 0.19832420349121094
2023-01-22 23:58:02.160471: step: 136/529, loss: 1.6694527864456177
2023-01-22 23:58:03.354382: step: 140/529, loss: 0.2284616380929947
2023-01-22 23:58:04.542488: step: 144/529, loss: 0.36430272459983826
2023-01-22 23:58:05.736208: step: 148/529, loss: 0.25114500522613525
2023-01-22 23:58:06.992394: step: 152/529, loss: 0.05569835007190704
2023-01-22 23:58:08.193219: step: 156/529, loss: 0.13806477189064026
2023-01-22 23:58:09.414334: step: 160/529, loss: 0.3269232511520386
2023-01-22 23:58:10.590522: step: 164/529, loss: 1.2911128997802734
2023-01-22 23:58:11.783378: step: 168/529, loss: 0.8094059228897095
2023-01-22 23:58:12.935036: step: 172/529, loss: 0.27050113677978516
2023-01-22 23:58:14.104018: step: 176/529, loss: 0.21918554604053497
2023-01-22 23:58:15.320501: step: 180/529, loss: 0.21964406967163086
2023-01-22 23:58:16.497167: step: 184/529, loss: 0.09067407250404358
2023-01-22 23:58:17.675660: step: 188/529, loss: 0.5115076303482056
2023-01-22 23:58:18.846064: step: 192/529, loss: 0.21389245986938477
2023-01-22 23:58:20.059194: step: 196/529, loss: 0.7584950923919678
2023-01-22 23:58:21.269284: step: 200/529, loss: 0.05163879692554474
2023-01-22 23:58:22.436081: step: 204/529, loss: 0.2306777983903885
2023-01-22 23:58:23.632787: step: 208/529, loss: 0.07892732322216034
2023-01-22 23:58:24.845700: step: 212/529, loss: 0.12173176556825638
2023-01-22 23:58:26.037531: step: 216/529, loss: 0.2150571048259735
2023-01-22 23:58:27.255243: step: 220/529, loss: 0.04045877605676651
2023-01-22 23:58:28.443835: step: 224/529, loss: 0.1015826165676117
2023-01-22 23:58:29.616356: step: 228/529, loss: 0.16814184188842773
2023-01-22 23:58:30.814170: step: 232/529, loss: 6.8595662117004395
2023-01-22 23:58:31.963280: step: 236/529, loss: 6.207767486572266
2023-01-22 23:58:33.177371: step: 240/529, loss: 0.08937664330005646
2023-01-22 23:58:34.387182: step: 244/529, loss: 0.41951608657836914
2023-01-22 23:58:35.594853: step: 248/529, loss: 0.08552493900060654
2023-01-22 23:58:36.775446: step: 252/529, loss: 0.2039077877998352
2023-01-22 23:58:37.938365: step: 256/529, loss: 0.056791454553604126
2023-01-22 23:58:39.114268: step: 260/529, loss: 0.44299763441085815
2023-01-22 23:58:40.279107: step: 264/529, loss: 0.05849161744117737
2023-01-22 23:58:41.463357: step: 268/529, loss: 0.7345892786979675
2023-01-22 23:58:42.724170: step: 272/529, loss: 0.7938448190689087
2023-01-22 23:58:43.930748: step: 276/529, loss: 0.9983171224594116
2023-01-22 23:58:45.109651: step: 280/529, loss: 0.08468132466077805
2023-01-22 23:58:46.295300: step: 284/529, loss: 0.17036715149879456
2023-01-22 23:58:47.497508: step: 288/529, loss: 0.20651274919509888
2023-01-22 23:58:48.722078: step: 292/529, loss: 0.09717493504285812
2023-01-22 23:58:49.944685: step: 296/529, loss: 0.7852643132209778
2023-01-22 23:58:51.124928: step: 300/529, loss: 0.2795930504798889
2023-01-22 23:58:52.305410: step: 304/529, loss: 0.13673889636993408
2023-01-22 23:58:53.490139: step: 308/529, loss: 0.5701743960380554
2023-01-22 23:58:54.716130: step: 312/529, loss: 1.238905429840088
2023-01-22 23:58:55.944791: step: 316/529, loss: 0.2844606339931488
2023-01-22 23:58:57.146054: step: 320/529, loss: 0.1601576805114746
2023-01-22 23:58:58.320445: step: 324/529, loss: 0.25467196106910706
2023-01-22 23:58:59.524164: step: 328/529, loss: 2.1542980670928955
2023-01-22 23:59:00.739988: step: 332/529, loss: 0.35070475935935974
2023-01-22 23:59:01.973423: step: 336/529, loss: 0.14309945702552795
2023-01-22 23:59:03.202407: step: 340/529, loss: 0.4852376878261566
2023-01-22 23:59:04.423447: step: 344/529, loss: 0.12140484154224396
2023-01-22 23:59:05.623881: step: 348/529, loss: 0.10886368900537491
2023-01-22 23:59:06.841699: step: 352/529, loss: 0.19722777605056763
2023-01-22 23:59:08.028445: step: 356/529, loss: 6.47122049331665
2023-01-22 23:59:09.250973: step: 360/529, loss: 0.22177237272262573
2023-01-22 23:59:10.417795: step: 364/529, loss: 0.1820840835571289
2023-01-22 23:59:11.620878: step: 368/529, loss: 0.16937704384326935
2023-01-22 23:59:12.788083: step: 372/529, loss: 0.39619603753089905
2023-01-22 23:59:14.011869: step: 376/529, loss: 0.2773638963699341
2023-01-22 23:59:15.216954: step: 380/529, loss: 0.18199768662452698
2023-01-22 23:59:16.419463: step: 384/529, loss: 0.12582755088806152
2023-01-22 23:59:17.631953: step: 388/529, loss: 0.15641355514526367
2023-01-22 23:59:18.844552: step: 392/529, loss: 1.1052515506744385
2023-01-22 23:59:20.033881: step: 396/529, loss: 0.3339536786079407
2023-01-22 23:59:21.196444: step: 400/529, loss: 0.036341190338134766
2023-01-22 23:59:22.392919: step: 404/529, loss: 0.3012176752090454
2023-01-22 23:59:23.597119: step: 408/529, loss: 0.179648756980896
2023-01-22 23:59:24.782503: step: 412/529, loss: 0.060222819447517395
2023-01-22 23:59:25.958276: step: 416/529, loss: 0.7835181951522827
2023-01-22 23:59:27.129624: step: 420/529, loss: 0.2005150020122528
2023-01-22 23:59:28.288793: step: 424/529, loss: 0.49489861726760864
2023-01-22 23:59:29.482489: step: 428/529, loss: 0.12319083511829376
2023-01-22 23:59:30.682490: step: 432/529, loss: 0.12356844544410706
2023-01-22 23:59:31.927273: step: 436/529, loss: 0.21137410402297974
2023-01-22 23:59:33.104286: step: 440/529, loss: 0.24912777543067932
2023-01-22 23:59:34.288048: step: 444/529, loss: 0.9127544164657593
2023-01-22 23:59:35.480867: step: 448/529, loss: 0.2940702438354492
2023-01-22 23:59:36.653149: step: 452/529, loss: 1.3996059894561768
2023-01-22 23:59:37.837264: step: 456/529, loss: 0.7008556723594666
2023-01-22 23:59:39.036589: step: 460/529, loss: 0.1283189356327057
2023-01-22 23:59:40.242274: step: 464/529, loss: 0.05786309391260147
2023-01-22 23:59:41.467385: step: 468/529, loss: 6.357701778411865
2023-01-22 23:59:42.682262: step: 472/529, loss: 0.838046669960022
2023-01-22 23:59:43.865847: step: 476/529, loss: 0.20604373514652252
2023-01-22 23:59:45.040084: step: 480/529, loss: 0.12215200066566467
2023-01-22 23:59:46.225542: step: 484/529, loss: 0.4220316708087921
2023-01-22 23:59:47.404593: step: 488/529, loss: 0.6431341171264648
2023-01-22 23:59:48.565455: step: 492/529, loss: 0.309932142496109
2023-01-22 23:59:49.791335: step: 496/529, loss: 6.305740833282471
2023-01-22 23:59:51.015283: step: 500/529, loss: 0.5798084139823914
2023-01-22 23:59:52.232770: step: 504/529, loss: 1.1165878772735596
2023-01-22 23:59:53.436693: step: 508/529, loss: 0.42484939098358154
2023-01-22 23:59:54.624547: step: 512/529, loss: 0.14822569489479065
2023-01-22 23:59:55.811027: step: 516/529, loss: 0.6631903052330017
2023-01-22 23:59:57.042347: step: 520/529, loss: 0.10189656913280487
2023-01-22 23:59:58.274911: step: 524/529, loss: 0.10649529099464417
2023-01-22 23:59:59.453750: step: 528/529, loss: 0.244944229722023
2023-01-23 00:00:00.618164: step: 532/529, loss: 0.18202033638954163
2023-01-23 00:00:01.798764: step: 536/529, loss: 0.08590392768383026
2023-01-23 00:00:03.001421: step: 540/529, loss: 0.14160548150539398
2023-01-23 00:00:04.229010: step: 544/529, loss: 2.385071277618408
2023-01-23 00:00:05.437808: step: 548/529, loss: 0.11255516856908798
2023-01-23 00:00:06.627957: step: 552/529, loss: 0.8202965259552002
2023-01-23 00:00:07.808431: step: 556/529, loss: 0.15509234368801117
2023-01-23 00:00:09.033803: step: 560/529, loss: 0.10815811157226562
2023-01-23 00:00:10.226958: step: 564/529, loss: 0.14583225548267365
2023-01-23 00:00:11.423409: step: 568/529, loss: 0.061933234333992004
2023-01-23 00:00:12.640615: step: 572/529, loss: 0.22751104831695557
2023-01-23 00:00:13.839511: step: 576/529, loss: 6.163327217102051
2023-01-23 00:00:15.022532: step: 580/529, loss: 0.9687484502792358
2023-01-23 00:00:16.247171: step: 584/529, loss: 0.6361277103424072
2023-01-23 00:00:17.450217: step: 588/529, loss: 0.14939336478710175
2023-01-23 00:00:18.602977: step: 592/529, loss: 0.5203262567520142
2023-01-23 00:00:19.813083: step: 596/529, loss: 0.23648720979690552
2023-01-23 00:00:20.993389: step: 600/529, loss: 0.17689228057861328
2023-01-23 00:00:22.152204: step: 604/529, loss: 0.920056164264679
2023-01-23 00:00:23.401352: step: 608/529, loss: 0.5570315718650818
2023-01-23 00:00:24.614089: step: 612/529, loss: 0.2973543107509613
2023-01-23 00:00:25.799641: step: 616/529, loss: 1.263750433921814
2023-01-23 00:00:26.975408: step: 620/529, loss: 0.3595085144042969
2023-01-23 00:00:28.151084: step: 624/529, loss: 0.5976070165634155
2023-01-23 00:00:29.349054: step: 628/529, loss: 0.4708814322948456
2023-01-23 00:00:30.552888: step: 632/529, loss: 0.2147449553012848
2023-01-23 00:00:31.699506: step: 636/529, loss: 0.4652779698371887
2023-01-23 00:00:32.962423: step: 640/529, loss: 0.17160634696483612
2023-01-23 00:00:34.124231: step: 644/529, loss: 0.13353107869625092
2023-01-23 00:00:35.310407: step: 648/529, loss: 0.20135146379470825
2023-01-23 00:00:36.471347: step: 652/529, loss: 1.2545086145401
2023-01-23 00:00:37.641172: step: 656/529, loss: 6.808806896209717
2023-01-23 00:00:38.827348: step: 660/529, loss: 0.1724664717912674
2023-01-23 00:00:40.031531: step: 664/529, loss: 0.6020802855491638
2023-01-23 00:00:41.248585: step: 668/529, loss: 0.20385518670082092
2023-01-23 00:00:42.458308: step: 672/529, loss: 0.0566895455121994
2023-01-23 00:00:43.703368: step: 676/529, loss: 0.15117855370044708
2023-01-23 00:00:44.962782: step: 680/529, loss: 0.30817556381225586
2023-01-23 00:00:46.146983: step: 684/529, loss: 0.20230546593666077
2023-01-23 00:00:47.327187: step: 688/529, loss: 0.56947922706604
2023-01-23 00:00:48.510786: step: 692/529, loss: 0.7333808541297913
2023-01-23 00:00:49.698759: step: 696/529, loss: 0.21116027235984802
2023-01-23 00:00:50.894620: step: 700/529, loss: 0.3762238621711731
2023-01-23 00:00:52.068153: step: 704/529, loss: 0.1824939250946045
2023-01-23 00:00:53.233078: step: 708/529, loss: 0.04479799419641495
2023-01-23 00:00:54.440516: step: 712/529, loss: 1.4403314590454102
2023-01-23 00:00:55.611356: step: 716/529, loss: 0.14453621208667755
2023-01-23 00:00:56.785864: step: 720/529, loss: 0.027975894510746002
2023-01-23 00:00:57.911343: step: 724/529, loss: 0.0838829055428505
2023-01-23 00:00:59.064635: step: 728/529, loss: 0.06790085136890411
2023-01-23 00:01:00.271327: step: 732/529, loss: 0.02364349365234375
2023-01-23 00:01:01.506987: step: 736/529, loss: 0.2607499957084656
2023-01-23 00:01:02.665286: step: 740/529, loss: 0.7614808678627014
2023-01-23 00:01:03.835020: step: 744/529, loss: 0.0895475521683693
2023-01-23 00:01:04.998590: step: 748/529, loss: 0.04825344309210777
2023-01-23 00:01:06.159236: step: 752/529, loss: 0.17991089820861816
2023-01-23 00:01:07.357797: step: 756/529, loss: 0.411781370639801
2023-01-23 00:01:08.554372: step: 760/529, loss: 0.2736542820930481
2023-01-23 00:01:09.725318: step: 764/529, loss: 0.24587230384349823
2023-01-23 00:01:10.911667: step: 768/529, loss: 0.2465108036994934
2023-01-23 00:01:12.074072: step: 772/529, loss: 0.21385689079761505
2023-01-23 00:01:13.275684: step: 776/529, loss: 0.6135229468345642
2023-01-23 00:01:14.486916: step: 780/529, loss: 0.1008480042219162
2023-01-23 00:01:15.688978: step: 784/529, loss: 0.05660128593444824
2023-01-23 00:01:16.864767: step: 788/529, loss: 0.21203604340553284
2023-01-23 00:01:18.045666: step: 792/529, loss: 0.4665027856826782
2023-01-23 00:01:19.248593: step: 796/529, loss: 1.4546465873718262
2023-01-23 00:01:20.430436: step: 800/529, loss: 0.12697425484657288
2023-01-23 00:01:21.619233: step: 804/529, loss: 0.1567641794681549
2023-01-23 00:01:22.831577: step: 808/529, loss: 1.7793183326721191
2023-01-23 00:01:24.019433: step: 812/529, loss: 0.3820658326148987
2023-01-23 00:01:25.193703: step: 816/529, loss: 6.272670269012451
2023-01-23 00:01:26.380123: step: 820/529, loss: 0.18555909395217896
2023-01-23 00:01:27.567166: step: 824/529, loss: 0.15330100059509277
2023-01-23 00:01:28.763088: step: 828/529, loss: 0.2847210764884949
2023-01-23 00:01:29.992902: step: 832/529, loss: 0.11364109814167023
2023-01-23 00:01:31.233022: step: 836/529, loss: 0.6854779124259949
2023-01-23 00:01:32.445244: step: 840/529, loss: 1.2999851703643799
2023-01-23 00:01:33.695125: step: 844/529, loss: 0.8045494556427002
2023-01-23 00:01:34.869177: step: 848/529, loss: 0.2060120701789856
2023-01-23 00:01:36.073114: step: 852/529, loss: 0.06410017609596252
2023-01-23 00:01:37.259323: step: 856/529, loss: 0.16923925280570984
2023-01-23 00:01:38.472490: step: 860/529, loss: 0.5960256457328796
2023-01-23 00:01:39.637403: step: 864/529, loss: 0.20848403871059418
2023-01-23 00:01:40.838261: step: 868/529, loss: 0.17049500346183777
2023-01-23 00:01:42.017648: step: 872/529, loss: 0.11787271499633789
2023-01-23 00:01:43.209071: step: 876/529, loss: 0.09072265774011612
2023-01-23 00:01:44.411616: step: 880/529, loss: 0.21228435635566711
2023-01-23 00:01:45.611327: step: 884/529, loss: 0.5185469388961792
2023-01-23 00:01:46.816015: step: 888/529, loss: 0.1307760775089264
2023-01-23 00:01:48.006351: step: 892/529, loss: 0.2846911549568176
2023-01-23 00:01:49.204433: step: 896/529, loss: 1.2598540782928467
2023-01-23 00:01:50.420467: step: 900/529, loss: 0.793027937412262
2023-01-23 00:01:51.612340: step: 904/529, loss: 0.05815587192773819
2023-01-23 00:01:52.802024: step: 908/529, loss: 0.8849951028823853
2023-01-23 00:01:53.944480: step: 912/529, loss: 0.6899126768112183
2023-01-23 00:01:55.126129: step: 916/529, loss: 0.07221993803977966
2023-01-23 00:01:56.359133: step: 920/529, loss: 0.11165991425514221
2023-01-23 00:01:57.580716: step: 924/529, loss: 0.2791863679885864
2023-01-23 00:01:58.807362: step: 928/529, loss: 0.19381389021873474
2023-01-23 00:02:00.007056: step: 932/529, loss: 1.0754708051681519
2023-01-23 00:02:01.219336: step: 936/529, loss: 0.29282352328300476
2023-01-23 00:02:02.415960: step: 940/529, loss: 1.066131353378296
2023-01-23 00:02:03.605556: step: 944/529, loss: 0.20834693312644958
2023-01-23 00:02:04.805926: step: 948/529, loss: 0.24618284404277802
2023-01-23 00:02:06.027537: step: 952/529, loss: 0.7845458984375
2023-01-23 00:02:07.233512: step: 956/529, loss: 0.09872083365917206
2023-01-23 00:02:08.387682: step: 960/529, loss: 0.08556786179542542
2023-01-23 00:02:09.629092: step: 964/529, loss: 1.088285207748413
2023-01-23 00:02:10.797629: step: 968/529, loss: 0.07125687599182129
2023-01-23 00:02:11.983555: step: 972/529, loss: 1.1183327436447144
2023-01-23 00:02:13.191277: step: 976/529, loss: 0.2211429625749588
2023-01-23 00:02:14.383239: step: 980/529, loss: 0.941512405872345
2023-01-23 00:02:15.548805: step: 984/529, loss: 0.14278888702392578
2023-01-23 00:02:16.776511: step: 988/529, loss: 0.20018434524536133
2023-01-23 00:02:17.964833: step: 992/529, loss: 1.1467530727386475
2023-01-23 00:02:19.188942: step: 996/529, loss: 0.0738748088479042
2023-01-23 00:02:20.355234: step: 1000/529, loss: 0.15200920403003693
2023-01-23 00:02:21.558747: step: 1004/529, loss: 0.15242335200309753
2023-01-23 00:02:22.696807: step: 1008/529, loss: 0.710332989692688
2023-01-23 00:02:23.869141: step: 1012/529, loss: 0.3448978364467621
2023-01-23 00:02:25.049688: step: 1016/529, loss: 0.07349491119384766
2023-01-23 00:02:26.266227: step: 1020/529, loss: 0.8348375558853149
2023-01-23 00:02:27.468434: step: 1024/529, loss: 1.107804536819458
2023-01-23 00:02:28.668905: step: 1028/529, loss: 0.11502466350793839
2023-01-23 00:02:29.906713: step: 1032/529, loss: 0.32818615436553955
2023-01-23 00:02:31.142682: step: 1036/529, loss: 1.8135936260223389
2023-01-23 00:02:32.325898: step: 1040/529, loss: 0.30856990814208984
2023-01-23 00:02:33.556535: step: 1044/529, loss: 0.38151323795318604
2023-01-23 00:02:34.754712: step: 1048/529, loss: 0.6319208145141602
2023-01-23 00:02:35.942249: step: 1052/529, loss: 0.665233850479126
2023-01-23 00:02:37.193101: step: 1056/529, loss: 0.07123690098524094
2023-01-23 00:02:38.420669: step: 1060/529, loss: 0.13324937224388123
2023-01-23 00:02:39.608151: step: 1064/529, loss: 0.048981428146362305
2023-01-23 00:02:40.810491: step: 1068/529, loss: 0.1499921828508377
2023-01-23 00:02:42.002203: step: 1072/529, loss: 0.29684311151504517
2023-01-23 00:02:43.188908: step: 1076/529, loss: 0.10205487906932831
2023-01-23 00:02:44.400912: step: 1080/529, loss: 1.0443146228790283
2023-01-23 00:02:45.611647: step: 1084/529, loss: 0.4533035159111023
2023-01-23 00:02:46.836224: step: 1088/529, loss: 0.28314828872680664
2023-01-23 00:02:48.156725: step: 1092/529, loss: 0.2152790129184723
2023-01-23 00:02:49.346792: step: 1096/529, loss: 0.25698530673980713
2023-01-23 00:02:50.515036: step: 1100/529, loss: 0.07423897087574005
2023-01-23 00:02:51.731426: step: 1104/529, loss: 0.20360970497131348
2023-01-23 00:02:52.920806: step: 1108/529, loss: 0.07388553768396378
2023-01-23 00:02:54.150027: step: 1112/529, loss: 0.4620504081249237
2023-01-23 00:02:55.388420: step: 1116/529, loss: 6.0797295570373535
2023-01-23 00:02:56.562738: step: 1120/529, loss: 0.10023251175880432
2023-01-23 00:02:57.785323: step: 1124/529, loss: 0.5048360824584961
2023-01-23 00:02:58.971797: step: 1128/529, loss: 0.10539598762989044
2023-01-23 00:03:00.190021: step: 1132/529, loss: 0.3162137269973755
2023-01-23 00:03:01.390226: step: 1136/529, loss: 0.202396959066391
2023-01-23 00:03:02.588778: step: 1140/529, loss: 0.8612620830535889
2023-01-23 00:03:03.830197: step: 1144/529, loss: 0.12645836174488068
2023-01-23 00:03:05.042156: step: 1148/529, loss: 6.365048408508301
2023-01-23 00:03:06.246406: step: 1152/529, loss: 0.6691771745681763
2023-01-23 00:03:07.404294: step: 1156/529, loss: 0.5278523564338684
2023-01-23 00:03:08.626628: step: 1160/529, loss: 0.4883405566215515
2023-01-23 00:03:09.783692: step: 1164/529, loss: 6.404985427856445
2023-01-23 00:03:10.979086: step: 1168/529, loss: 0.15984183549880981
2023-01-23 00:03:12.164461: step: 1172/529, loss: 0.04248318821191788
2023-01-23 00:03:13.420986: step: 1176/529, loss: 0.11476249992847443
2023-01-23 00:03:14.654939: step: 1180/529, loss: 0.15053291618824005
2023-01-23 00:03:15.850068: step: 1184/529, loss: 0.07252518832683563
2023-01-23 00:03:17.034801: step: 1188/529, loss: 0.8370453119277954
2023-01-23 00:03:18.206492: step: 1192/529, loss: 0.18597184121608734
2023-01-23 00:03:19.412447: step: 1196/529, loss: 0.18255853652954102
2023-01-23 00:03:20.605623: step: 1200/529, loss: 0.8022556304931641
2023-01-23 00:03:21.784543: step: 1204/529, loss: 0.12340659648180008
2023-01-23 00:03:22.947310: step: 1208/529, loss: 0.15646138787269592
2023-01-23 00:03:24.153581: step: 1212/529, loss: 0.39518415927886963
2023-01-23 00:03:25.344906: step: 1216/529, loss: 0.18684397637844086
2023-01-23 00:03:26.555086: step: 1220/529, loss: 0.012744761072099209
2023-01-23 00:03:27.772297: step: 1224/529, loss: 1.641706109046936
2023-01-23 00:03:28.986100: step: 1228/529, loss: 0.35822969675064087
2023-01-23 00:03:30.167148: step: 1232/529, loss: 0.05193042755126953
2023-01-23 00:03:31.332598: step: 1236/529, loss: 1.405439853668213
2023-01-23 00:03:32.514614: step: 1240/529, loss: 0.02931075170636177
2023-01-23 00:03:33.724663: step: 1244/529, loss: 0.10154262185096741
2023-01-23 00:03:34.950605: step: 1248/529, loss: 0.5561035871505737
2023-01-23 00:03:36.135451: step: 1252/529, loss: 0.13672709465026855
2023-01-23 00:03:37.342755: step: 1256/529, loss: 0.2545683681964874
2023-01-23 00:03:38.500145: step: 1260/529, loss: 0.20950919389724731
2023-01-23 00:03:39.695485: step: 1264/529, loss: 0.15473446249961853
2023-01-23 00:03:40.903225: step: 1268/529, loss: 0.13981465995311737
2023-01-23 00:03:42.158509: step: 1272/529, loss: 0.7003820538520813
2023-01-23 00:03:43.360330: step: 1276/529, loss: 0.07366523891687393
2023-01-23 00:03:44.577993: step: 1280/529, loss: 0.06368014961481094
2023-01-23 00:03:45.748304: step: 1284/529, loss: 0.19977210462093353
2023-01-23 00:03:46.942791: step: 1288/529, loss: 0.2320655882358551
2023-01-23 00:03:48.156372: step: 1292/529, loss: 0.04660029709339142
2023-01-23 00:03:49.354913: step: 1296/529, loss: 0.06706514209508896
2023-01-23 00:03:50.541929: step: 1300/529, loss: 0.1906927227973938
2023-01-23 00:03:51.708531: step: 1304/529, loss: 0.3095458149909973
2023-01-23 00:03:52.880471: step: 1308/529, loss: 0.19476346671581268
2023-01-23 00:03:54.050687: step: 1312/529, loss: 0.4397938847541809
2023-01-23 00:03:55.211105: step: 1316/529, loss: 0.6443344354629517
2023-01-23 00:03:56.396849: step: 1320/529, loss: 0.15377309918403625
2023-01-23 00:03:57.602743: step: 1324/529, loss: 0.28709226846694946
2023-01-23 00:03:58.783020: step: 1328/529, loss: 0.20887838304042816
2023-01-23 00:04:00.003328: step: 1332/529, loss: 0.762951672077179
2023-01-23 00:04:01.203850: step: 1336/529, loss: 0.12815412878990173
2023-01-23 00:04:02.412208: step: 1340/529, loss: 0.17199945449829102
2023-01-23 00:04:03.616327: step: 1344/529, loss: 0.03209657967090607
2023-01-23 00:04:04.876200: step: 1348/529, loss: 0.24765682220458984
2023-01-23 00:04:06.095236: step: 1352/529, loss: 0.11222286522388458
2023-01-23 00:04:07.312971: step: 1356/529, loss: 1.4803955554962158
2023-01-23 00:04:08.504548: step: 1360/529, loss: 0.058991432189941406
2023-01-23 00:04:09.689871: step: 1364/529, loss: 0.1906137466430664
2023-01-23 00:04:10.882623: step: 1368/529, loss: 0.14589159190654755
2023-01-23 00:04:12.079446: step: 1372/529, loss: 0.7356292009353638
2023-01-23 00:04:13.259017: step: 1376/529, loss: 0.0292937271296978
2023-01-23 00:04:14.428947: step: 1380/529, loss: 0.1148996651172638
2023-01-23 00:04:15.619588: step: 1384/529, loss: 0.4950922429561615
2023-01-23 00:04:16.784288: step: 1388/529, loss: 0.6311390995979309
2023-01-23 00:04:17.965452: step: 1392/529, loss: 0.22987575829029083
2023-01-23 00:04:19.152543: step: 1396/529, loss: 0.10704431682825089
2023-01-23 00:04:20.339446: step: 1400/529, loss: 0.1649210900068283
2023-01-23 00:04:21.485658: step: 1404/529, loss: 2.6152503490448
2023-01-23 00:04:22.667628: step: 1408/529, loss: 0.6494420766830444
2023-01-23 00:04:23.870811: step: 1412/529, loss: 0.8145421743392944
2023-01-23 00:04:25.093246: step: 1416/529, loss: 0.5473567843437195
2023-01-23 00:04:26.279418: step: 1420/529, loss: 0.1390179544687271
2023-01-23 00:04:27.437988: step: 1424/529, loss: 0.8674865365028381
2023-01-23 00:04:28.663187: step: 1428/529, loss: 0.10704083740711212
2023-01-23 00:04:29.872316: step: 1432/529, loss: 0.3758760690689087
2023-01-23 00:04:31.092181: step: 1436/529, loss: 0.6295431852340698
2023-01-23 00:04:32.270162: step: 1440/529, loss: 0.38997578620910645
2023-01-23 00:04:33.469592: step: 1444/529, loss: 0.11759305000305176
2023-01-23 00:04:34.650627: step: 1448/529, loss: 0.7263033986091614
2023-01-23 00:04:35.821388: step: 1452/529, loss: 0.4058622121810913
2023-01-23 00:04:37.026153: step: 1456/529, loss: 0.2892892062664032
2023-01-23 00:04:38.207108: step: 1460/529, loss: 0.26381224393844604
2023-01-23 00:04:39.390481: step: 1464/529, loss: 0.8017733693122864
2023-01-23 00:04:40.579116: step: 1468/529, loss: 0.34554481506347656
2023-01-23 00:04:41.789926: step: 1472/529, loss: 0.18896789848804474
2023-01-23 00:04:42.956455: step: 1476/529, loss: 0.31995201110839844
2023-01-23 00:04:44.126921: step: 1480/529, loss: 0.7046374678611755
2023-01-23 00:04:45.371792: step: 1484/529, loss: 0.2419232428073883
2023-01-23 00:04:46.545895: step: 1488/529, loss: 0.6109528541564941
2023-01-23 00:04:47.702244: step: 1492/529, loss: 0.1533583700656891
2023-01-23 00:04:48.920984: step: 1496/529, loss: 0.15195946395397186
2023-01-23 00:04:50.190222: step: 1500/529, loss: 0.7536163926124573
2023-01-23 00:04:51.375847: step: 1504/529, loss: 0.048946477472782135
2023-01-23 00:04:52.569081: step: 1508/529, loss: 0.1295931339263916
2023-01-23 00:04:53.748854: step: 1512/529, loss: 0.5034002661705017
2023-01-23 00:04:54.943611: step: 1516/529, loss: 0.177537739276886
2023-01-23 00:04:56.126573: step: 1520/529, loss: 0.762010931968689
2023-01-23 00:04:57.313368: step: 1524/529, loss: 0.3654606342315674
2023-01-23 00:04:58.522993: step: 1528/529, loss: 0.24029389023780823
2023-01-23 00:04:59.693532: step: 1532/529, loss: 0.902274489402771
2023-01-23 00:05:00.890450: step: 1536/529, loss: 0.1744929850101471
2023-01-23 00:05:02.138327: step: 1540/529, loss: 0.26031026244163513
2023-01-23 00:05:03.373507: step: 1544/529, loss: 0.08439760655164719
2023-01-23 00:05:04.630231: step: 1548/529, loss: 0.03405600041151047
2023-01-23 00:05:05.816132: step: 1552/529, loss: 0.0916815772652626
2023-01-23 00:05:07.019532: step: 1556/529, loss: 0.3352050185203552
2023-01-23 00:05:08.220080: step: 1560/529, loss: 0.3663368225097656
2023-01-23 00:05:09.417173: step: 1564/529, loss: 0.05466461181640625
2023-01-23 00:05:10.617249: step: 1568/529, loss: 0.49147921800613403
2023-01-23 00:05:11.839059: step: 1572/529, loss: 0.2640061378479004
2023-01-23 00:05:13.068042: step: 1576/529, loss: 0.3838962912559509
2023-01-23 00:05:14.298663: step: 1580/529, loss: 0.24831877648830414
2023-01-23 00:05:15.514410: step: 1584/529, loss: 0.11662021279335022
2023-01-23 00:05:16.736479: step: 1588/529, loss: 0.20084114372730255
2023-01-23 00:05:17.927196: step: 1592/529, loss: 0.309184730052948
2023-01-23 00:05:19.100243: step: 1596/529, loss: 0.43160516023635864
2023-01-23 00:05:20.301737: step: 1600/529, loss: 0.2824947237968445
2023-01-23 00:05:21.510223: step: 1604/529, loss: 0.8066858649253845
2023-01-23 00:05:22.682148: step: 1608/529, loss: 0.19391365349292755
2023-01-23 00:05:23.867181: step: 1612/529, loss: 0.5352584719657898
2023-01-23 00:05:25.107698: step: 1616/529, loss: 0.1670810729265213
2023-01-23 00:05:26.288041: step: 1620/529, loss: 1.385312795639038
2023-01-23 00:05:27.463399: step: 1624/529, loss: 0.13863128423690796
2023-01-23 00:05:28.639286: step: 1628/529, loss: 0.7014477252960205
2023-01-23 00:05:29.856751: step: 1632/529, loss: 0.47930222749710083
2023-01-23 00:05:31.037708: step: 1636/529, loss: 0.3952499330043793
2023-01-23 00:05:32.253763: step: 1640/529, loss: 1.3406263589859009
2023-01-23 00:05:33.481740: step: 1644/529, loss: 0.11925850063562393
2023-01-23 00:05:34.732623: step: 1648/529, loss: 0.7813748121261597
2023-01-23 00:05:35.918614: step: 1652/529, loss: 0.25027528405189514
2023-01-23 00:05:37.102423: step: 1656/529, loss: 0.4950025677680969
2023-01-23 00:05:38.294982: step: 1660/529, loss: 1.7744572162628174
2023-01-23 00:05:39.525878: step: 1664/529, loss: 0.14767208695411682
2023-01-23 00:05:40.696599: step: 1668/529, loss: 0.43377143144607544
2023-01-23 00:05:41.953665: step: 1672/529, loss: 0.27826356887817383
2023-01-23 00:05:43.165981: step: 1676/529, loss: 0.55902099609375
2023-01-23 00:05:44.357546: step: 1680/529, loss: 0.08716002106666565
2023-01-23 00:05:45.637173: step: 1684/529, loss: 0.12237024307250977
2023-01-23 00:05:46.832918: step: 1688/529, loss: 0.14731532335281372
2023-01-23 00:05:48.006303: step: 1692/529, loss: 0.10474033653736115
2023-01-23 00:05:49.227264: step: 1696/529, loss: 0.030937576666474342
2023-01-23 00:05:50.388940: step: 1700/529, loss: 0.04436516761779785
2023-01-23 00:05:51.576461: step: 1704/529, loss: 0.3761083781719208
2023-01-23 00:05:52.784856: step: 1708/529, loss: 0.4886413514614105
2023-01-23 00:05:53.992115: step: 1712/529, loss: 0.1376006305217743
2023-01-23 00:05:55.209044: step: 1716/529, loss: 0.054845474660396576
2023-01-23 00:05:56.385913: step: 1720/529, loss: 0.7890036702156067
2023-01-23 00:05:57.558953: step: 1724/529, loss: 0.2800571322441101
2023-01-23 00:05:58.730142: step: 1728/529, loss: 0.1427145004272461
2023-01-23 00:05:59.936236: step: 1732/529, loss: 0.10956144332885742
2023-01-23 00:06:01.119781: step: 1736/529, loss: 0.11455106735229492
2023-01-23 00:06:02.316750: step: 1740/529, loss: 0.39195671677589417
2023-01-23 00:06:03.539305: step: 1744/529, loss: 0.12060967087745667
2023-01-23 00:06:04.773681: step: 1748/529, loss: 0.6424474716186523
2023-01-23 00:06:05.953864: step: 1752/529, loss: 0.6103021502494812
2023-01-23 00:06:07.148623: step: 1756/529, loss: 0.3288912773132324
2023-01-23 00:06:08.388798: step: 1760/529, loss: 0.13594570755958557
2023-01-23 00:06:09.587271: step: 1764/529, loss: 0.06404094398021698
2023-01-23 00:06:10.818886: step: 1768/529, loss: 0.0946381539106369
2023-01-23 00:06:12.003932: step: 1772/529, loss: 0.1461222767829895
2023-01-23 00:06:13.212422: step: 1776/529, loss: 0.08773450553417206
2023-01-23 00:06:14.409854: step: 1780/529, loss: 0.575681209564209
2023-01-23 00:06:15.648462: step: 1784/529, loss: 0.1255619078874588
2023-01-23 00:06:16.857502: step: 1788/529, loss: 0.7396607398986816
2023-01-23 00:06:18.026962: step: 1792/529, loss: 0.0425536148250103
2023-01-23 00:06:19.214510: step: 1796/529, loss: 0.10895557701587677
2023-01-23 00:06:20.410191: step: 1800/529, loss: 0.4857218861579895
2023-01-23 00:06:21.624416: step: 1804/529, loss: 0.5225170850753784
2023-01-23 00:06:22.812279: step: 1808/529, loss: 0.281673401594162
2023-01-23 00:06:24.004324: step: 1812/529, loss: 1.1940937042236328
2023-01-23 00:06:25.234277: step: 1816/529, loss: 0.210743248462677
2023-01-23 00:06:26.431993: step: 1820/529, loss: 0.43428170680999756
2023-01-23 00:06:27.646658: step: 1824/529, loss: 0.06261620670557022
2023-01-23 00:06:28.818113: step: 1828/529, loss: 0.21472720801830292
2023-01-23 00:06:30.014433: step: 1832/529, loss: 0.27495822310447693
2023-01-23 00:06:31.234419: step: 1836/529, loss: 0.326531320810318
2023-01-23 00:06:32.493196: step: 1840/529, loss: 0.1997019350528717
2023-01-23 00:06:33.728486: step: 1844/529, loss: 0.1821242868900299
2023-01-23 00:06:34.918759: step: 1848/529, loss: 0.15181970596313477
2023-01-23 00:06:36.141183: step: 1852/529, loss: 0.6286935806274414
2023-01-23 00:06:37.331440: step: 1856/529, loss: 0.14447203278541565
2023-01-23 00:06:38.489029: step: 1860/529, loss: 0.15174522995948792
2023-01-23 00:06:39.702212: step: 1864/529, loss: 0.2580508589744568
2023-01-23 00:06:40.888340: step: 1868/529, loss: 0.10839777439832687
2023-01-23 00:06:42.076528: step: 1872/529, loss: 0.07493095099925995
2023-01-23 00:06:43.300246: step: 1876/529, loss: 0.15180546045303345
2023-01-23 00:06:44.516869: step: 1880/529, loss: 0.45923691987991333
2023-01-23 00:06:45.735828: step: 1884/529, loss: 0.11712709069252014
2023-01-23 00:06:46.978185: step: 1888/529, loss: 0.6078892946243286
2023-01-23 00:06:48.229670: step: 1892/529, loss: 0.0914234146475792
2023-01-23 00:06:49.437601: step: 1896/529, loss: 0.8523756861686707
2023-01-23 00:06:50.622366: step: 1900/529, loss: 0.9335610866546631
2023-01-23 00:06:51.855979: step: 1904/529, loss: 0.23920392990112305
2023-01-23 00:06:53.066878: step: 1908/529, loss: 0.09496049582958221
2023-01-23 00:06:54.260562: step: 1912/529, loss: 0.3865712285041809
2023-01-23 00:06:55.481046: step: 1916/529, loss: 0.12209845334291458
2023-01-23 00:06:56.681145: step: 1920/529, loss: 0.3588685393333435
2023-01-23 00:06:57.876178: step: 1924/529, loss: 1.01535964012146
2023-01-23 00:06:59.108201: step: 1928/529, loss: 0.12728175520896912
2023-01-23 00:07:00.322816: step: 1932/529, loss: 0.13523274660110474
2023-01-23 00:07:01.550153: step: 1936/529, loss: 0.3225170075893402
2023-01-23 00:07:02.766968: step: 1940/529, loss: 0.15277346968650818
2023-01-23 00:07:03.962615: step: 1944/529, loss: 1.0891169309616089
2023-01-23 00:07:05.254789: step: 1948/529, loss: 0.4466021656990051
2023-01-23 00:07:06.439235: step: 1952/529, loss: 0.9465929865837097
2023-01-23 00:07:07.656770: step: 1956/529, loss: 0.23988103866577148
2023-01-23 00:07:08.856873: step: 1960/529, loss: 0.05404920503497124
2023-01-23 00:07:10.057696: step: 1964/529, loss: 0.6631994247436523
2023-01-23 00:07:11.279762: step: 1968/529, loss: 0.17227205634117126
2023-01-23 00:07:12.473248: step: 1972/529, loss: 0.10587625950574875
2023-01-23 00:07:13.679697: step: 1976/529, loss: 0.46818360686302185
2023-01-23 00:07:14.898315: step: 1980/529, loss: 0.38124608993530273
2023-01-23 00:07:16.107420: step: 1984/529, loss: 0.03677845001220703
2023-01-23 00:07:17.324300: step: 1988/529, loss: 6.685095310211182
2023-01-23 00:07:18.523467: step: 1992/529, loss: 0.22513896226882935
2023-01-23 00:07:19.718810: step: 1996/529, loss: 0.1617441177368164
2023-01-23 00:07:20.898761: step: 2000/529, loss: 0.03118271939456463
2023-01-23 00:07:22.116514: step: 2004/529, loss: 0.18503373861312866
2023-01-23 00:07:23.274025: step: 2008/529, loss: 0.8965415954589844
2023-01-23 00:07:24.478369: step: 2012/529, loss: 0.5357754230499268
2023-01-23 00:07:25.718975: step: 2016/529, loss: 1.1179760694503784
2023-01-23 00:07:26.955264: step: 2020/529, loss: 0.09247355908155441
2023-01-23 00:07:28.191434: step: 2024/529, loss: 0.11763171851634979
2023-01-23 00:07:29.408069: step: 2028/529, loss: 0.1918288767337799
2023-01-23 00:07:30.593715: step: 2032/529, loss: 0.16145601868629456
2023-01-23 00:07:31.818143: step: 2036/529, loss: 0.8493215441703796
2023-01-23 00:07:33.051349: step: 2040/529, loss: 1.5145994424819946
2023-01-23 00:07:34.283265: step: 2044/529, loss: 0.24307653307914734
2023-01-23 00:07:35.478128: step: 2048/529, loss: 0.20988675951957703
2023-01-23 00:07:36.698485: step: 2052/529, loss: 0.8853633999824524
2023-01-23 00:07:37.931290: step: 2056/529, loss: 0.1410486251115799
2023-01-23 00:07:39.141369: step: 2060/529, loss: 0.11293602734804153
2023-01-23 00:07:40.364132: step: 2064/529, loss: 0.2375413030385971
2023-01-23 00:07:41.601839: step: 2068/529, loss: 0.7124490737915039
2023-01-23 00:07:42.881476: step: 2072/529, loss: 0.1207837164402008
2023-01-23 00:07:44.055036: step: 2076/529, loss: 0.04087388515472412
2023-01-23 00:07:45.248712: step: 2080/529, loss: 1.069754719734192
2023-01-23 00:07:46.471429: step: 2084/529, loss: 0.08507518470287323
2023-01-23 00:07:47.727088: step: 2088/529, loss: 0.11504700779914856
2023-01-23 00:07:48.929190: step: 2092/529, loss: 0.24900245666503906
2023-01-23 00:07:50.118391: step: 2096/529, loss: 0.6266627311706543
2023-01-23 00:07:51.315776: step: 2100/529, loss: 0.022880934178829193
2023-01-23 00:07:52.483495: step: 2104/529, loss: 0.2722981572151184
2023-01-23 00:07:53.647750: step: 2108/529, loss: 0.4525381922721863
2023-01-23 00:07:54.828194: step: 2112/529, loss: 0.621144711971283
2023-01-23 00:07:56.026410: step: 2116/529, loss: 0.058031752705574036
==================================================
Loss: 0.545
--------------------
Dev: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.65, 'r': 0.4126984126984127, 'f1': 0.5048543689320388}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, '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': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5942350332594235, 'r': 0.7137150466045273, 'f1': 0.6485178463399879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5454545454545454, 'r': 0.6578789694427801, 'f1': 0.5964149918522542}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:08:57.564947: step: 4/529, loss: 0.2502412796020508
2023-01-23 00:08:58.720427: step: 8/529, loss: 0.21559953689575195
2023-01-23 00:08:59.947805: step: 12/529, loss: 0.19210587441921234
2023-01-23 00:09:01.201479: step: 16/529, loss: 0.03894238546490669
2023-01-23 00:09:02.403999: step: 20/529, loss: 0.2251969277858734
2023-01-23 00:09:03.582471: step: 24/529, loss: 0.06638240814208984
2023-01-23 00:09:04.845233: step: 28/529, loss: 0.23995256423950195
2023-01-23 00:09:06.050858: step: 32/529, loss: 0.06886114925146103
2023-01-23 00:09:07.307826: step: 36/529, loss: 0.12067346274852753
2023-01-23 00:09:08.503995: step: 40/529, loss: 0.16794681549072266
2023-01-23 00:09:09.675918: step: 44/529, loss: 0.07075369358062744
2023-01-23 00:09:10.876819: step: 48/529, loss: 0.12292347103357315
2023-01-23 00:09:12.062812: step: 52/529, loss: 0.6521369218826294
2023-01-23 00:09:13.245059: step: 56/529, loss: 0.05216493830084801
2023-01-23 00:09:14.423394: step: 60/529, loss: 0.09195118397474289
2023-01-23 00:09:15.616802: step: 64/529, loss: 0.09234986454248428
2023-01-23 00:09:16.793142: step: 68/529, loss: 0.17367076873779297
2023-01-23 00:09:18.014539: step: 72/529, loss: 0.22387734055519104
2023-01-23 00:09:19.254943: step: 76/529, loss: 0.08996899425983429
2023-01-23 00:09:20.469927: step: 80/529, loss: 0.21819201111793518
2023-01-23 00:09:21.654306: step: 84/529, loss: 0.11473675072193146
2023-01-23 00:09:22.870933: step: 88/529, loss: 0.082275390625
2023-01-23 00:09:24.092674: step: 92/529, loss: 0.19086790084838867
2023-01-23 00:09:25.288191: step: 96/529, loss: 0.04892168194055557
2023-01-23 00:09:26.471576: step: 100/529, loss: 0.8130882978439331
2023-01-23 00:09:27.685772: step: 104/529, loss: 0.14128953218460083
2023-01-23 00:09:28.882636: step: 108/529, loss: 0.656221866607666
2023-01-23 00:09:30.079926: step: 112/529, loss: 0.20366695523262024
2023-01-23 00:09:31.321350: step: 116/529, loss: 0.25114861130714417
2023-01-23 00:09:32.481991: step: 120/529, loss: 0.10173463821411133
2023-01-23 00:09:33.696284: step: 124/529, loss: 0.1308383047580719
2023-01-23 00:09:34.872143: step: 128/529, loss: 0.6807863116264343
2023-01-23 00:09:36.032458: step: 132/529, loss: 0.2657139301300049
2023-01-23 00:09:37.251433: step: 136/529, loss: 0.16858011484146118
2023-01-23 00:09:38.518734: step: 140/529, loss: 0.17533636093139648
2023-01-23 00:09:39.720661: step: 144/529, loss: 0.15527839958667755
2023-01-23 00:09:40.968186: step: 148/529, loss: 0.13998566567897797
2023-01-23 00:09:42.147121: step: 152/529, loss: 6.27352237701416
2023-01-23 00:09:43.362461: step: 156/529, loss: 0.7151943445205688
2023-01-23 00:09:44.560966: step: 160/529, loss: 0.3012429177761078
2023-01-23 00:09:45.804689: step: 164/529, loss: 0.11990289390087128
2023-01-23 00:09:46.978916: step: 168/529, loss: 0.13066883385181427
2023-01-23 00:09:48.183271: step: 172/529, loss: 0.629902720451355
2023-01-23 00:09:49.398030: step: 176/529, loss: 0.14125214517116547
2023-01-23 00:09:50.580348: step: 180/529, loss: 0.11176681518554688
2023-01-23 00:09:51.772544: step: 184/529, loss: 0.27583953738212585
2023-01-23 00:09:52.956890: step: 188/529, loss: 0.07218732684850693
2023-01-23 00:09:54.144690: step: 192/529, loss: 6.145091533660889
2023-01-23 00:09:55.331633: step: 196/529, loss: 0.09435997903347015
2023-01-23 00:09:56.552761: step: 200/529, loss: 0.20767942070960999
2023-01-23 00:09:57.759304: step: 204/529, loss: 0.08072328567504883
2023-01-23 00:09:59.000290: step: 208/529, loss: 0.06381388008594513
2023-01-23 00:10:00.186848: step: 212/529, loss: 0.025726724416017532
2023-01-23 00:10:01.371052: step: 216/529, loss: 5.529368877410889
2023-01-23 00:10:02.582173: step: 220/529, loss: 0.28097963333129883
2023-01-23 00:10:03.771344: step: 224/529, loss: 0.10538144409656525
2023-01-23 00:10:04.966809: step: 228/529, loss: 0.6860580444335938
2023-01-23 00:10:06.159442: step: 232/529, loss: 0.44918498396873474
2023-01-23 00:10:07.308625: step: 236/529, loss: 0.17048045992851257
2023-01-23 00:10:08.532652: step: 240/529, loss: 0.10401153564453125
2023-01-23 00:10:09.701942: step: 244/529, loss: 0.18155184388160706
2023-01-23 00:10:10.909333: step: 248/529, loss: 0.6845030784606934
2023-01-23 00:10:12.096930: step: 252/529, loss: 0.3077487051486969
2023-01-23 00:10:13.312504: step: 256/529, loss: 0.09060707688331604
2023-01-23 00:10:14.518752: step: 260/529, loss: 0.30717048048973083
2023-01-23 00:10:15.708424: step: 264/529, loss: 0.08343382179737091
2023-01-23 00:10:16.966557: step: 268/529, loss: 0.47527599334716797
2023-01-23 00:10:18.119084: step: 272/529, loss: 0.024470090866088867
2023-01-23 00:10:19.303534: step: 276/529, loss: 0.30808818340301514
2023-01-23 00:10:20.497403: step: 280/529, loss: 0.7827953100204468
2023-01-23 00:10:21.695712: step: 284/529, loss: 0.7774907350540161
2023-01-23 00:10:22.864766: step: 288/529, loss: 0.03212566301226616
2023-01-23 00:10:24.070523: step: 292/529, loss: 0.9486326575279236
2023-01-23 00:10:25.273477: step: 296/529, loss: 0.2746638357639313
2023-01-23 00:10:26.431530: step: 300/529, loss: 0.16681557893753052
2023-01-23 00:10:27.639614: step: 304/529, loss: 0.08173046261072159
2023-01-23 00:10:28.841498: step: 308/529, loss: 6.288697719573975
2023-01-23 00:10:30.042314: step: 312/529, loss: 0.14964056015014648
2023-01-23 00:10:31.278286: step: 316/529, loss: 0.2742324471473694
2023-01-23 00:10:32.464609: step: 320/529, loss: 0.14716453850269318
2023-01-23 00:10:33.625880: step: 324/529, loss: 0.5346121191978455
2023-01-23 00:10:34.843820: step: 328/529, loss: 0.5574740171432495
2023-01-23 00:10:36.038421: step: 332/529, loss: 0.2730085253715515
2023-01-23 00:10:37.234828: step: 336/529, loss: 0.12539997696876526
2023-01-23 00:10:38.397195: step: 340/529, loss: 0.04188213497400284
2023-01-23 00:10:39.585051: step: 344/529, loss: 0.14948859810829163
2023-01-23 00:10:40.792480: step: 348/529, loss: 0.2436954528093338
2023-01-23 00:10:42.028020: step: 352/529, loss: 1.1195698976516724
2023-01-23 00:10:43.221007: step: 356/529, loss: 0.2025630921125412
2023-01-23 00:10:44.412053: step: 360/529, loss: 0.5436082482337952
2023-01-23 00:10:45.596048: step: 364/529, loss: 0.20505733788013458
2023-01-23 00:10:46.817220: step: 368/529, loss: 0.6219170689582825
2023-01-23 00:10:47.965014: step: 372/529, loss: 0.9745227098464966
2023-01-23 00:10:49.145746: step: 376/529, loss: 0.09567232429981232
2023-01-23 00:10:50.302142: step: 380/529, loss: 0.10994787514209747
2023-01-23 00:10:51.481223: step: 384/529, loss: 0.06637553870677948
2023-01-23 00:10:52.701003: step: 388/529, loss: 0.38644522428512573
2023-01-23 00:10:53.884534: step: 392/529, loss: 0.12255477905273438
2023-01-23 00:10:55.062379: step: 396/529, loss: 0.5542092323303223
2023-01-23 00:10:56.290118: step: 400/529, loss: 0.053899191319942474
2023-01-23 00:10:57.501844: step: 404/529, loss: 0.4054171144962311
2023-01-23 00:10:58.714948: step: 408/529, loss: 0.24461831152439117
2023-01-23 00:10:59.956902: step: 412/529, loss: 0.07134656608104706
2023-01-23 00:11:01.123891: step: 416/529, loss: 0.043059565126895905
2023-01-23 00:11:02.297519: step: 420/529, loss: 0.08745727688074112
2023-01-23 00:11:03.473372: step: 424/529, loss: 0.1223725825548172
2023-01-23 00:11:04.657723: step: 428/529, loss: 0.5513986349105835
2023-01-23 00:11:05.837062: step: 432/529, loss: 1.014221429824829
2023-01-23 00:11:07.060436: step: 436/529, loss: 0.7200706005096436
2023-01-23 00:11:08.218033: step: 440/529, loss: 0.04349174350500107
2023-01-23 00:11:09.357717: step: 444/529, loss: 0.137525275349617
2023-01-23 00:11:10.562504: step: 448/529, loss: 0.7859518527984619
2023-01-23 00:11:11.744319: step: 452/529, loss: 0.6683461666107178
2023-01-23 00:11:12.987410: step: 456/529, loss: 0.2929232716560364
2023-01-23 00:11:14.206972: step: 460/529, loss: 0.3526670038700104
2023-01-23 00:11:15.400223: step: 464/529, loss: 0.12022700905799866
2023-01-23 00:11:16.587263: step: 468/529, loss: 0.17588362097740173
2023-01-23 00:11:17.788262: step: 472/529, loss: 0.08686542510986328
2023-01-23 00:11:18.985931: step: 476/529, loss: 0.23461675643920898
2023-01-23 00:11:20.212952: step: 480/529, loss: 0.14042958617210388
2023-01-23 00:11:21.378690: step: 484/529, loss: 0.07853622734546661
2023-01-23 00:11:22.565764: step: 488/529, loss: 1.4251697063446045
2023-01-23 00:11:23.786037: step: 492/529, loss: 5.416125774383545
2023-01-23 00:11:24.971872: step: 496/529, loss: 0.16637592017650604
2023-01-23 00:11:26.154681: step: 500/529, loss: 0.04373054578900337
2023-01-23 00:11:27.336137: step: 504/529, loss: 0.7165427803993225
2023-01-23 00:11:28.547342: step: 508/529, loss: 0.09049635380506516
2023-01-23 00:11:29.756022: step: 512/529, loss: 0.25090402364730835
2023-01-23 00:11:30.930928: step: 516/529, loss: 0.18650618195533752
2023-01-23 00:11:32.137326: step: 520/529, loss: 0.9127770662307739
2023-01-23 00:11:33.310786: step: 524/529, loss: 0.1572188436985016
2023-01-23 00:11:34.513284: step: 528/529, loss: 0.4635128974914551
2023-01-23 00:11:35.705992: step: 532/529, loss: 0.7403554320335388
2023-01-23 00:11:36.941638: step: 536/529, loss: 0.1569177657365799
2023-01-23 00:11:38.185905: step: 540/529, loss: 0.6742302179336548
2023-01-23 00:11:39.449733: step: 544/529, loss: 0.1890222579240799
2023-01-23 00:11:40.633849: step: 548/529, loss: 0.06375548988580704
2023-01-23 00:11:41.844821: step: 552/529, loss: 0.1572054922580719
2023-01-23 00:11:43.037681: step: 556/529, loss: 0.4539460241794586
2023-01-23 00:11:44.232227: step: 560/529, loss: 0.07919806987047195
2023-01-23 00:11:45.436517: step: 564/529, loss: 0.06230345368385315
2023-01-23 00:11:46.642986: step: 568/529, loss: 0.2389349341392517
2023-01-23 00:11:47.837298: step: 572/529, loss: 0.18917961418628693
2023-01-23 00:11:49.023233: step: 576/529, loss: 0.6497324109077454
2023-01-23 00:11:50.252544: step: 580/529, loss: 0.4957512319087982
2023-01-23 00:11:51.462468: step: 584/529, loss: 0.6842037439346313
2023-01-23 00:11:52.677396: step: 588/529, loss: 0.10157127678394318
2023-01-23 00:11:53.868937: step: 592/529, loss: 0.10126753151416779
2023-01-23 00:11:55.083520: step: 596/529, loss: 0.0788264274597168
2023-01-23 00:11:56.281348: step: 600/529, loss: 0.14935550093650818
2023-01-23 00:11:57.471325: step: 604/529, loss: 0.07220669090747833
2023-01-23 00:11:58.661664: step: 608/529, loss: 0.36246538162231445
2023-01-23 00:11:59.843855: step: 612/529, loss: 0.21938246488571167
2023-01-23 00:12:01.061471: step: 616/529, loss: 0.12169580906629562
2023-01-23 00:12:02.241029: step: 620/529, loss: 0.1293935328722
2023-01-23 00:12:03.456908: step: 624/529, loss: 0.17244437336921692
2023-01-23 00:12:04.702791: step: 628/529, loss: 0.3392561674118042
2023-01-23 00:12:05.945172: step: 632/529, loss: 0.11422643065452576
2023-01-23 00:12:07.186085: step: 636/529, loss: 0.126190185546875
2023-01-23 00:12:08.368609: step: 640/529, loss: 0.37342149019241333
2023-01-23 00:12:09.560305: step: 644/529, loss: 0.24555817246437073
2023-01-23 00:12:10.751494: step: 648/529, loss: 0.6092405319213867
2023-01-23 00:12:11.977664: step: 652/529, loss: 0.05914516746997833
2023-01-23 00:12:13.166318: step: 656/529, loss: 1.1573021411895752
2023-01-23 00:12:14.358374: step: 660/529, loss: 1.499564528465271
2023-01-23 00:12:15.555892: step: 664/529, loss: 0.12421464920043945
2023-01-23 00:12:16.752610: step: 668/529, loss: 0.1295979619026184
2023-01-23 00:12:17.938014: step: 672/529, loss: 0.06339740753173828
2023-01-23 00:12:19.158787: step: 676/529, loss: 0.4435332119464874
2023-01-23 00:12:20.311331: step: 680/529, loss: 0.2729329466819763
2023-01-23 00:12:21.495004: step: 684/529, loss: 0.15566444396972656
2023-01-23 00:12:22.711144: step: 688/529, loss: 0.2621266543865204
2023-01-23 00:12:23.932690: step: 692/529, loss: 0.5348869562149048
2023-01-23 00:12:25.147569: step: 696/529, loss: 1.1988469362258911
2023-01-23 00:12:26.328662: step: 700/529, loss: 0.2524147033691406
2023-01-23 00:12:27.552871: step: 704/529, loss: 0.10733585059642792
2023-01-23 00:12:28.717404: step: 708/529, loss: 0.07933025062084198
2023-01-23 00:12:29.928379: step: 712/529, loss: 0.028967857360839844
2023-01-23 00:12:31.114607: step: 716/529, loss: 0.9275743365287781
2023-01-23 00:12:32.292275: step: 720/529, loss: 0.20581255853176117
2023-01-23 00:12:33.459921: step: 724/529, loss: 0.12088622897863388
2023-01-23 00:12:34.625569: step: 728/529, loss: 0.7049477100372314
2023-01-23 00:12:35.791571: step: 732/529, loss: 0.7286319136619568
2023-01-23 00:12:36.985564: step: 736/529, loss: 0.6800567507743835
2023-01-23 00:12:38.173171: step: 740/529, loss: 0.13806940615177155
2023-01-23 00:12:39.359924: step: 744/529, loss: 0.7309344410896301
2023-01-23 00:12:40.556494: step: 748/529, loss: 0.24343052506446838
2023-01-23 00:12:41.789121: step: 752/529, loss: 0.07532835006713867
2023-01-23 00:12:43.000987: step: 756/529, loss: 0.1570483148097992
2023-01-23 00:12:44.180812: step: 760/529, loss: 0.11138339340686798
2023-01-23 00:12:45.372283: step: 764/529, loss: 0.1902478188276291
2023-01-23 00:12:46.571933: step: 768/529, loss: 0.5234995484352112
2023-01-23 00:12:47.788585: step: 772/529, loss: 0.07961826026439667
2023-01-23 00:12:49.004667: step: 776/529, loss: 0.1992332488298416
2023-01-23 00:12:50.189856: step: 780/529, loss: 0.30524635314941406
2023-01-23 00:12:51.395502: step: 784/529, loss: 0.2621254026889801
2023-01-23 00:12:52.597717: step: 788/529, loss: 6.731590270996094
2023-01-23 00:12:53.821431: step: 792/529, loss: 1.0632907152175903
2023-01-23 00:12:55.042455: step: 796/529, loss: 0.2712801992893219
2023-01-23 00:12:56.247173: step: 800/529, loss: 0.33300885558128357
2023-01-23 00:12:57.445597: step: 804/529, loss: 0.07124600559473038
2023-01-23 00:12:58.652903: step: 808/529, loss: 0.289437860250473
2023-01-23 00:12:59.900211: step: 812/529, loss: 0.10650768131017685
2023-01-23 00:13:01.101593: step: 816/529, loss: 0.2907988429069519
2023-01-23 00:13:02.293685: step: 820/529, loss: 0.15293750166893005
2023-01-23 00:13:03.477909: step: 824/529, loss: 0.04618760570883751
2023-01-23 00:13:04.667499: step: 828/529, loss: 0.7582330703735352
2023-01-23 00:13:05.875011: step: 832/529, loss: 0.1023097038269043
2023-01-23 00:13:07.071019: step: 836/529, loss: 0.19602380692958832
2023-01-23 00:13:08.290416: step: 840/529, loss: 0.39763709902763367
2023-01-23 00:13:09.501567: step: 844/529, loss: 0.16959291696548462
2023-01-23 00:13:10.690399: step: 848/529, loss: 0.11945943534374237
2023-01-23 00:13:11.867578: step: 852/529, loss: 0.7064674496650696
2023-01-23 00:13:13.049437: step: 856/529, loss: 0.07346732914447784
2023-01-23 00:13:14.227642: step: 860/529, loss: 0.7056807279586792
2023-01-23 00:13:15.431210: step: 864/529, loss: 0.11672163754701614
2023-01-23 00:13:16.642190: step: 868/529, loss: 0.8193079233169556
2023-01-23 00:13:17.875431: step: 872/529, loss: 0.17722482979297638
2023-01-23 00:13:19.060565: step: 876/529, loss: 0.5032776594161987
2023-01-23 00:13:20.301218: step: 880/529, loss: 0.22781753540039062
2023-01-23 00:13:21.544075: step: 884/529, loss: 0.33599910140037537
2023-01-23 00:13:22.713588: step: 888/529, loss: 0.24913644790649414
2023-01-23 00:13:23.898646: step: 892/529, loss: 1.0517165660858154
2023-01-23 00:13:25.103712: step: 896/529, loss: 0.023081159219145775
2023-01-23 00:13:26.252320: step: 900/529, loss: 0.079694464802742
2023-01-23 00:13:27.463942: step: 904/529, loss: 0.13987857103347778
2023-01-23 00:13:28.648478: step: 908/529, loss: 0.04917202144861221
2023-01-23 00:13:29.874298: step: 912/529, loss: 0.38371506333351135
2023-01-23 00:13:31.072109: step: 916/529, loss: 0.14735527336597443
2023-01-23 00:13:32.296311: step: 920/529, loss: 0.19159266352653503
2023-01-23 00:13:33.511299: step: 924/529, loss: 0.02148113213479519
2023-01-23 00:13:34.720634: step: 928/529, loss: 0.6060795783996582
2023-01-23 00:13:35.938912: step: 932/529, loss: 0.03179464489221573
2023-01-23 00:13:37.155574: step: 936/529, loss: 0.5949546694755554
2023-01-23 00:13:38.329914: step: 940/529, loss: 0.0662682056427002
2023-01-23 00:13:39.543692: step: 944/529, loss: 0.15894919633865356
2023-01-23 00:13:40.734768: step: 948/529, loss: 0.6855624914169312
2023-01-23 00:13:41.954014: step: 952/529, loss: 0.9729734063148499
2023-01-23 00:13:43.158925: step: 956/529, loss: 0.5432029962539673
2023-01-23 00:13:44.312466: step: 960/529, loss: 0.033452510833740234
2023-01-23 00:13:45.536338: step: 964/529, loss: 0.5826089382171631
2023-01-23 00:13:46.739631: step: 968/529, loss: 0.16668090224266052
2023-01-23 00:13:47.933715: step: 972/529, loss: 0.4389062821865082
2023-01-23 00:13:49.108721: step: 976/529, loss: 0.627124547958374
2023-01-23 00:13:50.263966: step: 980/529, loss: 0.1279161423444748
2023-01-23 00:13:51.438752: step: 984/529, loss: 0.5198164582252502
2023-01-23 00:13:52.672103: step: 988/529, loss: 0.8815890550613403
2023-01-23 00:13:53.850336: step: 992/529, loss: 0.5943320393562317
2023-01-23 00:13:55.089521: step: 996/529, loss: 0.1565295308828354
2023-01-23 00:13:56.257936: step: 1000/529, loss: 0.054601289331912994
2023-01-23 00:13:57.499155: step: 1004/529, loss: 0.33045950531959534
2023-01-23 00:13:58.709161: step: 1008/529, loss: 4.906688213348389
2023-01-23 00:13:59.915738: step: 1012/529, loss: 0.16284996271133423
2023-01-23 00:14:01.137232: step: 1016/529, loss: 0.08170967549085617
2023-01-23 00:14:02.328891: step: 1020/529, loss: 0.07424584031105042
2023-01-23 00:14:03.483119: step: 1024/529, loss: 0.34577685594558716
2023-01-23 00:14:04.648249: step: 1028/529, loss: 0.23452281951904297
2023-01-23 00:14:05.786790: step: 1032/529, loss: 0.3462425172328949
2023-01-23 00:14:06.982400: step: 1036/529, loss: 0.6544706225395203
2023-01-23 00:14:08.156467: step: 1040/529, loss: 0.09467440098524094
2023-01-23 00:14:09.379716: step: 1044/529, loss: 0.2865774929523468
2023-01-23 00:14:10.584571: step: 1048/529, loss: 0.6097820997238159
2023-01-23 00:14:11.794776: step: 1052/529, loss: 0.22973862290382385
2023-01-23 00:14:12.933433: step: 1056/529, loss: 6.003236770629883
2023-01-23 00:14:14.145061: step: 1060/529, loss: 0.16612310707569122
2023-01-23 00:14:15.362325: step: 1064/529, loss: 0.3027915060520172
2023-01-23 00:14:16.548484: step: 1068/529, loss: 0.10988998413085938
2023-01-23 00:14:17.755003: step: 1072/529, loss: 0.2076096534729004
2023-01-23 00:14:18.991770: step: 1076/529, loss: 0.6231120228767395
2023-01-23 00:14:20.197517: step: 1080/529, loss: 0.11262819916009903
2023-01-23 00:14:21.384172: step: 1084/529, loss: 0.10338087379932404
2023-01-23 00:14:22.623339: step: 1088/529, loss: 0.28512048721313477
2023-01-23 00:14:23.840708: step: 1092/529, loss: 0.3338623046875
2023-01-23 00:14:25.032029: step: 1096/529, loss: 0.154316246509552
2023-01-23 00:14:26.220846: step: 1100/529, loss: 0.16560226678848267
2023-01-23 00:14:27.390083: step: 1104/529, loss: 0.21936655044555664
2023-01-23 00:14:28.581574: step: 1108/529, loss: 0.1365387886762619
2023-01-23 00:14:29.762601: step: 1112/529, loss: 0.273162841796875
2023-01-23 00:14:30.950079: step: 1116/529, loss: 0.19150061905384064
2023-01-23 00:14:32.146516: step: 1120/529, loss: 0.14278630912303925
2023-01-23 00:14:33.353255: step: 1124/529, loss: 0.10513119399547577
2023-01-23 00:14:34.566309: step: 1128/529, loss: 0.24738502502441406
2023-01-23 00:14:35.800634: step: 1132/529, loss: 0.14306268095970154
2023-01-23 00:14:36.975520: step: 1136/529, loss: 0.04414534568786621
2023-01-23 00:14:38.220065: step: 1140/529, loss: 0.17272883653640747
2023-01-23 00:14:39.381115: step: 1144/529, loss: 0.05614333599805832
2023-01-23 00:14:40.590604: step: 1148/529, loss: 0.9135578274726868
2023-01-23 00:14:41.765923: step: 1152/529, loss: 0.14959993958473206
2023-01-23 00:14:42.979776: step: 1156/529, loss: 0.17412757873535156
2023-01-23 00:14:44.151130: step: 1160/529, loss: 0.12987175583839417
2023-01-23 00:14:45.331693: step: 1164/529, loss: 0.06797285377979279
2023-01-23 00:14:46.574458: step: 1168/529, loss: 0.1130923479795456
2023-01-23 00:14:47.792672: step: 1172/529, loss: 0.4426470398902893
2023-01-23 00:14:48.996678: step: 1176/529, loss: 0.19118309020996094
2023-01-23 00:14:50.182807: step: 1180/529, loss: 0.1117292195558548
2023-01-23 00:14:51.452215: step: 1184/529, loss: 0.6640169620513916
2023-01-23 00:14:52.657574: step: 1188/529, loss: 4.48140811920166
2023-01-23 00:14:53.817214: step: 1192/529, loss: 0.08659081161022186
2023-01-23 00:14:54.971478: step: 1196/529, loss: 0.03147587925195694
2023-01-23 00:14:56.173060: step: 1200/529, loss: 0.11511115729808807
2023-01-23 00:14:57.369338: step: 1204/529, loss: 0.1763749122619629
2023-01-23 00:14:58.520897: step: 1208/529, loss: 0.16321153938770294
2023-01-23 00:14:59.712557: step: 1212/529, loss: 0.4295472204685211
2023-01-23 00:15:00.868245: step: 1216/529, loss: 0.6507922410964966
2023-01-23 00:15:02.050908: step: 1220/529, loss: 0.26718711853027344
2023-01-23 00:15:03.237724: step: 1224/529, loss: 0.044921256601810455
2023-01-23 00:15:04.411096: step: 1228/529, loss: 0.08841486275196075
2023-01-23 00:15:05.592267: step: 1232/529, loss: 0.10089216381311417
2023-01-23 00:15:06.828193: step: 1236/529, loss: 0.7087823748588562
2023-01-23 00:15:08.033470: step: 1240/529, loss: 0.1036825180053711
2023-01-23 00:15:09.251483: step: 1244/529, loss: 0.20612198114395142
2023-01-23 00:15:10.482335: step: 1248/529, loss: 0.17646685242652893
2023-01-23 00:15:11.692443: step: 1252/529, loss: 0.1127084270119667
2023-01-23 00:15:12.885325: step: 1256/529, loss: 0.46867480874061584
2023-01-23 00:15:14.090646: step: 1260/529, loss: 0.457366406917572
2023-01-23 00:15:15.267666: step: 1264/529, loss: 1.3867372274398804
2023-01-23 00:15:16.476851: step: 1268/529, loss: 0.07479186356067657
2023-01-23 00:15:17.630249: step: 1272/529, loss: 0.2538675367832184
2023-01-23 00:15:18.814491: step: 1276/529, loss: 0.1473599076271057
2023-01-23 00:15:20.013978: step: 1280/529, loss: 0.10108103603124619
2023-01-23 00:15:21.172798: step: 1284/529, loss: 0.372117817401886
2023-01-23 00:15:22.330264: step: 1288/529, loss: 0.12571612000465393
2023-01-23 00:15:23.511247: step: 1292/529, loss: 0.07035856693983078
2023-01-23 00:15:24.691789: step: 1296/529, loss: 0.030086757615208626
2023-01-23 00:15:25.955067: step: 1300/529, loss: 0.21377216279506683
2023-01-23 00:15:27.151277: step: 1304/529, loss: 0.09911099076271057
2023-01-23 00:15:28.438461: step: 1308/529, loss: 0.617196798324585
2023-01-23 00:15:29.611104: step: 1312/529, loss: 0.8181546926498413
2023-01-23 00:15:30.807298: step: 1316/529, loss: 0.2112378031015396
2023-01-23 00:15:32.028461: step: 1320/529, loss: 0.10260926187038422
2023-01-23 00:15:33.215258: step: 1324/529, loss: 0.05346975475549698
2023-01-23 00:15:34.381852: step: 1328/529, loss: 0.3387274742126465
2023-01-23 00:15:35.539340: step: 1332/529, loss: 0.0790284126996994
2023-01-23 00:15:36.727848: step: 1336/529, loss: 0.1004907637834549
2023-01-23 00:15:37.924541: step: 1340/529, loss: 0.18727150559425354
2023-01-23 00:15:39.145203: step: 1344/529, loss: 6.199986934661865
2023-01-23 00:15:40.354109: step: 1348/529, loss: 0.23256847262382507
2023-01-23 00:15:41.555277: step: 1352/529, loss: 0.12678948044776917
2023-01-23 00:15:42.768642: step: 1356/529, loss: 0.16418799757957458
2023-01-23 00:15:43.952511: step: 1360/529, loss: 0.0450749397277832
2023-01-23 00:15:45.199422: step: 1364/529, loss: 0.4133574366569519
2023-01-23 00:15:46.366335: step: 1368/529, loss: 0.16582107543945312
2023-01-23 00:15:47.586003: step: 1372/529, loss: 0.17802810668945312
2023-01-23 00:15:48.761669: step: 1376/529, loss: 0.22307071089744568
2023-01-23 00:15:49.954624: step: 1380/529, loss: 2.0557503700256348
2023-01-23 00:15:51.178487: step: 1384/529, loss: 0.08926315605640411
2023-01-23 00:15:52.353995: step: 1388/529, loss: 0.38156142830848694
2023-01-23 00:15:53.583204: step: 1392/529, loss: 0.6394654512405396
2023-01-23 00:15:54.788804: step: 1396/529, loss: 0.08124236762523651
2023-01-23 00:15:55.976854: step: 1400/529, loss: 0.1441776305437088
2023-01-23 00:15:57.132567: step: 1404/529, loss: 0.20134636759757996
2023-01-23 00:15:58.271822: step: 1408/529, loss: 0.17993207275867462
2023-01-23 00:15:59.453520: step: 1412/529, loss: 0.09152422100305557
2023-01-23 00:16:00.636478: step: 1416/529, loss: 0.40726202726364136
2023-01-23 00:16:01.821654: step: 1420/529, loss: 0.3616032302379608
2023-01-23 00:16:03.013720: step: 1424/529, loss: 0.23492255806922913
2023-01-23 00:16:04.233828: step: 1428/529, loss: 0.05406615510582924
2023-01-23 00:16:05.411813: step: 1432/529, loss: 0.5799874663352966
2023-01-23 00:16:06.579363: step: 1436/529, loss: 0.04527115821838379
2023-01-23 00:16:07.790770: step: 1440/529, loss: 0.5468133091926575
2023-01-23 00:16:08.983401: step: 1444/529, loss: 0.11244764924049377
2023-01-23 00:16:10.185199: step: 1448/529, loss: 0.266893208026886
2023-01-23 00:16:11.372338: step: 1452/529, loss: 0.15133695304393768
2023-01-23 00:16:12.536422: step: 1456/529, loss: 0.189447820186615
2023-01-23 00:16:13.718000: step: 1460/529, loss: 0.05978555977344513
2023-01-23 00:16:14.886771: step: 1464/529, loss: 0.529640257358551
2023-01-23 00:16:16.049341: step: 1468/529, loss: 0.6634248495101929
2023-01-23 00:16:17.272914: step: 1472/529, loss: 0.07440290600061417
2023-01-23 00:16:18.509540: step: 1476/529, loss: 0.11741209030151367
2023-01-23 00:16:19.724244: step: 1480/529, loss: 0.8374691009521484
2023-01-23 00:16:20.918792: step: 1484/529, loss: 0.17753085494041443
2023-01-23 00:16:22.109432: step: 1488/529, loss: 0.3507664203643799
2023-01-23 00:16:23.279567: step: 1492/529, loss: 1.8072805404663086
2023-01-23 00:16:24.455324: step: 1496/529, loss: 1.472825527191162
2023-01-23 00:16:25.650358: step: 1500/529, loss: 0.6865641474723816
2023-01-23 00:16:26.880987: step: 1504/529, loss: 1.0736228227615356
2023-01-23 00:16:28.071607: step: 1508/529, loss: 0.0917641669511795
2023-01-23 00:16:29.244428: step: 1512/529, loss: 0.3716105818748474
2023-01-23 00:16:30.434682: step: 1516/529, loss: 0.3487027585506439
2023-01-23 00:16:31.640656: step: 1520/529, loss: 0.8320213556289673
2023-01-23 00:16:32.817519: step: 1524/529, loss: 0.4757848381996155
2023-01-23 00:16:34.048993: step: 1528/529, loss: 0.18038229644298553
2023-01-23 00:16:35.242594: step: 1532/529, loss: 0.2668381631374359
2023-01-23 00:16:36.436148: step: 1536/529, loss: 0.07612647861242294
2023-01-23 00:16:37.625870: step: 1540/529, loss: 0.21797865629196167
2023-01-23 00:16:38.774108: step: 1544/529, loss: 0.058518316596746445
2023-01-23 00:16:39.963312: step: 1548/529, loss: 0.18121612071990967
2023-01-23 00:16:41.132611: step: 1552/529, loss: 0.1679491102695465
2023-01-23 00:16:42.386795: step: 1556/529, loss: 0.32042181491851807
2023-01-23 00:16:43.582245: step: 1560/529, loss: 0.22156062722206116
2023-01-23 00:16:44.755254: step: 1564/529, loss: 0.3879724144935608
2023-01-23 00:16:45.941869: step: 1568/529, loss: 0.14725805819034576
2023-01-23 00:16:47.136386: step: 1572/529, loss: 0.16188357770442963
2023-01-23 00:16:48.310394: step: 1576/529, loss: 0.12782125174999237
2023-01-23 00:16:49.519120: step: 1580/529, loss: 1.4023945331573486
2023-01-23 00:16:50.718639: step: 1584/529, loss: 0.16383209824562073
2023-01-23 00:16:51.932562: step: 1588/529, loss: 0.4181675910949707
2023-01-23 00:16:53.110282: step: 1592/529, loss: 0.217121422290802
2023-01-23 00:16:54.294309: step: 1596/529, loss: 0.43179693818092346
2023-01-23 00:16:55.503276: step: 1600/529, loss: 0.28129568696022034
2023-01-23 00:16:56.726370: step: 1604/529, loss: 0.1418551355600357
2023-01-23 00:16:57.953988: step: 1608/529, loss: 1.4765256643295288
2023-01-23 00:16:59.172960: step: 1612/529, loss: 0.10199747234582901
2023-01-23 00:17:00.344118: step: 1616/529, loss: 0.4221336543560028
2023-01-23 00:17:01.547893: step: 1620/529, loss: 0.2339315414428711
2023-01-23 00:17:02.769599: step: 1624/529, loss: 5.125759124755859
2023-01-23 00:17:03.920304: step: 1628/529, loss: 0.6543909907341003
2023-01-23 00:17:05.115009: step: 1632/529, loss: 0.0964723601937294
2023-01-23 00:17:06.313685: step: 1636/529, loss: 0.039095688611269
2023-01-23 00:17:07.489724: step: 1640/529, loss: 0.1001126766204834
2023-01-23 00:17:08.665171: step: 1644/529, loss: 0.3113107681274414
2023-01-23 00:17:09.843108: step: 1648/529, loss: 0.24315276741981506
2023-01-23 00:17:11.078055: step: 1652/529, loss: 0.16151729226112366
2023-01-23 00:17:12.262532: step: 1656/529, loss: 1.046234369277954
2023-01-23 00:17:13.479290: step: 1660/529, loss: 0.28707069158554077
2023-01-23 00:17:14.719853: step: 1664/529, loss: 0.4638436436653137
2023-01-23 00:17:15.920440: step: 1668/529, loss: 0.25943848490715027
2023-01-23 00:17:17.125612: step: 1672/529, loss: 0.12710922956466675
2023-01-23 00:17:18.353354: step: 1676/529, loss: 0.08610612154006958
2023-01-23 00:17:19.513510: step: 1680/529, loss: 0.6280315518379211
2023-01-23 00:17:20.696116: step: 1684/529, loss: 0.6920431852340698
2023-01-23 00:17:21.901095: step: 1688/529, loss: 0.18153858184814453
2023-01-23 00:17:23.081244: step: 1692/529, loss: 0.24365907907485962
2023-01-23 00:17:24.290493: step: 1696/529, loss: 0.2582958936691284
2023-01-23 00:17:25.538017: step: 1700/529, loss: 0.7487557530403137
2023-01-23 00:17:26.777494: step: 1704/529, loss: 0.618736982345581
2023-01-23 00:17:27.938316: step: 1708/529, loss: 0.09239549934864044
2023-01-23 00:17:29.105966: step: 1712/529, loss: 0.30387306213378906
2023-01-23 00:17:30.294053: step: 1716/529, loss: 0.9698070287704468
2023-01-23 00:17:31.508892: step: 1720/529, loss: 0.1637330949306488
2023-01-23 00:17:32.712543: step: 1724/529, loss: 0.9275952577590942
2023-01-23 00:17:33.888947: step: 1728/529, loss: 0.3570396304130554
2023-01-23 00:17:35.115099: step: 1732/529, loss: 0.23173418641090393
2023-01-23 00:17:36.327297: step: 1736/529, loss: 0.08866572380065918
2023-01-23 00:17:37.516379: step: 1740/529, loss: 1.144148826599121
2023-01-23 00:17:38.711332: step: 1744/529, loss: 0.16854286193847656
2023-01-23 00:17:39.914678: step: 1748/529, loss: 0.290663480758667
2023-01-23 00:17:41.142313: step: 1752/529, loss: 0.21626943349838257
2023-01-23 00:17:42.355487: step: 1756/529, loss: 0.1097053587436676
2023-01-23 00:17:43.559657: step: 1760/529, loss: 0.18987546861171722
2023-01-23 00:17:44.773607: step: 1764/529, loss: 0.12195196747779846
2023-01-23 00:17:45.967524: step: 1768/529, loss: 0.17239037156105042
2023-01-23 00:17:47.172709: step: 1772/529, loss: 0.04777822643518448
2023-01-23 00:17:48.406089: step: 1776/529, loss: 0.231571763753891
2023-01-23 00:17:49.590592: step: 1780/529, loss: 0.18764953315258026
2023-01-23 00:17:50.786819: step: 1784/529, loss: 0.13542090356349945
2023-01-23 00:17:51.993243: step: 1788/529, loss: 0.13952189683914185
2023-01-23 00:17:53.161025: step: 1792/529, loss: 1.1039947271347046
2023-01-23 00:17:54.326144: step: 1796/529, loss: 0.31469279527664185
2023-01-23 00:17:55.557418: step: 1800/529, loss: 0.141163632273674
2023-01-23 00:17:56.765745: step: 1804/529, loss: 0.13917790353298187
2023-01-23 00:17:57.982021: step: 1808/529, loss: 0.05063953623175621
2023-01-23 00:17:59.272447: step: 1812/529, loss: 0.1642959713935852
2023-01-23 00:18:00.500351: step: 1816/529, loss: 0.018425656482577324
2023-01-23 00:18:01.716675: step: 1820/529, loss: 0.3701033592224121
2023-01-23 00:18:02.958230: step: 1824/529, loss: 0.0518035888671875
2023-01-23 00:18:04.141277: step: 1828/529, loss: 0.02172534540295601
2023-01-23 00:18:05.324093: step: 1832/529, loss: 0.1204461082816124
2023-01-23 00:18:06.516147: step: 1836/529, loss: 1.6124284267425537
2023-01-23 00:18:07.708448: step: 1840/529, loss: 0.6887340545654297
2023-01-23 00:18:08.872247: step: 1844/529, loss: 0.2187584936618805
2023-01-23 00:18:10.036665: step: 1848/529, loss: 0.3393929600715637
2023-01-23 00:18:11.216331: step: 1852/529, loss: 0.13632269203662872
2023-01-23 00:18:12.420103: step: 1856/529, loss: 0.39690670371055603
2023-01-23 00:18:13.628690: step: 1860/529, loss: 0.17722836136817932
2023-01-23 00:18:14.788066: step: 1864/529, loss: 0.1351182907819748
2023-01-23 00:18:16.033524: step: 1868/529, loss: 1.1313598155975342
2023-01-23 00:18:17.228743: step: 1872/529, loss: 0.15648508071899414
2023-01-23 00:18:18.391358: step: 1876/529, loss: 0.1422465443611145
2023-01-23 00:18:19.539834: step: 1880/529, loss: 0.09015731513500214
2023-01-23 00:18:20.743494: step: 1884/529, loss: 0.1626604050397873
2023-01-23 00:18:21.955414: step: 1888/529, loss: 0.10304880142211914
2023-01-23 00:18:23.127197: step: 1892/529, loss: 0.17091742157936096
2023-01-23 00:18:24.329183: step: 1896/529, loss: 0.1544683575630188
2023-01-23 00:18:25.529160: step: 1900/529, loss: 0.13257665932178497
2023-01-23 00:18:26.760143: step: 1904/529, loss: 0.4589420258998871
2023-01-23 00:18:27.973983: step: 1908/529, loss: 0.060416512191295624
2023-01-23 00:18:29.134304: step: 1912/529, loss: 0.1425163298845291
2023-01-23 00:18:30.294763: step: 1916/529, loss: 0.41728153824806213
2023-01-23 00:18:31.514542: step: 1920/529, loss: 0.1548786610364914
2023-01-23 00:18:32.724655: step: 1924/529, loss: 0.13955669105052948
2023-01-23 00:18:33.930148: step: 1928/529, loss: 0.23480787873268127
2023-01-23 00:18:35.099270: step: 1932/529, loss: 0.12438789010047913
2023-01-23 00:18:36.282527: step: 1936/529, loss: 0.3161556124687195
2023-01-23 00:18:37.487366: step: 1940/529, loss: 0.1263858824968338
2023-01-23 00:18:38.705706: step: 1944/529, loss: 0.22066307067871094
2023-01-23 00:18:39.886076: step: 1948/529, loss: 0.12270255386829376
2023-01-23 00:18:41.128337: step: 1952/529, loss: 0.593161940574646
2023-01-23 00:18:42.361209: step: 1956/529, loss: 0.08518419414758682
2023-01-23 00:18:43.574325: step: 1960/529, loss: 0.5108179450035095
2023-01-23 00:18:44.783662: step: 1964/529, loss: 0.6039228439331055
2023-01-23 00:18:45.982397: step: 1968/529, loss: 0.2617681622505188
2023-01-23 00:18:47.206586: step: 1972/529, loss: 0.17124386131763458
2023-01-23 00:18:48.383002: step: 1976/529, loss: 0.07970023155212402
2023-01-23 00:18:49.598441: step: 1980/529, loss: 0.47440657019615173
2023-01-23 00:18:50.794914: step: 1984/529, loss: 0.21349477767944336
2023-01-23 00:18:51.997839: step: 1988/529, loss: 0.10600729286670685
2023-01-23 00:18:53.175662: step: 1992/529, loss: 0.14141102135181427
2023-01-23 00:18:54.387023: step: 1996/529, loss: 0.33906498551368713
2023-01-23 00:18:55.643269: step: 2000/529, loss: 1.9259979724884033
2023-01-23 00:18:56.854635: step: 2004/529, loss: 0.7772596478462219
2023-01-23 00:18:58.032878: step: 2008/529, loss: 0.26714658737182617
2023-01-23 00:18:59.286080: step: 2012/529, loss: 0.26636749505996704
2023-01-23 00:19:00.458617: step: 2016/529, loss: 0.1128692626953125
2023-01-23 00:19:01.659521: step: 2020/529, loss: 0.08774447441101074
2023-01-23 00:19:02.838389: step: 2024/529, loss: 0.34954845905303955
2023-01-23 00:19:04.048814: step: 2028/529, loss: 0.36431077122688293
2023-01-23 00:19:05.250826: step: 2032/529, loss: 0.11794634163379669
2023-01-23 00:19:06.430291: step: 2036/529, loss: 0.1983383744955063
2023-01-23 00:19:07.610841: step: 2040/529, loss: 0.05095238983631134
2023-01-23 00:19:08.800605: step: 2044/529, loss: 0.22152921557426453
2023-01-23 00:19:10.055013: step: 2048/529, loss: 0.14781494438648224
2023-01-23 00:19:11.254179: step: 2052/529, loss: 0.6407216787338257
2023-01-23 00:19:12.436982: step: 2056/529, loss: 0.14101961255073547
2023-01-23 00:19:13.647478: step: 2060/529, loss: 0.42766687273979187
2023-01-23 00:19:14.858283: step: 2064/529, loss: 0.08741907775402069
2023-01-23 00:19:16.043032: step: 2068/529, loss: 0.6224902868270874
2023-01-23 00:19:17.226003: step: 2072/529, loss: 0.4738982319831848
2023-01-23 00:19:18.463428: step: 2076/529, loss: 0.27600136399269104
2023-01-23 00:19:19.686963: step: 2080/529, loss: 0.6062637567520142
2023-01-23 00:19:20.896234: step: 2084/529, loss: 0.09425287693738937
2023-01-23 00:19:22.117945: step: 2088/529, loss: 0.1627206802368164
2023-01-23 00:19:23.318600: step: 2092/529, loss: 0.13426536321640015
2023-01-23 00:19:24.530798: step: 2096/529, loss: 0.08971855789422989
2023-01-23 00:19:25.764966: step: 2100/529, loss: 0.18097352981567383
2023-01-23 00:19:26.940201: step: 2104/529, loss: 0.2610015869140625
2023-01-23 00:19:28.158418: step: 2108/529, loss: 0.7071977853775024
2023-01-23 00:19:29.367734: step: 2112/529, loss: 0.1372658759355545
2023-01-23 00:19:30.544641: step: 2116/529, loss: 0.03658909723162651
==================================================
Loss: 0.422
--------------------
Dev: {'event': {'p': 0.5972944849115505, 'r': 0.7643142476697736, 'f1': 0.6705607476635514}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6162162162162163, 'r': 0.7513481126423007, 'f1': 0.6771058315334773}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.64, 'r': 0.8888888888888888, 'f1': 0.7441860465116279}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
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': 4}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5972944849115505, 'r': 0.7643142476697736, 'f1': 0.6705607476635514}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6162162162162163, 'r': 0.7513481126423007, 'f1': 0.6771058315334773}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.6296296296296297, 'r': 0.4722222222222222, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:20:19.607594: step: 4/529, loss: 0.3368922173976898
2023-01-23 00:20:20.857894: step: 8/529, loss: 0.2498549371957779
2023-01-23 00:20:21.976901: step: 12/529, loss: 0.13210654258728027
2023-01-23 00:20:23.198614: step: 16/529, loss: 0.04694252088665962
2023-01-23 00:20:24.397522: step: 20/529, loss: 0.1581013947725296
2023-01-23 00:20:25.602643: step: 24/529, loss: 0.08795900642871857
2023-01-23 00:20:26.790840: step: 28/529, loss: 0.06205299496650696
2023-01-23 00:20:27.976188: step: 32/529, loss: 0.07818803936243057
2023-01-23 00:20:29.138559: step: 36/529, loss: 0.03181157261133194
2023-01-23 00:20:30.308822: step: 40/529, loss: 0.0711650401353836
2023-01-23 00:20:31.491038: step: 44/529, loss: 0.06321640312671661
2023-01-23 00:20:32.698230: step: 48/529, loss: 0.16439934074878693
2023-01-23 00:20:33.900363: step: 52/529, loss: 0.012914848513901234
2023-01-23 00:20:35.074242: step: 56/529, loss: 0.1339038610458374
2023-01-23 00:20:36.282972: step: 60/529, loss: 0.013389921747148037
2023-01-23 00:20:37.482325: step: 64/529, loss: 0.16260270774364471
2023-01-23 00:20:38.647902: step: 68/529, loss: 0.2935546040534973
2023-01-23 00:20:39.859235: step: 72/529, loss: 0.09496411681175232
2023-01-23 00:20:41.054268: step: 76/529, loss: 0.877576470375061
2023-01-23 00:20:42.231412: step: 80/529, loss: 0.19418397545814514
2023-01-23 00:20:43.394435: step: 84/529, loss: 0.0757625624537468
2023-01-23 00:20:44.532208: step: 88/529, loss: 0.23217211663722992
2023-01-23 00:20:45.698882: step: 92/529, loss: 0.245915025472641
2023-01-23 00:20:46.900138: step: 96/529, loss: 0.4205031394958496
2023-01-23 00:20:48.101412: step: 100/529, loss: 0.0636201873421669
2023-01-23 00:20:49.287851: step: 104/529, loss: 0.20632687211036682
2023-01-23 00:20:50.489022: step: 108/529, loss: 0.06781215965747833
2023-01-23 00:20:51.702366: step: 112/529, loss: 0.23506608605384827
2023-01-23 00:20:52.913990: step: 116/529, loss: 0.03888101875782013
2023-01-23 00:20:54.077228: step: 120/529, loss: 0.27391594648361206
2023-01-23 00:20:55.270974: step: 124/529, loss: 0.13371562957763672
2023-01-23 00:20:56.463740: step: 128/529, loss: 0.7427403926849365
2023-01-23 00:20:57.657423: step: 132/529, loss: 0.19109773635864258
2023-01-23 00:20:58.847469: step: 136/529, loss: 0.11806771904230118
2023-01-23 00:21:00.050060: step: 140/529, loss: 0.0564023032784462
2023-01-23 00:21:01.264245: step: 144/529, loss: 0.17895051836967468
2023-01-23 00:21:02.493982: step: 148/529, loss: 0.09865856170654297
2023-01-23 00:21:03.692121: step: 152/529, loss: 0.02326202392578125
2023-01-23 00:21:04.893430: step: 156/529, loss: 0.14999417960643768
2023-01-23 00:21:06.074155: step: 160/529, loss: 0.104170061647892
2023-01-23 00:21:07.264799: step: 164/529, loss: 0.03118734434247017
2023-01-23 00:21:08.415558: step: 168/529, loss: 0.14105692505836487
2023-01-23 00:21:09.616900: step: 172/529, loss: 1.0737955570220947
2023-01-23 00:21:10.829358: step: 176/529, loss: 0.14666888117790222
2023-01-23 00:21:11.987948: step: 180/529, loss: 0.16274519264698029
2023-01-23 00:21:13.168406: step: 184/529, loss: 0.07790937274694443
2023-01-23 00:21:14.421146: step: 188/529, loss: 0.9040259718894958
2023-01-23 00:21:15.581038: step: 192/529, loss: 0.10623179376125336
2023-01-23 00:21:16.768243: step: 196/529, loss: 0.154289111495018
2023-01-23 00:21:17.969096: step: 200/529, loss: 0.2605861723423004
2023-01-23 00:21:19.172229: step: 204/529, loss: 0.2002088725566864
2023-01-23 00:21:20.361759: step: 208/529, loss: 0.3796895444393158
2023-01-23 00:21:21.561039: step: 212/529, loss: 0.406202495098114
2023-01-23 00:21:22.732577: step: 216/529, loss: 0.44357118010520935
2023-01-23 00:21:23.939660: step: 220/529, loss: 0.10600404441356659
2023-01-23 00:21:25.114173: step: 224/529, loss: 0.006806469056755304
2023-01-23 00:21:26.352836: step: 228/529, loss: 0.054962921887636185
2023-01-23 00:21:27.592669: step: 232/529, loss: 0.4608858823776245
2023-01-23 00:21:28.764596: step: 236/529, loss: 0.03203745186328888
2023-01-23 00:21:29.942391: step: 240/529, loss: 0.33352941274642944
2023-01-23 00:21:31.146992: step: 244/529, loss: 0.11124230176210403
2023-01-23 00:21:32.304167: step: 248/529, loss: 1.1060606241226196
2023-01-23 00:21:33.486906: step: 252/529, loss: 2.1010019779205322
2023-01-23 00:21:34.701655: step: 256/529, loss: 0.10182676464319229
2023-01-23 00:21:35.903991: step: 260/529, loss: 0.19599036872386932
2023-01-23 00:21:37.109259: step: 264/529, loss: 0.23356997966766357
2023-01-23 00:21:38.305689: step: 268/529, loss: 0.15966132283210754
2023-01-23 00:21:39.467516: step: 272/529, loss: 0.40934592485427856
2023-01-23 00:21:40.680479: step: 276/529, loss: 0.40123826265335083
2023-01-23 00:21:41.864584: step: 280/529, loss: 0.15164980292320251
2023-01-23 00:21:43.106209: step: 284/529, loss: 0.10599565505981445
2023-01-23 00:21:44.287889: step: 288/529, loss: 0.3209083676338196
2023-01-23 00:21:45.443545: step: 292/529, loss: 0.10308961570262909
2023-01-23 00:21:46.655245: step: 296/529, loss: 0.3025496006011963
2023-01-23 00:21:47.838048: step: 300/529, loss: 0.42719945311546326
2023-01-23 00:21:49.044194: step: 304/529, loss: 0.17302380502223969
2023-01-23 00:21:50.216563: step: 308/529, loss: 0.32263821363449097
2023-01-23 00:21:51.452623: step: 312/529, loss: 0.293412983417511
2023-01-23 00:21:52.634756: step: 316/529, loss: 0.14710655808448792
2023-01-23 00:21:53.829117: step: 320/529, loss: 0.07069597393274307
2023-01-23 00:21:55.007046: step: 324/529, loss: 0.07201728969812393
2023-01-23 00:21:56.245608: step: 328/529, loss: 0.0860690101981163
2023-01-23 00:21:57.428415: step: 332/529, loss: 0.26549968123435974
2023-01-23 00:21:58.605684: step: 336/529, loss: 0.23117035627365112
2023-01-23 00:21:59.816259: step: 340/529, loss: 0.5455995202064514
2023-01-23 00:22:01.010386: step: 344/529, loss: 0.07775802910327911
2023-01-23 00:22:02.218085: step: 348/529, loss: 0.992932915687561
2023-01-23 00:22:03.445586: step: 352/529, loss: 0.25192126631736755
2023-01-23 00:22:04.647897: step: 356/529, loss: 0.19559749960899353
2023-01-23 00:22:05.859532: step: 360/529, loss: 0.10951748490333557
2023-01-23 00:22:07.032893: step: 364/529, loss: 0.3038797080516815
2023-01-23 00:22:08.260660: step: 368/529, loss: 0.08814611285924911
2023-01-23 00:22:09.489389: step: 372/529, loss: 0.6434275507926941
2023-01-23 00:22:10.718091: step: 376/529, loss: 0.0830361396074295
2023-01-23 00:22:11.898600: step: 380/529, loss: 0.09309542179107666
2023-01-23 00:22:13.076431: step: 384/529, loss: 0.2797517478466034
2023-01-23 00:22:14.318463: step: 388/529, loss: 0.03623028099536896
2023-01-23 00:22:15.520358: step: 392/529, loss: 0.41027534008026123
2023-01-23 00:22:16.715937: step: 396/529, loss: 0.24451595544815063
2023-01-23 00:22:17.881884: step: 400/529, loss: 0.08677756786346436
2023-01-23 00:22:19.139853: step: 404/529, loss: 0.18799933791160583
2023-01-23 00:22:20.366791: step: 408/529, loss: 1.2076491117477417
2023-01-23 00:22:21.585798: step: 412/529, loss: 0.19329233467578888
2023-01-23 00:22:22.798670: step: 416/529, loss: 0.16854381561279297
2023-01-23 00:22:24.002604: step: 420/529, loss: 0.05669412761926651
2023-01-23 00:22:25.218007: step: 424/529, loss: 0.10756617039442062
2023-01-23 00:22:26.430533: step: 428/529, loss: 0.19117392599582672
2023-01-23 00:22:27.613190: step: 432/529, loss: 1.4733712673187256
2023-01-23 00:22:28.797101: step: 436/529, loss: 0.2350231111049652
2023-01-23 00:22:29.985426: step: 440/529, loss: 1.290475845336914
2023-01-23 00:22:31.149884: step: 444/529, loss: 0.08296690136194229
2023-01-23 00:22:32.376582: step: 448/529, loss: 0.43990230560302734
2023-01-23 00:22:33.569024: step: 452/529, loss: 0.19779834151268005
2023-01-23 00:22:34.794475: step: 456/529, loss: 0.10606088489294052
2023-01-23 00:22:36.034596: step: 460/529, loss: 0.06485767662525177
2023-01-23 00:22:37.231404: step: 464/529, loss: 0.25423184037208557
2023-01-23 00:22:38.440385: step: 468/529, loss: 0.15825147926807404
2023-01-23 00:22:39.630696: step: 472/529, loss: 0.23665395379066467
2023-01-23 00:22:40.828082: step: 476/529, loss: 0.5980239510536194
2023-01-23 00:22:42.025863: step: 480/529, loss: 0.07079296559095383
2023-01-23 00:22:43.241450: step: 484/529, loss: 0.2878645956516266
2023-01-23 00:22:44.406569: step: 488/529, loss: 0.1929466277360916
2023-01-23 00:22:45.580546: step: 492/529, loss: 0.015117883682250977
2023-01-23 00:22:46.764916: step: 496/529, loss: 0.12071068584918976
2023-01-23 00:22:47.924124: step: 500/529, loss: 0.3531966805458069
2023-01-23 00:22:49.172111: step: 504/529, loss: 0.4819986820220947
2023-01-23 00:22:50.356561: step: 508/529, loss: 0.2964286804199219
2023-01-23 00:22:51.535089: step: 512/529, loss: 0.16189280152320862
2023-01-23 00:22:52.710521: step: 516/529, loss: 0.0845704972743988
2023-01-23 00:22:53.940565: step: 520/529, loss: 0.2002183049917221
2023-01-23 00:22:55.113740: step: 524/529, loss: 0.014196586795151234
2023-01-23 00:22:56.299099: step: 528/529, loss: 0.544185996055603
2023-01-23 00:22:57.488078: step: 532/529, loss: 0.0861654281616211
2023-01-23 00:22:58.679144: step: 536/529, loss: 0.07937517017126083
2023-01-23 00:22:59.885090: step: 540/529, loss: 0.1246723160147667
2023-01-23 00:23:01.112425: step: 544/529, loss: 0.09098978340625763
2023-01-23 00:23:02.260990: step: 548/529, loss: 0.051527928560972214
2023-01-23 00:23:03.439100: step: 552/529, loss: 0.18235445022583008
2023-01-23 00:23:04.617588: step: 556/529, loss: 0.09235215187072754
2023-01-23 00:23:05.788148: step: 560/529, loss: 0.09273795783519745
2023-01-23 00:23:07.006060: step: 564/529, loss: 0.4784258306026459
2023-01-23 00:23:08.222936: step: 568/529, loss: 0.40999284386634827
2023-01-23 00:23:09.416172: step: 572/529, loss: 0.11626291275024414
2023-01-23 00:23:10.658255: step: 576/529, loss: 0.4656146168708801
2023-01-23 00:23:11.817805: step: 580/529, loss: 0.06487789750099182
2023-01-23 00:23:13.023474: step: 584/529, loss: 0.23979537189006805
2023-01-23 00:23:14.251447: step: 588/529, loss: 0.11722078919410706
2023-01-23 00:23:15.455500: step: 592/529, loss: 0.12201094627380371
2023-01-23 00:23:16.657187: step: 596/529, loss: 0.0864621102809906
2023-01-23 00:23:17.818522: step: 600/529, loss: 0.426220566034317
2023-01-23 00:23:18.990311: step: 604/529, loss: 0.06975936889648438
2023-01-23 00:23:20.203696: step: 608/529, loss: 0.27815327048301697
2023-01-23 00:23:21.381686: step: 612/529, loss: 0.4007023572921753
2023-01-23 00:23:22.592057: step: 616/529, loss: 0.14910751581192017
2023-01-23 00:23:23.780815: step: 620/529, loss: 0.09513149410486221
2023-01-23 00:23:24.965227: step: 624/529, loss: 0.07580986618995667
2023-01-23 00:23:26.149556: step: 628/529, loss: 0.05873217433691025
2023-01-23 00:23:27.365795: step: 632/529, loss: 0.32759779691696167
2023-01-23 00:23:28.526419: step: 636/529, loss: 0.12283525615930557
2023-01-23 00:23:29.756521: step: 640/529, loss: 0.0848771184682846
2023-01-23 00:23:30.944101: step: 644/529, loss: 0.29472485184669495
2023-01-23 00:23:32.139691: step: 648/529, loss: 0.4429854452610016
2023-01-23 00:23:33.335039: step: 652/529, loss: 0.06603134423494339
2023-01-23 00:23:34.566044: step: 656/529, loss: 0.32188865542411804
2023-01-23 00:23:35.736556: step: 660/529, loss: 1.5369899272918701
2023-01-23 00:23:36.917793: step: 664/529, loss: 0.9638265371322632
2023-01-23 00:23:38.105704: step: 668/529, loss: 0.012149143032729626
2023-01-23 00:23:39.317479: step: 672/529, loss: 0.16493645310401917
2023-01-23 00:23:40.514773: step: 676/529, loss: 0.07542910426855087
2023-01-23 00:23:41.656495: step: 680/529, loss: 0.2924463748931885
2023-01-23 00:23:42.895507: step: 684/529, loss: 0.10549774020910263
2023-01-23 00:23:44.114891: step: 688/529, loss: 0.2298925518989563
2023-01-23 00:23:45.360150: step: 692/529, loss: 2.7476649284362793
2023-01-23 00:23:46.566084: step: 696/529, loss: 0.11038355529308319
2023-01-23 00:23:47.765875: step: 700/529, loss: 0.7959449887275696
2023-01-23 00:23:48.964507: step: 704/529, loss: 0.15166091918945312
2023-01-23 00:23:50.138403: step: 708/529, loss: 0.8752228021621704
2023-01-23 00:23:51.329644: step: 712/529, loss: 0.0954316109418869
2023-01-23 00:23:52.547788: step: 716/529, loss: 0.4553895890712738
2023-01-23 00:23:53.707450: step: 720/529, loss: 0.03252401575446129
2023-01-23 00:23:54.855243: step: 724/529, loss: 0.34170404076576233
2023-01-23 00:23:56.031782: step: 728/529, loss: 0.06364612281322479
2023-01-23 00:23:57.278044: step: 732/529, loss: 0.8943905830383301
2023-01-23 00:23:58.485281: step: 736/529, loss: 0.23584184050559998
2023-01-23 00:23:59.749392: step: 740/529, loss: 0.4798815846443176
2023-01-23 00:24:00.964489: step: 744/529, loss: 0.16191625595092773
2023-01-23 00:24:02.168751: step: 748/529, loss: 0.08670292049646378
2023-01-23 00:24:03.360809: step: 752/529, loss: 0.09526281803846359
2023-01-23 00:24:04.550815: step: 756/529, loss: 0.04325075447559357
2023-01-23 00:24:05.722014: step: 760/529, loss: 0.07826395332813263
2023-01-23 00:24:06.929174: step: 764/529, loss: 0.2919696867465973
2023-01-23 00:24:08.171835: step: 768/529, loss: 0.19557294249534607
2023-01-23 00:24:09.345405: step: 772/529, loss: 0.11964817345142365
2023-01-23 00:24:10.533889: step: 776/529, loss: 0.08191376179456711
2023-01-23 00:24:11.700762: step: 780/529, loss: 0.1510431319475174
2023-01-23 00:24:12.909023: step: 784/529, loss: 0.3965839445590973
2023-01-23 00:24:14.089203: step: 788/529, loss: 0.08628664165735245
2023-01-23 00:24:15.327356: step: 792/529, loss: 0.6498953104019165
2023-01-23 00:24:16.531307: step: 796/529, loss: 0.1226348727941513
2023-01-23 00:24:17.735017: step: 800/529, loss: 0.03941622003912926
2023-01-23 00:24:18.945129: step: 804/529, loss: 0.16135630011558533
2023-01-23 00:24:20.193810: step: 808/529, loss: 0.07068949192762375
2023-01-23 00:24:21.395420: step: 812/529, loss: 0.1697521060705185
2023-01-23 00:24:22.583350: step: 816/529, loss: 0.1488906741142273
2023-01-23 00:24:23.799733: step: 820/529, loss: 0.09741143882274628
2023-01-23 00:24:25.027770: step: 824/529, loss: 0.22455954551696777
2023-01-23 00:24:26.267094: step: 828/529, loss: 0.06436805427074432
2023-01-23 00:24:27.511804: step: 832/529, loss: 0.1164170503616333
2023-01-23 00:24:28.706775: step: 836/529, loss: 0.07019386440515518
2023-01-23 00:24:29.915652: step: 840/529, loss: 0.15635260939598083
2023-01-23 00:24:31.139940: step: 844/529, loss: 0.0648404136300087
2023-01-23 00:24:32.312871: step: 848/529, loss: 0.1756184995174408
2023-01-23 00:24:33.539796: step: 852/529, loss: 0.06272697448730469
2023-01-23 00:24:34.763203: step: 856/529, loss: 0.20437927544116974
2023-01-23 00:24:35.961082: step: 860/529, loss: 0.05671968311071396
2023-01-23 00:24:37.137160: step: 864/529, loss: 0.3450182378292084
2023-01-23 00:24:38.323109: step: 868/529, loss: 0.033079661428928375
2023-01-23 00:24:39.538766: step: 872/529, loss: 0.09306202083826065
2023-01-23 00:24:40.739498: step: 876/529, loss: 0.8007081747055054
2023-01-23 00:24:41.939828: step: 880/529, loss: 0.07276339828968048
2023-01-23 00:24:43.146950: step: 884/529, loss: 0.2312414050102234
2023-01-23 00:24:44.359237: step: 888/529, loss: 0.060846708714962006
2023-01-23 00:24:45.531448: step: 892/529, loss: 0.09002557396888733
2023-01-23 00:24:46.745373: step: 896/529, loss: 0.2715110182762146
2023-01-23 00:24:47.953740: step: 900/529, loss: 0.18790817260742188
2023-01-23 00:24:49.214342: step: 904/529, loss: 0.0989135205745697
2023-01-23 00:24:50.471121: step: 908/529, loss: 0.07950916141271591
2023-01-23 00:24:51.658487: step: 912/529, loss: 0.11917848885059357
2023-01-23 00:24:52.874936: step: 916/529, loss: 0.842942476272583
2023-01-23 00:24:54.083830: step: 920/529, loss: 0.035099223256111145
2023-01-23 00:24:55.279533: step: 924/529, loss: 0.06903371959924698
2023-01-23 00:24:56.456053: step: 928/529, loss: 0.10572004318237305
2023-01-23 00:24:57.656952: step: 932/529, loss: 0.06524658203125
2023-01-23 00:24:58.872733: step: 936/529, loss: 0.003122329944744706
2023-01-23 00:25:00.089948: step: 940/529, loss: 0.06736727058887482
2023-01-23 00:25:01.271055: step: 944/529, loss: 0.05806684494018555
2023-01-23 00:25:02.511650: step: 948/529, loss: 0.1061316505074501
2023-01-23 00:25:03.716189: step: 952/529, loss: 0.11372075229883194
2023-01-23 00:25:04.870732: step: 956/529, loss: 0.10416851192712784
2023-01-23 00:25:06.097262: step: 960/529, loss: 0.1355249434709549
2023-01-23 00:25:07.289758: step: 964/529, loss: 0.06759805977344513
2023-01-23 00:25:08.496841: step: 968/529, loss: 0.06649474799633026
2023-01-23 00:25:09.717070: step: 972/529, loss: 0.42227956652641296
2023-01-23 00:25:10.896195: step: 976/529, loss: 0.0725914016366005
2023-01-23 00:25:12.086514: step: 980/529, loss: 0.0722140297293663
2023-01-23 00:25:13.307680: step: 984/529, loss: 0.3616194725036621
2023-01-23 00:25:14.472235: step: 988/529, loss: 0.16700276732444763
2023-01-23 00:25:15.672062: step: 992/529, loss: 0.16695700585842133
2023-01-23 00:25:16.844960: step: 996/529, loss: 0.11583714187145233
2023-01-23 00:25:18.034367: step: 1000/529, loss: 0.17715506255626678
2023-01-23 00:25:19.243181: step: 1004/529, loss: 0.13055677711963654
2023-01-23 00:25:20.427669: step: 1008/529, loss: 0.45041924715042114
2023-01-23 00:25:21.607918: step: 1012/529, loss: 0.07279562950134277
2023-01-23 00:25:22.804123: step: 1016/529, loss: 0.07018999755382538
2023-01-23 00:25:24.009179: step: 1020/529, loss: 0.052582837641239166
2023-01-23 00:25:25.237685: step: 1024/529, loss: 0.07242272794246674
2023-01-23 00:25:26.434615: step: 1028/529, loss: 0.44716396927833557
2023-01-23 00:25:27.624413: step: 1032/529, loss: 0.2427215576171875
2023-01-23 00:25:28.822480: step: 1036/529, loss: 0.11899687349796295
2023-01-23 00:25:30.042282: step: 1040/529, loss: 0.05931386724114418
2023-01-23 00:25:31.254554: step: 1044/529, loss: 0.42251184582710266
2023-01-23 00:25:32.452893: step: 1048/529, loss: 0.04243669658899307
2023-01-23 00:25:33.653720: step: 1052/529, loss: 0.4443243741989136
2023-01-23 00:25:34.829622: step: 1056/529, loss: 0.3045470416545868
2023-01-23 00:25:36.049067: step: 1060/529, loss: 0.49162760376930237
2023-01-23 00:25:37.232888: step: 1064/529, loss: 0.08958248049020767
2023-01-23 00:25:38.442876: step: 1068/529, loss: 0.1678430587053299
2023-01-23 00:25:39.640546: step: 1072/529, loss: 0.3991091847419739
2023-01-23 00:25:40.784961: step: 1076/529, loss: 0.14095774292945862
2023-01-23 00:25:41.949415: step: 1080/529, loss: 0.04410099983215332
2023-01-23 00:25:43.164840: step: 1084/529, loss: 0.12525591254234314
2023-01-23 00:25:44.322653: step: 1088/529, loss: 0.1044493168592453
2023-01-23 00:25:45.542913: step: 1092/529, loss: 0.4947187602519989
2023-01-23 00:25:46.784691: step: 1096/529, loss: 0.060716915875673294
2023-01-23 00:25:47.952220: step: 1100/529, loss: 0.018504096195101738
2023-01-23 00:25:49.176566: step: 1104/529, loss: 1.369433045387268
2023-01-23 00:25:50.389779: step: 1108/529, loss: 0.19306893646717072
2023-01-23 00:25:51.576064: step: 1112/529, loss: 0.16246303915977478
2023-01-23 00:25:52.745559: step: 1116/529, loss: 0.711046040058136
2023-01-23 00:25:54.014428: step: 1120/529, loss: 0.04261474311351776
2023-01-23 00:25:55.200032: step: 1124/529, loss: 0.3693057894706726
2023-01-23 00:25:56.429585: step: 1128/529, loss: 0.23279480636119843
2023-01-23 00:25:57.613036: step: 1132/529, loss: 0.13697485625743866
2023-01-23 00:25:58.814249: step: 1136/529, loss: 0.044436171650886536
2023-01-23 00:26:00.030571: step: 1140/529, loss: 0.16294154524803162
2023-01-23 00:26:01.209771: step: 1144/529, loss: 0.4666368365287781
2023-01-23 00:26:02.400372: step: 1148/529, loss: 0.14895009994506836
2023-01-23 00:26:03.584724: step: 1152/529, loss: 0.29820647835731506
2023-01-23 00:26:04.769411: step: 1156/529, loss: 0.020008422434329987
2023-01-23 00:26:05.981315: step: 1160/529, loss: 0.41993483901023865
2023-01-23 00:26:07.167557: step: 1164/529, loss: 0.4133132994174957
2023-01-23 00:26:08.364443: step: 1168/529, loss: 0.3883378803730011
2023-01-23 00:26:09.549556: step: 1172/529, loss: 0.3750898241996765
2023-01-23 00:26:10.761776: step: 1176/529, loss: 0.14187221229076385
2023-01-23 00:26:11.950042: step: 1180/529, loss: 0.24963007867336273
2023-01-23 00:26:13.142784: step: 1184/529, loss: 0.057286933064460754
2023-01-23 00:26:14.369778: step: 1188/529, loss: 0.12287655472755432
2023-01-23 00:26:15.613575: step: 1192/529, loss: 1.093945860862732
2023-01-23 00:26:16.848339: step: 1196/529, loss: 0.24185018241405487
2023-01-23 00:26:18.021744: step: 1200/529, loss: 0.03350668027997017
2023-01-23 00:26:19.221756: step: 1204/529, loss: 0.10707263648509979
2023-01-23 00:26:20.425343: step: 1208/529, loss: 0.6292132139205933
2023-01-23 00:26:21.617089: step: 1212/529, loss: 0.12353439629077911
2023-01-23 00:26:22.819885: step: 1216/529, loss: 0.03813161700963974
2023-01-23 00:26:24.049705: step: 1220/529, loss: 0.31402310729026794
2023-01-23 00:26:25.242081: step: 1224/529, loss: 0.17011003196239471
2023-01-23 00:26:26.450388: step: 1228/529, loss: 0.09156350791454315
2023-01-23 00:26:27.649779: step: 1232/529, loss: 0.1751844435930252
2023-01-23 00:26:28.836217: step: 1236/529, loss: 0.2659228444099426
2023-01-23 00:26:30.082487: step: 1240/529, loss: 0.3951171040534973
2023-01-23 00:26:31.256602: step: 1244/529, loss: 0.07096286118030548
2023-01-23 00:26:32.457602: step: 1248/529, loss: 0.17628613114356995
2023-01-23 00:26:33.648738: step: 1252/529, loss: 0.1602945327758789
2023-01-23 00:26:34.827297: step: 1256/529, loss: 0.027808405458927155
2023-01-23 00:26:35.989996: step: 1260/529, loss: 0.061707306653261185
2023-01-23 00:26:37.228608: step: 1264/529, loss: 0.2329026758670807
2023-01-23 00:26:38.436636: step: 1268/529, loss: 0.12378893047571182
2023-01-23 00:26:39.664543: step: 1272/529, loss: 0.39805689454078674
2023-01-23 00:26:40.857183: step: 1276/529, loss: 0.611111581325531
2023-01-23 00:26:42.140167: step: 1280/529, loss: 0.5031253695487976
2023-01-23 00:26:43.351047: step: 1284/529, loss: 0.16896553337574005
2023-01-23 00:26:44.533151: step: 1288/529, loss: 0.07348137348890305
2023-01-23 00:26:45.732521: step: 1292/529, loss: 0.09705796837806702
2023-01-23 00:26:46.945819: step: 1296/529, loss: 0.20655202865600586
2023-01-23 00:26:48.181524: step: 1300/529, loss: 0.05219273641705513
2023-01-23 00:26:49.384532: step: 1304/529, loss: 0.024089336395263672
2023-01-23 00:26:50.594396: step: 1308/529, loss: 0.3057098388671875
2023-01-23 00:26:51.783665: step: 1312/529, loss: 0.07620535045862198
2023-01-23 00:26:53.016074: step: 1316/529, loss: 1.2700896263122559
2023-01-23 00:26:54.184520: step: 1320/529, loss: 0.10412168502807617
2023-01-23 00:26:55.403133: step: 1324/529, loss: 0.062221430242061615
2023-01-23 00:26:56.622135: step: 1328/529, loss: 0.10426702350378036
2023-01-23 00:26:57.852996: step: 1332/529, loss: 0.16047362983226776
2023-01-23 00:26:58.999366: step: 1336/529, loss: 0.03934831917285919
2023-01-23 00:27:00.189236: step: 1340/529, loss: 0.24802951514720917
2023-01-23 00:27:01.381266: step: 1344/529, loss: 0.02524590492248535
2023-01-23 00:27:02.587615: step: 1348/529, loss: 0.08456268906593323
2023-01-23 00:27:03.770799: step: 1352/529, loss: 0.04311637952923775
2023-01-23 00:27:04.939352: step: 1356/529, loss: 0.07134446501731873
2023-01-23 00:27:06.118025: step: 1360/529, loss: 0.40787267684936523
2023-01-23 00:27:07.339660: step: 1364/529, loss: 0.10543957352638245
2023-01-23 00:27:08.510835: step: 1368/529, loss: 0.12224235385656357
2023-01-23 00:27:09.732127: step: 1372/529, loss: 0.7178272008895874
2023-01-23 00:27:10.934909: step: 1376/529, loss: 0.056239090859889984
2023-01-23 00:27:12.090175: step: 1380/529, loss: 0.05826739966869354
2023-01-23 00:27:13.249535: step: 1384/529, loss: 0.36607295274734497
2023-01-23 00:27:14.451848: step: 1388/529, loss: 0.11008220165967941
2023-01-23 00:27:15.657654: step: 1392/529, loss: 0.23859873414039612
2023-01-23 00:27:16.845155: step: 1396/529, loss: 0.02314014360308647
2023-01-23 00:27:18.057590: step: 1400/529, loss: 0.18839998543262482
2023-01-23 00:27:19.272529: step: 1404/529, loss: 0.6206230521202087
2023-01-23 00:27:20.470009: step: 1408/529, loss: 0.09049182385206223
2023-01-23 00:27:21.659979: step: 1412/529, loss: 0.2897721230983734
2023-01-23 00:27:22.879435: step: 1416/529, loss: 0.2700129449367523
2023-01-23 00:27:24.078272: step: 1420/529, loss: 0.19877544045448303
2023-01-23 00:27:25.275312: step: 1424/529, loss: 0.0664820671081543
2023-01-23 00:27:26.496044: step: 1428/529, loss: 0.28000402450561523
2023-01-23 00:27:27.688565: step: 1432/529, loss: 0.074510857462883
2023-01-23 00:27:28.894067: step: 1436/529, loss: 0.1641642153263092
2023-01-23 00:27:30.093466: step: 1440/529, loss: 0.15378575026988983
2023-01-23 00:27:31.298274: step: 1444/529, loss: 0.1630905121564865
2023-01-23 00:27:32.457381: step: 1448/529, loss: 0.4707326889038086
2023-01-23 00:27:33.667102: step: 1452/529, loss: 0.3298848271369934
2023-01-23 00:27:34.859107: step: 1456/529, loss: 0.20145931839942932
2023-01-23 00:27:36.071649: step: 1460/529, loss: 0.134362131357193
2023-01-23 00:27:37.302033: step: 1464/529, loss: 0.03931255266070366
2023-01-23 00:27:38.532876: step: 1468/529, loss: 0.10354576259851456
2023-01-23 00:27:39.732225: step: 1472/529, loss: 0.11603575199842453
2023-01-23 00:27:40.912916: step: 1476/529, loss: 0.2502133548259735
2023-01-23 00:27:42.125545: step: 1480/529, loss: 0.06853652000427246
2023-01-23 00:27:43.365427: step: 1484/529, loss: 0.10526428371667862
2023-01-23 00:27:44.587542: step: 1488/529, loss: 0.3817511796951294
2023-01-23 00:27:45.830919: step: 1492/529, loss: 0.346446692943573
2023-01-23 00:27:47.022121: step: 1496/529, loss: 0.9585376977920532
2023-01-23 00:27:48.223153: step: 1500/529, loss: 0.6719222664833069
2023-01-23 00:27:49.413887: step: 1504/529, loss: 0.05418987199664116
2023-01-23 00:27:50.635524: step: 1508/529, loss: 0.20145903527736664
2023-01-23 00:27:51.815125: step: 1512/529, loss: 0.3391339182853699
2023-01-23 00:27:53.007788: step: 1516/529, loss: 0.11726198345422745
2023-01-23 00:27:54.237354: step: 1520/529, loss: 0.23056840896606445
2023-01-23 00:27:55.433114: step: 1524/529, loss: 0.1521472930908203
2023-01-23 00:27:56.596688: step: 1528/529, loss: 0.8188669681549072
2023-01-23 00:27:57.798700: step: 1532/529, loss: 0.16956940293312073
2023-01-23 00:27:59.006252: step: 1536/529, loss: 0.06618394702672958
2023-01-23 00:28:00.220579: step: 1540/529, loss: 0.23513688147068024
2023-01-23 00:28:01.463107: step: 1544/529, loss: 0.05753679573535919
2023-01-23 00:28:02.686330: step: 1548/529, loss: 0.3507155478000641
2023-01-23 00:28:03.896365: step: 1552/529, loss: 0.11184482276439667
2023-01-23 00:28:05.074597: step: 1556/529, loss: 0.12555654346942902
2023-01-23 00:28:06.353157: step: 1560/529, loss: 0.17332783341407776
2023-01-23 00:28:07.533385: step: 1564/529, loss: 0.48004570603370667
2023-01-23 00:28:08.751328: step: 1568/529, loss: 0.2001146674156189
2023-01-23 00:28:09.918956: step: 1572/529, loss: 0.11530779302120209
2023-01-23 00:28:11.121734: step: 1576/529, loss: 0.4709669053554535
2023-01-23 00:28:12.274845: step: 1580/529, loss: 0.21258020401000977
2023-01-23 00:28:13.490082: step: 1584/529, loss: 1.6643543243408203
2023-01-23 00:28:14.673764: step: 1588/529, loss: 0.1019502654671669
2023-01-23 00:28:15.863711: step: 1592/529, loss: 0.6992985606193542
2023-01-23 00:28:17.109484: step: 1596/529, loss: 0.5678982734680176
2023-01-23 00:28:18.298489: step: 1600/529, loss: 0.16735419631004333
2023-01-23 00:28:19.519444: step: 1604/529, loss: 0.2393384575843811
2023-01-23 00:28:20.733320: step: 1608/529, loss: 0.13760320842266083
2023-01-23 00:28:21.918637: step: 1612/529, loss: 0.04805126413702965
2023-01-23 00:28:23.118014: step: 1616/529, loss: 0.3238641619682312
2023-01-23 00:28:24.363870: step: 1620/529, loss: 0.5406720638275146
2023-01-23 00:28:25.590501: step: 1624/529, loss: 0.20301905274391174
2023-01-23 00:28:26.805223: step: 1628/529, loss: 0.3603173494338989
2023-01-23 00:28:28.034814: step: 1632/529, loss: 0.255856990814209
2023-01-23 00:28:29.255257: step: 1636/529, loss: 0.3791975975036621
2023-01-23 00:28:30.413030: step: 1640/529, loss: 0.08984789252281189
2023-01-23 00:28:31.606801: step: 1644/529, loss: 0.15052680671215057
2023-01-23 00:28:32.808875: step: 1648/529, loss: 0.0904684066772461
2023-01-23 00:28:33.985379: step: 1652/529, loss: 0.07586755603551865
2023-01-23 00:28:35.175773: step: 1656/529, loss: 0.08873328566551208
2023-01-23 00:28:36.403943: step: 1660/529, loss: 0.2630959451198578
2023-01-23 00:28:37.541365: step: 1664/529, loss: 0.04309406131505966
2023-01-23 00:28:38.782141: step: 1668/529, loss: 0.2471274435520172
2023-01-23 00:28:40.015337: step: 1672/529, loss: 0.7920916676521301
2023-01-23 00:28:41.238679: step: 1676/529, loss: 0.17498460412025452
2023-01-23 00:28:42.410349: step: 1680/529, loss: 0.298117995262146
2023-01-23 00:28:43.613913: step: 1684/529, loss: 0.5017746686935425
2023-01-23 00:28:44.815833: step: 1688/529, loss: 0.08158578723669052
2023-01-23 00:28:45.994918: step: 1692/529, loss: 0.03380145877599716
2023-01-23 00:28:47.190106: step: 1696/529, loss: 0.5202838182449341
2023-01-23 00:28:48.357285: step: 1700/529, loss: 0.23248635232448578
2023-01-23 00:28:49.525792: step: 1704/529, loss: 0.032161712646484375
2023-01-23 00:28:50.720363: step: 1708/529, loss: 0.017815638333559036
2023-01-23 00:28:51.947282: step: 1712/529, loss: 1.1783852577209473
2023-01-23 00:28:53.117417: step: 1716/529, loss: 0.1213672012090683
2023-01-23 00:28:54.286015: step: 1720/529, loss: 0.04418399557471275
2023-01-23 00:28:55.476018: step: 1724/529, loss: 0.1420421600341797
2023-01-23 00:28:56.691065: step: 1728/529, loss: 0.15293598175048828
2023-01-23 00:28:57.905231: step: 1732/529, loss: 0.14314956963062286
2023-01-23 00:28:59.135747: step: 1736/529, loss: 0.848331093788147
2023-01-23 00:29:00.342019: step: 1740/529, loss: 0.1606319546699524
2023-01-23 00:29:01.544871: step: 1744/529, loss: 1.2704627513885498
2023-01-23 00:29:02.787620: step: 1748/529, loss: 0.28026026487350464
2023-01-23 00:29:04.041662: step: 1752/529, loss: 0.1323471963405609
2023-01-23 00:29:05.259859: step: 1756/529, loss: 0.12400197982788086
2023-01-23 00:29:06.508434: step: 1760/529, loss: 0.18167515099048615
2023-01-23 00:29:07.723492: step: 1764/529, loss: 0.612712025642395
2023-01-23 00:29:08.934891: step: 1768/529, loss: 0.08404932171106339
2023-01-23 00:29:10.141705: step: 1772/529, loss: 0.1690712422132492
2023-01-23 00:29:11.327708: step: 1776/529, loss: 1.1270406246185303
2023-01-23 00:29:12.532062: step: 1780/529, loss: 0.1806797981262207
2023-01-23 00:29:13.744213: step: 1784/529, loss: 0.3205658495426178
2023-01-23 00:29:14.989806: step: 1788/529, loss: 0.47389286756515503
2023-01-23 00:29:16.183848: step: 1792/529, loss: 0.11828117072582245
2023-01-23 00:29:17.365078: step: 1796/529, loss: 0.0999017208814621
2023-01-23 00:29:18.666446: step: 1800/529, loss: 0.43107879161834717
2023-01-23 00:29:19.868623: step: 1804/529, loss: 0.1836099624633789
2023-01-23 00:29:21.058332: step: 1808/529, loss: 0.3601379692554474
2023-01-23 00:29:22.250058: step: 1812/529, loss: 0.06813059002161026
2023-01-23 00:29:23.472484: step: 1816/529, loss: 0.21963539719581604
2023-01-23 00:29:24.670599: step: 1820/529, loss: 0.1584382951259613
2023-01-23 00:29:25.841914: step: 1824/529, loss: 0.16205815970897675
2023-01-23 00:29:27.059980: step: 1828/529, loss: 0.3298429846763611
2023-01-23 00:29:28.308522: step: 1832/529, loss: 0.09752638638019562
2023-01-23 00:29:29.531886: step: 1836/529, loss: 0.24355296790599823
2023-01-23 00:29:30.739717: step: 1840/529, loss: 0.3982164263725281
2023-01-23 00:29:31.935526: step: 1844/529, loss: 0.1338053196668625
2023-01-23 00:29:33.140783: step: 1848/529, loss: 0.1026037186384201
2023-01-23 00:29:34.372527: step: 1852/529, loss: 0.2660253643989563
2023-01-23 00:29:35.534250: step: 1856/529, loss: 0.08683805912733078
2023-01-23 00:29:36.726551: step: 1860/529, loss: 0.09859263896942139
2023-01-23 00:29:37.947380: step: 1864/529, loss: 0.18862372636795044
2023-01-23 00:29:39.142706: step: 1868/529, loss: 0.2622078061103821
2023-01-23 00:29:40.353391: step: 1872/529, loss: 1.7078286409378052
2023-01-23 00:29:41.572846: step: 1876/529, loss: 0.5195013284683228
2023-01-23 00:29:42.813193: step: 1880/529, loss: 0.1314561814069748
2023-01-23 00:29:43.991400: step: 1884/529, loss: 0.13290110230445862
2023-01-23 00:29:45.162082: step: 1888/529, loss: 0.1165735274553299
2023-01-23 00:29:46.341393: step: 1892/529, loss: 0.1444697380065918
2023-01-23 00:29:47.598207: step: 1896/529, loss: 0.325215607881546
2023-01-23 00:29:48.805703: step: 1900/529, loss: 0.2552858293056488
2023-01-23 00:29:49.993463: step: 1904/529, loss: 0.12094173580408096
2023-01-23 00:29:51.172584: step: 1908/529, loss: 0.07685938477516174
2023-01-23 00:29:52.360133: step: 1912/529, loss: 0.041986849159002304
2023-01-23 00:29:53.512600: step: 1916/529, loss: 0.13326062262058258
2023-01-23 00:29:54.685063: step: 1920/529, loss: 0.08943261951208115
2023-01-23 00:29:55.910129: step: 1924/529, loss: 0.33203163743019104
2023-01-23 00:29:57.120049: step: 1928/529, loss: 0.19435596466064453
2023-01-23 00:29:58.350286: step: 1932/529, loss: 0.32233601808547974
2023-01-23 00:29:59.512228: step: 1936/529, loss: 0.06961946189403534
2023-01-23 00:30:00.688585: step: 1940/529, loss: 0.4815933406352997
2023-01-23 00:30:01.918998: step: 1944/529, loss: 3.1408493518829346
2023-01-23 00:30:03.148906: step: 1948/529, loss: 1.1807891130447388
2023-01-23 00:30:04.378351: step: 1952/529, loss: 0.05921440199017525
2023-01-23 00:30:05.648725: step: 1956/529, loss: 0.6824713945388794
2023-01-23 00:30:06.849571: step: 1960/529, loss: 0.1524069756269455
2023-01-23 00:30:08.036269: step: 1964/529, loss: 0.035631559789180756
2023-01-23 00:30:09.248638: step: 1968/529, loss: 0.00496253976598382
2023-01-23 00:30:10.414720: step: 1972/529, loss: 0.27055779099464417
2023-01-23 00:30:11.589043: step: 1976/529, loss: 0.046446993947029114
2023-01-23 00:30:12.787427: step: 1980/529, loss: 0.2582065463066101
2023-01-23 00:30:14.023987: step: 1984/529, loss: 0.11286059021949768
2023-01-23 00:30:15.209955: step: 1988/529, loss: 0.12138843536376953
2023-01-23 00:30:16.365346: step: 1992/529, loss: 0.6295469403266907
2023-01-23 00:30:17.558182: step: 1996/529, loss: 0.07660198211669922
2023-01-23 00:30:18.707337: step: 2000/529, loss: 0.5249840021133423
2023-01-23 00:30:19.908929: step: 2004/529, loss: 0.21708515286445618
2023-01-23 00:30:21.089947: step: 2008/529, loss: 0.08994626998901367
2023-01-23 00:30:22.292172: step: 2012/529, loss: 0.1991274356842041
2023-01-23 00:30:23.473562: step: 2016/529, loss: 0.03229856491088867
2023-01-23 00:30:24.705508: step: 2020/529, loss: 0.11284971237182617
2023-01-23 00:30:25.902653: step: 2024/529, loss: 0.1971236765384674
2023-01-23 00:30:27.074535: step: 2028/529, loss: 0.029836272820830345
2023-01-23 00:30:28.288602: step: 2032/529, loss: 0.6303896307945251
2023-01-23 00:30:29.489591: step: 2036/529, loss: 0.05511905997991562
2023-01-23 00:30:30.737621: step: 2040/529, loss: 0.37411537766456604
2023-01-23 00:30:31.937766: step: 2044/529, loss: 0.0494970828294754
2023-01-23 00:30:33.158795: step: 2048/529, loss: 0.05961489677429199
2023-01-23 00:30:34.365907: step: 2052/529, loss: 0.14190036058425903
2023-01-23 00:30:35.568909: step: 2056/529, loss: 0.15941821038722992
2023-01-23 00:30:36.732217: step: 2060/529, loss: 0.04620103910565376
2023-01-23 00:30:37.968143: step: 2064/529, loss: 0.1399737000465393
2023-01-23 00:30:39.201586: step: 2068/529, loss: 0.2921361029148102
2023-01-23 00:30:40.394164: step: 2072/529, loss: 0.3828907012939453
2023-01-23 00:30:41.593571: step: 2076/529, loss: 0.18975695967674255
2023-01-23 00:30:42.796164: step: 2080/529, loss: 0.053339533507823944
2023-01-23 00:30:43.965152: step: 2084/529, loss: 1.0323189496994019
2023-01-23 00:30:45.160859: step: 2088/529, loss: 0.08985204249620438
2023-01-23 00:30:46.339501: step: 2092/529, loss: 0.5369731187820435
2023-01-23 00:30:47.532217: step: 2096/529, loss: 0.05523400753736496
2023-01-23 00:30:48.748308: step: 2100/529, loss: 0.12967653572559357
2023-01-23 00:30:50.019521: step: 2104/529, loss: 0.4421672821044922
2023-01-23 00:30:51.218536: step: 2108/529, loss: 0.07011689990758896
2023-01-23 00:30:52.415567: step: 2112/529, loss: 0.2283024787902832
2023-01-23 00:30:53.635318: step: 2116/529, loss: 0.23045654594898224
==================================================
Loss: 0.258
--------------------
Dev: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.6, 'r': 0.7777777777777778, 'f1': 0.6774193548387097}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.5396825396825397, 'r': 0.5396825396825397, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5972944849115505, 'r': 0.7643142476697736, 'f1': 0.6705607476635514}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6162162162162163, 'r': 0.7513481126423007, 'f1': 0.6771058315334773}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 00:31:43.091143: step: 4/529, loss: 0.10589957237243652
2023-01-23 00:31:44.267494: step: 8/529, loss: 0.21908380091190338
2023-01-23 00:31:45.453080: step: 12/529, loss: 0.07282567024230957
2023-01-23 00:31:46.643119: step: 16/529, loss: 0.6927698850631714
2023-01-23 00:31:47.824157: step: 20/529, loss: 0.16808386147022247
2023-01-23 00:31:49.036665: step: 24/529, loss: 0.3427462577819824
2023-01-23 00:31:50.220683: step: 28/529, loss: 0.07606158405542374
2023-01-23 00:31:51.411640: step: 32/529, loss: 0.17398712038993835
2023-01-23 00:31:52.609894: step: 36/529, loss: 0.08700942993164062
2023-01-23 00:31:53.777741: step: 40/529, loss: 0.16824179887771606
2023-01-23 00:31:54.967678: step: 44/529, loss: 0.03893642500042915
2023-01-23 00:31:56.162756: step: 48/529, loss: 0.18418365716934204
2023-01-23 00:31:57.392924: step: 52/529, loss: 0.14820843935012817
2023-01-23 00:31:58.600310: step: 56/529, loss: 0.02458428218960762
2023-01-23 00:31:59.775695: step: 60/529, loss: 0.07334604114294052
2023-01-23 00:32:01.017730: step: 64/529, loss: 0.13620567321777344
2023-01-23 00:32:02.245866: step: 68/529, loss: 0.04479523003101349
2023-01-23 00:32:03.436905: step: 72/529, loss: 0.10311079025268555
2023-01-23 00:32:04.615684: step: 76/529, loss: 0.17127513885498047
2023-01-23 00:32:05.838045: step: 80/529, loss: 0.12035751342773438
2023-01-23 00:32:07.055525: step: 84/529, loss: 0.07973573356866837
2023-01-23 00:32:08.235036: step: 88/529, loss: 0.17489276826381683
2023-01-23 00:32:09.456476: step: 92/529, loss: 0.04985666275024414
2023-01-23 00:32:10.634131: step: 96/529, loss: 0.12287703156471252
2023-01-23 00:32:11.846589: step: 100/529, loss: 0.22918052971363068
2023-01-23 00:32:13.029209: step: 104/529, loss: 0.07233639061450958
2023-01-23 00:32:14.185198: step: 108/529, loss: 0.09398073703050613
2023-01-23 00:32:15.392111: step: 112/529, loss: 0.23602047562599182
2023-01-23 00:32:16.555148: step: 116/529, loss: 0.09541550278663635
2023-01-23 00:32:17.725805: step: 120/529, loss: 0.017404623329639435
2023-01-23 00:32:18.939634: step: 124/529, loss: 0.6073402762413025
2023-01-23 00:32:20.127265: step: 128/529, loss: 0.09669695794582367
2023-01-23 00:32:21.287521: step: 132/529, loss: 0.44639524817466736
2023-01-23 00:32:22.475876: step: 136/529, loss: 0.3745598793029785
2023-01-23 00:32:23.679967: step: 140/529, loss: 0.16365870833396912
2023-01-23 00:32:24.832563: step: 144/529, loss: 0.2182145118713379
2023-01-23 00:32:26.060509: step: 148/529, loss: 0.12828445434570312
2023-01-23 00:32:27.265933: step: 152/529, loss: 0.09437441825866699
2023-01-23 00:32:28.475254: step: 156/529, loss: 0.10758233070373535
2023-01-23 00:32:29.658933: step: 160/529, loss: 0.08210039138793945
2023-01-23 00:32:30.857182: step: 164/529, loss: 0.14318743348121643
2023-01-23 00:32:32.135302: step: 168/529, loss: 0.761003851890564
2023-01-23 00:32:33.293960: step: 172/529, loss: 0.17744722962379456
2023-01-23 00:32:34.530657: step: 176/529, loss: 0.05552082136273384
2023-01-23 00:32:35.714491: step: 180/529, loss: 0.040445901453495026
2023-01-23 00:32:36.887542: step: 184/529, loss: 0.22667713463306427
2023-01-23 00:32:38.118014: step: 188/529, loss: 0.09442977607250214
2023-01-23 00:32:39.304402: step: 192/529, loss: 0.04959920048713684
2023-01-23 00:32:40.494279: step: 196/529, loss: 0.12227264046669006
2023-01-23 00:32:41.661298: step: 200/529, loss: 0.08564300835132599
2023-01-23 00:32:42.842647: step: 204/529, loss: 0.2260417342185974
2023-01-23 00:32:44.082741: step: 208/529, loss: 0.3497160077095032
2023-01-23 00:32:45.261200: step: 212/529, loss: 0.08734989166259766
2023-01-23 00:32:46.461598: step: 216/529, loss: 0.3192896842956543
2023-01-23 00:32:47.679121: step: 220/529, loss: 0.07175035774707794
2023-01-23 00:32:48.847550: step: 224/529, loss: 0.05217437818646431
2023-01-23 00:32:50.040839: step: 228/529, loss: 0.22653542459011078
2023-01-23 00:32:51.235404: step: 232/529, loss: 0.05051755905151367
2023-01-23 00:32:52.437445: step: 236/529, loss: 0.09453191608190536
2023-01-23 00:32:53.636399: step: 240/529, loss: 0.3061576783657074
2023-01-23 00:32:54.867275: step: 244/529, loss: 0.5732786059379578
2023-01-23 00:32:56.032380: step: 248/529, loss: 0.08783912658691406
2023-01-23 00:32:57.221041: step: 252/529, loss: 0.08129101246595383
2023-01-23 00:32:58.410365: step: 256/529, loss: 0.10382424294948578
2023-01-23 00:32:59.594431: step: 260/529, loss: 0.03250408172607422
2023-01-23 00:33:00.789217: step: 264/529, loss: 0.25739455223083496
2023-01-23 00:33:01.991755: step: 268/529, loss: 0.4122230112552643
2023-01-23 00:33:03.178797: step: 272/529, loss: 0.0798913985490799
2023-01-23 00:33:04.363800: step: 276/529, loss: 0.12691421806812286
2023-01-23 00:33:05.565614: step: 280/529, loss: 0.035292983055114746
2023-01-23 00:33:06.777307: step: 284/529, loss: 0.2380600869655609
2023-01-23 00:33:07.946633: step: 288/529, loss: 0.044199660420417786
2023-01-23 00:33:09.183365: step: 292/529, loss: 0.14047423005104065
2023-01-23 00:33:10.427023: step: 296/529, loss: 0.13608382642269135
2023-01-23 00:33:11.629276: step: 300/529, loss: 0.7455171346664429
2023-01-23 00:33:12.794288: step: 304/529, loss: 0.04918579012155533
2023-01-23 00:33:13.987034: step: 308/529, loss: 0.23515090346336365
2023-01-23 00:33:15.193645: step: 312/529, loss: 0.3390515446662903
2023-01-23 00:33:16.437515: step: 316/529, loss: 0.12649232149124146
2023-01-23 00:33:17.617973: step: 320/529, loss: 0.07180137932300568
2023-01-23 00:33:18.819326: step: 324/529, loss: 0.13320092856884003
2023-01-23 00:33:19.996419: step: 328/529, loss: 0.0655854195356369
2023-01-23 00:33:21.245486: step: 332/529, loss: 0.222435861825943
2023-01-23 00:33:22.454661: step: 336/529, loss: 0.03322477638721466
2023-01-23 00:33:23.621590: step: 340/529, loss: 0.09303388744592667
2023-01-23 00:33:24.831587: step: 344/529, loss: 0.6150559186935425
2023-01-23 00:33:26.005060: step: 348/529, loss: 0.22516921162605286
2023-01-23 00:33:27.236265: step: 352/529, loss: 0.06781677901744843
2023-01-23 00:33:28.412171: step: 356/529, loss: 0.3233199119567871
2023-01-23 00:33:29.641169: step: 360/529, loss: 1.7418625354766846
2023-01-23 00:33:30.803626: step: 364/529, loss: 0.11892616003751755
2023-01-23 00:33:32.024870: step: 368/529, loss: 0.08918438106775284
2023-01-23 00:33:33.248151: step: 372/529, loss: 0.4355054795742035
2023-01-23 00:33:34.478759: step: 376/529, loss: 0.2471255660057068
2023-01-23 00:33:35.683816: step: 380/529, loss: 0.12259600311517715
2023-01-23 00:33:36.889499: step: 384/529, loss: 0.1358955353498459
2023-01-23 00:33:38.173293: step: 388/529, loss: 0.779319167137146
2023-01-23 00:33:39.395406: step: 392/529, loss: 0.21276387572288513
2023-01-23 00:33:40.601536: step: 396/529, loss: 0.17627926170825958
2023-01-23 00:33:41.819018: step: 400/529, loss: 0.014339685440063477
2023-01-23 00:33:43.005738: step: 404/529, loss: 0.42780694365501404
2023-01-23 00:33:44.254089: step: 408/529, loss: 0.15504422783851624
2023-01-23 00:33:45.411853: step: 412/529, loss: 0.08078651875257492
2023-01-23 00:33:46.604910: step: 416/529, loss: 0.10272950679063797
2023-01-23 00:33:47.803589: step: 420/529, loss: 0.03373727947473526
2023-01-23 00:33:48.976924: step: 424/529, loss: 0.051468562334775925
2023-01-23 00:33:50.179483: step: 428/529, loss: 0.21358510851860046
2023-01-23 00:33:51.407563: step: 432/529, loss: 0.14000442624092102
2023-01-23 00:33:52.603380: step: 436/529, loss: 0.18310546875
2023-01-23 00:33:53.789880: step: 440/529, loss: 0.046625807881355286
2023-01-23 00:33:54.983235: step: 444/529, loss: 0.10094237327575684
2023-01-23 00:33:56.148812: step: 448/529, loss: 0.10158684104681015
2023-01-23 00:33:57.352738: step: 452/529, loss: 0.45576751232147217
2023-01-23 00:33:58.571951: step: 456/529, loss: 0.04575367271900177
2023-01-23 00:33:59.766322: step: 460/529, loss: 0.03559841960668564
2023-01-23 00:34:00.956388: step: 464/529, loss: 0.03655586391687393
2023-01-23 00:34:02.165521: step: 468/529, loss: 0.07966232299804688
2023-01-23 00:34:03.379510: step: 472/529, loss: 0.06193351745605469
2023-01-23 00:34:04.590321: step: 476/529, loss: 0.18272274732589722
2023-01-23 00:34:05.788793: step: 480/529, loss: 0.045558929443359375
2023-01-23 00:34:06.971931: step: 484/529, loss: 0.2142782211303711
2023-01-23 00:34:08.159048: step: 488/529, loss: 0.11159686744213104
2023-01-23 00:34:09.339538: step: 492/529, loss: 1.1090492010116577
2023-01-23 00:34:10.527495: step: 496/529, loss: 0.44914522767066956
2023-01-23 00:34:11.755797: step: 500/529, loss: 0.12861518561840057
2023-01-23 00:34:12.988718: step: 504/529, loss: 0.0794256180524826
2023-01-23 00:34:14.156538: step: 508/529, loss: 1.1489883661270142
2023-01-23 00:34:15.324120: step: 512/529, loss: 0.3028290271759033
2023-01-23 00:34:16.502375: step: 516/529, loss: 0.4474167823791504
2023-01-23 00:34:17.677922: step: 520/529, loss: 0.05286760628223419
2023-01-23 00:34:18.907277: step: 524/529, loss: 0.0742516964673996
2023-01-23 00:34:20.083864: step: 528/529, loss: 0.13036441802978516
2023-01-23 00:34:21.261807: step: 532/529, loss: 0.0628504753112793
2023-01-23 00:34:22.444037: step: 536/529, loss: 0.26407405734062195
2023-01-23 00:34:23.675315: step: 540/529, loss: 0.1905006766319275
2023-01-23 00:34:24.889269: step: 544/529, loss: 0.09538622200489044
2023-01-23 00:34:26.102810: step: 548/529, loss: 0.06817150115966797
2023-01-23 00:34:27.326598: step: 552/529, loss: 0.09002959728240967
2023-01-23 00:34:28.468938: step: 556/529, loss: 0.06637854874134064
2023-01-23 00:34:29.697092: step: 560/529, loss: 0.14218568801879883
2023-01-23 00:34:30.876454: step: 564/529, loss: 0.10075482726097107
2023-01-23 00:34:32.051003: step: 568/529, loss: 0.0855649933218956
2023-01-23 00:34:33.248313: step: 572/529, loss: 0.05151872709393501
2023-01-23 00:34:34.465645: step: 576/529, loss: 0.09031935036182404
2023-01-23 00:34:35.608062: step: 580/529, loss: 0.09525956958532333
2023-01-23 00:34:36.851544: step: 584/529, loss: 0.10757496953010559
2023-01-23 00:34:38.005335: step: 588/529, loss: 0.06247062608599663
2023-01-23 00:34:39.186526: step: 592/529, loss: 0.1461045742034912
2023-01-23 00:34:40.371625: step: 596/529, loss: 0.05201916769146919
2023-01-23 00:34:41.564785: step: 600/529, loss: 0.1091095432639122
2023-01-23 00:34:42.800199: step: 604/529, loss: 0.13102392852306366
2023-01-23 00:34:43.989168: step: 608/529, loss: 0.1188901960849762
2023-01-23 00:34:45.165349: step: 612/529, loss: 0.031339120119810104
2023-01-23 00:34:46.371030: step: 616/529, loss: 0.17421989142894745
2023-01-23 00:34:47.561018: step: 620/529, loss: 0.2147742360830307
2023-01-23 00:34:48.811052: step: 624/529, loss: 0.028879739344120026
2023-01-23 00:34:50.066243: step: 628/529, loss: 0.048896029591560364
2023-01-23 00:34:51.294510: step: 632/529, loss: 0.06603431701660156
2023-01-23 00:34:52.467763: step: 636/529, loss: 0.2266365885734558
2023-01-23 00:34:53.680892: step: 640/529, loss: 0.517035186290741
2023-01-23 00:34:54.880675: step: 644/529, loss: 0.10150003433227539
2023-01-23 00:34:56.091969: step: 648/529, loss: 0.18182729184627533
2023-01-23 00:34:57.323021: step: 652/529, loss: 0.08189000934362411
2023-01-23 00:34:58.498626: step: 656/529, loss: 0.746856689453125
2023-01-23 00:34:59.700245: step: 660/529, loss: 0.16903123259544373
2023-01-23 00:35:00.926348: step: 664/529, loss: 0.27688655257225037
2023-01-23 00:35:02.136098: step: 668/529, loss: 0.13444343209266663
2023-01-23 00:35:03.336343: step: 672/529, loss: 0.09752359986305237
2023-01-23 00:35:04.516117: step: 676/529, loss: 0.14398424327373505
2023-01-23 00:35:05.719875: step: 680/529, loss: 0.0674186646938324
2023-01-23 00:35:06.898619: step: 684/529, loss: 0.05894365906715393
2023-01-23 00:35:08.114228: step: 688/529, loss: 0.15008696913719177
2023-01-23 00:35:09.291716: step: 692/529, loss: 0.05433502420783043
2023-01-23 00:35:10.460582: step: 696/529, loss: 0.06244697794318199
2023-01-23 00:35:11.656936: step: 700/529, loss: 0.11346426606178284
2023-01-23 00:35:12.876653: step: 704/529, loss: 0.31059932708740234
2023-01-23 00:35:14.058898: step: 708/529, loss: 0.42036062479019165
2023-01-23 00:35:15.230686: step: 712/529, loss: 0.17736978828907013
2023-01-23 00:35:16.427296: step: 716/529, loss: 0.20522668957710266
2023-01-23 00:35:17.610601: step: 720/529, loss: 0.13032397627830505
2023-01-23 00:35:18.835069: step: 724/529, loss: 0.15366163849830627
2023-01-23 00:35:20.074470: step: 728/529, loss: 0.17785649001598358
2023-01-23 00:35:21.292118: step: 732/529, loss: 0.07725667953491211
2023-01-23 00:35:22.502463: step: 736/529, loss: 0.327543169260025
2023-01-23 00:35:23.657880: step: 740/529, loss: 0.11206570267677307
2023-01-23 00:35:24.842605: step: 744/529, loss: 0.1620674431324005
2023-01-23 00:35:26.093259: step: 748/529, loss: 0.09441623091697693
2023-01-23 00:35:27.302046: step: 752/529, loss: 0.08023242652416229
2023-01-23 00:35:28.513343: step: 756/529, loss: 0.14856243133544922
2023-01-23 00:35:29.731687: step: 760/529, loss: 0.20588092505931854
2023-01-23 00:35:30.945329: step: 764/529, loss: 0.35215798020362854
2023-01-23 00:35:32.212410: step: 768/529, loss: 0.08385610580444336
2023-01-23 00:35:33.408730: step: 772/529, loss: 0.45255520939826965
2023-01-23 00:35:34.592437: step: 776/529, loss: 0.17122679948806763
2023-01-23 00:35:35.756974: step: 780/529, loss: 0.1269122064113617
2023-01-23 00:35:36.952524: step: 784/529, loss: 0.19283480942249298
2023-01-23 00:35:38.130560: step: 788/529, loss: 0.3809739947319031
2023-01-23 00:35:39.307764: step: 792/529, loss: 0.17116416990756989
2023-01-23 00:35:40.459530: step: 796/529, loss: 0.09271755069494247
2023-01-23 00:35:41.679616: step: 800/529, loss: 0.3224680423736572
2023-01-23 00:35:42.886978: step: 804/529, loss: 0.08264753967523575
2023-01-23 00:35:44.029215: step: 808/529, loss: 0.1487569361925125
2023-01-23 00:35:45.260237: step: 812/529, loss: 0.21787682175636292
2023-01-23 00:35:46.434513: step: 816/529, loss: 0.14486685395240784
2023-01-23 00:35:47.643571: step: 820/529, loss: 0.06020841747522354
2023-01-23 00:35:48.827525: step: 824/529, loss: 0.08215351402759552
2023-01-23 00:35:50.034040: step: 828/529, loss: 0.29529374837875366
2023-01-23 00:35:51.227313: step: 832/529, loss: 0.09386768937110901
2023-01-23 00:35:52.426155: step: 836/529, loss: 0.10929146409034729
2023-01-23 00:35:53.592969: step: 840/529, loss: 0.10478658974170685
2023-01-23 00:35:54.828004: step: 844/529, loss: 0.04086117446422577
2023-01-23 00:35:56.027808: step: 848/529, loss: 0.14262591302394867
2023-01-23 00:35:57.222215: step: 852/529, loss: 0.2966577112674713
2023-01-23 00:35:58.411871: step: 856/529, loss: 0.07949323952198029
2023-01-23 00:35:59.588014: step: 860/529, loss: 0.06210136413574219
2023-01-23 00:36:00.794758: step: 864/529, loss: 0.12779837846755981
2023-01-23 00:36:01.985957: step: 868/529, loss: 0.0899849385023117
2023-01-23 00:36:03.229139: step: 872/529, loss: 0.19754600524902344
2023-01-23 00:36:04.421715: step: 876/529, loss: 0.06834087520837784
2023-01-23 00:36:05.618389: step: 880/529, loss: 0.39172792434692383
2023-01-23 00:36:06.810795: step: 884/529, loss: 0.2842188775539398
2023-01-23 00:36:08.001532: step: 888/529, loss: 1.0451123714447021
2023-01-23 00:36:09.166752: step: 892/529, loss: 0.0974455326795578
2023-01-23 00:36:10.354672: step: 896/529, loss: 0.08310942351818085
2023-01-23 00:36:11.578738: step: 900/529, loss: 0.3428930342197418
2023-01-23 00:36:12.811637: step: 904/529, loss: 0.6722579598426819
2023-01-23 00:36:13.984591: step: 908/529, loss: 0.09764671325683594
2023-01-23 00:36:15.160142: step: 912/529, loss: 0.13239383697509766
2023-01-23 00:36:16.344941: step: 916/529, loss: 0.7763820886611938
2023-01-23 00:36:17.544796: step: 920/529, loss: 0.20144206285476685
2023-01-23 00:36:18.769189: step: 924/529, loss: 0.05530283600091934
2023-01-23 00:36:19.949681: step: 928/529, loss: 1.1358426809310913
2023-01-23 00:36:21.141882: step: 932/529, loss: 0.04838709905743599
2023-01-23 00:36:22.290046: step: 936/529, loss: 0.17898578941822052
2023-01-23 00:36:23.487344: step: 940/529, loss: 0.0015744924312457442
2023-01-23 00:36:24.708437: step: 944/529, loss: 0.3382924497127533
2023-01-23 00:36:25.926483: step: 948/529, loss: 0.11519765853881836
2023-01-23 00:36:27.124330: step: 952/529, loss: 0.6631711721420288
2023-01-23 00:36:28.305763: step: 956/529, loss: 0.09338932484388351
2023-01-23 00:36:29.495422: step: 960/529, loss: 0.0464324951171875
2023-01-23 00:36:30.685154: step: 964/529, loss: 0.09477519989013672
2023-01-23 00:36:31.874157: step: 968/529, loss: 0.07203254848718643
2023-01-23 00:36:33.070916: step: 972/529, loss: 0.28010159730911255
2023-01-23 00:36:34.247412: step: 976/529, loss: 0.1176910474896431
2023-01-23 00:36:35.517349: step: 980/529, loss: 0.21471108496189117
2023-01-23 00:36:36.666789: step: 984/529, loss: 0.038515470921993256
2023-01-23 00:36:37.849124: step: 988/529, loss: 0.1317310333251953
2023-01-23 00:36:38.995512: step: 992/529, loss: 0.018651485443115234
2023-01-23 00:36:40.164357: step: 996/529, loss: 0.06031942367553711
2023-01-23 00:36:41.395420: step: 1000/529, loss: 0.17538222670555115
2023-01-23 00:36:42.602343: step: 1004/529, loss: 0.3069891333580017
2023-01-23 00:36:43.815799: step: 1008/529, loss: 0.0990542396903038
2023-01-23 00:36:45.035400: step: 1012/529, loss: 0.0547361820936203
2023-01-23 00:36:46.260431: step: 1016/529, loss: 0.11041097342967987
2023-01-23 00:36:47.481084: step: 1020/529, loss: 0.1792929768562317
2023-01-23 00:36:48.682977: step: 1024/529, loss: 0.06711836159229279
2023-01-23 00:36:49.883032: step: 1028/529, loss: 0.05936441570520401
2023-01-23 00:36:51.037876: step: 1032/529, loss: 0.09092765301465988
2023-01-23 00:36:52.235468: step: 1036/529, loss: 0.03158579021692276
2023-01-23 00:36:53.410170: step: 1040/529, loss: 0.10615473240613937
2023-01-23 00:36:54.624559: step: 1044/529, loss: 0.09594269096851349
2023-01-23 00:36:55.810267: step: 1048/529, loss: 0.12677517533302307
2023-01-23 00:36:57.005466: step: 1052/529, loss: 0.1462719887495041
2023-01-23 00:36:58.184880: step: 1056/529, loss: 0.14660054445266724
2023-01-23 00:36:59.360362: step: 1060/529, loss: 0.10974879562854767
