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
2023-01-21 08:25:17.568347: step: 4/530, loss: 3.600830554962158
2023-01-21 08:25:18.721506: step: 8/530, loss: 11.446001052856445
2023-01-21 08:25:19.863462: step: 12/530, loss: 5.477788925170898
2023-01-21 08:25:20.974393: step: 16/530, loss: 3.1343941688537598
2023-01-21 08:25:22.131060: step: 20/530, loss: 3.854640007019043
2023-01-21 08:25:23.236138: step: 24/530, loss: 3.0547313690185547
2023-01-21 08:25:24.385475: step: 28/530, loss: 11.198469161987305
2023-01-21 08:25:25.498488: step: 32/530, loss: 10.628847122192383
2023-01-21 08:25:26.629348: step: 36/530, loss: 19.666278839111328
2023-01-21 08:25:27.748690: step: 40/530, loss: 4.534551620483398
2023-01-21 08:25:28.907968: step: 44/530, loss: 3.983240842819214
2023-01-21 08:25:30.035333: step: 48/530, loss: 5.397889137268066
2023-01-21 08:25:31.147651: step: 52/530, loss: 5.041791915893555
2023-01-21 08:25:32.264855: step: 56/530, loss: 2.1729354858398438
2023-01-21 08:25:33.388994: step: 60/530, loss: 3.4424490928649902
2023-01-21 08:25:34.572373: step: 64/530, loss: 22.45005989074707
2023-01-21 08:25:35.716208: step: 68/530, loss: 30.6683349609375
2023-01-21 08:25:36.842272: step: 72/530, loss: 3.5177664756774902
2023-01-21 08:25:37.994647: step: 76/530, loss: 4.0421295166015625
2023-01-21 08:25:39.098263: step: 80/530, loss: 3.200045108795166
2023-01-21 08:25:40.203950: step: 84/530, loss: 3.304994583129883
2023-01-21 08:25:41.342847: step: 88/530, loss: 19.04894256591797
2023-01-21 08:25:42.445799: step: 92/530, loss: 3.5746703147888184
2023-01-21 08:25:43.557979: step: 96/530, loss: 11.587350845336914
2023-01-21 08:25:44.658046: step: 100/530, loss: 3.2992119789123535
2023-01-21 08:25:45.759051: step: 104/530, loss: 13.409751892089844
2023-01-21 08:25:46.879239: step: 108/530, loss: 9.834317207336426
2023-01-21 08:25:48.012040: step: 112/530, loss: 5.219486236572266
2023-01-21 08:25:49.128736: step: 116/530, loss: 2.659261703491211
2023-01-21 08:25:50.232035: step: 120/530, loss: 21.642410278320312
2023-01-21 08:25:51.361818: step: 124/530, loss: 2.6457650661468506
2023-01-21 08:25:52.483171: step: 128/530, loss: 7.287134170532227
2023-01-21 08:25:53.579464: step: 132/530, loss: 10.075141906738281
2023-01-21 08:25:54.688930: step: 136/530, loss: 9.616050720214844
2023-01-21 08:25:55.811891: step: 140/530, loss: 10.84445858001709
2023-01-21 08:25:56.931590: step: 144/530, loss: 19.43450164794922
2023-01-21 08:25:58.062344: step: 148/530, loss: 2.7353615760803223
2023-01-21 08:25:59.197187: step: 152/530, loss: 3.719870090484619
2023-01-21 08:26:00.330684: step: 156/530, loss: 11.29328441619873
2023-01-21 08:26:01.441760: step: 160/530, loss: 8.982820510864258
2023-01-21 08:26:02.574226: step: 164/530, loss: 4.201029300689697
2023-01-21 08:26:03.702981: step: 168/530, loss: 14.721243858337402
2023-01-21 08:26:04.817563: step: 172/530, loss: 20.664798736572266
2023-01-21 08:26:05.922726: step: 176/530, loss: 6.335413932800293
2023-01-21 08:26:07.030022: step: 180/530, loss: 3.3321621417999268
2023-01-21 08:26:08.141157: step: 184/530, loss: 16.395395278930664
2023-01-21 08:26:09.260448: step: 188/530, loss: 2.9829115867614746
2023-01-21 08:26:10.406242: step: 192/530, loss: 3.75447940826416
2023-01-21 08:26:11.531465: step: 196/530, loss: 3.3201072216033936
2023-01-21 08:26:12.668105: step: 200/530, loss: 16.67919158935547
2023-01-21 08:26:13.811274: step: 204/530, loss: 12.394281387329102
2023-01-21 08:26:14.913034: step: 208/530, loss: 22.63667106628418
2023-01-21 08:26:16.044604: step: 212/530, loss: 21.802249908447266
2023-01-21 08:26:17.195864: step: 216/530, loss: 17.718791961669922
2023-01-21 08:26:18.320661: step: 220/530, loss: 7.292086124420166
2023-01-21 08:26:19.414152: step: 224/530, loss: 9.311068534851074
2023-01-21 08:26:20.500048: step: 228/530, loss: 8.232246398925781
2023-01-21 08:26:21.618542: step: 232/530, loss: 3.0800533294677734
2023-01-21 08:26:22.788406: step: 236/530, loss: 5.678860664367676
2023-01-21 08:26:23.921593: step: 240/530, loss: 12.479248046875
2023-01-21 08:26:25.027119: step: 244/530, loss: 14.88258171081543
2023-01-21 08:26:26.148936: step: 248/530, loss: 3.3008227348327637
2023-01-21 08:26:27.254822: step: 252/530, loss: 1.9073622226715088
2023-01-21 08:26:28.403701: step: 256/530, loss: 3.8980636596679688
2023-01-21 08:26:29.559829: step: 260/530, loss: 20.849109649658203
2023-01-21 08:26:30.683316: step: 264/530, loss: 12.183300018310547
2023-01-21 08:26:31.817654: step: 268/530, loss: 3.017989158630371
2023-01-21 08:26:32.994074: step: 272/530, loss: 4.457563400268555
2023-01-21 08:26:34.095329: step: 276/530, loss: 3.3766024112701416
2023-01-21 08:26:35.212094: step: 280/530, loss: 2.2874879837036133
2023-01-21 08:26:36.320444: step: 284/530, loss: 13.350345611572266
2023-01-21 08:26:37.462273: step: 288/530, loss: 4.229209899902344
2023-01-21 08:26:38.572263: step: 292/530, loss: 30.592504501342773
2023-01-21 08:26:39.728494: step: 296/530, loss: 3.621605157852173
2023-01-21 08:26:40.821155: step: 300/530, loss: 2.939500570297241
2023-01-21 08:26:41.948980: step: 304/530, loss: 11.074926376342773
2023-01-21 08:26:43.052884: step: 308/530, loss: 16.21042823791504
2023-01-21 08:26:44.190425: step: 312/530, loss: 32.711097717285156
2023-01-21 08:26:45.307295: step: 316/530, loss: 2.7682790756225586
2023-01-21 08:26:46.453794: step: 320/530, loss: 19.118976593017578
2023-01-21 08:26:47.605332: step: 324/530, loss: 10.407299995422363
2023-01-21 08:26:48.733183: step: 328/530, loss: 2.090254068374634
2023-01-21 08:26:49.870964: step: 332/530, loss: 4.193398475646973
2023-01-21 08:26:51.004522: step: 336/530, loss: 20.624755859375
2023-01-21 08:26:52.118084: step: 340/530, loss: 3.584094524383545
2023-01-21 08:26:53.249673: step: 344/530, loss: 11.230154037475586
2023-01-21 08:26:54.368305: step: 348/530, loss: 10.490753173828125
2023-01-21 08:26:55.515516: step: 352/530, loss: 29.088909149169922
2023-01-21 08:26:56.630041: step: 356/530, loss: 2.8673999309539795
2023-01-21 08:26:57.782358: step: 360/530, loss: 9.16180419921875
2023-01-21 08:26:58.902045: step: 364/530, loss: 7.584294319152832
2023-01-21 08:27:00.015407: step: 368/530, loss: 2.8562428951263428
2023-01-21 08:27:01.138375: step: 372/530, loss: 2.784353733062744
2023-01-21 08:27:02.317320: step: 376/530, loss: 23.008869171142578
2023-01-21 08:27:03.435438: step: 380/530, loss: 8.876879692077637
2023-01-21 08:27:04.607446: step: 384/530, loss: 8.077498435974121
2023-01-21 08:27:05.722113: step: 388/530, loss: 3.9711127281188965
2023-01-21 08:27:06.837501: step: 392/530, loss: 9.134020805358887
2023-01-21 08:27:07.963294: step: 396/530, loss: 25.49004364013672
2023-01-21 08:27:09.106149: step: 400/530, loss: 4.108882427215576
2023-01-21 08:27:10.214599: step: 404/530, loss: 7.861549377441406
2023-01-21 08:27:11.367272: step: 408/530, loss: 7.5175461769104
2023-01-21 08:27:12.522071: step: 412/530, loss: 9.480937004089355
2023-01-21 08:27:13.670419: step: 416/530, loss: 10.70997428894043
2023-01-21 08:27:14.789733: step: 420/530, loss: 2.3260340690612793
2023-01-21 08:27:15.925634: step: 424/530, loss: 3.471595287322998
2023-01-21 08:27:17.039737: step: 428/530, loss: 3.711090087890625
2023-01-21 08:27:18.198733: step: 432/530, loss: 3.251601219177246
2023-01-21 08:27:19.323962: step: 436/530, loss: 3.768089771270752
2023-01-21 08:27:20.461346: step: 440/530, loss: 2.9075162410736084
2023-01-21 08:27:21.583653: step: 444/530, loss: 2.0615603923797607
2023-01-21 08:27:22.687488: step: 448/530, loss: 11.910271644592285
2023-01-21 08:27:23.813710: step: 452/530, loss: 7.101742744445801
2023-01-21 08:27:24.946704: step: 456/530, loss: 7.715378761291504
2023-01-21 08:27:26.090988: step: 460/530, loss: 1.998674988746643
2023-01-21 08:27:27.241175: step: 464/530, loss: 14.214048385620117
2023-01-21 08:27:28.383971: step: 468/530, loss: 8.028645515441895
2023-01-21 08:27:29.511134: step: 472/530, loss: 2.282589912414551
2023-01-21 08:27:30.630105: step: 476/530, loss: 5.238405227661133
2023-01-21 08:27:31.758070: step: 480/530, loss: 2.1900508403778076
2023-01-21 08:27:32.876924: step: 484/530, loss: 7.375765800476074
2023-01-21 08:27:33.988624: step: 488/530, loss: 4.8053765296936035
2023-01-21 08:27:35.136901: step: 492/530, loss: 7.305607795715332
2023-01-21 08:27:36.285518: step: 496/530, loss: 13.81304931640625
2023-01-21 08:27:37.444809: step: 500/530, loss: 5.6990556716918945
2023-01-21 08:27:38.555097: step: 504/530, loss: 3.9752540588378906
2023-01-21 08:27:39.667185: step: 508/530, loss: 1.5550434589385986
2023-01-21 08:27:40.804754: step: 512/530, loss: 1.7749539613723755
2023-01-21 08:27:41.922930: step: 516/530, loss: 1.4538006782531738
2023-01-21 08:27:43.063415: step: 520/530, loss: 3.191053867340088
2023-01-21 08:27:44.189985: step: 524/530, loss: 1.3320629596710205
2023-01-21 08:27:45.333190: step: 528/530, loss: 2.291764736175537
2023-01-21 08:27:46.429924: step: 532/530, loss: 3.120242118835449
2023-01-21 08:27:47.557457: step: 536/530, loss: 4.4088945388793945
2023-01-21 08:27:48.647543: step: 540/530, loss: 4.373464584350586
2023-01-21 08:27:49.769830: step: 544/530, loss: 2.950277805328369
2023-01-21 08:27:50.894554: step: 548/530, loss: 6.946873188018799
2023-01-21 08:27:52.013319: step: 552/530, loss: 8.5263090133667
2023-01-21 08:27:53.150792: step: 556/530, loss: 2.9757401943206787
2023-01-21 08:27:54.262782: step: 560/530, loss: 0.8556032180786133
2023-01-21 08:27:55.390851: step: 564/530, loss: 2.5542051792144775
2023-01-21 08:27:56.512353: step: 568/530, loss: 8.050448417663574
2023-01-21 08:27:57.618827: step: 572/530, loss: 1.2285194396972656
2023-01-21 08:27:58.752535: step: 576/530, loss: 3.2618823051452637
2023-01-21 08:27:59.862608: step: 580/530, loss: 1.3381786346435547
2023-01-21 08:28:00.978188: step: 584/530, loss: 0.6971803307533264
2023-01-21 08:28:02.114209: step: 588/530, loss: 4.007962226867676
2023-01-21 08:28:03.221754: step: 592/530, loss: 1.5476454496383667
2023-01-21 08:28:04.326296: step: 596/530, loss: 0.6741154193878174
2023-01-21 08:28:05.436863: step: 600/530, loss: 4.426174163818359
2023-01-21 08:28:06.565414: step: 604/530, loss: 1.5493625402450562
2023-01-21 08:28:07.697238: step: 608/530, loss: 4.625621318817139
2023-01-21 08:28:08.815553: step: 612/530, loss: 1.687483549118042
2023-01-21 08:28:09.903350: step: 616/530, loss: 4.624767303466797
2023-01-21 08:28:11.038882: step: 620/530, loss: 4.724775314331055
2023-01-21 08:28:12.149129: step: 624/530, loss: 0.7202094793319702
2023-01-21 08:28:13.257979: step: 628/530, loss: 1.3630282878875732
2023-01-21 08:28:14.379891: step: 632/530, loss: 1.2366769313812256
2023-01-21 08:28:15.497331: step: 636/530, loss: 0.607374370098114
2023-01-21 08:28:16.635739: step: 640/530, loss: 3.485468864440918
2023-01-21 08:28:17.750278: step: 644/530, loss: 1.0302376747131348
2023-01-21 08:28:18.869822: step: 648/530, loss: 0.8324732184410095
2023-01-21 08:28:20.001248: step: 652/530, loss: 3.657708168029785
2023-01-21 08:28:21.119916: step: 656/530, loss: 2.873729705810547
2023-01-21 08:28:22.276519: step: 660/530, loss: 7.555106163024902
2023-01-21 08:28:23.358369: step: 664/530, loss: 0.5502809286117554
2023-01-21 08:28:24.479363: step: 668/530, loss: 2.3129308223724365
2023-01-21 08:28:25.596968: step: 672/530, loss: 1.891132116317749
2023-01-21 08:28:26.717972: step: 676/530, loss: 9.392467498779297
2023-01-21 08:28:27.839848: step: 680/530, loss: 1.7686702013015747
2023-01-21 08:28:28.940323: step: 684/530, loss: 2.2616591453552246
2023-01-21 08:28:30.037760: step: 688/530, loss: 2.5172009468078613
2023-01-21 08:28:31.157243: step: 692/530, loss: 1.1885987520217896
2023-01-21 08:28:32.305339: step: 696/530, loss: 0.6277967691421509
2023-01-21 08:28:33.458706: step: 700/530, loss: 0.45983749628067017
2023-01-21 08:28:34.571406: step: 704/530, loss: 3.198279857635498
2023-01-21 08:28:35.672692: step: 708/530, loss: 0.674511194229126
2023-01-21 08:28:36.780943: step: 712/530, loss: 0.8145885467529297
2023-01-21 08:28:37.929758: step: 716/530, loss: 1.9764336347579956
2023-01-21 08:28:39.071266: step: 720/530, loss: 3.313617706298828
2023-01-21 08:28:40.195380: step: 724/530, loss: 0.6266363263130188
2023-01-21 08:28:41.294919: step: 728/530, loss: 0.5607494115829468
2023-01-21 08:28:42.428835: step: 732/530, loss: 0.5683830976486206
2023-01-21 08:28:43.568445: step: 736/530, loss: 5.060230255126953
2023-01-21 08:28:44.715645: step: 740/530, loss: 0.6281356811523438
2023-01-21 08:28:45.815509: step: 744/530, loss: 0.637123703956604
2023-01-21 08:28:46.936303: step: 748/530, loss: 0.6059290170669556
2023-01-21 08:28:48.066355: step: 752/530, loss: 4.053745746612549
2023-01-21 08:28:49.188680: step: 756/530, loss: 2.8495497703552246
2023-01-21 08:28:50.302059: step: 760/530, loss: 2.016963481903076
2023-01-21 08:28:51.434631: step: 764/530, loss: 1.4283347129821777
2023-01-21 08:28:52.546962: step: 768/530, loss: 2.5355424880981445
2023-01-21 08:28:53.677865: step: 772/530, loss: 2.572380781173706
2023-01-21 08:28:54.790110: step: 776/530, loss: 2.76509690284729
2023-01-21 08:28:55.906479: step: 780/530, loss: 3.676267623901367
2023-01-21 08:28:57.059952: step: 784/530, loss: 2.0123727321624756
2023-01-21 08:28:58.193843: step: 788/530, loss: 3.093647003173828
2023-01-21 08:28:59.328035: step: 792/530, loss: 1.3893589973449707
2023-01-21 08:29:00.439176: step: 796/530, loss: 0.5670020580291748
2023-01-21 08:29:01.535980: step: 800/530, loss: 1.9091811180114746
2023-01-21 08:29:02.646480: step: 804/530, loss: 1.1956661939620972
2023-01-21 08:29:03.752680: step: 808/530, loss: 0.33247166872024536
2023-01-21 08:29:04.897850: step: 812/530, loss: 2.714752197265625
2023-01-21 08:29:06.021946: step: 816/530, loss: 2.7602460384368896
2023-01-21 08:29:07.149612: step: 820/530, loss: 1.389080286026001
2023-01-21 08:29:08.248639: step: 824/530, loss: 1.6229441165924072
2023-01-21 08:29:09.368105: step: 828/530, loss: 0.9028524160385132
2023-01-21 08:29:10.495960: step: 832/530, loss: 2.3566911220550537
2023-01-21 08:29:11.629781: step: 836/530, loss: 1.0580787658691406
2023-01-21 08:29:12.746708: step: 840/530, loss: 1.3911709785461426
2023-01-21 08:29:13.871274: step: 844/530, loss: 1.1588531732559204
2023-01-21 08:29:14.989492: step: 848/530, loss: 0.7124577760696411
2023-01-21 08:29:16.099895: step: 852/530, loss: 0.46316224336624146
2023-01-21 08:29:17.247719: step: 856/530, loss: 0.675922691822052
2023-01-21 08:29:18.377888: step: 860/530, loss: 0.7243403196334839
2023-01-21 08:29:19.518723: step: 864/530, loss: 0.27582770586013794
2023-01-21 08:29:20.615845: step: 868/530, loss: 3.4991581439971924
2023-01-21 08:29:21.745021: step: 872/530, loss: 0.9697194695472717
2023-01-21 08:29:22.854243: step: 876/530, loss: 1.0417035818099976
2023-01-21 08:29:23.980958: step: 880/530, loss: 0.7541743516921997
2023-01-21 08:29:25.084596: step: 884/530, loss: 0.46459466218948364
2023-01-21 08:29:26.209546: step: 888/530, loss: 1.741030216217041
2023-01-21 08:29:27.396921: step: 892/530, loss: 0.4115075170993805
2023-01-21 08:29:28.508401: step: 896/530, loss: 0.5463149547576904
2023-01-21 08:29:29.623376: step: 900/530, loss: 0.6377755403518677
2023-01-21 08:29:30.742420: step: 904/530, loss: 2.4856197834014893
2023-01-21 08:29:31.902795: step: 908/530, loss: 3.756301164627075
2023-01-21 08:29:33.028525: step: 912/530, loss: 0.4391940236091614
2023-01-21 08:29:34.136908: step: 916/530, loss: 1.045654058456421
2023-01-21 08:29:35.258295: step: 920/530, loss: 1.518012523651123
2023-01-21 08:29:36.377250: step: 924/530, loss: 3.4010565280914307
2023-01-21 08:29:37.506876: step: 928/530, loss: 0.46121102571487427
2023-01-21 08:29:38.624881: step: 932/530, loss: 7.733952045440674
2023-01-21 08:29:39.738704: step: 936/530, loss: 0.608338475227356
2023-01-21 08:29:40.843017: step: 940/530, loss: 2.4491991996765137
2023-01-21 08:29:41.975772: step: 944/530, loss: 1.2341818809509277
2023-01-21 08:29:43.095234: step: 948/530, loss: 0.30906087160110474
2023-01-21 08:29:44.195531: step: 952/530, loss: 2.2727456092834473
2023-01-21 08:29:45.332858: step: 956/530, loss: 3.5723812580108643
2023-01-21 08:29:46.444252: step: 960/530, loss: 0.5487877130508423
2023-01-21 08:29:47.570809: step: 964/530, loss: 1.386991024017334
2023-01-21 08:29:48.708885: step: 968/530, loss: 0.4014175534248352
2023-01-21 08:29:49.825860: step: 972/530, loss: 0.33909910917282104
2023-01-21 08:29:50.932180: step: 976/530, loss: 1.0264865159988403
2023-01-21 08:29:52.062707: step: 980/530, loss: 0.48007574677467346
2023-01-21 08:29:53.207223: step: 984/530, loss: 0.5306209325790405
2023-01-21 08:29:54.324035: step: 988/530, loss: 1.0716761350631714
2023-01-21 08:29:55.467549: step: 992/530, loss: 0.5828955769538879
2023-01-21 08:29:56.575680: step: 996/530, loss: 0.685972273349762
2023-01-21 08:29:57.724217: step: 1000/530, loss: 0.412115216255188
2023-01-21 08:29:58.858481: step: 1004/530, loss: 0.29873672127723694
2023-01-21 08:29:59.974949: step: 1008/530, loss: 8.87093734741211
2023-01-21 08:30:01.103315: step: 1012/530, loss: 1.144291877746582
2023-01-21 08:30:02.220920: step: 1016/530, loss: 0.43664783239364624
2023-01-21 08:30:03.344931: step: 1020/530, loss: 1.815722942352295
2023-01-21 08:30:04.492129: step: 1024/530, loss: 1.0974397659301758
2023-01-21 08:30:05.662067: step: 1028/530, loss: 2.252948522567749
2023-01-21 08:30:06.761975: step: 1032/530, loss: 0.3966113030910492
2023-01-21 08:30:07.873614: step: 1036/530, loss: 2.0770246982574463
2023-01-21 08:30:08.980804: step: 1040/530, loss: 0.345125675201416
2023-01-21 08:30:10.105099: step: 1044/530, loss: 0.523857593536377
2023-01-21 08:30:11.233059: step: 1048/530, loss: 1.4699203968048096
2023-01-21 08:30:12.372872: step: 1052/530, loss: 2.2116103172302246
2023-01-21 08:30:13.495534: step: 1056/530, loss: 2.7866392135620117
2023-01-21 08:30:14.606683: step: 1060/530, loss: 1.5094499588012695
2023-01-21 08:30:15.737435: step: 1064/530, loss: 2.090209722518921
2023-01-21 08:30:16.868150: step: 1068/530, loss: 0.44535475969314575
2023-01-21 08:30:17.990248: step: 1072/530, loss: 3.7799086570739746
2023-01-21 08:30:19.142593: step: 1076/530, loss: 2.126986503601074
2023-01-21 08:30:20.259291: step: 1080/530, loss: 2.398672580718994
2023-01-21 08:30:21.405006: step: 1084/530, loss: 1.9506633281707764
2023-01-21 08:30:22.509867: step: 1088/530, loss: 2.201355457305908
2023-01-21 08:30:23.637695: step: 1092/530, loss: 0.6073480248451233
2023-01-21 08:30:24.745290: step: 1096/530, loss: 1.36834716796875
2023-01-21 08:30:25.908672: step: 1100/530, loss: 2.315734386444092
2023-01-21 08:30:27.080955: step: 1104/530, loss: 0.33206498622894287
2023-01-21 08:30:28.195795: step: 1108/530, loss: 2.451411485671997
2023-01-21 08:30:29.313483: step: 1112/530, loss: 2.069584846496582
2023-01-21 08:30:30.474709: step: 1116/530, loss: 1.9682148694992065
2023-01-21 08:30:31.587498: step: 1120/530, loss: 0.3384386897087097
2023-01-21 08:30:32.743813: step: 1124/530, loss: 1.7715543508529663
2023-01-21 08:30:33.879840: step: 1128/530, loss: 1.2660282850265503
2023-01-21 08:30:34.973343: step: 1132/530, loss: 1.1928772926330566
2023-01-21 08:30:36.065254: step: 1136/530, loss: 1.8105182647705078
2023-01-21 08:30:37.164769: step: 1140/530, loss: 0.5496821403503418
2023-01-21 08:30:38.351467: step: 1144/530, loss: 0.6329587697982788
2023-01-21 08:30:39.453913: step: 1148/530, loss: 1.0937938690185547
2023-01-21 08:30:40.596430: step: 1152/530, loss: 0.43902474641799927
2023-01-21 08:30:41.717713: step: 1156/530, loss: 2.580002546310425
2023-01-21 08:30:42.832346: step: 1160/530, loss: 0.3949740529060364
2023-01-21 08:30:43.961416: step: 1164/530, loss: 2.565321683883667
2023-01-21 08:30:45.059597: step: 1168/530, loss: 0.32813262939453125
2023-01-21 08:30:46.199428: step: 1172/530, loss: 0.47925710678100586
2023-01-21 08:30:47.322242: step: 1176/530, loss: 0.6064233779907227
2023-01-21 08:30:48.465826: step: 1180/530, loss: 1.4329512119293213
2023-01-21 08:30:49.587423: step: 1184/530, loss: 0.5150305032730103
2023-01-21 08:30:50.730592: step: 1188/530, loss: 0.5031442642211914
2023-01-21 08:30:51.858761: step: 1192/530, loss: 2.933885335922241
2023-01-21 08:30:52.971586: step: 1196/530, loss: 2.081019163131714
2023-01-21 08:30:54.089710: step: 1200/530, loss: 1.5043662786483765
2023-01-21 08:30:55.185937: step: 1204/530, loss: 2.3235888481140137
2023-01-21 08:30:56.324865: step: 1208/530, loss: 1.176701545715332
2023-01-21 08:30:57.451993: step: 1212/530, loss: 0.944574236869812
2023-01-21 08:30:58.579909: step: 1216/530, loss: 0.4637095630168915
2023-01-21 08:30:59.760038: step: 1220/530, loss: 0.64052414894104
2023-01-21 08:31:00.881597: step: 1224/530, loss: 0.8622530102729797
2023-01-21 08:31:02.003044: step: 1228/530, loss: 1.340064525604248
2023-01-21 08:31:03.135559: step: 1232/530, loss: 0.9074380397796631
2023-01-21 08:31:04.236988: step: 1236/530, loss: 0.9914621710777283
2023-01-21 08:31:05.351355: step: 1240/530, loss: 1.7066187858581543
2023-01-21 08:31:06.443682: step: 1244/530, loss: 0.4488796293735504
2023-01-21 08:31:07.565422: step: 1248/530, loss: 1.4746979475021362
2023-01-21 08:31:08.691092: step: 1252/530, loss: 1.0657771825790405
2023-01-21 08:31:09.865994: step: 1256/530, loss: 0.5082967281341553
2023-01-21 08:31:11.025201: step: 1260/530, loss: 0.9484478831291199
2023-01-21 08:31:12.140297: step: 1264/530, loss: 0.5143436789512634
2023-01-21 08:31:13.285291: step: 1268/530, loss: 4.903132438659668
2023-01-21 08:31:14.419490: step: 1272/530, loss: 1.4742833375930786
2023-01-21 08:31:15.540858: step: 1276/530, loss: 0.49241095781326294
2023-01-21 08:31:16.653889: step: 1280/530, loss: 1.8619345426559448
2023-01-21 08:31:17.788588: step: 1284/530, loss: 0.46827393770217896
2023-01-21 08:31:18.908117: step: 1288/530, loss: 2.9534099102020264
2023-01-21 08:31:20.016232: step: 1292/530, loss: 8.42802906036377
2023-01-21 08:31:21.117265: step: 1296/530, loss: 1.7902815341949463
2023-01-21 08:31:22.247156: step: 1300/530, loss: 1.2165833711624146
2023-01-21 08:31:23.393385: step: 1304/530, loss: 1.3490514755249023
2023-01-21 08:31:24.485926: step: 1308/530, loss: 1.2527767419815063
2023-01-21 08:31:25.601303: step: 1312/530, loss: 0.5281668305397034
2023-01-21 08:31:26.729543: step: 1316/530, loss: 1.4810662269592285
2023-01-21 08:31:27.848984: step: 1320/530, loss: 0.4196866750717163
2023-01-21 08:31:28.948905: step: 1324/530, loss: 0.3975706696510315
2023-01-21 08:31:30.108682: step: 1328/530, loss: 0.5328815579414368
2023-01-21 08:31:31.215337: step: 1332/530, loss: 2.9793622493743896
2023-01-21 08:31:32.351219: step: 1336/530, loss: 1.081673502922058
2023-01-21 08:31:33.468852: step: 1340/530, loss: 0.2754342555999756
2023-01-21 08:31:34.556482: step: 1344/530, loss: 0.7935055494308472
2023-01-21 08:31:35.681583: step: 1348/530, loss: 0.4227084517478943
2023-01-21 08:31:36.798172: step: 1352/530, loss: 8.243891716003418
2023-01-21 08:31:37.894827: step: 1356/530, loss: 1.0183504819869995
2023-01-21 08:31:38.998017: step: 1360/530, loss: 0.6033120155334473
2023-01-21 08:31:40.118742: step: 1364/530, loss: 2.24267578125
2023-01-21 08:31:41.263496: step: 1368/530, loss: 0.4645126461982727
2023-01-21 08:31:42.389834: step: 1372/530, loss: 0.8822733163833618
2023-01-21 08:31:43.480384: step: 1376/530, loss: 1.4328054189682007
2023-01-21 08:31:44.581238: step: 1380/530, loss: 1.7444825172424316
2023-01-21 08:31:45.685524: step: 1384/530, loss: 0.9913070201873779
2023-01-21 08:31:46.827675: step: 1388/530, loss: 0.8182525634765625
2023-01-21 08:31:47.969677: step: 1392/530, loss: 1.2500710487365723
2023-01-21 08:31:49.096524: step: 1396/530, loss: 0.6330999732017517
2023-01-21 08:31:50.203344: step: 1400/530, loss: 0.25191688537597656
2023-01-21 08:31:51.336153: step: 1404/530, loss: 3.7340052127838135
2023-01-21 08:31:52.489705: step: 1408/530, loss: 1.532026767730713
2023-01-21 08:31:53.615267: step: 1412/530, loss: 1.451857566833496
2023-01-21 08:31:54.709674: step: 1416/530, loss: 1.818490982055664
2023-01-21 08:31:55.860281: step: 1420/530, loss: 0.36859849095344543
2023-01-21 08:31:56.978668: step: 1424/530, loss: 0.3752859830856323
2023-01-21 08:31:58.094643: step: 1428/530, loss: 0.6991058588027954
2023-01-21 08:31:59.238452: step: 1432/530, loss: 0.27190127968788147
2023-01-21 08:32:00.375217: step: 1436/530, loss: 0.6830970048904419
2023-01-21 08:32:01.490665: step: 1440/530, loss: 0.22408531606197357
2023-01-21 08:32:02.656130: step: 1444/530, loss: 2.056386709213257
2023-01-21 08:32:03.770868: step: 1448/530, loss: 0.5733118057250977
2023-01-21 08:32:04.918447: step: 1452/530, loss: 0.3968283534049988
2023-01-21 08:32:06.038131: step: 1456/530, loss: 1.7949159145355225
2023-01-21 08:32:07.139491: step: 1460/530, loss: 0.3667941987514496
2023-01-21 08:32:08.239011: step: 1464/530, loss: 0.46869271993637085
2023-01-21 08:32:09.354267: step: 1468/530, loss: 1.4501781463623047
2023-01-21 08:32:10.455615: step: 1472/530, loss: 2.5580124855041504
2023-01-21 08:32:11.583988: step: 1476/530, loss: 2.118748903274536
2023-01-21 08:32:12.684225: step: 1480/530, loss: 1.0308361053466797
2023-01-21 08:32:13.780560: step: 1484/530, loss: 0.5159183740615845
2023-01-21 08:32:14.895655: step: 1488/530, loss: 1.057452917098999
2023-01-21 08:32:15.993058: step: 1492/530, loss: 1.4485530853271484
2023-01-21 08:32:17.128639: step: 1496/530, loss: 3.538574457168579
2023-01-21 08:32:18.255087: step: 1500/530, loss: 0.667655348777771
2023-01-21 08:32:19.336189: step: 1504/530, loss: 0.2334914207458496
2023-01-21 08:32:20.450227: step: 1508/530, loss: 0.23393484950065613
2023-01-21 08:32:21.599694: step: 1512/530, loss: 0.31054389476776123
2023-01-21 08:32:22.726644: step: 1516/530, loss: 0.23938751220703125
2023-01-21 08:32:23.874797: step: 1520/530, loss: 1.1196620464324951
2023-01-21 08:32:24.973643: step: 1524/530, loss: 0.8583744168281555
2023-01-21 08:32:26.099227: step: 1528/530, loss: 1.2071545124053955
2023-01-21 08:32:27.238203: step: 1532/530, loss: 1.1557931900024414
2023-01-21 08:32:28.359828: step: 1536/530, loss: 1.8818198442459106
2023-01-21 08:32:29.473126: step: 1540/530, loss: 0.255204975605011
2023-01-21 08:32:30.605932: step: 1544/530, loss: 2.2218806743621826
2023-01-21 08:32:31.714004: step: 1548/530, loss: 0.23186376690864563
2023-01-21 08:32:32.836659: step: 1552/530, loss: 0.2523016929626465
2023-01-21 08:32:33.952752: step: 1556/530, loss: 1.8257893323898315
2023-01-21 08:32:35.074937: step: 1560/530, loss: 0.3640386462211609
2023-01-21 08:32:36.211753: step: 1564/530, loss: 0.3130548298358917
2023-01-21 08:32:37.334942: step: 1568/530, loss: 0.3681375980377197
2023-01-21 08:32:38.437305: step: 1572/530, loss: 0.4442242383956909
2023-01-21 08:32:39.556202: step: 1576/530, loss: 0.25453662872314453
2023-01-21 08:32:40.672746: step: 1580/530, loss: 3.7313971519470215
2023-01-21 08:32:41.790509: step: 1584/530, loss: 0.3674551248550415
2023-01-21 08:32:42.913502: step: 1588/530, loss: 1.8774027824401855
2023-01-21 08:32:44.036956: step: 1592/530, loss: 0.42305582761764526
2023-01-21 08:32:45.172152: step: 1596/530, loss: 2.530494213104248
2023-01-21 08:32:46.330956: step: 1600/530, loss: 0.4066914916038513
2023-01-21 08:32:47.489403: step: 1604/530, loss: 1.1537199020385742
2023-01-21 08:32:48.601831: step: 1608/530, loss: 1.0986946821212769
2023-01-21 08:32:49.724268: step: 1612/530, loss: 1.5892796516418457
2023-01-21 08:32:50.841061: step: 1616/530, loss: 0.6171531677246094
2023-01-21 08:32:51.958964: step: 1620/530, loss: 1.014963150024414
2023-01-21 08:32:53.063566: step: 1624/530, loss: 0.37272512912750244
2023-01-21 08:32:54.199276: step: 1628/530, loss: 0.7471286058425903
2023-01-21 08:32:55.315004: step: 1632/530, loss: 0.21901212632656097
2023-01-21 08:32:56.397553: step: 1636/530, loss: 1.7878408432006836
2023-01-21 08:32:57.517066: step: 1640/530, loss: 0.9727045893669128
2023-01-21 08:32:58.630349: step: 1644/530, loss: 0.7920225262641907
2023-01-21 08:32:59.774690: step: 1648/530, loss: 1.2238308191299438
2023-01-21 08:33:00.884582: step: 1652/530, loss: 0.2008354663848877
2023-01-21 08:33:02.004668: step: 1656/530, loss: 0.6294609308242798
2023-01-21 08:33:03.138666: step: 1660/530, loss: 1.1559182405471802
2023-01-21 08:33:04.274423: step: 1664/530, loss: 0.186271071434021
2023-01-21 08:33:05.383308: step: 1668/530, loss: 1.243440866470337
2023-01-21 08:33:06.518564: step: 1672/530, loss: 0.3269496560096741
2023-01-21 08:33:07.648063: step: 1676/530, loss: 0.1378132402896881
2023-01-21 08:33:08.757543: step: 1680/530, loss: 0.5146986842155457
2023-01-21 08:33:09.831856: step: 1684/530, loss: 0.28378400206565857
2023-01-21 08:33:10.919521: step: 1688/530, loss: 0.15652476251125336
2023-01-21 08:33:12.038653: step: 1692/530, loss: 0.5861271023750305
2023-01-21 08:33:13.155295: step: 1696/530, loss: 1.3331334590911865
2023-01-21 08:33:14.262829: step: 1700/530, loss: 8.364970207214355
2023-01-21 08:33:15.400711: step: 1704/530, loss: 0.8491256237030029
2023-01-21 08:33:16.526095: step: 1708/530, loss: 0.36198320984840393
2023-01-21 08:33:17.629024: step: 1712/530, loss: 0.5336839556694031
2023-01-21 08:33:18.741983: step: 1716/530, loss: 0.5477591156959534
2023-01-21 08:33:19.887932: step: 1720/530, loss: 1.49003267288208
2023-01-21 08:33:20.991653: step: 1724/530, loss: 1.797303557395935
2023-01-21 08:33:22.109039: step: 1728/530, loss: 1.4529967308044434
2023-01-21 08:33:23.234523: step: 1732/530, loss: 1.5711355209350586
2023-01-21 08:33:24.346365: step: 1736/530, loss: 0.17998333275318146
2023-01-21 08:33:25.467093: step: 1740/530, loss: 3.067667007446289
2023-01-21 08:33:26.568945: step: 1744/530, loss: 0.27986735105514526
2023-01-21 08:33:27.691759: step: 1748/530, loss: 0.4771209955215454
2023-01-21 08:33:28.800076: step: 1752/530, loss: 0.4389764070510864
2023-01-21 08:33:29.896494: step: 1756/530, loss: 1.14346444606781
2023-01-21 08:33:31.019788: step: 1760/530, loss: 0.43427371978759766
2023-01-21 08:33:32.161828: step: 1764/530, loss: 2.199627161026001
2023-01-21 08:33:33.248049: step: 1768/530, loss: 3.8894827365875244
2023-01-21 08:33:34.391650: step: 1772/530, loss: 0.24031981825828552
2023-01-21 08:33:35.484230: step: 1776/530, loss: 0.8863033056259155
2023-01-21 08:33:36.597222: step: 1780/530, loss: 0.6817730069160461
2023-01-21 08:33:37.719948: step: 1784/530, loss: 2.9836671352386475
2023-01-21 08:33:38.816009: step: 1788/530, loss: 0.2790653705596924
2023-01-21 08:33:39.952870: step: 1792/530, loss: 0.39870119094848633
2023-01-21 08:33:41.093354: step: 1796/530, loss: 1.2312772274017334
2023-01-21 08:33:42.196751: step: 1800/530, loss: 0.4943826198577881
2023-01-21 08:33:43.286607: step: 1804/530, loss: 0.14156588912010193
2023-01-21 08:33:44.417800: step: 1808/530, loss: 1.042165756225586
2023-01-21 08:33:45.524877: step: 1812/530, loss: 0.2378344088792801
2023-01-21 08:33:46.645452: step: 1816/530, loss: 1.5827640295028687
2023-01-21 08:33:47.765409: step: 1820/530, loss: 0.9896622896194458
2023-01-21 08:33:48.893055: step: 1824/530, loss: 0.5366732478141785
2023-01-21 08:33:49.979351: step: 1828/530, loss: 0.29550257325172424
2023-01-21 08:33:51.086432: step: 1832/530, loss: 0.6661741137504578
2023-01-21 08:33:52.218896: step: 1836/530, loss: 1.6965742111206055
2023-01-21 08:33:53.320787: step: 1840/530, loss: 2.8654441833496094
2023-01-21 08:33:54.441425: step: 1844/530, loss: 0.9360326528549194
2023-01-21 08:33:55.565684: step: 1848/530, loss: 0.48728516697883606
2023-01-21 08:33:56.686157: step: 1852/530, loss: 0.7745282649993896
2023-01-21 08:33:57.786552: step: 1856/530, loss: 0.5575208067893982
2023-01-21 08:33:58.895116: step: 1860/530, loss: 1.5983372926712036
2023-01-21 08:33:59.989172: step: 1864/530, loss: 1.5419771671295166
2023-01-21 08:34:01.105494: step: 1868/530, loss: 0.3139318525791168
2023-01-21 08:34:02.210106: step: 1872/530, loss: 1.8479645252227783
2023-01-21 08:34:03.339757: step: 1876/530, loss: 1.23250412940979
2023-01-21 08:34:04.470234: step: 1880/530, loss: 0.8113978505134583
2023-01-21 08:34:05.587306: step: 1884/530, loss: 0.8430125117301941
2023-01-21 08:34:06.721080: step: 1888/530, loss: 0.31167298555374146
2023-01-21 08:34:07.837920: step: 1892/530, loss: 0.47321024537086487
2023-01-21 08:34:08.969975: step: 1896/530, loss: 0.2288370132446289
2023-01-21 08:34:10.107153: step: 1900/530, loss: 0.3992019593715668
2023-01-21 08:34:11.237956: step: 1904/530, loss: 2.973729372024536
2023-01-21 08:34:12.349105: step: 1908/530, loss: 0.29276227951049805
2023-01-21 08:34:13.486037: step: 1912/530, loss: 0.3745533227920532
2023-01-21 08:34:14.596311: step: 1916/530, loss: 0.6668537259101868
2023-01-21 08:34:15.692864: step: 1920/530, loss: 1.711925983428955
2023-01-21 08:34:16.820175: step: 1924/530, loss: 3.0173497200012207
2023-01-21 08:34:17.943948: step: 1928/530, loss: 2.8242077827453613
2023-01-21 08:34:19.066351: step: 1932/530, loss: 0.4657968580722809
2023-01-21 08:34:20.190218: step: 1936/530, loss: 2.0983266830444336
2023-01-21 08:34:21.364757: step: 1940/530, loss: 0.4327394366264343
2023-01-21 08:34:22.457005: step: 1944/530, loss: 0.8828244209289551
2023-01-21 08:34:23.557742: step: 1948/530, loss: 0.3461621403694153
2023-01-21 08:34:24.699128: step: 1952/530, loss: 0.9902653694152832
2023-01-21 08:34:25.849062: step: 1956/530, loss: 0.6558536887168884
2023-01-21 08:34:26.982368: step: 1960/530, loss: 0.2337017059326172
2023-01-21 08:34:28.137349: step: 1964/530, loss: 0.8781980276107788
2023-01-21 08:34:29.260986: step: 1968/530, loss: 2.319739580154419
2023-01-21 08:34:30.358457: step: 1972/530, loss: 0.8620238900184631
2023-01-21 08:34:31.491058: step: 1976/530, loss: 0.28784117102622986
2023-01-21 08:34:32.623633: step: 1980/530, loss: 2.2409591674804688
2023-01-21 08:34:33.714409: step: 1984/530, loss: 0.3111709654331207
2023-01-21 08:34:34.851177: step: 1988/530, loss: 1.2188161611557007
2023-01-21 08:34:36.005186: step: 1992/530, loss: 1.1012210845947266
2023-01-21 08:34:37.095956: step: 1996/530, loss: 1.094132423400879
2023-01-21 08:34:38.208850: step: 2000/530, loss: 0.4319194555282593
2023-01-21 08:34:39.312459: step: 2004/530, loss: 1.8047986030578613
2023-01-21 08:34:40.461018: step: 2008/530, loss: 0.2863107919692993
2023-01-21 08:34:41.576920: step: 2012/530, loss: 0.5039840936660767
2023-01-21 08:34:42.708001: step: 2016/530, loss: 0.37399351596832275
2023-01-21 08:34:43.823579: step: 2020/530, loss: 0.7118241786956787
2023-01-21 08:34:44.944158: step: 2024/530, loss: 0.4375157356262207
2023-01-21 08:34:46.040632: step: 2028/530, loss: 0.0410003662109375
2023-01-21 08:34:47.190766: step: 2032/530, loss: 2.3981244564056396
2023-01-21 08:34:48.308319: step: 2036/530, loss: 0.5573617815971375
2023-01-21 08:34:49.436608: step: 2040/530, loss: 0.2811049520969391
2023-01-21 08:34:50.567976: step: 2044/530, loss: 0.4849625527858734
2023-01-21 08:34:51.668803: step: 2048/530, loss: 0.9386671781539917
2023-01-21 08:34:52.792550: step: 2052/530, loss: 0.6929950714111328
2023-01-21 08:34:53.918290: step: 2056/530, loss: 0.18222494423389435
2023-01-21 08:34:55.033448: step: 2060/530, loss: 0.5865623950958252
2023-01-21 08:34:56.170472: step: 2064/530, loss: 1.2626607418060303
2023-01-21 08:34:57.283793: step: 2068/530, loss: 0.10001854598522186
2023-01-21 08:34:58.425875: step: 2072/530, loss: 0.15827837586402893
2023-01-21 08:34:59.578016: step: 2076/530, loss: 0.6684004664421082
2023-01-21 08:35:00.717738: step: 2080/530, loss: 0.6001387238502502
2023-01-21 08:35:01.868232: step: 2084/530, loss: 0.3209933340549469
2023-01-21 08:35:02.986743: step: 2088/530, loss: 0.7773169279098511
2023-01-21 08:35:04.110436: step: 2092/530, loss: 0.2292274534702301
2023-01-21 08:35:05.227571: step: 2096/530, loss: 0.19434042274951935
2023-01-21 08:35:06.362694: step: 2100/530, loss: 1.7122278213500977
2023-01-21 08:35:07.487803: step: 2104/530, loss: 2.20381498336792
2023-01-21 08:35:08.589766: step: 2108/530, loss: 0.38788869976997375
2023-01-21 08:35:09.731123: step: 2112/530, loss: 0.4826367497444153
2023-01-21 08:35:10.878885: step: 2116/530, loss: 1.1367560625076294
2023-01-21 08:35:12.013967: step: 2120/530, loss: 0.21407929062843323
==================================================
Loss: 3.221
--------------------
Dev: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.55, 'r': 0.4074074074074074, 'f1': 0.46808510638297873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.9444444444444444, 'r': 0.2698412698412698, 'f1': 0.41975308641975306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.5625, 'r': 0.25, 'f1': 0.34615384615384615}, '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': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.55, 'r': 0.4074074074074074, 'f1': 0.46808510638297873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.9444444444444444, 'r': 0.2698412698412698, 'f1': 0.41975308641975306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.5625, 'r': 0.25, 'f1': 0.34615384615384615}, '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
2023-01-21 08:36:09.381834: step: 4/530, loss: 0.3566058278083801
2023-01-21 08:36:10.497779: step: 8/530, loss: 0.4130827784538269
2023-01-21 08:36:11.598739: step: 12/530, loss: 0.3445383608341217
2023-01-21 08:36:12.711142: step: 16/530, loss: 1.0949736833572388
2023-01-21 08:36:13.868762: step: 20/530, loss: 0.4339710474014282
2023-01-21 08:36:15.017847: step: 24/530, loss: 0.42941704392433167
2023-01-21 08:36:16.170243: step: 28/530, loss: 0.13230538368225098
2023-01-21 08:36:17.310598: step: 32/530, loss: 0.5876734256744385
2023-01-21 08:36:18.426993: step: 36/530, loss: 1.8525090217590332
2023-01-21 08:36:19.545751: step: 40/530, loss: 1.193851113319397
2023-01-21 08:36:20.650237: step: 44/530, loss: 0.409809410572052
2023-01-21 08:36:21.795340: step: 48/530, loss: 1.872848629951477
2023-01-21 08:36:22.900095: step: 52/530, loss: 1.0504995584487915
2023-01-21 08:36:24.041287: step: 56/530, loss: 1.1709342002868652
2023-01-21 08:36:25.196268: step: 60/530, loss: 0.2039329558610916
2023-01-21 08:36:26.327021: step: 64/530, loss: 0.4649409353733063
2023-01-21 08:36:27.485293: step: 68/530, loss: 0.29313212633132935
2023-01-21 08:36:28.599503: step: 72/530, loss: 2.413440704345703
2023-01-21 08:36:29.738930: step: 76/530, loss: 0.2135639190673828
2023-01-21 08:36:30.844152: step: 80/530, loss: 1.319648265838623
2023-01-21 08:36:31.989111: step: 84/530, loss: 0.764073371887207
2023-01-21 08:36:33.127002: step: 88/530, loss: 0.8711465001106262
2023-01-21 08:36:34.230762: step: 92/530, loss: 0.2745100259780884
2023-01-21 08:36:35.346703: step: 96/530, loss: 0.3904329836368561
2023-01-21 08:36:36.459435: step: 100/530, loss: 0.20956841111183167
2023-01-21 08:36:37.596207: step: 104/530, loss: 0.5658622980117798
2023-01-21 08:36:38.715684: step: 108/530, loss: 0.30235034227371216
2023-01-21 08:36:39.842448: step: 112/530, loss: 0.3002249598503113
2023-01-21 08:36:40.960455: step: 116/530, loss: 0.6919804811477661
2023-01-21 08:36:42.069425: step: 120/530, loss: 0.6587099432945251
2023-01-21 08:36:43.203659: step: 124/530, loss: 0.3840743601322174
2023-01-21 08:36:44.342629: step: 128/530, loss: 0.5738978385925293
2023-01-21 08:36:45.463568: step: 132/530, loss: 0.7326037287712097
2023-01-21 08:36:46.594468: step: 136/530, loss: 3.655930280685425
2023-01-21 08:36:47.734555: step: 140/530, loss: 0.5548944473266602
2023-01-21 08:36:48.850139: step: 144/530, loss: 0.7589792609214783
2023-01-21 08:36:49.984311: step: 148/530, loss: 0.5321389436721802
2023-01-21 08:36:51.081900: step: 152/530, loss: 1.2859963178634644
2023-01-21 08:36:52.195305: step: 156/530, loss: 1.2933050394058228
2023-01-21 08:36:53.319589: step: 160/530, loss: 0.23951034247875214
2023-01-21 08:36:54.431154: step: 164/530, loss: 7.642308712005615
2023-01-21 08:36:55.535108: step: 168/530, loss: 0.3990862965583801
2023-01-21 08:36:56.656996: step: 172/530, loss: 10.411173820495605
2023-01-21 08:36:57.793466: step: 176/530, loss: 0.4032111167907715
2023-01-21 08:36:58.931139: step: 180/530, loss: 2.958904266357422
2023-01-21 08:37:00.073948: step: 184/530, loss: 0.7786664962768555
2023-01-21 08:37:01.191702: step: 188/530, loss: 1.576459288597107
2023-01-21 08:37:02.325991: step: 192/530, loss: 3.7912445068359375
2023-01-21 08:37:03.422556: step: 196/530, loss: 1.166519045829773
2023-01-21 08:37:04.530209: step: 200/530, loss: 0.9358481168746948
2023-01-21 08:37:05.663991: step: 204/530, loss: 0.36315298080444336
2023-01-21 08:37:06.781382: step: 208/530, loss: 0.2807299494743347
2023-01-21 08:37:07.876354: step: 212/530, loss: 0.5661808252334595
2023-01-21 08:37:08.982973: step: 216/530, loss: 1.0351403951644897
2023-01-21 08:37:10.112317: step: 220/530, loss: 0.40887367725372314
2023-01-21 08:37:11.245882: step: 224/530, loss: 0.671779990196228
2023-01-21 08:37:12.347341: step: 228/530, loss: 0.10804577171802521
2023-01-21 08:37:13.461082: step: 232/530, loss: 0.350119024515152
2023-01-21 08:37:14.613657: step: 236/530, loss: 0.3751036822795868
2023-01-21 08:37:15.758036: step: 240/530, loss: 7.320432186126709
2023-01-21 08:37:16.885725: step: 244/530, loss: 0.41650259494781494
2023-01-21 08:37:17.992489: step: 248/530, loss: 0.4484068751335144
2023-01-21 08:37:19.121753: step: 252/530, loss: 0.6989626884460449
2023-01-21 08:37:20.233761: step: 256/530, loss: 0.5099005103111267
2023-01-21 08:37:21.363125: step: 260/530, loss: 0.90438312292099
2023-01-21 08:37:22.502016: step: 264/530, loss: 0.9393069744110107
2023-01-21 08:37:23.612416: step: 268/530, loss: 0.49958059191703796
2023-01-21 08:37:24.736084: step: 272/530, loss: 1.126135230064392
2023-01-21 08:37:25.849597: step: 276/530, loss: 0.4600154161453247
2023-01-21 08:37:26.962178: step: 280/530, loss: 0.7101521492004395
2023-01-21 08:37:28.086223: step: 284/530, loss: 3.1613001823425293
2023-01-21 08:37:29.226768: step: 288/530, loss: 0.2667194902896881
2023-01-21 08:37:30.362664: step: 292/530, loss: 0.669231653213501
2023-01-21 08:37:31.441896: step: 296/530, loss: 1.1442652940750122
2023-01-21 08:37:32.610313: step: 300/530, loss: 0.16563892364501953
2023-01-21 08:37:33.717162: step: 304/530, loss: 0.6221114993095398
2023-01-21 08:37:34.829970: step: 308/530, loss: 1.3496848344802856
2023-01-21 08:37:35.945996: step: 312/530, loss: 0.448622465133667
2023-01-21 08:37:37.078363: step: 316/530, loss: 2.4301681518554688
2023-01-21 08:37:38.181170: step: 320/530, loss: 2.4049713611602783
2023-01-21 08:37:39.287785: step: 324/530, loss: 0.6371944546699524
2023-01-21 08:37:40.400135: step: 328/530, loss: 1.4824625253677368
2023-01-21 08:37:41.531143: step: 332/530, loss: 0.36765578389167786
2023-01-21 08:37:42.669239: step: 336/530, loss: 3.296193838119507
2023-01-21 08:37:43.812912: step: 340/530, loss: 0.6682201623916626
2023-01-21 08:37:44.939791: step: 344/530, loss: 0.8573024868965149
2023-01-21 08:37:46.063930: step: 348/530, loss: 0.14986252784729004
2023-01-21 08:37:47.166854: step: 352/530, loss: 1.0312409400939941
2023-01-21 08:37:48.289892: step: 356/530, loss: 0.5645427703857422
2023-01-21 08:37:49.396545: step: 360/530, loss: 0.588174045085907
2023-01-21 08:37:50.527325: step: 364/530, loss: 0.23256036639213562
2023-01-21 08:37:51.638935: step: 368/530, loss: 0.5504868030548096
2023-01-21 08:37:52.737559: step: 372/530, loss: 0.16431033611297607
2023-01-21 08:37:53.884159: step: 376/530, loss: 0.3678847849369049
2023-01-21 08:37:55.004085: step: 380/530, loss: 0.7806366682052612
2023-01-21 08:37:56.101476: step: 384/530, loss: 0.11238108575344086
2023-01-21 08:37:57.224277: step: 388/530, loss: 1.022740364074707
2023-01-21 08:37:58.345247: step: 392/530, loss: 0.21687498688697815
2023-01-21 08:37:59.453596: step: 396/530, loss: 0.23517140746116638
2023-01-21 08:38:00.574763: step: 400/530, loss: 1.8847451210021973
2023-01-21 08:38:01.673387: step: 404/530, loss: 0.7515870332717896
2023-01-21 08:38:02.843620: step: 408/530, loss: 0.922863245010376
2023-01-21 08:38:03.961804: step: 412/530, loss: 0.2927433252334595
2023-01-21 08:38:05.086331: step: 416/530, loss: 1.2556331157684326
2023-01-21 08:38:06.204131: step: 420/530, loss: 1.6767101287841797
2023-01-21 08:38:07.304285: step: 424/530, loss: 0.2748070955276489
2023-01-21 08:38:08.402626: step: 428/530, loss: 0.15707266330718994
2023-01-21 08:38:09.549718: step: 432/530, loss: 1.6101641654968262
2023-01-21 08:38:10.640369: step: 436/530, loss: 1.7438379526138306
2023-01-21 08:38:11.755067: step: 440/530, loss: 0.57662034034729
2023-01-21 08:38:12.902856: step: 444/530, loss: 0.5762401819229126
2023-01-21 08:38:14.030129: step: 448/530, loss: 0.1595286875963211
2023-01-21 08:38:15.157144: step: 452/530, loss: 0.30400657653808594
2023-01-21 08:38:16.287880: step: 456/530, loss: 1.4402575492858887
2023-01-21 08:38:17.384522: step: 460/530, loss: 0.2760410010814667
2023-01-21 08:38:18.501922: step: 464/530, loss: 0.7937334179878235
2023-01-21 08:38:19.609825: step: 468/530, loss: 1.8473342657089233
2023-01-21 08:38:20.753182: step: 472/530, loss: 1.0623207092285156
2023-01-21 08:38:21.910057: step: 476/530, loss: 0.625682532787323
2023-01-21 08:38:23.030074: step: 480/530, loss: 0.9409477710723877
2023-01-21 08:38:24.133968: step: 484/530, loss: 0.8266118764877319
2023-01-21 08:38:25.235403: step: 488/530, loss: 0.19022828340530396
2023-01-21 08:38:26.309377: step: 492/530, loss: 1.2855019569396973
2023-01-21 08:38:27.423793: step: 496/530, loss: 0.14154188334941864
2023-01-21 08:38:28.540281: step: 500/530, loss: 0.314447820186615
2023-01-21 08:38:29.687960: step: 504/530, loss: 0.9460071921348572
2023-01-21 08:38:30.807493: step: 508/530, loss: 0.6269891858100891
2023-01-21 08:38:31.945284: step: 512/530, loss: 1.5256773233413696
2023-01-21 08:38:33.105784: step: 516/530, loss: 0.515169084072113
2023-01-21 08:38:34.216743: step: 520/530, loss: 1.4351682662963867
2023-01-21 08:38:35.333842: step: 524/530, loss: 0.6430720090866089
2023-01-21 08:38:36.441053: step: 528/530, loss: 0.9238367080688477
2023-01-21 08:38:37.548810: step: 532/530, loss: 0.38574808835983276
2023-01-21 08:38:38.665731: step: 536/530, loss: 0.3678542971611023
2023-01-21 08:38:39.812345: step: 540/530, loss: 0.2950584888458252
2023-01-21 08:38:40.964466: step: 544/530, loss: 0.9912084341049194
2023-01-21 08:38:42.078106: step: 548/530, loss: 0.49688720703125
2023-01-21 08:38:43.193014: step: 552/530, loss: 0.21537886559963226
2023-01-21 08:38:44.332112: step: 556/530, loss: 0.28884661197662354
2023-01-21 08:38:45.461062: step: 560/530, loss: 0.9238185286521912
2023-01-21 08:38:46.585616: step: 564/530, loss: 0.3266097903251648
2023-01-21 08:38:47.725841: step: 568/530, loss: 0.9632443189620972
2023-01-21 08:38:48.846075: step: 572/530, loss: 0.3264654874801636
2023-01-21 08:38:49.972745: step: 576/530, loss: 1.3379392623901367
2023-01-21 08:38:51.103585: step: 580/530, loss: 0.9528099298477173
2023-01-21 08:38:52.203528: step: 584/530, loss: 0.7141236066818237
2023-01-21 08:38:53.325308: step: 588/530, loss: 0.506945013999939
2023-01-21 08:38:54.423462: step: 592/530, loss: 1.045934796333313
2023-01-21 08:38:55.539395: step: 596/530, loss: 0.34235143661499023
2023-01-21 08:38:56.653481: step: 600/530, loss: 1.2318871021270752
2023-01-21 08:38:57.762226: step: 604/530, loss: 0.4056874215602875
2023-01-21 08:38:58.893171: step: 608/530, loss: 0.413580060005188
2023-01-21 08:39:00.022345: step: 612/530, loss: 0.2892702519893646
2023-01-21 08:39:01.139044: step: 616/530, loss: 6.976891994476318
2023-01-21 08:39:02.262029: step: 620/530, loss: 0.27013903856277466
2023-01-21 08:39:03.398502: step: 624/530, loss: 0.21309155225753784
2023-01-21 08:39:04.529113: step: 628/530, loss: 1.6618425846099854
2023-01-21 08:39:05.642989: step: 632/530, loss: 0.07346592098474503
2023-01-21 08:39:06.774538: step: 636/530, loss: 1.146353006362915
2023-01-21 08:39:07.926815: step: 640/530, loss: 0.20191031694412231
2023-01-21 08:39:09.052032: step: 644/530, loss: 1.1306957006454468
2023-01-21 08:39:10.172229: step: 648/530, loss: 0.23944978415966034
2023-01-21 08:39:11.286627: step: 652/530, loss: 0.7822617888450623
2023-01-21 08:39:12.410738: step: 656/530, loss: 0.7542898654937744
2023-01-21 08:39:13.533017: step: 660/530, loss: 0.17951121926307678
2023-01-21 08:39:14.687918: step: 664/530, loss: 0.44017887115478516
2023-01-21 08:39:15.818521: step: 668/530, loss: 0.6335656642913818
2023-01-21 08:39:16.914693: step: 672/530, loss: 0.22563424706459045
2023-01-21 08:39:18.033549: step: 676/530, loss: 0.09069471806287766
2023-01-21 08:39:19.143945: step: 680/530, loss: 0.3064506947994232
2023-01-21 08:39:20.280529: step: 684/530, loss: 1.5548375844955444
2023-01-21 08:39:21.432495: step: 688/530, loss: 0.16918258368968964
2023-01-21 08:39:22.551265: step: 692/530, loss: 0.2627032995223999
2023-01-21 08:39:23.683735: step: 696/530, loss: 0.2972683906555176
2023-01-21 08:39:24.826189: step: 700/530, loss: 0.8079271912574768
2023-01-21 08:39:25.925073: step: 704/530, loss: 0.21016903221607208
2023-01-21 08:39:27.040539: step: 708/530, loss: 0.5566600561141968
2023-01-21 08:39:28.165005: step: 712/530, loss: 2.9727137088775635
2023-01-21 08:39:29.284456: step: 716/530, loss: 0.8868815898895264
2023-01-21 08:39:30.393926: step: 720/530, loss: 0.6727351546287537
2023-01-21 08:39:31.520671: step: 724/530, loss: 0.41052961349487305
2023-01-21 08:39:32.613407: step: 728/530, loss: 0.15838566422462463
2023-01-21 08:39:33.758309: step: 732/530, loss: 1.1593433618545532
2023-01-21 08:39:34.867059: step: 736/530, loss: 1.0618622303009033
2023-01-21 08:39:36.003405: step: 740/530, loss: 2.73171329498291
2023-01-21 08:39:37.144526: step: 744/530, loss: 0.6454010009765625
2023-01-21 08:39:38.275808: step: 748/530, loss: 0.18166008591651917
2023-01-21 08:39:39.387893: step: 752/530, loss: 0.12550459802150726
2023-01-21 08:39:40.533495: step: 756/530, loss: 0.36531150341033936
2023-01-21 08:39:41.665377: step: 760/530, loss: 0.14516229927539825
2023-01-21 08:39:42.796652: step: 764/530, loss: 0.8672568202018738
2023-01-21 08:39:43.916248: step: 768/530, loss: 0.24750952422618866
2023-01-21 08:39:45.040598: step: 772/530, loss: 0.6645693778991699
2023-01-21 08:39:46.157198: step: 776/530, loss: 0.8205047249794006
2023-01-21 08:39:47.284005: step: 780/530, loss: 0.36898624897003174
2023-01-21 08:39:48.389108: step: 784/530, loss: 0.25122299790382385
2023-01-21 08:39:49.528947: step: 788/530, loss: 1.738002061843872
2023-01-21 08:39:50.658744: step: 792/530, loss: 0.47999632358551025
2023-01-21 08:39:51.805348: step: 796/530, loss: 0.3370702266693115
2023-01-21 08:39:52.938871: step: 800/530, loss: 0.26940375566482544
2023-01-21 08:39:54.057623: step: 804/530, loss: 0.5166050791740417
2023-01-21 08:39:55.179638: step: 808/530, loss: 0.2013622224330902
2023-01-21 08:39:56.313957: step: 812/530, loss: 1.0816948413848877
2023-01-21 08:39:57.422098: step: 816/530, loss: 0.7672421932220459
2023-01-21 08:39:58.556155: step: 820/530, loss: 0.4618135392665863
2023-01-21 08:39:59.663485: step: 824/530, loss: 2.2708003520965576
2023-01-21 08:40:00.775116: step: 828/530, loss: 1.307183027267456
2023-01-21 08:40:01.878480: step: 832/530, loss: 6.292883396148682
2023-01-21 08:40:02.996957: step: 836/530, loss: 0.23577895760536194
2023-01-21 08:40:04.143186: step: 840/530, loss: 1.5875312089920044
2023-01-21 08:40:05.303560: step: 844/530, loss: 0.20029973983764648
2023-01-21 08:40:06.417699: step: 848/530, loss: 0.14980784058570862
2023-01-21 08:40:07.534839: step: 852/530, loss: 0.9651031494140625
2023-01-21 08:40:08.716474: step: 856/530, loss: 0.24396952986717224
2023-01-21 08:40:09.833328: step: 860/530, loss: 1.1361064910888672
2023-01-21 08:40:10.974924: step: 864/530, loss: 0.1594073325395584
2023-01-21 08:40:12.080708: step: 868/530, loss: 0.048084452748298645
2023-01-21 08:40:13.220357: step: 872/530, loss: 0.3147246539592743
2023-01-21 08:40:14.336408: step: 876/530, loss: 0.7524187564849854
2023-01-21 08:40:15.465904: step: 880/530, loss: 0.5513640642166138
2023-01-21 08:40:16.611572: step: 884/530, loss: 2.0146548748016357
2023-01-21 08:40:17.728176: step: 888/530, loss: 0.17148466408252716
2023-01-21 08:40:18.864168: step: 892/530, loss: 0.2688533067703247
2023-01-21 08:40:19.964724: step: 896/530, loss: 0.1653767228126526
2023-01-21 08:40:21.099690: step: 900/530, loss: 0.31855255365371704
2023-01-21 08:40:22.222451: step: 904/530, loss: 0.7202506065368652
2023-01-21 08:40:23.362242: step: 908/530, loss: 0.46812745928764343
2023-01-21 08:40:24.509839: step: 912/530, loss: 1.197242259979248
2023-01-21 08:40:25.630894: step: 916/530, loss: 0.20905455946922302
2023-01-21 08:40:26.776520: step: 920/530, loss: 1.059620976448059
2023-01-21 08:40:27.898053: step: 924/530, loss: 0.14065943658351898
2023-01-21 08:40:29.024709: step: 928/530, loss: 0.7345306873321533
2023-01-21 08:40:30.154684: step: 932/530, loss: 0.2738502621650696
2023-01-21 08:40:31.286807: step: 936/530, loss: 0.9302751421928406
2023-01-21 08:40:32.425635: step: 940/530, loss: 1.3788981437683105
2023-01-21 08:40:33.584071: step: 944/530, loss: 0.2821890711784363
2023-01-21 08:40:34.673200: step: 948/530, loss: 0.26237952709198
2023-01-21 08:40:35.787890: step: 952/530, loss: 0.2008712887763977
2023-01-21 08:40:36.954396: step: 956/530, loss: 0.35614025592803955
2023-01-21 08:40:38.093231: step: 960/530, loss: 0.3039717674255371
2023-01-21 08:40:39.218332: step: 964/530, loss: 0.13932275772094727
2023-01-21 08:40:40.347466: step: 968/530, loss: 0.7154656648635864
2023-01-21 08:40:41.496118: step: 972/530, loss: 0.14186687767505646
2023-01-21 08:40:42.608887: step: 976/530, loss: 0.23681649565696716
2023-01-21 08:40:43.741613: step: 980/530, loss: 0.8003570437431335
2023-01-21 08:40:44.837861: step: 984/530, loss: 0.5427683591842651
2023-01-21 08:40:45.976348: step: 988/530, loss: 0.4901230037212372
2023-01-21 08:40:47.091084: step: 992/530, loss: 0.3047858476638794
2023-01-21 08:40:48.184048: step: 996/530, loss: 0.536281406879425
2023-01-21 08:40:49.350680: step: 1000/530, loss: 1.6701381206512451
2023-01-21 08:40:50.454177: step: 1004/530, loss: 0.19230122864246368
2023-01-21 08:40:51.569131: step: 1008/530, loss: 0.22382239997386932
2023-01-21 08:40:52.675470: step: 1012/530, loss: 0.1477527618408203
2023-01-21 08:40:53.768984: step: 1016/530, loss: 0.5205669403076172
2023-01-21 08:40:54.879825: step: 1020/530, loss: 0.19983796775341034
2023-01-21 08:40:56.003029: step: 1024/530, loss: 1.0030394792556763
2023-01-21 08:40:57.135859: step: 1028/530, loss: 1.1196682453155518
2023-01-21 08:40:58.255930: step: 1032/530, loss: 0.47917041182518005
2023-01-21 08:40:59.374858: step: 1036/530, loss: 1.2454583644866943
2023-01-21 08:41:00.497540: step: 1040/530, loss: 1.2044823169708252
2023-01-21 08:41:01.604316: step: 1044/530, loss: 0.7468950748443604
2023-01-21 08:41:02.713075: step: 1048/530, loss: 0.7009557485580444
2023-01-21 08:41:03.844401: step: 1052/530, loss: 0.2177600860595703
2023-01-21 08:41:05.013249: step: 1056/530, loss: 0.47021159529685974
2023-01-21 08:41:06.147283: step: 1060/530, loss: 6.791146755218506
2023-01-21 08:41:07.265168: step: 1064/530, loss: 1.4735078811645508
2023-01-21 08:41:08.407067: step: 1068/530, loss: 1.6379945278167725
2023-01-21 08:41:09.519480: step: 1072/530, loss: 0.7927103638648987
2023-01-21 08:41:10.627106: step: 1076/530, loss: 1.2895610332489014
2023-01-21 08:41:11.772485: step: 1080/530, loss: 0.5735262036323547
2023-01-21 08:41:12.919457: step: 1084/530, loss: 0.44888830184936523
2023-01-21 08:41:14.037936: step: 1088/530, loss: 0.14473238587379456
2023-01-21 08:41:15.174035: step: 1092/530, loss: 0.1704268604516983
2023-01-21 08:41:16.298327: step: 1096/530, loss: 0.2278425395488739
2023-01-21 08:41:17.392894: step: 1100/530, loss: 0.16720008850097656
2023-01-21 08:41:18.539956: step: 1104/530, loss: 1.661759376525879
2023-01-21 08:41:19.649023: step: 1108/530, loss: 1.5906410217285156
2023-01-21 08:41:20.807656: step: 1112/530, loss: 1.7449020147323608
2023-01-21 08:41:21.911732: step: 1116/530, loss: 0.3117155134677887
2023-01-21 08:41:23.069781: step: 1120/530, loss: 0.16042709350585938
2023-01-21 08:41:24.210972: step: 1124/530, loss: 1.4187798500061035
2023-01-21 08:41:25.366705: step: 1128/530, loss: 1.6446759700775146
2023-01-21 08:41:26.476914: step: 1132/530, loss: 0.4482409358024597
2023-01-21 08:41:27.577116: step: 1136/530, loss: 0.2240900695323944
2023-01-21 08:41:28.684990: step: 1140/530, loss: 0.3433306813240051
2023-01-21 08:41:29.806253: step: 1144/530, loss: 6.444187641143799
2023-01-21 08:41:30.914616: step: 1148/530, loss: 0.23748381435871124
2023-01-21 08:41:32.091072: step: 1152/530, loss: 0.2018374353647232
2023-01-21 08:41:33.226953: step: 1156/530, loss: 0.30465179681777954
2023-01-21 08:41:34.346989: step: 1160/530, loss: 0.5044019818305969
2023-01-21 08:41:35.481478: step: 1164/530, loss: 1.08774733543396
2023-01-21 08:41:36.581036: step: 1168/530, loss: 0.6293907761573792
2023-01-21 08:41:37.695010: step: 1172/530, loss: 0.15773901343345642
2023-01-21 08:41:38.825033: step: 1176/530, loss: 0.20408979058265686
2023-01-21 08:41:39.945366: step: 1180/530, loss: 0.6606953144073486
2023-01-21 08:41:41.061917: step: 1184/530, loss: 0.8491404056549072
2023-01-21 08:41:42.205995: step: 1188/530, loss: 0.9160614013671875
2023-01-21 08:41:43.303281: step: 1192/530, loss: 0.3279854357242584
2023-01-21 08:41:44.423412: step: 1196/530, loss: 0.37932348251342773
2023-01-21 08:41:45.560778: step: 1200/530, loss: 0.19620972871780396
2023-01-21 08:41:46.695759: step: 1204/530, loss: 1.3911794424057007
2023-01-21 08:41:47.846441: step: 1208/530, loss: 0.45618483424186707
2023-01-21 08:41:48.969340: step: 1212/530, loss: 0.5725933909416199
2023-01-21 08:41:50.067796: step: 1216/530, loss: 0.2683318555355072
2023-01-21 08:41:51.183024: step: 1220/530, loss: 0.9543277025222778
2023-01-21 08:41:52.301868: step: 1224/530, loss: 0.19767579436302185
2023-01-21 08:41:53.454775: step: 1228/530, loss: 0.31375494599342346
2023-01-21 08:41:54.586536: step: 1232/530, loss: 0.24461689591407776
2023-01-21 08:41:55.678970: step: 1236/530, loss: 0.8889716267585754
2023-01-21 08:41:56.782629: step: 1240/530, loss: 0.293101966381073
2023-01-21 08:41:57.915222: step: 1244/530, loss: 1.2730488777160645
2023-01-21 08:41:59.056937: step: 1248/530, loss: 0.3960801064968109
2023-01-21 08:42:00.198899: step: 1252/530, loss: 0.2290855497121811
2023-01-21 08:42:01.330464: step: 1256/530, loss: 0.20648488402366638
2023-01-21 08:42:02.441629: step: 1260/530, loss: 0.10601487010717392
2023-01-21 08:42:03.553979: step: 1264/530, loss: 0.536906361579895
2023-01-21 08:42:04.693234: step: 1268/530, loss: 0.3468421995639801
2023-01-21 08:42:05.835162: step: 1272/530, loss: 0.24444961547851562
2023-01-21 08:42:06.937102: step: 1276/530, loss: 0.08144369721412659
2023-01-21 08:42:08.037706: step: 1280/530, loss: 0.5225187540054321
2023-01-21 08:42:09.174474: step: 1284/530, loss: 0.411137193441391
2023-01-21 08:42:10.303933: step: 1288/530, loss: 0.7633897066116333
2023-01-21 08:42:11.425305: step: 1292/530, loss: 0.4491537809371948
2023-01-21 08:42:12.540516: step: 1296/530, loss: 0.5478394627571106
2023-01-21 08:42:13.675026: step: 1300/530, loss: 0.5223590135574341
2023-01-21 08:42:14.800625: step: 1304/530, loss: 0.19366580247879028
2023-01-21 08:42:15.957173: step: 1308/530, loss: 1.493715763092041
2023-01-21 08:42:17.107747: step: 1312/530, loss: 0.7926374673843384
2023-01-21 08:42:18.231424: step: 1316/530, loss: 0.2620566487312317
2023-01-21 08:42:19.369247: step: 1320/530, loss: 0.2101770043373108
2023-01-21 08:42:20.540881: step: 1324/530, loss: 0.36574631929397583
2023-01-21 08:42:21.656300: step: 1328/530, loss: 1.2851864099502563
2023-01-21 08:42:22.784098: step: 1332/530, loss: 0.334254652261734
2023-01-21 08:42:23.900936: step: 1336/530, loss: 0.13697519898414612
2023-01-21 08:42:25.034726: step: 1340/530, loss: 0.9536935687065125
2023-01-21 08:42:26.153018: step: 1344/530, loss: 1.5413018465042114
2023-01-21 08:42:27.343056: step: 1348/530, loss: 0.7670227289199829
2023-01-21 08:42:28.471281: step: 1352/530, loss: 0.2627897262573242
2023-01-21 08:42:29.584395: step: 1356/530, loss: 0.34195834398269653
2023-01-21 08:42:30.691910: step: 1360/530, loss: 0.1234525665640831
2023-01-21 08:42:31.843745: step: 1364/530, loss: 0.24544048309326172
2023-01-21 08:42:32.952941: step: 1368/530, loss: 0.7134837508201599
2023-01-21 08:42:34.071454: step: 1372/530, loss: 0.1867872178554535
2023-01-21 08:42:35.222935: step: 1376/530, loss: 0.20178325474262238
2023-01-21 08:42:36.342181: step: 1380/530, loss: 0.7981695532798767
2023-01-21 08:42:37.488418: step: 1384/530, loss: 0.12979841232299805
2023-01-21 08:42:38.682343: step: 1388/530, loss: 0.8277761340141296
2023-01-21 08:42:39.821271: step: 1392/530, loss: 0.08861684799194336
2023-01-21 08:42:40.962736: step: 1396/530, loss: 0.4481843113899231
2023-01-21 08:42:42.193441: step: 1400/530, loss: 6.67739200592041
2023-01-21 08:42:43.320746: step: 1404/530, loss: 0.3434179425239563
2023-01-21 08:42:44.442790: step: 1408/530, loss: 0.3478502035140991
2023-01-21 08:42:45.543896: step: 1412/530, loss: 0.21788367629051208
2023-01-21 08:42:46.677318: step: 1416/530, loss: 0.4262528717517853
2023-01-21 08:42:47.812944: step: 1420/530, loss: 0.17025771737098694
2023-01-21 08:42:48.934999: step: 1424/530, loss: 0.8870526552200317
2023-01-21 08:42:50.086312: step: 1428/530, loss: 0.9154606461524963
2023-01-21 08:42:51.209761: step: 1432/530, loss: 0.12415867298841476
2023-01-21 08:42:52.333116: step: 1436/530, loss: 0.21688851714134216
2023-01-21 08:42:53.463445: step: 1440/530, loss: 0.7055283188819885
2023-01-21 08:42:54.597209: step: 1444/530, loss: 0.25743627548217773
2023-01-21 08:42:55.731665: step: 1448/530, loss: 1.9429590702056885
2023-01-21 08:42:56.862455: step: 1452/530, loss: 0.21187180280685425
2023-01-21 08:42:57.980134: step: 1456/530, loss: 0.5164682269096375
2023-01-21 08:42:59.080352: step: 1460/530, loss: 0.09471134841442108
2023-01-21 08:43:00.190978: step: 1464/530, loss: 2.2872867584228516
2023-01-21 08:43:01.309533: step: 1468/530, loss: 0.5719640851020813
2023-01-21 08:43:02.441235: step: 1472/530, loss: 1.6966402530670166
2023-01-21 08:43:03.551729: step: 1476/530, loss: 1.3545782566070557
2023-01-21 08:43:04.665730: step: 1480/530, loss: 0.636709451675415
2023-01-21 08:43:05.819615: step: 1484/530, loss: 0.7344902157783508
2023-01-21 08:43:06.951131: step: 1488/530, loss: 0.48277369141578674
2023-01-21 08:43:08.081999: step: 1492/530, loss: 0.24266642332077026
2023-01-21 08:43:09.202565: step: 1496/530, loss: 0.3556075096130371
2023-01-21 08:43:10.314602: step: 1500/530, loss: 0.23602394759655
2023-01-21 08:43:11.434403: step: 1504/530, loss: 1.1088502407073975
2023-01-21 08:43:12.556538: step: 1508/530, loss: 1.6270503997802734
2023-01-21 08:43:13.697155: step: 1512/530, loss: 0.0618162639439106
2023-01-21 08:43:14.806753: step: 1516/530, loss: 0.0733531042933464
2023-01-21 08:43:15.940594: step: 1520/530, loss: 1.8814818859100342
2023-01-21 08:43:17.065608: step: 1524/530, loss: 7.419620990753174
2023-01-21 08:43:18.223031: step: 1528/530, loss: 1.6803817749023438
2023-01-21 08:43:19.332326: step: 1532/530, loss: 0.1288263350725174
2023-01-21 08:43:20.472647: step: 1536/530, loss: 0.8849203586578369
2023-01-21 08:43:21.601103: step: 1540/530, loss: 0.36991938948631287
2023-01-21 08:43:22.730128: step: 1544/530, loss: 0.1908399611711502
2023-01-21 08:43:23.849750: step: 1548/530, loss: 0.19451384246349335
2023-01-21 08:43:24.978369: step: 1552/530, loss: 0.5053917765617371
2023-01-21 08:43:26.080889: step: 1556/530, loss: 1.2861690521240234
2023-01-21 08:43:27.226900: step: 1560/530, loss: 0.3923514485359192
2023-01-21 08:43:28.349368: step: 1564/530, loss: 0.6893815994262695
2023-01-21 08:43:29.476228: step: 1568/530, loss: 0.6902713775634766
2023-01-21 08:43:30.616900: step: 1572/530, loss: 0.4286918640136719
2023-01-21 08:43:31.744434: step: 1576/530, loss: 0.07515612244606018
2023-01-21 08:43:32.865679: step: 1580/530, loss: 0.39479684829711914
2023-01-21 08:43:33.987479: step: 1584/530, loss: 0.6350180506706238
2023-01-21 08:43:35.112798: step: 1588/530, loss: 0.2779053747653961
2023-01-21 08:43:36.217975: step: 1592/530, loss: 0.13090582191944122
2023-01-21 08:43:37.342389: step: 1596/530, loss: 0.9883217811584473
2023-01-21 08:43:38.469553: step: 1600/530, loss: 0.09409274905920029
2023-01-21 08:43:39.577693: step: 1604/530, loss: 0.2982763648033142
2023-01-21 08:43:40.675769: step: 1608/530, loss: 0.2672467827796936
2023-01-21 08:43:41.836640: step: 1612/530, loss: 1.5939741134643555
2023-01-21 08:43:42.959699: step: 1616/530, loss: 0.8672860860824585
2023-01-21 08:43:44.060163: step: 1620/530, loss: 0.8958872556686401
2023-01-21 08:43:45.164780: step: 1624/530, loss: 0.0984601080417633
2023-01-21 08:43:46.288615: step: 1628/530, loss: 2.789956569671631
2023-01-21 08:43:47.421881: step: 1632/530, loss: 0.2605394124984741
2023-01-21 08:43:48.534616: step: 1636/530, loss: 0.15066084265708923
2023-01-21 08:43:49.662007: step: 1640/530, loss: 1.1546671390533447
2023-01-21 08:43:50.777202: step: 1644/530, loss: 0.2743123173713684
2023-01-21 08:43:51.907831: step: 1648/530, loss: 0.8997188210487366
2023-01-21 08:43:53.054720: step: 1652/530, loss: 0.24478493630886078
2023-01-21 08:43:54.188935: step: 1656/530, loss: 0.8704109191894531
2023-01-21 08:43:55.303653: step: 1660/530, loss: 1.2081955671310425
2023-01-21 08:43:56.415269: step: 1664/530, loss: 0.16584762930870056
2023-01-21 08:43:57.555705: step: 1668/530, loss: 0.42290323972702026
2023-01-21 08:43:58.680477: step: 1672/530, loss: 1.1843347549438477
2023-01-21 08:43:59.815129: step: 1676/530, loss: 0.18201667070388794
2023-01-21 08:44:00.959297: step: 1680/530, loss: 0.1348247528076172
2023-01-21 08:44:02.110518: step: 1684/530, loss: 0.3566984236240387
2023-01-21 08:44:03.244591: step: 1688/530, loss: 2.0272209644317627
2023-01-21 08:44:04.389429: step: 1692/530, loss: 0.1784757673740387
2023-01-21 08:44:05.497616: step: 1696/530, loss: 1.0046180486679077
2023-01-21 08:44:06.622440: step: 1700/530, loss: 0.30544471740722656
2023-01-21 08:44:07.741301: step: 1704/530, loss: 0.2551521360874176
2023-01-21 08:44:08.866189: step: 1708/530, loss: 1.7154011726379395
2023-01-21 08:44:09.990643: step: 1712/530, loss: 0.2702065706253052
2023-01-21 08:44:11.112580: step: 1716/530, loss: 0.194538414478302
2023-01-21 08:44:12.248105: step: 1720/530, loss: 0.5195850133895874
2023-01-21 08:44:13.384500: step: 1724/530, loss: 0.5444344282150269
2023-01-21 08:44:14.493589: step: 1728/530, loss: 0.45696118474006653
2023-01-21 08:44:15.646266: step: 1732/530, loss: 0.6724588871002197
2023-01-21 08:44:16.778232: step: 1736/530, loss: 0.6436266899108887
2023-01-21 08:44:17.917555: step: 1740/530, loss: 0.06118364259600639
2023-01-21 08:44:19.032761: step: 1744/530, loss: 0.4872073531150818
2023-01-21 08:44:20.165760: step: 1748/530, loss: 0.5396503806114197
2023-01-21 08:44:21.282074: step: 1752/530, loss: 0.13950863480567932
2023-01-21 08:44:22.387896: step: 1756/530, loss: 1.0801059007644653
2023-01-21 08:44:23.521830: step: 1760/530, loss: 1.0713865756988525
2023-01-21 08:44:24.672959: step: 1764/530, loss: 1.0806747674942017
2023-01-21 08:44:25.788206: step: 1768/530, loss: 0.27925539016723633
2023-01-21 08:44:26.902740: step: 1772/530, loss: 0.8207964301109314
2023-01-21 08:44:28.006377: step: 1776/530, loss: 0.07673411071300507
2023-01-21 08:44:29.119533: step: 1780/530, loss: 1.3512283563613892
2023-01-21 08:44:30.239324: step: 1784/530, loss: 1.031259536743164
2023-01-21 08:44:31.370436: step: 1788/530, loss: 0.7698662281036377
2023-01-21 08:44:32.471858: step: 1792/530, loss: 0.2016758918762207
2023-01-21 08:44:33.583525: step: 1796/530, loss: 0.8086709976196289
2023-01-21 08:44:34.710988: step: 1800/530, loss: 0.2249886691570282
2023-01-21 08:44:35.840191: step: 1804/530, loss: 0.7650534510612488
2023-01-21 08:44:36.943899: step: 1808/530, loss: 0.15870437026023865
2023-01-21 08:44:38.060145: step: 1812/530, loss: 0.7360981702804565
2023-01-21 08:44:39.183844: step: 1816/530, loss: 6.378812789916992
2023-01-21 08:44:40.302241: step: 1820/530, loss: 0.358445942401886
2023-01-21 08:44:41.463708: step: 1824/530, loss: 0.812828779220581
2023-01-21 08:44:42.613712: step: 1828/530, loss: 1.0967357158660889
2023-01-21 08:44:43.743708: step: 1832/530, loss: 0.40618619322776794
2023-01-21 08:44:44.879281: step: 1836/530, loss: 2.38862681388855
2023-01-21 08:44:46.020720: step: 1840/530, loss: 2.1479198932647705
2023-01-21 08:44:47.152142: step: 1844/530, loss: 0.85140061378479
2023-01-21 08:44:48.269805: step: 1848/530, loss: 0.7551918625831604
2023-01-21 08:44:49.372424: step: 1852/530, loss: 0.5966693162918091
2023-01-21 08:44:50.521616: step: 1856/530, loss: 2.546915054321289
2023-01-21 08:44:51.637581: step: 1860/530, loss: 1.9478868246078491
2023-01-21 08:44:52.809741: step: 1864/530, loss: 0.26968422532081604
2023-01-21 08:44:53.940249: step: 1868/530, loss: 0.7457396984100342
2023-01-21 08:44:55.035545: step: 1872/530, loss: 0.7320360541343689
2023-01-21 08:44:56.153351: step: 1876/530, loss: 0.14077992737293243
2023-01-21 08:44:57.274650: step: 1880/530, loss: 0.09402614086866379
2023-01-21 08:44:58.382035: step: 1884/530, loss: 0.1349850594997406
2023-01-21 08:44:59.490760: step: 1888/530, loss: 0.693934977054596
2023-01-21 08:45:00.619065: step: 1892/530, loss: 0.30236172676086426
2023-01-21 08:45:01.758210: step: 1896/530, loss: 1.1149325370788574
2023-01-21 08:45:02.870241: step: 1900/530, loss: 0.27901583909988403
2023-01-21 08:45:04.001138: step: 1904/530, loss: 0.19165612757205963
2023-01-21 08:45:05.124704: step: 1908/530, loss: 0.06629457324743271
2023-01-21 08:45:06.247253: step: 1912/530, loss: 0.8024194240570068
2023-01-21 08:45:07.362598: step: 1916/530, loss: 0.7966238260269165
2023-01-21 08:45:08.475394: step: 1920/530, loss: 0.06974106281995773
2023-01-21 08:45:09.592472: step: 1924/530, loss: 0.7855917811393738
2023-01-21 08:45:10.698071: step: 1928/530, loss: 0.7097975015640259
2023-01-21 08:45:11.823275: step: 1932/530, loss: 0.6111996173858643
2023-01-21 08:45:12.945751: step: 1936/530, loss: 2.051295757293701
2023-01-21 08:45:14.054611: step: 1940/530, loss: 0.26898786425590515
2023-01-21 08:45:15.215673: step: 1944/530, loss: 1.0412803888320923
2023-01-21 08:45:16.316356: step: 1948/530, loss: 0.9236189126968384
2023-01-21 08:45:17.413024: step: 1952/530, loss: 0.5727674961090088
2023-01-21 08:45:18.521893: step: 1956/530, loss: 0.08463945984840393
2023-01-21 08:45:19.657807: step: 1960/530, loss: 0.2254650592803955
2023-01-21 08:45:20.768030: step: 1964/530, loss: 0.19339652359485626
2023-01-21 08:45:21.885361: step: 1968/530, loss: 0.7773427963256836
2023-01-21 08:45:23.004957: step: 1972/530, loss: 0.14954176545143127
2023-01-21 08:45:24.135828: step: 1976/530, loss: 0.5910944938659668
2023-01-21 08:45:25.256180: step: 1980/530, loss: 0.22116994857788086
2023-01-21 08:45:26.380315: step: 1984/530, loss: 0.1570582389831543
2023-01-21 08:45:27.510188: step: 1988/530, loss: 0.07202224433422089
2023-01-21 08:45:28.639001: step: 1992/530, loss: 0.14000225067138672
2023-01-21 08:45:29.740725: step: 1996/530, loss: 0.4157206118106842
2023-01-21 08:45:30.831970: step: 2000/530, loss: 0.6648862361907959
2023-01-21 08:45:31.942279: step: 2004/530, loss: 0.286368727684021
2023-01-21 08:45:33.074662: step: 2008/530, loss: 0.15232335031032562
2023-01-21 08:45:34.201360: step: 2012/530, loss: 0.6181201934814453
2023-01-21 08:45:35.320687: step: 2016/530, loss: 0.09782581776380539
2023-01-21 08:45:36.408769: step: 2020/530, loss: 0.17981024086475372
2023-01-21 08:45:37.561059: step: 2024/530, loss: 1.29769766330719
2023-01-21 08:45:38.681370: step: 2028/530, loss: 0.22478684782981873
2023-01-21 08:45:39.802843: step: 2032/530, loss: 0.07622937858104706
2023-01-21 08:45:40.928180: step: 2036/530, loss: 0.1252705603837967
2023-01-21 08:45:42.075396: step: 2040/530, loss: 0.3433162569999695
2023-01-21 08:45:43.207441: step: 2044/530, loss: 0.19063769280910492
2023-01-21 08:45:44.347446: step: 2048/530, loss: 0.22122856974601746
2023-01-21 08:45:45.476277: step: 2052/530, loss: 0.14650268852710724
2023-01-21 08:45:46.596684: step: 2056/530, loss: 1.1723874807357788
2023-01-21 08:45:47.701175: step: 2060/530, loss: 0.198953777551651
2023-01-21 08:45:48.831732: step: 2064/530, loss: 1.712605595588684
2023-01-21 08:45:49.981785: step: 2068/530, loss: 0.22792960703372955
2023-01-21 08:45:51.089578: step: 2072/530, loss: 0.6539992094039917
2023-01-21 08:45:52.196081: step: 2076/530, loss: 0.7947683930397034
2023-01-21 08:45:53.323935: step: 2080/530, loss: 1.8783246278762817
2023-01-21 08:45:54.454110: step: 2084/530, loss: 0.20687751471996307
2023-01-21 08:45:55.571913: step: 2088/530, loss: 0.1786704957485199
2023-01-21 08:45:56.704053: step: 2092/530, loss: 1.5413072109222412
2023-01-21 08:45:57.846720: step: 2096/530, loss: 0.2419353425502777
2023-01-21 08:45:58.966357: step: 2100/530, loss: 0.17813606560230255
2023-01-21 08:46:00.096770: step: 2104/530, loss: 0.14032870531082153
2023-01-21 08:46:01.227145: step: 2108/530, loss: 0.0925634428858757
2023-01-21 08:46:02.353639: step: 2112/530, loss: 0.45660123229026794
2023-01-21 08:46:03.482058: step: 2116/530, loss: 0.2844177484512329
2023-01-21 08:46:04.621842: step: 2120/530, loss: 0.36299824714660645
==================================================
Loss: 0.794
--------------------
Dev: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5932203389830508, 'r': 0.6481481481481481, 'f1': 0.6194690265486725}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.75, 'r': 0.3333333333333333, 'f1': 0.46153846153846156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, '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': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5932203389830508, 'r': 0.6481481481481481, 'f1': 0.6194690265486725}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.75, 'r': 0.3333333333333333, 'f1': 0.46153846153846156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, '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
2023-01-21 08:46:58.879058: step: 4/530, loss: 0.2549871802330017
2023-01-21 08:47:00.056456: step: 8/530, loss: 1.7303869724273682
2023-01-21 08:47:01.167648: step: 12/530, loss: 1.153725266456604
2023-01-21 08:47:02.331338: step: 16/530, loss: 0.5541088581085205
2023-01-21 08:47:03.469380: step: 20/530, loss: 0.07219181209802628
2023-01-21 08:47:04.601730: step: 24/530, loss: 0.11997681111097336
2023-01-21 08:47:05.754991: step: 28/530, loss: 0.6570150256156921
2023-01-21 08:47:06.893495: step: 32/530, loss: 1.6036723852157593
2023-01-21 08:47:08.063065: step: 36/530, loss: 0.1650841385126114
2023-01-21 08:47:09.214882: step: 40/530, loss: 0.8205879330635071
2023-01-21 08:47:10.357509: step: 44/530, loss: 1.344017505645752
2023-01-21 08:47:11.457304: step: 48/530, loss: 0.4052448272705078
2023-01-21 08:47:12.592380: step: 52/530, loss: 0.28544116020202637
2023-01-21 08:47:13.714531: step: 56/530, loss: 0.22886408865451813
2023-01-21 08:47:14.844758: step: 60/530, loss: 0.12092933803796768
2023-01-21 08:47:15.952884: step: 64/530, loss: 0.1983252614736557
2023-01-21 08:47:17.076891: step: 68/530, loss: 1.4818247556686401
2023-01-21 08:47:18.171683: step: 72/530, loss: 0.15928326547145844
2023-01-21 08:47:19.272262: step: 76/530, loss: 0.3694389760494232
2023-01-21 08:47:20.381104: step: 80/530, loss: 0.4056609869003296
2023-01-21 08:47:21.502695: step: 84/530, loss: 0.26151764392852783
2023-01-21 08:47:22.595566: step: 88/530, loss: 0.1126493439078331
2023-01-21 08:47:23.701936: step: 92/530, loss: 0.2248607724905014
2023-01-21 08:47:24.794309: step: 96/530, loss: 0.33363789319992065
2023-01-21 08:47:25.925494: step: 100/530, loss: 0.11394501477479935
2023-01-21 08:47:27.051266: step: 104/530, loss: 0.18549376726150513
2023-01-21 08:47:28.181183: step: 108/530, loss: 0.7846215963363647
2023-01-21 08:47:29.282837: step: 112/530, loss: 1.0464065074920654
2023-01-21 08:47:30.394434: step: 116/530, loss: 0.18868285417556763
2023-01-21 08:47:31.494826: step: 120/530, loss: 0.7378286123275757
2023-01-21 08:47:32.606646: step: 124/530, loss: 0.3399714529514313
2023-01-21 08:47:33.717072: step: 128/530, loss: 0.23601636290550232
2023-01-21 08:47:34.859087: step: 132/530, loss: 0.16574101150035858
2023-01-21 08:47:35.961362: step: 136/530, loss: 0.9829902648925781
2023-01-21 08:47:37.062855: step: 140/530, loss: 0.7383224368095398
2023-01-21 08:47:38.216797: step: 144/530, loss: 1.2845613956451416
2023-01-21 08:47:39.353302: step: 148/530, loss: 0.938347578048706
2023-01-21 08:47:40.468485: step: 152/530, loss: 0.18910598754882812
2023-01-21 08:47:41.580541: step: 156/530, loss: 0.05874957889318466
2023-01-21 08:47:42.725020: step: 160/530, loss: 0.9890762567520142
2023-01-21 08:47:43.858623: step: 164/530, loss: 1.5207116603851318
2023-01-21 08:47:44.998349: step: 168/530, loss: 0.5067645907402039
2023-01-21 08:47:46.129187: step: 172/530, loss: 0.6130468845367432
2023-01-21 08:47:47.267893: step: 176/530, loss: 0.08087359368801117
2023-01-21 08:47:48.379507: step: 180/530, loss: 0.4731321632862091
2023-01-21 08:47:49.518376: step: 184/530, loss: 0.2755403518676758
2023-01-21 08:47:50.637878: step: 188/530, loss: 0.3389209806919098
2023-01-21 08:47:51.788681: step: 192/530, loss: 0.247080996632576
2023-01-21 08:47:52.915549: step: 196/530, loss: 0.1220521479845047
2023-01-21 08:47:54.058493: step: 200/530, loss: 0.7505062222480774
2023-01-21 08:47:55.177293: step: 204/530, loss: 0.13835224509239197
2023-01-21 08:47:56.275777: step: 208/530, loss: 0.08297586441040039
2023-01-21 08:47:57.423133: step: 212/530, loss: 0.47152671217918396
2023-01-21 08:47:58.580192: step: 216/530, loss: 0.4521659016609192
2023-01-21 08:47:59.682147: step: 220/530, loss: 0.058286383748054504
2023-01-21 08:48:00.804764: step: 224/530, loss: 0.569999635219574
2023-01-21 08:48:01.903695: step: 228/530, loss: 0.1763368546962738
2023-01-21 08:48:03.060464: step: 232/530, loss: 0.7132700681686401
2023-01-21 08:48:04.172375: step: 236/530, loss: 0.7418447732925415
2023-01-21 08:48:05.307364: step: 240/530, loss: 0.151699498295784
2023-01-21 08:48:06.425394: step: 244/530, loss: 0.21459513902664185
2023-01-21 08:48:07.578204: step: 248/530, loss: 0.1821517050266266
2023-01-21 08:48:08.702603: step: 252/530, loss: 0.4466073513031006
2023-01-21 08:48:09.810971: step: 256/530, loss: 0.161688432097435
2023-01-21 08:48:10.935935: step: 260/530, loss: 0.8341001868247986
2023-01-21 08:48:12.061750: step: 264/530, loss: 0.5594701766967773
2023-01-21 08:48:13.170740: step: 268/530, loss: 0.8592886924743652
2023-01-21 08:48:14.314751: step: 272/530, loss: 0.36857423186302185
2023-01-21 08:48:15.435262: step: 276/530, loss: 0.11693410575389862
2023-01-21 08:48:16.546883: step: 280/530, loss: 0.4446922838687897
2023-01-21 08:48:17.656723: step: 284/530, loss: 0.6469581723213196
2023-01-21 08:48:18.790263: step: 288/530, loss: 0.2586190104484558
2023-01-21 08:48:19.923982: step: 292/530, loss: 0.4812266528606415
2023-01-21 08:48:21.040174: step: 296/530, loss: 0.7611778974533081
2023-01-21 08:48:22.151018: step: 300/530, loss: 1.189784049987793
2023-01-21 08:48:23.257736: step: 304/530, loss: 0.5434539318084717
2023-01-21 08:48:24.375966: step: 308/530, loss: 0.6020355224609375
2023-01-21 08:48:25.495675: step: 312/530, loss: 1.158416748046875
2023-01-21 08:48:26.646617: step: 316/530, loss: 0.16148415207862854
2023-01-21 08:48:27.772525: step: 320/530, loss: 0.40499603748321533
2023-01-21 08:48:28.856712: step: 324/530, loss: 0.12176743149757385
2023-01-21 08:48:29.970198: step: 328/530, loss: 1.566463828086853
2023-01-21 08:48:31.088676: step: 332/530, loss: 0.18461808562278748
2023-01-21 08:48:32.209391: step: 336/530, loss: 0.6959921717643738
2023-01-21 08:48:33.351755: step: 340/530, loss: 0.8371450304985046
2023-01-21 08:48:34.467126: step: 344/530, loss: 1.0187971591949463
2023-01-21 08:48:35.625738: step: 348/530, loss: 0.3670177459716797
2023-01-21 08:48:36.733956: step: 352/530, loss: 0.41727352142333984
2023-01-21 08:48:37.847139: step: 356/530, loss: 0.17567510902881622
2023-01-21 08:48:38.962362: step: 360/530, loss: 0.757550835609436
2023-01-21 08:48:40.079427: step: 364/530, loss: 0.06790180504322052
2023-01-21 08:48:41.179680: step: 368/530, loss: 0.13106070458889008
2023-01-21 08:48:42.283018: step: 372/530, loss: 0.1412394940853119
2023-01-21 08:48:43.410996: step: 376/530, loss: 0.2952960133552551
2023-01-21 08:48:44.539565: step: 380/530, loss: 0.6557536125183105
2023-01-21 08:48:45.667590: step: 384/530, loss: 0.9003782868385315
2023-01-21 08:48:46.824893: step: 388/530, loss: 0.099893718957901
2023-01-21 08:48:47.959855: step: 392/530, loss: 0.1825265884399414
2023-01-21 08:48:49.088687: step: 396/530, loss: 0.2066102921962738
2023-01-21 08:48:50.201910: step: 400/530, loss: 0.43238189816474915
2023-01-21 08:48:51.342357: step: 404/530, loss: 0.14483137428760529
2023-01-21 08:48:52.462498: step: 408/530, loss: 0.39697813987731934
2023-01-21 08:48:53.597708: step: 412/530, loss: 0.7833611369132996
2023-01-21 08:48:54.713933: step: 416/530, loss: 0.8130244016647339
2023-01-21 08:48:55.853394: step: 420/530, loss: 0.26998642086982727
2023-01-21 08:48:56.976512: step: 424/530, loss: 0.45044320821762085
2023-01-21 08:48:58.096195: step: 428/530, loss: 1.0882318019866943
2023-01-21 08:48:59.218805: step: 432/530, loss: 0.10300693660974503
2023-01-21 08:49:00.314796: step: 436/530, loss: 0.41531428694725037
2023-01-21 08:49:01.423322: step: 440/530, loss: 0.027932167053222656
2023-01-21 08:49:02.568945: step: 444/530, loss: 0.20370645821094513
2023-01-21 08:49:03.679901: step: 448/530, loss: 0.9263323545455933
2023-01-21 08:49:04.852540: step: 452/530, loss: 0.445218563079834
2023-01-21 08:49:05.958360: step: 456/530, loss: 0.7113152146339417
2023-01-21 08:49:07.084828: step: 460/530, loss: 0.5523746609687805
2023-01-21 08:49:08.195629: step: 464/530, loss: 0.21276822686195374
2023-01-21 08:49:09.284748: step: 468/530, loss: 0.15584564208984375
2023-01-21 08:49:10.394817: step: 472/530, loss: 0.20984001457691193
2023-01-21 08:49:11.507735: step: 476/530, loss: 0.2754071354866028
2023-01-21 08:49:12.629730: step: 480/530, loss: 0.17370755970478058
2023-01-21 08:49:13.748315: step: 484/530, loss: 0.176835834980011
2023-01-21 08:49:14.874084: step: 488/530, loss: 0.2124270498752594
2023-01-21 08:49:16.012789: step: 492/530, loss: 0.1323350965976715
2023-01-21 08:49:17.115066: step: 496/530, loss: 1.0380834341049194
2023-01-21 08:49:18.226895: step: 500/530, loss: 6.5939741134643555
2023-01-21 08:49:19.339053: step: 504/530, loss: 0.21367189288139343
2023-01-21 08:49:20.471729: step: 508/530, loss: 0.6519832015037537
2023-01-21 08:49:21.603608: step: 512/530, loss: 0.3971001207828522
2023-01-21 08:49:22.713923: step: 516/530, loss: 0.2099950760602951
2023-01-21 08:49:23.836956: step: 520/530, loss: 0.6482779383659363
2023-01-21 08:49:24.946649: step: 524/530, loss: 0.036852024495601654
2023-01-21 08:49:26.093824: step: 528/530, loss: 1.981764793395996
2023-01-21 08:49:27.284679: step: 532/530, loss: 0.2899623513221741
2023-01-21 08:49:28.419975: step: 536/530, loss: 0.7923697233200073
2023-01-21 08:49:29.556817: step: 540/530, loss: 0.36124134063720703
2023-01-21 08:49:30.653626: step: 544/530, loss: 0.16855287551879883
2023-01-21 08:49:31.755734: step: 548/530, loss: 0.6073692440986633
2023-01-21 08:49:32.886989: step: 552/530, loss: 1.2224150896072388
2023-01-21 08:49:33.977620: step: 556/530, loss: 1.0469428300857544
2023-01-21 08:49:35.122634: step: 560/530, loss: 0.1363590508699417
2023-01-21 08:49:36.254320: step: 564/530, loss: 0.3859992027282715
2023-01-21 08:49:37.388288: step: 568/530, loss: 0.14113959670066833
2023-01-21 08:49:38.520618: step: 572/530, loss: 0.3557610511779785
2023-01-21 08:49:39.635582: step: 576/530, loss: 0.09070573002099991
2023-01-21 08:49:40.784250: step: 580/530, loss: 0.08663950115442276
2023-01-21 08:49:41.899755: step: 584/530, loss: 0.3012918531894684
2023-01-21 08:49:43.026480: step: 588/530, loss: 0.7022686004638672
2023-01-21 08:49:44.172208: step: 592/530, loss: 0.7342543601989746
2023-01-21 08:49:45.307148: step: 596/530, loss: 2.139040470123291
2023-01-21 08:49:46.407657: step: 600/530, loss: 0.9770023822784424
2023-01-21 08:49:47.517589: step: 604/530, loss: 0.20111560821533203
2023-01-21 08:49:48.639523: step: 608/530, loss: 1.280655860900879
2023-01-21 08:49:49.758650: step: 612/530, loss: 0.22764426469802856
2023-01-21 08:49:50.864511: step: 616/530, loss: 0.5092660188674927
2023-01-21 08:49:51.991815: step: 620/530, loss: 0.08441576361656189
2023-01-21 08:49:53.110236: step: 624/530, loss: 0.41629570722579956
2023-01-21 08:49:54.220410: step: 628/530, loss: 1.22637140750885
2023-01-21 08:49:55.340017: step: 632/530, loss: 1.4531912803649902
2023-01-21 08:49:56.466842: step: 636/530, loss: 0.45081931352615356
2023-01-21 08:49:57.608417: step: 640/530, loss: 0.39078283309936523
2023-01-21 08:49:58.718050: step: 644/530, loss: 0.3018566966056824
2023-01-21 08:49:59.831819: step: 648/530, loss: 0.829871654510498
2023-01-21 08:50:00.970006: step: 652/530, loss: 0.5401266813278198
2023-01-21 08:50:02.105273: step: 656/530, loss: 6.142358303070068
2023-01-21 08:50:03.196521: step: 660/530, loss: 0.8059202432632446
2023-01-21 08:50:04.312355: step: 664/530, loss: 0.14764243364334106
2023-01-21 08:50:05.459740: step: 668/530, loss: 0.2622183859348297
2023-01-21 08:50:06.562807: step: 672/530, loss: 7.544880390167236
2023-01-21 08:50:07.677293: step: 676/530, loss: 0.8880947828292847
2023-01-21 08:50:08.805421: step: 680/530, loss: 0.14731311798095703
2023-01-21 08:50:09.912825: step: 684/530, loss: 0.5059198141098022
2023-01-21 08:50:11.026681: step: 688/530, loss: 0.26448696851730347
2023-01-21 08:50:12.158118: step: 692/530, loss: 1.2483859062194824
2023-01-21 08:50:13.259723: step: 696/530, loss: 0.08068018406629562
2023-01-21 08:50:14.381365: step: 700/530, loss: 0.14242082834243774
2023-01-21 08:50:15.518220: step: 704/530, loss: 0.32842761278152466
2023-01-21 08:50:16.627576: step: 708/530, loss: 0.08093119412660599
2023-01-21 08:50:17.744800: step: 712/530, loss: 0.03687271848320961
2023-01-21 08:50:18.865569: step: 716/530, loss: 0.18993185460567474
2023-01-21 08:50:19.974856: step: 720/530, loss: 0.37675780057907104
2023-01-21 08:50:21.102567: step: 724/530, loss: 0.24144478142261505
2023-01-21 08:50:22.201167: step: 728/530, loss: 1.2489759922027588
2023-01-21 08:50:23.310439: step: 732/530, loss: 0.64762943983078
2023-01-21 08:50:24.435525: step: 736/530, loss: 0.22054243087768555
2023-01-21 08:50:25.540867: step: 740/530, loss: 0.7320102453231812
2023-01-21 08:50:26.632619: step: 744/530, loss: 0.18115448951721191
2023-01-21 08:50:27.731517: step: 748/530, loss: 0.18425212800502777
2023-01-21 08:50:28.857984: step: 752/530, loss: 0.1290455311536789
2023-01-21 08:50:29.969863: step: 756/530, loss: 0.22215071320533752
2023-01-21 08:50:31.049173: step: 760/530, loss: 0.9888249039649963
2023-01-21 08:50:32.156614: step: 764/530, loss: 0.12373016029596329
2023-01-21 08:50:33.292046: step: 768/530, loss: 0.15127182006835938
2023-01-21 08:50:34.418327: step: 772/530, loss: 0.3780156970024109
2023-01-21 08:50:35.559900: step: 776/530, loss: 0.17230844497680664
2023-01-21 08:50:36.686465: step: 780/530, loss: 0.800753116607666
2023-01-21 08:50:37.823524: step: 784/530, loss: 1.518019676208496
2023-01-21 08:50:38.960946: step: 788/530, loss: 0.1791977435350418
2023-01-21 08:50:40.078130: step: 792/530, loss: 0.3912786543369293
2023-01-21 08:50:41.226221: step: 796/530, loss: 0.3245595097541809
2023-01-21 08:50:42.318108: step: 800/530, loss: 0.7361921072006226
2023-01-21 08:50:43.443138: step: 804/530, loss: 0.3055207133293152
2023-01-21 08:50:44.573232: step: 808/530, loss: 0.2662474513053894
2023-01-21 08:50:45.677575: step: 812/530, loss: 0.05306663364171982
2023-01-21 08:50:46.790979: step: 816/530, loss: 1.3680143356323242
2023-01-21 08:50:47.884357: step: 820/530, loss: 0.06519480049610138
2023-01-21 08:50:49.008282: step: 824/530, loss: 0.180962473154068
2023-01-21 08:50:50.105163: step: 828/530, loss: 0.07015037536621094
2023-01-21 08:50:51.203800: step: 832/530, loss: 0.7355828881263733
2023-01-21 08:50:52.316870: step: 836/530, loss: 0.5996140241622925
2023-01-21 08:50:53.429904: step: 840/530, loss: 0.15328168869018555
2023-01-21 08:50:54.562013: step: 844/530, loss: 0.042687609791755676
2023-01-21 08:50:55.661963: step: 848/530, loss: 0.16516882181167603
2023-01-21 08:50:56.776851: step: 852/530, loss: 0.6940152645111084
2023-01-21 08:50:57.869755: step: 856/530, loss: 0.7352458834648132
2023-01-21 08:50:59.009578: step: 860/530, loss: 0.47857657074928284
2023-01-21 08:51:00.124189: step: 864/530, loss: 1.603176474571228
2023-01-21 08:51:01.235192: step: 868/530, loss: 0.7686771154403687
2023-01-21 08:51:02.364749: step: 872/530, loss: 0.24088802933692932
2023-01-21 08:51:03.483900: step: 876/530, loss: 0.11938619613647461
2023-01-21 08:51:04.637222: step: 880/530, loss: 0.04923210293054581
2023-01-21 08:51:05.785835: step: 884/530, loss: 0.14917898178100586
2023-01-21 08:51:06.889839: step: 888/530, loss: 0.061806872487068176
2023-01-21 08:51:07.993156: step: 892/530, loss: 0.1656983494758606
2023-01-21 08:51:09.110786: step: 896/530, loss: 1.5073906183242798
2023-01-21 08:51:10.215684: step: 900/530, loss: 0.26584750413894653
2023-01-21 08:51:11.334510: step: 904/530, loss: 0.1944114714860916
2023-01-21 08:51:12.460257: step: 908/530, loss: 0.26362448930740356
2023-01-21 08:51:13.599610: step: 912/530, loss: 0.38007867336273193
2023-01-21 08:51:14.703915: step: 916/530, loss: 0.4378413259983063
2023-01-21 08:51:15.804938: step: 920/530, loss: 1.208674669265747
2023-01-21 08:51:16.927626: step: 924/530, loss: 0.175586998462677
2023-01-21 08:51:18.056139: step: 928/530, loss: 0.6227144598960876
2023-01-21 08:51:19.195862: step: 932/530, loss: 1.5765175819396973
2023-01-21 08:51:20.326903: step: 936/530, loss: 0.1888962835073471
2023-01-21 08:51:21.493163: step: 940/530, loss: 0.09631138294935226
2023-01-21 08:51:22.617133: step: 944/530, loss: 0.2614017426967621
2023-01-21 08:51:23.722267: step: 948/530, loss: 0.055631544440984726
2023-01-21 08:51:24.857809: step: 952/530, loss: 0.32814350724220276
2023-01-21 08:51:25.977224: step: 956/530, loss: 1.0186214447021484
2023-01-21 08:51:27.123847: step: 960/530, loss: 0.41222620010375977
2023-01-21 08:51:28.235858: step: 964/530, loss: 0.06350564956665039
2023-01-21 08:51:29.372925: step: 968/530, loss: 0.12357597053050995
2023-01-21 08:51:30.481532: step: 972/530, loss: 0.3315253257751465
2023-01-21 08:51:31.575574: step: 976/530, loss: 0.9720466732978821
2023-01-21 08:51:32.672168: step: 980/530, loss: 0.06506018340587616
2023-01-21 08:51:33.794666: step: 984/530, loss: 0.3916108310222626
2023-01-21 08:51:34.946849: step: 988/530, loss: 0.861648678779602
2023-01-21 08:51:36.038924: step: 992/530, loss: 0.08412675559520721
2023-01-21 08:51:37.229018: step: 996/530, loss: 0.23973016440868378
2023-01-21 08:51:38.357460: step: 1000/530, loss: 0.8282028436660767
2023-01-21 08:51:39.474031: step: 1004/530, loss: 0.7034934759140015
2023-01-21 08:51:40.581870: step: 1008/530, loss: 0.29350337386131287
2023-01-21 08:51:41.727070: step: 1012/530, loss: 0.3190247714519501
2023-01-21 08:51:42.856443: step: 1016/530, loss: 0.7765703797340393
2023-01-21 08:51:43.981635: step: 1020/530, loss: 0.28241467475891113
2023-01-21 08:51:45.093585: step: 1024/530, loss: 0.5483298301696777
2023-01-21 08:51:46.228039: step: 1028/530, loss: 0.515511691570282
2023-01-21 08:51:47.354948: step: 1032/530, loss: 0.12958142161369324
2023-01-21 08:51:48.474667: step: 1036/530, loss: 6.191729545593262
2023-01-21 08:51:49.595518: step: 1040/530, loss: 0.7704676985740662
2023-01-21 08:51:50.723170: step: 1044/530, loss: 0.10454535484313965
2023-01-21 08:51:51.834054: step: 1048/530, loss: 0.09000349044799805
2023-01-21 08:51:52.942560: step: 1052/530, loss: 0.7896023988723755
2023-01-21 08:51:54.045041: step: 1056/530, loss: 0.6158335208892822
2023-01-21 08:51:55.157224: step: 1060/530, loss: 0.6221862435340881
2023-01-21 08:51:56.259161: step: 1064/530, loss: 0.5899291634559631
2023-01-21 08:51:57.406529: step: 1068/530, loss: 0.8752052187919617
2023-01-21 08:51:58.520489: step: 1072/530, loss: 0.4298314154148102
2023-01-21 08:51:59.683234: step: 1076/530, loss: 0.13121899962425232
2023-01-21 08:52:00.801326: step: 1080/530, loss: 0.1385403871536255
2023-01-21 08:52:01.922600: step: 1084/530, loss: 0.23179060220718384
2023-01-21 08:52:03.095664: step: 1088/530, loss: 1.016118049621582
2023-01-21 08:52:04.242930: step: 1092/530, loss: 0.10098409652709961
2023-01-21 08:52:05.413437: step: 1096/530, loss: 0.4687042236328125
2023-01-21 08:52:06.531161: step: 1100/530, loss: 2.1217658519744873
2023-01-21 08:52:07.677128: step: 1104/530, loss: 0.12036685645580292
2023-01-21 08:52:08.786376: step: 1108/530, loss: 0.34987831115722656
2023-01-21 08:52:09.884975: step: 1112/530, loss: 0.052722882479429245
2023-01-21 08:52:11.002726: step: 1116/530, loss: 0.06628718972206116
2023-01-21 08:52:12.125082: step: 1120/530, loss: 0.6652696132659912
2023-01-21 08:52:13.230600: step: 1124/530, loss: 0.15781469643115997
2023-01-21 08:52:14.351139: step: 1128/530, loss: 0.6451373100280762
2023-01-21 08:52:15.488184: step: 1132/530, loss: 1.2718219757080078
2023-01-21 08:52:16.613532: step: 1136/530, loss: 0.24527369439601898
2023-01-21 08:52:17.742298: step: 1140/530, loss: 0.22603583335876465
2023-01-21 08:52:18.853409: step: 1144/530, loss: 1.5129776000976562
2023-01-21 08:52:19.972291: step: 1148/530, loss: 0.10716376453638077
2023-01-21 08:52:21.088629: step: 1152/530, loss: 0.185224249958992
2023-01-21 08:52:22.199899: step: 1156/530, loss: 0.12649841606616974
2023-01-21 08:52:23.339579: step: 1160/530, loss: 0.14966841042041779
2023-01-21 08:52:24.483845: step: 1164/530, loss: 0.7400844693183899
2023-01-21 08:52:25.591458: step: 1168/530, loss: 0.08268282562494278
2023-01-21 08:52:26.746024: step: 1172/530, loss: 0.7513513565063477
2023-01-21 08:52:27.867740: step: 1176/530, loss: 0.45528754591941833
2023-01-21 08:52:29.028714: step: 1180/530, loss: 0.449070543050766
2023-01-21 08:52:30.164837: step: 1184/530, loss: 0.09797721356153488
2023-01-21 08:52:31.283642: step: 1188/530, loss: 0.24434785544872284
2023-01-21 08:52:32.398550: step: 1192/530, loss: 0.184340238571167
2023-01-21 08:52:33.518553: step: 1196/530, loss: 1.1998863220214844
2023-01-21 08:52:34.651022: step: 1200/530, loss: 0.210282564163208
2023-01-21 08:52:35.744756: step: 1204/530, loss: 1.3139013051986694
2023-01-21 08:52:36.887432: step: 1208/530, loss: 0.5444134473800659
2023-01-21 08:52:37.980174: step: 1212/530, loss: 0.29207244515419006
2023-01-21 08:52:39.087914: step: 1216/530, loss: 0.09406566619873047
2023-01-21 08:52:40.218437: step: 1220/530, loss: 0.4249807596206665
2023-01-21 08:52:41.360134: step: 1224/530, loss: 0.2517785131931305
2023-01-21 08:52:42.485627: step: 1228/530, loss: 0.37605181336402893
2023-01-21 08:52:43.657167: step: 1232/530, loss: 0.1841794103384018
2023-01-21 08:52:44.779586: step: 1236/530, loss: 0.7708064317703247
2023-01-21 08:52:45.897924: step: 1240/530, loss: 1.9997828006744385
2023-01-21 08:52:47.008661: step: 1244/530, loss: 0.16339293122291565
2023-01-21 08:52:48.140493: step: 1248/530, loss: 0.49651604890823364
2023-01-21 08:52:49.264817: step: 1252/530, loss: 1.6021158695220947
2023-01-21 08:52:50.372022: step: 1256/530, loss: 0.1506500244140625
2023-01-21 08:52:51.476545: step: 1260/530, loss: 0.05822458490729332
2023-01-21 08:52:52.595017: step: 1264/530, loss: 0.09736347198486328
2023-01-21 08:52:53.704631: step: 1268/530, loss: 0.0550776943564415
2023-01-21 08:52:54.805753: step: 1272/530, loss: 0.2136070728302002
2023-01-21 08:52:55.950283: step: 1276/530, loss: 0.09297418594360352
2023-01-21 08:52:57.057983: step: 1280/530, loss: 0.16149863600730896
2023-01-21 08:52:58.168291: step: 1284/530, loss: 0.46872490644454956
2023-01-21 08:52:59.291575: step: 1288/530, loss: 0.32695770263671875
2023-01-21 08:53:00.411548: step: 1292/530, loss: 0.08009135723114014
2023-01-21 08:53:01.541662: step: 1296/530, loss: 0.6113733053207397
2023-01-21 08:53:02.672115: step: 1300/530, loss: 0.5991030931472778
2023-01-21 08:53:03.772182: step: 1304/530, loss: 0.5400673151016235
2023-01-21 08:53:04.888654: step: 1308/530, loss: 1.7407561540603638
2023-01-21 08:53:06.008282: step: 1312/530, loss: 0.222305029630661
2023-01-21 08:53:07.157673: step: 1316/530, loss: 0.11263298988342285
2023-01-21 08:53:08.299070: step: 1320/530, loss: 0.14874425530433655
2023-01-21 08:53:09.438298: step: 1324/530, loss: 0.2534072995185852
2023-01-21 08:53:10.548050: step: 1328/530, loss: 0.08204689621925354
2023-01-21 08:53:11.667314: step: 1332/530, loss: 0.22871409356594086
2023-01-21 08:53:12.768518: step: 1336/530, loss: 0.070670947432518
2023-01-21 08:53:13.896542: step: 1340/530, loss: 0.4729039669036865
2023-01-21 08:53:15.011605: step: 1344/530, loss: 0.22761201858520508
2023-01-21 08:53:16.102385: step: 1348/530, loss: 0.17169252038002014
2023-01-21 08:53:17.180235: step: 1352/530, loss: 0.21530741453170776
2023-01-21 08:53:18.320368: step: 1356/530, loss: 1.4356058835983276
2023-01-21 08:53:19.436448: step: 1360/530, loss: 0.37823906540870667
2023-01-21 08:53:20.594847: step: 1364/530, loss: 0.7812243700027466
2023-01-21 08:53:21.717190: step: 1368/530, loss: 1.2373443841934204
2023-01-21 08:53:22.809649: step: 1372/530, loss: 0.10183171927928925
2023-01-21 08:53:23.946388: step: 1376/530, loss: 0.8201669454574585
2023-01-21 08:53:25.035912: step: 1380/530, loss: 0.24404993653297424
2023-01-21 08:53:26.174047: step: 1384/530, loss: 0.1608392298221588
2023-01-21 08:53:27.309494: step: 1388/530, loss: 0.7014926075935364
2023-01-21 08:53:28.463366: step: 1392/530, loss: 0.45869407057762146
2023-01-21 08:53:29.583511: step: 1396/530, loss: 6.414951801300049
2023-01-21 08:53:30.729162: step: 1400/530, loss: 0.027323007583618164
2023-01-21 08:53:31.869796: step: 1404/530, loss: 0.5884970426559448
2023-01-21 08:53:32.993232: step: 1408/530, loss: 0.2120293825864792
2023-01-21 08:53:34.119425: step: 1412/530, loss: 0.0824156254529953
2023-01-21 08:53:35.261386: step: 1416/530, loss: 0.19473476707935333
2023-01-21 08:53:36.381861: step: 1420/530, loss: 0.37752535939216614
2023-01-21 08:53:37.493736: step: 1424/530, loss: 0.12089991569519043
2023-01-21 08:53:38.591709: step: 1428/530, loss: 6.326498508453369
2023-01-21 08:53:39.719309: step: 1432/530, loss: 0.4065941870212555
2023-01-21 08:53:40.837350: step: 1436/530, loss: 1.898832082748413
2023-01-21 08:53:41.964176: step: 1440/530, loss: 6.559451103210449
2023-01-21 08:53:43.104312: step: 1444/530, loss: 1.0750842094421387
2023-01-21 08:53:44.203954: step: 1448/530, loss: 0.08206968754529953
2023-01-21 08:53:45.272906: step: 1452/530, loss: 1.6692469120025635
2023-01-21 08:53:46.379377: step: 1456/530, loss: 0.08275580406188965
2023-01-21 08:53:47.516842: step: 1460/530, loss: 0.29534482955932617
2023-01-21 08:53:48.646184: step: 1464/530, loss: 0.12534990906715393
2023-01-21 08:53:49.778873: step: 1468/530, loss: 0.07975426316261292
2023-01-21 08:53:50.922643: step: 1472/530, loss: 0.7868443727493286
2023-01-21 08:53:52.044202: step: 1476/530, loss: 0.28463783860206604
2023-01-21 08:53:53.194293: step: 1480/530, loss: 1.543434739112854
2023-01-21 08:53:54.314477: step: 1484/530, loss: 0.5127757787704468
2023-01-21 08:53:55.442088: step: 1488/530, loss: 0.11634526401758194
2023-01-21 08:53:56.568563: step: 1492/530, loss: 0.1346220076084137
2023-01-21 08:53:57.726454: step: 1496/530, loss: 0.2461404800415039
2023-01-21 08:53:58.865073: step: 1500/530, loss: 0.3611830770969391
2023-01-21 08:54:00.048812: step: 1504/530, loss: 0.42270898818969727
2023-01-21 08:54:01.197975: step: 1508/530, loss: 0.2460983395576477
2023-01-21 08:54:02.320747: step: 1512/530, loss: 0.2051871418952942
2023-01-21 08:54:03.449956: step: 1516/530, loss: 1.3063852787017822
2023-01-21 08:54:04.540528: step: 1520/530, loss: 0.2958106994628906
2023-01-21 08:54:05.656800: step: 1524/530, loss: 0.5070406198501587
2023-01-21 08:54:06.772384: step: 1528/530, loss: 0.20924854278564453
2023-01-21 08:54:07.897161: step: 1532/530, loss: 0.15202771127223969
2023-01-21 08:54:09.004642: step: 1536/530, loss: 2.326475143432617
2023-01-21 08:54:10.113976: step: 1540/530, loss: 0.08757729828357697
2023-01-21 08:54:11.264191: step: 1544/530, loss: 1.299591064453125
2023-01-21 08:54:12.388051: step: 1548/530, loss: 0.3828961253166199
2023-01-21 08:54:13.517527: step: 1552/530, loss: 0.2863673269748688
2023-01-21 08:54:14.611971: step: 1556/530, loss: 0.07447466999292374
2023-01-21 08:54:15.738726: step: 1560/530, loss: 7.14508581161499
2023-01-21 08:54:16.872048: step: 1564/530, loss: 0.14088097214698792
2023-01-21 08:54:18.040276: step: 1568/530, loss: 1.9876673221588135
2023-01-21 08:54:19.158902: step: 1572/530, loss: 0.4182295799255371
2023-01-21 08:54:20.282298: step: 1576/530, loss: 0.8177449703216553
2023-01-21 08:54:21.400731: step: 1580/530, loss: 0.3151237368583679
2023-01-21 08:54:22.512856: step: 1584/530, loss: 1.5390770435333252
2023-01-21 08:54:23.653020: step: 1588/530, loss: 1.0214335918426514
2023-01-21 08:54:24.747978: step: 1592/530, loss: 0.09614195674657822
2023-01-21 08:54:25.873407: step: 1596/530, loss: 0.11271438747644424
2023-01-21 08:54:27.004724: step: 1600/530, loss: 0.5496959686279297
2023-01-21 08:54:28.124375: step: 1604/530, loss: 0.8033367991447449
2023-01-21 08:54:29.253185: step: 1608/530, loss: 0.6044737100601196
2023-01-21 08:54:30.358955: step: 1612/530, loss: 1.9274663925170898
2023-01-21 08:54:31.492260: step: 1616/530, loss: 0.25484132766723633
2023-01-21 08:54:32.606630: step: 1620/530, loss: 0.3882312476634979
2023-01-21 08:54:33.697258: step: 1624/530, loss: 7.3641357421875
2023-01-21 08:54:34.814562: step: 1628/530, loss: 1.288686990737915
2023-01-21 08:54:35.939701: step: 1632/530, loss: 0.08786025643348694
2023-01-21 08:54:37.054065: step: 1636/530, loss: 0.1812223494052887
2023-01-21 08:54:38.221868: step: 1640/530, loss: 1.2615675926208496
2023-01-21 08:54:39.332305: step: 1644/530, loss: 0.05477505177259445
2023-01-21 08:54:40.453245: step: 1648/530, loss: 0.10191360116004944
2023-01-21 08:54:41.572735: step: 1652/530, loss: 0.6886259317398071
2023-01-21 08:54:42.704966: step: 1656/530, loss: 1.9948408603668213
2023-01-21 08:54:43.817420: step: 1660/530, loss: 0.30972665548324585
2023-01-21 08:54:44.947466: step: 1664/530, loss: 0.048215627670288086
2023-01-21 08:54:46.076033: step: 1668/530, loss: 0.9507412910461426
2023-01-21 08:54:47.215546: step: 1672/530, loss: 1.0865137577056885
2023-01-21 08:54:48.358731: step: 1676/530, loss: 0.8738133907318115
2023-01-21 08:54:49.470305: step: 1680/530, loss: 0.23672696948051453
2023-01-21 08:54:50.605663: step: 1684/530, loss: 0.24212399125099182
2023-01-21 08:54:51.727933: step: 1688/530, loss: 0.23320885002613068
2023-01-21 08:54:52.871204: step: 1692/530, loss: 1.0013595819473267
2023-01-21 08:54:54.007723: step: 1696/530, loss: 0.15325136482715607
2023-01-21 08:54:55.128312: step: 1700/530, loss: 0.2142990529537201
2023-01-21 08:54:56.255354: step: 1704/530, loss: 0.22104549407958984
2023-01-21 08:54:57.350112: step: 1708/530, loss: 0.11247821152210236
2023-01-21 08:54:58.466526: step: 1712/530, loss: 0.6389761567115784
2023-01-21 08:54:59.568002: step: 1716/530, loss: 0.09800930321216583
2023-01-21 08:55:00.734403: step: 1720/530, loss: 0.30935680866241455
2023-01-21 08:55:01.913890: step: 1724/530, loss: 0.25702953338623047
2023-01-21 08:55:03.017542: step: 1728/530, loss: 0.06217360496520996
2023-01-21 08:55:04.144535: step: 1732/530, loss: 0.09047393500804901
2023-01-21 08:55:05.268177: step: 1736/530, loss: 0.1336732804775238
2023-01-21 08:55:06.440371: step: 1740/530, loss: 0.5340733528137207
2023-01-21 08:55:07.561567: step: 1744/530, loss: 0.531393826007843
2023-01-21 08:55:08.668162: step: 1748/530, loss: 0.5154545307159424
2023-01-21 08:55:09.801647: step: 1752/530, loss: 0.14974327385425568
2023-01-21 08:55:10.898200: step: 1756/530, loss: 0.053351547569036484
2023-01-21 08:55:12.016583: step: 1760/530, loss: 0.16407376527786255
2023-01-21 08:55:13.145953: step: 1764/530, loss: 0.08765693008899689
2023-01-21 08:55:14.290465: step: 1768/530, loss: 0.499778151512146
2023-01-21 08:55:15.422744: step: 1772/530, loss: 0.46413174271583557
2023-01-21 08:55:16.520113: step: 1776/530, loss: 0.11247333884239197
2023-01-21 08:55:17.643638: step: 1780/530, loss: 0.37716227769851685
2023-01-21 08:55:18.761586: step: 1784/530, loss: 2.129530906677246
2023-01-21 08:55:19.874371: step: 1788/530, loss: 0.6678089499473572
2023-01-21 08:55:21.016572: step: 1792/530, loss: 0.16081924736499786
2023-01-21 08:55:22.122377: step: 1796/530, loss: 0.3812602162361145
2023-01-21 08:55:23.250873: step: 1800/530, loss: 0.6328672170639038
2023-01-21 08:55:24.363331: step: 1804/530, loss: 0.6405184864997864
2023-01-21 08:55:25.496189: step: 1808/530, loss: 0.6990206837654114
2023-01-21 08:55:26.636197: step: 1812/530, loss: 0.352647602558136
2023-01-21 08:55:27.789640: step: 1816/530, loss: 0.10947147011756897
2023-01-21 08:55:28.917964: step: 1820/530, loss: 0.16661424934864044
2023-01-21 08:55:30.036831: step: 1824/530, loss: 0.10155987739562988
2023-01-21 08:55:31.177710: step: 1828/530, loss: 0.8162501454353333
2023-01-21 08:55:32.328653: step: 1832/530, loss: 0.2598547041416168
2023-01-21 08:55:33.465662: step: 1836/530, loss: 0.1784307062625885
2023-01-21 08:55:34.567310: step: 1840/530, loss: 0.7863420248031616
2023-01-21 08:55:35.672493: step: 1844/530, loss: 0.22834280133247375
2023-01-21 08:55:36.814647: step: 1848/530, loss: 0.7989018559455872
2023-01-21 08:55:37.946526: step: 1852/530, loss: 0.7019374966621399
2023-01-21 08:55:39.059616: step: 1856/530, loss: 0.19690647721290588
2023-01-21 08:55:40.174303: step: 1860/530, loss: 0.0850774273276329
2023-01-21 08:55:41.297086: step: 1864/530, loss: 0.9399198293685913
2023-01-21 08:55:42.431349: step: 1868/530, loss: 1.9015846252441406
2023-01-21 08:55:43.546074: step: 1872/530, loss: 0.16511507332324982
2023-01-21 08:55:44.671328: step: 1876/530, loss: 0.5228404998779297
2023-01-21 08:55:45.824309: step: 1880/530, loss: 0.41082051396369934
2023-01-21 08:55:46.979737: step: 1884/530, loss: 0.8720858693122864
2023-01-21 08:55:48.113337: step: 1888/530, loss: 0.05514850839972496
2023-01-21 08:55:49.233255: step: 1892/530, loss: 0.604894757270813
2023-01-21 08:55:50.368013: step: 1896/530, loss: 0.5620167851448059
2023-01-21 08:55:51.474905: step: 1900/530, loss: 0.8447092771530151
2023-01-21 08:55:52.584992: step: 1904/530, loss: 0.9962377548217773
2023-01-21 08:55:53.700411: step: 1908/530, loss: 0.23509721457958221
2023-01-21 08:55:54.832257: step: 1912/530, loss: 0.8576667308807373
2023-01-21 08:55:55.936301: step: 1916/530, loss: 0.349565327167511
2023-01-21 08:55:57.073682: step: 1920/530, loss: 0.18940743803977966
2023-01-21 08:55:58.237547: step: 1924/530, loss: 0.6548725366592407
2023-01-21 08:55:59.371709: step: 1928/530, loss: 1.9670281410217285
2023-01-21 08:56:00.472657: step: 1932/530, loss: 0.6714258193969727
2023-01-21 08:56:01.599933: step: 1936/530, loss: 0.04806642606854439
2023-01-21 08:56:02.740569: step: 1940/530, loss: 0.10305114090442657
2023-01-21 08:56:03.884715: step: 1944/530, loss: 0.422593891620636
2023-01-21 08:56:04.996924: step: 1948/530, loss: 0.7131737470626831
2023-01-21 08:56:06.098795: step: 1952/530, loss: 0.15087327361106873
2023-01-21 08:56:07.244941: step: 1956/530, loss: 0.7676081657409668
2023-01-21 08:56:08.383973: step: 1960/530, loss: 0.023475931957364082
2023-01-21 08:56:09.520097: step: 1964/530, loss: 1.2449216842651367
2023-01-21 08:56:10.633717: step: 1968/530, loss: 0.05243687331676483
2023-01-21 08:56:11.786371: step: 1972/530, loss: 0.22005577385425568
2023-01-21 08:56:12.908083: step: 1976/530, loss: 0.7210884094238281
2023-01-21 08:56:14.055725: step: 1980/530, loss: 0.15306778252124786
2023-01-21 08:56:15.199640: step: 1984/530, loss: 0.13331422209739685
2023-01-21 08:56:16.350400: step: 1988/530, loss: 0.18127784132957458
2023-01-21 08:56:17.512147: step: 1992/530, loss: 0.23089894652366638
2023-01-21 08:56:18.623082: step: 1996/530, loss: 0.7111529111862183
2023-01-21 08:56:19.745904: step: 2000/530, loss: 0.21061024069786072
2023-01-21 08:56:20.828815: step: 2004/530, loss: 0.4544907510280609
2023-01-21 08:56:21.923605: step: 2008/530, loss: 0.43710020184516907
2023-01-21 08:56:23.060242: step: 2012/530, loss: 0.3562057912349701
2023-01-21 08:56:24.160491: step: 2016/530, loss: 0.14166541397571564
2023-01-21 08:56:25.276937: step: 2020/530, loss: 0.19112272560596466
2023-01-21 08:56:26.406934: step: 2024/530, loss: 0.4822103977203369
2023-01-21 08:56:27.519909: step: 2028/530, loss: 0.515457272529602
2023-01-21 08:56:28.637099: step: 2032/530, loss: 0.195018008351326
2023-01-21 08:56:29.764844: step: 2036/530, loss: 0.9606984257698059
2023-01-21 08:56:30.889703: step: 2040/530, loss: 1.847872257232666
2023-01-21 08:56:32.012624: step: 2044/530, loss: 0.9115325212478638
2023-01-21 08:56:33.195777: step: 2048/530, loss: 1.8556472063064575
2023-01-21 08:56:34.308385: step: 2052/530, loss: 0.3390215039253235
2023-01-21 08:56:35.413794: step: 2056/530, loss: 0.32991498708724976
2023-01-21 08:56:36.562304: step: 2060/530, loss: 0.22730664908885956
2023-01-21 08:56:37.704683: step: 2064/530, loss: 0.16781559586524963
2023-01-21 08:56:38.853171: step: 2068/530, loss: 0.10911817848682404
2023-01-21 08:56:40.000059: step: 2072/530, loss: 1.1823575496673584
2023-01-21 08:56:41.140531: step: 2076/530, loss: 0.3871402442455292
2023-01-21 08:56:42.277819: step: 2080/530, loss: 0.12795454263687134
2023-01-21 08:56:43.399767: step: 2084/530, loss: 0.4788084030151367
2023-01-21 08:56:44.513009: step: 2088/530, loss: 0.45576614141464233
2023-01-21 08:56:45.650517: step: 2092/530, loss: 0.18033123016357422
2023-01-21 08:56:46.772099: step: 2096/530, loss: 0.8473040461540222
2023-01-21 08:56:47.857488: step: 2100/530, loss: 0.7381426692008972
2023-01-21 08:56:48.992918: step: 2104/530, loss: 1.4058525562286377
2023-01-21 08:56:50.113088: step: 2108/530, loss: 0.013858843594789505
2023-01-21 08:56:51.238457: step: 2112/530, loss: 0.75736004114151
2023-01-21 08:56:52.368603: step: 2116/530, loss: 0.3479897379875183
2023-01-21 08:56:53.490226: step: 2120/530, loss: 0.08949537575244904
==================================================
Loss: 0.599
--------------------
Dev: {'event': {'p': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5774647887323944, 'r': 0.7592592592592593, 'f1': 0.656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.5625, 'r': 0.5, 'f1': 0.5294117647058824}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5774647887323944, 'r': 0.7592592592592593, 'f1': 0.656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:57:48.920259: step: 4/530, loss: 0.17036724090576172
2023-01-21 08:57:50.047682: step: 8/530, loss: 0.16642971336841583
2023-01-21 08:57:51.209534: step: 12/530, loss: 0.34728074073791504
2023-01-21 08:57:52.321421: step: 16/530, loss: 0.23984479904174805
2023-01-21 08:57:53.456294: step: 20/530, loss: 1.1788955926895142
2023-01-21 08:57:54.603670: step: 24/530, loss: 0.1517195701599121
2023-01-21 08:57:55.738729: step: 28/530, loss: 0.9309684038162231
2023-01-21 08:57:56.867315: step: 32/530, loss: 0.027128791436553
2023-01-21 08:57:58.056904: step: 36/530, loss: 0.20915785431861877
2023-01-21 08:57:59.186262: step: 40/530, loss: 0.23358076810836792
2023-01-21 08:58:00.291729: step: 44/530, loss: 1.2669751644134521
2023-01-21 08:58:01.388397: step: 48/530, loss: 0.21642929315567017
2023-01-21 08:58:02.527821: step: 52/530, loss: 0.46964895725250244
2023-01-21 08:58:03.645425: step: 56/530, loss: 0.08487287163734436
2023-01-21 08:58:04.774933: step: 60/530, loss: 0.0885734111070633
2023-01-21 08:58:05.901613: step: 64/530, loss: 1.2772128582000732
2023-01-21 08:58:07.002444: step: 68/530, loss: 0.21787281334400177
2023-01-21 08:58:08.120714: step: 72/530, loss: 0.45431509613990784
2023-01-21 08:58:09.250852: step: 76/530, loss: 0.3456558585166931
2023-01-21 08:58:10.368112: step: 80/530, loss: 0.11414603888988495
2023-01-21 08:58:11.534210: step: 84/530, loss: 0.762995719909668
2023-01-21 08:58:12.652759: step: 88/530, loss: 0.17691020667552948
2023-01-21 08:58:13.764606: step: 92/530, loss: 0.4836730360984802
2023-01-21 08:58:14.880009: step: 96/530, loss: 7.069892883300781
2023-01-21 08:58:16.010795: step: 100/530, loss: 0.3584449887275696
2023-01-21 08:58:17.122866: step: 104/530, loss: 0.4535992741584778
2023-01-21 08:58:18.217244: step: 108/530, loss: 0.06003322824835777
2023-01-21 08:58:19.344649: step: 112/530, loss: 0.2212258279323578
2023-01-21 08:58:20.485856: step: 116/530, loss: 0.19721660017967224
2023-01-21 08:58:21.648449: step: 120/530, loss: 0.7173643112182617
2023-01-21 08:58:22.787343: step: 124/530, loss: 0.2072695791721344
2023-01-21 08:58:23.917791: step: 128/530, loss: 0.07194796204566956
2023-01-21 08:58:25.030651: step: 132/530, loss: 0.04120960459113121
2023-01-21 08:58:26.131938: step: 136/530, loss: 0.5953636765480042
2023-01-21 08:58:27.267555: step: 140/530, loss: 0.45882779359817505
2023-01-21 08:58:28.393556: step: 144/530, loss: 0.8287956118583679
2023-01-21 08:58:29.492022: step: 148/530, loss: 0.6020979881286621
2023-01-21 08:58:30.607252: step: 152/530, loss: 0.2859021723270416
2023-01-21 08:58:31.724838: step: 156/530, loss: 0.7586717009544373
2023-01-21 08:58:32.850877: step: 160/530, loss: 0.433019757270813
2023-01-21 08:58:33.952184: step: 164/530, loss: 0.09717945754528046
2023-01-21 08:58:35.077481: step: 168/530, loss: 0.0967007651925087
2023-01-21 08:58:36.193963: step: 172/530, loss: 1.19929039478302
2023-01-21 08:58:37.338153: step: 176/530, loss: 0.6184322237968445
2023-01-21 08:58:38.433972: step: 180/530, loss: 0.12002047896385193
2023-01-21 08:58:39.582719: step: 184/530, loss: 0.12334775924682617
2023-01-21 08:58:40.707511: step: 188/530, loss: 0.12159624695777893
2023-01-21 08:58:41.850336: step: 192/530, loss: 0.47953665256500244
2023-01-21 08:58:42.958929: step: 196/530, loss: 0.4455191195011139
2023-01-21 08:58:44.107701: step: 200/530, loss: 0.0381779670715332
2023-01-21 08:58:45.235986: step: 204/530, loss: 0.0698336586356163
2023-01-21 08:58:46.368518: step: 208/530, loss: 0.9178913235664368
2023-01-21 08:58:47.486821: step: 212/530, loss: 0.6019262671470642
2023-01-21 08:58:48.621456: step: 216/530, loss: 0.7543321847915649
2023-01-21 08:58:49.752484: step: 220/530, loss: 0.39735376834869385
2023-01-21 08:58:50.868609: step: 224/530, loss: 0.13671712577342987
2023-01-21 08:58:52.039163: step: 228/530, loss: 0.09299878776073456
2023-01-21 08:58:53.171004: step: 232/530, loss: 0.2131734937429428
2023-01-21 08:58:54.288538: step: 236/530, loss: 0.2404012829065323
2023-01-21 08:58:55.466821: step: 240/530, loss: 0.30490607023239136
2023-01-21 08:58:56.593159: step: 244/530, loss: 0.5144624710083008
2023-01-21 08:58:57.739000: step: 248/530, loss: 7.687002182006836
2023-01-21 08:58:58.897797: step: 252/530, loss: 0.1485731601715088
2023-01-21 08:59:00.024902: step: 256/530, loss: 0.7885928153991699
2023-01-21 08:59:01.171470: step: 260/530, loss: 0.8743067383766174
2023-01-21 08:59:02.341082: step: 264/530, loss: 0.1159951239824295
2023-01-21 08:59:03.429493: step: 268/530, loss: 0.08031110465526581
2023-01-21 08:59:04.541098: step: 272/530, loss: 6.587563991546631
2023-01-21 08:59:05.649474: step: 276/530, loss: 0.47947150468826294
2023-01-21 08:59:06.768423: step: 280/530, loss: 0.16153354942798615
2023-01-21 08:59:07.866788: step: 284/530, loss: 0.14447660744190216
2023-01-21 08:59:08.951279: step: 288/530, loss: 0.7117495536804199
2023-01-21 08:59:10.071259: step: 292/530, loss: 0.6613510847091675
2023-01-21 08:59:11.195011: step: 296/530, loss: 0.3186551034450531
2023-01-21 08:59:12.303762: step: 300/530, loss: 0.07023553550243378
2023-01-21 08:59:13.418423: step: 304/530, loss: 0.6561623811721802
2023-01-21 08:59:14.557905: step: 308/530, loss: 0.11302366107702255
2023-01-21 08:59:15.690788: step: 312/530, loss: 0.1771559715270996
2023-01-21 08:59:16.816380: step: 316/530, loss: 0.17372578382492065
2023-01-21 08:59:17.960511: step: 320/530, loss: 0.15440569818019867
2023-01-21 08:59:19.111477: step: 324/530, loss: 0.11930026859045029
2023-01-21 08:59:20.247244: step: 328/530, loss: 0.8409977555274963
2023-01-21 08:59:21.361082: step: 332/530, loss: 0.054646775126457214
2023-01-21 08:59:22.491790: step: 336/530, loss: 1.5318517684936523
2023-01-21 08:59:23.613606: step: 340/530, loss: 0.28302761912345886
2023-01-21 08:59:24.719591: step: 344/530, loss: 0.3082978129386902
2023-01-21 08:59:25.902541: step: 348/530, loss: 0.6703676581382751
2023-01-21 08:59:27.005068: step: 352/530, loss: 0.6897979378700256
2023-01-21 08:59:28.144456: step: 356/530, loss: 0.13538876175880432
2023-01-21 08:59:29.294312: step: 360/530, loss: 0.31450697779655457
2023-01-21 08:59:30.409503: step: 364/530, loss: 0.8024132251739502
2023-01-21 08:59:31.599423: step: 368/530, loss: 0.02173762395977974
2023-01-21 08:59:32.744421: step: 372/530, loss: 0.1503484696149826
2023-01-21 08:59:33.860863: step: 376/530, loss: 0.3332023620605469
2023-01-21 08:59:34.986367: step: 380/530, loss: 0.1747463196516037
2023-01-21 08:59:36.098698: step: 384/530, loss: 1.2421914339065552
2023-01-21 08:59:37.228728: step: 388/530, loss: 0.26384490728378296
2023-01-21 08:59:38.370087: step: 392/530, loss: 0.11498914659023285
2023-01-21 08:59:39.497430: step: 396/530, loss: 0.08179517090320587
2023-01-21 08:59:40.613212: step: 400/530, loss: 0.8759828209877014
2023-01-21 08:59:41.774844: step: 404/530, loss: 0.13246408104896545
2023-01-21 08:59:42.903049: step: 408/530, loss: 1.139804482460022
2023-01-21 08:59:44.029698: step: 412/530, loss: 0.08743028342723846
2023-01-21 08:59:45.134928: step: 416/530, loss: 0.7635576725006104
2023-01-21 08:59:46.248576: step: 420/530, loss: 0.9492528438568115
2023-01-21 08:59:47.388229: step: 424/530, loss: 0.03791513666510582
2023-01-21 08:59:48.520757: step: 428/530, loss: 0.0655418410897255
2023-01-21 08:59:49.650273: step: 432/530, loss: 0.17578358948230743
2023-01-21 08:59:50.784167: step: 436/530, loss: 0.11343555152416229
2023-01-21 08:59:51.860735: step: 440/530, loss: 0.6295663714408875
2023-01-21 08:59:52.993623: step: 444/530, loss: 1.0501545667648315
2023-01-21 08:59:54.138894: step: 448/530, loss: 0.004906797781586647
2023-01-21 08:59:55.262936: step: 452/530, loss: 0.17903494834899902
2023-01-21 08:59:56.391287: step: 456/530, loss: 0.14512687921524048
2023-01-21 08:59:57.499898: step: 460/530, loss: 0.039325617253780365
2023-01-21 08:59:58.640962: step: 464/530, loss: 0.09596538543701172
2023-01-21 08:59:59.766685: step: 468/530, loss: 5.930542469024658
2023-01-21 09:00:00.894817: step: 472/530, loss: 0.06485719978809357
2023-01-21 09:00:02.025319: step: 476/530, loss: 0.595467746257782
2023-01-21 09:00:03.140173: step: 480/530, loss: 0.07808828353881836
2023-01-21 09:00:04.253854: step: 484/530, loss: 0.4855794906616211
2023-01-21 09:00:05.366210: step: 488/530, loss: 0.7745007872581482
2023-01-21 09:00:06.500305: step: 492/530, loss: 0.05012564733624458
2023-01-21 09:00:07.634980: step: 496/530, loss: 0.05086483806371689
2023-01-21 09:00:08.776283: step: 500/530, loss: 1.30084228515625
2023-01-21 09:00:09.880633: step: 504/530, loss: 0.31470975279808044
2023-01-21 09:00:11.012828: step: 508/530, loss: 0.2153313159942627
2023-01-21 09:00:12.124939: step: 512/530, loss: 0.3217411935329437
2023-01-21 09:00:13.227548: step: 516/530, loss: 0.08524914085865021
2023-01-21 09:00:14.345655: step: 520/530, loss: 0.7159448266029358
2023-01-21 09:00:15.453858: step: 524/530, loss: 6.960169315338135
2023-01-21 09:00:16.594031: step: 528/530, loss: 0.1907837986946106
2023-01-21 09:00:17.710670: step: 532/530, loss: 0.8664283156394958
2023-01-21 09:00:18.813909: step: 536/530, loss: 0.3343973755836487
2023-01-21 09:00:19.932909: step: 540/530, loss: 0.36517515778541565
2023-01-21 09:00:21.048897: step: 544/530, loss: 0.47974395751953125
2023-01-21 09:00:22.156116: step: 548/530, loss: 0.6829677224159241
2023-01-21 09:00:23.287543: step: 552/530, loss: 0.15357132256031036
2023-01-21 09:00:24.408853: step: 556/530, loss: 1.2117977142333984
2023-01-21 09:00:25.535735: step: 560/530, loss: 0.11820311099290848
2023-01-21 09:00:26.645776: step: 564/530, loss: 0.11121435463428497
2023-01-21 09:00:27.790436: step: 568/530, loss: 0.14728155732154846
2023-01-21 09:00:28.919679: step: 572/530, loss: 0.22958365082740784
2023-01-21 09:00:30.054421: step: 576/530, loss: 0.14843511581420898
2023-01-21 09:00:31.158514: step: 580/530, loss: 0.03653326258063316
2023-01-21 09:00:32.343651: step: 584/530, loss: 0.7637840509414673
2023-01-21 09:00:33.443079: step: 588/530, loss: 0.7900869250297546
2023-01-21 09:00:34.561367: step: 592/530, loss: 0.6163390278816223
2023-01-21 09:00:35.660406: step: 596/530, loss: 0.16181430220603943
2023-01-21 09:00:36.782438: step: 600/530, loss: 0.05414404720067978
2023-01-21 09:00:37.920050: step: 604/530, loss: 0.424004465341568
2023-01-21 09:00:39.072877: step: 608/530, loss: 0.055150412023067474
2023-01-21 09:00:40.194262: step: 612/530, loss: 0.20257851481437683
2023-01-21 09:00:41.319122: step: 616/530, loss: 1.4594733715057373
2023-01-21 09:00:42.435571: step: 620/530, loss: 0.28739339113235474
2023-01-21 09:00:43.608703: step: 624/530, loss: 0.40655574202537537
2023-01-21 09:00:44.701142: step: 628/530, loss: 0.7748737335205078
2023-01-21 09:00:45.822557: step: 632/530, loss: 0.08959989249706268
2023-01-21 09:00:46.912014: step: 636/530, loss: 0.031038235872983932
2023-01-21 09:00:48.006511: step: 640/530, loss: 0.08690023422241211
2023-01-21 09:00:49.135553: step: 644/530, loss: 0.1289418339729309
2023-01-21 09:00:50.271610: step: 648/530, loss: 0.12941542267799377
2023-01-21 09:00:51.388123: step: 652/530, loss: 0.039647866040468216
2023-01-21 09:00:52.531730: step: 656/530, loss: 0.20582933723926544
2023-01-21 09:00:53.644606: step: 660/530, loss: 0.19206447899341583
2023-01-21 09:00:54.796040: step: 664/530, loss: 1.1911507844924927
2023-01-21 09:00:55.921601: step: 668/530, loss: 0.2263558804988861
2023-01-21 09:00:57.043378: step: 672/530, loss: 0.3241848647594452
2023-01-21 09:00:58.147929: step: 676/530, loss: 0.12599745392799377
2023-01-21 09:00:59.260659: step: 680/530, loss: 0.1579577475786209
2023-01-21 09:01:00.384142: step: 684/530, loss: 0.17495307326316833
2023-01-21 09:01:01.539825: step: 688/530, loss: 0.12659373879432678
2023-01-21 09:01:02.691134: step: 692/530, loss: 0.29097747802734375
2023-01-21 09:01:03.834266: step: 696/530, loss: 0.3467721939086914
2023-01-21 09:01:04.925411: step: 700/530, loss: 0.1125221773982048
2023-01-21 09:01:06.036003: step: 704/530, loss: 0.13981495797634125
2023-01-21 09:01:07.160540: step: 708/530, loss: 0.41114577651023865
2023-01-21 09:01:08.296956: step: 712/530, loss: 0.11268831044435501
2023-01-21 09:01:09.420841: step: 716/530, loss: 0.6382874250411987
2023-01-21 09:01:10.528391: step: 720/530, loss: 0.13899879157543182
2023-01-21 09:01:11.657883: step: 724/530, loss: 0.29497337341308594
2023-01-21 09:01:12.794176: step: 728/530, loss: 0.1831246018409729
2023-01-21 09:01:13.963682: step: 732/530, loss: 0.6397929191589355
2023-01-21 09:01:15.106385: step: 736/530, loss: 0.14032816886901855
2023-01-21 09:01:16.231420: step: 740/530, loss: 0.12659473717212677
2023-01-21 09:01:17.360220: step: 744/530, loss: 0.2427208125591278
2023-01-21 09:01:18.479683: step: 748/530, loss: 0.13204193115234375
2023-01-21 09:01:19.614105: step: 752/530, loss: 0.18585357069969177
2023-01-21 09:01:20.729774: step: 756/530, loss: 0.046698667109012604
2023-01-21 09:01:21.849392: step: 760/530, loss: 0.05091409757733345
2023-01-21 09:01:22.973505: step: 764/530, loss: 0.31775951385498047
2023-01-21 09:01:24.100698: step: 768/530, loss: 0.24497456848621368
2023-01-21 09:01:25.232562: step: 772/530, loss: 0.34144461154937744
2023-01-21 09:01:26.366317: step: 776/530, loss: 0.2530684471130371
2023-01-21 09:01:27.478094: step: 780/530, loss: 0.6524829268455505
2023-01-21 09:01:28.624664: step: 784/530, loss: 0.5054017901420593
2023-01-21 09:01:29.767533: step: 788/530, loss: 0.3866092562675476
2023-01-21 09:01:30.894735: step: 792/530, loss: 0.3562334179878235
2023-01-21 09:01:32.017790: step: 796/530, loss: 0.2593211233615875
2023-01-21 09:01:33.136567: step: 800/530, loss: 0.05630688741803169
2023-01-21 09:01:34.253601: step: 804/530, loss: 0.5241835117340088
2023-01-21 09:01:35.384269: step: 808/530, loss: 1.4336533546447754
2023-01-21 09:01:36.571161: step: 812/530, loss: 0.25675326585769653
2023-01-21 09:01:37.691748: step: 816/530, loss: 0.2492874264717102
2023-01-21 09:01:38.800776: step: 820/530, loss: 0.3151586651802063
2023-01-21 09:01:39.904591: step: 824/530, loss: 0.09283819794654846
2023-01-21 09:01:41.036250: step: 828/530, loss: 0.11414463818073273
2023-01-21 09:01:42.186660: step: 832/530, loss: 0.7769097089767456
2023-01-21 09:01:43.335236: step: 836/530, loss: 0.20338688790798187
2023-01-21 09:01:44.486650: step: 840/530, loss: 0.9682126045227051
2023-01-21 09:01:45.622579: step: 844/530, loss: 0.4638552665710449
2023-01-21 09:01:46.771341: step: 848/530, loss: 0.7936142683029175
2023-01-21 09:01:47.876541: step: 852/530, loss: 0.16188031435012817
2023-01-21 09:01:48.978430: step: 856/530, loss: 0.07353615760803223
2023-01-21 09:01:50.109635: step: 860/530, loss: 0.10312461853027344
2023-01-21 09:01:51.214732: step: 864/530, loss: 0.10354427993297577
2023-01-21 09:01:52.327050: step: 868/530, loss: 0.23886442184448242
2023-01-21 09:01:53.435877: step: 872/530, loss: 0.31222569942474365
2023-01-21 09:01:54.551272: step: 876/530, loss: 0.08500252664089203
2023-01-21 09:01:55.709900: step: 880/530, loss: 0.30035269260406494
2023-01-21 09:01:56.823148: step: 884/530, loss: 0.28802254796028137
2023-01-21 09:01:57.887364: step: 888/530, loss: 0.04839920997619629
2023-01-21 09:01:59.010116: step: 892/530, loss: 0.539877712726593
2023-01-21 09:02:00.142058: step: 896/530, loss: 0.710597813129425
2023-01-21 09:02:01.265227: step: 900/530, loss: 0.21863803267478943
2023-01-21 09:02:02.375825: step: 904/530, loss: 1.9587645530700684
2023-01-21 09:02:03.512445: step: 908/530, loss: 0.23699207603931427
2023-01-21 09:02:04.627493: step: 912/530, loss: 0.7093230485916138
2023-01-21 09:02:05.755068: step: 916/530, loss: 0.6573853492736816
2023-01-21 09:02:06.866286: step: 920/530, loss: 0.19469384849071503
2023-01-21 09:02:07.968994: step: 924/530, loss: 0.5714029669761658
2023-01-21 09:02:09.112012: step: 928/530, loss: 0.25678300857543945
2023-01-21 09:02:10.237656: step: 932/530, loss: 0.1119375228881836
2023-01-21 09:02:11.366187: step: 936/530, loss: 0.0706668347120285
2023-01-21 09:02:12.487079: step: 940/530, loss: 0.2677582800388336
2023-01-21 09:02:13.579896: step: 944/530, loss: 0.10434536635875702
2023-01-21 09:02:14.695156: step: 948/530, loss: 0.35396918654441833
2023-01-21 09:02:15.851665: step: 952/530, loss: 0.7816277742385864
2023-01-21 09:02:16.964772: step: 956/530, loss: 6.337296962738037
2023-01-21 09:02:18.076083: step: 960/530, loss: 0.04668422043323517
2023-01-21 09:02:19.230968: step: 964/530, loss: 0.2845540940761566
2023-01-21 09:02:20.351573: step: 968/530, loss: 0.11601004749536514
2023-01-21 09:02:21.482635: step: 972/530, loss: 0.869560718536377
2023-01-21 09:02:22.586896: step: 976/530, loss: 0.18167667090892792
2023-01-21 09:02:23.730832: step: 980/530, loss: 0.4020606279373169
2023-01-21 09:02:24.843242: step: 984/530, loss: 0.12131624668836594
2023-01-21 09:02:25.977468: step: 988/530, loss: 0.2102939486503601
2023-01-21 09:02:27.132823: step: 992/530, loss: 0.44801560044288635
2023-01-21 09:02:28.247496: step: 996/530, loss: 0.13658258318901062
2023-01-21 09:02:29.387101: step: 1000/530, loss: 0.3587406873703003
2023-01-21 09:02:30.506622: step: 1004/530, loss: 0.16822342574596405
2023-01-21 09:02:31.663794: step: 1008/530, loss: 0.24062567949295044
2023-01-21 09:02:32.830502: step: 1012/530, loss: 0.12505730986595154
2023-01-21 09:02:33.999743: step: 1016/530, loss: 0.5557454228401184
2023-01-21 09:02:35.125681: step: 1020/530, loss: 0.693396270275116
2023-01-21 09:02:36.235820: step: 1024/530, loss: 0.1114506721496582
2023-01-21 09:02:37.371177: step: 1028/530, loss: 0.21157866716384888
2023-01-21 09:02:38.500086: step: 1032/530, loss: 0.4216056764125824
2023-01-21 09:02:39.634797: step: 1036/530, loss: 0.32248449325561523
2023-01-21 09:02:40.771254: step: 1040/530, loss: 0.1275119185447693
2023-01-21 09:02:41.882416: step: 1044/530, loss: 0.142400324344635
2023-01-21 09:02:43.006423: step: 1048/530, loss: 0.7415033578872681
2023-01-21 09:02:44.110759: step: 1052/530, loss: 0.2202221006155014
2023-01-21 09:02:45.231299: step: 1056/530, loss: 0.0769352912902832
2023-01-21 09:02:46.372547: step: 1060/530, loss: 0.42288094758987427
2023-01-21 09:02:47.476546: step: 1064/530, loss: 0.09324227273464203
2023-01-21 09:02:48.594325: step: 1068/530, loss: 1.3253374099731445
2023-01-21 09:02:49.729309: step: 1072/530, loss: 0.7777339220046997
2023-01-21 09:02:50.855726: step: 1076/530, loss: 0.08843765407800674
2023-01-21 09:02:51.999061: step: 1080/530, loss: 0.4438443183898926
2023-01-21 09:02:53.128589: step: 1084/530, loss: 0.2560030519962311
2023-01-21 09:02:54.217181: step: 1088/530, loss: 0.06521987915039062
2023-01-21 09:02:55.345568: step: 1092/530, loss: 0.739310085773468
2023-01-21 09:02:56.452035: step: 1096/530, loss: 0.13745641708374023
2023-01-21 09:02:57.579495: step: 1100/530, loss: 1.1782341003417969
2023-01-21 09:02:58.702247: step: 1104/530, loss: 0.16865158081054688
2023-01-21 09:02:59.825894: step: 1108/530, loss: 0.1872844696044922
2023-01-21 09:03:00.977989: step: 1112/530, loss: 0.6049100160598755
2023-01-21 09:03:02.154383: step: 1116/530, loss: 0.6019338369369507
2023-01-21 09:03:03.277485: step: 1120/530, loss: 0.42210477590560913
