Command that produces this log: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> trigger_label_ffn.layers.0.weight: torch.Size([450, 1024])
>>> trigger_label_ffn.layers.0.bias: torch.Size([450])
>>> trigger_label_ffn.layers.1.weight: torch.Size([233, 450])
>>> trigger_label_ffn.layers.1.bias: torch.Size([233])
>>> trigger_crf.transition: torch.Size([235, 235])
n_trainable_params: 560511990, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:23:09.984881: step: 4/529, loss: 3.181039333343506
2023-01-22 23:23:11.110953: step: 8/529, loss: 4.148381233215332
2023-01-22 23:23:12.191070: step: 12/529, loss: 16.890193939208984
2023-01-22 23:23:13.309526: step: 16/529, loss: 14.784475326538086
2023-01-22 23:23:14.401487: step: 20/529, loss: 11.164883613586426
2023-01-22 23:23:15.534369: step: 24/529, loss: 5.907369613647461
2023-01-22 23:23:16.630214: step: 28/529, loss: 4.50492525100708
2023-01-22 23:23:17.739209: step: 32/529, loss: 11.313998222351074
2023-01-22 23:23:18.868430: step: 36/529, loss: 10.420550346374512
2023-01-22 23:23:19.985160: step: 40/529, loss: 3.6236844062805176
2023-01-22 23:23:21.099635: step: 44/529, loss: 3.544320821762085
2023-01-22 23:23:22.214990: step: 48/529, loss: 11.984138488769531
2023-01-22 23:23:23.349417: step: 52/529, loss: 8.288003921508789
2023-01-22 23:23:24.486582: step: 56/529, loss: 8.057869911193848
2023-01-22 23:23:25.567984: step: 60/529, loss: 21.183391571044922
2023-01-22 23:23:26.694081: step: 64/529, loss: 17.67329216003418
2023-01-22 23:23:27.787684: step: 68/529, loss: 4.543078899383545
2023-01-22 23:23:28.871687: step: 72/529, loss: 9.818075180053711
2023-01-22 23:23:29.951523: step: 76/529, loss: 3.9991519451141357
2023-01-22 23:23:31.043760: step: 80/529, loss: 6.863047122955322
2023-01-22 23:23:32.148343: step: 84/529, loss: 10.582906723022461
2023-01-22 23:23:33.236520: step: 88/529, loss: 3.1144561767578125
2023-01-22 23:23:34.351913: step: 92/529, loss: 4.24136209487915
2023-01-22 23:23:35.478520: step: 96/529, loss: 12.366209030151367
2023-01-22 23:23:36.582269: step: 100/529, loss: 24.492359161376953
2023-01-22 23:23:37.684045: step: 104/529, loss: 6.899333477020264
2023-01-22 23:23:38.831323: step: 108/529, loss: 5.953688621520996
2023-01-22 23:23:39.937764: step: 112/529, loss: 23.85785675048828
2023-01-22 23:23:41.037563: step: 116/529, loss: 2.31353497505188
2023-01-22 23:23:42.163347: step: 120/529, loss: 3.1844780445098877
2023-01-22 23:23:43.280953: step: 124/529, loss: 5.4410400390625
2023-01-22 23:23:44.391624: step: 128/529, loss: 3.788682699203491
2023-01-22 23:23:45.509877: step: 132/529, loss: 11.890104293823242
2023-01-22 23:23:46.652393: step: 136/529, loss: 27.87828826904297
2023-01-22 23:23:47.763806: step: 140/529, loss: 13.653682708740234
2023-01-22 23:23:48.879152: step: 144/529, loss: 4.0965728759765625
2023-01-22 23:23:50.042409: step: 148/529, loss: 3.878430128097534
2023-01-22 23:23:51.172940: step: 152/529, loss: 24.20764923095703
2023-01-22 23:23:52.267485: step: 156/529, loss: 3.142374038696289
2023-01-22 23:23:53.350611: step: 160/529, loss: 15.011707305908203
2023-01-22 23:23:54.470208: step: 164/529, loss: 13.921144485473633
2023-01-22 23:23:55.579755: step: 168/529, loss: 10.176070213317871
2023-01-22 23:23:56.681234: step: 172/529, loss: 3.584871530532837
2023-01-22 23:23:57.785011: step: 176/529, loss: 14.051507949829102
2023-01-22 23:23:58.886102: step: 180/529, loss: 3.3138160705566406
2023-01-22 23:23:59.997595: step: 184/529, loss: 16.57437515258789
2023-01-22 23:24:01.080676: step: 188/529, loss: 10.407448768615723
2023-01-22 23:24:02.186207: step: 192/529, loss: 3.171351432800293
2023-01-22 23:24:03.308156: step: 196/529, loss: 35.400482177734375
2023-01-22 23:24:04.455753: step: 200/529, loss: 2.9554643630981445
2023-01-22 23:24:05.579396: step: 204/529, loss: 7.949367523193359
2023-01-22 23:24:06.692660: step: 208/529, loss: 16.064252853393555
2023-01-22 23:24:07.804509: step: 212/529, loss: 20.374942779541016
2023-01-22 23:24:08.902317: step: 216/529, loss: 12.60849666595459
2023-01-22 23:24:10.014148: step: 220/529, loss: 9.891040802001953
2023-01-22 23:24:11.107389: step: 224/529, loss: 19.38750457763672
2023-01-22 23:24:12.240847: step: 228/529, loss: 11.243318557739258
2023-01-22 23:24:13.362277: step: 232/529, loss: 11.916040420532227
2023-01-22 23:24:14.507795: step: 236/529, loss: 4.941216468811035
2023-01-22 23:24:15.635816: step: 240/529, loss: 22.27077293395996
2023-01-22 23:24:16.739277: step: 244/529, loss: 8.686281204223633
2023-01-22 23:24:17.856425: step: 248/529, loss: 2.625258207321167
2023-01-22 23:24:18.986369: step: 252/529, loss: 5.587532997131348
2023-01-22 23:24:20.104458: step: 256/529, loss: 22.95246124267578
2023-01-22 23:24:21.224892: step: 260/529, loss: 3.4424848556518555
2023-01-22 23:24:22.308412: step: 264/529, loss: 23.686487197875977
2023-01-22 23:24:23.436978: step: 268/529, loss: 2.5376386642456055
2023-01-22 23:24:24.639541: step: 272/529, loss: 2.2287583351135254
2023-01-22 23:24:25.736493: step: 276/529, loss: 18.74136734008789
2023-01-22 23:24:26.846864: step: 280/529, loss: 2.306668996810913
2023-01-22 23:24:27.980079: step: 284/529, loss: 40.0789680480957
2023-01-22 23:24:29.102967: step: 288/529, loss: 16.543773651123047
2023-01-22 23:24:30.197477: step: 292/529, loss: 11.939416885375977
2023-01-22 23:24:31.302373: step: 296/529, loss: 3.78615140914917
2023-01-22 23:24:32.439877: step: 300/529, loss: 23.49304962158203
2023-01-22 23:24:33.572270: step: 304/529, loss: 18.0043888092041
2023-01-22 23:24:34.677907: step: 308/529, loss: 14.882118225097656
2023-01-22 23:24:35.849630: step: 312/529, loss: 3.264894485473633
2023-01-22 23:24:36.967947: step: 316/529, loss: 3.409369468688965
2023-01-22 23:24:38.084963: step: 320/529, loss: 6.533860206604004
2023-01-22 23:24:39.189260: step: 324/529, loss: 8.993955612182617
2023-01-22 23:24:40.305840: step: 328/529, loss: 2.536569595336914
2023-01-22 23:24:41.404988: step: 332/529, loss: 8.379501342773438
2023-01-22 23:24:42.529586: step: 336/529, loss: 9.593441009521484
2023-01-22 23:24:43.647846: step: 340/529, loss: 17.786354064941406
2023-01-22 23:24:44.767981: step: 344/529, loss: 3.9665145874023438
2023-01-22 23:24:45.876906: step: 348/529, loss: 3.009249687194824
2023-01-22 23:24:46.996801: step: 352/529, loss: 8.091318130493164
2023-01-22 23:24:48.117859: step: 356/529, loss: 15.7746000289917
2023-01-22 23:24:49.249020: step: 360/529, loss: 3.286609172821045
2023-01-22 23:24:50.347917: step: 364/529, loss: 1.8642345666885376
2023-01-22 23:24:51.469974: step: 368/529, loss: 3.2300446033477783
2023-01-22 23:24:52.596726: step: 372/529, loss: 3.2253260612487793
2023-01-22 23:24:53.713842: step: 376/529, loss: 3.3433282375335693
2023-01-22 23:24:54.838217: step: 380/529, loss: 19.346525192260742
2023-01-22 23:24:55.970668: step: 384/529, loss: 7.14265251159668
2023-01-22 23:24:57.080106: step: 388/529, loss: 3.98744797706604
2023-01-22 23:24:58.214985: step: 392/529, loss: 7.2256550788879395
2023-01-22 23:24:59.301762: step: 396/529, loss: 6.609988212585449
2023-01-22 23:25:00.436513: step: 400/529, loss: 4.187349319458008
2023-01-22 23:25:01.556766: step: 404/529, loss: 6.621717929840088
2023-01-22 23:25:02.726148: step: 408/529, loss: 4.242406368255615
2023-01-22 23:25:03.828075: step: 412/529, loss: 4.040754795074463
2023-01-22 23:25:04.943224: step: 416/529, loss: 10.107298851013184
2023-01-22 23:25:06.069320: step: 420/529, loss: 2.737809181213379
2023-01-22 23:25:07.201413: step: 424/529, loss: 21.25225067138672
2023-01-22 23:25:08.329616: step: 428/529, loss: 13.049256324768066
2023-01-22 23:25:09.423238: step: 432/529, loss: 16.234838485717773
2023-01-22 23:25:10.550843: step: 436/529, loss: 19.74777603149414
2023-01-22 23:25:11.657735: step: 440/529, loss: 3.085660934448242
2023-01-22 23:25:12.826539: step: 444/529, loss: 22.53052520751953
2023-01-22 23:25:13.930652: step: 448/529, loss: 2.378647565841675
2023-01-22 23:25:15.034029: step: 452/529, loss: 12.57361888885498
2023-01-22 23:25:16.148437: step: 456/529, loss: 16.89199447631836
2023-01-22 23:25:17.259209: step: 460/529, loss: 17.527381896972656
2023-01-22 23:25:18.360259: step: 464/529, loss: 3.964460611343384
2023-01-22 23:25:19.488036: step: 468/529, loss: 6.356296539306641
2023-01-22 23:25:20.612335: step: 472/529, loss: 5.459007263183594
2023-01-22 23:25:21.724831: step: 476/529, loss: 6.411293983459473
2023-01-22 23:25:22.831785: step: 480/529, loss: 1.7834112644195557
2023-01-22 23:25:23.940562: step: 484/529, loss: 2.5891640186309814
2023-01-22 23:25:25.035880: step: 488/529, loss: 2.1815664768218994
2023-01-22 23:25:26.132143: step: 492/529, loss: 1.5952057838439941
2023-01-22 23:25:27.252222: step: 496/529, loss: 6.655587196350098
2023-01-22 23:25:28.363705: step: 500/529, loss: 1.0166592597961426
2023-01-22 23:25:29.502353: step: 504/529, loss: 3.089906692504883
2023-01-22 23:25:30.642784: step: 508/529, loss: 5.251044750213623
2023-01-22 23:25:31.745330: step: 512/529, loss: 1.4529364109039307
2023-01-22 23:25:32.867509: step: 516/529, loss: 9.458945274353027
2023-01-22 23:25:33.991346: step: 520/529, loss: 1.1500593423843384
2023-01-22 23:25:35.122269: step: 524/529, loss: 3.7878050804138184
2023-01-22 23:25:36.207936: step: 528/529, loss: 5.998301029205322
2023-01-22 23:25:37.327861: step: 532/529, loss: 0.9841156005859375
2023-01-22 23:25:38.417262: step: 536/529, loss: 3.292997121810913
2023-01-22 23:25:39.547665: step: 540/529, loss: 2.9554991722106934
2023-01-22 23:25:40.667595: step: 544/529, loss: 3.5481033325195312
2023-01-22 23:25:41.802318: step: 548/529, loss: 4.928516864776611
2023-01-22 23:25:42.926702: step: 552/529, loss: 2.248809576034546
2023-01-22 23:25:44.035817: step: 556/529, loss: 0.8243222832679749
2023-01-22 23:25:45.124395: step: 560/529, loss: 0.8489829897880554
2023-01-22 23:25:46.207347: step: 564/529, loss: 0.9535242319107056
2023-01-22 23:25:47.319612: step: 568/529, loss: 0.9830405712127686
2023-01-22 23:25:48.443819: step: 572/529, loss: 1.7841838598251343
2023-01-22 23:25:49.547577: step: 576/529, loss: 0.6517889499664307
2023-01-22 23:25:50.651333: step: 580/529, loss: 0.5556949377059937
2023-01-22 23:25:51.771913: step: 584/529, loss: 4.726264476776123
2023-01-22 23:25:52.894998: step: 588/529, loss: 2.586247444152832
2023-01-22 23:25:54.004910: step: 592/529, loss: 2.321176528930664
2023-01-22 23:25:55.116835: step: 596/529, loss: 3.589031457901001
2023-01-22 23:25:56.225497: step: 600/529, loss: 3.104370355606079
2023-01-22 23:25:57.340164: step: 604/529, loss: 0.33468902111053467
2023-01-22 23:25:58.441272: step: 608/529, loss: 0.5355984568595886
2023-01-22 23:25:59.560546: step: 612/529, loss: 0.7732580900192261
2023-01-22 23:26:00.644373: step: 616/529, loss: 0.4325505197048187
2023-01-22 23:26:01.754720: step: 620/529, loss: 1.6645264625549316
2023-01-22 23:26:02.878343: step: 624/529, loss: 0.6770639419555664
2023-01-22 23:26:03.979448: step: 628/529, loss: 3.181455135345459
2023-01-22 23:26:05.093287: step: 632/529, loss: 2.588618516921997
2023-01-22 23:26:06.212440: step: 636/529, loss: 2.1700592041015625
2023-01-22 23:26:07.321547: step: 640/529, loss: 5.2609734535217285
2023-01-22 23:26:08.442884: step: 644/529, loss: 0.5777246356010437
2023-01-22 23:26:09.555238: step: 648/529, loss: 0.8448666334152222
2023-01-22 23:26:10.656907: step: 652/529, loss: 4.5122222900390625
2023-01-22 23:26:11.782179: step: 656/529, loss: 0.8130577206611633
2023-01-22 23:26:12.867200: step: 660/529, loss: 2.5856754779815674
2023-01-22 23:26:13.964118: step: 664/529, loss: 1.1001721620559692
2023-01-22 23:26:15.070735: step: 668/529, loss: 2.394239902496338
2023-01-22 23:26:16.157026: step: 672/529, loss: 7.212648391723633
2023-01-22 23:26:17.259921: step: 676/529, loss: 0.9773256778717041
2023-01-22 23:26:18.374930: step: 680/529, loss: 2.4082207679748535
2023-01-22 23:26:19.479125: step: 684/529, loss: 0.5685349702835083
2023-01-22 23:26:20.592673: step: 688/529, loss: 0.5630002021789551
2023-01-22 23:26:21.696372: step: 692/529, loss: 1.9442408084869385
2023-01-22 23:26:22.780107: step: 696/529, loss: 1.033196210861206
2023-01-22 23:26:23.889330: step: 700/529, loss: 0.6768302321434021
2023-01-22 23:26:24.986712: step: 704/529, loss: 0.6083481907844543
2023-01-22 23:26:26.133866: step: 708/529, loss: 2.609952211380005
2023-01-22 23:26:27.232891: step: 712/529, loss: 1.4654203653335571
2023-01-22 23:26:28.321212: step: 716/529, loss: 0.6262234449386597
2023-01-22 23:26:29.439064: step: 720/529, loss: 0.6272705793380737
2023-01-22 23:26:30.558479: step: 724/529, loss: 2.0398786067962646
2023-01-22 23:26:31.675202: step: 728/529, loss: 2.28105092048645
2023-01-22 23:26:32.778771: step: 732/529, loss: 1.607466697692871
2023-01-22 23:26:33.871867: step: 736/529, loss: 0.6245580911636353
2023-01-22 23:26:34.982653: step: 740/529, loss: 3.9305334091186523
2023-01-22 23:26:36.074931: step: 744/529, loss: 3.0112438201904297
2023-01-22 23:26:37.167137: step: 748/529, loss: 0.27578938007354736
2023-01-22 23:26:38.295727: step: 752/529, loss: 1.5843188762664795
2023-01-22 23:26:39.449814: step: 756/529, loss: 1.4928663969039917
2023-01-22 23:26:40.567393: step: 760/529, loss: 0.6400212049484253
2023-01-22 23:26:41.714193: step: 764/529, loss: 1.4070143699645996
2023-01-22 23:26:42.862184: step: 768/529, loss: 1.2450342178344727
2023-01-22 23:26:43.972660: step: 772/529, loss: 1.6456449031829834
2023-01-22 23:26:45.073338: step: 776/529, loss: 0.6609829664230347
2023-01-22 23:26:46.195779: step: 780/529, loss: 4.106722354888916
2023-01-22 23:26:47.300292: step: 784/529, loss: 6.329195022583008
2023-01-22 23:26:48.417276: step: 788/529, loss: 5.429108619689941
2023-01-22 23:26:49.550061: step: 792/529, loss: 0.5938752889633179
2023-01-22 23:26:50.685663: step: 796/529, loss: 0.5918770432472229
2023-01-22 23:26:51.822252: step: 800/529, loss: 0.5234934091567993
2023-01-22 23:26:52.937865: step: 804/529, loss: 2.6645586490631104
2023-01-22 23:26:54.027236: step: 808/529, loss: 0.789321780204773
2023-01-22 23:26:55.151569: step: 812/529, loss: 3.8546249866485596
2023-01-22 23:26:56.264794: step: 816/529, loss: 1.5031120777130127
2023-01-22 23:26:57.347892: step: 820/529, loss: 2.1692745685577393
2023-01-22 23:26:58.453739: step: 824/529, loss: 0.46271783113479614
2023-01-22 23:26:59.571115: step: 828/529, loss: 1.9248688220977783
2023-01-22 23:27:00.703347: step: 832/529, loss: 0.9935060739517212
2023-01-22 23:27:01.803066: step: 836/529, loss: 0.5535085201263428
2023-01-22 23:27:02.903876: step: 840/529, loss: 4.084255695343018
2023-01-22 23:27:04.031467: step: 844/529, loss: 1.3110045194625854
2023-01-22 23:27:05.125888: step: 848/529, loss: 0.6956640481948853
2023-01-22 23:27:06.228256: step: 852/529, loss: 1.6176519393920898
2023-01-22 23:27:07.347798: step: 856/529, loss: 2.4390833377838135
2023-01-22 23:27:08.447387: step: 860/529, loss: 2.0054521560668945
2023-01-22 23:27:09.536383: step: 864/529, loss: 0.6310192942619324
2023-01-22 23:27:10.641865: step: 868/529, loss: 2.099611759185791
2023-01-22 23:27:11.737784: step: 872/529, loss: 0.6212886571884155
2023-01-22 23:27:12.846079: step: 876/529, loss: 2.1017985343933105
2023-01-22 23:27:13.937532: step: 880/529, loss: 0.3207300305366516
2023-01-22 23:27:15.040951: step: 884/529, loss: 1.1053235530853271
2023-01-22 23:27:16.123957: step: 888/529, loss: 3.5223312377929688
2023-01-22 23:27:17.233196: step: 892/529, loss: 1.734467625617981
2023-01-22 23:27:18.337863: step: 896/529, loss: 1.2115098237991333
2023-01-22 23:27:19.466802: step: 900/529, loss: 2.927518367767334
2023-01-22 23:27:20.562633: step: 904/529, loss: 0.40983572602272034
2023-01-22 23:27:21.702904: step: 908/529, loss: 0.6246107816696167
2023-01-22 23:27:22.836440: step: 912/529, loss: 0.25027745962142944
2023-01-22 23:27:23.930505: step: 916/529, loss: 0.7158151865005493
2023-01-22 23:27:25.017571: step: 920/529, loss: 0.37871497869491577
2023-01-22 23:27:26.121281: step: 924/529, loss: 2.64094877243042
2023-01-22 23:27:27.218609: step: 928/529, loss: 1.651828646659851
2023-01-22 23:27:28.316428: step: 932/529, loss: 0.42743366956710815
2023-01-22 23:27:29.407902: step: 936/529, loss: 0.5861097574234009
2023-01-22 23:27:30.495762: step: 940/529, loss: 0.5607304573059082
2023-01-22 23:27:31.585881: step: 944/529, loss: 0.8535863757133484
2023-01-22 23:27:32.688256: step: 948/529, loss: 1.1883795261383057
2023-01-22 23:27:33.790206: step: 952/529, loss: 0.43676966428756714
2023-01-22 23:27:34.898765: step: 956/529, loss: 0.616195023059845
2023-01-22 23:27:36.026079: step: 960/529, loss: 2.350834846496582
2023-01-22 23:27:37.143254: step: 964/529, loss: 1.7469561100006104
2023-01-22 23:27:38.235175: step: 968/529, loss: 1.112709879875183
2023-01-22 23:27:39.348480: step: 972/529, loss: 1.9984407424926758
2023-01-22 23:27:40.452753: step: 976/529, loss: 2.033287525177002
2023-01-22 23:27:41.611210: step: 980/529, loss: 7.328566551208496
2023-01-22 23:27:42.761560: step: 984/529, loss: 0.5868288278579712
2023-01-22 23:27:43.864135: step: 988/529, loss: 1.683711051940918
2023-01-22 23:27:44.958582: step: 992/529, loss: 0.4353392720222473
2023-01-22 23:27:46.057916: step: 996/529, loss: 0.43061304092407227
2023-01-22 23:27:47.162413: step: 1000/529, loss: 0.4987958073616028
2023-01-22 23:27:48.270029: step: 1004/529, loss: 2.024533271789551
2023-01-22 23:27:49.441221: step: 1008/529, loss: 1.1182819604873657
2023-01-22 23:27:50.604570: step: 1012/529, loss: 2.887819528579712
2023-01-22 23:27:51.705495: step: 1016/529, loss: 1.126031756401062
2023-01-22 23:27:52.807120: step: 1020/529, loss: 0.7851737141609192
2023-01-22 23:27:53.910022: step: 1024/529, loss: 1.4584814310073853
2023-01-22 23:27:55.037035: step: 1028/529, loss: 0.9805344343185425
2023-01-22 23:27:56.131910: step: 1032/529, loss: 0.5942932367324829
2023-01-22 23:27:57.251430: step: 1036/529, loss: 3.926556348800659
2023-01-22 23:27:58.385156: step: 1040/529, loss: 1.3170838356018066
2023-01-22 23:27:59.472059: step: 1044/529, loss: 1.9300658702850342
2023-01-22 23:28:00.606066: step: 1048/529, loss: 0.864709734916687
2023-01-22 23:28:01.721050: step: 1052/529, loss: 6.743732929229736
2023-01-22 23:28:02.828620: step: 1056/529, loss: 0.4914347529411316
2023-01-22 23:28:03.937512: step: 1060/529, loss: 0.24263663589954376
2023-01-22 23:28:05.050731: step: 1064/529, loss: 0.2656261920928955
2023-01-22 23:28:06.124993: step: 1068/529, loss: 0.5748631954193115
2023-01-22 23:28:07.208452: step: 1072/529, loss: 0.4373299479484558
2023-01-22 23:28:08.313952: step: 1076/529, loss: 1.7935054302215576
2023-01-22 23:28:09.453667: step: 1080/529, loss: 5.035520553588867
2023-01-22 23:28:10.551694: step: 1084/529, loss: 0.4074358344078064
2023-01-22 23:28:11.674518: step: 1088/529, loss: 0.6925681233406067
2023-01-22 23:28:12.773933: step: 1092/529, loss: 1.405806541442871
2023-01-22 23:28:13.888567: step: 1096/529, loss: 1.9536575078964233
2023-01-22 23:28:14.982415: step: 1100/529, loss: 0.8262926936149597
2023-01-22 23:28:16.057498: step: 1104/529, loss: 0.6741202473640442
2023-01-22 23:28:17.193718: step: 1108/529, loss: 0.6606097221374512
2023-01-22 23:28:18.281922: step: 1112/529, loss: 0.7221142649650574
2023-01-22 23:28:19.376792: step: 1116/529, loss: 0.3612290024757385
2023-01-22 23:28:20.471002: step: 1120/529, loss: 0.8333176970481873
2023-01-22 23:28:21.574481: step: 1124/529, loss: 2.135603666305542
2023-01-22 23:28:22.653010: step: 1128/529, loss: 0.4876803457736969
2023-01-22 23:28:23.740490: step: 1132/529, loss: 0.4415576159954071
2023-01-22 23:28:24.850923: step: 1136/529, loss: 0.35199204087257385
2023-01-22 23:28:25.942093: step: 1140/529, loss: 0.773186981678009
2023-01-22 23:28:27.038160: step: 1144/529, loss: 0.3825199007987976
2023-01-22 23:28:28.154214: step: 1148/529, loss: 4.911041736602783
2023-01-22 23:28:29.272871: step: 1152/529, loss: 0.28321534395217896
2023-01-22 23:28:30.360885: step: 1156/529, loss: 1.4916503429412842
2023-01-22 23:28:31.463125: step: 1160/529, loss: 0.3870924711227417
2023-01-22 23:28:32.610787: step: 1164/529, loss: 0.5239297747612
2023-01-22 23:28:33.715138: step: 1168/529, loss: 0.601505696773529
2023-01-22 23:28:34.825168: step: 1172/529, loss: 2.5727901458740234
2023-01-22 23:28:35.903453: step: 1176/529, loss: 0.18190708756446838
2023-01-22 23:28:37.022122: step: 1180/529, loss: 0.9664733409881592
2023-01-22 23:28:38.137176: step: 1184/529, loss: 2.6611785888671875
2023-01-22 23:28:39.241701: step: 1188/529, loss: 0.5117823481559753
2023-01-22 23:28:40.355445: step: 1192/529, loss: 0.6579575538635254
2023-01-22 23:28:41.479946: step: 1196/529, loss: 0.19508495926856995
2023-01-22 23:28:42.611164: step: 1200/529, loss: 1.1678178310394287
2023-01-22 23:28:43.738965: step: 1204/529, loss: 1.455307960510254
2023-01-22 23:28:44.846170: step: 1208/529, loss: 2.3669700622558594
2023-01-22 23:28:45.992810: step: 1212/529, loss: 1.2312983274459839
2023-01-22 23:28:47.089971: step: 1216/529, loss: 1.9613423347473145
2023-01-22 23:28:48.198557: step: 1220/529, loss: 0.9335511922836304
2023-01-22 23:28:49.300769: step: 1224/529, loss: 0.9120486378669739
2023-01-22 23:28:50.385212: step: 1228/529, loss: 4.602816581726074
2023-01-22 23:28:51.516999: step: 1232/529, loss: 1.3636798858642578
2023-01-22 23:28:52.612035: step: 1236/529, loss: 2.050300359725952
2023-01-22 23:28:53.734648: step: 1240/529, loss: 1.53571355342865
2023-01-22 23:28:54.850043: step: 1244/529, loss: 1.6129343509674072
2023-01-22 23:28:55.974164: step: 1248/529, loss: 0.9573297500610352
2023-01-22 23:28:57.052862: step: 1252/529, loss: 1.0015984773635864
2023-01-22 23:28:58.161243: step: 1256/529, loss: 1.0051642656326294
2023-01-22 23:28:59.261207: step: 1260/529, loss: 1.1919217109680176
2023-01-22 23:29:00.353289: step: 1264/529, loss: 1.0392515659332275
2023-01-22 23:29:01.444261: step: 1268/529, loss: 0.1835152804851532
2023-01-22 23:29:02.533677: step: 1272/529, loss: 1.2002732753753662
2023-01-22 23:29:03.662910: step: 1276/529, loss: 1.7138750553131104
2023-01-22 23:29:04.758249: step: 1280/529, loss: 0.7357588410377502
2023-01-22 23:29:05.848777: step: 1284/529, loss: 1.2817983627319336
2023-01-22 23:29:06.927709: step: 1288/529, loss: 8.869969367980957
2023-01-22 23:29:08.041507: step: 1292/529, loss: 0.7919747829437256
2023-01-22 23:29:09.136139: step: 1296/529, loss: 0.2611018121242523
2023-01-22 23:29:10.244415: step: 1300/529, loss: 0.5784379243850708
2023-01-22 23:29:11.372909: step: 1304/529, loss: 3.6391208171844482
2023-01-22 23:29:12.496193: step: 1308/529, loss: 0.409001886844635
2023-01-22 23:29:13.619336: step: 1312/529, loss: 0.5249953269958496
2023-01-22 23:29:14.705860: step: 1316/529, loss: 0.35564833879470825
2023-01-22 23:29:15.849387: step: 1320/529, loss: 0.5548809170722961
2023-01-22 23:29:16.958263: step: 1324/529, loss: 0.7999005913734436
2023-01-22 23:29:18.077740: step: 1328/529, loss: 1.296330213546753
2023-01-22 23:29:19.191956: step: 1332/529, loss: 0.31105977296829224
2023-01-22 23:29:20.320409: step: 1336/529, loss: 1.0918596982955933
2023-01-22 23:29:21.427291: step: 1340/529, loss: 0.5353461503982544
2023-01-22 23:29:22.536818: step: 1344/529, loss: 1.0331121683120728
2023-01-22 23:29:23.674447: step: 1348/529, loss: 0.296822726726532
2023-01-22 23:29:24.785695: step: 1352/529, loss: 2.8359856605529785
2023-01-22 23:29:25.906930: step: 1356/529, loss: 0.17553797364234924
2023-01-22 23:29:26.984849: step: 1360/529, loss: 0.9902456402778625
2023-01-22 23:29:28.104929: step: 1364/529, loss: 0.969699501991272
2023-01-22 23:29:29.219252: step: 1368/529, loss: 1.8549939393997192
2023-01-22 23:29:30.317047: step: 1372/529, loss: 0.30430424213409424
2023-01-22 23:29:31.407038: step: 1376/529, loss: 1.735209345817566
2023-01-22 23:29:32.511463: step: 1380/529, loss: 0.3211958110332489
2023-01-22 23:29:33.615613: step: 1384/529, loss: 0.3108389973640442
2023-01-22 23:29:34.726941: step: 1388/529, loss: 0.7214325070381165
2023-01-22 23:29:35.813057: step: 1392/529, loss: 0.39114007353782654
2023-01-22 23:29:36.932998: step: 1396/529, loss: 0.4138685166835785
2023-01-22 23:29:38.055539: step: 1400/529, loss: 0.2378009408712387
2023-01-22 23:29:39.183596: step: 1404/529, loss: 0.1629185676574707
2023-01-22 23:29:40.302559: step: 1408/529, loss: 0.6681604385375977
2023-01-22 23:29:41.416359: step: 1412/529, loss: 1.066933274269104
2023-01-22 23:29:42.502546: step: 1416/529, loss: 0.5689336657524109
2023-01-22 23:29:43.609885: step: 1420/529, loss: 1.0357985496520996
2023-01-22 23:29:44.744734: step: 1424/529, loss: 9.961202621459961
2023-01-22 23:29:45.851910: step: 1428/529, loss: 1.0123765468597412
2023-01-22 23:29:46.943583: step: 1432/529, loss: 0.2440262883901596
2023-01-22 23:29:48.075904: step: 1436/529, loss: 1.2150473594665527
2023-01-22 23:29:49.192083: step: 1440/529, loss: 0.529533326625824
2023-01-22 23:29:50.327698: step: 1444/529, loss: 0.575178861618042
2023-01-22 23:29:51.422457: step: 1448/529, loss: 0.3072776794433594
2023-01-22 23:29:52.515789: step: 1452/529, loss: 0.33888113498687744
2023-01-22 23:29:53.605892: step: 1456/529, loss: 1.2264699935913086
2023-01-22 23:29:54.729594: step: 1460/529, loss: 1.055977463722229
2023-01-22 23:29:55.886918: step: 1464/529, loss: 0.43419021368026733
2023-01-22 23:29:56.977869: step: 1468/529, loss: 1.4148719310760498
2023-01-22 23:29:58.112473: step: 1472/529, loss: 0.9533913135528564
2023-01-22 23:29:59.217680: step: 1476/529, loss: 0.4055001735687256
2023-01-22 23:30:00.340729: step: 1480/529, loss: 3.253361225128174
2023-01-22 23:30:01.488839: step: 1484/529, loss: 0.47833073139190674
2023-01-22 23:30:02.622608: step: 1488/529, loss: 2.780667781829834
2023-01-22 23:30:03.739650: step: 1492/529, loss: 0.5709744691848755
2023-01-22 23:30:04.836429: step: 1496/529, loss: 0.3533855676651001
2023-01-22 23:30:05.966497: step: 1500/529, loss: 0.5642304420471191
2023-01-22 23:30:07.078478: step: 1504/529, loss: 2.8406996726989746
2023-01-22 23:30:08.192800: step: 1508/529, loss: 2.093322277069092
2023-01-22 23:30:09.297134: step: 1512/529, loss: 1.0322731733322144
2023-01-22 23:30:10.383323: step: 1516/529, loss: 1.583207130432129
2023-01-22 23:30:11.503256: step: 1520/529, loss: 0.9847851991653442
2023-01-22 23:30:12.638966: step: 1524/529, loss: 0.9704713821411133
2023-01-22 23:30:13.749972: step: 1528/529, loss: 0.7138993740081787
2023-01-22 23:30:14.856345: step: 1532/529, loss: 0.4014458656311035
2023-01-22 23:30:15.956073: step: 1536/529, loss: 0.2671958804130554
2023-01-22 23:30:17.055146: step: 1540/529, loss: 0.3832261860370636
2023-01-22 23:30:18.179351: step: 1544/529, loss: 2.7566158771514893
2023-01-22 23:30:19.287182: step: 1548/529, loss: 8.708740234375
2023-01-22 23:30:20.396372: step: 1552/529, loss: 0.5072838068008423
2023-01-22 23:30:21.504457: step: 1556/529, loss: 0.7055354118347168
2023-01-22 23:30:22.627234: step: 1560/529, loss: 1.6156117916107178
2023-01-22 23:30:23.725792: step: 1564/529, loss: 0.3917275369167328
2023-01-22 23:30:24.812297: step: 1568/529, loss: 1.8289592266082764
2023-01-22 23:30:25.923871: step: 1572/529, loss: 0.966462254524231
2023-01-22 23:30:27.014702: step: 1576/529, loss: 1.2601213455200195
2023-01-22 23:30:28.090694: step: 1580/529, loss: 1.5898438692092896
2023-01-22 23:30:29.207138: step: 1584/529, loss: 1.1666059494018555
2023-01-22 23:30:30.312349: step: 1588/529, loss: 1.4859836101531982
2023-01-22 23:30:31.406311: step: 1592/529, loss: 1.085548996925354
2023-01-22 23:30:32.493334: step: 1596/529, loss: 0.14204354584217072
2023-01-22 23:30:33.603959: step: 1600/529, loss: 0.7242662906646729
2023-01-22 23:30:34.712145: step: 1604/529, loss: 2.4299025535583496
2023-01-22 23:30:35.817100: step: 1608/529, loss: 3.8800811767578125
2023-01-22 23:30:36.930935: step: 1612/529, loss: 1.9202399253845215
2023-01-22 23:30:38.051140: step: 1616/529, loss: 1.2000303268432617
2023-01-22 23:30:39.146665: step: 1620/529, loss: 1.6702711582183838
2023-01-22 23:30:40.294039: step: 1624/529, loss: 2.940463066101074
2023-01-22 23:30:41.399793: step: 1628/529, loss: 1.8647282123565674
2023-01-22 23:30:42.522853: step: 1632/529, loss: 1.2855159044265747
2023-01-22 23:30:43.611068: step: 1636/529, loss: 0.27251410484313965
2023-01-22 23:30:44.707359: step: 1640/529, loss: 0.6215863823890686
2023-01-22 23:30:45.820357: step: 1644/529, loss: 0.7701816558837891
2023-01-22 23:30:46.918452: step: 1648/529, loss: 0.5594610571861267
2023-01-22 23:30:48.021145: step: 1652/529, loss: 1.321620225906372
2023-01-22 23:30:49.151412: step: 1656/529, loss: 0.7079131603240967
2023-01-22 23:30:50.261554: step: 1660/529, loss: 0.294409841299057
2023-01-22 23:30:51.358154: step: 1664/529, loss: 0.601701021194458
2023-01-22 23:30:52.455727: step: 1668/529, loss: 0.24158337712287903
2023-01-22 23:30:53.557922: step: 1672/529, loss: 0.8594356179237366
2023-01-22 23:30:54.659685: step: 1676/529, loss: 0.16382399201393127
2023-01-22 23:30:55.789371: step: 1680/529, loss: 0.4015040397644043
2023-01-22 23:30:56.881841: step: 1684/529, loss: 0.24749022722244263
2023-01-22 23:30:58.005178: step: 1688/529, loss: 1.1471235752105713
2023-01-22 23:30:59.094725: step: 1692/529, loss: 0.17843137681484222
2023-01-22 23:31:00.225599: step: 1696/529, loss: 1.7409522533416748
2023-01-22 23:31:01.331219: step: 1700/529, loss: 0.35028308629989624
2023-01-22 23:31:02.434888: step: 1704/529, loss: 5.486498832702637
2023-01-22 23:31:03.570070: step: 1708/529, loss: 3.1866891384124756
2023-01-22 23:31:04.693063: step: 1712/529, loss: 3.423689126968384
2023-01-22 23:31:05.806833: step: 1716/529, loss: 2.252361297607422
2023-01-22 23:31:06.915491: step: 1720/529, loss: 0.9043692350387573
2023-01-22 23:31:07.998485: step: 1724/529, loss: 0.31061768531799316
2023-01-22 23:31:09.112596: step: 1728/529, loss: 0.7108418941497803
2023-01-22 23:31:10.232585: step: 1732/529, loss: 0.41635262966156006
2023-01-22 23:31:11.348875: step: 1736/529, loss: 0.9218595623970032
2023-01-22 23:31:12.452537: step: 1740/529, loss: 0.2296573668718338
2023-01-22 23:31:13.575006: step: 1744/529, loss: 1.355069875717163
2023-01-22 23:31:14.683397: step: 1748/529, loss: 0.502210259437561
2023-01-22 23:31:15.779983: step: 1752/529, loss: 1.055375576019287
2023-01-22 23:31:16.885600: step: 1756/529, loss: 0.25308629870414734
2023-01-22 23:31:18.021630: step: 1760/529, loss: 1.177011489868164
2023-01-22 23:31:19.142392: step: 1764/529, loss: 1.0240637063980103
2023-01-22 23:31:20.294508: step: 1768/529, loss: 3.3754591941833496
2023-01-22 23:31:21.385100: step: 1772/529, loss: 0.40824973583221436
2023-01-22 23:31:22.503015: step: 1776/529, loss: 1.3220211267471313
2023-01-22 23:31:23.612249: step: 1780/529, loss: 0.5259435772895813
2023-01-22 23:31:24.721116: step: 1784/529, loss: 0.2256631851196289
2023-01-22 23:31:25.821580: step: 1788/529, loss: 1.046749234199524
2023-01-22 23:31:26.952467: step: 1792/529, loss: 1.698093056678772
2023-01-22 23:31:28.063120: step: 1796/529, loss: 3.0170767307281494
2023-01-22 23:31:29.186575: step: 1800/529, loss: 2.597223997116089
2023-01-22 23:31:30.289500: step: 1804/529, loss: 2.6770811080932617
2023-01-22 23:31:31.399379: step: 1808/529, loss: 1.8501085042953491
2023-01-22 23:31:32.517700: step: 1812/529, loss: 2.499187469482422
2023-01-22 23:31:33.593456: step: 1816/529, loss: 1.0655276775360107
2023-01-22 23:31:34.730818: step: 1820/529, loss: 1.0780234336853027
2023-01-22 23:31:35.822047: step: 1824/529, loss: 1.364769458770752
2023-01-22 23:31:36.911697: step: 1828/529, loss: 1.3978493213653564
2023-01-22 23:31:38.020812: step: 1832/529, loss: 1.6892147064208984
2023-01-22 23:31:39.097620: step: 1836/529, loss: 0.48332297801971436
2023-01-22 23:31:40.168897: step: 1840/529, loss: 0.4020690321922302
2023-01-22 23:31:41.263563: step: 1844/529, loss: 0.3157860040664673
2023-01-22 23:31:42.409888: step: 1848/529, loss: 3.5969014167785645
2023-01-22 23:31:43.538049: step: 1852/529, loss: 0.256857305765152
2023-01-22 23:31:44.648416: step: 1856/529, loss: 0.2124207466840744
2023-01-22 23:31:45.763016: step: 1860/529, loss: 0.5977795720100403
2023-01-22 23:31:46.866363: step: 1864/529, loss: 1.1359336376190186
2023-01-22 23:31:47.978598: step: 1868/529, loss: 0.8792713284492493
2023-01-22 23:31:49.125195: step: 1872/529, loss: 4.399348735809326
2023-01-22 23:31:50.232756: step: 1876/529, loss: 3.5783493518829346
2023-01-22 23:31:51.338893: step: 1880/529, loss: 0.8334358334541321
2023-01-22 23:31:52.478723: step: 1884/529, loss: 2.101957082748413
2023-01-22 23:31:53.578725: step: 1888/529, loss: 0.38834822177886963
2023-01-22 23:31:54.662671: step: 1892/529, loss: 0.7221038937568665
2023-01-22 23:31:55.788914: step: 1896/529, loss: 1.9736963510513306
2023-01-22 23:31:56.874130: step: 1900/529, loss: 0.29701775312423706
2023-01-22 23:31:57.955305: step: 1904/529, loss: 0.307219535112381
2023-01-22 23:31:59.058088: step: 1908/529, loss: 0.48136910796165466
2023-01-22 23:32:00.196982: step: 1912/529, loss: 2.253765821456909
2023-01-22 23:32:01.334350: step: 1916/529, loss: 2.1686315536499023
2023-01-22 23:32:02.440229: step: 1920/529, loss: 2.344276189804077
2023-01-22 23:32:03.546617: step: 1924/529, loss: 0.6985849142074585
2023-01-22 23:32:04.666641: step: 1928/529, loss: 1.2473480701446533
2023-01-22 23:32:05.760680: step: 1932/529, loss: 1.4237642288208008
2023-01-22 23:32:06.876469: step: 1936/529, loss: 1.9876503944396973
2023-01-22 23:32:07.975360: step: 1940/529, loss: 1.2747325897216797
2023-01-22 23:32:09.081970: step: 1944/529, loss: 0.4919694662094116
2023-01-22 23:32:10.208665: step: 1948/529, loss: 0.2038504183292389
2023-01-22 23:32:11.341515: step: 1952/529, loss: 0.7296062707901001
2023-01-22 23:32:12.428410: step: 1956/529, loss: 1.0391838550567627
2023-01-22 23:32:13.548567: step: 1960/529, loss: 1.391580581665039
2023-01-22 23:32:14.639042: step: 1964/529, loss: 1.7046737670898438
2023-01-22 23:32:15.730626: step: 1968/529, loss: 2.649137020111084
2023-01-22 23:32:16.853379: step: 1972/529, loss: 0.374473512172699
2023-01-22 23:32:18.002389: step: 1976/529, loss: 0.9903206825256348
2023-01-22 23:32:19.117688: step: 1980/529, loss: 0.4089466333389282
2023-01-22 23:32:20.251274: step: 1984/529, loss: 0.5839372873306274
2023-01-22 23:32:21.369000: step: 1988/529, loss: 0.6511991620063782
2023-01-22 23:32:22.484875: step: 1992/529, loss: 7.43670129776001
2023-01-22 23:32:23.599927: step: 1996/529, loss: 2.7200427055358887
2023-01-22 23:32:24.695976: step: 2000/529, loss: 1.0286198854446411
2023-01-22 23:32:25.825877: step: 2004/529, loss: 0.8617674112319946
2023-01-22 23:32:26.941644: step: 2008/529, loss: 1.0878889560699463
2023-01-22 23:32:28.054276: step: 2012/529, loss: 0.11046610027551651
2023-01-22 23:32:29.164755: step: 2016/529, loss: 1.6425484418869019
2023-01-22 23:32:30.275694: step: 2020/529, loss: 0.32265591621398926
2023-01-22 23:32:31.390652: step: 2024/529, loss: 1.2610677480697632
2023-01-22 23:32:32.508229: step: 2028/529, loss: 0.9181358218193054
2023-01-22 23:32:33.612793: step: 2032/529, loss: 1.7233859300613403
2023-01-22 23:32:34.717271: step: 2036/529, loss: 1.2776845693588257
2023-01-22 23:32:35.806786: step: 2040/529, loss: 1.0303120613098145
2023-01-22 23:32:36.907005: step: 2044/529, loss: 1.9361991882324219
2023-01-22 23:32:38.017274: step: 2048/529, loss: 1.1504749059677124
2023-01-22 23:32:39.122074: step: 2052/529, loss: 0.4072703421115875
2023-01-22 23:32:40.237330: step: 2056/529, loss: 0.865858256816864
2023-01-22 23:32:41.390350: step: 2060/529, loss: 0.8232263326644897
2023-01-22 23:32:42.503492: step: 2064/529, loss: 0.28695160150527954
2023-01-22 23:32:43.626913: step: 2068/529, loss: 0.3389263153076172
2023-01-22 23:32:44.725701: step: 2072/529, loss: 1.2257319688796997
2023-01-22 23:32:45.812306: step: 2076/529, loss: 0.27962803840637207
2023-01-22 23:32:46.914809: step: 2080/529, loss: 0.3544461131095886
2023-01-22 23:32:47.996150: step: 2084/529, loss: 1.265763521194458
2023-01-22 23:32:49.097695: step: 2088/529, loss: 0.5422605872154236
2023-01-22 23:32:50.266923: step: 2092/529, loss: 0.6045862436294556
2023-01-22 23:32:51.366810: step: 2096/529, loss: 0.2181510478258133
2023-01-22 23:32:52.469795: step: 2100/529, loss: 1.9928064346313477
2023-01-22 23:32:53.621031: step: 2104/529, loss: 0.5899723768234253
2023-01-22 23:32:54.712683: step: 2108/529, loss: 0.6856964230537415
2023-01-22 23:32:55.819496: step: 2112/529, loss: 0.21868202090263367
2023-01-22 23:32:56.922658: step: 2116/529, loss: 0.9663521647453308
==================================================
Loss: 3.450
--------------------
Dev: {'event': {'p': 0.5475578406169666, 'r': 0.5672436750998668, 'f1': 0.5572269457161544}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.43515470704410797, 'r': 0.37302483069977427, 'f1': 0.4017016104527499}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5, 'r': 0.42592592592592593, 'f1': 0.46}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.8095238095238095, 'r': 0.2698412698412698, 'f1': 0.40476190476190477}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.5, 'r': 0.19444444444444445, 'f1': 0.28}, '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': 0.5475578406169666, 'r': 0.5672436750998668, 'f1': 0.5572269457161544}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.43515470704410797, 'r': 0.37302483069977427, 'f1': 0.4017016104527499}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5, 'r': 0.42592592592592593, 'f1': 0.46}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5475578406169666, 'r': 0.5672436750998668, 'f1': 0.5572269457161544}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.43515470704410797, 'r': 0.37302483069977427, 'f1': 0.4017016104527499}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.8095238095238095, 'r': 0.2698412698412698, 'f1': 0.40476190476190477}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5475578406169666, 'r': 0.5672436750998668, 'f1': 0.5572269457161544}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.43515470704410797, 'r': 0.37302483069977427, 'f1': 0.4017016104527499}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.5, 'r': 0.19444444444444445, 'f1': 0.28}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:33:58.087939: step: 4/529, loss: 0.7036115527153015
2023-01-22 23:33:59.224139: step: 8/529, loss: 0.5496631264686584
2023-01-22 23:34:00.345352: step: 12/529, loss: 0.4532729983329773
2023-01-22 23:34:01.455192: step: 16/529, loss: 0.9465816020965576
2023-01-22 23:34:02.584514: step: 20/529, loss: 0.7065269947052002
2023-01-22 23:34:03.689210: step: 24/529, loss: 0.21801280975341797
2023-01-22 23:34:04.792400: step: 28/529, loss: 2.4378793239593506
2023-01-22 23:34:05.899181: step: 32/529, loss: 0.3654881715774536
2023-01-22 23:34:07.000767: step: 36/529, loss: 7.119620323181152
2023-01-22 23:34:08.133993: step: 40/529, loss: 0.2349395900964737
2023-01-22 23:34:09.239323: step: 44/529, loss: 0.13511833548545837
2023-01-22 23:34:10.362802: step: 48/529, loss: 0.38923513889312744
2023-01-22 23:34:11.493726: step: 52/529, loss: 1.208553433418274
2023-01-22 23:34:12.616035: step: 56/529, loss: 0.284493625164032
2023-01-22 23:34:13.762102: step: 60/529, loss: 0.9339026808738708
2023-01-22 23:34:14.917842: step: 64/529, loss: 1.5366356372833252
2023-01-22 23:34:16.019141: step: 68/529, loss: 0.10496456921100616
2023-01-22 23:34:17.160129: step: 72/529, loss: 0.2413443922996521
2023-01-22 23:34:18.281908: step: 76/529, loss: 0.31122028827667236
2023-01-22 23:34:19.465162: step: 80/529, loss: 1.0785201787948608
2023-01-22 23:34:20.567664: step: 84/529, loss: 0.25327664613723755
2023-01-22 23:34:21.689589: step: 88/529, loss: 0.7175557613372803
2023-01-22 23:34:22.762129: step: 92/529, loss: 0.7942209243774414
2023-01-22 23:34:23.933951: step: 96/529, loss: 0.44551795721054077
2023-01-22 23:34:25.051332: step: 100/529, loss: 0.18662285804748535
2023-01-22 23:34:26.147174: step: 104/529, loss: 1.2460848093032837
2023-01-22 23:34:27.251066: step: 108/529, loss: 0.6176908612251282
2023-01-22 23:34:28.363798: step: 112/529, loss: 2.0322630405426025
2023-01-22 23:34:29.483418: step: 116/529, loss: 0.09562650322914124
2023-01-22 23:34:30.598524: step: 120/529, loss: 0.888964056968689
2023-01-22 23:34:31.689726: step: 124/529, loss: 0.4442671537399292
2023-01-22 23:34:32.782177: step: 128/529, loss: 1.3291382789611816
2023-01-22 23:34:33.879706: step: 132/529, loss: 0.26445913314819336
2023-01-22 23:34:34.977980: step: 136/529, loss: 0.9219101071357727
2023-01-22 23:34:36.093926: step: 140/529, loss: 2.302140474319458
2023-01-22 23:34:37.216797: step: 144/529, loss: 1.288550615310669
2023-01-22 23:34:38.331098: step: 148/529, loss: 0.6995092630386353
2023-01-22 23:34:39.444784: step: 152/529, loss: 0.5388339757919312
2023-01-22 23:34:40.582135: step: 156/529, loss: 0.5267397165298462
2023-01-22 23:34:41.694110: step: 160/529, loss: 0.30286896228790283
2023-01-22 23:34:42.798480: step: 164/529, loss: 0.6007466316223145
2023-01-22 23:34:43.918058: step: 168/529, loss: 0.4984992742538452
2023-01-22 23:34:45.010456: step: 172/529, loss: 0.7836005687713623
2023-01-22 23:34:46.103674: step: 176/529, loss: 3.4949352741241455
2023-01-22 23:34:47.275382: step: 180/529, loss: 0.56257164478302
2023-01-22 23:34:48.401660: step: 184/529, loss: 0.6769910454750061
2023-01-22 23:34:49.546721: step: 188/529, loss: 1.000937819480896
2023-01-22 23:34:50.654710: step: 192/529, loss: 1.4219428300857544
2023-01-22 23:34:51.795226: step: 196/529, loss: 0.5274946093559265
2023-01-22 23:34:52.926267: step: 200/529, loss: 0.49316632747650146
2023-01-22 23:34:54.011551: step: 204/529, loss: 0.39516887068748474
2023-01-22 23:34:55.120749: step: 208/529, loss: 0.16148653626441956
2023-01-22 23:34:56.229700: step: 212/529, loss: 0.33876028656959534
2023-01-22 23:34:57.328873: step: 216/529, loss: 0.39098015427589417
2023-01-22 23:34:58.457859: step: 220/529, loss: 0.14921438694000244
2023-01-22 23:34:59.589277: step: 224/529, loss: 1.6781399250030518
2023-01-22 23:35:00.734479: step: 228/529, loss: 0.11910490691661835
2023-01-22 23:35:01.864960: step: 232/529, loss: 0.7250655293464661
2023-01-22 23:35:03.020792: step: 236/529, loss: 1.2986040115356445
2023-01-22 23:35:04.120738: step: 240/529, loss: 0.24357634782791138
2023-01-22 23:35:05.232909: step: 244/529, loss: 0.35963886976242065
2023-01-22 23:35:06.348808: step: 248/529, loss: 1.0588583946228027
2023-01-22 23:35:07.495909: step: 252/529, loss: 0.2864035665988922
2023-01-22 23:35:08.639774: step: 256/529, loss: 0.6596001386642456
2023-01-22 23:35:09.760371: step: 260/529, loss: 0.4405243992805481
2023-01-22 23:35:10.873398: step: 264/529, loss: 0.3350624144077301
2023-01-22 23:35:11.971680: step: 268/529, loss: 0.3889426589012146
2023-01-22 23:35:13.104879: step: 272/529, loss: 0.231179341673851
2023-01-22 23:35:14.227322: step: 276/529, loss: 0.5403510928153992
2023-01-22 23:35:15.385743: step: 280/529, loss: 1.8436577320098877
2023-01-22 23:35:16.489890: step: 284/529, loss: 0.27053770422935486
2023-01-22 23:35:17.594340: step: 288/529, loss: 0.6908745765686035
2023-01-22 23:35:18.729166: step: 292/529, loss: 0.6526495218276978
2023-01-22 23:35:19.825569: step: 296/529, loss: 0.08405972272157669
2023-01-22 23:35:20.921565: step: 300/529, loss: 0.34178784489631653
2023-01-22 23:35:22.036701: step: 304/529, loss: 1.9574577808380127
2023-01-22 23:35:23.135672: step: 308/529, loss: 0.43951866030693054
2023-01-22 23:35:24.264686: step: 312/529, loss: 1.7129429578781128
2023-01-22 23:35:25.363574: step: 316/529, loss: 0.3309894800186157
2023-01-22 23:35:26.485348: step: 320/529, loss: 1.1224126815795898
2023-01-22 23:35:27.565816: step: 324/529, loss: 0.23305730521678925
2023-01-22 23:35:28.685651: step: 328/529, loss: 0.07745695114135742
2023-01-22 23:35:29.777714: step: 332/529, loss: 6.454632759094238
2023-01-22 23:35:30.867845: step: 336/529, loss: 0.21550145745277405
2023-01-22 23:35:31.969864: step: 340/529, loss: 0.21445322036743164
2023-01-22 23:35:33.088943: step: 344/529, loss: 0.7850074768066406
2023-01-22 23:35:34.175440: step: 348/529, loss: 1.282077431678772
2023-01-22 23:35:35.275796: step: 352/529, loss: 0.6246235370635986
2023-01-22 23:35:36.419182: step: 356/529, loss: 1.216802716255188
2023-01-22 23:35:37.545009: step: 360/529, loss: 0.09026036411523819
2023-01-22 23:35:38.687595: step: 364/529, loss: 0.8711719512939453
2023-01-22 23:35:39.789859: step: 368/529, loss: 0.9840619564056396
2023-01-22 23:35:40.906639: step: 372/529, loss: 0.34870004653930664
2023-01-22 23:35:42.009347: step: 376/529, loss: 1.8122676610946655
2023-01-22 23:35:43.107831: step: 380/529, loss: 0.5293132662773132
2023-01-22 23:35:44.249403: step: 384/529, loss: 1.0776166915893555
2023-01-22 23:35:45.365523: step: 388/529, loss: 1.0728297233581543
2023-01-22 23:35:46.493538: step: 392/529, loss: 0.9263383746147156
2023-01-22 23:35:47.570273: step: 396/529, loss: 6.870106220245361
2023-01-22 23:35:48.668058: step: 400/529, loss: 1.1725728511810303
2023-01-22 23:35:49.797912: step: 404/529, loss: 0.29519081115722656
2023-01-22 23:35:50.912000: step: 408/529, loss: 0.34393128752708435
2023-01-22 23:35:52.015965: step: 412/529, loss: 0.1468048095703125
2023-01-22 23:35:53.177002: step: 416/529, loss: 0.3922603726387024
2023-01-22 23:35:54.297442: step: 420/529, loss: 0.5837979316711426
2023-01-22 23:35:55.421156: step: 424/529, loss: 0.7148324847221375
2023-01-22 23:35:56.513652: step: 428/529, loss: 0.5638807415962219
2023-01-22 23:35:57.632826: step: 432/529, loss: 0.8276436924934387
2023-01-22 23:35:58.739168: step: 436/529, loss: 0.7725765705108643
2023-01-22 23:35:59.874744: step: 440/529, loss: 0.450872004032135
2023-01-22 23:36:01.004630: step: 444/529, loss: 1.2682194709777832
2023-01-22 23:36:02.096721: step: 448/529, loss: 0.31782713532447815
2023-01-22 23:36:03.200113: step: 452/529, loss: 2.5355019569396973
2023-01-22 23:36:04.305731: step: 456/529, loss: 0.14280109107494354
2023-01-22 23:36:05.431773: step: 460/529, loss: 0.26157569885253906
2023-01-22 23:36:06.545111: step: 464/529, loss: 0.9144749641418457
2023-01-22 23:36:07.670753: step: 468/529, loss: 1.2637255191802979
2023-01-22 23:36:08.786255: step: 472/529, loss: 0.7113516330718994
2023-01-22 23:36:09.896407: step: 476/529, loss: 0.3593212366104126
2023-01-22 23:36:11.008611: step: 480/529, loss: 1.1298960447311401
2023-01-22 23:36:12.101783: step: 484/529, loss: 0.4189690947532654
2023-01-22 23:36:13.241370: step: 488/529, loss: 0.3121662139892578
2023-01-22 23:36:14.364097: step: 492/529, loss: 0.3331439197063446
2023-01-22 23:36:15.480468: step: 496/529, loss: 0.16605758666992188
2023-01-22 23:36:16.578778: step: 500/529, loss: 1.9005495309829712
2023-01-22 23:36:17.668757: step: 504/529, loss: 0.245101660490036
2023-01-22 23:36:18.808707: step: 508/529, loss: 0.7208782434463501
2023-01-22 23:36:19.907322: step: 512/529, loss: 0.1765473484992981
2023-01-22 23:36:20.998710: step: 516/529, loss: 0.1999608874320984
2023-01-22 23:36:22.092579: step: 520/529, loss: 0.2706255316734314
2023-01-22 23:36:23.199495: step: 524/529, loss: 0.7563664317131042
2023-01-22 23:36:24.307311: step: 528/529, loss: 0.5105339288711548
2023-01-22 23:36:25.436542: step: 532/529, loss: 0.3250455856323242
2023-01-22 23:36:26.536890: step: 536/529, loss: 0.6623229384422302
2023-01-22 23:36:27.631045: step: 540/529, loss: 0.5985125303268433
2023-01-22 23:36:28.740570: step: 544/529, loss: 0.941774308681488
2023-01-22 23:36:29.841768: step: 548/529, loss: 0.7502085566520691
2023-01-22 23:36:30.969950: step: 552/529, loss: 0.2502526342868805
2023-01-22 23:36:32.062749: step: 556/529, loss: 0.5988870859146118
2023-01-22 23:36:33.179283: step: 560/529, loss: 0.643242597579956
2023-01-22 23:36:34.336419: step: 564/529, loss: 0.32086771726608276
2023-01-22 23:36:35.435537: step: 568/529, loss: 0.28589364886283875
2023-01-22 23:36:36.527396: step: 572/529, loss: 0.3787912130355835
2023-01-22 23:36:37.616333: step: 576/529, loss: 0.2798100709915161
2023-01-22 23:36:38.715739: step: 580/529, loss: 0.6718266010284424
2023-01-22 23:36:39.822633: step: 584/529, loss: 0.6852802634239197
2023-01-22 23:36:40.976987: step: 588/529, loss: 0.17157721519470215
2023-01-22 23:36:42.112767: step: 592/529, loss: 0.26092034578323364
2023-01-22 23:36:43.208670: step: 596/529, loss: 0.21380558609962463
2023-01-22 23:36:44.320409: step: 600/529, loss: 0.24265041947364807
2023-01-22 23:36:45.446591: step: 604/529, loss: 0.41870707273483276
2023-01-22 23:36:46.543818: step: 608/529, loss: 0.29454079270362854
2023-01-22 23:36:47.655412: step: 612/529, loss: 0.19271717965602875
2023-01-22 23:36:48.777696: step: 616/529, loss: 0.480964332818985
2023-01-22 23:36:49.885785: step: 620/529, loss: 0.2303260862827301
2023-01-22 23:36:50.991684: step: 624/529, loss: 0.3906545341014862
2023-01-22 23:36:52.098381: step: 628/529, loss: 0.48213696479797363
2023-01-22 23:36:53.202344: step: 632/529, loss: 0.7085826992988586
2023-01-22 23:36:54.329973: step: 636/529, loss: 0.8184240460395813
2023-01-22 23:36:55.445480: step: 640/529, loss: 0.6251978874206543
2023-01-22 23:36:56.542752: step: 644/529, loss: 0.17595921456813812
2023-01-22 23:36:57.664565: step: 648/529, loss: 0.08084774017333984
2023-01-22 23:36:58.779217: step: 652/529, loss: 1.0904420614242554
2023-01-22 23:36:59.900344: step: 656/529, loss: 1.6529580354690552
2023-01-22 23:37:01.016991: step: 660/529, loss: 1.0905689001083374
2023-01-22 23:37:02.134635: step: 664/529, loss: 0.6265753507614136
2023-01-22 23:37:03.244905: step: 668/529, loss: 0.6836234927177429
2023-01-22 23:37:04.347508: step: 672/529, loss: 0.3016183078289032
2023-01-22 23:37:05.457969: step: 676/529, loss: 6.876376152038574
2023-01-22 23:37:06.558181: step: 680/529, loss: 0.21166175603866577
2023-01-22 23:37:07.685470: step: 684/529, loss: 0.30103379487991333
2023-01-22 23:37:08.809173: step: 688/529, loss: 0.19192494451999664
2023-01-22 23:37:09.923836: step: 692/529, loss: 0.15551204979419708
2023-01-22 23:37:11.086580: step: 696/529, loss: 1.1883652210235596
2023-01-22 23:37:12.195063: step: 700/529, loss: 0.3992368280887604
2023-01-22 23:37:13.299087: step: 704/529, loss: 2.868074655532837
2023-01-22 23:37:14.414886: step: 708/529, loss: 0.9678558111190796
2023-01-22 23:37:15.540771: step: 712/529, loss: 0.5711044073104858
2023-01-22 23:37:16.626729: step: 716/529, loss: 0.1846696436405182
2023-01-22 23:37:17.730832: step: 720/529, loss: 1.7841217517852783
2023-01-22 23:37:18.838129: step: 724/529, loss: 0.3993869721889496
2023-01-22 23:37:20.012246: step: 728/529, loss: 0.601866602897644
2023-01-22 23:37:21.123894: step: 732/529, loss: 0.5240635871887207
2023-01-22 23:37:22.230560: step: 736/529, loss: 0.44053757190704346
2023-01-22 23:37:23.354631: step: 740/529, loss: 0.28165900707244873
2023-01-22 23:37:24.453615: step: 744/529, loss: 0.5654706954956055
2023-01-22 23:37:25.549388: step: 748/529, loss: 0.3745911717414856
2023-01-22 23:37:26.663225: step: 752/529, loss: 0.24808111786842346
2023-01-22 23:37:27.754441: step: 756/529, loss: 0.35858869552612305
2023-01-22 23:37:28.851652: step: 760/529, loss: 0.223505899310112
2023-01-22 23:37:29.969845: step: 764/529, loss: 0.7637803554534912
2023-01-22 23:37:31.099396: step: 768/529, loss: 1.00881028175354
2023-01-22 23:37:32.188528: step: 772/529, loss: 0.33720290660858154
2023-01-22 23:37:33.297901: step: 776/529, loss: 0.26835161447525024
2023-01-22 23:37:34.395382: step: 780/529, loss: 0.20082814991474152
2023-01-22 23:37:35.480397: step: 784/529, loss: 0.5037037134170532
2023-01-22 23:37:36.581068: step: 788/529, loss: 0.08456037193536758
2023-01-22 23:37:37.666612: step: 792/529, loss: 0.7846124172210693
2023-01-22 23:37:38.764361: step: 796/529, loss: 0.17308759689331055
2023-01-22 23:37:39.856754: step: 800/529, loss: 0.20586219429969788
2023-01-22 23:37:40.954649: step: 804/529, loss: 0.5375609397888184
2023-01-22 23:37:42.069438: step: 808/529, loss: 0.14410077035427094
2023-01-22 23:37:43.182346: step: 812/529, loss: 2.275195598602295
2023-01-22 23:37:44.273729: step: 816/529, loss: 0.358944296836853
2023-01-22 23:37:45.356184: step: 820/529, loss: 1.0653698444366455
2023-01-22 23:37:46.504156: step: 824/529, loss: 0.3719783425331116
2023-01-22 23:37:47.626609: step: 828/529, loss: 0.17783474922180176
2023-01-22 23:37:48.725938: step: 832/529, loss: 0.2557685971260071
2023-01-22 23:37:49.849504: step: 836/529, loss: 3.7622501850128174
2023-01-22 23:37:50.956196: step: 840/529, loss: 0.24286863207817078
2023-01-22 23:37:52.045342: step: 844/529, loss: 0.7735523581504822
2023-01-22 23:37:53.150842: step: 848/529, loss: 2.3334944248199463
2023-01-22 23:37:54.253541: step: 852/529, loss: 0.25273099541664124
2023-01-22 23:37:55.366775: step: 856/529, loss: 1.5338503122329712
2023-01-22 23:37:56.475588: step: 860/529, loss: 0.5666224956512451
2023-01-22 23:37:57.585498: step: 864/529, loss: 0.3180598020553589
2023-01-22 23:37:58.746855: step: 868/529, loss: 0.6632059812545776
2023-01-22 23:37:59.840110: step: 872/529, loss: 1.041609764099121
2023-01-22 23:38:00.972820: step: 876/529, loss: 0.8791897296905518
2023-01-22 23:38:02.059125: step: 880/529, loss: 2.2251648902893066
2023-01-22 23:38:03.192132: step: 884/529, loss: 0.2375658005475998
2023-01-22 23:38:04.302988: step: 888/529, loss: 0.3670843243598938
2023-01-22 23:38:05.437155: step: 892/529, loss: 0.44228315353393555
2023-01-22 23:38:06.546487: step: 896/529, loss: 0.6931800246238708
2023-01-22 23:38:07.659620: step: 900/529, loss: 0.6793521642684937
2023-01-22 23:38:08.781332: step: 904/529, loss: 0.8143658638000488
2023-01-22 23:38:09.902380: step: 908/529, loss: 0.1742684543132782
2023-01-22 23:38:11.021855: step: 912/529, loss: 1.215588092803955
2023-01-22 23:38:12.103646: step: 916/529, loss: 0.49752432107925415
2023-01-22 23:38:13.258193: step: 920/529, loss: 0.37126654386520386
2023-01-22 23:38:14.381537: step: 924/529, loss: 0.32738104462623596
2023-01-22 23:38:15.508567: step: 928/529, loss: 1.0940759181976318
2023-01-22 23:38:16.632434: step: 932/529, loss: 2.2437081336975098
2023-01-22 23:38:17.738895: step: 936/529, loss: 0.49070829153060913
2023-01-22 23:38:18.838093: step: 940/529, loss: 0.29194411635398865
2023-01-22 23:38:19.980499: step: 944/529, loss: 0.8337479829788208
2023-01-22 23:38:21.087580: step: 948/529, loss: 2.0440027713775635
2023-01-22 23:38:22.224402: step: 952/529, loss: 0.9109687805175781
2023-01-22 23:38:23.358156: step: 956/529, loss: 0.5357109308242798
2023-01-22 23:38:24.466032: step: 960/529, loss: 0.4600534439086914
2023-01-22 23:38:25.605947: step: 964/529, loss: 7.5580549240112305
2023-01-22 23:38:26.734023: step: 968/529, loss: 0.6537569761276245
2023-01-22 23:38:27.862019: step: 972/529, loss: 1.4608421325683594
2023-01-22 23:38:28.996766: step: 976/529, loss: 0.3898892402648926
2023-01-22 23:38:30.095672: step: 980/529, loss: 0.9173405170440674
2023-01-22 23:38:31.195061: step: 984/529, loss: 2.3218090534210205
2023-01-22 23:38:32.333545: step: 988/529, loss: 1.6060621738433838
2023-01-22 23:38:33.426667: step: 992/529, loss: 0.3135437071323395
2023-01-22 23:38:34.533039: step: 996/529, loss: 0.4413120448589325
2023-01-22 23:38:35.658493: step: 1000/529, loss: 0.23012995719909668
2023-01-22 23:38:36.790583: step: 1004/529, loss: 1.0736677646636963
2023-01-22 23:38:37.908553: step: 1008/529, loss: 0.35119175910949707
2023-01-22 23:38:39.061004: step: 1012/529, loss: 0.3621875047683716
2023-01-22 23:38:40.145976: step: 1016/529, loss: 1.4045734405517578
2023-01-22 23:38:41.249154: step: 1020/529, loss: 0.14289188385009766
2023-01-22 23:38:42.377899: step: 1024/529, loss: 1.5238171815872192
2023-01-22 23:38:43.490705: step: 1028/529, loss: 0.255527138710022
2023-01-22 23:38:44.616625: step: 1032/529, loss: 2.3973302841186523
2023-01-22 23:38:45.720765: step: 1036/529, loss: 0.24948197603225708
2023-01-22 23:38:46.850847: step: 1040/529, loss: 0.7357456088066101
2023-01-22 23:38:47.943156: step: 1044/529, loss: 0.5525869131088257
2023-01-22 23:38:49.048596: step: 1048/529, loss: 0.28170856833457947
2023-01-22 23:38:50.176488: step: 1052/529, loss: 0.14208835363388062
2023-01-22 23:38:51.287235: step: 1056/529, loss: 1.1579396724700928
2023-01-22 23:38:52.401137: step: 1060/529, loss: 6.846298694610596
2023-01-22 23:38:53.504220: step: 1064/529, loss: 0.5858241319656372
2023-01-22 23:38:54.608678: step: 1068/529, loss: 1.2356059551239014
2023-01-22 23:38:55.693723: step: 1072/529, loss: 1.5922828912734985
2023-01-22 23:38:56.803954: step: 1076/529, loss: 0.1442646086215973
2023-01-22 23:38:57.921312: step: 1080/529, loss: 0.5200090408325195
2023-01-22 23:38:59.065288: step: 1084/529, loss: 2.0759453773498535
2023-01-22 23:39:00.197988: step: 1088/529, loss: 0.16801553964614868
2023-01-22 23:39:01.303312: step: 1092/529, loss: 1.6849634647369385
2023-01-22 23:39:02.405076: step: 1096/529, loss: 0.699837863445282
2023-01-22 23:39:03.502615: step: 1100/529, loss: 0.3389669358730316
2023-01-22 23:39:04.631665: step: 1104/529, loss: 2.048841953277588
2023-01-22 23:39:05.729696: step: 1108/529, loss: 0.4343034625053406
2023-01-22 23:39:06.843807: step: 1112/529, loss: 0.14017248153686523
2023-01-22 23:39:07.989630: step: 1116/529, loss: 0.22366638481616974
2023-01-22 23:39:09.094438: step: 1120/529, loss: 0.15395641326904297
2023-01-22 23:39:10.173749: step: 1124/529, loss: 0.24705466628074646
2023-01-22 23:39:11.302674: step: 1128/529, loss: 0.250865638256073
2023-01-22 23:39:12.394225: step: 1132/529, loss: 0.22677364945411682
2023-01-22 23:39:13.499194: step: 1136/529, loss: 0.32051271200180054
2023-01-22 23:39:14.585425: step: 1140/529, loss: 0.2160608172416687
2023-01-22 23:39:15.715183: step: 1144/529, loss: 1.5062017440795898
2023-01-22 23:39:16.843278: step: 1148/529, loss: 2.317227363586426
2023-01-22 23:39:17.973258: step: 1152/529, loss: 0.08393897861242294
2023-01-22 23:39:19.076234: step: 1156/529, loss: 0.3460056483745575
2023-01-22 23:39:20.225686: step: 1160/529, loss: 0.5972245931625366
2023-01-22 23:39:21.350235: step: 1164/529, loss: 0.35770758986473083
2023-01-22 23:39:22.444384: step: 1168/529, loss: 0.3233143985271454
2023-01-22 23:39:23.577198: step: 1172/529, loss: 0.1382053792476654
2023-01-22 23:39:24.676733: step: 1176/529, loss: 1.7616643905639648
2023-01-22 23:39:25.766850: step: 1180/529, loss: 1.4795652627944946
2023-01-22 23:39:26.861430: step: 1184/529, loss: 0.4514956474304199
2023-01-22 23:39:27.974582: step: 1188/529, loss: 0.11908464133739471
2023-01-22 23:39:29.067194: step: 1192/529, loss: 1.882380723953247
2023-01-22 23:39:30.181011: step: 1196/529, loss: 0.7030121088027954
2023-01-22 23:39:31.292715: step: 1200/529, loss: 0.26276880502700806
2023-01-22 23:39:32.398604: step: 1204/529, loss: 0.4116804599761963
2023-01-22 23:39:33.488685: step: 1208/529, loss: 0.8785880208015442
2023-01-22 23:39:34.576405: step: 1212/529, loss: 1.0726191997528076
2023-01-22 23:39:35.675767: step: 1216/529, loss: 0.46557560563087463
2023-01-22 23:39:36.793871: step: 1220/529, loss: 1.3430287837982178
2023-01-22 23:39:37.876077: step: 1224/529, loss: 0.3480450510978699
2023-01-22 23:39:38.964834: step: 1228/529, loss: 0.1810993254184723
2023-01-22 23:39:40.065887: step: 1232/529, loss: 1.1802563667297363
2023-01-22 23:39:41.172042: step: 1236/529, loss: 1.2568211555480957
2023-01-22 23:39:42.284004: step: 1240/529, loss: 0.7923814058303833
2023-01-22 23:39:43.386711: step: 1244/529, loss: 0.1576269268989563
2023-01-22 23:39:44.469105: step: 1248/529, loss: 0.13066306710243225
2023-01-22 23:39:45.572816: step: 1252/529, loss: 0.3931480646133423
2023-01-22 23:39:46.691076: step: 1256/529, loss: 0.09242627769708633
2023-01-22 23:39:47.759219: step: 1260/529, loss: 0.16336041688919067
2023-01-22 23:39:48.860692: step: 1264/529, loss: 0.13587962090969086
2023-01-22 23:39:49.981951: step: 1268/529, loss: 0.27442023158073425
2023-01-22 23:39:51.075391: step: 1272/529, loss: 0.3076659142971039
2023-01-22 23:39:52.182032: step: 1276/529, loss: 0.22706851363182068
2023-01-22 23:39:53.285896: step: 1280/529, loss: 0.2371736615896225
2023-01-22 23:39:54.382851: step: 1284/529, loss: 0.15129134058952332
2023-01-22 23:39:55.525319: step: 1288/529, loss: 0.9143304824829102
2023-01-22 23:39:56.630106: step: 1292/529, loss: 0.3363853693008423
2023-01-22 23:39:57.762215: step: 1296/529, loss: 0.5157318115234375
2023-01-22 23:39:58.843236: step: 1300/529, loss: 0.1957314908504486
2023-01-22 23:39:59.932661: step: 1304/529, loss: 0.29106923937797546
2023-01-22 23:40:01.048628: step: 1308/529, loss: 1.2171783447265625
2023-01-22 23:40:02.162337: step: 1312/529, loss: 0.37879467010498047
2023-01-22 23:40:03.249748: step: 1316/529, loss: 0.15320749580860138
2023-01-22 23:40:04.382635: step: 1320/529, loss: 0.16589584946632385
2023-01-22 23:40:05.505012: step: 1324/529, loss: 1.137056589126587
2023-01-22 23:40:06.620294: step: 1328/529, loss: 0.20302076637744904
2023-01-22 23:40:07.730527: step: 1332/529, loss: 0.21741986274719238
2023-01-22 23:40:08.816927: step: 1336/529, loss: 0.25976860523223877
2023-01-22 23:40:09.958599: step: 1340/529, loss: 2.7457759380340576
2023-01-22 23:40:11.079812: step: 1344/529, loss: 1.6406248807907104
2023-01-22 23:40:12.206511: step: 1348/529, loss: 0.2748958170413971
2023-01-22 23:40:13.310606: step: 1352/529, loss: 1.4270340204238892
2023-01-22 23:40:14.451326: step: 1356/529, loss: 1.1498936414718628
2023-01-22 23:40:15.581761: step: 1360/529, loss: 0.19536876678466797
2023-01-22 23:40:16.696954: step: 1364/529, loss: 0.668630838394165
2023-01-22 23:40:17.795656: step: 1368/529, loss: 0.14152947068214417
2023-01-22 23:40:18.883744: step: 1372/529, loss: 0.7408544421195984
2023-01-22 23:40:19.987288: step: 1376/529, loss: 0.27183055877685547
2023-01-22 23:40:21.094269: step: 1380/529, loss: 0.3502856492996216
2023-01-22 23:40:22.202748: step: 1384/529, loss: 0.27408719062805176
2023-01-22 23:40:23.302450: step: 1388/529, loss: 0.31254032254219055
2023-01-22 23:40:24.405080: step: 1392/529, loss: 0.11689014732837677
2023-01-22 23:40:25.509548: step: 1396/529, loss: 0.15305423736572266
2023-01-22 23:40:26.632813: step: 1400/529, loss: 0.8012265563011169
2023-01-22 23:40:27.728591: step: 1404/529, loss: 2.31156325340271
2023-01-22 23:40:28.874835: step: 1408/529, loss: 0.374700129032135
2023-01-22 23:40:29.969215: step: 1412/529, loss: 0.23223847150802612
2023-01-22 23:40:31.133064: step: 1416/529, loss: 0.11860805004835129
2023-01-22 23:40:32.230292: step: 1420/529, loss: 0.4748643636703491
2023-01-22 23:40:33.336368: step: 1424/529, loss: 0.1042964980006218
2023-01-22 23:40:34.473794: step: 1428/529, loss: 0.7844324707984924
2023-01-22 23:40:35.577819: step: 1432/529, loss: 0.13150271773338318
2023-01-22 23:40:36.709356: step: 1436/529, loss: 0.25126132369041443
2023-01-22 23:40:37.851906: step: 1440/529, loss: 0.2835647463798523
2023-01-22 23:40:38.945077: step: 1444/529, loss: 0.05659355968236923
2023-01-22 23:40:40.054822: step: 1448/529, loss: 0.9214946627616882
2023-01-22 23:40:41.213937: step: 1452/529, loss: 0.12622341513633728
2023-01-22 23:40:42.308408: step: 1456/529, loss: 0.7260076999664307
2023-01-22 23:40:43.380814: step: 1460/529, loss: 0.08598079532384872
2023-01-22 23:40:44.512206: step: 1464/529, loss: 0.5306049585342407
2023-01-22 23:40:45.633900: step: 1468/529, loss: 0.19852668046951294
2023-01-22 23:40:46.734130: step: 1472/529, loss: 1.3862760066986084
2023-01-22 23:40:47.865603: step: 1476/529, loss: 0.8602093458175659
2023-01-22 23:40:48.934809: step: 1480/529, loss: 0.1600692868232727
2023-01-22 23:40:50.029796: step: 1484/529, loss: 0.8565475344657898
2023-01-22 23:40:51.124486: step: 1488/529, loss: 0.11720190942287445
2023-01-22 23:40:52.238905: step: 1492/529, loss: 0.45756617188453674
2023-01-22 23:40:53.348791: step: 1496/529, loss: 6.647948265075684
2023-01-22 23:40:54.468444: step: 1500/529, loss: 0.2115098088979721
2023-01-22 23:40:55.550065: step: 1504/529, loss: 0.16186895966529846
2023-01-22 23:40:56.656277: step: 1508/529, loss: 0.6816369891166687
2023-01-22 23:40:57.754815: step: 1512/529, loss: 0.4905688166618347
2023-01-22 23:40:58.870196: step: 1516/529, loss: 0.8361889123916626
2023-01-22 23:41:00.005164: step: 1520/529, loss: 0.10857601463794708
2023-01-22 23:41:01.107326: step: 1524/529, loss: 0.6395866870880127
2023-01-22 23:41:02.205807: step: 1528/529, loss: 0.6413912773132324
2023-01-22 23:41:03.332721: step: 1532/529, loss: 0.12036089599132538
2023-01-22 23:41:04.439940: step: 1536/529, loss: 0.7675918936729431
2023-01-22 23:41:05.551424: step: 1540/529, loss: 0.33137089014053345
2023-01-22 23:41:06.679038: step: 1544/529, loss: 0.19094133377075195
2023-01-22 23:41:07.800078: step: 1548/529, loss: 0.2136303335428238
2023-01-22 23:41:08.911276: step: 1552/529, loss: 0.12485656142234802
2023-01-22 23:41:10.028952: step: 1556/529, loss: 0.8323894143104553
2023-01-22 23:41:11.122749: step: 1560/529, loss: 0.35746800899505615
2023-01-22 23:41:12.245462: step: 1564/529, loss: 2.2854628562927246
2023-01-22 23:41:13.347152: step: 1568/529, loss: 1.7288563251495361
2023-01-22 23:41:14.475776: step: 1572/529, loss: 0.09137392044067383
2023-01-22 23:41:15.567586: step: 1576/529, loss: 0.2721441388130188
2023-01-22 23:41:16.714637: step: 1580/529, loss: 1.2794252634048462
2023-01-22 23:41:17.830593: step: 1584/529, loss: 2.586719274520874
2023-01-22 23:41:18.934120: step: 1588/529, loss: 0.2548113167285919
2023-01-22 23:41:20.042500: step: 1592/529, loss: 1.0186208486557007
2023-01-22 23:41:21.165543: step: 1596/529, loss: 1.733971357345581
2023-01-22 23:41:22.269115: step: 1600/529, loss: 0.9125651121139526
2023-01-22 23:41:23.369836: step: 1604/529, loss: 0.6683480739593506
2023-01-22 23:41:24.514404: step: 1608/529, loss: 0.15578250586986542
2023-01-22 23:41:25.640736: step: 1612/529, loss: 0.1358446180820465
2023-01-22 23:41:26.767629: step: 1616/529, loss: 0.3594614863395691
2023-01-22 23:41:27.894784: step: 1620/529, loss: 0.1455286145210266
2023-01-22 23:41:29.010355: step: 1624/529, loss: 0.8110268712043762
2023-01-22 23:41:30.147514: step: 1628/529, loss: 0.08677692711353302
2023-01-22 23:41:31.265134: step: 1632/529, loss: 0.521518886089325
2023-01-22 23:41:32.367557: step: 1636/529, loss: 0.1192840114235878
2023-01-22 23:41:33.459596: step: 1640/529, loss: 0.1738756150007248
2023-01-22 23:41:34.593100: step: 1644/529, loss: 0.8496429324150085
2023-01-22 23:41:35.696490: step: 1648/529, loss: 0.2477641999721527
2023-01-22 23:41:36.817906: step: 1652/529, loss: 0.3932759463787079
2023-01-22 23:41:37.944542: step: 1656/529, loss: 0.21739532053470612
2023-01-22 23:41:39.036084: step: 1660/529, loss: 0.6948230862617493
2023-01-22 23:41:40.155093: step: 1664/529, loss: 0.48446816205978394
2023-01-22 23:41:41.253405: step: 1668/529, loss: 1.647700309753418
2023-01-22 23:41:42.376462: step: 1672/529, loss: 0.3154051899909973
2023-01-22 23:41:43.493492: step: 1676/529, loss: 0.22243304550647736
2023-01-22 23:41:44.585678: step: 1680/529, loss: 0.14397311210632324
2023-01-22 23:41:45.671712: step: 1684/529, loss: 0.10298324376344681
2023-01-22 23:41:46.763878: step: 1688/529, loss: 0.3207573890686035
2023-01-22 23:41:47.875036: step: 1692/529, loss: 0.3615146279335022
2023-01-22 23:41:48.986381: step: 1696/529, loss: 0.44014739990234375
2023-01-22 23:41:50.120803: step: 1700/529, loss: 0.19119468331336975
2023-01-22 23:41:51.221627: step: 1704/529, loss: 0.6909996271133423
2023-01-22 23:41:52.332837: step: 1708/529, loss: 0.5721532106399536
2023-01-22 23:41:53.455121: step: 1712/529, loss: 0.3849565386772156
2023-01-22 23:41:54.563904: step: 1716/529, loss: 2.519810914993286
2023-01-22 23:41:55.653397: step: 1720/529, loss: 0.1966181844472885
2023-01-22 23:41:56.753309: step: 1724/529, loss: 0.22541581094264984
2023-01-22 23:41:57.864228: step: 1728/529, loss: 0.2048512101173401
2023-01-22 23:41:58.996531: step: 1732/529, loss: 0.2168704867362976
2023-01-22 23:42:00.119027: step: 1736/529, loss: 0.5078675150871277
2023-01-22 23:42:01.275192: step: 1740/529, loss: 0.21213750541210175
2023-01-22 23:42:02.385173: step: 1744/529, loss: 0.3765409588813782
2023-01-22 23:42:03.540955: step: 1748/529, loss: 0.9130523800849915
2023-01-22 23:42:04.647658: step: 1752/529, loss: 0.5442807078361511
2023-01-22 23:42:05.744858: step: 1756/529, loss: 0.4957461953163147
2023-01-22 23:42:06.840009: step: 1760/529, loss: 0.13172730803489685
2023-01-22 23:42:07.959119: step: 1764/529, loss: 0.7788804173469543
2023-01-22 23:42:09.055980: step: 1768/529, loss: 1.0385152101516724
2023-01-22 23:42:10.177195: step: 1772/529, loss: 0.15449944138526917
2023-01-22 23:42:11.285045: step: 1776/529, loss: 0.6412561535835266
2023-01-22 23:42:12.400300: step: 1780/529, loss: 0.39307743310928345
2023-01-22 23:42:13.489813: step: 1784/529, loss: 0.166100412607193
2023-01-22 23:42:14.603982: step: 1788/529, loss: 0.7248702645301819
2023-01-22 23:42:15.725127: step: 1792/529, loss: 0.5662744641304016
2023-01-22 23:42:16.819736: step: 1796/529, loss: 0.44758567214012146
2023-01-22 23:42:17.928265: step: 1800/529, loss: 0.33152151107788086
2023-01-22 23:42:19.051536: step: 1804/529, loss: 0.7885726690292358
2023-01-22 23:42:20.151116: step: 1808/529, loss: 0.6790496706962585
2023-01-22 23:42:21.273873: step: 1812/529, loss: 1.0043998956680298
2023-01-22 23:42:22.412606: step: 1816/529, loss: 0.3004891872406006
2023-01-22 23:42:23.529589: step: 1820/529, loss: 0.1599387228488922
2023-01-22 23:42:24.633203: step: 1824/529, loss: 0.2533267140388489
2023-01-22 23:42:25.754812: step: 1828/529, loss: 0.7207271456718445
2023-01-22 23:42:26.855869: step: 1832/529, loss: 0.24773702025413513
2023-01-22 23:42:27.973563: step: 1836/529, loss: 0.7244818806648254
2023-01-22 23:42:29.066182: step: 1840/529, loss: 0.6834341883659363
2023-01-22 23:42:30.185730: step: 1844/529, loss: 1.0085415840148926
2023-01-22 23:42:31.276985: step: 1848/529, loss: 0.2685631215572357
2023-01-22 23:42:32.391174: step: 1852/529, loss: 1.247779369354248
2023-01-22 23:42:33.485086: step: 1856/529, loss: 0.6834778189659119
2023-01-22 23:42:34.577209: step: 1860/529, loss: 0.1104244738817215
2023-01-22 23:42:35.680442: step: 1864/529, loss: 0.5080947875976562
2023-01-22 23:42:36.755699: step: 1868/529, loss: 0.23532609641551971
2023-01-22 23:42:37.869204: step: 1872/529, loss: 0.1740579605102539
2023-01-22 23:42:38.983835: step: 1876/529, loss: 0.046334266662597656
2023-01-22 23:42:40.103672: step: 1880/529, loss: 0.26787012815475464
2023-01-22 23:42:41.208634: step: 1884/529, loss: 0.4222313165664673
2023-01-22 23:42:42.310887: step: 1888/529, loss: 0.39106273651123047
2023-01-22 23:42:43.408330: step: 1892/529, loss: 0.09448876976966858
2023-01-22 23:42:44.533377: step: 1896/529, loss: 0.19445809721946716
2023-01-22 23:42:45.630270: step: 1900/529, loss: 0.5161245465278625
2023-01-22 23:42:46.741601: step: 1904/529, loss: 0.3839361369609833
2023-01-22 23:42:47.866362: step: 1908/529, loss: 2.7287416458129883
2023-01-22 23:42:49.010399: step: 1912/529, loss: 2.105461359024048
2023-01-22 23:42:50.111692: step: 1916/529, loss: 0.1062900573015213
2023-01-22 23:42:51.219531: step: 1920/529, loss: 0.1700780987739563
2023-01-22 23:42:52.331026: step: 1924/529, loss: 0.550543487071991
2023-01-22 23:42:53.424565: step: 1928/529, loss: 0.5219593048095703
2023-01-22 23:42:54.528177: step: 1932/529, loss: 0.08461695164442062
2023-01-22 23:42:55.639054: step: 1936/529, loss: 0.3319927453994751
2023-01-22 23:42:56.722106: step: 1940/529, loss: 1.2415722608566284
2023-01-22 23:42:57.817701: step: 1944/529, loss: 0.19582301378250122
2023-01-22 23:42:58.958206: step: 1948/529, loss: 0.16134147346019745
2023-01-22 23:43:00.052886: step: 1952/529, loss: 0.16087284684181213
2023-01-22 23:43:01.168738: step: 1956/529, loss: 2.597561836242676
2023-01-22 23:43:02.286300: step: 1960/529, loss: 0.12044987082481384
2023-01-22 23:43:03.398334: step: 1964/529, loss: 0.15179438889026642
2023-01-22 23:43:04.503932: step: 1968/529, loss: 0.5907953381538391
2023-01-22 23:43:05.602888: step: 1972/529, loss: 0.589765727519989
2023-01-22 23:43:06.723741: step: 1976/529, loss: 0.40967217087745667
2023-01-22 23:43:07.844384: step: 1980/529, loss: 0.5136450529098511
2023-01-22 23:43:08.958767: step: 1984/529, loss: 0.23131780326366425
2023-01-22 23:43:10.086711: step: 1988/529, loss: 0.19981002807617188
2023-01-22 23:43:11.227951: step: 1992/529, loss: 0.1134800910949707
2023-01-22 23:43:12.344883: step: 1996/529, loss: 0.14816227555274963
2023-01-22 23:43:13.440196: step: 2000/529, loss: 0.17059297859668732
2023-01-22 23:43:14.533088: step: 2004/529, loss: 0.06281504780054092
2023-01-22 23:43:15.624970: step: 2008/529, loss: 0.3616578280925751
2023-01-22 23:43:16.732082: step: 2012/529, loss: 0.6039113998413086
2023-01-22 23:43:17.816054: step: 2016/529, loss: 0.433920294046402
2023-01-22 23:43:18.941293: step: 2020/529, loss: 0.17409348487854004
2023-01-22 23:43:20.092133: step: 2024/529, loss: 0.19531483948230743
2023-01-22 23:43:21.199303: step: 2028/529, loss: 0.4293663501739502
2023-01-22 23:43:22.290119: step: 2032/529, loss: 0.16214847564697266
2023-01-22 23:43:23.395877: step: 2036/529, loss: 0.21864166855812073
2023-01-22 23:43:24.487687: step: 2040/529, loss: 0.6431942582130432
2023-01-22 23:43:25.587212: step: 2044/529, loss: 0.15865576267242432
2023-01-22 23:43:26.676651: step: 2048/529, loss: 0.4180523753166199
2023-01-22 23:43:27.756240: step: 2052/529, loss: 0.220478817820549
2023-01-22 23:43:28.848433: step: 2056/529, loss: 0.21052700281143188
2023-01-22 23:43:29.935017: step: 2060/529, loss: 0.16934219002723694
2023-01-22 23:43:31.044440: step: 2064/529, loss: 0.0997040718793869
2023-01-22 23:43:32.126836: step: 2068/529, loss: 0.8931032419204712
2023-01-22 23:43:33.231524: step: 2072/529, loss: 0.029203986749053
2023-01-22 23:43:34.396313: step: 2076/529, loss: 0.30535459518432617
2023-01-22 23:43:35.499818: step: 2080/529, loss: 0.22159448266029358
2023-01-22 23:43:36.594278: step: 2084/529, loss: 0.4067089557647705
2023-01-22 23:43:37.715367: step: 2088/529, loss: 0.3600439429283142
2023-01-22 23:43:38.794676: step: 2092/529, loss: 0.06934278458356857
2023-01-22 23:43:39.891455: step: 2096/529, loss: 0.12507152557373047
2023-01-22 23:43:40.995067: step: 2100/529, loss: 0.745621919631958
2023-01-22 23:43:42.122971: step: 2104/529, loss: 0.8621286749839783
2023-01-22 23:43:43.244764: step: 2108/529, loss: 0.26914387941360474
2023-01-22 23:43:44.358740: step: 2112/529, loss: 0.10843344032764435
2023-01-22 23:43:45.480830: step: 2116/529, loss: 0.274789035320282
==================================================
Loss: 0.702
--------------------
Dev: {'event': {'p': 0.5240040858018387, 'r': 0.6830892143808256, 'f1': 0.593063583815029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5527544351073763, 'r': 0.6681715575620768, 'f1': 0.6050076647930506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5254237288135594, 'r': 0.5740740740740741, 'f1': 0.5486725663716815}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.31746031746031744, 'f1': 0.4081632653061224}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.40625, 'r': 0.3611111111111111, 'f1': 0.38235294117647056}, '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': 0.5240040858018387, 'r': 0.6830892143808256, 'f1': 0.593063583815029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5527544351073763, 'r': 0.6681715575620768, 'f1': 0.6050076647930506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5254237288135594, 'r': 0.5740740740740741, 'f1': 0.5486725663716815}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5240040858018387, 'r': 0.6830892143808256, 'f1': 0.593063583815029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5527544351073763, 'r': 0.6681715575620768, 'f1': 0.6050076647930506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.5714285714285714, 'r': 0.31746031746031744, 'f1': 0.4081632653061224}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5240040858018387, 'r': 0.6830892143808256, 'f1': 0.593063583815029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5527544351073763, 'r': 0.6681715575620768, 'f1': 0.6050076647930506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.40625, 'r': 0.3611111111111111, 'f1': 0.38235294117647056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:44:48.478772: step: 4/529, loss: 0.2860356569290161
2023-01-22 23:44:49.587975: step: 8/529, loss: 0.27518218755722046
2023-01-22 23:44:50.680540: step: 12/529, loss: 0.03611459955573082
2023-01-22 23:44:51.803959: step: 16/529, loss: 0.3172217607498169
2023-01-22 23:44:52.938661: step: 20/529, loss: 0.5037998557090759
2023-01-22 23:44:54.063651: step: 24/529, loss: 0.05699215084314346
2023-01-22 23:44:55.174849: step: 28/529, loss: 0.21777325868606567
2023-01-22 23:44:56.293250: step: 32/529, loss: 0.23721735179424286
2023-01-22 23:44:57.378700: step: 36/529, loss: 0.2301737368106842
2023-01-22 23:44:58.531868: step: 40/529, loss: 0.16542445123195648
2023-01-22 23:44:59.603218: step: 44/529, loss: 0.09972095489501953
2023-01-22 23:45:00.702966: step: 48/529, loss: 0.12891975045204163
2023-01-22 23:45:01.792033: step: 52/529, loss: 0.3611389994621277
2023-01-22 23:45:02.910495: step: 56/529, loss: 0.13424763083457947
2023-01-22 23:45:04.018463: step: 60/529, loss: 0.9503765106201172
2023-01-22 23:45:05.142394: step: 64/529, loss: 0.3756004869937897
2023-01-22 23:45:06.241741: step: 68/529, loss: 0.3070555329322815
2023-01-22 23:45:07.339270: step: 72/529, loss: 0.629376232624054
2023-01-22 23:45:08.459595: step: 76/529, loss: 0.3099052309989929
2023-01-22 23:45:09.593944: step: 80/529, loss: 0.41937607526779175
2023-01-22 23:45:10.685253: step: 84/529, loss: 0.15592436492443085
2023-01-22 23:45:11.825928: step: 88/529, loss: 0.3427921533584595
2023-01-22 23:45:12.949780: step: 92/529, loss: 0.11011648178100586
2023-01-22 23:45:14.039060: step: 96/529, loss: 0.1171741932630539
2023-01-22 23:45:15.144410: step: 100/529, loss: 0.9733048677444458
2023-01-22 23:45:16.259178: step: 104/529, loss: 0.17517490684986115
2023-01-22 23:45:17.402227: step: 108/529, loss: 0.07490038871765137
2023-01-22 23:45:18.542872: step: 112/529, loss: 0.13443231582641602
2023-01-22 23:45:19.657544: step: 116/529, loss: 0.2305595874786377
2023-01-22 23:45:20.769958: step: 120/529, loss: 0.3005775511264801
2023-01-22 23:45:21.889251: step: 124/529, loss: 0.23565511405467987
2023-01-22 23:45:23.000415: step: 128/529, loss: 0.5500003695487976
2023-01-22 23:45:24.136931: step: 132/529, loss: 0.22139397263526917
2023-01-22 23:45:25.231342: step: 136/529, loss: 0.19197499752044678
2023-01-22 23:45:26.362496: step: 140/529, loss: 1.0892413854599
2023-01-22 23:45:27.476114: step: 144/529, loss: 0.8368270993232727
2023-01-22 23:45:28.659075: step: 148/529, loss: 0.11113100498914719
2023-01-22 23:45:29.822279: step: 152/529, loss: 0.34302181005477905
2023-01-22 23:45:30.990055: step: 156/529, loss: 0.21152593195438385
2023-01-22 23:45:32.100442: step: 160/529, loss: 0.9145278930664062
2023-01-22 23:45:33.208002: step: 164/529, loss: 0.11634044349193573
2023-01-22 23:45:34.341354: step: 168/529, loss: 0.6937212944030762
2023-01-22 23:45:35.472521: step: 172/529, loss: 0.28506529331207275
2023-01-22 23:45:36.603055: step: 176/529, loss: 0.47687777876853943
2023-01-22 23:45:37.722857: step: 180/529, loss: 0.2957010269165039
2023-01-22 23:45:38.849421: step: 184/529, loss: 0.22779053449630737
2023-01-22 23:45:39.956242: step: 188/529, loss: 0.14600515365600586
2023-01-22 23:45:41.091960: step: 192/529, loss: 1.1644660234451294
2023-01-22 23:45:42.205163: step: 196/529, loss: 0.15589895844459534
2023-01-22 23:45:43.321552: step: 200/529, loss: 0.8292381167411804
2023-01-22 23:45:44.434674: step: 204/529, loss: 1.2156381607055664
2023-01-22 23:45:45.560677: step: 208/529, loss: 0.25848084688186646
2023-01-22 23:45:46.701462: step: 212/529, loss: 0.13020116090774536
2023-01-22 23:45:47.822984: step: 216/529, loss: 0.1744847297668457
2023-01-22 23:45:48.952647: step: 220/529, loss: 0.8398873209953308
2023-01-22 23:45:50.090814: step: 224/529, loss: 6.926356315612793
2023-01-22 23:45:51.210718: step: 228/529, loss: 7.660332202911377
2023-01-22 23:45:52.341345: step: 232/529, loss: 0.30642032623291016
2023-01-22 23:45:53.474748: step: 236/529, loss: 0.12316484749317169
2023-01-22 23:45:54.572225: step: 240/529, loss: 0.22747182846069336
2023-01-22 23:45:55.680541: step: 244/529, loss: 0.09230899810791016
2023-01-22 23:45:56.783659: step: 248/529, loss: 0.1784875988960266
2023-01-22 23:45:57.862642: step: 252/529, loss: 0.08645868301391602
2023-01-22 23:45:58.963092: step: 256/529, loss: 1.8523404598236084
2023-01-22 23:46:00.060912: step: 260/529, loss: 1.0354951620101929
2023-01-22 23:46:01.156714: step: 264/529, loss: 0.707019031047821
2023-01-22 23:46:02.259255: step: 268/529, loss: 0.37256985902786255
2023-01-22 23:46:03.348515: step: 272/529, loss: 0.1137721985578537
2023-01-22 23:46:04.464910: step: 276/529, loss: 0.37722882628440857
2023-01-22 23:46:05.574569: step: 280/529, loss: 1.10685133934021
2023-01-22 23:46:06.674933: step: 284/529, loss: 0.10990338027477264
2023-01-22 23:46:07.763931: step: 288/529, loss: 0.22471565008163452
2023-01-22 23:46:08.902197: step: 292/529, loss: 0.5236320495605469
2023-01-22 23:46:10.000594: step: 296/529, loss: 0.2033737748861313
2023-01-22 23:46:11.095847: step: 300/529, loss: 0.3361794650554657
2023-01-22 23:46:12.241428: step: 304/529, loss: 0.2288854569196701
2023-01-22 23:46:13.365687: step: 308/529, loss: 1.3480192422866821
2023-01-22 23:46:14.470461: step: 312/529, loss: 0.39426031708717346
2023-01-22 23:46:15.579685: step: 316/529, loss: 0.10438446700572968
2023-01-22 23:46:16.663820: step: 320/529, loss: 1.3860032558441162
2023-01-22 23:46:17.768936: step: 324/529, loss: 0.31454306840896606
2023-01-22 23:46:18.911196: step: 328/529, loss: 0.7631552815437317
2023-01-22 23:46:20.025129: step: 332/529, loss: 0.28372231125831604
2023-01-22 23:46:21.100537: step: 336/529, loss: 0.7222623825073242
2023-01-22 23:46:22.225406: step: 340/529, loss: 0.9577038884162903
2023-01-22 23:46:23.326088: step: 344/529, loss: 0.6774893999099731
2023-01-22 23:46:24.459484: step: 348/529, loss: 1.6684404611587524
2023-01-22 23:46:25.555316: step: 352/529, loss: 0.09131982922554016
2023-01-22 23:46:26.680447: step: 356/529, loss: 2.005427122116089
2023-01-22 23:46:27.824868: step: 360/529, loss: 0.2461986541748047
2023-01-22 23:46:28.960606: step: 364/529, loss: 0.14637012779712677
2023-01-22 23:46:30.063230: step: 368/529, loss: 0.48065081238746643
2023-01-22 23:46:31.188529: step: 372/529, loss: 0.2120942622423172
2023-01-22 23:46:32.290937: step: 376/529, loss: 0.0920385867357254
2023-01-22 23:46:33.378630: step: 380/529, loss: 0.7578844428062439
2023-01-22 23:46:34.517087: step: 384/529, loss: 1.5524718761444092
2023-01-22 23:46:35.637119: step: 388/529, loss: 0.08506367355585098
2023-01-22 23:46:36.745551: step: 392/529, loss: 0.2760906517505646
2023-01-22 23:46:37.854833: step: 396/529, loss: 0.10079348087310791
2023-01-22 23:46:38.947169: step: 400/529, loss: 0.15668383240699768
2023-01-22 23:46:40.090055: step: 404/529, loss: 0.13622145354747772
2023-01-22 23:46:41.202562: step: 408/529, loss: 0.10001173615455627
2023-01-22 23:46:42.309757: step: 412/529, loss: 0.13937222957611084
2023-01-22 23:46:43.435412: step: 416/529, loss: 0.12169227749109268
2023-01-22 23:46:44.559710: step: 420/529, loss: 0.13117718696594238
2023-01-22 23:46:45.688196: step: 424/529, loss: 0.053714849054813385
2023-01-22 23:46:46.794811: step: 428/529, loss: 0.11165256798267365
2023-01-22 23:46:47.902174: step: 432/529, loss: 0.4186984896659851
2023-01-22 23:46:49.004351: step: 436/529, loss: 0.18234197795391083
2023-01-22 23:46:50.128862: step: 440/529, loss: 0.16542989015579224
2023-01-22 23:46:51.234197: step: 444/529, loss: 0.20645684003829956
2023-01-22 23:46:52.354143: step: 448/529, loss: 0.8766270875930786
2023-01-22 23:46:53.466022: step: 452/529, loss: 0.6662218570709229
2023-01-22 23:46:54.567646: step: 456/529, loss: 1.0815006494522095
2023-01-22 23:46:55.679472: step: 460/529, loss: 0.16531048715114594
2023-01-22 23:46:56.790342: step: 464/529, loss: 0.8627262115478516
2023-01-22 23:46:57.911680: step: 468/529, loss: 0.31351956725120544
2023-01-22 23:46:59.011450: step: 472/529, loss: 0.21563774347305298
2023-01-22 23:47:00.162652: step: 476/529, loss: 0.2534770369529724
2023-01-22 23:47:01.257290: step: 480/529, loss: 0.3346182703971863
2023-01-22 23:47:02.362345: step: 484/529, loss: 0.1588408499956131
2023-01-22 23:47:03.449328: step: 488/529, loss: 0.8445334434509277
2023-01-22 23:47:04.534962: step: 492/529, loss: 0.09498071670532227
2023-01-22 23:47:05.631486: step: 496/529, loss: 0.4935251474380493
2023-01-22 23:47:06.743006: step: 500/529, loss: 0.12832719087600708
2023-01-22 23:47:07.861927: step: 504/529, loss: 0.7315385341644287
2023-01-22 23:47:08.986418: step: 508/529, loss: 0.5774371027946472
2023-01-22 23:47:10.104035: step: 512/529, loss: 0.7118686437606812
2023-01-22 23:47:11.244041: step: 516/529, loss: 0.03820633888244629
2023-01-22 23:47:12.357320: step: 520/529, loss: 0.34821614623069763
2023-01-22 23:47:13.477234: step: 524/529, loss: 0.16866126656532288
2023-01-22 23:47:14.592626: step: 528/529, loss: 0.19749489426612854
2023-01-22 23:47:15.704428: step: 532/529, loss: 0.4907470643520355
2023-01-22 23:47:16.815550: step: 536/529, loss: 1.2128127813339233
2023-01-22 23:47:17.921899: step: 540/529, loss: 0.7097907662391663
2023-01-22 23:47:19.048103: step: 544/529, loss: 0.08406487107276917
2023-01-22 23:47:20.161592: step: 548/529, loss: 0.27390700578689575
2023-01-22 23:47:21.260526: step: 552/529, loss: 0.0980248898267746
2023-01-22 23:47:22.412240: step: 556/529, loss: 0.2770588994026184
2023-01-22 23:47:23.574014: step: 560/529, loss: 0.676925003528595
2023-01-22 23:47:24.690750: step: 564/529, loss: 0.2937759757041931
2023-01-22 23:47:25.782634: step: 568/529, loss: 0.7336345314979553
2023-01-22 23:47:26.936703: step: 572/529, loss: 0.0925624817609787
2023-01-22 23:47:28.056559: step: 576/529, loss: 1.334926724433899
2023-01-22 23:47:29.172176: step: 580/529, loss: 0.03041706047952175
2023-01-22 23:47:30.261810: step: 584/529, loss: 6.906869888305664
2023-01-22 23:47:31.375869: step: 588/529, loss: 0.19706524908542633
2023-01-22 23:47:32.491210: step: 592/529, loss: 0.8816401958465576
2023-01-22 23:47:33.590105: step: 596/529, loss: 0.036309242248535156
2023-01-22 23:47:34.697829: step: 600/529, loss: 0.278812974691391
2023-01-22 23:47:35.809987: step: 604/529, loss: 0.8872995376586914
2023-01-22 23:47:36.928901: step: 608/529, loss: 1.1183286905288696
2023-01-22 23:47:38.027826: step: 612/529, loss: 0.789084255695343
2023-01-22 23:47:39.132937: step: 616/529, loss: 0.09627886116504669
2023-01-22 23:47:40.231202: step: 620/529, loss: 0.16537365317344666
2023-01-22 23:47:41.327808: step: 624/529, loss: 0.37847715616226196
2023-01-22 23:47:42.423464: step: 628/529, loss: 0.37421226501464844
2023-01-22 23:47:43.541958: step: 632/529, loss: 0.31230393052101135
2023-01-22 23:47:44.644738: step: 636/529, loss: 2.34479022026062
2023-01-22 23:47:45.745423: step: 640/529, loss: 6.490022659301758
2023-01-22 23:47:46.865270: step: 644/529, loss: 2.0917792320251465
2023-01-22 23:47:47.949922: step: 648/529, loss: 0.05058545991778374
2023-01-22 23:47:49.059291: step: 652/529, loss: 1.8338184356689453
2023-01-22 23:47:50.217615: step: 656/529, loss: 0.16708441078662872
2023-01-22 23:47:51.356658: step: 660/529, loss: 0.4179391860961914
2023-01-22 23:47:52.473387: step: 664/529, loss: 0.1016329824924469
2023-01-22 23:47:53.606870: step: 668/529, loss: 1.067753553390503
2023-01-22 23:47:54.736165: step: 672/529, loss: 0.14349260926246643
2023-01-22 23:47:55.839945: step: 676/529, loss: 0.0998539924621582
2023-01-22 23:47:56.919930: step: 680/529, loss: 0.18899011611938477
2023-01-22 23:47:58.048863: step: 684/529, loss: 0.1560390591621399
2023-01-22 23:47:59.163363: step: 688/529, loss: 0.7194616794586182
2023-01-22 23:48:00.261721: step: 692/529, loss: 0.7706704139709473
2023-01-22 23:48:01.367861: step: 696/529, loss: 0.19845056533813477
2023-01-22 23:48:02.488642: step: 700/529, loss: 0.8047633171081543
2023-01-22 23:48:03.605967: step: 704/529, loss: 0.6636126041412354
2023-01-22 23:48:04.697329: step: 708/529, loss: 1.625649094581604
2023-01-22 23:48:05.798592: step: 712/529, loss: 0.15570569038391113
2023-01-22 23:48:06.898847: step: 716/529, loss: 0.24859140813350677
2023-01-22 23:48:08.012431: step: 720/529, loss: 0.20342475175857544
2023-01-22 23:48:09.112655: step: 724/529, loss: 0.1019449234008789
2023-01-22 23:48:10.228480: step: 728/529, loss: 0.2307766079902649
2023-01-22 23:48:11.336875: step: 732/529, loss: 0.2157575637102127
2023-01-22 23:48:12.448556: step: 736/529, loss: 0.15788784623146057
2023-01-22 23:48:13.559026: step: 740/529, loss: 6.91624641418457
2023-01-22 23:48:14.658236: step: 744/529, loss: 0.11491823196411133
2023-01-22 23:48:15.786241: step: 748/529, loss: 0.14090195298194885
2023-01-22 23:48:16.884644: step: 752/529, loss: 0.5507321357727051
2023-01-22 23:48:18.010833: step: 756/529, loss: 1.4055075645446777
2023-01-22 23:48:19.103110: step: 760/529, loss: 0.9117105603218079
2023-01-22 23:48:20.201816: step: 764/529, loss: 0.4151371121406555
2023-01-22 23:48:21.320579: step: 768/529, loss: 0.15255776047706604
2023-01-22 23:48:22.426153: step: 772/529, loss: 0.18844282627105713
2023-01-22 23:48:23.545778: step: 776/529, loss: 2.801220417022705
2023-01-22 23:48:24.632619: step: 780/529, loss: 0.26680856943130493
2023-01-22 23:48:25.725573: step: 784/529, loss: 0.9256723523139954
2023-01-22 23:48:26.841264: step: 788/529, loss: 0.830964207649231
2023-01-22 23:48:27.945642: step: 792/529, loss: 0.06066305935382843
2023-01-22 23:48:29.063950: step: 796/529, loss: 0.09732022881507874
2023-01-22 23:48:30.165456: step: 800/529, loss: 0.1584729254245758
2023-01-22 23:48:31.282203: step: 804/529, loss: 0.7567061185836792
2023-01-22 23:48:32.411097: step: 808/529, loss: 0.06499285995960236
2023-01-22 23:48:33.516119: step: 812/529, loss: 0.11879683285951614
2023-01-22 23:48:34.611695: step: 816/529, loss: 0.09615898132324219
2023-01-22 23:48:35.720002: step: 820/529, loss: 0.7568000555038452
2023-01-22 23:48:36.802106: step: 824/529, loss: 0.49963921308517456
2023-01-22 23:48:37.893638: step: 828/529, loss: 0.40783947706222534
2023-01-22 23:48:39.024503: step: 832/529, loss: 0.9488718509674072
2023-01-22 23:48:40.129244: step: 836/529, loss: 0.2055523842573166
2023-01-22 23:48:41.222793: step: 840/529, loss: 0.732813835144043
2023-01-22 23:48:42.384188: step: 844/529, loss: 1.3017147779464722
2023-01-22 23:48:43.495577: step: 848/529, loss: 0.2309926152229309
2023-01-22 23:48:44.581257: step: 852/529, loss: 0.0938730239868164
2023-01-22 23:48:45.676825: step: 856/529, loss: 0.19092193245887756
2023-01-22 23:48:46.780478: step: 860/529, loss: 0.09991435706615448
2023-01-22 23:48:47.889442: step: 864/529, loss: 0.742562472820282
2023-01-22 23:48:49.016715: step: 868/529, loss: 0.07854809612035751
2023-01-22 23:48:50.137791: step: 872/529, loss: 0.7029688954353333
2023-01-22 23:48:51.245685: step: 876/529, loss: 1.4036539793014526
2023-01-22 23:48:52.365621: step: 880/529, loss: 0.350328266620636
2023-01-22 23:48:53.486581: step: 884/529, loss: 0.04996442794799805
2023-01-22 23:48:54.609747: step: 888/529, loss: 8.201461791992188
2023-01-22 23:48:55.739006: step: 892/529, loss: 0.0975864976644516
2023-01-22 23:48:56.853503: step: 896/529, loss: 0.12895183265209198
2023-01-22 23:48:57.935748: step: 900/529, loss: 0.34391850233078003
2023-01-22 23:48:59.050273: step: 904/529, loss: 0.10912913829088211
2023-01-22 23:49:00.128103: step: 908/529, loss: 0.23584072291851044
2023-01-22 23:49:01.242715: step: 912/529, loss: 1.426085114479065
2023-01-22 23:49:02.355685: step: 916/529, loss: 0.5282402038574219
2023-01-22 23:49:03.462848: step: 920/529, loss: 0.17803211510181427
2023-01-22 23:49:04.565282: step: 924/529, loss: 1.6859261989593506
2023-01-22 23:49:05.673276: step: 928/529, loss: 0.727862536907196
2023-01-22 23:49:06.821750: step: 932/529, loss: 0.09496030956506729
2023-01-22 23:49:07.928334: step: 936/529, loss: 0.9600954055786133
2023-01-22 23:49:09.040157: step: 940/529, loss: 0.15700650215148926
2023-01-22 23:49:10.149895: step: 944/529, loss: 0.2523081600666046
2023-01-22 23:49:11.259647: step: 948/529, loss: 0.06626439094543457
2023-01-22 23:49:12.366300: step: 952/529, loss: 0.5524584054946899
2023-01-22 23:49:13.482435: step: 956/529, loss: 0.16383175551891327
2023-01-22 23:49:14.591910: step: 960/529, loss: 0.3369196653366089
2023-01-22 23:49:15.725111: step: 964/529, loss: 0.05577874183654785
2023-01-22 23:49:16.825419: step: 968/529, loss: 0.21209755539894104
2023-01-22 23:49:17.907304: step: 972/529, loss: 0.21974115073680878
2023-01-22 23:49:19.032674: step: 976/529, loss: 0.6180623173713684
2023-01-22 23:49:20.154924: step: 980/529, loss: 0.07699732482433319
2023-01-22 23:49:21.260125: step: 984/529, loss: 0.13494902849197388
2023-01-22 23:49:22.407381: step: 988/529, loss: 0.08483333885669708
2023-01-22 23:49:23.498100: step: 992/529, loss: 0.16446347534656525
2023-01-22 23:49:24.608122: step: 996/529, loss: 0.4612805247306824
2023-01-22 23:49:25.733467: step: 1000/529, loss: 0.6165770292282104
2023-01-22 23:49:26.831291: step: 1004/529, loss: 0.9742149710655212
2023-01-22 23:49:27.934869: step: 1008/529, loss: 0.20880833268165588
2023-01-22 23:49:29.043662: step: 1012/529, loss: 0.4361006021499634
2023-01-22 23:49:30.161408: step: 1016/529, loss: 0.3200344741344452
2023-01-22 23:49:31.258324: step: 1020/529, loss: 0.6977413892745972
2023-01-22 23:49:32.362014: step: 1024/529, loss: 0.5455732941627502
2023-01-22 23:49:33.496680: step: 1028/529, loss: 0.9375991821289062
2023-01-22 23:49:34.591833: step: 1032/529, loss: 0.16531938314437866
2023-01-22 23:49:35.700989: step: 1036/529, loss: 0.5652868747711182
2023-01-22 23:49:36.782318: step: 1040/529, loss: 0.8211908936500549
2023-01-22 23:49:37.880876: step: 1044/529, loss: 0.756533682346344
2023-01-22 23:49:38.995889: step: 1048/529, loss: 0.8813340067863464
2023-01-22 23:49:40.132660: step: 1052/529, loss: 0.7167045474052429
2023-01-22 23:49:41.246082: step: 1056/529, loss: 0.20362785458564758
2023-01-22 23:49:42.363547: step: 1060/529, loss: 0.1289883702993393
2023-01-22 23:49:43.463748: step: 1064/529, loss: 1.2439157962799072
2023-01-22 23:49:44.564493: step: 1068/529, loss: 1.7101339101791382
2023-01-22 23:49:45.668995: step: 1072/529, loss: 0.06328277289867401
2023-01-22 23:49:46.764852: step: 1076/529, loss: 0.4203033745288849
2023-01-22 23:49:47.882275: step: 1080/529, loss: 0.6678031086921692
2023-01-22 23:49:49.016088: step: 1084/529, loss: 0.9080505967140198
2023-01-22 23:49:50.115904: step: 1088/529, loss: 0.08743324130773544
2023-01-22 23:49:51.240229: step: 1092/529, loss: 0.2029522955417633
2023-01-22 23:49:52.409687: step: 1096/529, loss: 1.1038970947265625
2023-01-22 23:49:53.496302: step: 1100/529, loss: 0.45893487334251404
2023-01-22 23:49:54.606724: step: 1104/529, loss: 0.3377528190612793
2023-01-22 23:49:55.730756: step: 1108/529, loss: 1.651160717010498
2023-01-22 23:49:56.809703: step: 1112/529, loss: 0.13979625701904297
2023-01-22 23:49:57.920066: step: 1116/529, loss: 0.23218198120594025
2023-01-22 23:49:59.021425: step: 1120/529, loss: 1.791353464126587
2023-01-22 23:50:00.143552: step: 1124/529, loss: 0.17537803947925568
2023-01-22 23:50:01.259476: step: 1128/529, loss: 0.5524899959564209
2023-01-22 23:50:02.372005: step: 1132/529, loss: 0.12660765647888184
2023-01-22 23:50:03.492316: step: 1136/529, loss: 0.16297034919261932
2023-01-22 23:50:04.573852: step: 1140/529, loss: 0.8825723528862
2023-01-22 23:50:05.697852: step: 1144/529, loss: 0.10069847106933594
2023-01-22 23:50:06.826343: step: 1148/529, loss: 0.7003568410873413
2023-01-22 23:50:07.968975: step: 1152/529, loss: 0.18493251502513885
2023-01-22 23:50:09.092943: step: 1156/529, loss: 0.8470341563224792
2023-01-22 23:50:10.186948: step: 1160/529, loss: 0.27277079224586487
2023-01-22 23:50:11.309839: step: 1164/529, loss: 0.059940434992313385
2023-01-22 23:50:12.416948: step: 1168/529, loss: 0.2493133544921875
2023-01-22 23:50:13.511888: step: 1172/529, loss: 0.3488086760044098
2023-01-22 23:50:14.633952: step: 1176/529, loss: 0.15316271781921387
2023-01-22 23:50:15.758294: step: 1180/529, loss: 0.5007015466690063
2023-01-22 23:50:16.866266: step: 1184/529, loss: 0.2625235617160797
2023-01-22 23:50:17.974584: step: 1188/529, loss: 1.4159905910491943
2023-01-22 23:50:19.104428: step: 1192/529, loss: 0.06470618396997452
2023-01-22 23:50:20.230011: step: 1196/529, loss: 0.9081791043281555
2023-01-22 23:50:21.341052: step: 1200/529, loss: 0.7985243797302246
2023-01-22 23:50:22.464023: step: 1204/529, loss: 0.5703268051147461
2023-01-22 23:50:23.555156: step: 1208/529, loss: 0.06196432188153267
2023-01-22 23:50:24.637122: step: 1212/529, loss: 0.996475338935852
2023-01-22 23:50:25.750670: step: 1216/529, loss: 0.07075901329517365
2023-01-22 23:50:26.836087: step: 1220/529, loss: 0.2182464599609375
2023-01-22 23:50:27.953430: step: 1224/529, loss: 0.11064356565475464
2023-01-22 23:50:29.048939: step: 1228/529, loss: 0.1474200338125229
2023-01-22 23:50:30.153409: step: 1232/529, loss: 0.5438947677612305
2023-01-22 23:50:31.303645: step: 1236/529, loss: 0.08816280961036682
2023-01-22 23:50:32.408399: step: 1240/529, loss: 0.3141501545906067
2023-01-22 23:50:33.549664: step: 1244/529, loss: 1.2704408168792725
2023-01-22 23:50:34.674206: step: 1248/529, loss: 0.7938334941864014
2023-01-22 23:50:35.804709: step: 1252/529, loss: 0.13236045837402344
2023-01-22 23:50:36.955433: step: 1256/529, loss: 0.41035032272338867
2023-01-22 23:50:38.052038: step: 1260/529, loss: 0.30850380659103394
2023-01-22 23:50:39.170629: step: 1264/529, loss: 0.22101956605911255
2023-01-22 23:50:40.305252: step: 1268/529, loss: 0.7396289706230164
2023-01-22 23:50:41.379031: step: 1272/529, loss: 0.8715603947639465
2023-01-22 23:50:42.468858: step: 1276/529, loss: 0.16690178215503693
2023-01-22 23:50:43.551843: step: 1280/529, loss: 0.2530982196331024
2023-01-22 23:50:44.722893: step: 1284/529, loss: 0.5470666885375977
2023-01-22 23:50:45.827723: step: 1288/529, loss: 0.17506083846092224
2023-01-22 23:50:46.930341: step: 1292/529, loss: 1.537326693534851
2023-01-22 23:50:48.067220: step: 1296/529, loss: 0.27675867080688477
2023-01-22 23:50:49.176854: step: 1300/529, loss: 0.43148624897003174
2023-01-22 23:50:50.310258: step: 1304/529, loss: 0.794842541217804
2023-01-22 23:50:51.446561: step: 1308/529, loss: 0.6822460889816284
2023-01-22 23:50:52.547349: step: 1312/529, loss: 0.3071845769882202
2023-01-22 23:50:53.665179: step: 1316/529, loss: 0.1444409340620041
2023-01-22 23:50:54.780761: step: 1320/529, loss: 0.6636388897895813
2023-01-22 23:50:55.882328: step: 1324/529, loss: 0.44452428817749023
2023-01-22 23:50:56.986726: step: 1328/529, loss: 0.11891746520996094
2023-01-22 23:50:58.101485: step: 1332/529, loss: 0.4584599733352661
2023-01-22 23:50:59.197051: step: 1336/529, loss: 0.3394605815410614
2023-01-22 23:51:00.355668: step: 1340/529, loss: 0.5514322519302368
2023-01-22 23:51:01.476423: step: 1344/529, loss: 0.4926857650279999
2023-01-22 23:51:02.608666: step: 1348/529, loss: 0.8418720364570618
2023-01-22 23:51:03.738154: step: 1352/529, loss: 0.16090410947799683
2023-01-22 23:51:04.832767: step: 1356/529, loss: 0.09347229450941086
2023-01-22 23:51:05.903453: step: 1360/529, loss: 0.7828988432884216
2023-01-22 23:51:07.040436: step: 1364/529, loss: 0.39452803134918213
2023-01-22 23:51:08.145273: step: 1368/529, loss: 0.15116086602210999
2023-01-22 23:51:09.250416: step: 1372/529, loss: 0.31756696105003357
2023-01-22 23:51:10.357620: step: 1376/529, loss: 0.24744626879692078
2023-01-22 23:51:11.494699: step: 1380/529, loss: 0.1375924050807953
2023-01-22 23:51:12.623907: step: 1384/529, loss: 0.18175840377807617
2023-01-22 23:51:13.714988: step: 1388/529, loss: 0.3222396969795227
2023-01-22 23:51:14.802824: step: 1392/529, loss: 0.10834214836359024
2023-01-22 23:51:15.879541: step: 1396/529, loss: 0.13487406075000763
2023-01-22 23:51:16.984793: step: 1400/529, loss: 0.6108031868934631
2023-01-22 23:51:18.098291: step: 1404/529, loss: 4.350836277008057
2023-01-22 23:51:19.249145: step: 1408/529, loss: 0.1640222668647766
2023-01-22 23:51:20.331720: step: 1412/529, loss: 0.1067267432808876
2023-01-22 23:51:21.424067: step: 1416/529, loss: 0.1348743438720703
2023-01-22 23:51:22.519224: step: 1420/529, loss: 0.4730883538722992
2023-01-22 23:51:23.624922: step: 1424/529, loss: 0.24327431619167328
2023-01-22 23:51:24.784289: step: 1428/529, loss: 0.22100697457790375
2023-01-22 23:51:25.882857: step: 1432/529, loss: 0.6290817856788635
2023-01-22 23:51:26.978518: step: 1436/529, loss: 0.30470961332321167
2023-01-22 23:51:28.084529: step: 1440/529, loss: 0.12193021178245544
2023-01-22 23:51:29.204123: step: 1444/529, loss: 0.1623374968767166
2023-01-22 23:51:30.317444: step: 1448/529, loss: 0.14038699865341187
2023-01-22 23:51:31.417254: step: 1452/529, loss: 0.9382328987121582
2023-01-22 23:51:32.531632: step: 1456/529, loss: 0.43177807331085205
2023-01-22 23:51:33.654354: step: 1460/529, loss: 0.4245401620864868
2023-01-22 23:51:34.796932: step: 1464/529, loss: 0.8357953429222107
2023-01-22 23:51:35.907426: step: 1468/529, loss: 0.7871928811073303
2023-01-22 23:51:37.016861: step: 1472/529, loss: 0.9252025485038757
2023-01-22 23:51:38.132393: step: 1476/529, loss: 0.15233880281448364
2023-01-22 23:51:39.233711: step: 1480/529, loss: 0.05792422592639923
2023-01-22 23:51:40.334726: step: 1484/529, loss: 1.088201880455017
2023-01-22 23:51:41.439514: step: 1488/529, loss: 0.106000617146492
2023-01-22 23:51:42.559271: step: 1492/529, loss: 0.06665768474340439
2023-01-22 23:51:43.654132: step: 1496/529, loss: 0.05442757532000542
2023-01-22 23:51:44.773004: step: 1500/529, loss: 0.23096761107444763
2023-01-22 23:51:45.899781: step: 1504/529, loss: 0.9938667416572571
2023-01-22 23:51:47.015287: step: 1508/529, loss: 0.5638448596000671
2023-01-22 23:51:48.139363: step: 1512/529, loss: 0.1069970577955246
2023-01-22 23:51:49.298526: step: 1516/529, loss: 0.16256123781204224
2023-01-22 23:51:50.411398: step: 1520/529, loss: 0.14033308625221252
2023-01-22 23:51:51.515364: step: 1524/529, loss: 0.7638886570930481
2023-01-22 23:51:52.615186: step: 1528/529, loss: 0.32965677976608276
2023-01-22 23:51:53.708815: step: 1532/529, loss: 0.2397201508283615
2023-01-22 23:51:54.844254: step: 1536/529, loss: 0.7115920782089233
2023-01-22 23:51:55.970355: step: 1540/529, loss: 0.20499220490455627
2023-01-22 23:51:57.055369: step: 1544/529, loss: 0.3668995797634125
2023-01-22 23:51:58.180610: step: 1548/529, loss: 0.1908825933933258
2023-01-22 23:51:59.272717: step: 1552/529, loss: 0.1789708137512207
2023-01-22 23:52:00.399502: step: 1556/529, loss: 0.11772161722183228
2023-01-22 23:52:01.506006: step: 1560/529, loss: 0.1586398184299469
2023-01-22 23:52:02.593166: step: 1564/529, loss: 0.256094366312027
2023-01-22 23:52:03.692867: step: 1568/529, loss: 0.48130911588668823
2023-01-22 23:52:04.805840: step: 1572/529, loss: 0.16873493790626526
2023-01-22 23:52:05.924038: step: 1576/529, loss: 0.0388309508562088
2023-01-22 23:52:07.038501: step: 1580/529, loss: 0.2380487024784088
2023-01-22 23:52:08.151214: step: 1584/529, loss: 0.2640243172645569
2023-01-22 23:52:09.273081: step: 1588/529, loss: 0.12211154401302338
2023-01-22 23:52:10.384814: step: 1592/529, loss: 0.10584276169538498
2023-01-22 23:52:11.506904: step: 1596/529, loss: 0.144094318151474
2023-01-22 23:52:12.630834: step: 1600/529, loss: 0.14474931359291077
2023-01-22 23:52:13.736056: step: 1604/529, loss: 1.1855412721633911
2023-01-22 23:52:14.855181: step: 1608/529, loss: 0.2967948913574219
2023-01-22 23:52:15.968541: step: 1612/529, loss: 0.20573052763938904
2023-01-22 23:52:17.083664: step: 1616/529, loss: 0.22052517533302307
2023-01-22 23:52:18.190393: step: 1620/529, loss: 0.31615716218948364
2023-01-22 23:52:19.301019: step: 1624/529, loss: 1.3725531101226807
2023-01-22 23:52:20.422350: step: 1628/529, loss: 0.44345206022262573
2023-01-22 23:52:21.530802: step: 1632/529, loss: 0.043688204139471054
2023-01-22 23:52:22.660146: step: 1636/529, loss: 0.4386120140552521
2023-01-22 23:52:23.790951: step: 1640/529, loss: 0.11705875396728516
2023-01-22 23:52:24.905215: step: 1644/529, loss: 6.528853893280029
2023-01-22 23:52:26.019910: step: 1648/529, loss: 0.12868361175060272
2023-01-22 23:52:27.128466: step: 1652/529, loss: 0.13987331092357635
2023-01-22 23:52:28.257156: step: 1656/529, loss: 1.27565336227417
2023-01-22 23:52:29.352891: step: 1660/529, loss: 0.28140562772750854
2023-01-22 23:52:30.479234: step: 1664/529, loss: 0.07724638283252716
2023-01-22 23:52:31.590096: step: 1668/529, loss: 0.6375335454940796
2023-01-22 23:52:32.693381: step: 1672/529, loss: 0.10636444389820099
2023-01-22 23:52:33.813023: step: 1676/529, loss: 0.16035687923431396
2023-01-22 23:52:34.925828: step: 1680/529, loss: 0.2522631585597992
2023-01-22 23:52:36.031375: step: 1684/529, loss: 1.538737416267395
2023-01-22 23:52:37.135487: step: 1688/529, loss: 1.489425778388977
2023-01-22 23:52:38.216151: step: 1692/529, loss: 0.19276371598243713
2023-01-22 23:52:39.333628: step: 1696/529, loss: 0.21864581108093262
2023-01-22 23:52:40.469851: step: 1700/529, loss: 0.2302083969116211
2023-01-22 23:52:41.560716: step: 1704/529, loss: 0.08679866790771484
2023-01-22 23:52:42.631374: step: 1708/529, loss: 0.12485584616661072
2023-01-22 23:52:43.748834: step: 1712/529, loss: 6.14894962310791
2023-01-22 23:52:44.868482: step: 1716/529, loss: 0.794439435005188
2023-01-22 23:52:46.018650: step: 1720/529, loss: 0.7427870035171509
2023-01-22 23:52:47.119217: step: 1724/529, loss: 0.4588386118412018
2023-01-22 23:52:48.236414: step: 1728/529, loss: 0.2772024869918823
2023-01-22 23:52:49.338027: step: 1732/529, loss: 2.1954152584075928
2023-01-22 23:52:50.457497: step: 1736/529, loss: 0.9224813580513
2023-01-22 23:52:51.557940: step: 1740/529, loss: 0.222464457154274
2023-01-22 23:52:52.675363: step: 1744/529, loss: 0.2673835754394531
2023-01-22 23:52:53.808572: step: 1748/529, loss: 0.7512953281402588
2023-01-22 23:52:54.926470: step: 1752/529, loss: 0.36012017726898193
2023-01-22 23:52:56.034907: step: 1756/529, loss: 0.13930052518844604
2023-01-22 23:52:57.177481: step: 1760/529, loss: 0.8526419401168823
2023-01-22 23:52:58.285391: step: 1764/529, loss: 0.05703430250287056
2023-01-22 23:52:59.386624: step: 1768/529, loss: 0.21558809280395508
2023-01-22 23:53:00.522448: step: 1772/529, loss: 0.2808411717414856
2023-01-22 23:53:01.630410: step: 1776/529, loss: 0.3419952392578125
2023-01-22 23:53:02.736951: step: 1780/529, loss: 0.12058372795581818
2023-01-22 23:53:03.828623: step: 1784/529, loss: 0.058970026671886444
2023-01-22 23:53:04.943045: step: 1788/529, loss: 1.2495381832122803
2023-01-22 23:53:06.060953: step: 1792/529, loss: 2.34295654296875
2023-01-22 23:53:07.154517: step: 1796/529, loss: 0.255861759185791
2023-01-22 23:53:08.246147: step: 1800/529, loss: 0.022750426083803177
2023-01-22 23:53:09.371490: step: 1804/529, loss: 0.1370266079902649
2023-01-22 23:53:10.494363: step: 1808/529, loss: 0.1721268892288208
2023-01-22 23:53:11.584139: step: 1812/529, loss: 1.962512493133545
2023-01-22 23:53:12.690618: step: 1816/529, loss: 0.9100700616836548
2023-01-22 23:53:13.798334: step: 1820/529, loss: 0.5272812843322754
2023-01-22 23:53:14.945751: step: 1824/529, loss: 0.24549484252929688
2023-01-22 23:53:16.030033: step: 1828/529, loss: 0.2327841818332672
2023-01-22 23:53:17.151286: step: 1832/529, loss: 0.5335144400596619
2023-01-22 23:53:18.236756: step: 1836/529, loss: 1.3104196786880493
2023-01-22 23:53:19.357240: step: 1840/529, loss: 0.9715365767478943
2023-01-22 23:53:20.472305: step: 1844/529, loss: 0.5726670622825623
2023-01-22 23:53:21.593286: step: 1848/529, loss: 0.14137744903564453
2023-01-22 23:53:22.722591: step: 1852/529, loss: 6.426032066345215
2023-01-22 23:53:23.845271: step: 1856/529, loss: 0.2132217437028885
2023-01-22 23:53:24.949570: step: 1860/529, loss: 0.4421789348125458
2023-01-22 23:53:26.071262: step: 1864/529, loss: 0.21401147544384003
2023-01-22 23:53:27.203323: step: 1868/529, loss: 0.3631221652030945
2023-01-22 23:53:28.335447: step: 1872/529, loss: 1.142690658569336
2023-01-22 23:53:29.521487: step: 1876/529, loss: 0.1468295156955719
2023-01-22 23:53:30.657458: step: 1880/529, loss: 0.1995573192834854
2023-01-22 23:53:31.761734: step: 1884/529, loss: 0.13073283433914185
2023-01-22 23:53:32.867324: step: 1888/529, loss: 0.230586439371109
2023-01-22 23:53:33.966562: step: 1892/529, loss: 0.9619349241256714
2023-01-22 23:53:35.046284: step: 1896/529, loss: 0.11495314538478851
2023-01-22 23:53:36.161154: step: 1900/529, loss: 0.18295860290527344
2023-01-22 23:53:37.323875: step: 1904/529, loss: 0.25179794430732727
2023-01-22 23:53:38.432595: step: 1908/529, loss: 0.3422781229019165
2023-01-22 23:53:39.557481: step: 1912/529, loss: 0.09139509499073029
2023-01-22 23:53:40.628623: step: 1916/529, loss: 0.44558393955230713
2023-01-22 23:53:41.723896: step: 1920/529, loss: 0.7917593717575073
2023-01-22 23:53:42.844366: step: 1924/529, loss: 0.18368090689182281
2023-01-22 23:53:43.967366: step: 1928/529, loss: 0.717082142829895
2023-01-22 23:53:45.106115: step: 1932/529, loss: 0.8882566690444946
2023-01-22 23:53:46.218581: step: 1936/529, loss: 0.1455463469028473
2023-01-22 23:53:47.313643: step: 1940/529, loss: 0.039681900292634964
2023-01-22 23:53:48.424484: step: 1944/529, loss: 0.2294284701347351
2023-01-22 23:53:49.563800: step: 1948/529, loss: 0.13052520155906677
2023-01-22 23:53:50.676370: step: 1952/529, loss: 0.3179095387458801
2023-01-22 23:53:51.778321: step: 1956/529, loss: 0.10047879070043564
2023-01-22 23:53:52.918137: step: 1960/529, loss: 0.18036779761314392
2023-01-22 23:53:54.014419: step: 1964/529, loss: 0.07747345417737961
2023-01-22 23:53:55.132245: step: 1968/529, loss: 0.7979085445404053
2023-01-22 23:53:56.251571: step: 1972/529, loss: 0.2452598512172699
2023-01-22 23:53:57.338926: step: 1976/529, loss: 0.7543932199478149
2023-01-22 23:53:58.434193: step: 1980/529, loss: 0.12381067126989365
2023-01-22 23:53:59.532180: step: 1984/529, loss: 0.16027717292308807
2023-01-22 23:54:00.668340: step: 1988/529, loss: 0.13522708415985107
2023-01-22 23:54:01.759166: step: 1992/529, loss: 0.8572558164596558
2023-01-22 23:54:02.867948: step: 1996/529, loss: 0.6600879430770874
2023-01-22 23:54:03.955310: step: 2000/529, loss: 0.12676039338111877
2023-01-22 23:54:05.066250: step: 2004/529, loss: 0.84746915102005
2023-01-22 23:54:06.206051: step: 2008/529, loss: 0.07441587746143341
2023-01-22 23:54:07.309075: step: 2012/529, loss: 0.7854389548301697
2023-01-22 23:54:08.400523: step: 2016/529, loss: 1.5562529563903809
2023-01-22 23:54:09.494699: step: 2020/529, loss: 0.4920474588871002
2023-01-22 23:54:10.591438: step: 2024/529, loss: 0.40680745244026184
2023-01-22 23:54:11.692702: step: 2028/529, loss: 0.12970677018165588
2023-01-22 23:54:12.812056: step: 2032/529, loss: 0.9063763618469238
2023-01-22 23:54:13.908613: step: 2036/529, loss: 0.5326225757598877
2023-01-22 23:54:14.995539: step: 2040/529, loss: 0.12516899406909943
2023-01-22 23:54:16.103976: step: 2044/529, loss: 0.0875358134508133
2023-01-22 23:54:17.220667: step: 2048/529, loss: 1.0739879608154297
2023-01-22 23:54:18.317410: step: 2052/529, loss: 1.4095219373703003
2023-01-22 23:54:19.442645: step: 2056/529, loss: 0.22320863604545593
2023-01-22 23:54:20.551672: step: 2060/529, loss: 0.4662877023220062
2023-01-22 23:54:21.662201: step: 2064/529, loss: 0.4730173349380493
2023-01-22 23:54:22.760149: step: 2068/529, loss: 0.12959042191505432
2023-01-22 23:54:23.844098: step: 2072/529, loss: 1.5932559967041016
2023-01-22 23:54:24.966786: step: 2076/529, loss: 0.2425878494977951
2023-01-22 23:54:26.050930: step: 2080/529, loss: 0.13698916137218475
2023-01-22 23:54:27.164915: step: 2084/529, loss: 0.7115722894668579
2023-01-22 23:54:28.278069: step: 2088/529, loss: 0.14050406217575073
2023-01-22 23:54:29.437953: step: 2092/529, loss: 0.10151372104883194
2023-01-22 23:54:30.525830: step: 2096/529, loss: 0.7830831408500671
2023-01-22 23:54:31.649656: step: 2100/529, loss: 1.3276368379592896
2023-01-22 23:54:32.759731: step: 2104/529, loss: 0.1844952553510666
2023-01-22 23:54:33.883329: step: 2108/529, loss: 0.25663870573043823
2023-01-22 23:54:35.010855: step: 2112/529, loss: 0.23623895645141602
2023-01-22 23:54:36.132042: step: 2116/529, loss: 0.8579446077346802
==================================================
Loss: 0.574
--------------------
Dev: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7575757575757576, 'r': 0.3968253968253968, 'f1': 0.5208333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.6176470588235294, 'r': 0.5833333333333334, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7575757575757576, 'r': 0.3968253968253968, 'f1': 0.5208333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Russian: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Russian: {'event': {'p': 0.6176470588235294, 'r': 0.5833333333333334, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:55:39.533112: step: 4/529, loss: 0.11128297448158264
2023-01-22 23:55:40.624358: step: 8/529, loss: 0.13652391731739044
2023-01-22 23:55:41.720369: step: 12/529, loss: 0.18167619407176971
2023-01-22 23:55:42.823030: step: 16/529, loss: 0.12678176164627075
2023-01-22 23:55:43.971437: step: 20/529, loss: 0.29143857955932617
2023-01-22 23:55:45.073592: step: 24/529, loss: 0.12004499137401581
2023-01-22 23:55:46.193673: step: 28/529, loss: 0.07078561931848526
2023-01-22 23:55:47.290962: step: 32/529, loss: 0.17433582246303558
2023-01-22 23:55:48.414181: step: 36/529, loss: 0.37478169798851013
2023-01-22 23:55:49.503864: step: 40/529, loss: 0.1412227749824524
2023-01-22 23:55:50.617314: step: 44/529, loss: 0.1689353883266449
2023-01-22 23:55:51.725822: step: 48/529, loss: 0.12702178955078125
2023-01-22 23:55:52.837770: step: 52/529, loss: 0.12902812659740448
2023-01-22 23:55:53.960647: step: 56/529, loss: 0.18746919929981232
2023-01-22 23:55:55.075804: step: 60/529, loss: 0.13098326325416565
2023-01-22 23:55:56.174572: step: 64/529, loss: 0.7679271697998047
2023-01-22 23:55:57.264636: step: 68/529, loss: 0.2812924385070801
2023-01-22 23:55:58.400248: step: 72/529, loss: 0.04974498599767685
2023-01-22 23:55:59.496965: step: 76/529, loss: 0.16167688369750977
2023-01-22 23:56:00.603710: step: 80/529, loss: 0.3687445819377899
2023-01-22 23:56:01.705857: step: 84/529, loss: 0.2611977159976959
2023-01-22 23:56:02.818690: step: 88/529, loss: 0.754612922668457
2023-01-22 23:56:03.936126: step: 92/529, loss: 0.35346242785453796
2023-01-22 23:56:05.054770: step: 96/529, loss: 0.09254489094018936
2023-01-22 23:56:06.169867: step: 100/529, loss: 0.5874930024147034
2023-01-22 23:56:07.255238: step: 104/529, loss: 0.4549519419670105
2023-01-22 23:56:08.348669: step: 108/529, loss: 0.7409536242485046
2023-01-22 23:56:09.467742: step: 112/529, loss: 0.2267622947692871
2023-01-22 23:56:10.585177: step: 116/529, loss: 0.24147367477416992
2023-01-22 23:56:11.680070: step: 120/529, loss: 0.05178098380565643
2023-01-22 23:56:12.787656: step: 124/529, loss: 0.05651436001062393
2023-01-22 23:56:13.890405: step: 128/529, loss: 0.6378711462020874
2023-01-22 23:56:14.975940: step: 132/529, loss: 0.11588358879089355
2023-01-22 23:56:16.079815: step: 136/529, loss: 0.14608259499073029
2023-01-22 23:56:17.176685: step: 140/529, loss: 0.2938465178012848
2023-01-22 23:56:18.284765: step: 144/529, loss: 0.14757758378982544
2023-01-22 23:56:19.376133: step: 148/529, loss: 0.06289301067590714
2023-01-22 23:56:20.499229: step: 152/529, loss: 0.5249178409576416
2023-01-22 23:56:21.624513: step: 156/529, loss: 0.13243542611598969
2023-01-22 23:56:22.724436: step: 160/529, loss: 0.13089700043201447
2023-01-22 23:56:23.826316: step: 164/529, loss: 1.393819808959961
2023-01-22 23:56:24.947462: step: 168/529, loss: 0.5352674722671509
2023-01-22 23:56:26.065989: step: 172/529, loss: 1.7434730529785156
2023-01-22 23:56:27.166852: step: 176/529, loss: 0.33729565143585205
2023-01-22 23:56:28.309928: step: 180/529, loss: 0.13706666231155396
2023-01-22 23:56:29.413756: step: 184/529, loss: 0.12028179317712784
2023-01-22 23:56:30.538907: step: 188/529, loss: 0.3744351863861084
2023-01-22 23:56:31.672381: step: 192/529, loss: 0.6514228582382202
2023-01-22 23:56:32.789143: step: 196/529, loss: 0.14292487502098083
2023-01-22 23:56:33.891525: step: 200/529, loss: 0.1727512925863266
2023-01-22 23:56:35.024585: step: 204/529, loss: 0.8078638315200806
2023-01-22 23:56:36.115125: step: 208/529, loss: 0.07706775516271591
2023-01-22 23:56:37.211454: step: 212/529, loss: 0.14386291801929474
2023-01-22 23:56:38.296706: step: 216/529, loss: 0.11720123887062073
2023-01-22 23:56:39.423631: step: 220/529, loss: 0.12753859162330627
2023-01-22 23:56:40.523479: step: 224/529, loss: 0.6784946918487549
2023-01-22 23:56:41.618436: step: 228/529, loss: 0.36837512254714966
2023-01-22 23:56:42.724734: step: 232/529, loss: 0.2314557135105133
2023-01-22 23:56:43.866562: step: 236/529, loss: 0.6996122598648071
2023-01-22 23:56:44.982171: step: 240/529, loss: 0.12325844168663025
2023-01-22 23:56:46.077392: step: 244/529, loss: 0.1912892758846283
2023-01-22 23:56:47.163553: step: 248/529, loss: 0.155488058924675
2023-01-22 23:56:48.279467: step: 252/529, loss: 0.2988097071647644
2023-01-22 23:56:49.399984: step: 256/529, loss: 0.2391349822282791
2023-01-22 23:56:50.543601: step: 260/529, loss: 0.21240109205245972
2023-01-22 23:56:51.657810: step: 264/529, loss: 0.14369621872901917
2023-01-22 23:56:52.780926: step: 268/529, loss: 0.073394775390625
2023-01-22 23:56:53.876463: step: 272/529, loss: 0.7761455178260803
2023-01-22 23:56:55.061657: step: 276/529, loss: 0.17235898971557617
2023-01-22 23:56:56.141896: step: 280/529, loss: 0.05230455473065376
2023-01-22 23:56:57.283373: step: 284/529, loss: 0.5639230608940125
2023-01-22 23:56:58.382351: step: 288/529, loss: 0.0593293160200119
2023-01-22 23:56:59.513021: step: 292/529, loss: 0.09990637749433517
2023-01-22 23:57:00.651445: step: 296/529, loss: 0.09749503433704376
2023-01-22 23:57:01.769169: step: 300/529, loss: 0.11232343316078186
2023-01-22 23:57:02.865604: step: 304/529, loss: 0.25702133774757385
2023-01-22 23:57:03.999424: step: 308/529, loss: 0.7633522152900696
2023-01-22 23:57:05.103461: step: 312/529, loss: 0.09290137141942978
2023-01-22 23:57:06.269767: step: 316/529, loss: 0.12361364811658859
2023-01-22 23:57:07.393384: step: 320/529, loss: 0.3535715639591217
2023-01-22 23:57:08.503476: step: 324/529, loss: 0.08157294243574142
2023-01-22 23:57:09.628758: step: 328/529, loss: 0.2751094400882721
2023-01-22 23:57:10.742570: step: 332/529, loss: 0.3667985200881958
2023-01-22 23:57:11.863859: step: 336/529, loss: 0.17447009682655334
2023-01-22 23:57:12.977662: step: 340/529, loss: 0.4401130676269531
2023-01-22 23:57:14.108891: step: 344/529, loss: 0.3819130063056946
2023-01-22 23:57:15.234346: step: 348/529, loss: 0.28337109088897705
2023-01-22 23:57:16.370585: step: 352/529, loss: 0.7851705551147461
2023-01-22 23:57:17.498310: step: 356/529, loss: 0.3282890319824219
2023-01-22 23:57:18.622373: step: 360/529, loss: 0.29331180453300476
2023-01-22 23:57:19.741878: step: 364/529, loss: 1.098751187324524
2023-01-22 23:57:20.827848: step: 368/529, loss: 0.7009627819061279
2023-01-22 23:57:21.925211: step: 372/529, loss: 0.02841215208172798
2023-01-22 23:57:23.036187: step: 376/529, loss: 0.21262173354625702
2023-01-22 23:57:24.154064: step: 380/529, loss: 0.1965780258178711
2023-01-22 23:57:25.263749: step: 384/529, loss: 0.6844325065612793
2023-01-22 23:57:26.395209: step: 388/529, loss: 0.2385258674621582
2023-01-22 23:57:27.510718: step: 392/529, loss: 0.03980207443237305
2023-01-22 23:57:28.611272: step: 396/529, loss: 0.859296441078186
2023-01-22 23:57:29.711163: step: 400/529, loss: 0.1316230744123459
2023-01-22 23:57:30.832035: step: 404/529, loss: 0.135273739695549
2023-01-22 23:57:31.955273: step: 408/529, loss: 1.2298753261566162
2023-01-22 23:57:33.063824: step: 412/529, loss: 0.25858479738235474
2023-01-22 23:57:34.175769: step: 416/529, loss: 0.05019988864660263
2023-01-22 23:57:35.291748: step: 420/529, loss: 0.8769996762275696
2023-01-22 23:57:36.388590: step: 424/529, loss: 0.1840103268623352
2023-01-22 23:57:37.527314: step: 428/529, loss: 1.0613447427749634
2023-01-22 23:57:38.640044: step: 432/529, loss: 0.09065236896276474
2023-01-22 23:57:39.765765: step: 436/529, loss: 0.12538452446460724
2023-01-22 23:57:40.873975: step: 440/529, loss: 0.22005310654640198
2023-01-22 23:57:41.985292: step: 444/529, loss: 0.1148044615983963
2023-01-22 23:57:43.115552: step: 448/529, loss: 0.07437839359045029
2023-01-22 23:57:44.193542: step: 452/529, loss: 0.06118325889110565
2023-01-22 23:57:45.307826: step: 456/529, loss: 0.13268804550170898
2023-01-22 23:57:46.427370: step: 460/529, loss: 0.34643229842185974
2023-01-22 23:57:47.557666: step: 464/529, loss: 0.3244630992412567
2023-01-22 23:57:48.668442: step: 468/529, loss: 0.30398598313331604
2023-01-22 23:57:49.817914: step: 472/529, loss: 0.22082296013832092
2023-01-22 23:57:50.943785: step: 476/529, loss: 0.1869596391916275
2023-01-22 23:57:52.051027: step: 480/529, loss: 0.5201295614242554
2023-01-22 23:57:53.155711: step: 484/529, loss: 6.798293590545654
2023-01-22 23:57:54.264219: step: 488/529, loss: 0.12290272861719131
2023-01-22 23:57:55.354378: step: 492/529, loss: 0.10110712051391602
2023-01-22 23:57:56.441606: step: 496/529, loss: 0.32220375537872314
2023-01-22 23:57:57.539233: step: 500/529, loss: 0.7954610586166382
2023-01-22 23:57:58.630257: step: 504/529, loss: 0.8145643472671509
2023-01-22 23:57:59.733647: step: 508/529, loss: 0.2596490979194641
2023-01-22 23:58:00.861158: step: 512/529, loss: 0.09804592281579971
2023-01-22 23:58:01.985499: step: 516/529, loss: 0.68377685546875
2023-01-22 23:58:03.075784: step: 520/529, loss: 0.08331127464771271
2023-01-22 23:58:04.173807: step: 524/529, loss: 0.7304783463478088
2023-01-22 23:58:05.272613: step: 528/529, loss: 0.029674889519810677
2023-01-22 23:58:06.385655: step: 532/529, loss: 1.4471884965896606
2023-01-22 23:58:07.510363: step: 536/529, loss: 0.07054352760314941
2023-01-22 23:58:08.605037: step: 540/529, loss: 0.17877325415611267
2023-01-22 23:58:09.703165: step: 544/529, loss: 0.46924152970314026
2023-01-22 23:58:10.810067: step: 548/529, loss: 0.09788914024829865
2023-01-22 23:58:11.938737: step: 552/529, loss: 0.5880101323127747
2023-01-22 23:58:13.054480: step: 556/529, loss: 1.1348435878753662
2023-01-22 23:58:14.170603: step: 560/529, loss: 0.24176493287086487
2023-01-22 23:58:15.292959: step: 564/529, loss: 0.12000855803489685
2023-01-22 23:58:16.449837: step: 568/529, loss: 0.49378010630607605
2023-01-22 23:58:17.562705: step: 572/529, loss: 0.09984531998634338
2023-01-22 23:58:18.699479: step: 576/529, loss: 0.3143824636936188
2023-01-22 23:58:19.818833: step: 580/529, loss: 0.21825580298900604
2023-01-22 23:58:20.946126: step: 584/529, loss: 0.26523810625076294
2023-01-22 23:58:22.054751: step: 588/529, loss: 0.26183652877807617
2023-01-22 23:58:23.177197: step: 592/529, loss: 0.5874617099761963
2023-01-22 23:58:24.335865: step: 596/529, loss: 1.2181098461151123
2023-01-22 23:58:25.456973: step: 600/529, loss: 0.6602262258529663
2023-01-22 23:58:26.588952: step: 604/529, loss: 0.4645019471645355
2023-01-22 23:58:27.734801: step: 608/529, loss: 0.2207527458667755
2023-01-22 23:58:28.852710: step: 612/529, loss: 0.09679269790649414
2023-01-22 23:58:29.949732: step: 616/529, loss: 1.0556899309158325
2023-01-22 23:58:31.068422: step: 620/529, loss: 1.3556993007659912
2023-01-22 23:58:32.172471: step: 624/529, loss: 0.06871695816516876
2023-01-22 23:58:33.294764: step: 628/529, loss: 0.4564691483974457
2023-01-22 23:58:34.408837: step: 632/529, loss: 0.2663634419441223
2023-01-22 23:58:35.532129: step: 636/529, loss: 1.0426877737045288
2023-01-22 23:58:36.647866: step: 640/529, loss: 0.040747880935668945
2023-01-22 23:58:37.737126: step: 644/529, loss: 0.3934265375137329
2023-01-22 23:58:38.871808: step: 648/529, loss: 0.20571193099021912
2023-01-22 23:58:40.000401: step: 652/529, loss: 0.24363946914672852
2023-01-22 23:58:41.108199: step: 656/529, loss: 0.503278374671936
2023-01-22 23:58:42.217542: step: 660/529, loss: 0.07683592289686203
2023-01-22 23:58:43.329584: step: 664/529, loss: 0.22995014488697052
2023-01-22 23:58:44.429325: step: 668/529, loss: 0.1132812574505806
2023-01-22 23:58:45.564334: step: 672/529, loss: 0.29321157932281494
2023-01-22 23:58:46.682591: step: 676/529, loss: 6.404324054718018
2023-01-22 23:58:47.785651: step: 680/529, loss: 0.7435594797134399
2023-01-22 23:58:48.898811: step: 684/529, loss: 0.1779492348432541
2023-01-22 23:58:50.000188: step: 688/529, loss: 0.19195112586021423
2023-01-22 23:58:51.099778: step: 692/529, loss: 0.04702947288751602
2023-01-22 23:58:52.205100: step: 696/529, loss: 0.03895268589258194
2023-01-22 23:58:53.344584: step: 700/529, loss: 0.1714916229248047
2023-01-22 23:58:54.420507: step: 704/529, loss: 0.11572809517383575
2023-01-22 23:58:55.525239: step: 708/529, loss: 0.7540234923362732
2023-01-22 23:58:56.641496: step: 712/529, loss: 0.5779246091842651
2023-01-22 23:58:57.752361: step: 716/529, loss: 0.18387430906295776
2023-01-22 23:58:58.847541: step: 720/529, loss: 0.19179849326610565
2023-01-22 23:58:59.953568: step: 724/529, loss: 0.9198240041732788
2023-01-22 23:59:01.071467: step: 728/529, loss: 0.9045203924179077
2023-01-22 23:59:02.172466: step: 732/529, loss: 0.038695622235536575
2023-01-22 23:59:03.289193: step: 736/529, loss: 0.6395885944366455
2023-01-22 23:59:04.394628: step: 740/529, loss: 0.13464191555976868
2023-01-22 23:59:05.503886: step: 744/529, loss: 0.3594089448451996
2023-01-22 23:59:06.605882: step: 748/529, loss: 0.3688087463378906
2023-01-22 23:59:07.696492: step: 752/529, loss: 0.06678777188062668
2023-01-22 23:59:08.792211: step: 756/529, loss: 0.40065494179725647
2023-01-22 23:59:09.929021: step: 760/529, loss: 0.17610502243041992
2023-01-22 23:59:11.029069: step: 764/529, loss: 0.7588016390800476
2023-01-22 23:59:12.125888: step: 768/529, loss: 0.8652192950248718
2023-01-22 23:59:13.277428: step: 772/529, loss: 0.5788482427597046
2023-01-22 23:59:14.357655: step: 776/529, loss: 0.06973810493946075
2023-01-22 23:59:15.486642: step: 780/529, loss: 0.1131652370095253
2023-01-22 23:59:16.608747: step: 784/529, loss: 0.7334602475166321
2023-01-22 23:59:17.693075: step: 788/529, loss: 0.20820684731006622
2023-01-22 23:59:18.875870: step: 792/529, loss: 0.2806049585342407
2023-01-22 23:59:20.003045: step: 796/529, loss: 0.12473927438259125
2023-01-22 23:59:21.102143: step: 800/529, loss: 0.6042113304138184
2023-01-22 23:59:22.204022: step: 804/529, loss: 0.34010282158851624
2023-01-22 23:59:23.333060: step: 808/529, loss: 0.1561412364244461
2023-01-22 23:59:24.444953: step: 812/529, loss: 0.09789478778839111
2023-01-22 23:59:25.559298: step: 816/529, loss: 0.9361017942428589
2023-01-22 23:59:26.688519: step: 820/529, loss: 0.1968742311000824
2023-01-22 23:59:27.783386: step: 824/529, loss: 1.2033723592758179
2023-01-22 23:59:28.899005: step: 828/529, loss: 0.13836780190467834
2023-01-22 23:59:30.022945: step: 832/529, loss: 0.1800197809934616
2023-01-22 23:59:31.126783: step: 836/529, loss: 0.35231488943099976
2023-01-22 23:59:32.243037: step: 840/529, loss: 0.7589906454086304
2023-01-22 23:59:33.356883: step: 844/529, loss: 0.12929654121398926
2023-01-22 23:59:34.462754: step: 848/529, loss: 0.15113696455955505
2023-01-22 23:59:35.565894: step: 852/529, loss: 0.7858595252037048
2023-01-22 23:59:36.722798: step: 856/529, loss: 0.7015398740768433
2023-01-22 23:59:37.817540: step: 860/529, loss: 0.2875896394252777
2023-01-22 23:59:38.922924: step: 864/529, loss: 0.5598541498184204
2023-01-22 23:59:40.063164: step: 868/529, loss: 0.20690393447875977
2023-01-22 23:59:41.162315: step: 872/529, loss: 0.6398031711578369
2023-01-22 23:59:42.253220: step: 876/529, loss: 0.6948320269584656
2023-01-22 23:59:43.361610: step: 880/529, loss: 0.7434417009353638
2023-01-22 23:59:44.491039: step: 884/529, loss: 0.31769075989723206
2023-01-22 23:59:45.601111: step: 888/529, loss: 0.04603876918554306
2023-01-22 23:59:46.739820: step: 892/529, loss: 0.68703693151474
2023-01-22 23:59:47.833980: step: 896/529, loss: 1.257704496383667
2023-01-22 23:59:48.953793: step: 900/529, loss: 0.04991288483142853
2023-01-22 23:59:50.089509: step: 904/529, loss: 0.033030033111572266
2023-01-22 23:59:51.194264: step: 908/529, loss: 0.18021836876869202
2023-01-22 23:59:52.316127: step: 912/529, loss: 0.31129178404808044
2023-01-22 23:59:53.386629: step: 916/529, loss: 0.08821897953748703
2023-01-22 23:59:54.507271: step: 920/529, loss: 0.3284940719604492
2023-01-22 23:59:55.646296: step: 924/529, loss: 0.44003069400787354
2023-01-22 23:59:56.745004: step: 928/529, loss: 0.7072644233703613
2023-01-22 23:59:57.854896: step: 932/529, loss: 0.04998297989368439
2023-01-22 23:59:58.970623: step: 936/529, loss: 1.1905598640441895
2023-01-23 00:00:00.067785: step: 940/529, loss: 0.04226398468017578
2023-01-23 00:00:01.182946: step: 944/529, loss: 0.4978475570678711
2023-01-23 00:00:02.308412: step: 948/529, loss: 0.1130976676940918
2023-01-23 00:00:03.427344: step: 952/529, loss: 0.7615178227424622
2023-01-23 00:00:04.516383: step: 956/529, loss: 0.09622316062450409
2023-01-23 00:00:05.634081: step: 960/529, loss: 0.05787640064954758
2023-01-23 00:00:06.753938: step: 964/529, loss: 0.21396437287330627
2023-01-23 00:00:07.871029: step: 968/529, loss: 0.1683407723903656
2023-01-23 00:00:08.979109: step: 972/529, loss: 0.13061919808387756
2023-01-23 00:00:10.087261: step: 976/529, loss: 0.08372955769300461
2023-01-23 00:00:11.197679: step: 980/529, loss: 0.09518122673034668
2023-01-23 00:00:12.303169: step: 984/529, loss: 0.7406069040298462
2023-01-23 00:00:13.405514: step: 988/529, loss: 0.08976936340332031
2023-01-23 00:00:14.489904: step: 992/529, loss: 0.33814573287963867
2023-01-23 00:00:15.605510: step: 996/529, loss: 0.14185667037963867
2023-01-23 00:00:16.703026: step: 1000/529, loss: 0.038360595703125
2023-01-23 00:00:17.802462: step: 1004/529, loss: 0.12126073986291885
2023-01-23 00:00:18.934409: step: 1008/529, loss: 0.3978820741176605
2023-01-23 00:00:20.074372: step: 1012/529, loss: 0.07474441826343536
2023-01-23 00:00:21.183588: step: 1016/529, loss: 0.1304573118686676
2023-01-23 00:00:22.286520: step: 1020/529, loss: 0.23377451300621033
2023-01-23 00:00:23.350419: step: 1024/529, loss: 7.644143581390381
2023-01-23 00:00:24.476887: step: 1028/529, loss: 0.0811273604631424
2023-01-23 00:00:25.596961: step: 1032/529, loss: 6.218911647796631
2023-01-23 00:00:26.716424: step: 1036/529, loss: 0.1395483911037445
2023-01-23 00:00:27.827277: step: 1040/529, loss: 0.8954647779464722
2023-01-23 00:00:28.932699: step: 1044/529, loss: 0.15395589172840118
2023-01-23 00:00:30.050172: step: 1048/529, loss: 0.7681409120559692
2023-01-23 00:00:31.158916: step: 1052/529, loss: 0.11389818787574768
2023-01-23 00:00:32.273681: step: 1056/529, loss: 0.2399909943342209
2023-01-23 00:00:33.373503: step: 1060/529, loss: 0.05504007637500763
2023-01-23 00:00:34.523006: step: 1064/529, loss: 0.4736661911010742
2023-01-23 00:00:35.619991: step: 1068/529, loss: 0.3544514775276184
2023-01-23 00:00:36.725398: step: 1072/529, loss: 0.2522240877151489
2023-01-23 00:00:37.835119: step: 1076/529, loss: 0.08705344796180725
2023-01-23 00:00:38.963678: step: 1080/529, loss: 0.12338896095752716
2023-01-23 00:00:40.073204: step: 1084/529, loss: 0.7841986417770386
2023-01-23 00:00:41.174270: step: 1088/529, loss: 0.80646151304245
2023-01-23 00:00:42.298190: step: 1092/529, loss: 0.7311602830886841
2023-01-23 00:00:43.396452: step: 1096/529, loss: 0.21718692779541016
2023-01-23 00:00:44.483533: step: 1100/529, loss: 0.17857493460178375
2023-01-23 00:00:45.587303: step: 1104/529, loss: 0.05556363984942436
2023-01-23 00:00:46.680141: step: 1108/529, loss: 0.7564243674278259
2023-01-23 00:00:47.809635: step: 1112/529, loss: 0.33097362518310547
2023-01-23 00:00:48.908756: step: 1116/529, loss: 1.0567814111709595
2023-01-23 00:00:50.012629: step: 1120/529, loss: 1.129134178161621
2023-01-23 00:00:51.093851: step: 1124/529, loss: 0.3711276054382324
2023-01-23 00:00:52.224539: step: 1128/529, loss: 0.09012921154499054
2023-01-23 00:00:53.349764: step: 1132/529, loss: 0.12297835946083069
2023-01-23 00:00:54.483871: step: 1136/529, loss: 0.10164375603199005
2023-01-23 00:00:55.603743: step: 1140/529, loss: 0.13223138451576233
2023-01-23 00:00:56.705639: step: 1144/529, loss: 0.05243721231818199
2023-01-23 00:00:57.804742: step: 1148/529, loss: 0.1398342251777649
2023-01-23 00:00:58.927569: step: 1152/529, loss: 0.09825744479894638
2023-01-23 00:01:00.037703: step: 1156/529, loss: 0.24497276544570923
2023-01-23 00:01:01.174129: step: 1160/529, loss: 0.12554606795310974
2023-01-23 00:01:02.279264: step: 1164/529, loss: 0.3235568404197693
2023-01-23 00:01:03.389899: step: 1168/529, loss: 0.2562273144721985
2023-01-23 00:01:04.509154: step: 1172/529, loss: 0.19707414507865906
2023-01-23 00:01:05.619248: step: 1176/529, loss: 0.29449576139450073
2023-01-23 00:01:06.735707: step: 1180/529, loss: 0.5240601301193237
2023-01-23 00:01:07.847740: step: 1184/529, loss: 0.5446715354919434
2023-01-23 00:01:08.966067: step: 1188/529, loss: 0.16990713775157928
2023-01-23 00:01:10.098662: step: 1192/529, loss: 0.25677481293678284
2023-01-23 00:01:11.224824: step: 1196/529, loss: 0.11575216054916382
2023-01-23 00:01:12.331639: step: 1200/529, loss: 0.05895288288593292
2023-01-23 00:01:13.436184: step: 1204/529, loss: 0.29789239168167114
2023-01-23 00:01:14.533744: step: 1208/529, loss: 0.24778369069099426
2023-01-23 00:01:15.628813: step: 1212/529, loss: 0.09482560306787491
2023-01-23 00:01:16.739153: step: 1216/529, loss: 0.38792508840560913
2023-01-23 00:01:17.841293: step: 1220/529, loss: 0.1624559462070465
2023-01-23 00:01:19.011601: step: 1224/529, loss: 0.06335077434778214
2023-01-23 00:01:20.118827: step: 1228/529, loss: 0.13133525848388672
2023-01-23 00:01:21.252615: step: 1232/529, loss: 0.36569005250930786
2023-01-23 00:01:22.368592: step: 1236/529, loss: 0.11706504225730896
2023-01-23 00:01:23.470817: step: 1240/529, loss: 0.2033659964799881
2023-01-23 00:01:24.616901: step: 1244/529, loss: 0.2285289764404297
2023-01-23 00:01:25.752625: step: 1248/529, loss: 0.3451489210128784
2023-01-23 00:01:26.850343: step: 1252/529, loss: 6.266887664794922
2023-01-23 00:01:27.971930: step: 1256/529, loss: 0.2964404225349426
2023-01-23 00:01:29.110900: step: 1260/529, loss: 0.26768603920936584
2023-01-23 00:01:30.231107: step: 1264/529, loss: 0.14428062736988068
2023-01-23 00:01:31.354017: step: 1268/529, loss: 0.07190468907356262
2023-01-23 00:01:32.496866: step: 1272/529, loss: 0.2975412607192993
2023-01-23 00:01:33.639468: step: 1276/529, loss: 0.1005764976143837
2023-01-23 00:01:34.752631: step: 1280/529, loss: 0.15953359007835388
2023-01-23 00:01:35.882334: step: 1284/529, loss: 0.24019962549209595
2023-01-23 00:01:37.013624: step: 1288/529, loss: 0.1978778839111328
2023-01-23 00:01:38.123250: step: 1292/529, loss: 0.39905303716659546
2023-01-23 00:01:39.259246: step: 1296/529, loss: 0.44769737124443054
2023-01-23 00:01:40.401636: step: 1300/529, loss: 0.3252217471599579
2023-01-23 00:01:41.544671: step: 1304/529, loss: 7.657644271850586
2023-01-23 00:01:42.651514: step: 1308/529, loss: 0.6352218985557556
2023-01-23 00:01:43.778154: step: 1312/529, loss: 0.5822814702987671
2023-01-23 00:01:44.903756: step: 1316/529, loss: 0.20116862654685974
2023-01-23 00:01:45.995737: step: 1320/529, loss: 0.04348144680261612
2023-01-23 00:01:47.090897: step: 1324/529, loss: 0.10757599025964737
2023-01-23 00:01:48.217880: step: 1328/529, loss: 0.24369993805885315
2023-01-23 00:01:49.310372: step: 1332/529, loss: 0.02398652955889702
2023-01-23 00:01:50.443850: step: 1336/529, loss: 1.0330395698547363
2023-01-23 00:01:51.537481: step: 1340/529, loss: 0.09930892288684845
2023-01-23 00:01:52.710099: step: 1344/529, loss: 1.3859328031539917
2023-01-23 00:01:53.796228: step: 1348/529, loss: 0.14805221557617188
2023-01-23 00:01:54.886139: step: 1352/529, loss: 0.6569976806640625
2023-01-23 00:01:55.993849: step: 1356/529, loss: 0.14053136110305786
2023-01-23 00:01:57.129453: step: 1360/529, loss: 0.11296391487121582
2023-01-23 00:01:58.238239: step: 1364/529, loss: 0.20357605814933777
2023-01-23 00:01:59.322107: step: 1368/529, loss: 0.6747820973396301
2023-01-23 00:02:00.423262: step: 1372/529, loss: 0.7554526925086975
2023-01-23 00:02:01.505366: step: 1376/529, loss: 0.27689898014068604
2023-01-23 00:02:02.603027: step: 1380/529, loss: 0.16605934500694275
2023-01-23 00:02:03.698026: step: 1384/529, loss: 0.18032407760620117
2023-01-23 00:02:04.800053: step: 1388/529, loss: 0.1738419085741043
2023-01-23 00:02:05.917951: step: 1392/529, loss: 6.825258731842041
2023-01-23 00:02:07.021025: step: 1396/529, loss: 0.10907812416553497
2023-01-23 00:02:08.143912: step: 1400/529, loss: 0.09888801723718643
2023-01-23 00:02:09.245388: step: 1404/529, loss: 0.9205310940742493
2023-01-23 00:02:10.346956: step: 1408/529, loss: 0.3518640398979187
2023-01-23 00:02:11.457443: step: 1412/529, loss: 0.11014070361852646
2023-01-23 00:02:12.546693: step: 1416/529, loss: 2.866546154022217
2023-01-23 00:02:13.653459: step: 1420/529, loss: 0.08448782563209534
2023-01-23 00:02:14.779647: step: 1424/529, loss: 0.17541609704494476
2023-01-23 00:02:15.886492: step: 1428/529, loss: 0.0688701644539833
2023-01-23 00:02:16.981807: step: 1432/529, loss: 0.22905360162258148
2023-01-23 00:02:18.120615: step: 1436/529, loss: 0.05497455969452858
2023-01-23 00:02:19.234849: step: 1440/529, loss: 0.6626628041267395
2023-01-23 00:02:20.345912: step: 1444/529, loss: 0.2110680639743805
2023-01-23 00:02:21.442191: step: 1448/529, loss: 0.2953304350376129
2023-01-23 00:02:22.546782: step: 1452/529, loss: 0.08944135159254074
2023-01-23 00:02:23.648856: step: 1456/529, loss: 0.5831474661827087
2023-01-23 00:02:24.755769: step: 1460/529, loss: 0.51947420835495
2023-01-23 00:02:25.875863: step: 1464/529, loss: 0.2941949665546417
2023-01-23 00:02:26.991695: step: 1468/529, loss: 0.12500719726085663
2023-01-23 00:02:28.120195: step: 1472/529, loss: 2.186870574951172
2023-01-23 00:02:29.220826: step: 1476/529, loss: 0.17179012298583984
2023-01-23 00:02:30.331311: step: 1480/529, loss: 1.3619778156280518
2023-01-23 00:02:31.439297: step: 1484/529, loss: 0.26388871669769287
2023-01-23 00:02:32.527154: step: 1488/529, loss: 0.8584086894989014
2023-01-23 00:02:33.644056: step: 1492/529, loss: 0.1718585044145584
2023-01-23 00:02:34.783222: step: 1496/529, loss: 0.8099654912948608
2023-01-23 00:02:35.950980: step: 1500/529, loss: 0.7845700979232788
2023-01-23 00:02:37.062088: step: 1504/529, loss: 0.10382194072008133
2023-01-23 00:02:38.158074: step: 1508/529, loss: 0.08117265999317169
2023-01-23 00:02:39.249897: step: 1512/529, loss: 0.22360281646251678
2023-01-23 00:02:40.364171: step: 1516/529, loss: 1.9387227296829224
2023-01-23 00:02:41.459032: step: 1520/529, loss: 0.13123612105846405
2023-01-23 00:02:42.576981: step: 1524/529, loss: 0.1132390946149826
2023-01-23 00:02:43.705960: step: 1528/529, loss: 0.7765964269638062
2023-01-23 00:02:44.811986: step: 1532/529, loss: 0.25017109513282776
2023-01-23 00:02:45.935931: step: 1536/529, loss: 0.3031921982765198
2023-01-23 00:02:47.037003: step: 1540/529, loss: 0.04496727138757706
2023-01-23 00:02:48.168174: step: 1544/529, loss: 0.8941881060600281
2023-01-23 00:02:49.293669: step: 1548/529, loss: 0.5266496539115906
2023-01-23 00:02:50.429702: step: 1552/529, loss: 0.3112978935241699
2023-01-23 00:02:51.557061: step: 1556/529, loss: 0.2610532343387604
2023-01-23 00:02:52.680892: step: 1560/529, loss: 0.13099098205566406
2023-01-23 00:02:53.785245: step: 1564/529, loss: 0.1538313329219818
2023-01-23 00:02:54.900275: step: 1568/529, loss: 0.5081146955490112
2023-01-23 00:02:56.032445: step: 1572/529, loss: 0.3228822946548462
2023-01-23 00:02:57.127997: step: 1576/529, loss: 0.7244106531143188
2023-01-23 00:02:58.258072: step: 1580/529, loss: 0.07521490752696991
2023-01-23 00:02:59.361301: step: 1584/529, loss: 0.1976000815629959
2023-01-23 00:03:00.521462: step: 1588/529, loss: 1.2680259943008423
2023-01-23 00:03:01.615860: step: 1592/529, loss: 0.4451565742492676
2023-01-23 00:03:02.720684: step: 1596/529, loss: 0.12641993165016174
2023-01-23 00:03:03.835852: step: 1600/529, loss: 0.06996989250183105
2023-01-23 00:03:04.938092: step: 1604/529, loss: 0.4087117314338684
2023-01-23 00:03:06.084124: step: 1608/529, loss: 0.12463803589344025
2023-01-23 00:03:07.185053: step: 1612/529, loss: 7.072520732879639
2023-01-23 00:03:08.313614: step: 1616/529, loss: 0.9215995669364929
2023-01-23 00:03:09.419720: step: 1620/529, loss: 0.11515302956104279
2023-01-23 00:03:10.516220: step: 1624/529, loss: 0.03171682357788086
2023-01-23 00:03:11.644517: step: 1628/529, loss: 0.604544997215271
2023-01-23 00:03:12.766384: step: 1632/529, loss: 0.11626625806093216
2023-01-23 00:03:13.841225: step: 1636/529, loss: 0.09962864220142365
2023-01-23 00:03:14.953942: step: 1640/529, loss: 0.17779016494750977
2023-01-23 00:03:16.068388: step: 1644/529, loss: 0.11542224884033203
2023-01-23 00:03:17.167876: step: 1648/529, loss: 0.6304776668548584
2023-01-23 00:03:18.277883: step: 1652/529, loss: 0.150037482380867