2023-01-23 00:37:00.561916: step: 1064/529, loss: 0.10343937575817108
2023-01-23 00:37:01.711174: step: 1068/529, loss: 0.23514434695243835
2023-01-23 00:37:02.914320: step: 1072/529, loss: 0.2881399095058441
2023-01-23 00:37:04.053351: step: 1076/529, loss: 0.1503990739583969
2023-01-23 00:37:05.249175: step: 1080/529, loss: 0.21785756945610046
2023-01-23 00:37:06.417741: step: 1084/529, loss: 0.16295868158340454
2023-01-23 00:37:07.605505: step: 1088/529, loss: 0.06543765217065811
2023-01-23 00:37:08.796586: step: 1092/529, loss: 0.13311271369457245
2023-01-23 00:37:10.004984: step: 1096/529, loss: 0.6653415560722351
2023-01-23 00:37:11.223804: step: 1100/529, loss: 0.0646912157535553
2023-01-23 00:37:12.563036: step: 1104/529, loss: 0.17172202467918396
2023-01-23 00:37:13.805739: step: 1108/529, loss: 0.07701635360717773
2023-01-23 00:37:15.012532: step: 1112/529, loss: 0.1330009400844574
2023-01-23 00:37:16.193170: step: 1116/529, loss: 0.15148693323135376
2023-01-23 00:37:17.392939: step: 1120/529, loss: 0.19542741775512695
2023-01-23 00:37:18.588047: step: 1124/529, loss: 0.059992220252752304
2023-01-23 00:37:19.827713: step: 1128/529, loss: 0.8736928105354309
2023-01-23 00:37:21.052439: step: 1132/529, loss: 0.08895877003669739
2023-01-23 00:37:22.212910: step: 1136/529, loss: 0.036873627454042435
2023-01-23 00:37:23.405147: step: 1140/529, loss: 0.3747602701187134
2023-01-23 00:37:24.623061: step: 1144/529, loss: 0.241233229637146
2023-01-23 00:37:25.831376: step: 1148/529, loss: 0.10447006672620773
2023-01-23 00:37:26.992868: step: 1152/529, loss: 0.16195747256278992
2023-01-23 00:37:28.221581: step: 1156/529, loss: 0.3099810481071472
2023-01-23 00:37:29.455966: step: 1160/529, loss: 0.012358666397631168
2023-01-23 00:37:30.693041: step: 1164/529, loss: 0.061627957969903946
2023-01-23 00:37:31.908061: step: 1168/529, loss: 0.4493255615234375
2023-01-23 00:37:33.090034: step: 1172/529, loss: 0.06605024635791779
2023-01-23 00:37:34.353904: step: 1176/529, loss: 0.0601743683218956
2023-01-23 00:37:35.514856: step: 1180/529, loss: 0.5440307855606079
2023-01-23 00:37:36.792394: step: 1184/529, loss: 0.4135196805000305
2023-01-23 00:37:38.009672: step: 1188/529, loss: 0.10755673050880432
2023-01-23 00:37:39.202825: step: 1192/529, loss: 0.09541235119104385
2023-01-23 00:37:40.433913: step: 1196/529, loss: 0.2487073838710785
2023-01-23 00:37:41.627946: step: 1200/529, loss: 0.09223347157239914
2023-01-23 00:37:42.792275: step: 1204/529, loss: 0.1353287696838379
2023-01-23 00:37:43.994824: step: 1208/529, loss: 0.12909898161888123
2023-01-23 00:37:45.198306: step: 1212/529, loss: 0.18661917746067047
2023-01-23 00:37:46.412960: step: 1216/529, loss: 0.09025654941797256
2023-01-23 00:37:47.645277: step: 1220/529, loss: 0.1750471144914627
2023-01-23 00:37:48.846404: step: 1224/529, loss: 0.04515476152300835
2023-01-23 00:37:50.057898: step: 1228/529, loss: 0.5536761283874512
2023-01-23 00:37:51.228379: step: 1232/529, loss: 0.09854154288768768
2023-01-23 00:37:52.427950: step: 1236/529, loss: 0.10595427453517914
2023-01-23 00:37:53.625771: step: 1240/529, loss: 0.054291535168886185
2023-01-23 00:37:54.805383: step: 1244/529, loss: 0.064898781478405
2023-01-23 00:37:55.981317: step: 1248/529, loss: 0.09864282608032227
2023-01-23 00:37:57.226347: step: 1252/529, loss: 0.34795936942100525
2023-01-23 00:37:58.409909: step: 1256/529, loss: 0.03506441414356232
2023-01-23 00:37:59.624595: step: 1260/529, loss: 0.16099444031715393
2023-01-23 00:38:00.802469: step: 1264/529, loss: 0.036310866475105286
2023-01-23 00:38:01.977364: step: 1268/529, loss: 0.0830836296081543
2023-01-23 00:38:03.189301: step: 1272/529, loss: 0.11686515808105469
2023-01-23 00:38:04.374826: step: 1276/529, loss: 0.1329561173915863
2023-01-23 00:38:05.585836: step: 1280/529, loss: 0.08197034895420074
2023-01-23 00:38:06.855999: step: 1284/529, loss: 0.23507671058177948
2023-01-23 00:38:08.054563: step: 1288/529, loss: 0.11753444373607635
2023-01-23 00:38:09.247904: step: 1292/529, loss: 0.14726237952709198
2023-01-23 00:38:10.474712: step: 1296/529, loss: 0.15031376481056213
2023-01-23 00:38:11.681617: step: 1300/529, loss: 0.5373073816299438
2023-01-23 00:38:12.832375: step: 1304/529, loss: 0.03905687481164932
2023-01-23 00:38:14.078387: step: 1308/529, loss: 0.1880422830581665
2023-01-23 00:38:15.287988: step: 1312/529, loss: 0.17137441039085388
2023-01-23 00:38:16.486701: step: 1316/529, loss: 0.28714749217033386
2023-01-23 00:38:17.708798: step: 1320/529, loss: 0.14100919663906097
2023-01-23 00:38:18.910855: step: 1324/529, loss: 0.017325926572084427
2023-01-23 00:38:20.104548: step: 1328/529, loss: 0.051026154309511185
2023-01-23 00:38:21.311807: step: 1332/529, loss: 0.12988539040088654
2023-01-23 00:38:22.514541: step: 1336/529, loss: 0.11078184098005295
2023-01-23 00:38:23.700696: step: 1340/529, loss: 0.06654338538646698
2023-01-23 00:38:24.889994: step: 1344/529, loss: 0.21339836716651917
2023-01-23 00:38:26.082540: step: 1348/529, loss: 0.03113708645105362
2023-01-23 00:38:27.281394: step: 1352/529, loss: 0.06716771423816681
2023-01-23 00:38:28.440254: step: 1356/529, loss: 0.44783973693847656
2023-01-23 00:38:29.638268: step: 1360/529, loss: 0.2566145956516266
2023-01-23 00:38:30.816855: step: 1364/529, loss: 0.14547625184059143
2023-01-23 00:38:32.084473: step: 1368/529, loss: 0.10531790554523468
2023-01-23 00:38:33.297833: step: 1372/529, loss: 0.12327289581298828
2023-01-23 00:38:34.475818: step: 1376/529, loss: 0.0153217613697052
2023-01-23 00:38:35.725831: step: 1380/529, loss: 0.21671715378761292
2023-01-23 00:38:36.932981: step: 1384/529, loss: 0.11157159507274628
2023-01-23 00:38:38.139379: step: 1388/529, loss: 0.42696744203567505
2023-01-23 00:38:39.352688: step: 1392/529, loss: 0.2715120315551758
2023-01-23 00:38:40.601712: step: 1396/529, loss: 0.26450294256210327
2023-01-23 00:38:41.807134: step: 1400/529, loss: 0.6119434833526611
2023-01-23 00:38:43.005637: step: 1404/529, loss: 0.18399199843406677
2023-01-23 00:38:44.199985: step: 1408/529, loss: 0.2501608729362488
2023-01-23 00:38:45.420979: step: 1412/529, loss: 0.4303356111049652
2023-01-23 00:38:46.624157: step: 1416/529, loss: 0.05102033540606499
2023-01-23 00:38:47.854404: step: 1420/529, loss: 0.481133371591568
2023-01-23 00:38:49.028934: step: 1424/529, loss: 0.14962634444236755
2023-01-23 00:38:50.213297: step: 1428/529, loss: 0.03391450643539429
2023-01-23 00:38:51.395737: step: 1432/529, loss: 0.2718815803527832
2023-01-23 00:38:52.635590: step: 1436/529, loss: 0.39867112040519714
2023-01-23 00:38:53.829676: step: 1440/529, loss: 0.22161683440208435
2023-01-23 00:38:55.044923: step: 1444/529, loss: 0.6567305326461792
2023-01-23 00:38:56.239564: step: 1448/529, loss: 0.04203090816736221
2023-01-23 00:38:57.447693: step: 1452/529, loss: 0.08172011375427246
2023-01-23 00:38:58.657117: step: 1456/529, loss: 0.23961743712425232
2023-01-23 00:38:59.875927: step: 1460/529, loss: 0.06445465236902237
2023-01-23 00:39:01.080744: step: 1464/529, loss: 0.07300949096679688
2023-01-23 00:39:02.229067: step: 1468/529, loss: 0.1495160162448883
2023-01-23 00:39:03.468744: step: 1472/529, loss: 0.09207125008106232
2023-01-23 00:39:04.623406: step: 1476/529, loss: 0.3349166512489319
2023-01-23 00:39:05.859969: step: 1480/529, loss: 0.5212050676345825
2023-01-23 00:39:07.049169: step: 1484/529, loss: 0.18425656855106354
2023-01-23 00:39:08.260809: step: 1488/529, loss: 0.48989734053611755
2023-01-23 00:39:09.422586: step: 1492/529, loss: 0.0749574676156044
2023-01-23 00:39:10.595045: step: 1496/529, loss: 0.3424680233001709
2023-01-23 00:39:11.770379: step: 1500/529, loss: 0.18373823165893555
2023-01-23 00:39:12.978687: step: 1504/529, loss: 0.2712888717651367
2023-01-23 00:39:14.171025: step: 1508/529, loss: 0.048180483281612396
2023-01-23 00:39:15.387853: step: 1512/529, loss: 0.06005420535802841
2023-01-23 00:39:16.546172: step: 1516/529, loss: 0.14139194786548615
2023-01-23 00:39:17.798652: step: 1520/529, loss: 0.0999637097120285
2023-01-23 00:39:18.992882: step: 1524/529, loss: 0.06776027381420135
2023-01-23 00:39:20.195755: step: 1528/529, loss: 0.11130230128765106
2023-01-23 00:39:21.377951: step: 1532/529, loss: 0.10155268013477325
2023-01-23 00:39:22.599177: step: 1536/529, loss: 0.530655562877655
2023-01-23 00:39:23.782293: step: 1540/529, loss: 0.03936328738927841
2023-01-23 00:39:24.990023: step: 1544/529, loss: 0.0909823477268219
2023-01-23 00:39:26.189439: step: 1548/529, loss: 0.05777755007147789
2023-01-23 00:39:27.426880: step: 1552/529, loss: 0.13439245522022247
2023-01-23 00:39:28.658529: step: 1556/529, loss: 0.14082685112953186
2023-01-23 00:39:29.833139: step: 1560/529, loss: 0.3213765025138855
2023-01-23 00:39:31.060407: step: 1564/529, loss: 0.06599275767803192
2023-01-23 00:39:32.239987: step: 1568/529, loss: 0.18704243004322052
2023-01-23 00:39:33.403544: step: 1572/529, loss: 0.06092967838048935
2023-01-23 00:39:34.577768: step: 1576/529, loss: 0.14499612152576447
2023-01-23 00:39:35.758477: step: 1580/529, loss: 0.17739105224609375
2023-01-23 00:39:36.920994: step: 1584/529, loss: 0.48578178882598877
2023-01-23 00:39:38.101840: step: 1588/529, loss: 0.06537933647632599
2023-01-23 00:39:39.311467: step: 1592/529, loss: 0.06096382066607475
2023-01-23 00:39:40.520005: step: 1596/529, loss: 0.0891498550772667
2023-01-23 00:39:41.718387: step: 1600/529, loss: 0.3035891652107239
2023-01-23 00:39:42.928522: step: 1604/529, loss: 0.17341357469558716
2023-01-23 00:39:44.138938: step: 1608/529, loss: 0.15328426659107208
2023-01-23 00:39:45.337823: step: 1612/529, loss: 0.10283203423023224
2023-01-23 00:39:46.523781: step: 1616/529, loss: 0.1294664442539215
2023-01-23 00:39:47.685486: step: 1620/529, loss: 0.08666791766881943
2023-01-23 00:39:48.963513: step: 1624/529, loss: 0.18237236142158508
2023-01-23 00:39:50.173226: step: 1628/529, loss: 0.7318611741065979
2023-01-23 00:39:51.358412: step: 1632/529, loss: 0.0477423220872879
2023-01-23 00:39:52.576787: step: 1636/529, loss: 0.16483289003372192
2023-01-23 00:39:53.785098: step: 1640/529, loss: 1.1591278314590454
2023-01-23 00:39:54.987637: step: 1644/529, loss: 0.10539735108613968
2023-01-23 00:39:56.142595: step: 1648/529, loss: 0.4011775255203247
2023-01-23 00:39:57.346190: step: 1652/529, loss: 0.12273788452148438
2023-01-23 00:39:58.554359: step: 1656/529, loss: 0.19339217245578766
2023-01-23 00:39:59.771490: step: 1660/529, loss: 0.06434116512537003
2023-01-23 00:40:01.011715: step: 1664/529, loss: 0.12760713696479797
2023-01-23 00:40:02.245360: step: 1668/529, loss: 0.3298415243625641
2023-01-23 00:40:03.458370: step: 1672/529, loss: 0.26326093077659607
2023-01-23 00:40:04.716194: step: 1676/529, loss: 0.19430240988731384
2023-01-23 00:40:05.911560: step: 1680/529, loss: 0.07733235508203506
2023-01-23 00:40:07.091311: step: 1684/529, loss: 0.08207711577415466
2023-01-23 00:40:08.328265: step: 1688/529, loss: 0.07611904293298721
2023-01-23 00:40:09.522168: step: 1692/529, loss: 0.7262917757034302
2023-01-23 00:40:10.719463: step: 1696/529, loss: 0.38938167691230774
2023-01-23 00:40:11.901648: step: 1700/529, loss: 0.1283935308456421
2023-01-23 00:40:13.052131: step: 1704/529, loss: 0.10140834003686905
2023-01-23 00:40:14.265915: step: 1708/529, loss: 0.20819798111915588
2023-01-23 00:40:15.493678: step: 1712/529, loss: 0.020225979387760162
2023-01-23 00:40:16.715394: step: 1716/529, loss: 0.1567997932434082
2023-01-23 00:40:17.879323: step: 1720/529, loss: 0.15373000502586365
2023-01-23 00:40:19.114546: step: 1724/529, loss: 0.09842424094676971
2023-01-23 00:40:20.308615: step: 1728/529, loss: 0.03168511390686035
2023-01-23 00:40:21.533605: step: 1732/529, loss: 0.04384488984942436
2023-01-23 00:40:22.731392: step: 1736/529, loss: 0.21343976259231567
2023-01-23 00:40:23.917383: step: 1740/529, loss: 0.06888332217931747
2023-01-23 00:40:25.141242: step: 1744/529, loss: 0.0893133133649826
2023-01-23 00:40:26.316394: step: 1748/529, loss: 0.10008268803358078
2023-01-23 00:40:27.528070: step: 1752/529, loss: 0.167872816324234
2023-01-23 00:40:28.738631: step: 1756/529, loss: 0.4022245407104492
2023-01-23 00:40:29.942175: step: 1760/529, loss: 0.04134855419397354
2023-01-23 00:40:31.147754: step: 1764/529, loss: 0.030942248180508614
2023-01-23 00:40:32.317609: step: 1768/529, loss: 0.09721393883228302
2023-01-23 00:40:33.495938: step: 1772/529, loss: 0.03240518644452095
2023-01-23 00:40:34.637760: step: 1776/529, loss: 0.9947913885116577
2023-01-23 00:40:35.869865: step: 1780/529, loss: 0.19643336534500122
2023-01-23 00:40:37.063566: step: 1784/529, loss: 0.01492605172097683
2023-01-23 00:40:38.300123: step: 1788/529, loss: 0.09687414020299911
2023-01-23 00:40:39.529035: step: 1792/529, loss: 0.28758639097213745
2023-01-23 00:40:40.688349: step: 1796/529, loss: 0.22570115327835083
2023-01-23 00:40:41.875844: step: 1800/529, loss: 0.04280395433306694
2023-01-23 00:40:43.051699: step: 1804/529, loss: 0.09879274666309357
2023-01-23 00:40:44.254067: step: 1808/529, loss: 0.6870439052581787
2023-01-23 00:40:45.417398: step: 1812/529, loss: 0.06153907999396324
2023-01-23 00:40:46.652631: step: 1816/529, loss: 0.08938350528478622
2023-01-23 00:40:47.816660: step: 1820/529, loss: 0.10924364626407623
2023-01-23 00:40:49.009745: step: 1824/529, loss: 0.5274261832237244
2023-01-23 00:40:50.208841: step: 1828/529, loss: 0.4776703715324402
2023-01-23 00:40:51.450846: step: 1832/529, loss: 0.019423581659793854
2023-01-23 00:40:52.645044: step: 1836/529, loss: 0.2219340205192566
2023-01-23 00:40:53.827014: step: 1840/529, loss: 0.6077440977096558
2023-01-23 00:40:55.024357: step: 1844/529, loss: 0.25719720125198364
2023-01-23 00:40:56.244334: step: 1848/529, loss: 0.22958669066429138
2023-01-23 00:40:57.466557: step: 1852/529, loss: 0.25654125213623047
2023-01-23 00:40:58.652304: step: 1856/529, loss: 0.05707988515496254
2023-01-23 00:40:59.870434: step: 1860/529, loss: 0.0982334166765213
2023-01-23 00:41:01.054579: step: 1864/529, loss: 0.11462493240833282
2023-01-23 00:41:02.274896: step: 1868/529, loss: 0.2678220868110657
2023-01-23 00:41:03.489376: step: 1872/529, loss: 0.08859243988990784
2023-01-23 00:41:04.717668: step: 1876/529, loss: 0.5402352213859558
2023-01-23 00:41:05.913469: step: 1880/529, loss: 0.06526260077953339
2023-01-23 00:41:07.125156: step: 1884/529, loss: 0.6797018051147461
2023-01-23 00:41:08.337310: step: 1888/529, loss: 0.2423418164253235
2023-01-23 00:41:09.560732: step: 1892/529, loss: 0.1985209584236145
2023-01-23 00:41:10.731911: step: 1896/529, loss: 0.08824422210454941
2023-01-23 00:41:11.924713: step: 1900/529, loss: 0.26627302169799805
2023-01-23 00:41:13.078990: step: 1904/529, loss: 0.1284509301185608
2023-01-23 00:41:14.294642: step: 1908/529, loss: 0.6680278182029724
2023-01-23 00:41:15.508570: step: 1912/529, loss: 0.4039851129055023
2023-01-23 00:41:16.695286: step: 1916/529, loss: 0.08700904995203018
2023-01-23 00:41:17.895230: step: 1920/529, loss: 0.13818468153476715
2023-01-23 00:41:19.098309: step: 1924/529, loss: 0.4956548810005188
2023-01-23 00:41:20.287153: step: 1928/529, loss: 0.6594530940055847
2023-01-23 00:41:21.460061: step: 1932/529, loss: 0.11204744875431061
2023-01-23 00:41:22.655397: step: 1936/529, loss: 0.09674148261547089
2023-01-23 00:41:23.855158: step: 1940/529, loss: 0.16983680427074432
2023-01-23 00:41:25.046967: step: 1944/529, loss: 0.0009875536197796464
2023-01-23 00:41:26.254794: step: 1948/529, loss: 0.1586267054080963
2023-01-23 00:41:27.461427: step: 1952/529, loss: 0.42432236671447754
2023-01-23 00:41:28.628397: step: 1956/529, loss: 0.0937003642320633
2023-01-23 00:41:29.851236: step: 1960/529, loss: 0.14340762794017792
2023-01-23 00:41:31.042421: step: 1964/529, loss: 0.47758838534355164
2023-01-23 00:41:32.289375: step: 1968/529, loss: 0.1976001262664795
2023-01-23 00:41:33.474524: step: 1972/529, loss: 0.046059273183345795
2023-01-23 00:41:34.666744: step: 1976/529, loss: 0.048142239451408386
2023-01-23 00:41:35.920745: step: 1980/529, loss: 0.20206299424171448
2023-01-23 00:41:37.102659: step: 1984/529, loss: 0.07489385455846786
2023-01-23 00:41:38.335946: step: 1988/529, loss: 0.1461162567138672
2023-01-23 00:41:39.545694: step: 1992/529, loss: 1.400456190109253
2023-01-23 00:41:40.738419: step: 1996/529, loss: 0.005507993511855602
2023-01-23 00:41:41.935610: step: 2000/529, loss: 0.21512573957443237
2023-01-23 00:41:43.153124: step: 2004/529, loss: 0.09254741668701172
2023-01-23 00:41:44.370370: step: 2008/529, loss: 0.09168457984924316
2023-01-23 00:41:45.628555: step: 2012/529, loss: 0.0891714096069336
2023-01-23 00:41:46.863088: step: 2016/529, loss: 0.05012502893805504
2023-01-23 00:41:48.135040: step: 2020/529, loss: 0.05382196605205536
2023-01-23 00:41:49.344234: step: 2024/529, loss: 0.29301711916923523
2023-01-23 00:41:50.533446: step: 2028/529, loss: 0.05165357515215874
2023-01-23 00:41:51.719855: step: 2032/529, loss: 0.0846046507358551
2023-01-23 00:41:52.900114: step: 2036/529, loss: 0.18431416153907776
2023-01-23 00:41:54.115352: step: 2040/529, loss: 0.09120287746191025
2023-01-23 00:41:55.347041: step: 2044/529, loss: 0.1373794674873352
2023-01-23 00:41:56.559909: step: 2048/529, loss: 0.17447508871555328
2023-01-23 00:41:57.775520: step: 2052/529, loss: 0.13549461960792542
2023-01-23 00:41:58.963884: step: 2056/529, loss: 0.03647775575518608
2023-01-23 00:42:00.203050: step: 2060/529, loss: 0.08494958281517029
2023-01-23 00:42:01.423910: step: 2064/529, loss: 0.7453889846801758
2023-01-23 00:42:02.643374: step: 2068/529, loss: 0.19579295814037323
2023-01-23 00:42:03.807132: step: 2072/529, loss: 0.1647653877735138
2023-01-23 00:42:04.986344: step: 2076/529, loss: 0.30069634318351746
2023-01-23 00:42:06.179699: step: 2080/529, loss: 0.12725667655467987
2023-01-23 00:42:07.384247: step: 2084/529, loss: 0.11948347091674805
2023-01-23 00:42:08.593099: step: 2088/529, loss: 0.09413222968578339
2023-01-23 00:42:09.801642: step: 2092/529, loss: 0.01352386549115181
2023-01-23 00:42:11.025456: step: 2096/529, loss: 0.08415775746107101
2023-01-23 00:42:12.208336: step: 2100/529, loss: 0.08150902390480042
2023-01-23 00:42:13.433088: step: 2104/529, loss: 0.16767293214797974
2023-01-23 00:42:14.634116: step: 2108/529, loss: 0.907122015953064
2023-01-23 00:42:15.844903: step: 2112/529, loss: 0.07126370072364807
2023-01-23 00:42:17.064424: step: 2116/529, loss: 0.1488230675458908
==================================================
Loss: 0.196
--------------------
Dev: {'event': {'p': 0.564922480620155, 'r': 0.7762982689747004, 'f1': 0.6539540100953449}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6181046676096181, 'r': 0.7855002995805872, 'f1': 0.691820580474934}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.573170731707317, 'r': 0.8703703703703703, 'f1': 0.6911764705882353}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.5223880597014925, 'r': 0.5555555555555556, 'f1': 0.5384615384615385}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.3958333333333333, 'r': 0.5277777777777778, 'f1': 0.45238095238095233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5972944849115505, 'r': 0.7643142476697736, 'f1': 0.6705607476635514}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6162162162162163, 'r': 0.7513481126423007, 'f1': 0.6771058315334773}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 00:43:01.113904: step: 4/529, loss: 0.14414720237255096
2023-01-23 00:43:02.317491: step: 8/529, loss: 0.08610916882753372
2023-01-23 00:43:03.505363: step: 12/529, loss: 0.09214423596858978
2023-01-23 00:43:04.702256: step: 16/529, loss: 0.10569429397583008
2023-01-23 00:43:05.903158: step: 20/529, loss: 0.012187529355287552
2023-01-23 00:43:07.101074: step: 24/529, loss: 0.04768495634198189
2023-01-23 00:43:08.333493: step: 28/529, loss: 0.17110490798950195
2023-01-23 00:43:09.513418: step: 32/529, loss: 0.05441169813275337
2023-01-23 00:43:10.683153: step: 36/529, loss: 0.07184362411499023
2023-01-23 00:43:11.893836: step: 40/529, loss: 0.08034954220056534
2023-01-23 00:43:13.084069: step: 44/529, loss: 0.5869011282920837
2023-01-23 00:43:14.323068: step: 48/529, loss: 0.10149791091680527
2023-01-23 00:43:15.506592: step: 52/529, loss: 0.12109003216028214
2023-01-23 00:43:16.708515: step: 56/529, loss: 0.027198124676942825
2023-01-23 00:43:17.883517: step: 60/529, loss: 0.04667243734002113
2023-01-23 00:43:19.047569: step: 64/529, loss: 0.020627975463867188
2023-01-23 00:43:20.255312: step: 68/529, loss: 0.07522383332252502
2023-01-23 00:43:21.423804: step: 72/529, loss: 0.1055065169930458
2023-01-23 00:43:22.614509: step: 76/529, loss: 0.198052778840065
2023-01-23 00:43:23.781100: step: 80/529, loss: 0.034584809094667435
2023-01-23 00:43:24.981669: step: 84/529, loss: 0.16676485538482666
2023-01-23 00:43:26.197050: step: 88/529, loss: 0.14330492913722992
2023-01-23 00:43:27.456233: step: 92/529, loss: 0.1588471382856369
2023-01-23 00:43:28.636623: step: 96/529, loss: 0.07598753273487091
2023-01-23 00:43:29.830425: step: 100/529, loss: 0.401014119386673
2023-01-23 00:43:30.982381: step: 104/529, loss: 0.22215361893177032
2023-01-23 00:43:32.169080: step: 108/529, loss: 0.06700734794139862
2023-01-23 00:43:33.387518: step: 112/529, loss: 0.2054046094417572
2023-01-23 00:43:34.571247: step: 116/529, loss: 0.11804036796092987
2023-01-23 00:43:35.772983: step: 120/529, loss: 0.09916677325963974
2023-01-23 00:43:36.990721: step: 124/529, loss: 0.04561276361346245
2023-01-23 00:43:38.178166: step: 128/529, loss: 0.08148641884326935
2023-01-23 00:43:39.339156: step: 132/529, loss: 0.03351778909564018
2023-01-23 00:43:40.516354: step: 136/529, loss: 0.04172353446483612
2023-01-23 00:43:41.685858: step: 140/529, loss: 0.01796731911599636
2023-01-23 00:43:42.877230: step: 144/529, loss: 0.09609613567590714
2023-01-23 00:43:44.074419: step: 148/529, loss: 0.06445484608411789
2023-01-23 00:43:45.238317: step: 152/529, loss: 0.0369747169315815
2023-01-23 00:43:46.441915: step: 156/529, loss: 0.016296863555908203
2023-01-23 00:43:47.696303: step: 160/529, loss: 0.0977272093296051
2023-01-23 00:43:48.899587: step: 164/529, loss: 0.04573802649974823
2023-01-23 00:43:50.094313: step: 168/529, loss: 0.22275123000144958
2023-01-23 00:43:51.274791: step: 172/529, loss: 0.10831575095653534
2023-01-23 00:43:52.449959: step: 176/529, loss: 0.17365506291389465
2023-01-23 00:43:53.677013: step: 180/529, loss: 0.4810195863246918
2023-01-23 00:43:54.910384: step: 184/529, loss: 0.0827573835849762
2023-01-23 00:43:56.113826: step: 188/529, loss: 0.1930348426103592
2023-01-23 00:43:57.299537: step: 192/529, loss: 0.025715328752994537
2023-01-23 00:43:58.501297: step: 196/529, loss: 0.09359245747327805
2023-01-23 00:43:59.687535: step: 200/529, loss: 0.020565176382660866
2023-01-23 00:44:00.864761: step: 204/529, loss: 0.025641536340117455
2023-01-23 00:44:02.031208: step: 208/529, loss: 0.18171711266040802
2023-01-23 00:44:03.252545: step: 212/529, loss: 0.0633297935128212
2023-01-23 00:44:04.483814: step: 216/529, loss: 0.354599267244339
2023-01-23 00:44:05.683714: step: 220/529, loss: 0.07756538689136505
2023-01-23 00:44:06.878012: step: 224/529, loss: 0.33542659878730774
2023-01-23 00:44:08.070354: step: 228/529, loss: 0.3240453898906708
2023-01-23 00:44:09.250957: step: 232/529, loss: 0.04538364335894585
2023-01-23 00:44:10.478540: step: 236/529, loss: 0.04080557823181152
2023-01-23 00:44:11.662219: step: 240/529, loss: 0.7638151049613953
2023-01-23 00:44:12.898886: step: 244/529, loss: 0.3556199073791504
2023-01-23 00:44:14.113560: step: 248/529, loss: 0.26836538314819336
2023-01-23 00:44:15.315813: step: 252/529, loss: 0.1899253875017166
2023-01-23 00:44:16.530582: step: 256/529, loss: 0.050566673278808594
2023-01-23 00:44:17.738829: step: 260/529, loss: 0.28201359510421753
2023-01-23 00:44:18.940379: step: 264/529, loss: 0.031092606484889984
2023-01-23 00:44:20.116994: step: 268/529, loss: 0.0398009791970253
2023-01-23 00:44:21.299236: step: 272/529, loss: 0.09260912239551544
2023-01-23 00:44:22.478424: step: 276/529, loss: 0.04423123225569725
2023-01-23 00:44:23.662976: step: 280/529, loss: 0.05221528932452202
2023-01-23 00:44:24.820126: step: 284/529, loss: 0.004040050320327282
2023-01-23 00:44:26.005445: step: 288/529, loss: 0.8165051341056824
2023-01-23 00:44:27.211486: step: 292/529, loss: 0.3493371903896332
2023-01-23 00:44:28.424777: step: 296/529, loss: 0.11197242885828018
2023-01-23 00:44:29.660808: step: 300/529, loss: 0.295889675617218
2023-01-23 00:44:30.877151: step: 304/529, loss: 0.29164400696754456
2023-01-23 00:44:32.043133: step: 308/529, loss: 0.06157274171710014
2023-01-23 00:44:33.241421: step: 312/529, loss: 0.0882442444562912
2023-01-23 00:44:34.457015: step: 316/529, loss: 0.1500554084777832
2023-01-23 00:44:35.642439: step: 320/529, loss: 0.2247953861951828
2023-01-23 00:44:36.852640: step: 324/529, loss: 0.10559125244617462
2023-01-23 00:44:38.066624: step: 328/529, loss: 0.19618292152881622
2023-01-23 00:44:39.273237: step: 332/529, loss: 0.12368012219667435
2023-01-23 00:44:40.439629: step: 336/529, loss: 0.09588590264320374
2023-01-23 00:44:41.647653: step: 340/529, loss: 0.11881313472986221
2023-01-23 00:44:42.876688: step: 344/529, loss: 0.42184609174728394
2023-01-23 00:44:44.070706: step: 348/529, loss: 0.025215625762939453
2023-01-23 00:44:45.311522: step: 352/529, loss: 0.4897242486476898
2023-01-23 00:44:46.529161: step: 356/529, loss: 0.020172975957393646
2023-01-23 00:44:47.733762: step: 360/529, loss: 0.29419660568237305
2023-01-23 00:44:48.949347: step: 364/529, loss: 0.08933086693286896
2023-01-23 00:44:50.129021: step: 368/529, loss: 0.02380390092730522
2023-01-23 00:44:51.311139: step: 372/529, loss: 0.24956035614013672
2023-01-23 00:44:52.515639: step: 376/529, loss: 0.07972851395606995
2023-01-23 00:44:53.745688: step: 380/529, loss: 0.11400480568408966
2023-01-23 00:44:54.984392: step: 384/529, loss: 0.07235798984766006
2023-01-23 00:44:56.141931: step: 388/529, loss: 0.032538414001464844
2023-01-23 00:44:57.372942: step: 392/529, loss: 0.0408930778503418
2023-01-23 00:44:58.616346: step: 396/529, loss: 0.3430141508579254
2023-01-23 00:44:59.807221: step: 400/529, loss: 0.030090905725955963
2023-01-23 00:45:01.035422: step: 404/529, loss: 0.2875344753265381
2023-01-23 00:45:02.246867: step: 408/529, loss: 0.011258221231400967
2023-01-23 00:45:03.397699: step: 412/529, loss: 0.031578682363033295
2023-01-23 00:45:04.579061: step: 416/529, loss: 0.31611311435699463
2023-01-23 00:45:05.792558: step: 420/529, loss: 0.05510731041431427
2023-01-23 00:45:06.973691: step: 424/529, loss: 0.07624687999486923
2023-01-23 00:45:08.190454: step: 428/529, loss: 0.06054506450891495
2023-01-23 00:45:09.394221: step: 432/529, loss: 0.03580637276172638
2023-01-23 00:45:10.555624: step: 436/529, loss: 0.20370140671730042
2023-01-23 00:45:11.781861: step: 440/529, loss: 0.08785905689001083
2023-01-23 00:45:12.985481: step: 444/529, loss: 0.056346990168094635
2023-01-23 00:45:14.167764: step: 448/529, loss: 0.06762728840112686
2023-01-23 00:45:15.336297: step: 452/529, loss: 0.00726971635594964
2023-01-23 00:45:16.509873: step: 456/529, loss: 0.06746310740709305
2023-01-23 00:45:17.741517: step: 460/529, loss: 0.13362936675548553
2023-01-23 00:45:18.945673: step: 464/529, loss: 0.025434209033846855
2023-01-23 00:45:20.119898: step: 468/529, loss: 0.06456603854894638
2023-01-23 00:45:21.369764: step: 472/529, loss: 0.08219128102064133
2023-01-23 00:45:22.550165: step: 476/529, loss: 0.3151577413082123
2023-01-23 00:45:23.774612: step: 480/529, loss: 0.06379556655883789
2023-01-23 00:45:24.961614: step: 484/529, loss: 0.027253054082393646
2023-01-23 00:45:26.190085: step: 488/529, loss: 0.04433002322912216
2023-01-23 00:45:27.370894: step: 492/529, loss: 0.1069088950753212
2023-01-23 00:45:28.578682: step: 496/529, loss: 0.13772830367088318
2023-01-23 00:45:29.746422: step: 500/529, loss: 0.058483317494392395
2023-01-23 00:45:31.003173: step: 504/529, loss: 1.2549943923950195
2023-01-23 00:45:32.159207: step: 508/529, loss: 0.07459201663732529
2023-01-23 00:45:33.371759: step: 512/529, loss: 0.2625943124294281
2023-01-23 00:45:34.567227: step: 516/529, loss: 1.8364765644073486
2023-01-23 00:45:35.741936: step: 520/529, loss: 0.39650508761405945
2023-01-23 00:45:36.954504: step: 524/529, loss: 0.5529074668884277
2023-01-23 00:45:38.094919: step: 528/529, loss: 0.04726262390613556
2023-01-23 00:45:39.301266: step: 532/529, loss: 0.07336633652448654
2023-01-23 00:45:40.510231: step: 536/529, loss: 0.37702199816703796
2023-01-23 00:45:41.722930: step: 540/529, loss: 0.12614865601062775
2023-01-23 00:45:42.917649: step: 544/529, loss: 0.18821199238300323
2023-01-23 00:45:44.174408: step: 548/529, loss: 0.02433795854449272
2023-01-23 00:45:45.377007: step: 552/529, loss: 0.05870981514453888
2023-01-23 00:45:46.573933: step: 556/529, loss: 0.3052510619163513
2023-01-23 00:45:47.769826: step: 560/529, loss: 0.10687504708766937
2023-01-23 00:45:49.005831: step: 564/529, loss: 0.1900564730167389
2023-01-23 00:45:50.196087: step: 568/529, loss: 0.062425900250673294
2023-01-23 00:45:51.392026: step: 572/529, loss: 0.04736023396253586
2023-01-23 00:45:52.590330: step: 576/529, loss: 0.0904124304652214
2023-01-23 00:45:53.778481: step: 580/529, loss: 0.18770459294319153
2023-01-23 00:45:54.966705: step: 584/529, loss: 0.056600190699100494
2023-01-23 00:45:56.177193: step: 588/529, loss: 0.09418735653162003
2023-01-23 00:45:57.389977: step: 592/529, loss: 0.5272855162620544
2023-01-23 00:45:58.563912: step: 596/529, loss: 0.10469424724578857
2023-01-23 00:45:59.771742: step: 600/529, loss: 0.01532745361328125
2023-01-23 00:46:00.950336: step: 604/529, loss: 0.05669808387756348
2023-01-23 00:46:02.151230: step: 608/529, loss: 0.055425144731998444
2023-01-23 00:46:03.337584: step: 612/529, loss: 0.008281421847641468
2023-01-23 00:46:04.568818: step: 616/529, loss: 0.05983608216047287
2023-01-23 00:46:05.793379: step: 620/529, loss: 0.11513213813304901
2023-01-23 00:46:06.971890: step: 624/529, loss: 0.0886169895529747
2023-01-23 00:46:08.132765: step: 628/529, loss: 0.0753655880689621
2023-01-23 00:46:09.364932: step: 632/529, loss: 0.21485203504562378
2023-01-23 00:46:10.589715: step: 636/529, loss: 0.33699098229408264
2023-01-23 00:46:11.828554: step: 640/529, loss: 0.15715599060058594
2023-01-23 00:46:13.074040: step: 644/529, loss: 0.14431075751781464
2023-01-23 00:46:14.274765: step: 648/529, loss: 0.15808573365211487
2023-01-23 00:46:15.485777: step: 652/529, loss: 0.2170001119375229
2023-01-23 00:46:16.657363: step: 656/529, loss: 0.07208108901977539
2023-01-23 00:46:17.845978: step: 660/529, loss: 0.08158054202795029
2023-01-23 00:46:19.097332: step: 664/529, loss: 0.18894919753074646
2023-01-23 00:46:20.283922: step: 668/529, loss: 0.5570565462112427
2023-01-23 00:46:21.511110: step: 672/529, loss: 0.1003580093383789
2023-01-23 00:46:22.693547: step: 676/529, loss: 0.04667682945728302
2023-01-23 00:46:23.935711: step: 680/529, loss: 0.05080671235918999
2023-01-23 00:46:25.119429: step: 684/529, loss: 0.1406419277191162
2023-01-23 00:46:26.311866: step: 688/529, loss: 0.05003051832318306
2023-01-23 00:46:27.530527: step: 692/529, loss: 0.1397019922733307
2023-01-23 00:46:28.739387: step: 696/529, loss: 0.22290164232254028
2023-01-23 00:46:29.946906: step: 700/529, loss: 0.5983518958091736
2023-01-23 00:46:31.146268: step: 704/529, loss: 0.038890838623046875
2023-01-23 00:46:32.355572: step: 708/529, loss: 0.060469530522823334
2023-01-23 00:46:33.509321: step: 712/529, loss: 0.07994937896728516
2023-01-23 00:46:34.710856: step: 716/529, loss: 0.09934130311012268
2023-01-23 00:46:35.908388: step: 720/529, loss: 0.11925573647022247
2023-01-23 00:46:37.137108: step: 724/529, loss: 0.10380133986473083
2023-01-23 00:46:38.314695: step: 728/529, loss: 0.1414201706647873
2023-01-23 00:46:39.548775: step: 732/529, loss: 0.10719519108533859
2023-01-23 00:46:40.694271: step: 736/529, loss: 0.08757490664720535
2023-01-23 00:46:41.905472: step: 740/529, loss: 0.23866048455238342
2023-01-23 00:46:43.137286: step: 744/529, loss: 0.7229957580566406
2023-01-23 00:46:44.380148: step: 748/529, loss: 0.025325536727905273
2023-01-23 00:46:45.568402: step: 752/529, loss: 0.1644696742296219
2023-01-23 00:46:46.798362: step: 756/529, loss: 0.4008598327636719
2023-01-23 00:46:48.012341: step: 760/529, loss: 0.019062042236328125
2023-01-23 00:46:49.203860: step: 764/529, loss: 0.7790459990501404
2023-01-23 00:46:50.412076: step: 768/529, loss: 0.06344500184059143
2023-01-23 00:46:51.669743: step: 772/529, loss: 0.09370222687721252
2023-01-23 00:46:52.876622: step: 776/529, loss: 0.0684460699558258
2023-01-23 00:46:54.064760: step: 780/529, loss: 0.09711484611034393
2023-01-23 00:46:55.267436: step: 784/529, loss: 0.01529760379344225
2023-01-23 00:46:56.461597: step: 788/529, loss: 0.36080384254455566
2023-01-23 00:46:57.694969: step: 792/529, loss: 0.08460836112499237
2023-01-23 00:46:58.874169: step: 796/529, loss: 0.17579208314418793
2023-01-23 00:47:00.078017: step: 800/529, loss: 0.18806973099708557
2023-01-23 00:47:01.268813: step: 804/529, loss: 0.03975820541381836
2023-01-23 00:47:02.479532: step: 808/529, loss: 0.006653547286987305
2023-01-23 00:47:03.687712: step: 812/529, loss: 0.07395439594984055
2023-01-23 00:47:04.855112: step: 816/529, loss: 0.046633053570985794
2023-01-23 00:47:06.042514: step: 820/529, loss: 0.29164236783981323
2023-01-23 00:47:07.300053: step: 824/529, loss: 0.05899238586425781
2023-01-23 00:47:08.498540: step: 828/529, loss: 0.36911869049072266
2023-01-23 00:47:09.728368: step: 832/529, loss: 0.06191730499267578
2023-01-23 00:47:10.992048: step: 836/529, loss: 0.11162882298231125
2023-01-23 00:47:12.215825: step: 840/529, loss: 0.6514137983322144
2023-01-23 00:47:13.407445: step: 844/529, loss: 0.12691307067871094
2023-01-23 00:47:14.601113: step: 848/529, loss: 0.6717785596847534
2023-01-23 00:47:15.753560: step: 852/529, loss: 0.15295261144638062
2023-01-23 00:47:16.997761: step: 856/529, loss: 0.05758490785956383
2023-01-23 00:47:18.205969: step: 860/529, loss: 0.02046995237469673
2023-01-23 00:47:19.405742: step: 864/529, loss: 0.05305027961730957
2023-01-23 00:47:20.565759: step: 868/529, loss: 0.05044245719909668
2023-01-23 00:47:21.784230: step: 872/529, loss: 0.2777186632156372
2023-01-23 00:47:22.975400: step: 876/529, loss: 0.2014492005109787
2023-01-23 00:47:24.163885: step: 880/529, loss: 0.41537055373191833
2023-01-23 00:47:25.375220: step: 884/529, loss: 0.14407005906105042
2023-01-23 00:47:26.595718: step: 888/529, loss: 0.03330142796039581
2023-01-23 00:47:27.801717: step: 892/529, loss: 0.09800411015748978
2023-01-23 00:47:28.999998: step: 896/529, loss: 0.09380187839269638
2023-01-23 00:47:30.188796: step: 900/529, loss: 0.2185775637626648
2023-01-23 00:47:31.378188: step: 904/529, loss: 0.05491933599114418
2023-01-23 00:47:32.584199: step: 908/529, loss: 0.06201772764325142
2023-01-23 00:47:33.741200: step: 912/529, loss: 0.19165100157260895
2023-01-23 00:47:34.962517: step: 916/529, loss: 0.042129408568143845
2023-01-23 00:47:36.128370: step: 920/529, loss: 0.04134722054004669
2023-01-23 00:47:37.325222: step: 924/529, loss: 0.5099632143974304
2023-01-23 00:47:38.548475: step: 928/529, loss: 0.12240594625473022
2023-01-23 00:47:39.721182: step: 932/529, loss: 0.08612065017223358
2023-01-23 00:47:40.886153: step: 936/529, loss: 0.06671981513500214
2023-01-23 00:47:42.085250: step: 940/529, loss: 0.20419836044311523
2023-01-23 00:47:43.287288: step: 944/529, loss: 0.08661937713623047
2023-01-23 00:47:44.479135: step: 948/529, loss: 0.15728655457496643
2023-01-23 00:47:45.697629: step: 952/529, loss: 0.09781036525964737
2023-01-23 00:47:46.893656: step: 956/529, loss: 0.07027482986450195
2023-01-23 00:47:48.084564: step: 960/529, loss: 0.06562285125255585
2023-01-23 00:47:49.294415: step: 964/529, loss: 0.15864458680152893
2023-01-23 00:47:50.491254: step: 968/529, loss: 0.17225085198879242
2023-01-23 00:47:51.711616: step: 972/529, loss: 0.010514688678085804
2023-01-23 00:47:52.951768: step: 976/529, loss: 0.21594390273094177
2023-01-23 00:47:54.110807: step: 980/529, loss: 0.08297464996576309
2023-01-23 00:47:55.347856: step: 984/529, loss: 0.07915416359901428
2023-01-23 00:47:56.528058: step: 988/529, loss: 0.10100136697292328
2023-01-23 00:47:57.746254: step: 992/529, loss: 0.16859151422977448
2023-01-23 00:47:58.970570: step: 996/529, loss: 0.38472771644592285
2023-01-23 00:48:00.199669: step: 1000/529, loss: 0.3493598997592926
2023-01-23 00:48:01.461655: step: 1004/529, loss: 0.2528516948223114
2023-01-23 00:48:02.780997: step: 1008/529, loss: 0.08789043128490448
2023-01-23 00:48:03.984185: step: 1012/529, loss: 0.131754070520401
2023-01-23 00:48:05.219584: step: 1016/529, loss: 0.372668594121933
2023-01-23 00:48:06.391416: step: 1020/529, loss: 0.09886160492897034
2023-01-23 00:48:07.698930: step: 1024/529, loss: 0.2696099281311035
2023-01-23 00:48:08.893756: step: 1028/529, loss: 0.0637538880109787
2023-01-23 00:48:10.097807: step: 1032/529, loss: 0.05749655142426491
2023-01-23 00:48:11.257449: step: 1036/529, loss: 0.09321737289428711
2023-01-23 00:48:12.449708: step: 1040/529, loss: 0.12446780502796173
2023-01-23 00:48:13.639235: step: 1044/529, loss: 0.026815414428710938
2023-01-23 00:48:14.818712: step: 1048/529, loss: 0.01471786480396986
2023-01-23 00:48:15.995210: step: 1052/529, loss: 0.051738835871219635
2023-01-23 00:48:17.223896: step: 1056/529, loss: 0.3338344395160675
2023-01-23 00:48:18.438462: step: 1060/529, loss: 0.1210559606552124
2023-01-23 00:48:19.660581: step: 1064/529, loss: 0.04723243787884712
2023-01-23 00:48:20.832740: step: 1068/529, loss: 0.10160288959741592
2023-01-23 00:48:22.013299: step: 1072/529, loss: 0.1779688000679016
2023-01-23 00:48:23.206836: step: 1076/529, loss: 0.0451601967215538
2023-01-23 00:48:24.427543: step: 1080/529, loss: 0.18579836189746857
2023-01-23 00:48:25.602719: step: 1084/529, loss: 0.1562459021806717
2023-01-23 00:48:26.778097: step: 1088/529, loss: 0.10708599537611008
2023-01-23 00:48:27.964918: step: 1092/529, loss: 0.06045665964484215
2023-01-23 00:48:29.177127: step: 1096/529, loss: 0.04016532748937607
2023-01-23 00:48:30.360825: step: 1100/529, loss: 0.02961740642786026
2023-01-23 00:48:31.564574: step: 1104/529, loss: 0.13050255179405212
2023-01-23 00:48:32.793658: step: 1108/529, loss: 0.11328859627246857
2023-01-23 00:48:34.006085: step: 1112/529, loss: 0.2272767424583435
2023-01-23 00:48:35.205715: step: 1116/529, loss: 0.2151515930891037
2023-01-23 00:48:36.458791: step: 1120/529, loss: 0.20970459282398224
2023-01-23 00:48:37.665771: step: 1124/529, loss: 0.27438580989837646
2023-01-23 00:48:38.883786: step: 1128/529, loss: 0.0640861839056015
2023-01-23 00:48:40.099680: step: 1132/529, loss: 0.025502096861600876
2023-01-23 00:48:41.323941: step: 1136/529, loss: 0.07590790092945099
2023-01-23 00:48:42.539931: step: 1140/529, loss: 0.1393032968044281
2023-01-23 00:48:43.787830: step: 1144/529, loss: 0.3347460627555847
2023-01-23 00:48:44.946907: step: 1148/529, loss: 0.10406798869371414
2023-01-23 00:48:46.117362: step: 1152/529, loss: 1.4244558811187744
2023-01-23 00:48:47.306840: step: 1156/529, loss: 0.10619769245386124
2023-01-23 00:48:48.488857: step: 1160/529, loss: 0.09533052146434784
2023-01-23 00:48:49.663308: step: 1164/529, loss: 0.12391719967126846
2023-01-23 00:48:50.882095: step: 1168/529, loss: 0.10453243553638458
2023-01-23 00:48:52.088740: step: 1172/529, loss: 0.4716840982437134
2023-01-23 00:48:53.267708: step: 1176/529, loss: 0.08279738575220108
2023-01-23 00:48:54.453117: step: 1180/529, loss: 0.01758880726993084
2023-01-23 00:48:55.649668: step: 1184/529, loss: 0.03442859649658203
2023-01-23 00:48:56.827885: step: 1188/529, loss: 0.10302762687206268
2023-01-23 00:48:58.037498: step: 1192/529, loss: 0.055144499987363815
2023-01-23 00:48:59.234597: step: 1196/529, loss: 0.17081815004348755
2023-01-23 00:49:00.453542: step: 1200/529, loss: 0.0809200331568718
2023-01-23 00:49:01.630003: step: 1204/529, loss: 0.06702928245067596
2023-01-23 00:49:02.805665: step: 1208/529, loss: 0.04754498228430748
2023-01-23 00:49:04.042519: step: 1212/529, loss: 0.2841157913208008
2023-01-23 00:49:05.244703: step: 1216/529, loss: 0.5948737859725952
2023-01-23 00:49:06.432997: step: 1220/529, loss: 0.12462782859802246
2023-01-23 00:49:07.617582: step: 1224/529, loss: 0.09428625553846359
2023-01-23 00:49:08.840149: step: 1228/529, loss: 0.12613964080810547
2023-01-23 00:49:10.044439: step: 1232/529, loss: 0.04598255455493927
2023-01-23 00:49:11.241859: step: 1236/529, loss: 0.0697137862443924
2023-01-23 00:49:12.460696: step: 1240/529, loss: 0.10657081753015518
2023-01-23 00:49:13.690472: step: 1244/529, loss: 0.37994813919067383
2023-01-23 00:49:14.903918: step: 1248/529, loss: 0.45272141695022583
2023-01-23 00:49:16.072094: step: 1252/529, loss: 0.07155018299818039
2023-01-23 00:49:17.277128: step: 1256/529, loss: 0.1282035857439041
2023-01-23 00:49:18.445466: step: 1260/529, loss: 0.15995995700359344
2023-01-23 00:49:19.620124: step: 1264/529, loss: 0.34280338883399963
2023-01-23 00:49:20.814529: step: 1268/529, loss: 0.021961044520139694
2023-01-23 00:49:22.002754: step: 1272/529, loss: 0.041260723024606705
2023-01-23 00:49:23.171385: step: 1276/529, loss: 0.10261498391628265
2023-01-23 00:49:24.361690: step: 1280/529, loss: 0.10749664157629013
2023-01-23 00:49:25.604179: step: 1284/529, loss: 0.3650610148906708
2023-01-23 00:49:26.872500: step: 1288/529, loss: 0.12068872153759003
2023-01-23 00:49:28.055990: step: 1292/529, loss: 0.1430201530456543
2023-01-23 00:49:29.282539: step: 1296/529, loss: 1.3118350505828857
2023-01-23 00:49:30.476383: step: 1300/529, loss: 0.012200355529785156
2023-01-23 00:49:31.682500: step: 1304/529, loss: 0.057032011449337006
2023-01-23 00:49:32.898058: step: 1308/529, loss: 0.1295982301235199
2023-01-23 00:49:34.088906: step: 1312/529, loss: 0.07049560546875
2023-01-23 00:49:35.276155: step: 1316/529, loss: 0.04867897182703018
2023-01-23 00:49:36.462055: step: 1320/529, loss: 0.1340874582529068
2023-01-23 00:49:37.621987: step: 1324/529, loss: 0.021107196807861328
2023-01-23 00:49:38.804284: step: 1328/529, loss: 0.008972419425845146
2023-01-23 00:49:40.024141: step: 1332/529, loss: 0.11829090118408203
2023-01-23 00:49:41.249628: step: 1336/529, loss: 0.06536245346069336
2023-01-23 00:49:42.521026: step: 1340/529, loss: 0.04923496022820473
2023-01-23 00:49:43.759999: step: 1344/529, loss: 0.34935712814331055
2023-01-23 00:49:44.980595: step: 1348/529, loss: 0.027606630697846413
2023-01-23 00:49:46.175183: step: 1352/529, loss: 1.0833959579467773
2023-01-23 00:49:47.357001: step: 1356/529, loss: 0.017308330163359642
2023-01-23 00:49:48.514946: step: 1360/529, loss: 0.3455123007297516
2023-01-23 00:49:49.760623: step: 1364/529, loss: 0.037766262888908386
2023-01-23 00:49:50.976030: step: 1368/529, loss: 0.11279010772705078
2023-01-23 00:49:52.193993: step: 1372/529, loss: 0.022310638800263405
2023-01-23 00:49:53.383106: step: 1376/529, loss: 0.0952509418129921
2023-01-23 00:49:54.564228: step: 1380/529, loss: 0.11090002208948135
2023-01-23 00:49:55.741732: step: 1384/529, loss: 0.08343953639268875
2023-01-23 00:49:56.963769: step: 1388/529, loss: 0.04089689254760742
2023-01-23 00:49:58.136515: step: 1392/529, loss: 0.30994436144828796
2023-01-23 00:49:59.345561: step: 1396/529, loss: 0.11132745444774628
2023-01-23 00:50:00.523205: step: 1400/529, loss: 0.05379399657249451
2023-01-23 00:50:01.745379: step: 1404/529, loss: 0.11103429645299911
2023-01-23 00:50:03.002406: step: 1408/529, loss: 0.09269294887781143
2023-01-23 00:50:04.229115: step: 1412/529, loss: 0.03979680687189102
2023-01-23 00:50:05.418896: step: 1416/529, loss: 0.12062730640172958
2023-01-23 00:50:06.646601: step: 1420/529, loss: 0.3484598696231842
2023-01-23 00:50:07.823325: step: 1424/529, loss: 0.06316041946411133
2023-01-23 00:50:09.055891: step: 1428/529, loss: 0.12038116157054901
2023-01-23 00:50:10.260363: step: 1432/529, loss: 0.050589751452207565
2023-01-23 00:50:11.478653: step: 1436/529, loss: 0.12125988304615021
2023-01-23 00:50:12.677226: step: 1440/529, loss: 0.20059843361377716
2023-01-23 00:50:13.887287: step: 1444/529, loss: 0.019537828862667084
2023-01-23 00:50:15.111483: step: 1448/529, loss: 0.14411191642284393
2023-01-23 00:50:16.380534: step: 1452/529, loss: 0.04714317247271538
2023-01-23 00:50:17.595748: step: 1456/529, loss: 0.3148542642593384
2023-01-23 00:50:18.776591: step: 1460/529, loss: 0.24474793672561646
2023-01-23 00:50:19.952380: step: 1464/529, loss: 0.05517106130719185
2023-01-23 00:50:21.144863: step: 1468/529, loss: 0.225184828042984
2023-01-23 00:50:22.309192: step: 1472/529, loss: 0.06958065181970596
2023-01-23 00:50:23.494171: step: 1476/529, loss: 0.1354474127292633
2023-01-23 00:50:24.685375: step: 1480/529, loss: 0.02657771110534668
2023-01-23 00:50:25.896772: step: 1484/529, loss: 0.09428386390209198
2023-01-23 00:50:27.117593: step: 1488/529, loss: 0.19674520194530487
2023-01-23 00:50:28.329310: step: 1492/529, loss: 0.11501121520996094
2023-01-23 00:50:29.504284: step: 1496/529, loss: 0.19871121644973755
2023-01-23 00:50:30.736287: step: 1500/529, loss: 0.4033264219760895
2023-01-23 00:50:31.940735: step: 1504/529, loss: 0.12177863717079163
2023-01-23 00:50:33.148232: step: 1508/529, loss: 0.08350207656621933
2023-01-23 00:50:34.338537: step: 1512/529, loss: 0.019609831273555756
2023-01-23 00:50:35.516663: step: 1516/529, loss: 0.3669924736022949
2023-01-23 00:50:36.723196: step: 1520/529, loss: 0.03388643264770508
2023-01-23 00:50:37.912480: step: 1524/529, loss: 0.18395265936851501
2023-01-23 00:50:39.130002: step: 1528/529, loss: 0.1612405776977539
2023-01-23 00:50:40.324893: step: 1532/529, loss: 0.13534298539161682
2023-01-23 00:50:41.517210: step: 1536/529, loss: 0.07960841804742813
2023-01-23 00:50:42.703578: step: 1540/529, loss: 0.12602612376213074
2023-01-23 00:50:43.919893: step: 1544/529, loss: 0.0558650977909565
2023-01-23 00:50:45.100921: step: 1548/529, loss: 0.03162384033203125
2023-01-23 00:50:46.329456: step: 1552/529, loss: 0.3522595465183258
2023-01-23 00:50:47.516473: step: 1556/529, loss: 0.2920095920562744
2023-01-23 00:50:48.711666: step: 1560/529, loss: 0.12839755415916443
2023-01-23 00:50:49.904254: step: 1564/529, loss: 0.04806976392865181
2023-01-23 00:50:51.073263: step: 1568/529, loss: 0.0692567378282547
2023-01-23 00:50:52.278161: step: 1572/529, loss: 0.10409679263830185
2023-01-23 00:50:53.470055: step: 1576/529, loss: 0.06270952522754669
2023-01-23 00:50:54.634408: step: 1580/529, loss: 0.11875371634960175
2023-01-23 00:50:55.837472: step: 1584/529, loss: 0.05838203802704811
2023-01-23 00:50:57.035194: step: 1588/529, loss: 0.06086568534374237
2023-01-23 00:50:58.240430: step: 1592/529, loss: 0.14741821587085724
2023-01-23 00:50:59.464675: step: 1596/529, loss: 0.10667534172534943
2023-01-23 00:51:00.652486: step: 1600/529, loss: 0.08822593837976456
2023-01-23 00:51:01.887609: step: 1604/529, loss: 0.05639181286096573
2023-01-23 00:51:03.111214: step: 1608/529, loss: 0.17751845717430115
2023-01-23 00:51:04.303294: step: 1612/529, loss: 0.02821202203631401
2023-01-23 00:51:05.588714: step: 1616/529, loss: 0.17321842908859253
2023-01-23 00:51:06.845387: step: 1620/529, loss: 0.19982223212718964
2023-01-23 00:51:08.064427: step: 1624/529, loss: 0.08125362545251846
2023-01-23 00:51:09.254440: step: 1628/529, loss: 0.02132434770464897
2023-01-23 00:51:10.430025: step: 1632/529, loss: 0.26734429597854614
2023-01-23 00:51:11.595078: step: 1636/529, loss: 0.06552913039922714
2023-01-23 00:51:12.770539: step: 1640/529, loss: 0.0243743434548378
2023-01-23 00:51:13.961849: step: 1644/529, loss: 0.03976898267865181
2023-01-23 00:51:15.154591: step: 1648/529, loss: 0.07415466755628586
2023-01-23 00:51:16.377414: step: 1652/529, loss: 0.15793848037719727
2023-01-23 00:51:17.593068: step: 1656/529, loss: 0.20690852403640747
2023-01-23 00:51:18.789823: step: 1660/529, loss: 0.05217461660504341
2023-01-23 00:51:19.988294: step: 1664/529, loss: 0.0488986037671566
2023-01-23 00:51:21.189972: step: 1668/529, loss: 0.3758572041988373
2023-01-23 00:51:22.368414: step: 1672/529, loss: 0.1287458837032318
2023-01-23 00:51:23.572332: step: 1676/529, loss: 0.03412642702460289
2023-01-23 00:51:24.760321: step: 1680/529, loss: 0.017566537484526634
2023-01-23 00:51:25.962485: step: 1684/529, loss: 0.22134742140769958
2023-01-23 00:51:27.166273: step: 1688/529, loss: 0.1414697766304016
2023-01-23 00:51:28.396746: step: 1692/529, loss: 0.1128886267542839
2023-01-23 00:51:29.579187: step: 1696/529, loss: 0.2069406658411026
2023-01-23 00:51:30.761028: step: 1700/529, loss: 0.07560800760984421
2023-01-23 00:51:31.966504: step: 1704/529, loss: 0.07611308246850967
2023-01-23 00:51:33.140711: step: 1708/529, loss: 0.07005896419286728
2023-01-23 00:51:34.375262: step: 1712/529, loss: 0.17178316414356232
2023-01-23 00:51:35.625174: step: 1716/529, loss: 0.05612926557660103
2023-01-23 00:51:36.859177: step: 1720/529, loss: 0.04977273941040039
2023-01-23 00:51:38.061613: step: 1724/529, loss: 0.15518073737621307
2023-01-23 00:51:39.258230: step: 1728/529, loss: 0.04040198028087616
2023-01-23 00:51:40.438783: step: 1732/529, loss: 0.08940983563661575
2023-01-23 00:51:41.609195: step: 1736/529, loss: 0.05588426813483238
2023-01-23 00:51:42.791482: step: 1740/529, loss: 0.024835502728819847
2023-01-23 00:51:43.983638: step: 1744/529, loss: 0.6345804333686829
2023-01-23 00:51:45.176978: step: 1748/529, loss: 0.47183215618133545
2023-01-23 00:51:46.394334: step: 1752/529, loss: 0.1791291981935501
2023-01-23 00:51:47.604267: step: 1756/529, loss: 0.037714697420597076
2023-01-23 00:51:48.825391: step: 1760/529, loss: 0.06665611267089844
2023-01-23 00:51:50.020417: step: 1764/529, loss: 0.6147672533988953
2023-01-23 00:51:51.232383: step: 1768/529, loss: 0.11704973876476288
2023-01-23 00:51:52.416601: step: 1772/529, loss: 0.04602517932653427
2023-01-23 00:51:53.619634: step: 1776/529, loss: 0.1902427077293396
2023-01-23 00:51:54.784519: step: 1780/529, loss: 0.08552742004394531
2023-01-23 00:51:55.968747: step: 1784/529, loss: 0.2217470109462738
2023-01-23 00:51:57.145950: step: 1788/529, loss: 0.1756361871957779
2023-01-23 00:51:58.354805: step: 1792/529, loss: 0.00928716640919447
2023-01-23 00:51:59.584709: step: 1796/529, loss: 0.07677898555994034
2023-01-23 00:52:00.770591: step: 1800/529, loss: 0.15860281884670258
2023-01-23 00:52:01.943647: step: 1804/529, loss: 0.1334318220615387
2023-01-23 00:52:03.164159: step: 1808/529, loss: 0.007172394078224897
2023-01-23 00:52:04.335514: step: 1812/529, loss: 0.022566795349121094
2023-01-23 00:52:05.541710: step: 1816/529, loss: 0.11337108910083771
2023-01-23 00:52:06.751868: step: 1820/529, loss: 0.05176963657140732
2023-01-23 00:52:07.919093: step: 1824/529, loss: 0.09789667278528214
2023-01-23 00:52:09.099613: step: 1828/529, loss: 0.20572558045387268
2023-01-23 00:52:10.318100: step: 1832/529, loss: 0.06294755637645721
2023-01-23 00:52:11.515544: step: 1836/529, loss: 0.08909421414136887
2023-01-23 00:52:12.703028: step: 1840/529, loss: 0.08354387432336807
2023-01-23 00:52:13.914036: step: 1844/529, loss: 0.072461798787117
2023-01-23 00:52:15.102350: step: 1848/529, loss: 0.13327093422412872
2023-01-23 00:52:16.298497: step: 1852/529, loss: 0.08729010075330734
2023-01-23 00:52:17.485929: step: 1856/529, loss: 0.09080667048692703
2023-01-23 00:52:18.745386: step: 1860/529, loss: 0.16696929931640625
2023-01-23 00:52:19.931781: step: 1864/529, loss: 0.16344699263572693
2023-01-23 00:52:21.123655: step: 1868/529, loss: 0.056607436388731
2023-01-23 00:52:22.342798: step: 1872/529, loss: 0.20858383178710938
2023-01-23 00:52:23.574156: step: 1876/529, loss: 0.15799474716186523
2023-01-23 00:52:24.773286: step: 1880/529, loss: 0.10217438638210297
2023-01-23 00:52:25.974199: step: 1884/529, loss: 0.024437617510557175
2023-01-23 00:52:27.213759: step: 1888/529, loss: 0.05741949379444122
2023-01-23 00:52:28.398262: step: 1892/529, loss: 0.09978371113538742
2023-01-23 00:52:29.600401: step: 1896/529, loss: 0.07088422775268555
2023-01-23 00:52:30.813572: step: 1900/529, loss: 0.7726289629936218
2023-01-23 00:52:32.030561: step: 1904/529, loss: 0.05080311372876167
2023-01-23 00:52:33.228842: step: 1908/529, loss: 0.19627884030342102
2023-01-23 00:52:34.453166: step: 1912/529, loss: 0.4477725923061371
2023-01-23 00:52:35.650177: step: 1916/529, loss: 0.5173094868659973
2023-01-23 00:52:36.852725: step: 1920/529, loss: 0.1326911896467209
2023-01-23 00:52:38.065789: step: 1924/529, loss: 0.2749665081501007
2023-01-23 00:52:39.251702: step: 1928/529, loss: 0.07716703414916992
2023-01-23 00:52:40.432070: step: 1932/529, loss: 0.19308114051818848
2023-01-23 00:52:41.626278: step: 1936/529, loss: 0.15743032097816467
2023-01-23 00:52:42.848074: step: 1940/529, loss: 0.23950806260108948
2023-01-23 00:52:44.024637: step: 1944/529, loss: 0.08223400264978409
2023-01-23 00:52:45.230299: step: 1948/529, loss: 0.0815381109714508
2023-01-23 00:52:46.409938: step: 1952/529, loss: 0.2271292805671692
2023-01-23 00:52:47.652186: step: 1956/529, loss: 0.030028581619262695
2023-01-23 00:52:48.824581: step: 1960/529, loss: 0.005736017599701881
2023-01-23 00:52:50.027830: step: 1964/529, loss: 0.12222181260585785
2023-01-23 00:52:51.189341: step: 1968/529, loss: 0.096971794962883
2023-01-23 00:52:52.350676: step: 1972/529, loss: 0.0944160521030426
2023-01-23 00:52:53.537420: step: 1976/529, loss: 0.18898820877075195
2023-01-23 00:52:54.732565: step: 1980/529, loss: 0.09631462395191193
2023-01-23 00:52:55.931732: step: 1984/529, loss: 0.07906635105609894
2023-01-23 00:52:57.089713: step: 1988/529, loss: 0.4967004358768463
2023-01-23 00:52:58.273845: step: 1992/529, loss: 0.04845285415649414
2023-01-23 00:52:59.463328: step: 1996/529, loss: 0.052182961255311966
2023-01-23 00:53:00.669954: step: 2000/529, loss: 0.419796347618103
2023-01-23 00:53:01.887359: step: 2004/529, loss: 0.10645198822021484
2023-01-23 00:53:03.052182: step: 2008/529, loss: 0.3282504975795746
2023-01-23 00:53:04.239808: step: 2012/529, loss: 0.06817064434289932
2023-01-23 00:53:05.460752: step: 2016/529, loss: 0.0825490951538086
2023-01-23 00:53:06.673173: step: 2020/529, loss: 0.30041542649269104
2023-01-23 00:53:07.852228: step: 2024/529, loss: 0.11773135513067245
2023-01-23 00:53:09.101010: step: 2028/529, loss: 0.07731147110462189
2023-01-23 00:53:10.323804: step: 2032/529, loss: 0.13552813231945038
2023-01-23 00:53:11.509932: step: 2036/529, loss: 0.0021768570877611637
2023-01-23 00:53:12.698337: step: 2040/529, loss: 0.15446814894676208
2023-01-23 00:53:13.853610: step: 2044/529, loss: 0.07837028801441193
2023-01-23 00:53:15.037070: step: 2048/529, loss: 0.1547018587589264
2023-01-23 00:53:16.235157: step: 2052/529, loss: 0.03462862968444824
2023-01-23 00:53:17.485124: step: 2056/529, loss: 0.2763025164604187
2023-01-23 00:53:18.687125: step: 2060/529, loss: 0.06091451644897461
2023-01-23 00:53:19.893082: step: 2064/529, loss: 0.06399951130151749
2023-01-23 00:53:21.069202: step: 2068/529, loss: 0.030105162411928177
2023-01-23 00:53:22.237001: step: 2072/529, loss: 0.07769875228404999
2023-01-23 00:53:23.393377: step: 2076/529, loss: 0.13661842048168182
2023-01-23 00:53:24.570129: step: 2080/529, loss: 0.0390084870159626
2023-01-23 00:53:25.776623: step: 2084/529, loss: 0.5840644836425781
2023-01-23 00:53:26.973485: step: 2088/529, loss: 0.09293203800916672
2023-01-23 00:53:28.186934: step: 2092/529, loss: 0.2014886885881424
2023-01-23 00:53:29.395451: step: 2096/529, loss: 0.16322669386863708
2023-01-23 00:53:30.600485: step: 2100/529, loss: 0.45108363032341003
2023-01-23 00:53:31.856902: step: 2104/529, loss: 0.24104803800582886
2023-01-23 00:53:33.066592: step: 2108/529, loss: 0.04788923263549805
2023-01-23 00:53:34.296896: step: 2112/529, loss: 0.10468444973230362
2023-01-23 00:53:35.493335: step: 2116/529, loss: 0.1076471358537674
==================================================
Loss: 0.156
--------------------
Dev: {'event': {'p': 0.6077586206896551, 'r': 0.7509986684420772, 'f1': 0.6718284693269803}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6372795969773299, 'r': 0.7579388855602157, 'f1': 0.692391899288451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.6388888888888888, 'r': 0.8518518518518519, 'f1': 0.7301587301587301}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.58, 'r': 0.4603174603174603, 'f1': 0.5132743362831858}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5972944849115505, 'r': 0.7643142476697736, 'f1': 0.6705607476635514}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6162162162162163, 'r': 0.7513481126423007, 'f1': 0.6771058315334773}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 00:54:18.810910: step: 4/529, loss: 0.04047767072916031
2023-01-23 00:54:19.998136: step: 8/529, loss: 0.07821826636791229
2023-01-23 00:54:21.199903: step: 12/529, loss: 0.07875081896781921
2023-01-23 00:54:22.391810: step: 16/529, loss: 0.04651594161987305
2023-01-23 00:54:23.538448: step: 20/529, loss: 0.1396748572587967
2023-01-23 00:54:24.717934: step: 24/529, loss: 0.013078117743134499
2023-01-23 00:54:25.883940: step: 28/529, loss: 0.08061981201171875
2023-01-23 00:54:27.125750: step: 32/529, loss: 0.0347994789481163
2023-01-23 00:54:28.390607: step: 36/529, loss: 0.08932581543922424
2023-01-23 00:54:29.596793: step: 40/529, loss: 0.1444837599992752
2023-01-23 00:54:30.759415: step: 44/529, loss: 0.011849736794829369
2023-01-23 00:54:31.962184: step: 48/529, loss: 0.06010847166180611
2023-01-23 00:54:33.151243: step: 52/529, loss: 0.16181078553199768
2023-01-23 00:54:34.333887: step: 56/529, loss: 0.09997274726629257
2023-01-23 00:54:35.552464: step: 60/529, loss: 0.08434572070837021
2023-01-23 00:54:36.746980: step: 64/529, loss: 0.1226482167840004
2023-01-23 00:54:37.938154: step: 68/529, loss: 0.04693803936243057
2023-01-23 00:54:39.181418: step: 72/529, loss: 0.07839357107877731
2023-01-23 00:54:40.383205: step: 76/529, loss: 0.13694123923778534
2023-01-23 00:54:41.569851: step: 80/529, loss: 0.05220532417297363
2023-01-23 00:54:42.735585: step: 84/529, loss: 0.16351184248924255
2023-01-23 00:54:43.933818: step: 88/529, loss: 0.029614927247166634
2023-01-23 00:54:45.122091: step: 92/529, loss: 0.2026420533657074
2023-01-23 00:54:46.333985: step: 96/529, loss: 0.008451461791992188
2023-01-23 00:54:47.511701: step: 100/529, loss: 0.053057052195072174
2023-01-23 00:54:48.683109: step: 104/529, loss: 0.01918935775756836
2023-01-23 00:54:49.899390: step: 108/529, loss: 0.04503031075000763
2023-01-23 00:54:51.094018: step: 112/529, loss: 0.024651335552334785
2023-01-23 00:54:52.295359: step: 116/529, loss: 0.29497799277305603
2023-01-23 00:54:53.493832: step: 120/529, loss: 0.21508580446243286
2023-01-23 00:54:54.736560: step: 124/529, loss: 0.05541248247027397
2023-01-23 00:54:55.930537: step: 128/529, loss: 0.012671947479248047
2023-01-23 00:54:57.157720: step: 132/529, loss: 0.10966930538415909
2023-01-23 00:54:58.376983: step: 136/529, loss: 0.0374639518558979
2023-01-23 00:54:59.577214: step: 140/529, loss: 0.049568939954042435
2023-01-23 00:55:00.760395: step: 144/529, loss: 0.08577098697423935
2023-01-23 00:55:01.940909: step: 148/529, loss: 0.013721656054258347
2023-01-23 00:55:03.169199: step: 152/529, loss: 0.3713884949684143
2023-01-23 00:55:04.336275: step: 156/529, loss: 0.03838930279016495
2023-01-23 00:55:05.568440: step: 160/529, loss: 0.11151674389839172
2023-01-23 00:55:06.777664: step: 164/529, loss: 0.15473294258117676
2023-01-23 00:55:08.000448: step: 168/529, loss: 0.14717569947242737
2023-01-23 00:55:09.160276: step: 172/529, loss: 0.0909331813454628
2023-01-23 00:55:10.323722: step: 176/529, loss: 0.017193149775266647
2023-01-23 00:55:11.523632: step: 180/529, loss: 0.008180523291230202
2023-01-23 00:55:12.757908: step: 184/529, loss: 0.07138733565807343
2023-01-23 00:55:13.935024: step: 188/529, loss: 0.012599324807524681
2023-01-23 00:55:15.104472: step: 192/529, loss: 0.1007021889090538
2023-01-23 00:55:16.299139: step: 196/529, loss: 0.11016488075256348
2023-01-23 00:55:17.511071: step: 200/529, loss: 0.07014036178588867
2023-01-23 00:55:18.681918: step: 204/529, loss: 0.4783112406730652
2023-01-23 00:55:19.849326: step: 208/529, loss: 0.03167133033275604
2023-01-23 00:55:21.034688: step: 212/529, loss: 0.1298878788948059
2023-01-23 00:55:22.205349: step: 216/529, loss: 0.11687121540307999
2023-01-23 00:55:23.388988: step: 220/529, loss: 0.021193360909819603
2023-01-23 00:55:24.618661: step: 224/529, loss: 0.17543688416481018
2023-01-23 00:55:25.890483: step: 228/529, loss: 0.17486333847045898
2023-01-23 00:55:27.056806: step: 232/529, loss: 0.06752453744411469
2023-01-23 00:55:28.257530: step: 236/529, loss: 0.07916069775819778
2023-01-23 00:55:29.457651: step: 240/529, loss: 0.06988201290369034
2023-01-23 00:55:30.658380: step: 244/529, loss: 0.025316622108221054
2023-01-23 00:55:31.932020: step: 248/529, loss: 0.13482967019081116
2023-01-23 00:55:33.112455: step: 252/529, loss: 0.11785188317298889
2023-01-23 00:55:34.332888: step: 256/529, loss: 0.1267215758562088
2023-01-23 00:55:35.540017: step: 260/529, loss: 0.2078627347946167
2023-01-23 00:55:36.752443: step: 264/529, loss: 1.0372698307037354
2023-01-23 00:55:37.957053: step: 268/529, loss: 0.090336374938488
2023-01-23 00:55:39.140439: step: 272/529, loss: 0.040514782071113586
2023-01-23 00:55:40.355354: step: 276/529, loss: 0.0604795441031456
2023-01-23 00:55:41.617789: step: 280/529, loss: 0.13312676548957825
2023-01-23 00:55:42.827551: step: 284/529, loss: 0.04873685911297798
2023-01-23 00:55:44.039763: step: 288/529, loss: 0.04018230736255646
2023-01-23 00:55:45.248526: step: 292/529, loss: 0.08473005890846252
2023-01-23 00:55:46.455317: step: 296/529, loss: 0.0846981555223465
2023-01-23 00:55:47.642734: step: 300/529, loss: 0.10076389461755753
2023-01-23 00:55:48.851122: step: 304/529, loss: 0.041455648839473724
2023-01-23 00:55:50.045237: step: 308/529, loss: 0.07964906841516495
2023-01-23 00:55:51.226073: step: 312/529, loss: 0.2698894441127777
2023-01-23 00:55:52.417254: step: 316/529, loss: 0.02723999135196209
2023-01-23 00:55:53.573767: step: 320/529, loss: 0.4251673221588135
2023-01-23 00:55:54.754225: step: 324/529, loss: 0.1616990566253662
2023-01-23 00:55:55.961606: step: 328/529, loss: 0.07225904613733292
2023-01-23 00:55:57.168966: step: 332/529, loss: 0.039491843432188034
2023-01-23 00:55:58.363976: step: 336/529, loss: 0.347970575094223
2023-01-23 00:55:59.591506: step: 340/529, loss: 0.48211658000946045
2023-01-23 00:56:00.771659: step: 344/529, loss: 0.08665800094604492
2023-01-23 00:56:01.984706: step: 348/529, loss: 0.037229862064123154
2023-01-23 00:56:03.173420: step: 352/529, loss: 0.05745267868041992
2023-01-23 00:56:04.362318: step: 356/529, loss: 0.07717876881361008
2023-01-23 00:56:05.557446: step: 360/529, loss: 0.09231309592723846
2023-01-23 00:56:06.754894: step: 364/529, loss: 0.07006492465734482
2023-01-23 00:56:07.941291: step: 368/529, loss: 0.45909157395362854
2023-01-23 00:56:09.130537: step: 372/529, loss: 0.07901191711425781
2023-01-23 00:56:10.337185: step: 376/529, loss: 0.06261923909187317
2023-01-23 00:56:11.557730: step: 380/529, loss: 0.1023443266749382
2023-01-23 00:56:12.753545: step: 384/529, loss: 0.18097075819969177
2023-01-23 00:56:13.924651: step: 388/529, loss: 0.027232695370912552
2023-01-23 00:56:15.143415: step: 392/529, loss: 0.27917614579200745
2023-01-23 00:56:16.309004: step: 396/529, loss: 0.03713860362768173
2023-01-23 00:56:17.532034: step: 400/529, loss: 0.1250859797000885
2023-01-23 00:56:18.790887: step: 404/529, loss: 0.07704105973243713
2023-01-23 00:56:19.955175: step: 408/529, loss: 0.04263181611895561
2023-01-23 00:56:21.169833: step: 412/529, loss: 0.04491834715008736
2023-01-23 00:56:22.360124: step: 416/529, loss: 0.21583300828933716
2023-01-23 00:56:23.623319: step: 420/529, loss: 0.16193485260009766
2023-01-23 00:56:24.835687: step: 424/529, loss: 0.48976191878318787
2023-01-23 00:56:26.019106: step: 428/529, loss: 0.03811531513929367
2023-01-23 00:56:27.199919: step: 432/529, loss: 0.08802290260791779
2023-01-23 00:56:28.387982: step: 436/529, loss: 0.09434080123901367
2023-01-23 00:56:29.544334: step: 440/529, loss: 0.10715632140636444
2023-01-23 00:56:30.750197: step: 444/529, loss: 0.09228632599115372
2023-01-23 00:56:31.985724: step: 448/529, loss: 0.11972329765558243
2023-01-23 00:56:33.168034: step: 452/529, loss: 0.0010260582203045487
2023-01-23 00:56:34.375519: step: 456/529, loss: 0.04023704677820206
2023-01-23 00:56:35.528872: step: 460/529, loss: 0.004379749298095703
2023-01-23 00:56:36.668858: step: 464/529, loss: 0.07423634827136993
2023-01-23 00:56:37.855422: step: 468/529, loss: 0.03722720220685005
2023-01-23 00:56:39.060559: step: 472/529, loss: 0.03283347934484482
2023-01-23 00:56:40.231416: step: 476/529, loss: 0.7855027914047241
2023-01-23 00:56:41.452973: step: 480/529, loss: 0.06754789501428604
2023-01-23 00:56:42.596496: step: 484/529, loss: 0.020860005170106888
2023-01-23 00:56:43.784473: step: 488/529, loss: 0.023627091199159622
2023-01-23 00:56:44.960350: step: 492/529, loss: 0.005011129658669233
2023-01-23 00:56:46.154668: step: 496/529, loss: 0.06558027118444443
2023-01-23 00:56:47.347487: step: 500/529, loss: 0.06105814129114151
2023-01-23 00:56:48.515497: step: 504/529, loss: 0.16027694940567017
2023-01-23 00:56:49.754991: step: 508/529, loss: 0.08924088627099991
2023-01-23 00:56:50.980991: step: 512/529, loss: 0.39572152495384216
2023-01-23 00:56:52.210749: step: 516/529, loss: 0.10617408901453018
2023-01-23 00:56:53.409163: step: 520/529, loss: 0.13908430933952332
2023-01-23 00:56:54.610041: step: 524/529, loss: 0.0780036449432373
2023-01-23 00:56:55.816923: step: 528/529, loss: 0.3542849123477936
2023-01-23 00:56:57.010943: step: 532/529, loss: 0.03689432144165039
2023-01-23 00:56:58.225275: step: 536/529, loss: 0.16381417214870453
2023-01-23 00:56:59.434246: step: 540/529, loss: 0.05505218356847763
2023-01-23 00:57:00.662065: step: 544/529, loss: 1.293656349182129
2023-01-23 00:57:01.867259: step: 548/529, loss: 0.12761688232421875
2023-01-23 00:57:03.062403: step: 552/529, loss: 0.19070672988891602
2023-01-23 00:57:04.232031: step: 556/529, loss: 0.013144303113222122
2023-01-23 00:57:05.488624: step: 560/529, loss: 0.08128806203603745
2023-01-23 00:57:06.645055: step: 564/529, loss: 0.05706482008099556
2023-01-23 00:57:07.873810: step: 568/529, loss: 0.1587892472743988
2023-01-23 00:57:09.059459: step: 572/529, loss: 0.10761166363954544
2023-01-23 00:57:10.246292: step: 576/529, loss: 0.06638222187757492
2023-01-23 00:57:11.448802: step: 580/529, loss: 0.09939480572938919
2023-01-23 00:57:12.658303: step: 584/529, loss: 0.14611834287643433
2023-01-23 00:57:13.843835: step: 588/529, loss: 0.007876873016357422
2023-01-23 00:57:15.056554: step: 592/529, loss: 0.12069825828075409
2023-01-23 00:57:16.219791: step: 596/529, loss: 0.0007598876836709678
2023-01-23 00:57:17.454616: step: 600/529, loss: 0.026388835161924362
2023-01-23 00:57:18.651506: step: 604/529, loss: 0.09614834189414978
2023-01-23 00:57:19.818020: step: 608/529, loss: 0.06546439975500107
2023-01-23 00:57:20.987615: step: 612/529, loss: 0.02298755757510662
2023-01-23 00:57:22.153360: step: 616/529, loss: 0.05813789367675781
2023-01-23 00:57:23.298634: step: 620/529, loss: 0.03316373750567436
2023-01-23 00:57:24.479952: step: 624/529, loss: 0.024449540302157402
2023-01-23 00:57:25.659102: step: 628/529, loss: 0.3957507908344269
2023-01-23 00:57:26.885413: step: 632/529, loss: 0.3080708384513855
2023-01-23 00:57:28.092236: step: 636/529, loss: 0.09192705154418945
2023-01-23 00:57:29.290521: step: 640/529, loss: 0.11697450280189514
2023-01-23 00:57:30.507553: step: 644/529, loss: 0.04845685884356499
2023-01-23 00:57:31.710710: step: 648/529, loss: 0.16040655970573425
2023-01-23 00:57:32.939663: step: 652/529, loss: 0.1269499808549881
2023-01-23 00:57:34.123332: step: 656/529, loss: 0.024476148188114166
2023-01-23 00:57:35.298359: step: 660/529, loss: 0.007953787222504616
2023-01-23 00:57:36.533492: step: 664/529, loss: 0.0908367931842804
2023-01-23 00:57:37.771804: step: 668/529, loss: 0.013273334130644798
2023-01-23 00:57:38.974578: step: 672/529, loss: 0.06754917651414871
2023-01-23 00:57:40.216462: step: 676/529, loss: 0.024636365473270416
2023-01-23 00:57:41.396208: step: 680/529, loss: 0.01600360870361328
2023-01-23 00:57:42.620528: step: 684/529, loss: 0.012657023034989834
2023-01-23 00:57:43.818979: step: 688/529, loss: 0.03296785056591034
2023-01-23 00:57:45.019470: step: 692/529, loss: 0.08263721317052841
2023-01-23 00:57:46.216388: step: 696/529, loss: 0.024071549996733665
2023-01-23 00:57:47.416350: step: 700/529, loss: 0.09579934924840927
2023-01-23 00:57:48.595784: step: 704/529, loss: 0.016787387430667877
2023-01-23 00:57:49.773866: step: 708/529, loss: 0.05615215376019478
2023-01-23 00:57:50.966269: step: 712/529, loss: 0.02637634426355362
2023-01-23 00:57:52.169327: step: 716/529, loss: 0.14427319169044495
2023-01-23 00:57:53.373785: step: 720/529, loss: 0.053510282188653946
2023-01-23 00:57:54.579670: step: 724/529, loss: 0.08245811611413956
2023-01-23 00:57:55.773473: step: 728/529, loss: 0.0813908576965332
2023-01-23 00:57:57.003376: step: 732/529, loss: 0.5283936262130737
2023-01-23 00:57:58.200351: step: 736/529, loss: 0.29870322346687317
2023-01-23 00:57:59.370507: step: 740/529, loss: 0.022414540871977806
2023-01-23 00:58:00.558995: step: 744/529, loss: 0.1062687486410141
2023-01-23 00:58:01.729038: step: 748/529, loss: 0.04527187719941139
2023-01-23 00:58:02.944183: step: 752/529, loss: 0.08696842193603516
2023-01-23 00:58:04.159949: step: 756/529, loss: 0.10458926856517792
2023-01-23 00:58:05.385343: step: 760/529, loss: 0.06515693664550781
2023-01-23 00:58:06.613519: step: 764/529, loss: 0.22541780769824982
2023-01-23 00:58:07.786194: step: 768/529, loss: 0.14605307579040527
2023-01-23 00:58:08.964517: step: 772/529, loss: 0.026258373633027077
2023-01-23 00:58:10.160208: step: 776/529, loss: 0.12572507560253143
2023-01-23 00:58:11.369850: step: 780/529, loss: 0.16668052971363068
2023-01-23 00:58:12.547311: step: 784/529, loss: 0.0823274701833725
2023-01-23 00:58:13.764093: step: 788/529, loss: 0.11530504375696182
2023-01-23 00:58:14.981373: step: 792/529, loss: 0.29284152388572693
2023-01-23 00:58:16.206143: step: 796/529, loss: 0.08278483897447586
2023-01-23 00:58:17.370669: step: 800/529, loss: 0.12059229612350464
2023-01-23 00:58:18.547918: step: 804/529, loss: 0.00380191789008677
2023-01-23 00:58:19.734404: step: 808/529, loss: 0.10135946422815323
2023-01-23 00:58:20.966083: step: 812/529, loss: 0.09400882571935654
2023-01-23 00:58:22.153773: step: 816/529, loss: 0.06097893789410591
2023-01-23 00:58:23.366425: step: 820/529, loss: 0.012851476669311523
2023-01-23 00:58:24.564232: step: 824/529, loss: 0.22244702279567719
2023-01-23 00:58:25.737872: step: 828/529, loss: 0.07800417393445969
2023-01-23 00:58:26.912990: step: 832/529, loss: 0.04298420250415802
2023-01-23 00:58:28.038864: step: 836/529, loss: 0.0540955513715744
2023-01-23 00:58:29.259421: step: 840/529, loss: 0.05601468309760094
2023-01-23 00:58:30.460171: step: 844/529, loss: 0.016303157433867455
2023-01-23 00:58:31.647311: step: 848/529, loss: 0.03289385139942169
2023-01-23 00:58:32.849927: step: 852/529, loss: 0.05658779293298721
2023-01-23 00:58:34.056018: step: 856/529, loss: 0.05487480014562607
2023-01-23 00:58:35.248243: step: 860/529, loss: 0.34701091051101685
2023-01-23 00:58:36.466537: step: 864/529, loss: 0.05912923812866211
2023-01-23 00:58:37.676464: step: 868/529, loss: 0.16625633835792542
2023-01-23 00:58:38.914860: step: 872/529, loss: 0.09264211356639862
2023-01-23 00:58:40.123389: step: 876/529, loss: 0.027820684015750885
2023-01-23 00:58:41.296080: step: 880/529, loss: 0.01377172488719225
2023-01-23 00:58:42.505964: step: 884/529, loss: 0.39780083298683167
2023-01-23 00:58:43.712626: step: 888/529, loss: 0.07220707088708878
2023-01-23 00:58:44.921152: step: 892/529, loss: 0.21084824204444885
2023-01-23 00:58:46.101109: step: 896/529, loss: 0.02554459497332573
2023-01-23 00:58:47.303100: step: 900/529, loss: 0.09172508865594864
2023-01-23 00:58:48.504072: step: 904/529, loss: 0.054864026606082916
2023-01-23 00:58:49.705292: step: 908/529, loss: 0.05406989902257919
2023-01-23 00:58:50.878628: step: 912/529, loss: 0.0252551082521677
2023-01-23 00:58:52.086757: step: 916/529, loss: 0.5439997315406799
2023-01-23 00:58:53.291497: step: 920/529, loss: 0.0982782393693924
2023-01-23 00:58:54.473479: step: 924/529, loss: 0.1017635390162468
2023-01-23 00:58:55.703791: step: 928/529, loss: 0.06407535821199417
2023-01-23 00:58:56.897900: step: 932/529, loss: 0.043857574462890625
2023-01-23 00:58:58.088930: step: 936/529, loss: 0.06193418800830841
2023-01-23 00:58:59.324685: step: 940/529, loss: 0.09406929463148117
2023-01-23 00:59:00.526503: step: 944/529, loss: 0.0677550807595253
2023-01-23 00:59:01.724794: step: 948/529, loss: 0.05266690254211426
2023-01-23 00:59:02.997901: step: 952/529, loss: 0.09897145628929138
2023-01-23 00:59:04.180597: step: 956/529, loss: 0.00474205007776618
2023-01-23 00:59:05.373529: step: 960/529, loss: 0.05670957267284393
2023-01-23 00:59:06.558606: step: 964/529, loss: 0.4810495972633362
2023-01-23 00:59:07.744953: step: 968/529, loss: 0.09206457436084747
2023-01-23 00:59:08.996669: step: 972/529, loss: 0.03547511249780655
2023-01-23 00:59:10.184713: step: 976/529, loss: 0.3007730543613434
2023-01-23 00:59:11.382365: step: 980/529, loss: 0.035579536110162735
2023-01-23 00:59:12.590145: step: 984/529, loss: 0.22938866913318634
2023-01-23 00:59:13.845211: step: 988/529, loss: 0.059946633875370026
2023-01-23 00:59:15.012636: step: 992/529, loss: 0.04224582016468048
2023-01-23 00:59:16.269724: step: 996/529, loss: 0.18574008345603943
2023-01-23 00:59:17.509682: step: 1000/529, loss: 0.14251522719860077
2023-01-23 00:59:18.747818: step: 1004/529, loss: 0.14577370882034302
2023-01-23 00:59:19.925929: step: 1008/529, loss: 0.01887531206011772
2023-01-23 00:59:21.104359: step: 1012/529, loss: 0.0874418243765831
2023-01-23 00:59:22.312819: step: 1016/529, loss: 0.8079484105110168
2023-01-23 00:59:23.504197: step: 1020/529, loss: 0.172323077917099
2023-01-23 00:59:24.669826: step: 1024/529, loss: 0.11157283931970596
2023-01-23 00:59:25.844463: step: 1028/529, loss: 0.036309339106082916
2023-01-23 00:59:27.079960: step: 1032/529, loss: 0.11312361061573029
2023-01-23 00:59:28.291521: step: 1036/529, loss: 0.07403126358985901
2023-01-23 00:59:29.484222: step: 1040/529, loss: 0.09309511631727219
2023-01-23 00:59:30.665207: step: 1044/529, loss: 0.13171759247779846
2023-01-23 00:59:31.887459: step: 1048/529, loss: 0.10741788148880005
2023-01-23 00:59:33.095790: step: 1052/529, loss: 0.11655206978321075
2023-01-23 00:59:34.297602: step: 1056/529, loss: 0.07213926315307617
2023-01-23 00:59:35.509556: step: 1060/529, loss: 0.07369041442871094
2023-01-23 00:59:36.676639: step: 1064/529, loss: 0.07184381037950516
2023-01-23 00:59:37.857704: step: 1068/529, loss: 0.060051776468753815
2023-01-23 00:59:39.019800: step: 1072/529, loss: 0.7109342813491821
2023-01-23 00:59:40.266707: step: 1076/529, loss: 0.03996581956744194
2023-01-23 00:59:41.446193: step: 1080/529, loss: 0.013586855493485928
2023-01-23 00:59:42.672910: step: 1084/529, loss: 0.014812374487519264
2023-01-23 00:59:43.845150: step: 1088/529, loss: 0.1448853611946106
2023-01-23 00:59:45.058472: step: 1092/529, loss: 0.08025312423706055
2023-01-23 00:59:46.239192: step: 1096/529, loss: 0.03768768161535263
2023-01-23 00:59:47.435735: step: 1100/529, loss: 0.17361049354076385
2023-01-23 00:59:48.607074: step: 1104/529, loss: 0.05589780956506729
2023-01-23 00:59:49.793434: step: 1108/529, loss: 0.1783219277858734
2023-01-23 00:59:50.960312: step: 1112/529, loss: 0.0425073616206646
2023-01-23 00:59:52.188027: step: 1116/529, loss: 0.10130815953016281
2023-01-23 00:59:53.435970: step: 1120/529, loss: 0.6068741083145142
2023-01-23 00:59:54.627450: step: 1124/529, loss: 0.13269658386707306
2023-01-23 00:59:55.811443: step: 1128/529, loss: 0.12661753594875336
2023-01-23 00:59:56.998576: step: 1132/529, loss: 0.05074606090784073
2023-01-23 00:59:58.212513: step: 1136/529, loss: 0.02085275761783123
2023-01-23 00:59:59.379352: step: 1140/529, loss: 0.13153213262557983
2023-01-23 01:00:00.580330: step: 1144/529, loss: 0.3103060722351074
2023-01-23 01:00:01.745524: step: 1148/529, loss: 0.025852108374238014
2023-01-23 01:00:03.004042: step: 1152/529, loss: 0.10076145827770233
2023-01-23 01:00:04.222376: step: 1156/529, loss: 0.05120129883289337
2023-01-23 01:00:05.366006: step: 1160/529, loss: 0.02644982375204563
2023-01-23 01:00:06.588373: step: 1164/529, loss: 0.19872704148292542
2023-01-23 01:00:07.788586: step: 1168/529, loss: 0.1585426777601242
2023-01-23 01:00:08.962563: step: 1172/529, loss: 0.32388150691986084
2023-01-23 01:00:10.174882: step: 1176/529, loss: 0.015065575018525124
2023-01-23 01:00:11.340539: step: 1180/529, loss: 0.08784134685993195
2023-01-23 01:00:12.556307: step: 1184/529, loss: 0.0757235512137413
2023-01-23 01:00:13.722818: step: 1188/529, loss: 0.035753894597291946
2023-01-23 01:00:14.915304: step: 1192/529, loss: 0.04402007907629013
2023-01-23 01:00:16.131319: step: 1196/529, loss: 0.10342884063720703
2023-01-23 01:00:17.331415: step: 1200/529, loss: 0.6368496417999268
2023-01-23 01:00:18.539630: step: 1204/529, loss: 0.24611268937587738
2023-01-23 01:00:19.794983: step: 1208/529, loss: 0.1868046224117279
2023-01-23 01:00:20.997036: step: 1212/529, loss: 0.04192471504211426
2023-01-23 01:00:22.193974: step: 1216/529, loss: 0.38344359397888184
2023-01-23 01:00:23.354470: step: 1220/529, loss: 0.09596691280603409
2023-01-23 01:00:24.550763: step: 1224/529, loss: 0.16268451511859894
2023-01-23 01:00:25.732881: step: 1228/529, loss: 0.07357574254274368
2023-01-23 01:00:26.921343: step: 1232/529, loss: 0.04232821613550186
2023-01-23 01:00:28.111722: step: 1236/529, loss: 0.029508303850889206
2023-01-23 01:00:29.320784: step: 1240/529, loss: 0.05965328589081764
2023-01-23 01:00:30.491119: step: 1244/529, loss: 0.19239473342895508
2023-01-23 01:00:31.702029: step: 1248/529, loss: 0.0510801300406456
2023-01-23 01:00:32.902670: step: 1252/529, loss: 0.0352511890232563
2023-01-23 01:00:34.108236: step: 1256/529, loss: 0.3062821328639984
2023-01-23 01:00:35.341889: step: 1260/529, loss: 0.13641229271888733
2023-01-23 01:00:36.574978: step: 1264/529, loss: 0.23968066275119781
2023-01-23 01:00:37.779432: step: 1268/529, loss: 0.0965091735124588
2023-01-23 01:00:38.970279: step: 1272/529, loss: 0.21080684661865234
2023-01-23 01:00:40.181711: step: 1276/529, loss: 0.32785558700561523
2023-01-23 01:00:41.364818: step: 1280/529, loss: 0.16244274377822876
2023-01-23 01:00:42.543744: step: 1284/529, loss: 0.06273765861988068
2023-01-23 01:00:43.721354: step: 1288/529, loss: 0.09987225383520126
2023-01-23 01:00:44.944174: step: 1292/529, loss: 0.17433367669582367
2023-01-23 01:00:46.172026: step: 1296/529, loss: 0.2575455904006958
2023-01-23 01:00:47.404504: step: 1300/529, loss: 0.08590006828308105
2023-01-23 01:00:48.603237: step: 1304/529, loss: 0.08878374099731445
2023-01-23 01:00:49.824149: step: 1308/529, loss: 0.1368647664785385
2023-01-23 01:00:51.000381: step: 1312/529, loss: 0.0055213929153978825
2023-01-23 01:00:52.251200: step: 1316/529, loss: 0.09987707436084747
2023-01-23 01:00:53.447080: step: 1320/529, loss: 0.04167604818940163
2023-01-23 01:00:54.679476: step: 1324/529, loss: 0.17418260872364044
2023-01-23 01:00:55.927857: step: 1328/529, loss: 0.20379528403282166
2023-01-23 01:00:57.123547: step: 1332/529, loss: 0.12248249351978302
2023-01-23 01:00:58.323337: step: 1336/529, loss: 0.1846325844526291
2023-01-23 01:00:59.545418: step: 1340/529, loss: 0.09751148521900177
2023-01-23 01:01:00.724952: step: 1344/529, loss: 0.05286912992596626
2023-01-23 01:01:01.947458: step: 1348/529, loss: 0.09309554100036621
2023-01-23 01:01:03.204897: step: 1352/529, loss: 0.16922931373119354
2023-01-23 01:01:04.400454: step: 1356/529, loss: 0.13260327279567719
2023-01-23 01:01:05.592558: step: 1360/529, loss: 0.07543373107910156
2023-01-23 01:01:06.808620: step: 1364/529, loss: 0.11243017017841339
2023-01-23 01:01:08.016274: step: 1368/529, loss: 0.042791225016117096
2023-01-23 01:01:09.191620: step: 1372/529, loss: 0.12579889595508575
2023-01-23 01:01:10.415719: step: 1376/529, loss: 0.025398921221494675
2023-01-23 01:01:11.698898: step: 1380/529, loss: 0.11367006599903107
2023-01-23 01:01:12.865332: step: 1384/529, loss: 0.020359564572572708
2023-01-23 01:01:14.035383: step: 1388/529, loss: 0.02606039121747017
2023-01-23 01:01:15.239920: step: 1392/529, loss: 0.054610732942819595
2023-01-23 01:01:16.460673: step: 1396/529, loss: 0.3439517319202423
2023-01-23 01:01:17.628802: step: 1400/529, loss: 0.01565117947757244
2023-01-23 01:01:18.823206: step: 1404/529, loss: 0.0865788459777832
2023-01-23 01:01:20.014720: step: 1408/529, loss: 0.04938087612390518
2023-01-23 01:01:21.181876: step: 1412/529, loss: 0.04691317304968834
2023-01-23 01:01:22.350456: step: 1416/529, loss: 0.07006168365478516
2023-01-23 01:01:23.539057: step: 1420/529, loss: 0.11272773146629333
2023-01-23 01:01:24.772758: step: 1424/529, loss: 0.03806428983807564
2023-01-23 01:01:26.003934: step: 1428/529, loss: 0.03891425207257271
2023-01-23 01:01:27.182251: step: 1432/529, loss: 0.06599149852991104
2023-01-23 01:01:28.348807: step: 1436/529, loss: 0.0348605178296566
2023-01-23 01:01:29.537111: step: 1440/529, loss: 0.07947144657373428
2023-01-23 01:01:30.736844: step: 1444/529, loss: 0.06252908706665039
2023-01-23 01:01:31.935985: step: 1448/529, loss: 0.046996310353279114
2023-01-23 01:01:33.140464: step: 1452/529, loss: 0.1292612999677658
2023-01-23 01:01:34.285616: step: 1456/529, loss: 0.023672515526413918
2023-01-23 01:01:35.477244: step: 1460/529, loss: 0.41750413179397583
2023-01-23 01:01:36.704994: step: 1464/529, loss: 0.22391678392887115
2023-01-23 01:01:37.896073: step: 1468/529, loss: 0.18273591995239258
2023-01-23 01:01:39.071829: step: 1472/529, loss: 0.6467920541763306
2023-01-23 01:01:40.254862: step: 1476/529, loss: 0.06702125817537308
2023-01-23 01:01:41.445832: step: 1480/529, loss: 0.251875102519989
2023-01-23 01:01:42.648117: step: 1484/529, loss: 0.06994829326868057
2023-01-23 01:01:43.880314: step: 1488/529, loss: 0.3780898153781891
2023-01-23 01:01:45.060322: step: 1492/529, loss: 0.1128087043762207
2023-01-23 01:01:46.329721: step: 1496/529, loss: 0.18003129959106445
2023-01-23 01:01:47.508903: step: 1500/529, loss: 0.16708484292030334
2023-01-23 01:01:48.720493: step: 1504/529, loss: 0.050896644592285156
2023-01-23 01:01:49.906850: step: 1508/529, loss: 0.0634942501783371
2023-01-23 01:01:51.105917: step: 1512/529, loss: 0.11012440174818039
2023-01-23 01:01:52.335672: step: 1516/529, loss: 0.1159524917602539
2023-01-23 01:01:53.530673: step: 1520/529, loss: 0.09098625183105469
2023-01-23 01:01:54.736023: step: 1524/529, loss: 0.14877291023731232
2023-01-23 01:01:55.915504: step: 1528/529, loss: 0.027217866852879524
2023-01-23 01:01:57.161383: step: 1532/529, loss: 0.1360592246055603
2023-01-23 01:01:58.321778: step: 1536/529, loss: 0.11871004104614258
2023-01-23 01:01:59.485490: step: 1540/529, loss: 0.024248875677585602
2023-01-23 01:02:00.651396: step: 1544/529, loss: 0.04238881915807724
2023-01-23 01:02:01.895997: step: 1548/529, loss: 0.07538357377052307
2023-01-23 01:02:03.097304: step: 1552/529, loss: 0.26502570509910583
2023-01-23 01:02:04.316607: step: 1556/529, loss: 0.08521862328052521
2023-01-23 01:02:05.503439: step: 1560/529, loss: 0.10298766940832138
2023-01-23 01:02:06.715514: step: 1564/529, loss: 0.056702613830566406
2023-01-23 01:02:07.913368: step: 1568/529, loss: 0.31682783365249634
2023-01-23 01:02:09.147106: step: 1572/529, loss: 0.03723783418536186
2023-01-23 01:02:10.396626: step: 1576/529, loss: 0.034201718866825104
2023-01-23 01:02:11.580019: step: 1580/529, loss: 0.014857674017548561
2023-01-23 01:02:12.759736: step: 1584/529, loss: 0.08071684837341309
2023-01-23 01:02:13.977287: step: 1588/529, loss: 0.04908592998981476
2023-01-23 01:02:15.179673: step: 1592/529, loss: 0.057427406311035156
2023-01-23 01:02:16.394377: step: 1596/529, loss: 0.14947891235351562
2023-01-23 01:02:17.579669: step: 1600/529, loss: 0.13462170958518982
2023-01-23 01:02:18.729312: step: 1604/529, loss: 0.35665810108184814
2023-01-23 01:02:19.913922: step: 1608/529, loss: 0.034613847732543945
2023-01-23 01:02:21.110374: step: 1612/529, loss: 0.03477802127599716
2023-01-23 01:02:22.328633: step: 1616/529, loss: 0.2647930085659027
2023-01-23 01:02:23.514271: step: 1620/529, loss: 0.12565088272094727
2023-01-23 01:02:24.687321: step: 1624/529, loss: 0.895087480545044
2023-01-23 01:02:25.866449: step: 1628/529, loss: 0.23116064071655273
2023-01-23 01:02:27.050389: step: 1632/529, loss: 0.09947586059570312
2023-01-23 01:02:28.279848: step: 1636/529, loss: 0.09858989715576172
2023-01-23 01:02:29.512988: step: 1640/529, loss: 0.053867340087890625
2023-01-23 01:02:30.687542: step: 1644/529, loss: 0.01315016858279705
2023-01-23 01:02:31.941220: step: 1648/529, loss: 0.20471249520778656
2023-01-23 01:02:33.111016: step: 1652/529, loss: 0.05195903778076172
2023-01-23 01:02:34.349496: step: 1656/529, loss: 0.2735646069049835
2023-01-23 01:02:35.548187: step: 1660/529, loss: 0.15480592846870422
2023-01-23 01:02:36.723626: step: 1664/529, loss: 0.05930893495678902
2023-01-23 01:02:37.937270: step: 1668/529, loss: 0.12114687263965607
2023-01-23 01:02:39.145514: step: 1672/529, loss: 0.03629293292760849
2023-01-23 01:02:40.367945: step: 1676/529, loss: 0.10183429718017578
2023-01-23 01:02:41.538202: step: 1680/529, loss: 0.14595910906791687
2023-01-23 01:02:42.708746: step: 1684/529, loss: 0.14450454711914062
2023-01-23 01:02:43.921333: step: 1688/529, loss: 0.028574656695127487
2023-01-23 01:02:45.102885: step: 1692/529, loss: 0.03656186908483505
2023-01-23 01:02:46.374006: step: 1696/529, loss: 0.1851770430803299
2023-01-23 01:02:47.563981: step: 1700/529, loss: 0.037909604609012604
2023-01-23 01:02:48.722914: step: 1704/529, loss: 0.12020893394947052
2023-01-23 01:02:49.927487: step: 1708/529, loss: 0.013139819726347923
2023-01-23 01:02:51.159541: step: 1712/529, loss: 0.06804962456226349
2023-01-23 01:02:52.411276: step: 1716/529, loss: 0.20287780463695526
2023-01-23 01:02:53.621926: step: 1720/529, loss: 0.036954592913389206
2023-01-23 01:02:54.798386: step: 1724/529, loss: 0.13216161727905273
2023-01-23 01:02:55.998278: step: 1728/529, loss: 0.014828872866928577
2023-01-23 01:02:57.149485: step: 1732/529, loss: 0.01449351292103529
2023-01-23 01:02:58.341533: step: 1736/529, loss: 0.0587100088596344
2023-01-23 01:02:59.574868: step: 1740/529, loss: 0.12489938735961914
2023-01-23 01:03:00.755662: step: 1744/529, loss: 0.3651566505432129
2023-01-23 01:03:01.964879: step: 1748/529, loss: 0.0887083113193512
2023-01-23 01:03:03.155750: step: 1752/529, loss: 0.0992402583360672
2023-01-23 01:03:04.332998: step: 1756/529, loss: 0.12959490716457367
2023-01-23 01:03:05.583866: step: 1760/529, loss: 0.043139033019542694
2023-01-23 01:03:06.806299: step: 1764/529, loss: 0.12684936821460724
2023-01-23 01:03:08.020787: step: 1768/529, loss: 0.10574893653392792
2023-01-23 01:03:09.220316: step: 1772/529, loss: 0.004454374313354492
2023-01-23 01:03:10.379863: step: 1776/529, loss: 0.004342270083725452
2023-01-23 01:03:11.592759: step: 1780/529, loss: 0.04948420822620392
2023-01-23 01:03:12.792993: step: 1784/529, loss: 0.04153924062848091
2023-01-23 01:03:13.975484: step: 1788/529, loss: 0.706120491027832
2023-01-23 01:03:15.164560: step: 1792/529, loss: 0.0879400223493576
2023-01-23 01:03:16.375497: step: 1796/529, loss: 0.10746678709983826
2023-01-23 01:03:17.567548: step: 1800/529, loss: 0.06811189651489258
2023-01-23 01:03:18.740891: step: 1804/529, loss: 0.16225960850715637
2023-01-23 01:03:19.927077: step: 1808/529, loss: 0.26645317673683167
2023-01-23 01:03:21.145813: step: 1812/529, loss: 0.13903197646141052
2023-01-23 01:03:22.319544: step: 1816/529, loss: 0.10329466313123703
2023-01-23 01:03:23.556926: step: 1820/529, loss: 0.0913720577955246
2023-01-23 01:03:24.756871: step: 1824/529, loss: 0.16671404242515564
2023-01-23 01:03:25.960438: step: 1828/529, loss: 0.027530908584594727
2023-01-23 01:03:27.117910: step: 1832/529, loss: 0.6448995471000671
2023-01-23 01:03:28.272502: step: 1836/529, loss: 0.07307520508766174
2023-01-23 01:03:29.515110: step: 1840/529, loss: 0.10081490874290466
2023-01-23 01:03:30.720943: step: 1844/529, loss: 0.0912538543343544
2023-01-23 01:03:31.900005: step: 1848/529, loss: 0.11710606515407562
2023-01-23 01:03:33.097200: step: 1852/529, loss: 0.05176488310098648
2023-01-23 01:03:34.274659: step: 1856/529, loss: 0.2116812765598297
2023-01-23 01:03:35.487542: step: 1860/529, loss: 0.0839686393737793
2023-01-23 01:03:36.696684: step: 1864/529, loss: 0.07875747978687286
2023-01-23 01:03:37.944772: step: 1868/529, loss: 0.2987893521785736
2023-01-23 01:03:39.128805: step: 1872/529, loss: 0.03684444725513458
2023-01-23 01:03:40.318306: step: 1876/529, loss: 0.07712383568286896
2023-01-23 01:03:41.482246: step: 1880/529, loss: 0.010545921511948109
2023-01-23 01:03:42.657789: step: 1884/529, loss: 0.06599533557891846
2023-01-23 01:03:43.864136: step: 1888/529, loss: 0.025420378893613815
2023-01-23 01:03:45.091081: step: 1892/529, loss: 0.14610300958156586
2023-01-23 01:03:46.262777: step: 1896/529, loss: 0.05847196653485298
2023-01-23 01:03:47.459820: step: 1900/529, loss: 0.09752541035413742
2023-01-23 01:03:48.630744: step: 1904/529, loss: 0.026617813855409622
2023-01-23 01:03:49.819804: step: 1908/529, loss: 0.38210946321487427
2023-01-23 01:03:50.987031: step: 1912/529, loss: 0.042977333068847656
2023-01-23 01:03:52.215285: step: 1916/529, loss: 0.016511917114257812
2023-01-23 01:03:53.473000: step: 1920/529, loss: 0.07485198974609375
2023-01-23 01:03:54.696777: step: 1924/529, loss: 0.061173632740974426
2023-01-23 01:03:55.891351: step: 1928/529, loss: 0.05647630989551544
2023-01-23 01:03:57.074694: step: 1932/529, loss: 0.13428688049316406
2023-01-23 01:03:58.304627: step: 1936/529, loss: 0.056896306574344635
2023-01-23 01:03:59.538415: step: 1940/529, loss: 0.18245278298854828
2023-01-23 01:04:00.673371: step: 1944/529, loss: 0.06295967102050781
2023-01-23 01:04:01.900811: step: 1948/529, loss: 0.08530721813440323
2023-01-23 01:04:03.065077: step: 1952/529, loss: 0.17455103993415833
2023-01-23 01:04:04.254406: step: 1956/529, loss: 0.0513579398393631
2023-01-23 01:04:05.449508: step: 1960/529, loss: 0.06473426520824432
2023-01-23 01:04:06.630417: step: 1964/529, loss: 0.005498173646628857
2023-01-23 01:04:07.812164: step: 1968/529, loss: 0.0337066650390625
2023-01-23 01:04:09.010808: step: 1972/529, loss: 0.5874265432357788
2023-01-23 01:04:10.170023: step: 1976/529, loss: 0.12416896969079971
2023-01-23 01:04:11.399972: step: 1980/529, loss: 0.07729692757129669
2023-01-23 01:04:12.631644: step: 1984/529, loss: 0.11703939735889435
2023-01-23 01:04:13.833115: step: 1988/529, loss: 0.055304817855358124
2023-01-23 01:04:15.020466: step: 1992/529, loss: 0.09929418563842773
2023-01-23 01:04:16.239366: step: 1996/529, loss: 0.0662347823381424
2023-01-23 01:04:17.408990: step: 2000/529, loss: 0.09534512460231781
2023-01-23 01:04:18.647420: step: 2004/529, loss: 0.1967918872833252
2023-01-23 01:04:19.918448: step: 2008/529, loss: 0.08169937133789062
2023-01-23 01:04:21.118206: step: 2012/529, loss: 0.25774747133255005
2023-01-23 01:04:22.303365: step: 2016/529, loss: 0.10631094127893448
2023-01-23 01:04:23.478729: step: 2020/529, loss: 0.44311124086380005
2023-01-23 01:04:24.662881: step: 2024/529, loss: 0.023267174139618874
2023-01-23 01:04:25.815821: step: 2028/529, loss: 0.09495649486780167
2023-01-23 01:04:26.975879: step: 2032/529, loss: 0.03013906627893448
2023-01-23 01:04:28.154247: step: 2036/529, loss: 0.09901189804077148
2023-01-23 01:04:29.312691: step: 2040/529, loss: 0.011135769076645374
2023-01-23 01:04:30.496421: step: 2044/529, loss: 0.06298866868019104
2023-01-23 01:04:31.677767: step: 2048/529, loss: 0.019121933728456497
2023-01-23 01:04:32.877500: step: 2052/529, loss: 0.031234467402100563
2023-01-23 01:04:34.102655: step: 2056/529, loss: 0.017626380547881126
2023-01-23 01:04:35.300316: step: 2060/529, loss: 0.22762995958328247
2023-01-23 01:04:36.510665: step: 2064/529, loss: 0.14104080200195312
2023-01-23 01:04:37.658625: step: 2068/529, loss: 0.07647185027599335
2023-01-23 01:04:38.845813: step: 2072/529, loss: 0.40145397186279297
2023-01-23 01:04:40.084857: step: 2076/529, loss: 0.2017030417919159
2023-01-23 01:04:41.302234: step: 2080/529, loss: 0.1204218864440918
2023-01-23 01:04:42.484618: step: 2084/529, loss: 0.01604294776916504
2023-01-23 01:04:43.674368: step: 2088/529, loss: 0.8274124264717102
2023-01-23 01:04:44.873872: step: 2092/529, loss: 0.15177275240421295
2023-01-23 01:04:46.081931: step: 2096/529, loss: 0.9513418078422546
2023-01-23 01:04:47.282176: step: 2100/529, loss: 0.14701539278030396
2023-01-23 01:04:48.444693: step: 2104/529, loss: 0.3254031240940094
2023-01-23 01:04:49.658328: step: 2108/529, loss: 0.06617040932178497
2023-01-23 01:04:50.881795: step: 2112/529, loss: 0.7396628856658936
2023-01-23 01:04:52.078196: step: 2116/529, loss: 0.09895887225866318
==================================================
Loss: 0.127
--------------------
Dev: {'event': {'p': 0.5877106045589693, 'r': 0.7896138482023968, 'f1': 0.6738636363636363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6253574833174452, 'r': 0.7860994607549431, 'f1': 0.6965755242898859}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.5595238095238095, 'r': 0.8703703703703703, 'f1': 0.6811594202898551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.6271186440677966, 'r': 0.5873015873015873, 'f1': 0.6065573770491803}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877106045589693, 'r': 0.7896138482023968, 'f1': 0.6738636363636363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6253574833174452, 'r': 0.7860994607549431, 'f1': 0.6965755242898859}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.6271186440677966, 'r': 0.5873015873015873, 'f1': 0.6065573770491803}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 01:05:44.553670: step: 4/529, loss: 0.07706203311681747
2023-01-23 01:05:45.771473: step: 8/529, loss: 0.3609369397163391
2023-01-23 01:05:46.945559: step: 12/529, loss: 0.02501654624938965
2023-01-23 01:05:48.159874: step: 16/529, loss: 0.20460176467895508
2023-01-23 01:05:49.367168: step: 20/529, loss: 0.05868654325604439
2023-01-23 01:05:50.594280: step: 24/529, loss: 0.1241549551486969
2023-01-23 01:05:51.784546: step: 28/529, loss: 0.027274703606963158
2023-01-23 01:05:52.970197: step: 32/529, loss: 0.09330911934375763
2023-01-23 01:05:54.118465: step: 36/529, loss: 0.10482750833034515
2023-01-23 01:05:55.325876: step: 40/529, loss: 0.09188003093004227
2023-01-23 01:05:56.498070: step: 44/529, loss: 0.042665816843509674
2023-01-23 01:05:57.673474: step: 48/529, loss: 0.10282287746667862
2023-01-23 01:05:58.906438: step: 52/529, loss: 0.04815168306231499
2023-01-23 01:06:00.148148: step: 56/529, loss: 0.002200603485107422
2023-01-23 01:06:01.359943: step: 60/529, loss: 0.08510227501392365
2023-01-23 01:06:02.563572: step: 64/529, loss: 0.05405187979340553
2023-01-23 01:06:03.749988: step: 68/529, loss: 0.04417545348405838
2023-01-23 01:06:04.946590: step: 72/529, loss: 0.2788141071796417
2023-01-23 01:06:06.171683: step: 76/529, loss: 0.07424087822437286
2023-01-23 01:06:07.338356: step: 80/529, loss: 0.011209297925233841
2023-01-23 01:06:08.520918: step: 84/529, loss: 0.014039039611816406
2023-01-23 01:06:09.724442: step: 88/529, loss: 0.014297867193818092
2023-01-23 01:06:10.911715: step: 92/529, loss: 0.029778480529785156
2023-01-23 01:06:12.121190: step: 96/529, loss: 0.09650173783302307
2023-01-23 01:06:13.294714: step: 100/529, loss: 0.021039199084043503
2023-01-23 01:06:14.467001: step: 104/529, loss: 0.3834657073020935
2023-01-23 01:06:15.696348: step: 108/529, loss: 0.054160404950380325
2023-01-23 01:06:16.871749: step: 112/529, loss: 0.029475783929228783
2023-01-23 01:06:18.037581: step: 116/529, loss: 0.15277805924415588
2023-01-23 01:06:19.241658: step: 120/529, loss: 0.12655220925807953
2023-01-23 01:06:20.478372: step: 124/529, loss: 0.05424446985125542
2023-01-23 01:06:21.670047: step: 128/529, loss: 0.020809365436434746
2023-01-23 01:06:22.844593: step: 132/529, loss: 0.0649077445268631
2023-01-23 01:06:24.020568: step: 136/529, loss: 0.052417658269405365
2023-01-23 01:06:25.247296: step: 140/529, loss: 0.026404570788145065
2023-01-23 01:06:26.408318: step: 144/529, loss: 0.11163578182458878
2023-01-23 01:06:27.606091: step: 148/529, loss: 0.06529025733470917
2023-01-23 01:06:28.796833: step: 152/529, loss: 0.29639601707458496
2023-01-23 01:06:29.976925: step: 156/529, loss: 0.07414093613624573
2023-01-23 01:06:31.144710: step: 160/529, loss: 0.0452701598405838
2023-01-23 01:06:32.390202: step: 164/529, loss: 0.1126430481672287
2023-01-23 01:06:33.558975: step: 168/529, loss: 0.06600398570299149
2023-01-23 01:06:34.726251: step: 172/529, loss: 0.05362091213464737
2023-01-23 01:06:35.920573: step: 176/529, loss: 0.14277419447898865
2023-01-23 01:06:37.109486: step: 180/529, loss: 0.0647861510515213
2023-01-23 01:06:38.318631: step: 184/529, loss: 0.07490501552820206
2023-01-23 01:06:39.527208: step: 188/529, loss: 0.08984088897705078
2023-01-23 01:06:40.758725: step: 192/529, loss: 0.2683661878108978
2023-01-23 01:06:41.991162: step: 196/529, loss: 0.04118680953979492
2023-01-23 01:06:43.172702: step: 200/529, loss: 0.12113752961158752
2023-01-23 01:06:44.407076: step: 204/529, loss: 0.13915586471557617
2023-01-23 01:06:45.609945: step: 208/529, loss: 0.3384190797805786
2023-01-23 01:06:46.782882: step: 212/529, loss: 0.028758669272065163
2023-01-23 01:06:47.970003: step: 216/529, loss: 0.03902549669146538
2023-01-23 01:06:49.179559: step: 220/529, loss: 0.05488548427820206
2023-01-23 01:06:50.372533: step: 224/529, loss: 0.12658318877220154
2023-01-23 01:06:51.533276: step: 228/529, loss: 0.019839953631162643
2023-01-23 01:06:52.772188: step: 232/529, loss: 0.19139966368675232
2023-01-23 01:06:53.958341: step: 236/529, loss: 0.08031488955020905
2023-01-23 01:06:55.155254: step: 240/529, loss: 0.2018882781267166
2023-01-23 01:06:56.343581: step: 244/529, loss: 0.04423055797815323
2023-01-23 01:06:57.564654: step: 248/529, loss: 0.0513455867767334
2023-01-23 01:06:58.770742: step: 252/529, loss: 0.05306091159582138
2023-01-23 01:06:59.984247: step: 256/529, loss: 0.07549601048231125
2023-01-23 01:07:01.199151: step: 260/529, loss: 0.27129754424095154
2023-01-23 01:07:02.429523: step: 264/529, loss: 0.34771308302879333
2023-01-23 01:07:03.644998: step: 268/529, loss: 0.04903598129749298
2023-01-23 01:07:04.812414: step: 272/529, loss: 0.03504333645105362
2023-01-23 01:07:06.012410: step: 276/529, loss: 0.133867084980011
2023-01-23 01:07:07.231169: step: 280/529, loss: 0.5706217885017395
2023-01-23 01:07:08.404066: step: 284/529, loss: 0.09402342140674591
2023-01-23 01:07:09.643797: step: 288/529, loss: 0.07075071334838867
2023-01-23 01:07:10.862308: step: 292/529, loss: 0.027519797906279564
2023-01-23 01:07:12.038571: step: 296/529, loss: 0.11909227818250656
2023-01-23 01:07:13.249386: step: 300/529, loss: 0.08387766033411026
2023-01-23 01:07:14.465374: step: 304/529, loss: 0.263397216796875
2023-01-23 01:07:15.654942: step: 308/529, loss: 0.020185183733701706
2023-01-23 01:07:16.862233: step: 312/529, loss: 0.03851518779993057
2023-01-23 01:07:18.020254: step: 316/529, loss: 0.056471921503543854
2023-01-23 01:07:19.201313: step: 320/529, loss: 0.14544352889060974
2023-01-23 01:07:20.372235: step: 324/529, loss: 0.04146280884742737
2023-01-23 01:07:21.577020: step: 328/529, loss: 0.03757286071777344
2023-01-23 01:07:22.787608: step: 332/529, loss: 0.17466364800930023
2023-01-23 01:07:23.980957: step: 336/529, loss: 0.17639651894569397
2023-01-23 01:07:25.158554: step: 340/529, loss: 0.1868622750043869
2023-01-23 01:07:26.359470: step: 344/529, loss: 0.14407387375831604
2023-01-23 01:07:27.538655: step: 348/529, loss: 0.026997661218047142
2023-01-23 01:07:28.793820: step: 352/529, loss: 0.21264734864234924
2023-01-23 01:07:29.978329: step: 356/529, loss: 0.1343534290790558
2023-01-23 01:07:31.134777: step: 360/529, loss: 0.23456978797912598
2023-01-23 01:07:32.288249: step: 364/529, loss: 0.04469137266278267
2023-01-23 01:07:33.486679: step: 368/529, loss: 0.009378815069794655
2023-01-23 01:07:34.707130: step: 372/529, loss: 0.24064597487449646
2023-01-23 01:07:35.943410: step: 376/529, loss: 0.0624295249581337
2023-01-23 01:07:37.144447: step: 380/529, loss: 0.49790287017822266
2023-01-23 01:07:38.409909: step: 384/529, loss: 0.07479248195886612
2023-01-23 01:07:39.622910: step: 388/529, loss: 0.08195725083351135
2023-01-23 01:07:40.811694: step: 392/529, loss: 0.07117652893066406
2023-01-23 01:07:41.989395: step: 396/529, loss: 0.01633152924478054
2023-01-23 01:07:43.234258: step: 400/529, loss: 0.02432394027709961
2023-01-23 01:07:44.451470: step: 404/529, loss: 0.04968385770916939
2023-01-23 01:07:45.607971: step: 408/529, loss: 0.0017351150745525956
2023-01-23 01:07:46.800772: step: 412/529, loss: 0.12085647881031036
2023-01-23 01:07:47.985478: step: 416/529, loss: 0.02084331586956978
2023-01-23 01:07:49.180939: step: 420/529, loss: 0.030452441424131393
2023-01-23 01:07:50.344745: step: 424/529, loss: 0.2088872790336609
2023-01-23 01:07:51.546121: step: 428/529, loss: 0.03261137008666992
2023-01-23 01:07:52.792323: step: 432/529, loss: 0.10151596367359161
2023-01-23 01:07:54.024204: step: 436/529, loss: 0.08158822357654572
2023-01-23 01:07:55.199473: step: 440/529, loss: 0.01679687574505806
2023-01-23 01:07:56.393348: step: 444/529, loss: 0.056443214416503906
2023-01-23 01:07:57.610772: step: 448/529, loss: 0.08200817555189133
2023-01-23 01:07:58.820980: step: 452/529, loss: 0.01014404371380806
2023-01-23 01:08:00.014663: step: 456/529, loss: 0.03626766428351402
2023-01-23 01:08:01.193310: step: 460/529, loss: 0.05161895602941513
2023-01-23 01:08:02.411308: step: 464/529, loss: 0.1402040421962738
2023-01-23 01:08:03.597407: step: 468/529, loss: 0.1648157238960266
2023-01-23 01:08:04.832706: step: 472/529, loss: 0.015301037579774857
2023-01-23 01:08:06.036438: step: 476/529, loss: 0.48414841294288635
2023-01-23 01:08:07.212520: step: 480/529, loss: 0.11328811943531036
2023-01-23 01:08:08.426156: step: 484/529, loss: 0.05878782272338867
2023-01-23 01:08:09.612626: step: 488/529, loss: 0.08626174926757812
2023-01-23 01:08:10.763283: step: 492/529, loss: 1.5473535060882568
2023-01-23 01:08:11.971937: step: 496/529, loss: 0.025368690490722656
2023-01-23 01:08:13.145777: step: 500/529, loss: 1.169867753982544
2023-01-23 01:08:14.370518: step: 504/529, loss: 0.5612404942512512
2023-01-23 01:08:15.610221: step: 508/529, loss: 0.09032583236694336
2023-01-23 01:08:16.806049: step: 512/529, loss: 0.03566131740808487
2023-01-23 01:08:17.951198: step: 516/529, loss: 0.014281749725341797
2023-01-23 01:08:19.138983: step: 520/529, loss: 0.006334591191262007
2023-01-23 01:08:20.342416: step: 524/529, loss: 0.06767146289348602
2023-01-23 01:08:21.518452: step: 528/529, loss: 0.13928499817848206
2023-01-23 01:08:22.824765: step: 532/529, loss: 0.10244293510913849
2023-01-23 01:08:24.010407: step: 536/529, loss: 0.019744396209716797
2023-01-23 01:08:25.172709: step: 540/529, loss: 0.036473989486694336
2023-01-23 01:08:26.349992: step: 544/529, loss: 0.09676847606897354
2023-01-23 01:08:27.562210: step: 548/529, loss: 0.10120868682861328
2023-01-23 01:08:28.815666: step: 552/529, loss: 0.13388314843177795
2023-01-23 01:08:30.006067: step: 556/529, loss: 0.014387417584657669
2023-01-23 01:08:31.187296: step: 560/529, loss: 0.10456142574548721
2023-01-23 01:08:32.400308: step: 564/529, loss: 0.13018293678760529
2023-01-23 01:08:33.559174: step: 568/529, loss: 0.2190563678741455
2023-01-23 01:08:34.749941: step: 572/529, loss: 0.09677457809448242
2023-01-23 01:08:35.949511: step: 576/529, loss: 0.129651740193367
2023-01-23 01:08:37.138880: step: 580/529, loss: 0.02453765831887722
2023-01-23 01:08:38.351638: step: 584/529, loss: 0.17237071692943573
2023-01-23 01:08:39.553841: step: 588/529, loss: 0.12866467237472534
2023-01-23 01:08:40.756077: step: 592/529, loss: 0.1281770020723343
2023-01-23 01:08:41.962415: step: 596/529, loss: 0.11868076771497726
2023-01-23 01:08:43.138763: step: 600/529, loss: 0.005851459689438343
2023-01-23 01:08:44.337128: step: 604/529, loss: 0.06365146487951279
2023-01-23 01:08:45.554504: step: 608/529, loss: 0.025307275354862213
2023-01-23 01:08:46.712339: step: 612/529, loss: 0.05476546287536621
2023-01-23 01:08:47.906348: step: 616/529, loss: 0.032396603375673294
2023-01-23 01:08:49.114504: step: 620/529, loss: 0.33760377764701843
2023-01-23 01:08:50.288534: step: 624/529, loss: 0.11570902168750763
2023-01-23 01:08:51.518840: step: 628/529, loss: 0.04723663628101349
2023-01-23 01:08:52.706357: step: 632/529, loss: 0.021453188732266426
2023-01-23 01:08:53.912951: step: 636/529, loss: 0.04021596908569336
2023-01-23 01:08:55.136114: step: 640/529, loss: 0.04281273111701012
2023-01-23 01:08:56.393013: step: 644/529, loss: 0.060198500752449036
2023-01-23 01:08:57.611393: step: 648/529, loss: 0.289010226726532
2023-01-23 01:08:58.812232: step: 652/529, loss: 0.05201692879199982
2023-01-23 01:09:00.013393: step: 656/529, loss: 0.04979963228106499
2023-01-23 01:09:01.216471: step: 660/529, loss: 0.8255425095558167
2023-01-23 01:09:02.436269: step: 664/529, loss: 0.025757886469364166
2023-01-23 01:09:03.613343: step: 668/529, loss: 0.1857587695121765
2023-01-23 01:09:04.822221: step: 672/529, loss: 0.0813564658164978
2023-01-23 01:09:06.029613: step: 676/529, loss: 0.34784936904907227
2023-01-23 01:09:07.258292: step: 680/529, loss: 0.0848187580704689
2023-01-23 01:09:08.423693: step: 684/529, loss: 0.06092672422528267
2023-01-23 01:09:09.658128: step: 688/529, loss: 1.097140908241272
2023-01-23 01:09:10.855473: step: 692/529, loss: 0.01776568964123726
2023-01-23 01:09:12.061422: step: 696/529, loss: 0.12852688133716583
2023-01-23 01:09:13.242031: step: 700/529, loss: 0.050512123852968216
2023-01-23 01:09:14.455003: step: 704/529, loss: 0.07791423797607422
2023-01-23 01:09:15.690636: step: 708/529, loss: 0.03385234251618385
2023-01-23 01:09:16.927427: step: 712/529, loss: 0.02483396604657173
2023-01-23 01:09:18.132319: step: 716/529, loss: 0.15987731516361237
2023-01-23 01:09:19.329781: step: 720/529, loss: 0.04217751324176788
2023-01-23 01:09:20.514291: step: 724/529, loss: 0.07350321114063263
2023-01-23 01:09:21.720464: step: 728/529, loss: 0.1448248028755188
2023-01-23 01:09:22.902933: step: 732/529, loss: 0.0734289139509201
2023-01-23 01:09:24.071108: step: 736/529, loss: 0.0869404524564743
2023-01-23 01:09:25.246265: step: 740/529, loss: 0.04873237758874893
2023-01-23 01:09:26.450185: step: 744/529, loss: 0.05395345389842987
2023-01-23 01:09:27.663700: step: 748/529, loss: 0.03888511657714844
2023-01-23 01:09:28.843562: step: 752/529, loss: 0.05777006223797798
2023-01-23 01:09:30.043341: step: 756/529, loss: 0.2934258282184601
2023-01-23 01:09:31.256500: step: 760/529, loss: 0.05800657346844673
2023-01-23 01:09:32.493422: step: 764/529, loss: 0.08716487884521484
2023-01-23 01:09:33.691935: step: 768/529, loss: 0.02558775059878826
2023-01-23 01:09:34.885664: step: 772/529, loss: 0.008740568533539772
2023-01-23 01:09:36.057712: step: 776/529, loss: 0.015002918429672718
2023-01-23 01:09:37.314504: step: 780/529, loss: 0.07867622375488281
2023-01-23 01:09:38.521386: step: 784/529, loss: 0.15878896415233612
2023-01-23 01:09:39.691928: step: 788/529, loss: 0.06344223022460938
2023-01-23 01:09:40.890724: step: 792/529, loss: 0.21710500121116638
2023-01-23 01:09:42.049103: step: 796/529, loss: 0.054468631744384766
2023-01-23 01:09:43.233985: step: 800/529, loss: 0.09668131172657013
2023-01-23 01:09:44.409686: step: 804/529, loss: 0.03438092768192291
2023-01-23 01:09:45.602468: step: 808/529, loss: 0.06402941048145294
2023-01-23 01:09:46.816423: step: 812/529, loss: 0.11263751983642578
2023-01-23 01:09:48.001731: step: 816/529, loss: 0.020251015201210976
2023-01-23 01:09:49.199419: step: 820/529, loss: 0.10936126857995987
2023-01-23 01:09:50.452523: step: 824/529, loss: 0.019695425406098366
2023-01-23 01:09:51.637012: step: 828/529, loss: 0.05466928705573082
2023-01-23 01:09:52.803996: step: 832/529, loss: 0.16966834664344788
2023-01-23 01:09:53.997699: step: 836/529, loss: 0.12107186019420624
2023-01-23 01:09:55.165625: step: 840/529, loss: 0.03607664257287979
2023-01-23 01:09:56.339125: step: 844/529, loss: 0.10125122219324112
2023-01-23 01:09:57.526920: step: 848/529, loss: 0.015216827392578125
2023-01-23 01:09:58.697322: step: 852/529, loss: 0.08168697357177734
2023-01-23 01:09:59.886405: step: 856/529, loss: 0.06559620052576065
2023-01-23 01:10:01.082360: step: 860/529, loss: 0.0023474693298339844
2023-01-23 01:10:02.282569: step: 864/529, loss: 0.09548597037792206
2023-01-23 01:10:03.465743: step: 868/529, loss: 0.02702934667468071
2023-01-23 01:10:04.671341: step: 872/529, loss: 0.043364908546209335
2023-01-23 01:10:05.881292: step: 876/529, loss: 0.033113572746515274
2023-01-23 01:10:07.114929: step: 880/529, loss: 0.04623126983642578
2023-01-23 01:10:08.309507: step: 884/529, loss: 0.06952495872974396
2023-01-23 01:10:09.445354: step: 888/529, loss: 0.054462432861328125
2023-01-23 01:10:10.654693: step: 892/529, loss: 0.23846206068992615
2023-01-23 01:10:11.839984: step: 896/529, loss: 0.03779583051800728
2023-01-23 01:10:13.014564: step: 900/529, loss: 0.12914705276489258
2023-01-23 01:10:14.213398: step: 904/529, loss: 0.06119070202112198
2023-01-23 01:10:15.383940: step: 908/529, loss: 0.002698421711102128
2023-01-23 01:10:16.608826: step: 912/529, loss: 0.38810914754867554
2023-01-23 01:10:17.827245: step: 916/529, loss: 0.04940776899456978
2023-01-23 01:10:19.003671: step: 920/529, loss: 0.03824205324053764
2023-01-23 01:10:20.211028: step: 924/529, loss: 0.06851714849472046
2023-01-23 01:10:21.417510: step: 928/529, loss: 0.050595857203006744
2023-01-23 01:10:22.659541: step: 932/529, loss: 0.12183570861816406
2023-01-23 01:10:23.821692: step: 936/529, loss: 0.06306600570678711
2023-01-23 01:10:24.997390: step: 940/529, loss: 0.37963250279426575
2023-01-23 01:10:26.263036: step: 944/529, loss: 0.12578324973583221
2023-01-23 01:10:27.438383: step: 948/529, loss: 0.034774210304021835
2023-01-23 01:10:28.616886: step: 952/529, loss: 0.0017559052212163806
2023-01-23 01:10:29.782001: step: 956/529, loss: 0.0008977412944659591
2023-01-23 01:10:31.031268: step: 960/529, loss: 0.037227824330329895
2023-01-23 01:10:32.234203: step: 964/529, loss: 0.06928663700819016
2023-01-23 01:10:33.400269: step: 968/529, loss: 0.04085521399974823
2023-01-23 01:10:34.601291: step: 972/529, loss: 0.026029014959931374
2023-01-23 01:10:35.807039: step: 976/529, loss: 0.6921762228012085
2023-01-23 01:10:36.990856: step: 980/529, loss: 0.03453264385461807
2023-01-23 01:10:38.194970: step: 984/529, loss: 0.0025396347045898438
2023-01-23 01:10:39.415425: step: 988/529, loss: 0.14246463775634766
2023-01-23 01:10:40.636288: step: 992/529, loss: 0.1719975471496582
2023-01-23 01:10:41.805109: step: 996/529, loss: 0.012391663156449795
2023-01-23 01:10:43.041912: step: 1000/529, loss: 0.5715689659118652
2023-01-23 01:10:44.245786: step: 1004/529, loss: 0.2206006944179535
2023-01-23 01:10:45.442169: step: 1008/529, loss: 0.05662384256720543
2023-01-23 01:10:46.647984: step: 1012/529, loss: 0.08283748477697372
2023-01-23 01:10:47.812743: step: 1016/529, loss: 0.13019829988479614
2023-01-23 01:10:48.995891: step: 1020/529, loss: 0.04871978610754013
2023-01-23 01:10:50.179878: step: 1024/529, loss: 0.009431696496903896
2023-01-23 01:10:51.361831: step: 1028/529, loss: 0.09745875000953674
2023-01-23 01:10:52.570819: step: 1032/529, loss: 3.7824597358703613
2023-01-23 01:10:53.818971: step: 1036/529, loss: 0.05119842663407326
2023-01-23 01:10:55.009192: step: 1040/529, loss: 0.05995120853185654
2023-01-23 01:10:56.233778: step: 1044/529, loss: 0.22861547768115997
2023-01-23 01:10:57.416415: step: 1048/529, loss: 0.11673326790332794
2023-01-23 01:10:58.621961: step: 1052/529, loss: 0.02841949462890625
2023-01-23 01:10:59.818868: step: 1056/529, loss: 0.06642589718103409
2023-01-23 01:11:01.014279: step: 1060/529, loss: 0.08536510914564133
2023-01-23 01:11:02.208737: step: 1064/529, loss: 0.057392265647649765
2023-01-23 01:11:03.377745: step: 1068/529, loss: 0.018297864124178886
2023-01-23 01:11:04.582855: step: 1072/529, loss: 0.16273346543312073
2023-01-23 01:11:05.739485: step: 1076/529, loss: 0.03767561912536621
2023-01-23 01:11:06.913488: step: 1080/529, loss: 0.06970615684986115
2023-01-23 01:11:08.086062: step: 1084/529, loss: 0.0776124969124794
2023-01-23 01:11:09.251326: step: 1088/529, loss: 0.7339916229248047
2023-01-23 01:11:10.514523: step: 1092/529, loss: 0.03493137285113335
2023-01-23 01:11:11.762072: step: 1096/529, loss: 0.1935720443725586
2023-01-23 01:11:12.994138: step: 1100/529, loss: 0.04453315585851669
2023-01-23 01:11:14.177914: step: 1104/529, loss: 0.07666020095348358
2023-01-23 01:11:15.361387: step: 1108/529, loss: 0.042481180280447006
2023-01-23 01:11:16.594460: step: 1112/529, loss: 0.032961394637823105
2023-01-23 01:11:17.797759: step: 1116/529, loss: 0.051497265696525574
2023-01-23 01:11:18.997084: step: 1120/529, loss: 0.058836936950683594
2023-01-23 01:11:20.255592: step: 1124/529, loss: 0.055160000920295715
2023-01-23 01:11:21.432310: step: 1128/529, loss: 0.10562935471534729
2023-01-23 01:11:22.629737: step: 1132/529, loss: 0.0020885944832116365
2023-01-23 01:11:23.844340: step: 1136/529, loss: 0.03945513069629669
2023-01-23 01:11:25.046354: step: 1140/529, loss: 0.022968102246522903
2023-01-23 01:11:26.202610: step: 1144/529, loss: 0.11372071504592896
2023-01-23 01:11:27.374115: step: 1148/529, loss: 0.11726979911327362
2023-01-23 01:11:28.586967: step: 1152/529, loss: 0.008947182446718216
2023-01-23 01:11:29.767748: step: 1156/529, loss: 0.035971928387880325
2023-01-23 01:11:31.011579: step: 1160/529, loss: 0.11392173916101456
2023-01-23 01:11:32.197219: step: 1164/529, loss: 0.05277242511510849
2023-01-23 01:11:33.390081: step: 1168/529, loss: 0.03427296131849289
2023-01-23 01:11:34.592296: step: 1172/529, loss: 0.13313226401805878
2023-01-23 01:11:35.848252: step: 1176/529, loss: 0.045962050557136536
2023-01-23 01:11:37.076404: step: 1180/529, loss: 0.10334751754999161
2023-01-23 01:11:38.256878: step: 1184/529, loss: 0.028791427612304688
2023-01-23 01:11:39.456553: step: 1188/529, loss: 0.2083265483379364
2023-01-23 01:11:40.636423: step: 1192/529, loss: 0.044665709137916565
2023-01-23 01:11:41.820555: step: 1196/529, loss: 0.12532596290111542
2023-01-23 01:11:43.053069: step: 1200/529, loss: 0.06838683784008026
2023-01-23 01:11:44.243926: step: 1204/529, loss: 0.03884610906243324
2023-01-23 01:11:45.448455: step: 1208/529, loss: 0.026630450040102005
2023-01-23 01:11:46.664880: step: 1212/529, loss: 0.03295183181762695
2023-01-23 01:11:47.898701: step: 1216/529, loss: 0.1562710702419281
2023-01-23 01:11:49.147458: step: 1220/529, loss: 0.09037284553050995
2023-01-23 01:11:50.421958: step: 1224/529, loss: 0.1379532814025879
2023-01-23 01:11:51.595569: step: 1228/529, loss: 0.03228042274713516
2023-01-23 01:11:52.782380: step: 1232/529, loss: 0.03690236434340477
2023-01-23 01:11:53.999676: step: 1236/529, loss: 0.029663560912013054
2023-01-23 01:11:55.223196: step: 1240/529, loss: 0.07394389808177948
2023-01-23 01:11:56.394187: step: 1244/529, loss: 0.821942150592804
2023-01-23 01:11:57.645905: step: 1248/529, loss: 0.047072794288396835
2023-01-23 01:11:58.890779: step: 1252/529, loss: 0.1581771820783615
2023-01-23 01:12:00.130287: step: 1256/529, loss: 0.04433155059814453
2023-01-23 01:12:01.345096: step: 1260/529, loss: 0.023726653307676315
2023-01-23 01:12:02.563968: step: 1264/529, loss: 0.10929131507873535
2023-01-23 01:12:03.760071: step: 1268/529, loss: 0.021021651104092598
2023-01-23 01:12:04.956371: step: 1272/529, loss: 0.12015724182128906
2023-01-23 01:12:06.170345: step: 1276/529, loss: 0.1456432342529297
2023-01-23 01:12:07.410185: step: 1280/529, loss: 0.2869764268398285
2023-01-23 01:12:08.588016: step: 1284/529, loss: 0.06210336834192276
2023-01-23 01:12:09.759188: step: 1288/529, loss: 0.4272199869155884
2023-01-23 01:12:10.976164: step: 1292/529, loss: 0.08444433659315109
2023-01-23 01:12:12.208067: step: 1296/529, loss: 0.05749301612377167
2023-01-23 01:12:13.439651: step: 1300/529, loss: 0.10277929902076721
2023-01-23 01:12:14.584678: step: 1304/529, loss: 0.02456817775964737
2023-01-23 01:12:15.771415: step: 1308/529, loss: 0.012319850735366344
2023-01-23 01:12:16.956015: step: 1312/529, loss: 0.053867489099502563
2023-01-23 01:12:18.136340: step: 1316/529, loss: 0.1931808590888977
2023-01-23 01:12:19.339276: step: 1320/529, loss: 0.042501356452703476
2023-01-23 01:12:20.510809: step: 1324/529, loss: 0.030437849462032318
2023-01-23 01:12:21.722186: step: 1328/529, loss: 0.018532896414399147
2023-01-23 01:12:22.872842: step: 1332/529, loss: 0.04071979224681854
2023-01-23 01:12:24.062197: step: 1336/529, loss: 0.03715820237994194
2023-01-23 01:12:25.297631: step: 1340/529, loss: 0.12394581735134125
2023-01-23 01:12:26.483677: step: 1344/529, loss: 0.2526525557041168
2023-01-23 01:12:27.688029: step: 1348/529, loss: 0.10094404220581055
2023-01-23 01:12:28.880025: step: 1352/529, loss: 0.17400990426540375
2023-01-23 01:12:30.057777: step: 1356/529, loss: 0.1548875868320465
2023-01-23 01:12:31.240710: step: 1360/529, loss: 0.06449642032384872
2023-01-23 01:12:32.421400: step: 1364/529, loss: 0.16042232513427734
2023-01-23 01:12:33.617046: step: 1368/529, loss: 0.05946556478738785
2023-01-23 01:12:34.837529: step: 1372/529, loss: 0.05468807369470596
2023-01-23 01:12:36.010623: step: 1376/529, loss: 0.060177993029356
2023-01-23 01:12:37.209316: step: 1380/529, loss: 0.3314034342765808
2023-01-23 01:12:38.463804: step: 1384/529, loss: 0.10789716988801956
2023-01-23 01:12:39.661215: step: 1388/529, loss: 0.013530587777495384
2023-01-23 01:12:40.877803: step: 1392/529, loss: 0.02457904815673828
2023-01-23 01:12:42.029834: step: 1396/529, loss: 0.15012827515602112
2023-01-23 01:12:43.301086: step: 1400/529, loss: 0.15897050499916077
2023-01-23 01:12:44.499654: step: 1404/529, loss: 0.09443187713623047
2023-01-23 01:12:45.673841: step: 1408/529, loss: 0.06389837712049484
2023-01-23 01:12:46.851343: step: 1412/529, loss: 0.0392460823059082
2023-01-23 01:12:48.050403: step: 1416/529, loss: 0.03802771493792534
2023-01-23 01:12:49.211057: step: 1420/529, loss: 0.017196549102663994
2023-01-23 01:12:50.382026: step: 1424/529, loss: 0.0019979476928710938
2023-01-23 01:12:51.580752: step: 1428/529, loss: 0.05449257045984268
2023-01-23 01:12:52.822760: step: 1432/529, loss: 0.10396003723144531
2023-01-23 01:12:53.999212: step: 1436/529, loss: 0.11388321220874786
2023-01-23 01:12:55.202339: step: 1440/529, loss: 0.03711528703570366
2023-01-23 01:12:56.389516: step: 1444/529, loss: 0.39723843336105347
2023-01-23 01:12:57.639462: step: 1448/529, loss: 0.5783222317695618
2023-01-23 01:12:58.848115: step: 1452/529, loss: 0.27517127990722656
2023-01-23 01:13:00.047593: step: 1456/529, loss: 0.03254413604736328
2023-01-23 01:13:01.284817: step: 1460/529, loss: 0.11783038079738617
2023-01-23 01:13:02.461738: step: 1464/529, loss: 0.06386937946081161
2023-01-23 01:13:03.667569: step: 1468/529, loss: 0.0928686112165451
2023-01-23 01:13:04.833316: step: 1472/529, loss: 0.07659082859754562
2023-01-23 01:13:05.986535: step: 1476/529, loss: 0.1755451112985611
2023-01-23 01:13:07.179015: step: 1480/529, loss: 0.23981857299804688
2023-01-23 01:13:08.343391: step: 1484/529, loss: 0.023630524054169655
2023-01-23 01:13:09.511425: step: 1488/529, loss: 0.134020134806633
2023-01-23 01:13:10.747171: step: 1492/529, loss: 0.05197105556726456
2023-01-23 01:13:11.958019: step: 1496/529, loss: 0.025871945545077324
2023-01-23 01:13:13.150457: step: 1500/529, loss: 0.12018966674804688
2023-01-23 01:13:14.338492: step: 1504/529, loss: 0.04415726661682129
2023-01-23 01:13:15.516926: step: 1508/529, loss: 0.020696640014648438
2023-01-23 01:13:16.729999: step: 1512/529, loss: 0.1421644240617752
2023-01-23 01:13:17.900466: step: 1516/529, loss: 0.3093307614326477
2023-01-23 01:13:19.154339: step: 1520/529, loss: 0.03205394744873047
2023-01-23 01:13:20.374270: step: 1524/529, loss: 0.03148508071899414
2023-01-23 01:13:21.555899: step: 1528/529, loss: 0.05031432956457138
2023-01-23 01:13:22.750675: step: 1532/529, loss: 0.05000114440917969
2023-01-23 01:13:23.946493: step: 1536/529, loss: 0.02052149921655655
2023-01-23 01:13:25.128497: step: 1540/529, loss: 0.044590190052986145
2023-01-23 01:13:26.331929: step: 1544/529, loss: 0.06557836383581161
2023-01-23 01:13:27.491005: step: 1548/529, loss: 0.07163619995117188
2023-01-23 01:13:28.655247: step: 1552/529, loss: 0.16393285989761353
2023-01-23 01:13:29.867822: step: 1556/529, loss: 0.09536054730415344
2023-01-23 01:13:31.112128: step: 1560/529, loss: 0.2355089783668518
2023-01-23 01:13:32.294810: step: 1564/529, loss: 0.27672088146209717
2023-01-23 01:13:33.516321: step: 1568/529, loss: 0.08388538658618927
2023-01-23 01:13:34.723095: step: 1572/529, loss: 0.1348729133605957
2023-01-23 01:13:35.936479: step: 1576/529, loss: 0.06362266838550568
2023-01-23 01:13:37.096441: step: 1580/529, loss: 0.07376833260059357
2023-01-23 01:13:38.320526: step: 1584/529, loss: 0.1292678862810135
2023-01-23 01:13:39.545156: step: 1588/529, loss: 0.05223522335290909
2023-01-23 01:13:40.770149: step: 1592/529, loss: 0.037822578102350235
2023-01-23 01:13:41.969303: step: 1596/529, loss: 0.05437326431274414
2023-01-23 01:13:43.178634: step: 1600/529, loss: 0.10252627730369568
2023-01-23 01:13:44.352853: step: 1604/529, loss: 0.03990483283996582
2023-01-23 01:13:45.561706: step: 1608/529, loss: 0.05997011438012123
2023-01-23 01:13:46.773537: step: 1612/529, loss: 0.010653710924088955
2023-01-23 01:13:47.981357: step: 1616/529, loss: 0.12889929115772247
2023-01-23 01:13:49.184075: step: 1620/529, loss: 0.03674058988690376
2023-01-23 01:13:50.423792: step: 1624/529, loss: 0.09569883346557617
2023-01-23 01:13:51.621876: step: 1628/529, loss: 0.026285553351044655
2023-01-23 01:13:52.835100: step: 1632/529, loss: 0.07412166148424149
2023-01-23 01:13:53.993867: step: 1636/529, loss: 0.09094281494617462
2023-01-23 01:13:55.173145: step: 1640/529, loss: 0.08064451068639755
2023-01-23 01:13:56.368822: step: 1644/529, loss: 0.07012634724378586
2023-01-23 01:13:57.551971: step: 1648/529, loss: 0.009239577688276768
2023-01-23 01:13:58.841486: step: 1652/529, loss: 1.6439318656921387
2023-01-23 01:14:00.055832: step: 1656/529, loss: 0.07777824997901917
2023-01-23 01:14:01.226146: step: 1660/529, loss: 0.01565084606409073
2023-01-23 01:14:02.422324: step: 1664/529, loss: 0.0075900075025856495
2023-01-23 01:14:03.620661: step: 1668/529, loss: 0.028315259143710136
2023-01-23 01:14:04.850606: step: 1672/529, loss: 0.10052014142274857
2023-01-23 01:14:06.040264: step: 1676/529, loss: 0.0331057533621788
2023-01-23 01:14:07.232253: step: 1680/529, loss: 0.04570808634161949
2023-01-23 01:14:08.482748: step: 1684/529, loss: 0.09786806255578995
2023-01-23 01:14:09.626998: step: 1688/529, loss: 1.1208122968673706
2023-01-23 01:14:10.856198: step: 1692/529, loss: 0.012130022048950195
2023-01-23 01:14:12.068058: step: 1696/529, loss: 0.05638742446899414
2023-01-23 01:14:13.253752: step: 1700/529, loss: 0.03684711456298828
2023-01-23 01:14:14.456639: step: 1704/529, loss: 0.02162313461303711
2023-01-23 01:14:15.647829: step: 1708/529, loss: 0.07683763653039932
2023-01-23 01:14:16.850051: step: 1712/529, loss: 0.2494373321533203
2023-01-23 01:14:18.037392: step: 1716/529, loss: 0.13256961107254028
2023-01-23 01:14:19.263354: step: 1720/529, loss: 0.02953662909567356
2023-01-23 01:14:20.441107: step: 1724/529, loss: 0.09087281674146652
2023-01-23 01:14:21.667284: step: 1728/529, loss: 0.10782899707555771
2023-01-23 01:14:22.861607: step: 1732/529, loss: 0.006664848420768976
2023-01-23 01:14:24.059183: step: 1736/529, loss: 0.016600513830780983
2023-01-23 01:14:25.277115: step: 1740/529, loss: 0.15614071488380432
2023-01-23 01:14:26.465329: step: 1744/529, loss: 0.5339058637619019
2023-01-23 01:14:27.655426: step: 1748/529, loss: 0.15408745408058167
2023-01-23 01:14:28.883066: step: 1752/529, loss: 0.12845849990844727
2023-01-23 01:14:30.070578: step: 1756/529, loss: 0.040496826171875
2023-01-23 01:14:31.261635: step: 1760/529, loss: 0.04293489456176758
2023-01-23 01:14:32.470130: step: 1764/529, loss: 0.05974116548895836
2023-01-23 01:14:33.678316: step: 1768/529, loss: 0.1178036704659462
2023-01-23 01:14:34.899093: step: 1772/529, loss: 0.05413856357336044
2023-01-23 01:14:36.097735: step: 1776/529, loss: 0.013603448867797852
2023-01-23 01:14:37.321803: step: 1780/529, loss: 0.11620178818702698
2023-01-23 01:14:38.487342: step: 1784/529, loss: 0.04439087212085724
2023-01-23 01:14:39.659420: step: 1788/529, loss: 0.17102183401584625
2023-01-23 01:14:40.841820: step: 1792/529, loss: 0.00329933175817132
2023-01-23 01:14:42.052876: step: 1796/529, loss: 0.051810551434755325
2023-01-23 01:14:43.234267: step: 1800/529, loss: 0.1280687302350998
2023-01-23 01:14:44.414898: step: 1804/529, loss: 0.09831380844116211
2023-01-23 01:14:45.601479: step: 1808/529, loss: 0.03563718870282173
2023-01-23 01:14:46.805530: step: 1812/529, loss: 0.08889111876487732
2023-01-23 01:14:48.025487: step: 1816/529, loss: 0.22061900794506073
2023-01-23 01:14:49.188459: step: 1820/529, loss: 0.04422557353973389
2023-01-23 01:14:50.389306: step: 1824/529, loss: 0.0134124755859375
2023-01-23 01:14:51.560478: step: 1828/529, loss: 0.9438523650169373
2023-01-23 01:14:52.758798: step: 1832/529, loss: 0.030322838574647903
2023-01-23 01:14:53.946924: step: 1836/529, loss: 0.01393957156687975
2023-01-23 01:14:55.129483: step: 1840/529, loss: 0.8380979299545288
2023-01-23 01:14:56.319495: step: 1844/529, loss: 0.1119009256362915
2023-01-23 01:14:57.488267: step: 1848/529, loss: 0.10191259533166885
2023-01-23 01:14:58.713152: step: 1852/529, loss: 0.22992515563964844
2023-01-23 01:14:59.880784: step: 1856/529, loss: 0.03986644744873047
2023-01-23 01:15:01.062084: step: 1860/529, loss: 0.055548667907714844
2023-01-23 01:15:02.252020: step: 1864/529, loss: 0.10059471428394318
2023-01-23 01:15:03.447584: step: 1868/529, loss: 0.0764986127614975
2023-01-23 01:15:04.613035: step: 1872/529, loss: 0.11834988743066788
2023-01-23 01:15:05.790140: step: 1876/529, loss: 0.0778445228934288
2023-01-23 01:15:07.061790: step: 1880/529, loss: 0.09871644526720047
2023-01-23 01:15:08.232749: step: 1884/529, loss: 0.24607856571674347
2023-01-23 01:15:09.496936: step: 1888/529, loss: 0.09327040612697601
2023-01-23 01:15:10.678784: step: 1892/529, loss: 0.05929937586188316
2023-01-23 01:15:11.877815: step: 1896/529, loss: 0.15408927202224731
2023-01-23 01:15:13.084492: step: 1900/529, loss: 0.07512674480676651