2023-01-21 09:03:04.390510: step: 1124/530, loss: 0.28427088260650635
2023-01-21 09:03:05.540242: step: 1128/530, loss: 0.08407735824584961
2023-01-21 09:03:06.707594: step: 1132/530, loss: 0.6136186718940735
2023-01-21 09:03:07.849019: step: 1136/530, loss: 0.11276464909315109
2023-01-21 09:03:08.964730: step: 1140/530, loss: 0.4786517024040222
2023-01-21 09:03:10.094353: step: 1144/530, loss: 0.3155521750450134
2023-01-21 09:03:11.219879: step: 1148/530, loss: 1.332437515258789
2023-01-21 09:03:12.311640: step: 1152/530, loss: 0.38677850365638733
2023-01-21 09:03:13.452800: step: 1156/530, loss: 0.19574908912181854
2023-01-21 09:03:14.563679: step: 1160/530, loss: 0.1790851205587387
2023-01-21 09:03:15.706676: step: 1164/530, loss: 0.3607296943664551
2023-01-21 09:03:16.846366: step: 1168/530, loss: 0.8320285081863403
2023-01-21 09:03:17.955308: step: 1172/530, loss: 0.1929721236228943
2023-01-21 09:03:19.077754: step: 1176/530, loss: 1.0880717039108276
2023-01-21 09:03:20.206808: step: 1180/530, loss: 0.17029863595962524
2023-01-21 09:03:21.336932: step: 1184/530, loss: 0.30269670486450195
2023-01-21 09:03:22.452220: step: 1188/530, loss: 0.36966878175735474
2023-01-21 09:03:23.602106: step: 1192/530, loss: 0.09792809933423996
2023-01-21 09:03:24.751250: step: 1196/530, loss: 0.13636694848537445
2023-01-21 09:03:25.862855: step: 1200/530, loss: 0.3022838830947876
2023-01-21 09:03:26.972364: step: 1204/530, loss: 0.34465765953063965
2023-01-21 09:03:28.099896: step: 1208/530, loss: 0.4255351126194
2023-01-21 09:03:29.218640: step: 1212/530, loss: 0.07824020087718964
2023-01-21 09:03:30.355742: step: 1216/530, loss: 0.9964789748191833
2023-01-21 09:03:31.484192: step: 1220/530, loss: 0.047849610447883606
2023-01-21 09:03:32.591095: step: 1224/530, loss: 0.15184727311134338
2023-01-21 09:03:33.711638: step: 1228/530, loss: 0.1626778542995453
2023-01-21 09:03:34.860777: step: 1232/530, loss: 0.10159101337194443
2023-01-21 09:03:35.973676: step: 1236/530, loss: 0.10504229366779327
2023-01-21 09:03:37.106382: step: 1240/530, loss: 0.5259441137313843
2023-01-21 09:03:38.220262: step: 1244/530, loss: 8.02356243133545
2023-01-21 09:03:39.338531: step: 1248/530, loss: 0.21302662789821625
2023-01-21 09:03:40.475329: step: 1252/530, loss: 0.3146812319755554
2023-01-21 09:03:41.581304: step: 1256/530, loss: 0.11408501118421555
2023-01-21 09:03:42.698691: step: 1260/530, loss: 0.7517045736312866
2023-01-21 09:03:43.815827: step: 1264/530, loss: 0.7985848188400269
2023-01-21 09:03:44.925290: step: 1268/530, loss: 0.27232933044433594
2023-01-21 09:03:46.037495: step: 1272/530, loss: 0.31952157616615295
2023-01-21 09:03:47.168588: step: 1276/530, loss: 0.21916276216506958
2023-01-21 09:03:48.286237: step: 1280/530, loss: 0.04496030882000923
2023-01-21 09:03:49.434033: step: 1284/530, loss: 0.11020383983850479
2023-01-21 09:03:50.538770: step: 1288/530, loss: 0.18361882865428925
2023-01-21 09:03:51.665093: step: 1292/530, loss: 0.4127759039402008
2023-01-21 09:03:52.774111: step: 1296/530, loss: 0.16507530212402344
2023-01-21 09:03:53.904272: step: 1300/530, loss: 0.19806194305419922
2023-01-21 09:03:54.992021: step: 1304/530, loss: 0.04165811464190483
2023-01-21 09:03:56.104449: step: 1308/530, loss: 0.1296827346086502
2023-01-21 09:03:57.236316: step: 1312/530, loss: 0.1720447540283203
2023-01-21 09:03:58.373728: step: 1316/530, loss: 0.9106971621513367
2023-01-21 09:03:59.533870: step: 1320/530, loss: 0.2494775801897049
2023-01-21 09:04:00.655502: step: 1324/530, loss: 0.38870009779930115
2023-01-21 09:04:01.759324: step: 1328/530, loss: 0.13143309950828552
2023-01-21 09:04:02.877774: step: 1332/530, loss: 0.3807516098022461
2023-01-21 09:04:04.005898: step: 1336/530, loss: 0.43951416015625
2023-01-21 09:04:05.138365: step: 1340/530, loss: 0.8405409455299377
2023-01-21 09:04:06.253355: step: 1344/530, loss: 0.142801433801651
2023-01-21 09:04:07.323482: step: 1348/530, loss: 0.1895488202571869
2023-01-21 09:04:08.454039: step: 1352/530, loss: 0.2847919464111328
2023-01-21 09:04:09.544492: step: 1356/530, loss: 0.07428627461194992
2023-01-21 09:04:10.670805: step: 1360/530, loss: 0.07416939735412598
2023-01-21 09:04:11.809918: step: 1364/530, loss: 0.11670255661010742
2023-01-21 09:04:12.923838: step: 1368/530, loss: 0.2198708951473236
2023-01-21 09:04:14.068964: step: 1372/530, loss: 0.08131561428308487
2023-01-21 09:04:15.203153: step: 1376/530, loss: 0.208016499876976
2023-01-21 09:04:16.313639: step: 1380/530, loss: 0.08762387931346893
2023-01-21 09:04:17.440301: step: 1384/530, loss: 0.3269149661064148
2023-01-21 09:04:18.581015: step: 1388/530, loss: 0.2431713044643402
2023-01-21 09:04:19.718381: step: 1392/530, loss: 0.6110830307006836
2023-01-21 09:04:20.844051: step: 1396/530, loss: 0.0643744021654129
2023-01-21 09:04:21.990364: step: 1400/530, loss: 1.9066836833953857
2023-01-21 09:04:23.110266: step: 1404/530, loss: 0.514267086982727
2023-01-21 09:04:24.229028: step: 1408/530, loss: 0.16873283684253693
2023-01-21 09:04:25.370330: step: 1412/530, loss: 0.2858301103115082
2023-01-21 09:04:26.503031: step: 1416/530, loss: 0.19447803497314453
2023-01-21 09:04:27.617273: step: 1420/530, loss: 0.7655235528945923
2023-01-21 09:04:28.745933: step: 1424/530, loss: 0.9057453274726868
2023-01-21 09:04:29.864086: step: 1428/530, loss: 0.2897835969924927
2023-01-21 09:04:31.006936: step: 1432/530, loss: 0.18510980904102325
2023-01-21 09:04:32.156382: step: 1436/530, loss: 0.11482544243335724
2023-01-21 09:04:33.273911: step: 1440/530, loss: 0.07887572795152664
2023-01-21 09:04:34.400606: step: 1444/530, loss: 0.20164881646633148
2023-01-21 09:04:35.528673: step: 1448/530, loss: 0.48689284920692444
2023-01-21 09:04:36.650068: step: 1452/530, loss: 0.045612335205078125
2023-01-21 09:04:37.777232: step: 1456/530, loss: 0.677822470664978
2023-01-21 09:04:38.882018: step: 1460/530, loss: 0.8919574022293091
2023-01-21 09:04:39.996306: step: 1464/530, loss: 0.160923570394516
2023-01-21 09:04:41.125136: step: 1468/530, loss: 0.14006395637989044
2023-01-21 09:04:42.223126: step: 1472/530, loss: 0.1263522207736969
2023-01-21 09:04:43.374739: step: 1476/530, loss: 0.04875602945685387
2023-01-21 09:04:44.495616: step: 1480/530, loss: 0.11507539451122284
2023-01-21 09:04:45.591654: step: 1484/530, loss: 0.4592326283454895
2023-01-21 09:04:46.706861: step: 1488/530, loss: 0.9233525395393372
2023-01-21 09:04:47.823049: step: 1492/530, loss: 0.21476107835769653
2023-01-21 09:04:48.932566: step: 1496/530, loss: 0.05584440380334854
2023-01-21 09:04:50.036567: step: 1500/530, loss: 0.05728616937994957
2023-01-21 09:04:51.139817: step: 1504/530, loss: 0.9771144390106201
2023-01-21 09:04:52.257271: step: 1508/530, loss: 0.3630111515522003
2023-01-21 09:04:53.375257: step: 1512/530, loss: 0.12333698570728302
2023-01-21 09:04:54.529807: step: 1516/530, loss: 0.2548215985298157
2023-01-21 09:04:55.667566: step: 1520/530, loss: 0.6190086603164673
2023-01-21 09:04:56.803492: step: 1524/530, loss: 0.2342969924211502
2023-01-21 09:04:57.924613: step: 1528/530, loss: 0.34411242604255676
2023-01-21 09:04:59.034108: step: 1532/530, loss: 0.21410337090492249
2023-01-21 09:05:00.162182: step: 1536/530, loss: 1.0242745876312256
2023-01-21 09:05:01.289975: step: 1540/530, loss: 0.13568997383117676
2023-01-21 09:05:02.412291: step: 1544/530, loss: 0.2209858000278473
2023-01-21 09:05:03.529015: step: 1548/530, loss: 0.026560211554169655
2023-01-21 09:05:04.681018: step: 1552/530, loss: 0.23429393768310547
2023-01-21 09:05:05.770401: step: 1556/530, loss: 0.04659919813275337
2023-01-21 09:05:06.910918: step: 1560/530, loss: 0.9354751706123352
2023-01-21 09:05:08.038987: step: 1564/530, loss: 0.5804479122161865
2023-01-21 09:05:09.167886: step: 1568/530, loss: 0.36770325899124146
2023-01-21 09:05:10.284551: step: 1572/530, loss: 0.09268569946289062
2023-01-21 09:05:11.376700: step: 1576/530, loss: 0.07004991173744202
2023-01-21 09:05:12.495593: step: 1580/530, loss: 0.48980700969696045
2023-01-21 09:05:13.628918: step: 1584/530, loss: 0.585756778717041
2023-01-21 09:05:14.747714: step: 1588/530, loss: 0.09195587784051895
2023-01-21 09:05:15.865718: step: 1592/530, loss: 0.32577866315841675
2023-01-21 09:05:16.972338: step: 1596/530, loss: 0.04666896164417267
2023-01-21 09:05:18.130855: step: 1600/530, loss: 6.151769161224365
2023-01-21 09:05:19.252195: step: 1604/530, loss: 0.13677054643630981
2023-01-21 09:05:20.382228: step: 1608/530, loss: 0.7264582514762878
2023-01-21 09:05:21.501601: step: 1612/530, loss: 0.44529154896736145
2023-01-21 09:05:22.660528: step: 1616/530, loss: 0.26551979780197144
2023-01-21 09:05:23.792304: step: 1620/530, loss: 0.18485456705093384
2023-01-21 09:05:24.926236: step: 1624/530, loss: 0.5798535346984863
2023-01-21 09:05:26.052217: step: 1628/530, loss: 0.13767534494400024
2023-01-21 09:05:27.196561: step: 1632/530, loss: 1.4618440866470337
2023-01-21 09:05:28.309541: step: 1636/530, loss: 0.06379413604736328
2023-01-21 09:05:29.441413: step: 1640/530, loss: 0.12085109204053879
2023-01-21 09:05:30.560499: step: 1644/530, loss: 0.5972986221313477
2023-01-21 09:05:31.672743: step: 1648/530, loss: 0.17446888983249664
2023-01-21 09:05:32.769128: step: 1652/530, loss: 0.7446853518486023
2023-01-21 09:05:33.923452: step: 1656/530, loss: 0.1470375657081604
2023-01-21 09:05:35.030791: step: 1660/530, loss: 0.5677639842033386
2023-01-21 09:05:36.159528: step: 1664/530, loss: 0.28879988193511963
2023-01-21 09:05:37.275136: step: 1668/530, loss: 0.1233987808227539
2023-01-21 09:05:38.401048: step: 1672/530, loss: 0.36274638772010803
2023-01-21 09:05:39.519831: step: 1676/530, loss: 0.13657522201538086
2023-01-21 09:05:40.634504: step: 1680/530, loss: 0.8815388679504395
2023-01-21 09:05:41.738927: step: 1684/530, loss: 0.33287304639816284
2023-01-21 09:05:42.841023: step: 1688/530, loss: 0.5164784789085388
2023-01-21 09:05:43.979536: step: 1692/530, loss: 0.42818278074264526
2023-01-21 09:05:45.093625: step: 1696/530, loss: 0.035449910908937454
2023-01-21 09:05:46.219301: step: 1700/530, loss: 0.2492295801639557
2023-01-21 09:05:47.346816: step: 1704/530, loss: 0.16623243689537048
2023-01-21 09:05:48.466597: step: 1708/530, loss: 1.0236146450042725
2023-01-21 09:05:49.601603: step: 1712/530, loss: 0.1681804656982422
2023-01-21 09:05:50.718860: step: 1716/530, loss: 0.3860305845737457
2023-01-21 09:05:51.819605: step: 1720/530, loss: 0.2120051383972168
2023-01-21 09:05:52.918624: step: 1724/530, loss: 0.7842609286308289
2023-01-21 09:05:54.033103: step: 1728/530, loss: 1.6515214443206787
2023-01-21 09:05:55.158741: step: 1732/530, loss: 0.13141250610351562
2023-01-21 09:05:56.255630: step: 1736/530, loss: 0.08918621391057968
2023-01-21 09:05:57.346152: step: 1740/530, loss: 0.16304850578308105
2023-01-21 09:05:58.480079: step: 1744/530, loss: 2.0773239135742188
2023-01-21 09:05:59.627261: step: 1748/530, loss: 1.048683524131775
2023-01-21 09:06:00.748141: step: 1752/530, loss: 0.17725367844104767
2023-01-21 09:06:01.836061: step: 1756/530, loss: 0.6948029398918152
2023-01-21 09:06:02.964553: step: 1760/530, loss: 1.403632640838623
2023-01-21 09:06:04.072436: step: 1764/530, loss: 0.21824435889720917
2023-01-21 09:06:05.200291: step: 1768/530, loss: 0.7054895162582397
2023-01-21 09:06:06.306832: step: 1772/530, loss: 0.22495470941066742
2023-01-21 09:06:07.427623: step: 1776/530, loss: 0.49282923340797424
2023-01-21 09:06:08.549740: step: 1780/530, loss: 0.18711167573928833
2023-01-21 09:06:09.669312: step: 1784/530, loss: 0.07118716835975647
2023-01-21 09:06:10.816799: step: 1788/530, loss: 0.45792192220687866
2023-01-21 09:06:11.941400: step: 1792/530, loss: 0.11594811081886292
2023-01-21 09:06:13.071621: step: 1796/530, loss: 0.5197655558586121
2023-01-21 09:06:14.192129: step: 1800/530, loss: 0.7505996823310852
2023-01-21 09:06:15.318785: step: 1804/530, loss: 0.8414021730422974
2023-01-21 09:06:16.454353: step: 1808/530, loss: 1.1111630201339722
2023-01-21 09:06:17.584870: step: 1812/530, loss: 0.25381165742874146
2023-01-21 09:06:18.690987: step: 1816/530, loss: 0.32689225673675537
2023-01-21 09:06:19.809026: step: 1820/530, loss: 0.1935802400112152
2023-01-21 09:06:20.952457: step: 1824/530, loss: 0.08370056003332138
2023-01-21 09:06:22.039296: step: 1828/530, loss: 0.21775542199611664
2023-01-21 09:06:23.170487: step: 1832/530, loss: 0.29918763041496277
2023-01-21 09:06:24.306082: step: 1836/530, loss: 0.12295322120189667
2023-01-21 09:06:25.438176: step: 1840/530, loss: 0.7260211706161499
2023-01-21 09:06:26.558241: step: 1844/530, loss: 0.1619025319814682
2023-01-21 09:06:27.670246: step: 1848/530, loss: 0.06291775405406952
2023-01-21 09:06:28.778896: step: 1852/530, loss: 0.2906424105167389
2023-01-21 09:06:29.899966: step: 1856/530, loss: 0.23726846277713776
2023-01-21 09:06:31.037784: step: 1860/530, loss: 0.5974012613296509
2023-01-21 09:06:32.156210: step: 1864/530, loss: 0.6490985155105591
2023-01-21 09:06:33.271550: step: 1868/530, loss: 0.51610267162323
2023-01-21 09:06:34.393928: step: 1872/530, loss: 0.10148139297962189
2023-01-21 09:06:35.508821: step: 1876/530, loss: 0.5994809865951538
2023-01-21 09:06:36.622434: step: 1880/530, loss: 0.09673991054296494
2023-01-21 09:06:37.730513: step: 1884/530, loss: 0.6247178912162781
2023-01-21 09:06:38.862081: step: 1888/530, loss: 0.1039685308933258
2023-01-21 09:06:40.001528: step: 1892/530, loss: 0.4099477529525757
2023-01-21 09:06:41.116223: step: 1896/530, loss: 0.8992904424667358
2023-01-21 09:06:42.223732: step: 1900/530, loss: 0.583234965801239
2023-01-21 09:06:43.341497: step: 1904/530, loss: 0.3806690275669098
2023-01-21 09:06:44.449691: step: 1908/530, loss: 0.5566908121109009
2023-01-21 09:06:45.604716: step: 1912/530, loss: 0.11651559919118881
2023-01-21 09:06:46.724751: step: 1916/530, loss: 1.0576083660125732
2023-01-21 09:06:47.879947: step: 1920/530, loss: 0.16118082404136658
2023-01-21 09:06:49.013029: step: 1924/530, loss: 0.12736625969409943
2023-01-21 09:06:50.118953: step: 1928/530, loss: 0.13824300467967987
2023-01-21 09:06:51.234342: step: 1932/530, loss: 0.41821566224098206
2023-01-21 09:06:52.349341: step: 1936/530, loss: 0.7704918384552002
2023-01-21 09:06:53.497803: step: 1940/530, loss: 0.7969303131103516
2023-01-21 09:06:54.618717: step: 1944/530, loss: 0.08521604537963867
2023-01-21 09:06:55.751454: step: 1948/530, loss: 0.07951287925243378
2023-01-21 09:06:56.857040: step: 1952/530, loss: 0.17035618424415588
2023-01-21 09:06:57.957758: step: 1956/530, loss: 0.10889606177806854
2023-01-21 09:06:59.103442: step: 1960/530, loss: 6.4887003898620605
2023-01-21 09:07:00.236406: step: 1964/530, loss: 0.046761225908994675
2023-01-21 09:07:01.361600: step: 1968/530, loss: 0.006165886297821999
2023-01-21 09:07:02.483400: step: 1972/530, loss: 0.035973500460386276
2023-01-21 09:07:03.566827: step: 1976/530, loss: 0.04148568958044052
2023-01-21 09:07:04.657960: step: 1980/530, loss: 2.423964500427246
2023-01-21 09:07:05.823678: step: 1984/530, loss: 1.4673709869384766
2023-01-21 09:07:06.949200: step: 1988/530, loss: 2.032862663269043
2023-01-21 09:07:08.059063: step: 1992/530, loss: 1.201643466949463
2023-01-21 09:07:09.191656: step: 1996/530, loss: 0.1756226122379303
2023-01-21 09:07:10.365109: step: 2000/530, loss: 0.24756136536598206
2023-01-21 09:07:11.494358: step: 2004/530, loss: 0.26147061586380005
2023-01-21 09:07:12.647430: step: 2008/530, loss: 0.5023872256278992
2023-01-21 09:07:13.757150: step: 2012/530, loss: 0.18697504699230194
2023-01-21 09:07:14.910754: step: 2016/530, loss: 0.7710103988647461
2023-01-21 09:07:16.035200: step: 2020/530, loss: 0.4787195324897766
2023-01-21 09:07:17.159326: step: 2024/530, loss: 0.5848315358161926
2023-01-21 09:07:18.280120: step: 2028/530, loss: 0.27945375442504883
2023-01-21 09:07:19.406812: step: 2032/530, loss: 0.25259438157081604
2023-01-21 09:07:20.524176: step: 2036/530, loss: 0.5716609954833984
2023-01-21 09:07:21.654652: step: 2040/530, loss: 0.053400229662656784
2023-01-21 09:07:22.759966: step: 2044/530, loss: 1.0147889852523804
2023-01-21 09:07:23.888578: step: 2048/530, loss: 0.07517776638269424
2023-01-21 09:07:25.034556: step: 2052/530, loss: 0.2517591714859009
2023-01-21 09:07:26.140979: step: 2056/530, loss: 0.17578890919685364
2023-01-21 09:07:27.281352: step: 2060/530, loss: 0.3270758390426636
2023-01-21 09:07:28.408419: step: 2064/530, loss: 0.8309615850448608
2023-01-21 09:07:29.534505: step: 2068/530, loss: 3.2110702991485596
2023-01-21 09:07:30.665046: step: 2072/530, loss: 0.05585131794214249
2023-01-21 09:07:31.774725: step: 2076/530, loss: 0.1288878470659256
2023-01-21 09:07:32.926664: step: 2080/530, loss: 0.3452204167842865
2023-01-21 09:07:34.023926: step: 2084/530, loss: 0.13798275589942932
2023-01-21 09:07:35.129087: step: 2088/530, loss: 0.08709807693958282
2023-01-21 09:07:36.244010: step: 2092/530, loss: 0.25586891174316406
2023-01-21 09:07:37.393260: step: 2096/530, loss: 0.08041448891162872
2023-01-21 09:07:38.496583: step: 2100/530, loss: 0.39065685868263245
2023-01-21 09:07:39.635186: step: 2104/530, loss: 0.19825562834739685
2023-01-21 09:07:40.766966: step: 2108/530, loss: 0.626522421836853
2023-01-21 09:07:41.899206: step: 2112/530, loss: 0.08409452438354492
2023-01-21 09:07:43.049165: step: 2116/530, loss: 0.12319669872522354
2023-01-21 09:07:44.170916: step: 2120/530, loss: 0.44887515902519226
==================================================
Loss: 0.493
--------------------
Dev: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.575, 'r': 0.8518518518518519, 'f1': 0.6865671641791045}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.43243243243243246, 'r': 0.4444444444444444, 'f1': 0.4383561643835616}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.575, 'r': 0.8518518518518519, 'f1': 0.6865671641791045}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:08:40.865287: step: 4/530, loss: 0.2426898032426834
2023-01-21 09:08:42.012548: step: 8/530, loss: 0.20357075333595276
2023-01-21 09:08:43.148974: step: 12/530, loss: 0.07590899616479874
2023-01-21 09:08:44.245772: step: 16/530, loss: 0.09386958926916122
2023-01-21 09:08:45.350170: step: 20/530, loss: 0.14798539876937866
2023-01-21 09:08:46.470243: step: 24/530, loss: 0.7234320640563965
2023-01-21 09:08:47.574669: step: 28/530, loss: 0.10331859439611435
2023-01-21 09:08:48.674527: step: 32/530, loss: 0.10128088295459747
2023-01-21 09:08:49.816557: step: 36/530, loss: 0.6619992256164551
2023-01-21 09:08:50.944307: step: 40/530, loss: 0.1277463436126709
2023-01-21 09:08:52.061922: step: 44/530, loss: 0.07528219372034073
2023-01-21 09:08:53.202548: step: 48/530, loss: 0.9066574573516846
2023-01-21 09:08:54.302212: step: 52/530, loss: 0.059286929666996
2023-01-21 09:08:55.446405: step: 56/530, loss: 0.3750576972961426
2023-01-21 09:08:56.567934: step: 60/530, loss: 0.21866169571876526
2023-01-21 09:08:57.683669: step: 64/530, loss: 0.19564051926136017
2023-01-21 09:08:58.783564: step: 68/530, loss: 0.651627242565155
2023-01-21 09:08:59.884572: step: 72/530, loss: 0.7306483387947083
2023-01-21 09:09:01.003149: step: 76/530, loss: 0.0267396941781044
2023-01-21 09:09:02.105713: step: 80/530, loss: 0.09535031765699387
2023-01-21 09:09:03.220898: step: 84/530, loss: 0.3563896417617798
2023-01-21 09:09:04.329294: step: 88/530, loss: 0.6136549711227417
2023-01-21 09:09:05.479122: step: 92/530, loss: 0.09629111737012863
2023-01-21 09:09:06.600251: step: 96/530, loss: 1.346459150314331
2023-01-21 09:09:07.722367: step: 100/530, loss: 0.1783783882856369
2023-01-21 09:09:08.856258: step: 104/530, loss: 0.28856849670410156
2023-01-21 09:09:09.991278: step: 108/530, loss: 0.11380644142627716
2023-01-21 09:09:11.119860: step: 112/530, loss: 1.292015552520752
2023-01-21 09:09:12.239423: step: 116/530, loss: 0.08938512951135635
2023-01-21 09:09:13.348539: step: 120/530, loss: 1.0643033981323242
2023-01-21 09:09:14.498010: step: 124/530, loss: 0.1515856683254242
2023-01-21 09:09:15.620144: step: 128/530, loss: 0.5604331493377686
2023-01-21 09:09:16.744424: step: 132/530, loss: 0.08894267678260803
2023-01-21 09:09:17.862248: step: 136/530, loss: 0.13017530739307404
2023-01-21 09:09:19.011728: step: 140/530, loss: 0.09927596896886826
2023-01-21 09:09:20.149644: step: 144/530, loss: 0.09744873642921448
2023-01-21 09:09:21.303234: step: 148/530, loss: 0.19730836153030396
2023-01-21 09:09:22.408827: step: 152/530, loss: 0.7384673357009888
2023-01-21 09:09:23.521166: step: 156/530, loss: 0.2800275683403015
2023-01-21 09:09:24.620611: step: 160/530, loss: 0.12046681344509125
2023-01-21 09:09:25.739524: step: 164/530, loss: 0.02410411834716797
2023-01-21 09:09:26.886478: step: 168/530, loss: 0.02486124075949192
2023-01-21 09:09:28.021309: step: 172/530, loss: 0.09562597423791885
2023-01-21 09:09:29.099733: step: 176/530, loss: 0.08392749726772308
2023-01-21 09:09:30.221786: step: 180/530, loss: 0.07321682572364807
2023-01-21 09:09:31.381817: step: 184/530, loss: 0.15812483429908752
2023-01-21 09:09:32.488175: step: 188/530, loss: 0.37360915541648865
2023-01-21 09:09:33.614495: step: 192/530, loss: 0.5706270337104797
2023-01-21 09:09:34.740896: step: 196/530, loss: 1.1458741426467896
2023-01-21 09:09:35.848396: step: 200/530, loss: 0.15156421065330505
2023-01-21 09:09:36.950366: step: 204/530, loss: 0.3389979898929596
2023-01-21 09:09:38.060147: step: 208/530, loss: 0.10417509078979492
2023-01-21 09:09:39.161697: step: 212/530, loss: 0.09341412037611008
2023-01-21 09:09:40.304998: step: 216/530, loss: 1.0482102632522583
2023-01-21 09:09:41.432014: step: 220/530, loss: 0.12351961433887482
2023-01-21 09:09:42.597840: step: 224/530, loss: 0.4129384160041809
2023-01-21 09:09:43.716871: step: 228/530, loss: 0.2869279086589813
2023-01-21 09:09:44.854576: step: 232/530, loss: 0.19159956276416779
2023-01-21 09:09:45.970264: step: 236/530, loss: 0.09985899925231934
2023-01-21 09:09:47.082185: step: 240/530, loss: 1.044792890548706
2023-01-21 09:09:48.213297: step: 244/530, loss: 0.6497471928596497
2023-01-21 09:09:49.317347: step: 248/530, loss: 0.0644163116812706
2023-01-21 09:09:50.428942: step: 252/530, loss: 0.12396059185266495
2023-01-21 09:09:51.562196: step: 256/530, loss: 0.125981867313385
2023-01-21 09:09:52.693175: step: 260/530, loss: 0.1220371276140213
2023-01-21 09:09:53.807686: step: 264/530, loss: 0.32602912187576294
2023-01-21 09:09:54.937294: step: 268/530, loss: 1.0321238040924072
2023-01-21 09:09:56.085329: step: 272/530, loss: 0.1178189292550087
2023-01-21 09:09:57.248898: step: 276/530, loss: 0.16814814507961273
2023-01-21 09:09:58.381455: step: 280/530, loss: 0.14084625244140625
2023-01-21 09:09:59.478805: step: 284/530, loss: 0.0956568717956543
2023-01-21 09:10:00.590220: step: 288/530, loss: 0.5914638638496399
2023-01-21 09:10:01.722988: step: 292/530, loss: 0.16256102919578552
2023-01-21 09:10:02.869262: step: 296/530, loss: 0.410400390625
2023-01-21 09:10:03.999824: step: 300/530, loss: 0.05446135997772217
2023-01-21 09:10:05.177027: step: 304/530, loss: 0.37062549591064453
2023-01-21 09:10:06.351240: step: 308/530, loss: 0.25865477323532104
2023-01-21 09:10:07.480147: step: 312/530, loss: 0.21905192732810974
2023-01-21 09:10:08.593543: step: 316/530, loss: 0.08423290401697159
2023-01-21 09:10:09.696466: step: 320/530, loss: 0.40526628494262695
2023-01-21 09:10:10.799082: step: 324/530, loss: 0.5596331357955933
2023-01-21 09:10:11.930396: step: 328/530, loss: 0.057629965245723724
2023-01-21 09:10:13.045065: step: 332/530, loss: 0.07920923829078674
2023-01-21 09:10:14.161271: step: 336/530, loss: 0.28068098425865173
2023-01-21 09:10:15.283344: step: 340/530, loss: 0.12315788865089417
2023-01-21 09:10:16.379798: step: 344/530, loss: 0.04610776901245117
2023-01-21 09:10:17.495189: step: 348/530, loss: 0.10983829945325851
2023-01-21 09:10:18.624410: step: 352/530, loss: 0.13707371056079865
2023-01-21 09:10:19.738920: step: 356/530, loss: 0.04855484887957573
2023-01-21 09:10:20.855082: step: 360/530, loss: 0.15080510079860687
2023-01-21 09:10:21.973630: step: 364/530, loss: 0.2960459887981415
2023-01-21 09:10:23.081617: step: 368/530, loss: 0.38567107915878296
2023-01-21 09:10:24.190394: step: 372/530, loss: 0.8939532041549683
2023-01-21 09:10:25.307923: step: 376/530, loss: 0.016727160662412643
2023-01-21 09:10:26.404407: step: 380/530, loss: 0.24768222868442535
2023-01-21 09:10:27.534229: step: 384/530, loss: 0.7668226957321167
2023-01-21 09:10:28.666534: step: 388/530, loss: 0.7150883674621582
2023-01-21 09:10:29.792981: step: 392/530, loss: 1.1176691055297852
2023-01-21 09:10:30.936723: step: 396/530, loss: 0.05874443054199219
2023-01-21 09:10:32.093169: step: 400/530, loss: 0.03908901289105415
2023-01-21 09:10:33.218806: step: 404/530, loss: 0.9112390279769897
2023-01-21 09:10:34.357181: step: 408/530, loss: 0.09809088706970215
2023-01-21 09:10:35.487454: step: 412/530, loss: 0.631411612033844
2023-01-21 09:10:36.588247: step: 416/530, loss: 0.18457326292991638
2023-01-21 09:10:37.679574: step: 420/530, loss: 0.11251892894506454
2023-01-21 09:10:38.790816: step: 424/530, loss: 0.09046631306409836
2023-01-21 09:10:39.873212: step: 428/530, loss: 0.03998565673828125
2023-01-21 09:10:41.001494: step: 432/530, loss: 0.09033947438001633
2023-01-21 09:10:42.096915: step: 436/530, loss: 0.08593063801527023
2023-01-21 09:10:43.217846: step: 440/530, loss: 0.29131969809532166
2023-01-21 09:10:44.361709: step: 444/530, loss: 0.11450796574354172
2023-01-21 09:10:45.486976: step: 448/530, loss: 0.025425339117646217
2023-01-21 09:10:46.611321: step: 452/530, loss: 0.10331273078918457
2023-01-21 09:10:47.726423: step: 456/530, loss: 0.5864859223365784
2023-01-21 09:10:48.834720: step: 460/530, loss: 0.6186594367027283
2023-01-21 09:10:49.932989: step: 464/530, loss: 0.1444006860256195
2023-01-21 09:10:51.034361: step: 468/530, loss: 0.04403819888830185
2023-01-21 09:10:52.167107: step: 472/530, loss: 0.46927422285079956
2023-01-21 09:10:53.295678: step: 476/530, loss: 0.12903137505054474
2023-01-21 09:10:54.417794: step: 480/530, loss: 1.112038016319275
2023-01-21 09:10:55.525688: step: 484/530, loss: 0.08306923508644104
2023-01-21 09:10:56.680770: step: 488/530, loss: 0.19161853194236755
2023-01-21 09:10:57.800115: step: 492/530, loss: 0.518001914024353
2023-01-21 09:10:58.918454: step: 496/530, loss: 0.06959342956542969
2023-01-21 09:11:00.005675: step: 500/530, loss: 0.06137733533978462
2023-01-21 09:11:01.134247: step: 504/530, loss: 0.3269311785697937
2023-01-21 09:11:02.258919: step: 508/530, loss: 0.5023454427719116
2023-01-21 09:11:03.382929: step: 512/530, loss: 0.13778051733970642
2023-01-21 09:11:04.528475: step: 516/530, loss: 0.9450715184211731
2023-01-21 09:11:05.647295: step: 520/530, loss: 0.08117542415857315
2023-01-21 09:11:06.781426: step: 524/530, loss: 0.13776007294654846
2023-01-21 09:11:07.879614: step: 528/530, loss: 0.07911749184131622
2023-01-21 09:11:08.996623: step: 532/530, loss: 0.32076358795166016
2023-01-21 09:11:10.099353: step: 536/530, loss: 0.2454909384250641
2023-01-21 09:11:11.235915: step: 540/530, loss: 0.22251597046852112
2023-01-21 09:11:12.369258: step: 544/530, loss: 0.17575788497924805
2023-01-21 09:11:13.507636: step: 548/530, loss: 0.05004005506634712
2023-01-21 09:11:14.618189: step: 552/530, loss: 0.32304298877716064
2023-01-21 09:11:15.724180: step: 556/530, loss: 0.3375406265258789
2023-01-21 09:11:16.814192: step: 560/530, loss: 0.00990219134837389
2023-01-21 09:11:17.929070: step: 564/530, loss: 0.0975489616394043
2023-01-21 09:11:19.039197: step: 568/530, loss: 0.13485947251319885
2023-01-21 09:11:20.160034: step: 572/530, loss: 0.3519957363605499
2023-01-21 09:11:21.284231: step: 576/530, loss: 0.3879193365573883
2023-01-21 09:11:22.402284: step: 580/530, loss: 0.39379578828811646
2023-01-21 09:11:23.513105: step: 584/530, loss: 0.14923697710037231
2023-01-21 09:11:24.627137: step: 588/530, loss: 0.19109030067920685
2023-01-21 09:11:25.740373: step: 592/530, loss: 0.24350671470165253
2023-01-21 09:11:26.851869: step: 596/530, loss: 0.029885293915867805
2023-01-21 09:11:27.975553: step: 600/530, loss: 0.9649703502655029
2023-01-21 09:11:29.075748: step: 604/530, loss: 0.7610010504722595
2023-01-21 09:11:30.212742: step: 608/530, loss: 0.03967934101819992
2023-01-21 09:11:31.325541: step: 612/530, loss: 0.02753724902868271
2023-01-21 09:11:32.432595: step: 616/530, loss: 0.7964020371437073
2023-01-21 09:11:33.561245: step: 620/530, loss: 0.5280997157096863
2023-01-21 09:11:34.691474: step: 624/530, loss: 0.5744256973266602
2023-01-21 09:11:35.783249: step: 628/530, loss: 0.7409168481826782
2023-01-21 09:11:36.855732: step: 632/530, loss: 0.3102342188358307
2023-01-21 09:11:37.978958: step: 636/530, loss: 0.13078069686889648
2023-01-21 09:11:39.092391: step: 640/530, loss: 0.044184159487485886
2023-01-21 09:11:40.191450: step: 644/530, loss: 0.07325520366430283
2023-01-21 09:11:41.356622: step: 648/530, loss: 0.8813309669494629
2023-01-21 09:11:42.504383: step: 652/530, loss: 0.2608141005039215
2023-01-21 09:11:43.653197: step: 656/530, loss: 0.11824913322925568
2023-01-21 09:11:44.750419: step: 660/530, loss: 0.11784043163061142
2023-01-21 09:11:45.864248: step: 664/530, loss: 0.13362941145896912
2023-01-21 09:11:46.991656: step: 668/530, loss: 0.2579174041748047
2023-01-21 09:11:48.097241: step: 672/530, loss: 0.1547134518623352
2023-01-21 09:11:49.198258: step: 676/530, loss: 0.37035951018333435
2023-01-21 09:11:50.327471: step: 680/530, loss: 0.2700921893119812
2023-01-21 09:11:51.438163: step: 684/530, loss: 0.2412181943655014
2023-01-21 09:11:52.576165: step: 688/530, loss: 0.19370746612548828
2023-01-21 09:11:53.695976: step: 692/530, loss: 0.7111555337905884
2023-01-21 09:11:54.819348: step: 696/530, loss: 0.47564518451690674
2023-01-21 09:11:55.943347: step: 700/530, loss: 0.12684603035449982
2023-01-21 09:11:57.050245: step: 704/530, loss: 0.06669716536998749
2023-01-21 09:11:58.157751: step: 708/530, loss: 0.47259649634361267
2023-01-21 09:11:59.249976: step: 712/530, loss: 0.20346832275390625
2023-01-21 09:12:00.371645: step: 716/530, loss: 0.20383216440677643
2023-01-21 09:12:01.485008: step: 720/530, loss: 0.4766809344291687
2023-01-21 09:12:02.613788: step: 724/530, loss: 0.04410247504711151
2023-01-21 09:12:03.740385: step: 728/530, loss: 0.14399266242980957
2023-01-21 09:12:04.871860: step: 732/530, loss: 0.15260982513427734
2023-01-21 09:12:05.982731: step: 736/530, loss: 0.16811323165893555
2023-01-21 09:12:07.091748: step: 740/530, loss: 0.10209040343761444
2023-01-21 09:12:08.236483: step: 744/530, loss: 0.12906968593597412
2023-01-21 09:12:09.342327: step: 748/530, loss: 0.05279877036809921
2023-01-21 09:12:10.465204: step: 752/530, loss: 0.6425662636756897
2023-01-21 09:12:11.569051: step: 756/530, loss: 0.3395642042160034
2023-01-21 09:12:12.717546: step: 760/530, loss: 0.2783685624599457
2023-01-21 09:12:13.823528: step: 764/530, loss: 0.04553408548235893
2023-01-21 09:12:14.941470: step: 768/530, loss: 0.11670637130737305
2023-01-21 09:12:16.069400: step: 772/530, loss: 0.46865376830101013
2023-01-21 09:12:17.202039: step: 776/530, loss: 0.7218046188354492
2023-01-21 09:12:18.348581: step: 780/530, loss: 1.0530325174331665
2023-01-21 09:12:19.478416: step: 784/530, loss: 0.17734013497829437
2023-01-21 09:12:20.630917: step: 788/530, loss: 0.3175069987773895
2023-01-21 09:12:21.765456: step: 792/530, loss: 0.08610615134239197
2023-01-21 09:12:22.885280: step: 796/530, loss: 0.06858482956886292
2023-01-21 09:12:24.021794: step: 800/530, loss: 0.7775834202766418
2023-01-21 09:12:25.124140: step: 804/530, loss: 0.6047054529190063
2023-01-21 09:12:26.217483: step: 808/530, loss: 0.10581164062023163
2023-01-21 09:12:27.381486: step: 812/530, loss: 0.0590825080871582
2023-01-21 09:12:28.487331: step: 816/530, loss: 0.16704817116260529
2023-01-21 09:12:29.602080: step: 820/530, loss: 0.6027072072029114
2023-01-21 09:12:30.701887: step: 824/530, loss: 0.06710748374462128
2023-01-21 09:12:31.814162: step: 828/530, loss: 0.17862224578857422
2023-01-21 09:12:32.935458: step: 832/530, loss: 0.08034076541662216
2023-01-21 09:12:34.065699: step: 836/530, loss: 0.14182758331298828
2023-01-21 09:12:35.188807: step: 840/530, loss: 5.561537742614746
2023-01-21 09:12:36.301288: step: 844/530, loss: 0.8769439458847046
2023-01-21 09:12:37.416722: step: 848/530, loss: 0.19149112701416016
2023-01-21 09:12:38.534466: step: 852/530, loss: 0.12649592757225037
2023-01-21 09:12:39.657284: step: 856/530, loss: 0.8606684803962708
2023-01-21 09:12:40.794847: step: 860/530, loss: 0.0691070556640625
2023-01-21 09:12:41.911695: step: 864/530, loss: 0.18118353188037872
2023-01-21 09:12:43.016773: step: 868/530, loss: 0.11194916069507599
2023-01-21 09:12:44.125250: step: 872/530, loss: 0.3001757562160492
2023-01-21 09:12:45.269212: step: 876/530, loss: 0.7367363572120667
2023-01-21 09:12:46.407735: step: 880/530, loss: 0.11703381687402725
2023-01-21 09:12:47.525428: step: 884/530, loss: 0.596276581287384
2023-01-21 09:12:48.655048: step: 888/530, loss: 0.0638425350189209
2023-01-21 09:12:49.785646: step: 892/530, loss: 0.12961846590042114
2023-01-21 09:12:50.956779: step: 896/530, loss: 0.13920792937278748
2023-01-21 09:12:52.073695: step: 900/530, loss: 0.09304087609052658
2023-01-21 09:12:53.159334: step: 904/530, loss: 0.6309574246406555
2023-01-21 09:12:54.291175: step: 908/530, loss: 0.2951746881008148
2023-01-21 09:12:55.411040: step: 912/530, loss: 0.12824681401252747
2023-01-21 09:12:56.527110: step: 916/530, loss: 0.5646584033966064
2023-01-21 09:12:57.675871: step: 920/530, loss: 5.596519947052002
2023-01-21 09:12:58.803280: step: 924/530, loss: 0.04315061867237091
2023-01-21 09:12:59.924063: step: 928/530, loss: 0.3209080100059509
2023-01-21 09:13:01.039884: step: 932/530, loss: 0.09496760368347168
2023-01-21 09:13:02.160111: step: 936/530, loss: 0.197357177734375
2023-01-21 09:13:03.293202: step: 940/530, loss: 0.7305237054824829
2023-01-21 09:13:04.423644: step: 944/530, loss: 0.06873271614313126
2023-01-21 09:13:05.591497: step: 948/530, loss: 0.37570440769195557
2023-01-21 09:13:06.738689: step: 952/530, loss: 0.27637261152267456
2023-01-21 09:13:07.873982: step: 956/530, loss: 0.061997607350349426
2023-01-21 09:13:09.015643: step: 960/530, loss: 1.0024683475494385
2023-01-21 09:13:10.144548: step: 964/530, loss: 0.13721580803394318
2023-01-21 09:13:11.275062: step: 968/530, loss: 0.1336839199066162
2023-01-21 09:13:12.386098: step: 972/530, loss: 0.15640544891357422
2023-01-21 09:13:13.520510: step: 976/530, loss: 0.14638696610927582
2023-01-21 09:13:14.629665: step: 980/530, loss: 0.23668193817138672
2023-01-21 09:13:15.722281: step: 984/530, loss: 0.2937930226325989
2023-01-21 09:13:16.826966: step: 988/530, loss: 0.2170475870370865
2023-01-21 09:13:17.940533: step: 992/530, loss: 0.631024956703186
2023-01-21 09:13:19.022596: step: 996/530, loss: 0.10520673543214798
2023-01-21 09:13:20.159181: step: 1000/530, loss: 0.18981638550758362
2023-01-21 09:13:21.277804: step: 1004/530, loss: 0.4293762445449829
2023-01-21 09:13:22.460729: step: 1008/530, loss: 0.2915140986442566
2023-01-21 09:13:23.567897: step: 1012/530, loss: 0.05743970721960068
2023-01-21 09:13:24.700248: step: 1016/530, loss: 0.04022722318768501
2023-01-21 09:13:25.817479: step: 1020/530, loss: 0.03130464628338814
2023-01-21 09:13:26.937285: step: 1024/530, loss: 0.12952327728271484
2023-01-21 09:13:28.026464: step: 1028/530, loss: 0.2634626030921936
2023-01-21 09:13:29.147256: step: 1032/530, loss: 0.09073200821876526
2023-01-21 09:13:30.291438: step: 1036/530, loss: 0.16730089485645294
2023-01-21 09:13:31.396653: step: 1040/530, loss: 0.21579104661941528
2023-01-21 09:13:32.515814: step: 1044/530, loss: 0.10871829837560654
2023-01-21 09:13:33.632825: step: 1048/530, loss: 0.5240617990493774
2023-01-21 09:13:34.743945: step: 1052/530, loss: 0.1836831122636795
2023-01-21 09:13:35.856277: step: 1056/530, loss: 0.14211492240428925
2023-01-21 09:13:36.964756: step: 1060/530, loss: 1.059338927268982
2023-01-21 09:13:38.122643: step: 1064/530, loss: 6.697022438049316
2023-01-21 09:13:39.263579: step: 1068/530, loss: 0.11243682354688644
2023-01-21 09:13:40.369003: step: 1072/530, loss: 0.03249311447143555
2023-01-21 09:13:41.485950: step: 1076/530, loss: 0.02041592448949814
2023-01-21 09:13:42.615874: step: 1080/530, loss: 0.06910476833581924
2023-01-21 09:13:43.716993: step: 1084/530, loss: 0.5682775378227234
2023-01-21 09:13:44.836648: step: 1088/530, loss: 0.11185060441493988
2023-01-21 09:13:45.973860: step: 1092/530, loss: 1.2662150859832764
2023-01-21 09:13:47.060331: step: 1096/530, loss: 0.2531459927558899
2023-01-21 09:13:48.195248: step: 1100/530, loss: 0.1688491851091385
2023-01-21 09:13:49.337923: step: 1104/530, loss: 0.0957394614815712
2023-01-21 09:13:50.487264: step: 1108/530, loss: 0.14809615910053253
2023-01-21 09:13:51.610591: step: 1112/530, loss: 0.15989232063293457
2023-01-21 09:13:52.750035: step: 1116/530, loss: 1.0009489059448242
2023-01-21 09:13:53.854816: step: 1120/530, loss: 0.07803960144519806
2023-01-21 09:13:54.939318: step: 1124/530, loss: 0.03127622604370117
2023-01-21 09:13:56.059722: step: 1128/530, loss: 0.1130366325378418
2023-01-21 09:13:57.168122: step: 1132/530, loss: 0.12404890358448029
2023-01-21 09:13:58.322354: step: 1136/530, loss: 0.4977996051311493
2023-01-21 09:13:59.446521: step: 1140/530, loss: 0.9116091728210449
2023-01-21 09:14:00.535006: step: 1144/530, loss: 0.028257369995117188
2023-01-21 09:14:01.658941: step: 1148/530, loss: 0.7959879636764526
2023-01-21 09:14:02.766508: step: 1152/530, loss: 0.09358659386634827
2023-01-21 09:14:03.919737: step: 1156/530, loss: 0.034700918942689896
2023-01-21 09:14:05.022577: step: 1160/530, loss: 0.20606566965579987
2023-01-21 09:14:06.139925: step: 1164/530, loss: 0.37286311388015747
2023-01-21 09:14:07.249287: step: 1168/530, loss: 0.3449724316596985
2023-01-21 09:14:08.395290: step: 1172/530, loss: 0.17827215790748596
2023-01-21 09:14:09.550431: step: 1176/530, loss: 0.13285665214061737
2023-01-21 09:14:10.654871: step: 1180/530, loss: 0.13569337129592896
2023-01-21 09:14:11.749119: step: 1184/530, loss: 0.09818144142627716
2023-01-21 09:14:12.865984: step: 1188/530, loss: 0.15180349349975586
2023-01-21 09:14:13.995151: step: 1192/530, loss: 0.7923673391342163
2023-01-21 09:14:15.121390: step: 1196/530, loss: 0.7085750102996826
2023-01-21 09:14:16.238541: step: 1200/530, loss: 0.9579010605812073
2023-01-21 09:14:17.355995: step: 1204/530, loss: 0.4816337525844574
2023-01-21 09:14:18.498422: step: 1208/530, loss: 0.4566114544868469
2023-01-21 09:14:19.614868: step: 1212/530, loss: 4.5486979484558105
2023-01-21 09:14:20.743651: step: 1216/530, loss: 0.076572947204113
2023-01-21 09:14:21.872975: step: 1220/530, loss: 0.15429744124412537
2023-01-21 09:14:23.004448: step: 1224/530, loss: 0.7346298694610596
2023-01-21 09:14:24.181275: step: 1228/530, loss: 0.1368391066789627
2023-01-21 09:14:25.297796: step: 1232/530, loss: 0.18241462111473083
2023-01-21 09:14:26.433406: step: 1236/530, loss: 0.12973624467849731
2023-01-21 09:14:27.573114: step: 1240/530, loss: 0.11317090690135956
2023-01-21 09:14:28.695282: step: 1244/530, loss: 1.0910747051239014
2023-01-21 09:14:29.806446: step: 1248/530, loss: 1.8710020780563354
2023-01-21 09:14:30.894694: step: 1252/530, loss: 0.11874990165233612
2023-01-21 09:14:31.992524: step: 1256/530, loss: 0.14404550194740295
2023-01-21 09:14:33.148184: step: 1260/530, loss: 0.48172688484191895
2023-01-21 09:14:34.277989: step: 1264/530, loss: 0.6925452351570129
2023-01-21 09:14:35.389896: step: 1268/530, loss: 0.005505752749741077
2023-01-21 09:14:36.515214: step: 1272/530, loss: 0.12491970509290695
2023-01-21 09:14:37.645152: step: 1276/530, loss: 0.21732720732688904
2023-01-21 09:14:38.771052: step: 1280/530, loss: 0.6931290030479431
2023-01-21 09:14:39.892127: step: 1284/530, loss: 0.12014809250831604
2023-01-21 09:14:41.027976: step: 1288/530, loss: 3.9107110500335693
2023-01-21 09:14:42.133336: step: 1292/530, loss: 0.23418594896793365
2023-01-21 09:14:43.243779: step: 1296/530, loss: 0.43575289845466614
2023-01-21 09:14:44.358087: step: 1300/530, loss: 0.3126988410949707
2023-01-21 09:14:45.476085: step: 1304/530, loss: 0.029483510181307793
2023-01-21 09:14:46.623783: step: 1308/530, loss: 0.44991618394851685
2023-01-21 09:14:47.773883: step: 1312/530, loss: 0.5220819711685181
2023-01-21 09:14:48.933670: step: 1316/530, loss: 0.8805736303329468
2023-01-21 09:14:50.073124: step: 1320/530, loss: 0.09765376895666122
2023-01-21 09:14:51.210168: step: 1324/530, loss: 0.3835306763648987
2023-01-21 09:14:52.343225: step: 1328/530, loss: 0.7068468928337097
2023-01-21 09:14:53.472690: step: 1332/530, loss: 0.5412137508392334
2023-01-21 09:14:54.582325: step: 1336/530, loss: 0.5303499102592468
2023-01-21 09:14:55.688081: step: 1340/530, loss: 0.0532391332089901
2023-01-21 09:14:56.817465: step: 1344/530, loss: 0.0699133425951004
2023-01-21 09:14:57.951277: step: 1348/530, loss: 0.11602401733398438
2023-01-21 09:14:59.073051: step: 1352/530, loss: 0.11507931351661682
2023-01-21 09:15:00.177764: step: 1356/530, loss: 0.08576121181249619
2023-01-21 09:15:01.287529: step: 1360/530, loss: 1.2977372407913208
2023-01-21 09:15:02.461900: step: 1364/530, loss: 0.13552981615066528
2023-01-21 09:15:03.580408: step: 1368/530, loss: 0.15410995483398438
2023-01-21 09:15:04.728609: step: 1372/530, loss: 0.12532921135425568
2023-01-21 09:15:05.845320: step: 1376/530, loss: 0.9345909357070923
2023-01-21 09:15:06.968153: step: 1380/530, loss: 0.10559320449829102
2023-01-21 09:15:08.077984: step: 1384/530, loss: 0.5648598670959473
2023-01-21 09:15:09.235333: step: 1388/530, loss: 0.05499105527997017
2023-01-21 09:15:10.378540: step: 1392/530, loss: 1.5131492614746094
2023-01-21 09:15:11.482223: step: 1396/530, loss: 0.30266791582107544
2023-01-21 09:15:12.623572: step: 1400/530, loss: 0.36107635498046875
2023-01-21 09:15:13.733663: step: 1404/530, loss: 0.08211131393909454
2023-01-21 09:15:14.872211: step: 1408/530, loss: 0.1853996217250824
2023-01-21 09:15:15.983974: step: 1412/530, loss: 3.913877010345459
2023-01-21 09:15:17.083828: step: 1416/530, loss: 0.3650156855583191
2023-01-21 09:15:18.200595: step: 1420/530, loss: 0.07907247543334961
2023-01-21 09:15:19.331736: step: 1424/530, loss: 0.46418002247810364
2023-01-21 09:15:20.455606: step: 1428/530, loss: 0.34937965869903564
2023-01-21 09:15:21.565108: step: 1432/530, loss: 0.251691997051239
2023-01-21 09:15:22.716951: step: 1436/530, loss: 0.1269761621952057
2023-01-21 09:15:23.819780: step: 1440/530, loss: 0.3294636607170105
2023-01-21 09:15:24.944823: step: 1444/530, loss: 0.1376476287841797
2023-01-21 09:15:26.074228: step: 1448/530, loss: 0.0502413734793663
2023-01-21 09:15:27.178067: step: 1452/530, loss: 0.2584006190299988
2023-01-21 09:15:28.286032: step: 1456/530, loss: 0.06424055248498917
2023-01-21 09:15:29.428365: step: 1460/530, loss: 0.8068082928657532
2023-01-21 09:15:30.521168: step: 1464/530, loss: 0.4949599504470825
2023-01-21 09:15:31.614376: step: 1468/530, loss: 0.0526403933763504
2023-01-21 09:15:32.714103: step: 1472/530, loss: 2.772021532058716
2023-01-21 09:15:33.846871: step: 1476/530, loss: 0.029606152325868607
2023-01-21 09:15:34.929371: step: 1480/530, loss: 0.09204654395580292
2023-01-21 09:15:36.042944: step: 1484/530, loss: 0.04686170071363449
2023-01-21 09:15:37.152494: step: 1488/530, loss: 0.4500100910663605
2023-01-21 09:15:38.276843: step: 1492/530, loss: 0.10053558647632599
2023-01-21 09:15:39.407032: step: 1496/530, loss: 1.4256826639175415
2023-01-21 09:15:40.558283: step: 1500/530, loss: 0.15307369828224182
2023-01-21 09:15:41.667022: step: 1504/530, loss: 0.32327374815940857
2023-01-21 09:15:42.801269: step: 1508/530, loss: 0.10572662204504013
2023-01-21 09:15:43.928245: step: 1512/530, loss: 0.18129916489124298
2023-01-21 09:15:45.034921: step: 1516/530, loss: 0.10050592571496964
2023-01-21 09:15:46.167576: step: 1520/530, loss: 0.021743012592196465
2023-01-21 09:15:47.278829: step: 1524/530, loss: 0.05757313221693039
2023-01-21 09:15:48.414803: step: 1528/530, loss: 1.483445644378662
2023-01-21 09:15:49.535746: step: 1532/530, loss: 0.05383338779211044
2023-01-21 09:15:50.660308: step: 1536/530, loss: 2.020174741744995
2023-01-21 09:15:51.779167: step: 1540/530, loss: 0.038916923105716705
2023-01-21 09:15:52.880038: step: 1544/530, loss: 0.8860012292861938
2023-01-21 09:15:54.009067: step: 1548/530, loss: 0.13376203179359436
2023-01-21 09:15:55.167182: step: 1552/530, loss: 2.292222499847412
2023-01-21 09:15:56.309082: step: 1556/530, loss: 0.8194613456726074
2023-01-21 09:15:57.481594: step: 1560/530, loss: 0.1855698674917221
2023-01-21 09:15:58.625323: step: 1564/530, loss: 0.2875831723213196
2023-01-21 09:15:59.769792: step: 1568/530, loss: 2.010491132736206
2023-01-21 09:16:00.898211: step: 1572/530, loss: 0.25376319885253906
2023-01-21 09:16:02.027889: step: 1576/530, loss: 0.08488493412733078
2023-01-21 09:16:03.157013: step: 1580/530, loss: 0.5695492625236511
2023-01-21 09:16:04.272051: step: 1584/530, loss: 0.32643136382102966
2023-01-21 09:16:05.411161: step: 1588/530, loss: 0.021935129538178444
2023-01-21 09:16:06.539158: step: 1592/530, loss: 0.168484628200531
2023-01-21 09:16:07.639872: step: 1596/530, loss: 0.7492960691452026
2023-01-21 09:16:08.744636: step: 1600/530, loss: 0.28280019760131836
2023-01-21 09:16:09.869765: step: 1604/530, loss: 0.713383674621582
2023-01-21 09:16:11.005130: step: 1608/530, loss: 0.5585966110229492
2023-01-21 09:16:12.135484: step: 1612/530, loss: 0.3293589651584625
2023-01-21 09:16:13.241046: step: 1616/530, loss: 0.10880356281995773
2023-01-21 09:16:14.361108: step: 1620/530, loss: 0.5849825739860535
2023-01-21 09:16:15.484270: step: 1624/530, loss: 0.8764529228210449
2023-01-21 09:16:16.602194: step: 1628/530, loss: 0.06115712970495224
2023-01-21 09:16:17.759273: step: 1632/530, loss: 0.14915533363819122
2023-01-21 09:16:18.879789: step: 1636/530, loss: 0.09380646049976349
2023-01-21 09:16:20.008881: step: 1640/530, loss: 0.1113104298710823
2023-01-21 09:16:21.118153: step: 1644/530, loss: 0.1281011998653412
2023-01-21 09:16:22.216679: step: 1648/530, loss: 0.20835809409618378
2023-01-21 09:16:23.320253: step: 1652/530, loss: 0.07434120029211044
2023-01-21 09:16:24.426440: step: 1656/530, loss: 0.05488395690917969
2023-01-21 09:16:25.543552: step: 1660/530, loss: 0.049842022359371185
2023-01-21 09:16:26.652449: step: 1664/530, loss: 0.2538219392299652
2023-01-21 09:16:27.775160: step: 1668/530, loss: 0.058594606816768646
2023-01-21 09:16:28.907300: step: 1672/530, loss: 0.05866451561450958
2023-01-21 09:16:30.019424: step: 1676/530, loss: 0.22145463526248932
2023-01-21 09:16:31.140192: step: 1680/530, loss: 0.17822200059890747
2023-01-21 09:16:32.267063: step: 1684/530, loss: 0.7184593677520752
2023-01-21 09:16:33.373048: step: 1688/530, loss: 0.10963602364063263
2023-01-21 09:16:34.506755: step: 1692/530, loss: 0.807685911655426
2023-01-21 09:16:35.629418: step: 1696/530, loss: 0.08288630843162537
2023-01-21 09:16:36.737967: step: 1700/530, loss: 0.242415189743042
2023-01-21 09:16:37.860103: step: 1704/530, loss: 0.10757341235876083
2023-01-21 09:16:38.980549: step: 1708/530, loss: 0.02465801313519478
2023-01-21 09:16:40.144809: step: 1712/530, loss: 0.13817119598388672
2023-01-21 09:16:41.255699: step: 1716/530, loss: 0.28537243604660034
2023-01-21 09:16:42.373488: step: 1720/530, loss: 0.7142650485038757
2023-01-21 09:16:43.504886: step: 1724/530, loss: 0.2754554748535156
2023-01-21 09:16:44.607741: step: 1728/530, loss: 0.4273221790790558
2023-01-21 09:16:45.730418: step: 1732/530, loss: 0.8859471678733826
2023-01-21 09:16:46.885177: step: 1736/530, loss: 0.33142802119255066
2023-01-21 09:16:48.006462: step: 1740/530, loss: 0.12461915612220764
2023-01-21 09:16:49.136755: step: 1744/530, loss: 0.3007735311985016
2023-01-21 09:16:50.261108: step: 1748/530, loss: 0.5511849522590637
2023-01-21 09:16:51.405448: step: 1752/530, loss: 0.16630326211452484
2023-01-21 09:16:52.542824: step: 1756/530, loss: 0.12402570992708206
2023-01-21 09:16:53.651684: step: 1760/530, loss: 1.3395030498504639
2023-01-21 09:16:54.765432: step: 1764/530, loss: 0.23198625445365906
2023-01-21 09:16:55.866247: step: 1768/530, loss: 0.11191582679748535
2023-01-21 09:16:56.959450: step: 1772/530, loss: 0.10320186614990234
2023-01-21 09:16:58.103875: step: 1776/530, loss: 0.29644688963890076
2023-01-21 09:16:59.211756: step: 1780/530, loss: 0.1512923240661621
2023-01-21 09:17:00.350618: step: 1784/530, loss: 0.4369129538536072
2023-01-21 09:17:01.479862: step: 1788/530, loss: 0.1335986852645874
2023-01-21 09:17:02.587676: step: 1792/530, loss: 0.09932279586791992
2023-01-21 09:17:03.728787: step: 1796/530, loss: 0.24840280413627625
2023-01-21 09:17:04.840696: step: 1800/530, loss: 0.5166805386543274
2023-01-21 09:17:06.010613: step: 1804/530, loss: 1.2183558940887451
2023-01-21 09:17:07.116483: step: 1808/530, loss: 0.23145313560962677
2023-01-21 09:17:08.267985: step: 1812/530, loss: 0.5459344983100891
2023-01-21 09:17:09.409471: step: 1816/530, loss: 0.4104844927787781
2023-01-21 09:17:10.531638: step: 1820/530, loss: 0.3828395903110504
2023-01-21 09:17:11.660047: step: 1824/530, loss: 0.11716604232788086
2023-01-21 09:17:12.788168: step: 1828/530, loss: 0.5799517631530762
2023-01-21 09:17:13.920848: step: 1832/530, loss: 0.5515645742416382
2023-01-21 09:17:15.074719: step: 1836/530, loss: 0.07434368133544922
2023-01-21 09:17:16.177013: step: 1840/530, loss: 0.2095049023628235
2023-01-21 09:17:17.325521: step: 1844/530, loss: 0.16163387894630432
2023-01-21 09:17:18.440976: step: 1848/530, loss: 0.09525775909423828
2023-01-21 09:17:19.559046: step: 1852/530, loss: 0.6529601812362671
2023-01-21 09:17:20.664898: step: 1856/530, loss: 0.15268835425376892
2023-01-21 09:17:21.769807: step: 1860/530, loss: 0.15811890363693237
2023-01-21 09:17:22.862866: step: 1864/530, loss: 0.01988091506063938
2023-01-21 09:17:23.990718: step: 1868/530, loss: 0.10967741161584854
2023-01-21 09:17:25.087652: step: 1872/530, loss: 0.09564152359962463
2023-01-21 09:17:26.199376: step: 1876/530, loss: 2.1743366718292236
2023-01-21 09:17:27.359656: step: 1880/530, loss: 0.7197198867797852
2023-01-21 09:17:28.494402: step: 1884/530, loss: 0.11725623905658722
2023-01-21 09:17:29.628386: step: 1888/530, loss: 0.11699095368385315
2023-01-21 09:17:30.770486: step: 1892/530, loss: 0.12567205727100372
2023-01-21 09:17:31.897690: step: 1896/530, loss: 0.11940484493970871
2023-01-21 09:17:33.047636: step: 1900/530, loss: 0.5074408650398254
2023-01-21 09:17:34.184914: step: 1904/530, loss: 0.28615647554397583
2023-01-21 09:17:35.314327: step: 1908/530, loss: 0.11127553135156631
2023-01-21 09:17:36.477231: step: 1912/530, loss: 0.2144385278224945
2023-01-21 09:17:37.597181: step: 1916/530, loss: 0.19051532447338104
2023-01-21 09:17:38.726825: step: 1920/530, loss: 0.36019372940063477
2023-01-21 09:17:39.846383: step: 1924/530, loss: 0.2777508795261383
2023-01-21 09:17:40.963680: step: 1928/530, loss: 0.2543220520019531
2023-01-21 09:17:42.056535: step: 1932/530, loss: 0.40941813588142395
2023-01-21 09:17:43.166355: step: 1936/530, loss: 0.7665479183197021
2023-01-21 09:17:44.301624: step: 1940/530, loss: 0.1408340483903885
2023-01-21 09:17:45.426533: step: 1944/530, loss: 0.04568493366241455
2023-01-21 09:17:46.540584: step: 1948/530, loss: 0.07039077579975128
2023-01-21 09:17:47.676806: step: 1952/530, loss: 0.03977060317993164
2023-01-21 09:17:48.835789: step: 1956/530, loss: 0.7270016670227051
2023-01-21 09:17:49.956654: step: 1960/530, loss: 0.48939552903175354
2023-01-21 09:17:51.083585: step: 1964/530, loss: 3.0228066444396973
2023-01-21 09:17:52.211325: step: 1968/530, loss: 0.31307584047317505
2023-01-21 09:17:53.330338: step: 1972/530, loss: 0.11756334453821182
2023-01-21 09:17:54.434761: step: 1976/530, loss: 0.30105704069137573
2023-01-21 09:17:55.548420: step: 1980/530, loss: 0.02498607523739338
2023-01-21 09:17:56.704697: step: 1984/530, loss: 0.17753076553344727
2023-01-21 09:17:57.822884: step: 1988/530, loss: 0.16538485884666443
2023-01-21 09:17:58.963434: step: 1992/530, loss: 0.34773874282836914
2023-01-21 09:18:00.103345: step: 1996/530, loss: 0.45388665795326233
2023-01-21 09:18:01.210833: step: 2000/530, loss: 0.14956659078598022
2023-01-21 09:18:02.366439: step: 2004/530, loss: 0.11129655689001083
2023-01-21 09:18:03.473103: step: 2008/530, loss: 0.17294436693191528
2023-01-21 09:18:04.583918: step: 2012/530, loss: 0.09069366753101349
2023-01-21 09:18:05.684778: step: 2016/530, loss: 0.08433127403259277
2023-01-21 09:18:06.808259: step: 2020/530, loss: 0.4764396846294403
2023-01-21 09:18:07.957001: step: 2024/530, loss: 0.12009716033935547
2023-01-21 09:18:09.073001: step: 2028/530, loss: 0.315599262714386
2023-01-21 09:18:10.161976: step: 2032/530, loss: 0.5425676107406616
2023-01-21 09:18:11.296787: step: 2036/530, loss: 0.08703804016113281
2023-01-21 09:18:12.434683: step: 2040/530, loss: 0.2610679864883423
2023-01-21 09:18:13.539846: step: 2044/530, loss: 0.12227936089038849
2023-01-21 09:18:14.648224: step: 2048/530, loss: 0.012537575326859951
2023-01-21 09:18:15.761872: step: 2052/530, loss: 0.07939349114894867
2023-01-21 09:18:16.889359: step: 2056/530, loss: 0.2578169107437134
2023-01-21 09:18:18.033311: step: 2060/530, loss: 0.15415841341018677
2023-01-21 09:18:19.141729: step: 2064/530, loss: 0.8681615591049194
2023-01-21 09:18:20.301253: step: 2068/530, loss: 0.1851181983947754
2023-01-21 09:18:21.434192: step: 2072/530, loss: 0.3306097984313965
2023-01-21 09:18:22.562541: step: 2076/530, loss: 0.08711384236812592
2023-01-21 09:18:23.662925: step: 2080/530, loss: 0.7476381659507751
2023-01-21 09:18:24.786661: step: 2084/530, loss: 0.7445141673088074
2023-01-21 09:18:25.904684: step: 2088/530, loss: 0.12560033798217773
2023-01-21 09:18:27.014669: step: 2092/530, loss: 0.17096364498138428
2023-01-21 09:18:28.148608: step: 2096/530, loss: 0.10149335861206055
2023-01-21 09:18:29.251071: step: 2100/530, loss: 0.08993730694055557
2023-01-21 09:18:30.375952: step: 2104/530, loss: 1.4990428686141968
2023-01-21 09:18:31.501867: step: 2108/530, loss: 0.13334588706493378
2023-01-21 09:18:32.655634: step: 2112/530, loss: 0.36022433638572693
2023-01-21 09:18:33.761905: step: 2116/530, loss: 0.807364284992218
2023-01-21 09:18:34.878636: step: 2120/530, loss: 0.2485140860080719
==================================================
Loss: 0.386
--------------------
Dev: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.625, 'r': 0.3968253968253968, 'f1': 0.4854368932038835}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Chinese: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 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
2023-01-21 09:19:29.742976: step: 4/530, loss: 0.3328391909599304
2023-01-21 09:19:30.842536: step: 8/530, loss: 0.2161366492509842
2023-01-21 09:19:31.947637: step: 12/530, loss: 2.3184242248535156
2023-01-21 09:19:33.075030: step: 16/530, loss: 1.0192146301269531
2023-01-21 09:19:34.194742: step: 20/530, loss: 0.08197665214538574
2023-01-21 09:19:35.328365: step: 24/530, loss: 0.23187074065208435
2023-01-21 09:19:36.429111: step: 28/530, loss: 0.1261003464460373
2023-01-21 09:19:37.563863: step: 32/530, loss: 0.13355597853660583
2023-01-21 09:19:38.677754: step: 36/530, loss: 0.1482105255126953
2023-01-21 09:19:39.814808: step: 40/530, loss: 0.3279067873954773
2023-01-21 09:19:40.940003: step: 44/530, loss: 0.5191739797592163
2023-01-21 09:19:42.070066: step: 48/530, loss: 0.2949063181877136
2023-01-21 09:19:43.201499: step: 52/530, loss: 0.22519607841968536
2023-01-21 09:19:44.326402: step: 56/530, loss: 0.03790559992194176
2023-01-21 09:19:45.437714: step: 60/530, loss: 0.05702982097864151
2023-01-21 09:19:46.546860: step: 64/530, loss: 0.1355874091386795
2023-01-21 09:19:47.657721: step: 68/530, loss: 0.2908710837364197
2023-01-21 09:19:48.763328: step: 72/530, loss: 0.4064415991306305
2023-01-21 09:19:49.910942: step: 76/530, loss: 0.13113364577293396
2023-01-21 09:19:51.053731: step: 80/530, loss: 0.0589747428894043
2023-01-21 09:19:52.172024: step: 84/530, loss: 0.10074613243341446
2023-01-21 09:19:53.290825: step: 88/530, loss: 0.14747628569602966
2023-01-21 09:19:54.509707: step: 92/530, loss: 0.10192590206861496
2023-01-21 09:19:55.640660: step: 96/530, loss: 0.35114815831184387
2023-01-21 09:19:56.763916: step: 100/530, loss: 0.21711650490760803
2023-01-21 09:19:57.905002: step: 104/530, loss: 0.06990785896778107
2023-01-21 09:19:59.059924: step: 108/530, loss: 0.09487934410572052
2023-01-21 09:20:00.176373: step: 112/530, loss: 0.04557361453771591
2023-01-21 09:20:01.295653: step: 116/530, loss: 0.10987591743469238
2023-01-21 09:20:02.436953: step: 120/530, loss: 0.2561771273612976
2023-01-21 09:20:03.564635: step: 124/530, loss: 0.27180272340774536
2023-01-21 09:20:04.683390: step: 128/530, loss: 0.5598156452178955
2023-01-21 09:20:05.778171: step: 132/530, loss: 0.1672348976135254
2023-01-21 09:20:06.882529: step: 136/530, loss: 0.12120304256677628
2023-01-21 09:20:08.010353: step: 140/530, loss: 0.27204322814941406
2023-01-21 09:20:09.132175: step: 144/530, loss: 0.1415904015302658
2023-01-21 09:20:10.241496: step: 148/530, loss: 0.028807926923036575
2023-01-21 09:20:11.367216: step: 152/530, loss: 0.08358936756849289
2023-01-21 09:20:12.473731: step: 156/530, loss: 0.02778015099465847
2023-01-21 09:20:13.604915: step: 160/530, loss: 0.11728544533252716
2023-01-21 09:20:14.718838: step: 164/530, loss: 0.1509249210357666
2023-01-21 09:20:15.853162: step: 168/530, loss: 0.16300678253173828
2023-01-21 09:20:16.998197: step: 172/530, loss: 0.10371866822242737
2023-01-21 09:20:18.119059: step: 176/530, loss: 0.15409621596336365
2023-01-21 09:20:19.246509: step: 180/530, loss: 0.09803777188062668
2023-01-21 09:20:20.384873: step: 184/530, loss: 0.07412414252758026
2023-01-21 09:20:21.516796: step: 188/530, loss: 0.24671994149684906
2023-01-21 09:20:22.624146: step: 192/530, loss: 0.19809454679489136
2023-01-21 09:20:23.745629: step: 196/530, loss: 0.10713253170251846
2023-01-21 09:20:24.848839: step: 200/530, loss: 0.12279417365789413
2023-01-21 09:20:25.980885: step: 204/530, loss: 0.22239446640014648
2023-01-21 09:20:27.113168: step: 208/530, loss: 0.03668703883886337
2023-01-21 09:20:28.252898: step: 212/530, loss: 0.18285083770751953
2023-01-21 09:20:29.391498: step: 216/530, loss: 0.20613804459571838
2023-01-21 09:20:30.511548: step: 220/530, loss: 0.12802791595458984
2023-01-21 09:20:31.653013: step: 224/530, loss: 0.4143645465373993
2023-01-21 09:20:32.764562: step: 228/530, loss: 0.40455740690231323
2023-01-21 09:20:33.868584: step: 232/530, loss: 0.2410842627286911
2023-01-21 09:20:34.992872: step: 236/530, loss: 0.1660003662109375
2023-01-21 09:20:36.143068: step: 240/530, loss: 0.21147093176841736
2023-01-21 09:20:37.268947: step: 244/530, loss: 0.5502294301986694
2023-01-21 09:20:38.370250: step: 248/530, loss: 0.2317015826702118
2023-01-21 09:20:39.474151: step: 252/530, loss: 0.48736143112182617
2023-01-21 09:20:40.599649: step: 256/530, loss: 1.1992590427398682
2023-01-21 09:20:41.736949: step: 260/530, loss: 0.049887944012880325
2023-01-21 09:20:42.845268: step: 264/530, loss: 0.5157423615455627
2023-01-21 09:20:43.971189: step: 268/530, loss: 0.1872878074645996
2023-01-21 09:20:45.093272: step: 272/530, loss: 0.06069578975439072
2023-01-21 09:20:46.214655: step: 276/530, loss: 0.09013481438159943
2023-01-21 09:20:47.309157: step: 280/530, loss: 0.19185668230056763
2023-01-21 09:20:48.414480: step: 284/530, loss: 0.24523791670799255
2023-01-21 09:20:49.545621: step: 288/530, loss: 0.1333208680152893
2023-01-21 09:20:50.681774: step: 292/530, loss: 0.19570809602737427
2023-01-21 09:20:51.786032: step: 296/530, loss: 0.09879980236291885
2023-01-21 09:20:52.911989: step: 300/530, loss: 0.33673810958862305
2023-01-21 09:20:54.023938: step: 304/530, loss: 0.16912536323070526
2023-01-21 09:20:55.140526: step: 308/530, loss: 1.130427598953247
2023-01-21 09:20:56.267974: step: 312/530, loss: 0.4088205397129059
2023-01-21 09:20:57.400457: step: 316/530, loss: 0.1219671294093132
2023-01-21 09:20:58.533033: step: 320/530, loss: 1.049168348312378
2023-01-21 09:20:59.666463: step: 324/530, loss: 0.16328278183937073
2023-01-21 09:21:00.788720: step: 328/530, loss: 0.2961302697658539
2023-01-21 09:21:01.925148: step: 332/530, loss: 0.06673374027013779
2023-01-21 09:21:03.064691: step: 336/530, loss: 0.20635861158370972
2023-01-21 09:21:04.202986: step: 340/530, loss: 0.1278267353773117
2023-01-21 09:21:05.345929: step: 344/530, loss: 0.06825017929077148
2023-01-21 09:21:06.519755: step: 348/530, loss: 0.5643631219863892
2023-01-21 09:21:07.636025: step: 352/530, loss: 2.377779006958008
2023-01-21 09:21:08.742740: step: 356/530, loss: 0.1623862385749817
2023-01-21 09:21:09.878691: step: 360/530, loss: 0.14190712571144104
2023-01-21 09:21:10.984121: step: 364/530, loss: 0.1083555743098259
2023-01-21 09:21:12.097251: step: 368/530, loss: 0.04416332393884659
2023-01-21 09:21:13.240023: step: 372/530, loss: 0.08700676262378693
2023-01-21 09:21:14.394994: step: 376/530, loss: 0.3626858592033386
2023-01-21 09:21:15.521629: step: 380/530, loss: 0.1521831452846527
2023-01-21 09:21:16.635241: step: 384/530, loss: 0.26257649064064026
2023-01-21 09:21:17.797308: step: 388/530, loss: 0.3938552439212799
2023-01-21 09:21:18.938850: step: 392/530, loss: 0.1368224322795868
2023-01-21 09:21:20.085258: step: 396/530, loss: 0.5392426252365112
2023-01-21 09:21:21.205430: step: 400/530, loss: 0.5867196321487427
2023-01-21 09:21:22.320424: step: 404/530, loss: 0.08044548332691193
2023-01-21 09:21:23.429873: step: 408/530, loss: 0.490561842918396
2023-01-21 09:21:24.556234: step: 412/530, loss: 0.10304884612560272
2023-01-21 09:21:25.700470: step: 416/530, loss: 0.052866749465465546
2023-01-21 09:21:26.822716: step: 420/530, loss: 0.18571040034294128
2023-01-21 09:21:27.926677: step: 424/530, loss: 0.1016283631324768
2023-01-21 09:21:29.044740: step: 428/530, loss: 0.32809171080589294
2023-01-21 09:21:30.176484: step: 432/530, loss: 0.43588322401046753
2023-01-21 09:21:31.295151: step: 436/530, loss: 0.18912430107593536
2023-01-21 09:21:32.421288: step: 440/530, loss: 0.15097761154174805
2023-01-21 09:21:33.544446: step: 444/530, loss: 0.671211838722229
2023-01-21 09:21:34.673875: step: 448/530, loss: 1.5963035821914673
2023-01-21 09:21:35.820494: step: 452/530, loss: 0.1866540014743805
2023-01-21 09:21:36.992365: step: 456/530, loss: 0.24476033449172974
2023-01-21 09:21:38.114395: step: 460/530, loss: 0.12629517912864685
2023-01-21 09:21:39.239311: step: 464/530, loss: 0.1475435197353363
2023-01-21 09:21:40.355864: step: 468/530, loss: 0.1469893455505371
2023-01-21 09:21:41.501124: step: 472/530, loss: 0.23201203346252441
2023-01-21 09:21:42.647826: step: 476/530, loss: 0.07769317924976349
2023-01-21 09:21:43.769034: step: 480/530, loss: 0.14647254347801208
2023-01-21 09:21:44.878720: step: 484/530, loss: 0.1238466277718544
2023-01-21 09:21:45.996131: step: 488/530, loss: 0.0988299548625946
2023-01-21 09:21:47.094650: step: 492/530, loss: 0.3083796501159668
2023-01-21 09:21:48.227836: step: 496/530, loss: 0.4444504976272583
2023-01-21 09:21:49.345982: step: 500/530, loss: 0.2293771207332611
2023-01-21 09:21:50.483269: step: 504/530, loss: 0.3313515782356262
2023-01-21 09:21:51.608916: step: 508/530, loss: 0.19626016914844513
2023-01-21 09:21:52.723874: step: 512/530, loss: 0.08703222125768661
2023-01-21 09:21:53.841485: step: 516/530, loss: 0.09193181991577148
2023-01-21 09:21:54.964325: step: 520/530, loss: 0.13546772301197052
2023-01-21 09:21:56.081986: step: 524/530, loss: 0.044866085052490234
2023-01-21 09:21:57.194619: step: 528/530, loss: 0.040330030024051666
2023-01-21 09:21:58.332161: step: 532/530, loss: 0.6278777122497559
2023-01-21 09:21:59.445209: step: 536/530, loss: 0.16063614189624786
2023-01-21 09:22:00.580312: step: 540/530, loss: 0.2526487112045288
2023-01-21 09:22:01.713696: step: 544/530, loss: 0.10354487597942352
2023-01-21 09:22:02.844397: step: 548/530, loss: 0.06830969452857971
2023-01-21 09:22:03.963746: step: 552/530, loss: 0.10166035592556
2023-01-21 09:22:05.100420: step: 556/530, loss: 0.5175685882568359
2023-01-21 09:22:06.197514: step: 560/530, loss: 0.5365087389945984
2023-01-21 09:22:07.374357: step: 564/530, loss: 0.0465024933218956
2023-01-21 09:22:08.494816: step: 568/530, loss: 0.15384580194950104
2023-01-21 09:22:09.623955: step: 572/530, loss: 0.07074346393346786
2023-01-21 09:22:10.748963: step: 576/530, loss: 0.5204747319221497
2023-01-21 09:22:11.889641: step: 580/530, loss: 0.17314299941062927
2023-01-21 09:22:13.065710: step: 584/530, loss: 1.2452647686004639
2023-01-21 09:22:14.194560: step: 588/530, loss: 0.207940012216568
2023-01-21 09:22:15.311598: step: 592/530, loss: 0.019712068140506744
2023-01-21 09:22:16.412320: step: 596/530, loss: 0.08395443856716156
2023-01-21 09:22:17.529840: step: 600/530, loss: 0.24348679184913635
2023-01-21 09:22:18.659433: step: 604/530, loss: 0.10326090455055237
2023-01-21 09:22:19.794237: step: 608/530, loss: 0.43974122405052185
2023-01-21 09:22:20.918241: step: 612/530, loss: 0.1816503405570984
2023-01-21 09:22:22.076691: step: 616/530, loss: 0.1156463623046875
2023-01-21 09:22:23.187664: step: 620/530, loss: 0.10953550040721893
2023-01-21 09:22:24.320654: step: 624/530, loss: 0.03271923214197159
2023-01-21 09:22:25.425414: step: 628/530, loss: 0.3760426640510559
2023-01-21 09:22:26.507703: step: 632/530, loss: 0.17508994042873383
2023-01-21 09:22:27.644496: step: 636/530, loss: 0.09670362621545792
2023-01-21 09:22:28.800008: step: 640/530, loss: 0.21797600388526917
2023-01-21 09:22:29.922942: step: 644/530, loss: 0.3582476079463959
2023-01-21 09:22:31.041296: step: 648/530, loss: 0.06395077705383301
2023-01-21 09:22:32.159707: step: 652/530, loss: 0.05302887409925461
2023-01-21 09:22:33.272849: step: 656/530, loss: 0.038953591138124466
2023-01-21 09:22:34.410943: step: 660/530, loss: 0.13032856583595276
2023-01-21 09:22:35.513985: step: 664/530, loss: 0.1422923058271408
2023-01-21 09:22:36.583153: step: 668/530, loss: 0.5913253426551819
2023-01-21 09:22:37.699321: step: 672/530, loss: 0.5791007280349731
2023-01-21 09:22:38.849304: step: 676/530, loss: 0.09437239170074463
2023-01-21 09:22:39.972167: step: 680/530, loss: 0.1497097909450531
2023-01-21 09:22:41.105365: step: 684/530, loss: 0.19355785846710205
2023-01-21 09:22:42.211567: step: 688/530, loss: 0.13408851623535156
2023-01-21 09:22:43.325548: step: 692/530, loss: 0.3380964398384094
2023-01-21 09:22:44.434819: step: 696/530, loss: 0.19491642713546753
2023-01-21 09:22:45.567519: step: 700/530, loss: 0.19311437010765076
2023-01-21 09:22:46.705837: step: 704/530, loss: 0.1483035534620285
2023-01-21 09:22:47.824510: step: 708/530, loss: 0.3194564878940582
2023-01-21 09:22:48.940248: step: 712/530, loss: 0.08179903030395508
2023-01-21 09:22:50.066715: step: 716/530, loss: 0.2908279597759247
2023-01-21 09:22:51.191774: step: 720/530, loss: 0.10363516956567764
2023-01-21 09:22:52.305459: step: 724/530, loss: 0.07589159905910492
2023-01-21 09:22:53.445482: step: 728/530, loss: 0.09766826778650284
2023-01-21 09:22:54.567822: step: 732/530, loss: 0.2257830798625946
2023-01-21 09:22:55.691791: step: 736/530, loss: 0.5136715173721313
2023-01-21 09:22:56.830803: step: 740/530, loss: 0.12021151185035706
2023-01-21 09:22:57.977484: step: 744/530, loss: 0.17326650023460388
2023-01-21 09:22:59.101157: step: 748/530, loss: 0.04267315939068794
2023-01-21 09:23:00.248956: step: 752/530, loss: 0.10617952048778534
2023-01-21 09:23:01.408366: step: 756/530, loss: 0.2369038611650467
2023-01-21 09:23:02.565360: step: 760/530, loss: 0.05305519327521324
2023-01-21 09:23:03.708785: step: 764/530, loss: 0.24194279313087463
2023-01-21 09:23:04.829183: step: 768/530, loss: 1.0865648984909058
2023-01-21 09:23:05.954482: step: 772/530, loss: 0.14510604739189148
2023-01-21 09:23:07.049985: step: 776/530, loss: 0.15307465195655823
2023-01-21 09:23:08.178224: step: 780/530, loss: 0.04640016704797745
2023-01-21 09:23:09.333040: step: 784/530, loss: 0.34444141387939453
2023-01-21 09:23:10.449000: step: 788/530, loss: 0.11877629160881042
2023-01-21 09:23:11.564296: step: 792/530, loss: 0.07700634002685547
2023-01-21 09:23:12.676678: step: 796/530, loss: 0.3511069118976593
2023-01-21 09:23:13.822171: step: 800/530, loss: 0.41715505719184875
2023-01-21 09:23:14.946377: step: 804/530, loss: 0.13137730956077576
2023-01-21 09:23:16.047958: step: 808/530, loss: 0.12022048234939575
2023-01-21 09:23:17.184556: step: 812/530, loss: 0.13441486656665802
2023-01-21 09:23:18.312072: step: 816/530, loss: 0.2620023787021637
2023-01-21 09:23:19.472218: step: 820/530, loss: 0.06594095379114151
2023-01-21 09:23:20.584424: step: 824/530, loss: 0.17283029854297638
2023-01-21 09:23:21.699391: step: 828/530, loss: 0.14289219677448273
2023-01-21 09:23:22.799688: step: 832/530, loss: 1.140893816947937
2023-01-21 09:23:23.917097: step: 836/530, loss: 0.5993806719779968
2023-01-21 09:23:25.025852: step: 840/530, loss: 0.09278631210327148
2023-01-21 09:23:26.157717: step: 844/530, loss: 0.10381016880273819
2023-01-21 09:23:27.265403: step: 848/530, loss: 0.5966172218322754
2023-01-21 09:23:28.405993: step: 852/530, loss: 0.26500165462493896
2023-01-21 09:23:29.526854: step: 856/530, loss: 0.15709298849105835
2023-01-21 09:23:30.635941: step: 860/530, loss: 0.08998998999595642
2023-01-21 09:23:31.749985: step: 864/530, loss: 0.09043969959020615
2023-01-21 09:23:32.873242: step: 868/530, loss: 0.22988061606884003
2023-01-21 09:23:33.981448: step: 872/530, loss: 0.15304259955883026
2023-01-21 09:23:35.088315: step: 876/530, loss: 0.05835294723510742
2023-01-21 09:23:36.215962: step: 880/530, loss: 0.5869282484054565
2023-01-21 09:23:37.335665: step: 884/530, loss: 0.06869509816169739
2023-01-21 09:23:38.465259: step: 888/530, loss: 0.5883738398551941
2023-01-21 09:23:39.645475: step: 892/530, loss: 0.13258734345436096
2023-01-21 09:23:40.754822: step: 896/530, loss: 0.25757285952568054
2023-01-21 09:23:41.879712: step: 900/530, loss: 0.074462890625
2023-01-21 09:23:42.994149: step: 904/530, loss: 0.22323136031627655
2023-01-21 09:23:44.108855: step: 908/530, loss: 0.08468742668628693
2023-01-21 09:23:45.235032: step: 912/530, loss: 0.10809478908777237
2023-01-21 09:23:46.408602: step: 916/530, loss: 0.7821671962738037
2023-01-21 09:23:47.555622: step: 920/530, loss: 0.1058753952383995
2023-01-21 09:23:48.710605: step: 924/530, loss: 0.07042007148265839
2023-01-21 09:23:49.816550: step: 928/530, loss: 0.26982536911964417
2023-01-21 09:23:50.920475: step: 932/530, loss: 0.09188766777515411
2023-01-21 09:23:52.083452: step: 936/530, loss: 0.35422927141189575
2023-01-21 09:23:53.232761: step: 940/530, loss: 0.7445580959320068
2023-01-21 09:23:54.362797: step: 944/530, loss: 0.04747777059674263
2023-01-21 09:23:55.480500: step: 948/530, loss: 0.09176960587501526
2023-01-21 09:23:56.603632: step: 952/530, loss: 0.06079930067062378
2023-01-21 09:23:57.751613: step: 956/530, loss: 0.0665692389011383
2023-01-21 09:23:58.862753: step: 960/530, loss: 0.11003494262695312
2023-01-21 09:24:00.009575: step: 964/530, loss: 0.1225917860865593
2023-01-21 09:24:01.160273: step: 968/530, loss: 0.057576559484004974
2023-01-21 09:24:02.295068: step: 972/530, loss: 0.9640516042709351
2023-01-21 09:24:03.467435: step: 976/530, loss: 0.13804513216018677
2023-01-21 09:24:04.566891: step: 980/530, loss: 0.05690355598926544
2023-01-21 09:24:05.692059: step: 984/530, loss: 0.11256230622529984
2023-01-21 09:24:06.843677: step: 988/530, loss: 0.312844455242157
2023-01-21 09:24:07.964579: step: 992/530, loss: 0.06485471874475479
2023-01-21 09:24:09.099023: step: 996/530, loss: 0.24370832741260529
2023-01-21 09:24:10.215951: step: 1000/530, loss: 0.1107872948050499
2023-01-21 09:24:11.315170: step: 1004/530, loss: 0.18152594566345215
2023-01-21 09:24:12.416611: step: 1008/530, loss: 0.3008895814418793
2023-01-21 09:24:13.512540: step: 1012/530, loss: 0.10740160942077637
2023-01-21 09:24:14.665968: step: 1016/530, loss: 0.1232067197561264
2023-01-21 09:24:15.785833: step: 1020/530, loss: 0.11176462471485138
2023-01-21 09:24:16.903709: step: 1024/530, loss: 0.05635805055499077
2023-01-21 09:24:18.014036: step: 1028/530, loss: 0.13475151360034943
2023-01-21 09:24:19.146657: step: 1032/530, loss: 0.4001826345920563
2023-01-21 09:24:20.289883: step: 1036/530, loss: 0.18724600970745087
2023-01-21 09:24:21.396848: step: 1040/530, loss: 0.05257861688733101
2023-01-21 09:24:22.537499: step: 1044/530, loss: 0.4860478341579437
2023-01-21 09:24:23.648432: step: 1048/530, loss: 0.2075042724609375
2023-01-21 09:24:24.768605: step: 1052/530, loss: 0.1154942512512207
2023-01-21 09:24:25.885783: step: 1056/530, loss: 0.06639137119054794
2023-01-21 09:24:26.999051: step: 1060/530, loss: 0.9118468761444092
2023-01-21 09:24:28.155733: step: 1064/530, loss: 0.08206520974636078
2023-01-21 09:24:29.271285: step: 1068/530, loss: 0.16710948944091797
2023-01-21 09:24:30.389487: step: 1072/530, loss: 0.20957517623901367
2023-01-21 09:24:31.512291: step: 1076/530, loss: 0.4679213762283325
2023-01-21 09:24:32.634301: step: 1080/530, loss: 0.1396736204624176
2023-01-21 09:24:33.757650: step: 1084/530, loss: 0.05888848751783371
2023-01-21 09:24:34.876779: step: 1088/530, loss: 0.09545326232910156
2023-01-21 09:24:36.020599: step: 1092/530, loss: 0.044793032109737396
2023-01-21 09:24:37.145315: step: 1096/530, loss: 0.16030049324035645
2023-01-21 09:24:38.271427: step: 1100/530, loss: 0.3537948727607727
2023-01-21 09:24:39.379580: step: 1104/530, loss: 0.05103006213903427
2023-01-21 09:24:40.509292: step: 1108/530, loss: 0.047654539346694946
2023-01-21 09:24:41.646075: step: 1112/530, loss: 0.19664603471755981
2023-01-21 09:24:42.756950: step: 1116/530, loss: 0.4600929319858551
2023-01-21 09:24:43.892970: step: 1120/530, loss: 0.08519162982702255
2023-01-21 09:24:45.038218: step: 1124/530, loss: 0.44426119327545166
2023-01-21 09:24:46.195979: step: 1128/530, loss: 0.19597744941711426
2023-01-21 09:24:47.296145: step: 1132/530, loss: 0.04792299121618271
2023-01-21 09:24:48.391875: step: 1136/530, loss: 0.11004962772130966
2023-01-21 09:24:49.523969: step: 1140/530, loss: 0.1282147467136383
2023-01-21 09:24:50.660639: step: 1144/530, loss: 0.23563870787620544
2023-01-21 09:24:51.776654: step: 1148/530, loss: 0.1534150093793869
2023-01-21 09:24:52.889960: step: 1152/530, loss: 0.014919042587280273
2023-01-21 09:24:54.022887: step: 1156/530, loss: 0.3591992259025574
2023-01-21 09:24:55.144625: step: 1160/530, loss: 0.2913808822631836
2023-01-21 09:24:56.263694: step: 1164/530, loss: 0.37747278809547424
2023-01-21 09:24:57.397376: step: 1168/530, loss: 0.4004940986633301
2023-01-21 09:24:58.570240: step: 1172/530, loss: 0.08267870545387268
2023-01-21 09:24:59.711761: step: 1176/530, loss: 0.25983744859695435
2023-01-21 09:25:00.848028: step: 1180/530, loss: 0.14484748244285583
2023-01-21 09:25:01.953714: step: 1184/530, loss: 0.08454503864049911
2023-01-21 09:25:03.100187: step: 1188/530, loss: 0.12518340349197388
2023-01-21 09:25:04.229826: step: 1192/530, loss: 0.16108350455760956
2023-01-21 09:25:05.341619: step: 1196/530, loss: 0.07637319713830948
2023-01-21 09:25:06.462452: step: 1200/530, loss: 0.05120735242962837
2023-01-21 09:25:07.574878: step: 1204/530, loss: 0.6247413754463196
2023-01-21 09:25:08.666800: step: 1208/530, loss: 0.44350355863571167
2023-01-21 09:25:09.780273: step: 1212/530, loss: 0.20133991539478302
2023-01-21 09:25:10.886528: step: 1216/530, loss: 0.09835930168628693
2023-01-21 09:25:12.033929: step: 1220/530, loss: 0.15910738706588745
2023-01-21 09:25:13.205528: step: 1224/530, loss: 0.0912107527256012
2023-01-21 09:25:14.308903: step: 1228/530, loss: 0.09170942008495331
2023-01-21 09:25:15.368843: step: 1232/530, loss: 0.03578028827905655
2023-01-21 09:25:16.520681: step: 1236/530, loss: 0.5063158869743347
2023-01-21 09:25:17.641076: step: 1240/530, loss: 0.03750190883874893
2023-01-21 09:25:18.781540: step: 1244/530, loss: 0.4150182008743286
2023-01-21 09:25:19.893879: step: 1248/530, loss: 0.10190348327159882
2023-01-21 09:25:21.022951: step: 1252/530, loss: 0.08628308773040771
2023-01-21 09:25:22.127319: step: 1256/530, loss: 0.010641051456332207
2023-01-21 09:25:23.262260: step: 1260/530, loss: 0.4293396770954132
2023-01-21 09:25:24.381329: step: 1264/530, loss: 0.1042017936706543
2023-01-21 09:25:25.513147: step: 1268/530, loss: 0.40181973576545715
2023-01-21 09:25:26.628276: step: 1272/530, loss: 0.4539757966995239
2023-01-21 09:25:27.761666: step: 1276/530, loss: 0.04647216945886612
2023-01-21 09:25:28.879635: step: 1280/530, loss: 0.103580042719841
2023-01-21 09:25:29.988695: step: 1284/530, loss: 0.6041619181632996
2023-01-21 09:25:31.073132: step: 1288/530, loss: 0.23835164308547974
2023-01-21 09:25:32.225083: step: 1292/530, loss: 0.1521662473678589
2023-01-21 09:25:33.347774: step: 1296/530, loss: 0.14514799416065216
2023-01-21 09:25:34.461975: step: 1300/530, loss: 0.07047128677368164
2023-01-21 09:25:35.591278: step: 1304/530, loss: 0.2801291048526764
2023-01-21 09:25:36.739146: step: 1308/530, loss: 0.3373778462409973
2023-01-21 09:25:37.851769: step: 1312/530, loss: 0.8691965937614441
2023-01-21 09:25:38.949709: step: 1316/530, loss: 0.06026478111743927
2023-01-21 09:25:40.083807: step: 1320/530, loss: 0.18016988039016724
2023-01-21 09:25:41.198593: step: 1324/530, loss: 0.07727446407079697
2023-01-21 09:25:42.304356: step: 1328/530, loss: 0.15874509513378143
2023-01-21 09:25:43.420460: step: 1332/530, loss: 0.06604871898889542
2023-01-21 09:25:44.576807: step: 1336/530, loss: 0.19367733597755432
2023-01-21 09:25:45.705307: step: 1340/530, loss: 0.10540228337049484
2023-01-21 09:25:46.810899: step: 1344/530, loss: 0.4208540916442871
2023-01-21 09:25:47.941776: step: 1348/530, loss: 0.20355644822120667
2023-01-21 09:25:49.058371: step: 1352/530, loss: 0.31035566329956055
2023-01-21 09:25:50.173516: step: 1356/530, loss: 0.2901880741119385
2023-01-21 09:25:51.280831: step: 1360/530, loss: 0.09144363552331924
2023-01-21 09:25:52.406364: step: 1364/530, loss: 0.014129210263490677
2023-01-21 09:25:53.560641: step: 1368/530, loss: 0.7443875074386597
2023-01-21 09:25:54.678812: step: 1372/530, loss: 0.11810608208179474
2023-01-21 09:25:55.770163: step: 1376/530, loss: 0.5168406963348389
2023-01-21 09:25:56.898605: step: 1380/530, loss: 0.16402606666088104
2023-01-21 09:25:58.015882: step: 1384/530, loss: 0.08584009110927582
2023-01-21 09:25:59.154753: step: 1388/530, loss: 0.23799744248390198
2023-01-21 09:26:00.271827: step: 1392/530, loss: 0.23348312079906464
2023-01-21 09:26:01.416563: step: 1396/530, loss: 0.823794424533844
2023-01-21 09:26:02.540002: step: 1400/530, loss: 0.1546565145254135
2023-01-21 09:26:03.678673: step: 1404/530, loss: 0.2717716693878174
2023-01-21 09:26:04.788148: step: 1408/530, loss: 0.2602858543395996
2023-01-21 09:26:05.913309: step: 1412/530, loss: 0.9619173407554626
2023-01-21 09:26:07.039869: step: 1416/530, loss: 0.5547990202903748
2023-01-21 09:26:08.159254: step: 1420/530, loss: 0.13050489127635956
2023-01-21 09:26:09.279274: step: 1424/530, loss: 0.14009436964988708
2023-01-21 09:26:10.425964: step: 1428/530, loss: 0.03670034185051918
2023-01-21 09:26:11.525079: step: 1432/530, loss: 0.06494155526161194
2023-01-21 09:26:12.654979: step: 1436/530, loss: 0.27621030807495117
2023-01-21 09:26:13.829398: step: 1440/530, loss: 0.6529596447944641
2023-01-21 09:26:14.964696: step: 1444/530, loss: 0.0682094544172287
2023-01-21 09:26:16.096159: step: 1448/530, loss: 0.3881278932094574
2023-01-21 09:26:17.226622: step: 1452/530, loss: 0.9283435344696045
2023-01-21 09:26:18.332748: step: 1456/530, loss: 0.08008800446987152
2023-01-21 09:26:19.453793: step: 1460/530, loss: 0.10517697036266327
2023-01-21 09:26:20.596082: step: 1464/530, loss: 0.3689754605293274
2023-01-21 09:26:21.683611: step: 1468/530, loss: 1.9221255779266357
2023-01-21 09:26:22.824743: step: 1472/530, loss: 0.16830691695213318
2023-01-21 09:26:23.923485: step: 1476/530, loss: 0.07905427366495132
2023-01-21 09:26:25.048380: step: 1480/530, loss: 0.1761879026889801
2023-01-21 09:26:26.174692: step: 1484/530, loss: 1.4609920978546143
2023-01-21 09:26:27.315802: step: 1488/530, loss: 0.22796781361103058
2023-01-21 09:26:28.418772: step: 1492/530, loss: 0.18301787972450256
2023-01-21 09:26:29.539701: step: 1496/530, loss: 0.7601524591445923
2023-01-21 09:26:30.646488: step: 1500/530, loss: 1.4826362133026123
2023-01-21 09:26:31.758935: step: 1504/530, loss: 0.07959934324026108
2023-01-21 09:26:32.870838: step: 1508/530, loss: 0.2915472984313965
2023-01-21 09:26:33.992636: step: 1512/530, loss: 0.03482165187597275
2023-01-21 09:26:35.086709: step: 1516/530, loss: 0.2605397403240204
2023-01-21 09:26:36.232447: step: 1520/530, loss: 0.12189693748950958
2023-01-21 09:26:37.379717: step: 1524/530, loss: 0.18373775482177734
2023-01-21 09:26:38.511913: step: 1528/530, loss: 0.18816213309764862
2023-01-21 09:26:39.635310: step: 1532/530, loss: 0.10893383622169495
2023-01-21 09:26:40.772435: step: 1536/530, loss: 0.08929157257080078
2023-01-21 09:26:41.910669: step: 1540/530, loss: 0.3500238060951233
2023-01-21 09:26:43.032042: step: 1544/530, loss: 0.02064676210284233
2023-01-21 09:26:44.122321: step: 1548/530, loss: 0.04589357599616051
2023-01-21 09:26:45.223851: step: 1552/530, loss: 0.1696067750453949
2023-01-21 09:26:46.351794: step: 1556/530, loss: 0.16545256972312927
2023-01-21 09:26:47.466242: step: 1560/530, loss: 0.0654686912894249
2023-01-21 09:26:48.594430: step: 1564/530, loss: 0.6287447810173035
2023-01-21 09:26:49.706761: step: 1568/530, loss: 0.1089734137058258
2023-01-21 09:26:50.825060: step: 1572/530, loss: 0.06013832241296768
2023-01-21 09:26:51.956698: step: 1576/530, loss: 0.07506036758422852
2023-01-21 09:26:53.081751: step: 1580/530, loss: 0.5531541109085083
2023-01-21 09:26:54.193823: step: 1584/530, loss: 0.06878586113452911
2023-01-21 09:26:55.308229: step: 1588/530, loss: 0.1207190528512001
2023-01-21 09:26:56.435146: step: 1592/530, loss: 0.278353214263916
2023-01-21 09:26:57.545984: step: 1596/530, loss: 0.05043058469891548
2023-01-21 09:26:58.667701: step: 1600/530, loss: 0.1797867715358734
2023-01-21 09:26:59.764109: step: 1604/530, loss: 0.0501859188079834
2023-01-21 09:27:00.902428: step: 1608/530, loss: 0.8419907689094543
2023-01-21 09:27:02.097985: step: 1612/530, loss: 0.09508943557739258
2023-01-21 09:27:03.214757: step: 1616/530, loss: 0.14453211426734924
2023-01-21 09:27:04.336554: step: 1620/530, loss: 0.05309171974658966
2023-01-21 09:27:05.469531: step: 1624/530, loss: 0.08540558815002441
2023-01-21 09:27:06.591866: step: 1628/530, loss: 0.3839705288410187
2023-01-21 09:27:07.711336: step: 1632/530, loss: 0.2065594643354416
2023-01-21 09:27:08.846292: step: 1636/530, loss: 1.3691645860671997
2023-01-21 09:27:09.982954: step: 1640/530, loss: 0.4003581404685974
2023-01-21 09:27:11.117122: step: 1644/530, loss: 0.7048473954200745
2023-01-21 09:27:12.239659: step: 1648/530, loss: 0.24850665032863617
2023-01-21 09:27:13.369626: step: 1652/530, loss: 0.02414698526263237
2023-01-21 09:27:14.502036: step: 1656/530, loss: 0.08642005920410156
2023-01-21 09:27:15.643045: step: 1660/530, loss: 0.6366859674453735
2023-01-21 09:27:16.779622: step: 1664/530, loss: 0.1102198138833046
2023-01-21 09:27:17.935252: step: 1668/530, loss: 0.06933679431676865
2023-01-21 09:27:19.053262: step: 1672/530, loss: 0.2849675714969635
2023-01-21 09:27:20.178975: step: 1676/530, loss: 0.31922245025634766
2023-01-21 09:27:21.314503: step: 1680/530, loss: 0.42438358068466187
2023-01-21 09:27:22.423533: step: 1684/530, loss: 0.10104990005493164
2023-01-21 09:27:23.527855: step: 1688/530, loss: 0.08451852947473526
2023-01-21 09:27:24.665676: step: 1692/530, loss: 0.32380664348602295
2023-01-21 09:27:25.787045: step: 1696/530, loss: 0.2716783583164215
2023-01-21 09:27:26.923271: step: 1700/530, loss: 0.14854370057582855
2023-01-21 09:27:28.028745: step: 1704/530, loss: 0.07838621735572815
2023-01-21 09:27:29.153503: step: 1708/530, loss: 0.30359622836112976
2023-01-21 09:27:30.285974: step: 1712/530, loss: 0.29104965925216675
2023-01-21 09:27:31.400600: step: 1716/530, loss: 0.17394447326660156
2023-01-21 09:27:32.523407: step: 1720/530, loss: 0.20211371779441833
2023-01-21 09:27:33.659653: step: 1724/530, loss: 0.09822969883680344
2023-01-21 09:27:34.754601: step: 1728/530, loss: 0.09604644775390625
2023-01-21 09:27:35.895839: step: 1732/530, loss: 0.042954444885253906
2023-01-21 09:27:37.002286: step: 1736/530, loss: 0.4413073658943176
2023-01-21 09:27:38.091267: step: 1740/530, loss: 0.15138083696365356
2023-01-21 09:27:39.232175: step: 1744/530, loss: 0.2657526135444641
2023-01-21 09:27:40.356854: step: 1748/530, loss: 0.709804356098175
2023-01-21 09:27:41.493916: step: 1752/530, loss: 0.06254644691944122
2023-01-21 09:27:42.612267: step: 1756/530, loss: 0.13190633058547974
2023-01-21 09:27:43.737834: step: 1760/530, loss: 0.04444608837366104
2023-01-21 09:27:44.846003: step: 1764/530, loss: 0.09217515587806702
2023-01-21 09:27:46.019876: step: 1768/530, loss: 0.3437265455722809
2023-01-21 09:27:47.159347: step: 1772/530, loss: 0.40223953127861023
2023-01-21 09:27:48.270838: step: 1776/530, loss: 0.8026493787765503
2023-01-21 09:27:49.379450: step: 1780/530, loss: 0.15695348381996155
2023-01-21 09:27:50.533376: step: 1784/530, loss: 0.11650065332651138
2023-01-21 09:27:51.653440: step: 1788/530, loss: 0.36791807413101196
2023-01-21 09:27:52.770555: step: 1792/530, loss: 0.02191222831606865
2023-01-21 09:27:53.908191: step: 1796/530, loss: 0.5840681791305542
2023-01-21 09:27:55.027898: step: 1800/530, loss: 0.0982985571026802
2023-01-21 09:27:56.148604: step: 1804/530, loss: 0.11985808610916138
2023-01-21 09:27:57.251194: step: 1808/530, loss: 0.16817140579223633
2023-01-21 09:27:58.401583: step: 1812/530, loss: 0.1982143521308899
2023-01-21 09:27:59.543447: step: 1816/530, loss: 0.23344996571540833
2023-01-21 09:28:00.684196: step: 1820/530, loss: 0.09022513031959534
2023-01-21 09:28:01.812539: step: 1824/530, loss: 0.5485559105873108
2023-01-21 09:28:02.915218: step: 1828/530, loss: 0.19541864097118378
2023-01-21 09:28:04.035402: step: 1832/530, loss: 0.568931519985199
2023-01-21 09:28:05.163880: step: 1836/530, loss: 0.26919302344322205
2023-01-21 09:28:06.265475: step: 1840/530, loss: 0.08027572929859161
2023-01-21 09:28:07.382271: step: 1844/530, loss: 0.06768160313367844
2023-01-21 09:28:08.519875: step: 1848/530, loss: 0.45090949535369873
2023-01-21 09:28:09.660289: step: 1852/530, loss: 0.23631440103054047
2023-01-21 09:28:10.773169: step: 1856/530, loss: 1.2236262559890747
2023-01-21 09:28:11.863300: step: 1860/530, loss: 0.13902024924755096
2023-01-21 09:28:12.999565: step: 1864/530, loss: 0.6208492517471313
2023-01-21 09:28:14.125701: step: 1868/530, loss: 0.07035932689905167
2023-01-21 09:28:15.244380: step: 1872/530, loss: 0.4000682830810547
2023-01-21 09:28:16.357654: step: 1876/530, loss: 0.21575576066970825
2023-01-21 09:28:17.513419: step: 1880/530, loss: 0.0999719649553299
2023-01-21 09:28:18.645898: step: 1884/530, loss: 0.2011333405971527
2023-01-21 09:28:19.786689: step: 1888/530, loss: 0.5587990880012512
2023-01-21 09:28:20.908649: step: 1892/530, loss: 0.5708900690078735
2023-01-21 09:28:22.045677: step: 1896/530, loss: 0.08642025291919708
2023-01-21 09:28:23.151016: step: 1900/530, loss: 0.11000652611255646
2023-01-21 09:28:24.290864: step: 1904/530, loss: 0.09740067273378372
2023-01-21 09:28:25.401278: step: 1908/530, loss: 0.11247525364160538
2023-01-21 09:28:26.522157: step: 1912/530, loss: 0.10732746124267578
2023-01-21 09:28:27.642622: step: 1916/530, loss: 0.0624576136469841
2023-01-21 09:28:28.775488: step: 1920/530, loss: 0.48494482040405273
2023-01-21 09:28:29.899101: step: 1924/530, loss: 0.27472057938575745
2023-01-21 09:28:31.007726: step: 1928/530, loss: 0.39347752928733826
2023-01-21 09:28:32.142807: step: 1932/530, loss: 0.1965927630662918
2023-01-21 09:28:33.242234: step: 1936/530, loss: 0.10447807610034943
2023-01-21 09:28:34.397377: step: 1940/530, loss: 0.17233189940452576
2023-01-21 09:28:35.493776: step: 1944/530, loss: 0.125209242105484
2023-01-21 09:28:36.617871: step: 1948/530, loss: 0.04891815409064293
2023-01-21 09:28:37.733035: step: 1952/530, loss: 0.14031849801540375
2023-01-21 09:28:38.883828: step: 1956/530, loss: 0.13968229293823242
2023-01-21 09:28:40.022156: step: 1960/530, loss: 0.19782835245132446
2023-01-21 09:28:41.128201: step: 1964/530, loss: 0.23898521065711975
2023-01-21 09:28:42.300173: step: 1968/530, loss: 0.10926322638988495
2023-01-21 09:28:43.425981: step: 1972/530, loss: 0.18810200691223145
2023-01-21 09:28:44.560324: step: 1976/530, loss: 0.06363999843597412
2023-01-21 09:28:45.668079: step: 1980/530, loss: 0.08606290817260742
2023-01-21 09:28:46.845465: step: 1984/530, loss: 0.07819166034460068
2023-01-21 09:28:47.945896: step: 1988/530, loss: 0.07699299603700638
2023-01-21 09:28:49.100006: step: 1992/530, loss: 0.18645472824573517
2023-01-21 09:28:50.205238: step: 1996/530, loss: 0.04337611421942711
2023-01-21 09:28:51.336994: step: 2000/530, loss: 0.2782968580722809
2023-01-21 09:28:52.453248: step: 2004/530, loss: 0.9622762203216553
2023-01-21 09:28:53.555737: step: 2008/530, loss: 0.010148381814360619
2023-01-21 09:28:54.676127: step: 2012/530, loss: 0.05298314243555069
2023-01-21 09:28:55.789291: step: 2016/530, loss: 0.8698732852935791
2023-01-21 09:28:56.889657: step: 2020/530, loss: 0.42634153366088867
2023-01-21 09:28:58.008053: step: 2024/530, loss: 0.10237999260425568
2023-01-21 09:28:59.140508: step: 2028/530, loss: 0.3417743742465973
2023-01-21 09:29:00.277274: step: 2032/530, loss: 0.17312544584274292
2023-01-21 09:29:01.422159: step: 2036/530, loss: 0.03941159322857857
2023-01-21 09:29:02.585222: step: 2040/530, loss: 0.11214208602905273
2023-01-21 09:29:03.697944: step: 2044/530, loss: 0.5566015839576721
2023-01-21 09:29:04.818874: step: 2048/530, loss: 0.18551188707351685
2023-01-21 09:29:05.931506: step: 2052/530, loss: 0.04253873974084854
2023-01-21 09:29:07.062719: step: 2056/530, loss: 0.10253920406103134
2023-01-21 09:29:08.199452: step: 2060/530, loss: 1.281870722770691
2023-01-21 09:29:09.322677: step: 2064/530, loss: 0.2358206957578659
2023-01-21 09:29:10.428438: step: 2068/530, loss: 0.07573598623275757
2023-01-21 09:29:11.545982: step: 2072/530, loss: 0.30315670371055603
2023-01-21 09:29:12.682085: step: 2076/530, loss: 0.3258075714111328
2023-01-21 09:29:13.809204: step: 2080/530, loss: 0.11895184218883514
2023-01-21 09:29:14.914603: step: 2084/530, loss: 0.06229085847735405
2023-01-21 09:29:16.022781: step: 2088/530, loss: 0.08908441662788391
2023-01-21 09:29:17.145511: step: 2092/530, loss: 0.11622504889965057
2023-01-21 09:29:18.267824: step: 2096/530, loss: 0.1601143777370453
2023-01-21 09:29:19.383901: step: 2100/530, loss: 0.087957963347435
2023-01-21 09:29:20.492352: step: 2104/530, loss: 0.08399859070777893
2023-01-21 09:29:21.620316: step: 2108/530, loss: 0.09608087688684464
2023-01-21 09:29:22.763619: step: 2112/530, loss: 0.20828914642333984
2023-01-21 09:29:23.884404: step: 2116/530, loss: 1.5464457273483276
2023-01-21 09:29:25.020549: step: 2120/530, loss: 0.41183242201805115
==================================================
Loss: 0.257
--------------------
Dev: {'event': {'p': 0.5623781676413255, 'r': 0.7683089214380826, 'f1': 0.6494091164884638}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6135852451641925, 'r': 0.7794285714285715, 'f1': 0.6866347847973824}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.6049382716049383, 'r': 0.9074074074074074, 'f1': 0.725925925925926}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.6458333333333334, 'r': 0.49206349206349204, 'f1': 0.5585585585585586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.5, 'r': 0.6388888888888888, 'f1': 0.5609756097560975}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Chinese: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 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
2023-01-21 09:30:05.973501: step: 4/530, loss: 0.11194248497486115
2023-01-21 09:30:07.097598: step: 8/530, loss: 0.049623921513557434
2023-01-21 09:30:08.207833: step: 12/530, loss: 0.2674240171909332
2023-01-21 09:30:09.351192: step: 16/530, loss: 0.4016891419887543
2023-01-21 09:30:10.451897: step: 20/530, loss: 0.08837618678808212
2023-01-21 09:30:11.590857: step: 24/530, loss: 0.1961146891117096
2023-01-21 09:30:12.731146: step: 28/530, loss: 0.5754033923149109
2023-01-21 09:30:13.860028: step: 32/530, loss: 0.07500315457582474
2023-01-21 09:30:14.981107: step: 36/530, loss: 0.28617429733276367
2023-01-21 09:30:16.106254: step: 40/530, loss: 0.11771003901958466
2023-01-21 09:30:17.225761: step: 44/530, loss: 0.10080128163099289
2023-01-21 09:30:18.351405: step: 48/530, loss: 0.07413606345653534
2023-01-21 09:30:19.451745: step: 52/530, loss: 0.1635688841342926
2023-01-21 09:30:20.565016: step: 56/530, loss: 1.0997036695480347
2023-01-21 09:30:21.679318: step: 60/530, loss: 0.060564424842596054
2023-01-21 09:30:22.794139: step: 64/530, loss: 0.0589059442281723
2023-01-21 09:30:23.892245: step: 68/530, loss: 0.1011110320687294
2023-01-21 09:30:25.011921: step: 72/530, loss: 0.05460335314273834
2023-01-21 09:30:26.123233: step: 76/530, loss: 0.019150162115693092
2023-01-21 09:30:27.242805: step: 80/530, loss: 0.10857105255126953
2023-01-21 09:30:28.397011: step: 84/530, loss: 0.1468132585287094
2023-01-21 09:30:29.517804: step: 88/530, loss: 0.20085926353931427
2023-01-21 09:30:30.665759: step: 92/530, loss: 0.03862953186035156
2023-01-21 09:30:31.783454: step: 96/530, loss: 0.14193525910377502
2023-01-21 09:30:32.907812: step: 100/530, loss: 0.053687430918216705
2023-01-21 09:30:34.008564: step: 104/530, loss: 0.21082444489002228
2023-01-21 09:30:35.151246: step: 108/530, loss: 0.3369824290275574
2023-01-21 09:30:36.290973: step: 112/530, loss: 0.09846735000610352
2023-01-21 09:30:37.415786: step: 116/530, loss: 0.06406798213720322
2023-01-21 09:30:38.528700: step: 120/530, loss: 0.06315302848815918
2023-01-21 09:30:39.639035: step: 124/530, loss: 0.14239558577537537
2023-01-21 09:30:40.777744: step: 128/530, loss: 0.09159211814403534
2023-01-21 09:30:41.894508: step: 132/530, loss: 0.16498985886573792
2023-01-21 09:30:43.031744: step: 136/530, loss: 0.39249420166015625
2023-01-21 09:30:44.154024: step: 140/530, loss: 0.24727730453014374
2023-01-21 09:30:45.280947: step: 144/530, loss: 0.08183468878269196
2023-01-21 09:30:46.411366: step: 148/530, loss: 0.18683281540870667
2023-01-21 09:30:47.542080: step: 152/530, loss: 0.2134561687707901
2023-01-21 09:30:48.619893: step: 156/530, loss: 0.11397352814674377
2023-01-21 09:30:49.720918: step: 160/530, loss: 0.1358993500471115
2023-01-21 09:30:50.856204: step: 164/530, loss: 0.6313165426254272
2023-01-21 09:30:51.966674: step: 168/530, loss: 0.16857090592384338
2023-01-21 09:30:53.114563: step: 172/530, loss: 0.29583850502967834
2023-01-21 09:30:54.237144: step: 176/530, loss: 0.12963418662548065
2023-01-21 09:30:55.373348: step: 180/530, loss: 0.04939279705286026
2023-01-21 09:30:56.502689: step: 184/530, loss: 0.17047253251075745
2023-01-21 09:30:57.623711: step: 188/530, loss: 0.4329880475997925
2023-01-21 09:30:58.763188: step: 192/530, loss: 1.1938530206680298
2023-01-21 09:30:59.915811: step: 196/530, loss: 0.0672723799943924
2023-01-21 09:31:01.021444: step: 200/530, loss: 0.15000496804714203
2023-01-21 09:31:02.165958: step: 204/530, loss: 0.010749245062470436
2023-01-21 09:31:03.302434: step: 208/530, loss: 0.08671312034130096
2023-01-21 09:31:04.440914: step: 212/530, loss: 0.13785028457641602
2023-01-21 09:31:05.579870: step: 216/530, loss: 0.09297370910644531
2023-01-21 09:31:06.685097: step: 220/530, loss: 0.7623798251152039
2023-01-21 09:31:07.807177: step: 224/530, loss: 0.33997198939323425
2023-01-21 09:31:08.935837: step: 228/530, loss: 0.20066604018211365
2023-01-21 09:31:10.051227: step: 232/530, loss: 0.22781620919704437
2023-01-21 09:31:11.174204: step: 236/530, loss: 0.12429914623498917
2023-01-21 09:31:12.294117: step: 240/530, loss: 0.0406736359000206
2023-01-21 09:31:13.418937: step: 244/530, loss: 0.1048862487077713
2023-01-21 09:31:14.548702: step: 248/530, loss: 0.26026782393455505
2023-01-21 09:31:15.677987: step: 252/530, loss: 0.11861743777990341
2023-01-21 09:31:16.785465: step: 256/530, loss: 0.17957691848278046
2023-01-21 09:31:17.925533: step: 260/530, loss: 0.6569564342498779
2023-01-21 09:31:19.026167: step: 264/530, loss: 0.3405083119869232
2023-01-21 09:31:20.177226: step: 268/530, loss: 0.21052753925323486
2023-01-21 09:31:21.298377: step: 272/530, loss: 0.3186979591846466
2023-01-21 09:31:22.415839: step: 276/530, loss: 0.03326263278722763
2023-01-21 09:31:23.532757: step: 280/530, loss: 0.020763732492923737
2023-01-21 09:31:24.647389: step: 284/530, loss: 0.1216953694820404
2023-01-21 09:31:25.759956: step: 288/530, loss: 0.13241548836231232
2023-01-21 09:31:26.894625: step: 292/530, loss: 0.3040769696235657
2023-01-21 09:31:28.026394: step: 296/530, loss: 0.4823044538497925
2023-01-21 09:31:29.192008: step: 300/530, loss: 0.12489767372608185
2023-01-21 09:31:30.300723: step: 304/530, loss: 0.12295909225940704
2023-01-21 09:31:31.452165: step: 308/530, loss: 0.042694948613643646
2023-01-21 09:31:32.587299: step: 312/530, loss: 0.14850598573684692
2023-01-21 09:31:33.679708: step: 316/530, loss: 0.10556916892528534
2023-01-21 09:31:34.756474: step: 320/530, loss: 0.11462660133838654
2023-01-21 09:31:35.874530: step: 324/530, loss: 0.08037600666284561
2023-01-21 09:31:36.987149: step: 328/530, loss: 0.16339492797851562
2023-01-21 09:31:38.086612: step: 332/530, loss: 0.08692774921655655
2023-01-21 09:31:39.223966: step: 336/530, loss: 0.10949669778347015
2023-01-21 09:31:40.347318: step: 340/530, loss: 0.12452287971973419
2023-01-21 09:31:41.489917: step: 344/530, loss: 0.01850919798016548
2023-01-21 09:31:42.638929: step: 348/530, loss: 0.03559465333819389
2023-01-21 09:31:43.750142: step: 352/530, loss: 0.060702040791511536
2023-01-21 09:31:44.871946: step: 356/530, loss: 0.11019151657819748
2023-01-21 09:31:46.003222: step: 360/530, loss: 0.047522544860839844
2023-01-21 09:31:47.123735: step: 364/530, loss: 0.15981540083885193
2023-01-21 09:31:48.224467: step: 368/530, loss: 0.021494578570127487
2023-01-21 09:31:49.340837: step: 372/530, loss: 0.1744919866323471
2023-01-21 09:31:50.465519: step: 376/530, loss: 0.11825066059827805
2023-01-21 09:31:51.604816: step: 380/530, loss: 0.08242321014404297
2023-01-21 09:31:52.726345: step: 384/530, loss: 0.08118505775928497
2023-01-21 09:31:53.834683: step: 388/530, loss: 0.027975846081972122
2023-01-21 09:31:54.990946: step: 392/530, loss: 0.044190309941768646
2023-01-21 09:31:56.118127: step: 396/530, loss: 0.0552341490983963
2023-01-21 09:31:57.271304: step: 400/530, loss: 0.6174713373184204
2023-01-21 09:31:58.424298: step: 404/530, loss: 0.6127270460128784
2023-01-21 09:31:59.540654: step: 408/530, loss: 0.06541475653648376
2023-01-21 09:32:00.651473: step: 412/530, loss: 0.18652623891830444
2023-01-21 09:32:01.802143: step: 416/530, loss: 0.28773394227027893
2023-01-21 09:32:02.968509: step: 420/530, loss: 0.47584548592567444
2023-01-21 09:32:04.118473: step: 424/530, loss: 0.10230350494384766
2023-01-21 09:32:05.309707: step: 428/530, loss: 0.12202253192663193
2023-01-21 09:32:06.443649: step: 432/530, loss: 0.11746470630168915
2023-01-21 09:32:07.564840: step: 436/530, loss: 0.08739033341407776
2023-01-21 09:32:08.721167: step: 440/530, loss: 0.3817031979560852
2023-01-21 09:32:09.825463: step: 444/530, loss: 0.08086929470300674
2023-01-21 09:32:10.966704: step: 448/530, loss: 0.009555435739457607
2023-01-21 09:32:12.112962: step: 452/530, loss: 0.13949918746948242
2023-01-21 09:32:13.240292: step: 456/530, loss: 0.0866062194108963
2023-01-21 09:32:14.359618: step: 460/530, loss: 0.06560106575489044
2023-01-21 09:32:15.472218: step: 464/530, loss: 0.384586900472641
2023-01-21 09:32:16.571681: step: 468/530, loss: 0.3166958689689636
2023-01-21 09:32:17.694317: step: 472/530, loss: 0.019094564020633698
2023-01-21 09:32:18.805805: step: 476/530, loss: 0.1679706871509552
2023-01-21 09:32:19.907677: step: 480/530, loss: 0.03817443549633026
2023-01-21 09:32:21.060393: step: 484/530, loss: 0.2168036550283432
2023-01-21 09:32:22.215095: step: 488/530, loss: 0.11938080936670303
2023-01-21 09:32:23.334595: step: 492/530, loss: 0.15857356786727905
2023-01-21 09:32:24.462944: step: 496/530, loss: 0.08879127353429794
2023-01-21 09:32:25.580811: step: 500/530, loss: 0.03689851611852646
2023-01-21 09:32:26.681053: step: 504/530, loss: 0.13657721877098083
2023-01-21 09:32:27.818547: step: 508/530, loss: 0.04713382571935654
2023-01-21 09:32:28.945732: step: 512/530, loss: 0.054463766515254974
2023-01-21 09:32:30.056980: step: 516/530, loss: 0.17969933152198792
2023-01-21 09:32:31.223897: step: 520/530, loss: 0.017021656036376953
2023-01-21 09:32:32.351234: step: 524/530, loss: 0.26531982421875
2023-01-21 09:32:33.470098: step: 528/530, loss: 0.07258759438991547
2023-01-21 09:32:34.613205: step: 532/530, loss: 0.3317708969116211
2023-01-21 09:32:35.750879: step: 536/530, loss: 0.147942915558815
2023-01-21 09:32:36.878475: step: 540/530, loss: 0.08274231106042862
2023-01-21 09:32:38.010189: step: 544/530, loss: 0.14594116806983948
2023-01-21 09:32:39.087525: step: 548/530, loss: 0.24725544452667236
2023-01-21 09:32:40.198546: step: 552/530, loss: 0.3674476742744446
2023-01-21 09:32:41.327192: step: 556/530, loss: 0.01938924938440323
2023-01-21 09:32:42.440178: step: 560/530, loss: 0.13125286996364594
2023-01-21 09:32:43.559111: step: 564/530, loss: 0.060601044446229935
2023-01-21 09:32:44.701593: step: 568/530, loss: 0.0606420524418354
2023-01-21 09:32:45.843251: step: 572/530, loss: 0.11411742866039276
2023-01-21 09:32:46.980466: step: 576/530, loss: 0.04862036556005478
2023-01-21 09:32:48.136289: step: 580/530, loss: 0.09410410374403
2023-01-21 09:32:49.250142: step: 584/530, loss: 0.22315135598182678
2023-01-21 09:32:50.364219: step: 588/530, loss: 0.3560633659362793
2023-01-21 09:32:51.520571: step: 592/530, loss: 0.1942174881696701
2023-01-21 09:32:52.619155: step: 596/530, loss: 0.07413597404956818
2023-01-21 09:32:53.768003: step: 600/530, loss: 0.30392590165138245
2023-01-21 09:32:54.881383: step: 604/530, loss: 0.18566074967384338
2023-01-21 09:32:56.027047: step: 608/530, loss: 0.08718490600585938
2023-01-21 09:32:57.145123: step: 612/530, loss: 0.04963655769824982
2023-01-21 09:32:58.298844: step: 616/530, loss: 0.024406051263213158
2023-01-21 09:32:59.412282: step: 620/530, loss: 0.16222438216209412
2023-01-21 09:33:00.531184: step: 624/530, loss: 0.2591068744659424
2023-01-21 09:33:01.656818: step: 628/530, loss: 0.08294692635536194
2023-01-21 09:33:02.793809: step: 632/530, loss: 0.20426569879055023
2023-01-21 09:33:03.934898: step: 636/530, loss: 0.29253149032592773
2023-01-21 09:33:05.058143: step: 640/530, loss: 0.10060005635023117
2023-01-21 09:33:06.183776: step: 644/530, loss: 0.09808759391307831
2023-01-21 09:33:07.300145: step: 648/530, loss: 0.13261820375919342
2023-01-21 09:33:08.396293: step: 652/530, loss: 0.23392906785011292
2023-01-21 09:33:09.507814: step: 656/530, loss: 0.07397551834583282
2023-01-21 09:33:10.628392: step: 660/530, loss: 0.17286443710327148
2023-01-21 09:33:11.723702: step: 664/530, loss: 0.0275329127907753
2023-01-21 09:33:12.836150: step: 668/530, loss: 0.07778511196374893
2023-01-21 09:33:13.988227: step: 672/530, loss: 0.1746256798505783
2023-01-21 09:33:15.103916: step: 676/530, loss: 0.25683510303497314
2023-01-21 09:33:16.240259: step: 680/530, loss: 0.07895040512084961
2023-01-21 09:33:17.374305: step: 684/530, loss: 0.17074833810329437
2023-01-21 09:33:18.520130: step: 688/530, loss: 0.3005863130092621
2023-01-21 09:33:19.633159: step: 692/530, loss: 0.13454914093017578
2023-01-21 09:33:20.745038: step: 696/530, loss: 0.18390029668807983
2023-01-21 09:33:21.885477: step: 700/530, loss: 0.2685925364494324
2023-01-21 09:33:23.000161: step: 704/530, loss: 0.06342411041259766
2023-01-21 09:33:24.119257: step: 708/530, loss: 0.07591047137975693
2023-01-21 09:33:25.247391: step: 712/530, loss: 0.15268459916114807
2023-01-21 09:33:26.390033: step: 716/530, loss: 0.07096538692712784
2023-01-21 09:33:27.496708: step: 720/530, loss: 0.22825470566749573
2023-01-21 09:33:28.653002: step: 724/530, loss: 0.04830455780029297
2023-01-21 09:33:29.812251: step: 728/530, loss: 0.1716753989458084
2023-01-21 09:33:30.925413: step: 732/530, loss: 0.08199730515480042
2023-01-21 09:33:32.048984: step: 736/530, loss: 0.042665187269449234
2023-01-21 09:33:33.202441: step: 740/530, loss: 0.4883585572242737
2023-01-21 09:33:34.327945: step: 744/530, loss: 0.1581067144870758
2023-01-21 09:33:35.438491: step: 748/530, loss: 0.06403084099292755
2023-01-21 09:33:36.549589: step: 752/530, loss: 0.1654316782951355
2023-01-21 09:33:37.647142: step: 756/530, loss: 0.0798945426940918
2023-01-21 09:33:38.767947: step: 760/530, loss: 0.06621751934289932
2023-01-21 09:33:39.889137: step: 764/530, loss: 0.053577519953250885
2023-01-21 09:33:41.079157: step: 768/530, loss: 0.11058750748634338
2023-01-21 09:33:42.228819: step: 772/530, loss: 0.017936183139681816
2023-01-21 09:33:43.372242: step: 776/530, loss: 0.04355302080512047
2023-01-21 09:33:44.503547: step: 780/530, loss: 0.36495158076286316
2023-01-21 09:33:45.600310: step: 784/530, loss: 0.43934112787246704
2023-01-21 09:33:46.726249: step: 788/530, loss: 0.07102146744728088
2023-01-21 09:33:47.852547: step: 792/530, loss: 0.21190303564071655
2023-01-21 09:33:48.985785: step: 796/530, loss: 0.29780712723731995
2023-01-21 09:33:50.100539: step: 800/530, loss: 0.34278467297554016
2023-01-21 09:33:51.247514: step: 804/530, loss: 0.15146255493164062
2023-01-21 09:33:52.380473: step: 808/530, loss: 0.19004635512828827
2023-01-21 09:33:53.471189: step: 812/530, loss: 0.05664868652820587
2023-01-21 09:33:54.608042: step: 816/530, loss: 0.05887401103973389
2023-01-21 09:33:55.738849: step: 820/530, loss: 0.08248929679393768
2023-01-21 09:33:56.852238: step: 824/530, loss: 0.06411056965589523
2023-01-21 09:33:57.991149: step: 828/530, loss: 0.5204371213912964
2023-01-21 09:33:59.114412: step: 832/530, loss: 0.05493386089801788
2023-01-21 09:34:00.258844: step: 836/530, loss: 1.2070831060409546
2023-01-21 09:34:01.398331: step: 840/530, loss: 0.6121943593025208
2023-01-21 09:34:02.510830: step: 844/530, loss: 0.23101691901683807
2023-01-21 09:34:03.636313: step: 848/530, loss: 0.09901097416877747
2023-01-21 09:34:04.777963: step: 852/530, loss: 0.39380624890327454
2023-01-21 09:34:05.898982: step: 856/530, loss: 0.01799907721579075
2023-01-21 09:34:07.009269: step: 860/530, loss: 0.08131790161132812
2023-01-21 09:34:08.107966: step: 864/530, loss: 0.020610427483916283
2023-01-21 09:34:09.216639: step: 868/530, loss: 0.1006801575422287
2023-01-21 09:34:10.340882: step: 872/530, loss: 0.08300866931676865
2023-01-21 09:34:11.469296: step: 876/530, loss: 0.038166143000125885
2023-01-21 09:34:12.583435: step: 880/530, loss: 0.0500035285949707
2023-01-21 09:34:13.699099: step: 884/530, loss: 0.05715980380773544
2023-01-21 09:34:14.845774: step: 888/530, loss: 0.3410232663154602
2023-01-21 09:34:15.949448: step: 892/530, loss: 0.2113526463508606
2023-01-21 09:34:17.063883: step: 896/530, loss: 0.06199474260210991
2023-01-21 09:34:18.184626: step: 900/530, loss: 0.19418449699878693
2023-01-21 09:34:19.304861: step: 904/530, loss: 0.4718639552593231
2023-01-21 09:34:20.468840: step: 908/530, loss: 0.20216770470142365
2023-01-21 09:34:21.590255: step: 912/530, loss: 0.26844674348831177
2023-01-21 09:34:22.703185: step: 916/530, loss: 0.058798979967832565
2023-01-21 09:34:23.838951: step: 920/530, loss: 0.15817013382911682
2023-01-21 09:34:24.953694: step: 924/530, loss: 0.29059523344039917
2023-01-21 09:34:26.047867: step: 928/530, loss: 0.1474754363298416
2023-01-21 09:34:27.147223: step: 932/530, loss: 0.11966433376073837
2023-01-21 09:34:28.272324: step: 936/530, loss: 0.07209692895412445
2023-01-21 09:34:29.395347: step: 940/530, loss: 0.06701042503118515
2023-01-21 09:34:30.508926: step: 944/530, loss: 0.04705529287457466
2023-01-21 09:34:31.620461: step: 948/530, loss: 0.05824854224920273
2023-01-21 09:34:32.713530: step: 952/530, loss: 0.20646142959594727
2023-01-21 09:34:33.816871: step: 956/530, loss: 0.1423918604850769
2023-01-21 09:34:34.944830: step: 960/530, loss: 0.296003133058548
2023-01-21 09:34:36.083449: step: 964/530, loss: 0.08810319751501083
2023-01-21 09:34:37.230997: step: 968/530, loss: 0.7253124713897705
2023-01-21 09:34:38.365522: step: 972/530, loss: 1.5166828632354736
2023-01-21 09:34:39.505812: step: 976/530, loss: 0.0873604267835617
2023-01-21 09:34:40.618411: step: 980/530, loss: 0.9824960231781006
2023-01-21 09:34:41.759703: step: 984/530, loss: 0.013598823919892311
2023-01-21 09:34:42.879842: step: 988/530, loss: 0.7239496111869812
2023-01-21 09:34:43.999812: step: 992/530, loss: 0.12836608290672302
2023-01-21 09:34:45.126022: step: 996/530, loss: 0.08518409729003906
2023-01-21 09:34:46.246464: step: 1000/530, loss: 0.01154622994363308
2023-01-21 09:34:47.380325: step: 1004/530, loss: 0.4631291925907135
2023-01-21 09:34:48.503884: step: 1008/530, loss: 0.08600912243127823
2023-01-21 09:34:49.617312: step: 1012/530, loss: 0.01753721386194229
2023-01-21 09:34:50.729819: step: 1016/530, loss: 0.3470671772956848
2023-01-21 09:34:51.853597: step: 1020/530, loss: 0.5096868276596069
2023-01-21 09:34:52.988285: step: 1024/530, loss: 0.3036513030529022
2023-01-21 09:34:54.134188: step: 1028/530, loss: 0.13549338281154633
2023-01-21 09:34:55.275573: step: 1032/530, loss: 0.2141742706298828
2023-01-21 09:34:56.420759: step: 1036/530, loss: 0.1712675392627716
2023-01-21 09:34:57.577938: step: 1040/530, loss: 0.14944756031036377
2023-01-21 09:34:58.685163: step: 1044/530, loss: 0.05993552505970001
2023-01-21 09:34:59.814521: step: 1048/530, loss: 0.7211365103721619
2023-01-21 09:35:00.953189: step: 1052/530, loss: 0.0779966413974762
2023-01-21 09:35:02.102186: step: 1056/530, loss: 0.06341171264648438
2023-01-21 09:35:03.199476: step: 1060/530, loss: 0.13384047150611877
2023-01-21 09:35:04.330383: step: 1064/530, loss: 0.06296498328447342
2023-01-21 09:35:05.461350: step: 1068/530, loss: 0.2466968595981598
2023-01-21 09:35:06.572571: step: 1072/530, loss: 0.09526863694190979
2023-01-21 09:35:07.692908: step: 1076/530, loss: 0.014645003713667393
2023-01-21 09:35:08.796882: step: 1080/530, loss: 0.21385088562965393
2023-01-21 09:35:09.929135: step: 1084/530, loss: 0.3780633807182312
2023-01-21 09:35:11.060693: step: 1088/530, loss: 0.3160451054573059
2023-01-21 09:35:12.208381: step: 1092/530, loss: 0.32387468218803406
2023-01-21 09:35:13.323196: step: 1096/530, loss: 0.04341869428753853
2023-01-21 09:35:14.458136: step: 1100/530, loss: 0.07547321915626526
2023-01-21 09:35:15.592867: step: 1104/530, loss: 0.26678380370140076
2023-01-21 09:35:16.734255: step: 1108/530, loss: 0.2126132994890213
2023-01-21 09:35:17.874104: step: 1112/530, loss: 0.07048411667346954
2023-01-21 09:35:18.997649: step: 1116/530, loss: 0.08048667758703232
2023-01-21 09:35:20.090421: step: 1120/530, loss: 0.012352370657026768
2023-01-21 09:35:21.229197: step: 1124/530, loss: 0.06429357826709747
2023-01-21 09:35:22.395446: step: 1128/530, loss: 0.031514931470155716
2023-01-21 09:35:23.533740: step: 1132/530, loss: 1.2397717237472534
2023-01-21 09:35:24.657756: step: 1136/530, loss: 0.028403710573911667
2023-01-21 09:35:25.805064: step: 1140/530, loss: 0.10085955262184143
2023-01-21 09:35:26.951093: step: 1144/530, loss: 0.1403471976518631
2023-01-21 09:35:28.081177: step: 1148/530, loss: 0.7042710185050964
2023-01-21 09:35:29.240889: step: 1152/530, loss: 0.09390640258789062
2023-01-21 09:35:30.379547: step: 1156/530, loss: 0.09355869889259338
2023-01-21 09:35:31.504828: step: 1160/530, loss: 0.007473087403923273
2023-01-21 09:35:32.639231: step: 1164/530, loss: 0.27679768204689026
2023-01-21 09:35:33.799098: step: 1168/530, loss: 0.11187019944190979
2023-01-21 09:35:34.919597: step: 1172/530, loss: 0.053135111927986145
2023-01-21 09:35:36.021643: step: 1176/530, loss: 0.08385889232158661
2023-01-21 09:35:37.127590: step: 1180/530, loss: 0.17480221390724182
2023-01-21 09:35:38.253513: step: 1184/530, loss: 2.046238422393799
2023-01-21 09:35:39.365579: step: 1188/530, loss: 0.02764158323407173
2023-01-21 09:35:40.478776: step: 1192/530, loss: 0.0494568832218647
2023-01-21 09:35:41.620133: step: 1196/530, loss: 0.06500430405139923
2023-01-21 09:35:42.741642: step: 1200/530, loss: 0.12212173640727997
2023-01-21 09:35:43.881195: step: 1204/530, loss: 0.19683972001075745
2023-01-21 09:35:44.999599: step: 1208/530, loss: 0.06458806991577148
2023-01-21 09:35:46.136919: step: 1212/530, loss: 0.11424527317285538
2023-01-21 09:35:47.264241: step: 1216/530, loss: 0.19803999364376068
2023-01-21 09:35:48.393153: step: 1220/530, loss: 0.04700913652777672
2023-01-21 09:35:49.525785: step: 1224/530, loss: 0.048827171325683594
2023-01-21 09:35:50.642448: step: 1228/530, loss: 0.05452003329992294
2023-01-21 09:35:51.794207: step: 1232/530, loss: 0.21613922715187073
2023-01-21 09:35:52.914097: step: 1236/530, loss: 0.24322834610939026
2023-01-21 09:35:54.036571: step: 1240/530, loss: 0.04457903280854225
2023-01-21 09:35:55.150354: step: 1244/530, loss: 0.0448366180062294
2023-01-21 09:35:56.281276: step: 1248/530, loss: 0.09091325104236603
2023-01-21 09:35:57.396994: step: 1252/530, loss: 0.09748277813196182
2023-01-21 09:35:58.537718: step: 1256/530, loss: 0.12203522026538849
2023-01-21 09:35:59.677909: step: 1260/530, loss: 0.335780531167984
2023-01-21 09:36:00.804686: step: 1264/530, loss: 0.22614207863807678
2023-01-21 09:36:01.918151: step: 1268/530, loss: 0.2030268758535385
2023-01-21 09:36:03.024431: step: 1272/530, loss: 0.22400760650634766
2023-01-21 09:36:04.165701: step: 1276/530, loss: 0.08141575008630753
2023-01-21 09:36:05.316105: step: 1280/530, loss: 0.5172402858734131
2023-01-21 09:36:06.452000: step: 1284/530, loss: 0.22656220197677612
2023-01-21 09:36:07.587159: step: 1288/530, loss: 0.11657829582691193
2023-01-21 09:36:08.723847: step: 1292/530, loss: 0.06654205173254013
2023-01-21 09:36:09.851877: step: 1296/530, loss: 0.015016365796327591
2023-01-21 09:36:10.976046: step: 1300/530, loss: 0.4473293423652649
2023-01-21 09:36:12.111183: step: 1304/530, loss: 0.2816286087036133
2023-01-21 09:36:13.219843: step: 1308/530, loss: 0.2372780740261078
2023-01-21 09:36:14.326219: step: 1312/530, loss: 0.13489703834056854
2023-01-21 09:36:15.462112: step: 1316/530, loss: 0.052164364606142044
2023-01-21 09:36:16.556873: step: 1320/530, loss: 0.20643702149391174
2023-01-21 09:36:17.672436: step: 1324/530, loss: 0.2209964245557785
2023-01-21 09:36:18.770768: step: 1328/530, loss: 0.16489094495773315
2023-01-21 09:36:19.901299: step: 1332/530, loss: 0.23755799233913422
2023-01-21 09:36:21.061147: step: 1336/530, loss: 0.10670223087072372
2023-01-21 09:36:22.167480: step: 1340/530, loss: 0.0945381224155426
2023-01-21 09:36:23.271609: step: 1344/530, loss: 0.44866687059402466
2023-01-21 09:36:24.396378: step: 1348/530, loss: 0.21802903711795807
2023-01-21 09:36:25.512018: step: 1352/530, loss: 0.08314695209264755
2023-01-21 09:36:26.634232: step: 1356/530, loss: 0.1375287026166916
2023-01-21 09:36:27.787888: step: 1360/530, loss: 0.33060723543167114
2023-01-21 09:36:28.901355: step: 1364/530, loss: 0.11901453137397766
2023-01-21 09:36:30.027634: step: 1368/530, loss: 0.03996272385120392
2023-01-21 09:36:31.126207: step: 1372/530, loss: 0.05270390585064888
2023-01-21 09:36:32.232678: step: 1376/530, loss: 0.1120242103934288
2023-01-21 09:36:33.336913: step: 1380/530, loss: 0.11558208614587784
2023-01-21 09:36:34.445703: step: 1384/530, loss: 0.10492321848869324
2023-01-21 09:36:35.571653: step: 1388/530, loss: 0.01764545403420925
2023-01-21 09:36:36.684106: step: 1392/530, loss: 0.2943659722805023
2023-01-21 09:36:37.802228: step: 1396/530, loss: 0.10658684372901917
2023-01-21 09:36:38.901320: step: 1400/530, loss: 0.06164398044347763
2023-01-21 09:36:40.035867: step: 1404/530, loss: 0.09172210842370987
2023-01-21 09:36:41.160878: step: 1408/530, loss: 0.11529102176427841
2023-01-21 09:36:42.281983: step: 1412/530, loss: 0.36260128021240234
2023-01-21 09:36:43.416606: step: 1416/530, loss: 0.11755562573671341
2023-01-21 09:36:44.557175: step: 1420/530, loss: 0.1664118766784668
2023-01-21 09:36:45.695803: step: 1424/530, loss: 0.09763488918542862
2023-01-21 09:36:46.819378: step: 1428/530, loss: 0.16853809356689453
2023-01-21 09:36:47.968286: step: 1432/530, loss: 0.26410362124443054
2023-01-21 09:36:49.072537: step: 1436/530, loss: 0.1288415938615799
2023-01-21 09:36:50.227578: step: 1440/530, loss: 0.050049737095832825
2023-01-21 09:36:51.351691: step: 1444/530, loss: 0.24375152587890625
2023-01-21 09:36:52.467032: step: 1448/530, loss: 0.10457730293273926
2023-01-21 09:36:53.571180: step: 1452/530, loss: 0.3700190484523773
2023-01-21 09:36:54.700285: step: 1456/530, loss: 0.2309008538722992
2023-01-21 09:36:55.843641: step: 1460/530, loss: 0.0939367339015007
2023-01-21 09:36:56.952540: step: 1464/530, loss: 0.04740658402442932
2023-01-21 09:36:58.076681: step: 1468/530, loss: 0.03651466593146324
2023-01-21 09:36:59.251293: step: 1472/530, loss: 0.5056043267250061
2023-01-21 09:37:00.372295: step: 1476/530, loss: 0.12814083695411682
2023-01-21 09:37:01.483648: step: 1480/530, loss: 0.06132626533508301
2023-01-21 09:37:02.617631: step: 1484/530, loss: 0.021965885534882545
2023-01-21 09:37:03.703712: step: 1488/530, loss: 0.14142721891403198
2023-01-21 09:37:04.799730: step: 1492/530, loss: 0.042731285095214844
2023-01-21 09:37:05.912951: step: 1496/530, loss: 0.037416670471429825
2023-01-21 09:37:07.035299: step: 1500/530, loss: 0.02287759818136692
2023-01-21 09:37:08.158307: step: 1504/530, loss: 0.2768389582633972
2023-01-21 09:37:09.269372: step: 1508/530, loss: 0.4945589303970337
2023-01-21 09:37:10.410167: step: 1512/530, loss: 0.033917855471372604
2023-01-21 09:37:11.570942: step: 1516/530, loss: 1.3697296380996704
2023-01-21 09:37:12.718918: step: 1520/530, loss: 0.043160442262887955
2023-01-21 09:37:13.838567: step: 1524/530, loss: 0.07813435047864914
2023-01-21 09:37:14.951655: step: 1528/530, loss: 0.10764770954847336
2023-01-21 09:37:16.089114: step: 1532/530, loss: 0.2389325201511383
2023-01-21 09:37:17.194302: step: 1536/530, loss: 0.3503111004829407
2023-01-21 09:37:18.296656: step: 1540/530, loss: 0.06169404834508896
2023-01-21 09:37:19.419589: step: 1544/530, loss: 0.7213138341903687
2023-01-21 09:37:20.537879: step: 1548/530, loss: 0.1807718276977539
2023-01-21 09:37:21.639632: step: 1552/530, loss: 0.10531444847583771
2023-01-21 09:37:22.768205: step: 1556/530, loss: 0.2628301680088043
2023-01-21 09:37:23.876379: step: 1560/530, loss: 0.13537092506885529
2023-01-21 09:37:25.036735: step: 1564/530, loss: 0.091173455119133
2023-01-21 09:37:26.175405: step: 1568/530, loss: 0.050329022109508514
2023-01-21 09:37:27.292894: step: 1572/530, loss: 0.20693665742874146
2023-01-21 09:37:28.404940: step: 1576/530, loss: 0.0497838519513607
2023-01-21 09:37:29.518208: step: 1580/530, loss: 0.06012783199548721
2023-01-21 09:37:30.610333: step: 1584/530, loss: 0.2369484007358551
2023-01-21 09:37:31.723003: step: 1588/530, loss: 0.0898078978061676
2023-01-21 09:37:32.868377: step: 1592/530, loss: 0.0971534252166748
2023-01-21 09:37:33.986046: step: 1596/530, loss: 0.32569846510887146
2023-01-21 09:37:35.103596: step: 1600/530, loss: 0.1363188773393631
2023-01-21 09:37:36.191388: step: 1604/530, loss: 0.3215019106864929
2023-01-21 09:37:37.349106: step: 1608/530, loss: 0.19120875000953674
2023-01-21 09:37:38.481570: step: 1612/530, loss: 0.07800846546888351
2023-01-21 09:37:39.589723: step: 1616/530, loss: 0.31955671310424805
2023-01-21 09:37:40.742527: step: 1620/530, loss: 0.13016024231910706
2023-01-21 09:37:41.904248: step: 1624/530, loss: 0.140536367893219
2023-01-21 09:37:43.026034: step: 1628/530, loss: 0.01799945905804634
2023-01-21 09:37:44.143334: step: 1632/530, loss: 0.5441030263900757
2023-01-21 09:37:45.280830: step: 1636/530, loss: 0.01740856282413006
2023-01-21 09:37:46.414405: step: 1640/530, loss: 0.866162121295929
2023-01-21 09:37:47.531196: step: 1644/530, loss: 0.5128917098045349
2023-01-21 09:37:48.673236: step: 1648/530, loss: 0.08527746051549911
2023-01-21 09:37:49.840109: step: 1652/530, loss: 0.038887977600097656
2023-01-21 09:37:50.943799: step: 1656/530, loss: 0.300466924905777
2023-01-21 09:37:52.092584: step: 1660/530, loss: 0.08356447517871857
2023-01-21 09:37:53.224494: step: 1664/530, loss: 0.047193050384521484
2023-01-21 09:37:54.338807: step: 1668/530, loss: 0.04196572303771973
2023-01-21 09:37:55.483919: step: 1672/530, loss: 0.22638550400733948
2023-01-21 09:37:56.628195: step: 1676/530, loss: 0.060697294771671295
2023-01-21 09:37:57.765781: step: 1680/530, loss: 0.029040971770882607
2023-01-21 09:37:58.889664: step: 1684/530, loss: 0.32494333386421204
2023-01-21 09:37:59.992534: step: 1688/530, loss: 0.2050762176513672
2023-01-21 09:38:01.093292: step: 1692/530, loss: 0.15073424577713013
2023-01-21 09:38:02.201153: step: 1696/530, loss: 0.021234560757875443
2023-01-21 09:38:03.323721: step: 1700/530, loss: 0.22772693634033203
2023-01-21 09:38:04.425520: step: 1704/530, loss: 0.2048051953315735
2023-01-21 09:38:05.530769: step: 1708/530, loss: 1.229255199432373
2023-01-21 09:38:06.635802: step: 1712/530, loss: 0.07519569247961044
2023-01-21 09:38:07.737826: step: 1716/530, loss: 0.3553768992424011
2023-01-21 09:38:08.856480: step: 1720/530, loss: 0.31177273392677307
2023-01-21 09:38:09.974730: step: 1724/530, loss: 0.07540798932313919
2023-01-21 09:38:11.099913: step: 1728/530, loss: 0.4778037965297699
2023-01-21 09:38:12.250958: step: 1732/530, loss: 0.10925769805908203
2023-01-21 09:38:13.358299: step: 1736/530, loss: 0.1518394500017166
2023-01-21 09:38:14.494513: step: 1740/530, loss: 0.09637327492237091
2023-01-21 09:38:15.638735: step: 1744/530, loss: 0.2500007748603821
2023-01-21 09:38:16.782026: step: 1748/530, loss: 0.04216470569372177
2023-01-21 09:38:17.917907: step: 1752/530, loss: 0.3958495855331421
2023-01-21 09:38:19.045035: step: 1756/530, loss: 0.34370705485343933
2023-01-21 09:38:20.177617: step: 1760/530, loss: 0.16984349489212036
2023-01-21 09:38:21.306585: step: 1764/530, loss: 0.2212836742401123
2023-01-21 09:38:22.425937: step: 1768/530, loss: 0.1221095621585846
2023-01-21 09:38:23.528768: step: 1772/530, loss: 0.16367921233177185
2023-01-21 09:38:24.636399: step: 1776/530, loss: 0.09126263111829758
2023-01-21 09:38:25.767507: step: 1780/530, loss: 0.18614892661571503
2023-01-21 09:38:26.905992: step: 1784/530, loss: 0.14096757769584656
2023-01-21 09:38:28.034867: step: 1788/530, loss: 0.22768375277519226
2023-01-21 09:38:29.177868: step: 1792/530, loss: 0.4420034885406494
2023-01-21 09:38:30.296424: step: 1796/530, loss: 0.6020099520683289
2023-01-21 09:38:31.417950: step: 1800/530, loss: 0.013664103113114834
2023-01-21 09:38:32.512595: step: 1804/530, loss: 0.03677663952112198
2023-01-21 09:38:33.654219: step: 1808/530, loss: 0.1266801357269287
2023-01-21 09:38:34.787064: step: 1812/530, loss: 0.23877553641796112
2023-01-21 09:38:35.911932: step: 1816/530, loss: 0.06793355941772461
2023-01-21 09:38:37.043655: step: 1820/530, loss: 0.18614837527275085
2023-01-21 09:38:38.178051: step: 1824/530, loss: 0.052790261805057526
2023-01-21 09:38:39.283102: step: 1828/530, loss: 0.2922162115573883
2023-01-21 09:38:40.413949: step: 1832/530, loss: 0.07311079651117325
2023-01-21 09:38:41.520718: step: 1836/530, loss: 0.3650810420513153
2023-01-21 09:38:42.643124: step: 1840/530, loss: 0.01961350440979004
2023-01-21 09:38:43.737080: step: 1844/530, loss: 0.08485154807567596
2023-01-21 09:38:44.868062: step: 1848/530, loss: 0.4292561709880829
2023-01-21 09:38:46.039680: step: 1852/530, loss: 0.18198230862617493
2023-01-21 09:38:47.164153: step: 1856/530, loss: 0.08973255008459091
2023-01-21 09:38:48.312480: step: 1860/530, loss: 0.12911725044250488
2023-01-21 09:38:49.440571: step: 1864/530, loss: 0.0540163516998291
2023-01-21 09:38:50.595075: step: 1868/530, loss: 0.20200799405574799
2023-01-21 09:38:51.746842: step: 1872/530, loss: 0.09971609711647034
2023-01-21 09:38:52.856955: step: 1876/530, loss: 0.03512759506702423
2023-01-21 09:38:53.980844: step: 1880/530, loss: 0.09538641571998596
2023-01-21 09:38:55.102035: step: 1884/530, loss: 0.12151136249303818
2023-01-21 09:38:56.231437: step: 1888/530, loss: 0.20381908118724823
2023-01-21 09:38:57.374392: step: 1892/530, loss: 0.46223753690719604
2023-01-21 09:38:58.490801: step: 1896/530, loss: 0.027243424206972122
2023-01-21 09:38:59.629242: step: 1900/530, loss: 0.10899010300636292
2023-01-21 09:39:00.714676: step: 1904/530, loss: 0.153279110789299
2023-01-21 09:39:01.834750: step: 1908/530, loss: 0.6745237112045288
2023-01-21 09:39:02.959251: step: 1912/530, loss: 0.500869870185852
2023-01-21 09:39:04.104117: step: 1916/530, loss: 0.5899769067764282
2023-01-21 09:39:05.257715: step: 1920/530, loss: 0.07409355789422989
2023-01-21 09:39:06.368841: step: 1924/530, loss: 0.15016856789588928
2023-01-21 09:39:07.518866: step: 1928/530, loss: 0.21908608078956604
2023-01-21 09:39:08.627702: step: 1932/530, loss: 0.07517699897289276
2023-01-21 09:39:09.723475: step: 1936/530, loss: 0.09788842499256134
2023-01-21 09:39:10.826308: step: 1940/530, loss: 0.09046149253845215
2023-01-21 09:39:11.970279: step: 1944/530, loss: 0.17099237442016602
2023-01-21 09:39:13.096666: step: 1948/530, loss: 0.11549048870801926
2023-01-21 09:39:14.236545: step: 1952/530, loss: 0.17608605325222015
2023-01-21 09:39:15.358454: step: 1956/530, loss: 0.10070304572582245
2023-01-21 09:39:16.479888: step: 1960/530, loss: 0.13738679885864258
2023-01-21 09:39:17.606428: step: 1964/530, loss: 0.22463731467723846
2023-01-21 09:39:18.803893: step: 1968/530, loss: 0.6038355827331543
2023-01-21 09:39:19.903215: step: 1972/530, loss: 0.6044832468032837
2023-01-21 09:39:21.029666: step: 1976/530, loss: 0.12859220802783966
2023-01-21 09:39:22.135665: step: 1980/530, loss: 0.08989968150854111
2023-01-21 09:39:23.249858: step: 1984/530, loss: 0.12805600464344025
2023-01-21 09:39:24.361347: step: 1988/530, loss: 0.0669550895690918
2023-01-21 09:39:25.472040: step: 1992/530, loss: 0.04595589637756348
2023-01-21 09:39:26.580540: step: 1996/530, loss: 0.07101660221815109
2023-01-21 09:39:27.692032: step: 2000/530, loss: 0.16647876799106598
2023-01-21 09:39:28.801393: step: 2004/530, loss: 0.09565702080726624
2023-01-21 09:39:29.909169: step: 2008/530, loss: 0.1197698637843132
2023-01-21 09:39:31.046777: step: 2012/530, loss: 0.21390505135059357
2023-01-21 09:39:32.161487: step: 2016/530, loss: 0.17323322594165802
2023-01-21 09:39:33.267774: step: 2020/530, loss: 0.04296598583459854
2023-01-21 09:39:34.412336: step: 2024/530, loss: 0.06947288662195206
2023-01-21 09:39:35.547749: step: 2028/530, loss: 0.15835817158222198
2023-01-21 09:39:36.707063: step: 2032/530, loss: 0.0697358176112175
2023-01-21 09:39:37.833082: step: 2036/530, loss: 0.13951721787452698
2023-01-21 09:39:38.960490: step: 2040/530, loss: 0.12837333977222443
2023-01-21 09:39:40.100964: step: 2044/530, loss: 0.20212160050868988
2023-01-21 09:39:41.255649: step: 2048/530, loss: 0.14614444971084595
2023-01-21 09:39:42.382285: step: 2052/530, loss: 0.007374191656708717
2023-01-21 09:39:43.497523: step: 2056/530, loss: 0.08166094124317169
2023-01-21 09:39:44.623505: step: 2060/530, loss: 0.06730890274047852
2023-01-21 09:39:45.742996: step: 2064/530, loss: 0.05676688998937607
2023-01-21 09:39:46.881486: step: 2068/530, loss: 0.23960915207862854
2023-01-21 09:39:48.004263: step: 2072/530, loss: 0.8756664395332336
2023-01-21 09:39:49.136272: step: 2076/530, loss: 0.6012828946113586
2023-01-21 09:39:50.247296: step: 2080/530, loss: 0.1297682374715805
2023-01-21 09:39:51.357574: step: 2084/530, loss: 0.47456806898117065
2023-01-21 09:39:52.466422: step: 2088/530, loss: 0.05200080946087837
2023-01-21 09:39:53.583773: step: 2092/530, loss: 0.4557887613773346
2023-01-21 09:39:54.693289: step: 2096/530, loss: 0.011409521102905273
2023-01-21 09:39:55.805391: step: 2100/530, loss: 0.02104482613503933
2023-01-21 09:39:56.937896: step: 2104/530, loss: 0.18514509499073029
2023-01-21 09:39:58.024610: step: 2108/530, loss: 0.8774241209030151
2023-01-21 09:39:59.132968: step: 2112/530, loss: 0.4231996536254883
2023-01-21 09:40:00.271278: step: 2116/530, loss: 0.2420537918806076
2023-01-21 09:40:01.381195: step: 2120/530, loss: 0.7077285051345825
==================================================
Loss: 0.195
--------------------
Dev: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
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': 6}
Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:40:56.487421: step: 4/530, loss: 1.2680834531784058
2023-01-21 09:40:57.620302: step: 8/530, loss: 0.11628742516040802
2023-01-21 09:40:58.768374: step: 12/530, loss: 0.10035018622875214
2023-01-21 09:40:59.858781: step: 16/530, loss: 0.07771806418895721
2023-01-21 09:41:00.964598: step: 20/530, loss: 0.0396575927734375
2023-01-21 09:41:02.105616: step: 24/530, loss: 0.07201176136732101
2023-01-21 09:41:03.221590: step: 28/530, loss: 0.345685750246048
2023-01-21 09:41:04.350303: step: 32/530, loss: 0.18685273826122284
2023-01-21 09:41:05.470924: step: 36/530, loss: 0.11074590682983398
2023-01-21 09:41:06.569597: step: 40/530, loss: 0.036945439875125885
2023-01-21 09:41:07.669333: step: 44/530, loss: 0.019988251850008965
2023-01-21 09:41:08.790154: step: 48/530, loss: 0.10782280564308167
2023-01-21 09:41:09.908082: step: 52/530, loss: 0.043553560972213745
2023-01-21 09:41:11.021870: step: 56/530, loss: 0.03478240966796875
2023-01-21 09:41:12.169909: step: 60/530, loss: 0.3675309121608734
2023-01-21 09:41:13.294152: step: 64/530, loss: 0.12756377458572388
2023-01-21 09:41:14.384079: step: 68/530, loss: 0.04408903047442436