2023-01-23 00:03:19.387297: step: 1656/529, loss: 0.10930319130420685
2023-01-23 00:03:20.496867: step: 1660/529, loss: 0.054425764828920364
2023-01-23 00:03:21.591627: step: 1664/529, loss: 0.8273213505744934
2023-01-23 00:03:22.719084: step: 1668/529, loss: 0.11428241431713104
2023-01-23 00:03:23.830675: step: 1672/529, loss: 0.5153927803039551
2023-01-23 00:03:24.923110: step: 1676/529, loss: 0.07320769131183624
2023-01-23 00:03:26.063277: step: 1680/529, loss: 1.597503900527954
2023-01-23 00:03:27.187900: step: 1684/529, loss: 0.15810072422027588
2023-01-23 00:03:28.299641: step: 1688/529, loss: 0.9738703370094299
2023-01-23 00:03:29.398057: step: 1692/529, loss: 0.14176030457019806
2023-01-23 00:03:30.519567: step: 1696/529, loss: 0.15938439965248108
2023-01-23 00:03:31.632818: step: 1700/529, loss: 0.12168703973293304
2023-01-23 00:03:32.767017: step: 1704/529, loss: 0.24064913392066956
2023-01-23 00:03:33.868829: step: 1708/529, loss: 0.3153999447822571
2023-01-23 00:03:34.986947: step: 1712/529, loss: 6.021102428436279
2023-01-23 00:03:36.071776: step: 1716/529, loss: 0.29667505621910095
2023-01-23 00:03:37.165608: step: 1720/529, loss: 0.1244380921125412
2023-01-23 00:03:38.262558: step: 1724/529, loss: 0.11710548400878906
2023-01-23 00:03:39.374581: step: 1728/529, loss: 0.10147824138402939
2023-01-23 00:03:40.480874: step: 1732/529, loss: 0.16996492445468903
2023-01-23 00:03:41.559357: step: 1736/529, loss: 0.6971297860145569
2023-01-23 00:03:42.697238: step: 1740/529, loss: 0.1374097466468811
2023-01-23 00:03:43.797087: step: 1744/529, loss: 6.310600757598877
2023-01-23 00:03:44.912952: step: 1748/529, loss: 1.4986711740493774
2023-01-23 00:03:46.014592: step: 1752/529, loss: 0.6713878512382507
2023-01-23 00:03:47.121833: step: 1756/529, loss: 0.1214049905538559
2023-01-23 00:03:48.263389: step: 1760/529, loss: 0.24521350860595703
2023-01-23 00:03:49.364061: step: 1764/529, loss: 0.2385249137878418
2023-01-23 00:03:50.464083: step: 1768/529, loss: 0.3238133192062378
2023-01-23 00:03:51.569079: step: 1772/529, loss: 0.4617188572883606
2023-01-23 00:03:52.699904: step: 1776/529, loss: 0.13507910072803497
2023-01-23 00:03:53.809071: step: 1780/529, loss: 0.27470436692237854
2023-01-23 00:03:54.908293: step: 1784/529, loss: 0.3224661946296692
2023-01-23 00:03:56.048922: step: 1788/529, loss: 0.17379580438137054
2023-01-23 00:03:57.157605: step: 1792/529, loss: 0.21926411986351013
2023-01-23 00:03:58.247203: step: 1796/529, loss: 0.10533003509044647
2023-01-23 00:03:59.386983: step: 1800/529, loss: 4.866824150085449
2023-01-23 00:04:00.470157: step: 1804/529, loss: 0.46708834171295166
2023-01-23 00:04:01.566273: step: 1808/529, loss: 0.2679416537284851
2023-01-23 00:04:02.667973: step: 1812/529, loss: 0.0899043083190918
2023-01-23 00:04:03.777429: step: 1816/529, loss: 0.09973478317260742
2023-01-23 00:04:04.896620: step: 1820/529, loss: 0.1612849235534668
2023-01-23 00:04:05.992343: step: 1824/529, loss: 1.3038971424102783
2023-01-23 00:04:07.090956: step: 1828/529, loss: 0.2686694860458374
2023-01-23 00:04:08.210935: step: 1832/529, loss: 0.2632485628128052
2023-01-23 00:04:09.325690: step: 1836/529, loss: 0.12849335372447968
2023-01-23 00:04:10.424501: step: 1840/529, loss: 0.2791590690612793
2023-01-23 00:04:11.527700: step: 1844/529, loss: 0.42025184631347656
2023-01-23 00:04:12.626943: step: 1848/529, loss: 0.24211034178733826
2023-01-23 00:04:13.710110: step: 1852/529, loss: 0.15408745408058167
2023-01-23 00:04:14.827677: step: 1856/529, loss: 0.1954731047153473
2023-01-23 00:04:15.925270: step: 1860/529, loss: 0.07411280274391174
2023-01-23 00:04:17.029017: step: 1864/529, loss: 0.28218376636505127
2023-01-23 00:04:18.113615: step: 1868/529, loss: 0.06740951538085938
2023-01-23 00:04:19.243352: step: 1872/529, loss: 0.42508286237716675
2023-01-23 00:04:20.347813: step: 1876/529, loss: 0.2036547213792801
2023-01-23 00:04:21.443680: step: 1880/529, loss: 0.1151064932346344
2023-01-23 00:04:22.568281: step: 1884/529, loss: 0.5739890336990356
2023-01-23 00:04:23.685842: step: 1888/529, loss: 0.42548856139183044
2023-01-23 00:04:24.776087: step: 1892/529, loss: 0.08126717060804367
2023-01-23 00:04:25.872743: step: 1896/529, loss: 0.2387586236000061
2023-01-23 00:04:26.955560: step: 1900/529, loss: 0.638191819190979
2023-01-23 00:04:28.073755: step: 1904/529, loss: 0.668250322341919
2023-01-23 00:04:29.198054: step: 1908/529, loss: 0.1001528799533844
2023-01-23 00:04:30.295366: step: 1912/529, loss: 0.0707489550113678
2023-01-23 00:04:31.427140: step: 1916/529, loss: 0.2851121127605438
2023-01-23 00:04:32.546217: step: 1920/529, loss: 0.2972749173641205
2023-01-23 00:04:33.675940: step: 1924/529, loss: 0.06979580223560333
2023-01-23 00:04:34.775686: step: 1928/529, loss: 0.10663776844739914
2023-01-23 00:04:35.870536: step: 1932/529, loss: 0.11231927573680878
2023-01-23 00:04:36.992791: step: 1936/529, loss: 0.904582679271698
2023-01-23 00:04:38.091918: step: 1940/529, loss: 0.683761715888977
2023-01-23 00:04:39.203492: step: 1944/529, loss: 0.5466469526290894
2023-01-23 00:04:40.305832: step: 1948/529, loss: 0.40903064608573914
2023-01-23 00:04:41.448976: step: 1952/529, loss: 0.21860074996948242
2023-01-23 00:04:42.549344: step: 1956/529, loss: 0.4554615020751953
2023-01-23 00:04:43.678177: step: 1960/529, loss: 0.14795179665088654
2023-01-23 00:04:44.802222: step: 1964/529, loss: 0.16426968574523926
2023-01-23 00:04:45.904386: step: 1968/529, loss: 0.19438907504081726
2023-01-23 00:04:46.984902: step: 1972/529, loss: 0.6508668661117554
2023-01-23 00:04:48.081202: step: 1976/529, loss: 0.05450606346130371
2023-01-23 00:04:49.181086: step: 1980/529, loss: 0.5855188965797424
2023-01-23 00:04:50.291167: step: 1984/529, loss: 0.14482136070728302
2023-01-23 00:04:51.383581: step: 1988/529, loss: 0.9255144596099854
2023-01-23 00:04:52.509325: step: 1992/529, loss: 0.17067299783229828
2023-01-23 00:04:53.621780: step: 1996/529, loss: 0.09915242344141006
2023-01-23 00:04:54.721187: step: 2000/529, loss: 0.08624716103076935
2023-01-23 00:04:55.810281: step: 2004/529, loss: 0.06186475604772568
2023-01-23 00:04:56.894100: step: 2008/529, loss: 0.2465021163225174
2023-01-23 00:04:58.017109: step: 2012/529, loss: 0.08015727996826172
2023-01-23 00:04:59.097099: step: 2016/529, loss: 0.137742280960083
2023-01-23 00:05:00.222586: step: 2020/529, loss: 0.7874522805213928
2023-01-23 00:05:01.346755: step: 2024/529, loss: 0.7217190265655518
2023-01-23 00:05:02.494868: step: 2028/529, loss: 1.4282710552215576
2023-01-23 00:05:03.592502: step: 2032/529, loss: 0.07230110466480255
2023-01-23 00:05:04.713788: step: 2036/529, loss: 0.21527576446533203
2023-01-23 00:05:05.826169: step: 2040/529, loss: 0.18370608985424042
2023-01-23 00:05:06.946625: step: 2044/529, loss: 1.398308515548706
2023-01-23 00:05:08.042524: step: 2048/529, loss: 0.126674085855484
2023-01-23 00:05:09.147752: step: 2052/529, loss: 0.30660954117774963
2023-01-23 00:05:10.240683: step: 2056/529, loss: 0.08510196208953857
2023-01-23 00:05:11.378409: step: 2060/529, loss: 0.21761254966259003
2023-01-23 00:05:12.511994: step: 2064/529, loss: 2.3670084476470947
2023-01-23 00:05:13.624043: step: 2068/529, loss: 0.43338441848754883
2023-01-23 00:05:14.735824: step: 2072/529, loss: 0.1459934264421463
2023-01-23 00:05:15.854630: step: 2076/529, loss: 0.3969666659832001
2023-01-23 00:05:16.960455: step: 2080/529, loss: 0.669745683670044
2023-01-23 00:05:18.082652: step: 2084/529, loss: 0.7680432796478271
2023-01-23 00:05:19.178296: step: 2088/529, loss: 0.3431036174297333
2023-01-23 00:05:20.311013: step: 2092/529, loss: 0.20547810196876526
2023-01-23 00:05:21.416063: step: 2096/529, loss: 0.6426596641540527
2023-01-23 00:05:22.533327: step: 2100/529, loss: 0.9980220198631287
2023-01-23 00:05:23.636650: step: 2104/529, loss: 6.7970499992370605
2023-01-23 00:05:24.744923: step: 2108/529, loss: 0.9798686504364014
2023-01-23 00:05:25.849756: step: 2112/529, loss: 0.06655607372522354
2023-01-23 00:05:27.002889: step: 2116/529, loss: 0.3421632647514343
==================================================
Loss: 0.501
--------------------
Dev: {'event': {'p': 0.5572815533980583, 'r': 0.7643142476697736, 'f1': 0.6445816956765862}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.5485519591141397, 'r': 0.7268623024830699, 'f1': 0.6252427184466018}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
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': 3}
Korean: {'event': {'p': 0.7111111111111111, 'r': 0.5079365079365079, 'f1': 0.5925925925925924}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.5945945945945946, 'r': 0.6111111111111112, 'f1': 0.6027397260273972}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5572815533980583, 'r': 0.7643142476697736, 'f1': 0.6445816956765862}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.5485519591141397, 'r': 0.7268623024830699, 'f1': 0.6252427184466018}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.7111111111111111, 'r': 0.5079365079365079, 'f1': 0.5925925925925924}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Russian: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Russian: {'event': {'p': 0.6176470588235294, 'r': 0.5833333333333334, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:06:14.945859: step: 4/529, loss: 0.6615797281265259
2023-01-23 00:06:16.030917: step: 8/529, loss: 0.05763940513134003
2023-01-23 00:06:17.174702: step: 12/529, loss: 0.19935540854930878
2023-01-23 00:06:18.285217: step: 16/529, loss: 0.0393078587949276
2023-01-23 00:06:19.441007: step: 20/529, loss: 0.8522058725357056
2023-01-23 00:06:20.543477: step: 24/529, loss: 0.12867431342601776
2023-01-23 00:06:21.653813: step: 28/529, loss: 0.18457098305225372
2023-01-23 00:06:22.791949: step: 32/529, loss: 0.08480529487133026
2023-01-23 00:06:23.905311: step: 36/529, loss: 0.04493327438831329
2023-01-23 00:06:25.016233: step: 40/529, loss: 0.1839262843132019
2023-01-23 00:06:26.110038: step: 44/529, loss: 0.5116775631904602
2023-01-23 00:06:27.207409: step: 48/529, loss: 0.05727691948413849
2023-01-23 00:06:28.325203: step: 52/529, loss: 0.1392023265361786
2023-01-23 00:06:29.423329: step: 56/529, loss: 0.21133175492286682
2023-01-23 00:06:30.532825: step: 60/529, loss: 1.5186076164245605
2023-01-23 00:06:31.630254: step: 64/529, loss: 0.1221562922000885
2023-01-23 00:06:32.819759: step: 68/529, loss: 0.1041574478149414
2023-01-23 00:06:33.915359: step: 72/529, loss: 0.1703396737575531
2023-01-23 00:06:35.023700: step: 76/529, loss: 0.17172327637672424
2023-01-23 00:06:36.138294: step: 80/529, loss: 1.1180455684661865
2023-01-23 00:06:37.249706: step: 84/529, loss: 0.1603957712650299
2023-01-23 00:06:38.340349: step: 88/529, loss: 0.46226492524147034
2023-01-23 00:06:39.469030: step: 92/529, loss: 0.5222301483154297
2023-01-23 00:06:40.575146: step: 96/529, loss: 0.07915011048316956
2023-01-23 00:06:41.697228: step: 100/529, loss: 0.22018995881080627
2023-01-23 00:06:42.808381: step: 104/529, loss: 0.1150629073381424
2023-01-23 00:06:43.913101: step: 108/529, loss: 0.6044923663139343
2023-01-23 00:06:45.045144: step: 112/529, loss: 0.12086892873048782
2023-01-23 00:06:46.176842: step: 116/529, loss: 0.15235671401023865
2023-01-23 00:06:47.296864: step: 120/529, loss: 0.3981592357158661
2023-01-23 00:06:48.405365: step: 124/529, loss: 0.9084380865097046
2023-01-23 00:06:49.536550: step: 128/529, loss: 1.6567373275756836
2023-01-23 00:06:50.652973: step: 132/529, loss: 0.8471486568450928
2023-01-23 00:06:51.746255: step: 136/529, loss: 0.15174369513988495
2023-01-23 00:06:52.864877: step: 140/529, loss: 0.049643948674201965
2023-01-23 00:06:53.955328: step: 144/529, loss: 0.49346303939819336
2023-01-23 00:06:55.026276: step: 148/529, loss: 0.9318476915359497
2023-01-23 00:06:56.139571: step: 152/529, loss: 0.17108678817749023
2023-01-23 00:06:57.217417: step: 156/529, loss: 0.08710145950317383
2023-01-23 00:06:58.349188: step: 160/529, loss: 0.3642563223838806
2023-01-23 00:06:59.441387: step: 164/529, loss: 0.12289419770240784
2023-01-23 00:07:00.562736: step: 168/529, loss: 0.256794273853302
2023-01-23 00:07:01.688698: step: 172/529, loss: 0.10855893790721893
2023-01-23 00:07:02.894346: step: 176/529, loss: 0.33685681223869324
2023-01-23 00:07:03.983522: step: 180/529, loss: 0.0270296111702919
2023-01-23 00:07:05.096795: step: 184/529, loss: 0.030338477343320847
2023-01-23 00:07:06.197431: step: 188/529, loss: 0.13597774505615234
2023-01-23 00:07:07.289541: step: 192/529, loss: 0.11101846396923065
2023-01-23 00:07:08.401644: step: 196/529, loss: 0.20447483658790588
2023-01-23 00:07:09.527615: step: 200/529, loss: 0.053606078028678894
2023-01-23 00:07:10.651001: step: 204/529, loss: 0.10037890076637268
2023-01-23 00:07:11.742198: step: 208/529, loss: 0.2880972921848297
2023-01-23 00:07:12.862023: step: 212/529, loss: 0.7638998627662659
2023-01-23 00:07:13.975550: step: 216/529, loss: 0.9142026305198669
2023-01-23 00:07:15.074620: step: 220/529, loss: 1.1600990295410156
2023-01-23 00:07:16.210497: step: 224/529, loss: 0.7649625539779663
2023-01-23 00:07:17.334505: step: 228/529, loss: 0.06582774966955185
2023-01-23 00:07:18.475180: step: 232/529, loss: 1.1401495933532715
2023-01-23 00:07:19.579476: step: 236/529, loss: 0.05163174122571945
2023-01-23 00:07:20.675446: step: 240/529, loss: 0.2893497943878174
2023-01-23 00:07:21.823990: step: 244/529, loss: 0.7470611333847046
2023-01-23 00:07:22.955426: step: 248/529, loss: 0.12130794674158096
2023-01-23 00:07:24.055000: step: 252/529, loss: 0.13695335388183594
2023-01-23 00:07:25.179962: step: 256/529, loss: 0.09405794739723206
2023-01-23 00:07:26.301468: step: 260/529, loss: 1.3281975984573364
2023-01-23 00:07:27.456418: step: 264/529, loss: 0.3186616897583008
2023-01-23 00:07:28.560481: step: 268/529, loss: 0.13274574279785156
2023-01-23 00:07:29.653366: step: 272/529, loss: 0.18047982454299927
2023-01-23 00:07:30.766299: step: 276/529, loss: 0.7832397818565369
2023-01-23 00:07:31.894715: step: 280/529, loss: 0.28849613666534424
2023-01-23 00:07:33.014450: step: 284/529, loss: 0.1275920867919922
2023-01-23 00:07:34.146943: step: 288/529, loss: 0.18065795302391052
2023-01-23 00:07:35.317954: step: 292/529, loss: 0.5579242706298828
2023-01-23 00:07:36.423874: step: 296/529, loss: 0.09338913857936859
2023-01-23 00:07:37.543957: step: 300/529, loss: 0.17106589674949646
2023-01-23 00:07:38.651105: step: 304/529, loss: 0.14436836540699005
2023-01-23 00:07:39.749007: step: 308/529, loss: 0.14182138442993164
2023-01-23 00:07:40.883330: step: 312/529, loss: 0.19877047836780548
2023-01-23 00:07:41.995685: step: 316/529, loss: 6.462676048278809
2023-01-23 00:07:43.150526: step: 320/529, loss: 0.18959026038646698
2023-01-23 00:07:44.258783: step: 324/529, loss: 0.4373766779899597
2023-01-23 00:07:45.394470: step: 328/529, loss: 0.25225162506103516
2023-01-23 00:07:46.518957: step: 332/529, loss: 0.1100100576877594
2023-01-23 00:07:47.638703: step: 336/529, loss: 0.1648460328578949
2023-01-23 00:07:48.756710: step: 340/529, loss: 0.04197349399328232
2023-01-23 00:07:49.861596: step: 344/529, loss: 0.18330413103103638
2023-01-23 00:07:50.994410: step: 348/529, loss: 0.4961535334587097
2023-01-23 00:07:52.142128: step: 352/529, loss: 0.0831550657749176
2023-01-23 00:07:53.249878: step: 356/529, loss: 0.7677115797996521
2023-01-23 00:07:54.336125: step: 360/529, loss: 0.06961259990930557
2023-01-23 00:07:55.463253: step: 364/529, loss: 0.0457647331058979
2023-01-23 00:07:56.567063: step: 368/529, loss: 0.05683698505163193
2023-01-23 00:07:57.708613: step: 372/529, loss: 0.14422345161437988
2023-01-23 00:07:58.816930: step: 376/529, loss: 0.2522476315498352
2023-01-23 00:07:59.929563: step: 380/529, loss: 1.3967328071594238
2023-01-23 00:08:01.028577: step: 384/529, loss: 0.15042105317115784
2023-01-23 00:08:02.148936: step: 388/529, loss: 1.2744789123535156
2023-01-23 00:08:03.243080: step: 392/529, loss: 0.05517597496509552
2023-01-23 00:08:04.365420: step: 396/529, loss: 0.1627863049507141
2023-01-23 00:08:05.475547: step: 400/529, loss: 0.23674874007701874
2023-01-23 00:08:06.627319: step: 404/529, loss: 0.4522775113582611
2023-01-23 00:08:07.744366: step: 408/529, loss: 0.07138939201831818
2023-01-23 00:08:08.858259: step: 412/529, loss: 0.18453297019004822
2023-01-23 00:08:09.972519: step: 416/529, loss: 0.10821361839771271
2023-01-23 00:08:11.095736: step: 420/529, loss: 0.07641144096851349
2023-01-23 00:08:12.208805: step: 424/529, loss: 0.839661717414856
2023-01-23 00:08:13.323947: step: 428/529, loss: 0.09891395270824432
2023-01-23 00:08:14.446049: step: 432/529, loss: 0.8882951736450195
2023-01-23 00:08:15.565939: step: 436/529, loss: 0.11361751705408096
2023-01-23 00:08:16.686255: step: 440/529, loss: 0.6129663586616516
2023-01-23 00:08:17.816852: step: 444/529, loss: 0.16441236436367035
2023-01-23 00:08:18.932054: step: 448/529, loss: 0.4480552077293396
2023-01-23 00:08:20.035665: step: 452/529, loss: 0.07353896647691727
2023-01-23 00:08:21.148892: step: 456/529, loss: 0.17931196093559265
2023-01-23 00:08:22.255476: step: 460/529, loss: 0.11137089878320694
2023-01-23 00:08:23.357768: step: 464/529, loss: 0.10110397636890411
2023-01-23 00:08:24.495991: step: 468/529, loss: 0.17838773131370544
2023-01-23 00:08:25.610238: step: 472/529, loss: 0.855185866355896
2023-01-23 00:08:26.718898: step: 476/529, loss: 0.11198330670595169
2023-01-23 00:08:27.867291: step: 480/529, loss: 0.15248270332813263
2023-01-23 00:08:29.082427: step: 484/529, loss: 0.194318488240242
2023-01-23 00:08:30.174326: step: 488/529, loss: 1.2352555990219116
2023-01-23 00:08:31.296183: step: 492/529, loss: 0.1180235892534256
2023-01-23 00:08:32.439072: step: 496/529, loss: 0.31113529205322266
2023-01-23 00:08:33.535063: step: 500/529, loss: 0.09890633076429367
2023-01-23 00:08:34.665825: step: 504/529, loss: 0.20155149698257446
2023-01-23 00:08:35.807121: step: 508/529, loss: 0.6794360876083374
2023-01-23 00:08:36.925100: step: 512/529, loss: 0.3900454044342041
2023-01-23 00:08:38.022712: step: 516/529, loss: 0.03242664411664009
2023-01-23 00:08:39.145299: step: 520/529, loss: 0.8571157455444336
2023-01-23 00:08:40.304225: step: 524/529, loss: 0.08405561000108719
2023-01-23 00:08:41.427005: step: 528/529, loss: 0.3595353066921234
2023-01-23 00:08:42.569458: step: 532/529, loss: 0.1927490234375
2023-01-23 00:08:43.667128: step: 536/529, loss: 0.44470512866973877
2023-01-23 00:08:44.741638: step: 540/529, loss: 0.12757444381713867
2023-01-23 00:08:45.861493: step: 544/529, loss: 0.18529057502746582
2023-01-23 00:08:46.998812: step: 548/529, loss: 0.3882457911968231
2023-01-23 00:08:48.089015: step: 552/529, loss: 0.4076805114746094
2023-01-23 00:08:49.237379: step: 556/529, loss: 0.03375823795795441
2023-01-23 00:08:50.365886: step: 560/529, loss: 0.5030654668807983
2023-01-23 00:08:51.439062: step: 564/529, loss: 0.03556113317608833
2023-01-23 00:08:52.544188: step: 568/529, loss: 0.15654611587524414
2023-01-23 00:08:53.656742: step: 572/529, loss: 0.22579175233840942
2023-01-23 00:08:54.785011: step: 576/529, loss: 0.07832713425159454
2023-01-23 00:08:55.891437: step: 580/529, loss: 0.04010143503546715
2023-01-23 00:08:57.007665: step: 584/529, loss: 0.1238139197230339
2023-01-23 00:08:58.101972: step: 588/529, loss: 0.048009444028139114
2023-01-23 00:08:59.222120: step: 592/529, loss: 0.31844595074653625
2023-01-23 00:09:00.313755: step: 596/529, loss: 0.20688945055007935
2023-01-23 00:09:01.402782: step: 600/529, loss: 0.6314584612846375
2023-01-23 00:09:02.511749: step: 604/529, loss: 0.050681307911872864
2023-01-23 00:09:03.617506: step: 608/529, loss: 0.2556617856025696
2023-01-23 00:09:04.732094: step: 612/529, loss: 0.08270960301160812
2023-01-23 00:09:05.838628: step: 616/529, loss: 0.11264973133802414
2023-01-23 00:09:06.960906: step: 620/529, loss: 0.06644923985004425
2023-01-23 00:09:08.065704: step: 624/529, loss: 0.10791674256324768
2023-01-23 00:09:09.183805: step: 628/529, loss: 0.5957445502281189
2023-01-23 00:09:10.319922: step: 632/529, loss: 0.1686287820339203
2023-01-23 00:09:11.435146: step: 636/529, loss: 0.09545373916625977
2023-01-23 00:09:12.521053: step: 640/529, loss: 1.1102495193481445
2023-01-23 00:09:13.613683: step: 644/529, loss: 0.04795694351196289
2023-01-23 00:09:14.744160: step: 648/529, loss: 0.4312848746776581
2023-01-23 00:09:15.876309: step: 652/529, loss: 0.8475534319877625
2023-01-23 00:09:16.970216: step: 656/529, loss: 0.1673000603914261
2023-01-23 00:09:18.096042: step: 660/529, loss: 0.07831769436597824
2023-01-23 00:09:19.225077: step: 664/529, loss: 0.30501502752304077
2023-01-23 00:09:20.330341: step: 668/529, loss: 0.11304493248462677
2023-01-23 00:09:21.458505: step: 672/529, loss: 0.3964780867099762
2023-01-23 00:09:22.592791: step: 676/529, loss: 0.5287326574325562
2023-01-23 00:09:23.683245: step: 680/529, loss: 0.5996501445770264
2023-01-23 00:09:24.771152: step: 684/529, loss: 0.6651312112808228
2023-01-23 00:09:25.894930: step: 688/529, loss: 0.3873750567436218
2023-01-23 00:09:26.984931: step: 692/529, loss: 5.405714988708496
2023-01-23 00:09:28.081620: step: 696/529, loss: 0.0684031993150711
2023-01-23 00:09:29.200536: step: 700/529, loss: 0.03897981718182564
2023-01-23 00:09:30.333759: step: 704/529, loss: 0.24262170493602753
2023-01-23 00:09:31.435566: step: 708/529, loss: 0.26134711503982544
2023-01-23 00:09:32.543017: step: 712/529, loss: 0.3341098725795746
2023-01-23 00:09:33.645016: step: 716/529, loss: 0.013199329376220703
2023-01-23 00:09:34.736823: step: 720/529, loss: 5.43837833404541
2023-01-23 00:09:35.866288: step: 724/529, loss: 0.5513275861740112
2023-01-23 00:09:36.965446: step: 728/529, loss: 0.0895567387342453
2023-01-23 00:09:38.073326: step: 732/529, loss: 0.6694862246513367
2023-01-23 00:09:39.174717: step: 736/529, loss: 0.11934996396303177
2023-01-23 00:09:40.287947: step: 740/529, loss: 0.252363383769989
2023-01-23 00:09:41.385833: step: 744/529, loss: 0.064427949488163
2023-01-23 00:09:42.539880: step: 748/529, loss: 0.2742616534233093
2023-01-23 00:09:43.641186: step: 752/529, loss: 0.05188789591193199
2023-01-23 00:09:44.752325: step: 756/529, loss: 0.1607518196105957
2023-01-23 00:09:45.841984: step: 760/529, loss: 0.4873901307582855
2023-01-23 00:09:46.959393: step: 764/529, loss: 0.9535151720046997
2023-01-23 00:09:48.098783: step: 768/529, loss: 0.07002559304237366
2023-01-23 00:09:49.196691: step: 772/529, loss: 0.09257479012012482
2023-01-23 00:09:50.298073: step: 776/529, loss: 0.04662149026989937
2023-01-23 00:09:51.422669: step: 780/529, loss: 0.7043101191520691
2023-01-23 00:09:52.559876: step: 784/529, loss: 0.889208972454071
2023-01-23 00:09:53.664328: step: 788/529, loss: 0.1505270004272461
2023-01-23 00:09:54.800296: step: 792/529, loss: 0.1305987387895584
2023-01-23 00:09:55.921205: step: 796/529, loss: 0.6375781893730164
2023-01-23 00:09:57.034897: step: 800/529, loss: 0.07734694331884384
2023-01-23 00:09:58.121852: step: 804/529, loss: 0.08246222138404846
2023-01-23 00:09:59.204377: step: 808/529, loss: 0.11478619277477264
2023-01-23 00:10:00.366970: step: 812/529, loss: 1.2779672145843506
2023-01-23 00:10:01.493457: step: 816/529, loss: 0.12480269372463226
2023-01-23 00:10:02.589945: step: 820/529, loss: 0.037714291363954544
2023-01-23 00:10:03.719913: step: 824/529, loss: 0.45819342136383057
2023-01-23 00:10:04.839060: step: 828/529, loss: 0.2332388013601303
2023-01-23 00:10:05.979786: step: 832/529, loss: 0.10851164162158966
2023-01-23 00:10:07.101009: step: 836/529, loss: 0.07501611858606339
2023-01-23 00:10:08.222194: step: 840/529, loss: 0.05262966454029083
2023-01-23 00:10:09.310688: step: 844/529, loss: 0.10124874114990234
2023-01-23 00:10:10.441875: step: 848/529, loss: 0.9039085507392883
2023-01-23 00:10:11.581994: step: 852/529, loss: 0.05500993877649307
2023-01-23 00:10:12.744525: step: 856/529, loss: 0.17180556058883667
2023-01-23 00:10:13.833534: step: 860/529, loss: 0.09094668179750443
2023-01-23 00:10:14.924872: step: 864/529, loss: 0.06945426762104034
2023-01-23 00:10:16.020277: step: 868/529, loss: 0.48413917422294617
2023-01-23 00:10:17.140523: step: 872/529, loss: 0.1979755461215973
2023-01-23 00:10:18.245656: step: 876/529, loss: 0.5440086126327515
2023-01-23 00:10:19.332021: step: 880/529, loss: 0.12148857116699219
2023-01-23 00:10:20.461687: step: 884/529, loss: 0.0992768332362175
2023-01-23 00:10:21.562740: step: 888/529, loss: 0.3339608311653137
2023-01-23 00:10:22.682283: step: 892/529, loss: 0.15464048087596893
2023-01-23 00:10:23.807707: step: 896/529, loss: 0.3399643003940582
2023-01-23 00:10:24.919524: step: 900/529, loss: 0.06553025543689728
2023-01-23 00:10:26.024405: step: 904/529, loss: 0.21869993209838867
2023-01-23 00:10:27.142444: step: 908/529, loss: 0.12087535858154297
2023-01-23 00:10:28.235150: step: 912/529, loss: 0.3500957489013672
2023-01-23 00:10:29.335076: step: 916/529, loss: 0.24492283165454865
2023-01-23 00:10:30.446763: step: 920/529, loss: 0.10903721302747726
2023-01-23 00:10:31.568531: step: 924/529, loss: 0.37089115381240845
2023-01-23 00:10:32.690702: step: 928/529, loss: 0.10839272290468216
2023-01-23 00:10:33.823894: step: 932/529, loss: 0.09038126468658447
2023-01-23 00:10:34.952362: step: 936/529, loss: 0.4788447320461273
2023-01-23 00:10:36.070978: step: 940/529, loss: 0.9450740814208984
2023-01-23 00:10:37.181636: step: 944/529, loss: 0.028471995145082474
2023-01-23 00:10:38.261467: step: 948/529, loss: 0.5146323442459106
2023-01-23 00:10:39.348688: step: 952/529, loss: 0.1454252302646637
2023-01-23 00:10:40.470560: step: 956/529, loss: 1.1756420135498047
2023-01-23 00:10:41.605233: step: 960/529, loss: 0.3385176658630371
2023-01-23 00:10:42.722080: step: 964/529, loss: 1.9688810110092163
2023-01-23 00:10:43.837687: step: 968/529, loss: 0.33385169506073
2023-01-23 00:10:44.945720: step: 972/529, loss: 0.07641222327947617
2023-01-23 00:10:46.070769: step: 976/529, loss: 0.1423380821943283
2023-01-23 00:10:47.168907: step: 980/529, loss: 0.18539465963840485
2023-01-23 00:10:48.293408: step: 984/529, loss: 0.039935946464538574
2023-01-23 00:10:49.398582: step: 988/529, loss: 0.11682549118995667
2023-01-23 00:10:50.513689: step: 992/529, loss: 5.441535949707031
2023-01-23 00:10:51.626490: step: 996/529, loss: 0.39364928007125854
2023-01-23 00:10:52.731791: step: 1000/529, loss: 0.09668254852294922
2023-01-23 00:10:53.828696: step: 1004/529, loss: 0.20870447158813477
2023-01-23 00:10:54.962988: step: 1008/529, loss: 0.8664548397064209
2023-01-23 00:10:56.090865: step: 1012/529, loss: 0.025395464152097702
2023-01-23 00:10:57.233161: step: 1016/529, loss: 0.14459332823753357
2023-01-23 00:10:58.348842: step: 1020/529, loss: 0.14206562936306
2023-01-23 00:10:59.440380: step: 1024/529, loss: 0.4411858916282654
2023-01-23 00:11:00.547500: step: 1028/529, loss: 0.09147129207849503
2023-01-23 00:11:01.653634: step: 1032/529, loss: 0.13718290627002716
2023-01-23 00:11:02.774934: step: 1036/529, loss: 1.230292797088623
2023-01-23 00:11:03.872260: step: 1040/529, loss: 0.1264922171831131
2023-01-23 00:11:04.960389: step: 1044/529, loss: 0.742927074432373
2023-01-23 00:11:06.070173: step: 1048/529, loss: 0.3204580545425415
2023-01-23 00:11:07.204997: step: 1052/529, loss: 0.4529357850551605
2023-01-23 00:11:08.318425: step: 1056/529, loss: 0.17225661873817444
2023-01-23 00:11:09.443791: step: 1060/529, loss: 0.1273764669895172
2023-01-23 00:11:10.517788: step: 1064/529, loss: 0.22609463334083557
2023-01-23 00:11:11.636252: step: 1068/529, loss: 0.08944205939769745
2023-01-23 00:11:12.769010: step: 1072/529, loss: 0.19543838500976562
2023-01-23 00:11:13.868164: step: 1076/529, loss: 0.13746052980422974
2023-01-23 00:11:14.963674: step: 1080/529, loss: 1.2111434936523438
2023-01-23 00:11:16.047550: step: 1084/529, loss: 0.9062343239784241
2023-01-23 00:11:17.156544: step: 1088/529, loss: 0.7073706388473511
2023-01-23 00:11:18.265534: step: 1092/529, loss: 0.07628098130226135
2023-01-23 00:11:19.364514: step: 1096/529, loss: 0.14415112137794495
2023-01-23 00:11:20.483017: step: 1100/529, loss: 0.17419585585594177
2023-01-23 00:11:21.576427: step: 1104/529, loss: 0.643078088760376
2023-01-23 00:11:22.694370: step: 1108/529, loss: 0.07637377083301544
2023-01-23 00:11:23.824376: step: 1112/529, loss: 0.3820033073425293
2023-01-23 00:11:24.941392: step: 1116/529, loss: 0.1541009396314621
2023-01-23 00:11:26.055691: step: 1120/529, loss: 0.18002644181251526
2023-01-23 00:11:27.151795: step: 1124/529, loss: 0.2700064778327942
2023-01-23 00:11:28.244509: step: 1128/529, loss: 0.13846750557422638
2023-01-23 00:11:29.340233: step: 1132/529, loss: 0.019024468958377838
2023-01-23 00:11:30.442824: step: 1136/529, loss: 0.1351548284292221
2023-01-23 00:11:31.557814: step: 1140/529, loss: 0.16659009456634521
2023-01-23 00:11:32.649322: step: 1144/529, loss: 0.66960608959198
2023-01-23 00:11:33.773513: step: 1148/529, loss: 0.3959817886352539
2023-01-23 00:11:34.867944: step: 1152/529, loss: 0.6599615216255188
2023-01-23 00:11:35.976169: step: 1156/529, loss: 0.24681758880615234
2023-01-23 00:11:37.103586: step: 1160/529, loss: 0.6472986936569214
2023-01-23 00:11:38.197471: step: 1164/529, loss: 0.4726060926914215
2023-01-23 00:11:39.296781: step: 1168/529, loss: 0.13578566908836365
2023-01-23 00:11:40.424942: step: 1172/529, loss: 0.384170264005661
2023-01-23 00:11:41.539556: step: 1176/529, loss: 0.05696434900164604
2023-01-23 00:11:42.639460: step: 1180/529, loss: 0.2683303952217102
2023-01-23 00:11:43.755213: step: 1184/529, loss: 1.3950036764144897
2023-01-23 00:11:44.883862: step: 1188/529, loss: 0.07179585099220276
2023-01-23 00:11:45.999152: step: 1192/529, loss: 0.0888860747218132
2023-01-23 00:11:47.126566: step: 1196/529, loss: 0.08678951859474182
2023-01-23 00:11:48.236666: step: 1200/529, loss: 1.2237968444824219
2023-01-23 00:11:49.361060: step: 1204/529, loss: 0.19454210996627808
2023-01-23 00:11:50.458124: step: 1208/529, loss: 0.06480474770069122
2023-01-23 00:11:51.562000: step: 1212/529, loss: 0.06839413940906525
2023-01-23 00:11:52.668635: step: 1216/529, loss: 3.6366331577301025
2023-01-23 00:11:53.786872: step: 1220/529, loss: 0.7353880405426025
2023-01-23 00:11:54.910811: step: 1224/529, loss: 0.1569223403930664
2023-01-23 00:11:56.012426: step: 1228/529, loss: 0.1309196949005127
2023-01-23 00:11:57.138341: step: 1232/529, loss: 0.945237934589386
2023-01-23 00:11:58.261371: step: 1236/529, loss: 0.13430005311965942
2023-01-23 00:11:59.353573: step: 1240/529, loss: 0.6541158556938171
2023-01-23 00:12:00.465767: step: 1244/529, loss: 0.17606186866760254
2023-01-23 00:12:01.582587: step: 1248/529, loss: 0.552053689956665
2023-01-23 00:12:02.673623: step: 1252/529, loss: 0.29235193133354187
2023-01-23 00:12:03.815418: step: 1256/529, loss: 0.440141499042511
2023-01-23 00:12:04.930891: step: 1260/529, loss: 0.3931196331977844
2023-01-23 00:12:06.031077: step: 1264/529, loss: 0.6595352292060852
2023-01-23 00:12:07.159094: step: 1268/529, loss: 0.11719191074371338
2023-01-23 00:12:08.232905: step: 1272/529, loss: 0.3888036012649536
2023-01-23 00:12:09.351595: step: 1276/529, loss: 2.185023069381714
2023-01-23 00:12:10.459523: step: 1280/529, loss: 0.29192036390304565
2023-01-23 00:12:11.596903: step: 1284/529, loss: 0.4574712812900543
2023-01-23 00:12:12.703127: step: 1288/529, loss: 0.16599641740322113
2023-01-23 00:12:13.790878: step: 1292/529, loss: 0.7036542892456055
2023-01-23 00:12:14.905974: step: 1296/529, loss: 0.16504187881946564
2023-01-23 00:12:16.038743: step: 1300/529, loss: 0.48771950602531433
2023-01-23 00:12:17.170035: step: 1304/529, loss: 0.14329034090042114
2023-01-23 00:12:18.296718: step: 1308/529, loss: 0.16670912504196167
2023-01-23 00:12:19.408384: step: 1312/529, loss: 0.17818352580070496
2023-01-23 00:12:20.522004: step: 1316/529, loss: 0.4472460150718689
2023-01-23 00:12:21.622084: step: 1320/529, loss: 0.25523626804351807
2023-01-23 00:12:22.727459: step: 1324/529, loss: 0.8591079711914062
2023-01-23 00:12:23.871953: step: 1328/529, loss: 0.538292646408081
2023-01-23 00:12:24.986446: step: 1332/529, loss: 5.669210433959961
2023-01-23 00:12:26.104800: step: 1336/529, loss: 0.4780655801296234
2023-01-23 00:12:27.204321: step: 1340/529, loss: 0.4573246240615845
2023-01-23 00:12:28.298152: step: 1344/529, loss: 0.1562003642320633
2023-01-23 00:12:29.413317: step: 1348/529, loss: 0.08025407791137695
2023-01-23 00:12:30.528950: step: 1352/529, loss: 0.268251895904541
2023-01-23 00:12:31.659593: step: 1356/529, loss: 0.6470426321029663
2023-01-23 00:12:32.769381: step: 1360/529, loss: 0.12363128364086151
2023-01-23 00:12:33.887940: step: 1364/529, loss: 0.1786234974861145
2023-01-23 00:12:34.996254: step: 1368/529, loss: 0.49543020129203796
2023-01-23 00:12:36.076472: step: 1372/529, loss: 0.03644266352057457
2023-01-23 00:12:37.204503: step: 1376/529, loss: 0.38713881373405457
2023-01-23 00:12:38.327867: step: 1380/529, loss: 0.27469301223754883
2023-01-23 00:12:39.417161: step: 1384/529, loss: 0.12839722633361816
2023-01-23 00:12:40.524136: step: 1388/529, loss: 1.3029556274414062
2023-01-23 00:12:41.636685: step: 1392/529, loss: 0.06806459277868271
2023-01-23 00:12:42.734075: step: 1396/529, loss: 0.11641321331262589
2023-01-23 00:12:43.846921: step: 1400/529, loss: 0.07987819612026215
2023-01-23 00:12:44.944716: step: 1404/529, loss: 0.11395521461963654
2023-01-23 00:12:46.058805: step: 1408/529, loss: 0.47873154282569885
2023-01-23 00:12:47.171732: step: 1412/529, loss: 0.21033935248851776
2023-01-23 00:12:48.282984: step: 1416/529, loss: 0.17056827247142792
2023-01-23 00:12:49.380655: step: 1420/529, loss: 0.10613755881786346
2023-01-23 00:12:50.479030: step: 1424/529, loss: 0.15171536803245544
2023-01-23 00:12:51.564631: step: 1428/529, loss: 0.22751502692699432
2023-01-23 00:12:52.687626: step: 1432/529, loss: 0.06238298490643501
2023-01-23 00:12:53.794003: step: 1436/529, loss: 0.6377886533737183
2023-01-23 00:12:54.894344: step: 1440/529, loss: 0.1844189167022705
2023-01-23 00:12:55.984977: step: 1444/529, loss: 0.3766494691371918
2023-01-23 00:12:57.097597: step: 1448/529, loss: 0.16443492472171783
2023-01-23 00:12:58.234046: step: 1452/529, loss: 0.28271445631980896
2023-01-23 00:12:59.334348: step: 1456/529, loss: 0.1826373189687729
2023-01-23 00:13:00.455696: step: 1460/529, loss: 0.03917064517736435
2023-01-23 00:13:01.610922: step: 1464/529, loss: 0.11006021499633789
2023-01-23 00:13:02.741011: step: 1468/529, loss: 0.10037532448768616
2023-01-23 00:13:03.840681: step: 1472/529, loss: 0.7557169795036316
2023-01-23 00:13:04.951021: step: 1476/529, loss: 0.2257649004459381
2023-01-23 00:13:06.084661: step: 1480/529, loss: 0.10338573902845383
2023-01-23 00:13:07.171258: step: 1484/529, loss: 0.3532348573207855
2023-01-23 00:13:08.268337: step: 1488/529, loss: 0.05444040149450302
2023-01-23 00:13:09.390002: step: 1492/529, loss: 0.4606480598449707
2023-01-23 00:13:10.514252: step: 1496/529, loss: 0.11883287131786346
2023-01-23 00:13:11.648049: step: 1500/529, loss: 0.7818244099617004
2023-01-23 00:13:12.726776: step: 1504/529, loss: 0.6513429284095764
2023-01-23 00:13:13.847425: step: 1508/529, loss: 0.13442793488502502
2023-01-23 00:13:14.963771: step: 1512/529, loss: 0.889224648475647
2023-01-23 00:13:16.069737: step: 1516/529, loss: 0.08269243687391281
2023-01-23 00:13:17.167431: step: 1520/529, loss: 0.1586645245552063
2023-01-23 00:13:18.288307: step: 1524/529, loss: 0.2881953716278076
2023-01-23 00:13:19.402767: step: 1528/529, loss: 0.32926616072654724
2023-01-23 00:13:20.523358: step: 1532/529, loss: 0.09252652525901794
2023-01-23 00:13:21.645785: step: 1536/529, loss: 0.5710971355438232
2023-01-23 00:13:22.751268: step: 1540/529, loss: 0.04394941404461861
2023-01-23 00:13:23.873966: step: 1544/529, loss: 0.5223848819732666
2023-01-23 00:13:24.972884: step: 1548/529, loss: 1.9456416368484497
2023-01-23 00:13:26.080368: step: 1552/529, loss: 0.15376925468444824
2023-01-23 00:13:27.218803: step: 1556/529, loss: 0.6080523133277893
2023-01-23 00:13:28.342266: step: 1560/529, loss: 0.12001819163560867
2023-01-23 00:13:29.452117: step: 1564/529, loss: 0.051761530339717865
2023-01-23 00:13:30.564052: step: 1568/529, loss: 0.1882733553647995
2023-01-23 00:13:31.654493: step: 1572/529, loss: 0.5648950338363647
2023-01-23 00:13:32.772067: step: 1576/529, loss: 0.22642555832862854
2023-01-23 00:13:33.888491: step: 1580/529, loss: 0.046761300414800644
2023-01-23 00:13:34.991049: step: 1584/529, loss: 0.23881873488426208
2023-01-23 00:13:36.081917: step: 1588/529, loss: 0.4894735813140869
2023-01-23 00:13:37.185457: step: 1592/529, loss: 0.18804016709327698
2023-01-23 00:13:38.278788: step: 1596/529, loss: 0.6195987462997437
2023-01-23 00:13:39.417637: step: 1600/529, loss: 0.22057685256004333
2023-01-23 00:13:40.541158: step: 1604/529, loss: 0.08101234585046768
2023-01-23 00:13:41.660859: step: 1608/529, loss: 0.626783013343811
2023-01-23 00:13:42.782217: step: 1612/529, loss: 0.03388338163495064
2023-01-23 00:13:43.933286: step: 1616/529, loss: 0.2831869125366211
2023-01-23 00:13:45.035474: step: 1620/529, loss: 0.07124157249927521
2023-01-23 00:13:46.140946: step: 1624/529, loss: 0.6699535250663757
2023-01-23 00:13:47.264056: step: 1628/529, loss: 0.022092128172516823
2023-01-23 00:13:48.354439: step: 1632/529, loss: 0.09064579010009766
2023-01-23 00:13:49.472163: step: 1636/529, loss: 0.0951623022556305
2023-01-23 00:13:50.583509: step: 1640/529, loss: 0.2127547264099121
2023-01-23 00:13:51.700511: step: 1644/529, loss: 0.16088123619556427
2023-01-23 00:13:52.815805: step: 1648/529, loss: 0.6161696910858154
2023-01-23 00:13:53.912293: step: 1652/529, loss: 0.12120532989501953
2023-01-23 00:13:55.041326: step: 1656/529, loss: 1.0246459245681763
2023-01-23 00:13:56.156358: step: 1660/529, loss: 0.05651235580444336
2023-01-23 00:13:57.262889: step: 1664/529, loss: 0.9207844734191895
2023-01-23 00:13:58.350983: step: 1668/529, loss: 0.1448526382446289
2023-01-23 00:13:59.476695: step: 1672/529, loss: 0.08858537673950195
2023-01-23 00:14:00.618424: step: 1676/529, loss: 0.386136919260025
2023-01-23 00:14:01.706157: step: 1680/529, loss: 0.18111905455589294
2023-01-23 00:14:02.804494: step: 1684/529, loss: 0.17898598313331604
2023-01-23 00:14:03.924117: step: 1688/529, loss: 0.21989670395851135
2023-01-23 00:14:05.039049: step: 1692/529, loss: 0.031917523592710495
2023-01-23 00:14:06.121072: step: 1696/529, loss: 0.061630867421627045
2023-01-23 00:14:07.238772: step: 1700/529, loss: 0.17774944007396698
2023-01-23 00:14:08.349201: step: 1704/529, loss: 0.13025054335594177
2023-01-23 00:14:09.445990: step: 1708/529, loss: 0.10247235000133514
2023-01-23 00:14:10.575125: step: 1712/529, loss: 0.21328100562095642
2023-01-23 00:14:11.688170: step: 1716/529, loss: 0.11350855231285095
2023-01-23 00:14:12.814867: step: 1720/529, loss: 0.18481570482254028
2023-01-23 00:14:13.934980: step: 1724/529, loss: 0.7798261642456055
2023-01-23 00:14:15.036079: step: 1728/529, loss: 0.05474729463458061
2023-01-23 00:14:16.125918: step: 1732/529, loss: 0.2823188304901123
2023-01-23 00:14:17.227184: step: 1736/529, loss: 0.5540623664855957
2023-01-23 00:14:18.357307: step: 1740/529, loss: 0.34217938780784607
2023-01-23 00:14:19.477384: step: 1744/529, loss: 4.49744176864624
2023-01-23 00:14:20.584909: step: 1748/529, loss: 0.1192934513092041
2023-01-23 00:14:21.688308: step: 1752/529, loss: 0.1877593994140625
2023-01-23 00:14:22.811186: step: 1756/529, loss: 0.17658326029777527
2023-01-23 00:14:23.901238: step: 1760/529, loss: 0.2475995123386383
2023-01-23 00:14:24.986636: step: 1764/529, loss: 0.41121023893356323
2023-01-23 00:14:26.085665: step: 1768/529, loss: 2.9980592727661133
2023-01-23 00:14:27.165720: step: 1772/529, loss: 0.286930650472641
2023-01-23 00:14:28.263629: step: 1776/529, loss: 0.16938361525535583
2023-01-23 00:14:29.371679: step: 1780/529, loss: 0.05066043138504028
2023-01-23 00:14:30.481391: step: 1784/529, loss: 0.33080074191093445
2023-01-23 00:14:31.580425: step: 1788/529, loss: 0.23414728045463562
2023-01-23 00:14:32.673531: step: 1792/529, loss: 0.2902383804321289
2023-01-23 00:14:33.781048: step: 1796/529, loss: 0.2578304409980774
2023-01-23 00:14:34.887897: step: 1800/529, loss: 0.41495877504348755
2023-01-23 00:14:36.026944: step: 1804/529, loss: 0.24060077965259552
2023-01-23 00:14:37.149626: step: 1808/529, loss: 0.147386834025383
2023-01-23 00:14:38.278270: step: 1812/529, loss: 0.054194070398807526
2023-01-23 00:14:39.390474: step: 1816/529, loss: 0.054935719817876816
2023-01-23 00:14:40.498779: step: 1820/529, loss: 0.45009851455688477
2023-01-23 00:14:41.631758: step: 1824/529, loss: 0.186998188495636
2023-01-23 00:14:42.741508: step: 1828/529, loss: 0.48846301436424255
2023-01-23 00:14:43.826989: step: 1832/529, loss: 0.11444559693336487
2023-01-23 00:14:44.937145: step: 1836/529, loss: 0.1369856894016266
2023-01-23 00:14:46.056508: step: 1840/529, loss: 0.22920675575733185
2023-01-23 00:14:47.161330: step: 1844/529, loss: 0.12228593975305557
2023-01-23 00:14:48.254764: step: 1848/529, loss: 0.12914076447486877
2023-01-23 00:14:49.349751: step: 1852/529, loss: 0.06727103888988495
2023-01-23 00:14:50.461739: step: 1856/529, loss: 0.25102242827415466
2023-01-23 00:14:51.584329: step: 1860/529, loss: 0.07208700478076935
2023-01-23 00:14:52.679007: step: 1864/529, loss: 0.3147136867046356
2023-01-23 00:14:53.773747: step: 1868/529, loss: 0.11604194343090057
2023-01-23 00:14:54.876798: step: 1872/529, loss: 0.16825714707374573
2023-01-23 00:14:56.017543: step: 1876/529, loss: 0.5729438066482544
2023-01-23 00:14:57.121499: step: 1880/529, loss: 0.02032341994345188
2023-01-23 00:14:58.215058: step: 1884/529, loss: 1.2662216424942017
2023-01-23 00:14:59.311422: step: 1888/529, loss: 0.09326568245887756
2023-01-23 00:15:00.428684: step: 1892/529, loss: 0.16760015487670898
2023-01-23 00:15:01.529683: step: 1896/529, loss: 0.07247710227966309
2023-01-23 00:15:02.655253: step: 1900/529, loss: 0.06102919578552246
2023-01-23 00:15:03.798329: step: 1904/529, loss: 0.1514964997768402
2023-01-23 00:15:04.887670: step: 1908/529, loss: 0.04268374666571617
2023-01-23 00:15:06.006336: step: 1912/529, loss: 0.09840288758277893
2023-01-23 00:15:07.104235: step: 1916/529, loss: 0.3508193790912628
2023-01-23 00:15:08.204686: step: 1920/529, loss: 0.06758122891187668
2023-01-23 00:15:09.312383: step: 1924/529, loss: 0.21594581007957458
2023-01-23 00:15:10.422846: step: 1928/529, loss: 0.14001736044883728
2023-01-23 00:15:11.526233: step: 1932/529, loss: 0.06528887897729874
2023-01-23 00:15:12.641434: step: 1936/529, loss: 0.22349201142787933
2023-01-23 00:15:13.728816: step: 1940/529, loss: 0.10970593243837357
2023-01-23 00:15:14.893622: step: 1944/529, loss: 0.7762815952301025
2023-01-23 00:15:15.990294: step: 1948/529, loss: 0.15965993702411652
2023-01-23 00:15:17.089945: step: 1952/529, loss: 0.3056747317314148
2023-01-23 00:15:18.202384: step: 1956/529, loss: 0.5440365672111511
2023-01-23 00:15:19.304061: step: 1960/529, loss: 0.11164084076881409
2023-01-23 00:15:20.407832: step: 1964/529, loss: 0.2548164427280426
2023-01-23 00:15:21.540589: step: 1968/529, loss: 0.14545422792434692
2023-01-23 00:15:22.641251: step: 1972/529, loss: 4.151213645935059
2023-01-23 00:15:23.741835: step: 1976/529, loss: 0.49384671449661255
2023-01-23 00:15:24.869676: step: 1980/529, loss: 0.13706551492214203
2023-01-23 00:15:25.974947: step: 1984/529, loss: 0.2585916519165039
2023-01-23 00:15:27.068901: step: 1988/529, loss: 0.12723436951637268
2023-01-23 00:15:28.170018: step: 1992/529, loss: 0.19709739089012146
2023-01-23 00:15:29.266370: step: 1996/529, loss: 0.4232083559036255
2023-01-23 00:15:30.377857: step: 2000/529, loss: 0.20833492279052734
2023-01-23 00:15:31.530050: step: 2004/529, loss: 0.6804494261741638
2023-01-23 00:15:32.661590: step: 2008/529, loss: 0.30604103207588196
2023-01-23 00:15:33.761274: step: 2012/529, loss: 4.064002990722656
2023-01-23 00:15:34.900875: step: 2016/529, loss: 0.3089672327041626
2023-01-23 00:15:36.002997: step: 2020/529, loss: 0.07604637742042542
2023-01-23 00:15:37.129743: step: 2024/529, loss: 0.1061973124742508
2023-01-23 00:15:38.254661: step: 2028/529, loss: 0.22420406341552734
2023-01-23 00:15:39.377580: step: 2032/529, loss: 0.2828930914402008
2023-01-23 00:15:40.538002: step: 2036/529, loss: 0.055702365934848785
2023-01-23 00:15:41.635549: step: 2040/529, loss: 0.1882980465888977
2023-01-23 00:15:42.757645: step: 2044/529, loss: 0.3381475806236267
2023-01-23 00:15:43.874080: step: 2048/529, loss: 0.34776657819747925
2023-01-23 00:15:44.993477: step: 2052/529, loss: 0.16548840701580048
2023-01-23 00:15:46.099640: step: 2056/529, loss: 0.27984774112701416
2023-01-23 00:15:47.234871: step: 2060/529, loss: 0.21640339493751526
2023-01-23 00:15:48.344179: step: 2064/529, loss: 0.03279542922973633
2023-01-23 00:15:49.468877: step: 2068/529, loss: 0.4831317067146301
2023-01-23 00:15:50.593410: step: 2072/529, loss: 0.13899001479148865
2023-01-23 00:15:51.706163: step: 2076/529, loss: 0.08098659664392471
2023-01-23 00:15:52.804762: step: 2080/529, loss: 0.23954276740550995
2023-01-23 00:15:53.924621: step: 2084/529, loss: 4.100245952606201
2023-01-23 00:15:55.041028: step: 2088/529, loss: 0.153880313038826
2023-01-23 00:15:56.182488: step: 2092/529, loss: 0.20263110101222992
2023-01-23 00:15:57.294807: step: 2096/529, loss: 0.5009497404098511
2023-01-23 00:15:58.423180: step: 2100/529, loss: 0.07189646363258362
2023-01-23 00:15:59.549761: step: 2104/529, loss: 0.2859005928039551
2023-01-23 00:16:00.705747: step: 2108/529, loss: 0.5420616269111633
2023-01-23 00:16:01.825712: step: 2112/529, loss: 0.10264568030834198
2023-01-23 00:16:02.965506: step: 2116/529, loss: 2.240382194519043
==================================================
Loss: 0.406
--------------------
Dev: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.5, 'r': 0.8703703703703703, 'f1': 0.6351351351351352}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.453125, 'r': 0.4603174603174603, 'f1': 0.4566929133858268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5572815533980583, 'r': 0.7643142476697736, 'f1': 0.6445816956765862}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.5485519591141397, 'r': 0.7268623024830699, 'f1': 0.6252427184466018}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.7111111111111111, 'r': 0.5079365079365079, 'f1': 0.5925925925925924}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:16:48.560226: step: 4/529, loss: 0.07176800072193146
2023-01-23 00:16:49.751804: step: 8/529, loss: 0.48882177472114563
2023-01-23 00:16:50.858344: step: 12/529, loss: 0.08888855576515198
2023-01-23 00:16:51.963253: step: 16/529, loss: 0.12938714027404785
2023-01-23 00:16:53.064890: step: 20/529, loss: 0.46757346391677856
2023-01-23 00:16:54.157103: step: 24/529, loss: 0.34735241532325745
2023-01-23 00:16:55.249443: step: 28/529, loss: 4.39654541015625
2023-01-23 00:16:56.349844: step: 32/529, loss: 0.07400093227624893
2023-01-23 00:16:57.437149: step: 36/529, loss: 0.2866958677768707
2023-01-23 00:16:58.533588: step: 40/529, loss: 0.11702385544776917
2023-01-23 00:16:59.666928: step: 44/529, loss: 0.6336420774459839
2023-01-23 00:17:00.771844: step: 48/529, loss: 0.3022029995918274
2023-01-23 00:17:01.937227: step: 52/529, loss: 0.2538001239299774
2023-01-23 00:17:03.039751: step: 56/529, loss: 0.09459337592124939
2023-01-23 00:17:04.150087: step: 60/529, loss: 0.3749246597290039
2023-01-23 00:17:05.262565: step: 64/529, loss: 0.09169311821460724
2023-01-23 00:17:06.370244: step: 68/529, loss: 0.26982012391090393
2023-01-23 00:17:07.498373: step: 72/529, loss: 2.723605155944824
2023-01-23 00:17:08.647102: step: 76/529, loss: 0.26373690366744995
2023-01-23 00:17:09.759882: step: 80/529, loss: 0.16915054619312286
2023-01-23 00:17:10.876286: step: 84/529, loss: 0.13807296752929688
2023-01-23 00:17:11.992102: step: 88/529, loss: 0.1197231262922287
2023-01-23 00:17:13.106693: step: 92/529, loss: 0.12036142498254776
2023-01-23 00:17:14.202274: step: 96/529, loss: 0.09978790581226349
2023-01-23 00:17:15.314792: step: 100/529, loss: 0.05086259916424751
2023-01-23 00:17:16.396265: step: 104/529, loss: 0.11878304183483124
2023-01-23 00:17:17.494109: step: 108/529, loss: 0.30495673418045044
2023-01-23 00:17:18.603168: step: 112/529, loss: 0.15193353593349457
2023-01-23 00:17:19.718671: step: 116/529, loss: 0.032694898545742035
2023-01-23 00:17:20.804077: step: 120/529, loss: 0.07092676311731339
2023-01-23 00:17:21.918581: step: 124/529, loss: 0.36928021907806396
2023-01-23 00:17:23.024554: step: 128/529, loss: 0.24337291717529297
2023-01-23 00:17:24.124804: step: 132/529, loss: 0.15207695960998535
2023-01-23 00:17:25.254138: step: 136/529, loss: 0.04180867597460747
2023-01-23 00:17:26.370840: step: 140/529, loss: 0.33201128244400024
2023-01-23 00:17:27.459179: step: 144/529, loss: 0.11735763400793076
2023-01-23 00:17:28.549765: step: 148/529, loss: 0.038109827786684036
2023-01-23 00:17:29.658399: step: 152/529, loss: 0.15805473923683167
2023-01-23 00:17:30.772703: step: 156/529, loss: 0.10979817807674408
2023-01-23 00:17:31.892143: step: 160/529, loss: 0.1887872815132141
2023-01-23 00:17:33.008971: step: 164/529, loss: 0.06425094604492188
2023-01-23 00:17:34.110771: step: 168/529, loss: 0.10059285163879395
2023-01-23 00:17:35.247836: step: 172/529, loss: 0.25150051712989807
2023-01-23 00:17:36.353186: step: 176/529, loss: 0.08196024596691132
2023-01-23 00:17:37.488891: step: 180/529, loss: 0.5017951130867004
2023-01-23 00:17:38.601628: step: 184/529, loss: 0.3754850924015045
2023-01-23 00:17:39.714234: step: 188/529, loss: 0.49523216485977173
2023-01-23 00:17:40.813347: step: 192/529, loss: 0.052175380289554596
2023-01-23 00:17:41.918487: step: 196/529, loss: 0.310914546251297
2023-01-23 00:17:43.030036: step: 200/529, loss: 0.11522388458251953
2023-01-23 00:17:44.142916: step: 204/529, loss: 0.048056744039058685
2023-01-23 00:17:45.222354: step: 208/529, loss: 0.06516657024621964
2023-01-23 00:17:46.310995: step: 212/529, loss: 0.1264423429965973
2023-01-23 00:17:47.428464: step: 216/529, loss: 0.08873319625854492
2023-01-23 00:17:48.524813: step: 220/529, loss: 0.06373219192028046
2023-01-23 00:17:49.652749: step: 224/529, loss: 0.1512037217617035
2023-01-23 00:17:50.763990: step: 228/529, loss: 0.20380745828151703
2023-01-23 00:17:51.859025: step: 232/529, loss: 0.08971276879310608
2023-01-23 00:17:52.986808: step: 236/529, loss: 1.130300760269165
2023-01-23 00:17:54.091589: step: 240/529, loss: 0.2372211068868637
2023-01-23 00:17:55.185689: step: 244/529, loss: 0.38963738083839417
2023-01-23 00:17:56.292139: step: 248/529, loss: 0.11961832642555237
2023-01-23 00:17:57.414647: step: 252/529, loss: 0.11456408351659775
2023-01-23 00:17:58.581435: step: 256/529, loss: 0.4340522885322571
2023-01-23 00:17:59.679122: step: 260/529, loss: 0.4952842593193054
2023-01-23 00:18:00.782729: step: 264/529, loss: 1.0062696933746338
2023-01-23 00:18:01.878749: step: 268/529, loss: 0.31698256731033325
2023-01-23 00:18:02.971320: step: 272/529, loss: 0.033536337316036224
2023-01-23 00:18:04.067847: step: 276/529, loss: 0.14295777678489685
2023-01-23 00:18:05.193645: step: 280/529, loss: 0.06467914581298828
2023-01-23 00:18:06.295616: step: 284/529, loss: 0.2953764498233795
2023-01-23 00:18:07.412421: step: 288/529, loss: 0.17570915818214417
2023-01-23 00:18:08.506393: step: 292/529, loss: 0.04101882129907608
2023-01-23 00:18:09.630866: step: 296/529, loss: 0.23953105509281158
2023-01-23 00:18:10.762944: step: 300/529, loss: 0.27949273586273193
2023-01-23 00:18:11.855919: step: 304/529, loss: 0.008367824368178844
2023-01-23 00:18:12.977937: step: 308/529, loss: 0.23857679963111877
2023-01-23 00:18:14.087742: step: 312/529, loss: 0.24934254586696625
2023-01-23 00:18:15.184357: step: 316/529, loss: 0.6869691610336304
2023-01-23 00:18:16.319801: step: 320/529, loss: 0.09876394271850586
2023-01-23 00:18:17.437724: step: 324/529, loss: 0.2421676218509674
2023-01-23 00:18:18.548738: step: 328/529, loss: 0.37847620248794556
2023-01-23 00:18:19.663179: step: 332/529, loss: 0.15747416019439697
2023-01-23 00:18:20.772723: step: 336/529, loss: 0.1132832020521164
2023-01-23 00:18:21.874750: step: 340/529, loss: 0.5885408520698547
2023-01-23 00:18:22.975083: step: 344/529, loss: 0.2205224484205246
2023-01-23 00:18:24.061916: step: 348/529, loss: 0.366557776927948
2023-01-23 00:18:25.184075: step: 352/529, loss: 0.1642545759677887
2023-01-23 00:18:26.298247: step: 356/529, loss: 0.2124018669128418
2023-01-23 00:18:27.427380: step: 360/529, loss: 0.148661807179451
2023-01-23 00:18:28.543118: step: 364/529, loss: 1.1682111024856567
2023-01-23 00:18:29.644481: step: 368/529, loss: 0.12335072457790375
2023-01-23 00:18:30.756479: step: 372/529, loss: 0.025620698928833008
2023-01-23 00:18:31.867241: step: 376/529, loss: 0.05413227155804634
2023-01-23 00:18:32.976472: step: 380/529, loss: 0.16415753960609436
2023-01-23 00:18:34.074339: step: 384/529, loss: 0.18194541335105896
2023-01-23 00:18:35.188983: step: 388/529, loss: 0.43905311822891235
2023-01-23 00:18:36.294231: step: 392/529, loss: 0.0664089173078537
2023-01-23 00:18:37.408898: step: 396/529, loss: 0.5605072975158691
2023-01-23 00:18:38.501043: step: 400/529, loss: 0.4242580533027649
2023-01-23 00:18:39.599131: step: 404/529, loss: 0.246148020029068
2023-01-23 00:18:40.764144: step: 408/529, loss: 0.4521218240261078
2023-01-23 00:18:41.874330: step: 412/529, loss: 0.1906055510044098
2023-01-23 00:18:42.992236: step: 416/529, loss: 0.21712461113929749
2023-01-23 00:18:44.120461: step: 420/529, loss: 1.8412694931030273
2023-01-23 00:18:45.224498: step: 424/529, loss: 1.2602217197418213
2023-01-23 00:18:46.343170: step: 428/529, loss: 0.495075523853302
2023-01-23 00:18:47.464699: step: 432/529, loss: 0.2181301862001419
2023-01-23 00:18:48.583584: step: 436/529, loss: 0.10174522548913956
2023-01-23 00:18:49.707028: step: 440/529, loss: 0.36892640590667725
2023-01-23 00:18:50.841899: step: 444/529, loss: 0.7357617616653442
2023-01-23 00:18:52.010765: step: 448/529, loss: 0.19989554584026337
2023-01-23 00:18:53.142510: step: 452/529, loss: 0.38063403964042664
2023-01-23 00:18:54.252842: step: 456/529, loss: 0.8308342099189758
2023-01-23 00:18:55.364946: step: 460/529, loss: 0.2380828857421875
2023-01-23 00:18:56.489160: step: 464/529, loss: 0.04858918488025665
2023-01-23 00:18:57.620368: step: 468/529, loss: 0.1345197707414627
2023-01-23 00:18:58.785554: step: 472/529, loss: 0.24324941635131836
2023-01-23 00:18:59.888721: step: 476/529, loss: 0.17164115607738495
2023-01-23 00:19:01.031207: step: 480/529, loss: 0.31392115354537964
2023-01-23 00:19:02.176110: step: 484/529, loss: 0.3716011643409729
2023-01-23 00:19:03.268750: step: 488/529, loss: 0.07454583793878555
2023-01-23 00:19:04.391533: step: 492/529, loss: 0.3151795268058777
2023-01-23 00:19:05.461675: step: 496/529, loss: 0.126824289560318
2023-01-23 00:19:06.570259: step: 500/529, loss: 1.211808443069458
2023-01-23 00:19:07.673353: step: 504/529, loss: 0.16941985487937927
2023-01-23 00:19:08.771543: step: 508/529, loss: 0.05509186163544655
2023-01-23 00:19:09.881636: step: 512/529, loss: 0.1899217665195465
2023-01-23 00:19:10.991810: step: 516/529, loss: 0.10406293720006943
2023-01-23 00:19:12.087973: step: 520/529, loss: 0.20110595226287842
2023-01-23 00:19:13.219629: step: 524/529, loss: 0.32373762130737305
2023-01-23 00:19:14.324052: step: 528/529, loss: 0.963670015335083
2023-01-23 00:19:15.445184: step: 532/529, loss: 0.1061980202794075
2023-01-23 00:19:16.582700: step: 536/529, loss: 0.25688838958740234
2023-01-23 00:19:17.678767: step: 540/529, loss: 0.08908119052648544
2023-01-23 00:19:18.805349: step: 544/529, loss: 0.09998014569282532
2023-01-23 00:19:19.909333: step: 548/529, loss: 0.05474138259887695
2023-01-23 00:19:21.020151: step: 552/529, loss: 0.16262155771255493
2023-01-23 00:19:22.124064: step: 556/529, loss: 0.04006953164935112
2023-01-23 00:19:23.223555: step: 560/529, loss: 0.15252971649169922
2023-01-23 00:19:24.359336: step: 564/529, loss: 0.16855831444263458
2023-01-23 00:19:25.473889: step: 568/529, loss: 0.23425331711769104
2023-01-23 00:19:26.589856: step: 572/529, loss: 0.12185021489858627
2023-01-23 00:19:27.731772: step: 576/529, loss: 0.09067702293395996
2023-01-23 00:19:28.860977: step: 580/529, loss: 0.23523512482643127
2023-01-23 00:19:29.976410: step: 584/529, loss: 0.19013480842113495
2023-01-23 00:19:31.110413: step: 588/529, loss: 0.030865196138620377
2023-01-23 00:19:32.245622: step: 592/529, loss: 0.014112567529082298
2023-01-23 00:19:33.352719: step: 596/529, loss: 0.2811559736728668
2023-01-23 00:19:34.481184: step: 600/529, loss: 0.13876524567604065
2023-01-23 00:19:35.591183: step: 604/529, loss: 0.11205069720745087
2023-01-23 00:19:36.700372: step: 608/529, loss: 0.45882484316825867
2023-01-23 00:19:37.810131: step: 612/529, loss: 0.46615585684776306
2023-01-23 00:19:38.932017: step: 616/529, loss: 0.1883348524570465
2023-01-23 00:19:40.037925: step: 620/529, loss: 0.15784187614917755
2023-01-23 00:19:41.158525: step: 624/529, loss: 0.1897747963666916
2023-01-23 00:19:42.285175: step: 628/529, loss: 0.05434370040893555
2023-01-23 00:19:43.413903: step: 632/529, loss: 0.7836352586746216
2023-01-23 00:19:44.521666: step: 636/529, loss: 0.039287567138671875
2023-01-23 00:19:45.671640: step: 640/529, loss: 0.06502513587474823
2023-01-23 00:19:46.824410: step: 644/529, loss: 0.9671511054039001
2023-01-23 00:19:47.968527: step: 648/529, loss: 0.10725164413452148
2023-01-23 00:19:49.097870: step: 652/529, loss: 0.26869791746139526
2023-01-23 00:19:50.282906: step: 656/529, loss: 0.050656892359256744
2023-01-23 00:19:51.438095: step: 660/529, loss: 0.19444340467453003
2023-01-23 00:19:52.536078: step: 664/529, loss: 0.09351330250501633
2023-01-23 00:19:53.630468: step: 668/529, loss: 0.6219432950019836
2023-01-23 00:19:54.764296: step: 672/529, loss: 0.16720303893089294
2023-01-23 00:19:55.873624: step: 676/529, loss: 0.628582239151001
2023-01-23 00:19:56.996997: step: 680/529, loss: 4.476847171783447
2023-01-23 00:19:58.101694: step: 684/529, loss: 0.14616942405700684
2023-01-23 00:19:59.191045: step: 688/529, loss: 0.07479887455701828
2023-01-23 00:20:00.295885: step: 692/529, loss: 0.1100873053073883
2023-01-23 00:20:01.390196: step: 696/529, loss: 0.107672318816185
2023-01-23 00:20:02.492303: step: 700/529, loss: 0.13694247603416443
2023-01-23 00:20:03.587446: step: 704/529, loss: 1.302291750907898
2023-01-23 00:20:04.738497: step: 708/529, loss: 0.23167285323143005
2023-01-23 00:20:05.835007: step: 712/529, loss: 0.38994550704956055
2023-01-23 00:20:06.955784: step: 716/529, loss: 0.003508281661197543
2023-01-23 00:20:08.055890: step: 720/529, loss: 2.912047863006592
2023-01-23 00:20:09.165786: step: 724/529, loss: 0.22274373471736908
2023-01-23 00:20:10.294779: step: 728/529, loss: 0.8981214761734009
2023-01-23 00:20:11.431103: step: 732/529, loss: 0.16637632250785828
2023-01-23 00:20:12.568335: step: 736/529, loss: 0.8429765701293945
2023-01-23 00:20:13.675396: step: 740/529, loss: 0.14332342147827148
2023-01-23 00:20:14.801126: step: 744/529, loss: 0.9117512106895447
2023-01-23 00:20:15.931141: step: 748/529, loss: 0.8392467498779297
2023-01-23 00:20:17.074824: step: 752/529, loss: 0.287754625082016
2023-01-23 00:20:18.190129: step: 756/529, loss: 0.17760629951953888
2023-01-23 00:20:19.300836: step: 760/529, loss: 0.6325515508651733
2023-01-23 00:20:20.388923: step: 764/529, loss: 0.008400964550673962
2023-01-23 00:20:21.508455: step: 768/529, loss: 0.4714752435684204
2023-01-23 00:20:22.654765: step: 772/529, loss: 0.14944672584533691
2023-01-23 00:20:23.799683: step: 776/529, loss: 0.2023017406463623
2023-01-23 00:20:24.916718: step: 780/529, loss: 0.059515856206417084
2023-01-23 00:20:26.018715: step: 784/529, loss: 0.4514063000679016
2023-01-23 00:20:27.142397: step: 788/529, loss: 3.194371461868286
2023-01-23 00:20:28.248521: step: 792/529, loss: 0.10299444198608398
2023-01-23 00:20:29.365413: step: 796/529, loss: 0.1376463919878006
2023-01-23 00:20:30.482369: step: 800/529, loss: 0.11490288376808167
2023-01-23 00:20:31.616594: step: 804/529, loss: 0.0795622318983078
2023-01-23 00:20:32.724772: step: 808/529, loss: 0.3224641978740692
2023-01-23 00:20:33.823552: step: 812/529, loss: 0.21379882097244263
2023-01-23 00:20:34.930659: step: 816/529, loss: 0.35221731662750244
2023-01-23 00:20:36.016828: step: 820/529, loss: 0.03069133684039116
2023-01-23 00:20:37.127700: step: 824/529, loss: 0.11250162124633789
2023-01-23 00:20:38.250981: step: 828/529, loss: 0.14740753173828125
2023-01-23 00:20:39.366097: step: 832/529, loss: 0.2560974359512329
2023-01-23 00:20:40.467475: step: 836/529, loss: 0.5588887929916382
2023-01-23 00:20:41.574686: step: 840/529, loss: 0.8817388415336609
2023-01-23 00:20:42.700095: step: 844/529, loss: 0.28461599349975586
2023-01-23 00:20:43.783792: step: 848/529, loss: 0.3847476840019226
2023-01-23 00:20:44.884823: step: 852/529, loss: 0.03926238790154457
2023-01-23 00:20:45.998918: step: 856/529, loss: 0.9807325601577759
2023-01-23 00:20:47.109501: step: 860/529, loss: 0.07923221588134766
2023-01-23 00:20:48.213683: step: 864/529, loss: 0.09899359196424484
2023-01-23 00:20:49.335265: step: 868/529, loss: 0.16891708970069885
2023-01-23 00:20:50.442105: step: 872/529, loss: 0.15810136497020721
2023-01-23 00:20:51.539808: step: 876/529, loss: 0.042960025370121
2023-01-23 00:20:52.659624: step: 880/529, loss: 0.05048312991857529
2023-01-23 00:20:53.786648: step: 884/529, loss: 0.21107368171215057
2023-01-23 00:20:54.904859: step: 888/529, loss: 0.07904662936925888
2023-01-23 00:20:56.055186: step: 892/529, loss: 0.2755317687988281
2023-01-23 00:20:57.151720: step: 896/529, loss: 0.14549875259399414
2023-01-23 00:20:58.259544: step: 900/529, loss: 0.20205456018447876
2023-01-23 00:20:59.381743: step: 904/529, loss: 0.5239003896713257
2023-01-23 00:21:00.492492: step: 908/529, loss: 0.17224177718162537
2023-01-23 00:21:01.637978: step: 912/529, loss: 0.06187457963824272
2023-01-23 00:21:02.711200: step: 916/529, loss: 0.12379169464111328
2023-01-23 00:21:03.803082: step: 920/529, loss: 0.11094065010547638
2023-01-23 00:21:04.916766: step: 924/529, loss: 0.2921140789985657
2023-01-23 00:21:06.004874: step: 928/529, loss: 0.7407182455062866
2023-01-23 00:21:07.111087: step: 932/529, loss: 0.336601585149765
2023-01-23 00:21:08.244427: step: 936/529, loss: 0.07369747757911682
2023-01-23 00:21:09.360883: step: 940/529, loss: 0.13514146208763123
2023-01-23 00:21:10.467454: step: 944/529, loss: 0.16474317014217377
2023-01-23 00:21:11.552447: step: 948/529, loss: 0.024876069277524948
2023-01-23 00:21:12.646249: step: 952/529, loss: 0.9385433197021484
2023-01-23 00:21:13.751639: step: 956/529, loss: 0.02317180670797825
2023-01-23 00:21:14.857502: step: 960/529, loss: 1.1053519248962402
2023-01-23 00:21:15.953652: step: 964/529, loss: 0.011385440826416016
2023-01-23 00:21:17.077260: step: 968/529, loss: 0.11097273975610733
2023-01-23 00:21:18.186146: step: 972/529, loss: 0.4098798334598541
2023-01-23 00:21:19.301326: step: 976/529, loss: 0.31534457206726074
2023-01-23 00:21:20.406384: step: 980/529, loss: 0.021639680489897728
2023-01-23 00:21:21.510054: step: 984/529, loss: 0.252638578414917
2023-01-23 00:21:22.630709: step: 988/529, loss: 0.14069929718971252
2023-01-23 00:21:23.753049: step: 992/529, loss: 0.18577317893505096
2023-01-23 00:21:24.847502: step: 996/529, loss: 0.7731400728225708
2023-01-23 00:21:25.946298: step: 1000/529, loss: 0.979948103427887
2023-01-23 00:21:27.077289: step: 1004/529, loss: 0.2003905326128006
2023-01-23 00:21:28.210192: step: 1008/529, loss: 0.5764471292495728
2023-01-23 00:21:29.320203: step: 1012/529, loss: 0.35344016551971436
2023-01-23 00:21:30.439570: step: 1016/529, loss: 0.10928221046924591
2023-01-23 00:21:31.535860: step: 1020/529, loss: 0.09975261986255646
2023-01-23 00:21:32.629127: step: 1024/529, loss: 0.10154419392347336
2023-01-23 00:21:33.734556: step: 1028/529, loss: 0.36940690875053406
2023-01-23 00:21:34.845202: step: 1032/529, loss: 0.2673810124397278
2023-01-23 00:21:35.989562: step: 1036/529, loss: 0.04351988062262535
2023-01-23 00:21:37.090958: step: 1040/529, loss: 0.8431259393692017
2023-01-23 00:21:38.181845: step: 1044/529, loss: 0.1008274108171463
2023-01-23 00:21:39.310831: step: 1048/529, loss: 0.10504446178674698
2023-01-23 00:21:40.417569: step: 1052/529, loss: 0.3396528363227844
2023-01-23 00:21:41.548797: step: 1056/529, loss: 0.32092055678367615
2023-01-23 00:21:42.661585: step: 1060/529, loss: 2.079563617706299
2023-01-23 00:21:43.751775: step: 1064/529, loss: 0.0264403335750103
2023-01-23 00:21:44.868070: step: 1068/529, loss: 0.08323893696069717
2023-01-23 00:21:45.956958: step: 1072/529, loss: 0.13182954490184784
2023-01-23 00:21:47.064810: step: 1076/529, loss: 0.4027717411518097
2023-01-23 00:21:48.192806: step: 1080/529, loss: 0.1484191119670868
2023-01-23 00:21:49.319101: step: 1084/529, loss: 0.08234620094299316
2023-01-23 00:21:50.415578: step: 1088/529, loss: 1.2295171022415161
2023-01-23 00:21:51.530741: step: 1092/529, loss: 0.17482653260231018
2023-01-23 00:21:52.664117: step: 1096/529, loss: 0.6987869739532471
2023-01-23 00:21:53.790555: step: 1100/529, loss: 0.12622275948524475
2023-01-23 00:21:54.914017: step: 1104/529, loss: 0.1770588457584381
2023-01-23 00:21:56.023708: step: 1108/529, loss: 0.2589738965034485
2023-01-23 00:21:57.155516: step: 1112/529, loss: 0.49493399262428284
2023-01-23 00:21:58.243891: step: 1116/529, loss: 0.14513494074344635
2023-01-23 00:21:59.376872: step: 1120/529, loss: 0.16341623663902283
2023-01-23 00:22:00.460954: step: 1124/529, loss: 0.10604343563318253
2023-01-23 00:22:01.591901: step: 1128/529, loss: 1.788381576538086
2023-01-23 00:22:02.688886: step: 1132/529, loss: 0.11593261361122131
2023-01-23 00:22:03.783214: step: 1136/529, loss: 0.051560401916503906
2023-01-23 00:22:04.891258: step: 1140/529, loss: 0.06905083358287811
2023-01-23 00:22:06.005405: step: 1144/529, loss: 0.2862909436225891
2023-01-23 00:22:07.108203: step: 1148/529, loss: 0.0763545036315918
2023-01-23 00:22:08.200108: step: 1152/529, loss: 0.1487351506948471
2023-01-23 00:22:09.312669: step: 1156/529, loss: 0.07588143646717072
2023-01-23 00:22:10.451854: step: 1160/529, loss: 0.28959304094314575
2023-01-23 00:22:11.563016: step: 1164/529, loss: 0.027448464184999466
2023-01-23 00:22:12.659138: step: 1168/529, loss: 0.1361057311296463
2023-01-23 00:22:13.745748: step: 1172/529, loss: 1.1816768646240234
2023-01-23 00:22:14.869163: step: 1176/529, loss: 0.1459817886352539
2023-01-23 00:22:15.984299: step: 1180/529, loss: 0.4176911413669586
2023-01-23 00:22:17.076940: step: 1184/529, loss: 0.05482196807861328
2023-01-23 00:22:18.157974: step: 1188/529, loss: 0.4296841025352478
2023-01-23 00:22:19.292443: step: 1192/529, loss: 0.08291494846343994
2023-01-23 00:22:20.414677: step: 1196/529, loss: 0.6060510873794556
2023-01-23 00:22:21.520882: step: 1200/529, loss: 0.22685785591602325
2023-01-23 00:22:22.629031: step: 1204/529, loss: 0.25125741958618164
2023-01-23 00:22:23.713012: step: 1208/529, loss: 0.10662183910608292
2023-01-23 00:22:24.846161: step: 1212/529, loss: 0.11419658362865448
2023-01-23 00:22:25.965173: step: 1216/529, loss: 0.11586398631334305
2023-01-23 00:22:27.078373: step: 1220/529, loss: 0.2619855999946594
2023-01-23 00:22:28.243168: step: 1224/529, loss: 0.1439422219991684
2023-01-23 00:22:29.387171: step: 1228/529, loss: 0.7763123512268066
2023-01-23 00:22:30.504365: step: 1232/529, loss: 0.10478439182043076
2023-01-23 00:22:31.611404: step: 1236/529, loss: 0.15502873063087463
2023-01-23 00:22:32.736601: step: 1240/529, loss: 0.21867504715919495
2023-01-23 00:22:33.849189: step: 1244/529, loss: 0.4688391387462616
2023-01-23 00:22:34.930795: step: 1248/529, loss: 0.06149768829345703
2023-01-23 00:22:36.019565: step: 1252/529, loss: 0.12986259162425995
2023-01-23 00:22:37.125177: step: 1256/529, loss: 0.24377644062042236
2023-01-23 00:22:38.282555: step: 1260/529, loss: 0.23835992813110352
2023-01-23 00:22:39.358942: step: 1264/529, loss: 0.03838854283094406
2023-01-23 00:22:40.483095: step: 1268/529, loss: 0.10492667555809021
2023-01-23 00:22:41.597706: step: 1272/529, loss: 0.1702306866645813
2023-01-23 00:22:42.692096: step: 1276/529, loss: 0.3218880891799927
2023-01-23 00:22:43.793302: step: 1280/529, loss: 0.1520165503025055
2023-01-23 00:22:44.914524: step: 1284/529, loss: 0.14958299696445465
2023-01-23 00:22:46.011267: step: 1288/529, loss: 0.08503346145153046
2023-01-23 00:22:47.103319: step: 1292/529, loss: 0.40545588731765747
2023-01-23 00:22:48.208384: step: 1296/529, loss: 0.12282752990722656
2023-01-23 00:22:49.300464: step: 1300/529, loss: 0.02224903181195259
2023-01-23 00:22:50.400698: step: 1304/529, loss: 0.18410158157348633
2023-01-23 00:22:51.507845: step: 1308/529, loss: 0.06564927101135254
2023-01-23 00:22:52.614647: step: 1312/529, loss: 0.16934624314308167
2023-01-23 00:22:53.688623: step: 1316/529, loss: 0.04940595477819443
2023-01-23 00:22:54.805717: step: 1320/529, loss: 0.1700696051120758
2023-01-23 00:22:55.919665: step: 1324/529, loss: 0.05648774653673172
2023-01-23 00:22:57.011641: step: 1328/529, loss: 0.21957778930664062
2023-01-23 00:22:58.103616: step: 1332/529, loss: 0.15166538953781128
2023-01-23 00:22:59.275092: step: 1336/529, loss: 0.18586693704128265
2023-01-23 00:23:00.385027: step: 1340/529, loss: 0.3524380624294281
2023-01-23 00:23:01.501266: step: 1344/529, loss: 0.52020663022995
2023-01-23 00:23:02.606739: step: 1348/529, loss: 0.03911638259887695
2023-01-23 00:23:03.703751: step: 1352/529, loss: 0.7306599617004395
2023-01-23 00:23:04.809319: step: 1356/529, loss: 1.309922456741333
2023-01-23 00:23:05.900353: step: 1360/529, loss: 0.661201000213623
2023-01-23 00:23:07.005649: step: 1364/529, loss: 0.2064886838197708
2023-01-23 00:23:08.115019: step: 1368/529, loss: 0.22166918218135834
2023-01-23 00:23:09.247645: step: 1372/529, loss: 0.291122168302536
2023-01-23 00:23:10.382878: step: 1376/529, loss: 1.22531259059906
2023-01-23 00:23:11.485787: step: 1380/529, loss: 0.11571875214576721
2023-01-23 00:23:12.589688: step: 1384/529, loss: 0.18571476638317108
2023-01-23 00:23:13.694473: step: 1388/529, loss: 0.09639438986778259
2023-01-23 00:23:14.775495: step: 1392/529, loss: 0.14718157052993774
2023-01-23 00:23:15.884136: step: 1396/529, loss: 0.320192813873291
2023-01-23 00:23:17.002785: step: 1400/529, loss: 0.40457314252853394
2023-01-23 00:23:18.092252: step: 1404/529, loss: 0.151570126414299
2023-01-23 00:23:19.179435: step: 1408/529, loss: 0.32254552841186523
2023-01-23 00:23:20.288398: step: 1412/529, loss: 0.1903323233127594
2023-01-23 00:23:21.429683: step: 1416/529, loss: 1.7809343338012695
2023-01-23 00:23:22.569242: step: 1420/529, loss: 0.1599511206150055
2023-01-23 00:23:23.691674: step: 1424/529, loss: 0.07046294212341309
2023-01-23 00:23:24.808603: step: 1428/529, loss: 0.3870340883731842
2023-01-23 00:23:25.937631: step: 1432/529, loss: 0.0396091490983963
2023-01-23 00:23:27.035907: step: 1436/529, loss: 0.09298677742481232
2023-01-23 00:23:28.153074: step: 1440/529, loss: 1.5005346536636353
2023-01-23 00:23:29.247782: step: 1444/529, loss: 0.10666771233081818
2023-01-23 00:23:30.346245: step: 1448/529, loss: 0.3341483175754547
2023-01-23 00:23:31.484907: step: 1452/529, loss: 0.2629149556159973
2023-01-23 00:23:32.580046: step: 1456/529, loss: 0.591636061668396
2023-01-23 00:23:33.683315: step: 1460/529, loss: 0.10159340500831604
2023-01-23 00:23:34.793093: step: 1464/529, loss: 0.0817832499742508
2023-01-23 00:23:35.883944: step: 1468/529, loss: 0.12911973893642426
2023-01-23 00:23:36.987662: step: 1472/529, loss: 0.0567837730050087
2023-01-23 00:23:38.105465: step: 1476/529, loss: 0.6025118827819824
2023-01-23 00:23:39.196722: step: 1480/529, loss: 0.13568849861621857
2023-01-23 00:23:40.314644: step: 1484/529, loss: 0.007483577821403742
2023-01-23 00:23:41.421487: step: 1488/529, loss: 0.03460747003555298
2023-01-23 00:23:42.562627: step: 1492/529, loss: 0.0917363166809082
2023-01-23 00:23:43.684464: step: 1496/529, loss: 0.27723801136016846
2023-01-23 00:23:44.770330: step: 1500/529, loss: 0.194269061088562
2023-01-23 00:23:45.876684: step: 1504/529, loss: 0.14470605552196503
2023-01-23 00:23:46.966115: step: 1508/529, loss: 0.04845142737030983
2023-01-23 00:23:48.150738: step: 1512/529, loss: 0.803070068359375
2023-01-23 00:23:49.253518: step: 1516/529, loss: 0.18038225173950195
2023-01-23 00:23:50.364877: step: 1520/529, loss: 0.46802178025245667
2023-01-23 00:23:51.465131: step: 1524/529, loss: 0.1540185958147049
2023-01-23 00:23:52.568860: step: 1528/529, loss: 0.06892995536327362
2023-01-23 00:23:53.657840: step: 1532/529, loss: 0.1509508192539215
2023-01-23 00:23:54.792927: step: 1536/529, loss: 0.08187460899353027
2023-01-23 00:23:55.913541: step: 1540/529, loss: 0.2218642681837082
2023-01-23 00:23:57.010660: step: 1544/529, loss: 0.3623002767562866
2023-01-23 00:23:58.107001: step: 1548/529, loss: 0.3448387384414673
2023-01-23 00:23:59.193816: step: 1552/529, loss: 0.1906498670578003
2023-01-23 00:24:00.307879: step: 1556/529, loss: 0.054180387407541275
2023-01-23 00:24:01.396305: step: 1560/529, loss: 0.06531481444835663
2023-01-23 00:24:02.505856: step: 1564/529, loss: 0.061733536422252655
2023-01-23 00:24:03.593022: step: 1568/529, loss: 0.08037319779396057
2023-01-23 00:24:04.684895: step: 1572/529, loss: 0.16298404335975647
2023-01-23 00:24:05.789025: step: 1576/529, loss: 0.09026866406202316
2023-01-23 00:24:06.903349: step: 1580/529, loss: 0.22508811950683594
2023-01-23 00:24:07.983043: step: 1584/529, loss: 0.3090890049934387
2023-01-23 00:24:09.088183: step: 1588/529, loss: 0.04922962188720703
2023-01-23 00:24:10.217199: step: 1592/529, loss: 0.5558130145072937
2023-01-23 00:24:11.346533: step: 1596/529, loss: 0.1086030900478363
2023-01-23 00:24:12.460486: step: 1600/529, loss: 0.13965165615081787
2023-01-23 00:24:13.572621: step: 1604/529, loss: 0.13384190201759338
2023-01-23 00:24:14.731203: step: 1608/529, loss: 0.6677474975585938
2023-01-23 00:24:15.871758: step: 1612/529, loss: 0.08470864593982697
2023-01-23 00:24:17.001532: step: 1616/529, loss: 0.3861212730407715
2023-01-23 00:24:18.083171: step: 1620/529, loss: 0.1051628589630127
2023-01-23 00:24:19.235889: step: 1624/529, loss: 0.30070409178733826
2023-01-23 00:24:20.367095: step: 1628/529, loss: 0.877350389957428
2023-01-23 00:24:21.502312: step: 1632/529, loss: 2.248197555541992
2023-01-23 00:24:22.610952: step: 1636/529, loss: 0.19142599403858185
2023-01-23 00:24:23.693484: step: 1640/529, loss: 0.15653257071971893
2023-01-23 00:24:24.813969: step: 1644/529, loss: 0.20536357164382935
2023-01-23 00:24:25.926956: step: 1648/529, loss: 0.17358675599098206
2023-01-23 00:24:27.030392: step: 1652/529, loss: 0.17834492027759552
2023-01-23 00:24:28.143522: step: 1656/529, loss: 0.2236747294664383
2023-01-23 00:24:29.246275: step: 1660/529, loss: 0.28338009119033813
2023-01-23 00:24:30.380213: step: 1664/529, loss: 0.19938039779663086
2023-01-23 00:24:31.488284: step: 1668/529, loss: 0.6517542004585266
2023-01-23 00:24:32.612793: step: 1672/529, loss: 0.6286314129829407
2023-01-23 00:24:33.710757: step: 1676/529, loss: 0.10910497605800629
2023-01-23 00:24:34.831814: step: 1680/529, loss: 0.6725395321846008
2023-01-23 00:24:35.947425: step: 1684/529, loss: 0.07103876769542694
2023-01-23 00:24:37.075313: step: 1688/529, loss: 0.8393896818161011
2023-01-23 00:24:38.170721: step: 1692/529, loss: 0.035956382751464844
2023-01-23 00:24:39.272622: step: 1696/529, loss: 0.18945342302322388
2023-01-23 00:24:40.400978: step: 1700/529, loss: 0.040915776044130325
2023-01-23 00:24:41.502563: step: 1704/529, loss: 0.28783971071243286
2023-01-23 00:24:42.624839: step: 1708/529, loss: 0.21551647782325745
2023-01-23 00:24:43.762601: step: 1712/529, loss: 0.3832671046257019
2023-01-23 00:24:44.868419: step: 1716/529, loss: 0.12304279208183289
2023-01-23 00:24:46.009761: step: 1720/529, loss: 0.14177627861499786
2023-01-23 00:24:47.148396: step: 1724/529, loss: 0.16448087990283966
2023-01-23 00:24:48.253407: step: 1728/529, loss: 0.15942887961864471
2023-01-23 00:24:49.333966: step: 1732/529, loss: 0.5898841619491577
2023-01-23 00:24:50.442195: step: 1736/529, loss: 0.33383965492248535
2023-01-23 00:24:51.579362: step: 1740/529, loss: 0.24272727966308594
2023-01-23 00:24:52.677730: step: 1744/529, loss: 0.08787364512681961
2023-01-23 00:24:53.790652: step: 1748/529, loss: 0.6018533706665039
2023-01-23 00:24:54.901225: step: 1752/529, loss: 0.3568808436393738
2023-01-23 00:24:55.976246: step: 1756/529, loss: 0.05798931419849396
2023-01-23 00:24:57.060919: step: 1760/529, loss: 0.24187889695167542
2023-01-23 00:24:58.187123: step: 1764/529, loss: 0.16320466995239258
2023-01-23 00:24:59.321155: step: 1768/529, loss: 0.04443786293268204
2023-01-23 00:25:00.421331: step: 1772/529, loss: 0.0804021805524826
2023-01-23 00:25:01.535407: step: 1776/529, loss: 0.435655415058136
2023-01-23 00:25:02.668101: step: 1780/529, loss: 0.23417937755584717
2023-01-23 00:25:03.765776: step: 1784/529, loss: 0.10017052292823792
2023-01-23 00:25:04.869345: step: 1788/529, loss: 0.3650458753108978
2023-01-23 00:25:06.013864: step: 1792/529, loss: 0.20216694474220276
2023-01-23 00:25:07.121943: step: 1796/529, loss: 0.15957202017307281
2023-01-23 00:25:08.218885: step: 1800/529, loss: 0.44204607605934143
2023-01-23 00:25:09.321831: step: 1804/529, loss: 0.26193952560424805
2023-01-23 00:25:10.433437: step: 1808/529, loss: 0.38003477454185486
2023-01-23 00:25:11.554445: step: 1812/529, loss: 0.4287465214729309
2023-01-23 00:25:12.646561: step: 1816/529, loss: 0.3446895480155945
2023-01-23 00:25:13.750587: step: 1820/529, loss: 0.053977206349372864
2023-01-23 00:25:14.875606: step: 1824/529, loss: 0.5122342705726624
2023-01-23 00:25:15.970761: step: 1828/529, loss: 0.0634603500366211
2023-01-23 00:25:17.069038: step: 1832/529, loss: 0.10035190731287003
2023-01-23 00:25:18.197004: step: 1836/529, loss: 0.032689858227968216
2023-01-23 00:25:19.311026: step: 1840/529, loss: 1.1659190654754639
2023-01-23 00:25:20.407324: step: 1844/529, loss: 0.16175565123558044
2023-01-23 00:25:21.525360: step: 1848/529, loss: 0.006393528077751398
2023-01-23 00:25:22.642977: step: 1852/529, loss: 0.9888699054718018
2023-01-23 00:25:23.769413: step: 1856/529, loss: 0.13269320130348206
2023-01-23 00:25:24.892320: step: 1860/529, loss: 0.45847225189208984
2023-01-23 00:25:25.976278: step: 1864/529, loss: 0.5527905821800232
2023-01-23 00:25:27.098012: step: 1868/529, loss: 0.2132083922624588
2023-01-23 00:25:28.187887: step: 1872/529, loss: 0.049288153648376465
2023-01-23 00:25:29.305679: step: 1876/529, loss: 0.14698143303394318
2023-01-23 00:25:30.422181: step: 1880/529, loss: 0.23518601059913635
2023-01-23 00:25:31.518300: step: 1884/529, loss: 1.0319111347198486
2023-01-23 00:25:32.625088: step: 1888/529, loss: 0.029146291315555573
2023-01-23 00:25:33.751913: step: 1892/529, loss: 0.5506752729415894
2023-01-23 00:25:34.848712: step: 1896/529, loss: 0.3898093104362488
2023-01-23 00:25:35.955856: step: 1900/529, loss: 0.059124141931533813
2023-01-23 00:25:37.093607: step: 1904/529, loss: 0.04013986885547638
2023-01-23 00:25:38.219030: step: 1908/529, loss: 0.06953268498182297
2023-01-23 00:25:39.319742: step: 1912/529, loss: 0.1196565181016922
2023-01-23 00:25:40.474712: step: 1916/529, loss: 0.7917718887329102
2023-01-23 00:25:41.582552: step: 1920/529, loss: 0.1666768193244934
2023-01-23 00:25:42.662569: step: 1924/529, loss: 0.13419543206691742
2023-01-23 00:25:43.774772: step: 1928/529, loss: 0.3345470130443573
2023-01-23 00:25:44.893585: step: 1932/529, loss: 0.25586605072021484
2023-01-23 00:25:46.009357: step: 1936/529, loss: 0.12137804180383682
2023-01-23 00:25:47.147372: step: 1940/529, loss: 1.7105233669281006
2023-01-23 00:25:48.271050: step: 1944/529, loss: 0.25304508209228516
2023-01-23 00:25:49.389999: step: 1948/529, loss: 0.2101493626832962
2023-01-23 00:25:50.548628: step: 1952/529, loss: 0.22466516494750977
2023-01-23 00:25:51.652926: step: 1956/529, loss: 0.1067010909318924
2023-01-23 00:25:52.775961: step: 1960/529, loss: 0.08519849926233292
2023-01-23 00:25:53.874115: step: 1964/529, loss: 0.13402409851551056
2023-01-23 00:25:54.969655: step: 1968/529, loss: 0.06219963729381561
2023-01-23 00:25:56.116249: step: 1972/529, loss: 1.2101415395736694
2023-01-23 00:25:57.223546: step: 1976/529, loss: 0.0624537467956543
2023-01-23 00:25:58.341658: step: 1980/529, loss: 0.05861020088195801
2023-01-23 00:25:59.466723: step: 1984/529, loss: 0.573178768157959
2023-01-23 00:26:00.577936: step: 1988/529, loss: 0.5627970099449158
2023-01-23 00:26:01.719673: step: 1992/529, loss: 0.09205227345228195
2023-01-23 00:26:02.838158: step: 1996/529, loss: 0.27253830432891846
2023-01-23 00:26:03.957709: step: 2000/529, loss: 0.1250534951686859
2023-01-23 00:26:05.086071: step: 2004/529, loss: 0.09731898456811905
2023-01-23 00:26:06.199712: step: 2008/529, loss: 0.2533365488052368
2023-01-23 00:26:07.329393: step: 2012/529, loss: 0.13066311180591583
2023-01-23 00:26:08.478430: step: 2016/529, loss: 0.3655029535293579
2023-01-23 00:26:09.629126: step: 2020/529, loss: 0.1358109414577484
2023-01-23 00:26:10.762061: step: 2024/529, loss: 0.11143863201141357
2023-01-23 00:26:11.886669: step: 2028/529, loss: 0.14439940452575684
2023-01-23 00:26:13.012895: step: 2032/529, loss: 0.08167238533496857
2023-01-23 00:26:14.108771: step: 2036/529, loss: 0.504469096660614
2023-01-23 00:26:15.241661: step: 2040/529, loss: 0.1421714872121811
2023-01-23 00:26:16.361216: step: 2044/529, loss: 0.3318385183811188
2023-01-23 00:26:17.462594: step: 2048/529, loss: 0.0830760970711708
2023-01-23 00:26:18.569733: step: 2052/529, loss: 0.10016363114118576
2023-01-23 00:26:19.754245: step: 2056/529, loss: 0.27056217193603516
2023-01-23 00:26:20.854069: step: 2060/529, loss: 0.06310959160327911
2023-01-23 00:26:21.971207: step: 2064/529, loss: 0.05799704045057297
2023-01-23 00:26:23.098899: step: 2068/529, loss: 0.2633543014526367
2023-01-23 00:26:24.225480: step: 2072/529, loss: 0.13678884506225586
2023-01-23 00:26:25.319449: step: 2076/529, loss: 0.15997877717018127
2023-01-23 00:26:26.421540: step: 2080/529, loss: 0.10812397301197052
2023-01-23 00:26:27.508226: step: 2084/529, loss: 0.1123078316450119
2023-01-23 00:26:28.633798: step: 2088/529, loss: 0.1491670310497284
2023-01-23 00:26:29.724182: step: 2092/529, loss: 0.07064428180456161
2023-01-23 00:26:30.834502: step: 2096/529, loss: 0.5811355710029602
2023-01-23 00:26:31.940166: step: 2100/529, loss: 0.5360218286514282
2023-01-23 00:26:33.067044: step: 2104/529, loss: 0.09982369095087051
2023-01-23 00:26:34.183473: step: 2108/529, loss: 0.1943781077861786
2023-01-23 00:26:35.277396: step: 2112/529, loss: 0.7589541077613831
2023-01-23 00:26:36.366112: step: 2116/529, loss: 0.042855359613895416
==================================================
Loss: 0.314
--------------------
Dev: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.4222222222222222, 'r': 0.5277777777777778, 'f1': 0.46913580246913583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 6
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:27:22.870253: step: 4/529, loss: 0.41854560375213623
2023-01-23 00:27:23.985571: step: 8/529, loss: 0.2615930736064911
2023-01-23 00:27:25.079201: step: 12/529, loss: 0.12992648780345917
2023-01-23 00:27:26.197877: step: 16/529, loss: 0.1943288892507553
2023-01-23 00:27:27.314695: step: 20/529, loss: 0.14407122135162354
2023-01-23 00:27:28.426054: step: 24/529, loss: 0.20248670876026154
2023-01-23 00:27:29.529936: step: 28/529, loss: 0.08645305782556534
2023-01-23 00:27:30.614166: step: 32/529, loss: 0.12083292752504349
2023-01-23 00:27:31.724074: step: 36/529, loss: 0.17055034637451172
2023-01-23 00:27:32.823479: step: 40/529, loss: 0.11218681931495667
2023-01-23 00:27:33.911743: step: 44/529, loss: 0.040493011474609375
2023-01-23 00:27:35.049961: step: 48/529, loss: 0.09289960563182831
2023-01-23 00:27:36.190192: step: 52/529, loss: 0.349210262298584
2023-01-23 00:27:37.306586: step: 56/529, loss: 0.10196900367736816
2023-01-23 00:27:38.447493: step: 60/529, loss: 0.11311708390712738
2023-01-23 00:27:39.555866: step: 64/529, loss: 0.12583903968334198
2023-01-23 00:27:40.640611: step: 68/529, loss: 0.1280498504638672
2023-01-23 00:27:41.779654: step: 72/529, loss: 0.2826705873012543
2023-01-23 00:27:42.874087: step: 76/529, loss: 0.2821914553642273
2023-01-23 00:27:43.956461: step: 80/529, loss: 0.21954460442066193
2023-01-23 00:27:45.086671: step: 84/529, loss: 0.3892592191696167
2023-01-23 00:27:46.169507: step: 88/529, loss: 0.418751984834671
2023-01-23 00:27:47.274200: step: 92/529, loss: 0.21727648377418518
2023-01-23 00:27:48.375605: step: 96/529, loss: 0.0854133665561676
2023-01-23 00:27:49.472315: step: 100/529, loss: 0.15490931272506714
2023-01-23 00:27:50.562553: step: 104/529, loss: 0.1582166999578476
2023-01-23 00:27:51.657615: step: 108/529, loss: 0.35520878434181213
2023-01-23 00:27:52.786779: step: 112/529, loss: 0.10291080921888351
2023-01-23 00:27:53.891526: step: 116/529, loss: 0.09500789642333984
2023-01-23 00:27:54.987258: step: 120/529, loss: 0.08937511593103409
2023-01-23 00:27:56.130051: step: 124/529, loss: 0.24723386764526367
2023-01-23 00:27:57.224563: step: 128/529, loss: 0.07378844916820526
2023-01-23 00:27:58.326065: step: 132/529, loss: 0.06312823295593262
2023-01-23 00:27:59.436512: step: 136/529, loss: 0.11058712750673294
2023-01-23 00:28:00.543698: step: 140/529, loss: 0.9841111302375793
2023-01-23 00:28:01.684974: step: 144/529, loss: 0.025448037311434746
2023-01-23 00:28:02.770506: step: 148/529, loss: 0.14135445654392242
2023-01-23 00:28:03.887052: step: 152/529, loss: 0.041330672800540924
2023-01-23 00:28:04.968113: step: 156/529, loss: 0.05406588315963745
2023-01-23 00:28:06.073205: step: 160/529, loss: 0.2682167887687683
2023-01-23 00:28:07.195576: step: 164/529, loss: 0.12867975234985352
2023-01-23 00:28:08.283557: step: 168/529, loss: 0.11226129531860352
2023-01-23 00:28:09.404680: step: 172/529, loss: 0.03821101039648056
2023-01-23 00:28:10.519570: step: 176/529, loss: 0.0940001979470253
2023-01-23 00:28:11.655755: step: 180/529, loss: 0.22178764641284943
2023-01-23 00:28:12.751418: step: 184/529, loss: 0.2003268301486969
2023-01-23 00:28:13.891402: step: 188/529, loss: 0.1507258415222168
2023-01-23 00:28:15.023580: step: 192/529, loss: 0.10898199677467346
2023-01-23 00:28:16.129949: step: 196/529, loss: 0.07951474189758301
2023-01-23 00:28:17.232734: step: 200/529, loss: 0.10532769560813904
2023-01-23 00:28:18.340932: step: 204/529, loss: 0.17203585803508759
2023-01-23 00:28:19.469446: step: 208/529, loss: 0.15487423539161682
2023-01-23 00:28:20.587525: step: 212/529, loss: 0.11974792182445526
2023-01-23 00:28:21.685962: step: 216/529, loss: 0.12406959384679794
2023-01-23 00:28:22.800558: step: 220/529, loss: 0.7428269386291504
2023-01-23 00:28:23.915797: step: 224/529, loss: 0.056182861328125
2023-01-23 00:28:25.019510: step: 228/529, loss: 0.01631774939596653
2023-01-23 00:28:26.140169: step: 232/529, loss: 0.05640731006860733
2023-01-23 00:28:27.222525: step: 236/529, loss: 0.230677992105484
2023-01-23 00:28:28.322281: step: 240/529, loss: 0.3648664355278015
2023-01-23 00:28:29.425896: step: 244/529, loss: 0.08810434490442276
2023-01-23 00:28:30.520295: step: 248/529, loss: 0.3475028872489929
2023-01-23 00:28:31.630688: step: 252/529, loss: 0.056288961321115494
2023-01-23 00:28:32.729971: step: 256/529, loss: 0.01311262883245945
2023-01-23 00:28:33.810252: step: 260/529, loss: 0.38443297147750854
2023-01-23 00:28:34.908942: step: 264/529, loss: 0.335693359375
2023-01-23 00:28:36.030370: step: 268/529, loss: 0.16695089638233185
2023-01-23 00:28:37.120203: step: 272/529, loss: 0.06345872581005096
2023-01-23 00:28:38.250143: step: 276/529, loss: 0.2842293381690979
2023-01-23 00:28:39.327580: step: 280/529, loss: 0.06773070991039276
2023-01-23 00:28:40.447415: step: 284/529, loss: 0.135711669921875
2023-01-23 00:28:41.585558: step: 288/529, loss: 0.14520874619483948
2023-01-23 00:28:42.711777: step: 292/529, loss: 1.0627326965332031
2023-01-23 00:28:43.815998: step: 296/529, loss: 0.12591552734375
2023-01-23 00:28:44.912857: step: 300/529, loss: 0.16250251233577728
2023-01-23 00:28:46.052758: step: 304/529, loss: 0.22057685256004333
2023-01-23 00:28:47.149237: step: 308/529, loss: 0.029260635375976562
2023-01-23 00:28:48.266859: step: 312/529, loss: 0.019703388214111328
2023-01-23 00:28:49.390315: step: 316/529, loss: 0.4171700179576874
2023-01-23 00:28:50.548308: step: 320/529, loss: 0.2709653079509735
2023-01-23 00:28:51.667435: step: 324/529, loss: 0.1707896590232849
2023-01-23 00:28:52.760434: step: 328/529, loss: 0.10557766258716583
2023-01-23 00:28:53.874087: step: 332/529, loss: 0.1140020340681076
2023-01-23 00:28:54.970110: step: 336/529, loss: 0.23821982741355896
2023-01-23 00:28:56.080965: step: 340/529, loss: 0.05409717559814453
2023-01-23 00:28:57.183378: step: 344/529, loss: 0.07998485863208771
2023-01-23 00:28:58.303166: step: 348/529, loss: 0.030089855194091797
2023-01-23 00:28:59.398154: step: 352/529, loss: 0.02464304119348526
2023-01-23 00:29:00.526027: step: 356/529, loss: 0.13897676765918732
2023-01-23 00:29:01.631477: step: 360/529, loss: 0.0669856071472168
2023-01-23 00:29:02.725631: step: 364/529, loss: 0.08883456885814667
2023-01-23 00:29:03.813866: step: 368/529, loss: 0.11503658443689346
2023-01-23 00:29:04.902468: step: 372/529, loss: 0.2833155393600464
2023-01-23 00:29:06.058587: step: 376/529, loss: 0.09108105301856995
2023-01-23 00:29:07.184820: step: 380/529, loss: 0.14699287712574005
2023-01-23 00:29:08.306429: step: 384/529, loss: 0.5391696691513062
2023-01-23 00:29:09.415880: step: 388/529, loss: 0.09249172359704971
2023-01-23 00:29:10.545061: step: 392/529, loss: 0.09266749024391174
2023-01-23 00:29:11.660699: step: 396/529, loss: 0.06567039340734482
2023-01-23 00:29:12.773238: step: 400/529, loss: 0.1745540201663971
2023-01-23 00:29:13.891809: step: 404/529, loss: 0.15886621177196503
2023-01-23 00:29:15.017659: step: 408/529, loss: 0.1589856594800949
2023-01-23 00:29:16.126377: step: 412/529, loss: 0.3134172558784485
2023-01-23 00:29:17.219362: step: 416/529, loss: 0.125766322016716
2023-01-23 00:29:18.344530: step: 420/529, loss: 0.18280763924121857
2023-01-23 00:29:19.471545: step: 424/529, loss: 0.8104706406593323
2023-01-23 00:29:20.569343: step: 428/529, loss: 0.06938963383436203
2023-01-23 00:29:21.685796: step: 432/529, loss: 0.6461702585220337
2023-01-23 00:29:22.783664: step: 436/529, loss: 0.15197500586509705
2023-01-23 00:29:23.881309: step: 440/529, loss: 0.0949891060590744
2023-01-23 00:29:24.990892: step: 444/529, loss: 0.23109427094459534
2023-01-23 00:29:26.089991: step: 448/529, loss: 0.13077601790428162
2023-01-23 00:29:27.174064: step: 452/529, loss: 0.09038834273815155
2023-01-23 00:29:28.285202: step: 456/529, loss: 0.2053825557231903
2023-01-23 00:29:29.384906: step: 460/529, loss: 0.17105592787265778
2023-01-23 00:29:30.482751: step: 464/529, loss: 0.01946844905614853
2023-01-23 00:29:31.580143: step: 468/529, loss: 0.04283332824707031
2023-01-23 00:29:32.670481: step: 472/529, loss: 0.2230476438999176
2023-01-23 00:29:33.822216: step: 476/529, loss: 0.5186672210693359
2023-01-23 00:29:34.933029: step: 480/529, loss: 0.0735451728105545
2023-01-23 00:29:36.038535: step: 484/529, loss: 0.11196231842041016
2023-01-23 00:29:37.175634: step: 488/529, loss: 0.5283088684082031
2023-01-23 00:29:38.292045: step: 492/529, loss: 0.7329642176628113
2023-01-23 00:29:39.398601: step: 496/529, loss: 0.1420719176530838
2023-01-23 00:29:40.488074: step: 500/529, loss: 0.03245124965906143
2023-01-23 00:29:41.578813: step: 504/529, loss: 0.908942461013794
2023-01-23 00:29:42.683484: step: 508/529, loss: 0.14457498490810394
2023-01-23 00:29:43.794329: step: 512/529, loss: 0.3416524827480316
2023-01-23 00:29:44.918581: step: 516/529, loss: 0.16285952925682068
2023-01-23 00:29:46.001773: step: 520/529, loss: 0.05690765380859375
2023-01-23 00:29:47.123155: step: 524/529, loss: 0.7925837635993958
2023-01-23 00:29:48.240454: step: 528/529, loss: 0.21937322616577148
2023-01-23 00:29:49.324245: step: 532/529, loss: 0.2915459871292114
2023-01-23 00:29:50.400568: step: 536/529, loss: 0.12484331429004669
2023-01-23 00:29:51.497634: step: 540/529, loss: 0.15269441902637482
2023-01-23 00:29:52.585992: step: 544/529, loss: 0.13786816596984863
2023-01-23 00:29:53.678842: step: 548/529, loss: 0.054793838411569595
2023-01-23 00:29:54.763814: step: 552/529, loss: 1.2599841356277466
2023-01-23 00:29:55.877609: step: 556/529, loss: 0.18873223662376404
2023-01-23 00:29:56.961053: step: 560/529, loss: 0.0888739600777626
2023-01-23 00:29:58.089087: step: 564/529, loss: 0.17296858131885529
2023-01-23 00:29:59.180668: step: 568/529, loss: 0.021279525011777878
2023-01-23 00:30:00.268921: step: 572/529, loss: 0.07156114280223846
2023-01-23 00:30:01.401104: step: 576/529, loss: 0.29135942459106445
2023-01-23 00:30:02.527212: step: 580/529, loss: 0.18069811165332794
2023-01-23 00:30:03.624518: step: 584/529, loss: 0.08618822693824768
2023-01-23 00:30:04.776509: step: 588/529, loss: 0.08463239669799805
2023-01-23 00:30:05.888138: step: 592/529, loss: 0.175147145986557
2023-01-23 00:30:06.992375: step: 596/529, loss: 0.1767711490392685
2023-01-23 00:30:08.116812: step: 600/529, loss: 0.1781170815229416
2023-01-23 00:30:09.233073: step: 604/529, loss: 0.07512360066175461
2023-01-23 00:30:10.346171: step: 608/529, loss: 0.173912912607193
2023-01-23 00:30:11.454454: step: 612/529, loss: 0.1476341187953949
2023-01-23 00:30:12.572274: step: 616/529, loss: 0.08104848861694336
2023-01-23 00:30:13.697785: step: 620/529, loss: 0.040274716913700104
2023-01-23 00:30:14.807533: step: 624/529, loss: 0.201176717877388
2023-01-23 00:30:15.971048: step: 628/529, loss: 0.03966636583209038
2023-01-23 00:30:17.055461: step: 632/529, loss: 0.11002178490161896
2023-01-23 00:30:18.184607: step: 636/529, loss: 0.23965173959732056
2023-01-23 00:30:19.314821: step: 640/529, loss: 0.5823952555656433
2023-01-23 00:30:20.407805: step: 644/529, loss: 0.2902754843235016
2023-01-23 00:30:21.496072: step: 648/529, loss: 0.024506473913788795
2023-01-23 00:30:22.611523: step: 652/529, loss: 0.1066705659031868
2023-01-23 00:30:23.739547: step: 656/529, loss: 0.15058794617652893
2023-01-23 00:30:24.864522: step: 660/529, loss: 0.08300383388996124
2023-01-23 00:30:25.990157: step: 664/529, loss: 0.0694490522146225
2023-01-23 00:30:27.112131: step: 668/529, loss: 0.21036848425865173
2023-01-23 00:30:28.230545: step: 672/529, loss: 0.06634902954101562
2023-01-23 00:30:29.358581: step: 676/529, loss: 0.15171471238136292
2023-01-23 00:30:30.498622: step: 680/529, loss: 0.08180160820484161
2023-01-23 00:30:31.641573: step: 684/529, loss: 0.009794425219297409
2023-01-23 00:30:32.746800: step: 688/529, loss: 0.15289267897605896
2023-01-23 00:30:33.834261: step: 692/529, loss: 0.05382108688354492
2023-01-23 00:30:34.942834: step: 696/529, loss: 0.09971089661121368
2023-01-23 00:30:36.054406: step: 700/529, loss: 0.037062834948301315
2023-01-23 00:30:37.133515: step: 704/529, loss: 0.3365079164505005
2023-01-23 00:30:38.210411: step: 708/529, loss: 0.5037580728530884
2023-01-23 00:30:39.308784: step: 712/529, loss: 0.20521163940429688
2023-01-23 00:30:40.442522: step: 716/529, loss: 0.10319998115301132
2023-01-23 00:30:41.581232: step: 720/529, loss: 0.0753898173570633
2023-01-23 00:30:42.672068: step: 724/529, loss: 0.060896776616573334
2023-01-23 00:30:43.802397: step: 728/529, loss: 0.15772362053394318
2023-01-23 00:30:44.932491: step: 732/529, loss: 0.10997290164232254
2023-01-23 00:30:46.067382: step: 736/529, loss: 0.10512867569923401
2023-01-23 00:30:47.194781: step: 740/529, loss: 0.07967662811279297
2023-01-23 00:30:48.311614: step: 744/529, loss: 0.10420303046703339
2023-01-23 00:30:49.455702: step: 748/529, loss: 0.4614826440811157
2023-01-23 00:30:50.606257: step: 752/529, loss: 0.1640513390302658
2023-01-23 00:30:51.717610: step: 756/529, loss: 0.12356098741292953
2023-01-23 00:30:52.844227: step: 760/529, loss: 0.09436388313770294
2023-01-23 00:30:53.970404: step: 764/529, loss: 0.1559332013130188
2023-01-23 00:30:55.084341: step: 768/529, loss: 0.02114286459982395
2023-01-23 00:30:56.225849: step: 772/529, loss: 0.268502801656723
2023-01-23 00:30:57.342528: step: 776/529, loss: 0.030556965619325638
2023-01-23 00:30:58.436874: step: 780/529, loss: 0.0412907600402832
2023-01-23 00:30:59.554938: step: 784/529, loss: 0.1025749146938324
2023-01-23 00:31:00.693032: step: 788/529, loss: 0.5738879442214966
2023-01-23 00:31:01.804354: step: 792/529, loss: 0.1171075850725174
2023-01-23 00:31:02.935794: step: 796/529, loss: 0.1833280622959137
2023-01-23 00:31:04.017595: step: 800/529, loss: 0.04897637665271759
2023-01-23 00:31:05.137775: step: 804/529, loss: 0.1427517831325531
2023-01-23 00:31:06.220323: step: 808/529, loss: 0.12133254110813141
2023-01-23 00:31:07.338258: step: 812/529, loss: 0.08046194165945053
2023-01-23 00:31:08.438337: step: 816/529, loss: 0.33535730838775635
2023-01-23 00:31:09.538404: step: 820/529, loss: 0.8368805646896362
2023-01-23 00:31:10.674063: step: 824/529, loss: 0.4099559783935547
2023-01-23 00:31:11.791483: step: 828/529, loss: 0.34186702966690063
2023-01-23 00:31:12.900171: step: 832/529, loss: 0.08430376648902893
2023-01-23 00:31:13.996505: step: 836/529, loss: 0.33013916015625
2023-01-23 00:31:15.103994: step: 840/529, loss: 0.03210580348968506
2023-01-23 00:31:16.268768: step: 844/529, loss: 0.19541558623313904
2023-01-23 00:31:17.388551: step: 848/529, loss: 0.04549083858728409
2023-01-23 00:31:18.492549: step: 852/529, loss: 0.17762994766235352
2023-01-23 00:31:19.603666: step: 856/529, loss: 0.09288106113672256
2023-01-23 00:31:20.710008: step: 860/529, loss: 0.050241902470588684
2023-01-23 00:31:21.809441: step: 864/529, loss: 0.10067228972911835
2023-01-23 00:31:22.925475: step: 868/529, loss: 0.10773982852697372
2023-01-23 00:31:24.008696: step: 872/529, loss: 0.15044693648815155
2023-01-23 00:31:25.132257: step: 876/529, loss: 0.1522907167673111
2023-01-23 00:31:26.249035: step: 880/529, loss: 0.23786316812038422
2023-01-23 00:31:27.374727: step: 884/529, loss: 0.2061445713043213
2023-01-23 00:31:28.516185: step: 888/529, loss: 0.273600697517395
2023-01-23 00:31:29.621557: step: 892/529, loss: 0.052793025970458984
2023-01-23 00:31:30.717084: step: 896/529, loss: 0.04912302643060684
2023-01-23 00:31:31.838020: step: 900/529, loss: 0.11058846116065979
2023-01-23 00:31:32.927767: step: 904/529, loss: 0.0588347464799881
2023-01-23 00:31:34.040254: step: 908/529, loss: 0.05803394317626953
2023-01-23 00:31:35.155410: step: 912/529, loss: 0.060607049614191055
2023-01-23 00:31:36.248511: step: 916/529, loss: 0.12683998048305511
2023-01-23 00:31:37.352374: step: 920/529, loss: 0.42692652344703674
2023-01-23 00:31:38.455266: step: 924/529, loss: 0.13693276047706604
2023-01-23 00:31:39.573741: step: 928/529, loss: 0.20188485085964203
2023-01-23 00:31:40.689816: step: 932/529, loss: 0.865402102470398
2023-01-23 00:31:41.829421: step: 936/529, loss: 0.03904347866773605
2023-01-23 00:31:42.945627: step: 940/529, loss: 0.11379461735486984
2023-01-23 00:31:44.150087: step: 944/529, loss: 0.34854668378829956
2023-01-23 00:31:45.264944: step: 948/529, loss: 0.194636732339859
2023-01-23 00:31:46.366564: step: 952/529, loss: 0.05015420913696289
2023-01-23 00:31:47.479002: step: 956/529, loss: 0.2486804872751236
2023-01-23 00:31:48.589192: step: 960/529, loss: 0.0297896396368742
2023-01-23 00:31:49.713813: step: 964/529, loss: 0.03972931206226349
2023-01-23 00:31:50.840875: step: 968/529, loss: 0.6017562747001648
2023-01-23 00:31:51.955549: step: 972/529, loss: 0.06138205528259277
2023-01-23 00:31:53.082745: step: 976/529, loss: 0.12083926051855087
2023-01-23 00:31:54.205767: step: 980/529, loss: 0.13510942459106445
2023-01-23 00:31:55.334399: step: 984/529, loss: 0.11949028819799423
2023-01-23 00:31:56.460813: step: 988/529, loss: 0.3286727964878082
2023-01-23 00:31:57.570319: step: 992/529, loss: 0.048412345349788666
2023-01-23 00:31:58.702348: step: 996/529, loss: 0.15781421959400177
2023-01-23 00:31:59.786030: step: 1000/529, loss: 0.13084203004837036
2023-01-23 00:32:00.898358: step: 1004/529, loss: 0.1309451162815094
2023-01-23 00:32:02.027571: step: 1008/529, loss: 0.18249750137329102
2023-01-23 00:32:03.140709: step: 1012/529, loss: 0.011563658714294434
2023-01-23 00:32:04.251049: step: 1016/529, loss: 0.4749208688735962
2023-01-23 00:32:05.346909: step: 1020/529, loss: 0.1711321771144867
2023-01-23 00:32:06.457230: step: 1024/529, loss: 0.07321977615356445
2023-01-23 00:32:07.543230: step: 1028/529, loss: 0.1281047761440277
2023-01-23 00:32:08.653982: step: 1032/529, loss: 0.07690820842981339
2023-01-23 00:32:09.749145: step: 1036/529, loss: 0.29134905338287354
2023-01-23 00:32:10.887670: step: 1040/529, loss: 0.06452398002147675
2023-01-23 00:32:11.993686: step: 1044/529, loss: 0.34968137741088867
2023-01-23 00:32:13.131534: step: 1048/529, loss: 0.059043314307928085
2023-01-23 00:32:14.219538: step: 1052/529, loss: 1.9237512350082397
2023-01-23 00:32:15.328318: step: 1056/529, loss: 0.2849012315273285
2023-01-23 00:32:16.423594: step: 1060/529, loss: 0.031221581622958183
2023-01-23 00:32:17.543770: step: 1064/529, loss: 0.11973848193883896
2023-01-23 00:32:18.637771: step: 1068/529, loss: 0.1436946988105774
2023-01-23 00:32:19.758353: step: 1072/529, loss: 0.13366976380348206
2023-01-23 00:32:20.861166: step: 1076/529, loss: 0.11427507549524307
2023-01-23 00:32:21.995212: step: 1080/529, loss: 0.08487396687269211
2023-01-23 00:32:23.143055: step: 1084/529, loss: 0.06237798184156418
2023-01-23 00:32:24.246721: step: 1088/529, loss: 0.3203534185886383
2023-01-23 00:32:25.316479: step: 1092/529, loss: 0.10885315388441086
2023-01-23 00:32:26.438883: step: 1096/529, loss: 0.11889419704675674
2023-01-23 00:32:27.534250: step: 1100/529, loss: 0.10720300674438477
2023-01-23 00:32:28.630126: step: 1104/529, loss: 0.07960281521081924
2023-01-23 00:32:29.728096: step: 1108/529, loss: 0.12990784645080566
2023-01-23 00:32:30.830628: step: 1112/529, loss: 0.08828286826610565
2023-01-23 00:32:31.913901: step: 1116/529, loss: 0.45694124698638916
2023-01-23 00:32:33.018129: step: 1120/529, loss: 0.3834283947944641
2023-01-23 00:32:34.130802: step: 1124/529, loss: 0.38184791803359985
2023-01-23 00:32:35.239659: step: 1128/529, loss: 0.4068889617919922
2023-01-23 00:32:36.351578: step: 1132/529, loss: 0.126484677195549
2023-01-23 00:32:37.465963: step: 1136/529, loss: 0.043662022799253464
2023-01-23 00:32:38.581232: step: 1140/529, loss: 0.5155819654464722
2023-01-23 00:32:39.680727: step: 1144/529, loss: 0.6236297488212585
2023-01-23 00:32:40.787507: step: 1148/529, loss: 0.4206400215625763
2023-01-23 00:32:41.901988: step: 1152/529, loss: 0.45251503586769104
2023-01-23 00:32:43.026727: step: 1156/529, loss: 0.09222922474145889
2023-01-23 00:32:44.158974: step: 1160/529, loss: 0.15893355011940002
2023-01-23 00:32:45.285761: step: 1164/529, loss: 0.2277422845363617
2023-01-23 00:32:46.385401: step: 1168/529, loss: 0.0982811450958252
2023-01-23 00:32:47.476821: step: 1172/529, loss: 0.5409174561500549
2023-01-23 00:32:48.593010: step: 1176/529, loss: 0.14365874230861664
2023-01-23 00:32:49.724000: step: 1180/529, loss: 0.092638298869133
2023-01-23 00:32:50.845154: step: 1184/529, loss: 0.18114447593688965
2023-01-23 00:32:51.949171: step: 1188/529, loss: 0.34872645139694214
2023-01-23 00:32:53.048581: step: 1192/529, loss: 0.08287941664457321
2023-01-23 00:32:54.152032: step: 1196/529, loss: 0.06466036289930344
2023-01-23 00:32:55.273136: step: 1200/529, loss: 0.11960086971521378
2023-01-23 00:32:56.368307: step: 1204/529, loss: 0.07670927047729492
2023-01-23 00:32:57.478491: step: 1208/529, loss: 0.10437555611133575
2023-01-23 00:32:58.585452: step: 1212/529, loss: 0.08500556647777557
2023-01-23 00:32:59.679129: step: 1216/529, loss: 4.565764427185059
2023-01-23 00:33:00.793483: step: 1220/529, loss: 0.11555786430835724
2023-01-23 00:33:01.940953: step: 1224/529, loss: 0.22940626740455627
2023-01-23 00:33:03.065110: step: 1228/529, loss: 0.16571807861328125
2023-01-23 00:33:04.176490: step: 1232/529, loss: 0.24964351952075958
2023-01-23 00:33:05.275167: step: 1236/529, loss: 0.027376480400562286
2023-01-23 00:33:06.434103: step: 1240/529, loss: 0.04574167728424072
2023-01-23 00:33:07.538259: step: 1244/529, loss: 0.2441386878490448
2023-01-23 00:33:08.647724: step: 1248/529, loss: 0.19641664624214172
2023-01-23 00:33:09.770722: step: 1252/529, loss: 0.13524214923381805
2023-01-23 00:33:10.883082: step: 1256/529, loss: 0.17239660024642944
2023-01-23 00:33:11.962869: step: 1260/529, loss: 0.06970057636499405
2023-01-23 00:33:13.102735: step: 1264/529, loss: 0.07716956734657288
2023-01-23 00:33:14.230660: step: 1268/529, loss: 0.0870828628540039
2023-01-23 00:33:15.344516: step: 1272/529, loss: 0.028278542682528496
2023-01-23 00:33:16.474206: step: 1276/529, loss: 0.1458393633365631
2023-01-23 00:33:17.548652: step: 1280/529, loss: 0.15465813875198364
2023-01-23 00:33:18.672095: step: 1284/529, loss: 0.1331310272216797
2023-01-23 00:33:19.783525: step: 1288/529, loss: 0.06034698709845543
2023-01-23 00:33:20.944293: step: 1292/529, loss: 0.10232067108154297
2023-01-23 00:33:22.041295: step: 1296/529, loss: 0.06815081089735031
2023-01-23 00:33:23.140962: step: 1300/529, loss: 0.19847507774829865
2023-01-23 00:33:24.278854: step: 1304/529, loss: 0.8876577615737915
2023-01-23 00:33:25.390660: step: 1308/529, loss: 0.02369384840130806
2023-01-23 00:33:26.483644: step: 1312/529, loss: 0.33368349075317383
2023-01-23 00:33:27.594784: step: 1316/529, loss: 0.14370593428611755
2023-01-23 00:33:28.702516: step: 1320/529, loss: 0.498554527759552
2023-01-23 00:33:29.809001: step: 1324/529, loss: 0.0928216204047203
2023-01-23 00:33:30.904958: step: 1328/529, loss: 0.31891125440597534
2023-01-23 00:33:32.009418: step: 1332/529, loss: 0.6354032158851624
2023-01-23 00:33:33.117969: step: 1336/529, loss: 0.12121353298425674
2023-01-23 00:33:34.260867: step: 1340/529, loss: 0.501778244972229
2023-01-23 00:33:35.338930: step: 1344/529, loss: 0.08527665585279465
2023-01-23 00:33:36.441527: step: 1348/529, loss: 0.04209490120410919
2023-01-23 00:33:37.547253: step: 1352/529, loss: 0.055812835693359375
2023-01-23 00:33:38.637548: step: 1356/529, loss: 0.47979336977005005
2023-01-23 00:33:39.775131: step: 1360/529, loss: 0.08332987129688263
2023-01-23 00:33:40.898448: step: 1364/529, loss: 0.08934378623962402
2023-01-23 00:33:42.006187: step: 1368/529, loss: 0.0654059424996376
2023-01-23 00:33:43.107106: step: 1372/529, loss: 0.09324436634778976
2023-01-23 00:33:44.253018: step: 1376/529, loss: 0.5453853607177734
2023-01-23 00:33:45.377853: step: 1380/529, loss: 0.06243286281824112
2023-01-23 00:33:46.489721: step: 1384/529, loss: 0.09188661724328995
2023-01-23 00:33:47.615132: step: 1388/529, loss: 0.05345487594604492
2023-01-23 00:33:48.735599: step: 1392/529, loss: 0.13730306923389435
2023-01-23 00:33:49.837758: step: 1396/529, loss: 0.11564353108406067
2023-01-23 00:33:50.935054: step: 1400/529, loss: 0.07212846726179123
2023-01-23 00:33:52.023625: step: 1404/529, loss: 0.22219763696193695
2023-01-23 00:33:53.101204: step: 1408/529, loss: 0.01991863176226616
2023-01-23 00:33:54.205051: step: 1412/529, loss: 0.04755754768848419
2023-01-23 00:33:55.309036: step: 1416/529, loss: 0.19270697236061096
2023-01-23 00:33:56.478274: step: 1420/529, loss: 0.07280278205871582
2023-01-23 00:33:57.564152: step: 1424/529, loss: 0.1721513420343399
2023-01-23 00:33:58.666422: step: 1428/529, loss: 0.2575359344482422
2023-01-23 00:33:59.767738: step: 1432/529, loss: 0.05882635340094566
2023-01-23 00:34:00.869298: step: 1436/529, loss: 0.06694427877664566
2023-01-23 00:34:01.975247: step: 1440/529, loss: 0.06245095655322075
2023-01-23 00:34:03.063447: step: 1444/529, loss: 0.07255986332893372
2023-01-23 00:34:04.185858: step: 1448/529, loss: 0.3289529085159302
2023-01-23 00:34:05.308948: step: 1452/529, loss: 0.18068045377731323
2023-01-23 00:34:06.419881: step: 1456/529, loss: 0.0072196004912257195
2023-01-23 00:34:07.558632: step: 1460/529, loss: 0.09402026981115341
2023-01-23 00:34:08.663911: step: 1464/529, loss: 0.08594217896461487
2023-01-23 00:34:09.786359: step: 1468/529, loss: 0.13697758316993713
2023-01-23 00:34:10.877331: step: 1472/529, loss: 0.06967172771692276
2023-01-23 00:34:12.023105: step: 1476/529, loss: 0.06850939244031906
2023-01-23 00:34:13.118713: step: 1480/529, loss: 0.702797532081604
2023-01-23 00:34:14.231551: step: 1484/529, loss: 1.2072794437408447
2023-01-23 00:34:15.342123: step: 1488/529, loss: 0.0856056734919548
2023-01-23 00:34:16.450412: step: 1492/529, loss: 0.11645841598510742
2023-01-23 00:34:17.560768: step: 1496/529, loss: 0.12628121674060822
2023-01-23 00:34:18.667600: step: 1500/529, loss: 0.25913891196250916
2023-01-23 00:34:19.813080: step: 1504/529, loss: 0.16423968970775604
2023-01-23 00:34:20.925626: step: 1508/529, loss: 0.40236568450927734
2023-01-23 00:34:22.013764: step: 1512/529, loss: 0.10830002278089523
2023-01-23 00:34:23.104725: step: 1516/529, loss: 0.008442115969955921
2023-01-23 00:34:24.210623: step: 1520/529, loss: 0.4802786111831665
2023-01-23 00:34:25.352162: step: 1524/529, loss: 0.11132478713989258
2023-01-23 00:34:26.473486: step: 1528/529, loss: 0.12264872342348099
2023-01-23 00:34:27.572024: step: 1532/529, loss: 0.07006797939538956
2023-01-23 00:34:28.692998: step: 1536/529, loss: 0.08137015998363495
2023-01-23 00:34:29.779076: step: 1540/529, loss: 0.07594804465770721
2023-01-23 00:34:30.900505: step: 1544/529, loss: 0.08455229550600052
2023-01-23 00:34:32.005913: step: 1548/529, loss: 0.15987785160541534
2023-01-23 00:34:33.100242: step: 1552/529, loss: 0.1525147259235382
2023-01-23 00:34:34.223078: step: 1556/529, loss: 0.13496610522270203
2023-01-23 00:34:35.332863: step: 1560/529, loss: 0.04631509631872177
2023-01-23 00:34:36.425510: step: 1564/529, loss: 0.0944204330444336
2023-01-23 00:34:37.532875: step: 1568/529, loss: 0.04984412342309952
2023-01-23 00:34:38.649564: step: 1572/529, loss: 0.165119469165802
2023-01-23 00:34:39.762723: step: 1576/529, loss: 0.3083455264568329
2023-01-23 00:34:40.863181: step: 1580/529, loss: 0.08931250125169754
2023-01-23 00:34:41.962784: step: 1584/529, loss: 0.10379371792078018
2023-01-23 00:34:43.078019: step: 1588/529, loss: 1.0492594242095947
2023-01-23 00:34:44.164297: step: 1592/529, loss: 0.0825003832578659
2023-01-23 00:34:45.284610: step: 1596/529, loss: 0.33698076009750366
2023-01-23 00:34:46.423435: step: 1600/529, loss: 0.01838088035583496
2023-01-23 00:34:47.514397: step: 1604/529, loss: 0.06181211397051811
2023-01-23 00:34:48.613840: step: 1608/529, loss: 0.7557794451713562
2023-01-23 00:34:49.733082: step: 1612/529, loss: 0.23803357779979706
2023-01-23 00:34:50.830576: step: 1616/529, loss: 0.1964745968580246
2023-01-23 00:34:51.926462: step: 1620/529, loss: 0.15219077467918396
2023-01-23 00:34:53.048860: step: 1624/529, loss: 0.09088575839996338
2023-01-23 00:34:54.179499: step: 1628/529, loss: 0.08471640944480896
2023-01-23 00:34:55.306730: step: 1632/529, loss: 0.23300760984420776
2023-01-23 00:34:56.402820: step: 1636/529, loss: 0.29435643553733826
2023-01-23 00:34:57.497671: step: 1640/529, loss: 0.09191122651100159
2023-01-23 00:34:58.606691: step: 1644/529, loss: 0.30674517154693604
2023-01-23 00:34:59.714960: step: 1648/529, loss: 0.1423693597316742
2023-01-23 00:35:00.813881: step: 1652/529, loss: 0.07620749622583389
2023-01-23 00:35:01.935924: step: 1656/529, loss: 0.10474634170532227
2023-01-23 00:35:03.054554: step: 1660/529, loss: 0.22713498771190643
2023-01-23 00:35:04.158179: step: 1664/529, loss: 0.23579463362693787
2023-01-23 00:35:05.268380: step: 1668/529, loss: 0.2250600904226303
2023-01-23 00:35:06.376237: step: 1672/529, loss: 0.05981481075286865
2023-01-23 00:35:07.488716: step: 1676/529, loss: 0.10235671699047089
2023-01-23 00:35:08.595873: step: 1680/529, loss: 0.1429756134748459
2023-01-23 00:35:09.691368: step: 1684/529, loss: 0.04197216033935547
2023-01-23 00:35:10.795181: step: 1688/529, loss: 0.26908689737319946
2023-01-23 00:35:11.897782: step: 1692/529, loss: 0.04483480751514435
2023-01-23 00:35:13.018677: step: 1696/529, loss: 0.011022090911865234
2023-01-23 00:35:14.112979: step: 1700/529, loss: 0.12480011582374573
2023-01-23 00:35:15.205949: step: 1704/529, loss: 0.1403886377811432
2023-01-23 00:35:16.324738: step: 1708/529, loss: 0.06724562495946884
2023-01-23 00:35:17.429923: step: 1712/529, loss: 0.3738456964492798
2023-01-23 00:35:18.547222: step: 1716/529, loss: 0.0936737060546875
2023-01-23 00:35:19.682131: step: 1720/529, loss: 0.16844210028648376
2023-01-23 00:35:20.817852: step: 1724/529, loss: 6.272885322570801
2023-01-23 00:35:21.985616: step: 1728/529, loss: 0.034799911081790924
2023-01-23 00:35:23.121807: step: 1732/529, loss: 0.23540247976779938
2023-01-23 00:35:24.260191: step: 1736/529, loss: 0.3427356481552124
2023-01-23 00:35:25.343136: step: 1740/529, loss: 0.24107341468334198
2023-01-23 00:35:26.463440: step: 1744/529, loss: 0.08122486621141434
2023-01-23 00:35:27.628542: step: 1748/529, loss: 0.16982164978981018
2023-01-23 00:35:28.726529: step: 1752/529, loss: 0.09848213195800781
2023-01-23 00:35:29.829086: step: 1756/529, loss: 0.1173684149980545
2023-01-23 00:35:30.935037: step: 1760/529, loss: 0.03551540523767471
2023-01-23 00:35:32.040214: step: 1764/529, loss: 0.6210320591926575
2023-01-23 00:35:33.150337: step: 1768/529, loss: 0.1533488780260086
2023-01-23 00:35:34.274470: step: 1772/529, loss: 0.11132596433162689
2023-01-23 00:35:35.374319: step: 1776/529, loss: 2.3619251251220703
2023-01-23 00:35:36.470687: step: 1780/529, loss: 0.09598284214735031
2023-01-23 00:35:37.595426: step: 1784/529, loss: 0.136785089969635
2023-01-23 00:35:38.702924: step: 1788/529, loss: 0.08897629380226135
2023-01-23 00:35:39.842195: step: 1792/529, loss: 0.2811811566352844
2023-01-23 00:35:40.934295: step: 1796/529, loss: 3.5141055583953857
2023-01-23 00:35:42.067832: step: 1800/529, loss: 0.7922897338867188
2023-01-23 00:35:43.183156: step: 1804/529, loss: 0.06357469409704208
2023-01-23 00:35:44.292764: step: 1808/529, loss: 0.1857217699289322
2023-01-23 00:35:45.399559: step: 1812/529, loss: 0.10023783892393112
2023-01-23 00:35:46.506848: step: 1816/529, loss: 2.0442261695861816
2023-01-23 00:35:47.620543: step: 1820/529, loss: 0.11358185112476349
2023-01-23 00:35:48.746023: step: 1824/529, loss: 0.05978505685925484
2023-01-23 00:35:49.878396: step: 1828/529, loss: 0.13109531998634338
2023-01-23 00:35:51.006530: step: 1832/529, loss: 0.05982523411512375
2023-01-23 00:35:52.123166: step: 1836/529, loss: 0.0687781348824501
2023-01-23 00:35:53.286000: step: 1840/529, loss: 0.6758712530136108
2023-01-23 00:35:54.398337: step: 1844/529, loss: 0.8594818115234375
2023-01-23 00:35:55.517202: step: 1848/529, loss: 0.09919323772192001
2023-01-23 00:35:56.618622: step: 1852/529, loss: 0.12762147188186646
2023-01-23 00:35:57.722062: step: 1856/529, loss: 0.024706363677978516
2023-01-23 00:35:58.845153: step: 1860/529, loss: 0.14579400420188904
2023-01-23 00:35:59.940479: step: 1864/529, loss: 0.07150142639875412
2023-01-23 00:36:01.054890: step: 1868/529, loss: 0.09360170364379883
2023-01-23 00:36:02.160861: step: 1872/529, loss: 0.2526983618736267
2023-01-23 00:36:03.288086: step: 1876/529, loss: 1.3848556280136108
2023-01-23 00:36:04.410593: step: 1880/529, loss: 0.8493753671646118
2023-01-23 00:36:05.525385: step: 1884/529, loss: 0.14791786670684814
2023-01-23 00:36:06.646356: step: 1888/529, loss: 0.11459656059741974
2023-01-23 00:36:07.789775: step: 1892/529, loss: 1.0388320684432983
2023-01-23 00:36:08.901669: step: 1896/529, loss: 0.13002696633338928
2023-01-23 00:36:10.016014: step: 1900/529, loss: 0.5713960528373718
2023-01-23 00:36:11.121718: step: 1904/529, loss: 0.2998400330543518
2023-01-23 00:36:12.256504: step: 1908/529, loss: 0.16257724165916443
2023-01-23 00:36:13.371029: step: 1912/529, loss: 0.14772339165210724
2023-01-23 00:36:14.478927: step: 1916/529, loss: 0.4524449408054352
2023-01-23 00:36:15.573461: step: 1920/529, loss: 0.038282107561826706
2023-01-23 00:36:16.640904: step: 1924/529, loss: 0.015547753311693668
2023-01-23 00:36:17.753720: step: 1928/529, loss: 0.2802380621433258
2023-01-23 00:36:18.884402: step: 1932/529, loss: 0.08170171082019806
2023-01-23 00:36:20.013948: step: 1936/529, loss: 0.10421142727136612
2023-01-23 00:36:21.112282: step: 1940/529, loss: 0.03324277326464653
2023-01-23 00:36:22.244740: step: 1944/529, loss: 0.15926380455493927
2023-01-23 00:36:23.367038: step: 1948/529, loss: 0.19992399215698242
2023-01-23 00:36:24.455140: step: 1952/529, loss: 0.16030746698379517
2023-01-23 00:36:25.554914: step: 1956/529, loss: 0.376537024974823
2023-01-23 00:36:26.671250: step: 1960/529, loss: 0.07121982425451279
2023-01-23 00:36:27.766647: step: 1964/529, loss: 0.03374643251299858
2023-01-23 00:36:28.868152: step: 1968/529, loss: 0.005858802702277899
2023-01-23 00:36:30.016207: step: 1972/529, loss: 0.12500429153442383
2023-01-23 00:36:31.126745: step: 1976/529, loss: 0.397409051656723
2023-01-23 00:36:32.226455: step: 1980/529, loss: 0.06790447235107422
2023-01-23 00:36:33.336931: step: 1984/529, loss: 0.27846452593803406
2023-01-23 00:36:34.429899: step: 1988/529, loss: 0.07734747231006622
2023-01-23 00:36:35.528486: step: 1992/529, loss: 0.05856599658727646
2023-01-23 00:36:36.694427: step: 1996/529, loss: 0.22134943306446075
2023-01-23 00:36:37.779339: step: 2000/529, loss: 0.2235075980424881
2023-01-23 00:36:38.901308: step: 2004/529, loss: 0.054174572229385376
2023-01-23 00:36:39.996409: step: 2008/529, loss: 0.03818502649664879
2023-01-23 00:36:41.078791: step: 2012/529, loss: 0.20997053384780884
2023-01-23 00:36:42.195131: step: 2016/529, loss: 0.01845831796526909
2023-01-23 00:36:43.282677: step: 2020/529, loss: 0.0970921516418457
2023-01-23 00:36:44.367916: step: 2024/529, loss: 0.10060720145702362
2023-01-23 00:36:45.486996: step: 2028/529, loss: 0.07642068713903427
2023-01-23 00:36:46.575394: step: 2032/529, loss: 0.7391047477722168
2023-01-23 00:36:47.675361: step: 2036/529, loss: 0.036525726318359375
2023-01-23 00:36:48.777741: step: 2040/529, loss: 0.977632999420166
2023-01-23 00:36:49.885322: step: 2044/529, loss: 0.15666624903678894
2023-01-23 00:36:51.004856: step: 2048/529, loss: 0.05006761848926544
2023-01-23 00:36:52.091461: step: 2052/529, loss: 0.03367052227258682
2023-01-23 00:36:53.187617: step: 2056/529, loss: 0.0880374014377594
2023-01-23 00:36:54.311821: step: 2060/529, loss: 0.3515944480895996
2023-01-23 00:36:55.419615: step: 2064/529, loss: 0.860822856426239
2023-01-23 00:36:56.573782: step: 2068/529, loss: 0.08030586689710617
2023-01-23 00:36:57.701843: step: 2072/529, loss: 0.03577813878655434
2023-01-23 00:36:58.841456: step: 2076/529, loss: 0.07949074357748032
2023-01-23 00:36:59.951871: step: 2080/529, loss: 0.25775212049484253
2023-01-23 00:37:01.051270: step: 2084/529, loss: 0.7873144149780273
2023-01-23 00:37:02.125422: step: 2088/529, loss: 0.09113284200429916
2023-01-23 00:37:03.236690: step: 2092/529, loss: 0.21279078722000122
2023-01-23 00:37:04.378496: step: 2096/529, loss: 0.6283648610115051
2023-01-23 00:37:05.483757: step: 2100/529, loss: 0.06660356372594833
2023-01-23 00:37:06.588896: step: 2104/529, loss: 0.13064375519752502
2023-01-23 00:37:07.695413: step: 2108/529, loss: 0.05028362572193146
2023-01-23 00:37:08.795678: step: 2112/529, loss: 0.14067357778549194
2023-01-23 00:37:09.892366: step: 2116/529, loss: 0.7217963337898254
==================================================
Loss: 0.233
--------------------
Dev: {'event': {'p': 0.66388557806913, 'r': 0.7416777629826897, 'f1': 0.7006289308176101}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6845425867507886, 'r': 0.7347629796839729, 'f1': 0.708764289602613}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.5652173913043478, 'r': 0.7222222222222222, 'f1': 0.6341463414634146}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.6170212765957447, 'r': 0.4603174603174603, 'f1': 0.5272727272727272}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.3939393939393939, 'r': 0.3611111111111111, 'f1': 0.37681159420289856}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:37:49.254853: step: 4/529, loss: 0.08535995334386826
2023-01-23 00:37:50.389735: step: 8/529, loss: 0.016001129522919655
2023-01-23 00:37:51.551271: step: 12/529, loss: 0.10105905681848526
2023-01-23 00:37:52.671844: step: 16/529, loss: 0.1079353615641594
2023-01-23 00:37:53.791127: step: 20/529, loss: 0.05083636939525604
2023-01-23 00:37:54.897853: step: 24/529, loss: 0.03182806819677353
2023-01-23 00:37:55.988730: step: 28/529, loss: 0.0721050500869751
2023-01-23 00:37:57.119080: step: 32/529, loss: 0.13523554801940918
2023-01-23 00:37:58.225898: step: 36/529, loss: 0.04191866144537926
2023-01-23 00:37:59.329775: step: 40/529, loss: 0.051964666694402695
2023-01-23 00:38:00.475002: step: 44/529, loss: 0.17937658727169037
2023-01-23 00:38:01.559543: step: 48/529, loss: 0.03992772102355957
2023-01-23 00:38:02.696870: step: 52/529, loss: 0.11854753643274307
2023-01-23 00:38:03.803316: step: 56/529, loss: 0.0499691516160965
2023-01-23 00:38:04.922114: step: 60/529, loss: 0.05157136917114258
2023-01-23 00:38:06.048321: step: 64/529, loss: 0.20484094321727753
2023-01-23 00:38:07.175321: step: 68/529, loss: 0.2316499650478363
2023-01-23 00:38:08.272622: step: 72/529, loss: 0.0871744155883789
2023-01-23 00:38:09.376804: step: 76/529, loss: 0.07359835505485535
2023-01-23 00:38:10.461115: step: 80/529, loss: 0.3921722173690796
2023-01-23 00:38:11.558754: step: 84/529, loss: 0.1913851648569107
2023-01-23 00:38:12.697121: step: 88/529, loss: 0.06026472896337509
2023-01-23 00:38:13.790649: step: 92/529, loss: 0.09796439111232758
2023-01-23 00:38:14.867837: step: 96/529, loss: 0.03011322021484375
2023-01-23 00:38:16.014387: step: 100/529, loss: 0.32214635610580444
2023-01-23 00:38:17.106192: step: 104/529, loss: 0.11700396984815598
2023-01-23 00:38:18.226536: step: 108/529, loss: 0.04085185378789902
2023-01-23 00:38:19.365921: step: 112/529, loss: 0.0914732962846756
2023-01-23 00:38:20.476733: step: 116/529, loss: 0.04465823248028755
2023-01-23 00:38:21.595921: step: 120/529, loss: 0.13958540558815002
2023-01-23 00:38:22.725468: step: 124/529, loss: 0.07259884476661682
2023-01-23 00:38:23.847310: step: 128/529, loss: 0.08847961574792862
2023-01-23 00:38:24.966341: step: 132/529, loss: 0.08840484917163849
2023-01-23 00:38:26.077477: step: 136/529, loss: 0.1915014237165451
2023-01-23 00:38:27.191003: step: 140/529, loss: 0.12636291980743408
2023-01-23 00:38:28.306565: step: 144/529, loss: 0.08276939392089844
2023-01-23 00:38:29.402064: step: 148/529, loss: 0.03695201873779297
2023-01-23 00:38:30.523403: step: 152/529, loss: 0.07858090847730637
2023-01-23 00:38:31.665900: step: 156/529, loss: 0.06089286878705025
2023-01-23 00:38:32.792302: step: 160/529, loss: 0.12468412518501282
2023-01-23 00:38:33.895507: step: 164/529, loss: 0.04841804504394531
2023-01-23 00:38:35.023796: step: 168/529, loss: 0.19520455598831177
2023-01-23 00:38:36.111953: step: 172/529, loss: 0.042046450078487396
2023-01-23 00:38:37.249902: step: 176/529, loss: 0.10202236473560333
2023-01-23 00:38:38.365407: step: 180/529, loss: 0.026439856737852097
2023-01-23 00:38:39.506406: step: 184/529, loss: 0.013095999136567116
2023-01-23 00:38:40.623989: step: 188/529, loss: 0.0721866562962532
2023-01-23 00:38:41.737998: step: 192/529, loss: 0.13443756103515625
2023-01-23 00:38:42.847160: step: 196/529, loss: 0.005830669775605202
2023-01-23 00:38:43.929279: step: 200/529, loss: 0.03621787950396538
2023-01-23 00:38:45.049305: step: 204/529, loss: 0.019101334735751152
2023-01-23 00:38:46.145792: step: 208/529, loss: 0.18747597932815552
2023-01-23 00:38:47.241014: step: 212/529, loss: 0.0082693574950099
2023-01-23 00:38:48.355720: step: 216/529, loss: 0.059357643127441406
2023-01-23 00:38:49.511438: step: 220/529, loss: 0.1062961146235466
2023-01-23 00:38:50.609828: step: 224/529, loss: 0.13642655313014984
2023-01-23 00:38:51.735301: step: 228/529, loss: 0.12942571938037872
2023-01-23 00:38:52.855731: step: 232/529, loss: 0.010764027014374733
2023-01-23 00:38:53.961378: step: 236/529, loss: 0.022208143025636673
2023-01-23 00:38:55.040479: step: 240/529, loss: 0.19263982772827148
2023-01-23 00:38:56.165755: step: 244/529, loss: 0.02089548110961914
2023-01-23 00:38:57.261807: step: 248/529, loss: 0.0337187759578228
2023-01-23 00:38:58.353827: step: 252/529, loss: 1.025361180305481
2023-01-23 00:38:59.452392: step: 256/529, loss: 0.0693356990814209
2023-01-23 00:39:00.579303: step: 260/529, loss: 0.12926062941551208
2023-01-23 00:39:01.685741: step: 264/529, loss: 0.10652542114257812
2023-01-23 00:39:02.801503: step: 268/529, loss: 0.13642553985118866
2023-01-23 00:39:03.918477: step: 272/529, loss: 0.1928671896457672
2023-01-23 00:39:05.020735: step: 276/529, loss: 0.0912637710571289
2023-01-23 00:39:06.145758: step: 280/529, loss: 0.0898033156991005
2023-01-23 00:39:07.250290: step: 284/529, loss: 0.07509009540081024
2023-01-23 00:39:08.372549: step: 288/529, loss: 0.04311618581414223
2023-01-23 00:39:09.453296: step: 292/529, loss: 0.17369318008422852
2023-01-23 00:39:10.554586: step: 296/529, loss: 0.09234333783388138
2023-01-23 00:39:11.649198: step: 300/529, loss: 0.19594478607177734
2023-01-23 00:39:12.758488: step: 304/529, loss: 0.04409150779247284
2023-01-23 00:39:13.887933: step: 308/529, loss: 0.047379374504089355
2023-01-23 00:39:15.010829: step: 312/529, loss: 0.17639216780662537
2023-01-23 00:39:16.148646: step: 316/529, loss: 0.05121898651123047
2023-01-23 00:39:17.251309: step: 320/529, loss: 0.7693721652030945
2023-01-23 00:39:18.358582: step: 324/529, loss: 0.35669606924057007
2023-01-23 00:39:19.492315: step: 328/529, loss: 0.38664036989212036
2023-01-23 00:39:20.579652: step: 332/529, loss: 0.0558900348842144
2023-01-23 00:39:21.692843: step: 336/529, loss: 0.1913757175207138
2023-01-23 00:39:22.772803: step: 340/529, loss: 0.11070023477077484
2023-01-23 00:39:23.877596: step: 344/529, loss: 0.039197541773319244
2023-01-23 00:39:24.961627: step: 348/529, loss: 0.1517617255449295
2023-01-23 00:39:26.097053: step: 352/529, loss: 0.13259035348892212
2023-01-23 00:39:27.186039: step: 356/529, loss: 0.052670955657958984
2023-01-23 00:39:28.278810: step: 360/529, loss: 0.2514592111110687
2023-01-23 00:39:29.395670: step: 364/529, loss: 0.16890506446361542
2023-01-23 00:39:30.505770: step: 368/529, loss: 0.06347131729125977
2023-01-23 00:39:31.615522: step: 372/529, loss: 0.4140257239341736
2023-01-23 00:39:32.742882: step: 376/529, loss: 0.3851228952407837
2023-01-23 00:39:33.841025: step: 380/529, loss: 0.03889770805835724
2023-01-23 00:39:34.930658: step: 384/529, loss: 0.16113929450511932
2023-01-23 00:39:36.053252: step: 388/529, loss: 0.06517477333545685
2023-01-23 00:39:37.151941: step: 392/529, loss: 0.035893917083740234
2023-01-23 00:39:38.261374: step: 396/529, loss: 0.04008650779724121
2023-01-23 00:39:39.368040: step: 400/529, loss: 0.21062499284744263
2023-01-23 00:39:40.467595: step: 404/529, loss: 0.0751979798078537
2023-01-23 00:39:41.593874: step: 408/529, loss: 0.17072072625160217
2023-01-23 00:39:42.695126: step: 412/529, loss: 0.13009461760520935
2023-01-23 00:39:43.824568: step: 416/529, loss: 0.16932764649391174
2023-01-23 00:39:44.947540: step: 420/529, loss: 0.23037000000476837
2023-01-23 00:39:46.063489: step: 424/529, loss: 0.0965181365609169
2023-01-23 00:39:47.154022: step: 428/529, loss: 0.07707658410072327
2023-01-23 00:39:48.248342: step: 432/529, loss: 0.08312736451625824
2023-01-23 00:39:49.330724: step: 436/529, loss: 0.07003231346607208
2023-01-23 00:39:50.477641: step: 440/529, loss: 0.025251388549804688
2023-01-23 00:39:51.623260: step: 444/529, loss: 0.05140228196978569
2023-01-23 00:39:52.720157: step: 448/529, loss: 0.11442232131958008
2023-01-23 00:39:53.842494: step: 452/529, loss: 0.10901746898889542
2023-01-23 00:39:54.979126: step: 456/529, loss: 0.1073119193315506
2023-01-23 00:39:56.117497: step: 460/529, loss: 0.25079044699668884
2023-01-23 00:39:57.225437: step: 464/529, loss: 0.31729984283447266
2023-01-23 00:39:58.337820: step: 468/529, loss: 0.27446651458740234
2023-01-23 00:39:59.435720: step: 472/529, loss: 0.22311820089817047
2023-01-23 00:40:00.555624: step: 476/529, loss: 0.1324368268251419
2023-01-23 00:40:01.656076: step: 480/529, loss: 0.02860879898071289
2023-01-23 00:40:02.742582: step: 484/529, loss: 0.10911176353693008
2023-01-23 00:40:03.850423: step: 488/529, loss: 0.6487019062042236
2023-01-23 00:40:04.988301: step: 492/529, loss: 0.10456905514001846
2023-01-23 00:40:06.096704: step: 496/529, loss: 0.10264454036951065
2023-01-23 00:40:07.197146: step: 500/529, loss: 0.17587712407112122
2023-01-23 00:40:08.327275: step: 504/529, loss: 0.38415825366973877
2023-01-23 00:40:09.430644: step: 508/529, loss: 0.14278526604175568
2023-01-23 00:40:10.513583: step: 512/529, loss: 0.876387357711792
2023-01-23 00:40:11.627251: step: 516/529, loss: 0.02136249653995037
2023-01-23 00:40:12.742188: step: 520/529, loss: 0.30383986234664917
2023-01-23 00:40:13.865067: step: 524/529, loss: 0.06644754856824875
2023-01-23 00:40:14.978110: step: 528/529, loss: 0.05408506467938423
2023-01-23 00:40:16.083847: step: 532/529, loss: 0.18358105421066284
2023-01-23 00:40:17.175914: step: 536/529, loss: 0.43189141154289246
2023-01-23 00:40:18.285537: step: 540/529, loss: 0.1558370590209961
2023-01-23 00:40:19.408398: step: 544/529, loss: 0.02861003950238228
2023-01-23 00:40:20.488991: step: 548/529, loss: 0.1691078096628189
2023-01-23 00:40:21.595654: step: 552/529, loss: 0.08777222037315369
2023-01-23 00:40:22.725706: step: 556/529, loss: 0.18570689857006073
2023-01-23 00:40:23.827839: step: 560/529, loss: 0.1552501618862152
2023-01-23 00:40:24.935062: step: 564/529, loss: 0.12489528208971024
2023-01-23 00:40:26.042323: step: 568/529, loss: 0.06810909509658813
2023-01-23 00:40:27.122990: step: 572/529, loss: 0.08333795517683029
2023-01-23 00:40:28.231001: step: 576/529, loss: 0.0747753158211708
2023-01-23 00:40:29.320993: step: 580/529, loss: 0.1213603988289833
2023-01-23 00:40:30.437479: step: 584/529, loss: 0.10235204547643661
2023-01-23 00:40:31.516286: step: 588/529, loss: 0.21795593202114105
2023-01-23 00:40:32.628020: step: 592/529, loss: 0.2904343605041504
2023-01-23 00:40:33.734311: step: 596/529, loss: 0.02508638985455036
2023-01-23 00:40:34.813212: step: 600/529, loss: 0.03851909935474396
2023-01-23 00:40:35.927643: step: 604/529, loss: 0.19919902086257935
2023-01-23 00:40:37.073613: step: 608/529, loss: 0.5803912281990051
2023-01-23 00:40:38.186646: step: 612/529, loss: 0.16329871118068695
2023-01-23 00:40:39.337817: step: 616/529, loss: 0.16156300902366638
2023-01-23 00:40:40.439607: step: 620/529, loss: 0.4201776683330536
2023-01-23 00:40:41.569020: step: 624/529, loss: 0.2616937756538391
2023-01-23 00:40:42.697588: step: 628/529, loss: 0.08690319210290909
2023-01-23 00:40:43.817134: step: 632/529, loss: 0.09721431881189346
2023-01-23 00:40:44.957288: step: 636/529, loss: 0.0719393715262413
2023-01-23 00:40:46.059563: step: 640/529, loss: 0.07727108150720596
2023-01-23 00:40:47.149108: step: 644/529, loss: 0.02064523659646511
2023-01-23 00:40:48.278465: step: 648/529, loss: 0.06515903770923615
2023-01-23 00:40:49.379058: step: 652/529, loss: 0.032294370234012604
2023-01-23 00:40:50.518221: step: 656/529, loss: 0.3659224510192871
2023-01-23 00:40:51.605747: step: 660/529, loss: 0.06363248825073242
2023-01-23 00:40:52.707226: step: 664/529, loss: 0.1395689994096756
2023-01-23 00:40:53.832364: step: 668/529, loss: 0.1669834703207016
2023-01-23 00:40:54.938614: step: 672/529, loss: 0.07678094506263733
2023-01-23 00:40:56.070694: step: 676/529, loss: 0.18050357699394226
2023-01-23 00:40:57.170381: step: 680/529, loss: 0.03705973923206329
2023-01-23 00:40:58.305166: step: 684/529, loss: 0.20744390785694122
2023-01-23 00:40:59.414278: step: 688/529, loss: 0.11302336305379868
2023-01-23 00:41:00.543826: step: 692/529, loss: 0.0552794486284256
2023-01-23 00:41:01.686653: step: 696/529, loss: 0.10831566154956818
2023-01-23 00:41:02.802143: step: 700/529, loss: 0.14847736060619354
2023-01-23 00:41:03.923201: step: 704/529, loss: 0.10636377334594727
2023-01-23 00:41:05.030274: step: 708/529, loss: 0.10097765922546387
2023-01-23 00:41:06.167769: step: 712/529, loss: 0.14710339903831482
2023-01-23 00:41:07.286937: step: 716/529, loss: 0.04197302088141441
2023-01-23 00:41:08.388118: step: 720/529, loss: 0.35984688997268677
2023-01-23 00:41:09.482986: step: 724/529, loss: 1.2314952611923218
2023-01-23 00:41:10.601439: step: 728/529, loss: 0.08138785511255264
2023-01-23 00:41:11.707236: step: 732/529, loss: 0.13064813613891602
2023-01-23 00:41:12.823205: step: 736/529, loss: 0.0573970302939415
2023-01-23 00:41:13.933738: step: 740/529, loss: 0.08001823723316193
2023-01-23 00:41:15.065166: step: 744/529, loss: 0.14377526938915253
2023-01-23 00:41:16.199818: step: 748/529, loss: 0.12418365478515625
2023-01-23 00:41:17.354774: step: 752/529, loss: 0.037191201001405716
2023-01-23 00:41:18.437929: step: 756/529, loss: 0.07091245800256729
2023-01-23 00:41:19.558998: step: 760/529, loss: 0.1054040938615799
2023-01-23 00:41:20.689088: step: 764/529, loss: 0.0629824697971344
2023-01-23 00:41:21.780288: step: 768/529, loss: 0.09661710262298584
2023-01-23 00:41:22.904627: step: 772/529, loss: 0.10616204887628555
2023-01-23 00:41:23.989765: step: 776/529, loss: 0.05436534807085991
2023-01-23 00:41:25.117601: step: 780/529, loss: 0.08986649662256241
2023-01-23 00:41:26.211150: step: 784/529, loss: 0.15237101912498474
2023-01-23 00:41:27.334526: step: 788/529, loss: 0.03706107288599014
2023-01-23 00:41:28.421032: step: 792/529, loss: 0.06959257274866104
2023-01-23 00:41:29.533433: step: 796/529, loss: 0.041742704808712006
2023-01-23 00:41:30.656963: step: 800/529, loss: 0.08936090767383575
2023-01-23 00:41:31.814068: step: 804/529, loss: 0.16828516125679016
2023-01-23 00:41:32.952168: step: 808/529, loss: 0.09065123647451401
2023-01-23 00:41:34.059598: step: 812/529, loss: 0.12946276366710663
2023-01-23 00:41:35.143950: step: 816/529, loss: 0.05584364011883736
2023-01-23 00:41:36.241498: step: 820/529, loss: 0.49276256561279297
2023-01-23 00:41:37.332853: step: 824/529, loss: 0.11095300316810608
2023-01-23 00:41:38.450871: step: 828/529, loss: 0.06222191080451012
2023-01-23 00:41:39.558820: step: 832/529, loss: 0.07886314392089844
2023-01-23 00:41:40.658214: step: 836/529, loss: 0.1289811134338379
2023-01-23 00:41:41.737326: step: 840/529, loss: 0.05126838758587837
2023-01-23 00:41:42.839278: step: 844/529, loss: 0.12138824164867401
2023-01-23 00:41:43.928903: step: 848/529, loss: 0.0704202651977539
2023-01-23 00:41:45.031723: step: 852/529, loss: 0.03680281713604927
2023-01-23 00:41:46.109207: step: 856/529, loss: 0.007145881652832031
2023-01-23 00:41:47.230870: step: 860/529, loss: 0.06799888610839844
2023-01-23 00:41:48.330809: step: 864/529, loss: 0.0625530257821083
2023-01-23 00:41:49.412371: step: 868/529, loss: 0.2909412384033203
2023-01-23 00:41:50.521304: step: 872/529, loss: 0.1304069459438324
2023-01-23 00:41:51.624413: step: 876/529, loss: 0.14396364986896515
2023-01-23 00:41:52.718871: step: 880/529, loss: 0.38703393936157227
2023-01-23 00:41:53.834104: step: 884/529, loss: 0.12164366245269775
2023-01-23 00:41:54.961664: step: 888/529, loss: 0.07425308227539062
2023-01-23 00:41:56.071069: step: 892/529, loss: 0.35207778215408325
2023-01-23 00:41:57.191651: step: 896/529, loss: 0.16876216232776642
2023-01-23 00:41:58.298022: step: 900/529, loss: 0.08585414290428162
2023-01-23 00:41:59.430496: step: 904/529, loss: 0.08714637905359268
2023-01-23 00:42:00.537275: step: 908/529, loss: 0.13681745529174805
2023-01-23 00:42:01.646513: step: 912/529, loss: 0.06272868812084198
2023-01-23 00:42:02.819711: step: 916/529, loss: 0.0487370528280735
2023-01-23 00:42:03.981173: step: 920/529, loss: 0.17080570757389069
2023-01-23 00:42:05.135357: step: 924/529, loss: 0.06933536380529404
2023-01-23 00:42:06.257086: step: 928/529, loss: 0.0676342025399208
2023-01-23 00:42:07.370186: step: 932/529, loss: 0.27520352602005005
2023-01-23 00:42:08.496395: step: 936/529, loss: 0.1539454460144043
2023-01-23 00:42:09.618864: step: 940/529, loss: 1.416111707687378
2023-01-23 00:42:10.759322: step: 944/529, loss: 0.1712416708469391
2023-01-23 00:42:11.880255: step: 948/529, loss: 0.1625732034444809
2023-01-23 00:42:12.997584: step: 952/529, loss: 0.08752937614917755
2023-01-23 00:42:14.098723: step: 956/529, loss: 0.23820781707763672
2023-01-23 00:42:15.226511: step: 960/529, loss: 0.06130237877368927
2023-01-23 00:42:16.324309: step: 964/529, loss: 0.22669734060764313
2023-01-23 00:42:17.466129: step: 968/529, loss: 0.09415054321289062
2023-01-23 00:42:18.565034: step: 972/529, loss: 0.02753582037985325
2023-01-23 00:42:19.710427: step: 976/529, loss: 0.22043377161026
2023-01-23 00:42:20.826486: step: 980/529, loss: 0.06653241813182831
2023-01-23 00:42:21.944750: step: 984/529, loss: 0.15861931443214417
2023-01-23 00:42:23.055118: step: 988/529, loss: 0.1564960777759552
2023-01-23 00:42:24.204266: step: 992/529, loss: 0.060117244720458984
2023-01-23 00:42:25.321998: step: 996/529, loss: 0.21202115714550018
2023-01-23 00:42:26.446339: step: 1000/529, loss: 0.1770804524421692
2023-01-23 00:42:27.574149: step: 1004/529, loss: 0.17375174164772034
2023-01-23 00:42:28.720866: step: 1008/529, loss: 0.38376694917678833
2023-01-23 00:42:29.852742: step: 1012/529, loss: 0.04024467617273331
2023-01-23 00:42:30.943839: step: 1016/529, loss: 0.15649671852588654
2023-01-23 00:42:32.027951: step: 1020/529, loss: 0.07410085201263428
2023-01-23 00:42:33.154827: step: 1024/529, loss: 0.08371081948280334
2023-01-23 00:42:34.255971: step: 1028/529, loss: 0.43277493119239807
2023-01-23 00:42:35.355915: step: 1032/529, loss: 0.11992263793945312
2023-01-23 00:42:36.454159: step: 1036/529, loss: 0.12016751617193222
2023-01-23 00:42:37.588622: step: 1040/529, loss: 0.12992163002490997
2023-01-23 00:42:38.699766: step: 1044/529, loss: 0.025912238284945488
2023-01-23 00:42:39.792645: step: 1048/529, loss: 0.5583709478378296
2023-01-23 00:42:40.914804: step: 1052/529, loss: 0.14327797293663025
2023-01-23 00:42:42.027197: step: 1056/529, loss: 0.1275242418050766
2023-01-23 00:42:43.131838: step: 1060/529, loss: 0.15893106162548065
2023-01-23 00:42:44.235539: step: 1064/529, loss: 0.1193297952413559
2023-01-23 00:42:45.347726: step: 1068/529, loss: 0.054459381848573685
2023-01-23 00:42:46.453846: step: 1072/529, loss: 0.17819052934646606
2023-01-23 00:42:47.562744: step: 1076/529, loss: 0.15902462601661682
2023-01-23 00:42:48.692518: step: 1080/529, loss: 0.14294835925102234
2023-01-23 00:42:49.806245: step: 1084/529, loss: 0.05848880112171173
2023-01-23 00:42:50.922745: step: 1088/529, loss: 0.10031929612159729
2023-01-23 00:42:52.011664: step: 1092/529, loss: 0.31642967462539673
2023-01-23 00:42:53.106340: step: 1096/529, loss: 0.2695261538028717
2023-01-23 00:42:54.194855: step: 1100/529, loss: 0.2811482548713684
2023-01-23 00:42:55.310534: step: 1104/529, loss: 0.05957643687725067
2023-01-23 00:42:56.440193: step: 1108/529, loss: 0.062278151512145996
2023-01-23 00:42:57.576395: step: 1112/529, loss: 0.021506119519472122
2023-01-23 00:42:58.675819: step: 1116/529, loss: 0.7041778564453125
2023-01-23 00:42:59.778863: step: 1120/529, loss: 0.09198732674121857
2023-01-23 00:43:00.886820: step: 1124/529, loss: 0.08571124076843262
2023-01-23 00:43:01.971251: step: 1128/529, loss: 0.06545896828174591
2023-01-23 00:43:03.082769: step: 1132/529, loss: 0.0499020554125309
2023-01-23 00:43:04.184431: step: 1136/529, loss: 0.04824574291706085
2023-01-23 00:43:05.310375: step: 1140/529, loss: 0.04275684431195259
2023-01-23 00:43:06.418333: step: 1144/529, loss: 0.07564029842615128
2023-01-23 00:43:07.507664: step: 1148/529, loss: 0.05088425055146217
2023-01-23 00:43:08.621367: step: 1152/529, loss: 0.08161468803882599
2023-01-23 00:43:09.737458: step: 1156/529, loss: 0.16641655564308167
2023-01-23 00:43:10.853278: step: 1160/529, loss: 0.08168898522853851
2023-01-23 00:43:11.973088: step: 1164/529, loss: 0.19990329444408417
2023-01-23 00:43:13.081897: step: 1168/529, loss: 0.07986479252576828
2023-01-23 00:43:14.183122: step: 1172/529, loss: 0.15243932604789734
2023-01-23 00:43:15.291435: step: 1176/529, loss: 0.055414773523807526
2023-01-23 00:43:16.401300: step: 1180/529, loss: 0.10719247162342072
2023-01-23 00:43:17.519450: step: 1184/529, loss: 0.011735511012375355
2023-01-23 00:43:18.652672: step: 1188/529, loss: 0.2419900894165039
2023-01-23 00:43:19.752757: step: 1192/529, loss: 0.06695299595594406
2023-01-23 00:43:20.856379: step: 1196/529, loss: 0.6303110718727112
2023-01-23 00:43:21.968896: step: 1200/529, loss: 0.11464748531579971
2023-01-23 00:43:23.113214: step: 1204/529, loss: 0.6920454502105713
2023-01-23 00:43:24.221039: step: 1208/529, loss: 0.05030231550335884
2023-01-23 00:43:25.332391: step: 1212/529, loss: 0.12416372448205948
2023-01-23 00:43:26.450687: step: 1216/529, loss: 0.03824073076248169
2023-01-23 00:43:27.556966: step: 1220/529, loss: 0.3069017231464386
2023-01-23 00:43:28.652159: step: 1224/529, loss: 0.18959569931030273