2023-01-23 01:15:14.302425: step: 1904/529, loss: 0.12093200534582138
2023-01-23 01:15:15.460564: step: 1908/529, loss: 0.036788176745176315
2023-01-23 01:15:16.620502: step: 1912/529, loss: 0.03445596620440483
2023-01-23 01:15:17.799612: step: 1916/529, loss: 0.04038117080926895
2023-01-23 01:15:19.022465: step: 1920/529, loss: 0.04441061243414879
2023-01-23 01:15:20.185105: step: 1924/529, loss: 0.18578501045703888
2023-01-23 01:15:21.348221: step: 1928/529, loss: 0.023291492834687233
2023-01-23 01:15:22.552431: step: 1932/529, loss: 0.01905536837875843
2023-01-23 01:15:23.774811: step: 1936/529, loss: 0.07259535789489746
2023-01-23 01:15:24.977140: step: 1940/529, loss: 0.07072114944458008
2023-01-23 01:15:26.216194: step: 1944/529, loss: 0.12202244251966476
2023-01-23 01:15:27.424244: step: 1948/529, loss: 0.021721171215176582
2023-01-23 01:15:28.633593: step: 1952/529, loss: 0.021088410168886185
2023-01-23 01:15:29.782036: step: 1956/529, loss: 0.14635547995567322
2023-01-23 01:15:30.968580: step: 1960/529, loss: 0.021374035626649857
2023-01-23 01:15:32.157403: step: 1964/529, loss: 0.03525595739483833
2023-01-23 01:15:33.350920: step: 1968/529, loss: 0.1727035492658615
2023-01-23 01:15:34.568419: step: 1972/529, loss: 0.0465879961848259
2023-01-23 01:15:35.805012: step: 1976/529, loss: 0.027051258832216263
2023-01-23 01:15:37.001667: step: 1980/529, loss: 0.015650654211640358
2023-01-23 01:15:38.217077: step: 1984/529, loss: 0.028936101123690605
2023-01-23 01:15:39.464814: step: 1988/529, loss: 0.07564010471105576
2023-01-23 01:15:40.684584: step: 1992/529, loss: 0.017669105902314186
2023-01-23 01:15:41.874211: step: 1996/529, loss: 0.11853981018066406
2023-01-23 01:15:43.061829: step: 2000/529, loss: 0.006445837207138538
2023-01-23 01:15:44.224146: step: 2004/529, loss: 0.043023206293582916
2023-01-23 01:15:45.419019: step: 2008/529, loss: 0.0902436301112175
2023-01-23 01:15:46.634571: step: 2012/529, loss: 0.03726549446582794
2023-01-23 01:15:47.811530: step: 2016/529, loss: 0.0626346617937088
2023-01-23 01:15:49.050069: step: 2020/529, loss: 0.027577782049775124
2023-01-23 01:15:50.214167: step: 2024/529, loss: 0.13318586349487305
2023-01-23 01:15:51.433044: step: 2028/529, loss: 0.5146718621253967
2023-01-23 01:15:52.656159: step: 2032/529, loss: 0.12210503220558167
2023-01-23 01:15:53.867810: step: 2036/529, loss: 0.08855452388525009
2023-01-23 01:15:55.088401: step: 2040/529, loss: 0.05148293823003769
2023-01-23 01:15:56.300591: step: 2044/529, loss: 0.07322102040052414
2023-01-23 01:15:57.488729: step: 2048/529, loss: 0.07995501160621643
2023-01-23 01:15:58.691686: step: 2052/529, loss: 0.004712438676506281
2023-01-23 01:15:59.882231: step: 2056/529, loss: 0.22446632385253906
2023-01-23 01:16:01.091988: step: 2060/529, loss: 0.05641670525074005
2023-01-23 01:16:02.284674: step: 2064/529, loss: 0.0193037036806345
2023-01-23 01:16:03.452738: step: 2068/529, loss: 0.11494479328393936
2023-01-23 01:16:04.616459: step: 2072/529, loss: 0.02848968468606472
2023-01-23 01:16:05.821576: step: 2076/529, loss: 0.09234781563282013
2023-01-23 01:16:07.033469: step: 2080/529, loss: 0.32560861110687256
2023-01-23 01:16:08.257183: step: 2084/529, loss: 0.15645551681518555
2023-01-23 01:16:09.491837: step: 2088/529, loss: 0.035015396773815155
2023-01-23 01:16:10.686336: step: 2092/529, loss: 0.04155368730425835
2023-01-23 01:16:11.895684: step: 2096/529, loss: 0.17655391991138458
2023-01-23 01:16:13.111959: step: 2100/529, loss: 0.21046391129493713
2023-01-23 01:16:14.301521: step: 2104/529, loss: 0.006680441088974476
2023-01-23 01:16:15.477970: step: 2108/529, loss: 0.15230941772460938
2023-01-23 01:16:16.676547: step: 2112/529, loss: 0.040708351880311966
2023-01-23 01:16:17.927641: step: 2116/529, loss: 0.11756172776222229
==================================================
Loss: 0.121
--------------------
Dev: {'event': {'p': 0.5754245754245755, 'r': 0.7669773635153129, 'f1': 0.6575342465753425}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6193181818181818, 'r': 0.7837028160575195, 'f1': 0.6918804549061094}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5529411764705883, 'r': 0.8703703703703703, 'f1': 0.6762589928057553}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.5178571428571429, 'r': 0.4603174603174603, 'f1': 0.48739495798319327}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.47619047619047616, 'r': 0.5555555555555556, 'f1': 0.5128205128205129}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877106045589693, 'r': 0.7896138482023968, 'f1': 0.6738636363636363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Korean: {'event': {'p': 0.6253574833174452, 'r': 0.7860994607549431, 'f1': 0.6965755242898859}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Korean: {'event': {'p': 0.6271186440677966, 'r': 0.5873015873015873, 'f1': 0.6065573770491803}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 01:17:01.941492: step: 4/529, loss: 0.13319548964500427
2023-01-23 01:17:03.115726: step: 8/529, loss: 0.018059730529785156
2023-01-23 01:17:04.332624: step: 12/529, loss: 0.06347141414880753
2023-01-23 01:17:05.525858: step: 16/529, loss: 0.7278034687042236
2023-01-23 01:17:06.723022: step: 20/529, loss: 0.03369617462158203
2023-01-23 01:17:07.905488: step: 24/529, loss: 0.004032040014863014
2023-01-23 01:17:09.097359: step: 28/529, loss: 0.021892739459872246
2023-01-23 01:17:10.327351: step: 32/529, loss: 0.548066258430481
2023-01-23 01:17:11.516894: step: 36/529, loss: 0.049533747136592865
2023-01-23 01:17:12.700928: step: 40/529, loss: 0.4965149760246277
2023-01-23 01:17:13.930019: step: 44/529, loss: 0.06300202012062073
2023-01-23 01:17:15.094806: step: 48/529, loss: 0.015262365341186523
2023-01-23 01:17:16.329729: step: 52/529, loss: 0.08438215404748917
2023-01-23 01:17:17.547776: step: 56/529, loss: 0.06253781914710999
2023-01-23 01:17:18.700803: step: 60/529, loss: 0.025278473272919655
2023-01-23 01:17:19.878062: step: 64/529, loss: 0.07637815922498703
2023-01-23 01:17:21.036159: step: 68/529, loss: 0.017382239922881126
2023-01-23 01:17:22.250186: step: 72/529, loss: 0.04782142862677574
2023-01-23 01:17:23.452445: step: 76/529, loss: 0.03657874837517738
2023-01-23 01:17:24.636659: step: 80/529, loss: 0.05125589668750763
2023-01-23 01:17:25.830020: step: 84/529, loss: 0.08427486568689346
2023-01-23 01:17:27.026012: step: 88/529, loss: 0.05002489313483238
2023-01-23 01:17:28.193928: step: 92/529, loss: 0.053534530103206635
2023-01-23 01:17:29.426951: step: 96/529, loss: 0.013772344216704369
2023-01-23 01:17:30.597783: step: 100/529, loss: 0.14294010400772095
2023-01-23 01:17:31.780177: step: 104/529, loss: 0.03716163709759712
2023-01-23 01:17:32.997897: step: 108/529, loss: 0.07859639823436737
2023-01-23 01:17:34.135151: step: 112/529, loss: 0.04225420951843262
2023-01-23 01:17:35.367741: step: 116/529, loss: 0.04295364022254944
2023-01-23 01:17:36.565517: step: 120/529, loss: 0.010546302422881126
2023-01-23 01:17:37.734133: step: 124/529, loss: 0.0484435111284256
2023-01-23 01:17:38.952014: step: 128/529, loss: 0.0320165641605854
2023-01-23 01:17:40.154420: step: 132/529, loss: 0.05277876928448677
2023-01-23 01:17:41.328579: step: 136/529, loss: 0.0038738250732421875
2023-01-23 01:17:42.521956: step: 140/529, loss: 1.21299147605896
2023-01-23 01:17:43.736292: step: 144/529, loss: 0.05450868606567383
2023-01-23 01:17:44.941257: step: 148/529, loss: 0.053360890597105026
2023-01-23 01:17:46.143907: step: 152/529, loss: 0.0466761589050293
2023-01-23 01:17:47.322034: step: 156/529, loss: 0.03779389336705208
2023-01-23 01:17:48.516935: step: 160/529, loss: 0.31127986311912537
2023-01-23 01:17:49.712813: step: 164/529, loss: 0.009652900509536266
2023-01-23 01:17:50.911487: step: 168/529, loss: 0.025745011866092682
2023-01-23 01:17:52.118260: step: 172/529, loss: 1.607777714729309
2023-01-23 01:17:53.276191: step: 176/529, loss: 0.033055976033210754
2023-01-23 01:17:54.484062: step: 180/529, loss: 0.03438835218548775
2023-01-23 01:17:55.671735: step: 184/529, loss: 0.03239021450281143
2023-01-23 01:17:56.879645: step: 188/529, loss: 0.0017548560863360763
2023-01-23 01:17:58.080413: step: 192/529, loss: 0.07959385216236115
2023-01-23 01:17:59.315632: step: 196/529, loss: 0.05726489797234535
2023-01-23 01:18:00.510420: step: 200/529, loss: 0.05039789527654648
2023-01-23 01:18:01.722889: step: 204/529, loss: 0.05500612035393715
2023-01-23 01:18:02.923552: step: 208/529, loss: 0.02331404760479927
2023-01-23 01:18:04.204736: step: 212/529, loss: 0.09467992931604385
2023-01-23 01:18:05.405833: step: 216/529, loss: 0.02184772491455078
2023-01-23 01:18:06.604406: step: 220/529, loss: 0.04513363912701607
2023-01-23 01:18:07.841093: step: 224/529, loss: 0.029505157843232155
2023-01-23 01:18:09.027017: step: 228/529, loss: 0.05676870420575142
2023-01-23 01:18:10.276581: step: 232/529, loss: 0.1100500151515007
2023-01-23 01:18:11.478054: step: 236/529, loss: 0.007414055056869984
2023-01-23 01:18:12.674291: step: 240/529, loss: 0.05604495853185654
2023-01-23 01:18:13.898654: step: 244/529, loss: 0.2492111325263977
2023-01-23 01:18:15.089899: step: 248/529, loss: 0.17275163531303406
2023-01-23 01:18:16.274922: step: 252/529, loss: 0.03466100990772247
2023-01-23 01:18:17.441953: step: 256/529, loss: 0.0047782897017896175
2023-01-23 01:18:18.634599: step: 260/529, loss: 0.0862194076180458
2023-01-23 01:18:19.797316: step: 264/529, loss: 0.015404606238007545
2023-01-23 01:18:20.989332: step: 268/529, loss: 0.012108184397220612
2023-01-23 01:18:22.182355: step: 272/529, loss: 0.002204513642936945
2023-01-23 01:18:23.347214: step: 276/529, loss: 0.10799828171730042
2023-01-23 01:18:24.541006: step: 280/529, loss: 0.18516984581947327
2023-01-23 01:18:25.747725: step: 284/529, loss: 0.037203602492809296
2023-01-23 01:18:26.951908: step: 288/529, loss: 0.04303140565752983
2023-01-23 01:18:28.186621: step: 292/529, loss: 0.13160762190818787
2023-01-23 01:18:29.372208: step: 296/529, loss: 0.01925215683877468
2023-01-23 01:18:30.572013: step: 300/529, loss: 0.0520690456032753
2023-01-23 01:18:31.746470: step: 304/529, loss: 0.025791360065340996
2023-01-23 01:18:33.028181: step: 308/529, loss: 0.1583041250705719
2023-01-23 01:18:34.231335: step: 312/529, loss: 0.043757058680057526
2023-01-23 01:18:35.418177: step: 316/529, loss: 0.09216461330652237
2023-01-23 01:18:36.610180: step: 320/529, loss: 0.04335489124059677
2023-01-23 01:18:37.841778: step: 324/529, loss: 0.08223362267017365
2023-01-23 01:18:39.046441: step: 328/529, loss: 0.0650109276175499
2023-01-23 01:18:40.238362: step: 332/529, loss: 0.011264611035585403
2023-01-23 01:18:41.444665: step: 336/529, loss: 0.14198246598243713
2023-01-23 01:18:42.666560: step: 340/529, loss: 0.03590850904583931
2023-01-23 01:18:43.847415: step: 344/529, loss: 0.028302384540438652
2023-01-23 01:18:45.029837: step: 348/529, loss: 0.053537748754024506
2023-01-23 01:18:46.229220: step: 352/529, loss: 0.033713921904563904
2023-01-23 01:18:47.411415: step: 356/529, loss: 0.11537113040685654
2023-01-23 01:18:48.625213: step: 360/529, loss: 0.042710211127996445
2023-01-23 01:18:49.802368: step: 364/529, loss: 0.0415978878736496
2023-01-23 01:18:50.973152: step: 368/529, loss: 0.01885662041604519
2023-01-23 01:18:52.209153: step: 372/529, loss: 0.008861875161528587
2023-01-23 01:18:53.403672: step: 376/529, loss: 0.057954125106334686
2023-01-23 01:18:54.615489: step: 380/529, loss: 0.07978086173534393
2023-01-23 01:18:55.790322: step: 384/529, loss: 0.40618085861206055
2023-01-23 01:18:56.979295: step: 388/529, loss: 0.011972714215517044
2023-01-23 01:18:58.173359: step: 392/529, loss: 0.039052676409482956
2023-01-23 01:18:59.332108: step: 396/529, loss: 0.12208671867847443
2023-01-23 01:19:00.503127: step: 400/529, loss: 0.007897424511611462
2023-01-23 01:19:01.704303: step: 404/529, loss: 0.08028239756822586
2023-01-23 01:19:02.933500: step: 408/529, loss: 0.035206567496061325
2023-01-23 01:19:04.198574: step: 412/529, loss: 0.06528787314891815
2023-01-23 01:19:05.367149: step: 416/529, loss: 0.0524505153298378
2023-01-23 01:19:06.549834: step: 420/529, loss: 0.05712347477674484
2023-01-23 01:19:07.742312: step: 424/529, loss: 0.040287233889102936
2023-01-23 01:19:08.956972: step: 428/529, loss: 0.10688810795545578
2023-01-23 01:19:10.156424: step: 432/529, loss: 0.0826304480433464
2023-01-23 01:19:11.381631: step: 436/529, loss: 0.029454803094267845
2023-01-23 01:19:12.613267: step: 440/529, loss: 0.06835965812206268
2023-01-23 01:19:13.852354: step: 444/529, loss: 0.11208248138427734
2023-01-23 01:19:15.038579: step: 448/529, loss: 0.06697436422109604
2023-01-23 01:19:16.302975: step: 452/529, loss: 0.08378639817237854
2023-01-23 01:19:17.491071: step: 456/529, loss: 0.07583846896886826
2023-01-23 01:19:18.711332: step: 460/529, loss: 0.07790136337280273
2023-01-23 01:19:19.919216: step: 464/529, loss: 0.02196331135928631
2023-01-23 01:19:21.109572: step: 468/529, loss: 0.05186839401721954
2023-01-23 01:19:22.331994: step: 472/529, loss: 0.025539018213748932
2023-01-23 01:19:23.547305: step: 476/529, loss: 0.10688219219446182
2023-01-23 01:19:24.764988: step: 480/529, loss: 0.12453468143939972
2023-01-23 01:19:26.026534: step: 484/529, loss: 0.05586185306310654
2023-01-23 01:19:27.192164: step: 488/529, loss: 0.76120525598526
2023-01-23 01:19:28.403332: step: 492/529, loss: 0.05771160498261452
2023-01-23 01:19:29.596860: step: 496/529, loss: 0.044410038739442825
2023-01-23 01:19:30.798542: step: 500/529, loss: 0.007841015234589577
2023-01-23 01:19:31.995878: step: 504/529, loss: 0.03519125282764435
2023-01-23 01:19:33.199544: step: 508/529, loss: 0.04109792783856392
2023-01-23 01:19:34.398488: step: 512/529, loss: 0.003284883452579379
2023-01-23 01:19:35.571969: step: 516/529, loss: 0.16335734724998474
2023-01-23 01:19:36.745542: step: 520/529, loss: 0.0568576343357563
2023-01-23 01:19:37.927801: step: 524/529, loss: 0.024648571386933327
2023-01-23 01:19:39.182514: step: 528/529, loss: 0.07842740416526794
2023-01-23 01:19:40.353118: step: 532/529, loss: 0.0037682533729821444
2023-01-23 01:19:41.519573: step: 536/529, loss: 0.012028366327285767
2023-01-23 01:19:42.682118: step: 540/529, loss: 0.023465871810913086
2023-01-23 01:19:43.890954: step: 544/529, loss: 0.04558572918176651
2023-01-23 01:19:45.125300: step: 548/529, loss: 0.4863826036453247
2023-01-23 01:19:46.307404: step: 552/529, loss: 0.1269817352294922
2023-01-23 01:19:47.497989: step: 556/529, loss: 0.0556950606405735
2023-01-23 01:19:48.692426: step: 560/529, loss: 0.026216890662908554
2023-01-23 01:19:49.884287: step: 564/529, loss: 0.011079978197813034
2023-01-23 01:19:51.099999: step: 568/529, loss: 0.0196835994720459
2023-01-23 01:19:52.295809: step: 572/529, loss: 0.01098709087818861
2023-01-23 01:19:53.539451: step: 576/529, loss: 0.2602923512458801
2023-01-23 01:19:54.777259: step: 580/529, loss: 0.02339344099164009
2023-01-23 01:19:55.946667: step: 584/529, loss: 0.043868161737918854
2023-01-23 01:19:57.120538: step: 588/529, loss: 0.060431480407714844
2023-01-23 01:19:58.298387: step: 592/529, loss: 0.1173524409532547
2023-01-23 01:19:59.524850: step: 596/529, loss: 0.38689398765563965
2023-01-23 01:20:00.716573: step: 600/529, loss: 0.47778576612472534
2023-01-23 01:20:01.888517: step: 604/529, loss: 0.005942249670624733
2023-01-23 01:20:03.087372: step: 608/529, loss: 0.07339668273925781
2023-01-23 01:20:04.345103: step: 612/529, loss: 0.18461008369922638
2023-01-23 01:20:05.552165: step: 616/529, loss: 0.03339235857129097
2023-01-23 01:20:06.740555: step: 620/529, loss: 0.028765009716153145
2023-01-23 01:20:07.952241: step: 624/529, loss: 0.0717369094491005
2023-01-23 01:20:09.146386: step: 628/529, loss: 0.035436443984508514
2023-01-23 01:20:10.337204: step: 632/529, loss: 0.30106741189956665
2023-01-23 01:20:11.554142: step: 636/529, loss: 0.00485916156321764
2023-01-23 01:20:12.747711: step: 640/529, loss: 0.08416728675365448
2023-01-23 01:20:13.987601: step: 644/529, loss: 0.04262995719909668
2023-01-23 01:20:15.165191: step: 648/529, loss: 0.00021152498084120452
2023-01-23 01:20:16.376644: step: 652/529, loss: 0.11014995723962784
2023-01-23 01:20:17.582014: step: 656/529, loss: 0.1337263137102127
2023-01-23 01:20:18.768598: step: 660/529, loss: 0.020613862201571465
2023-01-23 01:20:19.956531: step: 664/529, loss: 0.3737545907497406
2023-01-23 01:20:21.150722: step: 668/529, loss: 0.03664112091064453
2023-01-23 01:20:22.389986: step: 672/529, loss: 0.030140304937958717
2023-01-23 01:20:23.558083: step: 676/529, loss: 0.025378037244081497
2023-01-23 01:20:24.777869: step: 680/529, loss: 0.016735846176743507
2023-01-23 01:20:25.999859: step: 684/529, loss: 0.2162659764289856
2023-01-23 01:20:27.234668: step: 688/529, loss: 0.11829642951488495
2023-01-23 01:20:28.472762: step: 692/529, loss: 0.020205307751893997
2023-01-23 01:20:29.694831: step: 696/529, loss: 0.06990861892700195
2023-01-23 01:20:30.898858: step: 700/529, loss: 0.05043850094079971
2023-01-23 01:20:32.104284: step: 704/529, loss: 0.0879116803407669
2023-01-23 01:20:33.283594: step: 708/529, loss: 0.11114483326673508
2023-01-23 01:20:34.478034: step: 712/529, loss: 0.050248242914676666
2023-01-23 01:20:35.751386: step: 716/529, loss: 0.016098951920866966
2023-01-23 01:20:36.956198: step: 720/529, loss: 0.08850259333848953
2023-01-23 01:20:38.118624: step: 724/529, loss: 0.8642034530639648
2023-01-23 01:20:39.313341: step: 728/529, loss: 0.22455640137195587
2023-01-23 01:20:40.506164: step: 732/529, loss: 0.02417612075805664
2023-01-23 01:20:41.740560: step: 736/529, loss: 0.3426995277404785
2023-01-23 01:20:42.929837: step: 740/529, loss: 0.11350803077220917
2023-01-23 01:20:44.093718: step: 744/529, loss: 0.14121656119823456
2023-01-23 01:20:45.281431: step: 748/529, loss: 0.06158151477575302
2023-01-23 01:20:46.471454: step: 752/529, loss: 0.010848474688827991
2023-01-23 01:20:47.653774: step: 756/529, loss: 0.06322264671325684
2023-01-23 01:20:48.818421: step: 760/529, loss: 0.02086639404296875
2023-01-23 01:20:50.072762: step: 764/529, loss: 0.044230081140995026
2023-01-23 01:20:51.268783: step: 768/529, loss: 0.14699527621269226
2023-01-23 01:20:52.427015: step: 772/529, loss: 0.04583549126982689
2023-01-23 01:20:53.620790: step: 776/529, loss: 0.0786447525024414
2023-01-23 01:20:54.832925: step: 780/529, loss: 0.059853557497262955
2023-01-23 01:20:56.015175: step: 784/529, loss: 0.10635185241699219
2023-01-23 01:20:57.231610: step: 788/529, loss: 0.10776054859161377
2023-01-23 01:20:58.432399: step: 792/529, loss: 0.1211184486746788
2023-01-23 01:20:59.647131: step: 796/529, loss: 0.057624056935310364
2023-01-23 01:21:00.867488: step: 800/529, loss: 0.14387273788452148
2023-01-23 01:21:02.044121: step: 804/529, loss: 0.04469814524054527
2023-01-23 01:21:03.312719: step: 808/529, loss: 0.46169471740722656
2023-01-23 01:21:04.540164: step: 812/529, loss: 0.05056142807006836
2023-01-23 01:21:05.717970: step: 816/529, loss: 0.9103809595108032
2023-01-23 01:21:06.925484: step: 820/529, loss: 0.06847725063562393
2023-01-23 01:21:08.100459: step: 824/529, loss: 0.03443317487835884
2023-01-23 01:21:09.286277: step: 828/529, loss: 0.006948280148208141
2023-01-23 01:21:10.513204: step: 832/529, loss: 0.017670728266239166
2023-01-23 01:21:11.717914: step: 836/529, loss: 0.06516246497631073
2023-01-23 01:21:12.884851: step: 840/529, loss: 0.07942891120910645
2023-01-23 01:21:14.053538: step: 844/529, loss: 0.02394256554543972
2023-01-23 01:21:15.270744: step: 848/529, loss: 0.015009118244051933
2023-01-23 01:21:16.465189: step: 852/529, loss: 0.015423298813402653
2023-01-23 01:21:17.698779: step: 856/529, loss: 0.06465931236743927
2023-01-23 01:21:18.905280: step: 860/529, loss: 0.08004292845726013
2023-01-23 01:21:20.123297: step: 864/529, loss: 0.04202743619680405
2023-01-23 01:21:21.288938: step: 868/529, loss: 0.06557998806238174
2023-01-23 01:21:22.490221: step: 872/529, loss: 0.07551483809947968
2023-01-23 01:21:23.682607: step: 876/529, loss: 0.0211213119328022
2023-01-23 01:21:24.878585: step: 880/529, loss: 0.06236915662884712
2023-01-23 01:21:26.072092: step: 884/529, loss: 0.14247122406959534
2023-01-23 01:21:27.238915: step: 888/529, loss: 0.019756030291318893
2023-01-23 01:21:28.442948: step: 892/529, loss: 0.06666717678308487
2023-01-23 01:21:29.631526: step: 896/529, loss: 0.008554745465517044
2023-01-23 01:21:30.841190: step: 900/529, loss: 0.053200624883174896
2023-01-23 01:21:32.037538: step: 904/529, loss: 0.37125349044799805
2023-01-23 01:21:33.236220: step: 908/529, loss: 0.040814876556396484
2023-01-23 01:21:34.452808: step: 912/529, loss: 0.014794540591537952
2023-01-23 01:21:35.655215: step: 916/529, loss: 0.029592324048280716
2023-01-23 01:21:36.832910: step: 920/529, loss: 0.121874138712883
2023-01-23 01:21:38.080650: step: 924/529, loss: 0.019934751093387604
2023-01-23 01:21:39.363622: step: 928/529, loss: 0.05108080059289932
2023-01-23 01:21:40.560163: step: 932/529, loss: 0.04032840579748154
2023-01-23 01:21:41.812324: step: 936/529, loss: 0.08637695014476776
2023-01-23 01:21:43.021293: step: 940/529, loss: 0.064073845744133
2023-01-23 01:21:44.206740: step: 944/529, loss: 0.029075955972075462
2023-01-23 01:21:45.391182: step: 948/529, loss: 0.0765417143702507
2023-01-23 01:21:46.583829: step: 952/529, loss: 0.04902248457074165
2023-01-23 01:21:47.772007: step: 956/529, loss: 0.03183465078473091
2023-01-23 01:21:49.003870: step: 960/529, loss: 0.06572423130273819
2023-01-23 01:21:50.191019: step: 964/529, loss: 0.009702682495117188
2023-01-23 01:21:51.349281: step: 968/529, loss: 0.018375016748905182
2023-01-23 01:21:52.543934: step: 972/529, loss: 0.12438878417015076
2023-01-23 01:21:53.747885: step: 976/529, loss: 0.03125810623168945
2023-01-23 01:21:54.929784: step: 980/529, loss: 0.04159488528966904
2023-01-23 01:21:56.146372: step: 984/529, loss: 0.12201671302318573
2023-01-23 01:21:57.333495: step: 988/529, loss: 0.018727876245975494
2023-01-23 01:21:58.505181: step: 992/529, loss: 0.012703276239335537
2023-01-23 01:21:59.713557: step: 996/529, loss: 0.04838228598237038
2023-01-23 01:22:00.904984: step: 1000/529, loss: 0.023961449041962624
2023-01-23 01:22:02.122910: step: 1004/529, loss: 0.09158802777528763
2023-01-23 01:22:03.320293: step: 1008/529, loss: 0.04957609251141548
2023-01-23 01:22:04.504595: step: 1012/529, loss: 0.021778298541903496
2023-01-23 01:22:05.714384: step: 1016/529, loss: 0.013942575082182884
2023-01-23 01:22:06.885547: step: 1020/529, loss: 0.285350501537323
2023-01-23 01:22:08.075429: step: 1024/529, loss: 0.1779472380876541
2023-01-23 01:22:09.274185: step: 1028/529, loss: 0.06171026453375816
2023-01-23 01:22:10.460537: step: 1032/529, loss: 0.09072227776050568
2023-01-23 01:22:11.668221: step: 1036/529, loss: 0.3835482597351074
2023-01-23 01:22:12.868551: step: 1040/529, loss: 0.06224212795495987
2023-01-23 01:22:14.023159: step: 1044/529, loss: 0.06522088497877121
2023-01-23 01:22:15.230822: step: 1048/529, loss: 0.1870567500591278
2023-01-23 01:22:16.475282: step: 1052/529, loss: 0.05466442182660103
2023-01-23 01:22:17.632944: step: 1056/529, loss: 0.16986331343650818
2023-01-23 01:22:18.820707: step: 1060/529, loss: 0.002873706864193082
2023-01-23 01:22:20.040284: step: 1064/529, loss: 0.05595429241657257
2023-01-23 01:22:21.265003: step: 1068/529, loss: 0.1596684455871582
2023-01-23 01:22:22.495521: step: 1072/529, loss: 0.04306383430957794
2023-01-23 01:22:23.662806: step: 1076/529, loss: 0.050516318529844284
2023-01-23 01:22:24.867938: step: 1080/529, loss: 0.060624219477176666
2023-01-23 01:22:26.053274: step: 1084/529, loss: 0.04683075100183487
2023-01-23 01:22:27.248780: step: 1088/529, loss: 0.15315961837768555
2023-01-23 01:22:28.439349: step: 1092/529, loss: 0.0033500194549560547
2023-01-23 01:22:29.629778: step: 1096/529, loss: 0.0043374537490308285
2023-01-23 01:22:30.806098: step: 1100/529, loss: 0.05547018349170685
2023-01-23 01:22:31.987633: step: 1104/529, loss: 0.06650204211473465
2023-01-23 01:22:33.184211: step: 1108/529, loss: 0.3064367175102234
2023-01-23 01:22:34.393033: step: 1112/529, loss: 0.04076967388391495
2023-01-23 01:22:35.605497: step: 1116/529, loss: 0.045052669942379
2023-01-23 01:22:36.791003: step: 1120/529, loss: 0.09005539864301682
2023-01-23 01:22:37.969838: step: 1124/529, loss: 0.5244442224502563
2023-01-23 01:22:39.184904: step: 1128/529, loss: 0.08465595543384552
2023-01-23 01:22:40.377458: step: 1132/529, loss: 0.024016762152314186
2023-01-23 01:22:41.563182: step: 1136/529, loss: 0.03293666988611221
2023-01-23 01:22:42.755634: step: 1140/529, loss: 0.07514485716819763
2023-01-23 01:22:43.968173: step: 1144/529, loss: 0.016962332651019096
2023-01-23 01:22:45.172072: step: 1148/529, loss: 0.045172788202762604
2023-01-23 01:22:46.393044: step: 1152/529, loss: 0.2070116102695465
2023-01-23 01:22:47.561398: step: 1156/529, loss: 0.04378795623779297
2023-01-23 01:22:48.770201: step: 1160/529, loss: 0.03152036666870117
2023-01-23 01:22:49.945549: step: 1164/529, loss: 0.02256651036441326
2023-01-23 01:22:51.153820: step: 1168/529, loss: 0.032332513481378555
2023-01-23 01:22:52.351166: step: 1172/529, loss: 0.04702835530042648
2023-01-23 01:22:53.549475: step: 1176/529, loss: 0.10719041526317596
2023-01-23 01:22:54.750425: step: 1180/529, loss: 0.11200113594532013
2023-01-23 01:22:55.992955: step: 1184/529, loss: 0.11812859028577805
2023-01-23 01:22:57.165832: step: 1188/529, loss: 0.004242801573127508
2023-01-23 01:22:58.370250: step: 1192/529, loss: 0.034917548298835754
2023-01-23 01:22:59.563646: step: 1196/529, loss: 0.18195569515228271
2023-01-23 01:23:00.787461: step: 1200/529, loss: 0.5743680000305176
2023-01-23 01:23:02.018232: step: 1204/529, loss: 0.0611509308218956
2023-01-23 01:23:03.181115: step: 1208/529, loss: 0.021572113037109375
2023-01-23 01:23:04.375801: step: 1212/529, loss: 0.00331878662109375
2023-01-23 01:23:05.574824: step: 1216/529, loss: 0.005379676818847656
2023-01-23 01:23:06.832118: step: 1220/529, loss: 0.05204496532678604
2023-01-23 01:23:08.027948: step: 1224/529, loss: 0.11636243015527725
2023-01-23 01:23:09.231030: step: 1228/529, loss: 0.07349061965942383
2023-01-23 01:23:10.465059: step: 1232/529, loss: 0.03672294691205025
2023-01-23 01:23:11.648133: step: 1236/529, loss: 0.04184398800134659
2023-01-23 01:23:12.847037: step: 1240/529, loss: 0.07160405814647675
2023-01-23 01:23:14.046912: step: 1244/529, loss: 0.04400477558374405
2023-01-23 01:23:15.229301: step: 1248/529, loss: 0.03861656412482262
2023-01-23 01:23:16.444898: step: 1252/529, loss: 0.08048562705516815
2023-01-23 01:23:17.612126: step: 1256/529, loss: 0.0093552116304636
2023-01-23 01:23:18.797500: step: 1260/529, loss: 0.07427319884300232
2023-01-23 01:23:19.981097: step: 1264/529, loss: 0.0884058028459549
2023-01-23 01:23:21.152604: step: 1268/529, loss: 0.10429945588111877
2023-01-23 01:23:22.318634: step: 1272/529, loss: 0.01878499984741211
2023-01-23 01:23:23.513403: step: 1276/529, loss: 0.005427074618637562
2023-01-23 01:23:24.688904: step: 1280/529, loss: 0.06605371832847595
2023-01-23 01:23:25.902516: step: 1284/529, loss: 0.009358787909150124
2023-01-23 01:23:27.116687: step: 1288/529, loss: 0.1979314684867859
2023-01-23 01:23:28.332524: step: 1292/529, loss: 0.0626378059387207
2023-01-23 01:23:29.537347: step: 1296/529, loss: 0.00027866364689543843
2023-01-23 01:23:30.779709: step: 1300/529, loss: 0.01588420942425728
2023-01-23 01:23:32.035418: step: 1304/529, loss: 0.011727476492524147
2023-01-23 01:23:33.275000: step: 1308/529, loss: 0.022165682166814804
2023-01-23 01:23:34.453601: step: 1312/529, loss: 0.47613105177879333
2023-01-23 01:23:35.708997: step: 1316/529, loss: 0.042531583458185196
2023-01-23 01:23:36.894627: step: 1320/529, loss: 0.24019335210323334
2023-01-23 01:23:38.091735: step: 1324/529, loss: 0.04384305700659752
2023-01-23 01:23:39.339869: step: 1328/529, loss: 0.3339088559150696
2023-01-23 01:23:40.518209: step: 1332/529, loss: 0.6282937526702881
2023-01-23 01:23:41.693157: step: 1336/529, loss: 0.07174015045166016
2023-01-23 01:23:42.945760: step: 1340/529, loss: 0.08688221126794815
2023-01-23 01:23:44.157843: step: 1344/529, loss: 0.007117795757949352
2023-01-23 01:23:45.345709: step: 1348/529, loss: 0.06505441665649414
2023-01-23 01:23:46.529790: step: 1352/529, loss: 0.09686699509620667
2023-01-23 01:23:47.736513: step: 1356/529, loss: 0.030857086181640625
2023-01-23 01:23:48.945682: step: 1360/529, loss: 0.013363170437514782
2023-01-23 01:23:50.113915: step: 1364/529, loss: 0.002827262971550226
2023-01-23 01:23:51.256494: step: 1368/529, loss: 0.09202156215906143
2023-01-23 01:23:52.429244: step: 1372/529, loss: 0.06125626713037491
2023-01-23 01:23:53.606481: step: 1376/529, loss: 0.19162344932556152
2023-01-23 01:23:54.812523: step: 1380/529, loss: 0.05741758272051811
2023-01-23 01:23:55.987428: step: 1384/529, loss: 0.0636628195643425
2023-01-23 01:23:57.201169: step: 1388/529, loss: 0.16150379180908203
2023-01-23 01:23:58.424337: step: 1392/529, loss: 0.06197939068078995
2023-01-23 01:23:59.623167: step: 1396/529, loss: 0.09217548370361328
2023-01-23 01:24:00.815018: step: 1400/529, loss: 0.12160249054431915
2023-01-23 01:24:01.998559: step: 1404/529, loss: 0.09355239570140839
2023-01-23 01:24:03.172192: step: 1408/529, loss: 0.0180224422365427
2023-01-23 01:24:04.365188: step: 1412/529, loss: 0.03396472707390785
2023-01-23 01:24:05.543459: step: 1416/529, loss: 0.010427569970488548
2023-01-23 01:24:06.757550: step: 1420/529, loss: 0.03540525585412979
2023-01-23 01:24:07.955581: step: 1424/529, loss: 0.06806745380163193
2023-01-23 01:24:09.158913: step: 1428/529, loss: 0.019762182608246803
2023-01-23 01:24:10.348723: step: 1432/529, loss: 0.018743038177490234
2023-01-23 01:24:11.543551: step: 1436/529, loss: 0.09737863391637802
2023-01-23 01:24:12.783532: step: 1440/529, loss: 0.024572182446718216
2023-01-23 01:24:13.953742: step: 1444/529, loss: 0.04427499696612358
2023-01-23 01:24:15.163168: step: 1448/529, loss: 0.010946846567094326
2023-01-23 01:24:16.371335: step: 1452/529, loss: 0.059969618916511536
2023-01-23 01:24:17.630736: step: 1456/529, loss: 0.017001723870635033
2023-01-23 01:24:18.818088: step: 1460/529, loss: 0.6445391178131104
2023-01-23 01:24:20.055763: step: 1464/529, loss: 0.04973822087049484
2023-01-23 01:24:21.267536: step: 1468/529, loss: 0.010976076126098633
2023-01-23 01:24:22.438172: step: 1472/529, loss: 0.00947415828704834
2023-01-23 01:24:23.645028: step: 1476/529, loss: 0.05750136822462082
2023-01-23 01:24:24.862576: step: 1480/529, loss: 0.11432208865880966
2023-01-23 01:24:26.027100: step: 1484/529, loss: 0.02811429463326931
2023-01-23 01:24:27.320920: step: 1488/529, loss: 0.2895934283733368
2023-01-23 01:24:28.529457: step: 1492/529, loss: 0.03552551567554474
2023-01-23 01:24:29.771250: step: 1496/529, loss: 0.1318141520023346
2023-01-23 01:24:30.925766: step: 1500/529, loss: 0.13489246368408203
2023-01-23 01:24:32.150359: step: 1504/529, loss: 0.031130218878388405
2023-01-23 01:24:33.346648: step: 1508/529, loss: 0.13389912247657776
2023-01-23 01:24:34.517967: step: 1512/529, loss: 0.07240858674049377
2023-01-23 01:24:35.717891: step: 1516/529, loss: 0.027633430436253548
2023-01-23 01:24:36.929568: step: 1520/529, loss: 0.2103595733642578
2023-01-23 01:24:38.181524: step: 1524/529, loss: 0.011047554202377796
2023-01-23 01:24:39.385678: step: 1528/529, loss: 0.051865674555301666
2023-01-23 01:24:40.592785: step: 1532/529, loss: 0.08383378386497498
2023-01-23 01:24:41.797336: step: 1536/529, loss: 0.16126574575901031
2023-01-23 01:24:42.982641: step: 1540/529, loss: 0.04711761325597763
2023-01-23 01:24:44.198979: step: 1544/529, loss: 0.1483105719089508
2023-01-23 01:24:45.371245: step: 1548/529, loss: 0.09462644159793854
2023-01-23 01:24:46.555528: step: 1552/529, loss: 0.01610751263797283
2023-01-23 01:24:47.759961: step: 1556/529, loss: 0.047036781907081604
2023-01-23 01:24:48.914732: step: 1560/529, loss: 0.035237133502960205
2023-01-23 01:24:50.131015: step: 1564/529, loss: 0.08369751274585724
2023-01-23 01:24:51.331367: step: 1568/529, loss: 0.019838809967041016
2023-01-23 01:24:52.568184: step: 1572/529, loss: 0.06706152111291885
2023-01-23 01:24:53.752041: step: 1576/529, loss: 0.009032058529555798
2023-01-23 01:24:54.939676: step: 1580/529, loss: 0.04050722345709801
2023-01-23 01:24:56.178347: step: 1584/529, loss: 0.027249623090028763
2023-01-23 01:24:57.382805: step: 1588/529, loss: 0.05882978439331055
2023-01-23 01:24:58.600093: step: 1592/529, loss: 0.005846119020134211
2023-01-23 01:24:59.795462: step: 1596/529, loss: 0.028565408661961555
2023-01-23 01:25:01.007579: step: 1600/529, loss: 0.008575011044740677
2023-01-23 01:25:02.200992: step: 1604/529, loss: 0.03824224695563316
2023-01-23 01:25:03.359687: step: 1608/529, loss: 0.05434904247522354
2023-01-23 01:25:04.599232: step: 1612/529, loss: 0.03480052947998047
2023-01-23 01:25:05.781934: step: 1616/529, loss: 0.08869180828332901
2023-01-23 01:25:07.029193: step: 1620/529, loss: 0.04703493416309357
2023-01-23 01:25:08.264908: step: 1624/529, loss: 0.04728660732507706
2023-01-23 01:25:09.466167: step: 1628/529, loss: 0.25898608565330505
2023-01-23 01:25:10.661798: step: 1632/529, loss: 0.07266082614660263
2023-01-23 01:25:11.797039: step: 1636/529, loss: 0.006017875857651234
2023-01-23 01:25:12.994968: step: 1640/529, loss: 0.005083751864731312
2023-01-23 01:25:14.195217: step: 1644/529, loss: 0.06535936146974564
2023-01-23 01:25:15.373974: step: 1648/529, loss: 0.026714229956269264
2023-01-23 01:25:16.640598: step: 1652/529, loss: 0.014203835278749466
2023-01-23 01:25:17.882588: step: 1656/529, loss: 0.17198285460472107
2023-01-23 01:25:19.046114: step: 1660/529, loss: 0.6538625955581665
2023-01-23 01:25:20.252999: step: 1664/529, loss: 0.0641627311706543
2023-01-23 01:25:21.466615: step: 1668/529, loss: 0.012610369361937046
2023-01-23 01:25:22.675340: step: 1672/529, loss: 0.0954427719116211
2023-01-23 01:25:23.841941: step: 1676/529, loss: 0.07017917931079865
2023-01-23 01:25:25.057118: step: 1680/529, loss: 0.07186637073755264
2023-01-23 01:25:26.229181: step: 1684/529, loss: 0.09809704124927521
2023-01-23 01:25:27.402070: step: 1688/529, loss: 0.021207522600889206
2023-01-23 01:25:28.592222: step: 1692/529, loss: 0.008821630850434303
2023-01-23 01:25:29.782766: step: 1696/529, loss: 0.18709488213062286
2023-01-23 01:25:31.013301: step: 1700/529, loss: 0.09484080970287323
2023-01-23 01:25:32.177131: step: 1704/529, loss: 0.09167365729808807
2023-01-23 01:25:33.396936: step: 1708/529, loss: 0.0692354217171669
2023-01-23 01:25:34.609401: step: 1712/529, loss: 0.09218921512365341
2023-01-23 01:25:35.751705: step: 1716/529, loss: 0.11082544922828674
2023-01-23 01:25:36.934047: step: 1720/529, loss: 0.4856891632080078
2023-01-23 01:25:38.177048: step: 1724/529, loss: 0.173588365316391
2023-01-23 01:25:39.353795: step: 1728/529, loss: 0.09916222095489502
2023-01-23 01:25:40.572738: step: 1732/529, loss: 0.33995094895362854
2023-01-23 01:25:41.770611: step: 1736/529, loss: 0.019084453582763672
2023-01-23 01:25:42.962066: step: 1740/529, loss: 0.10552337765693665
2023-01-23 01:25:44.141749: step: 1744/529, loss: 0.0319819450378418
2023-01-23 01:25:45.351401: step: 1748/529, loss: 0.07181663811206818
2023-01-23 01:25:46.557942: step: 1752/529, loss: 0.05091724544763565
2023-01-23 01:25:47.751743: step: 1756/529, loss: 0.04818334802985191
2023-01-23 01:25:48.922846: step: 1760/529, loss: 0.05908724293112755
2023-01-23 01:25:50.108671: step: 1764/529, loss: 0.08158192783594131
2023-01-23 01:25:51.327021: step: 1768/529, loss: 0.16746819019317627
2023-01-23 01:25:52.526460: step: 1772/529, loss: 0.005501556675881147
2023-01-23 01:25:53.755433: step: 1776/529, loss: 0.1229754388332367
2023-01-23 01:25:54.929940: step: 1780/529, loss: 0.04066481441259384
2023-01-23 01:25:56.142524: step: 1784/529, loss: 0.2833024859428406
2023-01-23 01:25:57.340009: step: 1788/529, loss: 0.05566740036010742
2023-01-23 01:25:58.528540: step: 1792/529, loss: 0.0060708047822117805
2023-01-23 01:25:59.737517: step: 1796/529, loss: 0.07069225609302521
2023-01-23 01:26:00.933168: step: 1800/529, loss: 0.038553811609745026
2023-01-23 01:26:02.237731: step: 1804/529, loss: 0.08105144649744034
2023-01-23 01:26:03.414332: step: 1808/529, loss: 0.040831662714481354
2023-01-23 01:26:04.585121: step: 1812/529, loss: 0.012246990576386452
2023-01-23 01:26:05.755827: step: 1816/529, loss: 0.005950260441750288
2023-01-23 01:26:06.958667: step: 1820/529, loss: 0.20272284746170044
2023-01-23 01:26:08.187384: step: 1824/529, loss: 0.04891033470630646
2023-01-23 01:26:09.398304: step: 1828/529, loss: 0.1917746514081955
2023-01-23 01:26:10.628015: step: 1832/529, loss: 0.23157139122486115
2023-01-23 01:26:11.851498: step: 1836/529, loss: 0.017279338091611862
2023-01-23 01:26:13.031913: step: 1840/529, loss: 0.006729698274284601
2023-01-23 01:26:14.245344: step: 1844/529, loss: 0.021752070635557175
2023-01-23 01:26:15.463471: step: 1848/529, loss: 0.05968036875128746
2023-01-23 01:26:16.631164: step: 1852/529, loss: 0.020246410742402077
2023-01-23 01:26:17.838142: step: 1856/529, loss: 0.02618122100830078
2023-01-23 01:26:19.010512: step: 1860/529, loss: 0.020935581997036934
2023-01-23 01:26:20.208828: step: 1864/529, loss: 0.2516254782676697
2023-01-23 01:26:21.470653: step: 1868/529, loss: 0.0006624698871746659
2023-01-23 01:26:22.681544: step: 1872/529, loss: 0.1720069795846939
2023-01-23 01:26:23.863979: step: 1876/529, loss: 0.006412982940673828
2023-01-23 01:26:25.072951: step: 1880/529, loss: 0.09994864463806152
2023-01-23 01:26:26.268987: step: 1884/529, loss: 0.6097953915596008
2023-01-23 01:26:27.487740: step: 1888/529, loss: 0.11386509239673615
2023-01-23 01:26:28.668965: step: 1892/529, loss: 0.036307334899902344
2023-01-23 01:26:29.906131: step: 1896/529, loss: 0.07576818019151688
2023-01-23 01:26:31.102926: step: 1900/529, loss: 0.09280133992433548
2023-01-23 01:26:32.285619: step: 1904/529, loss: 0.04515876621007919
2023-01-23 01:26:33.427904: step: 1908/529, loss: 0.032294463366270065
2023-01-23 01:26:34.629705: step: 1912/529, loss: 0.010451888665556908
2023-01-23 01:26:35.817138: step: 1916/529, loss: 0.19697609543800354
2023-01-23 01:26:36.956459: step: 1920/529, loss: 0.007030535023659468
2023-01-23 01:26:38.113550: step: 1924/529, loss: 0.078119657933712
2023-01-23 01:26:39.312009: step: 1928/529, loss: 0.054036520421504974
2023-01-23 01:26:40.519815: step: 1932/529, loss: 0.031043052673339844
2023-01-23 01:26:41.726679: step: 1936/529, loss: 0.04542751610279083
2023-01-23 01:26:42.939900: step: 1940/529, loss: 0.06074027717113495
2023-01-23 01:26:44.137743: step: 1944/529, loss: 0.04008760303258896
2023-01-23 01:26:45.337567: step: 1948/529, loss: 0.02817593887448311
2023-01-23 01:26:46.522260: step: 1952/529, loss: 0.03502235561609268
2023-01-23 01:26:47.703865: step: 1956/529, loss: 0.17737768590450287
2023-01-23 01:26:48.882200: step: 1960/529, loss: 0.05894641950726509
2023-01-23 01:26:50.089940: step: 1964/529, loss: 0.06258449703454971
2023-01-23 01:26:51.315724: step: 1968/529, loss: 0.09734315425157547
2023-01-23 01:26:52.541010: step: 1972/529, loss: 0.4017411172389984
2023-01-23 01:26:53.749511: step: 1976/529, loss: 0.06903314590454102
2023-01-23 01:26:54.941690: step: 1980/529, loss: 0.07976827770471573
2023-01-23 01:26:56.139732: step: 1984/529, loss: 0.05909710004925728
2023-01-23 01:26:57.329943: step: 1988/529, loss: 0.09733323752880096
2023-01-23 01:26:58.521442: step: 1992/529, loss: 0.0556214302778244
2023-01-23 01:26:59.754912: step: 1996/529, loss: 0.16538219153881073
2023-01-23 01:27:00.935682: step: 2000/529, loss: 0.10899905860424042
2023-01-23 01:27:02.130907: step: 2004/529, loss: 0.029842281714081764
2023-01-23 01:27:03.318029: step: 2008/529, loss: 0.042408086359500885
2023-01-23 01:27:04.553293: step: 2012/529, loss: 0.03325076401233673
2023-01-23 01:27:05.749015: step: 2016/529, loss: 0.026003647595643997
2023-01-23 01:27:06.976639: step: 2020/529, loss: 0.035254668444395065
2023-01-23 01:27:08.191908: step: 2024/529, loss: 0.04162921756505966
2023-01-23 01:27:09.381670: step: 2028/529, loss: 0.03584732860326767
2023-01-23 01:27:10.583489: step: 2032/529, loss: 0.024262525141239166
2023-01-23 01:27:11.773406: step: 2036/529, loss: 0.11120691895484924
2023-01-23 01:27:12.994479: step: 2040/529, loss: 0.04747423902153969
2023-01-23 01:27:14.215865: step: 2044/529, loss: 0.026966571807861328
2023-01-23 01:27:15.443032: step: 2048/529, loss: 0.13409996032714844
2023-01-23 01:27:16.639273: step: 2052/529, loss: 0.24730148911476135
2023-01-23 01:27:17.799393: step: 2056/529, loss: 0.08357515186071396
2023-01-23 01:27:19.002095: step: 2060/529, loss: 0.0038730620872229338
2023-01-23 01:27:20.189281: step: 2064/529, loss: 0.008508061990141869
2023-01-23 01:27:21.408456: step: 2068/529, loss: 0.05024733766913414
2023-01-23 01:27:22.591704: step: 2072/529, loss: 0.09975495934486389
2023-01-23 01:27:23.779626: step: 2076/529, loss: 0.48831596970558167
2023-01-23 01:27:25.011419: step: 2080/529, loss: 0.01406846009194851
2023-01-23 01:27:26.215261: step: 2084/529, loss: 0.8734437227249146
2023-01-23 01:27:27.417799: step: 2088/529, loss: 0.017843054607510567
2023-01-23 01:27:28.605398: step: 2092/529, loss: 0.1170232743024826
2023-01-23 01:27:29.791408: step: 2096/529, loss: 0.013381004333496094
2023-01-23 01:27:31.064342: step: 2100/529, loss: 0.05179738998413086
2023-01-23 01:27:32.293183: step: 2104/529, loss: 0.027214527130126953
2023-01-23 01:27:33.483849: step: 2108/529, loss: 0.11447896808385849
2023-01-23 01:27:34.674146: step: 2112/529, loss: 0.330289751291275
2023-01-23 01:27:35.873490: step: 2116/529, loss: 0.36585643887519836
==================================================
Loss: 0.096
--------------------
Dev: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5529411764705883, 'r': 0.8703703703703703, 'f1': 0.6762589928057553}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
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': 10}
Russian: {'event': {'p': 0.46, 'r': 0.6388888888888888, 'f1': 0.5348837209302325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 01:28:25.863718: step: 4/529, loss: 0.0415768176317215
2023-01-23 01:28:27.090814: step: 8/529, loss: 0.16287919878959656
2023-01-23 01:28:28.274411: step: 12/529, loss: 0.0070549012161791325
2023-01-23 01:28:29.484251: step: 16/529, loss: 0.03151078149676323
2023-01-23 01:28:30.718901: step: 20/529, loss: 0.03748636692762375
2023-01-23 01:28:31.926135: step: 24/529, loss: 0.0657106414437294
2023-01-23 01:28:33.125586: step: 28/529, loss: 0.00724449148401618
2023-01-23 01:28:34.356858: step: 32/529, loss: 0.010496187955141068
2023-01-23 01:28:35.575005: step: 36/529, loss: 0.11836367100477219
2023-01-23 01:28:36.760892: step: 40/529, loss: 0.06352093815803528
2023-01-23 01:28:37.955580: step: 44/529, loss: 0.007104778196662664
2023-01-23 01:28:39.180599: step: 48/529, loss: 0.017368067055940628
2023-01-23 01:28:40.371783: step: 52/529, loss: 0.01285247877240181
2023-01-23 01:28:41.567080: step: 56/529, loss: 0.35003361105918884
2023-01-23 01:28:42.752555: step: 60/529, loss: 0.06347475200891495
2023-01-23 01:28:43.979097: step: 64/529, loss: 0.05626125633716583
2023-01-23 01:28:45.164828: step: 68/529, loss: 0.021786022931337357
2023-01-23 01:28:46.358956: step: 72/529, loss: 0.028809165582060814
2023-01-23 01:28:47.547401: step: 76/529, loss: 0.059075068682432175
2023-01-23 01:28:48.768705: step: 80/529, loss: 0.14954443275928497
2023-01-23 01:28:49.991709: step: 84/529, loss: 0.03666548803448677
2023-01-23 01:28:51.211045: step: 88/529, loss: 0.028780652210116386
2023-01-23 01:28:52.425999: step: 92/529, loss: 0.006824493408203125
2023-01-23 01:28:53.603395: step: 96/529, loss: 0.18172197043895721
2023-01-23 01:28:54.822690: step: 100/529, loss: 0.05139312893152237
2023-01-23 01:28:56.004732: step: 104/529, loss: 0.0803680419921875
2023-01-23 01:28:57.203928: step: 108/529, loss: 0.14311495423316956
2023-01-23 01:28:58.378823: step: 112/529, loss: 0.07278792560100555
2023-01-23 01:28:59.543496: step: 116/529, loss: 0.03270377963781357
2023-01-23 01:29:00.724681: step: 120/529, loss: 0.0043490887619555
2023-01-23 01:29:01.941123: step: 124/529, loss: 0.012589359655976295
2023-01-23 01:29:03.101062: step: 128/529, loss: 0.03191699832677841
2023-01-23 01:29:04.329425: step: 132/529, loss: 0.06626572459936142
2023-01-23 01:29:05.514272: step: 136/529, loss: 0.011196709237992764
2023-01-23 01:29:06.726938: step: 140/529, loss: 0.018349885940551758
2023-01-23 01:29:07.931424: step: 144/529, loss: 0.037526704370975494
2023-01-23 01:29:09.133212: step: 148/529, loss: 0.018480874598026276
2023-01-23 01:29:10.333403: step: 152/529, loss: 0.010340118780732155
2023-01-23 01:29:11.528597: step: 156/529, loss: 0.07742618024349213
2023-01-23 01:29:12.730944: step: 160/529, loss: 0.05386161804199219
2023-01-23 01:29:13.921981: step: 164/529, loss: 0.04370565339922905
2023-01-23 01:29:15.100121: step: 168/529, loss: 0.05732927471399307
2023-01-23 01:29:16.333490: step: 172/529, loss: 0.10836195200681686
2023-01-23 01:29:17.532572: step: 176/529, loss: 0.02942199818789959
2023-01-23 01:29:18.691810: step: 180/529, loss: 0.04060402140021324
2023-01-23 01:29:19.892343: step: 184/529, loss: 0.01614408567547798
2023-01-23 01:29:21.074151: step: 188/529, loss: 0.18061956763267517
2023-01-23 01:29:22.278961: step: 192/529, loss: 0.0369415283203125
2023-01-23 01:29:23.437102: step: 196/529, loss: 0.1239471435546875
2023-01-23 01:29:24.687784: step: 200/529, loss: 0.058680009096860886
2023-01-23 01:29:25.882355: step: 204/529, loss: 0.05028572306036949
2023-01-23 01:29:27.079481: step: 208/529, loss: 0.060007862746715546
2023-01-23 01:29:28.294764: step: 212/529, loss: 0.03610801696777344
2023-01-23 01:29:29.473493: step: 216/529, loss: 0.042501404881477356
2023-01-23 01:29:30.663835: step: 220/529, loss: 0.02070922777056694
2023-01-23 01:29:31.871980: step: 224/529, loss: 0.010623836889863014
2023-01-23 01:29:33.071009: step: 228/529, loss: 0.024311255663633347
2023-01-23 01:29:34.302402: step: 232/529, loss: 0.05710411071777344
2023-01-23 01:29:35.523097: step: 236/529, loss: 0.07958227396011353
2023-01-23 01:29:36.710663: step: 240/529, loss: 0.05572567135095596
2023-01-23 01:29:37.888698: step: 244/529, loss: 0.331353098154068
2023-01-23 01:29:39.080108: step: 248/529, loss: 0.053750231862068176
2023-01-23 01:29:40.275139: step: 252/529, loss: 0.03795952722430229
2023-01-23 01:29:41.463071: step: 256/529, loss: 0.007666397374123335
2023-01-23 01:29:42.685709: step: 260/529, loss: 0.16255168616771698
2023-01-23 01:29:43.915967: step: 264/529, loss: 0.008515920490026474
2023-01-23 01:29:45.154478: step: 268/529, loss: 0.056786537170410156
2023-01-23 01:29:46.336009: step: 272/529, loss: 0.0397094264626503
2023-01-23 01:29:47.540701: step: 276/529, loss: 0.02472515031695366
2023-01-23 01:29:48.677366: step: 280/529, loss: 0.00625221710652113
2023-01-23 01:29:49.840948: step: 284/529, loss: 0.02401280403137207
2023-01-23 01:29:51.086061: step: 288/529, loss: 0.053014516830444336
2023-01-23 01:29:52.347455: step: 292/529, loss: 0.007286358159035444
2023-01-23 01:29:53.536152: step: 296/529, loss: 0.0013787508942186832
2023-01-23 01:29:54.724427: step: 300/529, loss: 0.24921369552612305
2023-01-23 01:29:55.908284: step: 304/529, loss: 0.05410442501306534
2023-01-23 01:29:57.104516: step: 308/529, loss: 0.038373470306396484
2023-01-23 01:29:58.325157: step: 312/529, loss: 0.44612064957618713
2023-01-23 01:29:59.517214: step: 316/529, loss: 0.06152915954589844
2023-01-23 01:30:00.664372: step: 320/529, loss: 0.09439195692539215
2023-01-23 01:30:01.898278: step: 324/529, loss: 0.018712997436523438
2023-01-23 01:30:03.103123: step: 328/529, loss: 0.002446127124130726
2023-01-23 01:30:04.261437: step: 332/529, loss: 0.014412927441298962
2023-01-23 01:30:05.459703: step: 336/529, loss: 0.08691225200891495
2023-01-23 01:30:06.637301: step: 340/529, loss: 0.014534950256347656
2023-01-23 01:30:07.795521: step: 344/529, loss: 0.11884526908397675
2023-01-23 01:30:09.015285: step: 348/529, loss: 0.03379569202661514
2023-01-23 01:30:10.225227: step: 352/529, loss: 0.020771600306034088
2023-01-23 01:30:11.407196: step: 356/529, loss: 0.26751813292503357
2023-01-23 01:30:12.610375: step: 360/529, loss: 0.10104808956384659
2023-01-23 01:30:13.818713: step: 364/529, loss: 0.11772260814905167
2023-01-23 01:30:14.962872: step: 368/529, loss: 0.06868879497051239
2023-01-23 01:30:16.138547: step: 372/529, loss: 0.09869156032800674
2023-01-23 01:30:17.334109: step: 376/529, loss: 0.042247869074344635
2023-01-23 01:30:18.576754: step: 380/529, loss: 0.03956031799316406
2023-01-23 01:30:19.752532: step: 384/529, loss: 0.07672491669654846
2023-01-23 01:30:21.002105: step: 388/529, loss: 0.11837844550609589
2023-01-23 01:30:22.212200: step: 392/529, loss: 0.012391806580126286
2023-01-23 01:30:23.483101: step: 396/529, loss: 0.2483467012643814
2023-01-23 01:30:24.682792: step: 400/529, loss: 0.005062580108642578
2023-01-23 01:30:25.854137: step: 404/529, loss: 0.07758307456970215
2023-01-23 01:30:27.045260: step: 408/529, loss: 0.08309879899024963
2023-01-23 01:30:28.229241: step: 412/529, loss: 0.0534786693751812
2023-01-23 01:30:29.423013: step: 416/529, loss: 0.04766378924250603
2023-01-23 01:30:30.665443: step: 420/529, loss: 0.017609978094697
2023-01-23 01:30:31.892747: step: 424/529, loss: 0.03704414516687393
2023-01-23 01:30:33.093299: step: 428/529, loss: 0.027111627161502838
2023-01-23 01:30:34.270049: step: 432/529, loss: 0.02130155637860298
2023-01-23 01:30:35.479542: step: 436/529, loss: 0.007975387386977673
2023-01-23 01:30:36.662870: step: 440/529, loss: 0.071660615503788
2023-01-23 01:30:37.878784: step: 444/529, loss: 0.05532436445355415
2023-01-23 01:30:39.047794: step: 448/529, loss: 0.08488073199987411
2023-01-23 01:30:40.303176: step: 452/529, loss: 0.0222688689827919
2023-01-23 01:30:41.520703: step: 456/529, loss: 0.04647884517908096
2023-01-23 01:30:42.734284: step: 460/529, loss: 0.17887821793556213
2023-01-23 01:30:43.938417: step: 464/529, loss: 0.10830917209386826
2023-01-23 01:30:45.135322: step: 468/529, loss: 0.03001413494348526
2023-01-23 01:30:46.321886: step: 472/529, loss: 0.059232331812381744
2023-01-23 01:30:47.527647: step: 476/529, loss: 0.0866231918334961
2023-01-23 01:30:48.700519: step: 480/529, loss: 0.001173305558040738
2023-01-23 01:30:49.939509: step: 484/529, loss: 0.04395580664277077
2023-01-23 01:30:51.132468: step: 488/529, loss: 0.012170601636171341
2023-01-23 01:30:52.307928: step: 492/529, loss: 0.006155920214951038
2023-01-23 01:30:53.505248: step: 496/529, loss: 0.009749412536621094
2023-01-23 01:30:54.756188: step: 500/529, loss: 0.08456535637378693
2023-01-23 01:30:55.990582: step: 504/529, loss: 0.07859258353710175
2023-01-23 01:30:57.154673: step: 508/529, loss: 0.044638726860284805
2023-01-23 01:30:58.342930: step: 512/529, loss: 0.03965149074792862
2023-01-23 01:30:59.545380: step: 516/529, loss: 0.3025369644165039
2023-01-23 01:31:00.788101: step: 520/529, loss: 0.005192232318222523
2023-01-23 01:31:01.980429: step: 524/529, loss: 0.016986466944217682
2023-01-23 01:31:03.202594: step: 528/529, loss: 0.018117427825927734
2023-01-23 01:31:04.360309: step: 532/529, loss: 0.01415863074362278
2023-01-23 01:31:05.555245: step: 536/529, loss: 0.1638137847185135
2023-01-23 01:31:06.762367: step: 540/529, loss: 2.179351806640625
2023-01-23 01:31:07.932250: step: 544/529, loss: 0.004407837055623531
2023-01-23 01:31:09.131475: step: 548/529, loss: 0.061171628534793854
2023-01-23 01:31:10.294062: step: 552/529, loss: 0.08730974793434143
2023-01-23 01:31:11.493577: step: 556/529, loss: 0.1683538407087326
2023-01-23 01:31:12.710135: step: 560/529, loss: 0.10898485779762268
2023-01-23 01:31:13.962414: step: 564/529, loss: 0.06438169628381729
2023-01-23 01:31:15.185179: step: 568/529, loss: 0.014602613635361195
2023-01-23 01:31:16.404816: step: 572/529, loss: 0.025857355445623398
2023-01-23 01:31:17.606447: step: 576/529, loss: 0.04417915269732475
2023-01-23 01:31:18.848872: step: 580/529, loss: 0.012629318982362747
2023-01-23 01:31:20.022473: step: 584/529, loss: 0.09801841527223587
2023-01-23 01:31:21.233237: step: 588/529, loss: 0.03852539137005806
2023-01-23 01:31:22.435232: step: 592/529, loss: 0.04214029386639595
2023-01-23 01:31:23.636414: step: 596/529, loss: 0.20783615112304688
2023-01-23 01:31:24.804526: step: 600/529, loss: 0.0742349624633789
2023-01-23 01:31:26.053846: step: 604/529, loss: 0.061101723462343216
2023-01-23 01:31:27.230094: step: 608/529, loss: 0.06343875080347061
2023-01-23 01:31:28.471212: step: 612/529, loss: 0.04918226972222328
2023-01-23 01:31:29.677406: step: 616/529, loss: 0.1318499594926834
2023-01-23 01:31:30.888256: step: 620/529, loss: 0.018779754638671875
2023-01-23 01:31:32.111212: step: 624/529, loss: 0.11114434897899628
2023-01-23 01:31:33.341241: step: 628/529, loss: 0.08607196807861328
2023-01-23 01:31:34.533905: step: 632/529, loss: 0.0006310463068075478
2023-01-23 01:31:35.758186: step: 636/529, loss: 0.0015189171535894275
2023-01-23 01:31:37.006514: step: 640/529, loss: 0.006538200657814741
2023-01-23 01:31:38.258380: step: 644/529, loss: 0.08150138705968857
2023-01-23 01:31:39.438290: step: 648/529, loss: 0.08642778545618057
2023-01-23 01:31:40.653059: step: 652/529, loss: 0.04719109833240509
2023-01-23 01:31:41.869019: step: 656/529, loss: 0.17432785034179688
2023-01-23 01:31:43.074761: step: 660/529, loss: 0.10804205387830734
2023-01-23 01:31:44.263716: step: 664/529, loss: 0.0521734245121479
2023-01-23 01:31:45.437710: step: 668/529, loss: 0.049578286707401276
2023-01-23 01:31:46.637271: step: 672/529, loss: 0.6951566934585571
2023-01-23 01:31:47.811865: step: 676/529, loss: 0.16706885397434235
2023-01-23 01:31:49.045428: step: 680/529, loss: 0.056014157831668854
2023-01-23 01:31:50.347638: step: 684/529, loss: 0.059819985181093216
2023-01-23 01:31:51.529739: step: 688/529, loss: 0.0017995834350585938
2023-01-23 01:31:52.783496: step: 692/529, loss: 0.013722610659897327
2023-01-23 01:31:53.965382: step: 696/529, loss: 0.348165899515152
2023-01-23 01:31:55.130746: step: 700/529, loss: 0.059636928141117096
2023-01-23 01:31:56.311027: step: 704/529, loss: 0.07060060650110245
2023-01-23 01:31:57.468194: step: 708/529, loss: 0.00022745133901480585
2023-01-23 01:31:58.635966: step: 712/529, loss: 0.002770645311102271
2023-01-23 01:31:59.845892: step: 716/529, loss: 0.05276527628302574
2023-01-23 01:32:01.032251: step: 720/529, loss: 0.02288804203271866
2023-01-23 01:32:02.226360: step: 724/529, loss: 0.025639917701482773
2023-01-23 01:32:03.448426: step: 728/529, loss: 0.013970565050840378
2023-01-23 01:32:04.627392: step: 732/529, loss: 0.03739595413208008
2023-01-23 01:32:05.837163: step: 736/529, loss: 0.03491213172674179
2023-01-23 01:32:07.052836: step: 740/529, loss: 0.048519134521484375
2023-01-23 01:32:08.276639: step: 744/529, loss: 0.0017409325810149312
2023-01-23 01:32:09.430554: step: 748/529, loss: 0.015275574289262295
2023-01-23 01:32:10.635924: step: 752/529, loss: 0.06074018403887749
2023-01-23 01:32:11.876577: step: 756/529, loss: 0.08562984317541122
2023-01-23 01:32:13.116064: step: 760/529, loss: 0.004721450619399548
2023-01-23 01:32:14.257196: step: 764/529, loss: 0.05725431442260742
2023-01-23 01:32:15.479862: step: 768/529, loss: 0.11611500382423401
2023-01-23 01:32:16.638868: step: 772/529, loss: 0.006209087558090687
2023-01-23 01:32:17.827379: step: 776/529, loss: 0.08293185383081436
2023-01-23 01:32:19.030505: step: 780/529, loss: 0.0747164785861969
2023-01-23 01:32:20.215040: step: 784/529, loss: 0.053025342524051666
2023-01-23 01:32:21.422729: step: 788/529, loss: 0.022747613489627838
2023-01-23 01:32:22.584212: step: 792/529, loss: 0.011130904778838158
2023-01-23 01:32:23.740054: step: 796/529, loss: 0.028368093073368073
2023-01-23 01:32:24.932632: step: 800/529, loss: 0.07959599792957306
2023-01-23 01:32:26.112761: step: 804/529, loss: 0.10140614956617355
2023-01-23 01:32:27.288131: step: 808/529, loss: 0.0361296683549881
2023-01-23 01:32:28.490364: step: 812/529, loss: 0.06905317306518555
2023-01-23 01:32:29.720681: step: 816/529, loss: 0.08662247657775879
2023-01-23 01:32:30.962940: step: 820/529, loss: 0.07569456100463867
2023-01-23 01:32:32.151416: step: 824/529, loss: 0.027566147968173027
2023-01-23 01:32:33.359871: step: 828/529, loss: 0.03365898132324219
2023-01-23 01:32:34.551771: step: 832/529, loss: 0.05202503129839897
2023-01-23 01:32:35.750602: step: 836/529, loss: 0.059766486287117004
2023-01-23 01:32:36.990311: step: 840/529, loss: 0.3832658529281616
2023-01-23 01:32:38.196434: step: 844/529, loss: 0.031035233289003372
2023-01-23 01:32:39.400716: step: 848/529, loss: 0.014853572472929955
2023-01-23 01:32:40.576173: step: 852/529, loss: 0.0037977220490574837
2023-01-23 01:32:41.801123: step: 856/529, loss: 0.10528374463319778
2023-01-23 01:32:42.963187: step: 860/529, loss: 0.0754704475402832
2023-01-23 01:32:44.130003: step: 864/529, loss: 0.0284087173640728
2023-01-23 01:32:45.303849: step: 868/529, loss: 0.015226030722260475
2023-01-23 01:32:46.481761: step: 872/529, loss: 0.04141269251704216
2023-01-23 01:32:47.687569: step: 876/529, loss: 0.03359193727374077
2023-01-23 01:32:48.909915: step: 880/529, loss: 0.0811983048915863
2023-01-23 01:32:50.082946: step: 884/529, loss: 0.2063777893781662
2023-01-23 01:32:51.286675: step: 888/529, loss: 0.011458205990493298
2023-01-23 01:32:52.489325: step: 892/529, loss: 0.0023745535872876644
2023-01-23 01:32:53.705507: step: 896/529, loss: 0.07005605101585388
2023-01-23 01:32:54.874324: step: 900/529, loss: 0.009489346295595169
2023-01-23 01:32:56.085657: step: 904/529, loss: 0.0004330635129008442
2023-01-23 01:32:57.281743: step: 908/529, loss: 0.028146887198090553
2023-01-23 01:32:58.482295: step: 912/529, loss: 0.06805019080638885
2023-01-23 01:32:59.685975: step: 916/529, loss: 0.013579512014985085
2023-01-23 01:33:00.922717: step: 920/529, loss: 0.02916431427001953
2023-01-23 01:33:02.145265: step: 924/529, loss: 0.08250255882740021
2023-01-23 01:33:03.376287: step: 928/529, loss: 0.03976269066333771
2023-01-23 01:33:04.609811: step: 932/529, loss: 0.009790134616196156
2023-01-23 01:33:05.791859: step: 936/529, loss: 0.014933109283447266
2023-01-23 01:33:07.016869: step: 940/529, loss: 0.013311576098203659
2023-01-23 01:33:08.231684: step: 944/529, loss: 0.045032598078250885
2023-01-23 01:33:09.430459: step: 948/529, loss: 0.2498399317264557
2023-01-23 01:33:10.608572: step: 952/529, loss: 0.005346202757209539
2023-01-23 01:33:11.804869: step: 956/529, loss: 0.039979077875614166
2023-01-23 01:33:13.054554: step: 960/529, loss: 0.14465287327766418
2023-01-23 01:33:14.269073: step: 964/529, loss: 0.13699102401733398
2023-01-23 01:33:15.483863: step: 968/529, loss: 0.04071617126464844
2023-01-23 01:33:16.661264: step: 972/529, loss: 0.08028783649206161
2023-01-23 01:33:17.882770: step: 976/529, loss: 0.0539124496281147
2023-01-23 01:33:19.066759: step: 980/529, loss: 0.03078932873904705
2023-01-23 01:33:20.249133: step: 984/529, loss: 0.008827686309814453
2023-01-23 01:33:21.439864: step: 988/529, loss: 0.004320716951042414
2023-01-23 01:33:22.634937: step: 992/529, loss: 0.03374020755290985
2023-01-23 01:33:23.811355: step: 996/529, loss: 0.04356823116540909
2023-01-23 01:33:25.014639: step: 1000/529, loss: 0.007504081819206476
2023-01-23 01:33:26.232638: step: 1004/529, loss: 0.2338055670261383
2023-01-23 01:33:27.431283: step: 1008/529, loss: 0.010401297360658646
2023-01-23 01:33:28.677653: step: 1012/529, loss: 0.7151467800140381
2023-01-23 01:33:29.896030: step: 1016/529, loss: 0.007266903296113014
2023-01-23 01:33:31.106222: step: 1020/529, loss: 0.03681335598230362
2023-01-23 01:33:32.312532: step: 1024/529, loss: 0.046021413058042526
2023-01-23 01:33:33.528534: step: 1028/529, loss: 0.5442251563072205
2023-01-23 01:33:34.736267: step: 1032/529, loss: 0.11134085804224014
2023-01-23 01:33:35.962603: step: 1036/529, loss: 0.03705864027142525
2023-01-23 01:33:37.140925: step: 1040/529, loss: 0.10039444267749786
2023-01-23 01:33:38.347292: step: 1044/529, loss: 0.035482216626405716
2023-01-23 01:33:39.580275: step: 1048/529, loss: 0.1307574212551117
2023-01-23 01:33:40.792090: step: 1052/529, loss: 0.0779542475938797
2023-01-23 01:33:41.978502: step: 1056/529, loss: 0.026824284344911575
2023-01-23 01:33:43.191095: step: 1060/529, loss: 0.06595049053430557
2023-01-23 01:33:44.383918: step: 1064/529, loss: 0.27425500750541687
2023-01-23 01:33:45.563163: step: 1068/529, loss: 0.8390282392501831
2023-01-23 01:33:46.750261: step: 1072/529, loss: 0.10883913189172745
2023-01-23 01:33:47.899331: step: 1076/529, loss: 0.4379534125328064
2023-01-23 01:33:49.058250: step: 1080/529, loss: 0.10718196630477905
2023-01-23 01:33:50.269190: step: 1084/529, loss: 0.6153775453567505
2023-01-23 01:33:51.503883: step: 1088/529, loss: 0.037024691700935364
2023-01-23 01:33:52.706023: step: 1092/529, loss: 0.09814572334289551
2023-01-23 01:33:53.869433: step: 1096/529, loss: 0.13121357560157776
2023-01-23 01:33:55.055687: step: 1100/529, loss: 0.004143333528190851
2023-01-23 01:33:56.224807: step: 1104/529, loss: 0.003635501954704523
2023-01-23 01:33:57.412619: step: 1108/529, loss: 0.09390535205602646
2023-01-23 01:33:58.627474: step: 1112/529, loss: 0.13246221840381622
2023-01-23 01:33:59.811383: step: 1116/529, loss: 0.04397711902856827
2023-01-23 01:34:00.991140: step: 1120/529, loss: 0.07568073272705078
2023-01-23 01:34:02.251568: step: 1124/529, loss: 0.024960899725556374
2023-01-23 01:34:03.474611: step: 1128/529, loss: 0.06967039406299591
2023-01-23 01:34:04.683989: step: 1132/529, loss: 0.03537330776453018
2023-01-23 01:34:05.901453: step: 1136/529, loss: 0.2469595968723297
2023-01-23 01:34:07.087802: step: 1140/529, loss: 0.03331012651324272
2023-01-23 01:34:08.230605: step: 1144/529, loss: 0.17991404235363007
2023-01-23 01:34:09.430566: step: 1148/529, loss: 0.0007800101884640753
2023-01-23 01:34:10.614761: step: 1152/529, loss: 0.03366527706384659
2023-01-23 01:34:11.800578: step: 1156/529, loss: 0.06735801696777344
2023-01-23 01:34:12.995716: step: 1160/529, loss: 0.01091608963906765
2023-01-23 01:34:14.197083: step: 1164/529, loss: 0.04776306077837944
2023-01-23 01:34:15.365860: step: 1168/529, loss: 0.020830631256103516
2023-01-23 01:34:16.539926: step: 1172/529, loss: 0.07038145512342453
2023-01-23 01:34:17.760993: step: 1176/529, loss: 0.035063743591308594
2023-01-23 01:34:18.957559: step: 1180/529, loss: 0.003455638885498047
2023-01-23 01:34:20.151917: step: 1184/529, loss: 0.024196529760956764
2023-01-23 01:34:21.339751: step: 1188/529, loss: 0.5926642417907715
2023-01-23 01:34:22.510934: step: 1192/529, loss: 0.016666889190673828
2023-01-23 01:34:23.703628: step: 1196/529, loss: 0.007498359773308039
2023-01-23 01:34:24.870642: step: 1200/529, loss: 0.08083172142505646
2023-01-23 01:34:26.049707: step: 1204/529, loss: 0.011226177215576172
2023-01-23 01:34:27.259702: step: 1208/529, loss: 0.026195431128144264
2023-01-23 01:34:28.408811: step: 1212/529, loss: 0.14075350761413574
2023-01-23 01:34:29.602239: step: 1216/529, loss: 0.01112380065023899
2023-01-23 01:34:30.814633: step: 1220/529, loss: 0.08782787621021271
2023-01-23 01:34:32.029756: step: 1224/529, loss: 0.045603275299072266
2023-01-23 01:34:33.229788: step: 1228/529, loss: 0.0511232390999794
2023-01-23 01:34:34.496162: step: 1232/529, loss: 0.033591464161872864
2023-01-23 01:34:35.677373: step: 1236/529, loss: 0.07966890186071396
2023-01-23 01:34:36.846493: step: 1240/529, loss: 0.08808381855487823
2023-01-23 01:34:38.042667: step: 1244/529, loss: 0.08162736892700195
2023-01-23 01:34:39.242775: step: 1248/529, loss: 0.004642772488296032
2023-01-23 01:34:40.437559: step: 1252/529, loss: 0.004563713446259499
2023-01-23 01:34:41.634069: step: 1256/529, loss: 0.04097886383533478
2023-01-23 01:34:42.814167: step: 1260/529, loss: 0.015616036020219326
2023-01-23 01:34:44.043581: step: 1264/529, loss: 0.2817387580871582
2023-01-23 01:34:45.223391: step: 1268/529, loss: 0.0014008521102368832
2023-01-23 01:34:46.399932: step: 1272/529, loss: 0.2954476475715637
2023-01-23 01:34:47.630789: step: 1276/529, loss: 0.016694659367203712
2023-01-23 01:34:48.836898: step: 1280/529, loss: 0.010402154177427292
2023-01-23 01:34:50.067139: step: 1284/529, loss: 0.010169655084609985
2023-01-23 01:34:51.301615: step: 1288/529, loss: 0.7191836833953857
2023-01-23 01:34:52.541400: step: 1292/529, loss: 0.04813079908490181
2023-01-23 01:34:53.776686: step: 1296/529, loss: 0.16865968704223633
2023-01-23 01:34:55.011609: step: 1300/529, loss: 0.0674375593662262
2023-01-23 01:34:56.276067: step: 1304/529, loss: 0.040503308176994324
2023-01-23 01:34:57.514711: step: 1308/529, loss: 0.009086275473237038
2023-01-23 01:34:58.758467: step: 1312/529, loss: 0.05688035488128662
2023-01-23 01:35:00.006835: step: 1316/529, loss: 0.13068923354148865
2023-01-23 01:35:01.215300: step: 1320/529, loss: 0.026905059814453125
2023-01-23 01:35:02.441177: step: 1324/529, loss: 0.02541036531329155
2023-01-23 01:35:03.619206: step: 1328/529, loss: 0.02647991105914116
2023-01-23 01:35:04.804634: step: 1332/529, loss: 0.03379230573773384
2023-01-23 01:35:06.012279: step: 1336/529, loss: 0.04011640325188637
2023-01-23 01:35:07.215124: step: 1340/529, loss: 0.051969338208436966
2023-01-23 01:35:08.402906: step: 1344/529, loss: 0.03831997141242027
2023-01-23 01:35:09.589407: step: 1348/529, loss: 0.0036433220375329256
2023-01-23 01:35:10.783346: step: 1352/529, loss: 0.031075477600097656
2023-01-23 01:35:12.016869: step: 1356/529, loss: 0.2768142819404602
2023-01-23 01:35:13.281519: step: 1360/529, loss: 0.11124163120985031
2023-01-23 01:35:14.467488: step: 1364/529, loss: 0.05142412334680557
2023-01-23 01:35:15.663215: step: 1368/529, loss: 0.06866578757762909
2023-01-23 01:35:16.874706: step: 1372/529, loss: 0.06152145937085152
2023-01-23 01:35:18.043942: step: 1376/529, loss: 0.04783432558178902
2023-01-23 01:35:19.228907: step: 1380/529, loss: 0.013824463821947575
2023-01-23 01:35:20.410685: step: 1384/529, loss: 0.04217877611517906
2023-01-23 01:35:21.608656: step: 1388/529, loss: 0.019161606207489967
2023-01-23 01:35:22.838115: step: 1392/529, loss: 0.014749813824892044
2023-01-23 01:35:24.024994: step: 1396/529, loss: 0.08193669468164444
2023-01-23 01:35:25.208887: step: 1400/529, loss: 1.2768535614013672
2023-01-23 01:35:26.407801: step: 1404/529, loss: 0.060097888112068176
2023-01-23 01:35:27.603745: step: 1408/529, loss: 0.03291139751672745
2023-01-23 01:35:28.798503: step: 1412/529, loss: 0.0447445884346962
2023-01-23 01:35:29.984891: step: 1416/529, loss: 0.06698312610387802
2023-01-23 01:35:31.203462: step: 1420/529, loss: 0.005542087368667126
2023-01-23 01:35:32.380115: step: 1424/529, loss: 0.0012058259453624487
2023-01-23 01:35:33.548008: step: 1428/529, loss: 0.01199884433299303
2023-01-23 01:35:34.753953: step: 1432/529, loss: 0.005538749508559704
2023-01-23 01:35:35.924215: step: 1436/529, loss: 0.1967674195766449
2023-01-23 01:35:37.158990: step: 1440/529, loss: 0.08329162746667862
2023-01-23 01:35:38.368826: step: 1444/529, loss: 0.09773287922143936
2023-01-23 01:35:39.578115: step: 1448/529, loss: 0.08748719841241837
2023-01-23 01:35:40.777958: step: 1452/529, loss: 0.11403703689575195
2023-01-23 01:35:42.007119: step: 1456/529, loss: 0.04840588569641113
2023-01-23 01:35:43.168105: step: 1460/529, loss: 0.021442366763949394
2023-01-23 01:35:44.351248: step: 1464/529, loss: 0.3614417016506195
2023-01-23 01:35:45.524676: step: 1468/529, loss: 0.05172135308384895
2023-01-23 01:35:46.684174: step: 1472/529, loss: 0.11756746470928192
2023-01-23 01:35:47.878394: step: 1476/529, loss: 0.03296380117535591
2023-01-23 01:35:49.059959: step: 1480/529, loss: 0.00482444791123271
2023-01-23 01:35:50.257204: step: 1484/529, loss: 0.04635229334235191
2023-01-23 01:35:51.476343: step: 1488/529, loss: 0.10678057372570038
2023-01-23 01:35:52.661007: step: 1492/529, loss: 0.08385252952575684
2023-01-23 01:35:53.833651: step: 1496/529, loss: 0.09917765110731125
2023-01-23 01:35:55.036406: step: 1500/529, loss: 0.0008244514465332031
2023-01-23 01:35:56.204524: step: 1504/529, loss: 0.006707263179123402
2023-01-23 01:35:57.409646: step: 1508/529, loss: 0.04261207580566406
2023-01-23 01:35:58.613381: step: 1512/529, loss: 0.038673970848321915
2023-01-23 01:35:59.806929: step: 1516/529, loss: 0.1708984375
2023-01-23 01:36:01.028826: step: 1520/529, loss: 0.02282085455954075
2023-01-23 01:36:02.252042: step: 1524/529, loss: 0.003697013948112726
2023-01-23 01:36:03.395626: step: 1528/529, loss: 0.1574891060590744
2023-01-23 01:36:04.559583: step: 1532/529, loss: 0.02370772324502468
2023-01-23 01:36:05.759497: step: 1536/529, loss: 0.1049346923828125
2023-01-23 01:36:07.004276: step: 1540/529, loss: 0.10836047679185867
2023-01-23 01:36:08.196059: step: 1544/529, loss: 0.06298549473285675
2023-01-23 01:36:09.423992: step: 1548/529, loss: 0.05909767374396324
2023-01-23 01:36:10.598884: step: 1552/529, loss: 0.22140489518642426
2023-01-23 01:36:11.790013: step: 1556/529, loss: 1.6520860195159912
2023-01-23 01:36:12.962592: step: 1560/529, loss: 0.03864097595214844
2023-01-23 01:36:14.170343: step: 1564/529, loss: 0.06007556617259979
2023-01-23 01:36:15.382893: step: 1568/529, loss: 0.0972478911280632
2023-01-23 01:36:16.529329: step: 1572/529, loss: 0.04356813430786133
2023-01-23 01:36:17.728759: step: 1576/529, loss: 0.023343658074736595
2023-01-23 01:36:18.936273: step: 1580/529, loss: 0.044876955449581146
2023-01-23 01:36:20.143338: step: 1584/529, loss: 0.09529328346252441
2023-01-23 01:36:21.341356: step: 1588/529, loss: 0.007829666137695312
2023-01-23 01:36:22.495449: step: 1592/529, loss: 0.009492016397416592
2023-01-23 01:36:23.728017: step: 1596/529, loss: 0.06847629696130753
2023-01-23 01:36:24.927357: step: 1600/529, loss: 0.04010649025440216
2023-01-23 01:36:26.089206: step: 1604/529, loss: 0.0021521567832678556
2023-01-23 01:36:27.260746: step: 1608/529, loss: 0.08057518303394318
2023-01-23 01:36:28.465609: step: 1612/529, loss: 0.0020606995094567537
2023-01-23 01:36:29.685434: step: 1616/529, loss: 0.011684322729706764
2023-01-23 01:36:30.951570: step: 1620/529, loss: 0.013513803482055664
2023-01-23 01:36:32.138575: step: 1624/529, loss: 0.049569036811590195
2023-01-23 01:36:33.367689: step: 1628/529, loss: 0.07808075100183487
2023-01-23 01:36:34.608334: step: 1632/529, loss: 0.0656675398349762
2023-01-23 01:36:35.833723: step: 1636/529, loss: 0.08072996884584427
2023-01-23 01:36:37.006419: step: 1640/529, loss: 0.10784606635570526
2023-01-23 01:36:38.220976: step: 1644/529, loss: 0.008269643411040306
2023-01-23 01:36:39.470282: step: 1648/529, loss: 0.02915988117456436
2023-01-23 01:36:40.675126: step: 1652/529, loss: 0.01055297814309597
2023-01-23 01:36:41.922700: step: 1656/529, loss: 0.16715869307518005
2023-01-23 01:36:43.149953: step: 1660/529, loss: 0.02644510380923748
2023-01-23 01:36:44.339400: step: 1664/529, loss: 0.039705850183963776
2023-01-23 01:36:45.518162: step: 1668/529, loss: 0.15847139060497284
2023-01-23 01:36:46.721898: step: 1672/529, loss: 0.0022668838500976562
2023-01-23 01:36:47.927496: step: 1676/529, loss: 0.05460897833108902
2023-01-23 01:36:49.117280: step: 1680/529, loss: 0.028580807149410248
2023-01-23 01:36:50.330875: step: 1684/529, loss: 0.009059716016054153
2023-01-23 01:36:51.516661: step: 1688/529, loss: 0.02703390084207058
2023-01-23 01:36:52.701072: step: 1692/529, loss: 0.11716632544994354
2023-01-23 01:36:53.898599: step: 1696/529, loss: 0.033617496490478516
2023-01-23 01:36:55.067250: step: 1700/529, loss: 0.014165449887514114
2023-01-23 01:36:56.286612: step: 1704/529, loss: 0.28714197874069214
2023-01-23 01:36:57.533024: step: 1708/529, loss: 0.06220531836152077
2023-01-23 01:36:58.753425: step: 1712/529, loss: 0.05443773418664932
2023-01-23 01:36:59.987913: step: 1716/529, loss: 0.05654316022992134
2023-01-23 01:37:01.175613: step: 1720/529, loss: 0.01900176890194416
2023-01-23 01:37:02.487071: step: 1724/529, loss: 0.05625953897833824
2023-01-23 01:37:03.669957: step: 1728/529, loss: 0.03941211849451065
2023-01-23 01:37:04.847833: step: 1732/529, loss: 0.047432586550712585
2023-01-23 01:37:06.103178: step: 1736/529, loss: 0.0619785338640213
2023-01-23 01:37:07.288857: step: 1740/529, loss: 0.03973264992237091
2023-01-23 01:37:08.463634: step: 1744/529, loss: 0.04565148428082466
2023-01-23 01:37:09.621982: step: 1748/529, loss: 0.002802229020744562
2023-01-23 01:37:10.828055: step: 1752/529, loss: 0.004509186837822199
2023-01-23 01:37:12.040381: step: 1756/529, loss: 0.07708778977394104
2023-01-23 01:37:13.216191: step: 1760/529, loss: 0.04762439802289009
2023-01-23 01:37:14.433677: step: 1764/529, loss: 0.023673629388213158
2023-01-23 01:37:15.637049: step: 1768/529, loss: 0.08362588286399841
2023-01-23 01:37:16.806923: step: 1772/529, loss: 0.032880593091249466
2023-01-23 01:37:17.990350: step: 1776/529, loss: 0.0415492057800293
2023-01-23 01:37:19.176689: step: 1780/529, loss: 0.020442772656679153
2023-01-23 01:37:20.341373: step: 1784/529, loss: 0.0461428165435791
2023-01-23 01:37:21.575738: step: 1788/529, loss: 0.005391550250351429
2023-01-23 01:37:22.799076: step: 1792/529, loss: 0.05739030987024307
2023-01-23 01:37:24.017034: step: 1796/529, loss: 0.08875790238380432
2023-01-23 01:37:25.180344: step: 1800/529, loss: 0.021050645038485527
2023-01-23 01:37:26.406345: step: 1804/529, loss: 0.11907606571912766
2023-01-23 01:37:27.603902: step: 1808/529, loss: 0.017148304730653763
2023-01-23 01:37:28.804768: step: 1812/529, loss: 0.010773849673569202
2023-01-23 01:37:30.022787: step: 1816/529, loss: 0.010222816839814186
2023-01-23 01:37:31.239644: step: 1820/529, loss: 0.0512174628674984
2023-01-23 01:37:32.478000: step: 1824/529, loss: 0.09181147068738937
2023-01-23 01:37:33.695200: step: 1828/529, loss: 0.0018573760753497481
2023-01-23 01:37:34.910078: step: 1832/529, loss: 0.007009983062744141
2023-01-23 01:37:36.111487: step: 1836/529, loss: 0.004858588799834251
2023-01-23 01:37:37.314939: step: 1840/529, loss: 0.03976621478796005
2023-01-23 01:37:38.509942: step: 1844/529, loss: 0.011035728268325329
2023-01-23 01:37:39.706798: step: 1848/529, loss: 0.010021209716796875
2023-01-23 01:37:40.905127: step: 1852/529, loss: 0.12872228026390076
2023-01-23 01:37:42.128282: step: 1856/529, loss: 0.36261507868766785
2023-01-23 01:37:43.299352: step: 1860/529, loss: 0.0037521361373364925
2023-01-23 01:37:44.459604: step: 1864/529, loss: 0.09352226555347443
2023-01-23 01:37:45.636557: step: 1868/529, loss: 0.04515848308801651
2023-01-23 01:37:46.843344: step: 1872/529, loss: 0.05004854127764702
2023-01-23 01:37:48.045586: step: 1876/529, loss: 0.025104999542236328
2023-01-23 01:37:49.232478: step: 1880/529, loss: 0.09868564456701279
2023-01-23 01:37:50.429846: step: 1884/529, loss: 0.06416326016187668
2023-01-23 01:37:51.606650: step: 1888/529, loss: 0.030042458325624466
2023-01-23 01:37:52.789902: step: 1892/529, loss: 0.032268330454826355
2023-01-23 01:37:53.979291: step: 1896/529, loss: 0.14064764976501465
2023-01-23 01:37:55.167442: step: 1900/529, loss: 0.021680736914277077
2023-01-23 01:37:56.365971: step: 1904/529, loss: 0.0785006508231163
2023-01-23 01:37:57.556475: step: 1908/529, loss: 0.14607620239257812
2023-01-23 01:37:58.814959: step: 1912/529, loss: 0.10666332393884659
2023-01-23 01:38:00.022488: step: 1916/529, loss: 0.05374584347009659
2023-01-23 01:38:01.193137: step: 1920/529, loss: 0.030852699652314186
2023-01-23 01:38:02.412527: step: 1924/529, loss: 0.012407065369188786
2023-01-23 01:38:03.591576: step: 1928/529, loss: 0.02901306189596653
2023-01-23 01:38:04.798767: step: 1932/529, loss: 0.0940331518650055
2023-01-23 01:38:05.999505: step: 1936/529, loss: 0.10514755547046661
2023-01-23 01:38:07.206306: step: 1940/529, loss: 0.005821514409035444
2023-01-23 01:38:08.396863: step: 1944/529, loss: 0.0033780098892748356
2023-01-23 01:38:09.597710: step: 1948/529, loss: 0.08220081031322479
2023-01-23 01:38:10.788854: step: 1952/529, loss: 0.10253963619470596
2023-01-23 01:38:12.004267: step: 1956/529, loss: 0.012839126400649548
2023-01-23 01:38:13.197330: step: 1960/529, loss: 0.0481351837515831
2023-01-23 01:38:14.389823: step: 1964/529, loss: 0.004809475038200617
2023-01-23 01:38:15.593486: step: 1968/529, loss: 0.05212026834487915
2023-01-23 01:38:16.783731: step: 1972/529, loss: 0.039101503789424896
2023-01-23 01:38:18.033056: step: 1976/529, loss: 0.021471597254276276
2023-01-23 01:38:19.239024: step: 1980/529, loss: 0.038008108735084534
2023-01-23 01:38:20.437488: step: 1984/529, loss: 0.0005153656238690019
2023-01-23 01:38:21.612001: step: 1988/529, loss: 0.05422983318567276
2023-01-23 01:38:22.806539: step: 1992/529, loss: 0.05885887145996094
2023-01-23 01:38:23.995548: step: 1996/529, loss: 0.09132575988769531
2023-01-23 01:38:25.162937: step: 2000/529, loss: 0.04573478922247887
2023-01-23 01:38:26.380639: step: 2004/529, loss: 0.031400490552186966
2023-01-23 01:38:27.596443: step: 2008/529, loss: 0.1244727075099945
2023-01-23 01:38:28.784477: step: 2012/529, loss: 0.030265428125858307
2023-01-23 01:38:30.018418: step: 2016/529, loss: 0.10329704731702805
2023-01-23 01:38:31.188710: step: 2020/529, loss: 0.0018930435180664062
2023-01-23 01:38:32.440323: step: 2024/529, loss: 0.02173147350549698
2023-01-23 01:38:33.616645: step: 2028/529, loss: 0.05556526407599449
2023-01-23 01:38:34.754206: step: 2032/529, loss: 0.01640152931213379
2023-01-23 01:38:36.031560: step: 2036/529, loss: 0.061226844787597656
2023-01-23 01:38:37.223710: step: 2040/529, loss: 0.0216490738093853
2023-01-23 01:38:38.463493: step: 2044/529, loss: 0.03312535211443901
2023-01-23 01:38:39.670396: step: 2048/529, loss: 0.030582714825868607
2023-01-23 01:38:40.893174: step: 2052/529, loss: 0.01811254397034645
2023-01-23 01:38:42.108658: step: 2056/529, loss: 0.0998251885175705
2023-01-23 01:38:43.294794: step: 2060/529, loss: 0.03838043287396431
2023-01-23 01:38:44.441705: step: 2064/529, loss: 0.04695744439959526
2023-01-23 01:38:45.640334: step: 2068/529, loss: 0.09503249824047089
2023-01-23 01:38:46.839191: step: 2072/529, loss: 0.016979455947875977
2023-01-23 01:38:48.066109: step: 2076/529, loss: 0.5666231513023376
2023-01-23 01:38:49.291133: step: 2080/529, loss: 0.043134406208992004
2023-01-23 01:38:50.476197: step: 2084/529, loss: 0.004335975740104914
2023-01-23 01:38:51.663404: step: 2088/529, loss: 0.005875587463378906
2023-01-23 01:38:52.844595: step: 2092/529, loss: 0.052643489092588425
2023-01-23 01:38:54.031319: step: 2096/529, loss: 0.08310270309448242
2023-01-23 01:38:55.240881: step: 2100/529, loss: 0.24817276000976562
2023-01-23 01:38:56.454779: step: 2104/529, loss: 0.030518721789121628
2023-01-23 01:38:57.646818: step: 2108/529, loss: 0.001597070717252791
2023-01-23 01:38:58.842003: step: 2112/529, loss: 0.10433516651391983
2023-01-23 01:39:00.019986: step: 2116/529, loss: 0.054807666689157486
==================================================
Loss: 0.080
--------------------
Dev: {'event': {'p': 0.5893037336024218, 'r': 0.7776298268974701, 'f1': 0.6704936854190586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6291547958214625, 'r': 0.7938885560215698, 'f1': 0.7019867549668874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5662650602409639, 'r': 0.8703703703703703, 'f1': 0.6861313868613138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 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': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 01:39:44.060150: step: 4/529, loss: 0.09461308270692825
2023-01-23 01:39:45.276020: step: 8/529, loss: 0.015323924832046032
2023-01-23 01:39:46.489084: step: 12/529, loss: 0.050940513610839844
2023-01-23 01:39:47.658230: step: 16/529, loss: 0.06520853191614151
2023-01-23 01:39:48.793916: step: 20/529, loss: 0.19915488362312317
2023-01-23 01:39:49.949276: step: 24/529, loss: 0.0025695799849927425
2023-01-23 01:39:51.147497: step: 28/529, loss: 0.015318823046982288
2023-01-23 01:39:52.372669: step: 32/529, loss: 0.06139631196856499
2023-01-23 01:39:53.540297: step: 36/529, loss: 0.006859683897346258
2023-01-23 01:39:54.719139: step: 40/529, loss: 0.0289854034781456
2023-01-23 01:39:55.942791: step: 44/529, loss: 0.12239294499158859
2023-01-23 01:39:57.154886: step: 48/529, loss: 0.022112753242254257
2023-01-23 01:39:58.362341: step: 52/529, loss: 0.004193782806396484
2023-01-23 01:39:59.538573: step: 56/529, loss: 0.0712035596370697
2023-01-23 01:40:00.747904: step: 60/529, loss: 0.016473818570375443
2023-01-23 01:40:01.993027: step: 64/529, loss: 0.04520554840564728
2023-01-23 01:40:03.163673: step: 68/529, loss: 0.00995492935180664
2023-01-23 01:40:04.329613: step: 72/529, loss: 0.019214224070310593
2023-01-23 01:40:05.504304: step: 76/529, loss: 0.2561284005641937
2023-01-23 01:40:06.677799: step: 80/529, loss: 0.059084296226501465
2023-01-23 01:40:07.857409: step: 84/529, loss: 0.0697411596775055
2023-01-23 01:40:09.073496: step: 88/529, loss: 5.209192752838135
2023-01-23 01:40:10.283236: step: 92/529, loss: 0.06205282360315323
2023-01-23 01:40:11.478992: step: 96/529, loss: 0.027886293828487396
2023-01-23 01:40:12.659105: step: 100/529, loss: 0.010370826348662376
2023-01-23 01:40:13.838405: step: 104/529, loss: 0.006428814493119717
2023-01-23 01:40:15.020255: step: 108/529, loss: 0.10677352547645569
2023-01-23 01:40:16.242625: step: 112/529, loss: 0.13863268494606018
2023-01-23 01:40:17.400874: step: 116/529, loss: 0.09578684717416763
2023-01-23 01:40:18.596890: step: 120/529, loss: 0.020717715844511986
2023-01-23 01:40:19.794010: step: 124/529, loss: 0.014867973513901234
2023-01-23 01:40:21.017368: step: 128/529, loss: 0.06393737345933914
2023-01-23 01:40:22.228737: step: 132/529, loss: 0.054084040224552155
2023-01-23 01:40:23.437218: step: 136/529, loss: 0.01900775544345379
2023-01-23 01:40:24.606530: step: 140/529, loss: 0.0064868927001953125
2023-01-23 01:40:25.808556: step: 144/529, loss: 0.018323326483368874
2023-01-23 01:40:27.003914: step: 148/529, loss: 0.007177924737334251
2023-01-23 01:40:28.198442: step: 152/529, loss: 0.05831766128540039
2023-01-23 01:40:29.384080: step: 156/529, loss: 0.013208579272031784
2023-01-23 01:40:30.589562: step: 160/529, loss: 0.014266777783632278
2023-01-23 01:40:31.810501: step: 164/529, loss: 0.12816008925437927
2023-01-23 01:40:33.010586: step: 168/529, loss: 0.019687842577695847
2023-01-23 01:40:34.212510: step: 172/529, loss: 0.025074752047657967
2023-01-23 01:40:35.429814: step: 176/529, loss: 0.041172221302986145
2023-01-23 01:40:36.610810: step: 180/529, loss: 0.14975497126579285
2023-01-23 01:40:37.809639: step: 184/529, loss: 0.10053076595067978
2023-01-23 01:40:39.000297: step: 188/529, loss: 0.03291922062635422
2023-01-23 01:40:40.255493: step: 192/529, loss: 0.024123001843690872
2023-01-23 01:40:41.455550: step: 196/529, loss: 0.09668521583080292
2023-01-23 01:40:42.675097: step: 200/529, loss: 0.006633949466049671
2023-01-23 01:40:43.865070: step: 204/529, loss: 0.01633734628558159
2023-01-23 01:40:45.040607: step: 208/529, loss: 0.016956424340605736
2023-01-23 01:40:46.278499: step: 212/529, loss: 0.07556218653917313
2023-01-23 01:40:47.499636: step: 216/529, loss: 0.07795467972755432
2023-01-23 01:40:48.708240: step: 220/529, loss: 0.010879325680434704
2023-01-23 01:40:49.858676: step: 224/529, loss: 0.0018048763740807772
2023-01-23 01:40:51.041840: step: 228/529, loss: 0.0389968603849411
2023-01-23 01:40:52.246878: step: 232/529, loss: 0.016606902703642845
2023-01-23 01:40:53.458935: step: 236/529, loss: 0.0254350658506155
2023-01-23 01:40:54.729735: step: 240/529, loss: 0.21078383922576904
2023-01-23 01:40:55.948327: step: 244/529, loss: 0.11606959998607635
2023-01-23 01:40:57.104154: step: 248/529, loss: 0.022133732214570045
2023-01-23 01:40:58.277962: step: 252/529, loss: 0.06801538169384003
2023-01-23 01:40:59.442393: step: 256/529, loss: 0.0504608154296875
2023-01-23 01:41:00.635185: step: 260/529, loss: 0.07034663110971451
2023-01-23 01:41:01.870939: step: 264/529, loss: 0.03427903354167938
2023-01-23 01:41:03.082158: step: 268/529, loss: 0.0036689518019557
2023-01-23 01:41:04.283664: step: 272/529, loss: 0.20312373340129852
2023-01-23 01:41:05.486983: step: 276/529, loss: 0.06532511860132217
2023-01-23 01:41:06.698224: step: 280/529, loss: 0.003205204149708152
2023-01-23 01:41:07.893995: step: 284/529, loss: 0.24573364853858948
2023-01-23 01:41:09.074262: step: 288/529, loss: 0.040628623217344284
2023-01-23 01:41:10.271199: step: 292/529, loss: 0.07421312481164932
2023-01-23 01:41:11.439096: step: 296/529, loss: 0.014757443219423294
2023-01-23 01:41:12.615410: step: 300/529, loss: 0.030996274203062057
2023-01-23 01:41:13.830481: step: 304/529, loss: 0.01604442670941353
2023-01-23 01:41:15.001793: step: 308/529, loss: 0.022764777764678
2023-01-23 01:41:16.171302: step: 312/529, loss: 0.0264129638671875
2023-01-23 01:41:17.358457: step: 316/529, loss: 0.02089815028011799
2023-01-23 01:41:18.598429: step: 320/529, loss: 0.019779682159423828
2023-01-23 01:41:19.761794: step: 324/529, loss: 0.002960694022476673
2023-01-23 01:41:20.906140: step: 328/529, loss: 0.0029618265107274055
2023-01-23 01:41:22.139158: step: 332/529, loss: 0.05655193328857422
2023-01-23 01:41:23.327644: step: 336/529, loss: 0.030414726585149765
2023-01-23 01:41:24.496078: step: 340/529, loss: 0.19958622753620148
2023-01-23 01:41:25.712702: step: 344/529, loss: 0.06624484062194824
2023-01-23 01:41:26.936405: step: 348/529, loss: 0.03439150005578995
2023-01-23 01:41:28.143814: step: 352/529, loss: 0.07798977196216583
2023-01-23 01:41:29.368596: step: 356/529, loss: 0.2156461775302887
2023-01-23 01:41:30.603167: step: 360/529, loss: 0.010379552841186523
2023-01-23 01:41:31.770742: step: 364/529, loss: 0.01006460189819336
2023-01-23 01:41:32.993900: step: 368/529, loss: 0.017821503803133965
2023-01-23 01:41:34.189642: step: 372/529, loss: 0.006402206607162952
2023-01-23 01:41:35.362018: step: 376/529, loss: 0.0037534714210778475
2023-01-23 01:41:36.537721: step: 380/529, loss: 0.0677327886223793
2023-01-23 01:41:37.714279: step: 384/529, loss: 0.038045406341552734
2023-01-23 01:41:38.875624: step: 388/529, loss: 0.024000264704227448
2023-01-23 01:41:40.056731: step: 392/529, loss: 0.12070684134960175
2023-01-23 01:41:41.250207: step: 396/529, loss: 0.0043558599427342415
2023-01-23 01:41:42.441908: step: 400/529, loss: 0.0075893402099609375
2023-01-23 01:41:43.638557: step: 404/529, loss: 0.007226181216537952
2023-01-23 01:41:44.860620: step: 408/529, loss: 0.046715546399354935
2023-01-23 01:41:46.072860: step: 412/529, loss: 0.0024368285667151213
2023-01-23 01:41:47.278633: step: 416/529, loss: 0.02151932753622532
2023-01-23 01:41:48.464867: step: 420/529, loss: 0.0023601532448083162
2023-01-23 01:41:49.651369: step: 424/529, loss: 0.03203096613287926
2023-01-23 01:41:50.841466: step: 428/529, loss: 0.003885936690494418
2023-01-23 01:41:52.016666: step: 432/529, loss: 0.07177035510540009
2023-01-23 01:41:53.203098: step: 436/529, loss: 0.012391472235321999
2023-01-23 01:41:54.360577: step: 440/529, loss: 0.05973052978515625
2023-01-23 01:41:55.566117: step: 444/529, loss: 0.06989746540784836
2023-01-23 01:41:56.797703: step: 448/529, loss: 0.004841280169785023
2023-01-23 01:41:57.981953: step: 452/529, loss: 0.09497766941785812
2023-01-23 01:41:59.211240: step: 456/529, loss: 0.03509116172790527
2023-01-23 01:42:00.436184: step: 460/529, loss: 0.10291356593370438
2023-01-23 01:42:01.604048: step: 464/529, loss: 0.013241196051239967
2023-01-23 01:42:02.809266: step: 468/529, loss: 0.019420623779296875
2023-01-23 01:42:04.011462: step: 472/529, loss: 0.022420763969421387
2023-01-23 01:42:05.214230: step: 476/529, loss: 0.07654790580272675
2023-01-23 01:42:06.415344: step: 480/529, loss: 0.09972763061523438
2023-01-23 01:42:07.627935: step: 484/529, loss: 0.007969999685883522
2023-01-23 01:42:08.829608: step: 488/529, loss: 0.07571058720350266
2023-01-23 01:42:10.019089: step: 492/529, loss: 0.0266784206032753
2023-01-23 01:42:11.191265: step: 496/529, loss: 0.015119075775146484
2023-01-23 01:42:12.429458: step: 500/529, loss: 0.014446831308305264
2023-01-23 01:42:13.632874: step: 504/529, loss: 0.0249054916203022
2023-01-23 01:42:14.836645: step: 508/529, loss: 0.08558405935764313
2023-01-23 01:42:16.003860: step: 512/529, loss: 0.014135551638901234
2023-01-23 01:42:17.229179: step: 516/529, loss: 0.019354963675141335
2023-01-23 01:42:18.452998: step: 520/529, loss: 0.2923146188259125
2023-01-23 01:42:19.707288: step: 524/529, loss: 0.026810120791196823
2023-01-23 01:42:20.911622: step: 528/529, loss: 0.11260776966810226
2023-01-23 01:42:22.103514: step: 532/529, loss: 0.04780283197760582
2023-01-23 01:42:23.312687: step: 536/529, loss: 0.0428677573800087
2023-01-23 01:42:24.507045: step: 540/529, loss: 0.005142593290656805
2023-01-23 01:42:25.690045: step: 544/529, loss: 0.01918959617614746
2023-01-23 01:42:26.854848: step: 548/529, loss: 0.011128854937851429
2023-01-23 01:42:28.064813: step: 552/529, loss: 0.054070379585027695
2023-01-23 01:42:29.334171: step: 556/529, loss: 0.03426065668463707
2023-01-23 01:42:30.541975: step: 560/529, loss: 0.01594552956521511
2023-01-23 01:42:31.732433: step: 564/529, loss: 0.04134702682495117
2023-01-23 01:42:32.954490: step: 568/529, loss: 0.0501188300549984
2023-01-23 01:42:34.149700: step: 572/529, loss: 0.09141997992992401
2023-01-23 01:42:35.326326: step: 576/529, loss: 0.028127051889896393
2023-01-23 01:42:36.503897: step: 580/529, loss: 0.026869487017393112
2023-01-23 01:42:37.667645: step: 584/529, loss: 0.030240248888731003
2023-01-23 01:42:38.881948: step: 588/529, loss: 0.02818460389971733
2023-01-23 01:42:40.045672: step: 592/529, loss: 0.023508453741669655
2023-01-23 01:42:41.241230: step: 596/529, loss: 0.05320854112505913
2023-01-23 01:42:42.479121: step: 600/529, loss: 0.07365011423826218
2023-01-23 01:42:43.656159: step: 604/529, loss: 0.0428253635764122
2023-01-23 01:42:44.862405: step: 608/529, loss: 0.06732264161109924
2023-01-23 01:42:46.032209: step: 612/529, loss: 0.03494701161980629
2023-01-23 01:42:47.198495: step: 616/529, loss: 0.004226016812026501
2023-01-23 01:42:48.396998: step: 620/529, loss: 0.03827972337603569
2023-01-23 01:42:49.595690: step: 624/529, loss: 0.21730975806713104
2023-01-23 01:42:50.797866: step: 628/529, loss: 0.0005623817560262978
2023-01-23 01:42:52.055006: step: 632/529, loss: 0.07962741702795029
2023-01-23 01:42:53.273779: step: 636/529, loss: 0.044205572456121445
2023-01-23 01:42:54.486276: step: 640/529, loss: 0.05206260830163956
2023-01-23 01:42:55.675487: step: 644/529, loss: 0.11605257540941238
2023-01-23 01:42:56.853997: step: 648/529, loss: 0.011652708053588867
2023-01-23 01:42:58.066194: step: 652/529, loss: 0.056532762944698334
2023-01-23 01:42:59.250583: step: 656/529, loss: 0.01340098399668932
2023-01-23 01:43:00.444612: step: 660/529, loss: 0.07416544109582901
2023-01-23 01:43:01.621128: step: 664/529, loss: 0.00959248561412096
2023-01-23 01:43:02.802275: step: 668/529, loss: 0.07944647967815399
2023-01-23 01:43:03.967676: step: 672/529, loss: 0.01790943183004856
2023-01-23 01:43:05.221054: step: 676/529, loss: 0.4197238087654114
2023-01-23 01:43:06.418466: step: 680/529, loss: 0.003906631376594305
2023-01-23 01:43:07.606502: step: 684/529, loss: 0.02599181979894638
2023-01-23 01:43:08.816622: step: 688/529, loss: 0.013612094335258007
2023-01-23 01:43:10.028021: step: 692/529, loss: 0.005812168121337891
2023-01-23 01:43:11.279106: step: 696/529, loss: 0.0794641524553299
2023-01-23 01:43:12.457781: step: 700/529, loss: 0.007331180386245251
2023-01-23 01:43:13.685835: step: 704/529, loss: 0.0018688678974285722
2023-01-23 01:43:14.888052: step: 708/529, loss: 0.04258701950311661
2023-01-23 01:43:16.091344: step: 712/529, loss: 0.17342452704906464
2023-01-23 01:43:17.277008: step: 716/529, loss: 0.0268572811037302
2023-01-23 01:43:18.492797: step: 720/529, loss: 0.3645104765892029
2023-01-23 01:43:19.689746: step: 724/529, loss: 0.05303540453314781
2023-01-23 01:43:20.906545: step: 728/529, loss: 0.01623992994427681
2023-01-23 01:43:22.124055: step: 732/529, loss: 0.17442341148853302
2023-01-23 01:43:23.304746: step: 736/529, loss: 0.05026240646839142
2023-01-23 01:43:24.516779: step: 740/529, loss: 0.06288299709558487
2023-01-23 01:43:25.750689: step: 744/529, loss: 0.0065247537568211555
2023-01-23 01:43:26.955859: step: 748/529, loss: 0.04794654995203018
2023-01-23 01:43:28.104365: step: 752/529, loss: 0.014880466274917126
2023-01-23 01:43:29.327120: step: 756/529, loss: 0.037469103932380676
2023-01-23 01:43:30.543733: step: 760/529, loss: 0.018707560375332832
2023-01-23 01:43:31.760404: step: 764/529, loss: 0.019561195746064186
2023-01-23 01:43:32.951279: step: 768/529, loss: 0.0009921550517901778
2023-01-23 01:43:34.203594: step: 772/529, loss: 0.25392797589302063
2023-01-23 01:43:35.415064: step: 776/529, loss: 0.33541297912597656
2023-01-23 01:43:36.606700: step: 780/529, loss: 0.01707172393798828
2023-01-23 01:43:37.806076: step: 784/529, loss: 0.02098911441862583
2023-01-23 01:43:39.050026: step: 788/529, loss: 0.3321826756000519
2023-01-23 01:43:40.270491: step: 792/529, loss: 0.3049025535583496
2023-01-23 01:43:41.462717: step: 796/529, loss: 0.10816683620214462
2023-01-23 01:43:42.608256: step: 800/529, loss: 0.025606347247958183
2023-01-23 01:43:43.809026: step: 804/529, loss: 0.02271747589111328
2023-01-23 01:43:45.046574: step: 808/529, loss: 0.010996055789291859
2023-01-23 01:43:46.251399: step: 812/529, loss: 0.006251621060073376
2023-01-23 01:43:47.424829: step: 816/529, loss: 0.013600422069430351
2023-01-23 01:43:48.637332: step: 820/529, loss: 0.019065190106630325
2023-01-23 01:43:49.837981: step: 824/529, loss: 0.04062776640057564
2023-01-23 01:43:51.026443: step: 828/529, loss: 0.019218921661376953
2023-01-23 01:43:52.205455: step: 832/529, loss: 0.013275337405502796
2023-01-23 01:43:53.412113: step: 836/529, loss: 0.012666894122958183
2023-01-23 01:43:54.610026: step: 840/529, loss: 0.0011449814774096012
2023-01-23 01:43:55.820096: step: 844/529, loss: 0.031485844403505325
2023-01-23 01:43:57.016485: step: 848/529, loss: 0.02624540403485298
2023-01-23 01:43:58.233789: step: 852/529, loss: 0.009102249518036842
2023-01-23 01:43:59.433316: step: 856/529, loss: 0.06545954197645187
2023-01-23 01:44:00.633723: step: 860/529, loss: 0.321106493473053
2023-01-23 01:44:01.824675: step: 864/529, loss: 0.028829121962189674
2023-01-23 01:44:03.094478: step: 868/529, loss: 0.021967221051454544
2023-01-23 01:44:04.317843: step: 872/529, loss: 0.061124518513679504
2023-01-23 01:44:05.520153: step: 876/529, loss: 0.06485958397388458
2023-01-23 01:44:06.747692: step: 880/529, loss: 0.022169413045048714
2023-01-23 01:44:07.957281: step: 884/529, loss: 0.005156898405402899
2023-01-23 01:44:09.278467: step: 888/529, loss: 0.03813190385699272
2023-01-23 01:44:10.477460: step: 892/529, loss: 0.0007540702936239541
2023-01-23 01:44:11.733567: step: 896/529, loss: 0.03882799297571182
2023-01-23 01:44:12.922805: step: 900/529, loss: 0.0030347825959324837
2023-01-23 01:44:14.147721: step: 904/529, loss: 0.013276767916977406
2023-01-23 01:44:15.352817: step: 908/529, loss: 0.06771676242351532
2023-01-23 01:44:16.559934: step: 912/529, loss: 0.012628268450498581
2023-01-23 01:44:17.729084: step: 916/529, loss: 0.11901235580444336
2023-01-23 01:44:18.929202: step: 920/529, loss: 0.3809569478034973
2023-01-23 01:44:20.111887: step: 924/529, loss: 0.030087757855653763
2023-01-23 01:44:21.358830: step: 928/529, loss: 0.17925891280174255
2023-01-23 01:44:22.559582: step: 932/529, loss: 0.018484115600585938
2023-01-23 01:44:23.785275: step: 936/529, loss: 0.04119310528039932
2023-01-23 01:44:24.965415: step: 940/529, loss: 0.05986042320728302
2023-01-23 01:44:26.221416: step: 944/529, loss: 0.046485330909490585
2023-01-23 01:44:27.422939: step: 948/529, loss: 0.004480266477912664
2023-01-23 01:44:28.593619: step: 952/529, loss: 0.05463600158691406
2023-01-23 01:44:29.818237: step: 956/529, loss: 0.0003727913135662675
2023-01-23 01:44:30.993712: step: 960/529, loss: 0.0339718796312809
2023-01-23 01:44:32.163539: step: 964/529, loss: 1.669961929321289
2023-01-23 01:44:33.356308: step: 968/529, loss: 0.006590652279555798
2023-01-23 01:44:34.578169: step: 972/529, loss: 0.052147865295410156
2023-01-23 01:44:35.768683: step: 976/529, loss: 0.011987876147031784
2023-01-23 01:44:36.946125: step: 980/529, loss: 0.026206208392977715
2023-01-23 01:44:38.126860: step: 984/529, loss: 0.031342603266239166
2023-01-23 01:44:39.324122: step: 988/529, loss: 0.03202629089355469
2023-01-23 01:44:40.511051: step: 992/529, loss: 0.030991649255156517
2023-01-23 01:44:41.720213: step: 996/529, loss: 0.026134680956602097
2023-01-23 01:44:42.937140: step: 1000/529, loss: 0.05096714198589325
2023-01-23 01:44:44.169663: step: 1004/529, loss: 0.2423064261674881
2023-01-23 01:44:45.362212: step: 1008/529, loss: 0.013319539837539196
2023-01-23 01:44:46.546062: step: 1012/529, loss: 0.07091889530420303
2023-01-23 01:44:47.710568: step: 1016/529, loss: 0.0694112777709961
2023-01-23 01:44:48.885450: step: 1020/529, loss: 0.11578676104545593
2023-01-23 01:44:50.123609: step: 1024/529, loss: 0.15999144315719604
2023-01-23 01:44:51.307592: step: 1028/529, loss: 0.006967830937355757
2023-01-23 01:44:52.523533: step: 1032/529, loss: 0.05098381265997887
2023-01-23 01:44:53.760740: step: 1036/529, loss: 0.08201351016759872
2023-01-23 01:44:54.984345: step: 1040/529, loss: 0.03741617500782013
2023-01-23 01:44:56.227510: step: 1044/529, loss: 0.017806481570005417
2023-01-23 01:44:57.434719: step: 1048/529, loss: 0.08050355315208435
2023-01-23 01:44:58.628121: step: 1052/529, loss: 0.5405857563018799
2023-01-23 01:44:59.794021: step: 1056/529, loss: 0.11757411807775497
2023-01-23 01:45:01.043845: step: 1060/529, loss: 0.21716323494911194
2023-01-23 01:45:02.240899: step: 1064/529, loss: 0.03898058086633682
2023-01-23 01:45:03.448893: step: 1068/529, loss: 0.017492199316620827
2023-01-23 01:45:04.650220: step: 1072/529, loss: 0.025894690304994583
2023-01-23 01:45:05.830159: step: 1076/529, loss: 0.018796445801854134
2023-01-23 01:45:07.059207: step: 1080/529, loss: 0.03311324119567871
2023-01-23 01:45:08.223240: step: 1084/529, loss: 0.06111498177051544
2023-01-23 01:45:09.464594: step: 1088/529, loss: 0.006524813361465931
2023-01-23 01:45:10.649742: step: 1092/529, loss: 0.043233491480350494
2023-01-23 01:45:11.821725: step: 1096/529, loss: 0.070864237844944
2023-01-23 01:45:13.013027: step: 1100/529, loss: 0.007418537046760321
2023-01-23 01:45:14.196136: step: 1104/529, loss: 0.0047269826754927635
2023-01-23 01:45:15.384904: step: 1108/529, loss: 0.022239113226532936
2023-01-23 01:45:16.591824: step: 1112/529, loss: 0.03437929227948189
2023-01-23 01:45:17.816854: step: 1116/529, loss: 0.05128903687000275
2023-01-23 01:45:19.012334: step: 1120/529, loss: 0.03506822511553764
2023-01-23 01:45:20.194321: step: 1124/529, loss: 0.024320315569639206
2023-01-23 01:45:21.420667: step: 1128/529, loss: 0.054823778569698334
2023-01-23 01:45:22.603630: step: 1132/529, loss: 0.06581497192382812
2023-01-23 01:45:23.800931: step: 1136/529, loss: 0.041820526123046875
2023-01-23 01:45:24.999323: step: 1140/529, loss: 0.12122364342212677
2023-01-23 01:45:26.173795: step: 1144/529, loss: 0.031093694269657135
2023-01-23 01:45:27.347065: step: 1148/529, loss: 0.8840776681900024
2023-01-23 01:45:28.541305: step: 1152/529, loss: 0.10295772552490234
2023-01-23 01:45:29.739273: step: 1156/529, loss: 0.01616945117712021
2023-01-23 01:45:30.953333: step: 1160/529, loss: 0.05126610025763512
2023-01-23 01:45:32.235957: step: 1164/529, loss: 0.0327458381652832
2023-01-23 01:45:33.402977: step: 1168/529, loss: 0.05950140953063965
2023-01-23 01:45:34.608675: step: 1172/529, loss: 0.09811064600944519
2023-01-23 01:45:35.810512: step: 1176/529, loss: 0.017319535836577415
2023-01-23 01:45:36.998983: step: 1180/529, loss: 0.013949966058135033
2023-01-23 01:45:38.219509: step: 1184/529, loss: 0.021736908704042435
2023-01-23 01:45:39.424963: step: 1188/529, loss: 0.008223820477724075
2023-01-23 01:45:40.623625: step: 1192/529, loss: 0.026146888732910156
2023-01-23 01:45:41.817252: step: 1196/529, loss: 0.07489853352308273
2023-01-23 01:45:43.042404: step: 1200/529, loss: 0.28294438123703003
2023-01-23 01:45:44.234781: step: 1204/529, loss: 0.09280635416507721
2023-01-23 01:45:45.425328: step: 1208/529, loss: 0.05431985855102539
2023-01-23 01:45:46.662890: step: 1212/529, loss: 0.015847016125917435
2023-01-23 01:45:47.899913: step: 1216/529, loss: 0.015099907293915749
2023-01-23 01:45:49.062472: step: 1220/529, loss: 0.018815994262695312
2023-01-23 01:45:50.255720: step: 1224/529, loss: 0.19454345107078552
2023-01-23 01:45:51.505419: step: 1228/529, loss: 0.03185071796178818
2023-01-23 01:45:52.673035: step: 1232/529, loss: 0.08119087666273117
2023-01-23 01:45:53.895680: step: 1236/529, loss: 0.028986692428588867
2023-01-23 01:45:55.085151: step: 1240/529, loss: 0.08334074169397354
2023-01-23 01:45:56.313089: step: 1244/529, loss: 0.0006021976005285978
2023-01-23 01:45:57.471876: step: 1248/529, loss: 0.017824841663241386
2023-01-23 01:45:58.632229: step: 1252/529, loss: 0.019753120839595795
2023-01-23 01:45:59.860950: step: 1256/529, loss: 0.057345200330019
2023-01-23 01:46:01.055454: step: 1260/529, loss: 0.08658619225025177
2023-01-23 01:46:02.252155: step: 1264/529, loss: 0.016444897279143333
2023-01-23 01:46:03.493547: step: 1268/529, loss: 0.01755542680621147
2023-01-23 01:46:04.700527: step: 1272/529, loss: 0.018363334238529205
2023-01-23 01:46:05.932833: step: 1276/529, loss: 0.05356493219733238
2023-01-23 01:46:07.099686: step: 1280/529, loss: 0.021189548075199127
2023-01-23 01:46:08.399639: step: 1284/529, loss: 0.07716875523328781
2023-01-23 01:46:09.630017: step: 1288/529, loss: 0.030627060681581497
2023-01-23 01:46:10.832787: step: 1292/529, loss: 0.04808850213885307
2023-01-23 01:46:12.022793: step: 1296/529, loss: 0.05766897276043892
2023-01-23 01:46:13.200700: step: 1300/529, loss: 0.1416155844926834
2023-01-23 01:46:14.399742: step: 1304/529, loss: 0.06356658786535263
2023-01-23 01:46:15.598074: step: 1308/529, loss: 0.006972694303840399
2023-01-23 01:46:16.801103: step: 1312/529, loss: 0.0775662362575531
2023-01-23 01:46:18.017578: step: 1316/529, loss: 0.021193789318203926
2023-01-23 01:46:19.194693: step: 1320/529, loss: 0.006855368614196777
2023-01-23 01:46:20.382931: step: 1324/529, loss: 0.05127792805433273
2023-01-23 01:46:21.599971: step: 1328/529, loss: 0.054251864552497864
2023-01-23 01:46:22.799660: step: 1332/529, loss: 0.016922971233725548
2023-01-23 01:46:23.960791: step: 1336/529, loss: 0.008650684729218483
2023-01-23 01:46:25.155912: step: 1340/529, loss: 0.004607868380844593
2023-01-23 01:46:26.383311: step: 1344/529, loss: 0.12435702979564667
2023-01-23 01:46:27.579049: step: 1348/529, loss: 0.015988444909453392
2023-01-23 01:46:28.743412: step: 1352/529, loss: 0.015291977673768997
2023-01-23 01:46:29.969075: step: 1356/529, loss: 0.03930168226361275
2023-01-23 01:46:31.194308: step: 1360/529, loss: 0.20888499915599823
2023-01-23 01:46:32.417011: step: 1364/529, loss: 0.03146400302648544
2023-01-23 01:46:33.672689: step: 1368/529, loss: 0.0033580781891942024
2023-01-23 01:46:34.921631: step: 1372/529, loss: 0.013326454907655716
2023-01-23 01:46:36.117509: step: 1376/529, loss: 0.013088989071547985
2023-01-23 01:46:37.295190: step: 1380/529, loss: 0.528385579586029
2023-01-23 01:46:38.493606: step: 1384/529, loss: 0.03378696367144585
2023-01-23 01:46:39.676962: step: 1388/529, loss: 0.006578922271728516
2023-01-23 01:46:40.878411: step: 1392/529, loss: 0.1777210235595703
2023-01-23 01:46:42.031646: step: 1396/529, loss: 0.04436364397406578
2023-01-23 01:46:43.294691: step: 1400/529, loss: 0.08823862671852112
2023-01-23 01:46:44.462197: step: 1404/529, loss: 0.15832966566085815
2023-01-23 01:46:45.686850: step: 1408/529, loss: 0.0797787681221962
2023-01-23 01:46:46.888701: step: 1412/529, loss: 0.0033970833756029606
2023-01-23 01:46:48.122740: step: 1416/529, loss: 0.059432413429021835
2023-01-23 01:46:49.333695: step: 1420/529, loss: 0.06300163269042969
2023-01-23 01:46:50.517791: step: 1424/529, loss: 0.09147863835096359
2023-01-23 01:46:51.714404: step: 1428/529, loss: 0.07947196811437607
2023-01-23 01:46:52.897954: step: 1432/529, loss: 0.02444438822567463
2023-01-23 01:46:54.089917: step: 1436/529, loss: 0.07819309830665588
2023-01-23 01:46:55.265035: step: 1440/529, loss: 0.009305763989686966
2023-01-23 01:46:56.455749: step: 1444/529, loss: 0.037786152213811874
2023-01-23 01:46:57.678870: step: 1448/529, loss: 0.16643677651882172
2023-01-23 01:46:58.857807: step: 1452/529, loss: 0.008370399475097656
2023-01-23 01:47:00.068824: step: 1456/529, loss: 0.04152803495526314
2023-01-23 01:47:01.248395: step: 1460/529, loss: 0.03420862928032875
2023-01-23 01:47:02.434965: step: 1464/529, loss: 0.006215715780854225
2023-01-23 01:47:03.629459: step: 1468/529, loss: 0.11815135180950165
2023-01-23 01:47:04.830693: step: 1472/529, loss: 0.08371029049158096
2023-01-23 01:47:06.057846: step: 1476/529, loss: 0.07180075347423553
2023-01-23 01:47:07.238200: step: 1480/529, loss: 0.08303123712539673
2023-01-23 01:47:08.441109: step: 1484/529, loss: 0.11439651995897293
2023-01-23 01:47:09.662212: step: 1488/529, loss: 0.13230475783348083
2023-01-23 01:47:10.850144: step: 1492/529, loss: 0.03144483640789986
2023-01-23 01:47:12.039681: step: 1496/529, loss: 0.121607206761837
2023-01-23 01:47:13.250467: step: 1500/529, loss: 0.030336331576108932
2023-01-23 01:47:14.422503: step: 1504/529, loss: 0.026038551703095436
2023-01-23 01:47:15.608640: step: 1508/529, loss: 0.13881778717041016
2023-01-23 01:47:16.777182: step: 1512/529, loss: 0.011060286313295364
2023-01-23 01:47:17.992438: step: 1516/529, loss: 0.022604942321777344
2023-01-23 01:47:19.169234: step: 1520/529, loss: 0.03933410719037056
2023-01-23 01:47:20.366717: step: 1524/529, loss: 0.007920932956039906
2023-01-23 01:47:21.572439: step: 1528/529, loss: 0.03963327407836914
2023-01-23 01:47:22.824695: step: 1532/529, loss: 0.05646514892578125
2023-01-23 01:47:24.008244: step: 1536/529, loss: 0.02344970777630806
2023-01-23 01:47:25.232048: step: 1540/529, loss: 0.039815474301576614
2023-01-23 01:47:26.399672: step: 1544/529, loss: 0.045206259936094284
2023-01-23 01:47:27.624216: step: 1548/529, loss: 0.37295645475387573
2023-01-23 01:47:28.853544: step: 1552/529, loss: 0.009088659659028053
2023-01-23 01:47:30.052880: step: 1556/529, loss: 0.06314563751220703
2023-01-23 01:47:31.237301: step: 1560/529, loss: 0.0035879136994481087
2023-01-23 01:47:32.435986: step: 1564/529, loss: 0.01016540452837944
2023-01-23 01:47:33.619875: step: 1568/529, loss: 0.03444109112024307
2023-01-23 01:47:34.836983: step: 1572/529, loss: 0.04573829472064972
2023-01-23 01:47:36.008406: step: 1576/529, loss: 0.0017147064208984375
2023-01-23 01:47:37.188600: step: 1580/529, loss: 0.19392293691635132
2023-01-23 01:47:38.375819: step: 1584/529, loss: 0.08233385533094406
2023-01-23 01:47:39.618150: step: 1588/529, loss: 0.8740646243095398
2023-01-23 01:47:40.813662: step: 1592/529, loss: 0.31442394852638245
2023-01-23 01:47:42.036654: step: 1596/529, loss: 0.055511474609375
2023-01-23 01:47:43.222150: step: 1600/529, loss: 0.05942859873175621
2023-01-23 01:47:44.393394: step: 1604/529, loss: 0.12933655083179474
2023-01-23 01:47:45.590228: step: 1608/529, loss: 0.061638880521059036
2023-01-23 01:47:46.760711: step: 1612/529, loss: 0.035477831959724426
2023-01-23 01:47:47.902878: step: 1616/529, loss: 0.037639666348695755
2023-01-23 01:47:49.087820: step: 1620/529, loss: 0.005637597758322954
2023-01-23 01:47:50.295369: step: 1624/529, loss: 0.04678850248456001
2023-01-23 01:47:51.528825: step: 1628/529, loss: 0.016644954681396484
2023-01-23 01:47:52.721587: step: 1632/529, loss: 0.035111334174871445
2023-01-23 01:47:53.897447: step: 1636/529, loss: 0.02014904096722603
2023-01-23 01:47:55.089186: step: 1640/529, loss: 0.031966306269168854
2023-01-23 01:47:56.315345: step: 1644/529, loss: 0.062006283551454544
2023-01-23 01:47:57.516951: step: 1648/529, loss: 0.05241985619068146
2023-01-23 01:47:58.760203: step: 1652/529, loss: 0.0505254752933979
2023-01-23 01:47:59.954373: step: 1656/529, loss: 0.004819107241928577
2023-01-23 01:48:01.133472: step: 1660/529, loss: 0.06722517311573029
2023-01-23 01:48:02.332360: step: 1664/529, loss: 0.007700538262724876
2023-01-23 01:48:03.492809: step: 1668/529, loss: 0.020280171185731888
2023-01-23 01:48:04.695884: step: 1672/529, loss: 0.08656089007854462
2023-01-23 01:48:05.884619: step: 1676/529, loss: 0.051488880068063736
2023-01-23 01:48:07.114274: step: 1680/529, loss: 0.025290392339229584
2023-01-23 01:48:08.293484: step: 1684/529, loss: 0.039223767817020416
2023-01-23 01:48:09.441393: step: 1688/529, loss: 0.025942638516426086
2023-01-23 01:48:10.664017: step: 1692/529, loss: 0.04711208492517471
2023-01-23 01:48:11.846618: step: 1696/529, loss: 0.012575579807162285
2023-01-23 01:48:13.081939: step: 1700/529, loss: 0.07909746468067169
2023-01-23 01:48:14.246455: step: 1704/529, loss: 0.0576418861746788
2023-01-23 01:48:15.474655: step: 1708/529, loss: 0.0006843090523034334
2023-01-23 01:48:16.640781: step: 1712/529, loss: 0.05928444862365723
2023-01-23 01:48:17.849829: step: 1716/529, loss: 0.009669494815170765
2023-01-23 01:48:19.084805: step: 1720/529, loss: 0.058765411376953125
2023-01-23 01:48:20.263183: step: 1724/529, loss: 0.03457631915807724
2023-01-23 01:48:21.467337: step: 1728/529, loss: 0.2439233809709549
2023-01-23 01:48:22.644989: step: 1732/529, loss: 0.07965365052223206
2023-01-23 01:48:23.829140: step: 1736/529, loss: 0.06890296936035156
2023-01-23 01:48:25.028612: step: 1740/529, loss: 0.1105751022696495
2023-01-23 01:48:26.228438: step: 1744/529, loss: 0.036740779876708984
2023-01-23 01:48:27.395512: step: 1748/529, loss: 0.03487520292401314
2023-01-23 01:48:28.613562: step: 1752/529, loss: 0.0848359614610672
2023-01-23 01:48:29.831322: step: 1756/529, loss: 0.024629021063447
2023-01-23 01:48:31.034844: step: 1760/529, loss: 0.06233549118041992
2023-01-23 01:48:32.275600: step: 1764/529, loss: 0.022668268531560898
2023-01-23 01:48:33.474887: step: 1768/529, loss: 0.031013870611786842
2023-01-23 01:48:34.684389: step: 1772/529, loss: 0.08588772267103195
2023-01-23 01:48:35.881818: step: 1776/529, loss: 0.019756412133574486
2023-01-23 01:48:37.071284: step: 1780/529, loss: 0.03923831135034561
2023-01-23 01:48:38.252886: step: 1784/529, loss: 0.04715175926685333
2023-01-23 01:48:39.488084: step: 1788/529, loss: 0.03348913416266441
2023-01-23 01:48:40.707777: step: 1792/529, loss: 0.24279536306858063
2023-01-23 01:48:41.894682: step: 1796/529, loss: 0.019339561462402344
2023-01-23 01:48:43.067285: step: 1800/529, loss: 0.13360892236232758
2023-01-23 01:48:44.278706: step: 1804/529, loss: 0.02291727066040039
2023-01-23 01:48:45.499620: step: 1808/529, loss: 0.03660411760210991
2023-01-23 01:48:46.743784: step: 1812/529, loss: 0.07315082848072052
2023-01-23 01:48:48.022792: step: 1816/529, loss: 0.037412360310554504
2023-01-23 01:48:49.266596: step: 1820/529, loss: 0.006944465916603804
2023-01-23 01:48:50.503954: step: 1824/529, loss: 0.06970392167568207
2023-01-23 01:48:51.706661: step: 1828/529, loss: 0.01299066562205553
2023-01-23 01:48:52.904090: step: 1832/529, loss: 0.07199078053236008
2023-01-23 01:48:54.096321: step: 1836/529, loss: 0.011887121014297009
2023-01-23 01:48:55.323975: step: 1840/529, loss: 0.00045189858064986765
2023-01-23 01:48:56.525156: step: 1844/529, loss: 0.02391376718878746
2023-01-23 01:48:57.759098: step: 1848/529, loss: 0.23020629584789276
2023-01-23 01:48:58.960576: step: 1852/529, loss: 0.012273884378373623
2023-01-23 01:49:00.166814: step: 1856/529, loss: 0.005406570620834827
2023-01-23 01:49:01.377103: step: 1860/529, loss: 0.03417768329381943
2023-01-23 01:49:02.560500: step: 1864/529, loss: 0.052526094019412994
2023-01-23 01:49:03.746414: step: 1868/529, loss: 0.009327221661806107
2023-01-23 01:49:05.016984: step: 1872/529, loss: 0.30849599838256836
2023-01-23 01:49:06.228151: step: 1876/529, loss: 0.04136858135461807
2023-01-23 01:49:07.398826: step: 1880/529, loss: 0.023511648178100586
2023-01-23 01:49:08.604135: step: 1884/529, loss: 0.007583570666611195
2023-01-23 01:49:09.786607: step: 1888/529, loss: 0.06826065480709076
2023-01-23 01:49:10.990386: step: 1892/529, loss: 0.06730309128761292
2023-01-23 01:49:12.178247: step: 1896/529, loss: 0.016716431826353073
2023-01-23 01:49:13.391771: step: 1900/529, loss: 0.014785576611757278
2023-01-23 01:49:14.580805: step: 1904/529, loss: 0.04808998107910156
2023-01-23 01:49:15.770538: step: 1908/529, loss: 0.03860732913017273
2023-01-23 01:49:16.947721: step: 1912/529, loss: 0.00348491664044559
2023-01-23 01:49:18.128706: step: 1916/529, loss: 0.005905247293412685
2023-01-23 01:49:19.339713: step: 1920/529, loss: 0.015135146677494049
2023-01-23 01:49:20.520788: step: 1924/529, loss: 0.024395275861024857
2023-01-23 01:49:21.705757: step: 1928/529, loss: 0.008846092969179153
2023-01-23 01:49:22.928971: step: 1932/529, loss: 0.03268633037805557
2023-01-23 01:49:24.133541: step: 1936/529, loss: 0.24961014091968536
2023-01-23 01:49:25.383975: step: 1940/529, loss: 0.007929516024887562
2023-01-23 01:49:26.566397: step: 1944/529, loss: 0.05357445776462555
2023-01-23 01:49:27.748375: step: 1948/529, loss: 0.029566098004579544
2023-01-23 01:49:28.966302: step: 1952/529, loss: 0.008351707831025124
2023-01-23 01:49:30.177156: step: 1956/529, loss: 0.008855628781020641
2023-01-23 01:49:31.379597: step: 1960/529, loss: 0.10262642055749893
2023-01-23 01:49:32.612875: step: 1964/529, loss: 0.05252294987440109
2023-01-23 01:49:33.819755: step: 1968/529, loss: 0.004825973883271217
2023-01-23 01:49:35.002667: step: 1972/529, loss: 0.00816421490162611
2023-01-23 01:49:36.204416: step: 1976/529, loss: 0.06373405456542969
2023-01-23 01:49:37.400742: step: 1980/529, loss: 0.016758346930146217
2023-01-23 01:49:38.612641: step: 1984/529, loss: 0.034069158136844635
2023-01-23 01:49:39.816399: step: 1988/529, loss: 0.06388463824987411
2023-01-23 01:49:41.024283: step: 1992/529, loss: 0.015813924372196198
2023-01-23 01:49:42.258711: step: 1996/529, loss: 0.024594688788056374
2023-01-23 01:49:43.476767: step: 2000/529, loss: 0.014341259375214577
2023-01-23 01:49:44.630518: step: 2004/529, loss: 0.028731895610690117
2023-01-23 01:49:45.825320: step: 2008/529, loss: 0.013081742450594902
2023-01-23 01:49:47.057695: step: 2012/529, loss: 0.05651276186108589
2023-01-23 01:49:48.264037: step: 2016/529, loss: 0.025107288733124733
2023-01-23 01:49:49.445009: step: 2020/529, loss: 0.019038867205381393
2023-01-23 01:49:50.639981: step: 2024/529, loss: 0.0070785521529614925
2023-01-23 01:49:51.864069: step: 2028/529, loss: 0.04467587545514107
2023-01-23 01:49:53.034297: step: 2032/529, loss: 0.0174710750579834
2023-01-23 01:49:54.209381: step: 2036/529, loss: 0.15973225235939026
2023-01-23 01:49:55.383817: step: 2040/529, loss: 0.018823623657226562
2023-01-23 01:49:56.558059: step: 2044/529, loss: 0.008092689327895641
2023-01-23 01:49:57.741528: step: 2048/529, loss: 0.04268283769488335
2023-01-23 01:49:58.970725: step: 2052/529, loss: 0.004303073976188898
2023-01-23 01:50:00.169246: step: 2056/529, loss: 0.03626861423254013
2023-01-23 01:50:01.387889: step: 2060/529, loss: 0.030824948102235794
2023-01-23 01:50:02.572872: step: 2064/529, loss: 0.077679343521595
2023-01-23 01:50:03.797183: step: 2068/529, loss: 0.021583938971161842
2023-01-23 01:50:05.069832: step: 2072/529, loss: 0.0035893439780920744
2023-01-23 01:50:06.282354: step: 2076/529, loss: 0.027521992102265358
2023-01-23 01:50:07.506722: step: 2080/529, loss: 0.0003895759582519531
2023-01-23 01:50:08.676558: step: 2084/529, loss: 0.008096123114228249
2023-01-23 01:50:09.848944: step: 2088/529, loss: 0.05906124413013458
2023-01-23 01:50:11.004671: step: 2092/529, loss: 0.026816463097929955
2023-01-23 01:50:12.203754: step: 2096/529, loss: 0.047417543828487396
2023-01-23 01:50:13.458586: step: 2100/529, loss: 0.03231191635131836
2023-01-23 01:50:14.649040: step: 2104/529, loss: 0.08727569878101349
2023-01-23 01:50:15.872526: step: 2108/529, loss: 0.10679206252098083
2023-01-23 01:50:17.040063: step: 2112/529, loss: 0.03921813890337944
2023-01-23 01:50:18.230533: step: 2116/529, loss: 0.046384263783693314
==================================================
Loss: 0.072
--------------------
Dev: {'event': {'p': 0.5710144927536231, 'r': 0.7869507323568575, 'f1': 0.6618141097424413}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6354166666666666, 'r': 0.8040742959856201, 'f1': 0.7098651150489288}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5161290322580645, 'r': 0.8888888888888888, 'f1': 0.6530612244897959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.5423728813559322, 'r': 0.5079365079365079, 'f1': 0.5245901639344263}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 01:51:02.032772: step: 4/529, loss: 0.03589210286736488
2023-01-23 01:51:03.218462: step: 8/529, loss: 0.04646158218383789
2023-01-23 01:51:04.411567: step: 12/529, loss: 0.0015617371536791325
2023-01-23 01:51:05.618764: step: 16/529, loss: 0.009456157684326172
2023-01-23 01:51:06.830653: step: 20/529, loss: 0.036652661859989166
2023-01-23 01:51:08.036987: step: 24/529, loss: 0.07016907632350922
2023-01-23 01:51:09.200211: step: 28/529, loss: 0.007915496826171875
2023-01-23 01:51:10.417527: step: 32/529, loss: 0.04337654262781143
2023-01-23 01:51:11.589789: step: 36/529, loss: 0.0009256363264285028
2023-01-23 01:51:12.818256: step: 40/529, loss: 0.08891038596630096
2023-01-23 01:51:14.028516: step: 44/529, loss: 0.06703028827905655
2023-01-23 01:51:15.203821: step: 48/529, loss: 0.03881406784057617
2023-01-23 01:51:16.376229: step: 52/529, loss: 0.05977373197674751
2023-01-23 01:51:17.583136: step: 56/529, loss: 0.0228405948728323
2023-01-23 01:51:18.811739: step: 60/529, loss: 0.04689016565680504
2023-01-23 01:51:20.023194: step: 64/529, loss: 0.04889635741710663
2023-01-23 01:51:21.195682: step: 68/529, loss: 0.09251828491687775
2023-01-23 01:51:22.366254: step: 72/529, loss: 0.06995969265699387
2023-01-23 01:51:23.550289: step: 76/529, loss: 0.042516373097896576
2023-01-23 01:51:24.756287: step: 80/529, loss: 1.0364328622817993
2023-01-23 01:51:25.964264: step: 84/529, loss: 0.006809329614043236
2023-01-23 01:51:27.169851: step: 88/529, loss: 0.1515457183122635
2023-01-23 01:51:28.404630: step: 92/529, loss: 0.01153254508972168
2023-01-23 01:51:29.630338: step: 96/529, loss: 0.04926338046789169
2023-01-23 01:51:30.821388: step: 100/529, loss: 0.02107715606689453
2023-01-23 01:51:32.050669: step: 104/529, loss: 0.04326820373535156
2023-01-23 01:51:33.249484: step: 108/529, loss: 0.04518928378820419
2023-01-23 01:51:34.477221: step: 112/529, loss: 0.22474442422389984
2023-01-23 01:51:35.653156: step: 116/529, loss: 0.043840885162353516
2023-01-23 01:51:36.842166: step: 120/529, loss: 0.04966764152050018
2023-01-23 01:51:38.007361: step: 124/529, loss: 0.025442887097597122
2023-01-23 01:51:39.224686: step: 128/529, loss: 0.030176257714629173
2023-01-23 01:51:40.472480: step: 132/529, loss: 0.02025279961526394
2023-01-23 01:51:41.665355: step: 136/529, loss: 0.029550839215517044
2023-01-23 01:51:42.852864: step: 140/529, loss: 0.017325783148407936
2023-01-23 01:51:44.037446: step: 144/529, loss: 0.013940048404037952
2023-01-23 01:51:45.227881: step: 148/529, loss: 0.02227191999554634
2023-01-23 01:51:46.420672: step: 152/529, loss: 0.021846294403076172
2023-01-23 01:51:47.600765: step: 156/529, loss: 0.0671592727303505
2023-01-23 01:51:48.789960: step: 160/529, loss: 0.02972097508609295
2023-01-23 01:51:50.019573: step: 164/529, loss: 0.023504257202148438
2023-01-23 01:51:51.193656: step: 168/529, loss: 0.05240507051348686
2023-01-23 01:51:52.376763: step: 172/529, loss: 0.012106704525649548
2023-01-23 01:51:53.521450: step: 176/529, loss: 0.00878896750509739
2023-01-23 01:51:54.705161: step: 180/529, loss: 0.011750412173569202
2023-01-23 01:51:55.901883: step: 184/529, loss: 0.680425226688385
2023-01-23 01:51:57.092075: step: 188/529, loss: 0.02919158898293972
2023-01-23 01:51:58.342140: step: 192/529, loss: 0.361136257648468
2023-01-23 01:51:59.544464: step: 196/529, loss: 0.06529875099658966
2023-01-23 01:52:00.728068: step: 200/529, loss: 0.16266211867332458
2023-01-23 01:52:01.940400: step: 204/529, loss: 0.0011018753284588456
2023-01-23 01:52:03.161542: step: 208/529, loss: 0.04203929752111435
2023-01-23 01:52:04.361061: step: 212/529, loss: 0.0029926300048828125
2023-01-23 01:52:05.526235: step: 216/529, loss: 0.05895552784204483
2023-01-23 01:52:06.734988: step: 220/529, loss: 0.0029110193718224764
2023-01-23 01:52:07.945034: step: 224/529, loss: 0.018513107672333717
2023-01-23 01:52:09.123419: step: 228/529, loss: 0.01807880401611328
2023-01-23 01:52:10.307932: step: 232/529, loss: 0.0023907662834972143
2023-01-23 01:52:11.497199: step: 236/529, loss: 0.31831127405166626
2023-01-23 01:52:12.709319: step: 240/529, loss: 0.011489678174257278
2023-01-23 01:52:13.900355: step: 244/529, loss: 0.028061963617801666
2023-01-23 01:52:15.074168: step: 248/529, loss: 0.037703897804021835
2023-01-23 01:52:16.265675: step: 252/529, loss: 0.008648396469652653
2023-01-23 01:52:17.502581: step: 256/529, loss: 0.007590389344841242
2023-01-23 01:52:18.688580: step: 260/529, loss: 0.06069403141736984
2023-01-23 01:52:19.884131: step: 264/529, loss: 0.05303707346320152
2023-01-23 01:52:21.111569: step: 268/529, loss: 0.010276603512465954
2023-01-23 01:52:22.307965: step: 272/529, loss: 0.011726569384336472
2023-01-23 01:52:23.473891: step: 276/529, loss: 0.04112198203802109
2023-01-23 01:52:24.706681: step: 280/529, loss: 0.0410066619515419
2023-01-23 01:52:25.912034: step: 284/529, loss: 0.010034275241196156
2023-01-23 01:52:27.112538: step: 288/529, loss: 0.11113253235816956
2023-01-23 01:52:28.314312: step: 292/529, loss: 0.05635128170251846
2023-01-23 01:52:29.505228: step: 296/529, loss: 0.013919925317168236
2023-01-23 01:52:30.710799: step: 300/529, loss: 0.023853302001953125
2023-01-23 01:52:31.942326: step: 304/529, loss: 0.05160675197839737
2023-01-23 01:52:33.123210: step: 308/529, loss: 0.0018610000843182206
2023-01-23 01:52:34.330820: step: 312/529, loss: 0.0082855224609375
2023-01-23 01:52:35.499187: step: 316/529, loss: 0.09461002796888351
2023-01-23 01:52:36.689875: step: 320/529, loss: 0.0010989189613610506
2023-01-23 01:52:37.924788: step: 324/529, loss: 0.012009715661406517
2023-01-23 01:52:39.143538: step: 328/529, loss: 0.034279823303222656
2023-01-23 01:52:40.323277: step: 332/529, loss: 0.0033151626121252775
2023-01-23 01:52:41.506274: step: 336/529, loss: 0.0009092331165447831
2023-01-23 01:52:42.656004: step: 340/529, loss: 0.08475551754236221
2023-01-23 01:52:43.840741: step: 344/529, loss: 0.021069718524813652
2023-01-23 01:52:45.023260: step: 348/529, loss: 0.05076861381530762
2023-01-23 01:52:46.234914: step: 352/529, loss: 0.02338237874209881
2023-01-23 01:52:47.413770: step: 356/529, loss: 0.029043961316347122
2023-01-23 01:52:48.599037: step: 360/529, loss: 0.0011564254527911544
2023-01-23 01:52:49.817198: step: 364/529, loss: 0.0520382896065712
2023-01-23 01:52:51.043223: step: 368/529, loss: 0.0035355566069483757
2023-01-23 01:52:52.242504: step: 372/529, loss: 0.02729806862771511
2023-01-23 01:52:53.465716: step: 376/529, loss: 0.016955947503447533
2023-01-23 01:52:54.661632: step: 380/529, loss: 0.045243073254823685
2023-01-23 01:52:55.836926: step: 384/529, loss: 0.0070375921204686165
2023-01-23 01:52:56.972520: step: 388/529, loss: 0.01606140285730362
2023-01-23 01:52:58.151130: step: 392/529, loss: 0.7768144011497498
2023-01-23 01:52:59.356553: step: 396/529, loss: 0.013397599570453167
2023-01-23 01:53:00.553748: step: 400/529, loss: 0.01559677068144083
2023-01-23 01:53:01.715450: step: 404/529, loss: 0.002626609755679965
2023-01-23 01:53:02.933058: step: 408/529, loss: 0.041284941136837006
2023-01-23 01:53:04.088752: step: 412/529, loss: 0.04969969019293785
2023-01-23 01:53:05.275762: step: 416/529, loss: 0.22172483801841736
2023-01-23 01:53:06.434620: step: 420/529, loss: 0.040380001068115234
2023-01-23 01:53:07.671249: step: 424/529, loss: 0.004055786412209272
2023-01-23 01:53:08.862837: step: 428/529, loss: 0.005878734402358532
2023-01-23 01:53:10.067193: step: 432/529, loss: 0.015458201989531517
2023-01-23 01:53:11.232016: step: 436/529, loss: 0.12731723487377167
2023-01-23 01:53:12.422913: step: 440/529, loss: 0.05409574508666992
2023-01-23 01:53:13.639498: step: 444/529, loss: 0.008396720513701439
2023-01-23 01:53:14.811821: step: 448/529, loss: 0.019727088510990143
2023-01-23 01:53:16.011473: step: 452/529, loss: 0.09304781258106232
2023-01-23 01:53:17.198292: step: 456/529, loss: 0.02880227565765381
2023-01-23 01:53:18.399556: step: 460/529, loss: 0.009797525592148304
2023-01-23 01:53:19.581322: step: 464/529, loss: 0.015048407949507236
2023-01-23 01:53:20.782902: step: 468/529, loss: 0.03133077546954155
2023-01-23 01:53:21.944904: step: 472/529, loss: 0.0329648032784462
2023-01-23 01:53:23.143712: step: 476/529, loss: 0.07482966780662537
2023-01-23 01:53:24.312855: step: 480/529, loss: 0.002013778779655695
2023-01-23 01:53:25.488455: step: 484/529, loss: 0.06957130879163742
2023-01-23 01:53:26.672421: step: 488/529, loss: 0.03861398622393608
2023-01-23 01:53:27.839938: step: 492/529, loss: 0.04085197299718857
2023-01-23 01:53:29.007058: step: 496/529, loss: 0.04988241195678711
2023-01-23 01:53:30.209296: step: 500/529, loss: 0.0883125364780426
2023-01-23 01:53:31.478222: step: 504/529, loss: 0.019052695482969284
2023-01-23 01:53:32.677731: step: 508/529, loss: 0.039664555341005325
2023-01-23 01:53:33.865285: step: 512/529, loss: 0.08069401234388351
2023-01-23 01:53:35.085687: step: 516/529, loss: 0.007090187165886164
2023-01-23 01:53:36.289462: step: 520/529, loss: 0.03291063383221626
2023-01-23 01:53:37.495353: step: 524/529, loss: 0.05287685617804527
2023-01-23 01:53:38.675301: step: 528/529, loss: 0.00021538735018111765
2023-01-23 01:53:39.857911: step: 532/529, loss: 0.07650041580200195
2023-01-23 01:53:41.058397: step: 536/529, loss: 0.024096012115478516
2023-01-23 01:53:42.309923: step: 540/529, loss: 0.03077392652630806
2023-01-23 01:53:43.523816: step: 544/529, loss: 0.04125552251935005
2023-01-23 01:53:44.731220: step: 548/529, loss: 0.047049619257450104
2023-01-23 01:53:45.927368: step: 552/529, loss: 0.03869781643152237
2023-01-23 01:53:47.181734: step: 556/529, loss: 0.00636062677949667
2023-01-23 01:53:48.383155: step: 560/529, loss: 0.0735289603471756
2023-01-23 01:53:49.551799: step: 564/529, loss: 0.027564240619540215
2023-01-23 01:53:50.747591: step: 568/529, loss: 0.016397427767515182
2023-01-23 01:53:51.984513: step: 572/529, loss: 0.061690427362918854
2023-01-23 01:53:53.188552: step: 576/529, loss: 0.13451018929481506
2023-01-23 01:53:54.365181: step: 580/529, loss: 0.09298533201217651
2023-01-23 01:53:55.570406: step: 584/529, loss: 0.023816490545868874
2023-01-23 01:53:56.744836: step: 588/529, loss: 0.10072250664234161
2023-01-23 01:53:57.977644: step: 592/529, loss: 0.006880283355712891