2023-01-21 09:41:15.527976: step: 72/530, loss: 0.06789093464612961
2023-01-21 09:41:16.654559: step: 76/530, loss: 0.2024621069431305
2023-01-21 09:41:17.773978: step: 80/530, loss: 0.07582321763038635
2023-01-21 09:41:18.892516: step: 84/530, loss: 0.08279547095298767
2023-01-21 09:41:20.020676: step: 88/530, loss: 0.11244364082813263
2023-01-21 09:41:21.156544: step: 92/530, loss: 0.6770861744880676
2023-01-21 09:41:22.272002: step: 96/530, loss: 0.17271490395069122
2023-01-21 09:41:23.416596: step: 100/530, loss: 0.2672789692878723
2023-01-21 09:41:24.531515: step: 104/530, loss: 0.03359966352581978
2023-01-21 09:41:25.685865: step: 108/530, loss: 0.15161657333374023
2023-01-21 09:41:26.798802: step: 112/530, loss: 0.04416675865650177
2023-01-21 09:41:27.940840: step: 116/530, loss: 0.05272217094898224
2023-01-21 09:41:29.069048: step: 120/530, loss: 0.07752113789319992
2023-01-21 09:41:30.199017: step: 124/530, loss: 0.04306497797369957
2023-01-21 09:41:31.317794: step: 128/530, loss: 0.08245506137609482
2023-01-21 09:41:32.426981: step: 132/530, loss: 0.693924069404602
2023-01-21 09:41:33.550637: step: 136/530, loss: 0.07675180584192276
2023-01-21 09:41:34.672784: step: 140/530, loss: 0.1386013627052307
2023-01-21 09:41:35.797704: step: 144/530, loss: 0.10035989433526993
2023-01-21 09:41:36.903458: step: 148/530, loss: 0.024668170139193535
2023-01-21 09:41:38.042129: step: 152/530, loss: 0.06383457034826279
2023-01-21 09:41:39.200358: step: 156/530, loss: 0.11973152309656143
2023-01-21 09:41:40.290744: step: 160/530, loss: 0.042676351964473724
2023-01-21 09:41:41.445665: step: 164/530, loss: 0.15362448990345
2023-01-21 09:41:42.549249: step: 168/530, loss: 0.14505767822265625
2023-01-21 09:41:43.671982: step: 172/530, loss: 0.13315200805664062
2023-01-21 09:41:44.780900: step: 176/530, loss: 0.2832792103290558
2023-01-21 09:41:45.884045: step: 180/530, loss: 0.17722105979919434
2023-01-21 09:41:47.015375: step: 184/530, loss: 0.15194718539714813
2023-01-21 09:41:48.157725: step: 188/530, loss: 0.150286003947258
2023-01-21 09:41:49.277613: step: 192/530, loss: 0.09859780967235565
2023-01-21 09:41:50.407098: step: 196/530, loss: 0.11405744403600693
2023-01-21 09:41:51.547901: step: 200/530, loss: 0.009566117078065872
2023-01-21 09:41:52.678689: step: 204/530, loss: 0.27399322390556335
2023-01-21 09:41:53.783958: step: 208/530, loss: 0.0459321029484272
2023-01-21 09:41:54.894225: step: 212/530, loss: 0.031373072415590286
2023-01-21 09:41:56.016415: step: 216/530, loss: 0.08388862758874893
2023-01-21 09:41:57.128081: step: 220/530, loss: 0.17334657907485962
2023-01-21 09:41:58.260374: step: 224/530, loss: 0.01612100750207901
2023-01-21 09:41:59.381889: step: 228/530, loss: 0.05114307254552841
2023-01-21 09:42:00.481837: step: 232/530, loss: 0.023565197363495827
2023-01-21 09:42:01.603979: step: 236/530, loss: 0.06466398388147354
2023-01-21 09:42:02.719537: step: 240/530, loss: 0.127864271402359
2023-01-21 09:42:03.830114: step: 244/530, loss: 0.015131901949644089
2023-01-21 09:42:04.940743: step: 248/530, loss: 0.2220287322998047
2023-01-21 09:42:06.075642: step: 252/530, loss: 0.06713638454675674
2023-01-21 09:42:07.193933: step: 256/530, loss: 0.05299339070916176
2023-01-21 09:42:08.314766: step: 260/530, loss: 0.21844425797462463
2023-01-21 09:42:09.420931: step: 264/530, loss: 0.027155732735991478
2023-01-21 09:42:10.551333: step: 268/530, loss: 0.1889164000749588
2023-01-21 09:42:11.666193: step: 272/530, loss: 0.08978307247161865
2023-01-21 09:42:12.775641: step: 276/530, loss: 0.2027631253004074
2023-01-21 09:42:13.897875: step: 280/530, loss: 0.3179045617580414
2023-01-21 09:42:15.029147: step: 284/530, loss: 0.17387732863426208
2023-01-21 09:42:16.135425: step: 288/530, loss: 0.11703416705131531
2023-01-21 09:42:17.298861: step: 292/530, loss: 0.05413389205932617
2023-01-21 09:42:18.437386: step: 296/530, loss: 0.16706986725330353
2023-01-21 09:42:19.598953: step: 300/530, loss: 0.20405225455760956
2023-01-21 09:42:20.709064: step: 304/530, loss: 0.12181229889392853
2023-01-21 09:42:21.842650: step: 308/530, loss: 0.04867248609662056
2023-01-21 09:42:22.990159: step: 312/530, loss: 0.024172592908143997
2023-01-21 09:42:24.105495: step: 316/530, loss: 0.05715160816907883
2023-01-21 09:42:25.236581: step: 320/530, loss: 0.299630343914032
2023-01-21 09:42:26.395800: step: 324/530, loss: 0.23877058923244476
2023-01-21 09:42:27.512768: step: 328/530, loss: 0.05015774071216583
2023-01-21 09:42:28.636533: step: 332/530, loss: 0.10128937661647797
2023-01-21 09:42:29.777991: step: 336/530, loss: 0.3304719924926758
2023-01-21 09:42:30.926796: step: 340/530, loss: 0.2882063090801239
2023-01-21 09:42:32.100493: step: 344/530, loss: 0.007085896097123623
2023-01-21 09:42:33.207077: step: 348/530, loss: 0.11631961166858673
2023-01-21 09:42:34.376891: step: 352/530, loss: 0.2977229952812195
2023-01-21 09:42:35.518430: step: 356/530, loss: 0.3813876211643219
2023-01-21 09:42:36.655911: step: 360/530, loss: 0.4327712059020996
2023-01-21 09:42:37.786462: step: 364/530, loss: 0.036438848823308945
2023-01-21 09:42:38.918557: step: 368/530, loss: 0.07077427208423615
2023-01-21 09:42:40.041307: step: 372/530, loss: 0.12200746685266495
2023-01-21 09:42:41.181301: step: 376/530, loss: 0.02948732301592827
2023-01-21 09:42:42.300765: step: 380/530, loss: 0.1491079330444336
2023-01-21 09:42:43.421541: step: 384/530, loss: 0.02601945400238037
2023-01-21 09:42:44.554824: step: 388/530, loss: 0.37616854906082153
2023-01-21 09:42:45.674029: step: 392/530, loss: 0.06340713798999786
2023-01-21 09:42:46.783914: step: 396/530, loss: 1.1876200437545776
2023-01-21 09:42:47.881903: step: 400/530, loss: 0.08074913173913956
2023-01-21 09:42:49.002712: step: 404/530, loss: 0.08615941554307938
2023-01-21 09:42:50.123379: step: 408/530, loss: 0.027387047186493874
2023-01-21 09:42:51.275775: step: 412/530, loss: 0.061334848403930664
2023-01-21 09:42:52.396641: step: 416/530, loss: 0.1527661383152008
2023-01-21 09:42:53.537798: step: 420/530, loss: 0.041491247713565826
2023-01-21 09:42:54.651852: step: 424/530, loss: 0.04295506700873375
2023-01-21 09:42:55.778955: step: 428/530, loss: 0.19950208067893982
2023-01-21 09:42:56.890666: step: 432/530, loss: 0.030297422781586647
2023-01-21 09:42:58.042451: step: 436/530, loss: 0.09364042431116104
2023-01-21 09:42:59.203067: step: 440/530, loss: 0.030904626473784447
2023-01-21 09:43:00.364423: step: 444/530, loss: 0.23721298575401306
2023-01-21 09:43:01.480214: step: 448/530, loss: 0.04982786253094673
2023-01-21 09:43:02.605507: step: 452/530, loss: 0.2451189011335373
2023-01-21 09:43:03.712666: step: 456/530, loss: 0.16009148955345154
2023-01-21 09:43:04.830498: step: 460/530, loss: 1.979337453842163
2023-01-21 09:43:05.946432: step: 464/530, loss: 0.13183872401714325
2023-01-21 09:43:07.077587: step: 468/530, loss: 0.1537894308567047
2023-01-21 09:43:08.209819: step: 472/530, loss: 0.013261795043945312
2023-01-21 09:43:09.328944: step: 476/530, loss: 0.007299757096916437
2023-01-21 09:43:10.481913: step: 480/530, loss: 0.07049300521612167
2023-01-21 09:43:11.603240: step: 484/530, loss: 0.03040905110538006
2023-01-21 09:43:12.736756: step: 488/530, loss: 0.22414608299732208
2023-01-21 09:43:13.849551: step: 492/530, loss: 0.13880681991577148
2023-01-21 09:43:14.973768: step: 496/530, loss: 0.08127718418836594
2023-01-21 09:43:16.075941: step: 500/530, loss: 0.0580902099609375
2023-01-21 09:43:17.200939: step: 504/530, loss: 0.35004082322120667
2023-01-21 09:43:18.343401: step: 508/530, loss: 0.024770833551883698
2023-01-21 09:43:19.496052: step: 512/530, loss: 0.16093240678310394
2023-01-21 09:43:20.622554: step: 516/530, loss: 0.15723609924316406
2023-01-21 09:43:21.749044: step: 520/530, loss: 0.04057464376091957
2023-01-21 09:43:22.859849: step: 524/530, loss: 0.09470286965370178
2023-01-21 09:43:24.009960: step: 528/530, loss: 0.16625729203224182
2023-01-21 09:43:25.165799: step: 532/530, loss: 0.3267606794834137
2023-01-21 09:43:26.285682: step: 536/530, loss: 0.1564989537000656
2023-01-21 09:43:27.434856: step: 540/530, loss: 0.1945013552904129
2023-01-21 09:43:28.595709: step: 544/530, loss: 0.0932827964425087
2023-01-21 09:43:29.730249: step: 548/530, loss: 0.25178176164627075
2023-01-21 09:43:30.828198: step: 552/530, loss: 0.06794595718383789
2023-01-21 09:43:31.967168: step: 556/530, loss: 0.025017166510224342
2023-01-21 09:43:33.149810: step: 560/530, loss: 0.17379188537597656
2023-01-21 09:43:34.251048: step: 564/530, loss: 0.22268112003803253
2023-01-21 09:43:35.391069: step: 568/530, loss: 0.124933622777462
2023-01-21 09:43:36.483763: step: 572/530, loss: 0.1330583542585373
2023-01-21 09:43:37.610736: step: 576/530, loss: 0.3112865388393402
2023-01-21 09:43:38.708312: step: 580/530, loss: 0.044574640691280365
2023-01-21 09:43:39.839309: step: 584/530, loss: 0.08824305236339569
2023-01-21 09:43:40.974534: step: 588/530, loss: 0.05356311798095703
2023-01-21 09:43:42.100962: step: 592/530, loss: 0.19820280373096466
2023-01-21 09:43:43.241613: step: 596/530, loss: 0.26677417755126953
2023-01-21 09:43:44.395108: step: 600/530, loss: 0.09618616104125977
2023-01-21 09:43:45.534005: step: 604/530, loss: 0.03541979566216469
2023-01-21 09:43:46.639186: step: 608/530, loss: 0.011844397522509098
2023-01-21 09:43:47.752199: step: 612/530, loss: 0.12447986751794815
2023-01-21 09:43:48.857992: step: 616/530, loss: 0.02741217613220215
2023-01-21 09:43:49.975099: step: 620/530, loss: 0.0318482406437397
2023-01-21 09:43:51.085894: step: 624/530, loss: 0.03936829790472984
2023-01-21 09:43:52.222151: step: 628/530, loss: 0.08939743041992188
2023-01-21 09:43:53.338308: step: 632/530, loss: 0.39468926191329956
2023-01-21 09:43:54.465030: step: 636/530, loss: 0.08065292984247208
2023-01-21 09:43:55.614358: step: 640/530, loss: 0.019866371527314186
2023-01-21 09:43:56.731242: step: 644/530, loss: 0.02760334126651287
2023-01-21 09:43:57.837729: step: 648/530, loss: 0.1017528548836708
2023-01-21 09:43:58.941216: step: 652/530, loss: 0.054642342031002045
2023-01-21 09:44:00.054228: step: 656/530, loss: 0.1251974105834961
2023-01-21 09:44:01.169954: step: 660/530, loss: 0.13237157464027405
2023-01-21 09:44:02.335463: step: 664/530, loss: 0.023891830816864967
2023-01-21 09:44:03.487355: step: 668/530, loss: 0.031920768320560455
2023-01-21 09:44:04.614911: step: 672/530, loss: 0.5596164464950562
2023-01-21 09:44:05.714118: step: 676/530, loss: 0.1701713502407074
2023-01-21 09:44:06.817752: step: 680/530, loss: 0.322089821100235
2023-01-21 09:44:07.948527: step: 684/530, loss: 0.3374071717262268
2023-01-21 09:44:09.070412: step: 688/530, loss: 0.03748607635498047
2023-01-21 09:44:10.180944: step: 692/530, loss: 0.08294196426868439
2023-01-21 09:44:11.323096: step: 696/530, loss: 0.036841683089733124
2023-01-21 09:44:12.430986: step: 700/530, loss: 0.5671392679214478
2023-01-21 09:44:13.551846: step: 704/530, loss: 0.12063626945018768
2023-01-21 09:44:14.635402: step: 708/530, loss: 0.03777356445789337
2023-01-21 09:44:15.741693: step: 712/530, loss: 0.05540013313293457
2023-01-21 09:44:16.892866: step: 716/530, loss: 1.0611423254013062
2023-01-21 09:44:18.026751: step: 720/530, loss: 0.14903612434864044
2023-01-21 09:44:19.158666: step: 724/530, loss: 0.06801829487085342
2023-01-21 09:44:20.277404: step: 728/530, loss: 0.1702050268650055
2023-01-21 09:44:21.385689: step: 732/530, loss: 0.06455488502979279
2023-01-21 09:44:22.488064: step: 736/530, loss: 0.039522647857666016
2023-01-21 09:44:23.592314: step: 740/530, loss: 0.013491058722138405
2023-01-21 09:44:24.732340: step: 744/530, loss: 0.013341330923140049
2023-01-21 09:44:25.832878: step: 748/530, loss: 0.008408689871430397
2023-01-21 09:44:26.955048: step: 752/530, loss: 0.10313113033771515
2023-01-21 09:44:28.081274: step: 756/530, loss: 0.12600445747375488
2023-01-21 09:44:29.220370: step: 760/530, loss: 0.10465564578771591
2023-01-21 09:44:30.367904: step: 764/530, loss: 0.7691822052001953
2023-01-21 09:44:31.488035: step: 768/530, loss: 0.13884945213794708
2023-01-21 09:44:32.648858: step: 772/530, loss: 0.5772150158882141
2023-01-21 09:44:33.781248: step: 776/530, loss: 0.011269379407167435
2023-01-21 09:44:34.891432: step: 780/530, loss: 0.019548512995243073
2023-01-21 09:44:36.017101: step: 784/530, loss: 0.02127857133746147
2023-01-21 09:44:37.159130: step: 788/530, loss: 0.05510329082608223
2023-01-21 09:44:38.284641: step: 792/530, loss: 0.2115684449672699
2023-01-21 09:44:39.426017: step: 796/530, loss: 0.08806119114160538
2023-01-21 09:44:40.539503: step: 800/530, loss: 0.08503551036119461
2023-01-21 09:44:41.661549: step: 804/530, loss: 0.14497795701026917
2023-01-21 09:44:42.796627: step: 808/530, loss: 0.5076913237571716
2023-01-21 09:44:43.949440: step: 812/530, loss: 0.049543194472789764
2023-01-21 09:44:45.102136: step: 816/530, loss: 0.03858156502246857
2023-01-21 09:44:46.201707: step: 820/530, loss: 0.6613465547561646
2023-01-21 09:44:47.343233: step: 824/530, loss: 0.08955249935388565
2023-01-21 09:44:48.491246: step: 828/530, loss: 0.07663831859827042
2023-01-21 09:44:49.615382: step: 832/530, loss: 0.876922607421875
2023-01-21 09:44:50.727849: step: 836/530, loss: 0.4619845449924469
2023-01-21 09:44:51.857573: step: 840/530, loss: 1.1741057634353638
2023-01-21 09:44:52.965546: step: 844/530, loss: 0.20487356185913086
2023-01-21 09:44:54.085521: step: 848/530, loss: 0.04862041771411896
2023-01-21 09:44:55.207780: step: 852/530, loss: 0.0805690735578537
2023-01-21 09:44:56.345158: step: 856/530, loss: 0.13526864349842072
2023-01-21 09:44:57.490329: step: 860/530, loss: 0.2602815628051758
2023-01-21 09:44:58.608526: step: 864/530, loss: 0.15856361389160156
2023-01-21 09:44:59.736339: step: 868/530, loss: 0.060231827199459076
2023-01-21 09:45:00.863514: step: 872/530, loss: 0.1310029923915863
2023-01-21 09:45:01.971447: step: 876/530, loss: 0.2046949416399002
2023-01-21 09:45:03.123411: step: 880/530, loss: 0.007313728332519531
2023-01-21 09:45:04.269379: step: 884/530, loss: 0.13419418036937714
2023-01-21 09:45:05.394771: step: 888/530, loss: 0.0949595496058464
2023-01-21 09:45:06.495060: step: 892/530, loss: 0.33237114548683167
2023-01-21 09:45:07.638547: step: 896/530, loss: 0.022608280181884766
2023-01-21 09:45:08.765227: step: 900/530, loss: 1.4238147735595703
2023-01-21 09:45:09.929631: step: 904/530, loss: 0.061098575592041016
2023-01-21 09:45:11.058450: step: 908/530, loss: 0.11682215332984924
2023-01-21 09:45:12.164480: step: 912/530, loss: 0.5803439021110535
2023-01-21 09:45:13.289589: step: 916/530, loss: 0.0573551207780838
2023-01-21 09:45:14.400671: step: 920/530, loss: 0.05730133131146431
2023-01-21 09:45:15.527158: step: 924/530, loss: 0.2132701873779297
2023-01-21 09:45:16.673216: step: 928/530, loss: 0.06581659615039825
2023-01-21 09:45:17.789783: step: 932/530, loss: 0.025093458592891693
2023-01-21 09:45:18.913177: step: 936/530, loss: 0.021825648844242096
2023-01-21 09:45:20.032861: step: 940/530, loss: 0.11853313446044922
2023-01-21 09:45:21.163492: step: 944/530, loss: 0.16185303032398224
2023-01-21 09:45:22.282944: step: 948/530, loss: 0.09925565868616104
2023-01-21 09:45:23.383618: step: 952/530, loss: 0.08460798114538193
2023-01-21 09:45:24.514833: step: 956/530, loss: 0.24478113651275635
2023-01-21 09:45:25.615043: step: 960/530, loss: 0.0432397834956646
2023-01-21 09:45:26.721769: step: 964/530, loss: 0.05497493967413902
2023-01-21 09:45:27.854908: step: 968/530, loss: 0.23973789811134338
2023-01-21 09:45:28.966285: step: 972/530, loss: 0.01343536376953125
2023-01-21 09:45:30.090307: step: 976/530, loss: 0.435263454914093
2023-01-21 09:45:31.229717: step: 980/530, loss: 0.19541878998279572
2023-01-21 09:45:32.375845: step: 984/530, loss: 0.2850082516670227
2023-01-21 09:45:33.488023: step: 988/530, loss: 0.1438342034816742
2023-01-21 09:45:34.602376: step: 992/530, loss: 0.28700196743011475
2023-01-21 09:45:35.704894: step: 996/530, loss: 0.005561149213463068
2023-01-21 09:45:36.822495: step: 1000/530, loss: 0.396655410528183
2023-01-21 09:45:37.953578: step: 1004/530, loss: 0.04499969631433487
2023-01-21 09:45:39.120429: step: 1008/530, loss: 0.09269142150878906
2023-01-21 09:45:40.276547: step: 1012/530, loss: 0.16717949509620667
2023-01-21 09:45:41.417321: step: 1016/530, loss: 0.08923578262329102
2023-01-21 09:45:42.555506: step: 1020/530, loss: 0.12078352272510529
2023-01-21 09:45:43.667224: step: 1024/530, loss: 0.16229376196861267
2023-01-21 09:45:44.798594: step: 1028/530, loss: 0.0274245273321867
2023-01-21 09:45:45.937950: step: 1032/530, loss: 0.024878215044736862
2023-01-21 09:45:47.082836: step: 1036/530, loss: 0.07197790592908859
2023-01-21 09:45:48.199175: step: 1040/530, loss: 0.0647188201546669
2023-01-21 09:45:49.330113: step: 1044/530, loss: 0.1187833845615387
2023-01-21 09:45:50.471150: step: 1048/530, loss: 0.14217329025268555
2023-01-21 09:45:51.592829: step: 1052/530, loss: 0.07880067825317383
2023-01-21 09:45:52.734304: step: 1056/530, loss: 0.1424035131931305
2023-01-21 09:45:53.846452: step: 1060/530, loss: 0.02519674226641655
2023-01-21 09:45:54.961707: step: 1064/530, loss: 0.041162874549627304
2023-01-21 09:45:56.072600: step: 1068/530, loss: 0.050572872161865234
2023-01-21 09:45:57.213077: step: 1072/530, loss: 0.16051027178764343
2023-01-21 09:45:58.331986: step: 1076/530, loss: 0.11720800399780273
2023-01-21 09:45:59.438640: step: 1080/530, loss: 0.06875353306531906
2023-01-21 09:46:00.583679: step: 1084/530, loss: 0.032303810119628906
2023-01-21 09:46:01.692846: step: 1088/530, loss: 0.6615206003189087
2023-01-21 09:46:02.847657: step: 1092/530, loss: 0.0618986152112484
2023-01-21 09:46:04.008306: step: 1096/530, loss: 0.08714609593153
2023-01-21 09:46:05.131898: step: 1100/530, loss: 0.10588884353637695
2023-01-21 09:46:06.279515: step: 1104/530, loss: 0.05422933027148247
2023-01-21 09:46:07.460950: step: 1108/530, loss: 0.08528108149766922
2023-01-21 09:46:08.579745: step: 1112/530, loss: 0.04613494873046875
2023-01-21 09:46:09.719781: step: 1116/530, loss: 0.06508312374353409
2023-01-21 09:46:10.811581: step: 1120/530, loss: 0.0842016190290451
2023-01-21 09:46:11.938167: step: 1124/530, loss: 0.17549681663513184
2023-01-21 09:46:13.043415: step: 1128/530, loss: 0.021941518411040306
2023-01-21 09:46:14.165065: step: 1132/530, loss: 0.732150673866272
2023-01-21 09:46:15.269527: step: 1136/530, loss: 0.017777252942323685
2023-01-21 09:46:16.419451: step: 1140/530, loss: 0.26571425795555115
2023-01-21 09:46:17.534477: step: 1144/530, loss: 1.4252564907073975
2023-01-21 09:46:18.623181: step: 1148/530, loss: 0.057390954345464706
2023-01-21 09:46:19.742905: step: 1152/530, loss: 0.22549590468406677
2023-01-21 09:46:20.835615: step: 1156/530, loss: 0.15741194784641266
2023-01-21 09:46:22.000926: step: 1160/530, loss: 0.39007800817489624
2023-01-21 09:46:23.118859: step: 1164/530, loss: 0.07414837181568146
2023-01-21 09:46:24.240352: step: 1168/530, loss: 0.26224347949028015
2023-01-21 09:46:25.370139: step: 1172/530, loss: 0.1373356729745865
2023-01-21 09:46:26.503709: step: 1176/530, loss: 0.05471067875623703
2023-01-21 09:46:27.639690: step: 1180/530, loss: 0.11634416878223419
2023-01-21 09:46:28.784187: step: 1184/530, loss: 0.22966629266738892
2023-01-21 09:46:29.900882: step: 1188/530, loss: 0.0383848175406456
2023-01-21 09:46:30.988696: step: 1192/530, loss: 0.03922059386968613
2023-01-21 09:46:32.141655: step: 1196/530, loss: 0.04711313545703888
2023-01-21 09:46:33.259894: step: 1200/530, loss: 0.12867765128612518
2023-01-21 09:46:34.398174: step: 1204/530, loss: 0.20471186935901642
2023-01-21 09:46:35.535606: step: 1208/530, loss: 0.19581404328346252
2023-01-21 09:46:36.641581: step: 1212/530, loss: 0.07948637008666992
2023-01-21 09:46:37.757819: step: 1216/530, loss: 0.05376477539539337
2023-01-21 09:46:38.899667: step: 1220/530, loss: 0.036206819117069244
2023-01-21 09:46:39.997602: step: 1224/530, loss: 0.19651050865650177
2023-01-21 09:46:41.112580: step: 1228/530, loss: 0.033911801874637604
2023-01-21 09:46:42.228882: step: 1232/530, loss: 0.15604406595230103
2023-01-21 09:46:43.342387: step: 1236/530, loss: 0.0981866866350174
2023-01-21 09:46:44.464251: step: 1240/530, loss: 0.035298824310302734
2023-01-21 09:46:45.611203: step: 1244/530, loss: 0.13226062059402466
2023-01-21 09:46:46.746575: step: 1248/530, loss: 0.1768416464328766
2023-01-21 09:46:47.844086: step: 1252/530, loss: 0.16594401001930237
2023-01-21 09:46:48.960208: step: 1256/530, loss: 0.07306098937988281
2023-01-21 09:46:50.095129: step: 1260/530, loss: 0.09872972965240479
2023-01-21 09:46:51.225042: step: 1264/530, loss: 0.016474151983857155
2023-01-21 09:46:52.349472: step: 1268/530, loss: 0.10059785842895508
2023-01-21 09:46:53.459896: step: 1272/530, loss: 0.07504215091466904
2023-01-21 09:46:54.574304: step: 1276/530, loss: 0.02240929752588272
2023-01-21 09:46:55.714239: step: 1280/530, loss: 0.24671754240989685
2023-01-21 09:46:56.849506: step: 1284/530, loss: 0.06925249099731445
2023-01-21 09:46:57.941370: step: 1288/530, loss: 0.05390463024377823
2023-01-21 09:46:59.037923: step: 1292/530, loss: 0.25257396697998047
2023-01-21 09:47:00.168811: step: 1296/530, loss: 0.2731453776359558
2023-01-21 09:47:01.298717: step: 1300/530, loss: 0.04899749904870987
2023-01-21 09:47:02.413926: step: 1304/530, loss: 0.017156029120087624
2023-01-21 09:47:03.539374: step: 1308/530, loss: 0.05664246156811714
2023-01-21 09:47:04.657638: step: 1312/530, loss: 0.205424502491951
2023-01-21 09:47:05.778376: step: 1316/530, loss: 0.04082925245165825
2023-01-21 09:47:06.879830: step: 1320/530, loss: 0.2498483955860138
2023-01-21 09:47:08.008864: step: 1324/530, loss: 1.0341918468475342
2023-01-21 09:47:09.137308: step: 1328/530, loss: 0.02234964445233345
2023-01-21 09:47:10.354325: step: 1332/530, loss: 0.11992769688367844
2023-01-21 09:47:11.481020: step: 1336/530, loss: 0.12890520691871643
2023-01-21 09:47:12.594919: step: 1340/530, loss: 0.0451996810734272
2023-01-21 09:47:13.722918: step: 1344/530, loss: 0.12387257069349289
2023-01-21 09:47:14.850168: step: 1348/530, loss: 0.026116086170077324
2023-01-21 09:47:15.969371: step: 1352/530, loss: 0.233127623796463
2023-01-21 09:47:17.092532: step: 1356/530, loss: 0.12263259291648865
2023-01-21 09:47:18.191482: step: 1360/530, loss: 0.057888224720954895
2023-01-21 09:47:19.345985: step: 1364/530, loss: 0.12071923911571503
2023-01-21 09:47:20.479000: step: 1368/530, loss: 0.14103765785694122
2023-01-21 09:47:21.601934: step: 1372/530, loss: 0.19510279595851898
2023-01-21 09:47:22.711996: step: 1376/530, loss: 0.3639591932296753
2023-01-21 09:47:23.831081: step: 1380/530, loss: 0.08072170615196228
2023-01-21 09:47:24.937551: step: 1384/530, loss: 0.08210192620754242
2023-01-21 09:47:26.063488: step: 1388/530, loss: 0.03093853034079075
2023-01-21 09:47:27.198537: step: 1392/530, loss: 0.10535440593957901
2023-01-21 09:47:28.321991: step: 1396/530, loss: 0.01924286037683487
2023-01-21 09:47:29.427567: step: 1400/530, loss: 0.041249942034482956
2023-01-21 09:47:30.556482: step: 1404/530, loss: 0.11865682899951935
2023-01-21 09:47:31.663311: step: 1408/530, loss: 0.013319588266313076
2023-01-21 09:47:32.788587: step: 1412/530, loss: 0.022849559783935547
2023-01-21 09:47:33.900700: step: 1416/530, loss: 0.17736944556236267
2023-01-21 09:47:35.016247: step: 1420/530, loss: 0.6939536929130554
2023-01-21 09:47:36.151936: step: 1424/530, loss: 0.1634509116411209
2023-01-21 09:47:37.270955: step: 1428/530, loss: 0.09280534088611603
2023-01-21 09:47:38.411648: step: 1432/530, loss: 0.13037090003490448
2023-01-21 09:47:39.532030: step: 1436/530, loss: 0.17189759016036987
2023-01-21 09:47:40.656742: step: 1440/530, loss: 0.17920485138893127
2023-01-21 09:47:41.768004: step: 1444/530, loss: 0.08363771438598633
2023-01-21 09:47:42.864427: step: 1448/530, loss: 0.2847312092781067
2023-01-21 09:47:43.984325: step: 1452/530, loss: 0.07989463955163956
2023-01-21 09:47:45.100317: step: 1456/530, loss: 0.10486698150634766
2023-01-21 09:47:46.223393: step: 1460/530, loss: 0.12657156586647034
2023-01-21 09:47:47.382213: step: 1464/530, loss: 0.15494680404663086
2023-01-21 09:47:48.514561: step: 1468/530, loss: 0.01230688113719225
2023-01-21 09:47:49.641357: step: 1472/530, loss: 0.05029625818133354
2023-01-21 09:47:50.770918: step: 1476/530, loss: 0.032521724700927734
2023-01-21 09:47:51.902409: step: 1480/530, loss: 0.14653682708740234
2023-01-21 09:47:53.023111: step: 1484/530, loss: 0.09010009467601776
2023-01-21 09:47:54.151231: step: 1488/530, loss: 0.12466501444578171
2023-01-21 09:47:55.320304: step: 1492/530, loss: 0.05337543413043022
2023-01-21 09:47:56.446652: step: 1496/530, loss: 0.04406700283288956
2023-01-21 09:47:57.573585: step: 1500/530, loss: 0.2210375815629959
2023-01-21 09:47:58.697606: step: 1504/530, loss: 0.18387623131275177
2023-01-21 09:47:59.828881: step: 1508/530, loss: 0.12805165350437164
2023-01-21 09:48:00.961051: step: 1512/530, loss: 0.0774141326546669
2023-01-21 09:48:02.102560: step: 1516/530, loss: 0.10437707602977753
2023-01-21 09:48:03.228419: step: 1520/530, loss: 0.14396977424621582
2023-01-21 09:48:04.338972: step: 1524/530, loss: 0.05496826022863388
2023-01-21 09:48:05.463666: step: 1528/530, loss: 0.11916399002075195
2023-01-21 09:48:06.587208: step: 1532/530, loss: 0.1935289204120636
2023-01-21 09:48:07.696191: step: 1536/530, loss: 0.42479172348976135
2023-01-21 09:48:08.861001: step: 1540/530, loss: 0.36505621671676636
2023-01-21 09:48:09.965726: step: 1544/530, loss: 0.16534185409545898
2023-01-21 09:48:11.094257: step: 1548/530, loss: 0.03631606325507164
2023-01-21 09:48:12.206518: step: 1552/530, loss: 0.10368328541517258
2023-01-21 09:48:13.381136: step: 1556/530, loss: 0.68121337890625
2023-01-21 09:48:14.524329: step: 1560/530, loss: 0.13818788528442383
2023-01-21 09:48:15.637822: step: 1564/530, loss: 0.7915406823158264
2023-01-21 09:48:16.753373: step: 1568/530, loss: 0.06029238551855087
2023-01-21 09:48:17.889532: step: 1572/530, loss: 0.13905592262744904
2023-01-21 09:48:19.027785: step: 1576/530, loss: 0.10436001420021057
2023-01-21 09:48:20.129917: step: 1580/530, loss: 0.22023090720176697
2023-01-21 09:48:21.241823: step: 1584/530, loss: 0.05080080404877663
2023-01-21 09:48:22.352844: step: 1588/530, loss: 0.06474848091602325
2023-01-21 09:48:23.505332: step: 1592/530, loss: 0.14199644327163696
2023-01-21 09:48:24.627718: step: 1596/530, loss: 0.05756683275103569
2023-01-21 09:48:25.738354: step: 1600/530, loss: 0.13492439687252045
2023-01-21 09:48:26.820005: step: 1604/530, loss: 0.02302999421954155
2023-01-21 09:48:27.956330: step: 1608/530, loss: 0.16538085043430328
2023-01-21 09:48:29.075792: step: 1612/530, loss: 0.0825202465057373
2023-01-21 09:48:30.188763: step: 1616/530, loss: 0.05481024086475372
2023-01-21 09:48:31.306116: step: 1620/530, loss: 0.08377237617969513
2023-01-21 09:48:32.416917: step: 1624/530, loss: 0.009915542788803577
2023-01-21 09:48:33.561125: step: 1628/530, loss: 0.07840323448181152
2023-01-21 09:48:34.725871: step: 1632/530, loss: 0.06298070400953293
2023-01-21 09:48:35.810259: step: 1636/530, loss: 0.07393121719360352
2023-01-21 09:48:36.928633: step: 1640/530, loss: 0.13563385605812073
2023-01-21 09:48:38.060668: step: 1644/530, loss: 0.168226957321167
2023-01-21 09:48:39.214913: step: 1648/530, loss: 0.04362669214606285
2023-01-21 09:48:40.342771: step: 1652/530, loss: 0.054886434227228165
2023-01-21 09:48:41.458640: step: 1656/530, loss: 1.4837015867233276
2023-01-21 09:48:42.574008: step: 1660/530, loss: 0.06503525376319885
2023-01-21 09:48:43.716922: step: 1664/530, loss: 0.06147126853466034
2023-01-21 09:48:44.811041: step: 1668/530, loss: 0.08744516223669052
2023-01-21 09:48:45.984477: step: 1672/530, loss: 0.3688690662384033
2023-01-21 09:48:47.079087: step: 1676/530, loss: 0.024454019963741302
2023-01-21 09:48:48.210556: step: 1680/530, loss: 0.010876060463488102
2023-01-21 09:48:49.345730: step: 1684/530, loss: 0.11532311141490936
2023-01-21 09:48:50.452484: step: 1688/530, loss: 0.0986049622297287
2023-01-21 09:48:51.578082: step: 1692/530, loss: 0.07453000545501709
2023-01-21 09:48:52.695137: step: 1696/530, loss: 0.09139471501111984
2023-01-21 09:48:53.794728: step: 1700/530, loss: 0.05962200090289116
2023-01-21 09:48:54.928831: step: 1704/530, loss: 0.17260321974754333
2023-01-21 09:48:56.057609: step: 1708/530, loss: 0.06605947017669678
2023-01-21 09:48:57.169798: step: 1712/530, loss: 0.1656384915113449
2023-01-21 09:48:58.295667: step: 1716/530, loss: 0.35463786125183105
2023-01-21 09:48:59.455839: step: 1720/530, loss: 0.16194772720336914
2023-01-21 09:49:00.567129: step: 1724/530, loss: 0.06718187779188156
2023-01-21 09:49:01.688189: step: 1728/530, loss: 0.2318398505449295
2023-01-21 09:49:02.848890: step: 1732/530, loss: 0.07556295394897461
2023-01-21 09:49:03.951752: step: 1736/530, loss: 0.02566538006067276
2023-01-21 09:49:05.100280: step: 1740/530, loss: 0.09393348544836044
2023-01-21 09:49:06.217049: step: 1744/530, loss: 0.04976792261004448
2023-01-21 09:49:07.367293: step: 1748/530, loss: 0.07157669216394424
2023-01-21 09:49:08.532348: step: 1752/530, loss: 0.0800900012254715
2023-01-21 09:49:09.645144: step: 1756/530, loss: 0.019009782001376152
2023-01-21 09:49:10.755109: step: 1760/530, loss: 0.7311533689498901
2023-01-21 09:49:11.853178: step: 1764/530, loss: 0.13898307085037231
2023-01-21 09:49:12.951798: step: 1768/530, loss: 0.05152168869972229
2023-01-21 09:49:14.075630: step: 1772/530, loss: 0.055876828730106354
2023-01-21 09:49:15.201149: step: 1776/530, loss: 0.05248122289776802
2023-01-21 09:49:16.313480: step: 1780/530, loss: 0.07632989436388016
2023-01-21 09:49:17.434586: step: 1784/530, loss: 0.6406081318855286
2023-01-21 09:49:18.579462: step: 1788/530, loss: 0.6238624453544617
2023-01-21 09:49:19.685636: step: 1792/530, loss: 0.17739373445510864
2023-01-21 09:49:20.831203: step: 1796/530, loss: 0.06013917922973633
2023-01-21 09:49:21.987350: step: 1800/530, loss: 0.12412300705909729
2023-01-21 09:49:23.114971: step: 1804/530, loss: 0.07818011939525604
2023-01-21 09:49:24.207528: step: 1808/530, loss: 0.5141303539276123
2023-01-21 09:49:25.343739: step: 1812/530, loss: 0.2001221626996994
2023-01-21 09:49:26.470606: step: 1816/530, loss: 0.15150794386863708
2023-01-21 09:49:27.580237: step: 1820/530, loss: 0.13091126084327698
2023-01-21 09:49:28.700750: step: 1824/530, loss: 0.018029015511274338
2023-01-21 09:49:29.826598: step: 1828/530, loss: 0.13202953338623047
2023-01-21 09:49:30.977762: step: 1832/530, loss: 0.033278465270996094
2023-01-21 09:49:32.157012: step: 1836/530, loss: 0.02139580436050892
2023-01-21 09:49:33.271399: step: 1840/530, loss: 0.10722912102937698
2023-01-21 09:49:34.377020: step: 1844/530, loss: 0.1031157523393631
2023-01-21 09:49:35.518032: step: 1848/530, loss: 0.3295229971408844
2023-01-21 09:49:36.627798: step: 1852/530, loss: 0.06683597713708878
2023-01-21 09:49:37.760463: step: 1856/530, loss: 0.5251230001449585
2023-01-21 09:49:38.859130: step: 1860/530, loss: 0.07481712847948074
2023-01-21 09:49:39.995551: step: 1864/530, loss: 0.04296443611383438
2023-01-21 09:49:41.117835: step: 1868/530, loss: 0.10067825019359589
2023-01-21 09:49:42.235278: step: 1872/530, loss: 0.31604501605033875
2023-01-21 09:49:43.368413: step: 1876/530, loss: 0.17540818452835083
2023-01-21 09:49:44.516061: step: 1880/530, loss: 0.056783199310302734
2023-01-21 09:49:45.619285: step: 1884/530, loss: 0.06674452126026154
2023-01-21 09:49:46.764948: step: 1888/530, loss: 0.018225669860839844
2023-01-21 09:49:47.874146: step: 1892/530, loss: 0.09129539132118225
2023-01-21 09:49:48.967289: step: 1896/530, loss: 0.06556501239538193
2023-01-21 09:49:50.082104: step: 1900/530, loss: 0.08240365982055664
2023-01-21 09:49:51.191940: step: 1904/530, loss: 0.15672054886817932
2023-01-21 09:49:52.349668: step: 1908/530, loss: 0.07845965027809143
2023-01-21 09:49:53.464842: step: 1912/530, loss: 0.0674038901925087
2023-01-21 09:49:54.569651: step: 1916/530, loss: 0.17329376935958862
2023-01-21 09:49:55.742614: step: 1920/530, loss: 0.3830658793449402
2023-01-21 09:49:56.855903: step: 1924/530, loss: 0.017481040209531784
2023-01-21 09:49:58.004206: step: 1928/530, loss: 0.4208986759185791
2023-01-21 09:49:59.113944: step: 1932/530, loss: 0.08931312710046768
2023-01-21 09:50:00.250288: step: 1936/530, loss: 0.10816283524036407
2023-01-21 09:50:01.356749: step: 1940/530, loss: 0.04626784473657608
2023-01-21 09:50:02.477127: step: 1944/530, loss: 0.1099090576171875
2023-01-21 09:50:03.603454: step: 1948/530, loss: 0.02344541624188423
2023-01-21 09:50:04.752318: step: 1952/530, loss: 0.15743452310562134
2023-01-21 09:50:05.865715: step: 1956/530, loss: 0.1801835000514984
2023-01-21 09:50:07.032505: step: 1960/530, loss: 0.15383490920066833
2023-01-21 09:50:08.155354: step: 1964/530, loss: 0.2860403060913086
2023-01-21 09:50:09.285988: step: 1968/530, loss: 0.22299738228321075
2023-01-21 09:50:10.423018: step: 1972/530, loss: 0.07216902077198029
2023-01-21 09:50:11.552836: step: 1976/530, loss: 0.39765453338623047
2023-01-21 09:50:12.693715: step: 1980/530, loss: 0.03186450153589249
2023-01-21 09:50:13.814133: step: 1984/530, loss: 0.055449869483709335
2023-01-21 09:50:14.942598: step: 1988/530, loss: 0.11690497398376465
2023-01-21 09:50:16.061098: step: 1992/530, loss: 0.024784088134765625
2023-01-21 09:50:17.173914: step: 1996/530, loss: 0.005114507861435413
2023-01-21 09:50:18.285037: step: 2000/530, loss: 0.10327720642089844
2023-01-21 09:50:19.468158: step: 2004/530, loss: 0.016121864318847656
2023-01-21 09:50:20.619878: step: 2008/530, loss: 0.09388083964586258
2023-01-21 09:50:21.727073: step: 2012/530, loss: 0.3490671217441559
2023-01-21 09:50:22.844950: step: 2016/530, loss: 0.06737031787633896
2023-01-21 09:50:23.958593: step: 2020/530, loss: 0.10140247642993927
2023-01-21 09:50:25.076454: step: 2024/530, loss: 0.0574406161904335
2023-01-21 09:50:26.186736: step: 2028/530, loss: 0.25454071164131165
2023-01-21 09:50:27.330225: step: 2032/530, loss: 0.09743957221508026
2023-01-21 09:50:28.453271: step: 2036/530, loss: 0.08753442764282227
2023-01-21 09:50:29.578640: step: 2040/530, loss: 0.4302801191806793
2023-01-21 09:50:30.700444: step: 2044/530, loss: 0.0899573341012001
2023-01-21 09:50:31.857716: step: 2048/530, loss: 0.2613717019557953
2023-01-21 09:50:33.000662: step: 2052/530, loss: 0.08410835266113281
2023-01-21 09:50:34.147986: step: 2056/530, loss: 0.06310901790857315
2023-01-21 09:50:35.279665: step: 2060/530, loss: 0.06670618057250977
2023-01-21 09:50:36.441400: step: 2064/530, loss: 0.1709795892238617
2023-01-21 09:50:37.598181: step: 2068/530, loss: 0.8651343584060669
2023-01-21 09:50:38.733176: step: 2072/530, loss: 0.25615906715393066
2023-01-21 09:50:39.860844: step: 2076/530, loss: 0.1450739949941635
2023-01-21 09:50:40.982880: step: 2080/530, loss: 0.03266597166657448
2023-01-21 09:50:42.140075: step: 2084/530, loss: 0.12448253482580185
2023-01-21 09:50:43.277437: step: 2088/530, loss: 0.02251415327191353
2023-01-21 09:50:44.393364: step: 2092/530, loss: 0.09509305655956268
2023-01-21 09:50:45.522832: step: 2096/530, loss: 0.03014073520898819
2023-01-21 09:50:46.620610: step: 2100/530, loss: 0.10166730731725693
2023-01-21 09:50:47.785154: step: 2104/530, loss: 0.017941810190677643
2023-01-21 09:50:48.912099: step: 2108/530, loss: 0.01709207333624363
2023-01-21 09:50:50.034180: step: 2112/530, loss: 0.14904442429542542
2023-01-21 09:50:51.136711: step: 2116/530, loss: 0.03419847786426544
2023-01-21 09:50:52.265331: step: 2120/530, loss: 0.10788088291883469
==================================================
Loss: 0.160
--------------------
Dev: {'event': {'p': 0.5693215339233039, 'r': 0.7709720372836218, 'f1': 0.6549773755656109}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6194531600179292, 'r': 0.7897142857142857, 'f1': 0.6942979150967095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
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': 7}
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': 7}
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': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:51:32.932592: step: 4/530, loss: 0.03088674508035183
2023-01-21 09:51:34.051975: step: 8/530, loss: 0.0714973509311676
2023-01-21 09:51:35.166703: step: 12/530, loss: 0.03342180326581001
2023-01-21 09:51:36.285611: step: 16/530, loss: 0.08557090163230896
2023-01-21 09:51:37.407932: step: 20/530, loss: 0.11828122287988663
2023-01-21 09:51:38.514660: step: 24/530, loss: 0.02834930457174778
2023-01-21 09:51:39.641218: step: 28/530, loss: 0.09843587875366211
2023-01-21 09:51:40.736212: step: 32/530, loss: 0.10048885643482208
2023-01-21 09:51:41.849382: step: 36/530, loss: 0.7323719263076782
2023-01-21 09:51:42.990727: step: 40/530, loss: 0.15236178040504456
2023-01-21 09:51:44.132298: step: 44/530, loss: 0.08092904090881348
2023-01-21 09:51:45.259545: step: 48/530, loss: 0.007445144932717085
2023-01-21 09:51:46.371586: step: 52/530, loss: 0.06854166835546494
2023-01-21 09:51:47.508350: step: 56/530, loss: 0.11754970252513885
2023-01-21 09:51:48.641645: step: 60/530, loss: 0.32558268308639526
2023-01-21 09:51:49.730175: step: 64/530, loss: 0.023315954953432083
2023-01-21 09:51:50.833846: step: 68/530, loss: 0.8472309112548828
2023-01-21 09:51:51.931752: step: 72/530, loss: 0.07725968956947327
2023-01-21 09:51:53.076973: step: 76/530, loss: 0.08451500535011292
2023-01-21 09:51:54.204493: step: 80/530, loss: 0.025615310296416283
2023-01-21 09:51:55.315374: step: 84/530, loss: 0.06845617294311523
2023-01-21 09:51:56.431724: step: 88/530, loss: 0.005445909686386585
2023-01-21 09:51:57.564259: step: 92/530, loss: 0.01611170917749405
2023-01-21 09:51:58.708156: step: 96/530, loss: 0.14182491600513458
2023-01-21 09:51:59.835333: step: 100/530, loss: 0.03151226043701172
2023-01-21 09:52:00.978763: step: 104/530, loss: 0.14596061408519745
2023-01-21 09:52:02.097800: step: 108/530, loss: 0.13791608810424805
2023-01-21 09:52:03.202823: step: 112/530, loss: 0.0609862320125103
2023-01-21 09:52:04.317787: step: 116/530, loss: 0.1532306671142578
2023-01-21 09:52:05.443468: step: 120/530, loss: 0.1373240053653717
2023-01-21 09:52:06.545231: step: 124/530, loss: 0.09173421561717987
2023-01-21 09:52:07.647682: step: 128/530, loss: 0.3763471245765686
2023-01-21 09:52:08.753201: step: 132/530, loss: 0.12174288928508759
2023-01-21 09:52:09.838996: step: 136/530, loss: 0.06933148205280304
2023-01-21 09:52:10.934190: step: 140/530, loss: 0.014846229925751686
2023-01-21 09:52:12.113639: step: 144/530, loss: 0.034085944294929504
2023-01-21 09:52:13.234054: step: 148/530, loss: 0.04126236215233803
2023-01-21 09:52:14.358556: step: 152/530, loss: 0.10013517737388611
2023-01-21 09:52:15.487414: step: 156/530, loss: 0.07507873326539993
2023-01-21 09:52:16.597594: step: 160/530, loss: 0.09161396324634552
2023-01-21 09:52:17.699877: step: 164/530, loss: 0.009203052148222923
2023-01-21 09:52:18.819075: step: 168/530, loss: 0.312895268201828
2023-01-21 09:52:19.955670: step: 172/530, loss: 0.009002065286040306
2023-01-21 09:52:21.043502: step: 176/530, loss: 0.07059097290039062
2023-01-21 09:52:22.200220: step: 180/530, loss: 0.12018217146396637
2023-01-21 09:52:23.351099: step: 184/530, loss: 0.11672301590442657
2023-01-21 09:52:24.483397: step: 188/530, loss: 0.11591462790966034
2023-01-21 09:52:25.602606: step: 192/530, loss: 0.0751151591539383
2023-01-21 09:52:26.713467: step: 196/530, loss: 0.9985004663467407
2023-01-21 09:52:27.827577: step: 200/530, loss: 0.037081051617860794
2023-01-21 09:52:28.961223: step: 204/530, loss: 0.12355313450098038
2023-01-21 09:52:30.119181: step: 208/530, loss: 0.06885853409767151
2023-01-21 09:52:31.234783: step: 212/530, loss: 0.09651784598827362
2023-01-21 09:52:32.348905: step: 216/530, loss: 0.12591969966888428
2023-01-21 09:52:33.464665: step: 220/530, loss: 0.08783884346485138
2023-01-21 09:52:34.585017: step: 224/530, loss: 0.025673963129520416
2023-01-21 09:52:35.706184: step: 228/530, loss: 0.08829168975353241
2023-01-21 09:52:36.865649: step: 232/530, loss: 0.28565704822540283
2023-01-21 09:52:37.996233: step: 236/530, loss: 0.09349632263183594
2023-01-21 09:52:39.120266: step: 240/530, loss: 0.021793222054839134
2023-01-21 09:52:40.255795: step: 244/530, loss: 0.09603968262672424
2023-01-21 09:52:41.396859: step: 248/530, loss: 0.04812202602624893
2023-01-21 09:52:42.517329: step: 252/530, loss: 0.12237548828125
2023-01-21 09:52:43.644790: step: 256/530, loss: 0.04396219179034233
2023-01-21 09:52:44.748736: step: 260/530, loss: 0.05063905939459801
2023-01-21 09:52:45.903092: step: 264/530, loss: 0.18561352789402008
2023-01-21 09:52:47.040910: step: 268/530, loss: 0.06180925294756889
2023-01-21 09:52:48.178873: step: 272/530, loss: 0.07270612567663193
2023-01-21 09:52:49.331997: step: 276/530, loss: 0.06297808140516281
2023-01-21 09:52:50.430043: step: 280/530, loss: 0.09719981998205185
2023-01-21 09:52:51.548115: step: 284/530, loss: 0.12755441665649414
2023-01-21 09:52:52.693581: step: 288/530, loss: 0.40275105834007263
2023-01-21 09:52:53.815788: step: 292/530, loss: 0.07438831776380539
2023-01-21 09:52:54.935173: step: 296/530, loss: 0.030213166028261185
2023-01-21 09:52:56.042643: step: 300/530, loss: 0.04804039001464844
2023-01-21 09:52:57.212830: step: 304/530, loss: 0.5731737613677979
2023-01-21 09:52:58.351072: step: 308/530, loss: 0.053475238382816315
2023-01-21 09:52:59.471034: step: 312/530, loss: 0.09966201335191727
2023-01-21 09:53:00.568452: step: 316/530, loss: 0.09093177318572998
2023-01-21 09:53:01.718311: step: 320/530, loss: 0.004211616702377796
2023-01-21 09:53:02.864651: step: 324/530, loss: 0.09737997502088547
2023-01-21 09:53:03.987162: step: 328/530, loss: 0.043309975415468216
2023-01-21 09:53:05.101174: step: 332/530, loss: 0.022772599011659622
2023-01-21 09:53:06.255653: step: 336/530, loss: 0.033370498567819595
2023-01-21 09:53:07.394557: step: 340/530, loss: 0.050402261316776276
2023-01-21 09:53:08.506988: step: 344/530, loss: 0.043215371668338776
2023-01-21 09:53:09.618373: step: 348/530, loss: 0.27151376008987427
2023-01-21 09:53:10.775816: step: 352/530, loss: 0.1773693561553955
2023-01-21 09:53:11.888253: step: 356/530, loss: 0.04150247573852539
2023-01-21 09:53:13.020224: step: 360/530, loss: 0.15407544374465942
2023-01-21 09:53:14.143095: step: 364/530, loss: 0.054289959371089935
2023-01-21 09:53:15.272685: step: 368/530, loss: 0.029505252838134766
2023-01-21 09:53:16.389038: step: 372/530, loss: 0.0939764529466629
2023-01-21 09:53:17.515566: step: 376/530, loss: 0.4697422385215759
2023-01-21 09:53:18.627643: step: 380/530, loss: 0.05170917510986328
2023-01-21 09:53:19.769150: step: 384/530, loss: 0.4505559802055359
2023-01-21 09:53:20.925568: step: 388/530, loss: 0.12265956401824951
2023-01-21 09:53:22.025590: step: 392/530, loss: 0.0273679718375206
2023-01-21 09:53:23.163311: step: 396/530, loss: 0.3489646017551422
2023-01-21 09:53:24.301964: step: 400/530, loss: 0.014752007089555264
2023-01-21 09:53:25.437497: step: 404/530, loss: 0.03730654716491699
2023-01-21 09:53:26.570196: step: 408/530, loss: 0.050646115094423294
2023-01-21 09:53:27.692626: step: 412/530, loss: 0.012432193383574486
2023-01-21 09:53:28.815187: step: 416/530, loss: 0.07271060347557068
2023-01-21 09:53:29.939099: step: 420/530, loss: 0.03569746017456055
2023-01-21 09:53:31.069772: step: 424/530, loss: 0.2065838873386383
2023-01-21 09:53:32.198443: step: 428/530, loss: 0.04082994535565376
2023-01-21 09:53:33.316283: step: 432/530, loss: 0.043137550354003906
2023-01-21 09:53:34.424623: step: 436/530, loss: 0.09850387275218964
2023-01-21 09:53:35.555221: step: 440/530, loss: 0.03089609369635582
2023-01-21 09:53:36.655764: step: 444/530, loss: 0.009991872124373913
2023-01-21 09:53:37.764761: step: 448/530, loss: 0.12180376797914505
2023-01-21 09:53:38.906145: step: 452/530, loss: 0.14681577682495117
2023-01-21 09:53:40.008447: step: 456/530, loss: 0.0652797669172287
2023-01-21 09:53:41.153889: step: 460/530, loss: 0.03833465650677681
2023-01-21 09:53:42.282639: step: 464/530, loss: 0.06378021836280823
2023-01-21 09:53:43.395933: step: 468/530, loss: 0.03038034401834011
2023-01-21 09:53:44.526955: step: 472/530, loss: 0.06567096710205078
2023-01-21 09:53:45.654065: step: 476/530, loss: 0.07855186611413956
2023-01-21 09:53:46.794597: step: 480/530, loss: 0.18243679404258728
2023-01-21 09:53:47.915938: step: 484/530, loss: 0.1372160017490387
2023-01-21 09:53:49.042647: step: 488/530, loss: 0.11994900554418564
2023-01-21 09:53:50.190199: step: 492/530, loss: 0.15050125122070312
2023-01-21 09:53:51.322717: step: 496/530, loss: 0.11551618576049805
2023-01-21 09:53:52.460640: step: 500/530, loss: 0.04369340091943741
2023-01-21 09:53:53.579825: step: 504/530, loss: 0.06640468537807465
2023-01-21 09:53:54.699687: step: 508/530, loss: 0.007361006923019886
2023-01-21 09:53:55.834333: step: 512/530, loss: 0.048218343406915665
2023-01-21 09:53:56.936602: step: 516/530, loss: 0.060860682278871536
2023-01-21 09:53:58.091941: step: 520/530, loss: 0.08113536983728409
2023-01-21 09:53:59.231164: step: 524/530, loss: 0.14440375566482544
2023-01-21 09:54:00.362772: step: 528/530, loss: 0.022012807428836823
2023-01-21 09:54:01.490174: step: 532/530, loss: 0.14495879411697388
2023-01-21 09:54:02.604048: step: 536/530, loss: 0.0418274886906147
2023-01-21 09:54:03.725220: step: 540/530, loss: 0.09153890609741211
2023-01-21 09:54:04.856449: step: 544/530, loss: 0.13710197806358337
2023-01-21 09:54:05.962486: step: 548/530, loss: 0.04768846184015274
2023-01-21 09:54:07.101882: step: 552/530, loss: 0.0736326202750206
2023-01-21 09:54:08.228030: step: 556/530, loss: 1.2957487106323242
2023-01-21 09:54:09.345422: step: 560/530, loss: 0.042452335357666016
2023-01-21 09:54:10.490060: step: 564/530, loss: 0.08253307640552521
2023-01-21 09:54:11.611515: step: 568/530, loss: 0.1243891716003418
2023-01-21 09:54:12.728207: step: 572/530, loss: 0.08163681626319885
2023-01-21 09:54:13.863168: step: 576/530, loss: 0.02335796318948269
2023-01-21 09:54:15.007291: step: 580/530, loss: 0.06467590481042862
2023-01-21 09:54:16.126794: step: 584/530, loss: 0.05988512188196182
2023-01-21 09:54:17.237835: step: 588/530, loss: 0.09767093509435654
2023-01-21 09:54:18.356867: step: 592/530, loss: 0.1100701317191124
2023-01-21 09:54:19.458113: step: 596/530, loss: 0.29908645153045654
2023-01-21 09:54:20.605534: step: 600/530, loss: 0.015368079766631126
2023-01-21 09:54:21.719000: step: 604/530, loss: 0.08268795162439346
2023-01-21 09:54:22.843978: step: 608/530, loss: 0.018003465607762337
2023-01-21 09:54:23.976369: step: 612/530, loss: 0.08078031986951828
2023-01-21 09:54:25.109588: step: 616/530, loss: 0.027094364166259766
2023-01-21 09:54:26.230321: step: 620/530, loss: 0.04923610761761665
2023-01-21 09:54:27.339674: step: 624/530, loss: 0.07506600022315979
2023-01-21 09:54:28.451068: step: 628/530, loss: 0.024556400254368782
2023-01-21 09:54:29.552762: step: 632/530, loss: 0.05791368708014488
2023-01-21 09:54:30.673367: step: 636/530, loss: 0.08215484768152237
2023-01-21 09:54:31.802752: step: 640/530, loss: 0.041934773325920105
2023-01-21 09:54:32.929140: step: 644/530, loss: 0.05976295471191406
2023-01-21 09:54:34.067102: step: 648/530, loss: 0.32400768995285034
2023-01-21 09:54:35.208059: step: 652/530, loss: 0.03439519554376602
2023-01-21 09:54:36.332289: step: 656/530, loss: 0.2925798296928406
2023-01-21 09:54:37.454627: step: 660/530, loss: 0.027838896960020065
2023-01-21 09:54:38.569716: step: 664/530, loss: 0.07512311637401581
2023-01-21 09:54:39.689926: step: 668/530, loss: 0.09839363396167755
2023-01-21 09:54:40.819249: step: 672/530, loss: 0.07456064224243164
2023-01-21 09:54:41.973632: step: 676/530, loss: 0.035246849060058594
2023-01-21 09:54:43.086037: step: 680/530, loss: 0.07092466950416565
2023-01-21 09:54:44.197119: step: 684/530, loss: 0.2112814038991928
2023-01-21 09:54:45.325114: step: 688/530, loss: 0.05242948234081268
2023-01-21 09:54:46.469160: step: 692/530, loss: 0.07309255748987198
2023-01-21 09:54:47.580099: step: 696/530, loss: 0.07162085175514221
2023-01-21 09:54:48.709000: step: 700/530, loss: 0.06522292643785477
2023-01-21 09:54:49.851762: step: 704/530, loss: 0.09814925491809845
2023-01-21 09:54:50.968734: step: 708/530, loss: 0.16781044006347656
2023-01-21 09:54:52.082214: step: 712/530, loss: 0.055739592760801315
2023-01-21 09:54:53.163038: step: 716/530, loss: 0.04203863441944122
2023-01-21 09:54:54.314448: step: 720/530, loss: 0.05915536731481552
2023-01-21 09:54:55.455214: step: 724/530, loss: 0.19279813766479492
2023-01-21 09:54:56.596695: step: 728/530, loss: 0.34922534227371216
2023-01-21 09:54:57.754011: step: 732/530, loss: 0.1728130280971527
2023-01-21 09:54:58.896332: step: 736/530, loss: 0.12764176726341248
2023-01-21 09:55:00.029202: step: 740/530, loss: 0.20023518800735474
2023-01-21 09:55:01.195715: step: 744/530, loss: 0.019550751894712448
2023-01-21 09:55:02.319047: step: 748/530, loss: 0.4400915205478668
2023-01-21 09:55:03.448936: step: 752/530, loss: 0.23120427131652832
2023-01-21 09:55:04.558937: step: 756/530, loss: 0.019921613857150078
2023-01-21 09:55:05.659244: step: 760/530, loss: 0.06383663415908813
2023-01-21 09:55:06.813601: step: 764/530, loss: 0.08591480553150177
2023-01-21 09:55:07.942946: step: 768/530, loss: 0.13027562201023102
2023-01-21 09:55:09.064234: step: 772/530, loss: 0.07488145679235458
2023-01-21 09:55:10.168055: step: 776/530, loss: 0.044815681874752045
2023-01-21 09:55:11.318877: step: 780/530, loss: 0.11078119277954102
2023-01-21 09:55:12.428197: step: 784/530, loss: 0.12994547188282013
2023-01-21 09:55:13.549706: step: 788/530, loss: 0.08993014693260193
2023-01-21 09:55:14.657745: step: 792/530, loss: 0.21433153748512268
2023-01-21 09:55:15.764553: step: 796/530, loss: 0.014615010470151901
2023-01-21 09:55:16.919146: step: 800/530, loss: 0.019059086218476295
2023-01-21 09:55:18.020060: step: 804/530, loss: 0.09029875695705414
2023-01-21 09:55:19.149776: step: 808/530, loss: 0.032218173146247864
2023-01-21 09:55:20.281257: step: 812/530, loss: 0.03984851762652397
2023-01-21 09:55:21.407988: step: 816/530, loss: 0.127696231007576
2023-01-21 09:55:22.524996: step: 820/530, loss: 0.06995301693677902
2023-01-21 09:55:23.643026: step: 824/530, loss: 0.10436270385980606
2023-01-21 09:55:24.776535: step: 828/530, loss: 0.12582284212112427
2023-01-21 09:55:25.907941: step: 832/530, loss: 0.025069715455174446
2023-01-21 09:55:27.025234: step: 836/530, loss: 0.01713085174560547
2023-01-21 09:55:28.138100: step: 840/530, loss: 0.03806161880493164
2023-01-21 09:55:29.246023: step: 844/530, loss: 0.022437002509832382
2023-01-21 09:55:30.408601: step: 848/530, loss: 0.1250888854265213
2023-01-21 09:55:31.548186: step: 852/530, loss: 0.028609706088900566
2023-01-21 09:55:32.689379: step: 856/530, loss: 0.029798317700624466
2023-01-21 09:55:33.776662: step: 860/530, loss: 0.08777026832103729
2023-01-21 09:55:34.929462: step: 864/530, loss: 0.20468302071094513
2023-01-21 09:55:36.036456: step: 868/530, loss: 0.03855018690228462
2023-01-21 09:55:37.171416: step: 872/530, loss: 0.08856801688671112
2023-01-21 09:55:38.297547: step: 876/530, loss: 0.023838140070438385
2023-01-21 09:55:39.403604: step: 880/530, loss: 0.29989421367645264
2023-01-21 09:55:40.506404: step: 884/530, loss: 0.41837263107299805
2023-01-21 09:55:41.643383: step: 888/530, loss: 0.16151557862758636
2023-01-21 09:55:42.790837: step: 892/530, loss: 0.05406970903277397
2023-01-21 09:55:43.933603: step: 896/530, loss: 0.5375280380249023
2023-01-21 09:55:45.058740: step: 900/530, loss: 0.34047988057136536
2023-01-21 09:55:46.191982: step: 904/530, loss: 0.03292236477136612
2023-01-21 09:55:47.314205: step: 908/530, loss: 0.09112946689128876
2023-01-21 09:55:48.433728: step: 912/530, loss: 0.1620519608259201
2023-01-21 09:55:49.580825: step: 916/530, loss: 0.04178342968225479
2023-01-21 09:55:50.712315: step: 920/530, loss: 0.01404571533203125
2023-01-21 09:55:51.825573: step: 924/530, loss: 3.9763343334198
2023-01-21 09:55:52.963505: step: 928/530, loss: 0.035802461206912994
2023-01-21 09:55:54.109880: step: 932/530, loss: 0.26478224992752075
2023-01-21 09:55:55.231497: step: 936/530, loss: 0.03883552551269531
2023-01-21 09:55:56.368379: step: 940/530, loss: 0.0029333115089684725
2023-01-21 09:55:57.491832: step: 944/530, loss: 0.3648069500923157
2023-01-21 09:55:58.650286: step: 948/530, loss: 0.08199644088745117
2023-01-21 09:55:59.771731: step: 952/530, loss: 0.19840264320373535
2023-01-21 09:56:00.942084: step: 956/530, loss: 0.16729974746704102
2023-01-21 09:56:02.109385: step: 960/530, loss: 0.05994696915149689
2023-01-21 09:56:03.213344: step: 964/530, loss: 0.07341411709785461
2023-01-21 09:56:04.342569: step: 968/530, loss: 0.08187513053417206
2023-01-21 09:56:05.455701: step: 972/530, loss: 0.049796007573604584
2023-01-21 09:56:06.585757: step: 976/530, loss: 0.09649428725242615
2023-01-21 09:56:07.736744: step: 980/530, loss: 0.07598339766263962
2023-01-21 09:56:08.872628: step: 984/530, loss: 0.07876968383789062
2023-01-21 09:56:09.981572: step: 988/530, loss: 0.030896425247192383
2023-01-21 09:56:11.094010: step: 992/530, loss: 0.05377402529120445
2023-01-21 09:56:12.226020: step: 996/530, loss: 0.0895547866821289
2023-01-21 09:56:13.364240: step: 1000/530, loss: 0.046038150787353516
2023-01-21 09:56:14.556989: step: 1004/530, loss: 0.07872681319713593
2023-01-21 09:56:15.643865: step: 1008/530, loss: 0.09826698154211044
2023-01-21 09:56:16.773559: step: 1012/530, loss: 0.0428282730281353
2023-01-21 09:56:17.876528: step: 1016/530, loss: 0.6448582410812378
2023-01-21 09:56:19.002323: step: 1020/530, loss: 0.046166516840457916
2023-01-21 09:56:20.142956: step: 1024/530, loss: 0.19410762190818787
2023-01-21 09:56:21.353572: step: 1028/530, loss: 0.11003265529870987
2023-01-21 09:56:22.502525: step: 1032/530, loss: 0.1165589839220047
2023-01-21 09:56:23.627888: step: 1036/530, loss: 0.02948169782757759
2023-01-21 09:56:24.718624: step: 1040/530, loss: 0.3134117126464844
2023-01-21 09:56:25.862735: step: 1044/530, loss: 0.5719877481460571
2023-01-21 09:56:26.949062: step: 1048/530, loss: 0.11576595157384872
2023-01-21 09:56:28.066693: step: 1052/530, loss: 0.0035792351700365543
2023-01-21 09:56:29.191466: step: 1056/530, loss: 0.05913562700152397
2023-01-21 09:56:30.340422: step: 1060/530, loss: 0.06444358825683594
2023-01-21 09:56:31.443348: step: 1064/530, loss: 0.23844031989574432
2023-01-21 09:56:32.593658: step: 1068/530, loss: 0.1456901580095291
2023-01-21 09:56:33.720466: step: 1072/530, loss: 0.01520471554249525
2023-01-21 09:56:34.887791: step: 1076/530, loss: 0.09892044216394424
2023-01-21 09:56:36.014811: step: 1080/530, loss: 0.14753571152687073
2023-01-21 09:56:37.168031: step: 1084/530, loss: 0.0640416145324707
2023-01-21 09:56:38.304073: step: 1088/530, loss: 0.04655437543988228
2023-01-21 09:56:39.430934: step: 1092/530, loss: 0.04622550308704376
2023-01-21 09:56:40.581348: step: 1096/530, loss: 0.2176496684551239
2023-01-21 09:56:41.722848: step: 1100/530, loss: 0.06824783980846405
2023-01-21 09:56:42.832718: step: 1104/530, loss: 0.179981529712677
2023-01-21 09:56:43.953475: step: 1108/530, loss: 0.03285665810108185
2023-01-21 09:56:45.096945: step: 1112/530, loss: 0.03740978240966797
2023-01-21 09:56:46.221509: step: 1116/530, loss: 0.04311180114746094
2023-01-21 09:56:47.345071: step: 1120/530, loss: 0.08397160470485687
2023-01-21 09:56:48.454555: step: 1124/530, loss: 0.1097785085439682
2023-01-21 09:56:49.568258: step: 1128/530, loss: 0.06077098846435547
2023-01-21 09:56:50.681973: step: 1132/530, loss: 0.13154879212379456
2023-01-21 09:56:51.838436: step: 1136/530, loss: 0.11111602932214737
2023-01-21 09:56:52.959657: step: 1140/530, loss: 0.032245635986328125
2023-01-21 09:56:54.103974: step: 1144/530, loss: 0.08708296716213226
2023-01-21 09:56:55.252880: step: 1148/530, loss: 0.08207712322473526
2023-01-21 09:56:56.359573: step: 1152/530, loss: 0.08362355828285217
2023-01-21 09:56:57.482883: step: 1156/530, loss: 0.13088122010231018
2023-01-21 09:56:58.604173: step: 1160/530, loss: 0.4110361933708191
2023-01-21 09:56:59.755015: step: 1164/530, loss: 0.11537876725196838
2023-01-21 09:57:00.863275: step: 1168/530, loss: 0.04328203201293945
2023-01-21 09:57:01.968672: step: 1172/530, loss: 0.0701117068529129
2023-01-21 09:57:03.118310: step: 1176/530, loss: 0.1302386373281479
2023-01-21 09:57:04.240049: step: 1180/530, loss: 0.04262809827923775
2023-01-21 09:57:05.358922: step: 1184/530, loss: 0.010998058132827282
2023-01-21 09:57:06.477222: step: 1188/530, loss: 0.07971601188182831
2023-01-21 09:57:07.590103: step: 1192/530, loss: 0.00440636882558465
2023-01-21 09:57:08.723410: step: 1196/530, loss: 0.1615658700466156
2023-01-21 09:57:09.840540: step: 1200/530, loss: 0.10765416920185089
2023-01-21 09:57:10.946454: step: 1204/530, loss: 0.12520912289619446
2023-01-21 09:57:12.060393: step: 1208/530, loss: 0.08215294033288956
2023-01-21 09:57:13.156673: step: 1212/530, loss: 0.03524074703454971
2023-01-21 09:57:14.314854: step: 1216/530, loss: 0.023448754101991653
2023-01-21 09:57:15.432207: step: 1220/530, loss: 0.02454409748315811
2023-01-21 09:57:16.547778: step: 1224/530, loss: 0.0606236457824707
2023-01-21 09:57:17.681590: step: 1228/530, loss: 0.03665647655725479
2023-01-21 09:57:18.799957: step: 1232/530, loss: 0.018143273890018463
2023-01-21 09:57:19.879663: step: 1236/530, loss: 0.1944512277841568
2023-01-21 09:57:21.041234: step: 1240/530, loss: 0.0617918036878109
2023-01-21 09:57:22.242827: step: 1244/530, loss: 0.03439726680517197
2023-01-21 09:57:23.363478: step: 1248/530, loss: 0.2308807373046875
2023-01-21 09:57:24.485779: step: 1252/530, loss: 0.0649634376168251
2023-01-21 09:57:25.627853: step: 1256/530, loss: 0.10017891228199005
2023-01-21 09:57:26.755850: step: 1260/530, loss: 0.11726336181163788
2023-01-21 09:57:27.905400: step: 1264/530, loss: 0.10373449325561523
2023-01-21 09:57:29.014700: step: 1268/530, loss: 0.017322350293397903
2023-01-21 09:57:30.140743: step: 1272/530, loss: 0.11629681289196014
2023-01-21 09:57:31.257577: step: 1276/530, loss: 0.020702313631772995
2023-01-21 09:57:32.391450: step: 1280/530, loss: 0.05313124507665634
2023-01-21 09:57:33.485438: step: 1284/530, loss: 0.6437771320343018
2023-01-21 09:57:34.622622: step: 1288/530, loss: 0.07526913285255432
2023-01-21 09:57:35.756786: step: 1292/530, loss: 0.013522911816835403
2023-01-21 09:57:36.890571: step: 1296/530, loss: 0.06642293930053711
2023-01-21 09:57:38.002699: step: 1300/530, loss: 0.034535981714725494
2023-01-21 09:57:39.106589: step: 1304/530, loss: 0.006374877877533436
2023-01-21 09:57:40.236675: step: 1308/530, loss: 1.2615207433700562
2023-01-21 09:57:41.341855: step: 1312/530, loss: 0.04376354068517685
2023-01-21 09:57:42.476113: step: 1316/530, loss: 0.048059988766908646
2023-01-21 09:57:43.614381: step: 1320/530, loss: 0.21942730247974396
2023-01-21 09:57:44.712064: step: 1324/530, loss: 0.10523892194032669
2023-01-21 09:57:45.832275: step: 1328/530, loss: 0.3994571566581726
2023-01-21 09:57:46.972425: step: 1332/530, loss: 0.06274890899658203
2023-01-21 09:57:48.081181: step: 1336/530, loss: 0.16639643907546997
2023-01-21 09:57:49.187826: step: 1340/530, loss: 0.0745050460100174
2023-01-21 09:57:50.340710: step: 1344/530, loss: 0.020218467339873314
2023-01-21 09:57:51.486336: step: 1348/530, loss: 0.06965980678796768
2023-01-21 09:57:52.641886: step: 1352/530, loss: 0.07142181694507599
2023-01-21 09:57:53.746225: step: 1356/530, loss: 0.05727948993444443
2023-01-21 09:57:54.865981: step: 1360/530, loss: 0.06587830185890198
2023-01-21 09:57:55.955922: step: 1364/530, loss: 0.1136774942278862
2023-01-21 09:57:57.053308: step: 1368/530, loss: 0.045653726905584335
2023-01-21 09:57:58.155463: step: 1372/530, loss: 0.039304353296756744
2023-01-21 09:57:59.254046: step: 1376/530, loss: 0.07658644020557404
2023-01-21 09:58:00.366504: step: 1380/530, loss: 0.018712997436523438
2023-01-21 09:58:01.485251: step: 1384/530, loss: 0.03401937335729599
2023-01-21 09:58:02.600752: step: 1388/530, loss: 0.11538667976856232
2023-01-21 09:58:03.715857: step: 1392/530, loss: 0.13676157593727112
2023-01-21 09:58:04.825902: step: 1396/530, loss: 0.15297982096672058
2023-01-21 09:58:05.940160: step: 1400/530, loss: 0.018097544088959694
2023-01-21 09:58:07.072567: step: 1404/530, loss: 0.0774068832397461
2023-01-21 09:58:08.198761: step: 1408/530, loss: 0.07601775974035263
2023-01-21 09:58:09.334416: step: 1412/530, loss: 0.19643695652484894
2023-01-21 09:58:10.467353: step: 1416/530, loss: 0.0519014336168766
2023-01-21 09:58:11.593359: step: 1420/530, loss: 0.03080177493393421
2023-01-21 09:58:12.675653: step: 1424/530, loss: 0.0715765729546547
2023-01-21 09:58:13.792580: step: 1428/530, loss: 0.06904315948486328
2023-01-21 09:58:14.885959: step: 1432/530, loss: 0.03958840295672417
2023-01-21 09:58:16.026719: step: 1436/530, loss: 0.04114561155438423
2023-01-21 09:58:17.149430: step: 1440/530, loss: 0.06859956681728363
2023-01-21 09:58:18.298248: step: 1444/530, loss: 0.042545415461063385
2023-01-21 09:58:19.413611: step: 1448/530, loss: 0.06447849422693253
2023-01-21 09:58:20.544731: step: 1452/530, loss: 0.14115557074546814
2023-01-21 09:58:21.657122: step: 1456/530, loss: 0.15271377563476562
2023-01-21 09:58:22.818097: step: 1460/530, loss: 0.09959983825683594
2023-01-21 09:58:23.984032: step: 1464/530, loss: 0.05774059519171715
2023-01-21 09:58:25.163434: step: 1468/530, loss: 0.8459482192993164
2023-01-21 09:58:26.268197: step: 1472/530, loss: 0.1214621514081955
2023-01-21 09:58:27.396455: step: 1476/530, loss: 0.17651471495628357
2023-01-21 09:58:28.516157: step: 1480/530, loss: 0.036165524274110794
2023-01-21 09:58:29.621516: step: 1484/530, loss: 0.027136903256177902
2023-01-21 09:58:30.716360: step: 1488/530, loss: 0.02073807641863823
2023-01-21 09:58:31.826484: step: 1492/530, loss: 0.07076302915811539
2023-01-21 09:58:32.957731: step: 1496/530, loss: 0.03808724880218506
2023-01-21 09:58:34.051451: step: 1500/530, loss: 0.5862589478492737
2023-01-21 09:58:35.165933: step: 1504/530, loss: 0.04045257717370987
2023-01-21 09:58:36.271624: step: 1508/530, loss: 0.05408668518066406
2023-01-21 09:58:37.388213: step: 1512/530, loss: 0.8601412773132324
2023-01-21 09:58:38.504073: step: 1516/530, loss: 0.2603822648525238
2023-01-21 09:58:39.625492: step: 1520/530, loss: 0.1986106038093567
2023-01-21 09:58:40.748253: step: 1524/530, loss: 0.0456884391605854
2023-01-21 09:58:41.870413: step: 1528/530, loss: 0.07586565613746643
2023-01-21 09:58:42.965606: step: 1532/530, loss: 0.2109348326921463
2023-01-21 09:58:44.100566: step: 1536/530, loss: 0.2524593472480774
2023-01-21 09:58:45.266936: step: 1540/530, loss: 0.09041347354650497
2023-01-21 09:58:46.386813: step: 1544/530, loss: 0.027682732790708542
2023-01-21 09:58:47.532657: step: 1548/530, loss: 0.04460182413458824
2023-01-21 09:58:48.631824: step: 1552/530, loss: 0.06576766818761826
2023-01-21 09:58:49.734162: step: 1556/530, loss: 0.04151410982012749
2023-01-21 09:58:50.905525: step: 1560/530, loss: 0.03367156907916069
2023-01-21 09:58:52.021717: step: 1564/530, loss: 0.0012005805037915707
2023-01-21 09:58:53.137004: step: 1568/530, loss: 0.020243704319000244
2023-01-21 09:58:54.256717: step: 1572/530, loss: 0.07041990756988525
2023-01-21 09:58:55.373330: step: 1576/530, loss: 0.0623898059129715
2023-01-21 09:58:56.504372: step: 1580/530, loss: 0.08070193231105804
2023-01-21 09:58:57.621652: step: 1584/530, loss: 0.08670344948768616
2023-01-21 09:58:58.756724: step: 1588/530, loss: 0.09154634922742844
2023-01-21 09:58:59.862728: step: 1592/530, loss: 0.011732817627489567
2023-01-21 09:59:00.988139: step: 1596/530, loss: 0.08833663165569305
2023-01-21 09:59:02.154333: step: 1600/530, loss: 0.11914139986038208
2023-01-21 09:59:03.276335: step: 1604/530, loss: 0.09477101266384125
2023-01-21 09:59:04.392014: step: 1608/530, loss: 0.23316669464111328
2023-01-21 09:59:05.526928: step: 1612/530, loss: 0.03017454221844673
2023-01-21 09:59:06.650430: step: 1616/530, loss: 0.14386683702468872
2023-01-21 09:59:07.776965: step: 1620/530, loss: 0.08940906822681427
2023-01-21 09:59:08.907230: step: 1624/530, loss: 0.02055530622601509
2023-01-21 09:59:10.035042: step: 1628/530, loss: 0.10598006844520569
2023-01-21 09:59:11.150641: step: 1632/530, loss: 0.04440479353070259
2023-01-21 09:59:12.280714: step: 1636/530, loss: 0.09307155758142471
2023-01-21 09:59:13.419076: step: 1640/530, loss: 0.11901766061782837
2023-01-21 09:59:14.561972: step: 1644/530, loss: 0.09626798331737518
2023-01-21 09:59:15.690358: step: 1648/530, loss: 0.0802789255976677
2023-01-21 09:59:16.802553: step: 1652/530, loss: 0.2961452305316925
2023-01-21 09:59:17.935051: step: 1656/530, loss: 0.09225402027368546
2023-01-21 09:59:19.072171: step: 1660/530, loss: 0.12265992164611816
2023-01-21 09:59:20.204403: step: 1664/530, loss: 0.0021490096114575863
2023-01-21 09:59:21.320980: step: 1668/530, loss: 0.09488850086927414
2023-01-21 09:59:22.420544: step: 1672/530, loss: 0.07696390151977539
2023-01-21 09:59:23.546191: step: 1676/530, loss: 0.07524547725915909
2023-01-21 09:59:24.698225: step: 1680/530, loss: 0.04918060451745987
2023-01-21 09:59:25.843540: step: 1684/530, loss: 0.012505482882261276
2023-01-21 09:59:26.961479: step: 1688/530, loss: 0.04604711756110191
2023-01-21 09:59:28.073937: step: 1692/530, loss: 0.051996562629938126
2023-01-21 09:59:29.214288: step: 1696/530, loss: 0.01409225445240736
2023-01-21 09:59:30.349015: step: 1700/530, loss: 0.060300350189208984
2023-01-21 09:59:31.480203: step: 1704/530, loss: 0.18855877220630646
2023-01-21 09:59:32.592523: step: 1708/530, loss: 0.11008048057556152
2023-01-21 09:59:33.713443: step: 1712/530, loss: 0.04119386896491051
2023-01-21 09:59:34.835496: step: 1716/530, loss: 0.06107797846198082
2023-01-21 09:59:35.934574: step: 1720/530, loss: 0.27596521377563477
2023-01-21 09:59:37.034765: step: 1724/530, loss: 0.08460140228271484
2023-01-21 09:59:38.158613: step: 1728/530, loss: 0.11772172898054123
2023-01-21 09:59:39.307340: step: 1732/530, loss: 0.014800453558564186
2023-01-21 09:59:40.432010: step: 1736/530, loss: 0.02242593839764595
2023-01-21 09:59:41.570556: step: 1740/530, loss: 0.15692806243896484
2023-01-21 09:59:42.705353: step: 1744/530, loss: 0.06582526862621307
2023-01-21 09:59:43.811806: step: 1748/530, loss: 0.04527602344751358
2023-01-21 09:59:44.970965: step: 1752/530, loss: 0.07914133369922638
2023-01-21 09:59:46.089992: step: 1756/530, loss: 0.13442236185073853
2023-01-21 09:59:47.226705: step: 1760/530, loss: 0.5814440846443176
2023-01-21 09:59:48.332444: step: 1764/530, loss: 0.34597188234329224
2023-01-21 09:59:49.461795: step: 1768/530, loss: 0.5466675758361816
2023-01-21 09:59:50.563524: step: 1772/530, loss: 0.03274974972009659
2023-01-21 09:59:51.699769: step: 1776/530, loss: 0.10324878245592117
2023-01-21 09:59:52.824969: step: 1780/530, loss: 0.25266528129577637
2023-01-21 09:59:53.966157: step: 1784/530, loss: 0.04500222206115723
2023-01-21 09:59:55.108556: step: 1788/530, loss: 0.1351356953382492
2023-01-21 09:59:56.229844: step: 1792/530, loss: 0.031963445246219635
2023-01-21 09:59:57.349248: step: 1796/530, loss: 0.40441760420799255
2023-01-21 09:59:58.472545: step: 1800/530, loss: 0.2764412462711334
2023-01-21 09:59:59.608078: step: 1804/530, loss: 0.0966092124581337
2023-01-21 10:00:00.741841: step: 1808/530, loss: 0.048938751220703125
2023-01-21 10:00:01.852832: step: 1812/530, loss: 0.14263038337230682
2023-01-21 10:00:02.983669: step: 1816/530, loss: 0.08984461426734924
2023-01-21 10:00:04.090786: step: 1820/530, loss: 0.1023816168308258
2023-01-21 10:00:05.222419: step: 1824/530, loss: 0.050203923135995865
2023-01-21 10:00:06.361864: step: 1828/530, loss: 0.22512884438037872
2023-01-21 10:00:07.487820: step: 1832/530, loss: 0.2169717401266098
2023-01-21 10:00:08.613313: step: 1836/530, loss: 0.10818032920360565
2023-01-21 10:00:09.728257: step: 1840/530, loss: 0.013808537274599075
2023-01-21 10:00:10.866661: step: 1844/530, loss: 0.08203835785388947
2023-01-21 10:00:11.993020: step: 1848/530, loss: 0.09792857617139816
2023-01-21 10:00:13.121545: step: 1852/530, loss: 0.1966841220855713
2023-01-21 10:00:14.255739: step: 1856/530, loss: 0.05021515116095543
2023-01-21 10:00:15.372239: step: 1860/530, loss: 0.13389775156974792
2023-01-21 10:00:16.507541: step: 1864/530, loss: 0.16585904359817505
2023-01-21 10:00:17.607171: step: 1868/530, loss: 0.3613828420639038
2023-01-21 10:00:18.743596: step: 1872/530, loss: 0.08053598552942276
2023-01-21 10:00:19.849038: step: 1876/530, loss: 0.04160032421350479
2023-01-21 10:00:20.985198: step: 1880/530, loss: 0.041875626891851425
2023-01-21 10:00:22.107118: step: 1884/530, loss: 0.11476331204175949
2023-01-21 10:00:23.214462: step: 1888/530, loss: 0.10922642052173615
2023-01-21 10:00:24.320352: step: 1892/530, loss: 0.05841970443725586
2023-01-21 10:00:25.478958: step: 1896/530, loss: 0.05351386219263077
2023-01-21 10:00:26.636358: step: 1900/530, loss: 0.024054670706391335
2023-01-21 10:00:27.737479: step: 1904/530, loss: 0.06838121265172958
2023-01-21 10:00:28.858363: step: 1908/530, loss: 0.11356105655431747
2023-01-21 10:00:29.975284: step: 1912/530, loss: 0.03153543546795845
2023-01-21 10:00:31.108072: step: 1916/530, loss: 0.016533851623535156
2023-01-21 10:00:32.222079: step: 1920/530, loss: 0.056430913507938385
2023-01-21 10:00:33.364839: step: 1924/530, loss: 0.1042516678571701
2023-01-21 10:00:34.483636: step: 1928/530, loss: 0.09258913993835449
2023-01-21 10:00:35.582840: step: 1932/530, loss: 0.09291648864746094
2023-01-21 10:00:36.712936: step: 1936/530, loss: 0.049272727221250534
2023-01-21 10:00:37.835505: step: 1940/530, loss: 0.0884493887424469
2023-01-21 10:00:38.954564: step: 1944/530, loss: 0.14059877395629883
2023-01-21 10:00:40.086559: step: 1948/530, loss: 0.21385231614112854
2023-01-21 10:00:41.219463: step: 1952/530, loss: 0.11460743099451065
2023-01-21 10:00:42.324192: step: 1956/530, loss: 0.43515080213546753
2023-01-21 10:00:43.433892: step: 1960/530, loss: 0.07509736716747284
2023-01-21 10:00:44.557708: step: 1964/530, loss: 0.14917536079883575
2023-01-21 10:00:45.686706: step: 1968/530, loss: 0.08783073723316193
2023-01-21 10:00:46.825462: step: 1972/530, loss: 0.06715182960033417
2023-01-21 10:00:47.939977: step: 1976/530, loss: 0.3167229890823364
2023-01-21 10:00:49.086650: step: 1980/530, loss: 0.022747136652469635
2023-01-21 10:00:50.211700: step: 1984/530, loss: 0.014326667413115501
2023-01-21 10:00:51.351195: step: 1988/530, loss: 0.07179916650056839
2023-01-21 10:00:52.479327: step: 1992/530, loss: 0.06716380268335342
2023-01-21 10:00:53.647707: step: 1996/530, loss: 0.16477961838245392
2023-01-21 10:00:54.802830: step: 2000/530, loss: 0.033688828349113464
2023-01-21 10:00:55.945132: step: 2004/530, loss: 0.2741049826145172
2023-01-21 10:00:57.071125: step: 2008/530, loss: 0.09658517688512802
2023-01-21 10:00:58.176383: step: 2012/530, loss: 0.9274341464042664
2023-01-21 10:00:59.294422: step: 2016/530, loss: 0.004947471432387829
2023-01-21 10:01:00.403743: step: 2020/530, loss: 0.057419776916503906
2023-01-21 10:01:01.507083: step: 2024/530, loss: 0.01900796964764595
2023-01-21 10:01:02.613825: step: 2028/530, loss: 0.16491250693798065
2023-01-21 10:01:03.732393: step: 2032/530, loss: 0.09365349262952805
2023-01-21 10:01:04.858093: step: 2036/530, loss: 0.046285200864076614
2023-01-21 10:01:06.012462: step: 2040/530, loss: 0.06361713260412216
2023-01-21 10:01:07.143763: step: 2044/530, loss: 0.06339231133460999
2023-01-21 10:01:08.307490: step: 2048/530, loss: 0.10045404732227325
2023-01-21 10:01:09.429911: step: 2052/530, loss: 0.051396798342466354
2023-01-21 10:01:10.574319: step: 2056/530, loss: 0.09863011538982391
2023-01-21 10:01:11.733342: step: 2060/530, loss: 0.8275082111358643
2023-01-21 10:01:12.887130: step: 2064/530, loss: 0.11857318878173828
2023-01-21 10:01:14.010802: step: 2068/530, loss: 0.09697838127613068
2023-01-21 10:01:15.137692: step: 2072/530, loss: 0.1563989222049713
2023-01-21 10:01:16.270609: step: 2076/530, loss: 0.10821013152599335
2023-01-21 10:01:17.359804: step: 2080/530, loss: 0.049179743975400925
2023-01-21 10:01:18.489405: step: 2084/530, loss: 0.0793735533952713
2023-01-21 10:01:19.625500: step: 2088/530, loss: 0.011032676324248314
2023-01-21 10:01:20.741011: step: 2092/530, loss: 0.19795528054237366
2023-01-21 10:01:21.854555: step: 2096/530, loss: 0.08164076507091522
2023-01-21 10:01:22.978830: step: 2100/530, loss: 0.058263204991817474
2023-01-21 10:01:24.097559: step: 2104/530, loss: 0.013590408489108086
2023-01-21 10:01:25.208738: step: 2108/530, loss: 0.05726051330566406
2023-01-21 10:01:26.378312: step: 2112/530, loss: 0.5535554885864258
2023-01-21 10:01:27.497540: step: 2116/530, loss: 0.010237693786621094
2023-01-21 10:01:28.613666: step: 2120/530, loss: 0.1349318027496338
==================================================
Loss: 0.126
--------------------
Dev: {'event': {'p': 0.5679611650485437, 'r': 0.7789613848202397, 'f1': 0.656934306569343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.609845031905196, 'r': 0.7645714285714286, 'f1': 0.6784989858012171}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.5967741935483871, 'r': 0.5873015873015873, 'f1': 0.592}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.34782608695652173, 'r': 0.4444444444444444, 'f1': 0.3902439024390244}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:02:09.141807: step: 4/530, loss: 0.0790146216750145
2023-01-21 10:02:10.251227: step: 8/530, loss: 0.3121567368507385
2023-01-21 10:02:11.389708: step: 12/530, loss: 0.005270957946777344
2023-01-21 10:02:12.514033: step: 16/530, loss: 0.10345049202442169
2023-01-21 10:02:13.613944: step: 20/530, loss: 0.026897288858890533
2023-01-21 10:02:14.781787: step: 24/530, loss: 0.06734971702098846
2023-01-21 10:02:15.926040: step: 28/530, loss: 0.028751563280820847
2023-01-21 10:02:17.053076: step: 32/530, loss: 0.019435979425907135
2023-01-21 10:02:18.153425: step: 36/530, loss: 0.02271575853228569
2023-01-21 10:02:19.270122: step: 40/530, loss: 0.10955947637557983
2023-01-21 10:02:20.396331: step: 44/530, loss: 0.06370868533849716
2023-01-21 10:02:21.536263: step: 48/530, loss: 0.05016279220581055
2023-01-21 10:02:22.651741: step: 52/530, loss: 0.026475906372070312
2023-01-21 10:02:23.787979: step: 56/530, loss: 0.08268547058105469
2023-01-21 10:02:24.905216: step: 60/530, loss: 0.10631771385669708
2023-01-21 10:02:26.021112: step: 64/530, loss: 0.062207892537117004
2023-01-21 10:02:27.129841: step: 68/530, loss: 0.05992469936609268
2023-01-21 10:02:28.256696: step: 72/530, loss: 0.044905029237270355
2023-01-21 10:02:29.366776: step: 76/530, loss: 0.018973970785737038
2023-01-21 10:02:30.472640: step: 80/530, loss: 0.03886954486370087
2023-01-21 10:02:31.594867: step: 84/530, loss: 0.05941829830408096
2023-01-21 10:02:32.699580: step: 88/530, loss: 0.23195838928222656
2023-01-21 10:02:33.816112: step: 92/530, loss: 0.11491012573242188
2023-01-21 10:02:34.924041: step: 96/530, loss: 0.09214534610509872
2023-01-21 10:02:36.022366: step: 100/530, loss: 0.09660749137401581
2023-01-21 10:02:37.113773: step: 104/530, loss: 0.02130107954144478
2023-01-21 10:02:38.215109: step: 108/530, loss: 0.029286576434969902
2023-01-21 10:02:39.341776: step: 112/530, loss: 0.19082216918468475
2023-01-21 10:02:40.483256: step: 116/530, loss: 0.1164407730102539
2023-01-21 10:02:41.625741: step: 120/530, loss: 0.8564645648002625
2023-01-21 10:02:42.747912: step: 124/530, loss: 0.19386176764965057
2023-01-21 10:02:43.908403: step: 128/530, loss: 0.1229085922241211
2023-01-21 10:02:45.033525: step: 132/530, loss: 0.007953834719955921
2023-01-21 10:02:46.147276: step: 136/530, loss: 0.031861402094364166
2023-01-21 10:02:47.250581: step: 140/530, loss: 0.020019937306642532
2023-01-21 10:02:48.382554: step: 144/530, loss: 0.07812432199716568
2023-01-21 10:02:49.513276: step: 148/530, loss: 0.05324859917163849
2023-01-21 10:02:50.648599: step: 152/530, loss: 0.48522549867630005
2023-01-21 10:02:51.800870: step: 156/530, loss: 0.13192281126976013
2023-01-21 10:02:52.916907: step: 160/530, loss: 0.017609406262636185
2023-01-21 10:02:54.026191: step: 164/530, loss: 0.03794679790735245
2023-01-21 10:02:55.144162: step: 168/530, loss: 0.07091084122657776
2023-01-21 10:02:56.284773: step: 172/530, loss: 0.08146214485168457
2023-01-21 10:02:57.390636: step: 176/530, loss: 0.0790490135550499
2023-01-21 10:02:58.496516: step: 180/530, loss: 0.10353999584913254
2023-01-21 10:02:59.607175: step: 184/530, loss: 0.1889912188053131
2023-01-21 10:03:00.722674: step: 188/530, loss: 0.06240663677453995
2023-01-21 10:03:01.829545: step: 192/530, loss: 0.182064488530159
2023-01-21 10:03:02.945295: step: 196/530, loss: 0.042807579040527344
2023-01-21 10:03:04.093491: step: 200/530, loss: 0.16158857941627502
2023-01-21 10:03:05.221651: step: 204/530, loss: 0.053696535527706146
2023-01-21 10:03:06.346866: step: 208/530, loss: 0.2970302700996399
2023-01-21 10:03:07.469206: step: 212/530, loss: 0.027089547365903854
2023-01-21 10:03:08.606419: step: 216/530, loss: 0.15973377227783203
2023-01-21 10:03:09.707003: step: 220/530, loss: 0.2062583863735199
2023-01-21 10:03:10.833677: step: 224/530, loss: 0.07543697953224182
2023-01-21 10:03:11.983804: step: 228/530, loss: 0.057195283472537994
2023-01-21 10:03:13.118150: step: 232/530, loss: 0.11635017395019531
2023-01-21 10:03:14.278143: step: 236/530, loss: 0.7904821634292603
2023-01-21 10:03:15.400046: step: 240/530, loss: 0.1256381869316101
2023-01-21 10:03:16.523940: step: 244/530, loss: 0.14440707862377167
2023-01-21 10:03:17.642029: step: 248/530, loss: 0.049249935895204544
2023-01-21 10:03:18.769321: step: 252/530, loss: 0.0046364786103367805
2023-01-21 10:03:19.908573: step: 256/530, loss: 0.020391464233398438
2023-01-21 10:03:21.012195: step: 260/530, loss: 0.032820604741573334
2023-01-21 10:03:22.149426: step: 264/530, loss: 0.08701248466968536
2023-01-21 10:03:23.278249: step: 268/530, loss: 0.09363818168640137
2023-01-21 10:03:24.414779: step: 272/530, loss: 0.022823764011263847
2023-01-21 10:03:25.563989: step: 276/530, loss: 0.08607196807861328
2023-01-21 10:03:26.665352: step: 280/530, loss: 0.08581342548131943
2023-01-21 10:03:27.815535: step: 284/530, loss: 0.02920222282409668
2023-01-21 10:03:28.931777: step: 288/530, loss: 0.021055985242128372
2023-01-21 10:03:30.058522: step: 292/530, loss: 0.9731878638267517
2023-01-21 10:03:31.183716: step: 296/530, loss: 0.06904873996973038
2023-01-21 10:03:32.317686: step: 300/530, loss: 0.06195984035730362
2023-01-21 10:03:33.407299: step: 304/530, loss: 0.16180315613746643
2023-01-21 10:03:34.553806: step: 308/530, loss: 0.06663952022790909
2023-01-21 10:03:35.692568: step: 312/530, loss: 0.060877226293087006
2023-01-21 10:03:36.814021: step: 316/530, loss: 0.03636179119348526
2023-01-21 10:03:37.928298: step: 320/530, loss: 0.04690727964043617
2023-01-21 10:03:39.041685: step: 324/530, loss: 0.447091668844223
2023-01-21 10:03:40.188385: step: 328/530, loss: 0.10942287743091583
2023-01-21 10:03:41.338719: step: 332/530, loss: 0.06489335000514984
2023-01-21 10:03:42.446534: step: 336/530, loss: 0.07269497215747833
2023-01-21 10:03:43.552328: step: 340/530, loss: 0.2644649147987366
2023-01-21 10:03:44.674165: step: 344/530, loss: 0.10777568817138672
2023-01-21 10:03:45.811580: step: 348/530, loss: 0.026566505432128906
2023-01-21 10:03:46.907139: step: 352/530, loss: 0.034213267266750336
2023-01-21 10:03:48.037531: step: 356/530, loss: 0.4147357940673828
2023-01-21 10:03:49.148581: step: 360/530, loss: 0.07547035813331604
2023-01-21 10:03:50.279193: step: 364/530, loss: 0.3082072138786316
2023-01-21 10:03:51.411647: step: 368/530, loss: 0.5564893484115601
2023-01-21 10:03:52.531268: step: 372/530, loss: 0.06938190758228302
2023-01-21 10:03:53.654931: step: 376/530, loss: 0.05175306648015976
2023-01-21 10:03:54.781044: step: 380/530, loss: 0.06000519171357155
2023-01-21 10:03:55.900325: step: 384/530, loss: 0.34796857833862305
2023-01-21 10:03:57.000479: step: 388/530, loss: 0.0763828307390213
2023-01-21 10:03:58.105643: step: 392/530, loss: 0.016621733084321022
2023-01-21 10:03:59.203932: step: 396/530, loss: 0.12110351771116257
2023-01-21 10:04:00.327242: step: 400/530, loss: 0.06852512806653976
2023-01-21 10:04:01.475239: step: 404/530, loss: 0.03708639368414879
2023-01-21 10:04:02.590319: step: 408/530, loss: 0.2687458097934723
2023-01-21 10:04:03.750266: step: 412/530, loss: 0.057169344276189804
2023-01-21 10:04:04.902595: step: 416/530, loss: 0.0790010541677475
2023-01-21 10:04:06.014570: step: 420/530, loss: 0.11381244659423828
2023-01-21 10:04:07.153079: step: 424/530, loss: 0.0247865691781044
2023-01-21 10:04:08.260757: step: 428/530, loss: 0.032341957092285156
2023-01-21 10:04:09.355219: step: 432/530, loss: 0.037595055997371674
2023-01-21 10:04:10.481767: step: 436/530, loss: 0.06516475975513458
2023-01-21 10:04:11.604022: step: 440/530, loss: 0.03413037955760956
2023-01-21 10:04:12.733579: step: 444/530, loss: 0.07497907429933548
2023-01-21 10:04:13.857140: step: 448/530, loss: 0.08353137969970703
2023-01-21 10:04:14.994063: step: 452/530, loss: 0.05254316329956055
2023-01-21 10:04:16.128681: step: 456/530, loss: 0.8278747200965881
2023-01-21 10:04:17.249768: step: 460/530, loss: 0.09874637424945831
2023-01-21 10:04:18.354140: step: 464/530, loss: 0.6914241909980774
2023-01-21 10:04:19.467370: step: 468/530, loss: 0.05763216316699982
2023-01-21 10:04:20.598712: step: 472/530, loss: 0.15036840736865997
2023-01-21 10:04:21.726960: step: 476/530, loss: 0.24840950965881348
2023-01-21 10:04:22.888991: step: 480/530, loss: 0.03926057741045952
2023-01-21 10:04:24.004793: step: 484/530, loss: 0.07835254818201065
2023-01-21 10:04:25.119512: step: 488/530, loss: 0.4250585436820984
2023-01-21 10:04:26.255481: step: 492/530, loss: 0.04335727542638779
2023-01-21 10:04:27.387742: step: 496/530, loss: 0.0035352229606360197
2023-01-21 10:04:28.509495: step: 500/530, loss: 0.03633260726928711
2023-01-21 10:04:29.615501: step: 504/530, loss: 0.05147905275225639
2023-01-21 10:04:30.737549: step: 508/530, loss: 0.0861385390162468
2023-01-21 10:04:31.848395: step: 512/530, loss: 0.1566476821899414
2023-01-21 10:04:32.947767: step: 516/530, loss: 0.005314636509865522
2023-01-21 10:04:34.061759: step: 520/530, loss: 0.08648806065320969
2023-01-21 10:04:35.217595: step: 524/530, loss: 0.07566585391759872
2023-01-21 10:04:36.371964: step: 528/530, loss: 0.18203648924827576
2023-01-21 10:04:37.475679: step: 532/530, loss: 0.13507795333862305
2023-01-21 10:04:38.582928: step: 536/530, loss: 0.20587468147277832
2023-01-21 10:04:39.767521: step: 540/530, loss: 0.055060386657714844
2023-01-21 10:04:40.857658: step: 544/530, loss: 0.010841942392289639
2023-01-21 10:04:41.981810: step: 548/530, loss: 0.679426372051239
2023-01-21 10:04:43.090958: step: 552/530, loss: 0.0229357723146677
2023-01-21 10:04:44.226766: step: 556/530, loss: 0.058355141431093216
2023-01-21 10:04:45.372455: step: 560/530, loss: 0.18925486505031586
2023-01-21 10:04:46.480892: step: 564/530, loss: 0.06875462830066681
2023-01-21 10:04:47.620715: step: 568/530, loss: 0.1131775826215744
2023-01-21 10:04:48.737995: step: 572/530, loss: 0.11294879764318466
2023-01-21 10:04:49.899587: step: 576/530, loss: 0.043291714042425156
2023-01-21 10:04:51.019902: step: 580/530, loss: 0.0644916519522667
2023-01-21 10:04:52.136569: step: 584/530, loss: 0.024523068219423294
2023-01-21 10:04:53.251123: step: 588/530, loss: 0.021272946149110794
2023-01-21 10:04:54.390993: step: 592/530, loss: 0.1397315114736557
2023-01-21 10:04:55.537679: step: 596/530, loss: 0.044266462326049805
2023-01-21 10:04:56.655254: step: 600/530, loss: 0.0054864888079464436
2023-01-21 10:04:57.773067: step: 604/530, loss: 0.01130599994212389
2023-01-21 10:04:58.877879: step: 608/530, loss: 0.031546689569950104
2023-01-21 10:04:59.991997: step: 612/530, loss: 0.06674909591674805
2023-01-21 10:05:01.135402: step: 616/530, loss: 0.027262020856142044
2023-01-21 10:05:02.267871: step: 620/530, loss: 0.27579402923583984
2023-01-21 10:05:03.375267: step: 624/530, loss: 0.04268636554479599
2023-01-21 10:05:04.506621: step: 628/530, loss: 0.05083026736974716
2023-01-21 10:05:05.625870: step: 632/530, loss: 0.23850193619728088
2023-01-21 10:05:06.772741: step: 636/530, loss: 0.05563812702894211
2023-01-21 10:05:07.907834: step: 640/530, loss: 0.0673486739397049
2023-01-21 10:05:09.042407: step: 644/530, loss: 0.37997251749038696
2023-01-21 10:05:10.161777: step: 648/530, loss: 0.06310577690601349
2023-01-21 10:05:11.285863: step: 652/530, loss: 0.030410468578338623
2023-01-21 10:05:12.418973: step: 656/530, loss: 0.3537307679653168
2023-01-21 10:05:13.498154: step: 660/530, loss: 0.08765874058008194
2023-01-21 10:05:14.650684: step: 664/530, loss: 0.09160985797643661
2023-01-21 10:05:15.781271: step: 668/530, loss: 0.09218783676624298
2023-01-21 10:05:16.885386: step: 672/530, loss: 0.01848459243774414
2023-01-21 10:05:18.052961: step: 676/530, loss: 0.009665966033935547
2023-01-21 10:05:19.191663: step: 680/530, loss: 0.02227923832833767
2023-01-21 10:05:20.300808: step: 684/530, loss: 0.018256057053804398
2023-01-21 10:05:21.422931: step: 688/530, loss: 0.05286731943488121
2023-01-21 10:05:22.556860: step: 692/530, loss: 0.007831496186554432
2023-01-21 10:05:23.681443: step: 696/530, loss: 0.28025922179222107
2023-01-21 10:05:24.805734: step: 700/530, loss: 0.032499026507139206
2023-01-21 10:05:25.939687: step: 704/530, loss: 0.3166576027870178
2023-01-21 10:05:27.105490: step: 708/530, loss: 0.05491609498858452
2023-01-21 10:05:28.209812: step: 712/530, loss: 0.08305530995130539
2023-01-21 10:05:29.329481: step: 716/530, loss: 0.053624916821718216
2023-01-21 10:05:30.463749: step: 720/530, loss: 0.060971833765506744
2023-01-21 10:05:31.576926: step: 724/530, loss: 0.06447964161634445
2023-01-21 10:05:32.700163: step: 728/530, loss: 0.03336534649133682
2023-01-21 10:05:33.841778: step: 732/530, loss: 0.09625549614429474
2023-01-21 10:05:34.948260: step: 736/530, loss: 0.5622841119766235
2023-01-21 10:05:36.069384: step: 740/530, loss: 0.05314350128173828
2023-01-21 10:05:37.191777: step: 744/530, loss: 0.06232508644461632
2023-01-21 10:05:38.329494: step: 748/530, loss: 0.0464634895324707
2023-01-21 10:05:39.457288: step: 752/530, loss: 0.15146788954734802
2023-01-21 10:05:40.577552: step: 756/530, loss: 0.09412975609302521
2023-01-21 10:05:41.712843: step: 760/530, loss: 0.024077225476503372
2023-01-21 10:05:42.834455: step: 764/530, loss: 0.04605092853307724
2023-01-21 10:05:43.979847: step: 768/530, loss: 0.03228297084569931
2023-01-21 10:05:45.106250: step: 772/530, loss: 0.019731711596250534
2023-01-21 10:05:46.220167: step: 776/530, loss: 0.07025881111621857
2023-01-21 10:05:47.375016: step: 780/530, loss: 0.04610424116253853
2023-01-21 10:05:48.529673: step: 784/530, loss: 0.04086361080408096
2023-01-21 10:05:49.662601: step: 788/530, loss: 0.02827739715576172
2023-01-21 10:05:50.783384: step: 792/530, loss: 0.03472556918859482
2023-01-21 10:05:51.913897: step: 796/530, loss: 0.056482698768377304
2023-01-21 10:05:53.020229: step: 800/530, loss: 0.03596235811710358
2023-01-21 10:05:54.143641: step: 804/530, loss: 0.10903110355138779
2023-01-21 10:05:55.282601: step: 808/530, loss: 0.0865020751953125
2023-01-21 10:05:56.407908: step: 812/530, loss: 0.04447140917181969
2023-01-21 10:05:57.536303: step: 816/530, loss: 0.06706170737743378
2023-01-21 10:05:58.644056: step: 820/530, loss: 0.01953282207250595
2023-01-21 10:05:59.784247: step: 824/530, loss: 0.11724953353404999
2023-01-21 10:06:00.896318: step: 828/530, loss: 0.056803420186042786
2023-01-21 10:06:02.037844: step: 832/530, loss: 0.7149471640586853
2023-01-21 10:06:03.221229: step: 836/530, loss: 0.122760109603405
2023-01-21 10:06:04.336963: step: 840/530, loss: 0.014964200556278229
2023-01-21 10:06:05.493346: step: 844/530, loss: 0.05737876892089844
2023-01-21 10:06:06.600742: step: 848/530, loss: 0.0651622787117958
2023-01-21 10:06:07.733184: step: 852/530, loss: 0.13405953347682953
2023-01-21 10:06:08.831314: step: 856/530, loss: 0.07202019542455673
2023-01-21 10:06:09.988595: step: 860/530, loss: 0.09511547535657883
2023-01-21 10:06:11.091859: step: 864/530, loss: 0.06167984381318092
2023-01-21 10:06:12.196508: step: 868/530, loss: 0.14603640139102936
2023-01-21 10:06:13.356034: step: 872/530, loss: 0.10600428283214569
2023-01-21 10:06:14.488837: step: 876/530, loss: 0.03459315747022629
2023-01-21 10:06:15.609876: step: 880/530, loss: 0.047760773450136185
2023-01-21 10:06:16.720683: step: 884/530, loss: 0.07533969730138779
2023-01-21 10:06:17.865082: step: 888/530, loss: 0.07903270423412323
2023-01-21 10:06:18.984917: step: 892/530, loss: 0.03886070474982262
2023-01-21 10:06:20.128071: step: 896/530, loss: 0.0925288200378418
2023-01-21 10:06:21.266129: step: 900/530, loss: 0.027315188199281693
2023-01-21 10:06:22.389807: step: 904/530, loss: 0.06365995109081268
2023-01-21 10:06:23.563848: step: 908/530, loss: 0.05195145308971405
2023-01-21 10:06:24.722343: step: 912/530, loss: 0.09089546650648117
2023-01-21 10:06:25.879809: step: 916/530, loss: 0.11439648270606995
2023-01-21 10:06:27.001710: step: 920/530, loss: 0.026868630200624466
2023-01-21 10:06:28.119974: step: 924/530, loss: 0.05828814208507538
2023-01-21 10:06:29.245671: step: 928/530, loss: 0.21288034319877625
2023-01-21 10:06:30.374667: step: 932/530, loss: 0.060282520949840546
2023-01-21 10:06:31.496139: step: 936/530, loss: 0.025718022137880325
2023-01-21 10:06:32.605025: step: 940/530, loss: 0.03839864581823349
2023-01-21 10:06:33.717164: step: 944/530, loss: 0.10771417617797852
2023-01-21 10:06:34.855536: step: 948/530, loss: 0.013860464096069336
2023-01-21 10:06:35.976281: step: 952/530, loss: 0.018464185297489166
2023-01-21 10:06:37.095986: step: 956/530, loss: 0.0586027130484581
2023-01-21 10:06:38.231887: step: 960/530, loss: 0.03533783182501793
2023-01-21 10:06:39.351529: step: 964/530, loss: 0.0895792543888092
2023-01-21 10:06:40.483667: step: 968/530, loss: 0.02761068381369114
2023-01-21 10:06:41.651951: step: 972/530, loss: 6.560903549194336
2023-01-21 10:06:42.802336: step: 976/530, loss: 0.14062567055225372
2023-01-21 10:06:43.934400: step: 980/530, loss: 0.04823312908411026
2023-01-21 10:06:45.054877: step: 984/530, loss: 0.06727972626686096
2023-01-21 10:06:46.187149: step: 988/530, loss: 0.10017089545726776
2023-01-21 10:06:47.295193: step: 992/530, loss: 0.08516636490821838
2023-01-21 10:06:48.456218: step: 996/530, loss: 0.02323278784751892
2023-01-21 10:06:49.582672: step: 1000/530, loss: 0.8687888383865356
2023-01-21 10:06:50.664870: step: 1004/530, loss: 0.027425337582826614
2023-01-21 10:06:51.793543: step: 1008/530, loss: 0.05602312088012695
2023-01-21 10:06:52.910625: step: 1012/530, loss: 0.01217279490083456
2023-01-21 10:06:54.025614: step: 1016/530, loss: 0.08596086502075195
2023-01-21 10:06:55.135712: step: 1020/530, loss: 0.14333610236644745
2023-01-21 10:06:56.245817: step: 1024/530, loss: 0.16926316916942596
2023-01-21 10:06:57.350665: step: 1028/530, loss: 0.01046838704496622
2023-01-21 10:06:58.480136: step: 1032/530, loss: 0.03778515011072159
2023-01-21 10:06:59.584744: step: 1036/530, loss: 0.01136159896850586
2023-01-21 10:07:00.700359: step: 1040/530, loss: 0.02363138273358345
2023-01-21 10:07:01.828163: step: 1044/530, loss: 0.013595771975815296
2023-01-21 10:07:02.948198: step: 1048/530, loss: 0.03186054527759552
2023-01-21 10:07:04.093762: step: 1052/530, loss: 0.011513233184814453
2023-01-21 10:07:05.268319: step: 1056/530, loss: 0.02689356915652752
2023-01-21 10:07:06.384379: step: 1060/530, loss: 0.09482517838478088
2023-01-21 10:07:07.532202: step: 1064/530, loss: 0.12446188926696777
2023-01-21 10:07:08.648408: step: 1068/530, loss: 0.12660154700279236
2023-01-21 10:07:09.769994: step: 1072/530, loss: 0.10044154524803162
2023-01-21 10:07:10.895368: step: 1076/530, loss: 0.00036978721618652344
2023-01-21 10:07:12.006850: step: 1080/530, loss: 0.01193382777273655
2023-01-21 10:07:13.151876: step: 1084/530, loss: 0.09958532452583313
2023-01-21 10:07:14.289620: step: 1088/530, loss: 0.06786270439624786
2023-01-21 10:07:15.428549: step: 1092/530, loss: 0.0034145356621593237
2023-01-21 10:07:16.547729: step: 1096/530, loss: 0.07294435799121857
2023-01-21 10:07:17.684710: step: 1100/530, loss: 0.09617061913013458
2023-01-21 10:07:18.820893: step: 1104/530, loss: 0.07037369906902313
2023-01-21 10:07:19.938130: step: 1108/530, loss: 0.01848287507891655
2023-01-21 10:07:21.075741: step: 1112/530, loss: 0.07685699313879013
2023-01-21 10:07:22.215896: step: 1116/530, loss: 0.03291606903076172
2023-01-21 10:07:23.346385: step: 1120/530, loss: 0.08798322826623917
2023-01-21 10:07:24.485287: step: 1124/530, loss: 0.18928633630275726
2023-01-21 10:07:25.663651: step: 1128/530, loss: 0.03708620369434357
2023-01-21 10:07:26.789518: step: 1132/530, loss: 0.183427631855011
2023-01-21 10:07:27.930408: step: 1136/530, loss: 0.24276676774024963
2023-01-21 10:07:29.026151: step: 1140/530, loss: 0.028408052399754524
2023-01-21 10:07:30.146046: step: 1144/530, loss: 0.028786754235625267
2023-01-21 10:07:31.297264: step: 1148/530, loss: 0.2041950225830078
2023-01-21 10:07:32.411895: step: 1152/530, loss: 0.038805197924375534
2023-01-21 10:07:33.570240: step: 1156/530, loss: 0.05086822435259819
2023-01-21 10:07:34.693428: step: 1160/530, loss: 0.03743095323443413
2023-01-21 10:07:35.836505: step: 1164/530, loss: 0.024446584284305573
2023-01-21 10:07:36.942954: step: 1168/530, loss: 0.09873976558446884
2023-01-21 10:07:38.090255: step: 1172/530, loss: 0.04134741052985191
2023-01-21 10:07:39.247186: step: 1176/530, loss: 0.6849942207336426
2023-01-21 10:07:40.365222: step: 1180/530, loss: 0.13051578402519226
2023-01-21 10:07:41.521022: step: 1184/530, loss: 0.06943130493164062
2023-01-21 10:07:42.654356: step: 1188/530, loss: 0.04057817906141281
2023-01-21 10:07:43.801288: step: 1192/530, loss: 0.011747789569199085
2023-01-21 10:07:44.968207: step: 1196/530, loss: 0.4016820788383484
2023-01-21 10:07:46.095699: step: 1200/530, loss: 0.05502305179834366
2023-01-21 10:07:47.263149: step: 1204/530, loss: 0.02045278623700142
2023-01-21 10:07:48.386033: step: 1208/530, loss: 0.09430789947509766
2023-01-21 10:07:49.503062: step: 1212/530, loss: 0.07636761665344238
2023-01-21 10:07:50.610519: step: 1216/530, loss: 0.10635528713464737
2023-01-21 10:07:51.723405: step: 1220/530, loss: 0.010033512488007545
2023-01-21 10:07:52.837619: step: 1224/530, loss: 0.07806424796581268
2023-01-21 10:07:53.946316: step: 1228/530, loss: 0.008599281311035156
2023-01-21 10:07:55.059449: step: 1232/530, loss: 0.018236923962831497
2023-01-21 10:07:56.173342: step: 1236/530, loss: 0.08666108548641205
2023-01-21 10:07:57.303761: step: 1240/530, loss: 0.17101651430130005
2023-01-21 10:07:58.433834: step: 1244/530, loss: 0.08385143429040909
2023-01-21 10:07:59.586401: step: 1248/530, loss: 0.036004066467285156
2023-01-21 10:08:00.699448: step: 1252/530, loss: 0.04186706244945526
2023-01-21 10:08:01.849158: step: 1256/530, loss: 0.08961105346679688
2023-01-21 10:08:02.966272: step: 1260/530, loss: 0.029230643063783646
2023-01-21 10:08:04.093403: step: 1264/530, loss: 0.04703674465417862
2023-01-21 10:08:05.226567: step: 1268/530, loss: 0.522025465965271
2023-01-21 10:08:06.356106: step: 1272/530, loss: 0.1514565497636795
2023-01-21 10:08:07.480116: step: 1276/530, loss: 0.13386401534080505
2023-01-21 10:08:08.597317: step: 1280/530, loss: 0.17071080207824707
2023-01-21 10:08:09.728028: step: 1284/530, loss: 0.07503719627857208
2023-01-21 10:08:10.849973: step: 1288/530, loss: 0.5004467368125916
2023-01-21 10:08:11.982360: step: 1292/530, loss: 0.061617374420166016
2023-01-21 10:08:13.109342: step: 1296/530, loss: 0.10591130703687668
2023-01-21 10:08:14.234671: step: 1300/530, loss: 0.07752017676830292
2023-01-21 10:08:15.348576: step: 1304/530, loss: 0.011450815945863724
2023-01-21 10:08:16.468363: step: 1308/530, loss: 0.07293599098920822
2023-01-21 10:08:17.562314: step: 1312/530, loss: 0.04488656297326088
2023-01-21 10:08:18.698585: step: 1316/530, loss: 0.0789724811911583
2023-01-21 10:08:19.822670: step: 1320/530, loss: 0.027509786188602448
2023-01-21 10:08:20.947924: step: 1324/530, loss: 0.12159271538257599
2023-01-21 10:08:22.069210: step: 1328/530, loss: 0.03311128914356232
2023-01-21 10:08:23.223517: step: 1332/530, loss: 0.02288665808737278
2023-01-21 10:08:24.326820: step: 1336/530, loss: 0.10609426349401474
2023-01-21 10:08:25.443612: step: 1340/530, loss: 0.043726157397031784
2023-01-21 10:08:26.554591: step: 1344/530, loss: 0.006451750174164772
2023-01-21 10:08:27.668844: step: 1348/530, loss: 0.12351807951927185
2023-01-21 10:08:28.772673: step: 1352/530, loss: 0.16189061105251312
2023-01-21 10:08:29.883667: step: 1356/530, loss: 0.007510089781135321
2023-01-21 10:08:31.023181: step: 1360/530, loss: 0.04030637815594673
2023-01-21 10:08:32.162007: step: 1364/530, loss: 0.08193626254796982
2023-01-21 10:08:33.305023: step: 1368/530, loss: 0.1276511251926422
2023-01-21 10:08:34.433989: step: 1372/530, loss: 0.037912726402282715
2023-01-21 10:08:35.559928: step: 1376/530, loss: 0.06471309065818787
2023-01-21 10:08:36.711086: step: 1380/530, loss: 0.0040777684189379215
2023-01-21 10:08:37.838865: step: 1384/530, loss: 0.03407859802246094
2023-01-21 10:08:38.964124: step: 1388/530, loss: 0.09845371544361115
2023-01-21 10:08:40.090801: step: 1392/530, loss: 0.3267652690410614
2023-01-21 10:08:41.207571: step: 1396/530, loss: 0.11281280964612961
2023-01-21 10:08:42.350416: step: 1400/530, loss: 0.04188718646764755
2023-01-21 10:08:43.480972: step: 1404/530, loss: 0.49927303194999695
2023-01-21 10:08:44.617874: step: 1408/530, loss: 0.026709843426942825
2023-01-21 10:08:45.781880: step: 1412/530, loss: 0.1442207396030426
2023-01-21 10:08:46.895293: step: 1416/530, loss: 0.16683274507522583
2023-01-21 10:08:48.028617: step: 1420/530, loss: 0.014535332098603249
2023-01-21 10:08:49.113713: step: 1424/530, loss: 0.05050954967737198
2023-01-21 10:08:50.213887: step: 1428/530, loss: 0.06561928242444992
2023-01-21 10:08:51.370116: step: 1432/530, loss: 0.027131270617246628
2023-01-21 10:08:52.495870: step: 1436/530, loss: 0.011635875329375267
2023-01-21 10:08:53.623108: step: 1440/530, loss: 0.058353424072265625
2023-01-21 10:08:54.737697: step: 1444/530, loss: 0.06147165223956108
2023-01-21 10:08:55.859301: step: 1448/530, loss: 0.05459146574139595
2023-01-21 10:08:57.004446: step: 1452/530, loss: 0.063715361058712
2023-01-21 10:08:58.145195: step: 1456/530, loss: 0.025348853319883347
2023-01-21 10:08:59.244136: step: 1460/530, loss: 0.0006513595581054688
2023-01-21 10:09:00.381110: step: 1464/530, loss: 0.1258711814880371
2023-01-21 10:09:01.521262: step: 1468/530, loss: 0.06794948875904083
2023-01-21 10:09:02.654875: step: 1472/530, loss: 0.12003631889820099
2023-01-21 10:09:03.796566: step: 1476/530, loss: 0.1690683811903
2023-01-21 10:09:04.933456: step: 1480/530, loss: 0.017186546698212624
2023-01-21 10:09:06.088680: step: 1484/530, loss: 0.05246248468756676
2023-01-21 10:09:07.223038: step: 1488/530, loss: 0.053032875061035156
2023-01-21 10:09:08.345804: step: 1492/530, loss: 0.004847431555390358
2023-01-21 10:09:09.486900: step: 1496/530, loss: 0.06122569739818573
2023-01-21 10:09:10.600285: step: 1500/530, loss: 0.19184602797031403
2023-01-21 10:09:11.756295: step: 1504/530, loss: 0.07328452914953232
2023-01-21 10:09:12.872576: step: 1508/530, loss: 0.03860063850879669
2023-01-21 10:09:14.003937: step: 1512/530, loss: 0.07141876220703125
2023-01-21 10:09:15.142056: step: 1516/530, loss: 0.07593289017677307
2023-01-21 10:09:16.278238: step: 1520/530, loss: 0.18136702477931976
2023-01-21 10:09:17.400704: step: 1524/530, loss: 0.17930598556995392
2023-01-21 10:09:18.521829: step: 1528/530, loss: 0.0016337871784344316
2023-01-21 10:09:19.626214: step: 1532/530, loss: 0.0418432243168354
2023-01-21 10:09:20.770726: step: 1536/530, loss: 0.0071582794189453125
2023-01-21 10:09:21.910396: step: 1540/530, loss: 0.05998706817626953
2023-01-21 10:09:23.033573: step: 1544/530, loss: 0.0076999664306640625
2023-01-21 10:09:24.163759: step: 1548/530, loss: 0.025150299072265625
2023-01-21 10:09:25.298702: step: 1552/530, loss: 0.04065189138054848
2023-01-21 10:09:26.409975: step: 1556/530, loss: 0.09578075259923935
2023-01-21 10:09:27.556618: step: 1560/530, loss: 0.19159050285816193
2023-01-21 10:09:28.667709: step: 1564/530, loss: 0.1180192232131958
2023-01-21 10:09:29.788058: step: 1568/530, loss: 0.09115500003099442
2023-01-21 10:09:30.971086: step: 1572/530, loss: 0.2018662989139557
2023-01-21 10:09:32.108263: step: 1576/530, loss: 0.011330699548125267
2023-01-21 10:09:33.237873: step: 1580/530, loss: 0.03448767587542534
2023-01-21 10:09:34.374951: step: 1584/530, loss: 0.05008220672607422
2023-01-21 10:09:35.540858: step: 1588/530, loss: 0.10126900672912598
2023-01-21 10:09:36.680669: step: 1592/530, loss: 0.056223392486572266
2023-01-21 10:09:37.803023: step: 1596/530, loss: 0.11051645874977112
2023-01-21 10:09:38.951397: step: 1600/530, loss: 0.09102821350097656
2023-01-21 10:09:40.089618: step: 1604/530, loss: 0.16616077721118927
2023-01-21 10:09:41.240575: step: 1608/530, loss: 0.09570388495922089
2023-01-21 10:09:42.338563: step: 1612/530, loss: 0.00036115647526457906
2023-01-21 10:09:43.456456: step: 1616/530, loss: 0.06224660947918892
2023-01-21 10:09:44.572149: step: 1620/530, loss: 0.07185105979442596
2023-01-21 10:09:45.678435: step: 1624/530, loss: 0.06093177944421768
2023-01-21 10:09:46.793250: step: 1628/530, loss: 0.10062961280345917
2023-01-21 10:09:47.884814: step: 1632/530, loss: 0.0170472152531147
2023-01-21 10:09:48.997974: step: 1636/530, loss: 0.5759602785110474
2023-01-21 10:09:50.110178: step: 1640/530, loss: 0.07380161434412003
2023-01-21 10:09:51.241197: step: 1644/530, loss: 0.1147991195321083
2023-01-21 10:09:52.367748: step: 1648/530, loss: 0.09085425734519958
2023-01-21 10:09:53.507790: step: 1652/530, loss: 0.04240245744585991
2023-01-21 10:09:54.629105: step: 1656/530, loss: 0.032878972589969635
2023-01-21 10:09:55.769684: step: 1660/530, loss: 0.11079893261194229
2023-01-21 10:09:56.906706: step: 1664/530, loss: 0.4983340799808502
2023-01-21 10:09:58.040331: step: 1668/530, loss: 0.1105494499206543
2023-01-21 10:09:59.154614: step: 1672/530, loss: 0.10265432298183441
2023-01-21 10:10:00.276898: step: 1676/530, loss: 0.33097267150878906
2023-01-21 10:10:01.395214: step: 1680/530, loss: 0.00038557054358534515
2023-01-21 10:10:02.544982: step: 1684/530, loss: 0.014426374807953835
2023-01-21 10:10:03.668709: step: 1688/530, loss: 0.022704387083649635
2023-01-21 10:10:04.800903: step: 1692/530, loss: 0.1082952469587326
2023-01-21 10:10:05.903461: step: 1696/530, loss: 0.06152687221765518
2023-01-21 10:10:07.032332: step: 1700/530, loss: 0.01396484300494194
2023-01-21 10:10:08.178499: step: 1704/530, loss: 0.13204509019851685
2023-01-21 10:10:09.282295: step: 1708/530, loss: 0.16111384332180023
2023-01-21 10:10:10.438283: step: 1712/530, loss: 0.07105598598718643
2023-01-21 10:10:11.568939: step: 1716/530, loss: 0.044014930725097656
2023-01-21 10:10:12.696979: step: 1720/530, loss: 0.07751598209142685
2023-01-21 10:10:13.818252: step: 1724/530, loss: 0.013644028455018997
2023-01-21 10:10:14.930322: step: 1728/530, loss: 0.4771810472011566
2023-01-21 10:10:16.068870: step: 1732/530, loss: 0.08296814560890198
2023-01-21 10:10:17.187171: step: 1736/530, loss: 0.20678111910820007
2023-01-21 10:10:18.297838: step: 1740/530, loss: 0.08969905972480774
2023-01-21 10:10:19.422693: step: 1744/530, loss: 0.020624350756406784
2023-01-21 10:10:20.549604: step: 1748/530, loss: 0.18946728110313416
2023-01-21 10:10:21.668866: step: 1752/530, loss: 0.01571216620504856
2023-01-21 10:10:22.783647: step: 1756/530, loss: 0.07748472690582275
2023-01-21 10:10:23.899596: step: 1760/530, loss: 0.1304752379655838
2023-01-21 10:10:25.047727: step: 1764/530, loss: 0.020856570452451706
2023-01-21 10:10:26.183325: step: 1768/530, loss: 0.008144760504364967
2023-01-21 10:10:27.291099: step: 1772/530, loss: 0.1670517921447754
2023-01-21 10:10:28.383171: step: 1776/530, loss: 0.04218435287475586
2023-01-21 10:10:29.512758: step: 1780/530, loss: 0.09137530624866486
2023-01-21 10:10:30.653858: step: 1784/530, loss: 0.2485300600528717
2023-01-21 10:10:31.803783: step: 1788/530, loss: 0.12017574906349182
2023-01-21 10:10:32.908659: step: 1792/530, loss: 0.21962089836597443
2023-01-21 10:10:34.058851: step: 1796/530, loss: 0.004981517791748047
2023-01-21 10:10:35.160020: step: 1800/530, loss: 0.199933260679245
2023-01-21 10:10:36.306188: step: 1804/530, loss: 0.04714103043079376
2023-01-21 10:10:37.468979: step: 1808/530, loss: 0.004731369204819202
2023-01-21 10:10:38.585757: step: 1812/530, loss: 0.0011181235313415527
2023-01-21 10:10:39.709434: step: 1816/530, loss: 0.07350564002990723
2023-01-21 10:10:40.811415: step: 1820/530, loss: 0.41598719358444214
2023-01-21 10:10:41.919488: step: 1824/530, loss: 0.06858482211828232
2023-01-21 10:10:43.025129: step: 1828/530, loss: 0.1664014756679535
2023-01-21 10:10:44.132828: step: 1832/530, loss: 0.06379032135009766
2023-01-21 10:10:45.252234: step: 1836/530, loss: 0.12418480217456818
2023-01-21 10:10:46.406263: step: 1840/530, loss: 0.14654946327209473
2023-01-21 10:10:47.531131: step: 1844/530, loss: 0.037153054028749466
2023-01-21 10:10:48.641694: step: 1848/530, loss: 0.08995561301708221
2023-01-21 10:10:49.765088: step: 1852/530, loss: 0.06575407832860947
2023-01-21 10:10:50.900720: step: 1856/530, loss: 0.10117187350988388
2023-01-21 10:10:52.069856: step: 1860/530, loss: 0.24815022945404053
2023-01-21 10:10:53.185181: step: 1864/530, loss: 0.010378074832260609
2023-01-21 10:10:54.309014: step: 1868/530, loss: 0.08951392024755478
2023-01-21 10:10:55.440420: step: 1872/530, loss: 0.07183942943811417
2023-01-21 10:10:56.552890: step: 1876/530, loss: 0.061238862574100494
2023-01-21 10:10:57.665310: step: 1880/530, loss: 0.09973859786987305
2023-01-21 10:10:58.769810: step: 1884/530, loss: 0.04124307632446289
2023-01-21 10:10:59.896182: step: 1888/530, loss: 0.09564247727394104
2023-01-21 10:11:00.997123: step: 1892/530, loss: 0.013436890207231045
2023-01-21 10:11:02.149544: step: 1896/530, loss: 0.049610041081905365
2023-01-21 10:11:03.272798: step: 1900/530, loss: 0.12335586547851562
2023-01-21 10:11:04.379502: step: 1904/530, loss: 0.014607524499297142
2023-01-21 10:11:05.490037: step: 1908/530, loss: 0.15633372962474823
2023-01-21 10:11:06.581060: step: 1912/530, loss: 0.04107208177447319
2023-01-21 10:11:07.713366: step: 1916/530, loss: 0.03873138502240181
2023-01-21 10:11:08.841732: step: 1920/530, loss: 0.0539851188659668
2023-01-21 10:11:09.950859: step: 1924/530, loss: 0.9264144897460938
2023-01-21 10:11:11.074836: step: 1928/530, loss: 0.10763807594776154
2023-01-21 10:11:12.223208: step: 1932/530, loss: 0.05523405224084854
2023-01-21 10:11:13.377000: step: 1936/530, loss: 0.0531252846121788
2023-01-21 10:11:14.532617: step: 1940/530, loss: 0.1844370812177658
2023-01-21 10:11:15.636217: step: 1944/530, loss: 0.03949160501360893
2023-01-21 10:11:16.759480: step: 1948/530, loss: 0.027771569788455963
2023-01-21 10:11:17.886205: step: 1952/530, loss: 0.017905663698911667
2023-01-21 10:11:19.009614: step: 1956/530, loss: 0.010768735781311989
2023-01-21 10:11:20.105151: step: 1960/530, loss: 0.00064849853515625
2023-01-21 10:11:21.214764: step: 1964/530, loss: 0.08890162408351898
2023-01-21 10:11:22.371184: step: 1968/530, loss: 0.051820896565914154
2023-01-21 10:11:23.514855: step: 1972/530, loss: 0.015370655804872513
2023-01-21 10:11:24.665543: step: 1976/530, loss: 0.1209191381931305
2023-01-21 10:11:25.807959: step: 1980/530, loss: 0.09295487403869629
2023-01-21 10:11:26.923758: step: 1984/530, loss: 0.20483312010765076
2023-01-21 10:11:28.057235: step: 1988/530, loss: 0.19505666196346283
2023-01-21 10:11:29.228766: step: 1992/530, loss: 0.08865413069725037
2023-01-21 10:11:30.353625: step: 1996/530, loss: 0.19149601459503174
2023-01-21 10:11:31.486560: step: 2000/530, loss: 0.14197130501270294
2023-01-21 10:11:32.628989: step: 2004/530, loss: 0.05966319888830185
2023-01-21 10:11:33.763999: step: 2008/530, loss: 0.041666317731142044
2023-01-21 10:11:34.894926: step: 2012/530, loss: 0.08533763885498047
2023-01-21 10:11:36.036756: step: 2016/530, loss: 0.2117973417043686
2023-01-21 10:11:37.177278: step: 2020/530, loss: 0.02915506437420845
2023-01-21 10:11:38.333627: step: 2024/530, loss: 0.14061832427978516
2023-01-21 10:11:39.472959: step: 2028/530, loss: 0.1348496377468109
2023-01-21 10:11:40.598417: step: 2032/530, loss: 0.005411624908447266
2023-01-21 10:11:41.754904: step: 2036/530, loss: 0.02037353441119194
2023-01-21 10:11:42.859230: step: 2040/530, loss: 0.04704036936163902
2023-01-21 10:11:43.974150: step: 2044/530, loss: 0.012836170382797718
2023-01-21 10:11:45.081902: step: 2048/530, loss: 0.07903461903333664
2023-01-21 10:11:46.211497: step: 2052/530, loss: 0.09906673431396484
2023-01-21 10:11:47.332642: step: 2056/530, loss: 0.02335362508893013
2023-01-21 10:11:48.452915: step: 2060/530, loss: 0.015564728528261185
2023-01-21 10:11:49.587832: step: 2064/530, loss: 0.015874575823545456
2023-01-21 10:11:50.682756: step: 2068/530, loss: 0.030770661309361458
2023-01-21 10:11:51.799112: step: 2072/530, loss: 0.04608564451336861
2023-01-21 10:11:52.924932: step: 2076/530, loss: 0.015005970373749733
2023-01-21 10:11:54.081265: step: 2080/530, loss: 0.05450630187988281
2023-01-21 10:11:55.233957: step: 2084/530, loss: 0.11551046371459961
2023-01-21 10:11:56.360075: step: 2088/530, loss: 0.16853152215480804
2023-01-21 10:11:57.501675: step: 2092/530, loss: 0.12096138298511505
2023-01-21 10:11:58.586332: step: 2096/530, loss: 0.02918987348675728
2023-01-21 10:11:59.673395: step: 2100/530, loss: 0.0818575918674469
2023-01-21 10:12:00.803156: step: 2104/530, loss: 0.013566303066909313
2023-01-21 10:12:01.910104: step: 2108/530, loss: 0.16752614080905914
2023-01-21 10:12:03.035167: step: 2112/530, loss: 0.024146415293216705
2023-01-21 10:12:04.171269: step: 2116/530, loss: 0.04718070104718208
2023-01-21 10:12:05.282291: step: 2120/530, loss: 0.10455741733312607
==================================================
Loss: 0.115
--------------------
Dev: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5604395604395604, 'r': 0.9444444444444444, 'f1': 0.7034482758620689}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, '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}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:12:51.810010: step: 4/530, loss: 0.10765113681554794
2023-01-21 10:12:52.931064: step: 8/530, loss: 0.039498232305049896
2023-01-21 10:12:54.079150: step: 12/530, loss: 0.02771434746682644
2023-01-21 10:12:55.191280: step: 16/530, loss: 0.08857274055480957
2023-01-21 10:12:56.291157: step: 20/530, loss: 0.08839455246925354
2023-01-21 10:12:57.425578: step: 24/530, loss: 0.031239032745361328
2023-01-21 10:12:58.535637: step: 28/530, loss: 0.011895323172211647
2023-01-21 10:12:59.641456: step: 32/530, loss: 0.03530006483197212
2023-01-21 10:13:00.757453: step: 36/530, loss: 0.044904425740242004
2023-01-21 10:13:01.880295: step: 40/530, loss: 0.42820852994918823
2023-01-21 10:13:03.001398: step: 44/530, loss: 0.04303331300616264
2023-01-21 10:13:04.105267: step: 48/530, loss: 0.02294302172958851
2023-01-21 10:13:05.186476: step: 52/530, loss: 0.03592471405863762
2023-01-21 10:13:06.300367: step: 56/530, loss: 0.04403352737426758
2023-01-21 10:13:07.390804: step: 60/530, loss: 0.08497639000415802
2023-01-21 10:13:08.524272: step: 64/530, loss: 0.14726601541042328
2023-01-21 10:13:09.656528: step: 68/530, loss: 0.05775437504053116
2023-01-21 10:13:10.778628: step: 72/530, loss: 0.024156952276825905
2023-01-21 10:13:11.935312: step: 76/530, loss: 0.11047402024269104
2023-01-21 10:13:13.069626: step: 80/530, loss: 0.11057644337415695
2023-01-21 10:13:14.184940: step: 84/530, loss: 0.05052890628576279
2023-01-21 10:13:15.302107: step: 88/530, loss: 0.049050286412239075
2023-01-21 10:13:16.440014: step: 92/530, loss: 0.01645517349243164
2023-01-21 10:13:17.563119: step: 96/530, loss: 0.09989142417907715
2023-01-21 10:13:18.655014: step: 100/530, loss: 0.01087045669555664
2023-01-21 10:13:19.769526: step: 104/530, loss: 0.02903604507446289
2023-01-21 10:13:20.884829: step: 108/530, loss: 0.17633160948753357
2023-01-21 10:13:22.006183: step: 112/530, loss: 0.01232614554464817
2023-01-21 10:13:23.110452: step: 116/530, loss: 0.01432571467012167
2023-01-21 10:13:24.246605: step: 120/530, loss: 0.04102649912238121
2023-01-21 10:13:25.373613: step: 124/530, loss: 0.07410211861133575
2023-01-21 10:13:26.519817: step: 128/530, loss: 0.22276869416236877
2023-01-21 10:13:27.633159: step: 132/530, loss: 0.01596832275390625
2023-01-21 10:13:28.743175: step: 136/530, loss: 0.06610021740198135
2023-01-21 10:13:29.870130: step: 140/530, loss: 0.05329170823097229
2023-01-21 10:13:30.998692: step: 144/530, loss: 0.019696855917572975
2023-01-21 10:13:32.156196: step: 148/530, loss: 0.26527518033981323
2023-01-21 10:13:33.288514: step: 152/530, loss: 0.10803528130054474
2023-01-21 10:13:34.411038: step: 156/530, loss: 0.07411766052246094
2023-01-21 10:13:35.540822: step: 160/530, loss: 0.045439720153808594
2023-01-21 10:13:36.667794: step: 164/530, loss: 0.3324577808380127
2023-01-21 10:13:37.806940: step: 168/530, loss: 0.062174275517463684
2023-01-21 10:13:38.945074: step: 172/530, loss: 0.018614387139678
2023-01-21 10:13:40.057084: step: 176/530, loss: 0.04056167975068092
2023-01-21 10:13:41.207181: step: 180/530, loss: 0.12621356546878815
2023-01-21 10:13:42.336107: step: 184/530, loss: 0.12509211897850037
2023-01-21 10:13:43.457885: step: 188/530, loss: 0.0927850753068924
2023-01-21 10:13:44.608798: step: 192/530, loss: 0.07804946601390839
2023-01-21 10:13:45.750298: step: 196/530, loss: 0.10279674828052521
2023-01-21 10:13:46.877335: step: 200/530, loss: 0.08590393513441086
2023-01-21 10:13:47.982270: step: 204/530, loss: 0.023784827440977097
2023-01-21 10:13:49.106070: step: 208/530, loss: 0.05802679434418678
2023-01-21 10:13:50.247461: step: 212/530, loss: 0.0005128383636474609
2023-01-21 10:13:51.360105: step: 216/530, loss: 0.05874624103307724
2023-01-21 10:13:52.467705: step: 220/530, loss: 0.02341618575155735
2023-01-21 10:13:53.577995: step: 224/530, loss: 0.05245189741253853
2023-01-21 10:13:54.709356: step: 228/530, loss: 0.08626270294189453
2023-01-21 10:13:55.815784: step: 232/530, loss: 0.2873474061489105
2023-01-21 10:13:56.926746: step: 236/530, loss: 0.01621522754430771
2023-01-21 10:13:58.063815: step: 240/530, loss: 0.1179172545671463
2023-01-21 10:13:59.182466: step: 244/530, loss: 0.00968389492481947
2023-01-21 10:14:00.303049: step: 248/530, loss: 0.05039501190185547
2023-01-21 10:14:01.419340: step: 252/530, loss: 0.022718237712979317
2023-01-21 10:14:02.581542: step: 256/530, loss: 0.027546310797333717
2023-01-21 10:14:03.694293: step: 260/530, loss: 0.03861560672521591
2023-01-21 10:14:04.807475: step: 264/530, loss: 0.04481859132647514
2023-01-21 10:14:05.953261: step: 268/530, loss: 0.0638696700334549
2023-01-21 10:14:07.099396: step: 272/530, loss: 0.05806942284107208
2023-01-21 10:14:08.231798: step: 276/530, loss: 0.023115921765565872
2023-01-21 10:14:09.340152: step: 280/530, loss: 0.02539529837667942
2023-01-21 10:14:10.452170: step: 284/530, loss: 0.14105892181396484
2023-01-21 10:14:11.598987: step: 288/530, loss: 0.015781689435243607
2023-01-21 10:14:12.747962: step: 292/530, loss: 0.010963821783661842
2023-01-21 10:14:13.888983: step: 296/530, loss: 0.12178449332714081
2023-01-21 10:14:15.014429: step: 300/530, loss: 0.028708267956972122
2023-01-21 10:14:16.127821: step: 304/530, loss: 0.08935517817735672
2023-01-21 10:14:17.269878: step: 308/530, loss: 0.06159505993127823
2023-01-21 10:14:18.403194: step: 312/530, loss: 0.013109494000673294
2023-01-21 10:14:19.522640: step: 316/530, loss: 0.1577167510986328
2023-01-21 10:14:20.652167: step: 320/530, loss: 0.041231490671634674
2023-01-21 10:14:21.785980: step: 324/530, loss: 1.474432349205017
2023-01-21 10:14:22.898106: step: 328/530, loss: 0.05310077965259552
2023-01-21 10:14:24.089992: step: 332/530, loss: 0.011202669702470303
2023-01-21 10:14:25.177229: step: 336/530, loss: 0.10677547752857208
2023-01-21 10:14:26.317829: step: 340/530, loss: 0.12843990325927734
2023-01-21 10:14:27.449591: step: 344/530, loss: 0.0025238990783691406
2023-01-21 10:14:28.546674: step: 348/530, loss: 0.028189469128847122
2023-01-21 10:14:29.654220: step: 352/530, loss: 0.03873257711529732
2023-01-21 10:14:30.768286: step: 356/530, loss: 0.0664127916097641
2023-01-21 10:14:31.896669: step: 360/530, loss: 0.052901364862918854
2023-01-21 10:14:33.028894: step: 364/530, loss: 0.042401909828186035
2023-01-21 10:14:34.169070: step: 368/530, loss: 0.016837596893310547
2023-01-21 10:14:35.313723: step: 372/530, loss: 0.07129593193531036
2023-01-21 10:14:36.474330: step: 376/530, loss: 0.014962482266128063
2023-01-21 10:14:37.609759: step: 380/530, loss: 0.06429004669189453
2023-01-21 10:14:38.726976: step: 384/530, loss: 0.00642662076279521
2023-01-21 10:14:39.842403: step: 388/530, loss: 0.16434498131275177
2023-01-21 10:14:40.980160: step: 392/530, loss: 0.05184169113636017
2023-01-21 10:14:42.099481: step: 396/530, loss: 0.046453237533569336
2023-01-21 10:14:43.209733: step: 400/530, loss: 0.024739742279052734
2023-01-21 10:14:44.329202: step: 404/530, loss: 0.0801876112818718
2023-01-21 10:14:45.456967: step: 408/530, loss: 0.03692302852869034
2023-01-21 10:14:46.585280: step: 412/530, loss: 0.058938123285770416
2023-01-21 10:14:47.744412: step: 416/530, loss: 0.07724404335021973
2023-01-21 10:14:48.922669: step: 420/530, loss: 0.07342529296875
2023-01-21 10:14:50.020205: step: 424/530, loss: 0.02885305881500244
2023-01-21 10:14:51.166018: step: 428/530, loss: 0.1588561087846756
2023-01-21 10:14:52.275688: step: 432/530, loss: 0.17054371535778046
2023-01-21 10:14:53.416527: step: 436/530, loss: 0.08053378760814667
2023-01-21 10:14:54.525509: step: 440/530, loss: 0.7874759435653687
2023-01-21 10:14:55.642923: step: 444/530, loss: 0.011628913693130016
2023-01-21 10:14:56.776611: step: 448/530, loss: 0.018297767266631126
2023-01-21 10:14:57.891271: step: 452/530, loss: 0.021543312817811966
2023-01-21 10:14:59.016918: step: 456/530, loss: 0.005405521485954523
2023-01-21 10:15:00.137677: step: 460/530, loss: 0.16249045729637146
2023-01-21 10:15:01.259757: step: 464/530, loss: 0.02071523666381836
2023-01-21 10:15:02.375800: step: 468/530, loss: 0.1479371041059494
2023-01-21 10:15:03.530387: step: 472/530, loss: 0.6006187200546265
2023-01-21 10:15:04.628869: step: 476/530, loss: 0.08663597702980042
2023-01-21 10:15:05.732086: step: 480/530, loss: 0.11022194474935532
2023-01-21 10:15:06.846684: step: 484/530, loss: 0.07298507541418076
2023-01-21 10:15:07.990425: step: 488/530, loss: 0.22021742165088654
2023-01-21 10:15:09.106245: step: 492/530, loss: 0.11701764911413193
2023-01-21 10:15:10.251316: step: 496/530, loss: 0.25930604338645935
2023-01-21 10:15:11.360973: step: 500/530, loss: 0.09067802876234055
2023-01-21 10:15:12.499054: step: 504/530, loss: 0.008562088012695312
2023-01-21 10:15:13.655721: step: 508/530, loss: 0.027094651013612747
2023-01-21 10:15:14.768609: step: 512/530, loss: 0.1402035653591156
2023-01-21 10:15:15.881566: step: 516/530, loss: 0.02455282211303711
2023-01-21 10:15:16.995443: step: 520/530, loss: 0.07938452064990997
2023-01-21 10:15:18.128752: step: 524/530, loss: 0.07965602725744247
2023-01-21 10:15:19.261638: step: 528/530, loss: 0.018642330542206764
2023-01-21 10:15:20.414243: step: 532/530, loss: 0.10618558526039124
2023-01-21 10:15:21.556263: step: 536/530, loss: 0.028895283117890358
2023-01-21 10:15:22.715340: step: 540/530, loss: 0.026750946417450905
2023-01-21 10:15:23.848504: step: 544/530, loss: 0.024262618273496628
2023-01-21 10:15:24.973441: step: 548/530, loss: 0.003574943635612726
2023-01-21 10:15:26.081869: step: 552/530, loss: 0.05119892582297325
2023-01-21 10:15:27.220592: step: 556/530, loss: 0.35329532623291016
2023-01-21 10:15:28.363246: step: 560/530, loss: 0.10245752334594727
2023-01-21 10:15:29.481144: step: 564/530, loss: 0.07935552299022675
2023-01-21 10:15:30.612527: step: 568/530, loss: 0.08759871125221252
2023-01-21 10:15:31.707793: step: 572/530, loss: 0.058500003069639206
2023-01-21 10:15:32.841055: step: 576/530, loss: 0.020183134824037552
2023-01-21 10:15:33.946909: step: 580/530, loss: 0.036687564104795456
2023-01-21 10:15:35.079492: step: 584/530, loss: 0.035057827830314636
2023-01-21 10:15:36.233015: step: 588/530, loss: 0.05998945236206055
2023-01-21 10:15:37.392274: step: 592/530, loss: 0.004501724615693092
2023-01-21 10:15:38.545388: step: 596/530, loss: 0.013484383001923561
2023-01-21 10:15:39.655894: step: 600/530, loss: 0.011657047085464
2023-01-21 10:15:40.750275: step: 604/530, loss: 0.014903879724442959
2023-01-21 10:15:41.868597: step: 608/530, loss: 0.060456182807683945
2023-01-21 10:15:42.989556: step: 612/530, loss: 0.08970329165458679
2023-01-21 10:15:44.095877: step: 616/530, loss: 0.07361546158790588
2023-01-21 10:15:45.237027: step: 620/530, loss: 0.07196168601512909
2023-01-21 10:15:46.387288: step: 624/530, loss: 0.010826683603227139
2023-01-21 10:15:47.509918: step: 628/530, loss: 0.42353326082229614
2023-01-21 10:15:48.620749: step: 632/530, loss: 0.01778816059231758
2023-01-21 10:15:49.790739: step: 636/530, loss: 0.05257253721356392
2023-01-21 10:15:50.926796: step: 640/530, loss: 0.022453976795077324
2023-01-21 10:15:52.038331: step: 644/530, loss: 0.025582171976566315
2023-01-21 10:15:53.152617: step: 648/530, loss: 0.006249523255974054
2023-01-21 10:15:54.284982: step: 652/530, loss: 0.0723206102848053
2023-01-21 10:15:55.417406: step: 656/530, loss: 0.00969839096069336
2023-01-21 10:15:56.566646: step: 660/530, loss: 0.040892697870731354
2023-01-21 10:15:57.705178: step: 664/530, loss: 0.07451563328504562
2023-01-21 10:15:58.813432: step: 668/530, loss: 0.11151543259620667
2023-01-21 10:15:59.945395: step: 672/530, loss: 0.033945560455322266
2023-01-21 10:16:01.059167: step: 676/530, loss: 0.05096454918384552
2023-01-21 10:16:02.194436: step: 680/530, loss: 0.16975107789039612
2023-01-21 10:16:03.295055: step: 684/530, loss: 0.0540614128112793
2023-01-21 10:16:04.404410: step: 688/530, loss: 0.03207254409790039
2023-01-21 10:16:05.527390: step: 692/530, loss: 0.10302925109863281
2023-01-21 10:16:06.664343: step: 696/530, loss: 0.05581269413232803
2023-01-21 10:16:07.800912: step: 700/530, loss: 0.07609835267066956
2023-01-21 10:16:08.908652: step: 704/530, loss: 0.011246967129409313
2023-01-21 10:16:10.033831: step: 708/530, loss: 0.09025593101978302
2023-01-21 10:16:11.182777: step: 712/530, loss: 0.039476778358221054
2023-01-21 10:16:12.291222: step: 716/530, loss: 0.031519606709480286
2023-01-21 10:16:13.407632: step: 720/530, loss: 0.032343242317438126
2023-01-21 10:16:14.530427: step: 724/530, loss: 0.04513416439294815
2023-01-21 10:16:15.675182: step: 728/530, loss: 0.060396961867809296
2023-01-21 10:16:16.817941: step: 732/530, loss: 0.12892360985279083
2023-01-21 10:16:17.933591: step: 736/530, loss: 0.04455604404211044
2023-01-21 10:16:19.039284: step: 740/530, loss: 0.016609765589237213
2023-01-21 10:16:20.153400: step: 744/530, loss: 0.039734650403261185
2023-01-21 10:16:21.275968: step: 748/530, loss: 0.04650592803955078
2023-01-21 10:16:22.411928: step: 752/530, loss: 0.04336996003985405
2023-01-21 10:16:23.531904: step: 756/530, loss: 0.08165951073169708
2023-01-21 10:16:24.623239: step: 760/530, loss: 0.24136991798877716
2023-01-21 10:16:25.772359: step: 764/530, loss: 0.013903426937758923
2023-01-21 10:16:26.911267: step: 768/530, loss: 0.012473011389374733
2023-01-21 10:16:28.034294: step: 772/530, loss: 0.033951569348573685
2023-01-21 10:16:29.148339: step: 776/530, loss: 0.256072998046875
2023-01-21 10:16:30.257230: step: 780/530, loss: 0.03144855424761772
2023-01-21 10:16:31.349177: step: 784/530, loss: 0.06555668264627457
2023-01-21 10:16:32.466566: step: 788/530, loss: 0.1716821938753128
2023-01-21 10:16:33.609371: step: 792/530, loss: 0.1999543160200119
2023-01-21 10:16:34.740482: step: 796/530, loss: 0.18226367235183716
2023-01-21 10:16:35.868082: step: 800/530, loss: 0.0015272140735760331
2023-01-21 10:16:36.966631: step: 804/530, loss: 0.01624884642660618
2023-01-21 10:16:38.116685: step: 808/530, loss: 0.11577749252319336
2023-01-21 10:16:39.264663: step: 812/530, loss: 0.05146780237555504
2023-01-21 10:16:40.376055: step: 816/530, loss: 0.4820139408111572
2023-01-21 10:16:41.494577: step: 820/530, loss: 0.07320301234722137
2023-01-21 10:16:42.615743: step: 824/530, loss: 0.1259758025407791
2023-01-21 10:16:43.714780: step: 828/530, loss: 0.08337679505348206
2023-01-21 10:16:44.839780: step: 832/530, loss: 0.10451727360486984
2023-01-21 10:16:45.954722: step: 836/530, loss: 0.03495025634765625
2023-01-21 10:16:47.089050: step: 840/530, loss: 0.01575026474893093
2023-01-21 10:16:48.209611: step: 844/530, loss: 0.03577547147870064
2023-01-21 10:16:49.319534: step: 848/530, loss: 0.04008970409631729
2023-01-21 10:16:50.464462: step: 852/530, loss: 0.12645407021045685
2023-01-21 10:16:51.564396: step: 856/530, loss: 0.10761023312807083
2023-01-21 10:16:52.698982: step: 860/530, loss: 0.02683563157916069
2023-01-21 10:16:53.816895: step: 864/530, loss: 0.0854131281375885
2023-01-21 10:16:54.940956: step: 868/530, loss: 0.011182595044374466
2023-01-21 10:16:56.053931: step: 872/530, loss: 0.09581577777862549
2023-01-21 10:16:57.173474: step: 876/530, loss: 0.04635629802942276
2023-01-21 10:16:58.290616: step: 880/530, loss: 0.2457302063703537
2023-01-21 10:16:59.413117: step: 884/530, loss: 0.12046680599451065
2023-01-21 10:17:00.535716: step: 888/530, loss: 0.06635294109582901
2023-01-21 10:17:01.651539: step: 892/530, loss: 0.012544631958007812
2023-01-21 10:17:02.746326: step: 896/530, loss: 0.03818855434656143
2023-01-21 10:17:03.854610: step: 900/530, loss: 0.04055233299732208
2023-01-21 10:17:04.963832: step: 904/530, loss: 0.07662753760814667
2023-01-21 10:17:06.119122: step: 908/530, loss: 0.12469349056482315
2023-01-21 10:17:07.251444: step: 912/530, loss: 0.0028290273621678352
2023-01-21 10:17:08.374341: step: 916/530, loss: 0.04923210293054581
2023-01-21 10:17:09.528781: step: 920/530, loss: 0.10410775989294052
2023-01-21 10:17:10.694580: step: 924/530, loss: 0.1359046995639801
2023-01-21 10:17:11.828941: step: 928/530, loss: 0.07372274994850159
2023-01-21 10:17:12.932850: step: 932/530, loss: 0.09040529280900955
2023-01-21 10:17:14.061928: step: 936/530, loss: 0.11561093479394913
2023-01-21 10:17:15.182373: step: 940/530, loss: 0.27289941906929016
2023-01-21 10:17:16.317112: step: 944/530, loss: 0.02662224881350994
2023-01-21 10:17:17.432621: step: 948/530, loss: 0.056172944605350494
2023-01-21 10:17:18.537730: step: 952/530, loss: 0.035030364990234375
2023-01-21 10:17:19.648535: step: 956/530, loss: 0.01123189926147461
2023-01-21 10:17:20.755527: step: 960/530, loss: 0.054741762578487396
2023-01-21 10:17:21.899448: step: 964/530, loss: 0.05325598642230034
2023-01-21 10:17:23.018768: step: 968/530, loss: 0.13110850751399994
2023-01-21 10:17:24.181706: step: 972/530, loss: 0.033997632563114166
2023-01-21 10:17:25.308900: step: 976/530, loss: 0.005642128176987171
2023-01-21 10:17:26.485315: step: 980/530, loss: 0.020025063306093216
2023-01-21 10:17:27.613025: step: 984/530, loss: 0.03479595482349396
2023-01-21 10:17:28.737577: step: 988/530, loss: 0.21435566246509552
2023-01-21 10:17:29.859582: step: 992/530, loss: 0.10434789955615997
2023-01-21 10:17:30.993257: step: 996/530, loss: 0.06803098320960999
2023-01-21 10:17:32.135319: step: 1000/530, loss: 0.09369244426488876
2023-01-21 10:17:33.268756: step: 1004/530, loss: 0.01654071733355522
2023-01-21 10:17:34.391193: step: 1008/530, loss: 0.052614498883485794
2023-01-21 10:17:35.538243: step: 1012/530, loss: 0.12027569115161896
2023-01-21 10:17:36.656186: step: 1016/530, loss: 0.0188356414437294
2023-01-21 10:17:37.820845: step: 1020/530, loss: 0.4954391419887543
2023-01-21 10:17:38.955700: step: 1024/530, loss: 0.09468240290880203
2023-01-21 10:17:40.090138: step: 1028/530, loss: 0.09825067967176437
2023-01-21 10:17:41.224229: step: 1032/530, loss: 0.05871162563562393
2023-01-21 10:17:42.351995: step: 1036/530, loss: 0.05405168607831001
2023-01-21 10:17:43.496726: step: 1040/530, loss: 0.08131580054759979
2023-01-21 10:17:44.619059: step: 1044/530, loss: 0.0037410736549645662
2023-01-21 10:17:45.732446: step: 1048/530, loss: 0.05062122642993927
2023-01-21 10:17:46.862184: step: 1052/530, loss: 0.03069133684039116
2023-01-21 10:17:47.974442: step: 1056/530, loss: 0.1147225871682167
2023-01-21 10:17:49.116891: step: 1060/530, loss: 0.09318237006664276
2023-01-21 10:17:50.208727: step: 1064/530, loss: 0.2423088103532791
2023-01-21 10:17:51.325031: step: 1068/530, loss: 0.03568211942911148
2023-01-21 10:17:52.438350: step: 1072/530, loss: 0.012611103244125843
2023-01-21 10:17:53.566159: step: 1076/530, loss: 0.05418844148516655
2023-01-21 10:17:54.713387: step: 1080/530, loss: 0.04475107416510582
2023-01-21 10:17:55.806363: step: 1084/530, loss: 0.3632713258266449
2023-01-21 10:17:56.906218: step: 1088/530, loss: 0.024009324610233307
2023-01-21 10:17:57.997798: step: 1092/530, loss: 0.005177688784897327
2023-01-21 10:17:59.091833: step: 1096/530, loss: 0.09368596225976944
2023-01-21 10:18:00.226856: step: 1100/530, loss: 0.05512266233563423
2023-01-21 10:18:01.371560: step: 1104/530, loss: 0.011346627026796341
2023-01-21 10:18:02.478232: step: 1108/530, loss: 0.029341697692871094
2023-01-21 10:18:03.620556: step: 1112/530, loss: 0.03827638924121857
2023-01-21 10:18:04.746834: step: 1116/530, loss: 0.06597843021154404
2023-01-21 10:18:05.861672: step: 1120/530, loss: 0.006766128353774548
2023-01-21 10:18:07.004841: step: 1124/530, loss: 0.05839795991778374
2023-01-21 10:18:08.139682: step: 1128/530, loss: 0.04410533979535103