2023-01-23 00:43:29.784785: step: 1228/529, loss: 0.08258872479200363
2023-01-23 00:43:30.890919: step: 1232/529, loss: 0.3074410557746887
2023-01-23 00:43:31.996568: step: 1236/529, loss: 0.2622811198234558
2023-01-23 00:43:33.136415: step: 1240/529, loss: 0.12124772369861603
2023-01-23 00:43:34.234443: step: 1244/529, loss: 0.0762840211391449
2023-01-23 00:43:35.312942: step: 1248/529, loss: 0.042694661766290665
2023-01-23 00:43:36.405954: step: 1252/529, loss: 0.12141668796539307
2023-01-23 00:43:37.563583: step: 1256/529, loss: 0.07203512638807297
2023-01-23 00:43:38.674919: step: 1260/529, loss: 0.9234479069709778
2023-01-23 00:43:39.770784: step: 1264/529, loss: 0.03592194616794586
2023-01-23 00:43:40.871775: step: 1268/529, loss: 0.016762543469667435
2023-01-23 00:43:41.990969: step: 1272/529, loss: 0.11272773891687393
2023-01-23 00:43:43.108482: step: 1276/529, loss: 0.10014477372169495
2023-01-23 00:43:44.230878: step: 1280/529, loss: 0.07927493751049042
2023-01-23 00:43:45.348110: step: 1284/529, loss: 0.18116407096385956
2023-01-23 00:43:46.453410: step: 1288/529, loss: 0.07261667400598526
2023-01-23 00:43:47.587040: step: 1292/529, loss: 0.12926602363586426
2023-01-23 00:43:48.714032: step: 1296/529, loss: 0.08017349243164062
2023-01-23 00:43:49.852642: step: 1300/529, loss: 0.5795788168907166
2023-01-23 00:43:50.961004: step: 1304/529, loss: 0.11471805721521378
2023-01-23 00:43:52.073689: step: 1308/529, loss: 0.6441377997398376
2023-01-23 00:43:53.187510: step: 1312/529, loss: 0.9785250425338745
2023-01-23 00:43:54.311156: step: 1316/529, loss: 0.15522976219654083
2023-01-23 00:43:55.402655: step: 1320/529, loss: 0.1446654349565506
2023-01-23 00:43:56.499437: step: 1324/529, loss: 0.07780542224645615
2023-01-23 00:43:57.601452: step: 1328/529, loss: 0.04367389902472496
2023-01-23 00:43:58.703411: step: 1332/529, loss: 0.1036238744854927
2023-01-23 00:43:59.850809: step: 1336/529, loss: 0.14732956886291504
2023-01-23 00:44:00.983580: step: 1340/529, loss: 0.10989589989185333
2023-01-23 00:44:02.111877: step: 1344/529, loss: 0.06113891676068306
2023-01-23 00:44:03.194512: step: 1348/529, loss: 0.316057026386261
2023-01-23 00:44:04.271444: step: 1352/529, loss: 0.11345696449279785
2023-01-23 00:44:05.399343: step: 1356/529, loss: 0.03488645702600479
2023-01-23 00:44:06.513795: step: 1360/529, loss: 0.14009495079517365
2023-01-23 00:44:07.624109: step: 1364/529, loss: 0.20713704824447632
2023-01-23 00:44:08.754164: step: 1368/529, loss: 0.03848094865679741
2023-01-23 00:44:09.868811: step: 1372/529, loss: 0.09145593643188477
2023-01-23 00:44:11.010789: step: 1376/529, loss: 0.42008477449417114
2023-01-23 00:44:12.143779: step: 1380/529, loss: 0.04385938495397568
2023-01-23 00:44:13.277631: step: 1384/529, loss: 0.21850094199180603
2023-01-23 00:44:14.385819: step: 1388/529, loss: 0.14133116602897644
2023-01-23 00:44:15.503295: step: 1392/529, loss: 0.14615249633789062
2023-01-23 00:44:16.591118: step: 1396/529, loss: 0.09533253312110901
2023-01-23 00:44:17.709887: step: 1400/529, loss: 0.0530826561152935
2023-01-23 00:44:18.809642: step: 1404/529, loss: 0.050835803151130676
2023-01-23 00:44:19.915028: step: 1408/529, loss: 0.8031697869300842
2023-01-23 00:44:21.011229: step: 1412/529, loss: 0.0764227882027626
2023-01-23 00:44:22.132888: step: 1416/529, loss: 0.17257362604141235
2023-01-23 00:44:23.258445: step: 1420/529, loss: 0.34137916564941406
2023-01-23 00:44:24.350379: step: 1424/529, loss: 0.02362356148660183
2023-01-23 00:44:25.511997: step: 1428/529, loss: 0.07728901505470276
2023-01-23 00:44:26.606306: step: 1432/529, loss: 1.083054542541504
2023-01-23 00:44:27.742640: step: 1436/529, loss: 0.3218139708042145
2023-01-23 00:44:28.837691: step: 1440/529, loss: 0.08511407673358917
2023-01-23 00:44:29.943389: step: 1444/529, loss: 0.029111862182617188
2023-01-23 00:44:31.036181: step: 1448/529, loss: 0.06409845501184464
2023-01-23 00:44:32.153227: step: 1452/529, loss: 0.028685474768280983
2023-01-23 00:44:33.290813: step: 1456/529, loss: 0.25656455755233765
2023-01-23 00:44:34.416096: step: 1460/529, loss: 0.1137796938419342
2023-01-23 00:44:35.516627: step: 1464/529, loss: 0.02136397361755371
2023-01-23 00:44:36.625291: step: 1468/529, loss: 0.04566369205713272
2023-01-23 00:44:37.723716: step: 1472/529, loss: 0.08377714455127716
2023-01-23 00:44:38.828231: step: 1476/529, loss: 0.10929107666015625
2023-01-23 00:44:39.944310: step: 1480/529, loss: 0.034664154052734375
2023-01-23 00:44:41.078493: step: 1484/529, loss: 0.06072532385587692
2023-01-23 00:44:42.192074: step: 1488/529, loss: 0.15987873077392578
2023-01-23 00:44:43.310894: step: 1492/529, loss: 0.07636241614818573
2023-01-23 00:44:44.437454: step: 1496/529, loss: 0.22534483671188354
2023-01-23 00:44:45.559737: step: 1500/529, loss: 0.05913911014795303
2023-01-23 00:44:46.652406: step: 1504/529, loss: 0.040613315999507904
2023-01-23 00:44:47.766096: step: 1508/529, loss: 0.005683040712028742
2023-01-23 00:44:48.886752: step: 1512/529, loss: 0.04234590381383896
2023-01-23 00:44:50.003393: step: 1516/529, loss: 0.08957324177026749
2023-01-23 00:44:51.080530: step: 1520/529, loss: 0.10978803783655167
2023-01-23 00:44:52.198120: step: 1524/529, loss: 0.13055287301540375
2023-01-23 00:44:53.318399: step: 1528/529, loss: 0.7986448407173157
2023-01-23 00:44:54.460716: step: 1532/529, loss: 0.06465015560388565
2023-01-23 00:44:55.559541: step: 1536/529, loss: 0.1254071295261383
2023-01-23 00:44:56.670859: step: 1540/529, loss: 0.15743064880371094
2023-01-23 00:44:57.776320: step: 1544/529, loss: 0.02288849465548992
2023-01-23 00:44:58.892730: step: 1548/529, loss: 0.27756041288375854
2023-01-23 00:45:00.017270: step: 1552/529, loss: 1.0142234563827515
2023-01-23 00:45:01.108940: step: 1556/529, loss: 0.24193666875362396
2023-01-23 00:45:02.217461: step: 1560/529, loss: 0.05651231110095978
2023-01-23 00:45:03.351356: step: 1564/529, loss: 0.2549936771392822
2023-01-23 00:45:04.480548: step: 1568/529, loss: 0.1243053525686264
2023-01-23 00:45:05.590745: step: 1572/529, loss: 0.3023591935634613
2023-01-23 00:45:06.736124: step: 1576/529, loss: 0.13557367026805878
2023-01-23 00:45:07.862788: step: 1580/529, loss: 0.10327358543872833
2023-01-23 00:45:08.990934: step: 1584/529, loss: 0.042285822331905365
2023-01-23 00:45:10.094696: step: 1588/529, loss: 0.05124945566058159
2023-01-23 00:45:11.245774: step: 1592/529, loss: 0.24578005075454712
2023-01-23 00:45:12.351937: step: 1596/529, loss: 0.002261877292767167
2023-01-23 00:45:13.484203: step: 1600/529, loss: 0.12609444558620453
2023-01-23 00:45:14.633673: step: 1604/529, loss: 0.032897043973207474
2023-01-23 00:45:15.736123: step: 1608/529, loss: 0.23663026094436646
2023-01-23 00:45:16.826108: step: 1612/529, loss: 0.03747249022126198
2023-01-23 00:45:17.943474: step: 1616/529, loss: 0.326956570148468
2023-01-23 00:45:19.082900: step: 1620/529, loss: 0.24182011187076569
2023-01-23 00:45:20.239563: step: 1624/529, loss: 0.11921420693397522
2023-01-23 00:45:21.346879: step: 1628/529, loss: 0.23733974993228912
2023-01-23 00:45:22.463381: step: 1632/529, loss: 0.1739656925201416
2023-01-23 00:45:23.572728: step: 1636/529, loss: 0.1930617392063141
2023-01-23 00:45:24.691688: step: 1640/529, loss: 0.13622340559959412
2023-01-23 00:45:25.804338: step: 1644/529, loss: 0.09134988486766815
2023-01-23 00:45:26.871235: step: 1648/529, loss: 0.11957743763923645
2023-01-23 00:45:27.976177: step: 1652/529, loss: 0.17525739967823029
2023-01-23 00:45:29.088542: step: 1656/529, loss: 0.14496764540672302
2023-01-23 00:45:30.193602: step: 1660/529, loss: 0.07576890289783478
2023-01-23 00:45:31.293837: step: 1664/529, loss: 0.039725493639707565
2023-01-23 00:45:32.403832: step: 1668/529, loss: 0.25583988428115845
2023-01-23 00:45:33.537399: step: 1672/529, loss: 0.10584848374128342
2023-01-23 00:45:34.681522: step: 1676/529, loss: 0.08671937137842178
2023-01-23 00:45:35.808170: step: 1680/529, loss: 0.24428725242614746
2023-01-23 00:45:36.926011: step: 1684/529, loss: 0.02268686331808567
2023-01-23 00:45:38.062014: step: 1688/529, loss: 0.1452745497226715
2023-01-23 00:45:39.175626: step: 1692/529, loss: 0.13715052604675293
2023-01-23 00:45:40.302328: step: 1696/529, loss: 0.24294573068618774
2023-01-23 00:45:41.425404: step: 1700/529, loss: 0.046733953058719635
2023-01-23 00:45:42.553259: step: 1704/529, loss: 0.12026557326316833
2023-01-23 00:45:43.666560: step: 1708/529, loss: 0.5860031843185425
2023-01-23 00:45:44.766297: step: 1712/529, loss: 0.14337225258350372
2023-01-23 00:45:45.868552: step: 1716/529, loss: 0.015405749902129173
2023-01-23 00:45:46.961749: step: 1720/529, loss: 0.1179957389831543
2023-01-23 00:45:48.055175: step: 1724/529, loss: 0.07472304999828339
2023-01-23 00:45:49.163316: step: 1728/529, loss: 0.04063577577471733
2023-01-23 00:45:50.268660: step: 1732/529, loss: 0.2767406404018402
2023-01-23 00:45:51.403879: step: 1736/529, loss: 0.14368943870067596
2023-01-23 00:45:52.511657: step: 1740/529, loss: 0.03707614168524742
2023-01-23 00:45:53.617421: step: 1744/529, loss: 0.08122568577528
2023-01-23 00:45:54.740779: step: 1748/529, loss: 0.3294723331928253
2023-01-23 00:45:55.830737: step: 1752/529, loss: 0.2733578681945801
2023-01-23 00:45:56.954989: step: 1756/529, loss: 0.10837097465991974
2023-01-23 00:45:58.069643: step: 1760/529, loss: 0.13828545808792114
2023-01-23 00:45:59.147219: step: 1764/529, loss: 0.025430480018258095
2023-01-23 00:46:00.296852: step: 1768/529, loss: 0.2437111884355545
2023-01-23 00:46:01.405356: step: 1772/529, loss: 0.846227765083313
2023-01-23 00:46:02.510853: step: 1776/529, loss: 0.19628086686134338
2023-01-23 00:46:03.608313: step: 1780/529, loss: 0.02281503565609455
2023-01-23 00:46:04.719463: step: 1784/529, loss: 0.11977167427539825
2023-01-23 00:46:05.821441: step: 1788/529, loss: 0.049698732793331146
2023-01-23 00:46:06.924634: step: 1792/529, loss: 0.09053479135036469
2023-01-23 00:46:08.029042: step: 1796/529, loss: 0.010919428430497646
2023-01-23 00:46:09.138775: step: 1800/529, loss: 0.0467991828918457
2023-01-23 00:46:10.247829: step: 1804/529, loss: 0.1239691749215126
2023-01-23 00:46:11.377527: step: 1808/529, loss: 0.07301340252161026
2023-01-23 00:46:12.496252: step: 1812/529, loss: 1.4295861721038818
2023-01-23 00:46:13.589395: step: 1816/529, loss: 0.12106428295373917
2023-01-23 00:46:14.678312: step: 1820/529, loss: 0.10724583268165588
2023-01-23 00:46:15.806822: step: 1824/529, loss: 0.12029847502708435
2023-01-23 00:46:16.901776: step: 1828/529, loss: 0.09509435296058655
2023-01-23 00:46:18.000205: step: 1832/529, loss: 0.3433665335178375
2023-01-23 00:46:19.124860: step: 1836/529, loss: 0.3622245788574219
2023-01-23 00:46:20.230373: step: 1840/529, loss: 0.2004317343235016
2023-01-23 00:46:21.382085: step: 1844/529, loss: 0.07593774795532227
2023-01-23 00:46:22.510583: step: 1848/529, loss: 0.11956129968166351
2023-01-23 00:46:23.643270: step: 1852/529, loss: 0.13061046600341797
2023-01-23 00:46:24.750510: step: 1856/529, loss: 0.011540794745087624
2023-01-23 00:46:25.857694: step: 1860/529, loss: 0.15258969366550446
2023-01-23 00:46:26.983549: step: 1864/529, loss: 0.3293248116970062
2023-01-23 00:46:28.078114: step: 1868/529, loss: 0.1792701780796051
2023-01-23 00:46:29.193847: step: 1872/529, loss: 0.05549650266766548
2023-01-23 00:46:30.273952: step: 1876/529, loss: 0.04407348483800888
2023-01-23 00:46:31.382138: step: 1880/529, loss: 0.18867263197898865
2023-01-23 00:46:32.501362: step: 1884/529, loss: 0.1611851304769516
2023-01-23 00:46:33.609792: step: 1888/529, loss: 2.4172065258026123
2023-01-23 00:46:34.720289: step: 1892/529, loss: 0.02128305472433567
2023-01-23 00:46:35.816124: step: 1896/529, loss: 0.09441566467285156
2023-01-23 00:46:36.929775: step: 1900/529, loss: 0.09435348212718964
2023-01-23 00:46:38.026962: step: 1904/529, loss: 0.12584267556667328
2023-01-23 00:46:39.168240: step: 1908/529, loss: 0.32921791076660156
2023-01-23 00:46:40.264205: step: 1912/529, loss: 0.11085724830627441
2023-01-23 00:46:41.356956: step: 1916/529, loss: 0.05103917047381401
2023-01-23 00:46:42.491570: step: 1920/529, loss: 0.11318647861480713
2023-01-23 00:46:43.579561: step: 1924/529, loss: 0.048955440521240234
2023-01-23 00:46:44.678189: step: 1928/529, loss: 0.24831648170948029
2023-01-23 00:46:45.795338: step: 1932/529, loss: 0.6102821230888367
2023-01-23 00:46:46.932145: step: 1936/529, loss: 0.22656604647636414
2023-01-23 00:46:48.051651: step: 1940/529, loss: 0.08460502326488495
2023-01-23 00:46:49.173770: step: 1944/529, loss: 0.24833299219608307
2023-01-23 00:46:50.276980: step: 1948/529, loss: 0.022953206673264503
2023-01-23 00:46:51.386715: step: 1952/529, loss: 0.13200822472572327
2023-01-23 00:46:52.508058: step: 1956/529, loss: 0.49229127168655396
2023-01-23 00:46:53.606111: step: 1960/529, loss: 0.018326759338378906
2023-01-23 00:46:54.722324: step: 1964/529, loss: 0.07689686119556427
2023-01-23 00:46:55.844626: step: 1968/529, loss: 0.1271245926618576
2023-01-23 00:46:56.963862: step: 1972/529, loss: 0.08844394981861115
2023-01-23 00:46:58.099518: step: 1976/529, loss: 0.1441512107849121
2023-01-23 00:46:59.202359: step: 1980/529, loss: 0.013108921237289906
2023-01-23 00:47:00.332841: step: 1984/529, loss: 0.06107616424560547
2023-01-23 00:47:01.432567: step: 1988/529, loss: 0.057968832552433014
2023-01-23 00:47:02.540910: step: 1992/529, loss: 0.19316329061985016
2023-01-23 00:47:03.651191: step: 1996/529, loss: 0.10691499710083008
2023-01-23 00:47:04.742676: step: 2000/529, loss: 0.1370590329170227
2023-01-23 00:47:05.862238: step: 2004/529, loss: 0.3125910758972168
2023-01-23 00:47:07.007682: step: 2008/529, loss: 0.09253168106079102
2023-01-23 00:47:08.144212: step: 2012/529, loss: 0.12707695364952087
2023-01-23 00:47:09.270168: step: 2016/529, loss: 0.04439949989318848
2023-01-23 00:47:10.378470: step: 2020/529, loss: 0.09081140160560608
2023-01-23 00:47:11.496405: step: 2024/529, loss: 0.040528394281864166
2023-01-23 00:47:12.640762: step: 2028/529, loss: 0.11726704239845276
2023-01-23 00:47:13.759910: step: 2032/529, loss: 0.05750226974487305
2023-01-23 00:47:14.856651: step: 2036/529, loss: 0.1197289451956749
2023-01-23 00:47:15.929326: step: 2040/529, loss: 0.11227035522460938
2023-01-23 00:47:17.023925: step: 2044/529, loss: 0.08200503885746002
2023-01-23 00:47:18.118460: step: 2048/529, loss: 0.0762428343296051
2023-01-23 00:47:19.242753: step: 2052/529, loss: 0.140770822763443
2023-01-23 00:47:20.350897: step: 2056/529, loss: 0.19765663146972656
2023-01-23 00:47:21.468308: step: 2060/529, loss: 0.07162541896104813
2023-01-23 00:47:22.581276: step: 2064/529, loss: 0.05690574645996094
2023-01-23 00:47:23.657713: step: 2068/529, loss: 0.06004057079553604
2023-01-23 00:47:24.761059: step: 2072/529, loss: 0.04730527475476265
2023-01-23 00:47:25.880501: step: 2076/529, loss: 0.983487069606781
2023-01-23 00:47:27.009409: step: 2080/529, loss: 0.07275024056434631
2023-01-23 00:47:28.121927: step: 2084/529, loss: 0.11760297417640686
2023-01-23 00:47:29.235675: step: 2088/529, loss: 0.028754521161317825
2023-01-23 00:47:30.324507: step: 2092/529, loss: 0.23850007355213165
2023-01-23 00:47:31.414029: step: 2096/529, loss: 0.08069562911987305
2023-01-23 00:47:32.507874: step: 2100/529, loss: 0.04391040652990341
2023-01-23 00:47:33.609067: step: 2104/529, loss: 0.019821597263216972
2023-01-23 00:47:34.706203: step: 2108/529, loss: 0.46703338623046875
2023-01-23 00:47:35.798942: step: 2112/529, loss: 0.12980279326438904
2023-01-23 00:47:36.924206: step: 2116/529, loss: 0.07758083939552307
==================================================
Loss: 0.162
--------------------
Dev: {'event': {'p': 0.58, 'r': 0.7723035952063915, 'f1': 0.6624785836664763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6209532374100719, 'r': 0.7793453724604966, 'f1': 0.6911911911911912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5476190476190477, 'r': 0.8518518518518519, 'f1': 0.6666666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.603448275862069, 'r': 0.5555555555555556, 'f1': 0.5785123966942148}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6170442286947141, 'r': 0.7616511318242344, 'f1': 0.6817640047675805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6101614434947769, 'r': 0.7251693002257337, 'f1': 0.662712738525013}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6052631578947368, 'r': 0.8518518518518519, 'f1': 0.7076923076923076}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 00:48:17.031536: step: 4/529, loss: 0.03989434242248535
2023-01-23 00:48:18.182974: step: 8/529, loss: 0.2188451737165451
2023-01-23 00:48:19.315297: step: 12/529, loss: 0.10504093766212463
2023-01-23 00:48:20.426334: step: 16/529, loss: 0.309755802154541
2023-01-23 00:48:21.534693: step: 20/529, loss: 0.11937002837657928
2023-01-23 00:48:22.620216: step: 24/529, loss: 0.06205105409026146
2023-01-23 00:48:23.740718: step: 28/529, loss: 0.09447021782398224
2023-01-23 00:48:24.862976: step: 32/529, loss: 0.09353575855493546
2023-01-23 00:48:25.994639: step: 36/529, loss: 0.1375660002231598
2023-01-23 00:48:27.087591: step: 40/529, loss: 0.17229272425174713
2023-01-23 00:48:28.180814: step: 44/529, loss: 0.06236105039715767
2023-01-23 00:48:29.303056: step: 48/529, loss: 0.06906719505786896
2023-01-23 00:48:30.419745: step: 52/529, loss: 0.05072145536541939
2023-01-23 00:48:31.522928: step: 56/529, loss: 0.2119751125574112
2023-01-23 00:48:32.664904: step: 60/529, loss: 0.14456796646118164
2023-01-23 00:48:33.751341: step: 64/529, loss: 0.015509462915360928
2023-01-23 00:48:34.842909: step: 68/529, loss: 0.16052651405334473
2023-01-23 00:48:35.937806: step: 72/529, loss: 0.10224280506372452
2023-01-23 00:48:37.046598: step: 76/529, loss: 0.04146871715784073
2023-01-23 00:48:38.185516: step: 80/529, loss: 0.16864213347434998
2023-01-23 00:48:39.318318: step: 84/529, loss: 0.020550251007080078
2023-01-23 00:48:40.411616: step: 88/529, loss: 0.08963613212108612
2023-01-23 00:48:41.517383: step: 92/529, loss: 0.061861325055360794
2023-01-23 00:48:42.648828: step: 96/529, loss: 0.07162876427173615
2023-01-23 00:48:43.779557: step: 100/529, loss: 0.055115606635808945
2023-01-23 00:48:44.889991: step: 104/529, loss: 0.03399200364947319
2023-01-23 00:48:45.982041: step: 108/529, loss: 0.08677015453577042
2023-01-23 00:48:47.095405: step: 112/529, loss: 0.25093039870262146
2023-01-23 00:48:48.198001: step: 116/529, loss: 0.006470757536590099
2023-01-23 00:48:49.329318: step: 120/529, loss: 0.1085021048784256
2023-01-23 00:48:50.420980: step: 124/529, loss: 0.09303541481494904
2023-01-23 00:48:51.573774: step: 128/529, loss: 0.03469095379114151
2023-01-23 00:48:52.687133: step: 132/529, loss: 0.01894378662109375
2023-01-23 00:48:53.789088: step: 136/529, loss: 0.6561349630355835
2023-01-23 00:48:54.891730: step: 140/529, loss: 0.4928744435310364
2023-01-23 00:48:55.997880: step: 144/529, loss: 0.05222949758172035
2023-01-23 00:48:57.096633: step: 148/529, loss: 0.07344484329223633
2023-01-23 00:48:58.215161: step: 152/529, loss: 0.6262034177780151
2023-01-23 00:48:59.315504: step: 156/529, loss: 0.02418375015258789
2023-01-23 00:49:00.488458: step: 160/529, loss: 0.13597603142261505
2023-01-23 00:49:01.600643: step: 164/529, loss: 0.0391719825565815
2023-01-23 00:49:02.733330: step: 168/529, loss: 0.09543323516845703
2023-01-23 00:49:03.829446: step: 172/529, loss: 0.022873498499393463
2023-01-23 00:49:04.932616: step: 176/529, loss: 0.09264907985925674
2023-01-23 00:49:06.063788: step: 180/529, loss: 0.10887741297483444
2023-01-23 00:49:07.148418: step: 184/529, loss: 0.1670815497636795
2023-01-23 00:49:08.286114: step: 188/529, loss: 0.48168981075286865
2023-01-23 00:49:09.377657: step: 192/529, loss: 0.04652233421802521
2023-01-23 00:49:10.493115: step: 196/529, loss: 0.11765947937965393
2023-01-23 00:49:11.589886: step: 200/529, loss: 0.10074634850025177
2023-01-23 00:49:12.715968: step: 204/529, loss: 0.030885985121130943
2023-01-23 00:49:13.803143: step: 208/529, loss: 0.14120788872241974
2023-01-23 00:49:14.918151: step: 212/529, loss: 0.007666588295251131
2023-01-23 00:49:16.049127: step: 216/529, loss: 0.36684083938598633
2023-01-23 00:49:17.139308: step: 220/529, loss: 0.04493532329797745
2023-01-23 00:49:18.249136: step: 224/529, loss: 0.1575014889240265
2023-01-23 00:49:19.379689: step: 228/529, loss: 0.04303760826587677
2023-01-23 00:49:20.514559: step: 232/529, loss: 0.09628082066774368
2023-01-23 00:49:21.633892: step: 236/529, loss: 0.07134309411048889
2023-01-23 00:49:22.755721: step: 240/529, loss: 0.05675921589136124
2023-01-23 00:49:23.874311: step: 244/529, loss: 0.08725909888744354
2023-01-23 00:49:24.971965: step: 248/529, loss: 0.14610710740089417
2023-01-23 00:49:26.075451: step: 252/529, loss: 0.05349111557006836
2023-01-23 00:49:27.205815: step: 256/529, loss: 0.500694751739502
2023-01-23 00:49:28.344264: step: 260/529, loss: 0.40201592445373535
2023-01-23 00:49:29.463476: step: 264/529, loss: 0.10057735443115234
2023-01-23 00:49:30.586265: step: 268/529, loss: 0.01609516143798828
2023-01-23 00:49:31.708649: step: 272/529, loss: 0.06261692196130753
2023-01-23 00:49:32.819363: step: 276/529, loss: 0.1567176878452301
2023-01-23 00:49:33.908132: step: 280/529, loss: 0.03514843061566353
2023-01-23 00:49:35.015441: step: 284/529, loss: 0.02055797539651394
2023-01-23 00:49:36.118912: step: 288/529, loss: 0.02409052848815918
2023-01-23 00:49:37.219152: step: 292/529, loss: 0.04031085968017578
2023-01-23 00:49:38.326681: step: 296/529, loss: 0.07768788933753967
2023-01-23 00:49:39.441949: step: 300/529, loss: 0.09934453666210175
2023-01-23 00:49:40.558449: step: 304/529, loss: 0.10431576520204544
2023-01-23 00:49:41.646624: step: 308/529, loss: 0.12383947521448135
2023-01-23 00:49:42.748685: step: 312/529, loss: 0.02905302122235298
2023-01-23 00:49:43.870857: step: 316/529, loss: 0.13825073838233948
2023-01-23 00:49:44.972222: step: 320/529, loss: 0.05561008304357529
2023-01-23 00:49:46.089681: step: 324/529, loss: 0.04135637357831001
2023-01-23 00:49:47.189838: step: 328/529, loss: 0.021561909466981888
2023-01-23 00:49:48.300074: step: 332/529, loss: 0.06837920844554901
2023-01-23 00:49:49.440511: step: 336/529, loss: 0.04222039878368378
2023-01-23 00:49:50.542289: step: 340/529, loss: 0.02071533352136612
2023-01-23 00:49:51.648471: step: 344/529, loss: 0.6496995687484741
2023-01-23 00:49:52.746307: step: 348/529, loss: 0.05602569505572319
2023-01-23 00:49:53.848950: step: 352/529, loss: 0.1458621472120285
2023-01-23 00:49:54.951222: step: 356/529, loss: 0.08259530365467072
2023-01-23 00:49:56.055691: step: 360/529, loss: 0.10850724577903748
2023-01-23 00:49:57.201353: step: 364/529, loss: 0.2262999564409256
2023-01-23 00:49:58.321774: step: 368/529, loss: 0.10388288646936417
2023-01-23 00:49:59.433802: step: 372/529, loss: 0.11695671081542969
2023-01-23 00:50:00.561067: step: 376/529, loss: 0.09209509193897247
2023-01-23 00:50:01.647011: step: 380/529, loss: 0.06842823326587677
2023-01-23 00:50:02.733720: step: 384/529, loss: 0.07121582329273224
2023-01-23 00:50:03.843389: step: 388/529, loss: 0.11692357063293457
2023-01-23 00:50:04.958082: step: 392/529, loss: 0.06335633993148804
2023-01-23 00:50:06.082303: step: 396/529, loss: 0.193498894572258
2023-01-23 00:50:07.186011: step: 400/529, loss: 0.2050722986459732
2023-01-23 00:50:08.298150: step: 404/529, loss: 0.05390138179063797
2023-01-23 00:50:09.397577: step: 408/529, loss: 0.1637982428073883
2023-01-23 00:50:10.502524: step: 412/529, loss: 0.042731188237667084
2023-01-23 00:50:11.625296: step: 416/529, loss: 0.022153139114379883
2023-01-23 00:50:12.726745: step: 420/529, loss: 0.0784984603524208
2023-01-23 00:50:13.846335: step: 424/529, loss: 0.02855692058801651
2023-01-23 00:50:14.964803: step: 428/529, loss: 0.07432766258716583
2023-01-23 00:50:16.108782: step: 432/529, loss: 0.22140216827392578
2023-01-23 00:50:17.177690: step: 436/529, loss: 0.12895917892456055
2023-01-23 00:50:18.296493: step: 440/529, loss: 0.2757503390312195
2023-01-23 00:50:19.392817: step: 444/529, loss: 0.12068644165992737
2023-01-23 00:50:20.515887: step: 448/529, loss: 0.054241567850112915
2023-01-23 00:50:21.632388: step: 452/529, loss: 0.045977212488651276
2023-01-23 00:50:22.745944: step: 456/529, loss: 0.09137392044067383
2023-01-23 00:50:23.843979: step: 460/529, loss: 0.053114842623472214
2023-01-23 00:50:24.976254: step: 464/529, loss: 0.11413630843162537
2023-01-23 00:50:26.068993: step: 468/529, loss: 0.02526998519897461
2023-01-23 00:50:27.199340: step: 472/529, loss: 0.20771875977516174
2023-01-23 00:50:28.301429: step: 476/529, loss: 0.10484285652637482
2023-01-23 00:50:29.421116: step: 480/529, loss: 0.08314388245344162
2023-01-23 00:50:30.531018: step: 484/529, loss: 0.1397075653076172
2023-01-23 00:50:31.646783: step: 488/529, loss: 0.26071417331695557
2023-01-23 00:50:32.749587: step: 492/529, loss: 0.1529836654663086
2023-01-23 00:50:33.900193: step: 496/529, loss: 0.022241592407226562
2023-01-23 00:50:35.046698: step: 500/529, loss: 0.09012861549854279
2023-01-23 00:50:36.159051: step: 504/529, loss: 0.019520092755556107
2023-01-23 00:50:37.258721: step: 508/529, loss: 0.12705931067466736
2023-01-23 00:50:38.398177: step: 512/529, loss: 0.16276608407497406
2023-01-23 00:50:39.503583: step: 516/529, loss: 0.08586812764406204
2023-01-23 00:50:40.664816: step: 520/529, loss: 0.013790750876069069
2023-01-23 00:50:41.770918: step: 524/529, loss: 0.06156792491674423
2023-01-23 00:50:42.871657: step: 528/529, loss: 0.050742436200380325
2023-01-23 00:50:43.972491: step: 532/529, loss: 0.029255010187625885
2023-01-23 00:50:45.084297: step: 536/529, loss: 0.47186341881752014
2023-01-23 00:50:46.181456: step: 540/529, loss: 0.005035304930061102
2023-01-23 00:50:47.283690: step: 544/529, loss: 0.031760167330503464
2023-01-23 00:50:48.377011: step: 548/529, loss: 0.030845189467072487
2023-01-23 00:50:49.481479: step: 552/529, loss: 0.18544712662696838
2023-01-23 00:50:50.611607: step: 556/529, loss: 0.10837945342063904
2023-01-23 00:50:51.684120: step: 560/529, loss: 0.035142041742801666
2023-01-23 00:50:52.796832: step: 564/529, loss: 0.07538872212171555
2023-01-23 00:50:53.917235: step: 568/529, loss: 0.03586931526660919
2023-01-23 00:50:55.026243: step: 572/529, loss: 0.017791176214814186
2023-01-23 00:50:56.115529: step: 576/529, loss: 0.12268924713134766
2023-01-23 00:50:57.228328: step: 580/529, loss: 0.10870666801929474
2023-01-23 00:50:58.347083: step: 584/529, loss: 0.024970388039946556
2023-01-23 00:50:59.456909: step: 588/529, loss: 0.14508552849292755
2023-01-23 00:51:00.551628: step: 592/529, loss: 0.11120348423719406
2023-01-23 00:51:01.647480: step: 596/529, loss: 0.1060466319322586
2023-01-23 00:51:02.736930: step: 600/529, loss: 0.034670162945985794
2023-01-23 00:51:03.856861: step: 604/529, loss: 0.020639659836888313
2023-01-23 00:51:04.996235: step: 608/529, loss: 0.14827147126197815
2023-01-23 00:51:06.119224: step: 612/529, loss: 0.4108858108520508
2023-01-23 00:51:07.219446: step: 616/529, loss: 0.04742574691772461
2023-01-23 00:51:08.293129: step: 620/529, loss: 0.02974834479391575
2023-01-23 00:51:09.406662: step: 624/529, loss: 0.194295734167099
2023-01-23 00:51:10.518882: step: 628/529, loss: 0.1625930368900299
2023-01-23 00:51:11.644044: step: 632/529, loss: 0.10084104537963867
2023-01-23 00:51:12.746394: step: 636/529, loss: 0.15282422304153442
2023-01-23 00:51:13.856387: step: 640/529, loss: 0.07411523908376694
2023-01-23 00:51:14.970723: step: 644/529, loss: 0.06980600953102112
2023-01-23 00:51:16.073600: step: 648/529, loss: 0.3058091104030609
2023-01-23 00:51:17.172716: step: 652/529, loss: 0.19508886337280273
2023-01-23 00:51:18.305058: step: 656/529, loss: 0.14279861748218536
2023-01-23 00:51:19.461505: step: 660/529, loss: 0.07856860011816025
2023-01-23 00:51:20.606366: step: 664/529, loss: 0.047208692878484726
2023-01-23 00:51:21.749829: step: 668/529, loss: 0.06210184097290039
2023-01-23 00:51:22.884140: step: 672/529, loss: 0.009226322174072266
2023-01-23 00:51:23.995061: step: 676/529, loss: 0.3376133441925049
2023-01-23 00:51:25.101061: step: 680/529, loss: 0.2074717879295349
2023-01-23 00:51:26.202783: step: 684/529, loss: 0.10775518417358398
2023-01-23 00:51:27.331795: step: 688/529, loss: 0.1584509313106537
2023-01-23 00:51:28.475519: step: 692/529, loss: 0.1252274513244629
2023-01-23 00:51:29.605794: step: 696/529, loss: 0.2734691798686981
2023-01-23 00:51:30.710181: step: 700/529, loss: 0.08306089043617249
2023-01-23 00:51:31.790416: step: 704/529, loss: 0.0260987039655447
2023-01-23 00:51:32.886313: step: 708/529, loss: 0.1043708324432373
2023-01-23 00:51:34.010605: step: 712/529, loss: 0.10401935875415802
2023-01-23 00:51:35.108821: step: 716/529, loss: 0.13772697746753693
2023-01-23 00:51:36.225762: step: 720/529, loss: 0.15383297204971313
2023-01-23 00:51:37.353005: step: 724/529, loss: 0.19827446341514587
2023-01-23 00:51:38.438560: step: 728/529, loss: 0.059778306633234024
2023-01-23 00:51:39.529680: step: 732/529, loss: 0.026334714144468307
2023-01-23 00:51:40.636392: step: 736/529, loss: 0.11739101260900497
2023-01-23 00:51:41.737641: step: 740/529, loss: 0.06597013771533966
2023-01-23 00:51:42.840489: step: 744/529, loss: 0.17049741744995117
2023-01-23 00:51:43.929941: step: 748/529, loss: 0.13470125198364258
2023-01-23 00:51:45.032769: step: 752/529, loss: 0.1963629424571991
2023-01-23 00:51:46.150057: step: 756/529, loss: 0.1465105265378952
2023-01-23 00:51:47.274639: step: 760/529, loss: 0.24067707359790802
2023-01-23 00:51:48.382685: step: 764/529, loss: 0.0548405647277832
2023-01-23 00:51:49.494731: step: 768/529, loss: 0.05560598522424698
2023-01-23 00:51:50.610625: step: 772/529, loss: 1.8638938665390015
2023-01-23 00:51:51.726989: step: 776/529, loss: 0.12758255004882812
2023-01-23 00:51:52.808827: step: 780/529, loss: 0.05670108646154404
2023-01-23 00:51:53.916479: step: 784/529, loss: 0.06468353420495987
2023-01-23 00:51:55.018533: step: 788/529, loss: 0.048354532569646835
2023-01-23 00:51:56.102459: step: 792/529, loss: 0.0731218233704567
2023-01-23 00:51:57.230779: step: 796/529, loss: 0.2670901417732239
2023-01-23 00:51:58.369456: step: 800/529, loss: 0.16406115889549255
2023-01-23 00:51:59.474045: step: 804/529, loss: 0.11984129250049591
2023-01-23 00:52:00.600233: step: 808/529, loss: 0.14334678649902344
2023-01-23 00:52:01.713567: step: 812/529, loss: 0.24785137176513672
2023-01-23 00:52:02.827985: step: 816/529, loss: 0.007072162814438343
2023-01-23 00:52:03.921408: step: 820/529, loss: 0.09852228313684464
2023-01-23 00:52:05.016271: step: 824/529, loss: 0.3261339068412781
2023-01-23 00:52:06.124726: step: 828/529, loss: 0.02823066897690296
2023-01-23 00:52:07.258540: step: 832/529, loss: 0.062287621200084686
2023-01-23 00:52:08.387082: step: 836/529, loss: 0.048912905156612396
2023-01-23 00:52:09.507625: step: 840/529, loss: 0.05576535686850548
2023-01-23 00:52:10.641243: step: 844/529, loss: 0.20508727431297302
2023-01-23 00:52:11.741855: step: 848/529, loss: 0.04440021514892578
2023-01-23 00:52:12.837430: step: 852/529, loss: 0.03855152428150177
2023-01-23 00:52:13.973817: step: 856/529, loss: 0.3242805600166321
2023-01-23 00:52:15.105845: step: 860/529, loss: 0.5788240432739258
2023-01-23 00:52:16.219517: step: 864/529, loss: 0.033098507672548294
2023-01-23 00:52:17.345532: step: 868/529, loss: 0.12986326217651367
2023-01-23 00:52:18.459325: step: 872/529, loss: 0.2866189479827881
2023-01-23 00:52:19.560345: step: 876/529, loss: 0.0950084701180458
2023-01-23 00:52:20.653725: step: 880/529, loss: 0.18983830511569977
2023-01-23 00:52:21.766512: step: 884/529, loss: 0.08172015845775604
2023-01-23 00:52:22.892563: step: 888/529, loss: 0.15899963676929474
2023-01-23 00:52:23.998246: step: 892/529, loss: 0.4648832082748413
2023-01-23 00:52:25.106501: step: 896/529, loss: 0.17418155074119568
2023-01-23 00:52:26.207621: step: 900/529, loss: 0.05792875587940216
2023-01-23 00:52:27.344550: step: 904/529, loss: 0.04514046013355255
2023-01-23 00:52:28.438953: step: 908/529, loss: 0.038633015006780624
2023-01-23 00:52:29.559723: step: 912/529, loss: 0.16504965722560883
2023-01-23 00:52:30.649642: step: 916/529, loss: 0.03185730054974556
2023-01-23 00:52:31.734932: step: 920/529, loss: 0.029438089579343796
2023-01-23 00:52:32.847593: step: 924/529, loss: 0.14387011528015137
2023-01-23 00:52:33.932405: step: 928/529, loss: 0.13822278380393982
2023-01-23 00:52:35.013623: step: 932/529, loss: 0.043334536254405975
2023-01-23 00:52:36.128946: step: 936/529, loss: 0.13769817352294922
2023-01-23 00:52:37.231317: step: 940/529, loss: 0.10432787984609604
2023-01-23 00:52:38.399807: step: 944/529, loss: 0.3595340847969055
2023-01-23 00:52:39.523987: step: 948/529, loss: 0.16920499503612518
2023-01-23 00:52:40.635694: step: 952/529, loss: 0.055108167231082916
2023-01-23 00:52:41.729178: step: 956/529, loss: 0.12649258971214294
2023-01-23 00:52:42.921346: step: 960/529, loss: 0.13529044389724731
2023-01-23 00:52:44.032909: step: 964/529, loss: 0.06275320053100586
2023-01-23 00:52:45.137467: step: 968/529, loss: 0.3659912943840027
2023-01-23 00:52:46.252931: step: 972/529, loss: 0.13667917251586914
2023-01-23 00:52:47.393362: step: 976/529, loss: 0.13459502160549164
2023-01-23 00:52:48.488451: step: 980/529, loss: 0.012503433041274548
2023-01-23 00:52:49.628854: step: 984/529, loss: 0.11710643768310547
2023-01-23 00:52:50.739508: step: 988/529, loss: 0.3439061939716339
2023-01-23 00:52:51.824603: step: 992/529, loss: 0.10192890465259552
2023-01-23 00:52:52.948371: step: 996/529, loss: 0.3993247449398041
2023-01-23 00:52:54.047702: step: 1000/529, loss: 0.023722808808088303
2023-01-23 00:52:55.157520: step: 1004/529, loss: 0.02011260949075222
2023-01-23 00:52:56.271541: step: 1008/529, loss: 0.08597803115844727
2023-01-23 00:52:57.366566: step: 1012/529, loss: 0.03914952278137207
2023-01-23 00:52:58.486262: step: 1016/529, loss: 0.02920856513082981
2023-01-23 00:52:59.598355: step: 1020/529, loss: 0.013190162368118763
2023-01-23 00:53:00.679054: step: 1024/529, loss: 0.11433763802051544
2023-01-23 00:53:01.793621: step: 1028/529, loss: 0.045697782188653946
2023-01-23 00:53:02.904114: step: 1032/529, loss: 0.1532432585954666
2023-01-23 00:53:04.009295: step: 1036/529, loss: 0.1075565367937088
2023-01-23 00:53:05.107682: step: 1040/529, loss: 0.03354320675134659
2023-01-23 00:53:06.204027: step: 1044/529, loss: 0.023433685302734375
2023-01-23 00:53:07.321936: step: 1048/529, loss: 0.12937398254871368
2023-01-23 00:53:08.442206: step: 1052/529, loss: 0.0020016669295728207
2023-01-23 00:53:09.572593: step: 1056/529, loss: 0.15442132949829102
2023-01-23 00:53:10.694319: step: 1060/529, loss: 0.02352127991616726
2023-01-23 00:53:11.812970: step: 1064/529, loss: 0.0686376541852951
2023-01-23 00:53:12.921461: step: 1068/529, loss: 0.39713162183761597
2023-01-23 00:53:14.039136: step: 1072/529, loss: 0.10481038689613342
2023-01-23 00:53:15.139482: step: 1076/529, loss: 0.030427539721131325
2023-01-23 00:53:16.235945: step: 1080/529, loss: 0.04467516019940376
2023-01-23 00:53:17.345913: step: 1084/529, loss: 0.1046157106757164
2023-01-23 00:53:18.479058: step: 1088/529, loss: 0.05927839130163193
2023-01-23 00:53:19.592169: step: 1092/529, loss: 0.11200771480798721
2023-01-23 00:53:20.726142: step: 1096/529, loss: 0.0482630729675293
2023-01-23 00:53:21.878938: step: 1100/529, loss: 0.0799582451581955
2023-01-23 00:53:22.994638: step: 1104/529, loss: 0.057820986956357956
2023-01-23 00:53:24.124467: step: 1108/529, loss: 0.05879940837621689
2023-01-23 00:53:25.252471: step: 1112/529, loss: 0.11061849445104599
2023-01-23 00:53:26.395338: step: 1116/529, loss: 0.07461271435022354
2023-01-23 00:53:27.524237: step: 1120/529, loss: 0.09170246124267578
2023-01-23 00:53:28.689196: step: 1124/529, loss: 0.07950973510742188
2023-01-23 00:53:29.806137: step: 1128/529, loss: 0.0448024719953537
2023-01-23 00:53:30.896755: step: 1132/529, loss: 0.22226496040821075
2023-01-23 00:53:32.029439: step: 1136/529, loss: 0.05509338527917862
2023-01-23 00:53:33.182435: step: 1140/529, loss: 0.3249807357788086
2023-01-23 00:53:34.299821: step: 1144/529, loss: 0.02433748170733452
2023-01-23 00:53:35.394165: step: 1148/529, loss: 0.34807834029197693
2023-01-23 00:53:36.497824: step: 1152/529, loss: 0.18976755440235138
2023-01-23 00:53:37.592244: step: 1156/529, loss: 0.04614315181970596
2023-01-23 00:53:38.683770: step: 1160/529, loss: 0.02836017496883869
2023-01-23 00:53:39.802798: step: 1164/529, loss: 0.09402541816234589
2023-01-23 00:53:40.915769: step: 1168/529, loss: 0.05163278430700302
2023-01-23 00:53:42.032011: step: 1172/529, loss: 0.246564581990242
2023-01-23 00:53:43.132282: step: 1176/529, loss: 0.19903278350830078
2023-01-23 00:53:44.258305: step: 1180/529, loss: 0.0760578140616417
2023-01-23 00:53:45.367330: step: 1184/529, loss: 0.13230033218860626
2023-01-23 00:53:46.464042: step: 1188/529, loss: 0.48669958114624023
2023-01-23 00:53:47.592584: step: 1192/529, loss: 0.014771080575883389
2023-01-23 00:53:48.701481: step: 1196/529, loss: 0.02422809787094593
2023-01-23 00:53:49.816314: step: 1200/529, loss: 0.009517192840576172
2023-01-23 00:53:50.930258: step: 1204/529, loss: 0.11889752745628357
2023-01-23 00:53:52.064012: step: 1208/529, loss: 0.12151375412940979
2023-01-23 00:53:53.181509: step: 1212/529, loss: 0.10582761466503143
2023-01-23 00:53:54.303961: step: 1216/529, loss: 0.07957177609205246
2023-01-23 00:53:55.402625: step: 1220/529, loss: 0.07901802659034729
2023-01-23 00:53:56.539221: step: 1224/529, loss: 0.17792721092700958
2023-01-23 00:53:57.622948: step: 1228/529, loss: 0.06355170905590057
2023-01-23 00:53:58.759045: step: 1232/529, loss: 0.1157953292131424
2023-01-23 00:53:59.869415: step: 1236/529, loss: 0.08996716141700745
2023-01-23 00:54:00.967405: step: 1240/529, loss: 0.04892396926879883
2023-01-23 00:54:02.075346: step: 1244/529, loss: 0.014222336001694202
2023-01-23 00:54:03.183237: step: 1248/529, loss: 0.5267826318740845
2023-01-23 00:54:04.295994: step: 1252/529, loss: 0.07460909336805344
2023-01-23 00:54:05.382440: step: 1256/529, loss: 0.10695400834083557
2023-01-23 00:54:06.477354: step: 1260/529, loss: 0.05616407468914986
2023-01-23 00:54:07.594909: step: 1264/529, loss: 0.03346419334411621
2023-01-23 00:54:08.699881: step: 1268/529, loss: 0.06809739768505096
2023-01-23 00:54:09.787343: step: 1272/529, loss: 0.07186833024024963
2023-01-23 00:54:10.910550: step: 1276/529, loss: 0.17860373854637146
2023-01-23 00:54:12.007229: step: 1280/529, loss: 0.029743101447820663
2023-01-23 00:54:13.160424: step: 1284/529, loss: 1.512211799621582
2023-01-23 00:54:14.268865: step: 1288/529, loss: 0.005821418948471546
2023-01-23 00:54:15.381564: step: 1292/529, loss: 0.08688574284315109
2023-01-23 00:54:16.503688: step: 1296/529, loss: 0.04068155586719513
2023-01-23 00:54:17.583226: step: 1300/529, loss: 0.08950367569923401
2023-01-23 00:54:18.707578: step: 1304/529, loss: 0.03899574279785156
2023-01-23 00:54:19.808402: step: 1308/529, loss: 0.0820469930768013
2023-01-23 00:54:20.883671: step: 1312/529, loss: 0.05772824212908745
2023-01-23 00:54:22.043839: step: 1316/529, loss: 0.23979711532592773
2023-01-23 00:54:23.150578: step: 1320/529, loss: 0.06210651248693466
2023-01-23 00:54:24.284480: step: 1324/529, loss: 0.14506320655345917
2023-01-23 00:54:25.386418: step: 1328/529, loss: 0.01283798273652792
2023-01-23 00:54:26.482565: step: 1332/529, loss: 0.13258647918701172
2023-01-23 00:54:27.596658: step: 1336/529, loss: 0.022126102820038795
2023-01-23 00:54:28.688415: step: 1340/529, loss: 0.06437671184539795
2023-01-23 00:54:29.793240: step: 1344/529, loss: 0.13645707070827484
2023-01-23 00:54:30.875867: step: 1348/529, loss: 0.09878106415271759
2023-01-23 00:54:31.975747: step: 1352/529, loss: 0.08160868287086487
2023-01-23 00:54:33.067756: step: 1356/529, loss: 0.07624302059412003
2023-01-23 00:54:34.153342: step: 1360/529, loss: 0.07845602184534073
2023-01-23 00:54:35.276437: step: 1364/529, loss: 0.06410370022058487
2023-01-23 00:54:36.364103: step: 1368/529, loss: 0.02327604405581951
2023-01-23 00:54:37.478828: step: 1372/529, loss: 0.2503858208656311
2023-01-23 00:54:38.603656: step: 1376/529, loss: 0.12697726488113403
2023-01-23 00:54:39.726285: step: 1380/529, loss: 0.05052796006202698
2023-01-23 00:54:40.876388: step: 1384/529, loss: 0.10965590178966522
2023-01-23 00:54:41.991651: step: 1388/529, loss: 0.04164714738726616
2023-01-23 00:54:43.081717: step: 1392/529, loss: 0.021717073395848274
2023-01-23 00:54:44.220659: step: 1396/529, loss: 0.07528341561555862
2023-01-23 00:54:45.317486: step: 1400/529, loss: 0.13904786109924316
2023-01-23 00:54:46.448802: step: 1404/529, loss: 0.03939530998468399
2023-01-23 00:54:47.574903: step: 1408/529, loss: 0.14536018669605255
2023-01-23 00:54:48.688948: step: 1412/529, loss: 0.11746422201395035
2023-01-23 00:54:49.810647: step: 1416/529, loss: 0.10972604900598526
2023-01-23 00:54:50.938860: step: 1420/529, loss: 0.030263518914580345
2023-01-23 00:54:52.026259: step: 1424/529, loss: 0.15680274367332458
2023-01-23 00:54:53.146543: step: 1428/529, loss: 0.4611307382583618
2023-01-23 00:54:54.277434: step: 1432/529, loss: 0.19050291180610657
2023-01-23 00:54:55.387239: step: 1436/529, loss: 0.2391345500946045
2023-01-23 00:54:56.477604: step: 1440/529, loss: 0.12605568766593933
2023-01-23 00:54:57.615366: step: 1444/529, loss: 0.17011089622974396
2023-01-23 00:54:58.747345: step: 1448/529, loss: 0.45945197343826294
2023-01-23 00:54:59.895172: step: 1452/529, loss: 0.008951187133789062
2023-01-23 00:55:00.999904: step: 1456/529, loss: 0.019978713244199753
2023-01-23 00:55:02.117987: step: 1460/529, loss: 0.39568251371383667
2023-01-23 00:55:03.203042: step: 1464/529, loss: 0.0516299270093441
2023-01-23 00:55:04.297880: step: 1468/529, loss: 0.01072320993989706
2023-01-23 00:55:05.407213: step: 1472/529, loss: 0.13910111784934998
2023-01-23 00:55:06.510566: step: 1476/529, loss: 0.03418789058923721
2023-01-23 00:55:07.678444: step: 1480/529, loss: 0.09762802720069885
2023-01-23 00:55:08.769743: step: 1484/529, loss: 0.09149055182933807
2023-01-23 00:55:09.901836: step: 1488/529, loss: 0.12796077132225037
2023-01-23 00:55:11.052416: step: 1492/529, loss: 0.1952836960554123
2023-01-23 00:55:12.151910: step: 1496/529, loss: 0.09624385833740234
2023-01-23 00:55:13.258597: step: 1500/529, loss: 0.015612030401825905
2023-01-23 00:55:14.375547: step: 1504/529, loss: 0.01025619637221098
2023-01-23 00:55:15.499737: step: 1508/529, loss: 0.11805696785449982
2023-01-23 00:55:16.593314: step: 1512/529, loss: 0.06687374413013458
2023-01-23 00:55:17.703468: step: 1516/529, loss: 0.021505165845155716
2023-01-23 00:55:18.807860: step: 1520/529, loss: 0.5881984233856201
2023-01-23 00:55:19.903591: step: 1524/529, loss: 0.18597888946533203
2023-01-23 00:55:20.991674: step: 1528/529, loss: 0.2339155673980713
2023-01-23 00:55:22.102095: step: 1532/529, loss: 0.7397167086601257
2023-01-23 00:55:23.229228: step: 1536/529, loss: 0.8801301121711731
2023-01-23 00:55:24.328445: step: 1540/529, loss: 0.05980673059821129
2023-01-23 00:55:25.436385: step: 1544/529, loss: 0.1172122061252594
2023-01-23 00:55:26.593638: step: 1548/529, loss: 0.007224726490676403
2023-01-23 00:55:27.672111: step: 1552/529, loss: 0.33185186982154846
2023-01-23 00:55:28.781939: step: 1556/529, loss: 0.11558599770069122
2023-01-23 00:55:29.883743: step: 1560/529, loss: 0.0766727477312088
2023-01-23 00:55:31.030654: step: 1564/529, loss: 0.1181788444519043
2023-01-23 00:55:32.129209: step: 1568/529, loss: 0.016602516174316406
2023-01-23 00:55:33.223126: step: 1572/529, loss: 0.11860628426074982
2023-01-23 00:55:34.355289: step: 1576/529, loss: 0.16875658929347992
2023-01-23 00:55:35.478146: step: 1580/529, loss: 0.05875139683485031
2023-01-23 00:55:36.626896: step: 1584/529, loss: 0.7112193703651428
2023-01-23 00:55:37.729906: step: 1588/529, loss: 0.17542333900928497
2023-01-23 00:55:38.841688: step: 1592/529, loss: 0.11918716132640839
2023-01-23 00:55:39.968213: step: 1596/529, loss: 0.05150041729211807
2023-01-23 00:55:41.092661: step: 1600/529, loss: 0.13940078020095825
2023-01-23 00:55:42.204057: step: 1604/529, loss: 0.13837090134620667
2023-01-23 00:55:43.325676: step: 1608/529, loss: 0.08137612789869308
2023-01-23 00:55:44.439616: step: 1612/529, loss: 0.04746093600988388
2023-01-23 00:55:45.577976: step: 1616/529, loss: 0.3600454330444336
2023-01-23 00:55:46.683154: step: 1620/529, loss: 0.035196926444768906
2023-01-23 00:55:47.788221: step: 1624/529, loss: 0.0704149454832077
2023-01-23 00:55:48.888258: step: 1628/529, loss: 0.13225889205932617
2023-01-23 00:55:50.021012: step: 1632/529, loss: 0.11158795654773712
2023-01-23 00:55:51.112983: step: 1636/529, loss: 0.5553426742553711
2023-01-23 00:55:52.204326: step: 1640/529, loss: 0.26906871795654297
2023-01-23 00:55:53.332382: step: 1644/529, loss: 0.06360411643981934
2023-01-23 00:55:54.447591: step: 1648/529, loss: 0.13051024079322815
2023-01-23 00:55:55.561041: step: 1652/529, loss: 0.08371467888355255
2023-01-23 00:55:56.683211: step: 1656/529, loss: 0.17047472298145294
2023-01-23 00:55:57.776958: step: 1660/529, loss: 0.1417037546634674
2023-01-23 00:55:58.883580: step: 1664/529, loss: 0.2107383757829666
2023-01-23 00:55:59.988918: step: 1668/529, loss: 0.10277318954467773
2023-01-23 00:56:01.138117: step: 1672/529, loss: 0.009971666149795055
2023-01-23 00:56:02.252484: step: 1676/529, loss: 0.11623702943325043
2023-01-23 00:56:03.353175: step: 1680/529, loss: 0.8221315145492554
2023-01-23 00:56:04.553374: step: 1684/529, loss: 1.698832631111145
2023-01-23 00:56:05.658152: step: 1688/529, loss: 0.10908474773168564
2023-01-23 00:56:06.760077: step: 1692/529, loss: 0.04670019447803497
2023-01-23 00:56:07.890885: step: 1696/529, loss: 0.10548000037670135
2023-01-23 00:56:08.983204: step: 1700/529, loss: 0.06395301967859268
2023-01-23 00:56:10.060713: step: 1704/529, loss: 0.36515045166015625
2023-01-23 00:56:11.203337: step: 1708/529, loss: 0.04566478729248047
2023-01-23 00:56:12.323282: step: 1712/529, loss: 0.12969131767749786
2023-01-23 00:56:13.429553: step: 1716/529, loss: 0.09466209262609482
2023-01-23 00:56:14.551795: step: 1720/529, loss: 0.4289804697036743
2023-01-23 00:56:15.652092: step: 1724/529, loss: 0.07257632911205292
2023-01-23 00:56:16.757049: step: 1728/529, loss: 0.09229574352502823
2023-01-23 00:56:17.857437: step: 1732/529, loss: 0.834445059299469
2023-01-23 00:56:18.999021: step: 1736/529, loss: 0.39292111992836
2023-01-23 00:56:20.080927: step: 1740/529, loss: 0.5804386138916016
2023-01-23 00:56:21.195128: step: 1744/529, loss: 0.0479232557117939
2023-01-23 00:56:22.325909: step: 1748/529, loss: 1.06978178024292
2023-01-23 00:56:23.440850: step: 1752/529, loss: 1.2441238164901733
2023-01-23 00:56:24.535513: step: 1756/529, loss: 0.07084637135267258
2023-01-23 00:56:25.630023: step: 1760/529, loss: 0.03839244693517685
2023-01-23 00:56:26.744101: step: 1764/529, loss: 0.10491366684436798
2023-01-23 00:56:27.852064: step: 1768/529, loss: 0.19416770339012146
2023-01-23 00:56:28.962359: step: 1772/529, loss: 0.2712913453578949
2023-01-23 00:56:30.116573: step: 1776/529, loss: 0.04234728962182999
2023-01-23 00:56:31.227412: step: 1780/529, loss: 0.06250448524951935
2023-01-23 00:56:32.345530: step: 1784/529, loss: 0.01987132988870144
2023-01-23 00:56:33.445752: step: 1788/529, loss: 0.04949207603931427
2023-01-23 00:56:34.532792: step: 1792/529, loss: 0.0982908308506012
2023-01-23 00:56:35.640254: step: 1796/529, loss: 0.04162416607141495
2023-01-23 00:56:36.768438: step: 1800/529, loss: 0.016437197104096413
2023-01-23 00:56:37.882133: step: 1804/529, loss: 0.06721341609954834
2023-01-23 00:56:38.983012: step: 1808/529, loss: 0.05924713611602783
2023-01-23 00:56:40.093164: step: 1812/529, loss: 0.031153012067079544
2023-01-23 00:56:41.180955: step: 1816/529, loss: 0.010325432755053043
2023-01-23 00:56:42.271642: step: 1820/529, loss: 0.057450439780950546
2023-01-23 00:56:43.397955: step: 1824/529, loss: 0.0797567367553711
2023-01-23 00:56:44.532617: step: 1828/529, loss: 0.21246853470802307
2023-01-23 00:56:45.641344: step: 1832/529, loss: 1.2157001495361328
2023-01-23 00:56:46.782371: step: 1836/529, loss: 0.09803581237792969
2023-01-23 00:56:47.913019: step: 1840/529, loss: 0.13262850046157837
2023-01-23 00:56:49.017662: step: 1844/529, loss: 0.06733512878417969
2023-01-23 00:56:50.153940: step: 1848/529, loss: 0.05996561422944069
2023-01-23 00:56:51.280599: step: 1852/529, loss: 0.025759601965546608
2023-01-23 00:56:52.427636: step: 1856/529, loss: 0.15843135118484497
2023-01-23 00:56:53.536398: step: 1860/529, loss: 0.03394956886768341
2023-01-23 00:56:54.646581: step: 1864/529, loss: 0.4541475176811218
2023-01-23 00:56:55.751054: step: 1868/529, loss: 0.053975533694028854
2023-01-23 00:56:56.866138: step: 1872/529, loss: 0.055335454642772675
2023-01-23 00:56:57.965988: step: 1876/529, loss: 0.09587828814983368
2023-01-23 00:56:59.084931: step: 1880/529, loss: 0.27150774002075195
2023-01-23 00:57:00.165633: step: 1884/529, loss: 0.055780794471502304
2023-01-23 00:57:01.284804: step: 1888/529, loss: 0.21617546677589417
2023-01-23 00:57:02.392900: step: 1892/529, loss: 0.17622947692871094
2023-01-23 00:57:03.491121: step: 1896/529, loss: 0.4544470012187958
2023-01-23 00:57:04.630315: step: 1900/529, loss: 0.16246432065963745
2023-01-23 00:57:05.748343: step: 1904/529, loss: 0.041576579213142395
2023-01-23 00:57:06.845854: step: 1908/529, loss: 0.42554759979248047
2023-01-23 00:57:07.950512: step: 1912/529, loss: 0.16898003220558167
2023-01-23 00:57:09.089869: step: 1916/529, loss: 0.018013715744018555
2023-01-23 00:57:10.216056: step: 1920/529, loss: 0.048802945762872696
2023-01-23 00:57:11.313418: step: 1924/529, loss: 0.08774089813232422
2023-01-23 00:57:12.479994: step: 1928/529, loss: 0.0564337782561779
2023-01-23 00:57:13.585840: step: 1932/529, loss: 0.018157958984375
2023-01-23 00:57:14.663723: step: 1936/529, loss: 0.00856781005859375
2023-01-23 00:57:15.776309: step: 1940/529, loss: 0.0033669949043542147
2023-01-23 00:57:16.886475: step: 1944/529, loss: 0.39807718992233276
2023-01-23 00:57:17.984860: step: 1948/529, loss: 0.08601990342140198
2023-01-23 00:57:19.090137: step: 1952/529, loss: 0.03397779539227486
2023-01-23 00:57:20.223443: step: 1956/529, loss: 0.09619808197021484
2023-01-23 00:57:21.325662: step: 1960/529, loss: 0.07587385177612305
2023-01-23 00:57:22.423508: step: 1964/529, loss: 0.15980473160743713
2023-01-23 00:57:23.519639: step: 1968/529, loss: 0.06064872816205025
2023-01-23 00:57:24.650352: step: 1972/529, loss: 0.08335505425930023
2023-01-23 00:57:25.759640: step: 1976/529, loss: 0.05104637145996094
2023-01-23 00:57:26.854973: step: 1980/529, loss: 0.06667838245630264
2023-01-23 00:57:27.987908: step: 1984/529, loss: 0.06676197052001953
2023-01-23 00:57:29.092465: step: 1988/529, loss: 0.04147772863507271
2023-01-23 00:57:30.213145: step: 1992/529, loss: 0.1335565149784088
2023-01-23 00:57:31.320201: step: 1996/529, loss: 0.09469977021217346
2023-01-23 00:57:32.437879: step: 2000/529, loss: 0.10614728927612305
2023-01-23 00:57:33.535603: step: 2004/529, loss: 0.03339986875653267
2023-01-23 00:57:34.700910: step: 2008/529, loss: 0.06371164321899414
2023-01-23 00:57:35.833839: step: 2012/529, loss: 0.10844211280345917
2023-01-23 00:57:36.963146: step: 2016/529, loss: 0.046425629407167435
2023-01-23 00:57:38.073319: step: 2020/529, loss: 0.4454374313354492
2023-01-23 00:57:39.191445: step: 2024/529, loss: 0.028484439477324486
2023-01-23 00:57:40.290602: step: 2028/529, loss: 0.05515031889081001
2023-01-23 00:57:41.398966: step: 2032/529, loss: 0.15749740600585938
2023-01-23 00:57:42.503054: step: 2036/529, loss: 0.13970308005809784
2023-01-23 00:57:43.612908: step: 2040/529, loss: 0.04967961460351944
2023-01-23 00:57:44.697549: step: 2044/529, loss: 0.06730881333351135
2023-01-23 00:57:45.808553: step: 2048/529, loss: 0.10771723091602325
2023-01-23 00:57:46.911435: step: 2052/529, loss: 0.02240614965558052
2023-01-23 00:57:48.051732: step: 2056/529, loss: 0.8355466723442078
2023-01-23 00:57:49.221613: step: 2060/529, loss: 0.29652151465415955
2023-01-23 00:57:50.315120: step: 2064/529, loss: 0.07766053080558777
2023-01-23 00:57:51.461646: step: 2068/529, loss: 0.022115757688879967
2023-01-23 00:57:52.591004: step: 2072/529, loss: 0.05893435329198837
2023-01-23 00:57:53.708521: step: 2076/529, loss: 0.04326352849602699
2023-01-23 00:57:54.836197: step: 2080/529, loss: 0.07256489992141724
2023-01-23 00:57:55.935856: step: 2084/529, loss: 0.07202653586864471
2023-01-23 00:57:57.013786: step: 2088/529, loss: 0.0957399383187294
2023-01-23 00:57:58.125745: step: 2092/529, loss: 0.402616024017334
2023-01-23 00:57:59.221040: step: 2096/529, loss: 0.03434129059314728
2023-01-23 00:58:00.332675: step: 2100/529, loss: 0.18043117225170135
2023-01-23 00:58:01.458824: step: 2104/529, loss: 0.19229133427143097
2023-01-23 00:58:02.574707: step: 2108/529, loss: 0.009256839752197266
2023-01-23 00:58:03.711930: step: 2112/529, loss: 0.3673548996448517
2023-01-23 00:58:04.840400: step: 2116/529, loss: 0.1312166303396225
==================================================
Loss: 0.144
--------------------
Dev: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.5, 'r': 0.5396825396825397, 'f1': 0.5190839694656489}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:58:55.070383: step: 4/529, loss: 0.10318270325660706
2023-01-23 00:58:56.153938: step: 8/529, loss: 0.105072021484375
2023-01-23 00:58:57.275644: step: 12/529, loss: 0.015979385003447533
2023-01-23 00:58:58.404098: step: 16/529, loss: 0.01690196990966797
2023-01-23 00:58:59.481178: step: 20/529, loss: 0.13673830032348633
2023-01-23 00:59:00.597975: step: 24/529, loss: 0.09302611649036407
2023-01-23 00:59:01.715937: step: 28/529, loss: 0.07394295185804367
2023-01-23 00:59:02.818703: step: 32/529, loss: 0.04304695129394531
2023-01-23 00:59:03.950193: step: 36/529, loss: 0.003732919692993164
2023-01-23 00:59:05.037831: step: 40/529, loss: 0.049425218254327774
2023-01-23 00:59:06.176403: step: 44/529, loss: 0.12254457175731659
2023-01-23 00:59:07.272579: step: 48/529, loss: 0.03959474712610245
2023-01-23 00:59:08.368988: step: 52/529, loss: 0.004907703492790461
2023-01-23 00:59:09.481839: step: 56/529, loss: 0.02334756776690483
2023-01-23 00:59:10.588732: step: 60/529, loss: 0.06160583347082138
2023-01-23 00:59:11.701536: step: 64/529, loss: 0.001178693724796176
2023-01-23 00:59:12.838495: step: 68/529, loss: 0.09667682647705078
2023-01-23 00:59:13.957959: step: 72/529, loss: 0.1715146005153656
2023-01-23 00:59:15.063941: step: 76/529, loss: 0.12750092148780823
2023-01-23 00:59:16.187417: step: 80/529, loss: 0.22564248740673065
2023-01-23 00:59:17.276417: step: 84/529, loss: 0.3637579083442688
2023-01-23 00:59:18.380754: step: 88/529, loss: 0.1013256087899208
2023-01-23 00:59:19.483401: step: 92/529, loss: 0.17825783789157867
2023-01-23 00:59:20.597546: step: 96/529, loss: 0.03938794136047363
2023-01-23 00:59:21.691262: step: 100/529, loss: 0.09575791656970978
2023-01-23 00:59:22.815814: step: 104/529, loss: 0.01864643022418022
2023-01-23 00:59:23.947434: step: 108/529, loss: 0.043246082961559296
2023-01-23 00:59:25.044212: step: 112/529, loss: 0.04642505943775177
2023-01-23 00:59:26.132416: step: 116/529, loss: 0.09158239513635635
2023-01-23 00:59:27.231374: step: 120/529, loss: 0.3673229217529297
2023-01-23 00:59:28.338884: step: 124/529, loss: 0.06282272934913635
2023-01-23 00:59:29.451754: step: 128/529, loss: 0.030046749860048294
2023-01-23 00:59:30.558166: step: 132/529, loss: 0.913371741771698
2023-01-23 00:59:31.639477: step: 136/529, loss: 0.014583492651581764
2023-01-23 00:59:32.770900: step: 140/529, loss: 0.1392134726047516
2023-01-23 00:59:33.906100: step: 144/529, loss: 0.012332153506577015
2023-01-23 00:59:35.010641: step: 148/529, loss: 0.24209661781787872
2023-01-23 00:59:36.142376: step: 152/529, loss: 0.03439502790570259
2023-01-23 00:59:37.232870: step: 156/529, loss: 0.042597465217113495
2023-01-23 00:59:38.345914: step: 160/529, loss: 0.0428801067173481
2023-01-23 00:59:39.443654: step: 164/529, loss: 0.04165458679199219
2023-01-23 00:59:40.576831: step: 168/529, loss: 0.06124467775225639
2023-01-23 00:59:41.708896: step: 172/529, loss: 0.11269131302833557
2023-01-23 00:59:42.819471: step: 176/529, loss: 0.03401822969317436
2023-01-23 00:59:43.952052: step: 180/529, loss: 0.04655499383807182
2023-01-23 00:59:45.044615: step: 184/529, loss: 0.12600970268249512
2023-01-23 00:59:46.157342: step: 188/529, loss: 0.34927740693092346
2023-01-23 00:59:47.271099: step: 192/529, loss: 0.08241882175207138
2023-01-23 00:59:48.399933: step: 196/529, loss: 0.0403929203748703
2023-01-23 00:59:49.496581: step: 200/529, loss: 0.13260889053344727
2023-01-23 00:59:50.616723: step: 204/529, loss: 0.09866514056921005
2023-01-23 00:59:51.739225: step: 208/529, loss: 0.01948518678545952
2023-01-23 00:59:52.882695: step: 212/529, loss: 0.06461925804615021
2023-01-23 00:59:54.000996: step: 216/529, loss: 0.031583406031131744
2023-01-23 00:59:55.124741: step: 220/529, loss: 0.27349501848220825
2023-01-23 00:59:56.230918: step: 224/529, loss: 0.22106106579303741
2023-01-23 00:59:57.348251: step: 228/529, loss: 0.027596376836299896
2023-01-23 00:59:58.471770: step: 232/529, loss: 0.11111310124397278
2023-01-23 00:59:59.578663: step: 236/529, loss: 0.021947573870420456
2023-01-23 01:00:00.689784: step: 240/529, loss: 0.2623458802700043
2023-01-23 01:00:01.788593: step: 244/529, loss: 0.01020063180476427
2023-01-23 01:00:02.914532: step: 248/529, loss: 0.3105677664279938
2023-01-23 01:00:04.035920: step: 252/529, loss: 0.08165402710437775
2023-01-23 01:00:05.125391: step: 256/529, loss: 0.013071322813630104
2023-01-23 01:00:06.228045: step: 260/529, loss: 0.01860819011926651
2023-01-23 01:00:07.309834: step: 264/529, loss: 0.09093275666236877
2023-01-23 01:00:08.414615: step: 268/529, loss: 0.06408461928367615
2023-01-23 01:00:09.514795: step: 272/529, loss: 0.1365509033203125
2023-01-23 01:00:10.605116: step: 276/529, loss: 0.051250554621219635
2023-01-23 01:00:11.704850: step: 280/529, loss: 0.08675403892993927
2023-01-23 01:00:12.812174: step: 284/529, loss: 0.02930011786520481
2023-01-23 01:00:13.926464: step: 288/529, loss: 0.06257658451795578
2023-01-23 01:00:15.033754: step: 292/529, loss: 0.0641520544886589
2023-01-23 01:00:16.147247: step: 296/529, loss: 0.017392493784427643
2023-01-23 01:00:17.274992: step: 300/529, loss: 0.03448858484625816
2023-01-23 01:00:18.380972: step: 304/529, loss: 0.045565128326416016
2023-01-23 01:00:19.553951: step: 308/529, loss: 0.09231019020080566
2023-01-23 01:00:20.659543: step: 312/529, loss: 0.1087920218706131
2023-01-23 01:00:21.827397: step: 316/529, loss: 0.04938516765832901
2023-01-23 01:00:22.959307: step: 320/529, loss: 0.08481334149837494
2023-01-23 01:00:24.081844: step: 324/529, loss: 0.03702735900878906
2023-01-23 01:00:25.173820: step: 328/529, loss: 0.13977545499801636
2023-01-23 01:00:26.287076: step: 332/529, loss: 0.20704421401023865
2023-01-23 01:00:27.390718: step: 336/529, loss: 0.30477452278137207
2023-01-23 01:00:28.527626: step: 340/529, loss: 8.35095500946045
2023-01-23 01:00:29.651265: step: 344/529, loss: 0.0928533598780632
2023-01-23 01:00:30.792654: step: 348/529, loss: 0.09858093410730362
2023-01-23 01:00:31.888447: step: 352/529, loss: 0.04527135193347931
2023-01-23 01:00:32.997715: step: 356/529, loss: 0.0664377212524414
2023-01-23 01:00:34.126785: step: 360/529, loss: 0.06432053446769714
2023-01-23 01:00:35.246671: step: 364/529, loss: 0.060967445373535156
2023-01-23 01:00:36.344239: step: 368/529, loss: 0.017093658447265625
2023-01-23 01:00:37.462765: step: 372/529, loss: 0.35670509934425354
2023-01-23 01:00:38.589434: step: 376/529, loss: 0.05980215221643448
2023-01-23 01:00:39.706897: step: 380/529, loss: 0.08419743180274963
2023-01-23 01:00:40.811668: step: 384/529, loss: 0.02702946774661541
2023-01-23 01:00:41.928030: step: 388/529, loss: 0.0651729553937912
2023-01-23 01:00:43.093155: step: 392/529, loss: 0.0750269889831543
2023-01-23 01:00:44.235137: step: 396/529, loss: 0.031039047986268997
2023-01-23 01:00:45.329688: step: 400/529, loss: 0.13804897665977478
2023-01-23 01:00:46.503795: step: 404/529, loss: 0.016185570508241653
2023-01-23 01:00:47.611347: step: 408/529, loss: 0.01443338394165039
2023-01-23 01:00:48.706334: step: 412/529, loss: 0.14113016426563263
2023-01-23 01:00:49.795881: step: 416/529, loss: 0.23866643011569977
2023-01-23 01:00:50.908269: step: 420/529, loss: 0.19302988052368164
2023-01-23 01:00:52.013000: step: 424/529, loss: 0.3451392948627472
2023-01-23 01:00:53.111982: step: 428/529, loss: 0.04785561561584473
2023-01-23 01:00:54.244909: step: 432/529, loss: 0.07870607078075409
2023-01-23 01:00:55.332630: step: 436/529, loss: 0.08337584137916565
2023-01-23 01:00:56.477698: step: 440/529, loss: 0.024120450019836426
2023-01-23 01:00:57.595316: step: 444/529, loss: 0.04644451290369034
2023-01-23 01:00:58.719978: step: 448/529, loss: 0.07648640125989914
2023-01-23 01:00:59.869242: step: 452/529, loss: 0.10845880955457687
2023-01-23 01:01:00.965034: step: 456/529, loss: 0.1912718415260315
2023-01-23 01:01:02.077661: step: 460/529, loss: 0.11780153214931488
2023-01-23 01:01:03.187494: step: 464/529, loss: 0.1476554423570633
2023-01-23 01:01:04.295151: step: 468/529, loss: 0.0731138214468956
2023-01-23 01:01:05.414012: step: 472/529, loss: 0.015170956030488014
2023-01-23 01:01:06.482569: step: 476/529, loss: 0.11919479817152023
2023-01-23 01:01:07.599209: step: 480/529, loss: 0.16263265907764435
2023-01-23 01:01:08.719413: step: 484/529, loss: 0.1139630377292633
2023-01-23 01:01:09.816040: step: 488/529, loss: 0.18790999054908752
2023-01-23 01:01:10.933232: step: 492/529, loss: 0.0621342696249485
2023-01-23 01:01:12.056913: step: 496/529, loss: 0.0645180195569992
2023-01-23 01:01:13.159490: step: 500/529, loss: 0.05574359744787216
2023-01-23 01:01:14.273428: step: 504/529, loss: 0.14265528321266174
2023-01-23 01:01:15.375202: step: 508/529, loss: 0.07000589370727539
2023-01-23 01:01:16.460932: step: 512/529, loss: 0.09280486404895782
2023-01-23 01:01:17.598832: step: 516/529, loss: 0.14939813315868378
2023-01-23 01:01:18.711299: step: 520/529, loss: 0.05603532865643501
2023-01-23 01:01:19.819650: step: 524/529, loss: 0.0800023078918457
2023-01-23 01:01:20.921786: step: 528/529, loss: 0.05761460214853287
2023-01-23 01:01:22.006676: step: 532/529, loss: 0.040703631937503815
2023-01-23 01:01:23.139661: step: 536/529, loss: 0.15799598395824432
2023-01-23 01:01:24.245016: step: 540/529, loss: 0.01688542403280735
2023-01-23 01:01:25.341641: step: 544/529, loss: 0.10103998333215714
2023-01-23 01:01:26.472693: step: 548/529, loss: 0.028824234381318092
2023-01-23 01:01:27.593128: step: 552/529, loss: 0.03666649013757706
2023-01-23 01:01:28.696906: step: 556/529, loss: 0.1671028435230255
2023-01-23 01:01:29.822805: step: 560/529, loss: 0.1756400167942047
2023-01-23 01:01:30.943640: step: 564/529, loss: 0.015729619190096855
2023-01-23 01:01:32.045495: step: 568/529, loss: 0.10626716911792755
2023-01-23 01:01:33.129261: step: 572/529, loss: 0.011851310729980469
2023-01-23 01:01:34.225557: step: 576/529, loss: 0.05698714405298233
2023-01-23 01:01:35.336418: step: 580/529, loss: 0.027351761236786842
2023-01-23 01:01:36.457934: step: 584/529, loss: 0.04248428717255592
2023-01-23 01:01:37.539950: step: 588/529, loss: 0.02740459330379963
2023-01-23 01:01:38.622714: step: 592/529, loss: 0.06386041641235352
2023-01-23 01:01:39.748365: step: 596/529, loss: 0.0068108560517430305
2023-01-23 01:01:40.862139: step: 600/529, loss: 0.05725877359509468
2023-01-23 01:01:41.980348: step: 604/529, loss: 0.08643150329589844
2023-01-23 01:01:43.089851: step: 608/529, loss: 0.6223519444465637
2023-01-23 01:01:44.202139: step: 612/529, loss: 0.04120521619915962
2023-01-23 01:01:45.306698: step: 616/529, loss: 0.007879400625824928
2023-01-23 01:01:46.428734: step: 620/529, loss: 0.04057574272155762
2023-01-23 01:01:47.557211: step: 624/529, loss: 0.10579729080200195
2023-01-23 01:01:48.656877: step: 628/529, loss: 0.057329509407281876
2023-01-23 01:01:49.774298: step: 632/529, loss: 0.06602416187524796
2023-01-23 01:01:50.874436: step: 636/529, loss: 0.09648457169532776
2023-01-23 01:01:51.977015: step: 640/529, loss: 0.05993414297699928
2023-01-23 01:01:53.098825: step: 644/529, loss: 0.016345595940947533
2023-01-23 01:01:54.217127: step: 648/529, loss: 0.12050972133874893
2023-01-23 01:01:55.346952: step: 652/529, loss: 0.13320191204547882
2023-01-23 01:01:56.461957: step: 656/529, loss: 0.07330746948719025
2023-01-23 01:01:57.555160: step: 660/529, loss: 0.0422452948987484
2023-01-23 01:01:58.670931: step: 664/529, loss: 0.06081104278564453
2023-01-23 01:01:59.798292: step: 668/529, loss: 0.02058258093893528
2023-01-23 01:02:00.933768: step: 672/529, loss: 0.49855002760887146
2023-01-23 01:02:02.028533: step: 676/529, loss: 0.18403233587741852
2023-01-23 01:02:03.146695: step: 680/529, loss: 0.31557580828666687
2023-01-23 01:02:04.260508: step: 684/529, loss: 0.012333488091826439
2023-01-23 01:02:05.349921: step: 688/529, loss: 0.02431764453649521
2023-01-23 01:02:06.484670: step: 692/529, loss: 0.28456413745880127
2023-01-23 01:02:07.597860: step: 696/529, loss: 0.17587552964687347
2023-01-23 01:02:08.691876: step: 700/529, loss: 0.10035070031881332
2023-01-23 01:02:09.777703: step: 704/529, loss: 0.04790849983692169
2023-01-23 01:02:10.903881: step: 708/529, loss: 0.06891946494579315
2023-01-23 01:02:12.014122: step: 712/529, loss: 0.028696918860077858
2023-01-23 01:02:13.169814: step: 716/529, loss: 0.01744098775088787
2023-01-23 01:02:14.266454: step: 720/529, loss: 0.05084972456097603
2023-01-23 01:02:15.374687: step: 724/529, loss: 0.7905058264732361
2023-01-23 01:02:16.474396: step: 728/529, loss: 0.023940706625580788
2023-01-23 01:02:17.585124: step: 732/529, loss: 0.048513222485780716
2023-01-23 01:02:18.673232: step: 736/529, loss: 0.04477844387292862
2023-01-23 01:02:19.780913: step: 740/529, loss: 0.042609453201293945
2023-01-23 01:02:20.868165: step: 744/529, loss: 0.13574886322021484
2023-01-23 01:02:21.974674: step: 748/529, loss: 0.057868484407663345
2023-01-23 01:02:23.061597: step: 752/529, loss: 0.077783964574337
2023-01-23 01:02:24.183864: step: 756/529, loss: 0.08376830816268921
2023-01-23 01:02:25.297659: step: 760/529, loss: 0.6848520636558533
2023-01-23 01:02:26.406255: step: 764/529, loss: 0.06643247604370117
2023-01-23 01:02:27.534825: step: 768/529, loss: 0.014272689819335938
2023-01-23 01:02:28.657014: step: 772/529, loss: 0.044089894741773605
2023-01-23 01:02:29.754387: step: 776/529, loss: 0.001986376941204071
2023-01-23 01:02:30.856939: step: 780/529, loss: 0.026595210656523705
2023-01-23 01:02:31.969735: step: 784/529, loss: 0.10692854225635529
2023-01-23 01:02:33.054640: step: 788/529, loss: 0.028864096850156784
2023-01-23 01:02:34.182866: step: 792/529, loss: 0.02127533033490181
2023-01-23 01:02:35.317197: step: 796/529, loss: 0.3346277177333832
2023-01-23 01:02:36.437511: step: 800/529, loss: 0.12227492034435272
2023-01-23 01:02:37.572065: step: 804/529, loss: 0.006898021791130304
2023-01-23 01:02:38.683609: step: 808/529, loss: 0.11880576610565186
2023-01-23 01:02:39.788390: step: 812/529, loss: 0.014857769012451172
2023-01-23 01:02:40.933630: step: 816/529, loss: 0.1547391712665558
2023-01-23 01:02:42.041602: step: 820/529, loss: 0.016665935516357422
2023-01-23 01:02:43.153966: step: 824/529, loss: 0.044320181012153625
2023-01-23 01:02:44.232613: step: 828/529, loss: 0.14291496574878693
2023-01-23 01:02:45.358155: step: 832/529, loss: 0.17214222252368927
2023-01-23 01:02:46.459101: step: 836/529, loss: 0.06896086037158966
2023-01-23 01:02:47.557614: step: 840/529, loss: 0.04852494224905968
2023-01-23 01:02:48.653143: step: 844/529, loss: 0.06520214676856995
2023-01-23 01:02:49.757216: step: 848/529, loss: 0.07643423229455948
2023-01-23 01:02:50.879139: step: 852/529, loss: 0.07438163459300995
2023-01-23 01:02:51.997204: step: 856/529, loss: 0.05007372051477432
2023-01-23 01:02:53.108543: step: 860/529, loss: 0.112081378698349
2023-01-23 01:02:54.227376: step: 864/529, loss: 0.06313200294971466
2023-01-23 01:02:55.321024: step: 868/529, loss: 0.05984840914607048
2023-01-23 01:02:56.433057: step: 872/529, loss: 0.03737363964319229
2023-01-23 01:02:57.545167: step: 876/529, loss: 0.04383154213428497
2023-01-23 01:02:58.636350: step: 880/529, loss: 0.18145990371704102
2023-01-23 01:02:59.746059: step: 884/529, loss: 0.07630787789821625
2023-01-23 01:03:00.856068: step: 888/529, loss: 0.03633446618914604
2023-01-23 01:03:01.938122: step: 892/529, loss: 0.03711829334497452
2023-01-23 01:03:03.028094: step: 896/529, loss: 0.04978237301111221
2023-01-23 01:03:04.122718: step: 900/529, loss: 0.09621293842792511
2023-01-23 01:03:05.262292: step: 904/529, loss: 0.1381158083677292
2023-01-23 01:03:06.373720: step: 908/529, loss: 0.07454118132591248
2023-01-23 01:03:07.488808: step: 912/529, loss: 0.6612171530723572
2023-01-23 01:03:08.621414: step: 916/529, loss: 0.09623517841100693
2023-01-23 01:03:09.737984: step: 920/529, loss: 0.04454955831170082
2023-01-23 01:03:10.869233: step: 924/529, loss: 0.06601305305957794
2023-01-23 01:03:11.990459: step: 928/529, loss: 0.060262106359004974
2023-01-23 01:03:13.079764: step: 932/529, loss: 0.0812913030385971
2023-01-23 01:03:14.193182: step: 936/529, loss: 0.05629901960492134
2023-01-23 01:03:15.295010: step: 940/529, loss: 0.1083926185965538
2023-01-23 01:03:16.412804: step: 944/529, loss: 0.044487953186035156
2023-01-23 01:03:17.510442: step: 948/529, loss: 0.09143247455358505
2023-01-23 01:03:18.632884: step: 952/529, loss: 0.13394412398338318
2023-01-23 01:03:19.747223: step: 956/529, loss: 0.06732816994190216
2023-01-23 01:03:20.874396: step: 960/529, loss: 0.08902082592248917
2023-01-23 01:03:21.988183: step: 964/529, loss: 0.08154439926147461
2023-01-23 01:03:23.111323: step: 968/529, loss: 0.032379150390625
2023-01-23 01:03:24.229803: step: 972/529, loss: 0.10394573211669922
2023-01-23 01:03:25.354481: step: 976/529, loss: 0.33629971742630005
2023-01-23 01:03:26.492879: step: 980/529, loss: 0.5062699317932129
2023-01-23 01:03:27.603980: step: 984/529, loss: 0.023540304973721504
2023-01-23 01:03:28.719149: step: 988/529, loss: 0.0951499491930008
2023-01-23 01:03:29.854801: step: 992/529, loss: 0.01879253424704075
2023-01-23 01:03:30.986703: step: 996/529, loss: 0.012501239776611328
2023-01-23 01:03:32.085813: step: 1000/529, loss: 0.10540914535522461
2023-01-23 01:03:33.185579: step: 1004/529, loss: 0.2552165985107422
2023-01-23 01:03:34.297749: step: 1008/529, loss: 0.05841560289263725
2023-01-23 01:03:35.405733: step: 1012/529, loss: 0.1975843459367752
2023-01-23 01:03:36.562845: step: 1016/529, loss: 0.060215093195438385
2023-01-23 01:03:37.699738: step: 1020/529, loss: 0.0384943000972271
2023-01-23 01:03:38.846953: step: 1024/529, loss: 0.06896467506885529
2023-01-23 01:03:39.977365: step: 1028/529, loss: 0.018214941024780273
2023-01-23 01:03:41.093810: step: 1032/529, loss: 0.11634024977684021
2023-01-23 01:03:42.210019: step: 1036/529, loss: 0.3821887969970703
2023-01-23 01:03:43.319681: step: 1040/529, loss: 0.2518870234489441
2023-01-23 01:03:44.428436: step: 1044/529, loss: 0.11563281714916229
2023-01-23 01:03:45.535181: step: 1048/529, loss: 0.12849339842796326
2023-01-23 01:03:46.619537: step: 1052/529, loss: 0.1095949113368988
2023-01-23 01:03:47.707467: step: 1056/529, loss: 0.32417404651641846
2023-01-23 01:03:48.812807: step: 1060/529, loss: 0.008027458563446999
2023-01-23 01:03:49.920139: step: 1064/529, loss: 0.06524324417114258
2023-01-23 01:03:51.055218: step: 1068/529, loss: 0.06365480273962021
2023-01-23 01:03:52.161354: step: 1072/529, loss: 0.031239653006196022
2023-01-23 01:03:53.268637: step: 1076/529, loss: 0.06233043596148491
2023-01-23 01:03:54.374590: step: 1080/529, loss: 0.10023470222949982
2023-01-23 01:03:55.477147: step: 1084/529, loss: 0.19548740983009338
2023-01-23 01:03:56.610862: step: 1088/529, loss: 0.08747239410877228
2023-01-23 01:03:57.735166: step: 1092/529, loss: 0.026029586791992188
2023-01-23 01:03:58.860187: step: 1096/529, loss: 0.05856723710894585
2023-01-23 01:04:00.031061: step: 1100/529, loss: 0.0699123814702034
2023-01-23 01:04:01.138125: step: 1104/529, loss: 0.060286711901426315
2023-01-23 01:04:02.234410: step: 1108/529, loss: 0.030222607776522636
2023-01-23 01:04:03.370235: step: 1112/529, loss: 0.09417829662561417
2023-01-23 01:04:04.461833: step: 1116/529, loss: 0.01377573050558567
2023-01-23 01:04:05.583697: step: 1120/529, loss: 0.1039462611079216
2023-01-23 01:04:06.672558: step: 1124/529, loss: 0.06650018692016602
2023-01-23 01:04:07.768570: step: 1128/529, loss: 0.045432060956954956
2023-01-23 01:04:08.864417: step: 1132/529, loss: 0.6863029599189758
2023-01-23 01:04:09.970994: step: 1136/529, loss: 0.18507003784179688
2023-01-23 01:04:11.108099: step: 1140/529, loss: 0.03508634865283966
2023-01-23 01:04:12.223548: step: 1144/529, loss: 0.040506839752197266
2023-01-23 01:04:13.343192: step: 1148/529, loss: 0.18322515487670898
2023-01-23 01:04:14.461837: step: 1152/529, loss: 0.1081615537405014
2023-01-23 01:04:15.571272: step: 1156/529, loss: 0.044408418238162994
2023-01-23 01:04:16.703723: step: 1160/529, loss: 0.04965457692742348
2023-01-23 01:04:17.836398: step: 1164/529, loss: 0.21872863173484802
2023-01-23 01:04:18.946908: step: 1168/529, loss: 0.08637867122888565
2023-01-23 01:04:20.109425: step: 1172/529, loss: 0.07635793834924698
2023-01-23 01:04:21.205535: step: 1176/529, loss: 0.07406573742628098
2023-01-23 01:04:22.286866: step: 1180/529, loss: 0.0973435491323471
2023-01-23 01:04:23.414654: step: 1184/529, loss: 0.04751301184296608
2023-01-23 01:04:24.504903: step: 1188/529, loss: 0.02748269960284233
2023-01-23 01:04:25.623330: step: 1192/529, loss: 0.2465149611234665
2023-01-23 01:04:26.745901: step: 1196/529, loss: 0.041822243481874466
2023-01-23 01:04:27.865742: step: 1200/529, loss: 0.08025749027729034
2023-01-23 01:04:28.984216: step: 1204/529, loss: 0.09643816947937012
2023-01-23 01:04:30.119653: step: 1208/529, loss: 0.0659547820687294
2023-01-23 01:04:31.220528: step: 1212/529, loss: 0.18151094019412994
2023-01-23 01:04:32.319801: step: 1216/529, loss: 0.07799167931079865
2023-01-23 01:04:33.440678: step: 1220/529, loss: 0.09307403862476349
2023-01-23 01:04:34.559591: step: 1224/529, loss: 0.006068134680390358
2023-01-23 01:04:35.674793: step: 1228/529, loss: 0.13911017775535583
2023-01-23 01:04:36.798686: step: 1232/529, loss: 0.06770257651805878
2023-01-23 01:04:37.918552: step: 1236/529, loss: 0.1125824972987175
2023-01-23 01:04:39.041467: step: 1240/529, loss: 0.06380510330200195
2023-01-23 01:04:40.172322: step: 1244/529, loss: 0.1834530383348465
2023-01-23 01:04:41.263057: step: 1248/529, loss: 0.03923363983631134
2023-01-23 01:04:42.366724: step: 1252/529, loss: 0.11145992577075958
2023-01-23 01:04:43.519100: step: 1256/529, loss: 0.08441410213708878
2023-01-23 01:04:44.621180: step: 1260/529, loss: 0.07938718795776367
2023-01-23 01:04:45.762521: step: 1264/529, loss: 0.02035675011575222
2023-01-23 01:04:46.898717: step: 1268/529, loss: 0.10938110947608948
2023-01-23 01:04:48.005262: step: 1272/529, loss: 0.19580736756324768
2023-01-23 01:04:49.122119: step: 1276/529, loss: 0.14145508408546448
2023-01-23 01:04:50.284559: step: 1280/529, loss: 0.04451394081115723
2023-01-23 01:04:51.405383: step: 1284/529, loss: 0.003300571581348777
2023-01-23 01:04:52.517161: step: 1288/529, loss: 0.3471525311470032
2023-01-23 01:04:53.649410: step: 1292/529, loss: 0.21434137225151062
2023-01-23 01:04:54.763409: step: 1296/529, loss: 0.0013439178001135588
2023-01-23 01:04:55.862843: step: 1300/529, loss: 0.13756266236305237
2023-01-23 01:04:56.955063: step: 1304/529, loss: 0.04944667965173721
2023-01-23 01:04:58.040261: step: 1308/529, loss: 0.1475081443786621
2023-01-23 01:04:59.143958: step: 1312/529, loss: 0.009082937613129616
2023-01-23 01:05:00.266724: step: 1316/529, loss: 0.04438390955328941
2023-01-23 01:05:01.414530: step: 1320/529, loss: 0.015398358926177025
2023-01-23 01:05:02.521299: step: 1324/529, loss: 0.08248873054981232
2023-01-23 01:05:03.626372: step: 1328/529, loss: 0.0918426513671875
2023-01-23 01:05:04.748358: step: 1332/529, loss: 0.04811515659093857
2023-01-23 01:05:05.863498: step: 1336/529, loss: 0.12027950584888458
2023-01-23 01:05:06.962483: step: 1340/529, loss: 0.04040975868701935
2023-01-23 01:05:08.102562: step: 1344/529, loss: 0.06928618252277374
2023-01-23 01:05:09.223664: step: 1348/529, loss: 0.07258549332618713
2023-01-23 01:05:10.319675: step: 1352/529, loss: 0.10316307842731476
2023-01-23 01:05:11.448189: step: 1356/529, loss: 0.14421701431274414
2023-01-23 01:05:12.533217: step: 1360/529, loss: 0.04028075933456421
2023-01-23 01:05:13.645946: step: 1364/529, loss: 0.025164222344756126
2023-01-23 01:05:14.768606: step: 1368/529, loss: 0.1758926957845688
2023-01-23 01:05:15.863852: step: 1372/529, loss: 0.031922150403261185
2023-01-23 01:05:16.968323: step: 1376/529, loss: 0.14625835418701172
2023-01-23 01:05:18.084459: step: 1380/529, loss: 0.2937980592250824
2023-01-23 01:05:19.190087: step: 1384/529, loss: 0.17285165190696716
2023-01-23 01:05:20.303631: step: 1388/529, loss: 0.007736682891845703
2023-01-23 01:05:21.405295: step: 1392/529, loss: 0.1878342628479004
2023-01-23 01:05:22.498590: step: 1396/529, loss: 0.13419370353221893
2023-01-23 01:05:23.622660: step: 1400/529, loss: 0.02635507471859455
2023-01-23 01:05:24.746332: step: 1404/529, loss: 0.05696258693933487
2023-01-23 01:05:25.862758: step: 1408/529, loss: 0.009402275085449219
2023-01-23 01:05:27.009416: step: 1412/529, loss: 0.12353183329105377
2023-01-23 01:05:28.108754: step: 1416/529, loss: 0.08068886399269104
2023-01-23 01:05:29.249976: step: 1420/529, loss: 0.02467794343829155
2023-01-23 01:05:30.342653: step: 1424/529, loss: 0.060294248163700104
2023-01-23 01:05:31.441084: step: 1428/529, loss: 0.08148124814033508
2023-01-23 01:05:32.562996: step: 1432/529, loss: 0.10907106101512909
2023-01-23 01:05:33.715196: step: 1436/529, loss: 0.14531207084655762
2023-01-23 01:05:34.809906: step: 1440/529, loss: 0.00984878558665514
2023-01-23 01:05:35.933859: step: 1444/529, loss: 0.014052271842956543
2023-01-23 01:05:37.058145: step: 1448/529, loss: 0.5679744482040405
2023-01-23 01:05:38.184987: step: 1452/529, loss: 0.09771182388067245
2023-01-23 01:05:39.293297: step: 1456/529, loss: 0.0191174503415823
2023-01-23 01:05:40.396416: step: 1460/529, loss: 0.0334656722843647
2023-01-23 01:05:41.493758: step: 1464/529, loss: 0.2043953835964203
2023-01-23 01:05:42.620723: step: 1468/529, loss: 0.009652710519731045
2023-01-23 01:05:43.728924: step: 1472/529, loss: 0.052018169313669205
2023-01-23 01:05:44.844076: step: 1476/529, loss: 0.11485262215137482
2023-01-23 01:05:45.979647: step: 1480/529, loss: 0.07693605870008469
2023-01-23 01:05:47.096015: step: 1484/529, loss: 0.13758641481399536
2023-01-23 01:05:48.201581: step: 1488/529, loss: 0.03982071578502655
2023-01-23 01:05:49.309343: step: 1492/529, loss: 0.0795324370265007
2023-01-23 01:05:50.441546: step: 1496/529, loss: 0.08048317581415176
2023-01-23 01:05:51.552849: step: 1500/529, loss: 0.03495984151959419
2023-01-23 01:05:52.673049: step: 1504/529, loss: 0.05106806755065918
2023-01-23 01:05:53.802361: step: 1508/529, loss: 0.1111084371805191
2023-01-23 01:05:54.898199: step: 1512/529, loss: 0.026851128786802292
2023-01-23 01:05:55.995736: step: 1516/529, loss: 0.2244413197040558
2023-01-23 01:05:57.119260: step: 1520/529, loss: 0.29151174426078796
2023-01-23 01:05:58.207769: step: 1524/529, loss: 0.13247866928577423
2023-01-23 01:05:59.328308: step: 1528/529, loss: 0.05381937325000763
2023-01-23 01:06:00.414910: step: 1532/529, loss: 0.013446998782455921
2023-01-23 01:06:01.512536: step: 1536/529, loss: 0.11355744302272797
2023-01-23 01:06:02.621322: step: 1540/529, loss: 0.5881436467170715
2023-01-23 01:06:03.743296: step: 1544/529, loss: 0.16452428698539734
2023-01-23 01:06:04.856295: step: 1548/529, loss: 0.018399905413389206
2023-01-23 01:06:05.984554: step: 1552/529, loss: 0.1797565519809723
2023-01-23 01:06:07.117166: step: 1556/529, loss: 0.10114951431751251
2023-01-23 01:06:08.215938: step: 1560/529, loss: 0.3463018536567688
2023-01-23 01:06:09.307140: step: 1564/529, loss: 0.0870586410164833
2023-01-23 01:06:10.389815: step: 1568/529, loss: 0.08252926170825958
2023-01-23 01:06:11.505773: step: 1572/529, loss: 0.17114019393920898
2023-01-23 01:06:12.622768: step: 1576/529, loss: 0.10457129776477814
2023-01-23 01:06:13.740980: step: 1580/529, loss: 0.07745208591222763
2023-01-23 01:06:14.850670: step: 1584/529, loss: 0.03918357193470001
2023-01-23 01:06:15.985139: step: 1588/529, loss: 0.12574857473373413
2023-01-23 01:06:17.066387: step: 1592/529, loss: 0.1182066947221756
2023-01-23 01:06:18.207458: step: 1596/529, loss: 0.010142517276108265
2023-01-23 01:06:19.318849: step: 1600/529, loss: 0.08751335740089417
2023-01-23 01:06:20.432569: step: 1604/529, loss: 0.11351537704467773
2023-01-23 01:06:21.534051: step: 1608/529, loss: 0.9204500317573547
2023-01-23 01:06:22.641607: step: 1612/529, loss: 0.05030689388513565
2023-01-23 01:06:23.774537: step: 1616/529, loss: 0.1784447729587555
2023-01-23 01:06:24.923376: step: 1620/529, loss: 0.05158596113324165
2023-01-23 01:06:26.019420: step: 1624/529, loss: 0.05183391645550728
2023-01-23 01:06:27.123968: step: 1628/529, loss: 0.60284423828125
2023-01-23 01:06:28.243522: step: 1632/529, loss: 0.003727531526237726
2023-01-23 01:06:29.375448: step: 1636/529, loss: 0.08788242936134338
2023-01-23 01:06:30.506464: step: 1640/529, loss: 0.025651073083281517
2023-01-23 01:06:31.580977: step: 1644/529, loss: 0.017536640167236328
2023-01-23 01:06:32.684872: step: 1648/529, loss: 0.08216686546802521
2023-01-23 01:06:33.789508: step: 1652/529, loss: 0.017567062750458717
2023-01-23 01:06:34.920944: step: 1656/529, loss: 0.10507622361183167
2023-01-23 01:06:36.028998: step: 1660/529, loss: 0.1343797743320465
2023-01-23 01:06:37.143965: step: 1664/529, loss: 0.0984993502497673
2023-01-23 01:06:38.226877: step: 1668/529, loss: 0.03480367735028267
2023-01-23 01:06:39.335267: step: 1672/529, loss: 0.07474584877490997
2023-01-23 01:06:40.466830: step: 1676/529, loss: 0.029497720301151276
2023-01-23 01:06:41.594361: step: 1680/529, loss: 0.02427997626364231
2023-01-23 01:06:42.713197: step: 1684/529, loss: 0.04129553213715553
2023-01-23 01:06:43.866742: step: 1688/529, loss: 0.0964839905500412
2023-01-23 01:06:44.959718: step: 1692/529, loss: 0.1205843985080719
2023-01-23 01:06:46.078520: step: 1696/529, loss: 0.026320649310946465
2023-01-23 01:06:47.211520: step: 1700/529, loss: 0.18613243103027344
2023-01-23 01:06:48.297925: step: 1704/529, loss: 0.010318756103515625
2023-01-23 01:06:49.376741: step: 1708/529, loss: 0.015778400003910065
2023-01-23 01:06:50.496672: step: 1712/529, loss: 0.3122726380825043
2023-01-23 01:06:51.587694: step: 1716/529, loss: 0.021357107907533646
2023-01-23 01:06:52.669191: step: 1720/529, loss: 0.05111951753497124
2023-01-23 01:06:53.750453: step: 1724/529, loss: 0.005657053552567959
2023-01-23 01:06:54.883795: step: 1728/529, loss: 0.11666889488697052
2023-01-23 01:06:55.990932: step: 1732/529, loss: 0.41078507900238037
2023-01-23 01:06:57.090130: step: 1736/529, loss: 0.36201146245002747
2023-01-23 01:06:58.233938: step: 1740/529, loss: 0.02566089667379856
2023-01-23 01:06:59.310801: step: 1744/529, loss: 0.22240696847438812
2023-01-23 01:07:00.409042: step: 1748/529, loss: 0.04610276222229004
2023-01-23 01:07:01.528916: step: 1752/529, loss: 0.04786386340856552
2023-01-23 01:07:02.630874: step: 1756/529, loss: 0.039374664425849915
2023-01-23 01:07:03.710586: step: 1760/529, loss: 0.08335819840431213
2023-01-23 01:07:04.826302: step: 1764/529, loss: 0.07185249775648117
2023-01-23 01:07:05.950691: step: 1768/529, loss: 0.15856905281543732
2023-01-23 01:07:07.073529: step: 1772/529, loss: 0.03192448616027832
2023-01-23 01:07:08.193050: step: 1776/529, loss: 0.12803632020950317
2023-01-23 01:07:09.311569: step: 1780/529, loss: 0.19158053398132324
2023-01-23 01:07:10.421424: step: 1784/529, loss: 0.630646824836731
2023-01-23 01:07:11.547264: step: 1788/529, loss: 0.021214868873357773
2023-01-23 01:07:12.646866: step: 1792/529, loss: 0.07143059372901917
2023-01-23 01:07:13.769802: step: 1796/529, loss: 0.1357056051492691
2023-01-23 01:07:14.895912: step: 1800/529, loss: 0.04163026809692383
2023-01-23 01:07:15.975553: step: 1804/529, loss: 0.05554194375872612
2023-01-23 01:07:17.061250: step: 1808/529, loss: 0.001104164170101285
2023-01-23 01:07:18.178027: step: 1812/529, loss: 0.1678251326084137
2023-01-23 01:07:19.305797: step: 1816/529, loss: 0.09261083602905273
2023-01-23 01:07:20.458466: step: 1820/529, loss: 0.07316761463880539
2023-01-23 01:07:21.570918: step: 1824/529, loss: 0.16719341278076172
2023-01-23 01:07:22.677584: step: 1828/529, loss: 0.25669464468955994
2023-01-23 01:07:23.774273: step: 1832/529, loss: 0.02870168723165989
2023-01-23 01:07:24.894448: step: 1836/529, loss: 0.05384483560919762
2023-01-23 01:07:26.005663: step: 1840/529, loss: 0.023204613476991653
2023-01-23 01:07:27.144819: step: 1844/529, loss: 0.3067391514778137
2023-01-23 01:07:28.275153: step: 1848/529, loss: 0.1798103302717209
2023-01-23 01:07:29.371099: step: 1852/529, loss: 0.024246692657470703
2023-01-23 01:07:30.453201: step: 1856/529, loss: 0.19331133365631104
2023-01-23 01:07:31.561294: step: 1860/529, loss: 0.1499234288930893
2023-01-23 01:07:32.678094: step: 1864/529, loss: 0.08906231075525284
2023-01-23 01:07:33.747275: step: 1868/529, loss: 0.013643741607666016
2023-01-23 01:07:34.839735: step: 1872/529, loss: 0.10728979110717773
2023-01-23 01:07:35.932115: step: 1876/529, loss: 0.2997283935546875
2023-01-23 01:07:37.030176: step: 1880/529, loss: 0.0766817107796669
2023-01-23 01:07:38.132714: step: 1884/529, loss: 0.0796487033367157
2023-01-23 01:07:39.251311: step: 1888/529, loss: 0.02410421520471573
2023-01-23 01:07:40.360478: step: 1892/529, loss: 0.26116690039634705
2023-01-23 01:07:41.469747: step: 1896/529, loss: 0.12138329446315765
2023-01-23 01:07:42.581328: step: 1900/529, loss: 0.2350689023733139
2023-01-23 01:07:43.680958: step: 1904/529, loss: 0.11842866241931915
2023-01-23 01:07:44.849728: step: 1908/529, loss: 0.05647840350866318
2023-01-23 01:07:45.972207: step: 1912/529, loss: 0.06652762740850449
2023-01-23 01:07:47.095046: step: 1916/529, loss: 0.19929274916648865
2023-01-23 01:07:48.206435: step: 1920/529, loss: 0.18102556467056274
2023-01-23 01:07:49.321639: step: 1924/529, loss: 0.16160912811756134
2023-01-23 01:07:50.425759: step: 1928/529, loss: 0.017178857699036598
2023-01-23 01:07:51.539383: step: 1932/529, loss: 0.07090263068675995
2023-01-23 01:07:52.621213: step: 1936/529, loss: 0.05810260772705078
2023-01-23 01:07:53.767037: step: 1940/529, loss: 0.1487790048122406
2023-01-23 01:07:54.867783: step: 1944/529, loss: 0.08140314370393753
2023-01-23 01:07:55.988663: step: 1948/529, loss: 0.17723149061203003
2023-01-23 01:07:57.089369: step: 1952/529, loss: 0.028296852484345436
2023-01-23 01:07:58.213692: step: 1956/529, loss: 0.0789031982421875
2023-01-23 01:07:59.310423: step: 1960/529, loss: 0.004878330510109663
2023-01-23 01:08:00.437833: step: 1964/529, loss: 0.08981533348560333
2023-01-23 01:08:01.522491: step: 1968/529, loss: 0.051788900047540665
2023-01-23 01:08:02.646466: step: 1972/529, loss: 0.18572577834129333
2023-01-23 01:08:03.764739: step: 1976/529, loss: 0.5622392892837524
2023-01-23 01:08:04.880303: step: 1980/529, loss: 0.05681190639734268
2023-01-23 01:08:05.989141: step: 1984/529, loss: 0.056949131190776825
2023-01-23 01:08:07.129914: step: 1988/529, loss: 0.11759801208972931
2023-01-23 01:08:08.247928: step: 1992/529, loss: 0.09613952785730362
2023-01-23 01:08:09.353616: step: 1996/529, loss: 0.04975314438343048
2023-01-23 01:08:10.499565: step: 2000/529, loss: 0.045046284794807434
2023-01-23 01:08:11.593163: step: 2004/529, loss: 0.09842129051685333
2023-01-23 01:08:12.681375: step: 2008/529, loss: 0.14135675132274628
2023-01-23 01:08:13.805788: step: 2012/529, loss: 0.1797056347131729
2023-01-23 01:08:14.918191: step: 2016/529, loss: 0.05608811229467392
2023-01-23 01:08:16.020502: step: 2020/529, loss: 0.04219484701752663
2023-01-23 01:08:17.130857: step: 2024/529, loss: 0.03295278549194336
2023-01-23 01:08:18.245694: step: 2028/529, loss: 0.020505620166659355
2023-01-23 01:08:19.380868: step: 2032/529, loss: 0.03445548936724663
2023-01-23 01:08:20.480602: step: 2036/529, loss: 0.003640031674876809
2023-01-23 01:08:21.570247: step: 2040/529, loss: 0.08202600479125977
2023-01-23 01:08:22.678318: step: 2044/529, loss: 0.008945586159825325
2023-01-23 01:08:23.799822: step: 2048/529, loss: 0.026433609426021576
2023-01-23 01:08:24.941629: step: 2052/529, loss: 0.09628425538539886
2023-01-23 01:08:26.063845: step: 2056/529, loss: 0.11806364357471466
2023-01-23 01:08:27.177987: step: 2060/529, loss: 0.08045964688062668
2023-01-23 01:08:28.303272: step: 2064/529, loss: 0.04945630952715874
2023-01-23 01:08:29.412093: step: 2068/529, loss: 0.06084764003753662
2023-01-23 01:08:30.516653: step: 2072/529, loss: 0.2920656204223633
2023-01-23 01:08:31.639623: step: 2076/529, loss: 0.05531301349401474
2023-01-23 01:08:32.731505: step: 2080/529, loss: 0.31405580043792725
2023-01-23 01:08:33.878689: step: 2084/529, loss: 0.03344249725341797
2023-01-23 01:08:34.987722: step: 2088/529, loss: 0.1520463079214096
2023-01-23 01:08:36.083553: step: 2092/529, loss: 0.20689153671264648
2023-01-23 01:08:37.186459: step: 2096/529, loss: 0.21345052123069763
2023-01-23 01:08:38.290737: step: 2100/529, loss: 0.11501679569482803
2023-01-23 01:08:39.397143: step: 2104/529, loss: 0.029697764664888382
2023-01-23 01:08:40.521592: step: 2108/529, loss: 0.2440405786037445
2023-01-23 01:08:41.635772: step: 2112/529, loss: 0.10995569825172424
2023-01-23 01:08:42.754048: step: 2116/529, loss: 0.04227665811777115
==================================================
Loss: 0.124
--------------------
Dev: {'event': {'p': 0.5798816568047337, 'r': 0.7829560585885486, 'f1': 0.6662889518413597}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.611233967271119, 'r': 0.7799097065462754, 'f1': 0.6853458963550707}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.4788732394366197, 'r': 0.5396825396825397, 'f1': 0.5074626865671641}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.4418604651162791, 'r': 0.5277777777777778, 'f1': 0.4810126582278481}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:09:22.911201: step: 4/529, loss: 0.06950245052576065
2023-01-23 01:09:24.002197: step: 8/529, loss: 0.04021148383617401
2023-01-23 01:09:25.119517: step: 12/529, loss: 0.14570626616477966
2023-01-23 01:09:26.217004: step: 16/529, loss: 0.0861416831612587
2023-01-23 01:09:27.331353: step: 20/529, loss: 0.1217346265912056
2023-01-23 01:09:28.412330: step: 24/529, loss: 0.02738165855407715
2023-01-23 01:09:29.518483: step: 28/529, loss: 0.012563848868012428
2023-01-23 01:09:30.621262: step: 32/529, loss: 0.021525001153349876
2023-01-23 01:09:31.715803: step: 36/529, loss: 0.025179320946335793
2023-01-23 01:09:32.797585: step: 40/529, loss: 0.016197968274354935
2023-01-23 01:09:33.899701: step: 44/529, loss: 0.028243256732821465
2023-01-23 01:09:35.026752: step: 48/529, loss: 0.06085710972547531
2023-01-23 01:09:36.140985: step: 52/529, loss: 0.009467840194702148
2023-01-23 01:09:37.239727: step: 56/529, loss: 0.03009519726037979
2023-01-23 01:09:38.343226: step: 60/529, loss: 0.1907138228416443
2023-01-23 01:09:39.460129: step: 64/529, loss: 0.1298326551914215
2023-01-23 01:09:40.550318: step: 68/529, loss: 0.04455399513244629
2023-01-23 01:09:41.679800: step: 72/529, loss: 0.027497030794620514
2023-01-23 01:09:42.792017: step: 76/529, loss: 0.0569947250187397
2023-01-23 01:09:43.882437: step: 80/529, loss: 0.044991157948970795
2023-01-23 01:09:44.978251: step: 84/529, loss: 0.10817378014326096
2023-01-23 01:09:46.071455: step: 88/529, loss: 0.017240095883607864
2023-01-23 01:09:47.198751: step: 92/529, loss: 0.01642007753252983
2023-01-23 01:09:48.313557: step: 96/529, loss: 0.019191836938261986
2023-01-23 01:09:49.442672: step: 100/529, loss: 0.0050757406279444695
2023-01-23 01:09:50.537663: step: 104/529, loss: 0.0720667839050293
2023-01-23 01:09:51.673391: step: 108/529, loss: 0.043734073638916016
2023-01-23 01:09:52.783553: step: 112/529, loss: 0.01588411256670952
2023-01-23 01:09:53.904949: step: 116/529, loss: 0.0852283462882042
2023-01-23 01:09:55.022920: step: 120/529, loss: 0.10721588134765625
2023-01-23 01:09:56.162543: step: 124/529, loss: 0.05493059381842613
2023-01-23 01:09:57.278256: step: 128/529, loss: 0.04765377193689346
2023-01-23 01:09:58.418804: step: 132/529, loss: 0.044267941266298294
2023-01-23 01:09:59.561710: step: 136/529, loss: 0.040538981556892395
2023-01-23 01:10:00.703700: step: 140/529, loss: 0.038683030754327774
2023-01-23 01:10:01.810060: step: 144/529, loss: 0.11157217621803284
2023-01-23 01:10:02.900175: step: 148/529, loss: 0.1508493423461914
2023-01-23 01:10:04.016910: step: 152/529, loss: 0.10179463028907776
2023-01-23 01:10:05.135560: step: 156/529, loss: 0.001695013022981584
2023-01-23 01:10:06.246246: step: 160/529, loss: 0.046556759625673294
2023-01-23 01:10:07.337993: step: 164/529, loss: 0.006415701471269131
2023-01-23 01:10:08.450676: step: 168/529, loss: 0.012030458077788353
2023-01-23 01:10:09.558227: step: 172/529, loss: 0.17725610733032227
2023-01-23 01:10:10.656991: step: 176/529, loss: 0.026179790496826172
2023-01-23 01:10:11.770879: step: 180/529, loss: 0.11263325810432434
2023-01-23 01:10:12.864315: step: 184/529, loss: 0.05074343830347061
2023-01-23 01:10:13.962466: step: 188/529, loss: 0.07608699798583984
2023-01-23 01:10:15.068703: step: 192/529, loss: 0.07712230831384659
2023-01-23 01:10:16.152198: step: 196/529, loss: 0.06077613681554794
2023-01-23 01:10:17.252109: step: 200/529, loss: 0.09429769217967987
2023-01-23 01:10:18.334060: step: 204/529, loss: 0.01578202284872532
2023-01-23 01:10:19.473591: step: 208/529, loss: 0.03738556057214737
2023-01-23 01:10:20.583515: step: 212/529, loss: 0.0626899003982544
2023-01-23 01:10:21.716745: step: 216/529, loss: 0.06241665035486221
2023-01-23 01:10:22.830598: step: 220/529, loss: 0.01506347581744194
2023-01-23 01:10:23.948237: step: 224/529, loss: 0.04915342107415199
2023-01-23 01:10:25.049657: step: 228/529, loss: 0.062230776995420456
2023-01-23 01:10:26.180482: step: 232/529, loss: 0.014750766567885876
2023-01-23 01:10:27.321378: step: 236/529, loss: 0.1026659607887268
2023-01-23 01:10:28.463855: step: 240/529, loss: 0.05019540712237358
2023-01-23 01:10:29.553249: step: 244/529, loss: 0.005922412965446711
2023-01-23 01:10:30.660816: step: 248/529, loss: 0.024925900623202324
2023-01-23 01:10:31.778947: step: 252/529, loss: 0.004024219699203968
2023-01-23 01:10:32.869127: step: 256/529, loss: 0.02569289319217205
2023-01-23 01:10:33.996863: step: 260/529, loss: 0.008908748626708984
2023-01-23 01:10:35.084462: step: 264/529, loss: 0.01979266107082367
2023-01-23 01:10:36.192421: step: 268/529, loss: 0.035695791244506836
2023-01-23 01:10:37.287675: step: 272/529, loss: 0.13730759918689728
2023-01-23 01:10:38.395324: step: 276/529, loss: 0.07338166236877441
2023-01-23 01:10:39.514552: step: 280/529, loss: 0.10899315029382706
2023-01-23 01:10:40.599670: step: 284/529, loss: 0.07925891876220703
2023-01-23 01:10:41.704718: step: 288/529, loss: 0.04474029690027237
2023-01-23 01:10:42.812262: step: 292/529, loss: 0.21635162830352783
2023-01-23 01:10:43.945013: step: 296/529, loss: 0.03347168117761612
2023-01-23 01:10:45.041185: step: 300/529, loss: 0.139997199177742
2023-01-23 01:10:46.145477: step: 304/529, loss: 0.013127708807587624
2023-01-23 01:10:47.296409: step: 308/529, loss: 0.0664484053850174
2023-01-23 01:10:48.394970: step: 312/529, loss: 0.04754181206226349
2023-01-23 01:10:49.495515: step: 316/529, loss: 0.02710428275167942
2023-01-23 01:10:50.593956: step: 320/529, loss: 0.08882904052734375
2023-01-23 01:10:51.704483: step: 324/529, loss: 0.06909863650798798
2023-01-23 01:10:52.804080: step: 328/529, loss: 0.05803317576646805
2023-01-23 01:10:53.939323: step: 332/529, loss: 0.24504026770591736
2023-01-23 01:10:55.032259: step: 336/529, loss: 0.08480215072631836
2023-01-23 01:10:56.159047: step: 340/529, loss: 0.10151185840368271
2023-01-23 01:10:57.256867: step: 344/529, loss: 0.06432318687438965
2023-01-23 01:10:58.373578: step: 348/529, loss: 0.15553614497184753
2023-01-23 01:10:59.488416: step: 352/529, loss: 0.10246536880731583
2023-01-23 01:11:00.598551: step: 356/529, loss: 0.034815311431884766
2023-01-23 01:11:01.699519: step: 360/529, loss: 0.07155991345643997
2023-01-23 01:11:02.826734: step: 364/529, loss: 0.10293684154748917
2023-01-23 01:11:03.917042: step: 368/529, loss: 0.04079904407262802
2023-01-23 01:11:05.048615: step: 372/529, loss: 0.12297402322292328
2023-01-23 01:11:06.192541: step: 376/529, loss: 0.0068219187669456005
2023-01-23 01:11:07.303839: step: 380/529, loss: 0.06119251251220703
2023-01-23 01:11:08.413044: step: 384/529, loss: 0.024859953671693802
2023-01-23 01:11:09.510922: step: 388/529, loss: 0.1250099539756775
2023-01-23 01:11:10.614611: step: 392/529, loss: 0.013640498742461205
2023-01-23 01:11:11.715148: step: 396/529, loss: 0.011499738320708275
2023-01-23 01:11:12.836507: step: 400/529, loss: 0.013403559103608131
2023-01-23 01:11:13.951073: step: 404/529, loss: 0.19005174934864044
2023-01-23 01:11:15.091894: step: 408/529, loss: 0.06413193047046661
2023-01-23 01:11:16.225375: step: 412/529, loss: 0.09859924018383026
2023-01-23 01:11:17.331330: step: 416/529, loss: 0.07810349762439728
2023-01-23 01:11:18.428209: step: 420/529, loss: 0.052854157984256744
2023-01-23 01:11:19.551676: step: 424/529, loss: 0.11092114448547363
2023-01-23 01:11:20.641742: step: 428/529, loss: 0.06058554723858833
2023-01-23 01:11:21.728535: step: 432/529, loss: 0.011052798479795456
2023-01-23 01:11:22.832746: step: 436/529, loss: 0.08526740968227386
2023-01-23 01:11:23.927535: step: 440/529, loss: 0.08960095047950745
2023-01-23 01:11:25.032785: step: 444/529, loss: 0.022571945562958717
2023-01-23 01:11:26.160247: step: 448/529, loss: 0.3154134154319763
2023-01-23 01:11:27.261707: step: 452/529, loss: 0.05916395038366318
2023-01-23 01:11:28.351081: step: 456/529, loss: 0.05604463070631027
2023-01-23 01:11:29.451067: step: 460/529, loss: 0.062203485518693924
2023-01-23 01:11:30.591323: step: 464/529, loss: 0.0969790518283844
2023-01-23 01:11:31.677998: step: 468/529, loss: 0.06417083740234375
2023-01-23 01:11:32.777485: step: 472/529, loss: 0.11251182109117508
2023-01-23 01:11:33.881054: step: 476/529, loss: 0.031088639050722122
2023-01-23 01:11:35.027981: step: 480/529, loss: 0.08974189311265945
2023-01-23 01:11:36.130848: step: 484/529, loss: 0.047586895525455475
2023-01-23 01:11:37.249978: step: 488/529, loss: 0.5900993943214417
2023-01-23 01:11:38.367943: step: 492/529, loss: 0.04580201953649521
2023-01-23 01:11:39.511271: step: 496/529, loss: 0.08017158508300781
2023-01-23 01:11:40.624740: step: 500/529, loss: 0.033750295639038086
2023-01-23 01:11:41.742121: step: 504/529, loss: 0.04029817506670952
2023-01-23 01:11:42.848186: step: 508/529, loss: 0.06806888431310654
2023-01-23 01:11:43.947161: step: 512/529, loss: 0.0344812385737896
2023-01-23 01:11:45.046723: step: 516/529, loss: 0.0668981596827507
2023-01-23 01:11:46.165771: step: 520/529, loss: 0.02187640778720379
2023-01-23 01:11:47.288270: step: 524/529, loss: 0.03815527260303497
2023-01-23 01:11:48.370251: step: 528/529, loss: 0.6970036625862122
2023-01-23 01:11:49.484863: step: 532/529, loss: 0.17776814103126526
2023-01-23 01:11:50.606609: step: 536/529, loss: 0.047922708094120026
2023-01-23 01:11:51.735407: step: 540/529, loss: 0.06548643112182617
2023-01-23 01:11:52.846643: step: 544/529, loss: 0.239887997508049
2023-01-23 01:11:53.955046: step: 548/529, loss: 0.0249770637601614
2023-01-23 01:11:55.044289: step: 552/529, loss: 0.025175761431455612
2023-01-23 01:11:56.137187: step: 556/529, loss: 0.04618034511804581
2023-01-23 01:11:57.250741: step: 560/529, loss: 0.0830078125
2023-01-23 01:11:58.343081: step: 564/529, loss: 0.11975231766700745
2023-01-23 01:11:59.445126: step: 568/529, loss: 0.6255862712860107
2023-01-23 01:12:00.574501: step: 572/529, loss: 0.0041533950716257095
2023-01-23 01:12:01.663889: step: 576/529, loss: 0.06521320343017578
2023-01-23 01:12:02.748537: step: 580/529, loss: 0.027253033593297005
2023-01-23 01:12:03.844941: step: 584/529, loss: 0.043028928339481354
2023-01-23 01:12:05.036441: step: 588/529, loss: 0.08211460709571838
2023-01-23 01:12:06.138723: step: 592/529, loss: 0.08129291236400604
2023-01-23 01:12:07.259445: step: 596/529, loss: 0.040040016174316406
2023-01-23 01:12:08.377099: step: 600/529, loss: 0.05761575698852539
2023-01-23 01:12:09.483806: step: 604/529, loss: 0.1538984328508377
2023-01-23 01:12:10.596394: step: 608/529, loss: 0.10057392716407776
2023-01-23 01:12:11.712630: step: 612/529, loss: 0.10902485251426697
2023-01-23 01:12:12.819384: step: 616/529, loss: 0.09169511497020721
2023-01-23 01:12:13.943053: step: 620/529, loss: 0.18789586424827576
2023-01-23 01:12:15.088412: step: 624/529, loss: 0.02539382129907608
2023-01-23 01:12:16.195567: step: 628/529, loss: 0.17691142857074738
2023-01-23 01:12:17.309306: step: 632/529, loss: 0.10114289075136185
2023-01-23 01:12:18.406909: step: 636/529, loss: 0.08607912063598633
2023-01-23 01:12:19.515230: step: 640/529, loss: 0.03666725382208824
2023-01-23 01:12:20.637783: step: 644/529, loss: 0.11375327408313751
2023-01-23 01:12:21.760184: step: 648/529, loss: 0.031490758061409
2023-01-23 01:12:22.879061: step: 652/529, loss: 0.0033008574973791838
2023-01-23 01:12:23.986570: step: 656/529, loss: 0.0477236770093441
2023-01-23 01:12:25.101133: step: 660/529, loss: 0.004269409459084272
2023-01-23 01:12:26.217097: step: 664/529, loss: 0.06674763560295105
2023-01-23 01:12:27.364457: step: 668/529, loss: 0.030095862224698067
2023-01-23 01:12:28.484535: step: 672/529, loss: 0.02253112755715847
2023-01-23 01:12:29.603684: step: 676/529, loss: 0.01704731024801731
2023-01-23 01:12:30.707059: step: 680/529, loss: 0.05232486501336098
2023-01-23 01:12:31.811225: step: 684/529, loss: 0.07303166389465332
2023-01-23 01:12:32.903036: step: 688/529, loss: 0.22654886543750763
2023-01-23 01:12:34.040166: step: 692/529, loss: 0.17165042459964752
2023-01-23 01:12:35.144725: step: 696/529, loss: 0.08732864260673523
2023-01-23 01:12:36.223775: step: 700/529, loss: 0.0269335750490427
2023-01-23 01:12:37.344829: step: 704/529, loss: 0.12308493256568909
2023-01-23 01:12:38.466059: step: 708/529, loss: 0.059477806091308594
2023-01-23 01:12:39.586519: step: 712/529, loss: 0.01904277689754963
2023-01-23 01:12:40.705693: step: 716/529, loss: 0.03123355098068714
2023-01-23 01:12:41.811862: step: 720/529, loss: 0.0851263552904129
2023-01-23 01:12:42.920521: step: 724/529, loss: 0.2921674847602844
2023-01-23 01:12:44.031108: step: 728/529, loss: 0.15794268250465393
2023-01-23 01:12:45.158124: step: 732/529, loss: 0.04390287399291992
2023-01-23 01:12:46.289677: step: 736/529, loss: 0.09830375015735626
2023-01-23 01:12:47.413420: step: 740/529, loss: 0.028116608038544655
2023-01-23 01:12:48.509574: step: 744/529, loss: 0.025487517938017845
2023-01-23 01:12:49.624107: step: 748/529, loss: 0.07403984665870667
2023-01-23 01:12:50.712349: step: 752/529, loss: 0.0343218669295311
2023-01-23 01:12:51.825227: step: 756/529, loss: 0.1437728852033615
2023-01-23 01:12:52.939831: step: 760/529, loss: 0.13192437589168549
2023-01-23 01:12:54.057324: step: 764/529, loss: 0.026557542383670807
2023-01-23 01:12:55.164768: step: 768/529, loss: 0.05518627539277077
2023-01-23 01:12:56.265927: step: 772/529, loss: 0.006531811319291592
2023-01-23 01:12:57.383198: step: 776/529, loss: 0.05170631781220436
2023-01-23 01:12:58.494175: step: 780/529, loss: 0.0362226739525795
2023-01-23 01:12:59.649952: step: 784/529, loss: 0.18278665840625763
2023-01-23 01:13:00.775980: step: 788/529, loss: 0.0196931604295969
2023-01-23 01:13:01.888317: step: 792/529, loss: 0.06992997974157333
2023-01-23 01:13:02.972069: step: 796/529, loss: 0.2194765955209732
2023-01-23 01:13:04.075049: step: 800/529, loss: 0.03704891353845596
2023-01-23 01:13:05.208648: step: 804/529, loss: 0.06582746654748917
2023-01-23 01:13:06.306139: step: 808/529, loss: 0.05394287407398224
2023-01-23 01:13:07.423592: step: 812/529, loss: 0.03265209123492241
2023-01-23 01:13:08.530326: step: 816/529, loss: 0.10381412506103516
2023-01-23 01:13:09.595462: step: 820/529, loss: 0.02874586544930935
2023-01-23 01:13:10.718724: step: 824/529, loss: 0.005927944090217352
2023-01-23 01:13:11.829810: step: 828/529, loss: 0.049616239964962006
2023-01-23 01:13:12.930663: step: 832/529, loss: 0.32866764068603516
2023-01-23 01:13:14.045871: step: 836/529, loss: 0.013270759955048561
2023-01-23 01:13:15.166689: step: 840/529, loss: 0.1976299285888672
2023-01-23 01:13:16.269246: step: 844/529, loss: 0.5636752843856812
2023-01-23 01:13:17.390845: step: 848/529, loss: 0.08105993270874023
2023-01-23 01:13:18.519780: step: 852/529, loss: 0.1500086784362793
2023-01-23 01:13:19.621178: step: 856/529, loss: 0.03187904506921768
2023-01-23 01:13:20.756523: step: 860/529, loss: 0.03752412647008896
2023-01-23 01:13:21.877950: step: 864/529, loss: 0.07712717354297638
2023-01-23 01:13:22.972312: step: 868/529, loss: 0.009344959631562233
2023-01-23 01:13:24.088759: step: 872/529, loss: 0.03660454973578453
2023-01-23 01:13:25.191312: step: 876/529, loss: 0.09308962523937225
2023-01-23 01:13:26.272172: step: 880/529, loss: 0.08583150804042816
2023-01-23 01:13:27.369059: step: 884/529, loss: 0.05918636545538902
2023-01-23 01:13:28.507737: step: 888/529, loss: 0.04658002778887749
2023-01-23 01:13:29.605515: step: 892/529, loss: 0.09445350617170334
2023-01-23 01:13:30.731607: step: 896/529, loss: 0.0929691344499588
2023-01-23 01:13:31.828838: step: 900/529, loss: 0.014909219928085804
2023-01-23 01:13:32.966899: step: 904/529, loss: 0.03253130987286568
2023-01-23 01:13:34.055519: step: 908/529, loss: 0.07860460877418518
2023-01-23 01:13:35.165079: step: 912/529, loss: 0.030065346509218216
2023-01-23 01:13:36.298882: step: 916/529, loss: 0.16117145121097565
2023-01-23 01:13:37.398580: step: 920/529, loss: 0.011951446533203125
2023-01-23 01:13:38.533622: step: 924/529, loss: 0.0917079895734787
2023-01-23 01:13:39.613788: step: 928/529, loss: 0.005024814512580633
2023-01-23 01:13:40.709740: step: 932/529, loss: 0.10253190994262695
2023-01-23 01:13:41.824190: step: 936/529, loss: 0.17319193482398987
2023-01-23 01:13:42.961054: step: 940/529, loss: 0.04013633728027344
2023-01-23 01:13:44.070695: step: 944/529, loss: 0.07327938079833984
2023-01-23 01:13:45.164610: step: 948/529, loss: 0.007530689239501953
2023-01-23 01:13:46.293359: step: 952/529, loss: 0.07090263813734055
2023-01-23 01:13:47.395766: step: 956/529, loss: 0.07901877909898758
2023-01-23 01:13:48.530818: step: 960/529, loss: 0.0318666473031044
2023-01-23 01:13:49.643718: step: 964/529, loss: 0.05167827755212784
2023-01-23 01:13:50.766085: step: 968/529, loss: 0.04520568996667862
2023-01-23 01:13:51.899590: step: 972/529, loss: 0.16680584847927094
2023-01-23 01:13:53.003932: step: 976/529, loss: 0.17241564393043518
2023-01-23 01:13:54.133382: step: 980/529, loss: 0.060108184814453125
2023-01-23 01:13:55.234383: step: 984/529, loss: 0.21506793797016144
2023-01-23 01:13:56.359777: step: 988/529, loss: 0.05670928955078125
2023-01-23 01:13:57.477396: step: 992/529, loss: 0.06589365005493164
2023-01-23 01:13:58.573381: step: 996/529, loss: 0.029415704309940338
2023-01-23 01:13:59.660588: step: 1000/529, loss: 0.06434173882007599
2023-01-23 01:14:00.811588: step: 1004/529, loss: 0.07568206638097763
2023-01-23 01:14:01.955662: step: 1008/529, loss: 0.028164483606815338
2023-01-23 01:14:03.101747: step: 1012/529, loss: 0.13938426971435547
2023-01-23 01:14:04.214653: step: 1016/529, loss: 0.02475166507065296
2023-01-23 01:14:05.360161: step: 1020/529, loss: 0.4329979121685028
2023-01-23 01:14:06.467452: step: 1024/529, loss: 0.08415546268224716
2023-01-23 01:14:07.581450: step: 1028/529, loss: 0.006848430726677179
2023-01-23 01:14:08.706537: step: 1032/529, loss: 0.002384758088737726
2023-01-23 01:14:09.818205: step: 1036/529, loss: 0.2246207296848297
2023-01-23 01:14:10.923273: step: 1040/529, loss: 0.19224748015403748
2023-01-23 01:14:12.033186: step: 1044/529, loss: 0.020032882690429688
2023-01-23 01:14:13.154109: step: 1048/529, loss: 0.055196452885866165
2023-01-23 01:14:14.266804: step: 1052/529, loss: 0.04472285509109497
2023-01-23 01:14:15.374430: step: 1056/529, loss: 0.1340726912021637
2023-01-23 01:14:16.487018: step: 1060/529, loss: 0.39980563521385193
2023-01-23 01:14:17.595463: step: 1064/529, loss: 0.026726534590125084
2023-01-23 01:14:18.736844: step: 1068/529, loss: 0.01442565955221653
2023-01-23 01:14:19.840324: step: 1072/529, loss: 0.0331222303211689
2023-01-23 01:14:20.947422: step: 1076/529, loss: 1.912477731704712
2023-01-23 01:14:22.068410: step: 1080/529, loss: 0.020315194502472878
2023-01-23 01:14:23.187431: step: 1084/529, loss: 0.1686621606349945
2023-01-23 01:14:24.309986: step: 1088/529, loss: 0.13259124755859375
2023-01-23 01:14:25.444197: step: 1092/529, loss: 0.034163523465394974
2023-01-23 01:14:26.574420: step: 1096/529, loss: 0.5313602685928345
2023-01-23 01:14:27.696065: step: 1100/529, loss: 0.05535001680254936
2023-01-23 01:14:28.803590: step: 1104/529, loss: 0.0796608030796051
2023-01-23 01:14:29.928241: step: 1108/529, loss: 0.017916584387421608
2023-01-23 01:14:31.048493: step: 1112/529, loss: 0.0645868331193924
2023-01-23 01:14:32.173901: step: 1116/529, loss: 0.07953600585460663
2023-01-23 01:14:33.309512: step: 1120/529, loss: 0.030167676508426666
2023-01-23 01:14:34.453567: step: 1124/529, loss: 0.06073722988367081
2023-01-23 01:14:35.550258: step: 1128/529, loss: 0.02266998402774334
2023-01-23 01:14:36.687541: step: 1132/529, loss: 0.09259691834449768
2023-01-23 01:14:37.790687: step: 1136/529, loss: 0.05960436165332794
2023-01-23 01:14:38.928582: step: 1140/529, loss: 0.06338825076818466
2023-01-23 01:14:40.035777: step: 1144/529, loss: 0.0370662696659565
2023-01-23 01:14:41.139181: step: 1148/529, loss: 0.07592706382274628
2023-01-23 01:14:42.274873: step: 1152/529, loss: 0.16204296052455902
2023-01-23 01:14:43.399747: step: 1156/529, loss: 0.044230081140995026
2023-01-23 01:14:44.495631: step: 1160/529, loss: 0.3214394450187683
2023-01-23 01:14:45.613135: step: 1164/529, loss: 0.10289172828197479
2023-01-23 01:14:46.759169: step: 1168/529, loss: 0.4607110023498535
2023-01-23 01:14:47.862869: step: 1172/529, loss: 0.007484054192900658
2023-01-23 01:14:48.988845: step: 1176/529, loss: 0.10458743572235107
2023-01-23 01:14:50.090739: step: 1180/529, loss: 0.07534690201282501
2023-01-23 01:14:51.194813: step: 1184/529, loss: 0.1800021231174469
2023-01-23 01:14:52.285731: step: 1188/529, loss: 0.0186602883040905
2023-01-23 01:14:53.421711: step: 1192/529, loss: 0.10658188164234161
2023-01-23 01:14:54.539980: step: 1196/529, loss: 0.13283920288085938
2023-01-23 01:14:55.645099: step: 1200/529, loss: 0.029497386887669563
2023-01-23 01:14:56.754624: step: 1204/529, loss: 0.13918933272361755
2023-01-23 01:14:57.872947: step: 1208/529, loss: 0.15209394693374634
2023-01-23 01:14:59.003414: step: 1212/529, loss: 0.0947432592511177
2023-01-23 01:15:00.138222: step: 1216/529, loss: 0.007777786813676357
2023-01-23 01:15:01.274359: step: 1220/529, loss: 0.045752912759780884
2023-01-23 01:15:02.389930: step: 1224/529, loss: 0.1949934959411621
2023-01-23 01:15:03.501364: step: 1228/529, loss: 0.42869171500205994
2023-01-23 01:15:04.586584: step: 1232/529, loss: 0.052896786481142044
2023-01-23 01:15:05.699562: step: 1236/529, loss: 0.044683218002319336
2023-01-23 01:15:06.838860: step: 1240/529, loss: 0.3001171052455902
2023-01-23 01:15:07.981111: step: 1244/529, loss: 0.025469493120908737
2023-01-23 01:15:09.067952: step: 1248/529, loss: 0.055413633584976196
2023-01-23 01:15:10.162743: step: 1252/529, loss: 0.002893017139285803
2023-01-23 01:15:11.267202: step: 1256/529, loss: 0.02019209787249565
2023-01-23 01:15:12.373951: step: 1260/529, loss: 0.5539092421531677
2023-01-23 01:15:13.496364: step: 1264/529, loss: 0.07252664864063263
2023-01-23 01:15:14.677008: step: 1268/529, loss: 0.3468475341796875
2023-01-23 01:15:15.760556: step: 1272/529, loss: 0.031056594103574753
2023-01-23 01:15:16.849837: step: 1276/529, loss: 0.015266155824065208
2023-01-23 01:15:17.958002: step: 1280/529, loss: 0.0981055274605751
2023-01-23 01:15:19.039979: step: 1284/529, loss: 0.0528842955827713
2023-01-23 01:15:20.135437: step: 1288/529, loss: 0.06403903663158417
2023-01-23 01:15:21.234559: step: 1292/529, loss: 0.3747352659702301
2023-01-23 01:15:22.362736: step: 1296/529, loss: 0.01789417304098606
2023-01-23 01:15:23.475376: step: 1300/529, loss: 0.06086044758558273
2023-01-23 01:15:24.572609: step: 1304/529, loss: 0.008039974607527256
2023-01-23 01:15:25.671327: step: 1308/529, loss: 0.8727419376373291
2023-01-23 01:15:26.769670: step: 1312/529, loss: 0.05934109911322594
2023-01-23 01:15:27.869943: step: 1316/529, loss: 0.03868570551276207
2023-01-23 01:15:28.969772: step: 1320/529, loss: 0.0005094528314657509
2023-01-23 01:15:30.094320: step: 1324/529, loss: 0.0983087569475174
2023-01-23 01:15:31.228701: step: 1328/529, loss: 0.04227724298834801
2023-01-23 01:15:32.336688: step: 1332/529, loss: 0.0652991309762001
2023-01-23 01:15:33.426105: step: 1336/529, loss: 0.0022724152076989412
2023-01-23 01:15:34.513574: step: 1340/529, loss: 0.19092664122581482
2023-01-23 01:15:35.666108: step: 1344/529, loss: 0.05441854149103165
2023-01-23 01:15:36.772302: step: 1348/529, loss: 0.030962657183408737
2023-01-23 01:15:37.865448: step: 1352/529, loss: 0.06297724694013596
2023-01-23 01:15:38.972578: step: 1356/529, loss: 0.0033655166625976562
2023-01-23 01:15:40.081624: step: 1360/529, loss: 0.02559366449713707
2023-01-23 01:15:41.192229: step: 1364/529, loss: 1.1154946088790894
2023-01-23 01:15:42.295858: step: 1368/529, loss: 0.01449041347950697
2023-01-23 01:15:43.430471: step: 1372/529, loss: 0.20906372368335724
2023-01-23 01:15:44.532164: step: 1376/529, loss: 0.0015120506286621094
2023-01-23 01:15:45.648552: step: 1380/529, loss: 0.15007105469703674
2023-01-23 01:15:46.763012: step: 1384/529, loss: 0.06564774364233017
2023-01-23 01:15:47.866714: step: 1388/529, loss: 0.13308311998844147
2023-01-23 01:15:48.968761: step: 1392/529, loss: 0.10358686745166779
2023-01-23 01:15:50.077438: step: 1396/529, loss: 0.03520488739013672
2023-01-23 01:15:51.230588: step: 1400/529, loss: 0.1521722823381424
2023-01-23 01:15:52.375437: step: 1404/529, loss: 0.08083543926477432
2023-01-23 01:15:53.503718: step: 1408/529, loss: 0.11886010318994522
2023-01-23 01:15:54.600796: step: 1412/529, loss: 0.0628652572631836
2023-01-23 01:15:55.724820: step: 1416/529, loss: 0.15924377739429474
2023-01-23 01:15:56.852142: step: 1420/529, loss: 0.17097461223602295
2023-01-23 01:15:57.956136: step: 1424/529, loss: 0.10538473725318909
2023-01-23 01:15:59.071220: step: 1428/529, loss: 0.045882657170295715
2023-01-23 01:16:00.212864: step: 1432/529, loss: 0.10997632145881653
2023-01-23 01:16:01.339201: step: 1436/529, loss: 0.14286451041698456
2023-01-23 01:16:02.449900: step: 1440/529, loss: 0.03170280531048775
2023-01-23 01:16:03.560358: step: 1444/529, loss: 0.11582193523645401
2023-01-23 01:16:04.695465: step: 1448/529, loss: 0.08530484139919281
2023-01-23 01:16:05.804859: step: 1452/529, loss: 0.035477638244628906
2023-01-23 01:16:06.905771: step: 1456/529, loss: 0.09922733157873154
2023-01-23 01:16:08.009779: step: 1460/529, loss: 0.05142870172858238
2023-01-23 01:16:09.130841: step: 1464/529, loss: 0.11757383495569229
2023-01-23 01:16:10.231449: step: 1468/529, loss: 0.059836193919181824
2023-01-23 01:16:11.356132: step: 1472/529, loss: 0.04173774644732475
2023-01-23 01:16:12.467730: step: 1476/529, loss: 0.06623878329992294
2023-01-23 01:16:13.552850: step: 1480/529, loss: 0.08290930092334747
2023-01-23 01:16:14.708057: step: 1484/529, loss: 0.06116848066449165
2023-01-23 01:16:15.800099: step: 1488/529, loss: 0.05420083925127983
2023-01-23 01:16:16.893694: step: 1492/529, loss: 0.07713265717029572
2023-01-23 01:16:18.003729: step: 1496/529, loss: 0.0663883239030838
2023-01-23 01:16:19.135871: step: 1500/529, loss: 0.09286212921142578
2023-01-23 01:16:20.245200: step: 1504/529, loss: 0.08248787373304367
2023-01-23 01:16:21.386561: step: 1508/529, loss: 0.006128883920609951
2023-01-23 01:16:22.531970: step: 1512/529, loss: 0.03740748390555382
2023-01-23 01:16:23.665750: step: 1516/529, loss: 0.04056992754340172
2023-01-23 01:16:24.803599: step: 1520/529, loss: 0.042075350880622864
2023-01-23 01:16:25.901632: step: 1524/529, loss: 0.09767808765172958
2023-01-23 01:16:27.023637: step: 1528/529, loss: 0.07884716987609863
2023-01-23 01:16:28.132047: step: 1532/529, loss: 0.07051058113574982
2023-01-23 01:16:29.282319: step: 1536/529, loss: 0.05629577860236168
2023-01-23 01:16:30.383821: step: 1540/529, loss: 0.06162138283252716
2023-01-23 01:16:31.495178: step: 1544/529, loss: 0.11712093651294708
2023-01-23 01:16:32.591413: step: 1548/529, loss: 0.05829601362347603
2023-01-23 01:16:33.689410: step: 1552/529, loss: 0.044644832611083984
2023-01-23 01:16:34.796133: step: 1556/529, loss: 0.0030996324494481087
2023-01-23 01:16:35.928824: step: 1560/529, loss: 0.04493984207510948
2023-01-23 01:16:37.059994: step: 1564/529, loss: 0.13707047700881958
2023-01-23 01:16:38.159639: step: 1568/529, loss: 0.060991764068603516
2023-01-23 01:16:39.270688: step: 1572/529, loss: 0.12425756454467773
2023-01-23 01:16:40.368026: step: 1576/529, loss: 0.06178493797779083
2023-01-23 01:16:41.515530: step: 1580/529, loss: 0.06205492466688156
2023-01-23 01:16:42.611737: step: 1584/529, loss: 0.11130929738283157
2023-01-23 01:16:43.743200: step: 1588/529, loss: 0.11500425636768341
2023-01-23 01:16:44.870265: step: 1592/529, loss: 0.16467972099781036
2023-01-23 01:16:45.998888: step: 1596/529, loss: 0.0663367286324501
2023-01-23 01:16:47.117659: step: 1600/529, loss: 0.07432594895362854
2023-01-23 01:16:48.258370: step: 1604/529, loss: 0.006584644317626953
2023-01-23 01:16:49.382367: step: 1608/529, loss: 0.0016658783424645662
2023-01-23 01:16:50.504697: step: 1612/529, loss: 0.3817630708217621
2023-01-23 01:16:51.596592: step: 1616/529, loss: 0.03890247642993927
2023-01-23 01:16:52.693291: step: 1620/529, loss: 0.08566303551197052
2023-01-23 01:16:53.804300: step: 1624/529, loss: 0.41197946667671204
2023-01-23 01:16:54.926126: step: 1628/529, loss: 0.1474742889404297
2023-01-23 01:16:56.057365: step: 1632/529, loss: 0.018197059631347656
2023-01-23 01:16:57.190985: step: 1636/529, loss: 0.11582642048597336
2023-01-23 01:16:58.288062: step: 1640/529, loss: 0.01915464550256729
2023-01-23 01:16:59.442118: step: 1644/529, loss: 0.01825237274169922
2023-01-23 01:17:00.540416: step: 1648/529, loss: 0.07225757092237473
2023-01-23 01:17:01.649620: step: 1652/529, loss: 0.10269680619239807
2023-01-23 01:17:02.759159: step: 1656/529, loss: 0.06576109677553177
2023-01-23 01:17:03.887918: step: 1660/529, loss: 0.15911951661109924
2023-01-23 01:17:05.042603: step: 1664/529, loss: 0.0031041146721690893
2023-01-23 01:17:06.180142: step: 1668/529, loss: 0.13001003861427307
2023-01-23 01:17:07.285307: step: 1672/529, loss: 0.02845921367406845
2023-01-23 01:17:08.397998: step: 1676/529, loss: 0.015304755419492722
2023-01-23 01:17:09.530128: step: 1680/529, loss: 0.17093610763549805
2023-01-23 01:17:10.637779: step: 1684/529, loss: 0.36709803342819214
2023-01-23 01:17:11.763487: step: 1688/529, loss: 0.00982294138520956
2023-01-23 01:17:12.909545: step: 1692/529, loss: 0.08794493973255157
2023-01-23 01:17:14.022027: step: 1696/529, loss: 0.043036460876464844
2023-01-23 01:17:15.129473: step: 1700/529, loss: 0.0265686996281147
2023-01-23 01:17:16.238039: step: 1704/529, loss: 0.296053409576416
2023-01-23 01:17:17.353768: step: 1708/529, loss: 0.037857912480831146
2023-01-23 01:17:18.460891: step: 1712/529, loss: 0.012712288647890091
2023-01-23 01:17:19.573612: step: 1716/529, loss: 0.06006031110882759
2023-01-23 01:17:20.679812: step: 1720/529, loss: 0.15958309173583984
2023-01-23 01:17:21.755541: step: 1724/529, loss: 0.03719472885131836
2023-01-23 01:17:22.872354: step: 1728/529, loss: 0.11248188465833664
2023-01-23 01:17:24.011108: step: 1732/529, loss: 0.04556594043970108
2023-01-23 01:17:25.105483: step: 1736/529, loss: 0.16809554398059845
2023-01-23 01:17:26.184927: step: 1740/529, loss: 0.11940333247184753
2023-01-23 01:17:27.296603: step: 1744/529, loss: 0.008860588073730469
2023-01-23 01:17:28.402648: step: 1748/529, loss: 0.005829811096191406
2023-01-23 01:17:29.515903: step: 1752/529, loss: 0.010744738392531872
2023-01-23 01:17:30.645327: step: 1756/529, loss: 0.15486498177051544
2023-01-23 01:17:31.743255: step: 1760/529, loss: 0.044983863830566406
2023-01-23 01:17:32.847698: step: 1764/529, loss: 0.12944364547729492
2023-01-23 01:17:33.965699: step: 1768/529, loss: 0.010328715667128563
2023-01-23 01:17:35.081622: step: 1772/529, loss: 0.08861346542835236
2023-01-23 01:17:36.208085: step: 1776/529, loss: 0.10198240727186203
2023-01-23 01:17:37.333618: step: 1780/529, loss: 0.10300026088953018
2023-01-23 01:17:38.473058: step: 1784/529, loss: 0.018926048651337624
2023-01-23 01:17:39.590038: step: 1788/529, loss: 0.0031180144287645817
2023-01-23 01:17:40.694916: step: 1792/529, loss: 0.09198741614818573
2023-01-23 01:17:41.802940: step: 1796/529, loss: 0.500396728515625
2023-01-23 01:17:42.923084: step: 1800/529, loss: 0.015450287610292435
2023-01-23 01:17:44.042340: step: 1804/529, loss: 0.12958678603172302
2023-01-23 01:17:45.138643: step: 1808/529, loss: 0.06736544519662857
2023-01-23 01:17:46.271370: step: 1812/529, loss: 0.06629429012537003
2023-01-23 01:17:47.364064: step: 1816/529, loss: 0.13922032713890076
2023-01-23 01:17:48.504440: step: 1820/529, loss: 0.2159046232700348
2023-01-23 01:17:49.619501: step: 1824/529, loss: 0.06676407158374786
2023-01-23 01:17:50.705603: step: 1828/529, loss: 0.5868772864341736
2023-01-23 01:17:51.798092: step: 1832/529, loss: 0.02198047749698162
2023-01-23 01:17:52.905896: step: 1836/529, loss: 0.11488499492406845
2023-01-23 01:17:54.010044: step: 1840/529, loss: 0.06417850404977798
2023-01-23 01:17:55.126178: step: 1844/529, loss: 0.017812252044677734
2023-01-23 01:17:56.223092: step: 1848/529, loss: 0.19078870117664337
2023-01-23 01:17:57.357800: step: 1852/529, loss: 0.20754380524158478
2023-01-23 01:17:58.442983: step: 1856/529, loss: 0.03929634019732475
2023-01-23 01:17:59.541829: step: 1860/529, loss: 0.022656727582216263
2023-01-23 01:18:00.674228: step: 1864/529, loss: 0.06775032728910446
2023-01-23 01:18:01.780004: step: 1868/529, loss: 0.05289635807275772
2023-01-23 01:18:02.886257: step: 1872/529, loss: 0.06041469797492027
2023-01-23 01:18:03.998475: step: 1876/529, loss: 0.05957479774951935
2023-01-23 01:18:05.092002: step: 1880/529, loss: 0.0886511355638504
2023-01-23 01:18:06.199087: step: 1884/529, loss: 0.184962198138237
2023-01-23 01:18:07.303187: step: 1888/529, loss: 0.07012825459241867
2023-01-23 01:18:08.442076: step: 1892/529, loss: 0.0929986983537674
2023-01-23 01:18:09.557190: step: 1896/529, loss: 0.04324252903461456
2023-01-23 01:18:10.662410: step: 1900/529, loss: 0.15844345092773438
2023-01-23 01:18:11.765660: step: 1904/529, loss: 0.10504860430955887
2023-01-23 01:18:12.864434: step: 1908/529, loss: 0.03284740447998047
2023-01-23 01:18:13.998349: step: 1912/529, loss: 0.14668092131614685
2023-01-23 01:18:15.116662: step: 1916/529, loss: 0.010412168689072132
2023-01-23 01:18:16.257282: step: 1920/529, loss: 0.0695522204041481
2023-01-23 01:18:17.375003: step: 1924/529, loss: 0.12053041905164719
2023-01-23 01:18:18.491343: step: 1928/529, loss: 0.04767570272088051
2023-01-23 01:18:19.593176: step: 1932/529, loss: 0.044094182550907135
2023-01-23 01:18:20.712849: step: 1936/529, loss: 0.31926095485687256
2023-01-23 01:18:21.829631: step: 1940/529, loss: 0.05498848110437393
2023-01-23 01:18:22.935280: step: 1944/529, loss: 0.02191934548318386
2023-01-23 01:18:24.032065: step: 1948/529, loss: 1.19880211353302
2023-01-23 01:18:25.148344: step: 1952/529, loss: 0.02490520477294922
2023-01-23 01:18:26.276443: step: 1956/529, loss: 0.04433279111981392
2023-01-23 01:18:27.398911: step: 1960/529, loss: 0.45662468671798706
2023-01-23 01:18:28.488636: step: 1964/529, loss: 0.04059944301843643
2023-01-23 01:18:29.625166: step: 1968/529, loss: 0.027599716559052467
2023-01-23 01:18:30.741664: step: 1972/529, loss: 0.04951610416173935
2023-01-23 01:18:31.837765: step: 1976/529, loss: 0.13329724967479706
2023-01-23 01:18:32.936309: step: 1980/529, loss: 0.02415151707828045
2023-01-23 01:18:34.054013: step: 1984/529, loss: 0.03460407257080078
2023-01-23 01:18:35.171909: step: 1988/529, loss: 0.09172935783863068
2023-01-23 01:18:36.273133: step: 1992/529, loss: 0.0057312012650072575
2023-01-23 01:18:37.397066: step: 1996/529, loss: 0.10153666138648987
2023-01-23 01:18:38.499547: step: 2000/529, loss: 0.04121112823486328
2023-01-23 01:18:39.612646: step: 2004/529, loss: 0.01641373708844185
2023-01-23 01:18:40.727285: step: 2008/529, loss: 0.027023935690522194
2023-01-23 01:18:41.840790: step: 2012/529, loss: 0.0180834773927927
2023-01-23 01:18:42.911248: step: 2016/529, loss: 0.05376157909631729
2023-01-23 01:18:44.071713: step: 2020/529, loss: 0.3516879081726074
2023-01-23 01:18:45.171497: step: 2024/529, loss: 0.11295566707849503
2023-01-23 01:18:46.286361: step: 2028/529, loss: 0.07551927864551544
2023-01-23 01:18:47.422785: step: 2032/529, loss: 0.586672306060791
2023-01-23 01:18:48.542086: step: 2036/529, loss: 0.042920973151922226
2023-01-23 01:18:49.671117: step: 2040/529, loss: 0.03974013403058052
2023-01-23 01:18:50.766791: step: 2044/529, loss: 0.0026085854042321444
2023-01-23 01:18:51.894573: step: 2048/529, loss: 0.05784473568201065
2023-01-23 01:18:52.992773: step: 2052/529, loss: 0.04035158455371857
2023-01-23 01:18:54.104405: step: 2056/529, loss: 0.16087280213832855
2023-01-23 01:18:55.225856: step: 2060/529, loss: 0.05341053009033203
2023-01-23 01:18:56.320948: step: 2064/529, loss: 0.024414371699094772
2023-01-23 01:18:57.417311: step: 2068/529, loss: 0.09351043403148651
2023-01-23 01:18:58.536213: step: 2072/529, loss: 0.017180848866701126
2023-01-23 01:18:59.662333: step: 2076/529, loss: 0.06118660047650337
2023-01-23 01:19:00.812629: step: 2080/529, loss: 0.03235488012433052
2023-01-23 01:19:01.924057: step: 2084/529, loss: 0.1415139138698578
2023-01-23 01:19:03.023688: step: 2088/529, loss: 0.010071372613310814
2023-01-23 01:19:04.157928: step: 2092/529, loss: 0.13087940216064453
2023-01-23 01:19:05.254570: step: 2096/529, loss: 0.0761045515537262
2023-01-23 01:19:06.364424: step: 2100/529, loss: 0.09669361263513565
2023-01-23 01:19:07.483369: step: 2104/529, loss: 0.023715972900390625
2023-01-23 01:19:08.576966: step: 2108/529, loss: 0.03133287653326988
2023-01-23 01:19:09.701751: step: 2112/529, loss: 0.053655434399843216
2023-01-23 01:19:10.823685: step: 2116/529, loss: 0.051026277244091034
==================================================
Loss: 0.097
--------------------
Dev: {'event': {'p': 0.6004119464469619, 'r': 0.7762982689747004, 'f1': 0.6771196283391405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6153512575888985, 'r': 0.8007900677200903, 'f1': 0.6959293771456597}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5454545454545454, 'r': 0.8888888888888888, 'f1': 0.676056338028169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.5454545454545454, 'r': 0.5714285714285714, 'f1': 0.5581395348837208}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
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': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:19:50.974540: step: 4/529, loss: 0.044892121106386185
2023-01-23 01:19:52.069338: step: 8/529, loss: 0.0625268965959549
2023-01-23 01:19:53.165026: step: 12/529, loss: 0.03142843395471573
2023-01-23 01:19:54.289267: step: 16/529, loss: 0.18187494575977325
2023-01-23 01:19:55.392377: step: 20/529, loss: 0.11568813025951385
2023-01-23 01:19:56.503804: step: 24/529, loss: 0.04502449184656143
2023-01-23 01:19:57.614023: step: 28/529, loss: 0.0923745185136795
2023-01-23 01:19:58.710275: step: 32/529, loss: 0.03228185325860977
2023-01-23 01:19:59.808045: step: 36/529, loss: 0.0037368773482739925
2023-01-23 01:20:00.955817: step: 40/529, loss: 0.0487639456987381
2023-01-23 01:20:02.075956: step: 44/529, loss: 0.01682748831808567
2023-01-23 01:20:03.168456: step: 48/529, loss: 0.01993861235678196
2023-01-23 01:20:04.310759: step: 52/529, loss: 0.10721054673194885
2023-01-23 01:20:05.429759: step: 56/529, loss: 0.03785209730267525
2023-01-23 01:20:06.539553: step: 60/529, loss: 0.04608885943889618
2023-01-23 01:20:07.645486: step: 64/529, loss: 0.0338287353515625
2023-01-23 01:20:08.746151: step: 68/529, loss: 0.012132120318710804
2023-01-23 01:20:09.824732: step: 72/529, loss: 0.004388713743537664
2023-01-23 01:20:10.963600: step: 76/529, loss: 0.0578186996281147
2023-01-23 01:20:12.066458: step: 80/529, loss: 0.03146343305706978
2023-01-23 01:20:13.157500: step: 84/529, loss: 0.007626248057931662
2023-01-23 01:20:14.261876: step: 88/529, loss: 0.034311581403017044
2023-01-23 01:20:15.386230: step: 92/529, loss: 0.1295042484998703
2023-01-23 01:20:16.500284: step: 96/529, loss: 0.017191410064697266
2023-01-23 01:20:17.633747: step: 100/529, loss: 0.05328216403722763
2023-01-23 01:20:18.755577: step: 104/529, loss: 0.2050791233778
2023-01-23 01:20:19.901128: step: 108/529, loss: 0.015751982107758522
2023-01-23 01:20:21.018229: step: 112/529, loss: 0.18110105395317078
2023-01-23 01:20:22.127055: step: 116/529, loss: 0.08174113929271698
2023-01-23 01:20:23.244640: step: 120/529, loss: 0.12513476610183716
2023-01-23 01:20:24.362644: step: 124/529, loss: 0.022868728265166283
2023-01-23 01:20:25.490225: step: 128/529, loss: 0.052204132080078125
2023-01-23 01:20:26.573817: step: 132/529, loss: 0.008044051937758923
2023-01-23 01:20:27.690152: step: 136/529, loss: 0.024648284539580345
2023-01-23 01:20:28.806730: step: 140/529, loss: 0.01880931854248047
2023-01-23 01:20:29.937455: step: 144/529, loss: 0.5584419965744019
2023-01-23 01:20:31.050550: step: 148/529, loss: 0.04732847213745117
2023-01-23 01:20:32.152123: step: 152/529, loss: 0.02764282189309597
2023-01-23 01:20:33.258935: step: 156/529, loss: 0.05077533796429634
2023-01-23 01:20:34.390752: step: 160/529, loss: 0.025649739429354668
2023-01-23 01:20:35.507245: step: 164/529, loss: 0.09128904342651367
2023-01-23 01:20:36.614285: step: 168/529, loss: 0.020452309399843216
2023-01-23 01:20:37.719478: step: 172/529, loss: 0.0022405623458325863
2023-01-23 01:20:38.838824: step: 176/529, loss: 0.003482246305793524
2023-01-23 01:20:39.938804: step: 180/529, loss: 0.026781463995575905
2023-01-23 01:20:41.054629: step: 184/529, loss: 0.017145443707704544
2023-01-23 01:20:42.161174: step: 188/529, loss: 0.050605013966560364
2023-01-23 01:20:43.283526: step: 192/529, loss: 0.056218527257442474
2023-01-23 01:20:44.390395: step: 196/529, loss: 0.08923760056495667
2023-01-23 01:20:45.538286: step: 200/529, loss: 0.22632159292697906
2023-01-23 01:20:46.637165: step: 204/529, loss: 0.013107681646943092
2023-01-23 01:20:47.743442: step: 208/529, loss: 0.030262090265750885
2023-01-23 01:20:48.861912: step: 212/529, loss: 0.010067367926239967
2023-01-23 01:20:49.987692: step: 216/529, loss: 0.040558528155088425
2023-01-23 01:20:51.095661: step: 220/529, loss: 0.09151677787303925
2023-01-23 01:20:52.199712: step: 224/529, loss: 0.016289377585053444
2023-01-23 01:20:53.324680: step: 228/529, loss: 0.07078304141759872
2023-01-23 01:20:54.430995: step: 232/529, loss: 0.032830189913511276
2023-01-23 01:20:55.524931: step: 236/529, loss: 0.1679474413394928
2023-01-23 01:20:56.641246: step: 240/529, loss: 0.01542511023581028
2023-01-23 01:20:57.746996: step: 244/529, loss: 0.05822563171386719
2023-01-23 01:20:58.836191: step: 248/529, loss: 0.0029464722611010075
2023-01-23 01:20:59.968322: step: 252/529, loss: 0.07984809577465057
2023-01-23 01:21:01.094332: step: 256/529, loss: 0.04578285291790962
2023-01-23 01:21:02.198233: step: 260/529, loss: 0.08597288280725479
2023-01-23 01:21:03.330170: step: 264/529, loss: 0.014625740237534046
2023-01-23 01:21:04.457200: step: 268/529, loss: 0.08937425911426544
2023-01-23 01:21:05.573081: step: 272/529, loss: 0.046263791620731354
2023-01-23 01:21:06.670275: step: 276/529, loss: 0.005494880955666304
2023-01-23 01:21:07.753922: step: 280/529, loss: 0.030833005905151367
2023-01-23 01:21:08.866968: step: 284/529, loss: 0.1821443736553192
2023-01-23 01:21:09.975210: step: 288/529, loss: 0.07623839378356934
2023-01-23 01:21:11.093329: step: 292/529, loss: 0.09481838345527649
2023-01-23 01:21:12.188744: step: 296/529, loss: 0.013539028353989124
2023-01-23 01:21:13.315994: step: 300/529, loss: 0.028644908219575882
2023-01-23 01:21:14.405517: step: 304/529, loss: 0.014699173159897327
2023-01-23 01:21:15.502689: step: 308/529, loss: 0.021160125732421875
2023-01-23 01:21:16.604501: step: 312/529, loss: 0.4187335968017578
2023-01-23 01:21:17.718814: step: 316/529, loss: 0.02988738939166069
2023-01-23 01:21:18.833024: step: 320/529, loss: 0.02997131273150444
2023-01-23 01:21:19.969935: step: 324/529, loss: 0.1314006745815277
2023-01-23 01:21:21.093704: step: 328/529, loss: 0.020139073953032494
2023-01-23 01:21:22.216987: step: 332/529, loss: 0.3240695595741272
2023-01-23 01:21:23.332866: step: 336/529, loss: 0.015273381024599075
2023-01-23 01:21:24.447055: step: 340/529, loss: 0.22114935517311096
2023-01-23 01:21:25.563185: step: 344/529, loss: 0.0349545031785965
2023-01-23 01:21:26.672413: step: 348/529, loss: 0.019772624596953392
2023-01-23 01:21:27.756460: step: 352/529, loss: 0.09770698845386505
2023-01-23 01:21:28.846777: step: 356/529, loss: 0.11316695809364319
2023-01-23 01:21:29.938205: step: 360/529, loss: 0.05522461235523224
2023-01-23 01:21:31.050466: step: 364/529, loss: 0.044603198766708374
2023-01-23 01:21:32.137123: step: 368/529, loss: 0.020693683996796608
2023-01-23 01:21:33.306519: step: 372/529, loss: 0.03904552757740021
2023-01-23 01:21:34.421186: step: 376/529, loss: 0.03238171339035034
2023-01-23 01:21:35.522591: step: 380/529, loss: 0.07206100970506668
2023-01-23 01:21:36.632834: step: 384/529, loss: 0.03099827840924263
2023-01-23 01:21:37.753644: step: 388/529, loss: 0.1448509693145752
2023-01-23 01:21:38.851988: step: 392/529, loss: 0.0327390693128109
2023-01-23 01:21:39.951659: step: 396/529, loss: 0.0008177757263183594
2023-01-23 01:21:41.069755: step: 400/529, loss: 0.003954553510993719
2023-01-23 01:21:42.182316: step: 404/529, loss: 0.1691402643918991
2023-01-23 01:21:43.284540: step: 408/529, loss: 0.014127827249467373
2023-01-23 01:21:44.393150: step: 412/529, loss: 0.03034992329776287
2023-01-23 01:21:45.540136: step: 416/529, loss: 0.04700450971722603
2023-01-23 01:21:46.656267: step: 420/529, loss: 0.04196205362677574
2023-01-23 01:21:47.785355: step: 424/529, loss: 0.07173824310302734
2023-01-23 01:21:48.911709: step: 428/529, loss: 0.051961325109004974
2023-01-23 01:21:50.023805: step: 432/529, loss: 0.032865334302186966
2023-01-23 01:21:51.177366: step: 436/529, loss: 0.09171953052282333
2023-01-23 01:21:52.293256: step: 440/529, loss: 0.09884472191333771
2023-01-23 01:21:53.449633: step: 444/529, loss: 0.062410928308963776
2023-01-23 01:21:54.550817: step: 448/529, loss: 0.009027529507875443
2023-01-23 01:21:55.648978: step: 452/529, loss: 0.056571390479803085
2023-01-23 01:21:56.759827: step: 456/529, loss: 0.023335743695497513
2023-01-23 01:21:57.901345: step: 460/529, loss: 0.03396587446331978
2023-01-23 01:21:59.027184: step: 464/529, loss: 0.022298144176602364
2023-01-23 01:22:00.134158: step: 468/529, loss: 0.12664107978343964
2023-01-23 01:22:01.254540: step: 472/529, loss: 0.047626398503780365
2023-01-23 01:22:02.359547: step: 476/529, loss: 0.025447560474276543
2023-01-23 01:22:03.467211: step: 480/529, loss: 0.10914306342601776
2023-01-23 01:22:04.571220: step: 484/529, loss: 0.05278158187866211
2023-01-23 01:22:05.676403: step: 488/529, loss: 0.0972658172249794
2023-01-23 01:22:06.766077: step: 492/529, loss: 0.031143857166171074
2023-01-23 01:22:07.831977: step: 496/529, loss: 0.10382290184497833
2023-01-23 01:22:08.935165: step: 500/529, loss: 0.004127121064811945
2023-01-23 01:22:10.055428: step: 504/529, loss: 0.04012127220630646
2023-01-23 01:22:11.161933: step: 508/529, loss: 0.03874502331018448
2023-01-23 01:22:12.322875: step: 512/529, loss: 0.03890252113342285
2023-01-23 01:22:13.422016: step: 516/529, loss: 0.09594850242137909
2023-01-23 01:22:14.534891: step: 520/529, loss: 0.049819089472293854
2023-01-23 01:22:15.697539: step: 524/529, loss: 0.01969614066183567
2023-01-23 01:22:16.796278: step: 528/529, loss: 0.027335453778505325
2023-01-23 01:22:17.903593: step: 532/529, loss: 0.021639443933963776
2023-01-23 01:22:19.010311: step: 536/529, loss: 0.050621893256902695
2023-01-23 01:22:20.139751: step: 540/529, loss: 0.050080299377441406
2023-01-23 01:22:21.259940: step: 544/529, loss: 0.0535762794315815
2023-01-23 01:22:22.384515: step: 548/529, loss: 0.11981220543384552
2023-01-23 01:22:23.525801: step: 552/529, loss: 0.09423381090164185
2023-01-23 01:22:24.644074: step: 556/529, loss: 0.0670996680855751
2023-01-23 01:22:25.747931: step: 560/529, loss: 0.10288429260253906
2023-01-23 01:22:26.858494: step: 564/529, loss: 0.06350155174732208
2023-01-23 01:22:27.968624: step: 568/529, loss: 0.10281587392091751
2023-01-23 01:22:29.068217: step: 572/529, loss: 0.12779581546783447
2023-01-23 01:22:30.192416: step: 576/529, loss: 0.08085943758487701
2023-01-23 01:22:31.301006: step: 580/529, loss: 0.09658604115247726
2023-01-23 01:22:32.406819: step: 584/529, loss: 0.008464241400361061
2023-01-23 01:22:33.507799: step: 588/529, loss: 0.21583539247512817
2023-01-23 01:22:34.639423: step: 592/529, loss: 0.039789870381355286
2023-01-23 01:22:35.767398: step: 596/529, loss: 0.07090745121240616
2023-01-23 01:22:36.879925: step: 600/529, loss: 0.09214477241039276
2023-01-23 01:22:37.995435: step: 604/529, loss: 0.005883693695068359
2023-01-23 01:22:39.130345: step: 608/529, loss: 0.03277955204248428
2023-01-23 01:22:40.249045: step: 612/529, loss: 0.04826831817626953
2023-01-23 01:22:41.385122: step: 616/529, loss: 0.028658676892518997
2023-01-23 01:22:42.494317: step: 620/529, loss: 0.030988717451691628
2023-01-23 01:22:43.593721: step: 624/529, loss: 0.011056710034608841
2023-01-23 01:22:44.717373: step: 628/529, loss: 0.014819574542343616
2023-01-23 01:22:45.856624: step: 632/529, loss: 0.047968581318855286
2023-01-23 01:22:46.973461: step: 636/529, loss: 0.01238107681274414
2023-01-23 01:22:48.092840: step: 640/529, loss: 0.06460742652416229
2023-01-23 01:22:49.237655: step: 644/529, loss: 0.0994729995727539
2023-01-23 01:22:50.336542: step: 648/529, loss: 0.04190712049603462
2023-01-23 01:22:51.460672: step: 652/529, loss: 0.02900867536664009
2023-01-23 01:22:52.562805: step: 656/529, loss: 0.07848282158374786
2023-01-23 01:22:53.690843: step: 660/529, loss: 0.009172726422548294
2023-01-23 01:22:54.794784: step: 664/529, loss: 0.04128170385956764
2023-01-23 01:22:55.943948: step: 668/529, loss: 0.019165707752108574
2023-01-23 01:22:57.056794: step: 672/529, loss: 0.11756525933742523
2023-01-23 01:22:58.172529: step: 676/529, loss: 0.06627778708934784
2023-01-23 01:22:59.274936: step: 680/529, loss: 0.24567127227783203
2023-01-23 01:23:00.377319: step: 684/529, loss: 0.05248670652508736
2023-01-23 01:23:01.492347: step: 688/529, loss: 0.07553596794605255
2023-01-23 01:23:02.608777: step: 692/529, loss: 0.08473311364650726
2023-01-23 01:23:03.695106: step: 696/529, loss: 0.04260959476232529
2023-01-23 01:23:04.776543: step: 700/529, loss: 0.07594089210033417
2023-01-23 01:23:05.875311: step: 704/529, loss: 0.01995544508099556
2023-01-23 01:23:06.999769: step: 708/529, loss: 0.11991729587316513
2023-01-23 01:23:08.085870: step: 712/529, loss: 0.03400077670812607
2023-01-23 01:23:09.199410: step: 716/529, loss: 0.03663177415728569
2023-01-23 01:23:10.308554: step: 720/529, loss: 0.09200859069824219
2023-01-23 01:23:11.421591: step: 724/529, loss: 0.10756722092628479
2023-01-23 01:23:12.521588: step: 728/529, loss: 0.06871548295021057
2023-01-23 01:23:13.623443: step: 732/529, loss: 0.16469335556030273
2023-01-23 01:23:14.718627: step: 736/529, loss: 0.08558855205774307
2023-01-23 01:23:15.850572: step: 740/529, loss: 0.09734473377466202
2023-01-23 01:23:16.961879: step: 744/529, loss: 0.0015523910988122225
2023-01-23 01:23:18.082652: step: 748/529, loss: 0.1339588165283203
2023-01-23 01:23:19.174552: step: 752/529, loss: 0.01891326904296875
2023-01-23 01:23:20.284067: step: 756/529, loss: 0.22935573756694794
2023-01-23 01:23:21.384210: step: 760/529, loss: 0.03181047737598419
2023-01-23 01:23:22.501763: step: 764/529, loss: 0.06916847825050354
2023-01-23 01:23:23.646578: step: 768/529, loss: 0.15863971412181854
2023-01-23 01:23:24.780751: step: 772/529, loss: 0.019536782056093216
2023-01-23 01:23:25.893406: step: 776/529, loss: 0.04048867151141167
2023-01-23 01:23:26.995484: step: 780/529, loss: 0.017746353521943092