2023-01-23 01:53:59.212306: step: 596/529, loss: 0.018852615728974342
2023-01-23 01:54:00.399394: step: 600/529, loss: 0.30449360609054565
2023-01-23 01:54:01.545588: step: 604/529, loss: 0.0024212838616222143
2023-01-23 01:54:02.768932: step: 608/529, loss: 0.013472843915224075
2023-01-23 01:54:03.963356: step: 612/529, loss: 0.030254507437348366
2023-01-23 01:54:05.150198: step: 616/529, loss: 0.009787368588149548
2023-01-23 01:54:06.394652: step: 620/529, loss: 0.013148308731615543
2023-01-23 01:54:07.580475: step: 624/529, loss: 0.016123484820127487
2023-01-23 01:54:08.790185: step: 628/529, loss: 0.001380824949592352
2023-01-23 01:54:10.022492: step: 632/529, loss: 0.0006970405811443925
2023-01-23 01:54:11.245863: step: 636/529, loss: 0.09678631275892258
2023-01-23 01:54:12.394319: step: 640/529, loss: 0.08303698897361755
2023-01-23 01:54:13.565683: step: 644/529, loss: 0.0005417346837930381
2023-01-23 01:54:14.743947: step: 648/529, loss: 0.02665691450238228
2023-01-23 01:54:15.936499: step: 652/529, loss: 0.12355299293994904
2023-01-23 01:54:17.140895: step: 656/529, loss: 0.002891921903938055
2023-01-23 01:54:18.383389: step: 660/529, loss: 0.08119087666273117
2023-01-23 01:54:19.595988: step: 664/529, loss: 0.07087497413158417
2023-01-23 01:54:20.763695: step: 668/529, loss: 0.010590840131044388
2023-01-23 01:54:21.963989: step: 672/529, loss: 0.016165543347597122
2023-01-23 01:54:23.132124: step: 676/529, loss: 0.0018718719948083162
2023-01-23 01:54:24.299861: step: 680/529, loss: 0.009228992275893688
2023-01-23 01:54:25.465606: step: 684/529, loss: 0.04632072150707245
2023-01-23 01:54:26.693183: step: 688/529, loss: 0.03412752225995064
2023-01-23 01:54:27.891581: step: 692/529, loss: 0.030023861676454544
2023-01-23 01:54:29.085824: step: 696/529, loss: 0.01071634329855442
2023-01-23 01:54:30.269617: step: 700/529, loss: 0.154022216796875
2023-01-23 01:54:31.448306: step: 704/529, loss: 0.10907518118619919
2023-01-23 01:54:32.668400: step: 708/529, loss: 0.00128002162091434
2023-01-23 01:54:33.876729: step: 712/529, loss: 0.05320291593670845
2023-01-23 01:54:35.059157: step: 716/529, loss: 0.0026769163087010384
2023-01-23 01:54:36.232012: step: 720/529, loss: 0.004432487301528454
2023-01-23 01:54:37.456785: step: 724/529, loss: 0.011027717962861061
2023-01-23 01:54:38.668901: step: 728/529, loss: 0.06812162697315216
2023-01-23 01:54:39.844872: step: 732/529, loss: 0.03999815136194229
2023-01-23 01:54:41.070065: step: 736/529, loss: 0.0667715072631836
2023-01-23 01:54:42.322509: step: 740/529, loss: 0.013537026010453701
2023-01-23 01:54:43.572896: step: 744/529, loss: 0.0009384155855514109
2023-01-23 01:54:44.750942: step: 748/529, loss: 0.014869261533021927
2023-01-23 01:54:45.949568: step: 752/529, loss: 0.006194686982780695
2023-01-23 01:54:47.162308: step: 756/529, loss: 0.0077079772017896175
2023-01-23 01:54:48.365266: step: 760/529, loss: 0.03536491468548775
2023-01-23 01:54:49.603683: step: 764/529, loss: 0.006357002072036266
2023-01-23 01:54:50.819171: step: 768/529, loss: 0.03909120708703995
2023-01-23 01:54:52.012778: step: 772/529, loss: 0.0005373954772949219
2023-01-23 01:54:53.185973: step: 776/529, loss: 0.04561972990632057
2023-01-23 01:54:54.388811: step: 780/529, loss: 0.023701095953583717
2023-01-23 01:54:55.588209: step: 784/529, loss: 0.030454445630311966
2023-01-23 01:54:56.807445: step: 788/529, loss: 0.00836334191262722
2023-01-23 01:54:57.974348: step: 792/529, loss: 0.018549060449004173
2023-01-23 01:54:59.203572: step: 796/529, loss: 0.03867530822753906
2023-01-23 01:55:00.390807: step: 800/529, loss: 0.04585866630077362
2023-01-23 01:55:01.570266: step: 804/529, loss: 0.01351385097950697
2023-01-23 01:55:02.777102: step: 808/529, loss: 0.016197824850678444
2023-01-23 01:55:03.959629: step: 812/529, loss: 0.5049812197685242
2023-01-23 01:55:05.123896: step: 816/529, loss: 0.004399907775223255
2023-01-23 01:55:06.305898: step: 820/529, loss: 0.03361711651086807
2023-01-23 01:55:07.459154: step: 824/529, loss: 0.028964996337890625
2023-01-23 01:55:08.647231: step: 828/529, loss: 0.05644054338335991
2023-01-23 01:55:09.833427: step: 832/529, loss: 0.06460876762866974
2023-01-23 01:55:11.037443: step: 836/529, loss: 0.007114887237548828
2023-01-23 01:55:12.293687: step: 840/529, loss: 0.07699642330408096
2023-01-23 01:55:13.444908: step: 844/529, loss: 0.004122877027839422
2023-01-23 01:55:14.652549: step: 848/529, loss: 0.04374675825238228
2023-01-23 01:55:15.841483: step: 852/529, loss: 0.038248348981142044
2023-01-23 01:55:16.988901: step: 856/529, loss: 0.034829046577215195
2023-01-23 01:55:18.186553: step: 860/529, loss: 0.046213533729314804
2023-01-23 01:55:19.399699: step: 864/529, loss: 0.026385022327303886
2023-01-23 01:55:20.595273: step: 868/529, loss: 0.005799293518066406
2023-01-23 01:55:21.813413: step: 872/529, loss: 0.2844853401184082
2023-01-23 01:55:23.007406: step: 876/529, loss: 0.020926428958773613
2023-01-23 01:55:24.194688: step: 880/529, loss: 0.02928609773516655
2023-01-23 01:55:25.380430: step: 884/529, loss: 0.03726644441485405
2023-01-23 01:55:26.552927: step: 888/529, loss: 0.4652038514614105
2023-01-23 01:55:27.748608: step: 892/529, loss: 0.02466583251953125
2023-01-23 01:55:28.964045: step: 896/529, loss: 0.011637592688202858
2023-01-23 01:55:30.122446: step: 900/529, loss: 0.0012027741177007556
2023-01-23 01:55:31.301835: step: 904/529, loss: 0.005543517880141735
2023-01-23 01:55:32.542221: step: 908/529, loss: 0.001992166042327881
2023-01-23 01:55:33.740449: step: 912/529, loss: 0.01972498930990696
2023-01-23 01:55:34.929664: step: 916/529, loss: 0.016737990081310272
2023-01-23 01:55:36.157637: step: 920/529, loss: 0.09065389633178711
2023-01-23 01:55:37.327286: step: 924/529, loss: 0.016427231952548027
2023-01-23 01:55:38.515703: step: 928/529, loss: 0.03529768064618111
2023-01-23 01:55:39.712563: step: 932/529, loss: 0.021167373284697533
2023-01-23 01:55:40.912685: step: 936/529, loss: 0.044316768646240234
2023-01-23 01:55:42.160621: step: 940/529, loss: 0.12078666687011719
2023-01-23 01:55:43.345515: step: 944/529, loss: 0.0019444465870037675
2023-01-23 01:55:44.576449: step: 948/529, loss: 0.0016371726524084806
2023-01-23 01:55:45.768043: step: 952/529, loss: 0.006275392137467861
2023-01-23 01:55:47.028723: step: 956/529, loss: 0.029324818402528763
2023-01-23 01:55:48.207710: step: 960/529, loss: 0.002056622412055731
2023-01-23 01:55:49.466920: step: 964/529, loss: 0.19268283247947693
2023-01-23 01:55:50.694563: step: 968/529, loss: 0.11185389012098312
2023-01-23 01:55:51.864943: step: 972/529, loss: 0.010258197784423828
2023-01-23 01:55:53.067442: step: 976/529, loss: 0.03547201305627823
2023-01-23 01:55:54.244150: step: 980/529, loss: 0.04166984558105469
2023-01-23 01:55:55.414095: step: 984/529, loss: 0.019840337336063385
2023-01-23 01:55:56.632539: step: 988/529, loss: 0.019434357061982155
2023-01-23 01:55:57.830795: step: 992/529, loss: 0.05450878292322159
2023-01-23 01:55:58.988296: step: 996/529, loss: 0.036869145929813385
2023-01-23 01:56:00.174023: step: 1000/529, loss: 0.011790085583925247
2023-01-23 01:56:01.330905: step: 1004/529, loss: 0.029982566833496094
2023-01-23 01:56:02.548443: step: 1008/529, loss: 0.019115637987852097
2023-01-23 01:56:03.743236: step: 1012/529, loss: 0.00112323765642941
2023-01-23 01:56:04.901627: step: 1016/529, loss: 0.0033578872680664062
2023-01-23 01:56:06.076500: step: 1020/529, loss: 0.03182220458984375
2023-01-23 01:56:07.295980: step: 1024/529, loss: 0.04552431404590607
2023-01-23 01:56:08.488583: step: 1028/529, loss: 0.04718761518597603
2023-01-23 01:56:09.669471: step: 1032/529, loss: 0.002457237336784601
2023-01-23 01:56:10.897449: step: 1036/529, loss: 7.613883018493652
2023-01-23 01:56:12.085984: step: 1040/529, loss: 0.019194984808564186
2023-01-23 01:56:13.234305: step: 1044/529, loss: 0.020956039428710938
2023-01-23 01:56:14.456781: step: 1048/529, loss: 0.0018651008140295744
2023-01-23 01:56:15.628071: step: 1052/529, loss: 0.0804869681596756
2023-01-23 01:56:16.840000: step: 1056/529, loss: 0.007631206884980202
2023-01-23 01:56:18.038062: step: 1060/529, loss: 0.003436565399169922
2023-01-23 01:56:19.242477: step: 1064/529, loss: 0.01638183556497097
2023-01-23 01:56:20.493650: step: 1068/529, loss: 0.0275771152228117
2023-01-23 01:56:21.712950: step: 1072/529, loss: 0.03643946722149849
2023-01-23 01:56:22.896093: step: 1076/529, loss: 0.0037660598754882812
2023-01-23 01:56:24.140428: step: 1080/529, loss: 0.04119758680462837
2023-01-23 01:56:25.360516: step: 1084/529, loss: 0.06853781640529633
2023-01-23 01:56:26.547968: step: 1088/529, loss: 0.00012159347534179688
2023-01-23 01:56:27.775986: step: 1092/529, loss: 0.013943481259047985
2023-01-23 01:56:28.980861: step: 1096/529, loss: 0.03274545818567276
2023-01-23 01:56:30.169686: step: 1100/529, loss: 0.08214292675256729
2023-01-23 01:56:31.342030: step: 1104/529, loss: 0.0075247762724757195
2023-01-23 01:56:32.547709: step: 1108/529, loss: 0.03893442451953888
2023-01-23 01:56:33.711595: step: 1112/529, loss: 0.05002059042453766
2023-01-23 01:56:34.908945: step: 1116/529, loss: 0.06410379707813263
2023-01-23 01:56:36.094649: step: 1120/529, loss: 0.008359337225556374
2023-01-23 01:56:37.324518: step: 1124/529, loss: 0.0009662627708166838
2023-01-23 01:56:38.505825: step: 1128/529, loss: 0.022592831403017044
2023-01-23 01:56:39.741192: step: 1132/529, loss: 0.6187344789505005
2023-01-23 01:56:40.938056: step: 1136/529, loss: 0.029236221686005592
2023-01-23 01:56:42.134228: step: 1140/529, loss: 0.01214456558227539
2023-01-23 01:56:43.310789: step: 1144/529, loss: 0.0078095439821481705
2023-01-23 01:56:44.558213: step: 1148/529, loss: 0.052944280207157135
2023-01-23 01:56:45.719079: step: 1152/529, loss: 0.06216888502240181
2023-01-23 01:56:46.890793: step: 1156/529, loss: 8.769035775912926e-05
2023-01-23 01:56:48.087450: step: 1160/529, loss: 0.03388276323676109
2023-01-23 01:56:49.295805: step: 1164/529, loss: 0.058298349380493164
2023-01-23 01:56:50.465719: step: 1168/529, loss: 0.2575405240058899
2023-01-23 01:56:51.650519: step: 1172/529, loss: 0.021151067689061165
2023-01-23 01:56:52.850605: step: 1176/529, loss: 0.01527795847505331
2023-01-23 01:56:54.037292: step: 1180/529, loss: 0.01699075847864151
2023-01-23 01:56:55.246888: step: 1184/529, loss: 0.09953327476978302
2023-01-23 01:56:56.484399: step: 1188/529, loss: 0.33709201216697693
2023-01-23 01:56:57.682711: step: 1192/529, loss: 0.013056564144790173
2023-01-23 01:56:58.872341: step: 1196/529, loss: 0.020695878192782402
2023-01-23 01:57:00.059922: step: 1200/529, loss: 0.08869123458862305
2023-01-23 01:57:01.317878: step: 1204/529, loss: 0.012712287716567516
2023-01-23 01:57:02.540913: step: 1208/529, loss: 0.06995334476232529
2023-01-23 01:57:03.713925: step: 1212/529, loss: 0.005582476034760475
2023-01-23 01:57:04.917977: step: 1216/529, loss: 0.016435623168945312
2023-01-23 01:57:06.125873: step: 1220/529, loss: 0.18591423332691193
2023-01-23 01:57:07.345333: step: 1224/529, loss: 0.0067001343704760075
2023-01-23 01:57:08.567399: step: 1228/529, loss: 0.020901108160614967
2023-01-23 01:57:09.772064: step: 1232/529, loss: 0.029928207397460938
2023-01-23 01:57:10.960781: step: 1236/529, loss: 0.01280994527041912
2023-01-23 01:57:12.200270: step: 1240/529, loss: 0.05920276790857315
2023-01-23 01:57:13.416703: step: 1244/529, loss: 0.012746095657348633
2023-01-23 01:57:14.598525: step: 1248/529, loss: 0.002952480223029852
2023-01-23 01:57:15.779074: step: 1252/529, loss: 0.09848232567310333
2023-01-23 01:57:16.984551: step: 1256/529, loss: 0.09303627908229828
2023-01-23 01:57:18.162435: step: 1260/529, loss: 0.028832150623202324
2023-01-23 01:57:19.385322: step: 1264/529, loss: 0.005545425694435835
2023-01-23 01:57:20.546338: step: 1268/529, loss: 0.16472569108009338
2023-01-23 01:57:21.754999: step: 1272/529, loss: 0.027658844366669655
2023-01-23 01:57:22.969309: step: 1276/529, loss: 0.12092819809913635
2023-01-23 01:57:24.155065: step: 1280/529, loss: 0.00525136012583971
2023-01-23 01:57:25.390657: step: 1284/529, loss: 0.006985223386436701
2023-01-23 01:57:26.567670: step: 1288/529, loss: 0.0033423902932554483
2023-01-23 01:57:27.728460: step: 1292/529, loss: 0.038785506039857864
2023-01-23 01:57:28.890976: step: 1296/529, loss: 0.009946918115019798
2023-01-23 01:57:30.056325: step: 1300/529, loss: 0.0059906006790697575
2023-01-23 01:57:31.307872: step: 1304/529, loss: 0.03427105024456978
2023-01-23 01:57:32.501365: step: 1308/529, loss: 0.05811386555433273
2023-01-23 01:57:33.697461: step: 1312/529, loss: 0.01921234093606472
2023-01-23 01:57:34.909920: step: 1316/529, loss: 0.0275576114654541
2023-01-23 01:57:36.072987: step: 1320/529, loss: 0.006468010134994984
2023-01-23 01:57:37.274886: step: 1324/529, loss: 0.03248901665210724
2023-01-23 01:57:38.440250: step: 1328/529, loss: 0.020908953621983528
2023-01-23 01:57:39.650975: step: 1332/529, loss: 0.019912149757146835
2023-01-23 01:57:40.857620: step: 1336/529, loss: 0.008447027765214443
2023-01-23 01:57:42.096497: step: 1340/529, loss: 0.3015109896659851
2023-01-23 01:57:43.255441: step: 1344/529, loss: 0.03302764892578125
2023-01-23 01:57:44.502445: step: 1348/529, loss: 0.033263400197029114
2023-01-23 01:57:45.711563: step: 1352/529, loss: 0.007282543461769819
2023-01-23 01:57:46.966500: step: 1356/529, loss: 0.06480860710144043
2023-01-23 01:57:48.170301: step: 1360/529, loss: 0.07706928998231888
2023-01-23 01:57:49.375498: step: 1364/529, loss: 0.00021967888460494578
2023-01-23 01:57:50.592133: step: 1368/529, loss: 0.007479286286979914
2023-01-23 01:57:51.819315: step: 1372/529, loss: 0.0020242691971361637
2023-01-23 01:57:53.003523: step: 1376/529, loss: 0.0025319100823253393
2023-01-23 01:57:54.228928: step: 1380/529, loss: 0.028531935065984726
2023-01-23 01:57:55.402652: step: 1384/529, loss: 0.05704698711633682
2023-01-23 01:57:56.603555: step: 1388/529, loss: 0.0183913242071867
2023-01-23 01:57:57.797475: step: 1392/529, loss: 0.007855034433305264
2023-01-23 01:57:58.986593: step: 1396/529, loss: 0.0016820431919768453
2023-01-23 01:58:00.209909: step: 1400/529, loss: 0.06636278331279755
2023-01-23 01:58:01.423689: step: 1404/529, loss: 0.01532160583883524
2023-01-23 01:58:02.694517: step: 1408/529, loss: 0.024730205535888672
2023-01-23 01:58:03.919859: step: 1412/529, loss: 0.0005437612417154014
2023-01-23 01:58:05.108535: step: 1416/529, loss: 0.04557623714208603
2023-01-23 01:58:06.314258: step: 1420/529, loss: 0.026226473972201347
2023-01-23 01:58:07.528493: step: 1424/529, loss: 0.0005801916122436523
2023-01-23 01:58:08.736523: step: 1428/529, loss: 0.03095417097210884
2023-01-23 01:58:09.923980: step: 1432/529, loss: 0.004605341237038374
2023-01-23 01:58:11.112056: step: 1436/529, loss: 0.05617962405085564
2023-01-23 01:58:12.308432: step: 1440/529, loss: 0.010184098035097122
2023-01-23 01:58:13.572705: step: 1444/529, loss: 0.004900550935417414
2023-01-23 01:58:14.776313: step: 1448/529, loss: 0.20014648139476776
2023-01-23 01:58:15.954859: step: 1452/529, loss: 0.011930370703339577
2023-01-23 01:58:17.131414: step: 1456/529, loss: 0.0005268097156658769
2023-01-23 01:58:18.356373: step: 1460/529, loss: 0.02560530975461006
2023-01-23 01:58:19.575780: step: 1464/529, loss: 0.06348982453346252
2023-01-23 01:58:20.756006: step: 1468/529, loss: 0.08747158199548721
2023-01-23 01:58:21.950159: step: 1472/529, loss: 0.022947883233428
2023-01-23 01:58:23.133915: step: 1476/529, loss: 0.04778118431568146
2023-01-23 01:58:24.360903: step: 1480/529, loss: 0.0037987353280186653
2023-01-23 01:58:25.572248: step: 1484/529, loss: 0.025248384103178978
2023-01-23 01:58:26.788123: step: 1488/529, loss: 0.011888314038515091
2023-01-23 01:58:27.978145: step: 1492/529, loss: 0.06573381274938583
2023-01-23 01:58:29.188912: step: 1496/529, loss: 0.012727736495435238
2023-01-23 01:58:30.382799: step: 1500/529, loss: 0.066846564412117
2023-01-23 01:58:31.575232: step: 1504/529, loss: 0.016164684668183327
2023-01-23 01:58:32.747558: step: 1508/529, loss: 0.01792125776410103
2023-01-23 01:58:33.951918: step: 1512/529, loss: 0.01788330264389515
2023-01-23 01:58:35.163613: step: 1516/529, loss: 0.07105641067028046
2023-01-23 01:58:36.382866: step: 1520/529, loss: 0.01463176030665636
2023-01-23 01:58:37.592986: step: 1524/529, loss: 0.07115145027637482
2023-01-23 01:58:38.795218: step: 1528/529, loss: 0.1553487777709961
2023-01-23 01:58:39.993450: step: 1532/529, loss: 0.033963393419981
2023-01-23 01:58:41.170578: step: 1536/529, loss: 0.013622378930449486
2023-01-23 01:58:42.361419: step: 1540/529, loss: 0.03125820308923721
2023-01-23 01:58:43.534826: step: 1544/529, loss: 0.004850661847740412
2023-01-23 01:58:44.718047: step: 1548/529, loss: 0.0060867308638989925
2023-01-23 01:58:45.886491: step: 1552/529, loss: 0.007416534703224897
2023-01-23 01:58:47.061294: step: 1556/529, loss: 0.0038619041442871094
2023-01-23 01:58:48.267925: step: 1560/529, loss: 0.0263079646974802
2023-01-23 01:58:49.497059: step: 1564/529, loss: 0.036171529442071915
2023-01-23 01:58:50.678201: step: 1568/529, loss: 0.046029187738895416
2023-01-23 01:58:51.935974: step: 1572/529, loss: 0.015340805053710938
2023-01-23 01:58:53.174019: step: 1576/529, loss: 0.06995902210474014
2023-01-23 01:58:54.400781: step: 1580/529, loss: 0.005814552307128906
2023-01-23 01:58:55.624656: step: 1584/529, loss: 0.055701542645692825
2023-01-23 01:58:56.776786: step: 1588/529, loss: 0.016504669561982155
2023-01-23 01:58:58.000607: step: 1592/529, loss: 0.06160459667444229
2023-01-23 01:58:59.210314: step: 1596/529, loss: 0.027900028973817825
2023-01-23 01:59:00.469174: step: 1600/529, loss: 0.006214332766830921
2023-01-23 01:59:01.646114: step: 1604/529, loss: 0.003419304033741355
2023-01-23 01:59:02.847281: step: 1608/529, loss: 0.0074745179153978825
2023-01-23 01:59:04.021961: step: 1612/529, loss: 0.017643345519900322
2023-01-23 01:59:05.221905: step: 1616/529, loss: 0.0021614551078528166
2023-01-23 01:59:06.394589: step: 1620/529, loss: 0.07348699867725372
2023-01-23 01:59:07.585908: step: 1624/529, loss: 0.130061075091362
2023-01-23 01:59:08.889586: step: 1628/529, loss: 0.05086164548993111
2023-01-23 01:59:10.112673: step: 1632/529, loss: 0.010193824768066406
2023-01-23 01:59:11.333123: step: 1636/529, loss: 0.005540275946259499
2023-01-23 01:59:12.531455: step: 1640/529, loss: 0.022570276632905006
2023-01-23 01:59:13.729883: step: 1644/529, loss: 0.045505695044994354
2023-01-23 01:59:14.898071: step: 1648/529, loss: 0.05347108840942383
2023-01-23 01:59:16.119910: step: 1652/529, loss: 0.06545610725879669
2023-01-23 01:59:17.310124: step: 1656/529, loss: 0.031281281262636185
2023-01-23 01:59:18.498134: step: 1660/529, loss: 0.04181130230426788
2023-01-23 01:59:19.663645: step: 1664/529, loss: 0.027374744415283203
2023-01-23 01:59:20.860924: step: 1668/529, loss: 0.008363437838852406
2023-01-23 01:59:22.038915: step: 1672/529, loss: 0.03581733629107475
2023-01-23 01:59:23.266438: step: 1676/529, loss: 0.05150566250085831
2023-01-23 01:59:24.474801: step: 1680/529, loss: 0.0016584396362304688
2023-01-23 01:59:25.672010: step: 1684/529, loss: 0.00958938617259264
2023-01-23 01:59:26.889387: step: 1688/529, loss: 0.03881445154547691
2023-01-23 01:59:28.093441: step: 1692/529, loss: 0.05616569519042969
2023-01-23 01:59:29.300591: step: 1696/529, loss: 0.003646993776783347
2023-01-23 01:59:30.479608: step: 1700/529, loss: 0.07463932037353516
2023-01-23 01:59:31.720523: step: 1704/529, loss: 0.007560920435935259
2023-01-23 01:59:32.946004: step: 1708/529, loss: 0.09490852802991867
2023-01-23 01:59:34.165607: step: 1712/529, loss: 0.02349872514605522
2023-01-23 01:59:35.378919: step: 1716/529, loss: 0.0493219755589962
2023-01-23 01:59:36.542722: step: 1720/529, loss: 0.048899270594120026
2023-01-23 01:59:37.748509: step: 1724/529, loss: 0.013747883029282093
2023-01-23 01:59:38.954867: step: 1728/529, loss: 0.027751732617616653
2023-01-23 01:59:40.141566: step: 1732/529, loss: 0.05959749221801758
2023-01-23 01:59:41.351889: step: 1736/529, loss: 0.021447371691465378
2023-01-23 01:59:42.553017: step: 1740/529, loss: 0.0032948970329016447
2023-01-23 01:59:43.767402: step: 1744/529, loss: 0.0014051944017410278
2023-01-23 01:59:44.930419: step: 1748/529, loss: 0.03415260463953018
2023-01-23 01:59:46.137949: step: 1752/529, loss: 0.07967357337474823
2023-01-23 01:59:47.314499: step: 1756/529, loss: 0.042795706540346146
2023-01-23 01:59:48.482749: step: 1760/529, loss: 0.07079362869262695
2023-01-23 01:59:49.669490: step: 1764/529, loss: 0.011539077386260033
2023-01-23 01:59:50.863451: step: 1768/529, loss: 0.014110947027802467
2023-01-23 01:59:52.039903: step: 1772/529, loss: 0.04072609171271324
2023-01-23 01:59:53.271250: step: 1776/529, loss: 0.03273210674524307
2023-01-23 01:59:54.512076: step: 1780/529, loss: 0.08004264533519745
2023-01-23 01:59:55.700274: step: 1784/529, loss: 0.04920263588428497
2023-01-23 01:59:56.925193: step: 1788/529, loss: 0.10527591407299042
2023-01-23 01:59:58.101054: step: 1792/529, loss: 0.0065056802704930305
2023-01-23 01:59:59.316456: step: 1796/529, loss: 0.056125592440366745
2023-01-23 02:00:00.522286: step: 1800/529, loss: 0.005870628636330366
2023-01-23 02:00:01.687845: step: 1804/529, loss: 0.01254568062722683
2023-01-23 02:00:02.928659: step: 1808/529, loss: 0.0728035494685173
2023-01-23 02:00:04.125501: step: 1812/529, loss: 0.08295102417469025
2023-01-23 02:00:05.304749: step: 1816/529, loss: 0.07871723175048828
2023-01-23 02:00:06.507510: step: 1820/529, loss: 0.010755443945527077
2023-01-23 02:00:07.711861: step: 1824/529, loss: 0.015051651746034622
2023-01-23 02:00:08.884915: step: 1828/529, loss: 0.008225775323808193
2023-01-23 02:00:10.071099: step: 1832/529, loss: 0.01578162983059883
2023-01-23 02:00:11.225442: step: 1836/529, loss: 0.0046412465162575245
2023-01-23 02:00:12.407959: step: 1840/529, loss: 0.1570996195077896
2023-01-23 02:00:13.622997: step: 1844/529, loss: 0.06905098259449005
2023-01-23 02:00:14.795596: step: 1848/529, loss: 0.02801513671875
2023-01-23 02:00:16.030925: step: 1852/529, loss: 0.06198396533727646
2023-01-23 02:00:17.195709: step: 1856/529, loss: 0.036179397255182266
2023-01-23 02:00:18.406852: step: 1860/529, loss: 0.012075996957719326
2023-01-23 02:00:19.614053: step: 1864/529, loss: 0.18381473422050476
2023-01-23 02:00:20.788894: step: 1868/529, loss: 0.04402294382452965
2023-01-23 02:00:22.020717: step: 1872/529, loss: 0.036356642842292786
2023-01-23 02:00:23.195386: step: 1876/529, loss: 0.018994569778442383
2023-01-23 02:00:24.461760: step: 1880/529, loss: 0.04035930708050728
2023-01-23 02:00:25.679774: step: 1884/529, loss: 0.024074364453554153
2023-01-23 02:00:26.903001: step: 1888/529, loss: 0.018526840955018997
2023-01-23 02:00:28.125010: step: 1892/529, loss: 0.010426235385239124
2023-01-23 02:00:29.335273: step: 1896/529, loss: 0.051320839673280716
2023-01-23 02:00:30.543144: step: 1900/529, loss: 0.12202034145593643
2023-01-23 02:00:31.776542: step: 1904/529, loss: 0.05969180911779404
2023-01-23 02:00:33.014215: step: 1908/529, loss: 0.07862873375415802
2023-01-23 02:00:34.193967: step: 1912/529, loss: 0.02726149559020996
2023-01-23 02:00:35.396475: step: 1916/529, loss: 0.03670492395758629
2023-01-23 02:00:36.576752: step: 1920/529, loss: 0.013945579528808594
2023-01-23 02:00:37.767284: step: 1924/529, loss: 0.02425394207239151
2023-01-23 02:00:39.020118: step: 1928/529, loss: 0.06108541786670685
2023-01-23 02:00:40.223802: step: 1932/529, loss: 0.1501600295305252
2023-01-23 02:00:41.388966: step: 1936/529, loss: 0.03265504911541939
2023-01-23 02:00:42.557390: step: 1940/529, loss: 0.16952934861183167
2023-01-23 02:00:43.787430: step: 1944/529, loss: 0.01171646174043417
2023-01-23 02:00:44.962453: step: 1948/529, loss: 0.12484703212976456
2023-01-23 02:00:46.151143: step: 1952/529, loss: 0.34257006645202637
2023-01-23 02:00:47.416080: step: 1956/529, loss: 0.056500911712646484
2023-01-23 02:00:48.637400: step: 1960/529, loss: 0.025409795343875885
2023-01-23 02:00:49.857192: step: 1964/529, loss: 0.036218930035829544
2023-01-23 02:00:51.071607: step: 1968/529, loss: 0.05441112443804741
2023-01-23 02:00:52.246667: step: 1972/529, loss: 0.025200797244906425
2023-01-23 02:00:53.414786: step: 1976/529, loss: 0.015030860900878906
2023-01-23 02:00:54.633852: step: 1980/529, loss: 0.020447731018066406
2023-01-23 02:00:55.849331: step: 1984/529, loss: 0.04184160754084587
2023-01-23 02:00:57.012025: step: 1988/529, loss: 0.028174782171845436
2023-01-23 02:00:58.258641: step: 1992/529, loss: 0.2870357632637024
2023-01-23 02:00:59.469111: step: 1996/529, loss: 0.1252630203962326
2023-01-23 02:01:00.652102: step: 2000/529, loss: 0.028281403705477715
2023-01-23 02:01:01.870353: step: 2004/529, loss: 0.02722320705652237
2023-01-23 02:01:03.076350: step: 2008/529, loss: 0.03438367694616318
2023-01-23 02:01:04.276621: step: 2012/529, loss: 0.014744091778993607
2023-01-23 02:01:05.482778: step: 2016/529, loss: 0.07052536308765411
2023-01-23 02:01:06.688980: step: 2020/529, loss: 0.11352807283401489
2023-01-23 02:01:07.893166: step: 2024/529, loss: 0.059533145278692245
2023-01-23 02:01:09.059270: step: 2028/529, loss: 0.007819080725312233
2023-01-23 02:01:10.261807: step: 2032/529, loss: 0.005525302607566118
2023-01-23 02:01:11.406255: step: 2036/529, loss: 0.023994911462068558
2023-01-23 02:01:12.593849: step: 2040/529, loss: 0.011910355649888515
2023-01-23 02:01:13.830542: step: 2044/529, loss: 0.00218791957013309
2023-01-23 02:01:15.004725: step: 2048/529, loss: 0.01730489730834961
2023-01-23 02:01:16.176527: step: 2052/529, loss: 0.03709264099597931
2023-01-23 02:01:17.376277: step: 2056/529, loss: 0.02214631997048855
2023-01-23 02:01:18.549778: step: 2060/529, loss: 0.027809666469693184
2023-01-23 02:01:19.694504: step: 2064/529, loss: 0.01901989057660103
2023-01-23 02:01:20.906775: step: 2068/529, loss: 0.01893148384988308
2023-01-23 02:01:22.156593: step: 2072/529, loss: 0.008374262601137161
2023-01-23 02:01:23.416372: step: 2076/529, loss: 0.02663717232644558
2023-01-23 02:01:24.632301: step: 2080/529, loss: 0.044006966054439545
2023-01-23 02:01:25.786995: step: 2084/529, loss: 0.09519825130701065
2023-01-23 02:01:26.990229: step: 2088/529, loss: 0.037520598620176315
2023-01-23 02:01:28.210915: step: 2092/529, loss: 0.0752742812037468
2023-01-23 02:01:29.396643: step: 2096/529, loss: 0.04630632326006889
2023-01-23 02:01:30.618742: step: 2100/529, loss: 0.026484372094273567
2023-01-23 02:01:31.818775: step: 2104/529, loss: 0.002570724580436945
2023-01-23 02:01:33.037112: step: 2108/529, loss: 0.01820087432861328
2023-01-23 02:01:34.201369: step: 2112/529, loss: 0.05377311632037163
2023-01-23 02:01:35.414023: step: 2116/529, loss: 0.06346340477466583
==================================================
Loss: 0.063
--------------------
Dev: {'event': {'p': 0.5783730158730159, 'r': 0.7762982689747004, 'f1': 0.6628766344513929}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6390361445783133, 'r': 0.7944877171959257, 'f1': 0.7083333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5595238095238095, 'r': 0.8703703703703703, 'f1': 0.6811594202898551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.4782608695652174, 'r': 0.5238095238095238, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.45652173913043476, 'r': 0.5833333333333334, 'f1': 0.5121951219512195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:02:19.124449: step: 4/529, loss: 0.006434726994484663
2023-01-23 02:02:20.348560: step: 8/529, loss: 0.0008400916703976691
2023-01-23 02:02:21.517360: step: 12/529, loss: 0.11036419868469238
2023-01-23 02:02:22.741593: step: 16/529, loss: 0.11412505805492401
2023-01-23 02:02:23.943755: step: 20/529, loss: 0.002006101654842496
2023-01-23 02:02:25.158537: step: 24/529, loss: 0.01931934431195259
2023-01-23 02:02:26.357617: step: 28/529, loss: 0.0006698131328448653
2023-01-23 02:02:27.564202: step: 32/529, loss: 0.00022406579228118062
2023-01-23 02:02:28.746226: step: 36/529, loss: 0.05135917663574219
2023-01-23 02:02:29.922374: step: 40/529, loss: 0.013453959487378597
2023-01-23 02:02:31.125767: step: 44/529, loss: 0.1395878791809082
2023-01-23 02:02:32.400012: step: 48/529, loss: 0.006522846408188343
2023-01-23 02:02:33.585278: step: 52/529, loss: 0.039248086512088776
2023-01-23 02:02:34.780333: step: 56/529, loss: 0.001166057656519115
2023-01-23 02:02:35.964761: step: 60/529, loss: 0.015667341649532318
2023-01-23 02:02:37.125923: step: 64/529, loss: 0.002609044313430786
2023-01-23 02:02:38.333178: step: 68/529, loss: 0.017549704760313034
2023-01-23 02:02:39.666830: step: 72/529, loss: 0.01764049381017685
2023-01-23 02:02:40.857299: step: 76/529, loss: 0.015106964856386185
2023-01-23 02:02:42.067112: step: 80/529, loss: 0.05608396977186203
2023-01-23 02:02:43.267109: step: 84/529, loss: 0.004139518830925226
2023-01-23 02:02:44.416110: step: 88/529, loss: 0.004285716917365789
2023-01-23 02:02:45.604427: step: 92/529, loss: 0.03477032855153084
2023-01-23 02:02:46.821777: step: 96/529, loss: 0.07379131019115448
2023-01-23 02:02:48.029624: step: 100/529, loss: 0.03617975860834122
2023-01-23 02:02:49.283177: step: 104/529, loss: 0.0012842179276049137
2023-01-23 02:02:50.490396: step: 108/529, loss: 0.10076847672462463
2023-01-23 02:02:51.725396: step: 112/529, loss: 0.027474403381347656
2023-01-23 02:02:52.960139: step: 116/529, loss: 0.018334198743104935
2023-01-23 02:02:54.140153: step: 120/529, loss: 0.04866437986493111
2023-01-23 02:02:55.379054: step: 124/529, loss: 0.04026756435632706
2023-01-23 02:02:56.564612: step: 128/529, loss: 0.08572883903980255
2023-01-23 02:02:57.738168: step: 132/529, loss: 0.006194686982780695
2023-01-23 02:02:58.949247: step: 136/529, loss: 0.053522590547800064
2023-01-23 02:03:00.120623: step: 140/529, loss: 0.03320331871509552
2023-01-23 02:03:01.327995: step: 144/529, loss: 0.009608983993530273
2023-01-23 02:03:02.523966: step: 148/529, loss: 0.0009262085077352822
2023-01-23 02:03:03.703330: step: 152/529, loss: 0.0314909927546978
2023-01-23 02:03:04.901318: step: 156/529, loss: 0.0453365333378315
2023-01-23 02:03:06.074521: step: 160/529, loss: 0.06576023250818253
2023-01-23 02:03:07.260775: step: 164/529, loss: 0.004456997383385897
2023-01-23 02:03:08.470730: step: 168/529, loss: 0.0060249329544603825
2023-01-23 02:03:09.686225: step: 172/529, loss: 0.09245280921459198
2023-01-23 02:03:10.917245: step: 176/529, loss: 0.1105566993355751
2023-01-23 02:03:12.116856: step: 180/529, loss: 0.019758939743041992
2023-01-23 02:03:13.312390: step: 184/529, loss: 0.015011405572295189
2023-01-23 02:03:14.497514: step: 188/529, loss: 0.024150991812348366
2023-01-23 02:03:15.733152: step: 192/529, loss: 0.06746292114257812
2023-01-23 02:03:16.900709: step: 196/529, loss: 0.016742898151278496
2023-01-23 02:03:18.122113: step: 200/529, loss: 0.04550713673233986
2023-01-23 02:03:19.333722: step: 204/529, loss: 0.03450794145464897
2023-01-23 02:03:20.529258: step: 208/529, loss: 0.09060563892126083
2023-01-23 02:03:21.728165: step: 212/529, loss: 0.5808812379837036
2023-01-23 02:03:22.897506: step: 216/529, loss: 0.020499326288700104
2023-01-23 02:03:24.114233: step: 220/529, loss: 0.0982338935136795
2023-01-23 02:03:25.303614: step: 224/529, loss: 0.0031575202010571957
2023-01-23 02:03:26.490688: step: 228/529, loss: 0.0011027336586266756
2023-01-23 02:03:27.654352: step: 232/529, loss: 0.0063127996399998665
2023-01-23 02:03:28.845042: step: 236/529, loss: 0.02760915644466877
2023-01-23 02:03:30.025231: step: 240/529, loss: 2.726727247238159
2023-01-23 02:03:31.221570: step: 244/529, loss: 0.021411515772342682
2023-01-23 02:03:32.433027: step: 248/529, loss: 0.0002449035819154233
2023-01-23 02:03:33.678824: step: 252/529, loss: 0.055960461497306824
2023-01-23 02:03:34.889612: step: 256/529, loss: 0.01124725304543972
2023-01-23 02:03:36.063388: step: 260/529, loss: 0.0079659940674901
2023-01-23 02:03:37.288765: step: 264/529, loss: 0.03912172466516495
2023-01-23 02:03:38.475932: step: 268/529, loss: 0.0008550644270144403
2023-01-23 02:03:39.653881: step: 272/529, loss: 0.025252103805541992
2023-01-23 02:03:40.872030: step: 276/529, loss: 0.01659221760928631
2023-01-23 02:03:42.033456: step: 280/529, loss: 0.015396738424897194
2023-01-23 02:03:43.209424: step: 284/529, loss: 0.01416015625
2023-01-23 02:03:44.446815: step: 288/529, loss: 0.0008448601001873612
2023-01-23 02:03:45.623932: step: 292/529, loss: 0.02195291593670845
2023-01-23 02:03:46.814717: step: 296/529, loss: 0.011858178302645683
2023-01-23 02:03:48.023404: step: 300/529, loss: 0.020637130364775658
2023-01-23 02:03:49.262303: step: 304/529, loss: 0.02291898801922798
2023-01-23 02:03:50.475146: step: 308/529, loss: 0.012097597122192383
2023-01-23 02:03:51.630846: step: 312/529, loss: 0.0002045154687948525
2023-01-23 02:03:52.888986: step: 316/529, loss: 0.033960580825805664
2023-01-23 02:03:54.107795: step: 320/529, loss: 0.0037948605604469776
2023-01-23 02:03:55.292136: step: 324/529, loss: 0.000901722873095423
2023-01-23 02:03:56.505108: step: 328/529, loss: 0.026515580713748932
2023-01-23 02:03:57.691071: step: 332/529, loss: 0.0035042765084654093
2023-01-23 02:03:58.935434: step: 336/529, loss: 0.0032387732062488794
2023-01-23 02:04:00.138827: step: 340/529, loss: 0.09098567813634872
2023-01-23 02:04:01.341592: step: 344/529, loss: 0.03037567250430584
2023-01-23 02:04:02.577349: step: 348/529, loss: 0.009226626716554165
2023-01-23 02:04:03.810835: step: 352/529, loss: 0.01393747329711914
2023-01-23 02:04:05.009556: step: 356/529, loss: 0.00024585722712799907
2023-01-23 02:04:06.212857: step: 360/529, loss: 0.08063382655382156
2023-01-23 02:04:07.397169: step: 364/529, loss: 0.018328571692109108
2023-01-23 02:04:08.604360: step: 368/529, loss: 0.07306937873363495
2023-01-23 02:04:09.825563: step: 372/529, loss: 0.04751329496502876
2023-01-23 02:04:10.993164: step: 376/529, loss: 0.0012422561412677169
2023-01-23 02:04:12.164691: step: 380/529, loss: 0.07454396039247513
2023-01-23 02:04:13.368200: step: 384/529, loss: 0.0024165152572095394
2023-01-23 02:04:14.569431: step: 388/529, loss: 0.019887257367372513
2023-01-23 02:04:15.804288: step: 392/529, loss: 0.07866191864013672
2023-01-23 02:04:16.991943: step: 396/529, loss: 0.03600006178021431
2023-01-23 02:04:18.198525: step: 400/529, loss: 0.00916605070233345
2023-01-23 02:04:19.403464: step: 404/529, loss: 0.038260556757450104
2023-01-23 02:04:20.615868: step: 408/529, loss: 0.05882992595434189
2023-01-23 02:04:21.782203: step: 412/529, loss: 0.48201170563697815
2023-01-23 02:04:22.965439: step: 416/529, loss: 0.008504676632583141
2023-01-23 02:04:24.139329: step: 420/529, loss: 0.01841001585125923
2023-01-23 02:04:25.341089: step: 424/529, loss: 0.20601196587085724
2023-01-23 02:04:26.561038: step: 428/529, loss: 0.0026581764686852694
2023-01-23 02:04:27.752148: step: 432/529, loss: 0.018877126276493073
2023-01-23 02:04:28.919446: step: 436/529, loss: 0.06688833236694336
2023-01-23 02:04:30.108759: step: 440/529, loss: 0.04808664321899414
2023-01-23 02:04:31.341606: step: 444/529, loss: 0.022965431213378906
2023-01-23 02:04:32.529172: step: 448/529, loss: 0.005961370654404163
2023-01-23 02:04:33.699033: step: 452/529, loss: 0.012044096365571022
2023-01-23 02:04:34.897637: step: 456/529, loss: 0.025146102532744408
2023-01-23 02:04:36.080804: step: 460/529, loss: 0.03997688367962837
2023-01-23 02:04:37.252055: step: 464/529, loss: 0.0025017261505126953
2023-01-23 02:04:38.445197: step: 468/529, loss: 0.004339027684181929
2023-01-23 02:04:39.660174: step: 472/529, loss: 0.005260562989860773
2023-01-23 02:04:40.827335: step: 476/529, loss: 0.022475672885775566
2023-01-23 02:04:42.003770: step: 480/529, loss: 0.008837452158331871
2023-01-23 02:04:43.218673: step: 484/529, loss: 0.015871619805693626
2023-01-23 02:04:44.472549: step: 488/529, loss: 0.08900375664234161
2023-01-23 02:04:45.660261: step: 492/529, loss: 0.015891743823885918
2023-01-23 02:04:46.879465: step: 496/529, loss: 0.016161728650331497
2023-01-23 02:04:48.083893: step: 500/529, loss: 0.12802700698375702
2023-01-23 02:04:49.301944: step: 504/529, loss: 0.0031542659271508455
2023-01-23 02:04:50.497345: step: 508/529, loss: 0.0010539054637774825
2023-01-23 02:04:51.696383: step: 512/529, loss: 0.05295724794268608
2023-01-23 02:04:52.898598: step: 516/529, loss: 0.09179496765136719
2023-01-23 02:04:54.085313: step: 520/529, loss: 0.08914504200220108
2023-01-23 02:04:55.313184: step: 524/529, loss: 0.00392074603587389
2023-01-23 02:04:56.559211: step: 528/529, loss: 0.0016963481903076172
2023-01-23 02:04:57.795161: step: 532/529, loss: 0.003937530796974897
2023-01-23 02:04:59.029196: step: 536/529, loss: 0.03847523033618927
2023-01-23 02:05:00.269310: step: 540/529, loss: 0.01657574251294136
2023-01-23 02:05:01.438589: step: 544/529, loss: 0.0651828795671463
2023-01-23 02:05:02.666996: step: 548/529, loss: 0.007713747210800648
2023-01-23 02:05:03.839645: step: 552/529, loss: 0.025628376752138138
2023-01-23 02:05:04.987992: step: 556/529, loss: 0.0032600881531834602
2023-01-23 02:05:06.155916: step: 560/529, loss: 0.06552676856517792
2023-01-23 02:05:07.390464: step: 564/529, loss: 0.5084815621376038
2023-01-23 02:05:08.597576: step: 568/529, loss: 0.005863571539521217
2023-01-23 02:05:09.804392: step: 572/529, loss: 0.06808986514806747
2023-01-23 02:05:10.991820: step: 576/529, loss: 0.18612103164196014
2023-01-23 02:05:12.162202: step: 580/529, loss: 0.033710576593875885
2023-01-23 02:05:13.397634: step: 584/529, loss: 0.026553058996796608
2023-01-23 02:05:14.609267: step: 588/529, loss: 0.06056251376867294
2023-01-23 02:05:15.812513: step: 592/529, loss: 0.002029514405876398
2023-01-23 02:05:16.998261: step: 596/529, loss: 0.01723318174481392
2023-01-23 02:05:18.187863: step: 600/529, loss: 0.0005194663535803556
2023-01-23 02:05:19.367785: step: 604/529, loss: 0.02321462519466877
2023-01-23 02:05:20.563009: step: 608/529, loss: 0.0063208104111254215
2023-01-23 02:05:21.779405: step: 612/529, loss: 0.029242612421512604
2023-01-23 02:05:23.002339: step: 616/529, loss: 0.02488880231976509
2023-01-23 02:05:24.248234: step: 620/529, loss: 0.02666320651769638
2023-01-23 02:05:25.434553: step: 624/529, loss: 0.017958641052246094
2023-01-23 02:05:26.633061: step: 628/529, loss: 0.03376655653119087
2023-01-23 02:05:27.826689: step: 632/529, loss: 0.08083219826221466
2023-01-23 02:05:28.996940: step: 636/529, loss: 0.00589599646627903
2023-01-23 02:05:30.222937: step: 640/529, loss: 0.003988933749496937
2023-01-23 02:05:31.365811: step: 644/529, loss: 0.043036654591560364
2023-01-23 02:05:32.510638: step: 648/529, loss: 0.0315793976187706
2023-01-23 02:05:33.699444: step: 652/529, loss: 0.03280750662088394
2023-01-23 02:05:34.872067: step: 656/529, loss: 0.0444762259721756
2023-01-23 02:05:36.079667: step: 660/529, loss: 0.2329617589712143
2023-01-23 02:05:37.248264: step: 664/529, loss: 0.009524727240204811
2023-01-23 02:05:38.459334: step: 668/529, loss: 0.022509289905428886
2023-01-23 02:05:39.677659: step: 672/529, loss: 0.037732888013124466
2023-01-23 02:05:40.904175: step: 676/529, loss: 0.03295574337244034
2023-01-23 02:05:42.094983: step: 680/529, loss: 0.02532811276614666
2023-01-23 02:05:43.280678: step: 684/529, loss: 0.07379178702831268
2023-01-23 02:05:44.488501: step: 688/529, loss: 0.008675575256347656
2023-01-23 02:05:45.674008: step: 692/529, loss: 0.02624817006289959
2023-01-23 02:05:46.848953: step: 696/529, loss: 0.004151344299316406
2023-01-23 02:05:48.042188: step: 700/529, loss: 0.003677845001220703
2023-01-23 02:05:49.234082: step: 704/529, loss: 0.1063636764883995
2023-01-23 02:05:50.430419: step: 708/529, loss: 0.03356208652257919
2023-01-23 02:05:51.655112: step: 712/529, loss: 0.0001941680966410786
2023-01-23 02:05:52.843952: step: 716/529, loss: 0.21397551894187927
2023-01-23 02:05:54.014855: step: 720/529, loss: 0.0016517640324309468
2023-01-23 02:05:55.237731: step: 724/529, loss: 0.05578498914837837
2023-01-23 02:05:56.456109: step: 728/529, loss: 0.07641620934009552
2023-01-23 02:05:57.656737: step: 732/529, loss: 0.01671614684164524
2023-01-23 02:05:58.830664: step: 736/529, loss: 0.003430795855820179
2023-01-23 02:06:00.010167: step: 740/529, loss: 0.9274988174438477
2023-01-23 02:06:01.213480: step: 744/529, loss: 0.07541751861572266
2023-01-23 02:06:02.403808: step: 748/529, loss: 0.053116895258426666
2023-01-23 02:06:03.605148: step: 752/529, loss: 0.011973142623901367
2023-01-23 02:06:04.767434: step: 756/529, loss: 0.06626713275909424
2023-01-23 02:06:05.957602: step: 760/529, loss: 0.030478190630674362
2023-01-23 02:06:07.163098: step: 764/529, loss: 0.025000954046845436
2023-01-23 02:06:08.372833: step: 768/529, loss: 0.042382147163152695
2023-01-23 02:06:09.574889: step: 772/529, loss: 0.018733978271484375
2023-01-23 02:06:10.753156: step: 776/529, loss: 0.020431995391845703
2023-01-23 02:06:11.948733: step: 780/529, loss: 0.004310572519898415
2023-01-23 02:06:13.135181: step: 784/529, loss: 0.0185564998537302
2023-01-23 02:06:14.321222: step: 788/529, loss: 0.038434840738773346
2023-01-23 02:06:15.514204: step: 792/529, loss: 0.019561195746064186
2023-01-23 02:06:16.684874: step: 796/529, loss: 0.06027545779943466
2023-01-23 02:06:17.900950: step: 800/529, loss: 0.0046752928756177425
2023-01-23 02:06:19.065393: step: 804/529, loss: 0.019846344366669655
2023-01-23 02:06:20.249208: step: 808/529, loss: 0.006213807966560125
2023-01-23 02:06:21.480168: step: 812/529, loss: 0.11909833550453186
2023-01-23 02:06:22.682835: step: 816/529, loss: 0.13234928250312805
2023-01-23 02:06:23.871298: step: 820/529, loss: 0.011299706064164639
2023-01-23 02:06:25.060517: step: 824/529, loss: 0.33778563141822815
2023-01-23 02:06:26.254027: step: 828/529, loss: 0.002963733859360218
2023-01-23 02:06:27.501029: step: 832/529, loss: 0.016438674181699753
2023-01-23 02:06:28.675019: step: 836/529, loss: 0.13288964331150055
2023-01-23 02:06:29.854372: step: 840/529, loss: 0.05501976236701012
2023-01-23 02:06:31.079736: step: 844/529, loss: 0.011426448822021484
2023-01-23 02:06:32.282204: step: 848/529, loss: 0.014819907955825329
2023-01-23 02:06:33.526310: step: 852/529, loss: 0.033202577382326126
2023-01-23 02:06:34.734045: step: 856/529, loss: 0.03636999428272247
2023-01-23 02:06:35.953189: step: 860/529, loss: 0.012090111151337624
2023-01-23 02:06:37.187660: step: 864/529, loss: 0.005740070249885321
2023-01-23 02:06:38.419417: step: 868/529, loss: 0.0006246566772460938
2023-01-23 02:06:39.578852: step: 872/529, loss: 0.0747474730014801
2023-01-23 02:06:40.767889: step: 876/529, loss: 0.010081958957016468
2023-01-23 02:06:41.956368: step: 880/529, loss: 0.024919986724853516
2023-01-23 02:06:43.193576: step: 884/529, loss: 0.02447795867919922
2023-01-23 02:06:44.386611: step: 888/529, loss: 0.0512942336499691
2023-01-23 02:06:45.602840: step: 892/529, loss: 0.023643113672733307
2023-01-23 02:06:46.787640: step: 896/529, loss: 0.051764197647571564
2023-01-23 02:06:48.002354: step: 900/529, loss: 0.046014074236154556
2023-01-23 02:06:49.192343: step: 904/529, loss: 0.006800270173698664
2023-01-23 02:06:50.443671: step: 908/529, loss: 0.03627128526568413
2023-01-23 02:06:51.606836: step: 912/529, loss: 0.006840634159743786
2023-01-23 02:06:52.800908: step: 916/529, loss: 0.07601527869701385
2023-01-23 02:06:54.021951: step: 920/529, loss: 0.008344730362296104
2023-01-23 02:06:55.195566: step: 924/529, loss: 0.08563299477100372
2023-01-23 02:06:56.424481: step: 928/529, loss: 0.004166221711784601
2023-01-23 02:06:57.597797: step: 932/529, loss: 0.0009152413113042712
2023-01-23 02:06:58.821418: step: 936/529, loss: 0.06440772861242294
2023-01-23 02:07:00.039777: step: 940/529, loss: 0.10162906348705292
2023-01-23 02:07:01.276188: step: 944/529, loss: 0.025232411921024323
2023-01-23 02:07:02.517189: step: 948/529, loss: 0.002295208163559437
2023-01-23 02:07:03.729438: step: 952/529, loss: 0.009371376596391201
2023-01-23 02:07:04.913170: step: 956/529, loss: 0.010438680648803711
2023-01-23 02:07:06.107807: step: 960/529, loss: 0.04470653831958771
2023-01-23 02:07:07.287818: step: 964/529, loss: 0.042991068214178085
2023-01-23 02:07:08.498057: step: 968/529, loss: 0.02541675604879856
2023-01-23 02:07:09.691341: step: 972/529, loss: 0.0003917694266419858
2023-01-23 02:07:10.857339: step: 976/529, loss: 0.06460399925708771
2023-01-23 02:07:12.076548: step: 980/529, loss: 0.018777180463075638
2023-01-23 02:07:13.286344: step: 984/529, loss: 0.013294219970703125
2023-01-23 02:07:14.547057: step: 988/529, loss: 0.0044689178466796875
2023-01-23 02:07:15.759149: step: 992/529, loss: 0.01676197163760662
2023-01-23 02:07:16.940120: step: 996/529, loss: 0.0016300200950354338
2023-01-23 02:07:18.130586: step: 1000/529, loss: 0.06373615562915802
2023-01-23 02:07:19.333378: step: 1004/529, loss: 0.011961079202592373
2023-01-23 02:07:20.548079: step: 1008/529, loss: 0.016974449157714844
2023-01-23 02:07:21.742778: step: 1012/529, loss: 0.04460439831018448
2023-01-23 02:07:22.916295: step: 1016/529, loss: 0.0014761924976482987
2023-01-23 02:07:24.115304: step: 1020/529, loss: 0.002438449999317527
2023-01-23 02:07:25.318363: step: 1024/529, loss: 0.06784658879041672
2023-01-23 02:07:26.537310: step: 1028/529, loss: 5.356073233997449e-05
2023-01-23 02:07:27.720567: step: 1032/529, loss: 0.0034419295843690634
2023-01-23 02:07:28.911687: step: 1036/529, loss: 0.04433612525463104
2023-01-23 02:07:30.068984: step: 1040/529, loss: 0.021614840254187584
2023-01-23 02:07:31.263251: step: 1044/529, loss: 0.00931086577475071
2023-01-23 02:07:32.467384: step: 1048/529, loss: 0.00672181835398078
2023-01-23 02:07:33.668800: step: 1052/529, loss: 0.011656666174530983
2023-01-23 02:07:34.884369: step: 1056/529, loss: 0.003907013218849897
2023-01-23 02:07:36.085296: step: 1060/529, loss: 0.014815330505371094
2023-01-23 02:07:37.313004: step: 1064/529, loss: 0.04444169998168945
2023-01-23 02:07:38.518491: step: 1068/529, loss: 0.022906780242919922
2023-01-23 02:07:39.737772: step: 1072/529, loss: 0.04141044616699219
2023-01-23 02:07:40.986440: step: 1076/529, loss: 0.027387570589780807
2023-01-23 02:07:42.240399: step: 1080/529, loss: 0.0660918653011322
2023-01-23 02:07:43.475277: step: 1084/529, loss: 0.07434835284948349
2023-01-23 02:07:44.675119: step: 1088/529, loss: 0.009459877386689186
2023-01-23 02:07:45.836003: step: 1092/529, loss: 0.00022692680067848414
2023-01-23 02:07:47.041966: step: 1096/529, loss: 0.04892406240105629
2023-01-23 02:07:48.216119: step: 1100/529, loss: 0.00038533209590241313
2023-01-23 02:07:49.401647: step: 1104/529, loss: 0.00266265869140625
2023-01-23 02:07:50.574663: step: 1108/529, loss: 0.006957817357033491
2023-01-23 02:07:51.788075: step: 1112/529, loss: 0.018420647829771042
2023-01-23 02:07:53.008253: step: 1116/529, loss: 0.00014655590348411351
2023-01-23 02:07:54.202178: step: 1120/529, loss: 0.020693015307188034
2023-01-23 02:07:55.410938: step: 1124/529, loss: 0.062240030616521835
2023-01-23 02:07:56.567309: step: 1128/529, loss: 0.0307219997048378
2023-01-23 02:07:57.730823: step: 1132/529, loss: 0.054282285273075104
2023-01-23 02:07:58.933383: step: 1136/529, loss: 0.060857199132442474
2023-01-23 02:08:00.138567: step: 1140/529, loss: 0.011554241180419922
2023-01-23 02:08:01.365992: step: 1144/529, loss: 0.09443559497594833
2023-01-23 02:08:02.559797: step: 1148/529, loss: 0.006712627597153187
2023-01-23 02:08:03.784517: step: 1152/529, loss: 0.0019847869407385588
2023-01-23 02:08:05.027659: step: 1156/529, loss: 0.04674654081463814
2023-01-23 02:08:06.247123: step: 1160/529, loss: 0.10736479610204697
2023-01-23 02:08:07.408904: step: 1164/529, loss: 0.06859998404979706
2023-01-23 02:08:08.622764: step: 1168/529, loss: 0.04300422593951225
2023-01-23 02:08:09.793940: step: 1172/529, loss: 0.003788185305893421
2023-01-23 02:08:10.983997: step: 1176/529, loss: 0.05814613029360771
2023-01-23 02:08:12.162854: step: 1180/529, loss: 0.01941204071044922
2023-01-23 02:08:13.410891: step: 1184/529, loss: 0.02299346961081028
2023-01-23 02:08:14.578982: step: 1188/529, loss: 0.029853487387299538
2023-01-23 02:08:15.801196: step: 1192/529, loss: 0.012223467230796814
2023-01-23 02:08:17.017177: step: 1196/529, loss: 0.009244346991181374
2023-01-23 02:08:18.173362: step: 1200/529, loss: 1.0814969539642334
2023-01-23 02:08:19.351841: step: 1204/529, loss: 0.07040288299322128
2023-01-23 02:08:20.556736: step: 1208/529, loss: 0.022809602320194244
2023-01-23 02:08:21.765971: step: 1212/529, loss: 0.03156089782714844
2023-01-23 02:08:22.969458: step: 1216/529, loss: 0.04622860252857208
2023-01-23 02:08:24.147102: step: 1220/529, loss: 0.003847408341243863
2023-01-23 02:08:25.356460: step: 1224/529, loss: 0.03626842424273491
2023-01-23 02:08:26.568129: step: 1228/529, loss: 0.028188131749629974
2023-01-23 02:08:27.771009: step: 1232/529, loss: 0.03349714353680611
2023-01-23 02:08:28.983125: step: 1236/529, loss: 0.0012277603382244706
2023-01-23 02:08:30.206386: step: 1240/529, loss: 0.01671772077679634
2023-01-23 02:08:31.383349: step: 1244/529, loss: 0.016425132751464844
2023-01-23 02:08:32.606216: step: 1248/529, loss: 0.022949744015932083
2023-01-23 02:08:33.777353: step: 1252/529, loss: 0.00038061142549850047
2023-01-23 02:08:34.984874: step: 1256/529, loss: 0.023551560938358307
2023-01-23 02:08:36.138358: step: 1260/529, loss: 0.00201835623010993
2023-01-23 02:08:37.301595: step: 1264/529, loss: 0.05218858644366264
2023-01-23 02:08:38.510082: step: 1268/529, loss: 0.01800518110394478
2023-01-23 02:08:39.722049: step: 1272/529, loss: 0.005594968795776367
2023-01-23 02:08:40.886254: step: 1276/529, loss: 0.000411796587286517
2023-01-23 02:08:42.087355: step: 1280/529, loss: 0.017890071496367455
2023-01-23 02:08:43.322666: step: 1284/529, loss: 0.036007121205329895
2023-01-23 02:08:44.513114: step: 1288/529, loss: 0.008306790143251419
2023-01-23 02:08:45.666007: step: 1292/529, loss: 0.003742170287296176
2023-01-23 02:08:46.827674: step: 1296/529, loss: 0.013090801425278187
2023-01-23 02:08:48.041912: step: 1300/529, loss: 0.0004913330194540322
2023-01-23 02:08:49.207916: step: 1304/529, loss: 0.10652267932891846
2023-01-23 02:08:50.449702: step: 1308/529, loss: 0.03825564309954643
2023-01-23 02:08:51.645389: step: 1312/529, loss: 0.07320308685302734
2023-01-23 02:08:52.880194: step: 1316/529, loss: 0.17192836105823517
2023-01-23 02:08:54.111706: step: 1320/529, loss: 0.03330964967608452
2023-01-23 02:08:55.325112: step: 1324/529, loss: 0.014474963769316673
2023-01-23 02:08:56.526759: step: 1328/529, loss: 0.11852865666151047
2023-01-23 02:08:57.703377: step: 1332/529, loss: 0.0608641617000103
2023-01-23 02:08:58.897183: step: 1336/529, loss: 0.001866340753622353
2023-01-23 02:09:00.120178: step: 1340/529, loss: 0.006926822941750288
2023-01-23 02:09:01.316965: step: 1344/529, loss: 0.00719451904296875
2023-01-23 02:09:02.556722: step: 1348/529, loss: 0.008491134271025658
2023-01-23 02:09:03.744273: step: 1352/529, loss: 0.04129600524902344
2023-01-23 02:09:04.937508: step: 1356/529, loss: 0.00010333061800338328
2023-01-23 02:09:06.127495: step: 1360/529, loss: 0.0492795929312706
2023-01-23 02:09:07.301790: step: 1364/529, loss: 0.0018196107121184468
2023-01-23 02:09:08.542598: step: 1368/529, loss: 0.03764224052429199
2023-01-23 02:09:09.819668: step: 1372/529, loss: 0.10187163949012756
2023-01-23 02:09:11.017972: step: 1376/529, loss: 0.08095722645521164
2023-01-23 02:09:12.250948: step: 1380/529, loss: 0.04181652143597603
2023-01-23 02:09:13.460891: step: 1384/529, loss: 0.05039720609784126
2023-01-23 02:09:14.642816: step: 1388/529, loss: 0.0014057159423828125
2023-01-23 02:09:15.856867: step: 1392/529, loss: 0.009013366885483265
2023-01-23 02:09:17.030366: step: 1396/529, loss: 0.03609433025121689
2023-01-23 02:09:18.255533: step: 1400/529, loss: 0.005547666922211647
2023-01-23 02:09:19.468703: step: 1404/529, loss: 0.06917114555835724
2023-01-23 02:09:20.647740: step: 1408/529, loss: 0.018605804070830345
2023-01-23 02:09:21.822935: step: 1412/529, loss: 0.03199462965130806
2023-01-23 02:09:23.057115: step: 1416/529, loss: 0.005234909243881702
2023-01-23 02:09:24.227447: step: 1420/529, loss: 0.015880774706602097
2023-01-23 02:09:25.437526: step: 1424/529, loss: 0.0042021749541163445
2023-01-23 02:09:26.658625: step: 1428/529, loss: 0.016536809504032135
2023-01-23 02:09:27.850010: step: 1432/529, loss: 0.03170328214764595
2023-01-23 02:09:29.005063: step: 1436/529, loss: 0.02615375444293022
2023-01-23 02:09:30.232389: step: 1440/529, loss: 0.056096553802490234
2023-01-23 02:09:31.403351: step: 1444/529, loss: 0.03340788185596466
2023-01-23 02:09:32.620737: step: 1448/529, loss: 0.19283849000930786
2023-01-23 02:09:33.838804: step: 1452/529, loss: 0.23090897500514984
2023-01-23 02:09:35.040417: step: 1456/529, loss: 0.0010876655578613281
2023-01-23 02:09:36.265389: step: 1460/529, loss: 0.014848804101347923
2023-01-23 02:09:37.467642: step: 1464/529, loss: 0.07609906047582626
2023-01-23 02:09:38.657669: step: 1468/529, loss: 0.09213419258594513
2023-01-23 02:09:39.864438: step: 1472/529, loss: 0.0009335518116131425
2023-01-23 02:09:41.032214: step: 1476/529, loss: 0.07358980178833008
2023-01-23 02:09:42.247327: step: 1480/529, loss: 0.06184225156903267
2023-01-23 02:09:43.500801: step: 1484/529, loss: 0.017884254455566406
2023-01-23 02:09:44.712594: step: 1488/529, loss: 0.017476225271821022
2023-01-23 02:09:45.925964: step: 1492/529, loss: 0.004854679573327303
2023-01-23 02:09:47.093650: step: 1496/529, loss: 0.010556602850556374
2023-01-23 02:09:48.264638: step: 1500/529, loss: 0.00023078919912222773
2023-01-23 02:09:49.446221: step: 1504/529, loss: 0.02437286451458931
2023-01-23 02:09:50.675337: step: 1508/529, loss: 0.03038806840777397
2023-01-23 02:09:51.860737: step: 1512/529, loss: 0.00694322632625699
2023-01-23 02:09:53.049598: step: 1516/529, loss: 0.004525661468505859
2023-01-23 02:09:54.266079: step: 1520/529, loss: 0.03191728889942169
2023-01-23 02:09:55.440012: step: 1524/529, loss: 0.020081328228116035
2023-01-23 02:09:56.612471: step: 1528/529, loss: 0.02995023876428604
2023-01-23 02:09:57.800734: step: 1532/529, loss: 0.006091165356338024
2023-01-23 02:09:58.989425: step: 1536/529, loss: 0.04897952079772949
2023-01-23 02:10:00.171243: step: 1540/529, loss: 0.016426658257842064
2023-01-23 02:10:01.384779: step: 1544/529, loss: 0.011411094106733799
2023-01-23 02:10:02.541369: step: 1548/529, loss: 0.01201553363353014
2023-01-23 02:10:03.765751: step: 1552/529, loss: 0.02086820639669895
2023-01-23 02:10:05.013022: step: 1556/529, loss: 0.027756690979003906
2023-01-23 02:10:06.206307: step: 1560/529, loss: 0.039585113525390625
2023-01-23 02:10:07.404798: step: 1564/529, loss: 0.00830750446766615
2023-01-23 02:10:08.639355: step: 1568/529, loss: 0.1655474603176117
2023-01-23 02:10:09.832965: step: 1572/529, loss: 0.023420382291078568
2023-01-23 02:10:11.041033: step: 1576/529, loss: 0.03487744182348251
2023-01-23 02:10:12.262885: step: 1580/529, loss: 0.021817969158291817
2023-01-23 02:10:13.478248: step: 1584/529, loss: 0.21566659212112427
2023-01-23 02:10:14.660211: step: 1588/529, loss: 0.008579397574067116
2023-01-23 02:10:15.838523: step: 1592/529, loss: 0.027110768482089043
2023-01-23 02:10:17.023121: step: 1596/529, loss: 0.006395912263542414
2023-01-23 02:10:18.196569: step: 1600/529, loss: 0.037157345563173294
2023-01-23 02:10:19.350778: step: 1604/529, loss: 0.0024506808258593082
2023-01-23 02:10:20.557413: step: 1608/529, loss: 0.007738590240478516
2023-01-23 02:10:21.752307: step: 1612/529, loss: 0.043433211743831635
2023-01-23 02:10:22.944499: step: 1616/529, loss: 0.06994209438562393
2023-01-23 02:10:24.144488: step: 1620/529, loss: 0.03247642517089844
2023-01-23 02:10:25.348755: step: 1624/529, loss: 0.01715526543557644
2023-01-23 02:10:26.542620: step: 1628/529, loss: 0.09717759490013123
2023-01-23 02:10:27.815980: step: 1632/529, loss: 0.0369015708565712
2023-01-23 02:10:29.049356: step: 1636/529, loss: 0.008671188727021217
2023-01-23 02:10:30.274237: step: 1640/529, loss: 0.028925515711307526
2023-01-23 02:10:31.482939: step: 1644/529, loss: 0.06007962301373482
2023-01-23 02:10:32.671909: step: 1648/529, loss: 0.10519365966320038
2023-01-23 02:10:33.923875: step: 1652/529, loss: 0.023768329992890358
2023-01-23 02:10:35.101346: step: 1656/529, loss: 0.008392333984375
2023-01-23 02:10:36.317440: step: 1660/529, loss: 0.027727318927645683
2023-01-23 02:10:37.520049: step: 1664/529, loss: 0.04635639116168022
2023-01-23 02:10:38.754712: step: 1668/529, loss: 0.053844548761844635
2023-01-23 02:10:39.927309: step: 1672/529, loss: 0.00657577533274889
2023-01-23 02:10:41.147650: step: 1676/529, loss: 0.0302339568734169
2023-01-23 02:10:42.370567: step: 1680/529, loss: 0.05921907722949982
2023-01-23 02:10:43.553150: step: 1684/529, loss: 0.13537339866161346
2023-01-23 02:10:44.789302: step: 1688/529, loss: 0.012246895581483841
2023-01-23 02:10:46.025267: step: 1692/529, loss: 0.05579128488898277
2023-01-23 02:10:47.208704: step: 1696/529, loss: 0.04338718578219414
2023-01-23 02:10:48.411570: step: 1700/529, loss: 0.026494218036532402
2023-01-23 02:10:49.609950: step: 1704/529, loss: 0.001966858049854636
2023-01-23 02:10:50.785521: step: 1708/529, loss: 0.05786151811480522
2023-01-23 02:10:51.970342: step: 1712/529, loss: 0.005179214756935835
2023-01-23 02:10:53.176020: step: 1716/529, loss: 0.0737430602312088
2023-01-23 02:10:54.408095: step: 1720/529, loss: 0.021807575598359108
2023-01-23 02:10:55.606252: step: 1724/529, loss: 0.0010194778442382812
2023-01-23 02:10:56.834234: step: 1728/529, loss: 0.061908818781375885
2023-01-23 02:10:58.072913: step: 1732/529, loss: 0.0765039250254631
2023-01-23 02:10:59.296891: step: 1736/529, loss: 0.005922412965446711
2023-01-23 02:11:00.490220: step: 1740/529, loss: 0.3252026438713074
2023-01-23 02:11:01.702004: step: 1744/529, loss: 0.0926109328866005
2023-01-23 02:11:02.915817: step: 1748/529, loss: 0.027489136904478073
2023-01-23 02:11:04.113686: step: 1752/529, loss: 0.0010555267799645662
2023-01-23 02:11:05.327534: step: 1756/529, loss: 0.016663696616888046
2023-01-23 02:11:06.530135: step: 1760/529, loss: 0.0016357898712158203
2023-01-23 02:11:07.737043: step: 1764/529, loss: 0.014433860778808594
2023-01-23 02:11:08.953659: step: 1768/529, loss: 0.03584950044751167
2023-01-23 02:11:10.170428: step: 1772/529, loss: 0.0376676581799984
2023-01-23 02:11:11.310636: step: 1776/529, loss: 0.0016571879386901855
2023-01-23 02:11:12.485566: step: 1780/529, loss: 0.04992799460887909
2023-01-23 02:11:13.678778: step: 1784/529, loss: 0.0011640548473224044
2023-01-23 02:11:14.853911: step: 1788/529, loss: 0.00037755968514829874
2023-01-23 02:11:16.018937: step: 1792/529, loss: 0.0003247261047363281
2023-01-23 02:11:17.241528: step: 1796/529, loss: 0.06704292446374893
2023-01-23 02:11:18.460063: step: 1800/529, loss: 0.020928382873535156
2023-01-23 02:11:19.647916: step: 1804/529, loss: 0.02228565141558647
2023-01-23 02:11:20.890886: step: 1808/529, loss: 0.041188813745975494
2023-01-23 02:11:22.085238: step: 1812/529, loss: 0.02476959303021431
2023-01-23 02:11:23.289343: step: 1816/529, loss: 0.04090118780732155
2023-01-23 02:11:24.507357: step: 1820/529, loss: 0.09428396075963974
2023-01-23 02:11:25.722665: step: 1824/529, loss: 0.016428424045443535
2023-01-23 02:11:26.888747: step: 1828/529, loss: 0.1583634465932846
2023-01-23 02:11:28.094421: step: 1832/529, loss: 0.002458715345710516
2023-01-23 02:11:29.276672: step: 1836/529, loss: 0.5011193752288818
2023-01-23 02:11:30.418044: step: 1840/529, loss: 0.004469394683837891
2023-01-23 02:11:31.605503: step: 1844/529, loss: 0.026998329907655716
2023-01-23 02:11:32.806262: step: 1848/529, loss: 0.0014792443253099918
2023-01-23 02:11:33.998312: step: 1852/529, loss: 0.07603378593921661
2023-01-23 02:11:35.177371: step: 1856/529, loss: 0.020480729639530182
2023-01-23 02:11:36.399462: step: 1860/529, loss: 0.06016102060675621
2023-01-23 02:11:37.592673: step: 1864/529, loss: 0.05631885677576065
2023-01-23 02:11:38.771317: step: 1868/529, loss: 0.02674713358283043
2023-01-23 02:11:40.010120: step: 1872/529, loss: 0.016243457794189453
2023-01-23 02:11:41.216653: step: 1876/529, loss: 0.03381548076868057
2023-01-23 02:11:42.405558: step: 1880/529, loss: 0.11983232200145721
2023-01-23 02:11:43.568698: step: 1884/529, loss: 0.004639292135834694
2023-01-23 02:11:44.783518: step: 1888/529, loss: 0.01834392547607422
2023-01-23 02:11:45.946059: step: 1892/529, loss: 0.025397300720214844
2023-01-23 02:11:47.131559: step: 1896/529, loss: 0.044028472155332565
2023-01-23 02:11:48.324229: step: 1900/529, loss: 0.025841571390628815
2023-01-23 02:11:49.557515: step: 1904/529, loss: 0.06521806865930557
2023-01-23 02:11:50.785522: step: 1908/529, loss: 0.0029126168228685856
2023-01-23 02:11:51.952443: step: 1912/529, loss: 0.029267311096191406
2023-01-23 02:11:53.148415: step: 1916/529, loss: 0.0072495462372899055
2023-01-23 02:11:54.353766: step: 1920/529, loss: 0.019012833014130592
2023-01-23 02:11:55.563145: step: 1924/529, loss: 0.05298023298382759
2023-01-23 02:11:56.784379: step: 1928/529, loss: 0.03023510053753853
2023-01-23 02:11:57.987789: step: 1932/529, loss: 0.010569954290986061
2023-01-23 02:11:59.171094: step: 1936/529, loss: 0.023093413561582565
2023-01-23 02:12:00.362990: step: 1940/529, loss: 0.033271122723817825
2023-01-23 02:12:01.565828: step: 1944/529, loss: 0.03945844620466232
2023-01-23 02:12:02.762057: step: 1948/529, loss: 0.025533199310302734
2023-01-23 02:12:03.967747: step: 1952/529, loss: 0.00640106201171875
2023-01-23 02:12:05.215339: step: 1956/529, loss: 0.0009051322704181075
2023-01-23 02:12:06.399412: step: 1960/529, loss: 0.028422977775335312
2023-01-23 02:12:07.593494: step: 1964/529, loss: 0.00532188406214118
2023-01-23 02:12:08.775087: step: 1968/529, loss: 0.021473407745361328
2023-01-23 02:12:09.983272: step: 1972/529, loss: 0.014600562863051891
2023-01-23 02:12:11.171333: step: 1976/529, loss: 0.004134654998779297
2023-01-23 02:12:12.379695: step: 1980/529, loss: 0.01762828789651394
2023-01-23 02:12:13.593997: step: 1984/529, loss: 0.0854034423828125
2023-01-23 02:12:14.806388: step: 1988/529, loss: 0.013809156604111195
2023-01-23 02:12:15.991922: step: 1992/529, loss: 0.007717037573456764
2023-01-23 02:12:17.188521: step: 1996/529, loss: 0.05528444051742554
2023-01-23 02:12:18.366409: step: 2000/529, loss: 0.013115406967699528
2023-01-23 02:12:19.578509: step: 2004/529, loss: 0.007703018374741077
2023-01-23 02:12:20.771516: step: 2008/529, loss: 0.09631047397851944
2023-01-23 02:12:21.948126: step: 2012/529, loss: 0.0621306411921978
2023-01-23 02:12:23.163806: step: 2016/529, loss: 0.0782390609383583
2023-01-23 02:12:24.358658: step: 2020/529, loss: 0.02251298539340496
2023-01-23 02:12:25.532242: step: 2024/529, loss: 0.04134407266974449
2023-01-23 02:12:26.768305: step: 2028/529, loss: 0.004563379101455212
2023-01-23 02:12:27.929271: step: 2032/529, loss: 0.015045547857880592
2023-01-23 02:12:29.150058: step: 2036/529, loss: 0.028399229049682617
2023-01-23 02:12:30.366539: step: 2040/529, loss: 0.023426437750458717
2023-01-23 02:12:31.578166: step: 2044/529, loss: 0.003564548445865512
2023-01-23 02:12:32.833344: step: 2048/529, loss: 0.19866323471069336
2023-01-23 02:12:34.036762: step: 2052/529, loss: 0.02984476089477539
2023-01-23 02:12:35.198520: step: 2056/529, loss: 0.006458664312958717
2023-01-23 02:12:36.419188: step: 2060/529, loss: 0.021860789507627487
2023-01-23 02:12:37.644185: step: 2064/529, loss: 0.038942813873291016
2023-01-23 02:12:38.903550: step: 2068/529, loss: 0.0885000228881836
2023-01-23 02:12:40.093885: step: 2072/529, loss: 0.03750648349523544
2023-01-23 02:12:41.273408: step: 2076/529, loss: 0.03317384794354439
2023-01-23 02:12:42.429391: step: 2080/529, loss: 0.05186500772833824
2023-01-23 02:12:43.605373: step: 2084/529, loss: 0.5616950988769531
2023-01-23 02:12:44.763147: step: 2088/529, loss: 0.00017333030700683594
2023-01-23 02:12:46.002039: step: 2092/529, loss: 0.024314500391483307
2023-01-23 02:12:47.154484: step: 2096/529, loss: 0.010793877765536308
2023-01-23 02:12:48.351900: step: 2100/529, loss: 0.14183488488197327
2023-01-23 02:12:49.562666: step: 2104/529, loss: 0.022354889661073685
2023-01-23 02:12:50.790990: step: 2108/529, loss: 0.24488191306591034
2023-01-23 02:12:51.947422: step: 2112/529, loss: 0.01973886415362358
2023-01-23 02:12:53.142390: step: 2116/529, loss: 0.023023415356874466
==================================================
Loss: 0.049
--------------------
Dev: {'event': {'p': 0.6347634763476347, 'r': 0.7683089214380826, 'f1': 0.6951807228915663}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6570852244074634, 'r': 0.78070701018574, 'f1': 0.7135815991237677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.6164383561643836, 'r': 0.8333333333333334, 'f1': 0.7086614173228347}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.5769230769230769, 'r': 0.47619047619047616, 'f1': 0.5217391304347826}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.4857142857142857, 'r': 0.4722222222222222, 'f1': 0.47887323943661975}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6, 'r': 0.7470039946737683, 'f1': 0.6654804270462634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.630667345899134, 'r': 0.7417615338526063, 'f1': 0.6817180616740088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
******************************
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 02:13:36.826717: step: 4/529, loss: 0.03386259078979492
2023-01-23 02:13:38.044432: step: 8/529, loss: 0.01895732991397381
2023-01-23 02:13:39.269583: step: 12/529, loss: 0.004780387971550226
2023-01-23 02:13:40.473771: step: 16/529, loss: 0.0059111593291163445
2023-01-23 02:13:41.685864: step: 20/529, loss: 0.009102058596909046
2023-01-23 02:13:42.888490: step: 24/529, loss: 0.0008537292596884072
2023-01-23 02:13:44.061113: step: 28/529, loss: 0.030220700427889824
2023-01-23 02:13:45.283026: step: 32/529, loss: 0.01554260216653347
2023-01-23 02:13:46.475747: step: 36/529, loss: 0.03621234744787216
2023-01-23 02:13:47.687131: step: 40/529, loss: 0.007046795450150967
2023-01-23 02:13:48.873861: step: 44/529, loss: 0.041281700134277344
2023-01-23 02:13:50.072836: step: 48/529, loss: 0.016413306817412376
2023-01-23 02:13:51.295642: step: 52/529, loss: 0.313218891620636
2023-01-23 02:13:52.526802: step: 56/529, loss: 0.007563972845673561
2023-01-23 02:13:53.717410: step: 60/529, loss: 0.0021259309723973274
2023-01-23 02:13:54.903253: step: 64/529, loss: 0.014450454153120518
2023-01-23 02:13:56.093624: step: 68/529, loss: 0.013047791086137295
2023-01-23 02:13:57.293195: step: 72/529, loss: 0.025946902111172676
2023-01-23 02:13:58.457337: step: 76/529, loss: 0.0008395194890908897
2023-01-23 02:13:59.644290: step: 80/529, loss: 0.027770616114139557
2023-01-23 02:14:00.855243: step: 84/529, loss: 0.043586160987615585
2023-01-23 02:14:02.101582: step: 88/529, loss: 0.011481857858598232
2023-01-23 02:14:03.284993: step: 92/529, loss: 0.042740631848573685
2023-01-23 02:14:04.474242: step: 96/529, loss: 0.054631710052490234
2023-01-23 02:14:05.680661: step: 100/529, loss: 0.0072231292724609375
2023-01-23 02:14:06.866381: step: 104/529, loss: 0.045874498784542084
2023-01-23 02:14:08.032086: step: 108/529, loss: 0.031756602227687836
2023-01-23 02:14:09.215958: step: 112/529, loss: 0.00864114798605442
2023-01-23 02:14:10.374840: step: 116/529, loss: 0.0062046051025390625
2023-01-23 02:14:11.613883: step: 120/529, loss: 0.09919299930334091
2023-01-23 02:14:12.790257: step: 124/529, loss: 0.02214345894753933
2023-01-23 02:14:14.022492: step: 128/529, loss: 0.021587181836366653
2023-01-23 02:14:15.213992: step: 132/529, loss: 0.009229565039277077
2023-01-23 02:14:16.438473: step: 136/529, loss: 0.0022395134437829256
2023-01-23 02:14:17.665471: step: 140/529, loss: 0.008449936285614967
2023-01-23 02:14:18.832995: step: 144/529, loss: 0.04003726318478584
2023-01-23 02:14:20.044161: step: 148/529, loss: 0.03970833122730255
2023-01-23 02:14:21.197872: step: 152/529, loss: 0.003884220262989402
2023-01-23 02:14:22.344690: step: 156/529, loss: 0.02139425277709961
2023-01-23 02:14:23.537328: step: 160/529, loss: 0.053163837641477585
2023-01-23 02:14:24.763128: step: 164/529, loss: 0.01021342258900404
2023-01-23 02:14:25.960902: step: 168/529, loss: 0.00022326708131004125
2023-01-23 02:14:27.141775: step: 172/529, loss: 0.01319131813943386
2023-01-23 02:14:28.343269: step: 176/529, loss: 0.006054425146430731
2023-01-23 02:14:29.499948: step: 180/529, loss: 0.0011057853698730469
2023-01-23 02:14:30.722198: step: 184/529, loss: 0.0019320010906085372
2023-01-23 02:14:31.941087: step: 188/529, loss: 0.025048447772860527
2023-01-23 02:14:33.088402: step: 192/529, loss: 0.020913315936923027
2023-01-23 02:14:34.282114: step: 196/529, loss: 0.0015975474379956722
2023-01-23 02:14:35.496681: step: 200/529, loss: 0.0023563385475426912
2023-01-23 02:14:36.670044: step: 204/529, loss: 0.011036348529160023
2023-01-23 02:14:37.840114: step: 208/529, loss: 0.017014121636748314
2023-01-23 02:14:39.036121: step: 212/529, loss: 0.037658121436834335
2023-01-23 02:14:40.332977: step: 216/529, loss: 0.012936020269989967
2023-01-23 02:14:41.513071: step: 220/529, loss: 0.08248496055603027
2023-01-23 02:14:42.689182: step: 224/529, loss: 0.02506725676357746
2023-01-23 02:14:43.917004: step: 228/529, loss: 0.014095116406679153
2023-01-23 02:14:45.069104: step: 232/529, loss: 0.001775503158569336
2023-01-23 02:14:46.260871: step: 236/529, loss: 0.03330402448773384
2023-01-23 02:14:47.484518: step: 240/529, loss: 0.01157617662101984
2023-01-23 02:14:48.682025: step: 244/529, loss: 0.009611034765839577
2023-01-23 02:14:49.918176: step: 248/529, loss: 0.002068805741146207
2023-01-23 02:14:51.088830: step: 252/529, loss: 0.026804160326719284
2023-01-23 02:14:52.260593: step: 256/529, loss: 0.000242447858909145
2023-01-23 02:14:53.455993: step: 260/529, loss: 0.013714027591049671
2023-01-23 02:14:54.662704: step: 264/529, loss: 0.016179945319890976
2023-01-23 02:14:55.857999: step: 268/529, loss: 0.004040074534714222
2023-01-23 02:14:57.025498: step: 272/529, loss: 0.034638214856386185
2023-01-23 02:14:58.259554: step: 276/529, loss: 0.06983423233032227
2023-01-23 02:14:59.456297: step: 280/529, loss: 0.04929351806640625
2023-01-23 02:15:00.675643: step: 284/529, loss: 0.001996803330257535
2023-01-23 02:15:01.887694: step: 288/529, loss: 0.0008342742803506553
2023-01-23 02:15:03.060696: step: 292/529, loss: 0.0026855471078306437
2023-01-23 02:15:04.302101: step: 296/529, loss: 0.09072045981884003
2023-01-23 02:15:05.465914: step: 300/529, loss: 0.016280174255371094
2023-01-23 02:15:06.645558: step: 304/529, loss: 0.02234954945743084
2023-01-23 02:15:07.871600: step: 308/529, loss: 0.04812812805175781
2023-01-23 02:15:09.117944: step: 312/529, loss: 0.004421234130859375
2023-01-23 02:15:10.340957: step: 316/529, loss: 0.005058002658188343
2023-01-23 02:15:11.510911: step: 320/529, loss: 0.003060245420783758
2023-01-23 02:15:12.717945: step: 324/529, loss: 0.0555814728140831
2023-01-23 02:15:13.891336: step: 328/529, loss: 0.05863399803638458
2023-01-23 02:15:15.076830: step: 332/529, loss: 0.2641967833042145
2023-01-23 02:15:16.246302: step: 336/529, loss: 0.005670833867043257
2023-01-23 02:15:17.423471: step: 340/529, loss: 0.02503070794045925
2023-01-23 02:15:18.628208: step: 344/529, loss: 0.019318629056215286
2023-01-23 02:15:19.837752: step: 348/529, loss: 0.2950594127178192
2023-01-23 02:15:21.035933: step: 352/529, loss: 0.047513388097286224
2023-01-23 02:15:22.214134: step: 356/529, loss: 0.0666167289018631
2023-01-23 02:15:23.416053: step: 360/529, loss: 0.003142166417092085
2023-01-23 02:15:24.614582: step: 364/529, loss: 0.010245705023407936
2023-01-23 02:15:25.810284: step: 368/529, loss: 0.015403127297759056
2023-01-23 02:15:27.027276: step: 372/529, loss: 0.04624128341674805
2023-01-23 02:15:28.164501: step: 376/529, loss: 0.015455389395356178
2023-01-23 02:15:29.353640: step: 380/529, loss: 0.13157230615615845
2023-01-23 02:15:30.546831: step: 384/529, loss: 0.013043022714555264
2023-01-23 02:15:31.712562: step: 388/529, loss: 0.3139774203300476
2023-01-23 02:15:32.910919: step: 392/529, loss: 0.010184002108871937
2023-01-23 02:15:34.101876: step: 396/529, loss: 0.06964874267578125
2023-01-23 02:15:35.301913: step: 400/529, loss: 0.021155167371034622
2023-01-23 02:15:36.502470: step: 404/529, loss: 0.014400673098862171
2023-01-23 02:15:37.711773: step: 408/529, loss: 0.008025742135941982
2023-01-23 02:15:38.932388: step: 412/529, loss: 0.030499696731567383
2023-01-23 02:15:40.133951: step: 416/529, loss: 0.03894786909222603
2023-01-23 02:15:41.311885: step: 420/529, loss: 0.00033605098724365234
2023-01-23 02:15:42.498626: step: 424/529, loss: 0.0067351339384913445
2023-01-23 02:15:43.709152: step: 428/529, loss: 0.013858509249985218
2023-01-23 02:15:44.934826: step: 432/529, loss: 5.1021575927734375e-05
2023-01-23 02:15:46.124678: step: 436/529, loss: 0.0002719878975767642
2023-01-23 02:15:47.312220: step: 440/529, loss: 0.0006118774181231856
2023-01-23 02:15:48.497714: step: 444/529, loss: 0.017720509320497513
2023-01-23 02:15:49.671539: step: 448/529, loss: 0.0334598533809185
2023-01-23 02:15:50.845778: step: 452/529, loss: 0.017281150445342064
2023-01-23 02:15:52.069121: step: 456/529, loss: 0.0006261348607949913
2023-01-23 02:15:53.316458: step: 460/529, loss: 0.04263028874993324
2023-01-23 02:15:54.522283: step: 464/529, loss: 0.06358852237462997
2023-01-23 02:15:55.730880: step: 468/529, loss: 0.004293775651603937
2023-01-23 02:15:56.956346: step: 472/529, loss: 0.011333084665238857
2023-01-23 02:15:58.192394: step: 476/529, loss: 0.0314447395503521
2023-01-23 02:15:59.396119: step: 480/529, loss: 0.009497452527284622
2023-01-23 02:16:00.577928: step: 484/529, loss: 0.004403853323310614
2023-01-23 02:16:01.805308: step: 488/529, loss: 0.024588823318481445
2023-01-23 02:16:02.996831: step: 492/529, loss: 0.000617599522229284
2023-01-23 02:16:04.198027: step: 496/529, loss: 0.028503989800810814
2023-01-23 02:16:05.402549: step: 500/529, loss: 0.025380326434969902
2023-01-23 02:16:06.687844: step: 504/529, loss: 0.04590282589197159
2023-01-23 02:16:07.891643: step: 508/529, loss: 0.005432748701423407
2023-01-23 02:16:09.042859: step: 512/529, loss: 0.007571840658783913
2023-01-23 02:16:10.234235: step: 516/529, loss: 0.002200651215389371
2023-01-23 02:16:11.489589: step: 520/529, loss: 0.10663548111915588
2023-01-23 02:16:12.706273: step: 524/529, loss: 0.00011873245239257812
2023-01-23 02:16:13.904068: step: 528/529, loss: 0.0043000816367566586
2023-01-23 02:16:15.097623: step: 532/529, loss: 0.013962030410766602
2023-01-23 02:16:16.302720: step: 536/529, loss: 0.03724203258752823
2023-01-23 02:16:17.482331: step: 540/529, loss: 0.01220398023724556
2023-01-23 02:16:18.703502: step: 544/529, loss: 0.00094013218767941
2023-01-23 02:16:19.888414: step: 548/529, loss: 0.11208763718605042
2023-01-23 02:16:21.116504: step: 552/529, loss: 0.00269584683701396
2023-01-23 02:16:22.321859: step: 556/529, loss: 0.008362388238310814
2023-01-23 02:16:23.459317: step: 560/529, loss: 7.03811674611643e-05
2023-01-23 02:16:24.620570: step: 564/529, loss: 0.02459421195089817
2023-01-23 02:16:25.837815: step: 568/529, loss: 0.0016084671951830387
2023-01-23 02:16:27.069532: step: 572/529, loss: 0.00010249615297652781
2023-01-23 02:16:28.279185: step: 576/529, loss: 0.003461170243099332
2023-01-23 02:16:29.474816: step: 580/529, loss: 0.0967632308602333
2023-01-23 02:16:30.669988: step: 584/529, loss: 0.004319381900131702
2023-01-23 02:16:31.901703: step: 588/529, loss: 0.17025050520896912
2023-01-23 02:16:33.074982: step: 592/529, loss: 0.02927989885210991
2023-01-23 02:16:34.270610: step: 596/529, loss: 0.010028552263975143
2023-01-23 02:16:35.459495: step: 600/529, loss: 0.0898953527212143
2023-01-23 02:16:36.639987: step: 604/529, loss: 0.0050258636474609375
2023-01-23 02:16:37.850931: step: 608/529, loss: 0.007094001863151789
2023-01-23 02:16:39.047609: step: 612/529, loss: 0.014985848218202591
2023-01-23 02:16:40.219656: step: 616/529, loss: 0.005885475780814886
2023-01-23 02:16:41.429052: step: 620/529, loss: 0.07012100517749786
2023-01-23 02:16:42.601447: step: 624/529, loss: 0.0042441366240382195
2023-01-23 02:16:43.794710: step: 628/529, loss: 0.007571220397949219
2023-01-23 02:16:44.956943: step: 632/529, loss: 0.007518816273659468
2023-01-23 02:16:46.150497: step: 636/529, loss: 0.01237402018159628
2023-01-23 02:16:47.356790: step: 640/529, loss: 0.004335212521255016
2023-01-23 02:16:48.589762: step: 644/529, loss: 0.012503623962402344
2023-01-23 02:16:49.765880: step: 648/529, loss: 1.3706327676773071
2023-01-23 02:16:50.940747: step: 652/529, loss: 0.07127085328102112
2023-01-23 02:16:52.112008: step: 656/529, loss: 0.004528427496552467
2023-01-23 02:16:53.308916: step: 660/529, loss: 0.0044953348115086555
2023-01-23 02:16:54.467057: step: 664/529, loss: 0.017867375165224075
2023-01-23 02:16:55.703680: step: 668/529, loss: 0.00947660207748413
2023-01-23 02:16:56.914636: step: 672/529, loss: 0.0017441869713366032
2023-01-23 02:16:58.135630: step: 676/529, loss: 0.00891189556568861
2023-01-23 02:16:59.345975: step: 680/529, loss: 0.05151014402508736
2023-01-23 02:17:00.570050: step: 684/529, loss: 0.06192026287317276
2023-01-23 02:17:01.771666: step: 688/529, loss: 0.015614127740263939
2023-01-23 02:17:02.947998: step: 692/529, loss: 0.00044994353083893657
2023-01-23 02:17:04.166506: step: 696/529, loss: 0.02568059042096138
2023-01-23 02:17:05.392645: step: 700/529, loss: 0.012043857015669346
2023-01-23 02:17:06.591484: step: 704/529, loss: 0.00026807785616256297
2023-01-23 02:17:07.771868: step: 708/529, loss: 0.0009771824115887284
2023-01-23 02:17:09.003324: step: 712/529, loss: 0.001566219376400113
2023-01-23 02:17:10.179300: step: 716/529, loss: 0.026256466284394264
2023-01-23 02:17:11.386336: step: 720/529, loss: 0.05051736906170845
2023-01-23 02:17:12.589920: step: 724/529, loss: 0.034284114837646484
2023-01-23 02:17:13.811744: step: 728/529, loss: 0.04318294674158096
2023-01-23 02:17:15.010281: step: 732/529, loss: 0.0006236076587811112
2023-01-23 02:17:16.191150: step: 736/529, loss: 0.0037344933953136206
2023-01-23 02:17:17.374739: step: 740/529, loss: 0.021323634311556816
2023-01-23 02:17:18.538960: step: 744/529, loss: 0.1035049706697464
2023-01-23 02:17:19.800027: step: 748/529, loss: 0.0002919197140727192
2023-01-23 02:17:20.988439: step: 752/529, loss: 0.0005622864118777215
2023-01-23 02:17:22.170960: step: 756/529, loss: 0.12760527431964874
2023-01-23 02:17:23.367537: step: 760/529, loss: 0.0017379760975018144
2023-01-23 02:17:24.597572: step: 764/529, loss: 0.04026851803064346
2023-01-23 02:17:25.833983: step: 768/529, loss: 0.04715137928724289
2023-01-23 02:17:27.013650: step: 772/529, loss: 0.042139194905757904
2023-01-23 02:17:28.246092: step: 776/529, loss: 0.046198081225156784
2023-01-23 02:17:29.428508: step: 780/529, loss: 0.015376472845673561
2023-01-23 02:17:30.672546: step: 784/529, loss: 0.49414387345314026
2023-01-23 02:17:31.862971: step: 788/529, loss: 0.04853539541363716
2023-01-23 02:17:33.024670: step: 792/529, loss: 0.001589059829711914
2023-01-23 02:17:34.197686: step: 796/529, loss: 0.014024067670106888
2023-01-23 02:17:35.376662: step: 800/529, loss: 0.02421126328408718
2023-01-23 02:17:36.549904: step: 804/529, loss: 0.02999694272875786
2023-01-23 02:17:37.820606: step: 808/529, loss: 0.01574125327169895
2023-01-23 02:17:39.012326: step: 812/529, loss: 0.000994777656160295
2023-01-23 02:17:40.303016: step: 816/529, loss: 0.006306457333266735
2023-01-23 02:17:41.526070: step: 820/529, loss: 0.00876693706959486
2023-01-23 02:17:42.709662: step: 824/529, loss: 0.04562978819012642
2023-01-23 02:17:43.920266: step: 828/529, loss: 0.01352615375071764
2023-01-23 02:17:45.080317: step: 832/529, loss: 0.011071777902543545
2023-01-23 02:17:46.258303: step: 836/529, loss: 0.0028502466157078743
2023-01-23 02:17:47.461616: step: 840/529, loss: 0.007470130920410156
2023-01-23 02:17:48.649387: step: 844/529, loss: 0.03695087134838104
2023-01-23 02:17:49.816485: step: 848/529, loss: 0.040552519261837006
2023-01-23 02:17:51.044696: step: 852/529, loss: 0.006839561276137829
2023-01-23 02:17:52.227653: step: 856/529, loss: 0.025505127385258675
2023-01-23 02:17:53.482295: step: 860/529, loss: 0.01203093584626913
2023-01-23 02:17:54.676034: step: 864/529, loss: 0.031674861907958984
2023-01-23 02:17:55.850031: step: 868/529, loss: 0.015520190820097923
2023-01-23 02:17:57.078858: step: 872/529, loss: 0.0310027115046978
2023-01-23 02:17:58.271565: step: 876/529, loss: 0.028268050402402878
2023-01-23 02:17:59.480511: step: 880/529, loss: 0.017487049102783203
2023-01-23 02:18:00.675133: step: 884/529, loss: 0.022662067785859108
2023-01-23 02:18:01.888212: step: 888/529, loss: 0.0008187294006347656
2023-01-23 02:18:03.084092: step: 892/529, loss: 0.006766903679817915
2023-01-23 02:18:04.263507: step: 896/529, loss: 0.06830596923828125
2023-01-23 02:18:05.476165: step: 900/529, loss: 0.05154714733362198
2023-01-23 02:18:06.673221: step: 904/529, loss: 0.020001031458377838
2023-01-23 02:18:07.898141: step: 908/529, loss: 0.009759045206010342
2023-01-23 02:18:09.132380: step: 912/529, loss: 0.02165517769753933
2023-01-23 02:18:10.347052: step: 916/529, loss: 0.11270676553249359
2023-01-23 02:18:11.536856: step: 920/529, loss: 0.024031830951571465
2023-01-23 02:18:12.765861: step: 924/529, loss: 0.018333053216338158
2023-01-23 02:18:13.953943: step: 928/529, loss: 0.02349414862692356
2023-01-23 02:18:15.233127: step: 932/529, loss: 0.0009970664978027344
2023-01-23 02:18:16.405155: step: 936/529, loss: 0.013111591339111328
2023-01-23 02:18:17.596860: step: 940/529, loss: 0.002722835633903742
2023-01-23 02:18:18.804537: step: 944/529, loss: 0.08323125541210175
2023-01-23 02:18:20.023343: step: 948/529, loss: 0.11373920738697052
2023-01-23 02:18:21.195517: step: 952/529, loss: 0.03552971035242081
2023-01-23 02:18:22.422905: step: 956/529, loss: 0.00485689053311944
2023-01-23 02:18:23.632541: step: 960/529, loss: 0.017791032791137695
2023-01-23 02:18:24.825572: step: 964/529, loss: 0.03160820156335831
2023-01-23 02:18:26.062372: step: 968/529, loss: 0.0551326759159565
2023-01-23 02:18:27.252732: step: 972/529, loss: 0.072378970682621
2023-01-23 02:18:28.433107: step: 976/529, loss: 0.009146403521299362
2023-01-23 02:18:29.594859: step: 980/529, loss: 0.014388322830200195
2023-01-23 02:18:30.785925: step: 984/529, loss: 0.0001085281401174143
2023-01-23 02:18:31.978001: step: 988/529, loss: 0.0009907246567308903
2023-01-23 02:18:33.186629: step: 992/529, loss: 0.022311020642518997
2023-01-23 02:18:34.368030: step: 996/529, loss: 0.04650535807013512
2023-01-23 02:18:35.563871: step: 1000/529, loss: 0.0392637737095356
2023-01-23 02:18:36.807059: step: 1004/529, loss: 0.13808879256248474
2023-01-23 02:18:37.974109: step: 1008/529, loss: 0.0325559638440609
2023-01-23 02:18:39.148858: step: 1012/529, loss: 0.003709411481395364
2023-01-23 02:18:40.390465: step: 1016/529, loss: 0.0242327693849802
2023-01-23 02:18:41.581191: step: 1020/529, loss: 0.009673071093857288
2023-01-23 02:18:42.783586: step: 1024/529, loss: 0.012622070498764515
2023-01-23 02:18:43.937051: step: 1028/529, loss: 0.01915273815393448
2023-01-23 02:18:45.191199: step: 1032/529, loss: 0.032759569585323334
2023-01-23 02:18:46.390922: step: 1036/529, loss: 0.05134544521570206
2023-01-23 02:18:47.589507: step: 1040/529, loss: 0.04553031921386719
2023-01-23 02:18:48.775950: step: 1044/529, loss: 0.02095937728881836
2023-01-23 02:18:49.959144: step: 1048/529, loss: 0.0012256145710125566
2023-01-23 02:18:51.155148: step: 1052/529, loss: 0.036905381828546524
2023-01-23 02:18:52.330236: step: 1056/529, loss: 0.00185565953142941
2023-01-23 02:18:53.518994: step: 1060/529, loss: 0.012190436944365501
2023-01-23 02:18:54.742296: step: 1064/529, loss: 0.11687707901000977
2023-01-23 02:18:55.937782: step: 1068/529, loss: 0.010545921511948109
2023-01-23 02:18:57.119452: step: 1072/529, loss: 0.017496777698397636
2023-01-23 02:18:58.262319: step: 1076/529, loss: 0.026461221277713776
2023-01-23 02:18:59.472322: step: 1080/529, loss: 0.0037640570662915707
2023-01-23 02:19:00.669746: step: 1084/529, loss: 0.07564334571361542
2023-01-23 02:19:01.878361: step: 1088/529, loss: 0.0267194751650095
2023-01-23 02:19:03.118731: step: 1092/529, loss: 0.013687754049897194
2023-01-23 02:19:04.294846: step: 1096/529, loss: 0.0001232624053955078
2023-01-23 02:19:05.481421: step: 1100/529, loss: 0.005167103372514248
2023-01-23 02:19:06.697509: step: 1104/529, loss: 0.030566884204745293
2023-01-23 02:19:07.871594: step: 1108/529, loss: 0.006701088044792414
2023-01-23 02:19:09.081152: step: 1112/529, loss: 0.03737516701221466
2023-01-23 02:19:10.268701: step: 1116/529, loss: 0.0008534193621017039
2023-01-23 02:19:11.469522: step: 1120/529, loss: 0.01563892513513565
2023-01-23 02:19:12.654322: step: 1124/529, loss: 0.04441662132740021
2023-01-23 02:19:13.824143: step: 1128/529, loss: 0.004844713024795055
2023-01-23 02:19:15.040234: step: 1132/529, loss: 0.07932376861572266
2023-01-23 02:19:16.264742: step: 1136/529, loss: 0.0013658523093909025
2023-01-23 02:19:17.476615: step: 1140/529, loss: 0.0016350746154785156
2023-01-23 02:19:18.673699: step: 1144/529, loss: 0.005328559782356024
2023-01-23 02:19:19.897064: step: 1148/529, loss: 0.06714649498462677
2023-01-23 02:19:21.078625: step: 1152/529, loss: 0.0002677917364053428
2023-01-23 02:19:22.253133: step: 1156/529, loss: 0.06665830314159393
2023-01-23 02:19:23.460623: step: 1160/529, loss: 0.02783813513815403
2023-01-23 02:19:24.652741: step: 1164/529, loss: 0.0013402937911450863
2023-01-23 02:19:25.836560: step: 1168/529, loss: 0.04208948835730553
2023-01-23 02:19:27.030170: step: 1172/529, loss: 1.7547608877066523e-05
2023-01-23 02:19:28.231434: step: 1176/529, loss: 0.12692709267139435
2023-01-23 02:19:29.413615: step: 1180/529, loss: 0.48442211747169495
2023-01-23 02:19:30.621876: step: 1184/529, loss: 0.0024298669304698706
2023-01-23 02:19:31.887489: step: 1188/529, loss: 0.003436184022575617
2023-01-23 02:19:33.096796: step: 1192/529, loss: 0.003067588899284601
2023-01-23 02:19:34.317500: step: 1196/529, loss: 0.00865182839334011
2023-01-23 02:19:35.548856: step: 1200/529, loss: 0.016780853271484375
2023-01-23 02:19:36.775524: step: 1204/529, loss: 0.0481531135737896
2023-01-23 02:19:37.956856: step: 1208/529, loss: 0.007971477694809437
2023-01-23 02:19:39.142373: step: 1212/529, loss: 0.004215812310576439
2023-01-23 02:19:40.314962: step: 1216/529, loss: 0.004649353213608265
2023-01-23 02:19:41.472128: step: 1220/529, loss: 0.004528045654296875
2023-01-23 02:19:42.673764: step: 1224/529, loss: 0.0052315713837742805
2023-01-23 02:19:43.926660: step: 1228/529, loss: 0.01217193715274334
2023-01-23 02:19:45.143558: step: 1232/529, loss: 0.004373741336166859
2023-01-23 02:19:46.309124: step: 1236/529, loss: 0.006182289216667414
2023-01-23 02:19:47.469048: step: 1240/529, loss: 0.00027313234750181437
2023-01-23 02:19:48.658980: step: 1244/529, loss: 0.0034875872079283
2023-01-23 02:19:49.839607: step: 1248/529, loss: 0.2646411955356598
2023-01-23 02:19:51.059446: step: 1252/529, loss: 0.002607727190479636
2023-01-23 02:19:52.284921: step: 1256/529, loss: 0.7531660199165344
2023-01-23 02:19:53.455734: step: 1260/529, loss: 0.03487901762127876
2023-01-23 02:19:54.652117: step: 1264/529, loss: 0.03135108947753906
2023-01-23 02:19:55.890669: step: 1268/529, loss: 0.004093504045158625
2023-01-23 02:19:57.118002: step: 1272/529, loss: 0.0968753769993782
2023-01-23 02:19:58.313007: step: 1276/529, loss: 0.0015981674659997225
2023-01-23 02:19:59.530183: step: 1280/529, loss: 0.00389785785228014
2023-01-23 02:20:00.819255: step: 1284/529, loss: 0.07193365693092346
2023-01-23 02:20:02.037563: step: 1288/529, loss: 0.022795582190155983
2023-01-23 02:20:03.223784: step: 1292/529, loss: 1.197209358215332
2023-01-23 02:20:04.417762: step: 1296/529, loss: 0.02820768393576145
2023-01-23 02:20:05.583218: step: 1300/529, loss: 0.017236996442079544
2023-01-23 02:20:06.743594: step: 1304/529, loss: 0.008360767737030983
2023-01-23 02:20:07.947046: step: 1308/529, loss: 0.033712100237607956
2023-01-23 02:20:09.187567: step: 1312/529, loss: 0.022310351952910423
2023-01-23 02:20:10.387769: step: 1316/529, loss: 0.002975940704345703
2023-01-23 02:20:11.574658: step: 1320/529, loss: 0.007573175244033337
2023-01-23 02:20:12.753812: step: 1324/529, loss: 0.020482826977968216
2023-01-23 02:20:13.937835: step: 1328/529, loss: 0.0724654346704483
2023-01-23 02:20:15.107241: step: 1332/529, loss: 0.0022208928130567074
2023-01-23 02:20:16.286279: step: 1336/529, loss: 0.008019829168915749
2023-01-23 02:20:17.504604: step: 1340/529, loss: 0.01813511922955513
2023-01-23 02:20:18.666684: step: 1344/529, loss: 0.004330349154770374
2023-01-23 02:20:19.847410: step: 1348/529, loss: 0.06065215915441513
2023-01-23 02:20:21.054916: step: 1352/529, loss: 0.004653835669159889
2023-01-23 02:20:22.247072: step: 1356/529, loss: 0.023238133639097214
2023-01-23 02:20:23.477453: step: 1360/529, loss: 0.0682673454284668
2023-01-23 02:20:24.656102: step: 1364/529, loss: 0.006237936206161976
2023-01-23 02:20:25.891976: step: 1368/529, loss: 0.03821459040045738
2023-01-23 02:20:27.091562: step: 1372/529, loss: 0.006769227795302868
2023-01-23 02:20:28.295932: step: 1376/529, loss: 0.05889396741986275
2023-01-23 02:20:29.485164: step: 1380/529, loss: 0.0033165933564305305
2023-01-23 02:20:30.687174: step: 1384/529, loss: 0.03815498203039169
2023-01-23 02:20:31.899106: step: 1388/529, loss: 0.006605911068618298
2023-01-23 02:20:33.063286: step: 1392/529, loss: 0.005694007966667414
2023-01-23 02:20:34.196753: step: 1396/529, loss: 0.00038361549377441406
2023-01-23 02:20:35.343586: step: 1400/529, loss: 0.0003912925603799522
2023-01-23 02:20:36.563236: step: 1404/529, loss: 0.015763377770781517
2023-01-23 02:20:37.714514: step: 1408/529, loss: 0.06012139469385147
2023-01-23 02:20:38.950407: step: 1412/529, loss: 0.004133415408432484
2023-01-23 02:20:40.159232: step: 1416/529, loss: 0.041353560984134674
2023-01-23 02:20:41.323532: step: 1420/529, loss: 0.017238235101103783
2023-01-23 02:20:42.519928: step: 1424/529, loss: 0.044570159167051315
2023-01-23 02:20:43.747614: step: 1428/529, loss: 0.0005863189580850303
2023-01-23 02:20:44.920188: step: 1432/529, loss: 0.01669340208172798
2023-01-23 02:20:46.118235: step: 1436/529, loss: 0.007371616084128618
2023-01-23 02:20:47.317271: step: 1440/529, loss: 0.028499890118837357
2023-01-23 02:20:48.513203: step: 1444/529, loss: 0.04242124781012535
2023-01-23 02:20:49.681873: step: 1448/529, loss: 0.0008799553033895791
2023-01-23 02:20:50.885342: step: 1452/529, loss: 0.023804377764463425
2023-01-23 02:20:52.075441: step: 1456/529, loss: 0.00970306433737278
2023-01-23 02:20:53.215691: step: 1460/529, loss: 0.06566095352172852
2023-01-23 02:20:54.380097: step: 1464/529, loss: 0.026435375213623047
2023-01-23 02:20:55.592712: step: 1468/529, loss: 0.006897640414535999
2023-01-23 02:20:56.771385: step: 1472/529, loss: 0.038277819752693176
2023-01-23 02:20:57.986029: step: 1476/529, loss: 0.033819008618593216
2023-01-23 02:20:59.209539: step: 1480/529, loss: 0.03408203274011612
2023-01-23 02:21:00.427286: step: 1484/529, loss: 0.041475772857666016
2023-01-23 02:21:01.593002: step: 1488/529, loss: 0.133219912648201
2023-01-23 02:21:02.834316: step: 1492/529, loss: 0.018799876794219017
2023-01-23 02:21:04.035850: step: 1496/529, loss: 0.044335030019283295
2023-01-23 02:21:05.200664: step: 1500/529, loss: 0.02014923095703125
2023-01-23 02:21:06.412572: step: 1504/529, loss: 0.08037119358778
2023-01-23 02:21:07.629197: step: 1508/529, loss: 1.0089977979660034
2023-01-23 02:21:08.828292: step: 1512/529, loss: 0.046825215220451355
2023-01-23 02:21:10.040339: step: 1516/529, loss: 0.020081140100955963
2023-01-23 02:21:11.250841: step: 1520/529, loss: 0.042453862726688385
2023-01-23 02:21:12.440323: step: 1524/529, loss: 0.024216270074248314
2023-01-23 02:21:13.620740: step: 1528/529, loss: 0.05180168151855469
2023-01-23 02:21:14.857323: step: 1532/529, loss: 0.041919708251953125
2023-01-23 02:21:16.098867: step: 1536/529, loss: 0.017532825469970703
2023-01-23 02:21:17.298539: step: 1540/529, loss: 0.018871881067752838
2023-01-23 02:21:18.501803: step: 1544/529, loss: 0.012684965506196022
2023-01-23 02:21:19.713792: step: 1548/529, loss: 0.06335287541151047
2023-01-23 02:21:20.927505: step: 1552/529, loss: 0.007520914543420076
2023-01-23 02:21:22.121438: step: 1556/529, loss: 0.0012094497215002775
2023-01-23 02:21:23.319393: step: 1560/529, loss: 0.005062485113739967
2023-01-23 02:21:24.533003: step: 1564/529, loss: 0.0018834115471690893
2023-01-23 02:21:25.720817: step: 1568/529, loss: 0.039183810353279114
2023-01-23 02:21:26.932271: step: 1572/529, loss: 0.006548118777573109
2023-01-23 02:21:28.127642: step: 1576/529, loss: 0.04161491245031357
2023-01-23 02:21:29.340759: step: 1580/529, loss: 0.06325483322143555
2023-01-23 02:21:30.560788: step: 1584/529, loss: 0.13219738006591797
2023-01-23 02:21:31.753646: step: 1588/529, loss: 0.04285898432135582
2023-01-23 02:21:32.963819: step: 1592/529, loss: 0.005718231201171875
2023-01-23 02:21:34.155274: step: 1596/529, loss: 0.0009244919056072831
2023-01-23 02:21:35.311491: step: 1600/529, loss: 0.0001794815034372732
2023-01-23 02:21:36.543589: step: 1604/529, loss: 0.01938762702047825
2023-01-23 02:21:37.711957: step: 1608/529, loss: 0.00012264252291060984
2023-01-23 02:21:38.944589: step: 1612/529, loss: 0.0076004983857274055
2023-01-23 02:21:40.132745: step: 1616/529, loss: 0.008213996887207031
2023-01-23 02:21:41.325974: step: 1620/529, loss: 0.03521881252527237
2023-01-23 02:21:42.514976: step: 1624/529, loss: 0.05723857879638672
2023-01-23 02:21:43.686833: step: 1628/529, loss: 0.0016631126636639237
2023-01-23 02:21:44.864302: step: 1632/529, loss: 0.002435874892398715
2023-01-23 02:21:46.064340: step: 1636/529, loss: 0.0012926101917400956
2023-01-23 02:21:47.280547: step: 1640/529, loss: 0.20914383232593536
2023-01-23 02:21:48.520044: step: 1644/529, loss: 0.00137414934579283
2023-01-23 02:21:49.750650: step: 1648/529, loss: 0.11086144298315048
2023-01-23 02:21:51.004556: step: 1652/529, loss: 0.021106624975800514
2023-01-23 02:21:52.211227: step: 1656/529, loss: 0.07170820981264114
2023-01-23 02:21:53.397142: step: 1660/529, loss: 0.027965163812041283
2023-01-23 02:21:54.578721: step: 1664/529, loss: 0.011815452948212624
2023-01-23 02:21:55.753802: step: 1668/529, loss: 0.0005886077997274697
2023-01-23 02:21:56.967499: step: 1672/529, loss: 0.028856562450528145
2023-01-23 02:21:58.184572: step: 1676/529, loss: 0.036635592579841614
2023-01-23 02:21:59.368538: step: 1680/529, loss: 0.011177443899214268
2023-01-23 02:22:00.550991: step: 1684/529, loss: 0.015666676685214043
2023-01-23 02:22:01.754219: step: 1688/529, loss: 0.011370849795639515
2023-01-23 02:22:02.927445: step: 1692/529, loss: 0.029594993218779564
2023-01-23 02:22:04.104375: step: 1696/529, loss: 6.642795562744141
2023-01-23 02:22:05.337697: step: 1700/529, loss: 1.9073486328125e-06
2023-01-23 02:22:06.521374: step: 1704/529, loss: 0.0684257447719574
2023-01-23 02:22:07.733544: step: 1708/529, loss: 0.006921291351318359
2023-01-23 02:22:08.937740: step: 1712/529, loss: 0.0013270378112792969
2023-01-23 02:22:10.154818: step: 1716/529, loss: 0.00669174175709486
2023-01-23 02:22:11.342664: step: 1720/529, loss: 0.021431589499115944
2023-01-23 02:22:12.612332: step: 1724/529, loss: 0.056902315467596054
2023-01-23 02:22:13.823784: step: 1728/529, loss: 0.015398931689560413
2023-01-23 02:22:15.005024: step: 1732/529, loss: 0.05008867010474205
2023-01-23 02:22:16.173113: step: 1736/529, loss: 0.0014361381763592362
2023-01-23 02:22:17.345020: step: 1740/529, loss: 0.002488803816959262
2023-01-23 02:22:18.536988: step: 1744/529, loss: 0.0064025879837572575
2023-01-23 02:22:19.762575: step: 1748/529, loss: 0.002174949739128351
2023-01-23 02:22:20.976767: step: 1752/529, loss: 0.054010674357414246
2023-01-23 02:22:22.190836: step: 1756/529, loss: 0.01879558525979519
2023-01-23 02:22:23.372146: step: 1760/529, loss: 0.040892407298088074
2023-01-23 02:22:24.561056: step: 1764/529, loss: 0.015877151861786842
2023-01-23 02:22:25.768055: step: 1768/529, loss: 0.0018224716186523438
2023-01-23 02:22:26.991570: step: 1772/529, loss: 0.024832725524902344
2023-01-23 02:22:28.214645: step: 1776/529, loss: 0.010940122418105602
2023-01-23 02:22:29.386337: step: 1780/529, loss: 0.007358360569924116
2023-01-23 02:22:30.610567: step: 1784/529, loss: 0.03130703046917915
2023-01-23 02:22:31.820002: step: 1788/529, loss: 0.004744672682136297
2023-01-23 02:22:33.101442: step: 1792/529, loss: 0.0041048284620046616
2023-01-23 02:22:34.294606: step: 1796/529, loss: 0.011958122253417969
2023-01-23 02:22:35.531898: step: 1800/529, loss: 0.00035005214158445597
2023-01-23 02:22:36.758629: step: 1804/529, loss: 0.06836128234863281
2023-01-23 02:22:37.942921: step: 1808/529, loss: 0.01869945414364338
2023-01-23 02:22:39.120610: step: 1812/529, loss: 0.0030375481583178043
2023-01-23 02:22:40.338695: step: 1816/529, loss: 0.029547788202762604
2023-01-23 02:22:41.568678: step: 1820/529, loss: 0.014499188400804996
2023-01-23 02:22:42.774548: step: 1824/529, loss: 0.08833573758602142
2023-01-23 02:22:43.954447: step: 1828/529, loss: 0.23115572333335876
2023-01-23 02:22:45.156322: step: 1832/529, loss: 0.002206707140430808
2023-01-23 02:22:46.377172: step: 1836/529, loss: 0.015276908874511719
2023-01-23 02:22:47.626342: step: 1840/529, loss: 0.03730583190917969
2023-01-23 02:22:48.859576: step: 1844/529, loss: 0.0075813294388353825
2023-01-23 02:22:50.012359: step: 1848/529, loss: 0.028373051434755325
2023-01-23 02:22:51.192734: step: 1852/529, loss: 0.8360044360160828
2023-01-23 02:22:52.361981: step: 1856/529, loss: 0.03366518020629883
2023-01-23 02:22:53.555469: step: 1860/529, loss: 0.24306488037109375
2023-01-23 02:22:54.792380: step: 1864/529, loss: 0.005439949221909046
2023-01-23 02:22:56.035587: step: 1868/529, loss: 0.043221186846494675
2023-01-23 02:22:57.256587: step: 1872/529, loss: 0.005711936857551336
2023-01-23 02:22:58.460971: step: 1876/529, loss: 0.003545427229255438
2023-01-23 02:22:59.645200: step: 1880/529, loss: 0.045832060277462006
2023-01-23 02:23:00.861885: step: 1884/529, loss: 0.08937826752662659
2023-01-23 02:23:02.035070: step: 1888/529, loss: 0.01433253288269043
2023-01-23 02:23:03.233810: step: 1892/529, loss: 0.0729837417602539
2023-01-23 02:23:04.470845: step: 1896/529, loss: 0.00558319129049778
2023-01-23 02:23:05.702872: step: 1900/529, loss: 0.005814933683723211
2023-01-23 02:23:06.907229: step: 1904/529, loss: 0.004852867219597101
2023-01-23 02:23:08.071591: step: 1908/529, loss: 0.002795314881950617
2023-01-23 02:23:09.266922: step: 1912/529, loss: 0.18903236091136932
2023-01-23 02:23:10.452382: step: 1916/529, loss: 0.0008465528371743858
2023-01-23 02:23:11.610422: step: 1920/529, loss: 0.018373871222138405
2023-01-23 02:23:12.793391: step: 1924/529, loss: 0.00037751198397018015
2023-01-23 02:23:13.990448: step: 1928/529, loss: 0.04945354908704758
2023-01-23 02:23:15.275175: step: 1932/529, loss: 0.0007461548084393144
2023-01-23 02:23:16.467983: step: 1936/529, loss: 0.06285524368286133
2023-01-23 02:23:17.639329: step: 1940/529, loss: 0.023958398029208183
2023-01-23 02:23:18.852276: step: 1944/529, loss: 0.023633766919374466
2023-01-23 02:23:20.052536: step: 1948/529, loss: 0.00016717911057639867
2023-01-23 02:23:21.278853: step: 1952/529, loss: 0.005665207281708717
2023-01-23 02:23:22.444233: step: 1956/529, loss: 0.01394033432006836
2023-01-23 02:23:23.680861: step: 1960/529, loss: 0.002126026200130582
2023-01-23 02:23:24.910279: step: 1964/529, loss: 0.008430815301835537
2023-01-23 02:23:26.160734: step: 1968/529, loss: 0.014192390255630016
2023-01-23 02:23:27.336816: step: 1972/529, loss: 0.0002094268857035786
2023-01-23 02:23:28.559846: step: 1976/529, loss: 0.06872482597827911
2023-01-23 02:23:29.786900: step: 1980/529, loss: 0.009262656792998314
2023-01-23 02:23:30.998079: step: 1984/529, loss: 0.034957073628902435
2023-01-23 02:23:32.202211: step: 1988/529, loss: 0.017655039206147194
2023-01-23 02:23:33.390944: step: 1992/529, loss: 0.015191060490906239
2023-01-23 02:23:34.589962: step: 1996/529, loss: 0.022785378620028496
2023-01-23 02:23:35.815829: step: 2000/529, loss: 0.037732984870672226
2023-01-23 02:23:37.033854: step: 2004/529, loss: 0.017534922808408737
2023-01-23 02:23:38.247433: step: 2008/529, loss: 0.0014892579056322575
2023-01-23 02:23:39.496018: step: 2012/529, loss: 0.09685364365577698
2023-01-23 02:23:40.696310: step: 2016/529, loss: 0.005210495088249445
2023-01-23 02:23:41.918210: step: 2020/529, loss: 0.004749489016830921
2023-01-23 02:23:43.157020: step: 2024/529, loss: 0.012339066714048386
2023-01-23 02:23:44.357850: step: 2028/529, loss: 6.151199340820312e-05
2023-01-23 02:23:45.528322: step: 2032/529, loss: 0.03139953687787056
2023-01-23 02:23:46.721601: step: 2036/529, loss: 0.023186493664979935
2023-01-23 02:23:47.891571: step: 2040/529, loss: 0.022021150216460228
2023-01-23 02:23:49.098870: step: 2044/529, loss: 0.001293611596338451
2023-01-23 02:23:50.306271: step: 2048/529, loss: 0.030144404619932175
2023-01-23 02:23:51.479106: step: 2052/529, loss: 0.0006465911865234375
2023-01-23 02:23:52.669899: step: 2056/529, loss: 0.005116557702422142
2023-01-23 02:23:53.872885: step: 2060/529, loss: 0.018648911267518997
2023-01-23 02:23:55.052984: step: 2064/529, loss: 0.03609009087085724
2023-01-23 02:23:56.225585: step: 2068/529, loss: 0.002794933272525668
2023-01-23 02:23:57.377467: step: 2072/529, loss: 0.003845310304313898
2023-01-23 02:23:58.548792: step: 2076/529, loss: 0.10613413155078888
2023-01-23 02:23:59.768740: step: 2080/529, loss: 0.006571575999259949
2023-01-23 02:24:00.943702: step: 2084/529, loss: 0.0341605544090271
2023-01-23 02:24:02.155929: step: 2088/529, loss: 0.11511025577783585
2023-01-23 02:24:03.376414: step: 2092/529, loss: 0.002692603971809149
2023-01-23 02:24:04.537192: step: 2096/529, loss: 0.0010046481620520353
2023-01-23 02:24:05.691534: step: 2100/529, loss: 0.36170119047164917
2023-01-23 02:24:06.882050: step: 2104/529, loss: 0.35221290588378906
2023-01-23 02:24:08.097674: step: 2108/529, loss: 0.022685719653964043
2023-01-23 02:24:09.309797: step: 2112/529, loss: 0.02852764166891575
2023-01-23 02:24:10.482093: step: 2116/529, loss: 0.008012199774384499
==================================================
Loss: 0.053
--------------------
Dev: {'event': {'p': 0.5977249224405378, 'r': 0.7696404793608522, 'f1': 0.6728754365541327}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6421001926782274, 'r': 0.7986818454164171, 'f1': 0.7118825100133512}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5945945945945946, 'r': 0.8148148148148148, 'f1': 0.6875}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6326530612244898, 'r': 0.49206349206349204, 'f1': 0.5535714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
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': 15}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977249224405378, 'r': 0.7696404793608522, 'f1': 0.6728754365541327}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Russian: {'event': {'p': 0.6421001926782274, 'r': 0.7986818454164171, 'f1': 0.7118825100133512}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
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': 15}
******************************
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 02:25:02.978024: step: 4/529, loss: 0.01121821440756321
2023-01-23 02:25:04.147253: step: 8/529, loss: 0.009226560592651367
2023-01-23 02:25:05.325654: step: 12/529, loss: 0.0846099853515625
2023-01-23 02:25:06.547555: step: 16/529, loss: 0.012137413024902344
2023-01-23 02:25:07.733943: step: 20/529, loss: 0.012349986471235752
2023-01-23 02:25:08.900553: step: 24/529, loss: 0.0023848055861890316
2023-01-23 02:25:10.079290: step: 28/529, loss: 0.008556938730180264
2023-01-23 02:25:11.279602: step: 32/529, loss: 0.0001464843808207661
2023-01-23 02:25:12.483189: step: 36/529, loss: 0.027249909937381744
2023-01-23 02:25:13.681214: step: 40/529, loss: 0.0024625780060887337
2023-01-23 02:25:14.845289: step: 44/529, loss: 0.02579193189740181
2023-01-23 02:25:16.064915: step: 48/529, loss: 0.002651691436767578
2023-01-23 02:25:17.320881: step: 52/529, loss: 0.40329664945602417
2023-01-23 02:25:18.510558: step: 56/529, loss: 0.0604059211909771
2023-01-23 02:25:19.652326: step: 60/529, loss: 0.0022771835792809725
2023-01-23 02:25:20.844094: step: 64/529, loss: 0.004975414369255304
2023-01-23 02:25:22.077986: step: 68/529, loss: 0.0007012367132119834
2023-01-23 02:25:23.288163: step: 72/529, loss: 0.0647285208106041
2023-01-23 02:25:24.465500: step: 76/529, loss: 0.004416084382683039
2023-01-23 02:25:25.655257: step: 80/529, loss: 0.32259073853492737
2023-01-23 02:25:26.897108: step: 84/529, loss: 0.006053447723388672
2023-01-23 02:25:28.105263: step: 88/529, loss: 0.012158012948930264
2023-01-23 02:25:29.362762: step: 92/529, loss: 0.05882968753576279
2023-01-23 02:25:30.503760: step: 96/529, loss: 0.005947113502770662
2023-01-23 02:25:31.686316: step: 100/529, loss: 0.0033861161209642887
2023-01-23 02:25:32.916619: step: 104/529, loss: 0.0119476318359375
2023-01-23 02:25:34.094124: step: 108/529, loss: 0.05767965316772461
2023-01-23 02:25:35.281393: step: 112/529, loss: 0.021436691284179688
2023-01-23 02:25:36.490042: step: 116/529, loss: 0.02227325364947319
2023-01-23 02:25:37.673368: step: 120/529, loss: 0.0013520241482183337
2023-01-23 02:25:38.839432: step: 124/529, loss: 0.010037422180175781
2023-01-23 02:25:40.057340: step: 128/529, loss: 0.0115540511906147
2023-01-23 02:25:41.232432: step: 132/529, loss: 0.016535472124814987
2023-01-23 02:25:42.443569: step: 136/529, loss: 0.07580481469631195
2023-01-23 02:25:43.639006: step: 140/529, loss: 0.00099773402325809
2023-01-23 02:25:44.786964: step: 144/529, loss: 0.022234437987208366
2023-01-23 02:25:45.983574: step: 148/529, loss: 0.03079976886510849
2023-01-23 02:25:47.254987: step: 152/529, loss: 0.04285158962011337
2023-01-23 02:25:48.439362: step: 156/529, loss: 0.0010192871559411287
2023-01-23 02:25:49.634467: step: 160/529, loss: 0.012722802348434925
2023-01-23 02:25:50.801934: step: 164/529, loss: 0.00026292799157090485
2023-01-23 02:25:52.005597: step: 168/529, loss: 0.08401966094970703
2023-01-23 02:25:53.200958: step: 172/529, loss: 0.026950262486934662
2023-01-23 02:25:54.377874: step: 176/529, loss: 0.0032828333787620068
2023-01-23 02:25:55.576077: step: 180/529, loss: 0.0003248214488849044
2023-01-23 02:25:56.740945: step: 184/529, loss: 0.01965932734310627
2023-01-23 02:25:57.914415: step: 188/529, loss: 0.003544426057487726
2023-01-23 02:25:59.103137: step: 192/529, loss: 0.007383918855339289
2023-01-23 02:26:00.327342: step: 196/529, loss: 0.0006082534673623741
2023-01-23 02:26:01.490702: step: 200/529, loss: 0.0032835006713867188
2023-01-23 02:26:02.699229: step: 204/529, loss: 0.0021963119506835938
2023-01-23 02:26:03.890511: step: 208/529, loss: 0.0751006156206131
2023-01-23 02:26:05.093752: step: 212/529, loss: 0.006998253054916859
2023-01-23 02:26:06.305350: step: 216/529, loss: 0.11058690398931503
2023-01-23 02:26:07.483821: step: 220/529, loss: 0.011524009518325329
2023-01-23 02:26:08.696497: step: 224/529, loss: 0.12669506669044495
2023-01-23 02:26:09.890261: step: 228/529, loss: 0.00801916141062975
2023-01-23 02:26:11.089699: step: 232/529, loss: 0.003075027372688055
2023-01-23 02:26:12.291906: step: 236/529, loss: 0.0575687438249588
2023-01-23 02:26:13.469485: step: 240/529, loss: 0.00046362876310013235
2023-01-23 02:26:14.716457: step: 244/529, loss: 0.002476978348568082
2023-01-23 02:26:15.911401: step: 248/529, loss: 0.01172714214771986
2023-01-23 02:26:17.117902: step: 252/529, loss: 0.020298385992646217
2023-01-23 02:26:18.335183: step: 256/529, loss: 0.013495922088623047
2023-01-23 02:26:19.533076: step: 260/529, loss: 0.01186294574290514
2023-01-23 02:26:20.706392: step: 264/529, loss: 0.006715011782944202
2023-01-23 02:26:21.871578: step: 268/529, loss: 0.006658363621681929
2023-01-23 02:26:23.083456: step: 272/529, loss: 0.03999576345086098
2023-01-23 02:26:24.297265: step: 276/529, loss: 0.006159305572509766
2023-01-23 02:26:25.487052: step: 280/529, loss: 0.0008301734924316406
2023-01-23 02:26:26.722525: step: 284/529, loss: 0.005973624996840954
2023-01-23 02:26:27.912134: step: 288/529, loss: 0.019219208508729935
2023-01-23 02:26:29.073500: step: 292/529, loss: 0.0027778628282248974
2023-01-23 02:26:30.294938: step: 296/529, loss: 0.006109809968620539
2023-01-23 02:26:31.478580: step: 300/529, loss: 0.017147399485111237
2023-01-23 02:26:32.729688: step: 304/529, loss: 0.0014553070068359375
2023-01-23 02:26:33.905218: step: 308/529, loss: 0.00022627711587119848
2023-01-23 02:26:35.166272: step: 312/529, loss: 0.00605201767757535
2023-01-23 02:26:36.339563: step: 316/529, loss: 0.0034310820046812296
2023-01-23 02:26:37.548579: step: 320/529, loss: 0.022520065307617188
2023-01-23 02:26:38.716009: step: 324/529, loss: 0.6154108047485352
2023-01-23 02:26:39.908647: step: 328/529, loss: 7.524489774368703e-05
2023-01-23 02:26:41.162530: step: 332/529, loss: 7.32898770365864e-05
2023-01-23 02:26:42.348761: step: 336/529, loss: 0.004454994574189186
2023-01-23 02:26:43.530692: step: 340/529, loss: 0.0006483077886514366
2023-01-23 02:26:44.673125: step: 344/529, loss: 0.01694812811911106
2023-01-23 02:26:45.885244: step: 348/529, loss: 0.038036346435546875
2023-01-23 02:26:47.099548: step: 352/529, loss: 0.048842813819646835
2023-01-23 02:26:48.335646: step: 356/529, loss: 0.03309059143066406
2023-01-23 02:26:49.553940: step: 360/529, loss: 0.0056591033935546875
2023-01-23 02:26:50.729376: step: 364/529, loss: 0.01780109480023384
2023-01-23 02:26:51.928355: step: 368/529, loss: 0.015294170007109642
2023-01-23 02:26:53.152835: step: 372/529, loss: 0.016104508191347122
2023-01-23 02:26:54.369342: step: 376/529, loss: 0.014001751318573952
2023-01-23 02:26:55.562152: step: 380/529, loss: 0.02171015739440918
2023-01-23 02:26:56.745444: step: 384/529, loss: 0.01760873757302761
2023-01-23 02:26:57.928952: step: 388/529, loss: 0.0004352569521870464
2023-01-23 02:26:59.177575: step: 392/529, loss: 0.031203269958496094
2023-01-23 02:27:00.386662: step: 396/529, loss: 0.02887716330587864
2023-01-23 02:27:01.591558: step: 400/529, loss: 0.030919646844267845
2023-01-23 02:27:02.809682: step: 404/529, loss: 0.020296763628721237
2023-01-23 02:27:03.987105: step: 408/529, loss: 0.008166313171386719
2023-01-23 02:27:05.164388: step: 412/529, loss: 0.019211482256650925
2023-01-23 02:27:06.347737: step: 416/529, loss: 0.04082345962524414
2023-01-23 02:27:07.566610: step: 420/529, loss: 0.06339378654956818
2023-01-23 02:27:08.798509: step: 424/529, loss: 3.919601658708416e-05
2023-01-23 02:27:10.010699: step: 428/529, loss: 0.05355234444141388
2023-01-23 02:27:11.218865: step: 432/529, loss: 0.012090301141142845
2023-01-23 02:27:12.412142: step: 436/529, loss: 0.07747115939855576
2023-01-23 02:27:13.578057: step: 440/529, loss: 0.009994077496230602
2023-01-23 02:27:14.762298: step: 444/529, loss: 0.0014617920387536287
2023-01-23 02:27:15.963474: step: 448/529, loss: 5.14984130859375e-05
2023-01-23 02:27:17.151757: step: 452/529, loss: 0.0010608673328533769
2023-01-23 02:27:18.314526: step: 456/529, loss: 0.006717490963637829
2023-01-23 02:27:19.471141: step: 460/529, loss: 0.0038290023803710938
2023-01-23 02:27:20.685878: step: 464/529, loss: 0.0036141397431492805
2023-01-23 02:27:21.880146: step: 468/529, loss: 0.004974365234375
2023-01-23 02:27:23.091550: step: 472/529, loss: 0.03995056450366974
2023-01-23 02:27:24.222878: step: 476/529, loss: 0.034803010523319244
2023-01-23 02:27:25.437568: step: 480/529, loss: 0.04414510726928711
2023-01-23 02:27:26.640617: step: 484/529, loss: 0.0013128280406817794
2023-01-23 02:27:27.826072: step: 488/529, loss: 0.0024770735763013363
2023-01-23 02:27:29.011815: step: 492/529, loss: 0.0034605024848133326
2023-01-23 02:27:30.191600: step: 496/529, loss: 0.008593273349106312
2023-01-23 02:27:31.377376: step: 500/529, loss: 0.00027976036653853953
2023-01-23 02:27:32.587362: step: 504/529, loss: 0.08622293919324875
2023-01-23 02:27:33.790215: step: 508/529, loss: 0.008352423086762428
2023-01-23 02:27:35.021231: step: 512/529, loss: 0.015434456057846546
2023-01-23 02:27:36.230034: step: 516/529, loss: 0.030466269701719284
2023-01-23 02:27:37.410254: step: 520/529, loss: 0.00214729318395257
2023-01-23 02:27:38.631397: step: 524/529, loss: 0.0069138528779149055
2023-01-23 02:27:39.818361: step: 528/529, loss: 0.0016923904186114669
2023-01-23 02:27:41.049566: step: 532/529, loss: 0.0012170791160315275
2023-01-23 02:27:42.263265: step: 536/529, loss: 0.007384300697594881
2023-01-23 02:27:43.450963: step: 540/529, loss: 0.02920837327837944
2023-01-23 02:27:44.661296: step: 544/529, loss: 0.00040912628173828125
2023-01-23 02:27:45.855789: step: 548/529, loss: 0.0011096715461462736
2023-01-23 02:27:47.059528: step: 552/529, loss: 0.038210179656744
2023-01-23 02:27:48.266922: step: 556/529, loss: 0.0002511024649720639
2023-01-23 02:27:49.449889: step: 560/529, loss: 0.004841613583266735
2023-01-23 02:27:50.623216: step: 564/529, loss: 0.008134794421494007
2023-01-23 02:27:51.829535: step: 568/529, loss: 0.01677103154361248
2023-01-23 02:27:52.998614: step: 572/529, loss: 0.03830432891845703
2023-01-23 02:27:54.189303: step: 576/529, loss: 0.0004141807439737022
2023-01-23 02:27:55.454100: step: 580/529, loss: 0.006304312031716108
2023-01-23 02:27:56.665742: step: 584/529, loss: 0.07688693702220917
2023-01-23 02:27:57.926401: step: 588/529, loss: 0.07493872940540314
2023-01-23 02:27:59.119864: step: 592/529, loss: 0.021212458610534668
2023-01-23 02:28:00.338839: step: 596/529, loss: 0.040657807141542435
2023-01-23 02:28:01.544678: step: 600/529, loss: 0.029030513018369675
2023-01-23 02:28:02.785749: step: 604/529, loss: 0.015389442443847656
2023-01-23 02:28:04.003483: step: 608/529, loss: 0.0003103256458416581
2023-01-23 02:28:05.245390: step: 612/529, loss: 0.004745113663375378
2023-01-23 02:28:06.399791: step: 616/529, loss: 0.012839317321777344
2023-01-23 02:28:07.587281: step: 620/529, loss: 0.026345444843173027
2023-01-23 02:28:08.782841: step: 624/529, loss: 0.030898286029696465
2023-01-23 02:28:09.986798: step: 628/529, loss: 0.0033539296127855778
2023-01-23 02:28:11.176511: step: 632/529, loss: 0.003013992216438055
2023-01-23 02:28:12.377712: step: 636/529, loss: 0.0014978409744799137
2023-01-23 02:28:13.601604: step: 640/529, loss: 0.04772148281335831
2023-01-23 02:28:14.776328: step: 644/529, loss: 0.13713550567626953
2023-01-23 02:28:16.003006: step: 648/529, loss: 0.018921375274658203
2023-01-23 02:28:17.202051: step: 652/529, loss: 4.57763671875e-05
2023-01-23 02:28:18.401503: step: 656/529, loss: 0.0009199142223224044
2023-01-23 02:28:19.600413: step: 660/529, loss: 0.003127574920654297
2023-01-23 02:28:20.808857: step: 664/529, loss: 0.00039501191349700093
2023-01-23 02:28:22.005825: step: 668/529, loss: 0.0005623817560262978
2023-01-23 02:28:23.178554: step: 672/529, loss: 0.12925167381763458
2023-01-23 02:28:24.346585: step: 676/529, loss: 0.0006808757316321135
2023-01-23 02:28:25.480160: step: 680/529, loss: 0.012927723117172718
2023-01-23 02:28:26.664598: step: 684/529, loss: 0.0007337093120440841
2023-01-23 02:28:27.855498: step: 688/529, loss: 0.006521463394165039
2023-01-23 02:28:29.067758: step: 692/529, loss: 0.0020774840377271175
2023-01-23 02:28:30.229325: step: 696/529, loss: 0.000921058701351285
2023-01-23 02:28:31.418759: step: 700/529, loss: 0.001961231231689453
2023-01-23 02:28:32.624634: step: 704/529, loss: 0.016443252563476562
2023-01-23 02:28:33.858276: step: 708/529, loss: 0.014692497439682484
2023-01-23 02:28:35.098008: step: 712/529, loss: 0.0019512177677825093
2023-01-23 02:28:36.336802: step: 716/529, loss: 0.0249189380556345
2023-01-23 02:28:37.537668: step: 720/529, loss: 0.0023110867477953434
2023-01-23 02:28:38.817652: step: 724/529, loss: 0.04198732599616051
2023-01-23 02:28:39.995036: step: 728/529, loss: 0.02201404608786106
2023-01-23 02:28:41.229304: step: 732/529, loss: 0.009539724327623844
2023-01-23 02:28:42.411614: step: 736/529, loss: 0.007643270771950483
2023-01-23 02:28:43.607278: step: 740/529, loss: 0.0024990083184093237
2023-01-23 02:28:44.802352: step: 744/529, loss: 0.34504929184913635
2023-01-23 02:28:46.019297: step: 748/529, loss: 0.03697576746344566
2023-01-23 02:28:47.206708: step: 752/529, loss: 0.0015136718284338713
2023-01-23 02:28:48.419652: step: 756/529, loss: 0.016345692798495293
2023-01-23 02:28:49.575536: step: 760/529, loss: 0.004855346865952015
2023-01-23 02:28:50.803960: step: 764/529, loss: 0.01900806464254856
2023-01-23 02:28:51.962917: step: 768/529, loss: 0.02727355994284153
2023-01-23 02:28:53.182296: step: 772/529, loss: 0.0007274628151208162
2023-01-23 02:28:54.356560: step: 776/529, loss: 0.023694420233368874
2023-01-23 02:28:55.522000: step: 780/529, loss: 0.00031871796818450093
2023-01-23 02:28:56.698489: step: 784/529, loss: 0.04489602893590927
2023-01-23 02:28:57.914626: step: 788/529, loss: 0.057988740503787994
2023-01-23 02:28:59.120113: step: 792/529, loss: 0.004422807600349188
2023-01-23 02:29:00.299061: step: 796/529, loss: 0.025780821219086647
2023-01-23 02:29:01.477634: step: 800/529, loss: 0.02680225297808647
2023-01-23 02:29:02.688122: step: 804/529, loss: 0.005648136604577303
2023-01-23 02:29:03.843484: step: 808/529, loss: 0.011340761557221413
2023-01-23 02:29:05.041785: step: 812/529, loss: 6.45637555862777e-05
2023-01-23 02:29:06.249182: step: 816/529, loss: 0.0002510070626158267
2023-01-23 02:29:07.472272: step: 820/529, loss: 0.03329353407025337
2023-01-23 02:29:08.674589: step: 824/529, loss: 0.0010089874267578125
2023-01-23 02:29:09.840369: step: 828/529, loss: 0.0292326919734478
2023-01-23 02:29:11.097092: step: 832/529, loss: 0.0004772186221089214
2023-01-23 02:29:12.321125: step: 836/529, loss: 0.023160552605986595
2023-01-23 02:29:13.470655: step: 840/529, loss: 0.0014319419860839844
2023-01-23 02:29:14.641597: step: 844/529, loss: 0.004728889558464289
2023-01-23 02:29:15.825405: step: 848/529, loss: 0.0009454727405682206
2023-01-23 02:29:17.040443: step: 852/529, loss: 0.028275156393647194
2023-01-23 02:29:18.215327: step: 856/529, loss: 0.00031557082547806203
2023-01-23 02:29:19.411793: step: 860/529, loss: 0.0010160446399822831
2023-01-23 02:29:20.555152: step: 864/529, loss: 0.009815978817641735
2023-01-23 02:29:21.761551: step: 868/529, loss: 0.008692741394042969
2023-01-23 02:29:22.979034: step: 872/529, loss: 0.12085652351379395
2023-01-23 02:29:24.185183: step: 876/529, loss: 0.0038149834144860506
2023-01-23 02:29:25.372177: step: 880/529, loss: 0.26933154463768005
2023-01-23 02:29:26.544824: step: 884/529, loss: 0.0072152139618992805
2023-01-23 02:29:27.743845: step: 888/529, loss: 0.021677399054169655
2023-01-23 02:29:28.923601: step: 892/529, loss: 0.007256889715790749
2023-01-23 02:29:30.127964: step: 896/529, loss: 0.0056095123291015625
2023-01-23 02:29:31.367635: step: 900/529, loss: 0.0011039734818041325
2023-01-23 02:29:32.585239: step: 904/529, loss: 0.007837391458451748
2023-01-23 02:29:33.776914: step: 908/529, loss: 0.056517791002988815
2023-01-23 02:29:35.042857: step: 912/529, loss: 0.09569063782691956
2023-01-23 02:29:36.225347: step: 916/529, loss: 0.006251240149140358
2023-01-23 02:29:37.395563: step: 920/529, loss: 0.0009443163871765137
2023-01-23 02:29:38.587196: step: 924/529, loss: 0.0035196305252611637
2023-01-23 02:29:39.741830: step: 928/529, loss: 0.0057975295931100845
2023-01-23 02:29:40.908637: step: 932/529, loss: 0.0019431114196777344
2023-01-23 02:29:42.142924: step: 936/529, loss: 0.010368729010224342
2023-01-23 02:29:43.325686: step: 940/529, loss: 0.008254623971879482
2023-01-23 02:29:44.525214: step: 944/529, loss: 0.20224666595458984
2023-01-23 02:29:45.687925: step: 948/529, loss: 0.0019812583923339844
2023-01-23 02:29:46.911369: step: 952/529, loss: 0.001178741455078125
2023-01-23 02:29:48.107248: step: 956/529, loss: 0.06243705749511719
2023-01-23 02:29:49.312480: step: 960/529, loss: 0.04425458982586861
2023-01-23 02:29:50.472133: step: 964/529, loss: 0.010663795284926891
2023-01-23 02:29:51.681406: step: 968/529, loss: 0.022866439074277878
2023-01-23 02:29:52.867063: step: 972/529, loss: 0.0005489349132403731
2023-01-23 02:29:54.042844: step: 976/529, loss: 0.015569902025163174
2023-01-23 02:29:55.242808: step: 980/529, loss: 0.0002842903195414692
2023-01-23 02:29:56.422900: step: 984/529, loss: 0.06867074966430664
2023-01-23 02:29:57.611402: step: 988/529, loss: 0.0024886131286621094
2023-01-23 02:29:58.795422: step: 992/529, loss: 0.023933792486786842
2023-01-23 02:29:59.968580: step: 996/529, loss: 0.08007517457008362
2023-01-23 02:30:01.181810: step: 1000/529, loss: 0.009482097811996937
2023-01-23 02:30:02.394810: step: 1004/529, loss: 0.09728232026100159
2023-01-23 02:30:03.599272: step: 1008/529, loss: 0.03349161148071289
2023-01-23 02:30:04.784419: step: 1012/529, loss: 0.06912766396999359
2023-01-23 02:30:05.992075: step: 1016/529, loss: 0.004979133605957031
2023-01-23 02:30:07.197146: step: 1020/529, loss: 0.005501747131347656
2023-01-23 02:30:08.364678: step: 1024/529, loss: 0.0006181717035360634
2023-01-23 02:30:09.577096: step: 1028/529, loss: 0.1310766190290451
2023-01-23 02:30:10.743221: step: 1032/529, loss: 0.025401020422577858
2023-01-23 02:30:11.951135: step: 1036/529, loss: 0.009587478823959827
2023-01-23 02:30:13.134360: step: 1040/529, loss: 0.005969238467514515
2023-01-23 02:30:14.316137: step: 1044/529, loss: 0.0011276245350018144
2023-01-23 02:30:15.488064: step: 1048/529, loss: 0.009228324517607689
2023-01-23 02:30:16.700850: step: 1052/529, loss: 0.024904441088438034
2023-01-23 02:30:17.897925: step: 1056/529, loss: 0.06702175736427307
2023-01-23 02:30:19.102997: step: 1060/529, loss: 0.04661712795495987
2023-01-23 02:30:20.282315: step: 1064/529, loss: 0.0012708663707599044
2023-01-23 02:30:21.486365: step: 1068/529, loss: 0.4381944537162781
2023-01-23 02:30:22.660478: step: 1072/529, loss: 0.0014874637126922607
2023-01-23 02:30:23.815082: step: 1076/529, loss: 0.010035132989287376
2023-01-23 02:30:25.024269: step: 1080/529, loss: 0.00543665885925293
2023-01-23 02:30:26.216630: step: 1084/529, loss: 0.005423927679657936
2023-01-23 02:30:27.387623: step: 1088/529, loss: 0.0071464539505541325
2023-01-23 02:30:28.569038: step: 1092/529, loss: 0.015397739596664906
2023-01-23 02:30:29.790035: step: 1096/529, loss: 0.0010281562572345138
2023-01-23 02:30:31.037402: step: 1100/529, loss: 0.012851142324507236
2023-01-23 02:30:32.246138: step: 1104/529, loss: 0.00019159317889716476
2023-01-23 02:30:33.457791: step: 1108/529, loss: 0.06314335018396378
2023-01-23 02:30:34.670175: step: 1112/529, loss: 0.003363990690559149
2023-01-23 02:30:35.885111: step: 1116/529, loss: 0.0033940793946385384
2023-01-23 02:30:37.093059: step: 1120/529, loss: 0.024219417944550514
2023-01-23 02:30:38.255748: step: 1124/529, loss: 0.013112019747495651
2023-01-23 02:30:39.462455: step: 1128/529, loss: 0.04424247890710831
2023-01-23 02:30:40.648853: step: 1132/529, loss: 0.0023622512817382812
2023-01-23 02:30:41.812278: step: 1136/529, loss: 0.0319644957780838
2023-01-23 02:30:43.021156: step: 1140/529, loss: 9.479522850597277e-05
2023-01-23 02:30:44.269923: step: 1144/529, loss: 0.028423786163330078
2023-01-23 02:30:45.477731: step: 1148/529, loss: 0.03562774509191513
2023-01-23 02:30:46.663427: step: 1152/529, loss: 0.002202588366344571
2023-01-23 02:30:47.868987: step: 1156/529, loss: 0.02062663994729519
2023-01-23 02:30:49.062476: step: 1160/529, loss: 0.18561343848705292
2023-01-23 02:30:50.305660: step: 1164/529, loss: 0.012226772494614124
2023-01-23 02:30:51.538569: step: 1168/529, loss: 0.013913918286561966
2023-01-23 02:30:52.780270: step: 1172/529, loss: 0.00038404465885832906
2023-01-23 02:30:53.945263: step: 1176/529, loss: 0.029262160882353783
2023-01-23 02:30:55.125818: step: 1180/529, loss: 0.04159623757004738
2023-01-23 02:30:56.323322: step: 1184/529, loss: 0.0004094124014955014
2023-01-23 02:30:57.491378: step: 1188/529, loss: 0.010108851827681065
2023-01-23 02:30:58.684229: step: 1192/529, loss: 0.024247266352176666
2023-01-23 02:30:59.887136: step: 1196/529, loss: 0.006991386413574219
2023-01-23 02:31:01.061061: step: 1200/529, loss: 9.250640869140625e-05
2023-01-23 02:31:02.250307: step: 1204/529, loss: 0.007433605846017599
2023-01-23 02:31:03.437712: step: 1208/529, loss: 0.025221824645996094
2023-01-23 02:31:04.600578: step: 1212/529, loss: 0.009494495578110218
2023-01-23 02:31:05.833415: step: 1216/529, loss: 0.004331540782004595
2023-01-23 02:31:07.019580: step: 1220/529, loss: 0.03277161344885826
2023-01-23 02:31:08.255831: step: 1224/529, loss: 0.007504463195800781
2023-01-23 02:31:09.444264: step: 1228/529, loss: 0.01615610159933567
2023-01-23 02:31:10.624603: step: 1232/529, loss: 0.008563614450395107
2023-01-23 02:31:11.849683: step: 1236/529, loss: 0.03475017473101616
2023-01-23 02:31:13.069417: step: 1240/529, loss: 0.005573368165642023
2023-01-23 02:31:14.263997: step: 1244/529, loss: 0.027919579297304153
2023-01-23 02:31:15.447088: step: 1248/529, loss: 0.0002548217889852822
2023-01-23 02:31:16.627745: step: 1252/529, loss: 0.0007903099176473916
2023-01-23 02:31:17.823675: step: 1256/529, loss: 0.01017465628683567
2023-01-23 02:31:19.013362: step: 1260/529, loss: 0.007338523864746094
2023-01-23 02:31:20.214957: step: 1264/529, loss: 0.003681659698486328
2023-01-23 02:31:21.416246: step: 1268/529, loss: 0.009714031592011452
2023-01-23 02:31:22.625738: step: 1272/529, loss: 0.004846715833991766
2023-01-23 02:31:23.831989: step: 1276/529, loss: 0.01438795868307352
2023-01-23 02:31:25.010311: step: 1280/529, loss: 0.018788862973451614
2023-01-23 02:31:26.215448: step: 1284/529, loss: 0.006714058108627796
2023-01-23 02:31:27.386864: step: 1288/529, loss: 0.0031226160936057568
2023-01-23 02:31:28.583836: step: 1292/529, loss: 0.01138153113424778
2023-01-23 02:31:29.760020: step: 1296/529, loss: 0.013680171221494675
2023-01-23 02:31:30.985567: step: 1300/529, loss: 0.06703425198793411
2023-01-23 02:31:32.164715: step: 1304/529, loss: 0.04135749489068985
2023-01-23 02:31:33.405435: step: 1308/529, loss: 0.01202306803315878
2023-01-23 02:31:34.657616: step: 1312/529, loss: 0.0014865875709801912
2023-01-23 02:31:35.823321: step: 1316/529, loss: 0.0002413749898551032
2023-01-23 02:31:37.031442: step: 1320/529, loss: 0.040582943707704544
2023-01-23 02:31:38.195864: step: 1324/529, loss: 0.0029956817161291838
2023-01-23 02:31:39.395659: step: 1328/529, loss: 0.01362705323845148
2023-01-23 02:31:40.598449: step: 1332/529, loss: 0.05243435129523277
2023-01-23 02:31:41.784963: step: 1336/529, loss: 0.006578254513442516
2023-01-23 02:31:42.964607: step: 1340/529, loss: 0.013654327020049095
2023-01-23 02:31:44.142177: step: 1344/529, loss: 0.040641263127326965
2023-01-23 02:31:45.350427: step: 1348/529, loss: 0.00038814544677734375
2023-01-23 02:31:46.545937: step: 1352/529, loss: 0.1281740367412567
2023-01-23 02:31:47.724271: step: 1356/529, loss: 0.0008365631802007556