2023-01-21 10:18:09.276605: step: 1132/530, loss: 0.12106069922447205
2023-01-21 10:18:10.396364: step: 1136/530, loss: 0.03493161126971245
2023-01-21 10:18:11.504317: step: 1140/530, loss: 0.02443847618997097
2023-01-21 10:18:12.644847: step: 1144/530, loss: 0.035881903022527695
2023-01-21 10:18:13.802641: step: 1148/530, loss: 0.113833948969841
2023-01-21 10:18:14.915721: step: 1152/530, loss: 0.07648496329784393
2023-01-21 10:18:16.067969: step: 1156/530, loss: 0.0863349586725235
2023-01-21 10:18:17.201991: step: 1160/530, loss: 0.6466966867446899
2023-01-21 10:18:18.334199: step: 1164/530, loss: 0.06250123679637909
2023-01-21 10:18:19.452645: step: 1168/530, loss: 0.11098838597536087
2023-01-21 10:18:20.590618: step: 1172/530, loss: 0.07459316402673721
2023-01-21 10:18:21.694181: step: 1176/530, loss: 0.05114293098449707
2023-01-21 10:18:22.812963: step: 1180/530, loss: 1.2644160985946655
2023-01-21 10:18:23.933238: step: 1184/530, loss: 0.06528482586145401
2023-01-21 10:18:25.027581: step: 1188/530, loss: 0.08628320693969727
2023-01-21 10:18:26.134008: step: 1192/530, loss: 0.02360553853213787
2023-01-21 10:18:27.283334: step: 1196/530, loss: 0.014839936047792435
2023-01-21 10:18:28.423097: step: 1200/530, loss: 0.07058839499950409
2023-01-21 10:18:29.539293: step: 1204/530, loss: 0.0026111602783203125
2023-01-21 10:18:30.666177: step: 1208/530, loss: 0.04411683231592178
2023-01-21 10:18:31.790668: step: 1212/530, loss: 0.199140265583992
2023-01-21 10:18:32.946078: step: 1216/530, loss: 0.080120749771595
2023-01-21 10:18:34.075767: step: 1220/530, loss: 0.005340576637536287
2023-01-21 10:18:35.212824: step: 1224/530, loss: 0.01398096140474081
2023-01-21 10:18:36.309480: step: 1228/530, loss: 0.09265422821044922
2023-01-21 10:18:37.414762: step: 1232/530, loss: 0.09217549860477448
2023-01-21 10:18:38.547527: step: 1236/530, loss: 0.7396581172943115
2023-01-21 10:18:39.669533: step: 1240/530, loss: 0.16215386986732483
2023-01-21 10:18:40.792689: step: 1244/530, loss: 0.03207864984869957
2023-01-21 10:18:41.938734: step: 1248/530, loss: 0.1976570188999176
2023-01-21 10:18:43.086533: step: 1252/530, loss: 0.029663659632205963
2023-01-21 10:18:44.204504: step: 1256/530, loss: 0.05139150470495224
2023-01-21 10:18:45.332289: step: 1260/530, loss: 0.31529468297958374
2023-01-21 10:18:46.423502: step: 1264/530, loss: 0.09567108005285263
2023-01-21 10:18:47.590238: step: 1268/530, loss: 0.5147698521614075
2023-01-21 10:18:48.724600: step: 1272/530, loss: 0.06492443382740021
2023-01-21 10:18:49.859512: step: 1276/530, loss: 0.27599087357521057
2023-01-21 10:18:50.995192: step: 1280/530, loss: 0.07113823294639587
2023-01-21 10:18:52.087195: step: 1284/530, loss: 0.04100165516138077
2023-01-21 10:18:53.202819: step: 1288/530, loss: 0.01410763245075941
2023-01-21 10:18:54.323137: step: 1292/530, loss: 0.010512733832001686
2023-01-21 10:18:55.481112: step: 1296/530, loss: 0.0069130901247262955
2023-01-21 10:18:56.580183: step: 1300/530, loss: 0.05699882656335831
2023-01-21 10:18:57.740947: step: 1304/530, loss: 0.025124359875917435
2023-01-21 10:18:58.896944: step: 1308/530, loss: 0.013685036450624466
2023-01-21 10:19:00.028919: step: 1312/530, loss: 0.014512252993881702
2023-01-21 10:19:01.126383: step: 1316/530, loss: 0.04087622091174126
2023-01-21 10:19:02.305588: step: 1320/530, loss: 0.06798171997070312
2023-01-21 10:19:03.434612: step: 1324/530, loss: 0.10997334122657776
2023-01-21 10:19:04.545104: step: 1328/530, loss: 0.039987754076719284
2023-01-21 10:19:05.675568: step: 1332/530, loss: 0.027688980102539062
2023-01-21 10:19:06.815059: step: 1336/530, loss: 0.11296100914478302
2023-01-21 10:19:07.919418: step: 1340/530, loss: 0.01258707046508789
2023-01-21 10:19:09.020691: step: 1344/530, loss: 0.010766697116196156
2023-01-21 10:19:10.149903: step: 1348/530, loss: 0.009875917807221413
2023-01-21 10:19:11.287510: step: 1352/530, loss: 0.009843206033110619
2023-01-21 10:19:12.417368: step: 1356/530, loss: 0.056551504880189896
2023-01-21 10:19:13.560148: step: 1360/530, loss: 0.19640818238258362
2023-01-21 10:19:14.748626: step: 1364/530, loss: 0.1295129805803299
2023-01-21 10:19:15.869864: step: 1368/530, loss: 0.13788118958473206
2023-01-21 10:19:17.005066: step: 1372/530, loss: 0.020614244043827057
2023-01-21 10:19:18.125581: step: 1376/530, loss: 0.25282496213912964
2023-01-21 10:19:19.260263: step: 1380/530, loss: 0.03530731052160263
2023-01-21 10:19:20.371095: step: 1384/530, loss: 0.18435411155223846
2023-01-21 10:19:21.482207: step: 1388/530, loss: 0.10940217971801758
2023-01-21 10:19:22.669340: step: 1392/530, loss: 0.11272287368774414
2023-01-21 10:19:23.790205: step: 1396/530, loss: 0.1318398416042328
2023-01-21 10:19:24.937534: step: 1400/530, loss: 0.03157520294189453
2023-01-21 10:19:26.065834: step: 1404/530, loss: 0.008353996090590954
2023-01-21 10:19:27.207843: step: 1408/530, loss: 0.4283823072910309
2023-01-21 10:19:28.354285: step: 1412/530, loss: 0.10291337966918945
2023-01-21 10:19:29.458548: step: 1416/530, loss: 0.05410919338464737
2023-01-21 10:19:30.590789: step: 1420/530, loss: 0.04996194690465927
2023-01-21 10:19:31.696548: step: 1424/530, loss: 0.0653717964887619
2023-01-21 10:19:32.867566: step: 1428/530, loss: 0.06787414848804474
2023-01-21 10:19:33.978109: step: 1432/530, loss: 0.00700192479416728
2023-01-21 10:19:35.116313: step: 1436/530, loss: 0.1161777526140213
2023-01-21 10:19:36.259069: step: 1440/530, loss: 0.07731761783361435
2023-01-21 10:19:37.366551: step: 1444/530, loss: 0.07756614685058594
2023-01-21 10:19:38.509602: step: 1448/530, loss: 0.0411500446498394
2023-01-21 10:19:39.644632: step: 1452/530, loss: 0.1718452423810959
2023-01-21 10:19:40.758901: step: 1456/530, loss: 0.035085584968328476
2023-01-21 10:19:41.881672: step: 1460/530, loss: 0.002965736435726285
2023-01-21 10:19:43.027166: step: 1464/530, loss: 0.04071469232439995
2023-01-21 10:19:44.172364: step: 1468/530, loss: 0.07147331535816193
2023-01-21 10:19:45.310292: step: 1472/530, loss: 0.026366807520389557
2023-01-21 10:19:46.449025: step: 1476/530, loss: 0.06166896969079971
2023-01-21 10:19:47.583468: step: 1480/530, loss: 0.16291895508766174
2023-01-21 10:19:48.695283: step: 1484/530, loss: 0.07217002660036087
2023-01-21 10:19:49.821918: step: 1488/530, loss: 0.07616110146045685
2023-01-21 10:19:50.957890: step: 1492/530, loss: 0.04465656355023384
2023-01-21 10:19:52.072676: step: 1496/530, loss: 0.042730093002319336
2023-01-21 10:19:53.197403: step: 1500/530, loss: 0.008275412954390049
2023-01-21 10:19:54.318348: step: 1504/530, loss: 0.014320563524961472
2023-01-21 10:19:55.451756: step: 1508/530, loss: 0.022402573376893997
2023-01-21 10:19:56.547209: step: 1512/530, loss: 0.02273428626358509
2023-01-21 10:19:57.686498: step: 1516/530, loss: 0.07801590114831924
2023-01-21 10:19:58.801895: step: 1520/530, loss: 0.660473644733429
2023-01-21 10:19:59.904048: step: 1524/530, loss: 0.062969870865345
2023-01-21 10:20:01.041366: step: 1528/530, loss: 0.04149813577532768
2023-01-21 10:20:02.156856: step: 1532/530, loss: 0.534745991230011
2023-01-21 10:20:03.245507: step: 1536/530, loss: 0.04747038334608078
2023-01-21 10:20:04.366125: step: 1540/530, loss: 0.041450027376413345
2023-01-21 10:20:05.484974: step: 1544/530, loss: 0.002290964126586914
2023-01-21 10:20:06.612626: step: 1548/530, loss: 0.003115034196525812
2023-01-21 10:20:07.725775: step: 1552/530, loss: 0.0901481881737709
2023-01-21 10:20:08.854221: step: 1556/530, loss: 0.04049034044146538
2023-01-21 10:20:09.959660: step: 1560/530, loss: 0.06399927288293839
2023-01-21 10:20:11.083525: step: 1564/530, loss: 0.04926738888025284
2023-01-21 10:20:12.224398: step: 1568/530, loss: 0.06774749606847763
2023-01-21 10:20:13.402605: step: 1572/530, loss: 0.0345122329890728
2023-01-21 10:20:14.552204: step: 1576/530, loss: 0.004068565554916859
2023-01-21 10:20:15.687469: step: 1580/530, loss: 0.02066836506128311
2023-01-21 10:20:16.813501: step: 1584/530, loss: 0.0838892012834549
2023-01-21 10:20:17.948514: step: 1588/530, loss: 0.018881987780332565
2023-01-21 10:20:19.065117: step: 1592/530, loss: 0.09250137954950333
2023-01-21 10:20:20.212782: step: 1596/530, loss: 0.05074882507324219
2023-01-21 10:20:21.364636: step: 1600/530, loss: 0.00616983138024807
2023-01-21 10:20:22.496565: step: 1604/530, loss: 0.09350337833166122
2023-01-21 10:20:23.607206: step: 1608/530, loss: 0.024193860590457916
2023-01-21 10:20:24.731656: step: 1612/530, loss: 0.055021002888679504
2023-01-21 10:20:25.848025: step: 1616/530, loss: 0.6724486351013184
2023-01-21 10:20:26.967572: step: 1620/530, loss: 0.016064025461673737
2023-01-21 10:20:28.079914: step: 1624/530, loss: 0.05892963334918022
2023-01-21 10:20:29.193812: step: 1628/530, loss: 0.05799455568194389
2023-01-21 10:20:30.315688: step: 1632/530, loss: 0.09745702892541885
2023-01-21 10:20:31.418011: step: 1636/530, loss: 0.0015552043914794922
2023-01-21 10:20:32.595753: step: 1640/530, loss: 0.05822935327887535
2023-01-21 10:20:33.689210: step: 1644/530, loss: 0.025290869176387787
2023-01-21 10:20:34.816573: step: 1648/530, loss: 0.05255603790283203
2023-01-21 10:20:35.942486: step: 1652/530, loss: 0.020556354895234108
2023-01-21 10:20:37.063679: step: 1656/530, loss: 0.4559013247489929
2023-01-21 10:20:38.199841: step: 1660/530, loss: 0.02525482140481472
2023-01-21 10:20:39.322246: step: 1664/530, loss: 0.06422662734985352
2023-01-21 10:20:40.435959: step: 1668/530, loss: 0.12644276022911072
2023-01-21 10:20:41.555300: step: 1672/530, loss: 0.17926025390625
2023-01-21 10:20:42.689533: step: 1676/530, loss: 0.05211496353149414
2023-01-21 10:20:43.810588: step: 1680/530, loss: 0.16344602406024933
2023-01-21 10:20:44.930370: step: 1684/530, loss: 0.0701485201716423
2023-01-21 10:20:46.062165: step: 1688/530, loss: 0.043615687638521194
2023-01-21 10:20:47.221177: step: 1692/530, loss: 0.0025273323990404606
2023-01-21 10:20:48.355532: step: 1696/530, loss: 0.05736789479851723
2023-01-21 10:20:49.480169: step: 1700/530, loss: 0.04317808151245117
2023-01-21 10:20:50.606520: step: 1704/530, loss: 0.2833509147167206
2023-01-21 10:20:51.740599: step: 1708/530, loss: 0.07659697532653809
2023-01-21 10:20:52.853831: step: 1712/530, loss: 0.041161250323057175
2023-01-21 10:20:53.972885: step: 1716/530, loss: 0.06974592804908752
2023-01-21 10:20:55.078502: step: 1720/530, loss: 0.06852450221776962
2023-01-21 10:20:56.231563: step: 1724/530, loss: 0.0031832694076001644
2023-01-21 10:20:57.355259: step: 1728/530, loss: 0.020217228680849075
2023-01-21 10:20:58.527211: step: 1732/530, loss: 0.1470022201538086
2023-01-21 10:20:59.642736: step: 1736/530, loss: 0.011029482819139957
2023-01-21 10:21:00.737506: step: 1740/530, loss: 0.06349734216928482
2023-01-21 10:21:01.870754: step: 1744/530, loss: 0.08026114106178284
2023-01-21 10:21:02.992266: step: 1748/530, loss: 0.0418119877576828
2023-01-21 10:21:04.122769: step: 1752/530, loss: 0.04265284538269043
2023-01-21 10:21:05.236681: step: 1756/530, loss: 0.0036739350762218237
2023-01-21 10:21:06.374951: step: 1760/530, loss: 0.11331792175769806
2023-01-21 10:21:07.509126: step: 1764/530, loss: 0.14771810173988342
2023-01-21 10:21:08.673363: step: 1768/530, loss: 0.02606639824807644
2023-01-21 10:21:09.808085: step: 1772/530, loss: 0.05151662603020668
2023-01-21 10:21:10.964855: step: 1776/530, loss: 0.010968590155243874
2023-01-21 10:21:12.082626: step: 1780/530, loss: 0.029538821429014206
2023-01-21 10:21:13.182815: step: 1784/530, loss: 0.06696148216724396
2023-01-21 10:21:14.303539: step: 1788/530, loss: 0.051369860768318176
2023-01-21 10:21:15.456857: step: 1792/530, loss: 0.6859917044639587
2023-01-21 10:21:16.593384: step: 1796/530, loss: 0.06786274909973145
2023-01-21 10:21:17.730175: step: 1800/530, loss: 0.059851549565792084
2023-01-21 10:21:18.852532: step: 1804/530, loss: 0.044039536267519
2023-01-21 10:21:19.987979: step: 1808/530, loss: 0.009844970889389515
2023-01-21 10:21:21.091466: step: 1812/530, loss: 0.6420565843582153
2023-01-21 10:21:22.220395: step: 1816/530, loss: 0.04098225012421608
2023-01-21 10:21:23.350042: step: 1820/530, loss: 0.15927332639694214
2023-01-21 10:21:24.479781: step: 1824/530, loss: 0.160509392619133
2023-01-21 10:21:25.627816: step: 1828/530, loss: 0.12359962612390518
2023-01-21 10:21:26.745612: step: 1832/530, loss: 0.04187892749905586
2023-01-21 10:21:27.872075: step: 1836/530, loss: 0.016002655029296875
2023-01-21 10:21:28.993682: step: 1840/530, loss: 0.021069765090942383
2023-01-21 10:21:30.140504: step: 1844/530, loss: 0.1635255664587021
2023-01-21 10:21:31.267148: step: 1848/530, loss: 0.10742644965648651
2023-01-21 10:21:32.414181: step: 1852/530, loss: 0.10360260307788849
2023-01-21 10:21:33.529489: step: 1856/530, loss: 0.01583815924823284
2023-01-21 10:21:34.633757: step: 1860/530, loss: 0.012880707159638405
2023-01-21 10:21:35.765684: step: 1864/530, loss: 0.10445842891931534
2023-01-21 10:21:36.887708: step: 1868/530, loss: 0.027312923222780228
2023-01-21 10:21:38.011989: step: 1872/530, loss: 0.02525165118277073
2023-01-21 10:21:39.149572: step: 1876/530, loss: 0.22788628935813904
2023-01-21 10:21:40.254639: step: 1880/530, loss: 0.00774993933737278
2023-01-21 10:21:41.383170: step: 1884/530, loss: 0.04043865203857422
2023-01-21 10:21:42.507212: step: 1888/530, loss: 0.0032260895241051912
2023-01-21 10:21:43.665258: step: 1892/530, loss: 0.01276698149740696
2023-01-21 10:21:44.786647: step: 1896/530, loss: 0.08284330368041992
2023-01-21 10:21:45.919354: step: 1900/530, loss: 0.014325236901640892
2023-01-21 10:21:47.038622: step: 1904/530, loss: 0.07284488528966904
2023-01-21 10:21:48.148922: step: 1908/530, loss: 0.3223952353000641
2023-01-21 10:21:49.257768: step: 1912/530, loss: 0.06291351467370987
2023-01-21 10:21:50.385874: step: 1916/530, loss: 0.00580178527161479
2023-01-21 10:21:51.546164: step: 1920/530, loss: 0.0956028550863266
2023-01-21 10:21:52.695842: step: 1924/530, loss: 0.21865883469581604
2023-01-21 10:21:53.841439: step: 1928/530, loss: 0.08705687522888184
2023-01-21 10:21:54.986748: step: 1932/530, loss: 0.023654038086533546
2023-01-21 10:21:56.125387: step: 1936/530, loss: 0.29416608810424805
2023-01-21 10:21:57.264721: step: 1940/530, loss: 0.05245485529303551
2023-01-21 10:21:58.414753: step: 1944/530, loss: 0.08622479438781738
2023-01-21 10:21:59.555018: step: 1948/530, loss: 0.05781688541173935
2023-01-21 10:22:00.701849: step: 1952/530, loss: 0.06407561153173447
2023-01-21 10:22:01.841491: step: 1956/530, loss: 0.1016550064086914
2023-01-21 10:22:03.004922: step: 1960/530, loss: 0.04599037021398544
2023-01-21 10:22:04.174956: step: 1964/530, loss: 0.0449918732047081
2023-01-21 10:22:05.299686: step: 1968/530, loss: 0.025324631482362747
2023-01-21 10:22:06.404410: step: 1972/530, loss: 0.020659398287534714
2023-01-21 10:22:07.533970: step: 1976/530, loss: 0.07957782596349716
2023-01-21 10:22:08.652419: step: 1980/530, loss: 0.2930607497692108
2023-01-21 10:22:09.778362: step: 1984/530, loss: 0.0812654048204422
2023-01-21 10:22:10.948604: step: 1988/530, loss: 0.015449953265488148
2023-01-21 10:22:12.074525: step: 1992/530, loss: 0.09924278408288956
2023-01-21 10:22:13.192358: step: 1996/530, loss: 0.09803356975317001
2023-01-21 10:22:14.319183: step: 2000/530, loss: 0.8872809410095215
2023-01-21 10:22:15.453107: step: 2004/530, loss: 0.2716556489467621
2023-01-21 10:22:16.603835: step: 2008/530, loss: 0.15356646478176117
2023-01-21 10:22:17.737747: step: 2012/530, loss: 0.020653152838349342
2023-01-21 10:22:18.873518: step: 2016/530, loss: 0.08149471133947372
2023-01-21 10:22:20.005504: step: 2020/530, loss: 0.0851578414440155
2023-01-21 10:22:21.135570: step: 2024/530, loss: 0.032738495618104935
2023-01-21 10:22:22.288171: step: 2028/530, loss: 0.051030635833740234
2023-01-21 10:22:23.415206: step: 2032/530, loss: 0.011017322540283203
2023-01-21 10:22:24.565404: step: 2036/530, loss: 0.0707957074046135
2023-01-21 10:22:25.703508: step: 2040/530, loss: 0.01657099649310112
2023-01-21 10:22:26.884879: step: 2044/530, loss: 0.04788494110107422
2023-01-21 10:22:28.042376: step: 2048/530, loss: 0.058371927589178085
2023-01-21 10:22:29.209542: step: 2052/530, loss: 0.09562435746192932
2023-01-21 10:22:30.380397: step: 2056/530, loss: 0.10337600857019424
2023-01-21 10:22:31.528894: step: 2060/530, loss: 0.06824488937854767
2023-01-21 10:22:32.692078: step: 2064/530, loss: 0.037090301513671875
2023-01-21 10:22:33.851556: step: 2068/530, loss: 0.2514505386352539
2023-01-21 10:22:34.986134: step: 2072/530, loss: 0.07868289947509766
2023-01-21 10:22:36.134721: step: 2076/530, loss: 0.09531764686107635
2023-01-21 10:22:37.283883: step: 2080/530, loss: 0.08204317837953568
2023-01-21 10:22:38.423383: step: 2084/530, loss: 0.03345184400677681
2023-01-21 10:22:39.591790: step: 2088/530, loss: 0.158244326710701
2023-01-21 10:22:40.740472: step: 2092/530, loss: 0.024426650255918503
2023-01-21 10:22:41.849978: step: 2096/530, loss: 0.05949068069458008
2023-01-21 10:22:42.973350: step: 2100/530, loss: 0.6813151836395264
2023-01-21 10:22:44.113963: step: 2104/530, loss: 0.011803055182099342
2023-01-21 10:22:45.277960: step: 2108/530, loss: 0.053340815007686615
2023-01-21 10:22:46.425455: step: 2112/530, loss: 0.017792940139770508
2023-01-21 10:22:47.584653: step: 2116/530, loss: 0.0037843226455152035
2023-01-21 10:22:48.733185: step: 2120/530, loss: 1.2282586097717285
==================================================
Loss: 0.095
--------------------
Dev: {'event': {'p': 0.5675675675675675, 'r': 0.7829560585885486, 'f1': 0.6580861779518746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6069438491213031, 'r': 0.8091428571428572, 'f1': 0.6936076414401176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5340909090909091, 'r': 0.8703703703703703, 'f1': 0.6619718309859154}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.5671641791044776, 'r': 0.6031746031746031, 'f1': 0.5846153846153845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
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': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:23:31.639197: step: 4/530, loss: 0.01445770263671875
2023-01-21 10:23:32.800175: step: 8/530, loss: 0.03450345993041992
2023-01-21 10:23:33.951616: step: 12/530, loss: 0.07936783134937286
2023-01-21 10:23:35.083456: step: 16/530, loss: 0.012303435243666172
2023-01-21 10:23:36.254210: step: 20/530, loss: 0.02600078471004963
2023-01-21 10:23:37.382142: step: 24/530, loss: 0.039287663996219635
2023-01-21 10:23:38.506675: step: 28/530, loss: 0.08217611163854599
2023-01-21 10:23:39.652933: step: 32/530, loss: 0.0037899017333984375
2023-01-21 10:23:40.828327: step: 36/530, loss: 0.06696641445159912
2023-01-21 10:23:41.976784: step: 40/530, loss: 0.02762126922607422
2023-01-21 10:23:43.093398: step: 44/530, loss: 0.1270473450422287
2023-01-21 10:23:44.261353: step: 48/530, loss: 0.0277539249509573
2023-01-21 10:23:45.431972: step: 52/530, loss: 0.006583213806152344
2023-01-21 10:23:46.599378: step: 56/530, loss: 0.027288246899843216
2023-01-21 10:23:47.710609: step: 60/530, loss: 0.033304356038570404
2023-01-21 10:23:48.865471: step: 64/530, loss: 0.046938780695199966
2023-01-21 10:23:50.015511: step: 68/530, loss: 0.023034095764160156
2023-01-21 10:23:51.171087: step: 72/530, loss: 0.07793130725622177
2023-01-21 10:23:52.310293: step: 76/530, loss: 0.024054337292909622
2023-01-21 10:23:53.450813: step: 80/530, loss: 0.07088327407836914
2023-01-21 10:23:54.584380: step: 84/530, loss: 0.005694866180419922
2023-01-21 10:23:55.729355: step: 88/530, loss: 0.048822835087776184
2023-01-21 10:23:56.864197: step: 92/530, loss: 0.02551422268152237
2023-01-21 10:23:58.017036: step: 96/530, loss: 0.12112608551979065
2023-01-21 10:23:59.171639: step: 100/530, loss: 0.06975698471069336
2023-01-21 10:24:00.272550: step: 104/530, loss: 0.028263188898563385
2023-01-21 10:24:01.420782: step: 108/530, loss: 0.008280182257294655
2023-01-21 10:24:02.552552: step: 112/530, loss: 0.1454872041940689
2023-01-21 10:24:03.701903: step: 116/530, loss: 0.024723529815673828
2023-01-21 10:24:04.839907: step: 120/530, loss: 0.4002692997455597
2023-01-21 10:24:05.969995: step: 124/530, loss: 0.29019662737846375
2023-01-21 10:24:07.095751: step: 128/530, loss: 0.025742197409272194
2023-01-21 10:24:08.229037: step: 132/530, loss: 0.003211552044376731
2023-01-21 10:24:09.367722: step: 136/530, loss: 0.018715573474764824
2023-01-21 10:24:10.485884: step: 140/530, loss: 0.2575494945049286
2023-01-21 10:24:11.642102: step: 144/530, loss: 0.14548683166503906
2023-01-21 10:24:12.790741: step: 148/530, loss: 0.03913545608520508
2023-01-21 10:24:13.942076: step: 152/530, loss: 0.019583702087402344
2023-01-21 10:24:15.117448: step: 156/530, loss: 0.21997728943824768
2023-01-21 10:24:16.276737: step: 160/530, loss: 0.011895847506821156
2023-01-21 10:24:17.397316: step: 164/530, loss: 0.2892166078090668
2023-01-21 10:24:18.503328: step: 168/530, loss: 0.05348362773656845
2023-01-21 10:24:19.652673: step: 172/530, loss: 0.06256003677845001
2023-01-21 10:24:20.782622: step: 176/530, loss: 0.018559932708740234
2023-01-21 10:24:21.897041: step: 180/530, loss: 0.0371706523001194
2023-01-21 10:24:23.027844: step: 184/530, loss: 0.9415879249572754
2023-01-21 10:24:24.175439: step: 188/530, loss: 0.081817626953125
2023-01-21 10:24:25.328814: step: 192/530, loss: 0.019884299486875534
2023-01-21 10:24:26.474579: step: 196/530, loss: 0.05709486082196236
2023-01-21 10:24:27.617370: step: 200/530, loss: 0.07249286025762558
2023-01-21 10:24:28.729021: step: 204/530, loss: 0.011102485470473766
2023-01-21 10:24:29.856025: step: 208/530, loss: 0.1096406951546669
2023-01-21 10:24:31.047996: step: 212/530, loss: 0.08910264819860458
2023-01-21 10:24:32.179655: step: 216/530, loss: 0.2910998463630676
2023-01-21 10:24:33.312342: step: 220/530, loss: 0.05775747448205948
2023-01-21 10:24:34.438546: step: 224/530, loss: 0.0006633758312091231
2023-01-21 10:24:35.556912: step: 228/530, loss: 0.0011505603324621916
2023-01-21 10:24:36.685015: step: 232/530, loss: 0.09911108762025833
2023-01-21 10:24:37.827513: step: 236/530, loss: 0.06554313004016876
2023-01-21 10:24:38.987375: step: 240/530, loss: 0.02504882961511612
2023-01-21 10:24:40.112620: step: 244/530, loss: 0.10207463055849075
2023-01-21 10:24:41.229047: step: 248/530, loss: 0.04125576093792915
2023-01-21 10:24:42.372798: step: 252/530, loss: 0.08495473861694336
2023-01-21 10:24:43.508432: step: 256/530, loss: 0.04540920630097389
2023-01-21 10:24:44.661863: step: 260/530, loss: 0.1420988142490387
2023-01-21 10:24:45.835984: step: 264/530, loss: 0.03118143044412136
2023-01-21 10:24:46.952866: step: 268/530, loss: 0.10663948208093643
2023-01-21 10:24:48.106049: step: 272/530, loss: 0.011132621206343174
2023-01-21 10:24:49.242109: step: 276/530, loss: 0.027394961565732956
2023-01-21 10:24:50.357559: step: 280/530, loss: 0.07532797008752823
2023-01-21 10:24:51.468913: step: 284/530, loss: 0.13033714890480042
2023-01-21 10:24:52.617891: step: 288/530, loss: 0.051958370953798294
2023-01-21 10:24:53.736879: step: 292/530, loss: 0.009131526574492455
2023-01-21 10:24:54.869681: step: 296/530, loss: 0.0011385917896404862
2023-01-21 10:24:55.988421: step: 300/530, loss: 0.013597488403320312
2023-01-21 10:24:57.125460: step: 304/530, loss: 0.04292549937963486
2023-01-21 10:24:58.262892: step: 308/530, loss: 0.05222950130701065
2023-01-21 10:24:59.367119: step: 312/530, loss: 0.03021574206650257
2023-01-21 10:25:00.497824: step: 316/530, loss: 0.0709286704659462
2023-01-21 10:25:01.653553: step: 320/530, loss: 0.06238918378949165
2023-01-21 10:25:02.781862: step: 324/530, loss: 0.025046350434422493
2023-01-21 10:25:03.915781: step: 328/530, loss: 0.031374216079711914
2023-01-21 10:25:05.026598: step: 332/530, loss: 0.015353584662079811
2023-01-21 10:25:06.119996: step: 336/530, loss: 0.22220002114772797
2023-01-21 10:25:07.260052: step: 340/530, loss: 0.13547106087207794
2023-01-21 10:25:08.382922: step: 344/530, loss: 0.012132836505770683
2023-01-21 10:25:09.493499: step: 348/530, loss: 0.0672733336687088
2023-01-21 10:25:10.653857: step: 352/530, loss: 0.05815630033612251
2023-01-21 10:25:11.785228: step: 356/530, loss: 0.006888675503432751
2023-01-21 10:25:12.901415: step: 360/530, loss: 0.07691159844398499
2023-01-21 10:25:14.033197: step: 364/530, loss: 0.14771157503128052
2023-01-21 10:25:15.151925: step: 368/530, loss: 0.038546372205019
2023-01-21 10:25:16.285835: step: 372/530, loss: 0.02037830278277397
2023-01-21 10:25:17.406217: step: 376/530, loss: 0.013608884997665882
2023-01-21 10:25:18.529140: step: 380/530, loss: 0.16843700408935547
2023-01-21 10:25:19.644709: step: 384/530, loss: 0.016086386516690254
2023-01-21 10:25:20.750341: step: 388/530, loss: 0.013777637854218483
2023-01-21 10:25:21.875240: step: 392/530, loss: 0.003441238310188055
2023-01-21 10:25:22.997837: step: 396/530, loss: 0.07063465565443039
2023-01-21 10:25:24.116755: step: 400/530, loss: 0.207781121134758
2023-01-21 10:25:25.243096: step: 404/530, loss: 0.08404732495546341
2023-01-21 10:25:26.408028: step: 408/530, loss: 0.0668419897556305
2023-01-21 10:25:27.525366: step: 412/530, loss: 0.06274401396512985
2023-01-21 10:25:28.655107: step: 416/530, loss: 0.006211805157363415
2023-01-21 10:25:29.765979: step: 420/530, loss: 0.01486311573535204
2023-01-21 10:25:30.893613: step: 424/530, loss: 0.12865057587623596
2023-01-21 10:25:32.004140: step: 428/530, loss: 0.1546918898820877
2023-01-21 10:25:33.131349: step: 432/530, loss: 0.004378318786621094
2023-01-21 10:25:34.273249: step: 436/530, loss: 0.11989402770996094
2023-01-21 10:25:35.420617: step: 440/530, loss: 0.026608657091856003
2023-01-21 10:25:36.562467: step: 444/530, loss: 0.018164968118071556
2023-01-21 10:25:37.681649: step: 448/530, loss: 0.04957571253180504
2023-01-21 10:25:38.793754: step: 452/530, loss: 0.03682751581072807
2023-01-21 10:25:39.905814: step: 456/530, loss: 0.02497081831097603
2023-01-21 10:25:41.036914: step: 460/530, loss: 0.018630720674991608
2023-01-21 10:25:42.174335: step: 464/530, loss: 0.06690549850463867
2023-01-21 10:25:43.306969: step: 468/530, loss: 0.038674164563417435
2023-01-21 10:25:44.428985: step: 472/530, loss: 0.014288758859038353
2023-01-21 10:25:45.571814: step: 476/530, loss: 0.06731200218200684
2023-01-21 10:25:46.713621: step: 480/530, loss: 0.17412835359573364
2023-01-21 10:25:47.861913: step: 484/530, loss: 0.023894120007753372
2023-01-21 10:25:49.004842: step: 488/530, loss: 0.05509471893310547
2023-01-21 10:25:50.141018: step: 492/530, loss: 0.27944415807724
2023-01-21 10:25:51.293983: step: 496/530, loss: 0.051247790455818176
2023-01-21 10:25:52.415180: step: 500/530, loss: 0.1640431433916092
2023-01-21 10:25:53.552618: step: 504/530, loss: 0.020304251462221146
2023-01-21 10:25:54.673927: step: 508/530, loss: 0.009315062314271927
2023-01-21 10:25:55.820748: step: 512/530, loss: 0.03766131401062012
2023-01-21 10:25:56.914755: step: 516/530, loss: 0.03255338966846466
2023-01-21 10:25:58.036985: step: 520/530, loss: 0.019003022462129593
2023-01-21 10:25:59.174544: step: 524/530, loss: 0.00856394786387682
2023-01-21 10:26:00.284426: step: 528/530, loss: 0.08291111141443253
2023-01-21 10:26:01.401980: step: 532/530, loss: 0.0517425537109375
2023-01-21 10:26:02.524120: step: 536/530, loss: 0.0063506606966257095
2023-01-21 10:26:03.642224: step: 540/530, loss: 0.02998046949505806
2023-01-21 10:26:04.775035: step: 544/530, loss: 0.014499855227768421
2023-01-21 10:26:05.894756: step: 548/530, loss: 0.025513364002108574
2023-01-21 10:26:07.046637: step: 552/530, loss: 0.0032840727362781763
2023-01-21 10:26:08.217350: step: 556/530, loss: 0.06379013508558273
2023-01-21 10:26:09.344771: step: 560/530, loss: 0.027318669483065605
2023-01-21 10:26:10.527004: step: 564/530, loss: 0.18331317603588104
2023-01-21 10:26:11.667654: step: 568/530, loss: 0.0556914322078228
2023-01-21 10:26:12.805151: step: 572/530, loss: 0.01944875717163086
2023-01-21 10:26:13.937616: step: 576/530, loss: 0.05487499386072159
2023-01-21 10:26:15.071651: step: 580/530, loss: 0.01848888397216797
2023-01-21 10:26:16.226957: step: 584/530, loss: 0.10216408222913742
2023-01-21 10:26:17.319299: step: 588/530, loss: 0.03553037717938423
2023-01-21 10:26:18.474506: step: 592/530, loss: 0.026528263464570045
2023-01-21 10:26:19.585881: step: 596/530, loss: 0.0061918264254927635
2023-01-21 10:26:20.753114: step: 600/530, loss: 0.0188235305249691
2023-01-21 10:26:21.876825: step: 604/530, loss: 0.0622439831495285
2023-01-21 10:26:23.026474: step: 608/530, loss: 0.02280578576028347
2023-01-21 10:26:24.149039: step: 612/530, loss: 0.04630870744585991
2023-01-21 10:26:25.298824: step: 616/530, loss: 0.046742819249629974
2023-01-21 10:26:26.470878: step: 620/530, loss: 0.0693449079990387
2023-01-21 10:26:27.628528: step: 624/530, loss: 0.09341659396886826
2023-01-21 10:26:28.758350: step: 628/530, loss: 0.02776651456952095
2023-01-21 10:26:29.912601: step: 632/530, loss: 0.1390846222639084
2023-01-21 10:26:31.065219: step: 636/530, loss: 0.6937339901924133
2023-01-21 10:26:32.218018: step: 640/530, loss: 0.03495540842413902
2023-01-21 10:26:33.418336: step: 644/530, loss: 0.03575325012207031
2023-01-21 10:26:34.578810: step: 648/530, loss: 0.5459203720092773
2023-01-21 10:26:35.726864: step: 652/530, loss: 0.006506538018584251
2023-01-21 10:26:36.899878: step: 656/530, loss: 0.2865927517414093
2023-01-21 10:26:38.030799: step: 660/530, loss: 0.037972450256347656
2023-01-21 10:26:39.194489: step: 664/530, loss: 0.03791651874780655
2023-01-21 10:26:40.330193: step: 668/530, loss: 0.13957729935646057
2023-01-21 10:26:41.462512: step: 672/530, loss: 0.02175619639456272
2023-01-21 10:26:42.586940: step: 676/530, loss: 0.04468078538775444
2023-01-21 10:26:43.737244: step: 680/530, loss: 0.012370586395263672
2023-01-21 10:26:44.889805: step: 684/530, loss: 0.0033576965797692537
2023-01-21 10:26:46.018162: step: 688/530, loss: 0.019021224230527878
2023-01-21 10:26:47.167217: step: 692/530, loss: 0.013133621774613857
2023-01-21 10:26:48.345109: step: 696/530, loss: 0.1058053970336914
2023-01-21 10:26:49.481275: step: 700/530, loss: 0.062140658497810364
2023-01-21 10:26:50.617509: step: 704/530, loss: 0.02763814851641655
2023-01-21 10:26:51.757209: step: 708/530, loss: 0.03821153566241264
2023-01-21 10:26:52.891479: step: 712/530, loss: 0.07512583583593369
2023-01-21 10:26:54.050681: step: 716/530, loss: 0.12789902091026306
2023-01-21 10:26:55.170585: step: 720/530, loss: 0.019373273476958275
2023-01-21 10:26:56.312711: step: 724/530, loss: 0.025617599487304688
2023-01-21 10:26:57.457534: step: 728/530, loss: 0.011046218685805798
2023-01-21 10:26:58.604384: step: 732/530, loss: 0.039710428565740585
2023-01-21 10:26:59.752850: step: 736/530, loss: 0.00010223221033811569
2023-01-21 10:27:00.883409: step: 740/530, loss: 0.02292652055621147
2023-01-21 10:27:02.079397: step: 744/530, loss: 0.032210540026426315
2023-01-21 10:27:03.203043: step: 748/530, loss: 0.14425086975097656
2023-01-21 10:27:04.350299: step: 752/530, loss: 0.007232856936752796
2023-01-21 10:27:05.481227: step: 756/530, loss: 0.08457297831773758
2023-01-21 10:27:06.636711: step: 760/530, loss: 0.011852837167680264
2023-01-21 10:27:07.807995: step: 764/530, loss: 0.09369754791259766
2023-01-21 10:27:08.957794: step: 768/530, loss: 0.03629627078771591
2023-01-21 10:27:10.126429: step: 772/530, loss: 0.43800267577171326
2023-01-21 10:27:11.254774: step: 776/530, loss: 0.05042581632733345
2023-01-21 10:27:12.393968: step: 780/530, loss: 0.026218559592962265
2023-01-21 10:27:13.526411: step: 784/530, loss: 0.030567217618227005
2023-01-21 10:27:14.674316: step: 788/530, loss: 0.6515905261039734
2023-01-21 10:27:15.824637: step: 792/530, loss: 0.02814474143087864
2023-01-21 10:27:16.961800: step: 796/530, loss: 0.04781952127814293
2023-01-21 10:27:18.103457: step: 800/530, loss: 0.08095154166221619
2023-01-21 10:27:19.233322: step: 804/530, loss: 0.04170503839850426
2023-01-21 10:27:20.383114: step: 808/530, loss: 0.04887457191944122
2023-01-21 10:27:21.543922: step: 812/530, loss: 0.101282499730587
2023-01-21 10:27:22.686267: step: 816/530, loss: 0.0029612542130053043
2023-01-21 10:27:23.826967: step: 820/530, loss: 0.0007656335947103798
2023-01-21 10:27:24.960190: step: 824/530, loss: 0.10248041152954102
2023-01-21 10:27:26.096119: step: 828/530, loss: 0.06279736012220383
2023-01-21 10:27:27.259136: step: 832/530, loss: 0.01447677705436945
2023-01-21 10:27:28.368638: step: 836/530, loss: 0.03201131895184517
2023-01-21 10:27:29.498879: step: 840/530, loss: 0.014046764001250267
2023-01-21 10:27:30.650670: step: 844/530, loss: 0.0996561050415039
2023-01-21 10:27:31.777675: step: 848/530, loss: 0.03612957149744034
2023-01-21 10:27:32.887065: step: 852/530, loss: 0.020800210535526276
2023-01-21 10:27:34.097381: step: 856/530, loss: 0.00274581927806139
2023-01-21 10:27:35.222038: step: 860/530, loss: 0.030065441504120827
2023-01-21 10:27:36.363916: step: 864/530, loss: 0.0040302276611328125
2023-01-21 10:27:37.498109: step: 868/530, loss: 0.00771408062428236
2023-01-21 10:27:38.632611: step: 872/530, loss: 0.12622594833374023
2023-01-21 10:27:39.781644: step: 876/530, loss: 0.007862758822739124
2023-01-21 10:27:40.918423: step: 880/530, loss: 0.2506319284439087
2023-01-21 10:27:42.093135: step: 884/530, loss: 0.10726174712181091
2023-01-21 10:27:43.206085: step: 888/530, loss: 0.04552764818072319
2023-01-21 10:27:44.328903: step: 892/530, loss: 0.018457986414432526
2023-01-21 10:27:45.462643: step: 896/530, loss: 0.0013124465476721525
2023-01-21 10:27:46.593634: step: 900/530, loss: 0.2510325312614441
2023-01-21 10:27:47.718410: step: 904/530, loss: 0.04855804517865181
2023-01-21 10:27:48.854726: step: 908/530, loss: 0.09022665023803711
2023-01-21 10:27:49.969496: step: 912/530, loss: 0.0936279296875
2023-01-21 10:27:51.096847: step: 916/530, loss: 0.07424610108137131
2023-01-21 10:27:52.211799: step: 920/530, loss: 0.03892498090863228
2023-01-21 10:27:53.336016: step: 924/530, loss: 0.05424042046070099
2023-01-21 10:27:54.466515: step: 928/530, loss: 0.016835279762744904
2023-01-21 10:27:55.630413: step: 932/530, loss: 0.009508704766631126
2023-01-21 10:27:56.758779: step: 936/530, loss: 0.11599965393543243
2023-01-21 10:27:57.925463: step: 940/530, loss: 0.020278453826904297
2023-01-21 10:27:59.089620: step: 944/530, loss: 0.036522772163152695
2023-01-21 10:28:00.219913: step: 948/530, loss: 0.07682456821203232
2023-01-21 10:28:01.378028: step: 952/530, loss: 0.1798015534877777
2023-01-21 10:28:02.496805: step: 956/530, loss: 0.01995849795639515
2023-01-21 10:28:03.637068: step: 960/530, loss: 0.10105772316455841
2023-01-21 10:28:04.794407: step: 964/530, loss: 0.15047797560691833
2023-01-21 10:28:06.001990: step: 968/530, loss: 0.09532566368579865
2023-01-21 10:28:07.177084: step: 972/530, loss: 0.030692197382450104
2023-01-21 10:28:08.296952: step: 976/530, loss: 0.05657653883099556
2023-01-21 10:28:09.445134: step: 980/530, loss: 0.06002149358391762
2023-01-21 10:28:10.564295: step: 984/530, loss: 0.02169513702392578
2023-01-21 10:28:11.705737: step: 988/530, loss: 0.038320064544677734
2023-01-21 10:28:12.831930: step: 992/530, loss: 0.08170090615749359
2023-01-21 10:28:13.988023: step: 996/530, loss: 0.0005859375232830644
2023-01-21 10:28:15.137925: step: 1000/530, loss: 0.009829336777329445
2023-01-21 10:28:16.274747: step: 1004/530, loss: 0.00011296272714389488
2023-01-21 10:28:17.395918: step: 1008/530, loss: 0.016820382326841354
2023-01-21 10:28:18.520027: step: 1012/530, loss: 0.0171248447149992
2023-01-21 10:28:19.679963: step: 1016/530, loss: 0.10330505669116974
2023-01-21 10:28:20.811888: step: 1020/530, loss: 0.02688894420862198
2023-01-21 10:28:21.976127: step: 1024/530, loss: 0.003786420915275812
2023-01-21 10:28:23.129068: step: 1028/530, loss: 0.0174394603818655
2023-01-21 10:28:24.266414: step: 1032/530, loss: 0.011028338223695755
2023-01-21 10:28:25.418791: step: 1036/530, loss: 0.018026208505034447
2023-01-21 10:28:26.553244: step: 1040/530, loss: 0.07739534974098206
2023-01-21 10:28:27.716033: step: 1044/530, loss: 0.01706256903707981
2023-01-21 10:28:28.860537: step: 1048/530, loss: 0.0266692154109478
2023-01-21 10:28:30.031179: step: 1052/530, loss: 0.07829628139734268
2023-01-21 10:28:31.201809: step: 1056/530, loss: 0.019511796534061432
2023-01-21 10:28:32.340711: step: 1060/530, loss: 0.002972221467643976
2023-01-21 10:28:33.472874: step: 1064/530, loss: 0.03808288648724556
2023-01-21 10:28:34.619548: step: 1068/530, loss: 0.40817755460739136
2023-01-21 10:28:35.741206: step: 1072/530, loss: 0.08213977515697479
2023-01-21 10:28:36.880180: step: 1076/530, loss: 0.14943495392799377
2023-01-21 10:28:38.036500: step: 1080/530, loss: 0.0157381072640419
2023-01-21 10:28:39.178628: step: 1084/530, loss: 0.004616069607436657
2023-01-21 10:28:40.312450: step: 1088/530, loss: 0.07865428924560547
2023-01-21 10:28:41.455494: step: 1092/530, loss: 0.11023406684398651
2023-01-21 10:28:42.608181: step: 1096/530, loss: 0.07896137237548828
2023-01-21 10:28:43.753477: step: 1100/530, loss: 0.193163201212883
2023-01-21 10:28:44.870423: step: 1104/530, loss: 0.21725492179393768
2023-01-21 10:28:46.001174: step: 1108/530, loss: 0.01814866065979004
2023-01-21 10:28:47.140099: step: 1112/530, loss: 0.0029195784591138363
2023-01-21 10:28:48.249644: step: 1116/530, loss: 0.0165436752140522
2023-01-21 10:28:49.401911: step: 1120/530, loss: 0.02433796040713787
2023-01-21 10:28:50.562904: step: 1124/530, loss: 0.01960843987762928
2023-01-21 10:28:51.742533: step: 1128/530, loss: 0.028461933135986328
2023-01-21 10:28:52.880996: step: 1132/530, loss: 0.05832348018884659
2023-01-21 10:28:54.026273: step: 1136/530, loss: 0.0003609657287597656
2023-01-21 10:28:55.161743: step: 1140/530, loss: 0.008929729461669922
2023-01-21 10:28:56.304901: step: 1144/530, loss: 0.07246923446655273
2023-01-21 10:28:57.469747: step: 1148/530, loss: 0.010180855169892311
2023-01-21 10:28:58.610790: step: 1152/530, loss: 0.05389556661248207
2023-01-21 10:28:59.749992: step: 1156/530, loss: 0.011961890384554863
2023-01-21 10:29:00.930927: step: 1160/530, loss: 0.0748300552368164
2023-01-21 10:29:02.038112: step: 1164/530, loss: 0.0465640053153038
2023-01-21 10:29:03.166981: step: 1168/530, loss: 0.10560932010412216
2023-01-21 10:29:04.294504: step: 1172/530, loss: 0.03892073780298233
2023-01-21 10:29:05.449336: step: 1176/530, loss: 0.031076718121767044
2023-01-21 10:29:06.598665: step: 1180/530, loss: 0.02347918599843979
2023-01-21 10:29:07.733123: step: 1184/530, loss: 0.07828617095947266
2023-01-21 10:29:08.962048: step: 1188/530, loss: 0.1742088347673416
2023-01-21 10:29:10.148749: step: 1192/530, loss: 0.035913847386837006
2023-01-21 10:29:11.311306: step: 1196/530, loss: 0.006459998898208141
2023-01-21 10:29:12.459925: step: 1200/530, loss: 0.024181175976991653
2023-01-21 10:29:13.625337: step: 1204/530, loss: 0.042345236986875534
2023-01-21 10:29:14.792053: step: 1208/530, loss: 0.003262949176132679
2023-01-21 10:29:15.907589: step: 1212/530, loss: 0.11211252212524414
2023-01-21 10:29:17.071617: step: 1216/530, loss: 0.02284984663128853
2023-01-21 10:29:18.199760: step: 1220/530, loss: 0.04695471376180649
2023-01-21 10:29:19.322695: step: 1224/530, loss: 0.012668800540268421
2023-01-21 10:29:20.467557: step: 1228/530, loss: 0.1259150505065918
2023-01-21 10:29:21.610722: step: 1232/530, loss: 0.09182815998792648
2023-01-21 10:29:22.727564: step: 1236/530, loss: 0.030479764565825462
2023-01-21 10:29:23.866535: step: 1240/530, loss: 0.0050123692490160465
2023-01-21 10:29:24.994904: step: 1244/530, loss: 0.0282166488468647
2023-01-21 10:29:26.116909: step: 1248/530, loss: 0.0700405165553093
2023-01-21 10:29:27.275604: step: 1252/530, loss: 0.009382152929902077
2023-01-21 10:29:28.432416: step: 1256/530, loss: 0.030722713097929955
2023-01-21 10:29:29.603163: step: 1260/530, loss: 0.06939296424388885
2023-01-21 10:29:30.745397: step: 1264/530, loss: 0.047120094299316406
2023-01-21 10:29:31.874052: step: 1268/530, loss: 0.05680961534380913
2023-01-21 10:29:33.018633: step: 1272/530, loss: 0.06423606723546982
2023-01-21 10:29:34.151156: step: 1276/530, loss: 0.06578169018030167
2023-01-21 10:29:35.321371: step: 1280/530, loss: 0.008302784524857998
2023-01-21 10:29:36.440512: step: 1284/530, loss: 0.006422996520996094
2023-01-21 10:29:37.638637: step: 1288/530, loss: 0.025800514966249466
2023-01-21 10:29:38.791161: step: 1292/530, loss: 0.04233236610889435
2023-01-21 10:29:39.936052: step: 1296/530, loss: 0.00080194475594908
2023-01-21 10:29:41.069383: step: 1300/530, loss: 0.017215585336089134
2023-01-21 10:29:42.225838: step: 1304/530, loss: 0.049330711364746094
2023-01-21 10:29:43.391746: step: 1308/530, loss: 0.042549800127744675
2023-01-21 10:29:44.545953: step: 1312/530, loss: 0.052066802978515625
2023-01-21 10:29:45.697465: step: 1316/530, loss: 0.04202727973461151
2023-01-21 10:29:46.847472: step: 1320/530, loss: 0.06000897288322449
2023-01-21 10:29:47.982636: step: 1324/530, loss: 0.20177088677883148
2023-01-21 10:29:49.104434: step: 1328/530, loss: 0.051516056060791016
2023-01-21 10:29:50.247260: step: 1332/530, loss: 0.021866250783205032
2023-01-21 10:29:51.389943: step: 1336/530, loss: 0.02463226579129696
2023-01-21 10:29:52.527451: step: 1340/530, loss: 0.03839721903204918
2023-01-21 10:29:53.707739: step: 1344/530, loss: 0.03847694396972656
2023-01-21 10:29:54.849782: step: 1348/530, loss: 0.06000366061925888
2023-01-21 10:29:56.003953: step: 1352/530, loss: 0.0593835823237896
2023-01-21 10:29:57.158509: step: 1356/530, loss: 0.050646498799324036
2023-01-21 10:29:58.316569: step: 1360/530, loss: 0.009618950076401234
2023-01-21 10:29:59.501024: step: 1364/530, loss: 0.05122070387005806
2023-01-21 10:30:00.620192: step: 1368/530, loss: 0.028808213770389557
2023-01-21 10:30:01.767109: step: 1372/530, loss: 0.17811298370361328
2023-01-21 10:30:02.905427: step: 1376/530, loss: 0.03187117353081703
2023-01-21 10:30:04.042959: step: 1380/530, loss: 0.040517520159482956
2023-01-21 10:30:05.201604: step: 1384/530, loss: 0.640001654624939
2023-01-21 10:30:06.362128: step: 1388/530, loss: 0.044702719897031784
2023-01-21 10:30:07.492531: step: 1392/530, loss: 0.05064759403467178
2023-01-21 10:30:08.637795: step: 1396/530, loss: 0.06525421142578125
2023-01-21 10:30:09.768754: step: 1400/530, loss: 0.046235181391239166
2023-01-21 10:30:10.911459: step: 1404/530, loss: 0.024970628321170807
2023-01-21 10:30:12.046236: step: 1408/530, loss: 0.019870664924383163
2023-01-21 10:30:13.188724: step: 1412/530, loss: 0.1729743927717209
2023-01-21 10:30:14.318781: step: 1416/530, loss: 0.05711031332612038
2023-01-21 10:30:15.456561: step: 1420/530, loss: 0.07533387839794159
2023-01-21 10:30:16.570063: step: 1424/530, loss: 0.030455783009529114
2023-01-21 10:30:17.725070: step: 1428/530, loss: 0.0289122574031353
2023-01-21 10:30:18.886107: step: 1432/530, loss: 0.10187626630067825
2023-01-21 10:30:20.037141: step: 1436/530, loss: 0.03603868559002876
2023-01-21 10:30:21.183054: step: 1440/530, loss: 0.03162336349487305
2023-01-21 10:30:22.337951: step: 1444/530, loss: 0.020629405975341797
2023-01-21 10:30:23.480745: step: 1448/530, loss: 0.12042804062366486
2023-01-21 10:30:24.604791: step: 1452/530, loss: 0.03444423899054527
2023-01-21 10:30:25.741872: step: 1456/530, loss: 0.0018639564514160156
2023-01-21 10:30:26.894973: step: 1460/530, loss: 0.058011531829833984
2023-01-21 10:30:28.055533: step: 1464/530, loss: 0.276532918214798
2023-01-21 10:30:29.247183: step: 1468/530, loss: 0.145494282245636
2023-01-21 10:30:30.378037: step: 1472/530, loss: 0.03534507751464844
2023-01-21 10:30:31.518693: step: 1476/530, loss: 0.05287494510412216
2023-01-21 10:30:32.668694: step: 1480/530, loss: 0.04884395748376846
2023-01-21 10:30:33.808061: step: 1484/530, loss: 0.011091279797255993
2023-01-21 10:30:34.957120: step: 1488/530, loss: 0.010197639465332031
2023-01-21 10:30:36.111288: step: 1492/530, loss: 0.06927052140235901
2023-01-21 10:30:37.243273: step: 1496/530, loss: 0.05755405128002167
2023-01-21 10:30:38.428527: step: 1500/530, loss: 0.02384796179831028
2023-01-21 10:30:39.563104: step: 1504/530, loss: 0.5944212079048157
2023-01-21 10:30:40.709394: step: 1508/530, loss: 0.060752034187316895
2023-01-21 10:30:41.859133: step: 1512/530, loss: 0.10176029801368713
2023-01-21 10:30:42.993228: step: 1516/530, loss: 0.00897760409861803
2023-01-21 10:30:44.123439: step: 1520/530, loss: 0.096531942486763
2023-01-21 10:30:45.279399: step: 1524/530, loss: 0.02178940922021866
2023-01-21 10:30:46.432627: step: 1528/530, loss: 0.14092516899108887
2023-01-21 10:30:47.576376: step: 1532/530, loss: 0.04464459419250488
2023-01-21 10:30:48.698477: step: 1536/530, loss: 0.05871257930994034
2023-01-21 10:30:49.835264: step: 1540/530, loss: 0.008302975445985794
2023-01-21 10:30:50.975006: step: 1544/530, loss: 0.19416749477386475
2023-01-21 10:30:52.115765: step: 1548/530, loss: 0.027652930468320847
2023-01-21 10:30:53.300666: step: 1552/530, loss: 0.02328796312212944
2023-01-21 10:30:54.422844: step: 1556/530, loss: 0.0266539566218853
2023-01-21 10:30:55.552229: step: 1560/530, loss: 0.03760109096765518
2023-01-21 10:30:56.683138: step: 1564/530, loss: 0.11218070983886719
2023-01-21 10:30:57.811746: step: 1568/530, loss: 0.10916433483362198
2023-01-21 10:30:58.942588: step: 1572/530, loss: 0.03420887142419815
2023-01-21 10:31:00.094411: step: 1576/530, loss: 0.021595347672700882
2023-01-21 10:31:01.237328: step: 1580/530, loss: 0.06901824474334717
2023-01-21 10:31:02.418213: step: 1584/530, loss: 0.02319660224020481
2023-01-21 10:31:03.548467: step: 1588/530, loss: 0.02566986158490181
2023-01-21 10:31:04.678735: step: 1592/530, loss: 0.04655332863330841
2023-01-21 10:31:05.817204: step: 1596/530, loss: 0.031061720103025436
2023-01-21 10:31:06.932103: step: 1600/530, loss: 0.2984463572502136
2023-01-21 10:31:08.089366: step: 1604/530, loss: 0.04659252241253853
2023-01-21 10:31:09.221377: step: 1608/530, loss: 0.015270424075424671
2023-01-21 10:31:10.368532: step: 1612/530, loss: 0.024371527135372162
2023-01-21 10:31:11.502290: step: 1616/530, loss: 0.15676327049732208
2023-01-21 10:31:12.618298: step: 1620/530, loss: 0.17237024009227753
2023-01-21 10:31:13.763695: step: 1624/530, loss: 0.05896444618701935
2023-01-21 10:31:14.918701: step: 1628/530, loss: 0.10925626754760742
2023-01-21 10:31:16.056155: step: 1632/530, loss: 0.06329164654016495
2023-01-21 10:31:17.214729: step: 1636/530, loss: 0.13272634148597717
2023-01-21 10:31:18.335634: step: 1640/530, loss: 0.01004729326814413
2023-01-21 10:31:19.490690: step: 1644/530, loss: 0.10683955997228622
2023-01-21 10:31:20.640998: step: 1648/530, loss: 0.02809314802289009
2023-01-21 10:31:21.775772: step: 1652/530, loss: 0.01524581853300333
2023-01-21 10:31:22.960554: step: 1656/530, loss: 0.10205049812793732
2023-01-21 10:31:24.083999: step: 1660/530, loss: 0.09389620274305344
2023-01-21 10:31:25.228997: step: 1664/530, loss: 0.06841736286878586
2023-01-21 10:31:26.371246: step: 1668/530, loss: 0.022959517315030098
2023-01-21 10:31:27.526051: step: 1672/530, loss: 0.07232954353094101
2023-01-21 10:31:28.665534: step: 1676/530, loss: 0.06563596427440643
2023-01-21 10:31:29.782296: step: 1680/530, loss: 0.05518674850463867
2023-01-21 10:31:30.928933: step: 1684/530, loss: 0.05053729936480522
2023-01-21 10:31:32.084341: step: 1688/530, loss: 0.1637769639492035
2023-01-21 10:31:33.186124: step: 1692/530, loss: 0.03731890022754669
2023-01-21 10:31:34.344154: step: 1696/530, loss: 0.06530562043190002
2023-01-21 10:31:35.476629: step: 1700/530, loss: 0.01639573462307453
2023-01-21 10:31:36.612576: step: 1704/530, loss: 0.99970543384552
2023-01-21 10:31:37.765728: step: 1708/530, loss: 0.03499565273523331
2023-01-21 10:31:38.898251: step: 1712/530, loss: 0.0360812172293663
2023-01-21 10:31:40.021443: step: 1716/530, loss: 0.02043433114886284
2023-01-21 10:31:41.149081: step: 1720/530, loss: 0.04056520760059357
2023-01-21 10:31:42.316109: step: 1724/530, loss: 0.06651439517736435
2023-01-21 10:31:43.447529: step: 1728/530, loss: 0.020090769976377487
2023-01-21 10:31:44.568583: step: 1732/530, loss: 0.021418048068881035
2023-01-21 10:31:45.707575: step: 1736/530, loss: 0.06156749650835991
2023-01-21 10:31:46.837126: step: 1740/530, loss: 0.10172872990369797
2023-01-21 10:31:47.977224: step: 1744/530, loss: 0.16617614030838013
2023-01-21 10:31:49.164490: step: 1748/530, loss: 0.4521685838699341
2023-01-21 10:31:50.315246: step: 1752/530, loss: 0.09275803714990616
2023-01-21 10:31:51.481953: step: 1756/530, loss: 0.12140293419361115
2023-01-21 10:31:52.639204: step: 1760/530, loss: 0.12638473510742188
2023-01-21 10:31:53.774577: step: 1764/530, loss: 0.07202653586864471
2023-01-21 10:31:54.919004: step: 1768/530, loss: 0.6037311553955078
2023-01-21 10:31:56.068237: step: 1772/530, loss: 0.021046781912446022
2023-01-21 10:31:57.216630: step: 1776/530, loss: 0.019855499267578125
2023-01-21 10:31:58.373802: step: 1780/530, loss: 0.27081823348999023
2023-01-21 10:31:59.530013: step: 1784/530, loss: 0.0345311164855957
2023-01-21 10:32:00.649861: step: 1788/530, loss: 0.3245789706707001
2023-01-21 10:32:01.782472: step: 1792/530, loss: 0.04525794833898544
2023-01-21 10:32:02.946086: step: 1796/530, loss: 0.11900676786899567
2023-01-21 10:32:04.091068: step: 1800/530, loss: 0.09945344924926758
2023-01-21 10:32:05.248704: step: 1804/530, loss: 0.04015503078699112
2023-01-21 10:32:06.392805: step: 1808/530, loss: 0.030086733400821686
2023-01-21 10:32:07.502889: step: 1812/530, loss: 0.05636558309197426
2023-01-21 10:32:08.677975: step: 1816/530, loss: 0.013280868530273438
2023-01-21 10:32:09.829321: step: 1820/530, loss: 0.00011157989501953125
2023-01-21 10:32:10.955237: step: 1824/530, loss: 0.10377340018749237
2023-01-21 10:32:12.099727: step: 1828/530, loss: 0.024784373119473457
2023-01-21 10:32:13.265799: step: 1832/530, loss: 0.08820071071386337
2023-01-21 10:32:14.397576: step: 1836/530, loss: 0.03144865110516548
2023-01-21 10:32:15.535800: step: 1840/530, loss: 0.00724840210750699
2023-01-21 10:32:16.679754: step: 1844/530, loss: 0.10830254852771759
2023-01-21 10:32:17.814175: step: 1848/530, loss: 0.066503144800663
2023-01-21 10:32:18.948521: step: 1852/530, loss: 0.02907257154583931
2023-01-21 10:32:20.081996: step: 1856/530, loss: 0.04058127477765083
2023-01-21 10:32:21.228249: step: 1860/530, loss: 0.09039421379566193
2023-01-21 10:32:22.388944: step: 1864/530, loss: 0.07128114253282547
2023-01-21 10:32:23.524086: step: 1868/530, loss: 1.153980016708374
2023-01-21 10:32:24.722084: step: 1872/530, loss: 0.08205990493297577
2023-01-21 10:32:25.861824: step: 1876/530, loss: 0.02853412739932537
2023-01-21 10:32:26.987682: step: 1880/530, loss: 0.0814666748046875
2023-01-21 10:32:28.115679: step: 1884/530, loss: 0.02749776840209961
2023-01-21 10:32:29.254286: step: 1888/530, loss: 0.07677202671766281
2023-01-21 10:32:30.379973: step: 1892/530, loss: 0.04359283670783043
2023-01-21 10:32:31.497952: step: 1896/530, loss: 0.043320465832948685
2023-01-21 10:32:32.634208: step: 1900/530, loss: 0.0574478916823864
2023-01-21 10:32:33.779337: step: 1904/530, loss: 0.03754854202270508
2023-01-21 10:32:34.932919: step: 1908/530, loss: 0.0698099136352539
2023-01-21 10:32:36.084530: step: 1912/530, loss: 0.01396979484707117
2023-01-21 10:32:37.230187: step: 1916/530, loss: 0.02376404032111168
2023-01-21 10:32:38.395297: step: 1920/530, loss: 0.08164024353027344
2023-01-21 10:32:39.515937: step: 1924/530, loss: 0.05492382124066353
2023-01-21 10:32:40.667556: step: 1928/530, loss: 0.02073955535888672
2023-01-21 10:32:41.809146: step: 1932/530, loss: 0.001667881035245955
2023-01-21 10:32:42.936204: step: 1936/530, loss: 0.041443921625614166
2023-01-21 10:32:44.067050: step: 1940/530, loss: 0.3478538393974304
2023-01-21 10:32:45.176711: step: 1944/530, loss: 0.10430584102869034
2023-01-21 10:32:46.292182: step: 1948/530, loss: 0.281054824590683
2023-01-21 10:32:47.444053: step: 1952/530, loss: 0.034300997853279114
2023-01-21 10:32:48.588835: step: 1956/530, loss: 0.03845549002289772
2023-01-21 10:32:49.726644: step: 1960/530, loss: 3.0636723041534424
2023-01-21 10:32:50.848331: step: 1964/530, loss: 0.08521699905395508
2023-01-21 10:32:51.987969: step: 1968/530, loss: 0.036104965955019
2023-01-21 10:32:53.110077: step: 1972/530, loss: 0.12650585174560547
2023-01-21 10:32:54.287921: step: 1976/530, loss: 0.0829019546508789
2023-01-21 10:32:55.470442: step: 1980/530, loss: 0.1659226417541504
2023-01-21 10:32:56.616196: step: 1984/530, loss: 0.04490480571985245
2023-01-21 10:32:57.735756: step: 1988/530, loss: 0.23819756507873535
2023-01-21 10:32:58.872645: step: 1992/530, loss: 0.08589334785938263
2023-01-21 10:32:59.978135: step: 1996/530, loss: 0.01590270921587944
2023-01-21 10:33:01.127327: step: 2000/530, loss: 0.4315044581890106
2023-01-21 10:33:02.266818: step: 2004/530, loss: 0.051927998661994934
2023-01-21 10:33:03.400107: step: 2008/530, loss: 0.028842829167842865
2023-01-21 10:33:04.551447: step: 2012/530, loss: 0.02912616729736328
2023-01-21 10:33:05.679019: step: 2016/530, loss: 0.04855956882238388
2023-01-21 10:33:06.825686: step: 2020/530, loss: 0.04493856430053711
2023-01-21 10:33:07.975326: step: 2024/530, loss: 0.010172081179916859
2023-01-21 10:33:09.166900: step: 2028/530, loss: 0.12167644500732422
2023-01-21 10:33:10.349424: step: 2032/530, loss: 0.019178105518221855
2023-01-21 10:33:11.459464: step: 2036/530, loss: 0.05155201256275177
2023-01-21 10:33:12.599020: step: 2040/530, loss: 0.0021677971817553043
2023-01-21 10:33:13.762037: step: 2044/530, loss: 0.06638431549072266
2023-01-21 10:33:14.951884: step: 2048/530, loss: 0.01248855609446764
2023-01-21 10:33:16.082469: step: 2052/530, loss: 0.13607816398143768
2023-01-21 10:33:17.202096: step: 2056/530, loss: 0.03781623765826225
2023-01-21 10:33:18.363171: step: 2060/530, loss: 0.03121051751077175
2023-01-21 10:33:19.529283: step: 2064/530, loss: 0.036220550537109375
2023-01-21 10:33:20.672623: step: 2068/530, loss: 0.03292284160852432
2023-01-21 10:33:21.787227: step: 2072/530, loss: 7.696151442360133e-05
2023-01-21 10:33:22.942290: step: 2076/530, loss: 0.17656850814819336
2023-01-21 10:33:24.069752: step: 2080/530, loss: 0.012176895514130592
2023-01-21 10:33:25.207289: step: 2084/530, loss: 0.10169430077075958
2023-01-21 10:33:26.333547: step: 2088/530, loss: 0.07025375217199326
2023-01-21 10:33:27.493035: step: 2092/530, loss: 0.07257194817066193
2023-01-21 10:33:28.609720: step: 2096/530, loss: 0.011845779605209827
2023-01-21 10:33:29.748941: step: 2100/530, loss: 0.019803810864686966
2023-01-21 10:33:30.887535: step: 2104/530, loss: 0.023592090234160423
2023-01-21 10:33:32.049875: step: 2108/530, loss: 0.024277402088046074
2023-01-21 10:33:33.210890: step: 2112/530, loss: 0.015037250705063343
2023-01-21 10:33:34.354320: step: 2116/530, loss: 0.03745584562420845
2023-01-21 10:33:35.475625: step: 2120/530, loss: 0.09587268531322479
==================================================
Loss: 0.081
--------------------
Dev: {'event': {'p': 0.6010471204188481, 'r': 0.7643142476697736, 'f1': 0.6729191090269636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.645933014354067, 'r': 0.7714285714285715, 'f1': 0.7031250000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
Korean: {'event': {'p': 0.6538461538461539, 'r': 0.5396825396825397, 'f1': 0.5913043478260869}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:34:18.002947: step: 4/530, loss: 0.04146585613489151
2023-01-21 10:34:19.152625: step: 8/530, loss: 0.0164960864931345
2023-01-21 10:34:20.325252: step: 12/530, loss: 0.03456135094165802
2023-01-21 10:34:21.460628: step: 16/530, loss: 0.18468494713306427
2023-01-21 10:34:22.579566: step: 20/530, loss: 0.09135501831769943
2023-01-21 10:34:23.717829: step: 24/530, loss: 0.027293110266327858
2023-01-21 10:34:24.858433: step: 28/530, loss: 0.04382496327161789
2023-01-21 10:34:25.969013: step: 32/530, loss: 0.12391787022352219
2023-01-21 10:34:27.151928: step: 36/530, loss: 0.06755166500806808
2023-01-21 10:34:28.298340: step: 40/530, loss: 0.007240963168442249
2023-01-21 10:34:29.407266: step: 44/530, loss: 0.0015702247619628906
2023-01-21 10:34:30.539458: step: 48/530, loss: 0.06069831922650337
2023-01-21 10:34:31.670819: step: 52/530, loss: 0.06297197192907333
2023-01-21 10:34:32.795287: step: 56/530, loss: 0.14973267912864685
2023-01-21 10:34:33.929428: step: 60/530, loss: 0.0063460348173975945
2023-01-21 10:34:35.061178: step: 64/530, loss: 0.2561872601509094
2023-01-21 10:34:36.185098: step: 68/530, loss: 0.03596191480755806
2023-01-21 10:34:37.321326: step: 72/530, loss: 0.0290814395993948
2023-01-21 10:34:38.488368: step: 76/530, loss: 0.049086377024650574
2023-01-21 10:34:39.601942: step: 80/530, loss: 0.0009068489307537675
2023-01-21 10:34:40.741716: step: 84/530, loss: 0.09232454001903534
2023-01-21 10:34:41.881502: step: 88/530, loss: 0.0063554286025464535
2023-01-21 10:34:43.042417: step: 92/530, loss: 0.10055732727050781
2023-01-21 10:34:44.160383: step: 96/530, loss: 0.08032207190990448
2023-01-21 10:34:45.280827: step: 100/530, loss: 0.03787975385785103
2023-01-21 10:34:46.437903: step: 104/530, loss: 0.009539986029267311
2023-01-21 10:34:47.592139: step: 108/530, loss: 0.022919846698641777
2023-01-21 10:34:48.748244: step: 112/530, loss: 0.0420568473637104
2023-01-21 10:34:49.896215: step: 116/530, loss: 0.024195099249482155
2023-01-21 10:34:51.034734: step: 120/530, loss: 0.02817096747457981
2023-01-21 10:34:52.182628: step: 124/530, loss: 0.05008964613080025
2023-01-21 10:34:53.310928: step: 128/530, loss: 0.13800200819969177
2023-01-21 10:34:54.447772: step: 132/530, loss: 0.0007683277362957597
2023-01-21 10:34:55.588265: step: 136/530, loss: 0.04119687154889107
2023-01-21 10:34:56.731236: step: 140/530, loss: 0.4442861080169678
2023-01-21 10:34:57.833366: step: 144/530, loss: 0.07509423047304153
2023-01-21 10:34:58.956226: step: 148/530, loss: 0.05681591108441353
2023-01-21 10:35:00.079034: step: 152/530, loss: 0.005243396852165461
2023-01-21 10:35:01.180309: step: 156/530, loss: 0.05020580440759659
2023-01-21 10:35:02.352952: step: 160/530, loss: 0.08720698952674866
2023-01-21 10:35:03.518202: step: 164/530, loss: 0.07956667244434357
2023-01-21 10:35:04.663648: step: 168/530, loss: 0.06377530097961426
2023-01-21 10:35:05.805619: step: 172/530, loss: 0.016119956970214844
2023-01-21 10:35:06.956806: step: 176/530, loss: 0.017048906534910202
2023-01-21 10:35:08.090259: step: 180/530, loss: 0.05277865007519722
2023-01-21 10:35:09.235450: step: 184/530, loss: 0.0050366404466331005
2023-01-21 10:35:10.405925: step: 188/530, loss: 0.05620727688074112
2023-01-21 10:35:11.551553: step: 192/530, loss: 0.05632200092077255
2023-01-21 10:35:12.686109: step: 196/530, loss: 0.15684758126735687
2023-01-21 10:35:13.811950: step: 200/530, loss: 0.0258638858795166
2023-01-21 10:35:14.951560: step: 204/530, loss: 0.029148291796445847
2023-01-21 10:35:16.109324: step: 208/530, loss: 0.01912403106689453
2023-01-21 10:35:17.242643: step: 212/530, loss: 0.011973000131547451
2023-01-21 10:35:18.348824: step: 216/530, loss: 0.04125671461224556
2023-01-21 10:35:19.460104: step: 220/530, loss: 0.09170989692211151
2023-01-21 10:35:20.623417: step: 224/530, loss: 0.040692903101444244
2023-01-21 10:35:21.756776: step: 228/530, loss: 0.014829372987151146
2023-01-21 10:35:22.875802: step: 232/530, loss: 0.025092124938964844
2023-01-21 10:35:24.011880: step: 236/530, loss: 0.0481724739074707
2023-01-21 10:35:25.149614: step: 240/530, loss: 0.06974754482507706
2023-01-21 10:35:26.292211: step: 244/530, loss: 0.06489360332489014
2023-01-21 10:35:27.430809: step: 248/530, loss: 0.018863869830965996
2023-01-21 10:35:28.554476: step: 252/530, loss: 0.003004169324412942
2023-01-21 10:35:29.668797: step: 256/530, loss: 0.008741474710404873
2023-01-21 10:35:30.814182: step: 260/530, loss: 0.023272132501006126
2023-01-21 10:35:31.940086: step: 264/530, loss: 0.8038443922996521
2023-01-21 10:35:33.132524: step: 268/530, loss: 0.004899454303085804
2023-01-21 10:35:34.284887: step: 272/530, loss: 0.04940157011151314
2023-01-21 10:35:35.405574: step: 276/530, loss: 0.07593349367380142
2023-01-21 10:35:36.561847: step: 280/530, loss: 0.008756637573242188
2023-01-21 10:35:37.699351: step: 284/530, loss: 0.04515376314520836
2023-01-21 10:35:38.895120: step: 288/530, loss: 0.024807455018162727
2023-01-21 10:35:40.066461: step: 292/530, loss: 0.1753520965576172
2023-01-21 10:35:41.223375: step: 296/530, loss: 0.012975931167602539
2023-01-21 10:35:42.353538: step: 300/530, loss: 0.0167604461312294
2023-01-21 10:35:43.528190: step: 304/530, loss: 0.004330158233642578
2023-01-21 10:35:44.671007: step: 308/530, loss: 6.226780414581299
2023-01-21 10:35:45.802059: step: 312/530, loss: 0.034804344177246094
2023-01-21 10:35:46.918134: step: 316/530, loss: 0.005957412999123335
2023-01-21 10:35:48.062030: step: 320/530, loss: 0.04643554985523224
2023-01-21 10:35:49.195750: step: 324/530, loss: 0.04254427179694176
2023-01-21 10:35:50.330727: step: 328/530, loss: 0.09731712937355042
2023-01-21 10:35:51.474348: step: 332/530, loss: 0.008234405890107155
2023-01-21 10:35:52.593560: step: 336/530, loss: 0.07836703956127167
2023-01-21 10:35:53.726192: step: 340/530, loss: 0.032621145248413086
2023-01-21 10:35:54.862670: step: 344/530, loss: 0.031035710126161575
2023-01-21 10:35:56.028355: step: 348/530, loss: 0.0398748405277729
2023-01-21 10:35:57.206775: step: 352/530, loss: 0.07766761630773544
2023-01-21 10:35:58.310538: step: 356/530, loss: 0.03663988411426544
2023-01-21 10:35:59.437093: step: 360/530, loss: 0.005725192837417126
2023-01-21 10:36:00.550527: step: 364/530, loss: 0.03603353351354599
2023-01-21 10:36:01.698370: step: 368/530, loss: 0.05004243552684784
2023-01-21 10:36:02.826020: step: 372/530, loss: 0.16664715111255646
2023-01-21 10:36:03.973604: step: 376/530, loss: 0.08054390549659729
2023-01-21 10:36:05.093632: step: 380/530, loss: 0.08258800953626633
2023-01-21 10:36:06.235311: step: 384/530, loss: 0.0011554717784747481
2023-01-21 10:36:07.356539: step: 388/530, loss: 0.0006314754718914628
2023-01-21 10:36:08.512870: step: 392/530, loss: 0.009018135257065296
2023-01-21 10:36:09.668459: step: 396/530, loss: 0.045431043952703476
2023-01-21 10:36:10.797078: step: 400/530, loss: 0.008813095279037952
2023-01-21 10:36:11.974849: step: 404/530, loss: 0.018123149871826172
2023-01-21 10:36:13.155526: step: 408/530, loss: 0.12108249962329865
2023-01-21 10:36:14.323755: step: 412/530, loss: 0.06378650665283203
2023-01-21 10:36:15.468587: step: 416/530, loss: 0.048793695867061615
2023-01-21 10:36:16.648568: step: 420/530, loss: 0.017655229195952415
2023-01-21 10:36:17.813718: step: 424/530, loss: 0.012522506527602673
2023-01-21 10:36:18.979037: step: 428/530, loss: 0.06374216079711914
2023-01-21 10:36:20.123382: step: 432/530, loss: 0.10491828620433807
2023-01-21 10:36:21.300259: step: 436/530, loss: 0.0975012332201004
2023-01-21 10:36:22.432981: step: 440/530, loss: 0.0031029225792735815
2023-01-21 10:36:23.590382: step: 444/530, loss: 0.09400520473718643
2023-01-21 10:36:24.727894: step: 448/530, loss: 0.013028335757553577
2023-01-21 10:36:25.883217: step: 452/530, loss: 0.045618344098329544
2023-01-21 10:36:27.042875: step: 456/530, loss: 0.03030386008322239
2023-01-21 10:36:28.194667: step: 460/530, loss: 0.02246379852294922
2023-01-21 10:36:29.313622: step: 464/530, loss: 0.012247848324477673
2023-01-21 10:36:30.425899: step: 468/530, loss: 0.016779230907559395
2023-01-21 10:36:31.542008: step: 472/530, loss: 0.0005039215320721269
2023-01-21 10:36:32.672263: step: 476/530, loss: 0.009072018787264824
2023-01-21 10:36:33.832078: step: 480/530, loss: 0.03471393510699272
2023-01-21 10:36:34.969853: step: 484/530, loss: 0.017095565795898438
2023-01-21 10:36:36.084720: step: 488/530, loss: 0.04830913990736008
2023-01-21 10:36:37.243790: step: 492/530, loss: 0.007652092259377241
2023-01-21 10:36:38.384049: step: 496/530, loss: 0.02378563955426216
2023-01-21 10:36:39.510791: step: 500/530, loss: 0.026201438158750534
2023-01-21 10:36:40.649669: step: 504/530, loss: 0.03820495679974556
2023-01-21 10:36:41.796487: step: 508/530, loss: 0.023201845586299896
2023-01-21 10:36:42.939244: step: 512/530, loss: 0.015618515200912952
2023-01-21 10:36:44.056198: step: 516/530, loss: 0.008405590429902077
2023-01-21 10:36:45.188712: step: 520/530, loss: 0.013255024328827858
2023-01-21 10:36:46.365837: step: 524/530, loss: 0.36251935362815857
2023-01-21 10:36:47.506279: step: 528/530, loss: 0.0015875815879553556
2023-01-21 10:36:48.647002: step: 532/530, loss: 0.015517806634306908
2023-01-21 10:36:49.802144: step: 536/530, loss: 0.12606608867645264
2023-01-21 10:36:50.939827: step: 540/530, loss: 0.010173225775361061
2023-01-21 10:36:52.115716: step: 544/530, loss: 0.006377696990966797
2023-01-21 10:36:53.221917: step: 548/530, loss: 0.05588836595416069
2023-01-21 10:36:54.359557: step: 552/530, loss: 0.06918372958898544
2023-01-21 10:36:55.498832: step: 556/530, loss: 0.09663286805152893
2023-01-21 10:36:56.670647: step: 560/530, loss: 0.06582470238208771
2023-01-21 10:36:57.816342: step: 564/530, loss: 0.025864887982606888
2023-01-21 10:36:58.968071: step: 568/530, loss: 0.053361132740974426
2023-01-21 10:37:00.092232: step: 572/530, loss: 0.016445159912109375
2023-01-21 10:37:01.250734: step: 576/530, loss: 0.12411890178918839
2023-01-21 10:37:02.406890: step: 580/530, loss: 0.021427059546113014
2023-01-21 10:37:03.559115: step: 584/530, loss: 0.06904029846191406
2023-01-21 10:37:04.686613: step: 588/530, loss: 0.13493481278419495
2023-01-21 10:37:05.818668: step: 592/530, loss: 0.029292868450284004
2023-01-21 10:37:06.953273: step: 596/530, loss: 0.009181786328554153
2023-01-21 10:37:08.105268: step: 600/530, loss: 0.05648374557495117
2023-01-21 10:37:09.244976: step: 604/530, loss: 0.038665641099214554
2023-01-21 10:37:10.395526: step: 608/530, loss: 0.009718894958496094
2023-01-21 10:37:11.552851: step: 612/530, loss: 0.008212280459702015
2023-01-21 10:37:12.682270: step: 616/530, loss: 0.08202342689037323
2023-01-21 10:37:13.819491: step: 620/530, loss: 0.005619812291115522
2023-01-21 10:37:14.986255: step: 624/530, loss: 0.054976511746644974
2023-01-21 10:37:16.095166: step: 628/530, loss: 0.03801391273736954
2023-01-21 10:37:17.249343: step: 632/530, loss: 0.016525745391845703
2023-01-21 10:37:18.388869: step: 636/530, loss: 0.08721990883350372
2023-01-21 10:37:19.546838: step: 640/530, loss: 0.02155628241598606
2023-01-21 10:37:20.680932: step: 644/530, loss: 0.09035935997962952
2023-01-21 10:37:21.820829: step: 648/530, loss: 0.029609205201268196
2023-01-21 10:37:22.955813: step: 652/530, loss: 0.019499968737363815
2023-01-21 10:37:24.105797: step: 656/530, loss: 0.03985252603888512
2023-01-21 10:37:25.245237: step: 660/530, loss: 0.087981678545475
2023-01-21 10:37:26.403586: step: 664/530, loss: 0.059149932116270065
2023-01-21 10:37:27.521596: step: 668/530, loss: 0.06220431625843048
2023-01-21 10:37:28.654277: step: 672/530, loss: 0.002528381533920765
2023-01-21 10:37:29.813054: step: 676/530, loss: 0.028195716440677643
2023-01-21 10:37:30.962195: step: 680/530, loss: 0.024074697867035866
2023-01-21 10:37:32.105047: step: 684/530, loss: 0.0861758217215538
2023-01-21 10:37:33.244360: step: 688/530, loss: 0.09414668381214142
2023-01-21 10:37:34.388287: step: 692/530, loss: 0.024211978539824486
2023-01-21 10:37:35.520884: step: 696/530, loss: 0.02629375457763672
2023-01-21 10:37:36.690952: step: 700/530, loss: 0.0645742416381836
2023-01-21 10:37:37.862882: step: 704/530, loss: 0.027009274810552597
2023-01-21 10:37:39.012767: step: 708/530, loss: 0.07800912857055664
2023-01-21 10:37:40.113261: step: 712/530, loss: 0.014352703467011452
2023-01-21 10:37:41.246427: step: 716/530, loss: 0.04800605773925781
2023-01-21 10:37:42.361441: step: 720/530, loss: 0.08245086669921875
2023-01-21 10:37:43.491448: step: 724/530, loss: 0.01673748530447483
2023-01-21 10:37:44.668019: step: 728/530, loss: 0.07929801940917969
2023-01-21 10:37:45.818153: step: 732/530, loss: 0.002699923701584339
2023-01-21 10:37:46.965725: step: 736/530, loss: 0.07265863567590714
2023-01-21 10:37:48.105485: step: 740/530, loss: 0.028813553974032402
2023-01-21 10:37:49.217100: step: 744/530, loss: 0.04370279610157013
2023-01-21 10:37:50.385618: step: 748/530, loss: 0.00019559860811568797
2023-01-21 10:37:51.535084: step: 752/530, loss: 0.031233882531523705
2023-01-21 10:37:52.685082: step: 756/530, loss: 0.00712242117151618
2023-01-21 10:37:53.823487: step: 760/530, loss: 0.009337044321000576
2023-01-21 10:37:54.953203: step: 764/530, loss: 0.8297949433326721
2023-01-21 10:37:56.070163: step: 768/530, loss: 0.027551794424653053
2023-01-21 10:37:57.217212: step: 772/530, loss: 0.05590534210205078
2023-01-21 10:37:58.330649: step: 776/530, loss: 0.043745994567871094
2023-01-21 10:37:59.456794: step: 780/530, loss: 0.010922812856733799
2023-01-21 10:38:00.631349: step: 784/530, loss: 0.04017524793744087
2023-01-21 10:38:01.766878: step: 788/530, loss: 0.039598654955625534
2023-01-21 10:38:02.896477: step: 792/530, loss: 0.007432460784912109
2023-01-21 10:38:04.061262: step: 796/530, loss: 0.007860946469008923
2023-01-21 10:38:05.236598: step: 800/530, loss: 0.016886234283447266
2023-01-21 10:38:06.388280: step: 804/530, loss: 0.03184347227215767
2023-01-21 10:38:07.533086: step: 808/530, loss: 0.02033214643597603
2023-01-21 10:38:08.654850: step: 812/530, loss: 0.03039254993200302
2023-01-21 10:38:09.813009: step: 816/530, loss: 0.07868233323097229
2023-01-21 10:38:10.988963: step: 820/530, loss: 0.010586929507553577
2023-01-21 10:38:12.153256: step: 824/530, loss: 0.4011600613594055
2023-01-21 10:38:13.287802: step: 828/530, loss: 0.0167218204587698
2023-01-21 10:38:14.419417: step: 832/530, loss: 0.16747525334358215
2023-01-21 10:38:15.555677: step: 836/530, loss: 0.04014711454510689
2023-01-21 10:38:16.689423: step: 840/530, loss: 0.0198395736515522
2023-01-21 10:38:17.825093: step: 844/530, loss: 0.0016194343334063888
2023-01-21 10:38:18.950250: step: 848/530, loss: 0.05386009067296982
2023-01-21 10:38:20.088889: step: 852/530, loss: 0.035674382001161575
2023-01-21 10:38:21.216428: step: 856/530, loss: 0.02274188958108425
2023-01-21 10:38:22.374233: step: 860/530, loss: 0.030316829681396484
2023-01-21 10:38:23.518222: step: 864/530, loss: 0.0369170680642128
2023-01-21 10:38:24.640202: step: 868/530, loss: 0.027235697954893112
2023-01-21 10:38:25.783128: step: 872/530, loss: 0.031687356531620026
2023-01-21 10:38:26.873816: step: 876/530, loss: 0.006474614143371582
2023-01-21 10:38:28.008918: step: 880/530, loss: 0.02765359915792942
2023-01-21 10:38:29.168761: step: 884/530, loss: 0.11171627789735794
2023-01-21 10:38:30.300546: step: 888/530, loss: 0.026321982964873314
2023-01-21 10:38:31.447423: step: 892/530, loss: 0.0026480676606297493
2023-01-21 10:38:32.615898: step: 896/530, loss: 0.01588573306798935
2023-01-21 10:38:33.747918: step: 900/530, loss: 0.07487421482801437
2023-01-21 10:38:34.851248: step: 904/530, loss: 0.040831565856933594
2023-01-21 10:38:35.988088: step: 908/530, loss: 0.41110649704933167
2023-01-21 10:38:37.108174: step: 912/530, loss: 0.03103947825729847
2023-01-21 10:38:38.252095: step: 916/530, loss: 0.1822216659784317
2023-01-21 10:38:39.392596: step: 920/530, loss: 0.01214895211160183
2023-01-21 10:38:40.490273: step: 924/530, loss: 0.015990495681762695
2023-01-21 10:38:41.636238: step: 928/530, loss: 0.5049837827682495
2023-01-21 10:38:42.772543: step: 932/530, loss: 0.008755683898925781
2023-01-21 10:38:43.928433: step: 936/530, loss: 0.05490703508257866
2023-01-21 10:38:45.054307: step: 940/530, loss: 0.019974518567323685
2023-01-21 10:38:46.176703: step: 944/530, loss: 0.016568278893828392
2023-01-21 10:38:47.319072: step: 948/530, loss: 0.004858541768044233
2023-01-21 10:38:48.460636: step: 952/530, loss: 0.0048694610595703125
2023-01-21 10:38:49.608469: step: 956/530, loss: 0.060088206082582474
2023-01-21 10:38:50.747473: step: 960/530, loss: 0.004809761419892311
2023-01-21 10:38:51.892734: step: 964/530, loss: 0.04707353189587593
2023-01-21 10:38:53.028350: step: 968/530, loss: 0.03624153137207031
2023-01-21 10:38:54.194143: step: 972/530, loss: 0.020730018615722656
2023-01-21 10:38:55.334072: step: 976/530, loss: 0.03426048532128334
2023-01-21 10:38:56.497436: step: 980/530, loss: 0.025171946734189987
2023-01-21 10:38:57.659413: step: 984/530, loss: 0.009561729617416859
2023-01-21 10:38:58.822012: step: 988/530, loss: 0.07763605564832687
2023-01-21 10:38:59.974796: step: 992/530, loss: 0.027331778779625893
2023-01-21 10:39:01.105412: step: 996/530, loss: 0.7535378932952881
2023-01-21 10:39:02.233640: step: 1000/530, loss: 0.0663982480764389
2023-01-21 10:39:03.368110: step: 1004/530, loss: 0.03893308714032173
2023-01-21 10:39:04.485876: step: 1008/530, loss: 0.011975526809692383
2023-01-21 10:39:05.607600: step: 1012/530, loss: 0.09670901298522949
2023-01-21 10:39:06.740097: step: 1016/530, loss: 0.016979694366455078
2023-01-21 10:39:07.897611: step: 1020/530, loss: 0.019005490466952324
2023-01-21 10:39:09.032109: step: 1024/530, loss: 0.04517097398638725
2023-01-21 10:39:10.186637: step: 1028/530, loss: 0.011025047861039639
2023-01-21 10:39:11.335546: step: 1032/530, loss: 0.1146320328116417
2023-01-21 10:39:12.496221: step: 1036/530, loss: 0.06828584522008896
2023-01-21 10:39:13.614989: step: 1040/530, loss: 0.1598796844482422
2023-01-21 10:39:14.726470: step: 1044/530, loss: 0.10229549556970596
2023-01-21 10:39:15.862908: step: 1048/530, loss: 0.017337609082460403
2023-01-21 10:39:17.039185: step: 1052/530, loss: 0.036089349538087845
2023-01-21 10:39:18.172221: step: 1056/530, loss: 0.0346127524971962
2023-01-21 10:39:19.280862: step: 1060/530, loss: 0.007623481564223766
2023-01-21 10:39:20.401182: step: 1064/530, loss: 0.050319671630859375
2023-01-21 10:39:21.565598: step: 1068/530, loss: 0.01645965501666069
2023-01-21 10:39:22.685827: step: 1072/530, loss: 0.04982910305261612
2023-01-21 10:39:23.849815: step: 1076/530, loss: 0.024080883711576462
2023-01-21 10:39:24.972716: step: 1080/530, loss: 0.02354259416460991
2023-01-21 10:39:26.089025: step: 1084/530, loss: 0.03885345533490181
2023-01-21 10:39:27.229833: step: 1088/530, loss: 0.05298004299402237
2023-01-21 10:39:28.363845: step: 1092/530, loss: 0.02705850638449192
2023-01-21 10:39:29.523964: step: 1096/530, loss: 0.04123878479003906
2023-01-21 10:39:30.639900: step: 1100/530, loss: 0.10094118118286133
2023-01-21 10:39:31.782565: step: 1104/530, loss: 0.029483605176210403
2023-01-21 10:39:32.938450: step: 1108/530, loss: 0.11217517405748367
2023-01-21 10:39:34.056230: step: 1112/530, loss: 0.17927446961402893
2023-01-21 10:39:35.197686: step: 1116/530, loss: 0.07067833095788956
2023-01-21 10:39:36.366344: step: 1120/530, loss: 0.1162746399641037
2023-01-21 10:39:37.504471: step: 1124/530, loss: 0.0340668186545372
2023-01-21 10:39:38.633416: step: 1128/530, loss: 0.007141590118408203
2023-01-21 10:39:39.772110: step: 1132/530, loss: 0.03126878663897514
2023-01-21 10:39:40.893725: step: 1136/530, loss: 0.03748369216918945
2023-01-21 10:39:42.040405: step: 1140/530, loss: 0.001227092812769115
2023-01-21 10:39:43.157329: step: 1144/530, loss: 0.02130298689007759
2023-01-21 10:39:44.315380: step: 1148/530, loss: 0.012703514657914639
2023-01-21 10:39:45.437031: step: 1152/530, loss: 0.2367529422044754
2023-01-21 10:39:46.551641: step: 1156/530, loss: 0.0236591175198555
2023-01-21 10:39:47.691890: step: 1160/530, loss: 0.0019272805657237768
2023-01-21 10:39:48.849233: step: 1164/530, loss: 0.052582789212465286
2023-01-21 10:39:50.053594: step: 1168/530, loss: 0.12448345124721527
2023-01-21 10:39:51.183828: step: 1172/530, loss: 0.2623058259487152
2023-01-21 10:39:52.323768: step: 1176/530, loss: 0.03934812545776367
2023-01-21 10:39:53.444633: step: 1180/530, loss: 0.05309572443366051
2023-01-21 10:39:54.577182: step: 1184/530, loss: 0.03446225821971893
2023-01-21 10:39:55.713837: step: 1188/530, loss: 0.0435122586786747
2023-01-21 10:39:56.867487: step: 1192/530, loss: 0.0553533099591732
2023-01-21 10:39:58.003349: step: 1196/530, loss: 0.013289928436279297
2023-01-21 10:39:59.138804: step: 1200/530, loss: 0.013298642821609974
2023-01-21 10:40:00.313530: step: 1204/530, loss: 0.02317214012145996
2023-01-21 10:40:01.497512: step: 1208/530, loss: 0.058649253100156784
2023-01-21 10:40:02.655696: step: 1212/530, loss: 1.4833146333694458
2023-01-21 10:40:03.794390: step: 1216/530, loss: 0.025757789611816406
2023-01-21 10:40:04.923169: step: 1220/530, loss: 0.041926003992557526
2023-01-21 10:40:06.058281: step: 1224/530, loss: 0.11770649254322052
2023-01-21 10:40:07.187840: step: 1228/530, loss: 0.0029358863830566406
2023-01-21 10:40:08.335648: step: 1232/530, loss: 0.9838047027587891
2023-01-21 10:40:09.454125: step: 1236/530, loss: 0.04121103510260582
2023-01-21 10:40:10.628544: step: 1240/530, loss: 0.05901211500167847
2023-01-21 10:40:11.795351: step: 1244/530, loss: 0.0799943059682846
2023-01-21 10:40:12.957545: step: 1248/530, loss: 0.09362554550170898
2023-01-21 10:40:14.092566: step: 1252/530, loss: 1.3456366062164307
2023-01-21 10:40:15.264033: step: 1256/530, loss: 0.030677413567900658
2023-01-21 10:40:16.432545: step: 1260/530, loss: 0.09209322929382324
2023-01-21 10:40:17.564594: step: 1264/530, loss: 0.031025506556034088
2023-01-21 10:40:18.683412: step: 1268/530, loss: 0.008028984069824219
2023-01-21 10:40:19.814896: step: 1272/530, loss: 0.06793183833360672
2023-01-21 10:40:20.972187: step: 1276/530, loss: 0.030474090948700905
2023-01-21 10:40:22.094889: step: 1280/530, loss: 0.007448864169418812
2023-01-21 10:40:23.249037: step: 1284/530, loss: 0.027852153405547142
2023-01-21 10:40:24.396228: step: 1288/530, loss: 0.10311603546142578
2023-01-21 10:40:25.544759: step: 1292/530, loss: 0.07385721057653427
2023-01-21 10:40:26.710753: step: 1296/530, loss: 0.0898863822221756
2023-01-21 10:40:27.856467: step: 1300/530, loss: 0.3169923722743988
2023-01-21 10:40:28.980455: step: 1304/530, loss: 0.09978704154491425
2023-01-21 10:40:30.115740: step: 1308/530, loss: 0.06102476269006729
2023-01-21 10:40:31.250506: step: 1312/530, loss: 0.030858777463436127
2023-01-21 10:40:32.411840: step: 1316/530, loss: 0.015398884192109108
2023-01-21 10:40:33.562322: step: 1320/530, loss: 0.08353858441114426
2023-01-21 10:40:34.729671: step: 1324/530, loss: 0.07359378039836884
2023-01-21 10:40:35.840339: step: 1328/530, loss: 0.046921443194150925
2023-01-21 10:40:36.959309: step: 1332/530, loss: 0.0617523193359375
2023-01-21 10:40:38.085741: step: 1336/530, loss: 0.04049711301922798
2023-01-21 10:40:39.267821: step: 1340/530, loss: 0.012983131222426891
2023-01-21 10:40:40.433006: step: 1344/530, loss: 0.01473617646843195
2023-01-21 10:40:41.575610: step: 1348/530, loss: 0.007877158932387829
2023-01-21 10:40:42.699353: step: 1352/530, loss: 0.3036857545375824
2023-01-21 10:40:43.878303: step: 1356/530, loss: 0.040499210357666016
2023-01-21 10:40:45.036138: step: 1360/530, loss: 0.05816479027271271
2023-01-21 10:40:46.187387: step: 1364/530, loss: 0.09076805412769318
2023-01-21 10:40:47.311222: step: 1368/530, loss: 0.0436735637485981
2023-01-21 10:40:48.433887: step: 1372/530, loss: 0.011147355660796165
2023-01-21 10:40:49.559732: step: 1376/530, loss: 0.023430967703461647
2023-01-21 10:40:50.663432: step: 1380/530, loss: 0.017697811126708984
2023-01-21 10:40:51.800710: step: 1384/530, loss: 0.22648115456104279
2023-01-21 10:40:52.939787: step: 1388/530, loss: 0.005888843908905983
2023-01-21 10:40:54.088911: step: 1392/530, loss: 0.0368773490190506
2023-01-21 10:40:55.294127: step: 1396/530, loss: 0.0022420408204197884
2023-01-21 10:40:56.429340: step: 1400/530, loss: 0.0013060569763183594
2023-01-21 10:40:57.590593: step: 1404/530, loss: 0.3281448483467102
2023-01-21 10:40:58.751647: step: 1408/530, loss: 0.03287963941693306
2023-01-21 10:40:59.896844: step: 1412/530, loss: 0.015015030279755592
2023-01-21 10:41:01.052559: step: 1416/530, loss: 0.1252155303955078
2023-01-21 10:41:02.191715: step: 1420/530, loss: 0.016002941876649857
2023-01-21 10:41:03.325831: step: 1424/530, loss: 0.0055599212646484375
2023-01-21 10:41:04.486943: step: 1428/530, loss: 0.004454612731933594
2023-01-21 10:41:05.617115: step: 1432/530, loss: 0.1563817262649536
2023-01-21 10:41:06.761415: step: 1436/530, loss: 0.019991589710116386
2023-01-21 10:41:07.897983: step: 1440/530, loss: 0.03615932539105415
2023-01-21 10:41:09.034341: step: 1444/530, loss: 0.04416370391845703
2023-01-21 10:41:10.182528: step: 1448/530, loss: 0.02237873151898384
2023-01-21 10:41:11.339464: step: 1452/530, loss: 0.004031658172607422
2023-01-21 10:41:12.473632: step: 1456/530, loss: 0.10543432831764221
2023-01-21 10:41:13.611157: step: 1460/530, loss: 0.04476146772503853
2023-01-21 10:41:14.724712: step: 1464/530, loss: 0.013064957223832607
2023-01-21 10:41:15.871819: step: 1468/530, loss: 0.07537870109081268
2023-01-21 10:41:17.020151: step: 1472/530, loss: 0.19609889388084412
2023-01-21 10:41:18.180654: step: 1476/530, loss: 0.022807884961366653
2023-01-21 10:41:19.325484: step: 1480/530, loss: 0.00527267437428236
2023-01-21 10:41:20.473600: step: 1484/530, loss: 0.11423645913600922
2023-01-21 10:41:21.657399: step: 1488/530, loss: 0.041696835309267044
2023-01-21 10:41:22.786224: step: 1492/530, loss: 0.008644675835967064
2023-01-21 10:41:23.950903: step: 1496/530, loss: 0.02127685584127903
2023-01-21 10:41:25.101532: step: 1500/530, loss: 0.010269737802445889
2023-01-21 10:41:26.242707: step: 1504/530, loss: 0.12578992545604706
2023-01-21 10:41:27.365862: step: 1508/530, loss: 0.1257183998823166
2023-01-21 10:41:28.489877: step: 1512/530, loss: 0.061166100203990936
2023-01-21 10:41:29.616041: step: 1516/530, loss: 0.09761114418506622
2023-01-21 10:41:30.777299: step: 1520/530, loss: 0.05430469661951065
2023-01-21 10:41:31.930936: step: 1524/530, loss: 0.0682094544172287
2023-01-21 10:41:33.121482: step: 1528/530, loss: 0.08745650947093964
2023-01-21 10:41:34.244414: step: 1532/530, loss: 0.03851308673620224
2023-01-21 10:41:35.382475: step: 1536/530, loss: 0.13264040648937225
2023-01-21 10:41:36.546146: step: 1540/530, loss: 0.023351669311523438
2023-01-21 10:41:37.701619: step: 1544/530, loss: 0.010625744238495827
2023-01-21 10:41:38.839217: step: 1548/530, loss: 0.0032019615173339844
2023-01-21 10:41:39.964878: step: 1552/530, loss: 0.002635193057358265
2023-01-21 10:41:41.104732: step: 1556/530, loss: 0.03500928729772568
2023-01-21 10:41:42.242774: step: 1560/530, loss: 0.0467713363468647
2023-01-21 10:41:43.402513: step: 1564/530, loss: 0.05844561383128166
2023-01-21 10:41:44.556605: step: 1568/530, loss: 0.08722095191478729
2023-01-21 10:41:45.707037: step: 1572/530, loss: 0.06287989765405655
2023-01-21 10:41:46.829567: step: 1576/530, loss: 0.031231213361024857
2023-01-21 10:41:48.010203: step: 1580/530, loss: 0.05687766149640083
2023-01-21 10:41:49.156797: step: 1584/530, loss: 0.01974515989422798
2023-01-21 10:41:50.274361: step: 1588/530, loss: 0.004370022099465132
2023-01-21 10:41:51.398248: step: 1592/530, loss: 0.0794130340218544
2023-01-21 10:41:52.537139: step: 1596/530, loss: 0.040224839001894
2023-01-21 10:41:53.693806: step: 1600/530, loss: 0.013759803958237171
2023-01-21 10:41:54.820325: step: 1604/530, loss: 0.04306211322546005
2023-01-21 10:41:55.967186: step: 1608/530, loss: 0.03336386755108833
2023-01-21 10:41:57.100303: step: 1612/530, loss: 0.01677856408059597
2023-01-21 10:41:58.229075: step: 1616/530, loss: 0.013958167284727097
2023-01-21 10:41:59.377098: step: 1620/530, loss: 0.07066164910793304
2023-01-21 10:42:00.524862: step: 1624/530, loss: 0.019552230834960938
2023-01-21 10:42:01.651476: step: 1628/530, loss: 0.3767172396183014
2023-01-21 10:42:02.814767: step: 1632/530, loss: 0.16153717041015625
2023-01-21 10:42:03.995946: step: 1636/530, loss: 0.008396911434829235
2023-01-21 10:42:05.119005: step: 1640/530, loss: 0.11108437180519104
2023-01-21 10:42:06.306759: step: 1644/530, loss: 0.10089760273694992
2023-01-21 10:42:07.457614: step: 1648/530, loss: 0.08596020191907883
2023-01-21 10:42:08.646246: step: 1652/530, loss: 0.006371689029037952
2023-01-21 10:42:09.836446: step: 1656/530, loss: 0.0012007714249193668
2023-01-21 10:42:10.991544: step: 1660/530, loss: 0.14213065803050995
2023-01-21 10:42:12.134342: step: 1664/530, loss: 0.14099007844924927
2023-01-21 10:42:13.330486: step: 1668/530, loss: 0.08927521854639053
2023-01-21 10:42:14.460013: step: 1672/530, loss: 0.017639046534895897
2023-01-21 10:42:15.591760: step: 1676/530, loss: 0.02323169820010662
2023-01-21 10:42:16.788106: step: 1680/530, loss: 0.025168299674987793
2023-01-21 10:42:17.943545: step: 1684/530, loss: 0.014221000485122204
2023-01-21 10:42:19.070110: step: 1688/530, loss: 0.04615669324994087
2023-01-21 10:42:20.201137: step: 1692/530, loss: 0.019794845953583717
2023-01-21 10:42:21.343321: step: 1696/530, loss: 0.0795656219124794
2023-01-21 10:42:22.458803: step: 1700/530, loss: 0.02145867422223091
2023-01-21 10:42:23.635700: step: 1704/530, loss: 0.010657120496034622
2023-01-21 10:42:24.785743: step: 1708/530, loss: 0.02896442450582981
2023-01-21 10:42:25.942197: step: 1712/530, loss: 0.12802210450172424
2023-01-21 10:42:27.073267: step: 1716/530, loss: 0.044201187789440155
2023-01-21 10:42:28.209573: step: 1720/530, loss: 0.04937968775629997
2023-01-21 10:42:29.333854: step: 1724/530, loss: 0.0014869689475744963
2023-01-21 10:42:30.453996: step: 1728/530, loss: 0.1193552017211914
2023-01-21 10:42:31.590235: step: 1732/530, loss: 0.02165224589407444
2023-01-21 10:42:32.715736: step: 1736/530, loss: 0.015211200341582298
2023-01-21 10:42:33.846916: step: 1740/530, loss: 0.041077326983213425
2023-01-21 10:42:34.994700: step: 1744/530, loss: 0.06702794879674911
2023-01-21 10:42:36.118355: step: 1748/530, loss: 0.059510041028261185
2023-01-21 10:42:37.258448: step: 1752/530, loss: 0.07804689556360245
2023-01-21 10:42:38.415469: step: 1756/530, loss: 0.06708774715662003
2023-01-21 10:42:39.542462: step: 1760/530, loss: 0.2416139543056488
2023-01-21 10:42:40.672721: step: 1764/530, loss: 0.04386806860566139
2023-01-21 10:42:41.844592: step: 1768/530, loss: 0.0035983086563646793
2023-01-21 10:42:42.955277: step: 1772/530, loss: 0.05683918297290802
2023-01-21 10:42:44.097878: step: 1776/530, loss: 0.026645852252840996
2023-01-21 10:42:45.222068: step: 1780/530, loss: 0.010800170712172985
2023-01-21 10:42:46.370286: step: 1784/530, loss: 0.024897005409002304
2023-01-21 10:42:47.513705: step: 1788/530, loss: 0.03249054029583931
2023-01-21 10:42:48.666001: step: 1792/530, loss: 0.44863295555114746
2023-01-21 10:42:49.825436: step: 1796/530, loss: 0.03138303756713867
2023-01-21 10:42:50.974273: step: 1800/530, loss: 0.020154381170868874
2023-01-21 10:42:52.115688: step: 1804/530, loss: 0.00490570068359375
2023-01-21 10:42:53.269872: step: 1808/530, loss: 0.056840136647224426
2023-01-21 10:42:54.423532: step: 1812/530, loss: 0.014387797564268112
2023-01-21 10:42:55.549318: step: 1816/530, loss: 0.011014366522431374
2023-01-21 10:42:56.697769: step: 1820/530, loss: 0.034049034118652344
2023-01-21 10:42:57.845509: step: 1824/530, loss: 1.1494110822677612
2023-01-21 10:42:58.966978: step: 1828/530, loss: 0.04215068742632866
2023-01-21 10:43:00.151596: step: 1832/530, loss: 0.014886761084198952
2023-01-21 10:43:01.303619: step: 1836/530, loss: 0.04936542361974716
2023-01-21 10:43:02.460936: step: 1840/530, loss: 0.18636426329612732
2023-01-21 10:43:03.588562: step: 1844/530, loss: 0.0564267635345459
2023-01-21 10:43:04.740904: step: 1848/530, loss: 0.0022520541679114103
2023-01-21 10:43:05.882447: step: 1852/530, loss: 0.08404403179883957
2023-01-21 10:43:07.028376: step: 1856/530, loss: 0.02207489125430584
2023-01-21 10:43:08.156783: step: 1860/530, loss: 0.004207802005112171
2023-01-21 10:43:09.299362: step: 1864/530, loss: 0.025124549865722656
2023-01-21 10:43:10.458001: step: 1868/530, loss: 0.03257932513952255
2023-01-21 10:43:11.603715: step: 1872/530, loss: 0.016363907605409622
2023-01-21 10:43:12.722165: step: 1876/530, loss: 0.11972226202487946
2023-01-21 10:43:13.851727: step: 1880/530, loss: 0.024494744837284088
2023-01-21 10:43:15.034846: step: 1884/530, loss: 0.0037693025078624487
2023-01-21 10:43:16.185790: step: 1888/530, loss: 0.08576412498950958
2023-01-21 10:43:17.370305: step: 1892/530, loss: 0.03946724161505699
2023-01-21 10:43:18.526616: step: 1896/530, loss: 0.06874599307775497
2023-01-21 10:43:19.689705: step: 1900/530, loss: 0.044737860560417175
2023-01-21 10:43:20.868151: step: 1904/530, loss: 0.04775981977581978
2023-01-21 10:43:22.016094: step: 1908/530, loss: 0.01249094121158123
2023-01-21 10:43:23.125276: step: 1912/530, loss: 0.039031028747558594
2023-01-21 10:43:24.304650: step: 1916/530, loss: 0.05117683485150337
2023-01-21 10:43:25.444013: step: 1920/530, loss: 0.15757597982883453
2023-01-21 10:43:26.588432: step: 1924/530, loss: 0.13480520248413086
2023-01-21 10:43:27.689401: step: 1928/530, loss: 0.24551606178283691
2023-01-21 10:43:28.814931: step: 1932/530, loss: 0.02641897276043892
2023-01-21 10:43:29.950712: step: 1936/530, loss: 0.007512473966926336
2023-01-21 10:43:31.094753: step: 1940/530, loss: 0.03429088741540909
2023-01-21 10:43:32.250373: step: 1944/530, loss: 0.013879586011171341
2023-01-21 10:43:33.429858: step: 1948/530, loss: 0.0027643204666674137
2023-01-21 10:43:34.587928: step: 1952/530, loss: 0.019124697893857956
2023-01-21 10:43:35.726670: step: 1956/530, loss: 0.006795382592827082
2023-01-21 10:43:36.877160: step: 1960/530, loss: 0.0571383498609066
2023-01-21 10:43:37.997608: step: 1964/530, loss: 0.0031063079368323088
2023-01-21 10:43:39.143696: step: 1968/530, loss: 0.0088227279484272
2023-01-21 10:43:40.304448: step: 1972/530, loss: 0.06085358187556267
2023-01-21 10:43:41.457332: step: 1976/530, loss: 0.037062231451272964
2023-01-21 10:43:42.635705: step: 1980/530, loss: 0.11239328235387802
2023-01-21 10:43:43.737280: step: 1984/530, loss: 0.0081145279109478
2023-01-21 10:43:44.871719: step: 1988/530, loss: 0.06414061039686203
2023-01-21 10:43:46.028004: step: 1992/530, loss: 0.04222848266363144
2023-01-21 10:43:47.200392: step: 1996/530, loss: 0.13775186240673065
2023-01-21 10:43:48.342163: step: 2000/530, loss: 0.015492104925215244
2023-01-21 10:43:49.492480: step: 2004/530, loss: 0.03464484214782715
2023-01-21 10:43:50.646431: step: 2008/530, loss: 0.017658328637480736
2023-01-21 10:43:51.763921: step: 2012/530, loss: 0.01415109634399414
2023-01-21 10:43:52.922236: step: 2016/530, loss: 0.005431285593658686
2023-01-21 10:43:54.090338: step: 2020/530, loss: 0.052102088928222656
2023-01-21 10:43:55.198446: step: 2024/530, loss: 0.02921323850750923
2023-01-21 10:43:56.338277: step: 2028/530, loss: 0.06791029125452042
2023-01-21 10:43:57.473627: step: 2032/530, loss: 0.10938436537981033
2023-01-21 10:43:58.608860: step: 2036/530, loss: 0.0010814667912200093
2023-01-21 10:43:59.729047: step: 2040/530, loss: 0.008490944281220436
2023-01-21 10:44:00.879580: step: 2044/530, loss: 0.0015291214222088456
2023-01-21 10:44:02.024897: step: 2048/530, loss: 0.09002876281738281
2023-01-21 10:44:03.147606: step: 2052/530, loss: 0.02641620673239231
2023-01-21 10:44:04.301940: step: 2056/530, loss: 0.021425439044833183
2023-01-21 10:44:05.432393: step: 2060/530, loss: 0.028833676129579544
2023-01-21 10:44:06.569532: step: 2064/530, loss: 0.11477460712194443
2023-01-21 10:44:07.744428: step: 2068/530, loss: 0.014074612408876419
2023-01-21 10:44:08.859005: step: 2072/530, loss: 0.4296489953994751
2023-01-21 10:44:10.024284: step: 2076/530, loss: 0.026035403832793236
2023-01-21 10:44:11.165142: step: 2080/530, loss: 0.09399977326393127
2023-01-21 10:44:12.323838: step: 2084/530, loss: 0.22609558701515198
2023-01-21 10:44:13.482185: step: 2088/530, loss: 0.02794475667178631
2023-01-21 10:44:14.638518: step: 2092/530, loss: 0.24151897430419922
2023-01-21 10:44:15.755348: step: 2096/530, loss: 0.021518278867006302
2023-01-21 10:44:16.903921: step: 2100/530, loss: 0.016987085342407227
2023-01-21 10:44:18.046136: step: 2104/530, loss: 0.15023207664489746
2023-01-21 10:44:19.194769: step: 2108/530, loss: 0.04144134372472763
2023-01-21 10:44:20.319567: step: 2112/530, loss: 0.11343646794557571
2023-01-21 10:44:21.482138: step: 2116/530, loss: 0.11522826552391052
2023-01-21 10:44:22.615118: step: 2120/530, loss: 0.00948495976626873
==================================================
Loss: 0.080
--------------------
Dev: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5974025974025974, 'r': 0.8518518518518519, 'f1': 0.7022900763358778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.425, 'r': 0.4722222222222222, 'f1': 0.4473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:45:14.244154: step: 4/530, loss: 0.07398071140050888
2023-01-21 10:45:15.372841: step: 8/530, loss: 0.040528297424316406
2023-01-21 10:45:16.536523: step: 12/530, loss: 0.033846285194158554
2023-01-21 10:45:17.673171: step: 16/530, loss: 0.061208344995975494
2023-01-21 10:45:18.813424: step: 20/530, loss: 0.014437771402299404
2023-01-21 10:45:19.938797: step: 24/530, loss: 0.019230078905820847
2023-01-21 10:45:21.110209: step: 28/530, loss: 0.040814876556396484
2023-01-21 10:45:22.232693: step: 32/530, loss: 0.015940189361572266
2023-01-21 10:45:23.399656: step: 36/530, loss: 0.012237166985869408
2023-01-21 10:45:24.560977: step: 40/530, loss: 0.06769218295812607
2023-01-21 10:45:25.727296: step: 44/530, loss: 0.021685171872377396
2023-01-21 10:45:26.860767: step: 48/530, loss: 0.039278794080019
2023-01-21 10:45:28.009861: step: 52/530, loss: 0.09032197296619415
2023-01-21 10:45:29.147964: step: 56/530, loss: 0.002974605653434992
2023-01-21 10:45:30.268664: step: 60/530, loss: 0.03060626983642578
2023-01-21 10:45:31.442514: step: 64/530, loss: 0.36522141098976135
2023-01-21 10:45:32.617950: step: 68/530, loss: 0.004154587164521217
2023-01-21 10:45:33.786309: step: 72/530, loss: 0.016639327630400658
2023-01-21 10:45:34.937855: step: 76/530, loss: 0.803027868270874
2023-01-21 10:45:36.056021: step: 80/530, loss: 0.021478844806551933
2023-01-21 10:45:37.199879: step: 84/530, loss: 0.019259978085756302
2023-01-21 10:45:38.335708: step: 88/530, loss: 0.21379566192626953
2023-01-21 10:45:39.485189: step: 92/530, loss: 0.13825759291648865
2023-01-21 10:45:40.646159: step: 96/530, loss: 0.0801246166229248
2023-01-21 10:45:41.753561: step: 100/530, loss: 0.05334510654211044
2023-01-21 10:45:42.908214: step: 104/530, loss: 0.04725246503949165
2023-01-21 10:45:44.038825: step: 108/530, loss: 0.09036903828382492
2023-01-21 10:45:45.190513: step: 112/530, loss: 0.03862859308719635
2023-01-21 10:45:46.351188: step: 116/530, loss: 0.008417701348662376
2023-01-21 10:45:47.494238: step: 120/530, loss: 0.001842498779296875
2023-01-21 10:45:48.651903: step: 124/530, loss: 0.02998790517449379
2023-01-21 10:45:49.825873: step: 128/530, loss: 0.008072090335190296
2023-01-21 10:45:50.958758: step: 132/530, loss: 0.00067563058109954
2023-01-21 10:45:52.113476: step: 136/530, loss: 0.013930797576904297
2023-01-21 10:45:53.282348: step: 140/530, loss: 0.03284607082605362
2023-01-21 10:45:54.485515: step: 144/530, loss: 0.01740550994873047
2023-01-21 10:45:55.623048: step: 148/530, loss: 0.01164555549621582
2023-01-21 10:45:56.765280: step: 152/530, loss: 0.021640967577695847
2023-01-21 10:45:57.909650: step: 156/530, loss: 0.030883314087986946
2023-01-21 10:45:59.061775: step: 160/530, loss: 0.040308572351932526
2023-01-21 10:46:00.216883: step: 164/530, loss: 0.15443038940429688
2023-01-21 10:46:01.328689: step: 168/530, loss: 0.0005220413440838456
2023-01-21 10:46:02.474767: step: 172/530, loss: 0.02633199840784073
2023-01-21 10:46:03.648435: step: 176/530, loss: 0.03239555284380913
2023-01-21 10:46:04.811434: step: 180/530, loss: 0.005229187197983265
2023-01-21 10:46:05.947439: step: 184/530, loss: 0.02136669121682644
2023-01-21 10:46:07.108175: step: 188/530, loss: 0.18294048309326172
2023-01-21 10:46:08.256343: step: 192/530, loss: 0.00397415179759264
2023-01-21 10:46:09.419588: step: 196/530, loss: 0.0024996281135827303
2023-01-21 10:46:10.572985: step: 200/530, loss: 0.05724659189581871
2023-01-21 10:46:11.715841: step: 204/530, loss: 0.0010045052040368319
2023-01-21 10:46:12.861110: step: 208/530, loss: 0.008377457037568092
2023-01-21 10:46:14.034943: step: 212/530, loss: 0.0017427444690838456
2023-01-21 10:46:15.141087: step: 216/530, loss: 0.006104993633925915
2023-01-21 10:46:16.264458: step: 220/530, loss: 0.07204703986644745
2023-01-21 10:46:17.446110: step: 224/530, loss: 0.013346672058105469
2023-01-21 10:46:18.598451: step: 228/530, loss: 0.0033665657974779606
2023-01-21 10:46:19.766644: step: 232/530, loss: 0.0005195617559365928
2023-01-21 10:46:20.899806: step: 236/530, loss: 0.0021766661666333675
2023-01-21 10:46:22.061177: step: 240/530, loss: 0.02127990871667862
2023-01-21 10:46:23.208823: step: 244/530, loss: 0.04345512390136719
2023-01-21 10:46:24.372772: step: 248/530, loss: 0.02390117570757866
2023-01-21 10:46:25.525358: step: 252/530, loss: 0.014167689718306065
2023-01-21 10:46:26.689274: step: 256/530, loss: 0.08022921532392502
2023-01-21 10:46:27.826380: step: 260/530, loss: 0.08356304466724396
2023-01-21 10:46:28.990797: step: 264/530, loss: 0.079462431371212
2023-01-21 10:46:30.124873: step: 268/530, loss: 0.01774435117840767
2023-01-21 10:46:31.252259: step: 272/530, loss: 0.012601470574736595
2023-01-21 10:46:32.365957: step: 276/530, loss: 0.01583128049969673
2023-01-21 10:46:33.499273: step: 280/530, loss: 0.15616551041603088
2023-01-21 10:46:34.660243: step: 284/530, loss: 0.0051246643997728825
2023-01-21 10:46:35.821172: step: 288/530, loss: 0.04609479755163193
2023-01-21 10:46:36.945795: step: 292/530, loss: 0.001565313432365656
2023-01-21 10:46:38.087333: step: 296/530, loss: 0.0015541077591478825
2023-01-21 10:46:39.230635: step: 300/530, loss: 0.04877987131476402
2023-01-21 10:46:40.389771: step: 304/530, loss: 0.05408892780542374
2023-01-21 10:46:41.521681: step: 308/530, loss: 0.016455842182040215
2023-01-21 10:46:42.633012: step: 312/530, loss: 0.022357558831572533
2023-01-21 10:46:43.759322: step: 316/530, loss: 0.040270138531923294
2023-01-21 10:46:44.899692: step: 320/530, loss: 0.00941934622824192
2023-01-21 10:46:46.071595: step: 324/530, loss: 0.058518312871456146
2023-01-21 10:46:47.206944: step: 328/530, loss: 0.009145354852080345
2023-01-21 10:46:48.351500: step: 332/530, loss: 0.07680606842041016
2023-01-21 10:46:49.481265: step: 336/530, loss: 0.030954742804169655
2023-01-21 10:46:50.613648: step: 340/530, loss: 0.011797047220170498
2023-01-21 10:46:51.758359: step: 344/530, loss: 0.009526061825454235
2023-01-21 10:46:52.915460: step: 348/530, loss: 0.02530832216143608
2023-01-21 10:46:54.075049: step: 352/530, loss: 0.04044971615076065
2023-01-21 10:46:55.211989: step: 356/530, loss: 0.009169482626020908
2023-01-21 10:46:56.339978: step: 360/530, loss: 0.0006190777057781816
2023-01-21 10:46:57.433659: step: 364/530, loss: 0.018922805786132812
2023-01-21 10:46:58.587253: step: 368/530, loss: 0.01688690297305584
2023-01-21 10:46:59.740421: step: 372/530, loss: 0.09695987403392792
2023-01-21 10:47:00.874748: step: 376/530, loss: 0.028640173375606537
2023-01-21 10:47:02.087095: step: 380/530, loss: 0.03937482833862305
2023-01-21 10:47:03.246930: step: 384/530, loss: 0.008267381228506565
2023-01-21 10:47:04.366040: step: 388/530, loss: 0.05264930799603462
2023-01-21 10:47:05.514836: step: 392/530, loss: 0.04300546646118164
2023-01-21 10:47:06.630970: step: 396/530, loss: 0.036551475524902344
2023-01-21 10:47:07.794026: step: 400/530, loss: 0.0185044277459383
2023-01-21 10:47:08.923255: step: 404/530, loss: 0.025232840329408646
2023-01-21 10:47:10.067519: step: 408/530, loss: 0.0014047622680664062
2023-01-21 10:47:11.201668: step: 412/530, loss: 0.003603649325668812
2023-01-21 10:47:12.356010: step: 416/530, loss: 0.005042076110839844
2023-01-21 10:47:13.517616: step: 420/530, loss: 0.1185854896903038
2023-01-21 10:47:14.638373: step: 424/530, loss: 0.016942406073212624
2023-01-21 10:47:15.758288: step: 428/530, loss: 0.0016430855030193925
2023-01-21 10:47:16.899991: step: 432/530, loss: 0.08309340476989746
2023-01-21 10:47:18.046458: step: 436/530, loss: 0.010507297702133656
2023-01-21 10:47:19.179651: step: 440/530, loss: 0.012030982412397861
2023-01-21 10:47:20.299970: step: 444/530, loss: 0.04357652738690376
2023-01-21 10:47:21.434573: step: 448/530, loss: 0.05668983608484268
2023-01-21 10:47:22.550918: step: 452/530, loss: 0.006683635991066694
2023-01-21 10:47:23.676099: step: 456/530, loss: 0.012692738324403763
2023-01-21 10:47:24.834382: step: 460/530, loss: 0.0013941765064373612
2023-01-21 10:47:25.977565: step: 464/530, loss: 0.023555375635623932
2023-01-21 10:47:27.108678: step: 468/530, loss: 0.027986811473965645
2023-01-21 10:47:28.234540: step: 472/530, loss: 0.03971405327320099
2023-01-21 10:47:29.346170: step: 476/530, loss: 0.007008934393525124
2023-01-21 10:47:30.488225: step: 480/530, loss: 0.008699417114257812
2023-01-21 10:47:31.640358: step: 484/530, loss: 0.01346063707023859
2023-01-21 10:47:32.771058: step: 488/530, loss: 0.02027721516788006
2023-01-21 10:47:33.933282: step: 492/530, loss: 0.016364289447665215
2023-01-21 10:47:35.062054: step: 496/530, loss: 0.02846050262451172
2023-01-21 10:47:36.217106: step: 500/530, loss: 0.05443897098302841
2023-01-21 10:47:37.348357: step: 504/530, loss: 0.04571991041302681
2023-01-21 10:47:38.474849: step: 508/530, loss: 2.8133392333984375e-05
2023-01-21 10:47:39.620772: step: 512/530, loss: 0.012814999558031559
2023-01-21 10:47:40.758063: step: 516/530, loss: 0.03642425686120987
2023-01-21 10:47:41.867018: step: 520/530, loss: 0.028331659734249115
2023-01-21 10:47:42.977189: step: 524/530, loss: 0.037322428077459335
2023-01-21 10:47:44.139725: step: 528/530, loss: 0.0013184548588469625
2023-01-21 10:47:45.301702: step: 532/530, loss: 0.04839382320642471
2023-01-21 10:47:46.454998: step: 536/530, loss: 0.007972908206284046
2023-01-21 10:47:47.607273: step: 540/530, loss: 0.025253869593143463
2023-01-21 10:47:48.784771: step: 544/530, loss: 0.048673249781131744
2023-01-21 10:47:49.936800: step: 548/530, loss: 0.47579923272132874
2023-01-21 10:47:51.058607: step: 552/530, loss: 0.04266681522130966
2023-01-21 10:47:52.194504: step: 556/530, loss: 0.008650589734315872
2023-01-21 10:47:53.350021: step: 560/530, loss: 0.05090532451868057
2023-01-21 10:47:54.508499: step: 564/530, loss: 0.014536334201693535
2023-01-21 10:47:55.660869: step: 568/530, loss: 0.013978386297821999
2023-01-21 10:47:56.828056: step: 572/530, loss: 0.009700680151581764
2023-01-21 10:47:57.984910: step: 576/530, loss: 0.014577674679458141
2023-01-21 10:47:59.109952: step: 580/530, loss: 0.10754165053367615
2023-01-21 10:48:00.262115: step: 584/530, loss: 1.4149501323699951
2023-01-21 10:48:01.397410: step: 588/530, loss: 0.015349960885941982
2023-01-21 10:48:02.566575: step: 592/530, loss: 0.05725135654211044
2023-01-21 10:48:03.735494: step: 596/530, loss: 0.01492157019674778
2023-01-21 10:48:04.917956: step: 600/530, loss: 0.005946350283920765
2023-01-21 10:48:06.058627: step: 604/530, loss: 0.05546889454126358
2023-01-21 10:48:07.217943: step: 608/530, loss: 0.018617058172822
2023-01-21 10:48:08.369959: step: 612/530, loss: 0.03833752125501633
2023-01-21 10:48:09.520312: step: 616/530, loss: 0.02911682240664959
2023-01-21 10:48:10.644280: step: 620/530, loss: 0.013194657862186432
2023-01-21 10:48:11.812073: step: 624/530, loss: 0.005923461634665728
2023-01-21 10:48:12.975224: step: 628/530, loss: 0.010469531640410423
2023-01-21 10:48:14.104356: step: 632/530, loss: 0.14634600281715393
2023-01-21 10:48:15.242485: step: 636/530, loss: 0.03739814832806587
2023-01-21 10:48:16.367214: step: 640/530, loss: 0.011187553405761719
2023-01-21 10:48:17.501425: step: 644/530, loss: 0.023834586143493652
2023-01-21 10:48:18.653373: step: 648/530, loss: 0.013212013989686966
2023-01-21 10:48:19.811840: step: 652/530, loss: 0.06017895042896271
2023-01-21 10:48:20.982917: step: 656/530, loss: 0.0145111083984375
2023-01-21 10:48:22.114515: step: 660/530, loss: 0.03867216408252716
2023-01-21 10:48:23.264553: step: 664/530, loss: 0.039589788764715195
2023-01-21 10:48:24.434403: step: 668/530, loss: 0.010405921377241611
2023-01-21 10:48:25.590557: step: 672/530, loss: 0.0029806136153638363
2023-01-21 10:48:26.751391: step: 676/530, loss: 0.5452859997749329
2023-01-21 10:48:27.903668: step: 680/530, loss: 0.015895556658506393
2023-01-21 10:48:29.064242: step: 684/530, loss: 0.0563511848449707
2023-01-21 10:48:30.202081: step: 688/530, loss: 0.04863701015710831
2023-01-21 10:48:31.320453: step: 692/530, loss: 0.03756413608789444
2023-01-21 10:48:32.496936: step: 696/530, loss: 0.061608411371707916
2023-01-21 10:48:33.633834: step: 700/530, loss: 0.012370491400361061
2023-01-21 10:48:34.804172: step: 704/530, loss: 0.04571247100830078
2023-01-21 10:48:35.941386: step: 708/530, loss: 0.05659017711877823
2023-01-21 10:48:37.103021: step: 712/530, loss: 0.0012090683449059725
2023-01-21 10:48:38.243643: step: 716/530, loss: 0.017827987670898438
2023-01-21 10:48:39.408725: step: 720/530, loss: 0.0004285812610760331
2023-01-21 10:48:40.550050: step: 724/530, loss: 0.0041939737275242805
2023-01-21 10:48:41.651708: step: 728/530, loss: 0.10186271369457245
2023-01-21 10:48:42.779728: step: 732/530, loss: 0.03255319595336914
2023-01-21 10:48:43.911399: step: 736/530, loss: 0.0075965882278978825
2023-01-21 10:48:45.018759: step: 740/530, loss: 0.03246726840734482
2023-01-21 10:48:46.134773: step: 744/530, loss: 0.05694274976849556
2023-01-21 10:48:47.285483: step: 748/530, loss: 0.07809115201234818
2023-01-21 10:48:48.437353: step: 752/530, loss: 0.03993682935833931
2023-01-21 10:48:49.561265: step: 756/530, loss: 0.020905494689941406
2023-01-21 10:48:50.707678: step: 760/530, loss: 0.011625099927186966
2023-01-21 10:48:51.880760: step: 764/530, loss: 0.8200300335884094
2023-01-21 10:48:53.023580: step: 768/530, loss: 0.020424747839570045
2023-01-21 10:48:54.170265: step: 772/530, loss: 0.03499555587768555
2023-01-21 10:48:55.291340: step: 776/530, loss: 0.05534668266773224
2023-01-21 10:48:56.428541: step: 780/530, loss: 0.04006495699286461
2023-01-21 10:48:57.591135: step: 784/530, loss: 0.20489098131656647
2023-01-21 10:48:58.738843: step: 788/530, loss: 0.02467327192425728
2023-01-21 10:48:59.876177: step: 792/530, loss: 0.00025119780912064016
2023-01-21 10:49:01.010318: step: 796/530, loss: 0.04124889522790909
2023-01-21 10:49:02.171451: step: 800/530, loss: 0.036313820630311966
2023-01-21 10:49:03.291173: step: 804/530, loss: 0.10097198933362961
2023-01-21 10:49:04.423079: step: 808/530, loss: 0.011997032910585403
2023-01-21 10:49:05.534550: step: 812/530, loss: 0.007013249211013317
2023-01-21 10:49:06.676529: step: 816/530, loss: 0.03416423872113228
2023-01-21 10:49:07.803231: step: 820/530, loss: 0.18572503328323364
2023-01-21 10:49:08.985449: step: 824/530, loss: 0.018530750647187233
2023-01-21 10:49:10.132045: step: 828/530, loss: 0.0008031845209188759
2023-01-21 10:49:11.289035: step: 832/530, loss: 0.111823171377182
2023-01-21 10:49:12.462754: step: 836/530, loss: 0.00376548757776618
2023-01-21 10:49:13.611501: step: 840/530, loss: 0.09680958092212677
2023-01-21 10:49:14.776280: step: 844/530, loss: 0.00603141775354743
2023-01-21 10:49:15.902146: step: 848/530, loss: 0.045821402221918106
2023-01-21 10:49:17.037775: step: 852/530, loss: 0.031633950769901276
2023-01-21 10:49:18.179464: step: 856/530, loss: 0.03334445878863335
2023-01-21 10:49:19.291861: step: 860/530, loss: 0.07749243080615997
2023-01-21 10:49:20.422554: step: 864/530, loss: 0.049832917749881744
2023-01-21 10:49:21.622037: step: 868/530, loss: 0.01040792465209961
2023-01-21 10:49:22.759244: step: 872/530, loss: 0.08721017837524414
2023-01-21 10:49:23.916864: step: 876/530, loss: 0.24433784186840057
2023-01-21 10:49:25.052447: step: 880/530, loss: 0.03598470985889435
2023-01-21 10:49:26.181158: step: 884/530, loss: 0.004406738560646772
2023-01-21 10:49:27.339258: step: 888/530, loss: 0.326913446187973
2023-01-21 10:49:28.481277: step: 892/530, loss: 0.04628896713256836
2023-01-21 10:49:29.579343: step: 896/530, loss: 0.025586891919374466
2023-01-21 10:49:30.702818: step: 900/530, loss: 0.039945222437381744
2023-01-21 10:49:31.836676: step: 904/530, loss: 0.009619045071303844
2023-01-21 10:49:32.961171: step: 908/530, loss: 0.02143258973956108
2023-01-21 10:49:34.109554: step: 912/530, loss: 0.0413791686296463
2023-01-21 10:49:35.254338: step: 916/530, loss: 0.05025697126984596
2023-01-21 10:49:36.379423: step: 920/530, loss: 0.3042936325073242
2023-01-21 10:49:37.496565: step: 924/530, loss: 0.02534313127398491
2023-01-21 10:49:38.647557: step: 928/530, loss: 0.02383415773510933
2023-01-21 10:49:39.803056: step: 932/530, loss: 0.19055995345115662
2023-01-21 10:49:40.927415: step: 936/530, loss: 0.003114700550213456
2023-01-21 10:49:42.062063: step: 940/530, loss: 0.015610313974320889
2023-01-21 10:49:43.224399: step: 944/530, loss: 0.01200723648071289
2023-01-21 10:49:44.332707: step: 948/530, loss: 0.0345064178109169
2023-01-21 10:49:45.437965: step: 952/530, loss: 0.06942739337682724
2023-01-21 10:49:46.575635: step: 956/530, loss: 0.08161535114049911
2023-01-21 10:49:47.706498: step: 960/530, loss: 0.0808025375008583
2023-01-21 10:49:48.849820: step: 964/530, loss: 0.03148593753576279
2023-01-21 10:49:49.973505: step: 968/530, loss: 0.05908598750829697
2023-01-21 10:49:51.094869: step: 972/530, loss: 0.23652076721191406
2023-01-21 10:49:52.245669: step: 976/530, loss: 0.008577823638916016
2023-01-21 10:49:53.395902: step: 980/530, loss: 0.012327003292739391
2023-01-21 10:49:54.542957: step: 984/530, loss: 0.2261420339345932
2023-01-21 10:49:55.696827: step: 988/530, loss: 0.060776807367801666
2023-01-21 10:49:56.868484: step: 992/530, loss: 0.018669700250029564
2023-01-21 10:49:58.008502: step: 996/530, loss: 0.047416117042303085
2023-01-21 10:49:59.132678: step: 1000/530, loss: 0.04935278743505478
2023-01-21 10:50:00.293145: step: 1004/530, loss: 0.024928638711571693
2023-01-21 10:50:01.440197: step: 1008/530, loss: 0.021472929045557976
2023-01-21 10:50:02.580219: step: 1012/530, loss: 0.029722262173891068
2023-01-21 10:50:03.737283: step: 1016/530, loss: 0.09951954334974289
2023-01-21 10:50:04.878190: step: 1020/530, loss: 0.0039619444869458675
2023-01-21 10:50:06.033207: step: 1024/530, loss: 0.0562870018184185
2023-01-21 10:50:07.138622: step: 1028/530, loss: 0.0490182526409626
2023-01-21 10:50:08.298842: step: 1032/530, loss: 0.06122525781393051
2023-01-21 10:50:09.413143: step: 1036/530, loss: 0.046708058565855026
2023-01-21 10:50:10.619453: step: 1040/530, loss: 0.00039358140202239156
2023-01-21 10:50:11.747510: step: 1044/530, loss: 0.08382701873779297
2023-01-21 10:50:12.868704: step: 1048/530, loss: 0.08624887466430664
2023-01-21 10:50:13.999573: step: 1052/530, loss: 0.03083954006433487
2023-01-21 10:50:15.149506: step: 1056/530, loss: 0.0290464386343956
2023-01-21 10:50:16.261777: step: 1060/530, loss: 0.11408348381519318
2023-01-21 10:50:17.396009: step: 1064/530, loss: 0.03804807737469673
2023-01-21 10:50:18.531548: step: 1068/530, loss: 0.008701324462890625
2023-01-21 10:50:19.675058: step: 1072/530, loss: 0.0008764266967773438
2023-01-21 10:50:20.815654: step: 1076/530, loss: 0.031462620943784714
2023-01-21 10:50:21.928224: step: 1080/530, loss: 0.01626615598797798
2023-01-21 10:50:23.066297: step: 1084/530, loss: 0.050166890025138855
2023-01-21 10:50:24.198111: step: 1088/530, loss: 0.019926857203245163
2023-01-21 10:50:25.343286: step: 1092/530, loss: 0.025343704968690872
2023-01-21 10:50:26.474803: step: 1096/530, loss: 0.06629572063684464
2023-01-21 10:50:27.608095: step: 1100/530, loss: 0.015285802073776722
2023-01-21 10:50:28.749953: step: 1104/530, loss: 0.03376542031764984
2023-01-21 10:50:29.886087: step: 1108/530, loss: 0.06569776684045792
2023-01-21 10:50:31.016763: step: 1112/530, loss: 0.037779998034238815
2023-01-21 10:50:32.177121: step: 1116/530, loss: 0.09744323045015335
2023-01-21 10:50:33.328787: step: 1120/530, loss: 0.05023784935474396
2023-01-21 10:50:34.485955: step: 1124/530, loss: 0.04346742480993271
2023-01-21 10:50:35.589492: step: 1128/530, loss: 0.03752937540411949
2023-01-21 10:50:36.748066: step: 1132/530, loss: 0.0013034821022301912
2023-01-21 10:50:37.898308: step: 1136/530, loss: 0.03620576858520508
2023-01-21 10:50:39.021589: step: 1140/530, loss: 0.016366004943847656
2023-01-21 10:50:40.164360: step: 1144/530, loss: 0.025661468505859375
2023-01-21 10:50:41.308344: step: 1148/530, loss: 0.023536063730716705
2023-01-21 10:50:42.438832: step: 1152/530, loss: 0.08747889846563339
2023-01-21 10:50:43.575917: step: 1156/530, loss: 0.05126542970538139
2023-01-21 10:50:44.685374: step: 1160/530, loss: 0.0679684653878212
2023-01-21 10:50:45.809634: step: 1164/530, loss: 0.04883904755115509
2023-01-21 10:50:46.935022: step: 1168/530, loss: 0.2679372727870941
2023-01-21 10:50:48.086428: step: 1172/530, loss: 0.015944385901093483
2023-01-21 10:50:49.246740: step: 1176/530, loss: 0.1687939167022705
2023-01-21 10:50:50.392406: step: 1180/530, loss: 0.013532734476029873
2023-01-21 10:50:51.512855: step: 1184/530, loss: 0.0886436477303505
2023-01-21 10:50:52.674473: step: 1188/530, loss: 0.03256569057703018
2023-01-21 10:50:53.786975: step: 1192/530, loss: 0.013889789581298828
2023-01-21 10:50:54.918036: step: 1196/530, loss: 0.04050111770629883
2023-01-21 10:50:56.066888: step: 1200/530, loss: 0.03629150241613388
2023-01-21 10:50:57.247384: step: 1204/530, loss: 0.07319466769695282
2023-01-21 10:50:58.391901: step: 1208/530, loss: 0.026548005640506744
2023-01-21 10:50:59.498299: step: 1212/530, loss: 0.013202667236328125
2023-01-21 10:51:00.633519: step: 1216/530, loss: 0.01926402933895588
2023-01-21 10:51:01.749631: step: 1220/530, loss: 0.182640939950943
2023-01-21 10:51:02.877817: step: 1224/530, loss: 0.09590368717908859
2023-01-21 10:51:04.001350: step: 1228/530, loss: 0.005127239506691694
2023-01-21 10:51:05.120516: step: 1232/530, loss: 0.021857118234038353
2023-01-21 10:51:06.250036: step: 1236/530, loss: 0.02572507970035076
2023-01-21 10:51:07.400053: step: 1240/530, loss: 0.0413665771484375
2023-01-21 10:51:08.554688: step: 1244/530, loss: 0.0046179769560694695
2023-01-21 10:51:09.665075: step: 1248/530, loss: 0.013308191671967506
2023-01-21 10:51:10.793623: step: 1252/530, loss: 0.008606291376054287
2023-01-21 10:51:11.908066: step: 1256/530, loss: 0.010782265104353428
2023-01-21 10:51:13.058410: step: 1260/530, loss: 0.19547052681446075
2023-01-21 10:51:14.180417: step: 1264/530, loss: 0.054781630635261536
2023-01-21 10:51:15.325196: step: 1268/530, loss: 0.00021877288236282766
2023-01-21 10:51:16.455244: step: 1272/530, loss: 0.029821300879120827
2023-01-21 10:51:17.601346: step: 1276/530, loss: 0.01794891431927681
2023-01-21 10:51:18.752214: step: 1280/530, loss: 0.06071462854743004
2023-01-21 10:51:19.888378: step: 1284/530, loss: 0.0012153149582445621
2023-01-21 10:51:21.035099: step: 1288/530, loss: 0.05071248859167099
2023-01-21 10:51:22.161304: step: 1292/530, loss: 0.009397363290190697
2023-01-21 10:51:23.294231: step: 1296/530, loss: 0.032709695398807526
2023-01-21 10:51:24.414833: step: 1300/530, loss: 0.1351376473903656
2023-01-21 10:51:25.535880: step: 1304/530, loss: 0.009944058023393154
2023-01-21 10:51:26.639858: step: 1308/530, loss: 0.045655060559511185
2023-01-21 10:51:27.769066: step: 1312/530, loss: 0.0862884521484375
2023-01-21 10:51:28.892846: step: 1316/530, loss: 0.011104297824203968
2023-01-21 10:51:30.032969: step: 1320/530, loss: 0.0068988800048828125
2023-01-21 10:51:31.149386: step: 1324/530, loss: 0.011665822006762028
2023-01-21 10:51:32.246611: step: 1328/530, loss: 0.02241211012005806
2023-01-21 10:51:33.376040: step: 1332/530, loss: 0.046392299234867096
2023-01-21 10:51:34.530936: step: 1336/530, loss: 0.0018444061279296875
2023-01-21 10:51:35.719705: step: 1340/530, loss: 0.05024013668298721
2023-01-21 10:51:36.858228: step: 1344/530, loss: 0.0178254134953022
2023-01-21 10:51:37.975978: step: 1348/530, loss: 0.04663848876953125
2023-01-21 10:51:39.104677: step: 1352/530, loss: 0.06724052131175995
2023-01-21 10:51:40.280015: step: 1356/530, loss: 0.009629917331039906
2023-01-21 10:51:41.392189: step: 1360/530, loss: 0.02982483059167862
2023-01-21 10:51:42.550423: step: 1364/530, loss: 0.0008590698707848787
2023-01-21 10:51:43.678323: step: 1368/530, loss: 0.05316190794110298
2023-01-21 10:51:44.779022: step: 1372/530, loss: 0.001986694522202015
2023-01-21 10:51:45.935598: step: 1376/530, loss: 0.050048112869262695
2023-01-21 10:51:47.043035: step: 1380/530, loss: 0.02764434926211834
2023-01-21 10:51:48.160706: step: 1384/530, loss: 0.030058478936553
2023-01-21 10:51:49.304541: step: 1388/530, loss: 0.03251190111041069
2023-01-21 10:51:50.434989: step: 1392/530, loss: 0.08532381057739258
2023-01-21 10:51:51.569432: step: 1396/530, loss: 0.04369411617517471
2023-01-21 10:51:52.715900: step: 1400/530, loss: 0.0405157133936882
2023-01-21 10:51:53.847847: step: 1404/530, loss: 0.014038181863725185
2023-01-21 10:51:54.979025: step: 1408/530, loss: 0.011718273162841797
2023-01-21 10:51:56.153658: step: 1412/530, loss: 0.028931427747011185
2023-01-21 10:51:57.265771: step: 1416/530, loss: 0.13845320045948029
2023-01-21 10:51:58.407767: step: 1420/530, loss: 0.09256420284509659
2023-01-21 10:51:59.543013: step: 1424/530, loss: 0.00949859619140625
2023-01-21 10:52:00.739275: step: 1428/530, loss: 0.014885520562529564
2023-01-21 10:52:01.866319: step: 1432/530, loss: 0.01170492172241211
2023-01-21 10:52:02.997521: step: 1436/530, loss: 0.03163490444421768
2023-01-21 10:52:04.139380: step: 1440/530, loss: 0.008007621392607689
2023-01-21 10:52:05.262203: step: 1444/530, loss: 0.011084175668656826
2023-01-21 10:52:06.413260: step: 1448/530, loss: 0.006390380673110485
2023-01-21 10:52:07.524883: step: 1452/530, loss: 0.023880815133452415
2023-01-21 10:52:08.643763: step: 1456/530, loss: 0.020429516211152077
2023-01-21 10:52:09.760649: step: 1460/530, loss: 0.03908605873584747
2023-01-21 10:52:10.915886: step: 1464/530, loss: 0.007166767027229071
2023-01-21 10:52:12.083573: step: 1468/530, loss: 0.08937874436378479
2023-01-21 10:52:13.226249: step: 1472/530, loss: 0.03241314738988876
2023-01-21 10:52:14.320102: step: 1476/530, loss: 0.012744748964905739
2023-01-21 10:52:15.459977: step: 1480/530, loss: 0.008614778518676758
2023-01-21 10:52:16.573141: step: 1484/530, loss: 0.02712726593017578
2023-01-21 10:52:17.697977: step: 1488/530, loss: 0.02927122265100479
2023-01-21 10:52:18.832276: step: 1492/530, loss: 0.022269820794463158
2023-01-21 10:52:19.981284: step: 1496/530, loss: 0.022495746612548828
2023-01-21 10:52:21.118302: step: 1500/530, loss: 0.03468479961156845
2023-01-21 10:52:22.249200: step: 1504/530, loss: 0.0064643267542123795
2023-01-21 10:52:23.427150: step: 1508/530, loss: 0.027135848999023438
2023-01-21 10:52:24.564299: step: 1512/530, loss: 0.17398318648338318
2023-01-21 10:52:25.699194: step: 1516/530, loss: 0.052553750574588776
2023-01-21 10:52:26.844288: step: 1520/530, loss: 0.03342113643884659
2023-01-21 10:52:28.027384: step: 1524/530, loss: 0.02911529690027237
2023-01-21 10:52:29.190527: step: 1528/530, loss: 0.055855441838502884
2023-01-21 10:52:30.364388: step: 1532/530, loss: 0.04987840726971626
2023-01-21 10:52:31.500158: step: 1536/530, loss: 0.023444557562470436
2023-01-21 10:52:32.633492: step: 1540/530, loss: 0.008450699038803577
2023-01-21 10:52:33.802116: step: 1544/530, loss: 0.004190301988273859
2023-01-21 10:52:34.939107: step: 1548/530, loss: 0.01269979402422905
2023-01-21 10:52:36.117287: step: 1552/530, loss: 0.6657583117485046
2023-01-21 10:52:37.262358: step: 1556/530, loss: 0.044672489166259766
2023-01-21 10:52:38.404980: step: 1560/530, loss: 0.026215698570013046
2023-01-21 10:52:39.512506: step: 1564/530, loss: 0.008369358256459236
2023-01-21 10:52:40.648279: step: 1568/530, loss: 0.06663589179515839
2023-01-21 10:52:41.810615: step: 1572/530, loss: 0.06325502693653107
2023-01-21 10:52:42.941808: step: 1576/530, loss: 0.006842422299087048
2023-01-21 10:52:44.116823: step: 1580/530, loss: 0.14408570528030396
2023-01-21 10:52:45.255594: step: 1584/530, loss: 0.05181474611163139
2023-01-21 10:52:46.420083: step: 1588/530, loss: 0.013959884643554688
2023-01-21 10:52:47.580291: step: 1592/530, loss: 0.05548761039972305
2023-01-21 10:52:48.733795: step: 1596/530, loss: 0.03722257539629936
2023-01-21 10:52:49.889170: step: 1600/530, loss: 0.08740988373756409
2023-01-21 10:52:51.004571: step: 1604/530, loss: 0.06963644176721573
2023-01-21 10:52:52.140389: step: 1608/530, loss: 0.017441559582948685
2023-01-21 10:52:53.276679: step: 1612/530, loss: 0.018889809027314186
2023-01-21 10:52:54.403030: step: 1616/530, loss: 0.04833946377038956
2023-01-21 10:52:55.532244: step: 1620/530, loss: 0.04017071798443794
2023-01-21 10:52:56.665906: step: 1624/530, loss: 0.044857535511255264
2023-01-21 10:52:57.773745: step: 1628/530, loss: 0.0030335187911987305
2023-01-21 10:52:58.906128: step: 1632/530, loss: 0.05566072463989258
2023-01-21 10:53:00.027587: step: 1636/530, loss: 0.047643475234508514
2023-01-21 10:53:01.219588: step: 1640/530, loss: 0.017865944653749466
2023-01-21 10:53:02.343471: step: 1644/530, loss: 0.01834592968225479
2023-01-21 10:53:03.476767: step: 1648/530, loss: 0.03781948238611221
2023-01-21 10:53:04.650954: step: 1652/530, loss: 0.030655860900878906
2023-01-21 10:53:05.778563: step: 1656/530, loss: 0.033209990710020065
2023-01-21 10:53:06.908247: step: 1660/530, loss: 0.04573860019445419
2023-01-21 10:53:08.032628: step: 1664/530, loss: 0.020556068047881126
2023-01-21 10:53:09.165504: step: 1668/530, loss: 0.006572437472641468
2023-01-21 10:53:10.348359: step: 1672/530, loss: 0.058839987963438034
2023-01-21 10:53:11.507967: step: 1676/530, loss: 0.010986709967255592
2023-01-21 10:53:12.628095: step: 1680/530, loss: 0.03487148508429527
2023-01-21 10:53:13.743146: step: 1684/530, loss: 0.009535599499940872
2023-01-21 10:53:14.874026: step: 1688/530, loss: 0.44318628311157227
2023-01-21 10:53:16.023589: step: 1692/530, loss: 0.030763745307922363
2023-01-21 10:53:17.176625: step: 1696/530, loss: 0.0001489639253122732
2023-01-21 10:53:18.311899: step: 1700/530, loss: 0.0012716293567791581
2023-01-21 10:53:19.459776: step: 1704/530, loss: 0.0171247236430645
2023-01-21 10:53:20.580797: step: 1708/530, loss: 0.02732543833553791
2023-01-21 10:53:21.729107: step: 1712/530, loss: 0.013888073153793812
2023-01-21 10:53:22.888572: step: 1716/530, loss: 0.030884599313139915
2023-01-21 10:53:24.030340: step: 1720/530, loss: 0.007103061769157648
2023-01-21 10:53:25.174145: step: 1724/530, loss: 0.004729175940155983
2023-01-21 10:53:26.311845: step: 1728/530, loss: 0.05706644058227539
2023-01-21 10:53:27.448644: step: 1732/530, loss: 0.005995369050651789
2023-01-21 10:53:28.576821: step: 1736/530, loss: 0.0003991127014160156
2023-01-21 10:53:29.704843: step: 1740/530, loss: 0.6925798058509827
2023-01-21 10:53:30.846077: step: 1744/530, loss: 0.04055919498205185
2023-01-21 10:53:31.978237: step: 1748/530, loss: 0.002102470491081476
2023-01-21 10:53:33.161613: step: 1752/530, loss: 0.07019243389368057
2023-01-21 10:53:34.320002: step: 1756/530, loss: 0.05658683925867081
2023-01-21 10:53:35.454917: step: 1760/530, loss: 0.002086341381072998
2023-01-21 10:53:36.578535: step: 1764/530, loss: 0.001577663468196988
2023-01-21 10:53:37.744381: step: 1768/530, loss: 0.006244373507797718
2023-01-21 10:53:38.901048: step: 1772/530, loss: 0.3612518310546875
2023-01-21 10:53:40.022665: step: 1776/530, loss: 0.015101909637451172
2023-01-21 10:53:41.148688: step: 1780/530, loss: 0.0847724974155426
2023-01-21 10:53:42.264820: step: 1784/530, loss: 0.00976638775318861
2023-01-21 10:53:43.441292: step: 1788/530, loss: 0.02677140198647976
2023-01-21 10:53:44.588228: step: 1792/530, loss: 0.12057328224182129
2023-01-21 10:53:45.707732: step: 1796/530, loss: 0.039566993713378906
2023-01-21 10:53:46.840789: step: 1800/530, loss: 0.031155064702033997
2023-01-21 10:53:48.002417: step: 1804/530, loss: 0.0510038360953331
2023-01-21 10:53:49.120226: step: 1808/530, loss: 0.2271948754787445
2023-01-21 10:53:50.274255: step: 1812/530, loss: 0.03770599514245987
2023-01-21 10:53:51.425254: step: 1816/530, loss: 0.02655792236328125
2023-01-21 10:53:52.557008: step: 1820/530, loss: 0.06353969871997833
2023-01-21 10:53:53.675815: step: 1824/530, loss: 0.011070728302001953
2023-01-21 10:53:54.816786: step: 1828/530, loss: 0.02124013751745224
2023-01-21 10:53:55.964281: step: 1832/530, loss: 0.04510974884033203
2023-01-21 10:53:57.069996: step: 1836/530, loss: 0.0037247182335704565
2023-01-21 10:53:58.200961: step: 1840/530, loss: 0.0009141922346316278
2023-01-21 10:53:59.392939: step: 1844/530, loss: 0.07598743587732315
2023-01-21 10:54:00.528170: step: 1848/530, loss: 0.002524757292121649
2023-01-21 10:54:01.707701: step: 1852/530, loss: 0.002463913056999445
2023-01-21 10:54:02.861789: step: 1856/530, loss: 0.01686582714319229
2023-01-21 10:54:04.007114: step: 1860/530, loss: 0.04805488884449005
2023-01-21 10:54:05.139983: step: 1864/530, loss: 0.10145625472068787
2023-01-21 10:54:06.282645: step: 1868/530, loss: 0.014920043759047985
2023-01-21 10:54:07.435111: step: 1872/530, loss: 0.04007253795862198
2023-01-21 10:54:08.574344: step: 1876/530, loss: 0.01601381227374077
2023-01-21 10:54:09.750737: step: 1880/530, loss: 0.07569461315870285
2023-01-21 10:54:10.901325: step: 1884/530, loss: 0.08276758342981339
2023-01-21 10:54:12.039418: step: 1888/530, loss: 0.02415626309812069
2023-01-21 10:54:13.173291: step: 1892/530, loss: 0.0721045434474945
2023-01-21 10:54:14.302887: step: 1896/530, loss: 0.005602741148322821
2023-01-21 10:54:15.460081: step: 1900/530, loss: 0.028749562799930573
2023-01-21 10:54:16.663429: step: 1904/530, loss: 0.07246243953704834
2023-01-21 10:54:17.799208: step: 1908/530, loss: 0.0035462379455566406
2023-01-21 10:54:18.920990: step: 1912/530, loss: 0.027600575238466263
2023-01-21 10:54:20.072466: step: 1916/530, loss: 0.0345795638859272
2023-01-21 10:54:21.248582: step: 1920/530, loss: 0.027924824506044388
2023-01-21 10:54:22.373082: step: 1924/530, loss: 0.10221491008996964
2023-01-21 10:54:23.522992: step: 1928/530, loss: 0.033768463879823685
2023-01-21 10:54:24.678536: step: 1932/530, loss: 0.10360822081565857
2023-01-21 10:54:25.806074: step: 1936/530, loss: 0.008487892337143421
2023-01-21 10:54:26.955052: step: 1940/530, loss: 0.0664735808968544
2023-01-21 10:54:28.115739: step: 1944/530, loss: 0.01702880859375
2023-01-21 10:54:29.295606: step: 1948/530, loss: 0.041228488087654114
2023-01-21 10:54:30.427620: step: 1952/530, loss: 0.04789924621582031
2023-01-21 10:54:31.545682: step: 1956/530, loss: 0.24480323493480682
2023-01-21 10:54:32.704346: step: 1960/530, loss: 0.06211147457361221
2023-01-21 10:54:33.845458: step: 1964/530, loss: 0.08158645778894424
2023-01-21 10:54:34.990745: step: 1968/530, loss: 0.050138380378484726
2023-01-21 10:54:36.108059: step: 1972/530, loss: 0.0493866428732872
2023-01-21 10:54:37.253304: step: 1976/530, loss: 0.07204370945692062
2023-01-21 10:54:38.409914: step: 1980/530, loss: 0.00893263891339302
2023-01-21 10:54:39.551342: step: 1984/530, loss: 0.018795490264892578
2023-01-21 10:54:40.669884: step: 1988/530, loss: 0.005730056669563055
2023-01-21 10:54:41.792571: step: 1992/530, loss: 0.023281527683138847
2023-01-21 10:54:42.988937: step: 1996/530, loss: 0.0038669584318995476
2023-01-21 10:54:44.136749: step: 2000/530, loss: 0.005566787905991077
2023-01-21 10:54:45.276169: step: 2004/530, loss: 0.16923484206199646
2023-01-21 10:54:46.407772: step: 2008/530, loss: 0.002850151155143976
2023-01-21 10:54:47.548818: step: 2012/530, loss: 0.021324731409549713
2023-01-21 10:54:48.686401: step: 2016/530, loss: 0.05795307457447052
2023-01-21 10:54:49.821820: step: 2020/530, loss: 0.007312488742172718
2023-01-21 10:54:50.925838: step: 2024/530, loss: 0.10779037326574326
2023-01-21 10:54:52.041167: step: 2028/530, loss: 0.24489173293113708
2023-01-21 10:54:53.154895: step: 2032/530, loss: 0.07219743728637695
2023-01-21 10:54:54.280820: step: 2036/530, loss: 0.05699653923511505
2023-01-21 10:54:55.396843: step: 2040/530, loss: 0.009831905364990234
2023-01-21 10:54:56.538450: step: 2044/530, loss: 0.026160717010498047
2023-01-21 10:54:57.671661: step: 2048/530, loss: 0.08962202072143555
2023-01-21 10:54:58.798880: step: 2052/530, loss: 0.025419235229492188
2023-01-21 10:54:59.962374: step: 2056/530, loss: 0.07543888688087463
2023-01-21 10:55:01.097855: step: 2060/530, loss: 0.02982664294540882
2023-01-21 10:55:02.241211: step: 2064/530, loss: 0.007875251583755016
2023-01-21 10:55:03.362159: step: 2068/530, loss: 0.013072680681943893
2023-01-21 10:55:04.507057: step: 2072/530, loss: 0.014038849622011185
2023-01-21 10:55:05.636652: step: 2076/530, loss: 0.04870729520916939
2023-01-21 10:55:06.758853: step: 2080/530, loss: 0.007353019900619984
2023-01-21 10:55:07.892600: step: 2084/530, loss: 0.01072912197560072
2023-01-21 10:55:09.015303: step: 2088/530, loss: 0.024243880063295364
2023-01-21 10:55:10.134461: step: 2092/530, loss: 0.006252300925552845
2023-01-21 10:55:11.324996: step: 2096/530, loss: 0.04982433468103409
2023-01-21 10:55:12.472795: step: 2100/530, loss: 0.17879848182201385
2023-01-21 10:55:13.614621: step: 2104/530, loss: 0.5306503176689148
2023-01-21 10:55:14.762316: step: 2108/530, loss: 0.015310097485780716
2023-01-21 10:55:15.915748: step: 2112/530, loss: 0.26381298899650574
2023-01-21 10:55:17.051850: step: 2116/530, loss: 0.0025281906127929688
2023-01-21 10:55:18.192118: step: 2120/530, loss: 0.044076062738895416
==================================================
Loss: 0.054
--------------------
Dev: {'event': {'p': 0.5844155844155844, 'r': 0.7789613848202397, 'f1': 0.6678082191780821}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6120122753178431, 'r': 0.7977142857142857, 'f1': 0.6926321012155793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.532608695652174, 'r': 0.9074074074074074, 'f1': 0.6712328767123288}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.6029411764705882, 'r': 0.6507936507936508, 'f1': 0.6259541984732825}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.45652173913043476, 'r': 0.5833333333333334, 'f1': 0.5121951219512195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:56:00.553722: step: 4/530, loss: 0.011614632792770863