2023-01-23 01:23:28.109196: step: 784/529, loss: 0.0579533576965332
2023-01-23 01:23:29.209802: step: 788/529, loss: 0.006070256233215332
2023-01-23 01:23:30.324645: step: 792/529, loss: 0.003806042717769742
2023-01-23 01:23:31.404614: step: 796/529, loss: 0.044641975313425064
2023-01-23 01:23:32.511369: step: 800/529, loss: 0.062311507761478424
2023-01-23 01:23:33.605673: step: 804/529, loss: 0.004421234130859375
2023-01-23 01:23:34.698046: step: 808/529, loss: 0.10612402111291885
2023-01-23 01:23:35.817039: step: 812/529, loss: 0.010794401168823242
2023-01-23 01:23:36.897879: step: 816/529, loss: 0.32740622758865356
2023-01-23 01:23:37.997477: step: 820/529, loss: 0.015049362555146217
2023-01-23 01:23:39.124797: step: 824/529, loss: 0.060502246022224426
2023-01-23 01:23:40.264023: step: 828/529, loss: 0.013302040286362171
2023-01-23 01:23:41.397505: step: 832/529, loss: 0.010504627600312233
2023-01-23 01:23:42.513685: step: 836/529, loss: 0.049408912658691406
2023-01-23 01:23:43.634172: step: 840/529, loss: 0.06428012996912003
2023-01-23 01:23:44.714792: step: 844/529, loss: 0.11536665260791779
2023-01-23 01:23:45.816882: step: 848/529, loss: 0.04080810397863388
2023-01-23 01:23:46.903619: step: 852/529, loss: 0.06284475326538086
2023-01-23 01:23:47.992891: step: 856/529, loss: 0.03513374179601669
2023-01-23 01:23:49.098911: step: 860/529, loss: 0.014374161139130592
2023-01-23 01:23:50.252939: step: 864/529, loss: 0.00845341756939888
2023-01-23 01:23:51.338988: step: 868/529, loss: 0.011118650436401367
2023-01-23 01:23:52.474905: step: 872/529, loss: 0.08096780627965927
2023-01-23 01:23:53.582066: step: 876/529, loss: 0.09415154904127121
2023-01-23 01:23:54.682740: step: 880/529, loss: 0.0038011549040675163
2023-01-23 01:23:55.772434: step: 884/529, loss: 0.043622732162475586
2023-01-23 01:23:56.856256: step: 888/529, loss: 0.02371211163699627
2023-01-23 01:23:58.009839: step: 892/529, loss: 0.11620187759399414
2023-01-23 01:23:59.112277: step: 896/529, loss: 0.010068322531878948
2023-01-23 01:24:00.197163: step: 900/529, loss: 0.0750301331281662
2023-01-23 01:24:01.307329: step: 904/529, loss: 0.14115962386131287
2023-01-23 01:24:02.450851: step: 908/529, loss: 0.027680015191435814
2023-01-23 01:24:03.579723: step: 912/529, loss: 0.055596206337213516
2023-01-23 01:24:04.667883: step: 916/529, loss: 0.059714317321777344
2023-01-23 01:24:05.782963: step: 920/529, loss: 0.046524617820978165
2023-01-23 01:24:06.904165: step: 924/529, loss: 0.07550687342882156
2023-01-23 01:24:08.046226: step: 928/529, loss: 0.05579419061541557
2023-01-23 01:24:09.145893: step: 932/529, loss: 0.024288274347782135
2023-01-23 01:24:10.275497: step: 936/529, loss: 0.035298872739076614
2023-01-23 01:24:11.393162: step: 940/529, loss: 0.01730179786682129
2023-01-23 01:24:12.524402: step: 944/529, loss: 0.018743038177490234
2023-01-23 01:24:13.665942: step: 948/529, loss: 0.06931991875171661
2023-01-23 01:24:14.776725: step: 952/529, loss: 0.10813484340906143
2023-01-23 01:24:15.880862: step: 956/529, loss: 0.2916943430900574
2023-01-23 01:24:16.982791: step: 960/529, loss: 0.0444183349609375
2023-01-23 01:24:18.113910: step: 964/529, loss: 0.005892562679946423
2023-01-23 01:24:19.197438: step: 968/529, loss: 0.0025506019592285156
2023-01-23 01:24:20.323516: step: 972/529, loss: 0.011970138177275658
2023-01-23 01:24:21.424159: step: 976/529, loss: 0.08323879539966583
2023-01-23 01:24:22.512823: step: 980/529, loss: 0.02632913738489151
2023-01-23 01:24:23.636402: step: 984/529, loss: 0.0189119353890419
2023-01-23 01:24:24.745816: step: 988/529, loss: 0.04235429689288139
2023-01-23 01:24:25.867995: step: 992/529, loss: 0.0024054530076682568
2023-01-23 01:24:26.962413: step: 996/529, loss: 0.04512377083301544
2023-01-23 01:24:28.078557: step: 1000/529, loss: 0.11528539657592773
2023-01-23 01:24:29.176940: step: 1004/529, loss: 0.009076309390366077
2023-01-23 01:24:30.271094: step: 1008/529, loss: 0.05923214182257652
2023-01-23 01:24:31.386671: step: 1012/529, loss: 0.04387540742754936
2023-01-23 01:24:32.484856: step: 1016/529, loss: 0.06292214244604111
2023-01-23 01:24:33.602576: step: 1020/529, loss: 0.037033937871456146
2023-01-23 01:24:34.725154: step: 1024/529, loss: 0.006282615941017866
2023-01-23 01:24:35.843211: step: 1028/529, loss: 0.10495968163013458
2023-01-23 01:24:36.957041: step: 1032/529, loss: 0.020461272448301315
2023-01-23 01:24:38.067526: step: 1036/529, loss: 0.02928142622113228
2023-01-23 01:24:39.152491: step: 1040/529, loss: 0.039076901972293854
2023-01-23 01:24:40.286650: step: 1044/529, loss: 1.8212745189666748
2023-01-23 01:24:41.426726: step: 1048/529, loss: 0.04300975799560547
2023-01-23 01:24:42.569541: step: 1052/529, loss: 0.08516388386487961
2023-01-23 01:24:43.695513: step: 1056/529, loss: 0.07014532387256622
2023-01-23 01:24:44.850698: step: 1060/529, loss: 0.02226734161376953
2023-01-23 01:24:45.998856: step: 1064/529, loss: 0.4326225817203522
2023-01-23 01:24:47.141672: step: 1068/529, loss: 0.4570654332637787
2023-01-23 01:24:48.279330: step: 1072/529, loss: 0.010837078094482422
2023-01-23 01:24:49.365330: step: 1076/529, loss: 0.03327608108520508
2023-01-23 01:24:50.515138: step: 1080/529, loss: 0.4362497329711914
2023-01-23 01:24:51.622578: step: 1084/529, loss: 0.016222380101680756
2023-01-23 01:24:52.741574: step: 1088/529, loss: 0.11577854305505753
2023-01-23 01:24:53.866500: step: 1092/529, loss: 0.08445930480957031
2023-01-23 01:24:54.984316: step: 1096/529, loss: 0.023132704198360443
2023-01-23 01:24:56.099271: step: 1100/529, loss: 0.012119198217988014
2023-01-23 01:24:57.244464: step: 1104/529, loss: 0.04031524434685707
2023-01-23 01:24:58.386806: step: 1108/529, loss: 0.07496533542871475
2023-01-23 01:24:59.520904: step: 1112/529, loss: 0.016175080090761185
2023-01-23 01:25:00.648715: step: 1116/529, loss: 0.007507038302719593
2023-01-23 01:25:01.769748: step: 1120/529, loss: 0.057738494127988815
2023-01-23 01:25:02.888346: step: 1124/529, loss: 0.07852659374475479
2023-01-23 01:25:04.001044: step: 1128/529, loss: 0.06139850616455078
2023-01-23 01:25:05.104398: step: 1132/529, loss: 0.08248867839574814
2023-01-23 01:25:06.197517: step: 1136/529, loss: 0.02164936065673828
2023-01-23 01:25:07.283947: step: 1140/529, loss: 0.008149909786880016
2023-01-23 01:25:08.419979: step: 1144/529, loss: 0.04141101986169815
2023-01-23 01:25:09.530421: step: 1148/529, loss: 0.044330596923828125
2023-01-23 01:25:10.645731: step: 1152/529, loss: 0.08643980324268341
2023-01-23 01:25:11.776259: step: 1156/529, loss: 0.05093735456466675
2023-01-23 01:25:12.885943: step: 1160/529, loss: 0.08762378990650177
2023-01-23 01:25:13.980320: step: 1164/529, loss: 0.029524803161621094
2023-01-23 01:25:15.138366: step: 1168/529, loss: 0.0019824982155114412
2023-01-23 01:25:16.236827: step: 1172/529, loss: 0.1028904914855957
2023-01-23 01:25:17.368539: step: 1176/529, loss: 0.034407127648591995
2023-01-23 01:25:18.453323: step: 1180/529, loss: 0.013445568270981312
2023-01-23 01:25:19.574748: step: 1184/529, loss: 0.059815600514411926
2023-01-23 01:25:20.672780: step: 1188/529, loss: 0.13818645477294922
2023-01-23 01:25:21.817658: step: 1192/529, loss: 0.02448730543255806
2023-01-23 01:25:22.935443: step: 1196/529, loss: 0.04031181335449219
2023-01-23 01:25:24.030691: step: 1200/529, loss: 0.06374092400074005
2023-01-23 01:25:25.122551: step: 1204/529, loss: 0.07150955498218536
2023-01-23 01:25:26.273134: step: 1208/529, loss: 0.21542797982692719
2023-01-23 01:25:27.368021: step: 1212/529, loss: 0.04838629066944122
2023-01-23 01:25:28.464636: step: 1216/529, loss: 0.0038162232376635075
2023-01-23 01:25:29.590306: step: 1220/529, loss: 0.07872195541858673
2023-01-23 01:25:30.667673: step: 1224/529, loss: 0.10093734413385391
2023-01-23 01:25:31.777409: step: 1228/529, loss: 0.23815956711769104
2023-01-23 01:25:32.880570: step: 1232/529, loss: 0.05550441890954971
2023-01-23 01:25:34.005760: step: 1236/529, loss: 0.0231951717287302
2023-01-23 01:25:35.101725: step: 1240/529, loss: 0.013909196481108665
2023-01-23 01:25:36.208935: step: 1244/529, loss: 0.15298815071582794
2023-01-23 01:25:37.313407: step: 1248/529, loss: 0.00274238595739007
2023-01-23 01:25:38.399396: step: 1252/529, loss: 0.04117918014526367
2023-01-23 01:25:39.505186: step: 1256/529, loss: 0.07713261246681213
2023-01-23 01:25:40.620327: step: 1260/529, loss: 0.027042007073760033
2023-01-23 01:25:41.710617: step: 1264/529, loss: 0.01716022565960884
2023-01-23 01:25:42.815539: step: 1268/529, loss: 0.14862041175365448
2023-01-23 01:25:43.901307: step: 1272/529, loss: 0.08967561274766922
2023-01-23 01:25:45.003297: step: 1276/529, loss: 0.013333129696547985
2023-01-23 01:25:46.126545: step: 1280/529, loss: 0.06216287612915039
2023-01-23 01:25:47.226804: step: 1284/529, loss: 0.025332070887088776
2023-01-23 01:25:48.312376: step: 1288/529, loss: 0.07996253669261932
2023-01-23 01:25:49.456028: step: 1292/529, loss: 0.19331598281860352
2023-01-23 01:25:50.566411: step: 1296/529, loss: 0.020469380542635918
2023-01-23 01:25:51.668000: step: 1300/529, loss: 0.08120517432689667
2023-01-23 01:25:52.771871: step: 1304/529, loss: 0.0030630589462816715
2023-01-23 01:25:53.877286: step: 1308/529, loss: 0.06431379169225693
2023-01-23 01:25:54.972406: step: 1312/529, loss: 0.06495921313762665
2023-01-23 01:25:56.072437: step: 1316/529, loss: 0.006024623289704323
2023-01-23 01:25:57.181251: step: 1320/529, loss: 0.01922912523150444
2023-01-23 01:25:58.298550: step: 1324/529, loss: 0.06610298156738281
2023-01-23 01:25:59.398436: step: 1328/529, loss: 0.10196170955896378
2023-01-23 01:26:00.519227: step: 1332/529, loss: 0.043562889099121094
2023-01-23 01:26:01.631305: step: 1336/529, loss: 0.002493953797966242
2023-01-23 01:26:02.748574: step: 1340/529, loss: 0.11579771339893341
2023-01-23 01:26:03.885030: step: 1344/529, loss: 0.023792171850800514
2023-01-23 01:26:05.008328: step: 1348/529, loss: 0.11767597496509552
2023-01-23 01:26:06.134957: step: 1352/529, loss: 0.07517480850219727
2023-01-23 01:26:07.233809: step: 1356/529, loss: 0.009095883928239346
2023-01-23 01:26:08.334929: step: 1360/529, loss: 0.03336753696203232
2023-01-23 01:26:09.449148: step: 1364/529, loss: 0.026984401047229767
2023-01-23 01:26:10.558936: step: 1368/529, loss: 0.192336767911911
2023-01-23 01:26:11.692199: step: 1372/529, loss: 0.3153672218322754
2023-01-23 01:26:12.788688: step: 1376/529, loss: 0.008458280935883522
2023-01-23 01:26:13.907448: step: 1380/529, loss: 0.04469604790210724
2023-01-23 01:26:15.024779: step: 1384/529, loss: 0.04680805280804634
2023-01-23 01:26:16.107670: step: 1388/529, loss: 0.05678558349609375
2023-01-23 01:26:17.205677: step: 1392/529, loss: 0.009009790606796741
2023-01-23 01:26:18.314291: step: 1396/529, loss: 0.09715954959392548
2023-01-23 01:26:19.441520: step: 1400/529, loss: 0.018822574988007545
2023-01-23 01:26:20.550662: step: 1404/529, loss: 0.01781749166548252
2023-01-23 01:26:21.681680: step: 1408/529, loss: 0.1727115660905838
2023-01-23 01:26:22.814946: step: 1412/529, loss: 0.013215900398790836
2023-01-23 01:26:23.934260: step: 1416/529, loss: 0.00029096603975631297
2023-01-23 01:26:25.046356: step: 1420/529, loss: 0.01745138131082058
2023-01-23 01:26:26.155655: step: 1424/529, loss: 0.10967454314231873
2023-01-23 01:26:27.286774: step: 1428/529, loss: 0.1127542108297348
2023-01-23 01:26:28.410268: step: 1432/529, loss: 0.4352186322212219
2023-01-23 01:26:29.546701: step: 1436/529, loss: 0.030798912048339844
2023-01-23 01:26:30.686142: step: 1440/529, loss: 0.33824315667152405
2023-01-23 01:26:31.823904: step: 1444/529, loss: 0.08715954422950745
2023-01-23 01:26:32.921133: step: 1448/529, loss: 0.11694198101758957
2023-01-23 01:26:34.053602: step: 1452/529, loss: 0.08019194006919861
2023-01-23 01:26:35.164530: step: 1456/529, loss: 0.041665174067020416
2023-01-23 01:26:36.297711: step: 1460/529, loss: 0.04990215227007866
2023-01-23 01:26:37.423835: step: 1464/529, loss: 0.04919024184346199
2023-01-23 01:26:38.523504: step: 1468/529, loss: 0.018529510125517845
2023-01-23 01:26:39.632615: step: 1472/529, loss: 0.10785657912492752
2023-01-23 01:26:40.753760: step: 1476/529, loss: 0.032964326441287994
2023-01-23 01:26:41.876805: step: 1480/529, loss: 0.03557319566607475
2023-01-23 01:26:42.970442: step: 1484/529, loss: 0.015588140115141869
2023-01-23 01:26:44.075133: step: 1488/529, loss: 0.11451463401317596
2023-01-23 01:26:45.190504: step: 1492/529, loss: 0.024896003305912018
2023-01-23 01:26:46.335721: step: 1496/529, loss: 0.03855838626623154
2023-01-23 01:26:47.442133: step: 1500/529, loss: 0.0448671355843544
2023-01-23 01:26:48.565789: step: 1504/529, loss: 0.016811847686767578
2023-01-23 01:26:49.657534: step: 1508/529, loss: 0.1740700751543045
2023-01-23 01:26:50.810990: step: 1512/529, loss: 0.06055469810962677
2023-01-23 01:26:51.937888: step: 1516/529, loss: 0.04968509450554848
2023-01-23 01:26:53.072049: step: 1520/529, loss: 0.21747250854969025
2023-01-23 01:26:54.217696: step: 1524/529, loss: 0.17350006103515625
2023-01-23 01:26:55.351221: step: 1528/529, loss: 0.011863518506288528
2023-01-23 01:26:56.488839: step: 1532/529, loss: 0.014476967044174671
2023-01-23 01:26:57.597462: step: 1536/529, loss: 0.033213138580322266
2023-01-23 01:26:58.770198: step: 1540/529, loss: 0.054854393005371094
2023-01-23 01:26:59.881805: step: 1544/529, loss: 0.06466779857873917
2023-01-23 01:27:01.046460: step: 1548/529, loss: 0.13704600930213928
2023-01-23 01:27:02.158564: step: 1552/529, loss: 0.007265186402946711
2023-01-23 01:27:03.261395: step: 1556/529, loss: 0.011124134063720703
2023-01-23 01:27:04.360922: step: 1560/529, loss: 0.21895579993724823
2023-01-23 01:27:05.484942: step: 1564/529, loss: 0.02361755259335041
2023-01-23 01:27:06.599036: step: 1568/529, loss: 0.051512762904167175
2023-01-23 01:27:07.684362: step: 1572/529, loss: 0.09439558535814285
2023-01-23 01:27:08.782934: step: 1576/529, loss: 0.03271055221557617
2023-01-23 01:27:09.909993: step: 1580/529, loss: 0.06723175197839737
2023-01-23 01:27:11.038173: step: 1584/529, loss: 0.11662255227565765
2023-01-23 01:27:12.121785: step: 1588/529, loss: 0.04502303525805473
2023-01-23 01:27:13.232861: step: 1592/529, loss: 0.07824917137622833
2023-01-23 01:27:14.325538: step: 1596/529, loss: 0.15707798302173615
2023-01-23 01:27:15.438896: step: 1600/529, loss: 0.13245125114917755
2023-01-23 01:27:16.567809: step: 1604/529, loss: 0.03590588644146919
2023-01-23 01:27:17.669536: step: 1608/529, loss: 0.03267412260174751
2023-01-23 01:27:18.787778: step: 1612/529, loss: 0.008365154266357422
2023-01-23 01:27:19.907691: step: 1616/529, loss: 0.061268400400877
2023-01-23 01:27:21.016591: step: 1620/529, loss: 0.4694023132324219
2023-01-23 01:27:22.135204: step: 1624/529, loss: 0.01960287243127823
2023-01-23 01:27:23.248513: step: 1628/529, loss: 0.07314815372228622
2023-01-23 01:27:24.454943: step: 1632/529, loss: 0.06247849389910698
2023-01-23 01:27:25.544672: step: 1636/529, loss: 0.0679868683218956
2023-01-23 01:27:26.633205: step: 1640/529, loss: 0.025119304656982422
2023-01-23 01:27:27.740021: step: 1644/529, loss: 0.08025984466075897
2023-01-23 01:27:28.821530: step: 1648/529, loss: 0.2910061776638031
2023-01-23 01:27:29.934209: step: 1652/529, loss: 0.020085670053958893
2023-01-23 01:27:31.043586: step: 1656/529, loss: 0.10923662781715393
2023-01-23 01:27:32.147723: step: 1660/529, loss: 0.6070134043693542
2023-01-23 01:27:33.284606: step: 1664/529, loss: 0.030062103644013405
2023-01-23 01:27:34.391154: step: 1668/529, loss: 0.016527796164155006
2023-01-23 01:27:35.489158: step: 1672/529, loss: 0.021309684962034225
2023-01-23 01:27:36.609485: step: 1676/529, loss: 0.11420612037181854
2023-01-23 01:27:37.755619: step: 1680/529, loss: 0.05534858629107475
2023-01-23 01:27:38.910614: step: 1684/529, loss: 0.07394818961620331
2023-01-23 01:27:40.018063: step: 1688/529, loss: 0.08401527255773544
2023-01-23 01:27:41.113005: step: 1692/529, loss: 0.050826214253902435
2023-01-23 01:27:42.229817: step: 1696/529, loss: 0.03811311721801758
2023-01-23 01:27:43.344515: step: 1700/529, loss: 0.04200448840856552
2023-01-23 01:27:44.428503: step: 1704/529, loss: 0.05162642151117325
2023-01-23 01:27:45.535653: step: 1708/529, loss: 0.041212987154722214
2023-01-23 01:27:46.638305: step: 1712/529, loss: 0.04088649898767471
2023-01-23 01:27:47.735305: step: 1716/529, loss: 0.08517150580883026
2023-01-23 01:27:48.848117: step: 1720/529, loss: 0.1025327742099762
2023-01-23 01:27:49.977334: step: 1724/529, loss: 0.033370211720466614
2023-01-23 01:27:51.107804: step: 1728/529, loss: 0.16073723137378693
2023-01-23 01:27:52.214135: step: 1732/529, loss: 0.008471203036606312
2023-01-23 01:27:53.355018: step: 1736/529, loss: 0.1142568588256836
2023-01-23 01:27:54.491472: step: 1740/529, loss: 0.026398276910185814
2023-01-23 01:27:55.625962: step: 1744/529, loss: 0.029660701751708984
2023-01-23 01:27:56.706142: step: 1748/529, loss: 0.07304278016090393
2023-01-23 01:27:57.795894: step: 1752/529, loss: 0.14309760928153992
2023-01-23 01:27:58.899074: step: 1756/529, loss: 0.054224301129579544
2023-01-23 01:28:00.012783: step: 1760/529, loss: 0.0358828529715538
2023-01-23 01:28:01.114505: step: 1764/529, loss: 0.0690569132566452
2023-01-23 01:28:02.234553: step: 1768/529, loss: 0.026938725262880325
2023-01-23 01:28:03.337953: step: 1772/529, loss: 0.014733219519257545
2023-01-23 01:28:04.463610: step: 1776/529, loss: 0.005133247468620539
2023-01-23 01:28:05.605552: step: 1780/529, loss: 0.02994842454791069
2023-01-23 01:28:06.703397: step: 1784/529, loss: 0.023548031225800514
2023-01-23 01:28:07.807747: step: 1788/529, loss: 0.10314564406871796
2023-01-23 01:28:08.928923: step: 1792/529, loss: 0.058193400502204895
2023-01-23 01:28:10.043502: step: 1796/529, loss: 0.09013862162828445
2023-01-23 01:28:11.145197: step: 1800/529, loss: 0.007958268746733665
2023-01-23 01:28:12.228613: step: 1804/529, loss: 0.0593988411128521
2023-01-23 01:28:13.335817: step: 1808/529, loss: 0.1553330421447754
2023-01-23 01:28:14.453437: step: 1812/529, loss: 0.09362685680389404
2023-01-23 01:28:15.556824: step: 1816/529, loss: 0.030263518914580345
2023-01-23 01:28:16.694977: step: 1820/529, loss: 0.041013337671756744
2023-01-23 01:28:17.848734: step: 1824/529, loss: 0.08637180924415588
2023-01-23 01:28:18.950294: step: 1828/529, loss: 0.13820229470729828
2023-01-23 01:28:20.067717: step: 1832/529, loss: 0.029839742928743362
2023-01-23 01:28:21.176379: step: 1836/529, loss: 0.026963043957948685
2023-01-23 01:28:22.315343: step: 1840/529, loss: 0.0016651629703119397
2023-01-23 01:28:23.425967: step: 1844/529, loss: 0.06535835564136505
2023-01-23 01:28:24.512704: step: 1848/529, loss: 0.02187070995569229
2023-01-23 01:28:25.607529: step: 1852/529, loss: 0.04506850242614746
2023-01-23 01:28:26.722789: step: 1856/529, loss: 0.06857109069824219
2023-01-23 01:28:27.824431: step: 1860/529, loss: 0.4883388578891754
2023-01-23 01:28:28.926760: step: 1864/529, loss: 0.025562096387147903
2023-01-23 01:28:30.024929: step: 1868/529, loss: 0.27632060647010803
2023-01-23 01:28:31.132895: step: 1872/529, loss: 0.17139454185962677
2023-01-23 01:28:32.244513: step: 1876/529, loss: 0.019004035741090775
2023-01-23 01:28:33.327775: step: 1880/529, loss: 0.03706197813153267
2023-01-23 01:28:34.458901: step: 1884/529, loss: 0.04961347579956055
2023-01-23 01:28:35.548644: step: 1888/529, loss: 0.023571301251649857
2023-01-23 01:28:36.644617: step: 1892/529, loss: 0.0631624236702919
2023-01-23 01:28:37.769075: step: 1896/529, loss: 0.019174670800566673
2023-01-23 01:28:38.871064: step: 1900/529, loss: 0.005490779876708984
2023-01-23 01:28:39.986666: step: 1904/529, loss: 0.11076603084802628
2023-01-23 01:28:41.102452: step: 1908/529, loss: 0.06614828109741211
2023-01-23 01:28:42.186767: step: 1912/529, loss: 0.3008156716823578
2023-01-23 01:28:43.287037: step: 1916/529, loss: 0.20936965942382812
2023-01-23 01:28:44.380531: step: 1920/529, loss: 0.03309326246380806
2023-01-23 01:28:45.518496: step: 1924/529, loss: 0.08620509505271912
2023-01-23 01:28:46.625736: step: 1928/529, loss: 0.019383668899536133
2023-01-23 01:28:47.742115: step: 1932/529, loss: 0.06761030852794647
2023-01-23 01:28:48.873320: step: 1936/529, loss: 0.1002282127737999
2023-01-23 01:28:50.005501: step: 1940/529, loss: 0.05093355104327202
2023-01-23 01:28:51.143870: step: 1944/529, loss: 0.3376179039478302
2023-01-23 01:28:52.285781: step: 1948/529, loss: 0.12597909569740295
2023-01-23 01:28:53.386071: step: 1952/529, loss: 0.15820197761058807
2023-01-23 01:28:54.477441: step: 1956/529, loss: 0.09152374416589737
2023-01-23 01:28:55.580608: step: 1960/529, loss: 0.0688050240278244
2023-01-23 01:28:56.712972: step: 1964/529, loss: 0.03563213720917702
2023-01-23 01:28:57.830306: step: 1968/529, loss: 0.12054653465747833
2023-01-23 01:28:58.964306: step: 1972/529, loss: 0.18245716392993927
2023-01-23 01:29:00.073709: step: 1976/529, loss: 0.1645512580871582
2023-01-23 01:29:01.163702: step: 1980/529, loss: 0.15209999680519104
2023-01-23 01:29:02.271880: step: 1984/529, loss: 0.014332962222397327
2023-01-23 01:29:03.380829: step: 1988/529, loss: 0.05136473476886749
2023-01-23 01:29:04.524415: step: 1992/529, loss: 0.3699323534965515
2023-01-23 01:29:05.629369: step: 1996/529, loss: 0.10661458969116211
2023-01-23 01:29:06.755072: step: 2000/529, loss: 0.12488795071840286
2023-01-23 01:29:07.861063: step: 2004/529, loss: 0.053247831761837006
2023-01-23 01:29:08.974599: step: 2008/529, loss: 0.029947664588689804
2023-01-23 01:29:10.080605: step: 2012/529, loss: 0.05026264116168022
2023-01-23 01:29:11.171583: step: 2016/529, loss: 0.11242732405662537
2023-01-23 01:29:12.263250: step: 2020/529, loss: 0.027987100183963776
2023-01-23 01:29:13.399832: step: 2024/529, loss: 0.16999435424804688
2023-01-23 01:29:14.503315: step: 2028/529, loss: 0.079311802983284
2023-01-23 01:29:15.619030: step: 2032/529, loss: 0.02260131761431694
2023-01-23 01:29:16.757910: step: 2036/529, loss: 0.006755828857421875
2023-01-23 01:29:17.921013: step: 2040/529, loss: 0.001632904983125627
2023-01-23 01:29:19.029507: step: 2044/529, loss: 0.1355283260345459
2023-01-23 01:29:20.146634: step: 2048/529, loss: 0.13581351935863495
2023-01-23 01:29:21.290780: step: 2052/529, loss: 0.11528797447681427
2023-01-23 01:29:22.423553: step: 2056/529, loss: 0.026104355230927467
2023-01-23 01:29:23.520622: step: 2060/529, loss: 0.48078620433807373
2023-01-23 01:29:24.628151: step: 2064/529, loss: 0.09292316436767578
2023-01-23 01:29:25.734924: step: 2068/529, loss: 0.16723380982875824
2023-01-23 01:29:26.869523: step: 2072/529, loss: 0.014786816202104092
2023-01-23 01:29:27.982153: step: 2076/529, loss: 0.0852775126695633
2023-01-23 01:29:29.072073: step: 2080/529, loss: 0.008470773696899414
2023-01-23 01:29:30.160013: step: 2084/529, loss: 0.05221007019281387
2023-01-23 01:29:31.282441: step: 2088/529, loss: 0.05150194466114044
2023-01-23 01:29:32.394506: step: 2092/529, loss: 0.026974773034453392
2023-01-23 01:29:33.477733: step: 2096/529, loss: 0.09263592213392258
2023-01-23 01:29:34.612353: step: 2100/529, loss: 0.027650833129882812
2023-01-23 01:29:35.689441: step: 2104/529, loss: 0.08481350541114807
2023-01-23 01:29:36.768406: step: 2108/529, loss: 0.002028989838436246
2023-01-23 01:29:37.877864: step: 2112/529, loss: 0.02868366241455078
2023-01-23 01:29:38.989564: step: 2116/529, loss: 0.019691206514835358
==================================================
Loss: 0.076
--------------------
Dev: {'event': {'p': 0.5742574257425742, 'r': 0.7723035952063915, 'f1': 0.6587166382737082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6344232515894641, 'r': 0.7883747178329571, 'f1': 0.7030699547055864}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
Korean: {'event': {'p': 0.6, 'r': 0.6190476190476191, 'f1': 0.609375}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.41025641025641024, 'r': 0.4444444444444444, 'f1': 0.42666666666666664}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 01:30:19.250175: step: 4/529, loss: 0.015634585171937943
2023-01-23 01:30:20.355134: step: 8/529, loss: 0.006419563200324774
2023-01-23 01:30:21.443011: step: 12/529, loss: 0.04357729107141495
2023-01-23 01:30:22.522199: step: 16/529, loss: 0.014276808127760887
2023-01-23 01:30:23.659984: step: 20/529, loss: 0.08221979439258575
2023-01-23 01:30:24.805983: step: 24/529, loss: 0.015496348962187767
2023-01-23 01:30:25.893462: step: 28/529, loss: 0.0071776630356907845
2023-01-23 01:30:27.009023: step: 32/529, loss: 0.06823565810918808
2023-01-23 01:30:28.115404: step: 36/529, loss: 0.08248968422412872
2023-01-23 01:30:29.218854: step: 40/529, loss: 0.004479527473449707
2023-01-23 01:30:30.367269: step: 44/529, loss: 0.13717421889305115
2023-01-23 01:30:31.448446: step: 48/529, loss: 0.007056808564811945
2023-01-23 01:30:32.571619: step: 52/529, loss: 0.08719882369041443
2023-01-23 01:30:33.701809: step: 56/529, loss: 0.6353353261947632
2023-01-23 01:30:34.796335: step: 60/529, loss: 0.05805234983563423
2023-01-23 01:30:35.902914: step: 64/529, loss: 0.04892003536224365
2023-01-23 01:30:37.022943: step: 68/529, loss: 0.1041591688990593
2023-01-23 01:30:38.116747: step: 72/529, loss: 0.04996924474835396
2023-01-23 01:30:39.224538: step: 76/529, loss: 0.3311885893344879
2023-01-23 01:30:40.332117: step: 80/529, loss: 0.6494429111480713
2023-01-23 01:30:41.421249: step: 84/529, loss: 0.15629205107688904
2023-01-23 01:30:42.533987: step: 88/529, loss: 0.035772036761045456
2023-01-23 01:30:43.679427: step: 92/529, loss: 0.05627737194299698
2023-01-23 01:30:44.794068: step: 96/529, loss: 0.011458969675004482
2023-01-23 01:30:45.910265: step: 100/529, loss: 0.15678353607654572
2023-01-23 01:30:47.037301: step: 104/529, loss: 0.03597602993249893
2023-01-23 01:30:48.144455: step: 108/529, loss: 0.058695316314697266
2023-01-23 01:30:49.248392: step: 112/529, loss: 0.0338197723031044
2023-01-23 01:30:50.379412: step: 116/529, loss: 0.14727360010147095
2023-01-23 01:30:51.486777: step: 120/529, loss: 0.03142547607421875
2023-01-23 01:30:52.594173: step: 124/529, loss: 0.033518124371767044
2023-01-23 01:30:53.694954: step: 128/529, loss: 0.11283960938453674
2023-01-23 01:30:54.812409: step: 132/529, loss: 0.017546653747558594
2023-01-23 01:30:55.929993: step: 136/529, loss: 0.11903420090675354
2023-01-23 01:30:57.010578: step: 140/529, loss: 0.3157869279384613
2023-01-23 01:30:58.107258: step: 144/529, loss: 0.1855243742465973
2023-01-23 01:30:59.195386: step: 148/529, loss: 0.021838141605257988
2023-01-23 01:31:00.299485: step: 152/529, loss: 0.007050132844597101
2023-01-23 01:31:01.401349: step: 156/529, loss: 0.05045595392584801
2023-01-23 01:31:02.533331: step: 160/529, loss: 0.006897354498505592
2023-01-23 01:31:03.630115: step: 164/529, loss: 0.07123079895973206
2023-01-23 01:31:04.762992: step: 168/529, loss: 0.020231151953339577
2023-01-23 01:31:05.875436: step: 172/529, loss: 0.06526605039834976
2023-01-23 01:31:06.978997: step: 176/529, loss: 0.042412757873535156
2023-01-23 01:31:08.084375: step: 180/529, loss: 0.02250983752310276
2023-01-23 01:31:09.155783: step: 184/529, loss: 0.04285914823412895
2023-01-23 01:31:10.265580: step: 188/529, loss: 0.048415567725896835
2023-01-23 01:31:11.369883: step: 192/529, loss: 0.08613376319408417
2023-01-23 01:31:12.471233: step: 196/529, loss: 0.011941147036850452
2023-01-23 01:31:13.609049: step: 200/529, loss: 0.021020984277129173
2023-01-23 01:31:14.704088: step: 204/529, loss: 0.12843847274780273
2023-01-23 01:31:15.817572: step: 208/529, loss: 0.0032606124877929688
2023-01-23 01:31:16.915800: step: 212/529, loss: 0.3989928364753723
2023-01-23 01:31:18.022353: step: 216/529, loss: 0.020298242568969727
2023-01-23 01:31:19.112769: step: 220/529, loss: 0.05939054489135742
2023-01-23 01:31:20.284434: step: 224/529, loss: 0.1745346188545227
2023-01-23 01:31:21.376152: step: 228/529, loss: 0.10474815964698792
2023-01-23 01:31:22.488539: step: 232/529, loss: 0.0008929253090173006
2023-01-23 01:31:23.661560: step: 236/529, loss: 0.13309641182422638
2023-01-23 01:31:24.781185: step: 240/529, loss: 0.01626415364444256
2023-01-23 01:31:25.914366: step: 244/529, loss: 0.012050438672304153
2023-01-23 01:31:27.012239: step: 248/529, loss: 0.034877873957157135
2023-01-23 01:31:28.145210: step: 252/529, loss: 0.0013515471946448088
2023-01-23 01:31:29.254589: step: 256/529, loss: 0.00017495155043434352
2023-01-23 01:31:30.372597: step: 260/529, loss: 0.059261322021484375
2023-01-23 01:31:31.485062: step: 264/529, loss: 0.008837556466460228
2023-01-23 01:31:32.586971: step: 268/529, loss: 0.03994917869567871
2023-01-23 01:31:33.695826: step: 272/529, loss: 0.029516959562897682
2023-01-23 01:31:34.788552: step: 276/529, loss: 0.01847228966653347
2023-01-23 01:31:35.934874: step: 280/529, loss: 0.05752287060022354
2023-01-23 01:31:37.036622: step: 284/529, loss: 0.41338494420051575
2023-01-23 01:31:38.134150: step: 288/529, loss: 0.006676006130874157
2023-01-23 01:31:39.255892: step: 292/529, loss: 0.02326345629990101
2023-01-23 01:31:40.376728: step: 296/529, loss: 0.23070678114891052
2023-01-23 01:31:41.476693: step: 300/529, loss: 0.05969208478927612
2023-01-23 01:31:42.589017: step: 304/529, loss: 0.17352323234081268
2023-01-23 01:31:43.727807: step: 308/529, loss: 0.10289621353149414
2023-01-23 01:31:44.836698: step: 312/529, loss: 0.0342593677341938
2023-01-23 01:31:45.947208: step: 316/529, loss: 0.03202342987060547
2023-01-23 01:31:47.064055: step: 320/529, loss: 0.01991640403866768
2023-01-23 01:31:48.165614: step: 324/529, loss: 0.10441437363624573
2023-01-23 01:31:49.300734: step: 328/529, loss: 0.022480487823486328
2023-01-23 01:31:50.399481: step: 332/529, loss: 0.01696782186627388
2023-01-23 01:31:51.494627: step: 336/529, loss: 0.13196228444576263
2023-01-23 01:31:52.632163: step: 340/529, loss: 0.001255083130672574
2023-01-23 01:31:53.776747: step: 344/529, loss: 0.09300652146339417
2023-01-23 01:31:54.862547: step: 348/529, loss: 0.071904756128788
2023-01-23 01:31:55.995559: step: 352/529, loss: 0.49297693371772766
2023-01-23 01:31:57.112321: step: 356/529, loss: 0.1843484491109848
2023-01-23 01:31:58.230886: step: 360/529, loss: 0.018433570861816406
2023-01-23 01:31:59.345140: step: 364/529, loss: 0.09107494354248047
2023-01-23 01:32:00.456933: step: 368/529, loss: 0.07947796583175659
2023-01-23 01:32:01.575550: step: 372/529, loss: 0.04172487556934357
2023-01-23 01:32:02.705911: step: 376/529, loss: 0.01647162437438965
2023-01-23 01:32:03.823338: step: 380/529, loss: 0.08153554052114487
2023-01-23 01:32:04.904667: step: 384/529, loss: 0.03464052826166153
2023-01-23 01:32:06.005132: step: 388/529, loss: 0.03863248974084854
2023-01-23 01:32:07.133451: step: 392/529, loss: 0.007461499888449907
2023-01-23 01:32:08.264225: step: 396/529, loss: 0.054502058774232864
2023-01-23 01:32:09.375680: step: 400/529, loss: 0.06054706871509552
2023-01-23 01:32:10.500856: step: 404/529, loss: 0.23481817543506622
2023-01-23 01:32:11.599711: step: 408/529, loss: 0.06370801478624344
2023-01-23 01:32:12.699232: step: 412/529, loss: 0.01590433157980442
2023-01-23 01:32:13.839449: step: 416/529, loss: 0.05279908329248428
2023-01-23 01:32:14.955263: step: 420/529, loss: 0.17367516458034515
2023-01-23 01:32:16.054405: step: 424/529, loss: 0.002672863192856312
2023-01-23 01:32:17.176852: step: 428/529, loss: 0.003030681749805808
2023-01-23 01:32:18.276745: step: 432/529, loss: 0.1320597231388092
2023-01-23 01:32:19.381366: step: 436/529, loss: 0.010323334485292435
2023-01-23 01:32:20.471752: step: 440/529, loss: 0.02219104766845703
2023-01-23 01:32:21.576429: step: 444/529, loss: 0.016097258776426315
2023-01-23 01:32:22.697535: step: 448/529, loss: 0.04870261996984482
2023-01-23 01:32:23.855853: step: 452/529, loss: 0.02037172205746174
2023-01-23 01:32:24.983172: step: 456/529, loss: 0.11630412936210632
2023-01-23 01:32:26.116520: step: 460/529, loss: 0.03807549551129341
2023-01-23 01:32:27.214494: step: 464/529, loss: 0.0593935027718544
2023-01-23 01:32:28.305151: step: 468/529, loss: 0.006680297665297985
2023-01-23 01:32:29.420286: step: 472/529, loss: 0.002512168837711215
2023-01-23 01:32:30.504239: step: 476/529, loss: 0.03684987872838974
2023-01-23 01:32:31.612611: step: 480/529, loss: 0.012775707989931107
2023-01-23 01:32:32.706995: step: 484/529, loss: 0.03353925049304962
2023-01-23 01:32:33.813381: step: 488/529, loss: 0.03995390236377716
2023-01-23 01:32:34.927107: step: 492/529, loss: 0.2139018028974533
2023-01-23 01:32:36.014288: step: 496/529, loss: 0.1484355479478836
2023-01-23 01:32:37.153149: step: 500/529, loss: 0.04455547407269478
2023-01-23 01:32:38.288971: step: 504/529, loss: 0.3537158966064453
2023-01-23 01:32:39.391900: step: 508/529, loss: 0.3285512924194336
2023-01-23 01:32:40.510194: step: 512/529, loss: 0.1303553283214569
2023-01-23 01:32:41.624338: step: 516/529, loss: 0.06636085361242294
2023-01-23 01:32:42.772595: step: 520/529, loss: 0.0025569917634129524
2023-01-23 01:32:43.859940: step: 524/529, loss: 0.0895816832780838
2023-01-23 01:32:44.989864: step: 528/529, loss: 0.018782544881105423
2023-01-23 01:32:46.098490: step: 532/529, loss: 0.03824892267584801
2023-01-23 01:32:47.193330: step: 536/529, loss: 0.00927422009408474
2023-01-23 01:32:48.313905: step: 540/529, loss: 0.10300073772668839
2023-01-23 01:32:49.462484: step: 544/529, loss: 0.03220396116375923
2023-01-23 01:32:50.582909: step: 548/529, loss: 0.0069176675751805305
2023-01-23 01:32:51.701864: step: 552/529, loss: 0.08452148735523224
2023-01-23 01:32:52.801433: step: 556/529, loss: 0.4841233491897583
2023-01-23 01:32:53.894972: step: 560/529, loss: 0.017428064718842506
2023-01-23 01:32:54.995884: step: 564/529, loss: 0.05555610731244087
2023-01-23 01:32:56.105534: step: 568/529, loss: 0.07069268822669983
2023-01-23 01:32:57.243964: step: 572/529, loss: 0.006107664201408625
2023-01-23 01:32:58.366135: step: 576/529, loss: 0.2340092658996582
2023-01-23 01:32:59.479473: step: 580/529, loss: 0.08533401787281036
2023-01-23 01:33:00.588411: step: 584/529, loss: 0.013085913844406605
2023-01-23 01:33:01.707372: step: 588/529, loss: 0.026302529498934746
2023-01-23 01:33:02.819236: step: 592/529, loss: 0.009231185540556908
2023-01-23 01:33:03.944129: step: 596/529, loss: 0.06901588290929794
2023-01-23 01:33:05.070381: step: 600/529, loss: 0.0263992790132761
2023-01-23 01:33:06.181542: step: 604/529, loss: 0.021418094635009766
2023-01-23 01:33:07.304437: step: 608/529, loss: 0.05278473347425461
2023-01-23 01:33:08.419447: step: 612/529, loss: 0.013976049609482288
2023-01-23 01:33:09.534786: step: 616/529, loss: 0.07042255997657776
2023-01-23 01:33:10.637876: step: 620/529, loss: 0.012071705423295498
2023-01-23 01:33:11.743761: step: 624/529, loss: 0.03619384765625
2023-01-23 01:33:12.868431: step: 628/529, loss: 0.010102653875946999
2023-01-23 01:33:13.984093: step: 632/529, loss: 0.0027556419372558594
2023-01-23 01:33:15.102861: step: 636/529, loss: 0.04009075090289116
2023-01-23 01:33:16.270532: step: 640/529, loss: 0.054708197712898254
2023-01-23 01:33:17.368762: step: 644/529, loss: 0.027746200561523438
2023-01-23 01:33:18.469342: step: 648/529, loss: 0.015670109540224075
2023-01-23 01:33:19.594592: step: 652/529, loss: 0.0326201468706131
2023-01-23 01:33:20.692856: step: 656/529, loss: 0.04464688524603844
2023-01-23 01:33:21.781575: step: 660/529, loss: 0.052407365292310715
2023-01-23 01:33:22.893947: step: 664/529, loss: 0.5318622589111328
2023-01-23 01:33:23.991153: step: 668/529, loss: 0.015525818802416325
2023-01-23 01:33:25.091767: step: 672/529, loss: 0.019034672528505325
2023-01-23 01:33:26.200408: step: 676/529, loss: 0.01824321784079075
2023-01-23 01:33:27.274522: step: 680/529, loss: 0.03645677492022514
2023-01-23 01:33:28.388971: step: 684/529, loss: 0.019097138196229935
2023-01-23 01:33:29.496408: step: 688/529, loss: 0.04615459591150284
2023-01-23 01:33:30.591748: step: 692/529, loss: 0.011239337734878063
2023-01-23 01:33:31.720785: step: 696/529, loss: 0.006378937046974897
2023-01-23 01:33:32.811115: step: 700/529, loss: 0.054081253707408905
2023-01-23 01:33:33.913159: step: 704/529, loss: 0.1335126906633377
2023-01-23 01:33:35.009713: step: 708/529, loss: 0.002607727190479636
2023-01-23 01:33:36.143651: step: 712/529, loss: 0.11718215048313141
2023-01-23 01:33:37.282919: step: 716/529, loss: 0.02962026558816433
2023-01-23 01:33:38.387067: step: 720/529, loss: 0.061727799475193024
2023-01-23 01:33:39.471355: step: 724/529, loss: 0.022665690630674362
2023-01-23 01:33:40.595437: step: 728/529, loss: 0.0004139900556765497
2023-01-23 01:33:41.708645: step: 732/529, loss: 0.019195938482880592
2023-01-23 01:33:42.808301: step: 736/529, loss: 0.031145954504609108
2023-01-23 01:33:43.923510: step: 740/529, loss: 0.05455417558550835
2023-01-23 01:33:45.012202: step: 744/529, loss: 0.008442306891083717
2023-01-23 01:33:46.151004: step: 748/529, loss: 0.0033290863502770662
2023-01-23 01:33:47.253155: step: 752/529, loss: 0.07226744294166565
2023-01-23 01:33:48.365545: step: 756/529, loss: 0.07950744777917862
2023-01-23 01:33:49.477958: step: 760/529, loss: 0.0033757209312170744
2023-01-23 01:33:50.580595: step: 764/529, loss: 0.04112539440393448
2023-01-23 01:33:51.679488: step: 768/529, loss: 0.25970783829689026
2023-01-23 01:33:52.788427: step: 772/529, loss: 0.005614042282104492
2023-01-23 01:33:53.886831: step: 776/529, loss: 0.06463642418384552
2023-01-23 01:33:55.027784: step: 780/529, loss: 0.031077099964022636
2023-01-23 01:33:56.103225: step: 784/529, loss: 0.03211555629968643
2023-01-23 01:33:57.208012: step: 788/529, loss: 0.05314221233129501
2023-01-23 01:33:58.314159: step: 792/529, loss: 0.0020237923599779606
2023-01-23 01:33:59.423871: step: 796/529, loss: 0.07007293403148651
2023-01-23 01:34:00.536386: step: 800/529, loss: 0.025855064392089844
2023-01-23 01:34:01.636815: step: 804/529, loss: 0.008034516125917435
2023-01-23 01:34:02.763291: step: 808/529, loss: 0.03595848008990288
2023-01-23 01:34:03.883696: step: 812/529, loss: 0.0032608031760901213
2023-01-23 01:34:04.979348: step: 816/529, loss: 0.013169003650546074
2023-01-23 01:34:06.087401: step: 820/529, loss: 0.024141501635313034
2023-01-23 01:34:07.238377: step: 824/529, loss: 0.1024479866027832
2023-01-23 01:34:08.336600: step: 828/529, loss: 0.019344709813594818
2023-01-23 01:34:09.417076: step: 832/529, loss: 0.0014323710929602385
2023-01-23 01:34:10.500209: step: 836/529, loss: 0.029245663434267044
2023-01-23 01:34:11.600654: step: 840/529, loss: 0.013254070654511452
2023-01-23 01:34:12.703931: step: 844/529, loss: 0.020444203168153763
2023-01-23 01:34:13.854316: step: 848/529, loss: 0.07971153408288956
2023-01-23 01:34:14.995654: step: 852/529, loss: 0.18301840126514435
2023-01-23 01:34:16.103705: step: 856/529, loss: 0.02782120741903782
2023-01-23 01:34:17.237963: step: 860/529, loss: 0.015463829040527344
2023-01-23 01:34:18.355776: step: 864/529, loss: 0.03686103969812393
2023-01-23 01:34:19.479793: step: 868/529, loss: 0.023042678833007812
2023-01-23 01:34:20.564673: step: 872/529, loss: 0.046110060065984726
2023-01-23 01:34:21.671903: step: 876/529, loss: 0.032063912600278854
2023-01-23 01:34:22.779762: step: 880/529, loss: 0.06866931915283203
2023-01-23 01:34:23.879768: step: 884/529, loss: 0.02893519401550293
2023-01-23 01:34:25.005767: step: 888/529, loss: 0.5382149815559387
2023-01-23 01:34:26.135556: step: 892/529, loss: 0.05076196417212486
2023-01-23 01:34:27.231240: step: 896/529, loss: 0.06138572841882706
2023-01-23 01:34:28.337815: step: 900/529, loss: 0.037667322903871536
2023-01-23 01:34:29.451700: step: 904/529, loss: 0.062125399708747864
2023-01-23 01:34:30.565408: step: 908/529, loss: 0.14272108674049377
2023-01-23 01:34:31.689358: step: 912/529, loss: 0.031221581622958183
2023-01-23 01:34:32.812876: step: 916/529, loss: 0.03425560146570206
2023-01-23 01:34:33.959686: step: 920/529, loss: 0.03369269147515297
2023-01-23 01:34:35.050945: step: 924/529, loss: 0.0652259811758995
2023-01-23 01:34:36.157327: step: 928/529, loss: 0.06813813000917435
2023-01-23 01:34:37.308737: step: 932/529, loss: 0.013027573004364967
2023-01-23 01:34:38.430215: step: 936/529, loss: 0.025594711303710938
2023-01-23 01:34:39.543057: step: 940/529, loss: 0.016342926770448685
2023-01-23 01:34:40.645313: step: 944/529, loss: 0.012179946526885033
2023-01-23 01:34:41.770224: step: 948/529, loss: 1.0101159811019897
2023-01-23 01:34:42.874972: step: 952/529, loss: 0.11328279972076416
2023-01-23 01:34:43.993006: step: 956/529, loss: 0.017920399084687233
2023-01-23 01:34:45.110974: step: 960/529, loss: 0.037798501551151276
2023-01-23 01:34:46.230224: step: 964/529, loss: 0.12885704636573792
2023-01-23 01:34:47.359860: step: 968/529, loss: 0.001981496810913086
2023-01-23 01:34:48.462077: step: 972/529, loss: 0.030063629150390625
2023-01-23 01:34:49.572953: step: 976/529, loss: 0.03332536295056343
2023-01-23 01:34:50.684383: step: 980/529, loss: 0.04087886959314346
2023-01-23 01:34:51.824225: step: 984/529, loss: 0.039319656789302826
2023-01-23 01:34:52.935622: step: 988/529, loss: 0.10448842495679855
2023-01-23 01:34:54.063281: step: 992/529, loss: 0.04496314749121666
2023-01-23 01:34:55.191898: step: 996/529, loss: 0.03794918209314346
2023-01-23 01:34:56.298407: step: 1000/529, loss: 0.018438149243593216
2023-01-23 01:34:57.409320: step: 1004/529, loss: 0.01054925937205553
2023-01-23 01:34:58.523246: step: 1008/529, loss: 0.1984979659318924
2023-01-23 01:34:59.646390: step: 1012/529, loss: 0.012137318029999733
2023-01-23 01:35:00.774980: step: 1016/529, loss: 0.016981076449155807
2023-01-23 01:35:01.868749: step: 1020/529, loss: 0.054285429418087006
2023-01-23 01:35:02.983845: step: 1024/529, loss: 0.025885486975312233
2023-01-23 01:35:04.093416: step: 1028/529, loss: 0.031004810705780983
2023-01-23 01:35:05.199069: step: 1032/529, loss: 0.009832668118178844
2023-01-23 01:35:06.295810: step: 1036/529, loss: 0.020828628912568092
2023-01-23 01:35:07.406195: step: 1040/529, loss: 0.07629795372486115
2023-01-23 01:35:08.526708: step: 1044/529, loss: 0.04315061494708061
2023-01-23 01:35:09.652040: step: 1048/529, loss: 0.009748315438628197
2023-01-23 01:35:10.769352: step: 1052/529, loss: 0.06804456561803818
2023-01-23 01:35:11.851993: step: 1056/529, loss: 0.05234070122241974
2023-01-23 01:35:12.949906: step: 1060/529, loss: 0.03478412330150604
2023-01-23 01:35:14.042182: step: 1064/529, loss: 0.022547150030732155
2023-01-23 01:35:15.171899: step: 1068/529, loss: 0.0698062926530838
2023-01-23 01:35:16.268204: step: 1072/529, loss: 0.07025470584630966
2023-01-23 01:35:17.394128: step: 1076/529, loss: 0.06398516148328781
2023-01-23 01:35:18.507234: step: 1080/529, loss: 0.1375909149646759
2023-01-23 01:35:19.648711: step: 1084/529, loss: 0.040517523884773254
2023-01-23 01:35:20.733061: step: 1088/529, loss: 0.14841842651367188
2023-01-23 01:35:21.863230: step: 1092/529, loss: 0.086273193359375
2023-01-23 01:35:22.951572: step: 1096/529, loss: 0.06956568360328674
2023-01-23 01:35:24.049482: step: 1100/529, loss: 0.08271627128124237
2023-01-23 01:35:25.160549: step: 1104/529, loss: 0.08006992191076279
2023-01-23 01:35:26.258882: step: 1108/529, loss: 0.2676321864128113
2023-01-23 01:35:27.364873: step: 1112/529, loss: 0.08240614086389542
2023-01-23 01:35:28.489487: step: 1116/529, loss: 0.10963144898414612
2023-01-23 01:35:29.580664: step: 1120/529, loss: 0.015755273401737213
2023-01-23 01:35:30.725343: step: 1124/529, loss: 0.0639006644487381
2023-01-23 01:35:31.832442: step: 1128/529, loss: 0.008260917849838734
2023-01-23 01:35:32.968587: step: 1132/529, loss: 0.00912246759980917
2023-01-23 01:35:34.138894: step: 1136/529, loss: 0.05913090705871582
2023-01-23 01:35:35.247629: step: 1140/529, loss: 0.06082306057214737
2023-01-23 01:35:36.360062: step: 1144/529, loss: 0.047199077904224396
2023-01-23 01:35:37.463679: step: 1148/529, loss: 0.00542340287938714
2023-01-23 01:35:38.559514: step: 1152/529, loss: 0.00975647009909153
2023-01-23 01:35:39.651961: step: 1156/529, loss: 0.056063272058963776
2023-01-23 01:35:40.767126: step: 1160/529, loss: 0.018897246569395065
2023-01-23 01:35:41.876835: step: 1164/529, loss: 0.05194282531738281
2023-01-23 01:35:42.995867: step: 1168/529, loss: 0.029150735586881638
2023-01-23 01:35:44.103300: step: 1172/529, loss: 0.018677283078432083
2023-01-23 01:35:45.204407: step: 1176/529, loss: 0.07526731491088867
2023-01-23 01:35:46.302642: step: 1180/529, loss: 0.03196830675005913
2023-01-23 01:35:47.414944: step: 1184/529, loss: 0.055865198373794556
2023-01-23 01:35:48.525710: step: 1188/529, loss: 0.1328238546848297
2023-01-23 01:35:49.634990: step: 1192/529, loss: 0.04624681547284126
2023-01-23 01:35:50.759764: step: 1196/529, loss: 0.08423338085412979
2023-01-23 01:35:51.870645: step: 1200/529, loss: 0.026012137532234192
2023-01-23 01:35:52.973227: step: 1204/529, loss: 0.001549196313135326
2023-01-23 01:35:54.079261: step: 1208/529, loss: 0.023470783606171608
2023-01-23 01:35:55.220287: step: 1212/529, loss: 0.049822043627500534
2023-01-23 01:35:56.382993: step: 1216/529, loss: 0.10277938842773438
2023-01-23 01:35:57.518871: step: 1220/529, loss: 0.009597779251635075
2023-01-23 01:35:58.606803: step: 1224/529, loss: 0.01658325269818306
2023-01-23 01:35:59.742285: step: 1228/529, loss: 0.061242491006851196
2023-01-23 01:36:00.881952: step: 1232/529, loss: 0.36316853761672974
2023-01-23 01:36:01.988713: step: 1236/529, loss: 0.09373664855957031
2023-01-23 01:36:03.108397: step: 1240/529, loss: 0.00899038277566433
2023-01-23 01:36:04.193353: step: 1244/529, loss: 0.0021594048012048006
2023-01-23 01:36:05.297544: step: 1248/529, loss: 0.12025928497314453
2023-01-23 01:36:06.405944: step: 1252/529, loss: 0.03190011903643608
2023-01-23 01:36:07.502329: step: 1256/529, loss: 0.05552215874195099
2023-01-23 01:36:08.616984: step: 1260/529, loss: 0.031192127615213394
2023-01-23 01:36:09.754251: step: 1264/529, loss: 0.006292581558227539
2023-01-23 01:36:10.872839: step: 1268/529, loss: 0.0015749931335449219
2023-01-23 01:36:11.974423: step: 1272/529, loss: 0.06892938911914825
2023-01-23 01:36:13.077937: step: 1276/529, loss: 0.14832572638988495
2023-01-23 01:36:14.199808: step: 1280/529, loss: 0.028995418921113014
2023-01-23 01:36:15.300911: step: 1284/529, loss: 0.10269031673669815
2023-01-23 01:36:16.408247: step: 1288/529, loss: 0.01741924323141575
2023-01-23 01:36:17.552594: step: 1292/529, loss: 0.02010469324886799
2023-01-23 01:36:18.674776: step: 1296/529, loss: 0.02647099643945694
2023-01-23 01:36:19.792365: step: 1300/529, loss: 0.01633281819522381
2023-01-23 01:36:20.912587: step: 1304/529, loss: 0.014727115631103516
2023-01-23 01:36:22.017844: step: 1308/529, loss: 0.011113643646240234
2023-01-23 01:36:23.144966: step: 1312/529, loss: 0.016550255939364433
2023-01-23 01:36:24.252494: step: 1316/529, loss: 0.02597637102007866
2023-01-23 01:36:25.369855: step: 1320/529, loss: 0.012275981716811657
2023-01-23 01:36:26.490372: step: 1324/529, loss: 0.006790637969970703
2023-01-23 01:36:27.619380: step: 1328/529, loss: 0.047884371131658554
2023-01-23 01:36:28.768961: step: 1332/529, loss: 0.08185453712940216
2023-01-23 01:36:29.855663: step: 1336/529, loss: 0.041016869246959686
2023-01-23 01:36:30.985840: step: 1340/529, loss: 0.042281534522771835
2023-01-23 01:36:32.112135: step: 1344/529, loss: 0.05097236484289169
2023-01-23 01:36:33.222309: step: 1348/529, loss: 0.03887634351849556
2023-01-23 01:36:34.316875: step: 1352/529, loss: 0.08085336536169052
2023-01-23 01:36:35.400617: step: 1356/529, loss: 0.06968836486339569
2023-01-23 01:36:36.502142: step: 1360/529, loss: 0.018033599480986595
2023-01-23 01:36:37.609252: step: 1364/529, loss: 0.1166471540927887
2023-01-23 01:36:38.737357: step: 1368/529, loss: 0.022437667474150658
2023-01-23 01:36:39.857821: step: 1372/529, loss: 0.043592311441898346
2023-01-23 01:36:40.975488: step: 1376/529, loss: 0.044651225209236145
2023-01-23 01:36:42.090345: step: 1380/529, loss: 0.1370231658220291
2023-01-23 01:36:43.204773: step: 1384/529, loss: 0.03458767011761665
2023-01-23 01:36:44.310982: step: 1388/529, loss: 0.017298508435487747
2023-01-23 01:36:45.418238: step: 1392/529, loss: 0.00023469925508834422
2023-01-23 01:36:46.519795: step: 1396/529, loss: 0.0022085190284997225
2023-01-23 01:36:47.613713: step: 1400/529, loss: 0.06543579697608948
2023-01-23 01:36:48.715316: step: 1404/529, loss: 0.15252408385276794
2023-01-23 01:36:49.818884: step: 1408/529, loss: 0.02981758303940296
2023-01-23 01:36:50.923708: step: 1412/529, loss: 0.018331432715058327
2023-01-23 01:36:52.031759: step: 1416/529, loss: 0.05113248899579048
2023-01-23 01:36:53.143545: step: 1420/529, loss: 0.0463414192199707
2023-01-23 01:36:54.246217: step: 1424/529, loss: 0.02421570010483265
2023-01-23 01:36:55.372517: step: 1428/529, loss: 0.06854267418384552
2023-01-23 01:36:56.477732: step: 1432/529, loss: 0.07120855152606964
2023-01-23 01:36:57.595636: step: 1436/529, loss: 0.015619087032973766
2023-01-23 01:36:58.712114: step: 1440/529, loss: 0.07546329498291016
2023-01-23 01:36:59.841785: step: 1444/529, loss: 0.009140062145888805
2023-01-23 01:37:00.943127: step: 1448/529, loss: 0.01577281951904297
2023-01-23 01:37:02.023437: step: 1452/529, loss: 0.011563492007553577
2023-01-23 01:37:03.119177: step: 1456/529, loss: 0.033582307398319244
2023-01-23 01:37:04.210792: step: 1460/529, loss: 0.011561584658920765
2023-01-23 01:37:05.340443: step: 1464/529, loss: 0.035955097526311874
2023-01-23 01:37:06.457118: step: 1468/529, loss: 0.0008926392183639109
2023-01-23 01:37:07.593287: step: 1472/529, loss: 0.010932732373476028
2023-01-23 01:37:08.692309: step: 1476/529, loss: 0.026738930493593216
2023-01-23 01:37:09.841544: step: 1480/529, loss: 0.005289840511977673
2023-01-23 01:37:10.937968: step: 1484/529, loss: 1.2817879915237427
2023-01-23 01:37:12.091057: step: 1488/529, loss: 0.18614941835403442
2023-01-23 01:37:13.181610: step: 1492/529, loss: 0.020973587408661842
2023-01-23 01:37:14.248504: step: 1496/529, loss: 0.021105099469423294
2023-01-23 01:37:15.402524: step: 1500/529, loss: 0.04409465938806534
2023-01-23 01:37:16.506852: step: 1504/529, loss: 0.02840442582964897
2023-01-23 01:37:17.622695: step: 1508/529, loss: 0.4077225625514984
2023-01-23 01:37:18.737886: step: 1512/529, loss: 0.12635794281959534
2023-01-23 01:37:19.836052: step: 1516/529, loss: 0.028376102447509766
2023-01-23 01:37:20.965366: step: 1520/529, loss: 0.03752918168902397
2023-01-23 01:37:22.083028: step: 1524/529, loss: 0.03224983066320419
2023-01-23 01:37:23.187388: step: 1528/529, loss: 0.023200606927275658
2023-01-23 01:37:24.283584: step: 1532/529, loss: 0.0007997512584552169
2023-01-23 01:37:25.388718: step: 1536/529, loss: 0.0032644271850585938
2023-01-23 01:37:26.501850: step: 1540/529, loss: 0.04025211185216904
2023-01-23 01:37:27.593059: step: 1544/529, loss: 0.16581708192825317
2023-01-23 01:37:28.748575: step: 1548/529, loss: 0.04532432556152344
2023-01-23 01:37:29.877111: step: 1552/529, loss: 0.08706779778003693
2023-01-23 01:37:30.994425: step: 1556/529, loss: 0.04276624694466591
2023-01-23 01:37:32.081417: step: 1560/529, loss: 0.03359370306134224
2023-01-23 01:37:33.239716: step: 1564/529, loss: 0.028411865234375
2023-01-23 01:37:34.337338: step: 1568/529, loss: 0.03997201845049858
2023-01-23 01:37:35.444998: step: 1572/529, loss: 0.03255004808306694
2023-01-23 01:37:36.533194: step: 1576/529, loss: 0.0849708542227745
2023-01-23 01:37:37.667733: step: 1580/529, loss: 0.03191395103931427
2023-01-23 01:37:38.824004: step: 1584/529, loss: 0.08040819317102432
2023-01-23 01:37:39.909429: step: 1588/529, loss: 0.01630554348230362
2023-01-23 01:37:41.029345: step: 1592/529, loss: 0.02791604958474636
2023-01-23 01:37:42.154590: step: 1596/529, loss: 0.09858722239732742
2023-01-23 01:37:43.262181: step: 1600/529, loss: 0.06216542795300484
2023-01-23 01:37:44.409340: step: 1604/529, loss: 0.1791582703590393
2023-01-23 01:37:45.528260: step: 1608/529, loss: 0.09997282177209854
2023-01-23 01:37:46.616953: step: 1612/529, loss: 0.0009524345514364541
2023-01-23 01:37:47.715198: step: 1616/529, loss: 0.08954592049121857
2023-01-23 01:37:48.819678: step: 1620/529, loss: 0.012497663497924805
2023-01-23 01:37:49.954147: step: 1624/529, loss: 0.009469079785048962
2023-01-23 01:37:51.043454: step: 1628/529, loss: 0.018001150339841843
2023-01-23 01:37:52.177410: step: 1632/529, loss: 0.028762245550751686
2023-01-23 01:37:53.278590: step: 1636/529, loss: 0.08118200302124023
2023-01-23 01:37:54.406467: step: 1640/529, loss: 0.10868954658508301
2023-01-23 01:37:55.528862: step: 1644/529, loss: 0.0661388412117958
2023-01-23 01:37:56.643388: step: 1648/529, loss: 0.024476435035467148
2023-01-23 01:37:57.776919: step: 1652/529, loss: 0.02030305750668049
2023-01-23 01:37:58.877530: step: 1656/529, loss: 0.050966549664735794
2023-01-23 01:37:59.999812: step: 1660/529, loss: 0.2167210578918457
2023-01-23 01:38:01.102484: step: 1664/529, loss: 0.032126620411872864
2023-01-23 01:38:02.220280: step: 1668/529, loss: 0.01632622443139553
2023-01-23 01:38:03.372288: step: 1672/529, loss: 0.45482900738716125
2023-01-23 01:38:04.460167: step: 1676/529, loss: 0.016525840386748314
2023-01-23 01:38:05.617147: step: 1680/529, loss: 0.18198880553245544
2023-01-23 01:38:06.760668: step: 1684/529, loss: 0.02922077104449272
2023-01-23 01:38:07.874829: step: 1688/529, loss: 0.33754825592041016
2023-01-23 01:38:08.986678: step: 1692/529, loss: 0.01591520383954048
2023-01-23 01:38:10.094060: step: 1696/529, loss: 0.1771833449602127
2023-01-23 01:38:11.181227: step: 1700/529, loss: 0.0012199401389807463
2023-01-23 01:38:12.308690: step: 1704/529, loss: 0.030598830431699753
2023-01-23 01:38:13.394241: step: 1708/529, loss: 0.018317176029086113
2023-01-23 01:38:14.493431: step: 1712/529, loss: 0.008237361907958984
2023-01-23 01:38:15.595916: step: 1716/529, loss: 0.07449178397655487
2023-01-23 01:38:16.721264: step: 1720/529, loss: 0.13098879158496857
2023-01-23 01:38:17.826202: step: 1724/529, loss: 0.012220572680234909
2023-01-23 01:38:18.921482: step: 1728/529, loss: 0.061811067163944244
2023-01-23 01:38:20.059588: step: 1732/529, loss: 0.009442901238799095
2023-01-23 01:38:21.174022: step: 1736/529, loss: 0.003170651150867343
2023-01-23 01:38:22.287857: step: 1740/529, loss: 0.018052101135253906
2023-01-23 01:38:23.387622: step: 1744/529, loss: 0.043543148785829544
2023-01-23 01:38:24.493500: step: 1748/529, loss: 0.6302715539932251
2023-01-23 01:38:25.629895: step: 1752/529, loss: 0.29814016819000244
2023-01-23 01:38:26.740571: step: 1756/529, loss: 0.018412113189697266
2023-01-23 01:38:27.850827: step: 1760/529, loss: 0.04240760952234268
2023-01-23 01:38:29.007037: step: 1764/529, loss: 0.06515979766845703
2023-01-23 01:38:30.119646: step: 1768/529, loss: 0.14517177641391754
2023-01-23 01:38:31.237550: step: 1772/529, loss: 0.07652683556079865
2023-01-23 01:38:32.354405: step: 1776/529, loss: 0.05062122642993927
2023-01-23 01:38:33.459098: step: 1780/529, loss: 0.017912961542606354
2023-01-23 01:38:34.553067: step: 1784/529, loss: 0.03451428562402725
2023-01-23 01:38:35.687738: step: 1788/529, loss: 0.0849205031991005
2023-01-23 01:38:36.824174: step: 1792/529, loss: 0.00943670328706503
2023-01-23 01:38:37.942554: step: 1796/529, loss: 0.048021744936704636
2023-01-23 01:38:39.045581: step: 1800/529, loss: 0.07249584794044495
2023-01-23 01:38:40.174937: step: 1804/529, loss: 0.022319890558719635
2023-01-23 01:38:41.299924: step: 1808/529, loss: 0.027266694232821465
2023-01-23 01:38:42.378839: step: 1812/529, loss: 0.03726387396454811
2023-01-23 01:38:43.512711: step: 1816/529, loss: 0.1139443963766098
2023-01-23 01:38:44.726938: step: 1820/529, loss: 0.08703994750976562
2023-01-23 01:38:45.852689: step: 1824/529, loss: 0.015526198782026768
2023-01-23 01:38:46.969835: step: 1828/529, loss: 0.03237032890319824
2023-01-23 01:38:48.093810: step: 1832/529, loss: 0.009862994775176048
2023-01-23 01:38:49.238950: step: 1836/529, loss: 0.04492530971765518
2023-01-23 01:38:50.387738: step: 1840/529, loss: 0.027873801067471504
2023-01-23 01:38:51.509988: step: 1844/529, loss: 0.19703903794288635
2023-01-23 01:38:52.620018: step: 1848/529, loss: 0.013106727972626686
2023-01-23 01:38:53.754829: step: 1852/529, loss: 0.010895348154008389
2023-01-23 01:38:54.876313: step: 1856/529, loss: 0.01015615463256836
2023-01-23 01:38:56.007983: step: 1860/529, loss: 0.10346546024084091
2023-01-23 01:38:57.116602: step: 1864/529, loss: 0.43522942066192627
2023-01-23 01:38:58.241241: step: 1868/529, loss: 0.035448648035526276
2023-01-23 01:38:59.362030: step: 1872/529, loss: 0.007220649626106024
2023-01-23 01:39:00.465472: step: 1876/529, loss: 0.01151819247752428
2023-01-23 01:39:01.597361: step: 1880/529, loss: 0.07154957950115204
2023-01-23 01:39:02.703668: step: 1884/529, loss: 0.0020329237449914217
2023-01-23 01:39:03.848752: step: 1888/529, loss: 0.015955829992890358
2023-01-23 01:39:04.958908: step: 1892/529, loss: 0.1267586201429367
2023-01-23 01:39:06.045418: step: 1896/529, loss: 0.04730387032032013
2023-01-23 01:39:07.149898: step: 1900/529, loss: 0.1389884054660797
2023-01-23 01:39:08.267551: step: 1904/529, loss: 0.2638680338859558
2023-01-23 01:39:09.390307: step: 1908/529, loss: 0.0234375
2023-01-23 01:39:10.484939: step: 1912/529, loss: 0.6985609531402588
2023-01-23 01:39:11.572506: step: 1916/529, loss: 0.35749319195747375
2023-01-23 01:39:12.692450: step: 1920/529, loss: 0.0287201888859272
2023-01-23 01:39:13.797683: step: 1924/529, loss: 0.03194260597229004
2023-01-23 01:39:14.909166: step: 1928/529, loss: 0.02880726009607315
2023-01-23 01:39:16.012214: step: 1932/529, loss: 0.14732703566551208
2023-01-23 01:39:17.131605: step: 1936/529, loss: 0.033373452723026276
2023-01-23 01:39:18.246508: step: 1940/529, loss: 0.030338667333126068
2023-01-23 01:39:19.375863: step: 1944/529, loss: 0.07796420902013779
2023-01-23 01:39:20.464242: step: 1948/529, loss: 0.07340216636657715
2023-01-23 01:39:21.560882: step: 1952/529, loss: 6.369919300079346
2023-01-23 01:39:22.689332: step: 1956/529, loss: 0.1040363758802414
2023-01-23 01:39:23.804178: step: 1960/529, loss: 0.12936702370643616
2023-01-23 01:39:24.943408: step: 1964/529, loss: 0.037236977368593216
2023-01-23 01:39:26.054688: step: 1968/529, loss: 0.04321565479040146
2023-01-23 01:39:27.177417: step: 1972/529, loss: 0.009425735101103783
2023-01-23 01:39:28.314522: step: 1976/529, loss: 0.007780981250107288
2023-01-23 01:39:29.444568: step: 1980/529, loss: 0.06220731511712074
2023-01-23 01:39:30.561767: step: 1984/529, loss: 0.11651439964771271
2023-01-23 01:39:31.693381: step: 1988/529, loss: 0.013585568405687809
2023-01-23 01:39:32.795320: step: 1992/529, loss: 0.016615772619843483
2023-01-23 01:39:33.896726: step: 1996/529, loss: 0.011364936828613281
2023-01-23 01:39:35.004647: step: 2000/529, loss: 0.3767964243888855
2023-01-23 01:39:36.091011: step: 2004/529, loss: 0.0048768045380711555
2023-01-23 01:39:37.190465: step: 2008/529, loss: 0.011681205593049526
2023-01-23 01:39:38.267160: step: 2012/529, loss: 0.0638306587934494
2023-01-23 01:39:39.382062: step: 2016/529, loss: 0.02537841722369194
2023-01-23 01:39:40.487963: step: 2020/529, loss: 0.09910902380943298
2023-01-23 01:39:41.640010: step: 2024/529, loss: 0.0655437484383583
2023-01-23 01:39:42.739046: step: 2028/529, loss: 0.0441129207611084
2023-01-23 01:39:43.855256: step: 2032/529, loss: 0.031630899757146835
2023-01-23 01:39:44.966257: step: 2036/529, loss: 0.008608913980424404
2023-01-23 01:39:46.085229: step: 2040/529, loss: 0.00925140455365181
2023-01-23 01:39:47.220794: step: 2044/529, loss: 0.05186887085437775
2023-01-23 01:39:48.329429: step: 2048/529, loss: 0.0050865174271166325
2023-01-23 01:39:49.464301: step: 2052/529, loss: 0.04473453015089035
2023-01-23 01:39:50.557850: step: 2056/529, loss: 0.04050302505493164
2023-01-23 01:39:51.652387: step: 2060/529, loss: 0.023241043090820312
2023-01-23 01:39:52.761157: step: 2064/529, loss: 0.10674099624156952
2023-01-23 01:39:53.857681: step: 2068/529, loss: 0.04414501041173935
2023-01-23 01:39:54.969532: step: 2072/529, loss: 0.013210296630859375
2023-01-23 01:39:56.052548: step: 2076/529, loss: 0.018911074846982956
2023-01-23 01:39:57.134914: step: 2080/529, loss: 0.030109308660030365
2023-01-23 01:39:58.264586: step: 2084/529, loss: 0.015364646911621094
2023-01-23 01:39:59.378802: step: 2088/529, loss: 0.007328510750085115
2023-01-23 01:40:00.498628: step: 2092/529, loss: 0.040717221796512604
2023-01-23 01:40:01.622837: step: 2096/529, loss: 0.1877738982439041
2023-01-23 01:40:02.725439: step: 2100/529, loss: 0.04347119480371475
2023-01-23 01:40:03.816394: step: 2104/529, loss: 0.03549699857831001
2023-01-23 01:40:04.940554: step: 2108/529, loss: 0.16354884207248688
2023-01-23 01:40:06.051868: step: 2112/529, loss: 0.008365154266357422
2023-01-23 01:40:07.150884: step: 2116/529, loss: 0.06444015353918076
==================================================
Loss: 0.083
--------------------
Dev: {'event': {'p': 0.6060606060606061, 'r': 0.7723035952063915, 'f1': 0.6791569086651054}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6296123306865951, 'r': 0.7607223476297968, 'f1': 0.6889854331714796}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5434782608695652, 'r': 0.9259259259259259, 'f1': 0.6849315068493151}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.532258064516129, 'r': 0.5238095238095238, 'f1': 0.5280000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:40:46.889995: step: 4/529, loss: 0.07293281704187393
2023-01-23 01:40:48.008476: step: 8/529, loss: 0.05306410789489746
2023-01-23 01:40:49.136084: step: 12/529, loss: 0.0043087005615234375
2023-01-23 01:40:50.267649: step: 16/529, loss: 0.02919778972864151
2023-01-23 01:40:51.354604: step: 20/529, loss: 0.06782207638025284
2023-01-23 01:40:52.454739: step: 24/529, loss: 0.05834408104419708
2023-01-23 01:40:53.572796: step: 28/529, loss: 0.02410259284079075
2023-01-23 01:40:54.681820: step: 32/529, loss: 0.03040762059390545
2023-01-23 01:40:55.840530: step: 36/529, loss: 0.04593805968761444
2023-01-23 01:40:56.947257: step: 40/529, loss: 0.0033075332175940275
2023-01-23 01:40:58.078273: step: 44/529, loss: 0.1294124573469162
2023-01-23 01:40:59.206103: step: 48/529, loss: 0.014727211557328701
2023-01-23 01:41:00.321498: step: 52/529, loss: 0.03246564790606499
2023-01-23 01:41:01.424690: step: 56/529, loss: 0.04186735302209854
2023-01-23 01:41:02.556061: step: 60/529, loss: 0.11083802580833435
2023-01-23 01:41:03.674470: step: 64/529, loss: 0.1341545134782791
2023-01-23 01:41:04.772773: step: 68/529, loss: 0.03129563480615616
2023-01-23 01:41:05.870522: step: 72/529, loss: 0.026824189350008965
2023-01-23 01:41:06.979306: step: 76/529, loss: 0.004168987274169922
2023-01-23 01:41:08.080157: step: 80/529, loss: 0.010345744900405407
2023-01-23 01:41:09.181094: step: 84/529, loss: 0.08374261856079102
2023-01-23 01:41:10.297151: step: 88/529, loss: 0.0028049468528479338
2023-01-23 01:41:11.408912: step: 92/529, loss: 0.013827514834702015
2023-01-23 01:41:12.508660: step: 96/529, loss: 0.10413875430822372
2023-01-23 01:41:13.581870: step: 100/529, loss: 0.0017693996196612716
2023-01-23 01:41:14.691850: step: 104/529, loss: 0.030693912878632545
2023-01-23 01:41:15.828535: step: 108/529, loss: 0.09507226943969727
2023-01-23 01:41:16.941928: step: 112/529, loss: 0.003758668899536133
2023-01-23 01:41:18.057254: step: 116/529, loss: 0.04741577059030533
2023-01-23 01:41:19.165287: step: 120/529, loss: 0.0698552206158638
2023-01-23 01:41:20.272654: step: 124/529, loss: 0.019583702087402344
2023-01-23 01:41:21.402388: step: 128/529, loss: 0.0826694443821907
2023-01-23 01:41:22.514984: step: 132/529, loss: 0.0446566604077816
2023-01-23 01:41:23.609104: step: 136/529, loss: 0.02641153521835804
2023-01-23 01:41:24.703884: step: 140/529, loss: 0.015978194773197174
2023-01-23 01:41:25.848786: step: 144/529, loss: 0.016172980889678
2023-01-23 01:41:26.950255: step: 148/529, loss: 0.04405966028571129
2023-01-23 01:41:28.076792: step: 152/529, loss: 0.012769126333296299
2023-01-23 01:41:29.197128: step: 156/529, loss: 0.06906633824110031
2023-01-23 01:41:30.334400: step: 160/529, loss: 0.02988309971988201
2023-01-23 01:41:31.432930: step: 164/529, loss: 0.026522064581513405
2023-01-23 01:41:32.562987: step: 168/529, loss: 0.10043449699878693
2023-01-23 01:41:33.676158: step: 172/529, loss: 0.04777669906616211
2023-01-23 01:41:34.795587: step: 176/529, loss: 0.08264217525720596
2023-01-23 01:41:35.917967: step: 180/529, loss: 0.04310645908117294
2023-01-23 01:41:37.034435: step: 184/529, loss: 0.004085731692612171
2023-01-23 01:41:38.128384: step: 188/529, loss: 0.02329711988568306
2023-01-23 01:41:39.259178: step: 192/529, loss: 0.04551362991333008
2023-01-23 01:41:40.356534: step: 196/529, loss: 0.012001561932265759
2023-01-23 01:41:41.473975: step: 200/529, loss: 0.004966163542121649
2023-01-23 01:41:42.587855: step: 204/529, loss: 0.04300098493695259
2023-01-23 01:41:43.672715: step: 208/529, loss: 0.042791180312633514
2023-01-23 01:41:44.787267: step: 212/529, loss: 0.030836915597319603
2023-01-23 01:41:45.895270: step: 216/529, loss: 0.0011765003437176347
2023-01-23 01:41:46.978020: step: 220/529, loss: 0.007782173343002796
2023-01-23 01:41:48.092181: step: 224/529, loss: 0.0169556625187397
2023-01-23 01:41:49.229748: step: 228/529, loss: 0.006486034020781517
2023-01-23 01:41:50.311866: step: 232/529, loss: 0.053126052021980286
2023-01-23 01:41:51.439661: step: 236/529, loss: 0.08858838677406311
2023-01-23 01:41:52.542679: step: 240/529, loss: 0.03427934646606445
2023-01-23 01:41:53.664475: step: 244/529, loss: 0.11107286810874939
2023-01-23 01:41:54.779135: step: 248/529, loss: 0.012371874414384365
2023-01-23 01:41:55.887426: step: 252/529, loss: 0.15168094635009766
2023-01-23 01:41:56.986933: step: 256/529, loss: 0.002318096114322543
2023-01-23 01:41:58.069208: step: 260/529, loss: 0.0011807441478595138
2023-01-23 01:41:59.182058: step: 264/529, loss: 0.05001430585980415
2023-01-23 01:42:00.276039: step: 268/529, loss: 0.027407310903072357
2023-01-23 01:42:01.386612: step: 272/529, loss: 0.05107688903808594
2023-01-23 01:42:02.471505: step: 276/529, loss: 0.012657929211854935
2023-01-23 01:42:03.611690: step: 280/529, loss: 0.0623016357421875
2023-01-23 01:42:04.759907: step: 284/529, loss: 0.42091426253318787
2023-01-23 01:42:05.881287: step: 288/529, loss: 0.024303628131747246
2023-01-23 01:42:06.970196: step: 292/529, loss: 0.00238971714861691
2023-01-23 01:42:08.075071: step: 296/529, loss: 0.06544456630945206
2023-01-23 01:42:09.194437: step: 300/529, loss: 0.022367000579833984
2023-01-23 01:42:10.341166: step: 304/529, loss: 0.038046568632125854
2023-01-23 01:42:11.501663: step: 308/529, loss: 0.030861474573612213
2023-01-23 01:42:12.622708: step: 312/529, loss: 0.07363948971033096
2023-01-23 01:42:13.728786: step: 316/529, loss: 0.09577986598014832
2023-01-23 01:42:14.848266: step: 320/529, loss: 0.003931427374482155
2023-01-23 01:42:15.957057: step: 324/529, loss: 0.007610988803207874
2023-01-23 01:42:17.076437: step: 328/529, loss: 0.018694495782256126
2023-01-23 01:42:18.193973: step: 332/529, loss: 0.1604211926460266
2023-01-23 01:42:19.305371: step: 336/529, loss: 0.03756294399499893
2023-01-23 01:42:20.394796: step: 340/529, loss: 0.0027392387855798006
2023-01-23 01:42:21.519868: step: 344/529, loss: 0.022695541381835938
2023-01-23 01:42:22.625846: step: 348/529, loss: 0.05300109460949898
2023-01-23 01:42:23.715859: step: 352/529, loss: 0.0515655055642128
2023-01-23 01:42:24.821773: step: 356/529, loss: 0.06699886173009872
2023-01-23 01:42:25.934472: step: 360/529, loss: 0.02273263968527317
2023-01-23 01:42:27.026301: step: 364/529, loss: 0.009206676855683327
2023-01-23 01:42:28.136219: step: 368/529, loss: 0.022063683718442917
2023-01-23 01:42:29.264334: step: 372/529, loss: 0.021879959851503372
2023-01-23 01:42:30.362216: step: 376/529, loss: 0.006477165035903454
2023-01-23 01:42:31.493970: step: 380/529, loss: 0.029498625546693802
2023-01-23 01:42:32.591030: step: 384/529, loss: 0.04163990169763565
2023-01-23 01:42:33.696963: step: 388/529, loss: 0.05253582447767258
2023-01-23 01:42:34.834901: step: 392/529, loss: 0.03861827775835991
2023-01-23 01:42:35.938600: step: 396/529, loss: 0.012377738952636719
2023-01-23 01:42:37.026641: step: 400/529, loss: 0.03954572603106499
2023-01-23 01:42:38.124700: step: 404/529, loss: 0.02371964603662491
2023-01-23 01:42:39.254216: step: 408/529, loss: 0.0023258209694176912
2023-01-23 01:42:40.348179: step: 412/529, loss: 0.022819137200713158
2023-01-23 01:42:41.462322: step: 416/529, loss: 0.19572706520557404
2023-01-23 01:42:42.583324: step: 420/529, loss: 0.03498144447803497
2023-01-23 01:42:43.693845: step: 424/529, loss: 0.09448914974927902
2023-01-23 01:42:44.800872: step: 428/529, loss: 0.07198276370763779
2023-01-23 01:42:45.918075: step: 432/529, loss: 0.07265033572912216
2023-01-23 01:42:46.999384: step: 436/529, loss: 0.010719014331698418
2023-01-23 01:42:48.147008: step: 440/529, loss: 0.002009487245231867
2023-01-23 01:42:49.291980: step: 444/529, loss: 0.04184990003705025
2023-01-23 01:42:50.400496: step: 448/529, loss: 0.04704742506146431
2023-01-23 01:42:51.514409: step: 452/529, loss: 0.014574432745575905
2023-01-23 01:42:52.638080: step: 456/529, loss: 0.02465210109949112
2023-01-23 01:42:53.767660: step: 460/529, loss: 0.00980224646627903
2023-01-23 01:42:54.870320: step: 464/529, loss: 0.0031983377411961555
2023-01-23 01:42:56.008161: step: 468/529, loss: 0.0863095298409462
2023-01-23 01:42:57.117998: step: 472/529, loss: 0.025953197851777077
2023-01-23 01:42:58.232819: step: 476/529, loss: 0.008178329095244408
2023-01-23 01:42:59.365727: step: 480/529, loss: 0.021496010944247246
2023-01-23 01:43:00.472590: step: 484/529, loss: 0.06223573535680771
2023-01-23 01:43:01.562709: step: 488/529, loss: 0.15695570409297943
2023-01-23 01:43:02.677974: step: 492/529, loss: 0.024889133870601654
2023-01-23 01:43:03.778658: step: 496/529, loss: 0.01629314385354519
2023-01-23 01:43:04.892060: step: 500/529, loss: 0.029558181762695312
2023-01-23 01:43:06.022801: step: 504/529, loss: 0.009670638479292393
2023-01-23 01:43:07.172222: step: 508/529, loss: 0.031327057629823685
2023-01-23 01:43:08.277146: step: 512/529, loss: 0.31777894496917725
2023-01-23 01:43:09.380857: step: 516/529, loss: 0.01933746412396431
2023-01-23 01:43:10.499317: step: 520/529, loss: 0.03571300581097603
2023-01-23 01:43:11.613620: step: 524/529, loss: 0.05715503916144371
2023-01-23 01:43:12.699655: step: 528/529, loss: 0.007799291983246803
2023-01-23 01:43:13.843013: step: 532/529, loss: 0.1013161689043045
2023-01-23 01:43:14.941590: step: 536/529, loss: 0.02707824856042862
2023-01-23 01:43:16.067224: step: 540/529, loss: 0.04957713931798935
2023-01-23 01:43:17.156393: step: 544/529, loss: 0.0015176773304119706
2023-01-23 01:43:18.246316: step: 548/529, loss: 0.11670036613941193
2023-01-23 01:43:19.347695: step: 552/529, loss: 0.053476713597774506
2023-01-23 01:43:20.449257: step: 556/529, loss: 0.002906894776970148
2023-01-23 01:43:21.544977: step: 560/529, loss: 0.017011260613799095
2023-01-23 01:43:22.649686: step: 564/529, loss: 0.023801662027835846
2023-01-23 01:43:23.737401: step: 568/529, loss: 0.04368725046515465
2023-01-23 01:43:24.835747: step: 572/529, loss: 0.015525627881288528
2023-01-23 01:43:25.967688: step: 576/529, loss: 0.030176306143403053
2023-01-23 01:43:27.078903: step: 580/529, loss: 0.030388785526156425
2023-01-23 01:43:28.167229: step: 584/529, loss: 0.03607215732336044
2023-01-23 01:43:29.270275: step: 588/529, loss: 0.05016031116247177
2023-01-23 01:43:30.368446: step: 592/529, loss: 0.00012159347534179688
2023-01-23 01:43:31.459603: step: 596/529, loss: 0.020132923498749733
2023-01-23 01:43:32.562823: step: 600/529, loss: 0.017664004117250443
2023-01-23 01:43:33.690941: step: 604/529, loss: 0.0875476822257042
2023-01-23 01:43:34.788228: step: 608/529, loss: 0.008771324530243874
2023-01-23 01:43:35.900141: step: 612/529, loss: 0.018830489367246628
2023-01-23 01:43:37.030349: step: 616/529, loss: 0.07054519653320312
2023-01-23 01:43:38.176125: step: 620/529, loss: 0.01978626288473606
2023-01-23 01:43:39.294185: step: 624/529, loss: 0.011927127838134766
2023-01-23 01:43:40.448759: step: 628/529, loss: 0.06222324073314667
2023-01-23 01:43:41.591382: step: 632/529, loss: 0.022385025396943092
2023-01-23 01:43:42.693307: step: 636/529, loss: 0.011860180646181107
2023-01-23 01:43:43.822197: step: 640/529, loss: 0.05222740024328232
2023-01-23 01:43:44.924478: step: 644/529, loss: 0.03897275775671005
2023-01-23 01:43:46.073124: step: 648/529, loss: 0.11284789443016052
2023-01-23 01:43:47.177254: step: 652/529, loss: 0.006290435791015625
2023-01-23 01:43:48.298791: step: 656/529, loss: 0.02301778830587864
2023-01-23 01:43:49.470736: step: 660/529, loss: 0.07369986176490784
2023-01-23 01:43:50.570902: step: 664/529, loss: 0.013823938556015491
2023-01-23 01:43:51.681085: step: 668/529, loss: 0.03308677673339844
2023-01-23 01:43:52.794054: step: 672/529, loss: 0.09483185410499573
2023-01-23 01:43:53.906890: step: 676/529, loss: 0.0015774727798998356
2023-01-23 01:43:55.053561: step: 680/529, loss: 0.02214374579489231
2023-01-23 01:43:56.183097: step: 684/529, loss: 0.035392455756664276
2023-01-23 01:43:57.287358: step: 688/529, loss: 0.030090808868408203
2023-01-23 01:43:58.414318: step: 692/529, loss: 0.005709934514015913
2023-01-23 01:43:59.538359: step: 696/529, loss: 0.06359271705150604
2023-01-23 01:44:00.654278: step: 700/529, loss: 0.043273165822029114
2023-01-23 01:44:01.764285: step: 704/529, loss: 0.07162122428417206
2023-01-23 01:44:02.872728: step: 708/529, loss: 0.033919334411621094
2023-01-23 01:44:04.009543: step: 712/529, loss: 0.024324918165802956
2023-01-23 01:44:05.148514: step: 716/529, loss: 0.011709785088896751
2023-01-23 01:44:06.272134: step: 720/529, loss: 0.05855837091803551
2023-01-23 01:44:07.409912: step: 724/529, loss: 0.04289679229259491
2023-01-23 01:44:08.507682: step: 728/529, loss: 0.01994934119284153
2023-01-23 01:44:09.618568: step: 732/529, loss: 0.02031421661376953
2023-01-23 01:44:10.732482: step: 736/529, loss: 0.0349552184343338
2023-01-23 01:44:11.829643: step: 740/529, loss: 0.01612529717385769
2023-01-23 01:44:12.922459: step: 744/529, loss: 0.019127940759062767
2023-01-23 01:44:14.097640: step: 748/529, loss: 0.02261028252542019
2023-01-23 01:44:15.199475: step: 752/529, loss: 0.011346054263412952
2023-01-23 01:44:16.324462: step: 756/529, loss: 0.004826259799301624
2023-01-23 01:44:17.440675: step: 760/529, loss: 0.03502840921282768
2023-01-23 01:44:18.559222: step: 764/529, loss: 0.01723918877542019
2023-01-23 01:44:19.679101: step: 768/529, loss: 0.10384960472583771
2023-01-23 01:44:20.808498: step: 772/529, loss: 0.050301648676395416
2023-01-23 01:44:21.915822: step: 776/529, loss: 0.020436907187104225
2023-01-23 01:44:23.014857: step: 780/529, loss: 0.012467408552765846
2023-01-23 01:44:24.130356: step: 784/529, loss: 0.08142328262329102
2023-01-23 01:44:25.247607: step: 788/529, loss: 0.09496984630823135
2023-01-23 01:44:26.359632: step: 792/529, loss: 0.02488865703344345
2023-01-23 01:44:27.475906: step: 796/529, loss: 0.07901573181152344
2023-01-23 01:44:28.590610: step: 800/529, loss: 0.014664888381958008
2023-01-23 01:44:29.703912: step: 804/529, loss: 0.045256901532411575
2023-01-23 01:44:30.829287: step: 808/529, loss: 0.023755645379424095
2023-01-23 01:44:31.941763: step: 812/529, loss: 0.016444873064756393
2023-01-23 01:44:33.035863: step: 816/529, loss: 1.7624906301498413
2023-01-23 01:44:34.121795: step: 820/529, loss: 0.002922630403190851
2023-01-23 01:44:35.212472: step: 824/529, loss: 0.010241365991532803
2023-01-23 01:44:36.344357: step: 828/529, loss: 0.034173011779785156
2023-01-23 01:44:37.444388: step: 832/529, loss: 0.008757353760302067
2023-01-23 01:44:38.575848: step: 836/529, loss: 0.07103338092565536
2023-01-23 01:44:39.679658: step: 840/529, loss: 0.05490932613611221
2023-01-23 01:44:40.766045: step: 844/529, loss: 0.022204017266631126
2023-01-23 01:44:41.859437: step: 848/529, loss: 0.011773490346968174
2023-01-23 01:44:42.977351: step: 852/529, loss: 0.013375520706176758
2023-01-23 01:44:44.096001: step: 856/529, loss: 0.002599048661068082
2023-01-23 01:44:45.187097: step: 860/529, loss: 0.03408966213464737
2023-01-23 01:44:46.286641: step: 864/529, loss: 0.12001418322324753
2023-01-23 01:44:47.377376: step: 868/529, loss: 0.14384213089942932
2023-01-23 01:44:48.498517: step: 872/529, loss: 0.014993762597441673
2023-01-23 01:44:49.606815: step: 876/529, loss: 0.0626152977347374
2023-01-23 01:44:50.709386: step: 880/529, loss: 0.0652843490242958
2023-01-23 01:44:51.824525: step: 884/529, loss: 0.10830879211425781
2023-01-23 01:44:52.905158: step: 888/529, loss: 0.13697996735572815
2023-01-23 01:44:54.026639: step: 892/529, loss: 0.3752841353416443
2023-01-23 01:44:55.157806: step: 896/529, loss: 0.05899696797132492
2023-01-23 01:44:56.279115: step: 900/529, loss: 0.03325328975915909
2023-01-23 01:44:57.406255: step: 904/529, loss: 0.11066999286413193
2023-01-23 01:44:58.544029: step: 908/529, loss: 0.060028839856386185
2023-01-23 01:44:59.634557: step: 912/529, loss: 0.01938605308532715
2023-01-23 01:45:00.740477: step: 916/529, loss: 0.0058522941544651985
2023-01-23 01:45:01.847576: step: 920/529, loss: 0.014265060424804688
2023-01-23 01:45:02.944308: step: 924/529, loss: 0.017250824719667435
2023-01-23 01:45:04.060616: step: 928/529, loss: 0.032796718180179596
2023-01-23 01:45:05.148574: step: 932/529, loss: 0.04005365073680878
2023-01-23 01:45:06.288691: step: 936/529, loss: 0.04614553228020668
2023-01-23 01:45:07.365948: step: 940/529, loss: 0.14798007905483246
2023-01-23 01:45:08.443572: step: 944/529, loss: 0.036196134984493256
2023-01-23 01:45:09.550369: step: 948/529, loss: 0.029706383123993874
2023-01-23 01:45:10.649930: step: 952/529, loss: 0.04193758964538574
2023-01-23 01:45:11.765284: step: 956/529, loss: 0.021543120965361595
2023-01-23 01:45:12.878508: step: 960/529, loss: 0.01782970502972603
2023-01-23 01:45:14.036038: step: 964/529, loss: 0.03339047729969025
2023-01-23 01:45:15.124179: step: 968/529, loss: 0.341751366853714
2023-01-23 01:45:16.234902: step: 972/529, loss: 0.02943885326385498
2023-01-23 01:45:17.346734: step: 976/529, loss: 0.006870842073112726
2023-01-23 01:45:18.466628: step: 980/529, loss: 0.0309968963265419
2023-01-23 01:45:19.572187: step: 984/529, loss: 0.25331854820251465
2023-01-23 01:45:20.688541: step: 988/529, loss: 0.03831310197710991
2023-01-23 01:45:21.779729: step: 992/529, loss: 0.0008615494007244706
2023-01-23 01:45:22.858664: step: 996/529, loss: 0.006113243289291859
2023-01-23 01:45:23.986510: step: 1000/529, loss: 0.7010480165481567
2023-01-23 01:45:25.110035: step: 1004/529, loss: 0.11332845687866211
2023-01-23 01:45:26.192538: step: 1008/529, loss: 0.05447997897863388
2023-01-23 01:45:27.306888: step: 1012/529, loss: 0.007079887203872204
2023-01-23 01:45:28.400056: step: 1016/529, loss: 0.009257650002837181
2023-01-23 01:45:29.559785: step: 1020/529, loss: 0.19070139527320862
2023-01-23 01:45:30.660225: step: 1024/529, loss: 0.01338118314743042
2023-01-23 01:45:31.758860: step: 1028/529, loss: 0.001272869179956615
2023-01-23 01:45:32.870660: step: 1032/529, loss: 0.06684227287769318
2023-01-23 01:45:33.996871: step: 1036/529, loss: 0.01168808899819851
2023-01-23 01:45:35.106532: step: 1040/529, loss: 0.32215794920921326
2023-01-23 01:45:36.215890: step: 1044/529, loss: 0.0520719513297081
2023-01-23 01:45:37.320824: step: 1048/529, loss: 0.12193412333726883
2023-01-23 01:45:38.431286: step: 1052/529, loss: 0.06630926579236984
2023-01-23 01:45:39.573537: step: 1056/529, loss: 0.011602640151977539
2023-01-23 01:45:40.683965: step: 1060/529, loss: 0.05215277522802353
2023-01-23 01:45:41.794695: step: 1064/529, loss: 0.018575571477413177
2023-01-23 01:45:42.921760: step: 1068/529, loss: 0.004266071133315563
2023-01-23 01:45:44.006391: step: 1072/529, loss: 0.08493126928806305
2023-01-23 01:45:45.134790: step: 1076/529, loss: 0.035504911094903946
2023-01-23 01:45:46.243140: step: 1080/529, loss: 0.03413458168506622
2023-01-23 01:45:47.347144: step: 1084/529, loss: 0.055048421025276184
2023-01-23 01:45:48.447315: step: 1088/529, loss: 0.06059369817376137
2023-01-23 01:45:49.563254: step: 1092/529, loss: 0.004771423526108265
2023-01-23 01:45:50.664234: step: 1096/529, loss: 0.0011592864757403731
2023-01-23 01:45:51.763458: step: 1100/529, loss: 0.49570825695991516
2023-01-23 01:45:52.886668: step: 1104/529, loss: 0.09929446876049042
2023-01-23 01:45:54.018355: step: 1108/529, loss: 0.022623255848884583
2023-01-23 01:45:55.152881: step: 1112/529, loss: 0.2396383285522461
2023-01-23 01:45:56.292294: step: 1116/529, loss: 0.0005959034315310419
2023-01-23 01:45:57.365878: step: 1120/529, loss: 0.013457298278808594
2023-01-23 01:45:58.478762: step: 1124/529, loss: 0.06752882152795792
2023-01-23 01:45:59.590585: step: 1128/529, loss: 0.006843948271125555
2023-01-23 01:46:00.721583: step: 1132/529, loss: 0.10009326785802841
2023-01-23 01:46:01.835017: step: 1136/529, loss: 0.02182168886065483
2023-01-23 01:46:02.937342: step: 1140/529, loss: 0.00824661273509264
2023-01-23 01:46:04.085171: step: 1144/529, loss: 0.08958091586828232
2023-01-23 01:46:05.192989: step: 1148/529, loss: 0.09390156716108322
2023-01-23 01:46:06.314289: step: 1152/529, loss: 0.06819095462560654
2023-01-23 01:46:07.419413: step: 1156/529, loss: 0.2882021963596344
2023-01-23 01:46:08.564717: step: 1160/529, loss: 0.04466400295495987
2023-01-23 01:46:09.661465: step: 1164/529, loss: 0.1249622330069542
2023-01-23 01:46:10.777895: step: 1168/529, loss: 0.01870594173669815
2023-01-23 01:46:11.887464: step: 1172/529, loss: 0.10197696834802628
2023-01-23 01:46:12.990044: step: 1176/529, loss: 0.07632827758789062
2023-01-23 01:46:14.098220: step: 1180/529, loss: 0.013493537902832031
2023-01-23 01:46:15.186816: step: 1184/529, loss: 0.04766673967242241
2023-01-23 01:46:16.302088: step: 1188/529, loss: 0.041199587285518646
2023-01-23 01:46:17.409826: step: 1192/529, loss: 0.06494684517383575
2023-01-23 01:46:18.552162: step: 1196/529, loss: 0.0155525216832757
2023-01-23 01:46:19.663362: step: 1200/529, loss: 0.012423325330018997
2023-01-23 01:46:20.768299: step: 1204/529, loss: 0.0001695632963674143
2023-01-23 01:46:21.880214: step: 1208/529, loss: 0.07731194794178009
2023-01-23 01:46:23.002761: step: 1212/529, loss: 0.017555713653564453
2023-01-23 01:46:24.091194: step: 1216/529, loss: 0.00043268201989121735
2023-01-23 01:46:25.211476: step: 1220/529, loss: 0.030835531651973724
2023-01-23 01:46:26.335705: step: 1224/529, loss: 0.2707158923149109
2023-01-23 01:46:27.458006: step: 1228/529, loss: 0.025734711438417435
2023-01-23 01:46:28.564022: step: 1232/529, loss: 0.0034225464332848787
2023-01-23 01:46:29.681365: step: 1236/529, loss: 0.004409885499626398
2023-01-23 01:46:30.775721: step: 1240/529, loss: 0.1639002412557602
2023-01-23 01:46:31.894945: step: 1244/529, loss: 0.11163682490587234
2023-01-23 01:46:33.012885: step: 1248/529, loss: 0.004207706544548273
2023-01-23 01:46:34.105565: step: 1252/529, loss: 0.0468423031270504
2023-01-23 01:46:35.213119: step: 1256/529, loss: 0.026732921600341797
2023-01-23 01:46:36.319242: step: 1260/529, loss: 0.0011005401611328125
2023-01-23 01:46:37.441966: step: 1264/529, loss: 0.0655902847647667
2023-01-23 01:46:38.532051: step: 1268/529, loss: 0.04583730548620224
2023-01-23 01:46:39.618467: step: 1272/529, loss: 0.008058547973632812
2023-01-23 01:46:40.694631: step: 1276/529, loss: 0.001617431640625
2023-01-23 01:46:41.821024: step: 1280/529, loss: 0.1286485642194748
2023-01-23 01:46:42.928577: step: 1284/529, loss: 0.37244758009910583
2023-01-23 01:46:44.057032: step: 1288/529, loss: 0.058251574635505676
2023-01-23 01:46:45.193150: step: 1292/529, loss: 0.012123584747314453
2023-01-23 01:46:46.298515: step: 1296/529, loss: 0.041721489280462265
2023-01-23 01:46:47.416158: step: 1300/529, loss: 0.0674106627702713
2023-01-23 01:46:48.541321: step: 1304/529, loss: 0.056020356714725494
2023-01-23 01:46:49.659760: step: 1308/529, loss: 0.029988478869199753
2023-01-23 01:46:50.765682: step: 1312/529, loss: 0.013033008202910423
2023-01-23 01:46:51.889217: step: 1316/529, loss: 0.049913980066776276
2023-01-23 01:46:52.986134: step: 1320/529, loss: 0.03180895000696182
2023-01-23 01:46:54.066083: step: 1324/529, loss: 0.032746508717536926
2023-01-23 01:46:55.188169: step: 1328/529, loss: 0.06756601482629776
2023-01-23 01:46:56.288540: step: 1332/529, loss: 0.028934193775057793
2023-01-23 01:46:57.379663: step: 1336/529, loss: 0.0183321014046669
2023-01-23 01:46:58.502392: step: 1340/529, loss: 0.025823401287198067
2023-01-23 01:46:59.635705: step: 1344/529, loss: 0.013457298278808594
2023-01-23 01:47:00.739254: step: 1348/529, loss: 0.11250286549329758
2023-01-23 01:47:01.853012: step: 1352/529, loss: 0.031952571123838425
2023-01-23 01:47:02.976968: step: 1356/529, loss: 0.00920867919921875
2023-01-23 01:47:04.097842: step: 1360/529, loss: 0.01450414676219225
2023-01-23 01:47:05.204018: step: 1364/529, loss: 0.11879067122936249
2023-01-23 01:47:06.328547: step: 1368/529, loss: 0.020023442804813385
2023-01-23 01:47:07.444472: step: 1372/529, loss: 0.273714542388916
2023-01-23 01:47:08.547458: step: 1376/529, loss: 0.04705781862139702
2023-01-23 01:47:09.658785: step: 1380/529, loss: 0.03726167976856232
2023-01-23 01:47:10.746988: step: 1384/529, loss: 0.024841928854584694
2023-01-23 01:47:11.875014: step: 1388/529, loss: 0.008778381161391735
2023-01-23 01:47:12.979391: step: 1392/529, loss: 0.028741836547851562
2023-01-23 01:47:14.108609: step: 1396/529, loss: 0.04222536087036133
2023-01-23 01:47:15.201720: step: 1400/529, loss: 0.003799915313720703
2023-01-23 01:47:16.313533: step: 1404/529, loss: 0.08891496807336807
2023-01-23 01:47:17.403244: step: 1408/529, loss: 0.01604478433728218
2023-01-23 01:47:18.522716: step: 1412/529, loss: 0.14737826585769653
2023-01-23 01:47:19.648702: step: 1416/529, loss: 0.118444062769413
2023-01-23 01:47:20.743482: step: 1420/529, loss: 0.07689027488231659
2023-01-23 01:47:21.870545: step: 1424/529, loss: 0.08351021260023117
2023-01-23 01:47:22.988308: step: 1428/529, loss: 0.7681671380996704
2023-01-23 01:47:24.100498: step: 1432/529, loss: 0.05300083011388779
2023-01-23 01:47:25.194870: step: 1436/529, loss: 0.015417384915053844
2023-01-23 01:47:26.287865: step: 1440/529, loss: 0.08357041329145432
2023-01-23 01:47:27.399200: step: 1444/529, loss: 0.060283709317445755
2023-01-23 01:47:28.505957: step: 1448/529, loss: 0.07480278611183167
2023-01-23 01:47:29.614291: step: 1452/529, loss: 0.0731332004070282
2023-01-23 01:47:30.703427: step: 1456/529, loss: 0.05331382900476456
2023-01-23 01:47:31.826378: step: 1460/529, loss: 0.6107146739959717
2023-01-23 01:47:32.932605: step: 1464/529, loss: 0.02226409874856472
2023-01-23 01:47:34.035712: step: 1468/529, loss: 0.0247986800968647
2023-01-23 01:47:35.171292: step: 1472/529, loss: 0.03485984727740288
2023-01-23 01:47:36.286327: step: 1476/529, loss: 0.07304602861404419
2023-01-23 01:47:37.381113: step: 1480/529, loss: 0.08118553459644318
2023-01-23 01:47:38.498487: step: 1484/529, loss: 0.050348568707704544
2023-01-23 01:47:39.596223: step: 1488/529, loss: 0.03297467157244682
2023-01-23 01:47:40.705132: step: 1492/529, loss: 0.045783109962940216
2023-01-23 01:47:41.793311: step: 1496/529, loss: 0.047002602368593216
2023-01-23 01:47:42.911175: step: 1500/529, loss: 0.006312465760856867
2023-01-23 01:47:44.026240: step: 1504/529, loss: 0.010353517718613148
2023-01-23 01:47:45.131690: step: 1508/529, loss: 0.0301087386906147
2023-01-23 01:47:46.243501: step: 1512/529, loss: 0.011759853921830654
2023-01-23 01:47:47.387557: step: 1516/529, loss: 0.015729617327451706
2023-01-23 01:47:48.534415: step: 1520/529, loss: 0.013049221597611904
2023-01-23 01:47:49.656499: step: 1524/529, loss: 0.034577276557683945
2023-01-23 01:47:50.811492: step: 1528/529, loss: 0.01103891059756279
2023-01-23 01:47:51.920580: step: 1532/529, loss: 0.014093780890107155
2023-01-23 01:47:53.031858: step: 1536/529, loss: 0.020003415644168854
2023-01-23 01:47:54.121045: step: 1540/529, loss: 0.02118401601910591
2023-01-23 01:47:55.229631: step: 1544/529, loss: 0.024834156036376953
2023-01-23 01:47:56.380424: step: 1548/529, loss: 0.02395954169332981
2023-01-23 01:47:57.478053: step: 1552/529, loss: 0.03550539165735245
2023-01-23 01:47:58.614421: step: 1556/529, loss: 0.019602488726377487
2023-01-23 01:47:59.741871: step: 1560/529, loss: 0.0151703841984272
2023-01-23 01:48:00.865621: step: 1564/529, loss: 0.03718709945678711
2023-01-23 01:48:01.987099: step: 1568/529, loss: 0.04355449602007866
2023-01-23 01:48:03.110954: step: 1572/529, loss: 0.0421999916434288
2023-01-23 01:48:04.240469: step: 1576/529, loss: 0.03545551374554634
2023-01-23 01:48:05.355194: step: 1580/529, loss: 0.030100345611572266
2023-01-23 01:48:06.486357: step: 1584/529, loss: 0.01910381391644478
2023-01-23 01:48:07.594792: step: 1588/529, loss: 0.02902050130069256
2023-01-23 01:48:08.713771: step: 1592/529, loss: 0.06081266701221466
2023-01-23 01:48:09.818143: step: 1596/529, loss: 0.004420375917106867
2023-01-23 01:48:10.913703: step: 1600/529, loss: 0.014257130213081837
2023-01-23 01:48:12.013289: step: 1604/529, loss: 0.04803962633013725
2023-01-23 01:48:13.132031: step: 1608/529, loss: 0.04708156734704971
2023-01-23 01:48:14.288161: step: 1612/529, loss: 0.01819610595703125
2023-01-23 01:48:15.404784: step: 1616/529, loss: 0.0681610107421875
2023-01-23 01:48:16.526860: step: 1620/529, loss: 0.04678454250097275
2023-01-23 01:48:17.645334: step: 1624/529, loss: 0.06651964783668518
2023-01-23 01:48:18.764630: step: 1628/529, loss: 0.020511532202363014
2023-01-23 01:48:19.865305: step: 1632/529, loss: 0.08219242095947266
2023-01-23 01:48:20.979708: step: 1636/529, loss: 0.03554592281579971
2023-01-23 01:48:22.066153: step: 1640/529, loss: 0.01932506635785103
2023-01-23 01:48:23.189602: step: 1644/529, loss: 0.008379315957427025
2023-01-23 01:48:24.305853: step: 1648/529, loss: 0.010648544877767563
2023-01-23 01:48:25.396026: step: 1652/529, loss: 0.03567094728350639
2023-01-23 01:48:26.528380: step: 1656/529, loss: 0.043998800218105316
2023-01-23 01:48:27.690478: step: 1660/529, loss: 0.07056055217981339
2023-01-23 01:48:28.811400: step: 1664/529, loss: 0.010371970944106579
2023-01-23 01:48:29.956216: step: 1668/529, loss: 0.03254912048578262
2023-01-23 01:48:31.035293: step: 1672/529, loss: 0.028117896988987923
2023-01-23 01:48:32.126112: step: 1676/529, loss: 0.11690196394920349
2023-01-23 01:48:33.273469: step: 1680/529, loss: 0.0931786522269249
2023-01-23 01:48:34.357661: step: 1684/529, loss: 0.006766319274902344
2023-01-23 01:48:35.475695: step: 1688/529, loss: 0.07551456242799759
2023-01-23 01:48:36.572676: step: 1692/529, loss: 0.17780761420726776
2023-01-23 01:48:37.705607: step: 1696/529, loss: 0.060100436210632324
2023-01-23 01:48:38.839620: step: 1700/529, loss: 0.024545002728700638
2023-01-23 01:48:39.949335: step: 1704/529, loss: 0.0704471617937088
2023-01-23 01:48:41.060628: step: 1708/529, loss: 0.023421861231327057
2023-01-23 01:48:42.149650: step: 1712/529, loss: 0.013410281389951706
2023-01-23 01:48:43.240242: step: 1716/529, loss: 0.05588135868310928
2023-01-23 01:48:44.350195: step: 1720/529, loss: 0.007395029067993164
2023-01-23 01:48:45.479922: step: 1724/529, loss: 0.1294885128736496
2023-01-23 01:48:46.620904: step: 1728/529, loss: 0.04471225664019585
2023-01-23 01:48:47.740924: step: 1732/529, loss: 0.05116519704461098
2023-01-23 01:48:48.874978: step: 1736/529, loss: 0.08819885551929474
2023-01-23 01:48:49.994449: step: 1740/529, loss: 0.17374782264232635
2023-01-23 01:48:51.079225: step: 1744/529, loss: 0.0027803422417491674
2023-01-23 01:48:52.198375: step: 1748/529, loss: 0.002521610353142023
2023-01-23 01:48:53.313021: step: 1752/529, loss: 0.0056362152099609375
2023-01-23 01:48:54.431551: step: 1756/529, loss: 0.01562805101275444
2023-01-23 01:48:55.531410: step: 1760/529, loss: 0.04769149050116539
2023-01-23 01:48:56.648320: step: 1764/529, loss: 0.012091398239135742
2023-01-23 01:48:57.743251: step: 1768/529, loss: 0.015734482556581497
2023-01-23 01:48:58.869288: step: 1772/529, loss: 0.07509279996156693
2023-01-23 01:48:59.983680: step: 1776/529, loss: 0.1594143956899643
2023-01-23 01:49:01.135076: step: 1780/529, loss: 0.013957023620605469
2023-01-23 01:49:02.234758: step: 1784/529, loss: 5.817413330078125e-05
2023-01-23 01:49:03.341369: step: 1788/529, loss: 0.1091470792889595
2023-01-23 01:49:04.469868: step: 1792/529, loss: 0.1412241905927658
2023-01-23 01:49:05.608169: step: 1796/529, loss: 0.015224265865981579
2023-01-23 01:49:06.750438: step: 1800/529, loss: 0.14745500683784485
2023-01-23 01:49:07.865909: step: 1804/529, loss: 0.003253340721130371
2023-01-23 01:49:08.956298: step: 1808/529, loss: 0.01631612703204155
2023-01-23 01:49:10.088791: step: 1812/529, loss: 0.011667251586914062
2023-01-23 01:49:11.221049: step: 1816/529, loss: 0.021270085126161575
2023-01-23 01:49:12.437348: step: 1820/529, loss: 0.3226621448993683
2023-01-23 01:49:13.552263: step: 1824/529, loss: 0.11391735076904297
2023-01-23 01:49:14.649122: step: 1828/529, loss: 0.028792666271328926
2023-01-23 01:49:15.750810: step: 1832/529, loss: 0.018990231677889824
2023-01-23 01:49:16.874558: step: 1836/529, loss: 0.003859901335090399
2023-01-23 01:49:17.948876: step: 1840/529, loss: 0.054879650473594666
2023-01-23 01:49:19.069428: step: 1844/529, loss: 0.08546887338161469
2023-01-23 01:49:20.170313: step: 1848/529, loss: 0.020268870517611504
2023-01-23 01:49:21.275761: step: 1852/529, loss: 0.13133297860622406
2023-01-23 01:49:22.361563: step: 1856/529, loss: 0.004431438632309437
2023-01-23 01:49:23.480921: step: 1860/529, loss: 0.04313831031322479
2023-01-23 01:49:24.587329: step: 1864/529, loss: 0.11732502281665802
2023-01-23 01:49:25.683275: step: 1868/529, loss: 0.0823608934879303
2023-01-23 01:49:26.774541: step: 1872/529, loss: 0.06921844929456711
2023-01-23 01:49:27.862683: step: 1876/529, loss: 0.18772143125534058
2023-01-23 01:49:28.980608: step: 1880/529, loss: 0.023085784167051315
2023-01-23 01:49:30.086463: step: 1884/529, loss: 0.0010964394314214587
2023-01-23 01:49:31.207442: step: 1888/529, loss: 0.04357624053955078
2023-01-23 01:49:32.308561: step: 1892/529, loss: 0.09856834262609482
2023-01-23 01:49:33.460874: step: 1896/529, loss: 0.037571147084236145
2023-01-23 01:49:34.622328: step: 1900/529, loss: 0.03520956262946129
2023-01-23 01:49:35.714737: step: 1904/529, loss: 0.08882074803113937
2023-01-23 01:49:36.840640: step: 1908/529, loss: 0.02763180620968342
2023-01-23 01:49:37.937664: step: 1912/529, loss: 0.15327243506908417
2023-01-23 01:49:39.060444: step: 1916/529, loss: 0.11791391670703888
2023-01-23 01:49:40.173580: step: 1920/529, loss: 0.018830109387636185
2023-01-23 01:49:41.285146: step: 1924/529, loss: 0.08174372464418411
2023-01-23 01:49:42.418735: step: 1928/529, loss: 0.06939716637134552
2023-01-23 01:49:43.519431: step: 1932/529, loss: 0.05230093002319336
2023-01-23 01:49:44.616815: step: 1936/529, loss: 0.17533046007156372
2023-01-23 01:49:45.712403: step: 1940/529, loss: 0.007310295477509499
2023-01-23 01:49:46.824245: step: 1944/529, loss: 0.014315605163574219
2023-01-23 01:49:47.945807: step: 1948/529, loss: 0.023603271692991257
2023-01-23 01:49:49.068908: step: 1952/529, loss: 0.002918052952736616
2023-01-23 01:49:50.156675: step: 1956/529, loss: 0.003342056181281805
2023-01-23 01:49:51.268489: step: 1960/529, loss: 0.08848772197961807
2023-01-23 01:49:52.369275: step: 1964/529, loss: 0.06822852790355682
2023-01-23 01:49:53.476997: step: 1968/529, loss: 0.09141135215759277
2023-01-23 01:49:54.573034: step: 1972/529, loss: 0.012217319570481777
2023-01-23 01:49:55.712913: step: 1976/529, loss: 0.06513891369104385
2023-01-23 01:49:56.804786: step: 1980/529, loss: 0.0016072273720055819
2023-01-23 01:49:57.917924: step: 1984/529, loss: 0.0009511947864666581
2023-01-23 01:49:58.994294: step: 1988/529, loss: 0.000521802925504744
2023-01-23 01:50:00.091949: step: 1992/529, loss: 0.06409807503223419
2023-01-23 01:50:01.191204: step: 1996/529, loss: 0.024903012439608574
2023-01-23 01:50:02.302720: step: 2000/529, loss: 0.006233835127204657
2023-01-23 01:50:03.413496: step: 2004/529, loss: 0.00327816023491323
2023-01-23 01:50:04.514968: step: 2008/529, loss: 0.000973129237536341
2023-01-23 01:50:05.645023: step: 2012/529, loss: 0.15951919555664062
2023-01-23 01:50:06.759270: step: 2016/529, loss: 0.02843017503619194
2023-01-23 01:50:07.888455: step: 2020/529, loss: 0.07817402482032776
2023-01-23 01:50:09.025549: step: 2024/529, loss: 0.19659671187400818
2023-01-23 01:50:10.118354: step: 2028/529, loss: 0.007664203643798828
2023-01-23 01:50:11.205017: step: 2032/529, loss: 0.04596920311450958
2023-01-23 01:50:12.278317: step: 2036/529, loss: 0.02553539350628853
2023-01-23 01:50:13.388513: step: 2040/529, loss: 0.0249815471470356
2023-01-23 01:50:14.486936: step: 2044/529, loss: 0.007485067937523127
2023-01-23 01:50:15.592615: step: 2048/529, loss: 0.04357624053955078
2023-01-23 01:50:16.699468: step: 2052/529, loss: 0.07949686050415039
2023-01-23 01:50:17.833299: step: 2056/529, loss: 0.00826110877096653
2023-01-23 01:50:18.948261: step: 2060/529, loss: 0.0363314151763916
2023-01-23 01:50:20.065589: step: 2064/529, loss: 0.018836308270692825
2023-01-23 01:50:21.210371: step: 2068/529, loss: 0.012301159091293812
2023-01-23 01:50:22.335733: step: 2072/529, loss: 0.1309131681919098
2023-01-23 01:50:23.472132: step: 2076/529, loss: 0.03051462210714817
2023-01-23 01:50:24.590829: step: 2080/529, loss: 0.0825420394539833
2023-01-23 01:50:25.697246: step: 2084/529, loss: 0.05312299728393555
2023-01-23 01:50:26.786335: step: 2088/529, loss: 0.017402267083525658
2023-01-23 01:50:27.877061: step: 2092/529, loss: 0.011228561401367188
2023-01-23 01:50:28.996666: step: 2096/529, loss: 0.011606263928115368
2023-01-23 01:50:30.074816: step: 2100/529, loss: 0.005156659986823797
2023-01-23 01:50:31.179401: step: 2104/529, loss: 0.021921921521425247
2023-01-23 01:50:32.288527: step: 2108/529, loss: 0.09455004334449768
2023-01-23 01:50:33.362910: step: 2112/529, loss: 0.0348484069108963
2023-01-23 01:50:34.470285: step: 2116/529, loss: 0.0025954246520996094
==================================================
Loss: 0.057
--------------------
Dev: {'event': {'p': 0.5737211634904714, 'r': 0.7616511318242344, 'f1': 0.6544622425629291}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6309523809523809, 'r': 0.7776523702031602, 'f1': 0.6966632962588473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5853658536585366, 'r': 0.8888888888888888, 'f1': 0.7058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.5694444444444444, 'r': 0.6507936507936508, 'f1': 0.6074074074074073}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.4090909090909091, 'r': 0.5, 'f1': 0.45}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:51:14.508996: step: 4/529, loss: 0.28542229533195496
2023-01-23 01:51:15.656843: step: 8/529, loss: 0.0042168619111180305
2023-01-23 01:51:16.775609: step: 12/529, loss: 0.04806122928857803
2023-01-23 01:51:17.900473: step: 16/529, loss: 0.017220783978700638
2023-01-23 01:51:19.004559: step: 20/529, loss: 0.0016108989948406816
2023-01-23 01:51:20.126374: step: 24/529, loss: 0.0064242840744555
2023-01-23 01:51:21.258646: step: 28/529, loss: 0.06656856834888458
2023-01-23 01:51:22.370681: step: 32/529, loss: 0.005133247002959251
2023-01-23 01:51:23.468173: step: 36/529, loss: 0.038977812975645065
2023-01-23 01:51:24.594993: step: 40/529, loss: 0.0028447629883885384
2023-01-23 01:51:25.710402: step: 44/529, loss: 0.06085243076086044
2023-01-23 01:51:26.825150: step: 48/529, loss: 0.026661396026611328
2023-01-23 01:51:27.923597: step: 52/529, loss: 0.10043134540319443
2023-01-23 01:51:29.023249: step: 56/529, loss: 0.014155769720673561
2023-01-23 01:51:30.116230: step: 60/529, loss: 0.009986400604248047
2023-01-23 01:51:31.202681: step: 64/529, loss: 0.009379482828080654
2023-01-23 01:51:32.306700: step: 68/529, loss: 0.02329711988568306
2023-01-23 01:51:33.416180: step: 72/529, loss: 0.017309190705418587
2023-01-23 01:51:34.513225: step: 76/529, loss: 0.03655261918902397
2023-01-23 01:51:35.634038: step: 80/529, loss: 0.0006664872053079307
2023-01-23 01:51:36.763000: step: 84/529, loss: 0.0023785592056810856
2023-01-23 01:51:37.882229: step: 88/529, loss: 0.044165994971990585
2023-01-23 01:51:38.986681: step: 92/529, loss: 0.010099363513290882
2023-01-23 01:51:40.118192: step: 96/529, loss: 0.007143402472138405
2023-01-23 01:51:41.229699: step: 100/529, loss: 0.009181499481201172
2023-01-23 01:51:42.373340: step: 104/529, loss: 0.036187078803777695
2023-01-23 01:51:43.481236: step: 108/529, loss: 0.014006709679961205
2023-01-23 01:51:44.617223: step: 112/529, loss: 0.0037601948715746403
2023-01-23 01:51:45.728918: step: 116/529, loss: 0.002389908069744706
2023-01-23 01:51:46.835114: step: 120/529, loss: 0.00984582956880331
2023-01-23 01:51:47.965501: step: 124/529, loss: 0.06060028076171875
2023-01-23 01:51:49.099236: step: 128/529, loss: 0.021651554852724075
2023-01-23 01:51:50.239017: step: 132/529, loss: 0.02246398851275444
2023-01-23 01:51:51.335758: step: 136/529, loss: 0.027455855160951614
2023-01-23 01:51:52.419166: step: 140/529, loss: 0.03280293941497803
2023-01-23 01:51:53.555710: step: 144/529, loss: 0.04183788597583771
2023-01-23 01:51:54.652127: step: 148/529, loss: 0.47634103894233704
2023-01-23 01:51:55.744464: step: 152/529, loss: 0.007531070616096258
2023-01-23 01:51:56.854529: step: 156/529, loss: 0.016284942626953125
2023-01-23 01:51:57.959282: step: 160/529, loss: 0.0007408142555505037
2023-01-23 01:51:59.078945: step: 164/529, loss: 0.15402469038963318
2023-01-23 01:52:00.220658: step: 168/529, loss: 0.04643745720386505
2023-01-23 01:52:01.336860: step: 172/529, loss: 0.030351685360074043
2023-01-23 01:52:02.435868: step: 176/529, loss: 0.000744724296964705
2023-01-23 01:52:03.545690: step: 180/529, loss: 0.018285728991031647
2023-01-23 01:52:04.647431: step: 184/529, loss: 0.027756405994296074
2023-01-23 01:52:05.764167: step: 188/529, loss: 0.07891988754272461
2023-01-23 01:52:06.898342: step: 192/529, loss: 0.032425977289676666
2023-01-23 01:52:07.991906: step: 196/529, loss: 0.019214630126953125
2023-01-23 01:52:09.101619: step: 200/529, loss: 0.005147123243659735
2023-01-23 01:52:10.267306: step: 204/529, loss: 0.07959537208080292
2023-01-23 01:52:11.382741: step: 208/529, loss: 0.029631519690155983
2023-01-23 01:52:12.481280: step: 212/529, loss: 0.023068904876708984
2023-01-23 01:52:13.606911: step: 216/529, loss: 0.3601033091545105
2023-01-23 01:52:14.727738: step: 220/529, loss: 0.15707498788833618
2023-01-23 01:52:15.825385: step: 224/529, loss: 0.0167996883392334
2023-01-23 01:52:16.921245: step: 228/529, loss: 0.027569960802793503
2023-01-23 01:52:18.007984: step: 232/529, loss: 0.008847236633300781
2023-01-23 01:52:19.105760: step: 236/529, loss: 0.021175097674131393
2023-01-23 01:52:20.251833: step: 240/529, loss: 0.0478336364030838
2023-01-23 01:52:21.356769: step: 244/529, loss: 0.00977716501802206
2023-01-23 01:52:22.474233: step: 248/529, loss: 0.027523290365934372
2023-01-23 01:52:23.564914: step: 252/529, loss: 0.015262030996382236
2023-01-23 01:52:24.684206: step: 256/529, loss: 0.12833844125270844
2023-01-23 01:52:25.795551: step: 260/529, loss: 0.08741166442632675
2023-01-23 01:52:26.908965: step: 264/529, loss: 3.805160304182209e-05
2023-01-23 01:52:28.035676: step: 268/529, loss: 0.24247604608535767
2023-01-23 01:52:29.159843: step: 272/529, loss: 0.012257575988769531
2023-01-23 01:52:30.296923: step: 276/529, loss: 0.07098159939050674
2023-01-23 01:52:31.422447: step: 280/529, loss: 0.011781120672821999
2023-01-23 01:52:32.510221: step: 284/529, loss: 0.016565512865781784
2023-01-23 01:52:33.602370: step: 288/529, loss: 0.0062236785888671875
2023-01-23 01:52:34.690205: step: 292/529, loss: 0.05268917232751846
2023-01-23 01:52:35.811329: step: 296/529, loss: 0.05069713667035103
2023-01-23 01:52:36.952138: step: 300/529, loss: 0.11061763763427734
2023-01-23 01:52:38.062152: step: 304/529, loss: 0.03950538486242294
2023-01-23 01:52:39.176540: step: 308/529, loss: 0.009746265597641468
2023-01-23 01:52:40.299527: step: 312/529, loss: 0.0030401230324059725
2023-01-23 01:52:41.399530: step: 316/529, loss: 0.1662786602973938
2023-01-23 01:52:42.512052: step: 320/529, loss: 0.011009598150849342
2023-01-23 01:52:43.620454: step: 324/529, loss: 0.010093117132782936
2023-01-23 01:52:44.749405: step: 328/529, loss: 0.031298160552978516
2023-01-23 01:52:45.848493: step: 332/529, loss: 0.02296752855181694
2023-01-23 01:52:46.957804: step: 336/529, loss: 0.02767777256667614
2023-01-23 01:52:48.088339: step: 340/529, loss: 0.01911487616598606
2023-01-23 01:52:49.240740: step: 344/529, loss: 0.015407824888825417
2023-01-23 01:52:50.330025: step: 348/529, loss: 0.005767822265625
2023-01-23 01:52:51.439169: step: 352/529, loss: 0.06564221531152725
2023-01-23 01:52:52.542743: step: 356/529, loss: 0.05016353353857994
2023-01-23 01:52:53.659777: step: 360/529, loss: 0.11410064995288849
2023-01-23 01:52:54.731376: step: 364/529, loss: 0.0035696029663085938
2023-01-23 01:52:55.850312: step: 368/529, loss: 0.011361980810761452
2023-01-23 01:52:56.940066: step: 372/529, loss: 0.5807350277900696
2023-01-23 01:52:58.111672: step: 376/529, loss: 0.09486951678991318
2023-01-23 01:52:59.198546: step: 380/529, loss: 0.04363078996539116
2023-01-23 01:53:00.307158: step: 384/529, loss: 0.024254370480775833
2023-01-23 01:53:01.465502: step: 388/529, loss: 0.007377815432846546
2023-01-23 01:53:02.565671: step: 392/529, loss: 0.09204283356666565
2023-01-23 01:53:03.663566: step: 396/529, loss: 0.01895122602581978
2023-01-23 01:53:04.782096: step: 400/529, loss: 0.0023217203561216593
2023-01-23 01:53:05.904610: step: 404/529, loss: 0.19429558515548706
2023-01-23 01:53:06.992146: step: 408/529, loss: 0.04059314727783203
2023-01-23 01:53:08.109928: step: 412/529, loss: 0.009821319952607155
2023-01-23 01:53:09.180590: step: 416/529, loss: 0.003291606903076172
2023-01-23 01:53:10.291487: step: 420/529, loss: 0.027608491480350494
2023-01-23 01:53:11.413900: step: 424/529, loss: 0.04036521911621094
2023-01-23 01:53:12.534657: step: 428/529, loss: 0.00449371337890625
2023-01-23 01:53:13.664939: step: 432/529, loss: 0.051935769617557526
2023-01-23 01:53:14.782047: step: 436/529, loss: 0.044599153101444244
2023-01-23 01:53:15.901725: step: 440/529, loss: 0.018408585339784622
2023-01-23 01:53:17.001541: step: 444/529, loss: 0.1137228012084961
2023-01-23 01:53:18.102559: step: 448/529, loss: 0.047884751111269
2023-01-23 01:53:19.233646: step: 452/529, loss: 0.001063489937223494
2023-01-23 01:53:20.368115: step: 456/529, loss: 0.12674351036548615
2023-01-23 01:53:21.456004: step: 460/529, loss: 0.029877090826630592
2023-01-23 01:53:22.594194: step: 464/529, loss: 0.04743204265832901
2023-01-23 01:53:23.720618: step: 468/529, loss: 0.003746605012565851
2023-01-23 01:53:24.818225: step: 472/529, loss: 0.00803365744650364
2023-01-23 01:53:25.958523: step: 476/529, loss: 0.06054859235882759
2023-01-23 01:53:27.066299: step: 480/529, loss: 0.009893608279526234
2023-01-23 01:53:28.167106: step: 484/529, loss: 0.016243744641542435
2023-01-23 01:53:29.289734: step: 488/529, loss: 0.02563939243555069
2023-01-23 01:53:30.426103: step: 492/529, loss: 0.00029244425240904093
2023-01-23 01:53:31.531245: step: 496/529, loss: 0.08795707672834396
2023-01-23 01:53:32.672551: step: 500/529, loss: 0.04089775308966637
2023-01-23 01:53:33.788601: step: 504/529, loss: 0.06499533355236053
2023-01-23 01:53:34.886198: step: 508/529, loss: 0.006019783206284046
2023-01-23 01:53:35.988612: step: 512/529, loss: 0.02006855048239231
2023-01-23 01:53:37.102501: step: 516/529, loss: 0.08030052483081818
2023-01-23 01:53:38.231260: step: 520/529, loss: 0.022870827466249466
2023-01-23 01:53:39.341659: step: 524/529, loss: 0.031397152692079544
2023-01-23 01:53:40.448003: step: 528/529, loss: 0.1236150711774826
2023-01-23 01:53:41.556802: step: 532/529, loss: 0.06669120490550995
2023-01-23 01:53:42.677039: step: 536/529, loss: 0.0012908936478197575
2023-01-23 01:53:43.766423: step: 540/529, loss: 0.020603036507964134
2023-01-23 01:53:44.871388: step: 544/529, loss: 0.00563020771369338
2023-01-23 01:53:46.041871: step: 548/529, loss: 0.027902984991669655
2023-01-23 01:53:47.171712: step: 552/529, loss: 0.0007241249550133944
2023-01-23 01:53:48.326863: step: 556/529, loss: 0.04835481941699982
2023-01-23 01:53:49.457764: step: 560/529, loss: 0.01345295924693346
2023-01-23 01:53:50.564758: step: 564/529, loss: 0.010922098532319069
2023-01-23 01:53:51.696220: step: 568/529, loss: 0.20667631924152374
2023-01-23 01:53:52.835072: step: 572/529, loss: 0.04800424724817276
2023-01-23 01:53:53.955205: step: 576/529, loss: 0.005822932813316584
2023-01-23 01:53:55.075901: step: 580/529, loss: 0.1518479287624359
2023-01-23 01:53:56.201265: step: 584/529, loss: 0.015522956848144531
2023-01-23 01:53:57.292287: step: 588/529, loss: 0.04946718364953995
2023-01-23 01:53:58.406796: step: 592/529, loss: 0.019103432074189186
2023-01-23 01:53:59.509419: step: 596/529, loss: 0.15405121445655823
2023-01-23 01:54:00.618187: step: 600/529, loss: 0.04489975422620773
2023-01-23 01:54:01.699863: step: 604/529, loss: 0.08661253750324249
2023-01-23 01:54:02.804228: step: 608/529, loss: 0.03749570995569229
2023-01-23 01:54:03.890371: step: 612/529, loss: 0.002836799481883645
2023-01-23 01:54:05.006024: step: 616/529, loss: 0.0020859241485595703
2023-01-23 01:54:06.119874: step: 620/529, loss: 0.000773525214754045
2023-01-23 01:54:07.237192: step: 624/529, loss: 0.012419032864272594
2023-01-23 01:54:08.362920: step: 628/529, loss: 0.02784571796655655
2023-01-23 01:54:09.481883: step: 632/529, loss: 0.04108161851763725
2023-01-23 01:54:10.588392: step: 636/529, loss: 0.03397693857550621
2023-01-23 01:54:11.703025: step: 640/529, loss: 0.007110023871064186
2023-01-23 01:54:12.807208: step: 644/529, loss: 0.00018262863159179688
2023-01-23 01:54:13.923081: step: 648/529, loss: 0.029517151415348053
2023-01-23 01:54:15.038351: step: 652/529, loss: 0.007136869709938765
2023-01-23 01:54:16.110315: step: 656/529, loss: 0.0023105621803551912
2023-01-23 01:54:17.226975: step: 660/529, loss: 0.0077842059545218945
2023-01-23 01:54:18.319423: step: 664/529, loss: 0.013601399026811123
2023-01-23 01:54:19.463336: step: 668/529, loss: 0.15256109833717346
2023-01-23 01:54:20.574028: step: 672/529, loss: 0.017472077161073685
2023-01-23 01:54:21.710623: step: 676/529, loss: 0.028391553089022636
2023-01-23 01:54:22.833751: step: 680/529, loss: 0.031828153878450394
2023-01-23 01:54:23.935521: step: 684/529, loss: 0.010595321655273438
2023-01-23 01:54:25.025064: step: 688/529, loss: 0.005619335453957319
2023-01-23 01:54:26.139358: step: 692/529, loss: 0.036168668419122696
2023-01-23 01:54:27.265548: step: 696/529, loss: 0.1293676346540451
2023-01-23 01:54:28.384094: step: 700/529, loss: 0.0038583758287131786
2023-01-23 01:54:29.514995: step: 704/529, loss: 0.006727505009621382
2023-01-23 01:54:30.627359: step: 708/529, loss: 0.017378998920321465
2023-01-23 01:54:31.735194: step: 712/529, loss: 0.18939504027366638
2023-01-23 01:54:32.838978: step: 716/529, loss: 0.0037367106415331364
2023-01-23 01:54:33.960146: step: 720/529, loss: 0.009022330865263939
2023-01-23 01:54:35.097328: step: 724/529, loss: 0.08170413970947266
2023-01-23 01:54:36.204202: step: 728/529, loss: 0.143260195851326
2023-01-23 01:54:37.295115: step: 732/529, loss: 0.002220106078311801
2023-01-23 01:54:38.406630: step: 736/529, loss: 0.00667648296803236
2023-01-23 01:54:39.504073: step: 740/529, loss: 0.0002624511835165322
2023-01-23 01:54:40.619001: step: 744/529, loss: 0.0014350891578942537
2023-01-23 01:54:41.742478: step: 748/529, loss: 0.055256180465221405
2023-01-23 01:54:42.880735: step: 752/529, loss: 0.009876633062958717
2023-01-23 01:54:43.984385: step: 756/529, loss: 0.006892490200698376
2023-01-23 01:54:45.112545: step: 760/529, loss: 0.04370613023638725
2023-01-23 01:54:46.199350: step: 764/529, loss: 0.04192943871021271
2023-01-23 01:54:47.328642: step: 768/529, loss: 0.012794646434485912
2023-01-23 01:54:48.434857: step: 772/529, loss: 0.004298686981201172
2023-01-23 01:54:49.549771: step: 776/529, loss: 0.009894943796098232
2023-01-23 01:54:50.666216: step: 780/529, loss: 0.06111784279346466
2023-01-23 01:54:51.794612: step: 784/529, loss: 0.004887962713837624
2023-01-23 01:54:52.899571: step: 788/529, loss: 0.05174970626831055
2023-01-23 01:54:54.002024: step: 792/529, loss: 0.012651443481445312
2023-01-23 01:54:55.141952: step: 796/529, loss: 0.014636039733886719
2023-01-23 01:54:56.271293: step: 800/529, loss: 0.007879066281020641
2023-01-23 01:54:57.388863: step: 804/529, loss: 0.011621571145951748
2023-01-23 01:54:58.506053: step: 808/529, loss: 0.005214977078139782
2023-01-23 01:54:59.616213: step: 812/529, loss: 0.11691112816333771
2023-01-23 01:55:00.715903: step: 816/529, loss: 0.015779685229063034
2023-01-23 01:55:01.821668: step: 820/529, loss: 0.017511941492557526
2023-01-23 01:55:02.955158: step: 824/529, loss: 0.045705415308475494
2023-01-23 01:55:04.069124: step: 828/529, loss: 0.012109566479921341
2023-01-23 01:55:05.165953: step: 832/529, loss: 0.000602293002884835
2023-01-23 01:55:06.312161: step: 836/529, loss: 0.06588821858167648
2023-01-23 01:55:07.418994: step: 840/529, loss: 0.14721809327602386
2023-01-23 01:55:08.513503: step: 844/529, loss: 0.01297235582023859
2023-01-23 01:55:09.636822: step: 848/529, loss: 0.04844837263226509
2023-01-23 01:55:10.758233: step: 852/529, loss: 0.07427187263965607
2023-01-23 01:55:11.876726: step: 856/529, loss: 0.021271325647830963
2023-01-23 01:55:12.998147: step: 860/529, loss: 0.03399200737476349
2023-01-23 01:55:14.119822: step: 864/529, loss: 0.3483470380306244
2023-01-23 01:55:15.215734: step: 868/529, loss: 0.011655235663056374
2023-01-23 01:55:16.367572: step: 872/529, loss: 0.09243965148925781
2023-01-23 01:55:17.474125: step: 876/529, loss: 0.014841079711914062
2023-01-23 01:55:18.558481: step: 880/529, loss: 0.00798502005636692
2023-01-23 01:55:19.707313: step: 884/529, loss: 0.02210206910967827
2023-01-23 01:55:20.819123: step: 888/529, loss: 0.004823732189834118
2023-01-23 01:55:21.949397: step: 892/529, loss: 0.008584022521972656
2023-01-23 01:55:23.051536: step: 896/529, loss: 0.06557025760412216
2023-01-23 01:55:24.152691: step: 900/529, loss: 0.006735515780746937
2023-01-23 01:55:25.243763: step: 904/529, loss: 0.07895927131175995
2023-01-23 01:55:26.332377: step: 908/529, loss: 0.0009802818531170487
2023-01-23 01:55:27.416093: step: 912/529, loss: 0.004580020904541016
2023-01-23 01:55:28.528302: step: 916/529, loss: 0.015382385812699795
2023-01-23 01:55:29.629052: step: 920/529, loss: 0.06200065463781357
2023-01-23 01:55:30.752305: step: 924/529, loss: 0.0052734375931322575
2023-01-23 01:55:31.886770: step: 928/529, loss: 0.010949802584946156
2023-01-23 01:55:32.997357: step: 932/529, loss: 0.0022441863548010588
2023-01-23 01:55:34.085928: step: 936/529, loss: 0.0019631385803222656
2023-01-23 01:55:35.217581: step: 940/529, loss: 0.03144259378314018
2023-01-23 01:55:36.349254: step: 944/529, loss: 0.020041657611727715
2023-01-23 01:55:37.472580: step: 948/529, loss: 0.04442944750189781
2023-01-23 01:55:38.572702: step: 952/529, loss: 0.04252944141626358
2023-01-23 01:55:39.672410: step: 956/529, loss: 0.01144332904368639
2023-01-23 01:55:40.786956: step: 960/529, loss: 0.004132079891860485
2023-01-23 01:55:41.883702: step: 964/529, loss: 0.004291629884392023
2023-01-23 01:55:43.002717: step: 968/529, loss: 0.05982246622443199
2023-01-23 01:55:44.117991: step: 972/529, loss: 0.0009747505537234247
2023-01-23 01:55:45.230399: step: 976/529, loss: 0.12167644500732422
2023-01-23 01:55:46.316368: step: 980/529, loss: 0.007058620452880859
2023-01-23 01:55:47.433226: step: 984/529, loss: 0.03338613733649254
2023-01-23 01:55:48.544185: step: 988/529, loss: 0.05592937394976616
2023-01-23 01:55:49.649142: step: 992/529, loss: 0.03216876834630966
2023-01-23 01:55:50.729852: step: 996/529, loss: 0.13147468864917755
2023-01-23 01:55:51.836917: step: 1000/529, loss: 0.884032130241394
2023-01-23 01:55:52.928422: step: 1004/529, loss: 0.05263042449951172
2023-01-23 01:55:54.025099: step: 1008/529, loss: 0.060459233820438385
2023-01-23 01:55:55.157856: step: 1012/529, loss: 0.05985517427325249
2023-01-23 01:55:56.276649: step: 1016/529, loss: 0.010261249728500843
2023-01-23 01:55:57.379045: step: 1020/529, loss: 0.046550750732421875
2023-01-23 01:55:58.464823: step: 1024/529, loss: 0.025100301951169968
2023-01-23 01:55:59.575875: step: 1028/529, loss: 0.004088974092155695
2023-01-23 01:56:00.660260: step: 1032/529, loss: 0.1093822717666626
2023-01-23 01:56:01.790678: step: 1036/529, loss: 0.0045642852783203125
2023-01-23 01:56:02.914244: step: 1040/529, loss: 0.0670870840549469
2023-01-23 01:56:04.021538: step: 1044/529, loss: 0.006023979280143976
2023-01-23 01:56:05.109238: step: 1048/529, loss: 0.0063266754150390625
2023-01-23 01:56:06.211106: step: 1052/529, loss: 0.02001981809735298
2023-01-23 01:56:07.331149: step: 1056/529, loss: 0.044989779591560364
2023-01-23 01:56:08.437112: step: 1060/529, loss: 0.11159010231494904
2023-01-23 01:56:09.551018: step: 1064/529, loss: 0.006058120634406805
2023-01-23 01:56:10.658360: step: 1068/529, loss: 0.01607370376586914
2023-01-23 01:56:11.762980: step: 1072/529, loss: 0.0021827698219567537
2023-01-23 01:56:12.867109: step: 1076/529, loss: 0.3098045289516449
2023-01-23 01:56:13.999788: step: 1080/529, loss: 0.0009037017589434981
2023-01-23 01:56:15.132657: step: 1084/529, loss: 0.012361908331513405
2023-01-23 01:56:16.222733: step: 1088/529, loss: 0.004008507821708918
2023-01-23 01:56:17.321274: step: 1092/529, loss: 0.0027400015387684107
2023-01-23 01:56:18.437277: step: 1096/529, loss: 0.04791250452399254
2023-01-23 01:56:19.538190: step: 1100/529, loss: 0.038619138300418854
2023-01-23 01:56:20.665734: step: 1104/529, loss: 0.00642161350697279
2023-01-23 01:56:21.796060: step: 1108/529, loss: 0.0019177437061443925
2023-01-23 01:56:22.943414: step: 1112/529, loss: 0.06991234421730042
2023-01-23 01:56:24.028707: step: 1116/529, loss: 0.04513683170080185
2023-01-23 01:56:25.150870: step: 1120/529, loss: 0.04821434244513512
2023-01-23 01:56:26.266711: step: 1124/529, loss: 0.014318719506263733
2023-01-23 01:56:27.371817: step: 1128/529, loss: 0.045820239931344986
2023-01-23 01:56:28.492724: step: 1132/529, loss: 0.00822591781616211
2023-01-23 01:56:29.618996: step: 1136/529, loss: 0.10409088432788849
2023-01-23 01:56:30.753289: step: 1140/529, loss: 0.019231416285037994
2023-01-23 01:56:31.848096: step: 1144/529, loss: 0.0037736238446086645
2023-01-23 01:56:32.992316: step: 1148/529, loss: 0.009040355682373047
2023-01-23 01:56:34.098418: step: 1152/529, loss: 0.03665924072265625
2023-01-23 01:56:35.186903: step: 1156/529, loss: 0.007178878877311945
2023-01-23 01:56:36.301603: step: 1160/529, loss: 0.06026649475097656
2023-01-23 01:56:37.400764: step: 1164/529, loss: 0.36482754349708557
2023-01-23 01:56:38.507916: step: 1168/529, loss: 0.004725265316665173
2023-01-23 01:56:39.636952: step: 1172/529, loss: 0.04809093475341797
2023-01-23 01:56:40.736936: step: 1176/529, loss: 0.013447762466967106
2023-01-23 01:56:41.861272: step: 1180/529, loss: 0.00018405914306640625
2023-01-23 01:56:42.981143: step: 1184/529, loss: 0.0003297329240012914
2023-01-23 01:56:44.107998: step: 1188/529, loss: 0.026902198791503906
2023-01-23 01:56:45.231328: step: 1192/529, loss: 0.020311832427978516
2023-01-23 01:56:46.342684: step: 1196/529, loss: 0.0022874355781823397
2023-01-23 01:56:47.467820: step: 1200/529, loss: 0.007556915283203125
2023-01-23 01:56:48.588053: step: 1204/529, loss: 0.004610705655068159
2023-01-23 01:56:49.712852: step: 1208/529, loss: 0.06693993508815765
2023-01-23 01:56:50.833074: step: 1212/529, loss: 0.026430893689393997
2023-01-23 01:56:51.956511: step: 1216/529, loss: 0.01758584938943386
2023-01-23 01:56:53.057907: step: 1220/529, loss: 0.017342805862426758
2023-01-23 01:56:54.196343: step: 1224/529, loss: 0.011812401004135609
2023-01-23 01:56:55.314838: step: 1228/529, loss: 0.02156543731689453
2023-01-23 01:56:56.421110: step: 1232/529, loss: 0.024366378784179688
2023-01-23 01:56:57.536287: step: 1236/529, loss: 0.0028502463828772306
2023-01-23 01:56:58.665919: step: 1240/529, loss: 0.012836921028792858
2023-01-23 01:56:59.768269: step: 1244/529, loss: 0.002596950624138117
2023-01-23 01:57:00.882725: step: 1248/529, loss: 0.013252640143036842
2023-01-23 01:57:02.003856: step: 1252/529, loss: 0.021851157769560814
2023-01-23 01:57:03.146325: step: 1256/529, loss: 0.04858551174402237
2023-01-23 01:57:04.240935: step: 1260/529, loss: 0.056967735290527344
2023-01-23 01:57:05.362355: step: 1264/529, loss: 0.045302774757146835
2023-01-23 01:57:06.511349: step: 1268/529, loss: 0.01122751273214817
2023-01-23 01:57:07.638514: step: 1272/529, loss: 0.009167671203613281
2023-01-23 01:57:08.745306: step: 1276/529, loss: 0.04904327541589737
2023-01-23 01:57:09.833777: step: 1280/529, loss: 0.038149259984493256
2023-01-23 01:57:10.936463: step: 1284/529, loss: 0.08703117817640305
2023-01-23 01:57:12.037087: step: 1288/529, loss: 0.034574221819639206
2023-01-23 01:57:13.140230: step: 1292/529, loss: 0.043476298451423645
2023-01-23 01:57:14.272038: step: 1296/529, loss: 0.07742729038000107
2023-01-23 01:57:15.362541: step: 1300/529, loss: 0.024439431726932526
2023-01-23 01:57:16.507135: step: 1304/529, loss: 0.03694910928606987
2023-01-23 01:57:17.628138: step: 1308/529, loss: 0.028636742383241653
2023-01-23 01:57:18.718668: step: 1312/529, loss: 0.048247016966342926
2023-01-23 01:57:19.818371: step: 1316/529, loss: 0.0014256477588787675
2023-01-23 01:57:20.924672: step: 1320/529, loss: 0.012219620868563652
2023-01-23 01:57:22.016873: step: 1324/529, loss: 0.0881534144282341
2023-01-23 01:57:23.112337: step: 1328/529, loss: 0.06409988552331924
2023-01-23 01:57:24.211599: step: 1332/529, loss: 0.034006405621767044
2023-01-23 01:57:25.281366: step: 1336/529, loss: 0.008554316125810146
2023-01-23 01:57:26.419644: step: 1340/529, loss: 0.019129181280732155
2023-01-23 01:57:27.522488: step: 1344/529, loss: 0.006757402792572975
2023-01-23 01:57:28.602284: step: 1348/529, loss: 0.08117235451936722
2023-01-23 01:57:29.726338: step: 1352/529, loss: 0.015814591199159622
2023-01-23 01:57:30.819187: step: 1356/529, loss: 0.06495046615600586
2023-01-23 01:57:31.907853: step: 1360/529, loss: 0.011937332339584827
2023-01-23 01:57:33.007074: step: 1364/529, loss: 0.013608360663056374
2023-01-23 01:57:34.099078: step: 1368/529, loss: 0.02305459976196289
2023-01-23 01:57:35.189690: step: 1372/529, loss: 0.03589329868555069
2023-01-23 01:57:36.289233: step: 1376/529, loss: 0.016468429937958717
2023-01-23 01:57:37.428745: step: 1380/529, loss: 0.0040308949537575245
2023-01-23 01:57:38.559981: step: 1384/529, loss: 0.0046943663619458675
2023-01-23 01:57:39.668826: step: 1388/529, loss: 0.0018876552348956466
2023-01-23 01:57:40.796424: step: 1392/529, loss: 0.008018684573471546
2023-01-23 01:57:41.908568: step: 1396/529, loss: 0.029947759583592415
2023-01-23 01:57:43.010839: step: 1400/529, loss: 0.010931015014648438
2023-01-23 01:57:44.167506: step: 1404/529, loss: 0.00782022438943386
2023-01-23 01:57:45.297052: step: 1408/529, loss: 0.05877294763922691
2023-01-23 01:57:46.423464: step: 1412/529, loss: 0.015551663003861904
2023-01-23 01:57:47.591696: step: 1416/529, loss: 0.005804348271340132
2023-01-23 01:57:48.692017: step: 1420/529, loss: 0.001958656357601285
2023-01-23 01:57:49.809233: step: 1424/529, loss: 0.003894853638485074
2023-01-23 01:57:50.902858: step: 1428/529, loss: 0.006210899446159601
2023-01-23 01:57:52.029346: step: 1432/529, loss: 0.010835647583007812
2023-01-23 01:57:53.169511: step: 1436/529, loss: 0.023590851575136185
2023-01-23 01:57:54.270653: step: 1440/529, loss: 0.0008525848388671875
2023-01-23 01:57:55.377354: step: 1444/529, loss: 0.002076101489365101
2023-01-23 01:57:56.499202: step: 1448/529, loss: 0.051577188074588776
2023-01-23 01:57:57.604763: step: 1452/529, loss: 0.0019813061226159334
2023-01-23 01:57:58.718288: step: 1456/529, loss: 0.05126991495490074
2023-01-23 01:57:59.800120: step: 1460/529, loss: 0.02657637745141983
2023-01-23 01:58:00.891581: step: 1464/529, loss: 0.08320770412683487
2023-01-23 01:58:02.038673: step: 1468/529, loss: 0.06510219722986221
2023-01-23 01:58:03.143503: step: 1472/529, loss: 0.013584066182374954
2023-01-23 01:58:04.247142: step: 1476/529, loss: 0.2623741030693054
2023-01-23 01:58:05.377709: step: 1480/529, loss: 0.023077774792909622
2023-01-23 01:58:06.538798: step: 1484/529, loss: 0.053269293159246445
2023-01-23 01:58:07.667811: step: 1488/529, loss: 0.004222107119858265
2023-01-23 01:58:08.769008: step: 1492/529, loss: 0.023256875574588776
2023-01-23 01:58:09.873605: step: 1496/529, loss: 0.01752915419638157
2023-01-23 01:58:10.953875: step: 1500/529, loss: 0.005416584201157093
2023-01-23 01:58:12.044729: step: 1504/529, loss: 0.002806043718010187
2023-01-23 01:58:13.132836: step: 1508/529, loss: 0.030350064858794212
2023-01-23 01:58:14.243501: step: 1512/529, loss: 0.014558697119355202
2023-01-23 01:58:15.363711: step: 1516/529, loss: 0.08598404377698898
2023-01-23 01:58:16.467348: step: 1520/529, loss: 0.0382019504904747
2023-01-23 01:58:17.563185: step: 1524/529, loss: 0.007064259145408869
2023-01-23 01:58:18.661409: step: 1528/529, loss: 0.05376832187175751
2023-01-23 01:58:19.763229: step: 1532/529, loss: 0.03178863599896431
2023-01-23 01:58:20.873093: step: 1536/529, loss: 0.009189700707793236
2023-01-23 01:58:21.976857: step: 1540/529, loss: 0.051366519182920456
2023-01-23 01:58:23.076114: step: 1544/529, loss: 0.034120846539735794
2023-01-23 01:58:24.214334: step: 1548/529, loss: 0.023156166076660156
2023-01-23 01:58:25.342690: step: 1552/529, loss: 0.013827420771121979
2023-01-23 01:58:26.464713: step: 1556/529, loss: 0.03251180797815323
2023-01-23 01:58:27.584322: step: 1560/529, loss: 0.028513146564364433
2023-01-23 01:58:28.692789: step: 1564/529, loss: 0.5190154910087585
2023-01-23 01:58:29.819559: step: 1568/529, loss: 0.029238274320960045
2023-01-23 01:58:30.911793: step: 1572/529, loss: 0.002899265382438898
2023-01-23 01:58:32.042015: step: 1576/529, loss: 0.035485681146383286
2023-01-23 01:58:33.137399: step: 1580/529, loss: 0.01726846769452095
2023-01-23 01:58:34.274820: step: 1584/529, loss: 0.013656712137162685
2023-01-23 01:58:35.382844: step: 1588/529, loss: 0.03733348846435547
2023-01-23 01:58:36.514569: step: 1592/529, loss: 0.06979713588953018
2023-01-23 01:58:37.628068: step: 1596/529, loss: 0.049913790076971054
2023-01-23 01:58:38.740375: step: 1600/529, loss: 0.006816482171416283
2023-01-23 01:58:39.863691: step: 1604/529, loss: 0.010957884602248669
2023-01-23 01:58:40.963685: step: 1608/529, loss: 0.011243057437241077
2023-01-23 01:58:42.080257: step: 1612/529, loss: 0.10663265734910965
2023-01-23 01:58:43.163703: step: 1616/529, loss: 0.022330619394779205
2023-01-23 01:58:44.251043: step: 1620/529, loss: 0.004148292355239391
2023-01-23 01:58:45.400911: step: 1624/529, loss: 0.078783318400383
2023-01-23 01:58:46.521416: step: 1628/529, loss: 0.019055012613534927
2023-01-23 01:58:47.670072: step: 1632/529, loss: 0.00965871848165989
2023-01-23 01:58:48.807404: step: 1636/529, loss: 0.021849345415830612
2023-01-23 01:58:49.906838: step: 1640/529, loss: 0.07309045642614365
2023-01-23 01:58:51.042117: step: 1644/529, loss: 0.27570265531539917
2023-01-23 01:58:52.184429: step: 1648/529, loss: 0.021379852667450905
2023-01-23 01:58:53.297136: step: 1652/529, loss: 0.00640716589987278
2023-01-23 01:58:54.410179: step: 1656/529, loss: 0.010583113878965378
2023-01-23 01:58:55.522755: step: 1660/529, loss: 0.022100163623690605
2023-01-23 01:58:56.637498: step: 1664/529, loss: 0.0035991668701171875
2023-01-23 01:58:57.738619: step: 1668/529, loss: 0.018027067184448242
2023-01-23 01:58:58.843680: step: 1672/529, loss: 0.022297287359833717
2023-01-23 01:58:59.964393: step: 1676/529, loss: 0.1069829985499382
2023-01-23 01:59:01.063492: step: 1680/529, loss: 0.015033340081572533
2023-01-23 01:59:02.191766: step: 1684/529, loss: 0.7259511351585388
2023-01-23 01:59:03.316143: step: 1688/529, loss: 0.013080645352602005
2023-01-23 01:59:04.450817: step: 1692/529, loss: 0.011502360925078392
2023-01-23 01:59:05.574829: step: 1696/529, loss: 0.04706869274377823
2023-01-23 01:59:06.671130: step: 1700/529, loss: 0.028891896829009056
2023-01-23 01:59:07.773826: step: 1704/529, loss: 0.016765978187322617
2023-01-23 01:59:08.891403: step: 1708/529, loss: 0.008686160668730736
2023-01-23 01:59:09.983159: step: 1712/529, loss: 0.04540519788861275
2023-01-23 01:59:11.065648: step: 1716/529, loss: 0.05992479249835014
2023-01-23 01:59:12.199535: step: 1720/529, loss: 0.309914767742157
2023-01-23 01:59:13.318200: step: 1724/529, loss: 0.2603258192539215
2023-01-23 01:59:14.462000: step: 1728/529, loss: 0.019812941551208496
2023-01-23 01:59:15.573200: step: 1732/529, loss: 0.05162016302347183
2023-01-23 01:59:16.649671: step: 1736/529, loss: 0.0030622482299804688
2023-01-23 01:59:17.774437: step: 1740/529, loss: 0.0012599944602698088
2023-01-23 01:59:18.915111: step: 1744/529, loss: 0.31702733039855957
2023-01-23 01:59:20.028530: step: 1748/529, loss: 0.0022668838500976562
2023-01-23 01:59:21.134892: step: 1752/529, loss: 0.03912544250488281
2023-01-23 01:59:22.250805: step: 1756/529, loss: 0.026839256286621094
2023-01-23 01:59:23.367420: step: 1760/529, loss: 0.07360468059778214
2023-01-23 01:59:24.506114: step: 1764/529, loss: 0.042208481580019
2023-01-23 01:59:25.643451: step: 1768/529, loss: 0.010390853509306908
2023-01-23 01:59:26.759502: step: 1772/529, loss: 0.08274458348751068
2023-01-23 01:59:27.874407: step: 1776/529, loss: 0.038687705993652344
2023-01-23 01:59:28.969209: step: 1780/529, loss: 0.03593158721923828
2023-01-23 01:59:30.068118: step: 1784/529, loss: 0.004655647091567516
2023-01-23 01:59:31.145142: step: 1788/529, loss: 0.2558261752128601
2023-01-23 01:59:32.263965: step: 1792/529, loss: 0.05115795135498047
2023-01-23 01:59:33.373644: step: 1796/529, loss: 0.08115635067224503
2023-01-23 01:59:34.496825: step: 1800/529, loss: 0.07354607433080673
2023-01-23 01:59:35.592758: step: 1804/529, loss: 0.009752940386533737
2023-01-23 01:59:36.685732: step: 1808/529, loss: 0.0009815931553021073
2023-01-23 01:59:37.813421: step: 1812/529, loss: 0.010867690667510033
2023-01-23 01:59:38.927215: step: 1816/529, loss: 0.016701603308320045
2023-01-23 01:59:40.069864: step: 1820/529, loss: 0.05021953582763672
2023-01-23 01:59:41.200926: step: 1824/529, loss: 0.02888660319149494
2023-01-23 01:59:42.307117: step: 1828/529, loss: 0.014526177197694778
2023-01-23 01:59:43.422930: step: 1832/529, loss: 0.025641441345214844
2023-01-23 01:59:44.517752: step: 1836/529, loss: 0.014953423291444778
2023-01-23 01:59:45.645211: step: 1840/529, loss: 0.031143762171268463
2023-01-23 01:59:46.745790: step: 1844/529, loss: 0.02171764336526394
2023-01-23 01:59:47.849791: step: 1848/529, loss: 0.01120681781321764
2023-01-23 01:59:48.967695: step: 1852/529, loss: 0.04787120968103409
2023-01-23 01:59:50.094184: step: 1856/529, loss: 0.08074355870485306
2023-01-23 01:59:51.203386: step: 1860/529, loss: 0.005659008398652077
2023-01-23 01:59:52.334358: step: 1864/529, loss: 0.0758235901594162
2023-01-23 01:59:53.483086: step: 1868/529, loss: 0.10522308945655823
2023-01-23 01:59:54.582940: step: 1872/529, loss: 0.014465617947280407
2023-01-23 01:59:55.704468: step: 1876/529, loss: 0.0687403678894043
2023-01-23 01:59:56.831648: step: 1880/529, loss: 0.022282984107732773
2023-01-23 01:59:57.943727: step: 1884/529, loss: 0.015118788927793503
2023-01-23 01:59:59.054817: step: 1888/529, loss: 0.03575773537158966
2023-01-23 02:00:00.160241: step: 1892/529, loss: 0.007437491789460182
2023-01-23 02:00:01.264816: step: 1896/529, loss: 0.08016910403966904
2023-01-23 02:00:02.427661: step: 1900/529, loss: 0.019894791767001152
2023-01-23 02:00:03.571826: step: 1904/529, loss: 0.05418711155653
2023-01-23 02:00:04.673058: step: 1908/529, loss: 0.022116661071777344
2023-01-23 02:00:05.790529: step: 1912/529, loss: 0.016554927453398705
2023-01-23 02:00:06.934551: step: 1916/529, loss: 0.004768180660903454
2023-01-23 02:00:08.039446: step: 1920/529, loss: 0.010572051629424095
2023-01-23 02:00:09.162765: step: 1924/529, loss: 0.028961801901459694
2023-01-23 02:00:10.276486: step: 1928/529, loss: 0.07067890465259552
2023-01-23 02:00:11.378126: step: 1932/529, loss: 0.0065080164931714535
2023-01-23 02:00:12.534944: step: 1936/529, loss: 0.002762413118034601
2023-01-23 02:00:13.645972: step: 1940/529, loss: 0.05084487050771713
2023-01-23 02:00:14.764378: step: 1944/529, loss: 0.016050148755311966
2023-01-23 02:00:15.873484: step: 1948/529, loss: 0.035315800458192825
2023-01-23 02:00:17.020953: step: 1952/529, loss: 0.03607607260346413
2023-01-23 02:00:18.142555: step: 1956/529, loss: 0.04850387945771217
2023-01-23 02:00:19.247619: step: 1960/529, loss: 0.027379514649510384
2023-01-23 02:00:20.343578: step: 1964/529, loss: 0.032022763043642044
2023-01-23 02:00:21.444305: step: 1968/529, loss: 0.013166236691176891
2023-01-23 02:00:22.547534: step: 1972/529, loss: 0.03219404071569443
2023-01-23 02:00:23.629070: step: 1976/529, loss: 0.011235046200454235
2023-01-23 02:00:24.734175: step: 1980/529, loss: 0.03635311499238014
2023-01-23 02:00:25.842221: step: 1984/529, loss: 0.011315440759062767
2023-01-23 02:00:26.956700: step: 1988/529, loss: 0.4759610891342163
2023-01-23 02:00:28.039844: step: 1992/529, loss: 0.011649226769804955
2023-01-23 02:00:29.146308: step: 1996/529, loss: 0.010376167483627796
2023-01-23 02:00:30.226758: step: 2000/529, loss: 0.03820042684674263
2023-01-23 02:00:31.340993: step: 2004/529, loss: 0.016927147284150124
2023-01-23 02:00:32.467062: step: 2008/529, loss: 0.05818786472082138
2023-01-23 02:00:33.566447: step: 2012/529, loss: 0.0522676482796669
2023-01-23 02:00:34.660954: step: 2016/529, loss: 0.03870201110839844
2023-01-23 02:00:35.754503: step: 2020/529, loss: 0.020067311823368073
2023-01-23 02:00:36.850028: step: 2024/529, loss: 0.0005195617559365928
2023-01-23 02:00:37.982710: step: 2028/529, loss: 0.10371380299329758
2023-01-23 02:00:39.081982: step: 2032/529, loss: 0.010229396633803844
2023-01-23 02:00:40.187107: step: 2036/529, loss: 0.0035326003562659025
2023-01-23 02:00:41.311832: step: 2040/529, loss: 0.03127174451947212
2023-01-23 02:00:42.437225: step: 2044/529, loss: 0.02008695714175701
2023-01-23 02:00:43.553217: step: 2048/529, loss: 0.01170883234590292
2023-01-23 02:00:44.652246: step: 2052/529, loss: 0.01786642149090767
2023-01-23 02:00:45.770607: step: 2056/529, loss: 0.04937922954559326
2023-01-23 02:00:46.865240: step: 2060/529, loss: 0.10546989738941193
2023-01-23 02:00:48.013027: step: 2064/529, loss: 0.06906566768884659
2023-01-23 02:00:49.128207: step: 2068/529, loss: 0.06697960197925568
2023-01-23 02:00:50.245352: step: 2072/529, loss: 0.05685315281152725
2023-01-23 02:00:51.361014: step: 2076/529, loss: 0.04433488845825195
2023-01-23 02:00:52.472225: step: 2080/529, loss: 0.011316823773086071
2023-01-23 02:00:53.574255: step: 2084/529, loss: 0.0305952075868845
2023-01-23 02:00:54.669061: step: 2088/529, loss: 0.0007498741615563631
2023-01-23 02:00:55.796714: step: 2092/529, loss: 0.00426592817530036
2023-01-23 02:00:56.891875: step: 2096/529, loss: 0.13869649171829224
2023-01-23 02:00:58.033613: step: 2100/529, loss: 0.008698845282196999
2023-01-23 02:00:59.122560: step: 2104/529, loss: 0.004303073976188898
2023-01-23 02:01:00.244445: step: 2108/529, loss: 0.024271393194794655
2023-01-23 02:01:01.397236: step: 2112/529, loss: 0.02950286865234375
2023-01-23 02:01:02.493161: step: 2116/529, loss: 0.009170723147690296
==================================================
Loss: 0.045
--------------------
Dev: {'event': {'p': 0.5793650793650794, 'r': 0.7776298268974701, 'f1': 0.6640136441159751}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6310592459605027, 'r': 0.7934537246049661, 'f1': 0.703}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5333333333333333, 'r': 0.8888888888888888, 'f1': 0.6666666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
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': 14}
Russian: {'event': {'p': 0.45, 'r': 0.5, 'f1': 0.4736842105263158}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5842696629213483, 'r': 0.7616511318242344, 'f1': 0.661271676300578}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.6081741448245225, 'r': 0.7725733634311512, 'f1': 0.6805866268953518}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.6190476190476191, 'f1': 0.6190476190476191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:01:42.770549: step: 4/529, loss: 0.02822570875287056
2023-01-23 02:01:43.878382: step: 8/529, loss: 0.00940475519746542
2023-01-23 02:01:44.982661: step: 12/529, loss: 0.006194019690155983
2023-01-23 02:01:46.085478: step: 16/529, loss: 0.0021185874938964844
2023-01-23 02:01:47.209507: step: 20/529, loss: 0.0009635925525799394
2023-01-23 02:01:48.292325: step: 24/529, loss: 0.003908062353730202
2023-01-23 02:01:49.386598: step: 28/529, loss: 0.10393648594617844
2023-01-23 02:01:50.500109: step: 32/529, loss: 0.0164628978818655
2023-01-23 02:01:51.603647: step: 36/529, loss: 0.23524247109889984
2023-01-23 02:01:52.696340: step: 40/529, loss: 0.0393267385661602
2023-01-23 02:01:53.830932: step: 44/529, loss: 0.010589790530502796
2023-01-23 02:01:54.937542: step: 48/529, loss: 0.003737163729965687
2023-01-23 02:01:56.067965: step: 52/529, loss: 0.05091991648077965
2023-01-23 02:01:57.168622: step: 56/529, loss: 0.004349804017692804
2023-01-23 02:01:58.323221: step: 60/529, loss: 0.014333629980683327
2023-01-23 02:01:59.418495: step: 64/529, loss: 0.014070892706513405
2023-01-23 02:02:00.528850: step: 68/529, loss: 0.004953670781105757
2023-01-23 02:02:01.640018: step: 72/529, loss: 0.011232947930693626
2023-01-23 02:02:02.732760: step: 76/529, loss: 0.027726365253329277
2023-01-23 02:02:03.831208: step: 80/529, loss: 0.04711728170514107
2023-01-23 02:02:04.949231: step: 84/529, loss: 0.006350231356918812
2023-01-23 02:02:06.062289: step: 88/529, loss: 0.029451562091708183
2023-01-23 02:02:07.186070: step: 92/529, loss: 0.0012616157764568925
2023-01-23 02:02:08.277213: step: 96/529, loss: 0.01969289965927601
2023-01-23 02:02:09.383080: step: 100/529, loss: 0.008139610290527344
2023-01-23 02:02:10.497031: step: 104/529, loss: 0.05815467983484268
2023-01-23 02:02:11.625428: step: 108/529, loss: 0.016068648546934128
2023-01-23 02:02:12.739729: step: 112/529, loss: 0.031229544430971146
2023-01-23 02:02:13.827818: step: 116/529, loss: 0.0016626358265057206
2023-01-23 02:02:14.974242: step: 120/529, loss: 0.001676845597103238
2023-01-23 02:02:16.080069: step: 124/529, loss: 0.036770012229681015
2023-01-23 02:02:17.188851: step: 128/529, loss: 0.004294777289032936
2023-01-23 02:02:18.284177: step: 132/529, loss: 0.02440032921731472
2023-01-23 02:02:19.361945: step: 136/529, loss: 0.09974256157875061
2023-01-23 02:02:20.483645: step: 140/529, loss: 0.004360604099929333
2023-01-23 02:02:21.577657: step: 144/529, loss: 0.001702594687230885
2023-01-23 02:02:22.674156: step: 148/529, loss: 0.05367422103881836
2023-01-23 02:02:23.783498: step: 152/529, loss: 0.327165424823761
2023-01-23 02:02:24.902219: step: 156/529, loss: 0.06527883559465408
2023-01-23 02:02:26.020909: step: 160/529, loss: 0.010801506228744984
2023-01-23 02:02:27.120320: step: 164/529, loss: 0.13365012407302856
2023-01-23 02:02:28.218496: step: 168/529, loss: 0.010923480615019798
2023-01-23 02:02:29.340739: step: 172/529, loss: 0.07018747180700302
2023-01-23 02:02:30.478668: step: 176/529, loss: 0.03233347088098526
2023-01-23 02:02:31.573630: step: 180/529, loss: 0.01683983951807022
2023-01-23 02:02:32.654746: step: 184/529, loss: 0.04851646348834038
2023-01-23 02:02:33.739995: step: 188/529, loss: 0.00893859937787056
2023-01-23 02:02:34.817170: step: 192/529, loss: 0.013376235030591488
2023-01-23 02:02:35.904708: step: 196/529, loss: 0.007291603367775679
2023-01-23 02:02:37.006647: step: 200/529, loss: 0.00826406478881836
2023-01-23 02:02:38.096834: step: 204/529, loss: 0.005395126529037952
2023-01-23 02:02:39.175105: step: 208/529, loss: 0.016063833609223366
2023-01-23 02:02:40.287424: step: 212/529, loss: 0.047331809997558594
2023-01-23 02:02:41.363217: step: 216/529, loss: 0.02811565436422825
2023-01-23 02:02:42.482023: step: 220/529, loss: 0.0023702620528638363
2023-01-23 02:02:43.590088: step: 224/529, loss: 0.06053737550973892
2023-01-23 02:02:44.702587: step: 228/529, loss: 0.006602573674172163
2023-01-23 02:02:45.790796: step: 232/529, loss: 0.027394484728574753
2023-01-23 02:02:46.905639: step: 236/529, loss: 0.06755141913890839
2023-01-23 02:02:48.041180: step: 240/529, loss: 0.0016830444801598787
2023-01-23 02:02:49.171220: step: 244/529, loss: 0.3285873532295227
2023-01-23 02:02:50.292392: step: 248/529, loss: 0.004387283232063055
2023-01-23 02:02:51.382263: step: 252/529, loss: 0.0550416000187397
2023-01-23 02:02:52.497643: step: 256/529, loss: 7.834434654796496e-05
2023-01-23 02:02:53.604515: step: 260/529, loss: 0.007579613011330366
2023-01-23 02:02:54.676812: step: 264/529, loss: 0.027159595862030983