2023-01-23 02:31:48.902262: step: 1360/529, loss: 0.0012022495502606034
2023-01-23 02:31:50.082246: step: 1364/529, loss: 0.005544376093894243
2023-01-23 02:31:51.312506: step: 1368/529, loss: 0.00048084260197356343
2023-01-23 02:31:52.532107: step: 1372/529, loss: 0.0035402297507971525
2023-01-23 02:31:53.707022: step: 1376/529, loss: 0.00027799609233625233
2023-01-23 02:31:54.918503: step: 1380/529, loss: 0.01206054724752903
2023-01-23 02:31:56.128116: step: 1384/529, loss: 0.024425983428955078
2023-01-23 02:31:57.313918: step: 1388/529, loss: 0.0038602829445153475
2023-01-23 02:31:58.553053: step: 1392/529, loss: 0.0025281906127929688
2023-01-23 02:31:59.758749: step: 1396/529, loss: 0.03226060792803764
2023-01-23 02:32:00.974226: step: 1400/529, loss: 0.04071927070617676
2023-01-23 02:32:02.147803: step: 1404/529, loss: 0.0009320259559899569
2023-01-23 02:32:03.393445: step: 1408/529, loss: 0.07824049144983292
2023-01-23 02:32:04.626158: step: 1412/529, loss: 0.003738880157470703
2023-01-23 02:32:05.796516: step: 1416/529, loss: 0.05905161052942276
2023-01-23 02:32:06.974915: step: 1420/529, loss: 0.01171798724681139
2023-01-23 02:32:08.141237: step: 1424/529, loss: 0.012498283758759499
2023-01-23 02:32:09.377786: step: 1428/529, loss: 0.002703094622120261
2023-01-23 02:32:10.609026: step: 1432/529, loss: 0.011316108517348766
2023-01-23 02:32:11.864776: step: 1436/529, loss: 0.06114530935883522
2023-01-23 02:32:13.065318: step: 1440/529, loss: 0.0012956619029864669
2023-01-23 02:32:14.250518: step: 1444/529, loss: 0.019363021478056908
2023-01-23 02:32:15.477143: step: 1448/529, loss: 0.02879038080573082
2023-01-23 02:32:16.682307: step: 1452/529, loss: 0.047258805483579636
2023-01-23 02:32:17.863761: step: 1456/529, loss: 0.0016565322875976562
2023-01-23 02:32:19.087666: step: 1460/529, loss: 0.0010992051102221012
2023-01-23 02:32:20.247344: step: 1464/529, loss: 0.026791954413056374
2023-01-23 02:32:21.463156: step: 1468/529, loss: 0.008302116766571999
2023-01-23 02:32:22.642209: step: 1472/529, loss: 0.049391746520996094
2023-01-23 02:32:23.856560: step: 1476/529, loss: 0.08932819217443466
2023-01-23 02:32:25.091105: step: 1480/529, loss: 0.021849442273378372
2023-01-23 02:32:26.272474: step: 1484/529, loss: 0.013622093945741653
2023-01-23 02:32:27.508635: step: 1488/529, loss: 0.022086476907134056
2023-01-23 02:32:28.692239: step: 1492/529, loss: 0.0036905291490256786
2023-01-23 02:32:29.890305: step: 1496/529, loss: 0.01504507102072239
2023-01-23 02:32:31.054096: step: 1500/529, loss: 0.012854481115937233
2023-01-23 02:32:32.257922: step: 1504/529, loss: 0.0008449077722616494
2023-01-23 02:32:33.464462: step: 1508/529, loss: 0.015509843826293945
2023-01-23 02:32:34.678739: step: 1512/529, loss: 0.00522689800709486
2023-01-23 02:32:35.890532: step: 1516/529, loss: 0.030788518488407135
2023-01-23 02:32:37.094191: step: 1520/529, loss: 0.0058441162109375
2023-01-23 02:32:38.281615: step: 1524/529, loss: 0.0012895583640784025
2023-01-23 02:32:39.457301: step: 1528/529, loss: 0.0012809752952307463
2023-01-23 02:32:40.701355: step: 1532/529, loss: 0.04959602281451225
2023-01-23 02:32:41.873360: step: 1536/529, loss: 0.001171112060546875
2023-01-23 02:32:43.104499: step: 1540/529, loss: 0.02509183995425701
2023-01-23 02:32:44.296953: step: 1544/529, loss: 0.0034193038009107113
2023-01-23 02:32:45.514942: step: 1548/529, loss: 9.689330909168348e-05
2023-01-23 02:32:46.664845: step: 1552/529, loss: 0.005097580142319202
2023-01-23 02:32:47.884368: step: 1556/529, loss: 0.035167478024959564
2023-01-23 02:32:49.063257: step: 1560/529, loss: 0.027625370770692825
2023-01-23 02:32:50.242699: step: 1564/529, loss: 0.004566192626953125
2023-01-23 02:32:51.445743: step: 1568/529, loss: 0.0054801939986646175
2023-01-23 02:32:52.676895: step: 1572/529, loss: 1.7290217876434326
2023-01-23 02:32:53.850765: step: 1576/529, loss: 0.028194140642881393
2023-01-23 02:32:55.050599: step: 1580/529, loss: 0.007608318235725164
2023-01-23 02:32:56.265768: step: 1584/529, loss: 0.01574697531759739
2023-01-23 02:32:57.448536: step: 1588/529, loss: 0.026951074600219727
2023-01-23 02:32:58.652740: step: 1592/529, loss: 0.005021381191909313
2023-01-23 02:32:59.845477: step: 1596/529, loss: 0.006332588382065296
2023-01-23 02:33:01.052790: step: 1600/529, loss: 0.000997257186099887
2023-01-23 02:33:02.205552: step: 1604/529, loss: 0.006206321530044079
2023-01-23 02:33:03.415880: step: 1608/529, loss: 0.023686503991484642
2023-01-23 02:33:04.688100: step: 1612/529, loss: 0.022844314575195312
2023-01-23 02:33:05.874810: step: 1616/529, loss: 0.007186699192970991
2023-01-23 02:33:07.120510: step: 1620/529, loss: 0.00924606341868639
2023-01-23 02:33:08.374624: step: 1624/529, loss: 0.004923725500702858
2023-01-23 02:33:09.594940: step: 1628/529, loss: 0.025643253698945045
2023-01-23 02:33:10.787073: step: 1632/529, loss: 0.018687628209590912
2023-01-23 02:33:12.015057: step: 1636/529, loss: 0.024279212579131126
2023-01-23 02:33:13.208787: step: 1640/529, loss: 0.027161790058016777
2023-01-23 02:33:14.422103: step: 1644/529, loss: 0.003999567124992609
2023-01-23 02:33:15.620053: step: 1648/529, loss: 0.00629425048828125
2023-01-23 02:33:16.852479: step: 1652/529, loss: 0.0024860859848558903
2023-01-23 02:33:18.080712: step: 1656/529, loss: 0.04794752970337868
2023-01-23 02:33:19.306854: step: 1660/529, loss: 0.0013815879356116056
2023-01-23 02:33:20.534282: step: 1664/529, loss: 0.051721714437007904
2023-01-23 02:33:21.769027: step: 1668/529, loss: 0.0013279914855957031
2023-01-23 02:33:22.959327: step: 1672/529, loss: 0.045391276478767395
2023-01-23 02:33:24.145781: step: 1676/529, loss: 0.002954673720523715
2023-01-23 02:33:25.365411: step: 1680/529, loss: 0.013586617074906826
2023-01-23 02:33:26.548709: step: 1684/529, loss: 0.04551806300878525
2023-01-23 02:33:27.726019: step: 1688/529, loss: 0.006103039253503084
2023-01-23 02:33:28.933984: step: 1692/529, loss: 0.02467222325503826
2023-01-23 02:33:30.108597: step: 1696/529, loss: 0.014585686847567558
2023-01-23 02:33:31.311447: step: 1700/529, loss: 0.0015466214390471578
2023-01-23 02:33:32.530162: step: 1704/529, loss: 0.09454059600830078
2023-01-23 02:33:33.740008: step: 1708/529, loss: 0.020899580791592598
2023-01-23 02:33:34.988618: step: 1712/529, loss: 0.008185243234038353
2023-01-23 02:33:36.162830: step: 1716/529, loss: 0.001505184220150113
2023-01-23 02:33:37.312808: step: 1720/529, loss: 0.003099441761150956
2023-01-23 02:33:38.503512: step: 1724/529, loss: 0.011951684951782227
2023-01-23 02:33:39.694074: step: 1728/529, loss: 0.007378101348876953
2023-01-23 02:33:40.873400: step: 1732/529, loss: 0.00152587890625
2023-01-23 02:33:42.073497: step: 1736/529, loss: 0.0012115954887121916
2023-01-23 02:33:43.300264: step: 1740/529, loss: 0.03050861321389675
2023-01-23 02:33:44.476495: step: 1744/529, loss: 0.00444717425853014
2023-01-23 02:33:45.680897: step: 1748/529, loss: 0.04294319078326225
2023-01-23 02:33:46.867157: step: 1752/529, loss: 0.13906900584697723
2023-01-23 02:33:48.070409: step: 1756/529, loss: 0.004921626765280962
2023-01-23 02:33:49.284487: step: 1760/529, loss: 0.005080700386315584
2023-01-23 02:33:50.485160: step: 1764/529, loss: 0.012706183828413486
2023-01-23 02:33:51.708443: step: 1768/529, loss: 3.662109520519152e-05
2023-01-23 02:33:52.885774: step: 1772/529, loss: 0.03647499158978462
2023-01-23 02:33:54.116072: step: 1776/529, loss: 0.04907546192407608
2023-01-23 02:33:55.303411: step: 1780/529, loss: 0.3328498601913452
2023-01-23 02:33:56.525164: step: 1784/529, loss: 0.002761268522590399
2023-01-23 02:33:57.766594: step: 1788/529, loss: 0.004390048794448376
2023-01-23 02:33:59.000157: step: 1792/529, loss: 0.006041717249900103
2023-01-23 02:34:00.244503: step: 1796/529, loss: 0.017708588391542435
2023-01-23 02:34:01.427343: step: 1800/529, loss: 0.07054843753576279
2023-01-23 02:34:02.645055: step: 1804/529, loss: 0.009965325705707073
2023-01-23 02:34:03.834305: step: 1808/529, loss: 0.054119400680065155
2023-01-23 02:34:05.051614: step: 1812/529, loss: 0.06457634270191193
2023-01-23 02:34:06.248061: step: 1816/529, loss: 0.01677706278860569
2023-01-23 02:34:07.460283: step: 1820/529, loss: 0.007974434643983841
2023-01-23 02:34:08.633252: step: 1824/529, loss: 0.019582368433475494
2023-01-23 02:34:09.860778: step: 1828/529, loss: 0.019602203741669655
2023-01-23 02:34:11.066268: step: 1832/529, loss: 0.0006181717035360634
2023-01-23 02:34:12.253735: step: 1836/529, loss: 0.6808400750160217
2023-01-23 02:34:13.435532: step: 1840/529, loss: 0.0051863668486475945
2023-01-23 02:34:14.597346: step: 1844/529, loss: 0.055155351758003235
2023-01-23 02:34:15.774456: step: 1848/529, loss: 0.02918853983283043
2023-01-23 02:34:16.955840: step: 1852/529, loss: 0.024594496935606003
2023-01-23 02:34:18.150984: step: 1856/529, loss: 0.0910254493355751
2023-01-23 02:34:19.364264: step: 1860/529, loss: 0.05084395408630371
2023-01-23 02:34:20.580116: step: 1864/529, loss: 0.060060784220695496
2023-01-23 02:34:21.749444: step: 1868/529, loss: 0.05107574164867401
2023-01-23 02:34:22.969984: step: 1872/529, loss: 0.04668428748846054
2023-01-23 02:34:24.144383: step: 1876/529, loss: 0.009514618664979935
2023-01-23 02:34:25.353283: step: 1880/529, loss: 0.006371926981955767
2023-01-23 02:34:26.617401: step: 1884/529, loss: 0.1806192398071289
2023-01-23 02:34:27.791161: step: 1888/529, loss: 4.792213439941406e-05
2023-01-23 02:34:29.023254: step: 1892/529, loss: 0.2598453462123871
2023-01-23 02:34:30.228433: step: 1896/529, loss: 0.0001903533993754536
2023-01-23 02:34:31.448064: step: 1900/529, loss: 7.43865966796875e-05
2023-01-23 02:34:32.686315: step: 1904/529, loss: 0.012529182247817516
2023-01-23 02:34:33.870083: step: 1908/529, loss: 0.04476690664887428
2023-01-23 02:34:35.073641: step: 1912/529, loss: 0.005770206451416016
2023-01-23 02:34:36.325675: step: 1916/529, loss: 0.0027514458633959293
2023-01-23 02:34:37.491096: step: 1920/529, loss: 0.005097389221191406
2023-01-23 02:34:38.696784: step: 1924/529, loss: 0.009049415588378906
2023-01-23 02:34:39.886331: step: 1928/529, loss: 0.12448372691869736
2023-01-23 02:34:41.117995: step: 1932/529, loss: 0.017469406127929688
2023-01-23 02:34:42.292827: step: 1936/529, loss: 0.005369949154555798
2023-01-23 02:34:43.509092: step: 1940/529, loss: 0.054808903485536575
2023-01-23 02:34:44.735855: step: 1944/529, loss: 0.009992980398237705
2023-01-23 02:34:45.956135: step: 1948/529, loss: 0.040560342371463776
2023-01-23 02:34:47.171372: step: 1952/529, loss: 0.21151982247829437
2023-01-23 02:34:48.353111: step: 1956/529, loss: 0.14898987114429474
2023-01-23 02:34:49.530596: step: 1960/529, loss: 0.10263834148645401
2023-01-23 02:34:50.722415: step: 1964/529, loss: 0.03355102613568306
2023-01-23 02:34:51.904273: step: 1968/529, loss: 0.008838415145874023
2023-01-23 02:34:53.157625: step: 1972/529, loss: 0.00287456507794559
2023-01-23 02:34:54.346558: step: 1976/529, loss: 0.02179746702313423
2023-01-23 02:34:55.536223: step: 1980/529, loss: 0.0022665977012366056
2023-01-23 02:34:56.763994: step: 1984/529, loss: 0.0020546913146972656
2023-01-23 02:34:57.950915: step: 1988/529, loss: 0.02467956580221653
2023-01-23 02:34:59.102262: step: 1992/529, loss: 0.0016218662494793534
2023-01-23 02:35:00.313463: step: 1996/529, loss: 0.0455591194331646
2023-01-23 02:35:01.489302: step: 2000/529, loss: 0.012937354855239391
2023-01-23 02:35:02.709897: step: 2004/529, loss: 0.00029430389986373484
2023-01-23 02:35:03.905430: step: 2008/529, loss: 0.018345260992646217
2023-01-23 02:35:05.102832: step: 2012/529, loss: 0.01963214948773384
2023-01-23 02:35:06.268471: step: 2016/529, loss: 0.0324590690433979
2023-01-23 02:35:07.439537: step: 2020/529, loss: 0.003579521318897605
2023-01-23 02:35:08.637495: step: 2024/529, loss: 0.012766839005053043
2023-01-23 02:35:09.869209: step: 2028/529, loss: 0.07166843861341476
2023-01-23 02:35:11.103644: step: 2032/529, loss: 0.046289682388305664
2023-01-23 02:35:12.292421: step: 2036/529, loss: 0.0010502815712243319
2023-01-23 02:35:13.470679: step: 2040/529, loss: 0.0020748137030750513
2023-01-23 02:35:14.645973: step: 2044/529, loss: 4.320144944358617e-05
2023-01-23 02:35:15.884451: step: 2048/529, loss: 0.01425857562571764
2023-01-23 02:35:17.098776: step: 2052/529, loss: 0.0026103975251317024
2023-01-23 02:35:18.298072: step: 2056/529, loss: 0.03824196010828018
2023-01-23 02:35:19.498130: step: 2060/529, loss: 0.0035764696076512337
2023-01-23 02:35:20.671677: step: 2064/529, loss: 0.023006059229373932
2023-01-23 02:35:21.905521: step: 2068/529, loss: 0.03257961571216583
2023-01-23 02:35:23.140039: step: 2072/529, loss: 0.004044151399284601
2023-01-23 02:35:24.358643: step: 2076/529, loss: 0.00021162032498978078
2023-01-23 02:35:25.568814: step: 2080/529, loss: 0.11506490409374237
2023-01-23 02:35:26.787765: step: 2084/529, loss: 0.001313495566137135
2023-01-23 02:35:27.978877: step: 2088/529, loss: 0.012626123614609241
2023-01-23 02:35:29.207010: step: 2092/529, loss: 0.00032138824462890625
2023-01-23 02:35:30.370760: step: 2096/529, loss: 0.005664253141731024
2023-01-23 02:35:31.606881: step: 2100/529, loss: 0.03302164003252983
2023-01-23 02:35:32.789333: step: 2104/529, loss: 0.05964851751923561
2023-01-23 02:35:33.963583: step: 2108/529, loss: 0.006173897068947554
2023-01-23 02:35:35.116353: step: 2112/529, loss: 0.006352138239890337
2023-01-23 02:35:36.331022: step: 2116/529, loss: 0.09593772888183594
==================================================
Loss: 0.031
--------------------
Dev: {'event': {'p': 0.6079664570230608, 'r': 0.7723035952063915, 'f1': 0.6803519061583578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6472317491425772, 'r': 0.7914919113241462, 'f1': 0.7121293800539084}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5915492957746479, 'r': 0.7777777777777778, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.5538461538461539, 'r': 0.5714285714285714, 'f1': 0.5625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977249224405378, 'r': 0.7696404793608522, 'f1': 0.6728754365541327}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Russian: {'event': {'p': 0.6421001926782274, 'r': 0.7986818454164171, 'f1': 0.7118825100133512}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
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': 15}
******************************
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 02:36:19.824202: step: 4/529, loss: 0.006571960635483265
2023-01-23 02:36:21.053827: step: 8/529, loss: 0.3789542317390442
2023-01-23 02:36:22.238733: step: 12/529, loss: 0.10134448856115341
2023-01-23 02:36:23.472173: step: 16/529, loss: 0.012534618377685547
2023-01-23 02:36:24.652369: step: 20/529, loss: 0.025675201788544655
2023-01-23 02:36:25.802394: step: 24/529, loss: 0.008911609649658203
2023-01-23 02:36:27.018410: step: 28/529, loss: 0.05687293782830238
2023-01-23 02:36:28.228238: step: 32/529, loss: 0.005775260739028454
2023-01-23 02:36:29.391010: step: 36/529, loss: 0.00014379025378730148
2023-01-23 02:36:30.628208: step: 40/529, loss: 0.015054893679916859
2023-01-23 02:36:31.759696: step: 44/529, loss: 0.005792808718979359
2023-01-23 02:36:33.094709: step: 48/529, loss: 0.003933334723114967
2023-01-23 02:36:34.304307: step: 52/529, loss: 0.00013227463932707906
2023-01-23 02:36:35.542854: step: 56/529, loss: 0.010695314034819603
2023-01-23 02:36:36.737553: step: 60/529, loss: 0.01738920249044895
2023-01-23 02:36:37.971343: step: 64/529, loss: 0.0016285896999761462
2023-01-23 02:36:39.171967: step: 68/529, loss: 0.0009321690304204822
2023-01-23 02:36:40.408564: step: 72/529, loss: 0.039693549275398254
2023-01-23 02:36:41.591503: step: 76/529, loss: 0.002345752902328968
2023-01-23 02:36:42.750640: step: 80/529, loss: 0.00020928384037688375
2023-01-23 02:36:43.959383: step: 84/529, loss: 0.009134196676313877
2023-01-23 02:36:45.133560: step: 88/529, loss: 0.0166186336427927
2023-01-23 02:36:46.335454: step: 92/529, loss: 0.0007817268487997353
2023-01-23 02:36:47.507878: step: 96/529, loss: 0.011416149325668812
2023-01-23 02:36:48.716354: step: 100/529, loss: 0.003180980682373047
2023-01-23 02:36:49.883309: step: 104/529, loss: 0.04525613784790039
2023-01-23 02:36:51.071907: step: 108/529, loss: 0.0002058029203908518
2023-01-23 02:36:52.270312: step: 112/529, loss: 0.0019274712540209293
2023-01-23 02:36:53.492991: step: 116/529, loss: 0.037876129150390625
2023-01-23 02:36:54.678566: step: 120/529, loss: 0.0005941391573287547
2023-01-23 02:36:55.880481: step: 124/529, loss: 0.0012660056818276644
2023-01-23 02:36:57.070153: step: 128/529, loss: 0.012882089242339134
2023-01-23 02:36:58.309938: step: 132/529, loss: 0.02698535844683647
2023-01-23 02:36:59.500959: step: 136/529, loss: 0.003217506455257535
2023-01-23 02:37:00.704629: step: 140/529, loss: 0.0021598339080810547
2023-01-23 02:37:01.900615: step: 144/529, loss: 0.06418894976377487
2023-01-23 02:37:03.055908: step: 148/529, loss: 0.03130693361163139
2023-01-23 02:37:04.272274: step: 152/529, loss: 0.011578226462006569
2023-01-23 02:37:05.468512: step: 156/529, loss: 0.0030247687827795744
2023-01-23 02:37:06.668274: step: 160/529, loss: 0.012471770867705345
2023-01-23 02:37:07.852922: step: 164/529, loss: 0.03228330612182617
2023-01-23 02:37:09.004889: step: 168/529, loss: 0.009148389101028442
2023-01-23 02:37:10.204766: step: 172/529, loss: 0.02418060228228569
2023-01-23 02:37:11.377107: step: 176/529, loss: 0.011884975247085094
2023-01-23 02:37:12.568545: step: 180/529, loss: 0.0002838134823832661
2023-01-23 02:37:13.746180: step: 184/529, loss: 0.0006986617809161544
2023-01-23 02:37:14.940584: step: 188/529, loss: 0.04712171480059624
2023-01-23 02:37:16.096310: step: 192/529, loss: 0.0741826519370079
2023-01-23 02:37:17.293340: step: 196/529, loss: 0.005088806618005037
2023-01-23 02:37:18.457685: step: 200/529, loss: 0.00757675152271986
2023-01-23 02:37:19.661178: step: 204/529, loss: 0.002328396076336503
2023-01-23 02:37:20.910920: step: 208/529, loss: 0.0028010366950184107
2023-01-23 02:37:22.085634: step: 212/529, loss: 0.01111297681927681
2023-01-23 02:37:23.296588: step: 216/529, loss: 0.01621084287762642
2023-01-23 02:37:24.528122: step: 220/529, loss: 0.005317973904311657
2023-01-23 02:37:25.696949: step: 224/529, loss: 0.00105457310564816
2023-01-23 02:37:26.893396: step: 228/529, loss: 0.00031681061955168843
2023-01-23 02:37:28.104751: step: 232/529, loss: 0.016783427447080612
2023-01-23 02:37:29.292530: step: 236/529, loss: 0.05583992227911949
2023-01-23 02:37:30.508366: step: 240/529, loss: 0.031087016686797142
2023-01-23 02:37:31.726829: step: 244/529, loss: 0.0019330024952068925
2023-01-23 02:37:32.932775: step: 248/529, loss: 0.00423278845846653
2023-01-23 02:37:34.141080: step: 252/529, loss: 0.00016126631817314774
2023-01-23 02:37:35.383934: step: 256/529, loss: 0.041787147521972656
2023-01-23 02:37:36.628533: step: 260/529, loss: 0.00141315464861691
2023-01-23 02:37:37.845448: step: 264/529, loss: 0.0016763686435297132
2023-01-23 02:37:39.110188: step: 268/529, loss: 0.021828651428222656
2023-01-23 02:37:40.312022: step: 272/529, loss: 0.0238539706915617
2023-01-23 02:37:41.469563: step: 276/529, loss: 0.0015583992935717106
2023-01-23 02:37:42.631489: step: 280/529, loss: 0.0005940437549725175
2023-01-23 02:37:43.848964: step: 284/529, loss: 0.0038047791458666325
2023-01-23 02:37:45.055562: step: 288/529, loss: 0.07631397247314453
2023-01-23 02:37:46.285761: step: 292/529, loss: 0.0028490067925304174
2023-01-23 02:37:47.500427: step: 296/529, loss: 0.0024476051330566406
2023-01-23 02:37:48.716174: step: 300/529, loss: 0.0007816314464434981
2023-01-23 02:37:49.903285: step: 304/529, loss: 0.014049815945327282
2023-01-23 02:37:51.137588: step: 308/529, loss: 0.004992294125258923
2023-01-23 02:37:52.336867: step: 312/529, loss: 0.010159874334931374
2023-01-23 02:37:53.570988: step: 316/529, loss: 0.00039901735726743937
2023-01-23 02:37:54.737915: step: 320/529, loss: 0.0036937713157385588
2023-01-23 02:37:55.967968: step: 324/529, loss: 0.02211008034646511
2023-01-23 02:37:57.178037: step: 328/529, loss: 0.0004680156707763672
2023-01-23 02:37:58.411074: step: 332/529, loss: 0.018275832757353783
2023-01-23 02:37:59.618933: step: 336/529, loss: 0.007916641421616077
2023-01-23 02:38:00.801275: step: 340/529, loss: 0.0007257461547851562
2023-01-23 02:38:02.005885: step: 344/529, loss: 0.007826900109648705
2023-01-23 02:38:03.198307: step: 348/529, loss: 0.01871032826602459
2023-01-23 02:38:04.415348: step: 352/529, loss: 9.880066500045359e-05
2023-01-23 02:38:05.615552: step: 356/529, loss: 0.0033885003067553043
2023-01-23 02:38:06.783152: step: 360/529, loss: 0.004598522093147039
2023-01-23 02:38:07.992459: step: 364/529, loss: 0.02944660186767578
2023-01-23 02:38:09.214733: step: 368/529, loss: 0.001666212105192244
2023-01-23 02:38:10.409351: step: 372/529, loss: 0.007786560337990522
2023-01-23 02:38:11.616288: step: 376/529, loss: 0.014383077621459961
2023-01-23 02:38:12.848055: step: 380/529, loss: 0.00168695452157408
2023-01-23 02:38:13.994484: step: 384/529, loss: 3.4856795537052676e-05
2023-01-23 02:38:15.169228: step: 388/529, loss: 9.841918654274195e-05
2023-01-23 02:38:16.355623: step: 392/529, loss: 0.00204048166051507
2023-01-23 02:38:17.544525: step: 396/529, loss: 0.00855102576315403
2023-01-23 02:38:18.730227: step: 400/529, loss: 0.022398853674530983
2023-01-23 02:38:19.883443: step: 404/529, loss: 0.024639606475830078
2023-01-23 02:38:21.073256: step: 408/529, loss: 0.0036026001907885075
2023-01-23 02:38:22.270340: step: 412/529, loss: 0.018871117383241653
2023-01-23 02:38:23.438084: step: 416/529, loss: 0.03730565309524536
2023-01-23 02:38:24.597254: step: 420/529, loss: 0.01784696616232395
2023-01-23 02:38:25.784849: step: 424/529, loss: 0.004335498902946711
2023-01-23 02:38:26.957561: step: 428/529, loss: 0.07183676213026047
2023-01-23 02:38:28.178254: step: 432/529, loss: 0.011652946472167969
2023-01-23 02:38:29.366157: step: 436/529, loss: 0.0003651619190350175
2023-01-23 02:38:30.587437: step: 440/529, loss: 0.03558044135570526
2023-01-23 02:38:31.753829: step: 444/529, loss: 0.024232864379882812
2023-01-23 02:38:32.978750: step: 448/529, loss: 0.045076750218868256
2023-01-23 02:38:34.179777: step: 452/529, loss: 0.003825378604233265
2023-01-23 02:38:35.412531: step: 456/529, loss: 0.04449443891644478
2023-01-23 02:38:36.619584: step: 460/529, loss: 0.003377723740413785
2023-01-23 02:38:37.827659: step: 464/529, loss: 0.0029262544121593237
2023-01-23 02:38:39.046341: step: 468/529, loss: 0.06795196235179901
2023-01-23 02:38:40.206854: step: 472/529, loss: 0.05705471336841583
2023-01-23 02:38:41.423899: step: 476/529, loss: 0.05007028579711914
2023-01-23 02:38:42.622010: step: 480/529, loss: 0.02044752985239029
2023-01-23 02:38:43.828775: step: 484/529, loss: 0.05402488633990288
2023-01-23 02:38:45.059235: step: 488/529, loss: 0.004245567601174116
2023-01-23 02:38:46.209162: step: 492/529, loss: 0.0018449783092364669
2023-01-23 02:38:47.417140: step: 496/529, loss: 0.02396526373922825
2023-01-23 02:38:48.600410: step: 500/529, loss: 0.055263713002204895
2023-01-23 02:38:49.816953: step: 504/529, loss: 0.02273092418909073
2023-01-23 02:38:51.041296: step: 508/529, loss: 0.014951705932617188
2023-01-23 02:38:52.241409: step: 512/529, loss: 0.010766410268843174
2023-01-23 02:38:53.454561: step: 516/529, loss: 0.005733966827392578
2023-01-23 02:38:54.675333: step: 520/529, loss: 0.011838722042739391
2023-01-23 02:38:55.879770: step: 524/529, loss: 0.01317259669303894
2023-01-23 02:38:57.111482: step: 528/529, loss: 0.03067016787827015
2023-01-23 02:38:58.298991: step: 532/529, loss: 0.004012489225715399
2023-01-23 02:38:59.523944: step: 536/529, loss: 0.04266476631164551
2023-01-23 02:39:00.747593: step: 540/529, loss: 0.6610426902770996
2023-01-23 02:39:01.958329: step: 544/529, loss: 0.014409112744033337
2023-01-23 02:39:03.169361: step: 548/529, loss: 1.2493132999225054e-05
2023-01-23 02:39:04.401217: step: 552/529, loss: 0.007291411980986595
2023-01-23 02:39:05.587049: step: 556/529, loss: 0.03713931888341904
2023-01-23 02:39:06.814435: step: 560/529, loss: 0.010931110940873623
2023-01-23 02:39:08.020748: step: 564/529, loss: 0.0015510559314861894
2023-01-23 02:39:09.254120: step: 568/529, loss: 0.007613754365593195
2023-01-23 02:39:10.405235: step: 572/529, loss: 0.05505962669849396
2023-01-23 02:39:11.618051: step: 576/529, loss: 0.0015285492409020662
2023-01-23 02:39:12.783120: step: 580/529, loss: 0.07072468101978302
2023-01-23 02:39:13.977717: step: 584/529, loss: 0.03504753112792969
2023-01-23 02:39:15.244557: step: 588/529, loss: 0.011196804232895374
2023-01-23 02:39:16.446233: step: 592/529, loss: 0.058238983154296875
2023-01-23 02:39:17.651250: step: 596/529, loss: 0.002355909440666437
2023-01-23 02:39:18.850187: step: 600/529, loss: 0.003253936767578125
2023-01-23 02:39:20.063546: step: 604/529, loss: 0.03973989561200142
2023-01-23 02:39:21.268877: step: 608/529, loss: 0.17533054947853088
2023-01-23 02:39:22.457843: step: 612/529, loss: 0.00117664341814816
2023-01-23 02:39:23.673348: step: 616/529, loss: 0.0010062218643724918
2023-01-23 02:39:24.913718: step: 620/529, loss: 0.0017116547096520662
2023-01-23 02:39:26.106340: step: 624/529, loss: 0.002258873078972101
2023-01-23 02:39:27.301973: step: 628/529, loss: 0.025373173877596855
2023-01-23 02:39:28.454428: step: 632/529, loss: 0.10393805056810379
2023-01-23 02:39:29.632016: step: 636/529, loss: 0.009538006968796253
2023-01-23 02:39:30.810701: step: 640/529, loss: 0.0037597655318677425
2023-01-23 02:39:32.048639: step: 644/529, loss: 0.0028879165183752775
2023-01-23 02:39:33.245879: step: 648/529, loss: 0.0011927604209631681
2023-01-23 02:39:34.451855: step: 652/529, loss: 0.003087806748226285
2023-01-23 02:39:35.664176: step: 656/529, loss: 0.053670503199100494
2023-01-23 02:39:36.843157: step: 660/529, loss: 0.019797706976532936
2023-01-23 02:39:38.043668: step: 664/529, loss: 0.0404604896903038
2023-01-23 02:39:39.228472: step: 668/529, loss: 0.0015056610573083162
2023-01-23 02:39:40.433331: step: 672/529, loss: 0.028074074536561966
2023-01-23 02:39:41.613931: step: 676/529, loss: 0.008553934283554554
2023-01-23 02:39:42.801446: step: 680/529, loss: 0.041733644902706146
2023-01-23 02:39:44.003326: step: 684/529, loss: 0.01942129246890545
2023-01-23 02:39:45.210174: step: 688/529, loss: 0.009439945220947266
2023-01-23 02:39:46.419704: step: 692/529, loss: 0.005882549099624157
2023-01-23 02:39:47.648809: step: 696/529, loss: 0.006945610046386719
2023-01-23 02:39:48.838649: step: 700/529, loss: 0.009824943728744984
2023-01-23 02:39:50.073104: step: 704/529, loss: 0.03566179424524307
2023-01-23 02:39:51.330025: step: 708/529, loss: 0.006748676300048828
2023-01-23 02:39:52.544279: step: 712/529, loss: 0.0012460709549486637
2023-01-23 02:39:53.752964: step: 716/529, loss: 0.002067947294563055
2023-01-23 02:39:54.970547: step: 720/529, loss: 0.00664520263671875
2023-01-23 02:39:56.166555: step: 724/529, loss: 0.03570222854614258
2023-01-23 02:39:57.430441: step: 728/529, loss: 0.010402202606201172
2023-01-23 02:39:58.607516: step: 732/529, loss: 0.016822339966893196
2023-01-23 02:39:59.817734: step: 736/529, loss: 0.000281858432572335
2023-01-23 02:40:01.017896: step: 740/529, loss: 0.026053808629512787
2023-01-23 02:40:02.289541: step: 744/529, loss: 0.03105487860739231
2023-01-23 02:40:03.457313: step: 748/529, loss: 1.71661376953125e-05
2023-01-23 02:40:04.636228: step: 752/529, loss: 9.121894981944934e-05
2023-01-23 02:40:05.832093: step: 756/529, loss: 0.0020624161697924137
2023-01-23 02:40:07.052402: step: 760/529, loss: 0.0011945724254474044
2023-01-23 02:40:08.236729: step: 764/529, loss: 0.0013222694396972656
2023-01-23 02:40:09.410551: step: 768/529, loss: 0.05161752924323082
2023-01-23 02:40:10.612592: step: 772/529, loss: 0.00734558142721653
2023-01-23 02:40:11.789112: step: 776/529, loss: 0.004113960545510054
2023-01-23 02:40:12.990712: step: 780/529, loss: 0.00046529772225767374
2023-01-23 02:40:14.198118: step: 784/529, loss: 0.03204412758350372
2023-01-23 02:40:15.416801: step: 788/529, loss: 0.0036285400856286287
2023-01-23 02:40:16.632220: step: 792/529, loss: 0.011181068606674671
2023-01-23 02:40:17.789775: step: 796/529, loss: 0.0006835937383584678
2023-01-23 02:40:18.972854: step: 800/529, loss: 0.006413078401237726
2023-01-23 02:40:20.177855: step: 804/529, loss: 0.31526806950569153
2023-01-23 02:40:21.336695: step: 808/529, loss: 0.26873940229415894
2023-01-23 02:40:22.492792: step: 812/529, loss: 0.013759994879364967
2023-01-23 02:40:23.734088: step: 816/529, loss: 0.0015799523098394275
2023-01-23 02:40:24.913144: step: 820/529, loss: 0.06830139458179474
2023-01-23 02:40:26.094082: step: 824/529, loss: 0.2790340185165405
2023-01-23 02:40:27.302171: step: 828/529, loss: 0.006582784466445446
2023-01-23 02:40:28.449237: step: 832/529, loss: 0.09185931086540222
2023-01-23 02:40:29.680997: step: 836/529, loss: 0.0755043476819992
2023-01-23 02:40:30.929548: step: 840/529, loss: 0.013502979651093483
2023-01-23 02:40:32.144960: step: 844/529, loss: 0.08826322853565216
2023-01-23 02:40:33.367447: step: 848/529, loss: 0.024544810876250267
2023-01-23 02:40:34.560716: step: 852/529, loss: 0.00805587787181139
2023-01-23 02:40:35.779295: step: 856/529, loss: 0.012436485849320889
2023-01-23 02:40:36.968103: step: 860/529, loss: 0.008637333288788795
2023-01-23 02:40:38.123847: step: 864/529, loss: 0.012133502401411533
2023-01-23 02:40:39.299942: step: 868/529, loss: 0.014812324196100235
2023-01-23 02:40:40.454158: step: 872/529, loss: 0.015912819653749466
2023-01-23 02:40:41.644324: step: 876/529, loss: 0.07575374096632004
2023-01-23 02:40:42.841943: step: 880/529, loss: 0.03498053550720215
2023-01-23 02:40:44.037740: step: 884/529, loss: 0.0006704330444335938
2023-01-23 02:40:45.257467: step: 888/529, loss: 0.00042639972525648773
2023-01-23 02:40:46.460010: step: 892/529, loss: 0.009276200085878372
2023-01-23 02:40:47.673480: step: 896/529, loss: 0.001554775284603238
2023-01-23 02:40:48.894477: step: 900/529, loss: 0.010940838605165482
2023-01-23 02:40:50.065935: step: 904/529, loss: 0.008047867566347122
2023-01-23 02:40:51.247542: step: 908/529, loss: 0.01586151123046875
2023-01-23 02:40:52.482976: step: 912/529, loss: 0.012513875029981136
2023-01-23 02:40:53.650023: step: 916/529, loss: 0.03560008853673935
2023-01-23 02:40:54.869854: step: 920/529, loss: 0.04224357753992081
2023-01-23 02:40:56.095750: step: 924/529, loss: 0.01746082305908203
2023-01-23 02:40:57.286613: step: 928/529, loss: 0.024683572351932526
2023-01-23 02:40:58.445993: step: 932/529, loss: 0.0329832062125206
2023-01-23 02:40:59.604089: step: 936/529, loss: 0.002388095948845148
2023-01-23 02:41:00.788913: step: 940/529, loss: 0.0007612705230712891
2023-01-23 02:41:01.990331: step: 944/529, loss: 0.043321993201971054
2023-01-23 02:41:03.167949: step: 948/529, loss: 0.0029769898392260075
2023-01-23 02:41:04.347112: step: 952/529, loss: 0.0005672454717569053
2023-01-23 02:41:05.531973: step: 956/529, loss: 0.04524478688836098
2023-01-23 02:41:06.749469: step: 960/529, loss: 0.0048018451780080795
2023-01-23 02:41:07.921738: step: 964/529, loss: 0.006884098052978516
2023-01-23 02:41:09.100529: step: 968/529, loss: 0.022586917504668236
2023-01-23 02:41:10.321343: step: 972/529, loss: 0.5738434195518494
2023-01-23 02:41:11.552931: step: 976/529, loss: 0.04804258421063423
2023-01-23 02:41:12.750125: step: 980/529, loss: 0.0022665977012366056
2023-01-23 02:41:13.937690: step: 984/529, loss: 0.0009860992431640625
2023-01-23 02:41:15.104123: step: 988/529, loss: 0.003027630038559437
2023-01-23 02:41:16.328276: step: 992/529, loss: 0.0001685619354248047
2023-01-23 02:41:17.547461: step: 996/529, loss: 0.0057128253392875195
2023-01-23 02:41:18.769864: step: 1000/529, loss: 0.08522529900074005
2023-01-23 02:41:19.936300: step: 1004/529, loss: 0.01741781271994114
2023-01-23 02:41:21.172162: step: 1008/529, loss: 0.007825016975402832
2023-01-23 02:41:22.358944: step: 1012/529, loss: 0.0022407532669603825
2023-01-23 02:41:23.557365: step: 1016/529, loss: 0.02085113525390625
2023-01-23 02:41:24.747907: step: 1020/529, loss: 0.007826042361557484
2023-01-23 02:41:25.964713: step: 1024/529, loss: 0.00010738372657215223
2023-01-23 02:41:27.134376: step: 1028/529, loss: 0.017702292650938034
2023-01-23 02:41:28.327641: step: 1032/529, loss: 0.0039351461455225945
2023-01-23 02:41:29.515252: step: 1036/529, loss: 0.013628054410219193
2023-01-23 02:41:30.739198: step: 1040/529, loss: 0.0008265495416708291
2023-01-23 02:41:31.979481: step: 1044/529, loss: 0.01953139342367649
2023-01-23 02:41:33.201996: step: 1048/529, loss: 0.0017587661277502775
2023-01-23 02:41:34.363242: step: 1052/529, loss: 0.0026020051445811987
2023-01-23 02:41:35.568025: step: 1056/529, loss: 0.006898117251694202
2023-01-23 02:41:36.766237: step: 1060/529, loss: 0.05593309551477432
2023-01-23 02:41:37.934003: step: 1064/529, loss: 0.06625232845544815
2023-01-23 02:41:39.128362: step: 1068/529, loss: 0.0061355591751635075
2023-01-23 02:41:40.302202: step: 1072/529, loss: 0.029186248779296875
2023-01-23 02:41:41.531254: step: 1076/529, loss: 7.495879981433973e-05
2023-01-23 02:41:42.700024: step: 1080/529, loss: 0.014934826642274857
2023-01-23 02:41:43.882868: step: 1084/529, loss: 1.7833710444392636e-05
2023-01-23 02:41:45.100831: step: 1088/529, loss: 0.005803585052490234
2023-01-23 02:41:46.322961: step: 1092/529, loss: 0.01610098034143448
2023-01-23 02:41:47.501436: step: 1096/529, loss: 0.01956787146627903
2023-01-23 02:41:48.680199: step: 1100/529, loss: 1.0681153071345761e-05
2023-01-23 02:41:49.872406: step: 1104/529, loss: 0.002038669539615512
2023-01-23 02:41:51.129383: step: 1108/529, loss: 0.02741718292236328
2023-01-23 02:41:52.332411: step: 1112/529, loss: 0.12127208709716797
2023-01-23 02:41:53.481938: step: 1116/529, loss: 0.0003486633358988911
2023-01-23 02:41:54.700903: step: 1120/529, loss: 0.0025796890258789062
2023-01-23 02:41:55.892927: step: 1124/529, loss: 0.0004753112734761089
2023-01-23 02:41:57.058287: step: 1128/529, loss: 0.0010111809242516756
2023-01-23 02:41:58.229927: step: 1132/529, loss: 0.01136474683880806
2023-01-23 02:41:59.429637: step: 1136/529, loss: 0.013244867324829102
2023-01-23 02:42:00.597093: step: 1140/529, loss: 0.015136336907744408
2023-01-23 02:42:01.887442: step: 1144/529, loss: 0.04565753787755966
2023-01-23 02:42:03.111035: step: 1148/529, loss: 0.03288231045007706
2023-01-23 02:42:04.313809: step: 1152/529, loss: 0.07918472588062286
2023-01-23 02:42:05.541641: step: 1156/529, loss: 0.009158515371382236
2023-01-23 02:42:06.743187: step: 1160/529, loss: 1.014816403388977
2023-01-23 02:42:07.952711: step: 1164/529, loss: 0.05476246029138565
2023-01-23 02:42:09.120263: step: 1168/529, loss: 0.0002135276881745085
2023-01-23 02:42:10.291644: step: 1172/529, loss: 0.028290940448641777
2023-01-23 02:42:11.469333: step: 1176/529, loss: 0.05173978954553604
2023-01-23 02:42:12.663606: step: 1180/529, loss: 0.04988740757107735
2023-01-23 02:42:13.896703: step: 1184/529, loss: 0.018652820959687233
2023-01-23 02:42:15.086675: step: 1188/529, loss: 0.03699808195233345
2023-01-23 02:42:16.291269: step: 1192/529, loss: 0.03100281022489071
2023-01-23 02:42:17.474904: step: 1196/529, loss: 0.02783365361392498
2023-01-23 02:42:18.670008: step: 1200/529, loss: 0.027106190100312233
2023-01-23 02:42:19.873449: step: 1204/529, loss: 0.002590274903923273
2023-01-23 02:42:21.047426: step: 1208/529, loss: 0.16605910658836365
2023-01-23 02:42:22.258945: step: 1212/529, loss: 0.3674212396144867
2023-01-23 02:42:23.549227: step: 1216/529, loss: 0.028063582256436348
2023-01-23 02:42:24.737076: step: 1220/529, loss: 0.016549110412597656
2023-01-23 02:42:25.912937: step: 1224/529, loss: 0.005625104531645775
2023-01-23 02:42:27.112982: step: 1228/529, loss: 0.00025601388188079
2023-01-23 02:42:28.282886: step: 1232/529, loss: 0.004915332887321711
2023-01-23 02:42:29.459346: step: 1236/529, loss: 0.004533672239631414
2023-01-23 02:42:30.652291: step: 1240/529, loss: 0.006754970643669367
2023-01-23 02:42:31.947338: step: 1244/529, loss: 0.03239727020263672
2023-01-23 02:42:33.174349: step: 1248/529, loss: 0.07681388407945633
2023-01-23 02:42:34.387120: step: 1252/529, loss: 0.005131632089614868
2023-01-23 02:42:35.616385: step: 1256/529, loss: 0.0021423338912427425
2023-01-23 02:42:36.816119: step: 1260/529, loss: 0.0013616561191156507
2023-01-23 02:42:37.998554: step: 1264/529, loss: 0.015633296221494675
2023-01-23 02:42:39.219725: step: 1268/529, loss: 0.04625868797302246
2023-01-23 02:42:40.389169: step: 1272/529, loss: 0.00016145705012604594
2023-01-23 02:42:41.600000: step: 1276/529, loss: 6.4849853515625e-05
2023-01-23 02:42:42.806416: step: 1280/529, loss: 0.20325584709644318
2023-01-23 02:42:44.024366: step: 1284/529, loss: 0.20736046135425568
2023-01-23 02:42:45.244546: step: 1288/529, loss: 0.003837489988654852
2023-01-23 02:42:46.437012: step: 1292/529, loss: 0.0018584252102300525
2023-01-23 02:42:47.586336: step: 1296/529, loss: 0.00408592214807868
2023-01-23 02:42:48.788081: step: 1300/529, loss: 0.011039352975785732
2023-01-23 02:42:49.984143: step: 1304/529, loss: 0.0006231308216229081
2023-01-23 02:42:51.215995: step: 1308/529, loss: 0.05428466945886612
2023-01-23 02:42:52.459253: step: 1312/529, loss: 0.009240532293915749
2023-01-23 02:42:53.652317: step: 1316/529, loss: 0.003713846206665039
2023-01-23 02:42:54.880135: step: 1320/529, loss: 0.02912120893597603
2023-01-23 02:42:56.071027: step: 1324/529, loss: 0.00027823448181152344
2023-01-23 02:42:57.280965: step: 1328/529, loss: 0.0011169433128088713
2023-01-23 02:42:58.490267: step: 1332/529, loss: 0.0014785766834393144
2023-01-23 02:42:59.688803: step: 1336/529, loss: 0.000480842572869733
2023-01-23 02:43:00.853652: step: 1340/529, loss: 0.018392659723758698
2023-01-23 02:43:02.102532: step: 1344/529, loss: 0.004159736912697554
2023-01-23 02:43:03.315330: step: 1348/529, loss: 0.021472740918397903
2023-01-23 02:43:04.524971: step: 1352/529, loss: 0.03484220430254936
2023-01-23 02:43:05.714565: step: 1356/529, loss: 0.0028735161758959293
2023-01-23 02:43:06.912692: step: 1360/529, loss: 0.0011415481567382812
2023-01-23 02:43:08.088118: step: 1364/529, loss: 0.005647468846291304
2023-01-23 02:43:09.272325: step: 1368/529, loss: 0.008494806475937366
2023-01-23 02:43:10.457355: step: 1372/529, loss: 0.0046915714628994465
2023-01-23 02:43:11.629775: step: 1376/529, loss: 0.013881778344511986
2023-01-23 02:43:12.877012: step: 1380/529, loss: 0.0013718605041503906
2023-01-23 02:43:14.048526: step: 1384/529, loss: 0.007982289418578148
2023-01-23 02:43:15.242940: step: 1388/529, loss: 5.145073009771295e-05
2023-01-23 02:43:16.420116: step: 1392/529, loss: 0.0008903503767214715
2023-01-23 02:43:17.649747: step: 1396/529, loss: 0.0009665489196777344
2023-01-23 02:43:18.818551: step: 1400/529, loss: 0.0009942532051354647
2023-01-23 02:43:20.037087: step: 1404/529, loss: 0.04839128255844116
2023-01-23 02:43:21.194863: step: 1408/529, loss: 0.00291271205060184
2023-01-23 02:43:22.360853: step: 1412/529, loss: 0.03854217752814293
2023-01-23 02:43:23.528318: step: 1416/529, loss: 0.000541305576916784
2023-01-23 02:43:24.741178: step: 1420/529, loss: 0.01825394481420517
2023-01-23 02:43:25.947946: step: 1424/529, loss: 0.1423528641462326
2023-01-23 02:43:27.146091: step: 1428/529, loss: 0.00010032653517555445
2023-01-23 02:43:28.328113: step: 1432/529, loss: 0.0003559827746357769
2023-01-23 02:43:29.506401: step: 1436/529, loss: 7.781982276355848e-05
2023-01-23 02:43:30.723350: step: 1440/529, loss: 0.0014945983421057463
2023-01-23 02:43:31.940912: step: 1444/529, loss: 3.376007225597277e-05
2023-01-23 02:43:33.132268: step: 1448/529, loss: 0.01575806923210621
2023-01-23 02:43:34.299015: step: 1452/529, loss: 0.0018788338638842106
2023-01-23 02:43:35.482464: step: 1456/529, loss: 0.002624702639877796
2023-01-23 02:43:36.696066: step: 1460/529, loss: 0.0018415451049804688
2023-01-23 02:43:37.877326: step: 1464/529, loss: 0.004680562298744917
2023-01-23 02:43:39.125590: step: 1468/529, loss: 0.05300407484173775
2023-01-23 02:43:40.312567: step: 1472/529, loss: 0.0304412841796875
2023-01-23 02:43:41.556947: step: 1476/529, loss: 0.121337890625
2023-01-23 02:43:42.744296: step: 1480/529, loss: 0.027698229998350143
2023-01-23 02:43:43.953471: step: 1484/529, loss: 0.04926319420337677
2023-01-23 02:43:45.169715: step: 1488/529, loss: 0.022179411724209785
2023-01-23 02:43:46.368556: step: 1492/529, loss: 0.00044317246647551656
2023-01-23 02:43:47.568990: step: 1496/529, loss: 0.0031815350521355867
2023-01-23 02:43:48.783234: step: 1500/529, loss: 0.0795368179678917
2023-01-23 02:43:50.023690: step: 1504/529, loss: 0.02361736260354519
2023-01-23 02:43:51.233587: step: 1508/529, loss: 0.06574898213148117
2023-01-23 02:43:52.476714: step: 1512/529, loss: 0.1653156280517578
2023-01-23 02:43:53.639167: step: 1516/529, loss: 0.021730568259954453
2023-01-23 02:43:54.914957: step: 1520/529, loss: 0.003413581755012274
2023-01-23 02:43:56.148288: step: 1524/529, loss: 0.00037059784517623484
2023-01-23 02:43:57.324270: step: 1528/529, loss: 0.09672079235315323
2023-01-23 02:43:58.579553: step: 1532/529, loss: 0.051881350576877594
2023-01-23 02:43:59.804282: step: 1536/529, loss: 0.004330158233642578
2023-01-23 02:44:01.002021: step: 1540/529, loss: 0.011902237311005592
2023-01-23 02:44:02.185766: step: 1544/529, loss: 0.0005717277526855469
2023-01-23 02:44:03.379380: step: 1548/529, loss: 0.29159051179885864
2023-01-23 02:44:04.573582: step: 1552/529, loss: 0.009038162417709827
2023-01-23 02:44:05.743772: step: 1556/529, loss: 0.001659661647863686
2023-01-23 02:44:06.948756: step: 1560/529, loss: 0.059976864606142044
2023-01-23 02:44:08.161370: step: 1564/529, loss: 0.01754627376794815
2023-01-23 02:44:09.366627: step: 1568/529, loss: 0.00023312569828704
2023-01-23 02:44:10.561171: step: 1572/529, loss: 0.005563163664191961
2023-01-23 02:44:11.744282: step: 1576/529, loss: 0.0010837077861651778
2023-01-23 02:44:12.908715: step: 1580/529, loss: 0.00657157925888896
2023-01-23 02:44:14.103191: step: 1584/529, loss: 0.008053207769989967
2023-01-23 02:44:15.267360: step: 1588/529, loss: 0.0010655403602868319
2023-01-23 02:44:16.460527: step: 1592/529, loss: 0.0046104430221021175
2023-01-23 02:44:17.673697: step: 1596/529, loss: 0.005394125357270241
2023-01-23 02:44:18.850157: step: 1600/529, loss: 0.017582226544618607
2023-01-23 02:44:20.044206: step: 1604/529, loss: 0.03404712677001953
2023-01-23 02:44:21.227360: step: 1608/529, loss: 0.02000255510210991
2023-01-23 02:44:22.411861: step: 1612/529, loss: 0.004681883845478296
2023-01-23 02:44:23.598417: step: 1616/529, loss: 0.0028125762473791838
2023-01-23 02:44:24.749641: step: 1620/529, loss: 0.016115987673401833
2023-01-23 02:44:25.971038: step: 1624/529, loss: 0.009394645690917969
2023-01-23 02:44:27.165636: step: 1628/529, loss: 0.00820016860961914
2023-01-23 02:44:28.326388: step: 1632/529, loss: 0.09341640770435333
2023-01-23 02:44:29.562259: step: 1636/529, loss: 0.019188690930604935
2023-01-23 02:44:30.761591: step: 1640/529, loss: 0.09687347710132599
2023-01-23 02:44:31.940891: step: 1644/529, loss: 0.00403518695384264
2023-01-23 02:44:33.153309: step: 1648/529, loss: 0.03035411797463894
2023-01-23 02:44:34.350317: step: 1652/529, loss: 0.0021083832252770662
2023-01-23 02:44:35.531917: step: 1656/529, loss: 0.016806984320282936
2023-01-23 02:44:36.720055: step: 1660/529, loss: 0.14373797178268433
2023-01-23 02:44:37.925983: step: 1664/529, loss: 0.01669750176370144
2023-01-23 02:44:39.121386: step: 1668/529, loss: 0.07492275536060333
2023-01-23 02:44:40.285217: step: 1672/529, loss: 0.021019555628299713
2023-01-23 02:44:41.557465: step: 1676/529, loss: 0.04082183539867401
2023-01-23 02:44:42.775226: step: 1680/529, loss: 0.0009871483780443668
2023-01-23 02:44:43.919118: step: 1684/529, loss: 0.0035179615952074528
2023-01-23 02:44:45.089246: step: 1688/529, loss: 0.0017014980548992753
2023-01-23 02:44:46.272363: step: 1692/529, loss: 0.056725598871707916
2023-01-23 02:44:47.496919: step: 1696/529, loss: 0.18515071272850037
2023-01-23 02:44:48.685589: step: 1700/529, loss: 0.04341382905840874
2023-01-23 02:44:49.865626: step: 1704/529, loss: 0.021404171362519264
2023-01-23 02:44:51.053548: step: 1708/529, loss: 3.337860107421875e-05
2023-01-23 02:44:52.239584: step: 1712/529, loss: 0.002731704618781805
2023-01-23 02:44:53.439783: step: 1716/529, loss: 0.012829303741455078
2023-01-23 02:44:54.601882: step: 1720/529, loss: 0.000878453254699707
2023-01-23 02:44:55.801149: step: 1724/529, loss: 0.02314412221312523
2023-01-23 02:44:57.040921: step: 1728/529, loss: 0.0098114013671875
2023-01-23 02:44:58.278046: step: 1732/529, loss: 0.037679292261600494
2023-01-23 02:44:59.482919: step: 1736/529, loss: 0.02869434282183647
2023-01-23 02:45:00.682116: step: 1740/529, loss: 0.014662742614746094
2023-01-23 02:45:01.873309: step: 1744/529, loss: 0.047613147646188736
2023-01-23 02:45:03.083178: step: 1748/529, loss: 0.007218551822006702
2023-01-23 02:45:04.273214: step: 1752/529, loss: 0.05199103429913521
2023-01-23 02:45:05.487393: step: 1756/529, loss: 0.00269489292986691
2023-01-23 02:45:06.679455: step: 1760/529, loss: 0.0016673087375238538
2023-01-23 02:45:07.859298: step: 1764/529, loss: 0.012362862005829811
2023-01-23 02:45:09.066660: step: 1768/529, loss: 0.1458592563867569
2023-01-23 02:45:10.296927: step: 1772/529, loss: 0.05312805250287056
2023-01-23 02:45:11.485257: step: 1776/529, loss: 0.0008801460498943925
2023-01-23 02:45:12.684262: step: 1780/529, loss: 0.054697465151548386
2023-01-23 02:45:13.859466: step: 1784/529, loss: 0.007571316324174404
2023-01-23 02:45:15.049472: step: 1788/529, loss: 0.0024704933166503906
2023-01-23 02:45:16.263377: step: 1792/529, loss: 0.0009280681842938066
2023-01-23 02:45:17.484980: step: 1796/529, loss: 0.003054714296013117
2023-01-23 02:45:18.672642: step: 1800/529, loss: 0.006800842471420765
2023-01-23 02:45:19.915053: step: 1804/529, loss: 0.01835303194820881
2023-01-23 02:45:21.059361: step: 1808/529, loss: 0.03291856124997139
2023-01-23 02:45:22.288737: step: 1812/529, loss: 0.007248306181281805
2023-01-23 02:45:23.475208: step: 1816/529, loss: 0.006799554452300072
2023-01-23 02:45:24.729959: step: 1820/529, loss: 0.012285137549042702
2023-01-23 02:45:25.906136: step: 1824/529, loss: 0.008073901757597923
2023-01-23 02:45:27.054527: step: 1828/529, loss: 0.008564376272261143
2023-01-23 02:45:28.233384: step: 1832/529, loss: 0.04788989946246147
2023-01-23 02:45:29.488012: step: 1836/529, loss: 0.0033513070084154606
2023-01-23 02:45:30.706120: step: 1840/529, loss: 0.07816791534423828
2023-01-23 02:45:31.934193: step: 1844/529, loss: 0.0001598358212504536
2023-01-23 02:45:33.156774: step: 1848/529, loss: 0.008773136883974075
2023-01-23 02:45:34.330206: step: 1852/529, loss: 0.004462623503059149
2023-01-23 02:45:35.540157: step: 1856/529, loss: 0.008317852392792702
2023-01-23 02:45:36.741621: step: 1860/529, loss: 0.006545543670654297
2023-01-23 02:45:37.947181: step: 1864/529, loss: 0.14648190140724182
2023-01-23 02:45:39.175987: step: 1868/529, loss: 0.024390220642089844
2023-01-23 02:45:40.358993: step: 1872/529, loss: 0.017086029052734375
2023-01-23 02:45:41.553192: step: 1876/529, loss: 0.02382678911089897
2023-01-23 02:45:42.750974: step: 1880/529, loss: 0.004903741180896759
2023-01-23 02:45:43.943069: step: 1884/529, loss: 0.00018033981905318797
2023-01-23 02:45:45.124585: step: 1888/529, loss: 0.03513813391327858
2023-01-23 02:45:46.278789: step: 1892/529, loss: 0.000362205522833392
2023-01-23 02:45:47.463198: step: 1896/529, loss: 0.0208453182131052
2023-01-23 02:45:48.678419: step: 1900/529, loss: 0.009539700113236904
2023-01-23 02:45:49.903868: step: 1904/529, loss: 0.01561746560037136
2023-01-23 02:45:51.115989: step: 1908/529, loss: 0.09768714755773544
2023-01-23 02:45:52.348186: step: 1912/529, loss: 0.025345230475068092
2023-01-23 02:45:53.536249: step: 1916/529, loss: 0.027213675901293755
2023-01-23 02:45:54.791503: step: 1920/529, loss: 0.002090645022690296
2023-01-23 02:45:55.963618: step: 1924/529, loss: 0.026171397417783737
2023-01-23 02:45:57.154617: step: 1928/529, loss: 0.010178041644394398
2023-01-23 02:45:58.366378: step: 1932/529, loss: 0.05351848527789116
2023-01-23 02:45:59.546350: step: 1936/529, loss: 0.0030673982109874487
2023-01-23 02:46:00.717996: step: 1940/529, loss: 0.00229988107457757
2023-01-23 02:46:01.893070: step: 1944/529, loss: 0.011982298456132412
2023-01-23 02:46:03.061371: step: 1948/529, loss: 0.09695949405431747
2023-01-23 02:46:04.235777: step: 1952/529, loss: 0.00252456683665514
2023-01-23 02:46:05.409546: step: 1956/529, loss: 0.00902624148875475
2023-01-23 02:46:06.599093: step: 1960/529, loss: 0.009364367462694645
2023-01-23 02:46:07.788280: step: 1964/529, loss: 0.005198335740715265
2023-01-23 02:46:09.006587: step: 1968/529, loss: 0.0012603760696947575
2023-01-23 02:46:10.240094: step: 1972/529, loss: 0.00810775812715292
2023-01-23 02:46:11.441574: step: 1976/529, loss: 0.0907234251499176
2023-01-23 02:46:12.618443: step: 1980/529, loss: 0.001408433890901506
2023-01-23 02:46:13.795609: step: 1984/529, loss: 0.0027451515197753906
2023-01-23 02:46:15.027669: step: 1988/529, loss: 0.011291027069091797
2023-01-23 02:46:16.242963: step: 1992/529, loss: 0.002602529479190707
2023-01-23 02:46:17.422124: step: 1996/529, loss: 0.005759811960160732
2023-01-23 02:46:18.630029: step: 2000/529, loss: 0.01916332170367241
2023-01-23 02:46:19.806909: step: 2004/529, loss: 0.004253959748893976
2023-01-23 02:46:20.954337: step: 2008/529, loss: 0.00305099505931139
2023-01-23 02:46:22.140268: step: 2012/529, loss: 0.0014254569541662931
2023-01-23 02:46:23.307897: step: 2016/529, loss: 0.006015682127326727
2023-01-23 02:46:24.467466: step: 2020/529, loss: 0.014016724191606045
2023-01-23 02:46:25.718503: step: 2024/529, loss: 0.0018743515247479081
2023-01-23 02:46:26.950006: step: 2028/529, loss: 0.011777544394135475
2023-01-23 02:46:28.149156: step: 2032/529, loss: 0.020840167999267578
2023-01-23 02:46:29.336931: step: 2036/529, loss: 0.0001446724054403603
2023-01-23 02:46:30.538080: step: 2040/529, loss: 0.05276113003492355
2023-01-23 02:46:31.723350: step: 2044/529, loss: 0.04874706268310547
2023-01-23 02:46:32.953288: step: 2048/529, loss: 0.021726323291659355
2023-01-23 02:46:34.144551: step: 2052/529, loss: 0.0004444122314453125
2023-01-23 02:46:35.345096: step: 2056/529, loss: 0.0022496222518384457
2023-01-23 02:46:36.611846: step: 2060/529, loss: 0.018486356362700462
2023-01-23 02:46:37.847518: step: 2064/529, loss: 0.03096456453204155
2023-01-23 02:46:39.014686: step: 2068/529, loss: 0.010410308837890625
2023-01-23 02:46:40.240320: step: 2072/529, loss: 0.00010929107520496473
2023-01-23 02:46:41.437982: step: 2076/529, loss: 0.027348138391971588
2023-01-23 02:46:42.648703: step: 2080/529, loss: 0.015237999148666859
2023-01-23 02:46:43.834469: step: 2084/529, loss: 0.021816540509462357
2023-01-23 02:46:45.055756: step: 2088/529, loss: 0.004836464300751686
2023-01-23 02:46:46.312377: step: 2092/529, loss: 0.0010181904071941972
2023-01-23 02:46:47.504496: step: 2096/529, loss: 0.006256484892219305
2023-01-23 02:46:48.705884: step: 2100/529, loss: 0.03036174736917019
2023-01-23 02:46:49.970678: step: 2104/529, loss: 0.36529675126075745
2023-01-23 02:46:51.175387: step: 2108/529, loss: 0.010082244873046875
2023-01-23 02:46:52.366009: step: 2112/529, loss: 0.03462104871869087
2023-01-23 02:46:53.563111: step: 2116/529, loss: 0.00874700490385294
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.6376811594202898, 'r': 0.8148148148148148, 'f1': 0.7154471544715448}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.6739130434782609, 'r': 0.49206349206349204, 'f1': 0.5688073394495413}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 02:47:42.628464: step: 4/529, loss: 0.06424503028392792
2023-01-23 02:47:43.802913: step: 8/529, loss: 0.008706474676728249
2023-01-23 02:47:45.019319: step: 12/529, loss: 0.007932472042739391
2023-01-23 02:47:46.201439: step: 16/529, loss: 7.572174217784777e-05
2023-01-23 02:47:47.382320: step: 20/529, loss: 0.09052447974681854
2023-01-23 02:47:48.596711: step: 24/529, loss: 8.277893357444555e-05
2023-01-23 02:47:49.760667: step: 28/529, loss: 0.004005813505500555
2023-01-23 02:47:50.947345: step: 32/529, loss: 0.005010413937270641
2023-01-23 02:47:52.164194: step: 36/529, loss: 0.015244293957948685
2023-01-23 02:47:53.336279: step: 40/529, loss: 0.028431154787540436
2023-01-23 02:47:54.556117: step: 44/529, loss: 0.00016918181790970266
2023-01-23 02:47:55.748387: step: 48/529, loss: 0.04810895770788193
2023-01-23 02:47:56.960749: step: 52/529, loss: 0.020151138305664062
2023-01-23 02:47:58.181591: step: 56/529, loss: 0.0078071593306958675
2023-01-23 02:47:59.322778: step: 60/529, loss: 0.002602195832878351
2023-01-23 02:48:00.544514: step: 64/529, loss: 0.0021851540077477694
2023-01-23 02:48:01.740059: step: 68/529, loss: 0.028033830225467682
2023-01-23 02:48:02.945675: step: 72/529, loss: 0.019364167004823685
2023-01-23 02:48:04.114340: step: 76/529, loss: 0.05893249809741974
2023-01-23 02:48:05.283893: step: 80/529, loss: 0.137858584523201
2023-01-23 02:48:06.488558: step: 84/529, loss: 0.0037191391456872225
2023-01-23 02:48:07.730206: step: 88/529, loss: 0.0005077362293377519
2023-01-23 02:48:08.929788: step: 92/529, loss: 0.021845554932951927
2023-01-23 02:48:10.102627: step: 96/529, loss: 0.004063797183334827
2023-01-23 02:48:11.253880: step: 100/529, loss: 0.007959174923598766
2023-01-23 02:48:12.450863: step: 104/529, loss: 0.0042365072295069695
2023-01-23 02:48:13.643531: step: 108/529, loss: 0.02066984213888645
2023-01-23 02:48:14.867802: step: 112/529, loss: 0.016972161829471588
2023-01-23 02:48:16.096748: step: 116/529, loss: 0.17690548300743103
2023-01-23 02:48:17.291745: step: 120/529, loss: 0.07662391662597656
2023-01-23 02:48:18.437020: step: 124/529, loss: 0.04297695308923721
2023-01-23 02:48:19.643734: step: 128/529, loss: 0.0019210815662518144
2023-01-23 02:48:20.864049: step: 132/529, loss: 0.0053751468658447266
2023-01-23 02:48:22.072934: step: 136/529, loss: 0.00046062469482421875
2023-01-23 02:48:23.258755: step: 140/529, loss: 0.008402824401855469
2023-01-23 02:48:24.433895: step: 144/529, loss: 0.009838677011430264
2023-01-23 02:48:25.632551: step: 148/529, loss: 0.003105735871940851
2023-01-23 02:48:26.837030: step: 152/529, loss: 0.25977858901023865
2023-01-23 02:48:28.057594: step: 156/529, loss: 0.009750175289809704
2023-01-23 02:48:29.235198: step: 160/529, loss: 0.003467082977294922
2023-01-23 02:48:30.441631: step: 164/529, loss: 0.0028938292525708675
2023-01-23 02:48:31.663982: step: 168/529, loss: 0.004630994983017445
2023-01-23 02:48:32.839032: step: 172/529, loss: 0.0011221885215491056
2023-01-23 02:48:34.065345: step: 176/529, loss: 0.002478695008903742
2023-01-23 02:48:35.258707: step: 180/529, loss: 0.0029655457474291325
2023-01-23 02:48:36.494135: step: 184/529, loss: 0.0015304565895348787
2023-01-23 02:48:37.692147: step: 188/529, loss: 0.004024410620331764
2023-01-23 02:48:38.848767: step: 192/529, loss: 0.017668360844254494
2023-01-23 02:48:40.067139: step: 196/529, loss: 0.006122017279267311
2023-01-23 02:48:41.245485: step: 200/529, loss: 0.05918922647833824
2023-01-23 02:48:42.472284: step: 204/529, loss: 0.004817390814423561
2023-01-23 02:48:43.669994: step: 208/529, loss: 0.008568000979721546
2023-01-23 02:48:44.846988: step: 212/529, loss: 0.0013031960697844625
2023-01-23 02:48:46.082802: step: 216/529, loss: 0.0086517333984375
2023-01-23 02:48:47.299572: step: 220/529, loss: 0.023004816845059395
2023-01-23 02:48:48.508210: step: 224/529, loss: 0.005378055851906538
2023-01-23 02:48:49.658644: step: 228/529, loss: 0.03881673887372017
2023-01-23 02:48:50.844429: step: 232/529, loss: 0.007745838724076748
2023-01-23 02:48:52.052446: step: 236/529, loss: 0.08488941937685013
2023-01-23 02:48:53.245947: step: 240/529, loss: 0.016089629381895065
2023-01-23 02:48:54.440764: step: 244/529, loss: 0.008154870010912418
2023-01-23 02:48:55.627237: step: 248/529, loss: 0.06566081196069717
2023-01-23 02:48:56.842776: step: 252/529, loss: 2.7370453608455136e-05
2023-01-23 02:48:58.001298: step: 256/529, loss: 4.715919931186363e-05
2023-01-23 02:48:59.201579: step: 260/529, loss: 0.02048931084573269
2023-01-23 02:49:00.394587: step: 264/529, loss: 0.0015218734042719007
2023-01-23 02:49:01.559012: step: 268/529, loss: 0.03358745574951172
2023-01-23 02:49:02.776061: step: 272/529, loss: 0.00013828277587890625
2023-01-23 02:49:03.999468: step: 276/529, loss: 0.004203987307846546
2023-01-23 02:49:05.221550: step: 280/529, loss: 0.01325836218893528
2023-01-23 02:49:06.424317: step: 284/529, loss: 0.0995725691318512
2023-01-23 02:49:07.615821: step: 288/529, loss: 0.0031786919571459293
2023-01-23 02:49:08.842746: step: 292/529, loss: 0.00556869525462389
2023-01-23 02:49:10.076370: step: 296/529, loss: 0.002055597258731723
2023-01-23 02:49:11.274961: step: 300/529, loss: 0.001387095544487238
2023-01-23 02:49:12.467013: step: 304/529, loss: 0.001844215439632535
2023-01-23 02:49:13.677946: step: 308/529, loss: 0.015028762631118298
2023-01-23 02:49:14.846446: step: 312/529, loss: 0.036978576332330704
2023-01-23 02:49:16.033949: step: 316/529, loss: 0.006365966983139515
2023-01-23 02:49:17.306790: step: 320/529, loss: 0.004104995634406805
2023-01-23 02:49:18.498432: step: 324/529, loss: 0.009681510739028454
2023-01-23 02:49:19.663484: step: 328/529, loss: 0.0002933502255473286
2023-01-23 02:49:20.866883: step: 332/529, loss: 0.0018339157104492188
2023-01-23 02:49:22.039141: step: 336/529, loss: 0.0024933815002441406
2023-01-23 02:49:23.276488: step: 340/529, loss: 0.014305305667221546
2023-01-23 02:49:24.515704: step: 344/529, loss: 0.007672500796616077
2023-01-23 02:49:25.701539: step: 348/529, loss: 9.870529174804688e-05
2023-01-23 02:49:26.882889: step: 352/529, loss: 0.0012907981872558594
2023-01-23 02:49:28.116862: step: 356/529, loss: 0.000255584716796875
2023-01-23 02:49:29.335308: step: 360/529, loss: 0.010764884762465954
2023-01-23 02:49:30.529799: step: 364/529, loss: 0.01815338060259819
2023-01-23 02:49:31.737581: step: 368/529, loss: 0.06235694885253906
2023-01-23 02:49:33.021128: step: 372/529, loss: 0.011397361755371094
2023-01-23 02:49:34.197278: step: 376/529, loss: 0.00359687814489007
2023-01-23 02:49:35.424529: step: 380/529, loss: 0.05834845080971718
2023-01-23 02:49:36.593713: step: 384/529, loss: 0.001628875732421875
2023-01-23 02:49:37.805517: step: 388/529, loss: 0.013346291147172451
2023-01-23 02:49:39.075552: step: 392/529, loss: 0.09892668575048447
2023-01-23 02:49:40.341622: step: 396/529, loss: 0.0017574310768395662
2023-01-23 02:49:41.508642: step: 400/529, loss: 0.0038386343512684107
2023-01-23 02:49:42.732121: step: 404/529, loss: 0.003656578017398715
2023-01-23 02:49:43.940794: step: 408/529, loss: 0.0422358512878418
2023-01-23 02:49:45.161197: step: 412/529, loss: 0.008557033725082874
2023-01-23 02:49:46.357240: step: 416/529, loss: 0.0542333610355854
2023-01-23 02:49:47.582640: step: 420/529, loss: 0.028049660846590996
2023-01-23 02:49:48.783234: step: 424/529, loss: 0.0005784034729003906
2023-01-23 02:49:49.969400: step: 428/529, loss: 0.0033512115478515625
2023-01-23 02:49:51.167152: step: 432/529, loss: 0.055254556238651276
2023-01-23 02:49:52.374633: step: 436/529, loss: 0.0023679733276367188
2023-01-23 02:49:53.562192: step: 440/529, loss: 0.0010782241588458419
2023-01-23 02:49:54.765308: step: 444/529, loss: 8.7738037109375e-05
2023-01-23 02:49:55.969427: step: 448/529, loss: 0.006907558999955654
2023-01-23 02:49:57.169908: step: 452/529, loss: 0.00539774913340807
2023-01-23 02:49:58.416434: step: 456/529, loss: 0.01805396005511284
2023-01-23 02:49:59.698026: step: 460/529, loss: 0.060446739196777344
2023-01-23 02:50:00.867777: step: 464/529, loss: 0.0008045196300372481
2023-01-23 02:50:02.042613: step: 468/529, loss: 0.13915549218654633
2023-01-23 02:50:03.209910: step: 472/529, loss: 0.025353431701660156
2023-01-23 02:50:04.377299: step: 476/529, loss: 0.018467998132109642
2023-01-23 02:50:05.561629: step: 480/529, loss: 0.014942443929612637
2023-01-23 02:50:06.790622: step: 484/529, loss: 0.015442563220858574
2023-01-23 02:50:07.981772: step: 488/529, loss: 0.00036154090776108205
2023-01-23 02:50:09.171468: step: 492/529, loss: 2.0790101189049892e-05
2023-01-23 02:50:10.347827: step: 496/529, loss: 0.000743865966796875
2023-01-23 02:50:11.532669: step: 500/529, loss: 0.00969996489584446
2023-01-23 02:50:12.723919: step: 504/529, loss: 6.122589547885582e-05
2023-01-23 02:50:13.913269: step: 508/529, loss: 0.00043911935063079
2023-01-23 02:50:15.136368: step: 512/529, loss: 0.025482559576630592
2023-01-23 02:50:16.322753: step: 516/529, loss: 0.015529823489487171
2023-01-23 02:50:17.540591: step: 520/529, loss: 0.007698011584579945
2023-01-23 02:50:18.740061: step: 524/529, loss: 0.005531501956284046
2023-01-23 02:50:19.913828: step: 528/529, loss: 0.04183664545416832
2023-01-23 02:50:21.113543: step: 532/529, loss: 0.002524757292121649
2023-01-23 02:50:22.292904: step: 536/529, loss: 0.0004337310965638608
2023-01-23 02:50:23.506858: step: 540/529, loss: 0.027965927496552467
2023-01-23 02:50:24.685780: step: 544/529, loss: 0.01026067789644003
2023-01-23 02:50:25.916907: step: 548/529, loss: 0.003141164779663086
2023-01-23 02:50:27.093595: step: 552/529, loss: 0.055869486182928085
2023-01-23 02:50:28.304573: step: 556/529, loss: 0.0028190254233777523
2023-01-23 02:50:29.495848: step: 560/529, loss: 0.00136909494176507
2023-01-23 02:50:30.686060: step: 564/529, loss: 0.0025454522110521793
2023-01-23 02:50:31.871670: step: 568/529, loss: 0.008861064910888672
2023-01-23 02:50:33.048024: step: 572/529, loss: 0.007780647370964289
2023-01-23 02:50:34.267939: step: 576/529, loss: 0.003621101612225175
2023-01-23 02:50:35.416036: step: 580/529, loss: 0.0003100395551882684
2023-01-23 02:50:36.649777: step: 584/529, loss: 0.005069160368293524
2023-01-23 02:50:37.866295: step: 588/529, loss: 0.0027904033195227385
2023-01-23 02:50:39.064016: step: 592/529, loss: 0.002065372420474887
2023-01-23 02:50:40.262469: step: 596/529, loss: 0.013754081912338734
2023-01-23 02:50:41.460754: step: 600/529, loss: 0.0006410598871298134
2023-01-23 02:50:42.674906: step: 604/529, loss: 0.007453632541000843
2023-01-23 02:50:43.860034: step: 608/529, loss: 0.43801918625831604
2023-01-23 02:50:45.015791: step: 612/529, loss: 0.012390327639877796
2023-01-23 02:50:46.265904: step: 616/529, loss: 0.09776792675256729
2023-01-23 02:50:47.453418: step: 620/529, loss: 0.008025741204619408
2023-01-23 02:50:48.653451: step: 624/529, loss: 0.01973114162683487
2023-01-23 02:50:49.872282: step: 628/529, loss: 0.010404204949736595
2023-01-23 02:50:51.071919: step: 632/529, loss: 0.0007291794172488153
2023-01-23 02:50:52.282553: step: 636/529, loss: 0.0015153884887695312
2023-01-23 02:50:53.449181: step: 640/529, loss: 0.0011337280739098787
2023-01-23 02:50:54.633115: step: 644/529, loss: 7.243156142067164e-05
2023-01-23 02:50:55.801824: step: 648/529, loss: 0.008921433240175247
2023-01-23 02:50:56.967733: step: 652/529, loss: 9.346007573185489e-06
2023-01-23 02:50:58.129948: step: 656/529, loss: 0.0009045600891113281
2023-01-23 02:50:59.307146: step: 660/529, loss: 0.004174423404037952
2023-01-23 02:51:00.503597: step: 664/529, loss: 0.008622074499726295
2023-01-23 02:51:01.742077: step: 668/529, loss: 0.0034662247635424137
2023-01-23 02:51:03.010204: step: 672/529, loss: 0.015787601470947266
2023-01-23 02:51:04.205284: step: 676/529, loss: 0.00700383260846138
2023-01-23 02:51:05.371158: step: 680/529, loss: 0.06572704762220383
2023-01-23 02:51:06.546918: step: 684/529, loss: 0.035642433911561966
2023-01-23 02:51:07.724392: step: 688/529, loss: 0.004046916961669922
2023-01-23 02:51:08.961722: step: 692/529, loss: 0.021069765090942383
2023-01-23 02:51:10.164592: step: 696/529, loss: 5.4550167988054454e-05
2023-01-23 02:51:11.412645: step: 700/529, loss: 0.004474544897675514
2023-01-23 02:51:12.590971: step: 704/529, loss: 0.037020303308963776
2023-01-23 02:51:13.788557: step: 708/529, loss: 0.04548950493335724
2023-01-23 02:51:14.986186: step: 712/529, loss: 0.02918701246380806
2023-01-23 02:51:16.190524: step: 716/529, loss: 0.003761101048439741
2023-01-23 02:51:17.387010: step: 720/529, loss: 0.0030232430435717106
2023-01-23 02:51:18.593796: step: 724/529, loss: 0.013779353350400925
2023-01-23 02:51:19.745643: step: 728/529, loss: 0.04705391079187393
2023-01-23 02:51:20.952670: step: 732/529, loss: 0.012912321835756302
2023-01-23 02:51:22.140856: step: 736/529, loss: 0.6670275926589966
2023-01-23 02:51:23.324098: step: 740/529, loss: 0.051375675946474075
2023-01-23 02:51:24.536307: step: 744/529, loss: 0.015016174875199795
2023-01-23 02:51:25.747213: step: 748/529, loss: 0.012148857116699219
2023-01-23 02:51:26.992174: step: 752/529, loss: 0.057822417467832565
2023-01-23 02:51:28.242721: step: 756/529, loss: 0.028007127344608307
2023-01-23 02:51:29.397506: step: 760/529, loss: 0.0005052089691162109
2023-01-23 02:51:30.610485: step: 764/529, loss: 0.002269458957016468
2023-01-23 02:51:31.847287: step: 768/529, loss: 6.842613220214844e-05
2023-01-23 02:51:33.019597: step: 772/529, loss: 0.0006751060136593878
2023-01-23 02:51:34.252754: step: 776/529, loss: 0.0009168624528683722
2023-01-23 02:51:35.429609: step: 780/529, loss: 0.007680845446884632
2023-01-23 02:51:36.591223: step: 784/529, loss: 0.004424571990966797
2023-01-23 02:51:37.808745: step: 788/529, loss: 0.006457233801484108
2023-01-23 02:51:39.017796: step: 792/529, loss: 0.0023097037337720394
2023-01-23 02:51:40.220870: step: 796/529, loss: 0.014001274481415749
2023-01-23 02:51:41.399741: step: 800/529, loss: 0.001825094223022461
2023-01-23 02:51:42.601623: step: 804/529, loss: 0.15867634117603302
2023-01-23 02:51:43.862390: step: 808/529, loss: 0.006685495376586914
2023-01-23 02:51:45.038808: step: 812/529, loss: 0.34852904081344604
2023-01-23 02:51:46.299652: step: 816/529, loss: 0.009759140200912952
2023-01-23 02:51:47.481932: step: 820/529, loss: 0.007753563113510609
2023-01-23 02:51:48.679503: step: 824/529, loss: 0.004956340882927179
2023-01-23 02:51:49.888866: step: 828/529, loss: 0.015973662957549095
2023-01-23 02:51:51.062964: step: 832/529, loss: 0.002685642335563898
2023-01-23 02:51:52.216556: step: 836/529, loss: 0.0029163360595703125
2023-01-23 02:51:53.422459: step: 840/529, loss: 0.00093669886700809
2023-01-23 02:51:54.628859: step: 844/529, loss: 0.03747301176190376
2023-01-23 02:51:55.843634: step: 848/529, loss: 0.021499251946806908
2023-01-23 02:51:57.009769: step: 852/529, loss: 0.000241184257902205
2023-01-23 02:51:58.203035: step: 856/529, loss: 0.03581847995519638
2023-01-23 02:51:59.346514: step: 860/529, loss: 0.0035420418716967106
2023-01-23 02:52:00.581172: step: 864/529, loss: 0.024512864649295807
2023-01-23 02:52:01.754392: step: 868/529, loss: 0.006778290029615164
2023-01-23 02:52:02.906874: step: 872/529, loss: 0.0019012452103197575
2023-01-23 02:52:04.086898: step: 876/529, loss: 0.0024512293748557568
2023-01-23 02:52:05.290873: step: 880/529, loss: 0.001793003175407648
2023-01-23 02:52:06.501993: step: 884/529, loss: 0.05764207988977432
2023-01-23 02:52:07.724689: step: 888/529, loss: 0.01868429221212864
2023-01-23 02:52:08.922418: step: 892/529, loss: 0.00026149750920012593
2023-01-23 02:52:10.110580: step: 896/529, loss: 0.0016706467140465975
2023-01-23 02:52:11.264287: step: 900/529, loss: 0.0296328067779541
2023-01-23 02:52:12.453440: step: 904/529, loss: 0.034564971923828125
2023-01-23 02:52:13.629405: step: 908/529, loss: 0.04131045192480087
2023-01-23 02:52:14.806135: step: 912/529, loss: 0.009833813644945621
2023-01-23 02:52:15.960775: step: 916/529, loss: 0.019705582410097122
2023-01-23 02:52:17.178981: step: 920/529, loss: 0.013294219970703125
2023-01-23 02:52:18.378477: step: 924/529, loss: 0.04758806526660919
2023-01-23 02:52:19.596732: step: 928/529, loss: 0.22303810715675354
2023-01-23 02:52:20.780358: step: 932/529, loss: 0.07901981472969055
2023-01-23 02:52:21.963013: step: 936/529, loss: 0.0025468827225267887
2023-01-23 02:52:23.169418: step: 940/529, loss: 0.0006996154552325606
2023-01-23 02:52:24.413625: step: 944/529, loss: 0.028627874329686165
2023-01-23 02:52:25.611306: step: 948/529, loss: 0.004445123486220837
2023-01-23 02:52:26.815132: step: 952/529, loss: 0.013493537902832031
2023-01-23 02:52:27.982949: step: 956/529, loss: 0.019879436120390892
2023-01-23 02:52:29.203255: step: 960/529, loss: 0.05215025320649147
2023-01-23 02:52:30.423985: step: 964/529, loss: 0.000286102294921875
2023-01-23 02:52:31.654551: step: 968/529, loss: 0.03295727074146271
2023-01-23 02:52:32.875952: step: 972/529, loss: 0.005147552117705345
2023-01-23 02:52:34.052215: step: 976/529, loss: 0.00522613525390625
2023-01-23 02:52:35.227826: step: 980/529, loss: 0.0008656025165691972
2023-01-23 02:52:36.423991: step: 984/529, loss: 0.00034236907958984375
2023-01-23 02:52:37.627850: step: 988/529, loss: 0.024534225463867188
2023-01-23 02:52:38.794612: step: 992/529, loss: 0.01809110678732395
2023-01-23 02:52:39.990791: step: 996/529, loss: 0.01804046705365181
2023-01-23 02:52:41.197360: step: 1000/529, loss: 0.02171487733721733
2023-01-23 02:52:42.398914: step: 1004/529, loss: 0.04370298236608505
2023-01-23 02:52:43.607492: step: 1008/529, loss: 0.022652246057987213
2023-01-23 02:52:44.803023: step: 1012/529, loss: 0.00015854835510253906
2023-01-23 02:52:46.035154: step: 1016/529, loss: 0.010126590728759766
2023-01-23 02:52:47.234020: step: 1020/529, loss: 0.02750396728515625
2023-01-23 02:52:48.391526: step: 1024/529, loss: 0.0030849457252770662
2023-01-23 02:52:49.601679: step: 1028/529, loss: 0.021029474213719368
2023-01-23 02:52:50.807734: step: 1032/529, loss: 0.0019851208198815584
2023-01-23 02:52:52.059804: step: 1036/529, loss: 0.0017242431640625
2023-01-23 02:52:53.290454: step: 1040/529, loss: 0.05150318518280983
2023-01-23 02:52:54.473877: step: 1044/529, loss: 0.046482231467962265
2023-01-23 02:52:55.655320: step: 1048/529, loss: 0.03938732296228409
2023-01-23 02:52:56.859130: step: 1052/529, loss: 0.004544639959931374
2023-01-23 02:52:58.070692: step: 1056/529, loss: 0.012930489145219326
2023-01-23 02:52:59.266877: step: 1060/529, loss: 0.06606350094079971
2023-01-23 02:53:00.469779: step: 1064/529, loss: 0.13102301955223083
2023-01-23 02:53:01.651248: step: 1068/529, loss: 0.018883515149354935
2023-01-23 02:53:02.844843: step: 1072/529, loss: 0.00043230055598542094
2023-01-23 02:53:04.052495: step: 1076/529, loss: 0.061090562492609024
2023-01-23 02:53:05.251006: step: 1080/529, loss: 0.01868267171084881
2023-01-23 02:53:06.431527: step: 1084/529, loss: 0.02054271660745144
2023-01-23 02:53:07.613065: step: 1088/529, loss: 0.014475250616669655
2023-01-23 02:53:08.801888: step: 1092/529, loss: 0.013321589678525925
2023-01-23 02:53:10.003025: step: 1096/529, loss: 0.0029973508790135384
2023-01-23 02:53:11.199240: step: 1100/529, loss: 0.05721712112426758
2023-01-23 02:53:12.406529: step: 1104/529, loss: 0.0016152382595464587
2023-01-23 02:53:13.648036: step: 1108/529, loss: 0.007339096628129482
2023-01-23 02:53:14.839370: step: 1112/529, loss: 0.01019744947552681
2023-01-23 02:53:16.045747: step: 1116/529, loss: 0.016485881060361862
2023-01-23 02:53:17.205866: step: 1120/529, loss: 0.004796076100319624
2023-01-23 02:53:18.427324: step: 1124/529, loss: 0.0078108785673975945
2023-01-23 02:53:19.646875: step: 1128/529, loss: 0.005593681707978249
2023-01-23 02:53:20.855042: step: 1132/529, loss: 0.04302167892456055
2023-01-23 02:53:22.045179: step: 1136/529, loss: 0.0029899119399487972
2023-01-23 02:53:23.216996: step: 1140/529, loss: 0.0039408206939697266
2023-01-23 02:53:24.420410: step: 1144/529, loss: 0.015243053436279297
2023-01-23 02:53:25.616503: step: 1148/529, loss: 0.008402634412050247
2023-01-23 02:53:26.849828: step: 1152/529, loss: 0.0356656089425087
2023-01-23 02:53:28.016611: step: 1156/529, loss: 0.02371673658490181
2023-01-23 02:53:29.245479: step: 1160/529, loss: 0.004023551940917969
2023-01-23 02:53:30.433611: step: 1164/529, loss: 0.0035541534889489412
2023-01-23 02:53:31.697702: step: 1168/529, loss: 0.0019771575462073088
2023-01-23 02:53:32.906129: step: 1172/529, loss: 0.012814903631806374
2023-01-23 02:53:34.104230: step: 1176/529, loss: 0.00015735626220703125
2023-01-23 02:53:35.289889: step: 1180/529, loss: 0.005934262182563543
2023-01-23 02:53:36.458071: step: 1184/529, loss: 4.7492983867414296e-05
2023-01-23 02:53:37.700125: step: 1188/529, loss: 0.000568389892578125
2023-01-23 02:53:38.860569: step: 1192/529, loss: 0.0047317505814135075
2023-01-23 02:53:39.996981: step: 1196/529, loss: 0.0015502930618822575
2023-01-23 02:53:41.209793: step: 1200/529, loss: 0.04354400932788849
2023-01-23 02:53:42.388470: step: 1204/529, loss: 0.0015049935318529606
2023-01-23 02:53:43.566675: step: 1208/529, loss: 0.01749744452536106
2023-01-23 02:53:44.761246: step: 1212/529, loss: 0.1285255402326584
2023-01-23 02:53:45.921184: step: 1216/529, loss: 0.00011482239642646164
2023-01-23 02:53:47.075073: step: 1220/529, loss: 0.007799911312758923
2023-01-23 02:53:48.252913: step: 1224/529, loss: 0.00016622543625999242
2023-01-23 02:53:49.378740: step: 1228/529, loss: 0.0008256912115029991
2023-01-23 02:53:50.555737: step: 1232/529, loss: 0.008492779918015003
2023-01-23 02:53:51.772711: step: 1236/529, loss: 0.0019851685501635075
2023-01-23 02:53:52.940503: step: 1240/529, loss: 0.060060691088438034
2023-01-23 02:53:54.179506: step: 1244/529, loss: 0.0013676644302904606
2023-01-23 02:53:55.402411: step: 1248/529, loss: 0.03038635291159153
2023-01-23 02:53:56.644954: step: 1252/529, loss: 0.046868182718753815
2023-01-23 02:53:57.859338: step: 1256/529, loss: 0.046543315052986145
2023-01-23 02:53:59.118400: step: 1260/529, loss: 0.00159120571333915
2023-01-23 02:54:00.305087: step: 1264/529, loss: 0.0002974033122882247
2023-01-23 02:54:01.512718: step: 1268/529, loss: 0.009661865420639515
2023-01-23 02:54:02.740417: step: 1272/529, loss: 0.028136014938354492
2023-01-23 02:54:03.914944: step: 1276/529, loss: 0.00021605491929221898
2023-01-23 02:54:05.132582: step: 1280/529, loss: 0.009549331851303577
2023-01-23 02:54:06.354233: step: 1284/529, loss: 0.009549617767333984
2023-01-23 02:54:07.526782: step: 1288/529, loss: 0.00022563934908248484
2023-01-23 02:54:08.781362: step: 1292/529, loss: 0.006129646208137274
2023-01-23 02:54:09.972501: step: 1296/529, loss: 4.2343137465650216e-05
2023-01-23 02:54:11.174495: step: 1300/529, loss: 0.0018351555336266756
2023-01-23 02:54:12.409038: step: 1304/529, loss: 0.001064300537109375
2023-01-23 02:54:13.634383: step: 1308/529, loss: 0.047364044934511185
2023-01-23 02:54:14.818653: step: 1312/529, loss: 0.027245236560702324
2023-01-23 02:54:16.020858: step: 1316/529, loss: 0.04909687116742134
2023-01-23 02:54:17.221270: step: 1320/529, loss: 0.008952331729233265
2023-01-23 02:54:18.450725: step: 1324/529, loss: 0.008603191934525967
2023-01-23 02:54:19.675935: step: 1328/529, loss: 0.006449508480727673
2023-01-23 02:54:20.904620: step: 1332/529, loss: 0.007208824623376131
2023-01-23 02:54:22.135036: step: 1336/529, loss: 0.0018554687267169356
2023-01-23 02:54:23.335828: step: 1340/529, loss: 0.013210153207182884
2023-01-23 02:54:24.548921: step: 1344/529, loss: 0.03131254017353058
2023-01-23 02:54:25.778077: step: 1348/529, loss: 0.021416282281279564
2023-01-23 02:54:26.983681: step: 1352/529, loss: 0.021112823858857155
2023-01-23 02:54:28.183337: step: 1356/529, loss: 0.024181555956602097
2023-01-23 02:54:29.387061: step: 1360/529, loss: 0.0011964797740802169
2023-01-23 02:54:30.591482: step: 1364/529, loss: 0.0003619194030761719
2023-01-23 02:54:31.779348: step: 1368/529, loss: 0.03746175765991211
2023-01-23 02:54:33.013199: step: 1372/529, loss: 0.002320241881534457
2023-01-23 02:54:34.192395: step: 1376/529, loss: 0.03711114078760147
2023-01-23 02:54:35.399077: step: 1380/529, loss: 0.03472557291388512
2023-01-23 02:54:36.580803: step: 1384/529, loss: 0.004736900329589844
2023-01-23 02:54:37.814832: step: 1388/529, loss: 0.0034609795548021793
2023-01-23 02:54:39.067378: step: 1392/529, loss: 0.0391940101981163
2023-01-23 02:54:40.271449: step: 1396/529, loss: 0.006446361541748047
2023-01-23 02:54:41.486941: step: 1400/529, loss: 0.0011011123424395919
2023-01-23 02:54:42.718018: step: 1404/529, loss: 0.02707061730325222
2023-01-23 02:54:43.909731: step: 1408/529, loss: 0.008593464270234108
2023-01-23 02:54:45.144198: step: 1412/529, loss: 0.005849075503647327
2023-01-23 02:54:46.311262: step: 1416/529, loss: 0.008972168900072575
2023-01-23 02:54:47.492615: step: 1420/529, loss: 0.047736648470163345
2023-01-23 02:54:48.734044: step: 1424/529, loss: 0.0008117676479741931
2023-01-23 02:54:49.950584: step: 1428/529, loss: 0.026935484260320663
2023-01-23 02:54:51.156697: step: 1432/529, loss: 0.041068557649850845
2023-01-23 02:54:52.348188: step: 1436/529, loss: 0.00026874541072174907
2023-01-23 02:54:53.517786: step: 1440/529, loss: 0.031628336757421494
2023-01-23 02:54:54.688402: step: 1444/529, loss: 0.006427955813705921
2023-01-23 02:54:55.916442: step: 1448/529, loss: 0.005690575111657381
2023-01-23 02:54:57.101039: step: 1452/529, loss: 0.0006567955133505166
2023-01-23 02:54:58.283554: step: 1456/529, loss: 0.0030237198807299137
2023-01-23 02:54:59.426928: step: 1460/529, loss: 0.0068683624267578125
2023-01-23 02:55:00.645768: step: 1464/529, loss: 0.0023954391945153475
2023-01-23 02:55:01.875570: step: 1468/529, loss: 0.003706264542415738
2023-01-23 02:55:03.079230: step: 1472/529, loss: 0.010748482309281826
2023-01-23 02:55:04.319610: step: 1476/529, loss: 0.018119478598237038
2023-01-23 02:55:05.455542: step: 1480/529, loss: 0.010569977574050426
2023-01-23 02:55:06.646687: step: 1484/529, loss: 0.04724063724279404
2023-01-23 02:55:07.811652: step: 1488/529, loss: 1.792907642084174e-05
2023-01-23 02:55:08.985894: step: 1492/529, loss: 0.0736178383231163
2023-01-23 02:55:10.175867: step: 1496/529, loss: 0.00263385777361691
2023-01-23 02:55:11.366655: step: 1500/529, loss: 0.000102996826171875
2023-01-23 02:55:12.555841: step: 1504/529, loss: 0.08344592899084091
2023-01-23 02:55:13.729380: step: 1508/529, loss: 0.008185386657714844
2023-01-23 02:55:14.937841: step: 1512/529, loss: 0.02715597115457058
2023-01-23 02:55:16.105918: step: 1516/529, loss: 0.004849815275520086
2023-01-23 02:55:17.295370: step: 1520/529, loss: 0.005395602900534868
2023-01-23 02:55:18.483614: step: 1524/529, loss: 0.004115152172744274
2023-01-23 02:55:19.674177: step: 1528/529, loss: 0.0003519534948281944
2023-01-23 02:55:20.894154: step: 1532/529, loss: 0.3924638628959656
2023-01-23 02:55:22.081647: step: 1536/529, loss: 0.0459442175924778
2023-01-23 02:55:23.325264: step: 1540/529, loss: 0.2564008831977844
2023-01-23 02:55:24.532755: step: 1544/529, loss: 0.0105011947453022
2023-01-23 02:55:25.694927: step: 1548/529, loss: 0.0003972053527832031
2023-01-23 02:55:26.877313: step: 1552/529, loss: 0.0016611098544672132
2023-01-23 02:55:28.063816: step: 1556/529, loss: 0.0011737823951989412
2023-01-23 02:55:29.272418: step: 1560/529, loss: 0.009410095401108265
2023-01-23 02:55:30.488129: step: 1564/529, loss: 0.03652916103601456
2023-01-23 02:55:31.677199: step: 1568/529, loss: 0.019153403118252754
2023-01-23 02:55:32.849232: step: 1572/529, loss: 0.07477583736181259
2023-01-23 02:55:34.056328: step: 1576/529, loss: 0.03913898766040802
2023-01-23 02:55:35.245873: step: 1580/529, loss: 0.008938598446547985
2023-01-23 02:55:36.440556: step: 1584/529, loss: 0.0014506339794024825
2023-01-23 02:55:37.632708: step: 1588/529, loss: 9.212493750965223e-05
2023-01-23 02:55:38.806523: step: 1592/529, loss: 0.0002627372741699219
2023-01-23 02:55:40.027090: step: 1596/529, loss: 0.036153409630060196
2023-01-23 02:55:41.235389: step: 1600/529, loss: 0.024897100403904915
2023-01-23 02:55:42.421030: step: 1604/529, loss: 0.0018195391166955233
2023-01-23 02:55:43.585733: step: 1608/529, loss: 0.0006594657897949219
2023-01-23 02:55:44.795559: step: 1612/529, loss: 0.018125344067811966
2023-01-23 02:55:45.981655: step: 1616/529, loss: 0.023831749334931374
2023-01-23 02:55:47.183276: step: 1620/529, loss: 0.7519766688346863
2023-01-23 02:55:48.359725: step: 1624/529, loss: 0.012073611840605736
2023-01-23 02:55:49.577062: step: 1628/529, loss: 0.021049117669463158
2023-01-23 02:55:50.785581: step: 1632/529, loss: 3.356933666509576e-05
2023-01-23 02:55:51.982628: step: 1636/529, loss: 0.012299228459596634
2023-01-23 02:55:53.204277: step: 1640/529, loss: 0.03125343099236488
2023-01-23 02:55:54.399925: step: 1644/529, loss: 0.03994322195649147
2023-01-23 02:55:55.604526: step: 1648/529, loss: 0.010166454128921032
2023-01-23 02:55:56.779882: step: 1652/529, loss: 0.011269474402070045
2023-01-23 02:55:57.967936: step: 1656/529, loss: 0.004206943325698376
2023-01-23 02:55:59.235244: step: 1660/529, loss: 0.015709497034549713
2023-01-23 02:56:00.439783: step: 1664/529, loss: 0.08432827144861221
2023-01-23 02:56:01.643960: step: 1668/529, loss: 0.03844795376062393
2023-01-23 02:56:02.836218: step: 1672/529, loss: 0.007732391357421875
2023-01-23 02:56:04.038684: step: 1676/529, loss: 0.0016179084777832031
2023-01-23 02:56:05.242153: step: 1680/529, loss: 0.009468006901443005
2023-01-23 02:56:06.426636: step: 1684/529, loss: 0.0014778138138353825
2023-01-23 02:56:07.753371: step: 1688/529, loss: 0.20578722655773163
2023-01-23 02:56:08.962377: step: 1692/529, loss: 0.01151266135275364
2023-01-23 02:56:10.183946: step: 1696/529, loss: 0.010944557376205921
2023-01-23 02:56:11.422609: step: 1700/529, loss: 0.05595417320728302
2023-01-23 02:56:12.604549: step: 1704/529, loss: 0.018660927191376686
2023-01-23 02:56:13.769003: step: 1708/529, loss: 0.0008911133045330644
2023-01-23 02:56:14.996767: step: 1712/529, loss: 0.06262359023094177
2023-01-23 02:56:16.185148: step: 1716/529, loss: 0.0032632825896143913
2023-01-23 02:56:17.397324: step: 1720/529, loss: 0.006718921475112438
2023-01-23 02:56:18.700361: step: 1724/529, loss: 0.0031825066544115543
2023-01-23 02:56:19.940916: step: 1728/529, loss: 0.030719662085175514
2023-01-23 02:56:21.143642: step: 1732/529, loss: 0.022855568677186966
2023-01-23 02:56:22.326519: step: 1736/529, loss: 0.011527299880981445
2023-01-23 02:56:23.515506: step: 1740/529, loss: 0.028424454852938652
2023-01-23 02:56:24.686742: step: 1744/529, loss: 0.00027675629826262593
2023-01-23 02:56:25.900545: step: 1748/529, loss: 0.011684417724609375
2023-01-23 02:56:27.156006: step: 1752/529, loss: 0.08835625648498535
2023-01-23 02:56:28.334450: step: 1756/529, loss: 0.08548679947853088
2023-01-23 02:56:29.512965: step: 1760/529, loss: 0.003707838011905551
2023-01-23 02:56:30.696065: step: 1764/529, loss: 0.0014142035506665707
2023-01-23 02:56:31.942408: step: 1768/529, loss: 0.010040379129350185
2023-01-23 02:56:33.166384: step: 1772/529, loss: 0.011329079046845436
2023-01-23 02:56:34.383594: step: 1776/529, loss: 0.009504318237304688
2023-01-23 02:56:35.577730: step: 1780/529, loss: 0.09586277604103088
2023-01-23 02:56:36.767255: step: 1784/529, loss: 0.044762708246707916
2023-01-23 02:56:37.974800: step: 1788/529, loss: 0.009194565005600452
2023-01-23 02:56:39.168648: step: 1792/529, loss: 0.019130611792206764
2023-01-23 02:56:40.403065: step: 1796/529, loss: 0.032532550394535065
2023-01-23 02:56:41.590611: step: 1800/529, loss: 0.002416324568912387
2023-01-23 02:56:42.775505: step: 1804/529, loss: 0.12907905876636505
2023-01-23 02:56:43.967663: step: 1808/529, loss: 0.001695060869678855
2023-01-23 02:56:45.180238: step: 1812/529, loss: 0.026753615587949753
2023-01-23 02:56:46.372695: step: 1816/529, loss: 0.044733572751283646
2023-01-23 02:56:47.606338: step: 1820/529, loss: 0.017317676916718483
2023-01-23 02:56:48.814408: step: 1824/529, loss: 0.040297508239746094
2023-01-23 02:56:49.990561: step: 1828/529, loss: 0.02081015147268772
2023-01-23 02:56:51.164904: step: 1832/529, loss: 0.00019874573627021164
2023-01-23 02:56:52.386608: step: 1836/529, loss: 0.015726901590824127
2023-01-23 02:56:53.591230: step: 1840/529, loss: 0.010347366333007812
2023-01-23 02:56:54.787706: step: 1844/529, loss: 0.00031410454539582133
2023-01-23 02:56:55.951830: step: 1848/529, loss: 0.012937640771269798
2023-01-23 02:56:57.150584: step: 1852/529, loss: 0.0008021831745281816
2023-01-23 02:56:58.333855: step: 1856/529, loss: 0.02051115222275257
2023-01-23 02:56:59.543375: step: 1860/529, loss: 0.020203400403261185
2023-01-23 02:57:00.709946: step: 1864/529, loss: 0.002439212752506137
2023-01-23 02:57:01.886732: step: 1868/529, loss: 0.0023755072616040707
2023-01-23 02:57:03.090674: step: 1872/529, loss: 0.016912128776311874
2023-01-23 02:57:04.309299: step: 1876/529, loss: 0.05541591718792915
2023-01-23 02:57:05.491360: step: 1880/529, loss: 0.010518074035644531
2023-01-23 02:57:06.729906: step: 1884/529, loss: 0.005601120181381702
2023-01-23 02:57:07.935639: step: 1888/529, loss: 0.00017547607421875
2023-01-23 02:57:09.127021: step: 1892/529, loss: 0.009705543518066406
2023-01-23 02:57:10.289058: step: 1896/529, loss: 1.3732910701946821e-05
2023-01-23 02:57:11.459811: step: 1900/529, loss: 0.0019033431308344007
2023-01-23 02:57:12.644764: step: 1904/529, loss: 0.03345794975757599
2023-01-23 02:57:13.833778: step: 1908/529, loss: 7.83920258982107e-05
2023-01-23 02:57:15.015706: step: 1912/529, loss: 0.0019386291969567537
2023-01-23 02:57:16.188173: step: 1916/529, loss: 0.017402220517396927
2023-01-23 02:57:17.362626: step: 1920/529, loss: 0.03869824483990669
2023-01-23 02:57:18.619049: step: 1924/529, loss: 0.0214520450681448
2023-01-23 02:57:19.839991: step: 1928/529, loss: 0.0009203911176882684
2023-01-23 02:57:21.054235: step: 1932/529, loss: 0.06093807518482208
2023-01-23 02:57:22.220616: step: 1936/529, loss: 0.0027781487442553043
2023-01-23 02:57:23.413536: step: 1940/529, loss: 0.0013230800395831466
2023-01-23 02:57:24.619458: step: 1944/529, loss: 0.00035896303597837687
2023-01-23 02:57:25.781309: step: 1948/529, loss: 0.049846649169921875
2023-01-23 02:57:26.966035: step: 1952/529, loss: 0.0010044098598882556
2023-01-23 02:57:28.203715: step: 1956/529, loss: 0.0958099439740181
2023-01-23 02:57:29.417303: step: 1960/529, loss: 0.00028228759765625
2023-01-23 02:57:30.598621: step: 1964/529, loss: 0.029911233112215996
2023-01-23 02:57:31.778327: step: 1968/529, loss: 0.0011051774490624666
2023-01-23 02:57:32.984342: step: 1972/529, loss: 0.0001562118559377268
2023-01-23 02:57:34.182645: step: 1976/529, loss: 0.006267261691391468
2023-01-23 02:57:35.389165: step: 1980/529, loss: 0.0007879257318563759
2023-01-23 02:57:36.599751: step: 1984/529, loss: 0.0077056884765625
2023-01-23 02:57:37.851649: step: 1988/529, loss: 0.003443432040512562
2023-01-23 02:57:39.057685: step: 1992/529, loss: 0.02061910554766655
2023-01-23 02:57:40.351951: step: 1996/529, loss: 0.00135040283203125
2023-01-23 02:57:41.552887: step: 2000/529, loss: 0.04771852120757103
2023-01-23 02:57:42.780882: step: 2004/529, loss: 0.007236003875732422
2023-01-23 02:57:43.958439: step: 2008/529, loss: 0.0054528238251805305
2023-01-23 02:57:45.108566: step: 2012/529, loss: 0.03294019773602486
2023-01-23 02:57:46.270839: step: 2016/529, loss: 9.13620024221018e-05
2023-01-23 02:57:47.472567: step: 2020/529, loss: 0.010421467013657093
2023-01-23 02:57:48.655717: step: 2024/529, loss: 0.020175648853182793
2023-01-23 02:57:49.862196: step: 2028/529, loss: 0.01042032241821289
2023-01-23 02:57:51.069900: step: 2032/529, loss: 0.014084530994296074
2023-01-23 02:57:52.258914: step: 2036/529, loss: 0.02331419102847576
2023-01-23 02:57:53.495723: step: 2040/529, loss: 0.04138088598847389
2023-01-23 02:57:54.699923: step: 2044/529, loss: 0.007630777545273304
2023-01-23 02:57:55.898762: step: 2048/529, loss: 0.0072886464186012745
2023-01-23 02:57:57.100326: step: 2052/529, loss: 0.005963707342743874
2023-01-23 02:57:58.282607: step: 2056/529, loss: 0.024396324530243874
2023-01-23 02:57:59.446789: step: 2060/529, loss: 0.023745249956846237
2023-01-23 02:58:00.661456: step: 2064/529, loss: 0.005225372035056353
2023-01-23 02:58:01.813188: step: 2068/529, loss: 0.01992173306643963
2023-01-23 02:58:03.022114: step: 2072/529, loss: 0.3842557966709137
2023-01-23 02:58:04.186481: step: 2076/529, loss: 0.000415802001953125
2023-01-23 02:58:05.386550: step: 2080/529, loss: 0.039803698658943176
2023-01-23 02:58:06.617159: step: 2084/529, loss: 0.0005195617559365928
2023-01-23 02:58:07.807258: step: 2088/529, loss: 0.0003741264226846397
2023-01-23 02:58:09.017235: step: 2092/529, loss: 0.03693675994873047
2023-01-23 02:58:10.222900: step: 2096/529, loss: 0.005920505616813898
2023-01-23 02:58:11.415781: step: 2100/529, loss: 0.029214000329375267
2023-01-23 02:58:12.618636: step: 2104/529, loss: 0.0033657075837254524
2023-01-23 02:58:13.827499: step: 2108/529, loss: 0.04295841604471207
2023-01-23 02:58:15.063667: step: 2112/529, loss: 0.04494164139032364
2023-01-23 02:58:16.252159: step: 2116/529, loss: 0.0019300461281090975
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.6002066115702479, 'r': 0.7736351531291611, 'f1': 0.6759744037230948}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6511056511056511, 'r': 0.7938885560215698, 'f1': 0.7154427645788337}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5949367088607594, 'r': 0.8703703703703703, 'f1': 0.706766917293233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.5636363636363636, 'r': 0.49206349206349204, 'f1': 0.5254237288135594}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 02:58:59.758673: step: 4/529, loss: 0.042935751378536224
2023-01-23 02:59:00.905244: step: 8/529, loss: 0.004815959837287664
2023-01-23 02:59:02.090308: step: 12/529, loss: 0.005259990692138672
2023-01-23 02:59:03.344948: step: 16/529, loss: 0.6996700167655945
2023-01-23 02:59:04.564610: step: 20/529, loss: 0.06484298408031464
2023-01-23 02:59:05.750906: step: 24/529, loss: 0.0007749557844363153
2023-01-23 02:59:06.919472: step: 28/529, loss: 0.017015792429447174
2023-01-23 02:59:08.111975: step: 32/529, loss: 0.0003442764573264867
2023-01-23 02:59:09.288591: step: 36/529, loss: 0.002808952471241355
2023-01-23 02:59:10.521153: step: 40/529, loss: 0.006525897886604071
2023-01-23 02:59:11.732062: step: 44/529, loss: 0.028618622571229935
2023-01-23 02:59:12.912039: step: 48/529, loss: 0.0017216682899743319
2023-01-23 02:59:14.107016: step: 52/529, loss: 0.019769860431551933
2023-01-23 02:59:15.341369: step: 56/529, loss: 3.2424923119833693e-06
2023-01-23 02:59:16.509884: step: 60/529, loss: 0.0063193319365382195
2023-01-23 02:59:17.734798: step: 64/529, loss: 0.00045680999755859375
2023-01-23 02:59:18.922446: step: 68/529, loss: 0.0002552986261434853
2023-01-23 02:59:20.086450: step: 72/529, loss: 0.06339512020349503
2023-01-23 02:59:21.256557: step: 76/529, loss: 0.006579685024917126
2023-01-23 02:59:22.413629: step: 80/529, loss: 0.00028629304142668843
2023-01-23 02:59:23.631003: step: 84/529, loss: 0.0038661002181470394
2023-01-23 02:59:24.838005: step: 88/529, loss: 0.0009481430170126259
2023-01-23 02:59:26.054183: step: 92/529, loss: 0.0023017884232103825
2023-01-23 02:59:27.226115: step: 96/529, loss: 0.0019096970790997148
2023-01-23 02:59:28.411079: step: 100/529, loss: 0.00011987685866188258
2023-01-23 02:59:29.607819: step: 104/529, loss: 0.009096241556107998
2023-01-23 02:59:30.826578: step: 108/529, loss: 0.0023687363136559725
2023-01-23 02:59:32.094462: step: 112/529, loss: 0.015666484832763672
2023-01-23 02:59:33.287103: step: 116/529, loss: 0.010844516567885876
2023-01-23 02:59:34.506740: step: 120/529, loss: 0.00016021728515625
2023-01-23 02:59:35.701283: step: 124/529, loss: 0.00017271040997002274
2023-01-23 02:59:36.944506: step: 128/529, loss: 0.014075851067900658
2023-01-23 02:59:38.165486: step: 132/529, loss: 0.0013660431141033769
2023-01-23 02:59:39.350806: step: 136/529, loss: 1.9168852304574102e-05
2023-01-23 02:59:40.534515: step: 140/529, loss: 0.0013269424671307206
2023-01-23 02:59:41.763915: step: 144/529, loss: 0.005456352140754461
2023-01-23 02:59:42.983951: step: 148/529, loss: 0.001750087714754045
2023-01-23 02:59:44.172604: step: 152/529, loss: 0.026131058111786842
2023-01-23 02:59:45.404990: step: 156/529, loss: 0.04542860761284828
2023-01-23 02:59:46.644766: step: 160/529, loss: 4.386902219266631e-06
2023-01-23 02:59:47.887685: step: 164/529, loss: 0.009830665774643421
2023-01-23 02:59:49.089784: step: 168/529, loss: 0.0005489349132403731
2023-01-23 02:59:50.288189: step: 172/529, loss: 0.007158470340073109
2023-01-23 02:59:51.488140: step: 176/529, loss: 0.008014869876205921
2023-01-23 02:59:52.689336: step: 180/529, loss: 0.035913754254579544
2023-01-23 02:59:53.891422: step: 184/529, loss: 0.02865428850054741
2023-01-23 02:59:55.085308: step: 188/529, loss: 0.10077238082885742
2023-01-23 02:59:56.267732: step: 192/529, loss: 0.004261970520019531
2023-01-23 02:59:57.496380: step: 196/529, loss: 0.000240325927734375
2023-01-23 02:59:58.728912: step: 200/529, loss: 0.011649513617157936
2023-01-23 02:59:59.944249: step: 204/529, loss: 0.0006336212391033769
2023-01-23 03:00:01.115551: step: 208/529, loss: 0.01825389824807644
2023-01-23 03:00:02.345230: step: 212/529, loss: 0.0030647278763353825
2023-01-23 03:00:03.551333: step: 216/529, loss: 0.01799612119793892
2023-01-23 03:00:04.721964: step: 220/529, loss: 0.040863037109375
2023-01-23 03:00:05.926416: step: 224/529, loss: 0.01732940785586834
2023-01-23 03:00:07.106325: step: 228/529, loss: 0.007949638180434704
2023-01-23 03:00:08.311903: step: 232/529, loss: 0.025159548968076706
2023-01-23 03:00:09.524672: step: 236/529, loss: 0.028084373101592064
2023-01-23 03:00:10.700433: step: 240/529, loss: 0.009926891885697842
2023-01-23 03:00:11.889398: step: 244/529, loss: 0.004693221766501665
2023-01-23 03:00:13.045417: step: 248/529, loss: 0.007546487729996443
2023-01-23 03:00:14.227085: step: 252/529, loss: 0.00022850035747978836
2023-01-23 03:00:15.456444: step: 256/529, loss: 0.0015692710876464844
2023-01-23 03:00:16.633608: step: 260/529, loss: 0.021524859592318535
2023-01-23 03:00:17.853778: step: 264/529, loss: 0.0020837783813476562
2023-01-23 03:00:19.034395: step: 268/529, loss: 0.000560379063244909
2023-01-23 03:00:20.204158: step: 272/529, loss: 0.0011016845237463713
2023-01-23 03:00:21.383177: step: 276/529, loss: 0.0015305518172681332
2023-01-23 03:00:22.545068: step: 280/529, loss: 0.0006735801580362022
2023-01-23 03:00:23.726829: step: 284/529, loss: 0.0008599281427450478
2023-01-23 03:00:24.963750: step: 288/529, loss: 0.010336684994399548
2023-01-23 03:00:26.165758: step: 292/529, loss: 0.0006685256958007812
2023-01-23 03:00:27.356619: step: 296/529, loss: 0.0060256957076489925
2023-01-23 03:00:28.531309: step: 300/529, loss: 0.000815963780041784
2023-01-23 03:00:29.706352: step: 304/529, loss: 0.02645416185259819
2023-01-23 03:00:30.910953: step: 308/529, loss: 0.01834697835147381
2023-01-23 03:00:32.141084: step: 312/529, loss: 0.008624554611742496
2023-01-23 03:00:33.350142: step: 316/529, loss: 0.007229137234389782
2023-01-23 03:00:34.595801: step: 320/529, loss: 0.008791828528046608
2023-01-23 03:00:35.790504: step: 324/529, loss: 7.247925168485381e-06
2023-01-23 03:00:37.006168: step: 328/529, loss: 0.04197730869054794
2023-01-23 03:00:38.233818: step: 332/529, loss: 0.015083122067153454
2023-01-23 03:00:39.436616: step: 336/529, loss: 0.00303230294957757
2023-01-23 03:00:40.633092: step: 340/529, loss: 0.00012350082397460938
2023-01-23 03:00:41.856064: step: 344/529, loss: 0.000244140625
2023-01-23 03:00:43.044492: step: 348/529, loss: 0.0011779784690588713
2023-01-23 03:00:44.218597: step: 352/529, loss: 0.0009716034401208162
2023-01-23 03:00:45.403037: step: 356/529, loss: 0.024477768689393997
2023-01-23 03:00:46.602696: step: 360/529, loss: 0.005537224002182484
2023-01-23 03:00:47.788924: step: 364/529, loss: 0.0011005401611328125
2023-01-23 03:00:49.008253: step: 368/529, loss: 0.0023327828384935856
2023-01-23 03:00:50.251378: step: 372/529, loss: 0.012629889883100986
2023-01-23 03:00:51.452746: step: 376/529, loss: 0.000884628330823034
2023-01-23 03:00:52.656297: step: 380/529, loss: 0.0020687105134129524
2023-01-23 03:00:53.870522: step: 384/529, loss: 0.004502487368881702
2023-01-23 03:00:55.091107: step: 388/529, loss: 0.008827496320009232
2023-01-23 03:00:56.247033: step: 392/529, loss: 0.028681088238954544
2023-01-23 03:00:57.415137: step: 396/529, loss: 0.004202461335808039
2023-01-23 03:00:58.562048: step: 400/529, loss: 0.07386750727891922
2023-01-23 03:00:59.767782: step: 404/529, loss: 0.0651487410068512
2023-01-23 03:01:00.942055: step: 408/529, loss: 0.0022944926749914885
2023-01-23 03:01:02.080080: step: 412/529, loss: 0.015975380316376686
2023-01-23 03:01:03.306583: step: 416/529, loss: 0.004264259245246649
2023-01-23 03:01:04.486961: step: 420/529, loss: 0.0006412506336346269
2023-01-23 03:01:05.688790: step: 424/529, loss: 0.0010412216652184725
2023-01-23 03:01:06.863734: step: 428/529, loss: 0.00019407272338867188
2023-01-23 03:01:08.131272: step: 432/529, loss: 0.0026771544944494963
2023-01-23 03:01:09.335782: step: 436/529, loss: 0.0003685951232910156
2023-01-23 03:01:10.521776: step: 440/529, loss: 0.019832421094179153
2023-01-23 03:01:11.766446: step: 444/529, loss: 0.00048246385995298624
2023-01-23 03:01:12.955735: step: 448/529, loss: 0.00011801719665527344
2023-01-23 03:01:14.123752: step: 452/529, loss: 0.005002498626708984
2023-01-23 03:01:15.339045: step: 456/529, loss: 0.02692241594195366
2023-01-23 03:01:16.513002: step: 460/529, loss: 0.0001867294340627268
2023-01-23 03:01:17.735083: step: 464/529, loss: 0.02612285688519478
2023-01-23 03:01:18.969029: step: 468/529, loss: 0.007007598876953125
2023-01-23 03:01:20.166945: step: 472/529, loss: 0.003475189208984375
2023-01-23 03:01:21.395143: step: 476/529, loss: 0.012428474612534046
2023-01-23 03:01:22.585430: step: 480/529, loss: 0.0009718418004922569
2023-01-23 03:01:23.787910: step: 484/529, loss: 0.00010185241990257055
2023-01-23 03:01:24.968916: step: 488/529, loss: 0.000911331211682409
2023-01-23 03:01:26.131160: step: 492/529, loss: 0.00024662018404342234
2023-01-23 03:01:27.323404: step: 496/529, loss: 0.04441995546221733
2023-01-23 03:01:28.546740: step: 500/529, loss: 0.004452705383300781
2023-01-23 03:01:29.694571: step: 504/529, loss: 0.0008153438684530556
2023-01-23 03:01:30.868746: step: 508/529, loss: 0.018802309408783913
2023-01-23 03:01:32.082792: step: 512/529, loss: 0.004047775641083717
2023-01-23 03:01:33.274254: step: 516/529, loss: 0.005288982763886452
2023-01-23 03:01:34.418484: step: 520/529, loss: 0.03788948059082031
2023-01-23 03:01:35.621808: step: 524/529, loss: 0.0015561580657958984
2023-01-23 03:01:36.824373: step: 528/529, loss: 0.6090884804725647
2023-01-23 03:01:38.049998: step: 532/529, loss: 0.02444629557430744
2023-01-23 03:01:39.223353: step: 536/529, loss: 0.025970458984375
2023-01-23 03:01:40.414710: step: 540/529, loss: 0.0029148103203624487
2023-01-23 03:01:41.663323: step: 544/529, loss: 0.00287132291123271
2023-01-23 03:01:42.883466: step: 548/529, loss: 0.005879211239516735
2023-01-23 03:01:44.066924: step: 552/529, loss: 0.00017366409883834422
2023-01-23 03:01:45.284221: step: 556/529, loss: 0.00036563872708939016
2023-01-23 03:01:46.442244: step: 560/529, loss: 0.008824491873383522
2023-01-23 03:01:47.612841: step: 564/529, loss: 0.00010423660569358617
2023-01-23 03:01:48.778448: step: 568/529, loss: 6.141662743175402e-05
2023-01-23 03:01:49.972006: step: 572/529, loss: 0.0029921531677246094
2023-01-23 03:01:51.152649: step: 576/529, loss: 0.031603239476680756
2023-01-23 03:01:52.376203: step: 580/529, loss: 0.008437538519501686
2023-01-23 03:01:53.591672: step: 584/529, loss: 0.0007762908935546875
2023-01-23 03:01:54.720470: step: 588/529, loss: 6.008148375258315e-06
2023-01-23 03:01:55.933653: step: 592/529, loss: 0.020706748589873314
2023-01-23 03:01:57.122378: step: 596/529, loss: 0.0021098137367516756
2023-01-23 03:01:58.322166: step: 600/529, loss: 0.026454545557498932
2023-01-23 03:01:59.536289: step: 604/529, loss: 0.38733500242233276
2023-01-23 03:02:00.698705: step: 608/529, loss: 0.040145114064216614
2023-01-23 03:02:01.893539: step: 612/529, loss: 0.02242717705667019
2023-01-23 03:02:03.102387: step: 616/529, loss: 0.011246300302445889
2023-01-23 03:02:04.273659: step: 620/529, loss: 0.10426407307386398
2023-01-23 03:02:05.516161: step: 624/529, loss: 0.031542014330625534
2023-01-23 03:02:06.724147: step: 628/529, loss: 0.01098785363137722
2023-01-23 03:02:07.967281: step: 632/529, loss: 0.029364967718720436
2023-01-23 03:02:09.200725: step: 636/529, loss: 0.031473252922296524
2023-01-23 03:02:10.390650: step: 640/529, loss: 0.0009755134815350175
2023-01-23 03:02:11.548692: step: 644/529, loss: 0.003891182132065296
2023-01-23 03:02:12.758197: step: 648/529, loss: 0.01086578331887722
2023-01-23 03:02:13.958117: step: 652/529, loss: 0.040348101407289505
2023-01-23 03:02:15.145117: step: 656/529, loss: 0.0060707093216478825
2023-01-23 03:02:16.344540: step: 660/529, loss: 0.002191019244492054
2023-01-23 03:02:17.577161: step: 664/529, loss: 0.0010872840648517013
2023-01-23 03:02:18.774028: step: 668/529, loss: 0.049207497388124466
2023-01-23 03:02:19.978053: step: 672/529, loss: 0.015920164063572884
2023-01-23 03:02:21.201414: step: 676/529, loss: 0.03878040239214897
2023-01-23 03:02:22.439113: step: 680/529, loss: 0.03665771707892418
2023-01-23 03:02:23.670685: step: 684/529, loss: 0.00017604828462935984
2023-01-23 03:02:24.852440: step: 688/529, loss: 0.0013577460777014494
2023-01-23 03:02:26.035895: step: 692/529, loss: 0.008386707864701748
2023-01-23 03:02:27.214756: step: 696/529, loss: 5.655288987327367e-05
2023-01-23 03:02:28.404461: step: 700/529, loss: 0.02446003071963787
2023-01-23 03:02:29.631567: step: 704/529, loss: 0.004346084780991077
2023-01-23 03:02:30.800447: step: 708/529, loss: 0.004009819123893976
2023-01-23 03:02:32.021410: step: 712/529, loss: 0.021407699212431908
2023-01-23 03:02:33.269686: step: 716/529, loss: 0.0011683463817462325
2023-01-23 03:02:34.463870: step: 720/529, loss: 0.006407547276467085
2023-01-23 03:02:35.682112: step: 724/529, loss: 0.0028341293800622225
2023-01-23 03:02:36.887979: step: 728/529, loss: 0.12858662009239197
2023-01-23 03:02:38.054886: step: 732/529, loss: 0.001036643865518272
2023-01-23 03:02:39.240374: step: 736/529, loss: 0.0035652159713208675
2023-01-23 03:02:40.419666: step: 740/529, loss: 0.002392721129581332
2023-01-23 03:02:41.652840: step: 744/529, loss: 1.487731969973538e-05
2023-01-23 03:02:42.808797: step: 748/529, loss: 0.03475785255432129
2023-01-23 03:02:44.046685: step: 752/529, loss: 0.0001604080171091482
2023-01-23 03:02:45.300306: step: 756/529, loss: 0.0992010086774826
2023-01-23 03:02:46.466848: step: 760/529, loss: 0.005539322271943092
2023-01-23 03:02:47.635252: step: 764/529, loss: 0.006421280093491077
2023-01-23 03:02:48.848230: step: 768/529, loss: 0.0068187713623046875
2023-01-23 03:02:50.058857: step: 772/529, loss: 0.00850753765553236
2023-01-23 03:02:51.245911: step: 776/529, loss: 0.0023262023460119963
2023-01-23 03:02:52.421624: step: 780/529, loss: 0.10414247959852219
2023-01-23 03:02:53.651347: step: 784/529, loss: 0.06970927864313126
2023-01-23 03:02:54.859186: step: 788/529, loss: 0.1101720854640007
2023-01-23 03:02:56.049877: step: 792/529, loss: 0.0008069038740359247
2023-01-23 03:02:57.239072: step: 796/529, loss: 0.006174373906105757
2023-01-23 03:02:58.440457: step: 800/529, loss: 0.07027263194322586
2023-01-23 03:02:59.680285: step: 804/529, loss: 0.012847852893173695
2023-01-23 03:03:00.866671: step: 808/529, loss: 0.008003043942153454
2023-01-23 03:03:02.105284: step: 812/529, loss: 0.03995443508028984
2023-01-23 03:03:03.326487: step: 816/529, loss: 0.03222246095538139
2023-01-23 03:03:04.478993: step: 820/529, loss: 0.02943878062069416
2023-01-23 03:03:05.679462: step: 824/529, loss: 0.0002769470156636089
2023-01-23 03:03:06.908245: step: 828/529, loss: 0.0018831252818927169
2023-01-23 03:03:08.093027: step: 832/529, loss: 0.03874276205897331
2023-01-23 03:03:09.302967: step: 836/529, loss: 0.0018135070567950606
2023-01-23 03:03:10.501225: step: 840/529, loss: 0.015957452356815338
2023-01-23 03:03:11.661434: step: 844/529, loss: 0.004188633523881435
2023-01-23 03:03:12.823099: step: 848/529, loss: 0.004436301998794079
2023-01-23 03:03:14.018096: step: 852/529, loss: 0.04503602907061577
2023-01-23 03:03:15.243814: step: 856/529, loss: 0.013290406204760075
2023-01-23 03:03:16.441714: step: 860/529, loss: 0.0005834579933434725
2023-01-23 03:03:17.656532: step: 864/529, loss: 0.0037806988693773746
2023-01-23 03:03:18.872741: step: 868/529, loss: 0.004334593191742897
2023-01-23 03:03:20.073870: step: 872/529, loss: 0.0030536651611328125
2023-01-23 03:03:21.289732: step: 876/529, loss: 0.0018623352516442537
2023-01-23 03:03:22.484533: step: 880/529, loss: 0.00014553070650435984
2023-01-23 03:03:23.659806: step: 884/529, loss: 0.006325721740722656
2023-01-23 03:03:24.847544: step: 888/529, loss: 8.525848534191027e-05
2023-01-23 03:03:26.076699: step: 892/529, loss: 0.11257939785718918
2023-01-23 03:03:27.289121: step: 896/529, loss: 0.0007785797351971269
2023-01-23 03:03:28.484723: step: 900/529, loss: 0.02764301188290119
2023-01-23 03:03:29.682034: step: 904/529, loss: 0.007180404849350452
2023-01-23 03:03:30.933571: step: 908/529, loss: 0.032185934484004974
2023-01-23 03:03:32.142064: step: 912/529, loss: 7.05718994140625e-05
2023-01-23 03:03:33.340641: step: 916/529, loss: 0.021619606763124466
2023-01-23 03:03:34.500306: step: 920/529, loss: 0.00023937225341796875
2023-01-23 03:03:35.683004: step: 924/529, loss: 0.0003494262637104839
2023-01-23 03:03:36.893234: step: 928/529, loss: 0.009297179989516735
2023-01-23 03:03:38.103888: step: 932/529, loss: 0.0012050628429278731
2023-01-23 03:03:39.339808: step: 936/529, loss: 0.04403753578662872
2023-01-23 03:03:40.537753: step: 940/529, loss: 0.00047931671724654734
2023-01-23 03:03:41.716102: step: 944/529, loss: 0.0030799866653978825
2023-01-23 03:03:42.889203: step: 948/529, loss: 9.698867506813258e-05
2023-01-23 03:03:44.107778: step: 952/529, loss: 0.016660690307617188
2023-01-23 03:03:45.276551: step: 956/529, loss: 0.025107193738222122
2023-01-23 03:03:46.472010: step: 960/529, loss: 0.010676764883100986
2023-01-23 03:03:47.679091: step: 964/529, loss: 0.028946496546268463
2023-01-23 03:03:48.868588: step: 968/529, loss: 0.02181243896484375
2023-01-23 03:03:50.085207: step: 972/529, loss: 0.07496700435876846
2023-01-23 03:03:51.272610: step: 976/529, loss: 0.004200423136353493
2023-01-23 03:03:52.434109: step: 980/529, loss: 0.005382442381232977
2023-01-23 03:03:53.594306: step: 984/529, loss: 0.0029206275939941406
2023-01-23 03:03:54.780539: step: 988/529, loss: 0.10541171580553055
2023-01-23 03:03:55.972554: step: 992/529, loss: 0.0001316070556640625
2023-01-23 03:03:57.193829: step: 996/529, loss: 0.0007550239679403603
2023-01-23 03:03:58.379407: step: 1000/529, loss: 0.00869069155305624
2023-01-23 03:03:59.566719: step: 1004/529, loss: 0.029651977121829987
2023-01-23 03:04:00.820694: step: 1008/529, loss: 0.006114387419074774
2023-01-23 03:04:01.966532: step: 1012/529, loss: 0.06513696163892746
2023-01-23 03:04:03.163085: step: 1016/529, loss: 0.03226127475500107
2023-01-23 03:04:04.374241: step: 1020/529, loss: 0.03772401809692383
2023-01-23 03:04:05.611438: step: 1024/529, loss: 0.03134498745203018
2023-01-23 03:04:06.804029: step: 1028/529, loss: 0.015622902661561966
2023-01-23 03:04:08.018970: step: 1032/529, loss: 0.003602599957957864
2023-01-23 03:04:09.228452: step: 1036/529, loss: 0.0030490877106785774
2023-01-23 03:04:10.424796: step: 1040/529, loss: 0.01727619208395481
2023-01-23 03:04:11.651009: step: 1044/529, loss: 0.03474845737218857
2023-01-23 03:04:12.900539: step: 1048/529, loss: 0.016892720013856888
2023-01-23 03:04:14.139596: step: 1052/529, loss: 0.0053730010986328125
2023-01-23 03:04:15.324373: step: 1056/529, loss: 0.0010399818420410156
2023-01-23 03:04:16.530955: step: 1060/529, loss: 0.016312886029481888
2023-01-23 03:04:17.727452: step: 1064/529, loss: 0.00034084319486282766
2023-01-23 03:04:18.954674: step: 1068/529, loss: 0.04338092729449272
2023-01-23 03:04:20.141481: step: 1072/529, loss: 0.04091205447912216
2023-01-23 03:04:21.313191: step: 1076/529, loss: 0.018723249435424805
2023-01-23 03:04:22.519367: step: 1080/529, loss: 0.037447549402713776
2023-01-23 03:04:23.710220: step: 1084/529, loss: 5.149841672391631e-05
2023-01-23 03:04:24.903690: step: 1088/529, loss: 0.11782610416412354
2023-01-23 03:04:26.098892: step: 1092/529, loss: 0.011681366711854935
2023-01-23 03:04:27.283207: step: 1096/529, loss: 0.03158588334918022
2023-01-23 03:04:28.510591: step: 1100/529, loss: 0.0027848242316395044
2023-01-23 03:04:29.739507: step: 1104/529, loss: 0.0015151978004723787
2023-01-23 03:04:30.926094: step: 1108/529, loss: 0.0001126289353123866
2023-01-23 03:04:32.139291: step: 1112/529, loss: 0.2589547038078308
2023-01-23 03:04:33.364448: step: 1116/529, loss: 0.006248379126191139
2023-01-23 03:04:34.601104: step: 1120/529, loss: 0.0002654075506143272
2023-01-23 03:04:35.808804: step: 1124/529, loss: 0.00021305083646439016
2023-01-23 03:04:37.006318: step: 1128/529, loss: 0.035358332097530365
2023-01-23 03:04:38.165123: step: 1132/529, loss: 0.002123546553775668
2023-01-23 03:04:39.358978: step: 1136/529, loss: 0.00122661585919559
2023-01-23 03:04:40.576009: step: 1140/529, loss: 9.36508149607107e-05
2023-01-23 03:04:41.793908: step: 1144/529, loss: 0.00020828247943427414
2023-01-23 03:04:43.001279: step: 1148/529, loss: 0.0339202880859375
2023-01-23 03:04:44.198618: step: 1152/529, loss: 0.0015138626331463456
2023-01-23 03:04:45.383164: step: 1156/529, loss: 0.012713718228042126
2023-01-23 03:04:46.633612: step: 1160/529, loss: 0.05988325923681259
2023-01-23 03:04:47.819070: step: 1164/529, loss: 6.065368506824598e-05
2023-01-23 03:04:49.016920: step: 1168/529, loss: 0.025690842419862747
2023-01-23 03:04:50.225333: step: 1172/529, loss: 0.024699974805116653
2023-01-23 03:04:51.440064: step: 1176/529, loss: 0.01584930345416069
2023-01-23 03:04:52.632077: step: 1180/529, loss: 0.0004261970752850175
2023-01-23 03:04:53.844782: step: 1184/529, loss: 0.0013479233020916581
2023-01-23 03:04:55.016514: step: 1188/529, loss: 0.0002750396670307964
2023-01-23 03:04:56.180993: step: 1192/529, loss: 0.001307678292505443
2023-01-23 03:04:57.379779: step: 1196/529, loss: 0.013512516394257545
2023-01-23 03:04:58.550584: step: 1200/529, loss: 0.016615010797977448
2023-01-23 03:04:59.748395: step: 1204/529, loss: 0.002271938370540738
2023-01-23 03:05:00.920361: step: 1208/529, loss: 0.05526590347290039
2023-01-23 03:05:02.163430: step: 1212/529, loss: 0.021343043074011803
2023-01-23 03:05:03.311875: step: 1216/529, loss: 0.0004173278866801411
2023-01-23 03:05:04.522761: step: 1220/529, loss: 0.006449985783547163
2023-01-23 03:05:05.717910: step: 1224/529, loss: 0.027311896905303
2023-01-23 03:05:06.920768: step: 1228/529, loss: 0.01453247107565403
2023-01-23 03:05:08.113007: step: 1232/529, loss: 0.0019279479747638106
2023-01-23 03:05:09.259360: step: 1236/529, loss: 0.0004570961173158139
2023-01-23 03:05:10.467411: step: 1240/529, loss: 0.00037975312443450093
2023-01-23 03:05:11.702416: step: 1244/529, loss: 0.016918564215302467
2023-01-23 03:05:12.904540: step: 1248/529, loss: 0.011882019229233265
2023-01-23 03:05:14.109015: step: 1252/529, loss: 0.022782515734434128
2023-01-23 03:05:15.308169: step: 1256/529, loss: 0.2287009209394455
2023-01-23 03:05:16.567511: step: 1260/529, loss: 0.0557008758187294
2023-01-23 03:05:17.747862: step: 1264/529, loss: 0.004025841131806374
2023-01-23 03:05:18.937078: step: 1268/529, loss: 0.002757263369858265
2023-01-23 03:05:20.261818: step: 1272/529, loss: 0.002262687776237726
2023-01-23 03:05:21.437154: step: 1276/529, loss: 0.17201462388038635
2023-01-23 03:05:22.688397: step: 1280/529, loss: 0.0007619857788085938
2023-01-23 03:05:23.887038: step: 1284/529, loss: 0.038854315876960754
2023-01-23 03:05:25.104015: step: 1288/529, loss: 0.010829162783920765
2023-01-23 03:05:26.297889: step: 1292/529, loss: 0.028765391558408737
2023-01-23 03:05:27.502745: step: 1296/529, loss: 0.004512500949203968
2023-01-23 03:05:28.752223: step: 1300/529, loss: 0.01488342322409153
2023-01-23 03:05:30.042797: step: 1304/529, loss: 0.05646705627441406
2023-01-23 03:05:31.235749: step: 1308/529, loss: 0.0418243408203125
2023-01-23 03:05:32.396146: step: 1312/529, loss: 0.007448387332260609
2023-01-23 03:05:33.584429: step: 1316/529, loss: 0.004742145538330078
2023-01-23 03:05:34.805796: step: 1320/529, loss: 0.005156040191650391
2023-01-23 03:05:35.988344: step: 1324/529, loss: 0.1142582893371582
2023-01-23 03:05:37.171153: step: 1328/529, loss: 0.003535938449203968
2023-01-23 03:05:38.355271: step: 1332/529, loss: 8.296966552734375e-05
2023-01-23 03:05:39.575576: step: 1336/529, loss: 0.0034512518905103207
2023-01-23 03:05:40.798626: step: 1340/529, loss: 0.00480918912217021
2023-01-23 03:05:41.967851: step: 1344/529, loss: 0.014030265621840954
2023-01-23 03:05:43.189747: step: 1348/529, loss: 0.016479969024658203
2023-01-23 03:05:44.375092: step: 1352/529, loss: 0.1699983775615692
2023-01-23 03:05:45.627883: step: 1356/529, loss: 0.03920488432049751
2023-01-23 03:05:46.824528: step: 1360/529, loss: 0.007481765933334827
2023-01-23 03:05:47.997262: step: 1364/529, loss: 0.00048913958016783
2023-01-23 03:05:49.201996: step: 1368/529, loss: 0.08634891360998154
2023-01-23 03:05:50.387545: step: 1372/529, loss: 0.00015211105346679688
2023-01-23 03:05:51.586053: step: 1376/529, loss: 0.036019135266542435
2023-01-23 03:05:52.758513: step: 1380/529, loss: 3.0517578125e-05
2023-01-23 03:05:53.973504: step: 1384/529, loss: 0.008962249383330345
2023-01-23 03:05:55.195775: step: 1388/529, loss: 0.2295665740966797
2023-01-23 03:05:56.434855: step: 1392/529, loss: 0.027381135150790215
2023-01-23 03:05:57.636842: step: 1396/529, loss: 0.0017087936867028475
2023-01-23 03:05:58.826933: step: 1400/529, loss: 0.00073666573734954
2023-01-23 03:06:00.034212: step: 1404/529, loss: 0.07298936694860458
2023-01-23 03:06:01.182772: step: 1408/529, loss: 0.0032261849846690893
2023-01-23 03:06:02.411632: step: 1412/529, loss: 0.0341595895588398
2023-01-23 03:06:03.603047: step: 1416/529, loss: 0.022269297391176224
2023-01-23 03:06:04.756980: step: 1420/529, loss: 4.100799742445815e-06
2023-01-23 03:06:05.957626: step: 1424/529, loss: 0.011155366897583008
2023-01-23 03:06:07.148616: step: 1428/529, loss: 0.001195764634758234
2023-01-23 03:06:08.330418: step: 1432/529, loss: 0.0007196426158770919
2023-01-23 03:06:09.531764: step: 1436/529, loss: 0.03333578258752823
2023-01-23 03:06:10.751205: step: 1440/529, loss: 0.03145332634449005
2023-01-23 03:06:11.950051: step: 1444/529, loss: 0.0593264065682888
2023-01-23 03:06:13.164053: step: 1448/529, loss: 0.01563272438943386
2023-01-23 03:06:14.357650: step: 1452/529, loss: 0.0015298366779461503
2023-01-23 03:06:15.541898: step: 1456/529, loss: 0.023151110857725143
2023-01-23 03:06:16.718839: step: 1460/529, loss: 0.008292580023407936
2023-01-23 03:06:17.909836: step: 1464/529, loss: 0.0032569884788244963
2023-01-23 03:06:19.152202: step: 1468/529, loss: 0.055326174944639206
2023-01-23 03:06:20.351324: step: 1472/529, loss: 0.0008455276256427169
2023-01-23 03:06:21.538094: step: 1476/529, loss: 0.0005357742193154991
2023-01-23 03:06:22.705253: step: 1480/529, loss: 0.03813495859503746
2023-01-23 03:06:23.930419: step: 1484/529, loss: 0.002634143689647317
2023-01-23 03:06:25.152861: step: 1488/529, loss: 0.006098556332290173
2023-01-23 03:06:26.340006: step: 1492/529, loss: 2.28881845032447e-06
2023-01-23 03:06:27.564881: step: 1496/529, loss: 0.017171192914247513
2023-01-23 03:06:28.763977: step: 1500/529, loss: 0.0027893066871911287
2023-01-23 03:06:29.972522: step: 1504/529, loss: 0.019234228879213333
2023-01-23 03:06:31.175329: step: 1508/529, loss: 0.00029468536376953125
2023-01-23 03:06:32.393169: step: 1512/529, loss: 0.00987706147134304
2023-01-23 03:06:33.555969: step: 1516/529, loss: 0.04477691650390625
2023-01-23 03:06:34.773869: step: 1520/529, loss: 0.000858306884765625
2023-01-23 03:06:35.974025: step: 1524/529, loss: 0.021194934844970703
2023-01-23 03:06:37.214652: step: 1528/529, loss: 0.04408779367804527
2023-01-23 03:06:38.418722: step: 1532/529, loss: 0.002058029407635331
2023-01-23 03:06:39.670952: step: 1536/529, loss: 0.025771522894501686
2023-01-23 03:06:40.879165: step: 1540/529, loss: 0.05279712751507759
2023-01-23 03:06:42.065787: step: 1544/529, loss: 0.0425536148250103
2023-01-23 03:06:43.279984: step: 1548/529, loss: 0.05156688764691353
2023-01-23 03:06:44.450803: step: 1552/529, loss: 0.005675602238625288
2023-01-23 03:06:45.659034: step: 1556/529, loss: 0.00023174285888671875
2023-01-23 03:06:46.860316: step: 1560/529, loss: 0.0016486168606206775
2023-01-23 03:06:48.077963: step: 1564/529, loss: 0.0038089752197265625
2023-01-23 03:06:49.232571: step: 1568/529, loss: 0.0075532435439527035
2023-01-23 03:06:50.411386: step: 1572/529, loss: 0.002165222307667136
2023-01-23 03:06:51.603220: step: 1576/529, loss: 0.05667886510491371
2023-01-23 03:06:52.766864: step: 1580/529, loss: 0.00043935776920989156
2023-01-23 03:06:53.999611: step: 1584/529, loss: 0.00920791644603014
2023-01-23 03:06:55.186190: step: 1588/529, loss: 0.0038474085740745068
2023-01-23 03:06:56.373600: step: 1592/529, loss: 0.07811546325683594
2023-01-23 03:06:57.549809: step: 1596/529, loss: 0.05807380750775337
2023-01-23 03:06:58.748554: step: 1600/529, loss: 0.00041942595271393657
2023-01-23 03:06:59.937128: step: 1604/529, loss: 0.02204456366598606
2023-01-23 03:07:01.192625: step: 1608/529, loss: 0.005208015441894531
2023-01-23 03:07:02.394019: step: 1612/529, loss: 0.008244229480624199
2023-01-23 03:07:03.573320: step: 1616/529, loss: 0.0006495475536212325
2023-01-23 03:07:04.758813: step: 1620/529, loss: 0.0012501715682446957
2023-01-23 03:07:05.907224: step: 1624/529, loss: 0.011770821176469326
2023-01-23 03:07:07.082937: step: 1628/529, loss: 0.0430939681828022
2023-01-23 03:07:08.323194: step: 1632/529, loss: 0.0009360313997603953
2023-01-23 03:07:09.524115: step: 1636/529, loss: 0.03535766527056694
2023-01-23 03:07:10.732011: step: 1640/529, loss: 0.007501030340790749
2023-01-23 03:07:11.922595: step: 1644/529, loss: 0.015155602246522903
2023-01-23 03:07:13.093872: step: 1648/529, loss: 0.025030899792909622
2023-01-23 03:07:14.272954: step: 1652/529, loss: 0.005852699279785156
2023-01-23 03:07:15.448682: step: 1656/529, loss: 0.001203346299007535
2023-01-23 03:07:16.683644: step: 1660/529, loss: 0.0012742995750159025
2023-01-23 03:07:17.899864: step: 1664/529, loss: 0.01425943337380886
2023-01-23 03:07:19.123236: step: 1668/529, loss: 0.0005098342662677169
2023-01-23 03:07:20.359127: step: 1672/529, loss: 0.0005107164615765214
2023-01-23 03:07:21.529434: step: 1676/529, loss: 0.0010564328404143453
2023-01-23 03:07:22.744097: step: 1680/529, loss: 0.00022201538376975805
2023-01-23 03:07:23.934713: step: 1684/529, loss: 0.007825469598174095
2023-01-23 03:07:25.140203: step: 1688/529, loss: 0.05650081858038902
2023-01-23 03:07:26.294008: step: 1692/529, loss: 0.0008904456626623869
2023-01-23 03:07:27.489558: step: 1696/529, loss: 0.003869724227115512
2023-01-23 03:07:28.700527: step: 1700/529, loss: 0.02690863609313965
2023-01-23 03:07:29.894882: step: 1704/529, loss: 0.00015697479830123484
2023-01-23 03:07:31.090077: step: 1708/529, loss: 0.0013691901694983244
2023-01-23 03:07:32.298533: step: 1712/529, loss: 0.0009058952564373612
2023-01-23 03:07:33.525189: step: 1716/529, loss: 0.06457547843456268
2023-01-23 03:07:34.703971: step: 1720/529, loss: 0.004027175717055798
2023-01-23 03:07:35.918361: step: 1724/529, loss: 0.0747649222612381
2023-01-23 03:07:37.153413: step: 1728/529, loss: 0.011796379461884499
2023-01-23 03:07:38.358050: step: 1732/529, loss: 0.09886636584997177
2023-01-23 03:07:39.521658: step: 1736/529, loss: 0.009797287173569202
2023-01-23 03:07:40.706843: step: 1740/529, loss: 0.0022899629548192024
2023-01-23 03:07:41.939144: step: 1744/529, loss: 0.0005227565998211503
2023-01-23 03:07:43.114422: step: 1748/529, loss: 0.004146575927734375
2023-01-23 03:07:44.342875: step: 1752/529, loss: 0.0010561943054199219
2023-01-23 03:07:45.515355: step: 1756/529, loss: 0.016541479155421257
2023-01-23 03:07:46.736136: step: 1760/529, loss: 0.03152790293097496
2023-01-23 03:07:47.941201: step: 1764/529, loss: 0.05371475592255592
2023-01-23 03:07:49.126072: step: 1768/529, loss: 0.11742812395095825
2023-01-23 03:07:50.354037: step: 1772/529, loss: 0.13532543182373047
2023-01-23 03:07:51.528504: step: 1776/529, loss: 0.06766372174024582
2023-01-23 03:07:52.716693: step: 1780/529, loss: 0.37517157196998596
2023-01-23 03:07:53.914561: step: 1784/529, loss: 0.046967267990112305
2023-01-23 03:07:55.120621: step: 1788/529, loss: 0.07056532055139542
2023-01-23 03:07:56.310697: step: 1792/529, loss: 0.0005147933843545616
2023-01-23 03:07:57.518885: step: 1796/529, loss: 0.0560787171125412
2023-01-23 03:07:58.776517: step: 1800/529, loss: 0.006079196929931641
2023-01-23 03:07:59.988167: step: 1804/529, loss: 0.013102340511977673
2023-01-23 03:08:01.164580: step: 1808/529, loss: 0.44049468636512756
2023-01-23 03:08:02.383399: step: 1812/529, loss: 0.027129841968417168
2023-01-23 03:08:03.580853: step: 1816/529, loss: 0.012971687130630016
2023-01-23 03:08:04.787476: step: 1820/529, loss: 0.038538359105587006
2023-01-23 03:08:05.954714: step: 1824/529, loss: 0.00048389434232376516
2023-01-23 03:08:07.150326: step: 1828/529, loss: 0.0005072593921795487
2023-01-23 03:08:08.357024: step: 1832/529, loss: 0.002433872316032648
2023-01-23 03:08:09.591988: step: 1836/529, loss: 0.024733543395996094
2023-01-23 03:08:10.769824: step: 1840/529, loss: 0.004181766416877508
2023-01-23 03:08:11.956238: step: 1844/529, loss: 0.0002925872977357358
2023-01-23 03:08:13.130055: step: 1848/529, loss: 0.02150707319378853
2023-01-23 03:08:14.338798: step: 1852/529, loss: 0.0015194893348962069
2023-01-23 03:08:15.510929: step: 1856/529, loss: 0.0004215836524963379
2023-01-23 03:08:16.685825: step: 1860/529, loss: 0.052111152559518814
2023-01-23 03:08:17.911050: step: 1864/529, loss: 0.0054779052734375
2023-01-23 03:08:19.078097: step: 1868/529, loss: 0.005977058317512274
2023-01-23 03:08:20.271384: step: 1872/529, loss: 0.011924266815185547
2023-01-23 03:08:21.459386: step: 1876/529, loss: 0.020780611783266068
2023-01-23 03:08:22.648940: step: 1880/529, loss: 0.09207862615585327
2023-01-23 03:08:23.846658: step: 1884/529, loss: 0.00015788078599143773
2023-01-23 03:08:25.123490: step: 1888/529, loss: 0.003840923309326172
2023-01-23 03:08:26.300350: step: 1892/529, loss: 0.0019676208030432463
2023-01-23 03:08:27.506829: step: 1896/529, loss: 0.00837850570678711
2023-01-23 03:08:28.695243: step: 1900/529, loss: 0.011746288277208805
2023-01-23 03:08:29.874476: step: 1904/529, loss: 0.041113436222076416
2023-01-23 03:08:31.048773: step: 1908/529, loss: 0.002162837889045477
2023-01-23 03:08:32.254771: step: 1912/529, loss: 0.11363878101110458
2023-01-23 03:08:33.454340: step: 1916/529, loss: 0.0003292083856649697
2023-01-23 03:08:34.648002: step: 1920/529, loss: 0.1145562157034874
2023-01-23 03:08:35.822038: step: 1924/529, loss: 0.006500816438347101
2023-01-23 03:08:37.006208: step: 1928/529, loss: 0.07559080421924591
2023-01-23 03:08:38.221288: step: 1932/529, loss: 0.050786685198545456
2023-01-23 03:08:39.394525: step: 1936/529, loss: 1.2361985445022583
2023-01-23 03:08:40.620309: step: 1940/529, loss: 0.007229328155517578
2023-01-23 03:08:41.880384: step: 1944/529, loss: 0.03435201942920685
2023-01-23 03:08:43.112867: step: 1948/529, loss: 0.017311954870820045
2023-01-23 03:08:44.312240: step: 1952/529, loss: 0.005193233489990234
2023-01-23 03:08:45.506352: step: 1956/529, loss: 0.00022010804968886077
2023-01-23 03:08:46.703191: step: 1960/529, loss: 0.015543175861239433
2023-01-23 03:08:47.867708: step: 1964/529, loss: 0.003014469286426902
2023-01-23 03:08:49.008570: step: 1968/529, loss: 9.55581635935232e-05
2023-01-23 03:08:50.206717: step: 1972/529, loss: 0.014536094851791859
2023-01-23 03:08:51.391508: step: 1976/529, loss: 0.03141927719116211
2023-01-23 03:08:52.592380: step: 1980/529, loss: 0.0026701928582042456
2023-01-23 03:08:53.770029: step: 1984/529, loss: 0.002510261721909046
2023-01-23 03:08:54.952472: step: 1988/529, loss: 0.03645653650164604
2023-01-23 03:08:56.144924: step: 1992/529, loss: 0.00030179024906829
2023-01-23 03:08:57.343532: step: 1996/529, loss: 0.0101776123046875
2023-01-23 03:08:58.525329: step: 2000/529, loss: 0.006832325365394354
2023-01-23 03:08:59.759394: step: 2004/529, loss: 0.007663822267204523
2023-01-23 03:09:01.000063: step: 2008/529, loss: 0.009458637796342373
2023-01-23 03:09:02.181989: step: 2012/529, loss: 0.016492033377289772
2023-01-23 03:09:03.344422: step: 2016/529, loss: 0.005748271942138672
2023-01-23 03:09:04.520193: step: 2020/529, loss: 0.0003354072687216103
2023-01-23 03:09:05.691130: step: 2024/529, loss: 0.030788470059633255
2023-01-23 03:09:06.893416: step: 2028/529, loss: 0.0008027076837606728
2023-01-23 03:09:08.057692: step: 2032/529, loss: 0.006003665737807751
2023-01-23 03:09:09.252568: step: 2036/529, loss: 0.00010275841486873105
2023-01-23 03:09:10.428121: step: 2040/529, loss: 0.004646110814064741
2023-01-23 03:09:11.663691: step: 2044/529, loss: 0.015318943187594414
2023-01-23 03:09:12.815109: step: 2048/529, loss: 0.017773056402802467
2023-01-23 03:09:14.001947: step: 2052/529, loss: 0.01988658867776394
2023-01-23 03:09:15.195703: step: 2056/529, loss: 0.00151405343785882
2023-01-23 03:09:16.386237: step: 2060/529, loss: 0.001674652099609375
2023-01-23 03:09:17.605742: step: 2064/529, loss: 0.015311241149902344
2023-01-23 03:09:18.838160: step: 2068/529, loss: 0.007903862744569778
2023-01-23 03:09:20.068087: step: 2072/529, loss: 0.01455917302519083
2023-01-23 03:09:21.248497: step: 2076/529, loss: 0.0010942459339275956
2023-01-23 03:09:22.429015: step: 2080/529, loss: 0.0020085335709154606
2023-01-23 03:09:23.653454: step: 2084/529, loss: 0.002347290515899658
2023-01-23 03:09:24.844677: step: 2088/529, loss: 0.009985732845962048
2023-01-23 03:09:25.995615: step: 2092/529, loss: 1.0842952728271484
2023-01-23 03:09:27.151825: step: 2096/529, loss: 0.0009742736583575606
2023-01-23 03:09:28.361342: step: 2100/529, loss: 0.005417156033217907
2023-01-23 03:09:29.548754: step: 2104/529, loss: 4.9591064453125e-05
2023-01-23 03:09:30.746457: step: 2108/529, loss: 0.005000579636543989
2023-01-23 03:09:31.945667: step: 2112/529, loss: 0.004596090875566006
2023-01-23 03:09:33.120982: step: 2116/529, loss: 0.04891243204474449
==================================================
Loss: 0.028
--------------------