2023-01-21 10:56:01.699072: step: 8/530, loss: 0.00875482615083456
2023-01-21 10:56:02.843737: step: 12/530, loss: 0.006048774812370539
2023-01-21 10:56:03.975422: step: 16/530, loss: 0.038019370287656784
2023-01-21 10:56:05.086861: step: 20/530, loss: 0.055533263832330704
2023-01-21 10:56:06.225173: step: 24/530, loss: 0.09281311184167862
2023-01-21 10:56:07.381575: step: 28/530, loss: 0.05190415307879448
2023-01-21 10:56:08.519501: step: 32/530, loss: 0.037296175956726074
2023-01-21 10:56:09.673806: step: 36/530, loss: 0.022765349596738815
2023-01-21 10:56:10.812054: step: 40/530, loss: 0.018834495916962624
2023-01-21 10:56:11.945061: step: 44/530, loss: 0.01993551291525364
2023-01-21 10:56:13.107190: step: 48/530, loss: 0.071375273168087
2023-01-21 10:56:14.243474: step: 52/530, loss: 0.06283202022314072
2023-01-21 10:56:15.406510: step: 56/530, loss: 0.00954127311706543
2023-01-21 10:56:16.560446: step: 60/530, loss: 0.01134424190968275
2023-01-21 10:56:17.700028: step: 64/530, loss: 0.04735145717859268
2023-01-21 10:56:18.832146: step: 68/530, loss: 0.01192550640553236
2023-01-21 10:56:19.942926: step: 72/530, loss: 0.00162420270498842
2023-01-21 10:56:21.088622: step: 76/530, loss: 0.013175392523407936
2023-01-21 10:56:22.237766: step: 80/530, loss: 0.03166847303509712
2023-01-21 10:56:23.357111: step: 84/530, loss: 0.018859293311834335
2023-01-21 10:56:24.510886: step: 88/530, loss: 0.007655191235244274
2023-01-21 10:56:25.635379: step: 92/530, loss: 0.005402469541877508
2023-01-21 10:56:26.762908: step: 96/530, loss: 0.007023811340332031
2023-01-21 10:56:27.861958: step: 100/530, loss: 0.008267688564956188
2023-01-21 10:56:29.000548: step: 104/530, loss: 0.00035915375337935984
2023-01-21 10:56:30.144675: step: 108/530, loss: 0.010041522793471813
2023-01-21 10:56:31.263087: step: 112/530, loss: 0.021944807842373848
2023-01-21 10:56:32.421770: step: 116/530, loss: 0.00869598425924778
2023-01-21 10:56:33.558338: step: 120/530, loss: 0.02496328391134739
2023-01-21 10:56:34.731363: step: 124/530, loss: 0.01858053170144558
2023-01-21 10:56:35.874965: step: 128/530, loss: 0.002537250518798828
2023-01-21 10:56:37.013584: step: 132/530, loss: 0.09897881001234055
2023-01-21 10:56:38.172389: step: 136/530, loss: 0.02609109878540039
2023-01-21 10:56:39.293238: step: 140/530, loss: 0.010743808932602406
2023-01-21 10:56:40.462008: step: 144/530, loss: 0.02468266524374485
2023-01-21 10:56:41.628337: step: 148/530, loss: 0.008451557718217373
2023-01-21 10:56:42.768565: step: 152/530, loss: 0.05584258958697319
2023-01-21 10:56:43.889774: step: 156/530, loss: 0.025601863861083984
2023-01-21 10:56:45.035096: step: 160/530, loss: 0.014312935061752796
2023-01-21 10:56:46.182875: step: 164/530, loss: 0.024593163281679153
2023-01-21 10:56:47.302119: step: 168/530, loss: 0.0048694610595703125
2023-01-21 10:56:48.462528: step: 172/530, loss: 0.04972973093390465
2023-01-21 10:56:49.607992: step: 176/530, loss: 0.033026073127985
2023-01-21 10:56:50.744324: step: 180/530, loss: 0.004881524946540594
2023-01-21 10:56:51.919837: step: 184/530, loss: 0.010072755627334118
2023-01-21 10:56:53.074736: step: 188/530, loss: 0.0007537842029705644
2023-01-21 10:56:54.204164: step: 192/530, loss: 0.061823271214962006
2023-01-21 10:56:55.347160: step: 196/530, loss: 0.09506092220544815
2023-01-21 10:56:56.475076: step: 200/530, loss: 0.051161766052246094
2023-01-21 10:56:57.644689: step: 204/530, loss: 0.06315699219703674
2023-01-21 10:56:58.776647: step: 208/530, loss: 0.04589395597577095
2023-01-21 10:56:59.931291: step: 212/530, loss: 0.021100236102938652
2023-01-21 10:57:01.052318: step: 216/530, loss: 0.0356840118765831
2023-01-21 10:57:02.200449: step: 220/530, loss: 0.07996167987585068
2023-01-21 10:57:03.337050: step: 224/530, loss: 0.0011939048999920487
2023-01-21 10:57:04.482113: step: 228/530, loss: 0.013439369387924671
2023-01-21 10:57:05.630344: step: 232/530, loss: 0.003192424774169922
2023-01-21 10:57:06.737906: step: 236/530, loss: 0.01443710457533598
2023-01-21 10:57:07.876049: step: 240/530, loss: 0.0623815543949604
2023-01-21 10:57:09.028356: step: 244/530, loss: 0.06008262559771538
2023-01-21 10:57:10.165632: step: 248/530, loss: 0.13958033919334412
2023-01-21 10:57:11.313165: step: 252/530, loss: 0.0049245357513427734
2023-01-21 10:57:12.477854: step: 256/530, loss: 0.04537773132324219
2023-01-21 10:57:13.630436: step: 260/530, loss: 0.03262901306152344
2023-01-21 10:57:14.765794: step: 264/530, loss: 0.002602195832878351
2023-01-21 10:57:15.898426: step: 268/530, loss: 0.03478863090276718
2023-01-21 10:57:17.064977: step: 272/530, loss: 0.02126617543399334
2023-01-21 10:57:18.212230: step: 276/530, loss: 0.03520050272345543
2023-01-21 10:57:19.341136: step: 280/530, loss: 0.018367433920502663
2023-01-21 10:57:20.481560: step: 284/530, loss: 0.0038623332511633635
2023-01-21 10:57:21.636493: step: 288/530, loss: 0.07485237717628479
2023-01-21 10:57:22.777919: step: 292/530, loss: 0.0318751335144043
2023-01-21 10:57:23.891826: step: 296/530, loss: 0.5978411436080933
2023-01-21 10:57:25.020737: step: 300/530, loss: 0.0038347244262695312
2023-01-21 10:57:26.159063: step: 304/530, loss: 0.0168367400765419
2023-01-21 10:57:27.306059: step: 308/530, loss: 0.07303667068481445
2023-01-21 10:57:28.461709: step: 312/530, loss: 0.0010248185135424137
2023-01-21 10:57:29.601392: step: 316/530, loss: 0.07247648388147354
2023-01-21 10:57:30.734697: step: 320/530, loss: 0.013176393695175648
2023-01-21 10:57:31.885870: step: 324/530, loss: 0.0006782054551877081
2023-01-21 10:57:33.041115: step: 328/530, loss: 0.0049765584990382195
2023-01-21 10:57:34.156372: step: 332/530, loss: 0.6479880213737488
2023-01-21 10:57:35.296047: step: 336/530, loss: 0.054956816136837006
2023-01-21 10:57:36.414227: step: 340/530, loss: 0.05968761444091797
2023-01-21 10:57:37.551212: step: 344/530, loss: 0.009917259216308594
2023-01-21 10:57:38.694682: step: 348/530, loss: 0.0050331116653978825
2023-01-21 10:57:39.828319: step: 352/530, loss: 0.016166210174560547
2023-01-21 10:57:40.930505: step: 356/530, loss: 0.042746689170598984
2023-01-21 10:57:42.058057: step: 360/530, loss: 0.08296074718236923
2023-01-21 10:57:43.219997: step: 364/530, loss: 0.015878774225711823
2023-01-21 10:57:44.359451: step: 368/530, loss: 0.0005882263649255037
2023-01-21 10:57:45.526822: step: 372/530, loss: 0.05169658735394478
2023-01-21 10:57:46.660780: step: 376/530, loss: 0.04137105867266655
2023-01-21 10:57:47.825093: step: 380/530, loss: 0.0017870903247967362
2023-01-21 10:57:48.952876: step: 384/530, loss: 0.0015769958263263106
2023-01-21 10:57:50.084370: step: 388/530, loss: 0.025294732302427292
2023-01-21 10:57:51.226258: step: 392/530, loss: 0.010542010888457298
2023-01-21 10:57:52.359824: step: 396/530, loss: 0.00035343170748092234
2023-01-21 10:57:53.570383: step: 400/530, loss: 0.0047206878662109375
2023-01-21 10:57:54.708819: step: 404/530, loss: 0.03917226940393448
2023-01-21 10:57:55.837784: step: 408/530, loss: 0.034130096435546875
2023-01-21 10:57:56.941914: step: 412/530, loss: 0.023939132690429688
2023-01-21 10:57:58.076860: step: 416/530, loss: 0.02044057846069336
2023-01-21 10:57:59.232477: step: 420/530, loss: 0.08950252830982208
2023-01-21 10:58:00.378798: step: 424/530, loss: 0.04264846071600914
2023-01-21 10:58:01.505094: step: 428/530, loss: 0.01305251196026802
2023-01-21 10:58:02.704311: step: 432/530, loss: 0.07245617359876633
2023-01-21 10:58:03.853382: step: 436/530, loss: 0.12039823830127716
2023-01-21 10:58:04.991595: step: 440/530, loss: 0.04762401431798935
2023-01-21 10:58:06.145482: step: 444/530, loss: 0.016257477924227715
2023-01-21 10:58:07.311901: step: 448/530, loss: 0.0035455701872706413
2023-01-21 10:58:08.460818: step: 452/530, loss: 0.05297694355249405
2023-01-21 10:58:09.612131: step: 456/530, loss: 0.033902548253536224
2023-01-21 10:58:10.761707: step: 460/530, loss: 0.045664310455322266
2023-01-21 10:58:11.904476: step: 464/530, loss: 0.05560912936925888
2023-01-21 10:58:13.043208: step: 468/530, loss: 0.19419363141059875
2023-01-21 10:58:14.175500: step: 472/530, loss: 0.0026996613014489412
2023-01-21 10:58:15.343320: step: 476/530, loss: 0.014448070898652077
2023-01-21 10:58:16.491395: step: 480/530, loss: 0.15438775718212128
2023-01-21 10:58:17.657278: step: 484/530, loss: 0.018667984753847122
2023-01-21 10:58:18.778077: step: 488/530, loss: 0.10785046219825745
2023-01-21 10:58:19.901397: step: 492/530, loss: 0.041814230382442474
2023-01-21 10:58:21.011268: step: 496/530, loss: 0.048674874007701874
2023-01-21 10:58:22.154354: step: 500/530, loss: 0.09097880870103836
2023-01-21 10:58:23.273565: step: 504/530, loss: 0.009897613897919655
2023-01-21 10:58:24.425528: step: 508/530, loss: 0.05281992256641388
2023-01-21 10:58:25.553497: step: 512/530, loss: 0.01778879202902317
2023-01-21 10:58:26.677072: step: 516/530, loss: 0.03255109861493111
2023-01-21 10:58:27.824927: step: 520/530, loss: 0.04271812364459038
2023-01-21 10:58:28.959689: step: 524/530, loss: 0.0186964999884367
2023-01-21 10:58:30.071641: step: 528/530, loss: 0.084368035197258
2023-01-21 10:58:31.242752: step: 532/530, loss: 0.055545903742313385
2023-01-21 10:58:32.351620: step: 536/530, loss: 0.0026681902818381786
2023-01-21 10:58:33.467202: step: 540/530, loss: 0.013454437255859375
2023-01-21 10:58:34.631231: step: 544/530, loss: 0.02357807196676731
2023-01-21 10:58:35.767371: step: 548/530, loss: 0.004240131471306086
2023-01-21 10:58:36.903307: step: 552/530, loss: 0.05067300796508789
2023-01-21 10:58:38.022035: step: 556/530, loss: 0.024183034896850586
2023-01-21 10:58:39.185877: step: 560/530, loss: 0.06223888322710991
2023-01-21 10:58:40.316844: step: 564/530, loss: 0.016031645238399506
2023-01-21 10:58:41.448667: step: 568/530, loss: 0.0013477326137945056
2023-01-21 10:58:42.611565: step: 572/530, loss: 0.011874294839799404
2023-01-21 10:58:43.706157: step: 576/530, loss: 0.0015110969543457031
2023-01-21 10:58:44.889382: step: 580/530, loss: 0.029699325561523438
2023-01-21 10:58:46.019521: step: 584/530, loss: 0.013843799009919167
2023-01-21 10:58:47.131311: step: 588/530, loss: 0.07956790924072266
2023-01-21 10:58:48.294056: step: 592/530, loss: 0.03493232652544975
2023-01-21 10:58:49.402881: step: 596/530, loss: 0.0057496074587106705
2023-01-21 10:58:50.554966: step: 600/530, loss: 0.02654147334396839
2023-01-21 10:58:51.680839: step: 604/530, loss: 0.006798935122787952
2023-01-21 10:58:52.833847: step: 608/530, loss: 0.0016205310821533203
2023-01-21 10:58:53.980653: step: 612/530, loss: 0.03766594082117081
2023-01-21 10:58:55.132148: step: 616/530, loss: 0.0216046329587698
2023-01-21 10:58:56.251518: step: 620/530, loss: 0.021416999399662018
2023-01-21 10:58:57.404317: step: 624/530, loss: 0.025049591436982155
2023-01-21 10:58:58.532563: step: 628/530, loss: 0.004002762027084827
2023-01-21 10:58:59.667531: step: 632/530, loss: 0.04841761663556099
2023-01-21 10:59:00.798945: step: 636/530, loss: 0.0026119709946215153
2023-01-21 10:59:01.926174: step: 640/530, loss: 0.01607217825949192
2023-01-21 10:59:03.029544: step: 644/530, loss: 0.014604663476347923
2023-01-21 10:59:04.173039: step: 648/530, loss: 0.009646224789321423
2023-01-21 10:59:05.291728: step: 652/530, loss: 0.03547925874590874
2023-01-21 10:59:06.422807: step: 656/530, loss: 0.006899738218635321
2023-01-21 10:59:07.584564: step: 660/530, loss: 0.005611706059426069
2023-01-21 10:59:08.720339: step: 664/530, loss: 0.00176239013671875
2023-01-21 10:59:09.858929: step: 668/530, loss: 0.013766860589385033
2023-01-21 10:59:10.973967: step: 672/530, loss: 0.010090637020766735
2023-01-21 10:59:12.139149: step: 676/530, loss: 0.026205826550722122
2023-01-21 10:59:13.269972: step: 680/530, loss: 0.058071136474609375
2023-01-21 10:59:14.383002: step: 684/530, loss: 0.008561707101762295
2023-01-21 10:59:15.535706: step: 688/530, loss: 0.6043720841407776
2023-01-21 10:59:16.700732: step: 692/530, loss: 0.011764168739318848
2023-01-21 10:59:17.825760: step: 696/530, loss: 0.05540619045495987
2023-01-21 10:59:18.975622: step: 700/530, loss: 0.0029535293579101562
2023-01-21 10:59:20.109575: step: 704/530, loss: 0.010497570969164371
2023-01-21 10:59:21.248265: step: 708/530, loss: 0.0013535500038415194
2023-01-21 10:59:22.370544: step: 712/530, loss: 0.06170158460736275
2023-01-21 10:59:23.546128: step: 716/530, loss: 0.20160122215747833
2023-01-21 10:59:24.673317: step: 720/530, loss: 0.00259819021448493
2023-01-21 10:59:25.826766: step: 724/530, loss: 0.03059425577521324
2023-01-21 10:59:26.971495: step: 728/530, loss: 0.03595118597149849
2023-01-21 10:59:28.096660: step: 732/530, loss: 0.017497826367616653
2023-01-21 10:59:29.247240: step: 736/530, loss: 0.0982154905796051
2023-01-21 10:59:30.399924: step: 740/530, loss: 0.05615973472595215
2023-01-21 10:59:31.553858: step: 744/530, loss: 0.015278339385986328
2023-01-21 10:59:32.688270: step: 748/530, loss: 0.019547367468476295
2023-01-21 10:59:33.836986: step: 752/530, loss: 0.030991362407803535
2023-01-21 10:59:35.002546: step: 756/530, loss: 0.03493404760956764
2023-01-21 10:59:36.132866: step: 760/530, loss: 0.02912154234945774
2023-01-21 10:59:37.290468: step: 764/530, loss: 0.017034530639648438
2023-01-21 10:59:38.438809: step: 768/530, loss: 0.0055144308134913445
2023-01-21 10:59:39.573059: step: 772/530, loss: 0.007080123294144869
2023-01-21 10:59:40.739168: step: 776/530, loss: 0.02785949781537056
2023-01-21 10:59:41.851908: step: 780/530, loss: 0.07312522083520889
2023-01-21 10:59:42.979897: step: 784/530, loss: 0.009125327691435814
2023-01-21 10:59:44.108637: step: 788/530, loss: 0.0877407044172287
2023-01-21 10:59:45.243640: step: 792/530, loss: 0.008423805236816406
2023-01-21 10:59:46.379580: step: 796/530, loss: 0.0689065009355545
2023-01-21 10:59:47.547392: step: 800/530, loss: 0.027076052501797676
2023-01-21 10:59:48.691934: step: 804/530, loss: 0.00040054324199445546
2023-01-21 10:59:49.836317: step: 808/530, loss: 0.04793129116296768
2023-01-21 10:59:50.959791: step: 812/530, loss: 0.13440386950969696
2023-01-21 10:59:52.078914: step: 816/530, loss: 0.04555549472570419
2023-01-21 10:59:53.244410: step: 820/530, loss: 0.053875066339969635
2023-01-21 10:59:54.345837: step: 824/530, loss: 0.04407463222742081
2023-01-21 10:59:55.496408: step: 828/530, loss: 0.004495048429816961
2023-01-21 10:59:56.631705: step: 832/530, loss: 0.022128771990537643
2023-01-21 10:59:57.776408: step: 836/530, loss: 0.12945061922073364
2023-01-21 10:59:58.927127: step: 840/530, loss: 0.023941706866025925
2023-01-21 11:00:00.095130: step: 844/530, loss: 0.01931781880557537
2023-01-21 11:00:01.227197: step: 848/530, loss: 0.24548988044261932
2023-01-21 11:00:02.336168: step: 852/530, loss: 0.040032196789979935
2023-01-21 11:00:03.491989: step: 856/530, loss: 0.022159194573760033
2023-01-21 11:00:04.641231: step: 860/530, loss: 0.02491931989789009
2023-01-21 11:00:05.761611: step: 864/530, loss: 0.007970571517944336
2023-01-21 11:00:06.885324: step: 868/530, loss: 0.005455113016068935
2023-01-21 11:00:08.062338: step: 872/530, loss: 0.021799776703119278
2023-01-21 11:00:09.253671: step: 876/530, loss: 0.00021867752366233617
2023-01-21 11:00:10.386537: step: 880/530, loss: 0.020279215648770332
2023-01-21 11:00:11.510050: step: 884/530, loss: 0.052863121032714844
2023-01-21 11:00:12.657311: step: 888/530, loss: 0.04783926159143448
2023-01-21 11:00:13.785688: step: 892/530, loss: 0.007754087448120117
2023-01-21 11:00:14.968840: step: 896/530, loss: 0.002638149308040738
2023-01-21 11:00:16.143233: step: 900/530, loss: 0.01988067664206028
2023-01-21 11:00:17.301633: step: 904/530, loss: 0.034543611109256744
2023-01-21 11:00:18.425371: step: 908/530, loss: 0.0473298579454422
2023-01-21 11:00:19.542106: step: 912/530, loss: 0.0488801971077919
2023-01-21 11:00:20.682916: step: 916/530, loss: 0.025903893634676933
2023-01-21 11:00:21.809748: step: 920/530, loss: 0.13345539569854736
2023-01-21 11:00:22.976894: step: 924/530, loss: 0.031414031982421875
2023-01-21 11:00:24.127745: step: 928/530, loss: 0.020247556269168854
2023-01-21 11:00:25.273285: step: 932/530, loss: 0.03822936862707138
2023-01-21 11:00:26.408961: step: 936/530, loss: 0.0014460564125329256
2023-01-21 11:00:27.538244: step: 940/530, loss: 0.009243393316864967
2023-01-21 11:00:28.703368: step: 944/530, loss: 0.030127812176942825
2023-01-21 11:00:29.835088: step: 948/530, loss: 0.3189052641391754
2023-01-21 11:00:30.983554: step: 952/530, loss: 0.01964416541159153
2023-01-21 11:00:32.160023: step: 956/530, loss: 0.0015039443969726562
2023-01-21 11:00:33.275557: step: 960/530, loss: 0.05226850509643555
2023-01-21 11:00:34.398556: step: 964/530, loss: 9.179115295410156e-05
2023-01-21 11:00:35.552685: step: 968/530, loss: 0.020391609519720078
2023-01-21 11:00:36.682024: step: 972/530, loss: 0.04525108262896538
2023-01-21 11:00:37.786039: step: 976/530, loss: 0.026174068450927734
2023-01-21 11:00:38.931476: step: 980/530, loss: 0.0138397216796875
2023-01-21 11:00:40.065475: step: 984/530, loss: 0.00580520648509264
2023-01-21 11:00:41.214842: step: 988/530, loss: 0.03634243085980415
2023-01-21 11:00:42.375965: step: 992/530, loss: 0.0058565144427120686
2023-01-21 11:00:43.532595: step: 996/530, loss: 0.03171367943286896
2023-01-21 11:00:44.637353: step: 1000/530, loss: 0.01773528940975666
2023-01-21 11:00:45.802987: step: 1004/530, loss: 0.026846598833799362
2023-01-21 11:00:46.943144: step: 1008/530, loss: 0.0807517021894455
2023-01-21 11:00:48.072979: step: 1012/530, loss: 0.0032012939918786287
2023-01-21 11:00:49.220138: step: 1016/530, loss: 0.005792141426354647
2023-01-21 11:00:50.363020: step: 1020/530, loss: 0.0022260667756199837
2023-01-21 11:00:51.494572: step: 1024/530, loss: 0.03456611931324005
2023-01-21 11:00:52.643854: step: 1028/530, loss: 0.03213310241699219
2023-01-21 11:00:53.772796: step: 1032/530, loss: 0.046746253967285156
2023-01-21 11:00:54.920668: step: 1036/530, loss: 0.01656341552734375
2023-01-21 11:00:56.040648: step: 1040/530, loss: 0.020496560260653496
2023-01-21 11:00:57.196100: step: 1044/530, loss: 0.015752125531435013
2023-01-21 11:00:58.326150: step: 1048/530, loss: 0.03952827304601669
2023-01-21 11:00:59.485266: step: 1052/530, loss: 0.03926678001880646
2023-01-21 11:01:00.622593: step: 1056/530, loss: 0.03547210618853569
2023-01-21 11:01:01.760384: step: 1060/530, loss: 0.007499885745346546
2023-01-21 11:01:02.914158: step: 1064/530, loss: 0.08795013278722763
2023-01-21 11:01:04.022735: step: 1068/530, loss: 0.01462945993989706
2023-01-21 11:01:05.155733: step: 1072/530, loss: 0.0024263381492346525
2023-01-21 11:01:06.264202: step: 1076/530, loss: 0.030530165880918503
2023-01-21 11:01:07.397456: step: 1080/530, loss: 0.025494862347841263
2023-01-21 11:01:08.543285: step: 1084/530, loss: 0.03757515177130699
2023-01-21 11:01:09.700045: step: 1088/530, loss: 0.003063297364860773
2023-01-21 11:01:10.818071: step: 1092/530, loss: 0.03311929479241371
2023-01-21 11:01:11.938741: step: 1096/530, loss: 0.02033987082540989
2023-01-21 11:01:13.104649: step: 1100/530, loss: 0.07032446563243866
2023-01-21 11:01:14.239164: step: 1104/530, loss: 0.07821130752563477
2023-01-21 11:01:15.368339: step: 1108/530, loss: 0.007036781404167414
2023-01-21 11:01:16.513631: step: 1112/530, loss: 0.04807768017053604
2023-01-21 11:01:17.681235: step: 1116/530, loss: 0.06623172760009766
2023-01-21 11:01:18.824855: step: 1120/530, loss: 0.011804867535829544
2023-01-21 11:01:19.969293: step: 1124/530, loss: 0.02893754467368126
2023-01-21 11:01:21.133748: step: 1128/530, loss: 0.012345314025878906
2023-01-21 11:01:22.294453: step: 1132/530, loss: 0.004823207855224609
2023-01-21 11:01:23.445355: step: 1136/530, loss: 0.042534828186035156
2023-01-21 11:01:24.600421: step: 1140/530, loss: 0.016106510534882545
2023-01-21 11:01:25.742060: step: 1144/530, loss: 0.006917620077729225
2023-01-21 11:01:26.883732: step: 1148/530, loss: 0.027724934741854668
2023-01-21 11:01:28.004680: step: 1152/530, loss: 0.0031442642211914062
2023-01-21 11:01:29.146156: step: 1156/530, loss: 0.04799060896039009
2023-01-21 11:01:30.287917: step: 1160/530, loss: 0.01398468017578125
2023-01-21 11:01:31.406899: step: 1164/530, loss: 0.00039610863314010203
2023-01-21 11:01:32.594074: step: 1168/530, loss: 0.0068511962890625
2023-01-21 11:01:33.763329: step: 1172/530, loss: 0.04163169860839844
2023-01-21 11:01:34.888120: step: 1176/530, loss: 0.05417843163013458
2023-01-21 11:01:36.031650: step: 1180/530, loss: 0.0002711772976908833
2023-01-21 11:01:37.149687: step: 1184/530, loss: 0.007947730831801891
2023-01-21 11:01:38.291974: step: 1188/530, loss: 0.07177191227674484
2023-01-21 11:01:39.459869: step: 1192/530, loss: 0.011019134894013405
2023-01-21 11:01:40.631035: step: 1196/530, loss: 0.0009962081676349044
2023-01-21 11:01:41.768794: step: 1200/530, loss: 0.04658927768468857
2023-01-21 11:01:42.923833: step: 1204/530, loss: 0.029930591583251953
2023-01-21 11:01:44.058238: step: 1208/530, loss: 0.09436826407909393
2023-01-21 11:01:45.220311: step: 1212/530, loss: 0.05301017314195633
2023-01-21 11:01:46.343785: step: 1216/530, loss: 0.012265825644135475
2023-01-21 11:01:47.477015: step: 1220/530, loss: 0.011836815625429153
2023-01-21 11:01:48.605831: step: 1224/530, loss: 0.011752987280488014
2023-01-21 11:01:49.755479: step: 1228/530, loss: 0.08987322449684143
2023-01-21 11:01:50.881367: step: 1232/530, loss: 0.06338530033826828
2023-01-21 11:01:52.072785: step: 1236/530, loss: 0.11370324343442917
2023-01-21 11:01:53.200634: step: 1240/530, loss: 0.004010105039924383
2023-01-21 11:01:54.331196: step: 1244/530, loss: 0.023255730047822
2023-01-21 11:01:55.498714: step: 1248/530, loss: 0.03536796569824219
2023-01-21 11:01:56.634824: step: 1252/530, loss: 0.011076068505644798
2023-01-21 11:01:57.775320: step: 1256/530, loss: 0.026825379580259323
2023-01-21 11:01:58.936044: step: 1260/530, loss: 0.05673384666442871
2023-01-21 11:02:00.121881: step: 1264/530, loss: 0.061617661267519
2023-01-21 11:02:01.272042: step: 1268/530, loss: 0.029776956886053085
2023-01-21 11:02:02.427848: step: 1272/530, loss: 0.0402863509953022
2023-01-21 11:02:03.537192: step: 1276/530, loss: 0.09151887893676758
2023-01-21 11:02:04.649539: step: 1280/530, loss: 0.08565321564674377
2023-01-21 11:02:05.804999: step: 1284/530, loss: 0.19208411872386932
2023-01-21 11:02:06.956243: step: 1288/530, loss: 0.06013622134923935
2023-01-21 11:02:08.099646: step: 1292/530, loss: 0.002103495644405484
2023-01-21 11:02:09.226569: step: 1296/530, loss: 0.05688466876745224
2023-01-21 11:02:10.357521: step: 1300/530, loss: 0.020755957812070847
2023-01-21 11:02:11.519198: step: 1304/530, loss: 0.6078685522079468
2023-01-21 11:02:12.690620: step: 1308/530, loss: 0.04209098964929581
2023-01-21 11:02:13.840485: step: 1312/530, loss: 0.0006928443908691406
2023-01-21 11:02:14.958650: step: 1316/530, loss: 0.0005797386402264237
2023-01-21 11:02:16.102567: step: 1320/530, loss: 0.06263237446546555
2023-01-21 11:02:17.226409: step: 1324/530, loss: 0.0015227318508550525
2023-01-21 11:02:18.353691: step: 1328/530, loss: 0.011327744461596012
2023-01-21 11:02:19.509127: step: 1332/530, loss: 0.026087570935487747
2023-01-21 11:02:20.673272: step: 1336/530, loss: 0.03292350843548775
2023-01-21 11:02:21.813674: step: 1340/530, loss: 0.01969299279153347
2023-01-21 11:02:22.974203: step: 1344/530, loss: 0.0038364408537745476
2023-01-21 11:02:24.133027: step: 1348/530, loss: 0.04836463928222656
2023-01-21 11:02:25.269835: step: 1352/530, loss: 0.012911511585116386
2023-01-21 11:02:26.422563: step: 1356/530, loss: 0.013796997256577015
2023-01-21 11:02:27.537270: step: 1360/530, loss: 0.10867755115032196
2023-01-21 11:02:28.746623: step: 1364/530, loss: 0.04073600843548775
2023-01-21 11:02:29.889415: step: 1368/530, loss: 0.22793197631835938
2023-01-21 11:02:31.027347: step: 1372/530, loss: 0.018036365509033203
2023-01-21 11:02:32.162636: step: 1376/530, loss: 0.10865173488855362
2023-01-21 11:02:33.313805: step: 1380/530, loss: 0.010687733069062233
2023-01-21 11:02:34.454562: step: 1384/530, loss: 0.04401545599102974
2023-01-21 11:02:35.592276: step: 1388/530, loss: 0.028109312057495117
2023-01-21 11:02:36.740034: step: 1392/530, loss: 0.008869337849318981
2023-01-21 11:02:37.919867: step: 1396/530, loss: 0.8209370374679565
2023-01-21 11:02:39.063611: step: 1400/530, loss: 0.19197502732276917
2023-01-21 11:02:40.205286: step: 1404/530, loss: 0.15016447007656097
2023-01-21 11:02:41.354251: step: 1408/530, loss: 0.03181910514831543
2023-01-21 11:02:42.470696: step: 1412/530, loss: 0.004067468922585249
2023-01-21 11:02:43.619712: step: 1416/530, loss: 0.024436473846435547
2023-01-21 11:02:44.796827: step: 1420/530, loss: 0.020074177533388138
2023-01-21 11:02:45.945914: step: 1424/530, loss: 0.0016744612948969007
2023-01-21 11:02:47.105162: step: 1428/530, loss: 0.01753692701458931
2023-01-21 11:02:48.237649: step: 1432/530, loss: 0.040731146931648254
2023-01-21 11:02:49.355845: step: 1436/530, loss: 0.14642544090747833
2023-01-21 11:02:50.517560: step: 1440/530, loss: 0.012515068054199219
2023-01-21 11:02:51.639257: step: 1444/530, loss: 0.0251206886023283
2023-01-21 11:02:52.792514: step: 1448/530, loss: 0.0033741951920092106
2023-01-21 11:02:53.948786: step: 1452/530, loss: 0.16393500566482544
2023-01-21 11:02:55.077751: step: 1456/530, loss: 0.005092191975563765
2023-01-21 11:02:56.202640: step: 1460/530, loss: 0.028334427624940872
2023-01-21 11:02:57.352284: step: 1464/530, loss: 0.02130146138370037
2023-01-21 11:02:58.467649: step: 1468/530, loss: 0.0023598670959472656
2023-01-21 11:02:59.650257: step: 1472/530, loss: 0.026300620287656784
2023-01-21 11:03:00.799655: step: 1476/530, loss: 0.02457866631448269
2023-01-21 11:03:01.926453: step: 1480/530, loss: 0.049874190241098404
2023-01-21 11:03:03.123104: step: 1484/530, loss: 0.00018138886662200093
2023-01-21 11:03:04.254550: step: 1488/530, loss: 0.01586780697107315
2023-01-21 11:03:05.421789: step: 1492/530, loss: 0.007094383239746094
2023-01-21 11:03:06.559894: step: 1496/530, loss: 0.013970375061035156
2023-01-21 11:03:07.700169: step: 1500/530, loss: 0.006769562140107155
2023-01-21 11:03:08.868741: step: 1504/530, loss: 0.03720364719629288
2023-01-21 11:03:10.032343: step: 1508/530, loss: 0.004189491271972656
2023-01-21 11:03:11.164167: step: 1512/530, loss: 0.00684509240090847
2023-01-21 11:03:12.294477: step: 1516/530, loss: 0.004998529329895973
2023-01-21 11:03:13.415227: step: 1520/530, loss: 0.011357736773788929
2023-01-21 11:03:14.565833: step: 1524/530, loss: 0.009348297491669655
2023-01-21 11:03:15.697458: step: 1528/530, loss: 0.0015817641979083419
2023-01-21 11:03:16.842764: step: 1532/530, loss: 0.043148234486579895
2023-01-21 11:03:18.003651: step: 1536/530, loss: 0.022484874352812767
2023-01-21 11:03:19.140945: step: 1540/530, loss: 0.08454723656177521
2023-01-21 11:03:20.302133: step: 1544/530, loss: 0.043316081166267395
2023-01-21 11:03:21.432910: step: 1548/530, loss: 0.01892075501382351
2023-01-21 11:03:22.577910: step: 1552/530, loss: 0.09686336666345596
2023-01-21 11:03:23.707144: step: 1556/530, loss: 0.048360638320446014
2023-01-21 11:03:24.849982: step: 1560/530, loss: 0.04056549072265625
2023-01-21 11:03:25.975845: step: 1564/530, loss: 0.008250045590102673
2023-01-21 11:03:27.106556: step: 1568/530, loss: 0.04723015055060387
2023-01-21 11:03:28.218248: step: 1572/530, loss: 0.011099529452621937
2023-01-21 11:03:29.381610: step: 1576/530, loss: 0.016785716637969017
2023-01-21 11:03:30.523649: step: 1580/530, loss: 0.014361954294145107
2023-01-21 11:03:31.681146: step: 1584/530, loss: 0.09405174851417542
2023-01-21 11:03:32.834900: step: 1588/530, loss: 0.06905422359704971
2023-01-21 11:03:33.989994: step: 1592/530, loss: 0.06335728615522385
2023-01-21 11:03:35.121170: step: 1596/530, loss: 0.037729643285274506
2023-01-21 11:03:36.261514: step: 1600/530, loss: 0.05177593231201172
2023-01-21 11:03:37.392968: step: 1604/530, loss: 0.23136445879936218
2023-01-21 11:03:38.525245: step: 1608/530, loss: 0.004282331559807062
2023-01-21 11:03:39.670197: step: 1612/530, loss: 0.026232624426484108
2023-01-21 11:03:40.777634: step: 1616/530, loss: 0.1315983384847641
2023-01-21 11:03:41.945022: step: 1620/530, loss: 0.0872398391366005
2023-01-21 11:03:43.086028: step: 1624/530, loss: 0.021900463849306107
2023-01-21 11:03:44.266587: step: 1628/530, loss: 0.07352671772241592
2023-01-21 11:03:45.406694: step: 1632/530, loss: 0.0126075753942132
2023-01-21 11:03:46.535970: step: 1636/530, loss: 0.006818008609116077
2023-01-21 11:03:47.692363: step: 1640/530, loss: 0.006765037775039673
2023-01-21 11:03:48.803403: step: 1644/530, loss: 0.08382062613964081
2023-01-21 11:03:49.969608: step: 1648/530, loss: 0.00010414123971713707
2023-01-21 11:03:51.113953: step: 1652/530, loss: 0.008768081665039062
2023-01-21 11:03:52.254481: step: 1656/530, loss: 0.005158806219696999
2023-01-21 11:03:53.389001: step: 1660/530, loss: 0.014765358529984951
2023-01-21 11:03:54.508521: step: 1664/530, loss: 0.15240421891212463
2023-01-21 11:03:55.658616: step: 1668/530, loss: 0.03971615061163902
2023-01-21 11:03:56.807483: step: 1672/530, loss: 0.02486591413617134
2023-01-21 11:03:57.961648: step: 1676/530, loss: 0.0031307220924645662
2023-01-21 11:03:59.089045: step: 1680/530, loss: 0.0004601478576660156
2023-01-21 11:04:00.245794: step: 1684/530, loss: 0.08950719982385635
2023-01-21 11:04:01.365235: step: 1688/530, loss: 0.018713902682065964
2023-01-21 11:04:02.498302: step: 1692/530, loss: 0.00400543212890625
2023-01-21 11:04:03.634930: step: 1696/530, loss: 0.009966564364731312
2023-01-21 11:04:04.762050: step: 1700/530, loss: 0.07936535030603409
2023-01-21 11:04:05.872985: step: 1704/530, loss: 0.004069423768669367
2023-01-21 11:04:07.003742: step: 1708/530, loss: 0.03754892200231552
2023-01-21 11:04:08.153166: step: 1712/530, loss: 0.0348600409924984
2023-01-21 11:04:09.290551: step: 1716/530, loss: 0.2651368975639343
2023-01-21 11:04:10.464523: step: 1720/530, loss: 0.025855161249637604
2023-01-21 11:04:11.595412: step: 1724/530, loss: 0.001140594482421875
2023-01-21 11:04:12.758071: step: 1728/530, loss: 0.06389045715332031
2023-01-21 11:04:13.911842: step: 1732/530, loss: 0.1389492005109787
2023-01-21 11:04:15.068798: step: 1736/530, loss: 0.015485953539609909
2023-01-21 11:04:16.225928: step: 1740/530, loss: 0.005508899688720703
2023-01-21 11:04:17.364279: step: 1744/530, loss: 0.009121894836425781
2023-01-21 11:04:18.514073: step: 1748/530, loss: 0.009945916943252087
2023-01-21 11:04:19.642947: step: 1752/530, loss: 0.006153964903205633
2023-01-21 11:04:20.778319: step: 1756/530, loss: 0.09885292500257492
2023-01-21 11:04:21.899273: step: 1760/530, loss: 0.04025983810424805
2023-01-21 11:04:23.054986: step: 1764/530, loss: 0.07625599205493927
2023-01-21 11:04:24.207643: step: 1768/530, loss: 0.019740868359804153
2023-01-21 11:04:25.368141: step: 1772/530, loss: 0.021004868671298027
2023-01-21 11:04:26.503561: step: 1776/530, loss: 0.014562273398041725
2023-01-21 11:04:27.690317: step: 1780/530, loss: 0.04524674266576767
2023-01-21 11:04:28.830476: step: 1784/530, loss: 0.05356607586145401
2023-01-21 11:04:29.986006: step: 1788/530, loss: 0.0212983600795269
2023-01-21 11:04:31.113590: step: 1792/530, loss: 0.00856771506369114
2023-01-21 11:04:32.257438: step: 1796/530, loss: 0.04802503436803818
2023-01-21 11:04:33.391230: step: 1800/530, loss: 0.0057763103395700455
2023-01-21 11:04:34.517927: step: 1804/530, loss: 0.009444618597626686
2023-01-21 11:04:35.644367: step: 1808/530, loss: 0.04359636455774307
2023-01-21 11:04:36.789354: step: 1812/530, loss: 0.06904659420251846
2023-01-21 11:04:37.940527: step: 1816/530, loss: 0.007182121276855469
2023-01-21 11:04:39.067200: step: 1820/530, loss: 0.042980484664440155
2023-01-21 11:04:40.207759: step: 1824/530, loss: 0.16691899299621582
2023-01-21 11:04:41.370325: step: 1828/530, loss: 0.1238914504647255
2023-01-21 11:04:42.502788: step: 1832/530, loss: 0.08206959068775177
2023-01-21 11:04:43.645116: step: 1836/530, loss: 0.13522785902023315
2023-01-21 11:04:44.765875: step: 1840/530, loss: 0.048134710639715195
2023-01-21 11:04:45.922706: step: 1844/530, loss: 0.05525932461023331
2023-01-21 11:04:47.056717: step: 1848/530, loss: 0.012070799246430397
2023-01-21 11:04:48.179632: step: 1852/530, loss: 0.0012735367054119706
2023-01-21 11:04:49.304156: step: 1856/530, loss: 0.01072161179035902
2023-01-21 11:04:50.493733: step: 1860/530, loss: 0.002234077313914895
2023-01-21 11:04:51.643537: step: 1864/530, loss: 0.020227743312716484
2023-01-21 11:04:52.757291: step: 1868/530, loss: 0.015953445807099342
2023-01-21 11:04:53.902775: step: 1872/530, loss: 0.06407356262207031
2023-01-21 11:04:55.048763: step: 1876/530, loss: 0.004475403111428022
2023-01-21 11:04:56.193306: step: 1880/530, loss: 0.0023292540572583675
2023-01-21 11:04:57.339880: step: 1884/530, loss: 0.029547691345214844
2023-01-21 11:04:58.491583: step: 1888/530, loss: 0.024480152875185013
2023-01-21 11:04:59.605775: step: 1892/530, loss: 0.06298257410526276
2023-01-21 11:05:00.753065: step: 1896/530, loss: 0.024497129023075104
2023-01-21 11:05:01.912735: step: 1900/530, loss: 0.03539686277508736
2023-01-21 11:05:03.021783: step: 1904/530, loss: 0.0018640517955645919
2023-01-21 11:05:04.153550: step: 1908/530, loss: 0.03484821319580078
2023-01-21 11:05:05.302511: step: 1912/530, loss: 0.0005494117503985763
2023-01-21 11:05:06.477541: step: 1916/530, loss: 0.03587331995368004
2023-01-21 11:05:07.615836: step: 1920/530, loss: 0.03732709959149361
2023-01-21 11:05:08.763449: step: 1924/530, loss: 0.06584224849939346
2023-01-21 11:05:09.922407: step: 1928/530, loss: 0.01770963706076145
2023-01-21 11:05:11.059069: step: 1932/530, loss: 0.02332754246890545
2023-01-21 11:05:12.201715: step: 1936/530, loss: 0.025484418496489525
2023-01-21 11:05:13.348569: step: 1940/530, loss: 0.049616243690252304
2023-01-21 11:05:14.457260: step: 1944/530, loss: 0.0028761865105479956
2023-01-21 11:05:15.600768: step: 1948/530, loss: 0.006197929382324219
2023-01-21 11:05:16.735758: step: 1952/530, loss: 0.03634147718548775
2023-01-21 11:05:17.889166: step: 1956/530, loss: 0.016082191839814186
2023-01-21 11:05:19.018047: step: 1960/530, loss: 0.07926121354103088
2023-01-21 11:05:20.149380: step: 1964/530, loss: 0.04786348342895508
2023-01-21 11:05:21.262444: step: 1968/530, loss: 0.32118111848831177
2023-01-21 11:05:22.403463: step: 1972/530, loss: 0.06851263344287872
2023-01-21 11:05:23.546343: step: 1976/530, loss: 0.002298068953678012
2023-01-21 11:05:24.681687: step: 1980/530, loss: 0.0031773566734045744
2023-01-21 11:05:25.828469: step: 1984/530, loss: 0.03522634506225586
2023-01-21 11:05:26.961377: step: 1988/530, loss: 0.012848949991166592
2023-01-21 11:05:28.153492: step: 1992/530, loss: 0.01975088194012642
2023-01-21 11:05:29.307559: step: 1996/530, loss: 0.007328987121582031
2023-01-21 11:05:30.439992: step: 2000/530, loss: 0.002330494113266468
2023-01-21 11:05:31.605258: step: 2004/530, loss: 0.005862521938979626
2023-01-21 11:05:32.780606: step: 2008/530, loss: 0.06223049387335777
2023-01-21 11:05:33.935143: step: 2012/530, loss: 0.037198830395936966
2023-01-21 11:05:35.111887: step: 2016/530, loss: 0.0237592700868845
2023-01-21 11:05:36.249426: step: 2020/530, loss: 0.026169586926698685
2023-01-21 11:05:37.408438: step: 2024/530, loss: 0.004082823172211647
2023-01-21 11:05:38.531035: step: 2028/530, loss: 0.004319810774177313
2023-01-21 11:05:39.676826: step: 2032/530, loss: 0.11130237579345703
2023-01-21 11:05:40.834386: step: 2036/530, loss: 0.025355147197842598
2023-01-21 11:05:41.984395: step: 2040/530, loss: 0.006113815121352673
2023-01-21 11:05:43.121299: step: 2044/530, loss: 0.01732168346643448
2023-01-21 11:05:44.269575: step: 2048/530, loss: 0.03524360805749893
2023-01-21 11:05:45.402174: step: 2052/530, loss: 0.012261915020644665
2023-01-21 11:05:46.562952: step: 2056/530, loss: 0.0031192780006676912
2023-01-21 11:05:47.678263: step: 2060/530, loss: 0.018718766048550606
2023-01-21 11:05:48.810678: step: 2064/530, loss: 0.011591911315917969
2023-01-21 11:05:49.941785: step: 2068/530, loss: 0.2759284973144531
2023-01-21 11:05:51.097503: step: 2072/530, loss: 0.029091263189911842
2023-01-21 11:05:52.209556: step: 2076/530, loss: 0.008381462655961514
2023-01-21 11:05:53.373459: step: 2080/530, loss: 0.32871073484420776
2023-01-21 11:05:54.517982: step: 2084/530, loss: 0.03321533277630806
2023-01-21 11:05:55.665452: step: 2088/530, loss: 0.016414355486631393
2023-01-21 11:05:56.800553: step: 2092/530, loss: 0.03246940299868584
2023-01-21 11:05:57.927230: step: 2096/530, loss: 0.38019055128097534
2023-01-21 11:05:59.043915: step: 2100/530, loss: 0.0020826340187340975
2023-01-21 11:06:00.130669: step: 2104/530, loss: 0.19869403541088104
2023-01-21 11:06:01.271322: step: 2108/530, loss: 0.04479274898767471
2023-01-21 11:06:02.465453: step: 2112/530, loss: 0.009046363644301891
2023-01-21 11:06:03.610083: step: 2116/530, loss: 0.07706699520349503
2023-01-21 11:06:04.775727: step: 2120/530, loss: 0.0016527175903320312
==================================================
Loss: 0.044
--------------------
Dev: {'event': {'p': 0.601025641025641, 'r': 0.7802929427430093, 'f1': 0.679026651216686}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6302177858439202, 'r': 0.7937142857142857, 'f1': 0.7025796661608498}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5833333333333334, 'r': 0.9074074074074074, 'f1': 0.7101449275362318}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.59375, 'r': 0.6031746031746031, 'f1': 0.5984251968503936}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.45454545454545453, 'r': 0.5555555555555556, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:06:47.650764: step: 4/530, loss: 0.0022495747543871403
2023-01-21 11:06:48.846373: step: 8/530, loss: 0.027453137561678886
2023-01-21 11:06:49.974749: step: 12/530, loss: 0.015173769555985928
2023-01-21 11:06:51.093222: step: 16/530, loss: 1.9836426872643642e-05
2023-01-21 11:06:52.222952: step: 20/530, loss: 0.04127292335033417
2023-01-21 11:06:53.393059: step: 24/530, loss: 0.0335293784737587
2023-01-21 11:06:54.537643: step: 28/530, loss: 0.0039837840013206005
2023-01-21 11:06:55.667319: step: 32/530, loss: 0.019377900287508965
2023-01-21 11:06:56.797322: step: 36/530, loss: 0.030337335541844368
2023-01-21 11:06:57.932250: step: 40/530, loss: 0.03910894691944122
2023-01-21 11:06:59.066360: step: 44/530, loss: 0.07952761650085449
2023-01-21 11:07:00.194102: step: 48/530, loss: 0.01567859575152397
2023-01-21 11:07:01.346590: step: 52/530, loss: 0.054190926253795624
2023-01-21 11:07:02.514490: step: 56/530, loss: 0.07511263340711594
2023-01-21 11:07:03.624849: step: 60/530, loss: 0.024922847747802734
2023-01-21 11:07:04.741203: step: 64/530, loss: 0.004439163021743298
2023-01-21 11:07:05.860630: step: 68/530, loss: 0.011149120517075062
2023-01-21 11:07:06.990626: step: 72/530, loss: 0.0002089500630972907
2023-01-21 11:07:08.112290: step: 76/530, loss: 0.004873752593994141
2023-01-21 11:07:09.293984: step: 80/530, loss: 0.00047369004460051656
2023-01-21 11:07:10.412514: step: 84/530, loss: 0.027544498443603516
2023-01-21 11:07:11.562726: step: 88/530, loss: 0.11396074295043945
2023-01-21 11:07:12.697647: step: 92/530, loss: 0.03277111053466797
2023-01-21 11:07:13.830866: step: 96/530, loss: 0.0812450423836708
2023-01-21 11:07:14.977872: step: 100/530, loss: 0.009062194265425205
2023-01-21 11:07:16.128586: step: 104/530, loss: 0.02160368114709854
2023-01-21 11:07:17.271966: step: 108/530, loss: 0.021747970953583717
2023-01-21 11:07:18.399494: step: 112/530, loss: 0.05263872444629669
2023-01-21 11:07:19.558427: step: 116/530, loss: 0.021317483857274055
2023-01-21 11:07:20.694957: step: 120/530, loss: 0.028965378180146217
2023-01-21 11:07:21.863020: step: 124/530, loss: 0.05956468731164932
2023-01-21 11:07:22.980850: step: 128/530, loss: 0.018841171637177467
2023-01-21 11:07:24.114967: step: 132/530, loss: 0.0026429176796227694
2023-01-21 11:07:25.252369: step: 136/530, loss: 0.012954902835190296
2023-01-21 11:07:26.398924: step: 140/530, loss: 0.043633464723825455
2023-01-21 11:07:27.564803: step: 144/530, loss: 0.5690780878067017
2023-01-21 11:07:28.701814: step: 148/530, loss: 0.04194507747888565
2023-01-21 11:07:29.831503: step: 152/530, loss: 0.0075348857790231705
2023-01-21 11:07:30.946949: step: 156/530, loss: 0.006257819943130016
2023-01-21 11:07:32.106299: step: 160/530, loss: 0.0001625060976948589
2023-01-21 11:07:33.243015: step: 164/530, loss: 0.02559070475399494
2023-01-21 11:07:34.397942: step: 168/530, loss: 0.023813629522919655
2023-01-21 11:07:35.543112: step: 172/530, loss: 0.0028514862060546875
2023-01-21 11:07:36.691200: step: 176/530, loss: 0.025811387225985527
2023-01-21 11:07:37.810667: step: 180/530, loss: 0.0026000975631177425
2023-01-21 11:07:38.946480: step: 184/530, loss: 0.00015859604172874242
2023-01-21 11:07:40.066898: step: 188/530, loss: 0.047522738575935364
2023-01-21 11:07:41.186523: step: 192/530, loss: 0.0197772029787302
2023-01-21 11:07:42.309518: step: 196/530, loss: 0.007173729594796896
2023-01-21 11:07:43.432864: step: 200/530, loss: 0.008785438723862171
2023-01-21 11:07:44.614986: step: 204/530, loss: 0.05324520915746689
2023-01-21 11:07:45.758371: step: 208/530, loss: 0.08029670268297195
2023-01-21 11:07:46.895023: step: 212/530, loss: 0.014413261786103249
2023-01-21 11:07:48.039900: step: 216/530, loss: 0.0404631607234478
2023-01-21 11:07:49.170673: step: 220/530, loss: 0.022835921496152878
2023-01-21 11:07:50.292274: step: 224/530, loss: 0.01685018464922905
2023-01-21 11:07:51.482741: step: 228/530, loss: 0.019518554210662842
2023-01-21 11:07:52.618109: step: 232/530, loss: 0.0031232833862304688
2023-01-21 11:07:53.776215: step: 236/530, loss: 0.027121352031826973
2023-01-21 11:07:54.882865: step: 240/530, loss: 0.009561348706483841
2023-01-21 11:07:56.000534: step: 244/530, loss: 0.0013095855247229338
2023-01-21 11:07:57.148789: step: 248/530, loss: 0.11128824949264526
2023-01-21 11:07:58.304137: step: 252/530, loss: 0.00362319964915514
2023-01-21 11:07:59.459180: step: 256/530, loss: 0.0161406509578228
2023-01-21 11:08:00.564769: step: 260/530, loss: 0.02786397933959961
2023-01-21 11:08:01.706777: step: 264/530, loss: 0.01587553136050701
2023-01-21 11:08:02.845583: step: 268/530, loss: 0.0009485245100222528
2023-01-21 11:08:03.987558: step: 272/530, loss: 0.012115478515625
2023-01-21 11:08:05.125121: step: 276/530, loss: 0.006558800116181374
2023-01-21 11:08:06.268065: step: 280/530, loss: 0.008723640814423561
2023-01-21 11:08:07.429193: step: 284/530, loss: 0.016211414709687233
2023-01-21 11:08:08.543713: step: 288/530, loss: 0.003396606305614114
2023-01-21 11:08:09.692547: step: 292/530, loss: 0.03265266492962837
2023-01-21 11:08:10.813518: step: 296/530, loss: 0.0011013984913006425
2023-01-21 11:08:11.946558: step: 300/530, loss: 0.0047817230224609375
2023-01-21 11:08:13.096072: step: 304/530, loss: 0.0015641212230548263
2023-01-21 11:08:14.279692: step: 308/530, loss: 0.025176238268613815
2023-01-21 11:08:15.412293: step: 312/530, loss: 0.009770012460649014
2023-01-21 11:08:16.528766: step: 316/530, loss: 0.006199407856911421
2023-01-21 11:08:17.682726: step: 320/530, loss: 0.024837994948029518
2023-01-21 11:08:18.815625: step: 324/530, loss: 0.0173492431640625
2023-01-21 11:08:19.969039: step: 328/530, loss: 0.019259072840213776
2023-01-21 11:08:21.092261: step: 332/530, loss: 0.004490661434829235
2023-01-21 11:08:22.230876: step: 336/530, loss: 0.03045501746237278
2023-01-21 11:08:23.385420: step: 340/530, loss: 0.010313368402421474
2023-01-21 11:08:24.524206: step: 344/530, loss: 0.12140186131000519
2023-01-21 11:08:25.678258: step: 348/530, loss: 0.0033143043983727694
2023-01-21 11:08:26.822977: step: 352/530, loss: 0.011401081457734108
2023-01-21 11:08:27.959598: step: 356/530, loss: 0.009322643280029297
2023-01-21 11:08:29.121884: step: 360/530, loss: 0.020762061700224876
2023-01-21 11:08:30.273266: step: 364/530, loss: 0.0015563011402264237
2023-01-21 11:08:31.394251: step: 368/530, loss: 0.002956581301987171
2023-01-21 11:08:32.546930: step: 372/530, loss: 0.05156007036566734
2023-01-21 11:08:33.728711: step: 376/530, loss: 0.1172674149274826
2023-01-21 11:08:34.877936: step: 380/530, loss: 0.25614890456199646
2023-01-21 11:08:36.047166: step: 384/530, loss: 0.5383098721504211
2023-01-21 11:08:37.207685: step: 388/530, loss: 0.04896602779626846
2023-01-21 11:08:38.371561: step: 392/530, loss: 0.025785064324736595
2023-01-21 11:08:39.522806: step: 396/530, loss: 0.002616977784782648
2023-01-21 11:08:40.706547: step: 400/530, loss: 0.0023356438614428043
2023-01-21 11:08:41.871312: step: 404/530, loss: 0.036078643053770065
2023-01-21 11:08:43.037404: step: 408/530, loss: 0.016096973791718483
2023-01-21 11:08:44.179902: step: 412/530, loss: 0.11197032779455185
2023-01-21 11:08:45.320504: step: 416/530, loss: 0.001728916191495955
2023-01-21 11:08:46.424828: step: 420/530, loss: 0.7216484546661377
2023-01-21 11:08:47.571846: step: 424/530, loss: 0.11852455139160156
2023-01-21 11:08:48.737403: step: 428/530, loss: 0.0615270659327507
2023-01-21 11:08:49.869859: step: 432/530, loss: 0.01127920113503933
2023-01-21 11:08:51.027268: step: 436/530, loss: 0.04503965377807617
2023-01-21 11:08:52.186897: step: 440/530, loss: 0.02493734285235405
2023-01-21 11:08:53.330225: step: 444/530, loss: 0.022767448797822
2023-01-21 11:08:54.509953: step: 448/530, loss: 0.0014804840320721269
2023-01-21 11:08:55.648372: step: 452/530, loss: 0.002362004015594721
2023-01-21 11:08:56.795007: step: 456/530, loss: 0.011768865399062634
2023-01-21 11:08:57.916112: step: 460/530, loss: 0.0006501197931356728
2023-01-21 11:08:59.036816: step: 464/530, loss: 0.0033471081405878067
2023-01-21 11:09:00.156496: step: 468/530, loss: 0.019545840099453926
2023-01-21 11:09:01.283765: step: 472/530, loss: 0.017697429284453392
2023-01-21 11:09:02.433680: step: 476/530, loss: 0.003911018371582031
2023-01-21 11:09:03.562602: step: 480/530, loss: 0.0004428863467182964
2023-01-21 11:09:04.706967: step: 484/530, loss: 0.03216571733355522
2023-01-21 11:09:05.879507: step: 488/530, loss: 0.002635478973388672
2023-01-21 11:09:07.012316: step: 492/530, loss: 0.0017868519062176347
2023-01-21 11:09:08.179010: step: 496/530, loss: 0.011644745245575905
2023-01-21 11:09:09.311576: step: 500/530, loss: 0.02579822577536106
2023-01-21 11:09:10.478772: step: 504/530, loss: 0.04940824583172798
2023-01-21 11:09:11.628642: step: 508/530, loss: 0.012224579229950905
2023-01-21 11:09:12.740644: step: 512/530, loss: 0.01204976998269558
2023-01-21 11:09:13.886697: step: 516/530, loss: 0.0043631079606711864
2023-01-21 11:09:15.023685: step: 520/530, loss: 0.028780747205018997
2023-01-21 11:09:16.167682: step: 524/530, loss: 0.03128452226519585
2023-01-21 11:09:17.322028: step: 528/530, loss: 0.04554860666394234
2023-01-21 11:09:18.459591: step: 532/530, loss: 0.014803219586610794
2023-01-21 11:09:19.603067: step: 536/530, loss: 0.02670145034790039
2023-01-21 11:09:20.729408: step: 540/530, loss: 0.020496414974331856
2023-01-21 11:09:21.858576: step: 544/530, loss: 0.0012233257293701172
2023-01-21 11:09:23.022023: step: 548/530, loss: 0.008387756533920765
2023-01-21 11:09:24.143570: step: 552/530, loss: 0.0001066207914846018
2023-01-21 11:09:25.285574: step: 556/530, loss: 0.02556305006146431
2023-01-21 11:09:26.409730: step: 560/530, loss: 0.038468170911073685
2023-01-21 11:09:27.543014: step: 564/530, loss: 0.11213312298059464
2023-01-21 11:09:28.687369: step: 568/530, loss: 0.04802103340625763
2023-01-21 11:09:29.797023: step: 572/530, loss: 0.0009373187785968184
2023-01-21 11:09:30.917584: step: 576/530, loss: 0.004887962713837624
2023-01-21 11:09:32.097721: step: 580/530, loss: 0.030956365168094635
2023-01-21 11:09:33.258398: step: 584/530, loss: 0.0010581969982013106
2023-01-21 11:09:34.396165: step: 588/530, loss: 0.028652288019657135
2023-01-21 11:09:35.524631: step: 592/530, loss: 0.023152925074100494
2023-01-21 11:09:36.703062: step: 596/530, loss: 0.006566429045051336
2023-01-21 11:09:37.830758: step: 600/530, loss: 0.01933755911886692
2023-01-21 11:09:38.987911: step: 604/530, loss: 0.02361154742538929
2023-01-21 11:09:40.137655: step: 608/530, loss: 0.04239635542035103
2023-01-21 11:09:41.288718: step: 612/530, loss: 0.08468551933765411
2023-01-21 11:09:42.432664: step: 616/530, loss: 0.009547806344926357
2023-01-21 11:09:43.586795: step: 620/530, loss: 0.00022602081298828125
2023-01-21 11:09:44.732416: step: 624/530, loss: 0.05247362703084946
2023-01-21 11:09:45.868259: step: 628/530, loss: 0.04792613908648491
2023-01-21 11:09:47.011653: step: 632/530, loss: 0.00105371477548033
2023-01-21 11:09:48.169695: step: 636/530, loss: 0.0013751983642578125
2023-01-21 11:09:49.305572: step: 640/530, loss: 0.002451324602589011
2023-01-21 11:09:50.447646: step: 644/530, loss: 0.006276130676269531
2023-01-21 11:09:51.578205: step: 648/530, loss: 0.08488478511571884
2023-01-21 11:09:52.740971: step: 652/530, loss: 0.10239487141370773
2023-01-21 11:09:53.897898: step: 656/530, loss: 0.19045695662498474
2023-01-21 11:09:55.051345: step: 660/530, loss: 0.015345001593232155
2023-01-21 11:09:56.192725: step: 664/530, loss: 0.02175135724246502
2023-01-21 11:09:57.299061: step: 668/530, loss: 0.0006373882642947137
2023-01-21 11:09:58.439214: step: 672/530, loss: 0.08657453209161758
2023-01-21 11:09:59.565051: step: 676/530, loss: 0.004469871986657381
2023-01-21 11:10:00.718134: step: 680/530, loss: 0.003891468048095703
2023-01-21 11:10:01.852322: step: 684/530, loss: 0.004010486416518688
2023-01-21 11:10:03.006562: step: 688/530, loss: 0.04857354238629341
2023-01-21 11:10:04.129219: step: 692/530, loss: 0.07218170166015625
2023-01-21 11:10:05.283105: step: 696/530, loss: 0.022953415289521217
2023-01-21 11:10:06.459637: step: 700/530, loss: 0.014371681027114391
2023-01-21 11:10:07.629487: step: 704/530, loss: 0.020641900599002838
2023-01-21 11:10:08.771974: step: 708/530, loss: 0.04459667205810547
2023-01-21 11:10:09.867530: step: 712/530, loss: 0.00032927992288023233
2023-01-21 11:10:11.013273: step: 716/530, loss: 0.0008575440151616931
2023-01-21 11:10:12.150584: step: 720/530, loss: 0.0030700683128088713
2023-01-21 11:10:13.300757: step: 724/530, loss: 0.4481928050518036
2023-01-21 11:10:14.468516: step: 728/530, loss: 0.039377786219120026
2023-01-21 11:10:15.615544: step: 732/530, loss: 0.01096496544778347
2023-01-21 11:10:16.772170: step: 736/530, loss: 0.00903244037181139
2023-01-21 11:10:17.921954: step: 740/530, loss: 0.25938883423805237
2023-01-21 11:10:19.025974: step: 744/530, loss: 0.00915222242474556
2023-01-21 11:10:20.147400: step: 748/530, loss: 0.015636634081602097
2023-01-21 11:10:21.334517: step: 752/530, loss: 0.0004044532834086567
2023-01-21 11:10:22.468702: step: 756/530, loss: 0.011844445019960403
2023-01-21 11:10:23.618349: step: 760/530, loss: 0.01631746254861355
2023-01-21 11:10:24.809093: step: 764/530, loss: 0.04962310940027237
2023-01-21 11:10:25.953273: step: 768/530, loss: 0.011441421695053577
2023-01-21 11:10:27.123959: step: 772/530, loss: 0.01764697954058647
2023-01-21 11:10:28.257763: step: 776/530, loss: 0.08282966911792755
2023-01-21 11:10:29.391809: step: 780/530, loss: 0.5871692299842834
2023-01-21 11:10:30.527536: step: 784/530, loss: 0.04664936289191246
2023-01-21 11:10:31.668959: step: 788/530, loss: 0.009368419647216797
2023-01-21 11:10:32.840035: step: 792/530, loss: 0.031528569757938385
2023-01-21 11:10:33.995619: step: 796/530, loss: 0.027863502502441406
2023-01-21 11:10:35.139829: step: 800/530, loss: 0.019846439361572266
2023-01-21 11:10:36.265702: step: 804/530, loss: 0.08358190953731537
2023-01-21 11:10:37.380367: step: 808/530, loss: 0.039481259882450104
2023-01-21 11:10:38.531840: step: 812/530, loss: 0.11425495147705078
2023-01-21 11:10:39.651181: step: 816/530, loss: 0.06822285801172256
2023-01-21 11:10:40.768720: step: 820/530, loss: 0.0009700298542156816
2023-01-21 11:10:41.910290: step: 824/530, loss: 0.016520213335752487
2023-01-21 11:10:43.030745: step: 828/530, loss: 0.00345611572265625
2023-01-21 11:10:44.166183: step: 832/530, loss: 0.03575306385755539
2023-01-21 11:10:45.318012: step: 836/530, loss: 0.06122875213623047
2023-01-21 11:10:46.477235: step: 840/530, loss: 0.004982376471161842
2023-01-21 11:10:47.611882: step: 844/530, loss: 0.01490790769457817
2023-01-21 11:10:48.752418: step: 848/530, loss: 0.027049541473388672
2023-01-21 11:10:49.865012: step: 852/530, loss: 0.03465709835290909
2023-01-21 11:10:51.006236: step: 856/530, loss: 0.00519218435510993
2023-01-21 11:10:52.129699: step: 860/530, loss: 0.0035415650345385075
2023-01-21 11:10:53.266940: step: 864/530, loss: 0.03077240101993084
2023-01-21 11:10:54.398971: step: 868/530, loss: 0.021011972799897194
2023-01-21 11:10:55.509339: step: 872/530, loss: 0.0033246041275560856
2023-01-21 11:10:56.648362: step: 876/530, loss: 0.03613033518195152
2023-01-21 11:10:57.774749: step: 880/530, loss: 0.04351158067584038
2023-01-21 11:10:58.917696: step: 884/530, loss: 0.0026803971268236637
2023-01-21 11:11:00.044313: step: 888/530, loss: 0.02001781575381756
2023-01-21 11:11:01.201392: step: 892/530, loss: 0.003724479814991355
2023-01-21 11:11:02.334939: step: 896/530, loss: 0.024578142911195755
2023-01-21 11:11:03.501650: step: 900/530, loss: 0.06598224490880966
2023-01-21 11:11:04.622206: step: 904/530, loss: 0.053090669214725494
2023-01-21 11:11:05.782987: step: 908/530, loss: 0.01750488393008709
2023-01-21 11:11:06.905064: step: 912/530, loss: 0.039853956550359726
2023-01-21 11:11:08.041137: step: 916/530, loss: 0.007404947187751532
2023-01-21 11:11:09.211859: step: 920/530, loss: 0.0014955521328374743
2023-01-21 11:11:10.341914: step: 924/530, loss: 0.04957304149866104
2023-01-21 11:11:11.480018: step: 928/530, loss: 0.002016258193179965
2023-01-21 11:11:12.604919: step: 932/530, loss: 0.04202842712402344
2023-01-21 11:11:13.751613: step: 936/530, loss: 0.004660606384277344
2023-01-21 11:11:14.907545: step: 940/530, loss: 0.029612064361572266
2023-01-21 11:11:16.039521: step: 944/530, loss: 0.011448907665908337
2023-01-21 11:11:17.188482: step: 948/530, loss: 0.019666194915771484
2023-01-21 11:11:18.370217: step: 952/530, loss: 0.028432132676243782
2023-01-21 11:11:19.510180: step: 956/530, loss: 0.0387774258852005
2023-01-21 11:11:20.632991: step: 960/530, loss: 0.00818166695535183
2023-01-21 11:11:21.772042: step: 964/530, loss: 0.00033168791560456157
2023-01-21 11:11:22.912445: step: 968/530, loss: 0.0005858421209268272
2023-01-21 11:11:24.060532: step: 972/530, loss: 0.0048181889578700066
2023-01-21 11:11:25.206352: step: 976/530, loss: 0.006972027011215687
2023-01-21 11:11:26.306565: step: 980/530, loss: 0.014428138732910156
2023-01-21 11:11:27.435236: step: 984/530, loss: 0.0013927459949627519
2023-01-21 11:11:28.545415: step: 988/530, loss: 0.04205961525440216
2023-01-21 11:11:29.685781: step: 992/530, loss: 0.0018564225174486637
2023-01-21 11:11:30.820542: step: 996/530, loss: 0.11214561015367508
2023-01-21 11:11:31.949588: step: 1000/530, loss: 0.044797517359256744
2023-01-21 11:11:33.162604: step: 1004/530, loss: 0.006389426998794079
2023-01-21 11:11:34.280673: step: 1008/530, loss: 0.07247067242860794
2023-01-21 11:11:35.403057: step: 1012/530, loss: 0.011844920925796032
2023-01-21 11:11:36.532840: step: 1016/530, loss: 0.07476310431957245
2023-01-21 11:11:37.679665: step: 1020/530, loss: 0.07355518639087677
2023-01-21 11:11:38.811297: step: 1024/530, loss: 0.00018343926058150828
2023-01-21 11:11:39.945080: step: 1028/530, loss: 0.0309524554759264
2023-01-21 11:11:41.099099: step: 1032/530, loss: 0.0075664520263671875
2023-01-21 11:11:42.241832: step: 1036/530, loss: 0.012372780591249466
2023-01-21 11:11:43.398193: step: 1040/530, loss: 0.04217557981610298
2023-01-21 11:11:44.548025: step: 1044/530, loss: 0.00113334646448493
2023-01-21 11:11:45.694543: step: 1048/530, loss: 0.01747121848165989
2023-01-21 11:11:46.856217: step: 1052/530, loss: 0.033419419080019
2023-01-21 11:11:47.989202: step: 1056/530, loss: 0.012417793273925781
2023-01-21 11:11:49.150692: step: 1060/530, loss: 0.02894134633243084
2023-01-21 11:11:50.277758: step: 1064/530, loss: 0.02543802373111248
2023-01-21 11:11:51.399647: step: 1068/530, loss: 0.03713976591825485
2023-01-21 11:11:52.556246: step: 1072/530, loss: 0.03670807182788849
2023-01-21 11:11:53.678609: step: 1076/530, loss: 0.004036712925881147
2023-01-21 11:11:54.809907: step: 1080/530, loss: 0.011581946164369583
2023-01-21 11:11:55.975438: step: 1084/530, loss: 0.005394076928496361
2023-01-21 11:11:57.100803: step: 1088/530, loss: 0.018703460693359375
2023-01-21 11:11:58.240624: step: 1092/530, loss: 0.04775209724903107
2023-01-21 11:11:59.370104: step: 1096/530, loss: 0.014824104495346546
2023-01-21 11:12:00.537147: step: 1100/530, loss: 0.7751873135566711
2023-01-21 11:12:01.684261: step: 1104/530, loss: 0.055441856384277344
2023-01-21 11:12:02.843998: step: 1108/530, loss: 0.0009801865089684725
2023-01-21 11:12:03.956112: step: 1112/530, loss: 9.479522850597277e-05
2023-01-21 11:12:05.085173: step: 1116/530, loss: 0.00298900599591434
2023-01-21 11:12:06.222151: step: 1120/530, loss: 0.0027958869468420744
2023-01-21 11:12:07.388247: step: 1124/530, loss: 0.04132647439837456
2023-01-21 11:12:08.534870: step: 1128/530, loss: 0.0006742477416992188
2023-01-21 11:12:09.668954: step: 1132/530, loss: 0.015451241284608841
2023-01-21 11:12:10.810840: step: 1136/530, loss: 0.00542373675853014
2023-01-21 11:12:11.950483: step: 1140/530, loss: 0.026175014674663544
2023-01-21 11:12:13.087708: step: 1144/530, loss: 0.004846715833991766
2023-01-21 11:12:14.241736: step: 1148/530, loss: 0.1631934642791748
2023-01-21 11:12:15.383014: step: 1152/530, loss: 0.009257292374968529
2023-01-21 11:12:16.524156: step: 1156/530, loss: 0.019746972247958183
2023-01-21 11:12:17.672690: step: 1160/530, loss: 0.09086446464061737
2023-01-21 11:12:18.817236: step: 1164/530, loss: 0.015233039855957031
2023-01-21 11:12:19.936955: step: 1168/530, loss: 0.004391479305922985
2023-01-21 11:12:21.071997: step: 1172/530, loss: 0.16498994827270508
2023-01-21 11:12:22.284936: step: 1176/530, loss: 0.000125885009765625
2023-01-21 11:12:23.442030: step: 1180/530, loss: 0.025980282574892044
2023-01-21 11:12:24.591448: step: 1184/530, loss: 0.008759498596191406
2023-01-21 11:12:25.753163: step: 1188/530, loss: 0.0016201974358409643
2023-01-21 11:12:26.910272: step: 1192/530, loss: 0.018706941977143288
2023-01-21 11:12:28.056879: step: 1196/530, loss: 0.012826346792280674
2023-01-21 11:12:29.205951: step: 1200/530, loss: 0.0036918639671057463
2023-01-21 11:12:30.371629: step: 1204/530, loss: 0.0005822181701660156
2023-01-21 11:12:31.507341: step: 1208/530, loss: 0.01943178102374077
2023-01-21 11:12:32.634238: step: 1212/530, loss: 0.003605079837143421
2023-01-21 11:12:33.807040: step: 1216/530, loss: 0.142752543091774
2023-01-21 11:12:34.966910: step: 1220/530, loss: 0.12354221194982529
2023-01-21 11:12:36.106217: step: 1224/530, loss: 0.03123927116394043
2023-01-21 11:12:37.238665: step: 1228/530, loss: 0.07926268875598907
2023-01-21 11:12:38.361417: step: 1232/530, loss: 0.004521084018051624
2023-01-21 11:12:39.513504: step: 1236/530, loss: 0.005951500032097101
2023-01-21 11:12:40.637721: step: 1240/530, loss: 0.0013096809852868319
2023-01-21 11:12:41.776223: step: 1244/530, loss: 0.08325204998254776
2023-01-21 11:12:42.911749: step: 1248/530, loss: 0.008430671878159046
2023-01-21 11:12:44.079717: step: 1252/530, loss: 0.0002208709775004536
2023-01-21 11:12:45.184693: step: 1256/530, loss: 0.003626400139182806
2023-01-21 11:12:46.373136: step: 1260/530, loss: 0.03239841386675835
2023-01-21 11:12:47.534570: step: 1264/530, loss: 0.2533597946166992
2023-01-21 11:12:48.648314: step: 1268/530, loss: 0.0015319825615733862
2023-01-21 11:12:49.770073: step: 1272/530, loss: 0.023151494562625885
2023-01-21 11:12:50.917974: step: 1276/530, loss: 0.020995520055294037
2023-01-21 11:12:52.046336: step: 1280/530, loss: 0.06405086815357208
2023-01-21 11:12:53.213043: step: 1284/530, loss: 0.011304665356874466
2023-01-21 11:12:54.363436: step: 1288/530, loss: 0.010596848092973232
2023-01-21 11:12:55.533448: step: 1292/530, loss: 0.02088928036391735
2023-01-21 11:12:56.678671: step: 1296/530, loss: 0.0031269073951989412
2023-01-21 11:12:57.794946: step: 1300/530, loss: 0.05312724411487579
2023-01-21 11:12:58.933578: step: 1304/530, loss: 0.009411764331161976
2023-01-21 11:13:00.090922: step: 1308/530, loss: 0.08324223011732101
2023-01-21 11:13:01.221246: step: 1312/530, loss: 0.009753083810210228
2023-01-21 11:13:02.363054: step: 1316/530, loss: 0.01343164499849081
2023-01-21 11:13:03.511248: step: 1320/530, loss: 0.040036965161561966
2023-01-21 11:13:04.649059: step: 1324/530, loss: 0.038382720202207565
2023-01-21 11:13:05.783569: step: 1328/530, loss: 0.019205475226044655
2023-01-21 11:13:06.954274: step: 1332/530, loss: 0.06474494934082031
2023-01-21 11:13:08.102225: step: 1336/530, loss: 0.0567447654902935
2023-01-21 11:13:09.257361: step: 1340/530, loss: 0.022373007610440254
2023-01-21 11:13:10.377945: step: 1344/530, loss: 0.09464531391859055
2023-01-21 11:13:11.512690: step: 1348/530, loss: 0.24595364928245544
2023-01-21 11:13:12.649997: step: 1352/530, loss: 0.06726942956447601
2023-01-21 11:13:13.779009: step: 1356/530, loss: 0.000587892543990165
2023-01-21 11:13:14.914654: step: 1360/530, loss: 0.03328799456357956
2023-01-21 11:13:16.067406: step: 1364/530, loss: 0.006768417079001665
2023-01-21 11:13:17.190419: step: 1368/530, loss: 0.0036138533614575863
2023-01-21 11:13:18.325233: step: 1372/530, loss: 0.019726086407899857
2023-01-21 11:13:19.453699: step: 1376/530, loss: 0.020239925011992455
2023-01-21 11:13:20.607928: step: 1380/530, loss: 0.061925604939460754
2023-01-21 11:13:21.769977: step: 1384/530, loss: 0.007011318579316139
2023-01-21 11:13:22.922617: step: 1388/530, loss: 0.012970829382538795
2023-01-21 11:13:24.075214: step: 1392/530, loss: 0.05281582102179527
2023-01-21 11:13:25.239681: step: 1396/530, loss: 0.00199127197265625
2023-01-21 11:13:26.362853: step: 1400/530, loss: 0.083338163793087
2023-01-21 11:13:27.496717: step: 1404/530, loss: 0.001103305839933455
2023-01-21 11:13:28.638258: step: 1408/530, loss: 0.03239836543798447
2023-01-21 11:13:29.810552: step: 1412/530, loss: 0.013076973147690296
2023-01-21 11:13:30.961646: step: 1416/530, loss: 0.053762149065732956
2023-01-21 11:13:32.131879: step: 1420/530, loss: 0.01584300957620144
2023-01-21 11:13:33.291334: step: 1424/530, loss: 0.057558417320251465
2023-01-21 11:13:34.419563: step: 1428/530, loss: 0.07993412017822266
2023-01-21 11:13:35.563620: step: 1432/530, loss: 0.06793813407421112
2023-01-21 11:13:36.707304: step: 1436/530, loss: 0.013351822271943092
2023-01-21 11:13:37.838724: step: 1440/530, loss: 0.012730789370834827
2023-01-21 11:13:38.974941: step: 1444/530, loss: 0.018189240247011185
2023-01-21 11:13:40.088037: step: 1448/530, loss: 0.013106727972626686
2023-01-21 11:13:41.226462: step: 1452/530, loss: 0.03323383256793022
2023-01-21 11:13:42.365657: step: 1456/530, loss: 0.044008851051330566
2023-01-21 11:13:43.509937: step: 1460/530, loss: 0.027964306995272636
2023-01-21 11:13:44.669966: step: 1464/530, loss: 0.20341968536376953
2023-01-21 11:13:45.812838: step: 1468/530, loss: 0.014215660281479359
2023-01-21 11:13:46.956101: step: 1472/530, loss: 0.06564760208129883
2023-01-21 11:13:48.098097: step: 1476/530, loss: 0.03257398679852486
2023-01-21 11:13:49.225209: step: 1480/530, loss: 0.034955885261297226
2023-01-21 11:13:50.370166: step: 1484/530, loss: 0.014664220623672009
2023-01-21 11:13:51.488794: step: 1488/530, loss: 0.0292223934084177
2023-01-21 11:13:52.640668: step: 1492/530, loss: 0.019066713750362396
2023-01-21 11:13:53.750334: step: 1496/530, loss: 0.0007094383472576737
2023-01-21 11:13:54.898654: step: 1500/530, loss: 1.05991966847796e-05
2023-01-21 11:13:56.062396: step: 1504/530, loss: 0.04739703983068466
2023-01-21 11:13:57.170737: step: 1508/530, loss: 0.025888871401548386
2023-01-21 11:13:58.310664: step: 1512/530, loss: 0.012617398053407669
2023-01-21 11:13:59.450961: step: 1516/530, loss: 0.28444352746009827
2023-01-21 11:14:00.583555: step: 1520/530, loss: 0.009024095721542835
2023-01-21 11:14:01.727407: step: 1524/530, loss: 0.04159350320696831
2023-01-21 11:14:02.852954: step: 1528/530, loss: 0.04926910623908043
2023-01-21 11:14:03.983583: step: 1532/530, loss: 0.04357462003827095
2023-01-21 11:14:05.113097: step: 1536/530, loss: 0.01802654191851616
2023-01-21 11:14:06.260640: step: 1540/530, loss: 0.09883490204811096
2023-01-21 11:14:07.430242: step: 1544/530, loss: 0.021542739123106003
2023-01-21 11:14:08.556791: step: 1548/530, loss: 0.05192837491631508
2023-01-21 11:14:09.696943: step: 1552/530, loss: 0.04709911346435547
2023-01-21 11:14:10.841666: step: 1556/530, loss: 0.003937769215553999
2023-01-21 11:14:11.950975: step: 1560/530, loss: 0.012407207861542702
2023-01-21 11:14:13.089366: step: 1564/530, loss: 0.08206062018871307
2023-01-21 11:14:14.263458: step: 1568/530, loss: 0.07946185767650604
2023-01-21 11:14:15.392096: step: 1572/530, loss: 0.033326055854558945
2023-01-21 11:14:16.510953: step: 1576/530, loss: 0.004254436586052179
2023-01-21 11:14:17.626123: step: 1580/530, loss: 0.023253725841641426
2023-01-21 11:14:18.756390: step: 1584/530, loss: 0.0005327224498614669
2023-01-21 11:14:19.887602: step: 1588/530, loss: 0.033684540539979935
2023-01-21 11:14:21.012799: step: 1592/530, loss: 0.004670047666877508
2023-01-21 11:14:22.139279: step: 1596/530, loss: 0.010883951559662819
2023-01-21 11:14:23.300278: step: 1600/530, loss: 0.001874303910881281
2023-01-21 11:14:24.458022: step: 1604/530, loss: 0.5510677099227905
2023-01-21 11:14:25.600279: step: 1608/530, loss: 0.08102130889892578
2023-01-21 11:14:26.727126: step: 1612/530, loss: 0.020445728674530983
2023-01-21 11:14:27.874298: step: 1616/530, loss: 0.00021982192993164062
2023-01-21 11:14:29.039197: step: 1620/530, loss: 0.042637065052986145
2023-01-21 11:14:30.181413: step: 1624/530, loss: 0.03626289218664169
2023-01-21 11:14:31.297244: step: 1628/530, loss: 6.201267387950793e-05
2023-01-21 11:14:32.412277: step: 1632/530, loss: 0.1518077850341797
2023-01-21 11:14:33.561667: step: 1636/530, loss: 0.000354766845703125
2023-01-21 11:14:34.690473: step: 1640/530, loss: 0.011517238803207874
2023-01-21 11:14:35.850437: step: 1644/530, loss: 0.08944845199584961
2023-01-21 11:14:36.985955: step: 1648/530, loss: 0.04848074913024902
2023-01-21 11:14:38.102199: step: 1652/530, loss: 0.023461056873202324
2023-01-21 11:14:39.240967: step: 1656/530, loss: 0.01971564255654812
2023-01-21 11:14:40.370566: step: 1660/530, loss: 0.003798866178840399
2023-01-21 11:14:41.506787: step: 1664/530, loss: 0.0005322456709109247
2023-01-21 11:14:42.635623: step: 1668/530, loss: 0.00226764683611691
2023-01-21 11:14:43.733746: step: 1672/530, loss: 0.07877865433692932
2023-01-21 11:14:44.867414: step: 1676/530, loss: 0.017559051513671875
2023-01-21 11:14:45.998713: step: 1680/530, loss: 0.0555761344730854
2023-01-21 11:14:47.118425: step: 1684/530, loss: 0.03500433266162872
2023-01-21 11:14:48.266539: step: 1688/530, loss: 0.03232298046350479
2023-01-21 11:14:49.400290: step: 1692/530, loss: 0.0359375961124897
2023-01-21 11:14:50.521508: step: 1696/530, loss: 0.037431810051202774
2023-01-21 11:14:51.680650: step: 1700/530, loss: 0.030335808172822
2023-01-21 11:14:52.840651: step: 1704/530, loss: 0.07949409633874893
2023-01-21 11:14:53.972250: step: 1708/530, loss: 0.006646347232162952
2023-01-21 11:14:55.116191: step: 1712/530, loss: 0.0024454116355627775
2023-01-21 11:14:56.258961: step: 1716/530, loss: 0.04267530515789986
2023-01-21 11:14:57.386503: step: 1720/530, loss: 0.005366945173591375
2023-01-21 11:14:58.531040: step: 1724/530, loss: 0.0634043738245964
2023-01-21 11:14:59.709235: step: 1728/530, loss: 0.05149383470416069
2023-01-21 11:15:00.887131: step: 1732/530, loss: 0.03491363674402237
2023-01-21 11:15:02.023093: step: 1736/530, loss: 0.036701466888189316
2023-01-21 11:15:03.150720: step: 1740/530, loss: 0.015925992280244827
2023-01-21 11:15:04.300043: step: 1744/530, loss: 0.0012866973411291838
2023-01-21 11:15:05.450550: step: 1748/530, loss: 0.026250457391142845
2023-01-21 11:15:06.622060: step: 1752/530, loss: 0.08851146697998047
2023-01-21 11:15:07.747363: step: 1756/530, loss: 0.01152658462524414
2023-01-21 11:15:08.892289: step: 1760/530, loss: 0.005018806550651789
2023-01-21 11:15:10.059775: step: 1764/530, loss: 0.6873079538345337
2023-01-21 11:15:11.199235: step: 1768/530, loss: 0.12106628715991974
2023-01-21 11:15:12.369996: step: 1772/530, loss: 0.0023463249672204256
2023-01-21 11:15:13.480686: step: 1776/530, loss: 0.4988580644130707
2023-01-21 11:15:14.579865: step: 1780/530, loss: 0.057986073195934296
2023-01-21 11:15:15.705289: step: 1784/530, loss: 0.0013458728790283203
2023-01-21 11:15:16.833166: step: 1788/530, loss: 0.046936798840761185
2023-01-21 11:15:17.985386: step: 1792/530, loss: 0.01726841926574707
2023-01-21 11:15:19.132510: step: 1796/530, loss: 0.010210990905761719
2023-01-21 11:15:20.249753: step: 1800/530, loss: 0.0487792007625103
2023-01-21 11:15:21.390820: step: 1804/530, loss: 0.009932136163115501
2023-01-21 11:15:22.558968: step: 1808/530, loss: 0.024523163214325905
2023-01-21 11:15:23.693678: step: 1812/530, loss: 0.04125223308801651
2023-01-21 11:15:24.839668: step: 1816/530, loss: 0.04036378860473633
2023-01-21 11:15:26.000692: step: 1820/530, loss: 0.3591706156730652
2023-01-21 11:15:27.137184: step: 1824/530, loss: 0.04822826385498047
2023-01-21 11:15:28.270672: step: 1828/530, loss: 0.05476117134094238
2023-01-21 11:15:29.430560: step: 1832/530, loss: 0.034261513501405716
2023-01-21 11:15:30.574903: step: 1836/530, loss: 0.013497447595000267
2023-01-21 11:15:31.732488: step: 1840/530, loss: 0.034429170191287994
2023-01-21 11:15:32.882041: step: 1844/530, loss: 0.002293872879818082
2023-01-21 11:15:34.009472: step: 1848/530, loss: 0.0019749640487134457
2023-01-21 11:15:35.150969: step: 1852/530, loss: 0.04181012883782387
2023-01-21 11:15:36.264527: step: 1856/530, loss: 0.00024565457715652883
2023-01-21 11:15:37.435034: step: 1860/530, loss: 0.020519353449344635
2023-01-21 11:15:38.564077: step: 1864/530, loss: 0.028027629479765892
2023-01-21 11:15:39.727352: step: 1868/530, loss: 0.24358253180980682
2023-01-21 11:15:40.850276: step: 1872/530, loss: 0.074903704226017
2023-01-21 11:15:41.980346: step: 1876/530, loss: 0.0020058155059814453
2023-01-21 11:15:43.089464: step: 1880/530, loss: 0.042814258486032486
2023-01-21 11:15:44.259058: step: 1884/530, loss: 0.007417869754135609
2023-01-21 11:15:45.424697: step: 1888/530, loss: 0.015611648559570312
2023-01-21 11:15:46.531275: step: 1892/530, loss: 0.034890320152044296
2023-01-21 11:15:47.668938: step: 1896/530, loss: 0.00016932487778831273
2023-01-21 11:15:48.807002: step: 1900/530, loss: 0.03131704404950142
2023-01-21 11:15:49.951028: step: 1904/530, loss: 0.003062772797420621
2023-01-21 11:15:51.066591: step: 1908/530, loss: 0.0022687495220452547
2023-01-21 11:15:52.201916: step: 1912/530, loss: 0.026704657822847366
2023-01-21 11:15:53.333498: step: 1916/530, loss: 0.011846351437270641
2023-01-21 11:15:54.481273: step: 1920/530, loss: 0.016640376299619675
2023-01-21 11:15:55.598198: step: 1924/530, loss: 0.0004940032958984375
2023-01-21 11:15:56.722544: step: 1928/530, loss: 0.03679848089814186
2023-01-21 11:15:57.864595: step: 1932/530, loss: 0.010357856750488281
2023-01-21 11:15:59.001472: step: 1936/530, loss: 0.030941247940063477
2023-01-21 11:16:00.176408: step: 1940/530, loss: 0.0673748031258583
2023-01-21 11:16:01.321072: step: 1944/530, loss: 0.004721737001091242
2023-01-21 11:16:02.459570: step: 1948/530, loss: 0.00037875177804380655
2023-01-21 11:16:03.599971: step: 1952/530, loss: 0.05491599813103676
2023-01-21 11:16:04.804031: step: 1956/530, loss: 0.31745922565460205
2023-01-21 11:16:05.934319: step: 1960/530, loss: 0.06049938127398491
2023-01-21 11:16:07.119045: step: 1964/530, loss: 0.009197951294481754
2023-01-21 11:16:08.264489: step: 1968/530, loss: 0.007301711943000555
2023-01-21 11:16:09.412274: step: 1972/530, loss: 0.0244950782507658
2023-01-21 11:16:10.574407: step: 1976/530, loss: 0.05256430059671402
2023-01-21 11:16:11.699291: step: 1980/530, loss: 0.007440376561135054
2023-01-21 11:16:12.857867: step: 1984/530, loss: 0.05788583680987358
2023-01-21 11:16:13.978872: step: 1988/530, loss: 0.04040832445025444
2023-01-21 11:16:15.113131: step: 1992/530, loss: 0.013705158606171608
2023-01-21 11:16:16.222168: step: 1996/530, loss: 0.0027181627228856087
2023-01-21 11:16:17.371212: step: 2000/530, loss: 0.05286836624145508
2023-01-21 11:16:18.513362: step: 2004/530, loss: 0.08677192032337189
2023-01-21 11:16:19.655001: step: 2008/530, loss: 0.019402693957090378
2023-01-21 11:16:20.829828: step: 2012/530, loss: 0.009622668847441673
2023-01-21 11:16:21.954093: step: 2016/530, loss: 0.01846771314740181
2023-01-21 11:16:23.115095: step: 2020/530, loss: 0.018915940076112747
2023-01-21 11:16:24.211206: step: 2024/530, loss: 0.004593086428940296
2023-01-21 11:16:25.359005: step: 2028/530, loss: 0.034824881702661514
2023-01-21 11:16:26.498574: step: 2032/530, loss: 0.07127256691455841
2023-01-21 11:16:27.641055: step: 2036/530, loss: 0.00504226703196764
2023-01-21 11:16:28.770167: step: 2040/530, loss: 0.017795467749238014
2023-01-21 11:16:29.948265: step: 2044/530, loss: 0.05929870903491974
2023-01-21 11:16:31.085894: step: 2048/530, loss: 0.029300592839717865
2023-01-21 11:16:32.226964: step: 2052/530, loss: 0.048245858401060104
2023-01-21 11:16:33.354898: step: 2056/530, loss: 0.024977970868349075
2023-01-21 11:16:34.470854: step: 2060/530, loss: 0.014585781842470169
2023-01-21 11:16:35.627865: step: 2064/530, loss: 0.003798580262809992
2023-01-21 11:16:36.731179: step: 2068/530, loss: 0.08062377572059631
2023-01-21 11:16:37.871301: step: 2072/530, loss: 0.11755017936229706
2023-01-21 11:16:39.041652: step: 2076/530, loss: 0.03792534023523331
2023-01-21 11:16:40.222116: step: 2080/530, loss: 0.008829927071928978
2023-01-21 11:16:41.371035: step: 2084/530, loss: 0.04152316972613335
2023-01-21 11:16:42.565171: step: 2088/530, loss: 0.004197502043098211
2023-01-21 11:16:43.723645: step: 2092/530, loss: 0.01802806928753853
2023-01-21 11:16:44.869973: step: 2096/530, loss: 0.02399163320660591
2023-01-21 11:16:45.990437: step: 2100/530, loss: 0.00042316914186812937
2023-01-21 11:16:47.122605: step: 2104/530, loss: 0.0051198964938521385
2023-01-21 11:16:48.255037: step: 2108/530, loss: 0.008419417776167393
2023-01-21 11:16:49.394194: step: 2112/530, loss: 0.008710384368896484
2023-01-21 11:16:50.515376: step: 2116/530, loss: 0.002822971437126398
2023-01-21 11:16:51.641765: step: 2120/530, loss: 0.0706886276602745
==================================================
Loss: 0.042
--------------------
Dev: {'event': {'p': 0.5909090909090909, 'r': 0.7789613848202397, 'f1': 0.6720275703618609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6181980374665478, 'r': 0.792, 'f1': 0.6943887775551102}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5617977528089888, 'r': 0.9259259259259259, 'f1': 0.6993006993006993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.5901639344262295, 'r': 0.5714285714285714, 'f1': 0.5806451612903226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
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': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:17:33.889286: step: 4/530, loss: 0.06301908940076828
2023-01-21 11:17:35.007433: step: 8/530, loss: 0.02876119688153267
2023-01-21 11:17:36.127714: step: 12/530, loss: 0.015044212341308594
2023-01-21 11:17:37.248452: step: 16/530, loss: 0.002354526426643133
2023-01-21 11:17:38.395918: step: 20/530, loss: 0.03818511962890625
2023-01-21 11:17:39.547655: step: 24/530, loss: 0.0059782033786177635
2023-01-21 11:17:40.677539: step: 28/530, loss: 0.06077738106250763
2023-01-21 11:17:41.813843: step: 32/530, loss: 0.005969667807221413
2023-01-21 11:17:42.951163: step: 36/530, loss: 0.002396011259406805
2023-01-21 11:17:44.075902: step: 40/530, loss: 0.000508483499288559
2023-01-21 11:17:45.235420: step: 44/530, loss: 0.02786741405725479
2023-01-21 11:17:46.357878: step: 48/530, loss: 0.008535710163414478
2023-01-21 11:17:47.497677: step: 52/530, loss: 0.04281940311193466
2023-01-21 11:17:48.617519: step: 56/530, loss: 0.015337658114731312
2023-01-21 11:17:49.788936: step: 60/530, loss: 0.004324722103774548
2023-01-21 11:17:50.963311: step: 64/530, loss: 0.0053123473189771175
2023-01-21 11:17:52.108890: step: 68/530, loss: 0.006029605865478516
2023-01-21 11:17:53.255560: step: 72/530, loss: 0.02556157112121582
2023-01-21 11:17:54.411303: step: 76/530, loss: 0.008643055334687233
2023-01-21 11:17:55.554282: step: 80/530, loss: 0.00536537216976285
2023-01-21 11:17:56.702220: step: 84/530, loss: 0.00017042159743141383
2023-01-21 11:17:57.863348: step: 88/530, loss: 0.004296398255974054
2023-01-21 11:17:58.999160: step: 92/530, loss: 0.015748023986816406
2023-01-21 11:18:00.159700: step: 96/530, loss: 0.017750263214111328
2023-01-21 11:18:01.290565: step: 100/530, loss: 0.010699748992919922
2023-01-21 11:18:02.447679: step: 104/530, loss: 0.7596079111099243
2023-01-21 11:18:03.576505: step: 108/530, loss: 0.007402515504509211
2023-01-21 11:18:04.709068: step: 112/530, loss: 0.04561633989214897
2023-01-21 11:18:05.845108: step: 116/530, loss: 0.03657369315624237
2023-01-21 11:18:06.980279: step: 120/530, loss: 0.015366936102509499
2023-01-21 11:18:08.117039: step: 124/530, loss: 0.0004837036249227822
2023-01-21 11:18:09.257048: step: 128/530, loss: 0.0021389008034020662
2023-01-21 11:18:10.411055: step: 132/530, loss: 0.0013599395751953125
2023-01-21 11:18:11.566655: step: 136/530, loss: 0.006531191058456898
2023-01-21 11:18:12.681753: step: 140/530, loss: 0.039427757263183594
2023-01-21 11:18:13.821723: step: 144/530, loss: 0.010342788882553577
2023-01-21 11:18:14.974468: step: 148/530, loss: 0.001985931536182761
2023-01-21 11:18:16.086701: step: 152/530, loss: 0.07353687286376953
2023-01-21 11:18:17.242099: step: 156/530, loss: 0.00117664341814816
2023-01-21 11:18:18.391655: step: 160/530, loss: 0.0002525329473428428
2023-01-21 11:18:19.525851: step: 164/530, loss: 0.09442013502120972
2023-01-21 11:18:20.641915: step: 168/530, loss: 0.27707234025001526
2023-01-21 11:18:21.774370: step: 172/530, loss: 0.0026547431480139494
2023-01-21 11:18:22.872976: step: 176/530, loss: 0.0006613731384277344
2023-01-21 11:18:23.999336: step: 180/530, loss: 0.010602761059999466
2023-01-21 11:18:25.138393: step: 184/530, loss: 0.00397338904440403
2023-01-21 11:18:26.275707: step: 188/530, loss: 0.007596493232995272
2023-01-21 11:18:27.395484: step: 192/530, loss: 0.004687977023422718
2023-01-21 11:18:28.553268: step: 196/530, loss: 0.04013033211231232
2023-01-21 11:18:29.694705: step: 200/530, loss: 0.04576144367456436
2023-01-21 11:18:30.809898: step: 204/530, loss: 0.0008302688365802169
2023-01-21 11:18:31.970422: step: 208/530, loss: 0.0037252428010106087
2023-01-21 11:18:33.132134: step: 212/530, loss: 0.01154251117259264
2023-01-21 11:18:34.259680: step: 216/530, loss: 0.05089616775512695
2023-01-21 11:18:35.418178: step: 220/530, loss: 0.001321649644523859
2023-01-21 11:18:36.562987: step: 224/530, loss: 0.038405418395996094
2023-01-21 11:18:37.688273: step: 228/530, loss: 0.0046478272415697575
2023-01-21 11:18:38.817754: step: 232/530, loss: 0.9784982800483704
2023-01-21 11:18:39.945613: step: 236/530, loss: 0.01976604573428631
2023-01-21 11:18:41.092505: step: 240/530, loss: 0.0001201629638671875
2023-01-21 11:18:42.241272: step: 244/530, loss: 0.021088028326630592
2023-01-21 11:18:43.383330: step: 248/530, loss: 0.02731933817267418
2023-01-21 11:18:44.541550: step: 252/530, loss: 0.0005513190990313888
2023-01-21 11:18:45.678571: step: 256/530, loss: 0.10139027237892151
2023-01-21 11:18:46.823611: step: 260/530, loss: 0.00933084450662136
2023-01-21 11:18:47.976599: step: 264/530, loss: 0.02404460869729519
2023-01-21 11:18:49.145075: step: 268/530, loss: 0.0029658316634595394
2023-01-21 11:18:50.275720: step: 272/530, loss: 0.05531797558069229
2023-01-21 11:18:51.410652: step: 276/530, loss: 0.01288375910371542
2023-01-21 11:18:52.552995: step: 280/530, loss: 0.0010653972858563066
2023-01-21 11:18:53.673616: step: 284/530, loss: 0.0038002014625817537
2023-01-21 11:18:54.822744: step: 288/530, loss: 0.025200653821229935
2023-01-21 11:18:55.994770: step: 292/530, loss: 0.01848907582461834
2023-01-21 11:18:57.124436: step: 296/530, loss: 0.0005010605091229081
2023-01-21 11:18:58.274448: step: 300/530, loss: 0.0005220413440838456
2023-01-21 11:18:59.429195: step: 304/530, loss: 0.026517678052186966
2023-01-21 11:19:00.589741: step: 308/530, loss: 0.08356904983520508
2023-01-21 11:19:01.736629: step: 312/530, loss: 0.009510469622910023
2023-01-21 11:19:02.882352: step: 316/530, loss: 0.0733041763305664
2023-01-21 11:19:04.035938: step: 320/530, loss: 0.0075698853470385075
2023-01-21 11:19:05.192400: step: 324/530, loss: 0.0228818878531456
2023-01-21 11:19:06.324998: step: 328/530, loss: 0.13211460411548615
2023-01-21 11:19:07.445756: step: 332/530, loss: 0.021465588361024857
2023-01-21 11:19:08.612279: step: 336/530, loss: 0.01985016092658043
2023-01-21 11:19:09.760193: step: 340/530, loss: 0.06771975010633469
2023-01-21 11:19:10.937947: step: 344/530, loss: 0.008022308349609375
2023-01-21 11:19:12.095221: step: 348/530, loss: 0.03173542022705078
2023-01-21 11:19:13.234256: step: 352/530, loss: 0.025593949481844902
2023-01-21 11:19:14.386913: step: 356/530, loss: 0.011091423220932484
2023-01-21 11:19:15.532210: step: 360/530, loss: 0.012034225277602673
2023-01-21 11:19:16.662988: step: 364/530, loss: 0.02886953391134739
2023-01-21 11:19:17.805071: step: 368/530, loss: 0.04371687024831772
2023-01-21 11:19:18.916820: step: 372/530, loss: 0.00019750595674850047
2023-01-21 11:19:20.025502: step: 376/530, loss: 0.009295654483139515
2023-01-21 11:19:21.172392: step: 380/530, loss: 0.08063545823097229
2023-01-21 11:19:22.296132: step: 384/530, loss: 0.03663082420825958
2023-01-21 11:19:23.440758: step: 388/530, loss: 0.0015880585415288806
2023-01-21 11:19:24.594608: step: 392/530, loss: 0.02606317773461342
2023-01-21 11:19:25.742424: step: 396/530, loss: 0.001323699951171875
2023-01-21 11:19:26.870703: step: 400/530, loss: 0.07313556224107742
2023-01-21 11:19:28.003669: step: 404/530, loss: 0.026813890784978867
2023-01-21 11:19:29.139370: step: 408/530, loss: 0.0016522407531738281
2023-01-21 11:19:30.319747: step: 412/530, loss: 0.05738115310668945
2023-01-21 11:19:31.455339: step: 416/530, loss: 9.117126319324598e-05
2023-01-21 11:19:32.604221: step: 420/530, loss: 0.010639572516083717
2023-01-21 11:19:33.738651: step: 424/530, loss: 0.03826894611120224
2023-01-21 11:19:34.875537: step: 428/530, loss: 0.009136009961366653
2023-01-21 11:19:35.984645: step: 432/530, loss: 0.009017085656523705
2023-01-21 11:19:37.144074: step: 436/530, loss: 0.07303555309772491
2023-01-21 11:19:38.284725: step: 440/530, loss: 0.0015249490970745683
2023-01-21 11:19:39.411985: step: 444/530, loss: 0.0029181481804698706
2023-01-21 11:19:40.554284: step: 448/530, loss: 0.0001624107244424522
2023-01-21 11:19:41.692676: step: 452/530, loss: 0.006937885191291571
2023-01-21 11:19:42.807628: step: 456/530, loss: 0.0015713691245764494
2023-01-21 11:19:43.918047: step: 460/530, loss: 0.005838585086166859
2023-01-21 11:19:45.065315: step: 464/530, loss: 0.035994816571474075
2023-01-21 11:19:46.192032: step: 468/530, loss: 0.04271211847662926
2023-01-21 11:19:47.343760: step: 472/530, loss: 2.956390380859375e-05
2023-01-21 11:19:48.597419: step: 476/530, loss: 0.013714408501982689
2023-01-21 11:19:49.747543: step: 480/530, loss: 0.00209980015642941
2023-01-21 11:19:50.904061: step: 484/530, loss: 0.05198374018073082
2023-01-21 11:19:52.087351: step: 488/530, loss: 0.03801736608147621
2023-01-21 11:19:53.207784: step: 492/530, loss: 0.00574836740270257
2023-01-21 11:19:54.325360: step: 496/530, loss: 0.0014463425613939762
2023-01-21 11:19:55.451347: step: 500/530, loss: 0.002930927090346813
2023-01-21 11:19:56.635339: step: 504/530, loss: 0.00855398178100586
2023-01-21 11:19:57.751824: step: 508/530, loss: 0.05135517194867134
2023-01-21 11:19:58.884793: step: 512/530, loss: 0.002239322755485773
2023-01-21 11:20:00.033171: step: 516/530, loss: 0.008370209485292435
2023-01-21 11:20:01.190189: step: 520/530, loss: 0.07912015914916992
2023-01-21 11:20:02.365262: step: 524/530, loss: 0.051090337336063385
2023-01-21 11:20:03.505530: step: 528/530, loss: 0.013118267059326172
2023-01-21 11:20:04.642646: step: 532/530, loss: 0.022995568811893463
2023-01-21 11:20:05.771309: step: 536/530, loss: 0.0009084702469408512
2023-01-21 11:20:06.897749: step: 540/530, loss: 0.02875232696533203
2023-01-21 11:20:08.050569: step: 544/530, loss: 0.002215576358139515
2023-01-21 11:20:09.168509: step: 548/530, loss: 0.044439125806093216
2023-01-21 11:20:10.305639: step: 552/530, loss: 0.027898024767637253
2023-01-21 11:20:11.449710: step: 556/530, loss: 0.0005229950184002519
2023-01-21 11:20:12.603327: step: 560/530, loss: 0.024617576971650124
2023-01-21 11:20:13.748466: step: 564/530, loss: 0.013333892449736595
2023-01-21 11:20:14.869020: step: 568/530, loss: 0.026875782757997513
2023-01-21 11:20:16.010106: step: 572/530, loss: 0.011289024725556374
2023-01-21 11:20:17.149560: step: 576/530, loss: 0.03284483402967453
2023-01-21 11:20:18.275844: step: 580/530, loss: 0.0021974563132971525
2023-01-21 11:20:19.399522: step: 584/530, loss: 0.06609725952148438
2023-01-21 11:20:20.536264: step: 588/530, loss: 0.01821298711001873
2023-01-21 11:20:21.679266: step: 592/530, loss: 1.0563435554504395
2023-01-21 11:20:22.834730: step: 596/530, loss: 0.012204552069306374
2023-01-21 11:20:23.978159: step: 600/530, loss: 0.025958824902772903
2023-01-21 11:20:25.123996: step: 604/530, loss: 0.02353687211871147
2023-01-21 11:20:26.253056: step: 608/530, loss: 0.004166364669799805
2023-01-21 11:20:27.397280: step: 612/530, loss: 0.01948533020913601
2023-01-21 11:20:28.526427: step: 616/530, loss: 0.01134634017944336
2023-01-21 11:20:29.659667: step: 620/530, loss: 0.009821987710893154
2023-01-21 11:20:30.802324: step: 624/530, loss: 0.07768841087818146
2023-01-21 11:20:31.894155: step: 628/530, loss: 0.018469810485839844
2023-01-21 11:20:33.038761: step: 632/530, loss: 0.00554690370336175
2023-01-21 11:20:34.217878: step: 636/530, loss: 0.006787681952118874
2023-01-21 11:20:35.370269: step: 640/530, loss: 0.004995155148208141
2023-01-21 11:20:36.543654: step: 644/530, loss: -9.5367431640625e-07
2023-01-21 11:20:37.654880: step: 648/530, loss: 0.02008981630206108
2023-01-21 11:20:38.825561: step: 652/530, loss: 0.0032486915588378906
2023-01-21 11:20:39.957959: step: 656/530, loss: 0.019436310976743698
2023-01-21 11:20:41.061616: step: 660/530, loss: 0.0022603035904467106
2023-01-21 11:20:42.226398: step: 664/530, loss: 0.0014338493347167969
2023-01-21 11:20:43.374951: step: 668/530, loss: 0.022200871258974075
2023-01-21 11:20:44.500130: step: 672/530, loss: 0.003977012820541859
2023-01-21 11:20:45.628774: step: 676/530, loss: 0.0037576674949377775
2023-01-21 11:20:46.757707: step: 680/530, loss: 0.0034274100326001644
2023-01-21 11:20:47.882948: step: 684/530, loss: 0.001448345254175365
2023-01-21 11:20:49.016269: step: 688/530, loss: 0.657168984413147
2023-01-21 11:20:50.163494: step: 692/530, loss: 0.06804457306861877
2023-01-21 11:20:51.284675: step: 696/530, loss: 0.02938881143927574
2023-01-21 11:20:52.405416: step: 700/530, loss: 0.00861902255564928
2023-01-21 11:20:53.554098: step: 704/530, loss: 0.039499662816524506
2023-01-21 11:20:54.686996: step: 708/530, loss: 0.0007273674127645791
2023-01-21 11:20:55.835975: step: 712/530, loss: 0.0016185521380975842
2023-01-21 11:20:56.943924: step: 716/530, loss: 0.00935277994722128
2023-01-21 11:20:58.064361: step: 720/530, loss: 0.15545310080051422
2023-01-21 11:20:59.168791: step: 724/530, loss: 2.7418136596679688e-05
2023-01-21 11:21:00.273020: step: 728/530, loss: 0.2362150251865387
2023-01-21 11:21:01.399600: step: 732/530, loss: 0.07468290627002716
2023-01-21 11:21:02.563293: step: 736/530, loss: 0.005737781524658203
2023-01-21 11:21:03.684898: step: 740/530, loss: 0.051972582936286926
2023-01-21 11:21:04.825851: step: 744/530, loss: 0.0015926361083984375
2023-01-21 11:21:05.953615: step: 748/530, loss: 0.03697628900408745
2023-01-21 11:21:07.118881: step: 752/530, loss: 0.0014581680297851562
2023-01-21 11:21:08.234088: step: 756/530, loss: 0.014050101861357689
2023-01-21 11:21:09.387598: step: 760/530, loss: 0.0018521309830248356
2023-01-21 11:21:10.551882: step: 764/530, loss: 0.5094509720802307
2023-01-21 11:21:11.688521: step: 768/530, loss: 0.021326638758182526
2023-01-21 11:21:12.829281: step: 772/530, loss: 0.0595640167593956
2023-01-21 11:21:13.953506: step: 776/530, loss: 0.008613968268036842
2023-01-21 11:21:15.056964: step: 780/530, loss: 0.008191651664674282
2023-01-21 11:21:16.160136: step: 784/530, loss: 0.012143135070800781
2023-01-21 11:21:17.271168: step: 788/530, loss: 0.0003234863397665322
2023-01-21 11:21:18.409713: step: 792/530, loss: 0.016315460205078125
2023-01-21 11:21:19.552721: step: 796/530, loss: 0.004610276315361261
2023-01-21 11:21:20.702107: step: 800/530, loss: 0.6781415939331055
2023-01-21 11:21:21.828912: step: 804/530, loss: 0.01867532730102539
2023-01-21 11:21:22.994624: step: 808/530, loss: 0.00023565591254737228
2023-01-21 11:21:24.123726: step: 812/530, loss: 0.03674297407269478
2023-01-21 11:21:25.229285: step: 816/530, loss: 0.026883315294981003
2023-01-21 11:21:26.338652: step: 820/530, loss: 0.04646725580096245
2023-01-21 11:21:27.479065: step: 824/530, loss: 0.25731638073921204
2023-01-21 11:21:28.601902: step: 828/530, loss: 0.00021610260591842234
2023-01-21 11:21:29.778858: step: 832/530, loss: 0.025727082043886185
2023-01-21 11:21:30.955716: step: 836/530, loss: 0.0569889098405838
2023-01-21 11:21:32.107940: step: 840/530, loss: 0.00020866392878815532
2023-01-21 11:21:33.247556: step: 844/530, loss: 0.002565765520557761
2023-01-21 11:21:34.375874: step: 848/530, loss: 0.01056518591940403
2023-01-21 11:21:35.518520: step: 852/530, loss: 0.03997664526104927
2023-01-21 11:21:36.650838: step: 856/530, loss: 0.007743263617157936
2023-01-21 11:21:37.778472: step: 860/530, loss: 4.4488908315543085e-05
2023-01-21 11:21:38.885182: step: 864/530, loss: 0.0046096802689135075
2023-01-21 11:21:40.019899: step: 868/530, loss: 0.014674091711640358
2023-01-21 11:21:41.179443: step: 872/530, loss: 0.018805695697665215
2023-01-21 11:21:42.302519: step: 876/530, loss: 0.0006470441585406661
2023-01-21 11:21:43.422412: step: 880/530, loss: 0.013023472391068935
2023-01-21 11:21:44.573507: step: 884/530, loss: 0.005887794308364391
2023-01-21 11:21:45.737211: step: 888/530, loss: 0.030852604657411575
2023-01-21 11:21:46.870573: step: 892/530, loss: 0.008310317993164062
2023-01-21 11:21:47.987319: step: 896/530, loss: 0.007686138153076172
2023-01-21 11:21:49.144277: step: 900/530, loss: 0.032025717198848724
2023-01-21 11:21:50.294983: step: 904/530, loss: 0.13664494454860687
2023-01-21 11:21:51.449761: step: 908/530, loss: 0.13686561584472656
2023-01-21 11:21:52.609830: step: 912/530, loss: 0.045676231384277344
2023-01-21 11:21:53.745037: step: 916/530, loss: 0.02201395109295845
2023-01-21 11:21:54.911482: step: 920/530, loss: 0.004035472869873047
2023-01-21 11:21:56.078072: step: 924/530, loss: 0.0007376670837402344
2023-01-21 11:21:57.232475: step: 928/530, loss: 0.018345260992646217
2023-01-21 11:21:58.361674: step: 932/530, loss: 0.00278892507776618
2023-01-21 11:21:59.507570: step: 936/530, loss: 0.05030975118279457
2023-01-21 11:22:00.630982: step: 940/530, loss: 0.004177522845566273
2023-01-21 11:22:01.784144: step: 944/530, loss: 0.02850179746747017
2023-01-21 11:22:02.925763: step: 948/530, loss: 0.007239770609885454
2023-01-21 11:22:04.059400: step: 952/530, loss: 0.011342811398208141
2023-01-21 11:22:05.232821: step: 956/530, loss: 0.016461849212646484
2023-01-21 11:22:06.369022: step: 960/530, loss: 0.018616534769535065
2023-01-21 11:22:07.538185: step: 964/530, loss: 0.0012501716846600175
2023-01-21 11:22:08.658083: step: 968/530, loss: 0.01305084303021431
2023-01-21 11:22:09.791131: step: 972/530, loss: 0.005561256781220436
2023-01-21 11:22:10.917457: step: 976/530, loss: 0.13052532076835632
2023-01-21 11:22:12.060752: step: 980/530, loss: 0.00989465694874525
2023-01-21 11:22:13.199452: step: 984/530, loss: 0.014339066110551357
2023-01-21 11:22:14.325812: step: 988/530, loss: 6.732940528308973e-05
2023-01-21 11:22:15.477289: step: 992/530, loss: 0.006600475404411554
2023-01-21 11:22:16.640074: step: 996/530, loss: 0.021700739860534668
2023-01-21 11:22:17.771902: step: 1000/530, loss: 0.026310348883271217
2023-01-21 11:22:18.920296: step: 1004/530, loss: 0.020311737433075905
2023-01-21 11:22:20.059784: step: 1008/530, loss: 0.08196954429149628
2023-01-21 11:22:21.173679: step: 1012/530, loss: 0.0003003597375936806
2023-01-21 11:22:22.288166: step: 1016/530, loss: 0.0028558254707604647
2023-01-21 11:22:23.420563: step: 1020/530, loss: 0.0011283399071544409
2023-01-21 11:22:24.544123: step: 1024/530, loss: 0.024431325495243073
2023-01-21 11:22:25.664931: step: 1028/530, loss: 0.026449013501405716
2023-01-21 11:22:26.807822: step: 1032/530, loss: 0.017591094598174095
2023-01-21 11:22:27.982203: step: 1036/530, loss: 0.0007052421569824219
2023-01-21 11:22:29.128643: step: 1040/530, loss: 0.02456970326602459
2023-01-21 11:22:30.274861: step: 1044/530, loss: 0.03580150380730629
2023-01-21 11:22:31.417041: step: 1048/530, loss: 0.011391258798539639
2023-01-21 11:22:32.596163: step: 1052/530, loss: 0.01680774800479412
2023-01-21 11:22:33.710859: step: 1056/530, loss: 0.02341938018798828
2023-01-21 11:22:34.838279: step: 1060/530, loss: 0.010100937448441982
2023-01-21 11:22:35.995018: step: 1064/530, loss: 0.006063365843147039
2023-01-21 11:22:37.130619: step: 1068/530, loss: 0.010940885171294212
2023-01-21 11:22:38.294946: step: 1072/530, loss: 0.42117881774902344
2023-01-21 11:22:39.439745: step: 1076/530, loss: 0.0270646084100008
2023-01-21 11:22:40.580164: step: 1080/530, loss: 0.06631851196289062
2023-01-21 11:22:41.726283: step: 1084/530, loss: 0.0265746358782053
2023-01-21 11:22:42.854820: step: 1088/530, loss: 0.02209014818072319
2023-01-21 11:22:44.025650: step: 1092/530, loss: 0.04482688754796982
2023-01-21 11:22:45.149489: step: 1096/530, loss: 0.03228512033820152
2023-01-21 11:22:46.311441: step: 1100/530, loss: 0.000110626220703125
2023-01-21 11:22:47.410700: step: 1104/530, loss: 0.0808483138680458
2023-01-21 11:22:48.556431: step: 1108/530, loss: 0.10856809467077255
2023-01-21 11:22:49.703539: step: 1112/530, loss: 0.002850818447768688
2023-01-21 11:22:50.847042: step: 1116/530, loss: 0.01867103762924671
2023-01-21 11:22:52.038358: step: 1120/530, loss: 0.003425789065659046
2023-01-21 11:22:53.210078: step: 1124/530, loss: 0.01171493623405695
2023-01-21 11:22:54.316251: step: 1128/530, loss: 0.00037660598172806203
2023-01-21 11:22:55.478218: step: 1132/530, loss: 0.0634550154209137
2023-01-21 11:22:56.627814: step: 1136/530, loss: 0.008655071258544922
2023-01-21 11:22:57.775379: step: 1140/530, loss: 0.0020933151245117188
2023-01-21 11:22:58.920534: step: 1144/530, loss: 0.02985682524740696
2023-01-21 11:23:00.076312: step: 1148/530, loss: 0.012695884332060814
2023-01-21 11:23:01.251146: step: 1152/530, loss: 0.024936510249972343
2023-01-21 11:23:02.426648: step: 1156/530, loss: 0.030585383996367455
2023-01-21 11:23:03.598012: step: 1160/530, loss: 0.009078312665224075
2023-01-21 11:23:04.733904: step: 1164/530, loss: 0.008010960184037685
2023-01-21 11:23:05.847470: step: 1168/530, loss: 0.0036783218383789062
2023-01-21 11:23:06.999434: step: 1172/530, loss: 0.02302856370806694
2023-01-21 11:23:08.162998: step: 1176/530, loss: 0.00702743511646986
2023-01-21 11:23:09.295612: step: 1180/530, loss: 0.0002359390346100554
2023-01-21 11:23:10.447027: step: 1184/530, loss: 3.166198803228326e-05
2023-01-21 11:23:11.596145: step: 1188/530, loss: 0.03865652158856392
2023-01-21 11:23:12.709513: step: 1192/530, loss: 0.006236553192138672
2023-01-21 11:23:13.833551: step: 1196/530, loss: 0.005015039350837469
2023-01-21 11:23:14.984586: step: 1200/530, loss: 0.00248374929651618
2023-01-21 11:23:16.131708: step: 1204/530, loss: 0.0006333351484499872
2023-01-21 11:23:17.305043: step: 1208/530, loss: 0.018186094239354134
2023-01-21 11:23:18.428652: step: 1212/530, loss: 0.024813033640384674
2023-01-21 11:23:19.578744: step: 1216/530, loss: 0.007860183715820312
2023-01-21 11:23:20.717049: step: 1220/530, loss: 0.011639213189482689
2023-01-21 11:23:21.901786: step: 1224/530, loss: 0.5874112844467163
2023-01-21 11:23:23.041268: step: 1228/530, loss: 0.00048131943913176656
2023-01-21 11:23:24.194120: step: 1232/530, loss: 0.002529907040297985
2023-01-21 11:23:25.337703: step: 1236/530, loss: 0.0005347415572032332
2023-01-21 11:23:26.433872: step: 1240/530, loss: 0.006069183349609375
2023-01-21 11:23:27.572600: step: 1244/530, loss: 0.0018108368385583162
2023-01-21 11:23:28.718900: step: 1248/530, loss: 0.01851367950439453
2023-01-21 11:23:29.860594: step: 1252/530, loss: 0.10787548869848251
2023-01-21 11:23:31.010536: step: 1256/530, loss: 0.039223670959472656
2023-01-21 11:23:32.154548: step: 1260/530, loss: 0.002181434538215399
2023-01-21 11:23:33.282361: step: 1264/530, loss: 0.0009279251098632812
2023-01-21 11:23:34.426233: step: 1268/530, loss: 0.40292245149612427
2023-01-21 11:23:35.560387: step: 1272/530, loss: 0.026256084442138672
2023-01-21 11:23:36.658845: step: 1276/530, loss: 9.15527380129788e-06
2023-01-21 11:23:37.817097: step: 1280/530, loss: 0.051944732666015625
2023-01-21 11:23:38.968299: step: 1284/530, loss: 0.0008594036335125566
2023-01-21 11:23:40.116828: step: 1288/530, loss: 0.07917194813489914
2023-01-21 11:23:41.253117: step: 1292/530, loss: 0.13904426991939545
2023-01-21 11:23:42.421116: step: 1296/530, loss: 0.09802704304456711
2023-01-21 11:23:43.575786: step: 1300/530, loss: 0.03351593017578125
2023-01-21 11:23:44.680773: step: 1304/530, loss: 0.04357731714844704
2023-01-21 11:23:45.805015: step: 1308/530, loss: 0.00451583880931139
2023-01-21 11:23:46.914665: step: 1312/530, loss: 0.0017642974853515625
2023-01-21 11:23:48.023244: step: 1316/530, loss: 0.09723100811243057
2023-01-21 11:23:49.181811: step: 1320/530, loss: 0.007618522737175226
2023-01-21 11:23:50.324107: step: 1324/530, loss: 0.040081217885017395
2023-01-21 11:23:51.499860: step: 1328/530, loss: 0.029881859198212624
2023-01-21 11:23:52.605683: step: 1332/530, loss: 0.03812370449304581
2023-01-21 11:23:53.763852: step: 1336/530, loss: 0.0563817024230957
2023-01-21 11:23:54.888597: step: 1340/530, loss: 0.04955501854419708
2023-01-21 11:23:56.034606: step: 1344/530, loss: 0.013701161369681358
2023-01-21 11:23:57.190326: step: 1348/530, loss: 0.02276611328125
2023-01-21 11:23:58.349506: step: 1352/530, loss: 0.0004288673517294228
2023-01-21 11:23:59.470711: step: 1356/530, loss: 0.015003586187958717
2023-01-21 11:24:00.590306: step: 1360/530, loss: 0.04562520980834961
2023-01-21 11:24:01.706187: step: 1364/530, loss: 0.018922997638583183
2023-01-21 11:24:02.873381: step: 1368/530, loss: 0.02266693115234375
2023-01-21 11:24:04.006429: step: 1372/530, loss: 0.005838871002197266
2023-01-21 11:24:05.138870: step: 1376/530, loss: 0.0029023527167737484
2023-01-21 11:24:06.291005: step: 1380/530, loss: 0.0149695398285985
2023-01-21 11:24:07.454292: step: 1384/530, loss: 0.004807853605598211
2023-01-21 11:24:08.588909: step: 1388/530, loss: 0.014610386453568935
2023-01-21 11:24:09.701198: step: 1392/530, loss: 0.00854024849832058
2023-01-21 11:24:10.819251: step: 1396/530, loss: 0.0006809234619140625
2023-01-21 11:24:11.944637: step: 1400/530, loss: 0.022415639832615852
2023-01-21 11:24:13.098746: step: 1404/530, loss: 0.029984187334775925
2023-01-21 11:24:14.231887: step: 1408/530, loss: 0.023117495700716972
2023-01-21 11:24:15.359059: step: 1412/530, loss: 0.06122494116425514
2023-01-21 11:24:16.512130: step: 1416/530, loss: 0.004453182220458984
2023-01-21 11:24:17.645570: step: 1420/530, loss: 0.05998754873871803
2023-01-21 11:24:18.807376: step: 1424/530, loss: 0.0006221771473065019
2023-01-21 11:24:19.923917: step: 1428/530, loss: 0.05530204996466637
2023-01-21 11:24:21.066079: step: 1432/530, loss: 0.00868377648293972
2023-01-21 11:24:22.181344: step: 1436/530, loss: 0.00870046578347683
2023-01-21 11:24:23.322762: step: 1440/530, loss: 0.017313959077000618
2023-01-21 11:24:24.451760: step: 1444/530, loss: 0.0027986527420580387
2023-01-21 11:24:25.628985: step: 1448/530, loss: 0.018596267327666283
2023-01-21 11:24:26.759495: step: 1452/530, loss: 0.0007522970554418862
2023-01-21 11:24:27.877254: step: 1456/530, loss: 0.0029664994217455387
2023-01-21 11:24:29.012080: step: 1460/530, loss: 0.008461189456284046
2023-01-21 11:24:30.111852: step: 1464/530, loss: 0.05176115408539772
2023-01-21 11:24:31.220503: step: 1468/530, loss: 0.00011796951002907008
2023-01-21 11:24:32.344703: step: 1472/530, loss: 0.038598060607910156
2023-01-21 11:24:33.463768: step: 1476/530, loss: 0.0007402420160360634
2023-01-21 11:24:34.633433: step: 1480/530, loss: 0.02830381505191326
2023-01-21 11:24:35.769915: step: 1484/530, loss: 0.0010368346702307463
2023-01-21 11:24:36.904512: step: 1488/530, loss: 0.022386837750673294
2023-01-21 11:24:38.070488: step: 1492/530, loss: 0.011796570383012295
2023-01-21 11:24:39.221384: step: 1496/530, loss: 0.0001773834228515625
2023-01-21 11:24:40.345206: step: 1500/530, loss: 0.00111217494122684
2023-01-21 11:24:41.479340: step: 1504/530, loss: 0.04430866241455078
2023-01-21 11:24:42.625837: step: 1508/530, loss: 0.03873375803232193
2023-01-21 11:24:43.769457: step: 1512/530, loss: 0.007622718811035156
2023-01-21 11:24:44.897784: step: 1516/530, loss: 0.02032499387860298
2023-01-21 11:24:46.034949: step: 1520/530, loss: 0.00884780939668417
2023-01-21 11:24:47.163457: step: 1524/530, loss: 0.0009005547035485506
2023-01-21 11:24:48.291444: step: 1528/530, loss: 0.096226267516613
2023-01-21 11:24:49.455138: step: 1532/530, loss: 0.05904083326458931
2023-01-21 11:24:50.636881: step: 1536/530, loss: 0.0036804198753088713
2023-01-21 11:24:51.782499: step: 1540/530, loss: 0.0644993782043457
2023-01-21 11:24:52.893240: step: 1544/530, loss: 0.007517147343605757
2023-01-21 11:24:54.041130: step: 1548/530, loss: 0.003606605576351285
2023-01-21 11:24:55.192134: step: 1552/530, loss: 0.0049468521028757095
2023-01-21 11:24:56.339449: step: 1556/530, loss: 0.013503646478056908
2023-01-21 11:24:57.478946: step: 1560/530, loss: 0.0015736579662188888
2023-01-21 11:24:58.636173: step: 1564/530, loss: 0.002293205354362726
2023-01-21 11:24:59.758025: step: 1568/530, loss: 0.0008790969732217491
2023-01-21 11:25:00.924386: step: 1572/530, loss: 7.43865966796875e-05
2023-01-21 11:25:02.094464: step: 1576/530, loss: 0.033884476870298386
2023-01-21 11:25:03.206430: step: 1580/530, loss: 0.15299153327941895
2023-01-21 11:25:04.339675: step: 1584/530, loss: 0.023784542456269264
2023-01-21 11:25:05.500155: step: 1588/530, loss: 0.01032323855906725
2023-01-21 11:25:06.620122: step: 1592/530, loss: 0.029903031885623932
2023-01-21 11:25:07.774162: step: 1596/530, loss: 0.0003773212374653667
2023-01-21 11:25:08.930927: step: 1600/530, loss: 0.12320718914270401
2023-01-21 11:25:10.067095: step: 1604/530, loss: 0.5541620254516602
2023-01-21 11:25:11.195218: step: 1608/530, loss: 0.0037043574266135693
2023-01-21 11:25:12.342707: step: 1612/530, loss: 0.025124119594693184
2023-01-21 11:25:13.470126: step: 1616/530, loss: 0.02287464216351509
2023-01-21 11:25:14.621152: step: 1620/530, loss: 0.08258037269115448
2023-01-21 11:25:15.748067: step: 1624/530, loss: 0.00163097376935184
2023-01-21 11:25:16.895510: step: 1628/530, loss: 0.00035452842712402344
2023-01-21 11:25:18.061070: step: 1632/530, loss: 0.003934239968657494
2023-01-21 11:25:19.239957: step: 1636/530, loss: 0.02038288302719593
2023-01-21 11:25:20.380567: step: 1640/530, loss: 0.013879776000976562
2023-01-21 11:25:21.503600: step: 1644/530, loss: 0.09607429802417755
2023-01-21 11:25:22.695753: step: 1648/530, loss: 0.06835365295410156
2023-01-21 11:25:23.847476: step: 1652/530, loss: 0.01781644858419895
2023-01-21 11:25:25.016698: step: 1656/530, loss: 0.01643829420208931
2023-01-21 11:25:26.175036: step: 1660/530, loss: 0.006119156256318092
2023-01-21 11:25:27.321120: step: 1664/530, loss: 0.10356283187866211
2023-01-21 11:25:28.463403: step: 1668/530, loss: 0.05298471450805664
2023-01-21 11:25:29.611656: step: 1672/530, loss: 6.427765038097277e-05
2023-01-21 11:25:30.724841: step: 1676/530, loss: 0.01542515680193901
2023-01-21 11:25:31.863886: step: 1680/530, loss: 0.024073602631688118
2023-01-21 11:25:32.986731: step: 1684/530, loss: 0.02604503743350506
2023-01-21 11:25:34.147627: step: 1688/530, loss: 0.03920355066657066
2023-01-21 11:25:35.263831: step: 1692/530, loss: 0.007467078976333141
2023-01-21 11:25:36.382255: step: 1696/530, loss: 0.013394070789217949
2023-01-21 11:25:37.545864: step: 1700/530, loss: 0.012524223886430264
2023-01-21 11:25:38.692858: step: 1704/530, loss: 0.003688239958137274
2023-01-21 11:25:39.836332: step: 1708/530, loss: 0.01958923414349556
2023-01-21 11:25:40.975267: step: 1712/530, loss: 0.013335037976503372
2023-01-21 11:25:42.110113: step: 1716/530, loss: 0.02902812883257866
2023-01-21 11:25:43.266428: step: 1720/530, loss: 0.113642118871212
2023-01-21 11:25:44.407544: step: 1724/530, loss: 0.04945125803351402
2023-01-21 11:25:45.503884: step: 1728/530, loss: 0.011638784781098366
2023-01-21 11:25:46.657911: step: 1732/530, loss: 0.03705959394574165
2023-01-21 11:25:47.804433: step: 1736/530, loss: 0.022434331476688385
2023-01-21 11:25:48.929744: step: 1740/530, loss: 0.022758103907108307
2023-01-21 11:25:50.036242: step: 1744/530, loss: 0.009679795242846012
2023-01-21 11:25:51.150217: step: 1748/530, loss: 0.005592561326920986
2023-01-21 11:25:52.293058: step: 1752/530, loss: 0.0015164853539317846
2023-01-21 11:25:53.435533: step: 1756/530, loss: 0.05279827117919922
2023-01-21 11:25:54.590544: step: 1760/530, loss: 0.0008146286127157509
2023-01-21 11:25:55.795287: step: 1764/530, loss: 5.292892819852568e-05
2023-01-21 11:25:56.934217: step: 1768/530, loss: 0.00389175396412611
2023-01-21 11:25:58.097046: step: 1772/530, loss: 0.004557990934699774
2023-01-21 11:25:59.262906: step: 1776/530, loss: 0.03280467912554741
2023-01-21 11:26:00.413894: step: 1780/530, loss: 0.043671224266290665
2023-01-21 11:26:01.558897: step: 1784/530, loss: 0.00019655228243209422
2023-01-21 11:26:02.714918: step: 1788/530, loss: 0.003915214445441961
2023-01-21 11:26:03.855654: step: 1792/530, loss: 0.003193473909050226
2023-01-21 11:26:05.022069: step: 1796/530, loss: 0.01273260172456503
2023-01-21 11:26:06.160737: step: 1800/530, loss: 5.645752025884576e-05
2023-01-21 11:26:07.284288: step: 1804/530, loss: 0.005122947972267866
2023-01-21 11:26:08.394042: step: 1808/530, loss: 0.030591202899813652
2023-01-21 11:26:09.517745: step: 1812/530, loss: 0.014458179473876953
2023-01-21 11:26:10.653348: step: 1816/530, loss: 0.00010585784912109375
2023-01-21 11:26:11.807691: step: 1820/530, loss: 0.00512008648365736
2023-01-21 11:26:12.965366: step: 1824/530, loss: 0.005435371771454811
2023-01-21 11:26:14.092027: step: 1828/530, loss: 0.003403520444408059
2023-01-21 11:26:15.260178: step: 1832/530, loss: 0.014070987701416016
2023-01-21 11:26:16.406133: step: 1836/530, loss: 0.024495316669344902
2023-01-21 11:26:17.551621: step: 1840/530, loss: 0.019470976665616035
2023-01-21 11:26:18.700744: step: 1844/530, loss: 0.022258473560214043
2023-01-21 11:26:19.841253: step: 1848/530, loss: 0.060204315930604935
2023-01-21 11:26:20.997152: step: 1852/530, loss: 0.020189572125673294
2023-01-21 11:26:22.153186: step: 1856/530, loss: 0.0062272134236991405
2023-01-21 11:26:23.276558: step: 1860/530, loss: 0.006847381591796875
2023-01-21 11:26:24.413349: step: 1864/530, loss: 0.02475299872457981
2023-01-21 11:26:25.571550: step: 1868/530, loss: 0.024157142266631126
2023-01-21 11:26:26.738180: step: 1872/530, loss: 0.0008168220520019531
2023-01-21 11:26:27.892561: step: 1876/530, loss: 0.0006221771473065019
2023-01-21 11:26:29.034718: step: 1880/530, loss: 0.02816629409790039
2023-01-21 11:26:30.161778: step: 1884/530, loss: 0.024259090423583984
2023-01-21 11:26:31.304879: step: 1888/530, loss: 0.0005876540672034025
2023-01-21 11:26:32.447024: step: 1892/530, loss: 0.0029769898392260075
2023-01-21 11:26:33.603647: step: 1896/530, loss: 0.006971264258027077
2023-01-21 11:26:34.754968: step: 1900/530, loss: 0.0040115355513989925
2023-01-21 11:26:35.886462: step: 1904/530, loss: 0.004012393765151501
2023-01-21 11:26:37.011889: step: 1908/530, loss: 0.06063403934240341
2023-01-21 11:26:38.170355: step: 1912/530, loss: 0.004015493206679821
2023-01-21 11:26:39.307022: step: 1916/530, loss: 0.06390835344791412
2023-01-21 11:26:40.476717: step: 1920/530, loss: 0.03961925581097603
2023-01-21 11:26:41.608736: step: 1924/530, loss: 0.00011520386033225805
2023-01-21 11:26:42.748642: step: 1928/530, loss: 0.006448650732636452
2023-01-21 11:26:43.847097: step: 1932/530, loss: 0.010734128765761852
2023-01-21 11:26:45.008845: step: 1936/530, loss: 3.852844383800402e-05
2023-01-21 11:26:46.170691: step: 1940/530, loss: 0.02266845665872097
2023-01-21 11:26:47.327993: step: 1944/530, loss: 0.029458142817020416
2023-01-21 11:26:48.478032: step: 1948/530, loss: 0.046312905848026276
2023-01-21 11:26:49.617125: step: 1952/530, loss: 0.016111183911561966
2023-01-21 11:26:50.728382: step: 1956/530, loss: 0.027915572747588158
2023-01-21 11:26:51.867028: step: 1960/530, loss: 0.03202624246478081
2023-01-21 11:26:53.037813: step: 1964/530, loss: 0.037285804748535156
2023-01-21 11:26:54.190476: step: 1968/530, loss: 0.022404098883271217
2023-01-21 11:26:55.345637: step: 1972/530, loss: 0.024330127984285355
2023-01-21 11:26:56.526088: step: 1976/530, loss: 0.045806884765625
2023-01-21 11:26:57.642680: step: 1980/530, loss: 0.055925749242305756
2023-01-21 11:26:58.769414: step: 1984/530, loss: 0.0024288177955895662
2023-01-21 11:26:59.904272: step: 1988/530, loss: 0.02773284912109375
2023-01-21 11:27:01.047061: step: 1992/530, loss: 0.12617407739162445
2023-01-21 11:27:02.188835: step: 1996/530, loss: 0.0001798153098206967
2023-01-21 11:27:03.337113: step: 2000/530, loss: 0.022842025384306908
2023-01-21 11:27:04.494185: step: 2004/530, loss: 0.0009710312006063759
2023-01-21 11:27:05.628135: step: 2008/530, loss: 0.016420984640717506
2023-01-21 11:27:06.778229: step: 2012/530, loss: 0.011293316259980202
2023-01-21 11:27:07.911221: step: 2016/530, loss: 0.02388370968401432
2023-01-21 11:27:09.043486: step: 2020/530, loss: 0.05840883404016495
2023-01-21 11:27:10.201027: step: 2024/530, loss: 0.017496870830655098
2023-01-21 11:27:11.356560: step: 2028/530, loss: 0.03535033389925957
2023-01-21 11:27:12.502992: step: 2032/530, loss: 0.002891731448471546
2023-01-21 11:27:13.626800: step: 2036/530, loss: 0.04080677032470703
2023-01-21 11:27:14.747462: step: 2040/530, loss: 0.037096213549375534
2023-01-21 11:27:15.881183: step: 2044/530, loss: 0.005787706468254328
2023-01-21 11:27:17.031142: step: 2048/530, loss: 0.0067806243896484375
2023-01-21 11:27:18.205503: step: 2052/530, loss: 0.2756132185459137
2023-01-21 11:27:19.333098: step: 2056/530, loss: 0.06020336225628853
2023-01-21 11:27:20.463400: step: 2060/530, loss: 0.04308032989501953
2023-01-21 11:27:21.634109: step: 2064/530, loss: 0.0013789177173748612
2023-01-21 11:27:22.770242: step: 2068/530, loss: 0.016801167279481888
2023-01-21 11:27:23.926305: step: 2072/530, loss: 0.042267706245183945
2023-01-21 11:27:25.055327: step: 2076/530, loss: 0.0032761571928858757
2023-01-21 11:27:26.219636: step: 2080/530, loss: 0.004434108734130859
2023-01-21 11:27:27.359584: step: 2084/530, loss: 0.0003732681507244706
2023-01-21 11:27:28.530809: step: 2088/530, loss: 0.0034166336990892887
2023-01-21 11:27:29.663255: step: 2092/530, loss: 0.07679310441017151
2023-01-21 11:27:30.836593: step: 2096/530, loss: 0.05839109420776367
2023-01-21 11:27:31.975797: step: 2100/530, loss: 0.002606010530143976
2023-01-21 11:27:33.162649: step: 2104/530, loss: 0.0004708290216512978
2023-01-21 11:27:34.319984: step: 2108/530, loss: 0.012980842962861061
2023-01-21 11:27:35.449674: step: 2112/530, loss: 0.021744156256318092
2023-01-21 11:27:36.614115: step: 2116/530, loss: 0.0007800102466717362
2023-01-21 11:27:37.743708: step: 2120/530, loss: 0.030373573303222656
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.57405614714424, 'r': 0.7896138482023968, 'f1': 0.6647982062780268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.5953389830508474, 'r': 0.8028571428571428, 'f1': 0.6836982968369829}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5393258426966292, 'r': 0.8888888888888888, 'f1': 0.6713286713286712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
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': 16}
Russian: {'event': {'p': 0.37254901960784315, 'r': 0.5277777777777778, 'f1': 0.4367816091954023}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:28:20.376328: step: 4/530, loss: 0.015292358584702015
2023-01-21 11:28:21.521725: step: 8/530, loss: 0.00026569367037154734
2023-01-21 11:28:22.669941: step: 12/530, loss: 0.002992343856021762
2023-01-21 11:28:23.823217: step: 16/530, loss: 0.2529309391975403
2023-01-21 11:28:24.958546: step: 20/530, loss: 0.038007546216249466
2023-01-21 11:28:26.093083: step: 24/530, loss: 0.0013069153064861894
2023-01-21 11:28:27.198185: step: 28/530, loss: 0.023984145373106003
2023-01-21 11:28:28.317222: step: 32/530, loss: 0.026635169982910156
2023-01-21 11:28:29.446429: step: 36/530, loss: 0.00894174538552761
2023-01-21 11:28:30.589333: step: 40/530, loss: 0.02837815321981907
2023-01-21 11:28:31.761820: step: 44/530, loss: 0.024371815845370293
2023-01-21 11:28:32.916001: step: 48/530, loss: 0.0006031990051269531
2023-01-21 11:28:34.076406: step: 52/530, loss: 0.004345322027802467
2023-01-21 11:28:35.194278: step: 56/530, loss: 0.0026497840881347656
2023-01-21 11:28:36.328822: step: 60/530, loss: 0.008657646365463734
2023-01-21 11:28:37.432666: step: 64/530, loss: 0.036218974739313126
2023-01-21 11:28:38.566317: step: 68/530, loss: 0.000977325369603932
2023-01-21 11:28:39.692461: step: 72/530, loss: 0.00144443497993052
2023-01-21 11:28:40.869649: step: 76/530, loss: 0.004104423336684704
2023-01-21 11:28:42.017812: step: 80/530, loss: 0.0036943438462913036
2023-01-21 11:28:43.151069: step: 84/530, loss: 0.010357379913330078
2023-01-21 11:28:44.306677: step: 88/530, loss: 0.8404155373573303
2023-01-21 11:28:45.430918: step: 92/530, loss: 0.023323822766542435
2023-01-21 11:28:46.595474: step: 96/530, loss: 0.00033845900907181203
2023-01-21 11:28:47.718875: step: 100/530, loss: 0.019304275512695312
2023-01-21 11:28:48.877427: step: 104/530, loss: 8.61167864059098e-05
2023-01-21 11:28:49.980015: step: 108/530, loss: 0.002255773637443781
2023-01-21 11:28:51.134478: step: 112/530, loss: 0.05083437263965607
2023-01-21 11:28:52.282601: step: 116/530, loss: 0.006120586302131414
2023-01-21 11:28:53.409791: step: 120/530, loss: 0.0011106490856036544
2023-01-21 11:28:54.547510: step: 124/530, loss: 0.582511305809021
2023-01-21 11:28:55.666129: step: 128/530, loss: 0.010121774859726429
2023-01-21 11:28:56.799571: step: 132/530, loss: 0.025431443005800247
2023-01-21 11:28:57.938637: step: 136/530, loss: 0.07729344069957733
2023-01-21 11:28:59.056247: step: 140/530, loss: 0.012636279687285423
2023-01-21 11:29:00.221345: step: 144/530, loss: 0.0013322830200195312
2023-01-21 11:29:01.344957: step: 148/530, loss: 0.01015863474458456
2023-01-21 11:29:02.469971: step: 152/530, loss: 0.001292324042879045
2023-01-21 11:29:03.612644: step: 156/530, loss: 0.00539011973887682
2023-01-21 11:29:04.736419: step: 160/530, loss: 0.0023737431038171053
2023-01-21 11:29:05.914116: step: 164/530, loss: 0.0007633209461346269
2023-01-21 11:29:07.062601: step: 168/530, loss: 0.0025578022468835115
2023-01-21 11:29:08.165974: step: 172/530, loss: 0.001564121339470148
2023-01-21 11:29:09.315660: step: 176/530, loss: 0.27624911069869995
2023-01-21 11:29:10.434495: step: 180/530, loss: 0.010771751403808594
2023-01-21 11:29:11.585893: step: 184/530, loss: 0.005230728071182966
2023-01-21 11:29:12.723403: step: 188/530, loss: 0.004926491063088179
2023-01-21 11:29:13.850537: step: 192/530, loss: 3.519058373058215e-05
2023-01-21 11:29:14.996897: step: 196/530, loss: 0.04157733917236328
2023-01-21 11:29:16.150510: step: 200/530, loss: 0.004698800854384899
2023-01-21 11:29:17.290262: step: 204/530, loss: 0.028289103880524635
2023-01-21 11:29:18.442649: step: 208/530, loss: 0.009384537115693092
2023-01-21 11:29:19.572239: step: 212/530, loss: 0.001333046006038785
2023-01-21 11:29:20.721279: step: 216/530, loss: 0.022342300042510033
2023-01-21 11:29:21.850490: step: 220/530, loss: 0.009606361389160156
2023-01-21 11:29:22.975739: step: 224/530, loss: 0.025665760040283203
2023-01-21 11:29:24.140571: step: 228/530, loss: 0.027713298797607422
2023-01-21 11:29:25.287358: step: 232/530, loss: 0.2112916111946106
2023-01-21 11:29:26.399656: step: 236/530, loss: 0.010000419802963734
2023-01-21 11:29:27.556086: step: 240/530, loss: 0.03228450194001198
2023-01-21 11:29:28.688448: step: 244/530, loss: 4.482269287109375e-05
2023-01-21 11:29:29.824518: step: 248/530, loss: 0.0764358788728714
2023-01-21 11:29:30.985855: step: 252/530, loss: 0.027337217703461647
2023-01-21 11:29:32.158482: step: 256/530, loss: 0.015713881701231003
2023-01-21 11:29:33.295149: step: 260/530, loss: 0.010607052594423294
2023-01-21 11:29:34.429259: step: 264/530, loss: 0.00903863925486803
2023-01-21 11:29:35.532599: step: 268/530, loss: 0.0038719179574400187
2023-01-21 11:29:36.655363: step: 272/530, loss: 0.03119659423828125
2023-01-21 11:29:37.790976: step: 276/530, loss: 0.020299959927797318
2023-01-21 11:29:38.939097: step: 280/530, loss: 0.03040914610028267
2023-01-21 11:29:40.040176: step: 284/530, loss: 0.01949186436831951
2023-01-21 11:29:41.201618: step: 288/530, loss: 0.00021748543076682836
2023-01-21 11:29:42.370602: step: 292/530, loss: 0.02996225468814373
2023-01-21 11:29:43.529329: step: 296/530, loss: 0.04797401651740074
2023-01-21 11:29:44.720957: step: 300/530, loss: 0.012944793328642845
2023-01-21 11:29:45.866879: step: 304/530, loss: 0.0019062042701989412
2023-01-21 11:29:47.027788: step: 308/530, loss: 0.0010084152454510331
2023-01-21 11:29:48.145250: step: 312/530, loss: 0.006839561276137829
2023-01-21 11:29:49.281030: step: 316/530, loss: 0.005239582154899836
2023-01-21 11:29:50.420759: step: 320/530, loss: 0.0025242806877940893
2023-01-21 11:29:51.572901: step: 324/530, loss: 0.5970168709754944
2023-01-21 11:29:52.686155: step: 328/530, loss: 0.015532874502241611
2023-01-21 11:29:53.830207: step: 332/530, loss: 0.023647451773285866
2023-01-21 11:29:54.983035: step: 336/530, loss: 0.006076335906982422
2023-01-21 11:29:56.141845: step: 340/530, loss: 0.07079296559095383
2023-01-21 11:29:57.278645: step: 344/530, loss: 3.89575980079826e-05
2023-01-21 11:29:58.408636: step: 348/530, loss: 0.017483185976743698
2023-01-21 11:29:59.575677: step: 352/530, loss: 0.0016483307117596269
2023-01-21 11:30:00.724525: step: 356/530, loss: 0.006072736345231533
2023-01-21 11:30:01.869260: step: 360/530, loss: 0.004326057620346546
2023-01-21 11:30:03.006464: step: 364/530, loss: 0.011350440792739391
2023-01-21 11:30:04.158494: step: 368/530, loss: 0.014878654852509499
2023-01-21 11:30:05.285321: step: 372/530, loss: 0.001069463905878365
2023-01-21 11:30:06.432460: step: 376/530, loss: 0.04634685441851616
2023-01-21 11:30:07.585857: step: 380/530, loss: 0.05124073103070259
2023-01-21 11:30:08.754437: step: 384/530, loss: 0.030756378546357155
2023-01-21 11:30:09.884971: step: 388/530, loss: 0.0017457485664635897
2023-01-21 11:30:11.042583: step: 392/530, loss: 0.021778490394353867
2023-01-21 11:30:12.209822: step: 396/530, loss: 0.0046524046920239925
2023-01-21 11:30:13.354371: step: 400/530, loss: 0.004118442535400391
2023-01-21 11:30:14.485201: step: 404/530, loss: 0.008835410699248314
2023-01-21 11:30:15.608286: step: 408/530, loss: 0.031606532633304596
2023-01-21 11:30:16.743021: step: 412/530, loss: 0.003976249601691961
2023-01-21 11:30:17.887507: step: 416/530, loss: 0.009182929992675781
2023-01-21 11:30:19.013471: step: 420/530, loss: 0.0003534317365847528
2023-01-21 11:30:20.181418: step: 424/530, loss: 0.013076209463179111
2023-01-21 11:30:21.370077: step: 428/530, loss: 0.010522890836000443
2023-01-21 11:30:22.506585: step: 432/530, loss: 0.010675431229174137
2023-01-21 11:30:23.599835: step: 436/530, loss: 0.036707308143377304
2023-01-21 11:30:24.706864: step: 440/530, loss: 0.009436417371034622
2023-01-21 11:30:25.834874: step: 444/530, loss: 0.021233653649687767
2023-01-21 11:30:26.979762: step: 448/530, loss: 0.00812521018087864
2023-01-21 11:30:28.125939: step: 452/530, loss: 0.0026074410416185856
2023-01-21 11:30:29.297056: step: 456/530, loss: 0.03212928771972656
2023-01-21 11:30:30.429227: step: 460/530, loss: 0.009420204907655716
2023-01-21 11:30:31.552164: step: 464/530, loss: 0.008159256540238857
2023-01-21 11:30:32.677242: step: 468/530, loss: 0.008121872320771217
2023-01-21 11:30:33.799953: step: 472/530, loss: 0.04783668741583824
2023-01-21 11:30:34.955801: step: 476/530, loss: 0.018864108249545097
2023-01-21 11:30:36.105059: step: 480/530, loss: 0.015483103692531586
2023-01-21 11:30:37.260769: step: 484/530, loss: 0.040277671068906784
2023-01-21 11:30:38.388998: step: 488/530, loss: 0.09269017726182938
2023-01-21 11:30:39.523097: step: 492/530, loss: 0.0831671729683876
2023-01-21 11:30:40.662888: step: 496/530, loss: 0.004986572079360485
2023-01-21 11:30:41.795316: step: 500/530, loss: 0.02617473714053631
2023-01-21 11:30:42.923003: step: 504/530, loss: 0.055841825902462006
2023-01-21 11:30:44.066461: step: 508/530, loss: 0.004359626676887274
2023-01-21 11:30:45.222639: step: 512/530, loss: 0.05129947513341904
2023-01-21 11:30:46.384844: step: 516/530, loss: 0.00033016205998137593
2023-01-21 11:30:47.489889: step: 520/530, loss: 0.003555202390998602
2023-01-21 11:30:48.609560: step: 524/530, loss: 0.013533401302993298
2023-01-21 11:30:49.721724: step: 528/530, loss: 0.03858394920825958
2023-01-21 11:30:50.866094: step: 532/530, loss: 0.046680644154548645
2023-01-21 11:30:52.014346: step: 536/530, loss: 0.004794502165168524
2023-01-21 11:30:53.164850: step: 540/530, loss: 0.9126772880554199
2023-01-21 11:30:54.356826: step: 544/530, loss: 0.4460304379463196
2023-01-21 11:30:55.517389: step: 548/530, loss: 0.01091155968606472
2023-01-21 11:30:56.660593: step: 552/530, loss: 0.00333824148401618
2023-01-21 11:30:57.823140: step: 556/530, loss: 0.018437718972563744
2023-01-21 11:30:58.926539: step: 560/530, loss: 0.00156574253924191
2023-01-21 11:31:00.064539: step: 564/530, loss: 0.002931213239207864
2023-01-21 11:31:01.227261: step: 568/530, loss: 0.013604020699858665
2023-01-21 11:31:02.357736: step: 572/530, loss: 0.0710744857788086
2023-01-21 11:31:03.504498: step: 576/530, loss: 0.00013408661470748484
2023-01-21 11:31:04.641951: step: 580/530, loss: 9.021758887683973e-05
2023-01-21 11:31:05.826326: step: 584/530, loss: 0.008456040173768997
2023-01-21 11:31:06.958719: step: 588/530, loss: 0.006662178784608841
2023-01-21 11:31:08.112340: step: 592/530, loss: 0.01610393449664116
2023-01-21 11:31:09.242758: step: 596/530, loss: 0.09527778625488281
2023-01-21 11:31:10.376910: step: 600/530, loss: 0.047502804547548294
2023-01-21 11:31:11.538817: step: 604/530, loss: 0.39616021513938904
2023-01-21 11:31:12.667473: step: 608/530, loss: 6.561278860317543e-05
2023-01-21 11:31:13.851387: step: 612/530, loss: 0.027946854010224342
2023-01-21 11:31:14.980937: step: 616/530, loss: 0.002735137939453125
2023-01-21 11:31:16.140963: step: 620/530, loss: 0.0008907318115234375
2023-01-21 11:31:17.316871: step: 624/530, loss: 0.009626960381865501
2023-01-21 11:31:18.474125: step: 628/530, loss: 0.07941360026597977
2023-01-21 11:31:19.630537: step: 632/530, loss: 0.004505539312958717
2023-01-21 11:31:20.747926: step: 636/530, loss: 0.006349098868668079
2023-01-21 11:31:21.901235: step: 640/530, loss: 0.05294186994433403
2023-01-21 11:31:23.039262: step: 644/530, loss: 0.02378559298813343
2023-01-21 11:31:24.173950: step: 648/530, loss: 0.03638515621423721
2023-01-21 11:31:25.312039: step: 652/530, loss: 0.2197938859462738
2023-01-21 11:31:26.443160: step: 656/530, loss: 0.00023374558077193797
2023-01-21 11:31:27.608110: step: 660/530, loss: 0.018462849780917168
2023-01-21 11:31:28.782349: step: 664/530, loss: 0.020740890875458717
2023-01-21 11:31:29.930944: step: 668/530, loss: 0.007229900453239679
2023-01-21 11:31:31.070479: step: 672/530, loss: 0.0002155303955078125
2023-01-21 11:31:32.196811: step: 676/530, loss: 0.0017820358043536544
2023-01-21 11:31:33.359015: step: 680/530, loss: 0.024843215942382812
2023-01-21 11:31:34.490478: step: 684/530, loss: 0.02043304406106472
2023-01-21 11:31:35.611969: step: 688/530, loss: 0.022045325487852097
2023-01-21 11:31:36.759814: step: 692/530, loss: 0.010693741030991077
2023-01-21 11:31:37.902740: step: 696/530, loss: 0.5845828652381897
2023-01-21 11:31:39.091291: step: 700/530, loss: 0.00490913400426507
2023-01-21 11:31:40.222483: step: 704/530, loss: 0.039392758160829544
2023-01-21 11:31:41.370749: step: 708/530, loss: 0.05005168914794922
2023-01-21 11:31:42.527789: step: 712/530, loss: 0.13192492723464966
2023-01-21 11:31:43.646004: step: 716/530, loss: 0.0031072618439793587
2023-01-21 11:31:44.773905: step: 720/530, loss: 0.032012272626161575
2023-01-21 11:31:45.910731: step: 724/530, loss: 0.03921985626220703
2023-01-21 11:31:47.031871: step: 728/530, loss: 0.008837318047881126
2023-01-21 11:31:48.169977: step: 732/530, loss: 0.003178930375725031
2023-01-21 11:31:49.291961: step: 736/530, loss: 0.0032990456093102694
2023-01-21 11:31:50.426761: step: 740/530, loss: 0.05809302255511284
2023-01-21 11:31:51.585967: step: 744/530, loss: 0.4365171492099762
2023-01-21 11:31:52.722612: step: 748/530, loss: 0.011650276370346546
2023-01-21 11:31:53.834625: step: 752/530, loss: 0.00486335763707757
2023-01-21 11:31:54.925329: step: 756/530, loss: 0.002232837723568082
2023-01-21 11:31:56.036923: step: 760/530, loss: 0.002267384435981512
2023-01-21 11:31:57.178892: step: 764/530, loss: 0.000416040449636057
2023-01-21 11:31:58.351647: step: 768/530, loss: 0.093775175511837
2023-01-21 11:31:59.483020: step: 772/530, loss: 0.0014932631747797132
2023-01-21 11:32:00.611866: step: 776/530, loss: 0.0033706664107739925
2023-01-21 11:32:01.724891: step: 780/530, loss: 0.002823066897690296
2023-01-21 11:32:02.895375: step: 784/530, loss: 0.0004391670227050781
2023-01-21 11:32:04.017406: step: 788/530, loss: 0.00149879464879632
2023-01-21 11:32:05.159533: step: 792/530, loss: 0.027102280408143997
2023-01-21 11:32:06.293343: step: 796/530, loss: 0.00024994611158035696
2023-01-21 11:32:07.415165: step: 800/530, loss: 0.011526107788085938
2023-01-21 11:32:08.534492: step: 804/530, loss: 0.01932373084127903
2023-01-21 11:32:09.649403: step: 808/530, loss: 0.04275193065404892
2023-01-21 11:32:10.801542: step: 812/530, loss: 0.0011491775512695312
2023-01-21 11:32:11.919767: step: 816/530, loss: 0.01269297581166029
2023-01-21 11:32:13.107510: step: 820/530, loss: 0.01688356325030327
2023-01-21 11:32:14.210693: step: 824/530, loss: 0.02442302741110325
2023-01-21 11:32:15.351334: step: 828/530, loss: 1.201629675051663e-05
2023-01-21 11:32:16.521149: step: 832/530, loss: 0.0010560989612713456
2023-01-21 11:32:17.652627: step: 836/530, loss: 0.005330848973244429
2023-01-21 11:32:18.768848: step: 840/530, loss: 0.07421279698610306
2023-01-21 11:32:19.927613: step: 844/530, loss: 0.03576316684484482
2023-01-21 11:32:21.073631: step: 848/530, loss: 0.004836750216782093
2023-01-21 11:32:22.254915: step: 852/530, loss: 0.0076614380814135075
2023-01-21 11:32:23.394426: step: 856/530, loss: 0.14129638671875
2023-01-21 11:32:24.514537: step: 860/530, loss: 0.0008947372552938759
2023-01-21 11:32:25.637947: step: 864/530, loss: 0.008805847726762295
2023-01-21 11:32:26.783777: step: 868/530, loss: 0.004365730099380016
2023-01-21 11:32:27.955304: step: 872/530, loss: 0.005825710482895374
2023-01-21 11:32:29.130500: step: 876/530, loss: 0.0013536453479900956
2023-01-21 11:32:30.290704: step: 880/530, loss: 0.04631233215332031
2023-01-21 11:32:31.446936: step: 884/530, loss: 0.02337360382080078
2023-01-21 11:32:32.596591: step: 888/530, loss: 0.015082931146025658
2023-01-21 11:32:33.741557: step: 892/530, loss: 0.016497422009706497
2023-01-21 11:32:34.887362: step: 896/530, loss: 0.022277260199189186
2023-01-21 11:32:36.040387: step: 900/530, loss: 0.011800384148955345
2023-01-21 11:32:37.189852: step: 904/530, loss: 0.0020702362526208162
2023-01-21 11:32:38.314652: step: 908/530, loss: 0.010740947909653187
2023-01-21 11:32:39.466329: step: 912/530, loss: 0.030042266473174095
2023-01-21 11:32:40.585078: step: 916/530, loss: 0.000881195068359375
2023-01-21 11:32:41.739181: step: 920/530, loss: 0.06256160885095596
2023-01-21 11:32:42.880107: step: 924/530, loss: 0.004214811138808727
2023-01-21 11:32:44.003650: step: 928/530, loss: 0.03674383461475372
2023-01-21 11:32:45.154573: step: 932/530, loss: 0.0001410484401276335
2023-01-21 11:32:46.319426: step: 936/530, loss: 0.005725002381950617
2023-01-21 11:32:47.479458: step: 940/530, loss: 0.02806529961526394
2023-01-21 11:32:48.611853: step: 944/530, loss: 0.005276394076645374
2023-01-21 11:32:49.746466: step: 948/530, loss: 0.03865776211023331