2023-01-23 02:02:55.801226: step: 268/529, loss: 0.11134834587574005
2023-01-23 02:02:56.898607: step: 272/529, loss: 0.017879962921142578
2023-01-23 02:02:58.016617: step: 276/529, loss: 0.017342282459139824
2023-01-23 02:02:59.125031: step: 280/529, loss: 0.0011494637001305819
2023-01-23 02:03:00.247175: step: 284/529, loss: 0.0005737781757488847
2023-01-23 02:03:01.350818: step: 288/529, loss: 0.027031267061829567
2023-01-23 02:03:02.424359: step: 292/529, loss: 0.006271743681281805
2023-01-23 02:03:03.511818: step: 296/529, loss: 0.07226734608411789
2023-01-23 02:03:04.607033: step: 300/529, loss: 0.011046409606933594
2023-01-23 02:03:05.750809: step: 304/529, loss: 0.02284526824951172
2023-01-23 02:03:06.867513: step: 308/529, loss: 0.028666973114013672
2023-01-23 02:03:08.010466: step: 312/529, loss: 0.0015861510764807463
2023-01-23 02:03:09.179174: step: 316/529, loss: 0.005906105041503906
2023-01-23 02:03:10.318843: step: 320/529, loss: 0.04558046534657478
2023-01-23 02:03:11.434943: step: 324/529, loss: 0.2842459976673126
2023-01-23 02:03:12.555149: step: 328/529, loss: 0.03322868421673775
2023-01-23 02:03:13.671595: step: 332/529, loss: 0.05849600210785866
2023-01-23 02:03:14.756871: step: 336/529, loss: 0.000492095947265625
2023-01-23 02:03:15.876970: step: 340/529, loss: 0.035881806164979935
2023-01-23 02:03:16.973580: step: 344/529, loss: 0.008594751358032227
2023-01-23 02:03:18.094112: step: 348/529, loss: 0.05172138288617134
2023-01-23 02:03:19.248467: step: 352/529, loss: 0.020600175485014915
2023-01-23 02:03:20.366960: step: 356/529, loss: 0.0032741546165198088
2023-01-23 02:03:21.455477: step: 360/529, loss: 0.03638134151697159
2023-01-23 02:03:22.540892: step: 364/529, loss: 0.0177778247743845
2023-01-23 02:03:23.649430: step: 368/529, loss: 0.02365584298968315
2023-01-23 02:03:24.743474: step: 372/529, loss: 0.0453500971198082
2023-01-23 02:03:25.861479: step: 376/529, loss: 0.10588875412940979
2023-01-23 02:03:26.974078: step: 380/529, loss: 0.012697696685791016
2023-01-23 02:03:28.078082: step: 384/529, loss: 0.01796755939722061
2023-01-23 02:03:29.197652: step: 388/529, loss: 0.025812674313783646
2023-01-23 02:03:30.328239: step: 392/529, loss: 0.01332387886941433
2023-01-23 02:03:31.450749: step: 396/529, loss: 0.021006394177675247
2023-01-23 02:03:32.562691: step: 400/529, loss: 0.015304852277040482
2023-01-23 02:03:33.674521: step: 404/529, loss: 0.004199981689453125
2023-01-23 02:03:34.794587: step: 408/529, loss: 0.02092723734676838
2023-01-23 02:03:35.894672: step: 412/529, loss: 0.21907749772071838
2023-01-23 02:03:37.001431: step: 416/529, loss: 0.0034286021254956722
2023-01-23 02:03:38.121083: step: 420/529, loss: 0.025684071704745293
2023-01-23 02:03:39.242761: step: 424/529, loss: 0.02913360670208931
2023-01-23 02:03:40.367774: step: 428/529, loss: 0.09381237626075745
2023-01-23 02:03:41.501631: step: 432/529, loss: 0.002601051237434149
2023-01-23 02:03:42.622182: step: 436/529, loss: 0.015467643737792969
2023-01-23 02:03:43.743288: step: 440/529, loss: 0.015519714914262295
2023-01-23 02:03:44.847064: step: 444/529, loss: 0.11587519943714142
2023-01-23 02:03:45.992215: step: 448/529, loss: 0.06438083946704865
2023-01-23 02:03:47.135614: step: 452/529, loss: 0.04938783496618271
2023-01-23 02:03:48.256966: step: 456/529, loss: 0.018175793811678886
2023-01-23 02:03:49.409936: step: 460/529, loss: 0.002646827604621649
2023-01-23 02:03:50.555261: step: 464/529, loss: 0.04045305401086807
2023-01-23 02:03:51.650284: step: 468/529, loss: 0.023006536066532135
2023-01-23 02:03:52.757097: step: 472/529, loss: 0.023910902440547943
2023-01-23 02:03:53.855228: step: 476/529, loss: 0.0004017830069642514
2023-01-23 02:03:54.966652: step: 480/529, loss: 0.0016859055031090975
2023-01-23 02:03:56.074299: step: 484/529, loss: 0.3180274963378906
2023-01-23 02:03:57.165339: step: 488/529, loss: 0.012497425079345703
2023-01-23 02:03:58.286822: step: 492/529, loss: 0.01527872122824192
2023-01-23 02:03:59.410395: step: 496/529, loss: 0.036000825464725494
2023-01-23 02:04:00.560554: step: 500/529, loss: 0.03184108808636665
2023-01-23 02:04:01.676254: step: 504/529, loss: 0.014605618081986904
2023-01-23 02:04:02.785505: step: 508/529, loss: 0.0010390281677246094
2023-01-23 02:04:03.893133: step: 512/529, loss: 0.005808734800666571
2023-01-23 02:04:05.000999: step: 516/529, loss: 0.015707969665527344
2023-01-23 02:04:06.127712: step: 520/529, loss: 0.0053192139603197575
2023-01-23 02:04:07.224854: step: 524/529, loss: 0.00015954971604514867
2023-01-23 02:04:08.319140: step: 528/529, loss: 0.04520053789019585
2023-01-23 02:04:09.472419: step: 532/529, loss: 0.04092540591955185
2023-01-23 02:04:10.595081: step: 536/529, loss: 0.012979078106582165
2023-01-23 02:04:11.694587: step: 540/529, loss: 0.12213268131017685
2023-01-23 02:04:12.866698: step: 544/529, loss: 0.0021313666366040707
2023-01-23 02:04:13.962208: step: 548/529, loss: 0.007439231965690851
2023-01-23 02:04:15.037974: step: 552/529, loss: 0.006300831213593483
2023-01-23 02:04:16.151116: step: 556/529, loss: 0.0004946708795614541
2023-01-23 02:04:17.262865: step: 560/529, loss: 0.03266744688153267
2023-01-23 02:04:18.386901: step: 564/529, loss: 0.006650161929428577
2023-01-23 02:04:19.494466: step: 568/529, loss: 0.003451061435043812
2023-01-23 02:04:20.593114: step: 572/529, loss: 0.030447769910097122
2023-01-23 02:04:21.695833: step: 576/529, loss: 0.01534972246736288
2023-01-23 02:04:22.802196: step: 580/529, loss: 0.06121664121747017
2023-01-23 02:04:23.927019: step: 584/529, loss: 0.07532940059900284
2023-01-23 02:04:25.041997: step: 588/529, loss: 0.00793371256440878
2023-01-23 02:04:26.142924: step: 592/529, loss: 0.036535073071718216
2023-01-23 02:04:27.247900: step: 596/529, loss: 0.034652043133974075
2023-01-23 02:04:28.365612: step: 600/529, loss: 0.06478134542703629
2023-01-23 02:04:29.448585: step: 604/529, loss: 0.014225340448319912
2023-01-23 02:04:30.539875: step: 608/529, loss: 0.01539382990449667
2023-01-23 02:04:31.637611: step: 612/529, loss: 0.008771324530243874
2023-01-23 02:04:32.745581: step: 616/529, loss: 0.05536933243274689
2023-01-23 02:04:33.856968: step: 620/529, loss: 0.036444857716560364
2023-01-23 02:04:34.973635: step: 624/529, loss: 0.003640127135440707
2023-01-23 02:04:36.086903: step: 628/529, loss: 0.36066606640815735
2023-01-23 02:04:37.197143: step: 632/529, loss: 0.16692844033241272
2023-01-23 02:04:38.297789: step: 636/529, loss: 0.03918934240937233
2023-01-23 02:04:39.401927: step: 640/529, loss: 0.003963756840676069
2023-01-23 02:04:40.520017: step: 644/529, loss: 0.03221387788653374
2023-01-23 02:04:41.636327: step: 648/529, loss: 0.0691455826163292
2023-01-23 02:04:42.709724: step: 652/529, loss: 0.024606704711914062
2023-01-23 02:04:43.804897: step: 656/529, loss: 0.02569131925702095
2023-01-23 02:04:44.912980: step: 660/529, loss: 0.050624653697013855
2023-01-23 02:04:45.993557: step: 664/529, loss: 0.0037870886735618114
2023-01-23 02:04:47.103368: step: 668/529, loss: 0.006491470150649548
2023-01-23 02:04:48.216840: step: 672/529, loss: 0.1585306078195572
2023-01-23 02:04:49.313697: step: 676/529, loss: 0.02358388900756836
2023-01-23 02:04:50.406339: step: 680/529, loss: 0.5519237518310547
2023-01-23 02:04:51.527593: step: 684/529, loss: 0.0049301148392260075
2023-01-23 02:04:52.618200: step: 688/529, loss: 0.287584513425827
2023-01-23 02:04:53.706453: step: 692/529, loss: 0.024935245513916016
2023-01-23 02:04:54.810693: step: 696/529, loss: 0.004320716951042414
2023-01-23 02:04:55.937111: step: 700/529, loss: 0.0030488967895507812
2023-01-23 02:04:57.063316: step: 704/529, loss: 0.03374214097857475
2023-01-23 02:04:58.172632: step: 708/529, loss: 0.03261518478393555
2023-01-23 02:04:59.292431: step: 712/529, loss: 0.043166350573301315
2023-01-23 02:05:00.386951: step: 716/529, loss: 0.009520197287201881
2023-01-23 02:05:01.519853: step: 720/529, loss: 0.002094268798828125
2023-01-23 02:05:02.666798: step: 724/529, loss: 0.07955612987279892
2023-01-23 02:05:03.792340: step: 728/529, loss: 0.002158737275749445
2023-01-23 02:05:04.894215: step: 732/529, loss: 0.0661383643746376
2023-01-23 02:05:05.990008: step: 736/529, loss: 0.028620148077607155
2023-01-23 02:05:07.090528: step: 740/529, loss: 0.004321098327636719
2023-01-23 02:05:08.197849: step: 744/529, loss: 0.06198091432452202
2023-01-23 02:05:09.292224: step: 748/529, loss: 0.01991443708539009
2023-01-23 02:05:10.380432: step: 752/529, loss: 0.021515274420380592
2023-01-23 02:05:11.471606: step: 756/529, loss: 0.005078697111457586
2023-01-23 02:05:12.560211: step: 760/529, loss: 0.046824172139167786
2023-01-23 02:05:13.665515: step: 764/529, loss: 0.027736950665712357
2023-01-23 02:05:14.774257: step: 768/529, loss: 0.0024580953177064657
2023-01-23 02:05:15.915623: step: 772/529, loss: 0.019012451171875
2023-01-23 02:05:17.026008: step: 776/529, loss: 0.017098141834139824
2023-01-23 02:05:18.116552: step: 780/529, loss: 0.026880167424678802
2023-01-23 02:05:19.287059: step: 784/529, loss: 0.00014579296112060547
2023-01-23 02:05:20.414721: step: 788/529, loss: 0.02515239641070366
2023-01-23 02:05:21.591059: step: 792/529, loss: 0.024906732141971588
2023-01-23 02:05:22.695509: step: 796/529, loss: 0.0066581727005541325
2023-01-23 02:05:23.810380: step: 800/529, loss: 0.017708491533994675
2023-01-23 02:05:24.929396: step: 804/529, loss: 0.06911754608154297
2023-01-23 02:05:26.030535: step: 808/529, loss: 0.0449383519589901
2023-01-23 02:05:27.140190: step: 812/529, loss: 0.15337209403514862
2023-01-23 02:05:28.233716: step: 816/529, loss: 0.0415617935359478
2023-01-23 02:05:29.331866: step: 820/529, loss: 0.04999237135052681
2023-01-23 02:05:30.447514: step: 824/529, loss: 0.09302043914794922
2023-01-23 02:05:31.578125: step: 828/529, loss: 0.004516792483627796
2023-01-23 02:05:32.669859: step: 832/529, loss: 0.048300981521606445
2023-01-23 02:05:33.788986: step: 836/529, loss: 0.005957460962235928
2023-01-23 02:05:34.889132: step: 840/529, loss: 0.006057166960090399
2023-01-23 02:05:36.012429: step: 844/529, loss: 0.004037285223603249
2023-01-23 02:05:37.120701: step: 848/529, loss: 0.06434802711009979
2023-01-23 02:05:38.251368: step: 852/529, loss: 0.002489280654117465
2023-01-23 02:05:39.351412: step: 856/529, loss: 0.23927058279514313
2023-01-23 02:05:40.462774: step: 860/529, loss: 0.005560684017837048
2023-01-23 02:05:41.575560: step: 864/529, loss: 0.043326377868652344
2023-01-23 02:05:42.692251: step: 868/529, loss: 0.007733345031738281
2023-01-23 02:05:43.793940: step: 872/529, loss: 0.07311849296092987
2023-01-23 02:05:44.911270: step: 876/529, loss: 3.06129441014491e-05
2023-01-23 02:05:46.030039: step: 880/529, loss: 0.00482940673828125
2023-01-23 02:05:47.170736: step: 884/529, loss: 0.08264847099781036
2023-01-23 02:05:48.278098: step: 888/529, loss: 0.0009354114881716669
2023-01-23 02:05:49.419092: step: 892/529, loss: 0.15960197150707245
2023-01-23 02:05:50.531329: step: 896/529, loss: 0.004975604824721813
2023-01-23 02:05:51.636291: step: 900/529, loss: 0.054918862879276276
2023-01-23 02:05:52.710687: step: 904/529, loss: 0.01359262503683567
2023-01-23 02:05:53.840596: step: 908/529, loss: 0.05474882200360298
2023-01-23 02:05:54.943211: step: 912/529, loss: 0.003283691592514515
2023-01-23 02:05:56.054345: step: 916/529, loss: 0.00036773679312318563
2023-01-23 02:05:57.175273: step: 920/529, loss: 0.0027414322830736637
2023-01-23 02:05:58.293349: step: 924/529, loss: 0.024626540020108223
2023-01-23 02:05:59.400938: step: 928/529, loss: 0.0008567810291424394
2023-01-23 02:06:00.501587: step: 932/529, loss: 0.060804370790719986
2023-01-23 02:06:01.606182: step: 936/529, loss: 0.006113338749855757
2023-01-23 02:06:02.686397: step: 940/529, loss: 0.04157848656177521
2023-01-23 02:06:03.805155: step: 944/529, loss: 0.01965959183871746
2023-01-23 02:06:04.937038: step: 948/529, loss: 0.27173954248428345
2023-01-23 02:06:06.051651: step: 952/529, loss: 0.20857134461402893
2023-01-23 02:06:07.168477: step: 956/529, loss: 0.008108711801469326
2023-01-23 02:06:08.287421: step: 960/529, loss: 0.11366715282201767
2023-01-23 02:06:09.410715: step: 964/529, loss: 0.02399921603500843
2023-01-23 02:06:10.531014: step: 968/529, loss: 0.028089476749300957
2023-01-23 02:06:11.629968: step: 972/529, loss: 0.11822175979614258
2023-01-23 02:06:12.703417: step: 976/529, loss: 0.01480865478515625
2023-01-23 02:06:13.822944: step: 980/529, loss: 0.017039109021425247
2023-01-23 02:06:14.928778: step: 984/529, loss: 0.036610983312129974
2023-01-23 02:06:16.020842: step: 988/529, loss: 0.006156873889267445
2023-01-23 02:06:17.136577: step: 992/529, loss: 0.008353233337402344
2023-01-23 02:06:18.244336: step: 996/529, loss: 0.15275651216506958
2023-01-23 02:06:19.384180: step: 1000/529, loss: 0.022661972790956497
2023-01-23 02:06:20.461726: step: 1004/529, loss: 0.005509567447006702
2023-01-23 02:06:21.594231: step: 1008/529, loss: 0.0036905291490256786
2023-01-23 02:06:22.697944: step: 1012/529, loss: 0.01190652884542942
2023-01-23 02:06:23.783638: step: 1016/529, loss: 0.0016812323592603207
2023-01-23 02:06:24.883881: step: 1020/529, loss: 0.0014493941562250257
2023-01-23 02:06:26.000493: step: 1024/529, loss: 0.01684284210205078
2023-01-23 02:06:27.142863: step: 1028/529, loss: 0.009927082806825638
2023-01-23 02:06:28.255338: step: 1032/529, loss: 0.15844497084617615
2023-01-23 02:06:29.387980: step: 1036/529, loss: 1.012674331665039
2023-01-23 02:06:30.472788: step: 1040/529, loss: 0.05566806718707085
2023-01-23 02:06:31.575183: step: 1044/529, loss: 0.04399833828210831
2023-01-23 02:06:32.702757: step: 1048/529, loss: 0.19140681624412537
2023-01-23 02:06:33.798912: step: 1052/529, loss: 0.010280419141054153
2023-01-23 02:06:34.935890: step: 1056/529, loss: 0.13566331565380096
2023-01-23 02:06:36.057267: step: 1060/529, loss: 0.0197919849306345
2023-01-23 02:06:37.177501: step: 1064/529, loss: 0.12768897414207458
2023-01-23 02:06:38.285503: step: 1068/529, loss: 0.023880768567323685
2023-01-23 02:06:39.388113: step: 1072/529, loss: 2.784109592437744
2023-01-23 02:06:40.485040: step: 1076/529, loss: 0.014256644994020462
2023-01-23 02:06:41.586350: step: 1080/529, loss: 0.03602752462029457
2023-01-23 02:06:42.680772: step: 1084/529, loss: 0.024809647351503372
2023-01-23 02:06:43.782437: step: 1088/529, loss: 0.017095183953642845
2023-01-23 02:06:44.906117: step: 1092/529, loss: 0.061055686324834824
2023-01-23 02:06:46.006686: step: 1096/529, loss: 0.07091826945543289
2023-01-23 02:06:47.102220: step: 1100/529, loss: 0.013196468353271484
2023-01-23 02:06:48.205164: step: 1104/529, loss: 0.0017759323818609118
2023-01-23 02:06:49.300153: step: 1108/529, loss: 0.0013233184581622481
2023-01-23 02:06:50.419871: step: 1112/529, loss: 0.012111281976103783
2023-01-23 02:06:51.520716: step: 1116/529, loss: 0.044538021087646484
2023-01-23 02:06:52.619516: step: 1120/529, loss: 0.03583526611328125
2023-01-23 02:06:53.751568: step: 1124/529, loss: 0.006453681271523237
2023-01-23 02:06:54.855897: step: 1128/529, loss: 0.05612201616168022
2023-01-23 02:06:56.016611: step: 1132/529, loss: 0.0349210724234581
2023-01-23 02:06:57.153195: step: 1136/529, loss: 0.015649283304810524
2023-01-23 02:06:58.262522: step: 1140/529, loss: 0.07226867973804474
2023-01-23 02:06:59.371814: step: 1144/529, loss: 0.8925444483757019
2023-01-23 02:07:00.500925: step: 1148/529, loss: 0.00380878453142941
2023-01-23 02:07:01.639087: step: 1152/529, loss: 0.03990011289715767
2023-01-23 02:07:02.767317: step: 1156/529, loss: 0.005954170133918524
2023-01-23 02:07:03.882404: step: 1160/529, loss: 0.001020240830257535
2023-01-23 02:07:04.996782: step: 1164/529, loss: 0.33216121792793274
2023-01-23 02:07:06.109647: step: 1168/529, loss: 0.017474651336669922
2023-01-23 02:07:07.252486: step: 1172/529, loss: 0.04607431963086128
2023-01-23 02:07:08.397050: step: 1176/529, loss: 0.006637764163315296
2023-01-23 02:07:09.512778: step: 1180/529, loss: 0.060863494873046875
2023-01-23 02:07:10.619363: step: 1184/529, loss: 0.0466187484562397
2023-01-23 02:07:11.734985: step: 1188/529, loss: 0.014934349805116653
2023-01-23 02:07:12.853157: step: 1192/529, loss: 0.021178342401981354
2023-01-23 02:07:13.968223: step: 1196/529, loss: 0.009847735986113548
2023-01-23 02:07:15.072567: step: 1200/529, loss: 0.012802696786820889
2023-01-23 02:07:16.170621: step: 1204/529, loss: 0.0938815101981163
2023-01-23 02:07:17.265150: step: 1208/529, loss: 0.1923181563615799
2023-01-23 02:07:18.397941: step: 1212/529, loss: 0.03403129428625107
2023-01-23 02:07:19.498122: step: 1216/529, loss: 0.0035559178795665503
2023-01-23 02:07:20.612235: step: 1220/529, loss: 0.13441739976406097
2023-01-23 02:07:21.721631: step: 1224/529, loss: 0.014824485406279564
2023-01-23 02:07:22.819452: step: 1228/529, loss: 0.0183365810662508
2023-01-23 02:07:23.934404: step: 1232/529, loss: 0.028984833508729935
2023-01-23 02:07:25.075944: step: 1236/529, loss: 0.04728889465332031
2023-01-23 02:07:26.205537: step: 1240/529, loss: 0.013409232720732689
2023-01-23 02:07:27.293671: step: 1244/529, loss: 0.21374927461147308
2023-01-23 02:07:28.433818: step: 1248/529, loss: 0.06234750896692276
2023-01-23 02:07:29.526333: step: 1252/529, loss: 0.003662490751594305
2023-01-23 02:07:30.654939: step: 1256/529, loss: 0.05922403559088707
2023-01-23 02:07:31.740179: step: 1260/529, loss: 0.06785106658935547
2023-01-23 02:07:32.838631: step: 1264/529, loss: 0.004977608099579811
2023-01-23 02:07:33.933510: step: 1268/529, loss: 0.003946209326386452
2023-01-23 02:07:35.034860: step: 1272/529, loss: 0.013188743032515049
2023-01-23 02:07:36.148465: step: 1276/529, loss: 0.027324475347995758
2023-01-23 02:07:37.286850: step: 1280/529, loss: 0.012353707104921341
2023-01-23 02:07:38.405504: step: 1284/529, loss: 0.08095379173755646
2023-01-23 02:07:39.516640: step: 1288/529, loss: 0.010207748971879482
2023-01-23 02:07:40.614830: step: 1292/529, loss: 0.008919095620512962
2023-01-23 02:07:41.713024: step: 1296/529, loss: 0.001168060232885182
2023-01-23 02:07:42.827163: step: 1300/529, loss: 0.015664292499423027
2023-01-23 02:07:43.943633: step: 1304/529, loss: 0.03494663164019585
2023-01-23 02:07:45.050549: step: 1308/529, loss: 0.01756284199655056
2023-01-23 02:07:46.199898: step: 1312/529, loss: 0.011372661218047142
2023-01-23 02:07:47.290470: step: 1316/529, loss: 0.01863689348101616
2023-01-23 02:07:48.401899: step: 1320/529, loss: 0.005563593469560146
2023-01-23 02:07:49.564125: step: 1324/529, loss: 0.025613784790039062
2023-01-23 02:07:50.680510: step: 1328/529, loss: 0.05599260330200195
2023-01-23 02:07:51.816551: step: 1332/529, loss: 0.012350654229521751
2023-01-23 02:07:52.925123: step: 1336/529, loss: 0.10752163082361221
2023-01-23 02:07:54.035771: step: 1340/529, loss: 0.044048357754945755
2023-01-23 02:07:55.181859: step: 1344/529, loss: 0.04717312008142471
2023-01-23 02:07:56.269633: step: 1348/529, loss: 0.025150252506136894
2023-01-23 02:07:57.393696: step: 1352/529, loss: 0.01689434051513672
2023-01-23 02:07:58.497935: step: 1356/529, loss: 0.5690412521362305
2023-01-23 02:07:59.652693: step: 1360/529, loss: 0.11586761474609375
2023-01-23 02:08:00.783939: step: 1364/529, loss: 0.05314836651086807
2023-01-23 02:08:01.925214: step: 1368/529, loss: 0.04475117102265358
2023-01-23 02:08:03.057622: step: 1372/529, loss: 0.004604530055075884
2023-01-23 02:08:04.167443: step: 1376/529, loss: 0.01128406636416912
2023-01-23 02:08:05.266130: step: 1380/529, loss: 0.031459711492061615
2023-01-23 02:08:06.357464: step: 1384/529, loss: 0.030724240466952324
2023-01-23 02:08:07.451245: step: 1388/529, loss: 0.02933340147137642
2023-01-23 02:08:08.560765: step: 1392/529, loss: 0.04226074367761612
2023-01-23 02:08:09.705027: step: 1396/529, loss: 0.0802769660949707
2023-01-23 02:08:10.824434: step: 1400/529, loss: 0.029257584363222122
2023-01-23 02:08:11.940515: step: 1404/529, loss: 0.03714311122894287
2023-01-23 02:08:13.061142: step: 1408/529, loss: 0.003967666532844305
2023-01-23 02:08:14.166421: step: 1412/529, loss: 0.008970069698989391
2023-01-23 02:08:15.264866: step: 1416/529, loss: 0.00018949508375953883
2023-01-23 02:08:16.346820: step: 1420/529, loss: 0.0017972945934161544
2023-01-23 02:08:17.483592: step: 1424/529, loss: 0.05047006532549858
2023-01-23 02:08:18.622267: step: 1428/529, loss: 0.01947307586669922
2023-01-23 02:08:19.820441: step: 1432/529, loss: 0.05660073459148407
2023-01-23 02:08:20.936972: step: 1436/529, loss: 0.0013745308388024569
2023-01-23 02:08:22.044722: step: 1440/529, loss: 0.060073185712099075
2023-01-23 02:08:23.161028: step: 1444/529, loss: 0.010673332959413528
2023-01-23 02:08:24.287119: step: 1448/529, loss: 0.034828949719667435
2023-01-23 02:08:25.407809: step: 1452/529, loss: 0.07121066749095917
2023-01-23 02:08:26.547191: step: 1456/529, loss: 0.038569070398807526
2023-01-23 02:08:27.658386: step: 1460/529, loss: 0.04711113125085831
2023-01-23 02:08:28.770392: step: 1464/529, loss: 0.02956237830221653
2023-01-23 02:08:29.928156: step: 1468/529, loss: 0.0025766375474631786
2023-01-23 02:08:31.031408: step: 1472/529, loss: 0.012780284509062767
2023-01-23 02:08:32.122018: step: 1476/529, loss: 0.03177938610315323
2023-01-23 02:08:33.249046: step: 1480/529, loss: 0.05872516706585884
2023-01-23 02:08:34.347824: step: 1484/529, loss: 0.0188769344240427
2023-01-23 02:08:35.458252: step: 1488/529, loss: 0.022259997203946114
2023-01-23 02:08:36.560703: step: 1492/529, loss: 0.00033202170743606985
2023-01-23 02:08:37.681146: step: 1496/529, loss: 0.029712343588471413
2023-01-23 02:08:38.796594: step: 1500/529, loss: 0.04746971279382706
2023-01-23 02:08:39.925512: step: 1504/529, loss: 0.02252502366900444
2023-01-23 02:08:41.045442: step: 1508/529, loss: 0.04196300730109215
2023-01-23 02:08:42.193311: step: 1512/529, loss: 0.034624673426151276
2023-01-23 02:08:43.313457: step: 1516/529, loss: 0.007928848266601562
2023-01-23 02:08:44.430660: step: 1520/529, loss: 0.0027473450172692537
2023-01-23 02:08:45.522213: step: 1524/529, loss: 0.020561981946229935
2023-01-23 02:08:46.616601: step: 1528/529, loss: 0.005965805146843195
2023-01-23 02:08:47.738764: step: 1532/529, loss: 0.08079500496387482
2023-01-23 02:08:48.872459: step: 1536/529, loss: 0.11873187869787216
2023-01-23 02:08:49.999676: step: 1540/529, loss: 0.28856000304222107
2023-01-23 02:08:51.136504: step: 1544/529, loss: 0.0011587142944335938
2023-01-23 02:08:52.239249: step: 1548/529, loss: 0.0003411293146200478
2023-01-23 02:08:53.334279: step: 1552/529, loss: 0.0868481695652008
2023-01-23 02:08:54.417559: step: 1556/529, loss: 0.01118860300630331
2023-01-23 02:08:55.526712: step: 1560/529, loss: 0.0008830070728436112
2023-01-23 02:08:56.647932: step: 1564/529, loss: 0.009162998758256435
2023-01-23 02:08:57.745403: step: 1568/529, loss: 0.005147743504494429
2023-01-23 02:08:58.875123: step: 1572/529, loss: 0.0026901247911155224
2023-01-23 02:08:59.998597: step: 1576/529, loss: 0.010972786694765091
2023-01-23 02:09:01.104619: step: 1580/529, loss: 0.05199165269732475
2023-01-23 02:09:02.232859: step: 1584/529, loss: 0.14903374016284943
2023-01-23 02:09:03.372395: step: 1588/529, loss: 0.06888733059167862
2023-01-23 02:09:04.491850: step: 1592/529, loss: 0.026501081883907318
2023-01-23 02:09:05.592394: step: 1596/529, loss: 0.02939748764038086
2023-01-23 02:09:06.713622: step: 1600/529, loss: 0.023587321862578392
2023-01-23 02:09:07.849206: step: 1604/529, loss: 0.02911682054400444
2023-01-23 02:09:08.949166: step: 1608/529, loss: 0.004750251770019531
2023-01-23 02:09:10.083934: step: 1612/529, loss: 0.022888565436005592
2023-01-23 02:09:11.206711: step: 1616/529, loss: 0.05539379268884659
2023-01-23 02:09:12.320534: step: 1620/529, loss: 0.019959401339292526
2023-01-23 02:09:13.392805: step: 1624/529, loss: 0.04987926408648491
2023-01-23 02:09:14.491170: step: 1628/529, loss: 0.00900125503540039
2023-01-23 02:09:15.610053: step: 1632/529, loss: 0.0690908432006836
2023-01-23 02:09:16.739733: step: 1636/529, loss: 0.012089347466826439
2023-01-23 02:09:17.856609: step: 1640/529, loss: 0.013158036395907402
2023-01-23 02:09:18.931548: step: 1644/529, loss: 0.007267570123076439
2023-01-23 02:09:20.067627: step: 1648/529, loss: 0.009405136108398438
2023-01-23 02:09:21.193020: step: 1652/529, loss: 0.038481712341308594
2023-01-23 02:09:22.318304: step: 1656/529, loss: 0.05638699233531952
2023-01-23 02:09:23.388699: step: 1660/529, loss: 0.04726886749267578
2023-01-23 02:09:24.509234: step: 1664/529, loss: 0.13326320052146912
2023-01-23 02:09:25.642529: step: 1668/529, loss: 0.04291302338242531
2023-01-23 02:09:26.735381: step: 1672/529, loss: 0.08542804419994354
2023-01-23 02:09:27.868381: step: 1676/529, loss: 0.006975841708481312
2023-01-23 02:09:28.954884: step: 1680/529, loss: 4.4417382014216855e-05
2023-01-23 02:09:30.065906: step: 1684/529, loss: 0.05392418056726456
2023-01-23 02:09:31.169510: step: 1688/529, loss: 0.00897512398660183
2023-01-23 02:09:32.277108: step: 1692/529, loss: 0.008361482992768288
2023-01-23 02:09:33.398186: step: 1696/529, loss: 0.3334774971008301
2023-01-23 02:09:34.487540: step: 1700/529, loss: 0.09300556033849716
2023-01-23 02:09:35.607550: step: 1704/529, loss: 0.028688624501228333
2023-01-23 02:09:36.692782: step: 1708/529, loss: 0.0024240135680884123
2023-01-23 02:09:37.799996: step: 1712/529, loss: 0.07397708296775818
2023-01-23 02:09:38.932740: step: 1716/529, loss: 0.2645646035671234
2023-01-23 02:09:40.049875: step: 1720/529, loss: 0.02503833919763565
2023-01-23 02:09:41.150623: step: 1724/529, loss: 0.004874467849731445
2023-01-23 02:09:42.254491: step: 1728/529, loss: 7.82012939453125e-05
2023-01-23 02:09:43.348178: step: 1732/529, loss: 0.8507784008979797
2023-01-23 02:09:44.474819: step: 1736/529, loss: 0.1318719983100891
2023-01-23 02:09:45.601742: step: 1740/529, loss: 0.021417807787656784
2023-01-23 02:09:46.703319: step: 1744/529, loss: 0.0011737822787836194
2023-01-23 02:09:47.809750: step: 1748/529, loss: 0.018645858392119408
2023-01-23 02:09:48.944914: step: 1752/529, loss: 0.02441110834479332
2023-01-23 02:09:50.099253: step: 1756/529, loss: 0.07416267693042755
2023-01-23 02:09:51.199204: step: 1760/529, loss: 0.016349315643310547
2023-01-23 02:09:52.316591: step: 1764/529, loss: 0.03471078723669052
2023-01-23 02:09:53.426863: step: 1768/529, loss: 0.03573598712682724
2023-01-23 02:09:54.538703: step: 1772/529, loss: 0.009135628119111061
2023-01-23 02:09:55.650767: step: 1776/529, loss: 0.030147649347782135
2023-01-23 02:09:56.792009: step: 1780/529, loss: 0.0015956878196448088
2023-01-23 02:09:57.884064: step: 1784/529, loss: 0.3427744507789612
2023-01-23 02:09:58.988506: step: 1788/529, loss: 0.02135854959487915
2023-01-23 02:10:00.072102: step: 1792/529, loss: 0.027435969561338425
2023-01-23 02:10:01.181528: step: 1796/529, loss: 0.039005398750305176
2023-01-23 02:10:02.301148: step: 1800/529, loss: 0.022168828174471855
2023-01-23 02:10:03.409448: step: 1804/529, loss: 0.04677620157599449
2023-01-23 02:10:04.493113: step: 1808/529, loss: 0.03503427654504776
2023-01-23 02:10:05.584107: step: 1812/529, loss: 0.010628987103700638
2023-01-23 02:10:06.686318: step: 1816/529, loss: 0.019567154347896576
2023-01-23 02:10:07.790469: step: 1820/529, loss: 0.01189203280955553
2023-01-23 02:10:08.934257: step: 1824/529, loss: 0.0355776771903038
2023-01-23 02:10:10.059582: step: 1828/529, loss: 0.013114642351865768
2023-01-23 02:10:11.153919: step: 1832/529, loss: 0.027872467413544655
2023-01-23 02:10:12.279182: step: 1836/529, loss: 0.13127270340919495
2023-01-23 02:10:13.414017: step: 1840/529, loss: 0.007633971981704235
2023-01-23 02:10:14.517310: step: 1844/529, loss: 0.03973674774169922
2023-01-23 02:10:15.602069: step: 1848/529, loss: 0.014048004522919655
2023-01-23 02:10:16.733702: step: 1852/529, loss: 0.011321032419800758
2023-01-23 02:10:17.859015: step: 1856/529, loss: 0.006206703372299671
2023-01-23 02:10:18.964458: step: 1860/529, loss: 0.13167135417461395
2023-01-23 02:10:20.071527: step: 1864/529, loss: 0.06124553829431534
2023-01-23 02:10:21.174121: step: 1868/529, loss: 0.01782989501953125
2023-01-23 02:10:22.264552: step: 1872/529, loss: 0.04866466671228409
2023-01-23 02:10:23.364881: step: 1876/529, loss: 0.006202983669936657
2023-01-23 02:10:24.473405: step: 1880/529, loss: 0.011512374505400658
2023-01-23 02:10:25.561920: step: 1884/529, loss: 0.004651069641113281
2023-01-23 02:10:26.657512: step: 1888/529, loss: 0.013984394259750843
2023-01-23 02:10:27.757536: step: 1892/529, loss: 0.05618901178240776
2023-01-23 02:10:28.858501: step: 1896/529, loss: 0.014040661044418812
2023-01-23 02:10:29.949630: step: 1900/529, loss: 0.03840827941894531
2023-01-23 02:10:31.047790: step: 1904/529, loss: 0.040229037404060364
2023-01-23 02:10:32.165604: step: 1908/529, loss: 0.019501496106386185
2023-01-23 02:10:33.272138: step: 1912/529, loss: 0.23917751014232635
2023-01-23 02:10:34.406071: step: 1916/529, loss: 0.11080218106508255
2023-01-23 02:10:35.511054: step: 1920/529, loss: 0.08093462139368057
2023-01-23 02:10:36.650891: step: 1924/529, loss: 0.061968617141246796
2023-01-23 02:10:37.758806: step: 1928/529, loss: 0.012190151028335094
2023-01-23 02:10:38.852305: step: 1932/529, loss: 0.04579916223883629
2023-01-23 02:10:39.989403: step: 1936/529, loss: 0.05415744706988335
2023-01-23 02:10:41.116270: step: 1940/529, loss: 0.024793434888124466
2023-01-23 02:10:42.248885: step: 1944/529, loss: 0.036486051976680756
2023-01-23 02:10:43.375112: step: 1948/529, loss: 0.021683646366000175
2023-01-23 02:10:44.463537: step: 1952/529, loss: 0.10531672835350037
2023-01-23 02:10:45.610021: step: 1956/529, loss: 0.04025259241461754
2023-01-23 02:10:46.743445: step: 1960/529, loss: 0.005909156985580921
2023-01-23 02:10:47.829751: step: 1964/529, loss: 0.029218867421150208
2023-01-23 02:10:48.975598: step: 1968/529, loss: 0.023702239617705345
2023-01-23 02:10:50.097826: step: 1972/529, loss: 0.012431717477738857
2023-01-23 02:10:51.214542: step: 1976/529, loss: 0.012362003326416016
2023-01-23 02:10:52.345900: step: 1980/529, loss: 0.10852088779211044
2023-01-23 02:10:53.453394: step: 1984/529, loss: 0.03397426754236221
2023-01-23 02:10:54.550548: step: 1988/529, loss: 0.017452050000429153
2023-01-23 02:10:55.664788: step: 1992/529, loss: 0.005427340045571327
2023-01-23 02:10:56.787984: step: 1996/529, loss: 0.05447263643145561
2023-01-23 02:10:57.904842: step: 2000/529, loss: 0.05303196981549263
2023-01-23 02:10:59.011943: step: 2004/529, loss: 0.029610633850097656
2023-01-23 02:11:00.097171: step: 2008/529, loss: 0.01581287384033203
2023-01-23 02:11:01.197452: step: 2012/529, loss: 0.01895303837954998
2023-01-23 02:11:02.299285: step: 2016/529, loss: 0.012185860425233841
2023-01-23 02:11:03.383836: step: 2020/529, loss: 0.03466777876019478
2023-01-23 02:11:04.509762: step: 2024/529, loss: 0.05949373543262482
2023-01-23 02:11:05.631733: step: 2028/529, loss: 0.000171661376953125
2023-01-23 02:11:06.749964: step: 2032/529, loss: 0.005026054568588734
2023-01-23 02:11:07.846458: step: 2036/529, loss: 0.0004886210081167519
2023-01-23 02:11:08.944074: step: 2040/529, loss: 0.01560983620584011
2023-01-23 02:11:10.055721: step: 2044/529, loss: 0.04823331907391548
2023-01-23 02:11:11.185354: step: 2048/529, loss: 0.013470268808305264
2023-01-23 02:11:12.294829: step: 2052/529, loss: 0.05151491239666939
2023-01-23 02:11:13.448554: step: 2056/529, loss: 0.024869920685887337
2023-01-23 02:11:14.569342: step: 2060/529, loss: 0.020335961133241653
2023-01-23 02:11:15.706801: step: 2064/529, loss: 0.01641559600830078
2023-01-23 02:11:16.817242: step: 2068/529, loss: 0.012571334838867188
2023-01-23 02:11:17.935621: step: 2072/529, loss: 0.01003799494355917
2023-01-23 02:11:19.071783: step: 2076/529, loss: 0.044074155390262604
2023-01-23 02:11:20.170651: step: 2080/529, loss: 0.023874282836914062
2023-01-23 02:11:21.297087: step: 2084/529, loss: 0.04250383377075195
2023-01-23 02:11:22.406794: step: 2088/529, loss: 0.036631397902965546
2023-01-23 02:11:23.511873: step: 2092/529, loss: 0.06407790631055832
2023-01-23 02:11:24.621382: step: 2096/529, loss: 0.001379680703394115
2023-01-23 02:11:25.753507: step: 2100/529, loss: 0.05193347856402397
2023-01-23 02:11:26.868669: step: 2104/529, loss: 0.03535137325525284
2023-01-23 02:11:27.999454: step: 2108/529, loss: 0.031992726027965546
2023-01-23 02:11:29.092500: step: 2112/529, loss: 0.002292537596076727
2023-01-23 02:11:30.213656: step: 2116/529, loss: 0.024569178000092506
==================================================
Loss: 0.053
--------------------
Dev: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5465116279069767, 'r': 0.8703703703703703, 'f1': 0.6714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4772727272727273, 'r': 0.5833333333333334, 'f1': 0.5250000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 02:12:17.615725: step: 4/529, loss: 0.01759509928524494
2023-01-23 02:12:18.730293: step: 8/529, loss: 0.005558204837143421
2023-01-23 02:12:19.821352: step: 12/529, loss: 0.002117633819580078
2023-01-23 02:12:20.939970: step: 16/529, loss: 0.008744430728256702
2023-01-23 02:12:22.032071: step: 20/529, loss: 0.008201027289032936
2023-01-23 02:12:23.144591: step: 24/529, loss: 0.0010945319663733244
2023-01-23 02:12:24.252178: step: 28/529, loss: 0.0016349792713299394
2023-01-23 02:12:25.338201: step: 32/529, loss: 0.013190556317567825
2023-01-23 02:12:26.422132: step: 36/529, loss: 0.01243896596133709
2023-01-23 02:12:27.532252: step: 40/529, loss: 0.005727005191147327
2023-01-23 02:12:28.624921: step: 44/529, loss: 0.007983779534697533
2023-01-23 02:12:29.747332: step: 48/529, loss: 0.0060284677892923355
2023-01-23 02:12:30.858403: step: 52/529, loss: 0.0008068084716796875
2023-01-23 02:12:31.937820: step: 56/529, loss: 0.010333872400224209
2023-01-23 02:12:33.011409: step: 60/529, loss: 0.005064924713224173
2023-01-23 02:12:34.113789: step: 64/529, loss: 0.019730854779481888
2023-01-23 02:12:35.204729: step: 68/529, loss: 0.0005346297984942794
2023-01-23 02:12:36.343879: step: 72/529, loss: 0.010563087649643421
2023-01-23 02:12:37.440661: step: 76/529, loss: 0.043862439692020416
2023-01-23 02:12:38.552789: step: 80/529, loss: 0.04054107517004013
2023-01-23 02:12:39.639876: step: 84/529, loss: 0.025189924985170364
2023-01-23 02:12:40.737779: step: 88/529, loss: 0.0018634796142578125
2023-01-23 02:12:41.861582: step: 92/529, loss: 0.002568149706348777
2023-01-23 02:12:42.974925: step: 96/529, loss: 0.04394207149744034
2023-01-23 02:12:44.119975: step: 100/529, loss: 0.059703826904296875
2023-01-23 02:12:45.239509: step: 104/529, loss: 0.006520175840705633
2023-01-23 02:12:46.361025: step: 108/529, loss: 0.006911659147590399
2023-01-23 02:12:47.453281: step: 112/529, loss: 0.4324420392513275
2023-01-23 02:12:48.568337: step: 116/529, loss: 0.00030512810917571187
2023-01-23 02:12:49.652961: step: 120/529, loss: 0.04342012479901314
2023-01-23 02:12:50.760259: step: 124/529, loss: 0.007519531529396772
2023-01-23 02:12:51.877454: step: 128/529, loss: 0.006271171383559704
2023-01-23 02:12:52.996873: step: 132/529, loss: 0.07997055351734161
2023-01-23 02:12:54.099944: step: 136/529, loss: 0.03751564025878906
2023-01-23 02:12:55.189395: step: 140/529, loss: 0.011118745431303978
2023-01-23 02:12:56.293212: step: 144/529, loss: 0.019529057666659355
2023-01-23 02:12:57.408286: step: 148/529, loss: 0.004872131161391735
2023-01-23 02:12:58.533714: step: 152/529, loss: 0.030228614807128906
2023-01-23 02:12:59.652215: step: 156/529, loss: 0.01074142474681139
2023-01-23 02:13:00.759177: step: 160/529, loss: 0.0026817324105650187
2023-01-23 02:13:01.862327: step: 164/529, loss: 0.06483488529920578
2023-01-23 02:13:02.970715: step: 168/529, loss: 0.0009596824529580772
2023-01-23 02:13:04.081230: step: 172/529, loss: 0.01357660349458456
2023-01-23 02:13:05.181294: step: 176/529, loss: 0.012223434634506702
2023-01-23 02:13:06.316687: step: 180/529, loss: 0.0004608154413290322
2023-01-23 02:13:07.464346: step: 184/529, loss: 0.005642223171889782
2023-01-23 02:13:08.562881: step: 188/529, loss: 0.027587413787841797
2023-01-23 02:13:09.666985: step: 192/529, loss: 0.0011214256519451737
2023-01-23 02:13:10.786428: step: 196/529, loss: 0.04644327238202095
2023-01-23 02:13:11.876724: step: 200/529, loss: 0.020015234127640724
2023-01-23 02:13:12.993597: step: 204/529, loss: 0.005170631222426891
2023-01-23 02:13:14.114729: step: 208/529, loss: 0.08247242122888565
2023-01-23 02:13:15.248242: step: 212/529, loss: 0.0524735189974308
2023-01-23 02:13:16.383501: step: 216/529, loss: 0.005427646916359663
2023-01-23 02:13:17.476998: step: 220/529, loss: 0.07797518372535706
2023-01-23 02:13:18.587108: step: 224/529, loss: 0.015720367431640625
2023-01-23 02:13:19.713259: step: 228/529, loss: 0.0032287598587572575
2023-01-23 02:13:20.800088: step: 232/529, loss: 0.01717534102499485
2023-01-23 02:13:21.906415: step: 236/529, loss: 0.07521457970142365
2023-01-23 02:13:23.028858: step: 240/529, loss: 0.030816268175840378
2023-01-23 02:13:24.111221: step: 244/529, loss: 0.0008546352619305253
2023-01-23 02:13:25.258499: step: 248/529, loss: 0.02214374579489231
2023-01-23 02:13:26.380444: step: 252/529, loss: 0.0053382874466478825
2023-01-23 02:13:27.505656: step: 256/529, loss: 0.01530303992331028
2023-01-23 02:13:28.620998: step: 260/529, loss: 0.07069454342126846
2023-01-23 02:13:29.733507: step: 264/529, loss: 0.010964298620820045
2023-01-23 02:13:30.817175: step: 268/529, loss: 0.0720447525382042
2023-01-23 02:13:31.906114: step: 272/529, loss: 0.07317724078893661
2023-01-23 02:13:32.999887: step: 276/529, loss: 0.01610383950173855
2023-01-23 02:13:34.127631: step: 280/529, loss: 7.224082946777344e-05
2023-01-23 02:13:35.229808: step: 284/529, loss: 0.047832489013671875
2023-01-23 02:13:36.332683: step: 288/529, loss: 9.632110595703125e-05
2023-01-23 02:13:37.426578: step: 292/529, loss: 6.48498553346144e-06
2023-01-23 02:13:38.520613: step: 296/529, loss: 0.018159102648496628
2023-01-23 02:13:39.640158: step: 300/529, loss: 0.00666003255173564
2023-01-23 02:13:40.728746: step: 304/529, loss: 0.00021076203847769648
2023-01-23 02:13:41.835315: step: 308/529, loss: 0.04769439622759819
2023-01-23 02:13:42.920941: step: 312/529, loss: 0.0011162757873535156
2023-01-23 02:13:44.009652: step: 316/529, loss: 0.007105064578354359
2023-01-23 02:13:45.128092: step: 320/529, loss: 0.011291789822280407
2023-01-23 02:13:46.242131: step: 324/529, loss: 0.025879669934511185
2023-01-23 02:13:47.367053: step: 328/529, loss: 0.1660911589860916
2023-01-23 02:13:48.488486: step: 332/529, loss: 0.06511249393224716
2023-01-23 02:13:49.591209: step: 336/529, loss: 0.04030895233154297
2023-01-23 02:13:50.709644: step: 340/529, loss: 0.03682670742273331
2023-01-23 02:13:51.818460: step: 344/529, loss: 0.023293208330869675
2023-01-23 02:13:52.927534: step: 348/529, loss: 0.017755890265107155
2023-01-23 02:13:54.033307: step: 352/529, loss: 0.008890628814697266
2023-01-23 02:13:55.136320: step: 356/529, loss: 0.01848297193646431
2023-01-23 02:13:56.225453: step: 360/529, loss: 0.04334626346826553
2023-01-23 02:13:57.343265: step: 364/529, loss: 0.0025909424293786287
2023-01-23 02:13:58.463828: step: 368/529, loss: 0.10297536849975586
2023-01-23 02:13:59.597425: step: 372/529, loss: 0.2696473002433777
2023-01-23 02:14:00.721715: step: 376/529, loss: 7.23838820704259e-05
2023-01-23 02:14:01.823976: step: 380/529, loss: 0.05467405170202255
2023-01-23 02:14:02.924259: step: 384/529, loss: 0.03773241117596626
2023-01-23 02:14:04.009127: step: 388/529, loss: 0.005128288175910711
2023-01-23 02:14:05.119026: step: 392/529, loss: 0.0326143279671669
2023-01-23 02:14:06.235746: step: 396/529, loss: 0.002808475401252508
2023-01-23 02:14:07.355315: step: 400/529, loss: 0.0018304826226085424
2023-01-23 02:14:08.457707: step: 404/529, loss: 0.016602396965026855
2023-01-23 02:14:09.555798: step: 408/529, loss: 0.03432111814618111
2023-01-23 02:14:10.702461: step: 412/529, loss: 0.030054284259676933
2023-01-23 02:14:11.797769: step: 416/529, loss: 0.029904749244451523
2023-01-23 02:14:12.909387: step: 420/529, loss: 0.011365986429154873
2023-01-23 02:14:14.014053: step: 424/529, loss: 0.036942388862371445
2023-01-23 02:14:15.131174: step: 428/529, loss: 0.1254151463508606
2023-01-23 02:14:16.249896: step: 432/529, loss: 0.05761528015136719
2023-01-23 02:14:17.349213: step: 436/529, loss: 0.0015936612617224455
2023-01-23 02:14:18.438780: step: 440/529, loss: 0.007861328311264515
2023-01-23 02:14:19.572987: step: 444/529, loss: 0.04824542999267578
2023-01-23 02:14:20.669141: step: 448/529, loss: 0.02397623099386692
2023-01-23 02:14:21.768916: step: 452/529, loss: 0.017048239707946777
2023-01-23 02:14:22.858092: step: 456/529, loss: 0.12359494715929031
2023-01-23 02:14:23.946223: step: 460/529, loss: 0.00046868325443938375
2023-01-23 02:14:25.057335: step: 464/529, loss: 0.04047088697552681
2023-01-23 02:14:26.176467: step: 468/529, loss: 0.02680187113583088
2023-01-23 02:14:27.281971: step: 472/529, loss: 0.008870887570083141
2023-01-23 02:14:28.402488: step: 476/529, loss: 0.047852709889411926
2023-01-23 02:14:29.493317: step: 480/529, loss: 0.006445503327995539
2023-01-23 02:14:30.612032: step: 484/529, loss: 0.01652688905596733
2023-01-23 02:14:31.713593: step: 488/529, loss: 0.0021993399132043123
2023-01-23 02:14:32.857063: step: 492/529, loss: 0.002772808074951172
2023-01-23 02:14:34.014286: step: 496/529, loss: 0.07501278072595596
2023-01-23 02:14:35.110582: step: 500/529, loss: 0.055669210851192474
2023-01-23 02:14:36.231427: step: 504/529, loss: 0.04873981326818466
2023-01-23 02:14:37.347557: step: 508/529, loss: 0.05307312309741974
2023-01-23 02:14:38.434947: step: 512/529, loss: 0.0007361412281170487
2023-01-23 02:14:39.544043: step: 516/529, loss: 0.005601024720817804
2023-01-23 02:14:40.636337: step: 520/529, loss: 0.011008357629179955
2023-01-23 02:14:41.727380: step: 524/529, loss: 0.02171478420495987
2023-01-23 02:14:42.834801: step: 528/529, loss: 0.020067309960722923
2023-01-23 02:14:43.960451: step: 532/529, loss: 0.05024278163909912
2023-01-23 02:14:45.078510: step: 536/529, loss: 0.06246328726410866
2023-01-23 02:14:46.190477: step: 540/529, loss: 0.009054947644472122
2023-01-23 02:14:47.303206: step: 544/529, loss: 0.046475209295749664
2023-01-23 02:14:48.411437: step: 548/529, loss: 0.007139307446777821
2023-01-23 02:14:49.512059: step: 552/529, loss: 0.021619129925966263
2023-01-23 02:14:50.629901: step: 556/529, loss: 0.008919572457671165
2023-01-23 02:14:51.724828: step: 560/529, loss: 0.06467042118310928
2023-01-23 02:14:52.849087: step: 564/529, loss: 7.982253737282008e-05
2023-01-23 02:14:54.011814: step: 568/529, loss: 0.0006339072715491056
2023-01-23 02:14:55.155219: step: 572/529, loss: 0.010019492357969284
2023-01-23 02:14:56.306395: step: 576/529, loss: 0.014912128448486328
2023-01-23 02:14:57.404239: step: 580/529, loss: 0.021863173693418503
2023-01-23 02:14:58.495577: step: 584/529, loss: 0.0007422447670251131
2023-01-23 02:14:59.616909: step: 588/529, loss: 0.015879059210419655
2023-01-23 02:15:00.703636: step: 592/529, loss: 0.0011568069458007812
2023-01-23 02:15:01.846666: step: 596/529, loss: 0.020446205511689186
2023-01-23 02:15:02.975910: step: 600/529, loss: 0.05336475372314453
2023-01-23 02:15:04.095187: step: 604/529, loss: 6.895065598655492e-05
2023-01-23 02:15:05.231767: step: 608/529, loss: 0.46739864349365234
2023-01-23 02:15:06.345037: step: 612/529, loss: 0.010795939713716507
2023-01-23 02:15:07.458014: step: 616/529, loss: 0.027636241167783737
2023-01-23 02:15:08.562492: step: 620/529, loss: 0.09429407119750977
2023-01-23 02:15:09.667587: step: 624/529, loss: 0.07420787960290909
2023-01-23 02:15:10.808947: step: 628/529, loss: 0.0014320374466478825
2023-01-23 02:15:11.934194: step: 632/529, loss: 0.10110418498516083
2023-01-23 02:15:13.043972: step: 636/529, loss: 0.006761932745575905
2023-01-23 02:15:14.144921: step: 640/529, loss: 0.12080192565917969
2023-01-23 02:15:15.229589: step: 644/529, loss: 0.0023211955558508635
2023-01-23 02:15:16.372283: step: 648/529, loss: 0.09358477592468262
2023-01-23 02:15:17.510155: step: 652/529, loss: 0.004716969095170498
2023-01-23 02:15:18.663848: step: 656/529, loss: 0.020423317328095436
2023-01-23 02:15:19.740413: step: 660/529, loss: 3.0040740966796875e-05
2023-01-23 02:15:20.881909: step: 664/529, loss: 0.0008813910535536706
2023-01-23 02:15:22.008630: step: 668/529, loss: 0.007923126220703125
2023-01-23 02:15:23.143237: step: 672/529, loss: 0.037394046783447266
2023-01-23 02:15:24.238223: step: 676/529, loss: 0.0008081436390057206
2023-01-23 02:15:25.353022: step: 680/529, loss: 0.05073799192905426
2023-01-23 02:15:26.471420: step: 684/529, loss: 0.021272849291563034
2023-01-23 02:15:27.566031: step: 688/529, loss: 0.026344871148467064
2023-01-23 02:15:28.691993: step: 692/529, loss: 0.011310672387480736
2023-01-23 02:15:29.799588: step: 696/529, loss: 0.12726135551929474
2023-01-23 02:15:30.933819: step: 700/529, loss: 0.04306221008300781
2023-01-23 02:15:32.034257: step: 704/529, loss: 0.007143735885620117
2023-01-23 02:15:33.140974: step: 708/529, loss: 0.03567161411046982
2023-01-23 02:15:34.233131: step: 712/529, loss: 0.0015853882068768144
2023-01-23 02:15:35.349239: step: 716/529, loss: 0.004586124327033758
2023-01-23 02:15:36.469035: step: 720/529, loss: 0.012326335534453392
2023-01-23 02:15:37.591600: step: 724/529, loss: 0.0005102157592773438
2023-01-23 02:15:38.705967: step: 728/529, loss: 0.0015952109824866056
2023-01-23 02:15:39.808065: step: 732/529, loss: 0.014678955078125
2023-01-23 02:15:40.911281: step: 736/529, loss: 0.06628882884979248
2023-01-23 02:15:42.030455: step: 740/529, loss: 0.000903868698514998
2023-01-23 02:15:43.139718: step: 744/529, loss: 0.052529335021972656
2023-01-23 02:15:44.246770: step: 748/529, loss: 0.021105384454131126
2023-01-23 02:15:45.348837: step: 752/529, loss: 0.0865146666765213
2023-01-23 02:15:46.470841: step: 756/529, loss: 0.0017707825172692537
2023-01-23 02:15:47.577123: step: 760/529, loss: 0.00037088393582962453
2023-01-23 02:15:48.680024: step: 764/529, loss: 0.012800311669707298
2023-01-23 02:15:49.819578: step: 768/529, loss: 0.0025392533279955387
2023-01-23 02:15:50.912768: step: 772/529, loss: 0.04057617112994194
2023-01-23 02:15:52.032681: step: 776/529, loss: 0.004737472627311945
2023-01-23 02:15:53.144520: step: 780/529, loss: 0.056742168962955475
2023-01-23 02:15:54.260671: step: 784/529, loss: 0.0018266676925122738
2023-01-23 02:15:55.364429: step: 788/529, loss: 0.010502815246582031
2023-01-23 02:15:56.469723: step: 792/529, loss: 0.012565422803163528
2023-01-23 02:15:57.568995: step: 796/529, loss: 0.019710158929228783
2023-01-23 02:15:58.667915: step: 800/529, loss: 0.05536976084113121
2023-01-23 02:15:59.797186: step: 804/529, loss: 0.004331779666244984
2023-01-23 02:16:00.893444: step: 808/529, loss: 0.011479330249130726
2023-01-23 02:16:02.007198: step: 812/529, loss: 0.05956754833459854
2023-01-23 02:16:03.135672: step: 816/529, loss: 0.055561065673828125
2023-01-23 02:16:04.261771: step: 820/529, loss: 0.005342293065041304
2023-01-23 02:16:05.361803: step: 824/529, loss: 0.003073072526603937
2023-01-23 02:16:06.456985: step: 828/529, loss: 0.0037328721955418587
2023-01-23 02:16:07.588621: step: 832/529, loss: 0.020804787054657936
2023-01-23 02:16:08.694707: step: 836/529, loss: 0.014915943145751953
2023-01-23 02:16:09.807765: step: 840/529, loss: 0.028075218200683594
2023-01-23 02:16:10.974024: step: 844/529, loss: 0.03220729902386665
2023-01-23 02:16:12.091639: step: 848/529, loss: 0.0013166428543627262
2023-01-23 02:16:13.199582: step: 852/529, loss: 0.03249330446124077
2023-01-23 02:16:14.299453: step: 856/529, loss: 0.03174781799316406
2023-01-23 02:16:15.422843: step: 860/529, loss: 0.03603344410657883
2023-01-23 02:16:16.553808: step: 864/529, loss: 0.044113826006650925
2023-01-23 02:16:17.686424: step: 868/529, loss: 0.011435795575380325
2023-01-23 02:16:18.819913: step: 872/529, loss: 0.006736183539032936
2023-01-23 02:16:19.925278: step: 876/529, loss: 0.027289342135190964
2023-01-23 02:16:21.019628: step: 880/529, loss: 0.0060266610234975815
2023-01-23 02:16:22.106728: step: 884/529, loss: 0.006854248698800802
2023-01-23 02:16:23.217536: step: 888/529, loss: 0.003201723098754883
2023-01-23 02:16:24.329699: step: 892/529, loss: 0.0032588958274573088
2023-01-23 02:16:25.445519: step: 896/529, loss: 0.0595417246222496
2023-01-23 02:16:26.551506: step: 900/529, loss: 0.0007473469013348222
2023-01-23 02:16:27.669416: step: 904/529, loss: 0.058427829295396805
2023-01-23 02:16:28.825347: step: 908/529, loss: 0.03661804273724556
2023-01-23 02:16:29.944330: step: 912/529, loss: 0.022238921374082565
2023-01-23 02:16:31.046715: step: 916/529, loss: 0.03210010752081871
2023-01-23 02:16:32.123909: step: 920/529, loss: 2.6655196052161045e-05
2023-01-23 02:16:33.220142: step: 924/529, loss: 0.029155446216464043
2023-01-23 02:16:34.330250: step: 928/529, loss: 0.00039548875065520406
2023-01-23 02:16:35.447014: step: 932/529, loss: 0.0001445770321879536
2023-01-23 02:16:36.573746: step: 936/529, loss: 0.0034053800627589226
2023-01-23 02:16:37.673934: step: 940/529, loss: 0.009549761191010475
2023-01-23 02:16:38.782601: step: 944/529, loss: 0.02778167836368084
2023-01-23 02:16:39.896354: step: 948/529, loss: 0.07834930717945099
2023-01-23 02:16:41.011046: step: 952/529, loss: 0.0006052016979083419
2023-01-23 02:16:42.100637: step: 956/529, loss: 0.05377340316772461
2023-01-23 02:16:43.181544: step: 960/529, loss: 0.0004207611200399697
2023-01-23 02:16:44.285853: step: 964/529, loss: 0.03605365753173828
2023-01-23 02:16:45.409592: step: 968/529, loss: 0.004719352815300226
2023-01-23 02:16:46.531396: step: 972/529, loss: 0.006659412756562233
2023-01-23 02:16:47.659757: step: 976/529, loss: 0.06506204605102539
2023-01-23 02:16:48.755960: step: 980/529, loss: 0.0002754211309365928
2023-01-23 02:16:49.868404: step: 984/529, loss: 0.0007025718805380166
2023-01-23 02:16:50.976499: step: 988/529, loss: 0.3186468183994293
2023-01-23 02:16:52.065019: step: 992/529, loss: 0.10364627838134766
2023-01-23 02:16:53.184107: step: 996/529, loss: 0.028425216674804688
2023-01-23 02:16:54.303372: step: 1000/529, loss: 0.019411087036132812
2023-01-23 02:16:55.415379: step: 1004/529, loss: 0.010079288855195045
2023-01-23 02:16:56.535482: step: 1008/529, loss: 0.012311267666518688
2023-01-23 02:16:57.674845: step: 1012/529, loss: 0.0022874833084642887
2023-01-23 02:16:58.778193: step: 1016/529, loss: 0.03241335600614548
2023-01-23 02:16:59.876048: step: 1020/529, loss: 0.03270426020026207
2023-01-23 02:17:00.967672: step: 1024/529, loss: 0.0014565945602953434
2023-01-23 02:17:02.061364: step: 1028/529, loss: 0.013020897284150124
2023-01-23 02:17:03.196523: step: 1032/529, loss: 0.12631407380104065
2023-01-23 02:17:04.340104: step: 1036/529, loss: 0.019868278875947
2023-01-23 02:17:05.470288: step: 1040/529, loss: 0.03553180769085884
2023-01-23 02:17:06.565437: step: 1044/529, loss: 0.0031086921226233244
2023-01-23 02:17:07.676361: step: 1048/529, loss: 0.016033364459872246
2023-01-23 02:17:08.796439: step: 1052/529, loss: 0.0021656989119946957
2023-01-23 02:17:09.919925: step: 1056/529, loss: 0.005913925357162952
2023-01-23 02:17:11.038667: step: 1060/529, loss: 0.019308757036924362
2023-01-23 02:17:12.137158: step: 1064/529, loss: 0.15139923989772797
2023-01-23 02:17:13.243137: step: 1068/529, loss: 0.029529571533203125
2023-01-23 02:17:14.355537: step: 1072/529, loss: 0.02379711903631687
2023-01-23 02:17:15.490229: step: 1076/529, loss: 0.0012794971698895097
2023-01-23 02:17:16.592394: step: 1080/529, loss: 0.028619766235351562
2023-01-23 02:17:17.716064: step: 1084/529, loss: 0.009420335292816162
2023-01-23 02:17:18.818310: step: 1088/529, loss: 0.023762226104736328
2023-01-23 02:17:19.936313: step: 1092/529, loss: 0.05547494813799858
2023-01-23 02:17:21.031794: step: 1096/529, loss: 0.0640069991350174
2023-01-23 02:17:22.182921: step: 1100/529, loss: 0.044533442705869675
2023-01-23 02:17:23.337346: step: 1104/529, loss: 1.912116931634955e-05
2023-01-23 02:17:24.442729: step: 1108/529, loss: 0.02153453789651394
2023-01-23 02:17:25.554195: step: 1112/529, loss: 0.08407821506261826
2023-01-23 02:17:26.663624: step: 1116/529, loss: 0.0314946174621582
2023-01-23 02:17:27.768857: step: 1120/529, loss: 0.015937425196170807
2023-01-23 02:17:28.875301: step: 1124/529, loss: 0.03895702585577965
2023-01-23 02:17:29.994865: step: 1128/529, loss: 0.043290603905916214
2023-01-23 02:17:31.095058: step: 1132/529, loss: 0.04781074821949005
2023-01-23 02:17:32.207519: step: 1136/529, loss: 0.006644487846642733
2023-01-23 02:17:33.312797: step: 1140/529, loss: 0.02222309075295925
2023-01-23 02:17:34.412271: step: 1144/529, loss: 0.00012764931307174265
2023-01-23 02:17:35.506249: step: 1148/529, loss: 0.09591178596019745
2023-01-23 02:17:36.607933: step: 1152/529, loss: 0.03915290907025337
2023-01-23 02:17:37.737388: step: 1156/529, loss: 0.0045146942138671875
2023-01-23 02:17:38.838696: step: 1160/529, loss: 0.003057861467823386
2023-01-23 02:17:39.924727: step: 1164/529, loss: 0.013817215338349342
2023-01-23 02:17:41.044185: step: 1168/529, loss: 0.007404518313705921
2023-01-23 02:17:42.145121: step: 1172/529, loss: 0.0034379959106445312
2023-01-23 02:17:43.269272: step: 1176/529, loss: 0.02954845502972603
2023-01-23 02:17:44.436415: step: 1180/529, loss: 0.04490194469690323
2023-01-23 02:17:45.570488: step: 1184/529, loss: 0.008612059988081455
2023-01-23 02:17:46.703646: step: 1188/529, loss: 0.038852788507938385
2023-01-23 02:17:47.821987: step: 1192/529, loss: 0.02552204206585884
2023-01-23 02:17:48.926600: step: 1196/529, loss: 0.00870294589549303
2023-01-23 02:17:50.055615: step: 1200/529, loss: 0.01828165166079998
2023-01-23 02:17:51.147805: step: 1204/529, loss: 0.0019250869518145919
2023-01-23 02:17:52.268888: step: 1208/529, loss: 0.062151338905096054
2023-01-23 02:17:53.373966: step: 1212/529, loss: 0.00042018890962935984
2023-01-23 02:17:54.516142: step: 1216/529, loss: 0.0059455870650708675
2023-01-23 02:17:55.647075: step: 1220/529, loss: 0.011283207684755325
2023-01-23 02:17:56.785496: step: 1224/529, loss: 0.012472724542021751
2023-01-23 02:17:57.903630: step: 1228/529, loss: 0.0035551071632653475
2023-01-23 02:17:59.017329: step: 1232/529, loss: 0.01893634721636772
2023-01-23 02:18:00.136177: step: 1236/529, loss: 0.00046453476534225047
2023-01-23 02:18:01.231525: step: 1240/529, loss: 0.029596518725156784
2023-01-23 02:18:02.339626: step: 1244/529, loss: 0.002021408174186945
2023-01-23 02:18:03.468137: step: 1248/529, loss: 0.04575634002685547
2023-01-23 02:18:04.580583: step: 1252/529, loss: 0.06333780288696289
2023-01-23 02:18:05.698314: step: 1256/529, loss: 0.0009008407359942794
2023-01-23 02:18:06.813431: step: 1260/529, loss: 0.006089329719543457
2023-01-23 02:18:07.912657: step: 1264/529, loss: 0.005976581480354071
2023-01-23 02:18:09.026623: step: 1268/529, loss: 0.0009419440757483244
2023-01-23 02:18:10.140544: step: 1272/529, loss: 0.0240189079195261
2023-01-23 02:18:11.245932: step: 1276/529, loss: 0.01443700771778822
2023-01-23 02:18:12.388183: step: 1280/529, loss: 0.0021149159874767065
2023-01-23 02:18:13.475748: step: 1284/529, loss: 0.00947418250143528
2023-01-23 02:18:14.582499: step: 1288/529, loss: 0.17442846298217773
2023-01-23 02:18:15.675783: step: 1292/529, loss: 0.0038775443099439144
2023-01-23 02:18:16.771613: step: 1296/529, loss: 0.012499738484621048
2023-01-23 02:18:17.902483: step: 1300/529, loss: 0.028967667371034622
2023-01-23 02:18:19.014132: step: 1304/529, loss: 0.05090503767132759
2023-01-23 02:18:20.105651: step: 1308/529, loss: 0.015236472710967064
2023-01-23 02:18:21.236480: step: 1312/529, loss: 0.014673185534775257
2023-01-23 02:18:22.329808: step: 1316/529, loss: 0.00047292711678892374
2023-01-23 02:18:23.428210: step: 1320/529, loss: 0.0027740478981286287
2023-01-23 02:18:24.524351: step: 1324/529, loss: 0.0005285263177938759
2023-01-23 02:18:25.646670: step: 1328/529, loss: 0.005422926042228937
2023-01-23 02:18:26.735557: step: 1332/529, loss: 0.026267338544130325
2023-01-23 02:18:27.832811: step: 1336/529, loss: 0.08325314521789551
2023-01-23 02:18:28.924988: step: 1340/529, loss: 0.0005667209625244141
2023-01-23 02:18:30.027140: step: 1344/529, loss: 0.05620746687054634
2023-01-23 02:18:31.140704: step: 1348/529, loss: 0.008568763732910156
2023-01-23 02:18:32.277022: step: 1352/529, loss: 0.0054128170013427734
2023-01-23 02:18:33.379472: step: 1356/529, loss: 9.50813337112777e-05
2023-01-23 02:18:34.501790: step: 1360/529, loss: 0.04579639434814453
2023-01-23 02:18:35.604908: step: 1364/529, loss: 0.025598812848329544
2023-01-23 02:18:36.725145: step: 1368/529, loss: 0.01798391342163086
2023-01-23 02:18:37.838618: step: 1372/529, loss: 0.04349198192358017
2023-01-23 02:18:38.964733: step: 1376/529, loss: 0.00796742457896471
2023-01-23 02:18:40.096576: step: 1380/529, loss: 0.32121312618255615
2023-01-23 02:18:41.200151: step: 1384/529, loss: 0.12058448791503906
2023-01-23 02:18:42.317608: step: 1388/529, loss: 0.0397859588265419
2023-01-23 02:18:43.435939: step: 1392/529, loss: 0.04373965412378311
2023-01-23 02:18:44.544262: step: 1396/529, loss: 0.03370971605181694
2023-01-23 02:18:45.657510: step: 1400/529, loss: 0.00021610260591842234
2023-01-23 02:18:46.773390: step: 1404/529, loss: 0.004474925808608532
2023-01-23 02:18:47.891312: step: 1408/529, loss: 0.001635646796785295
2023-01-23 02:18:49.024439: step: 1412/529, loss: 0.0037488937377929688
2023-01-23 02:18:50.121260: step: 1416/529, loss: 0.0010494232410565019
2023-01-23 02:18:51.243292: step: 1420/529, loss: 0.0026595115195959806
2023-01-23 02:18:52.362891: step: 1424/529, loss: 0.01549067534506321
2023-01-23 02:18:53.465136: step: 1428/529, loss: 0.013635540381073952
2023-01-23 02:18:54.574623: step: 1432/529, loss: 0.03781929239630699
2023-01-23 02:18:55.705144: step: 1436/529, loss: 0.003968143370002508
2023-01-23 02:18:56.796236: step: 1440/529, loss: 0.048525430262088776
2023-01-23 02:18:57.911791: step: 1444/529, loss: 0.005127429962158203
2023-01-23 02:18:59.034496: step: 1448/529, loss: 0.0021885870955884457
2023-01-23 02:19:00.128363: step: 1452/529, loss: 0.0070400238037109375
2023-01-23 02:19:01.226926: step: 1456/529, loss: 0.027751445770263672
2023-01-23 02:19:02.341160: step: 1460/529, loss: 0.010463809594511986
2023-01-23 02:19:03.437892: step: 1464/529, loss: 0.006424332037568092
2023-01-23 02:19:04.535502: step: 1468/529, loss: 0.010878181084990501
2023-01-23 02:19:05.627792: step: 1472/529, loss: 0.006523704621940851
2023-01-23 02:19:06.700344: step: 1476/529, loss: 0.004263115115463734
2023-01-23 02:19:07.847723: step: 1480/529, loss: 0.05791836231946945
2023-01-23 02:19:08.940624: step: 1484/529, loss: 0.028817366808652878
2023-01-23 02:19:10.039337: step: 1488/529, loss: 0.04910030588507652
2023-01-23 02:19:11.148017: step: 1492/529, loss: 0.0054565430618822575
2023-01-23 02:19:12.263898: step: 1496/529, loss: 0.01650269702076912
2023-01-23 02:19:13.370603: step: 1500/529, loss: 0.0033977509010583162
2023-01-23 02:19:14.479288: step: 1504/529, loss: 0.014163351617753506
2023-01-23 02:19:15.551247: step: 1508/529, loss: 0.007196045480668545
2023-01-23 02:19:16.721734: step: 1512/529, loss: 0.09505720436573029
2023-01-23 02:19:17.842998: step: 1516/529, loss: 0.21728669106960297
2023-01-23 02:19:18.963385: step: 1520/529, loss: 0.022905994206666946
2023-01-23 02:19:20.080599: step: 1524/529, loss: 0.029943037778139114
2023-01-23 02:19:21.211140: step: 1528/529, loss: 0.03110961988568306
2023-01-23 02:19:22.335698: step: 1532/529, loss: 0.004485511686652899
2023-01-23 02:19:23.461274: step: 1536/529, loss: 0.16147682070732117
2023-01-23 02:19:24.572126: step: 1540/529, loss: 0.007404995150864124
2023-01-23 02:19:25.707794: step: 1544/529, loss: 0.00901050679385662
2023-01-23 02:19:26.823640: step: 1548/529, loss: 0.05372605100274086
2023-01-23 02:19:27.928643: step: 1552/529, loss: 0.022143268957734108
2023-01-23 02:19:29.036951: step: 1556/529, loss: 0.04845810309052467
2023-01-23 02:19:30.161869: step: 1560/529, loss: 0.0153045654296875
2023-01-23 02:19:31.276477: step: 1564/529, loss: 0.00569496164098382
2023-01-23 02:19:32.369992: step: 1568/529, loss: 0.09224672615528107
2023-01-23 02:19:33.506343: step: 1572/529, loss: 0.07145166397094727
2023-01-23 02:19:34.654883: step: 1576/529, loss: 0.006652355194091797
2023-01-23 02:19:35.765638: step: 1580/529, loss: 0.030744075775146484
2023-01-23 02:19:36.869571: step: 1584/529, loss: 0.0035976411309093237
2023-01-23 02:19:37.975172: step: 1588/529, loss: 0.00803766306489706
2023-01-23 02:19:39.046134: step: 1592/529, loss: 0.010059547610580921
2023-01-23 02:19:40.174799: step: 1596/529, loss: 0.002731514163315296
2023-01-23 02:19:41.270898: step: 1600/529, loss: 0.07111578434705734
2023-01-23 02:19:42.392627: step: 1604/529, loss: 0.12307175993919373
2023-01-23 02:19:43.521164: step: 1608/529, loss: 0.021628571674227715
2023-01-23 02:19:44.670212: step: 1612/529, loss: 0.03154271841049194
2023-01-23 02:19:45.789237: step: 1616/529, loss: 0.00012645722017623484
2023-01-23 02:19:46.917607: step: 1620/529, loss: 0.017206192016601562
2023-01-23 02:19:48.018650: step: 1624/529, loss: 0.002230310346931219
2023-01-23 02:19:49.132109: step: 1628/529, loss: 0.0238389503210783
2023-01-23 02:19:50.265905: step: 1632/529, loss: 0.06463997066020966
2023-01-23 02:19:51.363019: step: 1636/529, loss: 0.03412942960858345
2023-01-23 02:19:52.454867: step: 1640/529, loss: 0.0066480631940066814
2023-01-23 02:19:53.601098: step: 1644/529, loss: 0.0455290786921978
2023-01-23 02:19:54.698967: step: 1648/529, loss: 0.18373900651931763
2023-01-23 02:19:55.811903: step: 1652/529, loss: 0.010761070996522903
2023-01-23 02:19:56.923820: step: 1656/529, loss: 0.002349758055061102
2023-01-23 02:19:58.039507: step: 1660/529, loss: 0.04829740524291992
2023-01-23 02:19:59.125189: step: 1664/529, loss: 0.16388721764087677
2023-01-23 02:20:00.240243: step: 1668/529, loss: 0.03143024444580078
2023-01-23 02:20:01.340149: step: 1672/529, loss: 0.05122409015893936
2023-01-23 02:20:02.487683: step: 1676/529, loss: 0.0005262374761514366
2023-01-23 02:20:03.604085: step: 1680/529, loss: 0.003352260682731867
2023-01-23 02:20:04.708393: step: 1684/529, loss: 0.03806591033935547
2023-01-23 02:20:05.832683: step: 1688/529, loss: 0.006078911013901234
2023-01-23 02:20:06.935015: step: 1692/529, loss: 0.028930090367794037
2023-01-23 02:20:08.028876: step: 1696/529, loss: 0.054664041846990585
2023-01-23 02:20:09.147959: step: 1700/529, loss: 0.027724266052246094
2023-01-23 02:20:10.234846: step: 1704/529, loss: 0.005173015408217907
2023-01-23 02:20:11.330379: step: 1708/529, loss: 0.026000645011663437
2023-01-23 02:20:12.482083: step: 1712/529, loss: 0.043677520006895065
2023-01-23 02:20:13.601397: step: 1716/529, loss: 0.056861989200115204
2023-01-23 02:20:14.702749: step: 1720/529, loss: 0.021589089184999466
2023-01-23 02:20:15.805283: step: 1724/529, loss: 0.0004339933511801064
2023-01-23 02:20:16.942329: step: 1728/529, loss: 0.004943370819091797
2023-01-23 02:20:18.057033: step: 1732/529, loss: 0.009901904501020908
2023-01-23 02:20:19.140245: step: 1736/529, loss: 0.015550781041383743
2023-01-23 02:20:20.220865: step: 1740/529, loss: 0.0015162468189373612
2023-01-23 02:20:21.330118: step: 1744/529, loss: 0.0029075623024255037
2023-01-23 02:20:22.440535: step: 1748/529, loss: 0.4520382285118103
2023-01-23 02:20:23.523642: step: 1752/529, loss: 0.00653419503942132
2023-01-23 02:20:24.644504: step: 1756/529, loss: 0.0431545227766037
2023-01-23 02:20:25.753648: step: 1760/529, loss: 0.007971953600645065
2023-01-23 02:20:26.857126: step: 1764/529, loss: 0.0013872147537767887
2023-01-23 02:20:27.964456: step: 1768/529, loss: 0.29605618119239807
2023-01-23 02:20:29.051702: step: 1772/529, loss: 0.020236873999238014
2023-01-23 02:20:30.169667: step: 1776/529, loss: 0.014721298590302467
2023-01-23 02:20:31.269162: step: 1780/529, loss: 0.00017032623873092234
2023-01-23 02:20:32.361249: step: 1784/529, loss: 0.07722122967243195
2023-01-23 02:20:33.490976: step: 1788/529, loss: 0.0676647201180458
2023-01-23 02:20:34.610430: step: 1792/529, loss: 0.012405872344970703
2023-01-23 02:20:35.687822: step: 1796/529, loss: 4.57763671875e-05
2023-01-23 02:20:36.791693: step: 1800/529, loss: 0.004603528883308172
2023-01-23 02:20:37.885521: step: 1804/529, loss: 0.001621246337890625
2023-01-23 02:20:38.982935: step: 1808/529, loss: 0.0024099349975585938
2023-01-23 02:20:40.102442: step: 1812/529, loss: 0.0013746261829510331
2023-01-23 02:20:41.214478: step: 1816/529, loss: 0.08621510863304138
2023-01-23 02:20:42.321948: step: 1820/529, loss: 0.06648464500904083
2023-01-23 02:20:43.428815: step: 1824/529, loss: 0.0012690543662756681
2023-01-23 02:20:44.548635: step: 1828/529, loss: 0.0007116794586181641
2023-01-23 02:20:45.666718: step: 1832/529, loss: 0.0034635544288903475
2023-01-23 02:20:46.786332: step: 1836/529, loss: 0.00012102127220714465
2023-01-23 02:20:47.874516: step: 1840/529, loss: 0.036646127700805664
2023-01-23 02:20:48.988538: step: 1844/529, loss: 0.01183543261140585
2023-01-23 02:20:50.132977: step: 1848/529, loss: 0.0014579773414880037
2023-01-23 02:20:51.248043: step: 1852/529, loss: 0.0003961563343182206
2023-01-23 02:20:52.353480: step: 1856/529, loss: 0.04968290403485298
2023-01-23 02:20:53.459088: step: 1860/529, loss: 0.00946798361837864
2023-01-23 02:20:54.581534: step: 1864/529, loss: 0.05361900478601456
2023-01-23 02:20:55.659383: step: 1868/529, loss: 0.021692801266908646
2023-01-23 02:20:56.795660: step: 1872/529, loss: 0.03295927122235298
2023-01-23 02:20:57.906211: step: 1876/529, loss: 0.0465368777513504
2023-01-23 02:20:59.027056: step: 1880/529, loss: 0.02541074901819229
2023-01-23 02:21:00.149152: step: 1884/529, loss: 0.055675603449344635
2023-01-23 02:21:01.246894: step: 1888/529, loss: 0.0022763251326978207
2023-01-23 02:21:02.345785: step: 1892/529, loss: 0.01654643937945366
2023-01-23 02:21:03.450127: step: 1896/529, loss: 0.03304043039679527
2023-01-23 02:21:04.557767: step: 1900/529, loss: 0.0023160933051258326
2023-01-23 02:21:05.655552: step: 1904/529, loss: 0.017093371599912643
2023-01-23 02:21:06.767237: step: 1908/529, loss: 0.01160345133394003
2023-01-23 02:21:07.888691: step: 1912/529, loss: 0.016899585723876953
2023-01-23 02:21:08.974372: step: 1916/529, loss: 0.04355192184448242
2023-01-23 02:21:10.110357: step: 1920/529, loss: 0.01504297275096178
2023-01-23 02:21:11.229032: step: 1924/529, loss: 0.028369521722197533
2023-01-23 02:21:12.321075: step: 1928/529, loss: 0.0086212158203125
2023-01-23 02:21:13.421672: step: 1932/529, loss: 0.00090789794921875
2023-01-23 02:21:14.555990: step: 1936/529, loss: 0.007388782687485218
2023-01-23 02:21:15.673242: step: 1940/529, loss: 2.7275083994027227e-05
2023-01-23 02:21:16.761441: step: 1944/529, loss: 0.0023542402777820826
2023-01-23 02:21:17.864651: step: 1948/529, loss: 0.0009572983253747225
2023-01-23 02:21:18.977154: step: 1952/529, loss: 0.07070598751306534
2023-01-23 02:21:20.064805: step: 1956/529, loss: 0.027022838592529297
2023-01-23 02:21:21.171247: step: 1960/529, loss: 0.0007778167491778731
2023-01-23 02:21:22.291157: step: 1964/529, loss: 0.007288360968232155
2023-01-23 02:21:23.384887: step: 1968/529, loss: 0.004833221435546875
2023-01-23 02:21:24.492410: step: 1972/529, loss: 0.0564996711909771
2023-01-23 02:21:25.642459: step: 1976/529, loss: 0.00883016549050808
2023-01-23 02:21:26.758519: step: 1980/529, loss: 0.004055881407111883
2023-01-23 02:21:27.869223: step: 1984/529, loss: 0.009660912677645683
2023-01-23 02:21:28.983454: step: 1988/529, loss: 0.015068341046571732
2023-01-23 02:21:30.149105: step: 1992/529, loss: 0.006891059689223766
2023-01-23 02:21:31.250954: step: 1996/529, loss: 0.0006494522094726562
2023-01-23 02:21:32.365593: step: 2000/529, loss: 0.056334689259529114
2023-01-23 02:21:33.448992: step: 2004/529, loss: 0.04470730200409889
2023-01-23 02:21:34.541521: step: 2008/529, loss: 0.006189537234604359
2023-01-23 02:21:35.628570: step: 2012/529, loss: 0.03673258051276207
2023-01-23 02:21:36.726902: step: 2016/529, loss: 0.00304241175763309
2023-01-23 02:21:37.824928: step: 2020/529, loss: 0.005485296715050936
2023-01-23 02:21:38.932272: step: 2024/529, loss: 0.021397780627012253
2023-01-23 02:21:40.058048: step: 2028/529, loss: 0.04088955000042915
2023-01-23 02:21:41.213020: step: 2032/529, loss: 0.04782600700855255
2023-01-23 02:21:42.298658: step: 2036/529, loss: 0.0009453773964196444
2023-01-23 02:21:43.423138: step: 2040/529, loss: 0.04519510269165039
2023-01-23 02:21:44.521250: step: 2044/529, loss: 0.010474396869540215
2023-01-23 02:21:45.643815: step: 2048/529, loss: 0.009509850293397903
2023-01-23 02:21:46.765072: step: 2052/529, loss: 0.07295895367860794
2023-01-23 02:21:47.869940: step: 2056/529, loss: 0.005055427551269531
2023-01-23 02:21:48.983722: step: 2060/529, loss: 0.014079665765166283
2023-01-23 02:21:50.094926: step: 2064/529, loss: 0.16413459181785583
2023-01-23 02:21:51.223297: step: 2068/529, loss: 0.014315415173768997
2023-01-23 02:21:52.293433: step: 2072/529, loss: 0.0027179718017578125
2023-01-23 02:21:53.391841: step: 2076/529, loss: 0.00542449951171875
2023-01-23 02:21:54.519805: step: 2080/529, loss: 0.007073068991303444
2023-01-23 02:21:55.636162: step: 2084/529, loss: 0.006602764129638672
2023-01-23 02:21:56.788896: step: 2088/529, loss: 0.01106405258178711
2023-01-23 02:21:57.897421: step: 2092/529, loss: 0.02700824663043022
2023-01-23 02:21:59.009096: step: 2096/529, loss: 0.04171320050954819
2023-01-23 02:22:00.127976: step: 2100/529, loss: 0.06613288819789886
2023-01-23 02:22:01.257279: step: 2104/529, loss: 0.007037639617919922
2023-01-23 02:22:02.365959: step: 2108/529, loss: 0.08476867526769638
2023-01-23 02:22:03.533160: step: 2112/529, loss: 0.011888790875673294
2023-01-23 02:22:04.649614: step: 2116/529, loss: 0.027255915105342865
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5814889336016097, 'r': 0.7696404793608522, 'f1': 0.6624641833810889}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6259440248778321, 'r': 0.7951467268623025, 'f1': 0.7004722843649017}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5795454545454546, 'r': 0.9444444444444444, 'f1': 0.7183098591549296}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.5806451612903226, 'r': 0.5714285714285714, 'f1': 0.576}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.425, 'r': 0.4722222222222222, 'f1': 0.4473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:22:44.967242: step: 4/529, loss: 0.007236194796860218
2023-01-23 02:22:46.053224: step: 8/529, loss: 0.012864941731095314
2023-01-23 02:22:47.138601: step: 12/529, loss: 0.02682342566549778
2023-01-23 02:22:48.266385: step: 16/529, loss: 0.021349716931581497
2023-01-23 02:22:49.406596: step: 20/529, loss: 0.02792081981897354
2023-01-23 02:22:50.512262: step: 24/529, loss: 0.0148963937535882
2023-01-23 02:22:51.634762: step: 28/529, loss: 0.007674217224121094
2023-01-23 02:22:52.729868: step: 32/529, loss: 0.052739571779966354
2023-01-23 02:22:53.849586: step: 36/529, loss: 0.0015630245907232165
2023-01-23 02:22:54.954201: step: 40/529, loss: 0.021659279242157936
2023-01-23 02:22:56.067375: step: 44/529, loss: 0.0002853393671102822
2023-01-23 02:22:57.163344: step: 48/529, loss: 0.04237651824951172
2023-01-23 02:22:58.325583: step: 52/529, loss: 0.006783866789191961
2023-01-23 02:22:59.427372: step: 56/529, loss: 0.015005683526396751
2023-01-23 02:23:00.518743: step: 60/529, loss: 0.030582809820771217
2023-01-23 02:23:01.623498: step: 64/529, loss: 0.010562468320131302
2023-01-23 02:23:02.738057: step: 68/529, loss: 0.08216266334056854
2023-01-23 02:23:03.829856: step: 72/529, loss: 0.010211657732725143
2023-01-23 02:23:04.942115: step: 76/529, loss: 0.008458519354462624
2023-01-23 02:23:06.046097: step: 80/529, loss: 0.05699892342090607
2023-01-23 02:23:07.143430: step: 84/529, loss: 0.017818927764892578
2023-01-23 02:23:08.232510: step: 88/529, loss: 0.00033926963806152344
2023-01-23 02:23:09.309337: step: 92/529, loss: 0.010666560381650925
2023-01-23 02:23:10.397497: step: 96/529, loss: 0.0004039764462504536
2023-01-23 02:23:11.498905: step: 100/529, loss: 0.009726524353027344
2023-01-23 02:23:12.591409: step: 104/529, loss: 0.002474975772202015
2023-01-23 02:23:13.686764: step: 108/529, loss: 0.035889625549316406
2023-01-23 02:23:14.791531: step: 112/529, loss: 0.0011489868629723787
2023-01-23 02:23:15.898031: step: 116/529, loss: 0.0012229920830577612
2023-01-23 02:23:17.031430: step: 120/529, loss: 0.0005732536083087325
2023-01-23 02:23:18.142740: step: 124/529, loss: 0.08603204041719437
2023-01-23 02:23:19.255613: step: 128/529, loss: 0.003493881318718195
2023-01-23 02:23:20.350721: step: 132/529, loss: 0.031853388994932175
2023-01-23 02:23:21.451728: step: 136/529, loss: 0.03113851696252823
2023-01-23 02:23:22.550207: step: 140/529, loss: 0.0057045938447117805
2023-01-23 02:23:23.679720: step: 144/529, loss: 0.03841762617230415
2023-01-23 02:23:24.799927: step: 148/529, loss: 0.005462074652314186
2023-01-23 02:23:25.890760: step: 152/529, loss: 0.0007432461134158075
2023-01-23 02:23:27.007882: step: 156/529, loss: 0.004455757327377796
2023-01-23 02:23:28.164961: step: 160/529, loss: 0.0036363601684570312
2023-01-23 02:23:29.262552: step: 164/529, loss: 0.009899521246552467
2023-01-23 02:23:30.367558: step: 168/529, loss: 0.006796318106353283
2023-01-23 02:23:31.456832: step: 172/529, loss: 0.3571142256259918
2023-01-23 02:23:32.572799: step: 176/529, loss: 0.010512541979551315
2023-01-23 02:23:33.697456: step: 180/529, loss: 0.0033124922774732113
2023-01-23 02:23:34.789182: step: 184/529, loss: 8.678436643094756e-06
2023-01-23 02:23:35.921733: step: 188/529, loss: 0.003802585881203413
2023-01-23 02:23:37.024692: step: 192/529, loss: 0.012919998727738857
2023-01-23 02:23:38.144544: step: 196/529, loss: 0.013766909018158913
2023-01-23 02:23:39.242609: step: 200/529, loss: 0.0013263702858239412
2023-01-23 02:23:40.337482: step: 204/529, loss: 0.007224178407341242
2023-01-23 02:23:41.453268: step: 208/529, loss: 0.0013332366943359375
2023-01-23 02:23:42.584150: step: 212/529, loss: 0.007906913757324219
2023-01-23 02:23:43.692189: step: 216/529, loss: 0.01584453694522381
2023-01-23 02:23:44.812110: step: 220/529, loss: 0.041970063000917435
2023-01-23 02:23:45.929537: step: 224/529, loss: 0.013851357623934746
2023-01-23 02:23:47.042001: step: 228/529, loss: 0.022777557373046875
2023-01-23 02:23:48.136419: step: 232/529, loss: 0.0034509659744799137
2023-01-23 02:23:49.249720: step: 236/529, loss: 0.0014532088534906507
2023-01-23 02:23:50.341033: step: 240/529, loss: 0.00862200278788805
2023-01-23 02:23:51.455042: step: 244/529, loss: 9.884834435069934e-05
2023-01-23 02:23:52.542539: step: 248/529, loss: 0.05267906188964844
2023-01-23 02:23:53.673154: step: 252/529, loss: 0.0010055541060864925
2023-01-23 02:23:54.780399: step: 256/529, loss: 0.022330857813358307
2023-01-23 02:23:55.909806: step: 260/529, loss: 0.15139131247997284
2023-01-23 02:23:57.038043: step: 264/529, loss: 0.09378699958324432
2023-01-23 02:23:58.138438: step: 268/529, loss: 0.007386207580566406
2023-01-23 02:23:59.256644: step: 272/529, loss: 0.02782278135418892
2023-01-23 02:24:00.378412: step: 276/529, loss: 0.0014570235507562757
2023-01-23 02:24:01.507216: step: 280/529, loss: 0.0122238639742136
2023-01-23 02:24:02.630131: step: 284/529, loss: 0.0002176284760935232
2023-01-23 02:24:03.742421: step: 288/529, loss: 0.00545611372217536
2023-01-23 02:24:04.831278: step: 292/529, loss: 0.0002180576411774382
2023-01-23 02:24:05.936850: step: 296/529, loss: 6.837844557594508e-05
2023-01-23 02:24:07.048413: step: 300/529, loss: 0.023854253813624382
2023-01-23 02:24:08.132235: step: 304/529, loss: 0.024345112964510918
2023-01-23 02:24:09.244804: step: 308/529, loss: 0.11616702377796173
2023-01-23 02:24:10.330406: step: 312/529, loss: 0.05671720579266548
2023-01-23 02:24:11.426019: step: 316/529, loss: 0.005731392186135054
2023-01-23 02:24:12.509861: step: 320/529, loss: 0.0009192362776957452
2023-01-23 02:24:13.624102: step: 324/529, loss: 0.019611548632383347
2023-01-23 02:24:14.757250: step: 328/529, loss: 0.015974808484315872
2023-01-23 02:24:15.881506: step: 332/529, loss: 0.0137062082067132
2023-01-23 02:24:16.979773: step: 336/529, loss: 0.004550695884972811
2023-01-23 02:24:18.109886: step: 340/529, loss: 0.11097335815429688
2023-01-23 02:24:19.247103: step: 344/529, loss: 0.022510338574647903
2023-01-23 02:24:20.335401: step: 348/529, loss: 0.01965322531759739
2023-01-23 02:24:21.456746: step: 352/529, loss: 0.031092356890439987
2023-01-23 02:24:22.514753: step: 356/529, loss: 0.0006049156654626131
2023-01-23 02:24:23.629246: step: 360/529, loss: 0.004075813572853804
2023-01-23 02:24:24.767824: step: 364/529, loss: 0.08412008732557297
2023-01-23 02:24:25.878982: step: 368/529, loss: 6.628036499023438e-05
2023-01-23 02:24:26.961507: step: 372/529, loss: 0.011430168524384499
2023-01-23 02:24:28.084616: step: 376/529, loss: 0.02530393749475479
2023-01-23 02:24:29.196225: step: 380/529, loss: 0.03544940799474716
2023-01-23 02:24:30.332983: step: 384/529, loss: 0.04354820027947426
2023-01-23 02:24:31.435841: step: 388/529, loss: 0.009791946969926357
2023-01-23 02:24:32.539733: step: 392/529, loss: 0.001482200575992465
2023-01-23 02:24:33.631186: step: 396/529, loss: 0.03681983798742294
2023-01-23 02:24:34.736258: step: 400/529, loss: 0.005219554994255304
2023-01-23 02:24:35.858311: step: 404/529, loss: 0.10754509270191193
2023-01-23 02:24:36.981941: step: 408/529, loss: 0.013379668816924095
2023-01-23 02:24:38.087208: step: 412/529, loss: 0.038869570940732956
2023-01-23 02:24:39.205531: step: 416/529, loss: 0.006100082769989967
2023-01-23 02:24:40.354595: step: 420/529, loss: 0.023983241990208626
2023-01-23 02:24:41.483408: step: 424/529, loss: 8.678436643094756e-06
2023-01-23 02:24:42.588366: step: 428/529, loss: 0.00715904263779521
2023-01-23 02:24:43.678271: step: 432/529, loss: 0.015358162112534046
2023-01-23 02:24:44.795861: step: 436/529, loss: 0.009467792697250843
2023-01-23 02:24:45.887899: step: 440/529, loss: 0.03373704105615616
2023-01-23 02:24:46.992736: step: 444/529, loss: 0.00965423509478569
2023-01-23 02:24:48.087981: step: 448/529, loss: 0.0037589548155665398
2023-01-23 02:24:49.231996: step: 452/529, loss: 0.10768795758485794
2023-01-23 02:24:50.306831: step: 456/529, loss: 0.05358562618494034
2023-01-23 02:24:51.398196: step: 460/529, loss: 0.0011633873218670487
2023-01-23 02:24:52.490037: step: 464/529, loss: 0.02670455165207386
2023-01-23 02:24:53.572932: step: 468/529, loss: 0.014192391186952591
2023-01-23 02:24:54.680380: step: 472/529, loss: 0.006118393037468195
2023-01-23 02:24:55.783277: step: 476/529, loss: 0.002104187151417136
2023-01-23 02:24:56.893734: step: 480/529, loss: 0.0248170867562294
2023-01-23 02:24:57.975001: step: 484/529, loss: 0.002963257022202015
2023-01-23 02:24:59.060009: step: 488/529, loss: 0.000711977481842041
2023-01-23 02:25:00.193052: step: 492/529, loss: 0.0024950981605798006
2023-01-23 02:25:01.319525: step: 496/529, loss: 0.006621265783905983
2023-01-23 02:25:02.426711: step: 500/529, loss: 0.014836407266557217
2023-01-23 02:25:03.513046: step: 504/529, loss: 0.011418056674301624
2023-01-23 02:25:04.618778: step: 508/529, loss: 0.0636986717581749
2023-01-23 02:25:05.753283: step: 512/529, loss: 0.039900828152894974
2023-01-23 02:25:06.857095: step: 516/529, loss: -1.3828277587890625e-05
2023-01-23 02:25:07.962975: step: 520/529, loss: 0.002452850341796875
2023-01-23 02:25:09.094858: step: 524/529, loss: 0.0038934708572924137
2023-01-23 02:25:10.203102: step: 528/529, loss: 0.010477161034941673
2023-01-23 02:25:11.317837: step: 532/529, loss: 0.0071919444017112255
2023-01-23 02:25:12.448412: step: 536/529, loss: 0.00015864371380303055
2023-01-23 02:25:13.549184: step: 540/529, loss: 0.018250465393066406
2023-01-23 02:25:14.677230: step: 544/529, loss: 0.0032693862449377775
2023-01-23 02:25:15.765201: step: 548/529, loss: 0.00015745163545943797
2023-01-23 02:25:16.865939: step: 552/529, loss: 0.06083851307630539
2023-01-23 02:25:17.964511: step: 556/529, loss: 0.0032431127037853003
2023-01-23 02:25:19.073239: step: 560/529, loss: 0.02098102495074272
2023-01-23 02:25:20.160326: step: 564/529, loss: 0.010703039355576038
2023-01-23 02:25:21.285457: step: 568/529, loss: 0.05978946387767792
2023-01-23 02:25:22.374366: step: 572/529, loss: 0.002813053084537387
2023-01-23 02:25:23.479787: step: 576/529, loss: 0.04347124323248863
2023-01-23 02:25:24.602297: step: 580/529, loss: 0.01481637917459011
2023-01-23 02:25:25.688211: step: 584/529, loss: 0.02793254889547825
2023-01-23 02:25:26.806231: step: 588/529, loss: 0.0008490562322549522
2023-01-23 02:25:27.896726: step: 592/529, loss: 0.00684547470882535
2023-01-23 02:25:29.005477: step: 596/529, loss: 0.0012743950355798006
2023-01-23 02:25:30.128937: step: 600/529, loss: 0.003914475440979004
2023-01-23 02:25:31.228898: step: 604/529, loss: 0.0004927635309286416
2023-01-23 02:25:32.334698: step: 608/529, loss: 0.010393905453383923
2023-01-23 02:25:33.465475: step: 612/529, loss: 0.01200017984956503
2023-01-23 02:25:34.622706: step: 616/529, loss: 0.11614914238452911
2023-01-23 02:25:35.719746: step: 620/529, loss: 0.0013360977172851562
2023-01-23 02:25:36.833029: step: 624/529, loss: 0.0043464661575853825
2023-01-23 02:25:37.946191: step: 628/529, loss: 0.0014190673828125
2023-01-23 02:25:39.039958: step: 632/529, loss: 0.07492131739854813
2023-01-23 02:25:40.145201: step: 636/529, loss: 0.012208842672407627
2023-01-23 02:25:41.258405: step: 640/529, loss: 0.001449680421501398
2023-01-23 02:25:42.395455: step: 644/529, loss: 0.021663475781679153
2023-01-23 02:25:43.465812: step: 648/529, loss: 1.3542176020564511e-05
2023-01-23 02:25:44.555025: step: 652/529, loss: 0.027807235717773438
2023-01-23 02:25:45.664758: step: 656/529, loss: 0.0062777516432106495
2023-01-23 02:25:46.797072: step: 660/529, loss: 0.009154224768280983
2023-01-23 02:25:47.920425: step: 664/529, loss: 0.03375568240880966
2023-01-23 02:25:49.042927: step: 668/529, loss: 0.0016595839988440275
2023-01-23 02:25:50.162292: step: 672/529, loss: 0.005206489935517311
2023-01-23 02:25:51.251776: step: 676/529, loss: 0.004783108830451965
2023-01-23 02:25:52.383296: step: 680/529, loss: 0.13351936638355255
2023-01-23 02:25:53.538085: step: 684/529, loss: 0.03379116207361221
2023-01-23 02:25:54.650667: step: 688/529, loss: 0.002034950302913785
2023-01-23 02:25:55.755792: step: 692/529, loss: 0.0030596733558923006
2023-01-23 02:25:56.854781: step: 696/529, loss: 0.01688232459127903
2023-01-23 02:25:57.943454: step: 700/529, loss: 0.005562114994972944
2023-01-23 02:25:59.027660: step: 704/529, loss: 0.024741649627685547
2023-01-23 02:26:00.121326: step: 708/529, loss: 0.000754928623791784
2023-01-23 02:26:01.223369: step: 712/529, loss: 0.0010656357044354081
2023-01-23 02:26:02.330881: step: 716/529, loss: 0.07712183147668839
2023-01-23 02:26:03.436564: step: 720/529, loss: 0.0018567085498943925
2023-01-23 02:26:04.567605: step: 724/529, loss: 0.025477027520537376
2023-01-23 02:26:05.677961: step: 728/529, loss: 0.07873684912919998
2023-01-23 02:26:06.756055: step: 732/529, loss: 0.032294657081365585
2023-01-23 02:26:07.892289: step: 736/529, loss: 0.008506583981215954
2023-01-23 02:26:09.040199: step: 740/529, loss: 0.007420158479362726
2023-01-23 02:26:10.181015: step: 744/529, loss: 0.005598259158432484
2023-01-23 02:26:11.294741: step: 748/529, loss: 6.632805161643773e-05
2023-01-23 02:26:12.397983: step: 752/529, loss: 0.005912971682846546
2023-01-23 02:26:13.517587: step: 756/529, loss: 0.016251374036073685
2023-01-23 02:26:14.626094: step: 760/529, loss: 0.5293411016464233
2023-01-23 02:26:15.733072: step: 764/529, loss: 0.0023424148093909025
2023-01-23 02:26:16.845570: step: 768/529, loss: 0.002216339111328125
2023-01-23 02:26:17.982576: step: 772/529, loss: 8.735656592762098e-05
2023-01-23 02:26:19.078022: step: 776/529, loss: 0.0282000545412302
2023-01-23 02:26:20.192583: step: 780/529, loss: 0.0027191161643713713
2023-01-23 02:26:21.298020: step: 784/529, loss: 0.042397309094667435
2023-01-23 02:26:22.388316: step: 788/529, loss: 0.010380363091826439
2023-01-23 02:26:23.512470: step: 792/529, loss: 0.0034318447578698397
2023-01-23 02:26:24.636217: step: 796/529, loss: 0.006031608674675226
2023-01-23 02:26:25.754565: step: 800/529, loss: 0.036104727536439896
2023-01-23 02:26:26.871852: step: 804/529, loss: 0.027247143909335136
2023-01-23 02:26:27.993746: step: 808/529, loss: 0.0003262520185671747
2023-01-23 02:26:29.085581: step: 812/529, loss: 0.017936134710907936
2023-01-23 02:26:30.219521: step: 816/529, loss: 0.02042541652917862
2023-01-23 02:26:31.308794: step: 820/529, loss: 0.022796964272856712
2023-01-23 02:26:32.434805: step: 824/529, loss: 0.1252817064523697
2023-01-23 02:26:33.562829: step: 828/529, loss: 0.01477670669555664
2023-01-23 02:26:34.677116: step: 832/529, loss: 0.08678007125854492
2023-01-23 02:26:35.819095: step: 836/529, loss: 0.017061900347471237
2023-01-23 02:26:36.926504: step: 840/529, loss: 0.019028853625059128
2023-01-23 02:26:38.049142: step: 844/529, loss: 0.0069172861985862255
2023-01-23 02:26:39.156289: step: 848/529, loss: 0.010430335998535156
2023-01-23 02:26:40.277814: step: 852/529, loss: 0.02069452591240406
2023-01-23 02:26:41.440683: step: 856/529, loss: 0.020403005182743073
2023-01-23 02:26:42.601921: step: 860/529, loss: 0.0027370452880859375
2023-01-23 02:26:43.702890: step: 864/529, loss: 0.004788017366081476
2023-01-23 02:26:44.795887: step: 868/529, loss: 0.03317966312170029
2023-01-23 02:26:45.903321: step: 872/529, loss: 0.054764557629823685
2023-01-23 02:26:47.025388: step: 876/529, loss: 0.0829157829284668
2023-01-23 02:26:48.143819: step: 880/529, loss: 0.027825355529785156
2023-01-23 02:26:49.250381: step: 884/529, loss: 0.05098400264978409
2023-01-23 02:26:50.352033: step: 888/529, loss: 0.0057725911028683186
2023-01-23 02:26:51.442589: step: 892/529, loss: 0.03614835813641548
2023-01-23 02:26:52.558822: step: 896/529, loss: 0.0006322860717773438
2023-01-23 02:26:53.687418: step: 900/529, loss: 0.002818298526108265
2023-01-23 02:26:54.807157: step: 904/529, loss: 0.26575013995170593
2023-01-23 02:26:55.953239: step: 908/529, loss: 0.007422256283462048
2023-01-23 02:26:57.043056: step: 912/529, loss: 0.01878061331808567
2023-01-23 02:26:58.178084: step: 916/529, loss: 0.007219791878014803
2023-01-23 02:26:59.276406: step: 920/529, loss: 0.0006025314796715975
2023-01-23 02:27:00.393843: step: 924/529, loss: 0.0012438774574548006
2023-01-23 02:27:01.490858: step: 928/529, loss: 0.020307209342718124
2023-01-23 02:27:02.586279: step: 932/529, loss: 0.0311342254281044
2023-01-23 02:27:03.697777: step: 936/529, loss: 0.0036264420486986637
2023-01-23 02:27:04.771085: step: 940/529, loss: 0.003145313123241067
2023-01-23 02:27:05.882768: step: 944/529, loss: 0.017205860465765
2023-01-23 02:27:07.033646: step: 948/529, loss: 0.041124965995550156
2023-01-23 02:27:08.136855: step: 952/529, loss: 0.04513072967529297
2023-01-23 02:27:09.269845: step: 956/529, loss: 0.007253456395119429
2023-01-23 02:27:10.334813: step: 960/529, loss: 0.029857492074370384
2023-01-23 02:27:11.438984: step: 964/529, loss: 0.07467031478881836
2023-01-23 02:27:12.526209: step: 968/529, loss: 0.04811658710241318
2023-01-23 02:27:13.647403: step: 972/529, loss: 0.011242199689149857
2023-01-23 02:27:14.824172: step: 976/529, loss: 0.0834631472826004
2023-01-23 02:27:15.942784: step: 980/529, loss: 0.007007026579231024
2023-01-23 02:27:17.058662: step: 984/529, loss: 0.00588116655126214
2023-01-23 02:27:18.200702: step: 988/529, loss: 0.027263546362519264
2023-01-23 02:27:19.297182: step: 992/529, loss: 0.005964470095932484
2023-01-23 02:27:20.405849: step: 996/529, loss: 0.008327484130859375
2023-01-23 02:27:21.549515: step: 1000/529, loss: 0.0031923295464366674
2023-01-23 02:27:22.652852: step: 1004/529, loss: 0.03464236110448837
2023-01-23 02:27:23.744563: step: 1008/529, loss: 0.041654013097286224
2023-01-23 02:27:24.854902: step: 1012/529, loss: 0.011207103729248047
2023-01-23 02:27:25.995277: step: 1016/529, loss: 0.00887765921652317
2023-01-23 02:27:27.103883: step: 1020/529, loss: 0.007322216406464577
2023-01-23 02:27:28.180814: step: 1024/529, loss: 0.0009346485021524131
2023-01-23 02:27:29.263687: step: 1028/529, loss: 0.0038628578186035156
2023-01-23 02:27:30.362163: step: 1032/529, loss: 0.05310516431927681
2023-01-23 02:27:31.485342: step: 1036/529, loss: 0.007705688942223787
2023-01-23 02:27:32.571780: step: 1040/529, loss: 0.005209731869399548
2023-01-23 02:27:33.670504: step: 1044/529, loss: 0.029564954340457916
2023-01-23 02:27:34.782142: step: 1048/529, loss: 0.6632478833198547
2023-01-23 02:27:35.906754: step: 1052/529, loss: 0.045206259936094284
2023-01-23 02:27:37.021742: step: 1056/529, loss: 0.036804962903261185
2023-01-23 02:27:38.144759: step: 1060/529, loss: 0.06002082675695419
2023-01-23 02:27:39.236209: step: 1064/529, loss: 0.030590534210205078
2023-01-23 02:27:40.339188: step: 1068/529, loss: 0.02960033528506756
2023-01-23 02:27:41.447885: step: 1072/529, loss: 0.0005201339954510331
2023-01-23 02:27:42.599854: step: 1076/529, loss: 0.07917747646570206
2023-01-23 02:27:43.710903: step: 1080/529, loss: 0.012373924255371094
2023-01-23 02:27:44.850298: step: 1084/529, loss: 0.03654327616095543
2023-01-23 02:27:45.959219: step: 1088/529, loss: 0.025353502482175827
2023-01-23 02:27:47.077520: step: 1092/529, loss: 0.015633774921298027
2023-01-23 02:27:48.178992: step: 1096/529, loss: 0.0013218403328210115
2023-01-23 02:27:49.297293: step: 1100/529, loss: 0.0006042480817995965
2023-01-23 02:27:50.404483: step: 1104/529, loss: 0.0016802788013592362
2023-01-23 02:27:51.516642: step: 1108/529, loss: 0.0032924653496593237
2023-01-23 02:27:52.700072: step: 1112/529, loss: 0.00364513392560184
2023-01-23 02:27:53.852391: step: 1116/529, loss: 0.001890039537101984
2023-01-23 02:27:55.010522: step: 1120/529, loss: 0.27777138352394104
2023-01-23 02:27:56.127174: step: 1124/529, loss: 0.006247472949326038
2023-01-23 02:27:57.260628: step: 1128/529, loss: 0.007719802670180798
2023-01-23 02:27:58.359637: step: 1132/529, loss: 0.026265526190400124
2023-01-23 02:27:59.470052: step: 1136/529, loss: 0.0666351318359375
2023-01-23 02:28:00.609641: step: 1140/529, loss: 0.048487283289432526
2023-01-23 02:28:01.708142: step: 1144/529, loss: 0.09375075995922089
2023-01-23 02:28:02.797428: step: 1148/529, loss: 0.0002989768981933594
2023-01-23 02:28:03.878729: step: 1152/529, loss: 0.00042276381282135844
2023-01-23 02:28:04.975369: step: 1156/529, loss: 0.042872242629528046
2023-01-23 02:28:06.082889: step: 1160/529, loss: 0.0010498047340661287
2023-01-23 02:28:07.231837: step: 1164/529, loss: 0.011212730780243874
2023-01-23 02:28:08.317397: step: 1168/529, loss: 0.0013476371532306075
2023-01-23 02:28:09.416414: step: 1172/529, loss: 0.11217289417982101
2023-01-23 02:28:10.538364: step: 1176/529, loss: 0.06064195930957794
2023-01-23 02:28:11.656523: step: 1180/529, loss: 0.0345364585518837
2023-01-23 02:28:12.774664: step: 1184/529, loss: 0.08045224845409393
2023-01-23 02:28:13.864553: step: 1188/529, loss: 0.003103935858234763
2023-01-23 02:28:15.000860: step: 1192/529, loss: 0.0014510632026940584
2023-01-23 02:28:16.083079: step: 1196/529, loss: 0.009851646609604359
2023-01-23 02:28:17.200178: step: 1200/529, loss: 0.013622951693832874
2023-01-23 02:28:18.301814: step: 1204/529, loss: 0.20609799027442932
2023-01-23 02:28:19.383570: step: 1208/529, loss: 0.005534553900361061
2023-01-23 02:28:20.491832: step: 1212/529, loss: 0.05313606560230255
2023-01-23 02:28:21.600094: step: 1216/529, loss: 0.034075211733579636
2023-01-23 02:28:22.713702: step: 1220/529, loss: 0.00260162353515625
2023-01-23 02:28:23.844523: step: 1224/529, loss: 5.455017162603326e-05
2023-01-23 02:28:24.943823: step: 1228/529, loss: 0.0028947831597179174
2023-01-23 02:28:26.044546: step: 1232/529, loss: 0.0009201050270348787
2023-01-23 02:28:27.184134: step: 1236/529, loss: 0.01868276670575142
2023-01-23 02:28:28.341099: step: 1240/529, loss: 0.02008838765323162
2023-01-23 02:28:29.452869: step: 1244/529, loss: 0.0003276825009379536
2023-01-23 02:28:30.611953: step: 1248/529, loss: 0.8614374995231628
2023-01-23 02:28:31.723609: step: 1252/529, loss: 0.0036573412362486124
2023-01-23 02:28:32.842162: step: 1256/529, loss: 0.0009625435341149569
2023-01-23 02:28:33.969498: step: 1260/529, loss: 0.03019714541733265
2023-01-23 02:28:35.097147: step: 1264/529, loss: 0.005444717593491077
2023-01-23 02:28:36.230043: step: 1268/529, loss: 0.0035126684233546257
2023-01-23 02:28:37.390282: step: 1272/529, loss: 0.011497306637465954
2023-01-23 02:28:38.515327: step: 1276/529, loss: 0.0055480957962572575
2023-01-23 02:28:39.627804: step: 1280/529, loss: 0.006733989808708429
2023-01-23 02:28:40.728955: step: 1284/529, loss: 0.04899817705154419
2023-01-23 02:28:41.844262: step: 1288/529, loss: 0.011456918902695179
2023-01-23 02:28:42.979215: step: 1292/529, loss: 0.027710085734725
2023-01-23 02:28:44.064259: step: 1296/529, loss: 0.01874075084924698
2023-01-23 02:28:45.200804: step: 1300/529, loss: 0.012926960363984108
2023-01-23 02:28:46.289159: step: 1304/529, loss: 0.0043496135622262955
2023-01-23 02:28:47.378786: step: 1308/529, loss: 0.013659668155014515
2023-01-23 02:28:48.456418: step: 1312/529, loss: 0.0006468773353844881
2023-01-23 02:28:49.552157: step: 1316/529, loss: 0.040293123573064804
2023-01-23 02:28:50.644658: step: 1320/529, loss: 0.00016374587721657008
2023-01-23 02:28:51.774327: step: 1324/529, loss: 0.018106840550899506
2023-01-23 02:28:52.876678: step: 1328/529, loss: 0.09573593735694885
2023-01-23 02:28:53.964519: step: 1332/529, loss: 0.009221458807587624
2023-01-23 02:28:55.050766: step: 1336/529, loss: 0.005654716864228249
2023-01-23 02:28:56.172707: step: 1340/529, loss: 0.007609749212861061
2023-01-23 02:28:57.284517: step: 1344/529, loss: 0.017772484570741653
2023-01-23 02:28:58.403625: step: 1348/529, loss: 0.004604435060173273
2023-01-23 02:28:59.500125: step: 1352/529, loss: 0.044849492609500885
2023-01-23 02:29:00.622242: step: 1356/529, loss: 0.019938278943300247
2023-01-23 02:29:01.735674: step: 1360/529, loss: 0.053911399096250534
2023-01-23 02:29:02.831309: step: 1364/529, loss: 0.0022809982765465975
2023-01-23 02:29:03.931004: step: 1368/529, loss: 0.0145721435546875
2023-01-23 02:29:05.040219: step: 1372/529, loss: 0.002082443330436945
2023-01-23 02:29:06.147285: step: 1376/529, loss: 0.07693834602832794
2023-01-23 02:29:07.249544: step: 1380/529, loss: 0.11413994431495667
2023-01-23 02:29:08.393634: step: 1384/529, loss: 0.06834125518798828
2023-01-23 02:29:09.493433: step: 1388/529, loss: 0.057936858385801315
2023-01-23 02:29:10.608401: step: 1392/529, loss: 0.05052356794476509
2023-01-23 02:29:11.708620: step: 1396/529, loss: 0.03631248697638512
2023-01-23 02:29:12.794111: step: 1400/529, loss: 0.023670196533203125
2023-01-23 02:29:13.904512: step: 1404/529, loss: 0.04947681725025177
2023-01-23 02:29:15.014567: step: 1408/529, loss: 0.10579337924718857
2023-01-23 02:29:16.138849: step: 1412/529, loss: 0.0837366133928299
2023-01-23 02:29:17.245941: step: 1416/529, loss: 0.00044727325439453125
2023-01-23 02:29:18.341611: step: 1420/529, loss: 0.01910400576889515
2023-01-23 02:29:19.470117: step: 1424/529, loss: 0.003924655728042126
2023-01-23 02:29:20.564548: step: 1428/529, loss: 0.0013859033351764083
2023-01-23 02:29:21.687202: step: 1432/529, loss: 0.002593517303466797
2023-01-23 02:29:22.818896: step: 1436/529, loss: 0.000583648681640625
2023-01-23 02:29:23.889431: step: 1440/529, loss: 0.00019402503676246852
2023-01-23 02:29:24.955084: step: 1444/529, loss: 0.042620182037353516
2023-01-23 02:29:26.069592: step: 1448/529, loss: 0.016722679138183594
2023-01-23 02:29:27.177813: step: 1452/529, loss: 0.00067052838858217
2023-01-23 02:29:28.309767: step: 1456/529, loss: 0.0017459869850426912
2023-01-23 02:29:29.411786: step: 1460/529, loss: 0.08023948967456818
2023-01-23 02:29:30.525911: step: 1464/529, loss: 0.009878730401396751
2023-01-23 02:29:31.627621: step: 1468/529, loss: 0.023539256304502487
2023-01-23 02:29:32.740327: step: 1472/529, loss: 0.019981766119599342
2023-01-23 02:29:33.832078: step: 1476/529, loss: 0.010811900720000267
2023-01-23 02:29:34.964460: step: 1480/529, loss: 0.062145281583070755
2023-01-23 02:29:36.085858: step: 1484/529, loss: 0.003956461325287819
2023-01-23 02:29:37.215925: step: 1488/529, loss: 0.009970379061996937
2023-01-23 02:29:38.322697: step: 1492/529, loss: 0.020316505804657936
2023-01-23 02:29:39.440042: step: 1496/529, loss: 0.0733499526977539
2023-01-23 02:29:40.559188: step: 1500/529, loss: 0.010421562008559704
2023-01-23 02:29:41.668692: step: 1504/529, loss: 0.010651921853423119
2023-01-23 02:29:42.758035: step: 1508/529, loss: 0.05582462251186371
2023-01-23 02:29:43.872083: step: 1512/529, loss: 0.004432773683220148
2023-01-23 02:29:44.990421: step: 1516/529, loss: 0.026908492669463158
2023-01-23 02:29:46.093978: step: 1520/529, loss: 0.001308441162109375
2023-01-23 02:29:47.223710: step: 1524/529, loss: 0.00920639093965292
2023-01-23 02:29:48.334335: step: 1528/529, loss: 0.07841330021619797
2023-01-23 02:29:49.487272: step: 1532/529, loss: 0.011953807435929775
2023-01-23 02:29:50.599701: step: 1536/529, loss: 0.05583386868238449
2023-01-23 02:29:51.710623: step: 1540/529, loss: 0.027892112731933594
2023-01-23 02:29:52.805511: step: 1544/529, loss: 0.02685546875
2023-01-23 02:29:53.902253: step: 1548/529, loss: 0.04306450113654137
2023-01-23 02:29:55.023088: step: 1552/529, loss: 0.0007810592651367188
2023-01-23 02:29:56.131192: step: 1556/529, loss: 0.0005102157592773438
2023-01-23 02:29:57.248745: step: 1560/529, loss: 0.027725793421268463
2023-01-23 02:29:58.352539: step: 1564/529, loss: 0.008467674255371094
2023-01-23 02:29:59.445698: step: 1568/529, loss: 0.0001546144630992785
2023-01-23 02:30:00.569187: step: 1572/529, loss: 0.014438152313232422
2023-01-23 02:30:01.701127: step: 1576/529, loss: 0.042174626141786575
2023-01-23 02:30:02.836638: step: 1580/529, loss: 0.02753734588623047
2023-01-23 02:30:03.977202: step: 1584/529, loss: 0.00016841889009810984
2023-01-23 02:30:05.107658: step: 1588/529, loss: 0.0010137557983398438
2023-01-23 02:30:06.212338: step: 1592/529, loss: 0.017825031653046608
2023-01-23 02:30:07.295056: step: 1596/529, loss: 0.0008176803821697831
2023-01-23 02:30:08.415856: step: 1600/529, loss: 0.018732547760009766
2023-01-23 02:30:09.543826: step: 1604/529, loss: 0.0032693862449377775
2023-01-23 02:30:10.681574: step: 1608/529, loss: 0.04006028175354004
2023-01-23 02:30:11.791423: step: 1612/529, loss: 0.002649164292961359
2023-01-23 02:30:12.895400: step: 1616/529, loss: 0.0437227264046669
2023-01-23 02:30:14.005431: step: 1620/529, loss: 0.02005309984087944
2023-01-23 02:30:15.125107: step: 1624/529, loss: 0.0009645462268963456
2023-01-23 02:30:16.267003: step: 1628/529, loss: 0.007365926168859005
2023-01-23 02:30:17.354890: step: 1632/529, loss: 0.09861570596694946
2023-01-23 02:30:18.468895: step: 1636/529, loss: 0.060585781931877136
2023-01-23 02:30:19.601622: step: 1640/529, loss: 0.03949327394366264
2023-01-23 02:30:20.762969: step: 1644/529, loss: 0.00044736862764693797
2023-01-23 02:30:21.881278: step: 1648/529, loss: 0.012586403638124466
2023-01-23 02:30:22.993540: step: 1652/529, loss: 0.005134296603500843
2023-01-23 02:30:24.112520: step: 1656/529, loss: 0.015186309814453125
2023-01-23 02:30:25.194529: step: 1660/529, loss: 0.02126135863363743
2023-01-23 02:30:26.295139: step: 1664/529, loss: 0.006412029266357422
2023-01-23 02:30:27.388785: step: 1668/529, loss: 0.025492003187537193
2023-01-23 02:30:28.473019: step: 1672/529, loss: 0.005620527546852827
2023-01-23 02:30:29.558648: step: 1676/529, loss: 0.009557342156767845
2023-01-23 02:30:30.682486: step: 1680/529, loss: 0.010870552621781826
2023-01-23 02:30:31.815451: step: 1684/529, loss: 0.03641529381275177
2023-01-23 02:30:32.921465: step: 1688/529, loss: 0.00741653423756361
2023-01-23 02:30:34.035658: step: 1692/529, loss: 0.013895892538130283
2023-01-23 02:30:35.135773: step: 1696/529, loss: 0.03253583982586861
2023-01-23 02:30:36.261112: step: 1700/529, loss: 0.016987323760986328
2023-01-23 02:30:37.362461: step: 1704/529, loss: 0.002588987350463867
2023-01-23 02:30:38.475809: step: 1708/529, loss: 0.0005561828729696572
2023-01-23 02:30:39.577670: step: 1712/529, loss: 0.008816909044981003
2023-01-23 02:30:40.712886: step: 1716/529, loss: 0.019388962537050247
2023-01-23 02:30:41.830754: step: 1720/529, loss: 0.015825558453798294
2023-01-23 02:30:42.944363: step: 1724/529, loss: 0.016736602410674095
2023-01-23 02:30:44.036190: step: 1728/529, loss: 0.0016808033687993884
2023-01-23 02:30:45.135923: step: 1732/529, loss: 0.007079220376908779
2023-01-23 02:30:46.231720: step: 1736/529, loss: 0.008332825265824795
2023-01-23 02:30:47.325867: step: 1740/529, loss: 0.014214038848876953
2023-01-23 02:30:48.462189: step: 1744/529, loss: 0.04362468793988228
2023-01-23 02:30:49.579087: step: 1748/529, loss: 0.016611767932772636
2023-01-23 02:30:50.714423: step: 1752/529, loss: 0.0069817546755075455
2023-01-23 02:30:51.827027: step: 1756/529, loss: 0.0020694732666015625
2023-01-23 02:30:52.951335: step: 1760/529, loss: 0.010686875320971012
2023-01-23 02:30:54.056663: step: 1764/529, loss: 0.01836833916604519
2023-01-23 02:30:55.175708: step: 1768/529, loss: 0.0010773659450933337
2023-01-23 02:30:56.304246: step: 1772/529, loss: 0.011740017682313919
2023-01-23 02:30:57.413875: step: 1776/529, loss: 0.0022144317626953125
2023-01-23 02:30:58.518331: step: 1780/529, loss: 0.04025249555706978
2023-01-23 02:30:59.634948: step: 1784/529, loss: 0.0018579483730718493
2023-01-23 02:31:00.757497: step: 1788/529, loss: 0.05710163339972496
2023-01-23 02:31:01.870616: step: 1792/529, loss: 0.0002894401550292969
2023-01-23 02:31:03.001408: step: 1796/529, loss: 0.017987919971346855
2023-01-23 02:31:04.122460: step: 1800/529, loss: 0.0022237778175622225
2023-01-23 02:31:05.220683: step: 1804/529, loss: 0.061766814440488815
2023-01-23 02:31:06.313656: step: 1808/529, loss: 0.05389413982629776
2023-01-23 02:31:07.423564: step: 1812/529, loss: 0.031571388244628906
2023-01-23 02:31:08.546631: step: 1816/529, loss: 0.01135721243917942
2023-01-23 02:31:09.705438: step: 1820/529, loss: 0.04927196353673935
2023-01-23 02:31:10.859100: step: 1824/529, loss: 0.036455631256103516
2023-01-23 02:31:12.002729: step: 1828/529, loss: 0.023421669378876686
2023-01-23 02:31:13.082548: step: 1832/529, loss: 0.046378135681152344
2023-01-23 02:31:14.185474: step: 1836/529, loss: 0.013359260745346546
2023-01-23 02:31:15.310340: step: 1840/529, loss: 0.9466407895088196
2023-01-23 02:31:16.381549: step: 1844/529, loss: 0.007301521487534046
2023-01-23 02:31:17.524523: step: 1848/529, loss: 0.007399082183837891
2023-01-23 02:31:18.608808: step: 1852/529, loss: 5.991458965581842e-05
2023-01-23 02:31:19.742049: step: 1856/529, loss: 0.01962299272418022
2023-01-23 02:31:20.870472: step: 1860/529, loss: 0.03183336555957794
2023-01-23 02:31:21.991663: step: 1864/529, loss: 0.003655338194221258
2023-01-23 02:31:23.078953: step: 1868/529, loss: 0.023988496512174606
2023-01-23 02:31:24.160259: step: 1872/529, loss: 0.015140724368393421
2023-01-23 02:31:25.279894: step: 1876/529, loss: 0.04513759911060333
2023-01-23 02:31:26.391153: step: 1880/529, loss: 0.025017166510224342
2023-01-23 02:31:27.501712: step: 1884/529, loss: 0.013048839755356312
2023-01-23 02:31:28.609360: step: 1888/529, loss: 0.0011128425830975175
2023-01-23 02:31:29.735622: step: 1892/529, loss: 5.059242539573461e-05
2023-01-23 02:31:30.868628: step: 1896/529, loss: 0.013761520385742188
2023-01-23 02:31:32.005828: step: 1900/529, loss: 0.0029476166237145662
2023-01-23 02:31:33.113178: step: 1904/529, loss: 0.000491285347379744
2023-01-23 02:31:34.235156: step: 1908/529, loss: 0.10273055732250214
2023-01-23 02:31:35.326938: step: 1912/529, loss: 1.6620161533355713
2023-01-23 02:31:36.399773: step: 1916/529, loss: 0.0021393776405602694
2023-01-23 02:31:37.510291: step: 1920/529, loss: 0.0120093347504735
2023-01-23 02:31:38.594661: step: 1924/529, loss: 0.04906215891242027
2023-01-23 02:31:39.688932: step: 1928/529, loss: 0.0005199432489462197
2023-01-23 02:31:40.798072: step: 1932/529, loss: 0.01281890831887722
2023-01-23 02:31:41.918659: step: 1936/529, loss: 0.03534068912267685
2023-01-23 02:31:43.018702: step: 1940/529, loss: 0.04288816452026367
2023-01-23 02:31:44.145687: step: 1944/529, loss: 0.013931083492934704
2023-01-23 02:31:45.289548: step: 1948/529, loss: 0.00337033299729228
2023-01-23 02:31:46.418676: step: 1952/529, loss: 0.0031180856749415398
2023-01-23 02:31:47.501677: step: 1956/529, loss: 0.004653358366340399
2023-01-23 02:31:48.620485: step: 1960/529, loss: 0.02243976667523384
2023-01-23 02:31:49.733138: step: 1964/529, loss: 0.032325174659490585
2023-01-23 02:31:50.851847: step: 1968/529, loss: 0.016070544719696045
2023-01-23 02:31:51.959682: step: 1972/529, loss: 0.043839454650878906
2023-01-23 02:31:53.066425: step: 1976/529, loss: 0.009467696771025658
2023-01-23 02:31:54.156736: step: 1980/529, loss: 0.05063324049115181
2023-01-23 02:31:55.278197: step: 1984/529, loss: 0.0005445480346679688
2023-01-23 02:31:56.389135: step: 1988/529, loss: 0.013491821475327015
2023-01-23 02:31:57.508278: step: 1992/529, loss: 0.004249191377311945
2023-01-23 02:31:58.642794: step: 1996/529, loss: 0.028296470642089844
2023-01-23 02:31:59.748008: step: 2000/529, loss: 0.0012382508721202612
2023-01-23 02:32:00.851772: step: 2004/529, loss: 0.00345611572265625
2023-01-23 02:32:01.990269: step: 2008/529, loss: 0.003939628601074219
2023-01-23 02:32:03.114691: step: 2012/529, loss: 0.0013811112148687243
2023-01-23 02:32:04.228933: step: 2016/529, loss: 0.004080319777131081
2023-01-23 02:32:05.365051: step: 2020/529, loss: 0.004145240876823664
2023-01-23 02:32:06.455988: step: 2024/529, loss: 0.0001321792515227571
2023-01-23 02:32:07.550901: step: 2028/529, loss: 0.002094364259392023
2023-01-23 02:32:08.652671: step: 2032/529, loss: 0.009102821350097656
2023-01-23 02:32:09.762271: step: 2036/529, loss: 0.0030755999032408
2023-01-23 02:32:10.858254: step: 2040/529, loss: 0.008584881201386452
2023-01-23 02:32:11.958478: step: 2044/529, loss: 0.0020897865761071444
2023-01-23 02:32:13.068851: step: 2048/529, loss: 0.0003311157342977822
2023-01-23 02:32:14.174641: step: 2052/529, loss: 0.022060489282011986
2023-01-23 02:32:15.301679: step: 2056/529, loss: 0.0026691914536058903
2023-01-23 02:32:16.435971: step: 2060/529, loss: 0.004038190934807062
2023-01-23 02:32:17.568709: step: 2064/529, loss: 0.0020453452598303556
2023-01-23 02:32:18.689221: step: 2068/529, loss: 0.010776758193969727
2023-01-23 02:32:19.826066: step: 2072/529, loss: 0.08061805367469788
2023-01-23 02:32:20.947381: step: 2076/529, loss: 0.09675603359937668
2023-01-23 02:32:22.062748: step: 2080/529, loss: 0.0015539169544354081
2023-01-23 02:32:23.200511: step: 2084/529, loss: 0.06428580731153488
2023-01-23 02:32:24.328353: step: 2088/529, loss: 0.013783454895019531
2023-01-23 02:32:25.437269: step: 2092/529, loss: 0.024349594488739967
2023-01-23 02:32:26.528167: step: 2096/529, loss: 0.030339624732732773
2023-01-23 02:32:27.633168: step: 2100/529, loss: 0.0008707046508789062
2023-01-23 02:32:28.762915: step: 2104/529, loss: 0.3763510584831238
2023-01-23 02:32:29.883330: step: 2108/529, loss: 0.01416854839771986
2023-01-23 02:32:30.983687: step: 2112/529, loss: 0.04438743740320206
2023-01-23 02:32:32.073298: step: 2116/529, loss: 0.0005743026849813759
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.5784114052953157, 'r': 0.7563249001331558, 'f1': 0.6555106751298327}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6442486085343229, 'r': 0.7838600451467269, 'f1': 0.7072301425661915}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5977011494252874, 'r': 0.9629629629629629, 'f1': 0.7375886524822696}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.5714285714285714, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
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': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 02:33:11.849813: step: 4/529, loss: 0.002998876851052046
2023-01-23 02:33:12.975097: step: 8/529, loss: 0.017006922513246536
2023-01-23 02:33:14.073711: step: 12/529, loss: 0.003844833467155695
2023-01-23 02:33:15.196285: step: 16/529, loss: 0.0018792152404785156
2023-01-23 02:33:16.340801: step: 20/529, loss: 0.031246567144989967
2023-01-23 02:33:17.453471: step: 24/529, loss: 0.009868621826171875
2023-01-23 02:33:18.550018: step: 28/529, loss: 0.009680366143584251
2023-01-23 02:33:19.719796: step: 32/529, loss: 0.03929562494158745
2023-01-23 02:33:20.827617: step: 36/529, loss: 0.00036087038461118937
2023-01-23 02:33:21.941697: step: 40/529, loss: 0.023014290258288383
2023-01-23 02:33:23.077313: step: 44/529, loss: 0.029668522998690605
2023-01-23 02:33:24.212955: step: 48/529, loss: 0.02438831329345703
2023-01-23 02:33:25.378202: step: 52/529, loss: 0.04918208345770836
2023-01-23 02:33:26.495005: step: 56/529, loss: 0.0012639046180993319
2023-01-23 02:33:27.579453: step: 60/529, loss: 0.003215980716049671
2023-01-23 02:33:28.669952: step: 64/529, loss: 0.001334381173364818
2023-01-23 02:33:29.780253: step: 68/529, loss: 0.03056182898581028
2023-01-23 02:33:30.886827: step: 72/529, loss: 0.030424689874053
2023-01-23 02:33:32.009892: step: 76/529, loss: 5.264282663119957e-05
2023-01-23 02:33:33.130385: step: 80/529, loss: 0.005367946811020374
2023-01-23 02:33:34.240826: step: 84/529, loss: 0.001497554825618863
2023-01-23 02:33:35.352275: step: 88/529, loss: 0.04599914699792862
2023-01-23 02:33:36.459521: step: 92/529, loss: 0.024938583374023438
2023-01-23 02:33:37.565151: step: 96/529, loss: 0.02764587476849556
2023-01-23 02:33:38.715227: step: 100/529, loss: 0.004647445864975452
2023-01-23 02:33:39.835716: step: 104/529, loss: 0.04710127040743828
2023-01-23 02:33:40.967056: step: 108/529, loss: 0.00010104477405548096
2023-01-23 02:33:42.078911: step: 112/529, loss: 0.007490253541618586
2023-01-23 02:33:43.173226: step: 116/529, loss: 0.06377296149730682
2023-01-23 02:33:44.276618: step: 120/529, loss: 0.0008453368791379035
2023-01-23 02:33:45.342671: step: 124/529, loss: 0.00010070800635730848
2023-01-23 02:33:46.480574: step: 128/529, loss: 0.03658290207386017
2023-01-23 02:33:47.602809: step: 132/529, loss: 0.07246951758861542
2023-01-23 02:33:48.729223: step: 136/529, loss: 0.06288440525531769
2023-01-23 02:33:49.835237: step: 140/529, loss: 0.028320789337158203
2023-01-23 02:33:50.928700: step: 144/529, loss: 0.007649326231330633
2023-01-23 02:33:52.029370: step: 148/529, loss: 0.005911732092499733
2023-01-23 02:33:53.152162: step: 152/529, loss: 0.017657184973359108
2023-01-23 02:33:54.261133: step: 156/529, loss: 0.012812996283173561
2023-01-23 02:33:55.347937: step: 160/529, loss: 0.0008520126575604081
2023-01-23 02:33:56.467210: step: 164/529, loss: 0.007799720857292414
2023-01-23 02:33:57.600769: step: 168/529, loss: 0.7407258749008179
2023-01-23 02:33:58.703758: step: 172/529, loss: 0.0006013870588503778
2023-01-23 02:33:59.809861: step: 176/529, loss: 4.6253204345703125e-05
2023-01-23 02:34:00.914281: step: 180/529, loss: 0.00033855438232421875
2023-01-23 02:34:02.035504: step: 184/529, loss: 0.035860441625118256
2023-01-23 02:34:03.115847: step: 188/529, loss: 0.005360031500458717
2023-01-23 02:34:04.226378: step: 192/529, loss: 0.0020776509772986174
2023-01-23 02:34:05.326067: step: 196/529, loss: 0.008920478634536266
2023-01-23 02:34:06.418270: step: 200/529, loss: 0.00017471313185524195
2023-01-23 02:34:07.548706: step: 204/529, loss: 0.002953433897346258
2023-01-23 02:34:08.649955: step: 208/529, loss: 0.0018602609634399414
2023-01-23 02:34:09.731155: step: 212/529, loss: 0.022137831896543503
2023-01-23 02:34:10.850451: step: 216/529, loss: 0.059075355529785156
2023-01-23 02:34:11.949962: step: 220/529, loss: 0.0029333115089684725
2023-01-23 02:34:13.045985: step: 224/529, loss: 0.05030112341046333
2023-01-23 02:34:14.197608: step: 228/529, loss: 0.034888651221990585
2023-01-23 02:34:15.309549: step: 232/529, loss: 0.01607859879732132
2023-01-23 02:34:16.415479: step: 236/529, loss: 0.018686486408114433
2023-01-23 02:34:17.541466: step: 240/529, loss: 0.0004830360412597656
2023-01-23 02:34:18.647071: step: 244/529, loss: 0.7120140790939331
2023-01-23 02:34:19.755179: step: 248/529, loss: 0.011679649353027344
2023-01-23 02:34:20.893011: step: 252/529, loss: 0.00034103391226381063
2023-01-23 02:34:22.034736: step: 256/529, loss: 0.021803760901093483
2023-01-23 02:34:23.140493: step: 260/529, loss: 0.00021166801161598414
2023-01-23 02:34:24.239042: step: 264/529, loss: 0.0002639770391397178
2023-01-23 02:34:25.358636: step: 268/529, loss: 0.043738484382629395
2023-01-23 02:34:26.447518: step: 272/529, loss: 0.005989647004753351
2023-01-23 02:34:27.558067: step: 276/529, loss: 0.01483612135052681
2023-01-23 02:34:28.659802: step: 280/529, loss: 0.051297903060913086
2023-01-23 02:34:29.769093: step: 284/529, loss: 0.026013851165771484
2023-01-23 02:34:30.889414: step: 288/529, loss: 0.010733413510024548
2023-01-23 02:34:31.979313: step: 292/529, loss: 0.0016160011291503906
2023-01-23 02:34:33.091713: step: 296/529, loss: 0.00427665701135993
2023-01-23 02:34:34.188726: step: 300/529, loss: 0.0008289337274618447
2023-01-23 02:34:35.275621: step: 304/529, loss: 0.03157844394445419
2023-01-23 02:34:36.369977: step: 308/529, loss: 0.013669395819306374
2023-01-23 02:34:37.492526: step: 312/529, loss: 0.2017984390258789
2023-01-23 02:34:38.612019: step: 316/529, loss: 0.048645973205566406
2023-01-23 02:34:39.692220: step: 320/529, loss: 0.0008381843799725175
2023-01-23 02:34:40.814670: step: 324/529, loss: 0.0011798859341070056
2023-01-23 02:34:41.920515: step: 328/529, loss: 0.0009162903297692537
2023-01-23 02:34:43.025102: step: 332/529, loss: 0.2096746563911438
2023-01-23 02:34:44.125379: step: 336/529, loss: 5.1212311518611386e-05
2023-01-23 02:34:45.214310: step: 340/529, loss: -2.026558377110632e-06
2023-01-23 02:34:46.298628: step: 344/529, loss: 0.0006766319856978953
2023-01-23 02:34:47.396493: step: 348/529, loss: 0.05172481760382652
2023-01-23 02:34:48.509861: step: 352/529, loss: 0.00019484758377075195
2023-01-23 02:34:49.634112: step: 356/529, loss: 0.0008844852563925087
2023-01-23 02:34:50.728299: step: 360/529, loss: 0.039675142616033554
2023-01-23 02:34:51.829261: step: 364/529, loss: 0.003983497619628906
2023-01-23 02:34:52.927578: step: 368/529, loss: 0.003175782971084118
2023-01-23 02:34:54.056206: step: 372/529, loss: 0.03502597659826279
2023-01-23 02:34:55.169025: step: 376/529, loss: 0.0018219947814941406
2023-01-23 02:34:56.268832: step: 380/529, loss: 0.012453271076083183
2023-01-23 02:34:57.364715: step: 384/529, loss: 0.0008155822870321572
2023-01-23 02:34:58.464447: step: 388/529, loss: 0.0072119953110814095
2023-01-23 02:34:59.597128: step: 392/529, loss: 0.00017900466627907008
2023-01-23 02:35:00.721061: step: 396/529, loss: 0.0008088112226687372
2023-01-23 02:35:01.860757: step: 400/529, loss: 0.013781547546386719
2023-01-23 02:35:02.963083: step: 404/529, loss: 0.006226074881851673
2023-01-23 02:35:04.113724: step: 408/529, loss: 0.0018296241760253906
2023-01-23 02:35:05.227811: step: 412/529, loss: 0.0027431489434093237
2023-01-23 02:35:06.340902: step: 416/529, loss: 0.031016064807772636
2023-01-23 02:35:07.476190: step: 420/529, loss: 0.04904906824231148
2023-01-23 02:35:08.576759: step: 424/529, loss: 0.000911331211682409
2023-01-23 02:35:09.681504: step: 428/529, loss: 0.01816740073263645
2023-01-23 02:35:10.793747: step: 432/529, loss: 0.06186337396502495
2023-01-23 02:35:11.910801: step: 436/529, loss: 0.02241954766213894
2023-01-23 02:35:13.014657: step: 440/529, loss: 0.00855712965130806
2023-01-23 02:35:14.123366: step: 444/529, loss: 0.06964576244354248
2023-01-23 02:35:15.202787: step: 448/529, loss: 0.01756115071475506
2023-01-23 02:35:16.321885: step: 452/529, loss: 0.10006542503833771
2023-01-23 02:35:17.447857: step: 456/529, loss: 0.005373287480324507
2023-01-23 02:35:18.544600: step: 460/529, loss: 0.0046129231341183186
2023-01-23 02:35:19.656812: step: 464/529, loss: 0.18387280404567719
2023-01-23 02:35:20.769746: step: 468/529, loss: -8.01086389401462e-06
2023-01-23 02:35:21.905503: step: 472/529, loss: 0.0007985115516930819
2023-01-23 02:35:23.015173: step: 476/529, loss: 0.007560539525002241
2023-01-23 02:35:24.121832: step: 480/529, loss: 0.007399940397590399
2023-01-23 02:35:25.218998: step: 484/529, loss: 0.01924762688577175
2023-01-23 02:35:26.336739: step: 488/529, loss: 0.18841572105884552
2023-01-23 02:35:27.453100: step: 492/529, loss: 0.0055946349166333675
2023-01-23 02:35:28.541042: step: 496/529, loss: 0.004186153411865234
2023-01-23 02:35:29.629958: step: 500/529, loss: 0.004673385992646217
2023-01-23 02:35:30.738160: step: 504/529, loss: 0.0016197204822674394
2023-01-23 02:35:31.864029: step: 508/529, loss: 0.00099945068359375
2023-01-23 02:35:32.973582: step: 512/529, loss: 0.009970665909349918
2023-01-23 02:35:34.095654: step: 516/529, loss: 0.0025717734824866056
2023-01-23 02:35:35.177348: step: 520/529, loss: 0.001628828002139926
2023-01-23 02:35:36.282788: step: 524/529, loss: 0.04026193544268608
2023-01-23 02:35:37.393462: step: 528/529, loss: 0.024524927139282227
2023-01-23 02:35:38.489392: step: 532/529, loss: 0.059690192341804504
2023-01-23 02:35:39.590779: step: 536/529, loss: 0.004295348655432463
2023-01-23 02:35:40.675201: step: 540/529, loss: 0.0007504463428631425
2023-01-23 02:35:41.783901: step: 544/529, loss: 0.0011619568103924394
2023-01-23 02:35:42.902409: step: 548/529, loss: 0.002483653835952282
2023-01-23 02:35:43.983231: step: 552/529, loss: 0.016633223742246628
2023-01-23 02:35:45.116609: step: 556/529, loss: 0.007696914952248335
2023-01-23 02:35:46.252207: step: 560/529, loss: 0.01152792014181614
2023-01-23 02:35:47.334049: step: 564/529, loss: 0.0009445667965337634
2023-01-23 02:35:48.433033: step: 568/529, loss: 0.06436033546924591
2023-01-23 02:35:49.554531: step: 572/529, loss: 0.007954549975693226
2023-01-23 02:35:50.668707: step: 576/529, loss: 0.00019187928410246968
2023-01-23 02:35:51.768034: step: 580/529, loss: 0.0014989853370934725
2023-01-23 02:35:52.888863: step: 584/529, loss: 0.027545928955078125
2023-01-23 02:35:53.984138: step: 588/529, loss: 0.03548269718885422
2023-01-23 02:35:55.102273: step: 592/529, loss: 0.039650533348321915
2023-01-23 02:35:56.221465: step: 596/529, loss: 0.10010643303394318
2023-01-23 02:35:57.353261: step: 600/529, loss: 0.04125375673174858
2023-01-23 02:35:58.466032: step: 604/529, loss: 0.0014337539905682206
2023-01-23 02:35:59.555131: step: 608/529, loss: 0.0053543089888989925
2023-01-23 02:36:00.672804: step: 612/529, loss: 0.015803862363100052
2023-01-23 02:36:01.783079: step: 616/529, loss: 0.006803130730986595
2023-01-23 02:36:02.890494: step: 620/529, loss: 0.0362127311527729
2023-01-23 02:36:03.967428: step: 624/529, loss: 0.01996450498700142
2023-01-23 02:36:05.092800: step: 628/529, loss: 0.044396210461854935
2023-01-23 02:36:06.199592: step: 632/529, loss: 0.01491236686706543
2023-01-23 02:36:07.293866: step: 636/529, loss: 0.001185512519441545
2023-01-23 02:36:08.379974: step: 640/529, loss: 0.013698006048798561
2023-01-23 02:36:09.559228: step: 644/529, loss: 0.10506153106689453
2023-01-23 02:36:10.680199: step: 648/529, loss: 0.01607685163617134
2023-01-23 02:36:11.780762: step: 652/529, loss: 0.0027788160368800163
2023-01-23 02:36:12.918117: step: 656/529, loss: 0.00062475202139467
2023-01-23 02:36:14.022872: step: 660/529, loss: 0.00652580289170146
2023-01-23 02:36:15.142477: step: 664/529, loss: 0.09088211506605148
2023-01-23 02:36:16.241159: step: 668/529, loss: 0.051072120666503906
2023-01-23 02:36:17.344603: step: 672/529, loss: 0.009678077884018421
2023-01-23 02:36:18.439501: step: 676/529, loss: 0.39746949076652527
2023-01-23 02:36:19.555342: step: 680/529, loss: 0.006929969880729914
2023-01-23 02:36:20.665183: step: 684/529, loss: 0.0039031982887536287
2023-01-23 02:36:21.785377: step: 688/529, loss: 0.025171469897031784
2023-01-23 02:36:22.955937: step: 692/529, loss: 0.11790676414966583
2023-01-23 02:36:24.040592: step: 696/529, loss: 0.011981487274169922
2023-01-23 02:36:25.174185: step: 700/529, loss: 0.00302543630823493
2023-01-23 02:36:26.279295: step: 704/529, loss: 0.0005494594806805253
2023-01-23 02:36:27.399392: step: 708/529, loss: 0.0020995140075683594
2023-01-23 02:36:28.510138: step: 712/529, loss: 0.009449435397982597
2023-01-23 02:36:29.617542: step: 716/529, loss: 0.001592922257259488
2023-01-23 02:36:30.702368: step: 720/529, loss: 0.012718009762465954
2023-01-23 02:36:31.793071: step: 724/529, loss: 2.8133392333984375e-05
2023-01-23 02:36:32.920163: step: 728/529, loss: 0.003930950071662664
2023-01-23 02:36:34.048454: step: 732/529, loss: 0.03534838184714317
2023-01-23 02:36:35.165141: step: 736/529, loss: 0.009404946118593216
2023-01-23 02:36:36.281667: step: 740/529, loss: 0.029752518981695175
2023-01-23 02:36:37.405603: step: 744/529, loss: 0.0020939826499670744
2023-01-23 02:36:38.519255: step: 748/529, loss: 0.009065628051757812
2023-01-23 02:36:39.627464: step: 752/529, loss: 0.008211707696318626
2023-01-23 02:36:40.740135: step: 756/529, loss: 0.003811454866081476
2023-01-23 02:36:41.873540: step: 760/529, loss: 0.056560613214969635
2023-01-23 02:36:42.977702: step: 764/529, loss: 0.0009943009354174137
2023-01-23 02:36:44.113870: step: 768/529, loss: 0.014568901620805264
2023-01-23 02:36:45.266926: step: 772/529, loss: 0.009718704037368298
2023-01-23 02:36:46.407466: step: 776/529, loss: 0.002511978382244706
2023-01-23 02:36:47.523974: step: 780/529, loss: 0.0017391204601153731
2023-01-23 02:36:48.632605: step: 784/529, loss: 0.0023900987580418587
2023-01-23 02:36:49.742498: step: 788/529, loss: 0.062331557273864746
2023-01-23 02:36:50.878509: step: 792/529, loss: 0.007258367724716663
2023-01-23 02:36:52.001406: step: 796/529, loss: 0.005029201507568359
2023-01-23 02:36:53.128948: step: 800/529, loss: 0.025862693786621094
2023-01-23 02:36:54.259623: step: 804/529, loss: 0.006263923831284046
2023-01-23 02:36:55.383688: step: 808/529, loss: 0.009171104989945889
2023-01-23 02:36:56.516767: step: 812/529, loss: 0.02699914015829563
2023-01-23 02:36:57.605640: step: 816/529, loss: 0.010309792123734951
2023-01-23 02:36:58.708941: step: 820/529, loss: 0.0490327812731266
2023-01-23 02:36:59.803120: step: 824/529, loss: 0.004374122712761164
2023-01-23 02:37:00.927123: step: 828/529, loss: 0.0011720657348632812
2023-01-23 02:37:02.019598: step: 832/529, loss: 0.005498313810676336
2023-01-23 02:37:03.132219: step: 836/529, loss: 0.03520713001489639
2023-01-23 02:37:04.231931: step: 840/529, loss: 0.08220825344324112
2023-01-23 02:37:05.337734: step: 844/529, loss: 0.005397772882133722
2023-01-23 02:37:06.455381: step: 848/529, loss: 0.021099282428622246
2023-01-23 02:37:07.599794: step: 852/529, loss: 0.006635904312133789
2023-01-23 02:37:08.716069: step: 856/529, loss: 0.003965330310165882
2023-01-23 02:37:09.788301: step: 860/529, loss: 0.00016231538029387593
2023-01-23 02:37:10.955362: step: 864/529, loss: 0.01697998121380806
2023-01-23 02:37:12.070904: step: 868/529, loss: 0.005830002017319202
2023-01-23 02:37:13.184258: step: 872/529, loss: 0.006504678633064032
2023-01-23 02:37:14.292471: step: 876/529, loss: 0.015044712461531162
2023-01-23 02:37:15.392644: step: 880/529, loss: 0.024628639221191406
2023-01-23 02:37:16.519589: step: 884/529, loss: 0.02321024052798748
2023-01-23 02:37:17.618537: step: 888/529, loss: 0.05142345651984215
2023-01-23 02:37:18.746933: step: 892/529, loss: 0.015437603928148746
2023-01-23 02:37:19.863377: step: 896/529, loss: 0.4070507884025574
2023-01-23 02:37:20.978672: step: 900/529, loss: 0.005261897575110197
2023-01-23 02:37:22.118409: step: 904/529, loss: 0.09527730941772461
2023-01-23 02:37:23.266167: step: 908/529, loss: 0.06323669105768204
2023-01-23 02:37:24.383488: step: 912/529, loss: 0.01142120361328125
2023-01-23 02:37:25.488044: step: 916/529, loss: 0.00011005402484443039
2023-01-23 02:37:26.593422: step: 920/529, loss: 0.0073678018525242805
2023-01-23 02:37:27.693228: step: 924/529, loss: 0.008548641577363014
2023-01-23 02:37:28.830955: step: 928/529, loss: 0.06399421393871307
2023-01-23 02:37:29.929129: step: 932/529, loss: 0.0050106048583984375
2023-01-23 02:37:31.051784: step: 936/529, loss: 0.03731298819184303
2023-01-23 02:37:32.129809: step: 940/529, loss: 0.006247329525649548
2023-01-23 02:37:33.231961: step: 944/529, loss: 0.0015016555553302169
2023-01-23 02:37:34.333208: step: 948/529, loss: 0.06272812187671661
2023-01-23 02:37:35.433461: step: 952/529, loss: 0.014216327108442783
2023-01-23 02:37:36.537857: step: 956/529, loss: 0.0019206047290936112
2023-01-23 02:37:37.694810: step: 960/529, loss: 0.01927342638373375
2023-01-23 02:37:38.805687: step: 964/529, loss: 0.03705215826630592
2023-01-23 02:37:39.909439: step: 968/529, loss: 0.00043144228402525187
2023-01-23 02:37:40.996625: step: 972/529, loss: 0.013107729144394398
2023-01-23 02:37:42.126673: step: 976/529, loss: 0.0005803108215332031
2023-01-23 02:37:43.223812: step: 980/529, loss: 0.0036330223083496094
2023-01-23 02:37:44.354809: step: 984/529, loss: 0.04333171993494034
2023-01-23 02:37:45.457645: step: 988/529, loss: 0.0007926941034384072
2023-01-23 02:37:46.541820: step: 992/529, loss: 0.016463281586766243
2023-01-23 02:37:47.646293: step: 996/529, loss: 0.014256191439926624
2023-01-23 02:37:48.793552: step: 1000/529, loss: 0.018715476617217064
2023-01-23 02:37:49.918956: step: 1004/529, loss: 0.005838441662490368
2023-01-23 02:37:51.049375: step: 1008/529, loss: 0.02546234242618084
2023-01-23 02:37:52.183817: step: 1012/529, loss: 0.008594894781708717
2023-01-23 02:37:53.328689: step: 1016/529, loss: 0.003566741943359375
2023-01-23 02:37:54.462892: step: 1020/529, loss: 0.013203669339418411
2023-01-23 02:37:55.560398: step: 1024/529, loss: 0.00263557443395257
2023-01-23 02:37:56.671725: step: 1028/529, loss: 0.018791770562529564
2023-01-23 02:37:57.768782: step: 1032/529, loss: 0.009150695987045765
2023-01-23 02:37:58.889495: step: 1036/529, loss: 0.11048545688390732
2023-01-23 02:37:59.985328: step: 1040/529, loss: 0.005415535066276789
2023-01-23 02:38:01.092790: step: 1044/529, loss: 0.00793304480612278
2023-01-23 02:38:02.188662: step: 1048/529, loss: 0.00057134625967592
2023-01-23 02:38:03.284273: step: 1052/529, loss: 0.006138897035270929
2023-01-23 02:38:04.365142: step: 1056/529, loss: 0.00030097959097474813
2023-01-23 02:38:05.462645: step: 1060/529, loss: 0.0046217916533350945
2023-01-23 02:38:06.583747: step: 1064/529, loss: 9.164810762740672e-05
2023-01-23 02:38:07.699180: step: 1068/529, loss: 0.03677258640527725
2023-01-23 02:38:08.807348: step: 1072/529, loss: 6.246566772460938e-05
2023-01-23 02:38:09.920623: step: 1076/529, loss: 0.010938645340502262
2023-01-23 02:38:11.035161: step: 1080/529, loss: 0.0027471540961414576
2023-01-23 02:38:12.161497: step: 1084/529, loss: 0.10885143280029297
2023-01-23 02:38:13.287008: step: 1088/529, loss: 0.051083944737911224
2023-01-23 02:38:14.391970: step: 1092/529, loss: 0.008761787787079811
2023-01-23 02:38:15.505921: step: 1096/529, loss: 0.013092994689941406
2023-01-23 02:38:16.598893: step: 1100/529, loss: 0.011665535159409046
2023-01-23 02:38:17.701087: step: 1104/529, loss: 0.007028103340417147
2023-01-23 02:38:18.833688: step: 1108/529, loss: 0.04167022928595543
2023-01-23 02:38:19.912209: step: 1112/529, loss: 0.0443972572684288
2023-01-23 02:38:21.033772: step: 1116/529, loss: 2.002716064453125e-05
2023-01-23 02:38:22.152130: step: 1120/529, loss: 0.03889331966638565
2023-01-23 02:38:23.243521: step: 1124/529, loss: 0.03410196304321289
2023-01-23 02:38:24.342110: step: 1128/529, loss: 0.006856727413833141
2023-01-23 02:38:25.449329: step: 1132/529, loss: 0.004176878836005926
2023-01-23 02:38:26.567082: step: 1136/529, loss: 0.010348701849579811
2023-01-23 02:38:27.683540: step: 1140/529, loss: 0.0006244659889489412
2023-01-23 02:38:28.797396: step: 1144/529, loss: 0.00046367646427825093
2023-01-23 02:38:29.878862: step: 1148/529, loss: 0.0033706664107739925
2023-01-23 02:38:31.008728: step: 1152/529, loss: 0.1157769188284874
2023-01-23 02:38:32.124807: step: 1156/529, loss: 0.002324152272194624
2023-01-23 02:38:33.230185: step: 1160/529, loss: 0.06894226372241974
2023-01-23 02:38:34.336652: step: 1164/529, loss: 0.00021476746769621968
2023-01-23 02:38:35.431055: step: 1168/529, loss: 0.028710652142763138
2023-01-23 02:38:36.583349: step: 1172/529, loss: 3.633499363786541e-05
2023-01-23 02:38:37.681317: step: 1176/529, loss: 0.006111431401222944
2023-01-23 02:38:38.778250: step: 1180/529, loss: 0.0037243845872581005
2023-01-23 02:38:39.917800: step: 1184/529, loss: 0.002398157026618719
2023-01-23 02:38:41.029575: step: 1188/529, loss: 0.0007041931385174394
2023-01-23 02:38:42.099458: step: 1192/529, loss: 0.007344198413193226
2023-01-23 02:38:43.239184: step: 1196/529, loss: 0.05882740020751953
2023-01-23 02:38:44.320686: step: 1200/529, loss: 0.0030315399635583162
2023-01-23 02:38:45.440569: step: 1204/529, loss: 0.0015590668190270662
2023-01-23 02:38:46.522943: step: 1208/529, loss: 0.015018177218735218
2023-01-23 02:38:47.631296: step: 1212/529, loss: 0.02497711218893528
2023-01-23 02:38:48.763935: step: 1216/529, loss: 0.001429700874723494
2023-01-23 02:38:49.886098: step: 1220/529, loss: 0.2614055573940277
2023-01-23 02:38:50.978262: step: 1224/529, loss: 0.04572753980755806
2023-01-23 02:38:52.074025: step: 1228/529, loss: 0.08436601608991623
2023-01-23 02:38:53.216793: step: 1232/529, loss: 0.00014324189396575093
2023-01-23 02:38:54.349247: step: 1236/529, loss: 0.022670842707157135
2023-01-23 02:38:55.452163: step: 1240/529, loss: 0.016945458948612213
2023-01-23 02:38:56.523626: step: 1244/529, loss: 0.014529895968735218
2023-01-23 02:38:57.636246: step: 1248/529, loss: 0.010189247317612171
2023-01-23 02:38:58.729662: step: 1252/529, loss: 0.0005743026849813759
2023-01-23 02:38:59.802584: step: 1256/529, loss: 0.0006975174183025956
2023-01-23 02:39:00.909965: step: 1260/529, loss: 0.024681951850652695
2023-01-23 02:39:01.999864: step: 1264/529, loss: 0.060361672192811966
2023-01-23 02:39:03.100274: step: 1268/529, loss: 0.024263381958007812
2023-01-23 02:39:04.200149: step: 1272/529, loss: 0.007101631257683039
2023-01-23 02:39:05.315601: step: 1276/529, loss: 0.006656646728515625
2023-01-23 02:39:06.433799: step: 1280/529, loss: 0.06424445658922195
2023-01-23 02:39:07.549556: step: 1284/529, loss: 6.828308687545359e-05
2023-01-23 02:39:08.683071: step: 1288/529, loss: 0.03032694011926651
2023-01-23 02:39:09.786913: step: 1292/529, loss: 0.0008079528925009072
2023-01-23 02:39:10.887269: step: 1296/529, loss: 0.0007113456958904862
2023-01-23 02:39:12.013899: step: 1300/529, loss: 0.0009732246398925781
2023-01-23 02:39:13.149689: step: 1304/529, loss: 0.010020256042480469
2023-01-23 02:39:14.214506: step: 1308/529, loss: 0.006526088807731867
2023-01-23 02:39:15.343603: step: 1312/529, loss: 0.008561898022890091
2023-01-23 02:39:16.469381: step: 1316/529, loss: 0.005761242005974054
2023-01-23 02:39:17.612235: step: 1320/529, loss: 0.00023384093947242945
2023-01-23 02:39:18.715818: step: 1324/529, loss: 0.00028743743314407766
2023-01-23 02:39:19.813926: step: 1328/529, loss: 0.00019149782019667327
2023-01-23 02:39:20.912677: step: 1332/529, loss: 0.030652904883027077
2023-01-23 02:39:22.021484: step: 1336/529, loss: 0.018249893561005592
2023-01-23 02:39:23.150070: step: 1340/529, loss: 0.011918735690414906
2023-01-23 02:39:24.259895: step: 1344/529, loss: 0.017681121826171875
2023-01-23 02:39:25.369792: step: 1348/529, loss: 0.0380517952144146
2023-01-23 02:39:26.457627: step: 1352/529, loss: 0.0001126289353123866
2023-01-23 02:39:27.556405: step: 1356/529, loss: 0.044347286224365234
2023-01-23 02:39:28.659330: step: 1360/529, loss: 0.03411588817834854
2023-01-23 02:39:29.783071: step: 1364/529, loss: 0.022443199530243874
2023-01-23 02:39:30.908687: step: 1368/529, loss: 0.10914954543113708
2023-01-23 02:39:32.052928: step: 1372/529, loss: 0.8595108389854431
2023-01-23 02:39:33.156128: step: 1376/529, loss: 0.11565246433019638
2023-01-23 02:39:34.269187: step: 1380/529, loss: 0.0047623636201024055
2023-01-23 02:39:35.394980: step: 1384/529, loss: 0.03679618611931801
2023-01-23 02:39:36.517371: step: 1388/529, loss: 0.0006746292347088456
2023-01-23 02:39:37.624801: step: 1392/529, loss: 0.03144397586584091
2023-01-23 02:39:38.730807: step: 1396/529, loss: 0.0007534027099609375
2023-01-23 02:39:39.831219: step: 1400/529, loss: 0.008688926696777344
2023-01-23 02:39:40.942579: step: 1404/529, loss: 0.014102840796113014
2023-01-23 02:39:42.058170: step: 1408/529, loss: 0.06872701644897461
2023-01-23 02:39:43.169692: step: 1412/529, loss: 0.008532905951142311
2023-01-23 02:39:44.285897: step: 1416/529, loss: 0.12858524918556213
2023-01-23 02:39:45.382228: step: 1420/529, loss: 0.001873624394647777
2023-01-23 02:39:46.495480: step: 1424/529, loss: 0.0013468742836266756
2023-01-23 02:39:47.604882: step: 1428/529, loss: 0.013448620215058327
2023-01-23 02:39:48.730531: step: 1432/529, loss: 0.0015245438553392887
2023-01-23 02:39:49.837022: step: 1436/529, loss: 0.0005301475175656378
2023-01-23 02:39:50.957007: step: 1440/529, loss: 0.010562896728515625
2023-01-23 02:39:52.076187: step: 1444/529, loss: 0.03284778818488121
2023-01-23 02:39:53.199695: step: 1448/529, loss: 0.029086114838719368
2023-01-23 02:39:54.307244: step: 1452/529, loss: 0.048919677734375
2023-01-23 02:39:55.410946: step: 1456/529, loss: 0.004399681463837624
2023-01-23 02:39:56.496458: step: 1460/529, loss: 0.01125488243997097
2023-01-23 02:39:57.582110: step: 1464/529, loss: 0.0551794059574604
2023-01-23 02:39:58.713857: step: 1468/529, loss: 0.015229607000946999
2023-01-23 02:39:59.813144: step: 1472/529, loss: 0.18658971786499023
2023-01-23 02:40:00.931398: step: 1476/529, loss: 0.04222278669476509
2023-01-23 02:40:02.035626: step: 1480/529, loss: 0.027546502649784088
2023-01-23 02:40:03.151727: step: 1484/529, loss: 0.0049821375869214535
2023-01-23 02:40:04.288148: step: 1488/529, loss: 0.0003444671747274697
2023-01-23 02:40:05.423541: step: 1492/529, loss: 0.0006232261657714844
2023-01-23 02:40:06.536605: step: 1496/529, loss: 0.013267231173813343
2023-01-23 02:40:07.645159: step: 1500/529, loss: 0.00242443080060184
2023-01-23 02:40:08.741515: step: 1504/529, loss: 0.00020465851412154734
2023-01-23 02:40:09.844747: step: 1508/529, loss: 0.0023739340249449015
2023-01-23 02:40:10.963338: step: 1512/529, loss: 0.0065437317825853825
2023-01-23 02:40:12.060775: step: 1516/529, loss: 0.011449528858065605
2023-01-23 02:40:13.145072: step: 1520/529, loss: 0.0242049228399992
2023-01-23 02:40:14.246370: step: 1524/529, loss: 0.018066883087158203
2023-01-23 02:40:15.367866: step: 1528/529, loss: 0.02419414557516575
2023-01-23 02:40:16.468477: step: 1532/529, loss: 0.014324760064482689
2023-01-23 02:40:17.589841: step: 1536/529, loss: 0.011695289984345436
2023-01-23 02:40:18.701983: step: 1540/529, loss: 0.006884956732392311
2023-01-23 02:40:19.829147: step: 1544/529, loss: 0.09910842031240463
2023-01-23 02:40:20.966375: step: 1548/529, loss: 0.0006841659778729081
2023-01-23 02:40:22.186503: step: 1552/529, loss: 0.03175327181816101
2023-01-23 02:40:23.319789: step: 1556/529, loss: 0.037883758544921875
2023-01-23 02:40:24.456304: step: 1560/529, loss: 0.13884659111499786
2023-01-23 02:40:25.561653: step: 1564/529, loss: 0.001976394560188055
2023-01-23 02:40:26.676045: step: 1568/529, loss: 0.00010504722740733996
2023-01-23 02:40:27.782789: step: 1572/529, loss: 0.019742773845791817
2023-01-23 02:40:28.893473: step: 1576/529, loss: 0.008479118347167969
2023-01-23 02:40:29.993999: step: 1580/529, loss: 0.15628795325756073
2023-01-23 02:40:31.154429: step: 1584/529, loss: 0.11336851119995117
2023-01-23 02:40:32.260940: step: 1588/529, loss: 0.0001903533993754536
2023-01-23 02:40:33.364007: step: 1592/529, loss: 0.03635072708129883
2023-01-23 02:40:34.469480: step: 1596/529, loss: 0.006968498229980469
2023-01-23 02:40:35.569526: step: 1600/529, loss: 0.03251037746667862
2023-01-23 02:40:36.679482: step: 1604/529, loss: 0.22056026756763458
2023-01-23 02:40:37.795763: step: 1608/529, loss: 0.013068771921098232
2023-01-23 02:40:38.911833: step: 1612/529, loss: 0.07117576897144318
2023-01-23 02:40:40.008174: step: 1616/529, loss: 0.016994666308164597
2023-01-23 02:40:41.104552: step: 1620/529, loss: 0.07627410441637039
2023-01-23 02:40:42.210619: step: 1624/529, loss: 0.0030422210693359375
2023-01-23 02:40:43.333042: step: 1628/529, loss: 0.020182132720947266
2023-01-23 02:40:44.453147: step: 1632/529, loss: 0.015240669250488281
2023-01-23 02:40:45.550418: step: 1636/529, loss: 0.004169655032455921
2023-01-23 02:40:46.674813: step: 1640/529, loss: 0.004290199372917414
2023-01-23 02:40:47.791204: step: 1644/529, loss: 0.0020856857299804688
2023-01-23 02:40:48.902897: step: 1648/529, loss: 0.0017930985195562243
2023-01-23 02:40:50.045430: step: 1652/529, loss: 0.05909614637494087
2023-01-23 02:40:51.156405: step: 1656/529, loss: 4.997253563487902e-05
2023-01-23 02:40:52.301205: step: 1660/529, loss: 0.002527427626773715
2023-01-23 02:40:53.408582: step: 1664/529, loss: 0.004800987429916859
2023-01-23 02:40:54.544102: step: 1668/529, loss: 0.01271915528923273
2023-01-23 02:40:55.670013: step: 1672/529, loss: 0.0016716003883630037
2023-01-23 02:40:56.796377: step: 1676/529, loss: 0.003542328020557761
2023-01-23 02:40:57.919019: step: 1680/529, loss: 0.006430245004594326
2023-01-23 02:40:59.043245: step: 1684/529, loss: 0.5775493383407593
2023-01-23 02:41:00.172548: step: 1688/529, loss: 0.009461593814194202
2023-01-23 02:41:01.287424: step: 1692/529, loss: 0.1243845522403717
2023-01-23 02:41:02.386832: step: 1696/529, loss: 0.020012855529785156
2023-01-23 02:41:03.468740: step: 1700/529, loss: 0.0006521225441247225
2023-01-23 02:41:04.595928: step: 1704/529, loss: 0.0007424354553222656
2023-01-23 02:41:05.700317: step: 1708/529, loss: 0.00028476715669967234
2023-01-23 02:41:06.794146: step: 1712/529, loss: 0.0010662078857421875
2023-01-23 02:41:07.908211: step: 1716/529, loss: 0.13426867127418518
2023-01-23 02:41:09.016434: step: 1720/529, loss: 1.6117095583467744e-05
2023-01-23 02:41:10.135803: step: 1724/529, loss: 0.016417598351836205
2023-01-23 02:41:11.250296: step: 1728/529, loss: 0.012674522586166859
2023-01-23 02:41:12.359072: step: 1732/529, loss: 0.1762961447238922
2023-01-23 02:41:13.440766: step: 1736/529, loss: 0.056645773351192474
2023-01-23 02:41:14.567615: step: 1740/529, loss: 0.01091537531465292
2023-01-23 02:41:15.670528: step: 1744/529, loss: 0.0075928689911961555
2023-01-23 02:41:16.775047: step: 1748/529, loss: 0.08950477838516235
2023-01-23 02:41:17.881081: step: 1752/529, loss: 0.04054737091064453
2023-01-23 02:41:18.961793: step: 1756/529, loss: 0.005307960789650679
2023-01-23 02:41:20.094161: step: 1760/529, loss: 0.0028938292525708675
2023-01-23 02:41:21.182528: step: 1764/529, loss: 0.024899005889892578
2023-01-23 02:41:22.285228: step: 1768/529, loss: 0.02730732038617134
2023-01-23 02:41:23.367954: step: 1772/529, loss: 0.0139128677546978
2023-01-23 02:41:24.479935: step: 1776/529, loss: 0.021582795307040215
2023-01-23 02:41:25.621412: step: 1780/529, loss: 0.020476914942264557
2023-01-23 02:41:26.730295: step: 1784/529, loss: 0.00108509068377316
2023-01-23 02:41:27.837062: step: 1788/529, loss: 0.05165863037109375
2023-01-23 02:41:28.959451: step: 1792/529, loss: 0.03100724332034588
2023-01-23 02:41:30.041164: step: 1796/529, loss: 0.002113723661750555
2023-01-23 02:41:31.153712: step: 1800/529, loss: 0.017702486366033554
2023-01-23 02:41:32.300159: step: 1804/529, loss: 0.04667053371667862
2023-01-23 02:41:33.402877: step: 1808/529, loss: 0.009372711181640625
2023-01-23 02:41:34.535319: step: 1812/529, loss: 0.002443504286929965
2023-01-23 02:41:35.710396: step: 1816/529, loss: 0.001627588295377791
2023-01-23 02:41:36.858319: step: 1820/529, loss: 0.010867882519960403
2023-01-23 02:41:37.962513: step: 1824/529, loss: 0.0048233033157885075
2023-01-23 02:41:39.105757: step: 1828/529, loss: 0.03398914262652397
2023-01-23 02:41:40.232812: step: 1832/529, loss: 0.0035132409539073706
2023-01-23 02:41:41.356335: step: 1836/529, loss: 2.593994213384576e-05
2023-01-23 02:41:42.452500: step: 1840/529, loss: 0.012753963470458984
2023-01-23 02:41:43.563382: step: 1844/529, loss: 0.0012276172637939453
2023-01-23 02:41:44.683125: step: 1848/529, loss: 0.0008684158092364669
2023-01-23 02:41:45.802466: step: 1852/529, loss: 0.0020522119011729956
2023-01-23 02:41:46.928740: step: 1856/529, loss: 0.0026235580444335938
2023-01-23 02:41:48.031853: step: 1860/529, loss: 0.0723545104265213
2023-01-23 02:41:49.169112: step: 1864/529, loss: 0.000373649614630267
2023-01-23 02:41:50.252232: step: 1868/529, loss: 0.0012364387512207031
2023-01-23 02:41:51.367814: step: 1872/529, loss: 0.0015027045737951994
2023-01-23 02:41:52.491385: step: 1876/529, loss: 0.07378172874450684
2023-01-23 02:41:53.575856: step: 1880/529, loss: 0.0022869110107421875
2023-01-23 02:41:54.703353: step: 1884/529, loss: 0.008147239685058594
2023-01-23 02:41:55.811065: step: 1888/529, loss: 0.009593391790986061
2023-01-23 02:41:56.919667: step: 1892/529, loss: 0.014007187448441982