Dev: {'event': {'p': 0.6046747967479674, 'r': 0.7922769640479361, 'f1': 0.685878962536023}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6377990430622009, 'r': 0.7986818454164171, 'f1': 0.7092311785049216}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.631578947368421, 'r': 0.8888888888888888, 'f1': 0.7384615384615385}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.5, 'r': 0.5079365079365079, 'f1': 0.5039370078740157}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.42857142857142855, 'r': 0.5, 'f1': 0.4615384615384615}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:10:16.768517: step: 4/529, loss: 0.0016073227161541581
2023-01-23 03:10:17.933610: step: 8/529, loss: 0.0013536930782720447
2023-01-23 03:10:19.111799: step: 12/529, loss: 0.03565731272101402
2023-01-23 03:10:20.324653: step: 16/529, loss: 0.02318735234439373
2023-01-23 03:10:21.510211: step: 20/529, loss: 0.00046825408935546875
2023-01-23 03:10:22.728965: step: 24/529, loss: 0.011806678958237171
2023-01-23 03:10:23.877771: step: 28/529, loss: 0.002562230918556452
2023-01-23 03:10:25.093374: step: 32/529, loss: 7.643699791515246e-05
2023-01-23 03:10:26.241993: step: 36/529, loss: 0.09265337139368057
2023-01-23 03:10:27.427245: step: 40/529, loss: 9.698867506813258e-05
2023-01-23 03:10:28.633665: step: 44/529, loss: 0.00016403199697379023
2023-01-23 03:10:29.825138: step: 48/529, loss: 0.003382873721420765
2023-01-23 03:10:31.087840: step: 52/529, loss: 0.006996918004006147
2023-01-23 03:10:32.326152: step: 56/529, loss: 0.0020665170159190893
2023-01-23 03:10:33.540545: step: 60/529, loss: 0.0033197402954101562
2023-01-23 03:10:34.741935: step: 64/529, loss: 0.028774453327059746
2023-01-23 03:10:35.941886: step: 68/529, loss: 0.010026264004409313
2023-01-23 03:10:37.115140: step: 72/529, loss: 0.0035764218773692846
2023-01-23 03:10:38.314569: step: 76/529, loss: 0.00037221910315565765
2023-01-23 03:10:39.506812: step: 80/529, loss: 0.046616170555353165
2023-01-23 03:10:40.690173: step: 84/529, loss: 0.016783332452178
2023-01-23 03:10:41.879965: step: 88/529, loss: 0.014735984615981579
2023-01-23 03:10:43.077962: step: 92/529, loss: 0.0016683578724041581
2023-01-23 03:10:44.273413: step: 96/529, loss: 0.00018568038649391383
2023-01-23 03:10:45.454078: step: 100/529, loss: 0.0022497177124023438
2023-01-23 03:10:46.655849: step: 104/529, loss: 0.028211116790771484
2023-01-23 03:10:47.923656: step: 108/529, loss: 0.04281797632575035
2023-01-23 03:10:49.113385: step: 112/529, loss: 0.010030555538833141
2023-01-23 03:10:50.287123: step: 116/529, loss: 0.04286494478583336
2023-01-23 03:10:51.487912: step: 120/529, loss: 0.016987990587949753
2023-01-23 03:10:52.668339: step: 124/529, loss: 0.000446128862677142
2023-01-23 03:10:53.882850: step: 128/529, loss: 0.019921589642763138
2023-01-23 03:10:55.067191: step: 132/529, loss: 0.04748887941241264
2023-01-23 03:10:56.272645: step: 136/529, loss: 0.00899276789277792
2023-01-23 03:10:57.467399: step: 140/529, loss: 0.0006554603460244834
2023-01-23 03:10:58.659449: step: 144/529, loss: 1.354217511106981e-05
2023-01-23 03:10:59.839603: step: 148/529, loss: 0.0031435966957360506
2023-01-23 03:11:01.010063: step: 152/529, loss: 0.00028028490487486124
2023-01-23 03:11:02.212022: step: 156/529, loss: 0.00738182058557868
2023-01-23 03:11:03.391518: step: 160/529, loss: 0.013612747192382812
2023-01-23 03:11:04.587438: step: 164/529, loss: 0.00028209685115143657
2023-01-23 03:11:05.779781: step: 168/529, loss: 0.0022464515641331673
2023-01-23 03:11:06.954322: step: 172/529, loss: 0.00041670797509141266
2023-01-23 03:11:08.197483: step: 176/529, loss: 0.0002637386496644467
2023-01-23 03:11:09.357119: step: 180/529, loss: 0.00023403167142532766
2023-01-23 03:11:10.557436: step: 184/529, loss: 0.0037538527976721525
2023-01-23 03:11:11.743924: step: 188/529, loss: 0.0004145622078794986
2023-01-23 03:11:12.923436: step: 192/529, loss: 0.011241721920669079
2023-01-23 03:11:14.117394: step: 196/529, loss: 0.007048130035400391
2023-01-23 03:11:15.316799: step: 200/529, loss: 0.0032802580390125513
2023-01-23 03:11:16.496009: step: 204/529, loss: 0.02246570587158203
2023-01-23 03:11:17.697469: step: 208/529, loss: 0.02220172993838787
2023-01-23 03:11:18.909826: step: 212/529, loss: 0.7484796047210693
2023-01-23 03:11:20.077534: step: 216/529, loss: 0.01000671461224556
2023-01-23 03:11:21.253298: step: 220/529, loss: 0.006572246551513672
2023-01-23 03:11:22.488744: step: 224/529, loss: 0.008432101458311081
2023-01-23 03:11:23.682094: step: 228/529, loss: 0.004733157344162464
2023-01-23 03:11:24.881112: step: 232/529, loss: 0.010437775403261185
2023-01-23 03:11:26.048901: step: 236/529, loss: 0.0018742561805993319
2023-01-23 03:11:27.223923: step: 240/529, loss: 6.837844557594508e-05
2023-01-23 03:11:28.421250: step: 244/529, loss: 0.02784719690680504
2023-01-23 03:11:29.569775: step: 248/529, loss: 0.0012046813499182463
2023-01-23 03:11:30.778888: step: 252/529, loss: 0.0001548767031636089
2023-01-23 03:11:31.972031: step: 256/529, loss: 0.0013825417263433337
2023-01-23 03:11:33.177497: step: 260/529, loss: 0.0012588024837896228
2023-01-23 03:11:34.357205: step: 264/529, loss: 0.005891228094696999
2023-01-23 03:11:35.568072: step: 268/529, loss: 0.0007252931827679276
2023-01-23 03:11:36.733592: step: 272/529, loss: 0.015035438351333141
2023-01-23 03:11:37.958290: step: 276/529, loss: 0.09604117274284363
2023-01-23 03:11:39.157231: step: 280/529, loss: 0.023737384006381035
2023-01-23 03:11:40.366814: step: 284/529, loss: 0.0026497840881347656
2023-01-23 03:11:41.628005: step: 288/529, loss: 0.07260475307703018
2023-01-23 03:11:42.766560: step: 292/529, loss: 0.001001119613647461
2023-01-23 03:11:43.956335: step: 296/529, loss: 0.002080631209537387
2023-01-23 03:11:45.145056: step: 300/529, loss: 0.05675039440393448
2023-01-23 03:11:46.305638: step: 304/529, loss: 0.0003025055048055947
2023-01-23 03:11:47.488047: step: 308/529, loss: 0.002463150303810835
2023-01-23 03:11:48.690589: step: 312/529, loss: 0.07567157596349716
2023-01-23 03:11:49.898477: step: 316/529, loss: 0.005502796731889248
2023-01-23 03:11:51.088976: step: 320/529, loss: 0.007103347685188055
2023-01-23 03:11:52.310250: step: 324/529, loss: 0.043245889246463776
2023-01-23 03:11:53.509511: step: 328/529, loss: 0.05011434480547905
2023-01-23 03:11:54.717622: step: 332/529, loss: 0.05334950238466263
2023-01-23 03:11:55.905979: step: 336/529, loss: 0.020284080877900124
2023-01-23 03:11:57.099681: step: 340/529, loss: 6.294250852079131e-06
2023-01-23 03:11:58.299746: step: 344/529, loss: 0.593254804611206
2023-01-23 03:11:59.445330: step: 348/529, loss: 9.775161743164062e-05
2023-01-23 03:12:00.682246: step: 352/529, loss: 0.0025234222412109375
2023-01-23 03:12:01.887415: step: 356/529, loss: 0.22762832045555115
2023-01-23 03:12:03.086449: step: 360/529, loss: 0.0017623902531340718
2023-01-23 03:12:04.306649: step: 364/529, loss: 0.007865333929657936
2023-01-23 03:12:05.466317: step: 368/529, loss: 0.08284921199083328
2023-01-23 03:12:06.646029: step: 372/529, loss: 0.0011682510375976562
2023-01-23 03:12:07.848380: step: 376/529, loss: 1.4209747860149946e-05
2023-01-23 03:12:09.049750: step: 380/529, loss: 0.01260232925415039
2023-01-23 03:12:10.230930: step: 384/529, loss: 0.006535148713737726
2023-01-23 03:12:11.414661: step: 388/529, loss: 0.0010840416653081775
2023-01-23 03:12:12.627467: step: 392/529, loss: 0.11127223819494247
2023-01-23 03:12:13.809328: step: 396/529, loss: 0.004363822750747204
2023-01-23 03:12:14.971310: step: 400/529, loss: 0.0313815139234066
2023-01-23 03:12:16.199536: step: 404/529, loss: 0.0976623073220253
2023-01-23 03:12:17.417007: step: 408/529, loss: 0.030428696423768997
2023-01-23 03:12:18.594489: step: 412/529, loss: 0.9066535234451294
2023-01-23 03:12:19.800071: step: 416/529, loss: 0.00017480850510764867
2023-01-23 03:12:21.049427: step: 420/529, loss: 0.00018277167691849172
2023-01-23 03:12:22.266761: step: 424/529, loss: 0.00012407303438521922
2023-01-23 03:12:23.459342: step: 428/529, loss: 7.80105619924143e-05
2023-01-23 03:12:24.725808: step: 432/529, loss: 0.1299879550933838
2023-01-23 03:12:25.944406: step: 436/529, loss: 0.007201099302619696
2023-01-23 03:12:27.172851: step: 440/529, loss: 0.030178260058164597
2023-01-23 03:12:28.396675: step: 444/529, loss: 0.0011638641590252519
2023-01-23 03:12:29.601053: step: 448/529, loss: 0.01890125311911106
2023-01-23 03:12:30.812085: step: 452/529, loss: 0.0255903247743845
2023-01-23 03:12:32.105273: step: 456/529, loss: 0.0007987022399902344
2023-01-23 03:12:33.283724: step: 460/529, loss: 0.0005666256183758378
2023-01-23 03:12:34.513516: step: 464/529, loss: 0.0009533882257528603
2023-01-23 03:12:35.689417: step: 468/529, loss: 0.009092355147004128
2023-01-23 03:12:36.856169: step: 472/529, loss: 0.057149793952703476
2023-01-23 03:12:38.032413: step: 476/529, loss: 0.07583598792552948
2023-01-23 03:12:39.215399: step: 480/529, loss: 0.029883574694395065
2023-01-23 03:12:40.415853: step: 484/529, loss: 0.02776813507080078
2023-01-23 03:12:41.598958: step: 488/529, loss: 0.004580259323120117
2023-01-23 03:12:42.809333: step: 492/529, loss: 0.019835853949189186
2023-01-23 03:12:44.077500: step: 496/529, loss: 0.0029943466652184725
2023-01-23 03:12:45.259141: step: 500/529, loss: 0.010996437631547451
2023-01-23 03:12:46.459740: step: 504/529, loss: 0.014081097207963467
2023-01-23 03:12:47.655347: step: 508/529, loss: 0.0014564513694494963
2023-01-23 03:12:48.926797: step: 512/529, loss: 0.00030517578125
2023-01-23 03:12:50.107838: step: 516/529, loss: 0.040574267506599426
2023-01-23 03:12:51.365557: step: 520/529, loss: 0.00870523415505886
2023-01-23 03:12:52.559930: step: 524/529, loss: 0.07299929112195969
2023-01-23 03:12:53.754798: step: 528/529, loss: 0.0005697250599041581
2023-01-23 03:12:54.927624: step: 532/529, loss: 0.006549358367919922
2023-01-23 03:12:56.145914: step: 536/529, loss: 0.007571410853415728
2023-01-23 03:12:57.369546: step: 540/529, loss: 0.03962249681353569
2023-01-23 03:12:58.584377: step: 544/529, loss: 0.00168523786123842
2023-01-23 03:12:59.801370: step: 548/529, loss: 0.04717826843261719
2023-01-23 03:13:01.032106: step: 552/529, loss: 5.130767749506049e-05
2023-01-23 03:13:02.222083: step: 556/529, loss: 0.002742862794548273
2023-01-23 03:13:03.435979: step: 560/529, loss: 0.052001193165779114
2023-01-23 03:13:04.636747: step: 564/529, loss: 0.04471731185913086
2023-01-23 03:13:05.829631: step: 568/529, loss: 0.018649626523256302
2023-01-23 03:13:07.042881: step: 572/529, loss: 0.0024925232864916325
2023-01-23 03:13:08.293192: step: 576/529, loss: 0.00191841134801507
2023-01-23 03:13:09.516401: step: 580/529, loss: 0.018245507031679153
2023-01-23 03:13:10.689291: step: 584/529, loss: 0.0001753807155182585
2023-01-23 03:13:11.900095: step: 588/529, loss: 0.1297696977853775
2023-01-23 03:13:13.094894: step: 592/529, loss: 0.0013309955829754472
2023-01-23 03:13:14.315778: step: 596/529, loss: 0.02813739888370037
2023-01-23 03:13:15.508162: step: 600/529, loss: 0.01161866169422865
2023-01-23 03:13:16.682070: step: 604/529, loss: 0.004985237494111061
2023-01-23 03:13:17.903929: step: 608/529, loss: 0.013849449343979359
2023-01-23 03:13:19.100325: step: 612/529, loss: 0.05014057457447052
2023-01-23 03:13:20.251126: step: 616/529, loss: 0.0005031585460528731
2023-01-23 03:13:21.403389: step: 620/529, loss: 0.00379600515589118
2023-01-23 03:13:22.580178: step: 624/529, loss: 0.0028319358825683594
2023-01-23 03:13:23.768503: step: 628/529, loss: 0.0027130127418786287
2023-01-23 03:13:24.977515: step: 632/529, loss: 0.029138755053281784
2023-01-23 03:13:26.214348: step: 636/529, loss: 0.0012501716846600175
2023-01-23 03:13:27.404583: step: 640/529, loss: 0.0007723808521404862
2023-01-23 03:13:28.613145: step: 644/529, loss: 0.012537766247987747
2023-01-23 03:13:29.820647: step: 648/529, loss: 0.003552055452018976
2023-01-23 03:13:31.016244: step: 652/529, loss: 0.0008320808410644531
2023-01-23 03:13:32.217316: step: 656/529, loss: 0.022772502154111862
2023-01-23 03:13:33.431393: step: 660/529, loss: 0.0010007858509197831
2023-01-23 03:13:34.625240: step: 664/529, loss: 0.537615954875946
2023-01-23 03:13:35.795109: step: 668/529, loss: 5.7220458984375e-06
2023-01-23 03:13:37.016454: step: 672/529, loss: 0.023189926519989967
2023-01-23 03:13:38.225625: step: 676/529, loss: 0.020878886803984642
2023-01-23 03:13:39.413711: step: 680/529, loss: 0.00383338937535882
2023-01-23 03:13:40.605431: step: 684/529, loss: 0.0005691051483154297
2023-01-23 03:13:41.810447: step: 688/529, loss: 0.12039170414209366
2023-01-23 03:13:42.966805: step: 692/529, loss: 0.0004737853887490928
2023-01-23 03:13:44.147757: step: 696/529, loss: 0.03276491165161133
2023-01-23 03:13:45.359797: step: 700/529, loss: 0.019254494458436966
2023-01-23 03:13:46.532784: step: 704/529, loss: 0.001360988593660295
2023-01-23 03:13:47.766375: step: 708/529, loss: 5.3894520533503965e-05
2023-01-23 03:13:48.976159: step: 712/529, loss: 0.004268837161362171
2023-01-23 03:13:50.210904: step: 716/529, loss: 0.011077880859375
2023-01-23 03:13:51.450174: step: 720/529, loss: 0.0006185531965456903
2023-01-23 03:13:52.610548: step: 724/529, loss: 0.018194008618593216
2023-01-23 03:13:53.753767: step: 728/529, loss: 0.00045809749281033874
2023-01-23 03:13:54.931528: step: 732/529, loss: 0.010229205712676048
2023-01-23 03:13:56.161746: step: 736/529, loss: 0.00107488629873842
2023-01-23 03:13:57.338928: step: 740/529, loss: 0.14359036087989807
2023-01-23 03:13:58.537054: step: 744/529, loss: 7.514953904319555e-05
2023-01-23 03:13:59.713309: step: 748/529, loss: 0.092382051050663
2023-01-23 03:14:00.894928: step: 752/529, loss: 0.0001911163271870464
2023-01-23 03:14:02.137177: step: 756/529, loss: 0.1937045156955719
2023-01-23 03:14:03.323860: step: 760/529, loss: 0.1064656674861908
2023-01-23 03:14:04.501957: step: 764/529, loss: 1.8215179807157256e-05
2023-01-23 03:14:05.698003: step: 768/529, loss: 0.030310630798339844
2023-01-23 03:14:06.900234: step: 772/529, loss: 0.012318420223891735
2023-01-23 03:14:08.088711: step: 776/529, loss: 0.19332891702651978
2023-01-23 03:14:09.254529: step: 780/529, loss: 0.005836868658661842
2023-01-23 03:14:10.437189: step: 784/529, loss: 0.002092361683025956
2023-01-23 03:14:11.656512: step: 788/529, loss: 0.00038909912109375
2023-01-23 03:14:12.883098: step: 792/529, loss: 0.037246037274599075
2023-01-23 03:14:14.075970: step: 796/529, loss: 0.02420949935913086
2023-01-23 03:14:15.214945: step: 800/529, loss: 0.01276335772126913
2023-01-23 03:14:16.402247: step: 804/529, loss: 0.045938681811094284
2023-01-23 03:14:17.593021: step: 808/529, loss: 0.0020398139022290707
2023-01-23 03:14:18.789164: step: 812/529, loss: 0.004785728175193071
2023-01-23 03:14:19.973899: step: 816/529, loss: 0.020598506554961205
2023-01-23 03:14:21.121881: step: 820/529, loss: 0.005712604615837336
2023-01-23 03:14:22.296345: step: 824/529, loss: 0.004669592250138521
2023-01-23 03:14:23.472877: step: 828/529, loss: 0.002628326416015625
2023-01-23 03:14:24.638945: step: 832/529, loss: 0.00013209581084083766
2023-01-23 03:14:25.827868: step: 836/529, loss: 0.01651954837143421
2023-01-23 03:14:27.023409: step: 840/529, loss: 0.0256989486515522
2023-01-23 03:14:28.253316: step: 844/529, loss: 0.005681419279426336
2023-01-23 03:14:29.487738: step: 848/529, loss: 0.004430532455444336
2023-01-23 03:14:30.704693: step: 852/529, loss: 0.021818209439516068
2023-01-23 03:14:31.910697: step: 856/529, loss: 0.001922511961311102
2023-01-23 03:14:33.132039: step: 860/529, loss: 0.0014760971534997225
2023-01-23 03:14:34.358110: step: 864/529, loss: 0.0018540859455242753
2023-01-23 03:14:35.545362: step: 868/529, loss: 0.7207501530647278
2023-01-23 03:14:36.748049: step: 872/529, loss: 0.010114670731127262
2023-01-23 03:14:37.923533: step: 876/529, loss: 0.0010590553283691406
2023-01-23 03:14:39.088600: step: 880/529, loss: 0.0004748344363179058
2023-01-23 03:14:40.279756: step: 884/529, loss: 0.03907651826739311
2023-01-23 03:14:41.462957: step: 888/529, loss: 0.0006536960718221962
2023-01-23 03:14:42.674785: step: 892/529, loss: 0.10833549499511719
2023-01-23 03:14:43.871056: step: 896/529, loss: 0.0037919997703284025
2023-01-23 03:14:45.081317: step: 900/529, loss: 0.006622600834816694
2023-01-23 03:14:46.296162: step: 904/529, loss: 0.0005246162181720138
2023-01-23 03:14:47.523458: step: 908/529, loss: 0.02417621575295925
2023-01-23 03:14:48.706334: step: 912/529, loss: 0.02222600020468235
2023-01-23 03:14:49.899407: step: 916/529, loss: 0.0001682281435932964
2023-01-23 03:14:51.112184: step: 920/529, loss: 6.418228440452367e-05
2023-01-23 03:14:52.286364: step: 924/529, loss: 0.05570679157972336
2023-01-23 03:14:53.499203: step: 928/529, loss: 0.0003883361932821572
2023-01-23 03:14:54.668000: step: 932/529, loss: 0.00046939851017668843
2023-01-23 03:14:55.890055: step: 936/529, loss: 0.014226722531020641
2023-01-23 03:14:57.088468: step: 940/529, loss: 0.028089523315429688
2023-01-23 03:14:58.269274: step: 944/529, loss: 0.017992019653320312
2023-01-23 03:14:59.481794: step: 948/529, loss: 0.042827751487493515
2023-01-23 03:15:00.653105: step: 952/529, loss: 0.0011246681679040194
2023-01-23 03:15:01.880852: step: 956/529, loss: 0.027071570977568626
2023-01-23 03:15:03.058953: step: 960/529, loss: 0.002462100936099887
2023-01-23 03:15:04.277179: step: 964/529, loss: 0.001001596450805664
2023-01-23 03:15:05.491745: step: 968/529, loss: 0.002326583955436945
2023-01-23 03:15:06.693578: step: 972/529, loss: 0.006061935797333717
2023-01-23 03:15:07.850898: step: 976/529, loss: 0.0010293960804119706
2023-01-23 03:15:09.060053: step: 980/529, loss: 0.028292465955018997
2023-01-23 03:15:10.276214: step: 984/529, loss: 0.018955135717988014
2023-01-23 03:15:11.459495: step: 988/529, loss: 5.9795380366267636e-05
2023-01-23 03:15:12.695120: step: 992/529, loss: 0.00214385986328125
2023-01-23 03:15:13.867410: step: 996/529, loss: 0.010997582226991653
2023-01-23 03:15:15.091914: step: 1000/529, loss: 0.051388930529356
2023-01-23 03:15:16.259420: step: 1004/529, loss: 0.0022928237449377775
2023-01-23 03:15:17.466905: step: 1008/529, loss: 0.0025238036178052425
2023-01-23 03:15:18.625260: step: 1012/529, loss: 0.01413431204855442
2023-01-23 03:15:19.853346: step: 1016/529, loss: 0.0011574745876714587
2023-01-23 03:15:21.054315: step: 1020/529, loss: 5.9318539570085704e-05
2023-01-23 03:15:22.237948: step: 1024/529, loss: 0.027594758197665215
2023-01-23 03:15:23.423380: step: 1028/529, loss: 1.8978118532686494e-05
2023-01-23 03:15:24.614874: step: 1032/529, loss: 0.002118015196174383
2023-01-23 03:15:25.802604: step: 1036/529, loss: 5.7220458984375e-06
2023-01-23 03:15:27.013785: step: 1040/529, loss: 0.00027694704476743937
2023-01-23 03:15:28.222832: step: 1044/529, loss: 0.00014371873112395406
2023-01-23 03:15:29.470831: step: 1048/529, loss: 0.030681420117616653
2023-01-23 03:15:30.658933: step: 1052/529, loss: 0.02742939069867134
2023-01-23 03:15:31.887215: step: 1056/529, loss: 0.027376748621463776
2023-01-23 03:15:33.080040: step: 1060/529, loss: 0.00011324882507324219
2023-01-23 03:15:34.289968: step: 1064/529, loss: 0.00013806819333694875
2023-01-23 03:15:35.550198: step: 1068/529, loss: 2.09808349609375e-05
2023-01-23 03:15:36.729772: step: 1072/529, loss: 0.0022203922271728516
2023-01-23 03:15:37.898692: step: 1076/529, loss: 0.0006958008161745965
2023-01-23 03:15:39.122866: step: 1080/529, loss: 0.0008769988780841231
2023-01-23 03:15:40.306952: step: 1084/529, loss: 0.0034041404724121094
2023-01-23 03:15:41.499306: step: 1088/529, loss: 0.010478496551513672
2023-01-23 03:15:42.667392: step: 1092/529, loss: 0.0035492898896336555
2023-01-23 03:15:43.829337: step: 1096/529, loss: 0.03338112682104111
2023-01-23 03:15:45.041143: step: 1100/529, loss: 0.0004745483456645161
2023-01-23 03:15:46.232764: step: 1104/529, loss: 0.009274768643081188
2023-01-23 03:15:47.414846: step: 1108/529, loss: 0.0006011963123455644
2023-01-23 03:15:48.646424: step: 1112/529, loss: 0.001428794814273715
2023-01-23 03:15:49.820549: step: 1116/529, loss: 0.008805084973573685
2023-01-23 03:15:51.022139: step: 1120/529, loss: 0.00511245708912611
2023-01-23 03:15:52.203922: step: 1124/529, loss: 0.0023772239219397306
2023-01-23 03:15:53.424196: step: 1128/529, loss: 0.0047760009765625
2023-01-23 03:15:54.614196: step: 1132/529, loss: 0.05124321207404137
2023-01-23 03:15:55.780276: step: 1136/529, loss: 0.027296971529722214
2023-01-23 03:15:56.956808: step: 1140/529, loss: 0.015580369159579277
2023-01-23 03:15:58.143401: step: 1144/529, loss: 1.905228853225708
2023-01-23 03:15:59.359120: step: 1148/529, loss: 0.004398536402732134
2023-01-23 03:16:00.568350: step: 1152/529, loss: 0.0006052016979083419
2023-01-23 03:16:01.718096: step: 1156/529, loss: 0.08208908885717392
2023-01-23 03:16:02.928930: step: 1160/529, loss: 0.021008683368563652
2023-01-23 03:16:04.118487: step: 1164/529, loss: 0.013992881402373314
2023-01-23 03:16:05.324334: step: 1168/529, loss: 0.02656869776546955
2023-01-23 03:16:06.504599: step: 1172/529, loss: 6.647109694313258e-05
2023-01-23 03:16:07.703948: step: 1176/529, loss: 0.0025585652329027653
2023-01-23 03:16:08.918764: step: 1180/529, loss: 0.06045074760913849
2023-01-23 03:16:10.083281: step: 1184/529, loss: 0.002610874129459262
2023-01-23 03:16:11.296201: step: 1188/529, loss: 0.7269910573959351
2023-01-23 03:16:12.524656: step: 1192/529, loss: 0.1248149424791336
2023-01-23 03:16:13.714414: step: 1196/529, loss: 0.003365802811458707
2023-01-23 03:16:14.905665: step: 1200/529, loss: 0.001822996186092496
2023-01-23 03:16:16.126531: step: 1204/529, loss: 0.02316865883767605
2023-01-23 03:16:17.347102: step: 1208/529, loss: 0.0001424789516022429
2023-01-23 03:16:18.637501: step: 1212/529, loss: 0.0001937389315571636
2023-01-23 03:16:19.806007: step: 1216/529, loss: 0.006111335940659046
2023-01-23 03:16:21.058301: step: 1220/529, loss: 0.00031118394690565765
2023-01-23 03:16:22.304209: step: 1224/529, loss: 0.020068645477294922
2023-01-23 03:16:23.457331: step: 1228/529, loss: 0.01991257630288601
2023-01-23 03:16:24.670365: step: 1232/529, loss: 0.039063453674316406
2023-01-23 03:16:25.827865: step: 1236/529, loss: 2.7942656743107364e-05
2023-01-23 03:16:27.012162: step: 1240/529, loss: 0.06479320675134659
2023-01-23 03:16:28.231211: step: 1244/529, loss: 0.00020675660925917327
2023-01-23 03:16:29.377967: step: 1248/529, loss: 0.0023190020583570004
2023-01-23 03:16:30.582159: step: 1252/529, loss: 0.01610546186566353
2023-01-23 03:16:31.817432: step: 1256/529, loss: 0.014467049390077591
2023-01-23 03:16:32.986204: step: 1260/529, loss: 0.0018232346046715975
2023-01-23 03:16:34.162541: step: 1264/529, loss: 0.01195917185395956
2023-01-23 03:16:35.406952: step: 1268/529, loss: 0.0013654709327965975
2023-01-23 03:16:36.614808: step: 1272/529, loss: 0.029822159558534622
2023-01-23 03:16:37.786688: step: 1276/529, loss: 0.0003397941472940147
2023-01-23 03:16:39.096259: step: 1280/529, loss: 0.00039768218994140625
2023-01-23 03:16:40.303144: step: 1284/529, loss: 0.00290088658221066
2023-01-23 03:16:41.505919: step: 1288/529, loss: 0.004054450895637274
2023-01-23 03:16:42.710839: step: 1292/529, loss: 0.0015881540020927787
2023-01-23 03:16:43.896407: step: 1296/529, loss: 0.08943118900060654
2023-01-23 03:16:45.095773: step: 1300/529, loss: 0.00017538070096634328
2023-01-23 03:16:46.322458: step: 1304/529, loss: 0.15942907333374023
2023-01-23 03:16:47.515066: step: 1308/529, loss: 0.0014765739906579256
2023-01-23 03:16:48.745966: step: 1312/529, loss: 0.01698584482073784
2023-01-23 03:16:49.953698: step: 1316/529, loss: 0.014727783389389515
2023-01-23 03:16:51.150401: step: 1320/529, loss: 0.0006592273712158203
2023-01-23 03:16:52.442746: step: 1324/529, loss: 0.00010104179818881676
2023-01-23 03:16:53.629326: step: 1328/529, loss: 0.009118080139160156
2023-01-23 03:16:54.794865: step: 1332/529, loss: 0.03366592153906822
2023-01-23 03:16:55.949242: step: 1336/529, loss: 0.0008112907526083291
2023-01-23 03:16:57.115669: step: 1340/529, loss: 0.018190480768680573
2023-01-23 03:16:58.336322: step: 1344/529, loss: 0.037294767796993256
2023-01-23 03:16:59.525438: step: 1348/529, loss: 0.029923629015684128
2023-01-23 03:17:00.687365: step: 1352/529, loss: 0.01628437079489231
2023-01-23 03:17:01.950262: step: 1356/529, loss: 0.0019905089866369963
2023-01-23 03:17:03.144041: step: 1360/529, loss: 0.006911182310432196
2023-01-23 03:17:04.330901: step: 1364/529, loss: 0.03901968151330948
2023-01-23 03:17:05.516771: step: 1368/529, loss: 0.02261362038552761
2023-01-23 03:17:06.739859: step: 1372/529, loss: 0.0022178650833666325
2023-01-23 03:17:07.935292: step: 1376/529, loss: 0.0070931436493992805
2023-01-23 03:17:09.147082: step: 1380/529, loss: 0.04878511279821396
2023-01-23 03:17:10.350211: step: 1384/529, loss: 0.01128082349896431
2023-01-23 03:17:11.530988: step: 1388/529, loss: 0.0001964569091796875
2023-01-23 03:17:12.717113: step: 1392/529, loss: 0.0005277633899822831
2023-01-23 03:17:13.936662: step: 1396/529, loss: 0.003966141026467085
2023-01-23 03:17:15.108311: step: 1400/529, loss: 0.021597862243652344
2023-01-23 03:17:16.330359: step: 1404/529, loss: 0.013552665710449219
2023-01-23 03:17:17.523705: step: 1408/529, loss: 0.0006745815626345575
2023-01-23 03:17:18.722148: step: 1412/529, loss: 0.019646883010864258
2023-01-23 03:17:19.974308: step: 1416/529, loss: 0.010751819238066673
2023-01-23 03:17:21.181285: step: 1420/529, loss: 0.017238998785614967
2023-01-23 03:17:22.347174: step: 1424/529, loss: 3.900528099620715e-05
2023-01-23 03:17:23.546435: step: 1428/529, loss: 0.0016060828929767013
2023-01-23 03:17:24.718998: step: 1432/529, loss: 0.002705526538193226
2023-01-23 03:17:25.934204: step: 1436/529, loss: 0.002124214079231024
2023-01-23 03:17:27.181046: step: 1440/529, loss: 0.00521926861256361
2023-01-23 03:17:28.366254: step: 1444/529, loss: 0.24625560641288757
2023-01-23 03:17:29.547290: step: 1448/529, loss: 0.0007156372303143144
2023-01-23 03:17:30.744249: step: 1452/529, loss: 0.0061820982955396175
2023-01-23 03:17:31.947844: step: 1456/529, loss: 0.0010063170921057463
2023-01-23 03:17:33.147647: step: 1460/529, loss: 0.3570823669433594
2023-01-23 03:17:34.341853: step: 1464/529, loss: 0.0005876541254110634
2023-01-23 03:17:35.535286: step: 1468/529, loss: 0.0010268212063238025
2023-01-23 03:17:36.734158: step: 1472/529, loss: 0.00039510728674940765
2023-01-23 03:17:37.889541: step: 1476/529, loss: 0.00904550589621067
2023-01-23 03:17:39.093856: step: 1480/529, loss: 0.013424396514892578
2023-01-23 03:17:40.290408: step: 1484/529, loss: 0.001997566083446145
2023-01-23 03:17:41.492925: step: 1488/529, loss: 0.01690368726849556
2023-01-23 03:17:42.686693: step: 1492/529, loss: 0.01404027920216322
2023-01-23 03:17:43.909575: step: 1496/529, loss: 0.00025777818518690765
2023-01-23 03:17:45.072295: step: 1500/529, loss: 0.0012628554832190275
2023-01-23 03:17:46.231244: step: 1504/529, loss: 0.003780364990234375
2023-01-23 03:17:47.443480: step: 1508/529, loss: 0.0034401954617351294
2023-01-23 03:17:48.681561: step: 1512/529, loss: 0.00096044538076967
2023-01-23 03:17:49.862532: step: 1516/529, loss: 0.017782973125576973
2023-01-23 03:17:51.048757: step: 1520/529, loss: 0.021206380799412727
2023-01-23 03:17:52.280861: step: 1524/529, loss: 0.029020071029663086
2023-01-23 03:17:53.463215: step: 1528/529, loss: 0.0018839358817785978
2023-01-23 03:17:54.703316: step: 1532/529, loss: 0.001266098115593195
2023-01-23 03:17:55.866989: step: 1536/529, loss: 0.004473114386200905
2023-01-23 03:17:57.072468: step: 1540/529, loss: 0.07688990235328674
2023-01-23 03:17:58.310025: step: 1544/529, loss: 0.0014057159423828125
2023-01-23 03:17:59.508003: step: 1548/529, loss: 0.03889627382159233
2023-01-23 03:18:00.713959: step: 1552/529, loss: 2.4414061044808477e-05
2023-01-23 03:18:01.947665: step: 1556/529, loss: 0.01679687574505806
2023-01-23 03:18:03.143198: step: 1560/529, loss: 0.003276014467701316
2023-01-23 03:18:04.362125: step: 1564/529, loss: 0.012526988983154297
2023-01-23 03:18:05.559387: step: 1568/529, loss: 0.0015130043029785156
2023-01-23 03:18:06.719117: step: 1572/529, loss: 0.00183448800817132
2023-01-23 03:18:07.887826: step: 1576/529, loss: 0.02165050618350506
2023-01-23 03:18:09.058685: step: 1580/529, loss: 0.01760711707174778
2023-01-23 03:18:10.271568: step: 1584/529, loss: 0.007588768377900124
2023-01-23 03:18:11.486301: step: 1588/529, loss: 1.71661376953125e-05
2023-01-23 03:18:12.676294: step: 1592/529, loss: 0.008407974615693092
2023-01-23 03:18:13.841919: step: 1596/529, loss: 0.0005439758533611894
2023-01-23 03:18:15.017852: step: 1600/529, loss: 0.03986234590411186
2023-01-23 03:18:16.268556: step: 1604/529, loss: 0.000877761805895716
2023-01-23 03:18:17.458572: step: 1608/529, loss: 0.016019631177186966
2023-01-23 03:18:18.639464: step: 1612/529, loss: 0.002694988390430808
2023-01-23 03:18:19.829023: step: 1616/529, loss: 0.0005079269176349044
2023-01-23 03:18:21.003200: step: 1620/529, loss: 0.0021526336204260588
2023-01-23 03:18:22.252442: step: 1624/529, loss: 0.035662271082401276
2023-01-23 03:18:23.467924: step: 1628/529, loss: 1.068115216185106e-05
2023-01-23 03:18:24.674350: step: 1632/529, loss: 0.00200653076171875
2023-01-23 03:18:25.894045: step: 1636/529, loss: 0.013348388485610485
2023-01-23 03:18:27.103988: step: 1640/529, loss: 0.6704956889152527
2023-01-23 03:18:28.285236: step: 1644/529, loss: 0.007969331927597523
2023-01-23 03:18:29.474255: step: 1648/529, loss: 0.0027492523659020662
2023-01-23 03:18:30.625603: step: 1652/529, loss: 0.002999591873958707
2023-01-23 03:18:31.813904: step: 1656/529, loss: 0.047217655926942825
2023-01-23 03:18:33.021681: step: 1660/529, loss: 0.07541093975305557
2023-01-23 03:18:34.241560: step: 1664/529, loss: 0.0128333093598485
2023-01-23 03:18:35.451610: step: 1668/529, loss: 0.018995190039277077
2023-01-23 03:18:36.670124: step: 1672/529, loss: 0.00039949416532181203
2023-01-23 03:18:37.848803: step: 1676/529, loss: 0.0001434326113667339
2023-01-23 03:18:39.075846: step: 1680/529, loss: 0.011221122927963734
2023-01-23 03:18:40.256307: step: 1684/529, loss: 0.0006533623090945184
2023-01-23 03:18:41.467117: step: 1688/529, loss: 0.026187706738710403
2023-01-23 03:18:42.643268: step: 1692/529, loss: 0.051987841725349426
2023-01-23 03:18:43.812810: step: 1696/529, loss: 0.0020817758049815893
2023-01-23 03:18:44.997047: step: 1700/529, loss: 0.014611244201660156
2023-01-23 03:18:46.157655: step: 1704/529, loss: 0.015263748355209827
2023-01-23 03:18:47.316050: step: 1708/529, loss: 0.0015641212230548263
2023-01-23 03:18:48.509000: step: 1712/529, loss: 0.003006553743034601
2023-01-23 03:18:49.712911: step: 1716/529, loss: 0.04374561086297035
2023-01-23 03:18:50.890173: step: 1720/529, loss: 0.0007204055436886847
2023-01-23 03:18:52.085449: step: 1724/529, loss: 0.003359937807545066
2023-01-23 03:18:53.268880: step: 1728/529, loss: 0.005859375465661287
2023-01-23 03:18:54.546206: step: 1732/529, loss: 0.03243722766637802
2023-01-23 03:18:55.746118: step: 1736/529, loss: 7.114410254871473e-05
2023-01-23 03:18:56.934050: step: 1740/529, loss: 0.1302306205034256
2023-01-23 03:18:58.104361: step: 1744/529, loss: 0.03613262251019478
2023-01-23 03:18:59.307995: step: 1748/529, loss: 0.0005180359003134072
2023-01-23 03:19:00.521865: step: 1752/529, loss: 0.007503319066017866
2023-01-23 03:19:01.773558: step: 1756/529, loss: 0.04974937438964844
2023-01-23 03:19:02.959310: step: 1760/529, loss: 0.01761932484805584
2023-01-23 03:19:04.124551: step: 1764/529, loss: 0.0006916046258993447
2023-01-23 03:19:05.318992: step: 1768/529, loss: 0.005828857421875
2023-01-23 03:19:06.548452: step: 1772/529, loss: 0.006870460696518421
2023-01-23 03:19:07.720524: step: 1776/529, loss: 0.0004364967462606728
2023-01-23 03:19:08.915383: step: 1780/529, loss: 0.0002768516424112022
2023-01-23 03:19:10.099550: step: 1784/529, loss: 0.0021639822516590357
2023-01-23 03:19:11.319086: step: 1788/529, loss: 0.006115913391113281
2023-01-23 03:19:12.487478: step: 1792/529, loss: 0.0001923561212606728
2023-01-23 03:19:13.705132: step: 1796/529, loss: 0.00017061234393622726
2023-01-23 03:19:14.874879: step: 1800/529, loss: 0.006600570864975452
2023-01-23 03:19:16.085293: step: 1804/529, loss: 0.0006340027321130037
2023-01-23 03:19:17.266797: step: 1808/529, loss: 0.0011976242531090975
2023-01-23 03:19:18.521262: step: 1812/529, loss: 8.459091623080894e-05
2023-01-23 03:19:19.725547: step: 1816/529, loss: 0.03202095255255699
2023-01-23 03:19:20.927514: step: 1820/529, loss: 0.019614791497588158
2023-01-23 03:19:22.101935: step: 1824/529, loss: 3.604888843256049e-05
2023-01-23 03:19:23.344377: step: 1828/529, loss: 0.00018167495727539062
2023-01-23 03:19:24.585740: step: 1832/529, loss: 0.0374908447265625
2023-01-23 03:19:25.789590: step: 1836/529, loss: 0.017992116510868073
2023-01-23 03:19:27.008011: step: 1840/529, loss: 0.04459953308105469
2023-01-23 03:19:28.229308: step: 1844/529, loss: 0.007378006353974342
2023-01-23 03:19:29.505019: step: 1848/529, loss: 0.0009414672967977822
2023-01-23 03:19:30.695204: step: 1852/529, loss: 0.005203342530876398
2023-01-23 03:19:31.909932: step: 1856/529, loss: 1.5543813705444336
2023-01-23 03:19:33.151657: step: 1860/529, loss: 0.0008533477666787803
2023-01-23 03:19:34.320064: step: 1864/529, loss: 0.004583168309181929
2023-01-23 03:19:35.519653: step: 1868/529, loss: 0.00023059846716932952
2023-01-23 03:19:36.687141: step: 1872/529, loss: 0.06282377243041992
2023-01-23 03:19:37.899572: step: 1876/529, loss: 0.0007351875538006425
2023-01-23 03:19:39.081900: step: 1880/529, loss: 0.0001617431698832661
2023-01-23 03:19:40.284712: step: 1884/529, loss: -4.863738922722405e-06
2023-01-23 03:19:41.449771: step: 1888/529, loss: 0.013444977812469006
2023-01-23 03:19:42.651713: step: 1892/529, loss: 0.06164093315601349
2023-01-23 03:19:43.826144: step: 1896/529, loss: 0.009922981262207031
2023-01-23 03:19:45.068318: step: 1900/529, loss: 0.026669027283787727
2023-01-23 03:19:46.283972: step: 1904/529, loss: 0.012551403604447842
2023-01-23 03:19:47.518418: step: 1908/529, loss: 0.2914290428161621
2023-01-23 03:19:48.716132: step: 1912/529, loss: 0.012662124820053577
2023-01-23 03:19:49.897787: step: 1916/529, loss: 0.0052946568466722965
2023-01-23 03:19:51.062383: step: 1920/529, loss: 0.07859744876623154
2023-01-23 03:19:52.255875: step: 1924/529, loss: 0.046630859375
2023-01-23 03:19:53.448445: step: 1928/529, loss: 0.0011096000671386719
2023-01-23 03:19:54.625721: step: 1932/529, loss: 0.013671446591615677
2023-01-23 03:19:55.859576: step: 1936/529, loss: 0.03882698714733124
2023-01-23 03:19:57.065220: step: 1940/529, loss: 0.016082847490906715
2023-01-23 03:19:58.261232: step: 1944/529, loss: 0.020233154296875
2023-01-23 03:19:59.502825: step: 1948/529, loss: 0.0036792755126953125
2023-01-23 03:20:00.697864: step: 1952/529, loss: 0.00017132758512161672
2023-01-23 03:20:01.926239: step: 1956/529, loss: 0.00024623872013762593
2023-01-23 03:20:03.167276: step: 1960/529, loss: 0.02321949042379856
2023-01-23 03:20:04.396589: step: 1964/529, loss: 0.008112525567412376
2023-01-23 03:20:05.565322: step: 1968/529, loss: 0.008886623196303844
2023-01-23 03:20:06.726885: step: 1972/529, loss: 0.000754880893509835
2023-01-23 03:20:07.935693: step: 1976/529, loss: 0.0007356643909588456
2023-01-23 03:20:09.161662: step: 1980/529, loss: 0.0013558388454839587
2023-01-23 03:20:10.328683: step: 1984/529, loss: 0.008496666327118874
2023-01-23 03:20:11.512664: step: 1988/529, loss: 0.019655991345643997
2023-01-23 03:20:12.696581: step: 1992/529, loss: 0.03364581987261772
2023-01-23 03:20:13.878707: step: 1996/529, loss: 0.00404667854309082
2023-01-23 03:20:15.056308: step: 2000/529, loss: 0.001017761300317943
2023-01-23 03:20:16.275214: step: 2004/529, loss: 0.001706790877506137
2023-01-23 03:20:17.484913: step: 2008/529, loss: 0.006466579623520374
2023-01-23 03:20:18.697721: step: 2012/529, loss: 0.03728752210736275
2023-01-23 03:20:19.892687: step: 2016/529, loss: 0.09564084559679031
2023-01-23 03:20:21.091510: step: 2020/529, loss: 0.0026894567999988794
2023-01-23 03:20:22.271994: step: 2024/529, loss: 0.0015523910988122225
2023-01-23 03:20:23.440991: step: 2028/529, loss: 0.001751708914525807
2023-01-23 03:20:24.599379: step: 2032/529, loss: 0.002993297530338168
2023-01-23 03:20:25.793702: step: 2036/529, loss: 0.0010641098488122225
2023-01-23 03:20:26.987663: step: 2040/529, loss: 0.10790844261646271
2023-01-23 03:20:28.161656: step: 2044/529, loss: 0.0006014824029989541
2023-01-23 03:20:29.349632: step: 2048/529, loss: 0.00023059846716932952
2023-01-23 03:20:30.537657: step: 2052/529, loss: 0.0009954452980309725
2023-01-23 03:20:31.733078: step: 2056/529, loss: 0.04278812184929848
2023-01-23 03:20:32.962868: step: 2060/529, loss: 0.0279101375490427
2023-01-23 03:20:34.174269: step: 2064/529, loss: 0.0009799957042559981
2023-01-23 03:20:35.389370: step: 2068/529, loss: 0.5962082147598267
2023-01-23 03:20:36.563932: step: 2072/529, loss: 0.0005461692926473916
2023-01-23 03:20:37.786936: step: 2076/529, loss: 0.00013847352238371968
2023-01-23 03:20:38.976163: step: 2080/529, loss: 0.017247533425688744
2023-01-23 03:20:40.243995: step: 2084/529, loss: 0.02177906036376953
2023-01-23 03:20:41.399952: step: 2088/529, loss: 0.0005646705394610763
2023-01-23 03:20:42.566720: step: 2092/529, loss: 0.0012795449001714587
2023-01-23 03:20:43.759780: step: 2096/529, loss: 0.005169391632080078
2023-01-23 03:20:44.996814: step: 2100/529, loss: 0.005059337709099054
2023-01-23 03:20:46.187691: step: 2104/529, loss: 0.0015271187294274569
2023-01-23 03:20:47.365061: step: 2108/529, loss: 0.00047559739323332906
2023-01-23 03:20:48.533600: step: 2112/529, loss: 0.004547024145722389
2023-01-23 03:20:49.695747: step: 2116/529, loss: 0.004264927469193935
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.5826693227091634, 'r': 0.7789613848202397, 'f1': 0.6666666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6177145479577788, 'r': 0.8064709406830437, 'f1': 0.6995841995841996}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5487804878048781, 'r': 0.8333333333333334, 'f1': 0.6617647058823529}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.5245901639344263, 'r': 0.5079365079365079, 'f1': 0.5161290322580645}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.4146341463414634, 'r': 0.4722222222222222, 'f1': 0.4415584415584415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 03:21:33.818228: step: 4/529, loss: 0.003536258591338992
2023-01-23 03:21:35.023262: step: 8/529, loss: 0.00401649484410882
2023-01-23 03:21:36.224840: step: 12/529, loss: 0.009791756048798561
2023-01-23 03:21:37.415573: step: 16/529, loss: 0.03188343346118927
2023-01-23 03:21:38.582811: step: 20/529, loss: 5.500912811839953e-05
2023-01-23 03:21:39.772942: step: 24/529, loss: 0.008395016193389893
2023-01-23 03:21:40.958416: step: 28/529, loss: 0.0025276183150708675
2023-01-23 03:21:42.175256: step: 32/529, loss: 0.02211780659854412
2023-01-23 03:21:43.364815: step: 36/529, loss: 0.001338195870630443
2023-01-23 03:21:44.537187: step: 40/529, loss: 0.0004429817199707031
2023-01-23 03:21:45.762657: step: 44/529, loss: 0.022576140239834785
2023-01-23 03:21:46.958817: step: 48/529, loss: 0.01085510291159153
2023-01-23 03:21:48.164547: step: 52/529, loss: 1.411438006471144e-05
2023-01-23 03:21:49.363773: step: 56/529, loss: 0.043985746800899506
2023-01-23 03:21:50.566435: step: 60/529, loss: 0.0011208534706383944
2023-01-23 03:21:51.762026: step: 64/529, loss: 0.02612333372235298
2023-01-23 03:21:52.989131: step: 68/529, loss: 0.005660533905029297
2023-01-23 03:21:54.204532: step: 72/529, loss: 0.015165328979492188
2023-01-23 03:21:55.389866: step: 76/529, loss: 0.0007496834150515497
2023-01-23 03:21:56.588209: step: 80/529, loss: 0.00016832351684570312
2023-01-23 03:21:57.810464: step: 84/529, loss: 0.011369897052645683
2023-01-23 03:21:58.976147: step: 88/529, loss: 0.00012662410154007375
2023-01-23 03:22:00.166662: step: 92/529, loss: 0.0035753250122070312
2023-01-23 03:22:01.366835: step: 96/529, loss: 0.00040302277193404734
2023-01-23 03:22:02.558457: step: 100/529, loss: 0.0001674652157817036
2023-01-23 03:22:03.756815: step: 104/529, loss: 0.00047588348388671875
2023-01-23 03:22:04.989918: step: 108/529, loss: 0.029589273035526276
2023-01-23 03:22:06.136106: step: 112/529, loss: 4.854202416026965e-05
2023-01-23 03:22:07.308831: step: 116/529, loss: 0.005323315039277077
2023-01-23 03:22:08.499663: step: 120/529, loss: 0.0034019469749182463
2023-01-23 03:22:09.689622: step: 124/529, loss: 0.00132579798810184
2023-01-23 03:22:10.907807: step: 128/529, loss: 0.0004345893976278603
2023-01-23 03:22:12.089779: step: 132/529, loss: 0.00021781922259833664
2023-01-23 03:22:13.285793: step: 136/529, loss: 3.6239621294953395e-06
2023-01-23 03:22:14.513325: step: 140/529, loss: 0.004038429353386164
2023-01-23 03:22:15.719371: step: 144/529, loss: 2.6416779292048886e-05
2023-01-23 03:22:16.918117: step: 148/529, loss: 0.03313455358147621
2023-01-23 03:22:18.073775: step: 152/529, loss: 0.0026945113204419613
2023-01-23 03:22:19.280748: step: 156/529, loss: 0.0006809235201217234
2023-01-23 03:22:20.432104: step: 160/529, loss: 0.01350097730755806
2023-01-23 03:22:21.603349: step: 164/529, loss: 0.00012521744065452367
2023-01-23 03:22:22.762840: step: 168/529, loss: 0.011375904083251953
2023-01-23 03:22:23.958790: step: 172/529, loss: 0.010783863253891468
2023-01-23 03:22:25.190021: step: 176/529, loss: 0.005101298913359642
2023-01-23 03:22:26.391680: step: 180/529, loss: 0.03699932247400284
2023-01-23 03:22:27.586537: step: 184/529, loss: 0.04721546173095703
2023-01-23 03:22:28.804731: step: 188/529, loss: 0.0003075599961448461
2023-01-23 03:22:30.097889: step: 192/529, loss: 0.008887100033462048
2023-01-23 03:22:31.278416: step: 196/529, loss: 0.0007946014520712197
2023-01-23 03:22:32.454445: step: 200/529, loss: 0.00021104812913108617
2023-01-23 03:22:33.656516: step: 204/529, loss: 0.00012912749662064016
2023-01-23 03:22:34.838341: step: 208/529, loss: 7.162988367781509e-06
2023-01-23 03:22:36.041923: step: 212/529, loss: 0.0015114308334887028
2023-01-23 03:22:37.217392: step: 216/529, loss: 0.019399071112275124
2023-01-23 03:22:38.407826: step: 220/529, loss: 0.006062602624297142
2023-01-23 03:22:39.564616: step: 224/529, loss: 0.0007863998180255294
2023-01-23 03:22:40.774528: step: 228/529, loss: 0.0009471893426962197
2023-01-23 03:22:41.963456: step: 232/529, loss: 0.025431107729673386
2023-01-23 03:22:43.177058: step: 236/529, loss: 0.03290128707885742
2023-01-23 03:22:44.352276: step: 240/529, loss: 0.02950897254049778
2023-01-23 03:22:45.559612: step: 244/529, loss: 0.0008078575483523309
2023-01-23 03:22:46.777358: step: 248/529, loss: 0.0052238465286791325
2023-01-23 03:22:47.944745: step: 252/529, loss: 0.0016533373855054379
2023-01-23 03:22:49.121991: step: 256/529, loss: 0.009891225025057793
2023-01-23 03:22:50.278256: step: 260/529, loss: 0.00014419555373024195
2023-01-23 03:22:51.515313: step: 264/529, loss: 0.03104419820010662
2023-01-23 03:22:52.731362: step: 268/529, loss: 0.013837910257279873
2023-01-23 03:22:53.917802: step: 272/529, loss: 0.00020356177992653102
2023-01-23 03:22:55.065583: step: 276/529, loss: 0.0030412673950195312
2023-01-23 03:22:56.282079: step: 280/529, loss: 0.004071045201271772
2023-01-23 03:22:57.509307: step: 284/529, loss: 0.012658214196562767
2023-01-23 03:22:58.659565: step: 288/529, loss: 0.0003450393851380795
2023-01-23 03:22:59.823883: step: 292/529, loss: 0.10960173606872559
2023-01-23 03:23:00.985282: step: 296/529, loss: 8.034706115722656e-05
2023-01-23 03:23:02.181342: step: 300/529, loss: 0.0008501053089275956
2023-01-23 03:23:03.354316: step: 304/529, loss: 0.0015618324978277087
2023-01-23 03:23:04.567902: step: 308/529, loss: 0.00710296630859375
2023-01-23 03:23:05.830107: step: 312/529, loss: 6.50405854685232e-05
2023-01-23 03:23:07.020077: step: 316/529, loss: 0.1365833580493927
2023-01-23 03:23:08.218272: step: 320/529, loss: 0.0015281677478924394
2023-01-23 03:23:09.463640: step: 324/529, loss: 0.005007743835449219
2023-01-23 03:23:10.662033: step: 328/529, loss: 0.0002971649228129536
2023-01-23 03:23:11.872121: step: 332/529, loss: 0.004324436187744141
2023-01-23 03:23:13.070580: step: 336/529, loss: 0.0028727531898766756
2023-01-23 03:23:14.245050: step: 340/529, loss: 0.002777671907097101
2023-01-23 03:23:15.467254: step: 344/529, loss: 0.014994049444794655
2023-01-23 03:23:16.649677: step: 348/529, loss: 0.0023178099654614925
2023-01-23 03:23:17.884952: step: 352/529, loss: 0.023823166266083717
2023-01-23 03:23:19.043949: step: 356/529, loss: 0.006887626834213734
2023-01-23 03:23:20.242733: step: 360/529, loss: 0.00013637542724609375
2023-01-23 03:23:21.451324: step: 364/529, loss: 0.001359653426334262
2023-01-23 03:23:22.638512: step: 368/529, loss: 0.06855068355798721
2023-01-23 03:23:23.823883: step: 372/529, loss: -2.47955313170678e-06
2023-01-23 03:23:25.027234: step: 376/529, loss: 0.0009726047283038497
2023-01-23 03:23:26.209613: step: 380/529, loss: 0.0002743721124716103
2023-01-23 03:23:27.403623: step: 384/529, loss: 0.19169625639915466
2023-01-23 03:23:28.597211: step: 388/529, loss: 0.0013978957431390882
2023-01-23 03:23:29.809350: step: 392/529, loss: 0.003904151963070035
2023-01-23 03:23:31.043981: step: 396/529, loss: 0.0008531571365892887
2023-01-23 03:23:32.224185: step: 400/529, loss: 0.00040855410043150187
2023-01-23 03:23:33.428211: step: 404/529, loss: 0.04409322887659073
2023-01-23 03:23:34.621247: step: 408/529, loss: 0.00435562152415514
2023-01-23 03:23:35.815235: step: 412/529, loss: 0.003629970597103238
2023-01-23 03:23:36.997146: step: 416/529, loss: 1.6975403923424892e-05
2023-01-23 03:23:38.158241: step: 420/529, loss: 0.00011405944678699598
2023-01-23 03:23:39.417341: step: 424/529, loss: 0.0049426318146288395
2023-01-23 03:23:40.598057: step: 428/529, loss: 0.007988596335053444
2023-01-23 03:23:41.785995: step: 432/529, loss: 0.00614242535084486
2023-01-23 03:23:42.974937: step: 436/529, loss: 0.028187084943056107
2023-01-23 03:23:44.185686: step: 440/529, loss: 0.013258266262710094
2023-01-23 03:23:45.363141: step: 444/529, loss: 0.0049720765091478825
2023-01-23 03:23:46.586145: step: 448/529, loss: 0.013359450735151768
2023-01-23 03:23:47.780849: step: 452/529, loss: 0.0017400265205651522
2023-01-23 03:23:49.003150: step: 456/529, loss: 0.0007940292125567794
2023-01-23 03:23:50.198660: step: 460/529, loss: 0.008706379681825638
2023-01-23 03:23:51.369023: step: 464/529, loss: 0.0002285003720317036
2023-01-23 03:23:52.584303: step: 468/529, loss: 0.009459304623305798
2023-01-23 03:23:53.781894: step: 472/529, loss: 0.0020677566062659025
2023-01-23 03:23:54.939209: step: 476/529, loss: 2.1123885744600557e-05
2023-01-23 03:23:56.112909: step: 480/529, loss: 0.08410850167274475
2023-01-23 03:23:57.342162: step: 484/529, loss: 0.00011711120168911293
2023-01-23 03:23:58.595353: step: 488/529, loss: 0.0040624141693115234
2023-01-23 03:23:59.804257: step: 492/529, loss: 0.0008524894947186112
2023-01-23 03:24:01.003682: step: 496/529, loss: 0.0017962456913664937
2023-01-23 03:24:02.218903: step: 500/529, loss: 0.02494506910443306
2023-01-23 03:24:03.438256: step: 504/529, loss: 0.02695484273135662
2023-01-23 03:24:04.636901: step: 508/529, loss: 0.004578590393066406
2023-01-23 03:24:05.847541: step: 512/529, loss: 0.0003187179390806705
2023-01-23 03:24:07.022030: step: 516/529, loss: 0.00011186600022483617
2023-01-23 03:24:08.215112: step: 520/529, loss: 0.08090553432703018
2023-01-23 03:24:09.406636: step: 524/529, loss: 0.0005354881286621094
2023-01-23 03:24:10.557032: step: 528/529, loss: 0.0222603902220726
2023-01-23 03:24:11.748081: step: 532/529, loss: 0.04537668451666832
2023-01-23 03:24:12.951696: step: 536/529, loss: 0.0017190934158861637
2023-01-23 03:24:14.127547: step: 540/529, loss: 0.004778957460075617
2023-01-23 03:24:15.322634: step: 544/529, loss: 0.0038251876831054688
2023-01-23 03:24:16.497837: step: 548/529, loss: 0.009939384646713734
2023-01-23 03:24:17.710240: step: 552/529, loss: 0.032839205116033554
2023-01-23 03:24:18.919686: step: 556/529, loss: 0.09469451755285263
2023-01-23 03:24:20.118783: step: 560/529, loss: 0.00033283233642578125
2023-01-23 03:24:21.368384: step: 564/529, loss: 0.005995369050651789
2023-01-23 03:24:22.585989: step: 568/529, loss: 0.27593690156936646
2023-01-23 03:24:23.791273: step: 572/529, loss: 0.010373879224061966
2023-01-23 03:24:24.983849: step: 576/529, loss: 8.659363084007055e-05
2023-01-23 03:24:26.226992: step: 580/529, loss: 0.002545595169067383
2023-01-23 03:24:27.411724: step: 584/529, loss: 0.0017949105240404606
2023-01-23 03:24:28.620907: step: 588/529, loss: 0.00016803742619231343
2023-01-23 03:24:29.845709: step: 592/529, loss: 0.00021395683870650828
2023-01-23 03:24:31.014812: step: 596/529, loss: 0.0022533417213708162
2023-01-23 03:24:32.203197: step: 600/529, loss: 0.0010963439708575606
2023-01-23 03:24:33.385251: step: 604/529, loss: 3.8576126826228574e-05
2023-01-23 03:24:34.626908: step: 608/529, loss: 0.2497566193342209
2023-01-23 03:24:35.843828: step: 612/529, loss: 7.24792471373803e-06
2023-01-23 03:24:37.088548: step: 616/529, loss: 0.017292022705078125
2023-01-23 03:24:38.265558: step: 620/529, loss: 0.046401023864746094
2023-01-23 03:24:39.472825: step: 624/529, loss: 0.001372909639030695
2023-01-23 03:24:40.703804: step: 628/529, loss: 9.613037400413305e-05
2023-01-23 03:24:41.901553: step: 632/529, loss: 0.002762699266895652
2023-01-23 03:24:43.099322: step: 636/529, loss: 0.04123172536492348
2023-01-23 03:24:44.284222: step: 640/529, loss: 0.0005984306335449219
2023-01-23 03:24:45.497985: step: 644/529, loss: 0.01367807388305664
2023-01-23 03:24:46.699608: step: 648/529, loss: 0.8617509603500366
2023-01-23 03:24:47.892625: step: 652/529, loss: 0.010860348120331764
2023-01-23 03:24:49.038212: step: 656/529, loss: 0.00017023086547851562
2023-01-23 03:24:50.221987: step: 660/529, loss: 0.0034050941467285156
2023-01-23 03:24:51.445253: step: 664/529, loss: 0.018602848052978516
2023-01-23 03:24:52.632656: step: 668/529, loss: 0.0005172729725018144
2023-01-23 03:24:53.865369: step: 672/529, loss: 0.0017038345104083419
2023-01-23 03:24:54.993528: step: 676/529, loss: 0.010099983774125576
2023-01-23 03:24:56.211925: step: 680/529, loss: 0.021842384710907936
2023-01-23 03:24:57.434126: step: 684/529, loss: 0.0013540268409997225
2023-01-23 03:24:58.634865: step: 688/529, loss: 0.009274386800825596
2023-01-23 03:24:59.859498: step: 692/529, loss: 0.0017917632358148694
2023-01-23 03:25:01.042656: step: 696/529, loss: 0.00023126603628043085
2023-01-23 03:25:02.269984: step: 700/529, loss: 0.001645830343477428
2023-01-23 03:25:03.475754: step: 704/529, loss: 0.0015456199180334806
2023-01-23 03:25:04.658295: step: 708/529, loss: 0.0009533882257528603
2023-01-23 03:25:05.885534: step: 712/529, loss: 0.0005386352422647178
2023-01-23 03:25:07.067287: step: 716/529, loss: 0.000213623046875
2023-01-23 03:25:08.239930: step: 720/529, loss: 0.014083003625273705
2023-01-23 03:25:09.426185: step: 724/529, loss: 5.207061622058973e-05
2023-01-23 03:25:10.644548: step: 728/529, loss: 0.0012840271228924394
2023-01-23 03:25:11.837880: step: 732/529, loss: 0.001161861466243863
2023-01-23 03:25:13.000479: step: 736/529, loss: 3.519058373058215e-05
2023-01-23 03:25:14.255015: step: 740/529, loss: 0.02496509626507759
2023-01-23 03:25:15.491860: step: 744/529, loss: 3.0517578125e-05
2023-01-23 03:25:16.724002: step: 748/529, loss: -1.5258788153005298e-06
2023-01-23 03:25:17.927084: step: 752/529, loss: 0.06933784484863281
2023-01-23 03:25:19.149808: step: 756/529, loss: 0.004029512405395508
2023-01-23 03:25:20.381198: step: 760/529, loss: 0.00035624505835585296
2023-01-23 03:25:21.573457: step: 764/529, loss: 0.030359458178281784
2023-01-23 03:25:22.802247: step: 768/529, loss: 4.2724612285383046e-05
2023-01-23 03:25:24.035682: step: 772/529, loss: 0.09139309078454971
2023-01-23 03:25:25.230296: step: 776/529, loss: 0.0003488540824037045
2023-01-23 03:25:26.480555: step: 780/529, loss: 0.037384990602731705
2023-01-23 03:25:27.680543: step: 784/529, loss: 0.04303741455078125
2023-01-23 03:25:28.881208: step: 788/529, loss: 0.0006812095525674522
2023-01-23 03:25:30.051669: step: 792/529, loss: 0.0005521774291992188
2023-01-23 03:25:31.202046: step: 796/529, loss: 0.0057732341811060905
2023-01-23 03:25:32.450028: step: 800/529, loss: 0.002682304475456476
2023-01-23 03:25:33.644417: step: 804/529, loss: 0.0033542632590979338
2023-01-23 03:25:34.842390: step: 808/529, loss: 0.01537857111543417
2023-01-23 03:25:36.011939: step: 812/529, loss: 0.004690742585808039
2023-01-23 03:25:37.277839: step: 816/529, loss: 0.008952331729233265
2023-01-23 03:25:38.560219: step: 820/529, loss: 0.0034716606605798006
2023-01-23 03:25:39.761496: step: 824/529, loss: 0.0033850669860839844
2023-01-23 03:25:41.012158: step: 828/529, loss: 0.001586818601936102
2023-01-23 03:25:42.171083: step: 832/529, loss: 0.00036578180151991546
2023-01-23 03:25:43.391233: step: 836/529, loss: 0.040811728686094284
2023-01-23 03:25:44.564573: step: 840/529, loss: 0.007379340939223766
2023-01-23 03:25:45.778276: step: 844/529, loss: 0.0026514052879065275
2023-01-23 03:25:47.009451: step: 848/529, loss: 0.011712265200912952
2023-01-23 03:25:48.232761: step: 852/529, loss: 0.5419204235076904
2023-01-23 03:25:49.401231: step: 856/529, loss: 0.008180045522749424
2023-01-23 03:25:50.638060: step: 860/529, loss: 0.00390453333966434
2023-01-23 03:25:51.827343: step: 864/529, loss: 0.04202689975500107
2023-01-23 03:25:53.003583: step: 868/529, loss: 0.0007396817090921104
2023-01-23 03:25:54.239502: step: 872/529, loss: 0.00846948567777872
2023-01-23 03:25:55.461034: step: 876/529, loss: 0.0719936341047287
2023-01-23 03:25:56.653550: step: 880/529, loss: 0.00221843714825809
2023-01-23 03:25:57.919016: step: 884/529, loss: 0.004226875491440296
2023-01-23 03:25:59.128095: step: 888/529, loss: 0.021477794274687767
2023-01-23 03:26:00.320942: step: 892/529, loss: 0.03520527109503746
2023-01-23 03:26:01.527798: step: 896/529, loss: 0.00015630721463821828
2023-01-23 03:26:02.688113: step: 900/529, loss: 0.012874030508100986
2023-01-23 03:26:03.829629: step: 904/529, loss: 5.3882598876953125e-05
2023-01-23 03:26:05.000373: step: 908/529, loss: 0.03362884745001793
2023-01-23 03:26:06.198467: step: 912/529, loss: 0.0075553893111646175
2023-01-23 03:26:07.388480: step: 916/529, loss: 0.0011791229480877519
2023-01-23 03:26:08.568253: step: 920/529, loss: 0.3843654692173004
2023-01-23 03:26:09.750492: step: 924/529, loss: 0.023404695093631744
2023-01-23 03:26:10.965378: step: 928/529, loss: 5.455017162603326e-05
2023-01-23 03:26:12.198543: step: 932/529, loss: 0.039823438972234726
2023-01-23 03:26:13.416582: step: 936/529, loss: 0.003694439074024558
2023-01-23 03:26:14.584783: step: 940/529, loss: 0.021706486120820045
2023-01-23 03:26:15.749812: step: 944/529, loss: 7.934570021461695e-05
2023-01-23 03:26:16.942994: step: 948/529, loss: 0.008457946591079235
2023-01-23 03:26:18.084542: step: 952/529, loss: 0.0008961677667684853
2023-01-23 03:26:19.316370: step: 956/529, loss: 0.00037422182504087687
2023-01-23 03:26:20.467747: step: 960/529, loss: 0.005460643675178289
2023-01-23 03:26:21.658263: step: 964/529, loss: 0.02651066705584526
2023-01-23 03:26:22.866341: step: 968/529, loss: 7.629394644936838e-07
2023-01-23 03:26:24.031049: step: 972/529, loss: 6.637573096668348e-05
2023-01-23 03:26:25.274252: step: 976/529, loss: 0.002395438961684704
2023-01-23 03:26:26.472029: step: 980/529, loss: 0.0043611531145870686
2023-01-23 03:26:27.661130: step: 984/529, loss: 0.010830879211425781
2023-01-23 03:26:28.890272: step: 988/529, loss: 0.017606543377041817
2023-01-23 03:26:30.078800: step: 992/529, loss: 0.012253857217729092
2023-01-23 03:26:31.231571: step: 996/529, loss: 4.653930591302924e-05
2023-01-23 03:26:32.506092: step: 1000/529, loss: 9.5367431640625e-06
2023-01-23 03:26:33.738559: step: 1004/529, loss: 0.025669097900390625
2023-01-23 03:26:34.936830: step: 1008/529, loss: 0.0023054121993482113
2023-01-23 03:26:36.118209: step: 1012/529, loss: 0.0008772372966632247
2023-01-23 03:26:37.304926: step: 1016/529, loss: 0.00021200180344749242
2023-01-23 03:26:38.501891: step: 1020/529, loss: 0.0025230408646166325
2023-01-23 03:26:39.715443: step: 1024/529, loss: 0.012245750986039639
2023-01-23 03:26:40.902736: step: 1028/529, loss: 0.022622013464570045
2023-01-23 03:26:42.119046: step: 1032/529, loss: 0.0014062881236895919
2023-01-23 03:26:43.298593: step: 1036/529, loss: 0.00652656564489007
2023-01-23 03:26:44.459106: step: 1040/529, loss: 0.0006211280706338584
2023-01-23 03:26:45.728699: step: 1044/529, loss: 0.05848102644085884
2023-01-23 03:26:46.876516: step: 1048/529, loss: 0.0018608197569847107
2023-01-23 03:26:48.098573: step: 1052/529, loss: 0.005982398986816406
2023-01-23 03:26:49.297074: step: 1056/529, loss: 0.013392448425292969
2023-01-23 03:26:50.564359: step: 1060/529, loss: 0.012042808346450329
2023-01-23 03:26:51.783462: step: 1064/529, loss: 0.00027179718017578125
2023-01-23 03:26:52.964211: step: 1068/529, loss: 1.716613724056515e-06
2023-01-23 03:26:54.185009: step: 1072/529, loss: 0.00745887728407979
2023-01-23 03:26:55.429520: step: 1076/529, loss: 0.05139007419347763
2023-01-23 03:26:56.616401: step: 1080/529, loss: 0.0003081798495259136
2023-01-23 03:26:57.802756: step: 1084/529, loss: 0.004885197151452303
2023-01-23 03:26:59.035565: step: 1088/529, loss: 0.01110916119068861
2023-01-23 03:27:00.231234: step: 1092/529, loss: 0.0004084586980752647
2023-01-23 03:27:01.461907: step: 1096/529, loss: 9.14573683985509e-05
2023-01-23 03:27:02.684633: step: 1100/529, loss: 0.0012966155773028731
2023-01-23 03:27:03.882290: step: 1104/529, loss: 0.0002846241113729775
2023-01-23 03:27:05.059660: step: 1108/529, loss: 0.025937365368008614
2023-01-23 03:27:06.258892: step: 1112/529, loss: 0.030796300619840622
2023-01-23 03:27:07.457574: step: 1116/529, loss: 0.0004399299796205014
2023-01-23 03:27:08.647498: step: 1120/529, loss: 0.00017662048048805445
2023-01-23 03:27:09.844363: step: 1124/529, loss: 0.019646836444735527
2023-01-23 03:27:11.060005: step: 1128/529, loss: 0.008589553646743298
2023-01-23 03:27:12.275586: step: 1132/529, loss: 0.0024746893905103207
2023-01-23 03:27:13.446777: step: 1136/529, loss: 0.00013790131197310984
2023-01-23 03:27:14.650457: step: 1140/529, loss: 0.015877723693847656
2023-01-23 03:27:15.835790: step: 1144/529, loss: 0.0019639015663415194
2023-01-23 03:27:17.058866: step: 1148/529, loss: 0.00019588469876907766
2023-01-23 03:27:18.298912: step: 1152/529, loss: 0.0010656355880200863
2023-01-23 03:27:19.488566: step: 1156/529, loss: 3.4809113458322827e-06
2023-01-23 03:27:20.676520: step: 1160/529, loss: 0.017291545867919922
2023-01-23 03:27:21.850826: step: 1164/529, loss: 0.08784690499305725
2023-01-23 03:27:23.046517: step: 1168/529, loss: 0.006003189366310835
2023-01-23 03:27:24.329802: step: 1172/529, loss: 0.06397876888513565
2023-01-23 03:27:25.481429: step: 1176/529, loss: 4.5108794438419864e-05
2023-01-23 03:27:26.672949: step: 1180/529, loss: 0.03741512447595596
2023-01-23 03:27:27.892437: step: 1184/529, loss: 0.03997192531824112
2023-01-23 03:27:29.093853: step: 1188/529, loss: 0.00814743060618639
2023-01-23 03:27:30.367552: step: 1192/529, loss: 0.0019296647515147924
2023-01-23 03:27:31.540112: step: 1196/529, loss: 0.007316398434340954
2023-01-23 03:27:32.790805: step: 1200/529, loss: 0.005738449282944202
2023-01-23 03:27:33.992631: step: 1204/529, loss: 0.011988830752670765
2023-01-23 03:27:35.186978: step: 1208/529, loss: 0.0002483367861714214
2023-01-23 03:27:36.397538: step: 1212/529, loss: 0.012173938564956188
2023-01-23 03:27:37.607128: step: 1216/529, loss: 0.008593368344008923
2023-01-23 03:27:38.809309: step: 1220/529, loss: 0.002732848981395364
2023-01-23 03:27:39.968634: step: 1224/529, loss: 0.001075363252311945
2023-01-23 03:27:41.194622: step: 1228/529, loss: 0.0035504342522472143
2023-01-23 03:27:42.361081: step: 1232/529, loss: 0.01102523785084486
2023-01-23 03:27:43.558745: step: 1236/529, loss: 1.0433621406555176
2023-01-23 03:27:44.797538: step: 1240/529, loss: 0.005492592230439186
2023-01-23 03:27:45.988773: step: 1244/529, loss: 0.009107494726777077
2023-01-23 03:27:47.271898: step: 1248/529, loss: 0.0006118774181231856
2023-01-23 03:27:48.429132: step: 1252/529, loss: 0.0015988349914550781
2023-01-23 03:27:49.645238: step: 1256/529, loss: 0.0009424209711141884
2023-01-23 03:27:50.815571: step: 1260/529, loss: 0.0021330832969397306
2023-01-23 03:27:51.997282: step: 1264/529, loss: 0.0034543040674179792
2023-01-23 03:27:53.221735: step: 1268/529, loss: 0.02487774007022381
2023-01-23 03:27:54.407920: step: 1272/529, loss: 0.001723480294458568
2023-01-23 03:27:55.627471: step: 1276/529, loss: -2.9563905172835803e-06
2023-01-23 03:27:56.803009: step: 1280/529, loss: 0.1012289971113205
2023-01-23 03:27:57.997234: step: 1284/529, loss: 0.012979316525161266
2023-01-23 03:27:59.202129: step: 1288/529, loss: 0.03601064905524254
2023-01-23 03:28:00.373542: step: 1292/529, loss: 0.017980385571718216
2023-01-23 03:28:01.580778: step: 1296/529, loss: 0.029918862506747246
2023-01-23 03:28:02.763050: step: 1300/529, loss: 0.04778280481696129
2023-01-23 03:28:03.956514: step: 1304/529, loss: 0.0007806778303347528
2023-01-23 03:28:05.193565: step: 1308/529, loss: 0.013626289553940296
2023-01-23 03:28:06.362088: step: 1312/529, loss: 2.117157055181451e-05
2023-01-23 03:28:07.531287: step: 1316/529, loss: 0.015629006549715996
2023-01-23 03:28:08.742977: step: 1320/529, loss: 0.00102491385769099
2023-01-23 03:28:09.946459: step: 1324/529, loss: 0.03168588876724243
2023-01-23 03:28:11.161132: step: 1328/529, loss: 0.08364677429199219
2023-01-23 03:28:12.368732: step: 1332/529, loss: 6.54130744934082
2023-01-23 03:28:13.518893: step: 1336/529, loss: 0.10628020763397217
2023-01-23 03:28:14.692039: step: 1340/529, loss: 0.0005728721152991056
2023-01-23 03:28:15.895975: step: 1344/529, loss: 0.0016220093239098787
2023-01-23 03:28:17.066835: step: 1348/529, loss: 0.003975295927375555
2023-01-23 03:28:18.269218: step: 1352/529, loss: 0.0009122848859988153
2023-01-23 03:28:19.462549: step: 1356/529, loss: 0.006723451893776655
2023-01-23 03:28:20.649477: step: 1360/529, loss: 0.00216426863335073
2023-01-23 03:28:21.869393: step: 1364/529, loss: 0.003072547959163785
2023-01-23 03:28:23.045002: step: 1368/529, loss: 0.0002906322479248047
2023-01-23 03:28:24.212268: step: 1372/529, loss: 0.007688426878303289
2023-01-23 03:28:25.405510: step: 1376/529, loss: 0.03008747100830078
2023-01-23 03:28:26.611154: step: 1380/529, loss: 0.09815044701099396
2023-01-23 03:28:27.832841: step: 1384/529, loss: 0.00253047957085073
2023-01-23 03:28:29.037696: step: 1388/529, loss: 0.031522177159786224
2023-01-23 03:28:30.211379: step: 1392/529, loss: 0.004557228181511164
2023-01-23 03:28:31.391129: step: 1396/529, loss: 0.0005568504566326737
2023-01-23 03:28:32.578077: step: 1400/529, loss: 0.019248582422733307
2023-01-23 03:28:33.797484: step: 1404/529, loss: 3.757476952159777e-05
2023-01-23 03:28:34.964259: step: 1408/529, loss: 0.3026461601257324
2023-01-23 03:28:36.156449: step: 1412/529, loss: 0.033855997025966644
2023-01-23 03:28:37.323045: step: 1416/529, loss: 0.001484012696892023
2023-01-23 03:28:38.511007: step: 1420/529, loss: 0.0004883766523562372
2023-01-23 03:28:39.718060: step: 1424/529, loss: 0.00010242462303722277
2023-01-23 03:28:40.909323: step: 1428/529, loss: 0.014437961392104626
2023-01-23 03:28:42.114028: step: 1432/529, loss: 0.025298595428466797
2023-01-23 03:28:43.344050: step: 1436/529, loss: 0.00977945327758789
2023-01-23 03:28:44.524909: step: 1440/529, loss: 0.02181701548397541
2023-01-23 03:28:45.716076: step: 1444/529, loss: 0.01446991041302681
2023-01-23 03:28:46.948350: step: 1448/529, loss: 0.002718687057495117
2023-01-23 03:28:48.155620: step: 1452/529, loss: 0.00040612221346236765
2023-01-23 03:28:49.386533: step: 1456/529, loss: 0.0014866827987134457
2023-01-23 03:28:50.643866: step: 1460/529, loss: 0.025051381438970566
2023-01-23 03:28:51.831743: step: 1464/529, loss: 0.005203437991440296
2023-01-23 03:28:53.076188: step: 1468/529, loss: 0.0014740824699401855
2023-01-23 03:28:54.242594: step: 1472/529, loss: 0.02445850521326065
2023-01-23 03:28:55.433120: step: 1476/529, loss: 0.0006958484882488847
2023-01-23 03:28:56.652050: step: 1480/529, loss: 0.06531887501478195
2023-01-23 03:28:57.846677: step: 1484/529, loss: 0.044643305242061615
2023-01-23 03:28:59.073280: step: 1488/529, loss: 0.004179954528808594
2023-01-23 03:29:00.295709: step: 1492/529, loss: 0.0019033432472497225
2023-01-23 03:29:01.475000: step: 1496/529, loss: 0.0009115219581872225
2023-01-23 03:29:02.700836: step: 1500/529, loss: 0.01475915964692831
2023-01-23 03:29:03.911461: step: 1504/529, loss: 0.01742544211447239
2023-01-23 03:29:05.075575: step: 1508/529, loss: 6.160736666060984e-05
2023-01-23 03:29:06.238222: step: 1512/529, loss: 0.0008149623754434288
2023-01-23 03:29:07.449132: step: 1516/529, loss: 0.0003214835887774825
2023-01-23 03:29:08.639619: step: 1520/529, loss: 0.0006517410511150956
2023-01-23 03:29:09.793550: step: 1524/529, loss: 0.01327667199075222
2023-01-23 03:29:10.981529: step: 1528/529, loss: 0.0025823593605309725
2023-01-23 03:29:12.186034: step: 1532/529, loss: 0.013388633728027344
2023-01-23 03:29:13.423224: step: 1536/529, loss: 0.031649161130189896
2023-01-23 03:29:14.628700: step: 1540/529, loss: 0.0002270221884828061
2023-01-23 03:29:15.813882: step: 1544/529, loss: 0.0012959480518475175
2023-01-23 03:29:17.010514: step: 1548/529, loss: 0.005197572521865368
2023-01-23 03:29:18.207001: step: 1552/529, loss: 0.0027899742126464844
2023-01-23 03:29:19.358161: step: 1556/529, loss: 0.0001034975066431798
2023-01-23 03:29:20.563590: step: 1560/529, loss: 0.004379653837531805
2023-01-23 03:29:21.772121: step: 1564/529, loss: 0.004017258062958717
2023-01-23 03:29:22.982522: step: 1568/529, loss: 0.003856086637824774
2023-01-23 03:29:24.166775: step: 1572/529, loss: 0.001081275986507535
2023-01-23 03:29:25.393222: step: 1576/529, loss: 0.0038760663010179996
2023-01-23 03:29:26.614931: step: 1580/529, loss: 0.0024871828500181437
2023-01-23 03:29:27.804849: step: 1584/529, loss: 0.047409821301698685
2023-01-23 03:29:29.000664: step: 1588/529, loss: 0.0003452301025390625
2023-01-23 03:29:30.154130: step: 1592/529, loss: 2.8038026357535273e-05
2023-01-23 03:29:31.329281: step: 1596/529, loss: 0.0019240856636315584
2023-01-23 03:29:32.488115: step: 1600/529, loss: 0.0010791778331622481
2023-01-23 03:29:33.674203: step: 1604/529, loss: 0.013415718451142311
2023-01-23 03:29:34.889867: step: 1608/529, loss: 0.2130260467529297
2023-01-23 03:29:36.063393: step: 1612/529, loss: 0.001004123711027205
2023-01-23 03:29:37.219216: step: 1616/529, loss: 0.0004294872051104903
2023-01-23 03:29:38.398983: step: 1620/529, loss: 0.001323795411735773
2023-01-23 03:29:39.573452: step: 1624/529, loss: 4.997253563487902e-05
2023-01-23 03:29:40.783211: step: 1628/529, loss: 0.05893135070800781
2023-01-23 03:29:41.942241: step: 1632/529, loss: 0.0002254486025776714
2023-01-23 03:29:43.163473: step: 1636/529, loss: 0.004370022099465132
2023-01-23 03:29:44.339839: step: 1640/529, loss: 0.0016426086658611894
2023-01-23 03:29:45.568186: step: 1644/529, loss: 0.013583755120635033
2023-01-23 03:29:46.783741: step: 1648/529, loss: 0.01568617857992649
2023-01-23 03:29:48.014002: step: 1652/529, loss: 0.10471649467945099
2023-01-23 03:29:49.211871: step: 1656/529, loss: 0.0027340890374034643
2023-01-23 03:29:50.414547: step: 1660/529, loss: 0.003850650740787387
2023-01-23 03:29:51.627578: step: 1664/529, loss: 0.8167505264282227
2023-01-23 03:29:52.801823: step: 1668/529, loss: 0.0005524397129192948
2023-01-23 03:29:53.979085: step: 1672/529, loss: 0.0005867957952432334
2023-01-23 03:29:55.166806: step: 1676/529, loss: 0.004097366705536842
2023-01-23 03:29:56.379841: step: 1680/529, loss: 0.004999065771698952
2023-01-23 03:29:57.573116: step: 1684/529, loss: 0.02600574679672718
2023-01-23 03:29:58.767113: step: 1688/529, loss: 0.012535858899354935
2023-01-23 03:29:59.986848: step: 1692/529, loss: 0.022948648780584335
2023-01-23 03:30:01.204758: step: 1696/529, loss: 0.026111412793397903
2023-01-23 03:30:02.422143: step: 1700/529, loss: 0.01734142377972603
2023-01-23 03:30:03.629554: step: 1704/529, loss: 0.1176968589425087
2023-01-23 03:30:04.776358: step: 1708/529, loss: 0.004532337188720703
2023-01-23 03:30:05.957762: step: 1712/529, loss: 0.012049293145537376
2023-01-23 03:30:07.121640: step: 1716/529, loss: 0.011378765106201172
2023-01-23 03:30:08.367887: step: 1720/529, loss: 0.01756277121603489
2023-01-23 03:30:09.602321: step: 1724/529, loss: 0.010570907965302467
2023-01-23 03:30:10.768410: step: 1728/529, loss: 3.7670135498046875e-05
2023-01-23 03:30:11.948320: step: 1732/529, loss: 1.735687328618951e-05
2023-01-23 03:30:13.153570: step: 1736/529, loss: 0.0002173423854401335
2023-01-23 03:30:14.395749: step: 1740/529, loss: 0.0018852234352380037
2023-01-23 03:30:15.572699: step: 1744/529, loss: 0.003607082413509488
2023-01-23 03:30:16.758274: step: 1748/529, loss: 0.012110329233109951
2023-01-23 03:30:17.957048: step: 1752/529, loss: 0.00013599396334029734
2023-01-23 03:30:19.193542: step: 1756/529, loss: 0.021680641919374466
2023-01-23 03:30:20.397686: step: 1760/529, loss: 0.007324123755097389
2023-01-23 03:30:21.606833: step: 1764/529, loss: 0.008916569873690605
2023-01-23 03:30:22.874875: step: 1768/529, loss: 0.01064910925924778
2023-01-23 03:30:24.057825: step: 1772/529, loss: 0.012298869900405407
2023-01-23 03:30:25.233443: step: 1776/529, loss: 0.0027667046524584293
2023-01-23 03:30:26.448494: step: 1780/529, loss: 4.978180368198082e-05
2023-01-23 03:30:27.694851: step: 1784/529, loss: 0.013062858022749424
2023-01-23 03:30:28.913659: step: 1788/529, loss: 0.04527664557099342
2023-01-23 03:30:30.112225: step: 1792/529, loss: 0.00011978149996139109
2023-01-23 03:30:31.313577: step: 1796/529, loss: 0.004878378007560968
2023-01-23 03:30:32.482583: step: 1800/529, loss: 0.0009832382202148438
2023-01-23 03:30:33.686651: step: 1804/529, loss: 0.007679652888327837
2023-01-23 03:30:34.931791: step: 1808/529, loss: 0.010171796195209026
2023-01-23 03:30:36.127496: step: 1812/529, loss: 0.00025091171846725047
2023-01-23 03:30:37.297118: step: 1816/529, loss: 0.00021839141845703125
2023-01-23 03:30:38.482113: step: 1820/529, loss: 0.009160232730209827
2023-01-23 03:30:39.635350: step: 1824/529, loss: 7.157326035667211e-05
2023-01-23 03:30:40.837522: step: 1828/529, loss: 0.0010103225940838456
2023-01-23 03:30:42.069106: step: 1832/529, loss: 0.121434785425663
2023-01-23 03:30:43.343935: step: 1836/529, loss: 0.007035255432128906
2023-01-23 03:30:44.559318: step: 1840/529, loss: 0.023754501715302467
2023-01-23 03:30:45.763974: step: 1844/529, loss: 0.055586766451597214
2023-01-23 03:30:46.945713: step: 1848/529, loss: 0.03387375921010971
2023-01-23 03:30:48.142170: step: 1852/529, loss: 0.027310943230986595
2023-01-23 03:30:49.333530: step: 1856/529, loss: 0.004269313998520374
2023-01-23 03:30:50.482613: step: 1860/529, loss: 0.02469787560403347
2023-01-23 03:30:51.715008: step: 1864/529, loss: 0.020456695929169655
2023-01-23 03:30:52.971436: step: 1868/529, loss: 0.004259491339325905
2023-01-23 03:30:54.160967: step: 1872/529, loss: 0.011418819427490234
2023-01-23 03:30:55.375219: step: 1876/529, loss: 0.00019569396681617945
2023-01-23 03:30:56.557090: step: 1880/529, loss: 5.722049536416307e-07
2023-01-23 03:30:57.754148: step: 1884/529, loss: 0.0038892747834324837
2023-01-23 03:30:58.917639: step: 1888/529, loss: 0.009188652038574219
2023-01-23 03:31:00.115309: step: 1892/529, loss: 0.04315633699297905
2023-01-23 03:31:01.289161: step: 1896/529, loss: 0.0001201629638671875
2023-01-23 03:31:02.513147: step: 1900/529, loss: 0.00011901855759788305
2023-01-23 03:31:03.725148: step: 1904/529, loss: 0.0020957947708666325
2023-01-23 03:31:04.885741: step: 1908/529, loss: 0.07537918537855148
2023-01-23 03:31:06.069251: step: 1912/529, loss: 0.008517456240952015
2023-01-23 03:31:07.257473: step: 1916/529, loss: 0.011315489187836647
2023-01-23 03:31:08.449862: step: 1920/529, loss: 0.027272367849946022
2023-01-23 03:31:09.634145: step: 1924/529, loss: 0.003683662274852395
2023-01-23 03:31:10.813536: step: 1928/529, loss: 8.544922457076609e-05
2023-01-23 03:31:12.032605: step: 1932/529, loss: 0.024008655920624733
2023-01-23 03:31:13.208333: step: 1936/529, loss: 0.0006074905395507812
2023-01-23 03:31:14.389859: step: 1940/529, loss: 0.0015086650382727385
2023-01-23 03:31:15.589493: step: 1944/529, loss: 0.005527210421860218
2023-01-23 03:31:16.799295: step: 1948/529, loss: 0.01891803927719593
2023-01-23 03:31:18.023734: step: 1952/529, loss: 0.3365371823310852
2023-01-23 03:31:19.180417: step: 1956/529, loss: 0.0031655312050133944
2023-01-23 03:31:20.380823: step: 1960/529, loss: 4.56810012110509e-05
2023-01-23 03:31:21.567297: step: 1964/529, loss: 0.004829073324799538
2023-01-23 03:31:22.816955: step: 1968/529, loss: 0.016674233600497246
2023-01-23 03:31:24.020209: step: 1972/529, loss: 0.0006406784523278475
2023-01-23 03:31:25.214123: step: 1976/529, loss: 5.216598219703883e-05
2023-01-23 03:31:26.393830: step: 1980/529, loss: 0.002842521760612726
2023-01-23 03:31:27.600592: step: 1984/529, loss: 0.008170604705810547
2023-01-23 03:31:28.813412: step: 1988/529, loss: 0.0002967834589071572
2023-01-23 03:31:30.019739: step: 1992/529, loss: 0.0002035141078522429
2023-01-23 03:31:31.170315: step: 1996/529, loss: 2.6226043701171875e-06
2023-01-23 03:31:32.400006: step: 2000/529, loss: 0.00036640168400481343
2023-01-23 03:31:33.668961: step: 2004/529, loss: 0.0018598557217046618
2023-01-23 03:31:34.866447: step: 2008/529, loss: 0.026102256029844284
2023-01-23 03:31:36.081120: step: 2012/529, loss: 0.005317592527717352
2023-01-23 03:31:37.263155: step: 2016/529, loss: 0.010424232110381126
2023-01-23 03:31:38.447753: step: 2020/529, loss: 0.0006548881647177041
2023-01-23 03:31:39.656942: step: 2024/529, loss: 0.02035045623779297
2023-01-23 03:31:40.848236: step: 2028/529, loss: 0.0013819695450365543
2023-01-23 03:31:42.039159: step: 2032/529, loss: 0.011353731155395508
2023-01-23 03:31:43.251029: step: 2036/529, loss: 0.00028066636878065765
2023-01-23 03:31:44.392594: step: 2040/529, loss: 0.0007247448083944619
2023-01-23 03:31:45.614128: step: 2044/529, loss: 0.029674530029296875
2023-01-23 03:31:46.795984: step: 2048/529, loss: 0.0016052245628088713
2023-01-23 03:31:48.001799: step: 2052/529, loss: 0.0005439758533611894
2023-01-23 03:31:49.216647: step: 2056/529, loss: 0.009554862976074219
2023-01-23 03:31:50.380912: step: 2060/529, loss: 0.02063455618917942
2023-01-23 03:31:51.610467: step: 2064/529, loss: 0.0025295258965343237
2023-01-23 03:31:52.788050: step: 2068/529, loss: 0.0031034471467137337
2023-01-23 03:31:54.034690: step: 2072/529, loss: 0.0003180503845214844
2023-01-23 03:31:55.245395: step: 2076/529, loss: 0.00011911392357433215
2023-01-23 03:31:56.431545: step: 2080/529, loss: 0.0004371166287455708
2023-01-23 03:31:57.621441: step: 2084/529, loss: 0.017603684216737747
2023-01-23 03:31:58.800223: step: 2088/529, loss: 0.037097737193107605
2023-01-23 03:31:59.964253: step: 2092/529, loss: 0.0011396408081054688
2023-01-23 03:32:01.165218: step: 2096/529, loss: 6.519556336570531e-05
2023-01-23 03:32:02.380714: step: 2100/529, loss: 0.032398417592048645
2023-01-23 03:32:03.523634: step: 2104/529, loss: 0.016867637634277344
2023-01-23 03:32:04.725217: step: 2108/529, loss: 0.0005841254605911672
2023-01-23 03:32:05.894231: step: 2112/529, loss: 0.0011454150080680847
2023-01-23 03:32:07.078634: step: 2116/529, loss: 9.72747784544481e-06
==================================================
Loss: 0.034
--------------------
Dev: {'event': {'p': 0.6016427104722792, 'r': 0.7802929427430093, 'f1': 0.6794202898550724}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6448007774538387, 'r': 0.7950868783702816, 'f1': 0.7121008854306413}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5679012345679012, 'r': 0.8518518518518519, 'f1': 0.6814814814814814}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.5396825396825397, 'r': 0.5396825396825397, 'f1': 0.5396825396825397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4318181818181818, 'r': 0.5277777777777778, 'f1': 0.47500000000000003}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 03:32:50.595834: step: 4/529, loss: 0.000898170517757535
2023-01-23 03:32:51.754398: step: 8/529, loss: 0.0036108018830418587
2023-01-23 03:32:52.961876: step: 12/529, loss: 0.00015649796114303172
2023-01-23 03:32:54.161167: step: 16/529, loss: 0.003478622529655695
2023-01-23 03:32:55.320090: step: 20/529, loss: 0.000854110752698034
2023-01-23 03:32:56.528767: step: 24/529, loss: 0.0006662368541583419
2023-01-23 03:32:57.785873: step: 28/529, loss: 0.0652950257062912
2023-01-23 03:32:59.021927: step: 32/529, loss: 0.0008264541975222528
2023-01-23 03:33:00.212580: step: 36/529, loss: 0.00046195986215025187
2023-01-23 03:33:01.448665: step: 40/529, loss: 0.00012683868408203125
2023-01-23 03:33:02.661988: step: 44/529, loss: 4.0721897676121444e-05
2023-01-23 03:33:03.824231: step: 48/529, loss: 4.339218776294729e-06
2023-01-23 03:33:05.023879: step: 52/529, loss: 0.0124785415828228
2023-01-23 03:33:06.210449: step: 56/529, loss: 0.0054172039963305
2023-01-23 03:33:07.355193: step: 60/529, loss: 5.474090721691027e-05
2023-01-23 03:33:08.594142: step: 64/529, loss: 0.04378366470336914
2023-01-23 03:33:09.838269: step: 68/529, loss: 0.0018190382979810238
2023-01-23 03:33:11.006443: step: 72/529, loss: 0.005840111058205366
2023-01-23 03:33:12.189654: step: 76/529, loss: 0.0023975849617272615
2023-01-23 03:33:13.420734: step: 80/529, loss: 0.004075098317116499
2023-01-23 03:33:14.597344: step: 84/529, loss: 0.3560231328010559
2023-01-23 03:33:15.800875: step: 88/529, loss: 0.0016739845741540194
2023-01-23 03:33:16.985673: step: 92/529, loss: 0.4803546071052551
2023-01-23 03:33:18.209824: step: 96/529, loss: 1.9788742065429688e-05
2023-01-23 03:33:19.394574: step: 100/529, loss: 0.010644244961440563
2023-01-23 03:33:20.583833: step: 104/529, loss: 0.05007629469037056
2023-01-23 03:33:21.773784: step: 108/529, loss: 0.0007342934841290116
2023-01-23 03:33:22.984848: step: 112/529, loss: 0.0019673823844641447
2023-01-23 03:33:24.216996: step: 116/529, loss: 0.007548236753791571
2023-01-23 03:33:25.384869: step: 120/529, loss: -6.675722943327855e-07
2023-01-23 03:33:26.563193: step: 124/529, loss: 0.010536003857851028
2023-01-23 03:33:27.750044: step: 128/529, loss: 0.002724266145378351
2023-01-23 03:33:28.972943: step: 132/529, loss: 0.0025578499771654606
2023-01-23 03:33:30.180472: step: 136/529, loss: 0.0001903533993754536
2023-01-23 03:33:31.366793: step: 140/529, loss: 0.0005716323503293097
2023-01-23 03:33:32.592649: step: 144/529, loss: 0.010661887936294079
2023-01-23 03:33:33.827173: step: 148/529, loss: 9.479522850597277e-05
2023-01-23 03:33:35.022644: step: 152/529, loss: 0.00019254683866165578
2023-01-23 03:33:36.208368: step: 156/529, loss: 0.0006583214271813631
2023-01-23 03:33:37.433064: step: 160/529, loss: 0.021617794409394264
2023-01-23 03:33:38.603862: step: 164/529, loss: 0.007967852987349033
2023-01-23 03:33:39.785015: step: 168/529, loss: 0.022089196369051933
2023-01-23 03:33:40.984420: step: 172/529, loss: 0.00033512114896439016
2023-01-23 03:33:42.147310: step: 176/529, loss: 0.0001146316499216482
2023-01-23 03:33:43.323629: step: 180/529, loss: 0.008104896172881126
2023-01-23 03:33:44.488002: step: 184/529, loss: 0.00011768341937568039
2023-01-23 03:33:45.662936: step: 188/529, loss: 0.008573532104492188
2023-01-23 03:33:46.806715: step: 192/529, loss: 0.04063277319073677
2023-01-23 03:33:47.994435: step: 196/529, loss: 0.0036703108344227076
2023-01-23 03:33:49.206797: step: 200/529, loss: 0.0321260467171669
2023-01-23 03:33:50.398121: step: 204/529, loss: 0.004272747319191694
2023-01-23 03:33:51.531300: step: 208/529, loss: 0.00010042190842796117
2023-01-23 03:33:52.752177: step: 212/529, loss: 0.0007357597351074219
2023-01-23 03:33:53.937166: step: 216/529, loss: 0.01537170447409153
2023-01-23 03:33:55.125911: step: 220/529, loss: 0.0023218155838549137
2023-01-23 03:33:56.336805: step: 224/529, loss: 0.00044889451237395406
2023-01-23 03:33:57.487849: step: 228/529, loss: 0.0013660431141033769
2023-01-23 03:33:58.676894: step: 232/529, loss: 0.0004330635129008442
2023-01-23 03:33:59.868528: step: 236/529, loss: 6.29425048828125e-05
2023-01-23 03:34:01.045851: step: 240/529, loss: 0.005469989497214556
2023-01-23 03:34:02.217500: step: 244/529, loss: 0.009460163302719593
2023-01-23 03:34:03.413719: step: 248/529, loss: 0.00032253266545012593
2023-01-23 03:34:04.629657: step: 252/529, loss: 0.001751041505485773
2023-01-23 03:34:05.850279: step: 256/529, loss: 0.0013683318393304944
2023-01-23 03:34:07.066702: step: 260/529, loss: 0.020910168066620827
2023-01-23 03:34:08.234185: step: 264/529, loss: 0.030348969623446465
2023-01-23 03:34:09.446415: step: 268/529, loss: 0.019161511212587357
2023-01-23 03:34:10.684433: step: 272/529, loss: 0.020816612988710403
2023-01-23 03:34:11.989199: step: 276/529, loss: 0.0016132354503497481
2023-01-23 03:34:13.164159: step: 280/529, loss: 0.016295909881591797
2023-01-23 03:34:14.401742: step: 284/529, loss: 0.025266075506806374
2023-01-23 03:34:15.586416: step: 288/529, loss: 0.011342430487275124
2023-01-23 03:34:16.775983: step: 292/529, loss: 0.02742328681051731
2023-01-23 03:34:17.979943: step: 296/529, loss: 0.00030794143094681203
2023-01-23 03:34:19.157636: step: 300/529, loss: 0.00015134812565520406
2023-01-23 03:34:20.320187: step: 304/529, loss: 0.00656933756545186
2023-01-23 03:34:21.514148: step: 308/529, loss: 4.3582916987361386e-05
2023-01-23 03:34:22.727615: step: 312/529, loss: 0.012262344360351562
2023-01-23 03:34:23.925247: step: 316/529, loss: 0.0012790679465979338
2023-01-23 03:34:25.127705: step: 320/529, loss: 0.011958600021898746
2023-01-23 03:34:26.324434: step: 324/529, loss: 0.00024366378784179688
2023-01-23 03:34:27.513911: step: 328/529, loss: 0.0012674331665039062
2023-01-23 03:34:28.729223: step: 332/529, loss: 0.050702571868896484
2023-01-23 03:34:29.945086: step: 336/529, loss: 0.0012767792213708162
2023-01-23 03:34:31.147356: step: 340/529, loss: 0.012340545654296875
2023-01-23 03:34:32.365560: step: 344/529, loss: 0.001984119415283203
2023-01-23 03:34:33.559170: step: 348/529, loss: 0.01017541904002428
2023-01-23 03:34:34.742451: step: 352/529, loss: 0.00038437845068983734
2023-01-23 03:34:36.012962: step: 356/529, loss: 0.003945684526115656
2023-01-23 03:34:37.254183: step: 360/529, loss: 0.1507761925458908
2023-01-23 03:34:38.445102: step: 364/529, loss: 4.081726001459174e-05
2023-01-23 03:34:39.654814: step: 368/529, loss: 0.016002465039491653
2023-01-23 03:34:40.851997: step: 372/529, loss: 0.1385457068681717
2023-01-23 03:34:42.032944: step: 376/529, loss: 0.0004816055588889867
2023-01-23 03:34:43.255307: step: 380/529, loss: 0.01354208029806614
2023-01-23 03:34:44.476254: step: 384/529, loss: 0.0003362655406817794
2023-01-23 03:34:45.700517: step: 388/529, loss: 6.103515625e-05
2023-01-23 03:34:46.910038: step: 392/529, loss: 5.435943421616685e-06
2023-01-23 03:34:48.111232: step: 396/529, loss: 0.0013409615494310856
2023-01-23 03:34:49.301761: step: 400/529, loss: 0.007124709896743298
2023-01-23 03:34:50.490491: step: 404/529, loss: 0.0001832962007028982
2023-01-23 03:34:51.656948: step: 408/529, loss: 0.004058551974594593
2023-01-23 03:34:52.878252: step: 412/529, loss: 0.0012286186683923006
2023-01-23 03:34:54.074675: step: 416/529, loss: 0.004363155458122492
2023-01-23 03:34:55.247109: step: 420/529, loss: 0.00022745132446289062
2023-01-23 03:34:56.463694: step: 424/529, loss: 0.030775094404816628
2023-01-23 03:34:57.626230: step: 428/529, loss: 0.006182861514389515
2023-01-23 03:34:58.816390: step: 432/529, loss: -7.152557373046875e-06
2023-01-23 03:34:59.997766: step: 436/529, loss: 0.02369880862534046
2023-01-23 03:35:01.150275: step: 440/529, loss: 0.013905716128647327
2023-01-23 03:35:02.362607: step: 444/529, loss: 0.0012062073219567537
2023-01-23 03:35:03.567201: step: 448/529, loss: 0.0031617165077477694
2023-01-23 03:35:04.788299: step: 452/529, loss: 0.0003533363342285156
2023-01-23 03:35:06.020540: step: 456/529, loss: 0.0004265785391908139
2023-01-23 03:35:07.202388: step: 460/529, loss: 0.001143455388955772
2023-01-23 03:35:08.494924: step: 464/529, loss: 0.006726074498146772
2023-01-23 03:35:09.775881: step: 468/529, loss: 0.103388212621212
2023-01-23 03:35:10.938673: step: 472/529, loss: 0.00012693404278252274
2023-01-23 03:35:12.108933: step: 476/529, loss: 0.033284951001405716
2023-01-23 03:35:13.315709: step: 480/529, loss: 0.0007293701637536287
2023-01-23 03:35:14.550497: step: 484/529, loss: 0.001493167830631137
2023-01-23 03:35:15.799134: step: 488/529, loss: 0.12736888229846954
2023-01-23 03:35:16.995509: step: 492/529, loss: 0.0004247665638104081
2023-01-23 03:35:18.214173: step: 496/529, loss: 0.007828759960830212
2023-01-23 03:35:19.410725: step: 500/529, loss: 0.0004994392511434853
2023-01-23 03:35:20.571065: step: 504/529, loss: 5.1307681133039296e-05
2023-01-23 03:35:21.775469: step: 508/529, loss: 0.009360289201140404
2023-01-23 03:35:22.979786: step: 512/529, loss: 0.0005950927734375
2023-01-23 03:35:24.190102: step: 516/529, loss: 0.0006711006280966103
2023-01-23 03:35:25.378455: step: 520/529, loss: 0.0017589569324627519
2023-01-23 03:35:26.611984: step: 524/529, loss: 0.03187408670783043
2023-01-23 03:35:27.831909: step: 528/529, loss: 0.016418838873505592
2023-01-23 03:35:29.056782: step: 532/529, loss: 0.003821468446403742
2023-01-23 03:35:30.186642: step: 536/529, loss: 0.0004405975341796875
2023-01-23 03:35:31.354687: step: 540/529, loss: 0.017548855394124985
2023-01-23 03:35:32.547908: step: 544/529, loss: 0.0020092965569347143
2023-01-23 03:35:33.760957: step: 548/529, loss: 0.004520607180893421
2023-01-23 03:35:34.978102: step: 552/529, loss: 0.05471072345972061
2023-01-23 03:35:36.179605: step: 556/529, loss: 0.03413067013025284
2023-01-23 03:35:37.406749: step: 560/529, loss: 0.00017023086547851562
2023-01-23 03:35:38.625976: step: 564/529, loss: 0.018899155780673027
2023-01-23 03:35:39.796652: step: 568/529, loss: 1.3637543816003017e-05
2023-01-23 03:35:41.001347: step: 572/529, loss: 0.0420990027487278
2023-01-23 03:35:42.230291: step: 576/529, loss: 0.0003098964807577431
2023-01-23 03:35:43.432086: step: 580/529, loss: 0.07922515273094177
2023-01-23 03:35:44.628406: step: 584/529, loss: 0.0020321845076978207
2023-01-23 03:35:45.801510: step: 588/529, loss: 0.12905311584472656
2023-01-23 03:35:46.995717: step: 592/529, loss: 0.00039615630521439016
2023-01-23 03:35:48.214156: step: 596/529, loss: 0.00038280486478470266
2023-01-23 03:35:49.395033: step: 600/529, loss: 0.0007277489057742059
2023-01-23 03:35:50.563825: step: 604/529, loss: 0.007420635316520929
2023-01-23 03:35:51.802928: step: 608/529, loss: 0.018919754773378372
2023-01-23 03:35:53.038079: step: 612/529, loss: 9.32693510549143e-05
2023-01-23 03:35:54.212843: step: 616/529, loss: 0.023487472906708717
2023-01-23 03:35:55.438858: step: 620/529, loss: 0.020222092047333717
2023-01-23 03:35:56.633918: step: 624/529, loss: 0.028501415625214577
2023-01-23 03:35:57.799450: step: 628/529, loss: 9.16481003514491e-05
2023-01-23 03:35:59.009218: step: 632/529, loss: 0.03372354432940483
2023-01-23 03:36:00.182678: step: 636/529, loss: 0.0003410339413676411
2023-01-23 03:36:01.405236: step: 640/529, loss: 0.0005878924857825041
2023-01-23 03:36:02.640611: step: 644/529, loss: 0.03943615034222603
2023-01-23 03:36:03.851202: step: 648/529, loss: 0.011771392077207565
2023-01-23 03:36:05.085517: step: 652/529, loss: 0.01586771011352539
2023-01-23 03:36:06.250411: step: 656/529, loss: 0.002084159990772605
2023-01-23 03:36:07.500504: step: 660/529, loss: 0.023773955181241035
2023-01-23 03:36:08.690657: step: 664/529, loss: 2.8705597287626006e-05
2023-01-23 03:36:09.855943: step: 668/529, loss: 8.172988600563258e-05
2023-01-23 03:36:11.040606: step: 672/529, loss: 0.06975989788770676
2023-01-23 03:36:12.250232: step: 676/529, loss: 7.677078247070312e-05
2023-01-23 03:36:13.465732: step: 680/529, loss: 0.0027942657470703125
2023-01-23 03:36:14.705684: step: 684/529, loss: 0.011702632531523705
2023-01-23 03:36:15.907408: step: 688/529, loss: 0.04537677764892578
2023-01-23 03:36:17.104315: step: 692/529, loss: 0.0002615928533487022
2023-01-23 03:36:18.289516: step: 696/529, loss: 0.005172061733901501
2023-01-23 03:36:19.484048: step: 700/529, loss: 0.019414568319916725
2023-01-23 03:36:20.689787: step: 704/529, loss: 0.0023340226616710424
2023-01-23 03:36:21.993724: step: 708/529, loss: 0.023093223571777344
2023-01-23 03:36:23.152700: step: 712/529, loss: 0.07595959305763245
2023-01-23 03:36:24.352571: step: 716/529, loss: 5.970001075183973e-05
2023-01-23 03:36:25.553499: step: 720/529, loss: 0.024978255853056908
2023-01-23 03:36:26.740977: step: 724/529, loss: 0.004244994837790728
2023-01-23 03:36:27.923328: step: 728/529, loss: 0.04862070083618164
2023-01-23 03:36:29.108718: step: 732/529, loss: 4.4441225327318534e-05
2023-01-23 03:36:30.267991: step: 736/529, loss: 0.002824401715770364
2023-01-23 03:36:31.426482: step: 740/529, loss: 0.0015510559314861894
2023-01-23 03:36:32.639186: step: 744/529, loss: 0.0005427360301837325
2023-01-23 03:36:33.842617: step: 748/529, loss: 0.016252899542450905
2023-01-23 03:36:35.073676: step: 752/529, loss: 0.08495263010263443
2023-01-23 03:36:36.269603: step: 756/529, loss: 0.003172254655510187
2023-01-23 03:36:37.471326: step: 760/529, loss: 0.0015342712868005037
2023-01-23 03:36:38.690795: step: 764/529, loss: 0.00022029876708984375
2023-01-23 03:36:39.886717: step: 768/529, loss: 0.00035686494084075093
2023-01-23 03:36:41.104596: step: 772/529, loss: 0.0008879661909304559
2023-01-23 03:36:42.309941: step: 776/529, loss: 0.0001375198335153982
2023-01-23 03:36:43.436650: step: 780/529, loss: 0.011178922839462757
2023-01-23 03:36:44.618688: step: 784/529, loss: 0.0025388719514012337
2023-01-23 03:36:45.780698: step: 788/529, loss: 0.002006149385124445
2023-01-23 03:36:47.071980: step: 792/529, loss: 0.0040136342868208885
2023-01-23 03:36:48.254077: step: 796/529, loss: 0.06336746364831924
2023-01-23 03:36:49.489224: step: 800/529, loss: 0.03689708933234215
2023-01-23 03:36:50.692291: step: 804/529, loss: 0.016944121569395065
2023-01-23 03:36:51.878799: step: 808/529, loss: 0.0004863739013671875
2023-01-23 03:36:53.074336: step: 812/529, loss: 0.019335174933075905
2023-01-23 03:36:54.290967: step: 816/529, loss: 0.054054830223321915
2023-01-23 03:36:55.502713: step: 820/529, loss: 0.0015951156383380294
2023-01-23 03:36:56.681302: step: 824/529, loss: 0.04383373260498047
2023-01-23 03:36:57.878527: step: 828/529, loss: 0.0003765106375794858
2023-01-23 03:36:59.057284: step: 832/529, loss: 0.05890718474984169
2023-01-23 03:37:00.307705: step: 836/529, loss: 0.0010253905784338713
2023-01-23 03:37:01.475395: step: 840/529, loss: 0.07326450943946838
2023-01-23 03:37:02.710706: step: 844/529, loss: 6.394386582542211e-05
2023-01-23 03:37:03.936726: step: 848/529, loss: 6.518364534713328e-05
2023-01-23 03:37:05.132740: step: 852/529, loss: 0.00027294160099700093
2023-01-23 03:37:06.335257: step: 856/529, loss: 0.0026446343399584293
2023-01-23 03:37:07.537793: step: 860/529, loss: 0.009461402893066406
2023-01-23 03:37:08.727869: step: 864/529, loss: 0.025462724268436432
2023-01-23 03:37:09.938798: step: 868/529, loss: 0.011704540811479092
2023-01-23 03:37:11.149818: step: 872/529, loss: 4.9400332500226796e-05
2023-01-23 03:37:12.320373: step: 876/529, loss: 0.0022995946928858757
2023-01-23 03:37:13.523512: step: 880/529, loss: 0.004719448275864124
2023-01-23 03:37:14.709647: step: 884/529, loss: 0.14319248497486115
2023-01-23 03:37:15.894607: step: 888/529, loss: 1.850128137448337e-05
2023-01-23 03:37:17.099296: step: 892/529, loss: 0.03753848001360893
2023-01-23 03:37:18.318531: step: 896/529, loss: 0.012701893225312233
2023-01-23 03:37:19.559492: step: 900/529, loss: 0.0013249159092083573
2023-01-23 03:37:20.760941: step: 904/529, loss: 0.00012512208195403218
2023-01-23 03:37:21.932419: step: 908/529, loss: 0.00013785957708023489
2023-01-23 03:37:23.136378: step: 912/529, loss: 0.030365657061338425
2023-01-23 03:37:24.309664: step: 916/529, loss: 8.258819434558973e-05
2023-01-23 03:37:25.492460: step: 920/529, loss: 0.0012405395973473787
2023-01-23 03:37:26.710691: step: 924/529, loss: 0.013542176224291325
2023-01-23 03:37:27.915072: step: 928/529, loss: 0.0004238128603901714
2023-01-23 03:37:29.117303: step: 932/529, loss: 0.0019830705132335424
2023-01-23 03:37:30.273549: step: 936/529, loss: 0.0016424179775640368
2023-01-23 03:37:31.449830: step: 940/529, loss: 4.348754737293348e-05
2023-01-23 03:37:32.657973: step: 944/529, loss: 0.03330859914422035
2023-01-23 03:37:33.818990: step: 948/529, loss: 0.0001504898100392893
2023-01-23 03:37:34.995487: step: 952/529, loss: 0.002265429589897394
2023-01-23 03:37:36.205173: step: 956/529, loss: 2.059936559817288e-05
2023-01-23 03:37:37.377027: step: 960/529, loss: 0.0007035851594991982
2023-01-23 03:37:38.559303: step: 964/529, loss: 0.0048697469756007195
2023-01-23 03:37:39.748448: step: 968/529, loss: 0.0015480995643883944
2023-01-23 03:37:40.962661: step: 972/529, loss: 0.002645349595695734
2023-01-23 03:37:42.181905: step: 976/529, loss: 0.000987148261629045
2023-01-23 03:37:43.356531: step: 980/529, loss: 0.011107087135314941
2023-01-23 03:37:44.592389: step: 984/529, loss: 0.16761799156665802
2023-01-23 03:37:45.794153: step: 988/529, loss: 0.00363674177788198
2023-01-23 03:37:46.981540: step: 992/529, loss: 0.0010346651542931795
2023-01-23 03:37:48.184479: step: 996/529, loss: 0.022006798535585403
2023-01-23 03:37:49.386528: step: 1000/529, loss: 0.01878967322409153
2023-01-23 03:37:50.600952: step: 1004/529, loss: 0.001506519503891468
2023-01-23 03:37:51.806707: step: 1008/529, loss: 1.1587143490032759e-05
2023-01-23 03:37:52.953987: step: 1012/529, loss: 0.033208273351192474
2023-01-23 03:37:54.102978: step: 1016/529, loss: 0.04389353096485138
2023-01-23 03:37:55.283593: step: 1020/529, loss: 0.0032369615510106087
2023-01-23 03:37:56.486832: step: 1024/529, loss: 0.05927124246954918
2023-01-23 03:37:57.641633: step: 1028/529, loss: 0.06422028690576553
2023-01-23 03:37:58.801080: step: 1032/529, loss: 9.937286813510582e-05
2023-01-23 03:38:00.022945: step: 1036/529, loss: 0.005011939909309149
2023-01-23 03:38:01.237138: step: 1040/529, loss: 0.005518722347915173
2023-01-23 03:38:02.461957: step: 1044/529, loss: 0.09006920456886292
2023-01-23 03:38:03.616646: step: 1048/529, loss: 0.003423976944759488
2023-01-23 03:38:04.816191: step: 1052/529, loss: 0.016025066375732422
2023-01-23 03:38:06.021706: step: 1056/529, loss: 1.1253356205997989e-05
2023-01-23 03:38:07.224885: step: 1060/529, loss: 0.009554862976074219
2023-01-23 03:38:08.435785: step: 1064/529, loss: 0.0010534287430346012
2023-01-23 03:38:09.635815: step: 1068/529, loss: 0.000583648681640625
2023-01-23 03:38:10.828066: step: 1072/529, loss: 0.0005009651649743319
2023-01-23 03:38:12.016474: step: 1076/529, loss: 0.0002645492786541581
2023-01-23 03:38:13.237676: step: 1080/529, loss: 0.019129563122987747
2023-01-23 03:38:14.444490: step: 1084/529, loss: 0.0005270004621706903
2023-01-23 03:38:15.636321: step: 1088/529, loss: 0.00031490327091887593
2023-01-23 03:38:16.862712: step: 1092/529, loss: 0.0001180648832814768
2023-01-23 03:38:18.060244: step: 1096/529, loss: 0.017127513885498047
2023-01-23 03:38:19.293711: step: 1100/529, loss: 0.0007427215459756553
2023-01-23 03:38:20.467029: step: 1104/529, loss: 0.010594367980957031
2023-01-23 03:38:21.706433: step: 1108/529, loss: 0.004141903016716242
2023-01-23 03:38:22.879756: step: 1112/529, loss: 0.5100986361503601
2023-01-23 03:38:24.060032: step: 1116/529, loss: 0.0015306472778320312
2023-01-23 03:38:25.319298: step: 1120/529, loss: 0.07941456139087677
2023-01-23 03:38:26.542783: step: 1124/529, loss: 0.004347038455307484
2023-01-23 03:38:27.752466: step: 1128/529, loss: 0.03517203405499458
2023-01-23 03:38:28.939883: step: 1132/529, loss: 0.00018129349336959422
2023-01-23 03:38:30.137477: step: 1136/529, loss: 0.003693962236866355
2023-01-23 03:38:31.341978: step: 1140/529, loss: 0.026404380798339844
2023-01-23 03:38:32.578005: step: 1144/529, loss: 6.046295311534777e-05
2023-01-23 03:38:33.821961: step: 1148/529, loss: 0.01632366143167019
2023-01-23 03:38:34.998431: step: 1152/529, loss: 0.015412474051117897
2023-01-23 03:38:36.194609: step: 1156/529, loss: 0.001611566636711359
2023-01-23 03:38:37.392980: step: 1160/529, loss: 0.0003528594970703125
2023-01-23 03:38:38.577558: step: 1164/529, loss: 0.06460094451904297
2023-01-23 03:38:39.800175: step: 1168/529, loss: 0.002927589463070035
2023-01-23 03:38:40.993649: step: 1172/529, loss: 0.028927041217684746
2023-01-23 03:38:42.207188: step: 1176/529, loss: 0.03572044521570206
2023-01-23 03:38:43.390364: step: 1180/529, loss: 0.019527077674865723
2023-01-23 03:38:44.548394: step: 1184/529, loss: 0.014702415093779564
2023-01-23 03:38:45.736361: step: 1188/529, loss: 0.010488605126738548
2023-01-23 03:38:46.998005: step: 1192/529, loss: 0.001035499619320035
2023-01-23 03:38:48.211322: step: 1196/529, loss: 0.04453869163990021
2023-01-23 03:38:49.421264: step: 1200/529, loss: 0.006957626435905695
2023-01-23 03:38:50.604816: step: 1204/529, loss: 0.002349948976188898
2023-01-23 03:38:51.830962: step: 1208/529, loss: 0.0002538680855650455
2023-01-23 03:38:52.970974: step: 1212/529, loss: 0.0028120994102209806
2023-01-23 03:38:54.177787: step: 1216/529, loss: 0.004297828767448664
2023-01-23 03:38:55.387654: step: 1220/529, loss: 0.003631210420280695
2023-01-23 03:38:56.552101: step: 1224/529, loss: 0.00024385451979469508
2023-01-23 03:38:57.763235: step: 1228/529, loss: 0.02272777631878853
2023-01-23 03:38:58.945071: step: 1232/529, loss: 0.27537012100219727
2023-01-23 03:39:00.140852: step: 1236/529, loss: 0.015215015970170498
2023-01-23 03:39:01.338529: step: 1240/529, loss: 0.007067585363984108
2023-01-23 03:39:02.508341: step: 1244/529, loss: 0.0032721522729843855
2023-01-23 03:39:03.747615: step: 1248/529, loss: 0.002231597900390625
2023-01-23 03:39:04.981624: step: 1252/529, loss: 0.0018440247513353825
2023-01-23 03:39:06.194838: step: 1256/529, loss: 6.961822509765625e-05
2023-01-23 03:39:07.361378: step: 1260/529, loss: 3.719329833984375e-05
2023-01-23 03:39:08.589760: step: 1264/529, loss: 0.008255720138549805
2023-01-23 03:39:09.813151: step: 1268/529, loss: 0.18575401604175568
2023-01-23 03:39:11.020259: step: 1272/529, loss: 0.0010348320938646793
2023-01-23 03:39:12.245834: step: 1276/529, loss: 0.0012639999622479081
2023-01-23 03:39:13.508604: step: 1280/529, loss: 0.002755546709522605
2023-01-23 03:39:14.649422: step: 1284/529, loss: 0.011878490447998047
2023-01-23 03:39:15.815186: step: 1288/529, loss: 0.030170299112796783
2023-01-23 03:39:17.030097: step: 1292/529, loss: 0.05582933500409126
2023-01-23 03:39:18.322892: step: 1296/529, loss: 0.014387655071914196
2023-01-23 03:39:19.532075: step: 1300/529, loss: 0.0024883272126317024
2023-01-23 03:39:20.706297: step: 1304/529, loss: 0.025716353207826614
2023-01-23 03:39:21.878262: step: 1308/529, loss: 7.648468454135582e-05
2023-01-23 03:39:23.026306: step: 1312/529, loss: 2.1266936528263614e-05
2023-01-23 03:39:24.216899: step: 1316/529, loss: 0.00329341902397573
2023-01-23 03:39:25.386920: step: 1320/529, loss: 6.847381155239418e-05
2023-01-23 03:39:26.594713: step: 1324/529, loss: 0.00016870498075149953
2023-01-23 03:39:27.809860: step: 1328/529, loss: 5.14984130859375e-05
2023-01-23 03:39:28.962798: step: 1332/529, loss: 0.036052536219358444
2023-01-23 03:39:30.172493: step: 1336/529, loss: 0.000446319580078125
2023-01-23 03:39:31.350397: step: 1340/529, loss: 0.003314495086669922
2023-01-23 03:39:32.483778: step: 1344/529, loss: 0.0031042098999023438
2023-01-23 03:39:33.665861: step: 1348/529, loss: 0.0008060456020757556
2023-01-23 03:39:34.880746: step: 1352/529, loss: 0.001272010849788785
2023-01-23 03:39:36.123297: step: 1356/529, loss: 0.06508941948413849
2023-01-23 03:39:37.328165: step: 1360/529, loss: 0.00029096603975631297
2023-01-23 03:39:38.510923: step: 1364/529, loss: 0.00904998742043972
2023-01-23 03:39:39.705970: step: 1368/529, loss: 0.00498199462890625
2023-01-23 03:39:40.925017: step: 1372/529, loss: 0.002743625780567527
2023-01-23 03:39:42.173606: step: 1376/529, loss: 0.07878484576940536
2023-01-23 03:39:43.372606: step: 1380/529, loss: 9.855032112682238e-05
2023-01-23 03:39:44.585731: step: 1384/529, loss: 2.269744800287299e-05
2023-01-23 03:39:45.799054: step: 1388/529, loss: 0.0020182610023766756
2023-01-23 03:39:46.982285: step: 1392/529, loss: 0.008685683831572533
2023-01-23 03:39:48.201938: step: 1396/529, loss: 0.0031312943901866674
2023-01-23 03:39:49.431565: step: 1400/529, loss: 0.034381963312625885
2023-01-23 03:39:50.649297: step: 1404/529, loss: 0.01310033816844225
2023-01-23 03:39:51.826831: step: 1408/529, loss: 0.0005679130554199219
2023-01-23 03:39:53.001611: step: 1412/529, loss: 3.128051685052924e-05
2023-01-23 03:39:54.187670: step: 1416/529, loss: 0.06314654648303986
2023-01-23 03:39:55.385936: step: 1420/529, loss: 0.00017089843458961695
2023-01-23 03:39:56.595795: step: 1424/529, loss: 0.0020983696449548006
2023-01-23 03:39:57.823558: step: 1428/529, loss: 0.004392432980239391
2023-01-23 03:39:59.014779: step: 1432/529, loss: 0.5976591110229492
2023-01-23 03:40:00.168174: step: 1436/529, loss: 0.00067224504891783
2023-01-23 03:40:01.354894: step: 1440/529, loss: 0.0054450989700853825
2023-01-23 03:40:02.557230: step: 1444/529, loss: 0.023593807592988014
2023-01-23 03:40:03.798951: step: 1448/529, loss: 0.0015541077591478825
2023-01-23 03:40:05.002672: step: 1452/529, loss: 0.051627349108457565
2023-01-23 03:40:06.196105: step: 1456/529, loss: 0.0075782774947583675
2023-01-23 03:40:07.399812: step: 1460/529, loss: 0.02765197679400444
2023-01-23 03:40:08.554317: step: 1464/529, loss: 0.0008444786071777344
2023-01-23 03:40:09.743012: step: 1468/529, loss: 0.00035037993802689016
2023-01-23 03:40:10.949185: step: 1472/529, loss: 0.00997009314596653
2023-01-23 03:40:12.148614: step: 1476/529, loss: 0.11177940666675568
2023-01-23 03:40:13.364365: step: 1480/529, loss: 0.008936119265854359
2023-01-23 03:40:14.547766: step: 1484/529, loss: 0.0004549503210000694
2023-01-23 03:40:15.781812: step: 1488/529, loss: 0.0005990028730593622
2023-01-23 03:40:16.920302: step: 1492/529, loss: 0.03421497344970703
2023-01-23 03:40:18.090902: step: 1496/529, loss: 0.0045372010208666325
2023-01-23 03:40:19.271775: step: 1500/529, loss: 0.2617638409137726
2023-01-23 03:40:20.430260: step: 1504/529, loss: 0.0007524490938521922
2023-01-23 03:40:21.623370: step: 1508/529, loss: 1.6832351320772432e-05
2023-01-23 03:40:22.830696: step: 1512/529, loss: 0.0016531944274902344
2023-01-23 03:40:24.026987: step: 1516/529, loss: 0.06861049681901932
2023-01-23 03:40:25.206018: step: 1520/529, loss: 0.0664815902709961
2023-01-23 03:40:26.425123: step: 1524/529, loss: 0.001583099365234375
2023-01-23 03:40:27.583431: step: 1528/529, loss: 0.0028020860627293587
2023-01-23 03:40:28.753082: step: 1532/529, loss: 0.0009150505065917969
2023-01-23 03:40:29.954124: step: 1536/529, loss: 0.009389019571244717
2023-01-23 03:40:31.141319: step: 1540/529, loss: 0.0004385947831906378
2023-01-23 03:40:32.387542: step: 1544/529, loss: 0.005563164129853249
2023-01-23 03:40:33.551653: step: 1548/529, loss: 0.00017862320237327367
2023-01-23 03:40:34.739752: step: 1552/529, loss: 0.0131384851410985
2023-01-23 03:40:35.969583: step: 1556/529, loss: 0.013698577880859375
2023-01-23 03:40:37.168195: step: 1560/529, loss: 0.00808407086879015
2023-01-23 03:40:38.395469: step: 1564/529, loss: 0.00026960374088957906
2023-01-23 03:40:39.604307: step: 1568/529, loss: 0.004306221380829811
2023-01-23 03:40:40.797335: step: 1572/529, loss: 0.004226732533425093
2023-01-23 03:40:41.988898: step: 1576/529, loss: 0.0013734340900555253
2023-01-23 03:40:43.171798: step: 1580/529, loss: 0.007473850157111883
2023-01-23 03:40:44.365460: step: 1584/529, loss: 0.017133522778749466
2023-01-23 03:40:45.509041: step: 1588/529, loss: 0.007586574647575617
2023-01-23 03:40:46.670498: step: 1592/529, loss: 6.198883056640625e-05
2023-01-23 03:40:47.878615: step: 1596/529, loss: 0.0015925407642498612
2023-01-23 03:40:49.058787: step: 1600/529, loss: 0.021272659301757812
2023-01-23 03:40:50.259052: step: 1604/529, loss: 0.013446665368974209
2023-01-23 03:40:51.460668: step: 1608/529, loss: 0.032831527292728424
2023-01-23 03:40:52.696250: step: 1612/529, loss: 0.07146281749010086
2023-01-23 03:40:53.882989: step: 1616/529, loss: 0.009949398227036
2023-01-23 03:40:55.067611: step: 1620/529, loss: 9.441375732421875e-05
2023-01-23 03:40:56.279690: step: 1624/529, loss: 0.037702418863773346
2023-01-23 03:40:57.471213: step: 1628/529, loss: 0.0012516975402832031
2023-01-23 03:40:58.664984: step: 1632/529, loss: 7.219314284157008e-05
2023-01-23 03:40:59.869857: step: 1636/529, loss: 0.03187829628586769
2023-01-23 03:41:01.054896: step: 1640/529, loss: 0.006687736604362726
2023-01-23 03:41:02.270138: step: 1644/529, loss: 0.002936935517936945
2023-01-23 03:41:03.452790: step: 1648/529, loss: 0.003667736193165183
2023-01-23 03:41:04.658577: step: 1652/529, loss: 0.002071523806080222
2023-01-23 03:41:05.893176: step: 1656/529, loss: 0.013837242498993874
2023-01-23 03:41:07.093641: step: 1660/529, loss: 0.44162482023239136
2023-01-23 03:41:08.274737: step: 1664/529, loss: 6.227493577171117e-05
2023-01-23 03:41:09.479407: step: 1668/529, loss: 0.007802486419677734
2023-01-23 03:41:10.690538: step: 1672/529, loss: 0.009524345397949219
2023-01-23 03:41:11.887403: step: 1676/529, loss: 0.007470607757568359
2023-01-23 03:41:13.069299: step: 1680/529, loss: 0.005115986336022615
2023-01-23 03:41:14.262866: step: 1684/529, loss: 6.771088010282256e-06
2023-01-23 03:41:15.442050: step: 1688/529, loss: 0.0024892569053918123
2023-01-23 03:41:16.648209: step: 1692/529, loss: 0.0007131576421670616
2023-01-23 03:41:17.816078: step: 1696/529, loss: 0.034295033663511276
2023-01-23 03:41:18.985094: step: 1700/529, loss: 6.942749314475805e-05
2023-01-23 03:41:20.255693: step: 1704/529, loss: 0.013085603713989258
2023-01-23 03:41:21.492839: step: 1708/529, loss: 0.019481658935546875
2023-01-23 03:41:22.677832: step: 1712/529, loss: 0.00022064447693992406
2023-01-23 03:41:23.855434: step: 1716/529, loss: 0.1772640198469162
2023-01-23 03:41:25.054372: step: 1720/529, loss: 0.0050002094358205795
2023-01-23 03:41:26.239162: step: 1724/529, loss: 0.004858207888901234
2023-01-23 03:41:27.434638: step: 1728/529, loss: 0.009202385321259499
2023-01-23 03:41:28.604918: step: 1732/529, loss: 2.2602080207434483e-05
2023-01-23 03:41:29.820672: step: 1736/529, loss: -7.629394644936838e-07
2023-01-23 03:41:30.988498: step: 1740/529, loss: 0.007745265960693359
2023-01-23 03:41:32.142100: step: 1744/529, loss: 0.00013227463932707906
2023-01-23 03:41:33.402960: step: 1748/529, loss: 0.0014761924976482987
2023-01-23 03:41:34.626854: step: 1752/529, loss: 0.00010704994201660156
2023-01-23 03:41:35.841298: step: 1756/529, loss: 0.0009677886846475303
2023-01-23 03:41:37.058493: step: 1760/529, loss: 0.0005519867409020662
2023-01-23 03:41:38.211351: step: 1764/529, loss: 0.02731151506304741
2023-01-23 03:41:39.388816: step: 1768/529, loss: 0.0007440566550940275
2023-01-23 03:41:40.591665: step: 1772/529, loss: 0.017073439434170723
2023-01-23 03:41:41.791739: step: 1776/529, loss: 0.016886521130800247
2023-01-23 03:41:42.970222: step: 1780/529, loss: 0.0002614021359477192
2023-01-23 03:41:44.158412: step: 1784/529, loss: 0.012561511248350143
2023-01-23 03:41:45.405431: step: 1788/529, loss: 1.0352295637130737
2023-01-23 03:41:46.637795: step: 1792/529, loss: 1.6075966358184814
2023-01-23 03:41:47.807192: step: 1796/529, loss: 1.2111664545955136e-05
2023-01-23 03:41:49.030315: step: 1800/529, loss: 5.1212311518611386e-05
2023-01-23 03:41:50.243302: step: 1804/529, loss: 6.089210728532635e-05
2023-01-23 03:41:51.418489: step: 1808/529, loss: 0.0014251709217205644
2023-01-23 03:41:52.632884: step: 1812/529, loss: 0.013620949350297451
2023-01-23 03:41:53.839468: step: 1816/529, loss: 0.018726635724306107
2023-01-23 03:41:55.014539: step: 1820/529, loss: 0.0004659652477130294
2023-01-23 03:41:56.236783: step: 1824/529, loss: 0.0474826842546463
2023-01-23 03:41:57.448873: step: 1828/529, loss: 2.1457672119140625e-06
2023-01-23 03:41:58.668878: step: 1832/529, loss: 0.26096248626708984
2023-01-23 03:41:59.872870: step: 1836/529, loss: 0.0018550873501226306
2023-01-23 03:42:01.084588: step: 1840/529, loss: 0.02120218425989151
2023-01-23 03:42:02.282990: step: 1844/529, loss: 0.001298332354053855
2023-01-23 03:42:03.459110: step: 1848/529, loss: 0.0010971069568768144
2023-01-23 03:42:04.668024: step: 1852/529, loss: 8.497238741256297e-05
2023-01-23 03:42:05.861458: step: 1856/529, loss: 6.923675391590223e-05
2023-01-23 03:42:07.053110: step: 1860/529, loss: 0.0001624107244424522
2023-01-23 03:42:08.238885: step: 1864/529, loss: 0.00016980171494651586
2023-01-23 03:42:09.430206: step: 1868/529, loss: 0.00019006729417014867
2023-01-23 03:42:10.626580: step: 1872/529, loss: 0.08499736338853836
2023-01-23 03:42:11.822775: step: 1876/529, loss: 0.003906059078872204
2023-01-23 03:42:13.027445: step: 1880/529, loss: 0.025139618664979935
2023-01-23 03:42:14.207113: step: 1884/529, loss: 0.044082071632146835
2023-01-23 03:42:15.390906: step: 1888/529, loss: 0.004578971769660711
2023-01-23 03:42:16.597035: step: 1892/529, loss: 0.013745593838393688
2023-01-23 03:42:17.791614: step: 1896/529, loss: 0.0011387825943529606
2023-01-23 03:42:18.961403: step: 1900/529, loss: 0.0006008148193359375
2023-01-23 03:42:20.151755: step: 1904/529, loss: 0.016133690252900124
2023-01-23 03:42:21.364549: step: 1908/529, loss: 0.0001794815034372732
2023-01-23 03:42:22.561157: step: 1912/529, loss: 9.493828110862523e-05
2023-01-23 03:42:23.798899: step: 1916/529, loss: 0.006560373120009899
2023-01-23 03:42:25.022541: step: 1920/529, loss: 0.12894611060619354
2023-01-23 03:42:26.223808: step: 1924/529, loss: 4.7349931264761835e-05
2023-01-23 03:42:27.434217: step: 1928/529, loss: 0.001413536025211215
2023-01-23 03:42:28.617548: step: 1932/529, loss: 0.0014220238663256168
2023-01-23 03:42:29.809794: step: 1936/529, loss: 0.00019788742065429688
2023-01-23 03:42:31.013031: step: 1940/529, loss: 0.0005460738902911544
2023-01-23 03:42:32.209511: step: 1944/529, loss: 0.0019762038718909025
2023-01-23 03:42:33.405418: step: 1948/529, loss: 0.042997173964977264
2023-01-23 03:42:34.586000: step: 1952/529, loss: 0.04138369485735893
2023-01-23 03:42:35.854809: step: 1956/529, loss: 0.006378364749252796
2023-01-23 03:42:37.022209: step: 1960/529, loss: 0.0005731344572268426
2023-01-23 03:42:38.230560: step: 1964/529, loss: 0.007376671303063631
2023-01-23 03:42:39.476246: step: 1968/529, loss: 0.0012138367164880037
2023-01-23 03:42:40.648494: step: 1972/529, loss: 0.00034012793912552297
2023-01-23 03:42:41.859426: step: 1976/529, loss: 0.33268243074417114
2023-01-23 03:42:43.083022: step: 1980/529, loss: -5.483627774083288e-07
2023-01-23 03:42:44.307978: step: 1984/529, loss: 0.016938399523496628
2023-01-23 03:42:45.479975: step: 1988/529, loss: 0.009025001898407936
2023-01-23 03:42:46.653941: step: 1992/529, loss: 0.005885410588234663
2023-01-23 03:42:47.818677: step: 1996/529, loss: 9.384154691360891e-05
2023-01-23 03:42:49.038102: step: 2000/529, loss: 0.08298740535974503
2023-01-23 03:42:50.245678: step: 2004/529, loss: 0.00032634736271575093
2023-01-23 03:42:51.440705: step: 2008/529, loss: 0.13261787593364716
2023-01-23 03:42:52.615629: step: 2012/529, loss: 0.033293724060058594
2023-01-23 03:42:53.794895: step: 2016/529, loss: 0.00035409926204010844
2023-01-23 03:42:54.992839: step: 2020/529, loss: 0.0011157034896314144
2023-01-23 03:42:56.171812: step: 2024/529, loss: 0.001242351601831615
2023-01-23 03:42:57.397702: step: 2028/529, loss: 0.009975624270737171
2023-01-23 03:42:58.624677: step: 2032/529, loss: 0.00020103454880882055
2023-01-23 03:42:59.781383: step: 2036/529, loss: 0.42387503385543823
2023-01-23 03:43:00.975963: step: 2040/529, loss: 0.018227767199277878
2023-01-23 03:43:02.189958: step: 2044/529, loss: 0.00041770937968976796
2023-01-23 03:43:03.387870: step: 2048/529, loss: 0.08130493015050888
2023-01-23 03:43:04.591908: step: 2052/529, loss: 0.023687362670898438
2023-01-23 03:43:05.789010: step: 2056/529, loss: 0.0005147934425622225
2023-01-23 03:43:06.982529: step: 2060/529, loss: 0.009633636102080345
2023-01-23 03:43:08.167797: step: 2064/529, loss: 0.009859466925263405
2023-01-23 03:43:09.340594: step: 2068/529, loss: 0.0032457353081554174
2023-01-23 03:43:10.542469: step: 2072/529, loss: 0.0010078430641442537
2023-01-23 03:43:11.756947: step: 2076/529, loss: 0.013354111462831497
2023-01-23 03:43:12.949875: step: 2080/529, loss: 0.0013794898986816406
2023-01-23 03:43:14.141536: step: 2084/529, loss: 0.0003688812139444053
2023-01-23 03:43:15.316766: step: 2088/529, loss: 0.00066123012220487
2023-01-23 03:43:16.464456: step: 2092/529, loss: 2.5558472771081142e-05
2023-01-23 03:43:17.651076: step: 2096/529, loss: 0.021580219268798828
2023-01-23 03:43:18.895848: step: 2100/529, loss: 0.0540035255253315
2023-01-23 03:43:20.101382: step: 2104/529, loss: 0.012967204675078392
2023-01-23 03:43:21.279902: step: 2108/529, loss: 0.044558335095644
2023-01-23 03:43:22.478676: step: 2112/529, loss: 0.005290317814797163
2023-01-23 03:43:23.697334: step: 2116/529, loss: 0.004627418704330921
==================================================
Loss: 0.026
--------------------
Dev: {'event': {'p': 0.5983772819472617, 'r': 0.7856191744340879, 'f1': 0.6793321819228555}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6215456674473068, 'r': 0.7950868783702816, 'f1': 0.6976866456361724}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.6103896103896104, 'r': 0.8703703703703703, 'f1': 0.7175572519083969}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.5645161290322581, 'r': 0.5555555555555556, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.4418604651162791, 'r': 0.5277777777777778, 'f1': 0.4810126582278481}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 03:44:07.701899: step: 4/529, loss: 0.0011466980213299394
2023-01-23 03:44:08.922172: step: 8/529, loss: 0.011140919290482998
2023-01-23 03:44:10.119088: step: 12/529, loss: 0.021004866808652878
2023-01-23 03:44:11.332977: step: 16/529, loss: 0.0010696412064135075
2023-01-23 03:44:12.521531: step: 20/529, loss: 5.855560448253527e-05
2023-01-23 03:44:13.756529: step: 24/529, loss: -1.106262243411038e-05
2023-01-23 03:44:14.957680: step: 28/529, loss: 0.001407623291015625
2023-01-23 03:44:16.132920: step: 32/529, loss: 0.0002246856747660786
2023-01-23 03:44:17.325621: step: 36/529, loss: 0.0006568909157067537
2023-01-23 03:44:18.508259: step: 40/529, loss: 0.0017924308776855469
2023-01-23 03:44:19.715570: step: 44/529, loss: 0.0008139610290527344
2023-01-23 03:44:20.910039: step: 48/529, loss: 0.000766754150390625
2023-01-23 03:44:22.123474: step: 52/529, loss: 0.00024299623328261077
2023-01-23 03:44:23.327721: step: 56/529, loss: 0.019057463854551315
2023-01-23 03:44:24.507832: step: 60/529, loss: 0.0006607055547647178
2023-01-23 03:44:25.749485: step: 64/529, loss: 0.002446079161018133
2023-01-23 03:44:26.939498: step: 68/529, loss: 2.384185791015625e-05
2023-01-23 03:44:28.117676: step: 72/529, loss: 0.0002698898606467992
2023-01-23 03:44:29.325527: step: 76/529, loss: 0.002190876053646207
2023-01-23 03:44:30.503012: step: 80/529, loss: 0.0023322582710534334
2023-01-23 03:44:31.667753: step: 84/529, loss: 0.0057866573333740234
2023-01-23 03:44:32.860530: step: 88/529, loss: 0.0017610550858080387
2023-01-23 03:44:34.017579: step: 92/529, loss: 0.007925319485366344
2023-01-23 03:44:35.254757: step: 96/529, loss: -3.261566234868951e-05
2023-01-23 03:44:36.457628: step: 100/529, loss: 0.08399781584739685
2023-01-23 03:44:37.675912: step: 104/529, loss: 0.0006403923034667969
2023-01-23 03:44:38.853771: step: 108/529, loss: 5.207061622058973e-05
2023-01-23 03:44:40.024384: step: 112/529, loss: 0.0011971474159508944
2023-01-23 03:44:41.200208: step: 116/529, loss: 0.006357765290886164
2023-01-23 03:44:42.359039: step: 120/529, loss: 0.00043311118497513235
2023-01-23 03:44:43.563870: step: 124/529, loss: 0.000164031982421875
2023-01-23 03:44:44.808372: step: 128/529, loss: 0.022243691608309746
2023-01-23 03:44:46.012685: step: 132/529, loss: 0.0003643035888671875
2023-01-23 03:44:47.218471: step: 136/529, loss: 0.19191579520702362
2023-01-23 03:44:48.516277: step: 140/529, loss: 0.0017140388954430819
2023-01-23 03:44:49.675045: step: 144/529, loss: 0.004242515657097101
2023-01-23 03:44:50.872259: step: 148/529, loss: 0.04884643480181694
2023-01-23 03:44:52.074485: step: 152/529, loss: 0.05515914410352707
2023-01-23 03:44:53.296938: step: 156/529, loss: 0.005044078920036554
2023-01-23 03:44:54.470829: step: 160/529, loss: 0.00034618377685546875
2023-01-23 03:44:55.696269: step: 164/529, loss: 0.00033988954965025187
2023-01-23 03:44:56.887652: step: 168/529, loss: 2.136230432370212e-05
2023-01-23 03:44:58.091181: step: 172/529, loss: 0.00537109375
2023-01-23 03:44:59.310327: step: 176/529, loss: 0.0037658691871911287
2023-01-23 03:45:00.499939: step: 180/529, loss: 0.005347347352653742
2023-01-23 03:45:01.750982: step: 184/529, loss: 6.732941255904734e-05
2023-01-23 03:45:02.962989: step: 188/529, loss: 2.441406286379788e-05
2023-01-23 03:45:04.136341: step: 192/529, loss: 0.02805481106042862
2023-01-23 03:45:05.308650: step: 196/529, loss: 0.0001373291015625
2023-01-23 03:45:06.506023: step: 200/529, loss: 0.00017805099196266383
2023-01-23 03:45:07.703001: step: 204/529, loss: 0.015758514404296875
2023-01-23 03:45:08.949757: step: 208/529, loss: 0.21355171501636505
2023-01-23 03:45:10.117981: step: 212/529, loss: 0.00011086463928222656
2023-01-23 03:45:11.291034: step: 216/529, loss: 0.006464862730354071
2023-01-23 03:45:12.490507: step: 220/529, loss: 0.0763818770647049
2023-01-23 03:45:13.702049: step: 224/529, loss: 0.08663111180067062
2023-01-23 03:45:14.859787: step: 228/529, loss: 0.010535096749663353
2023-01-23 03:45:16.018465: step: 232/529, loss: 0.020877551287412643
2023-01-23 03:45:17.249031: step: 236/529, loss: 0.01925039477646351
2023-01-23 03:45:18.413839: step: 240/529, loss: 0.004262924659997225
2023-01-23 03:45:19.594114: step: 244/529, loss: 0.03810299560427666
2023-01-23 03:45:20.766779: step: 248/529, loss: 0.00286521902307868
2023-01-23 03:45:22.005803: step: 252/529, loss: 0.08436579257249832
2023-01-23 03:45:23.198752: step: 256/529, loss: 0.03114328533411026
2023-01-23 03:45:24.377993: step: 260/529, loss: 0.006331252865493298
2023-01-23 03:45:25.610204: step: 264/529, loss: 0.01859569549560547
2023-01-23 03:45:26.778950: step: 268/529, loss: 0.0009475707774981856
2023-01-23 03:45:27.954603: step: 272/529, loss: 0.0001999855157919228
2023-01-23 03:45:29.145658: step: 276/529, loss: 0.014757824130356312
2023-01-23 03:45:30.314490: step: 280/529, loss: 0.00096893310546875
2023-01-23 03:45:31.491024: step: 284/529, loss: 0.00014920235844329
2023-01-23 03:45:32.742943: step: 288/529, loss: 0.031137848272919655
2023-01-23 03:45:33.911079: step: 292/529, loss: 0.010267352685332298
2023-01-23 03:45:35.091793: step: 296/529, loss: 0.012238883413374424
2023-01-23 03:45:36.335983: step: 300/529, loss: 0.00220832834020257
2023-01-23 03:45:37.512987: step: 304/529, loss: 0.02190227434039116
2023-01-23 03:45:38.717294: step: 308/529, loss: 0.001356363296508789
2023-01-23 03:45:39.962139: step: 312/529, loss: 0.01667766645550728
2023-01-23 03:45:41.162837: step: 316/529, loss: 0.003408050397410989
2023-01-23 03:45:42.361370: step: 320/529, loss: 0.010883904062211514
2023-01-23 03:45:43.595398: step: 324/529, loss: 0.025311851873993874
2023-01-23 03:45:44.783225: step: 328/529, loss: 0.00088329310528934
2023-01-23 03:45:45.943785: step: 332/529, loss: 0.007094192318618298
2023-01-23 03:45:47.154320: step: 336/529, loss: 0.00018911361985374242
2023-01-23 03:45:48.312322: step: 340/529, loss: 0.00045862197293899953
2023-01-23 03:45:49.502120: step: 344/529, loss: 7.638931856490672e-05
2023-01-23 03:45:50.665263: step: 348/529, loss: 0.0004475593741517514
2023-01-23 03:45:51.858624: step: 352/529, loss: 0.0477084182202816
2023-01-23 03:45:52.978266: step: 356/529, loss: 0.00011663437180686742
2023-01-23 03:45:54.192621: step: 360/529, loss: 0.004853058140724897
2023-01-23 03:45:55.513812: step: 364/529, loss: 0.0001011848435155116
2023-01-23 03:45:56.729807: step: 368/529, loss: 0.0011312485439702868
2023-01-23 03:45:57.914686: step: 372/529, loss: 0.0007665634038858116
2023-01-23 03:45:59.091693: step: 376/529, loss: 0.008740234188735485
2023-01-23 03:46:00.296110: step: 380/529, loss: 0.010465908795595169
2023-01-23 03:46:01.459111: step: 384/529, loss: 0.00942773837596178
2023-01-23 03:46:02.693759: step: 388/529, loss: 0.0003105163632426411
2023-01-23 03:46:03.867974: step: 392/529, loss: 0.003458309220150113
2023-01-23 03:46:05.056985: step: 396/529, loss: 0.0013598442310467362
2023-01-23 03:46:06.253507: step: 400/529, loss: 0.011349869892001152
2023-01-23 03:46:07.466849: step: 404/529, loss: 0.00021533964900299907
2023-01-23 03:46:08.605810: step: 408/529, loss: 0.00022144318791106343
2023-01-23 03:46:09.798625: step: 412/529, loss: 9.15527380129788e-06
2023-01-23 03:46:11.016810: step: 416/529, loss: 0.005234050564467907
2023-01-23 03:46:12.241684: step: 420/529, loss: 0.03963203728199005
2023-01-23 03:46:13.434731: step: 424/529, loss: 1.735687328618951e-05
2023-01-23 03:46:14.599922: step: 428/529, loss: 0.0015305520500987768
2023-01-23 03:46:15.853689: step: 432/529, loss: 0.020304633304476738
2023-01-23 03:46:17.060802: step: 436/529, loss: 0.04639263078570366
2023-01-23 03:46:18.229889: step: 440/529, loss: 0.00025539397029206157
2023-01-23 03:46:19.437161: step: 444/529, loss: 0.056534577161073685
2023-01-23 03:46:20.630248: step: 448/529, loss: 8.440018063993193e-06
2023-01-23 03:46:21.810187: step: 452/529, loss: 0.025882070884108543
2023-01-23 03:46:22.997346: step: 456/529, loss: 0.0001871108979685232
2023-01-23 03:46:24.220991: step: 460/529, loss: 0.001416015555150807
2023-01-23 03:46:25.433879: step: 464/529, loss: 6.904602196300402e-05
2023-01-23 03:46:26.564241: step: 468/529, loss: 0.00015163421630859375
2023-01-23 03:46:27.785682: step: 472/529, loss: 0.0022642137482762337
2023-01-23 03:46:28.972746: step: 476/529, loss: 0.0030195238068699837
2023-01-23 03:46:30.141267: step: 480/529, loss: 0.08980374783277512
2023-01-23 03:46:31.347273: step: 484/529, loss: 0.0006435394170694053
2023-01-23 03:46:32.556054: step: 488/529, loss: 0.07520389556884766
2023-01-23 03:46:33.782001: step: 492/529, loss: 0.09205436706542969
2023-01-23 03:46:34.988105: step: 496/529, loss: 9.675026376498863e-05
2023-01-23 03:46:36.191679: step: 500/529, loss: 0.006104469299316406
2023-01-23 03:46:37.366983: step: 504/529, loss: 0.0002510070917196572
2023-01-23 03:46:38.597474: step: 508/529, loss: 0.00519142160192132
2023-01-23 03:46:39.802642: step: 512/529, loss: 0.0221099853515625
2023-01-23 03:46:41.018245: step: 516/529, loss: 0.02217893674969673
2023-01-23 03:46:42.240064: step: 520/529, loss: 0.00015125275240279734
2023-01-23 03:46:43.402898: step: 524/529, loss: 0.008015727624297142
2023-01-23 03:46:44.619491: step: 528/529, loss: 0.011707497760653496
2023-01-23 03:46:45.790416: step: 532/529, loss: 0.003997230436652899
2023-01-23 03:46:46.995714: step: 536/529, loss: -3.814697265625e-06
2023-01-23 03:46:48.213634: step: 540/529, loss: 0.0002864837588276714
2023-01-23 03:46:49.427283: step: 544/529, loss: 0.0034162523224949837
2023-01-23 03:46:50.651570: step: 548/529, loss: 0.0002442359982524067
2023-01-23 03:46:51.860189: step: 552/529, loss: 0.01571192778646946
2023-01-23 03:46:53.039513: step: 556/529, loss: 0.00012807846360374242
2023-01-23 03:46:54.257958: step: 560/529, loss: 0.00701751746237278
2023-01-23 03:46:55.462309: step: 564/529, loss: 0.0005651474348269403
2023-01-23 03:46:56.646802: step: 568/529, loss: 0.030129052698612213
2023-01-23 03:46:57.857387: step: 572/529, loss: 0.00363845843821764
2023-01-23 03:46:59.058894: step: 576/529, loss: 0.0014683724148198962
2023-01-23 03:47:00.220368: step: 580/529, loss: 0.0019275664817541838
2023-01-23 03:47:01.422484: step: 584/529, loss: 0.0018230437999591231
2023-01-23 03:47:02.716783: step: 588/529, loss: 0.0016445161309093237
2023-01-23 03:47:03.906077: step: 592/529, loss: 5.9604644775390625e-05
2023-01-23 03:47:05.114873: step: 596/529, loss: 0.0002191543608205393
2023-01-23 03:47:06.304516: step: 600/529, loss: 0.0007568836444988847
2023-01-23 03:47:07.531591: step: 604/529, loss: 0.00040407179039902985
2023-01-23 03:47:08.720703: step: 608/529, loss: 0.0002759933704510331
2023-01-23 03:47:09.904638: step: 612/529, loss: 0.0007089138380251825
2023-01-23 03:47:11.108038: step: 616/529, loss: 6.532669794978574e-05
2023-01-23 03:47:12.302352: step: 620/529, loss: 0.0008990287315100431
2023-01-23 03:47:13.512373: step: 624/529, loss: 0.002867126604542136
2023-01-23 03:47:14.711462: step: 628/529, loss: 0.0003772735653910786
2023-01-23 03:47:15.892669: step: 632/529, loss: 0.021743880584836006
2023-01-23 03:47:17.102765: step: 636/529, loss: 0.004989433567970991
2023-01-23 03:47:18.267486: step: 640/529, loss: 0.00010070801363326609
2023-01-23 03:47:19.513253: step: 644/529, loss: 0.026337958872318268
2023-01-23 03:47:20.742953: step: 648/529, loss: 0.0022365569602698088
2023-01-23 03:47:21.925529: step: 652/529, loss: 0.0008566856267862022
2023-01-23 03:47:23.101737: step: 656/529, loss: 0.10277990996837616
2023-01-23 03:47:24.244125: step: 660/529, loss: 0.0002665519714355469
2023-01-23 03:47:25.529863: step: 664/529, loss: 0.0032622814178466797
2023-01-23 03:47:26.718394: step: 668/529, loss: 0.00014422535605262965
2023-01-23 03:47:27.905941: step: 672/529, loss: 0.003916407003998756
2023-01-23 03:47:29.131694: step: 676/529, loss: 0.00019788742065429688
2023-01-23 03:47:30.354446: step: 680/529, loss: 0.019771194085478783
2023-01-23 03:47:31.543158: step: 684/529, loss: 0.004765319637954235
2023-01-23 03:47:32.749026: step: 688/529, loss: 0.0004483223019633442
2023-01-23 03:47:33.945608: step: 692/529, loss: 0.0023601532448083162
2023-01-23 03:47:35.171998: step: 696/529, loss: 0.00390968332067132
2023-01-23 03:47:36.360045: step: 700/529, loss: 0.04851856082677841
2023-01-23 03:47:37.516712: step: 704/529, loss: 1.6212465197895654e-05
2023-01-23 03:47:38.707632: step: 708/529, loss: 0.0015943527687340975
2023-01-23 03:47:39.950707: step: 712/529, loss: 0.0713178738951683
2023-01-23 03:47:41.163296: step: 716/529, loss: 0.0019653320778161287
2023-01-23 03:47:42.369465: step: 720/529, loss: 0.0008353710290975869
2023-01-23 03:47:43.579342: step: 724/529, loss: 0.00015573501877952367
2023-01-23 03:47:44.767540: step: 728/529, loss: 0.005900764837861061
2023-01-23 03:47:45.946857: step: 732/529, loss: 0.07257615029811859
2023-01-23 03:47:47.116581: step: 736/529, loss: 0.008382988162338734
2023-01-23 03:47:48.301229: step: 740/529, loss: 0.006828689482063055