2023-01-21 11:32:50.888369: step: 952/530, loss: 0.018319224938750267
2023-01-21 11:32:52.038311: step: 956/530, loss: 0.15920843183994293
2023-01-21 11:32:53.158227: step: 960/530, loss: 0.0022800446022301912
2023-01-21 11:32:54.324824: step: 964/530, loss: 0.00034961701021529734
2023-01-21 11:32:55.486852: step: 968/530, loss: 0.0007337570423260331
2023-01-21 11:32:56.632373: step: 972/530, loss: 0.0019392013782635331
2023-01-21 11:32:57.789179: step: 976/530, loss: 0.002814674284309149
2023-01-21 11:32:58.924243: step: 980/530, loss: 0.002692151116207242
2023-01-21 11:33:00.070375: step: 984/530, loss: 0.04414090886712074
2023-01-21 11:33:01.200219: step: 988/530, loss: 0.0018574238056316972
2023-01-21 11:33:02.381889: step: 992/530, loss: 0.012186146341264248
2023-01-21 11:33:03.507841: step: 996/530, loss: 0.00014886856661178172
2023-01-21 11:33:04.646412: step: 1000/530, loss: 0.0013407707447186112
2023-01-21 11:33:05.789852: step: 1004/530, loss: 0.009565639309585094
2023-01-21 11:33:06.956431: step: 1008/530, loss: 0.03371448814868927
2023-01-21 11:33:08.105041: step: 1012/530, loss: 0.000559902167879045
2023-01-21 11:33:09.228178: step: 1016/530, loss: 0.0007171511533670127
2023-01-21 11:33:10.331360: step: 1020/530, loss: 0.032666780054569244
2023-01-21 11:33:11.459469: step: 1024/530, loss: 0.0008815765613690019
2023-01-21 11:33:12.614436: step: 1028/530, loss: 0.062098123133182526
2023-01-21 11:33:13.731859: step: 1032/530, loss: 0.006315517704933882
2023-01-21 11:33:14.876180: step: 1036/530, loss: 0.006799602881073952
2023-01-21 11:33:16.009627: step: 1040/530, loss: 0.004569625947624445
2023-01-21 11:33:17.155749: step: 1044/530, loss: 0.013460827060043812
2023-01-21 11:33:18.282469: step: 1048/530, loss: 0.030305862426757812
2023-01-21 11:33:19.438721: step: 1052/530, loss: 0.009350776672363281
2023-01-21 11:33:20.615513: step: 1056/530, loss: 0.008365822024643421
2023-01-21 11:33:21.780308: step: 1060/530, loss: 0.005614662077277899
2023-01-21 11:33:22.922625: step: 1064/530, loss: 0.0524333231151104
2023-01-21 11:33:24.044252: step: 1068/530, loss: 0.0037181854713708162
2023-01-21 11:33:25.193671: step: 1072/530, loss: 0.021323109045624733
2023-01-21 11:33:26.313309: step: 1076/530, loss: 0.015480900183320045
2023-01-21 11:33:27.415184: step: 1080/530, loss: 0.012609672732651234
2023-01-21 11:33:28.646516: step: 1084/530, loss: 0.014031315222382545
2023-01-21 11:33:29.770115: step: 1088/530, loss: 0.00398330669850111
2023-01-21 11:33:30.917908: step: 1092/530, loss: 0.008075237274169922
2023-01-21 11:33:32.027545: step: 1096/530, loss: 0.041944120079278946
2023-01-21 11:33:33.194225: step: 1100/530, loss: 0.0015975951682776213
2023-01-21 11:33:34.342262: step: 1104/530, loss: 0.05503235012292862
2023-01-21 11:33:35.481051: step: 1108/530, loss: 0.004263877868652344
2023-01-21 11:33:36.619612: step: 1112/530, loss: 0.015128898434340954
2023-01-21 11:33:37.764973: step: 1116/530, loss: 0.0086075309664011
2023-01-21 11:33:38.909234: step: 1120/530, loss: 0.01589355617761612
2023-01-21 11:33:40.084750: step: 1124/530, loss: 0.03546085208654404
2023-01-21 11:33:41.204929: step: 1128/530, loss: 0.010693646036088467
2023-01-21 11:33:42.324157: step: 1132/530, loss: 0.004012060351669788
2023-01-21 11:33:43.485158: step: 1136/530, loss: 0.0018407702445983887
2023-01-21 11:33:44.647651: step: 1140/530, loss: 0.0023242949973791838
2023-01-21 11:33:45.782279: step: 1144/530, loss: 0.012179756537079811
2023-01-21 11:33:46.876131: step: 1148/530, loss: 0.0027917863335460424
2023-01-21 11:33:48.017545: step: 1152/530, loss: 0.01964550092816353
2023-01-21 11:33:49.148016: step: 1156/530, loss: 0.049231529235839844
2023-01-21 11:33:50.296381: step: 1160/530, loss: 0.0075706481002271175
2023-01-21 11:33:51.445709: step: 1164/530, loss: 0.1298244446516037
2023-01-21 11:33:52.586268: step: 1168/530, loss: 0.0013109206920489669
2023-01-21 11:33:53.705609: step: 1172/530, loss: 0.016297435387969017
2023-01-21 11:33:54.830345: step: 1176/530, loss: 0.008211469277739525
2023-01-21 11:33:55.976194: step: 1180/530, loss: 0.0010014533763751388
2023-01-21 11:33:57.136952: step: 1184/530, loss: 0.13388614356517792
2023-01-21 11:33:58.269648: step: 1188/530, loss: 0.04209037125110626
2023-01-21 11:33:59.459058: step: 1192/530, loss: 0.03906765207648277
2023-01-21 11:34:00.582366: step: 1196/530, loss: 0.02360248565673828
2023-01-21 11:34:01.745104: step: 1200/530, loss: 0.014113474637269974
2023-01-21 11:34:02.878782: step: 1204/530, loss: 0.0016573906177654862
2023-01-21 11:34:04.038453: step: 1208/530, loss: 0.0651056319475174
2023-01-21 11:34:05.179124: step: 1212/530, loss: 0.013934182934463024
2023-01-21 11:34:06.292107: step: 1216/530, loss: 0.00417594937607646
2023-01-21 11:34:07.431584: step: 1220/530, loss: 0.000713348388671875
2023-01-21 11:34:08.574335: step: 1224/530, loss: 0.018771743401885033
2023-01-21 11:34:09.707011: step: 1228/530, loss: 0.0014384270180016756
2023-01-21 11:34:10.847010: step: 1232/530, loss: 0.015629053115844727
2023-01-21 11:34:11.981694: step: 1236/530, loss: 0.006462669465690851
2023-01-21 11:34:13.088574: step: 1240/530, loss: 0.004350590519607067
2023-01-21 11:34:14.242712: step: 1244/530, loss: 0.048005007207393646
2023-01-21 11:34:15.382662: step: 1248/530, loss: 0.0036044123116880655
2023-01-21 11:34:16.514016: step: 1252/530, loss: 0.00096044538076967
2023-01-21 11:34:17.685949: step: 1256/530, loss: 0.0004400253528729081
2023-01-21 11:34:18.803121: step: 1260/530, loss: 0.021367454901337624
2023-01-21 11:34:19.951724: step: 1264/530, loss: 0.0006041527376510203
2023-01-21 11:34:21.070837: step: 1268/530, loss: 0.03903598710894585
2023-01-21 11:34:22.205233: step: 1272/530, loss: 0.01013789139688015
2023-01-21 11:34:23.336227: step: 1276/530, loss: 0.0046936036087572575
2023-01-21 11:34:24.476340: step: 1280/530, loss: 0.006140995305031538
2023-01-21 11:34:25.620511: step: 1284/530, loss: 0.010223484598100185
2023-01-21 11:34:26.765003: step: 1288/530, loss: 0.07076644897460938
2023-01-21 11:34:27.905040: step: 1292/530, loss: 0.017858220264315605
2023-01-21 11:34:29.044899: step: 1296/530, loss: 0.013049697503447533
2023-01-21 11:34:30.171242: step: 1300/530, loss: 0.012957906350493431
2023-01-21 11:34:31.325241: step: 1304/530, loss: 0.0010457993485033512
2023-01-21 11:34:32.466113: step: 1308/530, loss: -4.38690176451928e-06
2023-01-21 11:34:33.628914: step: 1312/530, loss: 0.013954734429717064
2023-01-21 11:34:34.760104: step: 1316/530, loss: 0.0033947466872632504
2023-01-21 11:34:35.908898: step: 1320/530, loss: 0.06575240939855576
2023-01-21 11:34:37.043099: step: 1324/530, loss: 0.04318585246801376
2023-01-21 11:34:38.169518: step: 1328/530, loss: 0.04382972791790962
2023-01-21 11:34:39.296648: step: 1332/530, loss: 0.0007566451677121222
2023-01-21 11:34:40.467357: step: 1336/530, loss: 0.01949634589254856
2023-01-21 11:34:41.606350: step: 1340/530, loss: 0.010834027081727982
2023-01-21 11:34:42.751531: step: 1344/530, loss: 0.4003015458583832
2023-01-21 11:34:43.918836: step: 1348/530, loss: 0.002799701876938343
2023-01-21 11:34:45.074115: step: 1352/530, loss: 0.005150985904037952
2023-01-21 11:34:46.202053: step: 1356/530, loss: 0.005932617001235485
2023-01-21 11:34:47.336363: step: 1360/530, loss: 0.01842203177511692
2023-01-21 11:34:48.458755: step: 1364/530, loss: 0.0011153221130371094
2023-01-21 11:34:49.593194: step: 1368/530, loss: 0.09692482650279999
2023-01-21 11:34:50.713319: step: 1372/530, loss: 0.011766958050429821
2023-01-21 11:34:51.869304: step: 1376/530, loss: 0.0016706465976312757
2023-01-21 11:34:53.007564: step: 1380/530, loss: 4.839897155761719e-05
2023-01-21 11:34:54.131196: step: 1384/530, loss: 0.011758614331483841
2023-01-21 11:34:55.243366: step: 1388/530, loss: 0.029912948608398438
2023-01-21 11:34:56.395600: step: 1392/530, loss: 0.018086817115545273
2023-01-21 11:34:57.555791: step: 1396/530, loss: 0.0240649227052927
2023-01-21 11:34:58.672511: step: 1400/530, loss: 0.04873094707727432
2023-01-21 11:34:59.824877: step: 1404/530, loss: 0.001138925552368164
2023-01-21 11:35:00.976168: step: 1408/530, loss: 0.02376251295208931
2023-01-21 11:35:02.159022: step: 1412/530, loss: 0.0006364345317706466
2023-01-21 11:35:03.307421: step: 1416/530, loss: 0.06191730499267578
2023-01-21 11:35:04.456220: step: 1420/530, loss: 0.0047851563431322575
2023-01-21 11:35:05.571016: step: 1424/530, loss: 0.04018249362707138
2023-01-21 11:35:06.697570: step: 1428/530, loss: 0.03585944324731827
2023-01-21 11:35:07.849518: step: 1432/530, loss: 0.001352500868961215
2023-01-21 11:35:08.997313: step: 1436/530, loss: 0.7682409286499023
2023-01-21 11:35:10.120421: step: 1440/530, loss: 0.04735374450683594
2023-01-21 11:35:11.252086: step: 1444/530, loss: 0.044617556035518646
2023-01-21 11:35:12.383458: step: 1448/530, loss: 0.1915932148694992
2023-01-21 11:35:13.537078: step: 1452/530, loss: 0.007493495941162109
2023-01-21 11:35:14.679702: step: 1456/530, loss: 0.010313605889678001
2023-01-21 11:35:15.817216: step: 1460/530, loss: 0.003879451658576727
2023-01-21 11:35:16.900966: step: 1464/530, loss: 0.012420511804521084
2023-01-21 11:35:18.048078: step: 1468/530, loss: 0.047693394124507904
2023-01-21 11:35:19.166299: step: 1472/530, loss: 0.01220846176147461
2023-01-21 11:35:20.331133: step: 1476/530, loss: 0.013534116558730602
2023-01-21 11:35:21.483106: step: 1480/530, loss: 0.046292494982481
2023-01-21 11:35:22.631496: step: 1484/530, loss: 5.683898780262098e-05
2023-01-21 11:35:23.794164: step: 1488/530, loss: 0.0736316666007042
2023-01-21 11:35:24.916946: step: 1492/530, loss: 0.18067750334739685
2023-01-21 11:35:26.046360: step: 1496/530, loss: 0.014715098775923252
2023-01-21 11:35:27.190999: step: 1500/530, loss: 0.02805023267865181
2023-01-21 11:35:28.351316: step: 1504/530, loss: 0.0004917144542559981
2023-01-21 11:35:29.493874: step: 1508/530, loss: 0.05224017798900604
2023-01-21 11:35:30.680195: step: 1512/530, loss: 0.008056067861616611
2023-01-21 11:35:31.821881: step: 1516/530, loss: 0.0012901306618005037
2023-01-21 11:35:32.961242: step: 1520/530, loss: 0.017394209280610085
2023-01-21 11:35:34.083611: step: 1524/530, loss: 0.0049024103209376335
2023-01-21 11:35:35.225444: step: 1528/530, loss: 0.05933287367224693
2023-01-21 11:35:36.370247: step: 1532/530, loss: 0.028240490704774857
2023-01-21 11:35:37.510986: step: 1536/530, loss: 0.017984485253691673
2023-01-21 11:35:38.650516: step: 1540/530, loss: 9.322166442871094e-05
2023-01-21 11:35:39.801842: step: 1544/530, loss: 0.004147434141486883
2023-01-21 11:35:40.935995: step: 1548/530, loss: 0.0028263567946851254
2023-01-21 11:35:42.058810: step: 1552/530, loss: 0.002677345182746649
2023-01-21 11:35:43.187428: step: 1556/530, loss: 0.053376391530036926
2023-01-21 11:35:44.347693: step: 1560/530, loss: 0.010211181826889515
2023-01-21 11:35:45.481669: step: 1564/530, loss: 0.05120248720049858
2023-01-21 11:35:46.627811: step: 1568/530, loss: 0.029242707416415215
2023-01-21 11:35:47.783306: step: 1572/530, loss: 0.001630592392757535
2023-01-21 11:35:48.911174: step: 1576/530, loss: 0.013994408771395683
2023-01-21 11:35:50.030982: step: 1580/530, loss: 0.014351654797792435
2023-01-21 11:35:51.173227: step: 1584/530, loss: 0.045104410499334335
2023-01-21 11:35:52.295991: step: 1588/530, loss: 0.00011491775512695312
2023-01-21 11:35:53.474748: step: 1592/530, loss: 0.4080522656440735
2023-01-21 11:35:54.622483: step: 1596/530, loss: 0.008930779062211514
2023-01-21 11:35:55.761107: step: 1600/530, loss: 0.0003186225949320942
2023-01-21 11:35:56.889981: step: 1604/530, loss: 0.0005848884466104209
2023-01-21 11:35:58.017835: step: 1608/530, loss: 0.0009103775373660028
2023-01-21 11:35:59.162550: step: 1612/530, loss: 0.025302886962890625
2023-01-21 11:36:00.302661: step: 1616/530, loss: 0.07699184119701385
2023-01-21 11:36:01.419405: step: 1620/530, loss: 0.004268264397978783
2023-01-21 11:36:02.593959: step: 1624/530, loss: 0.034941770136356354
2023-01-21 11:36:03.731859: step: 1628/530, loss: 0.06112881004810333
2023-01-21 11:36:04.861219: step: 1632/530, loss: 0.050271034240722656
2023-01-21 11:36:06.031268: step: 1636/530, loss: 0.03523597866296768
2023-01-21 11:36:07.164783: step: 1640/530, loss: 0.039323046803474426
2023-01-21 11:36:08.294853: step: 1644/530, loss: 0.0007152557373046875
2023-01-21 11:36:09.459027: step: 1648/530, loss: 0.03070545382797718
2023-01-21 11:36:10.604416: step: 1652/530, loss: 0.0002801895316224545
2023-01-21 11:36:11.718925: step: 1656/530, loss: 0.03340888023376465
2023-01-21 11:36:12.840050: step: 1660/530, loss: 0.03912239149212837
2023-01-21 11:36:13.956257: step: 1664/530, loss: 0.029918670654296875
2023-01-21 11:36:15.094936: step: 1668/530, loss: 0.03626837953925133
2023-01-21 11:36:16.207417: step: 1672/530, loss: 0.00051627162611112
2023-01-21 11:36:17.340803: step: 1676/530, loss: 0.00024852753267623484
2023-01-21 11:36:18.454463: step: 1680/530, loss: 0.10333757847547531
2023-01-21 11:36:19.579636: step: 1684/530, loss: 0.032894037663936615
2023-01-21 11:36:20.704930: step: 1688/530, loss: 0.04468412697315216
2023-01-21 11:36:21.847382: step: 1692/530, loss: 0.06539478898048401
2023-01-21 11:36:22.982605: step: 1696/530, loss: 0.028319358825683594
2023-01-21 11:36:24.122036: step: 1700/530, loss: 0.026014043018221855
2023-01-21 11:36:25.290491: step: 1704/530, loss: 0.02412591129541397
2023-01-21 11:36:26.423575: step: 1708/530, loss: 0.003424358554184437
2023-01-21 11:36:27.576210: step: 1712/530, loss: 0.06916952133178711
2023-01-21 11:36:28.698610: step: 1716/530, loss: 0.018154717981815338
2023-01-21 11:36:29.861520: step: 1720/530, loss: 0.018002605065703392
2023-01-21 11:36:30.975221: step: 1724/530, loss: 0.027803612872958183
2023-01-21 11:36:32.145956: step: 1728/530, loss: 0.029755592346191406
2023-01-21 11:36:33.289504: step: 1732/530, loss: 0.022272396832704544
2023-01-21 11:36:34.424586: step: 1736/530, loss: 0.013708305545151234
2023-01-21 11:36:35.564226: step: 1740/530, loss: 0.010013199411332607
2023-01-21 11:36:36.704555: step: 1744/530, loss: 0.02849132940173149
2023-01-21 11:36:37.839406: step: 1748/530, loss: 0.004912948235869408
2023-01-21 11:36:39.011147: step: 1752/530, loss: 0.02959737740457058
2023-01-21 11:36:40.153995: step: 1756/530, loss: 0.06414385139942169
2023-01-21 11:36:41.328049: step: 1760/530, loss: 0.02694430574774742
2023-01-21 11:36:42.466703: step: 1764/530, loss: 0.007542610168457031
2023-01-21 11:36:43.570768: step: 1768/530, loss: 0.044791363179683685
2023-01-21 11:36:44.721721: step: 1772/530, loss: 0.06140861660242081
2023-01-21 11:36:45.905390: step: 1776/530, loss: 0.007136440370231867
2023-01-21 11:36:47.019799: step: 1780/530, loss: 0.06073713302612305
2023-01-21 11:36:48.191568: step: 1784/530, loss: 0.02201233059167862
2023-01-21 11:36:49.324678: step: 1788/530, loss: 0.14060278236865997
2023-01-21 11:36:50.471545: step: 1792/530, loss: 0.00232276925817132
2023-01-21 11:36:51.642904: step: 1796/530, loss: 0.03365373611450195
2023-01-21 11:36:52.777275: step: 1800/530, loss: 0.006580925080925226
2023-01-21 11:36:53.915463: step: 1804/530, loss: 0.10815596580505371
2023-01-21 11:36:55.046066: step: 1808/530, loss: 0.1154622733592987
2023-01-21 11:36:56.207866: step: 1812/530, loss: 0.005750847049057484
2023-01-21 11:36:57.387503: step: 1816/530, loss: 0.010682869702577591
2023-01-21 11:36:58.489277: step: 1820/530, loss: 0.016840457916259766
2023-01-21 11:36:59.625516: step: 1824/530, loss: 0.0032240867149084806
2023-01-21 11:37:00.785733: step: 1828/530, loss: 0.04145565256476402
2023-01-21 11:37:01.914034: step: 1832/530, loss: 0.011776257306337357
2023-01-21 11:37:03.024120: step: 1836/530, loss: 0.02168302610516548
2023-01-21 11:37:04.150149: step: 1840/530, loss: 0.007101201917976141
2023-01-21 11:37:05.303796: step: 1844/530, loss: 0.011563587933778763
2023-01-21 11:37:06.434889: step: 1848/530, loss: 0.0015417098766192794
2023-01-21 11:37:07.556170: step: 1852/530, loss: 0.023259639739990234
2023-01-21 11:37:08.669753: step: 1856/530, loss: 0.009025287814438343
2023-01-21 11:37:09.801715: step: 1860/530, loss: 0.05360355228185654
2023-01-21 11:37:10.924189: step: 1864/530, loss: 0.07667026668787003
2023-01-21 11:37:12.082799: step: 1868/530, loss: 0.02479849010705948
2023-01-21 11:37:13.241839: step: 1872/530, loss: 0.021096229553222656
2023-01-21 11:37:14.391311: step: 1876/530, loss: 0.025937652215361595
2023-01-21 11:37:15.535539: step: 1880/530, loss: 0.00142841343767941
2023-01-21 11:37:16.689627: step: 1884/530, loss: 0.06055860593914986
2023-01-21 11:37:17.856664: step: 1888/530, loss: 0.02900991216301918
2023-01-21 11:37:19.021334: step: 1892/530, loss: 0.02437887154519558
2023-01-21 11:37:20.122782: step: 1896/530, loss: 0.020090674981474876
2023-01-21 11:37:21.229104: step: 1900/530, loss: 0.0367036834359169
2023-01-21 11:37:22.396169: step: 1904/530, loss: 0.7667005658149719
2023-01-21 11:37:23.541952: step: 1908/530, loss: 0.025771141052246094
2023-01-21 11:37:24.694839: step: 1912/530, loss: 0.0015901147853583097
2023-01-21 11:37:25.827898: step: 1916/530, loss: 0.0046542645432055
2023-01-21 11:37:26.983873: step: 1920/530, loss: 0.008250046521425247
2023-01-21 11:37:28.114675: step: 1924/530, loss: 0.011295031756162643
2023-01-21 11:37:29.261573: step: 1928/530, loss: 0.007999039255082607
2023-01-21 11:37:30.385327: step: 1932/530, loss: 0.0009476662380620837
2023-01-21 11:37:31.526156: step: 1936/530, loss: 0.01576271280646324
2023-01-21 11:37:32.687108: step: 1940/530, loss: 0.016741622239351273
2023-01-21 11:37:33.813432: step: 1944/530, loss: 0.05731058120727539
2023-01-21 11:37:34.967871: step: 1948/530, loss: 0.015318680554628372
2023-01-21 11:37:36.128986: step: 1952/530, loss: 0.005451679695397615
2023-01-21 11:37:37.241455: step: 1956/530, loss: 0.0008780480129644275
2023-01-21 11:37:38.353812: step: 1960/530, loss: 0.024087905883789062
2023-01-21 11:37:39.507892: step: 1964/530, loss: 0.08922433853149414
2023-01-21 11:37:40.642271: step: 1968/530, loss: 0.05738535150885582
2023-01-21 11:37:41.811192: step: 1972/530, loss: 0.0319003127515316
2023-01-21 11:37:42.960273: step: 1976/530, loss: 0.018371202051639557
2023-01-21 11:37:44.093918: step: 1980/530, loss: 0.00092573172878474
2023-01-21 11:37:45.251490: step: 1984/530, loss: 0.01293201558291912
2023-01-21 11:37:46.368457: step: 1988/530, loss: 0.008470535278320312
2023-01-21 11:37:47.514046: step: 1992/530, loss: 0.00740737933665514
2023-01-21 11:37:48.675363: step: 1996/530, loss: 0.0041907308623194695
2023-01-21 11:37:49.801664: step: 2000/530, loss: 0.002651214599609375
2023-01-21 11:37:50.948858: step: 2004/530, loss: 0.0021840096451342106
2023-01-21 11:37:52.094622: step: 2008/530, loss: 0.0011714458232745528
2023-01-21 11:37:53.240115: step: 2012/530, loss: 0.014099788852036
2023-01-21 11:37:54.384980: step: 2016/530, loss: 0.0011686325306072831
2023-01-21 11:37:55.514977: step: 2020/530, loss: 0.020229339599609375
2023-01-21 11:37:56.645068: step: 2024/530, loss: 0.03471355512738228
2023-01-21 11:37:57.802017: step: 2028/530, loss: 0.014459704980254173
2023-01-21 11:37:58.930312: step: 2032/530, loss: 0.007038879673928022
2023-01-21 11:38:00.076733: step: 2036/530, loss: 0.09724826365709305
2023-01-21 11:38:01.219152: step: 2040/530, loss: 0.03464307636022568
2023-01-21 11:38:02.349249: step: 2044/530, loss: 0.005393314640969038
2023-01-21 11:38:03.488464: step: 2048/530, loss: 0.005774307064712048
2023-01-21 11:38:04.618895: step: 2052/530, loss: 0.03452944755554199
2023-01-21 11:38:05.739565: step: 2056/530, loss: 0.0019062042701989412
2023-01-21 11:38:06.844871: step: 2060/530, loss: 0.06154308468103409
2023-01-21 11:38:07.975426: step: 2064/530, loss: 0.00037870407686568797
2023-01-21 11:38:09.123228: step: 2068/530, loss: 0.017535973340272903
2023-01-21 11:38:10.259962: step: 2072/530, loss: 0.0013158798683434725
2023-01-21 11:38:11.408397: step: 2076/530, loss: 0.040188979357481
2023-01-21 11:38:12.546327: step: 2080/530, loss: 0.0002916336234193295
2023-01-21 11:38:13.685872: step: 2084/530, loss: 0.0021088123321533203
2023-01-21 11:38:14.828930: step: 2088/530, loss: 0.02428274229168892
2023-01-21 11:38:15.950696: step: 2092/530, loss: 0.0008046150323934853
2023-01-21 11:38:17.085819: step: 2096/530, loss: 0.02023186907172203
2023-01-21 11:38:18.211411: step: 2100/530, loss: 0.004340457729995251
2023-01-21 11:38:19.350082: step: 2104/530, loss: 0.0037119865883141756
2023-01-21 11:38:20.464757: step: 2108/530, loss: 0.008204841054975986
2023-01-21 11:38:21.620489: step: 2112/530, loss: 0.06804895401000977
2023-01-21 11:38:22.780094: step: 2116/530, loss: 0.013231849297881126
2023-01-21 11:38:23.921189: step: 2120/530, loss: 0.009294414892792702
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.6022845275181724, 'r': 0.7723035952063915, 'f1': 0.676779463243874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6318681318681318, 'r': 0.7885714285714286, 'f1': 0.7015760040671072}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5697674418604651, 'r': 0.9074074074074074, 'f1': 0.7}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.7, 'r': 0.5555555555555556, 'f1': 0.6194690265486726}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
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': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:39:07.756191: step: 4/530, loss: 0.021376801654696465
2023-01-21 11:39:08.892450: step: 8/530, loss: 0.01391296461224556
2023-01-21 11:39:10.018873: step: 12/530, loss: 0.047209374606609344
2023-01-21 11:39:11.210417: step: 16/530, loss: 0.005578422453254461
2023-01-21 11:39:12.336818: step: 20/530, loss: 0.00213203439489007
2023-01-21 11:39:13.480305: step: 24/530, loss: 0.02775449864566326
2023-01-21 11:39:14.613433: step: 28/530, loss: 0.0018810272449627519
2023-01-21 11:39:15.772055: step: 32/530, loss: 0.01108322199434042
2023-01-21 11:39:16.887156: step: 36/530, loss: 0.00011758804612327367
2023-01-21 11:39:18.057192: step: 40/530, loss: 0.034690190106630325
2023-01-21 11:39:19.170738: step: 44/530, loss: 0.0009428977500647306
2023-01-21 11:39:20.301564: step: 48/530, loss: 0.024576853960752487
2023-01-21 11:39:21.425153: step: 52/530, loss: 0.001983213471248746
2023-01-21 11:39:22.537214: step: 56/530, loss: 0.004894828889518976
2023-01-21 11:39:23.678709: step: 60/530, loss: 0.008528328500688076
2023-01-21 11:39:24.815918: step: 64/530, loss: 0.0009912491077557206
2023-01-21 11:39:25.962144: step: 68/530, loss: 0.011310959234833717
2023-01-21 11:39:27.077059: step: 72/530, loss: 0.0005329131963662803
2023-01-21 11:39:28.248658: step: 76/530, loss: 0.008119810372591019
2023-01-21 11:39:29.406471: step: 80/530, loss: 0.0006246566772460938
2023-01-21 11:39:30.507709: step: 84/530, loss: 0.0008472918998450041
2023-01-21 11:39:31.647844: step: 88/530, loss: 0.08781089633703232
2023-01-21 11:39:32.766804: step: 92/530, loss: 0.0008754730224609375
2023-01-21 11:39:33.950083: step: 96/530, loss: 0.010413646697998047
2023-01-21 11:39:35.090566: step: 100/530, loss: 0.0020195008255541325
2023-01-21 11:39:36.245202: step: 104/530, loss: 0.006958008278161287
2023-01-21 11:39:37.386355: step: 108/530, loss: 0.0031405449844896793
2023-01-21 11:39:38.522228: step: 112/530, loss: 0.023438643664121628
2023-01-21 11:39:39.687211: step: 116/530, loss: 0.000370025634765625
2023-01-21 11:39:40.836898: step: 120/530, loss: 0.044766999781131744
2023-01-21 11:39:41.983387: step: 124/530, loss: 0.01146621722728014
2023-01-21 11:39:43.100795: step: 128/530, loss: 0.005335998721420765
2023-01-21 11:39:44.249634: step: 132/530, loss: 0.0009471892844885588
2023-01-21 11:39:45.420566: step: 136/530, loss: 0.08883900940418243
2023-01-21 11:39:46.549159: step: 140/530, loss: 0.003948879428207874
2023-01-21 11:39:47.688481: step: 144/530, loss: 0.010422038845717907
2023-01-21 11:39:48.810077: step: 148/530, loss: 0.07162895798683167
2023-01-21 11:39:49.936386: step: 152/530, loss: 0.004631662741303444
2023-01-21 11:39:51.073984: step: 156/530, loss: 0.024773500859737396
2023-01-21 11:39:52.202768: step: 160/530, loss: 0.004440593533217907
2023-01-21 11:39:53.343343: step: 164/530, loss: 0.0001966476411325857
2023-01-21 11:39:54.509832: step: 168/530, loss: 0.049112655222415924
2023-01-21 11:39:55.645506: step: 172/530, loss: 0.015824317932128906
2023-01-21 11:39:56.819852: step: 176/530, loss: 0.004867744632065296
2023-01-21 11:39:58.000341: step: 180/530, loss: 0.0012513160472735763
2023-01-21 11:39:59.115725: step: 184/530, loss: 0.007091092877089977
2023-01-21 11:40:00.297487: step: 188/530, loss: 0.000102996826171875
2023-01-21 11:40:01.435733: step: 192/530, loss: 0.001186370849609375
2023-01-21 11:40:02.639459: step: 196/530, loss: 0.0690065398812294
2023-01-21 11:40:03.750001: step: 200/530, loss: 0.030933953821659088
2023-01-21 11:40:04.867675: step: 204/530, loss: 0.0020143508445471525
2023-01-21 11:40:06.015800: step: 208/530, loss: 0.05099372938275337
2023-01-21 11:40:07.146121: step: 212/530, loss: 0.0025164843536913395
2023-01-21 11:40:08.281321: step: 216/530, loss: 0.0004335403791628778
2023-01-21 11:40:09.414421: step: 220/530, loss: 0.35948413610458374
2023-01-21 11:40:10.546734: step: 224/530, loss: 0.03319816663861275
2023-01-21 11:40:11.705280: step: 228/530, loss: 0.04940204694867134
2023-01-21 11:40:12.815864: step: 232/530, loss: 0.0018831252818927169
2023-01-21 11:40:13.973221: step: 236/530, loss: 0.0030321122612804174
2023-01-21 11:40:15.127518: step: 240/530, loss: 0.006460762117058039
2023-01-21 11:40:16.275719: step: 244/530, loss: 0.0007497787592001259
2023-01-21 11:40:17.437143: step: 248/530, loss: 0.01710362546145916
2023-01-21 11:40:18.562976: step: 252/530, loss: 0.003238201141357422
2023-01-21 11:40:19.711857: step: 256/530, loss: 0.005177593324333429
2023-01-21 11:40:20.867136: step: 260/530, loss: 0.04141349717974663
2023-01-21 11:40:22.039816: step: 264/530, loss: 0.05800752714276314
2023-01-21 11:40:23.186009: step: 268/530, loss: 9.288787987316027e-05
2023-01-21 11:40:24.341464: step: 272/530, loss: 0.08847922831773758
2023-01-21 11:40:25.475487: step: 276/530, loss: 0.02693157084286213
2023-01-21 11:40:26.609868: step: 280/530, loss: 0.009939384646713734
2023-01-21 11:40:27.754744: step: 284/530, loss: 0.05439424514770508
2023-01-21 11:40:28.884444: step: 288/530, loss: 0.010117149911820889
2023-01-21 11:40:30.029592: step: 292/530, loss: 0.0004725456237792969
2023-01-21 11:40:31.144042: step: 296/530, loss: 0.0003830909845419228
2023-01-21 11:40:32.305315: step: 300/530, loss: 0.005652999971061945
2023-01-21 11:40:33.483276: step: 304/530, loss: 0.002002811525017023
2023-01-21 11:40:34.607941: step: 308/530, loss: 0.00045959948329254985
2023-01-21 11:40:35.748099: step: 312/530, loss: 0.060602568089962006
2023-01-21 11:40:36.891128: step: 316/530, loss: 0.0009962081676349044
2023-01-21 11:40:38.044390: step: 320/530, loss: 0.0027749778237193823
2023-01-21 11:40:39.168922: step: 324/530, loss: 0.00012998581223655492
2023-01-21 11:40:40.320414: step: 328/530, loss: 0.052935220301151276
2023-01-21 11:40:41.445185: step: 332/530, loss: 0.0015010833740234375
2023-01-21 11:40:42.593795: step: 336/530, loss: 0.009228706359863281
2023-01-21 11:40:43.725865: step: 340/530, loss: 0.0005983352893963456
2023-01-21 11:40:44.865096: step: 344/530, loss: 0.001098251435905695
2023-01-21 11:40:46.017195: step: 348/530, loss: 0.0018707276321947575
2023-01-21 11:40:47.167120: step: 352/530, loss: 0.0268402099609375
2023-01-21 11:40:48.345287: step: 356/530, loss: 0.0006840705755166709
2023-01-21 11:40:49.492650: step: 360/530, loss: 2.088546534650959e-05
2023-01-21 11:40:50.642896: step: 364/530, loss: 0.03954944387078285
2023-01-21 11:40:51.754530: step: 368/530, loss: 0.003739976789802313
2023-01-21 11:40:52.887241: step: 372/530, loss: 0.000991916749626398
2023-01-21 11:40:54.032295: step: 376/530, loss: 0.004334068391472101
2023-01-21 11:40:55.154072: step: 380/530, loss: 0.009727001190185547
2023-01-21 11:40:56.271852: step: 384/530, loss: 0.137060284614563
2023-01-21 11:40:57.409571: step: 388/530, loss: 2.079009937006049e-05
2023-01-21 11:40:58.544568: step: 392/530, loss: 0.0315219908952713
2023-01-21 11:40:59.713406: step: 396/530, loss: 0.31429120898246765
2023-01-21 11:41:00.840634: step: 400/530, loss: 0.050110626965761185
2023-01-21 11:41:01.973129: step: 404/530, loss: 0.00042238234891556203
2023-01-21 11:41:03.136939: step: 408/530, loss: 0.009432220831513405
2023-01-21 11:41:04.262867: step: 412/530, loss: 0.00604205159470439
2023-01-21 11:41:05.393416: step: 416/530, loss: 0.009143829345703125
2023-01-21 11:41:06.522938: step: 420/530, loss: 0.0012064933544024825
2023-01-21 11:41:07.657552: step: 424/530, loss: 0.04776516184210777
2023-01-21 11:41:08.837203: step: 428/530, loss: 0.026981163769960403
2023-01-21 11:41:09.954562: step: 432/530, loss: 0.0006433010566979647
2023-01-21 11:41:11.109635: step: 436/530, loss: 0.002374935196712613
2023-01-21 11:41:12.270973: step: 440/530, loss: 0.010933113284409046
2023-01-21 11:41:13.458678: step: 444/530, loss: 0.008148575201630592
2023-01-21 11:41:14.658336: step: 448/530, loss: 0.017184162512421608
2023-01-21 11:41:15.805325: step: 452/530, loss: 0.0020130157936364412
2023-01-21 11:41:16.982343: step: 456/530, loss: 0.014023089781403542
2023-01-21 11:41:18.148835: step: 460/530, loss: 0.06027087941765785
2023-01-21 11:41:19.258848: step: 464/530, loss: 0.02288827858865261
2023-01-21 11:41:20.454814: step: 468/530, loss: 0.00015625954256393015
2023-01-21 11:41:21.598399: step: 472/530, loss: 0.023492146283388138
2023-01-21 11:41:22.698121: step: 476/530, loss: 0.02190723456442356
2023-01-21 11:41:23.820370: step: 480/530, loss: 0.00013656617375090718
2023-01-21 11:41:24.966059: step: 484/530, loss: 0.09405479580163956
2023-01-21 11:41:26.119187: step: 488/530, loss: 0.00020732879056595266
2023-01-21 11:41:27.217020: step: 492/530, loss: 0.003944778349250555
2023-01-21 11:41:28.350992: step: 496/530, loss: 0.013114357367157936
2023-01-21 11:41:29.468957: step: 500/530, loss: 4.110336158191785e-05
2023-01-21 11:41:30.603590: step: 504/530, loss: 7.60078473831527e-05
2023-01-21 11:41:31.720040: step: 508/530, loss: 0.0002619743172544986
2023-01-21 11:41:32.878032: step: 512/530, loss: 0.0041793822310864925
2023-01-21 11:41:34.038684: step: 516/530, loss: 0.03414182737469673
2023-01-21 11:41:35.184469: step: 520/530, loss: 0.001016807509586215
2023-01-21 11:41:36.307899: step: 524/530, loss: 0.0018742084503173828
2023-01-21 11:41:37.428738: step: 528/530, loss: 0.04295921325683594
2023-01-21 11:41:38.549643: step: 532/530, loss: 0.009517956525087357
2023-01-21 11:41:39.671120: step: 536/530, loss: 0.0009746550931595266
2023-01-21 11:41:40.823373: step: 540/530, loss: 0.04565925896167755
2023-01-21 11:41:41.963801: step: 544/530, loss: 0.12162236869335175
2023-01-21 11:41:43.100956: step: 548/530, loss: 5.187988426769152e-05
2023-01-21 11:41:44.232876: step: 552/530, loss: 0.020954705774784088
2023-01-21 11:41:45.424286: step: 556/530, loss: 0.0005092620849609375
2023-01-21 11:41:46.572116: step: 560/530, loss: 0.012198067270219326
2023-01-21 11:41:47.708419: step: 564/530, loss: 0.009385108947753906
2023-01-21 11:41:48.820291: step: 568/530, loss: 0.030081558972597122
2023-01-21 11:41:49.955245: step: 572/530, loss: 0.12272453308105469
2023-01-21 11:41:51.102402: step: 576/530, loss: 0.04121856763958931
2023-01-21 11:41:52.241283: step: 580/530, loss: 1.3399124327406753e-05
2023-01-21 11:41:53.387096: step: 584/530, loss: 0.06907663494348526
2023-01-21 11:41:54.526815: step: 588/530, loss: 0.0247024055570364
2023-01-21 11:41:55.682726: step: 592/530, loss: 0.0027711871080100536
2023-01-21 11:41:56.854337: step: 596/530, loss: 0.015142488293349743
2023-01-21 11:41:57.996592: step: 600/530, loss: 0.03383655473589897
2023-01-21 11:41:59.120275: step: 604/530, loss: 0.04236316680908203
2023-01-21 11:42:00.246515: step: 608/530, loss: 0.015430832281708717
2023-01-21 11:42:01.383364: step: 612/530, loss: 0.0033058645203709602
2023-01-21 11:42:02.514158: step: 616/530, loss: 0.5328415632247925
2023-01-21 11:42:03.662290: step: 620/530, loss: 0.0005355835310183465
2023-01-21 11:42:04.792565: step: 624/530, loss: 0.03737277910113335
2023-01-21 11:42:05.913801: step: 628/530, loss: 0.017632579430937767
2023-01-21 11:42:07.045156: step: 632/530, loss: 0.005974388215690851
2023-01-21 11:42:08.190887: step: 636/530, loss: 0.048528481274843216
2023-01-21 11:42:09.340905: step: 640/530, loss: 0.02683448977768421
2023-01-21 11:42:10.455220: step: 644/530, loss: 0.00026149750920012593
2023-01-21 11:42:11.556805: step: 648/530, loss: 0.05040605366230011
2023-01-21 11:42:12.706186: step: 652/530, loss: 0.014464568346738815
2023-01-21 11:42:13.806564: step: 656/530, loss: 0.02264528162777424
2023-01-21 11:42:14.895716: step: 660/530, loss: 0.012154579162597656
2023-01-21 11:42:16.035176: step: 664/530, loss: 0.004620837979018688
2023-01-21 11:42:17.168159: step: 668/530, loss: 0.009050989523530006
2023-01-21 11:42:18.278685: step: 672/530, loss: 0.060083627700805664
2023-01-21 11:42:19.408424: step: 676/530, loss: 0.010952567681670189
2023-01-21 11:42:20.540853: step: 680/530, loss: 0.0549686923623085
2023-01-21 11:42:21.650221: step: 684/530, loss: 0.008303356356918812
2023-01-21 11:42:22.776982: step: 688/530, loss: 0.015359687618911266
2023-01-21 11:42:23.904208: step: 692/530, loss: 0.004053687676787376
2023-01-21 11:42:25.005749: step: 696/530, loss: 0.08860655128955841
2023-01-21 11:42:26.137969: step: 700/530, loss: 0.027171609923243523
2023-01-21 11:42:27.289315: step: 704/530, loss: 0.023876572027802467
2023-01-21 11:42:28.413737: step: 708/530, loss: 0.00023996829986572266
2023-01-21 11:42:29.562022: step: 712/530, loss: 0.07328624278306961
2023-01-21 11:42:30.682212: step: 716/530, loss: 0.012323093600571156
2023-01-21 11:42:31.798313: step: 720/530, loss: 1.506805438111769e-05
2023-01-21 11:42:32.959667: step: 724/530, loss: 0.0019681931007653475
2023-01-21 11:42:34.067380: step: 728/530, loss: 0.04083900526165962
2023-01-21 11:42:35.204047: step: 732/530, loss: 0.00083160400390625
2023-01-21 11:42:36.286814: step: 736/530, loss: 0.0021749495062977076
2023-01-21 11:42:37.407420: step: 740/530, loss: 0.6249213814735413
2023-01-21 11:42:38.546157: step: 744/530, loss: 0.01030359324067831
2023-01-21 11:42:39.690171: step: 748/530, loss: 0.032086946070194244
2023-01-21 11:42:40.810277: step: 752/530, loss: 0.04258289560675621
2023-01-21 11:42:41.938337: step: 756/530, loss: 0.0042785643599927425
2023-01-21 11:42:43.059148: step: 760/530, loss: 0.023368073627352715
2023-01-21 11:42:44.162940: step: 764/530, loss: 0.0016337394481524825
2023-01-21 11:42:45.296334: step: 768/530, loss: 0.010141182690858841
2023-01-21 11:42:46.422071: step: 772/530, loss: 0.036923836916685104
2023-01-21 11:42:47.547736: step: 776/530, loss: 0.0028108598198741674
2023-01-21 11:42:48.679899: step: 780/530, loss: 0.008792877197265625
2023-01-21 11:42:49.790909: step: 784/530, loss: 0.008434963412582874
2023-01-21 11:42:50.931244: step: 788/530, loss: 0.000682878540828824
2023-01-21 11:42:52.045531: step: 792/530, loss: 0.023146821185946465
2023-01-21 11:42:53.148126: step: 796/530, loss: 0.0013587952125817537
2023-01-21 11:42:54.259324: step: 800/530, loss: 0.003368377685546875
2023-01-21 11:42:55.361942: step: 804/530, loss: 0.0010303497547283769
2023-01-21 11:42:56.506420: step: 808/530, loss: 0.029104378074407578
2023-01-21 11:42:57.621892: step: 812/530, loss: 0.011813045479357243
2023-01-21 11:42:58.745044: step: 816/530, loss: 0.0013019561301916838
2023-01-21 11:42:59.880044: step: 820/530, loss: 0.14663906395435333
2023-01-21 11:43:01.001847: step: 824/530, loss: 0.0009376525995321572
2023-01-21 11:43:02.156892: step: 828/530, loss: 0.03287782520055771
2023-01-21 11:43:03.284379: step: 832/530, loss: 0.04450864717364311
2023-01-21 11:43:04.418526: step: 836/530, loss: 0.04730501398444176
2023-01-21 11:43:05.555173: step: 840/530, loss: 0.030045129358768463
2023-01-21 11:43:06.683920: step: 844/530, loss: 0.000533247017301619
2023-01-21 11:43:07.808473: step: 848/530, loss: 0.047948360443115234
2023-01-21 11:43:08.948032: step: 852/530, loss: 0.08938980102539062
2023-01-21 11:43:10.077015: step: 856/530, loss: 0.07054892182350159
2023-01-21 11:43:11.226895: step: 860/530, loss: 0.0005337238544598222
2023-01-21 11:43:12.371060: step: 864/530, loss: 0.0001386642543366179
2023-01-21 11:43:13.487763: step: 868/530, loss: 0.0003506660577841103
2023-01-21 11:43:14.622436: step: 872/530, loss: 0.025488808751106262
2023-01-21 11:43:15.759633: step: 876/530, loss: 0.27946898341178894
2023-01-21 11:43:16.857172: step: 880/530, loss: 0.0014894991181790829
2023-01-21 11:43:17.989109: step: 884/530, loss: 0.023252295330166817
2023-01-21 11:43:19.199986: step: 888/530, loss: 0.0004966736305505037
2023-01-21 11:43:20.366872: step: 892/530, loss: 0.09113006293773651
2023-01-21 11:43:21.465064: step: 896/530, loss: 0.0002075195370707661
2023-01-21 11:43:22.578043: step: 900/530, loss: 0.01126957032829523
2023-01-21 11:43:23.716072: step: 904/530, loss: 0.005335331428796053
2023-01-21 11:43:24.814620: step: 908/530, loss: 0.0017627717461436987
2023-01-21 11:43:25.958340: step: 912/530, loss: 0.00624008197337389
2023-01-21 11:43:27.069696: step: 916/530, loss: 0.003267192980274558
2023-01-21 11:43:28.174414: step: 920/530, loss: 0.0027115822304040194
2023-01-21 11:43:29.337685: step: 924/530, loss: 0.022049523890018463
2023-01-21 11:43:30.471045: step: 928/530, loss: 0.03569812700152397
2023-01-21 11:43:31.613754: step: 932/530, loss: 0.019016314297914505
2023-01-21 11:43:32.746109: step: 936/530, loss: 0.004714870825409889
2023-01-21 11:43:33.854578: step: 940/530, loss: 0.0004932403680868447
2023-01-21 11:43:34.991869: step: 944/530, loss: 0.0004512786981649697
2023-01-21 11:43:36.120435: step: 948/530, loss: 0.0046829222701489925
2023-01-21 11:43:37.275515: step: 952/530, loss: 0.004527711775153875
2023-01-21 11:43:38.407389: step: 956/530, loss: 0.009902680292725563
2023-01-21 11:43:39.507958: step: 960/530, loss: 3.952979750465602e-05
2023-01-21 11:43:40.656923: step: 964/530, loss: 0.0009933471446856856
2023-01-21 11:43:41.781705: step: 968/530, loss: 2.460479663568549e-05
2023-01-21 11:43:42.903802: step: 972/530, loss: 0.0016342162853106856
2023-01-21 11:43:44.042147: step: 976/530, loss: 0.005700302310287952
2023-01-21 11:43:45.137653: step: 980/530, loss: 0.0005764007801190019
2023-01-21 11:43:46.282485: step: 984/530, loss: 0.025848103687167168
2023-01-21 11:43:47.417073: step: 988/530, loss: 0.005493068601936102
2023-01-21 11:43:48.510099: step: 992/530, loss: 0.0025004863273352385
2023-01-21 11:43:49.640710: step: 996/530, loss: 0.001981067704036832
2023-01-21 11:43:50.767017: step: 1000/530, loss: 0.07185673713684082
2023-01-21 11:43:51.890365: step: 1004/530, loss: 0.4234001040458679
2023-01-21 11:43:52.989955: step: 1008/530, loss: 0.00034656524076126516
2023-01-21 11:43:54.104117: step: 1012/530, loss: 0.19825291633605957
2023-01-21 11:43:55.239338: step: 1016/530, loss: 0.008284568786621094
2023-01-21 11:43:56.343612: step: 1020/530, loss: 0.020164204761385918
2023-01-21 11:43:57.450916: step: 1024/530, loss: 0.010042286477982998
2023-01-21 11:43:58.571223: step: 1028/530, loss: 0.04541950300335884
2023-01-21 11:43:59.699752: step: 1032/530, loss: 0.03394145891070366
2023-01-21 11:44:00.818218: step: 1036/530, loss: 0.005318164825439453
2023-01-21 11:44:01.944552: step: 1040/530, loss: 0.018819905817508698
2023-01-21 11:44:03.096010: step: 1044/530, loss: 0.02320117875933647
2023-01-21 11:44:04.262012: step: 1048/530, loss: 0.00689043989405036
2023-01-21 11:44:05.393591: step: 1052/530, loss: 0.012432575225830078
2023-01-21 11:44:06.499056: step: 1056/530, loss: 0.0007476091268472373
2023-01-21 11:44:07.605772: step: 1060/530, loss: 0.0055480957962572575
2023-01-21 11:44:08.699592: step: 1064/530, loss: 0.006934452336281538
2023-01-21 11:44:09.827337: step: 1068/530, loss: 0.00020937919907737523
2023-01-21 11:44:10.971720: step: 1072/530, loss: 0.004772853571921587
2023-01-21 11:44:12.117456: step: 1076/530, loss: 0.004951858427375555
2023-01-21 11:44:13.243954: step: 1080/530, loss: 0.1476408988237381
2023-01-21 11:44:14.371791: step: 1084/530, loss: 0.05446682125329971
2023-01-21 11:44:15.510017: step: 1088/530, loss: 0.000392913818359375
2023-01-21 11:44:16.662583: step: 1092/530, loss: 0.06331367790699005
2023-01-21 11:44:17.765028: step: 1096/530, loss: 0.00222015380859375
2023-01-21 11:44:18.931983: step: 1100/530, loss: 0.0012237548362463713
2023-01-21 11:44:20.056109: step: 1104/530, loss: 2.47955322265625e-05
2023-01-21 11:44:21.185335: step: 1108/530, loss: 0.050952911376953125
2023-01-21 11:44:22.299473: step: 1112/530, loss: 0.04225749894976616
2023-01-21 11:44:23.419144: step: 1116/530, loss: 0.00017862320237327367
2023-01-21 11:44:24.548169: step: 1120/530, loss: 0.004182243719696999
2023-01-21 11:44:25.653035: step: 1124/530, loss: 0.00011167526827193797
2023-01-21 11:44:26.823272: step: 1128/530, loss: 0.24516411125659943
2023-01-21 11:44:27.940406: step: 1132/530, loss: 0.0318724662065506
2023-01-21 11:44:29.054323: step: 1136/530, loss: 0.1067424789071083
2023-01-21 11:44:30.216834: step: 1140/530, loss: 0.03593912348151207
2023-01-21 11:44:31.346642: step: 1144/530, loss: 0.0009889602661132812
2023-01-21 11:44:32.471395: step: 1148/530, loss: 0.03031158447265625
2023-01-21 11:44:33.561768: step: 1152/530, loss: 0.0592309944331646
2023-01-21 11:44:34.651041: step: 1156/530, loss: 0.00394515972584486
2023-01-21 11:44:35.769332: step: 1160/530, loss: 0.0005672455299645662
2023-01-21 11:44:36.878318: step: 1164/530, loss: 6.866455805720761e-05
2023-01-21 11:44:38.014234: step: 1168/530, loss: -1.182556115963962e-05
2023-01-21 11:44:39.138995: step: 1172/530, loss: 0.009155083447694778
2023-01-21 11:44:40.285841: step: 1176/530, loss: 0.0763792097568512
2023-01-21 11:44:41.428496: step: 1180/530, loss: 0.008555984124541283
2023-01-21 11:44:42.535641: step: 1184/530, loss: 0.0500640869140625
2023-01-21 11:44:43.637071: step: 1188/530, loss: 0.007271385286003351
2023-01-21 11:44:44.739048: step: 1192/530, loss: 0.02011279948055744
2023-01-21 11:44:45.882680: step: 1196/530, loss: 0.0688135176897049
2023-01-21 11:44:46.986424: step: 1200/530, loss: 0.04294218868017197
2023-01-21 11:44:48.141304: step: 1204/530, loss: 0.0026073455810546875
2023-01-21 11:44:49.272564: step: 1208/530, loss: 0.01093745231628418
2023-01-21 11:44:50.403695: step: 1212/530, loss: 0.0697048157453537
2023-01-21 11:44:51.500112: step: 1216/530, loss: 0.3891034424304962
2023-01-21 11:44:52.629084: step: 1220/530, loss: 0.011217307299375534
2023-01-21 11:44:53.734099: step: 1224/530, loss: 0.017900992184877396
2023-01-21 11:44:54.848098: step: 1228/530, loss: 0.0010059833293780684
2023-01-21 11:44:55.999068: step: 1232/530, loss: 0.012778043746948242
2023-01-21 11:44:57.114794: step: 1236/530, loss: 0.012760019861161709
2023-01-21 11:44:58.229400: step: 1240/530, loss: 0.057823631912469864
2023-01-21 11:44:59.364827: step: 1244/530, loss: 0.048862457275390625
2023-01-21 11:45:00.505860: step: 1248/530, loss: 0.089727021753788
2023-01-21 11:45:01.625458: step: 1252/530, loss: 0.013313102535903454
2023-01-21 11:45:02.765541: step: 1256/530, loss: 0.06653575599193573
2023-01-21 11:45:03.881268: step: 1260/530, loss: 0.022565318271517754
2023-01-21 11:45:05.002582: step: 1264/530, loss: 0.020505428314208984
2023-01-21 11:45:06.123120: step: 1268/530, loss: 0.013241958804428577
2023-01-21 11:45:07.270990: step: 1272/530, loss: 0.009296322241425514
2023-01-21 11:45:08.382962: step: 1276/530, loss: 0.05469541624188423
2023-01-21 11:45:09.510618: step: 1280/530, loss: 0.003972244448959827
2023-01-21 11:45:10.620875: step: 1284/530, loss: 0.00020618439884856343
2023-01-21 11:45:11.739232: step: 1288/530, loss: 0.0023051260504871607
2023-01-21 11:45:12.859584: step: 1292/530, loss: 0.03743896633386612
2023-01-21 11:45:13.986615: step: 1296/530, loss: 0.003361702198162675
2023-01-21 11:45:15.126226: step: 1300/530, loss: 0.0012639999622479081
2023-01-21 11:45:16.273255: step: 1304/530, loss: 0.0017868519062176347
2023-01-21 11:45:17.370478: step: 1308/530, loss: 0.0005592346424236894
2023-01-21 11:45:18.477079: step: 1312/530, loss: 0.05702686309814453
2023-01-21 11:45:19.604287: step: 1316/530, loss: 0.001959848450496793
2023-01-21 11:45:20.744774: step: 1320/530, loss: 0.00011930465552723035
2023-01-21 11:45:21.901217: step: 1324/530, loss: 0.05461826175451279
2023-01-21 11:45:23.015770: step: 1328/530, loss: 0.013545417226850986
2023-01-21 11:45:24.132022: step: 1332/530, loss: 0.11116848140954971
2023-01-21 11:45:25.242384: step: 1336/530, loss: 0.0016939162742346525
2023-01-21 11:45:26.365734: step: 1340/530, loss: 0.021041106432676315
2023-01-21 11:45:27.492555: step: 1344/530, loss: 0.03249244764447212
2023-01-21 11:45:28.658734: step: 1348/530, loss: 0.0161272045224905
2023-01-21 11:45:29.789868: step: 1352/530, loss: 0.03644008934497833
2023-01-21 11:45:30.909331: step: 1356/530, loss: 0.029905986040830612
2023-01-21 11:45:32.025868: step: 1360/530, loss: 0.010708236135542393
2023-01-21 11:45:33.183581: step: 1364/530, loss: 0.04342212527990341
2023-01-21 11:45:34.298728: step: 1368/530, loss: 0.013961220160126686
2023-01-21 11:45:35.405866: step: 1372/530, loss: 0.0029222487937659025
2023-01-21 11:45:36.509049: step: 1376/530, loss: 0.019478321075439453
2023-01-21 11:45:37.622825: step: 1380/530, loss: 0.009981346316635609
2023-01-21 11:45:38.750015: step: 1384/530, loss: 0.06494884192943573
2023-01-21 11:45:39.859281: step: 1388/530, loss: 0.0041595459915697575
2023-01-21 11:45:40.974863: step: 1392/530, loss: 0.00019254683866165578
2023-01-21 11:45:42.095005: step: 1396/530, loss: 0.001980805303901434
2023-01-21 11:45:43.215183: step: 1400/530, loss: 0.0058116912841796875
2023-01-21 11:45:44.347232: step: 1404/530, loss: 0.03374233469367027
2023-01-21 11:45:45.456091: step: 1408/530, loss: 0.007123374845832586
2023-01-21 11:45:46.575660: step: 1412/530, loss: 0.002434301422908902
2023-01-21 11:45:47.707775: step: 1416/530, loss: 0.01960582658648491
2023-01-21 11:45:48.817491: step: 1420/530, loss: 0.03069124184548855
2023-01-21 11:45:49.930597: step: 1424/530, loss: 0.05376854166388512
2023-01-21 11:45:51.056200: step: 1428/530, loss: 3.280639793956652e-05
2023-01-21 11:45:52.174708: step: 1432/530, loss: 0.29156073927879333
2023-01-21 11:45:53.289216: step: 1436/530, loss: 0.0010064125526696444
2023-01-21 11:45:54.386592: step: 1440/530, loss: 0.016932297497987747
2023-01-21 11:45:55.492440: step: 1444/530, loss: 2.2792815798311494e-05
2023-01-21 11:45:56.637911: step: 1448/530, loss: 0.00266609201207757
2023-01-21 11:45:57.782411: step: 1452/530, loss: 0.0023176195099949837
2023-01-21 11:45:58.893860: step: 1456/530, loss: 0.002462196396663785
2023-01-21 11:45:59.982937: step: 1460/530, loss: 0.0015404701698571444
2023-01-21 11:46:01.086288: step: 1464/530, loss: 0.00019922255887649953
2023-01-21 11:46:02.211972: step: 1468/530, loss: 0.0035831450950354338
2023-01-21 11:46:03.365624: step: 1472/530, loss: 0.012120532803237438
2023-01-21 11:46:04.485163: step: 1476/530, loss: 0.0002880096435546875
2023-01-21 11:46:05.606832: step: 1480/530, loss: 0.004423332400619984
2023-01-21 11:46:06.727092: step: 1484/530, loss: 0.004905891139060259
2023-01-21 11:46:07.847317: step: 1488/530, loss: 0.0012183189392089844
2023-01-21 11:46:08.961406: step: 1492/530, loss: 0.05871410667896271
2023-01-21 11:46:10.091667: step: 1496/530, loss: 0.1794639676809311
2023-01-21 11:46:11.202718: step: 1500/530, loss: 0.048838332295417786
2023-01-21 11:46:12.328298: step: 1504/530, loss: 0.00937876757234335
2023-01-21 11:46:13.462804: step: 1508/530, loss: 0.07528610527515411
2023-01-21 11:46:14.594917: step: 1512/530, loss: 0.04521942511200905
2023-01-21 11:46:15.731140: step: 1516/530, loss: 0.009680652990937233
2023-01-21 11:46:16.861026: step: 1520/530, loss: 0.00779800396412611
2023-01-21 11:46:17.976561: step: 1524/530, loss: 0.2331068068742752
2023-01-21 11:46:19.088633: step: 1528/530, loss: 5.064010474598035e-05
2023-01-21 11:46:20.179107: step: 1532/530, loss: 0.05807342752814293
2023-01-21 11:46:21.307645: step: 1536/530, loss: 0.0001390457182424143
2023-01-21 11:46:22.440254: step: 1540/530, loss: 0.0031814100220799446
2023-01-21 11:46:23.563853: step: 1544/530, loss: 0.023312855511903763
2023-01-21 11:46:24.670740: step: 1548/530, loss: 0.016035079956054688
2023-01-21 11:46:25.812216: step: 1552/530, loss: 0.00011692046973621473
2023-01-21 11:46:26.914662: step: 1556/530, loss: 0.0001737594575388357
2023-01-21 11:46:28.041579: step: 1560/530, loss: 0.053319789469242096
2023-01-21 11:46:29.181118: step: 1564/530, loss: 0.025724982842803
2023-01-21 11:46:30.362563: step: 1568/530, loss: 0.00043697358341887593
2023-01-21 11:46:31.483691: step: 1572/530, loss: 0.0449950248003006
2023-01-21 11:46:32.601573: step: 1576/530, loss: 0.00134449009783566
2023-01-21 11:46:33.741333: step: 1580/530, loss: 0.008546257391571999
2023-01-21 11:46:34.856127: step: 1584/530, loss: 0.003720760578289628
2023-01-21 11:46:36.020729: step: 1588/530, loss: 0.026486970484256744
2023-01-21 11:46:37.128270: step: 1592/530, loss: 0.0810934528708458
2023-01-21 11:46:38.257010: step: 1596/530, loss: 0.07892217487096786
2023-01-21 11:46:39.385205: step: 1600/530, loss: 0.0626898780465126
2023-01-21 11:46:40.498362: step: 1604/530, loss: 0.020459746941924095
2023-01-21 11:46:41.627345: step: 1608/530, loss: 0.003245449159294367
2023-01-21 11:46:42.744257: step: 1612/530, loss: 0.015804052352905273
2023-01-21 11:46:43.906022: step: 1616/530, loss: 0.02175426483154297
2023-01-21 11:46:45.028849: step: 1620/530, loss: 0.005942916963249445
2023-01-21 11:46:46.158742: step: 1624/530, loss: 0.03407726436853409
2023-01-21 11:46:47.270787: step: 1628/530, loss: 0.0007228851318359375
2023-01-21 11:46:48.396206: step: 1632/530, loss: 0.05168113857507706
2023-01-21 11:46:49.505991: step: 1636/530, loss: 0.0023353577125817537
2023-01-21 11:46:50.622709: step: 1640/530, loss: 0.05115985870361328
2023-01-21 11:46:51.768640: step: 1644/530, loss: 0.002491426421329379
2023-01-21 11:46:52.870233: step: 1648/530, loss: 0.0030633925925940275
2023-01-21 11:46:53.987964: step: 1652/530, loss: 0.009731292724609375
2023-01-21 11:46:55.134931: step: 1656/530, loss: 0.017003823071718216
2023-01-21 11:46:56.262768: step: 1660/530, loss: 0.06108655780553818
2023-01-21 11:46:57.365077: step: 1664/530, loss: 0.0021059035789221525
2023-01-21 11:46:58.508460: step: 1668/530, loss: 0.004141617100685835
2023-01-21 11:46:59.643806: step: 1672/530, loss: 0.035585831850767136
2023-01-21 11:47:00.776084: step: 1676/530, loss: 0.03586731106042862
2023-01-21 11:47:01.950786: step: 1680/530, loss: 0.0021348954178392887
2023-01-21 11:47:03.135061: step: 1684/530, loss: 0.017817020416259766
2023-01-21 11:47:04.257596: step: 1688/530, loss: 0.02136058919131756
2023-01-21 11:47:05.371943: step: 1692/530, loss: 0.04454679787158966
2023-01-21 11:47:06.457762: step: 1696/530, loss: 0.00857851468026638
2023-01-21 11:47:07.602377: step: 1700/530, loss: 0.053299762308597565
2023-01-21 11:47:08.734487: step: 1704/530, loss: 0.015199661254882812
2023-01-21 11:47:09.852497: step: 1708/530, loss: 0.017504120245575905
2023-01-21 11:47:10.974644: step: 1712/530, loss: 0.0019131660228595138
2023-01-21 11:47:12.077074: step: 1716/530, loss: 0.0006999016040936112
2023-01-21 11:47:13.223936: step: 1720/530, loss: 0.014224052429199219
2023-01-21 11:47:14.356251: step: 1724/530, loss: 0.002784347627311945
2023-01-21 11:47:15.475444: step: 1728/530, loss: 0.019688988104462624
2023-01-21 11:47:16.588417: step: 1732/530, loss: 0.004349899478256702
2023-01-21 11:47:17.717960: step: 1736/530, loss: 0.0033686638344079256
2023-01-21 11:47:18.839890: step: 1740/530, loss: 0.011678695678710938
2023-01-21 11:47:19.942733: step: 1744/530, loss: 0.036286164075136185
2023-01-21 11:47:21.080423: step: 1748/530, loss: 0.00017337800818495452
2023-01-21 11:47:22.212034: step: 1752/530, loss: 0.0018768310546875
2023-01-21 11:47:23.340806: step: 1756/530, loss: 0.04755065590143204
2023-01-21 11:47:24.488429: step: 1760/530, loss: 0.03820991516113281
2023-01-21 11:47:25.604576: step: 1764/530, loss: 0.0008551597711630166
2023-01-21 11:47:26.759749: step: 1768/530, loss: 0.003847789950668812
2023-01-21 11:47:27.881840: step: 1772/530, loss: 0.003237438155338168
2023-01-21 11:47:29.002917: step: 1776/530, loss: 0.00023202896409202367
2023-01-21 11:47:30.162296: step: 1780/530, loss: 0.04678459092974663
2023-01-21 11:47:31.275891: step: 1784/530, loss: 0.0011911392211914062
2023-01-21 11:47:32.450429: step: 1788/530, loss: 0.05273570865392685
2023-01-21 11:47:33.551579: step: 1792/530, loss: 0.011806010268628597
2023-01-21 11:47:34.685123: step: 1796/530, loss: 0.018580103293061256
2023-01-21 11:47:35.802826: step: 1800/530, loss: 0.0010605811839923263
2023-01-21 11:47:36.920035: step: 1804/530, loss: 0.07782287895679474
2023-01-21 11:47:38.048422: step: 1808/530, loss: 0.006934165954589844
2023-01-21 11:47:39.146269: step: 1812/530, loss: 0.06661901623010635
2023-01-21 11:47:40.249542: step: 1816/530, loss: 0.005472755525261164
2023-01-21 11:47:41.370785: step: 1820/530, loss: 0.0033046724274754524
2023-01-21 11:47:42.472106: step: 1824/530, loss: 0.004302788060158491
2023-01-21 11:47:43.600525: step: 1828/530, loss: 0.0441526398062706
2023-01-21 11:47:44.712122: step: 1832/530, loss: 0.019944049417972565
2023-01-21 11:47:45.848821: step: 1836/530, loss: 0.0746222510933876
2023-01-21 11:47:46.953411: step: 1840/530, loss: 0.004243755247443914
2023-01-21 11:47:48.091446: step: 1844/530, loss: 0.0036203383933752775
2023-01-21 11:47:49.212592: step: 1848/530, loss: 0.0005895614740438759
2023-01-21 11:47:50.332761: step: 1852/530, loss: 0.035605430603027344
2023-01-21 11:47:51.445647: step: 1856/530, loss: 0.0003087043878622353
2023-01-21 11:47:52.582955: step: 1860/530, loss: 0.04499950632452965
2023-01-21 11:47:53.722205: step: 1864/530, loss: 0.0010932445293292403
2023-01-21 11:47:54.817517: step: 1868/530, loss: 0.001951885293237865
2023-01-21 11:47:55.942084: step: 1872/530, loss: 0.049657247960567474
2023-01-21 11:47:57.077472: step: 1876/530, loss: 0.024089623242616653
2023-01-21 11:47:58.203082: step: 1880/530, loss: 0.04950447380542755
2023-01-21 11:47:59.334467: step: 1884/530, loss: 0.007705879397690296
2023-01-21 11:48:00.460155: step: 1888/530, loss: 0.03236236423254013
2023-01-21 11:48:01.583844: step: 1892/530, loss: 0.05093926191329956
2023-01-21 11:48:02.683918: step: 1896/530, loss: 0.05753746256232262
2023-01-21 11:48:03.786956: step: 1900/530, loss: 0.0002115249662892893
2023-01-21 11:48:04.892847: step: 1904/530, loss: 0.0075972555205225945
2023-01-21 11:48:06.042800: step: 1908/530, loss: 0.05229062959551811
2023-01-21 11:48:07.164570: step: 1912/530, loss: 0.0026124001014977694
2023-01-21 11:48:08.257257: step: 1916/530, loss: 0.00786886177957058
2023-01-21 11:48:09.361322: step: 1920/530, loss: 0.02142028883099556
2023-01-21 11:48:10.473595: step: 1924/530, loss: 0.0021814347710460424
2023-01-21 11:48:11.569709: step: 1928/530, loss: 0.00223884591832757
2023-01-21 11:48:12.700297: step: 1932/530, loss: 0.02219877392053604
2023-01-21 11:48:13.838896: step: 1936/530, loss: 0.0005825996631756425
2023-01-21 11:48:14.986418: step: 1940/530, loss: 0.002773761749267578
2023-01-21 11:48:16.101267: step: 1944/530, loss: 0.0045144082978367805
2023-01-21 11:48:17.228745: step: 1948/530, loss: 0.02409515529870987
2023-01-21 11:48:18.333722: step: 1952/530, loss: 0.0006704331026412547
2023-01-21 11:48:19.437700: step: 1956/530, loss: 0.004224204923957586
2023-01-21 11:48:20.536301: step: 1960/530, loss: 0.0015434264205396175
2023-01-21 11:48:21.654554: step: 1964/530, loss: 0.040897272527217865
2023-01-21 11:48:22.752903: step: 1968/530, loss: 0.10474738478660583
2023-01-21 11:48:23.895030: step: 1972/530, loss: 0.01076211966574192
2023-01-21 11:48:25.019292: step: 1976/530, loss: 0.0190963763743639
2023-01-21 11:48:26.150219: step: 1980/530, loss: 0.06103458255529404
2023-01-21 11:48:27.266088: step: 1984/530, loss: 0.02944965288043022
2023-01-21 11:48:28.373846: step: 1988/530, loss: 0.0020330429542809725
2023-01-21 11:48:29.489363: step: 1992/530, loss: 0.0001300811709370464
2023-01-21 11:48:30.629857: step: 1996/530, loss: 0.1824359893798828
2023-01-21 11:48:31.746280: step: 2000/530, loss: 0.016443466767668724
2023-01-21 11:48:32.876335: step: 2004/530, loss: 0.03230753168463707
2023-01-21 11:48:34.003254: step: 2008/530, loss: 0.00783538818359375
2023-01-21 11:48:35.105937: step: 2012/530, loss: 0.024396903812885284
2023-01-21 11:48:36.218165: step: 2016/530, loss: 0.0010374069679528475
2023-01-21 11:48:37.349853: step: 2020/530, loss: 0.007400131318718195
2023-01-21 11:48:38.498193: step: 2024/530, loss: 0.01990509033203125
2023-01-21 11:48:39.620095: step: 2028/530, loss: 0.0026630403008311987
2023-01-21 11:48:40.733983: step: 2032/530, loss: 0.0393676795065403
2023-01-21 11:48:41.843988: step: 2036/530, loss: 0.021541118621826172
2023-01-21 11:48:42.959496: step: 2040/530, loss: 0.01589679718017578
2023-01-21 11:48:44.089589: step: 2044/530, loss: 0.009590482339262962
2023-01-21 11:48:45.225459: step: 2048/530, loss: 0.034490346908569336
2023-01-21 11:48:46.362668: step: 2052/530, loss: 0.015813540667295456
2023-01-21 11:48:47.470461: step: 2056/530, loss: 0.001965808914974332
2023-01-21 11:48:48.582070: step: 2060/530, loss: 2.250671423098538e-05
2023-01-21 11:48:49.701446: step: 2064/530, loss: 0.044591713696718216
2023-01-21 11:48:50.839695: step: 2068/530, loss: 0.008554312400519848
2023-01-21 11:48:51.959852: step: 2072/530, loss: 0.00414619455114007
2023-01-21 11:48:53.105719: step: 2076/530, loss: 0.005199432838708162
2023-01-21 11:48:54.259571: step: 2080/530, loss: 0.0007673263316974044
2023-01-21 11:48:55.400911: step: 2084/530, loss: 0.013872337527573109
2023-01-21 11:48:56.551700: step: 2088/530, loss: 0.020048143342137337
2023-01-21 11:48:57.664967: step: 2092/530, loss: 0.009788990020751953
2023-01-21 11:48:58.781555: step: 2096/530, loss: 0.0009181022178381681
2023-01-21 11:48:59.945998: step: 2100/530, loss: 0.007423591800034046
2023-01-21 11:49:01.071264: step: 2104/530, loss: 0.007729626260697842
2023-01-21 11:49:02.217187: step: 2108/530, loss: 0.008791351690888405
2023-01-21 11:49:03.332466: step: 2112/530, loss: 0.022530268877744675
2023-01-21 11:49:04.465606: step: 2116/530, loss: 0.002525806427001953
2023-01-21 11:49:05.666364: step: 2120/530, loss: 0.016582202166318893
==================================================
Loss: 0.027
--------------------
Dev: {'event': {'p': 0.5865580448065173, 'r': 0.7669773635153129, 'f1': 0.6647432198499712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6027874564459931, 'r': 0.7908571428571428, 'f1': 0.6841324765200197}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5764705882352941, 'r': 0.9074074074074074, 'f1': 0.7050359712230215}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
Russian: {'event': {'p': 0.4186046511627907, 'r': 0.5, 'f1': 0.45569620253164556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 19
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:49:46.316772: step: 4/530, loss: 0.0006170272827148438
2023-01-21 11:49:47.452108: step: 8/530, loss: 0.008962727151811123
2023-01-21 11:49:48.602538: step: 12/530, loss: 0.0009142875787802041
2023-01-21 11:49:49.730358: step: 16/530, loss: 0.0021963119506835938
2023-01-21 11:49:50.850340: step: 20/530, loss: 0.004263448994606733
2023-01-21 11:49:51.966815: step: 24/530, loss: 0.024438858032226562
2023-01-21 11:49:53.087442: step: 28/530, loss: 0.07940807938575745
2023-01-21 11:49:54.205589: step: 32/530, loss: 0.00513458251953125
2023-01-21 11:49:55.325198: step: 36/530, loss: 0.004402923863381147
2023-01-21 11:49:56.461841: step: 40/530, loss: 0.003044223878532648
2023-01-21 11:49:57.592844: step: 44/530, loss: 0.016464948654174805
2023-01-21 11:49:58.741824: step: 48/530, loss: 0.008777236565947533
2023-01-21 11:49:59.870809: step: 52/530, loss: 0.001104641007259488
2023-01-21 11:50:00.966401: step: 56/530, loss: 0.008661651983857155
2023-01-21 11:50:02.109999: step: 60/530, loss: 0.022327184677124023
2023-01-21 11:50:03.183862: step: 64/530, loss: 0.0633670836687088
2023-01-21 11:50:04.302316: step: 68/530, loss: 0.004669189453125
2023-01-21 11:50:05.442375: step: 72/530, loss: 0.0003538132004905492
2023-01-21 11:50:06.565553: step: 76/530, loss: 0.03853330388665199
2023-01-21 11:50:07.698223: step: 80/530, loss: 0.007919502444565296
2023-01-21 11:50:08.834246: step: 84/530, loss: 0.027817536145448685
2023-01-21 11:50:09.955492: step: 88/530, loss: 0.012743568047881126
2023-01-21 11:50:11.087727: step: 92/530, loss: 0.03397679328918457
2023-01-21 11:50:12.245404: step: 96/530, loss: 0.0014127731556072831
2023-01-21 11:50:13.357145: step: 100/530, loss: 0.0008743763319216669
2023-01-21 11:50:14.479564: step: 104/530, loss: 0.04171466827392578
2023-01-21 11:50:15.599958: step: 108/530, loss: 0.049958229064941406
2023-01-21 11:50:16.712781: step: 112/530, loss: 0.006876373663544655
2023-01-21 11:50:17.825060: step: 116/530, loss: 0.01923818700015545
2023-01-21 11:50:18.936321: step: 120/530, loss: 0.00732765207067132
2023-01-21 11:50:20.086502: step: 124/530, loss: 0.008611107245087624
2023-01-21 11:50:21.211726: step: 128/530, loss: 0.0006887793424539268
2023-01-21 11:50:22.338179: step: 132/530, loss: 0.00702400179579854
2023-01-21 11:50:23.473555: step: 136/530, loss: 0.025534389540553093
2023-01-21 11:50:24.560947: step: 140/530, loss: 0.041330814361572266
2023-01-21 11:50:25.633594: step: 144/530, loss: 0.001424017595127225
2023-01-21 11:50:26.768407: step: 148/530, loss: 0.007486725226044655
2023-01-21 11:50:27.867268: step: 152/530, loss: 0.03888645023107529
2023-01-21 11:50:28.976140: step: 156/530, loss: 0.0001066207914846018
2023-01-21 11:50:30.089968: step: 160/530, loss: 0.153453066945076
2023-01-21 11:50:31.195199: step: 164/530, loss: 0.016442155465483665
2023-01-21 11:50:32.344155: step: 168/530, loss: 0.03246812894940376
2023-01-21 11:50:33.480379: step: 172/530, loss: 0.017256736755371094
2023-01-21 11:50:34.583861: step: 176/530, loss: 0.0009941101307049394
2023-01-21 11:50:35.709945: step: 180/530, loss: -2.2029877072782256e-05
2023-01-21 11:50:36.824359: step: 184/530, loss: 0.0015310286544263363
2023-01-21 11:50:37.944630: step: 188/530, loss: 0.06053924560546875
2023-01-21 11:50:39.060554: step: 192/530, loss: 0.6747072339057922
2023-01-21 11:50:40.214485: step: 196/530, loss: 0.013753890991210938
2023-01-21 11:50:41.326842: step: 200/530, loss: 0.011660766787827015
2023-01-21 11:50:42.429779: step: 204/530, loss: 0.10018176585435867
2023-01-21 11:50:43.543543: step: 208/530, loss: 5.4168704082258046e-05
2023-01-21 11:50:44.674977: step: 212/530, loss: 0.026498936116695404
2023-01-21 11:50:45.788499: step: 216/530, loss: 0.0007252693176269531
2023-01-21 11:50:46.929207: step: 220/530, loss: 0.060758400708436966
2023-01-21 11:50:48.069008: step: 224/530, loss: 0.027014732360839844
2023-01-21 11:50:49.202643: step: 228/530, loss: 0.00015926362539175898
2023-01-21 11:50:50.344878: step: 232/530, loss: 0.005106544587761164
2023-01-21 11:50:51.468324: step: 236/530, loss: 0.01175379753112793
2023-01-21 11:50:52.606391: step: 240/530, loss: 0.0009660720825195312
2023-01-21 11:50:53.736398: step: 244/530, loss: 0.010135556571185589
2023-01-21 11:50:54.864812: step: 248/530, loss: 0.01663360558450222
2023-01-21 11:50:55.965971: step: 252/530, loss: 0.006316948216408491
2023-01-21 11:50:57.063325: step: 256/530, loss: 0.004391288850456476
2023-01-21 11:50:58.194819: step: 260/530, loss: 0.07250719517469406
2023-01-21 11:50:59.337816: step: 264/530, loss: 0.0003520965692587197
2023-01-21 11:51:00.464433: step: 268/530, loss: 0.0043006897903978825
2023-01-21 11:51:01.581257: step: 272/530, loss: 0.007274055853486061
2023-01-21 11:51:02.699451: step: 276/530, loss: 0.0016317367553710938
2023-01-21 11:51:03.807962: step: 280/530, loss: 0.08037243038415909
2023-01-21 11:51:04.912472: step: 284/530, loss: 0.012360096909105778
2023-01-21 11:51:06.036600: step: 288/530, loss: 0.006418419070541859
2023-01-21 11:51:07.188593: step: 292/530, loss: 0.004541206639260054
2023-01-21 11:51:08.304772: step: 296/530, loss: 0.002791118808090687
2023-01-21 11:51:09.420244: step: 300/530, loss: 5.607604907709174e-05
2023-01-21 11:51:10.541489: step: 304/530, loss: 0.0010190963512286544
2023-01-21 11:51:11.646164: step: 308/530, loss: 0.03766059875488281
2023-01-21 11:51:12.736635: step: 312/530, loss: 0.08749494701623917
2023-01-21 11:51:13.869982: step: 316/530, loss: 0.039907075464725494
2023-01-21 11:51:14.999403: step: 320/530, loss: 0.0023992538917809725
2023-01-21 11:51:16.132877: step: 324/530, loss: 0.005767917726188898
2023-01-21 11:51:17.260767: step: 328/530, loss: 0.018404768779873848
2023-01-21 11:51:18.387757: step: 332/530, loss: 0.016777800396084785
2023-01-21 11:51:19.498978: step: 336/530, loss: 0.00243034353479743
2023-01-21 11:51:20.617386: step: 340/530, loss: 0.0010665893787518144
2023-01-21 11:51:21.752650: step: 344/530, loss: 0.0024063109885901213
2023-01-21 11:51:22.867633: step: 348/530, loss: 0.02555275149643421
2023-01-21 11:51:24.012721: step: 352/530, loss: 0.02347269095480442
2023-01-21 11:51:25.119884: step: 356/530, loss: 0.22958174347877502
2023-01-21 11:51:26.227153: step: 360/530, loss: 0.00014390944852493703
2023-01-21 11:51:27.348366: step: 364/530, loss: 0.0022373199462890625
2023-01-21 11:51:28.452639: step: 368/530, loss: 0.009851074777543545
2023-01-21 11:51:29.602698: step: 372/530, loss: 0.02221093326807022
2023-01-21 11:51:30.730426: step: 376/530, loss: 0.00037384033203125
2023-01-21 11:51:31.853743: step: 380/530, loss: 7.655620720470324e-05
2023-01-21 11:51:32.969983: step: 384/530, loss: 0.0001773834228515625
2023-01-21 11:51:34.059560: step: 388/530, loss: 0.005497884936630726
2023-01-21 11:51:35.165126: step: 392/530, loss: 0.0002777099725790322
2023-01-21 11:51:36.307062: step: 396/530, loss: 0.03215827792882919
2023-01-21 11:51:37.457324: step: 400/530, loss: 0.005587005987763405
2023-01-21 11:51:38.587413: step: 404/530, loss: 0.05372406914830208
2023-01-21 11:51:39.704587: step: 408/530, loss: 0.08013200759887695
2023-01-21 11:51:40.801596: step: 412/530, loss: 0.006840371992439032
2023-01-21 11:51:42.029059: step: 416/530, loss: 0.0003841400321107358
2023-01-21 11:51:43.137631: step: 420/530, loss: 1.9574166799429804e-05
2023-01-21 11:51:44.241137: step: 424/530, loss: 0.0021209716796875
2023-01-21 11:51:45.380805: step: 428/530, loss: 0.00475387554615736
2023-01-21 11:51:46.503663: step: 432/530, loss: 0.00013608933659270406
2023-01-21 11:51:47.618453: step: 436/530, loss: 4.024505687993951e-05
2023-01-21 11:51:48.761923: step: 440/530, loss: 0.002505397889763117
2023-01-21 11:51:49.884554: step: 444/530, loss: 0.010141611099243164
2023-01-21 11:51:51.031082: step: 448/530, loss: 1.926422191900201e-05
2023-01-21 11:51:52.153058: step: 452/530, loss: 0.0442357063293457
2023-01-21 11:51:53.316163: step: 456/530, loss: 0.1211620345711708
2023-01-21 11:51:54.458085: step: 460/530, loss: 0.02894299104809761
2023-01-21 11:51:55.571932: step: 464/530, loss: 0.0004015445592813194
2023-01-21 11:51:56.702538: step: 468/530, loss: 0.007358932867646217
2023-01-21 11:51:57.866594: step: 472/530, loss: 0.00270500173792243
2023-01-21 11:51:59.003769: step: 476/530, loss: 0.0007340431329794228
2023-01-21 11:52:00.128955: step: 480/530, loss: 0.027745626866817474
2023-01-21 11:52:01.304076: step: 484/530, loss: 0.11460423469543457
2023-01-21 11:52:02.420979: step: 488/530, loss: 0.007725572679191828
2023-01-21 11:52:03.569085: step: 492/530, loss: 0.0024312972091138363
2023-01-21 11:52:04.669544: step: 496/530, loss: 0.012563705444335938
2023-01-21 11:52:05.768753: step: 500/530, loss: 0.011520194821059704
2023-01-21 11:52:06.862237: step: 504/530, loss: 0.04189472272992134
2023-01-21 11:52:07.966409: step: 508/530, loss: 0.0007476806640625
2023-01-21 11:52:09.060994: step: 512/530, loss: 0.009466171264648438
2023-01-21 11:52:10.192936: step: 516/530, loss: 0.011503219604492188
2023-01-21 11:52:11.292728: step: 520/530, loss: 0.03649614006280899
2023-01-21 11:52:12.424589: step: 524/530, loss: 0.0006355285877361894
2023-01-21 11:52:13.523644: step: 528/530, loss: 0.02817249298095703
2023-01-21 11:52:14.628755: step: 532/530, loss: 0.013330173678696156
2023-01-21 11:52:15.750812: step: 536/530, loss: 0.015714168548583984
2023-01-21 11:52:16.861584: step: 540/530, loss: 0.007248115725815296
2023-01-21 11:52:17.982856: step: 544/530, loss: 0.00024785997811704874
2023-01-21 11:52:19.102984: step: 548/530, loss: 0.007177925202995539
2023-01-21 11:52:20.251028: step: 552/530, loss: 0.0022053720895200968
2023-01-21 11:52:21.360962: step: 556/530, loss: 1.389614462852478
2023-01-21 11:52:22.503124: step: 560/530, loss: 0.0018544197082519531
2023-01-21 11:52:23.600405: step: 564/530, loss: 0.023641683161258698
2023-01-21 11:52:24.701966: step: 568/530, loss: 0.012304306030273438
2023-01-21 11:52:25.794393: step: 572/530, loss: 0.027260446920990944
2023-01-21 11:52:26.894292: step: 576/530, loss: 0.00352401752024889
2023-01-21 11:52:27.998765: step: 580/530, loss: 0.08416776359081268
2023-01-21 11:52:29.143834: step: 584/530, loss: 0.011368370614945889
2023-01-21 11:52:30.253015: step: 588/530, loss: 0.0010231973137706518
2023-01-21 11:52:31.351266: step: 592/530, loss: 6.418228440452367e-05
2023-01-21 11:52:32.446626: step: 596/530, loss: 0.00793533306568861
2023-01-21 11:52:33.540820: step: 600/530, loss: 0.001327133271843195
2023-01-21 11:52:34.686401: step: 604/530, loss: 0.017234230414032936
2023-01-21 11:52:35.807363: step: 608/530, loss: 0.0009544373024255037
2023-01-21 11:52:36.928632: step: 612/530, loss: 0.017559148371219635
2023-01-21 11:52:38.063415: step: 616/530, loss: 0.027152730152010918
2023-01-21 11:52:39.174845: step: 620/530, loss: 0.01896820217370987
2023-01-21 11:52:40.280744: step: 624/530, loss: 0.03765459358692169
2023-01-21 11:52:41.364528: step: 628/530, loss: 0.00030541419982910156
2023-01-21 11:52:42.478704: step: 632/530, loss: 0.016469767317175865
2023-01-21 11:52:43.612036: step: 636/530, loss: 0.03996772691607475
2023-01-21 11:52:44.761518: step: 640/530, loss: 0.01603841781616211
2023-01-21 11:52:45.891958: step: 644/530, loss: 0.16668447852134705
2023-01-21 11:52:47.011978: step: 648/530, loss: 0.0003618240589275956
2023-01-21 11:52:48.131264: step: 652/530, loss: 0.003962898161262274
2023-01-21 11:52:49.233571: step: 656/530, loss: 0.0008433341863565147
2023-01-21 11:52:50.348257: step: 660/530, loss: 0.004819011315703392
2023-01-21 11:52:51.514435: step: 664/530, loss: 0.20168742537498474
2023-01-21 11:52:52.620077: step: 668/530, loss: 0.0016164779663085938
2023-01-21 11:52:53.759342: step: 672/530, loss: 0.005039215553551912
2023-01-21 11:52:54.907115: step: 676/530, loss: 0.04378318786621094
2023-01-21 11:52:56.034213: step: 680/530, loss: 0.006479168310761452
2023-01-21 11:52:57.152989: step: 684/530, loss: 0.023687170818448067
2023-01-21 11:52:58.289104: step: 688/530, loss: 0.001493263291195035
2023-01-21 11:52:59.429896: step: 692/530, loss: 0.00014171600923873484
2023-01-21 11:53:00.510650: step: 696/530, loss: 0.0008190155494958162
2023-01-21 11:53:01.628096: step: 700/530, loss: 0.00030174257699400187
2023-01-21 11:53:02.737914: step: 704/530, loss: 1.4972685676184483e-05
2023-01-21 11:53:03.864599: step: 708/530, loss: 0.004610443487763405
2023-01-21 11:53:04.975955: step: 712/530, loss: 0.033678632229566574
2023-01-21 11:53:06.113588: step: 716/530, loss: 0.01068346481770277
2023-01-21 11:53:07.213396: step: 720/530, loss: 0.021994877606630325
2023-01-21 11:53:08.303924: step: 724/530, loss: 0.02668910101056099
2023-01-21 11:53:09.401215: step: 728/530, loss: 0.036435317248106
2023-01-21 11:53:10.521521: step: 732/530, loss: 0.0004341125313658267
2023-01-21 11:53:11.625118: step: 736/530, loss: 0.000354766845703125
2023-01-21 11:53:12.778280: step: 740/530, loss: 0.001425075577571988
2023-01-21 11:53:13.906316: step: 744/530, loss: 0.023249246180057526
2023-01-21 11:53:15.013123: step: 748/530, loss: 0.0007686614990234375
2023-01-21 11:53:16.110790: step: 752/530, loss: 0.025387166067957878
2023-01-21 11:53:17.230566: step: 756/530, loss: 0.0004726409970317036
2023-01-21 11:53:18.355384: step: 760/530, loss: 0.038896940648555756
2023-01-21 11:53:19.474508: step: 764/530, loss: 0.00043277739314362407
2023-01-21 11:53:20.600815: step: 768/530, loss: 0.0034386159386485815
2023-01-21 11:53:21.731750: step: 772/530, loss: 0.029145622625947
2023-01-21 11:53:22.843343: step: 776/530, loss: 0.0018712998135015368
2023-01-21 11:53:23.962285: step: 780/530, loss: 0.0021556855645030737
2023-01-21 11:53:25.081594: step: 784/530, loss: 0.015527726151049137
2023-01-21 11:53:26.179773: step: 788/530, loss: 0.0001493453892180696
2023-01-21 11:53:27.301910: step: 792/530, loss: 4.281997826183215e-05
2023-01-21 11:53:28.440117: step: 796/530, loss: 0.01034460123628378
2023-01-21 11:53:29.558159: step: 800/530, loss: 0.006088066380470991
2023-01-21 11:53:30.683386: step: 804/530, loss: 0.02073812484741211
2023-01-21 11:53:31.800581: step: 808/530, loss: 0.0002723693905863911
2023-01-21 11:53:32.927022: step: 812/530, loss: 0.001817989395931363
2023-01-21 11:53:34.052848: step: 816/530, loss: 0.028634263202548027
2023-01-21 11:53:35.193034: step: 820/530, loss: 0.0005810738075524569
2023-01-21 11:53:36.343963: step: 824/530, loss: 0.0037511824630200863
2023-01-21 11:53:37.460275: step: 828/530, loss: 0.00021467207989189774
2023-01-21 11:53:38.570458: step: 832/530, loss: 0.026242733001708984
2023-01-21 11:53:39.693111: step: 836/530, loss: 0.03699150308966637
2023-01-21 11:53:40.803709: step: 840/530, loss: 0.003712272737175226
2023-01-21 11:53:41.926365: step: 844/530, loss: 0.0003410339413676411
2023-01-21 11:53:43.062871: step: 848/530, loss: 0.0019670487381517887
2023-01-21 11:53:44.196855: step: 852/530, loss: 0.008776617236435413
2023-01-21 11:53:45.332798: step: 856/530, loss: 0.00881042517721653
2023-01-21 11:53:46.471738: step: 860/530, loss: 0.0010787963401526213
2023-01-21 11:53:47.601198: step: 864/530, loss: 4.091262962901965e-05
2023-01-21 11:53:48.725718: step: 868/530, loss: 0.0031227110885083675
2023-01-21 11:53:49.847963: step: 872/530, loss: 0.00020532608323264867
2023-01-21 11:53:50.967014: step: 876/530, loss: 0.056491851806640625
2023-01-21 11:53:52.129955: step: 880/530, loss: 0.00961084384471178
2023-01-21 11:53:53.231994: step: 884/530, loss: 0.009857368655502796
2023-01-21 11:53:54.368317: step: 888/530, loss: 0.8669643402099609
2023-01-21 11:53:55.501923: step: 892/530, loss: 0.0165266040712595
2023-01-21 11:53:56.596646: step: 896/530, loss: 0.012455177493393421
2023-01-21 11:53:57.721776: step: 900/530, loss: 0.12309174239635468
2023-01-21 11:53:58.822780: step: 904/530, loss: 0.011877631768584251
2023-01-21 11:53:59.940589: step: 908/530, loss: 0.03761015087366104
2023-01-21 11:54:01.053924: step: 912/530, loss: 0.003395461943000555
2023-01-21 11:54:02.194023: step: 916/530, loss: 0.02661123313009739
2023-01-21 11:54:03.325083: step: 920/530, loss: 8.869171142578125e-05
2023-01-21 11:54:04.470278: step: 924/530, loss: 0.001127052353695035
2023-01-21 11:54:05.568822: step: 928/530, loss: 0.0001392364501953125
2023-01-21 11:54:06.676384: step: 932/530, loss: 0.0048828125
2023-01-21 11:54:07.790067: step: 936/530, loss: 0.01406564749777317
2023-01-21 11:54:08.928137: step: 940/530, loss: 0.04362945631146431
2023-01-21 11:54:10.066263: step: 944/530, loss: 0.009560775943100452
2023-01-21 11:54:11.183481: step: 948/530, loss: 0.005719184875488281
2023-01-21 11:54:12.309921: step: 952/530, loss: 0.03713631629943848
2023-01-21 11:54:13.425832: step: 956/530, loss: 0.005797004792839289
2023-01-21 11:54:14.543991: step: 960/530, loss: 4.291534423828125e-06
2023-01-21 11:54:15.688850: step: 964/530, loss: 3.3998490835074335e-05
2023-01-21 11:54:16.794592: step: 968/530, loss: 0.0008330345153808594
2023-01-21 11:54:17.885759: step: 972/530, loss: 0.00067729945294559
2023-01-21 11:54:18.964669: step: 976/530, loss: 0.02462148666381836
2023-01-21 11:54:20.071938: step: 980/530, loss: 0.02042408101260662
2023-01-21 11:54:21.157331: step: 984/530, loss: 0.0011967660393565893
2023-01-21 11:54:22.266650: step: 988/530, loss: 0.04451408237218857
2023-01-21 11:54:23.371874: step: 992/530, loss: 0.06557798385620117
2023-01-21 11:54:24.511578: step: 996/530, loss: 0.016010476276278496
2023-01-21 11:54:25.630801: step: 1000/530, loss: 0.04093341901898384
2023-01-21 11:54:26.754417: step: 1004/530, loss: 0.002197074703872204
2023-01-21 11:54:27.874936: step: 1008/530, loss: 0.047245025634765625
2023-01-21 11:54:28.995958: step: 1012/530, loss: 0.003819370409473777
2023-01-21 11:54:30.125527: step: 1016/530, loss: 0.00243206019513309
2023-01-21 11:54:31.243886: step: 1020/530, loss: 0.003633451648056507
2023-01-21 11:54:32.375044: step: 1024/530, loss: 0.018474770709872246
2023-01-21 11:54:33.527705: step: 1028/530, loss: 0.00106306083034724
2023-01-21 11:54:34.645171: step: 1032/530, loss: 0.0031681060791015625
2023-01-21 11:54:35.766149: step: 1036/530, loss: 0.08078479766845703
2023-01-21 11:54:36.872561: step: 1040/530, loss: 0.003502368927001953
2023-01-21 11:54:37.982114: step: 1044/530, loss: 0.0022749900817871094
2023-01-21 11:54:39.080048: step: 1048/530, loss: 0.00025472641573287547
2023-01-21 11:54:40.207163: step: 1052/530, loss: 0.028161145746707916
2023-01-21 11:54:41.357671: step: 1056/530, loss: 0.0007368088117800653
2023-01-21 11:54:42.479439: step: 1060/530, loss: 0.0037077905144542456
2023-01-21 11:54:43.604393: step: 1064/530, loss: 0.0017420768272131681
2023-01-21 11:54:44.744876: step: 1068/530, loss: 0.012484360486268997
2023-01-21 11:54:45.849419: step: 1072/530, loss: 0.0026571275666356087
2023-01-21 11:54:46.953623: step: 1076/530, loss: 0.004560661502182484
2023-01-21 11:54:48.047581: step: 1080/530, loss: 3.52859501617786e-06
2023-01-21 11:54:49.158060: step: 1084/530, loss: 0.04439201578497887
2023-01-21 11:54:50.289765: step: 1088/530, loss: 0.0045189871452748775
2023-01-21 11:54:51.409418: step: 1092/530, loss: 0.01673908159136772
2023-01-21 11:54:52.526925: step: 1096/530, loss: 0.0016184329288080335
2023-01-21 11:54:53.671482: step: 1100/530, loss: 0.22475281357765198
2023-01-21 11:54:54.814627: step: 1104/530, loss: 0.01683063618838787
2023-01-21 11:54:55.928727: step: 1108/530, loss: 0.00018711091252043843
2023-01-21 11:54:57.058370: step: 1112/530, loss: 0.06868467479944229
2023-01-21 11:54:58.184885: step: 1116/530, loss: 0.03353557735681534
2023-01-21 11:54:59.307247: step: 1120/530, loss: 0.05110645294189453
2023-01-21 11:55:00.409959: step: 1124/530, loss: 0.00029630662174895406
2023-01-21 11:55:01.511875: step: 1128/530, loss: 0.0009054184192791581
2023-01-21 11:55:02.631313: step: 1132/530, loss: 0.0806095153093338
2023-01-21 11:55:03.758415: step: 1136/530, loss: 0.0036535263061523438
2023-01-21 11:55:04.887889: step: 1140/530, loss: 0.006058323197066784
2023-01-21 11:55:06.047990: step: 1144/530, loss: 0.0035493853501975536
2023-01-21 11:55:07.149620: step: 1148/530, loss: 0.007952786050736904
2023-01-21 11:55:08.265402: step: 1152/530, loss: 0.004499530885368586
2023-01-21 11:55:09.372191: step: 1156/530, loss: 0.0030796052888035774
2023-01-21 11:55:10.485312: step: 1160/530, loss: 0.010721445083618164
2023-01-21 11:55:11.606859: step: 1164/530, loss: 0.035219766199588776
2023-01-21 11:55:12.728579: step: 1168/530, loss: 0.002448654267936945
2023-01-21 11:55:13.857011: step: 1172/530, loss: 0.000868940376676619
2023-01-21 11:55:14.967939: step: 1176/530, loss: 0.020801853388547897
2023-01-21 11:55:16.096852: step: 1180/530, loss: 0.04534759372472763
2023-01-21 11:55:17.187810: step: 1184/530, loss: 0.0008951186900958419
2023-01-21 11:55:18.325131: step: 1188/530, loss: 0.028798270970582962
2023-01-21 11:55:19.451537: step: 1192/530, loss: 0.009111499413847923
2023-01-21 11:55:20.563648: step: 1196/530, loss: 0.005178308580070734
2023-01-21 11:55:21.720006: step: 1200/530, loss: 0.024652909487485886
2023-01-21 11:55:22.828505: step: 1204/530, loss: 0.08762951195240021
2023-01-21 11:55:23.954203: step: 1208/530, loss: 0.0006271362653933465
2023-01-21 11:55:25.080197: step: 1212/530, loss: 0.034493256360292435
2023-01-21 11:55:26.225539: step: 1216/530, loss: 0.003872775938361883
2023-01-21 11:55:27.350900: step: 1220/530, loss: 0.0003028869687113911
2023-01-21 11:55:28.455858: step: 1224/530, loss: 0.0041214944794774055
2023-01-21 11:55:29.595464: step: 1228/530, loss: 0.0006351470947265625
2023-01-21 11:55:30.743864: step: 1232/530, loss: 0.7890416979789734
2023-01-21 11:55:31.850712: step: 1236/530, loss: 0.04070940241217613
2023-01-21 11:55:32.964007: step: 1240/530, loss: 0.0001262664736714214
2023-01-21 11:55:34.094093: step: 1244/530, loss: 0.0009400367853231728
2023-01-21 11:55:35.210064: step: 1248/530, loss: 0.08610954880714417
2023-01-21 11:55:36.362472: step: 1252/530, loss: 0.029549315571784973
2023-01-21 11:55:37.474705: step: 1256/530, loss: 0.00037844182224944234
2023-01-21 11:55:38.573237: step: 1260/530, loss: 0.0019823075272142887
2023-01-21 11:55:39.687353: step: 1264/530, loss: 0.0007590294117107987
2023-01-21 11:55:40.816982: step: 1268/530, loss: 0.07779411971569061
2023-01-21 11:55:41.942270: step: 1272/530, loss: 0.0027923583984375
2023-01-21 11:55:43.070521: step: 1276/530, loss: 0.013343526050448418
2023-01-21 11:55:44.172149: step: 1280/530, loss: 0.003886604215949774
2023-01-21 11:55:45.271236: step: 1284/530, loss: 0.004340553190559149
2023-01-21 11:55:46.386541: step: 1288/530, loss: 0.0005331516149453819
2023-01-21 11:55:47.507216: step: 1292/530, loss: 0.012051486410200596
2023-01-21 11:55:48.607455: step: 1296/530, loss: 0.0012164115905761719
2023-01-21 11:55:49.733896: step: 1300/530, loss: 0.008524704724550247
2023-01-21 11:55:50.872904: step: 1304/530, loss: 0.019993115216493607
2023-01-21 11:55:51.995768: step: 1308/530, loss: 0.00892577227205038
2023-01-21 11:55:53.120821: step: 1312/530, loss: 0.002249431796371937
2023-01-21 11:55:54.264906: step: 1316/530, loss: 0.011854744516313076
2023-01-21 11:55:55.369732: step: 1320/530, loss: 0.017955780029296875
2023-01-21 11:55:56.486346: step: 1324/530, loss: 0.08238229900598526
2023-01-21 11:55:57.574643: step: 1328/530, loss: 0.008172226138412952
2023-01-21 11:55:58.694268: step: 1332/530, loss: 0.032794952392578125
2023-01-21 11:55:59.854608: step: 1336/530, loss: 6.48498553346144e-06
2023-01-21 11:56:00.974513: step: 1340/530, loss: 0.017563628032803535
2023-01-21 11:56:02.138866: step: 1344/530, loss: 0.02641143836081028
2023-01-21 11:56:03.250836: step: 1348/530, loss: 0.020216751843690872
2023-01-21 11:56:04.380058: step: 1352/530, loss: 0.04610462114214897
2023-01-21 11:56:05.475983: step: 1356/530, loss: 0.0009861469734460115
2023-01-21 11:56:06.624614: step: 1360/530, loss: 0.01091918908059597
2023-01-21 11:56:07.745480: step: 1364/530, loss: 0.0001029014601954259
2023-01-21 11:56:08.867884: step: 1368/530, loss: 0.0007008552784100175
2023-01-21 11:56:10.000375: step: 1372/530, loss: 0.002441978547722101
2023-01-21 11:56:11.101123: step: 1376/530, loss: 8.373260061489418e-05
2023-01-21 11:56:12.208827: step: 1380/530, loss: 0.0001419544278178364
2023-01-21 11:56:13.312998: step: 1384/530, loss: 0.002406978514045477
2023-01-21 11:56:14.425707: step: 1388/530, loss: 1.4591217222914565e-05
2023-01-21 11:56:15.538081: step: 1392/530, loss: 0.0022152899764478207
2023-01-21 11:56:16.657404: step: 1396/530, loss: 0.022213174030184746
2023-01-21 11:56:17.768374: step: 1400/530, loss: 0.002324581379070878
2023-01-21 11:56:18.886416: step: 1404/530, loss: 0.018366431817412376
2023-01-21 11:56:19.999428: step: 1408/530, loss: 0.00019807815260719508
2023-01-21 11:56:21.132586: step: 1412/530, loss: 0.004859352018684149
2023-01-21 11:56:22.238039: step: 1416/530, loss: 0.0023203850723803043
2023-01-21 11:56:23.362806: step: 1420/530, loss: -4.76837158203125e-06
2023-01-21 11:56:24.485743: step: 1424/530, loss: 0.00162420270498842
2023-01-21 11:56:25.611998: step: 1428/530, loss: 0.017632007598876953
2023-01-21 11:56:26.730191: step: 1432/530, loss: 0.008682822808623314
2023-01-21 11:56:27.849411: step: 1436/530, loss: 2.1791458493680693e-05
2023-01-21 11:56:28.947248: step: 1440/530, loss: 0.14718493819236755
2023-01-21 11:56:30.068635: step: 1444/530, loss: 0.02180929109454155
2023-01-21 11:56:31.205255: step: 1448/530, loss: 0.009678458794951439
2023-01-21 11:56:32.330782: step: 1452/530, loss: 0.04201388359069824
2023-01-21 11:56:33.450317: step: 1456/530, loss: 0.0025659562088549137
2023-01-21 11:56:34.555763: step: 1460/530, loss: 0.0020736693404614925
2023-01-21 11:56:35.691119: step: 1464/530, loss: 0.015268850140273571
2023-01-21 11:56:36.824737: step: 1468/530, loss: 0.009681129828095436
2023-01-21 11:56:37.919111: step: 1472/530, loss: 0.0005296707386150956
2023-01-21 11:56:39.014732: step: 1476/530, loss: 0.0004803180636372417
2023-01-21 11:56:40.154660: step: 1480/530, loss: 0.007884884253144264
2023-01-21 11:56:41.271573: step: 1484/530, loss: 0.001230526017025113
2023-01-21 11:56:42.381317: step: 1488/530, loss: 0.0009352207416668534
2023-01-21 11:56:43.489608: step: 1492/530, loss: 0.013703537173569202
2023-01-21 11:56:44.610545: step: 1496/530, loss: 0.5990536212921143
2023-01-21 11:56:45.694940: step: 1500/530, loss: 0.023607540875673294
2023-01-21 11:56:46.790954: step: 1504/530, loss: 0.0006140708574093878
2023-01-21 11:56:47.942264: step: 1508/530, loss: 0.0032337189186364412
2023-01-21 11:56:49.078495: step: 1512/530, loss: 0.007204818539321423
2023-01-21 11:56:50.212475: step: 1516/530, loss: 0.013696098700165749
2023-01-21 11:56:51.319794: step: 1520/530, loss: 0.00051794049795717
2023-01-21 11:56:52.432527: step: 1524/530, loss: 0.01304397638887167
2023-01-21 11:56:53.540905: step: 1528/530, loss: 8.58306884765625e-05
2023-01-21 11:56:54.681905: step: 1532/530, loss: 0.03037414513528347
2023-01-21 11:56:55.793064: step: 1536/530, loss: 0.002983951708301902
2023-01-21 11:56:56.906025: step: 1540/530, loss: 0.021279336884617805
2023-01-21 11:56:57.998988: step: 1544/530, loss: 0.0013879776233807206
2023-01-21 11:56:59.151169: step: 1548/530, loss: 0.014726829715073109
2023-01-21 11:57:00.273206: step: 1552/530, loss: 0.00760917691513896
2023-01-21 11:57:01.412243: step: 1556/530, loss: 0.00154285435564816
2023-01-21 11:57:02.566816: step: 1560/530, loss: 5.6076052715070546e-05
2023-01-21 11:57:03.717818: step: 1564/530, loss: 0.007347679231315851
2023-01-21 11:57:04.835755: step: 1568/530, loss: 0.03694343566894531
2023-01-21 11:57:05.947305: step: 1572/530, loss: 0.005849361419677734
2023-01-21 11:57:07.060659: step: 1576/530, loss: 0.04314832761883736
2023-01-21 11:57:08.157162: step: 1580/530, loss: 2.937316821771674e-05
2023-01-21 11:57:09.240560: step: 1584/530, loss: 0.050464775413274765
2023-01-21 11:57:10.365544: step: 1588/530, loss: 0.07201328873634338
2023-01-21 11:57:11.470951: step: 1592/530, loss: 0.007155418861657381
2023-01-21 11:57:12.608884: step: 1596/530, loss: 0.06021900475025177
2023-01-21 11:57:13.707625: step: 1600/530, loss: 0.004035568330436945
2023-01-21 11:57:14.851669: step: 1604/530, loss: 0.016447830945253372
2023-01-21 11:57:15.974392: step: 1608/530, loss: 0.007470798213034868
2023-01-21 11:57:17.097157: step: 1612/530, loss: 1.8882752556237392e-05
2023-01-21 11:57:18.212137: step: 1616/530, loss: 0.029623698443174362
2023-01-21 11:57:19.330518: step: 1620/530, loss: 0.0308837890625
2023-01-21 11:57:20.444392: step: 1624/530, loss: 0.008257865905761719
2023-01-21 11:57:21.570000: step: 1628/530, loss: 0.0010222436394542456
2023-01-21 11:57:22.675763: step: 1632/530, loss: 0.0231843963265419
2023-01-21 11:57:23.800936: step: 1636/530, loss: 6.103515625e-05
2023-01-21 11:57:24.908946: step: 1640/530, loss: 0.008834457956254482
2023-01-21 11:57:26.023079: step: 1644/530, loss: 0.0008246421348303556
2023-01-21 11:57:27.151620: step: 1648/530, loss: 0.34993723034858704
2023-01-21 11:57:28.267728: step: 1652/530, loss: 0.044150736182928085
2023-01-21 11:57:29.400512: step: 1656/530, loss: 0.0015690803993493319
2023-01-21 11:57:30.522484: step: 1660/530, loss: 0.020256424322724342
2023-01-21 11:57:31.641740: step: 1664/530, loss: 0.004318046849220991
2023-01-21 11:57:32.768370: step: 1668/530, loss: 0.00022611618624068797
2023-01-21 11:57:33.903622: step: 1672/530, loss: 0.00209884624928236
2023-01-21 11:57:35.007288: step: 1676/530, loss: 0.04850583150982857
2023-01-21 11:57:36.136955: step: 1680/530, loss: 0.003920459654182196
2023-01-21 11:57:37.290596: step: 1684/530, loss: 0.04824981838464737
2023-01-21 11:57:38.389225: step: 1688/530, loss: 0.0015677452320232987
2023-01-21 11:57:39.510565: step: 1692/530, loss: 0.0069971089251339436
2023-01-21 11:57:40.614010: step: 1696/530, loss: 0.007292557042092085
2023-01-21 11:57:41.714761: step: 1700/530, loss: 0.05669093132019043
2023-01-21 11:57:42.838126: step: 1704/530, loss: 0.015943242236971855
2023-01-21 11:57:43.956131: step: 1708/530, loss: 0.0022111416328698397
2023-01-21 11:57:45.077249: step: 1712/530, loss: 0.00674552982673049
2023-01-21 11:57:46.207755: step: 1716/530, loss: 0.033381808549165726
2023-01-21 11:57:47.339259: step: 1720/530, loss: 0.0008404746768064797
2023-01-21 11:57:48.470756: step: 1724/530, loss: 0.0010616302024573088
2023-01-21 11:57:49.612237: step: 1728/530, loss: 0.002975654788315296
2023-01-21 11:57:50.760897: step: 1732/530, loss: 0.01167144812643528
2023-01-21 11:57:51.896195: step: 1736/530, loss: 0.07330246269702911
2023-01-21 11:57:52.989009: step: 1740/530, loss: 0.003134441329166293
2023-01-21 11:57:54.108411: step: 1744/530, loss: 0.022260475903749466
2023-01-21 11:57:55.235309: step: 1748/530, loss: 0.06419877707958221
2023-01-21 11:57:56.389346: step: 1752/530, loss: 0.016246415674686432
2023-01-21 11:57:57.501568: step: 1756/530, loss: 0.0004451751592569053
2023-01-21 11:57:58.627812: step: 1760/530, loss: 0.0027055740356445312
2023-01-21 11:57:59.772123: step: 1764/530, loss: 0.0034275054931640625
2023-01-21 11:58:00.936203: step: 1768/530, loss: 0.0011279582977294922
2023-01-21 11:58:02.090934: step: 1772/530, loss: 0.04172935709357262
2023-01-21 11:58:03.193976: step: 1776/530, loss: 0.0007325172773562372
2023-01-21 11:58:04.319121: step: 1780/530, loss: 0.004502487368881702
2023-01-21 11:58:05.481376: step: 1784/530, loss: 0.11960944533348083
2023-01-21 11:58:06.611847: step: 1788/530, loss: 0.003921127412468195
2023-01-21 11:58:07.768397: step: 1792/530, loss: 0.032137155532836914
2023-01-21 11:58:08.887884: step: 1796/530, loss: 0.0012937546707689762
2023-01-21 11:58:10.035302: step: 1800/530, loss: 0.6597188115119934
2023-01-21 11:58:11.166586: step: 1804/530, loss: 0.01892080344259739
2023-01-21 11:58:12.279031: step: 1808/530, loss: 0.016044998541474342
2023-01-21 11:58:13.421938: step: 1812/530, loss: 6.198897608555853e-07
2023-01-21 11:58:14.553659: step: 1816/530, loss: 0.001491117523983121
2023-01-21 11:58:15.692166: step: 1820/530, loss: 0.008706283755600452
2023-01-21 11:58:16.816777: step: 1824/530, loss: 0.00033245087251998484
2023-01-21 11:58:17.942754: step: 1828/530, loss: 0.0006847382173873484
2023-01-21 11:58:19.047192: step: 1832/530, loss: 9.469986252952367e-05
2023-01-21 11:58:20.180363: step: 1836/530, loss: 0.053072646260261536
2023-01-21 11:58:21.281802: step: 1840/530, loss: 0.0035694122780114412
2023-01-21 11:58:22.422487: step: 1844/530, loss: 0.02610321156680584
2023-01-21 11:58:23.536925: step: 1848/530, loss: 0.0050811767578125
2023-01-21 11:58:24.630669: step: 1852/530, loss: 0.0004945755354128778
2023-01-21 11:58:25.773309: step: 1856/530, loss: 0.01032409630715847
2023-01-21 11:58:26.881069: step: 1860/530, loss: 0.0009616852039471269
2023-01-21 11:58:27.974777: step: 1864/530, loss: 0.0003273010370321572
2023-01-21 11:58:29.102283: step: 1868/530, loss: 0.18396759033203125
2023-01-21 11:58:30.261603: step: 1872/530, loss: 0.013064097613096237
2023-01-21 11:58:31.393733: step: 1876/530, loss: 3.8909915019758046e-05
2023-01-21 11:58:32.498166: step: 1880/530, loss: 0.026477433741092682
2023-01-21 11:58:33.629732: step: 1884/530, loss: 0.04197445139288902
2023-01-21 11:58:34.765629: step: 1888/530, loss: 0.02575073204934597
2023-01-21 11:58:35.874162: step: 1892/530, loss: 0.028217125684022903
2023-01-21 11:58:36.996631: step: 1896/530, loss: 0.005238628946244717
2023-01-21 11:58:38.143801: step: 1900/530, loss: 9.098053124034777e-05
2023-01-21 11:58:39.274827: step: 1904/530, loss: 0.0003612518485169858
2023-01-21 11:58:40.398011: step: 1908/530, loss: 0.023641493171453476
2023-01-21 11:58:41.508770: step: 1912/530, loss: 0.007226848974823952
2023-01-21 11:58:42.587623: step: 1916/530, loss: 0.000567531562410295
2023-01-21 11:58:43.709252: step: 1920/530, loss: 0.00747947720810771
2023-01-21 11:58:44.823578: step: 1924/530, loss: 0.00084686279296875
2023-01-21 11:58:45.955393: step: 1928/530, loss: 0.00532608013600111
2023-01-21 11:58:47.080078: step: 1932/530, loss: 0.041840553283691406
2023-01-21 11:58:48.207093: step: 1936/530, loss: 0.028040315955877304
2023-01-21 11:58:49.367095: step: 1940/530, loss: 0.005005550570785999
2023-01-21 11:58:50.515859: step: 1944/530, loss: 0.016727352514863014
2023-01-21 11:58:51.639721: step: 1948/530, loss: 0.01028070505708456
2023-01-21 11:58:52.769248: step: 1952/530, loss: 0.010974694043397903
2023-01-21 11:58:53.906502: step: 1956/530, loss: 0.02663450315594673
2023-01-21 11:58:55.016263: step: 1960/530, loss: 0.0020390511490404606
2023-01-21 11:58:56.138849: step: 1964/530, loss: 0.00036144256591796875
2023-01-21 11:58:57.243361: step: 1968/530, loss: 0.019230175763368607
2023-01-21 11:58:58.350007: step: 1972/530, loss: 0.016310883685946465
2023-01-21 11:58:59.540401: step: 1976/530, loss: 0.05003839731216431
2023-01-21 11:59:00.662544: step: 1980/530, loss: 0.005981254857033491
2023-01-21 11:59:01.779783: step: 1984/530, loss: 0.11145592480897903
2023-01-21 11:59:02.893717: step: 1988/530, loss: 0.00351638812571764
2023-01-21 11:59:04.002286: step: 1992/530, loss: 0.020348692312836647
2023-01-21 11:59:05.116715: step: 1996/530, loss: 0.04157190024852753
2023-01-21 11:59:06.257481: step: 2000/530, loss: 0.015211963094770908
2023-01-21 11:59:07.385166: step: 2004/530, loss: 0.02807140350341797
2023-01-21 11:59:08.493999: step: 2008/530, loss: 0.0052252295427024364
2023-01-21 11:59:09.606982: step: 2012/530, loss: 6.217956251930445e-05
2023-01-21 11:59:10.697715: step: 2016/530, loss: 0.00076041225111112
2023-01-21 11:59:11.817279: step: 2020/530, loss: 0.002292847726494074
2023-01-21 11:59:12.953659: step: 2024/530, loss: 0.010550356470048428
2023-01-21 11:59:14.108974: step: 2028/530, loss: 0.0016943932278081775
2023-01-21 11:59:15.234400: step: 2032/530, loss: 0.00045757292537018657
2023-01-21 11:59:16.372802: step: 2036/530, loss: 0.006670570466667414
2023-01-21 11:59:17.500467: step: 2040/530, loss: 0.03963852301239967
2023-01-21 11:59:18.649328: step: 2044/530, loss: 0.04340400546789169
2023-01-21 11:59:19.761888: step: 2048/530, loss: 0.0006910323863849044
2023-01-21 11:59:20.884248: step: 2052/530, loss: 0.007282257545739412
2023-01-21 11:59:22.001379: step: 2056/530, loss: 0.003734398167580366
2023-01-21 11:59:23.113514: step: 2060/530, loss: 0.11991024017333984
2023-01-21 11:59:24.236718: step: 2064/530, loss: 0.01284322701394558
2023-01-21 11:59:25.372777: step: 2068/530, loss: 0.0004965782281942666
2023-01-21 11:59:26.494225: step: 2072/530, loss: 0.0005380630609579384
2023-01-21 11:59:27.649909: step: 2076/530, loss: 0.018630409613251686
2023-01-21 11:59:28.760263: step: 2080/530, loss: 0.00046854018000885844
2023-01-21 11:59:29.875571: step: 2084/530, loss: 0.005291461944580078
2023-01-21 11:59:31.033967: step: 2088/530, loss: 0.04149685055017471
2023-01-21 11:59:32.161686: step: 2092/530, loss: 0.014782142825424671
2023-01-21 11:59:33.287253: step: 2096/530, loss: 0.02965397760272026
2023-01-21 11:59:34.379082: step: 2100/530, loss: 0.026604272425174713
2023-01-21 11:59:35.508560: step: 2104/530, loss: 0.01924319379031658
2023-01-21 11:59:36.625416: step: 2108/530, loss: 0.010452747344970703
2023-01-21 11:59:37.722793: step: 2112/530, loss: 4.167556471657008e-05
2023-01-21 11:59:38.848653: step: 2116/530, loss: 0.059009552001953125
2023-01-21 11:59:39.954790: step: 2120/530, loss: 0.0021916390396654606
==================================================
Loss: 0.028
--------------------
Dev: {'event': {'p': 0.6031578947368421, 'r': 0.762982689747004, 'f1': 0.673721340388007}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6401463191586648, 'r': 0.8, 'f1': 0.7112014224028448}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.5376344086021505, 'r': 0.9259259259259259, 'f1': 0.6802721088435373}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
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': 19}
Russian: {'event': {'p': 0.3673469387755102, 'r': 0.5, 'f1': 0.42352941176470593}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:00:20.706369: step: 4/530, loss: 0.003492116928100586
2023-01-21 12:00:21.819490: step: 8/530, loss: 0.005364203825592995
2023-01-21 12:00:22.944118: step: 12/530, loss: 0.0005717277526855469
2023-01-21 12:00:24.090714: step: 16/530, loss: 0.025046730414032936
2023-01-21 12:00:25.221661: step: 20/530, loss: 4.634857032215223e-05
2023-01-21 12:00:26.391132: step: 24/530, loss: 0.00041937828063964844
2023-01-21 12:00:27.534396: step: 28/530, loss: 0.032282259315252304
2023-01-21 12:00:28.687781: step: 32/530, loss: 0.004409408662468195
2023-01-21 12:00:29.817182: step: 36/530, loss: 0.0066699981689453125
2023-01-21 12:00:30.941020: step: 40/530, loss: 0.0007936478359624743
2023-01-21 12:00:32.096100: step: 44/530, loss: 0.00171661376953125
2023-01-21 12:00:33.204872: step: 48/530, loss: 0.0035938501823693514
2023-01-21 12:00:34.345894: step: 52/530, loss: 0.0026996610686182976
2023-01-21 12:00:35.440352: step: 56/530, loss: 0.002084350446239114
2023-01-21 12:00:36.552072: step: 60/530, loss: 0.02218923531472683
2023-01-21 12:00:37.681814: step: 64/530, loss: 0.04186049476265907
2023-01-21 12:00:38.770049: step: 68/530, loss: 0.0020511627662926912
2023-01-21 12:00:39.875941: step: 72/530, loss: 0.06073322519659996
2023-01-21 12:00:41.008247: step: 76/530, loss: 0.0005309581756591797
2023-01-21 12:00:42.111769: step: 80/530, loss: 0.001096534775570035
2023-01-21 12:00:43.226132: step: 84/530, loss: 4.615784200723283e-05
2023-01-21 12:00:44.313425: step: 88/530, loss: 5.054474513599416e-06
2023-01-21 12:00:45.432059: step: 92/530, loss: 0.04574775695800781
2023-01-21 12:00:46.568440: step: 96/530, loss: 0.003422737354412675
2023-01-21 12:00:47.699110: step: 100/530, loss: 0.006926917936652899
2023-01-21 12:00:48.796286: step: 104/530, loss: 0.0016969681018963456
2023-01-21 12:00:49.932014: step: 108/530, loss: 0.030000973492860794
2023-01-21 12:00:51.062742: step: 112/530, loss: 0.011799240484833717
2023-01-21 12:00:52.184568: step: 116/530, loss: 0.0037521361373364925
2023-01-21 12:00:53.298624: step: 120/530, loss: 8.015632920432836e-05
2023-01-21 12:00:54.445533: step: 124/530, loss: 0.03898058086633682
2023-01-21 12:00:55.552761: step: 128/530, loss: 0.0015865325694903731
2023-01-21 12:00:56.703286: step: 132/530, loss: 0.014496517367661
2023-01-21 12:00:57.811419: step: 136/530, loss: 0.053733255714178085
2023-01-21 12:00:58.954882: step: 140/530, loss: 0.04569273069500923
2023-01-21 12:01:00.100525: step: 144/530, loss: 0.05728635936975479
2023-01-21 12:01:01.241963: step: 148/530, loss: 0.003631496336311102
2023-01-21 12:01:02.355856: step: 152/530, loss: 0.0008540153503417969
2023-01-21 12:01:03.469678: step: 156/530, loss: 0.02424955554306507
2023-01-21 12:01:04.564561: step: 160/530, loss: 0.007134628482162952
2023-01-21 12:01:05.689650: step: 164/530, loss: 0.0006804466247558594
2023-01-21 12:01:06.824549: step: 168/530, loss: 0.0016426086658611894
2023-01-21 12:01:07.938046: step: 172/530, loss: 0.02122783660888672
2023-01-21 12:01:09.033891: step: 176/530, loss: 0.001952362130396068
2023-01-21 12:01:10.125811: step: 180/530, loss: 0.006259918212890625
2023-01-21 12:01:11.266964: step: 184/530, loss: 0.12352123111486435
2023-01-21 12:01:12.368680: step: 188/530, loss: 0.05261344835162163
2023-01-21 12:01:13.494980: step: 192/530, loss: 0.005612564273178577
2023-01-21 12:01:14.592378: step: 196/530, loss: 0.035167768597602844
2023-01-21 12:01:15.708343: step: 200/530, loss: 0.002225208329036832
2023-01-21 12:01:16.806931: step: 204/530, loss: 0.0011348247062414885
2023-01-21 12:01:17.935173: step: 208/530, loss: 0.01935615763068199
2023-01-21 12:01:19.133649: step: 212/530, loss: 0.00784378033131361
2023-01-21 12:01:20.268978: step: 216/530, loss: 0.008266258984804153
2023-01-21 12:01:21.390483: step: 220/530, loss: 0.0007605552673339844
2023-01-21 12:01:22.511708: step: 224/530, loss: 0.000609970127698034
2023-01-21 12:01:23.626718: step: 228/530, loss: 0.058336831629276276
2023-01-21 12:01:24.727011: step: 232/530, loss: 0.00051794049795717
2023-01-21 12:01:25.823461: step: 236/530, loss: 0.0016651153564453125
2023-01-21 12:01:26.967531: step: 240/530, loss: 0.008790969848632812
2023-01-21 12:01:28.141991: step: 244/530, loss: 0.015874672681093216
2023-01-21 12:01:29.252995: step: 248/530, loss: 0.003860569093376398
2023-01-21 12:01:30.384386: step: 252/530, loss: 0.012919188477098942
2023-01-21 12:01:31.511399: step: 256/530, loss: 0.04431714862585068
2023-01-21 12:01:32.667496: step: 260/530, loss: 0.0068387980572879314
2023-01-21 12:01:33.812824: step: 264/530, loss: 0.04978370666503906
2023-01-21 12:01:34.939146: step: 268/530, loss: 9.512902033748105e-05
2023-01-21 12:01:36.082495: step: 272/530, loss: 0.0001293182431254536
2023-01-21 12:01:37.187531: step: 276/530, loss: 0.000587892543990165
2023-01-21 12:01:38.304629: step: 280/530, loss: 0.02096080780029297
2023-01-21 12:01:39.434512: step: 284/530, loss: 0.0003495216369628906
2023-01-21 12:01:40.562533: step: 288/530, loss: 0.006916618440300226
2023-01-21 12:01:41.666208: step: 292/530, loss: 0.011733626946806908
2023-01-21 12:01:42.774930: step: 296/530, loss: 0.0004991531604900956
2023-01-21 12:01:43.892991: step: 300/530, loss: 0.012934684753417969
2023-01-21 12:01:44.992563: step: 304/530, loss: 0.13992318511009216
2023-01-21 12:01:46.103682: step: 308/530, loss: 0.0005417824140749872
2023-01-21 12:01:47.234470: step: 312/530, loss: 0.01599092409014702
2023-01-21 12:01:48.407155: step: 316/530, loss: 0.0018291473388671875
2023-01-21 12:01:49.525744: step: 320/530, loss: 0.008711909875273705
2023-01-21 12:01:50.650751: step: 324/530, loss: 0.010356903076171875
2023-01-21 12:01:51.791649: step: 328/530, loss: 0.0003834724484477192
2023-01-21 12:01:52.919426: step: 332/530, loss: 0.04784455522894859
2023-01-21 12:01:54.043110: step: 336/530, loss: 0.008853721432387829
2023-01-21 12:01:55.156109: step: 340/530, loss: 0.0016565322875976562
2023-01-21 12:01:56.278035: step: 344/530, loss: 0.0012794494396075606
2023-01-21 12:01:57.401409: step: 348/530, loss: 0.025172902271151543
2023-01-21 12:01:58.531179: step: 352/530, loss: 0.00020275116548873484
2023-01-21 12:01:59.675964: step: 356/530, loss: 0.0015499114524573088
2023-01-21 12:02:00.804288: step: 360/530, loss: 0.020780278369784355
2023-01-21 12:02:01.918400: step: 364/530, loss: 4.6348573960131034e-05
2023-01-21 12:02:03.068402: step: 368/530, loss: 0.017505645751953125
2023-01-21 12:02:04.192394: step: 372/530, loss: 0.011124420911073685
2023-01-21 12:02:05.343306: step: 376/530, loss: 0.0008269369718618691
2023-01-21 12:02:06.482169: step: 380/530, loss: 0.0013065338134765625
2023-01-21 12:02:07.618992: step: 384/530, loss: 0.03151235729455948
2023-01-21 12:02:08.733003: step: 388/530, loss: 9.961127943824977e-05
2023-01-21 12:02:09.853284: step: 392/530, loss: 0.014006709679961205
2023-01-21 12:02:10.961086: step: 396/530, loss: 0.0017796993488445878
2023-01-21 12:02:12.125515: step: 400/530, loss: 0.002540111541748047
2023-01-21 12:02:13.220519: step: 404/530, loss: 0.009089660830795765
2023-01-21 12:02:14.359579: step: 408/530, loss: 0.0313870944082737
2023-01-21 12:02:15.482021: step: 412/530, loss: 0.006443977355957031
2023-01-21 12:02:16.610431: step: 416/530, loss: 0.008953667245805264
2023-01-21 12:02:17.713748: step: 420/530, loss: 0.00019855500431731343
2023-01-21 12:02:18.827468: step: 424/530, loss: 0.04034481197595596
2023-01-21 12:02:19.938280: step: 428/530, loss: 1.602172778802924e-05
2023-01-21 12:02:21.041650: step: 432/530, loss: 5.0067901611328125e-05
2023-01-21 12:02:22.173632: step: 436/530, loss: 0.010254574008286
2023-01-21 12:02:23.268647: step: 440/530, loss: 0.013773727230727673
2023-01-21 12:02:24.365534: step: 444/530, loss: 3.771782212425023e-05
2023-01-21 12:02:25.520563: step: 448/530, loss: 0.0012991904513910413
2023-01-21 12:02:26.629654: step: 452/530, loss: 0.0012516021961346269
2023-01-21 12:02:27.730000: step: 456/530, loss: 0.005177402403205633
2023-01-21 12:02:28.838997: step: 460/530, loss: 0.003760433290153742
2023-01-21 12:02:29.977291: step: 464/530, loss: 0.004835319239646196
2023-01-21 12:02:31.109801: step: 468/530, loss: 0.0021732330787926912
2023-01-21 12:02:32.220167: step: 472/530, loss: 0.0026501654647290707
2023-01-21 12:02:33.309484: step: 476/530, loss: 0.00015466808690689504
2023-01-21 12:02:34.463507: step: 480/530, loss: 0.0006868839845992625
2023-01-21 12:02:35.590445: step: 484/530, loss: 0.020505379885435104
2023-01-21 12:02:36.703952: step: 488/530, loss: 0.001527500106021762
2023-01-21 12:02:37.836819: step: 492/530, loss: 0.0009910583030432463
2023-01-21 12:02:38.923506: step: 496/530, loss: 0.004509925842285156
2023-01-21 12:02:40.017822: step: 500/530, loss: 0.0008550644270144403
2023-01-21 12:02:41.143612: step: 504/530, loss: 0.0003814697265625
2023-01-21 12:02:42.253336: step: 508/530, loss: 0.000613784824963659
2023-01-21 12:02:43.384827: step: 512/530, loss: 0.09463000297546387
2023-01-21 12:02:44.501119: step: 516/530, loss: 4.024505687993951e-05
2023-01-21 12:02:45.623819: step: 520/530, loss: 0.004937934689223766
2023-01-21 12:02:46.762080: step: 524/530, loss: 0.024849414825439453
2023-01-21 12:02:47.892563: step: 528/530, loss: 0.09353499114513397
2023-01-21 12:02:48.994101: step: 532/530, loss: -6.10351571594947e-06
2023-01-21 12:02:50.123980: step: 536/530, loss: 5.7220458984375e-06
2023-01-21 12:02:51.249597: step: 540/530, loss: 0.011748313903808594
2023-01-21 12:02:52.393054: step: 544/530, loss: 0.015749692916870117
2023-01-21 12:02:53.491442: step: 548/530, loss: 0.009624290280044079
2023-01-21 12:02:54.622546: step: 552/530, loss: 0.03919219970703125
2023-01-21 12:02:55.738219: step: 556/530, loss: 0.0007454872247762978
2023-01-21 12:02:56.836187: step: 560/530, loss: 0.00033988954965025187
2023-01-21 12:02:57.975697: step: 564/530, loss: 1.1444092706369702e-05
2023-01-21 12:02:59.095966: step: 568/530, loss: 0.0009068488725461066
2023-01-21 12:03:00.218425: step: 572/530, loss: 0.0001710891810944304
2023-01-21 12:03:01.369167: step: 576/530, loss: 0.01419143658131361
2023-01-21 12:03:02.579024: step: 580/530, loss: 2.822876012942288e-05
2023-01-21 12:03:03.689921: step: 584/530, loss: 0.011102009564638138
2023-01-21 12:03:04.815050: step: 588/530, loss: 0.0011966705787926912
2023-01-21 12:03:05.931293: step: 592/530, loss: 0.00020194053649902344
2023-01-21 12:03:07.061173: step: 596/530, loss: 0.1919269561767578
2023-01-21 12:03:08.187065: step: 600/530, loss: 0.00882654171437025
2023-01-21 12:03:09.300447: step: 604/530, loss: 0.0003261566162109375
2023-01-21 12:03:10.407398: step: 608/530, loss: 0.022101402282714844
2023-01-21 12:03:11.517976: step: 612/530, loss: 0.024153614416718483
2023-01-21 12:03:12.641041: step: 616/530, loss: 0.0008025646093301475
2023-01-21 12:03:13.770180: step: 620/530, loss: 0.027393151074647903
2023-01-21 12:03:14.907221: step: 624/530, loss: 0.0010135173797607422
2023-01-21 12:03:16.048655: step: 628/530, loss: 0.013886069878935814
2023-01-21 12:03:17.194072: step: 632/530, loss: 0.00018999577150680125
2023-01-21 12:03:18.332111: step: 636/530, loss: 0.011508369818329811
2023-01-21 12:03:19.449517: step: 640/530, loss: 0.004253101069480181
2023-01-21 12:03:20.559278: step: 644/530, loss: 0.031964682042598724
2023-01-21 12:03:21.670137: step: 648/530, loss: 0.007214928045868874
2023-01-21 12:03:22.821128: step: 652/530, loss: 0.0011971474159508944
2023-01-21 12:03:23.925671: step: 656/530, loss: 0.010186959058046341
2023-01-21 12:03:25.058331: step: 660/530, loss: 0.0019048691028729081
2023-01-21 12:03:26.188876: step: 664/530, loss: 0.0010955811012536287
2023-01-21 12:03:27.319773: step: 668/530, loss: 0.0305909626185894
2023-01-21 12:03:28.409057: step: 672/530, loss: 0.00156574253924191
2023-01-21 12:03:29.545965: step: 676/530, loss: 0.02763528749346733
2023-01-21 12:03:30.696870: step: 680/530, loss: 0.003212451934814453
2023-01-21 12:03:31.828943: step: 684/530, loss: 0.00037021638127043843
2023-01-21 12:03:32.951101: step: 688/530, loss: 0.00656471261754632
2023-01-21 12:03:34.047392: step: 692/530, loss: 0.047976307570934296
2023-01-21 12:03:35.175916: step: 696/530, loss: 0.0029567719902843237
2023-01-21 12:03:36.286618: step: 700/530, loss: 0.00097827916033566
2023-01-21 12:03:37.412857: step: 704/530, loss: 0.24476879835128784
2023-01-21 12:03:38.573698: step: 708/530, loss: 0.004502773284912109
2023-01-21 12:03:39.682573: step: 712/530, loss: 0.0003572463756427169
2023-01-21 12:03:40.828086: step: 716/530, loss: 0.03177185356616974
2023-01-21 12:03:41.974507: step: 720/530, loss: 0.0020856859628111124
2023-01-21 12:03:43.090600: step: 724/530, loss: 0.0014862060779705644
2023-01-21 12:03:44.180769: step: 728/530, loss: 0.00334415421821177
2023-01-21 12:03:45.284709: step: 732/530, loss: 0.00809183157980442
2023-01-21 12:03:46.372818: step: 736/530, loss: 0.0019266129238530993
2023-01-21 12:03:47.475996: step: 740/530, loss: 0.0009130477556027472
2023-01-21 12:03:48.585427: step: 744/530, loss: 0.015190697275102139
2023-01-21 12:03:49.721614: step: 748/530, loss: 0.026973916217684746
2023-01-21 12:03:50.845956: step: 752/530, loss: 5.14984139954322e-06
2023-01-21 12:03:51.944692: step: 756/530, loss: 0.0015502453316003084
2023-01-21 12:03:53.066066: step: 760/530, loss: 0.00027551653329283
2023-01-21 12:03:54.186407: step: 764/530, loss: 0.008426999673247337
2023-01-21 12:03:55.359381: step: 768/530, loss: 0.05790691822767258
2023-01-21 12:03:56.472896: step: 772/530, loss: 0.003280830569565296
2023-01-21 12:03:57.566671: step: 776/530, loss: 0.005009079352021217
2023-01-21 12:03:58.710532: step: 780/530, loss: 0.009288978762924671
2023-01-21 12:03:59.826435: step: 784/530, loss: 0.18046382069587708
2023-01-21 12:04:00.939267: step: 788/530, loss: 0.01253962516784668
2023-01-21 12:04:02.034592: step: 792/530, loss: 3.757476952159777e-05
2023-01-21 12:04:03.174580: step: 796/530, loss: 0.028840254992246628
2023-01-21 12:04:04.285870: step: 800/530, loss: 0.0027150153182446957
2023-01-21 12:04:05.398873: step: 804/530, loss: 0.011242866516113281
2023-01-21 12:04:06.517012: step: 808/530, loss: 0.030660152435302734
2023-01-21 12:04:07.649969: step: 812/530, loss: 0.0011314869625493884
2023-01-21 12:04:08.781269: step: 816/530, loss: 0.07943210750818253
2023-01-21 12:04:09.903454: step: 820/530, loss: 0.0005268097156658769
2023-01-21 12:04:11.027883: step: 824/530, loss: 0.0015645623207092285
2023-01-21 12:04:12.135875: step: 828/530, loss: 0.00013427734666038305
2023-01-21 12:04:13.234869: step: 832/530, loss: 0.012929343618452549
2023-01-21 12:04:14.347157: step: 836/530, loss: 0.002537250518798828
2023-01-21 12:04:15.442302: step: 840/530, loss: 0.007545280735939741
2023-01-21 12:04:16.551045: step: 844/530, loss: 0.008433151058852673
2023-01-21 12:04:17.667128: step: 848/530, loss: 0.0005313873407430947
2023-01-21 12:04:18.791299: step: 852/530, loss: 0.007874488830566406
2023-01-21 12:04:19.896851: step: 856/530, loss: 0.034624479711055756
2023-01-21 12:04:21.024261: step: 860/530, loss: 0.023485302925109863
2023-01-21 12:04:22.149340: step: 864/530, loss: 0.0033110626973211765
2023-01-21 12:04:23.252016: step: 868/530, loss: 0.009881210513412952
2023-01-21 12:04:24.358606: step: 872/530, loss: 0.001555633614771068
2023-01-21 12:04:25.497024: step: 876/530, loss: 0.04731525853276253
2023-01-21 12:04:26.618341: step: 880/530, loss: 0.002470779698342085
2023-01-21 12:04:27.754659: step: 884/530, loss: 0.023133039474487305
2023-01-21 12:04:28.885758: step: 888/530, loss: 0.022152137011289597
2023-01-21 12:04:30.022151: step: 892/530, loss: 0.005645895376801491
2023-01-21 12:04:31.148471: step: 896/530, loss: 0.0006113052368164062
2023-01-21 12:04:32.294392: step: 900/530, loss: 0.0030487061012536287
2023-01-21 12:04:33.394329: step: 904/530, loss: 0.006674480624496937
2023-01-21 12:04:34.532013: step: 908/530, loss: 0.054091643542051315
2023-01-21 12:04:35.624244: step: 912/530, loss: 0.0004943847889080644
2023-01-21 12:04:36.744156: step: 916/530, loss: 0.004277515225112438
2023-01-21 12:04:37.864275: step: 920/530, loss: 0.015009785071015358
2023-01-21 12:04:38.984354: step: 924/530, loss: 0.013983441516757011
2023-01-21 12:04:40.093053: step: 928/530, loss: 0.0004916191101074219
2023-01-21 12:04:41.220074: step: 932/530, loss: 0.004873562138527632
2023-01-21 12:04:42.330596: step: 936/530, loss: 0.0009518623119220138
2023-01-21 12:04:43.460778: step: 940/530, loss: 0.0010462760692462325
2023-01-21 12:04:44.564269: step: 944/530, loss: 3.33309180859942e-05
2023-01-21 12:04:45.699313: step: 948/530, loss: 0.00010976791236316785
2023-01-21 12:04:46.827900: step: 952/530, loss: 0.0505407340824604
2023-01-21 12:04:47.961379: step: 956/530, loss: 0.00014715194993186742
2023-01-21 12:04:49.079716: step: 960/530, loss: 0.02407236211001873
2023-01-21 12:04:50.190804: step: 964/530, loss: 0.005028247833251953
2023-01-21 12:04:51.322377: step: 968/530, loss: 0.0656309649348259
2023-01-21 12:04:52.478784: step: 972/530, loss: 0.1735997200012207
2023-01-21 12:04:53.651746: step: 976/530, loss: 0.3993709683418274
2023-01-21 12:04:54.760241: step: 980/530, loss: 0.0008949280017986894
2023-01-21 12:04:55.856870: step: 984/530, loss: 0.00274846563115716
2023-01-21 12:04:56.990145: step: 988/530, loss: 0.00064768799347803
2023-01-21 12:04:58.098044: step: 992/530, loss: 0.00041980744572356343
2023-01-21 12:04:59.169391: step: 996/530, loss: 0.0011851787567138672
2023-01-21 12:05:00.283453: step: 1000/530, loss: 0.0005203246837481856
2023-01-21 12:05:01.398666: step: 1004/530, loss: 3.5762791412707884e-06
2023-01-21 12:05:02.517162: step: 1008/530, loss: 0.10134754329919815
2023-01-21 12:05:03.635471: step: 1012/530, loss: 0.030083274468779564
2023-01-21 12:05:04.752874: step: 1016/530, loss: 0.013525581918656826
2023-01-21 12:05:05.902190: step: 1020/530, loss: 0.030022429302334785
2023-01-21 12:05:07.031174: step: 1024/530, loss: 0.0025085448287427425
2023-01-21 12:05:08.153360: step: 1028/530, loss: 0.0027269364800304174
2023-01-21 12:05:09.248288: step: 1032/530, loss: 0.0010020255576819181
2023-01-21 12:05:10.392550: step: 1036/530, loss: 0.0005570889334194362
2023-01-21 12:05:11.506430: step: 1040/530, loss: 0.0043961526826024055
2023-01-21 12:05:12.628572: step: 1044/530, loss: 0.00017080307588912547
2023-01-21 12:05:13.747591: step: 1048/530, loss: 0.009051132947206497
2023-01-21 12:05:14.884488: step: 1052/530, loss: 0.00014219284639693797
2023-01-21 12:05:16.029447: step: 1056/530, loss: 5.545616295421496e-05
2023-01-21 12:05:17.134048: step: 1060/530, loss: 0.018744181841611862
2023-01-21 12:05:18.239411: step: 1064/530, loss: 0.0028033496346324682
2023-01-21 12:05:19.340282: step: 1068/530, loss: 0.00042953493539243937
2023-01-21 12:05:20.488827: step: 1072/530, loss: 0.02830658107995987
2023-01-21 12:05:21.604844: step: 1076/530, loss: 0.0004821777401957661
2023-01-21 12:05:22.755028: step: 1080/530, loss: 0.0017843246459960938
2023-01-21 12:05:23.858914: step: 1084/530, loss: 0.02479691617190838
2023-01-21 12:05:24.996875: step: 1088/530, loss: 0.0014714241260662675
2023-01-21 12:05:26.129531: step: 1092/530, loss: 0.004219436552375555
2023-01-21 12:05:27.258813: step: 1096/530, loss: 0.0013544083340093493
2023-01-21 12:05:28.358785: step: 1100/530, loss: 0.00019931793212890625
2023-01-21 12:05:29.459679: step: 1104/530, loss: 4.520416405284777e-05
2023-01-21 12:05:30.585774: step: 1108/530, loss: 0.019473552703857422
2023-01-21 12:05:31.691009: step: 1112/530, loss: 0.025881005451083183
2023-01-21 12:05:32.842823: step: 1116/530, loss: 0.0013722418807446957
2023-01-21 12:05:33.977147: step: 1120/530, loss: 0.004391098394989967
2023-01-21 12:05:35.095210: step: 1124/530, loss: 0.0010742187732830644
2023-01-21 12:05:36.224844: step: 1128/530, loss: 0.0005341530195437372
2023-01-21 12:05:37.358141: step: 1132/530, loss: 0.0001489639253122732
2023-01-21 12:05:38.493072: step: 1136/530, loss: 0.08273229748010635
2023-01-21 12:05:39.615769: step: 1140/530, loss: 0.11430750042200089
2023-01-21 12:05:40.736497: step: 1144/530, loss: 0.021305561065673828
2023-01-21 12:05:41.836661: step: 1148/530, loss: 0.00949850119650364
2023-01-21 12:05:42.992999: step: 1152/530, loss: 0.04888945072889328
2023-01-21 12:05:44.106397: step: 1156/530, loss: 0.005693912506103516
2023-01-21 12:05:45.229782: step: 1160/530, loss: 0.11261558532714844
2023-01-21 12:05:46.320727: step: 1164/530, loss: 0.027210427448153496
2023-01-21 12:05:47.474706: step: 1168/530, loss: 0.0071239471435546875
2023-01-21 12:05:48.617542: step: 1172/530, loss: 0.0012688637943938375
2023-01-21 12:05:49.719928: step: 1176/530, loss: 0.001516151474788785
2023-01-21 12:05:50.830250: step: 1180/530, loss: 0.00017681121244095266
2023-01-21 12:05:51.938597: step: 1184/530, loss: 0.00855789240449667
2023-01-21 12:05:53.051710: step: 1188/530, loss: 0.0005306244711391628
2023-01-21 12:05:54.179603: step: 1192/530, loss: 5.817413330078125e-05
2023-01-21 12:05:55.296123: step: 1196/530, loss: 3.2138825190486386e-05
2023-01-21 12:05:56.413099: step: 1200/530, loss: 0.019547080621123314
2023-01-21 12:05:57.537384: step: 1204/530, loss: 0.0007558584329672158
2023-01-21 12:05:58.663649: step: 1208/530, loss: 7.762909081066027e-05
2023-01-21 12:05:59.783155: step: 1212/530, loss: 0.0007013321155682206
2023-01-21 12:06:00.924587: step: 1216/530, loss: 0.008767413906753063
2023-01-21 12:06:02.038176: step: 1220/530, loss: 0.0013755798572674394
2023-01-21 12:06:03.169838: step: 1224/530, loss: 0.018554305657744408
2023-01-21 12:06:04.293915: step: 1228/530, loss: 0.004549598786979914
2023-01-21 12:06:05.428929: step: 1232/530, loss: 0.03680025413632393
2023-01-21 12:06:06.566150: step: 1236/530, loss: 2.593994213384576e-05
2023-01-21 12:06:07.704589: step: 1240/530, loss: 0.00108680734410882
2023-01-21 12:06:08.820646: step: 1244/530, loss: 0.1470225304365158
2023-01-21 12:06:09.981865: step: 1248/530, loss: 0.002731609158217907
2023-01-21 12:06:11.128777: step: 1252/530, loss: 0.004733753390610218
2023-01-21 12:06:12.222860: step: 1256/530, loss: 0.02032909356057644
2023-01-21 12:06:13.325259: step: 1260/530, loss: 0.0007720947614870965
2023-01-21 12:06:14.426237: step: 1264/530, loss: 0.0003725051647052169
2023-01-21 12:06:15.567527: step: 1268/530, loss: 0.00889434851706028
2023-01-21 12:06:16.690868: step: 1272/530, loss: 0.009014797396957874
2023-01-21 12:06:17.814769: step: 1276/530, loss: 0.004097938537597656
2023-01-21 12:06:18.929606: step: 1280/530, loss: 0.00443954486399889
2023-01-21 12:06:20.056074: step: 1284/530, loss: 0.014520931988954544
2023-01-21 12:06:21.166248: step: 1288/530, loss: 0.006578922271728516
2023-01-21 12:06:22.297967: step: 1292/530, loss: 0.0069830892607569695
2023-01-21 12:06:23.418950: step: 1296/530, loss: 0.014919447712600231
2023-01-21 12:06:24.517567: step: 1300/530, loss: 0.007106971926987171
2023-01-21 12:06:25.637256: step: 1304/530, loss: 0.01165771484375
2023-01-21 12:06:26.742377: step: 1308/530, loss: 0.00011310577247058973
2023-01-21 12:06:27.880380: step: 1312/530, loss: 0.020130671560764313
2023-01-21 12:06:28.997908: step: 1316/530, loss: 0.006555354222655296
2023-01-21 12:06:30.133847: step: 1320/530, loss: 0.02274184301495552
2023-01-21 12:06:31.256189: step: 1324/530, loss: 0.013712692074477673
2023-01-21 12:06:32.417032: step: 1328/530, loss: 0.0002461433468852192
2023-01-21 12:06:33.539709: step: 1332/530, loss: 0.11550893634557724
2023-01-21 12:06:34.700046: step: 1336/530, loss: 0.005647087469696999
2023-01-21 12:06:35.812931: step: 1340/530, loss: 0.016373634338378906
2023-01-21 12:06:36.960200: step: 1344/530, loss: 0.006379890255630016
2023-01-21 12:06:38.103524: step: 1348/530, loss: 0.0027209282852709293
2023-01-21 12:06:39.259156: step: 1352/530, loss: 0.0001642227143747732
2023-01-21 12:06:40.368382: step: 1356/530, loss: 6.675720942439511e-05
2023-01-21 12:06:41.493851: step: 1360/530, loss: 0.0002590179501567036
2023-01-21 12:06:42.609934: step: 1364/530, loss: -9.5367431640625e-07
2023-01-21 12:06:43.732913: step: 1368/530, loss: 0.0009847640758380294
2023-01-21 12:06:44.844487: step: 1372/530, loss: 0.00058918003924191
2023-01-21 12:06:45.979823: step: 1376/530, loss: 0.008688544854521751
2023-01-21 12:06:47.097729: step: 1380/530, loss: 0.0005656242137774825
2023-01-21 12:06:48.210086: step: 1384/530, loss: 0.03173980861902237
2023-01-21 12:06:49.336757: step: 1388/530, loss: 0.0014307021629065275
2023-01-21 12:06:50.464942: step: 1392/530, loss: 0.008229827508330345
2023-01-21 12:06:51.580533: step: 1396/530, loss: 0.0028060912154614925
2023-01-21 12:06:52.717178: step: 1400/530, loss: 0.0014524459838867188
2023-01-21 12:06:53.848299: step: 1404/530, loss: 8.544921729480848e-05
2023-01-21 12:06:54.941514: step: 1408/530, loss: 0.0009904861217364669
2023-01-21 12:06:56.046869: step: 1412/530, loss: 0.008179950527846813
2023-01-21 12:06:57.143223: step: 1416/530, loss: 0.004760551266372204
2023-01-21 12:06:58.262974: step: 1420/530, loss: 0.0002079010009765625
2023-01-21 12:06:59.360976: step: 1424/530, loss: 0.016332244500517845
2023-01-21 12:07:00.472879: step: 1428/530, loss: 0.0004106521955691278
2023-01-21 12:07:01.597308: step: 1432/530, loss: 0.002635669894516468
2023-01-21 12:07:02.698992: step: 1436/530, loss: 0.06290683895349503
2023-01-21 12:07:03.826342: step: 1440/530, loss: 0.04638051986694336
2023-01-21 12:07:04.965582: step: 1444/530, loss: 0.01473770197480917
2023-01-21 12:07:06.092439: step: 1448/530, loss: 0.005959844682365656
2023-01-21 12:07:07.246619: step: 1452/530, loss: 0.00367488875053823
2023-01-21 12:07:08.369516: step: 1456/530, loss: 0.009038162417709827
2023-01-21 12:07:09.487400: step: 1460/530, loss: 0.0011934281792491674
2023-01-21 12:07:10.618386: step: 1464/530, loss: 0.06364183127880096
2023-01-21 12:07:11.762995: step: 1468/530, loss: 0.0006703451508656144
2023-01-21 12:07:12.892545: step: 1472/530, loss: 0.041925955563783646
2023-01-21 12:07:14.045160: step: 1476/530, loss: 0.004572487436234951
2023-01-21 12:07:15.203308: step: 1480/530, loss: 0.0020816803444176912
2023-01-21 12:07:16.322275: step: 1484/530, loss: 0.049416329711675644
2023-01-21 12:07:17.456977: step: 1488/530, loss: 0.00034084319486282766
2023-01-21 12:07:18.554897: step: 1492/530, loss: 0.00028295518131926656
2023-01-21 12:07:19.667878: step: 1496/530, loss: 0.026113128289580345
2023-01-21 12:07:20.799816: step: 1500/530, loss: 0.0002037048398051411
2023-01-21 12:07:21.924344: step: 1504/530, loss: 0.00041561125544831157
2023-01-21 12:07:23.046921: step: 1508/530, loss: 0.05303821712732315
2023-01-21 12:07:24.188191: step: 1512/530, loss: 0.02392749860882759
2023-01-21 12:07:25.294289: step: 1516/530, loss: 0.0012850761413574219
2023-01-21 12:07:26.424743: step: 1520/530, loss: 0.0007338523864746094
2023-01-21 12:07:27.550368: step: 1524/530, loss: 0.03653021156787872
2023-01-21 12:07:28.673907: step: 1528/530, loss: 6.036758713889867e-05
2023-01-21 12:07:29.798560: step: 1532/530, loss: 0.0009331703186035156
2023-01-21 12:07:30.892079: step: 1536/530, loss: 2.5081633793888614e-05
2023-01-21 12:07:32.038341: step: 1540/530, loss: 0.022811509668827057
2023-01-21 12:07:33.153345: step: 1544/530, loss: 0.0011051178444176912
2023-01-21 12:07:34.286550: step: 1548/530, loss: 0.0017063140403479338
2023-01-21 12:07:35.424217: step: 1552/530, loss: 0.054059792309999466
2023-01-21 12:07:36.584176: step: 1556/530, loss: 0.0027456283569335938
2023-01-21 12:07:37.737409: step: 1560/530, loss: 0.0030750276055186987
2023-01-21 12:07:38.854939: step: 1564/530, loss: 0.005989265628159046
2023-01-21 12:07:39.969674: step: 1568/530, loss: 0.00015435219393111765
2023-01-21 12:07:41.114127: step: 1572/530, loss: 0.015616798773407936
2023-01-21 12:07:42.260039: step: 1576/530, loss: 0.01568317413330078
2023-01-21 12:07:43.354009: step: 1580/530, loss: 0.00026035308837890625
2023-01-21 12:07:44.480816: step: 1584/530, loss: 0.0040832520462572575
2023-01-21 12:07:45.624385: step: 1588/530, loss: 0.004078674595803022
2023-01-21 12:07:46.761097: step: 1592/530, loss: 0.0016664504073560238
2023-01-21 12:07:47.892890: step: 1596/530, loss: 0.0007556438213214278
2023-01-21 12:07:49.043143: step: 1600/530, loss: 0.24110937118530273
2023-01-21 12:07:50.180291: step: 1604/530, loss: 0.003024292178452015
2023-01-21 12:07:51.292072: step: 1608/530, loss: 0.00032835008460097015
2023-01-21 12:07:52.414413: step: 1612/530, loss: 6.27517729299143e-05
2023-01-21 12:07:53.545689: step: 1616/530, loss: 0.044755078852176666
2023-01-21 12:07:54.661594: step: 1620/530, loss: 0.029242467135190964
2023-01-21 12:07:55.790368: step: 1624/530, loss: 0.009463501162827015
2023-01-21 12:07:56.930974: step: 1628/530, loss: 0.0005584716564044356
2023-01-21 12:07:58.045618: step: 1632/530, loss: 0.000999069306999445
2023-01-21 12:07:59.178793: step: 1636/530, loss: 0.016724014654755592
2023-01-21 12:08:00.354170: step: 1640/530, loss: 0.03345947340130806
2023-01-21 12:08:01.501057: step: 1644/530, loss: 0.017365837469697
2023-01-21 12:08:02.630770: step: 1648/530, loss: 0.02520732954144478
2023-01-21 12:08:03.721943: step: 1652/530, loss: 0.016848569735884666
2023-01-21 12:08:04.876870: step: 1656/530, loss: 0.003930568695068359
2023-01-21 12:08:05.993516: step: 1660/530, loss: 0.9112082123756409
2023-01-21 12:08:07.123163: step: 1664/530, loss: 0.02328939363360405
2023-01-21 12:08:08.257547: step: 1668/530, loss: 0.0008285999647341669
2023-01-21 12:08:09.402467: step: 1672/530, loss: 0.07141170650720596
2023-01-21 12:08:10.507175: step: 1676/530, loss: 0.02132892608642578
2023-01-21 12:08:11.596246: step: 1680/530, loss: 0.00040721893310546875
2023-01-21 12:08:12.747754: step: 1684/530, loss: 0.010220217518508434
2023-01-21 12:08:13.890991: step: 1688/530, loss: 0.06932849436998367
2023-01-21 12:08:14.999853: step: 1692/530, loss: 0.06803293526172638
2023-01-21 12:08:16.124202: step: 1696/530, loss: 0.08004798740148544
2023-01-21 12:08:17.243077: step: 1700/530, loss: 0.0005786895635537803
2023-01-21 12:08:18.375549: step: 1704/530, loss: 0.03284940868616104
2023-01-21 12:08:19.494210: step: 1708/530, loss: 0.0008985519525595009
2023-01-21 12:08:20.606055: step: 1712/530, loss: 0.028046132996678352
2023-01-21 12:08:21.770366: step: 1716/530, loss: 0.0070892334915697575
2023-01-21 12:08:22.893207: step: 1720/530, loss: 0.0024843693245202303
2023-01-21 12:08:24.026188: step: 1724/530, loss: 0.0004583120462484658
2023-01-21 12:08:25.173358: step: 1728/530, loss: 0.0011644839541986585
2023-01-21 12:08:26.261376: step: 1732/530, loss: 0.0013417721493169665
2023-01-21 12:08:27.401038: step: 1736/530, loss: 0.019415998831391335
2023-01-21 12:08:28.515889: step: 1740/530, loss: 3.4999848139705136e-05
2023-01-21 12:08:29.665808: step: 1744/530, loss: 0.018818091601133347
2023-01-21 12:08:30.770364: step: 1748/530, loss: 0.16344338655471802
2023-01-21 12:08:31.906758: step: 1752/530, loss: 0.027814865112304688
2023-01-21 12:08:33.025216: step: 1756/530, loss: 9.880065772449598e-05
2023-01-21 12:08:34.144422: step: 1760/530, loss: 0.020299339666962624
2023-01-21 12:08:35.271732: step: 1764/530, loss: 0.0011214256519451737
2023-01-21 12:08:36.357137: step: 1768/530, loss: 0.01122283935546875
2023-01-21 12:08:37.462813: step: 1772/530, loss: 0.014534950256347656
2023-01-21 12:08:38.635579: step: 1776/530, loss: 0.00034122465876862407
2023-01-21 12:08:39.755211: step: 1780/530, loss: 0.00016117095947265625
2023-01-21 12:08:40.877163: step: 1784/530, loss: 0.051281023770570755
2023-01-21 12:08:42.029472: step: 1788/530, loss: 5.664825584972277e-05
2023-01-21 12:08:43.132367: step: 1792/530, loss: 0.033597756177186966
2023-01-21 12:08:44.252062: step: 1796/530, loss: 0.012615203857421875
2023-01-21 12:08:45.368680: step: 1800/530, loss: 0.008051300421357155
2023-01-21 12:08:46.485850: step: 1804/530, loss: 0.00047912599984556437
2023-01-21 12:08:47.603049: step: 1808/530, loss: 0.04170174524188042
2023-01-21 12:08:48.720359: step: 1812/530, loss: 0.00012054443504894152
2023-01-21 12:08:49.875865: step: 1816/530, loss: 0.005619430914521217
2023-01-21 12:08:51.035804: step: 1820/530, loss: 0.07227249443531036
2023-01-21 12:08:52.171370: step: 1824/530, loss: 0.009703541174530983
2023-01-21 12:08:53.317144: step: 1828/530, loss: 0.0016011715633794665
2023-01-21 12:08:54.468275: step: 1832/530, loss: 0.00013809205847792327
2023-01-21 12:08:55.608409: step: 1836/530, loss: 0.0012617112370207906
2023-01-21 12:08:56.721296: step: 1840/530, loss: 0.005458927247673273
2023-01-21 12:08:57.829443: step: 1844/530, loss: 0.0007686614990234375
2023-01-21 12:08:58.954438: step: 1848/530, loss: 0.06442709267139435
2023-01-21 12:09:00.083854: step: 1852/530, loss: 0.0006074905395507812
2023-01-21 12:09:01.217454: step: 1856/530, loss: 0.0691281333565712
2023-01-21 12:09:02.360115: step: 1860/530, loss: 0.013582325540482998
2023-01-21 12:09:03.482360: step: 1864/530, loss: 0.059889983385801315
2023-01-21 12:09:04.601864: step: 1868/530, loss: 0.006908893585205078