2023-01-23 02:41:58.033385: step: 1896/529, loss: 0.01309671439230442
2023-01-23 02:41:59.157266: step: 1900/529, loss: 0.05403494834899902
2023-01-23 02:42:00.247132: step: 1904/529, loss: 0.015779972076416016
2023-01-23 02:42:01.347823: step: 1908/529, loss: 0.004146766848862171
2023-01-23 02:42:02.424218: step: 1912/529, loss: 2.0599363779183477e-05
2023-01-23 02:42:03.522265: step: 1916/529, loss: 0.010004043579101562
2023-01-23 02:42:04.619626: step: 1920/529, loss: 0.00024127960205078125
2023-01-23 02:42:05.721531: step: 1924/529, loss: 0.008876895532011986
2023-01-23 02:42:06.818886: step: 1928/529, loss: 0.042061615735292435
2023-01-23 02:42:07.933666: step: 1932/529, loss: 0.0005893707275390625
2023-01-23 02:42:09.064333: step: 1936/529, loss: 0.007040500640869141
2023-01-23 02:42:10.160113: step: 1940/529, loss: 0.0038908959832042456
2023-01-23 02:42:11.258630: step: 1944/529, loss: 0.002587700029835105
2023-01-23 02:42:12.342220: step: 1948/529, loss: 0.04027128219604492
2023-01-23 02:42:13.444840: step: 1952/529, loss: 0.6564247608184814
2023-01-23 02:42:14.537088: step: 1956/529, loss: 0.0012781142722815275
2023-01-23 02:42:15.626504: step: 1960/529, loss: 0.0016482830978929996
2023-01-23 02:42:16.725262: step: 1964/529, loss: 0.0017163276206701994
2023-01-23 02:42:17.836971: step: 1968/529, loss: 0.025080585852265358
2023-01-23 02:42:18.951688: step: 1972/529, loss: 0.0020043374970555305
2023-01-23 02:42:20.092014: step: 1976/529, loss: 0.002396488096565008
2023-01-23 02:42:21.214796: step: 1980/529, loss: 0.030241012573242188
2023-01-23 02:42:22.321614: step: 1984/529, loss: 0.0022886276710778475
2023-01-23 02:42:23.443072: step: 1988/529, loss: 0.02503395266830921
2023-01-23 02:42:24.572526: step: 1992/529, loss: 0.010606956668198109
2023-01-23 02:42:25.674627: step: 1996/529, loss: 0.006884432397782803
2023-01-23 02:42:26.810286: step: 2000/529, loss: 0.001625823904760182
2023-01-23 02:42:27.909862: step: 2004/529, loss: 0.053549814969301224
2023-01-23 02:42:29.031881: step: 2008/529, loss: 0.5644946098327637
2023-01-23 02:42:30.173217: step: 2012/529, loss: 0.05977001041173935
2023-01-23 02:42:31.286340: step: 2016/529, loss: 0.014062881469726562
2023-01-23 02:42:32.370550: step: 2020/529, loss: 0.16801948845386505
2023-01-23 02:42:33.467948: step: 2024/529, loss: 0.0013593673938885331
2023-01-23 02:42:34.567334: step: 2028/529, loss: 0.0016456603771075606
2023-01-23 02:42:35.681424: step: 2032/529, loss: 0.0001735687255859375
2023-01-23 02:42:36.788332: step: 2036/529, loss: 0.28335294127464294
2023-01-23 02:42:37.878163: step: 2040/529, loss: 0.0058845519088208675
2023-01-23 02:42:39.000130: step: 2044/529, loss: 0.04492301866412163
2023-01-23 02:42:40.111450: step: 2048/529, loss: 0.030686378479003906
2023-01-23 02:42:41.232948: step: 2052/529, loss: 0.034900762140750885
2023-01-23 02:42:42.311684: step: 2056/529, loss: 0.013790893368422985
2023-01-23 02:42:43.439041: step: 2060/529, loss: 0.0001466751127736643
2023-01-23 02:42:44.549879: step: 2064/529, loss: 0.0045375823974609375
2023-01-23 02:42:45.650785: step: 2068/529, loss: 0.06097235903143883
2023-01-23 02:42:46.805042: step: 2072/529, loss: 0.044893838465213776
2023-01-23 02:42:47.908911: step: 2076/529, loss: 0.005265617277473211
2023-01-23 02:42:49.012993: step: 2080/529, loss: 0.046027567237615585
2023-01-23 02:42:50.114107: step: 2084/529, loss: 0.002574348356574774
2023-01-23 02:42:51.201082: step: 2088/529, loss: 0.028423458337783813
2023-01-23 02:42:52.310935: step: 2092/529, loss: 0.012430763803422451
2023-01-23 02:42:53.418690: step: 2096/529, loss: 0.015805387869477272
2023-01-23 02:42:54.531637: step: 2100/529, loss: 0.0267868060618639
2023-01-23 02:42:55.631121: step: 2104/529, loss: 0.04761314392089844
2023-01-23 02:42:56.735937: step: 2108/529, loss: 0.0019538879860192537
2023-01-23 02:42:57.827632: step: 2112/529, loss: 0.0946991965174675
2023-01-23 02:42:58.924459: step: 2116/529, loss: 0.009499598294496536
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.5637583892617449, 'r': 0.7829560585885486, 'f1': 0.6555183946488293}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6213251426064064, 'r': 0.7990970654627539, 'f1': 0.6990866452727721}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5416666666666666, 'r': 0.9629629629629629, 'f1': 0.6933333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.5806451612903226, 'r': 0.5714285714285714, 'f1': 0.576}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.5555555555555556, 'f1': 0.49382716049382713}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 19
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:43:39.102870: step: 4/529, loss: 0.014355468563735485
2023-01-23 02:43:40.209163: step: 8/529, loss: 0.0006323337438516319
2023-01-23 02:43:41.299383: step: 12/529, loss: 0.0033627511002123356
2023-01-23 02:43:42.400781: step: 16/529, loss: 0.000671434449031949
2023-01-23 02:43:43.492057: step: 20/529, loss: 0.017496107146143913
2023-01-23 02:43:44.612129: step: 24/529, loss: 0.010253524407744408
2023-01-23 02:43:45.721934: step: 28/529, loss: 0.0040130615234375
2023-01-23 02:43:46.815738: step: 32/529, loss: 0.04756765440106392
2023-01-23 02:43:47.949671: step: 36/529, loss: 0.0031833648681640625
2023-01-23 02:43:49.057020: step: 40/529, loss: 0.0004937172052450478
2023-01-23 02:43:50.178723: step: 44/529, loss: 0.024747466668486595
2023-01-23 02:43:51.305882: step: 48/529, loss: 0.0034503936767578125
2023-01-23 02:43:52.401234: step: 52/529, loss: 0.21310386061668396
2023-01-23 02:43:53.521333: step: 56/529, loss: 0.016933441162109375
2023-01-23 02:43:54.624839: step: 60/529, loss: 0.28695639967918396
2023-01-23 02:43:55.716854: step: 64/529, loss: 0.0012784004211425781
2023-01-23 02:43:56.832118: step: 68/529, loss: 0.02222595177590847
2023-01-23 02:43:57.951014: step: 72/529, loss: 6.380081322276965e-05
2023-01-23 02:43:59.017851: step: 76/529, loss: 0.01010971050709486
2023-01-23 02:44:00.151148: step: 80/529, loss: 0.0035266876220703125
2023-01-23 02:44:01.269108: step: 84/529, loss: 0.004527282901108265
2023-01-23 02:44:02.367237: step: 88/529, loss: 0.013827419839799404
2023-01-23 02:44:03.498085: step: 92/529, loss: 0.02768847905099392
2023-01-23 02:44:04.605028: step: 96/529, loss: 0.04118843004107475
2023-01-23 02:44:05.717976: step: 100/529, loss: 0.0007052421569824219
2023-01-23 02:44:06.821997: step: 104/529, loss: 0.03379478678107262
2023-01-23 02:44:07.923488: step: 108/529, loss: 0.0008284568903036416
2023-01-23 02:44:09.019955: step: 112/529, loss: 4.711151268566027e-05
2023-01-23 02:44:10.127539: step: 116/529, loss: 0.002983665792271495
2023-01-23 02:44:11.219127: step: 120/529, loss: 0.012008953839540482
2023-01-23 02:44:12.328431: step: 124/529, loss: 0.0012169122928753495
2023-01-23 02:44:13.430216: step: 128/529, loss: 0.00524826068431139
2023-01-23 02:44:14.516759: step: 132/529, loss: 0.04662275314331055
2023-01-23 02:44:15.612399: step: 136/529, loss: 0.004094064235687256
2023-01-23 02:44:16.713997: step: 140/529, loss: 0.0022203444968909025
2023-01-23 02:44:17.843563: step: 144/529, loss: 0.004037189297378063
2023-01-23 02:44:18.946207: step: 148/529, loss: 0.004108428955078125
2023-01-23 02:44:20.083243: step: 152/529, loss: 0.009538555517792702
2023-01-23 02:44:21.214415: step: 156/529, loss: 0.0075501445680856705
2023-01-23 02:44:22.280624: step: 160/529, loss: 0.0029109478928148746
2023-01-23 02:44:23.373437: step: 164/529, loss: 0.051416970789432526
2023-01-23 02:44:24.520559: step: 168/529, loss: 0.000705718994140625
2023-01-23 02:44:25.656046: step: 172/529, loss: 0.00024313927860930562
2023-01-23 02:44:26.806685: step: 176/529, loss: 0.002595901722088456
2023-01-23 02:44:27.930151: step: 180/529, loss: 0.002785822842270136
2023-01-23 02:44:29.034015: step: 184/529, loss: 0.0002342224179301411
2023-01-23 02:44:30.146845: step: 188/529, loss: 0.021434593945741653
2023-01-23 02:44:31.244389: step: 192/529, loss: 0.0009616852039471269
2023-01-23 02:44:32.387690: step: 196/529, loss: 0.04459095001220703
2023-01-23 02:44:33.493599: step: 200/529, loss: 0.014522934332489967
2023-01-23 02:44:34.634971: step: 204/529, loss: 0.03135986253619194
2023-01-23 02:44:35.735563: step: 208/529, loss: 0.03364114463329315
2023-01-23 02:44:36.856370: step: 212/529, loss: 0.00024359226517844945
2023-01-23 02:44:37.961569: step: 216/529, loss: 0.03321495279669762
2023-01-23 02:44:39.059200: step: 220/529, loss: 0.001216888427734375
2023-01-23 02:44:40.152671: step: 224/529, loss: 0.004745102021843195
2023-01-23 02:44:41.269634: step: 228/529, loss: 0.019183922559022903
2023-01-23 02:44:42.367794: step: 232/529, loss: 0.006996536161750555
2023-01-23 02:44:43.502681: step: 236/529, loss: 0.0012030602665618062
2023-01-23 02:44:44.592234: step: 240/529, loss: 0.007956123910844326
2023-01-23 02:44:45.693106: step: 244/529, loss: 0.00935440044850111
2023-01-23 02:44:46.835075: step: 248/529, loss: 0.05777540057897568
2023-01-23 02:44:47.940257: step: 252/529, loss: 0.0004600524844136089
2023-01-23 02:44:49.047399: step: 256/529, loss: 0.012191391550004482
2023-01-23 02:44:50.180529: step: 260/529, loss: 0.0032075883354991674
2023-01-23 02:44:51.286957: step: 264/529, loss: 0.0007696151733398438
2023-01-23 02:44:52.391616: step: 268/529, loss: 0.24476762115955353
2023-01-23 02:44:53.507241: step: 272/529, loss: 0.01579446718096733
2023-01-23 02:44:54.615040: step: 276/529, loss: 0.00043735504732467234
2023-01-23 02:44:55.727629: step: 280/529, loss: 0.000748109829146415
2023-01-23 02:44:56.857573: step: 284/529, loss: 0.0019321441650390625
2023-01-23 02:44:57.984370: step: 288/529, loss: 0.0882728099822998
2023-01-23 02:44:59.072517: step: 292/529, loss: 0.010863685980439186
2023-01-23 02:45:00.190500: step: 296/529, loss: 0.0010265350574627519
2023-01-23 02:45:01.327877: step: 300/529, loss: 0.0011432648170739412
2023-01-23 02:45:02.417232: step: 304/529, loss: 0.0004352569521870464
2023-01-23 02:45:03.511417: step: 308/529, loss: 0.001831150148063898
2023-01-23 02:45:04.630137: step: 312/529, loss: 0.6326780319213867
2023-01-23 02:45:05.722712: step: 316/529, loss: 0.0367220900952816
2023-01-23 02:45:06.821068: step: 320/529, loss: 0.018698502331972122
2023-01-23 02:45:07.901499: step: 324/529, loss: 0.009912515059113503
2023-01-23 02:45:08.998465: step: 328/529, loss: 0.046420954167842865
2023-01-23 02:45:10.063567: step: 332/529, loss: 0.05252427980303764
2023-01-23 02:45:11.192525: step: 336/529, loss: 0.008003043942153454
2023-01-23 02:45:12.303531: step: 340/529, loss: 0.0013790130615234375
2023-01-23 02:45:13.408586: step: 344/529, loss: 0.0034000396262854338
2023-01-23 02:45:14.521687: step: 348/529, loss: 9.694099571788684e-05
2023-01-23 02:45:15.642459: step: 352/529, loss: 0.007418155670166016
2023-01-23 02:45:16.761459: step: 356/529, loss: 0.0044692992232739925
2023-01-23 02:45:17.859351: step: 360/529, loss: 0.0019312858348712325
2023-01-23 02:45:18.993361: step: 364/529, loss: 0.0312647819519043
2023-01-23 02:45:20.105429: step: 368/529, loss: 0.0022410391829907894
2023-01-23 02:45:21.199050: step: 372/529, loss: 0.0030117034912109375
2023-01-23 02:45:22.343920: step: 376/529, loss: 0.000590419746004045
2023-01-23 02:45:23.444607: step: 380/529, loss: 0.039423368871212006
2023-01-23 02:45:24.546620: step: 384/529, loss: 0.00378589634783566
2023-01-23 02:45:25.664469: step: 388/529, loss: 0.02882976643741131
2023-01-23 02:45:26.781129: step: 392/529, loss: 0.010480308905243874
2023-01-23 02:45:27.865540: step: 396/529, loss: 0.009607887826859951
2023-01-23 02:45:28.916995: step: 400/529, loss: 0.012318229302763939
2023-01-23 02:45:30.028156: step: 404/529, loss: 0.0019186973804607987
2023-01-23 02:45:31.144766: step: 408/529, loss: 0.013365937396883965
2023-01-23 02:45:32.269178: step: 412/529, loss: 0.04006042331457138
2023-01-23 02:45:33.376184: step: 416/529, loss: 0.005264186765998602
2023-01-23 02:45:34.459300: step: 420/529, loss: 0.0007431865087710321
2023-01-23 02:45:35.560869: step: 424/529, loss: 0.0017409325810149312
2023-01-23 02:45:36.648306: step: 428/529, loss: 0.020402144640684128
2023-01-23 02:45:37.782193: step: 432/529, loss: 0.0006545067299157381
2023-01-23 02:45:38.870766: step: 436/529, loss: 0.00023484230041503906
2023-01-23 02:45:39.961817: step: 440/529, loss: 0.0034800528082996607
2023-01-23 02:45:41.047507: step: 444/529, loss: 0.01729297637939453
2023-01-23 02:45:42.168574: step: 448/529, loss: 0.25457268953323364
2023-01-23 02:45:43.286705: step: 452/529, loss: 0.01759650744497776
2023-01-23 02:45:44.445411: step: 456/529, loss: 0.0005899429088458419
2023-01-23 02:45:45.587189: step: 460/529, loss: 0.03666868060827255
2023-01-23 02:45:46.700331: step: 464/529, loss: 0.06310119479894638
2023-01-23 02:45:47.815647: step: 468/529, loss: 0.09546433389186859
2023-01-23 02:45:48.907363: step: 472/529, loss: 0.038512710481882095
2023-01-23 02:45:50.011585: step: 476/529, loss: 0.022290658205747604
2023-01-23 02:45:51.100061: step: 480/529, loss: 0.03739328309893608
2023-01-23 02:45:52.190956: step: 484/529, loss: 2.193451337006991e-06
2023-01-23 02:45:53.282678: step: 488/529, loss: 0.028816889971494675
2023-01-23 02:45:54.373791: step: 492/529, loss: 0.001351213431917131
2023-01-23 02:45:55.454283: step: 496/529, loss: 0.005806589499115944
2023-01-23 02:45:56.552396: step: 500/529, loss: 0.00861969031393528
2023-01-23 02:45:57.650176: step: 504/529, loss: 0.028588009998202324
2023-01-23 02:45:58.757518: step: 508/529, loss: 0.0270233154296875
2023-01-23 02:45:59.877660: step: 512/529, loss: 0.0028108598198741674
2023-01-23 02:46:01.066219: step: 516/529, loss: 0.00611114501953125
2023-01-23 02:46:02.205358: step: 520/529, loss: 0.02396526373922825
2023-01-23 02:46:03.331938: step: 524/529, loss: 0.015333366580307484
2023-01-23 02:46:04.410714: step: 528/529, loss: 0.0013791085220873356
2023-01-23 02:46:05.502823: step: 532/529, loss: 0.0027270319405943155
2023-01-23 02:46:06.606068: step: 536/529, loss: 0.020116616040468216
2023-01-23 02:46:07.693063: step: 540/529, loss: 0.0017522812122479081
2023-01-23 02:46:08.832266: step: 544/529, loss: 0.11413393169641495
2023-01-23 02:46:09.948693: step: 548/529, loss: 0.0027193070854991674
2023-01-23 02:46:11.045650: step: 552/529, loss: 0.002698803087696433
2023-01-23 02:46:12.145755: step: 556/529, loss: 0.05554747208952904
2023-01-23 02:46:13.252109: step: 560/529, loss: 0.0005871772882528603
2023-01-23 02:46:14.416832: step: 564/529, loss: 0.039246559143066406
2023-01-23 02:46:15.513233: step: 568/529, loss: 1.4781951904296875e-05
2023-01-23 02:46:16.600264: step: 572/529, loss: 6.0749058320652694e-05
2023-01-23 02:46:17.715613: step: 576/529, loss: 0.00945911556482315
2023-01-23 02:46:18.788075: step: 580/529, loss: 1.8119812921213452e-06
2023-01-23 02:46:19.894802: step: 584/529, loss: 0.0006213188171386719
2023-01-23 02:46:21.007493: step: 588/529, loss: 0.04135427623987198
2023-01-23 02:46:22.119466: step: 592/529, loss: 0.0008311271667480469
2023-01-23 02:46:23.221996: step: 596/529, loss: 0.0040066721849143505
2023-01-23 02:46:24.318307: step: 600/529, loss: 0.0004817962762899697
2023-01-23 02:46:25.455428: step: 604/529, loss: 0.007086372934281826
2023-01-23 02:46:26.533376: step: 608/529, loss: 0.0003685951232910156
2023-01-23 02:46:27.637825: step: 612/529, loss: 0.2023063600063324
2023-01-23 02:46:28.765849: step: 616/529, loss: 0.0038887024857103825
2023-01-23 02:46:29.898872: step: 620/529, loss: 0.014190674759447575
2023-01-23 02:46:30.997207: step: 624/529, loss: 0.0025453567504882812
2023-01-23 02:46:32.119380: step: 628/529, loss: 0.00730133056640625
2023-01-23 02:46:33.222079: step: 632/529, loss: 0.004276657477021217
2023-01-23 02:46:34.319652: step: 636/529, loss: 0.04006042331457138
2023-01-23 02:46:35.429059: step: 640/529, loss: 2.021789623540826e-05
2023-01-23 02:46:36.522782: step: 644/529, loss: 0.08157215267419815
2023-01-23 02:46:37.620182: step: 648/529, loss: 0.0002880096435546875
2023-01-23 02:46:38.768600: step: 652/529, loss: 0.014393031597137451
2023-01-23 02:46:39.898581: step: 656/529, loss: 0.007098769769072533
2023-01-23 02:46:40.995935: step: 660/529, loss: 0.0006195545429363847
2023-01-23 02:46:42.104265: step: 664/529, loss: 0.012794685550034046
2023-01-23 02:46:43.218812: step: 668/529, loss: 5.569458153331652e-05
2023-01-23 02:46:44.354183: step: 672/529, loss: 0.06984329223632812
2023-01-23 02:46:45.452059: step: 676/529, loss: 0.002380180172622204
2023-01-23 02:46:46.567761: step: 680/529, loss: 0.0007987499702721834
2023-01-23 02:46:47.696730: step: 684/529, loss: 0.16498775780200958
2023-01-23 02:46:48.822269: step: 688/529, loss: 0.03566398844122887
2023-01-23 02:46:49.921403: step: 692/529, loss: 0.0005817413912154734
2023-01-23 02:46:51.036598: step: 696/529, loss: 0.0017530441982671618
2023-01-23 02:46:52.159575: step: 700/529, loss: 0.010729407891631126
2023-01-23 02:46:53.283712: step: 704/529, loss: 0.016094589605927467
2023-01-23 02:46:54.390559: step: 708/529, loss: 0.4038047790527344
2023-01-23 02:46:55.517101: step: 712/529, loss: 0.001567077706567943
2023-01-23 02:46:56.645227: step: 716/529, loss: 0.005270099733024836
2023-01-23 02:46:57.764674: step: 720/529, loss: 0.0032434463500976562
2023-01-23 02:46:58.846808: step: 724/529, loss: 0.022444821894168854
2023-01-23 02:46:59.969663: step: 728/529, loss: 0.0007795333513058722
2023-01-23 02:47:01.099919: step: 732/529, loss: 0.00010957718041026965
2023-01-23 02:47:02.205442: step: 736/529, loss: 0.006377029232680798
2023-01-23 02:47:03.345739: step: 740/529, loss: 0.05097942426800728
2023-01-23 02:47:04.444203: step: 744/529, loss: 0.044149018824100494
2023-01-23 02:47:05.580344: step: 748/529, loss: 0.042908765375614166
2023-01-23 02:47:06.664465: step: 752/529, loss: 0.005693626590073109
2023-01-23 02:47:07.760970: step: 756/529, loss: 0.005429267883300781
2023-01-23 02:47:08.856852: step: 760/529, loss: 0.01851024106144905
2023-01-23 02:47:09.959975: step: 764/529, loss: 0.0230986587703228
2023-01-23 02:47:11.060712: step: 768/529, loss: 0.016632651910185814
2023-01-23 02:47:12.171370: step: 772/529, loss: 0.00023937225341796875
2023-01-23 02:47:13.286692: step: 776/529, loss: 0.02695140801370144
2023-01-23 02:47:14.404230: step: 780/529, loss: 0.008199882693588734
2023-01-23 02:47:15.530260: step: 784/529, loss: 0.013084793463349342
2023-01-23 02:47:16.656137: step: 788/529, loss: 0.019443130120635033
2023-01-23 02:47:17.789651: step: 792/529, loss: 0.0005764007801190019
2023-01-23 02:47:18.897130: step: 796/529, loss: 0.025236893445253372
2023-01-23 02:47:19.994452: step: 800/529, loss: 0.004144476726651192
2023-01-23 02:47:21.097454: step: 804/529, loss: 0.03200054168701172
2023-01-23 02:47:22.198283: step: 808/529, loss: 0.00026149750920012593
2023-01-23 02:47:23.303144: step: 812/529, loss: 0.013726524077355862
2023-01-23 02:47:24.416419: step: 816/529, loss: 0.014700889587402344
2023-01-23 02:47:25.516482: step: 820/529, loss: 0.05683021992444992
2023-01-23 02:47:26.606778: step: 824/529, loss: 0.03358612209558487
2023-01-23 02:47:27.738067: step: 828/529, loss: 0.016904450953006744
2023-01-23 02:47:28.858246: step: 832/529, loss: 0.02762165106832981
2023-01-23 02:47:29.974250: step: 836/529, loss: 0.0017857551574707031
2023-01-23 02:47:31.081818: step: 840/529, loss: 0.010833931155502796
2023-01-23 02:47:32.180434: step: 844/529, loss: 0.0014444352127611637
2023-01-23 02:47:33.284714: step: 848/529, loss: 0.027597809210419655
2023-01-23 02:47:34.431648: step: 852/529, loss: 0.05364866554737091
2023-01-23 02:47:35.546957: step: 856/529, loss: 0.002945518586784601
2023-01-23 02:47:36.655543: step: 860/529, loss: 0.008834457956254482
2023-01-23 02:47:37.792421: step: 864/529, loss: 0.00010619164095260203
2023-01-23 02:47:38.882835: step: 868/529, loss: 0.008788681589066982
2023-01-23 02:47:40.006357: step: 872/529, loss: 0.014927864074707031
2023-01-23 02:47:41.097125: step: 876/529, loss: 0.003241920378059149
2023-01-23 02:47:42.190248: step: 880/529, loss: 0.0011375427711755037
2023-01-23 02:47:43.305077: step: 884/529, loss: 0.06047344207763672
2023-01-23 02:47:44.426137: step: 888/529, loss: 0.02774982526898384
2023-01-23 02:47:45.562358: step: 892/529, loss: 0.00427322369068861
2023-01-23 02:47:46.654815: step: 896/529, loss: 0.004375743679702282
2023-01-23 02:47:47.734770: step: 900/529, loss: 0.0007824897766113281
2023-01-23 02:47:48.850564: step: 904/529, loss: 0.00011625289334915578
2023-01-23 02:47:49.965319: step: 908/529, loss: 0.031965069472789764
2023-01-23 02:47:51.103903: step: 912/529, loss: 0.019513322040438652
2023-01-23 02:47:52.220507: step: 916/529, loss: 0.012214088812470436
2023-01-23 02:47:53.350893: step: 920/529, loss: 0.04048614948987961
2023-01-23 02:47:54.452082: step: 924/529, loss: 0.00038022996159270406
2023-01-23 02:47:55.573220: step: 928/529, loss: 0.003941345028579235
2023-01-23 02:47:56.689884: step: 932/529, loss: 7.476807513739914e-05
2023-01-23 02:47:57.813431: step: 936/529, loss: 0.0008944034343585372
2023-01-23 02:47:58.979462: step: 940/529, loss: 0.0842016190290451
2023-01-23 02:48:00.092927: step: 944/529, loss: 0.02452554740011692
2023-01-23 02:48:01.203509: step: 948/529, loss: 0.035330578684806824
2023-01-23 02:48:02.310972: step: 952/529, loss: 0.003975686617195606
2023-01-23 02:48:03.428659: step: 956/529, loss: 0.00010614395432639867
2023-01-23 02:48:04.530229: step: 960/529, loss: 0.01897735707461834
2023-01-23 02:48:05.684689: step: 964/529, loss: 0.005387497134506702
2023-01-23 02:48:06.798394: step: 968/529, loss: 0.040128327906131744
2023-01-23 02:48:07.903364: step: 972/529, loss: 0.07488436996936798
2023-01-23 02:48:09.047197: step: 976/529, loss: 0.08108091354370117
2023-01-23 02:48:10.166144: step: 980/529, loss: 0.03888225555419922
2023-01-23 02:48:11.262680: step: 984/529, loss: 0.024538803845643997
2023-01-23 02:48:12.362704: step: 988/529, loss: 0.004850483033806086
2023-01-23 02:48:13.453095: step: 992/529, loss: 0.0006504058837890625
2023-01-23 02:48:14.572726: step: 996/529, loss: 0.0026613236404955387
2023-01-23 02:48:15.694663: step: 1000/529, loss: 9.908677020575851e-05
2023-01-23 02:48:16.794618: step: 1004/529, loss: 0.006530189886689186
2023-01-23 02:48:17.904418: step: 1008/529, loss: 0.001556015107780695
2023-01-23 02:48:19.018536: step: 1012/529, loss: 0.006156063172966242
2023-01-23 02:48:20.121341: step: 1016/529, loss: 0.013196755200624466
2023-01-23 02:48:21.236471: step: 1020/529, loss: 0.00469474820420146
2023-01-23 02:48:22.295051: step: 1024/529, loss: 0.009793663397431374
2023-01-23 02:48:23.391495: step: 1028/529, loss: 0.03442397341132164
2023-01-23 02:48:24.514338: step: 1032/529, loss: 0.004127549938857555
2023-01-23 02:48:25.601953: step: 1036/529, loss: 0.017177294939756393
2023-01-23 02:48:26.720945: step: 1040/529, loss: 0.0050782207399606705
2023-01-23 02:48:27.819722: step: 1044/529, loss: 0.0014782905345782638
2023-01-23 02:48:28.951826: step: 1048/529, loss: 0.003768539521843195
2023-01-23 02:48:30.066190: step: 1052/529, loss: 0.6389240026473999
2023-01-23 02:48:31.163456: step: 1056/529, loss: 0.001468658447265625
2023-01-23 02:48:32.259489: step: 1060/529, loss: 0.00111303327139467
2023-01-23 02:48:33.376900: step: 1064/529, loss: 0.24889594316482544
2023-01-23 02:48:34.476966: step: 1068/529, loss: 0.002685165498405695
2023-01-23 02:48:35.562402: step: 1072/529, loss: 0.0006547927623614669
2023-01-23 02:48:36.675017: step: 1076/529, loss: 0.00028820039005950093
2023-01-23 02:48:37.785641: step: 1080/529, loss: 0.04075603559613228
2023-01-23 02:48:38.881244: step: 1084/529, loss: 0.07119331508874893
2023-01-23 02:48:39.994765: step: 1088/529, loss: 0.01147375162690878
2023-01-23 02:48:41.126630: step: 1092/529, loss: 0.19418220221996307
2023-01-23 02:48:42.258078: step: 1096/529, loss: 0.007575607392936945
2023-01-23 02:48:43.381621: step: 1100/529, loss: 0.049197006970644
2023-01-23 02:48:44.512582: step: 1104/529, loss: 0.00016412735567428172
2023-01-23 02:48:45.616478: step: 1108/529, loss: 0.0010312080848962069
2023-01-23 02:48:46.730635: step: 1112/529, loss: 0.014920998364686966
2023-01-23 02:48:47.834817: step: 1116/529, loss: 0.007286357693374157
2023-01-23 02:48:48.959975: step: 1120/529, loss: 0.002814102452248335
2023-01-23 02:48:50.053940: step: 1124/529, loss: 0.0026006698608398438
2023-01-23 02:48:51.154835: step: 1128/529, loss: 0.021419048309326172
2023-01-23 02:48:52.266453: step: 1132/529, loss: 0.05027348920702934
2023-01-23 02:48:53.374578: step: 1136/529, loss: 0.048186734318733215
2023-01-23 02:48:54.485027: step: 1140/529, loss: 0.003751134965568781
2023-01-23 02:48:55.577791: step: 1144/529, loss: 0.0060787200927734375
2023-01-23 02:48:56.698491: step: 1148/529, loss: 0.03135070949792862
2023-01-23 02:48:57.837066: step: 1152/529, loss: 0.023996246978640556
2023-01-23 02:48:58.948712: step: 1156/529, loss: 0.004766654688864946
2023-01-23 02:49:00.085377: step: 1160/529, loss: 0.002567768096923828
2023-01-23 02:49:01.206913: step: 1164/529, loss: 0.00115032191388309
2023-01-23 02:49:02.353679: step: 1168/529, loss: 0.0008221626630984247
2023-01-23 02:49:03.453043: step: 1172/529, loss: 0.0032484056428074837
2023-01-23 02:49:04.548934: step: 1176/529, loss: 0.010023307986557484
2023-01-23 02:49:05.647450: step: 1180/529, loss: 0.22237291932106018
2023-01-23 02:49:06.751317: step: 1184/529, loss: 0.0008107662433758378
2023-01-23 02:49:07.857597: step: 1188/529, loss: 0.003206253284588456
2023-01-23 02:49:08.948360: step: 1192/529, loss: 0.00039157868013717234
2023-01-23 02:49:10.055191: step: 1196/529, loss: 0.002326059387996793
2023-01-23 02:49:11.148596: step: 1200/529, loss: 8.869171142578125e-05
2023-01-23 02:49:12.286524: step: 1204/529, loss: 0.00040845872717909515
2023-01-23 02:49:13.399824: step: 1208/529, loss: 0.013240433298051357
2023-01-23 02:49:14.509736: step: 1212/529, loss: 0.02336854860186577
2023-01-23 02:49:15.619676: step: 1216/529, loss: 0.016819000244140625
2023-01-23 02:49:16.766415: step: 1220/529, loss: 0.0018589496612548828
2023-01-23 02:49:17.885804: step: 1224/529, loss: 0.2546026110649109
2023-01-23 02:49:18.994100: step: 1228/529, loss: 0.014909124001860619
2023-01-23 02:49:20.088417: step: 1232/529, loss: 0.005594539921730757
2023-01-23 02:49:21.245414: step: 1236/529, loss: 0.0008432388422079384
2023-01-23 02:49:22.346725: step: 1240/529, loss: 0.019699478521943092
2023-01-23 02:49:23.468595: step: 1244/529, loss: 0.0480710007250309
2023-01-23 02:49:24.558502: step: 1248/529, loss: 0.027770565822720528
2023-01-23 02:49:25.644910: step: 1252/529, loss: 0.005346587393432856
2023-01-23 02:49:26.761051: step: 1256/529, loss: 0.005622673314064741
2023-01-23 02:49:27.903330: step: 1260/529, loss: 0.03550710901618004
2023-01-23 02:49:29.018165: step: 1264/529, loss: 0.00888280849903822
2023-01-23 02:49:30.143076: step: 1268/529, loss: 0.016545962542295456
2023-01-23 02:49:31.274657: step: 1272/529, loss: 0.1267203390598297
2023-01-23 02:49:32.376030: step: 1276/529, loss: 0.002758884336799383
2023-01-23 02:49:33.437037: step: 1280/529, loss: 0.0006591796991415322
2023-01-23 02:49:34.568447: step: 1284/529, loss: 0.07975693047046661
2023-01-23 02:49:35.690477: step: 1288/529, loss: 0.009151888079941273
2023-01-23 02:49:36.802421: step: 1292/529, loss: 0.00054168701171875
2023-01-23 02:49:37.910549: step: 1296/529, loss: 0.014697838574647903
2023-01-23 02:49:38.980430: step: 1300/529, loss: 0.00033702849759720266
2023-01-23 02:49:40.092465: step: 1304/529, loss: 0.008200549520552158
2023-01-23 02:49:41.188647: step: 1308/529, loss: 0.0017564772861078382
2023-01-23 02:49:42.306078: step: 1312/529, loss: 0.009581851772964
2023-01-23 02:49:43.429708: step: 1316/529, loss: 0.0881785899400711
2023-01-23 02:49:44.514199: step: 1320/529, loss: 0.001798439072445035
2023-01-23 02:49:45.600960: step: 1324/529, loss: 0.0024221420753747225
2023-01-23 02:49:46.711233: step: 1328/529, loss: 0.37553003430366516
2023-01-23 02:49:47.817433: step: 1332/529, loss: 0.008842849172651768
2023-01-23 02:49:48.919974: step: 1336/529, loss: 0.009419179521501064
2023-01-23 02:49:49.996953: step: 1340/529, loss: 0.06424083560705185
2023-01-23 02:49:51.094939: step: 1344/529, loss: 0.0006669044378213584
2023-01-23 02:49:52.204145: step: 1348/529, loss: 0.010067272931337357
2023-01-23 02:49:53.331201: step: 1352/529, loss: 0.024624444544315338
2023-01-23 02:49:54.420947: step: 1356/529, loss: 0.00037059784517623484
2023-01-23 02:49:55.485581: step: 1360/529, loss: 0.01033774670213461
2023-01-23 02:49:56.587595: step: 1364/529, loss: 0.06833630055189133
2023-01-23 02:49:57.684929: step: 1368/529, loss: 0.003238201141357422
2023-01-23 02:49:58.767601: step: 1372/529, loss: 0.002369022462517023
2023-01-23 02:49:59.886026: step: 1376/529, loss: 0.12176161259412766
2023-01-23 02:50:01.038333: step: 1380/529, loss: 0.000920248101465404
2023-01-23 02:50:02.157322: step: 1384/529, loss: 0.0020751953125
2023-01-23 02:50:03.307658: step: 1388/529, loss: 0.0157470703125
2023-01-23 02:50:04.445173: step: 1392/529, loss: 0.0021440505515784025
2023-01-23 02:50:05.554165: step: 1396/529, loss: 0.024956895038485527
2023-01-23 02:50:06.675755: step: 1400/529, loss: 0.007620644755661488
2023-01-23 02:50:07.755897: step: 1404/529, loss: 0.037957288324832916
2023-01-23 02:50:08.840092: step: 1408/529, loss: 0.03819417953491211
2023-01-23 02:50:09.977095: step: 1412/529, loss: 0.028168868273496628
2023-01-23 02:50:11.066930: step: 1416/529, loss: 0.3601018786430359
2023-01-23 02:50:12.153907: step: 1420/529, loss: 0.01972637139260769
2023-01-23 02:50:13.264769: step: 1424/529, loss: 0.0028842927422374487
2023-01-23 02:50:14.404279: step: 1428/529, loss: 0.0618322379887104
2023-01-23 02:50:15.527967: step: 1432/529, loss: 7.629387255292386e-07
2023-01-23 02:50:16.659410: step: 1436/529, loss: 0.08798065036535263
2023-01-23 02:50:17.763306: step: 1440/529, loss: 0.00034427642822265625
2023-01-23 02:50:18.896783: step: 1444/529, loss: 0.00987997092306614
2023-01-23 02:50:20.029078: step: 1448/529, loss: 0.0006999970064498484
2023-01-23 02:50:21.131056: step: 1452/529, loss: 0.010639239102602005
2023-01-23 02:50:22.248083: step: 1456/529, loss: 0.021783066913485527
2023-01-23 02:50:23.346057: step: 1460/529, loss: 0.0015151978004723787
2023-01-23 02:50:24.478215: step: 1464/529, loss: 0.07769856601953506
2023-01-23 02:50:25.584661: step: 1468/529, loss: 0.0008311271667480469
2023-01-23 02:50:26.705467: step: 1472/529, loss: 0.0011723518837243319
2023-01-23 02:50:27.822042: step: 1476/529, loss: 0.0002541542053222656
2023-01-23 02:50:28.934728: step: 1480/529, loss: 0.0057230000384151936
2023-01-23 02:50:30.031731: step: 1484/529, loss: 0.02397918701171875
2023-01-23 02:50:31.159600: step: 1488/529, loss: 0.034673500806093216
2023-01-23 02:50:32.278929: step: 1492/529, loss: 0.2048366516828537
2023-01-23 02:50:33.390264: step: 1496/529, loss: 0.0008666992071084678
2023-01-23 02:50:34.523014: step: 1500/529, loss: 0.031070329248905182
2023-01-23 02:50:35.650998: step: 1504/529, loss: 0.0027331113815307617
2023-01-23 02:50:36.781000: step: 1508/529, loss: 0.013514221645891666
2023-01-23 02:50:37.902351: step: 1512/529, loss: 0.01528463326394558
2023-01-23 02:50:38.991792: step: 1516/529, loss: 0.005129528231918812
2023-01-23 02:50:40.094258: step: 1520/529, loss: 7.848739915061742e-05
2023-01-23 02:50:41.207467: step: 1524/529, loss: 0.0653371810913086
2023-01-23 02:50:42.315906: step: 1528/529, loss: 5.1689145038835704e-05
2023-01-23 02:50:43.455053: step: 1532/529, loss: 0.0012197494506835938
2023-01-23 02:50:44.554542: step: 1536/529, loss: 0.0005622863536700606
2023-01-23 02:50:45.681854: step: 1540/529, loss: 0.011204147711396217
2023-01-23 02:50:46.836530: step: 1544/529, loss: 0.008355235680937767
2023-01-23 02:50:47.936757: step: 1548/529, loss: 0.050809670239686966
2023-01-23 02:50:49.054823: step: 1552/529, loss: 0.023400498554110527
2023-01-23 02:50:50.164526: step: 1556/529, loss: 0.007494163233786821
2023-01-23 02:50:51.294443: step: 1560/529, loss: 0.03584270551800728
2023-01-23 02:50:52.402341: step: 1564/529, loss: 0.0004709243949037045
2023-01-23 02:50:53.499741: step: 1568/529, loss: 0.10162229835987091
2023-01-23 02:50:54.613187: step: 1572/529, loss: 0.005187034606933594
2023-01-23 02:50:55.717683: step: 1576/529, loss: 0.0015937327407300472
2023-01-23 02:50:56.836317: step: 1580/529, loss: 0.0359896644949913
2023-01-23 02:50:57.978622: step: 1584/529, loss: 0.06848374009132385
2023-01-23 02:50:59.066306: step: 1588/529, loss: 0.014183426275849342
2023-01-23 02:51:00.221408: step: 1592/529, loss: 0.0007497787592001259
2023-01-23 02:51:01.314122: step: 1596/529, loss: 0.04402303695678711
2023-01-23 02:51:02.402941: step: 1600/529, loss: 0.09942970424890518
2023-01-23 02:51:03.547049: step: 1604/529, loss: 0.012021827511489391
2023-01-23 02:51:04.651793: step: 1608/529, loss: 0.000706577324308455
2023-01-23 02:51:05.751061: step: 1612/529, loss: 0.0056008342653512955
2023-01-23 02:51:06.855715: step: 1616/529, loss: 0.0052515375427901745
2023-01-23 02:51:07.962133: step: 1620/529, loss: 0.0035362245980650187
2023-01-23 02:51:09.057447: step: 1624/529, loss: 0.00013875961303710938
2023-01-23 02:51:10.182194: step: 1628/529, loss: 0.01101598795503378
2023-01-23 02:51:11.300472: step: 1632/529, loss: 0.004846763331443071
2023-01-23 02:51:12.420340: step: 1636/529, loss: 0.0014327527023851871
2023-01-23 02:51:13.517220: step: 1640/529, loss: 0.004573249723762274
2023-01-23 02:51:14.624092: step: 1644/529, loss: 0.011237716302275658
2023-01-23 02:51:15.715115: step: 1648/529, loss: 0.01625981368124485
2023-01-23 02:51:16.817016: step: 1652/529, loss: 0.004238605499267578
2023-01-23 02:51:17.926764: step: 1656/529, loss: 0.02864856831729412
2023-01-23 02:51:19.018960: step: 1660/529, loss: 0.17483024299144745
2023-01-23 02:51:20.160420: step: 1664/529, loss: 0.6686692237854004
2023-01-23 02:51:21.260709: step: 1668/529, loss: 0.06777181476354599
2023-01-23 02:51:22.365068: step: 1672/529, loss: 0.04550151899456978
2023-01-23 02:51:23.450742: step: 1676/529, loss: 0.0031262398697435856
2023-01-23 02:51:24.549462: step: 1680/529, loss: 0.013519239611923695
2023-01-23 02:51:25.673252: step: 1684/529, loss: 0.0050182342529296875
2023-01-23 02:51:26.788713: step: 1688/529, loss: 0.028247740119695663
2023-01-23 02:51:27.902791: step: 1692/529, loss: 0.00013875961303710938
2023-01-23 02:51:29.002227: step: 1696/529, loss: 0.022792436182498932
2023-01-23 02:51:30.125152: step: 1700/529, loss: 0.003612041473388672
2023-01-23 02:51:31.240801: step: 1704/529, loss: 0.0006196022150106728
2023-01-23 02:51:32.354353: step: 1708/529, loss: 0.01440343912690878
2023-01-23 02:51:33.472313: step: 1712/529, loss: 0.03115013986825943
2023-01-23 02:51:34.595704: step: 1716/529, loss: 0.024906540289521217
2023-01-23 02:51:35.703902: step: 1720/529, loss: 0.028415298089385033
2023-01-23 02:51:36.806374: step: 1724/529, loss: 0.018455125391483307
2023-01-23 02:51:37.872173: step: 1728/529, loss: 8.039474778342992e-05
2023-01-23 02:51:39.015425: step: 1732/529, loss: 0.023265648633241653
2023-01-23 02:51:40.129157: step: 1736/529, loss: 0.014386728405952454
2023-01-23 02:51:41.230464: step: 1740/529, loss: 0.008734608069062233
2023-01-23 02:51:42.338748: step: 1744/529, loss: 0.017172623425722122
2023-01-23 02:51:43.483677: step: 1748/529, loss: 0.00036087038461118937
2023-01-23 02:51:44.592901: step: 1752/529, loss: 0.028025055304169655
2023-01-23 02:51:45.696525: step: 1756/529, loss: 0.068903349339962
2023-01-23 02:51:46.812359: step: 1760/529, loss: 0.07005921006202698
2023-01-23 02:51:47.909312: step: 1764/529, loss: 0.0003143310605082661
2023-01-23 02:51:49.034841: step: 1768/529, loss: 0.00530853308737278
2023-01-23 02:51:50.128388: step: 1772/529, loss: 0.0020563125144690275
2023-01-23 02:51:51.241962: step: 1776/529, loss: 0.00047931671724654734
2023-01-23 02:51:52.357946: step: 1780/529, loss: 0.00572280865162611
2023-01-23 02:51:53.469557: step: 1784/529, loss: 0.0036665915977209806
2023-01-23 02:51:54.565850: step: 1788/529, loss: 0.024647904559969902
2023-01-23 02:51:55.694641: step: 1792/529, loss: 0.15339794754981995
2023-01-23 02:51:56.809190: step: 1796/529, loss: 0.0010932922596111894
2023-01-23 02:51:57.943719: step: 1800/529, loss: 0.00855483952909708
2023-01-23 02:51:59.033893: step: 1804/529, loss: 0.045563891530036926
2023-01-23 02:52:00.159983: step: 1808/529, loss: 0.0002680778852663934
2023-01-23 02:52:01.333657: step: 1812/529, loss: 0.01278610248118639
2023-01-23 02:52:02.433499: step: 1816/529, loss: 0.09324774891138077
2023-01-23 02:52:03.531506: step: 1820/529, loss: 4.158019874012098e-05
2023-01-23 02:52:04.625892: step: 1824/529, loss: 0.0025367499329149723
2023-01-23 02:52:05.730064: step: 1828/529, loss: 0.0010714053642004728
2023-01-23 02:52:06.850221: step: 1832/529, loss: 0.08440761268138885
2023-01-23 02:52:07.989747: step: 1836/529, loss: 0.009079933166503906
2023-01-23 02:52:09.112152: step: 1840/529, loss: 0.004768466576933861
2023-01-23 02:52:10.226837: step: 1844/529, loss: 0.000629425048828125
2023-01-23 02:52:11.309057: step: 1848/529, loss: 0.056734468787908554
2023-01-23 02:52:12.396109: step: 1852/529, loss: 0.000171661376953125
2023-01-23 02:52:13.513712: step: 1856/529, loss: 0.015237808227539062
2023-01-23 02:52:14.625603: step: 1860/529, loss: 0.08406729251146317
2023-01-23 02:52:15.754127: step: 1864/529, loss: 0.012540149502456188
2023-01-23 02:52:16.894940: step: 1868/529, loss: 0.0014110564952716231
2023-01-23 02:52:18.013524: step: 1872/529, loss: 0.0038299560546875
2023-01-23 02:52:19.132931: step: 1876/529, loss: 0.0012363434070721269
2023-01-23 02:52:20.278593: step: 1880/529, loss: 0.004500627517700195
2023-01-23 02:52:21.382561: step: 1884/529, loss: 0.02730264887213707
2023-01-23 02:52:22.494632: step: 1888/529, loss: 0.0019573213066905737
2023-01-23 02:52:23.606899: step: 1892/529, loss: 0.0054178242571651936
2023-01-23 02:52:24.731845: step: 1896/529, loss: 0.00030956268892623484
2023-01-23 02:52:25.857146: step: 1900/529, loss: 0.00115966796875
2023-01-23 02:52:26.988057: step: 1904/529, loss: 0.014822816476225853
2023-01-23 02:52:28.110075: step: 1908/529, loss: 0.020738791674375534
2023-01-23 02:52:29.210598: step: 1912/529, loss: 0.028678035363554955
2023-01-23 02:52:30.332401: step: 1916/529, loss: 0.012335110455751419
2023-01-23 02:52:31.425995: step: 1920/529, loss: 0.32428044080734253
2023-01-23 02:52:32.516653: step: 1924/529, loss: 0.00010275840759277344
2023-01-23 02:52:33.616418: step: 1928/529, loss: 0.001251316163688898
2023-01-23 02:52:34.729439: step: 1932/529, loss: 0.0030506611801683903
2023-01-23 02:52:35.817310: step: 1936/529, loss: 0.0007130622980184853
2023-01-23 02:52:36.916078: step: 1940/529, loss: 0.00028476715669967234
2023-01-23 02:52:38.040283: step: 1944/529, loss: 0.6257377862930298
2023-01-23 02:52:39.179919: step: 1948/529, loss: 0.00018177033052779734
2023-01-23 02:52:40.302694: step: 1952/529, loss: 0.01791834831237793
2023-01-23 02:52:41.404788: step: 1956/529, loss: 0.00022716523380950093
2023-01-23 02:52:42.514714: step: 1960/529, loss: 0.002274131868034601
2023-01-23 02:52:43.607207: step: 1964/529, loss: 0.05136413499712944
2023-01-23 02:52:44.697235: step: 1968/529, loss: 0.012688255868852139
2023-01-23 02:52:45.828045: step: 1972/529, loss: 0.009505749680101871
2023-01-23 02:52:46.925957: step: 1976/529, loss: 0.0001369476376567036
2023-01-23 02:52:48.007683: step: 1980/529, loss: 0.00018324852862861007
2023-01-23 02:52:49.123009: step: 1984/529, loss: 0.03185243532061577
2023-01-23 02:52:50.255255: step: 1988/529, loss: 0.0008454322814941406
2023-01-23 02:52:51.358947: step: 1992/529, loss: 0.02744889259338379
2023-01-23 02:52:52.482925: step: 1996/529, loss: 0.027533387765288353
2023-01-23 02:52:53.596818: step: 2000/529, loss: 0.005228138063102961
2023-01-23 02:52:54.704327: step: 2004/529, loss: 0.01917858049273491
2023-01-23 02:52:55.836373: step: 2008/529, loss: 0.023989295586943626
2023-01-23 02:52:56.976312: step: 2012/529, loss: 0.0012901783920824528
2023-01-23 02:52:58.120629: step: 2016/529, loss: 0.00036678314791060984
2023-01-23 02:52:59.237373: step: 2020/529, loss: 0.01152567844837904
2023-01-23 02:53:00.333835: step: 2024/529, loss: 0.005275917239487171
2023-01-23 02:53:01.460066: step: 2028/529, loss: 0.02753319777548313
2023-01-23 02:53:02.567572: step: 2032/529, loss: 0.02874736860394478
2023-01-23 02:53:03.689646: step: 2036/529, loss: 0.004689216613769531
2023-01-23 02:53:04.777546: step: 2040/529, loss: 0.006198406219482422
2023-01-23 02:53:05.889437: step: 2044/529, loss: 0.013045703992247581
2023-01-23 02:53:06.999936: step: 2048/529, loss: 0.0075130462646484375
2023-01-23 02:53:08.084873: step: 2052/529, loss: 0.0035832407884299755
2023-01-23 02:53:09.239238: step: 2056/529, loss: 0.0739908218383789
2023-01-23 02:53:10.345384: step: 2060/529, loss: 0.000676059746183455
2023-01-23 02:53:11.473140: step: 2064/529, loss: 0.0018342972034588456
2023-01-23 02:53:12.568848: step: 2068/529, loss: 0.0003898620780091733
2023-01-23 02:53:13.706686: step: 2072/529, loss: 0.01401367224752903
2023-01-23 02:53:14.826290: step: 2076/529, loss: 0.009934616275131702
2023-01-23 02:53:15.970896: step: 2080/529, loss: 0.0006170272827148438
2023-01-23 02:53:17.067444: step: 2084/529, loss: 0.0003917693975381553
2023-01-23 02:53:18.216855: step: 2088/529, loss: 0.0016091347206383944
2023-01-23 02:53:19.332760: step: 2092/529, loss: 0.05111531913280487
2023-01-23 02:53:20.431921: step: 2096/529, loss: 0.04278087615966797
2023-01-23 02:53:21.562326: step: 2100/529, loss: 0.7997318506240845
2023-01-23 02:53:22.687264: step: 2104/529, loss: 0.00029544829158112407
2023-01-23 02:53:23.786496: step: 2108/529, loss: 0.010148381814360619
2023-01-23 02:53:24.889153: step: 2112/529, loss: 0.04116103798151016
2023-01-23 02:53:25.986397: step: 2116/529, loss: 0.0017887115245684981
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5898989898989899, 'r': 0.7776298268974701, 'f1': 0.6708788052843194}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6178458765209554, 'r': 0.7737020316027088, 'f1': 0.6870458531696316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.65, 'r': 0.6190476190476191, 'f1': 0.6341463414634146}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
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': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:54:06.246689: step: 4/529, loss: 0.020984530448913574
2023-01-23 02:54:07.406314: step: 8/529, loss: 0.024711037054657936
2023-01-23 02:54:08.512679: step: 12/529, loss: 0.01419610995799303
2023-01-23 02:54:09.610685: step: 16/529, loss: 0.0010246275924146175
2023-01-23 02:54:10.725372: step: 20/529, loss: 0.006266022101044655
2023-01-23 02:54:11.830289: step: 24/529, loss: 0.007914543151855469
2023-01-23 02:54:12.952414: step: 28/529, loss: 0.014003658667206764
2023-01-23 02:54:14.068537: step: 32/529, loss: 0.0009417533874511719
2023-01-23 02:54:15.166696: step: 36/529, loss: 0.007920265197753906
2023-01-23 02:54:16.284705: step: 40/529, loss: 0.021269990131258965
2023-01-23 02:54:17.389861: step: 44/529, loss: 0.0017608166672289371
2023-01-23 02:54:18.522889: step: 48/529, loss: 0.0015537261497229338
2023-01-23 02:54:19.621667: step: 52/529, loss: 0.0004150390741415322
2023-01-23 02:54:20.719487: step: 56/529, loss: 3.361701965332031e-05
2023-01-23 02:54:21.840088: step: 60/529, loss: 0.007055950351059437
2023-01-23 02:54:22.970426: step: 64/529, loss: 0.004631614778190851
2023-01-23 02:54:24.093541: step: 68/529, loss: 0.0010828971862792969
2023-01-23 02:54:25.183668: step: 72/529, loss: 0.002620199229568243
2023-01-23 02:54:26.295893: step: 76/529, loss: 0.055018093436956406
2023-01-23 02:54:27.393854: step: 80/529, loss: 0.0021310807205736637
2023-01-23 02:54:28.496638: step: 84/529, loss: 0.017327500507235527
2023-01-23 02:54:29.571321: step: 88/529, loss: 0.05563826858997345
2023-01-23 02:54:30.672861: step: 92/529, loss: 0.013677025213837624
2023-01-23 02:54:31.769956: step: 96/529, loss: 0.0010696410899981856
2023-01-23 02:54:32.843004: step: 100/529, loss: 0.008022118359804153
2023-01-23 02:54:33.962921: step: 104/529, loss: 0.009745026007294655
2023-01-23 02:54:35.070488: step: 108/529, loss: 0.0053882603533566
2023-01-23 02:54:36.198499: step: 112/529, loss: 0.016594314947724342
2023-01-23 02:54:37.305109: step: 116/529, loss: 0.011065680533647537
2023-01-23 02:54:38.424484: step: 120/529, loss: 2.689361645025201e-05
2023-01-23 02:54:39.529417: step: 124/529, loss: 0.04512729495763779
2023-01-23 02:54:40.614006: step: 128/529, loss: 0.012955261394381523
2023-01-23 02:54:41.731549: step: 132/529, loss: 0.03737945854663849
2023-01-23 02:54:42.831209: step: 136/529, loss: 0.039859771728515625
2023-01-23 02:54:43.919381: step: 140/529, loss: 0.04422473907470703
2023-01-23 02:54:45.044760: step: 144/529, loss: 0.3335091471672058
2023-01-23 02:54:46.167825: step: 148/529, loss: 0.008353996090590954
2023-01-23 02:54:47.267754: step: 152/529, loss: 0.060912229120731354
2023-01-23 02:54:48.361757: step: 156/529, loss: 0.02604498900473118
2023-01-23 02:54:49.477791: step: 160/529, loss: 0.0006613731384277344
2023-01-23 02:54:50.591282: step: 164/529, loss: 0.026853563264012337
2023-01-23 02:54:51.685108: step: 168/529, loss: 0.00016641616821289062
2023-01-23 02:54:52.821423: step: 172/529, loss: 0.005078315734863281
2023-01-23 02:54:53.913118: step: 176/529, loss: 0.00032548903254792094
2023-01-23 02:54:55.011031: step: 180/529, loss: 0.0005249023670330644
2023-01-23 02:54:56.119486: step: 184/529, loss: 8.93592878128402e-05
2023-01-23 02:54:57.209659: step: 188/529, loss: 0.0009150505647994578
2023-01-23 02:54:58.303540: step: 192/529, loss: 0.004787635989487171
2023-01-23 02:54:59.406388: step: 196/529, loss: 0.007172918412834406
2023-01-23 02:55:00.487857: step: 200/529, loss: 0.0004311561933718622
2023-01-23 02:55:01.581220: step: 204/529, loss: 0.0011467933654785156
2023-01-23 02:55:02.722548: step: 208/529, loss: 0.01928262785077095
2023-01-23 02:55:03.850232: step: 212/529, loss: 0.0008554458618164062
2023-01-23 02:55:04.952877: step: 216/529, loss: 0.0002612113894429058
2023-01-23 02:55:06.039762: step: 220/529, loss: 0.01692953146994114
2023-01-23 02:55:07.159489: step: 224/529, loss: 0.0007033348083496094
2023-01-23 02:55:08.276188: step: 228/529, loss: 0.002319431398063898
2023-01-23 02:55:09.372531: step: 232/529, loss: 0.18481312692165375
2023-01-23 02:55:10.478247: step: 236/529, loss: 0.7903178930282593
2023-01-23 02:55:11.589393: step: 240/529, loss: 0.002063655760139227
2023-01-23 02:55:12.702240: step: 244/529, loss: 0.011079215444624424
2023-01-23 02:55:13.818632: step: 248/529, loss: 0.0017589569324627519
2023-01-23 02:55:14.942984: step: 252/529, loss: 0.006633568089455366
2023-01-23 02:55:16.076082: step: 256/529, loss: 0.00037751198397018015
2023-01-23 02:55:17.164579: step: 260/529, loss: 0.005647039506584406
2023-01-23 02:55:18.298844: step: 264/529, loss: 0.0020733834244310856
2023-01-23 02:55:19.449474: step: 268/529, loss: 0.0057232859544456005
2023-01-23 02:55:20.562980: step: 272/529, loss: 0.0011430741287767887
2023-01-23 02:55:21.678307: step: 276/529, loss: 0.0009099960443563759
2023-01-23 02:55:22.807780: step: 280/529, loss: 0.00025367739726789296
2023-01-23 02:55:23.945289: step: 284/529, loss: 0.0008880614768713713
2023-01-23 02:55:25.061082: step: 288/529, loss: 0.003036880400031805
2023-01-23 02:55:26.170623: step: 292/529, loss: 0.0017561913700774312
2023-01-23 02:55:27.283744: step: 296/529, loss: 0.007814884185791016
2023-01-23 02:55:28.388079: step: 300/529, loss: 0.02033405192196369
2023-01-23 02:55:29.517749: step: 304/529, loss: 0.004198742099106312
2023-01-23 02:55:30.640322: step: 308/529, loss: 0.0005224705091677606
2023-01-23 02:55:31.751725: step: 312/529, loss: 0.0005334377055987716
2023-01-23 02:55:32.889398: step: 316/529, loss: 0.00020122528076171875
2023-01-23 02:55:33.995812: step: 320/529, loss: 5.445480201160535e-05
2023-01-23 02:55:35.099025: step: 324/529, loss: 9.13620024221018e-05
2023-01-23 02:55:36.208025: step: 328/529, loss: 0.0016367912758141756
2023-01-23 02:55:37.309226: step: 332/529, loss: 0.00014352798461914062
2023-01-23 02:55:38.413075: step: 336/529, loss: 0.0016219615936279297
2023-01-23 02:55:39.553599: step: 340/529, loss: 0.000988960382528603
2023-01-23 02:55:40.682924: step: 344/529, loss: 0.00015392302884720266
2023-01-23 02:55:41.755884: step: 348/529, loss: 0.0006551742553710938
2023-01-23 02:55:42.865632: step: 352/529, loss: 0.17161349952220917
2023-01-23 02:55:43.948389: step: 356/529, loss: 5.817413693876006e-06
2023-01-23 02:55:45.089996: step: 360/529, loss: 0.0066123963333666325
2023-01-23 02:55:46.207999: step: 364/529, loss: 7.686615572310984e-05
2023-01-23 02:55:47.300744: step: 368/529, loss: 6.952285912120715e-05
2023-01-23 02:55:48.404792: step: 372/529, loss: 0.05263710021972656
2023-01-23 02:55:49.512351: step: 376/529, loss: 0.00021228790865279734
2023-01-23 02:55:50.624134: step: 380/529, loss: 0.0030956268310546875
2023-01-23 02:55:51.743432: step: 384/529, loss: 0.008430957794189453
2023-01-23 02:55:52.827644: step: 388/529, loss: 0.0005131721263751388
2023-01-23 02:55:53.921998: step: 392/529, loss: 0.0002020835963776335
2023-01-23 02:55:55.013640: step: 396/529, loss: 0.005168342962861061
2023-01-23 02:55:56.129051: step: 400/529, loss: 0.030016519129276276
2023-01-23 02:55:57.258114: step: 404/529, loss: 0.02531719207763672
2023-01-23 02:55:58.346278: step: 408/529, loss: 0.0022316696122288704
2023-01-23 02:55:59.483041: step: 412/529, loss: 0.02414998970925808
2023-01-23 02:56:00.575847: step: 416/529, loss: 0.00096893310546875
2023-01-23 02:56:01.661129: step: 420/529, loss: 0.002853012178093195
2023-01-23 02:56:02.773898: step: 424/529, loss: 0.004511356353759766
2023-01-23 02:56:03.889326: step: 428/529, loss: 0.0008190632215701044
2023-01-23 02:56:05.016799: step: 432/529, loss: 0.015511131845414639
2023-01-23 02:56:06.101120: step: 436/529, loss: 0.0012537003494799137
2023-01-23 02:56:07.251006: step: 440/529, loss: 0.006739330478012562
2023-01-23 02:56:08.376872: step: 444/529, loss: 0.002609825227409601
2023-01-23 02:56:09.496339: step: 448/529, loss: 0.0006969452369958162
2023-01-23 02:56:10.617796: step: 452/529, loss: 0.0026191710494458675
2023-01-23 02:56:11.730882: step: 456/529, loss: 0.007627010345458984
2023-01-23 02:56:12.818998: step: 460/529, loss: 0.00930566806346178
2023-01-23 02:56:13.918535: step: 464/529, loss: 0.014107896015048027
2023-01-23 02:56:15.013244: step: 468/529, loss: 0.00014209747314453125
2023-01-23 02:56:16.101432: step: 472/529, loss: 0.0002609252987895161
2023-01-23 02:56:17.218583: step: 476/529, loss: 0.011373329907655716
2023-01-23 02:56:18.322195: step: 480/529, loss: 0.00033054352388717234
2023-01-23 02:56:19.453095: step: 484/529, loss: 0.0007009506225585938
2023-01-23 02:56:20.563855: step: 488/529, loss: 8.726120540814009e-06
2023-01-23 02:56:21.678776: step: 492/529, loss: 0.026540184393525124
2023-01-23 02:56:22.808666: step: 496/529, loss: 0.00015287399583030492
2023-01-23 02:56:23.935139: step: 500/529, loss: 0.017219258472323418
2023-01-23 02:56:25.063070: step: 504/529, loss: 0.05229397118091583
2023-01-23 02:56:26.196146: step: 508/529, loss: 0.0006369590992107987
2023-01-23 02:56:27.309976: step: 512/529, loss: 0.01734142377972603
2023-01-23 02:56:28.423825: step: 516/529, loss: 0.00670967111364007
2023-01-23 02:56:29.525750: step: 520/529, loss: 0.00349521660245955
2023-01-23 02:56:30.624165: step: 524/529, loss: 0.00948266964405775
2023-01-23 02:56:31.724095: step: 528/529, loss: 0.0013858318561688066
2023-01-23 02:56:32.803387: step: 532/529, loss: 5.8507917856331915e-05
2023-01-23 02:56:33.884124: step: 536/529, loss: 0.0011786938412114978
2023-01-23 02:56:35.019870: step: 540/529, loss: 0.0003211975272279233
2023-01-23 02:56:36.103461: step: 544/529, loss: 0.006136131007224321
2023-01-23 02:56:37.229749: step: 548/529, loss: 0.002990245819091797
2023-01-23 02:56:38.344764: step: 552/529, loss: 0.022269917652010918
2023-01-23 02:56:39.461266: step: 556/529, loss: 0.0010646820301190019
2023-01-23 02:56:40.587256: step: 560/529, loss: 0.00048022271948866546
2023-01-23 02:56:41.685773: step: 564/529, loss: 0.0010446547530591488
2023-01-23 02:56:42.800147: step: 568/529, loss: 0.05416097864508629
2023-01-23 02:56:43.952012: step: 572/529, loss: 0.00020618439884856343
2023-01-23 02:56:45.053581: step: 576/529, loss: 0.08019447326660156
2023-01-23 02:56:46.175731: step: 580/529, loss: 0.0031221387907862663
2023-01-23 02:56:47.259023: step: 584/529, loss: 0.004239177796989679
2023-01-23 02:56:48.353566: step: 588/529, loss: 0.00028438569279387593
2023-01-23 02:56:49.472644: step: 592/529, loss: 0.0190290454775095
2023-01-23 02:56:50.593596: step: 596/529, loss: 0.003799867583438754
2023-01-23 02:56:51.737043: step: 600/529, loss: 0.009310055524110794
2023-01-23 02:56:52.838431: step: 604/529, loss: 0.00041160586988553405
2023-01-23 02:56:53.956050: step: 608/529, loss: 0.0012542724143713713
2023-01-23 02:56:55.045990: step: 612/529, loss: 0.0010925770038738847
2023-01-23 02:56:56.144623: step: 616/529, loss: 1.9073486328125e-05
2023-01-23 02:56:57.248555: step: 620/529, loss: 0.02089872397482395
2023-01-23 02:56:58.351319: step: 624/529, loss: 0.00042786600533872843
2023-01-23 02:56:59.480490: step: 628/529, loss: 0.0002280235494254157
2023-01-23 02:57:00.579818: step: 632/529, loss: 0.00016098022751975805
2023-01-23 02:57:01.676553: step: 636/529, loss: 0.00039877890958450735
2023-01-23 02:57:02.783063: step: 640/529, loss: 0.02602844312787056
2023-01-23 02:57:03.877593: step: 644/529, loss: 3.833770824712701e-05
2023-01-23 02:57:04.974660: step: 648/529, loss: 0.005907726474106312
2023-01-23 02:57:06.061717: step: 652/529, loss: 0.0008953094366006553
2023-01-23 02:57:07.174564: step: 656/529, loss: 0.00023565292940475047
2023-01-23 02:57:08.292338: step: 660/529, loss: 0.0008718490717001259
2023-01-23 02:57:09.391509: step: 664/529, loss: 0.00237693777307868
2023-01-23 02:57:10.518304: step: 668/529, loss: 0.012457657605409622
2023-01-23 02:57:11.624615: step: 672/529, loss: 0.023097991943359375
2023-01-23 02:57:12.734086: step: 676/529, loss: 0.09297113120555878
2023-01-23 02:57:13.844717: step: 680/529, loss: 0.007905769161880016
2023-01-23 02:57:14.962036: step: 684/529, loss: 0.03787994384765625
2023-01-23 02:57:16.061064: step: 688/529, loss: 4.920959327137098e-05
2023-01-23 02:57:17.195882: step: 692/529, loss: 0.02614612877368927
2023-01-23 02:57:18.317889: step: 696/529, loss: 0.10093307495117188
2023-01-23 02:57:19.453131: step: 700/529, loss: 0.0029104233253747225
2023-01-23 02:57:20.568709: step: 704/529, loss: 0.0014276504516601562
2023-01-23 02:57:21.683733: step: 708/529, loss: 0.09107530117034912
2023-01-23 02:57:22.781889: step: 712/529, loss: 0.0002925872977357358
2023-01-23 02:57:23.868574: step: 716/529, loss: 0.017434168606996536
2023-01-23 02:57:24.963361: step: 720/529, loss: 0.00061626429669559
2023-01-23 02:57:26.061340: step: 724/529, loss: 0.03289041668176651
2023-01-23 02:57:27.179334: step: 728/529, loss: 0.0009641647338867188
2023-01-23 02:57:28.328508: step: 732/529, loss: 0.026391983032226562
2023-01-23 02:57:29.425322: step: 736/529, loss: 0.006184863857924938
2023-01-23 02:57:30.572055: step: 740/529, loss: 0.006008434109389782
2023-01-23 02:57:31.676133: step: 744/529, loss: 0.046254731714725494
2023-01-23 02:57:32.797200: step: 748/529, loss: 8.625983900856227e-05
2023-01-23 02:57:33.928462: step: 752/529, loss: 0.02526693418622017
2023-01-23 02:57:35.026338: step: 756/529, loss: 0.07945775985717773
2023-01-23 02:57:36.108772: step: 760/529, loss: 0.0048278807662427425
2023-01-23 02:57:37.255695: step: 764/529, loss: 0.04965219274163246
2023-01-23 02:57:38.361759: step: 768/529, loss: 0.0017281054751947522
2023-01-23 02:57:39.479128: step: 772/529, loss: 0.0003504753112792969
2023-01-23 02:57:40.601733: step: 776/529, loss: 0.016553306952118874
2023-01-23 02:57:41.725776: step: 780/529, loss: 0.0009123802301473916
2023-01-23 02:57:42.856958: step: 784/529, loss: 0.008713293820619583
2023-01-23 02:57:43.974637: step: 788/529, loss: 0.02239713817834854
2023-01-23 02:57:45.124158: step: 792/529, loss: 0.0030422210693359375
2023-01-23 02:57:46.255113: step: 796/529, loss: 0.04105987772345543
2023-01-23 02:57:47.384542: step: 800/529, loss: 0.05293693393468857
2023-01-23 02:57:48.491604: step: 804/529, loss: 0.0005140304565429688
2023-01-23 02:57:49.593997: step: 808/529, loss: 0.0014772415161132812
2023-01-23 02:57:50.711061: step: 812/529, loss: 0.0171419158577919
2023-01-23 02:57:51.823319: step: 816/529, loss: 0.02715468406677246
2023-01-23 02:57:52.946030: step: 820/529, loss: 0.0012449264759197831
2023-01-23 02:57:54.052631: step: 824/529, loss: 0.005867648404091597
2023-01-23 02:57:55.169793: step: 828/529, loss: 0.0019479751354083419
2023-01-23 02:57:56.267441: step: 832/529, loss: 0.0030104639008641243
2023-01-23 02:57:57.380120: step: 836/529, loss: 0.0190995205193758
2023-01-23 02:57:58.513205: step: 840/529, loss: 0.25192564725875854
2023-01-23 02:57:59.634047: step: 844/529, loss: 0.059175681322813034
2023-01-23 02:58:00.734548: step: 848/529, loss: 0.013447665609419346
2023-01-23 02:58:01.840731: step: 852/529, loss: 0.016181660816073418
2023-01-23 02:58:02.922308: step: 856/529, loss: 0.011273693293333054
2023-01-23 02:58:04.054845: step: 860/529, loss: 0.007645034696906805
2023-01-23 02:58:05.208565: step: 864/529, loss: 0.00015401840209960938
2023-01-23 02:58:06.322305: step: 868/529, loss: 0.00196418771520257
2023-01-23 02:58:07.446702: step: 872/529, loss: 0.011222553439438343
2023-01-23 02:58:08.540339: step: 876/529, loss: 0.07223377376794815
2023-01-23 02:58:09.663790: step: 880/529, loss: 0.021004199981689453
2023-01-23 02:58:10.809949: step: 884/529, loss: 0.9754303097724915
2023-01-23 02:58:11.904691: step: 888/529, loss: 0.000204181662411429
2023-01-23 02:58:12.998494: step: 892/529, loss: 0.03430728614330292
2023-01-23 02:58:14.079934: step: 896/529, loss: 0.0022115707397460938
2023-01-23 02:58:15.199393: step: 900/529, loss: 0.027570199221372604
2023-01-23 02:58:16.301933: step: 904/529, loss: 0.01960773579776287
2023-01-23 02:58:17.437318: step: 908/529, loss: 0.06493254005908966
2023-01-23 02:58:18.625413: step: 912/529, loss: 0.007010173983871937
2023-01-23 02:58:19.747461: step: 916/529, loss: 0.0026778222527354956
2023-01-23 02:58:20.866175: step: 920/529, loss: 0.024400806054472923
2023-01-23 02:58:21.953951: step: 924/529, loss: 0.0006547927623614669
2023-01-23 02:58:23.068500: step: 928/529, loss: 0.011786842718720436
2023-01-23 02:58:24.171645: step: 932/529, loss: 0.00019025802612304688
2023-01-23 02:58:25.288793: step: 936/529, loss: 0.00651474017649889
2023-01-23 02:58:26.414019: step: 940/529, loss: 0.00028705596923828125
2023-01-23 02:58:27.507964: step: 944/529, loss: 0.0037679672241210938
2023-01-23 02:58:28.602249: step: 948/529, loss: 0.005447006318718195
2023-01-23 02:58:29.737647: step: 952/529, loss: 1.4877318790240679e-05
2023-01-23 02:58:30.874240: step: 956/529, loss: 0.0004461407952476293
2023-01-23 02:58:31.978767: step: 960/529, loss: 0.00044097902718931437
2023-01-23 02:58:33.079526: step: 964/529, loss: 0.00014171600923873484
2023-01-23 02:58:34.209256: step: 968/529, loss: 0.00296535505913198
2023-01-23 02:58:35.307458: step: 972/529, loss: 0.008984755724668503
2023-01-23 02:58:36.408345: step: 976/529, loss: 0.009597063064575195
2023-01-23 02:58:37.511062: step: 980/529, loss: 0.0025451183319091797
2023-01-23 02:58:38.648529: step: 984/529, loss: 0.0005354404565878212
2023-01-23 02:58:39.746323: step: 988/529, loss: 0.09144258499145508
2023-01-23 02:58:40.827394: step: 992/529, loss: 0.002868366427719593
2023-01-23 02:58:41.929577: step: 996/529, loss: 0.00020256043353583664
2023-01-23 02:58:43.032301: step: 1000/529, loss: 0.0018606185913085938
2023-01-23 02:58:44.127835: step: 1004/529, loss: 0.0270251277834177
2023-01-23 02:58:45.242450: step: 1008/529, loss: 0.0188356414437294
2023-01-23 02:58:46.345095: step: 1012/529, loss: 0.0010814189445227385
2023-01-23 02:58:47.458883: step: 1016/529, loss: 4.434585662238533e-06
2023-01-23 02:58:48.610772: step: 1020/529, loss: 0.06488993018865585
2023-01-23 02:58:49.729566: step: 1024/529, loss: 0.0231507308781147
2023-01-23 02:58:50.866320: step: 1028/529, loss: 0.014320564456284046
2023-01-23 02:58:52.004773: step: 1032/529, loss: 0.0012389183975756168
2023-01-23 02:58:53.092879: step: 1036/529, loss: 0.00915222242474556
2023-01-23 02:58:54.201256: step: 1040/529, loss: 0.011677075177431107
2023-01-23 02:58:55.321816: step: 1044/529, loss: 0.005236148834228516
2023-01-23 02:58:56.439740: step: 1048/529, loss: 0.07618493586778641
2023-01-23 02:58:57.581379: step: 1052/529, loss: 0.019169950857758522
2023-01-23 02:58:58.692982: step: 1056/529, loss: 0.015366650186479092
2023-01-23 02:58:59.841584: step: 1060/529, loss: 0.0028061866760253906
2023-01-23 02:59:00.936229: step: 1064/529, loss: 0.0021330355666577816
2023-01-23 02:59:02.063584: step: 1068/529, loss: 0.00016889571270439774
2023-01-23 02:59:03.178494: step: 1072/529, loss: 5.483627683133818e-05
2023-01-23 02:59:04.284190: step: 1076/529, loss: 0.026884840801358223
2023-01-23 02:59:05.405636: step: 1080/529, loss: 6.523132469737902e-05
2023-01-23 02:59:06.536096: step: 1084/529, loss: 0.019875813275575638
2023-01-23 02:59:07.675160: step: 1088/529, loss: 0.004985237028449774
2023-01-23 02:59:08.768729: step: 1092/529, loss: 0.0018360137473791838
2023-01-23 02:59:09.896222: step: 1096/529, loss: 0.016112040728330612
2023-01-23 02:59:11.022190: step: 1100/529, loss: 0.0006847381591796875
2023-01-23 02:59:12.143981: step: 1104/529, loss: 0.03131461143493652
2023-01-23 02:59:13.248463: step: 1108/529, loss: 0.005988788791000843
2023-01-23 02:59:14.371698: step: 1112/529, loss: 0.0032947540748864412
2023-01-23 02:59:15.450890: step: 1116/529, loss: 0.03661594167351723
2023-01-23 02:59:16.537960: step: 1120/529, loss: 0.0005634307744912803
2023-01-23 02:59:17.663995: step: 1124/529, loss: 0.022788239642977715
2023-01-23 02:59:18.774075: step: 1128/529, loss: 0.027476264163851738
2023-01-23 02:59:19.865622: step: 1132/529, loss: 0.0023464204277843237
2023-01-23 02:59:20.973188: step: 1136/529, loss: 1.8978118532686494e-05
2023-01-23 02:59:22.076111: step: 1140/529, loss: 0.01290369126945734
2023-01-23 02:59:23.204173: step: 1144/529, loss: 0.0519598051905632
2023-01-23 02:59:24.347406: step: 1148/529, loss: 0.03210010379552841
2023-01-23 02:59:25.500430: step: 1152/529, loss: 0.0386316291987896
2023-01-23 02:59:26.615280: step: 1156/529, loss: 0.002997493837028742
2023-01-23 02:59:27.724044: step: 1160/529, loss: 0.002531051868572831
2023-01-23 02:59:28.834624: step: 1164/529, loss: 0.043094635009765625
2023-01-23 02:59:29.953031: step: 1168/529, loss: 0.0020805359818041325
2023-01-23 02:59:31.064772: step: 1172/529, loss: 0.005076789762824774
2023-01-23 02:59:32.167076: step: 1176/529, loss: 0.007420539855957031
2023-01-23 02:59:33.275262: step: 1180/529, loss: 0.007191467564553022
2023-01-23 02:59:34.393757: step: 1184/529, loss: 0.03194174915552139
2023-01-23 02:59:35.515529: step: 1188/529, loss: 0.0026786804664880037
2023-01-23 02:59:36.625981: step: 1192/529, loss: 0.0077419281005859375
2023-01-23 02:59:37.736789: step: 1196/529, loss: 0.02488403208553791
2023-01-23 02:59:38.835497: step: 1200/529, loss: 0.019365692511200905
2023-01-23 02:59:39.948526: step: 1204/529, loss: 0.06426334381103516
2023-01-23 02:59:41.084226: step: 1208/529, loss: 0.19323483109474182
2023-01-23 02:59:42.233304: step: 1212/529, loss: 0.0002995491086039692
2023-01-23 02:59:43.360984: step: 1216/529, loss: 0.006313800811767578
2023-01-23 02:59:44.467235: step: 1220/529, loss: 0.01786499097943306
2023-01-23 02:59:45.592529: step: 1224/529, loss: 0.0005496978992596269
2023-01-23 02:59:46.702651: step: 1228/529, loss: 0.00012912749662064016
2023-01-23 02:59:47.822667: step: 1232/529, loss: 0.04875793680548668
2023-01-23 02:59:48.924933: step: 1236/529, loss: 0.00183353410102427
2023-01-23 02:59:50.086212: step: 1240/529, loss: 0.0017376424511894584
2023-01-23 02:59:51.178486: step: 1244/529, loss: 0.0004755973641294986
2023-01-23 02:59:52.280383: step: 1248/529, loss: 0.04385976865887642
2023-01-23 02:59:53.396895: step: 1252/529, loss: 5.664825584972277e-05
2023-01-23 02:59:54.501953: step: 1256/529, loss: 0.0031322957947850227
2023-01-23 02:59:55.612627: step: 1260/529, loss: 0.02064957655966282
2023-01-23 02:59:56.706026: step: 1264/529, loss: 0.004171943757683039
2023-01-23 02:59:57.809426: step: 1268/529, loss: 0.022301102057099342
2023-01-23 02:59:58.906128: step: 1272/529, loss: 0.025876808911561966
2023-01-23 03:00:00.017178: step: 1276/529, loss: 0.007781696040183306
2023-01-23 03:00:01.124494: step: 1280/529, loss: 0.01775054819881916
2023-01-23 03:00:02.216918: step: 1284/529, loss: 0.0023900510277599096
2023-01-23 03:00:03.312158: step: 1288/529, loss: 0.027754688635468483
2023-01-23 03:00:04.418965: step: 1292/529, loss: 0.00011917352094314992
2023-01-23 03:00:05.510966: step: 1296/529, loss: 0.0007245064480230212
2023-01-23 03:00:06.621900: step: 1300/529, loss: 0.06863269954919815
2023-01-23 03:00:07.742733: step: 1304/529, loss: 0.013102531433105469
2023-01-23 03:00:08.871578: step: 1308/529, loss: 0.024417974054813385
2023-01-23 03:00:09.967367: step: 1312/529, loss: 7.629396350239404e-07
2023-01-23 03:00:11.067222: step: 1316/529, loss: 3.457069760770537e-05
2023-01-23 03:00:12.181408: step: 1320/529, loss: 0.006758022587746382
2023-01-23 03:00:13.302451: step: 1324/529, loss: 0.041713714599609375
2023-01-23 03:00:14.399265: step: 1328/529, loss: 0.08664874732494354
2023-01-23 03:00:15.481684: step: 1332/529, loss: 0.0007704734453000128
2023-01-23 03:00:16.598176: step: 1336/529, loss: 0.03634205088019371
2023-01-23 03:00:17.710225: step: 1340/529, loss: 0.00029077532235533
2023-01-23 03:00:18.826215: step: 1344/529, loss: 0.0003410339413676411
2023-01-23 03:00:19.914784: step: 1348/529, loss: 0.00039544107858091593
2023-01-23 03:00:21.056602: step: 1352/529, loss: 0.007435822859406471
2023-01-23 03:00:22.194649: step: 1356/529, loss: 0.03292837366461754
2023-01-23 03:00:23.283345: step: 1360/529, loss: 0.021404074504971504
2023-01-23 03:00:24.426643: step: 1364/529, loss: 0.03869705647230148
2023-01-23 03:00:25.552373: step: 1368/529, loss: 0.0014341354835778475
2023-01-23 03:00:26.658753: step: 1372/529, loss: 3.681182715808973e-05
2023-01-23 03:00:27.756427: step: 1376/529, loss: 0.0034673691261559725
2023-01-23 03:00:28.889088: step: 1380/529, loss: 0.0009338856325484812
2023-01-23 03:00:30.007064: step: 1384/529, loss: 0.00010204315185546875
2023-01-23 03:00:31.116119: step: 1388/529, loss: 0.0025687217712402344
2023-01-23 03:00:32.196706: step: 1392/529, loss: 0.000102996826171875
2023-01-23 03:00:33.316763: step: 1396/529, loss: 0.024662017822265625
2023-01-23 03:00:34.447336: step: 1400/529, loss: 0.011120045557618141
2023-01-23 03:00:35.593853: step: 1404/529, loss: 0.0006376743549481034
2023-01-23 03:00:36.707849: step: 1408/529, loss: 0.010180091485381126
2023-01-23 03:00:37.826649: step: 1412/529, loss: 0.0077002523466944695
2023-01-23 03:00:38.934965: step: 1416/529, loss: 0.00026502611581236124
2023-01-23 03:00:40.071724: step: 1420/529, loss: 0.06222133710980415
2023-01-23 03:00:41.185496: step: 1424/529, loss: 0.011392593383789062
2023-01-23 03:00:42.317045: step: 1428/529, loss: 0.041582297533750534
2023-01-23 03:00:43.430646: step: 1432/529, loss: 0.0016268730396404862
2023-01-23 03:00:44.516784: step: 1436/529, loss: 6.399154517566785e-05
2023-01-23 03:00:45.627551: step: 1440/529, loss: 0.00040950774564407766
2023-01-23 03:00:46.732595: step: 1444/529, loss: 0.01871499978005886
2023-01-23 03:00:47.821683: step: 1448/529, loss: 0.01595153845846653
2023-01-23 03:00:48.916176: step: 1452/529, loss: 5.7220458984375e-05
2023-01-23 03:00:50.021317: step: 1456/529, loss: 0.09844265133142471
2023-01-23 03:00:51.101088: step: 1460/529, loss: 0.006976318545639515
2023-01-23 03:00:52.193516: step: 1464/529, loss: 0.011003208346664906
2023-01-23 03:00:53.282500: step: 1468/529, loss: 0.018002891913056374
2023-01-23 03:00:54.422726: step: 1472/529, loss: 0.002467250684276223
2023-01-23 03:00:55.577461: step: 1476/529, loss: 0.02062053792178631
2023-01-23 03:00:56.694346: step: 1480/529, loss: 0.00406570453196764
2023-01-23 03:00:57.812848: step: 1484/529, loss: 6.446838233387098e-05
2023-01-23 03:00:58.927206: step: 1488/529, loss: 9.398460679221898e-05
2023-01-23 03:01:00.063561: step: 1492/529, loss: 0.17100505530834198
2023-01-23 03:01:01.186851: step: 1496/529, loss: 4.563331822282635e-05
2023-01-23 03:01:02.252951: step: 1500/529, loss: 0.0005127906915731728
2023-01-23 03:01:03.350092: step: 1504/529, loss: 0.000396537798224017
2023-01-23 03:01:04.457044: step: 1508/529, loss: 0.0030138969887048006
2023-01-23 03:01:05.561302: step: 1512/529, loss: 0.001436424208804965
2023-01-23 03:01:06.659294: step: 1516/529, loss: 0.00069427490234375
2023-01-23 03:01:07.810653: step: 1520/529, loss: 0.0021524429321289062
2023-01-23 03:01:08.932617: step: 1524/529, loss: 0.0012069703079760075
2023-01-23 03:01:10.040577: step: 1528/529, loss: 0.010901331901550293
2023-01-23 03:01:11.142298: step: 1532/529, loss: 0.002715492155402899
2023-01-23 03:01:12.245375: step: 1536/529, loss: 0.010830498300492764
2023-01-23 03:01:13.345998: step: 1540/529, loss: 0.002168846083804965
2023-01-23 03:01:14.467314: step: 1544/529, loss: 0.0012269974686205387
2023-01-23 03:01:15.598344: step: 1548/529, loss: 0.08148574829101562
2023-01-23 03:01:16.676520: step: 1552/529, loss: 0.0006669998401775956
2023-01-23 03:01:17.801238: step: 1556/529, loss: 0.0008137703407555819
2023-01-23 03:01:18.910487: step: 1560/529, loss: 0.07223119586706161
2023-01-23 03:01:20.014062: step: 1564/529, loss: 0.09631986916065216
2023-01-23 03:01:21.144177: step: 1568/529, loss: 0.009471584111452103
2023-01-23 03:01:22.275213: step: 1572/529, loss: 0.02781658247113228
2023-01-23 03:01:23.387828: step: 1576/529, loss: 1.8787384760798886e-05
2023-01-23 03:01:24.486880: step: 1580/529, loss: 0.0013381957542151213
2023-01-23 03:01:25.580841: step: 1584/529, loss: 0.005512905307114124
2023-01-23 03:01:26.700472: step: 1588/529, loss: 0.003703498747199774
2023-01-23 03:01:27.800247: step: 1592/529, loss: 0.002418899443000555
2023-01-23 03:01:28.965211: step: 1596/529, loss: 0.017078112810850143
2023-01-23 03:01:30.102181: step: 1600/529, loss: 0.006324720103293657
2023-01-23 03:01:31.240509: step: 1604/529, loss: 0.06168804317712784
2023-01-23 03:01:32.355440: step: 1608/529, loss: 0.00040493012056685984
2023-01-23 03:01:33.450696: step: 1612/529, loss: 0.0030885697342455387
2023-01-23 03:01:34.540942: step: 1616/529, loss: 0.005735206883400679
2023-01-23 03:01:35.656881: step: 1620/529, loss: 0.03360319137573242
2023-01-23 03:01:36.751715: step: 1624/529, loss: 0.002379798796027899
2023-01-23 03:01:37.869332: step: 1628/529, loss: 0.006606435868889093
2023-01-23 03:01:38.975573: step: 1632/529, loss: 0.0019009590614587069
2023-01-23 03:01:40.116529: step: 1636/529, loss: 0.0011101722484454513
2023-01-23 03:01:41.209575: step: 1640/529, loss: 0.0010530471336096525
2023-01-23 03:01:42.318531: step: 1644/529, loss: 0.0002922058047261089
2023-01-23 03:01:43.433633: step: 1648/529, loss: 0.0316736213862896
2023-01-23 03:01:44.537459: step: 1652/529, loss: 0.005758475977927446
2023-01-23 03:01:45.660449: step: 1656/529, loss: 0.02818622626364231
2023-01-23 03:01:46.790333: step: 1660/529, loss: 1.716613724056515e-06
2023-01-23 03:01:47.900623: step: 1664/529, loss: 0.00474205007776618
2023-01-23 03:01:49.018507: step: 1668/529, loss: 0.0318845771253109
2023-01-23 03:01:50.132346: step: 1672/529, loss: 0.014821624383330345
2023-01-23 03:01:51.224304: step: 1676/529, loss: 0.0004411697154864669
2023-01-23 03:01:52.354423: step: 1680/529, loss: 0.0005587577470578253
2023-01-23 03:01:53.477954: step: 1684/529, loss: 0.0539977103471756
2023-01-23 03:01:54.593809: step: 1688/529, loss: 0.021155642345547676
2023-01-23 03:01:55.690788: step: 1692/529, loss: 0.027691461145877838
2023-01-23 03:01:56.795656: step: 1696/529, loss: 0.03290477767586708
2023-01-23 03:01:57.902799: step: 1700/529, loss: 3.4332275390625e-05
2023-01-23 03:01:59.017829: step: 1704/529, loss: 0.04723091423511505
2023-01-23 03:02:00.112284: step: 1708/529, loss: -1.0013580322265625e-05
2023-01-23 03:02:01.234594: step: 1712/529, loss: 0.00556185282766819
2023-01-23 03:02:02.365263: step: 1716/529, loss: 0.005481719970703125
2023-01-23 03:02:03.485117: step: 1720/529, loss: 0.0052058217115700245
2023-01-23 03:02:04.658942: step: 1724/529, loss: 0.009868049062788486
2023-01-23 03:02:05.760320: step: 1728/529, loss: 0.000530719815287739
2023-01-23 03:02:06.862205: step: 1732/529, loss: 0.05551014095544815
2023-01-23 03:02:07.962610: step: 1736/529, loss: 0.007211876101791859
2023-01-23 03:02:09.068077: step: 1740/529, loss: 0.028414295986294746
2023-01-23 03:02:10.209967: step: 1744/529, loss: 0.007656860165297985
2023-01-23 03:02:11.310830: step: 1748/529, loss: 0.000996494316495955
2023-01-23 03:02:12.420903: step: 1752/529, loss: 0.006771469488739967
2023-01-23 03:02:13.518726: step: 1756/529, loss: 0.0017566680908203125
2023-01-23 03:02:14.606514: step: 1760/529, loss: 0.0005850791931152344
2023-01-23 03:02:15.723822: step: 1764/529, loss: 0.0010857820743694901
2023-01-23 03:02:16.843430: step: 1768/529, loss: 0.2705098092556
2023-01-23 03:02:17.977771: step: 1772/529, loss: 0.07381203770637512
2023-01-23 03:02:19.108637: step: 1776/529, loss: 0.03545703738927841
2023-01-23 03:02:20.244724: step: 1780/529, loss: 0.10171470791101456
2023-01-23 03:02:21.347051: step: 1784/529, loss: 8.087605237960815e-05
2023-01-23 03:02:22.451337: step: 1788/529, loss: 0.02450408972799778
2023-01-23 03:02:23.551867: step: 1792/529, loss: 0.00019836427236441523
2023-01-23 03:02:24.705437: step: 1796/529, loss: 0.0007505417452193797
2023-01-23 03:02:25.834809: step: 1800/529, loss: 0.004984474275261164
2023-01-23 03:02:26.925013: step: 1804/529, loss: 0.0047702789306640625
2023-01-23 03:02:28.041049: step: 1808/529, loss: 0.014599801041185856
2023-01-23 03:02:29.158819: step: 1812/529, loss: 0.05559387058019638
2023-01-23 03:02:30.262790: step: 1816/529, loss: 0.03633527830243111
2023-01-23 03:02:31.379799: step: 1820/529, loss: 0.004245663061738014
2023-01-23 03:02:32.498236: step: 1824/529, loss: 0.05724906921386719
2023-01-23 03:02:33.609837: step: 1828/529, loss: 0.004823446273803711
2023-01-23 03:02:34.731314: step: 1832/529, loss: 0.026070214807987213
2023-01-23 03:02:35.829787: step: 1836/529, loss: 0.01709003560245037
2023-01-23 03:02:36.974349: step: 1840/529, loss: 0.00035419463529251516
2023-01-23 03:02:38.108707: step: 1844/529, loss: 0.0033585550263524055
2023-01-23 03:02:39.213410: step: 1848/529, loss: 0.03517098352313042
2023-01-23 03:02:40.325096: step: 1852/529, loss: 2.1266938347253017e-05
2023-01-23 03:02:41.451508: step: 1856/529, loss: 0.18844357132911682
2023-01-23 03:02:42.547381: step: 1860/529, loss: 0.010949421674013138
2023-01-23 03:02:43.685191: step: 1864/529, loss: 0.0004792422114405781
2023-01-23 03:02:44.845125: step: 1868/529, loss: 0.07842407375574112
2023-01-23 03:02:45.926027: step: 1872/529, loss: 0.005452823359519243
2023-01-23 03:02:47.018187: step: 1876/529, loss: 0.0003111839178018272
2023-01-23 03:02:48.113862: step: 1880/529, loss: 4.65869925392326e-05
2023-01-23 03:02:49.198194: step: 1884/529, loss: 0.02787027321755886
2023-01-23 03:02:50.330346: step: 1888/529, loss: 0.01788453944027424
2023-01-23 03:02:51.441839: step: 1892/529, loss: 0.4779691696166992
2023-01-23 03:02:52.562352: step: 1896/529, loss: 0.3006353974342346
2023-01-23 03:02:53.659838: step: 1900/529, loss: 0.011092566885054111
2023-01-23 03:02:54.730390: step: 1904/529, loss: 0.0001417681633029133
2023-01-23 03:02:55.848086: step: 1908/529, loss: 0.10302677005529404
2023-01-23 03:02:56.951128: step: 1912/529, loss: 4.94956984766759e-05
2023-01-23 03:02:58.046449: step: 1916/529, loss: 0.039360810071229935
2023-01-23 03:02:59.115296: step: 1920/529, loss: 4.491806248552166e-05
2023-01-23 03:03:00.256689: step: 1924/529, loss: 0.0074977874755859375
2023-01-23 03:03:01.393923: step: 1928/529, loss: 0.010804463177919388
2023-01-23 03:03:02.525221: step: 1932/529, loss: 0.00016790107474662364
2023-01-23 03:03:03.630430: step: 1936/529, loss: 0.012201881036162376
2023-01-23 03:03:04.714223: step: 1940/529, loss: 0.004649448674172163
2023-01-23 03:03:05.800918: step: 1944/529, loss: 0.004570770543068647
2023-01-23 03:03:06.889853: step: 1948/529, loss: 0.0002151489316020161
2023-01-23 03:03:07.973797: step: 1952/529, loss: 0.000701522862073034
2023-01-23 03:03:09.094752: step: 1956/529, loss: 0.015621663071215153
2023-01-23 03:03:10.210960: step: 1960/529, loss: 0.035024262964725494
2023-01-23 03:03:11.324322: step: 1964/529, loss: 0.0008228301885537803
2023-01-23 03:03:12.442562: step: 1968/529, loss: 0.038230132311582565
2023-01-23 03:03:13.549604: step: 1972/529, loss: 0.003978633787482977
2023-01-23 03:03:14.686443: step: 1976/529, loss: 0.004439544398337603
2023-01-23 03:03:15.792850: step: 1980/529, loss: 0.05241961404681206
2023-01-23 03:03:16.914813: step: 1984/529, loss: 0.03841552883386612
2023-01-23 03:03:18.000761: step: 1988/529, loss: 0.0017431258456781507
2023-01-23 03:03:19.117145: step: 1992/529, loss: 0.0002325058012502268
2023-01-23 03:03:20.256626: step: 1996/529, loss: 0.008177090436220169
2023-01-23 03:03:21.372553: step: 2000/529, loss: 9.965896606445312e-05
2023-01-23 03:03:22.482179: step: 2004/529, loss: 0.0190550796687603
2023-01-23 03:03:23.572630: step: 2008/529, loss: 0.022170066833496094
2023-01-23 03:03:24.719799: step: 2012/529, loss: 0.015341853722929955
2023-01-23 03:03:25.852242: step: 2016/529, loss: 0.11924886703491211
2023-01-23 03:03:26.984366: step: 2020/529, loss: 0.013314819894731045
2023-01-23 03:03:28.118739: step: 2024/529, loss: 0.0006289482116699219
2023-01-23 03:03:29.250022: step: 2028/529, loss: 0.0013704299926757812
2023-01-23 03:03:30.368108: step: 2032/529, loss: 0.02000293880701065
2023-01-23 03:03:31.468205: step: 2036/529, loss: 0.07647235691547394
2023-01-23 03:03:32.576437: step: 2040/529, loss: 0.0012081146705895662
2023-01-23 03:03:33.670412: step: 2044/529, loss: 0.006828213110566139
2023-01-23 03:03:34.775824: step: 2048/529, loss: 0.0034330368507653475
2023-01-23 03:03:35.891638: step: 2052/529, loss: 0.003417587373405695
2023-01-23 03:03:37.013477: step: 2056/529, loss: 0.020191097632050514
2023-01-23 03:03:38.128856: step: 2060/529, loss: 0.03416576609015465
2023-01-23 03:03:39.250928: step: 2064/529, loss: 0.02537689171731472
2023-01-23 03:03:40.325303: step: 2068/529, loss: 0.0013364792102947831
2023-01-23 03:03:41.427903: step: 2072/529, loss: 0.0010828971862792969
2023-01-23 03:03:42.569028: step: 2076/529, loss: 0.0036756517365574837
2023-01-23 03:03:43.687383: step: 2080/529, loss: 0.007564115803688765
2023-01-23 03:03:44.779063: step: 2084/529, loss: 0.06037912145256996
2023-01-23 03:03:45.881852: step: 2088/529, loss: 0.009715653024613857
2023-01-23 03:03:47.000063: step: 2092/529, loss: 0.006321525666862726
2023-01-23 03:03:48.085531: step: 2096/529, loss: 0.044431500136852264
2023-01-23 03:03:49.194903: step: 2100/529, loss: 0.037435341626405716
2023-01-23 03:03:50.298873: step: 2104/529, loss: 0.00018548965454101562
2023-01-23 03:03:51.396264: step: 2108/529, loss: 0.011276436038315296
2023-01-23 03:03:52.500029: step: 2112/529, loss: 0.004372215364128351
2023-01-23 03:03:53.601784: step: 2116/529, loss: 0.05443563312292099
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.6067653276955602, 'r': 0.7643142476697736, 'f1': 0.6764879198585739}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6389806512505899, 'r': 0.7641083521444695, 'f1': 0.695965047545618}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5517241379310345, 'r': 0.8888888888888888, 'f1': 0.6808510638297872}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5714285714285714, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.425, 'r': 0.4722222222222222, 'f1': 0.4473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 21
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:04:33.378636: step: 4/529, loss: 2.613067590573337e-05
2023-01-23 03:04:34.474562: step: 8/529, loss: 0.021919824182987213
2023-01-23 03:04:35.591164: step: 12/529, loss: 0.08860154449939728
2023-01-23 03:04:36.688964: step: 16/529, loss: 0.015587473288178444
2023-01-23 03:04:37.858732: step: 20/529, loss: 0.00036115647526457906
2023-01-23 03:04:38.980811: step: 24/529, loss: 0.025742148980498314
2023-01-23 03:04:40.095925: step: 28/529, loss: 0.00487442035228014
2023-01-23 03:04:41.216008: step: 32/529, loss: 0.002731320448219776
2023-01-23 03:04:42.337375: step: 36/529, loss: 0.01446390151977539
2023-01-23 03:04:43.432035: step: 40/529, loss: 0.004962826147675514
2023-01-23 03:04:44.545147: step: 44/529, loss: 0.00042304996168240905
2023-01-23 03:04:45.655050: step: 48/529, loss: 0.0037470818497240543
2023-01-23 03:04:46.779276: step: 52/529, loss: 0.012492799200117588
2023-01-23 03:04:47.909844: step: 56/529, loss: 0.0003494262637104839
2023-01-23 03:04:49.010045: step: 60/529, loss: 0.00018911361985374242
2023-01-23 03:04:50.119025: step: 64/529, loss: 0.00023968219466041774
2023-01-23 03:04:51.225394: step: 68/529, loss: 0.9430027604103088
2023-01-23 03:04:52.343313: step: 72/529, loss: 0.00154962542001158
2023-01-23 03:04:53.489233: step: 76/529, loss: 0.0009286046260967851
2023-01-23 03:04:54.615300: step: 80/529, loss: 0.0041918279603123665
2023-01-23 03:04:55.719980: step: 84/529, loss: 0.0048690796829760075
2023-01-23 03:04:56.813630: step: 88/529, loss: 0.00898208562284708
2023-01-23 03:04:57.932824: step: 92/529, loss: 0.0012594700092449784
2023-01-23 03:04:59.015933: step: 96/529, loss: 0.0014060973189771175
2023-01-23 03:05:00.134840: step: 100/529, loss: 0.0011108398903161287
2023-01-23 03:05:01.231352: step: 104/529, loss: 0.001168966293334961
2023-01-23 03:05:02.361148: step: 108/529, loss: 0.005302238743752241
2023-01-23 03:05:03.459516: step: 112/529, loss: 0.020262623205780983
2023-01-23 03:05:04.546521: step: 116/529, loss: 0.015787124633789062
2023-01-23 03:05:05.665015: step: 120/529, loss: 0.019242573529481888
2023-01-23 03:05:06.798524: step: 124/529, loss: 0.03191409260034561
2023-01-23 03:05:07.897857: step: 128/529, loss: 0.0023286822251975536
2023-01-23 03:05:08.964018: step: 132/529, loss: 3.528594970703125e-05
2023-01-23 03:05:10.044899: step: 136/529, loss: 0.00017943383136298507
2023-01-23 03:05:11.162671: step: 140/529, loss: 0.0031764984596520662
2023-01-23 03:05:12.263855: step: 144/529, loss: 6.12258882028982e-05
2023-01-23 03:05:13.393351: step: 148/529, loss: 0.0012099266750738025
2023-01-23 03:05:14.509126: step: 152/529, loss: 0.0002994537353515625
2023-01-23 03:05:15.632760: step: 156/529, loss: 0.005751896183937788
2023-01-23 03:05:16.713716: step: 160/529, loss: 0.0032262802124023438
2023-01-23 03:05:17.843699: step: 164/529, loss: 0.08008003234863281
2023-01-23 03:05:18.940521: step: 168/529, loss: 0.00014925003051757812
2023-01-23 03:05:20.098476: step: 172/529, loss: 0.0010047913528978825
2023-01-23 03:05:21.201050: step: 176/529, loss: 0.044236376881599426
2023-01-23 03:05:22.305074: step: 180/529, loss: 0.00016288757615257055
2023-01-23 03:05:23.428082: step: 184/529, loss: 0.0011455535423010588
2023-01-23 03:05:24.513805: step: 188/529, loss: 0.0034526349045336246
2023-01-23 03:05:25.608856: step: 192/529, loss: 0.0437747985124588
2023-01-23 03:05:26.752811: step: 196/529, loss: 0.002347278641536832
2023-01-23 03:05:27.898331: step: 200/529, loss: 0.022580433636903763
2023-01-23 03:05:29.014892: step: 204/529, loss: 0.007929230108857155
2023-01-23 03:05:30.125832: step: 208/529, loss: 0.06851902604103088
2023-01-23 03:05:31.243924: step: 212/529, loss: 0.005290794186294079
2023-01-23 03:05:32.336558: step: 216/529, loss: 0.0003197670157533139
2023-01-23 03:05:33.459641: step: 220/529, loss: 0.002115535782650113
2023-01-23 03:05:34.567616: step: 224/529, loss: 0.0036491393111646175
2023-01-23 03:05:35.701108: step: 228/529, loss: 0.0006009340286254883
2023-01-23 03:05:36.804303: step: 232/529, loss: 0.2991218566894531
2023-01-23 03:05:37.924570: step: 236/529, loss: 0.02958526648581028
2023-01-23 03:05:39.025078: step: 240/529, loss: 0.00078496930655092
2023-01-23 03:05:40.150349: step: 244/529, loss: 0.14212216436862946
2023-01-23 03:05:41.282738: step: 248/529, loss: 0.007867050357162952
2023-01-23 03:05:42.394589: step: 252/529, loss: 0.0003217697376385331
2023-01-23 03:05:43.487805: step: 256/529, loss: 0.014172124676406384
2023-01-23 03:05:44.605679: step: 260/529, loss: 9.493828110862523e-05
2023-01-23 03:05:45.727610: step: 264/529, loss: 0.0013633727794513106
2023-01-23 03:05:46.813646: step: 268/529, loss: 0.006245422642678022
2023-01-23 03:05:47.910804: step: 272/529, loss: 0.0030531883239746094
2023-01-23 03:05:49.036988: step: 276/529, loss: 0.11727866530418396
2023-01-23 03:05:50.155955: step: 280/529, loss: 0.0007067203987389803
2023-01-23 03:05:51.245646: step: 284/529, loss: 0.09139136970043182
2023-01-23 03:05:52.361887: step: 288/529, loss: 0.019987013190984726
2023-01-23 03:05:53.465539: step: 292/529, loss: 0.1840529441833496
2023-01-23 03:05:54.579105: step: 296/529, loss: 0.004201030824333429
2023-01-23 03:05:55.687211: step: 300/529, loss: 0.00919113215059042
2023-01-23 03:05:56.804544: step: 304/529, loss: 0.0030369760934263468
2023-01-23 03:05:57.914468: step: 308/529, loss: 0.0007394790882244706
2023-01-23 03:05:59.044593: step: 312/529, loss: 0.0018394470680505037
2023-01-23 03:06:00.199819: step: 316/529, loss: 0.03560009226202965
2023-01-23 03:06:01.299550: step: 320/529, loss: 0.0011362076038494706
2023-01-23 03:06:02.424422: step: 324/529, loss: 0.029270555824041367
2023-01-23 03:06:03.520487: step: 328/529, loss: 0.022177983075380325
2023-01-23 03:06:04.626068: step: 332/529, loss: 0.02502279356122017
2023-01-23 03:06:05.751622: step: 336/529, loss: 0.004890823271125555
2023-01-23 03:06:06.850250: step: 340/529, loss: 0.0002095222589559853
2023-01-23 03:06:07.955700: step: 344/529, loss: 0.003365421202033758
2023-01-23 03:06:09.112000: step: 348/529, loss: 0.011507987976074219
2023-01-23 03:06:10.248412: step: 352/529, loss: 0.0010006905067712069
2023-01-23 03:06:11.369630: step: 356/529, loss: 0.0006176948663778603
2023-01-23 03:06:12.478556: step: 360/529, loss: 0.0005784988170489669
2023-01-23 03:06:13.574005: step: 364/529, loss: 0.004149246029555798
2023-01-23 03:06:14.674428: step: 368/529, loss: 0.0002172470121877268
2023-01-23 03:06:15.784241: step: 372/529, loss: 0.01653308980166912
2023-01-23 03:06:16.895868: step: 376/529, loss: 4.919171624351293e-05
2023-01-23 03:06:18.011437: step: 380/529, loss: 0.09673252701759338
2023-01-23 03:06:19.109274: step: 384/529, loss: 0.0005697250016964972
2023-01-23 03:06:20.213910: step: 388/529, loss: 0.035703565925359726
2023-01-23 03:06:21.344469: step: 392/529, loss: 0.00445103645324707
2023-01-23 03:06:22.452985: step: 396/529, loss: 0.0008612633100710809
2023-01-23 03:06:23.547979: step: 400/529, loss: 0.0566289909183979
2023-01-23 03:06:24.667783: step: 404/529, loss: 0.004525851923972368
2023-01-23 03:06:25.741601: step: 408/529, loss: 6.67572021484375e-06
2023-01-23 03:06:26.832568: step: 412/529, loss: 0.0006334304925985634
2023-01-23 03:06:27.929724: step: 416/529, loss: 0.00047788620577193797
2023-01-23 03:06:29.028008: step: 420/529, loss: 0.0042795659974217415
2023-01-23 03:06:30.132721: step: 424/529, loss: 0.005630016326904297
2023-01-23 03:06:31.224629: step: 428/529, loss: 0.016614211723208427
2023-01-23 03:06:32.360688: step: 432/529, loss: 0.005085754673928022
2023-01-23 03:06:33.471916: step: 436/529, loss: 0.004018020816147327
2023-01-23 03:06:34.591833: step: 440/529, loss: 0.0323827750980854
2023-01-23 03:06:35.695422: step: 444/529, loss: 0.00857534445822239
2023-01-23 03:06:36.813098: step: 448/529, loss: 3.929138256353326e-05
2023-01-23 03:06:37.942115: step: 452/529, loss: 0.03530597314238548
2023-01-23 03:06:39.065276: step: 456/529, loss: 0.01349721010774374
2023-01-23 03:06:40.198274: step: 460/529, loss: 0.0017461777897551656
2023-01-23 03:06:41.345052: step: 464/529, loss: 0.0006258010980673134
2023-01-23 03:06:42.474866: step: 468/529, loss: 0.025965308770537376
2023-01-23 03:06:43.587418: step: 472/529, loss: 0.0011900425888597965
2023-01-23 03:06:44.645481: step: 476/529, loss: 5.846023850608617e-05
2023-01-23 03:06:45.744667: step: 480/529, loss: 0.002334499265998602
2023-01-23 03:06:46.859537: step: 484/529, loss: 0.001425069523975253
2023-01-23 03:06:47.973873: step: 488/529, loss: 0.010773325338959694
2023-01-23 03:06:49.076591: step: 492/529, loss: 0.004265308380126953
2023-01-23 03:06:50.178305: step: 496/529, loss: 0.0007693290826864541
2023-01-23 03:06:51.254414: step: 500/529, loss: 0.002647972200065851
2023-01-23 03:06:52.361134: step: 504/529, loss: 0.002762031741440296
2023-01-23 03:06:53.456744: step: 508/529, loss: 0.001010894775390625
2023-01-23 03:06:54.551392: step: 512/529, loss: 0.028596973046660423
2023-01-23 03:06:55.682265: step: 516/529, loss: 0.0014122009743005037
2023-01-23 03:06:56.776681: step: 520/529, loss: 0.00185222621075809
2023-01-23 03:06:57.874149: step: 524/529, loss: 0.0004059791681356728
2023-01-23 03:06:58.978621: step: 528/529, loss: 0.0020330429542809725
2023-01-23 03:07:00.069401: step: 532/529, loss: 0.000370025634765625
2023-01-23 03:07:01.155278: step: 536/529, loss: 0.012719536200165749
2023-01-23 03:07:02.284268: step: 540/529, loss: 0.03291015699505806
2023-01-23 03:07:03.397502: step: 544/529, loss: 0.049634553492069244
2023-01-23 03:07:04.534415: step: 548/529, loss: 0.012201976962387562
2023-01-23 03:07:05.632335: step: 552/529, loss: 0.017602063715457916
2023-01-23 03:07:06.716228: step: 556/529, loss: 0.02855362929403782
2023-01-23 03:07:07.829859: step: 560/529, loss: 0.0002857208310160786
2023-01-23 03:07:08.919148: step: 564/529, loss: 0.003656578017398715
2023-01-23 03:07:10.035799: step: 568/529, loss: 0.017104625701904297
2023-01-23 03:07:11.144729: step: 572/529, loss: 6.027221752447076e-05
2023-01-23 03:07:12.286965: step: 576/529, loss: 0.007122325710952282
2023-01-23 03:07:13.374916: step: 580/529, loss: 0.001768398331478238
2023-01-23 03:07:14.469837: step: 584/529, loss: 0.003937148954719305
2023-01-23 03:07:15.586288: step: 588/529, loss: 0.005389594938606024
2023-01-23 03:07:16.686792: step: 592/529, loss: 0.012478924356400967
2023-01-23 03:07:17.804768: step: 596/529, loss: 0.02545471116900444
2023-01-23 03:07:18.904868: step: 600/529, loss: 0.06955185532569885
2023-01-23 03:07:20.040442: step: 604/529, loss: 0.011044503189623356
2023-01-23 03:07:21.188539: step: 608/529, loss: 0.007721519563347101
2023-01-23 03:07:22.301777: step: 612/529, loss: 0.0008298874017782509
2023-01-23 03:07:23.424461: step: 616/529, loss: 0.020178042352199554
2023-01-23 03:07:24.529804: step: 620/529, loss: 0.011399651877582073
2023-01-23 03:07:25.652128: step: 624/529, loss: 0.046204518526792526
2023-01-23 03:07:26.744082: step: 628/529, loss: 0.0010167121654376388
2023-01-23 03:07:27.872439: step: 632/529, loss: 0.00149116525426507
2023-01-23 03:07:29.017189: step: 636/529, loss: 0.026746368035674095
2023-01-23 03:07:30.115282: step: 640/529, loss: 0.020307207480072975
2023-01-23 03:07:31.249491: step: 644/529, loss: 0.020549917593598366
2023-01-23 03:07:32.352736: step: 648/529, loss: 1.316070574830519e-05
2023-01-23 03:07:33.453476: step: 652/529, loss: 0.0017923355335369706
2023-01-23 03:07:34.557786: step: 656/529, loss: 0.009404277428984642
2023-01-23 03:07:35.647413: step: 660/529, loss: 0.00814600009471178
2023-01-23 03:07:36.739928: step: 664/529, loss: 0.0017849921714514494
2023-01-23 03:07:37.850687: step: 668/529, loss: 0.005227899178862572
2023-01-23 03:07:38.979419: step: 672/529, loss: 0.024492979049682617
2023-01-23 03:07:40.094088: step: 676/529, loss: 1.773834264895413e-05
2023-01-23 03:07:41.209188: step: 680/529, loss: 0.007250881288200617
2023-01-23 03:07:42.304285: step: 684/529, loss: 0.0010100365616381168
2023-01-23 03:07:43.437940: step: 688/529, loss: 0.11091961711645126
2023-01-23 03:07:44.554155: step: 692/529, loss: 0.0006041526794433594
2023-01-23 03:07:45.647339: step: 696/529, loss: 0.003327846759930253
2023-01-23 03:07:46.744525: step: 700/529, loss: 0.0003040313604287803
2023-01-23 03:07:47.862013: step: 704/529, loss: 0.0030141829047352076
2023-01-23 03:07:48.985644: step: 708/529, loss: 0.000522232090588659
2023-01-23 03:07:50.106698: step: 712/529, loss: 0.0003856658877339214
2023-01-23 03:07:51.207290: step: 716/529, loss: 0.0007453918224200606
2023-01-23 03:07:52.332055: step: 720/529, loss: 0.06306882202625275
2023-01-23 03:07:53.435158: step: 724/529, loss: 0.006275367923080921
2023-01-23 03:07:54.556571: step: 728/529, loss: 0.00041105749551206827
2023-01-23 03:07:55.650430: step: 732/529, loss: 0.07748498767614365
2023-01-23 03:07:56.740010: step: 736/529, loss: 0.026653816923499107
2023-01-23 03:07:57.867427: step: 740/529, loss: 0.0443546287715435
2023-01-23 03:07:59.030925: step: 744/529, loss: 0.004307555966079235
2023-01-23 03:08:00.130343: step: 748/529, loss: 0.00023136139498092234
2023-01-23 03:08:01.244879: step: 752/529, loss: 0.001127052353695035
2023-01-23 03:08:02.350609: step: 756/529, loss: 0.0012309551239013672
2023-01-23 03:08:03.460639: step: 760/529, loss: 0.0002533912775106728
2023-01-23 03:08:04.566428: step: 764/529, loss: 0.0018871307838708162
2023-01-23 03:08:05.676052: step: 768/529, loss: 0.0025529861450195312
2023-01-23 03:08:06.786004: step: 772/529, loss: 0.0025209428276866674
2023-01-23 03:08:07.896788: step: 776/529, loss: 0.0029299496673047543
2023-01-23 03:08:09.028438: step: 780/529, loss: 1.2588501704158261e-05
2023-01-23 03:08:10.162639: step: 784/529, loss: 0.013435936532914639
2023-01-23 03:08:11.288799: step: 788/529, loss: 0.029555892571806908
2023-01-23 03:08:12.382742: step: 792/529, loss: 0.002090024994686246
2023-01-23 03:08:13.516703: step: 796/529, loss: 0.0005940914270468056
2023-01-23 03:08:14.641959: step: 800/529, loss: 0.004150867462158203
2023-01-23 03:08:15.766238: step: 804/529, loss: 0.008687401190400124
2023-01-23 03:08:16.892633: step: 808/529, loss: 0.007641410920768976
2023-01-23 03:08:17.994733: step: 812/529, loss: 0.0060357097536325455
2023-01-23 03:08:19.090247: step: 816/529, loss: 0.00730476388707757
2023-01-23 03:08:20.259149: step: 820/529, loss: 0.000347137451171875
2023-01-23 03:08:21.407410: step: 824/529, loss: 0.04311399161815643
2023-01-23 03:08:22.524777: step: 828/529, loss: 0.009614849463105202
2023-01-23 03:08:23.619853: step: 832/529, loss: 0.0257905013859272
2023-01-23 03:08:24.759661: step: 836/529, loss: 0.011482619680464268
2023-01-23 03:08:25.858357: step: 840/529, loss: 0.0001369476376567036
2023-01-23 03:08:27.013851: step: 844/529, loss: 0.0016026496887207031
2023-01-23 03:08:28.119486: step: 848/529, loss: 9.312629845226184e-05
2023-01-23 03:08:29.201672: step: 852/529, loss: 0.02016162872314453
2023-01-23 03:08:30.322835: step: 856/529, loss: 0.05476274713873863
2023-01-23 03:08:31.452146: step: 860/529, loss: 2.937316821771674e-05
2023-01-23 03:08:32.540885: step: 864/529, loss: 0.00026493071345612407
2023-01-23 03:08:33.687434: step: 868/529, loss: 0.010068893432617188
2023-01-23 03:08:34.796094: step: 872/529, loss: 0.00020074844360351562
2023-01-23 03:08:35.917305: step: 876/529, loss: 0.00027675629826262593
2023-01-23 03:08:37.006368: step: 880/529, loss: 0.014531517401337624
2023-01-23 03:08:38.134798: step: 884/529, loss: 0.0014039992820471525
2023-01-23 03:08:39.260525: step: 888/529, loss: 0.011753464117646217
2023-01-23 03:08:40.358597: step: 892/529, loss: 0.0047266483306884766
2023-01-23 03:08:41.445349: step: 896/529, loss: 0.0032814026344567537
2023-01-23 03:08:42.563928: step: 900/529, loss: 0.08225230872631073
2023-01-23 03:08:43.651103: step: 904/529, loss: 0.00025501250638626516
2023-01-23 03:08:44.743003: step: 908/529, loss: 0.00024185179790947586
2023-01-23 03:08:45.872437: step: 912/529, loss: 0.10555868595838547
2023-01-23 03:08:46.964108: step: 916/529, loss: 4.682540748035535e-05
2023-01-23 03:08:48.061390: step: 920/529, loss: 0.006677818484604359
2023-01-23 03:08:49.163131: step: 924/529, loss: 0.00028543471125885844
2023-01-23 03:08:50.281385: step: 928/529, loss: 0.0066127777099609375
2023-01-23 03:08:51.411314: step: 932/529, loss: 0.0003414154052734375
2023-01-23 03:08:52.522391: step: 936/529, loss: 0.00147504813503474
2023-01-23 03:08:53.593132: step: 940/529, loss: 0.0008194923866540194
2023-01-23 03:08:54.693855: step: 944/529, loss: 0.006486701779067516
2023-01-23 03:08:55.804860: step: 948/529, loss: 0.016590215265750885
2023-01-23 03:08:56.917479: step: 952/529, loss: 1.016620397567749
2023-01-23 03:08:58.083141: step: 956/529, loss: 0.006287908647209406
2023-01-23 03:08:59.202002: step: 960/529, loss: 0.060610584914684296
2023-01-23 03:09:00.306817: step: 964/529, loss: 0.0005306244129315019
2023-01-23 03:09:01.450538: step: 968/529, loss: 0.04360991716384888
2023-01-23 03:09:02.556244: step: 972/529, loss: 0.009817409329116344
2023-01-23 03:09:03.673280: step: 976/529, loss: 3.9768219721736386e-05
2023-01-23 03:09:04.813144: step: 980/529, loss: 0.003338718321174383
2023-01-23 03:09:05.916671: step: 984/529, loss: 0.010203361511230469
2023-01-23 03:09:07.030563: step: 988/529, loss: 0.0001313209650106728
2023-01-23 03:09:08.190931: step: 992/529, loss: 0.0002304077206645161
2023-01-23 03:09:09.321499: step: 996/529, loss: 0.06900434195995331
2023-01-23 03:09:10.476555: step: 1000/529, loss: 0.027210809290409088
2023-01-23 03:09:11.596739: step: 1004/529, loss: 0.12073516845703125
2023-01-23 03:09:12.722060: step: 1008/529, loss: 0.013430643826723099
2023-01-23 03:09:13.840022: step: 1012/529, loss: 0.0010364532936364412
2023-01-23 03:09:14.935689: step: 1016/529, loss: 0.006598282139748335
2023-01-23 03:09:16.059066: step: 1020/529, loss: 0.005657768342643976
2023-01-23 03:09:17.197921: step: 1024/529, loss: 0.0011806488037109375
2023-01-23 03:09:18.306715: step: 1028/529, loss: 0.0003438472922425717
2023-01-23 03:09:19.455538: step: 1032/529, loss: 0.004993343725800514
2023-01-23 03:09:20.565062: step: 1036/529, loss: 0.003002262208610773
2023-01-23 03:09:21.702406: step: 1040/529, loss: 0.014216137118637562
2023-01-23 03:09:22.808470: step: 1044/529, loss: 0.08601570129394531
2023-01-23 03:09:23.923322: step: 1048/529, loss: 0.0009085655328817666
2023-01-23 03:09:25.035281: step: 1052/529, loss: 0.00025286676827818155
2023-01-23 03:09:26.179860: step: 1056/529, loss: 0.0013441084884107113
2023-01-23 03:09:27.317372: step: 1060/529, loss: 0.008284187875688076
2023-01-23 03:09:28.446105: step: 1064/529, loss: 0.008956098929047585
2023-01-23 03:09:29.534674: step: 1068/529, loss: 0.0033546448685228825
2023-01-23 03:09:30.621265: step: 1072/529, loss: 0.0009879589779302478
2023-01-23 03:09:31.716290: step: 1076/529, loss: 0.0033112524542957544
2023-01-23 03:09:32.813947: step: 1080/529, loss: 0.02704768255352974
2023-01-23 03:09:33.905885: step: 1084/529, loss: 0.01084604300558567
2023-01-23 03:09:35.010666: step: 1088/529, loss: 0.0033391951583325863
2023-01-23 03:09:36.095918: step: 1092/529, loss: 0.005550289060920477
2023-01-23 03:09:37.236551: step: 1096/529, loss: 0.00013618469529319555
2023-01-23 03:09:38.359369: step: 1100/529, loss: 0.00012168884859420359
2023-01-23 03:09:39.483501: step: 1104/529, loss: 0.01589522324502468
2023-01-23 03:09:40.616376: step: 1108/529, loss: 0.044370412826538086
2023-01-23 03:09:41.711815: step: 1112/529, loss: 0.008757210336625576
2023-01-23 03:09:42.829861: step: 1116/529, loss: 0.00046672820462845266
2023-01-23 03:09:43.955661: step: 1120/529, loss: 0.013955128379166126
2023-01-23 03:09:45.062580: step: 1124/529, loss: 0.004243373870849609
2023-01-23 03:09:46.182612: step: 1128/529, loss: 0.04430122300982475
2023-01-23 03:09:47.326043: step: 1132/529, loss: 0.008907509967684746
2023-01-23 03:09:48.432703: step: 1136/529, loss: 0.0011700630420818925
2023-01-23 03:09:49.550055: step: 1140/529, loss: 6.999969627941027e-05
2023-01-23 03:09:50.662564: step: 1144/529, loss: 0.009433365426957607
2023-01-23 03:09:51.772097: step: 1148/529, loss: 0.04876670613884926
2023-01-23 03:09:52.908226: step: 1152/529, loss: 0.03381934389472008
2023-01-23 03:09:54.030147: step: 1156/529, loss: 3.5858156479662284e-05
2023-01-23 03:09:55.122216: step: 1160/529, loss: 0.008650779724121094
2023-01-23 03:09:56.228807: step: 1164/529, loss: 0.0090477941557765
2023-01-23 03:09:57.340707: step: 1168/529, loss: 0.009417342953383923
2023-01-23 03:09:58.446418: step: 1172/529, loss: 0.0002548217889852822
2023-01-23 03:09:59.560084: step: 1176/529, loss: 0.0003794670046772808
2023-01-23 03:10:00.677347: step: 1180/529, loss: 0.005774688441306353
2023-01-23 03:10:01.771390: step: 1184/529, loss: 8.430481102550402e-05
2023-01-23 03:10:02.866300: step: 1188/529, loss: 0.02354869805276394
2023-01-23 03:10:03.964565: step: 1192/529, loss: 0.0048355101607739925
2023-01-23 03:10:05.100030: step: 1196/529, loss: 0.0001371383696096018
2023-01-23 03:10:06.232175: step: 1200/529, loss: 0.027585793286561966
2023-01-23 03:10:07.331870: step: 1204/529, loss: 0.05016765743494034
2023-01-23 03:10:08.455736: step: 1208/529, loss: 0.0015378951793536544
2023-01-23 03:10:09.554072: step: 1212/529, loss: 0.0613313689827919
2023-01-23 03:10:10.660999: step: 1216/529, loss: 0.0005920410621911287
2023-01-23 03:10:11.770152: step: 1220/529, loss: 0.00033845900907181203
2023-01-23 03:10:12.857441: step: 1224/529, loss: 0.001554298447445035
2023-01-23 03:10:13.974361: step: 1228/529, loss: 0.0038946152199059725
2023-01-23 03:10:15.083364: step: 1232/529, loss: 0.030986785888671875
2023-01-23 03:10:16.236778: step: 1236/529, loss: 0.011160088703036308
2023-01-23 03:10:17.346816: step: 1240/529, loss: 0.04942665249109268
2023-01-23 03:10:18.468542: step: 1244/529, loss: 0.0011415063636377454
2023-01-23 03:10:19.605811: step: 1248/529, loss: 0.007232284639030695
2023-01-23 03:10:20.687618: step: 1252/529, loss: 0.02969837188720703
2023-01-23 03:10:21.791716: step: 1256/529, loss: 0.03896084055304527
2023-01-23 03:10:22.895300: step: 1260/529, loss: 0.001159071922302246
2023-01-23 03:10:24.022542: step: 1264/529, loss: 0.011816549114882946
2023-01-23 03:10:25.110837: step: 1268/529, loss: 0.001774597098119557
2023-01-23 03:10:26.246397: step: 1272/529, loss: 0.00081806187517941
2023-01-23 03:10:27.356971: step: 1276/529, loss: 0.0014037609798833728
2023-01-23 03:10:28.502650: step: 1280/529, loss: 0.06323757022619247
2023-01-23 03:10:29.630124: step: 1284/529, loss: 0.05183591693639755
2023-01-23 03:10:30.706434: step: 1288/529, loss: 0.0024730684235692024
2023-01-23 03:10:31.807481: step: 1292/529, loss: 0.004104614723473787
2023-01-23 03:10:32.908416: step: 1296/529, loss: 0.014987755566835403
2023-01-23 03:10:34.026077: step: 1300/529, loss: 0.0004473685985431075
2023-01-23 03:10:35.159906: step: 1304/529, loss: 0.007988072000443935
2023-01-23 03:10:36.259684: step: 1308/529, loss: 0.013030433095991611
2023-01-23 03:10:37.354274: step: 1312/529, loss: 0.00043201446533203125
2023-01-23 03:10:38.431938: step: 1316/529, loss: 0.0005203246837481856
2023-01-23 03:10:39.601593: step: 1320/529, loss: 0.0009806633461266756
2023-01-23 03:10:40.697073: step: 1324/529, loss: 0.0018163680797442794
2023-01-23 03:10:41.794419: step: 1328/529, loss: 0.0016283035511150956
2023-01-23 03:10:42.913214: step: 1332/529, loss: 0.0352325439453125
2023-01-23 03:10:44.020969: step: 1336/529, loss: 0.005730247590690851
2023-01-23 03:10:45.106241: step: 1340/529, loss: 0.020990945398807526
2023-01-23 03:10:46.243476: step: 1344/529, loss: 0.013221168890595436
2023-01-23 03:10:47.344717: step: 1348/529, loss: 0.011582947336137295
2023-01-23 03:10:48.426879: step: 1352/529, loss: 3.147125244140625e-05
2023-01-23 03:10:49.512097: step: 1356/529, loss: 0.0009323119884356856
2023-01-23 03:10:50.630726: step: 1360/529, loss: 0.0051641943864524364
2023-01-23 03:10:51.750113: step: 1364/529, loss: 0.004590797703713179
2023-01-23 03:10:52.861955: step: 1368/529, loss: 0.019164467230439186
2023-01-23 03:10:53.961025: step: 1372/529, loss: 3.621578071033582e-05
2023-01-23 03:10:55.067277: step: 1376/529, loss: 0.007919264025986195
2023-01-23 03:10:56.151050: step: 1380/529, loss: 0.004098796751350164
2023-01-23 03:10:57.269434: step: 1384/529, loss: 0.0010932921431958675
2023-01-23 03:10:58.376131: step: 1388/529, loss: 0.002154398011043668
2023-01-23 03:10:59.515259: step: 1392/529, loss: 0.0005236626020632684
2023-01-23 03:11:00.611528: step: 1396/529, loss: 0.43070220947265625
2023-01-23 03:11:01.727452: step: 1400/529, loss: 0.022328950464725494
2023-01-23 03:11:02.842763: step: 1404/529, loss: 0.014774608425796032
2023-01-23 03:11:03.961991: step: 1408/529, loss: 0.00046024323091842234
2023-01-23 03:11:05.071855: step: 1412/529, loss: 0.00028676987858489156
2023-01-23 03:11:06.179315: step: 1416/529, loss: 0.005784797482192516
2023-01-23 03:11:07.278119: step: 1420/529, loss: 0.009596442803740501
2023-01-23 03:11:08.397744: step: 1424/529, loss: 0.05635375902056694
2023-01-23 03:11:09.488729: step: 1428/529, loss: 4.01496872655116e-05
2023-01-23 03:11:10.568373: step: 1432/529, loss: 0.004881381988525391
2023-01-23 03:11:11.671724: step: 1436/529, loss: 3.223419116693549e-05
2023-01-23 03:11:12.768496: step: 1440/529, loss: 0.0004536628839559853
2023-01-23 03:11:13.898633: step: 1444/529, loss: 0.21957054734230042
2023-01-23 03:11:15.001970: step: 1448/529, loss: 0.05635872110724449
2023-01-23 03:11:16.117279: step: 1452/529, loss: 0.001562404679134488
2023-01-23 03:11:17.240363: step: 1456/529, loss: 0.010155296884477139
2023-01-23 03:11:18.353921: step: 1460/529, loss: 0.00622406043112278
2023-01-23 03:11:19.466877: step: 1464/529, loss: 0.017214488238096237
2023-01-23 03:11:20.582190: step: 1468/529, loss: 0.010006332769989967
2023-01-23 03:11:21.710603: step: 1472/529, loss: 0.0018203735817223787
2023-01-23 03:11:22.817441: step: 1476/529, loss: 0.040147777646780014
2023-01-23 03:11:23.944439: step: 1480/529, loss: 0.000255584716796875
2023-01-23 03:11:25.026184: step: 1484/529, loss: 0.0011684418423101306
2023-01-23 03:11:26.131870: step: 1488/529, loss: 0.005466938018798828
2023-01-23 03:11:27.241139: step: 1492/529, loss: 0.0014110564952716231
2023-01-23 03:11:28.365842: step: 1496/529, loss: 0.0007377624860964715
2023-01-23 03:11:29.460232: step: 1500/529, loss: 0.009814644232392311
2023-01-23 03:11:30.555601: step: 1504/529, loss: 4.677772813010961e-05
2023-01-23 03:11:31.657670: step: 1508/529, loss: 0.004952812101691961
2023-01-23 03:11:32.808302: step: 1512/529, loss: 0.2715301513671875
2023-01-23 03:11:33.928046: step: 1516/529, loss: 0.0002231597900390625
2023-01-23 03:11:35.031279: step: 1520/529, loss: 0.02539835125207901
2023-01-23 03:11:36.155428: step: 1524/529, loss: 0.0042705535888671875
2023-01-23 03:11:37.272721: step: 1528/529, loss: 0.7415567636489868
2023-01-23 03:11:38.383578: step: 1532/529, loss: 0.07374286651611328
2023-01-23 03:11:39.509920: step: 1536/529, loss: 0.02031269110739231
2023-01-23 03:11:40.630831: step: 1540/529, loss: 0.00041675567626953125
2023-01-23 03:11:41.745635: step: 1544/529, loss: 0.0003694534534588456
2023-01-23 03:11:42.847268: step: 1548/529, loss: 0.05913887172937393
2023-01-23 03:11:43.967116: step: 1552/529, loss: 0.013163280673325062
2023-01-23 03:11:45.099199: step: 1556/529, loss: 0.029240036383271217
2023-01-23 03:11:46.217403: step: 1560/529, loss: 0.0071218013763427734
2023-01-23 03:11:47.323492: step: 1564/529, loss: 0.0009699404472485185
2023-01-23 03:11:48.457974: step: 1568/529, loss: 0.000539588974788785
2023-01-23 03:11:49.582470: step: 1572/529, loss: 0.005153656005859375
2023-01-23 03:11:50.741220: step: 1576/529, loss: 0.02655940130352974
2023-01-23 03:11:51.869752: step: 1580/529, loss: 0.04200410842895508
2023-01-23 03:11:52.960533: step: 1584/529, loss: 0.0011692047119140625
2023-01-23 03:11:54.100752: step: 1588/529, loss: 0.04342499002814293
2023-01-23 03:11:55.218298: step: 1592/529, loss: 0.04300084337592125
2023-01-23 03:11:56.347075: step: 1596/529, loss: 0.011670398525893688
2023-01-23 03:11:57.457400: step: 1600/529, loss: 0.022550202906131744
2023-01-23 03:11:58.584209: step: 1604/529, loss: 0.0027776716742664576
2023-01-23 03:11:59.674578: step: 1608/529, loss: 0.004341507330536842
2023-01-23 03:12:00.784165: step: 1612/529, loss: 0.0013125420082360506
2023-01-23 03:12:01.920250: step: 1616/529, loss: 0.0021593093406409025
2023-01-23 03:12:03.029955: step: 1620/529, loss: 0.00011749267287086695
2023-01-23 03:12:04.141052: step: 1624/529, loss: 0.02150888554751873
2023-01-23 03:12:05.240161: step: 1628/529, loss: 0.045619964599609375
2023-01-23 03:12:06.362021: step: 1632/529, loss: 0.004310798831284046
2023-01-23 03:12:07.450194: step: 1636/529, loss: 2.2983551389188506e-05
2023-01-23 03:12:08.547231: step: 1640/529, loss: 0.028566457331180573
2023-01-23 03:12:09.675697: step: 1644/529, loss: 0.000789642333984375
2023-01-23 03:12:10.783918: step: 1648/529, loss: 0.004481792449951172
2023-01-23 03:12:11.879283: step: 1652/529, loss: 0.0011348724365234375
2023-01-23 03:12:12.988502: step: 1656/529, loss: 0.00030126573983579874
2023-01-23 03:12:14.078661: step: 1660/529, loss: 0.00104694371111691
2023-01-23 03:12:15.185419: step: 1664/529, loss: 0.0154876708984375
2023-01-23 03:12:16.287758: step: 1668/529, loss: 0.00035572052001953125
2023-01-23 03:12:17.423336: step: 1672/529, loss: 9.260178194381297e-05
2023-01-23 03:12:18.524554: step: 1676/529, loss: 0.007158947177231312
2023-01-23 03:12:19.626878: step: 1680/529, loss: 0.025133611634373665
2023-01-23 03:12:20.715729: step: 1684/529, loss: 0.006118583492934704
2023-01-23 03:12:21.820498: step: 1688/529, loss: 0.013369262218475342
2023-01-23 03:12:22.946443: step: 1692/529, loss: 0.009079551324248314
2023-01-23 03:12:24.066729: step: 1696/529, loss: 0.0014762879582121968
2023-01-23 03:12:25.156338: step: 1700/529, loss: 0.01657400280237198
2023-01-23 03:12:26.249398: step: 1704/529, loss: 0.043244171887636185
2023-01-23 03:12:27.352496: step: 1708/529, loss: 1.354217511106981e-05
2023-01-23 03:12:28.485911: step: 1712/529, loss: 0.002960681915283203
2023-01-23 03:12:29.592791: step: 1716/529, loss: 0.0009980201721191406
2023-01-23 03:12:30.707546: step: 1720/529, loss: 4.863738922722405e-06
2023-01-23 03:12:31.816453: step: 1724/529, loss: 0.0004366874636616558
2023-01-23 03:12:32.911099: step: 1728/529, loss: 0.006194877438247204
2023-01-23 03:12:34.025620: step: 1732/529, loss: 0.020427893847227097
2023-01-23 03:12:35.172233: step: 1736/529, loss: 0.013141060248017311
2023-01-23 03:12:36.287268: step: 1740/529, loss: 0.002741909120231867
2023-01-23 03:12:37.418557: step: 1744/529, loss: 0.016582680866122246
2023-01-23 03:12:38.521995: step: 1748/529, loss: 0.007382869720458984
2023-01-23 03:12:39.639851: step: 1752/529, loss: 0.00027446745662018657
2023-01-23 03:12:40.766777: step: 1756/529, loss: 0.010853147134184837
2023-01-23 03:12:41.866897: step: 1760/529, loss: 0.07315180450677872
2023-01-23 03:12:42.979969: step: 1764/529, loss: 0.004629040136933327
2023-01-23 03:12:44.086066: step: 1768/529, loss: 0.0005635261768475175
2023-01-23 03:12:45.180750: step: 1772/529, loss: 0.00105199811514467
2023-01-23 03:12:46.309172: step: 1776/529, loss: 0.0004665374872274697
2023-01-23 03:12:47.427533: step: 1780/529, loss: 0.0010008811950683594
2023-01-23 03:12:48.526458: step: 1784/529, loss: 0.0030444145668298006
2023-01-23 03:12:49.635786: step: 1788/529, loss: 0.021874619647860527
2023-01-23 03:12:50.765143: step: 1792/529, loss: 0.0029835226014256477
2023-01-23 03:12:51.867957: step: 1796/529, loss: 0.008694648742675781
2023-01-23 03:12:52.974706: step: 1800/529, loss: 0.00028266909066587687
2023-01-23 03:12:54.087657: step: 1804/529, loss: 0.0015039443969726562
2023-01-23 03:12:55.242167: step: 1808/529, loss: 0.00198268867097795
2023-01-23 03:12:56.334558: step: 1812/529, loss: 0.0007439613691531122
2023-01-23 03:12:57.412903: step: 1816/529, loss: 0.0008378028869628906
2023-01-23 03:12:58.504229: step: 1820/529, loss: 0.00011162758164573461
2023-01-23 03:12:59.595812: step: 1824/529, loss: 0.0003180503845214844
2023-01-23 03:13:00.700806: step: 1828/529, loss: 0.051531314849853516
2023-01-23 03:13:01.811962: step: 1832/529, loss: 0.019864464178681374
2023-01-23 03:13:02.946658: step: 1836/529, loss: 0.008056068792939186
2023-01-23 03:13:04.063455: step: 1840/529, loss: 0.11192789673805237
2023-01-23 03:13:05.169969: step: 1844/529, loss: 0.0037076950538903475
2023-01-23 03:13:06.297561: step: 1848/529, loss: 0.04940738528966904
2023-01-23 03:13:07.406134: step: 1852/529, loss: 0.006371498107910156
2023-01-23 03:13:08.549234: step: 1856/529, loss: 0.3699088990688324
2023-01-23 03:13:09.664546: step: 1860/529, loss: 3.0517576306010596e-06
2023-01-23 03:13:10.753645: step: 1864/529, loss: 4.0483475459041074e-05
2023-01-23 03:13:11.859803: step: 1868/529, loss: 0.00414695730432868
2023-01-23 03:13:12.960140: step: 1872/529, loss: 0.00820924062281847
2023-01-23 03:13:14.066293: step: 1876/529, loss: 0.2512439787387848
2023-01-23 03:13:15.177513: step: 1880/529, loss: 0.02620558813214302
2023-01-23 03:13:16.315139: step: 1884/529, loss: 0.05309629440307617
2023-01-23 03:13:17.413147: step: 1888/529, loss: 0.10921745747327805
2023-01-23 03:13:18.523607: step: 1892/529, loss: 0.0004646301094908267
2023-01-23 03:13:19.638718: step: 1896/529, loss: 0.11730308830738068
2023-01-23 03:13:20.738617: step: 1900/529, loss: 0.010869168676435947
2023-01-23 03:13:21.868557: step: 1904/529, loss: 0.04337196424603462
2023-01-23 03:13:22.994650: step: 1908/529, loss: 0.003235435578972101
2023-01-23 03:13:24.108307: step: 1912/529, loss: 0.00013227463932707906
2023-01-23 03:13:25.228380: step: 1916/529, loss: 0.018679238855838776
2023-01-23 03:13:26.345236: step: 1920/529, loss: 6.599426706088707e-05
2023-01-23 03:13:27.447828: step: 1924/529, loss: 0.3135354816913605
2023-01-23 03:13:28.549361: step: 1928/529, loss: 0.0017744064098224044
2023-01-23 03:13:29.670423: step: 1932/529, loss: 0.044943057000637054
2023-01-23 03:13:30.791229: step: 1936/529, loss: 0.0017619132995605469
2023-01-23 03:13:31.910332: step: 1940/529, loss: 0.06216239929199219
2023-01-23 03:13:33.028819: step: 1944/529, loss: 0.0032334327697753906
2023-01-23 03:13:34.129894: step: 1948/529, loss: 0.003442192217335105
2023-01-23 03:13:35.213987: step: 1952/529, loss: 0.006398964207619429
2023-01-23 03:13:36.333178: step: 1956/529, loss: 0.011774063110351562
2023-01-23 03:13:37.436455: step: 1960/529, loss: 0.012065314687788486
2023-01-23 03:13:38.546868: step: 1964/529, loss: 0.7654058337211609
2023-01-23 03:13:39.654506: step: 1968/529, loss: 0.0014257431030273438
2023-01-23 03:13:40.785103: step: 1972/529, loss: 0.0005074501386843622
2023-01-23 03:13:41.897146: step: 1976/529, loss: 0.0012655259342864156
2023-01-23 03:13:42.995277: step: 1980/529, loss: 0.0024993896950036287
2023-01-23 03:13:44.089231: step: 1984/529, loss: 0.008470725268125534
2023-01-23 03:13:45.201755: step: 1988/529, loss: 0.0005449295276775956
2023-01-23 03:13:46.335456: step: 1992/529, loss: 0.002991199493408203
2023-01-23 03:13:47.459134: step: 1996/529, loss: 1.0204315003647935e-05
2023-01-23 03:13:48.566316: step: 2000/529, loss: 0.025909423828125
2023-01-23 03:13:49.653044: step: 2004/529, loss: 0.0010359763400629163
2023-01-23 03:13:50.753442: step: 2008/529, loss: 0.01930256001651287
2023-01-23 03:13:51.875609: step: 2012/529, loss: 0.013964653015136719
2023-01-23 03:13:52.968671: step: 2016/529, loss: 0.01030054036527872
2023-01-23 03:13:54.048986: step: 2020/529, loss: 0.00588755588978529
2023-01-23 03:13:55.156604: step: 2024/529, loss: 5.5122378398664296e-05
2023-01-23 03:13:56.256995: step: 2028/529, loss: 0.010770846158266068
2023-01-23 03:13:57.357943: step: 2032/529, loss: 0.0028553009033203125
2023-01-23 03:13:58.475590: step: 2036/529, loss: 0.010937022976577282
2023-01-23 03:13:59.560152: step: 2040/529, loss: 0.27414292097091675
2023-01-23 03:14:00.645854: step: 2044/529, loss: 3.9482114516431466e-05
2023-01-23 03:14:01.749599: step: 2048/529, loss: 0.38262826204299927
2023-01-23 03:14:02.857723: step: 2052/529, loss: 0.0010560035007074475
2023-01-23 03:14:03.968537: step: 2056/529, loss: 0.0007604121929034591
2023-01-23 03:14:05.096736: step: 2060/529, loss: 0.004108143039047718
2023-01-23 03:14:06.224499: step: 2064/529, loss: 0.016538048163056374
2023-01-23 03:14:07.342585: step: 2068/529, loss: 0.005854463670402765
2023-01-23 03:14:08.435871: step: 2072/529, loss: 0.013224029913544655
2023-01-23 03:14:09.529969: step: 2076/529, loss: 0.03184051439166069
2023-01-23 03:14:10.648941: step: 2080/529, loss: 0.009176159277558327
2023-01-23 03:14:11.774511: step: 2084/529, loss: 0.0009187221294268966
2023-01-23 03:14:12.881128: step: 2088/529, loss: 0.00248298654332757
2023-01-23 03:14:13.982386: step: 2092/529, loss: 0.007567978464066982
2023-01-23 03:14:15.085632: step: 2096/529, loss: 0.004356956575065851
2023-01-23 03:14:16.182398: step: 2100/529, loss: 0.07182197272777557
2023-01-23 03:14:17.287892: step: 2104/529, loss: 0.021478915587067604
2023-01-23 03:14:18.386731: step: 2108/529, loss: 0.006385231390595436
2023-01-23 03:14:19.523792: step: 2112/529, loss: 1.024275779724121
2023-01-23 03:14:20.639603: step: 2116/529, loss: 0.026096520945429802
==================================================
Loss: 0.027
--------------------
Dev: {'event': {'p': 0.6094929881337648, 'r': 0.7523302263648469, 'f1': 0.6734207389749702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6587263004375303, 'r': 0.7646726862302483, 'f1': 0.7077565944110733}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5568181818181818, 'r': 0.9074074074074074, 'f1': 0.6901408450704225}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.6153846153846154, 'r': 0.5079365079365079, 'f1': 0.5565217391304348}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.38461538461538464, 'r': 0.4166666666666667, 'f1': 0.4}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 03:15:00.137125: step: 4/529, loss: 4.901886131847277e-05
2023-01-23 03:15:01.228958: step: 8/529, loss: 0.0004726409970317036
2023-01-23 03:15:02.336666: step: 12/529, loss: 0.0005843162653036416
2023-01-23 03:15:03.439647: step: 16/529, loss: 0.049048613756895065
2023-01-23 03:15:04.562760: step: 20/529, loss: 0.0026485442649573088
2023-01-23 03:15:05.709701: step: 24/529, loss: 0.0010603904956951737
2023-01-23 03:15:06.818188: step: 28/529, loss: 0.048999905586242676
2023-01-23 03:15:07.935753: step: 32/529, loss: 0.03976612165570259
2023-01-23 03:15:09.054421: step: 36/529, loss: 1.52587890625e-05
2023-01-23 03:15:10.141752: step: 40/529, loss: 8.912086923373863e-05
2023-01-23 03:15:11.272612: step: 44/529, loss: 0.0007578849908895791
2023-01-23 03:15:12.410377: step: 48/529, loss: 0.028232479467988014
2023-01-23 03:15:13.532970: step: 52/529, loss: 0.006174850277602673
2023-01-23 03:15:14.635589: step: 56/529, loss: 0.0016797066200524569
2023-01-23 03:15:15.770873: step: 60/529, loss: 0.002244377275928855
2023-01-23 03:15:16.885352: step: 64/529, loss: 0.005736160557717085
2023-01-23 03:15:17.976219: step: 68/529, loss: 0.0019905567169189453
2023-01-23 03:15:19.073140: step: 72/529, loss: 0.003225994063541293
2023-01-23 03:15:20.172651: step: 76/529, loss: 0.0010509968269616365
2023-01-23 03:15:21.291003: step: 80/529, loss: 0.003352546598762274
2023-01-23 03:15:22.398825: step: 84/529, loss: 0.004018831066787243
2023-01-23 03:15:23.489363: step: 88/529, loss: 0.023929011076688766
2023-01-23 03:15:24.587141: step: 92/529, loss: 0.005522346589714289
2023-01-23 03:15:25.712483: step: 96/529, loss: 0.0014234542613849044
2023-01-23 03:15:26.829162: step: 100/529, loss: 0.027295876294374466
2023-01-23 03:15:27.939427: step: 104/529, loss: 0.012465191073715687
2023-01-23 03:15:29.087307: step: 108/529, loss: 0.005788040347397327
2023-01-23 03:15:30.194613: step: 112/529, loss: 0.03737945482134819
2023-01-23 03:15:31.328883: step: 116/529, loss: 0.019512368366122246
2023-01-23 03:15:32.424636: step: 120/529, loss: 0.0006292343605309725
2023-01-23 03:15:33.550072: step: 124/529, loss: 0.003832245012745261
2023-01-23 03:15:34.654130: step: 128/529, loss: 0.0006239890935830772
2023-01-23 03:15:35.786582: step: 132/529, loss: 0.00016345977201126516
2023-01-23 03:15:36.895395: step: 136/529, loss: 0.00896678026765585
2023-01-23 03:15:37.988054: step: 140/529, loss: 2.0694733393611386e-05
2023-01-23 03:15:39.095300: step: 144/529, loss: 0.0008705139043740928
2023-01-23 03:15:40.215182: step: 148/529, loss: 0.003926277160644531
2023-01-23 03:15:41.345260: step: 152/529, loss: 0.0008455276256427169
2023-01-23 03:15:42.458001: step: 156/529, loss: 0.0031423568725585938
2023-01-23 03:15:43.577082: step: 160/529, loss: 0.553687334060669
2023-01-23 03:15:44.678903: step: 164/529, loss: 0.0011714935535565019
2023-01-23 03:15:45.817629: step: 168/529, loss: 0.5581789016723633
2023-01-23 03:15:46.908148: step: 172/529, loss: 0.005222129635512829
2023-01-23 03:15:48.023018: step: 176/529, loss: 0.009992409497499466
2023-01-23 03:15:49.142182: step: 180/529, loss: 0.004883193876594305
2023-01-23 03:15:50.277557: step: 184/529, loss: 0.0013727188343182206
2023-01-23 03:15:51.382845: step: 188/529, loss: 0.009607887826859951
2023-01-23 03:15:52.467122: step: 192/529, loss: 0.00033283233642578125
2023-01-23 03:15:53.610801: step: 196/529, loss: 0.017383098602294922
2023-01-23 03:15:54.744763: step: 200/529, loss: 0.0001848220854299143
2023-01-23 03:15:55.859425: step: 204/529, loss: 9.93728608591482e-05
2023-01-23 03:15:56.959366: step: 208/529, loss: 0.0021793365012854338
2023-01-23 03:15:58.056124: step: 212/529, loss: 0.00042705534724518657
2023-01-23 03:15:59.172399: step: 216/529, loss: 0.3826066851615906
2023-01-23 03:16:00.299582: step: 220/529, loss: 0.26318082213401794
2023-01-23 03:16:01.404136: step: 224/529, loss: 9.231566946255043e-05
2023-01-23 03:16:02.515225: step: 228/529, loss: 0.0006345749134197831
2023-01-23 03:16:03.633121: step: 232/529, loss: 0.0035393715370446444
2023-01-23 03:16:04.772636: step: 236/529, loss: 0.07823028415441513
2023-01-23 03:16:05.883133: step: 240/529, loss: 0.0004249572812113911
2023-01-23 03:16:07.045080: step: 244/529, loss: 0.00012073517427779734
2023-01-23 03:16:08.199439: step: 248/529, loss: 3.82423386326991e-05
2023-01-23 03:16:09.300176: step: 252/529, loss: 0.00955276470631361
2023-01-23 03:16:10.384380: step: 256/529, loss: 0.00027799609233625233
2023-01-23 03:16:11.490095: step: 260/529, loss: 0.011612558737397194
2023-01-23 03:16:12.581517: step: 264/529, loss: 0.040853217244148254
2023-01-23 03:16:13.692261: step: 268/529, loss: 0.01077041681855917
2023-01-23 03:16:14.810717: step: 272/529, loss: 0.006834125611931086
2023-01-23 03:16:15.916180: step: 276/529, loss: 0.0014696121215820312
2023-01-23 03:16:17.039183: step: 280/529, loss: 0.0016334534157067537
2023-01-23 03:16:18.152554: step: 284/529, loss: 0.0001579284726176411
2023-01-23 03:16:19.300494: step: 288/529, loss: 0.00015726090350653976
2023-01-23 03:16:20.423700: step: 292/529, loss: 0.004276657477021217
2023-01-23 03:16:21.518168: step: 296/529, loss: 3.5762786865234375e-06
2023-01-23 03:16:22.631837: step: 300/529, loss: 0.014804649166762829
2023-01-23 03:16:23.720899: step: 304/529, loss: 0.024490738287568092
2023-01-23 03:16:24.850422: step: 308/529, loss: 0.0019912063144147396
2023-01-23 03:16:25.966525: step: 312/529, loss: 0.1300937682390213
2023-01-23 03:16:27.094908: step: 316/529, loss: 0.002980518387630582
2023-01-23 03:16:28.184410: step: 320/529, loss: 0.023563861846923828
2023-01-23 03:16:29.291342: step: 324/529, loss: 4.3106076191179454e-05
2023-01-23 03:16:30.419674: step: 328/529, loss: 0.0004907608381472528
2023-01-23 03:16:31.517576: step: 332/529, loss: 0.010013771243393421
2023-01-23 03:16:32.633640: step: 336/529, loss: 0.0009902477031573653
2023-01-23 03:16:33.727964: step: 340/529, loss: 0.41364210844039917
2023-01-23 03:16:34.841759: step: 344/529, loss: 3.1948089599609375e-05
2023-01-23 03:16:35.936832: step: 348/529, loss: 0.002775049302726984
2023-01-23 03:16:37.022075: step: 352/529, loss: 0.0022239687386900187
2023-01-23 03:16:38.123253: step: 356/529, loss: 0.015602302737534046
2023-01-23 03:16:39.251960: step: 360/529, loss: 0.08141651004552841
2023-01-23 03:16:40.372502: step: 364/529, loss: 0.0009212494478560984
2023-01-23 03:16:41.472244: step: 368/529, loss: 0.1698707640171051
2023-01-23 03:16:42.550161: step: 372/529, loss: 0.013544559478759766
2023-01-23 03:16:43.638499: step: 376/529, loss: 0.0018564224010333419
2023-01-23 03:16:44.781712: step: 380/529, loss: 1.583099401614163e-05
2023-01-23 03:16:45.893825: step: 384/529, loss: 0.010606384836137295
2023-01-23 03:16:46.986511: step: 388/529, loss: 0.0024221420753747225
2023-01-23 03:16:48.092420: step: 392/529, loss: 0.0005651474348269403
2023-01-23 03:16:49.199440: step: 396/529, loss: 0.0028150558937340975
2023-01-23 03:16:50.317625: step: 400/529, loss: 0.001256752060726285
2023-01-23 03:16:51.433614: step: 404/529, loss: 0.002836036728695035
2023-01-23 03:16:52.547374: step: 408/529, loss: 2.326965295651462e-05
2023-01-23 03:16:53.656339: step: 412/529, loss: 0.005748748779296875
2023-01-23 03:16:54.725982: step: 416/529, loss: 4.9400332500226796e-05
2023-01-23 03:16:55.870720: step: 420/529, loss: 0.00025959016056731343
2023-01-23 03:16:56.995466: step: 424/529, loss: 0.006981086917221546
2023-01-23 03:16:58.084655: step: 428/529, loss: 0.00010318756540073082
2023-01-23 03:16:59.170041: step: 432/529, loss: 0.0007403373601846397
2023-01-23 03:17:00.320413: step: 436/529, loss: 0.03095264546573162
2023-01-23 03:17:01.413433: step: 440/529, loss: 0.04470587149262428
2023-01-23 03:17:02.500309: step: 444/529, loss: 0.0004709243949037045
2023-01-23 03:17:03.605203: step: 448/529, loss: 0.007936859503388405
2023-01-23 03:17:04.687028: step: 452/529, loss: 8.668900409247726e-05
2023-01-23 03:17:05.781325: step: 456/529, loss: 0.0007596969953738153
2023-01-23 03:17:06.886026: step: 460/529, loss: 0.003589821048080921
2023-01-23 03:17:08.018078: step: 464/529, loss: 0.0002636909484863281
2023-01-23 03:17:09.116711: step: 468/529, loss: 0.04603540897369385
2023-01-23 03:17:10.228626: step: 472/529, loss: 0.024915315210819244
2023-01-23 03:17:11.326680: step: 476/529, loss: 0.012034988962113857
2023-01-23 03:17:12.431888: step: 480/529, loss: 0.02733173407614231
2023-01-23 03:17:13.514521: step: 484/529, loss: 0.03851928561925888
2023-01-23 03:17:14.631906: step: 488/529, loss: 0.015702057629823685
2023-01-23 03:17:15.745947: step: 492/529, loss: 0.0033882143907248974
2023-01-23 03:17:16.841341: step: 496/529, loss: 0.0029401779174804688
2023-01-23 03:17:17.955578: step: 500/529, loss: 0.009630394168198109
2023-01-23 03:17:19.082107: step: 504/529, loss: 0.026005173102021217
2023-01-23 03:17:20.192519: step: 508/529, loss: 0.00022544861712958664
2023-01-23 03:17:21.309874: step: 512/529, loss: 0.0009356499067507684
2023-01-23 03:17:22.447466: step: 516/529, loss: 0.0028443813789635897
2023-01-23 03:17:23.544009: step: 520/529, loss: 0.008927345275878906
2023-01-23 03:17:24.634640: step: 524/529, loss: 0.0003406524483580142
2023-01-23 03:17:25.734768: step: 528/529, loss: 0.00324764265678823
2023-01-23 03:17:26.863775: step: 532/529, loss: 0.007606315892189741
2023-01-23 03:17:27.965828: step: 536/529, loss: 0.19162806868553162
2023-01-23 03:17:29.084285: step: 540/529, loss: 0.004835891537368298
2023-01-23 03:17:30.178257: step: 544/529, loss: 0.0001619339018361643
2023-01-23 03:17:31.288141: step: 548/529, loss: 0.6177568435668945
2023-01-23 03:17:32.399328: step: 552/529, loss: 0.012438583187758923
2023-01-23 03:17:33.537685: step: 556/529, loss: 0.2524687349796295
2023-01-23 03:17:34.655587: step: 560/529, loss: 0.0002919197140727192
2023-01-23 03:17:35.731751: step: 564/529, loss: 0.0002232074912171811
2023-01-23 03:17:36.811276: step: 568/529, loss: 0.0011180877918377519
2023-01-23 03:17:37.929915: step: 572/529, loss: 0.009082472883164883
2023-01-23 03:17:39.024751: step: 576/529, loss: 0.0005714416620321572
2023-01-23 03:17:40.210277: step: 580/529, loss: 2.155303991457913e-05
2023-01-23 03:17:41.330300: step: 584/529, loss: 8.897780935512856e-05
2023-01-23 03:17:42.464690: step: 588/529, loss: 0.0023399353958666325
2023-01-23 03:17:43.621428: step: 592/529, loss: 0.24765463173389435
2023-01-23 03:17:44.739338: step: 596/529, loss: 0.22901973128318787
2023-01-23 03:17:45.851937: step: 600/529, loss: 0.01999054104089737
2023-01-23 03:17:46.955287: step: 604/529, loss: 2.460479663568549e-05
2023-01-23 03:17:48.087112: step: 608/529, loss: 0.004704666323959827
2023-01-23 03:17:49.186915: step: 612/529, loss: 0.007064437959343195
2023-01-23 03:17:50.293564: step: 616/529, loss: 0.0025806427001953125
2023-01-23 03:17:51.407282: step: 620/529, loss: 0.00015382767014671117
2023-01-23 03:17:52.516146: step: 624/529, loss: 0.007519149221479893
2023-01-23 03:17:53.610781: step: 628/529, loss: 0.0013467789394780993
2023-01-23 03:17:54.693793: step: 632/529, loss: 0.0016680718399584293
2023-01-23 03:17:55.777492: step: 636/529, loss: 2.784729076665826e-05
2023-01-23 03:17:56.863472: step: 640/529, loss: 0.002814328530803323
2023-01-23 03:17:58.002475: step: 644/529, loss: 0.005088615696877241
2023-01-23 03:17:59.136601: step: 648/529, loss: 1.8596649169921875e-05
2023-01-23 03:18:00.253093: step: 652/529, loss: 0.01365804672241211
2023-01-23 03:18:01.357520: step: 656/529, loss: 0.015225409530103207
2023-01-23 03:18:02.443386: step: 660/529, loss: 0.0418458953499794
2023-01-23 03:18:03.535258: step: 664/529, loss: 0.0024587633088231087
2023-01-23 03:18:04.685502: step: 668/529, loss: 0.08581829071044922
2023-01-23 03:18:05.803523: step: 672/529, loss: 0.26394766569137573
2023-01-23 03:18:06.930994: step: 676/529, loss: 0.0002870559983421117
2023-01-23 03:18:08.078197: step: 680/529, loss: 0.04272060468792915
2023-01-23 03:18:09.197284: step: 684/529, loss: 0.01952838897705078
2023-01-23 03:18:10.297971: step: 688/529, loss: 0.00015697479830123484
2023-01-23 03:18:11.409322: step: 692/529, loss: 0.004638290498405695
2023-01-23 03:18:12.515588: step: 696/529, loss: 0.0224138256162405
2023-01-23 03:18:13.623499: step: 700/529, loss: 4.6205521357478574e-05
2023-01-23 03:18:14.719750: step: 704/529, loss: 0.02264728583395481
2023-01-23 03:18:15.897232: step: 708/529, loss: 6.980895705055445e-05
2023-01-23 03:18:17.004356: step: 712/529, loss: 0.02875976637005806
2023-01-23 03:18:18.123368: step: 716/529, loss: 0.01690845564007759
2023-01-23 03:18:19.223313: step: 720/529, loss: 0.0027151107788085938
2023-01-23 03:18:20.320088: step: 724/529, loss: 5.617141869151965e-05
2023-01-23 03:18:21.419302: step: 728/529, loss: 0.0006729125743731856
2023-01-23 03:18:22.550698: step: 732/529, loss: 4.4298172724666074e-05
2023-01-23 03:18:23.663482: step: 736/529, loss: 0.007973956875503063
2023-01-23 03:18:24.810883: step: 740/529, loss: 0.00034084319486282766
2023-01-23 03:18:25.917459: step: 744/529, loss: 0.00021448136249091476
2023-01-23 03:18:27.026483: step: 748/529, loss: 0.020554019138216972
2023-01-23 03:18:28.127192: step: 752/529, loss: 3.814697265625e-05
2023-01-23 03:18:29.240336: step: 756/529, loss: 2.174377368646674e-05
2023-01-23 03:18:30.344889: step: 760/529, loss: 0.01640625111758709
2023-01-23 03:18:31.477534: step: 764/529, loss: 0.0030371665488928556
2023-01-23 03:18:32.624898: step: 768/529, loss: 0.006185627076774836
2023-01-23 03:18:33.735822: step: 772/529, loss: 0.005714702419936657
2023-01-23 03:18:34.817941: step: 776/529, loss: 3.5762786865234375e-05
2023-01-23 03:18:35.904118: step: 780/529, loss: 0.003929233644157648
2023-01-23 03:18:36.984038: step: 784/529, loss: 0.015489769168198109
2023-01-23 03:18:38.079022: step: 788/529, loss: 0.018300725147128105
2023-01-23 03:18:39.173564: step: 792/529, loss: 0.09302692860364914
2023-01-23 03:18:40.265783: step: 796/529, loss: 0.014369487762451172
2023-01-23 03:18:41.406164: step: 800/529, loss: 0.03820314630866051
2023-01-23 03:18:42.510809: step: 804/529, loss: 0.01919526979327202
2023-01-23 03:18:43.598732: step: 808/529, loss: 0.008376121520996094
2023-01-23 03:18:44.706135: step: 812/529, loss: 0.0006199836498126388
2023-01-23 03:18:45.838388: step: 816/529, loss: 0.008919382467865944
2023-01-23 03:18:46.978993: step: 820/529, loss: 0.0005117416149005294
2023-01-23 03:18:48.112988: step: 824/529, loss: 0.007665443699806929
2023-01-23 03:18:49.232721: step: 828/529, loss: 0.00035896303597837687
2023-01-23 03:18:50.366801: step: 832/529, loss: 0.015477752313017845
2023-01-23 03:18:51.461552: step: 836/529, loss: 0.003006553743034601
2023-01-23 03:18:52.608630: step: 840/529, loss: 0.0019371986854821444
2023-01-23 03:18:53.695937: step: 844/529, loss: 0.04035945236682892
2023-01-23 03:18:54.787710: step: 848/529, loss: 0.00023889541625976562
2023-01-23 03:18:55.910038: step: 852/529, loss: 7.877349707996473e-05
2023-01-23 03:18:57.036459: step: 856/529, loss: 0.14644727110862732
2023-01-23 03:18:58.168547: step: 860/529, loss: 3.147125244140625e-05
2023-01-23 03:18:59.314670: step: 864/529, loss: 0.005475949961692095
2023-01-23 03:19:00.417128: step: 868/529, loss: 0.004447365179657936
2023-01-23 03:19:01.533065: step: 872/529, loss: 0.019777726382017136
2023-01-23 03:19:02.630993: step: 876/529, loss: 0.00755462609231472
2023-01-23 03:19:03.742828: step: 880/529, loss: 0.0007345199701376259
2023-01-23 03:19:04.882507: step: 884/529, loss: 0.03260960429906845
2023-01-23 03:19:05.991064: step: 888/529, loss: 0.00593643169850111
2023-01-23 03:19:07.086118: step: 892/529, loss: 0.041945651173591614
2023-01-23 03:19:08.215579: step: 896/529, loss: 0.0018585205543786287
2023-01-23 03:19:09.322976: step: 900/529, loss: 0.018059730529785156
2023-01-23 03:19:10.398693: step: 904/529, loss: 0.004139136988669634
2023-01-23 03:19:11.506429: step: 908/529, loss: 0.0861610397696495
2023-01-23 03:19:12.611434: step: 912/529, loss: 0.0001224517764057964
2023-01-23 03:19:13.687633: step: 916/529, loss: 0.02920396439731121
2023-01-23 03:19:14.761409: step: 920/529, loss: 0.0016676902305334806
2023-01-23 03:19:15.862985: step: 924/529, loss: 0.00087738037109375
2023-01-23 03:19:16.954901: step: 928/529, loss: -2.3245811462402344e-06
2023-01-23 03:19:18.051679: step: 932/529, loss: 0.009790134616196156
2023-01-23 03:19:19.159029: step: 936/529, loss: 5.3405768994707614e-05
2023-01-23 03:19:20.251709: step: 940/529, loss: 0.0036839961539953947
2023-01-23 03:19:21.395119: step: 944/529, loss: 0.018985319882631302
2023-01-23 03:19:22.537440: step: 948/529, loss: 0.006720351986587048
2023-01-23 03:19:23.681095: step: 952/529, loss: 0.015435028821229935
2023-01-23 03:19:24.828631: step: 956/529, loss: 0.007334804628044367
2023-01-23 03:19:25.924677: step: 960/529, loss: 0.004056167788803577
2023-01-23 03:19:27.055055: step: 964/529, loss: 0.0017294883728027344
2023-01-23 03:19:28.159863: step: 968/529, loss: 0.008531475439667702
2023-01-23 03:19:29.269467: step: 972/529, loss: 0.0009712219471111894
2023-01-23 03:19:30.380252: step: 976/529, loss: 0.020585060119628906
2023-01-23 03:19:31.497979: step: 980/529, loss: 0.004735756199806929
2023-01-23 03:19:32.577902: step: 984/529, loss: 0.0003392219659872353
2023-01-23 03:19:33.692790: step: 988/529, loss: 0.11765418201684952
2023-01-23 03:19:34.787476: step: 992/529, loss: 0.0001665592280915007
2023-01-23 03:19:35.898008: step: 996/529, loss: 0.0006993294227868319
2023-01-23 03:19:37.016177: step: 1000/529, loss: 0.00245761894620955
2023-01-23 03:19:38.122813: step: 1004/529, loss: 0.002206802600994706
2023-01-23 03:19:39.225287: step: 1008/529, loss: 0.011037826538085938
2023-01-23 03:19:40.352324: step: 1012/529, loss: 0.0883277952671051
2023-01-23 03:19:41.445463: step: 1016/529, loss: 0.02365279383957386
2023-01-23 03:19:42.573253: step: 1020/529, loss: 0.0008777619223110378
2023-01-23 03:19:43.673298: step: 1024/529, loss: 0.0206924919039011
2023-01-23 03:19:44.813766: step: 1028/529, loss: 0.0024992942344397306
2023-01-23 03:19:45.931042: step: 1032/529, loss: 0.03853616863489151
2023-01-23 03:19:47.005289: step: 1036/529, loss: 0.021762752905488014
2023-01-23 03:19:48.121294: step: 1040/529, loss: 0.0027247429825365543
2023-01-23 03:19:49.248400: step: 1044/529, loss: 0.047234728932380676
2023-01-23 03:19:50.360108: step: 1048/529, loss: 0.0011034011840820312
2023-01-23 03:19:51.455910: step: 1052/529, loss: 0.00025615692720748484
2023-01-23 03:19:52.603423: step: 1056/529, loss: 0.0006631851429119706
2023-01-23 03:19:53.711487: step: 1060/529, loss: 0.019662827253341675
2023-01-23 03:19:54.835891: step: 1064/529, loss: 0.03680616617202759
2023-01-23 03:19:55.956706: step: 1068/529, loss: 0.0013397217262536287
2023-01-23 03:19:57.064773: step: 1072/529, loss: 5.130767749506049e-05
2023-01-23 03:19:58.205659: step: 1076/529, loss: 0.00908365286886692
2023-01-23 03:19:59.320771: step: 1080/529, loss: 0.026836395263671875
2023-01-23 03:20:00.425461: step: 1084/529, loss: 0.018147969618439674
2023-01-23 03:20:01.558561: step: 1088/529, loss: 0.0041119991801679134
2023-01-23 03:20:02.697532: step: 1092/529, loss: 0.00146064767614007
2023-01-23 03:20:03.808233: step: 1096/529, loss: 0.011078167706727982
2023-01-23 03:20:04.921734: step: 1100/529, loss: 0.007022762671113014
2023-01-23 03:20:06.040897: step: 1104/529, loss: 0.004471206571906805
2023-01-23 03:20:07.121555: step: 1108/529, loss: 0.004838466644287109
2023-01-23 03:20:08.244931: step: 1112/529, loss: 0.001230430556461215
2023-01-23 03:20:09.381781: step: 1116/529, loss: 0.00297126779332757
2023-01-23 03:20:10.493466: step: 1120/529, loss: 0.0006961346371099353
2023-01-23 03:20:11.602430: step: 1124/529, loss: 0.050437163561582565
2023-01-23 03:20:12.718815: step: 1128/529, loss: 0.014729499816894531
2023-01-23 03:20:13.848883: step: 1132/529, loss: 0.00025882720365189016
2023-01-23 03:20:14.931745: step: 1136/529, loss: 0.0005743026849813759
2023-01-23 03:20:16.062932: step: 1140/529, loss: 0.04766368865966797
2023-01-23 03:20:17.151322: step: 1144/529, loss: 0.004402542021125555
2023-01-23 03:20:18.254810: step: 1148/529, loss: 0.029987763613462448
2023-01-23 03:20:19.387363: step: 1152/529, loss: 4.38690185546875e-05
2023-01-23 03:20:20.514618: step: 1156/529, loss: 0.00021882056898903102
2023-01-23 03:20:21.633366: step: 1160/529, loss: 0.0006704330444335938
2023-01-23 03:20:22.752063: step: 1164/529, loss: 0.0028752328362315893
2023-01-23 03:20:23.851142: step: 1168/529, loss: 0.00045638083247467875
2023-01-23 03:20:24.945539: step: 1172/529, loss: 0.054761506617069244
2023-01-23 03:20:26.059377: step: 1176/529, loss: 0.02462015114724636
2023-01-23 03:20:27.186053: step: 1180/529, loss: 0.0006656170007772744
2023-01-23 03:20:28.297543: step: 1184/529, loss: 0.002207088517025113
2023-01-23 03:20:29.409387: step: 1188/529, loss: 0.02447948418557644
2023-01-23 03:20:30.558012: step: 1192/529, loss: 0.3125797212123871
2023-01-23 03:20:31.669529: step: 1196/529, loss: 0.0005607605562545359
2023-01-23 03:20:32.755192: step: 1200/529, loss: 0.0037145614624023438
2023-01-23 03:20:33.872265: step: 1204/529, loss: 0.0024746896233409643
2023-01-23 03:20:34.997648: step: 1208/529, loss: 0.029154395684599876
2023-01-23 03:20:36.102398: step: 1212/529, loss: 0.017415069043636322
2023-01-23 03:20:37.247828: step: 1216/529, loss: 0.0004466056707315147
2023-01-23 03:20:38.358183: step: 1220/529, loss: 0.003207397647202015
2023-01-23 03:20:39.499943: step: 1224/529, loss: 0.0042174337431788445
2023-01-23 03:20:40.629077: step: 1228/529, loss: 0.017203141003847122
2023-01-23 03:20:41.717184: step: 1232/529, loss: 0.00029935839120298624
2023-01-23 03:20:42.846970: step: 1236/529, loss: 0.037312984466552734
2023-01-23 03:20:43.941287: step: 1240/529, loss: 0.006142330355942249
2023-01-23 03:20:45.042998: step: 1244/529, loss: 0.004630709066987038
2023-01-23 03:20:46.135721: step: 1248/529, loss: 0.004734516143798828
2023-01-23 03:20:47.234451: step: 1252/529, loss: 0.013993168249726295
2023-01-23 03:20:48.335464: step: 1256/529, loss: 0.01038427371531725
2023-01-23 03:20:49.482509: step: 1260/529, loss: 0.0028164866380393505
2023-01-23 03:20:50.610028: step: 1264/529, loss: 0.005387067794799805
2023-01-23 03:20:51.702986: step: 1268/529, loss: 0.011713218875229359
2023-01-23 03:20:52.803800: step: 1272/529, loss: 0.00017104149446822703
2023-01-23 03:20:53.896560: step: 1276/529, loss: 0.009637641720473766
2023-01-23 03:20:55.026334: step: 1280/529, loss: 3.643035961431451e-05
2023-01-23 03:20:56.106839: step: 1284/529, loss: 0.00011596679541980848
2023-01-23 03:20:57.205175: step: 1288/529, loss: 0.0003276825009379536
2023-01-23 03:20:58.323001: step: 1292/529, loss: 0.009432983584702015
2023-01-23 03:20:59.409865: step: 1296/529, loss: 0.0001576423819642514
2023-01-23 03:21:00.510192: step: 1300/529, loss: 0.0010855287546291947
2023-01-23 03:21:01.653082: step: 1304/529, loss: 0.02320423163473606
2023-01-23 03:21:02.783369: step: 1308/529, loss: 0.008127403445541859
2023-01-23 03:21:03.882230: step: 1312/529, loss: 0.0034690857864916325
2023-01-23 03:21:04.986658: step: 1316/529, loss: 0.09195423126220703