2023-01-23 03:47:49.472889: step: 744/529, loss: 0.008426666259765625
2023-01-23 03:47:50.724214: step: 748/529, loss: 0.00099945068359375
2023-01-23 03:47:51.898910: step: 752/529, loss: 0.033737894147634506
2023-01-23 03:47:53.125514: step: 756/529, loss: 0.00043392181396484375
2023-01-23 03:47:54.367574: step: 760/529, loss: 0.028609275817871094
2023-01-23 03:47:55.625009: step: 764/529, loss: 0.0004980087396688759
2023-01-23 03:47:56.835779: step: 768/529, loss: 0.05525636672973633
2023-01-23 03:47:58.034654: step: 772/529, loss: 0.026274489238858223
2023-01-23 03:47:59.199448: step: 776/529, loss: 4.215240915073082e-05
2023-01-23 03:48:00.380342: step: 780/529, loss: 0.021368885412812233
2023-01-23 03:48:01.541148: step: 784/529, loss: 0.002225208329036832
2023-01-23 03:48:02.727860: step: 788/529, loss: 0.016387177631258965
2023-01-23 03:48:03.924780: step: 792/529, loss: 0.012323761358857155
2023-01-23 03:48:05.132075: step: 796/529, loss: 0.0009130478138104081
2023-01-23 03:48:06.301744: step: 800/529, loss: 0.00011219978478038684
2023-01-23 03:48:07.513824: step: 804/529, loss: 0.04990873485803604
2023-01-23 03:48:08.731701: step: 808/529, loss: 3.690719313453883e-05
2023-01-23 03:48:09.921275: step: 812/529, loss: 0.0005104065057821572
2023-01-23 03:48:11.099412: step: 816/529, loss: 0.0008589744684286416
2023-01-23 03:48:12.272617: step: 820/529, loss: 0.003920650575309992
2023-01-23 03:48:13.501621: step: 824/529, loss: 0.012481831945478916
2023-01-23 03:48:14.745671: step: 828/529, loss: 0.05159268528223038
2023-01-23 03:48:15.919327: step: 832/529, loss: 0.0016345500480383635
2023-01-23 03:48:17.073194: step: 836/529, loss: 0.0011128425830975175
2023-01-23 03:48:18.273571: step: 840/529, loss: 0.0003391265927348286
2023-01-23 03:48:19.492257: step: 844/529, loss: 0.0008003473049029708
2023-01-23 03:48:20.707191: step: 848/529, loss: 0.003372669219970703
2023-01-23 03:48:21.936694: step: 852/529, loss: 0.005484771449118853
2023-01-23 03:48:23.151952: step: 856/529, loss: 0.020690681412816048
2023-01-23 03:48:24.346058: step: 860/529, loss: 0.0008691787952557206
2023-01-23 03:48:25.530248: step: 864/529, loss: 0.0003770828479900956
2023-01-23 03:48:26.782635: step: 868/529, loss: 0.002551555633544922
2023-01-23 03:48:28.002184: step: 872/529, loss: 0.0023283003829419613
2023-01-23 03:48:29.140995: step: 876/529, loss: 0.0013247966999188066
2023-01-23 03:48:30.319478: step: 880/529, loss: 0.013599300757050514
2023-01-23 03:48:31.520457: step: 884/529, loss: 0.0004140853707212955
2023-01-23 03:48:32.686114: step: 888/529, loss: 0.0003833770751953125
2023-01-23 03:48:33.892248: step: 892/529, loss: 0.010223388671875
2023-01-23 03:48:35.094568: step: 896/529, loss: 0.021367836743593216
2023-01-23 03:48:36.287953: step: 900/529, loss: 0.006887626834213734
2023-01-23 03:48:37.511163: step: 904/529, loss: 0.025962544605135918
2023-01-23 03:48:38.700076: step: 908/529, loss: 0.11311989277601242
2023-01-23 03:48:39.876118: step: 912/529, loss: 9.860992577159777e-05
2023-01-23 03:48:41.068641: step: 916/529, loss: 0.0002941131533589214
2023-01-23 03:48:42.309703: step: 920/529, loss: 0.008574104867875576
2023-01-23 03:48:43.521207: step: 924/529, loss: 0.014598656445741653
2023-01-23 03:48:44.719264: step: 928/529, loss: 0.008367538452148438
2023-01-23 03:48:45.956236: step: 932/529, loss: 0.007159137632697821
2023-01-23 03:48:47.188148: step: 936/529, loss: 0.00037450791569426656
2023-01-23 03:48:48.362423: step: 940/529, loss: 0.008912897668778896
2023-01-23 03:48:49.571793: step: 944/529, loss: 0.0006434440729208291
2023-01-23 03:48:50.790669: step: 948/529, loss: 0.0003526687796693295
2023-01-23 03:48:51.982807: step: 952/529, loss: 0.00012640953355003148
2023-01-23 03:48:53.173951: step: 956/529, loss: 0.004246425349265337
2023-01-23 03:48:54.392434: step: 960/529, loss: 0.0005268097156658769
2023-01-23 03:48:55.616910: step: 964/529, loss: 0.004040718078613281
2023-01-23 03:48:56.807467: step: 968/529, loss: 0.00014801025099586695
2023-01-23 03:48:58.011264: step: 972/529, loss: 0.024769021198153496
2023-01-23 03:48:59.186641: step: 976/529, loss: 1.010894811770413e-05
2023-01-23 03:49:00.427508: step: 980/529, loss: 0.02168731763958931
2023-01-23 03:49:01.631704: step: 984/529, loss: 0.0597570426762104
2023-01-23 03:49:02.796421: step: 988/529, loss: 8.544921729480848e-05
2023-01-23 03:49:04.008732: step: 992/529, loss: 0.009358787909150124
2023-01-23 03:49:05.212403: step: 996/529, loss: 8.888245065463707e-05
2023-01-23 03:49:06.411811: step: 1000/529, loss: 0.001436996622942388
2023-01-23 03:49:07.605577: step: 1004/529, loss: 0.003125953720882535
2023-01-23 03:49:08.784321: step: 1008/529, loss: 0.027190685272216797
2023-01-23 03:49:09.979596: step: 1012/529, loss: 0.0006450653309002519
2023-01-23 03:49:11.177129: step: 1016/529, loss: 0.2021610289812088
2023-01-23 03:49:12.386225: step: 1020/529, loss: 1.659393274167087e-05
2023-01-23 03:49:13.594245: step: 1024/529, loss: 0.00047588348388671875
2023-01-23 03:49:14.778624: step: 1028/529, loss: 5.512237476068549e-05
2023-01-23 03:49:15.985673: step: 1032/529, loss: 0.060749053955078125
2023-01-23 03:49:17.185495: step: 1036/529, loss: 0.0056081777438521385
2023-01-23 03:49:18.359173: step: 1040/529, loss: 0.0012121201725676656
2023-01-23 03:49:19.544138: step: 1044/529, loss: 0.0002593994140625
2023-01-23 03:49:20.740942: step: 1048/529, loss: 0.04466743767261505
2023-01-23 03:49:21.941755: step: 1052/529, loss: 0.007094955537468195
2023-01-23 03:49:23.122787: step: 1056/529, loss: 0.016281509771943092
2023-01-23 03:49:24.341659: step: 1060/529, loss: -9.34600848268019e-06
2023-01-23 03:49:25.531774: step: 1064/529, loss: 0.00012645722017623484
2023-01-23 03:49:26.719386: step: 1068/529, loss: 0.06765823811292648
2023-01-23 03:49:27.885388: step: 1072/529, loss: -7.295608156709932e-06
2023-01-23 03:49:29.055645: step: 1076/529, loss: 0.0007905960083007812
2023-01-23 03:49:30.263853: step: 1080/529, loss: 0.05456504970788956
2023-01-23 03:49:31.500990: step: 1084/529, loss: 0.008597373962402344
2023-01-23 03:49:32.676682: step: 1088/529, loss: 0.0007982254028320312
2023-01-23 03:49:33.865287: step: 1092/529, loss: 0.0019685744773596525
2023-01-23 03:49:35.047946: step: 1096/529, loss: 0.00016858578601386398
2023-01-23 03:49:36.229347: step: 1100/529, loss: 2.6607514882925898e-05
2023-01-23 03:49:37.410310: step: 1104/529, loss: 0.1957935392856598
2023-01-23 03:49:38.577875: step: 1108/529, loss: 7.247925168485381e-06
2023-01-23 03:49:39.734361: step: 1112/529, loss: 0.0011564255692064762
2023-01-23 03:49:40.932979: step: 1116/529, loss: 0.0030940056312829256
2023-01-23 03:49:42.114628: step: 1120/529, loss: 0.010408020578324795
2023-01-23 03:49:43.261524: step: 1124/529, loss: 9.13620024221018e-05
2023-01-23 03:49:44.471248: step: 1128/529, loss: 0.0021070479415357113
2023-01-23 03:49:45.670515: step: 1132/529, loss: 0.0001659393310546875
2023-01-23 03:49:46.863549: step: 1136/529, loss: 2.8419495720299892e-05
2023-01-23 03:49:48.089346: step: 1140/529, loss: 0.03549323230981827
2023-01-23 03:49:49.259119: step: 1144/529, loss: 0.000324249267578125
2023-01-23 03:49:50.435560: step: 1148/529, loss: 0.0008911133045330644
2023-01-23 03:49:51.665054: step: 1152/529, loss: 0.04113483428955078
2023-01-23 03:49:52.853354: step: 1156/529, loss: 0.0001880168856587261
2023-01-23 03:49:54.037665: step: 1160/529, loss: 0.001344966934993863
2023-01-23 03:49:55.207250: step: 1164/529, loss: 0.10941438376903534
2023-01-23 03:49:56.387832: step: 1168/529, loss: 0.01562347449362278
2023-01-23 03:49:57.553277: step: 1172/529, loss: 0.0001163482666015625
2023-01-23 03:49:58.731784: step: 1176/529, loss: 0.000244140625
2023-01-23 03:49:59.940306: step: 1180/529, loss: 0.002197265625
2023-01-23 03:50:01.139572: step: 1184/529, loss: 0.0017303467029705644
2023-01-23 03:50:02.356973: step: 1188/529, loss: 1.735687328618951e-05
2023-01-23 03:50:03.621652: step: 1192/529, loss: 0.023471450433135033
2023-01-23 03:50:04.859163: step: 1196/529, loss: 0.0016420366009697318
2023-01-23 03:50:06.067745: step: 1200/529, loss: 2.7084352041129023e-05
2023-01-23 03:50:07.254301: step: 1204/529, loss: 0.05576743930578232
2023-01-23 03:50:08.445384: step: 1208/529, loss: 0.00030298231285996735
2023-01-23 03:50:09.653604: step: 1212/529, loss: 0.00066375732421875
2023-01-23 03:50:10.904111: step: 1216/529, loss: 0.0050605772994458675
2023-01-23 03:50:12.074240: step: 1220/529, loss: 0.00010914802987826988
2023-01-23 03:50:13.241821: step: 1224/529, loss: 0.0546233169734478
2023-01-23 03:50:14.438858: step: 1228/529, loss: 0.0021585465874522924
2023-01-23 03:50:15.607751: step: 1232/529, loss: 0.004947852808982134
2023-01-23 03:50:16.813279: step: 1236/529, loss: 0.005428123287856579
2023-01-23 03:50:18.003386: step: 1240/529, loss: 0.0010595321655273438
2023-01-23 03:50:19.167981: step: 1244/529, loss: 0.007367610931396484
2023-01-23 03:50:20.388938: step: 1248/529, loss: 0.0010976791381835938
2023-01-23 03:50:21.606533: step: 1252/529, loss: 0.007058906368911266
2023-01-23 03:50:22.814268: step: 1256/529, loss: -5.5599211918888614e-05
2023-01-23 03:50:24.002087: step: 1260/529, loss: 0.005295943934470415
2023-01-23 03:50:25.179853: step: 1264/529, loss: 0.0005245208740234375
2023-01-23 03:50:26.319769: step: 1268/529, loss: 5.53131121705519e-06
2023-01-23 03:50:27.556623: step: 1272/529, loss: 0.029079819098114967
2023-01-23 03:50:28.767056: step: 1276/529, loss: 0.08116894215345383
2023-01-23 03:50:30.021564: step: 1280/529, loss: 0.0007322311284951866
2023-01-23 03:50:31.213097: step: 1284/529, loss: 0.002185344696044922
2023-01-23 03:50:32.402092: step: 1288/529, loss: 0.13346920907497406
2023-01-23 03:50:33.594556: step: 1292/529, loss: 0.005793952848762274
2023-01-23 03:50:34.765703: step: 1296/529, loss: 0.008227539248764515
2023-01-23 03:50:35.944303: step: 1300/529, loss: 7.696152169955894e-05
2023-01-23 03:50:37.166457: step: 1304/529, loss: 0.03481044992804527
2023-01-23 03:50:38.345724: step: 1308/529, loss: 0.02016420289874077
2023-01-23 03:50:39.556732: step: 1312/529, loss: 0.0004611969052348286
2023-01-23 03:50:40.740890: step: 1316/529, loss: 0.00869522150605917
2023-01-23 03:50:41.929090: step: 1320/529, loss: 0.0008018493535928428
2023-01-23 03:50:43.121309: step: 1324/529, loss: 0.0005743026849813759
2023-01-23 03:50:44.360103: step: 1328/529, loss: 0.031172847375273705
2023-01-23 03:50:45.587101: step: 1332/529, loss: 0.001120912958867848
2023-01-23 03:50:46.813629: step: 1336/529, loss: 0.00335445418022573
2023-01-23 03:50:47.985404: step: 1340/529, loss: 0.0003461838059592992
2023-01-23 03:50:49.165149: step: 1344/529, loss: 1.430511474609375e-05
2023-01-23 03:50:50.359617: step: 1348/529, loss: 0.00023345947556663305
2023-01-23 03:50:51.563848: step: 1352/529, loss: 0.00012245179095771164
2023-01-23 03:50:52.740711: step: 1356/529, loss: 0.01572895050048828
2023-01-23 03:50:53.914223: step: 1360/529, loss: 0.0003319740353617817
2023-01-23 03:50:55.135630: step: 1364/529, loss: 7.820130122127011e-06
2023-01-23 03:50:56.312152: step: 1368/529, loss: 0.046427156776189804
2023-01-23 03:50:57.580958: step: 1372/529, loss: 0.03627300634980202
2023-01-23 03:50:58.769738: step: 1376/529, loss: 0.0005508423200808465
2023-01-23 03:50:59.981248: step: 1380/529, loss: 0.010284805670380592
2023-01-23 03:51:01.206879: step: 1384/529, loss: 0.004490375518798828
2023-01-23 03:51:02.431451: step: 1388/529, loss: 0.0024746893905103207
2023-01-23 03:51:03.658378: step: 1392/529, loss: 0.00020141602726653218
2023-01-23 03:51:04.840163: step: 1396/529, loss: 0.0029833794105798006
2023-01-23 03:51:06.045428: step: 1400/529, loss: 0.00792026612907648
2023-01-23 03:51:07.228720: step: 1404/529, loss: 4.4631960918195546e-05
2023-01-23 03:51:08.406156: step: 1408/529, loss: 0.022495746612548828
2023-01-23 03:51:09.562631: step: 1412/529, loss: 0.0024471760261803865
2023-01-23 03:51:10.747633: step: 1416/529, loss: 0.003971099853515625
2023-01-23 03:51:11.988938: step: 1420/529, loss: 0.016007328405976295
2023-01-23 03:51:13.193731: step: 1424/529, loss: 7.090568396961316e-05
2023-01-23 03:51:14.378476: step: 1428/529, loss: 0.010274888016283512
2023-01-23 03:51:15.555211: step: 1432/529, loss: 0.021803809329867363
2023-01-23 03:51:16.722435: step: 1436/529, loss: 0.00027141571626998484
2023-01-23 03:51:17.946857: step: 1440/529, loss: 0.01190719660371542
2023-01-23 03:51:19.144151: step: 1444/529, loss: 0.003740501357242465
2023-01-23 03:51:20.381675: step: 1448/529, loss: 0.00031185150146484375
2023-01-23 03:51:21.552511: step: 1452/529, loss: 0.06364526599645615
2023-01-23 03:51:22.727504: step: 1456/529, loss: 0.0003293037589173764
2023-01-23 03:51:23.938574: step: 1460/529, loss: 0.004374980926513672
2023-01-23 03:51:25.131390: step: 1464/529, loss: 3.4046173823298886e-05
2023-01-23 03:51:26.324627: step: 1468/529, loss: 2.574920654296875e-05
2023-01-23 03:51:27.493360: step: 1472/529, loss: 0.0002283096400788054
2023-01-23 03:51:28.660007: step: 1476/529, loss: 2.6988982426701114e-05
2023-01-23 03:51:29.851321: step: 1480/529, loss: 0.0028427124489098787
2023-01-23 03:51:31.018843: step: 1484/529, loss: 0.024480247870087624
2023-01-23 03:51:32.191688: step: 1488/529, loss: 0.0013875007862225175
2023-01-23 03:51:33.381538: step: 1492/529, loss: 0.00023746490478515625
2023-01-23 03:51:34.585617: step: 1496/529, loss: 0.02492804452776909
2023-01-23 03:51:35.780320: step: 1500/529, loss: 0.01005945261567831
2023-01-23 03:51:36.955479: step: 1504/529, loss: 0.02878589555621147
2023-01-23 03:51:38.120507: step: 1508/529, loss: 7.62939453125e-06
2023-01-23 03:51:39.337876: step: 1512/529, loss: 5.426407005870715e-05
2023-01-23 03:51:40.523918: step: 1516/529, loss: 0.000453948974609375
2023-01-23 03:51:41.712063: step: 1520/529, loss: 0.01130456943064928
2023-01-23 03:51:42.944205: step: 1524/529, loss: 0.006641769781708717
2023-01-23 03:51:44.119694: step: 1528/529, loss: 2.408623549854383e-05
2023-01-23 03:51:45.292866: step: 1532/529, loss: 0.0009686946868896484
2023-01-23 03:51:46.503669: step: 1536/529, loss: 0.01239156723022461
2023-01-23 03:51:47.702771: step: 1540/529, loss: 0.012543296441435814
2023-01-23 03:51:48.923304: step: 1544/529, loss: 0.0011988639598712325
2023-01-23 03:51:50.107379: step: 1548/529, loss: 0.01417740061879158
2023-01-23 03:51:51.304548: step: 1552/529, loss: 1.8119812921213452e-06
2023-01-23 03:51:52.540080: step: 1556/529, loss: 0.006872177589684725
2023-01-23 03:51:53.713672: step: 1560/529, loss: 0.02960510365664959
2023-01-23 03:51:54.910645: step: 1564/529, loss: 0.00018749237642623484
2023-01-23 03:51:56.117232: step: 1568/529, loss: 1.010894811770413e-05
2023-01-23 03:51:57.311312: step: 1572/529, loss: 0.042542073875665665
2023-01-23 03:51:58.484652: step: 1576/529, loss: 0.05537395551800728
2023-01-23 03:51:59.716656: step: 1580/529, loss: 0.000194549560546875
2023-01-23 03:52:00.908113: step: 1584/529, loss: 0.0018932819366455078
2023-01-23 03:52:02.146561: step: 1588/529, loss: 0.00416336115449667
2023-01-23 03:52:03.350113: step: 1592/529, loss: 0.025518132373690605
2023-01-23 03:52:04.522662: step: 1596/529, loss: 0.009344673715531826
2023-01-23 03:52:05.692784: step: 1600/529, loss: 0.0032118798699229956
2023-01-23 03:52:06.882487: step: 1604/529, loss: 0.00014743805513717234
2023-01-23 03:52:08.050884: step: 1608/529, loss: 6.575584120582789e-05
2023-01-23 03:52:09.248963: step: 1612/529, loss: 0.00054931640625
2023-01-23 03:52:10.439085: step: 1616/529, loss: 0.013928604312241077
2023-01-23 03:52:11.640498: step: 1620/529, loss: 0.0024173737037926912
2023-01-23 03:52:12.833539: step: 1624/529, loss: 0.009382057934999466
2023-01-23 03:52:13.997970: step: 1628/529, loss: 4.38690185546875e-05
2023-01-23 03:52:15.200485: step: 1632/529, loss: 0.008113289251923561
2023-01-23 03:52:16.410808: step: 1636/529, loss: 0.0033277510665357113
2023-01-23 03:52:17.593684: step: 1640/529, loss: 0.12257251888513565
2023-01-23 03:52:18.789666: step: 1644/529, loss: 0.006795788183808327
2023-01-23 03:52:19.998503: step: 1648/529, loss: 0.005118942353874445
2023-01-23 03:52:21.227625: step: 1652/529, loss: 0.019062327221035957
2023-01-23 03:52:22.386017: step: 1656/529, loss: 0.0044578551314771175
2023-01-23 03:52:23.528801: step: 1660/529, loss: 9.040832082973793e-05
2023-01-23 03:52:24.751489: step: 1664/529, loss: 0.023558713495731354
2023-01-23 03:52:25.958134: step: 1668/529, loss: 0.006600379943847656
2023-01-23 03:52:27.119068: step: 1672/529, loss: 0.030307531356811523
2023-01-23 03:52:28.305587: step: 1676/529, loss: 4.5776364459015895e-06
2023-01-23 03:52:29.525747: step: 1680/529, loss: 0.018062591552734375
2023-01-23 03:52:30.698606: step: 1684/529, loss: 0.0003994941944256425
2023-01-23 03:52:31.935751: step: 1688/529, loss: 0.09516115486621857
2023-01-23 03:52:33.112313: step: 1692/529, loss: 0.0005546570173464715
2023-01-23 03:52:34.309242: step: 1696/529, loss: 6.8187719080015086e-06
2023-01-23 03:52:35.508100: step: 1700/529, loss: 0.029366517439484596
2023-01-23 03:52:36.740341: step: 1704/529, loss: 0.00013456343731377274
2023-01-23 03:52:37.949534: step: 1708/529, loss: 0.0027837753295898438
2023-01-23 03:52:39.153720: step: 1712/529, loss: 0.012783337384462357
2023-01-23 03:52:40.387479: step: 1716/529, loss: -7.629394076502649e-07
2023-01-23 03:52:41.594562: step: 1720/529, loss: 0.006575966253876686
2023-01-23 03:52:42.841327: step: 1724/529, loss: 0.00048255923320539296
2023-01-23 03:52:44.105910: step: 1728/529, loss: 0.0001010894775390625
2023-01-23 03:52:45.291830: step: 1732/529, loss: 0.0012860298156738281
2023-01-23 03:52:46.503469: step: 1736/529, loss: 1.4138221558823716e-05
2023-01-23 03:52:47.746312: step: 1740/529, loss: 0.0001581192045705393
2023-01-23 03:52:48.922693: step: 1744/529, loss: 0.13606788218021393
2023-01-23 03:52:50.141112: step: 1748/529, loss: 0.07141780853271484
2023-01-23 03:52:51.328738: step: 1752/529, loss: 0.0007764697074890137
2023-01-23 03:52:52.498276: step: 1756/529, loss: 0.0003563881036825478
2023-01-23 03:52:53.673935: step: 1760/529, loss: 0.00023126602172851562
2023-01-23 03:52:54.871199: step: 1764/529, loss: 0.20197181403636932
2023-01-23 03:52:56.089214: step: 1768/529, loss: 0.0018333016196265817
2023-01-23 03:52:57.277144: step: 1772/529, loss: 0.0001388549862895161
2023-01-23 03:52:58.428482: step: 1776/529, loss: -2.8610227218450746e-06
2023-01-23 03:52:59.605828: step: 1780/529, loss: 0.0002076149103231728
2023-01-23 03:53:00.829340: step: 1784/529, loss: 0.0037496089935302734
2023-01-23 03:53:02.007452: step: 1788/529, loss: 8.00132766016759e-05
2023-01-23 03:53:03.229237: step: 1792/529, loss: 0.001179695245809853
2023-01-23 03:53:04.431462: step: 1796/529, loss: 0.007172584533691406
2023-01-23 03:53:05.638112: step: 1800/529, loss: 0.00010862351336982101
2023-01-23 03:53:06.804890: step: 1804/529, loss: 3.957748504035408e-06
2023-01-23 03:53:08.014500: step: 1808/529, loss: 0.0012466430198401213
2023-01-23 03:53:09.210960: step: 1812/529, loss: 8.840560622047633e-05
2023-01-23 03:53:10.396613: step: 1816/529, loss: 0.0003914833068847656
2023-01-23 03:53:11.553014: step: 1820/529, loss: 0.018556786701083183
2023-01-23 03:53:12.785119: step: 1824/529, loss: 0.0011154175736010075
2023-01-23 03:53:13.992943: step: 1828/529, loss: -1.7690657841740176e-05
2023-01-23 03:53:15.176977: step: 1832/529, loss: 0.04803028330206871
2023-01-23 03:53:16.404360: step: 1836/529, loss: 0.0010268688201904297
2023-01-23 03:53:17.588599: step: 1840/529, loss: 0.01755809783935547
2023-01-23 03:53:18.821341: step: 1844/529, loss: 0.0047210692428052425
2023-01-23 03:53:20.021178: step: 1848/529, loss: 0.0007061004871502519
2023-01-23 03:53:21.261681: step: 1852/529, loss: 0.00408935546875
2023-01-23 03:53:22.457614: step: 1856/529, loss: 0.006187486927956343
2023-01-23 03:53:23.699402: step: 1860/529, loss: 2.002716064453125e-05
2023-01-23 03:53:24.914597: step: 1864/529, loss: 0.01383819617331028
2023-01-23 03:53:26.110790: step: 1868/529, loss: 6.66618361719884e-05
2023-01-23 03:53:27.331137: step: 1872/529, loss: 0.0011068343883380294
2023-01-23 03:53:28.560339: step: 1876/529, loss: 0.00041456223698332906
2023-01-23 03:53:29.765121: step: 1880/529, loss: 0.003167057177051902
2023-01-23 03:53:30.942721: step: 1884/529, loss: 1.6307829355355352e-05
2023-01-23 03:53:32.131606: step: 1888/529, loss: 0.0013562202220782638
2023-01-23 03:53:33.324157: step: 1892/529, loss: 0.00125207903329283
2023-01-23 03:53:34.538359: step: 1896/529, loss: 0.018916606903076172
2023-01-23 03:53:35.765117: step: 1900/529, loss: 0.0005151748773641884
2023-01-23 03:53:36.962671: step: 1904/529, loss: 0.009308434091508389
2023-01-23 03:53:38.165733: step: 1908/529, loss: 0.00052642822265625
2023-01-23 03:53:39.338734: step: 1912/529, loss: 6.771087555534905e-06
2023-01-23 03:53:40.527343: step: 1916/529, loss: 0.011631297878921032
2023-01-23 03:53:41.775946: step: 1920/529, loss: 0.009518814273178577
2023-01-23 03:53:42.989531: step: 1924/529, loss: 0.02677593193948269
2023-01-23 03:53:44.179847: step: 1928/529, loss: 0.008015250787138939
2023-01-23 03:53:45.373571: step: 1932/529, loss: 0.004521655850112438
2023-01-23 03:53:46.528345: step: 1936/529, loss: 6.914138793945312e-05
2023-01-23 03:53:47.744771: step: 1940/529, loss: 0.0019124031532555819
2023-01-23 03:53:48.980879: step: 1944/529, loss: 0.03182869032025337
2023-01-23 03:53:50.163091: step: 1948/529, loss: 0.001189804170280695
2023-01-23 03:53:51.364837: step: 1952/529, loss: 0.00010261536226607859
2023-01-23 03:53:52.587188: step: 1956/529, loss: 0.00010595321509754285
2023-01-23 03:53:53.793506: step: 1960/529, loss: 0.025307130068540573
2023-01-23 03:53:54.980955: step: 1964/529, loss: 0.0002987861807923764
2023-01-23 03:53:56.140568: step: 1968/529, loss: 0.00019760133000090718
2023-01-23 03:53:57.370506: step: 1972/529, loss: 2.4127959477482364e-05
2023-01-23 03:53:58.598453: step: 1976/529, loss: 0.0005468368763104081
2023-01-23 03:53:59.804645: step: 1980/529, loss: 0.007959079928696156
2023-01-23 03:54:01.019415: step: 1984/529, loss: 0.021266557276248932
2023-01-23 03:54:02.239959: step: 1988/529, loss: 0.002390289446339011
2023-01-23 03:54:03.516199: step: 1992/529, loss: 0.00016326904005836695
2023-01-23 03:54:04.724998: step: 1996/529, loss: 0.0011688232189044356
2023-01-23 03:54:05.913468: step: 2000/529, loss: 1.4591216313419864e-05
2023-01-23 03:54:07.119924: step: 2004/529, loss: 0.005731773562729359
2023-01-23 03:54:08.320240: step: 2008/529, loss: 0.0011002063984051347
2023-01-23 03:54:09.554778: step: 2012/529, loss: 0.0024938583374023438
2023-01-23 03:54:10.721414: step: 2016/529, loss: 4.920959327137098e-05
2023-01-23 03:54:11.926414: step: 2020/529, loss: 0.019359970465302467
2023-01-23 03:54:13.105477: step: 2024/529, loss: 0.0009479522705078125
2023-01-23 03:54:14.282892: step: 2028/529, loss: 0.008326435461640358
2023-01-23 03:54:15.455750: step: 2032/529, loss: 2.0503997802734375e-05
2023-01-23 03:54:16.684083: step: 2036/529, loss: 0.005489062983542681
2023-01-23 03:54:17.876658: step: 2040/529, loss: 3.929138256353326e-05
2023-01-23 03:54:19.091404: step: 2044/529, loss: 0.011785602197051048
2023-01-23 03:54:20.295357: step: 2048/529, loss: 0.006059455685317516
2023-01-23 03:54:21.510453: step: 2052/529, loss: 0.0043305400758981705
2023-01-23 03:54:22.694404: step: 2056/529, loss: 8.735657320357859e-05
2023-01-23 03:54:23.894719: step: 2060/529, loss: 3.013610876223538e-05
2023-01-23 03:54:25.075850: step: 2064/529, loss: 0.06370048969984055
2023-01-23 03:54:26.292754: step: 2068/529, loss: 0.0014255524147301912
2023-01-23 03:54:27.526368: step: 2072/529, loss: 0.0006597518804483116
2023-01-23 03:54:28.722161: step: 2076/529, loss: 0.00036649705725722015
2023-01-23 03:54:29.919574: step: 2080/529, loss: 0.0121612548828125
2023-01-23 03:54:31.140852: step: 2084/529, loss: 0.6038684844970703
2023-01-23 03:54:32.299382: step: 2088/529, loss: 2.861022494471399e-07
2023-01-23 03:54:33.510644: step: 2092/529, loss: 0.0030422210693359375
2023-01-23 03:54:34.716697: step: 2096/529, loss: 0.00014095308142714202
2023-01-23 03:54:35.916694: step: 2100/529, loss: 0.0013132572639733553
2023-01-23 03:54:37.111095: step: 2104/529, loss: 0.0006562233320437372
2023-01-23 03:54:38.318381: step: 2108/529, loss: 0.01683693192899227
2023-01-23 03:54:39.490982: step: 2112/529, loss: 0.0032360078766942024
2023-01-23 03:54:40.717254: step: 2116/529, loss: 0.01158595085144043
==================================================
Loss: 0.014
--------------------
Dev: {'event': {'p': 0.5989637305699482, 'r': 0.7696404793608522, 'f1': 0.6736596736596737}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6320076665069477, 'r': 0.7902935889754344, 'f1': 0.7023429179978701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.5569620253164557, 'r': 0.8148148148148148, 'f1': 0.6616541353383458}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.515625, 'r': 0.5238095238095238, 'f1': 0.5196850393700788}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.4888888888888889, 'r': 0.6111111111111112, 'f1': 0.5432098765432098}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 03:55:24.244412: step: 4/529, loss: 0.08703899383544922
2023-01-23 03:55:25.383929: step: 8/529, loss: 0.022186851128935814
2023-01-23 03:55:26.555896: step: 12/529, loss: 0.001086425851099193
2023-01-23 03:55:27.741662: step: 16/529, loss: 4.0721894038142636e-05
2023-01-23 03:55:28.982172: step: 20/529, loss: 0.0002344131498830393
2023-01-23 03:55:30.157746: step: 24/529, loss: 6.608963303733617e-05
2023-01-23 03:55:31.350240: step: 28/529, loss: 0.010137557983398438
2023-01-23 03:55:32.536653: step: 32/529, loss: 0.00024929046048782766
2023-01-23 03:55:33.720222: step: 36/529, loss: -1.602172778802924e-05
2023-01-23 03:55:34.904708: step: 40/529, loss: 6.990433030296117e-05
2023-01-23 03:55:36.104482: step: 44/529, loss: 0.00010929108248092234
2023-01-23 03:55:37.313982: step: 48/529, loss: 0.007225608453154564
2023-01-23 03:55:38.522559: step: 52/529, loss: 0.034627340734004974
2023-01-23 03:55:39.734481: step: 56/529, loss: 0.00010499954805709422
2023-01-23 03:55:40.941843: step: 60/529, loss: 0.014532947912812233
2023-01-23 03:55:42.111845: step: 64/529, loss: 0.002875900361686945
2023-01-23 03:55:43.282346: step: 68/529, loss: 1.33514404296875e-05
2023-01-23 03:55:44.469830: step: 72/529, loss: 0.015816498547792435
2023-01-23 03:55:45.680640: step: 76/529, loss: 0.0013780116569250822
2023-01-23 03:55:46.848686: step: 80/529, loss: 0.003924178890883923
2023-01-23 03:55:48.035640: step: 84/529, loss: 4.9114227294921875e-05
2023-01-23 03:55:49.219845: step: 88/529, loss: 7.691383507335559e-05
2023-01-23 03:55:50.451261: step: 92/529, loss: 0.005752182099968195
2023-01-23 03:55:51.662994: step: 96/529, loss: 0.04823489487171173
2023-01-23 03:55:52.851736: step: 100/529, loss: 0.00444793701171875
2023-01-23 03:55:54.031489: step: 104/529, loss: 0.0017443657852709293
2023-01-23 03:55:55.244429: step: 108/529, loss: 3.814697265625e-06
2023-01-23 03:55:56.431035: step: 112/529, loss: 0.003720092587172985
2023-01-23 03:55:57.638268: step: 116/529, loss: 0.00010356902930652723
2023-01-23 03:55:58.897944: step: 120/529, loss: 0.00181922921910882
2023-01-23 03:56:00.113526: step: 124/529, loss: 0.0009958266746252775
2023-01-23 03:56:01.306640: step: 128/529, loss: 0.0438106544315815
2023-01-23 03:56:02.494493: step: 132/529, loss: 0.01500854454934597
2023-01-23 03:56:03.674617: step: 136/529, loss: 0.000351142865838483
2023-01-23 03:56:04.957051: step: 140/529, loss: 0.0001565933198435232
2023-01-23 03:56:06.135099: step: 144/529, loss: 0.0006480694282799959
2023-01-23 03:56:07.345992: step: 148/529, loss: 0.0001642227143747732
2023-01-23 03:56:08.561880: step: 152/529, loss: 0.09603157639503479
2023-01-23 03:56:09.778944: step: 156/529, loss: 2.1171568732825108e-05
2023-01-23 03:56:10.979204: step: 160/529, loss: 0.883753776550293
2023-01-23 03:56:12.181717: step: 164/529, loss: 0.0009885788895189762
2023-01-23 03:56:13.403406: step: 168/529, loss: 0.0007259369012899697
2023-01-23 03:56:14.636621: step: 172/529, loss: 0.014078522101044655
2023-01-23 03:56:15.865838: step: 176/529, loss: 2.803802453854587e-05
2023-01-23 03:56:17.064530: step: 180/529, loss: 0.0028085708618164062
2023-01-23 03:56:18.222277: step: 184/529, loss: 0.0005070686456747353
2023-01-23 03:56:19.439989: step: 188/529, loss: 1.754760705807712e-05
2023-01-23 03:56:20.639045: step: 192/529, loss: 0.061084747314453125
2023-01-23 03:56:21.851850: step: 196/529, loss: 0.004200935363769531
2023-01-23 03:56:23.042052: step: 200/529, loss: 0.00029773713322356343
2023-01-23 03:56:24.239078: step: 204/529, loss: 5.2547460654750466e-05
2023-01-23 03:56:25.417912: step: 208/529, loss: 0.0001352310209767893
2023-01-23 03:56:26.631553: step: 212/529, loss: 0.0026991846971213818
2023-01-23 03:56:27.817489: step: 216/529, loss: 0.023371504619717598
2023-01-23 03:56:28.977482: step: 220/529, loss: 0.004308176226913929
2023-01-23 03:56:30.164901: step: 224/529, loss: 0.0005672455299645662
2023-01-23 03:56:31.335192: step: 228/529, loss: 0.0005071639898233116
2023-01-23 03:56:32.522878: step: 232/529, loss: 0.00012607575627043843
2023-01-23 03:56:33.687625: step: 236/529, loss: 0.0010143279796466231
2023-01-23 03:56:34.884032: step: 240/529, loss: 0.06271801143884659
2023-01-23 03:56:36.128038: step: 244/529, loss: 0.00872650183737278
2023-01-23 03:56:37.327174: step: 248/529, loss: 0.005633544642478228
2023-01-23 03:56:38.569460: step: 252/529, loss: 0.018194103613495827
2023-01-23 03:56:39.730062: step: 256/529, loss: 0.01584930345416069
2023-01-23 03:56:40.928123: step: 260/529, loss: 0.020670508965849876
2023-01-23 03:56:42.128652: step: 264/529, loss: 7.047652616165578e-05
2023-01-23 03:56:43.321687: step: 268/529, loss: 0.00018482207087799907
2023-01-23 03:56:44.566060: step: 272/529, loss: 0.00048351287841796875
2023-01-23 03:56:45.719753: step: 276/529, loss: 0.002191162435337901
2023-01-23 03:56:46.903377: step: 280/529, loss: 0.006224441807717085
2023-01-23 03:56:48.157370: step: 284/529, loss: 0.009140587411820889
2023-01-23 03:56:49.352050: step: 288/529, loss: 2.689361645025201e-05
2023-01-23 03:56:50.521966: step: 292/529, loss: 8.7738037109375e-05
2023-01-23 03:56:51.703518: step: 296/529, loss: 0.03854427486658096
2023-01-23 03:56:52.908272: step: 300/529, loss: 0.0005305290105752647
2023-01-23 03:56:54.098220: step: 304/529, loss: 0.004228019621223211
2023-01-23 03:56:55.284362: step: 308/529, loss: 0.043044187128543854
2023-01-23 03:56:56.449738: step: 312/529, loss: 9.322167170466855e-05
2023-01-23 03:56:57.631881: step: 316/529, loss: 0.013856029137969017
2023-01-23 03:56:58.846784: step: 320/529, loss: 0.0010091782314702868
2023-01-23 03:57:00.086252: step: 324/529, loss: 0.00734214810654521
2023-01-23 03:57:01.254317: step: 328/529, loss: 0.0008930206531658769
2023-01-23 03:57:02.449127: step: 332/529, loss: 0.001455593155696988
2023-01-23 03:57:03.667991: step: 336/529, loss: 0.0024827958550304174
2023-01-23 03:57:04.846073: step: 340/529, loss: 0.000335884076775983
2023-01-23 03:57:06.054468: step: 344/529, loss: 0.00793552491813898
2023-01-23 03:57:07.252052: step: 348/529, loss: 0.0026943206321448088
2023-01-23 03:57:08.441685: step: 352/529, loss: 7.2479248046875e-05
2023-01-23 03:57:09.607795: step: 356/529, loss: 0.004124355502426624
2023-01-23 03:57:10.796265: step: 360/529, loss: 0.03957557678222656
2023-01-23 03:57:11.969318: step: 364/529, loss: 0.0004838943714275956
2023-01-23 03:57:13.175868: step: 368/529, loss: 0.0059379576705396175
2023-01-23 03:57:14.463306: step: 372/529, loss: 0.052053071558475494
2023-01-23 03:57:15.641536: step: 376/529, loss: 0.00016708375187590718
2023-01-23 03:57:16.818028: step: 380/529, loss: 0.01997966691851616
2023-01-23 03:57:18.021245: step: 384/529, loss: 0.00010795592970680445
2023-01-23 03:57:19.310273: step: 388/529, loss: 0.0069217681884765625
2023-01-23 03:57:20.515199: step: 392/529, loss: 0.0005355835310183465
2023-01-23 03:57:21.700785: step: 396/529, loss: 0.03647136688232422
2023-01-23 03:57:22.872930: step: 400/529, loss: 0.033852577209472656
2023-01-23 03:57:24.070609: step: 404/529, loss: 0.00032672882662154734
2023-01-23 03:57:25.235990: step: 408/529, loss: 0.003079724498093128
2023-01-23 03:57:26.431030: step: 412/529, loss: 0.00234222412109375
2023-01-23 03:57:27.634695: step: 416/529, loss: 0.04577350988984108
2023-01-23 03:57:28.879378: step: 420/529, loss: 0.010225106030702591
2023-01-23 03:57:30.093290: step: 424/529, loss: 0.00011091232590842992
2023-01-23 03:57:31.278340: step: 428/529, loss: 0.0007096290355548263
2023-01-23 03:57:32.453781: step: 432/529, loss: 0.0010703086154535413
2023-01-23 03:57:33.654344: step: 436/529, loss: 0.0004926681285724044
2023-01-23 03:57:34.840563: step: 440/529, loss: 8.869171870173886e-05
2023-01-23 03:57:36.057308: step: 444/529, loss: 0.013087654486298561
2023-01-23 03:57:37.259397: step: 448/529, loss: 3.2901763916015625e-05
2023-01-23 03:57:38.420407: step: 452/529, loss: 0.04663858935236931
2023-01-23 03:57:39.629136: step: 456/529, loss: 0.0007803440093994141
2023-01-23 03:57:40.861044: step: 460/529, loss: 0.000606155430432409
2023-01-23 03:57:42.086260: step: 464/529, loss: 0.004592132288962603
2023-01-23 03:57:43.268372: step: 468/529, loss: 0.0033407211303710938
2023-01-23 03:57:44.486740: step: 472/529, loss: 0.0011446953285485506
2023-01-23 03:57:45.711979: step: 476/529, loss: 0.001308441162109375
2023-01-23 03:57:46.921375: step: 480/529, loss: 0.00011310577974654734
2023-01-23 03:57:48.104600: step: 484/529, loss: 0.0013108253479003906
2023-01-23 03:57:49.339473: step: 488/529, loss: -4.57763690064894e-06
2023-01-23 03:57:50.510632: step: 492/529, loss: 0.0006173133733682334
2023-01-23 03:57:51.725959: step: 496/529, loss: 2.527237120375503e-05
2023-01-23 03:57:52.911806: step: 500/529, loss: 6.866455078125e-05
2023-01-23 03:57:54.144231: step: 504/529, loss: 0.0836639404296875
2023-01-23 03:57:55.348606: step: 508/529, loss: 0.0005289078108035028
2023-01-23 03:57:56.565400: step: 512/529, loss: 0.016691779717803
2023-01-23 03:57:57.792309: step: 516/529, loss: 0.04110231623053551
2023-01-23 03:57:59.002254: step: 520/529, loss: -2.0599363779183477e-05
2023-01-23 03:58:00.192128: step: 524/529, loss: 0.00023736954608466476
2023-01-23 03:58:01.389707: step: 528/529, loss: 0.0008762360084801912
2023-01-23 03:58:02.567998: step: 532/529, loss: 0.000423431396484375
2023-01-23 03:58:03.756370: step: 536/529, loss: 0.054270461201667786
2023-01-23 03:58:04.954077: step: 540/529, loss: 0.08389253914356232
2023-01-23 03:58:06.136306: step: 544/529, loss: 0.03192710876464844
2023-01-23 03:58:07.412215: step: 548/529, loss: 0.005930709652602673
2023-01-23 03:58:08.578098: step: 552/529, loss: 4.901886131847277e-05
2023-01-23 03:58:09.752701: step: 556/529, loss: 0.03146667405962944
2023-01-23 03:58:10.949974: step: 560/529, loss: 3.814697265625e-05
2023-01-23 03:58:12.129185: step: 564/529, loss: 0.043440911918878555
2023-01-23 03:58:13.346331: step: 568/529, loss: 0.028762057423591614
2023-01-23 03:58:14.557841: step: 572/529, loss: 0.0034703253768384457
2023-01-23 03:58:15.771477: step: 576/529, loss: 0.01987428590655327
2023-01-23 03:58:17.014906: step: 580/529, loss: 0.04110870510339737
2023-01-23 03:58:18.191250: step: 584/529, loss: 0.026866436004638672
2023-01-23 03:58:19.382318: step: 588/529, loss: 0.001018524169921875
2023-01-23 03:58:20.610066: step: 592/529, loss: 0.017357636243104935
2023-01-23 03:58:21.754767: step: 596/529, loss: 0.00027208327082917094
2023-01-23 03:58:22.989100: step: 600/529, loss: 0.05283012241125107
2023-01-23 03:58:24.166269: step: 604/529, loss: 0.026448631659150124
2023-01-23 03:58:25.315329: step: 608/529, loss: 0.0029283524490892887
2023-01-23 03:58:26.532339: step: 612/529, loss: 0.024448204785585403
2023-01-23 03:58:27.762161: step: 616/529, loss: 2.174377368646674e-05
2023-01-23 03:58:28.969079: step: 620/529, loss: 0.08898010104894638
2023-01-23 03:58:30.195714: step: 624/529, loss: 0.00012140273611294106
2023-01-23 03:58:31.396988: step: 628/529, loss: 0.0007497787592001259
2023-01-23 03:58:32.585330: step: 632/529, loss: 0.0002910614130087197
2023-01-23 03:58:33.787826: step: 636/529, loss: 0.0003046512429136783
2023-01-23 03:58:34.948276: step: 640/529, loss: 0.006114721763879061
2023-01-23 03:58:36.152740: step: 644/529, loss: 0.0002195358247263357
2023-01-23 03:58:37.326441: step: 648/529, loss: 7.152557373046875e-05
2023-01-23 03:58:38.490488: step: 652/529, loss: 0.49724096059799194
2023-01-23 03:58:39.690495: step: 656/529, loss: 0.0011238098377361894
2023-01-23 03:58:40.857347: step: 660/529, loss: 0.005605077836662531
2023-01-23 03:58:42.073626: step: 664/529, loss: 0.008432770147919655
2023-01-23 03:58:43.261534: step: 668/529, loss: 0.0006137847667559981
2023-01-23 03:58:44.492871: step: 672/529, loss: 0.001155090401880443
2023-01-23 03:58:45.708903: step: 676/529, loss: 0.11891335994005203
2023-01-23 03:58:46.904344: step: 680/529, loss: 0.0037322998978197575
2023-01-23 03:58:48.075502: step: 684/529, loss: 0.0049332622438669205
2023-01-23 03:58:49.292775: step: 688/529, loss: 0.036225512623786926
2023-01-23 03:58:50.497836: step: 692/529, loss: 0.0023182868026196957
2023-01-23 03:58:51.706334: step: 696/529, loss: 0.00010499954805709422
2023-01-23 03:58:52.896795: step: 700/529, loss: 0.01994462125003338
2023-01-23 03:58:54.102538: step: 704/529, loss: 0.01813526265323162
2023-01-23 03:58:55.378971: step: 708/529, loss: 0.007596397772431374
2023-01-23 03:58:56.597925: step: 712/529, loss: 0.03473644703626633
2023-01-23 03:58:57.748355: step: 716/529, loss: 0.0009654999012127519
2023-01-23 03:58:58.945415: step: 720/529, loss: 0.0001998901425395161
2023-01-23 03:59:00.090332: step: 724/529, loss: 2.3746490114717744e-05
2023-01-23 03:59:01.263584: step: 728/529, loss: -1.010894811770413e-05
2023-01-23 03:59:02.437092: step: 732/529, loss: 0.00028247834416106343
2023-01-23 03:59:03.658683: step: 736/529, loss: 0.009356784634292126
2023-01-23 03:59:04.846717: step: 740/529, loss: 0.004090213682502508
2023-01-23 03:59:06.063488: step: 744/529, loss: 0.0009544372442178428
2023-01-23 03:59:07.212485: step: 748/529, loss: 1.3351441339182202e-06
2023-01-23 03:59:08.443495: step: 752/529, loss: 0.081451416015625
2023-01-23 03:59:09.610030: step: 756/529, loss: 0.005661583039909601
2023-01-23 03:59:10.816464: step: 760/529, loss: 0.3019602596759796
2023-01-23 03:59:12.045456: step: 764/529, loss: 3.9386748539982364e-05
2023-01-23 03:59:13.196201: step: 768/529, loss: 0.00024328232393600047
2023-01-23 03:59:14.385958: step: 772/529, loss: 0.0945829451084137
2023-01-23 03:59:15.602332: step: 776/529, loss: 0.0008716583251953125
2023-01-23 03:59:16.781642: step: 780/529, loss: 0.00021438598923850805
2023-01-23 03:59:17.966965: step: 784/529, loss: 0.0028961182106286287
2023-01-23 03:59:19.193555: step: 788/529, loss: 9.50813337112777e-05
2023-01-23 03:59:20.366385: step: 792/529, loss: -5.7220458984375e-06
2023-01-23 03:59:21.574347: step: 796/529, loss: 0.00040807726327329874
2023-01-23 03:59:22.767152: step: 800/529, loss: 0.000682449375744909
2023-01-23 03:59:23.977863: step: 804/529, loss: 8.75473051564768e-05
2023-01-23 03:59:25.177935: step: 808/529, loss: 0.02306804619729519
2023-01-23 03:59:26.313119: step: 812/529, loss: 0.0014967918395996094
2023-01-23 03:59:27.492287: step: 816/529, loss: 2.6702882678364404e-05
2023-01-23 03:59:28.662254: step: 820/529, loss: 7.43865984986769e-06
2023-01-23 03:59:29.833256: step: 824/529, loss: 0.0003253698523622006
2023-01-23 03:59:31.015959: step: 828/529, loss: 0.003597450442612171
2023-01-23 03:59:32.226035: step: 832/529, loss: 0.00011729002289939672
2023-01-23 03:59:33.385895: step: 836/529, loss: 1.773834264895413e-05
2023-01-23 03:59:34.608018: step: 840/529, loss: 0.0001504898100392893
2023-01-23 03:59:35.832260: step: 844/529, loss: 0.0023234367836266756
2023-01-23 03:59:37.060408: step: 848/529, loss: 0.004158973693847656
2023-01-23 03:59:38.284613: step: 852/529, loss: 0.05565262213349342
2023-01-23 03:59:39.427261: step: 856/529, loss: 0.0014417648781090975
2023-01-23 03:59:40.645987: step: 860/529, loss: 0.010286903008818626
2023-01-23 03:59:41.842572: step: 864/529, loss: 0.004706859588623047
2023-01-23 03:59:43.038128: step: 868/529, loss: 0.00017786027456168085
2023-01-23 03:59:44.218058: step: 872/529, loss: 0.01874399185180664
2023-01-23 03:59:45.416649: step: 876/529, loss: 0.04812603071331978
2023-01-23 03:59:46.606879: step: 880/529, loss: 2.1600722902803682e-05
2023-01-23 03:59:47.796135: step: 884/529, loss: 0.003119087079539895
2023-01-23 03:59:49.057948: step: 888/529, loss: 0.005294895265251398
2023-01-23 03:59:50.245177: step: 892/529, loss: 0.004654693882912397
2023-01-23 03:59:51.422601: step: 896/529, loss: 0.00036237240419723094
2023-01-23 03:59:52.583368: step: 900/529, loss: 0.003823757404461503
2023-01-23 03:59:53.800825: step: 904/529, loss: 1.3732910701946821e-05
2023-01-23 03:59:54.994611: step: 908/529, loss: 0.09959020465612411
2023-01-23 03:59:56.179011: step: 912/529, loss: 7.43865984986769e-06
2023-01-23 03:59:57.361347: step: 916/529, loss: 0.0012193679576739669
2023-01-23 03:59:58.518910: step: 920/529, loss: 0.004172801971435547
2023-01-23 03:59:59.716683: step: 924/529, loss: 0.03820228576660156
2023-01-23 04:00:00.914842: step: 928/529, loss: 0.0003452301025390625
2023-01-23 04:00:02.055533: step: 932/529, loss: 0.0024466991890221834
2023-01-23 04:00:03.237599: step: 936/529, loss: 0.062316037714481354
2023-01-23 04:00:04.420870: step: 940/529, loss: 0.0018846511375159025
2023-01-23 04:00:05.621392: step: 944/529, loss: 0.006036949343979359
2023-01-23 04:00:06.873465: step: 948/529, loss: 0.03917961195111275
2023-01-23 04:00:08.078163: step: 952/529, loss: 0.009608173742890358
2023-01-23 04:00:09.260308: step: 956/529, loss: 0.0013042449718341231
2023-01-23 04:00:10.459880: step: 960/529, loss: 0.00272541050799191
2023-01-23 04:00:11.614027: step: 964/529, loss: 0.006847381591796875
2023-01-23 04:00:12.804634: step: 968/529, loss: 0.000492954277433455
2023-01-23 04:00:14.028818: step: 972/529, loss: 0.006552505772560835
2023-01-23 04:00:15.280564: step: 976/529, loss: 0.0002483367861714214
2023-01-23 04:00:16.471700: step: 980/529, loss: 0.006560325622558594
2023-01-23 04:00:17.728150: step: 984/529, loss: -4.76837158203125e-06
2023-01-23 04:00:18.958963: step: 988/529, loss: 0.0001720428408589214
2023-01-23 04:00:20.170650: step: 992/529, loss: 0.014256476424634457
2023-01-23 04:00:21.354519: step: 996/529, loss: 4.081726001459174e-05
2023-01-23 04:00:22.527108: step: 1000/529, loss: 0.0009751320467330515
2023-01-23 04:00:23.775122: step: 1004/529, loss: 0.00298061384819448
2023-01-23 04:00:25.009553: step: 1008/529, loss: 0.0008645057678222656
2023-01-23 04:00:26.180731: step: 1012/529, loss: 0.013348006643354893
2023-01-23 04:00:27.405999: step: 1016/529, loss: 0.022020913660526276
2023-01-23 04:00:28.603651: step: 1020/529, loss: 0.004765987396240234
2023-01-23 04:00:29.783788: step: 1024/529, loss: 0.6906064748764038
2023-01-23 04:00:30.957473: step: 1028/529, loss: 0.00296707171946764
2023-01-23 04:00:32.155418: step: 1032/529, loss: 0.026301002129912376
2023-01-23 04:00:33.331677: step: 1036/529, loss: 0.05818118900060654
2023-01-23 04:00:34.482746: step: 1040/529, loss: 1.9454957509879023e-05
2023-01-23 04:00:35.672042: step: 1044/529, loss: 0.01805725134909153
2023-01-23 04:00:36.908730: step: 1048/529, loss: 0.023810388520359993
2023-01-23 04:00:38.112304: step: 1052/529, loss: 0.009112549014389515
2023-01-23 04:00:39.310880: step: 1056/529, loss: 3.337860107421875e-05
2023-01-23 04:00:40.520773: step: 1060/529, loss: 0.0013909341068938375
2023-01-23 04:00:41.691831: step: 1064/529, loss: 0.0026483535766601562
2023-01-23 04:00:42.879942: step: 1068/529, loss: 0.0010196685325354338
2023-01-23 04:00:44.089196: step: 1072/529, loss: 0.0009142875787802041
2023-01-23 04:00:45.321230: step: 1076/529, loss: 0.26565074920654297
2023-01-23 04:00:46.605778: step: 1080/529, loss: 0.01162881962954998
2023-01-23 04:00:47.780624: step: 1084/529, loss: 0.0004436492745298892
2023-01-23 04:00:49.015781: step: 1088/529, loss: 0.0006002426380291581
2023-01-23 04:00:50.198406: step: 1092/529, loss: 0.21182385087013245
2023-01-23 04:00:51.424440: step: 1096/529, loss: 0.024146651849150658
2023-01-23 04:00:52.625341: step: 1100/529, loss: 0.0009248733404092491
2023-01-23 04:00:53.796283: step: 1104/529, loss: 0.015993213281035423
2023-01-23 04:00:55.011354: step: 1108/529, loss: 0.0316954143345356
2023-01-23 04:00:56.183302: step: 1112/529, loss: 0.008948231115937233
2023-01-23 04:00:57.378390: step: 1116/529, loss: 0.0018062591552734375
2023-01-23 04:00:58.564282: step: 1120/529, loss: 0.012559986673295498
2023-01-23 04:00:59.729826: step: 1124/529, loss: 0.041483186185359955
2023-01-23 04:01:00.894128: step: 1128/529, loss: 0.19248619675636292
2023-01-23 04:01:02.105408: step: 1132/529, loss: 0.0011848449939861894
2023-01-23 04:01:03.315374: step: 1136/529, loss: 0.0025873184204101562
2023-01-23 04:01:04.532111: step: 1140/529, loss: 0.0001985549897653982
2023-01-23 04:01:05.752578: step: 1144/529, loss: 3.376007225597277e-05
2023-01-23 04:01:06.968161: step: 1148/529, loss: 0.001006698701530695
2023-01-23 04:01:08.170887: step: 1152/529, loss: 0.0023355484008789062
2023-01-23 04:01:09.341654: step: 1156/529, loss: 0.00019531250291038305
2023-01-23 04:01:10.495869: step: 1160/529, loss: 0.0009933472611010075
2023-01-23 04:01:11.699856: step: 1164/529, loss: 0.000141143798828125
2023-01-23 04:01:12.888279: step: 1168/529, loss: 0.007078933529555798
2023-01-23 04:01:14.101085: step: 1172/529, loss: 0.015691757202148438
2023-01-23 04:01:15.298818: step: 1176/529, loss: 0.004620718769729137
2023-01-23 04:01:16.485510: step: 1180/529, loss: 0.00032892229501158
2023-01-23 04:01:17.664133: step: 1184/529, loss: 0.008436775766313076
2023-01-23 04:01:18.862195: step: 1188/529, loss: 0.1825597882270813
2023-01-23 04:01:20.073028: step: 1192/529, loss: 0.006682968232780695
2023-01-23 04:01:21.280497: step: 1196/529, loss: 0.0018310546875
2023-01-23 04:01:22.459543: step: 1200/529, loss: 0.0028045654762536287
2023-01-23 04:01:23.649750: step: 1204/529, loss: 0.04111327975988388
2023-01-23 04:01:24.831490: step: 1208/529, loss: 0.007266044616699219
2023-01-23 04:01:25.970546: step: 1212/529, loss: 0.00042110084905289114
2023-01-23 04:01:27.136931: step: 1216/529, loss: 0.023906517773866653
2023-01-23 04:01:28.333573: step: 1220/529, loss: 0.026366423815488815
2023-01-23 04:01:29.539838: step: 1224/529, loss: 0.06181488186120987
2023-01-23 04:01:30.778451: step: 1228/529, loss: 0.004440403077751398
2023-01-23 04:01:31.983011: step: 1232/529, loss: 0.25809335708618164
2023-01-23 04:01:33.234526: step: 1236/529, loss: 0.00036640168400481343
2023-01-23 04:01:34.452393: step: 1240/529, loss: 0.02675599977374077
2023-01-23 04:01:35.658281: step: 1244/529, loss: 0.044527627527713776
2023-01-23 04:01:36.848513: step: 1248/529, loss: 0.00044384002103470266
2023-01-23 04:01:38.060452: step: 1252/529, loss: 0.0016265868907794356
2023-01-23 04:01:39.261693: step: 1256/529, loss: 0.0017253875266760588
2023-01-23 04:01:40.430499: step: 1260/529, loss: 0.0009447097545489669
2023-01-23 04:01:41.602040: step: 1264/529, loss: 0.0037884714547544718
2023-01-23 04:01:42.796628: step: 1268/529, loss: 0.0015060901641845703
2023-01-23 04:01:44.032833: step: 1272/529, loss: 0.0515931136906147
2023-01-23 04:01:45.198164: step: 1276/529, loss: 7.62939453125e-06
2023-01-23 04:01:46.384174: step: 1280/529, loss: 0.00015697479830123484
2023-01-23 04:01:47.589851: step: 1284/529, loss: 0.0009894848335534334
2023-01-23 04:01:48.818468: step: 1288/529, loss: 0.0008552551735192537
2023-01-23 04:01:50.056541: step: 1292/529, loss: 0.001204204629175365
2023-01-23 04:01:51.268352: step: 1296/529, loss: 0.009193611331284046
2023-01-23 04:01:52.483188: step: 1300/529, loss: 0.0029575349763035774
2023-01-23 04:01:53.664625: step: 1304/529, loss: 2.307891918462701e-05
2023-01-23 04:01:54.847326: step: 1308/529, loss: 0.0016100883949548006
2023-01-23 04:01:56.045071: step: 1312/529, loss: 0.0003833770751953125
2023-01-23 04:01:57.275337: step: 1316/529, loss: 0.00750656146556139
2023-01-23 04:01:58.472094: step: 1320/529, loss: 0.11062035709619522
2023-01-23 04:01:59.692467: step: 1324/529, loss: 0.0009062409517355263
2023-01-23 04:02:00.912187: step: 1328/529, loss: 9.603500802768394e-05
2023-01-23 04:02:02.117555: step: 1332/529, loss: 0.01048889197409153
2023-01-23 04:02:03.326926: step: 1336/529, loss: 0.0009457588312216103
2023-01-23 04:02:04.551968: step: 1340/529, loss: 0.013356066308915615
2023-01-23 04:02:05.750060: step: 1344/529, loss: 0.006854057312011719
2023-01-23 04:02:06.959568: step: 1348/529, loss: 6.313324411166832e-05
2023-01-23 04:02:08.165078: step: 1352/529, loss: 0.0018568038940429688
2023-01-23 04:02:09.363973: step: 1356/529, loss: 0.0003631591680459678
2023-01-23 04:02:10.554952: step: 1360/529, loss: 0.004102802369743586
2023-01-23 04:02:11.713939: step: 1364/529, loss: 0.00030736924964003265
2023-01-23 04:02:12.902776: step: 1368/529, loss: 0.03762407600879669
2023-01-23 04:02:14.105359: step: 1372/529, loss: 0.009470652788877487
2023-01-23 04:02:15.293999: step: 1376/529, loss: 0.0012943744659423828
2023-01-23 04:02:16.512994: step: 1380/529, loss: 0.017116928473114967
2023-01-23 04:02:17.701379: step: 1384/529, loss: 0.0026426315307617188
2023-01-23 04:02:18.942444: step: 1388/529, loss: 0.009540367871522903
2023-01-23 04:02:20.120362: step: 1392/529, loss: 0.0001813888520700857
2023-01-23 04:02:21.308545: step: 1396/529, loss: 0.010789012536406517
2023-01-23 04:02:22.545774: step: 1400/529, loss: 0.04092216491699219
2023-01-23 04:02:23.767067: step: 1404/529, loss: 0.003507232526317239
2023-01-23 04:02:24.966052: step: 1408/529, loss: 0.03182784095406532
2023-01-23 04:02:26.234545: step: 1412/529, loss: 0.028965570032596588
2023-01-23 04:02:27.437657: step: 1416/529, loss: 0.013645696453750134
2023-01-23 04:02:28.603032: step: 1420/529, loss: 6.752014451194555e-05
2023-01-23 04:02:29.811545: step: 1424/529, loss: 0.04342842102050781
2023-01-23 04:02:31.028888: step: 1428/529, loss: 0.0003849029599223286
2023-01-23 04:02:32.216210: step: 1432/529, loss: 0.041029881685972214
2023-01-23 04:02:33.437901: step: 1436/529, loss: 0.0007427216041833162
2023-01-23 04:02:34.612642: step: 1440/529, loss: 0.00022239684767555445
2023-01-23 04:02:35.792172: step: 1444/529, loss: 5.9413909184513614e-05
2023-01-23 04:02:36.975437: step: 1448/529, loss: 0.0018434524536132812
2023-01-23 04:02:38.152442: step: 1452/529, loss: 0.0016441346378996968
2023-01-23 04:02:39.319568: step: 1456/529, loss: 0.020009947940707207
2023-01-23 04:02:40.544446: step: 1460/529, loss: 2.4223329091910273e-05
2023-01-23 04:02:41.746691: step: 1464/529, loss: 4.2724612285383046e-05
2023-01-23 04:02:42.933228: step: 1468/529, loss: 0.00018644332885742188
2023-01-23 04:02:44.114012: step: 1472/529, loss: 5.760193016612902e-05
2023-01-23 04:02:45.308993: step: 1476/529, loss: 0.1125604659318924
2023-01-23 04:02:46.507906: step: 1480/529, loss: 0.005111026577651501
2023-01-23 04:02:47.766604: step: 1484/529, loss: 0.0013748168712481856
2023-01-23 04:02:48.951724: step: 1488/529, loss: 0.00010166168067371473
2023-01-23 04:02:50.172834: step: 1492/529, loss: 0.00165386195294559
2023-01-23 04:02:51.333275: step: 1496/529, loss: 0.06788130104541779
2023-01-23 04:02:52.522709: step: 1500/529, loss: 0.00046043400652706623
2023-01-23 04:02:53.704843: step: 1504/529, loss: 5.364418029785156e-05
2023-01-23 04:02:54.873058: step: 1508/529, loss: 0.002368831541389227
2023-01-23 04:02:56.083174: step: 1512/529, loss: 0.0002368926943745464
2023-01-23 04:02:57.301556: step: 1516/529, loss: 1.2254715329618193e-05
2023-01-23 04:02:58.515066: step: 1520/529, loss: 0.03748512640595436
2023-01-23 04:02:59.692772: step: 1524/529, loss: 5.15937790623866e-05
2023-01-23 04:03:00.897359: step: 1528/529, loss: 0.03810310363769531
2023-01-23 04:03:02.139910: step: 1532/529, loss: 0.0005926132434979081
2023-01-23 04:03:03.325044: step: 1536/529, loss: 0.0004899025079794228
2023-01-23 04:03:04.524962: step: 1540/529, loss: 0.03801784664392471
2023-01-23 04:03:05.740056: step: 1544/529, loss: 7.82012939453125e-05
2023-01-23 04:03:06.963990: step: 1548/529, loss: 0.005653571803122759
2023-01-23 04:03:08.179007: step: 1552/529, loss: 4.7159195673884824e-05
2023-01-23 04:03:09.404101: step: 1556/529, loss: 0.0006330489995889366
2023-01-23 04:03:10.615479: step: 1560/529, loss: 0.05439510568976402
2023-01-23 04:03:11.817764: step: 1564/529, loss: 3.62396240234375e-05
2023-01-23 04:03:13.004845: step: 1568/529, loss: 0.0010322571033611894
2023-01-23 04:03:14.218131: step: 1572/529, loss: 0.0022098540794104338
2023-01-23 04:03:15.405229: step: 1576/529, loss: 0.0029603957664221525
2023-01-23 04:03:16.597058: step: 1580/529, loss: 0.008899307809770107
2023-01-23 04:03:17.810255: step: 1584/529, loss: 0.004836654290556908
2023-01-23 04:03:18.957762: step: 1588/529, loss: 0.0004618644597940147
2023-01-23 04:03:20.175195: step: 1592/529, loss: 0.0250917449593544
2023-01-23 04:03:21.351287: step: 1596/529, loss: 0.03251810371875763
2023-01-23 04:03:22.546694: step: 1600/529, loss: 0.0005973815568722785
2023-01-23 04:03:23.787217: step: 1604/529, loss: 0.015264606103301048
2023-01-23 04:03:24.995339: step: 1608/529, loss: 0.006385994143784046
2023-01-23 04:03:26.216302: step: 1612/529, loss: 0.04300248995423317
2023-01-23 04:03:27.408003: step: 1616/529, loss: 0.00016651154146529734
2023-01-23 04:03:28.589346: step: 1620/529, loss: 0.00012578963651321828
2023-01-23 04:03:29.765515: step: 1624/529, loss: 0.0005056381342001259
2023-01-23 04:03:30.975873: step: 1628/529, loss: 0.09431781619787216
2023-01-23 04:03:32.155192: step: 1632/529, loss: 0.005275917239487171
2023-01-23 04:03:33.339859: step: 1636/529, loss: 0.0025323869194835424
2023-01-23 04:03:34.554178: step: 1640/529, loss: 0.011876821517944336
2023-01-23 04:03:35.760800: step: 1644/529, loss: 0.00017843247042037547
2023-01-23 04:03:36.993232: step: 1648/529, loss: 0.0916026160120964
2023-01-23 04:03:38.206013: step: 1652/529, loss: 0.01324691902846098
2023-01-23 04:03:39.400215: step: 1656/529, loss: 0.0011009216541424394
2023-01-23 04:03:40.580467: step: 1660/529, loss: 0.0004036426544189453
2023-01-23 04:03:41.782189: step: 1664/529, loss: 0.0001712799130473286
2023-01-23 04:03:42.977293: step: 1668/529, loss: 0.002393055008724332
2023-01-23 04:03:44.158618: step: 1672/529, loss: 0.023511027917265892
2023-01-23 04:03:45.348445: step: 1676/529, loss: 0.0009181976784020662
2023-01-23 04:03:46.510588: step: 1680/529, loss: 1.4400482541532256e-05
2023-01-23 04:03:47.723287: step: 1684/529, loss: 0.005416488740593195
2023-01-23 04:03:48.926300: step: 1688/529, loss: 0.00471992464736104
2023-01-23 04:03:50.145430: step: 1692/529, loss: 2.4032595320022665e-05
2023-01-23 04:03:51.349443: step: 1696/529, loss: 0.11666784435510635
2023-01-23 04:03:52.553379: step: 1700/529, loss: 0.002605962799862027
2023-01-23 04:03:53.742366: step: 1704/529, loss: 0.004446220584213734
2023-01-23 04:03:54.933055: step: 1708/529, loss: 0.006130027584731579
2023-01-23 04:03:56.117641: step: 1712/529, loss: 0.0010610581375658512
2023-01-23 04:03:57.314390: step: 1716/529, loss: 0.0014236450660973787
2023-01-23 04:03:58.499833: step: 1720/529, loss: 0.0008883953560143709
2023-01-23 04:03:59.700244: step: 1724/529, loss: 0.0034356117248535156
2023-01-23 04:04:00.883279: step: 1728/529, loss: 0.0008444786071777344
2023-01-23 04:04:02.151170: step: 1732/529, loss: 0.005627060309052467
2023-01-23 04:04:03.344752: step: 1736/529, loss: 8.02993745310232e-05
2023-01-23 04:04:04.529919: step: 1740/529, loss: 8.39233416627394e-06
2023-01-23 04:04:05.729374: step: 1744/529, loss: 0.001068210694938898
2023-01-23 04:04:06.917389: step: 1748/529, loss: 0.013585949316620827
2023-01-23 04:04:08.130836: step: 1752/529, loss: 0.0006834983360022306
2023-01-23 04:04:09.302469: step: 1756/529, loss: 0.011636734008789062
2023-01-23 04:04:10.525132: step: 1760/529, loss: 2.5081633793888614e-05
2023-01-23 04:04:11.694324: step: 1764/529, loss: 0.0002938270627055317
2023-01-23 04:04:12.884247: step: 1768/529, loss: 0.00014762878709007055
2023-01-23 04:04:14.045513: step: 1772/529, loss: 0.003143119625747204
2023-01-23 04:04:15.196049: step: 1776/529, loss: 0.0004108429129701108
2023-01-23 04:04:16.377100: step: 1780/529, loss: 0.009210300631821156
2023-01-23 04:04:17.567145: step: 1784/529, loss: 0.005858707707375288
2023-01-23 04:04:18.742770: step: 1788/529, loss: 0.005080032162368298
2023-01-23 04:04:19.969795: step: 1792/529, loss: 0.007211446762084961
2023-01-23 04:04:21.172962: step: 1796/529, loss: 0.0016631126636639237
2023-01-23 04:04:22.357712: step: 1800/529, loss: 0.00011739730689441785
2023-01-23 04:04:23.568988: step: 1804/529, loss: 0.0029680251609534025
2023-01-23 04:04:24.776242: step: 1808/529, loss: 0.04195919260382652
2023-01-23 04:04:26.020301: step: 1812/529, loss: 0.0007523060194216669
2023-01-23 04:04:27.201563: step: 1816/529, loss: 0.00557632464915514
2023-01-23 04:04:28.406511: step: 1820/529, loss: 0.0006479262956418097
2023-01-23 04:04:29.619769: step: 1824/529, loss: 0.0002773284795694053
2023-01-23 04:04:30.782249: step: 1828/529, loss: 0.2148026078939438
2023-01-23 04:04:31.945507: step: 1832/529, loss: 0.00019674301438499242
2023-01-23 04:04:33.142072: step: 1836/529, loss: 0.00010042190842796117
2023-01-23 04:04:34.336185: step: 1840/529, loss: 0.0002117156982421875
2023-01-23 04:04:35.518873: step: 1844/529, loss: 0.0005591392400674522
2023-01-23 04:04:36.683648: step: 1848/529, loss: 0.00020494460477493703
2023-01-23 04:04:37.826804: step: 1852/529, loss: 0.019325638189911842
2023-01-23 04:04:39.032374: step: 1856/529, loss: 0.004228496924042702
2023-01-23 04:04:40.221503: step: 1860/529, loss: 0.00027484894962981343
2023-01-23 04:04:41.406733: step: 1864/529, loss: 0.0004433155118022114
2023-01-23 04:04:42.594335: step: 1868/529, loss: 0.01247315388172865
2023-01-23 04:04:43.778945: step: 1872/529, loss: 0.0008173942333087325
2023-01-23 04:04:44.951491: step: 1876/529, loss: 0.020439432933926582
2023-01-23 04:04:46.137470: step: 1880/529, loss: 0.00034008026705123484
2023-01-23 04:04:47.332690: step: 1884/529, loss: 0.00028285980806685984
2023-01-23 04:04:48.563942: step: 1888/529, loss: 0.0009370804182253778
2023-01-23 04:04:49.780070: step: 1892/529, loss: 0.03917722776532173
2023-01-23 04:04:50.989725: step: 1896/529, loss: 0.0004302978341002017
2023-01-23 04:04:52.229399: step: 1900/529, loss: 0.00016093255544546992
2023-01-23 04:04:53.403772: step: 1904/529, loss: 0.0004818916495423764
2023-01-23 04:04:54.622604: step: 1908/529, loss: 4.615783836925402e-05
2023-01-23 04:04:55.837176: step: 1912/529, loss: 0.004528045654296875
2023-01-23 04:04:57.068798: step: 1916/529, loss: 0.0008831024169921875
2023-01-23 04:04:58.228440: step: 1920/529, loss: 0.001818323158659041
2023-01-23 04:04:59.472057: step: 1924/529, loss: 7.02858014847152e-05
2023-01-23 04:05:00.701249: step: 1928/529, loss: 0.00012321471876930445
2023-01-23 04:05:01.943288: step: 1932/529, loss: 0.003964233677834272
2023-01-23 04:05:03.107294: step: 1936/529, loss: 0.0038354399148374796
2023-01-23 04:05:04.277638: step: 1940/529, loss: 0.0005627631908282638
2023-01-23 04:05:05.468832: step: 1944/529, loss: 0.00045032502384856343
2023-01-23 04:05:06.665152: step: 1948/529, loss: 2.155303991457913e-05
2023-01-23 04:05:07.875623: step: 1952/529, loss: 0.00028438569279387593
2023-01-23 04:05:09.162021: step: 1956/529, loss: 0.005705928895622492
2023-01-23 04:05:10.360139: step: 1960/529, loss: 0.0015460015274584293
2023-01-23 04:05:11.545179: step: 1964/529, loss: 0.01661682315170765
2023-01-23 04:05:12.817722: step: 1968/529, loss: 0.08536114543676376
2023-01-23 04:05:13.987792: step: 1972/529, loss: 0.0005023956764489412
2023-01-23 04:05:15.170258: step: 1976/529, loss: 0.0014404297107830644
2023-01-23 04:05:16.325144: step: 1980/529, loss: 0.003703594207763672
2023-01-23 04:05:17.525407: step: 1984/529, loss: 0.004171181004494429
2023-01-23 04:05:18.737532: step: 1988/529, loss: 0.005911064334213734
2023-01-23 04:05:19.937769: step: 1992/529, loss: 0.01422643568366766
2023-01-23 04:05:21.119673: step: 1996/529, loss: 0.03371906280517578
2023-01-23 04:05:22.320755: step: 2000/529, loss: 0.00043234825716353953
2023-01-23 04:05:23.524762: step: 2004/529, loss: 1.602172778802924e-05
2023-01-23 04:05:24.735359: step: 2008/529, loss: 1.0490421118447557e-06
2023-01-23 04:05:25.908663: step: 2012/529, loss: 8.335113670909777e-05
2023-01-23 04:05:27.091732: step: 2016/529, loss: 0.00013484954251907766
2023-01-23 04:05:28.299745: step: 2020/529, loss: 0.007437038701027632
2023-01-23 04:05:29.466795: step: 2024/529, loss: 0.0023869038559496403
2023-01-23 04:05:30.674619: step: 2028/529, loss: 0.04378543049097061
2023-01-23 04:05:31.887391: step: 2032/529, loss: 0.0057586668990552425
2023-01-23 04:05:33.111489: step: 2036/529, loss: 0.010715675540268421
2023-01-23 04:05:34.307709: step: 2040/529, loss: 0.0005029678577557206
2023-01-23 04:05:35.489752: step: 2044/529, loss: 0.004349899478256702
2023-01-23 04:05:36.682001: step: 2048/529, loss: 4.625320343620842e-06
2023-01-23 04:05:37.866714: step: 2052/529, loss: 0.0016422271728515625
2023-01-23 04:05:39.063399: step: 2056/529, loss: 3.24249267578125e-05
2023-01-23 04:05:40.270153: step: 2060/529, loss: 0.003667163662612438
2023-01-23 04:05:41.502609: step: 2064/529, loss: 5.664825584972277e-05
2023-01-23 04:05:42.727146: step: 2068/529, loss: 1.8215179807157256e-05
2023-01-23 04:05:43.919161: step: 2072/529, loss: 0.00015563966007903218
2023-01-23 04:05:45.103320: step: 2076/529, loss: 0.0001848220854299143
2023-01-23 04:05:46.341366: step: 2080/529, loss: 0.03695087507367134
2023-01-23 04:05:47.557535: step: 2084/529, loss: 3.490447852527723e-05
2023-01-23 04:05:48.788769: step: 2088/529, loss: 0.007520962040871382
2023-01-23 04:05:49.958089: step: 2092/529, loss: 0.00028758050757460296
2023-01-23 04:05:51.160550: step: 2096/529, loss: 0.00033397675724700093
2023-01-23 04:05:52.348826: step: 2100/529, loss: 3.390312485862523e-05
2023-01-23 04:05:53.504908: step: 2104/529, loss: 0.00029048920259810984
2023-01-23 04:05:54.771947: step: 2108/529, loss: 0.006049156654626131
2023-01-23 04:05:55.956395: step: 2112/529, loss: 0.019324827939271927
2023-01-23 04:05:57.173661: step: 2116/529, loss: 0.023595044389367104
==================================================
Loss: 0.017
--------------------
Dev: {'event': {'p': 0.5989847715736041, 'r': 0.7856191744340879, 'f1': 0.6797235023041475}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6251175917215428, 'r': 0.7962852007189934, 'f1': 0.700395256916996}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5679012345679012, 'r': 0.8518518518518519, 'f1': 0.6814814814814814}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.5362318840579711, 'r': 0.5873015873015873, 'f1': 0.5606060606060606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:06:40.884075: step: 4/529, loss: 3.519058373058215e-05
2023-01-23 04:06:42.085671: step: 8/529, loss: 0.589938759803772
2023-01-23 04:06:43.346666: step: 12/529, loss: 0.0015676498878747225
2023-01-23 04:06:44.575197: step: 16/529, loss: 0.006231784820556641
2023-01-23 04:06:45.757662: step: 20/529, loss: 0.0007458686595782638
2023-01-23 04:06:46.957290: step: 24/529, loss: 0.010531043633818626
2023-01-23 04:06:48.159910: step: 28/529, loss: 0.0051742554642260075
2023-01-23 04:06:49.345203: step: 32/529, loss: 0.002394771669059992
2023-01-23 04:06:50.539850: step: 36/529, loss: 1.163482647825731e-05
2023-01-23 04:06:51.750865: step: 40/529, loss: 4.043579247081652e-05
2023-01-23 04:06:52.917952: step: 44/529, loss: 0.014004579745233059
2023-01-23 04:06:54.150600: step: 48/529, loss: 0.0005135536193847656
2023-01-23 04:06:55.359724: step: 52/529, loss: 0.0007102966192178428
2023-01-23 04:06:56.575017: step: 56/529, loss: 0.03771953657269478
2023-01-23 04:06:57.763325: step: 60/529, loss: 0.0005418777582235634
2023-01-23 04:06:58.930235: step: 64/529, loss: 0.0013505936367437243
2023-01-23 04:07:00.114695: step: 68/529, loss: 0.023321151733398438
2023-01-23 04:07:01.310241: step: 72/529, loss: 0.048165515065193176
2023-01-23 04:07:02.469495: step: 76/529, loss: 0.00012664795212913305
2023-01-23 04:07:03.700208: step: 80/529, loss: 0.2819991111755371
2023-01-23 04:07:04.914328: step: 84/529, loss: 0.037427328526973724
2023-01-23 04:07:06.095883: step: 88/529, loss: 0.007565689273178577
2023-01-23 04:07:07.312807: step: 92/529, loss: 0.00262451171875
2023-01-23 04:07:08.496817: step: 96/529, loss: 0.004447984509170055
2023-01-23 04:07:09.693116: step: 100/529, loss: 0.0008533477666787803
2023-01-23 04:07:10.894591: step: 104/529, loss: 0.0024695396423339844
2023-01-23 04:07:12.097033: step: 108/529, loss: 1.3971329281048384e-05
2023-01-23 04:07:13.274885: step: 112/529, loss: 0.0001579284726176411
2023-01-23 04:07:14.440820: step: 116/529, loss: 0.009340382181107998
2023-01-23 04:07:15.646467: step: 120/529, loss: 0.22913393378257751
2023-01-23 04:07:16.831966: step: 124/529, loss: 0.0002875328063964844
2023-01-23 04:07:18.048522: step: 128/529, loss: 0.0009663582313805819
2023-01-23 04:07:19.193325: step: 132/529, loss: 0.019967293366789818
2023-01-23 04:07:20.406987: step: 136/529, loss: 0.007351875305175781
2023-01-23 04:07:21.639366: step: 140/529, loss: 7.305145845748484e-05
2023-01-23 04:07:22.845756: step: 144/529, loss: 0.0020355223678052425
2023-01-23 04:07:24.053605: step: 148/529, loss: 0.0007492065196856856
2023-01-23 04:07:25.237882: step: 152/529, loss: 0.005029201507568359
2023-01-23 04:07:26.422539: step: 156/529, loss: 0.0002533912775106728
2023-01-23 04:07:27.609110: step: 160/529, loss: 2.307891918462701e-05
2023-01-23 04:07:28.803403: step: 164/529, loss: 0.030162431299686432
2023-01-23 04:07:30.014863: step: 168/529, loss: 0.008948802947998047
2023-01-23 04:07:31.185183: step: 172/529, loss: 1.8882752556237392e-05
2023-01-23 04:07:32.428538: step: 176/529, loss: 0.007852554321289062
2023-01-23 04:07:33.647267: step: 180/529, loss: 0.0001201629638671875
2023-01-23 04:07:34.850790: step: 184/529, loss: 0.00443191546946764
2023-01-23 04:07:36.054832: step: 188/529, loss: 0.35907572507858276
2023-01-23 04:07:37.246027: step: 192/529, loss: 5.245208740234375e-05
2023-01-23 04:07:38.413028: step: 196/529, loss: 0.013924050144851208
2023-01-23 04:07:39.612581: step: 200/529, loss: 0.007835770025849342
2023-01-23 04:07:40.907372: step: 204/529, loss: 0.024692537263035774
2023-01-23 04:07:42.108869: step: 208/529, loss: 0.0005146980402059853
2023-01-23 04:07:43.302015: step: 212/529, loss: 0.0010484695667400956
2023-01-23 04:07:44.484110: step: 216/529, loss: 0.0032876969780772924
2023-01-23 04:07:45.646280: step: 220/529, loss: 0.00010967254638671875
2023-01-23 04:07:46.890559: step: 224/529, loss: 0.012119054794311523
2023-01-23 04:07:48.144530: step: 228/529, loss: 0.002966261003166437
2023-01-23 04:07:49.347339: step: 232/529, loss: 0.0023641586303710938
2023-01-23 04:07:50.532521: step: 236/529, loss: 0.00012807846360374242
2023-01-23 04:07:51.761833: step: 240/529, loss: 0.00020973682694602758
2023-01-23 04:07:52.951766: step: 244/529, loss: 0.0053067682310938835
2023-01-23 04:07:54.142394: step: 248/529, loss: 0.0009965896606445312
2023-01-23 04:07:55.403643: step: 252/529, loss: 0.0003490447998046875
2023-01-23 04:07:56.554021: step: 256/529, loss: 1.258850079466356e-05
2023-01-23 04:07:57.770830: step: 260/529, loss: 0.03919544070959091
2023-01-23 04:07:59.003502: step: 264/529, loss: 0.002490520477294922
2023-01-23 04:08:00.158805: step: 268/529, loss: 0.006438255775719881
2023-01-23 04:08:01.340597: step: 272/529, loss: 0.00010890961129916832
2023-01-23 04:08:02.540896: step: 276/529, loss: 0.008707045577466488
2023-01-23 04:08:03.718971: step: 280/529, loss: 4.9591067181609105e-06
2023-01-23 04:08:04.900887: step: 284/529, loss: 0.0011163712479174137
2023-01-23 04:08:06.102634: step: 288/529, loss: 0.06883106380701065
2023-01-23 04:08:07.311518: step: 292/529, loss: 0.0002906799491029233
2023-01-23 04:08:08.550312: step: 296/529, loss: 0.03744640573859215
2023-01-23 04:08:09.769000: step: 300/529, loss: 0.0022716522216796875
2023-01-23 04:08:11.004132: step: 304/529, loss: 0.00017333030700683594
2023-01-23 04:08:12.184837: step: 308/529, loss: 0.0006372451898641884
2023-01-23 04:08:13.410158: step: 312/529, loss: 5.1784514653263614e-05
2023-01-23 04:08:14.607028: step: 316/529, loss: 5.91278057981981e-06
2023-01-23 04:08:15.797263: step: 320/529, loss: 0.00038051605224609375
2023-01-23 04:08:16.974817: step: 324/529, loss: 0.00400776881724596
2023-01-23 04:08:18.182872: step: 328/529, loss: 0.019878387451171875
2023-01-23 04:08:19.382904: step: 332/529, loss: 0.0005832671886309981
2023-01-23 04:08:20.543686: step: 336/529, loss: 0.00011296272714389488
2023-01-23 04:08:21.780416: step: 340/529, loss: 0.012678910046815872
2023-01-23 04:08:22.986541: step: 344/529, loss: 1.5354156857938506e-05
2023-01-23 04:08:24.138946: step: 348/529, loss: 0.02221374586224556
2023-01-23 04:08:25.332564: step: 352/529, loss: 0.0004319667932577431
2023-01-23 04:08:26.551160: step: 356/529, loss: 0.0012866019969806075
2023-01-23 04:08:27.770095: step: 360/529, loss: 0.0014366151299327612
2023-01-23 04:08:28.940790: step: 364/529, loss: 0.009512138552963734
2023-01-23 04:08:30.216698: step: 368/529, loss: 0.0007678985712118447
2023-01-23 04:08:31.439725: step: 372/529, loss: 5.7601926528150216e-05
2023-01-23 04:08:32.663444: step: 376/529, loss: 0.0007490158313885331
2023-01-23 04:08:33.884700: step: 380/529, loss: 0.33468008041381836
2023-01-23 04:08:35.092512: step: 384/529, loss: 0.003107261611148715
2023-01-23 04:08:36.344007: step: 388/529, loss: 0.0002445220889057964
2023-01-23 04:08:37.556324: step: 392/529, loss: 2.136230432370212e-05
2023-01-23 04:08:38.755360: step: 396/529, loss: 0.0033927918411791325
2023-01-23 04:08:39.957966: step: 400/529, loss: 0.0386258102953434
2023-01-23 04:08:41.136791: step: 404/529, loss: -4.1365624383615796e-06
2023-01-23 04:08:42.286952: step: 408/529, loss: 0.005389547441154718
2023-01-23 04:08:43.509302: step: 412/529, loss: 0.02464141882956028
2023-01-23 04:08:44.726215: step: 416/529, loss: 0.04879140853881836
2023-01-23 04:08:45.866002: step: 420/529, loss: 0.00010566711716819555
2023-01-23 04:08:47.080187: step: 424/529, loss: 0.029463957995176315
2023-01-23 04:08:48.289723: step: 428/529, loss: 0.013134574517607689
2023-01-23 04:08:49.472911: step: 432/529, loss: 0.0006608963012695312
2023-01-23 04:08:50.681995: step: 436/529, loss: 0.05553503334522247
2023-01-23 04:08:51.861111: step: 440/529, loss: 0.03685379400849342
2023-01-23 04:08:53.067144: step: 444/529, loss: 0.00010395050776423886
2023-01-23 04:08:54.259560: step: 448/529, loss: 9.5367431640625e-07
2023-01-23 04:08:55.461318: step: 452/529, loss: 0.00016485452943015844
2023-01-23 04:08:56.640846: step: 456/529, loss: 0.004799461457878351
2023-01-23 04:08:57.832496: step: 460/529, loss: 7.152557373046875e-06
2023-01-23 04:08:59.018935: step: 464/529, loss: 0.005683708004653454
2023-01-23 04:09:00.231555: step: 468/529, loss: 0.01776904985308647
2023-01-23 04:09:01.440253: step: 472/529, loss: 2.384185791015625e-06
2023-01-23 04:09:02.652132: step: 476/529, loss: 0.00020236970158293843
2023-01-23 04:09:03.884372: step: 480/529, loss: 0.006550169084221125
2023-01-23 04:09:05.101464: step: 484/529, loss: 0.0015988351078704
2023-01-23 04:09:06.327487: step: 488/529, loss: 0.00024127960205078125
2023-01-23 04:09:07.503799: step: 492/529, loss: 2.803802453854587e-05
2023-01-23 04:09:08.737935: step: 496/529, loss: 0.00527877826243639
2023-01-23 04:09:09.933942: step: 500/529, loss: 0.004704189486801624
2023-01-23 04:09:11.161222: step: 504/529, loss: 0.0002384185791015625
2023-01-23 04:09:12.367536: step: 508/529, loss: 0.0070091248489916325
2023-01-23 04:09:13.587989: step: 512/529, loss: 0.03541393578052521
2023-01-23 04:09:14.780747: step: 516/529, loss: 0.0001183509812108241
2023-01-23 04:09:15.949963: step: 520/529, loss: 0.0006942272302694619
2023-01-23 04:09:17.138716: step: 524/529, loss: 0.01378555316478014
2023-01-23 04:09:18.281887: step: 528/529, loss: 0.0132325179874897
2023-01-23 04:09:19.460065: step: 532/529, loss: 0.00013618469529319555
2023-01-23 04:09:20.663838: step: 536/529, loss: 0.1562759429216385
2023-01-23 04:09:21.829269: step: 540/529, loss: 9.08970832824707e-05
2023-01-23 04:09:22.979798: step: 544/529, loss: 0.0010103225940838456
2023-01-23 04:09:24.174595: step: 548/529, loss: 0.0025781632866710424
2023-01-23 04:09:25.407420: step: 552/529, loss: 0.007628345396369696
2023-01-23 04:09:26.609671: step: 556/529, loss: 0.00021572114201262593
2023-01-23 04:09:27.837587: step: 560/529, loss: 4.262923903297633e-05
2023-01-23 04:09:29.022991: step: 564/529, loss: 9.727478754939511e-06
2023-01-23 04:09:30.190687: step: 568/529, loss: 0.0023058413062244654
2023-01-23 04:09:31.445756: step: 572/529, loss: 0.00018901826115325093
2023-01-23 04:09:32.653268: step: 576/529, loss: 2.2697449821862392e-05
2023-01-23 04:09:33.838362: step: 580/529, loss: 4.76837158203125e-05
2023-01-23 04:09:35.054670: step: 584/529, loss: 0.013970708474516869
2023-01-23 04:09:36.248131: step: 588/529, loss: 0.0003679275687318295
2023-01-23 04:09:37.419339: step: 592/529, loss: 1.850128137448337e-05
2023-01-23 04:09:38.614867: step: 596/529, loss: 0.006728744599968195
2023-01-23 04:09:39.842732: step: 600/529, loss: 0.02705860137939453
2023-01-23 04:09:41.025929: step: 604/529, loss: 0.0022388456854969263
2023-01-23 04:09:42.224669: step: 608/529, loss: 6.027221752447076e-05
2023-01-23 04:09:43.389314: step: 612/529, loss: 0.03446245193481445
2023-01-23 04:09:44.594737: step: 616/529, loss: 0.00015945434279274195
2023-01-23 04:09:45.810892: step: 620/529, loss: 0.0026391984429210424
2023-01-23 04:09:47.004112: step: 624/529, loss: 0.0277772918343544
2023-01-23 04:09:48.241821: step: 628/529, loss: 0.011947202496230602
2023-01-23 04:09:49.429711: step: 632/529, loss: 3.409385681152344e-05
2023-01-23 04:09:50.662073: step: 636/529, loss: 0.007177162449806929
2023-01-23 04:09:51.836018: step: 640/529, loss: 0.022189904004335403
2023-01-23 04:09:53.024227: step: 644/529, loss: 0.0005662917974404991
2023-01-23 04:09:54.225570: step: 648/529, loss: 0.001060104463249445
2023-01-23 04:09:55.402644: step: 652/529, loss: 7.658005051780492e-05
2023-01-23 04:09:56.619655: step: 656/529, loss: 0.01444101333618164
2023-01-23 04:09:57.855608: step: 660/529, loss: 5.474090721691027e-05
2023-01-23 04:09:59.046174: step: 664/529, loss: 9.441375004826114e-05
2023-01-23 04:10:00.232496: step: 668/529, loss: 0.017198849469423294
2023-01-23 04:10:01.392147: step: 672/529, loss: 6.48498553346144e-06
2023-01-23 04:10:02.609031: step: 676/529, loss: 0.00018825530423782766
2023-01-23 04:10:03.828320: step: 680/529, loss: 0.0014240265591070056
2023-01-23 04:10:05.031604: step: 684/529, loss: 0.0015491485828533769
2023-01-23 04:10:06.241672: step: 688/529, loss: 1.0967254638671875e-05
2023-01-23 04:10:07.410894: step: 692/529, loss: 1.8262862795381807e-05
2023-01-23 04:10:08.618917: step: 696/529, loss: 0.0014374733436852694
2023-01-23 04:10:09.810586: step: 700/529, loss: 0.00024976732674986124
2023-01-23 04:10:11.017969: step: 704/529, loss: 0.0003394126833882183
2023-01-23 04:10:12.226024: step: 708/529, loss: 0.0013156890636309981
2023-01-23 04:10:13.401827: step: 712/529, loss: 0.008582497015595436
2023-01-23 04:10:14.562486: step: 716/529, loss: 0.007393646519631147
2023-01-23 04:10:15.764172: step: 720/529, loss: 0.0001539230433991179
2023-01-23 04:10:16.961153: step: 724/529, loss: 0.0030104636680334806
2023-01-23 04:10:18.161097: step: 728/529, loss: 0.041518211364746094
2023-01-23 04:10:19.357154: step: 732/529, loss: 0.033913709223270416
2023-01-23 04:10:20.570597: step: 736/529, loss: 0.0007184982532635331
2023-01-23 04:10:21.810070: step: 740/529, loss: 0.028669072315096855
2023-01-23 04:10:23.006316: step: 744/529, loss: 0.00010452270362293348
2023-01-23 04:10:24.191200: step: 748/529, loss: 0.03687705844640732
2023-01-23 04:10:25.358309: step: 752/529, loss: 0.00035572052001953125
2023-01-23 04:10:26.543997: step: 756/529, loss: 0.0001070022553903982
2023-01-23 04:10:27.707843: step: 760/529, loss: 0.004831123165786266
2023-01-23 04:10:28.890928: step: 764/529, loss: 0.0005943298456259072
2023-01-23 04:10:30.087642: step: 768/529, loss: 0.0012346267467364669
2023-01-23 04:10:31.251057: step: 772/529, loss: 5.0163271225756034e-05
2023-01-23 04:10:32.509777: step: 776/529, loss: 4.1484832763671875e-05
2023-01-23 04:10:33.678940: step: 780/529, loss: 0.002336263656616211
2023-01-23 04:10:34.846329: step: 784/529, loss: 3.4809111184586072e-06
2023-01-23 04:10:36.027680: step: 788/529, loss: 0.012293053790926933
2023-01-23 04:10:37.232032: step: 792/529, loss: 0.004297065548598766
2023-01-23 04:10:38.482274: step: 796/529, loss: 0.006991100497543812
2023-01-23 04:10:39.665875: step: 800/529, loss: 0.0004047393740620464
2023-01-23 04:10:40.892238: step: 804/529, loss: 0.00013511181168723851
2023-01-23 04:10:42.094214: step: 808/529, loss: 0.00046148302499204874
2023-01-23 04:10:43.282684: step: 812/529, loss: 7.2479248046875e-05
2023-01-23 04:10:44.437721: step: 816/529, loss: 0.0024557113647460938
2023-01-23 04:10:45.599736: step: 820/529, loss: 7.62939453125e-05
2023-01-23 04:10:46.812304: step: 824/529, loss: 0.009744835086166859
2023-01-23 04:10:48.017179: step: 828/529, loss: 0.10424967110157013
2023-01-23 04:10:49.232104: step: 832/529, loss: 0.010329628363251686
2023-01-23 04:10:50.462050: step: 836/529, loss: 0.009173011407256126
2023-01-23 04:10:51.654039: step: 840/529, loss: 0.03605499491095543
2023-01-23 04:10:52.870391: step: 844/529, loss: 0.0002420425444142893
2023-01-23 04:10:54.053021: step: 848/529, loss: 0.00012092590623069555
2023-01-23 04:10:55.209556: step: 852/529, loss: 0.006921720691025257
2023-01-23 04:10:56.382003: step: 856/529, loss: 0.01713581010699272
2023-01-23 04:10:57.570091: step: 860/529, loss: 0.0007255554082803428
2023-01-23 04:10:58.772345: step: 864/529, loss: 0.025281716138124466
2023-01-23 04:10:59.994510: step: 868/529, loss: 0.0003278255753684789
2023-01-23 04:11:01.166793: step: 872/529, loss: 2.0313262211857364e-05
2023-01-23 04:11:02.401999: step: 876/529, loss: 0.0006422996520996094
2023-01-23 04:11:03.605459: step: 880/529, loss: 0.001736545586027205
2023-01-23 04:11:04.822879: step: 884/529, loss: 0.15635128319263458
2023-01-23 04:11:06.054989: step: 888/529, loss: 0.00011463165719760582
2023-01-23 04:11:07.221658: step: 892/529, loss: 0.00067052838858217
2023-01-23 04:11:08.454382: step: 896/529, loss: 0.004331111907958984
2023-01-23 04:11:09.673504: step: 900/529, loss: 0.0013283728621900082
2023-01-23 04:11:10.889791: step: 904/529, loss: 0.0056386953219771385
2023-01-23 04:11:12.141527: step: 908/529, loss: 1.2874603271484375e-05
2023-01-23 04:11:13.330924: step: 912/529, loss: 0.00407066335901618
2023-01-23 04:11:14.526297: step: 916/529, loss: 0.003124713897705078
2023-01-23 04:11:15.721960: step: 920/529, loss: 0.00035057071363553405
2023-01-23 04:11:16.897097: step: 924/529, loss: 0.03272724151611328
2023-01-23 04:11:18.139404: step: 928/529, loss: 0.0002471923944540322
2023-01-23 04:11:19.372172: step: 932/529, loss: 0.0017559052212163806
2023-01-23 04:11:20.598119: step: 936/529, loss: 0.00048809050349518657
2023-01-23 04:11:21.805591: step: 940/529, loss: 0.2978772222995758
2023-01-23 04:11:23.014191: step: 944/529, loss: 0.00698776263743639
2023-01-23 04:11:24.210656: step: 948/529, loss: 6.12258882028982e-05
2023-01-23 04:11:25.398076: step: 952/529, loss: 0.00015125275240279734
2023-01-23 04:11:26.579046: step: 956/529, loss: 2.250671423098538e-05
2023-01-23 04:11:27.779367: step: 960/529, loss: 0.0002061843842966482
2023-01-23 04:11:28.978844: step: 964/529, loss: 0.010334777645766735
2023-01-23 04:11:30.184975: step: 968/529, loss: 5.2261355449445546e-05
2023-01-23 04:11:31.416704: step: 972/529, loss: 4.615783836925402e-05
2023-01-23 04:11:32.580425: step: 976/529, loss: 0.006630039773881435
2023-01-23 04:11:33.805805: step: 980/529, loss: 0.003926277160644531
2023-01-23 04:11:34.993585: step: 984/529, loss: 0.00029964448185637593
2023-01-23 04:11:36.190398: step: 988/529, loss: 8.94546537892893e-05
2023-01-23 04:11:37.363181: step: 992/529, loss: 0.003434467129409313
2023-01-23 04:11:38.537005: step: 996/529, loss: 8.144378807628527e-05
2023-01-23 04:11:39.741398: step: 1000/529, loss: 0.07996673882007599
2023-01-23 04:11:40.946526: step: 1004/529, loss: 9.51766996877268e-05
2023-01-23 04:11:42.120106: step: 1008/529, loss: 0.0006629943381994963
2023-01-23 04:11:43.290295: step: 1012/529, loss: 0.021312618628144264
2023-01-23 04:11:44.476861: step: 1016/529, loss: 0.0017731189727783203
2023-01-23 04:11:45.683020: step: 1020/529, loss: 0.004471111577004194
2023-01-23 04:11:46.894963: step: 1024/529, loss: 1.296997106692288e-05
2023-01-23 04:11:48.050322: step: 1028/529, loss: 0.000309848808683455
2023-01-23 04:11:49.222644: step: 1032/529, loss: 5.0830840336857364e-05
2023-01-23 04:11:50.364977: step: 1036/529, loss: 0.0001619339018361643
2023-01-23 04:11:51.555989: step: 1040/529, loss: 0.00020523072453215718
2023-01-23 04:11:52.732249: step: 1044/529, loss: 5.722049536416307e-07
2023-01-23 04:11:53.893630: step: 1048/529, loss: 2.355575270485133e-05
2023-01-23 04:11:55.075887: step: 1052/529, loss: -9.536779543850571e-08
2023-01-23 04:11:56.315200: step: 1056/529, loss: 5.574875831604004
2023-01-23 04:11:57.575193: step: 1060/529, loss: 3.4332276754867053e-06
2023-01-23 04:11:58.800569: step: 1064/529, loss: 0.0006635665777139366
2023-01-23 04:12:00.035506: step: 1068/529, loss: 0.025925828143954277
2023-01-23 04:12:01.218565: step: 1072/529, loss: 0.00012702943058684468
2023-01-23 04:12:02.377218: step: 1076/529, loss: 3.3092499506892636e-05
2023-01-23 04:12:03.543414: step: 1080/529, loss: 0.020606135949492455
2023-01-23 04:12:04.760385: step: 1084/529, loss: 0.0004594803031068295
2023-01-23 04:12:05.955958: step: 1088/529, loss: 0.015452956780791283
2023-01-23 04:12:07.114964: step: 1092/529, loss: 0.002453613094985485
2023-01-23 04:12:08.294203: step: 1096/529, loss: 0.00010023117647506297
2023-01-23 04:12:09.491530: step: 1100/529, loss: 0.0038464071694761515
2023-01-23 04:12:10.691099: step: 1104/529, loss: 0.03686580806970596
2023-01-23 04:12:11.870427: step: 1108/529, loss: 0.007505225948989391
2023-01-23 04:12:13.050979: step: 1112/529, loss: 0.0014426232082769275
2023-01-23 04:12:14.237921: step: 1116/529, loss: 3.61442580469884e-05
2023-01-23 04:12:15.430774: step: 1120/529, loss: 0.0026311874389648438
2023-01-23 04:12:16.604052: step: 1124/529, loss: 0.011591816321015358
2023-01-23 04:12:17.803077: step: 1128/529, loss: 3.6716461181640625e-05
2023-01-23 04:12:19.068559: step: 1132/529, loss: 5.149841854290571e-06
2023-01-23 04:12:20.219536: step: 1136/529, loss: 0.00011005401756847277
2023-01-23 04:12:21.410262: step: 1140/529, loss: 0.00087823870126158
2023-01-23 04:12:22.602854: step: 1144/529, loss: 0.0003364562871865928
2023-01-23 04:12:23.788747: step: 1148/529, loss: 0.002280616667121649
2023-01-23 04:12:25.002741: step: 1152/529, loss: 0.012219048105180264
2023-01-23 04:12:26.201256: step: 1156/529, loss: 0.04020838811993599
2023-01-23 04:12:27.392678: step: 1160/529, loss: 2.136230432370212e-05
2023-01-23 04:12:28.598928: step: 1164/529, loss: 0.009549903683364391
2023-01-23 04:12:29.812095: step: 1168/529, loss: 0.010606002993881702
2023-01-23 04:12:31.007820: step: 1172/529, loss: 0.00090789794921875
2023-01-23 04:12:32.156447: step: 1176/529, loss: 0.011428642086684704
2023-01-23 04:12:33.356152: step: 1180/529, loss: 0.016846848651766777
2023-01-23 04:12:34.599360: step: 1184/529, loss: 0.0007736206171102822
2023-01-23 04:12:35.780765: step: 1188/529, loss: 2.8133392333984375e-05
2023-01-23 04:12:37.005577: step: 1192/529, loss: 0.0010198593372479081
2023-01-23 04:12:38.188939: step: 1196/529, loss: 0.0026692866813391447
2023-01-23 04:12:39.367265: step: 1200/529, loss: 0.00013818741717841476
2023-01-23 04:12:40.575472: step: 1204/529, loss: 8.20159948489163e-06
2023-01-23 04:12:41.735338: step: 1208/529, loss: 0.003239917801693082
2023-01-23 04:12:42.937191: step: 1212/529, loss: 0.0004779815790243447
2023-01-23 04:12:44.125251: step: 1216/529, loss: 0.0011984348529949784
2023-01-23 04:12:45.330501: step: 1220/529, loss: 9.670257713878527e-05
2023-01-23 04:12:46.542154: step: 1224/529, loss: 0.003485966008156538
2023-01-23 04:12:47.770107: step: 1228/529, loss: 0.0010880469344556332
2023-01-23 04:12:48.994129: step: 1232/529, loss: 0.00021276473125908524
2023-01-23 04:12:50.219401: step: 1236/529, loss: 4.76837158203125e-06
2023-01-23 04:12:51.385578: step: 1240/529, loss: -1.3351439065445447e-06
2023-01-23 04:12:52.601539: step: 1244/529, loss: 0.0008756637689657509
2023-01-23 04:12:53.797749: step: 1248/529, loss: 0.02888660691678524
2023-01-23 04:12:54.993381: step: 1252/529, loss: 0.08788514137268066
2023-01-23 04:12:56.273494: step: 1256/529, loss: 0.00033130645169876516
2023-01-23 04:12:57.445219: step: 1260/529, loss: 0.0002189636288676411
2023-01-23 04:12:58.655800: step: 1264/529, loss: 0.0036752698943018913
2023-01-23 04:12:59.861552: step: 1268/529, loss: -2.384185791015625e-07
2023-01-23 04:13:01.079397: step: 1272/529, loss: 0.024285221472382545
2023-01-23 04:13:02.245859: step: 1276/529, loss: 3.814697322468419e-07
2023-01-23 04:13:03.430881: step: 1280/529, loss: 0.00014381408982444555
2023-01-23 04:13:04.592095: step: 1284/529, loss: -2.47955313170678e-06
2023-01-23 04:13:05.810194: step: 1288/529, loss: 0.03478727117180824
2023-01-23 04:13:06.936767: step: 1292/529, loss: 0.0002849579032044858
2023-01-23 04:13:08.131257: step: 1296/529, loss: 0.007300090976059437
2023-01-23 04:13:09.299906: step: 1300/529, loss: 0.003224706742912531
2023-01-23 04:13:10.487746: step: 1304/529, loss: 0.0001447677641408518
2023-01-23 04:13:11.674397: step: 1308/529, loss: 0.000463891017716378
2023-01-23 04:13:12.909057: step: 1312/529, loss: 0.00286026019603014
2023-01-23 04:13:14.085604: step: 1316/529, loss: 0.029608584940433502
2023-01-23 04:13:15.356223: step: 1320/529, loss: 0.008067512884736061
2023-01-23 04:13:16.516797: step: 1324/529, loss: 2.6798248654813506e-05
2023-01-23 04:13:17.734661: step: 1328/529, loss: 3.1936167943058535e-05
2023-01-23 04:13:18.925704: step: 1332/529, loss: 0.030396176502108574
2023-01-23 04:13:20.104398: step: 1336/529, loss: 0.01925182342529297
2023-01-23 04:13:21.283731: step: 1340/529, loss: 0.2518463134765625
2023-01-23 04:13:22.495792: step: 1344/529, loss: 3.8146970382513246e-06
2023-01-23 04:13:23.704756: step: 1348/529, loss: 0.0006702423561364412
2023-01-23 04:13:24.907353: step: 1352/529, loss: 0.00074939732439816
2023-01-23 04:13:26.123178: step: 1356/529, loss: 8.792877633823082e-05
2023-01-23 04:13:27.328304: step: 1360/529, loss: 0.00014200211444403976
2023-01-23 04:13:28.510492: step: 1364/529, loss: 0.00022964477830100805
2023-01-23 04:13:29.656697: step: 1368/529, loss: 0.013141060248017311
2023-01-23 04:13:30.876721: step: 1372/529, loss: 0.1378769427537918
2023-01-23 04:13:32.040655: step: 1376/529, loss: 0.0006799697293899953
2023-01-23 04:13:33.193636: step: 1380/529, loss: 0.00019021033949684352
2023-01-23 04:13:34.410577: step: 1384/529, loss: 0.028212929144501686
2023-01-23 04:13:35.597190: step: 1388/529, loss: 2.7561189199332148e-05
2023-01-23 04:13:36.815547: step: 1392/529, loss: 0.03977527469396591
2023-01-23 04:13:37.997385: step: 1396/529, loss: 5.455017162603326e-05
2023-01-23 04:13:39.180492: step: 1400/529, loss: 6.151199340820312e-05
2023-01-23 04:13:40.359757: step: 1404/529, loss: 0.006925821304321289
2023-01-23 04:13:41.547853: step: 1408/529, loss: 0.04187622293829918
2023-01-23 04:13:42.743625: step: 1412/529, loss: 0.00257282261736691
2023-01-23 04:13:43.953974: step: 1416/529, loss: 0.026589583605527878
2023-01-23 04:13:45.152280: step: 1420/529, loss: 0.007771492004394531
2023-01-23 04:13:46.376628: step: 1424/529, loss: 0.0024022101424634457
2023-01-23 04:13:47.602518: step: 1428/529, loss: 0.0005808830028399825
2023-01-23 04:13:48.818303: step: 1432/529, loss: 0.017254162579774857
2023-01-23 04:13:50.054240: step: 1436/529, loss: 0.38376161456108093
2023-01-23 04:13:51.203491: step: 1440/529, loss: 0.0022794725373387337
2023-01-23 04:13:52.388561: step: 1444/529, loss: 8.20159948489163e-06
2023-01-23 04:13:53.604095: step: 1448/529, loss: 0.0014661789173260331
2023-01-23 04:13:54.820476: step: 1452/529, loss: 4.978180004400201e-05
2023-01-23 04:13:55.994816: step: 1456/529, loss: 0.0010312080848962069
2023-01-23 04:13:57.170225: step: 1460/529, loss: 0.0070625306107103825
2023-01-23 04:13:58.354606: step: 1464/529, loss: 4.501342846197076e-05
2023-01-23 04:13:59.542408: step: 1468/529, loss: 0.004653740208595991
2023-01-23 04:14:00.672397: step: 1472/529, loss: 2.994537317135837e-05
2023-01-23 04:14:01.880369: step: 1476/529, loss: 0.00011477470252430066
2023-01-23 04:14:03.133680: step: 1480/529, loss: 0.0014583587180823088
2023-01-23 04:14:04.356794: step: 1484/529, loss: 0.04657306522130966
2023-01-23 04:14:05.551693: step: 1488/529, loss: 1.1539458682818804e-05
2023-01-23 04:14:06.723515: step: 1492/529, loss: 1.33514404296875e-05
2023-01-23 04:14:07.927686: step: 1496/529, loss: 0.0009698867797851562
2023-01-23 04:14:09.202652: step: 1500/529, loss: 0.0005991935613565147
2023-01-23 04:14:10.402150: step: 1504/529, loss: 0.0002716064336709678
2023-01-23 04:14:11.614735: step: 1508/529, loss: 1.049041748046875e-05
2023-01-23 04:14:12.792875: step: 1512/529, loss: 0.0002399444638285786
2023-01-23 04:14:13.994565: step: 1516/529, loss: 0.00013961792865302414
2023-01-23 04:14:15.158704: step: 1520/529, loss: 4.673004150390625e-05
2023-01-23 04:14:16.395096: step: 1524/529, loss: 0.0004291534423828125
2023-01-23 04:14:17.620188: step: 1528/529, loss: 0.011511802673339844
2023-01-23 04:14:18.795251: step: 1532/529, loss: 0.024472618475556374
2023-01-23 04:14:19.971659: step: 1536/529, loss: 0.00011825562251033261
2023-01-23 04:14:21.162047: step: 1540/529, loss: 0.00026950836763717234
2023-01-23 04:14:22.356123: step: 1544/529, loss: 0.0027468684129416943
2023-01-23 04:14:23.513266: step: 1548/529, loss: 9.269714064430445e-05
2023-01-23 04:14:24.704004: step: 1552/529, loss: 0.023320579901337624
2023-01-23 04:14:25.900937: step: 1556/529, loss: 0.007452297490090132
2023-01-23 04:14:27.140072: step: 1560/529, loss: 0.0007141113164834678
2023-01-23 04:14:28.313009: step: 1564/529, loss: 0.040764614939689636
2023-01-23 04:14:29.489094: step: 1568/529, loss: 0.026871085166931152
2023-01-23 04:14:30.643173: step: 1572/529, loss: 2.6702882678364404e-06
2023-01-23 04:14:31.874210: step: 1576/529, loss: 0.002458763075992465
2023-01-23 04:14:33.072478: step: 1580/529, loss: 0.17653360962867737
2023-01-23 04:14:34.264158: step: 1584/529, loss: 0.0001762867032084614
2023-01-23 04:14:35.484215: step: 1588/529, loss: 0.0001638412504689768
2023-01-23 04:14:36.691634: step: 1592/529, loss: 7.362365431617945e-05
2023-01-23 04:14:37.900409: step: 1596/529, loss: 0.002918815705925226
2023-01-23 04:14:39.116606: step: 1600/529, loss: 0.0003949165402445942
2023-01-23 04:14:40.255798: step: 1604/529, loss: 0.007817196659743786
2023-01-23 04:14:41.494968: step: 1608/529, loss: 0.19501753151416779
2023-01-23 04:14:42.697061: step: 1612/529, loss: 0.00028858185396529734
2023-01-23 04:14:43.897633: step: 1616/529, loss: 0.0014340400230139494
2023-01-23 04:14:45.104319: step: 1620/529, loss: -5.722044988942798e-07
2023-01-23 04:14:46.263762: step: 1624/529, loss: 0.007927799597382545
2023-01-23 04:14:47.440255: step: 1628/529, loss: 0.0007692337385378778
2023-01-23 04:14:48.631767: step: 1632/529, loss: 5.435943421616685e-06
2023-01-23 04:14:49.856608: step: 1636/529, loss: 0.7499170303344727
2023-01-23 04:14:51.078410: step: 1640/529, loss: -1.2302399227337446e-05
2023-01-23 04:14:52.268791: step: 1644/529, loss: 0.007376289460808039
2023-01-23 04:14:53.443140: step: 1648/529, loss: 0.000584459281526506
2023-01-23 04:14:54.674425: step: 1652/529, loss: 0.0014457226498052478
2023-01-23 04:14:55.853659: step: 1656/529, loss: 0.0026224851608276367
2023-01-23 04:14:57.094499: step: 1660/529, loss: 0.04477253183722496
2023-01-23 04:14:58.289547: step: 1664/529, loss: 0.004599952604621649
2023-01-23 04:14:59.507554: step: 1668/529, loss: 0.005660629365593195
2023-01-23 04:15:00.668572: step: 1672/529, loss: 0.0015316962962970138
2023-01-23 04:15:01.915179: step: 1676/529, loss: 0.0003719329833984375
2023-01-23 04:15:03.102928: step: 1680/529, loss: 0.004139423836022615
2023-01-23 04:15:04.276414: step: 1684/529, loss: 0.0035297395661473274
2023-01-23 04:15:05.462564: step: 1688/529, loss: 0.00048160552978515625
2023-01-23 04:15:06.665244: step: 1692/529, loss: 0.0028154372703284025
2023-01-23 04:15:07.851154: step: 1696/529, loss: 0.0015116692520678043
2023-01-23 04:15:09.151721: step: 1700/529, loss: 0.006237888243049383
2023-01-23 04:15:10.329155: step: 1704/529, loss: 0.0020206451881676912
2023-01-23 04:15:11.525839: step: 1708/529, loss: 0.002826500218361616
2023-01-23 04:15:12.738296: step: 1712/529, loss: 7.05719003235572e-06
2023-01-23 04:15:13.957436: step: 1716/529, loss: 2.9945374990347773e-05
2023-01-23 04:15:15.149795: step: 1720/529, loss: 0.0034042359329760075
2023-01-23 04:15:16.390969: step: 1724/529, loss: 0.031420040875673294
2023-01-23 04:15:17.592012: step: 1728/529, loss: 0.0038157464005053043
2023-01-23 04:15:18.786158: step: 1732/529, loss: 0.0002608299255371094
2023-01-23 04:15:20.003264: step: 1736/529, loss: 0.029870223253965378
2023-01-23 04:15:21.161948: step: 1740/529, loss: 0.0625544935464859
2023-01-23 04:15:22.361958: step: 1744/529, loss: 0.0016108036506921053
2023-01-23 04:15:23.552306: step: 1748/529, loss: 0.03388862684369087
2023-01-23 04:15:24.782519: step: 1752/529, loss: 0.00012941360182594508
2023-01-23 04:15:25.986873: step: 1756/529, loss: 0.00017662048048805445
2023-01-23 04:15:27.167653: step: 1760/529, loss: 0.00014102458953857422
2023-01-23 04:15:28.300833: step: 1764/529, loss: 0.011363220401108265
2023-01-23 04:15:29.522440: step: 1768/529, loss: 5.2738188969669864e-05
2023-01-23 04:15:30.714052: step: 1772/529, loss: 0.0006916046258993447
2023-01-23 04:15:31.940748: step: 1776/529, loss: -1.4066696166992188e-05
2023-01-23 04:15:33.148773: step: 1780/529, loss: 0.000110626220703125
2023-01-23 04:15:34.377702: step: 1784/529, loss: 0.016381453722715378
2023-01-23 04:15:35.559582: step: 1788/529, loss: 0.00945901870727539
2023-01-23 04:15:36.780673: step: 1792/529, loss: 0.020259572193026543
2023-01-23 04:15:37.975519: step: 1796/529, loss: 0.0005234241834841669
2023-01-23 04:15:39.158477: step: 1800/529, loss: 7.858276512706652e-05
2023-01-23 04:15:40.377203: step: 1804/529, loss: 0.00010566711716819555
2023-01-23 04:15:41.571408: step: 1808/529, loss: 0.000653171562589705
2023-01-23 04:15:42.750516: step: 1812/529, loss: 0.039186764508485794
2023-01-23 04:15:44.032071: step: 1816/529, loss: 0.00087146763689816
2023-01-23 04:15:45.231812: step: 1820/529, loss: 9.91821252682712e-06
2023-01-23 04:15:46.407992: step: 1824/529, loss: 0.0004175186331849545
2023-01-23 04:15:47.643960: step: 1828/529, loss: 4.510879807639867e-05
2023-01-23 04:15:48.851262: step: 1832/529, loss: 0.000721836113370955
2023-01-23 04:15:50.045295: step: 1836/529, loss: 0.03773384168744087
2023-01-23 04:15:51.237481: step: 1840/529, loss: 0.0001464843808207661
2023-01-23 04:15:52.386953: step: 1844/529, loss: 0.0006329536554403603
2023-01-23 04:15:53.581107: step: 1848/529, loss: 5.5933000112418085e-05
2023-01-23 04:15:54.774266: step: 1852/529, loss: 0.0012897491687908769
2023-01-23 04:15:55.970413: step: 1856/529, loss: 0.02592296525835991
2023-01-23 04:15:57.154155: step: 1860/529, loss: 0.0015470505459234118
2023-01-23 04:15:58.339436: step: 1864/529, loss: 0.049543190747499466
2023-01-23 04:15:59.573682: step: 1868/529, loss: 0.0015035629039630294
2023-01-23 04:16:00.756225: step: 1872/529, loss: 0.0188782699406147
2023-01-23 04:16:01.945761: step: 1876/529, loss: 0.0211073886603117
2023-01-23 04:16:03.134375: step: 1880/529, loss: 0.03014841116964817
2023-01-23 04:16:04.310901: step: 1884/529, loss: 0.003857135772705078
2023-01-23 04:16:05.521169: step: 1888/529, loss: 0.008114052005112171
2023-01-23 04:16:06.689227: step: 1892/529, loss: 5.5789947509765625e-05
2023-01-23 04:16:07.930475: step: 1896/529, loss: 0.053807638585567474
2023-01-23 04:16:09.116129: step: 1900/529, loss: 0.0039161681197583675
2023-01-23 04:16:10.291805: step: 1904/529, loss: 7.762909081066027e-05
2023-01-23 04:16:11.514924: step: 1908/529, loss: 0.0004047393740620464
2023-01-23 04:16:12.708339: step: 1912/529, loss: 0.0036408426240086555
2023-01-23 04:16:13.923139: step: 1916/529, loss: 0.0027837753295898438
2023-01-23 04:16:15.149043: step: 1920/529, loss: 0.014561224728822708
2023-01-23 04:16:16.367148: step: 1924/529, loss: 6.151199340820312e-05
2023-01-23 04:16:17.537546: step: 1928/529, loss: 2.8514863515738398e-05
2023-01-23 04:16:18.712947: step: 1932/529, loss: 0.0009162903297692537
2023-01-23 04:16:19.939584: step: 1936/529, loss: 0.0015294075710698962
2023-01-23 04:16:21.155736: step: 1940/529, loss: 1.354217511106981e-05
2023-01-23 04:16:22.393668: step: 1944/529, loss: 0.001585769816301763
2023-01-23 04:16:23.641187: step: 1948/529, loss: 1.773834264895413e-05
2023-01-23 04:16:24.814196: step: 1952/529, loss: -2.28881845032447e-06
2023-01-23 04:16:25.996671: step: 1956/529, loss: 6.628036771871848e-06
2023-01-23 04:16:27.193495: step: 1960/529, loss: 0.03980560228228569
2023-01-23 04:16:28.403913: step: 1964/529, loss: 0.03052501752972603
2023-01-23 04:16:29.649212: step: 1968/529, loss: 1.2683869499596767e-05
2023-01-23 04:16:30.844651: step: 1972/529, loss: 0.0005664825439453125
2023-01-23 04:16:32.033172: step: 1976/529, loss: 1.2302398317842744e-05
2023-01-23 04:16:33.187223: step: 1980/529, loss: 0.026405811309814453
2023-01-23 04:16:34.342194: step: 1984/529, loss: 0.0452028289437294
2023-01-23 04:16:35.503510: step: 1988/529, loss: 2.098083541568485e-06
2023-01-23 04:16:36.729658: step: 1992/529, loss: 0.03825235366821289
2023-01-23 04:16:37.918896: step: 1996/529, loss: 8.592606172896922e-05
2023-01-23 04:16:39.121132: step: 2000/529, loss: -3.8146970382513246e-07
2023-01-23 04:16:40.299884: step: 2004/529, loss: 0.00030694008455611765
2023-01-23 04:16:41.494981: step: 2008/529, loss: 0.026889991015195847
2023-01-23 04:16:42.721122: step: 2012/529, loss: 0.011952591128647327
2023-01-23 04:16:43.893292: step: 2016/529, loss: 0.0002199172886321321
2023-01-23 04:16:45.062484: step: 2020/529, loss: -4.95910626341356e-06
2023-01-23 04:16:46.207908: step: 2024/529, loss: 0.0004527568817138672
2023-01-23 04:16:47.382525: step: 2028/529, loss: 7.233619544422254e-05
2023-01-23 04:16:48.594457: step: 2032/529, loss: 0.0010230063926428556
2023-01-23 04:16:49.773362: step: 2036/529, loss: 0.0031953812576830387
2023-01-23 04:16:50.984927: step: 2040/529, loss: 0.00025687218294478953
2023-01-23 04:16:52.158658: step: 2044/529, loss: 0.0012039184803143144
2023-01-23 04:16:53.360738: step: 2048/529, loss: 0.059897422790527344
2023-01-23 04:16:54.551368: step: 2052/529, loss: 3.2997133530443534e-05
2023-01-23 04:16:55.731962: step: 2056/529, loss: 0.011304378509521484
2023-01-23 04:16:56.932712: step: 2060/529, loss: 0.0005025863647460938
2023-01-23 04:16:58.126406: step: 2064/529, loss: 2.708435022213962e-05
2023-01-23 04:16:59.340991: step: 2068/529, loss: 9.183883958030492e-05
2023-01-23 04:17:00.571446: step: 2072/529, loss: 0.00016613007755950093
2023-01-23 04:17:01.754529: step: 2076/529, loss: 0.003967666532844305
2023-01-23 04:17:02.959178: step: 2080/529, loss: 0.00012187957327114418
2023-01-23 04:17:04.111750: step: 2084/529, loss: 9.002685692394152e-05
2023-01-23 04:17:05.353637: step: 2088/529, loss: 0.004203033167868853
2023-01-23 04:17:06.552246: step: 2092/529, loss: 0.000575208687223494
2023-01-23 04:17:07.714187: step: 2096/529, loss: 0.003066539764404297
2023-01-23 04:17:08.897462: step: 2100/529, loss: 7.677078247070312e-05
2023-01-23 04:17:10.082838: step: 2104/529, loss: 0.00011692046973621473
2023-01-23 04:17:11.270213: step: 2108/529, loss: 0.009930610656738281
2023-01-23 04:17:12.421020: step: 2112/529, loss: 4.3630603613564745e-05
2023-01-23 04:17:13.633926: step: 2116/529, loss: 0.0004192352353129536
==================================================
Loss: 0.026
--------------------
Dev: {'event': {'p': 0.5885311871227364, 'r': 0.7789613848202397, 'f1': 0.6704871060171921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6141552511415526, 'r': 0.8058717795086878, 'f1': 0.6970717802539519}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.6075949367088608, 'r': 0.8888888888888888, 'f1': 0.7218045112781953}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.5588235294117647, 'r': 0.6031746031746031, 'f1': 0.5801526717557252}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.4, 'r': 0.5, 'f1': 0.4444444444444445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 04:17:57.744646: step: 4/529, loss: 4.863739013671875e-05
2023-01-23 04:17:58.973046: step: 8/529, loss: 0.007897567935287952
2023-01-23 04:18:00.133510: step: 12/529, loss: 0.0008023261907510459
2023-01-23 04:18:01.315876: step: 16/529, loss: -1.182556115963962e-05
2023-01-23 04:18:02.490502: step: 20/529, loss: 7.009506225585938e-05
2023-01-23 04:18:03.682353: step: 24/529, loss: 0.04871249198913574
2023-01-23 04:18:04.899332: step: 28/529, loss: 0.0014415740733966231
2023-01-23 04:18:06.066446: step: 32/529, loss: 0.000217437744140625
2023-01-23 04:18:07.285029: step: 36/529, loss: 0.00027027129544876516
2023-01-23 04:18:08.478705: step: 40/529, loss: 0.00011959076073253527
2023-01-23 04:18:09.687384: step: 44/529, loss: 0.00744972238317132
2023-01-23 04:18:10.863741: step: 48/529, loss: 3.395080420887098e-05
2023-01-23 04:18:12.126565: step: 52/529, loss: 1.7166138377433526e-06
2023-01-23 04:18:13.347244: step: 56/529, loss: 0.0001775741548044607
2023-01-23 04:18:14.519932: step: 60/529, loss: 2.3746491933707148e-05
2023-01-23 04:18:15.699624: step: 64/529, loss: 0.012915420345962048
2023-01-23 04:18:16.939416: step: 68/529, loss: 0.008329391479492188
2023-01-23 04:18:18.138188: step: 72/529, loss: 0.0016176223289221525
2023-01-23 04:18:19.335527: step: 76/529, loss: 0.00372905726544559
2023-01-23 04:18:20.559123: step: 80/529, loss: 0.0005328178522177041
2023-01-23 04:18:21.732877: step: 84/529, loss: 0.541806697845459
2023-01-23 04:18:22.938765: step: 88/529, loss: 0.5525747537612915
2023-01-23 04:18:24.173615: step: 92/529, loss: 0.03722648695111275
2023-01-23 04:18:25.387743: step: 96/529, loss: 0.0006057739374227822
2023-01-23 04:18:26.628697: step: 100/529, loss: 0.05169200897216797
2023-01-23 04:18:27.846634: step: 104/529, loss: 0.024047089740633965
2023-01-23 04:18:29.032008: step: 108/529, loss: -4.95910626341356e-06
2023-01-23 04:18:30.218247: step: 112/529, loss: 2.679825047380291e-05
2023-01-23 04:18:31.394114: step: 116/529, loss: 5.264282299322076e-05
2023-01-23 04:18:32.568615: step: 120/529, loss: 7.867813110351562e-05
2023-01-23 04:18:33.731858: step: 124/529, loss: 0.006603050045669079
2023-01-23 04:18:34.900589: step: 128/529, loss: 7.886887033237144e-05
2023-01-23 04:18:36.063809: step: 132/529, loss: 0.01063528098165989
2023-01-23 04:18:37.222743: step: 136/529, loss: 0.00019521712965797633
2023-01-23 04:18:38.509658: step: 140/529, loss: 0.12045975029468536
2023-01-23 04:18:39.677622: step: 144/529, loss: 1.9073486328125e-06
2023-01-23 04:18:40.845912: step: 148/529, loss: 0.052079200744628906
2023-01-23 04:18:42.097991: step: 152/529, loss: 0.0012541771866381168
2023-01-23 04:18:43.309802: step: 156/529, loss: 2.021789623540826e-05
2023-01-23 04:18:44.494307: step: 160/529, loss: 0.0002448081795591861
2023-01-23 04:18:45.679911: step: 164/529, loss: 0.03843631595373154
2023-01-23 04:18:46.859542: step: 168/529, loss: 0.0008377075428143144
2023-01-23 04:18:48.101937: step: 172/529, loss: 0.0003574371512513608
2023-01-23 04:18:49.289050: step: 176/529, loss: 0.004027176182717085
2023-01-23 04:18:50.456474: step: 180/529, loss: 4.391670154291205e-05
2023-01-23 04:18:51.665291: step: 184/529, loss: 0.035072021186351776
2023-01-23 04:18:52.899209: step: 188/529, loss: 1.239776611328125e-05
2023-01-23 04:18:54.102566: step: 192/529, loss: 0.0017299652099609375
2023-01-23 04:18:55.308924: step: 196/529, loss: 0.00040912628173828125
2023-01-23 04:18:56.493248: step: 200/529, loss: -1.1539459592313506e-05
2023-01-23 04:18:57.714419: step: 204/529, loss: 0.00048089027404785156
2023-01-23 04:18:58.922622: step: 208/529, loss: 0.0006774902576580644
2023-01-23 04:19:00.107807: step: 212/529, loss: 0.0016258240211755037
2023-01-23 04:19:01.281275: step: 216/529, loss: 0.00032072069006972015
2023-01-23 04:19:02.540400: step: 220/529, loss: 0.0018663406372070312
2023-01-23 04:19:03.734514: step: 224/529, loss: 7.715224637649953e-05
2023-01-23 04:19:04.922643: step: 228/529, loss: 0.010829126462340355
2023-01-23 04:19:06.092296: step: 232/529, loss: 0.00010375976125942543
2023-01-23 04:19:07.311971: step: 236/529, loss: 0.08788375556468964
2023-01-23 04:19:08.470257: step: 240/529, loss: 0.005086564924567938
2023-01-23 04:19:09.687763: step: 244/529, loss: 1.487731969973538e-05
2023-01-23 04:19:10.868504: step: 248/529, loss: 5.7220458984375e-06
2023-01-23 04:19:12.041056: step: 252/529, loss: 0.026588892564177513
2023-01-23 04:19:13.291563: step: 256/529, loss: 1.7929078239831142e-05
2023-01-23 04:19:14.481401: step: 260/529, loss: 8.20159948489163e-06
2023-01-23 04:19:15.678459: step: 264/529, loss: 0.0015436172252520919
2023-01-23 04:19:16.915299: step: 268/529, loss: 0.0009223938104696572
2023-01-23 04:19:18.112274: step: 272/529, loss: 0.0008216857677325606
2023-01-23 04:19:19.333988: step: 276/529, loss: 0.01021575927734375
2023-01-23 04:19:20.535460: step: 280/529, loss: 0.002016353653743863
2023-01-23 04:19:21.747012: step: 284/529, loss: 0.0005573272937908769
2023-01-23 04:19:22.911312: step: 288/529, loss: 0.00012702943058684468
2023-01-23 04:19:24.061041: step: 292/529, loss: 3.981589907198213e-05
2023-01-23 04:19:25.266779: step: 296/529, loss: 5.283355858409777e-05
2023-01-23 04:19:26.460232: step: 300/529, loss: -1.144409225162235e-06
2023-01-23 04:19:27.676567: step: 304/529, loss: 0.00012073517427779734
2023-01-23 04:19:28.859279: step: 308/529, loss: 0.00012073517427779734
2023-01-23 04:19:30.057061: step: 312/529, loss: 0.0034881592728197575
2023-01-23 04:19:31.276060: step: 316/529, loss: 0.004831505008041859
2023-01-23 04:19:32.499664: step: 320/529, loss: 0.045798301696777344
2023-01-23 04:19:33.678800: step: 324/529, loss: 0.00014333725266624242
2023-01-23 04:19:34.899643: step: 328/529, loss: 0.004484748933464289
2023-01-23 04:19:36.073220: step: 332/529, loss: 0.0028752805665135384
2023-01-23 04:19:37.268431: step: 336/529, loss: 0.005227088928222656
2023-01-23 04:19:38.502963: step: 340/529, loss: 0.015465069562196732
2023-01-23 04:19:39.700480: step: 344/529, loss: 3.299712989246473e-05
2023-01-23 04:19:40.908885: step: 348/529, loss: 0.016699982807040215
2023-01-23 04:19:42.083688: step: 352/529, loss: 0.002591419266536832
2023-01-23 04:19:43.312382: step: 356/529, loss: 5.1975250244140625e-05
2023-01-23 04:19:44.550575: step: 360/529, loss: 0.0003038406139239669
2023-01-23 04:19:45.782993: step: 364/529, loss: 0.014149331487715244
2023-01-23 04:19:46.967881: step: 368/529, loss: 0.021544646471738815
2023-01-23 04:19:48.132133: step: 372/529, loss: 0.007944679819047451
2023-01-23 04:19:49.308288: step: 376/529, loss: 0.0012592315906658769
2023-01-23 04:19:50.496945: step: 380/529, loss: 0.008535576052963734
2023-01-23 04:19:51.739302: step: 384/529, loss: 2.593994213384576e-05
2023-01-23 04:19:52.919746: step: 388/529, loss: 0.0004827499215025455
2023-01-23 04:19:54.122517: step: 392/529, loss: 0.002033233642578125
2023-01-23 04:19:55.329901: step: 396/529, loss: 2.0980833141948096e-06
2023-01-23 04:19:56.512008: step: 400/529, loss: 7.581711543025449e-05
2023-01-23 04:19:57.743546: step: 404/529, loss: 0.0004957198980264366
2023-01-23 04:19:58.983572: step: 408/529, loss: 0.020366763696074486
2023-01-23 04:20:00.192686: step: 412/529, loss: 0.055117081850767136
2023-01-23 04:20:01.352022: step: 416/529, loss: 0.025087451562285423
2023-01-23 04:20:02.549591: step: 420/529, loss: 0.00012531279935501516
2023-01-23 04:20:03.774590: step: 424/529, loss: 0.005813026800751686
2023-01-23 04:20:04.943038: step: 428/529, loss: 0.059925176203250885
2023-01-23 04:20:06.139531: step: 432/529, loss: 0.001520443009212613
2023-01-23 04:20:07.319139: step: 436/529, loss: 0.00107402796857059
2023-01-23 04:20:08.506447: step: 440/529, loss: 0.007129669189453125
2023-01-23 04:20:09.684812: step: 444/529, loss: 0.0007104873657226562
2023-01-23 04:20:10.902937: step: 448/529, loss: 0.009379005990922451
2023-01-23 04:20:12.121318: step: 452/529, loss: 4.186630030744709e-05
2023-01-23 04:20:13.312183: step: 456/529, loss: 0.002368164248764515
2023-01-23 04:20:14.465234: step: 460/529, loss: 0.5788941383361816
2023-01-23 04:20:15.693837: step: 464/529, loss: 0.00020599366689566523
2023-01-23 04:20:16.842808: step: 468/529, loss: 0.0011881828540936112
2023-01-23 04:20:18.040767: step: 472/529, loss: 7.743835158180445e-05
2023-01-23 04:20:19.241020: step: 476/529, loss: 0.0033714293967932463
2023-01-23 04:20:20.412021: step: 480/529, loss: 0.08300705254077911
2023-01-23 04:20:21.651603: step: 484/529, loss: 0.005856513977050781
2023-01-23 04:20:22.831388: step: 488/529, loss: 2.8324127924861386e-05
2023-01-23 04:20:24.009361: step: 492/529, loss: 3.6811830796068534e-05
2023-01-23 04:20:25.224607: step: 496/529, loss: 0.0002978801785502583
2023-01-23 04:20:26.429753: step: 500/529, loss: 6.198883056640625e-05
2023-01-23 04:20:27.644405: step: 504/529, loss: 0.008921146392822266
2023-01-23 04:20:28.825357: step: 508/529, loss: 3.643035961431451e-05
2023-01-23 04:20:30.006443: step: 512/529, loss: 0.09600763767957687
2023-01-23 04:20:31.190113: step: 516/529, loss: 0.0012737273937091231
2023-01-23 04:20:32.400647: step: 520/529, loss: 0.0014580488204956055
2023-01-23 04:20:33.608166: step: 524/529, loss: 0.011813831515610218
2023-01-23 04:20:34.873004: step: 528/529, loss: 0.750552773475647
2023-01-23 04:20:36.034003: step: 532/529, loss: 0.014604568481445312
2023-01-23 04:20:37.233575: step: 536/529, loss: 0.04468338564038277
2023-01-23 04:20:38.440448: step: 540/529, loss: 8.316040475619957e-05
2023-01-23 04:20:39.602988: step: 544/529, loss: 1.9073468138230965e-07
2023-01-23 04:20:40.831599: step: 548/529, loss: 0.0031305314041674137
2023-01-23 04:20:42.038540: step: 552/529, loss: 3.6239625842426904e-06
2023-01-23 04:20:43.270699: step: 556/529, loss: 0.00011024475679732859
2023-01-23 04:20:44.430290: step: 560/529, loss: 0.0006025314214639366
2023-01-23 04:20:45.635485: step: 564/529, loss: 4.272460864740424e-05
2023-01-23 04:20:46.896321: step: 568/529, loss: 0.07542724907398224
2023-01-23 04:20:48.051212: step: 572/529, loss: 5.035400317865424e-05
2023-01-23 04:20:49.229031: step: 576/529, loss: 0.011050987988710403
2023-01-23 04:20:50.442029: step: 580/529, loss: 0.0009958267910405993
2023-01-23 04:20:51.623073: step: 584/529, loss: 0.0032279014121741056
2023-01-23 04:20:52.795183: step: 588/529, loss: 0.012427901849150658
2023-01-23 04:20:54.002000: step: 592/529, loss: 0.0003264427068643272
2023-01-23 04:20:55.223061: step: 596/529, loss: 0.05097704008221626
2023-01-23 04:20:56.420464: step: 600/529, loss: 0.03349733352661133
2023-01-23 04:20:57.608934: step: 604/529, loss: 0.04917879030108452
2023-01-23 04:20:58.864347: step: 608/529, loss: 0.00736732454970479
2023-01-23 04:21:00.079368: step: 612/529, loss: 6.961822509765625e-05
2023-01-23 04:21:01.266627: step: 616/529, loss: 1.087188684323337e-05
2023-01-23 04:21:02.468595: step: 620/529, loss: 3.242493221478071e-06
2023-01-23 04:21:03.638442: step: 624/529, loss: 3.25202927342616e-05
2023-01-23 04:21:04.818654: step: 628/529, loss: -3.814697265625e-06
2023-01-23 04:21:06.011121: step: 632/529, loss: 0.037526510655879974
2023-01-23 04:21:07.194232: step: 636/529, loss: 0.0010787963401526213
2023-01-23 04:21:08.379524: step: 640/529, loss: 0.003557920688763261
2023-01-23 04:21:09.580691: step: 644/529, loss: 0.009724712930619717
2023-01-23 04:21:10.766702: step: 648/529, loss: 0.0016495705349370837
2023-01-23 04:21:11.945102: step: 652/529, loss: 0.0005769729614257812
2023-01-23 04:21:13.199013: step: 656/529, loss: 5.91278057981981e-06
2023-01-23 04:21:14.395592: step: 660/529, loss: 0.001140546752139926
2023-01-23 04:21:15.591193: step: 664/529, loss: 0.011935329996049404
2023-01-23 04:21:16.798782: step: 668/529, loss: 0.00394783029332757
2023-01-23 04:21:17.978270: step: 672/529, loss: 0.0012670516734942794
2023-01-23 04:21:19.177316: step: 676/529, loss: 0.1113218367099762
2023-01-23 04:21:20.403401: step: 680/529, loss: 0.0009527206420898438
2023-01-23 04:21:21.597566: step: 684/529, loss: 0.0025323869194835424
2023-01-23 04:21:22.801688: step: 688/529, loss: -1.52587890625e-05
2023-01-23 04:21:23.985655: step: 692/529, loss: 0.00011291504779364914
2023-01-23 04:21:25.162292: step: 696/529, loss: -3.14712519866589e-06
2023-01-23 04:21:26.411822: step: 700/529, loss: 0.00687065115198493
2023-01-23 04:21:27.549521: step: 704/529, loss: 0.000339508056640625
2023-01-23 04:21:28.741077: step: 708/529, loss: 0.008040428161621094
2023-01-23 04:21:29.942969: step: 712/529, loss: 0.0005170822259970009
2023-01-23 04:21:31.115201: step: 716/529, loss: 0.0002056121884379536
2023-01-23 04:21:32.344345: step: 720/529, loss: 0.024943161755800247
2023-01-23 04:21:33.511019: step: 724/529, loss: 0.0004837989981751889
2023-01-23 04:21:34.718774: step: 728/529, loss: 0.0034859657753258944
2023-01-23 04:21:35.907233: step: 732/529, loss: 0.0008152961963787675
2023-01-23 04:21:37.094958: step: 736/529, loss: 3.757476952159777e-05
2023-01-23 04:21:38.350287: step: 740/529, loss: 0.06342391669750214
2023-01-23 04:21:39.529274: step: 744/529, loss: 0.00021781922259833664
2023-01-23 04:21:40.696867: step: 748/529, loss: 1.3065338862361386e-05
2023-01-23 04:21:41.869664: step: 752/529, loss: 0.004344367887824774
2023-01-23 04:21:43.075730: step: 756/529, loss: 0.053530313074588776
2023-01-23 04:21:44.284179: step: 760/529, loss: 0.802336573600769
2023-01-23 04:21:45.491167: step: 764/529, loss: 0.0009565353393554688
2023-01-23 04:21:46.711029: step: 768/529, loss: 0.0004884243244305253
2023-01-23 04:21:47.932185: step: 772/529, loss: 0.022400524467229843
2023-01-23 04:21:49.125062: step: 776/529, loss: 0.01739025115966797
2023-01-23 04:21:50.291883: step: 780/529, loss: 0.0001124382033594884
2023-01-23 04:21:51.493201: step: 784/529, loss: 0.008530139923095703
2023-01-23 04:21:52.679252: step: 788/529, loss: 1.8596649169921875e-05
2023-01-23 04:21:53.860478: step: 792/529, loss: 0.010828113183379173
2023-01-23 04:21:55.076178: step: 796/529, loss: 0.048886775970458984
2023-01-23 04:21:56.297746: step: 800/529, loss: 0.00014734268188476562
2023-01-23 04:21:57.455820: step: 804/529, loss: 0.0017309188842773438
2023-01-23 04:21:58.630208: step: 808/529, loss: 0.08981933444738388
2023-01-23 04:21:59.850751: step: 812/529, loss: 0.04576887935400009
2023-01-23 04:22:01.037759: step: 816/529, loss: 3.0231476557673886e-05
2023-01-23 04:22:02.215692: step: 820/529, loss: 4.587173680192791e-05
2023-01-23 04:22:03.423475: step: 824/529, loss: 0.01203455962240696
2023-01-23 04:22:04.615297: step: 828/529, loss: 3.0279159545898438e-05
2023-01-23 04:22:05.780985: step: 832/529, loss: 0.0066534047946333885
2023-01-23 04:22:06.992111: step: 836/529, loss: 0.0025269510224461555
2023-01-23 04:22:08.200007: step: 840/529, loss: 0.039559267461299896
2023-01-23 04:22:09.384792: step: 844/529, loss: 9.393692016601562e-05
2023-01-23 04:22:10.600417: step: 848/529, loss: 0.04873852804303169
2023-01-23 04:22:11.785227: step: 852/529, loss: 0.013102197088301182
2023-01-23 04:22:12.963482: step: 856/529, loss: 0.00043487548828125
2023-01-23 04:22:14.184809: step: 860/529, loss: 0.02509746514260769
2023-01-23 04:22:15.414375: step: 864/529, loss: 0.03627157211303711
2023-01-23 04:22:16.647465: step: 868/529, loss: 0.0024751664604991674
2023-01-23 04:22:17.845804: step: 872/529, loss: 0.0014551162021234632
2023-01-23 04:22:19.112246: step: 876/529, loss: 0.0004028320254292339
2023-01-23 04:22:20.322630: step: 880/529, loss: 1.0967254638671875e-05
2023-01-23 04:22:21.497390: step: 884/529, loss: 8.58306884765625e-06
2023-01-23 04:22:22.655062: step: 888/529, loss: 0.0002563476446084678
2023-01-23 04:22:23.869534: step: 892/529, loss: 0.0015506744384765625
2023-01-23 04:22:25.029954: step: 896/529, loss: 0.0005542993894778192
2023-01-23 04:22:26.216829: step: 900/529, loss: 1.5926361811580136e-05
2023-01-23 04:22:27.428782: step: 904/529, loss: 0.011474848724901676
2023-01-23 04:22:28.639903: step: 908/529, loss: 0.031229974702000618
2023-01-23 04:22:29.818380: step: 912/529, loss: 2.4700166250113398e-05
2023-01-23 04:22:31.033751: step: 916/529, loss: 0.00014057158841751516
2023-01-23 04:22:32.254690: step: 920/529, loss: 6.618499901378527e-05
2023-01-23 04:22:33.469333: step: 924/529, loss: -2.346038854739163e-05
2023-01-23 04:22:34.679657: step: 928/529, loss: 0.07287827134132385
2023-01-23 04:22:35.891995: step: 932/529, loss: -2.002715973503655e-06
2023-01-23 04:22:37.138324: step: 936/529, loss: 0.009729957208037376
2023-01-23 04:22:38.345109: step: 940/529, loss: 0.00077905657235533
2023-01-23 04:22:39.534662: step: 944/529, loss: 0.00020761489577125758
2023-01-23 04:22:40.691833: step: 948/529, loss: 0.0003769874747376889
2023-01-23 04:22:41.878790: step: 952/529, loss: 0.0006922722095623612
2023-01-23 04:22:43.046943: step: 956/529, loss: 0.0003673553583212197
2023-01-23 04:22:44.233504: step: 960/529, loss: 2.956390289909905e-06
2023-01-23 04:22:45.437332: step: 964/529, loss: 0.00026359560433775187
2023-01-23 04:22:46.627284: step: 968/529, loss: 1.2969970157428179e-05
2023-01-23 04:22:47.832006: step: 972/529, loss: 0.05458088219165802
2023-01-23 04:22:49.007908: step: 976/529, loss: 1.1444091796875e-05
2023-01-23 04:22:50.249294: step: 980/529, loss: 0.026933861896395683
2023-01-23 04:22:51.421830: step: 984/529, loss: 0.0008135795942507684
2023-01-23 04:22:52.646619: step: 988/529, loss: 2.8991700673941523e-05
2023-01-23 04:22:53.864638: step: 992/529, loss: 0.0004686355823650956
2023-01-23 04:22:55.076909: step: 996/529, loss: 0.02346344105899334
2023-01-23 04:22:56.249834: step: 1000/529, loss: 0.004833845887333155
2023-01-23 04:22:57.476664: step: 1004/529, loss: 0.0020793916191905737
2023-01-23 04:22:58.696471: step: 1008/529, loss: 0.007673073094338179
2023-01-23 04:22:59.886553: step: 1012/529, loss: 5.0830840336857364e-05
2023-01-23 04:23:01.075416: step: 1016/529, loss: 0.0014425277477130294
2023-01-23 04:23:02.253309: step: 1020/529, loss: 4.76837158203125e-07
2023-01-23 04:23:03.438228: step: 1024/529, loss: 6.279945955611765e-05
2023-01-23 04:23:04.601146: step: 1028/529, loss: 0.0030023574363440275
2023-01-23 04:23:05.858885: step: 1032/529, loss: 0.020935440436005592
2023-01-23 04:23:07.015738: step: 1036/529, loss: 0.0015079497825354338
2023-01-23 04:23:08.245090: step: 1040/529, loss: 8.869171324477065e-06
2023-01-23 04:23:09.455229: step: 1044/529, loss: 0.03527965396642685
2023-01-23 04:23:10.628502: step: 1048/529, loss: 1.0490418844710803e-06
2023-01-23 04:23:11.793585: step: 1052/529, loss: 0.0003127098025288433
2023-01-23 04:23:12.974180: step: 1056/529, loss: 0.0001999855157919228
2023-01-23 04:23:14.175917: step: 1060/529, loss: 0.00170307164080441
2023-01-23 04:23:15.361776: step: 1064/529, loss: 0.0006354332435876131
2023-01-23 04:23:16.525805: step: 1068/529, loss: 3.6859513784293085e-05
2023-01-23 04:23:17.701460: step: 1072/529, loss: 7.724761962890625e-05
2023-01-23 04:23:18.878237: step: 1076/529, loss: 4.57763690064894e-06
2023-01-23 04:23:20.040651: step: 1080/529, loss: 2.765656063274946e-06
2023-01-23 04:23:21.218560: step: 1084/529, loss: 0.06073570251464844
2023-01-23 04:23:22.444429: step: 1088/529, loss: 0.0004094124014955014
2023-01-23 04:23:23.594112: step: 1092/529, loss: 3.910064697265625e-05
2023-01-23 04:23:24.791608: step: 1096/529, loss: 0.0017435074551030993
2023-01-23 04:23:25.986898: step: 1100/529, loss: 0.0064581395126879215
2023-01-23 04:23:27.192697: step: 1104/529, loss: 0.02167205885052681
2023-01-23 04:23:28.392076: step: 1108/529, loss: 1.5068053471622989e-05
2023-01-23 04:23:29.554306: step: 1112/529, loss: 0.004329585935920477
2023-01-23 04:23:30.757859: step: 1116/529, loss: 0.009985638782382011
2023-01-23 04:23:31.996835: step: 1120/529, loss: 0.00016508102999068797
2023-01-23 04:23:33.157773: step: 1124/529, loss: 0.0026569366455078125
2023-01-23 04:23:34.317749: step: 1128/529, loss: 0.004138756077736616
2023-01-23 04:23:35.515573: step: 1132/529, loss: 0.008070182986557484
2023-01-23 04:23:36.677521: step: 1136/529, loss: 4.00543194700731e-06
2023-01-23 04:23:37.864529: step: 1140/529, loss: 0.0002991676446981728
2023-01-23 04:23:39.085674: step: 1144/529, loss: 0.016420649364590645
2023-01-23 04:23:40.268958: step: 1148/529, loss: 0.003762149950489402
2023-01-23 04:23:41.440790: step: 1152/529, loss: 0.036241911351680756
2023-01-23 04:23:42.634051: step: 1156/529, loss: 0.011696243658661842
2023-01-23 04:23:43.854446: step: 1160/529, loss: 0.05250797048211098
2023-01-23 04:23:45.057411: step: 1164/529, loss: 6.69479341013357e-05
2023-01-23 04:23:46.321986: step: 1168/529, loss: 0.0013175965286791325
2023-01-23 04:23:47.484210: step: 1172/529, loss: 7.629396350239404e-07
2023-01-23 04:23:48.676071: step: 1176/529, loss: 0.0044708251953125
2023-01-23 04:23:49.863665: step: 1180/529, loss: 0.014200210571289062
2023-01-23 04:23:51.092541: step: 1184/529, loss: 0.0027084352914243937
2023-01-23 04:23:52.298880: step: 1188/529, loss: 0.011113166809082031
2023-01-23 04:23:53.502037: step: 1192/529, loss: 0.0011014938354492188
2023-01-23 04:23:54.723775: step: 1196/529, loss: 0.006846427917480469
2023-01-23 04:23:55.913135: step: 1200/529, loss: 0.0006832123035565019
2023-01-23 04:23:57.093495: step: 1204/529, loss: 0.00381641392596066
2023-01-23 04:23:58.314530: step: 1208/529, loss: 0.02046814002096653
2023-01-23 04:23:59.539979: step: 1212/529, loss: 0.008275222964584827
2023-01-23 04:24:00.721496: step: 1216/529, loss: 0.0030252456199377775
2023-01-23 04:24:01.927200: step: 1220/529, loss: 0.03834524378180504
2023-01-23 04:24:03.130735: step: 1224/529, loss: 0.00010585784912109375
2023-01-23 04:24:04.307861: step: 1228/529, loss: 0.0001394271821482107
2023-01-23 04:24:05.524288: step: 1232/529, loss: 0.00040798186091706157
2023-01-23 04:24:06.674209: step: 1236/529, loss: 0.0002079010009765625
2023-01-23 04:24:07.878454: step: 1240/529, loss: 0.0011264801723882556
2023-01-23 04:24:09.062831: step: 1244/529, loss: 0.007622480392456055
2023-01-23 04:24:10.249947: step: 1248/529, loss: 0.08837050944566727
2023-01-23 04:24:11.479491: step: 1252/529, loss: 0.00016403199697379023
2023-01-23 04:24:12.724419: step: 1256/529, loss: 0.0014233589172363281
2023-01-23 04:24:13.983867: step: 1260/529, loss: 4.234314110362902e-05
2023-01-23 04:24:15.166237: step: 1264/529, loss: 0.021548127755522728
2023-01-23 04:24:16.359515: step: 1268/529, loss: 0.013478565961122513
2023-01-23 04:24:17.571165: step: 1272/529, loss: 0.09491729736328125
2023-01-23 04:24:18.793877: step: 1276/529, loss: 0.04279670864343643
2023-01-23 04:24:19.999999: step: 1280/529, loss: 0.0018508434295654297
2023-01-23 04:24:21.189430: step: 1284/529, loss: 0.02612590789794922
2023-01-23 04:24:22.390093: step: 1288/529, loss: 0.0014410018920898438
2023-01-23 04:24:23.585786: step: 1292/529, loss: 8.1062319168268e-07
2023-01-23 04:24:24.813078: step: 1296/529, loss: 0.00702247628942132
2023-01-23 04:24:25.978569: step: 1300/529, loss: 0.00023112297640182078
2023-01-23 04:24:27.179223: step: 1304/529, loss: 0.0007623672718182206
2023-01-23 04:24:28.389488: step: 1308/529, loss: 0.00037822723970748484
2023-01-23 04:24:29.542126: step: 1312/529, loss: 0.02459869533777237
2023-01-23 04:24:30.769607: step: 1316/529, loss: 0.009889364242553711
2023-01-23 04:24:31.982353: step: 1320/529, loss: 0.00023279190645553172
2023-01-23 04:24:33.146633: step: 1324/529, loss: -1.5258790426742053e-06
2023-01-23 04:24:34.360320: step: 1328/529, loss: 0.4184935688972473
2023-01-23 04:24:35.585102: step: 1332/529, loss: 0.040122415870428085
2023-01-23 04:24:36.756415: step: 1336/529, loss: 0.01235275249928236
2023-01-23 04:24:37.931223: step: 1340/529, loss: 0.0002510070917196572
2023-01-23 04:24:39.135923: step: 1344/529, loss: 9.059906460606726e-07
2023-01-23 04:24:40.339673: step: 1348/529, loss: 0.0001520156947663054
2023-01-23 04:24:41.573085: step: 1352/529, loss: 0.0017858505016192794
2023-01-23 04:24:42.749884: step: 1356/529, loss: 0.001049041748046875
2023-01-23 04:24:43.919833: step: 1360/529, loss: 1.7356871467200108e-05
2023-01-23 04:24:45.146987: step: 1364/529, loss: 2.689361645025201e-05
2023-01-23 04:24:46.389451: step: 1368/529, loss: 0.012994194403290749
2023-01-23 04:24:47.564702: step: 1372/529, loss: 0.00758857699111104
2023-01-23 04:24:48.774445: step: 1376/529, loss: 0.059294987469911575
2023-01-23 04:24:49.966478: step: 1380/529, loss: 0.007464217953383923
2023-01-23 04:24:51.119591: step: 1384/529, loss: 1.068115216185106e-05
2023-01-23 04:24:52.334511: step: 1388/529, loss: -1.0013580322265625e-05
2023-01-23 04:24:53.527290: step: 1392/529, loss: 0.0013828754890710115
2023-01-23 04:24:54.744177: step: 1396/529, loss: 0.0034358978737145662
2023-01-23 04:24:55.916739: step: 1400/529, loss: 1.1777878171415068e-05
2023-01-23 04:24:57.086468: step: 1404/529, loss: 0.0036846159491688013
2023-01-23 04:24:58.267289: step: 1408/529, loss: 0.0008441925165243447
2023-01-23 04:24:59.508425: step: 1412/529, loss: 0.0008647918584756553
2023-01-23 04:25:00.702426: step: 1416/529, loss: 0.03754768148064613
2023-01-23 04:25:01.931470: step: 1420/529, loss: 9.584426152287051e-06
2023-01-23 04:25:03.126943: step: 1424/529, loss: 0.045939065515995026
2023-01-23 04:25:04.413874: step: 1428/529, loss: 0.0003535270516294986
2023-01-23 04:25:05.600861: step: 1432/529, loss: 0.0005018234369345009
2023-01-23 04:25:06.789249: step: 1436/529, loss: 0.0001672744838288054
2023-01-23 04:25:07.999219: step: 1440/529, loss: 0.0007632256019860506
2023-01-23 04:25:09.193859: step: 1444/529, loss: 3.9291378925554454e-05
2023-01-23 04:25:10.403132: step: 1448/529, loss: 0.00011777878535212949
2023-01-23 04:25:11.635669: step: 1452/529, loss: 0.00047130585880950093
2023-01-23 04:25:12.822916: step: 1456/529, loss: 2.050399962172378e-05
2023-01-23 04:25:13.997166: step: 1460/529, loss: 6.370544724632055e-05
2023-01-23 04:25:15.177859: step: 1464/529, loss: 0.0018415451049804688
2023-01-23 04:25:16.343221: step: 1468/529, loss: 8.869171324477065e-06