2023-01-21 12:09:05.712278: step: 1872/530, loss: 0.013760089874267578
2023-01-21 12:09:06.844789: step: 1876/530, loss: 0.6280676126480103
2023-01-21 12:09:07.949841: step: 1880/530, loss: 0.011935186572372913
2023-01-21 12:09:09.084964: step: 1884/530, loss: 0.01847400702536106
2023-01-21 12:09:10.231448: step: 1888/530, loss: 0.00018305779667571187
2023-01-21 12:09:11.331515: step: 1892/530, loss: 0.028408478945493698
2023-01-21 12:09:12.433571: step: 1896/530, loss: 0.007440042681992054
2023-01-21 12:09:13.551305: step: 1900/530, loss: 0.004222298040986061
2023-01-21 12:09:14.667444: step: 1904/530, loss: 0.00036523339804261923
2023-01-21 12:09:15.801537: step: 1908/530, loss: 0.025418665260076523
2023-01-21 12:09:16.921608: step: 1912/530, loss: 0.021502310410141945
2023-01-21 12:09:18.058769: step: 1916/530, loss: 0.0028753280639648438
2023-01-21 12:09:19.153339: step: 1920/530, loss: 0.0015292167663574219
2023-01-21 12:09:20.258248: step: 1924/530, loss: 0.019933605566620827
2023-01-21 12:09:21.378960: step: 1928/530, loss: 0.01926102675497532
2023-01-21 12:09:22.520686: step: 1932/530, loss: 0.04358353465795517
2023-01-21 12:09:23.605101: step: 1936/530, loss: 0.003917980007827282
2023-01-21 12:09:24.735623: step: 1940/530, loss: 0.002247762866318226
2023-01-21 12:09:25.868863: step: 1944/530, loss: 0.017661094665527344
2023-01-21 12:09:26.982146: step: 1948/530, loss: 0.03859272226691246
2023-01-21 12:09:28.127205: step: 1952/530, loss: 0.0017878531944006681
2023-01-21 12:09:29.246809: step: 1956/530, loss: 0.005416774656623602
2023-01-21 12:09:30.337918: step: 1960/530, loss: 0.00261096959002316
2023-01-21 12:09:31.427827: step: 1964/530, loss: 0.00031609536381438375
2023-01-21 12:09:32.568976: step: 1968/530, loss: 0.011586189270019531
2023-01-21 12:09:33.691959: step: 1972/530, loss: 0.02148418314754963
2023-01-21 12:09:34.818961: step: 1976/530, loss: 0.029879190027713776
2023-01-21 12:09:35.943878: step: 1980/530, loss: 0.024985410273075104
2023-01-21 12:09:37.042493: step: 1984/530, loss: 0.00131988525390625
2023-01-21 12:09:38.192886: step: 1988/530, loss: 0.0020587921608239412
2023-01-21 12:09:39.335727: step: 1992/530, loss: 0.0026371001731604338
2023-01-21 12:09:40.473820: step: 1996/530, loss: 0.01129989605396986
2023-01-21 12:09:41.644732: step: 2000/530, loss: 0.04454651102423668
2023-01-21 12:09:42.773664: step: 2004/530, loss: 0.13999152183532715
2023-01-21 12:09:43.906460: step: 2008/530, loss: 0.0035488130524754524
2023-01-21 12:09:45.038269: step: 2012/530, loss: 0.03099670447409153
2023-01-21 12:09:46.155105: step: 2016/530, loss: 0.005949592683464289
2023-01-21 12:09:47.300469: step: 2020/530, loss: 0.0419921912252903
2023-01-21 12:09:48.423323: step: 2024/530, loss: 0.016417408362030983
2023-01-21 12:09:49.580470: step: 2028/530, loss: 0.0002111435023834929
2023-01-21 12:09:50.719922: step: 2032/530, loss: 0.006318187806755304
2023-01-21 12:09:51.829827: step: 2036/530, loss: 0.0040801046416163445
2023-01-21 12:09:52.977626: step: 2040/530, loss: 0.023645877838134766
2023-01-21 12:09:54.109599: step: 2044/530, loss: 0.0011806488037109375
2023-01-21 12:09:55.227918: step: 2048/530, loss: 1.182556115963962e-05
2023-01-21 12:09:56.356626: step: 2052/530, loss: 0.000301551801385358
2023-01-21 12:09:57.455238: step: 2056/530, loss: 0.02842610329389572
2023-01-21 12:09:58.598024: step: 2060/530, loss: 0.005990887060761452
2023-01-21 12:09:59.743964: step: 2064/530, loss: 0.08526048809289932
2023-01-21 12:10:00.876122: step: 2068/530, loss: 0.030737783759832382
2023-01-21 12:10:01.996134: step: 2072/530, loss: 0.001333856605924666
2023-01-21 12:10:03.128651: step: 2076/530, loss: 0.00181665422860533
2023-01-21 12:10:04.249475: step: 2080/530, loss: 0.0009383201831951737
2023-01-21 12:10:05.372317: step: 2084/530, loss: 0.07532806694507599
2023-01-21 12:10:06.506043: step: 2088/530, loss: 0.05594940483570099
2023-01-21 12:10:07.648992: step: 2092/530, loss: 0.0026920319069176912
2023-01-21 12:10:08.787254: step: 2096/530, loss: 0.0017239570152014494
2023-01-21 12:10:09.917232: step: 2100/530, loss: 0.0021383287385106087
2023-01-21 12:10:11.080276: step: 2104/530, loss: 0.0056875706650316715
2023-01-21 12:10:12.256807: step: 2108/530, loss: 0.02622518688440323
2023-01-21 12:10:13.359647: step: 2112/530, loss: 0.0035455701872706413
2023-01-21 12:10:14.489645: step: 2116/530, loss: 0.0014051437610760331
2023-01-21 12:10:15.611652: step: 2120/530, loss: 0.0004934311145916581
==================================================
Loss: 0.020
--------------------
Dev: {'event': {'p': 0.6012591815320042, 'r': 0.762982689747004, 'f1': 0.6725352112676055}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6435969868173258, 'r': 0.7811428571428571, 'f1': 0.7057305110996387}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5116279069767442, 'r': 0.8148148148148148, 'f1': 0.6285714285714286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.6166666666666667, 'r': 0.5873015873015873, 'f1': 0.6016260162601625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.43902439024390244, 'r': 0.5, 'f1': 0.4675324675324676}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 21
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:10:56.033307: step: 4/530, loss: 0.49011632800102234
2023-01-21 12:10:57.152038: step: 8/530, loss: 0.004227065946906805
2023-01-21 12:10:58.270698: step: 12/530, loss: 0.016133999451994896
2023-01-21 12:10:59.400207: step: 16/530, loss: 0.0037785531021654606
2023-01-21 12:11:00.485395: step: 20/530, loss: 0.010957717895507812
2023-01-21 12:11:01.660789: step: 24/530, loss: 0.053522489964962006
2023-01-21 12:11:02.850292: step: 28/530, loss: 0.0015806198352947831
2023-01-21 12:11:03.992430: step: 32/530, loss: 0.038451384752988815
2023-01-21 12:11:05.106176: step: 36/530, loss: 0.00011548996553756297
2023-01-21 12:11:06.234727: step: 40/530, loss: 0.03133726119995117
2023-01-21 12:11:07.350976: step: 44/530, loss: 0.03824024274945259
2023-01-21 12:11:08.497557: step: 48/530, loss: 0.003679466200992465
2023-01-21 12:11:09.611837: step: 52/530, loss: 0.00012350082397460938
2023-01-21 12:11:10.733085: step: 56/530, loss: 0.01638650894165039
2023-01-21 12:11:11.844388: step: 60/530, loss: 0.019202042371034622
2023-01-21 12:11:13.000437: step: 64/530, loss: 0.0016574382316321135
2023-01-21 12:11:14.148639: step: 68/530, loss: 0.00110120780300349
2023-01-21 12:11:15.261487: step: 72/530, loss: 1.391005277633667
2023-01-21 12:11:16.368048: step: 76/530, loss: 0.0001434326113667339
2023-01-21 12:11:17.481154: step: 80/530, loss: 0.08163568377494812
2023-01-21 12:11:18.624650: step: 84/530, loss: 0.005132961552590132
2023-01-21 12:11:19.728388: step: 88/530, loss: 0.007859230041503906
2023-01-21 12:11:20.843003: step: 92/530, loss: 0.0036460875999182463
2023-01-21 12:11:21.951219: step: 96/530, loss: 0.04182014614343643
2023-01-21 12:11:23.075328: step: 100/530, loss: 0.017016984522342682
2023-01-21 12:11:24.193087: step: 104/530, loss: 0.0027931213844567537
2023-01-21 12:11:25.317932: step: 108/530, loss: 2.2172927856445312e-05
2023-01-21 12:11:26.416975: step: 112/530, loss: 0.0014137268299236894
2023-01-21 12:11:27.543416: step: 116/530, loss: 0.0013768672943115234
2023-01-21 12:11:28.644203: step: 120/530, loss: 0.0009717941284179688
2023-01-21 12:11:29.761332: step: 124/530, loss: 0.10848331451416016
2023-01-21 12:11:30.880654: step: 128/530, loss: 1.6451529264450073
2023-01-21 12:11:31.992390: step: 132/530, loss: 0.0010001182090491056
2023-01-21 12:11:33.140105: step: 136/530, loss: 0.019113779067993164
2023-01-21 12:11:34.256533: step: 140/530, loss: 0.16156692802906036
2023-01-21 12:11:35.369818: step: 144/530, loss: 2.5177003408316523e-05
2023-01-21 12:11:36.482484: step: 148/530, loss: 0.0006868839845992625
2023-01-21 12:11:37.600463: step: 152/530, loss: 0.0230528824031353
2023-01-21 12:11:38.701797: step: 156/530, loss: 0.001032161759212613
2023-01-21 12:11:39.824839: step: 160/530, loss: 0.0005208969232626259
2023-01-21 12:11:40.939126: step: 164/530, loss: 0.017513656988739967
2023-01-21 12:11:42.077756: step: 168/530, loss: 0.001582241035066545
2023-01-21 12:11:43.181836: step: 172/530, loss: 0.0005973338847979903
2023-01-21 12:11:44.334896: step: 176/530, loss: 0.0019715309608727694
2023-01-21 12:11:45.425534: step: 180/530, loss: 0.009799622930586338
2023-01-21 12:11:46.558533: step: 184/530, loss: 0.014711951836943626
2023-01-21 12:11:47.677653: step: 188/530, loss: 0.0002263069327455014
2023-01-21 12:11:48.772641: step: 192/530, loss: 0.0021007535979151726
2023-01-21 12:11:49.880717: step: 196/530, loss: 0.000976991606876254
2023-01-21 12:11:50.988843: step: 200/530, loss: 0.010377217084169388
2023-01-21 12:11:52.117946: step: 204/530, loss: 0.01644148863852024
2023-01-21 12:11:53.239119: step: 208/530, loss: 0.038106538355350494
2023-01-21 12:11:54.365808: step: 212/530, loss: 0.002868270967155695
2023-01-21 12:11:55.495978: step: 216/530, loss: 5.197525388211943e-05
2023-01-21 12:11:56.604189: step: 220/530, loss: 0.0011104702716693282
2023-01-21 12:11:57.733696: step: 224/530, loss: 0.013138055801391602
2023-01-21 12:11:58.878176: step: 228/530, loss: 0.016677284613251686
2023-01-21 12:12:00.001518: step: 232/530, loss: 0.0003247261047363281
2023-01-21 12:12:01.132705: step: 236/530, loss: 0.0007629871251992881
2023-01-21 12:12:02.251042: step: 240/530, loss: 0.0004142761172261089
2023-01-21 12:12:03.364702: step: 244/530, loss: 4.3201445805607364e-05
2023-01-21 12:12:04.511956: step: 248/530, loss: 0.02846856229007244
2023-01-21 12:12:05.642823: step: 252/530, loss: 0.012844085693359375
2023-01-21 12:12:06.765909: step: 256/530, loss: 0.020685385912656784
2023-01-21 12:12:07.891135: step: 260/530, loss: 0.01350174006074667
2023-01-21 12:12:09.059651: step: 264/530, loss: 0.00044803618220612407
2023-01-21 12:12:10.184625: step: 268/530, loss: 0.00299167656339705
2023-01-21 12:12:11.288789: step: 272/530, loss: 0.009971809573471546
2023-01-21 12:12:12.394181: step: 276/530, loss: 0.024344826117157936
2023-01-21 12:12:13.522826: step: 280/530, loss: 0.004234123043715954
2023-01-21 12:12:14.625174: step: 284/530, loss: 0.01858968660235405
2023-01-21 12:12:15.736563: step: 288/530, loss: 0.0006374359363690019
2023-01-21 12:12:16.886577: step: 292/530, loss: 0.00792074203491211
2023-01-21 12:12:18.015670: step: 296/530, loss: 0.00044841767521575093
2023-01-21 12:12:19.135979: step: 300/530, loss: 0.6544893383979797
2023-01-21 12:12:20.256076: step: 304/530, loss: 0.036920737475156784
2023-01-21 12:12:21.408058: step: 308/530, loss: 0.034932900220155716
2023-01-21 12:12:22.513748: step: 312/530, loss: 0.0008483887067995965
2023-01-21 12:12:23.652928: step: 316/530, loss: 0.01162796001881361
2023-01-21 12:12:24.824852: step: 320/530, loss: 0.006617164704948664
2023-01-21 12:12:25.959106: step: 324/530, loss: 0.10611972957849503
2023-01-21 12:12:27.113542: step: 328/530, loss: 0.004826927557587624
2023-01-21 12:12:28.278374: step: 332/530, loss: 0.003083944320678711
2023-01-21 12:12:29.414246: step: 336/530, loss: 0.0007933616871014237
2023-01-21 12:12:30.524752: step: 340/530, loss: 0.020416736602783203
2023-01-21 12:12:31.658080: step: 344/530, loss: 0.04075679928064346
2023-01-21 12:12:32.777137: step: 348/530, loss: 0.00032739638118073344
2023-01-21 12:12:33.909114: step: 352/530, loss: 0.12937593460083008
2023-01-21 12:12:35.028261: step: 356/530, loss: 0.03532858192920685
2023-01-21 12:12:36.156572: step: 360/530, loss: 0.011431765742599964
2023-01-21 12:12:37.306411: step: 364/530, loss: 0.012261486612260342
2023-01-21 12:12:38.413309: step: 368/530, loss: 0.00037374498788267374
2023-01-21 12:12:39.525966: step: 372/530, loss: 0.023598194122314453
2023-01-21 12:12:40.672607: step: 376/530, loss: 0.0346694141626358
2023-01-21 12:12:41.796539: step: 380/530, loss: 0.004454994574189186
2023-01-21 12:12:42.950446: step: 384/530, loss: 0.0006451606750488281
2023-01-21 12:12:44.057427: step: 388/530, loss: 8.22067231638357e-05
2023-01-21 12:12:45.144317: step: 392/530, loss: 0.0007439613109454513
2023-01-21 12:12:46.298854: step: 396/530, loss: 0.0017996788956224918
2023-01-21 12:12:47.413895: step: 400/530, loss: 0.006274128332734108
2023-01-21 12:12:48.521152: step: 404/530, loss: 0.003052616026252508
2023-01-21 12:12:49.634179: step: 408/530, loss: 0.0006673812749795616
2023-01-21 12:12:50.812443: step: 412/530, loss: 0.014032173901796341
2023-01-21 12:12:51.905386: step: 416/530, loss: 0.0003649711434263736
2023-01-21 12:12:53.008982: step: 420/530, loss: 0.00013265610323287547
2023-01-21 12:12:54.154213: step: 424/530, loss: 0.07189436256885529
2023-01-21 12:12:55.249267: step: 428/530, loss: 0.0009311676258221269
2023-01-21 12:12:56.373168: step: 432/530, loss: 0.02896256558597088
2023-01-21 12:12:57.506409: step: 436/530, loss: 0.0015769959427416325
2023-01-21 12:12:58.600534: step: 440/530, loss: 0.0001618385431356728
2023-01-21 12:12:59.746927: step: 444/530, loss: 0.004143416881561279
2023-01-21 12:13:00.864291: step: 448/530, loss: 0.0001451790303690359
2023-01-21 12:13:01.980159: step: 452/530, loss: 0.004675006493926048
2023-01-21 12:13:03.136258: step: 456/530, loss: 3.643035961431451e-05
2023-01-21 12:13:04.259194: step: 460/530, loss: 0.0003921985626220703
2023-01-21 12:13:05.379784: step: 464/530, loss: 0.008510875515639782
2023-01-21 12:13:06.520327: step: 468/530, loss: 0.00013465882511809468
2023-01-21 12:13:07.674780: step: 472/530, loss: 0.006438923068344593
2023-01-21 12:13:08.794116: step: 476/530, loss: 0.0075547220185399055
2023-01-21 12:13:09.941595: step: 480/530, loss: 0.0010969162685796618
2023-01-21 12:13:11.038716: step: 484/530, loss: 0.0026235580444335938
2023-01-21 12:13:12.182419: step: 488/530, loss: 0.32693445682525635
2023-01-21 12:13:13.295765: step: 492/530, loss: 0.0026502609252929688
2023-01-21 12:13:14.418149: step: 496/530, loss: 6.46591215627268e-05
2023-01-21 12:13:15.525305: step: 500/530, loss: 0.7742407321929932
2023-01-21 12:13:16.649547: step: 504/530, loss: 0.0012416839599609375
2023-01-21 12:13:17.768613: step: 508/530, loss: 0.00016717911057639867
2023-01-21 12:13:18.894742: step: 512/530, loss: 0.00022783280292060226
2023-01-21 12:13:20.035416: step: 516/530, loss: 0.002860164502635598
2023-01-21 12:13:21.185951: step: 520/530, loss: 0.0006827354663982987
2023-01-21 12:13:22.341821: step: 524/530, loss: 0.07887883484363556
2023-01-21 12:13:23.480210: step: 528/530, loss: 0.00046096445294097066
2023-01-21 12:13:24.565264: step: 532/530, loss: 0.014565085992217064
2023-01-21 12:13:25.697499: step: 536/530, loss: 0.006557941902428865
2023-01-21 12:13:26.801151: step: 540/530, loss: 4.673004150390625e-05
2023-01-21 12:13:27.918872: step: 544/530, loss: 3.185272362316027e-05
2023-01-21 12:13:29.038581: step: 548/530, loss: 0.0029134750366210938
2023-01-21 12:13:30.173207: step: 552/530, loss: 0.058595798909664154
2023-01-21 12:13:31.331044: step: 556/530, loss: 0.0006774902576580644
2023-01-21 12:13:32.446231: step: 560/530, loss: 0.014229201711714268
2023-01-21 12:13:33.578966: step: 564/530, loss: 0.0013820648891851306
2023-01-21 12:13:34.706626: step: 568/530, loss: 0.0044297222048044205
2023-01-21 12:13:35.837792: step: 572/530, loss: 0.022774314507842064
2023-01-21 12:13:36.996529: step: 576/530, loss: 0.029187774285674095
2023-01-21 12:13:38.118877: step: 580/530, loss: 0.0016811371315270662
2023-01-21 12:13:39.220602: step: 584/530, loss: 0.0011992455692961812
2023-01-21 12:13:40.335560: step: 588/530, loss: 0.055848024785518646
2023-01-21 12:13:41.457894: step: 592/530, loss: 0.3081279993057251
2023-01-21 12:13:42.605525: step: 596/530, loss: 0.013493156060576439
2023-01-21 12:13:43.749834: step: 600/530, loss: 0.0009476661798544228
2023-01-21 12:13:44.855200: step: 604/530, loss: 0.0005537033430300653
2023-01-21 12:13:45.969864: step: 608/530, loss: 0.0027714730240404606
2023-01-21 12:13:47.086598: step: 612/530, loss: 0.00194635393563658
2023-01-21 12:13:48.183613: step: 616/530, loss: 0.0005013465997762978
2023-01-21 12:13:49.290509: step: 620/530, loss: 0.01245727576315403
2023-01-21 12:13:50.417245: step: 624/530, loss: 0.050360869616270065
2023-01-21 12:13:51.544727: step: 628/530, loss: 0.001125335693359375
2023-01-21 12:13:52.674899: step: 632/530, loss: 0.014724541455507278
2023-01-21 12:13:53.775318: step: 636/530, loss: 0.0006517410511150956
2023-01-21 12:13:54.885362: step: 640/530, loss: 0.00015707015700172633
2023-01-21 12:13:56.016886: step: 644/530, loss: 0.02399311028420925
2023-01-21 12:13:57.140173: step: 648/530, loss: 0.0007123947143554688
2023-01-21 12:13:58.259379: step: 652/530, loss: 5.0735470722429454e-05
2023-01-21 12:13:59.392007: step: 656/530, loss: 0.7012096643447876
2023-01-21 12:14:00.534295: step: 660/530, loss: 0.6703810691833496
2023-01-21 12:14:01.658824: step: 664/530, loss: 0.008697891607880592
2023-01-21 12:14:02.764962: step: 668/530, loss: 0.00036010745679959655
2023-01-21 12:14:03.883080: step: 672/530, loss: 0.006646919529885054
2023-01-21 12:14:04.994468: step: 676/530, loss: 0.0017990112537518144
2023-01-21 12:14:06.109516: step: 680/530, loss: 0.013575363904237747
2023-01-21 12:14:07.220558: step: 684/530, loss: 0.021174049004912376
2023-01-21 12:14:08.329293: step: 688/530, loss: 0.004755496978759766
2023-01-21 12:14:09.451429: step: 692/530, loss: 0.00276699080131948
2023-01-21 12:14:10.604523: step: 696/530, loss: 0.02060394361615181
2023-01-21 12:14:11.720051: step: 700/530, loss: 0.0006732940673828125
2023-01-21 12:14:12.863202: step: 704/530, loss: 3.757476952159777e-05
2023-01-21 12:14:14.027786: step: 708/530, loss: 0.003176403231918812
2023-01-21 12:14:15.120536: step: 712/530, loss: 0.0019120455253869295
2023-01-21 12:14:16.237465: step: 716/530, loss: 0.0006477356073446572
2023-01-21 12:14:17.374598: step: 720/530, loss: 0.005207061767578125
2023-01-21 12:14:18.481527: step: 724/530, loss: 0.013041352853178978
2023-01-21 12:14:19.584689: step: 728/530, loss: 0.02233780175447464
2023-01-21 12:14:20.714202: step: 732/530, loss: 2.670288040462765e-06
2023-01-21 12:14:21.835463: step: 736/530, loss: 0.0144195556640625
2023-01-21 12:14:22.976114: step: 740/530, loss: 0.008275222964584827
2023-01-21 12:14:24.097552: step: 744/530, loss: 0.02954578399658203
2023-01-21 12:14:25.244258: step: 748/530, loss: -8.296966370835435e-06
2023-01-21 12:14:26.375946: step: 752/530, loss: 0.004961872007697821
2023-01-21 12:14:27.485658: step: 756/530, loss: 0.0013607979053631425
2023-01-21 12:14:28.580028: step: 760/530, loss: 0.0008280753972940147
2023-01-21 12:14:29.697202: step: 764/530, loss: 0.02119007334113121
2023-01-21 12:14:30.820636: step: 768/530, loss: 0.013470363803207874
2023-01-21 12:14:31.950804: step: 772/530, loss: 0.015328217297792435
2023-01-21 12:14:33.101301: step: 776/530, loss: 0.0005252838600426912
2023-01-21 12:14:34.198978: step: 780/530, loss: 2.365112231927924e-05
2023-01-21 12:14:35.328491: step: 784/530, loss: 0.00020437240891624242
2023-01-21 12:14:36.450908: step: 788/530, loss: 0.01071538869291544
2023-01-21 12:14:37.578224: step: 792/530, loss: 0.022870158776640892
2023-01-21 12:14:38.733466: step: 796/530, loss: 0.0002044677676167339
2023-01-21 12:14:39.853478: step: 800/530, loss: 0.00010385512723587453
2023-01-21 12:14:40.973665: step: 804/530, loss: 0.033193208277225494
2023-01-21 12:14:42.102072: step: 808/530, loss: 0.007413006387650967
2023-01-21 12:14:43.209854: step: 812/530, loss: 0.022733021527528763
2023-01-21 12:14:44.333528: step: 816/530, loss: 8.97407517186366e-05
2023-01-21 12:14:45.476287: step: 820/530, loss: 0.0007865906227380037
2023-01-21 12:14:46.577294: step: 824/530, loss: 0.0020891190506517887
2023-01-21 12:14:47.704125: step: 828/530, loss: 0.023992346599698067
2023-01-21 12:14:48.821919: step: 832/530, loss: 0.0011586189502850175
2023-01-21 12:14:49.941408: step: 836/530, loss: 0.05891776457428932
2023-01-21 12:14:51.084882: step: 840/530, loss: 0.021409176290035248
2023-01-21 12:14:52.235371: step: 844/530, loss: 0.0001924514799611643
2023-01-21 12:14:53.362864: step: 848/530, loss: 0.0001560211239848286
2023-01-21 12:14:54.480880: step: 852/530, loss: 0.0015741348033770919
2023-01-21 12:14:55.595488: step: 856/530, loss: 0.0003898620489053428
2023-01-21 12:14:56.702144: step: 860/530, loss: 0.016292572021484375
2023-01-21 12:14:57.839567: step: 864/530, loss: 0.03315143659710884
2023-01-21 12:14:58.916027: step: 868/530, loss: 0.003843116806820035
2023-01-21 12:15:00.045274: step: 872/530, loss: 3.9839746023062617e-05
2023-01-21 12:15:01.173575: step: 876/530, loss: 0.0007068634149618447
2023-01-21 12:15:02.357350: step: 880/530, loss: 0.006881332024931908
2023-01-21 12:15:03.478720: step: 884/530, loss: 0.003958416171371937
2023-01-21 12:15:04.588528: step: 888/530, loss: 0.01683931238949299
2023-01-21 12:15:05.708719: step: 892/530, loss: 0.0015444993041455746
2023-01-21 12:15:06.813010: step: 896/530, loss: 0.0019664764404296875
2023-01-21 12:15:07.950478: step: 900/530, loss: 0.01835479773581028
2023-01-21 12:15:09.051516: step: 904/530, loss: 0.002390289446339011
2023-01-21 12:15:10.144207: step: 908/530, loss: 0.032248880714178085
2023-01-21 12:15:11.269354: step: 912/530, loss: 0.0010766983032226562
2023-01-21 12:15:12.399794: step: 916/530, loss: 0.00036602019099518657
2023-01-21 12:15:13.617877: step: 920/530, loss: 0.003584289690479636
2023-01-21 12:15:14.730055: step: 924/530, loss: 0.0001146316499216482
2023-01-21 12:15:15.850955: step: 928/530, loss: 0.0035695554688572884
2023-01-21 12:15:16.962704: step: 932/530, loss: 0.00010061264038085938
2023-01-21 12:15:18.050125: step: 936/530, loss: 0.0019312859512865543
2023-01-21 12:15:19.139578: step: 940/530, loss: 0.0008093834039755166
2023-01-21 12:15:20.259950: step: 944/530, loss: 0.011751365847885609
2023-01-21 12:15:21.372783: step: 948/530, loss: 0.0005085945012979209
2023-01-21 12:15:22.480209: step: 952/530, loss: 0.002727604005485773
2023-01-21 12:15:23.613160: step: 956/530, loss: 4.682540748035535e-05
2023-01-21 12:15:24.733546: step: 960/530, loss: 0.00035858154296875
2023-01-21 12:15:25.859506: step: 964/530, loss: 0.00015647412510588765
2023-01-21 12:15:26.976816: step: 968/530, loss: 0.01577177084982395
2023-01-21 12:15:28.092249: step: 972/530, loss: 0.00025310515775345266
2023-01-21 12:15:29.196020: step: 976/530, loss: 0.006222057621926069
2023-01-21 12:15:30.311804: step: 980/530, loss: 0.012386512942612171
2023-01-21 12:15:31.437785: step: 984/530, loss: 0.015457344241440296
2023-01-21 12:15:32.590656: step: 988/530, loss: 0.0035745620261877775
2023-01-21 12:15:33.710644: step: 992/530, loss: 0.044710446149110794
2023-01-21 12:15:34.840887: step: 996/530, loss: 4.196166628389619e-06
2023-01-21 12:15:35.976057: step: 1000/530, loss: 0.0006580352783203125
2023-01-21 12:15:37.093921: step: 1004/530, loss: 0.03691520914435387
2023-01-21 12:15:38.223958: step: 1008/530, loss: 0.015237427316606045
2023-01-21 12:15:39.353881: step: 1012/530, loss: 0.0037853240501135588
2023-01-21 12:15:40.458152: step: 1016/530, loss: 0.020543480291962624
2023-01-21 12:15:41.572202: step: 1020/530, loss: 0.0017120360862463713
2023-01-21 12:15:42.711018: step: 1024/530, loss: 0.0008113860967569053
2023-01-21 12:15:43.839978: step: 1028/530, loss: 0.0001789093075785786
2023-01-21 12:15:44.965085: step: 1032/530, loss: 0.03347358852624893
2023-01-21 12:15:46.103725: step: 1036/530, loss: 0.0534856803715229
2023-01-21 12:15:47.236868: step: 1040/530, loss: 0.013461876660585403
2023-01-21 12:15:48.372164: step: 1044/530, loss: 0.003422737354412675
2023-01-21 12:15:49.493752: step: 1048/530, loss: 0.018561745062470436
2023-01-21 12:15:50.602687: step: 1052/530, loss: 0.1254653036594391
2023-01-21 12:15:51.697988: step: 1056/530, loss: 0.0005100250127725303
2023-01-21 12:15:52.824185: step: 1060/530, loss: 0.02449646033346653
2023-01-21 12:15:53.949780: step: 1064/530, loss: 0.025200605392456055
2023-01-21 12:15:55.092375: step: 1068/530, loss: 0.027215957641601562
2023-01-21 12:15:56.217226: step: 1072/530, loss: 0.01806488074362278
2023-01-21 12:15:57.329582: step: 1076/530, loss: 0.1416957825422287
2023-01-21 12:15:58.455627: step: 1080/530, loss: 0.01165008544921875
2023-01-21 12:15:59.577904: step: 1084/530, loss: -1.9073486328125e-06
2023-01-21 12:16:00.695543: step: 1088/530, loss: 0.013349246233701706
2023-01-21 12:16:01.827596: step: 1092/530, loss: 0.00018806458683684468
2023-01-21 12:16:02.953149: step: 1096/530, loss: 0.005420207977294922
2023-01-21 12:16:04.054734: step: 1100/530, loss: 0.009965182282030582
2023-01-21 12:16:05.173713: step: 1104/530, loss: 0.016663599759340286
2023-01-21 12:16:06.297605: step: 1108/530, loss: 0.022583769634366035
2023-01-21 12:16:07.395550: step: 1112/530, loss: 0.03428182750940323
2023-01-21 12:16:08.491897: step: 1116/530, loss: 0.01601552963256836
2023-01-21 12:16:09.633680: step: 1120/530, loss: 0.03004913404583931
2023-01-21 12:16:10.790443: step: 1124/530, loss: 0.019466208294034004
2023-01-21 12:16:11.936867: step: 1128/530, loss: 0.03588066250085831
2023-01-21 12:16:13.045027: step: 1132/530, loss: 0.0003498077276162803
2023-01-21 12:16:14.171377: step: 1136/530, loss: 0.028367996215820312
2023-01-21 12:16:15.289891: step: 1140/530, loss: 0.00011868477304233238
2023-01-21 12:16:16.400881: step: 1144/530, loss: 0.0023441314697265625
2023-01-21 12:16:17.491430: step: 1148/530, loss: 0.0007661819108761847
2023-01-21 12:16:18.617764: step: 1152/530, loss: 0.0500730499625206
2023-01-21 12:16:19.738974: step: 1156/530, loss: 8.058547973632812e-05
2023-01-21 12:16:20.872756: step: 1160/530, loss: 0.00014963149442337453
2023-01-21 12:16:21.974951: step: 1164/530, loss: 0.020379066467285156
2023-01-21 12:16:23.090789: step: 1168/530, loss: 0.0016283035511150956
2023-01-21 12:16:24.224583: step: 1172/530, loss: 0.023729609325528145
2023-01-21 12:16:25.332450: step: 1176/530, loss: 0.007485914509743452
2023-01-21 12:16:26.474131: step: 1180/530, loss: 0.02717299573123455
2023-01-21 12:16:27.605885: step: 1184/530, loss: 0.00108165736310184
2023-01-21 12:16:28.708002: step: 1188/530, loss: 0.0002513885556254536
2023-01-21 12:16:29.828756: step: 1192/530, loss: 0.00034160615177825093
2023-01-21 12:16:30.950394: step: 1196/530, loss: 5.4931642807787284e-05
2023-01-21 12:16:32.089166: step: 1200/530, loss: 0.00019159316434524953
2023-01-21 12:16:33.223369: step: 1204/530, loss: 4.692077709478326e-05
2023-01-21 12:16:34.366404: step: 1208/530, loss: 0.0010395051212981343
2023-01-21 12:16:35.460471: step: 1212/530, loss: 0.0017034531338140368
2023-01-21 12:16:36.582573: step: 1216/530, loss: 0.054489992558956146
2023-01-21 12:16:37.703574: step: 1220/530, loss: 0.007573127746582031
2023-01-21 12:16:38.837844: step: 1224/530, loss: 0.005268859677016735
2023-01-21 12:16:39.954750: step: 1228/530, loss: 0.0612645149230957
2023-01-21 12:16:41.057394: step: 1232/530, loss: 0.00707740755751729
2023-01-21 12:16:42.170431: step: 1236/530, loss: 0.0005743980873376131
2023-01-21 12:16:43.290453: step: 1240/530, loss: 0.0228118896484375
2023-01-21 12:16:44.443460: step: 1244/530, loss: 0.00022711753263138235
2023-01-21 12:16:45.535180: step: 1248/530, loss: 0.00017818213382270187
2023-01-21 12:16:46.668139: step: 1252/530, loss: 0.017669677734375
2023-01-21 12:16:47.788618: step: 1256/530, loss: 0.11473388969898224
2023-01-21 12:16:48.893435: step: 1260/530, loss: 0.004238129127770662
2023-01-21 12:16:50.049028: step: 1264/530, loss: 0.005385208409279585
2023-01-21 12:16:51.159464: step: 1268/530, loss: 0.0036874772049486637
2023-01-21 12:16:52.286613: step: 1272/530, loss: 0.0019821166060864925
2023-01-21 12:16:53.401703: step: 1276/530, loss: 0.004180908203125
2023-01-21 12:16:54.507231: step: 1280/530, loss: 9.670258441474289e-05
2023-01-21 12:16:55.651542: step: 1284/530, loss: 0.07886752486228943
2023-01-21 12:16:56.783286: step: 1288/530, loss: 0.0017394066089764237
2023-01-21 12:16:57.902264: step: 1292/530, loss: 0.0011807441478595138
2023-01-21 12:16:59.013295: step: 1296/530, loss: 0.18033771216869354
2023-01-21 12:17:00.135580: step: 1300/530, loss: 0.008785533718764782
2023-01-21 12:17:01.263210: step: 1304/530, loss: 0.03551235422492027
2023-01-21 12:17:02.366760: step: 1308/530, loss: 0.009478283114731312
2023-01-21 12:17:03.508142: step: 1312/530, loss: 0.03144025802612305
2023-01-21 12:17:04.614682: step: 1316/530, loss: 0.011328602209687233
2023-01-21 12:17:05.745518: step: 1320/530, loss: 0.010186529718339443
2023-01-21 12:17:06.859250: step: 1324/530, loss: 0.00021009445481467992
2023-01-21 12:17:07.947077: step: 1328/530, loss: 0.0022800446022301912
2023-01-21 12:17:09.080304: step: 1332/530, loss: 9.384155418956652e-05
2023-01-21 12:17:10.209538: step: 1336/530, loss: 0.013181495480239391
2023-01-21 12:17:11.343882: step: 1340/530, loss: 0.000575637852307409
2023-01-21 12:17:12.509584: step: 1344/530, loss: 0.0006193161243572831
2023-01-21 12:17:13.624660: step: 1348/530, loss: 0.005352592561393976
2023-01-21 12:17:14.749918: step: 1352/530, loss: 0.001437807222828269
2023-01-21 12:17:15.890227: step: 1356/530, loss: 0.002618980361148715
2023-01-21 12:17:17.026297: step: 1360/530, loss: 0.02991018444299698
2023-01-21 12:17:18.171686: step: 1364/530, loss: 0.0008039474487304688
2023-01-21 12:17:19.286892: step: 1368/530, loss: 0.05861339718103409
2023-01-21 12:17:20.386582: step: 1372/530, loss: 0.0026342393830418587
2023-01-21 12:17:21.532968: step: 1376/530, loss: 0.04842682182788849
2023-01-21 12:17:22.654889: step: 1380/530, loss: 0.009973621927201748
2023-01-21 12:17:23.761086: step: 1384/530, loss: 5.359649730962701e-05
2023-01-21 12:17:24.874311: step: 1388/530, loss: 0.003119564149528742
2023-01-21 12:17:26.015998: step: 1392/530, loss: 0.20365695655345917
2023-01-21 12:17:27.151763: step: 1396/530, loss: 9.560585567669477e-06
2023-01-21 12:17:28.277254: step: 1400/530, loss: 0.0046735769137740135
2023-01-21 12:17:29.404378: step: 1404/530, loss: 0.0557897575199604
2023-01-21 12:17:30.535600: step: 1408/530, loss: 0.00032682419987395406
2023-01-21 12:17:31.679218: step: 1412/530, loss: 0.00325167179107666
2023-01-21 12:17:32.878067: step: 1416/530, loss: 0.0004341125604696572
2023-01-21 12:17:33.987721: step: 1420/530, loss: 0.01347370259463787
2023-01-21 12:17:35.103721: step: 1424/530, loss: 0.0026268004439771175
2023-01-21 12:17:36.250298: step: 1428/530, loss: 0.006257152650505304
2023-01-21 12:17:37.375802: step: 1432/530, loss: 0.02206411398947239
2023-01-21 12:17:38.513148: step: 1436/530, loss: 0.0002388000430073589
2023-01-21 12:17:39.631180: step: 1440/530, loss: 0.012933732010424137
2023-01-21 12:17:40.754079: step: 1444/530, loss: 0.0028773308731615543
2023-01-21 12:17:41.882219: step: 1448/530, loss: 0.0375092513859272
2023-01-21 12:17:43.006394: step: 1452/530, loss: 0.0008903503185138106
2023-01-21 12:17:44.130810: step: 1456/530, loss: 0.00021238328190520406
2023-01-21 12:17:45.232286: step: 1460/530, loss: 1.5333126783370972
2023-01-21 12:17:46.324833: step: 1464/530, loss: 0.02745637856423855
2023-01-21 12:17:47.435569: step: 1468/530, loss: 0.0003685951523948461
2023-01-21 12:17:48.578290: step: 1472/530, loss: 0.022286606952548027
2023-01-21 12:17:49.663886: step: 1476/530, loss: 0.004867267794907093
2023-01-21 12:17:50.777571: step: 1480/530, loss: 0.00026416778564453125
2023-01-21 12:17:51.904143: step: 1484/530, loss: 0.020837783813476562
2023-01-21 12:17:53.021062: step: 1488/530, loss: 0.02726440504193306
2023-01-21 12:17:54.145514: step: 1492/530, loss: 0.0009504318586550653
2023-01-21 12:17:55.267758: step: 1496/530, loss: 0.011907387524843216
2023-01-21 12:17:56.424809: step: 1500/530, loss: 0.012531662359833717
2023-01-21 12:17:57.533538: step: 1504/530, loss: 0.6905828714370728
2023-01-21 12:17:58.657643: step: 1508/530, loss: 0.008626366034150124
2023-01-21 12:17:59.782255: step: 1512/530, loss: 0.0004220009141135961
2023-01-21 12:18:00.925370: step: 1516/530, loss: 0.003879356663674116
2023-01-21 12:18:02.020435: step: 1520/530, loss: 0.0003732681507244706
2023-01-21 12:18:03.137721: step: 1524/530, loss: 0.007319641299545765
2023-01-21 12:18:04.261194: step: 1528/530, loss: 0.0008094788063317537
2023-01-21 12:18:05.370827: step: 1532/530, loss: 0.00196247105486691
2023-01-21 12:18:06.467780: step: 1536/530, loss: 0.00027985573979094625
2023-01-21 12:18:07.585892: step: 1540/530, loss: 0.004294252954423428
2023-01-21 12:18:08.692867: step: 1544/530, loss: 0.00021991730318404734
2023-01-21 12:18:09.811311: step: 1548/530, loss: 0.0010298729175701737
2023-01-21 12:18:10.920749: step: 1552/530, loss: 0.04912203177809715
2023-01-21 12:18:12.049455: step: 1556/530, loss: 0.0023814202286303043
2023-01-21 12:18:13.151020: step: 1560/530, loss: 0.00015296936908271164
2023-01-21 12:18:14.261193: step: 1564/530, loss: -6.4849850787140895e-06
2023-01-21 12:18:15.373752: step: 1568/530, loss: 0.000583267246838659
2023-01-21 12:18:16.468956: step: 1572/530, loss: 0.002432107925415039
2023-01-21 12:18:17.586925: step: 1576/530, loss: 0.10006694495677948
2023-01-21 12:18:18.699622: step: 1580/530, loss: 0.011987018398940563
2023-01-21 12:18:19.836170: step: 1584/530, loss: 0.019217681139707565
2023-01-21 12:18:20.980488: step: 1588/530, loss: 0.008651352487504482
2023-01-21 12:18:22.074195: step: 1592/530, loss: 0.0003994941362179816
2023-01-21 12:18:23.190973: step: 1596/530, loss: 0.001673793769441545
2023-01-21 12:18:24.313709: step: 1600/530, loss: 0.04468126595020294
2023-01-21 12:18:25.448242: step: 1604/530, loss: 0.0004604339774232358
2023-01-21 12:18:26.572771: step: 1608/530, loss: 0.001903533935546875
2023-01-21 12:18:27.692619: step: 1612/530, loss: 0.02284236066043377
2023-01-21 12:18:28.833638: step: 1616/530, loss: 0.0006439209100790322
2023-01-21 12:18:29.953580: step: 1620/530, loss: 0.04527554661035538
2023-01-21 12:18:31.063293: step: 1624/530, loss: 0.0011399269569665194
2023-01-21 12:18:32.203507: step: 1628/530, loss: 8.935928053688258e-05
2023-01-21 12:18:33.319072: step: 1632/530, loss: 0.006617546547204256
2023-01-21 12:18:34.441720: step: 1636/530, loss: 0.0030029297340661287
2023-01-21 12:18:35.539391: step: 1640/530, loss: 0.0001149714007624425
2023-01-21 12:18:36.667867: step: 1644/530, loss: 0.004120826721191406
2023-01-21 12:18:37.791539: step: 1648/530, loss: 0.0007271766662597656
2023-01-21 12:18:38.899398: step: 1652/530, loss: 0.012736893258988857
2023-01-21 12:18:40.018216: step: 1656/530, loss: 0.00072650914080441
2023-01-21 12:18:41.142372: step: 1660/530, loss: 0.004993868060410023
2023-01-21 12:18:42.262197: step: 1664/530, loss: 0.005924033932387829
2023-01-21 12:18:43.376912: step: 1668/530, loss: 0.00020704269991256297
2023-01-21 12:18:44.493696: step: 1672/530, loss: 3.0493736630887724e-05
2023-01-21 12:18:45.622147: step: 1676/530, loss: 0.0005395889165811241
2023-01-21 12:18:46.724917: step: 1680/530, loss: 0.00020399093045853078
2023-01-21 12:18:47.877217: step: 1684/530, loss: 0.2955062985420227
2023-01-21 12:18:48.998178: step: 1688/530, loss: 0.00022764207096770406
2023-01-21 12:18:50.152573: step: 1692/530, loss: 0.0023202896118164062
2023-01-21 12:18:51.284886: step: 1696/530, loss: 0.010395050048828125
2023-01-21 12:18:52.433450: step: 1700/530, loss: 0.010214615613222122
2023-01-21 12:18:53.541342: step: 1704/530, loss: 0.0014660835731774569
2023-01-21 12:18:54.684914: step: 1708/530, loss: 0.0018846512539312243
2023-01-21 12:18:55.802200: step: 1712/530, loss: 0.0035795210860669613
2023-01-21 12:18:56.911699: step: 1716/530, loss: 0.00019140243239235133
2023-01-21 12:18:58.059902: step: 1720/530, loss: 0.011435985565185547
2023-01-21 12:18:59.181292: step: 1724/530, loss: 0.0029358866158872843
2023-01-21 12:19:00.277505: step: 1728/530, loss: 0.0010211945045739412
2023-01-21 12:19:01.409015: step: 1732/530, loss: 0.0024734498001635075
2023-01-21 12:19:02.521687: step: 1736/530, loss: 0.27268171310424805
2023-01-21 12:19:03.625732: step: 1740/530, loss: 0.003663778305053711
2023-01-21 12:19:04.727727: step: 1744/530, loss: 0.019527101889252663
2023-01-21 12:19:05.848792: step: 1748/530, loss: 0.0012912750244140625
2023-01-21 12:19:06.962966: step: 1752/530, loss: 0.0034158704802393913
2023-01-21 12:19:08.106745: step: 1756/530, loss: 0.002094030613079667
2023-01-21 12:19:09.232325: step: 1760/530, loss: 0.004107666201889515
2023-01-21 12:19:10.368688: step: 1764/530, loss: 0.00025806427584029734
2023-01-21 12:19:11.505638: step: 1768/530, loss: 0.0002704620419535786
2023-01-21 12:19:12.609929: step: 1772/530, loss: 0.00013360977754928172
2023-01-21 12:19:13.756655: step: 1776/530, loss: 0.041413117200136185
2023-01-21 12:19:14.879795: step: 1780/530, loss: 0.0010197639930993319
2023-01-21 12:19:15.975236: step: 1784/530, loss: 3.986358569818549e-05
2023-01-21 12:19:17.110473: step: 1788/530, loss: 0.02375469170510769
2023-01-21 12:19:18.249516: step: 1792/530, loss: 0.0007143020629882812
2023-01-21 12:19:19.357043: step: 1796/530, loss: 0.003890466643497348
2023-01-21 12:19:20.491344: step: 1800/530, loss: 0.009053230285644531
2023-01-21 12:19:21.633001: step: 1804/530, loss: 0.025924302637577057
2023-01-21 12:19:22.763774: step: 1808/530, loss: 0.010184478014707565
2023-01-21 12:19:23.876027: step: 1812/530, loss: 0.0751463919878006
2023-01-21 12:19:25.002288: step: 1816/530, loss: 7.009506134636467e-06
2023-01-21 12:19:26.134436: step: 1820/530, loss: 0.00019207000150345266
2023-01-21 12:19:27.258234: step: 1824/530, loss: 0.0007665634038858116
2023-01-21 12:19:28.412236: step: 1828/530, loss: 0.02518768236041069
2023-01-21 12:19:29.542900: step: 1832/530, loss: 0.00022349358187057078
2023-01-21 12:19:30.701655: step: 1836/530, loss: 0.00047779083251953125
2023-01-21 12:19:31.846926: step: 1840/530, loss: 0.00046539306640625
2023-01-21 12:19:33.013150: step: 1844/530, loss: 0.0021774291526526213
2023-01-21 12:19:34.150019: step: 1848/530, loss: 0.0005764007801190019
2023-01-21 12:19:35.267032: step: 1852/530, loss: 0.0015541077591478825
2023-01-21 12:19:36.386285: step: 1856/530, loss: 0.004560804460197687
2023-01-21 12:19:37.496126: step: 1860/530, loss: 0.00012855530076194555
2023-01-21 12:19:38.590894: step: 1864/530, loss: 0.025412941351532936
2023-01-21 12:19:39.776072: step: 1868/530, loss: 0.002062034560367465
2023-01-21 12:19:40.886573: step: 1872/530, loss: 0.017816925421357155
2023-01-21 12:19:41.991901: step: 1876/530, loss: 9.536744073557202e-06
2023-01-21 12:19:43.093452: step: 1880/530, loss: 0.06563711166381836
2023-01-21 12:19:44.200850: step: 1884/530, loss: 0.0010630607139319181
2023-01-21 12:19:45.301149: step: 1888/530, loss: 0.00199127197265625
2023-01-21 12:19:46.412446: step: 1892/530, loss: 0.019057465717196465
2023-01-21 12:19:47.554003: step: 1896/530, loss: 0.05794239044189453
2023-01-21 12:19:48.694554: step: 1900/530, loss: 0.0023369789123535156
2023-01-21 12:19:49.816348: step: 1904/530, loss: 0.0030307769775390625
2023-01-21 12:19:50.924791: step: 1908/530, loss: 0.01993427239358425
2023-01-21 12:19:52.046875: step: 1912/530, loss: 0.004283905029296875
2023-01-21 12:19:53.162552: step: 1916/530, loss: 0.0036249160766601562
2023-01-21 12:19:54.304331: step: 1920/530, loss: 0.00010251998901367188
2023-01-21 12:19:55.419212: step: 1924/530, loss: 0.001602601958438754
2023-01-21 12:19:56.577083: step: 1928/530, loss: 0.16394224762916565
2023-01-21 12:19:57.706487: step: 1932/530, loss: 0.0011976242531090975
2023-01-21 12:19:58.865087: step: 1936/530, loss: 0.007334232330322266
2023-01-21 12:20:00.003348: step: 1940/530, loss: 0.010462380014359951
2023-01-21 12:20:01.135898: step: 1944/530, loss: 9.288787987316027e-05
2023-01-21 12:20:02.306347: step: 1948/530, loss: 0.00923843402415514
2023-01-21 12:20:03.424080: step: 1952/530, loss: 0.0003485679626464844
2023-01-21 12:20:04.567373: step: 1956/530, loss: 0.01651592180132866
2023-01-21 12:20:05.700124: step: 1960/530, loss: 0.0021847723983228207
2023-01-21 12:20:06.818638: step: 1964/530, loss: 0.030588533729314804
2023-01-21 12:20:07.956773: step: 1968/530, loss: 0.029824543744325638
2023-01-21 12:20:09.088328: step: 1972/530, loss: 0.0004157066287007183
2023-01-21 12:20:10.194412: step: 1976/530, loss: 0.00022153856116347015
2023-01-21 12:20:11.340634: step: 1980/530, loss: 0.0042781829833984375
2023-01-21 12:20:12.458590: step: 1984/530, loss: 7.629396350239404e-07
2023-01-21 12:20:13.587774: step: 1988/530, loss: 0.020429613068699837
2023-01-21 12:20:14.673434: step: 1992/530, loss: 0.0002344131498830393
2023-01-21 12:20:15.805606: step: 1996/530, loss: 0.016537286341190338
2023-01-21 12:20:16.944737: step: 2000/530, loss: 0.00042533877422101796
2023-01-21 12:20:18.079294: step: 2004/530, loss: 0.01352539099752903
2023-01-21 12:20:19.196363: step: 2008/530, loss: 0.036016084253787994
2023-01-21 12:20:20.321250: step: 2012/530, loss: 0.00013818740262649953
2023-01-21 12:20:21.417613: step: 2016/530, loss: 0.0027946471236646175
2023-01-21 12:20:22.548260: step: 2020/530, loss: 0.0006717682117596269
2023-01-21 12:20:23.642511: step: 2024/530, loss: 0.001970004988834262
2023-01-21 12:20:24.761388: step: 2028/530, loss: 0.0053878785111010075
2023-01-21 12:20:25.879540: step: 2032/530, loss: 0.06713466346263885
2023-01-21 12:20:26.988852: step: 2036/530, loss: 0.005345344543457031
2023-01-21 12:20:28.158424: step: 2040/530, loss: 0.0012050628429278731
2023-01-21 12:20:29.326001: step: 2044/530, loss: 0.008620262145996094
2023-01-21 12:20:30.445752: step: 2048/530, loss: 0.0034687044098973274
2023-01-21 12:20:31.553293: step: 2052/530, loss: 0.043709564954042435
2023-01-21 12:20:32.683080: step: 2056/530, loss: 0.0012117385631427169
2023-01-21 12:20:33.802960: step: 2060/530, loss: 0.0814388319849968
2023-01-21 12:20:34.930512: step: 2064/530, loss: 0.18567946553230286
2023-01-21 12:20:36.024020: step: 2068/530, loss: 0.00045833588228560984
2023-01-21 12:20:37.134478: step: 2072/530, loss: 0.001036787056364119
2023-01-21 12:20:38.288821: step: 2076/530, loss: 0.09582772850990295
2023-01-21 12:20:39.387663: step: 2080/530, loss: 0.005129051394760609
2023-01-21 12:20:40.515732: step: 2084/530, loss: 0.033835604786872864
2023-01-21 12:20:41.630862: step: 2088/530, loss: 0.005956077482551336
2023-01-21 12:20:42.756983: step: 2092/530, loss: 0.03995513916015625
2023-01-21 12:20:43.907590: step: 2096/530, loss: 0.00458793668076396
2023-01-21 12:20:45.046343: step: 2100/530, loss: 0.003013801760971546
2023-01-21 12:20:46.163760: step: 2104/530, loss: 0.0007322311284951866
2023-01-21 12:20:47.315999: step: 2108/530, loss: 0.0066069127060472965
2023-01-21 12:20:48.429080: step: 2112/530, loss: 0.05391748622059822
2023-01-21 12:20:49.540401: step: 2116/530, loss: 0.00016255378432106227
2023-01-21 12:20:50.696137: step: 2120/530, loss: 0.020818233489990234
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.66, 'r': 0.5238095238095238, 'f1': 0.584070796460177}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.5294117647058824, 'r': 0.5, 'f1': 0.5142857142857143}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 22
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:21:35.839347: step: 4/530, loss: 0.013829231262207031
2023-01-21 12:21:36.945872: step: 8/530, loss: 0.028236009180545807
2023-01-21 12:21:38.078471: step: 12/530, loss: 0.020946312695741653
2023-01-21 12:21:39.199633: step: 16/530, loss: 0.02783794328570366
2023-01-21 12:21:40.329495: step: 20/530, loss: 0.005129194352775812
2023-01-21 12:21:41.491298: step: 24/530, loss: 0.0005687713855877519
2023-01-21 12:21:42.599750: step: 28/530, loss: 0.003909873776137829
2023-01-21 12:21:43.747270: step: 32/530, loss: 0.0048799519427120686
2023-01-21 12:21:44.865434: step: 36/530, loss: 1.411438006471144e-05
2023-01-21 12:21:45.992178: step: 40/530, loss: 0.07285986095666885
2023-01-21 12:21:47.136112: step: 44/530, loss: 0.0007911681896075606
2023-01-21 12:21:48.255167: step: 48/530, loss: 0.0018589019309729338
2023-01-21 12:21:49.400632: step: 52/530, loss: 0.01565570756793022
2023-01-21 12:21:50.496125: step: 56/530, loss: 0.002141857286915183
2023-01-21 12:21:51.636538: step: 60/530, loss: 0.010235786437988281
2023-01-21 12:21:52.773362: step: 64/530, loss: 0.0009053230169229209
2023-01-21 12:21:53.886253: step: 68/530, loss: 0.0040565491653978825
2023-01-21 12:21:55.016609: step: 72/530, loss: 0.0029331205878406763
2023-01-21 12:21:56.114771: step: 76/530, loss: 0.018975067883729935
2023-01-21 12:21:57.255371: step: 80/530, loss: 0.0004068374983035028
2023-01-21 12:21:58.373128: step: 84/530, loss: 0.0019807815551757812
2023-01-21 12:21:59.553664: step: 88/530, loss: 0.0025695799849927425
2023-01-21 12:22:00.682983: step: 92/530, loss: 0.0008378028869628906
2023-01-21 12:22:01.823122: step: 96/530, loss: 0.0007655143272131681
2023-01-21 12:22:02.967992: step: 100/530, loss: 0.01660318486392498
2023-01-21 12:22:04.084567: step: 104/530, loss: 0.0012273788452148438
2023-01-21 12:22:05.228576: step: 108/530, loss: 0.004020881373435259
2023-01-21 12:22:06.380940: step: 112/530, loss: 0.0005162238958291709
2023-01-21 12:22:07.541624: step: 116/530, loss: 0.0402795784175396
2023-01-21 12:22:08.656215: step: 120/530, loss: 0.005393505096435547
2023-01-21 12:22:09.804415: step: 124/530, loss: 0.08117543160915375
2023-01-21 12:22:10.929326: step: 128/530, loss: 2.880096508306451e-05
2023-01-21 12:22:12.059627: step: 132/530, loss: 0.022545242682099342
2023-01-21 12:22:13.159309: step: 136/530, loss: 0.023128509521484375
2023-01-21 12:22:14.274219: step: 140/530, loss: 0.0005208969232626259
2023-01-21 12:22:15.413574: step: 144/530, loss: 0.0010251045459881425
2023-01-21 12:22:16.496272: step: 148/530, loss: 0.0014766693348065019
2023-01-21 12:22:17.635442: step: 152/530, loss: 0.005837631411850452
2023-01-21 12:22:18.770629: step: 156/530, loss: 0.0004342079337220639
2023-01-21 12:22:19.902874: step: 160/530, loss: 0.02112274244427681
2023-01-21 12:22:21.030262: step: 164/530, loss: 0.047652244567871094
2023-01-21 12:22:22.170566: step: 168/530, loss: 0.00012140275066485628
2023-01-21 12:22:23.293420: step: 172/530, loss: 0.021535111591219902
2023-01-21 12:22:24.437397: step: 176/530, loss: 0.005016804207116365
2023-01-21 12:22:25.574849: step: 180/530, loss: 0.0008551598293706775
2023-01-21 12:22:26.707935: step: 184/530, loss: 0.0007279396522790194
2023-01-21 12:22:27.823107: step: 188/530, loss: 0.00015754700871184468
2023-01-21 12:22:28.970942: step: 192/530, loss: 0.008654212579131126
2023-01-21 12:22:30.061013: step: 196/530, loss: 0.0007607460138387978
2023-01-21 12:22:31.166352: step: 200/530, loss: 0.04100513458251953
2023-01-21 12:22:32.337919: step: 204/530, loss: 0.017502594739198685
2023-01-21 12:22:33.463944: step: 208/530, loss: 0.0004849433898925781
2023-01-21 12:22:34.573313: step: 212/530, loss: 0.002924978733062744
2023-01-21 12:22:35.688949: step: 216/530, loss: 0.009746551513671875
2023-01-21 12:22:36.787714: step: 220/530, loss: 0.01942138746380806
2023-01-21 12:22:37.897986: step: 224/530, loss: 3.132819983875379e-05
2023-01-21 12:22:39.008998: step: 228/530, loss: 0.0020584582816809416
2023-01-21 12:22:40.160059: step: 232/530, loss: 0.00204124441370368
2023-01-21 12:22:41.257406: step: 236/530, loss: 0.0002586364862509072
2023-01-21 12:22:42.386556: step: 240/530, loss: 0.017728805541992188
2023-01-21 12:22:43.545669: step: 244/530, loss: 0.005463409703224897
2023-01-21 12:22:44.660822: step: 248/530, loss: 0.0037986754905432463
2023-01-21 12:22:45.801681: step: 252/530, loss: 0.10300798714160919
2023-01-21 12:22:46.904997: step: 256/530, loss: 0.0009765625
2023-01-21 12:22:48.022880: step: 260/530, loss: 6.408691115211695e-05
2023-01-21 12:22:49.139292: step: 264/530, loss: 7.06672653905116e-05
2023-01-21 12:22:50.251174: step: 268/530, loss: 0.03311615064740181
2023-01-21 12:22:51.380715: step: 272/530, loss: 0.00034561159554868937
2023-01-21 12:22:52.509261: step: 276/530, loss: 0.029632091522216797
2023-01-21 12:22:53.636499: step: 280/530, loss: 0.001568698906339705
2023-01-21 12:22:54.760319: step: 284/530, loss: 0.006611061282455921
2023-01-21 12:22:55.881302: step: 288/530, loss: 0.0006584167131222785
2023-01-21 12:22:57.012670: step: 292/530, loss: 0.6212767958641052
2023-01-21 12:22:58.140999: step: 296/530, loss: 0.0346410758793354
2023-01-21 12:22:59.251573: step: 300/530, loss: 0.004952240269631147
2023-01-21 12:23:00.345931: step: 304/530, loss: 0.0004743576282635331
2023-01-21 12:23:01.453844: step: 308/530, loss: 0.008572769351303577
2023-01-21 12:23:02.593615: step: 312/530, loss: 0.02337370067834854
2023-01-21 12:23:03.713428: step: 316/530, loss: 0.06982908397912979
2023-01-21 12:23:04.852953: step: 320/530, loss: 0.0008627891074866056
2023-01-21 12:23:05.959564: step: 324/530, loss: 5.8794023061636835e-05
2023-01-21 12:23:07.114360: step: 328/530, loss: 0.0026374817825853825
2023-01-21 12:23:08.227733: step: 332/530, loss: 0.03246669843792915
2023-01-21 12:23:09.356352: step: 336/530, loss: 0.0005084991571493447
2023-01-21 12:23:10.478998: step: 340/530, loss: 0.008952951990067959
2023-01-21 12:23:11.591193: step: 344/530, loss: 0.0029693604446947575
2023-01-21 12:23:12.713068: step: 348/530, loss: 0.010965157300233841
2023-01-21 12:23:13.811145: step: 352/530, loss: 0.008252620697021484
2023-01-21 12:23:14.981514: step: 356/530, loss: 0.006879043765366077
2023-01-21 12:23:16.095148: step: 360/530, loss: 0.05324440076947212
2023-01-21 12:23:17.217655: step: 364/530, loss: 0.0006783485296182334
2023-01-21 12:23:18.329033: step: 368/530, loss: 0.012720013037323952
2023-01-21 12:23:19.436543: step: 372/530, loss: 0.08633708953857422
2023-01-21 12:23:20.554681: step: 376/530, loss: 0.004118633456528187
2023-01-21 12:23:21.664752: step: 380/530, loss: 0.00017189979553222656
2023-01-21 12:23:22.766037: step: 384/530, loss: 0.04844703897833824
2023-01-21 12:23:23.893253: step: 388/530, loss: 0.03181181102991104
2023-01-21 12:23:25.008519: step: 392/530, loss: 0.005729008000344038
2023-01-21 12:23:26.123957: step: 396/530, loss: 0.002358722733333707
2023-01-21 12:23:27.254869: step: 400/530, loss: 0.0004006385861430317
2023-01-21 12:23:28.363648: step: 404/530, loss: 0.06288424134254456
2023-01-21 12:23:29.490647: step: 408/530, loss: 0.00739631662145257
2023-01-21 12:23:30.631772: step: 412/530, loss: 0.042477987706661224
2023-01-21 12:23:31.750167: step: 416/530, loss: 0.003582096192985773
2023-01-21 12:23:32.870172: step: 420/530, loss: 0.0007232666248455644
2023-01-21 12:23:33.992804: step: 424/530, loss: 0.02542419545352459
2023-01-21 12:23:35.094920: step: 428/530, loss: 0.02205963060259819
2023-01-21 12:23:36.201816: step: 432/530, loss: 0.0006108283996582031
2023-01-21 12:23:37.333178: step: 436/530, loss: 0.0008171082008630037
2023-01-21 12:23:38.434981: step: 440/530, loss: 0.033006858080625534
2023-01-21 12:23:39.556298: step: 444/530, loss: 0.027925778180360794
2023-01-21 12:23:40.678760: step: 448/530, loss: 0.00240325927734375
2023-01-21 12:23:41.778250: step: 452/530, loss: 0.027349280193448067
2023-01-21 12:23:42.921477: step: 456/530, loss: 0.018412400037050247
2023-01-21 12:23:44.028049: step: 460/530, loss: 0.0034723279532045126
2023-01-21 12:23:45.122668: step: 464/530, loss: 1.8501283193472773e-05
2023-01-21 12:23:46.257148: step: 468/530, loss: 0.005109215155243874
2023-01-21 12:23:47.380759: step: 472/530, loss: 0.00025024416390806437
2023-01-21 12:23:48.497475: step: 476/530, loss: -8.01086389401462e-06
2023-01-21 12:23:49.619437: step: 480/530, loss: 0.0022285461891442537
2023-01-21 12:23:50.728983: step: 484/530, loss: 0.0015735626220703125
2023-01-21 12:23:51.908928: step: 488/530, loss: 0.0009603500366210938
2023-01-21 12:23:53.020947: step: 492/530, loss: 0.00028176308842375875
2023-01-21 12:23:54.131450: step: 496/530, loss: 3.170967102050781e-05
2023-01-21 12:23:55.242531: step: 500/530, loss: 0.019804857671260834
2023-01-21 12:23:56.390171: step: 504/530, loss: 0.00016222000704146922
2023-01-21 12:23:57.553105: step: 508/530, loss: 0.0215882770717144
2023-01-21 12:23:58.661692: step: 512/530, loss: -1.4781953723286279e-06
2023-01-21 12:23:59.806228: step: 516/530, loss: 0.11693544685840607
2023-01-21 12:24:00.927517: step: 520/530, loss: 0.013869999907910824
2023-01-21 12:24:02.044822: step: 524/530, loss: 3.986358569818549e-05
2023-01-21 12:24:03.212278: step: 528/530, loss: 0.0009098052978515625
2023-01-21 12:24:04.335548: step: 532/530, loss: 0.000244140625
2023-01-21 12:24:05.465653: step: 536/530, loss: 0.00024852753267623484
2023-01-21 12:24:06.563070: step: 540/530, loss: 7.705688040005043e-05
2023-01-21 12:24:07.712791: step: 544/530, loss: 0.02243633382022381
2023-01-21 12:24:08.810559: step: 548/530, loss: 0.0014440537197515368
2023-01-21 12:24:09.932819: step: 552/530, loss: 0.045681193470954895
2023-01-21 12:24:11.018391: step: 556/530, loss: 0.0003986358642578125
2023-01-21 12:24:12.151458: step: 560/530, loss: 0.005690813064575195
2023-01-21 12:24:13.286296: step: 564/530, loss: 0.04710979759693146
2023-01-21 12:24:14.409178: step: 568/530, loss: 1.9073486328125e-05
2023-01-21 12:24:15.527850: step: 572/530, loss: 0.03899326175451279
2023-01-21 12:24:16.624573: step: 576/530, loss: 0.002635193057358265
2023-01-21 12:24:17.759593: step: 580/530, loss: 0.005238533020019531
2023-01-21 12:24:18.881951: step: 584/530, loss: 0.0001941680966410786
2023-01-21 12:24:19.982199: step: 588/530, loss: 0.025834370404481888
2023-01-21 12:24:21.134364: step: 592/530, loss: 0.7795947194099426
2023-01-21 12:24:22.254548: step: 596/530, loss: 0.003987977281212807
2023-01-21 12:24:23.369191: step: 600/530, loss: 0.0012932777171954513
2023-01-21 12:24:24.491959: step: 604/530, loss: 0.32770684361457825
2023-01-21 12:24:25.598724: step: 608/530, loss: 0.0010576248168945312
2023-01-21 12:24:26.692221: step: 612/530, loss: 0.0003802776336669922
2023-01-21 12:24:27.793388: step: 616/530, loss: 0.00010375976853538305
2023-01-21 12:24:28.925950: step: 620/530, loss: 0.5229472517967224
2023-01-21 12:24:30.065726: step: 624/530, loss: 0.0347110740840435
2023-01-21 12:24:31.193389: step: 628/530, loss: 1.0824203855008818e-05
2023-01-21 12:24:32.344667: step: 632/530, loss: 0.0020164488814771175
2023-01-21 12:24:33.485043: step: 636/530, loss: 0.028372574597597122
2023-01-21 12:24:34.594692: step: 640/530, loss: 0.05191326141357422
2023-01-21 12:24:35.726463: step: 644/530, loss: 0.00024700164794921875
2023-01-21 12:24:36.870002: step: 648/530, loss: 0.01607513427734375
2023-01-21 12:24:37.988588: step: 652/530, loss: 8.60214204294607e-05
2023-01-21 12:24:39.086435: step: 656/530, loss: 3.147125244140625e-05
2023-01-21 12:24:40.197992: step: 660/530, loss: 0.00037174223689362407
2023-01-21 12:24:41.315299: step: 664/530, loss: 0.0008466720464639366
2023-01-21 12:24:42.448793: step: 668/530, loss: 0.07638807594776154
2023-01-21 12:24:43.602168: step: 672/530, loss: 0.058062173426151276
2023-01-21 12:24:44.720937: step: 676/530, loss: 0.03454608842730522
2023-01-21 12:24:45.835319: step: 680/530, loss: 0.0001295089750783518
2023-01-21 12:24:46.948048: step: 684/530, loss: 0.0029857635963708162
2023-01-21 12:24:48.055694: step: 688/530, loss: 0.0017117499373853207
2023-01-21 12:24:49.171339: step: 692/530, loss: 5.588531348621473e-05
2023-01-21 12:24:50.276256: step: 696/530, loss: 0.01333913765847683
2023-01-21 12:24:51.423055: step: 700/530, loss: 0.04393291473388672
2023-01-21 12:24:52.527563: step: 704/530, loss: 0.0035429000854492188
2023-01-21 12:24:53.668564: step: 708/530, loss: 0.009376906789839268
2023-01-21 12:24:54.796280: step: 712/530, loss: 0.00033254624577239156
2023-01-21 12:24:55.941100: step: 716/530, loss: 0.00018997192091774195
2023-01-21 12:24:57.074621: step: 720/530, loss: 0.0003508329391479492
2023-01-21 12:24:58.144027: step: 724/530, loss: 0.0007179260137490928
2023-01-21 12:24:59.278300: step: 728/530, loss: 6.694794137729332e-05
2023-01-21 12:25:00.431001: step: 732/530, loss: 0.0013194084167480469
2023-01-21 12:25:01.568787: step: 736/530, loss: 0.022631453350186348
2023-01-21 12:25:02.700842: step: 740/530, loss: 0.022176455706357956
2023-01-21 12:25:03.817800: step: 744/530, loss: 0.015521049499511719
2023-01-21 12:25:04.914650: step: 748/530, loss: 0.01170129794627428
2023-01-21 12:25:06.081570: step: 752/530, loss: 0.01095352228730917
2023-01-21 12:25:07.199166: step: 756/530, loss: 0.00048041343688964844
2023-01-21 12:25:08.296032: step: 760/530, loss: 7.252692739712074e-05
2023-01-21 12:25:09.420229: step: 764/530, loss: 0.0001354217529296875
2023-01-21 12:25:10.558871: step: 768/530, loss: 0.0017064096173271537
2023-01-21 12:25:11.696252: step: 772/530, loss: 0.0003833770751953125
2023-01-21 12:25:12.856722: step: 776/530, loss: 0.009389400482177734
2023-01-21 12:25:14.004591: step: 780/530, loss: 0.00044164658174850047
2023-01-21 12:25:15.107830: step: 784/530, loss: 0.055819131433963776
2023-01-21 12:25:16.210323: step: 788/530, loss: 0.03856682777404785
2023-01-21 12:25:17.319755: step: 792/530, loss: 0.06394214183092117
2023-01-21 12:25:18.419845: step: 796/530, loss: 0.0029307366348803043
2023-01-21 12:25:19.566018: step: 800/530, loss: 0.014421653933823109
2023-01-21 12:25:20.663195: step: 804/530, loss: 0.0017161369323730469
2023-01-21 12:25:21.772914: step: 808/530, loss: 0.009801912121474743
2023-01-21 12:25:22.859852: step: 812/530, loss: 0.02094402350485325
2023-01-21 12:25:23.986074: step: 816/530, loss: 0.012366056442260742
2023-01-21 12:25:25.083592: step: 820/530, loss: 0.00035343170748092234
2023-01-21 12:25:26.197652: step: 824/530, loss: 0.0017243385082110763
2023-01-21 12:25:27.328054: step: 828/530, loss: 0.004668044857680798
2023-01-21 12:25:28.461199: step: 832/530, loss: 0.0005001068348065019
2023-01-21 12:25:29.593217: step: 836/530, loss: 0.0018300532829016447
2023-01-21 12:25:30.687426: step: 840/530, loss: 0.01161875855177641
2023-01-21 12:25:31.826047: step: 844/530, loss: 0.0013685226440429688
2023-01-21 12:25:32.934638: step: 848/530, loss: 0.032754138112068176
2023-01-21 12:25:34.037958: step: 852/530, loss: 0.00020654201216530055
2023-01-21 12:25:35.145123: step: 856/530, loss: 0.010254478082060814
2023-01-21 12:25:36.294126: step: 860/530, loss: 0.00641288748010993
2023-01-21 12:25:37.412818: step: 864/530, loss: 0.02948017232120037
2023-01-21 12:25:38.524613: step: 868/530, loss: 0.006304026115685701
2023-01-21 12:25:39.614055: step: 872/530, loss: 0.006889724638313055
2023-01-21 12:25:40.737126: step: 876/530, loss: 0.0020359039772301912
2023-01-21 12:25:41.855043: step: 880/530, loss: -1.9073486328125e-06
2023-01-21 12:25:42.967880: step: 884/530, loss: 1.7642974853515625e-05
2023-01-21 12:25:44.087489: step: 888/530, loss: 0.0032953263726085424
2023-01-21 12:25:45.193803: step: 892/530, loss: 0.003936958033591509
2023-01-21 12:25:46.330088: step: 896/530, loss: 0.00012683868408203125
2023-01-21 12:25:47.448651: step: 900/530, loss: 0.0009784698486328125
2023-01-21 12:25:48.564512: step: 904/530, loss: 0.0030906677711755037
2023-01-21 12:25:49.713259: step: 908/530, loss: 0.0004165649297647178
2023-01-21 12:25:50.826754: step: 912/530, loss: 0.02554006688296795
2023-01-21 12:25:51.943523: step: 916/530, loss: 0.006756401155143976
2023-01-21 12:25:53.061144: step: 920/530, loss: 0.0031872272957116365
2023-01-21 12:25:54.192694: step: 924/530, loss: 0.0004385948122944683
2023-01-21 12:25:55.332538: step: 928/530, loss: 0.001860809396021068
2023-01-21 12:25:56.452815: step: 932/530, loss: 0.0008029937744140625
2023-01-21 12:25:57.603335: step: 936/530, loss: 0.00012717247591353953
2023-01-21 12:25:58.703637: step: 940/530, loss: 0.0023103714920580387
2023-01-21 12:25:59.817809: step: 944/530, loss: 0.0008705139043740928
2023-01-21 12:26:00.920717: step: 948/530, loss: 3.471374657237902e-05
2023-01-21 12:26:02.092401: step: 952/530, loss: 0.0008937835809774697
2023-01-21 12:26:03.241040: step: 956/530, loss: 0.025219345465302467
2023-01-21 12:26:04.355616: step: 960/530, loss: 0.00015397073002532125
2023-01-21 12:26:05.441402: step: 964/530, loss: 0.0004955291515216231
2023-01-21 12:26:06.576994: step: 968/530, loss: 0.022915270179510117
2023-01-21 12:26:07.730088: step: 972/530, loss: 0.02005748823285103
2023-01-21 12:26:08.840608: step: 976/530, loss: 0.28493309020996094
2023-01-21 12:26:09.954035: step: 980/530, loss: 0.017366694286465645
2023-01-21 12:26:11.050263: step: 984/530, loss: 0.0005136012914590538
2023-01-21 12:26:12.161468: step: 988/530, loss: 0.015446471981704235
2023-01-21 12:26:13.259618: step: 992/530, loss: 2.670288040462765e-06
2023-01-21 12:26:14.399455: step: 996/530, loss: 0.000491714512463659
2023-01-21 12:26:15.520745: step: 1000/530, loss: 2.1123885744600557e-05
2023-01-21 12:26:16.635476: step: 1004/530, loss: 0.00040416716365143657
2023-01-21 12:26:17.756663: step: 1008/530, loss: 0.006275463383644819
2023-01-21 12:26:18.855137: step: 1012/530, loss: 0.0001375198335153982
2023-01-21 12:26:20.004674: step: 1016/530, loss: 0.0008087158203125
2023-01-21 12:26:21.117674: step: 1020/530, loss: 0.0002460479736328125
2023-01-21 12:26:22.252765: step: 1024/530, loss: 1.6021729607018642e-05
2023-01-21 12:26:23.381838: step: 1028/530, loss: 0.0008857726934365928
2023-01-21 12:26:24.484268: step: 1032/530, loss: 0.024689579382538795
2023-01-21 12:26:25.595264: step: 1036/530, loss: 0.003535699797794223
2023-01-21 12:26:26.685989: step: 1040/530, loss: 0.0010266781318932772
2023-01-21 12:26:27.777139: step: 1044/530, loss: 0.0018572807312011719
2023-01-21 12:26:28.897679: step: 1048/530, loss: 0.0007299422868527472
2023-01-21 12:26:30.014224: step: 1052/530, loss: 2.5844574338407256e-05
2023-01-21 12:26:31.128587: step: 1056/530, loss: 0.017903901636600494
2023-01-21 12:26:32.308062: step: 1060/530, loss: 0.1707594394683838
2023-01-21 12:26:33.436385: step: 1064/530, loss: 0.03297806158661842
2023-01-21 12:26:34.550701: step: 1068/530, loss: 0.003120803739875555
2023-01-21 12:26:35.684059: step: 1072/530, loss: 0.0012836457462981343
2023-01-21 12:26:36.795311: step: 1076/530, loss: 0.0035257339477539062
2023-01-21 12:26:37.938283: step: 1080/530, loss: 0.0077565195970237255
2023-01-21 12:26:39.075268: step: 1084/530, loss: 0.0010362624889239669
2023-01-21 12:26:40.219633: step: 1088/530, loss: -1.0585784366412554e-05
2023-01-21 12:26:41.365120: step: 1092/530, loss: 0.0004044532834086567
2023-01-21 12:26:42.468940: step: 1096/530, loss: 4.8208235966740176e-05
2023-01-21 12:26:43.581575: step: 1100/530, loss: 0.012791729532182217
2023-01-21 12:26:44.706339: step: 1104/530, loss: 0.011905670166015625
2023-01-21 12:26:45.836734: step: 1108/530, loss: 5.722046125811175e-07
2023-01-21 12:26:46.975881: step: 1112/530, loss: 0.00017747879610396922
2023-01-21 12:26:48.089497: step: 1116/530, loss: 0.0006025314214639366
2023-01-21 12:26:49.224245: step: 1120/530, loss: 0.03519769012928009
2023-01-21 12:26:50.332942: step: 1124/530, loss: 3.299712989246473e-05
2023-01-21 12:26:51.444759: step: 1128/530, loss: 0.00010938644845737144
2023-01-21 12:26:52.566684: step: 1132/530, loss: 0.00042018890962935984
2023-01-21 12:26:53.675277: step: 1136/530, loss: 0.002977085066959262
2023-01-21 12:26:54.808257: step: 1140/530, loss: 0.01409912109375
2023-01-21 12:26:55.924701: step: 1144/530, loss: 0.0005296707386150956
2023-01-21 12:26:57.033109: step: 1148/530, loss: 0.00026416778564453125
2023-01-21 12:26:58.139269: step: 1152/530, loss: 0.022140981629490852
2023-01-21 12:26:59.246494: step: 1156/530, loss: 3.6239625842426904e-06
2023-01-21 12:27:00.370642: step: 1160/530, loss: 0.5915541648864746
2023-01-21 12:27:01.488862: step: 1164/530, loss: 0.0028985023964196444
2023-01-21 12:27:02.628248: step: 1168/530, loss: 0.00021629333787132055
2023-01-21 12:27:03.726926: step: 1172/530, loss: 0.006834125611931086
2023-01-21 12:27:04.849613: step: 1176/530, loss: 0.0014423370594158769
2023-01-21 12:27:06.008421: step: 1180/530, loss: 0.0011466980213299394
2023-01-21 12:27:07.131186: step: 1184/530, loss: 0.00010385513451183215
2023-01-21 12:27:08.230235: step: 1188/530, loss: 0.0007197380182333291
2023-01-21 12:27:09.353302: step: 1192/530, loss: 0.015859462320804596
2023-01-21 12:27:10.455694: step: 1196/530, loss: 0.005663394927978516
2023-01-21 12:27:11.563176: step: 1200/530, loss: 0.0005887985462322831
2023-01-21 12:27:12.685946: step: 1204/530, loss: 0.0009119987953454256
2023-01-21 12:27:13.810952: step: 1208/530, loss: 0.0029766084626317024
2023-01-21 12:27:14.933190: step: 1212/530, loss: 0.0135955810546875
2023-01-21 12:27:16.036768: step: 1216/530, loss: 0.00010051727440441027
2023-01-21 12:27:17.191932: step: 1220/530, loss: 4.291534423828125e-06
2023-01-21 12:27:18.323012: step: 1224/530, loss: 0.01460032444447279
2023-01-21 12:27:19.414899: step: 1228/530, loss: 0.00010528564598644152
2023-01-21 12:27:20.559386: step: 1232/530, loss: 5.292892637953628e-06
2023-01-21 12:27:21.734367: step: 1236/530, loss: 0.0002620696905069053
2023-01-21 12:27:22.847286: step: 1240/530, loss: 0.0004349708906374872
2023-01-21 12:27:23.966187: step: 1244/530, loss: 0.016066361218690872
2023-01-21 12:27:25.057883: step: 1248/530, loss: 0.016463566571474075
2023-01-21 12:27:26.174080: step: 1252/530, loss: 0.06696290522813797
2023-01-21 12:27:27.295655: step: 1256/530, loss: 0.0016881943447515368
2023-01-21 12:27:28.405939: step: 1260/530, loss: 0.003610038897022605
2023-01-21 12:27:29.529458: step: 1264/530, loss: 0.02721252478659153
2023-01-21 12:27:30.672572: step: 1268/530, loss: 0.04581651836633682
2023-01-21 12:27:31.803562: step: 1272/530, loss: 0.0006538390880450606
2023-01-21 12:27:32.955944: step: 1276/530, loss: 0.001772213145159185
2023-01-21 12:27:34.052822: step: 1280/530, loss: 0.0015751958126202226
2023-01-21 12:27:35.179529: step: 1284/530, loss: 4.7349931264761835e-05
2023-01-21 12:27:36.304205: step: 1288/530, loss: 0.0010425568325445056
2023-01-21 12:27:37.424222: step: 1292/530, loss: 0.00046682360698468983
2023-01-21 12:27:38.551626: step: 1296/530, loss: 0.0006074905395507812
2023-01-21 12:27:39.677746: step: 1300/530, loss: 0.0002407073916401714
2023-01-21 12:27:40.762552: step: 1304/530, loss: 0.007075262255966663
2023-01-21 12:27:41.882512: step: 1308/530, loss: 0.0012199401389807463
2023-01-21 12:27:43.006193: step: 1312/530, loss: 0.0028744698502123356
2023-01-21 12:27:44.128264: step: 1316/530, loss: 0.008667755872011185
2023-01-21 12:27:45.250838: step: 1320/530, loss: 0.0019455909496173263
2023-01-21 12:27:46.393232: step: 1324/530, loss: 0.01106247864663601
2023-01-21 12:27:47.510936: step: 1328/530, loss: 0.03754167631268501
2023-01-21 12:27:48.614441: step: 1332/530, loss: 9.522438631393015e-05
2023-01-21 12:27:49.743867: step: 1336/530, loss: 0.04916572570800781
2023-01-21 12:27:50.879886: step: 1340/530, loss: 0.002193546388298273
2023-01-21 12:27:52.005892: step: 1344/530, loss: 0.0001820087491068989
2023-01-21 12:27:53.129140: step: 1348/530, loss: 0.009278440847992897
2023-01-21 12:27:54.235880: step: 1352/530, loss: 0.0004127502324990928
2023-01-21 12:27:55.337638: step: 1356/530, loss: 0.031043052673339844
2023-01-21 12:27:56.449161: step: 1360/530, loss: 0.03140735998749733
2023-01-21 12:27:57.578240: step: 1364/530, loss: 0.004853058140724897
2023-01-21 12:27:58.724960: step: 1368/530, loss: 0.0028602599631994963
2023-01-21 12:27:59.874484: step: 1372/530, loss: 0.007622337434440851
2023-01-21 12:28:01.030614: step: 1376/530, loss: 0.014221095480024815
2023-01-21 12:28:02.149937: step: 1380/530, loss: 0.0026906966231763363
2023-01-21 12:28:03.275361: step: 1384/530, loss: 0.0019065381493419409
2023-01-21 12:28:04.381838: step: 1388/530, loss: 0.00012321471876930445
2023-01-21 12:28:05.486381: step: 1392/530, loss: 0.041698455810546875
2023-01-21 12:28:06.612243: step: 1396/530, loss: 0.13400626182556152
2023-01-21 12:28:07.747562: step: 1400/530, loss: -5.722040441469289e-07
2023-01-21 12:28:08.856883: step: 1404/530, loss: 0.011005783453583717
2023-01-21 12:28:09.990978: step: 1408/530, loss: 0.015074730850756168
2023-01-21 12:28:11.128156: step: 1412/530, loss: 0.006898403167724609
2023-01-21 12:28:12.259490: step: 1416/530, loss: 0.0070705413818359375
2023-01-21 12:28:13.391345: step: 1420/530, loss: 0.0066041951067745686
2023-01-21 12:28:14.548678: step: 1424/530, loss: 0.023800181224942207
2023-01-21 12:28:15.642696: step: 1428/530, loss: 0.03796839714050293
2023-01-21 12:28:16.741520: step: 1432/530, loss: 0.00023212432279251516
2023-01-21 12:28:17.865551: step: 1436/530, loss: 0.0312378890812397
2023-01-21 12:28:18.997989: step: 1440/530, loss: 0.013933945447206497
2023-01-21 12:28:20.114068: step: 1444/530, loss: 0.056984901428222656
2023-01-21 12:28:21.228666: step: 1448/530, loss: 0.00784149207174778
2023-01-21 12:28:22.345656: step: 1452/530, loss: 0.022394562140107155
2023-01-21 12:28:23.468250: step: 1456/530, loss: 0.0023054121993482113
2023-01-21 12:28:24.586096: step: 1460/530, loss: 0.00033206940861418843
2023-01-21 12:28:25.712272: step: 1464/530, loss: 0.0077651976607739925
2023-01-21 12:28:26.859555: step: 1468/530, loss: 0.007676935754716396
2023-01-21 12:28:27.963267: step: 1472/530, loss: 0.010902214795351028
2023-01-21 12:28:29.085241: step: 1476/530, loss: 0.016046905890107155
2023-01-21 12:28:30.202396: step: 1480/530, loss: 0.12760229408740997
2023-01-21 12:28:31.300987: step: 1484/530, loss: 0.018263543024659157
2023-01-21 12:28:32.426650: step: 1488/530, loss: 0.0007132530445232987
2023-01-21 12:28:33.550552: step: 1492/530, loss: 5.4740903578931466e-05
2023-01-21 12:28:34.677982: step: 1496/530, loss: 0.015716170892119408
2023-01-21 12:28:35.781981: step: 1500/530, loss: 0.025861646980047226
2023-01-21 12:28:36.897340: step: 1504/530, loss: 0.0020416260231286287
2023-01-21 12:28:38.031083: step: 1508/530, loss: 6.923675391590223e-05
2023-01-21 12:28:39.141098: step: 1512/530, loss: 0.017908668145537376
2023-01-21 12:28:40.297310: step: 1516/530, loss: 0.0012227059341967106
2023-01-21 12:28:41.405290: step: 1520/530, loss: 0.0023993493523448706
2023-01-21 12:28:42.517283: step: 1524/530, loss: 7.972717867232859e-05
2023-01-21 12:28:43.631369: step: 1528/530, loss: 2.784729076665826e-05
2023-01-21 12:28:44.754711: step: 1532/530, loss: 0.04759882390499115
2023-01-21 12:28:45.896537: step: 1536/530, loss: 0.019581986591219902
2023-01-21 12:28:47.039190: step: 1540/530, loss: 0.00014991761418059468
2023-01-21 12:28:48.158765: step: 1544/530, loss: 0.01125946082174778
2023-01-21 12:28:49.283715: step: 1548/530, loss: 0.016376685351133347
2023-01-21 12:28:50.418193: step: 1552/530, loss: 0.0001350402890238911
2023-01-21 12:28:51.557240: step: 1556/530, loss: 0.0020140649285167456
2023-01-21 12:28:52.706122: step: 1560/530, loss: 0.03773679956793785
2023-01-21 12:28:53.819396: step: 1564/530, loss: 0.00014610290236305445
2023-01-21 12:28:54.924624: step: 1568/530, loss: 0.0022867678198963404
2023-01-21 12:28:56.047087: step: 1572/530, loss: 0.0015377998352050781
2023-01-21 12:28:57.192955: step: 1576/530, loss: 0.004486274905502796
2023-01-21 12:28:58.312488: step: 1580/530, loss: 1.8314515352249146
2023-01-21 12:28:59.459615: step: 1584/530, loss: 0.0819968655705452
2023-01-21 12:29:00.598317: step: 1588/530, loss: 0.0658847764134407
2023-01-21 12:29:01.708335: step: 1592/530, loss: 0.02240161970257759
2023-01-21 12:29:02.854983: step: 1596/530, loss: 2.136230432370212e-05
2023-01-21 12:29:04.014524: step: 1600/530, loss: 0.0629582405090332
2023-01-21 12:29:05.148974: step: 1604/530, loss: 0.026969147846102715
2023-01-21 12:29:06.255102: step: 1608/530, loss: 0.00016589164442848414
2023-01-21 12:29:07.379628: step: 1612/530, loss: 0.012159157544374466
2023-01-21 12:29:08.485748: step: 1616/530, loss: 0.0005271911504678428
2023-01-21 12:29:09.610235: step: 1620/530, loss: 0.0009271621820516884
2023-01-21 12:29:10.727816: step: 1624/530, loss: 0.0004901885986328125
2023-01-21 12:29:11.823846: step: 1628/530, loss: 0.0006651878356933594
2023-01-21 12:29:12.947178: step: 1632/530, loss: 0.00012989045353606343
2023-01-21 12:29:14.090559: step: 1636/530, loss: 0.02283640019595623
2023-01-21 12:29:15.232729: step: 1640/530, loss: 6.933212716830894e-05
2023-01-21 12:29:16.363242: step: 1644/530, loss: 0.0005867004510946572
2023-01-21 12:29:17.446806: step: 1648/530, loss: 0.0002651214599609375
2023-01-21 12:29:18.580995: step: 1652/530, loss: 0.0008106231689453125
2023-01-21 12:29:19.722050: step: 1656/530, loss: 0.0016009330283850431
2023-01-21 12:29:20.866318: step: 1660/530, loss: 0.02342987060546875
2023-01-21 12:29:22.012439: step: 1664/530, loss: 0.002790832659229636
2023-01-21 12:29:23.133590: step: 1668/530, loss: 8.258819434558973e-05
2023-01-21 12:29:24.271148: step: 1672/530, loss: 0.0005496025551110506
2023-01-21 12:29:25.399981: step: 1676/530, loss: 0.00725822476670146
2023-01-21 12:29:26.534597: step: 1680/530, loss: 0.0015655517345294356
2023-01-21 12:29:27.671514: step: 1684/530, loss: 0.0005455970531329513
2023-01-21 12:29:28.815459: step: 1688/530, loss: 0.020603753626346588
2023-01-21 12:29:29.932368: step: 1692/530, loss: 0.015109825879335403
2023-01-21 12:29:31.053795: step: 1696/530, loss: 0.0020175965037196875
2023-01-21 12:29:32.183323: step: 1700/530, loss: 0.005991172976791859
2023-01-21 12:29:33.312905: step: 1704/530, loss: 1.468658410885837e-05
2023-01-21 12:29:34.401278: step: 1708/530, loss: 7.209777686512098e-05
2023-01-21 12:29:35.521932: step: 1712/530, loss: 0.0023065567947924137
2023-01-21 12:29:36.624292: step: 1716/530, loss: 0.0073375701904296875
2023-01-21 12:29:37.711036: step: 1720/530, loss: 0.12027668952941895
2023-01-21 12:29:38.822369: step: 1724/530, loss: 0.04579009860754013
2023-01-21 12:29:39.964408: step: 1728/530, loss: 0.0013393402332440019
2023-01-21 12:29:41.070995: step: 1732/530, loss: 0.026813127100467682
2023-01-21 12:29:42.190917: step: 1736/530, loss: 0.0028240205720067024
2023-01-21 12:29:43.300838: step: 1740/530, loss: 0.0001180648832814768
2023-01-21 12:29:44.437342: step: 1744/530, loss: 0.14016051590442657
2023-01-21 12:29:45.559703: step: 1748/530, loss: 0.07469246536493301
2023-01-21 12:29:46.697897: step: 1752/530, loss: 0.0035542489495128393
2023-01-21 12:29:47.830087: step: 1756/530, loss: 0.00022583008103538305
2023-01-21 12:29:48.943322: step: 1760/530, loss: 0.00032672882662154734
2023-01-21 12:29:50.068693: step: 1764/530, loss: 0.049144744873046875
2023-01-21 12:29:51.206529: step: 1768/530, loss: 7.886887033237144e-05
2023-01-21 12:29:52.330822: step: 1772/530, loss: 0.0015050411457195878
2023-01-21 12:29:53.439908: step: 1776/530, loss: 0.031502917408943176
2023-01-21 12:29:54.560833: step: 1780/530, loss: 0.0012326240539550781
2023-01-21 12:29:55.676379: step: 1784/530, loss: 0.23514500260353088
2023-01-21 12:29:56.799904: step: 1788/530, loss: 2.5087525844573975
2023-01-21 12:29:57.928558: step: 1792/530, loss: 0.00015745163545943797
2023-01-21 12:29:59.049390: step: 1796/530, loss: 5.1116945542162284e-05
2023-01-21 12:30:00.161738: step: 1800/530, loss: 0.0184160228818655
2023-01-21 12:30:01.301239: step: 1804/530, loss: 0.007402992341667414
2023-01-21 12:30:02.416498: step: 1808/530, loss: 5.2356725063873455e-05
2023-01-21 12:30:03.565234: step: 1812/530, loss: 8.7738037109375e-05
2023-01-21 12:30:04.711382: step: 1816/530, loss: 0.008153343573212624
2023-01-21 12:30:05.847104: step: 1820/530, loss: 0.0234832763671875
2023-01-21 12:30:06.963383: step: 1824/530, loss: 0.004779052920639515
2023-01-21 12:30:08.080426: step: 1828/530, loss: 1.033958077430725
2023-01-21 12:30:09.232061: step: 1832/530, loss: 0.0658964142203331
2023-01-21 12:30:10.321028: step: 1836/530, loss: 0.003172588534653187
2023-01-21 12:30:11.460984: step: 1840/530, loss: 0.5437927842140198
2023-01-21 12:30:12.568910: step: 1844/530, loss: 7.25746140233241e-05
2023-01-21 12:30:13.704603: step: 1848/530, loss: 0.009994315914809704
2023-01-21 12:30:14.814359: step: 1852/530, loss: 0.00011787415132857859
2023-01-21 12:30:15.942946: step: 1856/530, loss: 0.00974807795137167
2023-01-21 12:30:17.076251: step: 1860/530, loss: 0.012867546640336514
2023-01-21 12:30:18.197181: step: 1864/530, loss: 0.019749069586396217
2023-01-21 12:30:19.338374: step: 1868/530, loss: 0.002157306531444192
2023-01-21 12:30:20.455488: step: 1872/530, loss: 5.917549060541205e-05
2023-01-21 12:30:21.558113: step: 1876/530, loss: 0.0006668091518804431
2023-01-21 12:30:22.676764: step: 1880/530, loss: 0.02253551594913006
2023-01-21 12:30:23.782629: step: 1884/530, loss: 0.02967710606753826
2023-01-21 12:30:24.907394: step: 1888/530, loss: 0.001216125558130443
2023-01-21 12:30:26.016924: step: 1892/530, loss: 9.727478754939511e-06
2023-01-21 12:30:27.142471: step: 1896/530, loss: 0.00202598562464118
2023-01-21 12:30:28.295985: step: 1900/530, loss: 0.00018644332885742188
2023-01-21 12:30:29.428211: step: 1904/530, loss: 7.486343747586943e-06
2023-01-21 12:30:30.560630: step: 1908/530, loss: 0.00221080775372684
2023-01-21 12:30:31.668022: step: 1912/530, loss: 0.051728151738643646
2023-01-21 12:30:32.834844: step: 1916/530, loss: 0.028162576258182526
2023-01-21 12:30:33.961224: step: 1920/530, loss: 0.0009329795720987022
2023-01-21 12:30:35.078628: step: 1924/530, loss: 0.010509109124541283
2023-01-21 12:30:36.214700: step: 1928/530, loss: 0.0012278556823730469
2023-01-21 12:30:37.345298: step: 1932/530, loss: 0.0048049925826489925
2023-01-21 12:30:38.447351: step: 1936/530, loss: 0.001105022500269115
2023-01-21 12:30:39.608897: step: 1940/530, loss: 0.014538764953613281
2023-01-21 12:30:40.721567: step: 1944/530, loss: 0.0001770019589457661
2023-01-21 12:30:41.850246: step: 1948/530, loss: 0.0003121376212220639
2023-01-21 12:30:42.958423: step: 1952/530, loss: 0.007830333895981312
2023-01-21 12:30:44.086065: step: 1956/530, loss: 0.004420948214828968
2023-01-21 12:30:45.209273: step: 1960/530, loss: 0.026820659637451172
2023-01-21 12:30:46.351739: step: 1964/530, loss: 0.00023136139498092234
2023-01-21 12:30:47.487770: step: 1968/530, loss: 0.01574230194091797
2023-01-21 12:30:48.600993: step: 1972/530, loss: 0.02344541624188423
2023-01-21 12:30:49.714008: step: 1976/530, loss: 0.004365349188446999
2023-01-21 12:30:50.848358: step: 1980/530, loss: 0.020294189453125
2023-01-21 12:30:51.956000: step: 1984/530, loss: 0.0005817413330078125
2023-01-21 12:30:53.148463: step: 1988/530, loss: 0.0023246766068041325
2023-01-21 12:30:54.276013: step: 1992/530, loss: 0.0026029585860669613
2023-01-21 12:30:55.405533: step: 1996/530, loss: 0.1726539582014084
2023-01-21 12:30:56.528802: step: 2000/530, loss: 0.00016880035400390625
2023-01-21 12:30:57.641489: step: 2004/530, loss: 0.0009980201721191406
2023-01-21 12:30:58.765407: step: 2008/530, loss: 0.010536002926528454
2023-01-21 12:30:59.871647: step: 2012/530, loss: 0.0001770019589457661
2023-01-21 12:31:01.006102: step: 2016/530, loss: 0.0006753921625204384
2023-01-21 12:31:02.179878: step: 2020/530, loss: 0.002168846083804965
2023-01-21 12:31:03.303528: step: 2024/530, loss: 0.01672658883035183
2023-01-21 12:31:04.425950: step: 2028/530, loss: 0.00032329559326171875
2023-01-21 12:31:05.540225: step: 2032/530, loss: 0.04158210754394531
2023-01-21 12:31:06.679585: step: 2036/530, loss: 3.5095217754133046e-05
2023-01-21 12:31:07.830699: step: 2040/530, loss: 0.0030174257699400187
2023-01-21 12:31:08.982511: step: 2044/530, loss: 0.00010643005225574598
2023-01-21 12:31:10.117887: step: 2048/530, loss: 0.0012750625610351562
2023-01-21 12:31:11.255671: step: 2052/530, loss: 0.0005777358892373741
2023-01-21 12:31:12.383107: step: 2056/530, loss: 0.000556564365979284
2023-01-21 12:31:13.501665: step: 2060/530, loss: 0.003240251448005438
2023-01-21 12:31:14.680640: step: 2064/530, loss: 0.0016705513698980212
2023-01-21 12:31:15.788386: step: 2068/530, loss: 0.00024433137150481343
2023-01-21 12:31:16.927721: step: 2072/530, loss: 0.004001522436738014
2023-01-21 12:31:18.052408: step: 2076/530, loss: 0.0004519462527241558
2023-01-21 12:31:19.156099: step: 2080/530, loss: 0.0057003977708518505
2023-01-21 12:31:20.251831: step: 2084/530, loss: 9.384155418956652e-05
2023-01-21 12:31:21.396554: step: 2088/530, loss: 0.0015964508056640625
2023-01-21 12:31:22.560617: step: 2092/530, loss: 4.920959327137098e-05
2023-01-21 12:31:23.694514: step: 2096/530, loss: 0.0012268066639080644
2023-01-21 12:31:24.816298: step: 2100/530, loss: 0.0002544403250794858
2023-01-21 12:31:25.953810: step: 2104/530, loss: 0.0010980606311932206
2023-01-21 12:31:27.072578: step: 2108/530, loss: 0.0007318496936932206
2023-01-21 12:31:28.168860: step: 2112/530, loss: 0.0005483627319335938
2023-01-21 12:31:29.315980: step: 2116/530, loss: 0.00023312569828704
2023-01-21 12:31:30.429922: step: 2120/530, loss: 0.044845011085271835
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.5926294820717132, 'r': 0.7922769640479361, 'f1': 0.6780626780626782}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6258896797153025, 'r': 0.804, 'f1': 0.7038519259629815}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5393258426966292, 'r': 0.8888888888888888, 'f1': 0.6713286713286712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.5862068965517241, 'r': 0.5396825396825397, 'f1': 0.5619834710743802}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
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': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 12:32:11.326107: step: 4/530, loss: 0.0002652168332133442
2023-01-21 12:32:12.423748: step: 8/530, loss: 0.0021867752075195312
2023-01-21 12:32:13.544567: step: 12/530, loss: 5.736351158702746e-05
2023-01-21 12:32:14.647810: step: 16/530, loss: 0.0004987717256881297
2023-01-21 12:32:15.765983: step: 20/530, loss: 0.0022054670844227076
2023-01-21 12:32:16.877815: step: 24/530, loss: 0.00011386871483409777
2023-01-21 12:32:18.008334: step: 28/530, loss: 9.303689148509875e-05
2023-01-21 12:32:19.137861: step: 32/530, loss: 0.00013236999802757055
2023-01-21 12:32:20.299732: step: 36/530, loss: 0.24577312171459198
2023-01-21 12:32:21.412900: step: 40/530, loss: 0.018052147701382637
2023-01-21 12:32:22.547965: step: 44/530, loss: 0.0033402920234948397
2023-01-21 12:32:23.674834: step: 48/530, loss: 0.0001921653893077746
2023-01-21 12:32:24.799900: step: 52/530, loss: 0.0017047881847247481
2023-01-21 12:32:25.941095: step: 56/530, loss: 0.000439357798313722
2023-01-21 12:32:27.052123: step: 60/530, loss: 0.00656738318502903
2023-01-21 12:32:28.224377: step: 64/530, loss: 0.00370616908185184
2023-01-21 12:32:29.346333: step: 68/530, loss: 0.0008543014409951866
2023-01-21 12:32:30.443971: step: 72/530, loss: 0.0005480766412802041
2023-01-21 12:32:31.571587: step: 76/530, loss: 0.0012156486045569181
2023-01-21 12:32:32.675125: step: 80/530, loss: 9.35554489842616e-05
2023-01-21 12:32:33.781886: step: 84/530, loss: 0.00045013427734375
2023-01-21 12:32:34.889402: step: 88/530, loss: 9.002685692394152e-05
2023-01-21 12:32:36.000302: step: 92/530, loss: 0.0024712085723876953
2023-01-21 12:32:37.136240: step: 96/530, loss: 0.023923112079501152
2023-01-21 12:32:38.252484: step: 100/530, loss: 0.00013589859008789062
2023-01-21 12:32:39.349551: step: 104/530, loss: 0.005844783969223499
2023-01-21 12:32:40.499346: step: 108/530, loss: 0.00018224716768600047
2023-01-21 12:32:41.633706: step: 112/530, loss: 0.031000234186649323
2023-01-21 12:32:42.775001: step: 116/530, loss: 0.012397194281220436
2023-01-21 12:32:43.894050: step: 120/530, loss: 0.47705334424972534
2023-01-21 12:32:45.050518: step: 124/530, loss: 0.0020711899269372225
2023-01-21 12:32:46.176071: step: 128/530, loss: 0.014756584540009499
2023-01-21 12:32:47.289054: step: 132/530, loss: 0.0003341674746479839
2023-01-21 12:32:48.410295: step: 136/530, loss: -9.5367431640625e-06
2023-01-21 12:32:49.518076: step: 140/530, loss: 1.4686585018353071e-05
2023-01-21 12:32:50.643171: step: 144/530, loss: 1.5068053471622989e-05
2023-01-21 12:32:51.748936: step: 148/530, loss: 0.0022258758544921875
2023-01-21 12:32:52.868774: step: 152/530, loss: 0.005324650090187788
2023-01-21 12:32:53.989906: step: 156/530, loss: 0.004137897863984108
2023-01-21 12:32:55.102206: step: 160/530, loss: 0.0009320258977822959
2023-01-21 12:32:56.223421: step: 164/530, loss: 0.0018817902309820056
2023-01-21 12:32:57.360580: step: 168/530, loss: 0.015962744131684303
2023-01-21 12:32:58.490960: step: 172/530, loss: 0.13599014282226562
2023-01-21 12:32:59.616201: step: 176/530, loss: 0.004966879263520241
2023-01-21 12:33:00.762443: step: 180/530, loss: 0.05440349876880646
2023-01-21 12:33:01.916063: step: 184/530, loss: 0.010399341583251953
2023-01-21 12:33:03.018157: step: 188/530, loss: 0.00906233862042427
2023-01-21 12:33:04.168880: step: 192/530, loss: 0.0009181976201944053
2023-01-21 12:33:05.273304: step: 196/530, loss: 0.00033588410587981343
2023-01-21 12:33:06.380201: step: 200/530, loss: 0.00072736747097224
2023-01-21 12:33:07.510832: step: 204/530, loss: 0.0016552925808355212
2023-01-21 12:33:08.658135: step: 208/530, loss: 0.0005908965831622481
2023-01-21 12:33:09.787754: step: 212/530, loss: 0.018049050122499466
2023-01-21 12:33:10.933995: step: 216/530, loss: 0.0001046180768753402
2023-01-21 12:33:12.049477: step: 220/530, loss: 0.0018452645745128393
2023-01-21 12:33:13.146677: step: 224/530, loss: 9.822845640883315e-06
2023-01-21 12:33:14.294445: step: 228/530, loss: 0.0008958816761150956
2023-01-21 12:33:15.411846: step: 232/530, loss: 0.0030859948601573706
2023-01-21 12:33:16.522477: step: 236/530, loss: 0.001262664794921875
2023-01-21 12:33:17.660418: step: 240/530, loss: 0.00992963369935751
2023-01-21 12:33:18.747908: step: 244/530, loss: 0.004852390848100185
2023-01-21 12:33:19.884428: step: 248/530, loss: 0.0006431579822674394
2023-01-21 12:33:21.003708: step: 252/530, loss: 0.0007895947201177478
2023-01-21 12:33:22.113097: step: 256/530, loss: 0.00016098022751975805
2023-01-21 12:33:23.236229: step: 260/530, loss: 0.0013866424560546875
2023-01-21 12:33:24.370874: step: 264/530, loss: 0.00020599365234375
2023-01-21 12:33:25.508656: step: 268/530, loss: 0.15336064994335175
2023-01-21 12:33:26.603838: step: 272/530, loss: 0.0008141517173498869
2023-01-21 12:33:27.706817: step: 276/530, loss: 0.005021095275878906
2023-01-21 12:33:28.861739: step: 280/530, loss: 1.4400483451026957e-05
2023-01-21 12:33:29.986842: step: 284/530, loss: 0.013475418090820312
2023-01-21 12:33:31.118574: step: 288/530, loss: 0.002843189286068082
2023-01-21 12:33:32.249847: step: 292/530, loss: 0.0139312744140625
2023-01-21 12:33:33.385316: step: 296/530, loss: 0.0029879570938646793
2023-01-21 12:33:34.509885: step: 300/530, loss: 0.0336429625749588
2023-01-21 12:33:35.646145: step: 304/530, loss: 0.00017967224994208664
2023-01-21 12:33:36.789591: step: 308/530, loss: 0.025636862963438034
2023-01-21 12:33:37.935810: step: 312/530, loss: 0.0016681670676916838
2023-01-21 12:33:39.062959: step: 316/530, loss: 0.007277298253029585
2023-01-21 12:33:40.185055: step: 320/530, loss: 0.007306623738259077
2023-01-21 12:33:41.277794: step: 324/530, loss: 4.291534423828125e-05
2023-01-21 12:33:42.388875: step: 328/530, loss: 1.6468709707260132
2023-01-21 12:33:43.512149: step: 332/530, loss: 0.08663330227136612
2023-01-21 12:33:44.632135: step: 336/530, loss: 0.013335847295820713
2023-01-21 12:33:45.770184: step: 340/530, loss: 2.307891918462701e-05
2023-01-21 12:33:46.964583: step: 344/530, loss: 0.0011133194202557206
2023-01-21 12:33:48.080142: step: 348/530, loss: 0.0002575874386820942
2023-01-21 12:33:49.182496: step: 352/530, loss: 0.00011959076073253527
2023-01-21 12:33:50.299687: step: 356/530, loss: 0.0016545295948162675
2023-01-21 12:33:51.435572: step: 360/530, loss: 0.0014316559536382556
2023-01-21 12:33:52.542848: step: 364/530, loss: 0.0029211044311523438
2023-01-21 12:33:53.667352: step: 368/530, loss: 0.001989364856854081
2023-01-21 12:33:54.793364: step: 372/530, loss: -9.536744016713783e-08
2023-01-21 12:33:55.910837: step: 376/530, loss: 0.0011081695556640625
2023-01-21 12:33:57.020492: step: 380/530, loss: 0.0003450393851380795
2023-01-21 12:33:58.157714: step: 384/530, loss: 0.005698681343346834
2023-01-21 12:33:59.268638: step: 388/530, loss: 0.0011629104847088456
2023-01-21 12:34:00.401938: step: 392/530, loss: 0.00044193267240189016
2023-01-21 12:34:01.497346: step: 396/530, loss: 0.000639629433862865
2023-01-21 12:34:02.654992: step: 400/530, loss: 0.034870147705078125
2023-01-21 12:34:03.770292: step: 404/530, loss: 0.0034341812133789062
2023-01-21 12:34:04.901361: step: 408/530, loss: 1.888275073724799e-05
2023-01-21 12:34:06.011333: step: 412/530, loss: 1.621246337890625e-05
2023-01-21 12:34:07.127528: step: 416/530, loss: 0.01134481467306614
2023-01-21 12:34:08.256456: step: 420/530, loss: 7.629396350239404e-07
2023-01-21 12:34:09.359884: step: 424/530, loss: 2.307891918462701e-05
2023-01-21 12:34:10.469132: step: 428/530, loss: 4.482892990112305
2023-01-21 12:34:11.611181: step: 432/530, loss: 0.01120071392506361
2023-01-21 12:34:12.741795: step: 436/530, loss: 0.006993246264755726
2023-01-21 12:34:13.861609: step: 440/530, loss: 0.3945600390434265
2023-01-21 12:34:15.004919: step: 444/530, loss: 5.4359438763640355e-06
2023-01-21 12:34:16.133989: step: 448/530, loss: 0.0001337051362497732
2023-01-21 12:34:17.278708: step: 452/530, loss: 0.043811991810798645
2023-01-21 12:34:18.373135: step: 456/530, loss: 0.00966491736471653
2023-01-21 12:34:19.489974: step: 460/530, loss: 0.00011901855032192543
2023-01-21 12:34:20.634837: step: 464/530, loss: 0.020872557535767555
2023-01-21 12:34:21.762643: step: 468/530, loss: 0.0007745742914266884
2023-01-21 12:34:22.893829: step: 472/530, loss: 3.814697265625e-05
2023-01-21 12:34:23.999376: step: 476/530, loss: 0.017302418127655983
2023-01-21 12:34:25.126227: step: 480/530, loss: 0.0019216537475585938
2023-01-21 12:34:26.258241: step: 484/530, loss: 0.00607566861435771
2023-01-21 12:34:27.387956: step: 488/530, loss: 0.0013240814441815019
2023-01-21 12:34:28.517828: step: 492/530, loss: 0.04228191450238228
2023-01-21 12:34:29.621229: step: 496/530, loss: 0.0047626495361328125
2023-01-21 12:34:30.779595: step: 500/530, loss: 0.00312042236328125
2023-01-21 12:34:31.908914: step: 504/530, loss: 0.0016063690418377519
2023-01-21 12:34:33.047550: step: 508/530, loss: 0.0020351409912109375
2023-01-21 12:34:34.170822: step: 512/530, loss: 3.395080420887098e-05
2023-01-21 12:34:35.314987: step: 516/530, loss: 0.021654892712831497
2023-01-21 12:34:36.460783: step: 520/530, loss: 4.138946678722277e-05
2023-01-21 12:34:37.588911: step: 524/530, loss: 0.0013813019031658769
2023-01-21 12:34:38.687319: step: 528/530, loss: 0.009017754346132278
2023-01-21 12:34:39.807444: step: 532/530, loss: 0.006644630804657936
2023-01-21 12:34:40.942107: step: 536/530, loss: 2.098083541568485e-06
2023-01-21 12:34:42.086990: step: 540/530, loss: 6.198883056640625e-05
2023-01-21 12:34:43.214034: step: 544/530, loss: 1.2207030522404239e-05
2023-01-21 12:34:44.345063: step: 548/530, loss: 0.01349563617259264
2023-01-21 12:34:45.474600: step: 552/530, loss: 0.005539512727409601
2023-01-21 12:34:46.604781: step: 556/530, loss: 0.00018587111844681203
2023-01-21 12:34:47.732898: step: 560/530, loss: 0.007181453984230757
2023-01-21 12:34:48.853251: step: 564/530, loss: 0.01138381939381361
2023-01-21 12:34:49.974073: step: 568/530, loss: 0.003118896624073386
2023-01-21 12:34:51.110144: step: 572/530, loss: 0.0012011528015136719
2023-01-21 12:34:52.216930: step: 576/530, loss: 0.0004024505615234375
2023-01-21 12:34:53.361411: step: 580/530, loss: 0.00271778111346066
2023-01-21 12:34:54.465787: step: 584/530, loss: 0.0004760742303915322
2023-01-21 12:34:55.574733: step: 588/530, loss: 5.91278057981981e-06
2023-01-21 12:34:56.703783: step: 592/530, loss: 0.04535055160522461
2023-01-21 12:34:57.833116: step: 596/530, loss: 0.000162219992489554
2023-01-21 12:34:58.945302: step: 600/530, loss: 0.0010696887038648129
2023-01-21 12:35:00.075189: step: 604/530, loss: 0.038133811205625534
2023-01-21 12:35:01.182641: step: 608/530, loss: 0.0013736725086346269
2023-01-21 12:35:02.312220: step: 612/530, loss: 0.11062164604663849
2023-01-21 12:35:03.404350: step: 616/530, loss: 0.003072738880291581
2023-01-21 12:35:04.528927: step: 620/530, loss: 0.005662345793098211
2023-01-21 12:35:05.628491: step: 624/530, loss: 5.2165985835017636e-05
2023-01-21 12:35:06.743654: step: 628/530, loss: 0.03488664701581001
2023-01-21 12:35:07.877482: step: 632/530, loss: 0.0001316070556640625
2023-01-21 12:35:09.013088: step: 636/530, loss: 0.031374357640743256
2023-01-21 12:35:10.124895: step: 640/530, loss: 0.026055097579956055
2023-01-21 12:35:11.301315: step: 644/530, loss: 0.051069069653749466
2023-01-21 12:35:12.424777: step: 648/530, loss: 0.00034923554630950093
2023-01-21 12:35:13.533006: step: 652/530, loss: 0.009720420464873314
2023-01-21 12:35:14.636099: step: 656/530, loss: 1.0967255548166577e-05
2023-01-21 12:35:15.746762: step: 660/530, loss: 0.0012415886158123612
2023-01-21 12:35:16.863007: step: 664/530, loss: 0.004417038056999445
2023-01-21 12:35:18.002785: step: 668/530, loss: 0.00018463133892510086
2023-01-21 12:35:19.122014: step: 672/530, loss: 0.0075469971634447575
2023-01-21 12:35:20.239287: step: 676/530, loss: 0.03972005844116211
2023-01-21 12:35:21.357630: step: 680/530, loss: 0.007507515139877796
2023-01-21 12:35:22.447719: step: 684/530, loss: 0.0022188189905136824
2023-01-21 12:35:23.608009: step: 688/530, loss: 0.005376625340431929
2023-01-21 12:35:24.715648: step: 692/530, loss: 0.0035339356400072575
2023-01-21 12:35:25.824903: step: 696/530, loss: 3.5953522456111386e-05
2023-01-21 12:35:26.976037: step: 700/530, loss: 0.0020013810135424137
2023-01-21 12:35:28.097922: step: 704/530, loss: 0.00698013324290514
2023-01-21 12:35:29.236200: step: 708/530, loss: 0.007763099856674671
2023-01-21 12:35:30.334355: step: 712/530, loss: 0.03202075883746147
2023-01-21 12:35:31.442295: step: 716/530, loss: 0.0015447615878656507
2023-01-21 12:35:32.602824: step: 720/530, loss: 0.0006816864479333162
2023-01-21 12:35:33.722129: step: 724/530, loss: 0.0010725021129474044
2023-01-21 12:35:34.859242: step: 728/530, loss: 0.14784927666187286
2023-01-21 12:35:35.981527: step: 732/530, loss: 0.02184581756591797
2023-01-21 12:35:37.122911: step: 736/530, loss: 0.00106048583984375
2023-01-21 12:35:38.254708: step: 740/530, loss: 0.02141733095049858
2023-01-21 12:35:39.374888: step: 744/530, loss: 0.0013959883945062757
2023-01-21 12:35:40.511033: step: 748/530, loss: 0.05695819854736328
2023-01-21 12:35:41.631887: step: 752/530, loss: 0.008107949048280716
2023-01-21 12:35:42.778687: step: 756/530, loss: 0.0022806168999522924
2023-01-21 12:35:43.893619: step: 760/530, loss: 0.00018024444580078125
2023-01-21 12:35:45.050958: step: 764/530, loss: 0.02486133575439453
2023-01-21 12:35:46.175222: step: 768/530, loss: 0.0014122009743005037
2023-01-21 12:35:47.312593: step: 772/530, loss: 0.004006910603493452
2023-01-21 12:35:48.432769: step: 776/530, loss: 0.058977700769901276
2023-01-21 12:35:49.578104: step: 780/530, loss: 0.03047809563577175
2023-01-21 12:35:50.692792: step: 784/530, loss: 0.009504414163529873
2023-01-21 12:35:51.803767: step: 788/530, loss: 0.0023006440605968237
2023-01-21 12:35:52.942393: step: 792/530, loss: 0.019623756408691406
2023-01-21 12:35:54.054335: step: 796/530, loss: 0.005626964382827282
2023-01-21 12:35:55.181673: step: 800/530, loss: 0.0004570961173158139
2023-01-21 12:35:56.297640: step: 804/530, loss: 0.060202695429325104
2023-01-21 12:35:57.421912: step: 808/530, loss: 8.420944504905492e-05
2023-01-21 12:35:58.550765: step: 812/530, loss: 0.0019321441650390625
2023-01-21 12:35:59.668371: step: 816/530, loss: 0.06533565372228622
2023-01-21 12:36:00.810581: step: 820/530, loss: 0.0016355514526367188
2023-01-21 12:36:01.941186: step: 824/530, loss: 0.006747054867446423
2023-01-21 12:36:03.070424: step: 828/530, loss: 2.6988984245690517e-05
2023-01-21 12:36:04.191095: step: 832/530, loss: 0.00012931822857353836
2023-01-21 12:36:05.335403: step: 836/530, loss: 0.03265238180756569
2023-01-21 12:36:06.438404: step: 840/530, loss: 0.0001417636958649382
2023-01-21 12:36:07.569435: step: 844/530, loss: 0.00210914621129632
2023-01-21 12:36:08.704562: step: 848/530, loss: 0.000881195068359375
2023-01-21 12:36:09.830720: step: 852/530, loss: 0.0003283500554971397
2023-01-21 12:36:10.921623: step: 856/530, loss: 2.1457672119140625e-06
2023-01-21 12:36:12.008401: step: 860/530, loss: 0.002171135041862726
2023-01-21 12:36:13.130783: step: 864/530, loss: 0.0003616332833189517
2023-01-21 12:36:14.233990: step: 868/530, loss: 0.002990245819091797
2023-01-21 12:36:15.371948: step: 872/530, loss: 0.0005285263177938759
2023-01-21 12:36:16.549959: step: 876/530, loss: 0.00011482238915050402
2023-01-21 12:36:17.672235: step: 880/530, loss: 0.0002402305690338835
2023-01-21 12:36:18.777252: step: 884/530, loss: 9.31739850784652e-05
2023-01-21 12:36:19.871851: step: 888/530, loss: 0.00068073277361691
2023-01-21 12:36:20.998817: step: 892/530, loss: 0.003147983690723777
2023-01-21 12:36:22.133795: step: 896/530, loss: 0.0014652252430096269
2023-01-21 12:36:23.231636: step: 900/530, loss: 0.0007004737854003906
2023-01-21 12:36:24.345678: step: 904/530, loss: 6.008148375258315e-06
2023-01-21 12:36:25.469581: step: 908/530, loss: 0.06401939690113068
2023-01-21 12:36:26.582504: step: 912/530, loss: 0.0009490966913290322
2023-01-21 12:36:27.721137: step: 916/530, loss: 0.0013725280296057463
2023-01-21 12:36:28.851524: step: 920/530, loss: 0.022217940539121628
2023-01-21 12:36:29.974304: step: 924/530, loss: 0.1582581102848053
2023-01-21 12:36:31.147842: step: 928/530, loss: 0.0007942199590615928
2023-01-21 12:36:32.296784: step: 932/530, loss: 0.000782012939453125
2023-01-21 12:36:33.436910: step: 936/530, loss: 0.00031552318250760436
2023-01-21 12:36:34.542385: step: 940/530, loss: 0.00069427490234375
2023-01-21 12:36:35.657770: step: 944/530, loss: 1.6880036127986386e-05
2023-01-21 12:36:36.784932: step: 948/530, loss: 7.343292236328125e-05
2023-01-21 12:36:37.878183: step: 952/530, loss: 0.003228092333301902
2023-01-21 12:36:38.982247: step: 956/530, loss: 0.00015144346980378032
2023-01-21 12:36:40.149788: step: 960/530, loss: 0.00040464402991347015
2023-01-21 12:36:41.252473: step: 964/530, loss: 0.001304245088249445
2023-01-21 12:36:42.376105: step: 968/530, loss: 0.000301551801385358
2023-01-21 12:36:43.499362: step: 972/530, loss: 0.0001659393310546875
2023-01-21 12:36:44.580839: step: 976/530, loss: 0.027672292664647102
2023-01-21 12:36:45.707728: step: 980/530, loss: 0.0025873181875795126
2023-01-21 12:36:46.806410: step: 984/530, loss: 0.001699733780696988
2023-01-21 12:36:47.908470: step: 988/530, loss: 0.000926971435546875
2023-01-21 12:36:49.063233: step: 992/530, loss: 0.03643856197595596
2023-01-21 12:36:50.202395: step: 996/530, loss: 3.24249276673072e-06
2023-01-21 12:36:51.360063: step: 1000/530, loss: 4.9591064453125e-05
2023-01-21 12:36:52.484144: step: 1004/530, loss: 0.0005671501276083291
2023-01-21 12:36:53.641166: step: 1008/530, loss: 0.001154232071712613
2023-01-21 12:36:54.772942: step: 1012/530, loss: 0.031168939545750618
2023-01-21 12:36:55.880364: step: 1016/530, loss: 0.0010029793484136462
2023-01-21 12:36:57.072342: step: 1020/530, loss: 0.0015436172252520919
2023-01-21 12:36:58.225118: step: 1024/530, loss: 0.021173859015107155
2023-01-21 12:36:59.329797: step: 1028/530, loss: 0.05048447102308273
2023-01-21 12:37:00.472081: step: 1032/530, loss: 0.0004728376807179302
2023-01-21 12:37:01.625274: step: 1036/530, loss: 0.007236289791762829
2023-01-21 12:37:02.748166: step: 1040/530, loss: 0.0008633971447125077
2023-01-21 12:37:03.899360: step: 1044/530, loss: 0.014343309216201305
2023-01-21 12:37:05.007991: step: 1048/530, loss: 0.009192085824906826
2023-01-21 12:37:06.140776: step: 1052/530, loss: 0.004955005366355181
2023-01-21 12:37:07.241446: step: 1056/530, loss: 0.0013765335315838456
2023-01-21 12:37:08.349690: step: 1060/530, loss: 4.844665454584174e-05
2023-01-21 12:37:09.460177: step: 1064/530, loss: 0.00034670828608796
2023-01-21 12:37:10.576005: step: 1068/530, loss: 0.002631568815559149
2023-01-21 12:37:11.695054: step: 1072/530, loss: 6.0844424297101796e-05
2023-01-21 12:37:12.809026: step: 1076/530, loss: 0.0009773254860192537
2023-01-21 12:37:13.909514: step: 1080/530, loss: 0.009446144104003906
2023-01-21 12:37:15.035567: step: 1084/530, loss: 0.005185508634895086
2023-01-21 12:37:16.173319: step: 1088/530, loss: 0.040428876876831055
2023-01-21 12:37:17.305602: step: 1092/530, loss: 0.0006239891517907381
2023-01-21 12:37:18.442932: step: 1096/530, loss: 0.04018726199865341
2023-01-21 12:37:19.533214: step: 1100/530, loss: 2.1266938347253017e-05
2023-01-21 12:37:20.645098: step: 1104/530, loss: 0.0005405425908975303
2023-01-21 12:37:21.751857: step: 1108/530, loss: 0.0004604339774232358
2023-01-21 12:37:22.871629: step: 1112/530, loss: 3.948211815441027e-05
2023-01-21 12:37:24.016228: step: 1116/530, loss: 0.03215665742754936
2023-01-21 12:37:25.167085: step: 1120/530, loss: 0.0030050277709960938
2023-01-21 12:37:26.275327: step: 1124/530, loss: 4.386902219266631e-06
2023-01-21 12:37:27.387944: step: 1128/530, loss: 0.0014562606811523438
2023-01-21 12:37:28.534452: step: 1132/530, loss: 0.000377464311895892
2023-01-21 12:37:29.647406: step: 1136/530, loss: 0.002502012299373746
2023-01-21 12:37:30.746146: step: 1140/530, loss: 0.013344956561923027
2023-01-21 12:37:31.876815: step: 1144/530, loss: 0.0015727997524663806
2023-01-21 12:37:33.005819: step: 1148/530, loss: 0.008260536007583141
2023-01-21 12:37:34.132813: step: 1152/530, loss: 7.932185690151528e-05
2023-01-21 12:37:35.241408: step: 1156/530, loss: 5.7220458984375e-06
2023-01-21 12:37:36.345769: step: 1160/530, loss: 0.04091301187872887
2023-01-21 12:37:37.482815: step: 1164/530, loss: 0.0063818455673754215
2023-01-21 12:37:38.584327: step: 1168/530, loss: 0.004650211427360773
2023-01-21 12:37:39.717098: step: 1172/530, loss: 0.04616737738251686
2023-01-21 12:37:40.855258: step: 1176/530, loss: 0.0004634857177734375
2023-01-21 12:37:41.986500: step: 1180/530, loss: 4.9185753596248105e-05
2023-01-21 12:37:43.126857: step: 1184/530, loss: 0.0002958297554869205
2023-01-21 12:37:44.253854: step: 1188/530, loss: 0.07427101582288742
2023-01-21 12:37:45.362307: step: 1192/530, loss: 2.040863000729587e-05
2023-01-21 12:37:46.468647: step: 1196/530, loss: 0.48779773712158203
2023-01-21 12:37:47.612302: step: 1200/530, loss: 0.00032577518140897155
2023-01-21 12:37:48.740711: step: 1204/530, loss: 0.008599949069321156
2023-01-21 12:37:49.855471: step: 1208/530, loss: 0.0008096694946289062
2023-01-21 12:37:50.948167: step: 1212/530, loss: 0.013564110733568668
2023-01-21 12:37:52.068238: step: 1216/530, loss: 0.024104690179228783
2023-01-21 12:37:53.195194: step: 1220/530, loss: 0.0373104102909565
2023-01-21 12:37:54.323139: step: 1224/530, loss: 0.03739356994628906
2023-01-21 12:37:55.496939: step: 1228/530, loss: 0.0003410339413676411
2023-01-21 12:37:56.603293: step: 1232/530, loss: 0.010662746615707874
2023-01-21 12:37:57.723728: step: 1236/530, loss: 7.295608520507812e-05
2023-01-21 12:37:58.837867: step: 1240/530, loss: 0.00031194687471725047
2023-01-21 12:37:59.959828: step: 1244/530, loss: 0.5715429186820984
2023-01-21 12:38:01.056680: step: 1248/530, loss: 2.880096508306451e-05
2023-01-21 12:38:02.233399: step: 1252/530, loss: 0.01704993285238743
2023-01-21 12:38:03.354668: step: 1256/530, loss: 0.00756683386862278
2023-01-21 12:38:04.481675: step: 1260/530, loss: 0.0014079571701586246
2023-01-21 12:38:05.584004: step: 1264/530, loss: 0.002998924348503351
2023-01-21 12:38:06.694440: step: 1268/530, loss: 0.00014791489229537547
2023-01-21 12:38:07.819963: step: 1272/530, loss: 0.010972213931381702
2023-01-21 12:38:08.966342: step: 1276/530, loss: 0.0832241028547287
2023-01-21 12:38:10.070903: step: 1280/530, loss: 0.2894379496574402
2023-01-21 12:38:11.202917: step: 1284/530, loss: 0.00041284560575149953
2023-01-21 12:38:12.340785: step: 1288/530, loss: 0.0007882117643021047
2023-01-21 12:38:13.492492: step: 1292/530, loss: 0.0018182755447924137
2023-01-21 12:38:14.614536: step: 1296/530, loss: 0.0027608871459960938
2023-01-21 12:38:15.727658: step: 1300/530, loss: 0.0030174495186656713
2023-01-21 12:38:16.894026: step: 1304/530, loss: 0.05016689375042915
2023-01-21 12:38:18.004123: step: 1308/530, loss: 0.009126568213105202
2023-01-21 12:38:19.099159: step: 1312/530, loss: 1.9550323486328125e-05
2023-01-21 12:38:20.206629: step: 1316/530, loss: 0.003460502717643976
2023-01-21 12:38:21.298669: step: 1320/530, loss: 0.03002491220831871
2023-01-21 12:38:22.407297: step: 1324/530, loss: 0.03893012925982475
2023-01-21 12:38:23.531609: step: 1328/530, loss: 0.00024318695068359375
2023-01-21 12:38:24.629958: step: 1332/530, loss: 0.0005234241834841669
2023-01-21 12:38:25.759072: step: 1336/530, loss: 0.02037992514669895
2023-01-21 12:38:26.879652: step: 1340/530, loss: 0.007461833767592907
2023-01-21 12:38:28.009888: step: 1344/530, loss: 0.011014461517333984
2023-01-21 12:38:29.134004: step: 1348/530, loss: 0.0008279800531454384
2023-01-21 12:38:30.273272: step: 1352/530, loss: 0.00010414123244117945
2023-01-21 12:38:31.407719: step: 1356/530, loss: 0.04655780643224716
2023-01-21 12:38:32.527278: step: 1360/530, loss: 0.011810874566435814
2023-01-21 12:38:33.647869: step: 1364/530, loss: 7.066727266646922e-05
2023-01-21 12:38:34.769616: step: 1368/530, loss: 0.00028162001399323344
2023-01-21 12:38:35.867708: step: 1372/530, loss: 0.0029458999633789062
2023-01-21 12:38:36.991060: step: 1376/530, loss: 0.0025959014892578125
2023-01-21 12:38:38.095443: step: 1380/530, loss: 0.003925800323486328
2023-01-21 12:38:39.221015: step: 1384/530, loss: 0.02117319032549858
2023-01-21 12:38:40.381553: step: 1388/530, loss: 0.0001560211239848286
2023-01-21 12:38:41.562043: step: 1392/530, loss: 0.09024753421545029
2023-01-21 12:38:42.679845: step: 1396/530, loss: 0.0029159546829760075
2023-01-21 12:38:43.819471: step: 1400/530, loss: 0.00019493103900458664
2023-01-21 12:38:44.980046: step: 1404/530, loss: 0.03144645690917969
2023-01-21 12:38:46.116818: step: 1408/530, loss: 0.0027206421364098787
2023-01-21 12:38:47.259094: step: 1412/530, loss: 0.00043697358341887593
2023-01-21 12:38:48.405652: step: 1416/530, loss: 8.22067231638357e-05
2023-01-21 12:38:49.524464: step: 1420/530, loss: 0.00011167525372002274
2023-01-21 12:38:50.647857: step: 1424/530, loss: 0.044243812561035156
2023-01-21 12:38:51.751757: step: 1428/530, loss: 0.11790166050195694
2023-01-21 12:38:52.865372: step: 1432/530, loss: 0.0007271289941854775
2023-01-21 12:38:53.968821: step: 1436/530, loss: 7.796287536621094e-05
2023-01-21 12:38:55.070645: step: 1440/530, loss: 0.10536542534828186
2023-01-21 12:38:56.197187: step: 1444/530, loss: 0.03635730594396591
2023-01-21 12:38:57.322190: step: 1448/530, loss: 7.176399230957031e-05
2023-01-21 12:38:58.443760: step: 1452/530, loss: 0.014511299319565296
2023-01-21 12:38:59.551137: step: 1456/530, loss: 0.08388223499059677
2023-01-21 12:39:00.667061: step: 1460/530, loss: 0.00029792787972837687
2023-01-21 12:39:01.782086: step: 1464/530, loss: 5.7220458984375e-05
2023-01-21 12:39:02.925180: step: 1468/530, loss: 0.00041265488835051656
2023-01-21 12:39:04.025990: step: 1472/530, loss: 0.0018864631420001388
2023-01-21 12:39:05.142553: step: 1476/530, loss: 0.2275291383266449
2023-01-21 12:39:06.242504: step: 1480/530, loss: 0.0010129929287359118
2023-01-21 12:39:07.352556: step: 1484/530, loss: 0.0009576797601766884
2023-01-21 12:39:08.491182: step: 1488/530, loss: 0.02427196502685547
2023-01-21 12:39:09.588149: step: 1492/530, loss: 0.0002503395080566406
2023-01-21 12:39:10.707974: step: 1496/530, loss: 0.00032939910306595266
2023-01-21 12:39:11.853889: step: 1500/530, loss: 0.003056049346923828
2023-01-21 12:39:12.959626: step: 1504/530, loss: 0.0008501053089275956
2023-01-21 12:39:14.071792: step: 1508/530, loss: 0.007679510395973921
2023-01-21 12:39:15.210236: step: 1512/530, loss: 0.0004998207441531122
2023-01-21 12:39:16.363518: step: 1516/530, loss: 0.00039768218994140625
2023-01-21 12:39:17.466237: step: 1520/530, loss: 0.0057086944580078125
2023-01-21 12:39:18.591141: step: 1524/530, loss: 0.06266222149133682
2023-01-21 12:39:19.739931: step: 1528/530, loss: 0.0007397651788778603
2023-01-21 12:39:20.916646: step: 1532/530, loss: 0.0030588151421397924
2023-01-21 12:39:22.030276: step: 1536/530, loss: -1.9073468138230965e-07
2023-01-21 12:39:23.165002: step: 1540/530, loss: 0.004165077116340399
2023-01-21 12:39:24.307010: step: 1544/530, loss: 0.0005764961242675781
2023-01-21 12:39:25.414425: step: 1548/530, loss: 0.0015143394703045487
2023-01-21 12:39:26.536398: step: 1552/530, loss: 0.01902618445456028
2023-01-21 12:39:27.645635: step: 1556/530, loss: 0.0005631447420455515
2023-01-21 12:39:28.802976: step: 1560/530, loss: 0.005268335808068514
2023-01-21 12:39:29.918276: step: 1564/530, loss: 0.0013212204212322831
2023-01-21 12:39:31.047927: step: 1568/530, loss: 3.933906555175781e-06
2023-01-21 12:39:32.173675: step: 1572/530, loss: 0.0002745628298725933
2023-01-21 12:39:33.304143: step: 1576/530, loss: 0.0004952431190758944
2023-01-21 12:39:34.445678: step: 1580/530, loss: 0.0013483046786859632
2023-01-21 12:39:35.575682: step: 1584/530, loss: 0.0239944476634264
2023-01-21 12:39:36.679044: step: 1588/530, loss: 0.00026378632173873484
2023-01-21 12:39:37.792605: step: 1592/530, loss: 0.018082523718476295
2023-01-21 12:39:38.952351: step: 1596/530, loss: 0.004073714837431908
2023-01-21 12:39:40.037712: step: 1600/530, loss: 0.002628421876579523
2023-01-21 12:39:41.176485: step: 1604/530, loss: 5.34057608092553e-06
2023-01-21 12:39:42.331972: step: 1608/530, loss: 0.0017503738636150956
2023-01-21 12:39:43.457804: step: 1612/530, loss: 0.0005064487922936678
2023-01-21 12:39:44.592498: step: 1616/530, loss: 0.029465580359101295
2023-01-21 12:39:45.760163: step: 1620/530, loss: 0.0024291991721838713
2023-01-21 12:39:46.869807: step: 1624/530, loss: 0.0009017944685183465
2023-01-21 12:39:47.964067: step: 1628/530, loss: 0.06373786926269531
2023-01-21 12:39:49.076721: step: 1632/530, loss: 0.012770270928740501
2023-01-21 12:39:50.191701: step: 1636/530, loss: 0.00166578299831599
2023-01-21 12:39:51.344558: step: 1640/530, loss: 5.054474058852065e-06
2023-01-21 12:39:52.464484: step: 1644/530, loss: 0.000250399112701416
2023-01-21 12:39:53.569956: step: 1648/530, loss: 6.561278860317543e-05
2023-01-21 12:39:54.690046: step: 1652/530, loss: 0.0007844925276003778
2023-01-21 12:39:55.800161: step: 1656/530, loss: 0.02035980299115181
2023-01-21 12:39:56.927483: step: 1660/530, loss: 0.011255073361098766
2023-01-21 12:39:58.039230: step: 1664/530, loss: 0.047866251319646835
2023-01-21 12:39:59.142958: step: 1668/530, loss: 0.0017274855636060238
2023-01-21 12:40:00.247332: step: 1672/530, loss: 0.00018740296945907176
2023-01-21 12:40:01.359722: step: 1676/530, loss: 0.0021615028381347656
2023-01-21 12:40:02.490096: step: 1680/530, loss: 0.03169288486242294
2023-01-21 12:40:03.605554: step: 1684/530, loss: 4.291534423828125e-06
2023-01-21 12:40:04.754640: step: 1688/530, loss: 0.0038038729690015316
2023-01-21 12:40:05.896001: step: 1692/530, loss: 2.288818359375e-05
2023-01-21 12:40:07.006018: step: 1696/530, loss: 5.054473876953125e-05
2023-01-21 12:40:08.090267: step: 1700/530, loss: 0.04905281215906143
2023-01-21 12:40:09.200128: step: 1704/530, loss: 0.009461402893066406
2023-01-21 12:40:10.310320: step: 1708/530, loss: 0.015836715698242188
2023-01-21 12:40:11.450086: step: 1712/530, loss: 5.2928924560546875e-05
2023-01-21 12:40:12.569904: step: 1716/530, loss: 0.00027809140738099813
2023-01-21 12:40:13.677488: step: 1720/530, loss: 0.00023746491933707148
2023-01-21 12:40:14.795729: step: 1724/530, loss: 0.000225067138671875
2023-01-21 12:40:15.905597: step: 1728/530, loss: 0.0018990517128258944
2023-01-21 12:40:17.065924: step: 1732/530, loss: 0.0005748748662881553
2023-01-21 12:40:18.176709: step: 1736/530, loss: 0.013747597113251686
2023-01-21 12:40:19.293450: step: 1740/530, loss: 6.29425048828125e-05
2023-01-21 12:40:20.455134: step: 1744/530, loss: 0.00020828247943427414
2023-01-21 12:40:21.559772: step: 1748/530, loss: 0.00048451422480866313
2023-01-21 12:40:22.692875: step: 1752/530, loss: 0.006011295598000288
2023-01-21 12:40:23.816068: step: 1756/530, loss: 0.04006242752075195
2023-01-21 12:40:24.918912: step: 1760/530, loss: 0.00028905869112350047
2023-01-21 12:40:26.019311: step: 1764/530, loss: 0.0007390976534225047
2023-01-21 12:40:27.129924: step: 1768/530, loss: 0.8443310856819153
2023-01-21 12:40:28.255346: step: 1772/530, loss: 0.0006501197931356728
2023-01-21 12:40:29.386804: step: 1776/530, loss: 0.0036193716805428267
2023-01-21 12:40:30.510940: step: 1780/530, loss: 2.079009937006049e-05
2023-01-21 12:40:31.633832: step: 1784/530, loss: 0.006583786103874445
2023-01-21 12:40:32.726583: step: 1788/530, loss: 0.006136417388916016
2023-01-21 12:40:33.834358: step: 1792/530, loss: 0.00046596527681685984
2023-01-21 12:40:34.969123: step: 1796/530, loss: 0.06995125114917755
2023-01-21 12:40:36.075077: step: 1800/530, loss: 0.0018578529125079513
2023-01-21 12:40:37.189264: step: 1804/530, loss: 0.0067008971236646175
2023-01-21 12:40:38.302250: step: 1808/530, loss: 0.010495185852050781
2023-01-21 12:40:39.419545: step: 1812/530, loss: 1.373290979245212e-05
2023-01-21 12:40:40.561671: step: 1816/530, loss: 0.013246918097138405
2023-01-21 12:40:41.689803: step: 1820/530, loss: 0.00014605523028876632
2023-01-21 12:40:42.814355: step: 1824/530, loss: 0.0008626937633380294
2023-01-21 12:40:43.949193: step: 1828/530, loss: 0.002320671221241355
2023-01-21 12:40:45.068537: step: 1832/530, loss: 0.01488800160586834
2023-01-21 12:40:46.193891: step: 1836/530, loss: 0.0014726639492437243
2023-01-21 12:40:47.296867: step: 1840/530, loss: 0.025364303961396217
2023-01-21 12:40:48.398950: step: 1844/530, loss: 0.03314242511987686
2023-01-21 12:40:49.513171: step: 1848/530, loss: 0.027219535782933235
2023-01-21 12:40:50.634476: step: 1852/530, loss: 0.03045206144452095
2023-01-21 12:40:51.769043: step: 1856/530, loss: 0.012042809277772903
2023-01-21 12:40:52.881390: step: 1860/530, loss: -0.0
2023-01-21 12:40:54.002790: step: 1864/530, loss: 0.009336852468550205
2023-01-21 12:40:55.119850: step: 1868/530, loss: 0.00034294126089662313
2023-01-21 12:40:56.261681: step: 1872/530, loss: 0.0014785766834393144
2023-01-21 12:40:57.382596: step: 1876/530, loss: 0.08442115783691406
2023-01-21 12:40:58.506485: step: 1880/530, loss: 0.003116178559139371
2023-01-21 12:40:59.630978: step: 1884/530, loss: 0.009947204031050205
2023-01-21 12:41:00.720240: step: 1888/530, loss: 8.449554297840223e-05
2023-01-21 12:41:01.836457: step: 1892/530, loss: 0.0009847640758380294
2023-01-21 12:41:02.947462: step: 1896/530, loss: 0.040963172912597656
2023-01-21 12:41:04.053243: step: 1900/530, loss: 0.013965511694550514
2023-01-21 12:41:05.170846: step: 1904/530, loss: 0.05112838372588158
2023-01-21 12:41:06.267865: step: 1908/530, loss: 0.0006885528564453125
2023-01-21 12:41:07.361172: step: 1912/530, loss: 0.0009851455688476562
2023-01-21 12:41:08.497750: step: 1916/530, loss: 0.20425738394260406
2023-01-21 12:41:09.649880: step: 1920/530, loss: 0.0018428802723065019
2023-01-21 12:41:10.773640: step: 1924/530, loss: 0.03312397003173828
2023-01-21 12:41:11.901863: step: 1928/530, loss: 0.03607216104865074
2023-01-21 12:41:13.019654: step: 1932/530, loss: 5.90324416407384e-05
2023-01-21 12:41:14.150213: step: 1936/530, loss: 0.06407833099365234
2023-01-21 12:41:15.296710: step: 1940/530, loss: 0.0021198273170739412
2023-01-21 12:41:16.390902: step: 1944/530, loss: 0.007351208012551069
2023-01-21 12:41:17.493765: step: 1948/530, loss: 0.0006916105630807579
2023-01-21 12:41:18.644516: step: 1952/530, loss: 0.012972068972885609
2023-01-21 12:41:19.758502: step: 1956/530, loss: 0.00340957660228014
2023-01-21 12:41:20.871911: step: 1960/530, loss: 0.0008537292596884072
2023-01-21 12:41:21.993886: step: 1964/530, loss: 0.00670547503978014
2023-01-21 12:41:23.123209: step: 1968/530, loss: 0.0009922027820721269
2023-01-21 12:41:24.264265: step: 1972/530, loss: 0.0006067276117391884
2023-01-21 12:41:25.383871: step: 1976/530, loss: 0.47459742426872253
2023-01-21 12:41:26.527657: step: 1980/530, loss: 0.0037537156604230404
2023-01-21 12:41:27.644277: step: 1984/530, loss: 3.8528440200025216e-05
2023-01-21 12:41:28.769087: step: 1988/530, loss: 0.0028828619979321957
2023-01-21 12:41:29.876583: step: 1992/530, loss: 0.0012567519443109632
2023-01-21 12:41:31.012706: step: 1996/530, loss: 0.00022573472233489156
2023-01-21 12:41:32.154543: step: 2000/530, loss: 0.0003105163632426411
2023-01-21 12:41:33.276680: step: 2004/530, loss: 0.009796142578125
2023-01-21 12:41:34.382996: step: 2008/530, loss: 0.007603490725159645
2023-01-21 12:41:35.524797: step: 2012/530, loss: 0.0157470703125
2023-01-21 12:41:36.662912: step: 2016/530, loss: 0.00042028428288176656
2023-01-21 12:41:37.776871: step: 2020/530, loss: 0.001254606293514371
2023-01-21 12:41:38.881862: step: 2024/530, loss: 0.0030759815126657486
2023-01-21 12:41:39.983983: step: 2028/530, loss: 0.2857952415943146
2023-01-21 12:41:41.131831: step: 2032/530, loss: 0.0008859634981490672
2023-01-21 12:41:42.245795: step: 2036/530, loss: 0.028385544195771217
2023-01-21 12:41:43.372762: step: 2040/530, loss: 8.640289888717234e-05
2023-01-21 12:41:44.491593: step: 2044/530, loss: 0.00027523041353560984
2023-01-21 12:41:45.625918: step: 2048/530, loss: 8.487701052217744e-06
2023-01-21 12:41:46.747733: step: 2052/530, loss: 0.01129379216581583
2023-01-21 12:41:47.861514: step: 2056/530, loss: 0.005154800601303577
2023-01-21 12:41:49.024576: step: 2060/530, loss: 0.0001354217529296875
2023-01-21 12:41:50.167843: step: 2064/530, loss: 0.00201072683557868
2023-01-21 12:41:51.261117: step: 2068/530, loss: 0.006250286009162664
2023-01-21 12:41:52.365315: step: 2072/530, loss: 0.026176119223237038
2023-01-21 12:41:53.509051: step: 2076/530, loss: 0.0033628465607762337
2023-01-21 12:41:54.627958: step: 2080/530, loss: 0.0009593904251232743
2023-01-21 12:41:55.733244: step: 2084/530, loss: 0.002859401749446988
2023-01-21 12:41:56.838661: step: 2088/530, loss: 0.000500583671964705
2023-01-21 12:41:57.958281: step: 2092/530, loss: 0.011326218023896217
2023-01-21 12:41:59.066482: step: 2096/530, loss: 2.555549144744873e-06
2023-01-21 12:42:00.178516: step: 2100/530, loss: 0.011316013522446156
2023-01-21 12:42:01.298606: step: 2104/530, loss: 0.025014590471982956
2023-01-21 12:42:02.454314: step: 2108/530, loss: 0.008699418045580387
2023-01-21 12:42:03.562449: step: 2112/530, loss: 2.4604798454674892e-05
2023-01-21 12:42:04.677666: step: 2116/530, loss: 0.00029201508732512593
2023-01-21 12:42:05.801829: step: 2120/530, loss: 0.025395872071385384
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5988083416087389, 'r': 0.8029294274300932, 'f1': 0.6860068259385667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6291122127084272, 'r': 0.7977142857142857, 'f1': 0.7034517510707987}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.5555555555555556, 'r': 0.9259259259259259, 'f1': 0.6944444444444444}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.5818181818181818, 'r': 0.5079365079365079, 'f1': 0.5423728813559321}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
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': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 12:42:46.369918: step: 4/530, loss: 7.152557373046875e-06
2023-01-21 12:42:47.475596: step: 8/530, loss: 0.00015726088895462453
2023-01-21 12:42:48.601388: step: 12/530, loss: 0.011050033383071423
2023-01-21 12:42:49.721588: step: 16/530, loss: 0.0021656036842614412
2023-01-21 12:42:50.819178: step: 20/530, loss: 0.004557132720947266
2023-01-21 12:42:51.938863: step: 24/530, loss: 5.092620995128527e-05
2023-01-21 12:42:53.073541: step: 28/530, loss: 0.0166899673640728
2023-01-21 12:42:54.204122: step: 32/530, loss: 0.0006323814741335809
2023-01-21 12:42:55.326865: step: 36/530, loss: 0.0001312255917582661
2023-01-21 12:42:56.430117: step: 40/530, loss: 9.55581635935232e-05
2023-01-21 12:42:57.545610: step: 44/530, loss: 0.0031045437790453434
2023-01-21 12:42:58.668351: step: 48/530, loss: 0.0005063057178631425
2023-01-21 12:42:59.782483: step: 52/530, loss: 0.0007642745622433722
2023-01-21 12:43:00.895700: step: 56/530, loss: 0.0006123543134890497
2023-01-21 12:43:02.003055: step: 60/530, loss: 7.467270188499242e-05
2023-01-21 12:43:03.163823: step: 64/530, loss: 0.015358471311628819
2023-01-21 12:43:04.312011: step: 68/530, loss: 0.0010952949523925781
2023-01-21 12:43:05.450278: step: 72/530, loss: 0.0012739181984215975
2023-01-21 12:43:06.572708: step: 76/530, loss: 0.013843679800629616
2023-01-21 12:43:07.715971: step: 80/530, loss: 2.012253025895916e-05
2023-01-21 12:43:08.835720: step: 84/530, loss: 0.00014396906772162765
2023-01-21 12:43:09.926689: step: 88/530, loss: 0.004881524946540594
2023-01-21 12:43:11.042081: step: 92/530, loss: 0.0005595684051513672
2023-01-21 12:43:12.168693: step: 96/530, loss: 0.018429376184940338
2023-01-21 12:43:13.315643: step: 100/530, loss: 4.920959327137098e-05
2023-01-21 12:43:14.466732: step: 104/530, loss: 0.0004795074637513608
2023-01-21 12:43:15.602596: step: 108/530, loss: 7.514953904319555e-05
2023-01-21 12:43:16.692290: step: 112/530, loss: 3.0994415283203125e-06
2023-01-21 12:43:17.831999: step: 116/530, loss: 0.14638501405715942
2023-01-21 12:43:18.935143: step: 120/530, loss: 0.00093841552734375
2023-01-21 12:43:20.034878: step: 124/530, loss: 3.852844383800402e-05
2023-01-21 12:43:21.178506: step: 128/530, loss: 0.019143294543027878
2023-01-21 12:43:22.332534: step: 132/530, loss: 0.0029429434798657894
2023-01-21 12:43:23.436615: step: 136/530, loss: 0.15927410125732422
2023-01-21 12:43:24.548972: step: 140/530, loss: 0.0022758482955396175
2023-01-21 12:43:25.699578: step: 144/530, loss: 0.004237556830048561
2023-01-21 12:43:26.810964: step: 148/530, loss: 0.025659942999482155
2023-01-21 12:43:27.886669: step: 152/530, loss: 0.00012283325486350805
2023-01-21 12:43:28.996963: step: 156/530, loss: 0.03389463573694229
2023-01-21 12:43:30.109111: step: 160/530, loss: 0.051458172500133514
2023-01-21 12:43:31.261219: step: 164/530, loss: 0.03884730115532875
2023-01-21 12:43:32.360270: step: 168/530, loss: 0.022504042834043503
2023-01-21 12:43:33.477723: step: 172/530, loss: 0.002415561815723777
2023-01-21 12:43:34.600643: step: 176/530, loss: 0.0030837059020996094
2023-01-21 12:43:35.728623: step: 180/530, loss: 0.0007230758783407509
2023-01-21 12:43:36.838898: step: 184/530, loss: 0.0006591796991415322
2023-01-21 12:43:37.981923: step: 188/530, loss: 9.269714064430445e-05
2023-01-21 12:43:39.081279: step: 192/530, loss: 0.0004520416259765625
2023-01-21 12:43:40.204754: step: 196/530, loss: 0.07262267917394638
2023-01-21 12:43:41.314859: step: 200/530, loss: 0.025091933086514473
2023-01-21 12:43:42.440702: step: 204/530, loss: 0.0014873980544507504
2023-01-21 12:43:43.553590: step: 208/530, loss: 5.0878523325081915e-05
2023-01-21 12:43:44.668327: step: 212/530, loss: 1.3351441339182202e-06
2023-01-21 12:43:45.775543: step: 216/530, loss: 1.049041748046875e-05
2023-01-21 12:43:46.879501: step: 220/530, loss: 0.007101630792021751
2023-01-21 12:43:48.002670: step: 224/530, loss: 0.0008539200061932206
2023-01-21 12:43:49.097474: step: 228/530, loss: 6.399154517566785e-05
2023-01-21 12:43:50.201601: step: 232/530, loss: 0.01993255689740181
2023-01-21 12:43:51.336472: step: 236/530, loss: 0.03745536878705025
2023-01-21 12:43:52.466666: step: 240/530, loss: 0.0044799805618822575
2023-01-21 12:43:53.594404: step: 244/530, loss: 0.008800889365375042
2023-01-21 12:43:54.726538: step: 248/530, loss: 0.0002609252987895161
2023-01-21 12:43:55.851487: step: 252/530, loss: 2.3651125957258046e-05
2023-01-21 12:43:56.965886: step: 256/530, loss: 0.029016779735684395
2023-01-21 12:43:58.122158: step: 260/530, loss: 0.004665565211325884
2023-01-21 12:43:59.239061: step: 264/530, loss: 0.01407470740377903
2023-01-21 12:44:00.345240: step: 268/530, loss: 0.003800773760303855
2023-01-21 12:44:01.471735: step: 272/530, loss: 0.0005889892345294356
2023-01-21 12:44:02.599029: step: 276/530, loss: 0.0014353275764733553
2023-01-21 12:44:03.748627: step: 280/530, loss: 0.0002361297665629536
2023-01-21 12:44:04.867168: step: 284/530, loss: 0.028256798163056374
2023-01-21 12:44:05.988395: step: 288/530, loss: 0.005011558532714844
2023-01-21 12:44:07.086609: step: 292/530, loss: 0.0005118370172567666
2023-01-21 12:44:08.183999: step: 296/530, loss: 0.01968669891357422
2023-01-21 12:44:09.311549: step: 300/530, loss: 0.0001858234463725239
2023-01-21 12:44:10.426566: step: 304/530, loss: 3.356933666509576e-05
2023-01-21 12:44:11.557593: step: 308/530, loss: 0.0003142356872558594
2023-01-21 12:44:12.677681: step: 312/530, loss: 0.0001924514799611643
2023-01-21 12:44:13.827404: step: 316/530, loss: 0.03401012346148491
2023-01-21 12:44:14.934102: step: 320/530, loss: 0.015611362643539906
2023-01-21 12:44:16.101810: step: 324/530, loss: 0.00045566557673737407
2023-01-21 12:44:17.219887: step: 328/530, loss: 0.008899688720703125
2023-01-21 12:44:18.345368: step: 332/530, loss: 0.027733994647860527
2023-01-21 12:44:19.495463: step: 336/530, loss: 0.0008192062377929688
2023-01-21 12:44:20.606988: step: 340/530, loss: 0.0007672309875488281
2023-01-21 12:44:21.737613: step: 344/530, loss: 0.0020941735710948706
2023-01-21 12:44:22.868198: step: 348/530, loss: 0.00027942657470703125
2023-01-21 12:44:23.980511: step: 352/530, loss: 0.0003796577511820942
2023-01-21 12:44:25.118034: step: 356/530, loss: 3.9672853745287284e-05
2023-01-21 12:44:26.220677: step: 360/530, loss: 0.015471458435058594
2023-01-21 12:44:27.330005: step: 364/530, loss: 0.0010601043468341231
2023-01-21 12:44:28.463659: step: 368/530, loss: 1.0871887752728071e-05
2023-01-21 12:44:29.583483: step: 372/530, loss: 0.00013203620619606227
2023-01-21 12:44:30.699992: step: 376/530, loss: 0.008501529693603516
2023-01-21 12:44:31.831994: step: 380/530, loss: 0.09849023818969727
2023-01-21 12:44:32.955631: step: 384/530, loss: 0.002324771834537387
2023-01-21 12:44:34.086450: step: 388/530, loss: 0.0010253905784338713
2023-01-21 12:44:35.209704: step: 392/530, loss: 0.0011699676979333162
2023-01-21 12:44:36.328201: step: 396/530, loss: 0.04737091436982155
2023-01-21 12:44:37.446979: step: 400/530, loss: 0.04481881484389305
2023-01-21 12:44:38.582127: step: 404/530, loss: 0.0011053085327148438
2023-01-21 12:44:39.721770: step: 408/530, loss: 0.00013742447481490672
2023-01-21 12:44:40.821638: step: 412/530, loss: 0.004331398289650679
2023-01-21 12:44:41.944936: step: 416/530, loss: 0.0032176971435546875
2023-01-21 12:44:43.078822: step: 420/530, loss: 0.06962300091981888
2023-01-21 12:44:44.207591: step: 424/530, loss: 0.007407474331557751
2023-01-21 12:44:45.354396: step: 428/530, loss: 0.01403112430125475
2023-01-21 12:44:46.496684: step: 432/530, loss: 0.00010128022404387593
2023-01-21 12:44:47.619214: step: 436/530, loss: 0.001130390097387135
2023-01-21 12:44:48.721873: step: 440/530, loss: 0.0390382781624794
2023-01-21 12:44:49.816384: step: 444/530, loss: 0.0003303527773823589
2023-01-21 12:44:50.951982: step: 448/530, loss: 0.0044831279665231705
2023-01-21 12:44:52.067019: step: 452/530, loss: 0.04946641996502876
2023-01-21 12:44:53.190609: step: 456/530, loss: 0.0009009361965581775
2023-01-21 12:44:54.335989: step: 460/530, loss: 0.0012356758816167712
2023-01-21 12:44:55.453865: step: 464/530, loss: 1.3351440202313825e-06
2023-01-21 12:44:56.582758: step: 468/530, loss: 3.9991726875305176
2023-01-21 12:44:57.697332: step: 472/530, loss: 0.00012855530076194555
2023-01-21 12:44:58.798390: step: 476/530, loss: 0.0003608703555073589
2023-01-21 12:44:59.927947: step: 480/530, loss: 0.004592323210090399
2023-01-21 12:45:01.022521: step: 484/530, loss: 0.002927398541942239
2023-01-21 12:45:02.205674: step: 488/530, loss: 0.0010039329063147306
2023-01-21 12:45:03.315689: step: 492/530, loss: 0.00904550589621067
2023-01-21 12:45:04.441269: step: 496/530, loss: 0.03919067233800888
2023-01-21 12:45:05.552930: step: 500/530, loss: 9.212493750965223e-05
2023-01-21 12:45:06.684902: step: 504/530, loss: 0.006631660740822554
2023-01-21 12:45:07.821013: step: 508/530, loss: 0.0016904830699786544
2023-01-21 12:45:08.961795: step: 512/530, loss: 0.00022029876708984375
2023-01-21 12:45:10.072237: step: 516/530, loss: 0.00036764147807843983
2023-01-21 12:45:11.219684: step: 520/530, loss: 0.0003713608020916581
2023-01-21 12:45:12.355170: step: 524/530, loss: 0.026316454634070396
2023-01-21 12:45:13.455382: step: 528/530, loss: 0.0030215263832360506
2023-01-21 12:45:14.550337: step: 532/530, loss: 1.0204315913142636e-05
2023-01-21 12:45:15.663352: step: 536/530, loss: 0.000194549560546875
2023-01-21 12:45:16.777099: step: 540/530, loss: 0.00462842034175992
2023-01-21 12:45:17.878193: step: 544/530, loss: 0.08375683426856995
2023-01-21 12:45:18.999649: step: 548/530, loss: 4.0531158447265625e-05
2023-01-21 12:45:20.153655: step: 552/530, loss: 0.03683844953775406
2023-01-21 12:45:21.277593: step: 556/530, loss: 0.0009405136224813759
2023-01-21 12:45:22.383756: step: 560/530, loss: 0.013876914978027344
2023-01-21 12:45:23.520224: step: 564/530, loss: 0.011519242078065872
2023-01-21 12:45:24.664976: step: 568/530, loss: 0.003719902131706476
2023-01-21 12:45:25.785248: step: 572/530, loss: 0.0003807067987509072
2023-01-21 12:45:26.924975: step: 576/530, loss: 0.0076913838274776936
2023-01-21 12:45:28.040573: step: 580/530, loss: 0.008653640747070312
2023-01-21 12:45:29.169268: step: 584/530, loss: 4.405975414556451e-05
2023-01-21 12:45:30.275339: step: 588/530, loss: 0.007244396023452282
2023-01-21 12:45:31.397013: step: 592/530, loss: 0.00017280579777434468
2023-01-21 12:45:32.574890: step: 596/530, loss: 0.010655499063432217
2023-01-21 12:45:33.705579: step: 600/530, loss: 0.0015697956550866365
2023-01-21 12:45:34.826248: step: 604/530, loss: 0.0016318322159349918
2023-01-21 12:45:35.953382: step: 608/530, loss: 0.0008715629810467362
2023-01-21 12:45:37.099513: step: 612/530, loss: 0.06163635104894638
2023-01-21 12:45:38.239775: step: 616/530, loss: 0.01646709442138672
2023-01-21 12:45:39.361864: step: 620/530, loss: 1.71661376953125e-05
2023-01-21 12:45:40.472016: step: 624/530, loss: 7.43865984986769e-06