2023-01-23 03:21:06.072211: step: 1320/529, loss: 0.0010787963401526213
2023-01-23 03:21:07.190819: step: 1324/529, loss: 6.580352783203125e-05
2023-01-23 03:21:08.287798: step: 1328/529, loss: 3.223419116693549e-05
2023-01-23 03:21:09.404869: step: 1332/529, loss: 0.01861104927957058
2023-01-23 03:21:10.517781: step: 1336/529, loss: 0.03626365587115288
2023-01-23 03:21:11.629695: step: 1340/529, loss: 0.0009206772083416581
2023-01-23 03:21:12.749258: step: 1344/529, loss: 0.003135064383968711
2023-01-23 03:21:13.858448: step: 1348/529, loss: 0.00027303697424940765
2023-01-23 03:21:14.950758: step: 1352/529, loss: 0.027225017547607422
2023-01-23 03:21:16.037519: step: 1356/529, loss: 0.002821683883666992
2023-01-23 03:21:17.171477: step: 1360/529, loss: 0.00284061417914927
2023-01-23 03:21:18.280347: step: 1364/529, loss: 0.003860569093376398
2023-01-23 03:21:19.390993: step: 1368/529, loss: 0.026370812207460403
2023-01-23 03:21:20.519172: step: 1372/529, loss: 0.009623098187148571
2023-01-23 03:21:21.602110: step: 1376/529, loss: 0.02466106414794922
2023-01-23 03:21:22.717930: step: 1380/529, loss: 0.0011364937527105212
2023-01-23 03:21:23.806575: step: 1384/529, loss: 0.01477899495512247
2023-01-23 03:21:24.893651: step: 1388/529, loss: 0.005523490719497204
2023-01-23 03:21:25.973212: step: 1392/529, loss: 0.0035267830826342106
2023-01-23 03:21:27.043739: step: 1396/529, loss: 1.583099401614163e-05
2023-01-23 03:21:28.144465: step: 1400/529, loss: 0.006800174713134766
2023-01-23 03:21:29.245170: step: 1404/529, loss: 0.48850059509277344
2023-01-23 03:21:30.380220: step: 1408/529, loss: 0.0010370254749432206
2023-01-23 03:21:31.480503: step: 1412/529, loss: 7.247924258990679e-06
2023-01-23 03:21:32.611371: step: 1416/529, loss: 0.00026645659818314016
2023-01-23 03:21:33.758722: step: 1420/529, loss: 0.009211158379912376
2023-01-23 03:21:34.861761: step: 1424/529, loss: 0.0007445812225341797
2023-01-23 03:21:35.992156: step: 1428/529, loss: 6.86645489622606e-06
2023-01-23 03:21:37.109895: step: 1432/529, loss: 0.028753947466611862
2023-01-23 03:21:38.238074: step: 1436/529, loss: 0.00615768413990736
2023-01-23 03:21:39.333949: step: 1440/529, loss: 0.004310321994125843
2023-01-23 03:21:40.419141: step: 1444/529, loss: 0.0011844635009765625
2023-01-23 03:21:41.527128: step: 1448/529, loss: 0.009363938122987747
2023-01-23 03:21:42.633062: step: 1452/529, loss: 0.0027895928360521793
2023-01-23 03:21:43.756705: step: 1456/529, loss: 0.007210922427475452
2023-01-23 03:21:44.830569: step: 1460/529, loss: 0.004180908203125
2023-01-23 03:21:45.939017: step: 1464/529, loss: 0.0015493392711505294
2023-01-23 03:21:47.057164: step: 1468/529, loss: 0.0043792724609375
2023-01-23 03:21:48.165738: step: 1472/529, loss: 0.0038200379349291325
2023-01-23 03:21:49.250986: step: 1476/529, loss: 0.014241695404052734
2023-01-23 03:21:50.347824: step: 1480/529, loss: 0.008434867486357689
2023-01-23 03:21:51.458056: step: 1484/529, loss: 0.00013966560072731227
2023-01-23 03:21:52.597565: step: 1488/529, loss: 7.324219041038305e-05
2023-01-23 03:21:53.713628: step: 1492/529, loss: 0.008545302785933018
2023-01-23 03:21:54.809825: step: 1496/529, loss: 0.12751750648021698
2023-01-23 03:21:55.926182: step: 1500/529, loss: 0.029554177075624466
2023-01-23 03:21:57.058030: step: 1504/529, loss: 0.009050941094756126
2023-01-23 03:21:58.171015: step: 1508/529, loss: 0.027750778943300247
2023-01-23 03:21:59.277114: step: 1512/529, loss: 0.0012173652648925781
2023-01-23 03:22:00.413214: step: 1516/529, loss: 0.014473533257842064
2023-01-23 03:22:01.524562: step: 1520/529, loss: 0.0008525848388671875
2023-01-23 03:22:02.639511: step: 1524/529, loss: 0.0025352477096021175
2023-01-23 03:22:03.763475: step: 1528/529, loss: 0.2877357602119446
2023-01-23 03:22:04.869287: step: 1532/529, loss: 0.0002552032528910786
2023-01-23 03:22:05.996339: step: 1536/529, loss: 0.011604405008256435
2023-01-23 03:22:07.080050: step: 1540/529, loss: 0.0034202574752271175
2023-01-23 03:22:08.193802: step: 1544/529, loss: 0.063776396214962
2023-01-23 03:22:09.326767: step: 1548/529, loss: 0.01563110388815403
2023-01-23 03:22:10.468914: step: 1552/529, loss: 0.03626823425292969
2023-01-23 03:22:11.580072: step: 1556/529, loss: 0.10788936913013458
2023-01-23 03:22:12.698832: step: 1560/529, loss: 0.0006166458479128778
2023-01-23 03:22:13.834705: step: 1564/529, loss: 0.00020904542179778218
2023-01-23 03:22:14.931989: step: 1568/529, loss: 0.0024717331398278475
2023-01-23 03:22:16.060644: step: 1572/529, loss: 0.00015592575073242188
2023-01-23 03:22:17.210016: step: 1576/529, loss: 0.0013476371532306075
2023-01-23 03:22:18.301663: step: 1580/529, loss: 0.0695217102766037
2023-01-23 03:22:19.412531: step: 1584/529, loss: 0.04180781915783882
2023-01-23 03:22:20.516033: step: 1588/529, loss: 0.0023132325150072575
2023-01-23 03:22:21.635734: step: 1592/529, loss: 0.0003120899200439453
2023-01-23 03:22:22.769949: step: 1596/529, loss: 0.006851578131318092
2023-01-23 03:22:23.879733: step: 1600/529, loss: 0.010571003891527653
2023-01-23 03:22:25.001101: step: 1604/529, loss: 0.07600346207618713
2023-01-23 03:22:26.148716: step: 1608/529, loss: 0.05953731760382652
2023-01-23 03:22:27.248116: step: 1612/529, loss: 0.0007984161493368447
2023-01-23 03:22:28.339984: step: 1616/529, loss: 0.0001522690145066008
2023-01-23 03:22:29.434060: step: 1620/529, loss: 2.040863000729587e-05
2023-01-23 03:22:30.556793: step: 1624/529, loss: 0.0011659623123705387
2023-01-23 03:22:31.637539: step: 1628/529, loss: 0.00942907389253378
2023-01-23 03:22:32.734587: step: 1632/529, loss: 0.0026019096840173006
2023-01-23 03:22:33.855344: step: 1636/529, loss: 0.014038706198334694
2023-01-23 03:22:34.960363: step: 1640/529, loss: 0.0005350112915039062
2023-01-23 03:22:36.047485: step: 1644/529, loss: 4.720688230008818e-05
2023-01-23 03:22:37.164900: step: 1648/529, loss: 0.00210914621129632
2023-01-23 03:22:38.276800: step: 1652/529, loss: 0.005322504322975874
2023-01-23 03:22:39.351984: step: 1656/529, loss: 0.02371368370950222
2023-01-23 03:22:40.457434: step: 1660/529, loss: 0.00985736958682537
2023-01-23 03:22:41.545766: step: 1664/529, loss: 0.026445960626006126
2023-01-23 03:22:42.680694: step: 1668/529, loss: 0.0037639616057276726
2023-01-23 03:22:43.781788: step: 1672/529, loss: 0.017408180981874466
2023-01-23 03:22:44.910053: step: 1676/529, loss: 0.0005366325494833291
2023-01-23 03:22:46.049465: step: 1680/529, loss: 0.030685901641845703
2023-01-23 03:22:47.188465: step: 1684/529, loss: 0.034714438021183014
2023-01-23 03:22:48.299364: step: 1688/529, loss: 0.00029416085453704
2023-01-23 03:22:49.394242: step: 1692/529, loss: 0.0002092361537506804
2023-01-23 03:22:50.485588: step: 1696/529, loss: 0.0003733634948730469
2023-01-23 03:22:51.605888: step: 1700/529, loss: 0.044469740241765976
2023-01-23 03:22:52.717240: step: 1704/529, loss: 0.022730302065610886
2023-01-23 03:22:53.866554: step: 1708/529, loss: 0.00975952111184597
2023-01-23 03:22:54.978283: step: 1712/529, loss: 0.004509353544563055
2023-01-23 03:22:56.098767: step: 1716/529, loss: 0.022693252190947533
2023-01-23 03:22:57.194615: step: 1720/529, loss: 0.0021711348090320826
2023-01-23 03:22:58.315457: step: 1724/529, loss: 0.05210094898939133
2023-01-23 03:22:59.434800: step: 1728/529, loss: 0.03552999347448349
2023-01-23 03:23:00.526321: step: 1732/529, loss: 0.0009191512945108116
2023-01-23 03:23:01.653706: step: 1736/529, loss: 0.013871765695512295
2023-01-23 03:23:02.771024: step: 1740/529, loss: 1.697540210443549e-05
2023-01-23 03:23:03.869205: step: 1744/529, loss: 0.0002285003720317036
2023-01-23 03:23:04.968996: step: 1748/529, loss: 0.04652118682861328
2023-01-23 03:23:06.068947: step: 1752/529, loss: 0.002030658768489957
2023-01-23 03:23:07.196552: step: 1756/529, loss: 1.36113703250885
2023-01-23 03:23:08.310353: step: 1760/529, loss: 0.007953738793730736
2023-01-23 03:23:09.419992: step: 1764/529, loss: 2.8419495720299892e-05
2023-01-23 03:23:10.557375: step: 1768/529, loss: 0.023436356335878372
2023-01-23 03:23:11.708481: step: 1772/529, loss: 0.034502413123846054
2023-01-23 03:23:12.842945: step: 1776/529, loss: 0.04574594646692276
2023-01-23 03:23:13.951182: step: 1780/529, loss: 0.002615261124446988
2023-01-23 03:23:15.074192: step: 1784/529, loss: 0.004746842198073864
2023-01-23 03:23:16.194362: step: 1788/529, loss: 0.01699981838464737
2023-01-23 03:23:17.332129: step: 1792/529, loss: 0.050270941108465195
2023-01-23 03:23:18.439476: step: 1796/529, loss: 0.0001127243012888357
2023-01-23 03:23:19.550285: step: 1800/529, loss: 0.016205977648496628
2023-01-23 03:23:20.669157: step: 1804/529, loss: 0.0032377243041992188
2023-01-23 03:23:21.783277: step: 1808/529, loss: 0.005022430792450905
2023-01-23 03:23:22.890227: step: 1812/529, loss: 0.01888890378177166
2023-01-23 03:23:23.987006: step: 1816/529, loss: 0.015808487311005592
2023-01-23 03:23:25.069184: step: 1820/529, loss: 9.91821252682712e-06
2023-01-23 03:23:26.227884: step: 1824/529, loss: 0.0036518098786473274
2023-01-23 03:23:27.335397: step: 1828/529, loss: 0.016133643686771393
2023-01-23 03:23:28.454734: step: 1832/529, loss: 0.00464673014357686
2023-01-23 03:23:29.554646: step: 1836/529, loss: 0.004633140750229359
2023-01-23 03:23:30.652374: step: 1840/529, loss: 0.000640869140625
2023-01-23 03:23:31.768737: step: 1844/529, loss: 0.023274803534150124
2023-01-23 03:23:32.864936: step: 1848/529, loss: 0.009393502026796341
2023-01-23 03:23:33.955656: step: 1852/529, loss: 0.02821226231753826
2023-01-23 03:23:35.080198: step: 1856/529, loss: 0.001249122666195035
2023-01-23 03:23:36.236630: step: 1860/529, loss: 0.020393753424286842
2023-01-23 03:23:37.390451: step: 1864/529, loss: 0.046022988855838776
2023-01-23 03:23:38.488532: step: 1868/529, loss: 0.016793441027402878
2023-01-23 03:23:39.565616: step: 1872/529, loss: 0.001484871027059853
2023-01-23 03:23:40.682958: step: 1876/529, loss: 0.002045535948127508
2023-01-23 03:23:41.796819: step: 1880/529, loss: 0.009863662533462048
2023-01-23 03:23:42.940870: step: 1884/529, loss: 0.04506435617804527
2023-01-23 03:23:44.068603: step: 1888/529, loss: 0.011983584612607956
2023-01-23 03:23:45.173483: step: 1892/529, loss: 0.07662144303321838
2023-01-23 03:23:46.275620: step: 1896/529, loss: 0.0010465621016919613
2023-01-23 03:23:47.347744: step: 1900/529, loss: 0.0026866437401622534
2023-01-23 03:23:48.440715: step: 1904/529, loss: 0.01636953465640545
2023-01-23 03:23:49.554012: step: 1908/529, loss: 0.0008162498706951737
2023-01-23 03:23:50.648103: step: 1912/529, loss: 0.13790854811668396
2023-01-23 03:23:51.731417: step: 1916/529, loss: 0.00020818710618186742
2023-01-23 03:23:52.850351: step: 1920/529, loss: 0.0005504608270712197
2023-01-23 03:23:53.957449: step: 1924/529, loss: 0.008896350860595703
2023-01-23 03:23:55.058484: step: 1928/529, loss: 0.0002675056457519531
2023-01-23 03:23:56.174612: step: 1932/529, loss: 0.0005533218500204384
2023-01-23 03:23:57.271221: step: 1936/529, loss: 0.00042896269587799907
2023-01-23 03:23:58.426789: step: 1940/529, loss: 0.014613008126616478
2023-01-23 03:23:59.547475: step: 1944/529, loss: 0.004792308900505304
2023-01-23 03:24:00.642359: step: 1948/529, loss: 0.005675888154655695
2023-01-23 03:24:01.747979: step: 1952/529, loss: 0.013755322434008121
2023-01-23 03:24:02.849491: step: 1956/529, loss: 0.00043594837188720703
2023-01-23 03:24:03.960129: step: 1960/529, loss: 0.012760925106704235
2023-01-23 03:24:05.057912: step: 1964/529, loss: 9.32693510549143e-05
2023-01-23 03:24:06.157295: step: 1968/529, loss: 0.001598787377588451
2023-01-23 03:24:07.307904: step: 1972/529, loss: 0.01162738911807537
2023-01-23 03:24:08.440039: step: 1976/529, loss: 0.0074347020126879215
2023-01-23 03:24:09.535768: step: 1980/529, loss: 0.00021009446936659515
2023-01-23 03:24:10.673755: step: 1984/529, loss: 0.0006614684825763106
2023-01-23 03:24:11.752945: step: 1988/529, loss: 0.0036611557006835938
2023-01-23 03:24:12.875299: step: 1992/529, loss: 0.009977913461625576
2023-01-23 03:24:13.968854: step: 1996/529, loss: 0.022965241223573685
2023-01-23 03:24:15.083794: step: 2000/529, loss: 4.76837158203125e-05
2023-01-23 03:24:16.198245: step: 2004/529, loss: 0.036416102200746536
2023-01-23 03:24:17.291257: step: 2008/529, loss: 0.012509727850556374
2023-01-23 03:24:18.405756: step: 2012/529, loss: 0.00040836335392668843
2023-01-23 03:24:19.495670: step: 2016/529, loss: 2.861023403966101e-06
2023-01-23 03:24:20.645163: step: 2020/529, loss: 0.0002965927415061742
2023-01-23 03:24:21.763279: step: 2024/529, loss: 0.08842658996582031
2023-01-23 03:24:22.915722: step: 2028/529, loss: 0.0011669158702716231
2023-01-23 03:24:24.003794: step: 2032/529, loss: 0.00984115619212389
2023-01-23 03:24:25.129872: step: 2036/529, loss: 0.00340442662127316
2023-01-23 03:24:26.219479: step: 2040/529, loss: 0.0038094522897154093
2023-01-23 03:24:27.360629: step: 2044/529, loss: 0.0007734298706054688
2023-01-23 03:24:28.462434: step: 2048/529, loss: 0.0006843566661700606
2023-01-23 03:24:29.562992: step: 2052/529, loss: 0.00023689270892646164
2023-01-23 03:24:30.654969: step: 2056/529, loss: 0.00010099411883857101
2023-01-23 03:24:31.766931: step: 2060/529, loss: 2.708435022213962e-05
2023-01-23 03:24:32.874033: step: 2064/529, loss: 0.0001605987490620464
2023-01-23 03:24:33.984392: step: 2068/529, loss: 0.006698036100715399
2023-01-23 03:24:35.120442: step: 2072/529, loss: 0.005943012423813343
2023-01-23 03:24:36.267480: step: 2076/529, loss: 0.02304706536233425
2023-01-23 03:24:37.385719: step: 2080/529, loss: 0.09497890621423721
2023-01-23 03:24:38.529324: step: 2084/529, loss: 0.0004995345952920616
2023-01-23 03:24:39.641562: step: 2088/529, loss: 0.012242508120834827
2023-01-23 03:24:40.730315: step: 2092/529, loss: 0.018155433237552643
2023-01-23 03:24:41.811300: step: 2096/529, loss: 0.0022264004219323397
2023-01-23 03:24:42.911007: step: 2100/529, loss: 0.03890056908130646
2023-01-23 03:24:44.023691: step: 2104/529, loss: 0.014135170727968216
2023-01-23 03:24:45.120063: step: 2108/529, loss: 7.99179106252268e-05
2023-01-23 03:24:46.221411: step: 2112/529, loss: 1.6307831174344756e-05
2023-01-23 03:24:47.315104: step: 2116/529, loss: 0.004066276364028454
==================================================
Loss: 0.024
--------------------
Dev: {'event': {'p': 0.5803212851405622, 'r': 0.7696404793608522, 'f1': 0.661705781339439}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6334106728538283, 'r': 0.7703160270880361, 'f1': 0.6951871657754011}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.550561797752809, 'r': 0.9074074074074074, 'f1': 0.6853146853146853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.5079365079365079, 'f1': 0.5378151260504201}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
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': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 23
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:25:27.528136: step: 4/529, loss: 0.0002883911074604839
2023-01-23 03:25:28.651465: step: 8/529, loss: 0.03681345283985138
2023-01-23 03:25:29.761600: step: 12/529, loss: 0.0006464004400186241
2023-01-23 03:25:30.869846: step: 16/529, loss: 0.006453132722526789
2023-01-23 03:25:31.990596: step: 20/529, loss: 0.0021348954178392887
2023-01-23 03:25:33.136949: step: 24/529, loss: 0.0010612488258630037
2023-01-23 03:25:34.221408: step: 28/529, loss: 0.013253974728286266
2023-01-23 03:25:35.318902: step: 32/529, loss: 9.374618821311742e-05
2023-01-23 03:25:36.411527: step: 36/529, loss: 0.013882351107895374
2023-01-23 03:25:37.546216: step: 40/529, loss: 0.00047893525334075093
2023-01-23 03:25:38.653491: step: 44/529, loss: 0.0007560729864053428
2023-01-23 03:25:39.759496: step: 48/529, loss: 0.0011245727073401213
2023-01-23 03:25:40.840656: step: 52/529, loss: 0.004950141999870539
2023-01-23 03:25:41.977548: step: 56/529, loss: 3.4332279028603807e-06
2023-01-23 03:25:43.161493: step: 60/529, loss: 1.0315948724746704
2023-01-23 03:25:44.286629: step: 64/529, loss: 0.050814438611269
2023-01-23 03:25:45.413219: step: 68/529, loss: 0.0006988048553466797
2023-01-23 03:25:46.518598: step: 72/529, loss: 0.0038265229668468237
2023-01-23 03:25:47.615516: step: 76/529, loss: 0.00022995471954345703
2023-01-23 03:25:48.749314: step: 80/529, loss: 0.0007982254028320312
2023-01-23 03:25:49.879838: step: 84/529, loss: 6.103516170696821e-06
2023-01-23 03:25:50.960777: step: 88/529, loss: 7.581710815429688e-05
2023-01-23 03:25:52.102401: step: 92/529, loss: 0.0014209747314453125
2023-01-23 03:25:53.223662: step: 96/529, loss: 0.00044593808706849813
2023-01-23 03:25:54.332471: step: 100/529, loss: 0.0033233645372092724
2023-01-23 03:25:55.467412: step: 104/529, loss: 0.00080108642578125
2023-01-23 03:25:56.570396: step: 108/529, loss: 0.03795995935797691
2023-01-23 03:25:57.681043: step: 112/529, loss: 0.020905114710330963
2023-01-23 03:25:58.773150: step: 116/529, loss: 0.0023916244972497225
2023-01-23 03:25:59.883476: step: 120/529, loss: 0.00012936592975165695
2023-01-23 03:26:00.999731: step: 124/529, loss: 0.0007274627569131553
2023-01-23 03:26:02.120003: step: 128/529, loss: 0.012909985147416592
2023-01-23 03:26:03.214749: step: 132/529, loss: 0.00016303063603118062
2023-01-23 03:26:04.335794: step: 136/529, loss: 0.03207588195800781
2023-01-23 03:26:05.429642: step: 140/529, loss: 0.00023555755615234375
2023-01-23 03:26:06.545141: step: 144/529, loss: 0.00034775736276060343
2023-01-23 03:26:07.669397: step: 148/529, loss: 0.0015834808582440019
2023-01-23 03:26:08.786074: step: 152/529, loss: 0.0014513017376884818
2023-01-23 03:26:09.919174: step: 156/529, loss: 0.0654090866446495
2023-01-23 03:26:11.028543: step: 160/529, loss: 0.0019367217319086194
2023-01-23 03:26:12.150153: step: 164/529, loss: 0.03619079664349556
2023-01-23 03:26:13.290365: step: 168/529, loss: 0.03627815470099449
2023-01-23 03:26:14.404464: step: 172/529, loss: 0.00168952951207757
2023-01-23 03:26:15.515348: step: 176/529, loss: 0.00041542056715115905
2023-01-23 03:26:16.603396: step: 180/529, loss: 0.0015731812454760075
2023-01-23 03:26:17.709988: step: 184/529, loss: 0.010916901752352715
2023-01-23 03:26:18.787855: step: 188/529, loss: 0.054041292518377304
2023-01-23 03:26:19.887849: step: 192/529, loss: 0.018085859715938568
2023-01-23 03:26:21.022766: step: 196/529, loss: 0.035671282559633255
2023-01-23 03:26:22.122800: step: 200/529, loss: 0.05806489288806915
2023-01-23 03:26:23.251390: step: 204/529, loss: 0.0025993348099291325
2023-01-23 03:26:24.330464: step: 208/529, loss: 3.6239625842426904e-06
2023-01-23 03:26:25.437580: step: 212/529, loss: 0.0005254745483398438
2023-01-23 03:26:26.556891: step: 216/529, loss: 0.004301833920180798
2023-01-23 03:26:27.683846: step: 220/529, loss: 0.0010030746925622225
2023-01-23 03:26:28.775771: step: 224/529, loss: 1.9073486328125e-06
2023-01-23 03:26:29.898674: step: 228/529, loss: 0.06467180699110031
2023-01-23 03:26:31.010886: step: 232/529, loss: 0.004024696536362171
2023-01-23 03:26:32.119135: step: 236/529, loss: 0.006682396400719881
2023-01-23 03:26:33.204139: step: 240/529, loss: 0.0002454012574162334
2023-01-23 03:26:34.286205: step: 244/529, loss: 0.00267715472728014
2023-01-23 03:26:35.415778: step: 248/529, loss: 0.012624263763427734
2023-01-23 03:26:36.570454: step: 252/529, loss: 0.00028333664522506297
2023-01-23 03:26:37.656330: step: 256/529, loss: 0.034265995025634766
2023-01-23 03:26:38.768161: step: 260/529, loss: 6.12258882028982e-05
2023-01-23 03:26:39.857899: step: 264/529, loss: 8.745193190407008e-05
2023-01-23 03:26:40.979850: step: 268/529, loss: 0.03480052947998047
2023-01-23 03:26:42.077444: step: 272/529, loss: 0.003998184110969305
2023-01-23 03:26:43.165035: step: 276/529, loss: 0.012942028231918812
2023-01-23 03:26:44.289117: step: 280/529, loss: 0.009005356580018997
2023-01-23 03:26:45.398550: step: 284/529, loss: 0.02213153801858425
2023-01-23 03:26:46.509745: step: 288/529, loss: 0.000880813633557409
2023-01-23 03:26:47.600754: step: 292/529, loss: 0.0037752152420580387
2023-01-23 03:26:48.731832: step: 296/529, loss: 0.0006952285766601562
2023-01-23 03:26:49.851357: step: 300/529, loss: 4.129410081077367e-05
2023-01-23 03:26:50.964641: step: 304/529, loss: 0.0005508422618731856
2023-01-23 03:26:52.099829: step: 308/529, loss: 0.058629799634218216
2023-01-23 03:26:53.230908: step: 312/529, loss: 0.017781639471650124
2023-01-23 03:26:54.313850: step: 316/529, loss: 0.0012475013500079513
2023-01-23 03:26:55.446865: step: 320/529, loss: 2.2459029423771426e-05
2023-01-23 03:26:56.534833: step: 324/529, loss: 0.02574281580746174
2023-01-23 03:26:57.646113: step: 328/529, loss: 0.0009464264148846269
2023-01-23 03:26:58.763518: step: 332/529, loss: 0.01752842217683792
2023-01-23 03:26:59.866914: step: 336/529, loss: 0.10592098534107208
2023-01-23 03:27:00.970582: step: 340/529, loss: 0.006802177522331476
2023-01-23 03:27:02.112992: step: 344/529, loss: 0.00028142929659225047
2023-01-23 03:27:03.230851: step: 348/529, loss: 0.03823566436767578
2023-01-23 03:27:04.337306: step: 352/529, loss: 0.0006147384410724044
2023-01-23 03:27:05.467733: step: 356/529, loss: 0.00023174287343863398
2023-01-23 03:27:06.588407: step: 360/529, loss: 0.00016736984252929688
2023-01-23 03:27:07.697259: step: 364/529, loss: 0.010930824093520641
2023-01-23 03:27:08.821383: step: 368/529, loss: 0.002102422760799527
2023-01-23 03:27:09.957324: step: 372/529, loss: 0.0004864692746195942
2023-01-23 03:27:11.078943: step: 376/529, loss: 0.006289339158684015
2023-01-23 03:27:12.253009: step: 380/529, loss: 0.003525686217471957
2023-01-23 03:27:13.369618: step: 384/529, loss: 0.003340149065479636
2023-01-23 03:27:14.471246: step: 388/529, loss: 0.0002739906485658139
2023-01-23 03:27:15.610967: step: 392/529, loss: 0.023203223943710327
2023-01-23 03:27:16.717536: step: 396/529, loss: 0.0090522775426507
2023-01-23 03:27:17.793499: step: 400/529, loss: 0.000854110752698034
2023-01-23 03:27:18.896051: step: 404/529, loss: 0.00061883928719908
2023-01-23 03:27:20.000002: step: 408/529, loss: 0.0019355774857103825
2023-01-23 03:27:21.122066: step: 412/529, loss: 0.005366802215576172
2023-01-23 03:27:22.210626: step: 416/529, loss: 0.028545141220092773
2023-01-23 03:27:23.367613: step: 420/529, loss: 0.003251934191212058
2023-01-23 03:27:24.442524: step: 424/529, loss: 0.00029354094294831157
2023-01-23 03:27:25.565875: step: 428/529, loss: 0.005344772711396217
2023-01-23 03:27:26.670439: step: 432/529, loss: 0.0008024215931072831
2023-01-23 03:27:27.755223: step: 436/529, loss: 0.03718223795294762
2023-01-23 03:27:28.906786: step: 440/529, loss: 0.43041613698005676
2023-01-23 03:27:30.011441: step: 444/529, loss: 0.001266944338567555
2023-01-23 03:27:31.135841: step: 448/529, loss: 0.004234886262565851
2023-01-23 03:27:32.266320: step: 452/529, loss: 0.003745937254279852
2023-01-23 03:27:33.397076: step: 456/529, loss: 0.008444547653198242
2023-01-23 03:27:34.504022: step: 460/529, loss: 0.00043907167855650187
2023-01-23 03:27:35.617005: step: 464/529, loss: 0.00045180320739746094
2023-01-23 03:27:36.722606: step: 468/529, loss: 7.42912307032384e-05
2023-01-23 03:27:37.851181: step: 472/529, loss: 0.0066436766646802425
2023-01-23 03:27:38.951997: step: 476/529, loss: 0.02650442160665989
2023-01-23 03:27:40.076724: step: 480/529, loss: 0.00038185121957212687
2023-01-23 03:27:41.166276: step: 484/529, loss: 0.0009094238630495965
2023-01-23 03:27:42.299367: step: 488/529, loss: 0.0017925500869750977
2023-01-23 03:27:43.407331: step: 492/529, loss: 0.0003252029709983617
2023-01-23 03:27:44.506065: step: 496/529, loss: 0.006175899412482977
2023-01-23 03:27:45.626535: step: 500/529, loss: 0.001824235892854631
2023-01-23 03:27:46.710998: step: 504/529, loss: 0.00011224746413063258
2023-01-23 03:27:47.765817: step: 508/529, loss: 0.00032939910306595266
2023-01-23 03:27:48.906323: step: 512/529, loss: 0.0002157211274607107
2023-01-23 03:27:50.006362: step: 516/529, loss: 0.0014985561138018966
2023-01-23 03:27:51.133740: step: 520/529, loss: 0.00955963134765625
2023-01-23 03:27:52.232458: step: 524/529, loss: 0.006502533331513405
2023-01-23 03:27:53.345998: step: 528/529, loss: 0.07747097313404083
2023-01-23 03:27:54.475390: step: 532/529, loss: 2.5224686396541074e-05
2023-01-23 03:27:55.581318: step: 536/529, loss: 0.008847285062074661
2023-01-23 03:27:56.701305: step: 540/529, loss: 0.011590957641601562
2023-01-23 03:27:57.807321: step: 544/529, loss: 0.00023403167142532766
2023-01-23 03:27:58.926127: step: 548/529, loss: 0.00014133454533293843
2023-01-23 03:28:00.014476: step: 552/529, loss: 0.0001375198335153982
2023-01-23 03:28:01.115572: step: 556/529, loss: 0.0002899169921875
2023-01-23 03:28:02.214793: step: 560/529, loss: 0.012487697415053844
2023-01-23 03:28:03.330345: step: 564/529, loss: 0.010420609265565872
2023-01-23 03:28:04.443060: step: 568/529, loss: 7.028579420875758e-05
2023-01-23 03:28:05.537282: step: 572/529, loss: 0.049776457250118256
2023-01-23 03:28:06.650063: step: 576/529, loss: 0.00022802352032158524
2023-01-23 03:28:07.736789: step: 580/529, loss: 9.822845640883315e-06
2023-01-23 03:28:08.817781: step: 584/529, loss: 0.0054267882369458675
2023-01-23 03:28:09.941603: step: 588/529, loss: 0.04016227647662163
2023-01-23 03:28:11.078098: step: 592/529, loss: 5.340576535672881e-05
2023-01-23 03:28:12.178733: step: 596/529, loss: 0.003691291669383645
2023-01-23 03:28:13.270261: step: 600/529, loss: 0.0008340835920535028
2023-01-23 03:28:14.371902: step: 604/529, loss: 0.00025072097196243703
2023-01-23 03:28:15.450493: step: 608/529, loss: 0.03420591354370117
2023-01-23 03:28:16.567769: step: 612/529, loss: 0.011543131433427334
2023-01-23 03:28:17.680536: step: 616/529, loss: 0.04497117921710014
2023-01-23 03:28:18.773835: step: 620/529, loss: 0.000164031982421875
2023-01-23 03:28:19.867185: step: 624/529, loss: 0.010802173987030983
2023-01-23 03:28:20.993367: step: 628/529, loss: 0.012547683902084827
2023-01-23 03:28:22.101931: step: 632/529, loss: 0.00019340515427757055
2023-01-23 03:28:23.255865: step: 636/529, loss: 0.0006591796991415322
2023-01-23 03:28:24.365394: step: 640/529, loss: 0.012115002609789371
2023-01-23 03:28:25.484189: step: 644/529, loss: 0.004157543648034334
2023-01-23 03:28:26.610894: step: 648/529, loss: 2.7179717108083423e-06
2023-01-23 03:28:27.791034: step: 652/529, loss: 0.03401994705200195
2023-01-23 03:28:28.902067: step: 656/529, loss: 8.58306884765625e-05
2023-01-23 03:28:30.043651: step: 660/529, loss: 0.003197288606315851
2023-01-23 03:28:31.166889: step: 664/529, loss: 0.055520057678222656
2023-01-23 03:28:32.256398: step: 668/529, loss: 0.01597623899579048
2023-01-23 03:28:33.342758: step: 672/529, loss: 0.06323447078466415
2023-01-23 03:28:34.445637: step: 676/529, loss: 2.0408631826285273e-05
2023-01-23 03:28:35.572543: step: 680/529, loss: 3.0517578125e-05
2023-01-23 03:28:36.684142: step: 684/529, loss: 0.03477153927087784
2023-01-23 03:28:37.788013: step: 688/529, loss: 8.378028724109754e-05
2023-01-23 03:28:38.949208: step: 692/529, loss: 0.0023954391945153475
2023-01-23 03:28:40.050774: step: 696/529, loss: 2.593994213384576e-05
2023-01-23 03:28:41.146512: step: 700/529, loss: 0.3161248564720154
2023-01-23 03:28:42.304050: step: 704/529, loss: 1.296997106692288e-05
2023-01-23 03:28:43.417644: step: 708/529, loss: 0.0002456665097270161
2023-01-23 03:28:44.498442: step: 712/529, loss: 0.0005173683166503906
2023-01-23 03:28:45.607245: step: 716/529, loss: 0.0027935027610510588
2023-01-23 03:28:46.702085: step: 720/529, loss: 0.009577560238540173
2023-01-23 03:28:47.843760: step: 724/529, loss: 0.0449712760746479
2023-01-23 03:28:48.947505: step: 728/529, loss: 0.006515884771943092
2023-01-23 03:28:50.051760: step: 732/529, loss: 0.00012111664545955136
2023-01-23 03:28:51.147145: step: 736/529, loss: 0.0007436752202920616
2023-01-23 03:28:52.229080: step: 740/529, loss: 0.005751228425651789
2023-01-23 03:28:53.357172: step: 744/529, loss: 0.012774658389389515
2023-01-23 03:28:54.483794: step: 748/529, loss: 0.015220833010971546
2023-01-23 03:28:55.570357: step: 752/529, loss: 0.005015754606574774
2023-01-23 03:28:56.699921: step: 756/529, loss: 0.0040826802141964436
2023-01-23 03:28:57.794151: step: 760/529, loss: 0.0005961417919024825
2023-01-23 03:28:58.892132: step: 764/529, loss: 0.0018270493019372225
2023-01-23 03:29:00.017609: step: 768/529, loss: 0.00012331009202171117
2023-01-23 03:29:01.105590: step: 772/529, loss: 0.018587494269013405
2023-01-23 03:29:02.200455: step: 776/529, loss: 0.00492439279332757
2023-01-23 03:29:03.323928: step: 780/529, loss: 0.00092992780264467
2023-01-23 03:29:04.431831: step: 784/529, loss: 0.0021121979225426912
2023-01-23 03:29:05.523854: step: 788/529, loss: 1.850128137448337e-05
2023-01-23 03:29:06.661954: step: 792/529, loss: -2.2411345526052173e-06
2023-01-23 03:29:07.763404: step: 796/529, loss: 0.00023880005755927414
2023-01-23 03:29:08.863024: step: 800/529, loss: 0.03480348363518715
2023-01-23 03:29:09.988590: step: 804/529, loss: -2.47955322265625e-05
2023-01-23 03:29:11.091234: step: 808/529, loss: 0.0057960511185228825
2023-01-23 03:29:12.213693: step: 812/529, loss: 0.0013547898270189762
2023-01-23 03:29:13.338169: step: 816/529, loss: 0.014643669128417969
2023-01-23 03:29:14.433873: step: 820/529, loss: 0.03941555321216583
2023-01-23 03:29:15.573352: step: 824/529, loss: 0.035974979400634766
2023-01-23 03:29:16.664891: step: 828/529, loss: 0.0013183593982830644
2023-01-23 03:29:17.785879: step: 832/529, loss: 0.0019962310325354338
2023-01-23 03:29:18.904621: step: 836/529, loss: 0.0009966850047931075
2023-01-23 03:29:20.007836: step: 840/529, loss: 0.0027654648292809725
2023-01-23 03:29:21.117203: step: 844/529, loss: 2.584457615739666e-05
2023-01-23 03:29:22.227994: step: 848/529, loss: 0.00047864916268736124
2023-01-23 03:29:23.331587: step: 852/529, loss: 0.0004040718195028603
2023-01-23 03:29:24.433092: step: 856/529, loss: 0.025358200073242188
2023-01-23 03:29:25.555015: step: 860/529, loss: 1.640319896978326e-05
2023-01-23 03:29:26.674014: step: 864/529, loss: 0.001890850136987865
2023-01-23 03:29:27.784570: step: 868/529, loss: 0.008761894889175892
2023-01-23 03:29:28.868463: step: 872/529, loss: 0.005912589840590954
2023-01-23 03:29:30.019853: step: 876/529, loss: 0.1778927743434906
2023-01-23 03:29:31.130903: step: 880/529, loss: 2.140998731192667e-05
2023-01-23 03:29:32.228830: step: 884/529, loss: 0.004208373837172985
2023-01-23 03:29:33.333756: step: 888/529, loss: 0.04290733486413956
2023-01-23 03:29:34.476695: step: 892/529, loss: 0.0015522956382483244
2023-01-23 03:29:35.594676: step: 896/529, loss: 0.0017154216766357422
2023-01-23 03:29:36.705133: step: 900/529, loss: 0.005001259036362171
2023-01-23 03:29:37.823063: step: 904/529, loss: 8.58306884765625e-05
2023-01-23 03:29:38.956360: step: 908/529, loss: 0.02731633186340332
2023-01-23 03:29:40.102561: step: 912/529, loss: 0.0008234024280682206
2023-01-23 03:29:41.201846: step: 916/529, loss: 0.0015952109824866056
2023-01-23 03:29:42.345570: step: 920/529, loss: 0.006677437108010054
2023-01-23 03:29:43.438140: step: 924/529, loss: 9.059906005859375e-06
2023-01-23 03:29:44.536702: step: 928/529, loss: 0.0006336212391033769
2023-01-23 03:29:45.699359: step: 932/529, loss: 0.007230567745864391
2023-01-23 03:29:46.824614: step: 936/529, loss: 0.0015255927573889494
2023-01-23 03:29:47.912328: step: 940/529, loss: 0.06697139889001846
2023-01-23 03:29:49.016323: step: 944/529, loss: 0.004878711886703968
2023-01-23 03:29:50.114911: step: 948/529, loss: 2.365112231927924e-05
2023-01-23 03:29:51.216630: step: 952/529, loss: 0.004432773683220148
2023-01-23 03:29:52.362152: step: 956/529, loss: 0.0011806488037109375
2023-01-23 03:29:53.461679: step: 960/529, loss: 0.011307192035019398
2023-01-23 03:29:54.585864: step: 964/529, loss: 0.003016758244484663
2023-01-23 03:29:55.696545: step: 968/529, loss: 0.05561990663409233
2023-01-23 03:29:56.799130: step: 972/529, loss: 0.053038597106933594
2023-01-23 03:29:57.901397: step: 976/529, loss: 0.0059722899459302425
2023-01-23 03:29:59.004431: step: 980/529, loss: 0.0032155991066247225
2023-01-23 03:30:00.100873: step: 984/529, loss: 0.0002642631880007684
2023-01-23 03:30:01.214215: step: 988/529, loss: 0.000899887119885534
2023-01-23 03:30:02.359654: step: 992/529, loss: 0.0380154624581337
2023-01-23 03:30:03.494222: step: 996/529, loss: 0.0031909942626953125
2023-01-23 03:30:04.629029: step: 1000/529, loss: 0.018430233001708984
2023-01-23 03:30:05.711616: step: 1004/529, loss: 0.004919052589684725
2023-01-23 03:30:06.845306: step: 1008/529, loss: 0.00019683838763739914
2023-01-23 03:30:07.933794: step: 1012/529, loss: 0.01740889437496662
2023-01-23 03:30:09.047661: step: 1016/529, loss: 0.008913611993193626
2023-01-23 03:30:10.153405: step: 1020/529, loss: 0.09894199669361115
2023-01-23 03:30:11.253642: step: 1024/529, loss: 0.03086087480187416
2023-01-23 03:30:12.371590: step: 1028/529, loss: 0.0005334853776730597
2023-01-23 03:30:13.448401: step: 1032/529, loss: 0.0055595398880541325
2023-01-23 03:30:14.568482: step: 1036/529, loss: 4.243851071805693e-05
2023-01-23 03:30:15.684422: step: 1040/529, loss: 0.008710193447768688
2023-01-23 03:30:16.804464: step: 1044/529, loss: 0.012061690911650658
2023-01-23 03:30:17.911745: step: 1048/529, loss: 0.00426902761682868
2023-01-23 03:30:19.019808: step: 1052/529, loss: 0.002290916396304965
2023-01-23 03:30:20.139990: step: 1056/529, loss: 0.0005729675758630037
2023-01-23 03:30:21.265117: step: 1060/529, loss: 0.005400658119469881
2023-01-23 03:30:22.345194: step: 1064/529, loss: 0.0010809899540618062
2023-01-23 03:30:23.446912: step: 1068/529, loss: 0.0001702308509266004
2023-01-23 03:30:24.553198: step: 1072/529, loss: 0.00017502308764960617
2023-01-23 03:30:25.667914: step: 1076/529, loss: 0.0005151748773641884
2023-01-23 03:30:26.790356: step: 1080/529, loss: 0.0039052963256835938
2023-01-23 03:30:27.919665: step: 1084/529, loss: 0.00012598038301803172
2023-01-23 03:30:29.020794: step: 1088/529, loss: 0.027127837762236595
2023-01-23 03:30:30.183028: step: 1092/529, loss: 0.029183007776737213
2023-01-23 03:30:31.291477: step: 1096/529, loss: 0.004023742862045765
2023-01-23 03:30:32.432060: step: 1100/529, loss: 0.0034817694686353207
2023-01-23 03:30:33.531383: step: 1104/529, loss: 0.0076423645950853825
2023-01-23 03:30:34.634470: step: 1108/529, loss: 0.00019702911959029734
2023-01-23 03:30:35.740972: step: 1112/529, loss: -2.441406286379788e-05
2023-01-23 03:30:36.872017: step: 1116/529, loss: 0.0019440650939941406
2023-01-23 03:30:37.964454: step: 1120/529, loss: 0.0003028869687113911
2023-01-23 03:30:39.063752: step: 1124/529, loss: 0.10020647197961807
2023-01-23 03:30:40.164476: step: 1128/529, loss: 0.04185142740607262
2023-01-23 03:30:41.254857: step: 1132/529, loss: 0.005414009094238281
2023-01-23 03:30:42.353490: step: 1136/529, loss: 0.0011066437000408769
2023-01-23 03:30:43.484155: step: 1140/529, loss: 0.000976133334916085
2023-01-23 03:30:44.608424: step: 1144/529, loss: 0.0117934700101614
2023-01-23 03:30:45.707229: step: 1148/529, loss: 0.013056183233857155
2023-01-23 03:30:46.815043: step: 1152/529, loss: 0.0009434462408535182
2023-01-23 03:30:47.921504: step: 1156/529, loss: 0.00021486282639671117
2023-01-23 03:30:49.044563: step: 1160/529, loss: 0.0484987273812294
2023-01-23 03:30:50.181310: step: 1164/529, loss: 0.035813476890325546
2023-01-23 03:30:51.275316: step: 1168/529, loss: 0.03295135498046875
2023-01-23 03:30:52.423539: step: 1172/529, loss: 0.0008213043329305947
2023-01-23 03:30:53.535861: step: 1176/529, loss: 0.0531865693628788
2023-01-23 03:30:54.629490: step: 1180/529, loss: 0.002627754118293524
2023-01-23 03:30:55.764706: step: 1184/529, loss: 0.12368451058864594
2023-01-23 03:30:56.864122: step: 1188/529, loss: 0.00022735596576239914
2023-01-23 03:30:57.986847: step: 1192/529, loss: 0.004833448212593794
2023-01-23 03:30:59.124457: step: 1196/529, loss: 0.029396915808320045
2023-01-23 03:31:00.253587: step: 1200/529, loss: 0.003652954241260886
2023-01-23 03:31:01.373734: step: 1204/529, loss: 3.894728660583496
2023-01-23 03:31:02.495749: step: 1208/529, loss: 0.0001337051362497732
2023-01-23 03:31:03.617121: step: 1212/529, loss: 0.0005608559004031122
2023-01-23 03:31:04.730842: step: 1216/529, loss: 0.0067729949951171875
2023-01-23 03:31:05.837860: step: 1220/529, loss: 0.044348813593387604
2023-01-23 03:31:06.931533: step: 1224/529, loss: 0.0035758973099291325
2023-01-23 03:31:08.028203: step: 1228/529, loss: 0.0009157180902548134
2023-01-23 03:31:09.146894: step: 1232/529, loss: 0.0061286925338208675
2023-01-23 03:31:10.223530: step: 1236/529, loss: 0.0019105911487713456
2023-01-23 03:31:11.319447: step: 1240/529, loss: 0.0036661147605627775
2023-01-23 03:31:12.415233: step: 1244/529, loss: 0.0006690978771075606
2023-01-23 03:31:13.550333: step: 1248/529, loss: 0.05568714439868927
2023-01-23 03:31:14.709115: step: 1252/529, loss: 0.021386336535215378
2023-01-23 03:31:15.817846: step: 1256/529, loss: 0.003376817563548684
2023-01-23 03:31:16.921850: step: 1260/529, loss: 0.0014566421741619706
2023-01-23 03:31:18.012060: step: 1264/529, loss: 0.00011391640873625875
2023-01-23 03:31:19.122617: step: 1268/529, loss: 0.001253414200618863
2023-01-23 03:31:20.250048: step: 1272/529, loss: 0.0007602691766805947
2023-01-23 03:31:21.354783: step: 1276/529, loss: 0.0004299640713725239
2023-01-23 03:31:22.465321: step: 1280/529, loss: 0.009141732007265091
2023-01-23 03:31:23.603938: step: 1284/529, loss: 0.09636344760656357
2023-01-23 03:31:24.716386: step: 1288/529, loss: 0.06481647491455078
2023-01-23 03:31:25.839508: step: 1292/529, loss: 0.002770710038021207
2023-01-23 03:31:26.972654: step: 1296/529, loss: 9.069443331100047e-05
2023-01-23 03:31:28.074927: step: 1300/529, loss: 0.018890762701630592
2023-01-23 03:31:29.153993: step: 1304/529, loss: 0.00021400452533271164
2023-01-23 03:31:30.282236: step: 1308/529, loss: 0.002646541688591242
2023-01-23 03:31:31.402455: step: 1312/529, loss: 0.0012115478748455644
2023-01-23 03:31:32.498778: step: 1316/529, loss: 0.0699225440621376
2023-01-23 03:31:33.603437: step: 1320/529, loss: 7.286072650458664e-05
2023-01-23 03:31:34.685100: step: 1324/529, loss: 0.05436668545007706
2023-01-23 03:31:35.768312: step: 1328/529, loss: 0.0004395008145365864
2023-01-23 03:31:36.879361: step: 1332/529, loss: 0.0006276130443438888
2023-01-23 03:31:37.976112: step: 1336/529, loss: 0.013247775845229626
2023-01-23 03:31:39.069132: step: 1340/529, loss: 0.0005140304565429688
2023-01-23 03:31:40.168211: step: 1344/529, loss: 0.0002480507246218622
2023-01-23 03:31:41.284892: step: 1348/529, loss: 0.0017969131004065275
2023-01-23 03:31:42.407352: step: 1352/529, loss: 0.0001752853422658518
2023-01-23 03:31:43.529378: step: 1356/529, loss: 0.0019431114196777344
2023-01-23 03:31:44.651574: step: 1360/529, loss: 0.008020590990781784
2023-01-23 03:31:45.762241: step: 1364/529, loss: 0.0009081840398721397
2023-01-23 03:31:46.886330: step: 1368/529, loss: 0.022505568340420723
2023-01-23 03:31:47.984702: step: 1372/529, loss: 2.365112231927924e-05
2023-01-23 03:31:49.093900: step: 1376/529, loss: 0.0006483554607257247
2023-01-23 03:31:50.217460: step: 1380/529, loss: 0.0015235661994665861
2023-01-23 03:31:51.355043: step: 1384/529, loss: 0.0006504058837890625
2023-01-23 03:31:52.462626: step: 1388/529, loss: 0.0016690255142748356
2023-01-23 03:31:53.577186: step: 1392/529, loss: 0.020243167877197266
2023-01-23 03:31:54.673402: step: 1396/529, loss: 0.0031223297119140625
2023-01-23 03:31:55.776311: step: 1400/529, loss: 0.0007585525745525956
2023-01-23 03:31:56.898631: step: 1404/529, loss: 0.0008188247447833419
2023-01-23 03:31:58.009355: step: 1408/529, loss: 1.52587890625e-05
2023-01-23 03:31:59.175249: step: 1412/529, loss: 0.000181102761416696
2023-01-23 03:32:00.286633: step: 1416/529, loss: 0.029534244909882545
2023-01-23 03:32:01.366621: step: 1420/529, loss: 0.0017442703247070312
2023-01-23 03:32:02.479768: step: 1424/529, loss: 0.027648448944091797
2023-01-23 03:32:03.609206: step: 1428/529, loss: 0.002980804303660989
2023-01-23 03:32:04.683605: step: 1432/529, loss: 1.8596649169921875e-05
2023-01-23 03:32:05.774839: step: 1436/529, loss: 0.0008102416759356856
2023-01-23 03:32:06.897295: step: 1440/529, loss: 0.00788583792746067
2023-01-23 03:32:08.006749: step: 1444/529, loss: 2.574920654296875e-05
2023-01-23 03:32:09.098852: step: 1448/529, loss: 0.00309278373606503
2023-01-23 03:32:10.221903: step: 1452/529, loss: 0.003055000212043524
2023-01-23 03:32:11.356568: step: 1456/529, loss: 0.0030759810470044613
2023-01-23 03:32:12.465880: step: 1460/529, loss: 0.009456634521484375
2023-01-23 03:32:13.579404: step: 1464/529, loss: 0.06446877121925354
2023-01-23 03:32:14.679300: step: 1468/529, loss: 0.00015506744966842234
2023-01-23 03:32:15.802474: step: 1472/529, loss: 0.026921462267637253
2023-01-23 03:32:16.919236: step: 1476/529, loss: 0.3829685151576996
2023-01-23 03:32:18.017762: step: 1480/529, loss: 7.04765334376134e-05
2023-01-23 03:32:19.137945: step: 1484/529, loss: 7.925033423816785e-05
2023-01-23 03:32:20.242022: step: 1488/529, loss: 0.03731689602136612
2023-01-23 03:32:21.339820: step: 1492/529, loss: 0.0006093978881835938
2023-01-23 03:32:22.437825: step: 1496/529, loss: 0.07322235405445099
2023-01-23 03:32:23.552600: step: 1500/529, loss: 0.065831758081913
2023-01-23 03:32:24.666473: step: 1504/529, loss: 0.0005354881286621094
2023-01-23 03:32:25.760105: step: 1508/529, loss: 0.0026178359985351562
2023-01-23 03:32:26.879958: step: 1512/529, loss: 0.11140112578868866
2023-01-23 03:32:27.993156: step: 1516/529, loss: 0.001960277557373047
2023-01-23 03:32:29.120285: step: 1520/529, loss: 0.700862467288971
2023-01-23 03:32:30.232496: step: 1524/529, loss: 0.0034385682083666325
2023-01-23 03:32:31.331452: step: 1528/529, loss: 0.022772978991270065
2023-01-23 03:32:32.455777: step: 1532/529, loss: 0.006360912229865789
2023-01-23 03:32:33.576506: step: 1536/529, loss: 1.8978118532686494e-05
2023-01-23 03:32:34.676119: step: 1540/529, loss: 0.00010452271089889109
2023-01-23 03:32:35.788534: step: 1544/529, loss: 0.013959693722426891
2023-01-23 03:32:36.912170: step: 1548/529, loss: 0.006504154298454523
2023-01-23 03:32:38.022430: step: 1552/529, loss: 0.045899201184511185
2023-01-23 03:32:39.135716: step: 1556/529, loss: 0.016573715955018997
2023-01-23 03:32:40.242858: step: 1560/529, loss: 0.002582299755886197
2023-01-23 03:32:41.344768: step: 1564/529, loss: 0.004678439814597368
2023-01-23 03:32:42.459745: step: 1568/529, loss: -4.00543194700731e-06
2023-01-23 03:32:43.584294: step: 1572/529, loss: 0.00033626556978560984
2023-01-23 03:32:44.672645: step: 1576/529, loss: 0.002205467317253351
2023-01-23 03:32:45.786951: step: 1580/529, loss: 0.0002117156982421875
2023-01-23 03:32:46.885425: step: 1584/529, loss: 1.52587890625e-05
2023-01-23 03:32:47.985038: step: 1588/529, loss: 0.0009866714244708419
2023-01-23 03:32:49.084733: step: 1592/529, loss: 0.023676397278904915
2023-01-23 03:32:50.212111: step: 1596/529, loss: 0.0067746639251708984
2023-01-23 03:32:51.323174: step: 1600/529, loss: 0.02019519731402397
2023-01-23 03:32:52.436060: step: 1604/529, loss: 0.04520416632294655
2023-01-23 03:32:53.556436: step: 1608/529, loss: 9.91821252682712e-06
2023-01-23 03:32:54.667769: step: 1612/529, loss: 0.0018724919063970447
2023-01-23 03:32:55.792268: step: 1616/529, loss: 0.01027293223887682
2023-01-23 03:32:56.950868: step: 1620/529, loss: 0.034696388989686966
2023-01-23 03:32:58.073836: step: 1624/529, loss: 0.022735213860869408
2023-01-23 03:32:59.198448: step: 1628/529, loss: 0.0034936906304210424
2023-01-23 03:33:00.315023: step: 1632/529, loss: 0.0008212804677896202
2023-01-23 03:33:01.423110: step: 1636/529, loss: 0.00149879464879632
2023-01-23 03:33:02.534853: step: 1640/529, loss: 0.09865227341651917
2023-01-23 03:33:03.665571: step: 1644/529, loss: 0.05509652942419052
2023-01-23 03:33:04.766079: step: 1648/529, loss: 0.0005855560302734375
2023-01-23 03:33:05.879641: step: 1652/529, loss: 0.0034090043045580387
2023-01-23 03:33:07.007097: step: 1656/529, loss: 0.0008191108936443925
2023-01-23 03:33:08.123690: step: 1660/529, loss: 0.0007898330804891884
2023-01-23 03:33:09.222010: step: 1664/529, loss: 0.007561827078461647
2023-01-23 03:33:10.342017: step: 1668/529, loss: 9.355545626021922e-05
2023-01-23 03:33:11.418474: step: 1672/529, loss: 0.0020486831199377775
2023-01-23 03:33:12.530253: step: 1676/529, loss: 0.0004220008850097656
2023-01-23 03:33:13.654436: step: 1680/529, loss: 0.0004980087978765368
2023-01-23 03:33:14.775807: step: 1684/529, loss: 2.47955322265625e-05
2023-01-23 03:33:15.872528: step: 1688/529, loss: 5.52177443751134e-05
2023-01-23 03:33:17.003096: step: 1692/529, loss: 0.000846219074446708
2023-01-23 03:33:18.137382: step: 1696/529, loss: 0.006716919131577015
2023-01-23 03:33:19.248366: step: 1700/529, loss: 0.000965118408203125
2023-01-23 03:33:20.335944: step: 1704/529, loss: 0.0015100479358807206
2023-01-23 03:33:21.455460: step: 1708/529, loss: 0.052350856363773346
2023-01-23 03:33:22.532186: step: 1712/529, loss: 0.0038344860076904297
2023-01-23 03:33:23.616340: step: 1716/529, loss: 0.0007698058616369963
2023-01-23 03:33:24.719203: step: 1720/529, loss: 0.005507374182343483
2023-01-23 03:33:25.785691: step: 1724/529, loss: 0.003798961639404297
2023-01-23 03:33:26.937969: step: 1728/529, loss: 0.0007230758783407509
2023-01-23 03:33:28.049667: step: 1732/529, loss: 0.0028829574584960938
2023-01-23 03:33:29.179628: step: 1736/529, loss: 4.224777512717992e-05
2023-01-23 03:33:30.292745: step: 1740/529, loss: 0.016884375363588333
2023-01-23 03:33:31.387790: step: 1744/529, loss: 0.01977691613137722
2023-01-23 03:33:32.517224: step: 1748/529, loss: 4.158019874012098e-05
2023-01-23 03:33:33.630426: step: 1752/529, loss: 0.00023193359083961695
2023-01-23 03:33:34.721075: step: 1756/529, loss: 0.00020713807316496968
2023-01-23 03:33:35.831174: step: 1760/529, loss: 0.013233184814453125
2023-01-23 03:33:36.951585: step: 1764/529, loss: 0.001970577286556363
2023-01-23 03:33:38.059371: step: 1768/529, loss: 0.01619892194867134
2023-01-23 03:33:39.170250: step: 1772/529, loss: 0.0009502411121502519
2023-01-23 03:33:40.285792: step: 1776/529, loss: 0.0692434310913086
2023-01-23 03:33:41.432883: step: 1780/529, loss: 0.008482170291244984
2023-01-23 03:33:42.539776: step: 1784/529, loss: 3.924369957530871e-05
2023-01-23 03:33:43.651966: step: 1788/529, loss: 0.00017886162095237523
2023-01-23 03:33:44.744503: step: 1792/529, loss: 0.0010334014659747481
2023-01-23 03:33:45.848182: step: 1796/529, loss: 9.34600848268019e-06
2023-01-23 03:33:46.942025: step: 1800/529, loss: 0.0004550933954305947
2023-01-23 03:33:48.045195: step: 1804/529, loss: 9.679795039119199e-05
2023-01-23 03:33:49.143690: step: 1808/529, loss: 0.019238758832216263
2023-01-23 03:33:50.253372: step: 1812/529, loss: 0.00070362095721066
2023-01-23 03:33:51.363067: step: 1816/529, loss: 0.0054340362548828125
2023-01-23 03:33:52.510334: step: 1820/529, loss: 0.00012798310490325093
2023-01-23 03:33:53.618813: step: 1824/529, loss: 3.566742088878527e-05
2023-01-23 03:33:54.717404: step: 1828/529, loss: 0.006403446197509766
2023-01-23 03:33:55.829595: step: 1832/529, loss: 0.08049946278333664
2023-01-23 03:33:56.978204: step: 1836/529, loss: 0.0001386404037475586
2023-01-23 03:33:58.093919: step: 1840/529, loss: 0.034163858741521835
2023-01-23 03:33:59.192824: step: 1844/529, loss: 0.01553115900605917
2023-01-23 03:34:00.298141: step: 1848/529, loss: 0.0001234054652741179
2023-01-23 03:34:01.413976: step: 1852/529, loss: 8.20159948489163e-06
2023-01-23 03:34:02.521083: step: 1856/529, loss: 0.0010892868740484118
2023-01-23 03:34:03.613261: step: 1860/529, loss: 0.0004696846008300781
2023-01-23 03:34:04.711902: step: 1864/529, loss: 0.00040454865666106343
2023-01-23 03:34:05.811312: step: 1868/529, loss: 0.0007097244379110634
2023-01-23 03:34:06.921028: step: 1872/529, loss: 0.0008018494118005037
2023-01-23 03:34:08.002018: step: 1876/529, loss: 0.007692813873291016
2023-01-23 03:34:09.101660: step: 1880/529, loss: 0.00024509429931640625
2023-01-23 03:34:10.193619: step: 1884/529, loss: 0.002017498016357422
2023-01-23 03:34:11.279316: step: 1888/529, loss: 0.002883243840187788
2023-01-23 03:34:12.397156: step: 1892/529, loss: 0.004039764404296875
2023-01-23 03:34:13.485789: step: 1896/529, loss: 0.04199400171637535
2023-01-23 03:34:14.614777: step: 1900/529, loss: 0.01093978900462389
2023-01-23 03:34:15.741604: step: 1904/529, loss: 0.0019046784145757556
2023-01-23 03:34:16.831694: step: 1908/529, loss: 0.006050693802535534
2023-01-23 03:34:17.910841: step: 1912/529, loss: 8.354186866199598e-05
2023-01-23 03:34:19.014717: step: 1916/529, loss: 0.0001407623349223286
2023-01-23 03:34:20.102802: step: 1920/529, loss: 1.182556115963962e-05
2023-01-23 03:34:21.235722: step: 1924/529, loss: 0.04809394106268883
2023-01-23 03:34:22.349362: step: 1928/529, loss: 0.02637319825589657
2023-01-23 03:34:23.465120: step: 1932/529, loss: 0.05322151258587837
2023-01-23 03:34:24.579977: step: 1936/529, loss: 0.12012310326099396
2023-01-23 03:34:25.680577: step: 1940/529, loss: 0.0001468658447265625
2023-01-23 03:34:26.799039: step: 1944/529, loss: 0.0003570556582417339
2023-01-23 03:34:27.894069: step: 1948/529, loss: 0.0027442933060228825
2023-01-23 03:34:28.984148: step: 1952/529, loss: 0.0007123947143554688
2023-01-23 03:34:30.087045: step: 1956/529, loss: 0.0002639770391397178
2023-01-23 03:34:31.197829: step: 1960/529, loss: 0.033715344965457916
2023-01-23 03:34:32.298243: step: 1964/529, loss: 0.00021018982806708664
2023-01-23 03:34:33.429583: step: 1968/529, loss: 0.0033559321891516447
2023-01-23 03:34:34.522859: step: 1972/529, loss: 0.0077040670439600945
2023-01-23 03:34:35.624899: step: 1976/529, loss: 0.006897187326103449
2023-01-23 03:34:36.709376: step: 1980/529, loss: 0.001946258475072682
2023-01-23 03:34:37.811352: step: 1984/529, loss: 0.022505760192871094
2023-01-23 03:34:38.931148: step: 1988/529, loss: 0.0010709763737395406
2023-01-23 03:34:40.098632: step: 1992/529, loss: 0.00034427642822265625
2023-01-23 03:34:41.227364: step: 1996/529, loss: 0.00024776457576081157
2023-01-23 03:34:42.342150: step: 2000/529, loss: 0.0005731582641601562
2023-01-23 03:34:43.450827: step: 2004/529, loss: 0.028496552258729935
2023-01-23 03:34:44.549659: step: 2008/529, loss: 9.040832810569555e-05
2023-01-23 03:34:45.678773: step: 2012/529, loss: 0.01640176773071289
2023-01-23 03:34:46.795190: step: 2016/529, loss: 0.01987914927303791
2023-01-23 03:34:47.894814: step: 2020/529, loss: 0.007909774780273438
2023-01-23 03:34:49.025216: step: 2024/529, loss: 0.006548881530761719
2023-01-23 03:34:50.127305: step: 2028/529, loss: 0.037400055676698685
2023-01-23 03:34:51.214087: step: 2032/529, loss: 6.252527782635298e-06
2023-01-23 03:34:52.325171: step: 2036/529, loss: 0.001966858049854636
2023-01-23 03:34:53.429507: step: 2040/529, loss: 0.061445046216249466
2023-01-23 03:34:54.524800: step: 2044/529, loss: 0.00042428969754837453
2023-01-23 03:34:55.635940: step: 2048/529, loss: 0.01059055421501398
2023-01-23 03:34:56.744151: step: 2052/529, loss: 0.002580070635303855
2023-01-23 03:34:57.855232: step: 2056/529, loss: 1.9216537111788057e-05
2023-01-23 03:34:58.978772: step: 2060/529, loss: 0.03037882037460804
2023-01-23 03:35:00.118141: step: 2064/529, loss: 0.035574913024902344
2023-01-23 03:35:01.220799: step: 2068/529, loss: 0.004059553146362305
2023-01-23 03:35:02.372868: step: 2072/529, loss: 0.39640700817108154
2023-01-23 03:35:03.515366: step: 2076/529, loss: 0.011905480176210403
2023-01-23 03:35:04.625330: step: 2080/529, loss: 0.001651763916015625
2023-01-23 03:35:05.706851: step: 2084/529, loss: 0.0009592056157998741
2023-01-23 03:35:06.815222: step: 2088/529, loss: 0.012651586905121803
2023-01-23 03:35:07.924743: step: 2092/529, loss: 0.0075893402099609375
2023-01-23 03:35:09.032128: step: 2096/529, loss: 0.00016288757615257055
2023-01-23 03:35:10.120912: step: 2100/529, loss: 0.004981613252311945
2023-01-23 03:35:11.226761: step: 2104/529, loss: 0.020656870678067207
2023-01-23 03:35:12.339991: step: 2108/529, loss: 1.945495569088962e-05
2023-01-23 03:35:13.443278: step: 2112/529, loss: 0.0013467788230627775
2023-01-23 03:35:14.520231: step: 2116/529, loss: 0.0005268097156658769
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.5873015873015873, 'r': 0.7882822902796272, 'f1': 0.6731097214326321}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6295793758480326, 'r': 0.7855530474040632, 'f1': 0.6989706251569168}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.5517241379310345, 'r': 0.8888888888888888, 'f1': 0.6808510638297872}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.5774647887323944, 'r': 0.6507936507936508, 'f1': 0.6119402985074627}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.40425531914893614, 'r': 0.5277777777777778, 'f1': 0.45783132530120485}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 24
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:35:54.481349: step: 4/529, loss: 0.0003925323544535786
2023-01-23 03:35:55.602666: step: 8/529, loss: 0.0002473831409588456
2023-01-23 03:35:56.714652: step: 12/529, loss: 0.008356285281479359
2023-01-23 03:35:57.805991: step: 16/529, loss: 0.21779365837574005
2023-01-23 03:35:58.906935: step: 20/529, loss: 0.005253219977021217
2023-01-23 03:36:00.036123: step: 24/529, loss: 0.0007912635919637978
2023-01-23 03:36:01.169153: step: 28/529, loss: 0.003102731890976429
2023-01-23 03:36:02.291258: step: 32/529, loss: 0.00017538070096634328
2023-01-23 03:36:03.400703: step: 36/529, loss: 6.132126145530492e-05
2023-01-23 03:36:04.515286: step: 40/529, loss: 0.00975132081657648
2023-01-23 03:36:05.609812: step: 44/529, loss: 0.019554710015654564
2023-01-23 03:36:06.751886: step: 48/529, loss: 0.0008663177723065019
2023-01-23 03:36:07.915233: step: 52/529, loss: 0.001243639038875699
2023-01-23 03:36:09.041585: step: 56/529, loss: 8.525847806595266e-05
2023-01-23 03:36:10.138515: step: 60/529, loss: 0.00014123917208053172
2023-01-23 03:36:11.252645: step: 64/529, loss: 0.002201271243393421
2023-01-23 03:36:12.348111: step: 68/529, loss: 0.006466865539550781
2023-01-23 03:36:13.469552: step: 72/529, loss: 0.0014100074768066406
2023-01-23 03:36:14.579137: step: 76/529, loss: 0.0026243210304528475
2023-01-23 03:36:15.693871: step: 80/529, loss: 0.003959274850785732
2023-01-23 03:36:16.799619: step: 84/529, loss: 0.018009185791015625
2023-01-23 03:36:17.918479: step: 88/529, loss: 0.008799361996352673
2023-01-23 03:36:19.026127: step: 92/529, loss: 0.034955788403749466
2023-01-23 03:36:20.119955: step: 96/529, loss: 2.326965295651462e-05
2023-01-23 03:36:21.228343: step: 100/529, loss: 0.033087920397520065
2023-01-23 03:36:22.338802: step: 104/529, loss: 0.002468871884047985
2023-01-23 03:36:23.427872: step: 108/529, loss: 0.007968520745635033
2023-01-23 03:36:24.558989: step: 112/529, loss: 0.010781098157167435
2023-01-23 03:36:25.655282: step: 116/529, loss: 0.0010690211784094572
2023-01-23 03:36:26.760086: step: 120/529, loss: 0.02180042304098606
2023-01-23 03:36:27.851795: step: 124/529, loss: 0.002035522600635886
2023-01-23 03:36:28.974870: step: 128/529, loss: 0.08149462193250656
2023-01-23 03:36:30.094243: step: 132/529, loss: 0.0009987950325012207
2023-01-23 03:36:31.257265: step: 136/529, loss: 0.002506256103515625
2023-01-23 03:36:32.375991: step: 140/529, loss: 4.38690185546875e-05
2023-01-23 03:36:33.521033: step: 144/529, loss: 0.005530166439712048
2023-01-23 03:36:34.607052: step: 148/529, loss: 0.05460701137781143
2023-01-23 03:36:35.702160: step: 152/529, loss: 0.030742358416318893
2023-01-23 03:36:36.804444: step: 156/529, loss: 0.00010547637793933973
2023-01-23 03:36:37.926756: step: 160/529, loss: 0.0019791603554040194
2023-01-23 03:36:39.028227: step: 164/529, loss: 4.253388033248484e-05
2023-01-23 03:36:40.143994: step: 168/529, loss: 0.0008592605590820312
2023-01-23 03:36:41.267772: step: 172/529, loss: 0.000217437744140625
2023-01-23 03:36:42.367739: step: 176/529, loss: 0.0017484663985669613
2023-01-23 03:36:43.467925: step: 180/529, loss: 0.0002155303955078125
2023-01-23 03:36:44.558560: step: 184/529, loss: 0.006379890255630016
2023-01-23 03:36:45.650166: step: 188/529, loss: 0.0006915092235431075
2023-01-23 03:36:46.806511: step: 192/529, loss: 0.012439919635653496
2023-01-23 03:36:47.886782: step: 196/529, loss: 0.0020318033639341593
2023-01-23 03:36:49.007456: step: 200/529, loss: 0.014362812042236328
2023-01-23 03:36:50.140949: step: 204/529, loss: 0.000274658203125
2023-01-23 03:36:51.248858: step: 208/529, loss: 0.582240104675293
2023-01-23 03:36:52.358862: step: 212/529, loss: 0.008256340399384499
2023-01-23 03:36:53.468096: step: 216/529, loss: 4.920959327137098e-05
2023-01-23 03:36:54.587891: step: 220/529, loss: 0.0012525558704510331
2023-01-23 03:36:55.692439: step: 224/529, loss: 1.33514404296875e-05
2023-01-23 03:36:56.797136: step: 228/529, loss: 0.026694010943174362
2023-01-23 03:36:57.920371: step: 232/529, loss: 0.01851978339254856
2023-01-23 03:36:58.998296: step: 236/529, loss: 0.0005932808271609247
2023-01-23 03:37:00.133921: step: 240/529, loss: 0.012573814950883389
2023-01-23 03:37:01.239597: step: 244/529, loss: 0.004208183381706476
2023-01-23 03:37:02.336013: step: 248/529, loss: 0.008863353170454502
2023-01-23 03:37:03.444068: step: 252/529, loss: 0.0008830070728436112
2023-01-23 03:37:04.556638: step: 256/529, loss: 0.00016670227341819555
2023-01-23 03:37:05.658953: step: 260/529, loss: 5.588531348621473e-05
2023-01-23 03:37:06.750332: step: 264/529, loss: 0.013968467712402344
2023-01-23 03:37:07.892316: step: 268/529, loss: 0.04032020643353462
2023-01-23 03:37:08.993259: step: 272/529, loss: 0.0003326416190247983
2023-01-23 03:37:10.110469: step: 276/529, loss: 0.0013057708274573088
2023-01-23 03:37:11.193147: step: 280/529, loss: 9.050369408214465e-05
2023-01-23 03:37:12.319511: step: 284/529, loss: 0.00013809204392600805
2023-01-23 03:37:13.428871: step: 288/529, loss: 0.01706409640610218
2023-01-23 03:37:14.530216: step: 292/529, loss: 0.0028888704255223274
2023-01-23 03:37:15.630118: step: 296/529, loss: 0.00011711120896507055
2023-01-23 03:37:16.744636: step: 300/529, loss: 0.0006399155245162547
2023-01-23 03:37:17.832036: step: 304/529, loss: 0.00108251569326967
2023-01-23 03:37:18.943683: step: 308/529, loss: 0.0013418197631835938
2023-01-23 03:37:20.125282: step: 312/529, loss: 0.003175163408741355
2023-01-23 03:37:21.250816: step: 316/529, loss: 0.00037212372990325093
2023-01-23 03:37:22.344113: step: 320/529, loss: 0.0007799148443154991
2023-01-23 03:37:23.450454: step: 324/529, loss: 0.006014466285705566
2023-01-23 03:37:24.573860: step: 328/529, loss: 0.0095977783203125
2023-01-23 03:37:25.678536: step: 332/529, loss: 0.0011815071338787675
2023-01-23 03:37:26.817057: step: 336/529, loss: 0.0010402679909020662
2023-01-23 03:37:27.945473: step: 340/529, loss: 0.06329450756311417
2023-01-23 03:37:29.100444: step: 344/529, loss: 0.006624317727982998
2023-01-23 03:37:30.201067: step: 348/529, loss: 0.04829845577478409
2023-01-23 03:37:31.321253: step: 352/529, loss: 0.0002283096400788054
2023-01-23 03:37:32.455463: step: 356/529, loss: 0.000133514404296875
2023-01-23 03:37:33.573521: step: 360/529, loss: 4.19616708313697e-06
2023-01-23 03:37:34.664842: step: 364/529, loss: 0.0002418518124613911
2023-01-23 03:37:35.792790: step: 368/529, loss: 7.765292684780434e-05
2023-01-23 03:37:36.906923: step: 372/529, loss: 0.0004209518665447831
2023-01-23 03:37:38.012792: step: 376/529, loss: 0.012350846081972122
2023-01-23 03:37:39.095243: step: 380/529, loss: 0.008633232675492764
2023-01-23 03:37:40.227792: step: 384/529, loss: 0.0006875991821289062
2023-01-23 03:37:41.350146: step: 388/529, loss: 0.0002342224179301411
2023-01-23 03:37:42.441181: step: 392/529, loss: 9.5367431640625e-06
2023-01-23 03:37:43.561870: step: 396/529, loss: 0.007999230176210403
2023-01-23 03:37:44.656020: step: 400/529, loss: 0.0005586147890426219
2023-01-23 03:37:45.774620: step: 404/529, loss: 0.0002388000430073589
2023-01-23 03:37:46.906272: step: 408/529, loss: 0.000357079494278878
2023-01-23 03:37:48.005581: step: 412/529, loss: 0.004529762081801891
2023-01-23 03:37:49.105879: step: 416/529, loss: 0.0011648177169263363
2023-01-23 03:37:50.238342: step: 420/529, loss: 0.0017258645966649055
2023-01-23 03:37:51.371791: step: 424/529, loss: 0.0800677016377449
2023-01-23 03:37:52.471652: step: 428/529, loss: 0.0007628441089764237
2023-01-23 03:37:53.593541: step: 432/529, loss: 0.0019208431476727128
2023-01-23 03:37:54.698093: step: 436/529, loss: 0.00410385150462389
2023-01-23 03:37:55.846299: step: 440/529, loss: 8.36372419144027e-05
2023-01-23 03:37:56.981934: step: 444/529, loss: 0.013046455569565296
2023-01-23 03:37:58.094065: step: 448/529, loss: 0.02074127271771431
2023-01-23 03:37:59.211839: step: 452/529, loss: 0.0021046637557446957
2023-01-23 03:38:00.335741: step: 456/529, loss: 0.0009842872386798263
2023-01-23 03:38:01.425695: step: 460/529, loss: 0.009906863793730736
2023-01-23 03:38:02.541795: step: 464/529, loss: 0.02371845208108425
2023-01-23 03:38:03.643916: step: 468/529, loss: 2.8705597287626006e-05
2023-01-23 03:38:04.749565: step: 472/529, loss: 0.0011688233353197575
2023-01-23 03:38:05.842918: step: 476/529, loss: 6.532669067382812e-05
2023-01-23 03:38:06.930746: step: 480/529, loss: 0.006134224124252796
2023-01-23 03:38:08.012788: step: 484/529, loss: 9.202957699017134e-06
2023-01-23 03:38:09.102630: step: 488/529, loss: 0.007199001498520374
2023-01-23 03:38:10.232112: step: 492/529, loss: 0.2831043303012848
2023-01-23 03:38:11.326606: step: 496/529, loss: 0.009466147050261497
2023-01-23 03:38:12.406187: step: 500/529, loss: 0.0004096984921488911
2023-01-23 03:38:13.474792: step: 504/529, loss: 0.019950199872255325
2023-01-23 03:38:14.571960: step: 508/529, loss: 0.002665710635483265
2023-01-23 03:38:15.666135: step: 512/529, loss: 0.007513618562370539
2023-01-23 03:38:16.788395: step: 516/529, loss: 2.517700158932712e-05
2023-01-23 03:38:17.920232: step: 520/529, loss: -8.01086389401462e-06
2023-01-23 03:38:19.016512: step: 524/529, loss: 0.00019149782019667327
2023-01-23 03:38:20.131915: step: 528/529, loss: 0.0006608963012695312
2023-01-23 03:38:21.233074: step: 532/529, loss: 0.010239506140351295
2023-01-23 03:38:22.326102: step: 536/529, loss: 0.01025466900318861
2023-01-23 03:38:23.453357: step: 540/529, loss: 0.019496344029903412
2023-01-23 03:38:24.577841: step: 544/529, loss: 0.0022645951248705387
2023-01-23 03:38:25.688323: step: 548/529, loss: 0.0009126186487264931
2023-01-23 03:38:26.801388: step: 552/529, loss: 0.00038337710429914296
2023-01-23 03:38:27.917581: step: 556/529, loss: 0.00153522496111691
2023-01-23 03:38:28.995777: step: 560/529, loss: 0.0026688575744628906
2023-01-23 03:38:30.087799: step: 564/529, loss: 0.0023283003829419613
2023-01-23 03:38:31.231298: step: 568/529, loss: 5.5122378398664296e-05
2023-01-23 03:38:32.358601: step: 572/529, loss: 0.01564769819378853
2023-01-23 03:38:33.476594: step: 576/529, loss: 0.00650634802877903
2023-01-23 03:38:34.593207: step: 580/529, loss: 0.00034718512324616313
2023-01-23 03:38:35.695585: step: 584/529, loss: 2.4414064682787284e-05
2023-01-23 03:38:36.799472: step: 588/529, loss: 1.087188684323337e-05
2023-01-23 03:38:37.893902: step: 592/529, loss: 0.021163273602724075
2023-01-23 03:38:39.023440: step: 596/529, loss: 0.023978807032108307
2023-01-23 03:38:40.105673: step: 600/529, loss: 0.0012805939186364412
2023-01-23 03:38:41.250148: step: 604/529, loss: 0.0027101996820420027
2023-01-23 03:38:42.336377: step: 608/529, loss: 0.0006782531854696572
2023-01-23 03:38:43.448522: step: 612/529, loss: 0.011052703484892845
2023-01-23 03:38:44.543207: step: 616/529, loss: -1.087188684323337e-05
2023-01-23 03:38:45.664477: step: 620/529, loss: 0.061460401862859726
2023-01-23 03:38:46.773318: step: 624/529, loss: 0.0017684936756268144
2023-01-23 03:38:47.861681: step: 628/529, loss: 0.0009705544216558337
2023-01-23 03:38:48.996232: step: 632/529, loss: 0.006282901391386986
2023-01-23 03:38:50.117296: step: 636/529, loss: 8.58306884765625e-06
2023-01-23 03:38:51.245464: step: 640/529, loss: 0.03083820268511772
2023-01-23 03:38:52.349954: step: 644/529, loss: 0.0019453049171715975
2023-01-23 03:38:53.464745: step: 648/529, loss: 0.00011291503324173391
2023-01-23 03:38:54.584708: step: 652/529, loss: 0.0010592460166662931
2023-01-23 03:38:55.689079: step: 656/529, loss: 0.024510765448212624
2023-01-23 03:38:56.778760: step: 660/529, loss: 0.0017028809525072575
2023-01-23 03:38:57.891384: step: 664/529, loss: 0.007291984278708696
2023-01-23 03:38:59.006174: step: 668/529, loss: 0.0016824722988530993
2023-01-23 03:39:00.095813: step: 672/529, loss: 0.0003899097500834614
2023-01-23 03:39:01.238327: step: 676/529, loss: 0.02898998372256756
2023-01-23 03:39:02.392854: step: 680/529, loss: -2.86102294921875e-06
2023-01-23 03:39:03.492337: step: 684/529, loss: 0.0019882202614098787
2023-01-23 03:39:04.608969: step: 688/529, loss: 0.0005960463895462453
2023-01-23 03:39:05.742097: step: 692/529, loss: 0.00981826800853014
2023-01-23 03:39:06.863178: step: 696/529, loss: 0.014781760983169079
2023-01-23 03:39:07.974815: step: 700/529, loss: 0.003985595889389515
2023-01-23 03:39:09.087772: step: 704/529, loss: 0.0008586883777752519
2023-01-23 03:39:10.159380: step: 708/529, loss: 2.2697449821862392e-05
2023-01-23 03:39:11.254922: step: 712/529, loss: 0.00965585745871067
2023-01-23 03:39:12.325252: step: 716/529, loss: 0.0016796470154076815
2023-01-23 03:39:13.418293: step: 720/529, loss: 0.01489119604229927
2023-01-23 03:39:14.527706: step: 724/529, loss: 0.015282725915312767
2023-01-23 03:39:15.613461: step: 728/529, loss: 0.10183233767747879
2023-01-23 03:39:16.743156: step: 732/529, loss: 0.028457069769501686
2023-01-23 03:39:17.869398: step: 736/529, loss: 0.0004585266287904233
2023-01-23 03:39:18.966993: step: 740/529, loss: 0.0028816224075853825
2023-01-23 03:39:20.062565: step: 744/529, loss: 0.0035650255158543587
2023-01-23 03:39:21.158761: step: 748/529, loss: 0.0007166862487792969
2023-01-23 03:39:22.280772: step: 752/529, loss: 0.0003093719424214214
2023-01-23 03:39:23.382996: step: 756/529, loss: 0.02471332438290119
2023-01-23 03:39:24.531582: step: 760/529, loss: 0.0008200645097531378
2023-01-23 03:39:25.629822: step: 764/529, loss: 0.0005647182697430253
2023-01-23 03:39:26.757259: step: 768/529, loss: 0.0003486633358988911
2023-01-23 03:39:27.830275: step: 772/529, loss: 0.007267951965332031
2023-01-23 03:39:28.933061: step: 776/529, loss: 0.0013552665477618575
2023-01-23 03:39:30.026960: step: 780/529, loss: 0.0013607979053631425
2023-01-23 03:39:31.134994: step: 784/529, loss: 0.0005233764532022178
2023-01-23 03:39:32.225799: step: 788/529, loss: 6.046295311534777e-05
2023-01-23 03:39:33.356047: step: 792/529, loss: 6.723403930664062e-05
2023-01-23 03:39:34.483750: step: 796/529, loss: 0.0008447408908978105
2023-01-23 03:39:35.598905: step: 800/529, loss: 0.02805805206298828
2023-01-23 03:39:36.696368: step: 804/529, loss: 0.0001445770321879536
2023-01-23 03:39:37.824430: step: 808/529, loss: 2.3174286980065517e-05
2023-01-23 03:39:38.951855: step: 812/529, loss: 0.00216846470721066
2023-01-23 03:39:40.048003: step: 816/529, loss: 0.0009506225469522178
2023-01-23 03:39:41.186039: step: 820/529, loss: 0.0017351150745525956
2023-01-23 03:39:42.331692: step: 824/529, loss: 0.03768196329474449
2023-01-23 03:39:43.432809: step: 828/529, loss: 0.03584575653076172
2023-01-23 03:39:44.553243: step: 832/529, loss: 0.02200775034725666
2023-01-23 03:39:45.666563: step: 836/529, loss: 0.00029315947904251516
2023-01-23 03:39:46.774659: step: 840/529, loss: 0.0001504898100392893
2023-01-23 03:39:47.907246: step: 844/529, loss: 0.02613077126443386
2023-01-23 03:39:49.021185: step: 848/529, loss: 0.05107174068689346
2023-01-23 03:39:50.128307: step: 852/529, loss: 0.004071045201271772
2023-01-23 03:39:51.264761: step: 856/529, loss: 0.007562350947409868
2023-01-23 03:39:52.381152: step: 860/529, loss: 0.030723953619599342
2023-01-23 03:39:53.486509: step: 864/529, loss: 8.230209641624242e-05
2023-01-23 03:39:54.611539: step: 868/529, loss: 0.040189363062381744
2023-01-23 03:39:55.754158: step: 872/529, loss: 4.100799742445815e-06
2023-01-23 03:39:56.851338: step: 876/529, loss: 0.03584747016429901
2023-01-23 03:39:57.987756: step: 880/529, loss: 0.0792156234383583
2023-01-23 03:39:59.114459: step: 884/529, loss: 0.00014514924259856343
2023-01-23 03:40:00.239616: step: 888/529, loss: 0.0010093689197674394
2023-01-23 03:40:01.352484: step: 892/529, loss: 0.0003459930594544858
2023-01-23 03:40:02.490379: step: 896/529, loss: 0.0009670734289102256
2023-01-23 03:40:03.615833: step: 900/529, loss: 0.00011773109872592613
2023-01-23 03:40:04.736266: step: 904/529, loss: 0.038805581629276276
2023-01-23 03:40:05.884436: step: 908/529, loss: 0.00028705596923828125
2023-01-23 03:40:07.005899: step: 912/529, loss: 0.03404046222567558
2023-01-23 03:40:08.119818: step: 916/529, loss: 0.001767158624716103
2023-01-23 03:40:09.258631: step: 920/529, loss: 0.008560466580092907
2023-01-23 03:40:10.394938: step: 924/529, loss: 6.294250852079131e-06
2023-01-23 03:40:11.513738: step: 928/529, loss: 0.0023124695289880037
2023-01-23 03:40:12.678615: step: 932/529, loss: 0.006863737478852272
2023-01-23 03:40:13.767694: step: 936/529, loss: 7.63893112889491e-05
2023-01-23 03:40:14.881171: step: 940/529, loss: 0.0763576477766037
2023-01-23 03:40:16.004601: step: 944/529, loss: 1.0965994596481323
2023-01-23 03:40:17.125142: step: 948/529, loss: 0.01883668825030327
2023-01-23 03:40:18.205989: step: 952/529, loss: 0.016630172729492188
2023-01-23 03:40:19.306595: step: 956/529, loss: 0.00018901826115325093
2023-01-23 03:40:20.379918: step: 960/529, loss: 0.004084587097167969
2023-01-23 03:40:21.468278: step: 964/529, loss: 0.005934644024819136
2023-01-23 03:40:22.597082: step: 968/529, loss: 0.0012413025833666325
2023-01-23 03:40:23.710108: step: 972/529, loss: 0.0002578735293354839
2023-01-23 03:40:24.819175: step: 976/529, loss: 0.0015085219638422132
2023-01-23 03:40:25.965195: step: 980/529, loss: 0.0023611069191247225
2023-01-23 03:40:27.057987: step: 984/529, loss: 0.057363320142030716
2023-01-23 03:40:28.160528: step: 988/529, loss: 0.0008186340564861894
2023-01-23 03:40:29.256163: step: 992/529, loss: 0.01078262459486723
2023-01-23 03:40:30.371985: step: 996/529, loss: 0.0016262053977698088
2023-01-23 03:40:31.464855: step: 1000/529, loss: 0.005451202858239412
2023-01-23 03:40:32.569419: step: 1004/529, loss: 0.0014255524147301912
2023-01-23 03:40:33.726317: step: 1008/529, loss: 0.015783309936523438
2023-01-23 03:40:34.836267: step: 1012/529, loss: 0.0006582260248251259
2023-01-23 03:40:35.943802: step: 1016/529, loss: 0.0008030892349779606
2023-01-23 03:40:37.050690: step: 1020/529, loss: 0.004277610685676336
2023-01-23 03:40:38.139462: step: 1024/529, loss: 0.0001354217529296875
2023-01-23 03:40:39.263909: step: 1028/529, loss: 0.02090606652200222
2023-01-23 03:40:40.364666: step: 1032/529, loss: 0.0012190818088129163
2023-01-23 03:40:41.473074: step: 1036/529, loss: 0.01520385779440403
2023-01-23 03:40:42.578713: step: 1040/529, loss: 0.009545708075165749
2023-01-23 03:40:43.703502: step: 1044/529, loss: 0.009309959597885609
2023-01-23 03:40:44.817879: step: 1048/529, loss: 0.01163473166525364
2023-01-23 03:40:45.918918: step: 1052/529, loss: 0.00399703998118639
2023-01-23 03:40:47.031402: step: 1056/529, loss: 0.00531768798828125
2023-01-23 03:40:48.139552: step: 1060/529, loss: 0.054778195917606354
2023-01-23 03:40:49.298450: step: 1064/529, loss: 0.004431057255715132
2023-01-23 03:40:50.435316: step: 1068/529, loss: 0.006871271412819624
2023-01-23 03:40:51.555061: step: 1072/529, loss: 0.007038688287138939
2023-01-23 03:40:52.676068: step: 1076/529, loss: 0.0028528214897960424
2023-01-23 03:40:53.764288: step: 1080/529, loss: 8.21113571873866e-05
2023-01-23 03:40:54.881822: step: 1084/529, loss: 0.001213455107063055
2023-01-23 03:40:55.993738: step: 1088/529, loss: 0.002114200731739402
2023-01-23 03:40:57.108407: step: 1092/529, loss: 0.021538924425840378
2023-01-23 03:40:58.216426: step: 1096/529, loss: 0.01445617713034153
2023-01-23 03:40:59.301266: step: 1100/529, loss: 0.00035409926204010844
2023-01-23 03:41:00.394946: step: 1104/529, loss: 0.0006986617809161544
2023-01-23 03:41:01.520991: step: 1108/529, loss: 0.0022852900438010693
2023-01-23 03:41:02.655330: step: 1112/529, loss: 0.011485004797577858
2023-01-23 03:41:03.749768: step: 1116/529, loss: 0.0010349274380132556
2023-01-23 03:41:04.829615: step: 1120/529, loss: 6.444454629672691e-05
2023-01-23 03:41:05.966469: step: 1124/529, loss: 7.381439354503527e-05
2023-01-23 03:41:07.074466: step: 1128/529, loss: 0.00018558502779342234
2023-01-23 03:41:08.173115: step: 1132/529, loss: 0.001514530275017023
2023-01-23 03:41:09.321799: step: 1136/529, loss: 0.006368446629494429
2023-01-23 03:41:10.447084: step: 1140/529, loss: 0.0006160736083984375
2023-01-23 03:41:11.550593: step: 1144/529, loss: 0.007418299093842506
2023-01-23 03:41:12.656234: step: 1148/529, loss: 0.021350478753447533
2023-01-23 03:41:13.814289: step: 1152/529, loss: 0.00022666454606223851
2023-01-23 03:41:14.920226: step: 1156/529, loss: 0.0007070541614666581
2023-01-23 03:41:16.026054: step: 1160/529, loss: 0.0007173537742346525
2023-01-23 03:41:17.131285: step: 1164/529, loss: 3.2901763916015625e-05
2023-01-23 03:41:18.246308: step: 1168/529, loss: 0.027675151824951172
2023-01-23 03:41:19.349854: step: 1172/529, loss: 0.0005023002740927041
2023-01-23 03:41:20.468440: step: 1176/529, loss: 3.948211815441027e-05
2023-01-23 03:41:21.586158: step: 1180/529, loss: 0.004982948303222656
2023-01-23 03:41:22.709878: step: 1184/529, loss: 0.0015054703690111637
2023-01-23 03:41:23.817955: step: 1188/529, loss: 6.723403930664062e-05
2023-01-23 03:41:24.910109: step: 1192/529, loss: 0.00017843247042037547
2023-01-23 03:41:26.008418: step: 1196/529, loss: 0.0019850730895996094
2023-01-23 03:41:27.135814: step: 1200/529, loss: 0.39782485365867615
2023-01-23 03:41:28.254621: step: 1204/529, loss: 0.007019424811005592
2023-01-23 03:41:29.349368: step: 1208/529, loss: 0.00014715194993186742
2023-01-23 03:41:30.451564: step: 1212/529, loss: 0.07494864612817764
2023-01-23 03:41:31.582303: step: 1216/529, loss: 1.9602477550506592e-05
2023-01-23 03:41:32.685650: step: 1220/529, loss: 1.792907642084174e-05
2023-01-23 03:41:33.804264: step: 1224/529, loss: 0.0011323929065838456
2023-01-23 03:41:34.900647: step: 1228/529, loss: 0.0034996033646166325
2023-01-23 03:41:36.016179: step: 1232/529, loss: 0.021793365478515625
2023-01-23 03:41:37.099652: step: 1236/529, loss: 0.0005487442249432206
2023-01-23 03:41:38.243510: step: 1240/529, loss: 0.022512435913085938
2023-01-23 03:41:39.343809: step: 1244/529, loss: 0.0017073630588129163
2023-01-23 03:41:40.459170: step: 1248/529, loss: 0.0031631470192223787
2023-01-23 03:41:41.587175: step: 1252/529, loss: 0.0064199455082416534
2023-01-23 03:41:42.673085: step: 1256/529, loss: 0.0006179810152389109
2023-01-23 03:41:43.826701: step: 1260/529, loss: 0.00012683868408203125
2023-01-23 03:41:44.990257: step: 1264/529, loss: 0.0013432980049401522
2023-01-23 03:41:46.116893: step: 1268/529, loss: 0.0003296852228231728
2023-01-23 03:41:47.210097: step: 1272/529, loss: 0.009262013249099255
2023-01-23 03:41:48.307127: step: 1276/529, loss: 0.0056625367142260075
2023-01-23 03:41:49.450894: step: 1280/529, loss: 0.00039805175038054585
2023-01-23 03:41:50.543671: step: 1284/529, loss: 0.0005619049188680947
2023-01-23 03:41:51.682739: step: 1288/529, loss: 0.007315456867218018
2023-01-23 03:41:52.775826: step: 1292/529, loss: 0.00041909218998625875
2023-01-23 03:41:53.874661: step: 1296/529, loss: 0.6855027079582214
2023-01-23 03:41:54.946739: step: 1300/529, loss: 0.01907634735107422
2023-01-23 03:41:56.031320: step: 1304/529, loss: 0.0005462646367959678
2023-01-23 03:41:57.147856: step: 1308/529, loss: 0.0066363574005663395
2023-01-23 03:41:58.271700: step: 1312/529, loss: 0.00030727387638762593
2023-01-23 03:41:59.385795: step: 1316/529, loss: 0.0001274108944926411
2023-01-23 03:42:00.485456: step: 1320/529, loss: 4.94956984766759e-05
2023-01-23 03:42:01.617225: step: 1324/529, loss: 8.1062319168268e-07
2023-01-23 03:42:02.684655: step: 1328/529, loss: 0.01365447137504816
2023-01-23 03:42:03.785461: step: 1332/529, loss: 0.06259842216968536
2023-01-23 03:42:04.892745: step: 1336/529, loss: 0.00010309219942428172
2023-01-23 03:42:05.993136: step: 1340/529, loss: 0.00035572052001953125
2023-01-23 03:42:07.114421: step: 1344/529, loss: 0.015739820897579193
2023-01-23 03:42:08.232556: step: 1348/529, loss: 0.0008097171667031944
2023-01-23 03:42:09.329598: step: 1352/529, loss: 0.0005952835199423134
2023-01-23 03:42:10.445706: step: 1356/529, loss: 0.0034111500717699528
2023-01-23 03:42:11.585063: step: 1360/529, loss: 0.04425692558288574
2023-01-23 03:42:12.705107: step: 1364/529, loss: 0.0025315284729003906
2023-01-23 03:42:13.817832: step: 1368/529, loss: 0.016381217166781425
2023-01-23 03:42:14.934470: step: 1372/529, loss: 0.00038700102595612407
2023-01-23 03:42:16.015066: step: 1376/529, loss: 0.00019340515427757055
2023-01-23 03:42:17.131741: step: 1380/529, loss: 0.0010005474323406816
2023-01-23 03:42:18.226352: step: 1384/529, loss: 0.00034012793912552297
2023-01-23 03:42:19.330183: step: 1388/529, loss: 0.004056835547089577
2023-01-23 03:42:20.442699: step: 1392/529, loss: 0.00090198521502316
2023-01-23 03:42:21.529408: step: 1396/529, loss: 2.0790101189049892e-05
2023-01-23 03:42:22.655626: step: 1400/529, loss: 0.0012370110489428043
2023-01-23 03:42:23.770459: step: 1404/529, loss: 0.02625093422830105
2023-01-23 03:42:24.877816: step: 1408/529, loss: 0.03659839928150177
2023-01-23 03:42:26.005448: step: 1412/529, loss: 0.005652999971061945
2023-01-23 03:42:27.082409: step: 1416/529, loss: -1.23977656585339e-06
2023-01-23 03:42:28.175081: step: 1420/529, loss: 0.00016813278489280492
2023-01-23 03:42:29.305776: step: 1424/529, loss: 0.0003372192441020161
2023-01-23 03:42:30.422490: step: 1428/529, loss: 0.003093529026955366
2023-01-23 03:42:31.557412: step: 1432/529, loss: 0.014352607540786266
2023-01-23 03:42:32.663423: step: 1436/529, loss: 0.00524139404296875
2023-01-23 03:42:33.775988: step: 1440/529, loss: 0.02582702599465847
2023-01-23 03:42:34.907085: step: 1444/529, loss: 2.4509430659236386e-05
2023-01-23 03:42:36.039728: step: 1448/529, loss: 0.044438984245061874
2023-01-23 03:42:37.131940: step: 1452/529, loss: 5.6743621826171875e-05
2023-01-23 03:42:38.262422: step: 1456/529, loss: 3.814697265625e-05
2023-01-23 03:42:39.376730: step: 1460/529, loss: 0.003301334334537387
2023-01-23 03:42:40.498692: step: 1464/529, loss: 0.02140064351260662
2023-01-23 03:42:41.605275: step: 1468/529, loss: 0.008984756655991077
2023-01-23 03:42:42.698361: step: 1472/529, loss: 0.002600050065666437
2023-01-23 03:42:43.778338: step: 1476/529, loss: 0.3212962746620178
2023-01-23 03:42:44.889159: step: 1480/529, loss: 1.0997517108917236
2023-01-23 03:42:45.992757: step: 1484/529, loss: 1.926422191900201e-05
2023-01-23 03:42:47.089336: step: 1488/529, loss: 0.0004656791570596397
2023-01-23 03:42:48.191975: step: 1492/529, loss: 0.0016533852322027087
2023-01-23 03:42:49.300354: step: 1496/529, loss: 0.0009114265558309853
2023-01-23 03:42:50.384984: step: 1500/529, loss: 0.001280117081478238
2023-01-23 03:42:51.489346: step: 1504/529, loss: 0.07775726914405823
2023-01-23 03:42:52.587643: step: 1508/529, loss: 0.07758484035730362
2023-01-23 03:42:53.667649: step: 1512/529, loss: 0.007211207877844572
2023-01-23 03:42:54.767667: step: 1516/529, loss: 0.0004280090506654233
2023-01-23 03:42:55.922021: step: 1520/529, loss: 0.0003231048758607358
2023-01-23 03:42:57.067066: step: 1524/529, loss: 5.598067946266383e-05
2023-01-23 03:42:58.158291: step: 1528/529, loss: 0.17844629287719727
2023-01-23 03:42:59.277198: step: 1532/529, loss: 0.0026567461900413036
2023-01-23 03:43:00.385941: step: 1536/529, loss: 0.0003501892206259072
2023-01-23 03:43:01.478638: step: 1540/529, loss: 0.007067298982292414
2023-01-23 03:43:02.583729: step: 1544/529, loss: 0.000979518867097795
2023-01-23 03:43:03.699353: step: 1548/529, loss: 0.008297729305922985
2023-01-23 03:43:04.818758: step: 1552/529, loss: 0.004073619842529297
2023-01-23 03:43:05.905472: step: 1556/529, loss: 0.0011669874656945467
2023-01-23 03:43:07.037555: step: 1560/529, loss: 0.00564079312607646
2023-01-23 03:43:08.157285: step: 1564/529, loss: 0.0003078937588725239
2023-01-23 03:43:09.252805: step: 1568/529, loss: 0.002226901240646839
2023-01-23 03:43:10.380471: step: 1572/529, loss: 0.009495544247329235
2023-01-23 03:43:11.478045: step: 1576/529, loss: 0.045978449285030365
2023-01-23 03:43:12.576546: step: 1580/529, loss: 0.00076465611346066
2023-01-23 03:43:13.689041: step: 1584/529, loss: 0.0009368896717205644
2023-01-23 03:43:14.806499: step: 1588/529, loss: 0.00045070648775435984
2023-01-23 03:43:15.905621: step: 1592/529, loss: 0.0002929687616415322
2023-01-23 03:43:17.043232: step: 1596/529, loss: 0.005933189298957586
2023-01-23 03:43:18.153731: step: 1600/529, loss: 2.269744800287299e-05
2023-01-23 03:43:19.291594: step: 1604/529, loss: 1.8501283193472773e-05
2023-01-23 03:43:20.386765: step: 1608/529, loss: 0.0010840415488928556
2023-01-23 03:43:21.527402: step: 1612/529, loss: 0.008745002560317516
2023-01-23 03:43:22.643534: step: 1616/529, loss: 0.0017584800953045487
2023-01-23 03:43:23.736789: step: 1620/529, loss: 7.629394644936838e-07
2023-01-23 03:43:24.849544: step: 1624/529, loss: 0.0005194664117880166
2023-01-23 03:43:25.913025: step: 1628/529, loss: 0.000526046787854284
2023-01-23 03:43:27.032043: step: 1632/529, loss: 0.011903000064194202
2023-01-23 03:43:28.137780: step: 1636/529, loss: 0.00925521831959486
2023-01-23 03:43:29.252531: step: 1640/529, loss: 3.814697629422881e-05
2023-01-23 03:43:30.349770: step: 1644/529, loss: 0.0025532725267112255
2023-01-23 03:43:31.447740: step: 1648/529, loss: 0.00042743684025481343
2023-01-23 03:43:32.581445: step: 1652/529, loss: 0.0001200675978907384
2023-01-23 03:43:33.707525: step: 1656/529, loss: 0.0008883416885510087
2023-01-23 03:43:34.811909: step: 1660/529, loss: 2.6226043701171875e-05
2023-01-23 03:43:35.929745: step: 1664/529, loss: 0.0276491641998291
2023-01-23 03:43:37.012958: step: 1668/529, loss: 0.0007463454967364669
2023-01-23 03:43:38.122671: step: 1672/529, loss: 7.190704491222277e-05
2023-01-23 03:43:39.241233: step: 1676/529, loss: 0.017272569239139557
2023-01-23 03:43:40.325235: step: 1680/529, loss: 0.02514667622745037
2023-01-23 03:43:41.423099: step: 1684/529, loss: 0.014276313595473766
2023-01-23 03:43:42.595101: step: 1688/529, loss: 0.012987899594008923
2023-01-23 03:43:43.692842: step: 1692/529, loss: 0.18673306703567505
2023-01-23 03:43:44.799427: step: 1696/529, loss: 0.000686264073010534
2023-01-23 03:43:45.927661: step: 1700/529, loss: 0.0017111777560785413
2023-01-23 03:43:47.044592: step: 1704/529, loss: 0.006614399142563343
2023-01-23 03:43:48.164935: step: 1708/529, loss: 0.0029592514038085938
2023-01-23 03:43:49.300429: step: 1712/529, loss: 0.04951363056898117
2023-01-23 03:43:50.403011: step: 1716/529, loss: 1.52587890625e-05
2023-01-23 03:43:51.493878: step: 1720/529, loss: 0.0018980979220941663
2023-01-23 03:43:52.618549: step: 1724/529, loss: 0.07986793667078018
2023-01-23 03:43:53.722104: step: 1728/529, loss: 0.0013504981761798263
2023-01-23 03:43:54.833679: step: 1732/529, loss: 0.013439178466796875
2023-01-23 03:43:55.962272: step: 1736/529, loss: 0.07295895367860794
2023-01-23 03:43:57.065136: step: 1740/529, loss: 4.634857032215223e-05
2023-01-23 03:43:58.162338: step: 1744/529, loss: 0.015958214178681374
2023-01-23 03:43:59.238655: step: 1748/529, loss: 0.00034971238346770406
2023-01-23 03:44:00.362897: step: 1752/529, loss: 0.021625613793730736
2023-01-23 03:44:01.469381: step: 1756/529, loss: 0.001922607421875
2023-01-23 03:44:02.566144: step: 1760/529, loss: 9.33647170313634e-05
2023-01-23 03:44:03.671935: step: 1764/529, loss: 9.946823411155492e-05
2023-01-23 03:44:04.766315: step: 1768/529, loss: 0.09372882544994354
2023-01-23 03:44:05.894796: step: 1772/529, loss: 0.029911041259765625
2023-01-23 03:44:07.009550: step: 1776/529, loss: 0.00015077591524459422
2023-01-23 03:44:08.112628: step: 1780/529, loss: 0.000301170366583392
2023-01-23 03:44:09.202218: step: 1784/529, loss: 0.0011503220302984118
2023-01-23 03:44:10.338374: step: 1788/529, loss: 4.113429546356201
2023-01-23 03:44:11.446605: step: 1792/529, loss: 0.003711128141731024
2023-01-23 03:44:12.572405: step: 1796/529, loss: 0.004560828674584627
2023-01-23 03:44:13.712115: step: 1800/529, loss: 0.003116512205451727
2023-01-23 03:44:14.844222: step: 1804/529, loss: 0.012748622335493565
2023-01-23 03:44:15.980059: step: 1808/529, loss: 0.00034503935603424907
2023-01-23 03:44:17.084306: step: 1812/529, loss: 0.0001386642543366179
2023-01-23 03:44:18.184582: step: 1816/529, loss: 0.002111673355102539
2023-01-23 03:44:19.293803: step: 1820/529, loss: 0.0020411014556884766
2023-01-23 03:44:20.403243: step: 1824/529, loss: 0.0006233692402020097
2023-01-23 03:44:21.499657: step: 1828/529, loss: 0.02498159557580948
2023-01-23 03:44:22.619135: step: 1832/529, loss: 0.0004571914905682206
2023-01-23 03:44:23.730945: step: 1836/529, loss: 0.019417762756347656
2023-01-23 03:44:24.866193: step: 1840/529, loss: 0.05352463573217392
2023-01-23 03:44:25.978058: step: 1844/529, loss: 0.009871482849121094
2023-01-23 03:44:27.090246: step: 1848/529, loss: 0.0005116462707519531
2023-01-23 03:44:28.204977: step: 1852/529, loss: 0.0006893158424645662
2023-01-23 03:44:29.327277: step: 1856/529, loss: 0.00017662048048805445
2023-01-23 03:44:30.445651: step: 1860/529, loss: 0.03502922132611275
2023-01-23 03:44:31.569077: step: 1864/529, loss: 0.004192352294921875
2023-01-23 03:44:32.660164: step: 1868/529, loss: 3.24249276673072e-06
2023-01-23 03:44:33.792288: step: 1872/529, loss: 0.004363632295280695
2023-01-23 03:44:34.875207: step: 1876/529, loss: 5.1403050747467205e-05
2023-01-23 03:44:35.984916: step: 1880/529, loss: 0.006640816107392311
2023-01-23 03:44:37.065426: step: 1884/529, loss: 0.0002799987851176411
2023-01-23 03:44:38.179602: step: 1888/529, loss: 0.00011196136620128527
2023-01-23 03:44:39.301532: step: 1892/529, loss: 0.00013818741717841476
2023-01-23 03:44:40.418207: step: 1896/529, loss: 0.0016016960144042969
2023-01-23 03:44:41.526656: step: 1900/529, loss: 0.0011799812782555819
2023-01-23 03:44:42.642202: step: 1904/529, loss: 0.0006229400751180947
2023-01-23 03:44:43.777941: step: 1908/529, loss: 0.043372441083192825
2023-01-23 03:44:44.893952: step: 1912/529, loss: 0.00036525726318359375
2023-01-23 03:44:45.991775: step: 1916/529, loss: 4.535161018371582
2023-01-23 03:44:47.107551: step: 1920/529, loss: 0.0005552291986532509
2023-01-23 03:44:48.258885: step: 1924/529, loss: 0.008031273260712624
2023-01-23 03:44:49.349496: step: 1928/529, loss: 0.017209816724061966
2023-01-23 03:44:50.485293: step: 1932/529, loss: 0.030343318358063698
2023-01-23 03:44:51.599414: step: 1936/529, loss: 0.06060619279742241
2023-01-23 03:44:52.716931: step: 1940/529, loss: 0.05756263807415962
2023-01-23 03:44:53.818866: step: 1944/529, loss: 2.460479663568549e-05
2023-01-23 03:44:54.938112: step: 1948/529, loss: 1.2540817806439009e-05
2023-01-23 03:44:56.038925: step: 1952/529, loss: 0.01860685460269451
2023-01-23 03:44:57.139106: step: 1956/529, loss: 0.0010583162074908614
2023-01-23 03:44:58.235115: step: 1960/529, loss: 7.629395213371026e-07
2023-01-23 03:44:59.335819: step: 1964/529, loss: 0.030353952199220657
2023-01-23 03:45:00.450345: step: 1968/529, loss: 0.016438055783510208
2023-01-23 03:45:01.546756: step: 1972/529, loss: 0.007317352574318647
2023-01-23 03:45:02.652933: step: 1976/529, loss: 0.00286617293022573
2023-01-23 03:45:03.782982: step: 1980/529, loss: 0.016619157046079636
2023-01-23 03:45:04.904814: step: 1984/529, loss: 0.00387821183539927
2023-01-23 03:45:06.005685: step: 1988/529, loss: 2.3937225705594756e-05
2023-01-23 03:45:07.120747: step: 1992/529, loss: 0.00010986327833961695
2023-01-23 03:45:08.240284: step: 1996/529, loss: 0.0067840577103197575
2023-01-23 03:45:09.334004: step: 2000/529, loss: 0.00044889451237395406
2023-01-23 03:45:10.444257: step: 2004/529, loss: 0.14281636476516724
2023-01-23 03:45:11.538106: step: 2008/529, loss: 0.00017395020404364914
2023-01-23 03:45:12.671476: step: 2012/529, loss: 1.0299681889591739e-05
2023-01-23 03:45:13.794844: step: 2016/529, loss: 0.021697044372558594
2023-01-23 03:45:14.892055: step: 2020/529, loss: 0.1025310531258583
2023-01-23 03:45:16.010857: step: 2024/529, loss: 0.049604035913944244
2023-01-23 03:45:17.132640: step: 2028/529, loss: 0.00198955531232059
2023-01-23 03:45:18.239049: step: 2032/529, loss: 0.0008503913995809853
2023-01-23 03:45:19.346576: step: 2036/529, loss: 0.03170070797204971
2023-01-23 03:45:20.446446: step: 2040/529, loss: 0.0010135649936273694
2023-01-23 03:45:21.548669: step: 2044/529, loss: 0.01690368726849556
2023-01-23 03:45:22.642205: step: 2048/529, loss: 0.028699208050966263
2023-01-23 03:45:23.772811: step: 2052/529, loss: 0.006765174679458141
2023-01-23 03:45:24.887352: step: 2056/529, loss: 0.0016994476318359375
2023-01-23 03:45:26.004228: step: 2060/529, loss: 0.002978420350700617
2023-01-23 03:45:27.112312: step: 2064/529, loss: 0.00122241978533566
2023-01-23 03:45:28.197681: step: 2068/529, loss: 0.0004337310674600303
2023-01-23 03:45:29.289595: step: 2072/529, loss: 0.001850128173828125
2023-01-23 03:45:30.393637: step: 2076/529, loss: 0.0004557609499897808
2023-01-23 03:45:31.464847: step: 2080/529, loss: 0.00013418197340797633
2023-01-23 03:45:32.588719: step: 2084/529, loss: 0.0005438804510049522
2023-01-23 03:45:33.673917: step: 2088/529, loss: 0.0394718199968338
2023-01-23 03:45:34.792387: step: 2092/529, loss: 0.02898426167666912
2023-01-23 03:45:35.911333: step: 2096/529, loss: 0.036324311047792435
2023-01-23 03:45:37.021171: step: 2100/529, loss: 0.0004966735723428428
2023-01-23 03:45:38.124125: step: 2104/529, loss: 0.022907542064785957
2023-01-23 03:45:39.228854: step: 2108/529, loss: 0.6578750610351562
2023-01-23 03:45:40.361751: step: 2112/529, loss: 0.0012264251708984375
2023-01-23 03:45:41.468293: step: 2116/529, loss: 0.0040412903763353825
==================================================
Loss: 0.037
--------------------
Dev: {'event': {'p': 0.5921325051759835, 'r': 0.7616511318242344, 'f1': 0.6662783925451369}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.641958041958042, 'r': 0.7770880361173815, 'f1': 0.7030890988001022}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5375, 'r': 0.7962962962962963, 'f1': 0.6417910447761194}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.5555555555555556, 'r': 0.5555555555555556, 'f1': 0.5555555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.38636363636363635, 'r': 0.4722222222222222, 'f1': 0.425}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:46:21.774580: step: 4/529, loss: 8.239746239269152e-05
2023-01-23 03:46:22.864899: step: 8/529, loss: 0.06492728739976883
2023-01-23 03:46:23.964474: step: 12/529, loss: 0.0010535240871831775
2023-01-23 03:46:25.067682: step: 16/529, loss: 2.6512147087487392e-05
2023-01-23 03:46:26.174458: step: 20/529, loss: 3.61442580469884e-05
2023-01-23 03:46:27.268423: step: 24/529, loss: 0.00010061264038085938
2023-01-23 03:46:28.376192: step: 28/529, loss: 2.574920654296875e-05
2023-01-23 03:46:29.465588: step: 32/529, loss: 0.0016889096004888415
2023-01-23 03:46:30.593967: step: 36/529, loss: 0.0001029014601954259
2023-01-23 03:46:31.700799: step: 40/529, loss: 0.0011649131774902344
2023-01-23 03:46:32.808896: step: 44/529, loss: 0.013121413998305798
2023-01-23 03:46:33.923713: step: 48/529, loss: 4.1675571992527694e-05
2023-01-23 03:46:35.049309: step: 52/529, loss: 0.014288235455751419
2023-01-23 03:46:36.136726: step: 56/529, loss: 6.053448305465281e-05
2023-01-23 03:46:37.222785: step: 60/529, loss: 0.0013905526138842106
2023-01-23 03:46:38.356200: step: 64/529, loss: 0.00577621441334486
2023-01-23 03:46:39.456804: step: 68/529, loss: 6.341934204101562e-05
2023-01-23 03:46:40.569140: step: 72/529, loss: 2.5844574338407256e-05
2023-01-23 03:46:41.669749: step: 76/529, loss: 0.004614830017089844
2023-01-23 03:46:42.756784: step: 80/529, loss: 0.0009738922235555947
2023-01-23 03:46:43.864411: step: 84/529, loss: 0.02246265485882759
2023-01-23 03:46:44.989410: step: 88/529, loss: 3.046989513677545e-05
2023-01-23 03:46:46.113710: step: 92/529, loss: 0.0001928329438669607
2023-01-23 03:46:47.253544: step: 96/529, loss: 0.0019365311600267887
2023-01-23 03:46:48.395470: step: 100/529, loss: 0.0017698288429528475
2023-01-23 03:46:49.510960: step: 104/529, loss: 0.02767029032111168
2023-01-23 03:46:50.619649: step: 108/529, loss: 5.3119660151423886e-05
2023-01-23 03:46:51.709978: step: 112/529, loss: 9.70840483205393e-05
2023-01-23 03:46:52.816749: step: 116/529, loss: 0.0028869628440588713
2023-01-23 03:46:53.913524: step: 120/529, loss: -1.239776611328125e-05
2023-01-23 03:46:55.023113: step: 124/529, loss: 0.00014681815810035914
2023-01-23 03:46:56.154227: step: 128/529, loss: 0.00014324189396575093
2023-01-23 03:46:57.267254: step: 132/529, loss: 0.0001350402890238911
2023-01-23 03:46:58.365562: step: 136/529, loss: 5.91278076171875e-05
2023-01-23 03:46:59.494348: step: 140/529, loss: 0.0089270593598485
2023-01-23 03:47:00.631106: step: 144/529, loss: 0.0009086608770303428
2023-01-23 03:47:01.745948: step: 148/529, loss: 0.0016155242919921875
2023-01-23 03:47:02.829899: step: 152/529, loss: 0.042005158960819244
2023-01-23 03:47:03.977666: step: 156/529, loss: 0.0006219864008016884
2023-01-23 03:47:05.106837: step: 160/529, loss: 0.0007740020519122481
2023-01-23 03:47:06.195905: step: 164/529, loss: 3.814697265625e-05
2023-01-23 03:47:07.319491: step: 168/529, loss: 0.0016374588012695312
2023-01-23 03:47:08.447372: step: 172/529, loss: 0.008846855722367764
2023-01-23 03:47:09.567957: step: 176/529, loss: 0.002421474317088723
2023-01-23 03:47:10.672471: step: 180/529, loss: 2.574920654296875e-05
2023-01-23 03:47:11.773916: step: 184/529, loss: 0.0017307281959801912
2023-01-23 03:47:12.876786: step: 188/529, loss: 0.0006530761602334678
2023-01-23 03:47:13.969504: step: 192/529, loss: 0.002630615374073386
2023-01-23 03:47:15.062653: step: 196/529, loss: 0.0028165339026600122
2023-01-23 03:47:16.164785: step: 200/529, loss: 0.016945648938417435
2023-01-23 03:47:17.286285: step: 204/529, loss: 0.005320549476891756
2023-01-23 03:47:18.390043: step: 208/529, loss: 0.048088837414979935
2023-01-23 03:47:19.467686: step: 212/529, loss: 1.5211106074275449e-05
2023-01-23 03:47:20.602286: step: 216/529, loss: 0.002927398541942239
2023-01-23 03:47:21.716632: step: 220/529, loss: 2.651214526849799e-05
2023-01-23 03:47:22.822733: step: 224/529, loss: 0.00015563964552711695
2023-01-23 03:47:23.933599: step: 228/529, loss: 0.005594635382294655
2023-01-23 03:47:25.055060: step: 232/529, loss: 0.03022041544318199
2023-01-23 03:47:26.151679: step: 236/529, loss: 0.0025920867919921875
2023-01-23 03:47:27.255823: step: 240/529, loss: 0.0674860030412674
2023-01-23 03:47:28.367047: step: 244/529, loss: 0.00022382737370207906
2023-01-23 03:47:29.453966: step: 248/529, loss: 0.1946265697479248
2023-01-23 03:47:30.549604: step: 252/529, loss: 0.0003417968691792339
2023-01-23 03:47:31.648470: step: 256/529, loss: 0.01829090155661106
2023-01-23 03:47:32.742379: step: 260/529, loss: 0.001224517822265625
2023-01-23 03:47:33.881207: step: 264/529, loss: 0.00019187928410246968
2023-01-23 03:47:34.988178: step: 268/529, loss: 0.004771900363266468
2023-01-23 03:47:36.118268: step: 272/529, loss: 0.00033273696317337453
2023-01-23 03:47:37.222243: step: 276/529, loss: 0.00021781922259833664
2023-01-23 03:47:38.340422: step: 280/529, loss: 0.0014924048446118832
2023-01-23 03:47:39.411773: step: 284/529, loss: 0.001709079835563898
2023-01-23 03:47:40.546447: step: 288/529, loss: 0.0004725456237792969
2023-01-23 03:47:41.637898: step: 292/529, loss: 0.009066772647202015
2023-01-23 03:47:42.759029: step: 296/529, loss: 0.010678482241928577
2023-01-23 03:47:43.891505: step: 300/529, loss: 0.0405920036137104
2023-01-23 03:47:44.986720: step: 304/529, loss: 9.91821252682712e-06
2023-01-23 03:47:46.110085: step: 308/529, loss: 0.00014743805513717234
2023-01-23 03:47:47.201746: step: 312/529, loss: 1.9931794668082148e-05
2023-01-23 03:47:48.281830: step: 316/529, loss: 0.01950206607580185
2023-01-23 03:47:49.400786: step: 320/529, loss: 0.07506103068590164
2023-01-23 03:47:50.500382: step: 324/529, loss: 9.965896424546372e-06
2023-01-23 03:47:51.630547: step: 328/529, loss: 0.04887409135699272
2023-01-23 03:47:52.718094: step: 332/529, loss: 0.006680631544440985
2023-01-23 03:47:53.820954: step: 336/529, loss: 0.19106845557689667
2023-01-23 03:47:54.953054: step: 340/529, loss: 0.00011348725092830136
2023-01-23 03:47:56.047903: step: 344/529, loss: 0.0013216972583904862
2023-01-23 03:47:57.166122: step: 348/529, loss: 0.014134597964584827
2023-01-23 03:47:58.257207: step: 352/529, loss: 7.581710815429688e-05
2023-01-23 03:47:59.378362: step: 356/529, loss: 0.0002537727414164692
2023-01-23 03:48:00.478479: step: 360/529, loss: 0.007184028625488281
2023-01-23 03:48:01.572286: step: 364/529, loss: 0.00045909881009720266
2023-01-23 03:48:02.700643: step: 368/529, loss: 0.008728695102036
2023-01-23 03:48:03.832766: step: 372/529, loss: 0.00012292862811591476
2023-01-23 03:48:04.958723: step: 376/529, loss: 0.06993818283081055
2023-01-23 03:48:06.051175: step: 380/529, loss: 0.00019149780564475805
2023-01-23 03:48:07.157667: step: 384/529, loss: 0.002189445775002241
2023-01-23 03:48:08.280740: step: 388/529, loss: 0.0017707825172692537
2023-01-23 03:48:09.377117: step: 392/529, loss: 0.00016074179438874125
2023-01-23 03:48:10.496946: step: 396/529, loss: 0.0007915973546914756
2023-01-23 03:48:11.638075: step: 400/529, loss: 0.006847381591796875
2023-01-23 03:48:12.743827: step: 404/529, loss: 0.0010313987731933594
2023-01-23 03:48:13.848183: step: 408/529, loss: 0.01844930648803711
2023-01-23 03:48:14.994883: step: 412/529, loss: 0.6985594034194946
2023-01-23 03:48:16.117544: step: 416/529, loss: 0.001399993896484375
2023-01-23 03:48:17.219240: step: 420/529, loss: 0.005720996763557196
2023-01-23 03:48:18.323398: step: 424/529, loss: 7.896423630882055e-05
2023-01-23 03:48:19.455903: step: 428/529, loss: 0.026981163769960403
2023-01-23 03:48:20.566347: step: 432/529, loss: 0.002355384873226285
2023-01-23 03:48:21.658855: step: 436/529, loss: 1.640319896978326e-05
2023-01-23 03:48:22.761618: step: 440/529, loss: 8.258819434558973e-05
2023-01-23 03:48:23.848266: step: 444/529, loss: 0.0003450393851380795
2023-01-23 03:48:24.954525: step: 448/529, loss: 0.001911258790642023
2023-01-23 03:48:26.079205: step: 452/529, loss: 6.160735938465223e-05
2023-01-23 03:48:27.170497: step: 456/529, loss: 0.1715896725654602
2023-01-23 03:48:28.296294: step: 460/529, loss: 0.000431919121183455
2023-01-23 03:48:29.408881: step: 464/529, loss: 2.7561187380342744e-05
2023-01-23 03:48:30.513138: step: 468/529, loss: 0.09603271633386612
2023-01-23 03:48:31.631970: step: 472/529, loss: 0.013927746564149857
2023-01-23 03:48:32.716951: step: 476/529, loss: 0.0016885757213458419
2023-01-23 03:48:33.816578: step: 480/529, loss: 0.008866596966981888
2023-01-23 03:48:34.936302: step: 484/529, loss: 0.0033962251618504524
2023-01-23 03:48:36.044827: step: 488/529, loss: 0.0012064933544024825
2023-01-23 03:48:37.125956: step: 492/529, loss: 0.00138940813485533
2023-01-23 03:48:38.245097: step: 496/529, loss: 0.007605123333632946
2023-01-23 03:48:39.399603: step: 500/529, loss: 0.0014417648781090975
2023-01-23 03:48:40.538551: step: 504/529, loss: 0.014421463012695312
2023-01-23 03:48:41.668778: step: 508/529, loss: 0.002451992128044367
2023-01-23 03:48:42.785177: step: 512/529, loss: 0.0010552406311035156
2023-01-23 03:48:43.867593: step: 516/529, loss: 0.022318458184599876
2023-01-23 03:48:44.969147: step: 520/529, loss: 0.004051971714943647
2023-01-23 03:48:46.070235: step: 524/529, loss: 0.007374858483672142
2023-01-23 03:48:47.165250: step: 528/529, loss: 0.0007042884826660156
2023-01-23 03:48:48.301597: step: 532/529, loss: 0.0037859915755689144
2023-01-23 03:48:49.407354: step: 536/529, loss: 0.002202987438067794
2023-01-23 03:48:50.496767: step: 540/529, loss: 9.679794311523438e-05
2023-01-23 03:48:51.599875: step: 544/529, loss: 5.1975250244140625e-05
2023-01-23 03:48:52.733208: step: 548/529, loss: 0.017271708697080612
2023-01-23 03:48:53.865035: step: 552/529, loss: 0.06082115322351456
2023-01-23 03:48:54.991254: step: 556/529, loss: 0.00034880638122558594
2023-01-23 03:48:56.126697: step: 560/529, loss: 0.0004460811906028539
2023-01-23 03:48:57.241574: step: 564/529, loss: 0.0010293960804119706
2023-01-23 03:48:58.372845: step: 568/529, loss: 0.0021224976517260075
2023-01-23 03:48:59.480983: step: 572/529, loss: 6.809234764659777e-05
2023-01-23 03:49:00.594243: step: 576/529, loss: 0.010007381439208984
2023-01-23 03:49:01.687644: step: 580/529, loss: 1.373290979245212e-05
2023-01-23 03:49:02.800439: step: 584/529, loss: 7.152556918299524e-06
2023-01-23 03:49:03.933519: step: 588/529, loss: 0.0261096004396677
2023-01-23 03:49:05.051639: step: 592/529, loss: 0.025314997881650925
2023-01-23 03:49:06.154559: step: 596/529, loss: 0.007330894470214844
2023-01-23 03:49:07.269580: step: 600/529, loss: 0.023163508623838425
2023-01-23 03:49:08.369100: step: 604/529, loss: 0.012703800573945045
2023-01-23 03:49:09.486145: step: 608/529, loss: 0.005654830019921064
2023-01-23 03:49:10.597317: step: 612/529, loss: 0.0005739211919717491
2023-01-23 03:49:11.688824: step: 616/529, loss: 0.0010097504127770662
2023-01-23 03:49:12.800586: step: 620/529, loss: 0.0003084182972088456
2023-01-23 03:49:13.908884: step: 624/529, loss: 0.00014472007751464844
2023-01-23 03:49:15.038472: step: 628/529, loss: 0.00014610291691496968
2023-01-23 03:49:16.124031: step: 632/529, loss: 0.0011796951293945312
2023-01-23 03:49:17.219050: step: 636/529, loss: 0.00035533905611373484
2023-01-23 03:49:18.314929: step: 640/529, loss: 0.000594711338635534
2023-01-23 03:49:19.450151: step: 644/529, loss: 0.006466484162956476
2023-01-23 03:49:20.567440: step: 648/529, loss: 0.00022411346435546875
2023-01-23 03:49:21.679674: step: 652/529, loss: 0.0021045685280114412
2023-01-23 03:49:22.798868: step: 656/529, loss: 0.0012584686046466231
2023-01-23 03:49:23.921132: step: 660/529, loss: 0.04673194885253906
2023-01-23 03:49:25.017483: step: 664/529, loss: 0.0001146316499216482
2023-01-23 03:49:26.138539: step: 668/529, loss: 0.0004225253942422569
2023-01-23 03:49:27.275523: step: 672/529, loss: 0.0008788108825683594
2023-01-23 03:49:28.392147: step: 676/529, loss: 0.047112368047237396
2023-01-23 03:49:29.483106: step: 680/529, loss: 0.40907785296440125
2023-01-23 03:49:30.590659: step: 684/529, loss: 0.0010457038879394531
2023-01-23 03:49:31.702555: step: 688/529, loss: 0.02270498313009739
2023-01-23 03:49:32.797206: step: 692/529, loss: 0.02062349207699299
2023-01-23 03:49:33.912199: step: 696/529, loss: 0.00029754638671875
2023-01-23 03:49:35.032988: step: 700/529, loss: 0.0008483410347253084
2023-01-23 03:49:36.140801: step: 704/529, loss: 0.002695751143619418
2023-01-23 03:49:37.236484: step: 708/529, loss: 0.08103179931640625
2023-01-23 03:49:38.337651: step: 712/529, loss: 0.024988271296024323
2023-01-23 03:49:39.458318: step: 716/529, loss: 0.0007702827570028603
2023-01-23 03:49:40.561769: step: 720/529, loss: 4.425048973644152e-05
2023-01-23 03:49:41.675512: step: 724/529, loss: 0.0004734992980957031
2023-01-23 03:49:42.768965: step: 728/529, loss: 0.00011892318434547633
2023-01-23 03:49:43.890363: step: 732/529, loss: 0.005088520236313343
2023-01-23 03:49:45.013588: step: 736/529, loss: 0.009314918890595436
2023-01-23 03:49:46.125345: step: 740/529, loss: 0.005568313878029585
2023-01-23 03:49:47.225201: step: 744/529, loss: 0.03599729761481285
2023-01-23 03:49:48.315430: step: 748/529, loss: 5.14984139954322e-06
2023-01-23 03:49:49.410256: step: 752/529, loss: 0.02781515195965767
2023-01-23 03:49:50.523645: step: 756/529, loss: 0.1732281595468521
2023-01-23 03:49:51.661653: step: 760/529, loss: 0.009294891729950905
2023-01-23 03:49:52.775912: step: 764/529, loss: 0.026825524866580963
2023-01-23 03:49:53.888806: step: 768/529, loss: 0.00013275146193336695
2023-01-23 03:49:55.011739: step: 772/529, loss: 0.00018062590970657766
2023-01-23 03:49:56.105389: step: 776/529, loss: 0.0003990173281636089
2023-01-23 03:49:57.203312: step: 780/529, loss: 0.01617913320660591
2023-01-23 03:49:58.318922: step: 784/529, loss: 0.008256912231445312
2023-01-23 03:49:59.421931: step: 788/529, loss: 0.02213773876428604
2023-01-23 03:50:00.522695: step: 792/529, loss: 0.0031621933449059725
2023-01-23 03:50:01.636003: step: 796/529, loss: 0.07532644271850586
2023-01-23 03:50:02.751941: step: 800/529, loss: 0.0036155700217932463
2023-01-23 03:50:03.884677: step: 804/529, loss: 0.0035490035079419613
2023-01-23 03:50:04.984673: step: 808/529, loss: 7.724762326688506e-06
2023-01-23 03:50:06.111540: step: 812/529, loss: 0.015631485730409622
2023-01-23 03:50:07.246113: step: 816/529, loss: 0.06131019815802574
2023-01-23 03:50:08.347850: step: 820/529, loss: 0.02664356306195259
2023-01-23 03:50:09.448845: step: 824/529, loss: 0.010900306515395641
2023-01-23 03:50:10.554497: step: 828/529, loss: 0.001399993896484375
2023-01-23 03:50:11.658962: step: 832/529, loss: 0.002303504850715399
2023-01-23 03:50:12.775844: step: 836/529, loss: 0.0019275665981695056
2023-01-23 03:50:13.921303: step: 840/529, loss: 0.0014806748367846012
2023-01-23 03:50:15.007836: step: 844/529, loss: 0.004483222961425781
2023-01-23 03:50:16.113052: step: 848/529, loss: 0.031519509851932526
2023-01-23 03:50:17.214439: step: 852/529, loss: 0.0001905441313283518
2023-01-23 03:50:18.314639: step: 856/529, loss: 0.0016553879249840975
2023-01-23 03:50:19.469277: step: 860/529, loss: 0.028945446014404297
2023-01-23 03:50:20.588681: step: 864/529, loss: 0.0028638362418860197
2023-01-23 03:50:21.677393: step: 868/529, loss: 0.002261257264763117
2023-01-23 03:50:22.845987: step: 872/529, loss: 0.00027875902014784515
2023-01-23 03:50:23.953610: step: 876/529, loss: 3.14235694531817e-05
2023-01-23 03:50:25.058788: step: 880/529, loss: 6.065369234420359e-05
2023-01-23 03:50:26.184959: step: 884/529, loss: 0.015969276428222656
2023-01-23 03:50:27.283241: step: 888/529, loss: 0.00020036697969771922
2023-01-23 03:50:28.390281: step: 892/529, loss: 0.0001226902095368132
2023-01-23 03:50:29.505477: step: 896/529, loss: 0.010181712917983532
2023-01-23 03:50:30.627403: step: 900/529, loss: 0.00031824110192246735
2023-01-23 03:50:31.747668: step: 904/529, loss: 0.02685851976275444
2023-01-23 03:50:32.859950: step: 908/529, loss: -1.068115216185106e-05
2023-01-23 03:50:33.944128: step: 912/529, loss: 0.0007848739624023438
2023-01-23 03:50:35.047876: step: 916/529, loss: 0.017832279205322266
2023-01-23 03:50:36.172363: step: 920/529, loss: 0.017981721088290215
2023-01-23 03:50:37.300311: step: 924/529, loss: 0.8941981792449951
2023-01-23 03:50:38.413161: step: 928/529, loss: 0.0027111053932458162
2023-01-23 03:50:39.538169: step: 932/529, loss: 0.0010915757156908512
2023-01-23 03:50:40.634054: step: 936/529, loss: 0.007136440835893154
2023-01-23 03:50:41.755451: step: 940/529, loss: 6.84738188283518e-05
2023-01-23 03:50:42.876761: step: 944/529, loss: 0.00024788378505036235
2023-01-23 03:50:43.976745: step: 948/529, loss: 3.266334533691406e-05
2023-01-23 03:50:45.074041: step: 952/529, loss: 5.846023850608617e-05
2023-01-23 03:50:46.200202: step: 956/529, loss: 0.0003006935294251889
2023-01-23 03:50:47.317287: step: 960/529, loss: 0.0004750251828227192
2023-01-23 03:50:48.449374: step: 964/529, loss: 0.0004093170282430947
2023-01-23 03:50:49.513756: step: 968/529, loss: 0.006163883488625288
2023-01-23 03:50:50.637563: step: 972/529, loss: 0.0003914833068847656
2023-01-23 03:50:51.760302: step: 976/529, loss: 0.02201995812356472
2023-01-23 03:50:52.888387: step: 980/529, loss: 0.0007093429449014366
2023-01-23 03:50:53.987426: step: 984/529, loss: 0.01027908269315958
2023-01-23 03:50:55.149260: step: 988/529, loss: 0.0004440307675395161
2023-01-23 03:50:56.257510: step: 992/529, loss: 0.05865812301635742
2023-01-23 03:50:57.356857: step: 996/529, loss: 0.024614524096250534
2023-01-23 03:50:58.462202: step: 1000/529, loss: 0.0036050318740308285
2023-01-23 03:50:59.575892: step: 1004/529, loss: 0.0009887695778161287
2023-01-23 03:51:00.691232: step: 1008/529, loss: 0.024555588141083717
2023-01-23 03:51:01.791142: step: 1012/529, loss: 0.00018520356388762593
2023-01-23 03:51:02.907362: step: 1016/529, loss: 0.0006617546314373612
2023-01-23 03:51:04.023163: step: 1020/529, loss: 0.001563263009302318
2023-01-23 03:51:05.159702: step: 1024/529, loss: 0.00018014907254837453
2023-01-23 03:51:06.283343: step: 1028/529, loss: 0.00782079715281725
2023-01-23 03:51:07.420744: step: 1032/529, loss: 0.0005350112915039062
2023-01-23 03:51:08.537772: step: 1036/529, loss: 0.0004913330194540322
2023-01-23 03:51:09.711016: step: 1040/529, loss: 0.0004896164173260331
2023-01-23 03:51:10.819860: step: 1044/529, loss: 0.0010759353172034025
2023-01-23 03:51:11.924046: step: 1048/529, loss: 0.01298608910292387
2023-01-23 03:51:13.037703: step: 1052/529, loss: 0.00133686070330441
2023-01-23 03:51:14.136666: step: 1056/529, loss: 0.008045865222811699
2023-01-23 03:51:15.250534: step: 1060/529, loss: 0.0009768486488610506
2023-01-23 03:51:16.382874: step: 1064/529, loss: 0.0010396003490313888
2023-01-23 03:51:17.474255: step: 1068/529, loss: 0.013844775967299938
2023-01-23 03:51:18.567898: step: 1072/529, loss: 0.04795026779174805
2023-01-23 03:51:19.721893: step: 1076/529, loss: 0.04873504862189293
2023-01-23 03:51:20.820270: step: 1080/529, loss: 0.0020037651993334293
2023-01-23 03:51:21.943608: step: 1084/529, loss: 0.00018558502779342234
2023-01-23 03:51:23.065567: step: 1088/529, loss: 0.029660606756806374
2023-01-23 03:51:24.180481: step: 1092/529, loss: 0.0016973495949059725
2023-01-23 03:51:25.323032: step: 1096/529, loss: 0.0004295349062886089
2023-01-23 03:51:26.409799: step: 1100/529, loss: 0.0003998756583314389
2023-01-23 03:51:27.521558: step: 1104/529, loss: 9.365082223666832e-05
2023-01-23 03:51:28.654958: step: 1108/529, loss: 0.003821754362434149
2023-01-23 03:51:29.729317: step: 1112/529, loss: 0.010478687472641468
2023-01-23 03:51:30.829943: step: 1116/529, loss: 0.00570602435618639
2023-01-23 03:51:31.959545: step: 1120/529, loss: 0.0005778313498012722
2023-01-23 03:51:33.072188: step: 1124/529, loss: 0.0006515979766845703
2023-01-23 03:51:34.169911: step: 1128/529, loss: 0.00044827460078522563
2023-01-23 03:51:35.249414: step: 1132/529, loss: 0.002516245935112238
2023-01-23 03:51:36.379315: step: 1136/529, loss: 0.14684423804283142
2023-01-23 03:51:37.492839: step: 1140/529, loss: 0.0006649970891885459
2023-01-23 03:51:38.596347: step: 1144/529, loss: 2.346038854739163e-05
2023-01-23 03:51:39.704724: step: 1148/529, loss: 0.0003563404025044292
2023-01-23 03:51:40.837627: step: 1152/529, loss: 0.0018716811900958419
2023-01-23 03:51:41.970987: step: 1156/529, loss: 0.03818530961871147
2023-01-23 03:51:43.104610: step: 1160/529, loss: 0.010581206530332565
2023-01-23 03:51:44.221667: step: 1164/529, loss: 0.0004951476585119963
2023-01-23 03:51:45.353705: step: 1168/529, loss: 0.0015140533214434981
2023-01-23 03:51:46.456201: step: 1172/529, loss: 3.528594970703125e-05
2023-01-23 03:51:47.570944: step: 1176/529, loss: 0.2581014633178711
2023-01-23 03:51:48.666604: step: 1180/529, loss: 0.007263565436005592
2023-01-23 03:51:49.761722: step: 1184/529, loss: 0.0006606102106161416
2023-01-23 03:51:50.843398: step: 1188/529, loss: 0.004563236143440008
2023-01-23 03:51:51.955144: step: 1192/529, loss: 0.009277725592255592
2023-01-23 03:51:53.048553: step: 1196/529, loss: 0.00015840530977584422
2023-01-23 03:51:54.154197: step: 1200/529, loss: 0.001851844834163785
2023-01-23 03:51:55.326709: step: 1204/529, loss: 0.009067822247743607
2023-01-23 03:51:56.401376: step: 1208/529, loss: 0.00018033981905318797
2023-01-23 03:51:57.498470: step: 1212/529, loss: 0.001878175069577992
2023-01-23 03:51:58.590397: step: 1216/529, loss: 0.002087879227474332
2023-01-23 03:51:59.704113: step: 1220/529, loss: 0.03204955905675888
2023-01-23 03:52:00.836197: step: 1224/529, loss: 0.00027046201284974813
2023-01-23 03:52:01.962571: step: 1228/529, loss: 0.002836894942447543
2023-01-23 03:52:03.102564: step: 1232/529, loss: 0.0004068374400958419
2023-01-23 03:52:04.207406: step: 1236/529, loss: 2.746581958490424e-05
2023-01-23 03:52:05.346297: step: 1240/529, loss: 0.09197786450386047
2023-01-23 03:52:06.440631: step: 1244/529, loss: 0.056519556790590286
2023-01-23 03:52:07.544305: step: 1248/529, loss: 0.006399346049875021
2023-01-23 03:52:08.631042: step: 1252/529, loss: 0.0005100727430544794
2023-01-23 03:52:09.734961: step: 1256/529, loss: 0.00021066666522528976
2023-01-23 03:52:10.824248: step: 1260/529, loss: 0.007651233579963446
2023-01-23 03:52:11.950839: step: 1264/529, loss: 0.0013234138023108244
2023-01-23 03:52:13.035510: step: 1268/529, loss: 0.06373654305934906
2023-01-23 03:52:14.132752: step: 1272/529, loss: -1.4877318790240679e-05
2023-01-23 03:52:15.223518: step: 1276/529, loss: 1.6212466107390355e-06
2023-01-23 03:52:16.318778: step: 1280/529, loss: 0.0004873276047874242
2023-01-23 03:52:17.445431: step: 1284/529, loss: 0.011513615027070045
2023-01-23 03:52:18.546290: step: 1288/529, loss: 0.0006726265419274569
2023-01-23 03:52:19.642129: step: 1292/529, loss: 0.0005554198869504035
2023-01-23 03:52:20.747346: step: 1296/529, loss: 0.02368316799402237
2023-01-23 03:52:21.860538: step: 1300/529, loss: 0.019910622388124466
2023-01-23 03:52:22.975394: step: 1304/529, loss: 0.03583727404475212
2023-01-23 03:52:24.085092: step: 1308/529, loss: 0.0019070626003667712
2023-01-23 03:52:25.179271: step: 1312/529, loss: 2.8856097742391285e-06
2023-01-23 03:52:26.290494: step: 1316/529, loss: 0.0004150390741415322
2023-01-23 03:52:27.410720: step: 1320/529, loss: 0.00015940220328047872
2023-01-23 03:52:28.551884: step: 1324/529, loss: 0.00286788959056139
2023-01-23 03:52:29.667900: step: 1328/529, loss: 0.0075577739626169205
2023-01-23 03:52:30.773790: step: 1332/529, loss: 0.00010166168067371473
2023-01-23 03:52:31.889956: step: 1336/529, loss: 0.0002239704190287739
2023-01-23 03:52:33.022911: step: 1340/529, loss: 0.4347163736820221
2023-01-23 03:52:34.120870: step: 1344/529, loss: 1.0013580322265625e-05
2023-01-23 03:52:35.237669: step: 1348/529, loss: 0.0404568687081337
2023-01-23 03:52:36.340815: step: 1352/529, loss: 0.007117748726159334
2023-01-23 03:52:37.449776: step: 1356/529, loss: 0.00026063917903229594
2023-01-23 03:52:38.547760: step: 1360/529, loss: 0.016696738079190254
2023-01-23 03:52:39.685591: step: 1364/529, loss: 0.04320878908038139
2023-01-23 03:52:40.822524: step: 1368/529, loss: 0.0007826805231161416
2023-01-23 03:52:41.926737: step: 1372/529, loss: 0.005545139312744141
2023-01-23 03:52:43.000625: step: 1376/529, loss: 0.0026499389205127954
2023-01-23 03:52:44.094500: step: 1380/529, loss: 0.000301361083984375
2023-01-23 03:52:45.190864: step: 1384/529, loss: 0.00021457672119140625
2023-01-23 03:52:46.286679: step: 1388/529, loss: 0.00017261505126953125
2023-01-23 03:52:47.402351: step: 1392/529, loss: 0.001270294189453125
2023-01-23 03:52:48.521595: step: 1396/529, loss: 0.006884270813316107
2023-01-23 03:52:49.626776: step: 1400/529, loss: 0.003435802645981312
2023-01-23 03:52:50.729647: step: 1404/529, loss: 0.0012341499095782638
2023-01-23 03:52:51.830702: step: 1408/529, loss: 0.007880115881562233
2023-01-23 03:52:52.975203: step: 1412/529, loss: 0.003738784696906805
2023-01-23 03:52:54.080203: step: 1416/529, loss: 0.000274658203125
2023-01-23 03:52:55.206572: step: 1420/529, loss: -1.3828277587890625e-05
2023-01-23 03:52:56.327823: step: 1424/529, loss: 0.01891174353659153
2023-01-23 03:52:57.434681: step: 1428/529, loss: 0.04813346639275551
2023-01-23 03:52:58.556450: step: 1432/529, loss: 0.02498798258602619
2023-01-23 03:52:59.668000: step: 1436/529, loss: 0.017072487622499466
2023-01-23 03:53:00.761513: step: 1440/529, loss: 0.005184078589081764
2023-01-23 03:53:01.876605: step: 1444/529, loss: 0.00177173619158566
2023-01-23 03:53:02.973260: step: 1448/529, loss: 0.001831150148063898
2023-01-23 03:53:04.107491: step: 1452/529, loss: 0.002214884851127863
2023-01-23 03:53:05.245269: step: 1456/529, loss: 0.0010780334705486894
2023-01-23 03:53:06.370322: step: 1460/529, loss: 0.0035539628006517887
2023-01-23 03:53:07.486179: step: 1464/529, loss: 0.010195350274443626
2023-01-23 03:53:08.583638: step: 1468/529, loss: 7.381439354503527e-05
2023-01-23 03:53:09.679001: step: 1472/529, loss: 0.00023307801166083664
2023-01-23 03:53:10.787764: step: 1476/529, loss: 7.03811674611643e-05
2023-01-23 03:53:11.875956: step: 1480/529, loss: 0.021119307726621628
2023-01-23 03:53:12.975104: step: 1484/529, loss: 0.00022010804968886077
2023-01-23 03:53:14.058859: step: 1488/529, loss: 0.005672645289450884
2023-01-23 03:53:15.137202: step: 1492/529, loss: 5.5027012422215194e-05
2023-01-23 03:53:16.234048: step: 1496/529, loss: 0.008964920416474342
2023-01-23 03:53:17.385035: step: 1500/529, loss: 0.004028368275612593
2023-01-23 03:53:18.464293: step: 1504/529, loss: 0.015865325927734375
2023-01-23 03:53:19.603887: step: 1508/529, loss: 0.7701981067657471
2023-01-23 03:53:20.700330: step: 1512/529, loss: -1.1920928955078125e-06
2023-01-23 03:53:21.813614: step: 1516/529, loss: 0.014901733957231045
2023-01-23 03:53:22.950882: step: 1520/529, loss: 0.0008633613470010459
2023-01-23 03:53:24.077795: step: 1524/529, loss: 0.002908897353336215
2023-01-23 03:53:25.223885: step: 1528/529, loss: -4.673003786592744e-06
2023-01-23 03:53:26.346614: step: 1532/529, loss: 0.0021669387351721525
2023-01-23 03:53:27.449027: step: 1536/529, loss: 0.5673606991767883
2023-01-23 03:53:28.538126: step: 1540/529, loss: 0.0021881582215428352
2023-01-23 03:53:29.660518: step: 1544/529, loss: 0.05304775387048721
2023-01-23 03:53:30.768014: step: 1548/529, loss: 3.4332275390625e-05
2023-01-23 03:53:31.893272: step: 1552/529, loss: 0.008408928290009499
2023-01-23 03:53:32.991205: step: 1556/529, loss: 2.1743775505456142e-05
2023-01-23 03:53:34.108493: step: 1560/529, loss: 0.05852699652314186
2023-01-23 03:53:35.200958: step: 1564/529, loss: 0.0036611557006835938
2023-01-23 03:53:36.305376: step: 1568/529, loss: 5.550384594243951e-05
2023-01-23 03:53:37.397812: step: 1572/529, loss: 0.00034048559609800577
2023-01-23 03:53:38.493751: step: 1576/529, loss: 0.08137702941894531
2023-01-23 03:53:39.635279: step: 1580/529, loss: 0.0020496367942541838
2023-01-23 03:53:40.744846: step: 1584/529, loss: 0.03141505643725395
2023-01-23 03:53:41.835629: step: 1588/529, loss: 0.0007108688587322831
2023-01-23 03:53:42.967606: step: 1592/529, loss: 0.00016412735567428172
2023-01-23 03:53:44.120926: step: 1596/529, loss: 1.2492332458496094
2023-01-23 03:53:45.219681: step: 1600/529, loss: 0.04213924705982208
2023-01-23 03:53:46.333717: step: 1604/529, loss: 0.0007680415874347091
2023-01-23 03:53:47.427869: step: 1608/529, loss: 1.106262243411038e-05
2023-01-23 03:53:48.544946: step: 1612/529, loss: 0.002388191409409046
2023-01-23 03:53:49.698233: step: 1616/529, loss: 0.015336036682128906
2023-01-23 03:53:50.793370: step: 1620/529, loss: 0.00013313292583916336
2023-01-23 03:53:51.909176: step: 1624/529, loss: 0.004322623834013939
2023-01-23 03:53:53.002370: step: 1628/529, loss: 0.01439743023365736
2023-01-23 03:53:54.144690: step: 1632/529, loss: 0.013621330261230469
2023-01-23 03:53:55.255460: step: 1636/529, loss: 2.7370453608455136e-05
2023-01-23 03:53:56.370512: step: 1640/529, loss: 1.4066696166992188e-05
2023-01-23 03:53:57.502135: step: 1644/529, loss: 0.00033760073711164296
2023-01-23 03:53:58.597184: step: 1648/529, loss: 0.04081978648900986
2023-01-23 03:53:59.723078: step: 1652/529, loss: 0.0015802383422851562
2023-01-23 03:54:00.883869: step: 1656/529, loss: 0.01882457733154297
2023-01-23 03:54:01.981154: step: 1660/529, loss: 0.0020250321831554174
2023-01-23 03:54:03.061655: step: 1664/529, loss: 0.003597450442612171
2023-01-23 03:54:04.210480: step: 1668/529, loss: 0.035089682787656784
2023-01-23 03:54:05.323419: step: 1672/529, loss: 0.003991127014160156
2023-01-23 03:54:06.425595: step: 1676/529, loss: 1.049041748046875e-05
2023-01-23 03:54:07.497661: step: 1680/529, loss: 0.006166267674416304
2023-01-23 03:54:08.621765: step: 1684/529, loss: 0.025664711371064186
2023-01-23 03:54:09.699440: step: 1688/529, loss: 0.3616229295730591
2023-01-23 03:54:10.825801: step: 1692/529, loss: 0.0004459381161723286
2023-01-23 03:54:11.951443: step: 1696/529, loss: 0.010399913415312767
2023-01-23 03:54:13.049523: step: 1700/529, loss: 0.020368624478578568
2023-01-23 03:54:14.165286: step: 1704/529, loss: 0.0010580063099041581
2023-01-23 03:54:15.301651: step: 1708/529, loss: 3.080368333030492e-05
2023-01-23 03:54:16.419209: step: 1712/529, loss: 0.05797433853149414
2023-01-23 03:54:17.519282: step: 1716/529, loss: 0.012995148077607155
2023-01-23 03:54:18.627804: step: 1720/529, loss: 0.00011148452904308215
2023-01-23 03:54:19.729077: step: 1724/529, loss: 0.04312143474817276
2023-01-23 03:54:20.832764: step: 1728/529, loss: 0.04819145053625107
2023-01-23 03:54:21.924586: step: 1732/529, loss: 0.024585723876953125
2023-01-23 03:54:23.016763: step: 1736/529, loss: 0.0012557030422613025
2023-01-23 03:54:24.141396: step: 1740/529, loss: 0.010304260067641735
2023-01-23 03:54:25.217379: step: 1744/529, loss: 0.0007087707635946572
2023-01-23 03:54:26.335137: step: 1748/529, loss: 0.0021219253540039062
2023-01-23 03:54:27.446785: step: 1752/529, loss: 0.0021059990394860506
2023-01-23 03:54:28.549113: step: 1756/529, loss: 4.1770937968976796e-05
2023-01-23 03:54:29.677920: step: 1760/529, loss: 0.0029232024680823088
2023-01-23 03:54:30.785893: step: 1764/529, loss: 0.0004554748593363911
2023-01-23 03:54:31.867080: step: 1768/529, loss: 1.7547608877066523e-05
2023-01-23 03:54:32.980911: step: 1772/529, loss: 0.06798458099365234
2023-01-23 03:54:34.107312: step: 1776/529, loss: 0.03369732201099396
2023-01-23 03:54:35.179636: step: 1780/529, loss: 0.0004027843533549458
2023-01-23 03:54:36.277789: step: 1784/529, loss: 0.014034987427294254
2023-01-23 03:54:37.381819: step: 1788/529, loss: 0.0003894329129252583
2023-01-23 03:54:38.499436: step: 1792/529, loss: 0.0487096793949604
2023-01-23 03:54:39.584678: step: 1796/529, loss: 0.00046291350736282766
2023-01-23 03:54:40.719896: step: 1800/529, loss: 0.0002025604189839214
2023-01-23 03:54:41.816633: step: 1804/529, loss: 0.02630739100277424
2023-01-23 03:54:42.955191: step: 1808/529, loss: 0.0006984710926190019
2023-01-23 03:54:44.059840: step: 1812/529, loss: 0.009124946780502796
2023-01-23 03:54:45.194728: step: 1816/529, loss: 0.05882749333977699
2023-01-23 03:54:46.318552: step: 1820/529, loss: 3.237724376958795e-05
2023-01-23 03:54:47.423459: step: 1824/529, loss: 0.0009759903186932206
2023-01-23 03:54:48.560168: step: 1828/529, loss: 0.07676620781421661
2023-01-23 03:54:49.653206: step: 1832/529, loss: 0.00011663437180686742
2023-01-23 03:54:50.773376: step: 1836/529, loss: 0.021224021911621094
2023-01-23 03:54:51.880540: step: 1840/529, loss: 0.019350243732333183
2023-01-23 03:54:52.972006: step: 1844/529, loss: 0.007243919186294079
2023-01-23 03:54:54.084765: step: 1848/529, loss: 0.0014892577892169356
2023-01-23 03:54:55.206411: step: 1852/529, loss: 0.030296802520751953
2023-01-23 03:54:56.317500: step: 1856/529, loss: 0.008112716488540173
2023-01-23 03:54:57.442413: step: 1860/529, loss: 0.00026006699772551656
2023-01-23 03:54:58.541787: step: 1864/529, loss: 0.007880019955337048
2023-01-23 03:54:59.646815: step: 1868/529, loss: 0.0003829956112895161
2023-01-23 03:55:00.773755: step: 1872/529, loss: 0.07741031050682068
2023-01-23 03:55:01.906283: step: 1876/529, loss: 0.028162576258182526
2023-01-23 03:55:03.035844: step: 1880/529, loss: 0.0015431403880938888
2023-01-23 03:55:04.142260: step: 1884/529, loss: 0.004068565554916859
2023-01-23 03:55:05.234694: step: 1888/529, loss: 0.0016448021633550525
2023-01-23 03:55:06.328937: step: 1892/529, loss: 0.009966659359633923
2023-01-23 03:55:07.412544: step: 1896/529, loss: 0.00016231538029387593
2023-01-23 03:55:08.504448: step: 1900/529, loss: 0.0016377449501305819
2023-01-23 03:55:09.646025: step: 1904/529, loss: 0.0023283003829419613
2023-01-23 03:55:10.775477: step: 1908/529, loss: 0.00015869141498114914
2023-01-23 03:55:11.886551: step: 1912/529, loss: 0.0021070719230920076
2023-01-23 03:55:12.972265: step: 1916/529, loss: 7.781982276355848e-05
2023-01-23 03:55:14.110643: step: 1920/529, loss: 0.0002738475741352886
2023-01-23 03:55:15.277053: step: 1924/529, loss: 0.0158906951546669
2023-01-23 03:55:16.404852: step: 1928/529, loss: 0.0011287688976153731
2023-01-23 03:55:17.489083: step: 1932/529, loss: 0.009584140963852406
2023-01-23 03:55:18.624210: step: 1936/529, loss: 0.0729038268327713
2023-01-23 03:55:19.724001: step: 1940/529, loss: 0.009826993569731712
2023-01-23 03:55:20.838603: step: 1944/529, loss: 0.028536701574921608
2023-01-23 03:55:21.933971: step: 1948/529, loss: 0.00018758774967864156
2023-01-23 03:55:23.024162: step: 1952/529, loss: 0.00035581589327193797
2023-01-23 03:55:24.139450: step: 1956/529, loss: -6.67572021484375e-06
2023-01-23 03:55:25.250904: step: 1960/529, loss: 6.680488877464086e-05
2023-01-23 03:55:26.368266: step: 1964/529, loss: 1.912116931634955e-05
2023-01-23 03:55:27.506452: step: 1968/529, loss: 0.00015220641216728836
2023-01-23 03:55:28.603618: step: 1972/529, loss: 0.0015476227272301912
2023-01-23 03:55:29.707533: step: 1976/529, loss: 0.00914688128978014
2023-01-23 03:55:30.796891: step: 1980/529, loss: 0.00144872663076967
2023-01-23 03:55:31.898521: step: 1984/529, loss: 0.0004364967462606728
2023-01-23 03:55:33.040986: step: 1988/529, loss: 0.0039215087890625
2023-01-23 03:55:34.127175: step: 1992/529, loss: 1.029968279908644e-05
2023-01-23 03:55:35.253494: step: 1996/529, loss: 2.727508581301663e-05
2023-01-23 03:55:36.350192: step: 2000/529, loss: 0.016031980514526367
2023-01-23 03:55:37.453575: step: 2004/529, loss: 0.0006994247669354081
2023-01-23 03:55:38.545689: step: 2008/529, loss: 0.06915827095508575
2023-01-23 03:55:39.679632: step: 2012/529, loss: 0.0018802642589434981
2023-01-23 03:55:40.780056: step: 2016/529, loss: 0.013062858022749424
2023-01-23 03:55:41.885086: step: 2020/529, loss: 0.010177422314882278
2023-01-23 03:55:43.002923: step: 2024/529, loss: 0.0034377097617834806
2023-01-23 03:55:44.107683: step: 2028/529, loss: 0.00869131088256836
2023-01-23 03:55:45.225277: step: 2032/529, loss: 2.3651124138268642e-05
2023-01-23 03:55:46.323103: step: 2036/529, loss: 0.037790872156620026
2023-01-23 03:55:47.420881: step: 2040/529, loss: 0.029758168384432793
2023-01-23 03:55:48.512433: step: 2044/529, loss: 0.03365917131304741
2023-01-23 03:55:49.632410: step: 2048/529, loss: 0.013937568292021751
2023-01-23 03:55:50.731702: step: 2052/529, loss: -4.9591067181609105e-06
2023-01-23 03:55:51.813018: step: 2056/529, loss: 3.643035961431451e-05
2023-01-23 03:55:52.928465: step: 2060/529, loss: 0.01580982096493244
2023-01-23 03:55:54.030698: step: 2064/529, loss: 0.0012409688206389546
2023-01-23 03:55:55.158256: step: 2068/529, loss: 0.0008633614052087069
2023-01-23 03:55:56.256256: step: 2072/529, loss: 0.01094207726418972
2023-01-23 03:55:57.346146: step: 2076/529, loss: 0.015546416863799095
2023-01-23 03:55:58.467740: step: 2080/529, loss: 0.0002918243408203125
2023-01-23 03:55:59.599166: step: 2084/529, loss: 0.001398277236148715
2023-01-23 03:56:00.707891: step: 2088/529, loss: 0.001557350275106728
2023-01-23 03:56:01.810641: step: 2092/529, loss: 3.013610876223538e-05
2023-01-23 03:56:02.919401: step: 2096/529, loss: 0.012003613635897636
2023-01-23 03:56:04.029399: step: 2100/529, loss: 0.01590251922607422
2023-01-23 03:56:05.153804: step: 2104/529, loss: 0.001154136611148715
2023-01-23 03:56:06.288198: step: 2108/529, loss: 0.0012329102028161287
2023-01-23 03:56:07.413552: step: 2112/529, loss: 0.001546669052913785
2023-01-23 03:56:08.501900: step: 2116/529, loss: 0.05431947857141495
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.5945674044265593, 'r': 0.7869507323568575, 'f1': 0.6773638968481376}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6358950328022493, 'r': 0.7658013544018059, 'f1': 0.6948284690220173}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.5882352941176471, 'r': 0.9259259259259259, 'f1': 0.7194244604316546}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6, 'r': 0.5238095238095238, 'f1': 0.559322033898305}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.375, 'r': 0.5, 'f1': 0.42857142857142855}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 26
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:56:48.304822: step: 4/529, loss: 0.013025665655732155
2023-01-23 03:56:49.463941: step: 8/529, loss: 0.0027847292367368937
2023-01-23 03:56:50.556313: step: 12/529, loss: 9.34600848268019e-06
2023-01-23 03:56:51.627963: step: 16/529, loss: 0.0058952332474291325
2023-01-23 03:56:52.729234: step: 20/529, loss: 8.40187058201991e-05
2023-01-23 03:56:53.831531: step: 24/529, loss: 1.0013579867518274e-06
2023-01-23 03:56:54.947052: step: 28/529, loss: 0.00048770903958939016
2023-01-23 03:56:56.032604: step: 32/529, loss: 0.0002868652518372983
2023-01-23 03:56:57.129134: step: 36/529, loss: 0.011477470397949219
2023-01-23 03:56:58.253287: step: 40/529, loss: 0.03354759141802788
2023-01-23 03:56:59.362919: step: 44/529, loss: 0.0010120392544195056
2023-01-23 03:57:00.464571: step: 48/529, loss: 0.00029969215393066406
2023-01-23 03:57:01.553298: step: 52/529, loss: 6.303787813521922e-05
2023-01-23 03:57:02.673276: step: 56/529, loss: 5.588531348621473e-05
2023-01-23 03:57:03.771641: step: 60/529, loss: 0.05170316621661186
2023-01-23 03:57:04.896808: step: 64/529, loss: 0.021767234429717064
2023-01-23 03:57:05.992443: step: 68/529, loss: 0.03834161534905434
2023-01-23 03:57:07.106140: step: 72/529, loss: 0.00029392243595793843
2023-01-23 03:57:08.190211: step: 76/529, loss: 7.276535325217992e-05
2023-01-23 03:57:09.311428: step: 80/529, loss: 3.4332276754867053e-06
2023-01-23 03:57:10.419887: step: 84/529, loss: 0.0021758077200502157
2023-01-23 03:57:11.507739: step: 88/529, loss: 0.0002058029203908518
2023-01-23 03:57:12.597316: step: 92/529, loss: 8.487701052217744e-06
2023-01-23 03:57:13.709719: step: 96/529, loss: 0.0054690358228981495
2023-01-23 03:57:14.809336: step: 100/529, loss: 0.02786245383322239
2023-01-23 03:57:15.891000: step: 104/529, loss: 0.20832061767578125
2023-01-23 03:57:17.004503: step: 108/529, loss: 0.0001484871027059853
2023-01-23 03:57:18.112504: step: 112/529, loss: 0.002085351850837469
2023-01-23 03:57:19.234324: step: 116/529, loss: 0.0005060195690020919
2023-01-23 03:57:20.298810: step: 120/529, loss: -1.23977656585339e-06
2023-01-23 03:57:21.394816: step: 124/529, loss: 3.14712519866589e-06
2023-01-23 03:57:22.496919: step: 128/529, loss: 6.713867333019152e-05
2023-01-23 03:57:23.603504: step: 132/529, loss: 0.0018955230480059981
2023-01-23 03:57:24.774451: step: 136/529, loss: 0.0005881786346435547
2023-01-23 03:57:25.871544: step: 140/529, loss: 5.187988426769152e-05
2023-01-23 03:57:26.964734: step: 144/529, loss: 0.047556400299072266
2023-01-23 03:57:28.091577: step: 148/529, loss: 0.0008852005121298134
2023-01-23 03:57:29.175509: step: 152/529, loss: 1.5401839846163057e-05
2023-01-23 03:57:30.269385: step: 156/529, loss: 6.6784028604161e-05
2023-01-23 03:57:31.374926: step: 160/529, loss: 3.280639793956652e-05
2023-01-23 03:57:32.473466: step: 164/529, loss: 0.005192136857658625
2023-01-23 03:57:33.622291: step: 168/529, loss: 0.01980915106832981
2023-01-23 03:57:34.748613: step: 172/529, loss: 0.0140380859375
2023-01-23 03:57:35.823796: step: 176/529, loss: 0.00016603470430709422
2023-01-23 03:57:36.971817: step: 180/529, loss: 6.427764310501516e-05
2023-01-23 03:57:38.083163: step: 184/529, loss: 4.405975778354332e-05
2023-01-23 03:57:39.210009: step: 188/529, loss: 1.9550323031580774e-06
2023-01-23 03:57:40.309588: step: 192/529, loss: 2.784729076665826e-05
2023-01-23 03:57:41.420102: step: 196/529, loss: -6.48498553346144e-06
2023-01-23 03:57:42.587061: step: 200/529, loss: 0.008663367480039597
2023-01-23 03:57:43.705912: step: 204/529, loss: 0.010529518127441406
2023-01-23 03:57:44.786786: step: 208/529, loss: 0.00012340545072220266
2023-01-23 03:57:45.917226: step: 212/529, loss: 0.005165386013686657
2023-01-23 03:57:47.032699: step: 216/529, loss: 0.002931022783741355
2023-01-23 03:57:48.176736: step: 220/529, loss: 0.00018577575974632055
2023-01-23 03:57:49.297890: step: 224/529, loss: 0.04927084594964981
2023-01-23 03:57:50.389242: step: 228/529, loss: 1.6498566765221767e-05
2023-01-23 03:57:51.524355: step: 232/529, loss: 5.030632019042969e-05
2023-01-23 03:57:52.676858: step: 236/529, loss: 5.340576535672881e-06
2023-01-23 03:57:53.797562: step: 240/529, loss: 0.0010513782035559416
2023-01-23 03:57:54.903605: step: 244/529, loss: 0.0006593704456463456
2023-01-23 03:57:56.019914: step: 248/529, loss: 0.04218254238367081
2023-01-23 03:57:57.124902: step: 252/529, loss: 0.0010068893898278475
2023-01-23 03:57:58.226350: step: 256/529, loss: 0.0006353378412313759
2023-01-23 03:57:59.353571: step: 260/529, loss: 0.0013450622791424394
2023-01-23 03:58:00.441697: step: 264/529, loss: 0.00035037993802689016
2023-01-23 03:58:01.562501: step: 268/529, loss: 0.0051208497025072575
2023-01-23 03:58:02.657511: step: 272/529, loss: 0.03809080272912979
2023-01-23 03:58:03.762557: step: 276/529, loss: 0.05685706064105034
2023-01-23 03:58:04.857114: step: 280/529, loss: 0.009435271844267845
2023-01-23 03:58:05.988172: step: 284/529, loss: 0.1060028150677681
2023-01-23 03:58:07.097680: step: 288/529, loss: 0.06328850239515305
2023-01-23 03:58:08.187422: step: 292/529, loss: 0.008836936205625534
2023-01-23 03:58:09.328628: step: 296/529, loss: 4.1389463149243966e-05
2023-01-23 03:58:10.438992: step: 300/529, loss: 0.08662425726652145
2023-01-23 03:58:11.543950: step: 304/529, loss: 0.06862354278564453
2023-01-23 03:58:12.643025: step: 308/529, loss: 0.002481174422428012
2023-01-23 03:58:13.744197: step: 312/529, loss: 2.0694733393611386e-05
2023-01-23 03:58:14.853058: step: 316/529, loss: 0.00011291504779364914
2023-01-23 03:58:15.931377: step: 320/529, loss: 5.8650970458984375e-05
2023-01-23 03:58:17.041522: step: 324/529, loss: 0.00011100769916083664
2023-01-23 03:58:18.182741: step: 328/529, loss: 0.0003315925714559853
2023-01-23 03:58:19.306040: step: 332/529, loss: 0.0005913734785281122
2023-01-23 03:58:20.406551: step: 336/529, loss: 0.007082748226821423
2023-01-23 03:58:21.469585: step: 340/529, loss: -1.144409225162235e-06
2023-01-23 03:58:22.557125: step: 344/529, loss: 0.0002701759513001889
2023-01-23 03:58:23.648582: step: 348/529, loss: 7.05718994140625e-05
2023-01-23 03:58:24.737473: step: 352/529, loss: 1.296997106692288e-05
2023-01-23 03:58:25.850053: step: 356/529, loss: 1.926422191900201e-05
2023-01-23 03:58:26.970120: step: 360/529, loss: 0.00025048255338333547
2023-01-23 03:58:28.096350: step: 364/529, loss: 0.01147613488137722
2023-01-23 03:58:29.222945: step: 368/529, loss: 0.001139736152254045
2023-01-23 03:58:30.326790: step: 372/529, loss: 0.0008258819580078125
2023-01-23 03:58:31.439493: step: 376/529, loss: 0.0013508796691894531
2023-01-23 03:58:32.542175: step: 380/529, loss: 0.1910679191350937
2023-01-23 03:58:33.641645: step: 384/529, loss: 0.04526319354772568
2023-01-23 03:58:34.744837: step: 388/529, loss: 0.03982257843017578
2023-01-23 03:58:35.872272: step: 392/529, loss: 0.012942124158143997
2023-01-23 03:58:36.971674: step: 396/529, loss: 0.0037052154075354338
2023-01-23 03:58:38.065887: step: 400/529, loss: 0.00827803649008274
2023-01-23 03:58:39.164744: step: 404/529, loss: 8.125305612338707e-05
2023-01-23 03:58:40.258837: step: 408/529, loss: 0.0006135940784588456
2023-01-23 03:58:41.385045: step: 412/529, loss: 1.430511474609375e-05
2023-01-23 03:58:42.487848: step: 416/529, loss: 2.288818359375e-05
2023-01-23 03:58:43.609114: step: 420/529, loss: 0.000404548627557233
2023-01-23 03:58:44.722905: step: 424/529, loss: 0.0029531477484852076
2023-01-23 03:58:45.838911: step: 428/529, loss: 0.0005135536193847656
2023-01-23 03:58:46.947644: step: 432/529, loss: 0.00644607562571764
2023-01-23 03:58:48.080504: step: 436/529, loss: 0.0004478454648051411
2023-01-23 03:58:49.164914: step: 440/529, loss: 7.05719003235572e-06
2023-01-23 03:58:50.249996: step: 444/529, loss: 1.869201696536038e-05
2023-01-23 03:58:51.347640: step: 448/529, loss: 0.004633331671357155
2023-01-23 03:58:52.465372: step: 452/529, loss: 4.00543194700731e-06
2023-01-23 03:58:53.556742: step: 456/529, loss: 0.0007177353254519403
2023-01-23 03:58:54.655566: step: 460/529, loss: 0.1050867810845375
2023-01-23 03:58:55.766538: step: 464/529, loss: 0.00042257309542037547
2023-01-23 03:58:56.889503: step: 468/529, loss: 4.6443939936580136e-05
2023-01-23 03:58:57.982619: step: 472/529, loss: 0.00022220611572265625
2023-01-23 03:58:59.113713: step: 476/529, loss: 0.0016588212456554174
2023-01-23 03:59:00.216538: step: 480/529, loss: 0.006584167946130037
2023-01-23 03:59:01.319617: step: 484/529, loss: 0.00019583702669478953
2023-01-23 03:59:02.452150: step: 488/529, loss: 0.00016369819059036672
2023-01-23 03:59:03.562981: step: 492/529, loss: 0.009474468417465687
2023-01-23 03:59:04.640864: step: 496/529, loss: 2.6226043701171875e-06
2023-01-23 03:59:05.744551: step: 500/529, loss: 0.03279514238238335
2023-01-23 03:59:06.850808: step: 504/529, loss: 0.013543128967285156
2023-01-23 03:59:07.958364: step: 508/529, loss: 0.005602359771728516
2023-01-23 03:59:09.077173: step: 512/529, loss: -6.48498553346144e-06
2023-01-23 03:59:10.178384: step: 516/529, loss: 0.04302806779742241
2023-01-23 03:59:11.266502: step: 520/529, loss: 1.7547608877066523e-05
2023-01-23 03:59:12.376223: step: 524/529, loss: 2.403259350103326e-05
2023-01-23 03:59:13.502488: step: 528/529, loss: 0.0003664970281533897
2023-01-23 03:59:14.625135: step: 532/529, loss: 0.00047162771807052195
2023-01-23 03:59:15.768636: step: 536/529, loss: 4.501343209994957e-05
2023-01-23 03:59:16.893269: step: 540/529, loss: 0.019955063238739967
2023-01-23 03:59:18.004534: step: 544/529, loss: 9.751320612849668e-05
2023-01-23 03:59:19.106826: step: 548/529, loss: 3.852844383800402e-05
2023-01-23 03:59:20.236958: step: 552/529, loss: 0.0004089355352334678
2023-01-23 03:59:21.339136: step: 556/529, loss: 0.014489288441836834
2023-01-23 03:59:22.452025: step: 560/529, loss: 4.482269105210435e-06
2023-01-23 03:59:23.531946: step: 564/529, loss: 0.013504648581147194
2023-01-23 03:59:24.632860: step: 568/529, loss: 0.06941261142492294
2023-01-23 03:59:25.744583: step: 572/529, loss: 0.0018215716117992997
2023-01-23 03:59:26.857238: step: 576/529, loss: 0.02603950724005699
2023-01-23 03:59:27.974580: step: 580/529, loss: 0.009235001169145107
2023-01-23 03:59:29.079071: step: 584/529, loss: 1.716613724056515e-06
2023-01-23 03:59:30.204316: step: 588/529, loss: 0.008207893930375576
2023-01-23 03:59:31.324412: step: 592/529, loss: 3.2336976528167725
2023-01-23 03:59:32.460928: step: 596/529, loss: 0.022122908383607864
2023-01-23 03:59:33.571744: step: 600/529, loss: 5.245208740234375e-05
2023-01-23 03:59:34.702356: step: 604/529, loss: 0.00014190674119163305
2023-01-23 03:59:35.806888: step: 608/529, loss: 0.00774726876989007
2023-01-23 03:59:36.921231: step: 612/529, loss: 0.00158348074182868
2023-01-23 03:59:38.026107: step: 616/529, loss: 0.01694359816610813
2023-01-23 03:59:39.146290: step: 620/529, loss: 0.0017402649391442537
2023-01-23 03:59:40.237758: step: 624/529, loss: 0.04059801250696182
2023-01-23 03:59:41.345097: step: 628/529, loss: 0.03342742845416069
2023-01-23 03:59:42.439690: step: 632/529, loss: 0.0038545611314475536
2023-01-23 03:59:43.516269: step: 636/529, loss: 0.0020542622078210115
2023-01-23 03:59:44.614546: step: 640/529, loss: 0.0344633124768734
2023-01-23 03:59:45.721192: step: 644/529, loss: 0.0003381729475222528
2023-01-23 03:59:46.844519: step: 648/529, loss: 0.0012248993152752519
2023-01-23 03:59:47.956494: step: 652/529, loss: 0.0007341623422689736
2023-01-23 03:59:49.041307: step: 656/529, loss: 0.017383193597197533
2023-01-23 03:59:50.179123: step: 660/529, loss: 0.009919739328324795
2023-01-23 03:59:51.270814: step: 664/529, loss: 0.0011301517952233553
2023-01-23 03:59:52.383732: step: 668/529, loss: 0.029977895319461823
2023-01-23 03:59:53.469638: step: 672/529, loss: 0.0017427444690838456
2023-01-23 03:59:54.574196: step: 676/529, loss: 0.021220874041318893
2023-01-23 03:59:55.660142: step: 680/529, loss: 0.016243362799286842
2023-01-23 03:59:56.788511: step: 684/529, loss: 9.384155418956652e-05
2023-01-23 03:59:57.879363: step: 688/529, loss: 0.00158605573233217
2023-01-23 03:59:58.976243: step: 692/529, loss: 0.1293531358242035
2023-01-23 04:00:00.072416: step: 696/529, loss: 0.006448936183005571
2023-01-23 04:00:01.191310: step: 700/529, loss: 0.0023102760314941406