2023-01-23 04:25:17.572840: step: 1472/529, loss: 0.0006696701166220009
2023-01-23 04:25:18.729919: step: 1476/529, loss: 9.069442603504285e-05
2023-01-23 04:25:20.023779: step: 1480/529, loss: 0.024466706439852715
2023-01-23 04:25:21.274168: step: 1484/529, loss: 0.011666965670883656
2023-01-23 04:25:22.490832: step: 1488/529, loss: 0.011014366522431374
2023-01-23 04:25:23.698104: step: 1492/529, loss: 0.026410484686493874
2023-01-23 04:25:24.908148: step: 1496/529, loss: 0.00019407272338867188
2023-01-23 04:25:26.114019: step: 1500/529, loss: 0.003574156668037176
2023-01-23 04:25:27.288270: step: 1504/529, loss: 0.015203761868178844
2023-01-23 04:25:28.487302: step: 1508/529, loss: 0.0036230087280273438
2023-01-23 04:25:29.710208: step: 1512/529, loss: 0.0001472473086323589
2023-01-23 04:25:30.926759: step: 1516/529, loss: 0.06792354583740234
2023-01-23 04:25:32.227018: step: 1520/529, loss: 0.0014261245960369706
2023-01-23 04:25:33.405782: step: 1524/529, loss: 8.106231689453125e-06
2023-01-23 04:25:34.596594: step: 1528/529, loss: 7.247925623232732e-06
2023-01-23 04:25:35.830135: step: 1532/529, loss: 0.0002766609250102192
2023-01-23 04:25:37.015821: step: 1536/529, loss: 1.640319896978326e-05
2023-01-23 04:25:38.240200: step: 1540/529, loss: 4.978180004400201e-05
2023-01-23 04:25:39.386918: step: 1544/529, loss: 0.0013835907448083162
2023-01-23 04:25:40.651013: step: 1548/529, loss: 0.03432135656476021
2023-01-23 04:25:41.843974: step: 1552/529, loss: 5.517006138688885e-05
2023-01-23 04:25:43.053501: step: 1556/529, loss: 0.0003009796200785786
2023-01-23 04:25:44.246594: step: 1560/529, loss: 0.006619930267333984
2023-01-23 04:25:45.453553: step: 1564/529, loss: 0.02258882485330105
2023-01-23 04:25:46.656218: step: 1568/529, loss: 0.000751876796130091
2023-01-23 04:25:47.849416: step: 1572/529, loss: 0.11988982558250427
2023-01-23 04:25:49.043635: step: 1576/529, loss: 0.0005485772853717208
2023-01-23 04:25:50.277336: step: 1580/529, loss: 0.027642060071229935
2023-01-23 04:25:51.470096: step: 1584/529, loss: 0.014576531015336514
2023-01-23 04:25:52.643626: step: 1588/529, loss: 9.183883958030492e-05
2023-01-23 04:25:53.840604: step: 1592/529, loss: 0.004127406980842352
2023-01-23 04:25:55.002990: step: 1596/529, loss: 3.34262840624433e-05
2023-01-23 04:25:56.226584: step: 1600/529, loss: 6.8664553509734105e-06
2023-01-23 04:25:57.404514: step: 1604/529, loss: 0.030353927984833717
2023-01-23 04:25:58.625826: step: 1608/529, loss: 0.05172233656048775
2023-01-23 04:25:59.832665: step: 1612/529, loss: 0.001163482666015625
2023-01-23 04:26:01.007238: step: 1616/529, loss: 0.0005651473766192794
2023-01-23 04:26:02.215174: step: 1620/529, loss: 0.014611911959946156
2023-01-23 04:26:03.399878: step: 1624/529, loss: 3.814697265625e-05
2023-01-23 04:26:04.610092: step: 1628/529, loss: 0.05935544893145561
2023-01-23 04:26:05.804278: step: 1632/529, loss: 2.5177003408316523e-05
2023-01-23 04:26:07.034952: step: 1636/529, loss: 0.0007702827570028603
2023-01-23 04:26:08.246331: step: 1640/529, loss: 0.002065467881038785
2023-01-23 04:26:09.473436: step: 1644/529, loss: 0.005012321285903454
2023-01-23 04:26:10.632576: step: 1648/529, loss: 0.0012476444244384766
2023-01-23 04:26:11.805231: step: 1652/529, loss: 0.002281284425407648
2023-01-23 04:26:12.974666: step: 1656/529, loss: 0.009362364187836647
2023-01-23 04:26:14.143829: step: 1660/529, loss: 0.037930678576231
2023-01-23 04:26:15.380808: step: 1664/529, loss: 0.243106871843338
2023-01-23 04:26:16.560421: step: 1668/529, loss: 0.0015608788235113025
2023-01-23 04:26:17.745656: step: 1672/529, loss: 9.35554489842616e-05
2023-01-23 04:26:18.914244: step: 1676/529, loss: 7.543563697254285e-05
2023-01-23 04:26:20.085963: step: 1680/529, loss: 0.0008529663318768144
2023-01-23 04:26:21.290032: step: 1684/529, loss: 2.8610247682081535e-07
2023-01-23 04:26:22.455197: step: 1688/529, loss: 0.00015802383131813258
2023-01-23 04:26:23.646094: step: 1692/529, loss: 0.010190105997025967
2023-01-23 04:26:24.832183: step: 1696/529, loss: 0.005534553434699774
2023-01-23 04:26:26.051827: step: 1700/529, loss: 0.0004459381161723286
2023-01-23 04:26:27.222304: step: 1704/529, loss: 4.76837158203125e-06
2023-01-23 04:26:28.424278: step: 1708/529, loss: 0.02378368377685547
2023-01-23 04:26:29.596076: step: 1712/529, loss: 0.006598091218620539
2023-01-23 04:26:30.782523: step: 1716/529, loss: 0.019258594140410423
2023-01-23 04:26:31.964381: step: 1720/529, loss: 3.185272362316027e-05
2023-01-23 04:26:33.202213: step: 1724/529, loss: 0.012248420156538486
2023-01-23 04:26:34.397289: step: 1728/529, loss: 0.0001103401227737777
2023-01-23 04:26:35.603950: step: 1732/529, loss: 0.006299782078713179
2023-01-23 04:26:36.778572: step: 1736/529, loss: 0.006045246031135321
2023-01-23 04:26:37.953198: step: 1740/529, loss: 0.000209808349609375
2023-01-23 04:26:39.142672: step: 1744/529, loss: 8.75473051564768e-05
2023-01-23 04:26:40.345263: step: 1748/529, loss: 0.001033020089380443
2023-01-23 04:26:41.536589: step: 1752/529, loss: 0.02100515365600586
2023-01-23 04:26:42.738280: step: 1756/529, loss: -7.057189577608369e-06
2023-01-23 04:26:43.961751: step: 1760/529, loss: -4.0054324017546605e-06
2023-01-23 04:26:45.108651: step: 1764/529, loss: 0.016878794878721237
2023-01-23 04:26:46.298972: step: 1768/529, loss: 0.0010881423950195312
2023-01-23 04:26:47.467429: step: 1772/529, loss: 1.6880036127986386e-05
2023-01-23 04:26:48.604429: step: 1776/529, loss: 0.06962118297815323
2023-01-23 04:26:49.786234: step: 1780/529, loss: 0.0021721841767430305
2023-01-23 04:26:50.990369: step: 1784/529, loss: 0.024844933301210403
2023-01-23 04:26:52.140830: step: 1788/529, loss: 5.321502612787299e-05
2023-01-23 04:26:53.338928: step: 1792/529, loss: 0.00026512148906476796
2023-01-23 04:26:54.520497: step: 1796/529, loss: 0.038497354835271835
2023-01-23 04:26:55.712639: step: 1800/529, loss: -9.5367431640625e-06
2023-01-23 04:26:56.885216: step: 1804/529, loss: 0.002333736512809992
2023-01-23 04:26:58.075703: step: 1808/529, loss: 9.393692016601562e-05
2023-01-23 04:26:59.301541: step: 1812/529, loss: 0.0052017210982739925
2023-01-23 04:27:00.462254: step: 1816/529, loss: 0.0008275986183434725
2023-01-23 04:27:01.624979: step: 1820/529, loss: 8.707046799827367e-05
2023-01-23 04:27:02.788525: step: 1824/529, loss: 0.008606362156569958
2023-01-23 04:27:04.029422: step: 1828/529, loss: 0.0002910613839048892
2023-01-23 04:27:05.202771: step: 1832/529, loss: 0.011018658056855202
2023-01-23 04:27:06.394812: step: 1836/529, loss: 2.975463939947076e-05
2023-01-23 04:27:07.622990: step: 1840/529, loss: 0.00067224504891783
2023-01-23 04:27:08.843752: step: 1844/529, loss: 0.00022230148897506297
2023-01-23 04:27:10.040364: step: 1848/529, loss: 2.937316821771674e-05
2023-01-23 04:27:11.267752: step: 1852/529, loss: 0.00011758803884731606
2023-01-23 04:27:12.460580: step: 1856/529, loss: 0.002803039737045765
2023-01-23 04:27:13.665893: step: 1860/529, loss: 0.0055374144576489925
2023-01-23 04:27:14.876223: step: 1864/529, loss: 0.0005592346424236894
2023-01-23 04:27:16.059276: step: 1868/529, loss: 0.02321653440594673
2023-01-23 04:27:17.270572: step: 1872/529, loss: 5.416870044427924e-05
2023-01-23 04:27:18.466778: step: 1876/529, loss: 0.002674198243767023
2023-01-23 04:27:19.686561: step: 1880/529, loss: -7.033347628748743e-07
2023-01-23 04:27:20.869077: step: 1884/529, loss: 0.6018469333648682
2023-01-23 04:27:22.062194: step: 1888/529, loss: 2.47955322265625e-05
2023-01-23 04:27:23.272229: step: 1892/529, loss: 0.001531410263851285
2023-01-23 04:27:24.504593: step: 1896/529, loss: 0.0004920900100842118
2023-01-23 04:27:25.691923: step: 1900/529, loss: 0.03541088104248047
2023-01-23 04:27:26.884120: step: 1904/529, loss: 0.00011940002150367945
2023-01-23 04:27:28.080795: step: 1908/529, loss: 0.00033655168954283
2023-01-23 04:27:29.293564: step: 1912/529, loss: 0.007105445954948664
2023-01-23 04:27:30.456079: step: 1916/529, loss: 6.008148375258315e-06
2023-01-23 04:27:31.651606: step: 1920/529, loss: 0.012304354459047318
2023-01-23 04:27:32.835566: step: 1924/529, loss: 9.250640687241685e-06
2023-01-23 04:27:34.028884: step: 1928/529, loss: 0.019771575927734375
2023-01-23 04:27:35.240001: step: 1932/529, loss: 0.0007734298706054688
2023-01-23 04:27:36.467257: step: 1936/529, loss: 0.001318645547144115
2023-01-23 04:27:37.642082: step: 1940/529, loss: 0.00352058419957757
2023-01-23 04:27:38.872218: step: 1944/529, loss: 3.4809113458322827e-06
2023-01-23 04:27:40.074537: step: 1948/529, loss: 0.0061775208450853825
2023-01-23 04:27:41.255899: step: 1952/529, loss: 0.0004104614199604839
2023-01-23 04:27:42.442749: step: 1956/529, loss: 3.0422212148550898e-05
2023-01-23 04:27:43.645983: step: 1960/529, loss: 0.0029163360595703125
2023-01-23 04:27:44.856593: step: 1964/529, loss: 0.0637754499912262
2023-01-23 04:27:46.034423: step: 1968/529, loss: 0.00018959045701194555
2023-01-23 04:27:47.164509: step: 1972/529, loss: 0.0035562515258789062
2023-01-23 04:27:48.326667: step: 1976/529, loss: 0.0045639993622899055
2023-01-23 04:27:49.535843: step: 1980/529, loss: 0.00011138916306663305
2023-01-23 04:27:50.727253: step: 1984/529, loss: 0.0001979827939067036
2023-01-23 04:27:51.934344: step: 1988/529, loss: 0.008693313226103783
2023-01-23 04:27:53.169180: step: 1992/529, loss: 0.029511641710996628
2023-01-23 04:27:54.389675: step: 1996/529, loss: 0.0002187728969147429
2023-01-23 04:27:55.577785: step: 2000/529, loss: 0.0008719444158487022
2023-01-23 04:27:56.795413: step: 2004/529, loss: -1.544952465337701e-05
2023-01-23 04:27:58.028499: step: 2008/529, loss: 0.002560138702392578
2023-01-23 04:27:59.234836: step: 2012/529, loss: 0.0032976153306663036
2023-01-23 04:28:00.464945: step: 2016/529, loss: 2.403259350103326e-05
2023-01-23 04:28:01.630526: step: 2020/529, loss: 0.025091171264648438
2023-01-23 04:28:02.844292: step: 2024/529, loss: -1.2016295841021929e-05
2023-01-23 04:28:04.036023: step: 2028/529, loss: -1.6117095583467744e-05
2023-01-23 04:28:05.244420: step: 2032/529, loss: 0.000480461138067767
2023-01-23 04:28:06.436152: step: 2036/529, loss: 0.003774297423660755
2023-01-23 04:28:07.626264: step: 2040/529, loss: 0.0020401000510901213
2023-01-23 04:28:08.809772: step: 2044/529, loss: 0.0016375541454181075
2023-01-23 04:28:09.985020: step: 2048/529, loss: 3.318786548334174e-05
2023-01-23 04:28:11.173209: step: 2052/529, loss: 0.002202844712883234
2023-01-23 04:28:12.315965: step: 2056/529, loss: 0.018551349639892578
2023-01-23 04:28:13.523181: step: 2060/529, loss: 0.03924274817109108
2023-01-23 04:28:14.695792: step: 2064/529, loss: 0.0285168644040823
2023-01-23 04:28:15.860942: step: 2068/529, loss: 0.0011410713195800781
2023-01-23 04:28:17.048746: step: 2072/529, loss: 9.841918654274195e-05
2023-01-23 04:28:18.249423: step: 2076/529, loss: 0.00019073484872933477
2023-01-23 04:28:19.445544: step: 2080/529, loss: -5.626678102998994e-06
2023-01-23 04:28:20.630428: step: 2084/529, loss: 0.00012016297114314511
2023-01-23 04:28:21.835324: step: 2088/529, loss: 0.005490493960678577
2023-01-23 04:28:23.048114: step: 2092/529, loss: 2.784729076665826e-05
2023-01-23 04:28:24.200933: step: 2096/529, loss: 5.435943421616685e-06
2023-01-23 04:28:25.403848: step: 2100/529, loss: 0.0028486251831054688
2023-01-23 04:28:26.569845: step: 2104/529, loss: 0.0009204864618368447
2023-01-23 04:28:27.779129: step: 2108/529, loss: 0.007889271713793278
2023-01-23 04:28:28.970059: step: 2112/529, loss: 0.00013446807861328125
2023-01-23 04:28:30.148435: step: 2116/529, loss: 9.040832810569555e-05
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.6095744680851064, 'r': 0.762982689747004, 'f1': 0.6777054997043169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6495098039215687, 'r': 0.7938885560215698, 'f1': 0.7144782960366675}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.625, 'r': 0.8333333333333334, 'f1': 0.7142857142857143}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.6181818181818182, 'r': 0.5396825396825397, 'f1': 0.576271186440678}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 04:29:13.569995: step: 4/529, loss: 2.19345088225964e-06
2023-01-23 04:29:14.756257: step: 8/529, loss: 0.00020184516324661672
2023-01-23 04:29:15.979573: step: 12/529, loss: 6.198883056640625e-06
2023-01-23 04:29:17.161640: step: 16/529, loss: 0.0007835388532839715
2023-01-23 04:29:18.406921: step: 20/529, loss: 0.044389914721250534
2023-01-23 04:29:19.602044: step: 24/529, loss: 0.039454080164432526
2023-01-23 04:29:20.799785: step: 28/529, loss: 0.00010643005225574598
2023-01-23 04:29:22.053580: step: 32/529, loss: 0.00015716553025413305
2023-01-23 04:29:23.289216: step: 36/529, loss: 0.022363662719726562
2023-01-23 04:29:24.458989: step: 40/529, loss: 0.005863761994987726
2023-01-23 04:29:25.634478: step: 44/529, loss: 0.00014147759065963328
2023-01-23 04:29:26.823867: step: 48/529, loss: 0.08831176906824112
2023-01-23 04:29:28.018554: step: 52/529, loss: 3.814697265625e-05
2023-01-23 04:29:29.223052: step: 56/529, loss: 0.07169074565172195
2023-01-23 04:29:30.418003: step: 60/529, loss: 0.001692104386165738
2023-01-23 04:29:31.587398: step: 64/529, loss: 6.389617919921875e-05
2023-01-23 04:29:32.810123: step: 68/529, loss: 4.57763671875e-05
2023-01-23 04:29:33.946019: step: 72/529, loss: 0.0007342338794842362
2023-01-23 04:29:35.158639: step: 76/529, loss: 0.006405449006706476
2023-01-23 04:29:36.340438: step: 80/529, loss: 0.0009681701776571572
2023-01-23 04:29:37.543484: step: 84/529, loss: 0.04061546549201012
2023-01-23 04:29:38.709533: step: 88/529, loss: 0.0011108398903161287
2023-01-23 04:29:39.886933: step: 92/529, loss: 0.0007769108051434159
2023-01-23 04:29:41.092710: step: 96/529, loss: 0.0421789214015007
2023-01-23 04:29:42.252374: step: 100/529, loss: 0.00013875961303710938
2023-01-23 04:29:43.507891: step: 104/529, loss: 2.0980833141948096e-06
2023-01-23 04:29:44.718511: step: 108/529, loss: 5.0163271225756034e-05
2023-01-23 04:29:45.919236: step: 112/529, loss: 0.0036340714432299137
2023-01-23 04:29:47.085826: step: 116/529, loss: 1.7547608877066523e-05
2023-01-23 04:29:48.282060: step: 120/529, loss: 0.00015993117995094508
2023-01-23 04:29:49.463588: step: 124/529, loss: 0.011015511117875576
2023-01-23 04:29:50.671553: step: 128/529, loss: 0.000583648681640625
2023-01-23 04:29:51.825185: step: 132/529, loss: 3.045797348022461e-05
2023-01-23 04:29:53.002454: step: 136/529, loss: 0.0003021717129740864
2023-01-23 04:29:54.213964: step: 140/529, loss: 0.0018939971923828125
2023-01-23 04:29:55.420431: step: 144/529, loss: 2.365112231927924e-05
2023-01-23 04:29:56.572732: step: 148/529, loss: 1.6450881958007812e-05
2023-01-23 04:29:57.760381: step: 152/529, loss: 5.507469177246094e-05
2023-01-23 04:29:58.941405: step: 156/529, loss: 0.004967355635017157
2023-01-23 04:30:00.191813: step: 160/529, loss: 1.7166138377433526e-06
2023-01-23 04:30:01.370691: step: 164/529, loss: 0.00013780595327261835
2023-01-23 04:30:02.505432: step: 168/529, loss: 0.0017105103470385075
2023-01-23 04:30:03.702975: step: 172/529, loss: 0.015952683985233307
2023-01-23 04:30:04.887575: step: 176/529, loss: 0.002684688428416848
2023-01-23 04:30:06.063913: step: 180/529, loss: 5.092620995128527e-05
2023-01-23 04:30:07.263949: step: 184/529, loss: 3.1280520488508046e-05
2023-01-23 04:30:08.439886: step: 188/529, loss: 0.03620586544275284
2023-01-23 04:30:09.624840: step: 192/529, loss: 1.6307831174344756e-05
2023-01-23 04:30:10.811128: step: 196/529, loss: 3.2424929941043956e-06
2023-01-23 04:30:11.965019: step: 200/529, loss: 0.0006960869068279862
2023-01-23 04:30:13.103901: step: 204/529, loss: 0.00019054414588026702
2023-01-23 04:30:14.274206: step: 208/529, loss: 0.0035186768509447575
2023-01-23 04:30:15.458617: step: 212/529, loss: -2.021789623540826e-05
2023-01-23 04:30:16.691566: step: 216/529, loss: 0.0003067016659770161
2023-01-23 04:30:17.876850: step: 220/529, loss: 0.0003581047058105469
2023-01-23 04:30:19.078471: step: 224/529, loss: 0.010175704956054688
2023-01-23 04:30:20.278397: step: 228/529, loss: 0.00035562514676712453
2023-01-23 04:30:21.487887: step: 232/529, loss: 0.0033266067039221525
2023-01-23 04:30:22.674883: step: 236/529, loss: 0.02343006245791912
2023-01-23 04:30:23.862308: step: 240/529, loss: 0.00012750625319313258
2023-01-23 04:30:25.066791: step: 244/529, loss: 0.00013065338134765625
2023-01-23 04:30:26.267877: step: 248/529, loss: 0.000347137451171875
2023-01-23 04:30:27.470373: step: 252/529, loss: 0.00453033484518528
2023-01-23 04:30:28.653583: step: 256/529, loss: 0.00041685104952193797
2023-01-23 04:30:29.828893: step: 260/529, loss: 0.0001924514799611643
2023-01-23 04:30:31.015875: step: 264/529, loss: 0.00046253204345703125
2023-01-23 04:30:32.208721: step: 268/529, loss: 3.24249267578125e-05
2023-01-23 04:30:33.411855: step: 272/529, loss: 0.0029591561760753393
2023-01-23 04:30:34.600831: step: 276/529, loss: 5.5313107623078395e-06
2023-01-23 04:30:35.764061: step: 280/529, loss: 9.34600848268019e-06
2023-01-23 04:30:36.999225: step: 284/529, loss: 0.00013322829909157008
2023-01-23 04:30:38.140897: step: 288/529, loss: 0.0007555008050985634
2023-01-23 04:30:39.339772: step: 292/529, loss: 0.005958748050034046
2023-01-23 04:30:40.492534: step: 296/529, loss: 0.0029787064995616674
2023-01-23 04:30:41.702754: step: 300/529, loss: 0.000217437744140625
2023-01-23 04:30:42.895858: step: 304/529, loss: 2.765655517578125e-05
2023-01-23 04:30:44.082150: step: 308/529, loss: 0.018631553277373314
2023-01-23 04:30:45.258007: step: 312/529, loss: 0.0018231152789667249
2023-01-23 04:30:46.491529: step: 316/529, loss: 0.0012628554832190275
2023-01-23 04:30:47.712899: step: 320/529, loss: 0.0006187438848428428
2023-01-23 04:30:48.907757: step: 324/529, loss: 0.0005594253307208419
2023-01-23 04:30:50.062814: step: 328/529, loss: 0.00259742746129632
2023-01-23 04:30:51.234326: step: 332/529, loss: 0.0005500793922692537
2023-01-23 04:30:52.441659: step: 336/529, loss: 0.0007852554554119706
2023-01-23 04:30:53.651981: step: 340/529, loss: 7.62939453125e-06
2023-01-23 04:30:54.837547: step: 344/529, loss: 0.002188110491260886
2023-01-23 04:30:56.062726: step: 348/529, loss: 0.0006380081758834422
2023-01-23 04:30:57.274909: step: 352/529, loss: 0.0019458772148936987
2023-01-23 04:30:58.453300: step: 356/529, loss: 2.86102294921875e-06
2023-01-23 04:30:59.618365: step: 360/529, loss: 0.0468907356262207
2023-01-23 04:31:00.803733: step: 364/529, loss: 0.0018169403774663806
2023-01-23 04:31:01.986901: step: 368/529, loss: 0.0011387824779376388
2023-01-23 04:31:03.183940: step: 372/529, loss: 0.0018321990501135588
2023-01-23 04:31:04.358674: step: 376/529, loss: 0.0001605987490620464
2023-01-23 04:31:05.537772: step: 380/529, loss: 0.0016286849277094007
2023-01-23 04:31:06.701271: step: 384/529, loss: 0.0016176224453374743
2023-01-23 04:31:07.917682: step: 388/529, loss: 0.004326724912971258
2023-01-23 04:31:09.108157: step: 392/529, loss: 0.04388561472296715
2023-01-23 04:31:10.381335: step: 396/529, loss: 1.5735626220703125e-05
2023-01-23 04:31:11.614120: step: 400/529, loss: 0.0029001235961914062
2023-01-23 04:31:12.852961: step: 404/529, loss: 0.016232872381806374
2023-01-23 04:31:14.008246: step: 408/529, loss: 0.0008089065668173134
2023-01-23 04:31:15.200282: step: 412/529, loss: 8.707046072231606e-05
2023-01-23 04:31:16.362356: step: 416/529, loss: 0.0002419471857137978
2023-01-23 04:31:17.556892: step: 420/529, loss: 0.0007030487176962197
2023-01-23 04:31:18.766060: step: 424/529, loss: 0.03721580654382706
2023-01-23 04:31:19.997537: step: 428/529, loss: 0.0026134492363780737
2023-01-23 04:31:21.208192: step: 432/529, loss: 0.025157354772090912
2023-01-23 04:31:22.437662: step: 436/529, loss: 0.0016920090420171618
2023-01-23 04:31:23.663280: step: 440/529, loss: 0.0004112243477720767
2023-01-23 04:31:24.893647: step: 444/529, loss: 0.052002910524606705
2023-01-23 04:31:26.055274: step: 448/529, loss: 0.0019020081963390112
2023-01-23 04:31:27.295747: step: 452/529, loss: 0.014834118075668812
2023-01-23 04:31:28.490888: step: 456/529, loss: 3.967285010730848e-05
2023-01-23 04:31:29.692252: step: 460/529, loss: 4.2724612285383046e-05
2023-01-23 04:31:30.863531: step: 464/529, loss: 0.00010051727440441027
2023-01-23 04:31:32.112995: step: 468/529, loss: 0.011730194091796875
2023-01-23 04:31:33.277203: step: 472/529, loss: 6.656646291958168e-05
2023-01-23 04:31:34.491574: step: 476/529, loss: 1.33514404296875e-05
2023-01-23 04:31:35.678052: step: 480/529, loss: 1.0585784366412554e-05
2023-01-23 04:31:36.817288: step: 484/529, loss: 2.47955313170678e-06
2023-01-23 04:31:38.045444: step: 488/529, loss: 0.010639572516083717
2023-01-23 04:31:39.242423: step: 492/529, loss: 0.02635822258889675
2023-01-23 04:31:40.442643: step: 496/529, loss: 1.773834264895413e-05
2023-01-23 04:31:41.613009: step: 500/529, loss: 0.0062191965989768505
2023-01-23 04:31:42.768373: step: 504/529, loss: 0.0003980636829510331
2023-01-23 04:31:43.968176: step: 508/529, loss: 0.0029202462173998356
2023-01-23 04:31:45.165017: step: 512/529, loss: 0.0009311676258221269
2023-01-23 04:31:46.357696: step: 516/529, loss: 5.636215428239666e-05
2023-01-23 04:31:47.575056: step: 520/529, loss: 0.04598722606897354
2023-01-23 04:31:48.766767: step: 524/529, loss: 7.295608611457283e-06
2023-01-23 04:31:49.972476: step: 528/529, loss: 0.011223316192626953
2023-01-23 04:31:51.185531: step: 532/529, loss: 0.003146362490952015
2023-01-23 04:31:52.415294: step: 536/529, loss: 0.00026025774423033
2023-01-23 04:31:53.582740: step: 540/529, loss: 0.00035305024357512593
2023-01-23 04:31:54.786461: step: 544/529, loss: 0.00010547638521529734
2023-01-23 04:31:55.981370: step: 548/529, loss: 2.3078917365637608e-05
2023-01-23 04:31:57.158442: step: 552/529, loss: -1.3351439065445447e-06
2023-01-23 04:31:58.349263: step: 556/529, loss: 0.0007143020629882812
2023-01-23 04:31:59.543001: step: 560/529, loss: 0.0004932403680868447
2023-01-23 04:32:00.719889: step: 564/529, loss: 5.855560448253527e-05
2023-01-23 04:32:01.942757: step: 568/529, loss: 0.008263015188276768
2023-01-23 04:32:03.146492: step: 572/529, loss: 0.0734064131975174
2023-01-23 04:32:04.332990: step: 576/529, loss: 0.0005625725025311112
2023-01-23 04:32:05.571756: step: 580/529, loss: 3.757476952159777e-05
2023-01-23 04:32:06.743159: step: 584/529, loss: 0.0033500671852380037
2023-01-23 04:32:07.933811: step: 588/529, loss: 0.0004800796741619706
2023-01-23 04:32:09.130761: step: 592/529, loss: 0.005219078157097101
2023-01-23 04:32:10.311222: step: 596/529, loss: 0.0011716842418536544
2023-01-23 04:32:11.498588: step: 600/529, loss: 0.0002229690580861643
2023-01-23 04:32:12.709876: step: 604/529, loss: 0.00015525818162132055
2023-01-23 04:32:13.875969: step: 608/529, loss: 1.5258789289873675e-06
2023-01-23 04:32:15.057958: step: 612/529, loss: 0.0039768218994140625
2023-01-23 04:32:16.246065: step: 616/529, loss: 0.00028896331787109375
2023-01-23 04:32:17.401890: step: 620/529, loss: 0.0003613472217693925
2023-01-23 04:32:18.613778: step: 624/529, loss: 0.00010528565326239914
2023-01-23 04:32:19.786993: step: 628/529, loss: 0.018291091546416283
2023-01-23 04:32:20.934782: step: 632/529, loss: 0.005200195126235485
2023-01-23 04:32:22.120090: step: 636/529, loss: 0.001433086465112865
2023-01-23 04:32:23.315449: step: 640/529, loss: 0.0013350486988201737
2023-01-23 04:32:24.533141: step: 644/529, loss: 0.031363680958747864
2023-01-23 04:32:25.702343: step: 648/529, loss: 4.196166628389619e-06
2023-01-23 04:32:26.873530: step: 652/529, loss: 0.0012488365173339844
2023-01-23 04:32:28.043391: step: 656/529, loss: 3.719329833984375e-05
2023-01-23 04:32:29.259589: step: 660/529, loss: 0.005908107850700617
2023-01-23 04:32:30.461506: step: 664/529, loss: 0.00012736320786643773
2023-01-23 04:32:31.634769: step: 668/529, loss: 1.0204315913142636e-05
2023-01-23 04:32:32.798941: step: 672/529, loss: 0.00017976762319449335
2023-01-23 04:32:33.961186: step: 676/529, loss: 0.024214552715420723
2023-01-23 04:32:35.171312: step: 680/529, loss: 0.008968067355453968
2023-01-23 04:32:36.419550: step: 684/529, loss: 0.0034555436577647924
2023-01-23 04:32:37.605410: step: 688/529, loss: 0.012199974618852139
2023-01-23 04:32:38.842281: step: 692/529, loss: 0.0038137435913085938
2023-01-23 04:32:40.108440: step: 696/529, loss: 0.000660324061755091
2023-01-23 04:32:41.292620: step: 700/529, loss: 0.00025405886117368937
2023-01-23 04:32:42.499586: step: 704/529, loss: 0.3003028929233551
2023-01-23 04:32:43.699031: step: 708/529, loss: 1.5735626220703125e-05
2023-01-23 04:32:44.879620: step: 712/529, loss: -6.9618222369172145e-06
2023-01-23 04:32:46.093838: step: 716/529, loss: 1.955032530531753e-05
2023-01-23 04:32:47.297418: step: 720/529, loss: 4.38690176451928e-06
2023-01-23 04:32:48.462373: step: 724/529, loss: 6.675720669591101e-06
2023-01-23 04:32:49.624818: step: 728/529, loss: 0.013900566846132278
2023-01-23 04:32:50.800896: step: 732/529, loss: 0.00011157989501953125
2023-01-23 04:32:51.966920: step: 736/529, loss: 0.005905533209443092
2023-01-23 04:32:53.165594: step: 740/529, loss: 1.2016297660011332e-05
2023-01-23 04:32:54.371019: step: 744/529, loss: 5.3739546274300665e-05
2023-01-23 04:32:55.560018: step: 748/529, loss: 0.11075859516859055
2023-01-23 04:32:56.747002: step: 752/529, loss: 9.603500802768394e-05
2023-01-23 04:32:57.899144: step: 756/529, loss: 0.0001447677641408518
2023-01-23 04:32:59.094228: step: 760/529, loss: 9.059906005859375e-06
2023-01-23 04:33:00.297000: step: 764/529, loss: 0.013219070620834827
2023-01-23 04:33:01.485054: step: 768/529, loss: -9.34600848268019e-06
2023-01-23 04:33:02.692403: step: 772/529, loss: 0.0007427215459756553
2023-01-23 04:33:03.880870: step: 776/529, loss: 0.009543133899569511
2023-01-23 04:33:05.098108: step: 780/529, loss: 8.897781663108617e-05
2023-01-23 04:33:06.300486: step: 784/529, loss: 0.011541747488081455
2023-01-23 04:33:07.458461: step: 788/529, loss: 0.0004888534313067794
2023-01-23 04:33:08.694168: step: 792/529, loss: 0.0622706413269043
2023-01-23 04:33:09.882746: step: 796/529, loss: 1.4114379155216739e-05
2023-01-23 04:33:11.117684: step: 800/529, loss: 0.0014701844193041325
2023-01-23 04:33:12.277406: step: 804/529, loss: 0.0001698732521617785
2023-01-23 04:33:13.469975: step: 808/529, loss: 0.003596401307731867
2023-01-23 04:33:14.684035: step: 812/529, loss: 0.0003406524774618447
2023-01-23 04:33:15.864985: step: 816/529, loss: 0.017597390338778496
2023-01-23 04:33:17.003905: step: 820/529, loss: 1.182556115963962e-05
2023-01-23 04:33:18.189732: step: 824/529, loss: 0.00218715681694448
2023-01-23 04:33:19.349473: step: 828/529, loss: 0.029137611389160156
2023-01-23 04:33:20.606910: step: 832/529, loss: 0.02660808525979519
2023-01-23 04:33:21.799774: step: 836/529, loss: 0.017335321754217148
2023-01-23 04:33:22.991379: step: 840/529, loss: 0.00018177033052779734
2023-01-23 04:33:24.186698: step: 844/529, loss: 0.0019325255416333675
2023-01-23 04:33:25.391364: step: 848/529, loss: 0.00020437240891624242
2023-01-23 04:33:26.576662: step: 852/529, loss: 0.005922890268266201
2023-01-23 04:33:27.778825: step: 856/529, loss: 0.0001552104949951172
2023-01-23 04:33:28.970289: step: 860/529, loss: 0.01691455766558647
2023-01-23 04:33:30.162134: step: 864/529, loss: 0.0006818771362304688
2023-01-23 04:33:31.293072: step: 868/529, loss: -4.291534423828125e-06
2023-01-23 04:33:32.547633: step: 872/529, loss: 0.0014144896995276213
2023-01-23 04:33:33.745704: step: 876/529, loss: 1.3446808225126006e-05
2023-01-23 04:33:34.984546: step: 880/529, loss: 0.00864410400390625
2023-01-23 04:33:36.221896: step: 884/529, loss: 0.01627349853515625
2023-01-23 04:33:37.413817: step: 888/529, loss: 0.00018825530423782766
2023-01-23 04:33:38.668753: step: 892/529, loss: 7.820130122127011e-06
2023-01-23 04:33:39.842707: step: 896/529, loss: 0.7037311792373657
2023-01-23 04:33:41.015087: step: 900/529, loss: 0.0022602081298828125
2023-01-23 04:33:42.261559: step: 904/529, loss: 0.05023917928338051
2023-01-23 04:33:43.462441: step: 908/529, loss: 0.00010004043724620715
2023-01-23 04:33:44.629724: step: 912/529, loss: 0.0032807348761707544
2023-01-23 04:33:45.839444: step: 916/529, loss: 0.01593475230038166
2023-01-23 04:33:47.064469: step: 920/529, loss: 0.00019874573627021164
2023-01-23 04:33:48.298017: step: 924/529, loss: 0.017996979877352715
2023-01-23 04:33:49.480080: step: 928/529, loss: 0.005619811825454235
2023-01-23 04:33:50.697087: step: 932/529, loss: 4.720688230008818e-05
2023-01-23 04:33:51.899216: step: 936/529, loss: 3.43322744811303e-06
2023-01-23 04:33:53.113699: step: 940/529, loss: 6.885529001010582e-05
2023-01-23 04:33:54.237869: step: 944/529, loss: 0.0009704590192995965
2023-01-23 04:33:55.467195: step: 948/529, loss: 0.0012825012672692537
2023-01-23 04:33:56.659775: step: 952/529, loss: 0.0008444786071777344
2023-01-23 04:33:57.856846: step: 956/529, loss: 0.007120418827980757
2023-01-23 04:33:59.036861: step: 960/529, loss: 0.0002723693905863911
2023-01-23 04:34:00.209451: step: 964/529, loss: 0.00042386056156829
2023-01-23 04:34:01.412269: step: 968/529, loss: 1.52587890625e-05
2023-01-23 04:34:02.599713: step: 972/529, loss: 0.00051288609392941
2023-01-23 04:34:03.793038: step: 976/529, loss: 0.00043234828626737
2023-01-23 04:34:04.977467: step: 980/529, loss: 0.0001903533993754536
2023-01-23 04:34:06.176376: step: 984/529, loss: 0.005395126529037952
2023-01-23 04:34:07.357654: step: 988/529, loss: 0.020402908325195312
2023-01-23 04:34:08.538738: step: 992/529, loss: 1.7261505490751006e-05
2023-01-23 04:34:09.743603: step: 996/529, loss: 0.0001523971586721018
2023-01-23 04:34:10.952477: step: 1000/529, loss: 3.089904930675402e-05
2023-01-23 04:34:12.176755: step: 1004/529, loss: 0.00013556479825638235
2023-01-23 04:34:13.365388: step: 1008/529, loss: 0.00023975371732376516
2023-01-23 04:34:14.614047: step: 1012/529, loss: 0.0002521514834370464
2023-01-23 04:34:15.803274: step: 1016/529, loss: 0.05911846086382866
2023-01-23 04:34:17.009445: step: 1020/529, loss: 2.0027162008773303e-06
2023-01-23 04:34:18.220007: step: 1024/529, loss: 5.7220458984375e-06
2023-01-23 04:34:19.413472: step: 1028/529, loss: 0.013902951031923294
2023-01-23 04:34:20.656020: step: 1032/529, loss: 0.0017786026000976562
2023-01-23 04:34:21.839068: step: 1036/529, loss: 0.0005986213800497353
2023-01-23 04:34:23.049934: step: 1040/529, loss: 9.130835678661242e-05
2023-01-23 04:34:24.279560: step: 1044/529, loss: 0.04312162846326828
2023-01-23 04:34:25.473258: step: 1048/529, loss: 0.002151107881218195
2023-01-23 04:34:26.714284: step: 1052/529, loss: 0.027092933654785156
2023-01-23 04:34:27.891738: step: 1056/529, loss: 7.82012921263231e-06
2023-01-23 04:34:29.081153: step: 1060/529, loss: 0.019725419580936432
2023-01-23 04:34:30.276512: step: 1064/529, loss: 0.00010414123971713707
2023-01-23 04:34:31.475863: step: 1068/529, loss: 0.005253935232758522
2023-01-23 04:34:32.731498: step: 1072/529, loss: 0.43947526812553406
2023-01-23 04:34:33.926013: step: 1076/529, loss: 0.004548931494355202
2023-01-23 04:34:35.100320: step: 1080/529, loss: 0.059807490557432175
2023-01-23 04:34:36.337248: step: 1084/529, loss: 0.004552745725959539
2023-01-23 04:34:37.518495: step: 1088/529, loss: 0.010261917486786842
2023-01-23 04:34:38.732333: step: 1092/529, loss: 0.0020591735374182463
2023-01-23 04:34:39.898723: step: 1096/529, loss: 0.06018352508544922
2023-01-23 04:34:41.062363: step: 1100/529, loss: 0.02090167999267578
2023-01-23 04:34:42.309529: step: 1104/529, loss: 0.2931070327758789
2023-01-23 04:34:43.470813: step: 1108/529, loss: -4.95910626341356e-06
2023-01-23 04:34:44.670395: step: 1112/529, loss: 0.00036659243050962687
2023-01-23 04:34:45.876392: step: 1116/529, loss: 0.00027647020760923624
2023-01-23 04:34:47.077375: step: 1120/529, loss: 6.29425048828125e-05
2023-01-23 04:34:48.275834: step: 1124/529, loss: 3.814697265625e-06
2023-01-23 04:34:49.464831: step: 1128/529, loss: 0.003273487091064453
2023-01-23 04:34:50.720750: step: 1132/529, loss: 0.00039396286592818797
2023-01-23 04:34:51.941446: step: 1136/529, loss: 0.000423431396484375
2023-01-23 04:34:53.132148: step: 1140/529, loss: 0.00012474060349632055
2023-01-23 04:34:54.329076: step: 1144/529, loss: 0.008915329352021217
2023-01-23 04:34:55.619377: step: 1148/529, loss: 3.185272362316027e-05
2023-01-23 04:34:56.808711: step: 1152/529, loss: 0.00014762878709007055
2023-01-23 04:34:57.984519: step: 1156/529, loss: 0.031037140637636185
2023-01-23 04:34:59.180597: step: 1160/529, loss: 0.005969238001853228
2023-01-23 04:35:00.382668: step: 1164/529, loss: 0.0012039184803143144
2023-01-23 04:35:01.590742: step: 1168/529, loss: 6.88552827341482e-05
2023-01-23 04:35:02.772776: step: 1172/529, loss: 0.004775619599968195
2023-01-23 04:35:03.947817: step: 1176/529, loss: 0.0002693176211323589
2023-01-23 04:35:05.130179: step: 1180/529, loss: -1.33514404296875e-05
2023-01-23 04:35:06.352193: step: 1184/529, loss: 0.02767951600253582
2023-01-23 04:35:07.564950: step: 1188/529, loss: 0.0003884315665345639
2023-01-23 04:35:08.750418: step: 1192/529, loss: 1.5258789289873675e-06
2023-01-23 04:35:09.942161: step: 1196/529, loss: 1.0871887752728071e-05
2023-01-23 04:35:11.094303: step: 1200/529, loss: 8.678435733600054e-06
2023-01-23 04:35:12.274476: step: 1204/529, loss: 0.01877574808895588
2023-01-23 04:35:13.486707: step: 1208/529, loss: 0.00018076896958518773
2023-01-23 04:35:14.720024: step: 1212/529, loss: 0.00426936149597168
2023-01-23 04:35:15.873928: step: 1216/529, loss: 9.52720656641759e-05
2023-01-23 04:35:17.055071: step: 1220/529, loss: 0.011672401800751686
2023-01-23 04:35:18.216273: step: 1224/529, loss: 2.9563905172835803e-06
2023-01-23 04:35:19.394898: step: 1228/529, loss: 3.290176209702622e-06
2023-01-23 04:35:20.577294: step: 1232/529, loss: 3.814697265625e-06
2023-01-23 04:35:21.789493: step: 1236/529, loss: 0.0011616707779467106
2023-01-23 04:35:22.987332: step: 1240/529, loss: 0.006520652677863836
2023-01-23 04:35:24.177306: step: 1244/529, loss: 2.014822006225586
2023-01-23 04:35:25.388431: step: 1248/529, loss: 0.0009389877086505294
2023-01-23 04:35:26.619222: step: 1252/529, loss: 0.0013923646183684468
2023-01-23 04:35:27.821999: step: 1256/529, loss: 0.011000634171068668
2023-01-23 04:35:28.986647: step: 1260/529, loss: 0.00026683806208893657
2023-01-23 04:35:30.174042: step: 1264/529, loss: 0.00042724609375
2023-01-23 04:35:31.400537: step: 1268/529, loss: 0.0004532337188720703
2023-01-23 04:35:32.595403: step: 1272/529, loss: 0.037917040288448334
2023-01-23 04:35:33.787589: step: 1276/529, loss: 0.002945518586784601
2023-01-23 04:35:35.023143: step: 1280/529, loss: 6.513595872092992e-05
2023-01-23 04:35:36.213245: step: 1284/529, loss: 0.00044422148494049907
2023-01-23 04:35:37.404822: step: 1288/529, loss: 6.732940528308973e-05
2023-01-23 04:35:38.599567: step: 1292/529, loss: 0.010332870297133923
2023-01-23 04:35:39.821936: step: 1296/529, loss: 3.24249267578125e-05
2023-01-23 04:35:41.005275: step: 1300/529, loss: 0.0005731582641601562
2023-01-23 04:35:42.189121: step: 1304/529, loss: 4.405975414556451e-05
2023-01-23 04:35:43.377842: step: 1308/529, loss: 0.009279823862016201
2023-01-23 04:35:44.573648: step: 1312/529, loss: 0.011157035827636719
2023-01-23 04:35:45.746683: step: 1316/529, loss: 0.0017451286548748612
2023-01-23 04:35:46.924484: step: 1320/529, loss: 0.0003120422479696572
2023-01-23 04:35:48.114077: step: 1324/529, loss: 0.0662609115242958
2023-01-23 04:35:49.279778: step: 1328/529, loss: 8.163452002918348e-05
2023-01-23 04:35:50.435075: step: 1332/529, loss: 0.0007122606039047241
2023-01-23 04:35:51.604864: step: 1336/529, loss: 0.00018515587726142257
2023-01-23 04:35:52.818376: step: 1340/529, loss: 0.00019779204740189016
2023-01-23 04:35:54.034890: step: 1344/529, loss: 3.204345557605848e-05
2023-01-23 04:35:55.247450: step: 1348/529, loss: 9.31739850784652e-05
2023-01-23 04:35:56.468546: step: 1352/529, loss: 0.017632009461522102
2023-01-23 04:35:57.676439: step: 1356/529, loss: 0.033524226397275925
2023-01-23 04:35:58.905080: step: 1360/529, loss: 0.001314353896304965
2023-01-23 04:36:00.079759: step: 1364/529, loss: 1.9931794668082148e-05
2023-01-23 04:36:01.312024: step: 1368/529, loss: 0.0006610870477743447
2023-01-23 04:36:02.488629: step: 1372/529, loss: 0.00023546218289993703
2023-01-23 04:36:03.659222: step: 1376/529, loss: 0.0006831169012002647
2023-01-23 04:36:04.890345: step: 1380/529, loss: 0.0016157150967046618
2023-01-23 04:36:06.070970: step: 1384/529, loss: 0.0009798050159588456
2023-01-23 04:36:07.263725: step: 1388/529, loss: 0.00011453629122115672
2023-01-23 04:36:08.496336: step: 1392/529, loss: 0.00032958982046693563
2023-01-23 04:36:09.651995: step: 1396/529, loss: 2.212524486822076e-05
2023-01-23 04:36:10.853633: step: 1400/529, loss: 0.12508058547973633
2023-01-23 04:36:12.037274: step: 1404/529, loss: 0.0006109238020144403
2023-01-23 04:36:13.258661: step: 1408/529, loss: 0.0005239486927166581
2023-01-23 04:36:14.446141: step: 1412/529, loss: 8.621215965831652e-05
2023-01-23 04:36:15.646149: step: 1416/529, loss: 0.001671648002229631
2023-01-23 04:36:16.867722: step: 1420/529, loss: 0.0018751145107671618
2023-01-23 04:36:18.108605: step: 1424/529, loss: 1.9168854123563506e-05
2023-01-23 04:36:19.318937: step: 1428/529, loss: 0.0021585465874522924
2023-01-23 04:36:20.505709: step: 1432/529, loss: 0.0243548396974802
2023-01-23 04:36:21.694523: step: 1436/529, loss: 0.019945433363318443
2023-01-23 04:36:22.943598: step: 1440/529, loss: -4.9591067181609105e-06
2023-01-23 04:36:24.196584: step: 1444/529, loss: 0.001189422677271068
2023-01-23 04:36:25.432883: step: 1448/529, loss: 0.010272311978042126
2023-01-23 04:36:26.617482: step: 1452/529, loss: 0.00023288727970793843
2023-01-23 04:36:27.853234: step: 1456/529, loss: 0.01434249896556139
2023-01-23 04:36:29.024664: step: 1460/529, loss: 0.0005619525909423828
2023-01-23 04:36:30.211986: step: 1464/529, loss: 0.0018398285610601306
2023-01-23 04:36:31.387841: step: 1468/529, loss: 0.0023834705352783203
2023-01-23 04:36:32.546414: step: 1472/529, loss: 0.00046749116154387593
2023-01-23 04:36:33.746397: step: 1476/529, loss: 0.00139198312535882
2023-01-23 04:36:34.957719: step: 1480/529, loss: 0.0017762182978913188
2023-01-23 04:36:36.178756: step: 1484/529, loss: 3.7604360580444336
2023-01-23 04:36:37.326790: step: 1488/529, loss: 0.00020956993103027344
2023-01-23 04:36:38.509049: step: 1492/529, loss: 5.569458153331652e-05
2023-01-23 04:36:39.751162: step: 1496/529, loss: 0.0012048721546307206
2023-01-23 04:36:40.929065: step: 1500/529, loss: 0.0003140449698548764
2023-01-23 04:36:42.128317: step: 1504/529, loss: 0.0001008987455861643
2023-01-23 04:36:43.324026: step: 1508/529, loss: -4.887580871582031e-06
2023-01-23 04:36:44.540558: step: 1512/529, loss: -2.6035308110294864e-05
2023-01-23 04:36:45.735103: step: 1516/529, loss: 0.0016532897716388106
2023-01-23 04:36:46.948951: step: 1520/529, loss: 0.009258843027055264
2023-01-23 04:36:48.171395: step: 1524/529, loss: 0.027378082275390625
2023-01-23 04:36:49.356040: step: 1528/529, loss: 0.12286939471960068
2023-01-23 04:36:50.610628: step: 1532/529, loss: 2.155303991457913e-05
2023-01-23 04:36:51.762301: step: 1536/529, loss: 0.00108509068377316
2023-01-23 04:36:52.963714: step: 1540/529, loss: -8.1300731835654e-06
2023-01-23 04:36:54.153794: step: 1544/529, loss: 5.168914867681451e-05
2023-01-23 04:36:55.331150: step: 1548/529, loss: 0.0027379037346690893
2023-01-23 04:36:56.537415: step: 1552/529, loss: 0.05477733537554741
2023-01-23 04:36:57.725603: step: 1556/529, loss: 2.261141777038574
2023-01-23 04:36:58.886478: step: 1560/529, loss: 6.10351571594947e-06
2023-01-23 04:37:00.064521: step: 1564/529, loss: 0.007138634100556374
2023-01-23 04:37:01.269116: step: 1568/529, loss: 0.004919338505715132
2023-01-23 04:37:02.488042: step: 1572/529, loss: 4.639625331037678e-05
2023-01-23 04:37:03.677087: step: 1576/529, loss: 3.24249276673072e-06
2023-01-23 04:37:04.842923: step: 1580/529, loss: 0.0007768631330691278
2023-01-23 04:37:06.008992: step: 1584/529, loss: 0.000610732997301966
2023-01-23 04:37:07.142228: step: 1588/529, loss: 0.0009853362571448088
2023-01-23 04:37:08.350256: step: 1592/529, loss: 0.004426336381584406
2023-01-23 04:37:09.600797: step: 1596/529, loss: 0.0009174346923828125
2023-01-23 04:37:10.793406: step: 1600/529, loss: 0.0124359130859375
2023-01-23 04:37:11.986556: step: 1604/529, loss: 0.02292346954345703
2023-01-23 04:37:13.199632: step: 1608/529, loss: 0.012574195861816406
2023-01-23 04:37:14.404509: step: 1612/529, loss: 0.0005159854772500694
2023-01-23 04:37:15.548671: step: 1616/529, loss: 0.0016510963905602694
2023-01-23 04:37:16.744858: step: 1620/529, loss: 0.0036033629439771175
2023-01-23 04:37:17.957463: step: 1624/529, loss: 2.899169885495212e-05
2023-01-23 04:37:19.155854: step: 1628/529, loss: 0.0020426749251782894
2023-01-23 04:37:20.357631: step: 1632/529, loss: 4.425048973644152e-05
2023-01-23 04:37:21.522649: step: 1636/529, loss: 0.0011596680851653218
2023-01-23 04:37:22.682067: step: 1640/529, loss: 2.2220612663659267e-05
2023-01-23 04:37:23.880541: step: 1644/529, loss: -1.0776519047794864e-05
2023-01-23 04:37:25.082237: step: 1648/529, loss: 0.025642015039920807
2023-01-23 04:37:26.291846: step: 1652/529, loss: 0.0025005340576171875
2023-01-23 04:37:27.509653: step: 1656/529, loss: 0.07654371112585068
2023-01-23 04:37:28.719521: step: 1660/529, loss: 0.18458519876003265
2023-01-23 04:37:29.905882: step: 1664/529, loss: 8.926392183639109e-05
2023-01-23 04:37:31.137648: step: 1668/529, loss: 0.009643793106079102
2023-01-23 04:37:32.296038: step: 1672/529, loss: 0.0016570091247558594
2023-01-23 04:37:33.487688: step: 1676/529, loss: 0.010727310553193092
2023-01-23 04:37:34.669993: step: 1680/529, loss: 2.237558328488376e-05
2023-01-23 04:37:35.852363: step: 1684/529, loss: 0.2558395564556122
2023-01-23 04:37:37.051670: step: 1688/529, loss: 0.07726965099573135
2023-01-23 04:37:38.283920: step: 1692/529, loss: 0.0008657455327920616
2023-01-23 04:37:39.451751: step: 1696/529, loss: 0.0005592346424236894
2023-01-23 04:37:40.696601: step: 1700/529, loss: 0.02435169368982315
2023-01-23 04:37:41.975792: step: 1704/529, loss: 0.006641578394919634
2023-01-23 04:37:43.177755: step: 1708/529, loss: 0.0005907058948650956
2023-01-23 04:37:44.336567: step: 1712/529, loss: 0.002627659123390913
2023-01-23 04:37:45.527373: step: 1716/529, loss: 0.012280846014618874
2023-01-23 04:37:46.719084: step: 1720/529, loss: 1.6117095583467744e-05
2023-01-23 04:37:47.909414: step: 1724/529, loss: 0.047978781163692474
2023-01-23 04:37:49.142069: step: 1728/529, loss: 0.0007720947614870965
2023-01-23 04:37:50.332817: step: 1732/529, loss: -1.5258788153005298e-06
2023-01-23 04:37:51.515527: step: 1736/529, loss: 2.0885467165498994e-05
2023-01-23 04:37:52.793586: step: 1740/529, loss: 0.01361169759184122
2023-01-23 04:37:54.014695: step: 1744/529, loss: 9.212493750965223e-05
2023-01-23 04:37:55.217125: step: 1748/529, loss: 1.5211105164780747e-05
2023-01-23 04:37:56.443509: step: 1752/529, loss: 1.150965726992581e-05
2023-01-23 04:37:57.638569: step: 1756/529, loss: 0.002271461533382535
2023-01-23 04:37:58.828674: step: 1760/529, loss: 0.01685047149658203
2023-01-23 04:38:00.069900: step: 1764/529, loss: 0.0018886567559093237
2023-01-23 04:38:01.311043: step: 1768/529, loss: 0.015965841710567474
2023-01-23 04:38:02.527220: step: 1772/529, loss: 0.002438068389892578
2023-01-23 04:38:03.695114: step: 1776/529, loss: 0.0003922939649783075
2023-01-23 04:38:04.890485: step: 1780/529, loss: 0.0001739501894917339
2023-01-23 04:38:06.065136: step: 1784/529, loss: 0.00033779145451262593
2023-01-23 04:38:07.270353: step: 1788/529, loss: 0.0017832756275311112
2023-01-23 04:38:08.464454: step: 1792/529, loss: 0.00011749268014682457
2023-01-23 04:38:09.664225: step: 1796/529, loss: 4.730224463855848e-05
2023-01-23 04:38:10.877601: step: 1800/529, loss: 0.0010387421352788806
2023-01-23 04:38:12.065485: step: 1804/529, loss: 0.009067917242646217
2023-01-23 04:38:13.265764: step: 1808/529, loss: 0.0007368087535724044
2023-01-23 04:38:14.490608: step: 1812/529, loss: 6.289482553256676e-05
2023-01-23 04:38:15.692520: step: 1816/529, loss: 5.14984139954322e-06
2023-01-23 04:38:16.883074: step: 1820/529, loss: 0.00011310577974654734
2023-01-23 04:38:18.050658: step: 1824/529, loss: 1.773834264895413e-05
2023-01-23 04:38:19.253607: step: 1828/529, loss: 0.06255068629980087
2023-01-23 04:38:20.431893: step: 1832/529, loss: 0.0003951072576455772
2023-01-23 04:38:21.630449: step: 1836/529, loss: 0.0851929634809494
2023-01-23 04:38:22.835810: step: 1840/529, loss: 0.002176952548325062
2023-01-23 04:38:24.028145: step: 1844/529, loss: 0.0006973266135901213
2023-01-23 04:38:25.244020: step: 1848/529, loss: 0.011502456851303577
2023-01-23 04:38:26.447276: step: 1852/529, loss: 0.007765770424157381
2023-01-23 04:38:27.652330: step: 1856/529, loss: -6.103515261202119e-06
2023-01-23 04:38:28.837253: step: 1860/529, loss: 0.00012321471876930445
2023-01-23 04:38:30.016012: step: 1864/529, loss: 9.059906005859375e-06
2023-01-23 04:38:31.207390: step: 1868/529, loss: 0.015971088781952858
2023-01-23 04:38:32.405525: step: 1872/529, loss: 0.0037128927651792765
2023-01-23 04:38:33.618314: step: 1876/529, loss: 0.0021805763244628906
2023-01-23 04:38:34.820561: step: 1880/529, loss: 0.015220356173813343
2023-01-23 04:38:36.011528: step: 1884/529, loss: 0.00017452239990234375
2023-01-23 04:38:37.204978: step: 1888/529, loss: 0.0010402679909020662
2023-01-23 04:38:38.422123: step: 1892/529, loss: 0.0003410339413676411
2023-01-23 04:38:39.588824: step: 1896/529, loss: -2.9087066195643274e-06
2023-01-23 04:38:40.770506: step: 1900/529, loss: 0.010410022921860218
2023-01-23 04:38:41.956585: step: 1904/529, loss: 0.00027875902014784515
2023-01-23 04:38:43.135040: step: 1908/529, loss: 0.00042304996168240905
2023-01-23 04:38:44.348720: step: 1912/529, loss: 0.0062160491943359375
2023-01-23 04:38:45.568847: step: 1916/529, loss: 9.79900432866998e-05
2023-01-23 04:38:46.763570: step: 1920/529, loss: 8.39233416627394e-06
2023-01-23 04:38:47.918195: step: 1924/529, loss: 3.166198803228326e-05
2023-01-23 04:38:49.112359: step: 1928/529, loss: 0.027146339416503906
2023-01-23 04:38:50.338142: step: 1932/529, loss: 0.004527282901108265
2023-01-23 04:38:51.550310: step: 1936/529, loss: 3.8909915019758046e-05
2023-01-23 04:38:52.709249: step: 1940/529, loss: 5.054474058852065e-06
2023-01-23 04:38:53.893164: step: 1944/529, loss: 0.0021365166176110506
2023-01-23 04:38:55.085226: step: 1948/529, loss: 2.346038854739163e-05
2023-01-23 04:38:56.311815: step: 1952/529, loss: 0.0016041279304772615
2023-01-23 04:38:57.560648: step: 1956/529, loss: 0.06608200073242188
2023-01-23 04:38:58.801646: step: 1960/529, loss: 8.525848534191027e-05
2023-01-23 04:39:00.004307: step: 1964/529, loss: 0.0011838913196697831
2023-01-23 04:39:01.208349: step: 1968/529, loss: 0.0035634993109852076
2023-01-23 04:39:02.398398: step: 1972/529, loss: 0.0005339622730389237
2023-01-23 04:39:03.553391: step: 1976/529, loss: 0.0028240203391760588
2023-01-23 04:39:04.744697: step: 1980/529, loss: 0.00021314620971679688
2023-01-23 04:39:05.942889: step: 1984/529, loss: 0.02833261527121067
2023-01-23 04:39:07.124568: step: 1988/529, loss: 2.77042381640058e-05
2023-01-23 04:39:08.341004: step: 1992/529, loss: 0.09884300082921982
2023-01-23 04:39:09.541853: step: 1996/529, loss: 0.005834007635712624
2023-01-23 04:39:10.751615: step: 2000/529, loss: 0.005459595005959272
2023-01-23 04:39:11.984513: step: 2004/529, loss: 0.012092972174286842
2023-01-23 04:39:13.201882: step: 2008/529, loss: 5.083084397483617e-05
2023-01-23 04:39:14.422520: step: 2012/529, loss: 0.0010726929176598787
2023-01-23 04:39:15.601629: step: 2016/529, loss: 0.0007318496354855597
2023-01-23 04:39:16.817813: step: 2020/529, loss: 2.1839141481905244e-05
2023-01-23 04:39:18.018893: step: 2024/529, loss: 0.0002273559512104839
2023-01-23 04:39:19.213151: step: 2028/529, loss: 8.7738037109375e-05
2023-01-23 04:39:20.427365: step: 2032/529, loss: 0.031193161383271217
2023-01-23 04:39:21.627042: step: 2036/529, loss: 3.6525725590763614e-05
2023-01-23 04:39:22.875706: step: 2040/529, loss: 0.0024789811577647924
2023-01-23 04:39:24.085106: step: 2044/529, loss: 0.00010967255366267636
2023-01-23 04:39:25.307189: step: 2048/529, loss: 0.11280445754528046
2023-01-23 04:39:26.506746: step: 2052/529, loss: 0.00018043517775367945
2023-01-23 04:39:27.721891: step: 2056/529, loss: 0.003935051150619984
2023-01-23 04:39:28.917033: step: 2060/529, loss: 0.000484466552734375
2023-01-23 04:39:30.170975: step: 2064/529, loss: 0.0006269454606808722
2023-01-23 04:39:31.482998: step: 2068/529, loss: 0.0044602397829294205
2023-01-23 04:39:32.679364: step: 2072/529, loss: 0.0001160621686722152
2023-01-23 04:39:33.900236: step: 2076/529, loss: 0.00020751952251885086
2023-01-23 04:39:35.105788: step: 2080/529, loss: 0.00010733604722190648
2023-01-23 04:39:36.263571: step: 2084/529, loss: 0.00017858743376564234
2023-01-23 04:39:37.462167: step: 2088/529, loss: 5.14984130859375e-05
2023-01-23 04:39:38.668119: step: 2092/529, loss: 0.0007474899757653475
2023-01-23 04:39:39.918640: step: 2096/529, loss: 3.0517578125e-05
2023-01-23 04:39:41.098476: step: 2100/529, loss: 0.00019588469876907766
2023-01-23 04:39:42.323626: step: 2104/529, loss: 0.005795764736831188
2023-01-23 04:39:43.477046: step: 2108/529, loss: 3.3664702641544864e-05
2023-01-23 04:39:44.682094: step: 2112/529, loss: 5.35011276951991e-05
2023-01-23 04:39:45.855773: step: 2116/529, loss: 9.632110959501006e-06
==================================================
Loss: 0.027
--------------------
Dev: {'event': {'p': 0.608324439701174, 'r': 0.758988015978695, 'f1': 0.6753554502369669}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6355810616929699, 'r': 0.7962852007189934, 'f1': 0.7069148936170213}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.6571428571428571, 'r': 0.8518518518518519, 'f1': 0.7419354838709677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.54, 'r': 0.42857142857142855, 'f1': 0.47787610619469023}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 04:40:29.276140: step: 4/529, loss: 0.002486610319465399
2023-01-23 04:40:30.449815: step: 8/529, loss: 0.0005454063648357987
2023-01-23 04:40:31.691196: step: 12/529, loss: 1.3828277587890625e-05
2023-01-23 04:40:32.907684: step: 16/529, loss: 0.0005033492925576866
2023-01-23 04:40:34.136028: step: 20/529, loss: 0.0004085540713276714
2023-01-23 04:40:35.266367: step: 24/529, loss: 0.0005671024555340409
2023-01-23 04:40:36.478840: step: 28/529, loss: 0.0001996994105866179
2023-01-23 04:40:37.639024: step: 32/529, loss: 0.009290218353271484
2023-01-23 04:40:38.797948: step: 36/529, loss: 4.405975414556451e-05
2023-01-23 04:40:40.014241: step: 40/529, loss: 1.6975403923424892e-05
2023-01-23 04:40:41.167230: step: 44/529, loss: 3.166198803228326e-05
2023-01-23 04:40:42.419114: step: 48/529, loss: 0.03087139129638672
2023-01-23 04:40:43.656948: step: 52/529, loss: 0.008427905850112438
2023-01-23 04:40:44.846976: step: 56/529, loss: 1.7976761228055693e-05
2023-01-23 04:40:46.061644: step: 60/529, loss: 0.0009828568436205387
2023-01-23 04:40:47.277258: step: 64/529, loss: 0.00016860962205100805
2023-01-23 04:40:48.487792: step: 68/529, loss: 0.00017662048048805445
2023-01-23 04:40:49.657974: step: 72/529, loss: 0.02104807086288929
2023-01-23 04:40:50.842168: step: 76/529, loss: 2.09808349609375e-05
2023-01-23 04:40:52.059507: step: 80/529, loss: 0.0002040863037109375
2023-01-23 04:40:53.281897: step: 84/529, loss: 0.010392571799457073
2023-01-23 04:40:54.466927: step: 88/529, loss: 2.09808349609375e-05
2023-01-23 04:40:55.648342: step: 92/529, loss: 0.0007870674016885459
2023-01-23 04:40:56.883024: step: 96/529, loss: 0.00017404556274414062
2023-01-23 04:40:58.075287: step: 100/529, loss: 8.96453821042087e-06
2023-01-23 04:40:59.384199: step: 104/529, loss: 0.00034046173095703125
2023-01-23 04:41:00.569927: step: 108/529, loss: 0.006067848298698664
2023-01-23 04:41:01.789627: step: 112/529, loss: 0.00023155212693382055
2023-01-23 04:41:03.023234: step: 116/529, loss: 8.7738037109375e-05
2023-01-23 04:41:04.204786: step: 120/529, loss: 0.026311874389648438
2023-01-23 04:41:05.418392: step: 124/529, loss: 4.997253563487902e-05
2023-01-23 04:41:06.571713: step: 128/529, loss: 8.77380352903856e-06
2023-01-23 04:41:07.733542: step: 132/529, loss: 0.006289768498390913
2023-01-23 04:41:08.913006: step: 136/529, loss: 1.678466833254788e-05
2023-01-23 04:41:10.134964: step: 140/529, loss: 0.009939384646713734
2023-01-23 04:41:11.356679: step: 144/529, loss: 0.0007006645319052041
2023-01-23 04:41:12.530406: step: 148/529, loss: 2.603531174827367e-05
2023-01-23 04:41:13.727619: step: 152/529, loss: 0.023067761212587357
2023-01-23 04:41:14.903521: step: 156/529, loss: 0.000702285731676966
2023-01-23 04:41:16.087610: step: 160/529, loss: 4.196167537884321e-06
2023-01-23 04:41:17.269328: step: 164/529, loss: 0.01557083148509264
2023-01-23 04:41:18.431019: step: 168/529, loss: 0.0030640128534287214
2023-01-23 04:41:19.629171: step: 172/529, loss: 8.831024024402723e-05
2023-01-23 04:41:20.814585: step: 176/529, loss: 0.0007307053310796618
2023-01-23 04:41:22.016151: step: 180/529, loss: 0.5614844560623169
2023-01-23 04:41:23.210350: step: 184/529, loss: 5.1116945542162284e-05
2023-01-23 04:41:24.407817: step: 188/529, loss: 0.0006590366829186678
2023-01-23 04:41:25.619490: step: 192/529, loss: 0.024069594219326973
2023-01-23 04:41:26.834731: step: 196/529, loss: 8.525848534191027e-05
2023-01-23 04:41:28.057887: step: 200/529, loss: 5.91278057981981e-06
2023-01-23 04:41:29.298086: step: 204/529, loss: 0.0004283905145712197
2023-01-23 04:41:30.487680: step: 208/529, loss: 0.23826999962329865
2023-01-23 04:41:31.713787: step: 212/529, loss: 0.0013281822903081775
2023-01-23 04:41:32.964898: step: 216/529, loss: 2.6035309929284267e-05
2023-01-23 04:41:34.162167: step: 220/529, loss: 0.00026111601619049907
2023-01-23 04:41:35.325070: step: 224/529, loss: 0.0002505302254576236
2023-01-23 04:41:36.488967: step: 228/529, loss: 0.0002790451399050653
2023-01-23 04:41:37.677808: step: 232/529, loss: 0.0001808166562113911
2023-01-23 04:41:38.936645: step: 236/529, loss: 0.0013794898986816406
2023-01-23 04:41:40.131867: step: 240/529, loss: 3.452301098150201e-05
2023-01-23 04:41:41.312692: step: 244/529, loss: 1.8024444216280244e-05
2023-01-23 04:41:42.457142: step: 248/529, loss: 0.0009590149275027215
2023-01-23 04:41:43.678357: step: 252/529, loss: 0.0034128190018236637
2023-01-23 04:41:44.864169: step: 256/529, loss: 0.0032050132285803556
2023-01-23 04:41:46.048230: step: 260/529, loss: 1.6212465197895654e-05
2023-01-23 04:41:47.221059: step: 264/529, loss: 3.814697322468419e-07
2023-01-23 04:41:48.423945: step: 268/529, loss: 2.937316821771674e-05
2023-01-23 04:41:49.610203: step: 272/529, loss: 0.009503936395049095
2023-01-23 04:41:50.812248: step: 276/529, loss: 9.584426152287051e-06
2023-01-23 04:41:51.996817: step: 280/529, loss: 0.003019094467163086
2023-01-23 04:41:53.174514: step: 284/529, loss: 0.053794100880622864
2023-01-23 04:41:54.414057: step: 288/529, loss: 0.00039386749267578125
2023-01-23 04:41:55.670699: step: 292/529, loss: 0.0002857208310160786
2023-01-23 04:41:56.891454: step: 296/529, loss: 0.00019207000150345266
2023-01-23 04:41:58.080206: step: 300/529, loss: 0.0008145809406414628
2023-01-23 04:41:59.273523: step: 304/529, loss: 1.583099401614163e-05
2023-01-23 04:42:00.438325: step: 308/529, loss: 0.05093097686767578
2023-01-23 04:42:01.609213: step: 312/529, loss: -1.106262243411038e-05
2023-01-23 04:42:02.783171: step: 316/529, loss: 1.564025842526462e-05
2023-01-23 04:42:04.072288: step: 320/529, loss: 0.0007534981123171747
2023-01-23 04:42:05.258773: step: 324/529, loss: 7.724762326688506e-06
2023-01-23 04:42:06.475046: step: 328/529, loss: 0.0011709213722497225
2023-01-23 04:42:07.655642: step: 332/529, loss: 0.0011053085327148438
2023-01-23 04:42:08.828788: step: 336/529, loss: 0.0003216266632080078
2023-01-23 04:42:10.007626: step: 340/529, loss: 0.002346134278923273
2023-01-23 04:42:11.209555: step: 344/529, loss: 3.4046173823298886e-05
2023-01-23 04:42:12.435540: step: 348/529, loss: 0.022385407239198685
2023-01-23 04:42:13.607526: step: 352/529, loss: 0.00017142295837402344
2023-01-23 04:42:14.817647: step: 356/529, loss: 0.011541938409209251
2023-01-23 04:42:15.989374: step: 360/529, loss: 9.775162470759824e-05
2023-01-23 04:42:17.228544: step: 364/529, loss: 0.015950823202729225
2023-01-23 04:42:18.429966: step: 368/529, loss: 0.01206598337739706
2023-01-23 04:42:19.621886: step: 372/529, loss: -2.670288040462765e-06
2023-01-23 04:42:20.809417: step: 376/529, loss: 2.384185791015625e-06
2023-01-23 04:42:22.017107: step: 380/529, loss: 5.197525388211943e-05
2023-01-23 04:42:23.226475: step: 384/529, loss: 2.975463939947076e-05
2023-01-23 04:42:24.412712: step: 388/529, loss: 8.583068620282575e-07
2023-01-23 04:42:25.630959: step: 392/529, loss: 0.002277946565300226
2023-01-23 04:42:26.841191: step: 396/529, loss: 0.0003795623779296875
2023-01-23 04:42:28.047414: step: 400/529, loss: 5.948544185230276e-06
2023-01-23 04:42:29.256062: step: 404/529, loss: 2.264976683363784e-05
2023-01-23 04:42:30.483003: step: 408/529, loss: 0.008116102777421474
2023-01-23 04:42:31.664211: step: 412/529, loss: 0.01571502722799778
2023-01-23 04:42:32.890425: step: 416/529, loss: 0.0037660598754882812
2023-01-23 04:42:34.083550: step: 420/529, loss: 0.004323672968894243
2023-01-23 04:42:35.277128: step: 424/529, loss: -5.722044988942798e-07
2023-01-23 04:42:36.459357: step: 428/529, loss: 0.002426528837531805
2023-01-23 04:42:37.631910: step: 432/529, loss: 0.0012628554832190275
2023-01-23 04:42:38.859815: step: 436/529, loss: 0.0017341614002361894
2023-01-23 04:42:40.026143: step: 440/529, loss: 0.008396483026444912
2023-01-23 04:42:41.217035: step: 444/529, loss: -9.536745437799254e-08
2023-01-23 04:42:42.457972: step: 448/529, loss: 4.587173680192791e-05
2023-01-23 04:42:43.641804: step: 452/529, loss: 8.0108642578125e-05
2023-01-23 04:42:44.869777: step: 456/529, loss: 4.48703758593183e-05
2023-01-23 04:42:46.068217: step: 460/529, loss: 0.0006788254249840975
2023-01-23 04:42:47.276021: step: 464/529, loss: 0.0002368926943745464
2023-01-23 04:42:48.469317: step: 468/529, loss: 0.0015342712868005037
2023-01-23 04:42:49.656028: step: 472/529, loss: 0.03257932886481285
2023-01-23 04:42:50.819470: step: 476/529, loss: 0.000133514404296875
2023-01-23 04:42:52.007242: step: 480/529, loss: 0.00044574736966751516
2023-01-23 04:42:53.238706: step: 484/529, loss: 0.0001923561212606728
2023-01-23 04:42:54.472933: step: 488/529, loss: 0.0010777473216876388
2023-01-23 04:42:55.687019: step: 492/529, loss: 2.9087066195643274e-06
2023-01-23 04:42:56.933802: step: 496/529, loss: 0.0001256942778127268
2023-01-23 04:42:58.119066: step: 500/529, loss: 0.00018177033052779734
2023-01-23 04:42:59.284714: step: 504/529, loss: 0.00011037290096282959
2023-01-23 04:43:00.412239: step: 508/529, loss: 4.875659669778543e-06
2023-01-23 04:43:01.595114: step: 512/529, loss: 0.03704824671149254
2023-01-23 04:43:02.768529: step: 516/529, loss: 0.0005247116205282509
2023-01-23 04:43:03.953286: step: 520/529, loss: 9.5367431640625e-07
2023-01-23 04:43:05.138908: step: 524/529, loss: 1.029968279908644e-05
2023-01-23 04:43:06.349332: step: 528/529, loss: 0.019686318933963776
2023-01-23 04:43:07.533442: step: 532/529, loss: 0.0001111269011744298
2023-01-23 04:43:08.691396: step: 536/529, loss: 7.82012921263231e-06
2023-01-23 04:43:09.873321: step: 540/529, loss: 4.119873119634576e-05
2023-01-23 04:43:11.075153: step: 544/529, loss: 0.0014347076648846269
2023-01-23 04:43:12.288388: step: 548/529, loss: 0.001260089804418385
2023-01-23 04:43:13.456620: step: 552/529, loss: 0.0002948761102743447
2023-01-23 04:43:14.662436: step: 556/529, loss: 0.009482955560088158
2023-01-23 04:43:15.883375: step: 560/529, loss: 0.0001127243012888357
2023-01-23 04:43:17.106550: step: 564/529, loss: 2.574920654296875e-05
2023-01-23 04:43:18.310842: step: 568/529, loss: 0.0022785186301916838
2023-01-23 04:43:19.496976: step: 572/529, loss: 0.003586387727409601
2023-01-23 04:43:20.678126: step: 576/529, loss: 0.009890555404126644
2023-01-23 04:43:21.871817: step: 580/529, loss: 4.863739377469756e-06
2023-01-23 04:43:23.089886: step: 584/529, loss: 0.01574115827679634
2023-01-23 04:43:24.297063: step: 588/529, loss: 0.0031417845748364925
2023-01-23 04:43:25.485771: step: 592/529, loss: 0.07559995353221893
2023-01-23 04:43:26.672370: step: 596/529, loss: 0.0011539459228515625
2023-01-23 04:43:27.858810: step: 600/529, loss: 0.00301017751917243
2023-01-23 04:43:29.084139: step: 604/529, loss: 0.0008828163263387978
2023-01-23 04:43:30.255719: step: 608/529, loss: 0.001103305839933455
2023-01-23 04:43:31.418514: step: 612/529, loss: 7.83920258982107e-05
2023-01-23 04:43:32.647903: step: 616/529, loss: 0.5508025288581848
2023-01-23 04:43:33.831968: step: 620/529, loss: 0.0001636505185160786
2023-01-23 04:43:35.005232: step: 624/529, loss: 0.00022392273240257055
2023-01-23 04:43:36.146802: step: 628/529, loss: 8.487701052217744e-06
2023-01-23 04:43:37.353663: step: 632/529, loss: 8.440018063993193e-06
2023-01-23 04:43:38.607396: step: 636/529, loss: -3.719329924933845e-06
2023-01-23 04:43:39.820325: step: 640/529, loss: 6.215572648216039e-05
2023-01-23 04:43:41.046929: step: 644/529, loss: 0.0003132820129394531
2023-01-23 04:43:42.235454: step: 648/529, loss: 0.0046621328219771385
2023-01-23 04:43:43.430490: step: 652/529, loss: 0.001276302384212613
2023-01-23 04:43:44.621067: step: 656/529, loss: 1.106262243411038e-05
2023-01-23 04:43:45.820919: step: 660/529, loss: 0.0013508796691894531
2023-01-23 04:43:47.033119: step: 664/529, loss: 5.9890749980695546e-05
2023-01-23 04:43:48.242263: step: 668/529, loss: 0.006545639596879482
2023-01-23 04:43:49.402368: step: 672/529, loss: 2.765655608527595e-06
2023-01-23 04:43:50.580930: step: 676/529, loss: 0.00011539459228515625
2023-01-23 04:43:51.776611: step: 680/529, loss: 5.931854320806451e-05
2023-01-23 04:43:52.948811: step: 684/529, loss: 0.00044164658174850047
2023-01-23 04:43:54.192177: step: 688/529, loss: 0.0007810592651367188
2023-01-23 04:43:55.349511: step: 692/529, loss: 3.137588282697834e-05
2023-01-23 04:43:56.537686: step: 696/529, loss: 3.890991138177924e-05
2023-01-23 04:43:57.753473: step: 700/529, loss: 0.0807764008641243
2023-01-23 04:43:58.951162: step: 704/529, loss: 0.07057266682386398
2023-01-23 04:44:00.170632: step: 708/529, loss: 0.004187965299934149
2023-01-23 04:44:01.363691: step: 712/529, loss: 0.006999587640166283
2023-01-23 04:44:02.564621: step: 716/529, loss: 0.00022430421086028218
2023-01-23 04:44:03.735828: step: 720/529, loss: 9.775161743164062e-05
2023-01-23 04:44:04.933862: step: 724/529, loss: 0.00011463165719760582
2023-01-23 04:44:06.146511: step: 728/529, loss: 0.000489568745251745
2023-01-23 04:44:07.344732: step: 732/529, loss: 0.005581521894782782
2023-01-23 04:44:08.511514: step: 736/529, loss: 0.000760841416195035
2023-01-23 04:44:09.723990: step: 740/529, loss: 0.006346225738525391
2023-01-23 04:44:10.900197: step: 744/529, loss: 0.00013961792865302414
2023-01-23 04:44:12.094512: step: 748/529, loss: 0.00010690689668990672
2023-01-23 04:44:13.328515: step: 752/529, loss: 0.637780487537384
2023-01-23 04:44:14.509202: step: 756/529, loss: 0.0035182000137865543
2023-01-23 04:44:15.687817: step: 760/529, loss: 5.91278076171875e-05
2023-01-23 04:44:16.838867: step: 764/529, loss: 0.0017399787902832031
2023-01-23 04:44:18.035733: step: 768/529, loss: 0.0027918340638279915
2023-01-23 04:44:19.257871: step: 772/529, loss: 0.0005471229669637978
2023-01-23 04:44:20.424647: step: 776/529, loss: 0.011491012759506702
2023-01-23 04:44:21.694954: step: 780/529, loss: 0.033760640770196915
2023-01-23 04:44:22.923450: step: 784/529, loss: 0.01816840097308159
2023-01-23 04:44:24.115738: step: 788/529, loss: 0.0046198368072509766
2023-01-23 04:44:25.286039: step: 792/529, loss: 4.5156477426644415e-05
2023-01-23 04:44:26.493948: step: 796/529, loss: 0.00037469863309524953
2023-01-23 04:44:27.692588: step: 800/529, loss: 0.0029431821312755346
2023-01-23 04:44:28.876495: step: 804/529, loss: 0.022354699671268463
2023-01-23 04:44:30.047908: step: 808/529, loss: 0.03462781757116318
2023-01-23 04:44:31.232316: step: 812/529, loss: 0.00015592575073242188
2023-01-23 04:44:32.446156: step: 816/529, loss: 0.000102996826171875
2023-01-23 04:44:33.646897: step: 820/529, loss: 0.0003194332239218056
2023-01-23 04:44:34.811298: step: 824/529, loss: 0.002585983369499445
2023-01-23 04:44:35.975289: step: 828/529, loss: 0.0099938390776515
2023-01-23 04:44:37.154544: step: 832/529, loss: 0.00041918756323866546
2023-01-23 04:44:38.331877: step: 836/529, loss: 0.0003768921014852822
2023-01-23 04:44:39.550626: step: 840/529, loss: 4.18663039454259e-05
2023-01-23 04:44:40.746380: step: 844/529, loss: 0.00011382102820789441
2023-01-23 04:44:41.898314: step: 848/529, loss: 8.535384949936997e-06
2023-01-23 04:44:43.145730: step: 852/529, loss: 0.00019674301438499242
2023-01-23 04:44:44.350714: step: 856/529, loss: 0.0007982254610396922
2023-01-23 04:44:45.529344: step: 860/529, loss: 0.01453480776399374
2023-01-23 04:44:46.748764: step: 864/529, loss: 0.00403099087998271
2023-01-23 04:44:47.920628: step: 868/529, loss: 0.0033857347443699837
2023-01-23 04:44:49.121775: step: 872/529, loss: 5.4168704082258046e-05
2023-01-23 04:44:50.269165: step: 876/529, loss: 0.003027343889698386
2023-01-23 04:44:51.486885: step: 880/529, loss: 0.0005221366882324219
2023-01-23 04:44:52.729192: step: 884/529, loss: 4.95910626341356e-06
2023-01-23 04:44:53.903779: step: 888/529, loss: 0.00013847352238371968
2023-01-23 04:44:55.109997: step: 892/529, loss: 0.0012887954944744706
2023-01-23 04:44:56.375141: step: 896/529, loss: 0.0002054214564850554
2023-01-23 04:44:57.539737: step: 900/529, loss: 1.6689300537109375e-06
2023-01-23 04:44:58.762427: step: 904/529, loss: 0.0005992889637127519
2023-01-23 04:44:59.957518: step: 908/529, loss: 0.00015020370483398438
2023-01-23 04:45:01.179345: step: 912/529, loss: 0.02367849461734295
2023-01-23 04:45:02.419558: step: 916/529, loss: 0.03129472956061363
2023-01-23 04:45:03.599864: step: 920/529, loss: 0.07983321696519852
2023-01-23 04:45:04.830735: step: 924/529, loss: 3.24249276673072e-06
2023-01-23 04:45:05.996799: step: 928/529, loss: 2.1028519768151455e-05
2023-01-23 04:45:07.188965: step: 932/529, loss: 0.0003984451468568295
2023-01-23 04:45:08.361935: step: 936/529, loss: 0.004168891813606024
2023-01-23 04:45:09.585845: step: 940/529, loss: 0.00019202232942916453
2023-01-23 04:45:10.756987: step: 944/529, loss: 0.011140060611069202
2023-01-23 04:45:11.942871: step: 948/529, loss: 0.00029754638671875
2023-01-23 04:45:13.151991: step: 952/529, loss: 0.011180304922163486
2023-01-23 04:45:14.402654: step: 956/529, loss: 2.784729076665826e-05
2023-01-23 04:45:15.647467: step: 960/529, loss: 2.1553038095589727e-05
2023-01-23 04:45:16.830074: step: 964/529, loss: 0.08011846989393234
2023-01-23 04:45:18.027243: step: 968/529, loss: 0.010040283203125
2023-01-23 04:45:19.223564: step: 972/529, loss: 0.025724411010742188
2023-01-23 04:45:20.383612: step: 976/529, loss: 7.3909759521484375e-06
2023-01-23 04:45:21.581769: step: 980/529, loss: 0.0004756927664857358
2023-01-23 04:45:22.792879: step: 984/529, loss: 0.00335521693341434
2023-01-23 04:45:23.988630: step: 988/529, loss: 2.803802453854587e-05
2023-01-23 04:45:25.193739: step: 992/529, loss: 0.0028936387971043587
2023-01-23 04:45:26.385800: step: 996/529, loss: 0.04069824144244194
2023-01-23 04:45:27.580853: step: 1000/529, loss: 0.007387733552604914
2023-01-23 04:45:28.762593: step: 1004/529, loss: 0.0010744095779955387
2023-01-23 04:45:29.965224: step: 1008/529, loss: 0.00016803742619231343
2023-01-23 04:45:31.125815: step: 1012/529, loss: 0.002085113665089011
2023-01-23 04:45:32.284352: step: 1016/529, loss: -6.198883397701138e-07
2023-01-23 04:45:33.500239: step: 1020/529, loss: 2.6702880859375e-05
2023-01-23 04:45:34.682667: step: 1024/529, loss: -2.86102294921875e-06
2023-01-23 04:45:35.878633: step: 1028/529, loss: 4.754066685563885e-05
2023-01-23 04:45:37.123614: step: 1032/529, loss: 0.12673984467983246
2023-01-23 04:45:38.317391: step: 1036/529, loss: 0.0003602981742005795
2023-01-23 04:45:39.497589: step: 1040/529, loss: 2.2602082026423886e-05
2023-01-23 04:45:40.698742: step: 1044/529, loss: 1.2111663636460435e-05
2023-01-23 04:45:41.886582: step: 1048/529, loss: 0.002100181533023715
2023-01-23 04:45:43.130286: step: 1052/529, loss: 0.2902399003505707
2023-01-23 04:45:44.333488: step: 1056/529, loss: -4.38690176451928e-06
2023-01-23 04:45:45.530615: step: 1060/529, loss: 0.005321884527802467
2023-01-23 04:45:46.676313: step: 1064/529, loss: 1.0013580322265625e-05
2023-01-23 04:45:47.901913: step: 1068/529, loss: 0.04849839210510254
2023-01-23 04:45:49.077313: step: 1072/529, loss: 0.0009517669677734375
2023-01-23 04:45:50.277412: step: 1076/529, loss: -8.773804438533261e-06
2023-01-23 04:45:51.430060: step: 1080/529, loss: 0.00018634795560501516
2023-01-23 04:45:52.642565: step: 1084/529, loss: -6.675719532722724e-07
2023-01-23 04:45:53.862248: step: 1088/529, loss: 0.010739946737885475
2023-01-23 04:45:55.067760: step: 1092/529, loss: 4.6205521357478574e-05
2023-01-23 04:45:56.297292: step: 1096/529, loss: 7.743835885776207e-05
2023-01-23 04:45:57.506189: step: 1100/529, loss: 0.2479230910539627
2023-01-23 04:45:58.723235: step: 1104/529, loss: 0.020854569971561432
2023-01-23 04:45:59.895094: step: 1108/529, loss: 0.0001441717176930979
2023-01-23 04:46:01.076174: step: 1112/529, loss: 0.00016117095947265625
2023-01-23 04:46:02.291964: step: 1116/529, loss: 0.03041229397058487
2023-01-23 04:46:03.501597: step: 1120/529, loss: 0.006233597174286842
2023-01-23 04:46:04.686099: step: 1124/529, loss: -1.8835066839528736e-06
2023-01-23 04:46:05.951232: step: 1128/529, loss: 0.0012374878861010075
2023-01-23 04:46:07.152890: step: 1132/529, loss: 1.5258789289873675e-06
2023-01-23 04:46:08.306132: step: 1136/529, loss: 6.67572021484375e-06
2023-01-23 04:46:09.476928: step: 1140/529, loss: 4.57763690064894e-06
2023-01-23 04:46:10.645172: step: 1144/529, loss: 0.04687223210930824
2023-01-23 04:46:11.845124: step: 1148/529, loss: 0.010915899649262428
2023-01-23 04:46:12.982544: step: 1152/529, loss: 1.602172778802924e-05
2023-01-23 04:46:14.195871: step: 1156/529, loss: 0.02811412885785103
2023-01-23 04:46:15.393879: step: 1160/529, loss: 3.919601658708416e-05
2023-01-23 04:46:16.626467: step: 1164/529, loss: 0.0004516601620707661
2023-01-23 04:46:17.819431: step: 1168/529, loss: 2.689361645025201e-05
2023-01-23 04:46:19.033441: step: 1172/529, loss: 0.005347347352653742
2023-01-23 04:46:20.197460: step: 1176/529, loss: 0.007536268327385187
2023-01-23 04:46:21.391879: step: 1180/529, loss: 0.043550778180360794
2023-01-23 04:46:22.542034: step: 1184/529, loss: 2.2029877072782256e-05
2023-01-23 04:46:23.736282: step: 1188/529, loss: 1.201629675051663e-05
2023-01-23 04:46:24.915262: step: 1192/529, loss: 2.555847095209174e-05
2023-01-23 04:46:26.098324: step: 1196/529, loss: 0.0003506660577841103
2023-01-23 04:46:27.284654: step: 1200/529, loss: 0.0031450269743800163
2023-01-23 04:46:28.460966: step: 1204/529, loss: 0.10371074825525284
2023-01-23 04:46:29.669375: step: 1208/529, loss: 0.07595143467187881
2023-01-23 04:46:30.866992: step: 1212/529, loss: 0.0015107154613360763
2023-01-23 04:46:32.114238: step: 1216/529, loss: 0.0004150390741415322
2023-01-23 04:46:33.322317: step: 1220/529, loss: 0.005833053961396217
2023-01-23 04:46:34.503059: step: 1224/529, loss: 0.00012621880159713328
2023-01-23 04:46:35.707005: step: 1228/529, loss: 0.0037235261406749487
2023-01-23 04:46:36.885424: step: 1232/529, loss: 0.04663591459393501
2023-01-23 04:46:38.060559: step: 1236/529, loss: 1.1014938536391128e-05
2023-01-23 04:46:39.264054: step: 1240/529, loss: 3.4332276754867053e-06
2023-01-23 04:46:40.442768: step: 1244/529, loss: 0.013466835021972656
2023-01-23 04:46:41.673435: step: 1248/529, loss: 0.0031305314041674137
2023-01-23 04:46:42.886149: step: 1252/529, loss: 0.0013742446899414062
2023-01-23 04:46:44.069737: step: 1256/529, loss: 0.024256134405732155
2023-01-23 04:46:45.274581: step: 1260/529, loss: 0.0006215095636434853
2023-01-23 04:46:46.490121: step: 1264/529, loss: 0.004816532135009766
2023-01-23 04:46:47.651676: step: 1268/529, loss: 0.0010930061107501388
2023-01-23 04:46:48.827828: step: 1272/529, loss: 0.0013159752124920487
2023-01-23 04:46:50.018573: step: 1276/529, loss: 0.0001308917999267578
2023-01-23 04:46:51.258502: step: 1280/529, loss: 3.352165367687121e-05
2023-01-23 04:46:52.468551: step: 1284/529, loss: 0.0028423310723155737
2023-01-23 04:46:53.688398: step: 1288/529, loss: 0.0013466834789142013
2023-01-23 04:46:54.890028: step: 1292/529, loss: 1.430511474609375e-05
2023-01-23 04:46:56.092162: step: 1296/529, loss: 0.00586891220882535
2023-01-23 04:46:57.292827: step: 1300/529, loss: 0.007724952884018421
2023-01-23 04:46:58.483783: step: 1304/529, loss: 0.12593841552734375
2023-01-23 04:46:59.721765: step: 1308/529, loss: 0.0009386062738485634
2023-01-23 04:47:00.913500: step: 1312/529, loss: 0.0006546020740643144
2023-01-23 04:47:02.141775: step: 1316/529, loss: 5.435943603515625e-05
2023-01-23 04:47:03.348924: step: 1320/529, loss: 0.0003288268926553428
2023-01-23 04:47:04.549854: step: 1324/529, loss: -1.9311905816721264e-06
2023-01-23 04:47:05.788326: step: 1328/529, loss: 4.425048973644152e-05
2023-01-23 04:47:07.004982: step: 1332/529, loss: 6.866455078125e-05
2023-01-23 04:47:08.260917: step: 1336/529, loss: -1.4352798643813003e-05
2023-01-23 04:47:09.452780: step: 1340/529, loss: 0.0009828567272052169
2023-01-23 04:47:10.655173: step: 1344/529, loss: 0.02327137067914009
2023-01-23 04:47:11.849312: step: 1348/529, loss: 0.02124004438519478
2023-01-23 04:47:13.085292: step: 1352/529, loss: 0.00036783216637559235
2023-01-23 04:47:14.258858: step: 1356/529, loss: 0.012428618036210537
2023-01-23 04:47:15.486178: step: 1360/529, loss: 0.0004364013730082661
2023-01-23 04:47:16.722519: step: 1364/529, loss: 0.0009974479908123612
2023-01-23 04:47:17.978304: step: 1368/529, loss: 0.021364212036132812
2023-01-23 04:47:19.196518: step: 1372/529, loss: 0.0004796028370037675
2023-01-23 04:47:20.427741: step: 1376/529, loss: 0.00023784636869095266
2023-01-23 04:47:21.648008: step: 1380/529, loss: 0.010939240455627441
2023-01-23 04:47:22.848106: step: 1384/529, loss: 0.010668087750673294
2023-01-23 04:47:24.053695: step: 1388/529, loss: 0.010875415056943893
2023-01-23 04:47:25.316130: step: 1392/529, loss: 0.0016296387184411287
2023-01-23 04:47:26.507776: step: 1396/529, loss: 0.10114937275648117
2023-01-23 04:47:27.709309: step: 1400/529, loss: 0.00014142990403342992
2023-01-23 04:47:28.906898: step: 1404/529, loss: 0.01692981831729412
2023-01-23 04:47:30.106340: step: 1408/529, loss: 0.0073986053466796875
2023-01-23 04:47:31.295700: step: 1412/529, loss: 0.0018570900429040194
2023-01-23 04:47:32.498084: step: 1416/529, loss: 1.3351441339182202e-05
2023-01-23 04:47:33.690864: step: 1420/529, loss: 6.637573096668348e-05
2023-01-23 04:47:34.921882: step: 1424/529, loss: 4.901886131847277e-05
2023-01-23 04:47:36.155378: step: 1428/529, loss: 6.675720101156912e-07
2023-01-23 04:47:37.350717: step: 1432/529, loss: 4.38690176451928e-06
2023-01-23 04:47:38.597503: step: 1436/529, loss: 0.0013442039489746094
2023-01-23 04:47:39.846816: step: 1440/529, loss: 0.0004611015319824219
2023-01-23 04:47:41.041704: step: 1444/529, loss: -4.95910626341356e-06
2023-01-23 04:47:42.269665: step: 1448/529, loss: 0.002014636993408203
2023-01-23 04:47:43.448960: step: 1452/529, loss: 0.05167656019330025
2023-01-23 04:47:44.631399: step: 1456/529, loss: 0.0015058517456054688
2023-01-23 04:47:45.855205: step: 1460/529, loss: 0.03955860063433647
2023-01-23 04:47:47.066705: step: 1464/529, loss: 0.03722947835922241
2023-01-23 04:47:48.266752: step: 1468/529, loss: 0.01768798939883709
2023-01-23 04:47:49.443606: step: 1472/529, loss: 0.012889672070741653
2023-01-23 04:47:50.683123: step: 1476/529, loss: 0.0015233993763104081
2023-01-23 04:47:51.837952: step: 1480/529, loss: 0.0009507178911007941
2023-01-23 04:47:52.997010: step: 1484/529, loss: 0.0001539230433991179
2023-01-23 04:47:54.151844: step: 1488/529, loss: 2.7465821403893642e-05
2023-01-23 04:47:55.336027: step: 1492/529, loss: 0.00016374587721657008
2023-01-23 04:47:56.579445: step: 1496/529, loss: 0.013057136908173561
2023-01-23 04:47:57.763094: step: 1500/529, loss: 0.00038776398287154734
2023-01-23 04:47:58.971671: step: 1504/529, loss: 0.3891308903694153
2023-01-23 04:48:00.228487: step: 1508/529, loss: 2.4604798454674892e-05
2023-01-23 04:48:01.384189: step: 1512/529, loss: 0.0003338813839945942
2023-01-23 04:48:02.629906: step: 1516/529, loss: 0.00045928958570584655
2023-01-23 04:48:03.836224: step: 1520/529, loss: 1.4495850336970761e-05
2023-01-23 04:48:05.010527: step: 1524/529, loss: 0.0003067016659770161
2023-01-23 04:48:06.166672: step: 1528/529, loss: 0.0018367767333984375
2023-01-23 04:48:07.378352: step: 1532/529, loss: 0.0015243530506268144
2023-01-23 04:48:08.653713: step: 1536/529, loss: 0.008710002526640892
2023-01-23 04:48:09.841268: step: 1540/529, loss: 0.009780501946806908
2023-01-23 04:48:11.090326: step: 1544/529, loss: 6.713867333019152e-05
2023-01-23 04:48:12.315700: step: 1548/529, loss: 0.0002689361572265625
2023-01-23 04:48:13.500359: step: 1552/529, loss: 0.0006654262542724609
2023-01-23 04:48:14.735208: step: 1556/529, loss: 0.014021968469023705
2023-01-23 04:48:15.956325: step: 1560/529, loss: 5.626678466796875e-05
2023-01-23 04:48:17.195026: step: 1564/529, loss: 0.021380044519901276
2023-01-23 04:48:18.419303: step: 1568/529, loss: 0.003910636994987726
2023-01-23 04:48:19.679395: step: 1572/529, loss: 0.042675018310546875
2023-01-23 04:48:20.880905: step: 1576/529, loss: 0.004794502630829811
2023-01-23 04:48:22.058866: step: 1580/529, loss: 0.0016431808471679688
2023-01-23 04:48:23.250473: step: 1584/529, loss: 2.079009937006049e-05
2023-01-23 04:48:24.466881: step: 1588/529, loss: 0.003921222873032093
2023-01-23 04:48:25.644212: step: 1592/529, loss: 0.013204192742705345
2023-01-23 04:48:26.832426: step: 1596/529, loss: 0.00010919570922851562
2023-01-23 04:48:28.041546: step: 1600/529, loss: 0.01206207275390625
2023-01-23 04:48:29.230125: step: 1604/529, loss: 0.016500186175107956
2023-01-23 04:48:30.430633: step: 1608/529, loss: 2.651214526849799e-05
2023-01-23 04:48:31.658005: step: 1612/529, loss: 0.0038360594771802425
2023-01-23 04:48:32.897684: step: 1616/529, loss: 0.00177764892578125
2023-01-23 04:48:34.059372: step: 1620/529, loss: 0.0021054267417639494
2023-01-23 04:48:35.249351: step: 1624/529, loss: 0.0012552260886877775
2023-01-23 04:48:36.460113: step: 1628/529, loss: 0.007490634918212891
2023-01-23 04:48:37.690246: step: 1632/529, loss: 0.03485069423913956
2023-01-23 04:48:38.938828: step: 1636/529, loss: 0.004987811669707298
2023-01-23 04:48:40.155700: step: 1640/529, loss: -7.05719003235572e-06
2023-01-23 04:48:41.355571: step: 1644/529, loss: 0.0034748553298413754
2023-01-23 04:48:42.584845: step: 1648/529, loss: 0.0005661964532919228
2023-01-23 04:48:43.815345: step: 1652/529, loss: 0.022451020777225494
2023-01-23 04:48:45.052813: step: 1656/529, loss: 0.0001357078435830772
2023-01-23 04:48:46.244746: step: 1660/529, loss: 0.02911815606057644
2023-01-23 04:48:47.458252: step: 1664/529, loss: 0.0006277084467001259
2023-01-23 04:48:48.693835: step: 1668/529, loss: 0.00031528473482467234
2023-01-23 04:48:49.916559: step: 1672/529, loss: 8.335112943314016e-05
2023-01-23 04:48:51.140870: step: 1676/529, loss: 0.0021923722233623266
2023-01-23 04:48:52.358520: step: 1680/529, loss: 5.5027008784236386e-05
2023-01-23 04:48:53.534953: step: 1684/529, loss: 0.004140091128647327
2023-01-23 04:48:54.756329: step: 1688/529, loss: 9.078979928744957e-05
2023-01-23 04:48:55.955356: step: 1692/529, loss: 6.31332368357107e-05
2023-01-23 04:48:57.243646: step: 1696/529, loss: 0.0006995201110839844
2023-01-23 04:48:58.473512: step: 1700/529, loss: 0.02968435175716877
2023-01-23 04:48:59.704626: step: 1704/529, loss: 0.05621156841516495
2023-01-23 04:49:00.936723: step: 1708/529, loss: 1.869201696536038e-05
2023-01-23 04:49:02.137191: step: 1712/529, loss: 0.012327956967055798
2023-01-23 04:49:03.324500: step: 1716/529, loss: 0.000583648681640625
2023-01-23 04:49:04.522001: step: 1720/529, loss: -1.049041748046875e-05
2023-01-23 04:49:05.753166: step: 1724/529, loss: -0.0
2023-01-23 04:49:06.940913: step: 1728/529, loss: 0.009617805480957031
2023-01-23 04:49:08.183258: step: 1732/529, loss: 0.006374072749167681
2023-01-23 04:49:09.381057: step: 1736/529, loss: 0.0006165504455566406
2023-01-23 04:49:10.607325: step: 1740/529, loss: 4.7874447773210704e-05
2023-01-23 04:49:11.831599: step: 1744/529, loss: 7.591247413074598e-05
2023-01-23 04:49:13.015315: step: 1748/529, loss: 0.10577736049890518
2023-01-23 04:49:14.169975: step: 1752/529, loss: 0.006121492478996515
2023-01-23 04:49:15.371334: step: 1756/529, loss: 7.743835885776207e-05
2023-01-23 04:49:16.588618: step: 1760/529, loss: 0.0013271331554278731
2023-01-23 04:49:17.782690: step: 1764/529, loss: 0.0006898880237713456
2023-01-23 04:49:18.973615: step: 1768/529, loss: 0.0035812377464026213
2023-01-23 04:49:20.165187: step: 1772/529, loss: 0.0008927345043048263
2023-01-23 04:49:21.362409: step: 1776/529, loss: 0.00018568038649391383
2023-01-23 04:49:22.510349: step: 1780/529, loss: 0.004691887181252241
2023-01-23 04:49:23.678786: step: 1784/529, loss: 2.1743775505456142e-05
2023-01-23 04:49:24.893994: step: 1788/529, loss: 0.4828300476074219
2023-01-23 04:49:26.114857: step: 1792/529, loss: 0.0002576827828306705
2023-01-23 04:49:27.332271: step: 1796/529, loss: 0.004059982020407915
2023-01-23 04:49:28.529632: step: 1800/529, loss: 0.08966103196144104
2023-01-23 04:49:29.714305: step: 1804/529, loss: 0.0018215179443359375
2023-01-23 04:49:30.943769: step: 1808/529, loss: 0.04393348842859268
2023-01-23 04:49:32.132480: step: 1812/529, loss: 0.00022945404634810984
2023-01-23 04:49:33.326423: step: 1816/529, loss: 0.02981853485107422
2023-01-23 04:49:34.504426: step: 1820/529, loss: 0.21706753969192505
2023-01-23 04:49:35.694370: step: 1824/529, loss: 8.010864803509321e-06
2023-01-23 04:49:36.880806: step: 1828/529, loss: 0.010526467114686966
2023-01-23 04:49:38.047022: step: 1832/529, loss: 0.384307861328125
2023-01-23 04:49:39.233543: step: 1836/529, loss: 6.403923180187121e-05
2023-01-23 04:49:40.485862: step: 1840/529, loss: 0.0010183334816247225
2023-01-23 04:49:41.661115: step: 1844/529, loss: 6.580352783203125e-05
2023-01-23 04:49:42.858621: step: 1848/529, loss: 0.0016900539631024003
2023-01-23 04:49:44.037129: step: 1852/529, loss: 0.04127006232738495
2023-01-23 04:49:45.238814: step: 1856/529, loss: 1.4400482541532256e-05
2023-01-23 04:49:46.435070: step: 1860/529, loss: 5.865097136847908e-06
2023-01-23 04:49:47.623572: step: 1864/529, loss: 0.026184655725955963
2023-01-23 04:49:48.843091: step: 1868/529, loss: 0.0017786979442462325
2023-01-23 04:49:50.071520: step: 1872/529, loss: 0.02577819861471653
2023-01-23 04:49:51.282349: step: 1876/529, loss: 7.057190487103071e-06
2023-01-23 04:49:52.502257: step: 1880/529, loss: 1.068115216185106e-05
2023-01-23 04:49:53.740460: step: 1884/529, loss: 0.0005952835199423134
2023-01-23 04:49:54.998956: step: 1888/529, loss: 0.029308224096894264
2023-01-23 04:49:56.190226: step: 1892/529, loss: 0.0006029129144735634
2023-01-23 04:49:57.349015: step: 1896/529, loss: 0.0004171371692791581
2023-01-23 04:49:58.536795: step: 1900/529, loss: 0.01193017978221178
2023-01-23 04:49:59.731627: step: 1904/529, loss: 0.001606154371984303
2023-01-23 04:50:00.917645: step: 1908/529, loss: 0.0003562927304301411
2023-01-23 04:50:02.149315: step: 1912/529, loss: 0.00019655228243209422
2023-01-23 04:50:03.359081: step: 1916/529, loss: 0.010395621880888939
2023-01-23 04:50:04.540425: step: 1920/529, loss: 0.0001253843365702778
2023-01-23 04:50:05.723311: step: 1924/529, loss: 8.77380352903856e-06
2023-01-23 04:50:06.908289: step: 1928/529, loss: 0.015627099201083183
2023-01-23 04:50:08.108299: step: 1932/529, loss: 0.00200996408239007
2023-01-23 04:50:09.304857: step: 1936/529, loss: 0.0002484321594238281
2023-01-23 04:50:10.499101: step: 1940/529, loss: 0.0008121490245684981
2023-01-23 04:50:11.654064: step: 1944/529, loss: 1.5258789289873675e-06
2023-01-23 04:50:12.826313: step: 1948/529, loss: -6.008148375258315e-06
2023-01-23 04:50:14.028687: step: 1952/529, loss: 0.014435959048569202
2023-01-23 04:50:15.194303: step: 1956/529, loss: 0.007031822577118874
2023-01-23 04:50:16.396949: step: 1960/529, loss: 0.00036101340083405375
2023-01-23 04:50:17.559701: step: 1964/529, loss: 0.0004458427429199219
2023-01-23 04:50:18.724379: step: 1968/529, loss: 8.506774611305445e-05
2023-01-23 04:50:19.984711: step: 1972/529, loss: -2.86102294921875e-05
2023-01-23 04:50:21.205887: step: 1976/529, loss: 0.0005737662431783974
2023-01-23 04:50:22.409464: step: 1980/529, loss: 0.0033237459138035774
2023-01-23 04:50:23.568826: step: 1984/529, loss: 6.27517729299143e-05
2023-01-23 04:50:24.830618: step: 1988/529, loss: 0.05934343487024307
2023-01-23 04:50:25.999499: step: 1992/529, loss: 4.76837158203125e-07
2023-01-23 04:50:27.179683: step: 1996/529, loss: 0.00024776457576081157
2023-01-23 04:50:28.371734: step: 2000/529, loss: 0.017863083630800247
2023-01-23 04:50:29.556984: step: 2004/529, loss: 3.933906555175781e-05
2023-01-23 04:50:30.734478: step: 2008/529, loss: 0.32417765259742737
2023-01-23 04:50:31.960924: step: 2012/529, loss: 0.0009929656516760588
2023-01-23 04:50:33.154016: step: 2016/529, loss: 0.007342815399169922
2023-01-23 04:50:34.398764: step: 2020/529, loss: 7.343292236328125e-05
2023-01-23 04:50:35.558275: step: 2024/529, loss: 1.392364538332913e-05
2023-01-23 04:50:36.682812: step: 2028/529, loss: 0.00014572142390534282
2023-01-23 04:50:37.871920: step: 2032/529, loss: 0.006381034851074219
2023-01-23 04:50:39.082865: step: 2036/529, loss: 1.335144588665571e-06
2023-01-23 04:50:40.270672: step: 2040/529, loss: 1.9550323486328125e-05
2023-01-23 04:50:41.498819: step: 2044/529, loss: 0.00033969880314543843
2023-01-23 04:50:42.722695: step: 2048/529, loss: 0.00014381408982444555
2023-01-23 04:50:43.886275: step: 2052/529, loss: 0.00042142870370298624
2023-01-23 04:50:45.097831: step: 2056/529, loss: 0.021132469177246094
2023-01-23 04:50:46.288281: step: 2060/529, loss: 0.06449127197265625
2023-01-23 04:50:47.470978: step: 2064/529, loss: 0.0003295898495707661
2023-01-23 04:50:48.649580: step: 2068/529, loss: 0.0002716064336709678
2023-01-23 04:50:49.836503: step: 2072/529, loss: 0.0024772644974291325
2023-01-23 04:50:50.998826: step: 2076/529, loss: 0.06616067886352539
2023-01-23 04:50:52.213843: step: 2080/529, loss: 0.0008478164672851562
2023-01-23 04:50:53.411806: step: 2084/529, loss: 0.4999699592590332
2023-01-23 04:50:54.611699: step: 2088/529, loss: 9.250640687241685e-06
2023-01-23 04:50:55.807384: step: 2092/529, loss: -1.888275073724799e-05
2023-01-23 04:50:56.995032: step: 2096/529, loss: 2.5844574338407256e-05
2023-01-23 04:50:58.220104: step: 2100/529, loss: 0.004937362857162952
2023-01-23 04:50:59.447327: step: 2104/529, loss: 0.003136062528938055
2023-01-23 04:51:00.660202: step: 2108/529, loss: 0.06406402587890625
2023-01-23 04:51:01.875715: step: 2112/529, loss: 1.1634827387752011e-05
2023-01-23 04:51:03.039639: step: 2116/529, loss: 0.001333046006038785
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.6014418125643667, 'r': 0.7776298268974701, 'f1': 0.6782810685249709}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6387686387686388, 'r': 0.7956860395446375, 'f1': 0.7086446104589113}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
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': 28}
Korean: {'event': {'p': 0.5285714285714286, 'r': 0.5873015873015873, 'f1': 0.556390977443609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
******************************
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 04:51:47.971662: step: 4/529, loss: 1.3732910701946821e-05
2023-01-23 04:51:49.153162: step: 8/529, loss: 0.00113086705096066
2023-01-23 04:51:50.372724: step: 12/529, loss: 0.0009518623119220138
2023-01-23 04:51:51.591328: step: 16/529, loss: 0.0012510300148278475
2023-01-23 04:51:52.789314: step: 20/529, loss: 0.0003692627069540322
2023-01-23 04:51:53.980926: step: 24/529, loss: 0.004490328021347523
2023-01-23 04:51:55.171669: step: 28/529, loss: 0.0005512237548828125
2023-01-23 04:51:56.331800: step: 32/529, loss: 2.079009937006049e-05
2023-01-23 04:51:57.492875: step: 36/529, loss: 2.822876012942288e-05
2023-01-23 04:51:58.668094: step: 40/529, loss: 9.059906005859375e-06
2023-01-23 04:51:59.876264: step: 44/529, loss: 0.004665374755859375
2023-01-23 04:52:01.039071: step: 48/529, loss: 4.253387305652723e-05
2023-01-23 04:52:02.210856: step: 52/529, loss: 0.00018796921358443797
2023-01-23 04:52:03.404408: step: 56/529, loss: 3.719329924933845e-06
2023-01-23 04:52:04.614252: step: 60/529, loss: 0.0008264541975222528
2023-01-23 04:52:05.839311: step: 64/529, loss: 0.004531669896095991
2023-01-23 04:52:07.020797: step: 68/529, loss: 0.001506042550317943
2023-01-23 04:52:08.202912: step: 72/529, loss: 0.05139656364917755
2023-01-23 04:52:09.349892: step: 76/529, loss: 0.00015468598576262593
2023-01-23 04:52:10.512773: step: 80/529, loss: 5.245208740234375e-06
2023-01-23 04:52:11.731113: step: 84/529, loss: 0.006305885501205921
2023-01-23 04:52:12.908190: step: 88/529, loss: 0.0002493858337402344
2023-01-23 04:52:14.104992: step: 92/529, loss: 0.00018024446035269648
2023-01-23 04:52:15.357460: step: 96/529, loss: 0.004341077990829945
2023-01-23 04:52:16.536373: step: 100/529, loss: 0.018564321100711823
2023-01-23 04:52:17.713276: step: 104/529, loss: 0.07999381422996521
2023-01-23 04:52:18.917202: step: 108/529, loss: -3.910064151568804e-06
2023-01-23 04:52:20.132355: step: 112/529, loss: 3.0040741876291577e-06
2023-01-23 04:52:21.303208: step: 116/529, loss: 0.00025177001953125
2023-01-23 04:52:22.492215: step: 120/529, loss: 0.00040907858056016266
2023-01-23 04:52:23.737628: step: 124/529, loss: 0.0024687768891453743
2023-01-23 04:52:24.918062: step: 128/529, loss: -2.670288040462765e-06
2023-01-23 04:52:26.136161: step: 132/529, loss: 4.062652442371473e-05
2023-01-23 04:52:27.315625: step: 136/529, loss: 0.00042972565279342234
2023-01-23 04:52:28.503317: step: 140/529, loss: 0.0980004370212555
2023-01-23 04:52:29.708287: step: 144/529, loss: 0.006424331571906805
2023-01-23 04:52:30.905092: step: 148/529, loss: 0.0010761262383311987
2023-01-23 04:52:32.154614: step: 152/529, loss: 7.343292054429185e-06
2023-01-23 04:52:33.342005: step: 156/529, loss: 0.0018783569103106856
2023-01-23 04:52:34.512815: step: 160/529, loss: 0.02445368841290474
2023-01-23 04:52:35.704185: step: 164/529, loss: 0.007605171296745539
2023-01-23 04:52:36.910105: step: 168/529, loss: 4.3487551010912284e-05
2023-01-23 04:52:38.142081: step: 172/529, loss: 0.0003483772452455014
2023-01-23 04:52:39.307103: step: 176/529, loss: 0.00037403107853606343
2023-01-23 04:52:40.506605: step: 180/529, loss: -1.411438006471144e-05
2023-01-23 04:52:41.680650: step: 184/529, loss: 0.00045795441837981343
2023-01-23 04:52:42.859217: step: 188/529, loss: 4.57763690064894e-06
2023-01-23 04:52:44.061861: step: 192/529, loss: 0.0005281448247842491
2023-01-23 04:52:45.223825: step: 196/529, loss: 0.000709152256604284
2023-01-23 04:52:46.401021: step: 200/529, loss: 1.8119812921213452e-06
2023-01-23 04:52:47.579408: step: 204/529, loss: 3.4999848139705136e-05
2023-01-23 04:52:48.773286: step: 208/529, loss: 3.814697265625e-06
2023-01-23 04:52:49.927759: step: 212/529, loss: 0.00015144348435569555
2023-01-23 04:52:51.083142: step: 216/529, loss: 2.098083541568485e-06
2023-01-23 04:52:52.258418: step: 220/529, loss: 2.9182436264818534e-05
2023-01-23 04:52:53.440563: step: 224/529, loss: 0.03857875242829323
2023-01-23 04:52:54.674849: step: 228/529, loss: 0.004447269719094038
2023-01-23 04:52:55.846498: step: 232/529, loss: 0.0024159906897693872
2023-01-23 04:52:57.041987: step: 236/529, loss: 0.0012336730724200606
2023-01-23 04:52:58.265228: step: 240/529, loss: 0.003175163408741355
2023-01-23 04:52:59.440802: step: 244/529, loss: -1.1253356205997989e-05
2023-01-23 04:53:00.643982: step: 248/529, loss: 0.01205539796501398
2023-01-23 04:53:01.918649: step: 252/529, loss: 0.00443878211081028
2023-01-23 04:53:03.131614: step: 256/529, loss: 0.001834773924201727
2023-01-23 04:53:04.363909: step: 260/529, loss: 0.03584964573383331
2023-01-23 04:53:05.597784: step: 264/529, loss: 3.623962811616366e-06
2023-01-23 04:53:06.800292: step: 268/529, loss: 0.10174474120140076
2023-01-23 04:53:07.983203: step: 272/529, loss: 0.00570142874494195
2023-01-23 04:53:09.150839: step: 276/529, loss: 0.00019626619177870452
2023-01-23 04:53:10.369890: step: 280/529, loss: 0.5596234202384949
2023-01-23 04:53:11.555360: step: 284/529, loss: 0.019455909729003906
2023-01-23 04:53:12.741796: step: 288/529, loss: 9.880066500045359e-05
2023-01-23 04:53:13.959237: step: 292/529, loss: 0.0023687363136559725
2023-01-23 04:53:15.182376: step: 296/529, loss: 0.026824951171875
2023-01-23 04:53:16.393456: step: 300/529, loss: 0.0022735595703125
2023-01-23 04:53:17.545733: step: 304/529, loss: 0.0002544402959756553
2023-01-23 04:53:18.743398: step: 308/529, loss: 0.027847671881318092
2023-01-23 04:53:19.940291: step: 312/529, loss: 0.0008834838517941535
2023-01-23 04:53:21.114538: step: 316/529, loss: 0.023713111877441406
2023-01-23 04:53:22.311420: step: 320/529, loss: 0.0009000778663903475
2023-01-23 04:53:23.492250: step: 324/529, loss: 0.005767631810158491
2023-01-23 04:53:24.713734: step: 328/529, loss: 0.04710369184613228
2023-01-23 04:53:25.992540: step: 332/529, loss: 0.0007384300697594881
2023-01-23 04:53:27.159487: step: 336/529, loss: 0.000423240679083392
2023-01-23 04:53:28.393036: step: 340/529, loss: 9.632110595703125e-05
2023-01-23 04:53:29.580117: step: 344/529, loss: 0.05529461055994034
2023-01-23 04:53:30.775399: step: 348/529, loss: 0.00020985603623557836
2023-01-23 04:53:31.976183: step: 352/529, loss: 0.007557106204330921
2023-01-23 04:53:33.144077: step: 356/529, loss: 0.00012722014798782766
2023-01-23 04:53:34.352039: step: 360/529, loss: 0.0001659393310546875
2023-01-23 04:53:35.576683: step: 364/529, loss: 1.4019012269272935e-05
2023-01-23 04:53:36.738818: step: 368/529, loss: 3.623962356869015e-06
2023-01-23 04:53:37.911146: step: 372/529, loss: 0.00018978118896484375
2023-01-23 04:53:39.060375: step: 376/529, loss: 0.23175106942653656
2023-01-23 04:53:40.216641: step: 380/529, loss: 2.9277802241267636e-05
2023-01-23 04:53:41.427171: step: 384/529, loss: -5.722046125811175e-07
2023-01-23 04:53:42.623859: step: 388/529, loss: 0.027511978521943092
2023-01-23 04:53:43.794914: step: 392/529, loss: 4.4441225327318534e-05
2023-01-23 04:53:44.965952: step: 396/529, loss: 0.012281608767807484
2023-01-23 04:53:46.157906: step: 400/529, loss: 1.068115216185106e-05
2023-01-23 04:53:47.369742: step: 404/529, loss: 0.0023773193825036287
2023-01-23 04:53:48.583801: step: 408/529, loss: 0.004778099246323109
2023-01-23 04:53:49.753556: step: 412/529, loss: 2.288818359375e-05
2023-01-23 04:53:50.995750: step: 416/529, loss: 0.03590993955731392
2023-01-23 04:53:52.250104: step: 420/529, loss: 6.847381155239418e-05
2023-01-23 04:53:53.428772: step: 424/529, loss: 0.0026382445357739925
2023-01-23 04:53:54.663751: step: 428/529, loss: 0.018700027838349342
2023-01-23 04:53:55.884963: step: 432/529, loss: 0.004219437018036842
2023-01-23 04:53:57.060021: step: 436/529, loss: 0.007000541780143976
2023-01-23 04:53:58.300391: step: 440/529, loss: 9.965896424546372e-06
2023-01-23 04:53:59.463163: step: 444/529, loss: 3.814697265625e-06
2023-01-23 04:54:00.692780: step: 448/529, loss: 0.005376577842980623
2023-01-23 04:54:01.899358: step: 452/529, loss: 0.0016256332164630294
2023-01-23 04:54:03.108271: step: 456/529, loss: 9.15527380129788e-06
2023-01-23 04:54:04.309810: step: 460/529, loss: 0.00023155211238190532
2023-01-23 04:54:05.530443: step: 464/529, loss: 0.0001810073881642893
2023-01-23 04:54:06.718452: step: 468/529, loss: 0.003034305525943637
2023-01-23 04:54:07.899392: step: 472/529, loss: 0.0027370452880859375
2023-01-23 04:54:09.126925: step: 476/529, loss: 0.010607671923935413
2023-01-23 04:54:10.338931: step: 480/529, loss: 0.00036487579927779734
2023-01-23 04:54:11.541644: step: 484/529, loss: 0.005246544256806374
2023-01-23 04:54:12.732356: step: 488/529, loss: 0.006982612423598766
2023-01-23 04:54:13.935084: step: 492/529, loss: 0.0002725601370912045
2023-01-23 04:54:15.114636: step: 496/529, loss: 0.0001316070556640625
2023-01-23 04:54:16.330640: step: 500/529, loss: 0.0005240440368652344
2023-01-23 04:54:17.521942: step: 504/529, loss: 0.05100107565522194
2023-01-23 04:54:18.740648: step: 508/529, loss: 3.8814545405330136e-05
2023-01-23 04:54:19.918325: step: 512/529, loss: 0.0017307280795648694
2023-01-23 04:54:21.105390: step: 516/529, loss: 0.026123715564608574
2023-01-23 04:54:22.274872: step: 520/529, loss: 0.0002359390346100554
2023-01-23 04:54:23.521763: step: 524/529, loss: 1.9359587895451114e-05
2023-01-23 04:54:24.749380: step: 528/529, loss: 0.04048128426074982
2023-01-23 04:54:25.930133: step: 532/529, loss: 0.0003334045468363911
2023-01-23 04:54:27.096839: step: 536/529, loss: 0.002658843994140625
2023-01-23 04:54:28.330723: step: 540/529, loss: 0.02190380170941353
2023-01-23 04:54:29.536351: step: 544/529, loss: 2.002715973503655e-06
2023-01-23 04:54:30.751647: step: 548/529, loss: 0.005922365467995405
2023-01-23 04:54:31.911186: step: 552/529, loss: 2.7561187380342744e-05
2023-01-23 04:54:33.118469: step: 556/529, loss: 3.0183791750459932e-05
2023-01-23 04:54:34.305687: step: 560/529, loss: 0.031472206115722656
2023-01-23 04:54:35.507421: step: 564/529, loss: 5.950927879894152e-05
2023-01-23 04:54:36.693216: step: 568/529, loss: 9.536743306171047e-08
2023-01-23 04:54:37.861412: step: 572/529, loss: 0.005866241175681353
2023-01-23 04:54:39.028615: step: 576/529, loss: 0.00015716553025413305
2023-01-23 04:54:40.184653: step: 580/529, loss: 0.00015401840209960938
2023-01-23 04:54:41.338671: step: 584/529, loss: 1.468658410885837e-05
2023-01-23 04:54:42.475927: step: 588/529, loss: 0.0015761376125738025
2023-01-23 04:54:43.709977: step: 592/529, loss: 0.00042381288949400187
2023-01-23 04:54:44.943500: step: 596/529, loss: 0.016824722290039062
2023-01-23 04:54:46.164998: step: 600/529, loss: -2.6702880859375e-05
2023-01-23 04:54:47.321217: step: 604/529, loss: 0.009059811010956764
2023-01-23 04:54:48.549156: step: 608/529, loss: 7.624625868629664e-05
2023-01-23 04:54:49.765694: step: 612/529, loss: 0.008725929073989391
2023-01-23 04:54:50.894757: step: 616/529, loss: 6.222724914550781e-05
2023-01-23 04:54:52.107399: step: 620/529, loss: 0.005821752827614546
2023-01-23 04:54:53.331755: step: 624/529, loss: 0.043379951268434525
2023-01-23 04:54:54.530109: step: 628/529, loss: 0.0006338119274005294
2023-01-23 04:54:55.756737: step: 632/529, loss: 0.0015340804820880294
2023-01-23 04:54:56.913060: step: 636/529, loss: 0.0014158248668536544
2023-01-23 04:54:58.089307: step: 640/529, loss: 3.643035961431451e-05
2023-01-23 04:54:59.241139: step: 644/529, loss: -7.057189577608369e-06
2023-01-23 04:55:00.454917: step: 648/529, loss: 0.04231424629688263
2023-01-23 04:55:01.667627: step: 652/529, loss: 0.03902072831988335
2023-01-23 04:55:02.891919: step: 656/529, loss: 0.0033262253273278475
2023-01-23 04:55:04.080848: step: 660/529, loss: 2.8419495720299892e-05
2023-01-23 04:55:05.300982: step: 664/529, loss: 7.724761962890625e-05
2023-01-23 04:55:06.534547: step: 668/529, loss: 0.10927601158618927
2023-01-23 04:55:07.678249: step: 672/529, loss: 0.016883373260498047
2023-01-23 04:55:08.872629: step: 676/529, loss: 0.01273498497903347
2023-01-23 04:55:10.081124: step: 680/529, loss: 0.00022220611572265625
2023-01-23 04:55:11.254278: step: 684/529, loss: -9.5367431640625e-07
2023-01-23 04:55:12.459978: step: 688/529, loss: 0.000442695600213483
2023-01-23 04:55:13.679952: step: 692/529, loss: 5.91278076171875e-05
2023-01-23 04:55:14.870399: step: 696/529, loss: 0.036199573427438736
2023-01-23 04:55:16.045862: step: 700/529, loss: 0.0010829925304278731
2023-01-23 04:55:17.258932: step: 704/529, loss: 1.2445449101505801e-05
2023-01-23 04:55:18.499805: step: 708/529, loss: 0.025235366076231003
2023-01-23 04:55:19.733983: step: 712/529, loss: 0.2874128818511963
2023-01-23 04:55:20.928512: step: 716/529, loss: 0.00248889927752316
2023-01-23 04:55:22.134567: step: 720/529, loss: 0.0007202147971838713
2023-01-23 04:55:23.322824: step: 724/529, loss: 0.011014747433364391
2023-01-23 04:55:24.469000: step: 728/529, loss: 0.0002038955717580393
2023-01-23 04:55:25.642106: step: 732/529, loss: 0.00037536618765443563
2023-01-23 04:55:26.862515: step: 736/529, loss: 0.00024862290592864156
2023-01-23 04:55:28.068366: step: 740/529, loss: 4.6443943574558944e-05
2023-01-23 04:55:29.327464: step: 744/529, loss: 0.04201088100671768
2023-01-23 04:55:30.547454: step: 748/529, loss: 0.00036363600520417094
2023-01-23 04:55:31.751404: step: 752/529, loss: 3.943443516618572e-05
2023-01-23 04:55:32.996306: step: 756/529, loss: 0.0028442381881177425
2023-01-23 04:55:34.188509: step: 760/529, loss: 0.002449417021125555
2023-01-23 04:55:35.413288: step: 764/529, loss: 0.00412063580006361
2023-01-23 04:55:36.590648: step: 768/529, loss: 1.6021729607018642e-05
2023-01-23 04:55:37.789733: step: 772/529, loss: 0.014474011026322842
2023-01-23 04:55:39.003332: step: 776/529, loss: 0.0006295203929767013
2023-01-23 04:55:40.263343: step: 780/529, loss: 0.05057773366570473
2023-01-23 04:55:41.507308: step: 784/529, loss: 0.008190535940229893
2023-01-23 04:55:42.674852: step: 788/529, loss: 0.006695294287055731
2023-01-23 04:55:43.886391: step: 792/529, loss: 7.5292591645848e-05
2023-01-23 04:55:45.059794: step: 796/529, loss: 0.0003414154052734375
2023-01-23 04:55:46.242458: step: 800/529, loss: 0.0004547119315247983
2023-01-23 04:55:47.417055: step: 804/529, loss: 0.00012836456880904734
2023-01-23 04:55:48.620851: step: 808/529, loss: 0.0083503732457757
2023-01-23 04:55:49.770877: step: 812/529, loss: 1.5687943232478574e-05
2023-01-23 04:55:50.941267: step: 816/529, loss: 0.027898598462343216
2023-01-23 04:55:52.157553: step: 820/529, loss: 0.0020931244362145662
2023-01-23 04:55:53.362089: step: 824/529, loss: 0.0005487442249432206
2023-01-23 04:55:54.506079: step: 828/529, loss: 1.4972686585679185e-05
2023-01-23 04:55:55.771951: step: 832/529, loss: 0.0009633064619265497
2023-01-23 04:55:56.991490: step: 836/529, loss: 0.02407073974609375
2023-01-23 04:55:58.172848: step: 840/529, loss: 2.8133392333984375e-05
2023-01-23 04:55:59.374615: step: 844/529, loss: 0.0002899169921875
2023-01-23 04:56:00.584282: step: 848/529, loss: 0.00021638871112372726
2023-01-23 04:56:01.814586: step: 852/529, loss: 0.004264450166374445
2023-01-23 04:56:03.082720: step: 856/529, loss: 0.014208793640136719
2023-01-23 04:56:04.275987: step: 860/529, loss: 0.0017125130398198962
2023-01-23 04:56:05.514497: step: 864/529, loss: 0.0013696671230718493
2023-01-23 04:56:06.718394: step: 868/529, loss: 0.0005676269647665322
2023-01-23 04:56:07.944997: step: 872/529, loss: 0.016567612066864967
2023-01-23 04:56:09.167209: step: 876/529, loss: 0.0013925553066655993
2023-01-23 04:56:10.360832: step: 880/529, loss: 1.4400482541532256e-05
2023-01-23 04:56:11.556403: step: 884/529, loss: 0.0003388405020814389
2023-01-23 04:56:12.723593: step: 888/529, loss: 5.722046125811175e-07
2023-01-23 04:56:13.953308: step: 892/529, loss: 0.0003335952933412045
2023-01-23 04:56:15.159014: step: 896/529, loss: 0.000936317490413785
2023-01-23 04:56:16.345744: step: 900/529, loss: 0.0017990111373364925
2023-01-23 04:56:17.521801: step: 904/529, loss: 0.00029745104257017374
2023-01-23 04:56:18.701397: step: 908/529, loss: 0.08940735459327698
2023-01-23 04:56:19.886937: step: 912/529, loss: -3.52859501617786e-06
2023-01-23 04:56:21.076154: step: 916/529, loss: 0.0001536846102681011
2023-01-23 04:56:22.282331: step: 920/529, loss: -9.72747784544481e-06
2023-01-23 04:56:23.526345: step: 924/529, loss: 0.004598808474838734
2023-01-23 04:56:24.730353: step: 928/529, loss: 0.0011684418423101306
2023-01-23 04:56:25.995446: step: 932/529, loss: -9.5367431640625e-06
2023-01-23 04:56:27.186534: step: 936/529, loss: 8.39233416627394e-06
2023-01-23 04:56:28.351949: step: 940/529, loss: 0.0036809921730309725
2023-01-23 04:56:29.561619: step: 944/529, loss: 0.00024070740619208664
2023-01-23 04:56:30.756326: step: 948/529, loss: 0.0005346298567019403
2023-01-23 04:56:31.962488: step: 952/529, loss: 0.0014528273604810238
2023-01-23 04:56:33.150631: step: 956/529, loss: 0.0001371383696096018
2023-01-23 04:56:34.329289: step: 960/529, loss: 1.201629675051663e-05
2023-01-23 04:56:35.525043: step: 964/529, loss: 0.0548831969499588
2023-01-23 04:56:36.742895: step: 968/529, loss: 0.0005851269233971834
2023-01-23 04:56:37.912415: step: 972/529, loss: 0.013447761535644531
2023-01-23 04:56:39.090596: step: 976/529, loss: -1.4495848517981358e-05
2023-01-23 04:56:40.294608: step: 980/529, loss: 0.022922707721590996
2023-01-23 04:56:41.471160: step: 984/529, loss: 1.983642505365424e-05
2023-01-23 04:56:42.647491: step: 988/529, loss: 0.0060821534134447575
2023-01-23 04:56:43.895092: step: 992/529, loss: 0.000286102294921875
2023-01-23 04:56:45.102790: step: 996/529, loss: 1.907349087559851e-07
2023-01-23 04:56:46.298272: step: 1000/529, loss: 0.0013631820911541581
2023-01-23 04:56:47.453871: step: 1004/529, loss: 0.0034191131126135588
2023-01-23 04:56:48.619735: step: 1008/529, loss: 0.08127987384796143
2023-01-23 04:56:49.823606: step: 1012/529, loss: 0.0008543491712771356
2023-01-23 04:56:51.025135: step: 1016/529, loss: 0.0005819320795126259
2023-01-23 04:56:52.201492: step: 1020/529, loss: 0.0015231609577313066
2023-01-23 04:56:53.402934: step: 1024/529, loss: 0.028425026684999466
2023-01-23 04:56:54.629175: step: 1028/529, loss: 0.007377576548606157
2023-01-23 04:56:55.792685: step: 1032/529, loss: 0.0002226829674327746
2023-01-23 04:56:56.978607: step: 1036/529, loss: 0.0004733086097985506
2023-01-23 04:56:58.174070: step: 1040/529, loss: 0.0069751739501953125
2023-01-23 04:56:59.406587: step: 1044/529, loss: 0.0013044357765465975
2023-01-23 04:57:00.581820: step: 1048/529, loss: 0.008054542355239391
2023-01-23 04:57:01.753101: step: 1052/529, loss: 0.0001636505185160786
2023-01-23 04:57:02.982502: step: 1056/529, loss: 0.0007921219221316278
2023-01-23 04:57:04.135807: step: 1060/529, loss: 0.0005320549244061112
2023-01-23 04:57:05.321693: step: 1064/529, loss: 0.0011274099815636873
2023-01-23 04:57:06.495423: step: 1068/529, loss: 0.010270977392792702
2023-01-23 04:57:07.674505: step: 1072/529, loss: 1.869201696536038e-05
2023-01-23 04:57:08.859937: step: 1076/529, loss: 0.0002075195370707661
2023-01-23 04:57:10.055910: step: 1080/529, loss: 0.7307483553886414
2023-01-23 04:57:11.243872: step: 1084/529, loss: 0.010613000951707363
2023-01-23 04:57:12.448654: step: 1088/529, loss: 8.621215965831652e-05
2023-01-23 04:57:13.619835: step: 1092/529, loss: 0.007846069522202015
2023-01-23 04:57:14.767034: step: 1096/529, loss: 6.523132469737902e-05
2023-01-23 04:57:16.005944: step: 1100/529, loss: 8.931160846259445e-05
2023-01-23 04:57:17.176047: step: 1104/529, loss: 0.0005597114795818925
2023-01-23 04:57:18.380323: step: 1108/529, loss: 2.4795534045551904e-05
2023-01-23 04:57:19.556029: step: 1112/529, loss: 0.00027465823222883046
2023-01-23 04:57:20.723543: step: 1116/529, loss: 3.9529801142634824e-05
2023-01-23 04:57:21.934060: step: 1120/529, loss: 0.007442093454301357
2023-01-23 04:57:23.116635: step: 1124/529, loss: 0.00012378694373182952
2023-01-23 04:57:24.300888: step: 1128/529, loss: 0.028606891632080078
2023-01-23 04:57:25.470224: step: 1132/529, loss: 0.01957225799560547
2023-01-23 04:57:26.646909: step: 1136/529, loss: 0.007449245546013117
2023-01-23 04:57:27.816257: step: 1140/529, loss: 4.9591064453125e-05
2023-01-23 04:57:29.016455: step: 1144/529, loss: 5.254745337879285e-05
2023-01-23 04:57:30.199603: step: 1148/529, loss: 0.0027244091033935547
2023-01-23 04:57:31.508439: step: 1152/529, loss: 0.00439033517614007
2023-01-23 04:57:32.669932: step: 1156/529, loss: 6.294250852079131e-06
2023-01-23 04:57:33.876066: step: 1160/529, loss: 0.000913429306820035
2023-01-23 04:57:35.093894: step: 1164/529, loss: 0.009033155627548695
2023-01-23 04:57:36.301232: step: 1168/529, loss: 0.00177001953125
2023-01-23 04:57:37.481513: step: 1172/529, loss: 0.00033798220101743937
2023-01-23 04:57:38.682021: step: 1176/529, loss: 0.002139186952263117
2023-01-23 04:57:39.906892: step: 1180/529, loss: 0.0073337554931640625
2023-01-23 04:57:41.153951: step: 1184/529, loss: 0.0008852005121298134
2023-01-23 04:57:42.337089: step: 1188/529, loss: 0.0025569917634129524
2023-01-23 04:57:43.555465: step: 1192/529, loss: 0.00018558502779342234
2023-01-23 04:57:44.733120: step: 1196/529, loss: 0.0025222781114280224
2023-01-23 04:57:45.926635: step: 1200/529, loss: 0.002098608063533902
2023-01-23 04:57:47.135076: step: 1204/529, loss: 0.00010204315185546875
2023-01-23 04:57:48.379303: step: 1208/529, loss: 0.002108001848682761
2023-01-23 04:57:49.577789: step: 1212/529, loss: 0.00040225981501862407
2023-01-23 04:57:50.801074: step: 1216/529, loss: 0.0001434326113667339
2023-01-23 04:57:51.980182: step: 1220/529, loss: 2.765655608527595e-06
2023-01-23 04:57:53.177145: step: 1224/529, loss: 0.0033040824346244335
2023-01-23 04:57:54.378674: step: 1228/529, loss: -1.287460349885805e-06
2023-01-23 04:57:55.587243: step: 1232/529, loss: 6.12258882028982e-05
2023-01-23 04:57:56.785984: step: 1236/529, loss: 0.0016671180492267013
2023-01-23 04:57:58.032911: step: 1240/529, loss: 0.628967821598053
2023-01-23 04:57:59.236903: step: 1244/529, loss: 8.335113670909777e-05
2023-01-23 04:58:00.439563: step: 1248/529, loss: 2.28881845032447e-06
2023-01-23 04:58:01.644756: step: 1252/529, loss: 0.0017341615166515112
2023-01-23 04:58:02.795567: step: 1256/529, loss: 0.05816249921917915
2023-01-23 04:58:03.984783: step: 1260/529, loss: 0.00010776520502986386
2023-01-23 04:58:05.156365: step: 1264/529, loss: 0.01769847795367241
2023-01-23 04:58:06.341794: step: 1268/529, loss: 0.06173725426197052
2023-01-23 04:58:07.538234: step: 1272/529, loss: 0.0031499862670898438
2023-01-23 04:58:08.772811: step: 1276/529, loss: 0.09998436272144318
2023-01-23 04:58:10.010445: step: 1280/529, loss: 4.253387305652723e-05
2023-01-23 04:58:11.227298: step: 1284/529, loss: 0.0032931803725659847
2023-01-23 04:58:12.399904: step: 1288/529, loss: 0.002288436982780695
2023-01-23 04:58:13.605575: step: 1292/529, loss: 1.1157990229548886e-05
2023-01-23 04:58:14.754657: step: 1296/529, loss: 3.814697322468419e-07
2023-01-23 04:58:15.954833: step: 1300/529, loss: 8.668899681651965e-05
2023-01-23 04:58:17.152564: step: 1304/529, loss: 0.002167224884033203
2023-01-23 04:58:18.322966: step: 1308/529, loss: 0.05486641079187393
2023-01-23 04:58:19.498793: step: 1312/529, loss: 0.0024099352303892374
2023-01-23 04:58:20.730699: step: 1316/529, loss: 0.020002080127596855
2023-01-23 04:58:21.939334: step: 1320/529, loss: 4.19616708313697e-06
2023-01-23 04:58:23.129076: step: 1324/529, loss: 0.010896253399550915
2023-01-23 04:58:24.388690: step: 1328/529, loss: 0.05603199079632759
2023-01-23 04:58:25.587531: step: 1332/529, loss: 0.00064849853515625
2023-01-23 04:58:26.812972: step: 1336/529, loss: 0.0005826950073242188
2023-01-23 04:58:28.031002: step: 1340/529, loss: 0.04306488111615181
2023-01-23 04:58:29.218622: step: 1344/529, loss: 0.0001544952392578125
2023-01-23 04:58:30.407210: step: 1348/529, loss: 0.07240915298461914
2023-01-23 04:58:31.583846: step: 1352/529, loss: 0.0008665084606036544
2023-01-23 04:58:32.774083: step: 1356/529, loss: 0.10205211490392685
2023-01-23 04:58:34.002523: step: 1360/529, loss: 0.3231346011161804
2023-01-23 04:58:35.174822: step: 1364/529, loss: 0.038396645337343216
2023-01-23 04:58:36.366944: step: 1368/529, loss: 0.10998497158288956
2023-01-23 04:58:37.544844: step: 1372/529, loss: 0.034264590591192245
2023-01-23 04:58:38.744855: step: 1376/529, loss: 0.0009187698597088456
2023-01-23 04:58:39.911140: step: 1380/529, loss: 0.013098526746034622
2023-01-23 04:58:41.114046: step: 1384/529, loss: 0.0007959366193972528
2023-01-23 04:58:42.371210: step: 1388/529, loss: 7.915496098576114e-06
2023-01-23 04:58:43.547901: step: 1392/529, loss: 0.0016950607532635331
2023-01-23 04:58:44.763610: step: 1396/529, loss: 0.009640026837587357
2023-01-23 04:58:45.936905: step: 1400/529, loss: 0.03501405939459801
2023-01-23 04:58:47.132609: step: 1404/529, loss: 0.004276084713637829
2023-01-23 04:58:48.277977: step: 1408/529, loss: 0.005029868800193071
2023-01-23 04:58:49.459462: step: 1412/529, loss: 0.0031041146721690893
2023-01-23 04:58:50.632302: step: 1416/529, loss: 5.054474058852065e-06
2023-01-23 04:58:51.854356: step: 1420/529, loss: 4.00543194700731e-06
2023-01-23 04:58:53.039194: step: 1424/529, loss: 5.7029727031476796e-05
2023-01-23 04:58:54.245858: step: 1428/529, loss: 2.8228761948412284e-05
2023-01-23 04:58:55.432412: step: 1432/529, loss: 0.06308785080909729
2023-01-23 04:58:56.602564: step: 1436/529, loss: 0.0008561611175537109
2023-01-23 04:58:57.803724: step: 1440/529, loss: 2.4700164431123994e-05
2023-01-23 04:58:58.988808: step: 1444/529, loss: 0.003226661588996649
2023-01-23 04:59:00.154663: step: 1448/529, loss: 0.004049873445183039
2023-01-23 04:59:01.316839: step: 1452/529, loss: 0.0008733749273233116
2023-01-23 04:59:02.513788: step: 1456/529, loss: 0.00016326905461028218
2023-01-23 04:59:03.715310: step: 1460/529, loss: 0.00029439927311614156
2023-01-23 04:59:04.995397: step: 1464/529, loss: 0.003342247102409601
2023-01-23 04:59:06.165724: step: 1468/529, loss: 0.023175524547696114
2023-01-23 04:59:07.345725: step: 1472/529, loss: 0.019219398498535156
2023-01-23 04:59:08.509777: step: 1476/529, loss: 0.024181175976991653
2023-01-23 04:59:09.668648: step: 1480/529, loss: 0.00043621062650345266
2023-01-23 04:59:10.874043: step: 1484/529, loss: 0.0004558563232421875
2023-01-23 04:59:12.040943: step: 1488/529, loss: 6.632805161643773e-05
2023-01-23 04:59:13.252010: step: 1492/529, loss: 0.0022317885886877775
2023-01-23 04:59:14.455247: step: 1496/529, loss: 0.0036783218383789062
2023-01-23 04:59:15.674034: step: 1500/529, loss: 0.33480775356292725
2023-01-23 04:59:16.849509: step: 1504/529, loss: 5.722046125811175e-07
2023-01-23 04:59:18.062794: step: 1508/529, loss: 0.0043860916048288345
2023-01-23 04:59:19.237882: step: 1512/529, loss: 2.2506716049974784e-05
2023-01-23 04:59:20.438979: step: 1516/529, loss: 0.0005534648662433028
2023-01-23 04:59:21.627141: step: 1520/529, loss: 0.0030406953301280737
2023-01-23 04:59:22.819847: step: 1524/529, loss: -2.098083541568485e-06
2023-01-23 04:59:24.076254: step: 1528/529, loss: 0.0005517959361895919
2023-01-23 04:59:25.323465: step: 1532/529, loss: 0.056876279413700104
2023-01-23 04:59:26.529050: step: 1536/529, loss: 0.008852005004882812
2023-01-23 04:59:27.713064: step: 1540/529, loss: 4.76837158203125e-06
2023-01-23 04:59:28.923666: step: 1544/529, loss: 0.0021227120887488127
2023-01-23 04:59:30.119636: step: 1548/529, loss: 0.0013967513805255294
2023-01-23 04:59:31.324839: step: 1552/529, loss: 9.71794142969884e-05
2023-01-23 04:59:32.517770: step: 1556/529, loss: 0.03422565385699272
2023-01-23 04:59:33.738781: step: 1560/529, loss: 0.028199482709169388
2023-01-23 04:59:34.957325: step: 1564/529, loss: 0.00015182494826149195
2023-01-23 04:59:36.133571: step: 1568/529, loss: 0.038149263709783554
2023-01-23 04:59:37.345125: step: 1572/529, loss: 0.00139789585955441
2023-01-23 04:59:38.540073: step: 1576/529, loss: 0.00022726059250999242
2023-01-23 04:59:39.725385: step: 1580/529, loss: 0.0001848220854299143
2023-01-23 04:59:40.955901: step: 1584/529, loss: 0.00015487671771552414
2023-01-23 04:59:42.193050: step: 1588/529, loss: 0.00145721435546875
2023-01-23 04:59:43.425357: step: 1592/529, loss: 0.0006259918445721269
2023-01-23 04:59:44.636803: step: 1596/529, loss: 5.14984139954322e-06
2023-01-23 04:59:45.866510: step: 1600/529, loss: 0.0008106232271529734
2023-01-23 04:59:47.047576: step: 1604/529, loss: -2.1076202756376006e-05
2023-01-23 04:59:48.197329: step: 1608/529, loss: 0.0005048752063885331
2023-01-23 04:59:49.395777: step: 1612/529, loss: 0.0017232894897460938
2023-01-23 04:59:50.620733: step: 1616/529, loss: 0.0001220703125
2023-01-23 04:59:51.810445: step: 1620/529, loss: 0.0008788108825683594
2023-01-23 04:59:53.037863: step: 1624/529, loss: 0.0016613006591796875
2023-01-23 04:59:54.238752: step: 1628/529, loss: 0.015953348949551582
2023-01-23 04:59:55.415782: step: 1632/529, loss: 0.00039677618769928813
2023-01-23 04:59:56.618900: step: 1636/529, loss: 0.00019750595674850047
2023-01-23 04:59:57.819414: step: 1640/529, loss: 7.686615572310984e-05
2023-01-23 04:59:59.006942: step: 1644/529, loss: 3.319978759463993e-06
2023-01-23 05:00:00.160667: step: 1648/529, loss: 0.0036615373101085424
2023-01-23 05:00:01.360490: step: 1652/529, loss: 0.006658363621681929
2023-01-23 05:00:02.555215: step: 1656/529, loss: 0.005681514739990234
2023-01-23 05:00:03.810995: step: 1660/529, loss: 0.0007167815929278731
2023-01-23 05:00:04.993450: step: 1664/529, loss: 4.6539309551008046e-05
2023-01-23 05:00:06.140403: step: 1668/529, loss: -5.7220458984375e-06
2023-01-23 05:00:07.344888: step: 1672/529, loss: 0.0235443115234375
2023-01-23 05:00:08.559086: step: 1676/529, loss: 0.002525901887565851
2023-01-23 05:00:09.754671: step: 1680/529, loss: 2.002716064453125e-05
2023-01-23 05:00:10.942480: step: 1684/529, loss: 3.3664702641544864e-05
2023-01-23 05:00:12.081023: step: 1688/529, loss: 0.0007604121929034591
2023-01-23 05:00:13.281370: step: 1692/529, loss: 0.004181290045380592
2023-01-23 05:00:14.488136: step: 1696/529, loss: 0.004848528187721968
2023-01-23 05:00:15.684254: step: 1700/529, loss: 0.006644248962402344
2023-01-23 05:00:16.875156: step: 1704/529, loss: 0.014876174740493298
2023-01-23 05:00:18.061982: step: 1708/529, loss: 0.06999950855970383
2023-01-23 05:00:19.230063: step: 1712/529, loss: 0.0003153800789732486
2023-01-23 05:00:20.451541: step: 1716/529, loss: 0.0019784928299486637
2023-01-23 05:00:21.660003: step: 1720/529, loss: 7.07626313669607e-05
2023-01-23 05:00:22.840797: step: 1724/529, loss: 0.02034597471356392
2023-01-23 05:00:24.037409: step: 1728/529, loss: 0.00048065188457258046
2023-01-23 05:00:25.256294: step: 1732/529, loss: 1.5853469371795654
2023-01-23 05:00:26.453522: step: 1736/529, loss: 0.010175133123993874
2023-01-23 05:00:27.627610: step: 1740/529, loss: 0.0001585006684763357
2023-01-23 05:00:28.825614: step: 1744/529, loss: 0.0015062332386150956
2023-01-23 05:00:30.015462: step: 1748/529, loss: 1.392364538332913e-05
2023-01-23 05:00:31.203322: step: 1752/529, loss: 0.04295406490564346
2023-01-23 05:00:32.458801: step: 1756/529, loss: 0.00018281936354469508
2023-01-23 05:00:33.653839: step: 1760/529, loss: 3.719329924933845e-06
2023-01-23 05:00:34.874767: step: 1764/529, loss: 0.007261753082275391
2023-01-23 05:00:36.084280: step: 1768/529, loss: 0.005169677548110485
2023-01-23 05:00:37.246042: step: 1772/529, loss: 0.0004545212141238153
2023-01-23 05:00:38.489119: step: 1776/529, loss: 0.008730506524443626
2023-01-23 05:00:39.691608: step: 1780/529, loss: 3.43322744811303e-06
2023-01-23 05:00:40.878589: step: 1784/529, loss: 0.0007745742914266884
2023-01-23 05:00:42.061233: step: 1788/529, loss: 2.632141149661038e-05
2023-01-23 05:00:43.238742: step: 1792/529, loss: 0.002716904738917947
2023-01-23 05:00:44.401441: step: 1796/529, loss: 0.00016779899306129664
2023-01-23 05:00:45.562459: step: 1800/529, loss: 3.0708310077898204e-05
2023-01-23 05:00:46.710371: step: 1804/529, loss: 0.0017543792491778731
2023-01-23 05:00:47.903939: step: 1808/529, loss: 0.049134161323308945
2023-01-23 05:00:49.146698: step: 1812/529, loss: 0.2432354986667633
2023-01-23 05:00:50.337767: step: 1816/529, loss: 0.00014219283184502274
2023-01-23 05:00:51.515397: step: 1820/529, loss: 0.03889045864343643
2023-01-23 05:00:52.686740: step: 1824/529, loss: 0.00013351438974495977
2023-01-23 05:00:53.821659: step: 1828/529, loss: 0.08385400474071503
2023-01-23 05:00:55.054407: step: 1832/529, loss: 0.007090759463608265
2023-01-23 05:00:56.245033: step: 1836/529, loss: 0.0006044387700967491
2023-01-23 05:00:57.448215: step: 1840/529, loss: 0.00013494491577148438
2023-01-23 05:00:58.627721: step: 1844/529, loss: 0.0032146451994776726
2023-01-23 05:00:59.789636: step: 1848/529, loss: 9.183883958030492e-05
2023-01-23 05:01:00.955601: step: 1852/529, loss: -5.674362000718247e-06
2023-01-23 05:01:02.208352: step: 1856/529, loss: 0.00024547576322220266
2023-01-23 05:01:03.422144: step: 1860/529, loss: 0.00048656464787200093
2023-01-23 05:01:04.608076: step: 1864/529, loss: 0.0027584077324718237
2023-01-23 05:01:05.788108: step: 1868/529, loss: 0.0001434326113667339
2023-01-23 05:01:06.970563: step: 1872/529, loss: 0.0009277344215661287
2023-01-23 05:01:08.207407: step: 1876/529, loss: 0.006348991766571999
2023-01-23 05:01:09.398561: step: 1880/529, loss: 0.0003717422659974545
2023-01-23 05:01:10.621451: step: 1884/529, loss: 0.036380767822265625
2023-01-23 05:01:11.779300: step: 1888/529, loss: 0.031036807224154472
2023-01-23 05:01:12.989618: step: 1892/529, loss: 0.0053983209654688835
2023-01-23 05:01:14.181793: step: 1896/529, loss: 3.0708310077898204e-05
2023-01-23 05:01:15.386681: step: 1900/529, loss: 0.00629768380895257
2023-01-23 05:01:16.565635: step: 1904/529, loss: 2.555847095209174e-05
2023-01-23 05:01:17.714406: step: 1908/529, loss: 0.0008892059559002519
2023-01-23 05:01:18.964072: step: 1912/529, loss: 0.0058303833939135075
2023-01-23 05:01:20.133731: step: 1916/529, loss: 6.599426706088707e-05
2023-01-23 05:01:21.299720: step: 1920/529, loss: 0.026189804077148438
2023-01-23 05:01:22.496409: step: 1924/529, loss: 0.01587228663265705
2023-01-23 05:01:23.724937: step: 1928/529, loss: 0.0031957626342773438
2023-01-23 05:01:24.903061: step: 1932/529, loss: -1.430511474609375e-06
2023-01-23 05:01:26.158358: step: 1936/529, loss: 0.004824829287827015
2023-01-23 05:01:27.366859: step: 1940/529, loss: 5.054474240751006e-05
2023-01-23 05:01:28.578444: step: 1944/529, loss: 0.03985634073615074
2023-01-23 05:01:29.795992: step: 1948/529, loss: 0.00010471343557583168
2023-01-23 05:01:31.041334: step: 1952/529, loss: 0.012557410635054111
2023-01-23 05:01:32.240152: step: 1956/529, loss: 0.01804809644818306
2023-01-23 05:01:33.469527: step: 1960/529, loss: 0.004710960201919079
2023-01-23 05:01:34.623832: step: 1964/529, loss: 2.555847095209174e-05
2023-01-23 05:01:35.827920: step: 1968/529, loss: 0.03960246965289116
2023-01-23 05:01:37.031881: step: 1972/529, loss: 0.0014725684886798263
2023-01-23 05:01:38.192577: step: 1976/529, loss: 2.956390289909905e-06
2023-01-23 05:01:39.363780: step: 1980/529, loss: 4.482269287109375e-05
2023-01-23 05:01:40.539077: step: 1984/529, loss: 0.00027980803861282766
2023-01-23 05:01:41.719473: step: 1988/529, loss: 0.0002525329473428428
2023-01-23 05:01:42.892757: step: 1992/529, loss: 1.8978118532686494e-05
2023-01-23 05:01:44.111918: step: 1996/529, loss: 0.005339432042092085
2023-01-23 05:01:45.288657: step: 2000/529, loss: 0.0010305405594408512
2023-01-23 05:01:46.492588: step: 2004/529, loss: 1.0681153071345761e-05
2023-01-23 05:01:47.679410: step: 2008/529, loss: -1.8119812921213452e-06
2023-01-23 05:01:48.870265: step: 2012/529, loss: 3.42369094141759e-05
2023-01-23 05:01:50.045219: step: 2016/529, loss: 0.0003417968691792339
2023-01-23 05:01:51.261797: step: 2020/529, loss: 0.0011999130947515368
2023-01-23 05:01:52.436917: step: 2024/529, loss: 0.06895418465137482
2023-01-23 05:01:53.638904: step: 2028/529, loss: 1.8596649169921875e-05
2023-01-23 05:01:54.810714: step: 2032/529, loss: 0.05424537509679794
2023-01-23 05:01:55.970787: step: 2036/529, loss: 0.0005564690218307078
2023-01-23 05:01:57.156606: step: 2040/529, loss: 0.0004893303266726434
2023-01-23 05:01:58.342222: step: 2044/529, loss: 0.0006778478855267167
2023-01-23 05:01:59.558560: step: 2048/529, loss: 0.00010166168794967234
2023-01-23 05:02:00.753681: step: 2052/529, loss: 0.033219531178474426
2023-01-23 05:02:01.940322: step: 2056/529, loss: 0.0014505386352539062
2023-01-23 05:02:03.170058: step: 2060/529, loss: 3.871917579090223e-05
2023-01-23 05:02:04.395891: step: 2064/529, loss: 0.011248588562011719
2023-01-23 05:02:05.589189: step: 2068/529, loss: -1.411438006471144e-05
2023-01-23 05:02:06.749651: step: 2072/529, loss: 0.006740093231201172
2023-01-23 05:02:07.948237: step: 2076/529, loss: 6.198883056640625e-06
2023-01-23 05:02:09.146835: step: 2080/529, loss: 3.24249267578125e-05
2023-01-23 05:02:10.368278: step: 2084/529, loss: 0.17038460075855255
2023-01-23 05:02:11.577205: step: 2088/529, loss: 1.277923547604587e-05
2023-01-23 05:02:12.795604: step: 2092/529, loss: 0.006978320889174938
2023-01-23 05:02:13.978859: step: 2096/529, loss: 3.185272362316027e-05
2023-01-23 05:02:15.187307: step: 2100/529, loss: 0.0004268646298442036
2023-01-23 05:02:16.351539: step: 2104/529, loss: 0.03451395407319069
2023-01-23 05:02:17.569266: step: 2108/529, loss: 0.023598290979862213
2023-01-23 05:02:18.763772: step: 2112/529, loss: 0.443160742521286
2023-01-23 05:02:19.950394: step: 2116/529, loss: 0.0002507686731405556
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.5977710233029382, 'r': 0.7856191744340879, 'f1': 0.6789413118527042}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6216466234967623, 'r': 0.805272618334332, 'f1': 0.7016444792482381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5625, 'r': 0.8333333333333334, 'f1': 0.6716417910447761}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.49295774647887325, 'r': 0.5555555555555556, 'f1': 0.5223880597014925}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.40816326530612246, 'r': 0.5555555555555556, 'f1': 0.47058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6463560334528077, 'r': 0.7203728362183754, 'f1': 0.6813602015113349}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6293375394321766, 'r': 0.7171959257040144, 'f1': 0.6704004480537665}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7142857142857143, 'r': 0.8333333333333334, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5911764705882353, 'r': 0.8029294274300932, 'f1': 0.6809712027103332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6277407054337464, 'r': 0.7890952666267226, 'f1': 0.6992301566233077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6682464454976303, 'r': 0.7509986684420772, 'f1': 0.7072100313479625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Eng Test for Russian: {'event': {'p': 0.6650968079539508, 'r': 0.7615338526063511, 'f1': 0.7100558659217877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}