2023-01-23 04:00:02.287244: step: 704/529, loss: 7.104873020580271e-06
2023-01-23 04:00:03.405776: step: 708/529, loss: 0.12760746479034424
2023-01-23 04:00:04.499665: step: 712/529, loss: 0.0018495559925213456
2023-01-23 04:00:05.576824: step: 716/529, loss: 0.00471839914098382
2023-01-23 04:00:06.671263: step: 720/529, loss: 3.337860107421875e-06
2023-01-23 04:00:07.770467: step: 724/529, loss: 0.04250144958496094
2023-01-23 04:00:08.872514: step: 728/529, loss: 0.053050994873046875
2023-01-23 04:00:09.990655: step: 732/529, loss: 0.0004034042649436742
2023-01-23 04:00:11.089694: step: 736/529, loss: 0.0002035141078522429
2023-01-23 04:00:12.217107: step: 740/529, loss: 0.09148712456226349
2023-01-23 04:00:13.353487: step: 744/529, loss: 0.014636993408203125
2023-01-23 04:00:14.464823: step: 748/529, loss: 0.0017119408585131168
2023-01-23 04:00:15.551512: step: 752/529, loss: 4.310607982915826e-05
2023-01-23 04:00:16.673032: step: 756/529, loss: 0.0004661559942178428
2023-01-23 04:00:17.773893: step: 760/529, loss: 0.006013727281242609
2023-01-23 04:00:18.888294: step: 764/529, loss: 0.00046925543574616313
2023-01-23 04:00:19.994804: step: 768/529, loss: 0.04130706936120987
2023-01-23 04:00:21.135595: step: 772/529, loss: 0.007816696539521217
2023-01-23 04:00:22.260713: step: 776/529, loss: 0.012048817239701748
2023-01-23 04:00:23.350770: step: 780/529, loss: 0.0006542205810546875
2023-01-23 04:00:24.459735: step: 784/529, loss: 0.009632492437958717
2023-01-23 04:00:25.556962: step: 788/529, loss: -8.583067483414197e-07
2023-01-23 04:00:26.680251: step: 792/529, loss: 0.0007371902465820312
2023-01-23 04:00:27.795188: step: 796/529, loss: 0.00015506744966842234
2023-01-23 04:00:28.893970: step: 800/529, loss: 0.00017261505126953125
2023-01-23 04:00:29.983768: step: 804/529, loss: -1.2040136425639503e-06
2023-01-23 04:00:31.092257: step: 808/529, loss: 0.0007036208990029991
2023-01-23 04:00:32.201847: step: 812/529, loss: 0.021425379440188408
2023-01-23 04:00:33.307116: step: 816/529, loss: 0.25662097334861755
2023-01-23 04:00:34.426951: step: 820/529, loss: 0.0047245025634765625
2023-01-23 04:00:35.573464: step: 824/529, loss: 0.0062185293063521385
2023-01-23 04:00:36.681625: step: 828/529, loss: 0.0017829417483881116
2023-01-23 04:00:37.787511: step: 832/529, loss: 4.806518700206652e-05
2023-01-23 04:00:38.910136: step: 836/529, loss: 0.0004596710205078125
2023-01-23 04:00:40.023163: step: 840/529, loss: 2.670288040462765e-06
2023-01-23 04:00:41.149221: step: 844/529, loss: 3.623962356869015e-06
2023-01-23 04:00:42.267100: step: 848/529, loss: 0.04018077999353409
2023-01-23 04:00:43.374872: step: 852/529, loss: 0.22704820334911346
2023-01-23 04:00:44.504150: step: 856/529, loss: 0.0003452301025390625
2023-01-23 04:00:45.604769: step: 860/529, loss: 0.01042270753532648
2023-01-23 04:00:46.710965: step: 864/529, loss: 0.5174850225448608
2023-01-23 04:00:47.817434: step: 868/529, loss: 0.5592904090881348
2023-01-23 04:00:48.919520: step: 872/529, loss: 0.010742664337158203
2023-01-23 04:00:50.018402: step: 876/529, loss: 0.0008894919883459806
2023-01-23 04:00:51.116445: step: 880/529, loss: 0.005408096127212048
2023-01-23 04:00:52.211697: step: 884/529, loss: 0.0006146430969238281
2023-01-23 04:00:53.313479: step: 888/529, loss: 0.04459371790289879
2023-01-23 04:00:54.404244: step: 892/529, loss: 0.0012407302856445312
2023-01-23 04:00:55.509641: step: 896/529, loss: 0.0011411666637286544
2023-01-23 04:00:56.624895: step: 900/529, loss: 0.0003591299173422158
2023-01-23 04:00:57.721570: step: 904/529, loss: 0.0058914185501635075
2023-01-23 04:00:58.813316: step: 908/529, loss: 1.0585785275907256e-05
2023-01-23 04:00:59.930103: step: 912/529, loss: 0.0003442287561483681
2023-01-23 04:01:01.045142: step: 916/529, loss: 0.026396943256258965
2023-01-23 04:01:02.187912: step: 920/529, loss: 0.00126991281285882
2023-01-23 04:01:03.305344: step: 924/529, loss: 0.009387397207319736
2023-01-23 04:01:04.383638: step: 928/529, loss: 0.007410907652229071
2023-01-23 04:01:05.486830: step: 932/529, loss: 0.03458261862397194
2023-01-23 04:01:06.564305: step: 936/529, loss: 0.00617795018479228
2023-01-23 04:01:07.707696: step: 940/529, loss: 0.0156415943056345
2023-01-23 04:01:08.817825: step: 944/529, loss: 0.02698078379034996
2023-01-23 04:01:09.913763: step: 948/529, loss: 0.017787646502256393
2023-01-23 04:01:11.019337: step: 952/529, loss: 0.06816940009593964
2023-01-23 04:01:12.127259: step: 956/529, loss: 0.0009677887428551912
2023-01-23 04:01:13.229223: step: 960/529, loss: 0.006277275271713734
2023-01-23 04:01:14.351525: step: 964/529, loss: 6.160735938465223e-05
2023-01-23 04:01:15.455843: step: 968/529, loss: 0.04080080986022949
2023-01-23 04:01:16.564682: step: 972/529, loss: 0.010431194677948952
2023-01-23 04:01:17.666069: step: 976/529, loss: 0.01596083678305149
2023-01-23 04:01:18.785229: step: 980/529, loss: 0.0007116794586181641
2023-01-23 04:01:19.908641: step: 984/529, loss: 0.001605987548828125
2023-01-23 04:01:21.043489: step: 988/529, loss: 3.337860107421875e-05
2023-01-23 04:01:22.215832: step: 992/529, loss: 0.002616691403090954
2023-01-23 04:01:23.351158: step: 996/529, loss: 0.007730865851044655
2023-01-23 04:01:24.463680: step: 1000/529, loss: 0.0001491546572651714
2023-01-23 04:01:25.587621: step: 1004/529, loss: 0.0003711700264830142
2023-01-23 04:01:26.698536: step: 1008/529, loss: 0.0011664391495287418
2023-01-23 04:01:27.830888: step: 1012/529, loss: -1.583099401614163e-05
2023-01-23 04:01:28.938426: step: 1016/529, loss: 0.007588386535644531
2023-01-23 04:01:30.052893: step: 1020/529, loss: 0.0003841400321107358
2023-01-23 04:01:31.183697: step: 1024/529, loss: 0.0013720989227294922
2023-01-23 04:01:32.290337: step: 1028/529, loss: 0.002115202136337757
2023-01-23 04:01:33.413398: step: 1032/529, loss: 0.012281798757612705
2023-01-23 04:01:34.515827: step: 1036/529, loss: 0.011130142025649548
2023-01-23 04:01:35.622980: step: 1040/529, loss: 6.613731966353953e-05
2023-01-23 04:01:36.753325: step: 1044/529, loss: 0.00023927688016556203
2023-01-23 04:01:37.838099: step: 1048/529, loss: 0.0009638786432333291
2023-01-23 04:01:38.949853: step: 1052/529, loss: 0.02169027365744114
2023-01-23 04:01:40.025252: step: 1056/529, loss: 0.0015693664317950606
2023-01-23 04:01:41.108324: step: 1060/529, loss: 0.0024577141739428043
2023-01-23 04:01:42.218667: step: 1064/529, loss: 0.00015354156494140625
2023-01-23 04:01:43.305859: step: 1068/529, loss: 0.0005867004510946572
2023-01-23 04:01:44.401101: step: 1072/529, loss: 0.005464458838105202
2023-01-23 04:01:45.533385: step: 1076/529, loss: 0.002259588334709406
2023-01-23 04:01:46.648856: step: 1080/529, loss: 0.00015416146197821945
2023-01-23 04:01:47.786392: step: 1084/529, loss: 0.08061598986387253
2023-01-23 04:01:48.861877: step: 1088/529, loss: 0.009635353460907936
2023-01-23 04:01:50.050602: step: 1092/529, loss: 0.03504829481244087
2023-01-23 04:01:51.208105: step: 1096/529, loss: 0.009019183926284313
2023-01-23 04:01:52.343263: step: 1100/529, loss: 0.03563690558075905
2023-01-23 04:01:53.445167: step: 1104/529, loss: 0.001275444170460105
2023-01-23 04:01:54.570020: step: 1108/529, loss: 0.0002767562691587955
2023-01-23 04:01:55.707451: step: 1112/529, loss: 0.00045614244299940765
2023-01-23 04:01:56.821668: step: 1116/529, loss: 0.011727713979780674
2023-01-23 04:01:57.941138: step: 1120/529, loss: 0.0015352844493463635
2023-01-23 04:01:59.063849: step: 1124/529, loss: 0.007339191623032093
2023-01-23 04:02:00.196523: step: 1128/529, loss: 0.00920496042817831
2023-01-23 04:02:01.332752: step: 1132/529, loss: 0.011356162838637829
2023-01-23 04:02:02.434704: step: 1136/529, loss: 4.358291334938258e-05
2023-01-23 04:02:03.511689: step: 1140/529, loss: 0.00033245087251998484
2023-01-23 04:02:04.672007: step: 1144/529, loss: 9.155274165095761e-05
2023-01-23 04:02:05.775837: step: 1148/529, loss: 0.0015883445739746094
2023-01-23 04:02:06.906135: step: 1152/529, loss: 0.0006401062128134072
2023-01-23 04:02:08.011436: step: 1156/529, loss: 0.0001905441313283518
2023-01-23 04:02:09.127209: step: 1160/529, loss: 0.0004949569702148438
2023-01-23 04:02:10.235915: step: 1164/529, loss: 0.0011981964344158769
2023-01-23 04:02:11.340037: step: 1168/529, loss: 7.114410254871473e-05
2023-01-23 04:02:12.457634: step: 1172/529, loss: 0.014460334554314613
2023-01-23 04:02:13.544076: step: 1176/529, loss: 2.574920654296875e-05
2023-01-23 04:02:14.632035: step: 1180/529, loss: 0.0006227493286132812
2023-01-23 04:02:15.742436: step: 1184/529, loss: 0.564540684223175
2023-01-23 04:02:16.828050: step: 1188/529, loss: 8.029938180698082e-05
2023-01-23 04:02:17.949292: step: 1192/529, loss: 0.022452354431152344
2023-01-23 04:02:19.083714: step: 1196/529, loss: 0.004067373927682638
2023-01-23 04:02:20.237929: step: 1200/529, loss: 0.0031614305917173624
2023-01-23 04:02:21.352752: step: 1204/529, loss: 5.254745701677166e-05
2023-01-23 04:02:22.462466: step: 1208/529, loss: 0.00013580323138739914
2023-01-23 04:02:23.592442: step: 1212/529, loss: 0.005173874087631702
2023-01-23 04:02:24.695069: step: 1216/529, loss: 0.000751113926526159
2023-01-23 04:02:25.826765: step: 1220/529, loss: 0.016982652246952057
2023-01-23 04:02:26.922199: step: 1224/529, loss: 0.0006086349603720009
2023-01-23 04:02:28.028732: step: 1228/529, loss: 0.0014345645904541016
2023-01-23 04:02:29.126226: step: 1232/529, loss: 6.86645489622606e-06
2023-01-23 04:02:30.219568: step: 1236/529, loss: 2.09808349609375e-05
2023-01-23 04:02:31.309136: step: 1240/529, loss: 0.00014209747314453125
2023-01-23 04:02:32.415793: step: 1244/529, loss: 0.00017266272334381938
2023-01-23 04:02:33.479962: step: 1248/529, loss: 0.5793344378471375
2023-01-23 04:02:34.601450: step: 1252/529, loss: 0.0024230005219578743
2023-01-23 04:02:35.751558: step: 1256/529, loss: 0.007236480712890625
2023-01-23 04:02:36.845391: step: 1260/529, loss: 0.0005718230968341231
2023-01-23 04:02:37.952855: step: 1264/529, loss: 0.00046710966853424907
2023-01-23 04:02:39.070323: step: 1268/529, loss: 0.01821594312787056
2023-01-23 04:02:40.159693: step: 1272/529, loss: 0.04938144609332085
2023-01-23 04:02:41.266743: step: 1276/529, loss: 0.0003917694266419858
2023-01-23 04:02:42.374804: step: 1280/529, loss: 0.00631141709163785
2023-01-23 04:02:43.479860: step: 1284/529, loss: 0.06543522328138351
2023-01-23 04:02:44.588206: step: 1288/529, loss: 0.5150752663612366
2023-01-23 04:02:45.720318: step: 1292/529, loss: 0.00045375822810456157
2023-01-23 04:02:46.854495: step: 1296/529, loss: 0.000759857939556241
2023-01-23 04:02:47.971151: step: 1300/529, loss: 0.005687904544174671
2023-01-23 04:02:49.066489: step: 1304/529, loss: 0.0656890869140625
2023-01-23 04:02:50.144934: step: 1308/529, loss: 0.0001586914004292339
2023-01-23 04:02:51.254396: step: 1312/529, loss: 3.4904482163256034e-05
2023-01-23 04:02:52.387692: step: 1316/529, loss: 0.000712966953869909
2023-01-23 04:02:53.494736: step: 1320/529, loss: 0.000575637852307409
2023-01-23 04:02:54.608437: step: 1324/529, loss: 0.013082695193588734
2023-01-23 04:02:55.738029: step: 1328/529, loss: 0.0021923065651208162
2023-01-23 04:02:56.844281: step: 1332/529, loss: 0.003923511598259211
2023-01-23 04:02:58.001836: step: 1336/529, loss: 0.0002298072213307023
2023-01-23 04:02:59.124636: step: 1340/529, loss: -4.95910626341356e-06
2023-01-23 04:03:00.233035: step: 1344/529, loss: -1.2302398317842744e-05
2023-01-23 04:03:01.360791: step: 1348/529, loss: 0.009788895025849342
2023-01-23 04:03:02.464656: step: 1352/529, loss: 0.0022041320335119963
2023-01-23 04:03:03.591952: step: 1356/529, loss: 0.0001466751127736643
2023-01-23 04:03:04.705271: step: 1360/529, loss: 0.004870033357292414
2023-01-23 04:03:05.832459: step: 1364/529, loss: 0.001064300537109375
2023-01-23 04:03:06.937539: step: 1368/529, loss: 9.651183790992945e-05
2023-01-23 04:03:08.075826: step: 1372/529, loss: 0.00019216537475585938
2023-01-23 04:03:09.174591: step: 1376/529, loss: 0.0033470706548541784
2023-01-23 04:03:10.310502: step: 1380/529, loss: 5.5599211918888614e-05
2023-01-23 04:03:11.448364: step: 1384/529, loss: 2.269744800287299e-05
2023-01-23 04:03:12.534297: step: 1388/529, loss: 9.822845458984375e-05
2023-01-23 04:03:13.709317: step: 1392/529, loss: 8.39233416627394e-06
2023-01-23 04:03:14.814525: step: 1396/529, loss: 6.771087646484375e-05
2023-01-23 04:03:15.966650: step: 1400/529, loss: 3.2806394301587716e-05
2023-01-23 04:03:17.040885: step: 1404/529, loss: 0.0352204330265522
2023-01-23 04:03:18.159040: step: 1408/529, loss: 0.17665652930736542
2023-01-23 04:03:19.297250: step: 1412/529, loss: 0.10771813243627548
2023-01-23 04:03:20.436080: step: 1416/529, loss: 7.247925168485381e-06
2023-01-23 04:03:21.582695: step: 1420/529, loss: 0.029523469507694244
2023-01-23 04:03:22.712575: step: 1424/529, loss: 0.0025140761863440275
2023-01-23 04:03:23.800067: step: 1428/529, loss: 7.61985793360509e-05
2023-01-23 04:03:24.915414: step: 1432/529, loss: 5.9700014389818534e-05
2023-01-23 04:03:26.025870: step: 1436/529, loss: 0.003639650298282504
2023-01-23 04:03:27.124153: step: 1440/529, loss: 0.0025553943123668432
2023-01-23 04:03:28.240857: step: 1444/529, loss: 5.054473876953125e-05
2023-01-23 04:03:29.357521: step: 1448/529, loss: 0.002869558287784457
2023-01-23 04:03:30.454117: step: 1452/529, loss: 0.00020494461932685226
2023-01-23 04:03:31.567328: step: 1456/529, loss: 0.0295270923525095
2023-01-23 04:03:32.644549: step: 1460/529, loss: 0.000720977783203125
2023-01-23 04:03:33.763024: step: 1464/529, loss: 0.0030329704750329256
2023-01-23 04:03:34.905080: step: 1468/529, loss: 0.0011715888977050781
2023-01-23 04:03:36.002994: step: 1472/529, loss: 0.03882484510540962
2023-01-23 04:03:37.106051: step: 1476/529, loss: 0.0004371643008198589
2023-01-23 04:03:38.205753: step: 1480/529, loss: 0.06216182932257652
2023-01-23 04:03:39.313776: step: 1484/529, loss: 2.670288040462765e-06
2023-01-23 04:03:40.434320: step: 1488/529, loss: 0.004218196962028742
2023-01-23 04:03:41.527542: step: 1492/529, loss: 1.9073486612342094e-07
2023-01-23 04:03:42.616393: step: 1496/529, loss: 0.017743874341249466
2023-01-23 04:03:43.728438: step: 1500/529, loss: 1.907349087559851e-06
2023-01-23 04:03:44.834488: step: 1504/529, loss: 0.0002779960632324219
2023-01-23 04:03:45.924906: step: 1508/529, loss: 4.5299530029296875e-06
2023-01-23 04:03:47.044342: step: 1512/529, loss: 0.0018747331341728568
2023-01-23 04:03:48.157762: step: 1516/529, loss: 0.0005968093755654991
2023-01-23 04:03:49.285023: step: 1520/529, loss: 0.0003841877041850239
2023-01-23 04:03:50.393520: step: 1524/529, loss: 0.06617489457130432
2023-01-23 04:03:51.542777: step: 1528/529, loss: 0.0034699919633567333
2023-01-23 04:03:52.647015: step: 1532/529, loss: 0.1304466277360916
2023-01-23 04:03:53.771890: step: 1536/529, loss: 5.316734313964844e-05
2023-01-23 04:03:54.889836: step: 1540/529, loss: 0.01122360210865736
2023-01-23 04:03:56.008804: step: 1544/529, loss: 0.08428402245044708
2023-01-23 04:03:57.117079: step: 1548/529, loss: 0.00036230089608579874
2023-01-23 04:03:58.240681: step: 1552/529, loss: 0.023296929895877838
2023-01-23 04:03:59.346755: step: 1556/529, loss: 4.482269287109375e-05
2023-01-23 04:04:00.457732: step: 1560/529, loss: 0.0013785362243652344
2023-01-23 04:04:01.556946: step: 1564/529, loss: 0.00013961792865302414
2023-01-23 04:04:02.656113: step: 1568/529, loss: 0.0018196107121184468
2023-01-23 04:04:03.783603: step: 1572/529, loss: 0.0009608268737792969
2023-01-23 04:04:04.902624: step: 1576/529, loss: 0.0014187813503667712
2023-01-23 04:04:05.997564: step: 1580/529, loss: 0.0006870270008221269
2023-01-23 04:04:07.077626: step: 1584/529, loss: 0.028442764654755592
2023-01-23 04:04:08.237139: step: 1588/529, loss: 0.0001369476376567036
2023-01-23 04:04:09.348925: step: 1592/529, loss: 0.45006120204925537
2023-01-23 04:04:10.453097: step: 1596/529, loss: 0.0002739906485658139
2023-01-23 04:04:11.554212: step: 1600/529, loss: 0.2774600088596344
2023-01-23 04:04:12.645846: step: 1604/529, loss: 8.77380352903856e-06
2023-01-23 04:04:13.749783: step: 1608/529, loss: 0.0007786750793457031
2023-01-23 04:04:14.889356: step: 1612/529, loss: 0.0005665779463015497
2023-01-23 04:04:15.998744: step: 1616/529, loss: 0.12063168734312057
2023-01-23 04:04:17.159078: step: 1620/529, loss: -2.555847095209174e-05
2023-01-23 04:04:18.251299: step: 1624/529, loss: 0.0011086941231042147
2023-01-23 04:04:19.370877: step: 1628/529, loss: 0.0011747360695153475
2023-01-23 04:04:20.514769: step: 1632/529, loss: 1.4448165529756807e-05
2023-01-23 04:04:21.633362: step: 1636/529, loss: 0.028077125549316406
2023-01-23 04:04:22.753251: step: 1640/529, loss: 1.4352797734318301e-05
2023-01-23 04:04:23.846401: step: 1644/529, loss: 0.00059423444326967
2023-01-23 04:04:24.977002: step: 1648/529, loss: 0.17636986076831818
2023-01-23 04:04:26.098139: step: 1652/529, loss: 0.0003440857108216733
2023-01-23 04:04:27.216607: step: 1656/529, loss: 0.0004421234189067036
2023-01-23 04:04:28.306518: step: 1660/529, loss: 1.2683868590102065e-05
2023-01-23 04:04:29.412744: step: 1664/529, loss: 0.016375159844756126
2023-01-23 04:04:30.519774: step: 1668/529, loss: 5.178451829124242e-05
2023-01-23 04:04:31.643315: step: 1672/529, loss: 0.006978416349738836
2023-01-23 04:04:32.741205: step: 1676/529, loss: 0.0014961243141442537
2023-01-23 04:04:33.852960: step: 1680/529, loss: 0.012310790829360485
2023-01-23 04:04:34.949319: step: 1684/529, loss: 0.00024929046048782766
2023-01-23 04:04:36.054842: step: 1688/529, loss: 6.790161569369957e-05
2023-01-23 04:04:37.171796: step: 1692/529, loss: 0.03449878841638565
2023-01-23 04:04:38.249346: step: 1696/529, loss: 0.0007984161493368447
2023-01-23 04:04:39.340714: step: 1700/529, loss: 0.00013570785813499242
2023-01-23 04:04:40.485727: step: 1704/529, loss: 4.57763690064894e-06
2023-01-23 04:04:41.600113: step: 1708/529, loss: 0.0020987512543797493
2023-01-23 04:04:42.727936: step: 1712/529, loss: 0.0171248447149992
2023-01-23 04:04:43.850315: step: 1716/529, loss: 6.675720101156912e-07
2023-01-23 04:04:44.963269: step: 1720/529, loss: 3.266334533691406e-05
2023-01-23 04:04:46.106352: step: 1724/529, loss: 0.0007851123809814453
2023-01-23 04:04:47.202732: step: 1728/529, loss: 2.8157235647086054e-05
2023-01-23 04:04:48.316543: step: 1732/529, loss: 0.0003845214669127017
2023-01-23 04:04:49.443414: step: 1736/529, loss: 0.0008475304348394275
2023-01-23 04:04:50.573851: step: 1740/529, loss: 0.007184791844338179
2023-01-23 04:04:51.667285: step: 1744/529, loss: 0.007298660464584827
2023-01-23 04:04:52.806238: step: 1748/529, loss: 0.0032461166847497225
2023-01-23 04:04:53.927664: step: 1752/529, loss: 0.010535622015595436
2023-01-23 04:04:55.032835: step: 1756/529, loss: 0.06780029088258743
2023-01-23 04:04:56.126540: step: 1760/529, loss: 0.0024008750915527344
2023-01-23 04:04:57.208597: step: 1764/529, loss: 0.050618939101696014
2023-01-23 04:04:58.324657: step: 1768/529, loss: 0.0025347708724439144
2023-01-23 04:04:59.420800: step: 1772/529, loss: 0.06196479871869087
2023-01-23 04:05:00.530865: step: 1776/529, loss: 0.00031375885009765625
2023-01-23 04:05:01.689206: step: 1780/529, loss: 0.024052632972598076
2023-01-23 04:05:02.809444: step: 1784/529, loss: 1.0395049685030244e-05
2023-01-23 04:05:03.935432: step: 1788/529, loss: 0.025150012224912643
2023-01-23 04:05:05.031816: step: 1792/529, loss: 0.01808338239789009
2023-01-23 04:05:06.137519: step: 1796/529, loss: 0.009450817480683327
2023-01-23 04:05:07.241558: step: 1800/529, loss: 0.001556396484375
2023-01-23 04:05:08.331047: step: 1804/529, loss: 0.00036430361797101796
2023-01-23 04:05:09.408488: step: 1808/529, loss: 0.002257442567497492
2023-01-23 04:05:10.523252: step: 1812/529, loss: 0.00048284532385878265
2023-01-23 04:05:11.631696: step: 1816/529, loss: 0.26395654678344727
2023-01-23 04:05:12.717149: step: 1820/529, loss: 0.0002574920654296875
2023-01-23 04:05:13.845691: step: 1824/529, loss: 0.00429191580042243
2023-01-23 04:05:14.974028: step: 1828/529, loss: 7.514953904319555e-05
2023-01-23 04:05:16.070787: step: 1832/529, loss: 7.171631295932457e-05
2023-01-23 04:05:17.197278: step: 1836/529, loss: 0.0008050918695516884
2023-01-23 04:05:18.317811: step: 1840/529, loss: 0.028122615069150925
2023-01-23 04:05:19.435223: step: 1844/529, loss: 0.00010633468627929688
2023-01-23 04:05:20.542775: step: 1848/529, loss: 0.015671061351895332
2023-01-23 04:05:21.666961: step: 1852/529, loss: 0.006744480226188898
2023-01-23 04:05:22.766604: step: 1856/529, loss: 0.0002468586026225239
2023-01-23 04:05:23.871183: step: 1860/529, loss: 0.0068874359130859375
2023-01-23 04:05:24.977739: step: 1864/529, loss: 6.370544724632055e-05
2023-01-23 04:05:26.089975: step: 1868/529, loss: 0.0001638412504689768
2023-01-23 04:05:27.184767: step: 1872/529, loss: 0.015439462848007679
2023-01-23 04:05:28.315555: step: 1876/529, loss: 7.457733590854332e-05
2023-01-23 04:05:29.435648: step: 1880/529, loss: 2.536773718020413e-05
2023-01-23 04:05:30.510010: step: 1884/529, loss: 0.04463768005371094
2023-01-23 04:05:31.601526: step: 1888/529, loss: -1.23977656585339e-06
2023-01-23 04:05:32.687592: step: 1892/529, loss: 0.004299736116081476
2023-01-23 04:05:33.778450: step: 1896/529, loss: 0.037055160850286484
2023-01-23 04:05:34.888088: step: 1900/529, loss: 0.0802450180053711
2023-01-23 04:05:36.035613: step: 1904/529, loss: 1.049041748046875e-05
2023-01-23 04:05:37.164793: step: 1908/529, loss: 0.008633041754364967
2023-01-23 04:05:38.267130: step: 1912/529, loss: 0.0007404327625408769
2023-01-23 04:05:39.372698: step: 1916/529, loss: 0.0005960464477539062
2023-01-23 04:05:40.486957: step: 1920/529, loss: 2.098083541568485e-06
2023-01-23 04:05:41.586821: step: 1924/529, loss: 0.053429603576660156
2023-01-23 04:05:42.709349: step: 1928/529, loss: 0.001379299210384488
2023-01-23 04:05:43.865601: step: 1932/529, loss: 0.0007281303405761719
2023-01-23 04:05:44.974636: step: 1936/529, loss: -7.724762326688506e-06
2023-01-23 04:05:46.088465: step: 1940/529, loss: 0.0005960464477539062
2023-01-23 04:05:47.189837: step: 1944/529, loss: 0.001238059950992465
2023-01-23 04:05:48.303143: step: 1948/529, loss: 0.028688622638583183
2023-01-23 04:05:49.443016: step: 1952/529, loss: 0.00026226043701171875
2023-01-23 04:05:50.557827: step: 1956/529, loss: 2.975463939947076e-05
2023-01-23 04:05:51.681189: step: 1960/529, loss: 0.036904145032167435
2023-01-23 04:05:52.793602: step: 1964/529, loss: 0.014790916815400124
2023-01-23 04:05:53.892886: step: 1968/529, loss: 0.001980686094611883
2023-01-23 04:05:55.010176: step: 1972/529, loss: 0.0017474174965173006
2023-01-23 04:05:56.141446: step: 1976/529, loss: 0.00021162032498978078
2023-01-23 04:05:57.245665: step: 1980/529, loss: 0.003277301788330078
2023-01-23 04:05:58.356685: step: 1984/529, loss: 0.018806075677275658
2023-01-23 04:05:59.476628: step: 1988/529, loss: 0.010902022942900658
2023-01-23 04:06:00.558462: step: 1992/529, loss: 0.006938457489013672
2023-01-23 04:06:01.650784: step: 1996/529, loss: 0.004268646705895662
2023-01-23 04:06:02.757954: step: 2000/529, loss: 6.561279587913305e-05
2023-01-23 04:06:03.852657: step: 2004/529, loss: 0.01737232133746147
2023-01-23 04:06:04.980236: step: 2008/529, loss: 0.01622590981423855
2023-01-23 04:06:06.132906: step: 2012/529, loss: 0.003128433134406805
2023-01-23 04:06:07.225007: step: 2016/529, loss: 0.01795358583331108
2023-01-23 04:06:08.334959: step: 2020/529, loss: 0.0007976532215252519
2023-01-23 04:06:09.429093: step: 2024/529, loss: 0.00010929107520496473
2023-01-23 04:06:10.545796: step: 2028/529, loss: 0.0023077011574059725
2023-01-23 04:06:11.670048: step: 2032/529, loss: 0.0004248619079589844
2023-01-23 04:06:12.758072: step: 2036/529, loss: 1.487731969973538e-05
2023-01-23 04:06:13.872515: step: 2040/529, loss: 0.0026039122603833675
2023-01-23 04:06:14.977231: step: 2044/529, loss: 0.00868759211152792
2023-01-23 04:06:16.092623: step: 2048/529, loss: 0.0034478188026696444
2023-01-23 04:06:17.209830: step: 2052/529, loss: 0.0036638739984482527
2023-01-23 04:06:18.319805: step: 2056/529, loss: 0.0008930206531658769
2023-01-23 04:06:19.412709: step: 2060/529, loss: 0.019074583426117897
2023-01-23 04:06:20.536591: step: 2064/529, loss: 0.0005733490106649697
2023-01-23 04:06:21.673424: step: 2068/529, loss: 5.106926255393773e-05
2023-01-23 04:06:22.793713: step: 2072/529, loss: 0.020857907831668854
2023-01-23 04:06:23.917910: step: 2076/529, loss: 0.030022908002138138
2023-01-23 04:06:25.052475: step: 2080/529, loss: 0.0017591476207599044
2023-01-23 04:06:26.142784: step: 2084/529, loss: 0.02714099921286106
2023-01-23 04:06:27.240915: step: 2088/529, loss: 0.33061426877975464
2023-01-23 04:06:28.361176: step: 2092/529, loss: 0.0679231658577919
2023-01-23 04:06:29.473031: step: 2096/529, loss: 0.0006399154663085938
2023-01-23 04:06:30.596790: step: 2100/529, loss: 0.00016908645920921117
2023-01-23 04:06:31.714012: step: 2104/529, loss: 0.0020572661887854338
2023-01-23 04:06:32.836457: step: 2108/529, loss: 0.07673779129981995
2023-01-23 04:06:33.921699: step: 2112/529, loss: 1.0633468264131807e-05
2023-01-23 04:06:35.030206: step: 2116/529, loss: 0.02581310085952282
==================================================
Loss: 0.026
--------------------
Dev: {'event': {'p': 0.5639810426540285, 'r': 0.7922769640479361, 'f1': 0.6589147286821706}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6171977302487996, 'r': 0.7979683972911964, 'f1': 0.6960374107802116}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5208333333333334, 'r': 0.9259259259259259, 'f1': 0.6666666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.625, 'r': 0.6349206349206349, 'f1': 0.6299212598425197}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.5111111111111111, 'r': 0.6388888888888888, 'f1': 0.5679012345679012}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 04:07:15.206549: step: 4/529, loss: 0.009249688126146793
2023-01-23 04:07:16.346909: step: 8/529, loss: 0.000713348388671875
2023-01-23 04:07:17.450871: step: 12/529, loss: 0.00022373200044967234
2023-01-23 04:07:18.557075: step: 16/529, loss: 0.0004798889276571572
2023-01-23 04:07:19.674998: step: 20/529, loss: 0.020532751455903053
2023-01-23 04:07:20.788585: step: 24/529, loss: 0.0016321182483807206
2023-01-23 04:07:21.923926: step: 28/529, loss: 8.516311936546117e-05
2023-01-23 04:07:23.023972: step: 32/529, loss: 0.0007098674541339278
2023-01-23 04:07:24.141820: step: 36/529, loss: 0.005714798346161842
2023-01-23 04:07:25.265713: step: 40/529, loss: 0.001139783882535994
2023-01-23 04:07:26.384159: step: 44/529, loss: 0.0032330036628991365
2023-01-23 04:07:27.533849: step: 48/529, loss: 0.03191394731402397
2023-01-23 04:07:28.611599: step: 52/529, loss: 0.00016098022751975805
2023-01-23 04:07:29.754222: step: 56/529, loss: 0.007484626490622759
2023-01-23 04:07:30.863837: step: 60/529, loss: 0.007655906490981579
2023-01-23 04:07:31.964493: step: 64/529, loss: 0.0001906395045807585
2023-01-23 04:07:33.085160: step: 68/529, loss: 0.003427696181461215
2023-01-23 04:07:34.192977: step: 72/529, loss: 0.041635800153017044
2023-01-23 04:07:35.285999: step: 76/529, loss: 0.00031147003755904734
2023-01-23 04:07:36.394829: step: 80/529, loss: 6.389617919921875e-05
2023-01-23 04:07:37.534294: step: 84/529, loss: 0.005901527591049671
2023-01-23 04:07:38.612835: step: 88/529, loss: 9.536745437799254e-08
2023-01-23 04:07:39.736008: step: 92/529, loss: 0.0019780159927904606
2023-01-23 04:07:40.817347: step: 96/529, loss: 0.0002933502255473286
2023-01-23 04:07:41.949654: step: 100/529, loss: 0.0012407302856445312
2023-01-23 04:07:43.075726: step: 104/529, loss: 0.0025183677207678556
2023-01-23 04:07:44.178663: step: 108/529, loss: 0.05780811607837677
2023-01-23 04:07:45.286910: step: 112/529, loss: 5.4073334467830136e-05
2023-01-23 04:07:46.399768: step: 116/529, loss: 0.0001324176846537739
2023-01-23 04:07:47.513039: step: 120/529, loss: 0.00012874603271484375
2023-01-23 04:07:48.629243: step: 124/529, loss: 4.5585635234601796e-05
2023-01-23 04:07:49.726199: step: 128/529, loss: 6.999969627941027e-05
2023-01-23 04:07:50.840309: step: 132/529, loss: 0.015172004699707031
2023-01-23 04:07:51.930756: step: 136/529, loss: -2.2888179955771193e-06
2023-01-23 04:07:53.059768: step: 140/529, loss: 0.022600747644901276
2023-01-23 04:07:54.156334: step: 144/529, loss: 2.2888182229507947e-06
2023-01-23 04:07:55.275377: step: 148/529, loss: 0.0007817268487997353
2023-01-23 04:07:56.359088: step: 152/529, loss: 0.0002841949462890625
2023-01-23 04:07:57.474318: step: 156/529, loss: 0.0003963470517192036
2023-01-23 04:07:58.580552: step: 160/529, loss: 8.39233416627394e-06
2023-01-23 04:07:59.687702: step: 164/529, loss: 3.795623706537299e-05
2023-01-23 04:08:00.803353: step: 168/529, loss: 0.00017805100651457906
2023-01-23 04:08:01.946586: step: 172/529, loss: 0.002005005022510886
2023-01-23 04:08:03.060229: step: 176/529, loss: 0.00011520386033225805
2023-01-23 04:08:04.147978: step: 180/529, loss: 4.520416405284777e-05
2023-01-23 04:08:05.235333: step: 184/529, loss: 0.13518676161766052
2023-01-23 04:08:06.345012: step: 188/529, loss: 1.697540210443549e-05
2023-01-23 04:08:07.435627: step: 192/529, loss: 0.0003010749933309853
2023-01-23 04:08:08.571505: step: 196/529, loss: 0.001999282743781805
2023-01-23 04:08:09.689038: step: 200/529, loss: 0.0006336212391033769
2023-01-23 04:08:10.796798: step: 204/529, loss: 0.006953620817512274
2023-01-23 04:08:11.891128: step: 208/529, loss: 1.5068055290612392e-05
2023-01-23 04:08:13.001181: step: 212/529, loss: 3.0517578125e-05
2023-01-23 04:08:14.123456: step: 216/529, loss: 3.9386748539982364e-05
2023-01-23 04:08:15.248635: step: 220/529, loss: 0.0037118911277502775
2023-01-23 04:08:16.350923: step: 224/529, loss: 3.967285010730848e-05
2023-01-23 04:08:17.427129: step: 228/529, loss: 6.079673767089844e-05
2023-01-23 04:08:18.560912: step: 232/529, loss: 0.00022010803513694555
2023-01-23 04:08:19.704575: step: 236/529, loss: 0.04304943233728409
2023-01-23 04:08:20.815768: step: 240/529, loss: 0.00010061264038085938
2023-01-23 04:08:21.904102: step: 244/529, loss: 2.6226043701171875e-06
2023-01-23 04:08:22.989816: step: 248/529, loss: 1.45191490650177
2023-01-23 04:08:24.097730: step: 252/529, loss: 0.0006059646257199347
2023-01-23 04:08:25.218287: step: 256/529, loss: 0.0001846313534770161
2023-01-23 04:08:26.325743: step: 260/529, loss: 0.0012180329067632556
2023-01-23 04:08:27.458942: step: 264/529, loss: 1.029968279908644e-05
2023-01-23 04:08:28.565766: step: 268/529, loss: -7.724762326688506e-06
2023-01-23 04:08:29.680185: step: 272/529, loss: 0.0010332107776775956
2023-01-23 04:08:30.774697: step: 276/529, loss: 9.517669241176918e-05
2023-01-23 04:08:31.883033: step: 280/529, loss: 0.0005318641779012978
2023-01-23 04:08:32.983409: step: 284/529, loss: 0.0512206070125103
2023-01-23 04:08:34.077677: step: 288/529, loss: 0.019914817065000534
2023-01-23 04:08:35.154012: step: 292/529, loss: 2.09808349609375e-05
2023-01-23 04:08:36.269015: step: 296/529, loss: 0.0018430709606036544
2023-01-23 04:08:37.381720: step: 300/529, loss: -8.20159948489163e-06
2023-01-23 04:08:38.493942: step: 304/529, loss: -2.193450927734375e-05
2023-01-23 04:08:39.606039: step: 308/529, loss: 0.0005424499395303428
2023-01-23 04:08:40.674833: step: 312/529, loss: 0.0024175646249204874
2023-01-23 04:08:41.797094: step: 316/529, loss: 0.0012498855357989669
2023-01-23 04:08:42.961238: step: 320/529, loss: 0.00037899016751907766
2023-01-23 04:08:44.055954: step: 324/529, loss: 0.00155048375017941
2023-01-23 04:08:45.161664: step: 328/529, loss: 4.863739013671875e-05
2023-01-23 04:08:46.280848: step: 332/529, loss: 0.0035194396041333675
2023-01-23 04:08:47.383112: step: 336/529, loss: 0.016431475058197975
2023-01-23 04:08:48.499858: step: 340/529, loss: 1.1539459592313506e-05
2023-01-23 04:08:49.629247: step: 344/529, loss: 0.016260242089629173
2023-01-23 04:08:50.770144: step: 348/529, loss: 0.0001227855682373047
2023-01-23 04:08:51.873581: step: 352/529, loss: 0.0006414413801394403
2023-01-23 04:08:52.967871: step: 356/529, loss: 0.029979515820741653
2023-01-23 04:08:54.112543: step: 360/529, loss: 0.00261440291069448
2023-01-23 04:08:55.231701: step: 364/529, loss: 0.00019760131544899195
2023-01-23 04:08:56.344708: step: 368/529, loss: 0.003555011935532093
2023-01-23 04:08:57.446205: step: 372/529, loss: 2.593994213384576e-05
2023-01-23 04:08:58.579755: step: 376/529, loss: 7.381439354503527e-05
2023-01-23 04:08:59.685119: step: 380/529, loss: 0.00032224657479673624
2023-01-23 04:09:00.806452: step: 384/529, loss: 9.412765211891383e-05
2023-01-23 04:09:01.936881: step: 388/529, loss: 0.030803680419921875
2023-01-23 04:09:03.036079: step: 392/529, loss: 0.02362666092813015
2023-01-23 04:09:04.164470: step: 396/529, loss: 0.01728825643658638
2023-01-23 04:09:05.257031: step: 400/529, loss: 0.008720779791474342
2023-01-23 04:09:06.361293: step: 404/529, loss: 0.001058387802913785
2023-01-23 04:09:07.475399: step: 408/529, loss: 0.00369853968732059
2023-01-23 04:09:08.570429: step: 412/529, loss: 0.013082314282655716
2023-01-23 04:09:09.660114: step: 416/529, loss: 0.0007542610983364284
2023-01-23 04:09:10.749910: step: 420/529, loss: 0.001131343888118863
2023-01-23 04:09:11.875836: step: 424/529, loss: 0.0004672050417866558
2023-01-23 04:09:13.007566: step: 428/529, loss: 6.580352783203125e-05
2023-01-23 04:09:14.121401: step: 432/529, loss: 0.0031196593772619963
2023-01-23 04:09:15.225742: step: 436/529, loss: 5.939006950939074e-05
2023-01-23 04:09:16.367868: step: 440/529, loss: 0.013279056176543236
2023-01-23 04:09:17.466974: step: 444/529, loss: 1.2493133908719756e-05
2023-01-23 04:09:18.577603: step: 448/529, loss: 6.294250852079131e-06
2023-01-23 04:09:19.710290: step: 452/529, loss: 4.329681542003527e-05
2023-01-23 04:09:20.802820: step: 456/529, loss: 0.0001659393310546875
2023-01-23 04:09:21.880633: step: 460/529, loss: 8.583069188716763e-07
2023-01-23 04:09:22.979029: step: 464/529, loss: 0.0037823680322617292
2023-01-23 04:09:24.106970: step: 468/529, loss: 0.005554962437599897
2023-01-23 04:09:25.227276: step: 472/529, loss: 0.02116413228213787
2023-01-23 04:09:26.385412: step: 476/529, loss: 1.125335711549269e-05
2023-01-23 04:09:27.517790: step: 480/529, loss: 0.018422506749629974
2023-01-23 04:09:28.631991: step: 484/529, loss: 1.487731969973538e-05
2023-01-23 04:09:29.737912: step: 488/529, loss: 3.61442580469884e-05
2023-01-23 04:09:30.824429: step: 492/529, loss: 9.365082223666832e-05
2023-01-23 04:09:31.986256: step: 496/529, loss: 0.00935821607708931
2023-01-23 04:09:33.108233: step: 500/529, loss: 0.017224693670868874
2023-01-23 04:09:34.226747: step: 504/529, loss: 2.098083541568485e-06
2023-01-23 04:09:35.341443: step: 508/529, loss: -1.716613724056515e-06
2023-01-23 04:09:36.445189: step: 512/529, loss: 0.039348602294921875
2023-01-23 04:09:37.549801: step: 516/529, loss: 0.020688343793153763
2023-01-23 04:09:38.661780: step: 520/529, loss: 3.147125244140625e-05
2023-01-23 04:09:39.745614: step: 524/529, loss: 0.0017095565563067794
2023-01-23 04:09:40.837757: step: 528/529, loss: 1.8692018784349784e-05
2023-01-23 04:09:41.948028: step: 532/529, loss: 0.003843689104542136
2023-01-23 04:09:43.049311: step: 536/529, loss: 0.005428696051239967
2023-01-23 04:09:44.156611: step: 540/529, loss: 0.00017557144747115672
2023-01-23 04:09:45.275936: step: 544/529, loss: 7.629394644936838e-07
2023-01-23 04:09:46.375233: step: 548/529, loss: 0.05489044263958931
2023-01-23 04:09:47.502526: step: 552/529, loss: 0.0044387816451489925
2023-01-23 04:09:48.614668: step: 556/529, loss: -3.814697322468419e-07
2023-01-23 04:09:49.738679: step: 560/529, loss: 0.08018913120031357
2023-01-23 04:09:50.838439: step: 564/529, loss: 0.35270100831985474
2023-01-23 04:09:51.951177: step: 568/529, loss: 0.0008023262489587069
2023-01-23 04:09:53.066578: step: 572/529, loss: 0.00158863072283566
2023-01-23 04:09:54.186880: step: 576/529, loss: 7.925033423816785e-05
2023-01-23 04:09:55.316612: step: 580/529, loss: 0.03548803552985191
2023-01-23 04:09:56.438446: step: 584/529, loss: 9.574890282237902e-05
2023-01-23 04:09:57.556337: step: 588/529, loss: 3.6239625842426904e-06
2023-01-23 04:09:58.630102: step: 592/529, loss: 0.0001885414239950478
2023-01-23 04:09:59.739850: step: 596/529, loss: 0.00014934540376998484
2023-01-23 04:10:00.858865: step: 600/529, loss: 0.0001095295010600239
2023-01-23 04:10:02.002074: step: 604/529, loss: 0.00011510848707985133
2023-01-23 04:10:03.179638: step: 608/529, loss: 0.007095527835190296
2023-01-23 04:10:04.321524: step: 612/529, loss: 0.0008422852260991931
2023-01-23 04:10:05.475238: step: 616/529, loss: 1.430511474609375e-05
2023-01-23 04:10:06.584018: step: 620/529, loss: 0.0004137992800679058
2023-01-23 04:10:07.679093: step: 624/529, loss: 0.0005496978992596269
2023-01-23 04:10:08.763702: step: 628/529, loss: 0.0013875962467864156
2023-01-23 04:10:09.861021: step: 632/529, loss: 3.514289710437879e-05
2023-01-23 04:10:10.977023: step: 636/529, loss: 0.0001331329403910786
2023-01-23 04:10:12.107998: step: 640/529, loss: 0.002977657364681363
2023-01-23 04:10:13.221303: step: 644/529, loss: 0.0007304191822186112
2023-01-23 04:10:14.315462: step: 648/529, loss: 0.0443304069340229
2023-01-23 04:10:15.411655: step: 652/529, loss: 0.0002265930233988911
2023-01-23 04:10:16.517082: step: 656/529, loss: 0.012698746286332607
2023-01-23 04:10:17.605649: step: 660/529, loss: 0.0002633571857586503
2023-01-23 04:10:18.741738: step: 664/529, loss: 0.198590949177742
2023-01-23 04:10:19.839764: step: 668/529, loss: 0.0010515213944017887
2023-01-23 04:10:20.971601: step: 672/529, loss: 0.00012722014798782766
2023-01-23 04:10:22.101551: step: 676/529, loss: 3.662109520519152e-05
2023-01-23 04:10:23.230803: step: 680/529, loss: 0.006915092468261719
2023-01-23 04:10:24.321494: step: 684/529, loss: 0.024335289373993874
2023-01-23 04:10:25.441072: step: 688/529, loss: 3.2615658710710704e-05
2023-01-23 04:10:26.561168: step: 692/529, loss: 0.0022559165954589844
2023-01-23 04:10:27.688455: step: 696/529, loss: 0.0008451461908407509
2023-01-23 04:10:28.879126: step: 700/529, loss: 0.0013437271118164062
2023-01-23 04:10:30.008981: step: 704/529, loss: 0.00838174857199192
2023-01-23 04:10:31.115878: step: 708/529, loss: 0.05835456773638725
2023-01-23 04:10:32.224775: step: 712/529, loss: 0.15174180269241333
2023-01-23 04:10:33.311554: step: 716/529, loss: 0.048986151814460754
2023-01-23 04:10:34.425086: step: 720/529, loss: 0.00033588410587981343
2023-01-23 04:10:35.515565: step: 724/529, loss: 0.002157020615413785
2023-01-23 04:10:36.631226: step: 728/529, loss: 0.009601403027772903
2023-01-23 04:10:37.715462: step: 732/529, loss: 0.000854110752698034
2023-01-23 04:10:38.813052: step: 736/529, loss: 0.006050873082131147
2023-01-23 04:10:39.924064: step: 740/529, loss: 0.001328754355199635
2023-01-23 04:10:41.018935: step: 744/529, loss: 7.486343292839592e-06
2023-01-23 04:10:42.133608: step: 748/529, loss: 0.0005989194032736123
2023-01-23 04:10:43.244452: step: 752/529, loss: 0.03419437259435654
2023-01-23 04:10:44.372697: step: 756/529, loss: 0.0005435943603515625
2023-01-23 04:10:45.490730: step: 760/529, loss: 0.019770454615354538
2023-01-23 04:10:46.570205: step: 764/529, loss: 0.0010349273215979338
2023-01-23 04:10:47.648703: step: 768/529, loss: 0.0013326643966138363
2023-01-23 04:10:48.766487: step: 772/529, loss: 0.00383338937535882
2023-01-23 04:10:49.876250: step: 776/529, loss: 8.98361176950857e-05
2023-01-23 04:10:50.975005: step: 780/529, loss: 0.0009382247808389366
2023-01-23 04:10:52.106331: step: 784/529, loss: 0.004414177034050226
2023-01-23 04:10:53.234439: step: 788/529, loss: 0.0022933960426598787
2023-01-23 04:10:54.370979: step: 792/529, loss: 0.008202457800507545
2023-01-23 04:10:55.472791: step: 796/529, loss: -2.670288040462765e-06
2023-01-23 04:10:56.585195: step: 800/529, loss: 0.001972389407455921
2023-01-23 04:10:57.685147: step: 804/529, loss: 0.017171764746308327
2023-01-23 04:10:58.781495: step: 808/529, loss: 0.004138469696044922
2023-01-23 04:10:59.904985: step: 812/529, loss: 0.01918220706284046
2023-01-23 04:11:01.036327: step: 816/529, loss: 1.8119811784345075e-06
2023-01-23 04:11:02.129111: step: 820/529, loss: 5.135536048328504e-05
2023-01-23 04:11:03.241220: step: 824/529, loss: 0.0001255035458598286
2023-01-23 04:11:04.397488: step: 828/529, loss: 0.001076090382412076
2023-01-23 04:11:05.491392: step: 832/529, loss: 0.0008924484136514366
2023-01-23 04:11:06.597309: step: 836/529, loss: 5.950927879894152e-05
2023-01-23 04:11:07.685349: step: 840/529, loss: 0.0001996994105866179
2023-01-23 04:11:08.785914: step: 844/529, loss: 0.00040988920954987407
2023-01-23 04:11:09.879766: step: 848/529, loss: 1.5926361811580136e-05
2023-01-23 04:11:11.001586: step: 852/529, loss: 0.006637192331254482
2023-01-23 04:11:12.132998: step: 856/529, loss: 0.0005097389221191406
2023-01-23 04:11:13.218069: step: 860/529, loss: 1.9884109860868193e-05
2023-01-23 04:11:14.283474: step: 864/529, loss: 0.0001581192045705393
2023-01-23 04:11:15.390579: step: 868/529, loss: 0.00472679128870368
2023-01-23 04:11:16.512735: step: 872/529, loss: 0.0008339881896972656
2023-01-23 04:11:17.627816: step: 876/529, loss: 0.010357093997299671
2023-01-23 04:11:18.737488: step: 880/529, loss: 9.346007573185489e-06
2023-01-23 04:11:19.836275: step: 884/529, loss: 0.0036376952193677425
2023-01-23 04:11:20.939211: step: 888/529, loss: 3.24249276673072e-06
2023-01-23 04:11:22.038836: step: 892/529, loss: 0.012949180789291859
2023-01-23 04:11:23.130830: step: 896/529, loss: -6.198883397701138e-07
2023-01-23 04:11:24.245047: step: 900/529, loss: 0.004258441738784313
2023-01-23 04:11:25.353752: step: 904/529, loss: 8.869172233971767e-06
2023-01-23 04:11:26.506894: step: 908/529, loss: 0.047396469861269
2023-01-23 04:11:27.639107: step: 912/529, loss: -2.09808349609375e-05
2023-01-23 04:11:28.723743: step: 916/529, loss: 0.004712868016213179
2023-01-23 04:11:29.846710: step: 920/529, loss: 0.02129039727151394
2023-01-23 04:11:30.957772: step: 924/529, loss: 8.544922457076609e-05
2023-01-23 04:11:32.055811: step: 928/529, loss: 2.212524486822076e-05
2023-01-23 04:11:33.173543: step: 932/529, loss: 0.00032005313551053405
2023-01-23 04:11:34.288857: step: 936/529, loss: 0.0009243488311767578
2023-01-23 04:11:35.382418: step: 940/529, loss: 0.014508294872939587
2023-01-23 04:11:36.517604: step: 944/529, loss: 0.0003635406610555947
2023-01-23 04:11:37.633188: step: 948/529, loss: 0.00013170242891646922
2023-01-23 04:11:38.750221: step: 952/529, loss: 3.1471258807869162e-06
2023-01-23 04:11:39.857166: step: 956/529, loss: 2.746581958490424e-05
2023-01-23 04:11:40.945968: step: 960/529, loss: 4.5299530029296875e-05
2023-01-23 04:11:42.048021: step: 964/529, loss: 0.00018787384033203125
2023-01-23 04:11:43.172419: step: 968/529, loss: 0.00263137836009264
2023-01-23 04:11:44.263748: step: 972/529, loss: 0.009904003702104092
2023-01-23 04:11:45.418559: step: 976/529, loss: 0.0003784179862122983
2023-01-23 04:11:46.528561: step: 980/529, loss: 0.0004046917019877583
2023-01-23 04:11:47.620000: step: 984/529, loss: 0.003150367643684149
2023-01-23 04:11:48.731639: step: 988/529, loss: 0.01798992231488228
2023-01-23 04:11:49.849189: step: 992/529, loss: 4.00543194700731e-06
2023-01-23 04:11:50.950289: step: 996/529, loss: 0.024334335699677467
2023-01-23 04:11:52.065559: step: 1000/529, loss: 0.011549186892807484
2023-01-23 04:11:53.177856: step: 1004/529, loss: 3.795623706537299e-05
2023-01-23 04:11:54.271071: step: 1008/529, loss: 8.773804438533261e-05
2023-01-23 04:11:55.353768: step: 1012/529, loss: 0.004868126008659601
2023-01-23 04:11:56.484702: step: 1016/529, loss: 0.005821609869599342
2023-01-23 04:11:57.580600: step: 1020/529, loss: 2.2792815798311494e-05
2023-01-23 04:11:58.679781: step: 1024/529, loss: 0.0018356323707848787
2023-01-23 04:11:59.795709: step: 1028/529, loss: 0.0001569747837493196
2023-01-23 04:12:00.885978: step: 1032/529, loss: 0.0028627398423850536
2023-01-23 04:12:01.994124: step: 1036/529, loss: 0.009147453121840954
2023-01-23 04:12:03.071181: step: 1040/529, loss: 5.7220458984375e-06
2023-01-23 04:12:04.181135: step: 1044/529, loss: 0.004546642303466797
2023-01-23 04:12:05.308287: step: 1048/529, loss: 4.987716965842992e-05
2023-01-23 04:12:06.428269: step: 1052/529, loss: 0.02788076363503933
2023-01-23 04:12:07.539664: step: 1056/529, loss: 6.904602196300402e-05
2023-01-23 04:12:08.595153: step: 1060/529, loss: 0.00038757326547056437
2023-01-23 04:12:09.700335: step: 1064/529, loss: 0.0011676788562908769
2023-01-23 04:12:10.797649: step: 1068/529, loss: 5.769729796156753e-06
2023-01-23 04:12:11.911083: step: 1072/529, loss: 0.11478310078382492
2023-01-23 04:12:13.030317: step: 1076/529, loss: 0.0031817913986742496
2023-01-23 04:12:14.128976: step: 1080/529, loss: 0.0009860516292974353
2023-01-23 04:12:15.268824: step: 1084/529, loss: 0.0174013152718544
2023-01-23 04:12:16.373967: step: 1088/529, loss: 0.0009235382312908769
2023-01-23 04:12:17.466679: step: 1092/529, loss: 0.003840160556137562
2023-01-23 04:12:18.580406: step: 1096/529, loss: 6.971359835006297e-05
2023-01-23 04:12:19.718915: step: 1100/529, loss: 0.03844146803021431
2023-01-23 04:12:20.816482: step: 1104/529, loss: 0.0017689228989183903
2023-01-23 04:12:21.910693: step: 1108/529, loss: 0.002466583391651511
2023-01-23 04:12:23.031695: step: 1112/529, loss: 0.008643818087875843
2023-01-23 04:12:24.153806: step: 1116/529, loss: 6.47544875391759e-05
2023-01-23 04:12:25.253002: step: 1120/529, loss: 0.00039443967398256063
2023-01-23 04:12:26.396940: step: 1124/529, loss: 0.015641022473573685
2023-01-23 04:12:27.496252: step: 1128/529, loss: 0.00446662912145257
2023-01-23 04:12:28.611389: step: 1132/529, loss: 0.045239828526973724
2023-01-23 04:12:29.731759: step: 1136/529, loss: 0.03819665685296059
2023-01-23 04:12:30.838760: step: 1140/529, loss: 2.117157055181451e-05
2023-01-23 04:12:31.915593: step: 1144/529, loss: 0.00012054442777298391
2023-01-23 04:12:33.023792: step: 1148/529, loss: 0.03194008022546768
2023-01-23 04:12:34.129626: step: 1152/529, loss: 1.1931575536727905
2023-01-23 04:12:35.233428: step: 1156/529, loss: 0.05352325364947319
2023-01-23 04:12:36.330012: step: 1160/529, loss: 0.03431911766529083
2023-01-23 04:12:37.418443: step: 1164/529, loss: 0.009469223208725452
2023-01-23 04:12:38.518879: step: 1168/529, loss: 0.004056835547089577
2023-01-23 04:12:39.617303: step: 1172/529, loss: 0.0005332946893759072
2023-01-23 04:12:40.725028: step: 1176/529, loss: 0.004301262088119984
2023-01-23 04:12:41.837522: step: 1180/529, loss: 0.0010605811839923263
2023-01-23 04:12:42.958038: step: 1184/529, loss: 0.0005177497514523566
2023-01-23 04:12:44.068547: step: 1188/529, loss: 0.011030006222426891
2023-01-23 04:12:45.170103: step: 1192/529, loss: 7.057189577608369e-06
2023-01-23 04:12:46.296440: step: 1196/529, loss: 8.983612497104332e-05
2023-01-23 04:12:47.378776: step: 1200/529, loss: 0.00803918857127428
2023-01-23 04:12:48.467558: step: 1204/529, loss: 0.0003170013369526714
2023-01-23 04:12:49.558569: step: 1208/529, loss: 0.0014414788456633687
2023-01-23 04:12:50.673264: step: 1212/529, loss: 6.198883056640625e-06
2023-01-23 04:12:51.782720: step: 1216/529, loss: 0.02641163021326065
2023-01-23 04:12:52.890174: step: 1220/529, loss: 0.00011849403381347656
2023-01-23 04:12:53.999428: step: 1224/529, loss: 0.030809976160526276
2023-01-23 04:12:55.104838: step: 1228/529, loss: 0.00039272307185456157
2023-01-23 04:12:56.214780: step: 1232/529, loss: 0.00017204285541083664
2023-01-23 04:12:57.299020: step: 1236/529, loss: 0.013741064816713333
2023-01-23 04:12:58.410466: step: 1240/529, loss: 4.9591067181609105e-06
2023-01-23 04:12:59.501521: step: 1244/529, loss: 0.07047024369239807
2023-01-23 04:13:00.607422: step: 1248/529, loss: 0.007892417721450329
2023-01-23 04:13:01.708878: step: 1252/529, loss: 0.01241369266062975
2023-01-23 04:13:02.822308: step: 1256/529, loss: 2.532005419197958e-05
2023-01-23 04:13:03.930665: step: 1260/529, loss: 1.0585785275907256e-05
2023-01-23 04:13:04.994629: step: 1264/529, loss: 0.5731164813041687
2023-01-23 04:13:06.106982: step: 1268/529, loss: 1.5258788153005298e-06
2023-01-23 04:13:07.207491: step: 1272/529, loss: 0.0003201484796591103
2023-01-23 04:13:08.291046: step: 1276/529, loss: 9.5367431640625e-06
2023-01-23 04:13:09.411884: step: 1280/529, loss: 1.6975403923424892e-05
2023-01-23 04:13:10.541384: step: 1284/529, loss: 0.0057170395739376545
2023-01-23 04:13:11.615363: step: 1288/529, loss: 0.0005504131549969316
2023-01-23 04:13:12.742481: step: 1292/529, loss: 0.019441604614257812
2023-01-23 04:13:13.853701: step: 1296/529, loss: 0.0054035186767578125
2023-01-23 04:13:14.958919: step: 1300/529, loss: 0.009398058988153934
2023-01-23 04:13:16.054368: step: 1304/529, loss: 0.003941154573112726
2023-01-23 04:13:17.146392: step: 1308/529, loss: 0.0706939697265625
2023-01-23 04:13:18.263207: step: 1312/529, loss: 0.00103168492205441
2023-01-23 04:13:19.357154: step: 1316/529, loss: 0.0002323150692973286
2023-01-23 04:13:20.460770: step: 1320/529, loss: 7.314681715797633e-05
2023-01-23 04:13:21.598873: step: 1324/529, loss: 0.005231034941971302
2023-01-23 04:13:22.682137: step: 1328/529, loss: 0.0006383895524777472
2023-01-23 04:13:23.823717: step: 1332/529, loss: 0.04486904293298721
2023-01-23 04:13:24.950361: step: 1336/529, loss: 0.02622051350772381
2023-01-23 04:13:26.077694: step: 1340/529, loss: 0.0026576996315270662
2023-01-23 04:13:27.166185: step: 1344/529, loss: 1.215934844367439e-05
2023-01-23 04:13:28.291551: step: 1348/529, loss: 0.021055983379483223
2023-01-23 04:13:29.435225: step: 1352/529, loss: 0.001291451626457274
2023-01-23 04:13:30.542485: step: 1356/529, loss: 0.0005256652948446572
2023-01-23 04:13:31.655131: step: 1360/529, loss: -2.403259350103326e-05
2023-01-23 04:13:32.798263: step: 1364/529, loss: 0.016245460137724876
2023-01-23 04:13:33.883167: step: 1368/529, loss: 0.03890140354633331
2023-01-23 04:13:34.980192: step: 1372/529, loss: 0.0002449035819154233
2023-01-23 04:13:36.124495: step: 1376/529, loss: 0.15285950899124146
2023-01-23 04:13:37.226471: step: 1380/529, loss: 0.08986129611730576
2023-01-23 04:13:38.330131: step: 1384/529, loss: 0.012361908331513405
2023-01-23 04:13:39.428682: step: 1388/529, loss: 0.008724594488739967
2023-01-23 04:13:40.522546: step: 1392/529, loss: 0.0007171630859375
2023-01-23 04:13:41.635260: step: 1396/529, loss: 0.0007783889886923134
2023-01-23 04:13:42.727409: step: 1400/529, loss: 0.00027761459932662547
2023-01-23 04:13:43.839409: step: 1404/529, loss: 0.001807403634302318
2023-01-23 04:13:44.994696: step: 1408/529, loss: 0.0015897273551672697
2023-01-23 04:13:46.097667: step: 1412/529, loss: 5.1021575927734375e-05
2023-01-23 04:13:47.205737: step: 1416/529, loss: 1.0681153071345761e-05
2023-01-23 04:13:48.296846: step: 1420/529, loss: 0.016759108752012253
2023-01-23 04:13:49.418768: step: 1424/529, loss: 0.0016318499110639095
2023-01-23 04:13:50.554845: step: 1428/529, loss: 0.03196106106042862
2023-01-23 04:13:51.653857: step: 1432/529, loss: 0.0001388549862895161
2023-01-23 04:13:52.764149: step: 1436/529, loss: 1.678466833254788e-05
2023-01-23 04:13:53.852206: step: 1440/529, loss: 0.0005296707386150956
2023-01-23 04:13:54.969481: step: 1444/529, loss: 0.0009529591188766062
2023-01-23 04:13:56.078256: step: 1448/529, loss: 0.0046860696747899055
2023-01-23 04:13:57.174601: step: 1452/529, loss: 0.032364655286073685
2023-01-23 04:13:58.290718: step: 1456/529, loss: 0.01510009728372097
2023-01-23 04:13:59.402043: step: 1460/529, loss: 0.0028751373756676912
2023-01-23 04:14:00.531065: step: 1464/529, loss: 0.001624679658561945
2023-01-23 04:14:01.653057: step: 1468/529, loss: 0.09992923587560654
2023-01-23 04:14:02.749721: step: 1472/529, loss: 7.562637620139867e-05
2023-01-23 04:14:03.816976: step: 1476/529, loss: 5.626678557746345e-06
2023-01-23 04:14:04.896455: step: 1480/529, loss: 0.00019855500431731343
2023-01-23 04:14:06.061497: step: 1484/529, loss: 0.0008626937633380294
2023-01-23 04:14:07.176582: step: 1488/529, loss: 0.024179935455322266
2023-01-23 04:14:08.288723: step: 1492/529, loss: 0.00036945342435501516
2023-01-23 04:14:09.403939: step: 1496/529, loss: 0.0031189920846372843
2023-01-23 04:14:10.503127: step: 1500/529, loss: -3.14712519866589e-06
2023-01-23 04:14:11.606000: step: 1504/529, loss: 0.007780313491821289
2023-01-23 04:14:12.721941: step: 1508/529, loss: 0.027561282739043236
2023-01-23 04:14:13.848464: step: 1512/529, loss: 0.0009529113885946572
2023-01-23 04:14:14.963922: step: 1516/529, loss: 0.018427658826112747
2023-01-23 04:14:16.072350: step: 1520/529, loss: 0.06845531612634659
2023-01-23 04:14:17.202070: step: 1524/529, loss: 0.029588699340820312
2023-01-23 04:14:18.332675: step: 1528/529, loss: 0.02111683040857315
2023-01-23 04:14:19.442311: step: 1532/529, loss: 0.02276000939309597
2023-01-23 04:14:20.546682: step: 1536/529, loss: 0.02129554934799671
2023-01-23 04:14:21.663859: step: 1540/529, loss: 0.0004553794860839844
2023-01-23 04:14:22.800228: step: 1544/529, loss: 0.0002037048398051411
2023-01-23 04:14:23.898822: step: 1548/529, loss: 0.0003536224539857358
2023-01-23 04:14:24.996501: step: 1552/529, loss: 0.0057548522017896175
2023-01-23 04:14:26.103627: step: 1556/529, loss: 0.5353145599365234
2023-01-23 04:14:27.204115: step: 1560/529, loss: 0.0004351615789346397
2023-01-23 04:14:28.299140: step: 1564/529, loss: 3.3950807846849784e-05
2023-01-23 04:14:29.397738: step: 1568/529, loss: 0.016290094703435898
2023-01-23 04:14:30.518725: step: 1572/529, loss: 0.028105545789003372
2023-01-23 04:14:31.648853: step: 1576/529, loss: 4.37736525782384e-05
2023-01-23 04:14:32.757273: step: 1580/529, loss: 0.001196575234644115
2023-01-23 04:14:33.862258: step: 1584/529, loss: 0.018286513164639473
2023-01-23 04:14:34.962072: step: 1588/529, loss: 0.004174232482910156
2023-01-23 04:14:36.065778: step: 1592/529, loss: 0.003111171768978238
2023-01-23 04:14:37.163715: step: 1596/529, loss: 0.00027942657470703125
2023-01-23 04:14:38.265069: step: 1600/529, loss: 7.848739915061742e-05
2023-01-23 04:14:39.357326: step: 1604/529, loss: 0.017615366727113724
2023-01-23 04:14:40.453527: step: 1608/529, loss: 1.7166138377433526e-06
2023-01-23 04:14:41.561674: step: 1612/529, loss: 4.653930591302924e-05
2023-01-23 04:14:42.675990: step: 1616/529, loss: 0.1845863312482834
2023-01-23 04:14:43.767690: step: 1620/529, loss: 0.00018749237642623484
2023-01-23 04:14:44.877156: step: 1624/529, loss: 0.0024513243697583675
2023-01-23 04:14:45.975911: step: 1628/529, loss: 1.964569128176663e-05
2023-01-23 04:14:47.106390: step: 1632/529, loss: 0.00013608933659270406
2023-01-23 04:14:48.191003: step: 1636/529, loss: 0.002893829485401511
2023-01-23 04:14:49.298419: step: 1640/529, loss: 5.741119457525201e-05
2023-01-23 04:14:50.412140: step: 1644/529, loss: 0.013698482885956764
2023-01-23 04:14:51.526756: step: 1648/529, loss: 0.0008569717756472528
2023-01-23 04:14:52.662643: step: 1652/529, loss: 0.0013421059120446444
2023-01-23 04:14:53.752609: step: 1656/529, loss: 3.7813188100699335e-05
2023-01-23 04:14:54.876215: step: 1660/529, loss: 0.05416569858789444
2023-01-23 04:14:56.007672: step: 1664/529, loss: 0.06966057419776917
2023-01-23 04:14:57.132332: step: 1668/529, loss: 1.2731551578326616e-05
2023-01-23 04:14:58.217913: step: 1672/529, loss: 0.007915640249848366
2023-01-23 04:14:59.369677: step: 1676/529, loss: 0.012709617614746094
2023-01-23 04:15:00.471563: step: 1680/529, loss: 0.006764126010239124
2023-01-23 04:15:01.601443: step: 1684/529, loss: 0.014030933380126953
2023-01-23 04:15:02.703773: step: 1688/529, loss: 0.02049226127564907
2023-01-23 04:15:03.809628: step: 1692/529, loss: 0.00020647048950195312
2023-01-23 04:15:04.917765: step: 1696/529, loss: 0.0025929692201316357
2023-01-23 04:15:06.029770: step: 1700/529, loss: 0.0012098312145099044
2023-01-23 04:15:07.169026: step: 1704/529, loss: 0.011114120483398438
2023-01-23 04:15:08.285609: step: 1708/529, loss: 0.0011238098377361894
2023-01-23 04:15:09.372376: step: 1712/529, loss: 0.007730007171630859
2023-01-23 04:15:10.444465: step: 1716/529, loss: 0.0012298583751544356
2023-01-23 04:15:11.574681: step: 1720/529, loss: 0.006230831146240234
2023-01-23 04:15:12.671432: step: 1724/529, loss: 0.02225780487060547
2023-01-23 04:15:13.754013: step: 1728/529, loss: 0.0054454803466796875
2023-01-23 04:15:14.851555: step: 1732/529, loss: 0.00015673637972213328
2023-01-23 04:15:15.990696: step: 1736/529, loss: 3.280639793956652e-05
2023-01-23 04:15:17.081329: step: 1740/529, loss: 0.07476921379566193
2023-01-23 04:15:18.227515: step: 1744/529, loss: 0.006712436676025391
2023-01-23 04:15:19.347701: step: 1748/529, loss: 3.4141543437726796e-05
2023-01-23 04:15:20.454537: step: 1752/529, loss: 0.08540745079517365
2023-01-23 04:15:21.565468: step: 1756/529, loss: 0.00019397735013626516
2023-01-23 04:15:22.712987: step: 1760/529, loss: 0.13180121779441833
2023-01-23 04:15:23.833156: step: 1764/529, loss: 0.0006969451787881553
2023-01-23 04:15:24.955217: step: 1768/529, loss: 0.004588651936501265
2023-01-23 04:15:26.083916: step: 1772/529, loss: 0.012662315741181374
2023-01-23 04:15:27.195289: step: 1776/529, loss: 2.174377368646674e-05
2023-01-23 04:15:28.324774: step: 1780/529, loss: 0.0035919188521802425
2023-01-23 04:15:29.433573: step: 1784/529, loss: 9.250640869140625e-05
2023-01-23 04:15:30.521001: step: 1788/529, loss: 0.001991844270378351
2023-01-23 04:15:31.636784: step: 1792/529, loss: 0.0007330894004553556
2023-01-23 04:15:32.753068: step: 1796/529, loss: 0.036548711359500885
2023-01-23 04:15:33.836917: step: 1800/529, loss: 0.000274848920525983
2023-01-23 04:15:34.922026: step: 1804/529, loss: 0.0002880096435546875
2023-01-23 04:15:36.035735: step: 1808/529, loss: 0.00017296076111961156
2023-01-23 04:15:37.129044: step: 1812/529, loss: 0.0006086349603720009
2023-01-23 04:15:38.227786: step: 1816/529, loss: 0.00013275146193336695
2023-01-23 04:15:39.332627: step: 1820/529, loss: 0.0446077361702919
2023-01-23 04:15:40.444499: step: 1824/529, loss: 8.735656592762098e-05
2023-01-23 04:15:41.501020: step: 1828/529, loss: 0.030761336907744408
2023-01-23 04:15:42.572222: step: 1832/529, loss: 3.414153979974799e-05
2023-01-23 04:15:43.698503: step: 1836/529, loss: 0.0003948211669921875
2023-01-23 04:15:44.803564: step: 1840/529, loss: 0.0025129318237304688
2023-01-23 04:15:45.922328: step: 1844/529, loss: 0.0031431198585778475
2023-01-23 04:15:47.062969: step: 1848/529, loss: 0.008995628915727139
2023-01-23 04:15:48.185744: step: 1852/529, loss: 7.22885160939768e-05
2023-01-23 04:15:49.308242: step: 1856/529, loss: 7.22885160939768e-05
2023-01-23 04:15:50.401056: step: 1860/529, loss: 2.9850005375919864e-05
2023-01-23 04:15:51.489241: step: 1864/529, loss: 0.001070261001586914
2023-01-23 04:15:52.594152: step: 1868/529, loss: 1.33514404296875e-05
2023-01-23 04:15:53.720349: step: 1872/529, loss: 0.008897877298295498
2023-01-23 04:15:54.819533: step: 1876/529, loss: 7.82012921263231e-06
2023-01-23 04:15:55.949964: step: 1880/529, loss: 6.752014451194555e-05
2023-01-23 04:15:57.103123: step: 1884/529, loss: -6.389617738022935e-06
2023-01-23 04:15:58.259703: step: 1888/529, loss: 0.02295098267495632
2023-01-23 04:15:59.368574: step: 1892/529, loss: 0.01791095733642578
2023-01-23 04:16:00.469921: step: 1896/529, loss: 3.0517578125e-05
2023-01-23 04:16:01.557099: step: 1900/529, loss: 0.0015121459728106856
2023-01-23 04:16:02.663224: step: 1904/529, loss: 0.0013645171420648694
2023-01-23 04:16:03.753527: step: 1908/529, loss: 1.1157989320054185e-05
2023-01-23 04:16:04.858066: step: 1912/529, loss: -3.814697322468419e-07
2023-01-23 04:16:05.993496: step: 1916/529, loss: 0.0026739120949059725
2023-01-23 04:16:07.122895: step: 1920/529, loss: 0.008389092050492764
2023-01-23 04:16:08.248026: step: 1924/529, loss: 0.0005657196161337197
2023-01-23 04:16:09.340373: step: 1928/529, loss: 0.038118936121463776
2023-01-23 04:16:10.445922: step: 1932/529, loss: 3.52382667188067e-05
2023-01-23 04:16:11.587747: step: 1936/529, loss: 6.122589547885582e-05
2023-01-23 04:16:12.697416: step: 1940/529, loss: 1.2302398317842744e-05
2023-01-23 04:16:13.811272: step: 1944/529, loss: 0.00013666153245139867
2023-01-23 04:16:14.922852: step: 1948/529, loss: 0.07349758595228195
2023-01-23 04:16:16.054125: step: 1952/529, loss: -1.811981201171875e-05
2023-01-23 04:16:17.154523: step: 1956/529, loss: 0.0015071391826495528
2023-01-23 04:16:18.249575: step: 1960/529, loss: 0.026781557127833366
2023-01-23 04:16:19.343359: step: 1964/529, loss: 0.07961349934339523
2023-01-23 04:16:20.498635: step: 1968/529, loss: 0.013255120255053043
2023-01-23 04:16:21.565404: step: 1972/529, loss: 4.148483185417717e-06
2023-01-23 04:16:22.680800: step: 1976/529, loss: 0.002250194549560547
2023-01-23 04:16:23.769765: step: 1980/529, loss: 0.00086212158203125
2023-01-23 04:16:24.911407: step: 1984/529, loss: 5.178451829124242e-05
2023-01-23 04:16:26.009567: step: 1988/529, loss: 0.019272232428193092
2023-01-23 04:16:27.130624: step: 1992/529, loss: 0.001979827880859375
2023-01-23 04:16:28.244269: step: 1996/529, loss: 0.00032019615173339844
2023-01-23 04:16:29.351732: step: 2000/529, loss: 1.4972686585679185e-05
2023-01-23 04:16:30.466452: step: 2004/529, loss: 7.562637620139867e-05
2023-01-23 04:16:31.569878: step: 2008/529, loss: 0.0007724761962890625
2023-01-23 04:16:32.655916: step: 2012/529, loss: 1.0728836059570312e-05
2023-01-23 04:16:33.770528: step: 2016/529, loss: 0.03607349470257759
2023-01-23 04:16:34.885466: step: 2020/529, loss: 0.0013422967167571187
2023-01-23 04:16:35.967261: step: 2024/529, loss: 2.0214916730765253e-05
2023-01-23 04:16:37.072382: step: 2028/529, loss: 0.00013995172048453242
2023-01-23 04:16:38.192334: step: 2032/529, loss: 3.6716460272145923e-06
2023-01-23 04:16:39.297731: step: 2036/529, loss: 0.07480011880397797
2023-01-23 04:16:40.417382: step: 2040/529, loss: 6.885529001010582e-05
2023-01-23 04:16:41.537709: step: 2044/529, loss: 0.05830421298742294
2023-01-23 04:16:42.644863: step: 2048/529, loss: 0.012754631228744984
2023-01-23 04:16:43.752561: step: 2052/529, loss: 0.000579833984375
2023-01-23 04:16:44.849225: step: 2056/529, loss: 0.002208614256232977
2023-01-23 04:16:45.943369: step: 2060/529, loss: 0.00030879973201081157
2023-01-23 04:16:47.053310: step: 2064/529, loss: 1.163482647825731e-05
2023-01-23 04:16:48.158612: step: 2068/529, loss: 0.0025478361640125513
2023-01-23 04:16:49.300477: step: 2072/529, loss: 0.025456810370087624
2023-01-23 04:16:50.438711: step: 2076/529, loss: 0.0857234001159668
2023-01-23 04:16:51.603970: step: 2080/529, loss: 0.01265411451458931
2023-01-23 04:16:52.694960: step: 2084/529, loss: 0.017270851880311966
2023-01-23 04:16:53.803328: step: 2088/529, loss: 7.638931856490672e-05
2023-01-23 04:16:54.893398: step: 2092/529, loss: 1.9931794668082148e-05
2023-01-23 04:16:56.020508: step: 2096/529, loss: 0.02219982258975506
2023-01-23 04:16:57.144922: step: 2100/529, loss: 4.19616708313697e-06
2023-01-23 04:16:58.235352: step: 2104/529, loss: 0.0005815505865029991
2023-01-23 04:16:59.403757: step: 2108/529, loss: 0.011740684509277344
2023-01-23 04:17:00.533321: step: 2112/529, loss: 0.002584457630291581
2023-01-23 04:17:01.638521: step: 2116/529, loss: 0.0003216266632080078
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.582591493570722, 'r': 0.7842876165113183, 'f1': 0.6685584562996595}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6431818181818182, 'r': 0.7985327313769752, 'f1': 0.7124874118831823}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5909090909090909, 'r': 0.9629629629629629, 'f1': 0.732394366197183}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.5789473684210527, 'r': 0.5238095238095238, 'f1': 0.5500000000000002}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.5, 'r': 0.5555555555555556, 'f1': 0.5263157894736842}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 28
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:17:41.866173: step: 4/529, loss: 4.1675568354548886e-05
2023-01-23 04:17:42.962452: step: 8/529, loss: 0.0019330024952068925
2023-01-23 04:17:44.067157: step: 12/529, loss: 0.0040760040283203125
2023-01-23 04:17:45.173053: step: 16/529, loss: 0.003063392825424671
2023-01-23 04:17:46.263695: step: 20/529, loss: 7.476806786144152e-05
2023-01-23 04:17:47.356366: step: 24/529, loss: 0.016347313299775124
2023-01-23 04:17:48.467658: step: 28/529, loss: 0.0026133540086448193
2023-01-23 04:17:49.565578: step: 32/529, loss: 0.006859302520751953
2023-01-23 04:17:50.679438: step: 36/529, loss: 0.04303283989429474
2023-01-23 04:17:51.768608: step: 40/529, loss: 1.201629675051663e-05
2023-01-23 04:17:52.851899: step: 44/529, loss: 0.0008183956379070878
2023-01-23 04:17:53.976320: step: 48/529, loss: 6.675719760096399e-06
2023-01-23 04:17:55.073672: step: 52/529, loss: 0.042644403874874115
2023-01-23 04:17:56.161066: step: 56/529, loss: 0.04410209879279137
2023-01-23 04:17:57.266609: step: 60/529, loss: 3.547668529790826e-05
2023-01-23 04:17:58.376749: step: 64/529, loss: 0.0013964653480798006
2023-01-23 04:17:59.490946: step: 68/529, loss: 0.0005510210758075118
2023-01-23 04:18:00.570002: step: 72/529, loss: 0.010648155584931374
2023-01-23 04:18:01.690331: step: 76/529, loss: 0.018959617242217064
2023-01-23 04:18:02.822676: step: 80/529, loss: 0.0011581421131268144
2023-01-23 04:18:03.934432: step: 84/529, loss: 5.645752025884576e-05
2023-01-23 04:18:05.065318: step: 88/529, loss: 0.003786277724429965
2023-01-23 04:18:06.214196: step: 92/529, loss: 0.015619468875229359
2023-01-23 04:18:07.307250: step: 96/529, loss: 0.00026931765023618937
2023-01-23 04:18:08.410017: step: 100/529, loss: 7.534027190558845e-06
2023-01-23 04:18:09.513065: step: 104/529, loss: 3.361701828907826e-06
2023-01-23 04:18:10.628666: step: 108/529, loss: 0.006878566928207874
2023-01-23 04:18:11.731108: step: 112/529, loss: 2.536773718020413e-05
2023-01-23 04:18:12.834074: step: 116/529, loss: 0.00047340395394712687
2023-01-23 04:18:13.939793: step: 120/529, loss: 0.0002574920654296875
2023-01-23 04:18:15.042783: step: 124/529, loss: 1.7166139514301904e-06
2023-01-23 04:18:16.122890: step: 128/529, loss: 0.00016016959853004664
2023-01-23 04:18:17.226756: step: 132/529, loss: 0.06166372075676918
2023-01-23 04:18:18.321737: step: 136/529, loss: 0.0010903357760980725
2023-01-23 04:18:19.409889: step: 140/529, loss: 7.343292054429185e-06
2023-01-23 04:18:20.486095: step: 144/529, loss: 0.04374518245458603
2023-01-23 04:18:21.570786: step: 148/529, loss: 0.017122268676757812
2023-01-23 04:18:22.658480: step: 152/529, loss: 0.021277237683534622
2023-01-23 04:18:23.757400: step: 156/529, loss: 3.4713742934400216e-05
2023-01-23 04:18:24.877847: step: 160/529, loss: 0.00244483957067132
2023-01-23 04:18:25.983871: step: 164/529, loss: 0.0003370285267010331
2023-01-23 04:18:27.091623: step: 168/529, loss: 0.027969172224402428
2023-01-23 04:18:28.210897: step: 172/529, loss: 0.0002017974911723286
2023-01-23 04:18:29.357594: step: 176/529, loss: -7.915497008070815e-06
2023-01-23 04:18:30.505072: step: 180/529, loss: 3.013610876223538e-05
2023-01-23 04:18:31.606929: step: 184/529, loss: 0.016840744763612747
2023-01-23 04:18:32.781241: step: 188/529, loss: 0.0024993896950036287
2023-01-23 04:18:33.912203: step: 192/529, loss: 0.0007230758783407509
2023-01-23 04:18:35.040521: step: 196/529, loss: 0.09292087703943253
2023-01-23 04:18:36.132268: step: 200/529, loss: 9.250641596736386e-06
2023-01-23 04:18:37.231344: step: 204/529, loss: 0.04134989157319069
2023-01-23 04:18:38.332186: step: 208/529, loss: 0.022498415783047676
2023-01-23 04:18:39.436343: step: 212/529, loss: 0.04449932649731636
2023-01-23 04:18:40.548807: step: 216/529, loss: 8.840560622047633e-05
2023-01-23 04:18:41.652047: step: 220/529, loss: 0.002008151961490512
2023-01-23 04:18:42.781701: step: 224/529, loss: 3.643035961431451e-05
2023-01-23 04:18:43.919924: step: 228/529, loss: 0.0123443603515625
2023-01-23 04:18:45.028969: step: 232/529, loss: 4.301071021473035e-05
2023-01-23 04:18:46.133283: step: 236/529, loss: 4.291534423828125e-05
2023-01-23 04:18:47.262394: step: 240/529, loss: 0.0002036094811046496
2023-01-23 04:18:48.360846: step: 244/529, loss: 4.711151268566027e-05
2023-01-23 04:18:49.466313: step: 248/529, loss: 0.001927280449308455
2023-01-23 04:18:50.556779: step: 252/529, loss: 0.00010385513451183215
2023-01-23 04:18:51.632647: step: 256/529, loss: 6.580352783203125e-05
2023-01-23 04:18:52.770699: step: 260/529, loss: 0.0008489609463140368
2023-01-23 04:18:53.884939: step: 264/529, loss: 0.0055624013766646385
2023-01-23 04:18:54.991645: step: 268/529, loss: 0.4556151032447815
2023-01-23 04:18:56.110247: step: 272/529, loss: 0.0001372337428620085
2023-01-23 04:18:57.221456: step: 276/529, loss: 0.02538023144006729
2023-01-23 04:18:58.357233: step: 280/529, loss: 0.0007228851318359375
2023-01-23 04:18:59.453212: step: 284/529, loss: 0.0503961555659771
2023-01-23 04:19:00.587474: step: 288/529, loss: 0.01491613406687975
2023-01-23 04:19:01.699876: step: 292/529, loss: 2.2792815798311494e-05
2023-01-23 04:19:02.817894: step: 296/529, loss: 0.0011026383144780993
2023-01-23 04:19:03.923288: step: 300/529, loss: 0.049337007105350494
2023-01-23 04:19:05.035792: step: 304/529, loss: 0.018014907836914062
2023-01-23 04:19:06.117439: step: 308/529, loss: 6.961822509765625e-05
2023-01-23 04:19:07.226274: step: 312/529, loss: 4.863739377469756e-06
2023-01-23 04:19:08.313659: step: 316/529, loss: 0.00013365744962356985
2023-01-23 04:19:09.445016: step: 320/529, loss: 0.019527243450284004
2023-01-23 04:19:10.528710: step: 324/529, loss: 0.00510063162073493
2023-01-23 04:19:11.605828: step: 328/529, loss: 3.147125244140625e-05
2023-01-23 04:19:12.739046: step: 332/529, loss: 0.04550590366125107
2023-01-23 04:19:13.847690: step: 336/529, loss: 0.0004485130193643272
2023-01-23 04:19:14.967688: step: 340/529, loss: 3.070831371587701e-05
2023-01-23 04:19:16.059879: step: 344/529, loss: -6.055831818230217e-06
2023-01-23 04:19:17.163025: step: 348/529, loss: 2.384185791015625e-05
2023-01-23 04:19:18.263815: step: 352/529, loss: 0.00046577455941587687
2023-01-23 04:19:19.359531: step: 356/529, loss: 0.0888335257768631
2023-01-23 04:19:20.475711: step: 360/529, loss: 0.061147596687078476
2023-01-23 04:19:21.565086: step: 364/529, loss: 0.07501792907714844
2023-01-23 04:19:22.680959: step: 368/529, loss: 0.035291098058223724
2023-01-23 04:19:23.799286: step: 372/529, loss: 0.03167152777314186
2023-01-23 04:19:24.901722: step: 376/529, loss: 3.452301098150201e-05
2023-01-23 04:19:26.028488: step: 380/529, loss: 0.0009988785022869706
2023-01-23 04:19:27.147030: step: 384/529, loss: 0.07250308990478516
2023-01-23 04:19:28.282276: step: 388/529, loss: 8.521079871570691e-05
2023-01-23 04:19:29.363027: step: 392/529, loss: 0.031995583325624466
2023-01-23 04:19:30.468016: step: 396/529, loss: 0.009700489230453968
2023-01-23 04:19:31.579531: step: 400/529, loss: 0.011137199588119984
2023-01-23 04:19:32.706047: step: 404/529, loss: 3.80516066798009e-05
2023-01-23 04:19:33.782378: step: 408/529, loss: 0.0001894474116852507
2023-01-23 04:19:34.891353: step: 412/529, loss: 0.00128173828125
2023-01-23 04:19:35.989778: step: 416/529, loss: 1.125335711549269e-05
2023-01-23 04:19:37.097015: step: 420/529, loss: 0.00017080306133721024
2023-01-23 04:19:38.213812: step: 424/529, loss: 0.00037288665771484375
2023-01-23 04:19:39.346435: step: 428/529, loss: 0.010532189160585403
2023-01-23 04:19:40.464208: step: 432/529, loss: 0.019727326929569244
2023-01-23 04:19:41.567848: step: 436/529, loss: 0.00014085769362282008
2023-01-23 04:19:42.693401: step: 440/529, loss: 0.010293484665453434
2023-01-23 04:19:43.822940: step: 444/529, loss: 1.1539459592313506e-05
2023-01-23 04:19:44.942560: step: 448/529, loss: 6.837844557594508e-05
2023-01-23 04:19:46.064464: step: 452/529, loss: 0.007476424798369408
2023-01-23 04:19:47.184772: step: 456/529, loss: 0.05014381557703018
2023-01-23 04:19:48.285308: step: 460/529, loss: 0.0006255150074139237
2023-01-23 04:19:49.383829: step: 464/529, loss: 0.005975103471428156
2023-01-23 04:19:50.472282: step: 468/529, loss: 0.00031452177790924907
2023-01-23 04:19:51.587850: step: 472/529, loss: 0.0006915092817507684
2023-01-23 04:19:52.679827: step: 476/529, loss: 1.754760705807712e-05
2023-01-23 04:19:53.777444: step: 480/529, loss: 0.027279948815703392
2023-01-23 04:19:54.862568: step: 484/529, loss: 0.00023002624220680445
2023-01-23 04:19:56.002282: step: 488/529, loss: 0.0020013810135424137
2023-01-23 04:19:57.101409: step: 492/529, loss: 0.0008915901416912675
2023-01-23 04:19:58.180261: step: 496/529, loss: 0.0063003539107739925
2023-01-23 04:19:59.309639: step: 500/529, loss: 0.00211086287163198
2023-01-23 04:20:00.445944: step: 504/529, loss: -1.525878360553179e-06
2023-01-23 04:20:01.526156: step: 508/529, loss: 1.5926361811580136e-05
2023-01-23 04:20:02.627537: step: 512/529, loss: 0.00013341903104446828
2023-01-23 04:20:03.751555: step: 516/529, loss: 0.0005537032848224044
2023-01-23 04:20:04.855102: step: 520/529, loss: 0.0002683639759197831
2023-01-23 04:20:05.972435: step: 524/529, loss: 0.0008466661092825234
2023-01-23 04:20:07.122264: step: 528/529, loss: 0.003160190535709262
2023-01-23 04:20:08.242430: step: 532/529, loss: 0.000599288905505091
2023-01-23 04:20:09.358128: step: 536/529, loss: 0.0003606319660320878
2023-01-23 04:20:10.465915: step: 540/529, loss: 0.2402210235595703
2023-01-23 04:20:11.577541: step: 544/529, loss: 0.00023555755615234375
2023-01-23 04:20:12.652580: step: 548/529, loss: 0.00020904540724586695
2023-01-23 04:20:13.769542: step: 552/529, loss: 0.014582633972167969
2023-01-23 04:20:14.858226: step: 556/529, loss: 1.029968279908644e-05
2023-01-23 04:20:15.948746: step: 560/529, loss: 0.0020666124764829874
2023-01-23 04:20:17.060034: step: 564/529, loss: 0.008440589532256126
2023-01-23 04:20:18.161741: step: 568/529, loss: 0.11373557895421982
2023-01-23 04:20:19.296160: step: 572/529, loss: 0.01681804656982422
2023-01-23 04:20:20.384011: step: 576/529, loss: 0.0019423485500738025
2023-01-23 04:20:21.477894: step: 580/529, loss: 0.0007164001581259072
2023-01-23 04:20:22.605710: step: 584/529, loss: 0.0013063430087640882
2023-01-23 04:20:23.684174: step: 588/529, loss: 0.011357021518051624
2023-01-23 04:20:24.797733: step: 592/529, loss: 0.0005343913799151778
2023-01-23 04:20:25.906868: step: 596/529, loss: 9.15527380129788e-06
2023-01-23 04:20:26.996162: step: 600/529, loss: 0.057305146008729935
2023-01-23 04:20:28.077943: step: 604/529, loss: 0.012722969055175781
2023-01-23 04:20:29.191422: step: 608/529, loss: 0.00033626556978560984
2023-01-23 04:20:30.261170: step: 612/529, loss: 0.0031541348434984684
2023-01-23 04:20:31.366198: step: 616/529, loss: 3.757476952159777e-05
2023-01-23 04:20:32.480701: step: 620/529, loss: 0.009058380499482155
2023-01-23 04:20:33.587656: step: 624/529, loss: 0.00424881000071764
2023-01-23 04:20:34.690227: step: 628/529, loss: 0.0002155303955078125
2023-01-23 04:20:35.789006: step: 632/529, loss: 0.0017523766728118062
2023-01-23 04:20:36.881566: step: 636/529, loss: 0.0002902030828408897
2023-01-23 04:20:37.995746: step: 640/529, loss: 0.02160634845495224
2023-01-23 04:20:39.137495: step: 644/529, loss: 0.00945220049470663
2023-01-23 04:20:40.233602: step: 648/529, loss: 0.011438179761171341
2023-01-23 04:20:41.343626: step: 652/529, loss: 0.0010198593372479081
2023-01-23 04:20:42.455771: step: 656/529, loss: 0.00018892288790084422
2023-01-23 04:20:43.578544: step: 660/529, loss: 1.220703143189894e-05
2023-01-23 04:20:44.704876: step: 664/529, loss: 5.3024294174974784e-05
2023-01-23 04:20:45.794029: step: 668/529, loss: 0.00011568069749046117
2023-01-23 04:20:46.880447: step: 672/529, loss: 8.94546537892893e-05
2023-01-23 04:20:47.989345: step: 676/529, loss: 0.0008773327572271228
2023-01-23 04:20:49.106659: step: 680/529, loss: 0.0001535534975118935
2023-01-23 04:20:50.233840: step: 684/529, loss: 3.62396240234375e-05
2023-01-23 04:20:51.344326: step: 688/529, loss: 0.0007985115516930819
2023-01-23 04:20:52.447380: step: 692/529, loss: 9.059906005859375e-05
2023-01-23 04:20:53.534832: step: 696/529, loss: 0.0007797241560183465
2023-01-23 04:20:54.662533: step: 700/529, loss: 0.0002004623383982107
2023-01-23 04:20:55.769100: step: 704/529, loss: 0.0003780364932026714
2023-01-23 04:20:56.889800: step: 708/529, loss: 0.013645363971590996
2023-01-23 04:20:57.986820: step: 712/529, loss: 0.008221722207963467
2023-01-23 04:20:59.115266: step: 716/529, loss: 0.004894256591796875
2023-01-23 04:21:00.230435: step: 720/529, loss: 3.814697606685513e-07
2023-01-23 04:21:01.310831: step: 724/529, loss: 9.393691470904741e-06
2023-01-23 04:21:02.407451: step: 728/529, loss: 1.9454957509879023e-05
2023-01-23 04:21:03.489940: step: 732/529, loss: 0.0007548332214355469
2023-01-23 04:21:04.596967: step: 736/529, loss: 5.817413239128655e-06
2023-01-23 04:21:05.686613: step: 740/529, loss: 1.373290979245212e-05
2023-01-23 04:21:06.767225: step: 744/529, loss: 0.04232082515954971
2023-01-23 04:21:07.917112: step: 748/529, loss: 0.0006826400640420616
2023-01-23 04:21:09.040470: step: 752/529, loss: 0.00011243821063544601
2023-01-23 04:21:10.142723: step: 756/529, loss: 0.00010986327833961695
2023-01-23 04:21:11.235517: step: 760/529, loss: 0.001678466796875
2023-01-23 04:21:12.338932: step: 764/529, loss: 0.0007234573713503778
2023-01-23 04:21:13.449749: step: 768/529, loss: 9.5367431640625e-05
2023-01-23 04:21:14.532038: step: 772/529, loss: 0.00010766983905341476
2023-01-23 04:21:15.658172: step: 776/529, loss: 0.006166649051010609
2023-01-23 04:21:16.748973: step: 780/529, loss: 1.354217511106981e-05
2023-01-23 04:21:17.895496: step: 784/529, loss: 0.01085443515330553
2023-01-23 04:21:19.011362: step: 788/529, loss: 8.678436643094756e-06
2023-01-23 04:21:20.093579: step: 792/529, loss: 0.0002346038818359375
2023-01-23 04:21:21.176870: step: 796/529, loss: 0.0014541626442223787
2023-01-23 04:21:22.272679: step: 800/529, loss: 0.0018613814609125257
2023-01-23 04:21:23.381129: step: 804/529, loss: 0.001175022218376398
2023-01-23 04:21:24.499624: step: 808/529, loss: 0.0007246494060382247
2023-01-23 04:21:25.593214: step: 812/529, loss: 0.0009040356380864978
2023-01-23 04:21:26.704660: step: 816/529, loss: 0.032077983021736145
2023-01-23 04:21:27.809791: step: 820/529, loss: 0.0003749847237486392
2023-01-23 04:21:28.929631: step: 824/529, loss: 0.005182075779885054
2023-01-23 04:21:30.027219: step: 828/529, loss: -1.0871887752728071e-05
2023-01-23 04:21:31.110408: step: 832/529, loss: 0.007000637240707874
2023-01-23 04:21:32.218933: step: 836/529, loss: 0.590520441532135
2023-01-23 04:21:33.346789: step: 840/529, loss: 6.103515625e-05
2023-01-23 04:21:34.444960: step: 844/529, loss: 0.0010389328235760331
2023-01-23 04:21:35.569513: step: 848/529, loss: 5.779266211902723e-05
2023-01-23 04:21:36.658460: step: 852/529, loss: 0.0032056807540357113
2023-01-23 04:21:37.761083: step: 856/529, loss: 0.012347030453383923
2023-01-23 04:21:38.860447: step: 860/529, loss: 4.863739377469756e-06
2023-01-23 04:21:39.991785: step: 864/529, loss: 0.0014041900867596269
2023-01-23 04:21:41.118947: step: 868/529, loss: 0.0015330315800383687
2023-01-23 04:21:42.234190: step: 872/529, loss: 0.003272533416748047
2023-01-23 04:21:43.333593: step: 876/529, loss: 5.53131121705519e-06
2023-01-23 04:21:44.437018: step: 880/529, loss: 0.00414199847728014
2023-01-23 04:21:45.538011: step: 884/529, loss: 0.11855840682983398
2023-01-23 04:21:46.642102: step: 888/529, loss: 1.2683868590102065e-05
2023-01-23 04:21:47.738054: step: 892/529, loss: 0.11132202297449112
2023-01-23 04:21:48.848448: step: 896/529, loss: 1.544952465337701e-05
2023-01-23 04:21:49.953657: step: 900/529, loss: 0.0017951965564861894
2023-01-23 04:21:51.043847: step: 904/529, loss: 2.3746490114717744e-05
2023-01-23 04:21:52.137594: step: 908/529, loss: 0.0007156372303143144
2023-01-23 04:21:53.261334: step: 912/529, loss: 4.701614670921117e-05
2023-01-23 04:21:54.377048: step: 916/529, loss: 9.54627976170741e-05
2023-01-23 04:21:55.476808: step: 920/529, loss: 2.880096508306451e-05
2023-01-23 04:21:56.574506: step: 924/529, loss: 0.00024147033400367945
2023-01-23 04:21:57.668919: step: 928/529, loss: 0.005999756045639515
2023-01-23 04:21:58.763236: step: 932/529, loss: 0.00012702941603492945
2023-01-23 04:21:59.869111: step: 936/529, loss: 0.0007169723394326866
2023-01-23 04:22:00.963973: step: 940/529, loss: 0.0020458223298192024
2023-01-23 04:22:02.083475: step: 944/529, loss: 0.00039119721623137593
2023-01-23 04:22:03.236187: step: 948/529, loss: 0.0009192943689413369
2023-01-23 04:22:04.363598: step: 952/529, loss: 0.08902054280042648
2023-01-23 04:22:05.453358: step: 956/529, loss: -4.768372150465439e-07
2023-01-23 04:22:06.562152: step: 960/529, loss: 9.088515798794106e-05
2023-01-23 04:22:07.656447: step: 964/529, loss: 0.17736896872520447
2023-01-23 04:22:08.784106: step: 968/529, loss: 0.0014201165176928043
2023-01-23 04:22:09.904316: step: 972/529, loss: 0.0027999880257993937
2023-01-23 04:22:10.993308: step: 976/529, loss: 6.294250852079131e-06
2023-01-23 04:22:12.164622: step: 980/529, loss: 0.026045847684144974
2023-01-23 04:22:13.275171: step: 984/529, loss: 0.0005786895635537803
2023-01-23 04:22:14.370716: step: 988/529, loss: 0.00011186600022483617
2023-01-23 04:22:15.509721: step: 992/529, loss: 0.0009332656627520919
2023-01-23 04:22:16.632426: step: 996/529, loss: 3.2138825190486386e-05
2023-01-23 04:22:17.756974: step: 1000/529, loss: 0.007909584790468216
2023-01-23 04:22:18.845947: step: 1004/529, loss: 0.0005084037547931075
2023-01-23 04:22:19.996297: step: 1008/529, loss: 6.103515261202119e-06
2023-01-23 04:22:21.106688: step: 1012/529, loss: 0.0002325058012502268
2023-01-23 04:22:22.231028: step: 1016/529, loss: 9.984970529330894e-05
2023-01-23 04:22:23.338391: step: 1020/529, loss: 0.00112152099609375
2023-01-23 04:22:24.448854: step: 1024/529, loss: 4.673004150390625e-05
2023-01-23 04:22:25.560030: step: 1028/529, loss: 0.00011215209815418348
2023-01-23 04:22:26.677241: step: 1032/529, loss: 0.0017841339576989412
2023-01-23 04:22:27.776766: step: 1036/529, loss: 0.011297762393951416
2023-01-23 04:22:28.904199: step: 1040/529, loss: 0.0012785911094397306
2023-01-23 04:22:30.015594: step: 1044/529, loss: 0.001488971640355885
2023-01-23 04:22:31.129795: step: 1048/529, loss: 3.82423386326991e-05
2023-01-23 04:22:32.216892: step: 1052/529, loss: 0.02686181105673313
2023-01-23 04:22:33.316117: step: 1056/529, loss: 0.002179908799007535
2023-01-23 04:22:34.424257: step: 1060/529, loss: 0.00045108795166015625
2023-01-23 04:22:35.540122: step: 1064/529, loss: 0.018274975940585136
2023-01-23 04:22:36.635141: step: 1068/529, loss: 3.1185150874080136e-05
2023-01-23 04:22:37.733116: step: 1072/529, loss: 0.0016240120166912675
2023-01-23 04:22:38.826168: step: 1076/529, loss: 0.01855173148214817
2023-01-23 04:22:39.971067: step: 1080/529, loss: -3.681182715808973e-05
2023-01-23 04:22:41.090548: step: 1084/529, loss: 3.695487976074219e-05
2023-01-23 04:22:42.210976: step: 1088/529, loss: 0.00036106110201217234
2023-01-23 04:22:43.301685: step: 1092/529, loss: 0.036031533032655716
2023-01-23 04:22:44.388586: step: 1096/529, loss: 0.0006015778053551912
2023-01-23 04:22:45.478087: step: 1100/529, loss: 0.0013172150356695056
2023-01-23 04:22:46.582793: step: 1104/529, loss: 0.01700124889612198
2023-01-23 04:22:47.681631: step: 1108/529, loss: 0.005195140838623047
2023-01-23 04:22:48.778894: step: 1112/529, loss: 0.0018299103248864412
2023-01-23 04:22:49.891162: step: 1116/529, loss: 0.01735048182308674
2023-01-23 04:22:51.022531: step: 1120/529, loss: 0.000347137451171875
2023-01-23 04:22:52.138529: step: 1124/529, loss: 0.01861095428466797
2023-01-23 04:22:53.244227: step: 1128/529, loss: 0.03182811662554741
2023-01-23 04:22:54.331079: step: 1132/529, loss: 0.0003147125244140625
2023-01-23 04:22:55.459407: step: 1136/529, loss: 0.0008786201360635459
2023-01-23 04:22:56.605927: step: 1140/529, loss: 0.0053993226028978825
2023-01-23 04:22:57.692452: step: 1144/529, loss: 0.019384384155273438
2023-01-23 04:22:58.834287: step: 1148/529, loss: 0.02094736136496067
2023-01-23 04:22:59.919019: step: 1152/529, loss: 7.209777686512098e-05
2023-01-23 04:23:01.002772: step: 1156/529, loss: 0.0014679909218102694
2023-01-23 04:23:02.104600: step: 1160/529, loss: 0.0001363277406198904
2023-01-23 04:23:03.193440: step: 1164/529, loss: 8.01086389401462e-06
2023-01-23 04:23:04.318553: step: 1168/529, loss: 0.003501319792121649
2023-01-23 04:23:05.419843: step: 1172/529, loss: 0.0010204315185546875
2023-01-23 04:23:06.548315: step: 1176/529, loss: 0.043367769569158554
2023-01-23 04:23:07.689213: step: 1180/529, loss: 0.0002151489316020161
2023-01-23 04:23:08.778629: step: 1184/529, loss: 0.0004848480166401714
2023-01-23 04:23:09.875323: step: 1188/529, loss: 0.09257078915834427
2023-01-23 04:23:10.958320: step: 1192/529, loss: -8.77380352903856e-06
2023-01-23 04:23:12.111970: step: 1196/529, loss: 0.0006591796991415322
2023-01-23 04:23:13.238754: step: 1200/529, loss: 0.002654838375747204
2023-01-23 04:23:14.359170: step: 1204/529, loss: 0.005988502409309149
2023-01-23 04:23:15.506530: step: 1208/529, loss: 0.0018761635292321444
2023-01-23 04:23:16.638263: step: 1212/529, loss: 0.0011517525417730212
2023-01-23 04:23:17.745130: step: 1216/529, loss: 0.0055709839798510075
2023-01-23 04:23:18.876806: step: 1220/529, loss: 0.06934338063001633
2023-01-23 04:23:20.025630: step: 1224/529, loss: 5.426407005870715e-05
2023-01-23 04:23:21.130957: step: 1228/529, loss: 0.880345344543457
2023-01-23 04:23:22.250978: step: 1232/529, loss: -1.502037139289314e-05
2023-01-23 04:23:23.364827: step: 1236/529, loss: 7.100104994606227e-05
2023-01-23 04:23:24.484161: step: 1240/529, loss: 0.00224912166595459
2023-01-23 04:23:25.579327: step: 1244/529, loss: 0.0007546782144345343
2023-01-23 04:23:26.674935: step: 1248/529, loss: 0.011242485605180264
2023-01-23 04:23:27.780907: step: 1252/529, loss: 0.015579987317323685
2023-01-23 04:23:28.892574: step: 1256/529, loss: 0.06078395992517471
2023-01-23 04:23:30.015674: step: 1260/529, loss: 0.0741397887468338
2023-01-23 04:23:31.127376: step: 1264/529, loss: 0.0013955116737633944
2023-01-23 04:23:32.214280: step: 1268/529, loss: 0.0017473220359534025
2023-01-23 04:23:33.323404: step: 1272/529, loss: 0.0008215904235839844
2023-01-23 04:23:34.435965: step: 1276/529, loss: 7.03811674611643e-05
2023-01-23 04:23:35.556501: step: 1280/529, loss: -1.1777877261920366e-05
2023-01-23 04:23:36.652777: step: 1284/529, loss: 0.45340174436569214
2023-01-23 04:23:37.827353: step: 1288/529, loss: 0.09187754988670349
2023-01-23 04:23:38.946438: step: 1292/529, loss: 0.008336067199707031
2023-01-23 04:23:40.035349: step: 1296/529, loss: 2.689361645025201e-05
2023-01-23 04:23:41.166888: step: 1300/529, loss: 0.00023446083650924265
2023-01-23 04:23:42.309127: step: 1304/529, loss: 0.002177715301513672
2023-01-23 04:23:43.401835: step: 1308/529, loss: 1.411438006471144e-05
2023-01-23 04:23:44.500012: step: 1312/529, loss: 0.0009828567272052169
2023-01-23 04:23:45.603944: step: 1316/529, loss: 0.00015392302884720266
2023-01-23 04:23:46.730608: step: 1320/529, loss: 0.021826744079589844
2023-01-23 04:23:47.851652: step: 1324/529, loss: 0.0007827759254723787
2023-01-23 04:23:48.946364: step: 1328/529, loss: 6.48498553346144e-06
2023-01-23 04:23:50.078774: step: 1332/529, loss: 8.292197890114039e-05
2023-01-23 04:23:51.192239: step: 1336/529, loss: 0.0290861614048481
2023-01-23 04:23:52.294072: step: 1340/529, loss: 0.00013065338134765625
2023-01-23 04:23:53.448473: step: 1344/529, loss: 0.0011649131774902344
2023-01-23 04:23:54.560985: step: 1348/529, loss: 0.020685292780399323
2023-01-23 04:23:55.640932: step: 1352/529, loss: 8.78334030858241e-05
2023-01-23 04:23:56.737695: step: 1356/529, loss: 0.0004375457938294858
2023-01-23 04:23:57.856352: step: 1360/529, loss: 0.007586384192109108
2023-01-23 04:23:58.981505: step: 1364/529, loss: 0.24356335401535034
2023-01-23 04:24:00.116593: step: 1368/529, loss: 8.37326078908518e-05
2023-01-23 04:24:01.236304: step: 1372/529, loss: 7.333755638683215e-05
2023-01-23 04:24:02.369665: step: 1376/529, loss: 6.86645489622606e-06
2023-01-23 04:24:03.492238: step: 1380/529, loss: 6.29425048828125e-05
2023-01-23 04:24:04.610113: step: 1384/529, loss: 0.00018367767916060984
2023-01-23 04:24:05.727551: step: 1388/529, loss: 0.0017717838054522872
2023-01-23 04:24:06.873846: step: 1392/529, loss: 0.0002916336234193295
2023-01-23 04:24:07.975740: step: 1396/529, loss: 0.0019001007312908769
2023-01-23 04:24:09.078880: step: 1400/529, loss: 0.0002880096435546875
2023-01-23 04:24:10.192271: step: 1404/529, loss: 0.05448494106531143
2023-01-23 04:24:11.298471: step: 1408/529, loss: 0.00046625136747024953
2023-01-23 04:24:12.423698: step: 1412/529, loss: 0.00908813439309597
2023-01-23 04:24:13.520595: step: 1416/529, loss: 0.0049460409209132195
2023-01-23 04:24:14.619244: step: 1420/529, loss: 0.0005999565473757684
2023-01-23 04:24:15.716407: step: 1424/529, loss: 0.003921127412468195
2023-01-23 04:24:16.802543: step: 1428/529, loss: 0.0006348371971398592
2023-01-23 04:24:17.909702: step: 1432/529, loss: 0.0014342308277264237
2023-01-23 04:24:19.009541: step: 1436/529, loss: 0.02320881001651287
2023-01-23 04:24:20.104041: step: 1440/529, loss: 0.0009210586431436241
2023-01-23 04:24:21.215947: step: 1444/529, loss: 3.4761429560603574e-05
2023-01-23 04:24:22.294408: step: 1448/529, loss: 0.0005372524028643966
2023-01-23 04:24:23.378169: step: 1452/529, loss: 0.0002694130234885961
2023-01-23 04:24:24.493378: step: 1456/529, loss: 0.00567207345739007
2023-01-23 04:24:25.586888: step: 1460/529, loss: 3.0422210329561494e-05
2023-01-23 04:24:26.703572: step: 1464/529, loss: 0.00018806457228492945
2023-01-23 04:24:27.825251: step: 1468/529, loss: 0.007238960359245539
2023-01-23 04:24:28.941804: step: 1472/529, loss: 7.43865984986769e-06
2023-01-23 04:24:30.075500: step: 1476/529, loss: 0.00917520560324192
2023-01-23 04:24:31.184588: step: 1480/529, loss: 0.0030061721336096525
2023-01-23 04:24:32.290420: step: 1484/529, loss: 0.0005032539484091103
2023-01-23 04:24:33.410183: step: 1488/529, loss: 0.005369377322494984
2023-01-23 04:24:34.489265: step: 1492/529, loss: 6.385446613421664e-05
2023-01-23 04:24:35.624969: step: 1496/529, loss: 0.0016664029099047184
2023-01-23 04:24:36.730966: step: 1500/529, loss: 0.015155792236328125
2023-01-23 04:24:37.862718: step: 1504/529, loss: 0.020765209570527077
2023-01-23 04:24:38.979371: step: 1508/529, loss: 0.000118255615234375
2023-01-23 04:24:40.083183: step: 1512/529, loss: 0.0002330779971089214
2023-01-23 04:24:41.186899: step: 1516/529, loss: 4.463195728021674e-05
2023-01-23 04:24:42.301601: step: 1520/529, loss: 0.0027618408203125
2023-01-23 04:24:43.424786: step: 1524/529, loss: 0.001327419187873602
2023-01-23 04:24:44.532709: step: 1528/529, loss: 0.00013084412785246968
2023-01-23 04:24:45.633940: step: 1532/529, loss: 1.316070574830519e-05
2023-01-23 04:24:46.735156: step: 1536/529, loss: 0.03496236726641655
2023-01-23 04:24:47.844285: step: 1540/529, loss: 6.017684791004285e-05
2023-01-23 04:24:48.953408: step: 1544/529, loss: -0.0
2023-01-23 04:24:50.087279: step: 1548/529, loss: 0.0003089427773375064
2023-01-23 04:24:51.187220: step: 1552/529, loss: 0.0006787300226278603
2023-01-23 04:24:52.283499: step: 1556/529, loss: 0.0032237053383141756
2023-01-23 04:24:53.369801: step: 1560/529, loss: 9.083747863769531e-05
2023-01-23 04:24:54.452620: step: 1564/529, loss: 0.02887878566980362
2023-01-23 04:24:55.546359: step: 1568/529, loss: 0.04644288867712021
2023-01-23 04:24:56.671684: step: 1572/529, loss: 2.28881845032447e-06
2023-01-23 04:24:57.809563: step: 1576/529, loss: -2.28881845032447e-06
2023-01-23 04:24:58.922710: step: 1580/529, loss: 1.621246337890625e-05
2023-01-23 04:25:00.024074: step: 1584/529, loss: 0.0022249221801757812
2023-01-23 04:25:01.111889: step: 1588/529, loss: 2.1648407710017636e-05
2023-01-23 04:25:02.236805: step: 1592/529, loss: -6.10351571594947e-06
2023-01-23 04:25:03.328769: step: 1596/529, loss: 5.626678102998994e-06
2023-01-23 04:25:04.433640: step: 1600/529, loss: 0.0006933212280273438
2023-01-23 04:25:05.547467: step: 1604/529, loss: 0.0010688782203942537
2023-01-23 04:25:06.652902: step: 1608/529, loss: 0.0034814835526049137
2023-01-23 04:25:07.772361: step: 1612/529, loss: 9.155272891803179e-06
2023-01-23 04:25:08.874348: step: 1616/529, loss: 0.0014782429207116365
2023-01-23 04:25:10.037627: step: 1620/529, loss: 1.583099401614163e-05
2023-01-23 04:25:11.167495: step: 1624/529, loss: 0.0001087188720703125
2023-01-23 04:25:12.290606: step: 1628/529, loss: 6.29425039733178e-06
2023-01-23 04:25:13.386961: step: 1632/529, loss: 1.0299681889591739e-05
2023-01-23 04:25:14.482198: step: 1636/529, loss: 0.035803988575935364
2023-01-23 04:25:15.593355: step: 1640/529, loss: 0.004652786068618298
2023-01-23 04:25:16.738958: step: 1644/529, loss: 0.056727029383182526
2023-01-23 04:25:17.857853: step: 1648/529, loss: 2.555847095209174e-05
2023-01-23 04:25:18.927488: step: 1652/529, loss: 1.2683867680607364e-05
2023-01-23 04:25:20.026655: step: 1656/529, loss: 0.0020586014725267887
2023-01-23 04:25:21.142749: step: 1660/529, loss: 0.0009336948860436678
2023-01-23 04:25:22.237939: step: 1664/529, loss: 0.04230918735265732
2023-01-23 04:25:23.380234: step: 1668/529, loss: 0.018568802624940872
2023-01-23 04:25:24.464987: step: 1672/529, loss: -1.9073486328125e-06
2023-01-23 04:25:25.582017: step: 1676/529, loss: 0.01316919457167387
2023-01-23 04:25:26.731707: step: 1680/529, loss: 2.09808349609375e-05
2023-01-23 04:25:27.837448: step: 1684/529, loss: 1.735687328618951e-05
2023-01-23 04:25:28.964447: step: 1688/529, loss: 0.0011392593150958419
2023-01-23 04:25:30.078168: step: 1692/529, loss: 0.00011844635446323082
2023-01-23 04:25:31.186215: step: 1696/529, loss: 2.593994213384576e-05
2023-01-23 04:25:32.301242: step: 1700/529, loss: 0.00018711091252043843
2023-01-23 04:25:33.385790: step: 1704/529, loss: 8.20159948489163e-06
2023-01-23 04:25:34.531104: step: 1708/529, loss: -1.144409225162235e-06
2023-01-23 04:25:35.647726: step: 1712/529, loss: 0.04522743448615074
2023-01-23 04:25:36.758166: step: 1716/529, loss: 3.9672853745287284e-05
2023-01-23 04:25:37.855401: step: 1720/529, loss: 0.03481006622314453
2023-01-23 04:25:38.942333: step: 1724/529, loss: 0.011277103796601295
2023-01-23 04:25:40.038886: step: 1728/529, loss: 0.007256889250129461
2023-01-23 04:25:41.147636: step: 1732/529, loss: 2.517700158932712e-05
2023-01-23 04:25:42.246929: step: 1736/529, loss: 7.314682443393394e-05
2023-01-23 04:25:43.344180: step: 1740/529, loss: 0.05733747407793999
2023-01-23 04:25:44.462694: step: 1744/529, loss: 9.13620024221018e-05
2023-01-23 04:25:45.570061: step: 1748/529, loss: 0.015453720465302467
2023-01-23 04:25:46.710586: step: 1752/529, loss: 0.04392261430621147
2023-01-23 04:25:47.834540: step: 1756/529, loss: 0.021573258563876152
2023-01-23 04:25:48.914494: step: 1760/529, loss: 0.00043702125549316406
2023-01-23 04:25:50.013251: step: 1764/529, loss: 0.0047928811982274055
2023-01-23 04:25:51.144022: step: 1768/529, loss: 0.0014234542613849044
2023-01-23 04:25:52.276056: step: 1772/529, loss: 3.738403393072076e-05
2023-01-23 04:25:53.383124: step: 1776/529, loss: 6.103515625e-05
2023-01-23 04:25:54.505325: step: 1780/529, loss: 0.005189466290175915
2023-01-23 04:25:55.604482: step: 1784/529, loss: 0.00032806396484375
2023-01-23 04:25:56.700774: step: 1788/529, loss: 6.675720669591101e-07
2023-01-23 04:25:57.796400: step: 1792/529, loss: 3.24249276673072e-06
2023-01-23 04:25:58.938943: step: 1796/529, loss: 0.02434062957763672
2023-01-23 04:26:00.079865: step: 1800/529, loss: 0.02499408647418022
2023-01-23 04:26:01.150387: step: 1804/529, loss: 0.011557006277143955
2023-01-23 04:26:02.242882: step: 1808/529, loss: 0.0013374327681958675
2023-01-23 04:26:03.340277: step: 1812/529, loss: 0.009341811761260033
2023-01-23 04:26:04.461702: step: 1816/529, loss: 0.00012111663818359375
2023-01-23 04:26:05.592938: step: 1820/529, loss: 0.000495529209729284
2023-01-23 04:26:06.702376: step: 1824/529, loss: 0.016745759174227715
2023-01-23 04:26:07.779405: step: 1828/529, loss: 0.0001548767031636089
2023-01-23 04:26:08.899504: step: 1832/529, loss: 0.0006437778356485069
2023-01-23 04:26:09.998775: step: 1836/529, loss: 0.03592805936932564
2023-01-23 04:26:11.113731: step: 1840/529, loss: 0.001772117568179965
2023-01-23 04:26:12.243696: step: 1844/529, loss: 0.04893684759736061
2023-01-23 04:26:13.349726: step: 1848/529, loss: 2.86102294921875e-05
2023-01-23 04:26:14.504166: step: 1852/529, loss: 0.003789234207943082
2023-01-23 04:26:15.618109: step: 1856/529, loss: 0.6194444894790649
2023-01-23 04:26:16.718609: step: 1860/529, loss: 0.0020144463051110506
2023-01-23 04:26:17.832249: step: 1864/529, loss: 7.438658940372989e-06
2023-01-23 04:26:18.953707: step: 1868/529, loss: 0.013620566576719284
2023-01-23 04:26:20.048576: step: 1872/529, loss: 0.00036087038461118937
2023-01-23 04:26:21.181753: step: 1876/529, loss: 0.0003662109375
2023-01-23 04:26:22.320369: step: 1880/529, loss: 0.0039619444869458675
2023-01-23 04:26:23.419427: step: 1884/529, loss: 3.42369094141759e-05
2023-01-23 04:26:24.514548: step: 1888/529, loss: 0.0002265930233988911
2023-01-23 04:26:25.643712: step: 1892/529, loss: 0.0004863739013671875
2023-01-23 04:26:26.743382: step: 1896/529, loss: 0.0008038521045818925
2023-01-23 04:26:27.842531: step: 1900/529, loss: 0.010232735425233841
2023-01-23 04:26:28.965311: step: 1904/529, loss: 0.00863275583833456
2023-01-23 04:26:30.106393: step: 1908/529, loss: 0.018400192260742188
2023-01-23 04:26:31.222004: step: 1912/529, loss: 7.696151442360133e-05
2023-01-23 04:26:32.325285: step: 1916/529, loss: 0.0006605148082599044
2023-01-23 04:26:33.423752: step: 1920/529, loss: 0.0014730454422533512
2023-01-23 04:26:34.538531: step: 1924/529, loss: 0.08725529164075851
2023-01-23 04:26:35.652670: step: 1928/529, loss: 0.27439358830451965
2023-01-23 04:26:36.774432: step: 1932/529, loss: 0.00011577607074286789
2023-01-23 04:26:37.897098: step: 1936/529, loss: 0.0632333755493164
2023-01-23 04:26:38.979037: step: 1940/529, loss: 0.00046730044414289296
2023-01-23 04:26:40.086855: step: 1944/529, loss: 0.007697486784309149
2023-01-23 04:26:41.233840: step: 1948/529, loss: 0.21207351982593536
2023-01-23 04:26:42.348851: step: 1952/529, loss: 0.0023055076599121094
2023-01-23 04:26:43.460390: step: 1956/529, loss: 1.3351441339182202e-06
2023-01-23 04:26:44.541896: step: 1960/529, loss: 0.0021831037010997534
2023-01-23 04:26:45.714810: step: 1964/529, loss: 0.00088586809579283
2023-01-23 04:26:46.830378: step: 1968/529, loss: 0.044402312487363815
2023-01-23 04:26:47.931921: step: 1972/529, loss: 0.0005143165471963584
2023-01-23 04:26:49.046052: step: 1976/529, loss: 2.9468536013155244e-05
2023-01-23 04:26:50.176793: step: 1980/529, loss: 0.03940201178193092
2023-01-23 04:26:51.273507: step: 1984/529, loss: 0.00587310828268528
2023-01-23 04:26:52.373772: step: 1988/529, loss: 0.003031921572983265
2023-01-23 04:26:53.476581: step: 1992/529, loss: 0.09160403907299042
2023-01-23 04:26:54.615769: step: 1996/529, loss: 0.0006291389581747353
2023-01-23 04:26:55.780639: step: 2000/529, loss: 0.024505138397216797
2023-01-23 04:26:56.900827: step: 2004/529, loss: 0.00021419525728560984
2023-01-23 04:26:58.018253: step: 2008/529, loss: 0.00011277198791503906
2023-01-23 04:26:59.136507: step: 2012/529, loss: 0.00037384033203125
2023-01-23 04:27:00.265545: step: 2016/529, loss: 0.06208706274628639
2023-01-23 04:27:01.381600: step: 2020/529, loss: 3.261566234868951e-05
2023-01-23 04:27:02.523146: step: 2024/529, loss: 5.5789947509765625e-05
2023-01-23 04:27:03.647708: step: 2028/529, loss: 0.0006503105396404862
2023-01-23 04:27:04.763112: step: 2032/529, loss: 8.60214204294607e-05
2023-01-23 04:27:05.865541: step: 2036/529, loss: 0.0036647438537329435
2023-01-23 04:27:07.006714: step: 2040/529, loss: 0.0003295898495707661
2023-01-23 04:27:08.143256: step: 2044/529, loss: 0.0007380485767498612
2023-01-23 04:27:09.243593: step: 2048/529, loss: 0.0006364822620525956
2023-01-23 04:27:10.370818: step: 2052/529, loss: 0.0015435218811035156
2023-01-23 04:27:11.490631: step: 2056/529, loss: 6.45637555862777e-05
2023-01-23 04:27:12.600720: step: 2060/529, loss: 0.0014858245849609375
2023-01-23 04:27:13.762262: step: 2064/529, loss: 0.0010208130115643144
2023-01-23 04:27:14.877547: step: 2068/529, loss: 0.004155635833740234
2023-01-23 04:27:15.982851: step: 2072/529, loss: 0.00348663330078125
2023-01-23 04:27:17.096322: step: 2076/529, loss: 0.0008179664728231728
2023-01-23 04:27:18.222946: step: 2080/529, loss: 0.0011617183918133378
2023-01-23 04:27:19.331302: step: 2084/529, loss: 6.299019150901586e-05
2023-01-23 04:27:20.459151: step: 2088/529, loss: 0.0008985519525595009
2023-01-23 04:27:21.558168: step: 2092/529, loss: 0.012169456109404564
2023-01-23 04:27:22.660914: step: 2096/529, loss: 0.011667441576719284
2023-01-23 04:27:23.778728: step: 2100/529, loss: 0.0008366584661416709
2023-01-23 04:27:24.887583: step: 2104/529, loss: 0.0024226189125329256
2023-01-23 04:27:25.992345: step: 2108/529, loss: 0.004815768916159868
2023-01-23 04:27:27.148304: step: 2112/529, loss: 0.0008327484247274697
2023-01-23 04:27:28.259626: step: 2116/529, loss: 0.003198051592335105
==================================================
Loss: 0.017
--------------------
Dev: {'event': {'p': 0.5875763747454175, 'r': 0.7683089214380826, 'f1': 0.6658972879399884}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6284153005464481, 'r': 0.7787810383747178, 'f1': 0.6955645161290323}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
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': 28}
Korean: {'event': {'p': 0.5869565217391305, 'r': 0.42857142857142855, 'f1': 0.49541284403669733}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.46511627906976744, 'r': 0.5555555555555556, 'f1': 0.5063291139240507}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
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 04:28:08.195349: step: 4/529, loss: 0.004092597868293524
2023-01-23 04:28:09.299755: step: 8/529, loss: 0.00031185150146484375
2023-01-23 04:28:10.404652: step: 12/529, loss: 1.621246337890625e-05
2023-01-23 04:28:11.535148: step: 16/529, loss: 3.108978125965223e-05
2023-01-23 04:28:12.614281: step: 20/529, loss: 0.01533365249633789
2023-01-23 04:28:13.704302: step: 24/529, loss: 0.0003192901494912803
2023-01-23 04:28:14.812551: step: 28/529, loss: 0.0003437042178120464
2023-01-23 04:28:15.902387: step: 32/529, loss: 0.00042705534724518657
2023-01-23 04:28:17.009027: step: 36/529, loss: 0.0002023696870310232
2023-01-23 04:28:18.122507: step: 40/529, loss: 7.152557373046875e-05
2023-01-23 04:28:19.250401: step: 44/529, loss: 0.010753917507827282
2023-01-23 04:28:20.405551: step: 48/529, loss: 0.019957160577178
2023-01-23 04:28:21.499293: step: 52/529, loss: 3.814697322468419e-07
2023-01-23 04:28:22.622774: step: 56/529, loss: 0.0009521484607830644
2023-01-23 04:28:23.772411: step: 60/529, loss: 0.00011396408081054688
2023-01-23 04:28:24.907577: step: 64/529, loss: 0.050718214362859726
2023-01-23 04:28:25.995131: step: 68/529, loss: 0.009755993261933327
2023-01-23 04:28:27.081536: step: 72/529, loss: 7.629394076502649e-07
2023-01-23 04:28:28.185693: step: 76/529, loss: 4.320144944358617e-05
2023-01-23 04:28:29.288648: step: 80/529, loss: 0.00041990281897597015
2023-01-23 04:28:30.395732: step: 84/529, loss: 0.01795501820743084
2023-01-23 04:28:31.511244: step: 88/529, loss: 6.561279587913305e-05
2023-01-23 04:28:32.631071: step: 92/529, loss: 0.0010890960693359375
2023-01-23 04:28:33.752332: step: 96/529, loss: 0.00036525726318359375
2023-01-23 04:28:34.838337: step: 100/529, loss: -2.098083541568485e-06
2023-01-23 04:28:35.980668: step: 104/529, loss: 0.0006759643438272178
2023-01-23 04:28:37.109115: step: 108/529, loss: 7.629394076502649e-06
2023-01-23 04:28:38.202819: step: 112/529, loss: 2.4127961296471767e-05
2023-01-23 04:28:39.304116: step: 116/529, loss: 0.0004878044128417969
2023-01-23 04:28:40.389994: step: 120/529, loss: 0.00014495849609375
2023-01-23 04:28:41.521884: step: 124/529, loss: 0.0016555309994146228
2023-01-23 04:28:42.701916: step: 128/529, loss: 0.009090328589081764
2023-01-23 04:28:43.792403: step: 132/529, loss: 0.00012474060349632055
2023-01-23 04:28:44.874624: step: 136/529, loss: 1.3542176020564511e-05
2023-01-23 04:28:45.974437: step: 140/529, loss: 0.0008403778192587197
2023-01-23 04:28:47.082535: step: 144/529, loss: 0.008500290103256702
2023-01-23 04:28:48.204391: step: 148/529, loss: 0.0007547378772869706
2023-01-23 04:28:49.325827: step: 152/529, loss: 0.0004295349062886089
2023-01-23 04:28:50.432702: step: 156/529, loss: 0.001307678292505443
2023-01-23 04:28:51.536515: step: 160/529, loss: 0.0062122344970703125
2023-01-23 04:28:52.625435: step: 164/529, loss: 0.004171943757683039
2023-01-23 04:28:53.757523: step: 168/529, loss: 0.001203346299007535
2023-01-23 04:28:54.877685: step: 172/529, loss: 0.0015020370483398438
2023-01-23 04:28:55.981861: step: 176/529, loss: 0.0003014564572367817
2023-01-23 04:28:57.080078: step: 180/529, loss: 0.00488014193251729
2023-01-23 04:28:58.175199: step: 184/529, loss: 0.00313491839915514
2023-01-23 04:28:59.287516: step: 188/529, loss: 0.002962303115054965
2023-01-23 04:29:00.405561: step: 192/529, loss: 0.05255451053380966
2023-01-23 04:29:01.508550: step: 196/529, loss: 3.3855438232421875e-05
2023-01-23 04:29:02.601721: step: 200/529, loss: 7.62939453125e-06
2023-01-23 04:29:03.716136: step: 204/529, loss: 0.00600929232314229
2023-01-23 04:29:04.820927: step: 208/529, loss: 2.8419495720299892e-05
2023-01-23 04:29:05.975544: step: 212/529, loss: 0.0008700728067196906
2023-01-23 04:29:07.096923: step: 216/529, loss: 0.0007225990411825478
2023-01-23 04:29:08.187127: step: 220/529, loss: 0.05460834875702858
2023-01-23 04:29:09.299730: step: 224/529, loss: 0.0004034042649436742
2023-01-23 04:29:10.398822: step: 228/529, loss: 0.010929679498076439
2023-01-23 04:29:11.491429: step: 232/529, loss: 2.765655517578125e-05
2023-01-23 04:29:12.585084: step: 236/529, loss: 0.0027210237458348274
2023-01-23 04:29:13.668492: step: 240/529, loss: -4.00543194700731e-06
2023-01-23 04:29:14.765631: step: 244/529, loss: 0.0014099121326580644
2023-01-23 04:29:15.903705: step: 248/529, loss: -2.098083541568485e-06
2023-01-23 04:29:17.031234: step: 252/529, loss: 0.04202747717499733
2023-01-23 04:29:18.123597: step: 256/529, loss: 0.016085434705018997
2023-01-23 04:29:19.248550: step: 260/529, loss: 0.0030867578461766243
2023-01-23 04:29:20.355120: step: 264/529, loss: 3.051757857974735e-06
2023-01-23 04:29:21.463992: step: 268/529, loss: 0.015006543137133121
2023-01-23 04:29:22.558660: step: 272/529, loss: 0.0004784584161825478
2023-01-23 04:29:23.685239: step: 276/529, loss: 2.765655517578125e-05
2023-01-23 04:29:24.785434: step: 280/529, loss: 3.80516066798009e-05
2023-01-23 04:29:25.888516: step: 284/529, loss: 0.0004985809209756553
2023-01-23 04:29:27.000207: step: 288/529, loss: 0.0572628490626812
2023-01-23 04:29:28.110937: step: 292/529, loss: 0.0008211136446334422
2023-01-23 04:29:29.199691: step: 296/529, loss: 0.002113437745720148
2023-01-23 04:29:30.319037: step: 300/529, loss: 0.5935726165771484
2023-01-23 04:29:31.438209: step: 304/529, loss: 0.002004432724788785
2023-01-23 04:29:32.529798: step: 308/529, loss: 7.61032133596018e-05
2023-01-23 04:29:33.640935: step: 312/529, loss: 0.006684112828224897
2023-01-23 04:29:34.743417: step: 316/529, loss: 0.0004756927373819053
2023-01-23 04:29:35.865510: step: 320/529, loss: 0.0001390457182424143
2023-01-23 04:29:36.997539: step: 324/529, loss: 0.7323215007781982
2023-01-23 04:29:38.106632: step: 328/529, loss: 0.0002038002130575478
2023-01-23 04:29:39.241992: step: 332/529, loss: 1.5258790426742053e-06
2023-01-23 04:29:40.358342: step: 336/529, loss: 0.0012258529895916581
2023-01-23 04:29:41.485364: step: 340/529, loss: 0.00409665098413825
2023-01-23 04:29:42.601391: step: 344/529, loss: 0.0008167267078533769
2023-01-23 04:29:43.732815: step: 348/529, loss: 0.10731334239244461
2023-01-23 04:29:44.843379: step: 352/529, loss: 0.07027512043714523
2023-01-23 04:29:45.958986: step: 356/529, loss: 1.1842942237854004
2023-01-23 04:29:47.076155: step: 360/529, loss: 0.0015718459617346525
2023-01-23 04:29:48.154903: step: 364/529, loss: 0.022486304864287376
2023-01-23 04:29:49.248488: step: 368/529, loss: 0.0006540298345498741
2023-01-23 04:29:50.326160: step: 372/529, loss: 2.7751922971219756e-05
2023-01-23 04:29:51.425774: step: 376/529, loss: 0.0028486251831054688
2023-01-23 04:29:52.543480: step: 380/529, loss: 0.00137500767596066
2023-01-23 04:29:53.630861: step: 384/529, loss: 4.47750098828692e-05
2023-01-23 04:29:54.741431: step: 388/529, loss: 0.00015735626220703125
2023-01-23 04:29:55.836785: step: 392/529, loss: 0.002513885498046875
2023-01-23 04:29:56.935094: step: 396/529, loss: 0.010579205118119717
2023-01-23 04:29:58.020268: step: 400/529, loss: 2.1266938347253017e-05
2023-01-23 04:29:59.101919: step: 404/529, loss: 0.0045219422318041325
2023-01-23 04:30:00.213811: step: 408/529, loss: 5.569458153331652e-05
2023-01-23 04:30:01.310286: step: 412/529, loss: 5.9604644775390625e-05
2023-01-23 04:30:02.420859: step: 416/529, loss: 0.011366844177246094
2023-01-23 04:30:03.527454: step: 420/529, loss: 0.00616378802806139
2023-01-23 04:30:04.613509: step: 424/529, loss: 0.045984648168087006
2023-01-23 04:30:05.722040: step: 428/529, loss: 0.004430866800248623
2023-01-23 04:30:06.830031: step: 432/529, loss: 0.0026763915084302425
2023-01-23 04:30:07.964972: step: 436/529, loss: 0.0008678436279296875
2023-01-23 04:30:09.067826: step: 440/529, loss: 0.07574901729822159
2023-01-23 04:30:10.173047: step: 444/529, loss: 0.0001638412504689768
2023-01-23 04:30:11.306100: step: 448/529, loss: 8.46386028570123e-05
2023-01-23 04:30:12.389017: step: 452/529, loss: 1.621246337890625e-05
2023-01-23 04:30:13.496016: step: 456/529, loss: 0.0003631591971497983
2023-01-23 04:30:14.606872: step: 460/529, loss: 0.000377655029296875
2023-01-23 04:30:15.712285: step: 464/529, loss: 0.0018795013893395662
2023-01-23 04:30:16.821152: step: 468/529, loss: 0.004645919892936945
2023-01-23 04:30:17.906442: step: 472/529, loss: 3.1089784897631034e-05
2023-01-23 04:30:19.002433: step: 476/529, loss: 0.007003116421401501
2023-01-23 04:30:20.101960: step: 480/529, loss: 0.008932781405746937
2023-01-23 04:30:21.217729: step: 484/529, loss: 0.0029113772325217724
2023-01-23 04:30:22.323901: step: 488/529, loss: 0.017908478155732155
2023-01-23 04:30:23.407401: step: 492/529, loss: 0.002963257022202015
2023-01-23 04:30:24.478453: step: 496/529, loss: 0.3411533236503601
2023-01-23 04:30:25.598573: step: 500/529, loss: 0.0005902767297811806
2023-01-23 04:30:26.691507: step: 504/529, loss: 0.0001161575346486643
2023-01-23 04:30:27.810963: step: 508/529, loss: -2.6702882678364404e-06
2023-01-23 04:30:28.893618: step: 512/529, loss: 0.04043960198760033
2023-01-23 04:30:30.003444: step: 516/529, loss: 0.0002285957452841103
2023-01-23 04:30:31.182478: step: 520/529, loss: 0.11449813842773438
2023-01-23 04:30:32.292261: step: 524/529, loss: 0.0010884285438805819
2023-01-23 04:30:33.405612: step: 528/529, loss: 0.0011043548583984375
2023-01-23 04:30:34.510900: step: 532/529, loss: 0.010164165869355202
2023-01-23 04:30:35.627260: step: 536/529, loss: 0.00032272341195493937
2023-01-23 04:30:36.759069: step: 540/529, loss: 3.366470627952367e-05
2023-01-23 04:30:37.874200: step: 544/529, loss: 0.0005010605091229081
2023-01-23 04:30:39.000721: step: 548/529, loss: 0.00010848045349121094
2023-01-23 04:30:40.109275: step: 552/529, loss: 3.0136110581224784e-05
2023-01-23 04:30:41.222284: step: 556/529, loss: 1.201629675051663e-05
2023-01-23 04:30:42.296676: step: 560/529, loss: 1.296997106692288e-05
2023-01-23 04:30:43.399358: step: 564/529, loss: 0.018535614013671875
2023-01-23 04:30:44.497847: step: 568/529, loss: 0.004475736990571022
2023-01-23 04:30:45.628580: step: 572/529, loss: 0.03180637210607529
2023-01-23 04:30:46.771293: step: 576/529, loss: 0.0005739211919717491
2023-01-23 04:30:47.865003: step: 580/529, loss: 0.0015921592712402344
2023-01-23 04:30:48.976349: step: 584/529, loss: 0.011671066284179688
2023-01-23 04:30:50.103203: step: 588/529, loss: 0.00987854041159153
2023-01-23 04:30:51.198687: step: 592/529, loss: 0.003669929690659046
2023-01-23 04:30:52.337952: step: 596/529, loss: 1.5974044799804688e-05
2023-01-23 04:30:53.438583: step: 600/529, loss: 0.024297334253787994
2023-01-23 04:30:54.546220: step: 604/529, loss: 0.003869438311085105
2023-01-23 04:30:55.641927: step: 608/529, loss: 5.855560448253527e-05
2023-01-23 04:30:56.777917: step: 612/529, loss: 0.0010390282841399312
2023-01-23 04:30:57.902977: step: 616/529, loss: 0.0002941131533589214
2023-01-23 04:30:59.027056: step: 620/529, loss: 0.04735575243830681
2023-01-23 04:31:00.100955: step: 624/529, loss: -1.3351439065445447e-06
2023-01-23 04:31:01.206386: step: 628/529, loss: 0.00014495849609375
2023-01-23 04:31:02.304041: step: 632/529, loss: 0.0012647629482671618
2023-01-23 04:31:03.429420: step: 636/529, loss: 0.0002586364862509072
2023-01-23 04:31:04.568122: step: 640/529, loss: 9.5367431640625e-07
2023-01-23 04:31:05.700494: step: 644/529, loss: -2.09808349609375e-05
2023-01-23 04:31:06.815033: step: 648/529, loss: 0.024466706439852715
2023-01-23 04:31:07.944647: step: 652/529, loss: 0.002342700958251953
2023-01-23 04:31:09.058918: step: 656/529, loss: 0.0024061203002929688
2023-01-23 04:31:10.142396: step: 660/529, loss: 1.3732910701946821e-05
2023-01-23 04:31:11.228853: step: 664/529, loss: 0.000324058550177142
2023-01-23 04:31:12.337558: step: 668/529, loss: 4.158019874012098e-05
2023-01-23 04:31:13.499488: step: 672/529, loss: 0.005105209536850452
2023-01-23 04:31:14.635043: step: 676/529, loss: 0.0008537292596884072
2023-01-23 04:31:15.761902: step: 680/529, loss: 3.738403393072076e-05
2023-01-23 04:31:16.872461: step: 684/529, loss: 0.010645199567079544
2023-01-23 04:31:17.952732: step: 688/529, loss: 8.144378807628527e-05
2023-01-23 04:31:19.085138: step: 692/529, loss: 6.895065598655492e-05
2023-01-23 04:31:20.168293: step: 696/529, loss: 0.02693800814449787
2023-01-23 04:31:21.301685: step: 700/529, loss: 0.0011053085327148438
2023-01-23 04:31:22.396826: step: 704/529, loss: 4.100799742445815e-06
2023-01-23 04:31:23.480111: step: 708/529, loss: 2.6226043701171875e-06
2023-01-23 04:31:24.596942: step: 712/529, loss: 9.765624417923391e-05
2023-01-23 04:31:25.705236: step: 716/529, loss: 4.606247239280492e-05
2023-01-23 04:31:26.828378: step: 720/529, loss: 0.014852523803710938
2023-01-23 04:31:27.939957: step: 724/529, loss: 0.0006097317091189325
2023-01-23 04:31:29.018202: step: 728/529, loss: 6.675720101156912e-07
2023-01-23 04:31:30.134497: step: 732/529, loss: 0.014451599679887295
2023-01-23 04:31:31.264577: step: 736/529, loss: 0.022385217249393463
2023-01-23 04:31:32.377899: step: 740/529, loss: 2.6702882678364404e-06
2023-01-23 04:31:33.498154: step: 744/529, loss: 0.00013256072998046875
2023-01-23 04:31:34.585153: step: 748/529, loss: 2.021789623540826e-05
2023-01-23 04:31:35.703872: step: 752/529, loss: 0.0003832101938314736
2023-01-23 04:31:36.809041: step: 756/529, loss: 0.0033186913933604956
2023-01-23 04:31:37.906180: step: 760/529, loss: 0.0003864288446493447
2023-01-23 04:31:38.979979: step: 764/529, loss: 7.667542377021164e-05
2023-01-23 04:31:40.079100: step: 768/529, loss: 8.58306884765625e-06
2023-01-23 04:31:41.232359: step: 772/529, loss: 0.008380889892578125
2023-01-23 04:31:42.316354: step: 776/529, loss: 0.01411972101777792
2023-01-23 04:31:43.444493: step: 780/529, loss: -4.95910626341356e-06
2023-01-23 04:31:44.549620: step: 784/529, loss: 3.919601658708416e-05
2023-01-23 04:31:45.693031: step: 788/529, loss: 7.152557373046875e-06
2023-01-23 04:31:46.814610: step: 792/529, loss: 0.00010452270362293348
2023-01-23 04:31:47.915894: step: 796/529, loss: 0.015958786010742188
2023-01-23 04:31:49.038592: step: 800/529, loss: 2.746581958490424e-05
2023-01-23 04:31:50.155715: step: 804/529, loss: 0.00023328961106017232
2023-01-23 04:31:51.239178: step: 808/529, loss: 5.4788590205134824e-05
2023-01-23 04:31:52.319416: step: 812/529, loss: 2.19345088225964e-06
2023-01-23 04:31:53.430410: step: 816/529, loss: -1.735687328618951e-05
2023-01-23 04:31:54.518336: step: 820/529, loss: 0.00315780658274889
2023-01-23 04:31:55.631617: step: 824/529, loss: 5.636215428239666e-05
2023-01-23 04:31:56.750055: step: 828/529, loss: 0.00043354035005904734
2023-01-23 04:31:57.874624: step: 832/529, loss: 0.01212158240377903
2023-01-23 04:31:59.006451: step: 836/529, loss: 0.008632087148725986
2023-01-23 04:32:00.107979: step: 840/529, loss: 0.00041236879769712687
2023-01-23 04:32:01.214458: step: 844/529, loss: 0.0009363174322061241
2023-01-23 04:32:02.347769: step: 848/529, loss: 0.005694389343261719
2023-01-23 04:32:03.465308: step: 852/529, loss: 0.013215827755630016
2023-01-23 04:32:04.568182: step: 856/529, loss: 0.012385082431137562
2023-01-23 04:32:05.686822: step: 860/529, loss: 0.0038232803344726562
2023-01-23 04:32:06.795238: step: 864/529, loss: 0.029938984662294388
2023-01-23 04:32:07.902275: step: 868/529, loss: 1.831054760259576e-05
2023-01-23 04:32:08.994022: step: 872/529, loss: 1.0633468264131807e-05
2023-01-23 04:32:10.157210: step: 876/529, loss: 0.014688300900161266
2023-01-23 04:32:11.268970: step: 880/529, loss: 0.0007961273076944053
2023-01-23 04:32:12.388293: step: 884/529, loss: 0.0016300200950354338
2023-01-23 04:32:13.542955: step: 888/529, loss: 4.3821339204441756e-05
2023-01-23 04:32:14.652102: step: 892/529, loss: 1.773834264895413e-05
2023-01-23 04:32:15.768623: step: 896/529, loss: 0.00011291504779364914
2023-01-23 04:32:16.877512: step: 900/529, loss: 0.0004173278866801411
2023-01-23 04:32:17.977919: step: 904/529, loss: 0.008144665509462357
2023-01-23 04:32:19.087121: step: 908/529, loss: 0.004697227850556374
2023-01-23 04:32:20.214580: step: 912/529, loss: 0.0015292167663574219
2023-01-23 04:32:21.325441: step: 916/529, loss: 0.01612091064453125
2023-01-23 04:32:22.426247: step: 920/529, loss: 0.007676315493881702
2023-01-23 04:32:23.506951: step: 924/529, loss: 0.00025177001953125
2023-01-23 04:32:24.588139: step: 928/529, loss: 0.03468160703778267
2023-01-23 04:32:25.713952: step: 932/529, loss: 8.01086389401462e-06
2023-01-23 04:32:26.801860: step: 936/529, loss: 0.043299295008182526
2023-01-23 04:32:27.925728: step: 940/529, loss: 0.0011086465092375875
2023-01-23 04:32:29.044387: step: 944/529, loss: 0.005763053894042969
2023-01-23 04:32:30.177568: step: 948/529, loss: 0.0007173538324423134
2023-01-23 04:32:31.270934: step: 952/529, loss: 0.01083984412252903
2023-01-23 04:32:32.398495: step: 956/529, loss: 0.00032453538733534515
2023-01-23 04:32:33.489550: step: 960/529, loss: 0.0036390305031090975
2023-01-23 04:32:34.575498: step: 964/529, loss: 8.535385859431699e-05
2023-01-23 04:32:35.683438: step: 968/529, loss: 0.00025119780912064016
2023-01-23 04:32:36.848760: step: 972/529, loss: 0.0005382538074627519
2023-01-23 04:32:37.975768: step: 976/529, loss: 0.0005075454828329384
2023-01-23 04:32:39.094272: step: 980/529, loss: 5.512237476068549e-05
2023-01-23 04:32:40.185691: step: 984/529, loss: 5.91278057981981e-06
2023-01-23 04:32:41.299197: step: 988/529, loss: 0.00013828277587890625
2023-01-23 04:32:42.414265: step: 992/529, loss: 0.00013628005399368703
2023-01-23 04:32:43.493148: step: 996/529, loss: -8.010864803509321e-06
2023-01-23 04:32:44.603514: step: 1000/529, loss: 3.108978125965223e-05
2023-01-23 04:32:45.748785: step: 1004/529, loss: 0.00890426617115736
2023-01-23 04:32:46.868230: step: 1008/529, loss: -4.00543194700731e-06
2023-01-23 04:32:48.011785: step: 1012/529, loss: 5.9127810345671605e-06
2023-01-23 04:32:49.125616: step: 1016/529, loss: 3.7670135498046875e-05
2023-01-23 04:32:50.247630: step: 1020/529, loss: 0.05157947540283203
2023-01-23 04:32:51.359035: step: 1024/529, loss: 2.1934511096333154e-06
2023-01-23 04:32:52.462672: step: 1028/529, loss: 7.04765334376134e-05
2023-01-23 04:32:53.578651: step: 1032/529, loss: 0.0005767822149209678
2023-01-23 04:32:54.704758: step: 1036/529, loss: 0.01827411726117134
2023-01-23 04:32:55.794818: step: 1040/529, loss: 6.647109694313258e-05
2023-01-23 04:32:56.932764: step: 1044/529, loss: 0.002139949705451727
2023-01-23 04:32:58.038778: step: 1048/529, loss: 0.0008876801002770662
2023-01-23 04:32:59.153228: step: 1052/529, loss: 0.0016753196250647306
2023-01-23 04:33:00.265009: step: 1056/529, loss: 0.017768096178770065
2023-01-23 04:33:01.341742: step: 1060/529, loss: 1.9168854123563506e-05
2023-01-23 04:33:02.445592: step: 1064/529, loss: 0.0011323929065838456
2023-01-23 04:33:03.550460: step: 1068/529, loss: 0.00023193360539153218
2023-01-23 04:33:04.677168: step: 1072/529, loss: 0.007983589544892311
2023-01-23 04:33:05.778546: step: 1076/529, loss: -1.9073486328125e-06
2023-01-23 04:33:06.902827: step: 1080/529, loss: 0.0003346920129843056
2023-01-23 04:33:08.044657: step: 1084/529, loss: 0.006165123078972101
2023-01-23 04:33:09.139534: step: 1088/529, loss: 3.185272362316027e-05
2023-01-23 04:33:10.219759: step: 1092/529, loss: 0.00026836394681595266
2023-01-23 04:33:11.313215: step: 1096/529, loss: 0.010147953405976295
2023-01-23 04:33:12.421643: step: 1100/529, loss: 0.0009092330583371222
2023-01-23 04:33:13.547557: step: 1104/529, loss: 0.04119310528039932
2023-01-23 04:33:14.658823: step: 1108/529, loss: 0.0002062797429971397
2023-01-23 04:33:15.747933: step: 1112/529, loss: 1.8119812921213452e-06
2023-01-23 04:33:16.868494: step: 1116/529, loss: 0.006128692999482155
2023-01-23 04:33:17.966187: step: 1120/529, loss: 0.001466941786929965
2023-01-23 04:33:19.085327: step: 1124/529, loss: 2.47955322265625e-05
2023-01-23 04:33:20.227556: step: 1128/529, loss: 3.471374657237902e-05
2023-01-23 04:33:21.358815: step: 1132/529, loss: 0.0001370430109091103
2023-01-23 04:33:22.471535: step: 1136/529, loss: 0.0009796142112463713
2023-01-23 04:33:23.560864: step: 1140/529, loss: -9.536742027194123e-07
2023-01-23 04:33:24.657265: step: 1144/529, loss: 0.0003751754993572831
2023-01-23 04:33:25.775657: step: 1148/529, loss: 0.053568124771118164
2023-01-23 04:33:26.901455: step: 1152/529, loss: 0.00016880035400390625
2023-01-23 04:33:28.019679: step: 1156/529, loss: 8.392333984375e-05
2023-01-23 04:33:29.107918: step: 1160/529, loss: 0.0073226927779614925
2023-01-23 04:33:30.239625: step: 1164/529, loss: 0.0010486602550372481
2023-01-23 04:33:31.336036: step: 1168/529, loss: 5.054473876953125e-05
2023-01-23 04:33:32.448382: step: 1172/529, loss: 0.0002512931823730469
2023-01-23 04:33:33.563015: step: 1176/529, loss: 4.825591895496473e-05
2023-01-23 04:33:34.646268: step: 1180/529, loss: 0.0023343085777014494
2023-01-23 04:33:35.792728: step: 1184/529, loss: 0.0002460479736328125
2023-01-23 04:33:36.873617: step: 1188/529, loss: 0.000404548627557233
2023-01-23 04:33:38.002205: step: 1192/529, loss: -1.220703143189894e-05
2023-01-23 04:33:39.072461: step: 1196/529, loss: 0.00011239051673328504
2023-01-23 04:33:40.207399: step: 1200/529, loss: 0.0005481719854287803
2023-01-23 04:33:41.328788: step: 1204/529, loss: 5.14984139954322e-06
2023-01-23 04:33:42.455607: step: 1208/529, loss: 0.05054473876953125
2023-01-23 04:33:43.576469: step: 1212/529, loss: 1.811981201171875e-05
2023-01-23 04:33:44.703150: step: 1216/529, loss: 0.005728295538574457
2023-01-23 04:33:45.789126: step: 1220/529, loss: 1.8024446035269648e-05
2023-01-23 04:33:46.927781: step: 1224/529, loss: 0.01786670833826065
2023-01-23 04:33:48.019367: step: 1228/529, loss: -1.382828031637473e-06
2023-01-23 04:33:49.138272: step: 1232/529, loss: 9.860992577159777e-05
2023-01-23 04:33:50.267490: step: 1236/529, loss: 0.0050325398333370686
2023-01-23 04:33:51.388393: step: 1240/529, loss: 1.52587890625e-05
2023-01-23 04:33:52.493279: step: 1244/529, loss: 0.0020725249778479338
2023-01-23 04:33:53.608816: step: 1248/529, loss: 0.007106971461325884
2023-01-23 04:33:54.713049: step: 1252/529, loss: 3.871917579090223e-05
2023-01-23 04:33:55.833912: step: 1256/529, loss: 0.0026372908614575863
2023-01-23 04:33:56.957227: step: 1260/529, loss: 0.0071929930709302425
2023-01-23 04:33:58.069574: step: 1264/529, loss: 1.6880036127986386e-05
2023-01-23 04:33:59.166550: step: 1268/529, loss: 0.00011920928955078125
2023-01-23 04:34:00.255273: step: 1272/529, loss: 9.13620024221018e-05
2023-01-23 04:34:01.381070: step: 1276/529, loss: 0.016804886981844902
2023-01-23 04:34:02.485370: step: 1280/529, loss: 0.0008592605590820312
2023-01-23 04:34:03.578095: step: 1284/529, loss: 0.0005680083995684981
2023-01-23 04:34:04.656497: step: 1288/529, loss: 0.00018558502779342234
2023-01-23 04:34:05.778805: step: 1292/529, loss: 2.2737367544323206e-13
2023-01-23 04:34:06.917057: step: 1296/529, loss: 0.00027647020760923624
2023-01-23 04:34:08.005534: step: 1300/529, loss: 1.3446808225126006e-05
2023-01-23 04:34:09.150487: step: 1304/529, loss: 0.00505905132740736
2023-01-23 04:34:10.281258: step: 1308/529, loss: 0.1079990416765213
2023-01-23 04:34:11.393496: step: 1312/529, loss: 0.06154899671673775
2023-01-23 04:34:12.506209: step: 1316/529, loss: 6.389618647517636e-06
2023-01-23 04:34:13.610173: step: 1320/529, loss: 2.098083541568485e-06
2023-01-23 04:34:14.717651: step: 1324/529, loss: 1.010894811770413e-05
2023-01-23 04:34:15.837836: step: 1328/529, loss: 0.0015863417647778988
2023-01-23 04:34:16.960943: step: 1332/529, loss: 0.004235458094626665
2023-01-23 04:34:18.050478: step: 1336/529, loss: 5.674362546415068e-05
2023-01-23 04:34:19.191352: step: 1340/529, loss: 2.517700158932712e-05
2023-01-23 04:34:20.344824: step: 1344/529, loss: 1.3256072634248994e-05
2023-01-23 04:34:21.418060: step: 1348/529, loss: 0.5052580833435059
2023-01-23 04:34:22.571524: step: 1352/529, loss: 9.117127046920359e-05
2023-01-23 04:34:23.694744: step: 1356/529, loss: 0.0016935348976403475
2023-01-23 04:34:24.784889: step: 1360/529, loss: 0.504020094871521
2023-01-23 04:34:25.898893: step: 1364/529, loss: 0.00012311936006881297
2023-01-23 04:34:27.015602: step: 1368/529, loss: 0.0006533623090945184
2023-01-23 04:34:28.125569: step: 1372/529, loss: 3.0994415283203125e-05
2023-01-23 04:34:29.218214: step: 1376/529, loss: 0.01027364656329155
2023-01-23 04:34:30.313541: step: 1380/529, loss: -2.0503998712229077e-06
2023-01-23 04:34:31.440315: step: 1384/529, loss: 4.415512375999242e-05
2023-01-23 04:34:32.537093: step: 1388/529, loss: 0.00037231447640806437
2023-01-23 04:34:33.660749: step: 1392/529, loss: 0.00029757022275589406
2023-01-23 04:34:34.770608: step: 1396/529, loss: 0.009863471612334251
2023-01-23 04:34:35.865291: step: 1400/529, loss: 0.00014219284639693797
2023-01-23 04:34:36.983125: step: 1404/529, loss: 0.011015797033905983
2023-01-23 04:34:38.094884: step: 1408/529, loss: 0.00020713807316496968
2023-01-23 04:34:39.226254: step: 1412/529, loss: 0.0011715890141204
2023-01-23 04:34:40.320242: step: 1416/529, loss: 0.006308651063591242
2023-01-23 04:34:41.429465: step: 1420/529, loss: 0.000431251508416608
2023-01-23 04:34:42.520617: step: 1424/529, loss: 0.03197136148810387
2023-01-23 04:34:43.624643: step: 1428/529, loss: 0.0047660828568041325
2023-01-23 04:34:44.723291: step: 1432/529, loss: 4.57763690064894e-06
2023-01-23 04:34:45.849913: step: 1436/529, loss: 4.386902219266631e-06
2023-01-23 04:34:46.941203: step: 1440/529, loss: 5.760193016612902e-05
2023-01-23 04:34:48.042003: step: 1444/529, loss: 0.013804435729980469
2023-01-23 04:34:49.145858: step: 1448/529, loss: 0.03641214221715927
2023-01-23 04:34:50.264989: step: 1452/529, loss: 0.019589995965361595
2023-01-23 04:34:51.403634: step: 1456/529, loss: 0.00010566711716819555
2023-01-23 04:34:52.535892: step: 1460/529, loss: 9.670257713878527e-05
2023-01-23 04:34:53.644996: step: 1464/529, loss: -6.675720669591101e-07
2023-01-23 04:34:54.773106: step: 1468/529, loss: 0.0007474899175576866
2023-01-23 04:34:55.887256: step: 1472/529, loss: 0.02275843545794487
2023-01-23 04:34:56.967813: step: 1476/529, loss: 0.0007833481067791581
2023-01-23 04:34:58.077015: step: 1480/529, loss: 0.00023517609224654734
2023-01-23 04:34:59.169297: step: 1484/529, loss: 0.0009361267439089715
2023-01-23 04:35:00.291720: step: 1488/529, loss: 0.007314491551369429
2023-01-23 04:35:01.423946: step: 1492/529, loss: 0.0011762619251385331
2023-01-23 04:35:02.542696: step: 1496/529, loss: 0.00039615630521439016
2023-01-23 04:35:03.666540: step: 1500/529, loss: 0.02231578901410103
2023-01-23 04:35:04.809126: step: 1504/529, loss: 0.02380080334842205
2023-01-23 04:35:05.919108: step: 1508/529, loss: 0.0009593963623046875
2023-01-23 04:35:07.026932: step: 1512/529, loss: 0.00014925003051757812
2023-01-23 04:35:08.127715: step: 1516/529, loss: 7.452964928233996e-05
2023-01-23 04:35:09.239203: step: 1520/529, loss: 0.003545093582943082
2023-01-23 04:35:10.366351: step: 1524/529, loss: 0.0012932777171954513
2023-01-23 04:35:11.478835: step: 1528/529, loss: 0.00015916825213935226
2023-01-23 04:35:12.596699: step: 1532/529, loss: 2.102851794916205e-05
2023-01-23 04:35:13.691418: step: 1536/529, loss: 0.018183136358857155
2023-01-23 04:35:14.786852: step: 1540/529, loss: 4.982948303222656e-05
2023-01-23 04:35:15.886321: step: 1544/529, loss: 0.007026863284409046
2023-01-23 04:35:17.027135: step: 1548/529, loss: 0.00039997100248001516
2023-01-23 04:35:18.133031: step: 1552/529, loss: -1.1444089977885596e-06
2023-01-23 04:35:19.248176: step: 1556/529, loss: 7.209778414107859e-05
2023-01-23 04:35:20.338015: step: 1560/529, loss: 0.0002583026944193989
2023-01-23 04:35:21.445080: step: 1564/529, loss: 0.007990170270204544
2023-01-23 04:35:22.564293: step: 1568/529, loss: 2.803802453854587e-05
2023-01-23 04:35:23.722485: step: 1572/529, loss: 0.0016742706065997481
2023-01-23 04:35:24.831432: step: 1576/529, loss: 0.00016789436631370336
2023-01-23 04:35:25.915103: step: 1580/529, loss: 0.0010194778442382812
2023-01-23 04:35:27.033370: step: 1584/529, loss: 0.0024636269081383944
2023-01-23 04:35:28.154728: step: 1588/529, loss: 0.0002288818359375
2023-01-23 04:35:29.254735: step: 1592/529, loss: 0.0005058288807049394
2023-01-23 04:35:30.398662: step: 1596/529, loss: 0.0007925033569335938
2023-01-23 04:35:31.516565: step: 1600/529, loss: 0.0012141228653490543
2023-01-23 04:35:32.637494: step: 1604/529, loss: 0.002918243408203125
2023-01-23 04:35:33.762195: step: 1608/529, loss: 0.00102748884819448
2023-01-23 04:35:34.900121: step: 1612/529, loss: 0.0005796432378701866
2023-01-23 04:35:36.002949: step: 1616/529, loss: 0.0001220703125
2023-01-23 04:35:37.103454: step: 1620/529, loss: 2.136230432370212e-05
2023-01-23 04:35:38.199928: step: 1624/529, loss: 0.007133865728974342
2023-01-23 04:35:39.308435: step: 1628/529, loss: 0.003608131315559149
2023-01-23 04:35:40.447081: step: 1632/529, loss: 0.011096049100160599
2023-01-23 04:35:41.535188: step: 1636/529, loss: 0.0022530558053404093
2023-01-23 04:35:42.653892: step: 1640/529, loss: 9.860992577159777e-05
2023-01-23 04:35:43.757916: step: 1644/529, loss: 7.05719003235572e-06
2023-01-23 04:35:44.883820: step: 1648/529, loss: 0.003171730088070035
2023-01-23 04:35:45.980726: step: 1652/529, loss: 7.43865966796875e-05
2023-01-23 04:35:47.107575: step: 1656/529, loss: 0.02402954176068306
2023-01-23 04:35:48.209573: step: 1660/529, loss: 0.00013294219388626516
2023-01-23 04:35:49.310181: step: 1664/529, loss: 0.011955262161791325
2023-01-23 04:35:50.422617: step: 1668/529, loss: 0.00034580231294967234
2023-01-23 04:35:51.531467: step: 1672/529, loss: 0.00046443939208984375
2023-01-23 04:35:52.635380: step: 1676/529, loss: 0.0020887376740574837
2023-01-23 04:35:53.734672: step: 1680/529, loss: 0.0001638412504689768
2023-01-23 04:35:54.869831: step: 1684/529, loss: 0.01572876051068306
2023-01-23 04:35:55.968319: step: 1688/529, loss: 5.350113133317791e-05
2023-01-23 04:35:57.092065: step: 1692/529, loss: 0.01955118216574192
2023-01-23 04:35:58.203701: step: 1696/529, loss: 0.00024518967256881297
2023-01-23 04:35:59.295790: step: 1700/529, loss: 8.98361176950857e-05
2023-01-23 04:36:00.383287: step: 1704/529, loss: 0.019835758954286575
2023-01-23 04:36:01.460949: step: 1708/529, loss: 8.01086389401462e-06
2023-01-23 04:36:02.571995: step: 1712/529, loss: 0.0008781433571130037
2023-01-23 04:36:03.695643: step: 1716/529, loss: 7.152557373046875e-06
2023-01-23 04:36:04.811692: step: 1720/529, loss: 0.002100372454151511
2023-01-23 04:36:05.942629: step: 1724/529, loss: 0.06157030910253525
2023-01-23 04:36:07.027431: step: 1728/529, loss: 0.010883521288633347
2023-01-23 04:36:08.143333: step: 1732/529, loss: 0.00036258698673918843
2023-01-23 04:36:09.253816: step: 1736/529, loss: 7.43865984986769e-06
2023-01-23 04:36:10.342286: step: 1740/529, loss: 0.006790733430534601
2023-01-23 04:36:11.463825: step: 1744/529, loss: 0.00015544892812613398
2023-01-23 04:36:12.557374: step: 1748/529, loss: 0.0012887954944744706
2023-01-23 04:36:13.671801: step: 1752/529, loss: 3.204345557605848e-05
2023-01-23 04:36:14.778761: step: 1756/529, loss: 0.03918743133544922
2023-01-23 04:36:15.899897: step: 1760/529, loss: 0.0003551483096089214
2023-01-23 04:36:17.000810: step: 1764/529, loss: 2.1266938347253017e-05
2023-01-23 04:36:18.095492: step: 1768/529, loss: 3.871917579090223e-05
2023-01-23 04:36:19.189075: step: 1772/529, loss: 1.029968279908644e-05
2023-01-23 04:36:20.337041: step: 1776/529, loss: 0.0028073787689208984
2023-01-23 04:36:21.442247: step: 1780/529, loss: 9.136199514614418e-05
2023-01-23 04:36:22.535297: step: 1784/529, loss: 0.0005895138019695878
2023-01-23 04:36:23.644518: step: 1788/529, loss: 1.831054760259576e-05
2023-01-23 04:36:24.776208: step: 1792/529, loss: 4.9400332500226796e-05
2023-01-23 04:36:25.871638: step: 1796/529, loss: 0.014212418347597122
2023-01-23 04:36:27.011224: step: 1800/529, loss: 2.0980833141948096e-06
2023-01-23 04:36:28.130548: step: 1804/529, loss: 0.046585846692323685
2023-01-23 04:36:29.245231: step: 1808/529, loss: -3.52859501617786e-06
2023-01-23 04:36:30.343623: step: 1812/529, loss: 0.0023492814507335424
2023-01-23 04:36:31.462799: step: 1816/529, loss: 0.0005411148304119706
2023-01-23 04:36:32.569784: step: 1820/529, loss: 0.0026319504249840975
2023-01-23 04:36:33.698065: step: 1824/529, loss: 0.008322334848344326
2023-01-23 04:36:34.868579: step: 1828/529, loss: 0.0011900902027264237
2023-01-23 04:36:35.981618: step: 1832/529, loss: 0.00018825530423782766
2023-01-23 04:36:37.081734: step: 1836/529, loss: 9.72747784544481e-06
2023-01-23 04:36:38.196449: step: 1840/529, loss: 2.079009937006049e-05
2023-01-23 04:36:39.282340: step: 1844/529, loss: 0.05358171835541725
2023-01-23 04:36:40.380788: step: 1848/529, loss: 0.0012691498268395662
2023-01-23 04:36:41.498453: step: 1852/529, loss: 0.009786320850253105
2023-01-23 04:36:42.605598: step: 1856/529, loss: 6.980896432651207e-05
2023-01-23 04:36:43.711602: step: 1860/529, loss: 3.051757857974735e-06
2023-01-23 04:36:44.828110: step: 1864/529, loss: 2.880096508306451e-05
2023-01-23 04:36:45.901623: step: 1868/529, loss: 0.0014727592933923006
2023-01-23 04:36:46.990493: step: 1872/529, loss: 0.0025319100823253393
2023-01-23 04:36:48.093838: step: 1876/529, loss: 0.0006879806751385331
2023-01-23 04:36:49.232115: step: 1880/529, loss: 0.03494777902960777
2023-01-23 04:36:50.345019: step: 1884/529, loss: 7.99179106252268e-05
2023-01-23 04:36:51.446443: step: 1888/529, loss: 0.0007623672718182206
2023-01-23 04:36:52.540807: step: 1892/529, loss: 0.014723301865160465
2023-01-23 04:36:53.648561: step: 1896/529, loss: 0.0006964683998376131
2023-01-23 04:36:54.783088: step: 1900/529, loss: 0.0009338379022665322
2023-01-23 04:36:55.910314: step: 1904/529, loss: 0.004417228978127241
2023-01-23 04:36:57.028151: step: 1908/529, loss: 4.596710277837701e-05
2023-01-23 04:36:58.125084: step: 1912/529, loss: 6.69479341013357e-05
2023-01-23 04:36:59.222832: step: 1916/529, loss: 0.0020542144775390625
2023-01-23 04:37:00.324833: step: 1920/529, loss: 0.00020294189744163305
2023-01-23 04:37:01.411356: step: 1924/529, loss: 0.018357563763856888
2023-01-23 04:37:02.526022: step: 1928/529, loss: 6.31332368357107e-05
2023-01-23 04:37:03.616676: step: 1932/529, loss: 0.0002918243408203125
2023-01-23 04:37:04.711369: step: 1936/529, loss: 0.30141276121139526
2023-01-23 04:37:05.795994: step: 1940/529, loss: 0.0002953529474325478
2023-01-23 04:37:06.923978: step: 1944/529, loss: -1.316070574830519e-05
2023-01-23 04:37:08.034543: step: 1948/529, loss: 0.06830983608961105
2023-01-23 04:37:09.174915: step: 1952/529, loss: 0.004886818118393421
2023-01-23 04:37:10.282026: step: 1956/529, loss: 0.023650072515010834
2023-01-23 04:37:11.435030: step: 1960/529, loss: 0.0025791169609874487
2023-01-23 04:37:12.530148: step: 1964/529, loss: 0.008010578341782093
2023-01-23 04:37:13.636048: step: 1968/529, loss: 8.58306884765625e-06
2023-01-23 04:37:14.760010: step: 1972/529, loss: 0.008647155947983265
2023-01-23 04:37:15.880824: step: 1976/529, loss: 0.013877678662538528
2023-01-23 04:37:16.987336: step: 1980/529, loss: 1.239776611328125e-05
2023-01-23 04:37:18.105768: step: 1984/529, loss: 0.033011436462402344
2023-01-23 04:37:19.249462: step: 1988/529, loss: 0.004666232969611883
2023-01-23 04:37:20.371874: step: 1992/529, loss: 0.03419189527630806
2023-01-23 04:37:21.487575: step: 1996/529, loss: 0.0012063980102539062
2023-01-23 04:37:22.618047: step: 2000/529, loss: 0.0019620894454419613
2023-01-23 04:37:23.736493: step: 2004/529, loss: 0.003364181611686945
2023-01-23 04:37:24.836773: step: 2008/529, loss: 0.0037262917030602694
2023-01-23 04:37:25.973554: step: 2012/529, loss: 0.06978455185890198
2023-01-23 04:37:27.081032: step: 2016/529, loss: 0.1108541488647461
2023-01-23 04:37:28.177863: step: 2020/529, loss: 0.0027518272399902344
2023-01-23 04:37:29.301719: step: 2024/529, loss: -2.9802322387695312e-05
2023-01-23 04:37:30.441316: step: 2028/529, loss: 0.29665735363960266
2023-01-23 04:37:31.532003: step: 2032/529, loss: -3.8146970382513246e-07
2023-01-23 04:37:32.618453: step: 2036/529, loss: 0.0005783081287518144
2023-01-23 04:37:33.711692: step: 2040/529, loss: 2.708435022213962e-05
2023-01-23 04:37:34.846144: step: 2044/529, loss: 3.795623706537299e-05
2023-01-23 04:37:35.963889: step: 2048/529, loss: 0.00013809202937409282
2023-01-23 04:37:37.065596: step: 2052/529, loss: -1.182556115963962e-05
2023-01-23 04:37:38.228969: step: 2056/529, loss: 0.0034593583550304174
2023-01-23 04:37:39.324041: step: 2060/529, loss: 2.670288040462765e-06
2023-01-23 04:37:40.421531: step: 2064/529, loss: 1.964569128176663e-05
2023-01-23 04:37:41.543321: step: 2068/529, loss: 0.00012283325486350805
2023-01-23 04:37:42.660629: step: 2072/529, loss: 6.46591215627268e-05
2023-01-23 04:37:43.789997: step: 2076/529, loss: -4.95910626341356e-06
2023-01-23 04:37:44.869873: step: 2080/529, loss: 0.00048465729923918843
2023-01-23 04:37:45.980996: step: 2084/529, loss: 6.580352783203125e-05
2023-01-23 04:37:47.092928: step: 2088/529, loss: 0.0009780883556231856
2023-01-23 04:37:48.181947: step: 2092/529, loss: 0.02933654747903347
2023-01-23 04:37:49.291593: step: 2096/529, loss: 7.057190487103071e-06
2023-01-23 04:37:50.403823: step: 2100/529, loss: 0.0002346038818359375
2023-01-23 04:37:51.505999: step: 2104/529, loss: 0.005618095397949219
2023-01-23 04:37:52.613255: step: 2108/529, loss: 0.018789293244481087
2023-01-23 04:37:53.703207: step: 2112/529, loss: 3.0326846172101796e-05
2023-01-23 04:37:54.829868: step: 2116/529, loss: 0.013628196902573109
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5617342130065975, 'r': 0.7936085219707057, 'f1': 0.6578366445916115}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6246042514699232, 'r': 0.7793453724604966, 'f1': 0.6934471503891539}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.5873015873015873, 'r': 0.5873015873015873, 'f1': 0.5873015873015873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.4782608695652174, 'r': 0.6111111111111112, 'f1': 0.5365853658536586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.574384236453202, 'r': 0.7762982689747004, 'f1': 0.6602491506228766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.592640136927685, 'r': 0.7816027088036117, 'f1': 0.6741299586274032}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.6046511627906976, 'r': 0.9629629629629629, 'f1': 0.7428571428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5833333333333334, 'r': 0.7643142476697736, 'f1': 0.661671469740634}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Eng Test for Korean: {'event': {'p': 0.634571297569922, 'r': 0.781038374717833, 'f1': 0.7002276751834049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Sample Korean: {'event': {'p': 0.6774193548387096, 'r': 0.6666666666666666, 'f1': 0.6719999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6099893730074389, 'r': 0.7643142476697736, 'f1': 0.6784869976359338}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6238532110091743, 'r': 0.7291196388261851, 'f1': 0.6723913609159511}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.6046511627906976, 'r': 0.7222222222222222, 'f1': 0.6582278481012659}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}