2023-01-21 12:45:41.596929: step: 628/530, loss: 0.02240753173828125
2023-01-21 12:45:42.718018: step: 632/530, loss: 0.005022811703383923
2023-01-21 12:45:43.821720: step: 636/530, loss: 0.0019479751354083419
2023-01-21 12:45:44.945105: step: 640/530, loss: 0.0008593559614382684
2023-01-21 12:45:46.063500: step: 644/530, loss: 0.026267623528838158
2023-01-21 12:45:47.163807: step: 648/530, loss: 0.0009403228759765625
2023-01-21 12:45:48.258318: step: 652/530, loss: 0.018576670438051224
2023-01-21 12:45:49.388855: step: 656/530, loss: 0.02012653462588787
2023-01-21 12:45:50.523203: step: 660/530, loss: 0.007377624977380037
2023-01-21 12:45:51.630196: step: 664/530, loss: 0.00955963134765625
2023-01-21 12:45:52.761608: step: 668/530, loss: 0.0042743682861328125
2023-01-21 12:45:53.881580: step: 672/530, loss: 0.0004724502796307206
2023-01-21 12:45:54.988552: step: 676/530, loss: 0.0006839752313680947
2023-01-21 12:45:56.110594: step: 680/530, loss: 0.19893132150173187
2023-01-21 12:45:57.240029: step: 684/530, loss: 0.041143324226140976
2023-01-21 12:45:58.383269: step: 688/530, loss: 0.0006212234729900956
2023-01-21 12:45:59.503167: step: 692/530, loss: 0.010551405139267445
2023-01-21 12:46:00.624995: step: 696/530, loss: 3.833770824712701e-05
2023-01-21 12:46:01.739868: step: 700/530, loss: 0.00034747127210721374
2023-01-21 12:46:02.849926: step: 704/530, loss: 0.029045678675174713
2023-01-21 12:46:03.985394: step: 708/530, loss: 3.986358569818549e-05
2023-01-21 12:46:05.071059: step: 712/530, loss: 6.380081322276965e-05
2023-01-21 12:46:06.189749: step: 716/530, loss: 0.021427344530820847
2023-01-21 12:46:07.323899: step: 720/530, loss: 7.82012921263231e-06
2023-01-21 12:46:08.475864: step: 724/530, loss: 0.001431369804777205
2023-01-21 12:46:09.602337: step: 728/530, loss: 0.01021423377096653
2023-01-21 12:46:10.743396: step: 732/530, loss: 0.0003966331423725933
2023-01-21 12:46:11.865322: step: 736/530, loss: 0.0002779007190838456
2023-01-21 12:46:12.999613: step: 740/530, loss: 0.00010709762864280492
2023-01-21 12:46:14.120004: step: 744/530, loss: 0.005646133329719305
2023-01-21 12:46:15.259552: step: 748/530, loss: 0.03898201137781143
2023-01-21 12:46:16.375392: step: 752/530, loss: 0.0031970501877367496
2023-01-21 12:46:17.485443: step: 756/530, loss: 1.33514404296875e-05
2023-01-21 12:46:18.627659: step: 760/530, loss: 0.00042138100252486765
2023-01-21 12:46:19.739807: step: 764/530, loss: 8.0108642578125e-05
2023-01-21 12:46:20.874003: step: 768/530, loss: 1.277923547604587e-05
2023-01-21 12:46:22.000780: step: 772/530, loss: 0.0003429412900004536
2023-01-21 12:46:23.108800: step: 776/530, loss: 0.00037469866219908
2023-01-21 12:46:24.223475: step: 780/530, loss: 0.18206195533275604
2023-01-21 12:46:25.386166: step: 784/530, loss: 0.00570945767685771
2023-01-21 12:46:26.548860: step: 788/530, loss: 0.041329190135002136
2023-01-21 12:46:27.649470: step: 792/530, loss: 0.00223884591832757
2023-01-21 12:46:28.770710: step: 796/530, loss: 0.00364856724627316
2023-01-21 12:46:29.882451: step: 800/530, loss: 0.00012598038301803172
2023-01-21 12:46:30.999675: step: 804/530, loss: 0.00011348725092830136
2023-01-21 12:46:32.156795: step: 808/530, loss: 0.049199704080820084
2023-01-21 12:46:33.282368: step: 812/530, loss: 0.0013780593872070312
2023-01-21 12:46:34.414515: step: 816/530, loss: 0.042411185801029205
2023-01-21 12:46:35.543254: step: 820/530, loss: 0.00016288757615257055
2023-01-21 12:46:36.690321: step: 824/530, loss: 0.0019218922825530171
2023-01-21 12:46:37.787904: step: 828/530, loss: 2.250671423098538e-05
2023-01-21 12:46:38.903548: step: 832/530, loss: 0.012330221943557262
2023-01-21 12:46:40.023490: step: 836/530, loss: -8.296966370835435e-06
2023-01-21 12:46:41.127489: step: 840/530, loss: 0.012867164798080921
2023-01-21 12:46:42.230712: step: 844/530, loss: 0.004399108700454235
2023-01-21 12:46:43.358498: step: 848/530, loss: 0.0006018638960085809
2023-01-21 12:46:44.493080: step: 852/530, loss: 0.0002388954017078504
2023-01-21 12:46:45.620338: step: 856/530, loss: 0.0008094788063317537
2023-01-21 12:46:46.787273: step: 860/530, loss: 0.0022572875022888184
2023-01-21 12:46:47.933053: step: 864/530, loss: 0.00013055800809524953
2023-01-21 12:46:49.070017: step: 868/530, loss: 2.4318698706338182e-05
2023-01-21 12:46:50.200274: step: 872/530, loss: 0.005517005920410156
2023-01-21 12:46:51.282916: step: 876/530, loss: 0.00440063513815403
2023-01-21 12:46:52.404424: step: 880/530, loss: 0.00011453629122115672
2023-01-21 12:46:53.502978: step: 884/530, loss: 0.006240462884306908
2023-01-21 12:46:54.620245: step: 888/530, loss: 0.018604470416903496
2023-01-21 12:46:55.755701: step: 892/530, loss: 0.0014380932552739978
2023-01-21 12:46:56.865590: step: 896/530, loss: 0.11781015247106552
2023-01-21 12:46:58.001295: step: 900/530, loss: 6.83784528519027e-05
2023-01-21 12:46:59.117660: step: 904/530, loss: 0.018236063420772552
2023-01-21 12:47:00.221701: step: 908/530, loss: 0.0380365364253521
2023-01-21 12:47:01.334719: step: 912/530, loss: 0.00021753311739303172
2023-01-21 12:47:02.481580: step: 916/530, loss: 8.39233416627394e-06
2023-01-21 12:47:03.606965: step: 920/530, loss: 0.00018014907254837453
2023-01-21 12:47:04.720546: step: 924/530, loss: 8.630752745375503e-06
2023-01-21 12:47:05.860777: step: 928/530, loss: 0.0005167961353436112
2023-01-21 12:47:06.968523: step: 932/530, loss: 0.02090618759393692
2023-01-21 12:47:08.130425: step: 936/530, loss: 0.0028133392333984375
2023-01-21 12:47:09.271846: step: 940/530, loss: 0.004408359527587891
2023-01-21 12:47:10.386284: step: 944/530, loss: -3.910064606316155e-06
2023-01-21 12:47:11.498946: step: 948/530, loss: 0.0024011610075831413
2023-01-21 12:47:12.658418: step: 952/530, loss: 0.020877553150057793
2023-01-21 12:47:13.796359: step: 956/530, loss: 0.01916971243917942
2023-01-21 12:47:14.942889: step: 960/530, loss: 0.026388168334960938
2023-01-21 12:47:16.057804: step: 964/530, loss: 6.418228440452367e-05
2023-01-21 12:47:17.172949: step: 968/530, loss: 3.681182715808973e-05
2023-01-21 12:47:18.306929: step: 972/530, loss: 0.00012826919555664062
2023-01-21 12:47:19.430342: step: 976/530, loss: 0.0026149749755859375
2023-01-21 12:47:20.610986: step: 980/530, loss: 0.08449984341859818
2023-01-21 12:47:21.723662: step: 984/530, loss: 1.316070574830519e-05
2023-01-21 12:47:22.852990: step: 988/530, loss: 4.7063826059456915e-05
2023-01-21 12:47:23.991173: step: 992/530, loss: 0.008516693487763405
2023-01-21 12:47:25.101273: step: 996/530, loss: 0.1637924313545227
2023-01-21 12:47:26.225857: step: 1000/530, loss: 0.005981111433357
2023-01-21 12:47:27.367808: step: 1004/530, loss: 0.019586944952607155
2023-01-21 12:47:28.505525: step: 1008/530, loss: 0.005295563023537397
2023-01-21 12:47:29.638877: step: 1012/530, loss: 5.53131121705519e-06
2023-01-21 12:47:30.757395: step: 1016/530, loss: 2.9182432626839727e-05
2023-01-21 12:47:31.885455: step: 1020/530, loss: 0.002621269319206476
2023-01-21 12:47:33.020674: step: 1024/530, loss: 0.017374420538544655
2023-01-21 12:47:34.124609: step: 1028/530, loss: 1.754760705807712e-05
2023-01-21 12:47:35.244152: step: 1032/530, loss: 0.015008448623120785
2023-01-21 12:47:36.362014: step: 1036/530, loss: 0.07672309875488281
2023-01-21 12:47:37.501357: step: 1040/530, loss: 5.226135181146674e-05
2023-01-21 12:47:38.627996: step: 1044/530, loss: 0.01604476012289524
2023-01-21 12:47:39.775241: step: 1048/530, loss: 0.000881195068359375
2023-01-21 12:47:40.943192: step: 1052/530, loss: 0.02239532396197319
2023-01-21 12:47:42.047558: step: 1056/530, loss: 1.735687328618951e-05
2023-01-21 12:47:43.179761: step: 1060/530, loss: 0.004456138703972101
2023-01-21 12:47:44.286609: step: 1064/530, loss: 0.017177581787109375
2023-01-21 12:47:45.398434: step: 1068/530, loss: 0.02587909810245037
2023-01-21 12:47:46.509078: step: 1072/530, loss: 0.016202544793486595
2023-01-21 12:47:47.639053: step: 1076/530, loss: 0.0004410744004417211
2023-01-21 12:47:48.774048: step: 1080/530, loss: 0.0005770683055743575
2023-01-21 12:47:49.876957: step: 1084/530, loss: 0.0012900352012366056
2023-01-21 12:47:50.980979: step: 1088/530, loss: 0.03190803900361061
2023-01-21 12:47:52.117616: step: 1092/530, loss: 0.3949032723903656
2023-01-21 12:47:53.250262: step: 1096/530, loss: 8.96453857421875e-05
2023-01-21 12:47:54.378105: step: 1100/530, loss: 0.00016717909602448344
2023-01-21 12:47:55.534310: step: 1104/530, loss: 0.02153797075152397
2023-01-21 12:47:56.639721: step: 1108/530, loss: 0.0014883042313158512
2023-01-21 12:47:57.774913: step: 1112/530, loss: 0.16788645088672638
2023-01-21 12:47:58.908617: step: 1116/530, loss: 0.034400273114442825
2023-01-21 12:48:00.021543: step: 1120/530, loss: 0.016187667846679688
2023-01-21 12:48:01.144855: step: 1124/530, loss: 4.215240551275201e-05
2023-01-21 12:48:02.317436: step: 1128/530, loss: 0.0006538391462527215
2023-01-21 12:48:03.464597: step: 1132/530, loss: 0.035448551177978516
2023-01-21 12:48:04.566491: step: 1136/530, loss: 3.910064606316155e-06
2023-01-21 12:48:05.688166: step: 1140/530, loss: 4.00543194700731e-06
2023-01-21 12:48:06.815920: step: 1144/530, loss: 0.002973461290821433
2023-01-21 12:48:07.935253: step: 1148/530, loss: 0.0033791542518883944
2023-01-21 12:48:09.076381: step: 1152/530, loss: 0.0006357193342410028
2023-01-21 12:48:10.187522: step: 1156/530, loss: 0.00778121966868639
2023-01-21 12:48:11.305456: step: 1160/530, loss: 0.0856841579079628
2023-01-21 12:48:12.451604: step: 1164/530, loss: 4.472732689464465e-05
2023-01-21 12:48:13.578170: step: 1168/530, loss: 0.0012611389392986894
2023-01-21 12:48:14.705015: step: 1172/530, loss: 0.0007200241088867188
2023-01-21 12:48:15.809391: step: 1176/530, loss: 2.7656556994770654e-05
2023-01-21 12:48:16.953772: step: 1180/530, loss: 0.0015327453147619963
2023-01-21 12:48:18.118512: step: 1184/530, loss: 0.0008971214410848916
2023-01-21 12:48:19.253505: step: 1188/530, loss: 0.037331581115722656
2023-01-21 12:48:20.381839: step: 1192/530, loss: 5.9890749980695546e-05
2023-01-21 12:48:21.566910: step: 1196/530, loss: 0.007906246930360794
2023-01-21 12:48:22.684439: step: 1200/530, loss: 0.017188740894198418
2023-01-21 12:48:23.786938: step: 1204/530, loss: 0.02514934539794922
2023-01-21 12:48:24.934607: step: 1208/530, loss: 0.018845845013856888
2023-01-21 12:48:26.050214: step: 1212/530, loss: 0.0024932860396802425
2023-01-21 12:48:27.187590: step: 1216/530, loss: 0.05547017976641655
2023-01-21 12:48:28.335619: step: 1220/530, loss: 0.008429241366684437
2023-01-21 12:48:29.487595: step: 1224/530, loss: 0.003713417099788785
2023-01-21 12:48:30.627982: step: 1228/530, loss: 0.021436691284179688
2023-01-21 12:48:31.739125: step: 1232/530, loss: 0.0007604599231854081
2023-01-21 12:48:32.866030: step: 1236/530, loss: 7.82012939453125e-05
2023-01-21 12:48:33.993211: step: 1240/530, loss: 0.0011594772804528475
2023-01-21 12:48:35.115283: step: 1244/530, loss: 8.401871309615672e-05
2023-01-21 12:48:36.249367: step: 1248/530, loss: 6.771087555534905e-06
2023-01-21 12:48:37.351225: step: 1252/530, loss: 0.0007290840148925781
2023-01-21 12:48:38.487303: step: 1256/530, loss: 0.0013675689697265625
2023-01-21 12:48:39.630310: step: 1260/530, loss: 0.013032913208007812
2023-01-21 12:48:40.734027: step: 1264/530, loss: 1.52587890625e-05
2023-01-21 12:48:41.876994: step: 1268/530, loss: 0.032070159912109375
2023-01-21 12:48:43.002914: step: 1272/530, loss: 6.637573824264109e-05
2023-01-21 12:48:44.103101: step: 1276/530, loss: 0.0009118079906329513
2023-01-21 12:48:45.181810: step: 1280/530, loss: 0.023752881214022636
2023-01-21 12:48:46.307182: step: 1284/530, loss: 0.010328864678740501
2023-01-21 12:48:47.411665: step: 1288/530, loss: 0.0006488800281658769
2023-01-21 12:48:48.516259: step: 1292/530, loss: 0.7392614483833313
2023-01-21 12:48:49.622855: step: 1296/530, loss: 0.013381386175751686
2023-01-21 12:48:50.770562: step: 1300/530, loss: 0.014977074228227139
2023-01-21 12:48:51.887477: step: 1304/530, loss: 0.06726054847240448
2023-01-21 12:48:53.021453: step: 1308/530, loss: 0.001568269683048129
2023-01-21 12:48:54.200383: step: 1312/530, loss: 0.0031616210471838713
2023-01-21 12:48:55.310973: step: 1316/530, loss: 0.0012739181984215975
2023-01-21 12:48:56.419349: step: 1320/530, loss: 0.30644530057907104
2023-01-21 12:48:57.549749: step: 1324/530, loss: 0.011318778619170189
2023-01-21 12:48:58.663928: step: 1328/530, loss: 0.004583549685776234
2023-01-21 12:48:59.794041: step: 1332/530, loss: 0.07709579914808273
2023-01-21 12:49:00.934489: step: 1336/530, loss: 1.049041748046875e-05
2023-01-21 12:49:02.096277: step: 1340/530, loss: 0.0005133628728799522
2023-01-21 12:49:03.244463: step: 1344/530, loss: 0.055951498448848724
2023-01-21 12:49:04.366577: step: 1348/530, loss: 0.002674675080925226
2023-01-21 12:49:05.499151: step: 1352/530, loss: 0.005853176116943359
2023-01-21 12:49:06.619336: step: 1356/530, loss: 8.678436279296875e-05
2023-01-21 12:49:07.732281: step: 1360/530, loss: 0.00017986298189498484
2023-01-21 12:49:08.892467: step: 1364/530, loss: 0.06288294494152069
2023-01-21 12:49:10.016587: step: 1368/530, loss: 0.00013256072998046875
2023-01-21 12:49:11.143950: step: 1372/530, loss: 0.007794380187988281
2023-01-21 12:49:12.252635: step: 1376/530, loss: 9.536744983051904e-06
2023-01-21 12:49:13.367630: step: 1380/530, loss: 0.0009719848749227822
2023-01-21 12:49:14.459729: step: 1384/530, loss: 4.091262962901965e-05
2023-01-21 12:49:15.558934: step: 1388/530, loss: 0.0002930641348939389
2023-01-21 12:49:16.701070: step: 1392/530, loss: 0.00034999847412109375
2023-01-21 12:49:17.829910: step: 1396/530, loss: 0.0010705947643145919
2023-01-21 12:49:18.970247: step: 1400/530, loss: 7.43865984986769e-06
2023-01-21 12:49:20.087799: step: 1404/530, loss: 0.08713741600513458
2023-01-21 12:49:21.189265: step: 1408/530, loss: 0.0010047912364825606
2023-01-21 12:49:22.322983: step: 1412/530, loss: 0.0003778458049055189
2023-01-21 12:49:23.422335: step: 1416/530, loss: 0.00030231475830078125
2023-01-21 12:49:24.556827: step: 1420/530, loss: 0.008088684640824795
2023-01-21 12:49:25.697739: step: 1424/530, loss: 0.0066849710419774055
2023-01-21 12:49:26.823545: step: 1428/530, loss: 0.06372775882482529
2023-01-21 12:49:27.928544: step: 1432/530, loss: 5.683898780262098e-05
2023-01-21 12:49:29.063810: step: 1436/530, loss: 0.01704712025821209
2023-01-21 12:49:30.201093: step: 1440/530, loss: 3.385544005141128e-06
2023-01-21 12:49:31.337658: step: 1444/530, loss: 1.0776519957289565e-05
2023-01-21 12:49:32.469275: step: 1448/530, loss: 0.02682037279009819
2023-01-21 12:49:33.576279: step: 1452/530, loss: 0.013961411081254482
2023-01-21 12:49:34.712028: step: 1456/530, loss: 0.013233805075287819
2023-01-21 12:49:35.803967: step: 1460/530, loss: 0.00814275722950697
2023-01-21 12:49:36.929600: step: 1464/530, loss: 0.03822669759392738
2023-01-21 12:49:38.032039: step: 1468/530, loss: 0.00199127197265625
2023-01-21 12:49:39.156855: step: 1472/530, loss: 0.0005277633899822831
2023-01-21 12:49:40.291633: step: 1476/530, loss: 0.0026166916359215975
2023-01-21 12:49:41.410721: step: 1480/530, loss: 0.003086614655330777
2023-01-21 12:49:42.556621: step: 1484/530, loss: 5.5122378398664296e-05
2023-01-21 12:49:43.661639: step: 1488/530, loss: 0.005574607755988836
2023-01-21 12:49:44.779994: step: 1492/530, loss: 9.913444955600426e-05
2023-01-21 12:49:45.907042: step: 1496/530, loss: 0.00253887171857059
2023-01-21 12:49:47.027802: step: 1500/530, loss: 0.05445671081542969
2023-01-21 12:49:48.132440: step: 1504/530, loss: 0.0018342018593102694
2023-01-21 12:49:49.267330: step: 1508/530, loss: 0.0010273456573486328
2023-01-21 12:49:50.388232: step: 1512/530, loss: 0.0006852149963378906
2023-01-21 12:49:51.494673: step: 1516/530, loss: 0.0005591392982751131
2023-01-21 12:49:52.627471: step: 1520/530, loss: 0.0022735595703125
2023-01-21 12:49:53.785964: step: 1524/530, loss: 0.11696648597717285
2023-01-21 12:49:54.908050: step: 1528/530, loss: 0.0007255554082803428
2023-01-21 12:49:56.008931: step: 1532/530, loss: 6.761551048839465e-05
2023-01-21 12:49:57.105624: step: 1536/530, loss: 0.0010030746925622225
2023-01-21 12:49:58.213619: step: 1540/530, loss: 0.0005038738599978387
2023-01-21 12:49:59.338583: step: 1544/530, loss: 0.008318042382597923
2023-01-21 12:50:00.473806: step: 1548/530, loss: 0.006482839584350586
2023-01-21 12:50:01.627127: step: 1552/530, loss: 0.014519883319735527
2023-01-21 12:50:02.749302: step: 1556/530, loss: 0.006329250056296587
2023-01-21 12:50:03.858070: step: 1560/530, loss: 0.07595839351415634
2023-01-21 12:50:04.970190: step: 1564/530, loss: 0.003700447268784046
2023-01-21 12:50:06.135807: step: 1568/530, loss: 1.735687328618951e-05
2023-01-21 12:50:07.274536: step: 1572/530, loss: 0.003451442811638117
2023-01-21 12:50:08.397896: step: 1576/530, loss: 0.00025281906710006297
2023-01-21 12:50:09.533760: step: 1580/530, loss: 0.00036411284236237407
2023-01-21 12:50:10.651823: step: 1584/530, loss: 0.00417705811560154
2023-01-21 12:50:11.786360: step: 1588/530, loss: 0.0002956390380859375
2023-01-21 12:50:12.899115: step: 1592/530, loss: 0.0021317005157470703
2023-01-21 12:50:14.012078: step: 1596/530, loss: 0.002164697740226984
2023-01-21 12:50:15.168683: step: 1600/530, loss: 0.0001234054652741179
2023-01-21 12:50:16.287467: step: 1604/530, loss: 0.0010136604541912675
2023-01-21 12:50:17.431059: step: 1608/530, loss: 0.008666420355439186
2023-01-21 12:50:18.576675: step: 1612/530, loss: 0.007724285125732422
2023-01-21 12:50:19.685249: step: 1616/530, loss: 0.006575965788215399
2023-01-21 12:50:20.804255: step: 1620/530, loss: 0.009416580200195312
2023-01-21 12:50:21.943643: step: 1624/530, loss: 0.010112762451171875
2023-01-21 12:50:23.077797: step: 1628/530, loss: 0.00578198442235589
2023-01-21 12:50:24.212243: step: 1632/530, loss: 0.0006286621210165322
2023-01-21 12:50:25.334425: step: 1636/530, loss: 0.0003871917724609375
2023-01-21 12:50:26.457710: step: 1640/530, loss: 0.002748107770457864
2023-01-21 12:50:27.575119: step: 1644/530, loss: 0.0026155472733080387
2023-01-21 12:50:28.728487: step: 1648/530, loss: 0.014090919867157936
2023-01-21 12:50:29.857577: step: 1652/530, loss: 0.00803146418184042
2023-01-21 12:50:31.008847: step: 1656/530, loss: 0.013839340768754482
2023-01-21 12:50:32.147404: step: 1660/530, loss: 0.007971763610839844
2023-01-21 12:50:33.272639: step: 1664/530, loss: 2.765655608527595e-06
2023-01-21 12:50:34.383538: step: 1668/530, loss: 0.0007596015930175781
2023-01-21 12:50:35.498144: step: 1672/530, loss: 0.0515836700797081
2023-01-21 12:50:36.635234: step: 1676/530, loss: 0.07104549556970596
2023-01-21 12:50:37.727881: step: 1680/530, loss: 8.363723463844508e-05
2023-01-21 12:50:38.847920: step: 1684/530, loss: 0.00046176911564543843
2023-01-21 12:50:39.985136: step: 1688/530, loss: 0.0006183624500408769
2023-01-21 12:50:41.148772: step: 1692/530, loss: 6.27517729299143e-05
2023-01-21 12:50:42.262697: step: 1696/530, loss: 0.008471870794892311
2023-01-21 12:50:43.384106: step: 1700/530, loss: 0.003345584962517023
2023-01-21 12:50:44.488420: step: 1704/530, loss: 5.543231964111328e-05
2023-01-21 12:50:45.621876: step: 1708/530, loss: 0.020847130566835403
2023-01-21 12:50:46.725220: step: 1712/530, loss: 0.005173683166503906
2023-01-21 12:50:47.823319: step: 1716/530, loss: 3.814697265625e-06
2023-01-21 12:50:48.966145: step: 1720/530, loss: 0.00046443939208984375
2023-01-21 12:50:50.087342: step: 1724/530, loss: 0.00019030571274925023
2023-01-21 12:50:51.190769: step: 1728/530, loss: 0.006464672274887562
2023-01-21 12:50:52.295995: step: 1732/530, loss: 0.023212766274809837
2023-01-21 12:50:53.434835: step: 1736/530, loss: 8.163452002918348e-05
2023-01-21 12:50:54.576513: step: 1740/530, loss: 0.000545501708984375
2023-01-21 12:50:55.709076: step: 1744/530, loss: 0.004963874816894531
2023-01-21 12:50:56.806543: step: 1748/530, loss: 0.030713463202118874
2023-01-21 12:50:57.921636: step: 1752/530, loss: 0.005924797151237726
2023-01-21 12:50:59.031050: step: 1756/530, loss: 0.019602395594120026
2023-01-21 12:51:00.164690: step: 1760/530, loss: 0.0004323005850892514
2023-01-21 12:51:01.303408: step: 1764/530, loss: 0.05884575843811035
2023-01-21 12:51:02.461186: step: 1768/530, loss: 0.0010650635231286287
2023-01-21 12:51:03.580518: step: 1772/530, loss: 0.01959228515625
2023-01-21 12:51:04.716305: step: 1776/530, loss: 0.00044307709322310984
2023-01-21 12:51:05.820965: step: 1780/530, loss: 0.012017727829515934
2023-01-21 12:51:06.966553: step: 1784/530, loss: 0.034757040441036224
2023-01-21 12:51:08.095716: step: 1788/530, loss: 0.06316499412059784
2023-01-21 12:51:09.232532: step: 1792/530, loss: 0.025241469964385033
2023-01-21 12:51:10.323621: step: 1796/530, loss: 5.970001075183973e-05
2023-01-21 12:51:11.464411: step: 1800/530, loss: 0.003490924835205078
2023-01-21 12:51:12.623732: step: 1804/530, loss: 0.02016611211001873
2023-01-21 12:51:13.753166: step: 1808/530, loss: 0.00818862859159708
2023-01-21 12:51:14.852080: step: 1812/530, loss: 0.0024250030983239412
2023-01-21 12:51:15.976502: step: 1816/530, loss: 0.019534826278686523
2023-01-21 12:51:17.084336: step: 1820/530, loss: 0.008831215091049671
2023-01-21 12:51:18.191113: step: 1824/530, loss: 3.4809112548828125e-05
2023-01-21 12:51:19.310921: step: 1828/530, loss: 0.012275982648134232
2023-01-21 12:51:20.429766: step: 1832/530, loss: 0.0011055945651605725
2023-01-21 12:51:21.576916: step: 1836/530, loss: 1.258850079466356e-05
2023-01-21 12:51:22.672967: step: 1840/530, loss: 0.013837814331054688
2023-01-21 12:51:23.777904: step: 1844/530, loss: 0.004779530223459005
2023-01-21 12:51:24.900978: step: 1848/530, loss: -4.386901309771929e-06
2023-01-21 12:51:26.007599: step: 1852/530, loss: 0.0004432678106240928
2023-01-21 12:51:27.116170: step: 1856/530, loss: 0.0038407803513109684
2023-01-21 12:51:28.234710: step: 1860/530, loss: 0.00043444635230116546
2023-01-21 12:51:29.357874: step: 1864/530, loss: 0.0013799667358398438
2023-01-21 12:51:30.501632: step: 1868/530, loss: 0.0006229400751180947
2023-01-21 12:51:31.642038: step: 1872/530, loss: 0.010889053344726562
2023-01-21 12:51:32.756078: step: 1876/530, loss: 0.0004259109846316278
2023-01-21 12:51:33.886821: step: 1880/530, loss: 1.5258790881489404e-05
2023-01-21 12:51:34.996529: step: 1884/530, loss: 0.0014681816101074219
2023-01-21 12:51:36.114197: step: 1888/530, loss: 0.00062732701189816
2023-01-21 12:51:37.234205: step: 1892/530, loss: 0.0005293846479617059
2023-01-21 12:51:38.359490: step: 1896/530, loss: 0.0007566451677121222
2023-01-21 12:51:39.467336: step: 1900/530, loss: 0.0004562377871479839
2023-01-21 12:51:40.608171: step: 1904/530, loss: 0.00024633409339003265
2023-01-21 12:51:41.720509: step: 1908/530, loss: 4.6443939936580136e-05
2023-01-21 12:51:42.873372: step: 1912/530, loss: -3.2424923119833693e-06
2023-01-21 12:51:43.993807: step: 1916/530, loss: 0.03647003322839737
2023-01-21 12:51:45.105585: step: 1920/530, loss: 3.471374657237902e-05
2023-01-21 12:51:46.217976: step: 1924/530, loss: 0.00035514833871275187
2023-01-21 12:51:47.327722: step: 1928/530, loss: 8.583069188716763e-07
2023-01-21 12:51:48.451141: step: 1932/530, loss: 2.527237120375503e-05
2023-01-21 12:51:49.589317: step: 1936/530, loss: 0.001122462679632008
2023-01-21 12:51:50.688680: step: 1940/530, loss: 0.00011582375009311363
2023-01-21 12:51:51.807801: step: 1944/530, loss: 0.0007120132795535028
2023-01-21 12:51:52.931446: step: 1948/530, loss: 0.0009958266746252775
2023-01-21 12:51:54.049627: step: 1952/530, loss: 0.00016202926053665578
2023-01-21 12:51:55.180035: step: 1956/530, loss: 2.47955322265625e-05
2023-01-21 12:51:56.283870: step: 1960/530, loss: 0.00019187926955055445
2023-01-21 12:51:57.400693: step: 1964/530, loss: 0.00022373200044967234
2023-01-21 12:51:58.546629: step: 1968/530, loss: 0.00015335084754042327
2023-01-21 12:51:59.662808: step: 1972/530, loss: 8.921623521018773e-05
2023-01-21 12:52:00.784745: step: 1976/530, loss: 0.022678280249238014
2023-01-21 12:52:01.913945: step: 1980/530, loss: 4.85897071484942e-05
2023-01-21 12:52:03.052449: step: 1984/530, loss: 0.00862274132668972
2023-01-21 12:52:04.160537: step: 1988/530, loss: 0.006485462188720703
2023-01-21 12:52:05.302464: step: 1992/530, loss: 0.00014333725266624242
2023-01-21 12:52:06.441947: step: 1996/530, loss: 8.850097947288305e-05
2023-01-21 12:52:07.527840: step: 2000/530, loss: 3.051757857974735e-06
2023-01-21 12:52:08.649977: step: 2004/530, loss: 0.00011463165719760582
2023-01-21 12:52:09.771389: step: 2008/530, loss: 3.528594970703125e-05
2023-01-21 12:52:10.887011: step: 2012/530, loss: 0.0014966964954510331
2023-01-21 12:52:12.039583: step: 2016/530, loss: 0.0903010368347168
2023-01-21 12:52:13.158201: step: 2020/530, loss: 4.4155120122013614e-05
2023-01-21 12:52:14.268639: step: 2024/530, loss: 1.850128137448337e-05
2023-01-21 12:52:15.409577: step: 2028/530, loss: 0.011052322573959827
2023-01-21 12:52:16.511502: step: 2032/530, loss: 0.026906967163085938
2023-01-21 12:52:17.631749: step: 2036/530, loss: 0.0009341239929199219
2023-01-21 12:52:18.743385: step: 2040/530, loss: 0.0003383636358194053
2023-01-21 12:52:19.861664: step: 2044/530, loss: 0.143123060464859
2023-01-21 12:52:20.999868: step: 2048/530, loss: 0.0005216598510742188
2023-01-21 12:52:22.098003: step: 2052/530, loss: 0.0008076668018475175
2023-01-21 12:52:23.198436: step: 2056/530, loss: 0.000354766845703125
2023-01-21 12:52:24.302188: step: 2060/530, loss: 0.016980456188321114
2023-01-21 12:52:25.439941: step: 2064/530, loss: 0.022052954882383347
2023-01-21 12:52:26.573150: step: 2068/530, loss: 0.00031948089599609375
2023-01-21 12:52:27.709399: step: 2072/530, loss: 9.632110595703125e-05
2023-01-21 12:52:28.829072: step: 2076/530, loss: 0.0010297775734215975
2023-01-21 12:52:29.948371: step: 2080/530, loss: 0.0024024962913244963
2023-01-21 12:52:31.087030: step: 2084/530, loss: 0.0001483917294535786
2023-01-21 12:52:32.232152: step: 2088/530, loss: 0.006118011195212603
2023-01-21 12:52:33.406763: step: 2092/530, loss: 0.07015743106603622
2023-01-21 12:52:34.531698: step: 2096/530, loss: 0.0002815246698446572
2023-01-21 12:52:35.638595: step: 2100/530, loss: 0.00015611648268532008
2023-01-21 12:52:36.784727: step: 2104/530, loss: 0.017203141003847122
2023-01-21 12:52:37.928420: step: 2108/530, loss: 0.02082691341638565
2023-01-21 12:52:39.062751: step: 2112/530, loss: 3.156661841785535e-05
2023-01-21 12:52:40.206012: step: 2116/530, loss: 0.0029564856085926294
2023-01-21 12:52:41.330788: step: 2120/530, loss: 0.034891799092292786
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.5951417004048583, 'r': 0.7829560585885486, 'f1': 0.6762507188039103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6360715924736118, 'r': 0.792, 'f1': 0.7055230338508527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5647058823529412, 'r': 0.8888888888888888, 'f1': 0.6906474820143885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.5849056603773585, 'r': 0.49206349206349204, 'f1': 0.5344827586206896}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.43478260869565216, 'r': 0.5555555555555556, 'f1': 0.4878048780487805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 12:53:21.726235: step: 4/530, loss: 5.760193016612902e-05
2023-01-21 12:53:22.877827: step: 8/530, loss: 6.294251306826482e-06
2023-01-21 12:53:23.992034: step: 12/530, loss: 0.015520286746323109
2023-01-21 12:53:25.086756: step: 16/530, loss: 7.629394644936838e-07
2023-01-21 12:53:26.183348: step: 20/530, loss: 0.000690460205078125
2023-01-21 12:53:27.319517: step: 24/530, loss: 0.04330749437212944
2023-01-21 12:53:28.436279: step: 28/530, loss: 0.01213607843965292
2023-01-21 12:53:29.554985: step: 32/530, loss: 0.0005928516620770097
2023-01-21 12:53:30.686099: step: 36/530, loss: 3.356933666509576e-05
2023-01-21 12:53:31.845775: step: 40/530, loss: 0.004153442569077015
2023-01-21 12:53:32.951413: step: 44/530, loss: 0.021117497235536575
2023-01-21 12:53:34.075032: step: 48/530, loss: 0.2995050549507141
2023-01-21 12:53:35.196026: step: 52/530, loss: 8.020401583053172e-05
2023-01-21 12:53:36.298480: step: 56/530, loss: 0.03614845499396324
2023-01-21 12:53:37.424048: step: 60/530, loss: 0.0038333891425281763
2023-01-21 12:53:38.533250: step: 64/530, loss: 0.2555854618549347
2023-01-21 12:53:39.638057: step: 68/530, loss: 1.163482647825731e-05
2023-01-21 12:53:40.760185: step: 72/530, loss: 0.0010929107666015625
2023-01-21 12:53:41.860656: step: 76/530, loss: 0.000598907470703125
2023-01-21 12:53:42.999503: step: 80/530, loss: 0.010788917541503906
2023-01-21 12:53:44.149651: step: 84/530, loss: 0.01687498204410076
2023-01-21 12:53:45.269697: step: 88/530, loss: 0.00013828277587890625
2023-01-21 12:53:46.396608: step: 92/530, loss: 2.441406286379788e-05
2023-01-21 12:53:47.544005: step: 96/530, loss: 0.0004898071056231856
2023-01-21 12:53:48.660460: step: 100/530, loss: 0.00017232894606422633
2023-01-21 12:53:49.823259: step: 104/530, loss: 0.029174232855439186
2023-01-21 12:53:50.940197: step: 108/530, loss: 6.19411512161605e-05
2023-01-21 12:53:52.068947: step: 112/530, loss: 0.0020587921608239412
2023-01-21 12:53:53.206713: step: 116/530, loss: 0.010316919535398483
2023-01-21 12:53:54.332110: step: 120/530, loss: 0.2576211988925934
2023-01-21 12:53:55.438510: step: 124/530, loss: 5.722046125811175e-07
2023-01-21 12:53:56.572153: step: 128/530, loss: 7.553101022494957e-05
2023-01-21 12:53:57.662140: step: 132/530, loss: 2.8610231765924254e-06
2023-01-21 12:53:58.785666: step: 136/530, loss: 0.004568958189338446
2023-01-21 12:53:59.846829: step: 140/530, loss: 2.3746491933707148e-05
2023-01-21 12:54:00.987231: step: 144/530, loss: 0.06956224888563156
2023-01-21 12:54:02.142780: step: 148/530, loss: 0.019528819248080254
2023-01-21 12:54:03.296793: step: 152/530, loss: 0.03265991061925888
2023-01-21 12:54:04.421410: step: 156/530, loss: 0.01950244978070259
2023-01-21 12:54:05.528551: step: 160/530, loss: 0.0055661676451563835
2023-01-21 12:54:06.634958: step: 164/530, loss: 0.01079788152128458
2023-01-21 12:54:07.792836: step: 168/530, loss: 0.050382040441036224
2023-01-21 12:54:08.914147: step: 172/530, loss: 0.08066711574792862
2023-01-21 12:54:10.036851: step: 176/530, loss: 0.0007628441089764237
2023-01-21 12:54:11.164845: step: 180/530, loss: 0.0002130508510163054
2023-01-21 12:54:12.287743: step: 184/530, loss: 0.0036909105256199837
2023-01-21 12:54:13.394855: step: 188/530, loss: 0.0018259049393236637
2023-01-21 12:54:14.500668: step: 192/530, loss: 0.010990524664521217
2023-01-21 12:54:15.656569: step: 196/530, loss: 0.047499850392341614
2023-01-21 12:54:16.775490: step: 200/530, loss: 0.0013965606922283769
2023-01-21 12:54:17.919617: step: 204/530, loss: 0.007748221978545189
2023-01-21 12:54:19.025683: step: 208/530, loss: 0.0006358146201819181
2023-01-21 12:54:20.155026: step: 212/530, loss: 0.0666746124625206
2023-01-21 12:54:21.254265: step: 216/530, loss: 0.0017342568608000875
2023-01-21 12:54:22.359287: step: 220/530, loss: 0.0008307457319460809
2023-01-21 12:54:23.467364: step: 224/530, loss: 0.005261421203613281
2023-01-21 12:54:24.582475: step: 228/530, loss: 8.583068620282575e-07
2023-01-21 12:54:25.711528: step: 232/530, loss: 0.03453836217522621
2023-01-21 12:54:26.862591: step: 236/530, loss: 0.0027935029938817024
2023-01-21 12:54:27.972315: step: 240/530, loss: 0.009085082449018955
2023-01-21 12:54:29.061279: step: 244/530, loss: 0.00012674331082962453
2023-01-21 12:54:30.183943: step: 248/530, loss: 0.0001184463471872732
2023-01-21 12:54:31.314380: step: 252/530, loss: 0.00295944232493639
2023-01-21 12:54:32.438361: step: 256/530, loss: 5.34057608092553e-06
2023-01-21 12:54:33.552916: step: 260/530, loss: 0.05891399830579758
2023-01-21 12:54:34.696161: step: 264/530, loss: 0.012195397168397903
2023-01-21 12:54:35.818798: step: 268/530, loss: 0.009903717786073685
2023-01-21 12:54:36.919466: step: 272/530, loss: 0.005273247137665749
2023-01-21 12:54:38.049457: step: 276/530, loss: 0.0003357887326274067
2023-01-21 12:54:39.168571: step: 280/530, loss: 3.8909915019758046e-05
2023-01-21 12:54:40.284972: step: 284/530, loss: 0.3618527352809906
2023-01-21 12:54:41.409831: step: 288/530, loss: 0.00022010803513694555
2023-01-21 12:54:42.519749: step: 292/530, loss: 0.0013450622791424394
2023-01-21 12:54:43.614520: step: 296/530, loss: 0.00010929107520496473
2023-01-21 12:54:44.763566: step: 300/530, loss: 0.0009700774680823088
2023-01-21 12:54:45.914573: step: 304/530, loss: 0.0038476947229355574
2023-01-21 12:54:47.035201: step: 308/530, loss: 0.0008344650268554688
2023-01-21 12:54:48.166147: step: 312/530, loss: 0.00017433166794944555
2023-01-21 12:54:49.301267: step: 316/530, loss: 0.04964103922247887
2023-01-21 12:54:50.445521: step: 320/530, loss: 2.498626781743951e-05
2023-01-21 12:54:51.559308: step: 324/530, loss: 0.03583373874425888
2023-01-21 12:54:52.714839: step: 328/530, loss: 0.0001028060942189768
2023-01-21 12:54:53.830813: step: 332/530, loss: 0.016407204791903496
2023-01-21 12:54:54.966550: step: 336/530, loss: 0.016111182048916817
2023-01-21 12:54:56.117959: step: 340/530, loss: 8.96453857421875e-05
2023-01-21 12:54:57.239895: step: 344/530, loss: 0.00047512055607512593
2023-01-21 12:54:58.337084: step: 348/530, loss: 0.015705490484833717
2023-01-21 12:54:59.449410: step: 352/530, loss: 0.5802481174468994
2023-01-21 12:55:00.567047: step: 356/530, loss: 0.000232696533203125
2023-01-21 12:55:01.695499: step: 360/530, loss: 7.524490501964465e-05
2023-01-21 12:55:02.831200: step: 364/530, loss: 0.011943817138671875
2023-01-21 12:55:03.954433: step: 368/530, loss: 0.031771469861269
2023-01-21 12:55:05.084783: step: 372/530, loss: 0.0012729167938232422
2023-01-21 12:55:06.193984: step: 376/530, loss: 9.5367431640625e-07
2023-01-21 12:55:07.310695: step: 380/530, loss: 0.000213623046875
2023-01-21 12:55:08.433608: step: 384/530, loss: 0.0007368088117800653
2023-01-21 12:55:09.568992: step: 388/530, loss: 0.06365757435560226
2023-01-21 12:55:10.746229: step: 392/530, loss: 0.010807800106704235
2023-01-21 12:55:11.890402: step: 396/530, loss: 0.013941668905317783
2023-01-21 12:55:13.004755: step: 400/530, loss: 0.0019784928299486637
2023-01-21 12:55:14.144754: step: 404/530, loss: 3.185272362316027e-05
2023-01-21 12:55:15.310682: step: 408/530, loss: 0.00016727446927689016
2023-01-21 12:55:16.456303: step: 412/530, loss: 0.0889003798365593
2023-01-21 12:55:17.612474: step: 416/530, loss: 0.0004798888985533267
2023-01-21 12:55:18.728398: step: 420/530, loss: 0.0003810882626567036
2023-01-21 12:55:19.867141: step: 424/530, loss: 0.020220661535859108
2023-01-21 12:55:20.998240: step: 428/530, loss: 6.29425048828125e-05
2023-01-21 12:55:22.132344: step: 432/530, loss: 7.324218313442543e-05
2023-01-21 12:55:23.226987: step: 436/530, loss: 0.00018224716768600047
2023-01-21 12:55:24.345890: step: 440/530, loss: 0.0031751631759107113
2023-01-21 12:55:25.479950: step: 444/530, loss: 0.0001867294340627268
2023-01-21 12:55:26.588782: step: 448/530, loss: 4.5585635234601796e-05
2023-01-21 12:55:27.777511: step: 452/530, loss: 0.00010566711716819555
2023-01-21 12:55:28.883063: step: 456/530, loss: 0.0001087188720703125
2023-01-21 12:55:29.970150: step: 460/530, loss: 4.816055479750503e-06
2023-01-21 12:55:31.140355: step: 464/530, loss: 0.05063781887292862
2023-01-21 12:55:32.254078: step: 468/530, loss: 0.07520905137062073
2023-01-21 12:55:33.374562: step: 472/530, loss: 0.008673572912812233
2023-01-21 12:55:34.496430: step: 476/530, loss: 0.0006789207109250128
2023-01-21 12:55:35.614753: step: 480/530, loss: -8.106235327431932e-07
2023-01-21 12:55:36.725202: step: 484/530, loss: 0.0011214256519451737
2023-01-21 12:55:37.835341: step: 488/530, loss: 0.004423904698342085
2023-01-21 12:55:38.947109: step: 492/530, loss: 0.0004400253528729081
2023-01-21 12:55:40.059890: step: 496/530, loss: 1.9073486328125e-06
2023-01-21 12:55:41.202435: step: 500/530, loss: 9.288787987316027e-05
2023-01-21 12:55:42.324034: step: 504/530, loss: 0.022943973541259766
2023-01-21 12:55:43.432848: step: 508/530, loss: 0.03136320412158966
2023-01-21 12:55:44.555868: step: 512/530, loss: 0.0051250457763671875
2023-01-21 12:55:45.673123: step: 516/530, loss: -3.933906555175781e-06
2023-01-21 12:55:46.772274: step: 520/530, loss: 0.00021214484877418727
2023-01-21 12:55:47.908506: step: 524/530, loss: 0.0002285003720317036
2023-01-21 12:55:49.038563: step: 528/530, loss: 0.00011521577835083008
2023-01-21 12:55:50.132280: step: 532/530, loss: 0.0012777328956872225
2023-01-21 12:55:51.246191: step: 536/530, loss: 0.041399434208869934
2023-01-21 12:55:52.355357: step: 540/530, loss: 0.00311698904260993
2023-01-21 12:55:53.466310: step: 544/530, loss: 0.004006767179816961
2023-01-21 12:55:54.589374: step: 548/530, loss: 0.007896805182099342
2023-01-21 12:55:55.723660: step: 552/530, loss: 0.0001291275111725554
2023-01-21 12:55:56.841693: step: 556/530, loss: 0.00044536590576171875
2023-01-21 12:55:57.944052: step: 560/530, loss: 4.19616708313697e-06
2023-01-21 12:55:59.082411: step: 564/530, loss: 0.005494022276252508
2023-01-21 12:56:00.200005: step: 568/530, loss: 0.00023460389638785273
2023-01-21 12:56:01.309493: step: 572/530, loss: 0.00024433137150481343
2023-01-21 12:56:02.428500: step: 576/530, loss: 0.00197257986292243
2023-01-21 12:56:03.536471: step: 580/530, loss: 0.00055780413094908
2023-01-21 12:56:04.657049: step: 584/530, loss: 0.026679228991270065
2023-01-21 12:56:05.773201: step: 588/530, loss: 0.012189007364213467
2023-01-21 12:56:06.892843: step: 592/530, loss: 0.0001600265532033518
2023-01-21 12:56:08.048224: step: 596/530, loss: 0.011222731322050095
2023-01-21 12:56:09.161309: step: 600/530, loss: 0.0018152237171307206
2023-01-21 12:56:10.271056: step: 604/530, loss: 0.022639179602265358
2023-01-21 12:56:11.378381: step: 608/530, loss: 0.0015533447731286287
2023-01-21 12:56:12.494341: step: 612/530, loss: 3.910064606316155e-06
2023-01-21 12:56:13.621697: step: 616/530, loss: 0.05896148830652237
2023-01-21 12:56:14.710869: step: 620/530, loss: 0.009541917592287064
2023-01-21 12:56:15.836588: step: 624/530, loss: 0.16832828521728516
2023-01-21 12:56:16.958847: step: 628/530, loss: 0.10283298790454865
2023-01-21 12:56:18.105785: step: 632/530, loss: 0.008816242218017578
2023-01-21 12:56:19.189017: step: 636/530, loss: 0.0021834373474121094
2023-01-21 12:56:20.316132: step: 640/530, loss: 0.0006414413801394403
2023-01-21 12:56:21.434665: step: 644/530, loss: 0.053575899451971054
2023-01-21 12:56:22.562537: step: 648/530, loss: 0.22682718932628632
2023-01-21 12:56:23.662223: step: 652/530, loss: 3.4809113458322827e-06
2023-01-21 12:56:24.812852: step: 656/530, loss: 0.03373575210571289
2023-01-21 12:56:25.937974: step: 660/530, loss: 0.0208892822265625
2023-01-21 12:56:27.045216: step: 664/530, loss: 0.0015548706287518144
2023-01-21 12:56:28.159596: step: 668/530, loss: 5.9700014389818534e-05
2023-01-21 12:56:29.249286: step: 672/530, loss: 0.0038442614022642374
2023-01-21 12:56:30.378799: step: 676/530, loss: 0.01062402781099081
2023-01-21 12:56:31.503489: step: 680/530, loss: 0.008145141415297985
2023-01-21 12:56:32.632921: step: 684/530, loss: 0.008001899346709251
2023-01-21 12:56:33.747670: step: 688/530, loss: 0.0007680892595089972
2023-01-21 12:56:34.896327: step: 692/530, loss: 5.187988426769152e-05
2023-01-21 12:56:36.005083: step: 696/530, loss: 2.2315980459097773e-05
2023-01-21 12:56:37.118098: step: 700/530, loss: 0.016297722235322
2023-01-21 12:56:38.214023: step: 704/530, loss: 0.026692010462284088
2023-01-21 12:56:39.331236: step: 708/530, loss: 0.0065919398330152035
2023-01-21 12:56:40.456518: step: 712/530, loss: 0.00010747909982455894
2023-01-21 12:56:41.575149: step: 716/530, loss: 0.00015742778487037867
2023-01-21 12:56:42.703601: step: 720/530, loss: 0.002621269319206476
2023-01-21 12:56:43.798317: step: 724/530, loss: 0.0002571106015238911
2023-01-21 12:56:44.932681: step: 728/530, loss: 0.0019521713256835938
2023-01-21 12:56:46.038815: step: 732/530, loss: 0.022020291537046432
2023-01-21 12:56:47.146250: step: 736/530, loss: 0.002134132431820035
2023-01-21 12:56:48.294706: step: 740/530, loss: 0.005217170808464289
2023-01-21 12:56:49.405948: step: 744/530, loss: 5.53131103515625e-05
2023-01-21 12:56:50.537964: step: 748/530, loss: 0.002600383711978793
2023-01-21 12:56:51.653937: step: 752/530, loss: 0.00021409989858511835
2023-01-21 12:56:52.768859: step: 756/530, loss: 0.0004191398620605469
2023-01-21 12:56:53.864948: step: 760/530, loss: 8.602142770541832e-05
2023-01-21 12:56:55.014976: step: 764/530, loss: 5.7220458984375e-06
2023-01-21 12:56:56.120789: step: 768/530, loss: 6.67572021484375e-06
2023-01-21 12:56:57.235268: step: 772/530, loss: 0.012211799621582031
2023-01-21 12:56:58.358841: step: 776/530, loss: 0.0023056031204760075
2023-01-21 12:56:59.479035: step: 780/530, loss: 0.0010417938465252519
2023-01-21 12:57:00.627884: step: 784/530, loss: 1.3256072634248994e-05
2023-01-21 12:57:01.750284: step: 788/530, loss: 0.0016183375846594572
2023-01-21 12:57:02.883056: step: 792/530, loss: 0.00021648408437613398
2023-01-21 12:57:03.991661: step: 796/530, loss: 0.009194612503051758
2023-01-21 12:57:05.080990: step: 800/530, loss: 0.0014911651378497481
2023-01-21 12:57:06.175196: step: 804/530, loss: 5.9747697378043085e-05
2023-01-21 12:57:07.300849: step: 808/530, loss: 0.0015074253315106034
2023-01-21 12:57:08.440214: step: 812/530, loss: 0.00204124441370368
2023-01-21 12:57:09.548709: step: 816/530, loss: 0.00041809084359556437
2023-01-21 12:57:10.665956: step: 820/530, loss: 0.0001298904389841482
2023-01-21 12:57:11.807030: step: 824/530, loss: 0.014511299319565296
2023-01-21 12:57:12.918634: step: 828/530, loss: 0.000967431056778878
2023-01-21 12:57:14.027813: step: 832/530, loss: 6.29425048828125e-05
2023-01-21 12:57:15.145358: step: 836/530, loss: 0.003452873323112726
2023-01-21 12:57:16.267559: step: 840/530, loss: 0.0040378570556640625
2023-01-21 12:57:17.396717: step: 844/530, loss: 0.027158165350556374
2023-01-21 12:57:18.487110: step: 848/530, loss: 2.6226043701171875e-05
2023-01-21 12:57:19.629985: step: 852/530, loss: 2.1743775505456142e-05
2023-01-21 12:57:20.748185: step: 856/530, loss: 0.006146240513771772
2023-01-21 12:57:21.878491: step: 860/530, loss: 0.04234914854168892
2023-01-21 12:57:22.996646: step: 864/530, loss: 0.006815814878791571
2023-01-21 12:57:24.110253: step: 868/530, loss: 0.0002437591610942036
2023-01-21 12:57:25.210008: step: 872/530, loss: 3.352165367687121e-05
2023-01-21 12:57:26.296908: step: 876/530, loss: 0.020459938794374466
2023-01-21 12:57:27.410770: step: 880/530, loss: 0.0002548217598814517
2023-01-21 12:57:28.564064: step: 884/530, loss: 4.1007992876984645e-06
2023-01-21 12:57:29.692899: step: 888/530, loss: 5.483627683133818e-05
2023-01-21 12:57:30.838278: step: 892/530, loss: 0.024182798340916634
2023-01-21 12:57:31.944310: step: 896/530, loss: 0.008135223761200905
2023-01-21 12:57:33.077735: step: 900/530, loss: 0.00025577546330168843
2023-01-21 12:57:34.223991: step: 904/530, loss: 0.00011825562251033261
2023-01-21 12:57:35.353309: step: 908/530, loss: 6.752014451194555e-05
2023-01-21 12:57:36.486334: step: 912/530, loss: 0.00034332275390625
2023-01-21 12:57:37.657117: step: 916/530, loss: 0.0003939628368243575
2023-01-21 12:57:38.792259: step: 920/530, loss: 0.006469917483627796
2023-01-21 12:57:39.960075: step: 924/530, loss: 0.011805057525634766
2023-01-21 12:57:41.103239: step: 928/530, loss: 0.0002655983262229711
2023-01-21 12:57:42.264532: step: 932/530, loss: 0.041353560984134674
2023-01-21 12:57:43.392659: step: 936/530, loss: 4.4202803110238165e-05
2023-01-21 12:57:44.529083: step: 940/530, loss: 0.11973419040441513
2023-01-21 12:57:45.664899: step: 944/530, loss: 1.621246337890625e-05
2023-01-21 12:57:46.778115: step: 948/530, loss: 8.37326078908518e-05
2023-01-21 12:57:47.877828: step: 952/530, loss: 2.0408631826285273e-05
2023-01-21 12:57:48.987419: step: 956/530, loss: 0.0545259490609169
2023-01-21 12:57:50.122063: step: 960/530, loss: 0.022856904193758965
2023-01-21 12:57:51.255267: step: 964/530, loss: 0.00012044906907249242
2023-01-21 12:57:52.368851: step: 968/530, loss: -4.816055479750503e-06
2023-01-21 12:57:53.488388: step: 972/530, loss: 0.00599327078089118
2023-01-21 12:57:54.580374: step: 976/530, loss: 0.0001146316499216482
2023-01-21 12:57:55.689708: step: 980/530, loss: 4.596710277837701e-05
2023-01-21 12:57:56.805079: step: 984/530, loss: 0.01909642294049263
2023-01-21 12:57:57.927940: step: 988/530, loss: 2.5081635612878017e-05
2023-01-21 12:57:59.041986: step: 992/530, loss: 0.0011288643581792712
2023-01-21 12:58:00.151459: step: 996/530, loss: 0.0008054733625613153
2023-01-21 12:58:01.288424: step: 1000/530, loss: 0.002540207002311945
2023-01-21 12:58:02.422716: step: 1004/530, loss: 0.14998988807201385
2023-01-21 12:58:03.542277: step: 1008/530, loss: 0.0008680343744345009
2023-01-21 12:58:04.674923: step: 1012/530, loss: 0.02559218555688858
2023-01-21 12:58:05.804317: step: 1016/530, loss: 0.0001165389985544607
2023-01-21 12:58:06.909063: step: 1020/530, loss: 0.015374279581010342
2023-01-21 12:58:08.057568: step: 1024/530, loss: -2.19345088225964e-06
2023-01-21 12:58:09.200721: step: 1028/530, loss: 0.002293491503223777
2023-01-21 12:58:10.304842: step: 1032/530, loss: 4.5776364459015895e-06
2023-01-21 12:58:11.446007: step: 1036/530, loss: 0.007201576139777899
2023-01-21 12:58:12.640435: step: 1040/530, loss: 0.0009744644048623741
2023-01-21 12:58:13.765286: step: 1044/530, loss: 0.00432434119284153
2023-01-21 12:58:14.889924: step: 1048/530, loss: 5.0926206313306466e-05
2023-01-21 12:58:16.004944: step: 1052/530, loss: 2.6082992917508818e-05
2023-01-21 12:58:17.100585: step: 1056/530, loss: 0.0032881738152354956
2023-01-21 12:58:18.222941: step: 1060/530, loss: 0.0010266781318932772
2023-01-21 12:58:19.312924: step: 1064/530, loss: 0.022023582831025124
2023-01-21 12:58:20.428065: step: 1068/530, loss: 2.4032591682043858e-05
2023-01-21 12:58:21.515862: step: 1072/530, loss: 0.0015546799404546618
2023-01-21 12:58:22.632853: step: 1076/530, loss: 0.0010232925415039062
2023-01-21 12:58:23.762737: step: 1080/530, loss: 1.6021729607018642e-05
2023-01-21 12:58:24.889604: step: 1084/530, loss: 0.028565790504217148
2023-01-21 12:58:26.019908: step: 1088/530, loss: 0.0006079673767089844
2023-01-21 12:58:27.188458: step: 1092/530, loss: 0.0009604454389773309
2023-01-21 12:58:28.301601: step: 1096/530, loss: 0.0003078460576944053
2023-01-21 12:58:29.408324: step: 1100/530, loss: 0.0527295358479023
2023-01-21 12:58:30.529050: step: 1104/530, loss: 0.004945564083755016
2023-01-21 12:58:31.636228: step: 1108/530, loss: 9.059906005859375e-05
2023-01-21 12:58:32.785773: step: 1112/530, loss: 1.7833710444392636e-05
2023-01-21 12:58:33.906001: step: 1116/530, loss: 0.0004982948303222656
2023-01-21 12:58:35.033239: step: 1120/530, loss: 1.1253358934482094e-05
2023-01-21 12:58:36.178621: step: 1124/530, loss: 1.163482647825731e-05
2023-01-21 12:58:37.288942: step: 1128/530, loss: 0.012365054339170456
2023-01-21 12:58:38.420414: step: 1132/530, loss: -3.43322744811303e-06
2023-01-21 12:58:39.542261: step: 1136/530, loss: -1.487731969973538e-05
2023-01-21 12:58:40.694745: step: 1140/530, loss: 0.05293254926800728
2023-01-21 12:58:41.812529: step: 1144/530, loss: 0.0002735137823037803
2023-01-21 12:58:42.962494: step: 1148/530, loss: -3.0517580853484105e-06
2023-01-21 12:58:44.084124: step: 1152/530, loss: 9.174347360385582e-05
2023-01-21 12:58:45.211111: step: 1156/530, loss: 0.0002172470121877268
2023-01-21 12:58:46.320578: step: 1160/530, loss: 0.0017421721713617444
2023-01-21 12:58:47.451105: step: 1164/530, loss: 0.06765203922986984
2023-01-21 12:58:48.560656: step: 1168/530, loss: 0.0006789207109250128
2023-01-21 12:58:49.665915: step: 1172/530, loss: 0.016523336991667747
2023-01-21 12:58:50.779201: step: 1176/530, loss: 0.0007490158313885331
2023-01-21 12:58:51.909050: step: 1180/530, loss: 0.004408645909279585
2023-01-21 12:58:53.042065: step: 1184/530, loss: 0.00013017655874136835
2023-01-21 12:58:54.226057: step: 1188/530, loss: 2.117157055181451e-05
2023-01-21 12:58:55.372076: step: 1192/530, loss: 0.0036529540084302425
2023-01-21 12:58:56.494626: step: 1196/530, loss: 0.007598018739372492
2023-01-21 12:58:57.647589: step: 1200/530, loss: 2.689361645025201e-05
2023-01-21 12:58:58.806384: step: 1204/530, loss: 6.160735938465223e-05
2023-01-21 12:58:59.908789: step: 1208/530, loss: 0.0001338958682026714
2023-01-21 12:59:01.027067: step: 1212/530, loss: 0.03086128458380699
2023-01-21 12:59:02.149844: step: 1216/530, loss: 7.286071922862902e-05
2023-01-21 12:59:03.249851: step: 1220/530, loss: 0.013055801391601562
2023-01-21 12:59:04.354939: step: 1224/530, loss: 1.2373924619168974e-05
2023-01-21 12:59:05.453597: step: 1228/530, loss: 0.021085072308778763
2023-01-21 12:59:06.543874: step: 1232/530, loss: 2.117157055181451e-05
2023-01-21 12:59:07.677272: step: 1236/530, loss: 0.17790231108665466
2023-01-21 12:59:08.829328: step: 1240/530, loss: 0.012349128723144531
2023-01-21 12:59:09.953838: step: 1244/530, loss: 0.0005983352893963456
2023-01-21 12:59:11.072297: step: 1248/530, loss: 0.02866668626666069
2023-01-21 12:59:12.204522: step: 1252/530, loss: 0.005595398135483265
2023-01-21 12:59:13.301590: step: 1256/530, loss: 0.0021149637177586555
2023-01-21 12:59:14.432742: step: 1260/530, loss: 0.00010948181443382055
2023-01-21 12:59:15.545711: step: 1264/530, loss: 0.00018043517775367945
2023-01-21 12:59:16.692616: step: 1268/530, loss: 0.021932220086455345
2023-01-21 12:59:17.811229: step: 1272/530, loss: 0.00486183213070035
2023-01-21 12:59:18.883367: step: 1276/530, loss: 1.4829635802016128e-05
2023-01-21 12:59:20.010287: step: 1280/530, loss: 0.000545501708984375
2023-01-21 12:59:21.135706: step: 1284/530, loss: 0.005814719013869762
2023-01-21 12:59:22.276061: step: 1288/530, loss: 3.1471254260395654e-06
2023-01-21 12:59:23.387433: step: 1292/530, loss: 0.0007976532797329128
2023-01-21 12:59:24.532543: step: 1296/530, loss: 0.0004677772521972656
2023-01-21 12:59:25.643278: step: 1300/530, loss: 0.0003046035999432206
2023-01-21 12:59:26.780197: step: 1304/530, loss: 0.0003986358642578125
2023-01-21 12:59:27.882875: step: 1308/530, loss: 3.5285952435515355e-06
2023-01-21 12:59:28.997194: step: 1312/530, loss: 0.00101299281232059
2023-01-21 12:59:30.148823: step: 1316/530, loss: 9.078979201149195e-05
2023-01-21 12:59:31.256584: step: 1320/530, loss: 6.809234764659777e-05
2023-01-21 12:59:32.406023: step: 1324/530, loss: 4.00543194700731e-06
2023-01-21 12:59:33.536809: step: 1328/530, loss: 8.58306884765625e-06
2023-01-21 12:59:34.673442: step: 1332/530, loss: 0.0017309188842773438
2023-01-21 12:59:35.830523: step: 1336/530, loss: 0.027537154033780098
2023-01-21 12:59:36.940494: step: 1340/530, loss: 6.027221752447076e-05
2023-01-21 12:59:38.070969: step: 1344/530, loss: 0.0012868881458416581
2023-01-21 12:59:39.180259: step: 1348/530, loss: 0.017282672226428986
2023-01-21 12:59:40.297858: step: 1352/530, loss: 0.04293708875775337
2023-01-21 12:59:41.408878: step: 1356/530, loss: 0.0023069381713867188
2023-01-21 12:59:42.546009: step: 1360/530, loss: 0.0016736506950110197
2023-01-21 12:59:43.651985: step: 1364/530, loss: 9.870529902400449e-05
2023-01-21 12:59:44.760511: step: 1368/530, loss: 0.054799843579530716
2023-01-21 12:59:45.888790: step: 1372/530, loss: 0.02229003980755806
2023-01-21 12:59:47.034684: step: 1376/530, loss: 0.006322097964584827
2023-01-21 12:59:48.175043: step: 1380/530, loss: 9.460449655307457e-05
2023-01-21 12:59:49.304645: step: 1384/530, loss: 0.0002643585321493447
2023-01-21 12:59:50.440176: step: 1388/530, loss: 0.07097721099853516
2023-01-21 12:59:51.561742: step: 1392/530, loss: 0.0002117156982421875
2023-01-21 12:59:52.688433: step: 1396/530, loss: 4.916191392112523e-05
2023-01-21 12:59:53.802277: step: 1400/530, loss: 6.86645489622606e-06
2023-01-21 12:59:54.898697: step: 1404/530, loss: 0.011098289862275124
2023-01-21 12:59:55.999760: step: 1408/530, loss: 0.00038919446524232626
2023-01-21 12:59:57.137264: step: 1412/530, loss: 0.0002101898135151714
2023-01-21 12:59:58.255630: step: 1416/530, loss: 0.0003986358642578125
2023-01-21 12:59:59.387851: step: 1420/530, loss: 0.00483284005895257
2023-01-21 13:00:00.496564: step: 1424/530, loss: 3.051757857974735e-06
2023-01-21 13:00:01.608753: step: 1428/530, loss: 0.00142335903365165
2023-01-21 13:00:02.734925: step: 1432/530, loss: 0.03229503706097603
2023-01-21 13:00:03.869588: step: 1436/530, loss: 0.002235317137092352
2023-01-21 13:00:04.997348: step: 1440/530, loss: 0.03148498758673668
2023-01-21 13:00:06.120761: step: 1444/530, loss: 0.001020717667415738
2023-01-21 13:00:07.270472: step: 1448/530, loss: 0.0027269364800304174
2023-01-21 13:00:08.385285: step: 1452/530, loss: 0.011743354611098766
2023-01-21 13:00:09.510924: step: 1456/530, loss: 0.0004593372577801347
2023-01-21 13:00:10.657087: step: 1460/530, loss: 0.015277290716767311
2023-01-21 13:00:11.798902: step: 1464/530, loss: 0.00011568069749046117
2023-01-21 13:00:12.905628: step: 1468/530, loss: 0.00014925003051757812
2023-01-21 13:00:14.035392: step: 1472/530, loss: 0.005846405401825905
2023-01-21 13:00:15.154107: step: 1476/530, loss: 0.03164215385913849
2023-01-21 13:00:16.304826: step: 1480/530, loss: 0.00312976841814816
2023-01-21 13:00:17.438410: step: 1484/530, loss: 0.00018634795560501516
2023-01-21 13:00:18.577460: step: 1488/530, loss: 0.00010261535499012098
2023-01-21 13:00:19.719054: step: 1492/530, loss: 0.0975341796875
2023-01-21 13:00:20.860434: step: 1496/530, loss: 0.0004000186745543033
2023-01-21 13:00:21.977760: step: 1500/530, loss: 0.0030048370826989412
2023-01-21 13:00:23.097695: step: 1504/530, loss: 0.0015819550026208162
2023-01-21 13:00:24.194631: step: 1508/530, loss: 7.698535773670301e-05
2023-01-21 13:00:25.319212: step: 1512/530, loss: 3.814697322468419e-07
2023-01-21 13:00:26.423632: step: 1516/530, loss: 0.00020380019850563258
2023-01-21 13:00:27.556013: step: 1520/530, loss: 0.003494405886158347
2023-01-21 13:00:28.717563: step: 1524/530, loss: 0.0022994994651526213
2023-01-21 13:00:29.829814: step: 1528/530, loss: 0.00153865828178823
2023-01-21 13:00:30.968383: step: 1532/530, loss: 0.09261074662208557
2023-01-21 13:00:32.105125: step: 1536/530, loss: 0.003301429795101285
2023-01-21 13:00:33.241072: step: 1540/530, loss: 0.018247032538056374
2023-01-21 13:00:34.377440: step: 1544/530, loss: 0.0010723114246502519
2023-01-21 13:00:35.493585: step: 1548/530, loss: 1.0204315913142636e-05
2023-01-21 13:00:36.601866: step: 1552/530, loss: 4.2724612285383046e-05
2023-01-21 13:00:37.687871: step: 1556/530, loss: 8.804201934253797e-05
2023-01-21 13:00:38.781530: step: 1560/530, loss: 2.5272369384765625e-05
2023-01-21 13:00:39.912457: step: 1564/530, loss: 0.0007892608409747481
2023-01-21 13:00:41.031523: step: 1568/530, loss: 0.012942695990204811
2023-01-21 13:00:42.169160: step: 1572/530, loss: 0.0008290291298180819
2023-01-21 13:00:43.317913: step: 1576/530, loss: 8.811950829112902e-05
2023-01-21 13:00:44.455968: step: 1580/530, loss: 0.00042572023812681437
2023-01-21 13:00:45.570263: step: 1584/530, loss: 0.016614437103271484
2023-01-21 13:00:46.699778: step: 1588/530, loss: 0.011886310763657093
2023-01-21 13:00:47.812149: step: 1592/530, loss: 0.006525135133415461
2023-01-21 13:00:48.935234: step: 1596/530, loss: 7.314682443393394e-05
2023-01-21 13:00:50.058780: step: 1600/530, loss: 0.005259704776108265
2023-01-21 13:00:51.186385: step: 1604/530, loss: 0.021658897399902344
2023-01-21 13:00:52.292162: step: 1608/530, loss: 9.193420555675402e-05
2023-01-21 13:00:53.403060: step: 1612/530, loss: 0.0002578735293354839
2023-01-21 13:00:54.520749: step: 1616/530, loss: 0.03895826265215874
2023-01-21 13:00:55.642800: step: 1620/530, loss: 0.005460548680275679
2023-01-21 13:00:56.770560: step: 1624/530, loss: 0.0030788423027843237
2023-01-21 13:00:57.905480: step: 1628/530, loss: 0.015365028753876686
2023-01-21 13:00:59.077482: step: 1632/530, loss: -9.91821252682712e-06
2023-01-21 13:01:00.188302: step: 1636/530, loss: 0.042546749114990234
2023-01-21 13:01:01.291042: step: 1640/530, loss: 0.05019249767065048
2023-01-21 13:01:02.427581: step: 1644/530, loss: 2.346038854739163e-05
2023-01-21 13:01:03.562515: step: 1648/530, loss: 0.001820468925870955
2023-01-21 13:01:04.688495: step: 1652/530, loss: 5.016326758777723e-05
2023-01-21 13:01:05.828645: step: 1656/530, loss: 0.0016891479026526213
2023-01-21 13:01:06.950827: step: 1660/530, loss: 0.05559587478637695
2023-01-21 13:01:08.056730: step: 1664/530, loss: 0.009005165658891201
2023-01-21 13:01:09.149430: step: 1668/530, loss: 7.467270188499242e-05
2023-01-21 13:01:10.269065: step: 1672/530, loss: 0.0014442444080486894
2023-01-21 13:01:11.380360: step: 1676/530, loss: 0.003948783967643976
2023-01-21 13:01:12.486882: step: 1680/530, loss: 0.00039463042048737407
2023-01-21 13:01:13.607531: step: 1684/530, loss: 0.0032584667205810547
2023-01-21 13:01:14.733573: step: 1688/530, loss: 0.03420582041144371
2023-01-21 13:01:15.849700: step: 1692/530, loss: 0.0036219358444213867
2023-01-21 13:01:16.968615: step: 1696/530, loss: 0.029423905536532402
2023-01-21 13:01:18.064342: step: 1700/530, loss: 0.0003448009374551475
2023-01-21 13:01:19.193011: step: 1704/530, loss: 0.00032482147798873484
2023-01-21 13:01:20.310793: step: 1708/530, loss: 0.0387762077152729
2023-01-21 13:01:21.408021: step: 1712/530, loss: 0.0005709648248739541
2023-01-21 13:01:22.513124: step: 1716/530, loss: 0.0665929839015007
2023-01-21 13:01:23.630121: step: 1720/530, loss: 7.600784010719508e-05
2023-01-21 13:01:24.788306: step: 1724/530, loss: 0.03605065494775772
2023-01-21 13:01:25.919355: step: 1728/530, loss: 0.020040130242705345
2023-01-21 13:01:27.037501: step: 1732/530, loss: 0.002011108212172985
2023-01-21 13:01:28.164472: step: 1736/530, loss: 0.04630448669195175
2023-01-21 13:01:29.286066: step: 1740/530, loss: 0.013636552728712559
2023-01-21 13:01:30.398446: step: 1744/530, loss: 0.0006873130914755166
2023-01-21 13:01:31.526769: step: 1748/530, loss: 6.4849853515625e-05
2023-01-21 13:01:32.682064: step: 1752/530, loss: 0.001142215682193637
2023-01-21 13:01:33.785625: step: 1756/530, loss: 6.008148193359375e-05
2023-01-21 13:01:34.911810: step: 1760/530, loss: 0.019082164391875267
2023-01-21 13:01:36.029894: step: 1764/530, loss: 0.008120918646454811
2023-01-21 13:01:37.154802: step: 1768/530, loss: 0.011363839730620384
2023-01-21 13:01:38.279072: step: 1772/530, loss: 0.00016894341388251632
2023-01-21 13:01:39.413079: step: 1776/530, loss: 0.002326393034309149
2023-01-21 13:01:40.533567: step: 1780/530, loss: 0.03616046905517578
2023-01-21 13:01:41.642132: step: 1784/530, loss: 0.024187661707401276
2023-01-21 13:01:42.772584: step: 1788/530, loss: 0.046508025377988815
2023-01-21 13:01:43.901553: step: 1792/530, loss: 0.00937185250222683
2023-01-21 13:01:45.045615: step: 1796/530, loss: 4.2343137465650216e-05
2023-01-21 13:01:46.168915: step: 1800/530, loss: 0.417245090007782
2023-01-21 13:01:47.357809: step: 1804/530, loss: 3.108978125965223e-05
2023-01-21 13:01:48.500243: step: 1808/530, loss: 0.005215073004364967
2023-01-21 13:01:49.662119: step: 1812/530, loss: 0.001076507498510182
2023-01-21 13:01:50.767445: step: 1816/530, loss: 2.0885468984488398e-05
2023-01-21 13:01:51.901066: step: 1820/530, loss: 0.0029243947938084602
2023-01-21 13:01:53.020446: step: 1824/530, loss: 0.00010900497727561742
2023-01-21 13:01:54.132661: step: 1828/530, loss: 9.34600848268019e-06
2023-01-21 13:01:55.272524: step: 1832/530, loss: 0.003025627229362726
2023-01-21 13:01:56.384106: step: 1836/530, loss: 0.00205402378924191
2023-01-21 13:01:57.493974: step: 1840/530, loss: 0.0019567490089684725
2023-01-21 13:01:58.616894: step: 1844/530, loss: 0.0004435539012774825
2023-01-21 13:01:59.700683: step: 1848/530, loss: 0.0016492843860760331
2023-01-21 13:02:00.802105: step: 1852/530, loss: 0.0012628555996343493
2023-01-21 13:02:01.936738: step: 1856/530, loss: 0.005897903814911842
2023-01-21 13:02:03.105230: step: 1860/530, loss: 8.115769014693797e-05
2023-01-21 13:02:04.209201: step: 1864/530, loss: 7.400512549793348e-05
2023-01-21 13:02:05.321386: step: 1868/530, loss: 1.735687328618951e-05
2023-01-21 13:02:06.440401: step: 1872/530, loss: 9.803772263694555e-05
2023-01-21 13:02:07.624448: step: 1876/530, loss: 0.02789182774722576
2023-01-21 13:02:08.745515: step: 1880/530, loss: 0.008263969793915749
2023-01-21 13:02:09.866408: step: 1884/530, loss: 0.00019130707369185984
2023-01-21 13:02:10.998900: step: 1888/530, loss: 0.022878360003232956
2023-01-21 13:02:12.114331: step: 1892/530, loss: 0.00021805762662552297
2023-01-21 13:02:13.199611: step: 1896/530, loss: 4.57763671875e-05
2023-01-21 13:02:14.347183: step: 1900/530, loss: 0.00216770195402205
2023-01-21 13:02:15.464981: step: 1904/530, loss: 0.00010814666893566027
2023-01-21 13:02:16.591085: step: 1908/530, loss: 9.512901306152344e-05
2023-01-21 13:02:17.685744: step: 1912/530, loss: 0.00358238210901618
2023-01-21 13:02:18.793211: step: 1916/530, loss: 0.0021102905739098787
2023-01-21 13:02:19.912887: step: 1920/530, loss: 0.006354904267936945
2023-01-21 13:02:21.008898: step: 1924/530, loss: 0.00906310137361288
2023-01-21 13:02:22.148805: step: 1928/530, loss: 0.015767479315400124
2023-01-21 13:02:23.250472: step: 1932/530, loss: 0.023536013439297676
2023-01-21 13:02:24.365902: step: 1936/530, loss: 0.002283764071762562
2023-01-21 13:02:25.470063: step: 1940/530, loss: 0.001506805419921875
2023-01-21 13:02:26.594971: step: 1944/530, loss: 0.010860919952392578
2023-01-21 13:02:27.694094: step: 1948/530, loss: 9.422302537132055e-05
2023-01-21 13:02:28.828194: step: 1952/530, loss: 0.34278029203414917
2023-01-21 13:02:29.953160: step: 1956/530, loss: 0.000501442002132535
2023-01-21 13:02:31.069635: step: 1960/530, loss: 0.13314132392406464
2023-01-21 13:02:32.186805: step: 1964/530, loss: 0.0020015717018395662
2023-01-21 13:02:33.319383: step: 1968/530, loss: 7.514953904319555e-05
2023-01-21 13:02:34.437199: step: 1972/530, loss: 0.004270076751708984
2023-01-21 13:02:35.537412: step: 1976/530, loss: 0.00013647080049850047
2023-01-21 13:02:36.680590: step: 1980/530, loss: 0.03386888653039932
2023-01-21 13:02:37.769730: step: 1984/530, loss: 0.00276603689417243
2023-01-21 13:02:38.882065: step: 1988/530, loss: 0.0001352310209767893
2023-01-21 13:02:40.039501: step: 1992/530, loss: 0.004714584443718195
2023-01-21 13:02:41.196123: step: 1996/530, loss: 0.004117775242775679
2023-01-21 13:02:42.326732: step: 2000/530, loss: 0.003760433290153742
2023-01-21 13:02:43.443935: step: 2004/530, loss: 0.0006007194169797003
2023-01-21 13:02:44.591802: step: 2008/530, loss: 0.0024663927033543587
2023-01-21 13:02:45.732241: step: 2012/530, loss: 0.030516481027007103
2023-01-21 13:02:46.828655: step: 2016/530, loss: 0.0018155097495764494
2023-01-21 13:02:47.953270: step: 2020/530, loss: 5.722044988942798e-07
2023-01-21 13:02:49.070892: step: 2024/530, loss: 0.00195140833966434
2023-01-21 13:02:50.190618: step: 2028/530, loss: 0.006188392639160156
2023-01-21 13:02:51.365630: step: 2032/530, loss: 0.0067230225540697575
2023-01-21 13:02:52.491866: step: 2036/530, loss: 0.0002838134823832661
2023-01-21 13:02:53.643483: step: 2040/530, loss: 0.0002682686026673764
2023-01-21 13:02:54.747281: step: 2044/530, loss: 0.5250097513198853
2023-01-21 13:02:55.877175: step: 2048/530, loss: 0.004332160577178001
2023-01-21 13:02:56.981542: step: 2052/530, loss: 0.01495276764035225
2023-01-21 13:02:58.097318: step: 2056/530, loss: 0.0024236678145825863
2023-01-21 13:02:59.244073: step: 2060/530, loss: 0.00018310546875
2023-01-21 13:03:00.346750: step: 2064/530, loss: 0.00013675689115189016
2023-01-21 13:03:01.467668: step: 2068/530, loss: 0.001949405763298273
2023-01-21 13:03:02.585169: step: 2072/530, loss: 0.003637981601059437
2023-01-21 13:03:03.694965: step: 2076/530, loss: 0.000590467476285994
2023-01-21 13:03:04.803128: step: 2080/530, loss: 8.773804438533261e-06
2023-01-21 13:03:05.915391: step: 2084/530, loss: 0.0014101981651037931
2023-01-21 13:03:07.038623: step: 2088/530, loss: 0.007420730777084827
2023-01-21 13:03:08.187169: step: 2092/530, loss: 0.003148841904476285
2023-01-21 13:03:09.328175: step: 2096/530, loss: 0.0001987457217182964
2023-01-21 13:03:10.454935: step: 2100/530, loss: 0.09257392585277557
2023-01-21 13:03:11.576639: step: 2104/530, loss: 0.008580494672060013
2023-01-21 13:03:12.690260: step: 2108/530, loss: 0.0009945392375811934
2023-01-21 13:03:13.786803: step: 2112/530, loss: 0.000978660536929965
2023-01-21 13:03:14.914710: step: 2116/530, loss: 0.002523183822631836
2023-01-21 13:03:16.041773: step: 2120/530, loss: 0.049784183502197266
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.571150097465887, 'r': 0.7802929427430093, 'f1': 0.6595385481148002}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6182867288060364, 'r': 0.796, 'f1': 0.6959780164876342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
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': 25}
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': 25}
Russian: {'event': {'p': 0.36363636363636365, 'r': 0.4444444444444444, 'f1': 0.39999999999999997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 13:03:56.889488: step: 4/530, loss: 0.0005044937133789062
2023-01-21 13:03:58.001839: step: 8/530, loss: 2.9039383662166074e-05
2023-01-21 13:03:59.165426: step: 12/530, loss: 6.237030174816027e-05
2023-01-21 13:04:00.307573: step: 16/530, loss: 0.026513230055570602
2023-01-21 13:04:01.427038: step: 20/530, loss: 0.00014247893705032766
2023-01-21 13:04:02.593578: step: 24/530, loss: 0.0013393402332440019
2023-01-21 13:04:03.716201: step: 28/530, loss: 0.00018377305241301656
2023-01-21 13:04:04.786282: step: 32/530, loss: 3.7765505112474784e-05
2023-01-21 13:04:05.893847: step: 36/530, loss: 0.5083279013633728
2023-01-21 13:04:07.019780: step: 40/530, loss: 0.009083176031708717
2023-01-21 13:04:08.144151: step: 44/530, loss: 0.029361821711063385
2023-01-21 13:04:09.272361: step: 48/530, loss: 0.00019493103900458664
2023-01-21 13:04:10.410899: step: 52/530, loss: 0.02713470533490181
2023-01-21 13:04:11.536371: step: 56/530, loss: 0.0029672144446521997
2023-01-21 13:04:12.618497: step: 60/530, loss: -6.198883056640625e-06
2023-01-21 13:04:13.710938: step: 64/530, loss: 8.39233416627394e-06
2023-01-21 13:04:14.837692: step: 68/530, loss: 2.4318695068359375e-05
2023-01-21 13:04:15.984589: step: 72/530, loss: 0.14770202338695526
2023-01-21 13:04:17.111920: step: 76/530, loss: 0.032408908009529114
2023-01-21 13:04:18.228781: step: 80/530, loss: 4.6348573960131034e-05
2023-01-21 13:04:19.338012: step: 84/530, loss: 0.005390167236328125
2023-01-21 13:04:20.460819: step: 88/530, loss: 0.0011595250107347965
2023-01-21 13:04:21.566530: step: 92/530, loss: 0.0012166977394372225
2023-01-21 13:04:22.687286: step: 96/530, loss: 0.0009605407831259072
2023-01-21 13:04:23.826990: step: 100/530, loss: 0.10288061946630478
2023-01-21 13:04:24.973934: step: 104/530, loss: 0.0013006209628656507
2023-01-21 13:04:26.062283: step: 108/530, loss: 0.0006127358064986765
2023-01-21 13:04:27.154101: step: 112/530, loss: 0.00013828277587890625
2023-01-21 13:04:28.281397: step: 116/530, loss: 0.048932649195194244
2023-01-21 13:04:29.415037: step: 120/530, loss: 1.0013581231760327e-05
2023-01-21 13:04:30.546376: step: 124/530, loss: 3.166198803228326e-05
2023-01-21 13:04:31.653403: step: 128/530, loss: 0.0001892089785542339
2023-01-21 13:04:32.746318: step: 132/530, loss: 0.014916039071977139
2023-01-21 13:04:33.849237: step: 136/530, loss: 0.00012149811664130539
2023-01-21 13:04:34.938380: step: 140/530, loss: 0.0015719414222985506
2023-01-21 13:04:36.047721: step: 144/530, loss: 0.0024644851218909025
2023-01-21 13:04:37.151476: step: 148/530, loss: 0.00017480849055573344
2023-01-21 13:04:38.250650: step: 152/530, loss: 0.0004939079517498612
2023-01-21 13:04:39.375072: step: 156/530, loss: 0.00022573472233489156
2023-01-21 13:04:40.513588: step: 160/530, loss: 0.0006559371831826866
2023-01-21 13:04:41.654048: step: 164/530, loss: 0.12548397481441498
2023-01-21 13:04:42.789877: step: 168/530, loss: 0.0164628978818655
2023-01-21 13:04:43.908926: step: 172/530, loss: 0.03999223932623863
2023-01-21 13:04:45.035183: step: 176/530, loss: 0.002995586721226573
2023-01-21 13:04:46.140649: step: 180/530, loss: 0.00010185241262661293
2023-01-21 13:04:47.288434: step: 184/530, loss: 0.000442314165411517
2023-01-21 13:04:48.394687: step: 188/530, loss: 1.1444091796875e-05
2023-01-21 13:04:49.513995: step: 192/530, loss: 0.00028591154841706157
2023-01-21 13:04:50.632480: step: 196/530, loss: 0.008794641122221947
2023-01-21 13:04:51.742619: step: 200/530, loss: 0.0024064064491540194
2023-01-21 13:04:52.878411: step: 204/530, loss: 0.00047397613525390625
2023-01-21 13:04:54.004361: step: 208/530, loss: 0.00029602053109556437
2023-01-21 13:04:55.148890: step: 212/530, loss: -3.566742088878527e-05
2023-01-21 13:04:56.254991: step: 216/530, loss: 0.6951268911361694
2023-01-21 13:04:57.389278: step: 220/530, loss: 0.011384868994355202
2023-01-21 13:04:58.509713: step: 224/530, loss: 0.0051517486572265625
2023-01-21 13:04:59.627552: step: 228/530, loss: 8.535385131835938e-05
2023-01-21 13:05:00.757842: step: 232/530, loss: 0.004618453793227673
2023-01-21 13:05:01.886577: step: 236/530, loss: 0.00012865065946243703
2023-01-21 13:05:02.999478: step: 240/530, loss: 0.0009818077087402344
2023-01-21 13:05:04.121167: step: 244/530, loss: 5.71250930079259e-05
2023-01-21 13:05:05.213390: step: 248/530, loss: 1.950263867911417e-05
2023-01-21 13:05:06.346321: step: 252/530, loss: 0.0013868332607671618
2023-01-21 13:05:07.470858: step: 256/530, loss: 0.0005932330968789756
2023-01-21 13:05:08.604463: step: 260/530, loss: 0.000171661376953125
2023-01-21 13:05:09.706882: step: 264/530, loss: 2.946853419416584e-05
2023-01-21 13:05:10.854987: step: 268/530, loss: 0.007263374514877796
2023-01-21 13:05:11.965893: step: 272/530, loss: 0.0014606952900066972
2023-01-21 13:05:13.070433: step: 276/530, loss: 7.915497008070815e-06
2023-01-21 13:05:14.203530: step: 280/530, loss: 0.0002563476446084678
2023-01-21 13:05:15.284429: step: 284/530, loss: 6.67572021484375e-06
2023-01-21 13:05:16.369500: step: 288/530, loss: 0.00037326812162064016
2023-01-21 13:05:17.514236: step: 292/530, loss: 0.03829498589038849
2023-01-21 13:05:18.616694: step: 296/530, loss: 0.00015964507474564016
2023-01-21 13:05:19.746233: step: 300/530, loss: 0.0012250900035724044
2023-01-21 13:05:20.857155: step: 304/530, loss: 0.007395935244858265
2023-01-21 13:05:21.973178: step: 308/530, loss: 0.0002865791320800781
2023-01-21 13:05:23.113928: step: 312/530, loss: 0.011874771676957607
2023-01-21 13:05:24.276073: step: 316/530, loss: 6.48498553346144e-06
2023-01-21 13:05:25.415682: step: 320/530, loss: 0.0003611564461607486
2023-01-21 13:05:26.521165: step: 324/530, loss: 0.0012183189392089844
2023-01-21 13:05:27.637441: step: 328/530, loss: 0.0015171528793871403
2023-01-21 13:05:28.783339: step: 332/530, loss: 0.07417802512645721
2023-01-21 13:05:29.905974: step: 336/530, loss: 0.00022182465181685984
2023-01-21 13:05:31.004431: step: 340/530, loss: 0.00020065308490302414
2023-01-21 13:05:32.149988: step: 344/530, loss: 0.002754783723503351
2023-01-21 13:05:33.264612: step: 348/530, loss: 0.0044265748001635075
2023-01-21 13:05:34.387535: step: 352/530, loss: 0.00017309188842773438
2023-01-21 13:05:35.503640: step: 356/530, loss: 0.0009841920109465718
2023-01-21 13:05:36.632410: step: 360/530, loss: 0.0006649017450399697
2023-01-21 13:05:37.743791: step: 364/530, loss: 0.00034732819767668843
2023-01-21 13:05:38.874028: step: 368/530, loss: 1.697540210443549e-05
2023-01-21 13:05:39.975883: step: 372/530, loss: 0.018207168206572533
2023-01-21 13:05:41.120916: step: 376/530, loss: 0.0002567291376180947
2023-01-21 13:05:42.257266: step: 380/530, loss: 0.0034462930634617805
2023-01-21 13:05:43.393297: step: 384/530, loss: 0.00018348694720771164
2023-01-21 13:05:44.501381: step: 388/530, loss: 0.014695358462631702
2023-01-21 13:05:45.622655: step: 392/530, loss: 0.0014261245960369706
2023-01-21 13:05:46.742157: step: 396/530, loss: 0.09914422035217285
2023-01-21 13:05:47.844989: step: 400/530, loss: 0.0003533363342285156
2023-01-21 13:05:48.962055: step: 404/530, loss: 1.52587890625e-05
2023-01-21 13:05:50.079173: step: 408/530, loss: 0.0018154144054278731
2023-01-21 13:05:51.193436: step: 412/530, loss: 0.0004873752477578819
2023-01-21 13:05:52.323496: step: 416/530, loss: 0.029822731390595436
2023-01-21 13:05:53.485553: step: 420/530, loss: -1.33514404296875e-05
2023-01-21 13:05:54.657514: step: 424/530, loss: 0.013979149051010609
2023-01-21 13:05:55.778411: step: 428/530, loss: 0.045027781277894974
2023-01-21 13:05:56.896859: step: 432/530, loss: 0.00014057158841751516
2023-01-21 13:05:58.019466: step: 436/530, loss: 0.251665860414505
2023-01-21 13:05:59.145247: step: 440/530, loss: 0.0012916565174236894
2023-01-21 13:06:00.265859: step: 444/530, loss: 0.001100730849429965
2023-01-21 13:06:01.397468: step: 448/530, loss: 0.0018123626941815019
2023-01-21 13:06:02.549286: step: 452/530, loss: 0.00153350830078125
2023-01-21 13:06:03.703497: step: 456/530, loss: 0.0039081573486328125
2023-01-21 13:06:04.793608: step: 460/530, loss: 0.0027206421364098787
2023-01-21 13:06:05.915236: step: 464/530, loss: 0.02383604273200035
2023-01-21 13:06:07.011271: step: 468/530, loss: 0.019712449982762337
2023-01-21 13:06:08.132243: step: 472/530, loss: 0.029551077634096146
2023-01-21 13:06:09.272252: step: 476/530, loss: 2.3031234377413057e-05
2023-01-21 13:06:10.383305: step: 480/530, loss: 8.37326078908518e-05
2023-01-21 13:06:11.485941: step: 484/530, loss: 0.0003444671747274697
2023-01-21 13:06:12.593134: step: 488/530, loss: 0.00011839867511298507
2023-01-21 13:06:13.730702: step: 492/530, loss: 0.0003761291445698589
2023-01-21 13:06:14.880657: step: 496/530, loss: 0.001889896346256137
2023-01-21 13:06:16.002977: step: 500/530, loss: 0.039850424975156784
2023-01-21 13:06:17.175488: step: 504/530, loss: 0.00897131022065878
2023-01-21 13:06:18.299542: step: 508/530, loss: 0.000546360039152205
2023-01-21 13:06:19.454150: step: 512/530, loss: 0.00020809174748137593
2023-01-21 13:06:20.565086: step: 516/530, loss: 0.0010484695667400956
2023-01-21 13:06:21.672014: step: 520/530, loss: 0.0008975982782430947
2023-01-21 13:06:22.794284: step: 524/530, loss: 0.0001348495570709929
2023-01-21 13:06:23.956364: step: 528/530, loss: 0.003911399748176336
2023-01-21 13:06:25.069006: step: 532/530, loss: 1.4400482541532256e-05
2023-01-21 13:06:26.166975: step: 536/530, loss: 0.00047435759915970266
2023-01-21 13:06:27.318747: step: 540/530, loss: 0.00124616629909724
2023-01-21 13:06:28.420569: step: 544/530, loss: 1.9073486612342094e-07
2023-01-21 13:06:29.525984: step: 548/530, loss: 0.004593181889504194
2023-01-21 13:06:30.668927: step: 552/530, loss: 0.016797829419374466
2023-01-21 13:06:31.786541: step: 556/530, loss: 0.002057743025943637
2023-01-21 13:06:32.927209: step: 560/530, loss: 0.021702002733945847
2023-01-21 13:06:34.058512: step: 564/530, loss: 0.0023875234182924032
2023-01-21 13:06:35.208319: step: 568/530, loss: 0.0002008438023040071
2023-01-21 13:06:36.376098: step: 572/530, loss: 0.00331535330042243
2023-01-21 13:06:37.466852: step: 576/530, loss: 0.00017833709716796875
2023-01-21 13:06:38.593306: step: 580/530, loss: 2.0408631826285273e-05
2023-01-21 13:06:39.703131: step: 584/530, loss: 0.00028476715669967234
2023-01-21 13:06:40.821260: step: 588/530, loss: 0.00017492771439719945
2023-01-21 13:06:41.947675: step: 592/530, loss: 9.403228614246473e-05
2023-01-21 13:06:43.054716: step: 596/530, loss: 0.003907203674316406
2023-01-21 13:06:44.180476: step: 600/530, loss: 0.00012063980102539062
2023-01-21 13:06:45.266138: step: 604/530, loss: 1.5926361811580136e-05
2023-01-21 13:06:46.408621: step: 608/530, loss: 0.00021057129197288305
2023-01-21 13:06:47.576802: step: 612/530, loss: 0.00029411318246275187
2023-01-21 13:06:48.721694: step: 616/530, loss: 0.004790878389030695
2023-01-21 13:06:49.850591: step: 620/530, loss: 0.016141222789883614
2023-01-21 13:06:50.981527: step: 624/530, loss: 0.002587222959846258
2023-01-21 13:06:52.135821: step: 628/530, loss: 1.544952465337701e-05
2023-01-21 13:06:53.264390: step: 632/530, loss: 0.006550264544785023
2023-01-21 13:06:54.408398: step: 636/530, loss: 0.0010014057625085115
2023-01-21 13:06:55.567773: step: 640/530, loss: 0.001595306326635182
2023-01-21 13:06:56.655557: step: 644/530, loss: 0.004620933439582586
2023-01-21 13:06:57.764155: step: 648/530, loss: 0.0006326675647869706
2023-01-21 13:06:58.889477: step: 652/530, loss: 0.0013883591163903475
2023-01-21 13:06:59.991321: step: 656/530, loss: 4.4536591303767636e-05
2023-01-21 13:07:01.129487: step: 660/530, loss: 0.0014127731556072831
2023-01-21 13:07:02.261217: step: 664/530, loss: -3.910064606316155e-06
2023-01-21 13:07:03.376925: step: 668/530, loss: 0.00010194778587901965
2023-01-21 13:07:04.500740: step: 672/530, loss: 0.06518612056970596
2023-01-21 13:07:05.629951: step: 676/530, loss: 6.885529001010582e-05
2023-01-21 13:07:06.743915: step: 680/530, loss: 0.41986677050590515
2023-01-21 13:07:07.890559: step: 684/530, loss: 0.0232512466609478
2023-01-21 13:07:09.003006: step: 688/530, loss: 0.005348491482436657
2023-01-21 13:07:10.126975: step: 692/530, loss: 0.00010385513451183215
2023-01-21 13:07:11.267246: step: 696/530, loss: 0.0030729295685887337
2023-01-21 13:07:12.394968: step: 700/530, loss: 1.5115738278836943e-05
2023-01-21 13:07:13.485388: step: 704/530, loss: 7.114410982467234e-05
2023-01-21 13:07:14.620618: step: 708/530, loss: 0.016547203063964844
2023-01-21 13:07:15.744187: step: 712/530, loss: 0.0819944441318512
2023-01-21 13:07:16.883389: step: 716/530, loss: 0.5335685014724731
2023-01-21 13:07:18.023048: step: 720/530, loss: 1.010894811770413e-05
2023-01-21 13:07:19.137831: step: 724/530, loss: 0.004232502076774836
2023-01-21 13:07:20.239964: step: 728/530, loss: 0.0004566192510537803
2023-01-21 13:07:21.347301: step: 732/530, loss: 0.0017559051048010588
2023-01-21 13:07:22.463736: step: 736/530, loss: 0.00017194748215842992
2023-01-21 13:07:23.573059: step: 740/530, loss: 2.498626781743951e-05
2023-01-21 13:07:24.665117: step: 744/530, loss: 2.28881845032447e-06
2023-01-21 13:07:25.764612: step: 748/530, loss: 0.0025947571266442537
2023-01-21 13:07:26.827233: step: 752/530, loss: 0.00017938614473678172
2023-01-21 13:07:27.929260: step: 756/530, loss: 1.068115216185106e-05
2023-01-21 13:07:29.038752: step: 760/530, loss: 4.615783836925402e-05
2023-01-21 13:07:30.135684: step: 764/530, loss: 1.9264220100012608e-05
2023-01-21 13:07:31.241637: step: 768/530, loss: 5.264282663119957e-05
2023-01-21 13:07:32.372965: step: 772/530, loss: 0.00030498503474518657
2023-01-21 13:07:33.519144: step: 776/530, loss: 0.0012316711945459247
2023-01-21 13:07:34.652322: step: 780/530, loss: 0.020836448296904564
2023-01-21 13:07:35.778940: step: 784/530, loss: 0.020872116088867188
2023-01-21 13:07:36.930686: step: 788/530, loss: 0.01145782507956028
2023-01-21 13:07:38.060709: step: 792/530, loss: 5.614757537841797e-05
2023-01-21 13:07:39.186248: step: 796/530, loss: 0.0015381812117993832
2023-01-21 13:07:40.285669: step: 800/530, loss: 0.005966472905129194
2023-01-21 13:07:41.420857: step: 804/530, loss: 0.04548397287726402
2023-01-21 13:07:42.561355: step: 808/530, loss: 5.645752025884576e-05
2023-01-21 13:07:43.669602: step: 812/530, loss: 0.025250960141420364
2023-01-21 13:07:44.792007: step: 816/530, loss: 0.0008625984191894531
2023-01-21 13:07:45.930683: step: 820/530, loss: 0.01715412177145481
2023-01-21 13:07:47.049501: step: 824/530, loss: 0.0003951072576455772
2023-01-21 13:07:48.178806: step: 828/530, loss: 0.0012468575732782483
2023-01-21 13:07:49.313644: step: 832/530, loss: 0.1317061483860016
2023-01-21 13:07:50.441928: step: 836/530, loss: 0.00038466454134322703
2023-01-21 13:07:51.541762: step: 840/530, loss: 0.0006875991821289062
2023-01-21 13:07:52.667897: step: 844/530, loss: 0.011688805185258389
2023-01-21 13:07:53.833789: step: 848/530, loss: 0.013722610659897327
2023-01-21 13:07:54.958757: step: 852/530, loss: 0.0010877609020099044
2023-01-21 13:07:56.083812: step: 856/530, loss: 0.0003499865415506065
2023-01-21 13:07:57.189845: step: 860/530, loss: 0.0004296302795410156
2023-01-21 13:07:58.297340: step: 864/530, loss: 0.007331180851906538
2023-01-21 13:07:59.454118: step: 868/530, loss: 0.0002984285238198936
2023-01-21 13:08:00.557644: step: 872/530, loss: 0.0015621185302734375
2023-01-21 13:08:01.682358: step: 876/530, loss: 0.03164386749267578
2023-01-21 13:08:02.841571: step: 880/530, loss: 0.0001636505185160786
2023-01-21 13:08:04.017190: step: 884/530, loss: 0.008465575985610485
2023-01-21 13:08:05.156832: step: 888/530, loss: 0.007383919321000576
2023-01-21 13:08:06.242293: step: 892/530, loss: 0.005424213595688343
2023-01-21 13:08:07.354438: step: 896/530, loss: 8.96453857421875e-05
2023-01-21 13:08:08.484454: step: 900/530, loss: 0.000993442488834262
2023-01-21 13:08:09.610482: step: 904/530, loss: 0.015662193298339844
2023-01-21 13:08:10.724009: step: 908/530, loss: 0.005560874938964844
2023-01-21 13:08:11.834568: step: 912/530, loss: 0.010552024468779564
2023-01-21 13:08:12.965106: step: 916/530, loss: 0.00017433166794944555
2023-01-21 13:08:14.097548: step: 920/530, loss: 0.06706476956605911
2023-01-21 13:08:15.196340: step: 924/530, loss: 0.0013353824615478516
2023-01-21 13:08:16.340142: step: 928/530, loss: 1.983642505365424e-05
2023-01-21 13:08:17.474912: step: 932/530, loss: 0.0017625809414312243
2023-01-21 13:08:18.582727: step: 936/530, loss: 0.0002804756222758442
2023-01-21 13:08:19.725589: step: 940/530, loss: 0.00341205601580441
2023-01-21 13:08:20.847486: step: 944/530, loss: 0.002634239150211215
2023-01-21 13:08:21.934358: step: 948/530, loss: 0.014643574133515358
2023-01-21 13:08:23.044382: step: 952/530, loss: 0.0036361694801598787
2023-01-21 13:08:24.164622: step: 956/530, loss: 0.01740856096148491
2023-01-21 13:08:25.271824: step: 960/530, loss: 0.00014095305232331157
2023-01-21 13:08:26.379880: step: 964/530, loss: 0.056245993822813034
2023-01-21 13:08:27.504452: step: 968/530, loss: 0.03258171305060387
2023-01-21 13:08:28.638964: step: 972/530, loss: 0.017430592328310013
2023-01-21 13:08:29.751492: step: 976/530, loss: 0.02619628794491291
2023-01-21 13:08:30.859945: step: 980/530, loss: 0.0001300811709370464
2023-01-21 13:08:31.963530: step: 984/530, loss: 0.10193977504968643
2023-01-21 13:08:33.121705: step: 988/530, loss: 0.00136146554723382
2023-01-21 13:08:34.277077: step: 992/530, loss: 0.004538345150649548
2023-01-21 13:08:35.393545: step: 996/530, loss: 0.0016731263604015112
2023-01-21 13:08:36.499870: step: 1000/530, loss: -1.7166138377433526e-06
2023-01-21 13:08:37.617654: step: 1004/530, loss: 0.013771867379546165
2023-01-21 13:08:38.727933: step: 1008/530, loss: 0.07266059517860413
2023-01-21 13:08:39.874821: step: 1012/530, loss: 0.001842546509578824
2023-01-21 13:08:41.015024: step: 1016/530, loss: 0.0002815246698446572
2023-01-21 13:08:42.131814: step: 1020/530, loss: 4.854202416026965e-05
2023-01-21 13:08:43.287123: step: 1024/530, loss: 0.005524826236069202
2023-01-21 13:08:44.386766: step: 1028/530, loss: 0.05985851213335991
2023-01-21 13:08:45.493817: step: 1032/530, loss: 0.0035312653053551912
2023-01-21 13:08:46.598850: step: 1036/530, loss: 0.0004207015153951943
2023-01-21 13:08:47.708599: step: 1040/530, loss: 0.03308238834142685
2023-01-21 13:08:48.822152: step: 1044/530, loss: 0.13214130699634552
2023-01-21 13:08:49.943194: step: 1048/530, loss: 0.005187607370316982
2023-01-21 13:08:51.099730: step: 1052/530, loss: 0.0027896880637854338
2023-01-21 13:08:52.203288: step: 1056/530, loss: 0.03146076202392578
2023-01-21 13:08:53.330065: step: 1060/530, loss: 7.896423630882055e-05
2023-01-21 13:08:54.466074: step: 1064/530, loss: 0.0002637862926349044
2023-01-21 13:08:55.572033: step: 1068/530, loss: 0.015247821807861328
2023-01-21 13:08:56.697709: step: 1072/530, loss: 0.01875896565616131
2023-01-21 13:08:57.851100: step: 1076/530, loss: 0.011057281866669655
2023-01-21 13:08:58.943122: step: 1080/530, loss: 0.00037031175452284515
2023-01-21 13:09:00.047572: step: 1084/530, loss: 1.2779236385540571e-05
2023-01-21 13:09:01.184237: step: 1088/530, loss: 0.005370521917939186
2023-01-21 13:09:02.326377: step: 1092/530, loss: 0.0018253326416015625
2023-01-21 13:09:03.446505: step: 1096/530, loss: 0.0002666473446879536
2023-01-21 13:09:04.572372: step: 1100/530, loss: 0.00074090959969908
2023-01-21 13:09:05.682914: step: 1104/530, loss: 0.00038595200749114156
2023-01-21 13:09:06.795760: step: 1108/530, loss: 0.0001293182431254536
2023-01-21 13:09:07.929109: step: 1112/530, loss: 0.006157493684440851
2023-01-21 13:09:09.057092: step: 1116/530, loss: 0.01682724989950657
2023-01-21 13:09:10.173426: step: 1120/530, loss: 0.0002501726266928017
2023-01-21 13:09:11.300913: step: 1124/530, loss: 0.013865041546523571
2023-01-21 13:09:12.415209: step: 1128/530, loss: 0.009752177633345127
2023-01-21 13:09:13.514374: step: 1132/530, loss: 0.030916595831513405
2023-01-21 13:09:14.649707: step: 1136/530, loss: 0.0061159138567745686
2023-01-21 13:09:15.782938: step: 1140/530, loss: 0.0012445449829101562
2023-01-21 13:09:16.938848: step: 1144/530, loss: 0.010038471780717373
2023-01-21 13:09:18.074803: step: 1148/530, loss: 0.0036173821426928043
2023-01-21 13:09:19.202435: step: 1152/530, loss: 0.004916477017104626
2023-01-21 13:09:20.345991: step: 1156/530, loss: 0.006425237748771906
2023-01-21 13:09:21.442341: step: 1160/530, loss: 0.011096763424575329
2023-01-21 13:09:22.553789: step: 1164/530, loss: 0.042576029896736145
2023-01-21 13:09:23.662476: step: 1168/530, loss: 1.6689300537109375e-05
2023-01-21 13:09:24.783809: step: 1172/530, loss: 0.0052394866943359375
2023-01-21 13:09:25.914033: step: 1176/530, loss: 0.0002004623383982107
2023-01-21 13:09:27.022972: step: 1180/530, loss: 0.005846595391631126
2023-01-21 13:09:28.157768: step: 1184/530, loss: 0.017639541998505592
2023-01-21 13:09:29.271153: step: 1188/530, loss: 6.86645489622606e-06
2023-01-21 13:09:30.389500: step: 1192/530, loss: 0.0014862060779705644
2023-01-21 13:09:31.533323: step: 1196/530, loss: 8.58306884765625e-06
2023-01-21 13:09:32.674552: step: 1200/530, loss: 0.00046100615873001516
2023-01-21 13:09:33.831059: step: 1204/530, loss: 0.0007658958784304559
2023-01-21 13:09:34.946604: step: 1208/530, loss: 0.00031156541081145406
2023-01-21 13:09:36.093987: step: 1212/530, loss: 1.8119812921213452e-06
2023-01-21 13:09:37.244472: step: 1216/530, loss: 0.10358409583568573
2023-01-21 13:09:38.397242: step: 1220/530, loss: 0.000763368618208915
2023-01-21 13:09:39.540172: step: 1224/530, loss: 0.04680747911334038
2023-01-21 13:09:40.673526: step: 1228/530, loss: 0.014463615603744984
2023-01-21 13:09:41.785133: step: 1232/530, loss: 6.027221752447076e-05
2023-01-21 13:09:42.931016: step: 1236/530, loss: 0.022798538208007812
2023-01-21 13:09:44.030304: step: 1240/530, loss: 0.0004942893865518272
2023-01-21 13:09:45.174861: step: 1244/530, loss: 9.741782560013235e-05
2023-01-21 13:09:46.298711: step: 1248/530, loss: 0.007168960757553577
2023-01-21 13:09:47.411796: step: 1252/530, loss: 0.0031770707573741674
2023-01-21 13:09:48.516624: step: 1256/530, loss: 0.002415275666862726
2023-01-21 13:09:49.625604: step: 1260/530, loss: 0.00013618469529319555
2023-01-21 13:09:50.762329: step: 1264/530, loss: 0.00024662018404342234
2023-01-21 13:09:51.886891: step: 1268/530, loss: 0.0018333435291424394
2023-01-21 13:09:53.003133: step: 1272/530, loss: 0.0004924774402752519
2023-01-21 13:09:54.141899: step: 1276/530, loss: 0.16675598919391632
2023-01-21 13:09:55.253554: step: 1280/530, loss: 0.00046749116154387593
2023-01-21 13:09:56.394270: step: 1284/530, loss: 0.057106971740722656
2023-01-21 13:09:57.525908: step: 1288/530, loss: 0.0016298294067382812
2023-01-21 13:09:58.677378: step: 1292/530, loss: 8.296967280330136e-06
2023-01-21 13:09:59.798791: step: 1296/530, loss: 2.0980836779926904e-05
2023-01-21 13:10:00.922130: step: 1300/530, loss: 0.00020179747662041336
2023-01-21 13:10:02.035356: step: 1304/530, loss: 0.0008107185713015497
2023-01-21 13:10:03.185584: step: 1308/530, loss: 0.024582862854003906
2023-01-21 13:10:04.323535: step: 1312/530, loss: 0.003043937962502241
2023-01-21 13:10:05.453442: step: 1316/530, loss: 0.015055847354233265
2023-01-21 13:10:06.558072: step: 1320/530, loss: 0.003883600467815995
2023-01-21 13:10:07.701613: step: 1324/530, loss: 0.018159104511141777
2023-01-21 13:10:08.792210: step: 1328/530, loss: 1.735687328618951e-05
2023-01-21 13:10:09.883609: step: 1332/530, loss: 0.0008635520935058594
2023-01-21 13:10:11.000725: step: 1336/530, loss: 0.002245235489681363
2023-01-21 13:10:12.126608: step: 1340/530, loss: 0.009093952365219593
2023-01-21 13:10:13.256886: step: 1344/530, loss: 4.649162292480469e-05
2023-01-21 13:10:14.389333: step: 1348/530, loss: 6.599426706088707e-05
2023-01-21 13:10:15.511872: step: 1352/530, loss: 4.482269287109375e-05
2023-01-21 13:10:16.618560: step: 1356/530, loss: 0.015350389294326305
2023-01-21 13:10:17.729146: step: 1360/530, loss: 0.0002157211274607107
2023-01-21 13:10:18.870729: step: 1364/530, loss: 0.02983551099896431
2023-01-21 13:10:19.994951: step: 1368/530, loss: 0.007845520973205566
2023-01-21 13:10:21.112026: step: 1372/530, loss: 3.490447852527723e-05
2023-01-21 13:10:22.249375: step: 1376/530, loss: 0.00030803680419921875
2023-01-21 13:10:23.375959: step: 1380/530, loss: 0.001906585763208568
2023-01-21 13:10:24.490203: step: 1384/530, loss: 0.006847381591796875
2023-01-21 13:10:25.596816: step: 1388/530, loss: 6.027222116244957e-05
2023-01-21 13:10:26.699252: step: 1392/530, loss: 6.580352874152595e-06
2023-01-21 13:10:27.813958: step: 1396/530, loss: 5.626678466796875e-05
2023-01-21 13:10:28.945779: step: 1400/530, loss: 0.0010696888202801347
2023-01-21 13:10:30.080857: step: 1404/530, loss: 0.0048417565412819386
2023-01-21 13:10:31.203413: step: 1408/530, loss: 0.001983833499252796
2023-01-21 13:10:32.347097: step: 1412/530, loss: 0.010224675759673119
2023-01-21 13:10:33.479968: step: 1416/530, loss: 0.0007465362432412803
2023-01-21 13:10:34.596469: step: 1420/530, loss: 0.0054306029342114925
2023-01-21 13:10:35.722729: step: 1424/530, loss: 0.0017053603660315275
2023-01-21 13:10:36.853693: step: 1428/530, loss: 0.036640215665102005
2023-01-21 13:10:38.040443: step: 1432/530, loss: 4.291534423828125e-05
2023-01-21 13:10:39.158280: step: 1436/530, loss: 0.0002693176211323589
2023-01-21 13:10:40.246318: step: 1440/530, loss: 3.175735764671117e-05
2023-01-21 13:10:41.377465: step: 1444/530, loss: 9.956360008800402e-05
2023-01-21 13:10:42.514678: step: 1448/530, loss: 0.00011529923358466476
2023-01-21 13:10:43.659602: step: 1452/530, loss: 0.006119919009506702
2023-01-21 13:10:44.779615: step: 1456/530, loss: 3.986358569818549e-05
2023-01-21 13:10:45.886225: step: 1460/530, loss: 1.6689300537109375e-05
2023-01-21 13:10:47.018252: step: 1464/530, loss: 0.0012575149303302169
2023-01-21 13:10:48.109533: step: 1468/530, loss: 0.00020465851412154734
2023-01-21 13:10:49.265404: step: 1472/530, loss: 0.007644271943718195
2023-01-21 13:10:50.392265: step: 1476/530, loss: 0.0014940261607989669
2023-01-21 13:10:51.499269: step: 1480/530, loss: 0.0002783775271382183
2023-01-21 13:10:52.601940: step: 1484/530, loss: 2.7084352041129023e-05
2023-01-21 13:10:53.725548: step: 1488/530, loss: 5.664825584972277e-05
2023-01-21 13:10:54.840680: step: 1492/530, loss: 0.02048635482788086
2023-01-21 13:10:55.950105: step: 1496/530, loss: 0.0001255035458598286
2023-01-21 13:10:57.115176: step: 1500/530, loss: 0.006630897521972656
2023-01-21 13:10:58.225757: step: 1504/530, loss: 0.0014611243968829513
2023-01-21 13:10:59.360433: step: 1508/530, loss: 4.501342846197076e-05
2023-01-21 13:11:00.493585: step: 1512/530, loss: 0.03195362165570259
2023-01-21 13:11:01.610474: step: 1516/530, loss: 0.004269409459084272
2023-01-21 13:11:02.721979: step: 1520/530, loss: 0.00227699289098382
2023-01-21 13:11:03.837523: step: 1524/530, loss: 0.0019541741348803043
2023-01-21 13:11:04.943547: step: 1528/530, loss: 7.939338684082031e-05
2023-01-21 13:11:06.067489: step: 1532/530, loss: 4.301071385270916e-05
2023-01-21 13:11:07.195851: step: 1536/530, loss: 4.1961669921875e-05
2023-01-21 13:11:08.313110: step: 1540/530, loss: 9.403228614246473e-05
2023-01-21 13:11:09.440678: step: 1544/530, loss: 0.0020787238609045744
2023-01-21 13:11:10.559829: step: 1548/530, loss: 0.0001968383730854839
2023-01-21 13:11:11.679850: step: 1552/530, loss: 1.1157989320054185e-05
2023-01-21 13:11:12.809263: step: 1556/530, loss: 0.009734916500747204
2023-01-21 13:11:13.924734: step: 1560/530, loss: 0.0025604248512536287
2023-01-21 13:11:15.038651: step: 1564/530, loss: 0.22236642241477966
2023-01-21 13:11:16.150780: step: 1568/530, loss: 0.0002880096435546875
2023-01-21 13:11:17.266780: step: 1572/530, loss: 0.008819961920380592
2023-01-21 13:11:18.388339: step: 1576/530, loss: 0.019545985385775566
2023-01-21 13:11:19.496722: step: 1580/530, loss: 0.0009176731109619141
2023-01-21 13:11:20.585005: step: 1584/530, loss: 0.00021247864060569555
2023-01-21 13:11:21.732099: step: 1588/530, loss: 0.03221883997321129
2023-01-21 13:11:22.827591: step: 1592/530, loss: 0.03220844268798828
2023-01-21 13:11:23.951907: step: 1596/530, loss: 0.012983512133359909
2023-01-21 13:11:25.077936: step: 1600/530, loss: 8.640289161121473e-05
2023-01-21 13:11:26.199023: step: 1604/530, loss: 0.0003018379211425781
2023-01-21 13:11:27.321774: step: 1608/530, loss: 0.0004072189040016383
2023-01-21 13:11:28.450295: step: 1612/530, loss: 0.022624395787715912
2023-01-21 13:11:29.581401: step: 1616/530, loss: 0.046590711921453476
2023-01-21 13:11:30.688318: step: 1620/530, loss: 6.771087646484375e-05
2023-01-21 13:11:31.802103: step: 1624/530, loss: 0.0033524036407470703
2023-01-21 13:11:32.944829: step: 1628/530, loss: 0.007813072763383389
2023-01-21 13:11:34.069097: step: 1632/530, loss: 0.0018060685833916068
2023-01-21 13:11:35.220570: step: 1636/530, loss: 0.00040330886258743703
2023-01-21 13:11:36.322926: step: 1640/530, loss: 0.008052635006606579
2023-01-21 13:11:37.424042: step: 1644/530, loss: 1.1682344675064087
2023-01-21 13:11:38.567299: step: 1648/530, loss: 0.011875866912305355
2023-01-21 13:11:39.702109: step: 1652/530, loss: 0.03361182287335396
2023-01-21 13:11:40.805824: step: 1656/530, loss: 0.04020567238330841
2023-01-21 13:11:41.933248: step: 1660/530, loss: 0.0005714416620321572
2023-01-21 13:11:43.053382: step: 1664/530, loss: 0.0517704002559185
2023-01-21 13:11:44.171822: step: 1668/530, loss: 0.0002430439053568989
2023-01-21 13:11:45.277213: step: 1672/530, loss: 6.337166269076988e-05
2023-01-21 13:11:46.407391: step: 1676/530, loss: 0.037123870104551315
2023-01-21 13:11:47.503352: step: 1680/530, loss: 0.0031475068535655737
2023-01-21 13:11:48.641645: step: 1684/530, loss: 0.0074204448610544205
2023-01-21 13:11:49.729317: step: 1688/530, loss: 7.869302862673067e-06
2023-01-21 13:11:50.862823: step: 1692/530, loss: 0.007393646519631147
2023-01-21 13:11:51.972834: step: 1696/530, loss: 0.00017261505126953125
2023-01-21 13:11:53.094299: step: 1700/530, loss: 0.014226150698959827
2023-01-21 13:11:54.217841: step: 1704/530, loss: 9.860992577159777e-05
2023-01-21 13:11:55.316080: step: 1708/530, loss: 7.82012939453125e-05
2023-01-21 13:11:56.435906: step: 1712/530, loss: 0.00041618349496275187
2023-01-21 13:11:57.561609: step: 1716/530, loss: 0.02533740922808647
2023-01-21 13:11:58.671658: step: 1720/530, loss: 0.00488891638815403
2023-01-21 13:11:59.790313: step: 1724/530, loss: 0.016846656799316406
2023-01-21 13:12:00.915994: step: 1728/530, loss: 0.025334740057587624
2023-01-21 13:12:02.020950: step: 1732/530, loss: 0.0005181789165362716
2023-01-21 13:12:03.138426: step: 1736/530, loss: 0.012012195773422718
2023-01-21 13:12:04.247940: step: 1740/530, loss: 0.0005353927263058722
2023-01-21 13:12:05.400124: step: 1744/530, loss: 0.0018595695728436112
2023-01-21 13:12:06.491779: step: 1748/530, loss: 0.00014209745859261602
2023-01-21 13:12:07.615107: step: 1752/530, loss: 0.02372569963335991
2023-01-21 13:12:08.703600: step: 1756/530, loss: 0.019558431580662727
2023-01-21 13:12:09.792351: step: 1760/530, loss: 0.0005163192981854081
2023-01-21 13:12:10.877517: step: 1764/530, loss: 0.003431129502132535
2023-01-21 13:12:12.007865: step: 1768/530, loss: 0.025853728875517845
2023-01-21 13:12:13.125686: step: 1772/530, loss: 0.0009540558094158769
2023-01-21 13:12:14.240716: step: 1776/530, loss: 6.198883056640625e-05
2023-01-21 13:12:15.356415: step: 1780/530, loss: 0.0013238907558843493
2023-01-21 13:12:16.504214: step: 1784/530, loss: 0.0002556800900492817
2023-01-21 13:12:17.607808: step: 1788/530, loss: 0.00785675086081028
2023-01-21 13:12:18.750662: step: 1792/530, loss: 0.003692626953125
2023-01-21 13:12:19.865960: step: 1796/530, loss: 0.0002907276211772114
2023-01-21 13:12:20.935371: step: 1800/530, loss: 0.001292371773160994
2023-01-21 13:12:22.084697: step: 1804/530, loss: 0.06846971809864044
2023-01-21 13:12:23.225222: step: 1808/530, loss: 0.005768203642219305
2023-01-21 13:12:24.367797: step: 1812/530, loss: 0.0014713286655023694
2023-01-21 13:12:25.479503: step: 1816/530, loss: 0.005811834707856178
2023-01-21 13:12:26.614293: step: 1820/530, loss: 0.03165092691779137
2023-01-21 13:12:27.714426: step: 1824/530, loss: 0.0002092361537506804
2023-01-21 13:12:28.841474: step: 1828/530, loss: 0.027503110468387604
2023-01-21 13:12:29.966037: step: 1832/530, loss: 0.00041007998515851796
2023-01-21 13:12:31.097380: step: 1836/530, loss: 0.0001643180730752647
2023-01-21 13:12:32.187600: step: 1840/530, loss: 0.00012750625319313258
2023-01-21 13:12:33.303805: step: 1844/530, loss: 0.02797517739236355
2023-01-21 13:12:34.439225: step: 1848/530, loss: -7.247924258990679e-06
2023-01-21 13:12:35.577805: step: 1852/530, loss: 0.03835906833410263
2023-01-21 13:12:36.692353: step: 1856/530, loss: 0.00023431777663063258
2023-01-21 13:12:37.796996: step: 1860/530, loss: 0.0013417245354503393
2023-01-21 13:12:38.918144: step: 1864/530, loss: 0.00025243760319426656
2023-01-21 13:12:40.103055: step: 1868/530, loss: 0.592681348323822
2023-01-21 13:12:41.209842: step: 1872/530, loss: 4.363059997558594e-05
2023-01-21 13:12:42.324884: step: 1876/530, loss: 0.00028705596923828125
2023-01-21 13:12:43.433871: step: 1880/530, loss: 0.0006261825328692794
2023-01-21 13:12:44.598551: step: 1884/530, loss: 0.0007724761962890625
2023-01-21 13:12:45.727197: step: 1888/530, loss: 0.005222320556640625
2023-01-21 13:12:46.879247: step: 1892/530, loss: 0.0003673553583212197
2023-01-21 13:12:48.025951: step: 1896/530, loss: 0.0006048202631063759
2023-01-21 13:12:49.128368: step: 1900/530, loss: 0.0020086290314793587
2023-01-21 13:12:50.282424: step: 1904/530, loss: 0.0031676292419433594
2023-01-21 13:12:51.407849: step: 1908/530, loss: 0.0010183334816247225
2023-01-21 13:12:52.494774: step: 1912/530, loss: 0.01344757154583931
2023-01-21 13:12:53.619232: step: 1916/530, loss: -1.3828277587890625e-05
2023-01-21 13:12:54.747018: step: 1920/530, loss: 0.0010087013943120837
2023-01-21 13:12:55.881814: step: 1924/530, loss: 0.007440090179443359
2023-01-21 13:12:56.986153: step: 1928/530, loss: 0.004156017675995827
2023-01-21 13:12:58.114644: step: 1932/530, loss: 0.11128578335046768
2023-01-21 13:12:59.240046: step: 1936/530, loss: 0.0009811401832848787
2023-01-21 13:13:00.377610: step: 1940/530, loss: 0.00010204315913142636
2023-01-21 13:13:01.506216: step: 1944/530, loss: 0.006575584877282381
2023-01-21 13:13:02.641723: step: 1948/530, loss: 1.100994348526001
2023-01-21 13:13:03.777186: step: 1952/530, loss: 0.000194549560546875
2023-01-21 13:13:04.896890: step: 1956/530, loss: 0.026674749329686165
2023-01-21 13:13:06.050460: step: 1960/530, loss: 0.0002344131498830393
2023-01-21 13:13:07.195217: step: 1964/530, loss: 0.15680675208568573
2023-01-21 13:13:08.338269: step: 1968/530, loss: 0.00011682510375976562
2023-01-21 13:13:09.457850: step: 1972/530, loss: 0.00018057823763228953
2023-01-21 13:13:10.566938: step: 1976/530, loss: 0.01435403898358345
2023-01-21 13:13:11.686332: step: 1980/530, loss: 0.02198333665728569
2023-01-21 13:13:12.831230: step: 1984/530, loss: 0.00907211285084486
2023-01-21 13:13:13.978879: step: 1988/530, loss: 0.0008563041919842362
2023-01-21 13:13:15.124208: step: 1992/530, loss: 0.022344589233398438
2023-01-21 13:13:16.255121: step: 1996/530, loss: 0.00015454292588401586
2023-01-21 13:13:17.411293: step: 2000/530, loss: 5.378723290050402e-05
2023-01-21 13:13:18.528537: step: 2004/530, loss: 0.0005068778991699219
2023-01-21 13:13:19.639901: step: 2008/530, loss: 0.00240325927734375
2023-01-21 13:13:20.775054: step: 2012/530, loss: 0.35337141156196594
2023-01-21 13:13:21.885304: step: 2016/530, loss: 0.0015651703579351306
2023-01-21 13:13:22.998544: step: 2020/530, loss: 0.00012373924255371094
2023-01-21 13:13:24.088534: step: 2024/530, loss: 7.743835885776207e-05
2023-01-21 13:13:25.216911: step: 2028/530, loss: 0.01382293738424778
2023-01-21 13:13:26.354397: step: 2032/530, loss: 0.0010234832298010588
2023-01-21 13:13:27.499616: step: 2036/530, loss: 0.00421638460829854
2023-01-21 13:13:28.597822: step: 2040/530, loss: 4.968643406755291e-05
2023-01-21 13:13:29.762799: step: 2044/530, loss: 0.016026116907596588
2023-01-21 13:13:30.917829: step: 2048/530, loss: 0.0012573242420330644
2023-01-21 13:13:32.039981: step: 2052/530, loss: 0.0010458945762366056
2023-01-21 13:13:33.196612: step: 2056/530, loss: 8.640289161121473e-05
2023-01-21 13:13:34.289763: step: 2060/530, loss: 0.0007375717395916581
2023-01-21 13:13:35.407886: step: 2064/530, loss: 0.0022235752549022436
2023-01-21 13:13:36.528862: step: 2068/530, loss: 0.009613800793886185
2023-01-21 13:13:37.679951: step: 2072/530, loss: 0.2942659258842468
2023-01-21 13:13:38.803993: step: 2076/530, loss: 0.002518558641895652
2023-01-21 13:13:39.922285: step: 2080/530, loss: 3.0994415283203125e-05
2023-01-21 13:13:41.027970: step: 2084/530, loss: 0.007765007205307484
2023-01-21 13:13:42.127753: step: 2088/530, loss: 0.0009613037109375
2023-01-21 13:13:43.230703: step: 2092/530, loss: -5.626678102998994e-06
2023-01-21 13:13:44.353778: step: 2096/530, loss: 0.015579604543745518
2023-01-21 13:13:45.468340: step: 2100/530, loss: 0.016611386090517044
2023-01-21 13:13:46.610225: step: 2104/530, loss: 0.0009471416706219316
2023-01-21 13:13:47.761678: step: 2108/530, loss: 0.02815227583050728
2023-01-21 13:13:48.886921: step: 2112/530, loss: 0.014848137274384499
2023-01-21 13:13:50.026781: step: 2116/530, loss: 0.0022672652266919613
2023-01-21 13:13:51.140213: step: 2120/530, loss: 6.704330735374242e-05
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.7272727272727273, 'r': 0.5079365079365079, 'f1': 0.5981308411214953}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.43902439024390244, 'r': 0.5, 'f1': 0.4675324675324676}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 13:14:40.206762: step: 4/530, loss: 1.33514404296875e-05
2023-01-21 13:14:41.330785: step: 8/530, loss: 0.0006963729974813759
2023-01-21 13:14:42.513539: step: 12/530, loss: 8.106231689453125e-05
2023-01-21 13:14:43.622569: step: 16/530, loss: 1.468658410885837e-05
2023-01-21 13:14:44.747115: step: 20/530, loss: 0.0013601303799077868
2023-01-21 13:14:45.861225: step: 24/530, loss: 0.0007113456376828253
2023-01-21 13:14:47.009707: step: 28/530, loss: 0.00274486537091434
2023-01-21 13:14:48.147042: step: 32/530, loss: -2.670288040462765e-06
2023-01-21 13:14:49.284860: step: 36/530, loss: 0.00011882781836902723
2023-01-21 13:14:50.453370: step: 40/530, loss: 0.005424118135124445
2023-01-21 13:14:51.525594: step: 44/530, loss: -9.5367431640625e-07
2023-01-21 13:14:52.665547: step: 48/530, loss: 0.00010614395432639867
2023-01-21 13:14:53.772603: step: 52/530, loss: 0.0004831314436160028
2023-01-21 13:14:54.878793: step: 56/530, loss: 0.014301871880888939
2023-01-21 13:14:55.996963: step: 60/530, loss: 0.000858306884765625
2023-01-21 13:14:57.113782: step: 64/530, loss: 0.0006476402631960809
2023-01-21 13:14:58.237014: step: 68/530, loss: 0.003938865382224321
2023-01-21 13:14:59.369793: step: 72/530, loss: 0.00041408539982512593
2023-01-21 13:15:00.488419: step: 76/530, loss: 4.76837158203125e-05
2023-01-21 13:15:01.648648: step: 80/530, loss: 0.0008131027570925653
2023-01-21 13:15:02.792833: step: 84/530, loss: 0.0008766173850744963
2023-01-21 13:15:03.885951: step: 88/530, loss: 0.04265327379107475
2023-01-21 13:15:04.996471: step: 92/530, loss: 0.036463167518377304
2023-01-21 13:15:06.139442: step: 96/530, loss: 0.0019070626003667712
2023-01-21 13:15:07.265503: step: 100/530, loss: 0.0002019882231252268
2023-01-21 13:15:08.374318: step: 104/530, loss: 0.0002971649228129536
2023-01-21 13:15:09.496821: step: 108/530, loss: 0.016480350866913795
2023-01-21 13:15:10.623257: step: 112/530, loss: 0.00013418197340797633
2023-01-21 13:15:11.785827: step: 116/530, loss: 0.011288833804428577
2023-01-21 13:15:12.895716: step: 120/530, loss: 0.00025691985501907766
2023-01-21 13:15:14.026380: step: 124/530, loss: 0.00043830869253724813
2023-01-21 13:15:15.137391: step: 128/530, loss: 0.07729263603687286
2023-01-21 13:15:16.253564: step: 132/530, loss: -5.14984139954322e-06
2023-01-21 13:15:17.400830: step: 136/530, loss: 0.02654714696109295
2023-01-21 13:15:18.506672: step: 140/530, loss: 0.00045671462430618703
2023-01-21 13:15:19.613858: step: 144/530, loss: 1.1825562069134321e-05
2023-01-21 13:15:20.743926: step: 148/530, loss: 3.4809112548828125e-05
2023-01-21 13:15:21.871430: step: 152/530, loss: 7.266998727573082e-05
2023-01-21 13:15:22.989341: step: 156/530, loss: 0.016576863825321198
2023-01-21 13:15:24.128731: step: 160/530, loss: 0.0014238357543945312
2023-01-21 13:15:25.251884: step: 164/530, loss: 7.62939453125e-06
2023-01-21 13:15:26.378012: step: 168/530, loss: 0.0010342597961425781
2023-01-21 13:15:27.507410: step: 172/530, loss: 0.0012835502857342362
2023-01-21 13:15:28.646050: step: 176/530, loss: 0.005591964814811945
2023-01-21 13:15:29.769940: step: 180/530, loss: 0.00033483505831100047
2023-01-21 13:15:30.912380: step: 184/530, loss: 0.0006264210096560419
2023-01-21 13:15:32.034525: step: 188/530, loss: 9.803772263694555e-05
2023-01-21 13:15:33.150559: step: 192/530, loss: 2.28881845032447e-06
2023-01-21 13:15:34.249724: step: 196/530, loss: 0.00018615723820403218
2023-01-21 13:15:35.383899: step: 200/530, loss: 0.2512466311454773
2023-01-21 13:15:36.486624: step: 204/530, loss: 0.00427856482565403
2023-01-21 13:15:37.607579: step: 208/530, loss: 0.00813751295208931
2023-01-21 13:15:38.720695: step: 212/530, loss: 0.0011535644298419356
2023-01-21 13:15:39.871062: step: 216/530, loss: 0.00887308083474636
2023-01-21 13:15:40.985843: step: 220/530, loss: 5.588532076217234e-05
2023-01-21 13:15:42.110755: step: 224/530, loss: 0.0004654884396586567
2023-01-21 13:15:43.257970: step: 228/530, loss: 0.014969062991440296
2023-01-21 13:15:44.383032: step: 232/530, loss: 0.011599540710449219
2023-01-21 13:15:45.491533: step: 236/530, loss: 0.0003757476806640625
2023-01-21 13:15:46.616501: step: 240/530, loss: 0.0004986763233318925
2023-01-21 13:15:47.739946: step: 244/530, loss: 0.001185464789159596
2023-01-21 13:15:48.898421: step: 248/530, loss: 0.0018226623069494963
2023-01-21 13:15:50.010878: step: 252/530, loss: 1.544952465337701e-05
2023-01-21 13:15:51.129056: step: 256/530, loss: 0.0035889626014977694
2023-01-21 13:15:52.241201: step: 260/530, loss: 0.0015499115688726306
2023-01-21 13:15:53.370303: step: 264/530, loss: 0.0005758285406045616
2023-01-21 13:15:54.505739: step: 268/530, loss: 0.05413246527314186
2023-01-21 13:15:55.640908: step: 272/530, loss: 0.029965590685606003
2023-01-21 13:15:56.763104: step: 276/530, loss: 0.00231170654296875
2023-01-21 13:15:57.925027: step: 280/530, loss: 0.0001237869291799143
2023-01-21 13:15:59.049631: step: 284/530, loss: 4.08649466407951e-05
2023-01-21 13:16:00.152082: step: 288/530, loss: 0.00018892288790084422
2023-01-21 13:16:01.268653: step: 292/530, loss: 0.0002837181091308594
2023-01-21 13:16:02.424094: step: 296/530, loss: 0.0016630173195153475
2023-01-21 13:16:03.551204: step: 300/530, loss: 0.00010814666893566027
2023-01-21 13:16:04.660993: step: 304/530, loss: 5.626678830594756e-05
2023-01-21 13:16:05.776907: step: 308/530, loss: 0.01047420408576727
2023-01-21 13:16:06.913739: step: 312/530, loss: 0.023032475262880325
2023-01-21 13:16:08.014464: step: 316/530, loss: 7.329694926738739e-05
2023-01-21 13:16:09.112507: step: 320/530, loss: 3.623962356869015e-06
2023-01-21 13:16:10.239659: step: 324/530, loss: 0.0005151748191565275
2023-01-21 13:16:11.372733: step: 328/530, loss: 1.9073486328125e-05
2023-01-21 13:16:12.492510: step: 332/530, loss: 0.00022001266188453883
2023-01-21 13:16:13.595369: step: 336/530, loss: 6.794929504394531e-05
2023-01-21 13:16:14.720712: step: 340/530, loss: 9.260177466785535e-05
2023-01-21 13:16:15.852728: step: 344/530, loss: -4.100799742445815e-06
2023-01-21 13:16:16.980365: step: 348/530, loss: 0.00023689270892646164
2023-01-21 13:16:18.101615: step: 352/530, loss: 0.2725982367992401
2023-01-21 13:16:19.263057: step: 356/530, loss: 0.009602928534150124
2023-01-21 13:16:20.401322: step: 360/530, loss: 0.00011196136620128527
2023-01-21 13:16:21.510127: step: 364/530, loss: 0.0019847869407385588
2023-01-21 13:16:22.648651: step: 368/530, loss: 0.04716377332806587
2023-01-21 13:16:23.766258: step: 372/530, loss: 7.109642319846898e-05
2023-01-21 13:16:24.913558: step: 376/530, loss: 0.012071800418198109
2023-01-21 13:16:26.020025: step: 380/530, loss: 0.006669044494628906
2023-01-21 13:16:27.113426: step: 384/530, loss: 1.2779236385540571e-05
2023-01-21 13:16:28.238602: step: 388/530, loss: 0.0006935119163244963
2023-01-21 13:16:29.349388: step: 392/530, loss: 0.0005155563703738153
2023-01-21 13:16:30.449962: step: 396/530, loss: 3.919601658708416e-05
2023-01-21 13:16:31.557427: step: 400/530, loss: 0.0006895065307617188
2023-01-21 13:16:32.674568: step: 404/530, loss: 0.0009504318004474044
2023-01-21 13:16:33.790637: step: 408/530, loss: 0.00612220773473382
2023-01-21 13:16:34.950523: step: 412/530, loss: 0.01459961012005806
2023-01-21 13:16:36.047823: step: 416/530, loss: 2.0503998712229077e-06
2023-01-21 13:16:37.192328: step: 420/530, loss: 2.632141149661038e-05
2023-01-21 13:16:38.299853: step: 424/530, loss: 0.04956674948334694
2023-01-21 13:16:39.436850: step: 428/530, loss: 0.0017950058681890368
2023-01-21 13:16:40.544724: step: 432/530, loss: 2.2602082026423886e-05
2023-01-21 13:16:41.671073: step: 436/530, loss: 0.03938550874590874
2023-01-21 13:16:42.769675: step: 440/530, loss: 0.0003044128243345767
2023-01-21 13:16:43.906436: step: 444/530, loss: 0.0059951781295239925
2023-01-21 13:16:45.034829: step: 448/530, loss: 0.08512478321790695
2023-01-21 13:16:46.153873: step: 452/530, loss: 0.0013339996803551912
2023-01-21 13:16:47.263852: step: 456/530, loss: 0.001003265380859375
2023-01-21 13:16:48.392796: step: 460/530, loss: 1.5544890629826114e-05
2023-01-21 13:16:49.540465: step: 464/530, loss: 0.024083424359560013
2023-01-21 13:16:50.703472: step: 468/530, loss: 0.00010147094872081652
2023-01-21 13:16:51.835246: step: 472/530, loss: 7.152557373046875e-05
2023-01-21 13:16:52.970222: step: 476/530, loss: 0.6749169230461121
2023-01-21 13:16:54.062975: step: 480/530, loss: 0.0012912750244140625
2023-01-21 13:16:55.183795: step: 484/530, loss: 5.359650094760582e-05
2023-01-21 13:16:56.328189: step: 488/530, loss: 7.45773286325857e-05
2023-01-21 13:16:57.447158: step: 492/530, loss: 1.8596649169921875e-05
2023-01-21 13:16:58.569582: step: 496/530, loss: 0.00033702849759720266
2023-01-21 13:16:59.709748: step: 500/530, loss: 0.00029392243595793843
2023-01-21 13:17:00.819217: step: 504/530, loss: 0.006906700320541859
2023-01-21 13:17:01.922702: step: 508/530, loss: 0.000682449375744909
2023-01-21 13:17:03.087482: step: 512/530, loss: 0.04250946268439293
2023-01-21 13:17:04.230203: step: 516/530, loss: 0.0003803253057412803
2023-01-21 13:17:05.367580: step: 520/530, loss: 0.007968425750732422
2023-01-21 13:17:06.479712: step: 524/530, loss: 0.010615348815917969
2023-01-21 13:17:07.616320: step: 528/530, loss: 0.0003717422659974545
2023-01-21 13:17:08.734607: step: 532/530, loss: 1.6951562429312617e-05
2023-01-21 13:17:09.837027: step: 536/530, loss: 0.0012248038547113538
2023-01-21 13:17:10.976550: step: 540/530, loss: 6.637573096668348e-05
2023-01-21 13:17:12.101635: step: 544/530, loss: -6.103515261202119e-06
2023-01-21 13:17:13.223349: step: 548/530, loss: 6.48498553346144e-06
2023-01-21 13:17:14.313772: step: 552/530, loss: 0.016333866864442825
2023-01-21 13:17:15.451293: step: 556/530, loss: 0.00010395050048828125
2023-01-21 13:17:16.533615: step: 560/530, loss: 0.00030040740966796875
2023-01-21 13:17:17.657855: step: 564/530, loss: 0.0024424553848803043
2023-01-21 13:17:18.790195: step: 568/530, loss: 0.0011411666637286544
2023-01-21 13:17:19.902136: step: 572/530, loss: 0.000148773193359375
2023-01-21 13:17:21.005386: step: 576/530, loss: 8.850097219692543e-05
2023-01-21 13:17:22.122651: step: 580/530, loss: 0.0018905639881268144
2023-01-21 13:17:23.266535: step: 584/530, loss: 0.0012067795032635331
2023-01-21 13:17:24.395712: step: 588/530, loss: 0.00014162063598632812
2023-01-21 13:17:25.514008: step: 592/530, loss: -2.2888182229507947e-06
2023-01-21 13:17:26.649119: step: 596/530, loss: 0.019003773108124733
2023-01-21 13:17:27.764085: step: 600/530, loss: 0.0006348610040731728
2023-01-21 13:17:28.899040: step: 604/530, loss: 0.005875587463378906
2023-01-21 13:17:30.044691: step: 608/530, loss: 1.9359587895451114e-05
2023-01-21 13:17:31.160635: step: 612/530, loss: 0.033556174486875534
2023-01-21 13:17:32.321725: step: 616/530, loss: 8.115769014693797e-05
2023-01-21 13:17:33.476475: step: 620/530, loss: 0.014732694253325462
2023-01-21 13:17:34.605170: step: 624/530, loss: 0.0006362915155477822
2023-01-21 13:17:35.728253: step: 628/530, loss: 0.0014026642311364412
2023-01-21 13:17:36.881331: step: 632/530, loss: 0.0003367900790181011
2023-01-21 13:17:38.011032: step: 636/530, loss: 0.012792778201401234
2023-01-21 13:17:39.119370: step: 640/530, loss: 0.027961159124970436
2023-01-21 13:17:40.249237: step: 644/530, loss: 0.00618248013779521
2023-01-21 13:17:41.389384: step: 648/530, loss: 0.0002590179501567036
2023-01-21 13:17:42.504715: step: 652/530, loss: 0.0014540673000738025
2023-01-21 13:17:43.623672: step: 656/530, loss: 0.015654182061553
2023-01-21 13:17:44.747661: step: 660/530, loss: 0.0003867149353027344
2023-01-21 13:17:45.891485: step: 664/530, loss: 0.010762310586869717
2023-01-21 13:17:47.021290: step: 668/530, loss: 0.004128932952880859
2023-01-21 13:17:48.117331: step: 672/530, loss: 3.3950807846849784e-05
2023-01-21 13:17:49.248802: step: 676/530, loss: 0.14031583070755005
2023-01-21 13:17:50.375066: step: 680/530, loss: 2.4795534045551904e-05
2023-01-21 13:17:51.500520: step: 684/530, loss: 0.0003482818428892642
2023-01-21 13:17:52.645519: step: 688/530, loss: 0.10685501247644424
2023-01-21 13:17:53.775074: step: 692/530, loss: 1.7166134966828395e-06
2023-01-21 13:17:54.927616: step: 696/530, loss: 0.004745292942970991
2023-01-21 13:17:56.023777: step: 700/530, loss: 0.001017761300317943
2023-01-21 13:17:57.159253: step: 704/530, loss: 0.0004174232599325478
2023-01-21 13:17:58.266338: step: 708/530, loss: 0.0001891136053018272
2023-01-21 13:17:59.405554: step: 712/530, loss: 8.384585817111656e-05
2023-01-21 13:18:00.542478: step: 716/530, loss: 3.991126868641004e-05
2023-01-21 13:18:01.698102: step: 720/530, loss: 0.011674690991640091
2023-01-21 13:18:02.842082: step: 724/530, loss: 2.574920654296875e-05
2023-01-21 13:18:03.978004: step: 728/530, loss: 1.239776611328125e-05
2023-01-21 13:18:05.101757: step: 732/530, loss: 1.7261505490751006e-05
2023-01-21 13:18:06.208359: step: 736/530, loss: 2.136230432370212e-05
2023-01-21 13:18:07.336759: step: 740/530, loss: 0.0011869431473314762
2023-01-21 13:18:08.470654: step: 744/530, loss: 0.0023133279755711555
2023-01-21 13:18:09.598693: step: 748/530, loss: 0.002818203065544367
2023-01-21 13:18:10.739001: step: 752/530, loss: 0.029878806322813034
2023-01-21 13:18:11.846579: step: 756/530, loss: 5.34057608092553e-06
2023-01-21 13:18:12.961754: step: 760/530, loss: 0.0017185211181640625
2023-01-21 13:18:14.115382: step: 764/530, loss: 0.01397857628762722
2023-01-21 13:18:15.245382: step: 768/530, loss: 0.000978755997493863
2023-01-21 13:18:16.380006: step: 772/530, loss: 0.0011327743995934725
2023-01-21 13:18:17.507150: step: 776/530, loss: 0.00021915437537245452
2023-01-21 13:18:18.608981: step: 780/530, loss: 0.02690739743411541
2023-01-21 13:18:19.740987: step: 784/530, loss: 1.735687328618951e-05
2023-01-21 13:18:20.853470: step: 788/530, loss: 0.11035966873168945
2023-01-21 13:18:21.961376: step: 792/530, loss: 0.0005445480346679688
2023-01-21 13:18:23.053565: step: 796/530, loss: 6.12258882028982e-05
2023-01-21 13:18:24.188312: step: 800/530, loss: 3.337860107421875e-06
2023-01-21 13:18:25.301695: step: 804/530, loss: 0.0038760185707360506
2023-01-21 13:18:26.423701: step: 808/530, loss: 2.441406286379788e-05
2023-01-21 13:18:27.548528: step: 812/530, loss: 0.005829715635627508
2023-01-21 13:18:28.634779: step: 816/530, loss: 3.849268250633031e-05
2023-01-21 13:18:29.751986: step: 820/530, loss: -3.700256274896674e-05
2023-01-21 13:18:30.866599: step: 824/530, loss: 8.96453821042087e-06
2023-01-21 13:18:31.996041: step: 828/530, loss: 0.0009845733875408769
2023-01-21 13:18:33.107270: step: 832/530, loss: 0.0056663514114916325
2023-01-21 13:18:34.216258: step: 836/530, loss: 0.010106540285050869
2023-01-21 13:18:35.351530: step: 840/530, loss: 0.006153678987175226
2023-01-21 13:18:36.492742: step: 844/530, loss: 0.014376259408891201
2023-01-21 13:18:37.617050: step: 848/530, loss: 0.01888256147503853
2023-01-21 13:18:38.737622: step: 852/530, loss: 0.0016757964622229338
2023-01-21 13:18:39.863070: step: 856/530, loss: 0.00193109514657408
2023-01-21 13:18:40.997304: step: 860/530, loss: 5.769729341409402e-06
2023-01-21 13:18:42.120637: step: 864/530, loss: 0.04777565225958824
2023-01-21 13:18:43.263103: step: 868/530, loss: 0.0006130218971520662
2023-01-21 13:18:44.409574: step: 872/530, loss: 1.6021729607018642e-05
2023-01-21 13:18:45.524395: step: 876/530, loss: 0.03685932233929634
2023-01-21 13:18:46.638277: step: 880/530, loss: 0.00015897750563453883
2023-01-21 13:18:47.774356: step: 884/530, loss: 0.00010423660569358617
2023-01-21 13:18:48.923070: step: 888/530, loss: 0.003323173616081476
2023-01-21 13:18:50.050912: step: 892/530, loss: 0.0015552521217614412
2023-01-21 13:18:51.190415: step: 896/530, loss: 0.00012321471876930445
2023-01-21 13:18:52.311037: step: 900/530, loss: 0.03059844858944416
2023-01-21 13:18:53.439509: step: 904/530, loss: 0.004699421115219593
2023-01-21 13:18:54.563762: step: 908/530, loss: 7.534027645306196e-06
2023-01-21 13:18:55.661372: step: 912/530, loss: 0.0005949974292889237
2023-01-21 13:18:56.788223: step: 916/530, loss: 0.0002773285086732358
2023-01-21 13:18:57.910363: step: 920/530, loss: 0.005634307861328125
2023-01-21 13:18:59.039922: step: 924/530, loss: 0.0207806583493948
2023-01-21 13:19:00.168377: step: 928/530, loss: 1.4400482541532256e-05
2023-01-21 13:19:01.300093: step: 932/530, loss: 0.0009069442749023438
2023-01-21 13:19:02.421703: step: 936/530, loss: 3.9577484130859375e-05
2023-01-21 13:19:03.522615: step: 940/530, loss: 0.01210632361471653
2023-01-21 13:19:04.651011: step: 944/530, loss: 0.042786501348018646
2023-01-21 13:19:05.770041: step: 948/530, loss: 5.722047262679553e-07
2023-01-21 13:19:06.859442: step: 952/530, loss: 2.307891918462701e-05
2023-01-21 13:19:07.971573: step: 956/530, loss: 0.00025177001953125
2023-01-21 13:19:09.090838: step: 960/530, loss: 0.010819816961884499
2023-01-21 13:19:10.212808: step: 964/530, loss: 5.9127810345671605e-06
2023-01-21 13:19:11.345362: step: 968/530, loss: 0.00013818740262649953
2023-01-21 13:19:12.469631: step: 972/530, loss: 1.049041748046875e-05
2023-01-21 13:19:13.608418: step: 976/530, loss: 0.006081342697143555
2023-01-21 13:19:14.768753: step: 980/530, loss: 0.010370660573244095
2023-01-21 13:19:15.898969: step: 984/530, loss: 0.02096271514892578
2023-01-21 13:19:17.007312: step: 988/530, loss: 9.5367431640625e-06
2023-01-21 13:19:18.093476: step: 992/530, loss: 0.00010018348984885961
2023-01-21 13:19:19.230643: step: 996/530, loss: 9.71794142969884e-05
2023-01-21 13:19:20.336750: step: 1000/530, loss: 0.0004708290216512978
2023-01-21 13:19:21.472060: step: 1004/530, loss: 0.007357740309089422
2023-01-21 13:19:22.593206: step: 1008/530, loss: 5.817413330078125e-05
2023-01-21 13:19:23.726072: step: 1012/530, loss: 0.01956481859087944
2023-01-21 13:19:24.883340: step: 1016/530, loss: 0.00013589859008789062
2023-01-21 13:19:26.032869: step: 1020/530, loss: 0.00480308523401618
2023-01-21 13:19:27.198097: step: 1024/530, loss: 0.04133210331201553
2023-01-21 13:19:28.338548: step: 1028/530, loss: 0.01835022121667862
2023-01-21 13:19:29.500981: step: 1032/530, loss: 3.8909915019758046e-05
2023-01-21 13:19:30.603248: step: 1036/530, loss: 0.002245140029117465
2023-01-21 13:19:31.722281: step: 1040/530, loss: 0.0013062477810308337
2023-01-21 13:19:32.842986: step: 1044/530, loss: 1.4400482541532256e-05
2023-01-21 13:19:33.965004: step: 1048/530, loss: 5.111694918014109e-05
2023-01-21 13:19:35.096272: step: 1052/530, loss: 0.00614166259765625
2023-01-21 13:19:36.200029: step: 1056/530, loss: 0.0011013031471520662
2023-01-21 13:19:37.350532: step: 1060/530, loss: 0.00012755393981933594
2023-01-21 13:19:38.505859: step: 1064/530, loss: 0.0006929397350177169
2023-01-21 13:19:39.622330: step: 1068/530, loss: 0.004691123962402344
2023-01-21 13:19:40.722898: step: 1072/530, loss: 0.004897594451904297
2023-01-21 13:19:41.838629: step: 1076/530, loss: 0.0024919509887695312
2023-01-21 13:19:42.952370: step: 1080/530, loss: 0.009699773974716663
2023-01-21 13:19:44.099077: step: 1084/530, loss: 5.092620995128527e-05
2023-01-21 13:19:45.209778: step: 1088/530, loss: 8.37326078908518e-05
2023-01-21 13:19:46.346901: step: 1092/530, loss: 1.068115216185106e-05
2023-01-21 13:19:47.443147: step: 1096/530, loss: 1.23977656585339e-06
2023-01-21 13:19:48.542257: step: 1100/530, loss: 0.00042514799861237407
2023-01-21 13:19:49.668896: step: 1104/530, loss: 0.010024452582001686
2023-01-21 13:19:50.779990: step: 1108/530, loss: 2.9659269785042852e-05
2023-01-21 13:19:51.914874: step: 1112/530, loss: 0.0006076812860555947
2023-01-21 13:19:53.006674: step: 1116/530, loss: 0.06690111011266708
2023-01-21 13:19:54.116429: step: 1120/530, loss: 0.0011879921657964587
2023-01-21 13:19:55.253981: step: 1124/530, loss: 0.02864980697631836
2023-01-21 13:19:56.404215: step: 1128/530, loss: 0.00016021728515625
2023-01-21 13:19:57.520777: step: 1132/530, loss: 0.0007520675426349044
2023-01-21 13:19:58.634001: step: 1136/530, loss: 0.003181409789249301
2023-01-21 13:19:59.758119: step: 1140/530, loss: 0.00046281813411042094
2023-01-21 13:20:00.871229: step: 1144/530, loss: 0.0010197639930993319
2023-01-21 13:20:01.993382: step: 1148/530, loss: 0.00019078254990745336
2023-01-21 13:20:03.155864: step: 1152/530, loss: 2.3460386728402227e-05
2023-01-21 13:20:04.299405: step: 1156/530, loss: 0.04826164245605469
2023-01-21 13:20:05.411140: step: 1160/530, loss: 0.037078857421875
2023-01-21 13:20:06.543362: step: 1164/530, loss: 2.9563905172835803e-06
2023-01-21 13:20:07.667272: step: 1168/530, loss: 0.0006422043079510331
2023-01-21 13:20:08.776462: step: 1172/530, loss: 4.9591067181609105e-06
2023-01-21 13:20:09.896899: step: 1176/530, loss: 0.028036881238222122
2023-01-21 13:20:11.010185: step: 1180/530, loss: 7.247925168485381e-06
2023-01-21 13:20:12.161889: step: 1184/530, loss: 0.0009855270618572831
2023-01-21 13:20:13.285288: step: 1188/530, loss: 0.002782821888104081
2023-01-21 13:20:14.415307: step: 1192/530, loss: 0.0014248847728595138
2023-01-21 13:20:15.576772: step: 1196/530, loss: 0.00985031109303236
2023-01-21 13:20:16.675043: step: 1200/530, loss: 0.0033142089378088713
2023-01-21 13:20:17.795100: step: 1204/530, loss: 0.0012710571754723787
2023-01-21 13:20:18.906691: step: 1208/530, loss: 0.011067772284150124
2023-01-21 13:20:20.014329: step: 1212/530, loss: 0.008889294229447842
2023-01-21 13:20:21.108404: step: 1216/530, loss: 1.8405913579044864e-05
2023-01-21 13:20:22.229569: step: 1220/530, loss: 0.005579185672104359
2023-01-21 13:20:23.343025: step: 1224/530, loss: 0.0038913728203624487
2023-01-21 13:20:24.474488: step: 1228/530, loss: 0.00017795563326217234
2023-01-21 13:20:25.584011: step: 1232/530, loss: 2.4223329091910273e-05
2023-01-21 13:20:26.704551: step: 1236/530, loss: 5.7220458984375e-06
2023-01-21 13:20:27.817049: step: 1240/530, loss: 0.00043363572331145406
2023-01-21 13:20:28.946104: step: 1244/530, loss: 4.825591895496473e-05
2023-01-21 13:20:30.076790: step: 1248/530, loss: 3.490447852527723e-05
2023-01-21 13:20:31.181014: step: 1252/530, loss: 0.00037479400634765625
2023-01-21 13:20:32.312680: step: 1256/530, loss: 4.76837158203125e-07
2023-01-21 13:20:33.440249: step: 1260/530, loss: 0.0021940229926258326
2023-01-21 13:20:34.553313: step: 1264/530, loss: 0.1068042740225792
2023-01-21 13:20:35.674489: step: 1268/530, loss: 0.00038204193697310984
2023-01-21 13:20:36.799991: step: 1272/530, loss: 0.0003219604550395161
2023-01-21 13:20:37.909685: step: 1276/530, loss: 2.86102294921875e-06
2023-01-21 13:20:39.066222: step: 1280/530, loss: 0.024384213611483574
2023-01-21 13:20:40.194633: step: 1284/530, loss: 0.007886409759521484
2023-01-21 13:20:41.328346: step: 1288/530, loss: 0.01261148415505886
2023-01-21 13:20:42.431932: step: 1292/530, loss: 0.000667572021484375
2023-01-21 13:20:43.538982: step: 1296/530, loss: 0.0003046035999432206
2023-01-21 13:20:44.653626: step: 1300/530, loss: 0.0002510070917196572
2023-01-21 13:20:45.773334: step: 1304/530, loss: 0.00026159288245253265
2023-01-21 13:20:46.879576: step: 1308/530, loss: 0.0001598358212504536
2023-01-21 13:20:48.018625: step: 1312/530, loss: 0.05086078494787216
2023-01-21 13:20:49.177925: step: 1316/530, loss: 7.23838820704259e-05
2023-01-21 13:20:50.309046: step: 1320/530, loss: 0.0012585640652105212
2023-01-21 13:20:51.447474: step: 1324/530, loss: -3.051757857974735e-06
2023-01-21 13:20:52.568785: step: 1328/530, loss: 0.0014354229206219316
2023-01-21 13:20:53.697145: step: 1332/530, loss: 4.9591067181609105e-06
2023-01-21 13:20:54.813017: step: 1336/530, loss: 2.2602080207434483e-05
2023-01-21 13:20:55.943058: step: 1340/530, loss: 0.0006549835088662803
2023-01-21 13:20:57.071239: step: 1344/530, loss: 3.089904930675402e-05
2023-01-21 13:20:58.186013: step: 1348/530, loss: 0.012569237500429153
2023-01-21 13:20:59.295246: step: 1352/530, loss: 0.0004571914905682206
2023-01-21 13:21:00.400425: step: 1356/530, loss: 0.02011566422879696
2023-01-21 13:21:01.537801: step: 1360/530, loss: 0.00017471313185524195
2023-01-21 13:21:02.664199: step: 1364/530, loss: 0.00014772414579056203
2023-01-21 13:21:03.800312: step: 1368/530, loss: 0.0014085769653320312
2023-01-21 13:21:04.919506: step: 1372/530, loss: 0.0016020776238292456
2023-01-21 13:21:06.021889: step: 1376/530, loss: 7.877349707996473e-05
2023-01-21 13:21:07.145350: step: 1380/530, loss: 0.0003402710135560483
2023-01-21 13:21:08.269501: step: 1384/530, loss: 0.000286102294921875
2023-01-21 13:21:09.374508: step: 1388/530, loss: 0.004924488253891468
2023-01-21 13:21:10.543785: step: 1392/530, loss: 8.525847806595266e-05
2023-01-21 13:21:11.684164: step: 1396/530, loss: 2.498626781743951e-05
2023-01-21 13:21:12.818520: step: 1400/530, loss: 5.092620995128527e-05
2023-01-21 13:21:13.951298: step: 1404/530, loss: 3.0517580853484105e-06
2023-01-21 13:21:15.073210: step: 1408/530, loss: 4.96864304295741e-05
2023-01-21 13:21:16.235169: step: 1412/530, loss: 0.0012735367054119706
2023-01-21 13:21:17.348170: step: 1416/530, loss: 0.00017452239990234375
2023-01-21 13:21:18.454590: step: 1420/530, loss: 0.005168724339455366
2023-01-21 13:21:19.585590: step: 1424/530, loss: 0.0005486488225869834
2023-01-21 13:21:20.715343: step: 1428/530, loss: 8.20159948489163e-06
2023-01-21 13:21:21.816015: step: 1432/530, loss: 0.012815475463867188
2023-01-21 13:21:22.929920: step: 1436/530, loss: 0.0018611907726153731
2023-01-21 13:21:24.071933: step: 1440/530, loss: 0.004850959870964289
2023-01-21 13:21:25.185825: step: 1444/530, loss: 0.00027475954266265035
2023-01-21 13:21:26.320582: step: 1448/530, loss: 2.651214526849799e-05
2023-01-21 13:21:27.434654: step: 1452/530, loss: 0.00011496544175315648
2023-01-21 13:21:28.521630: step: 1456/530, loss: 0.0004398346063680947
2023-01-21 13:21:29.658000: step: 1460/530, loss: 0.027242470532655716
2023-01-21 13:21:30.766734: step: 1464/530, loss: 0.0001636505185160786
2023-01-21 13:21:31.868662: step: 1468/530, loss: 0.002613067626953125
2023-01-21 13:21:33.006135: step: 1472/530, loss: 0.01245107688009739
2023-01-21 13:21:34.127882: step: 1476/530, loss: 0.0012137412559241056
2023-01-21 13:21:35.275835: step: 1480/530, loss: 0.0002468109305482358
2023-01-21 13:21:36.408030: step: 1484/530, loss: -4.19616708313697e-06
2023-01-21 13:21:37.585729: step: 1488/530, loss: 0.010160732083022594
2023-01-21 13:21:38.728375: step: 1492/530, loss: 3.185272362316027e-05
2023-01-21 13:21:39.861484: step: 1496/530, loss: 9.317397780250758e-05
2023-01-21 13:21:40.965824: step: 1500/530, loss: 0.022419167682528496
2023-01-21 13:21:42.115568: step: 1504/530, loss: 0.024783708155155182
2023-01-21 13:21:43.239206: step: 1508/530, loss: 0.004865455906838179
2023-01-21 13:21:44.362051: step: 1512/530, loss: 0.017813779413700104
2023-01-21 13:21:45.518619: step: 1516/530, loss: 4.482269287109375e-05
2023-01-21 13:21:46.671838: step: 1520/530, loss: 0.024534082040190697
2023-01-21 13:21:47.804020: step: 1524/530, loss: 0.01102676335722208
2023-01-21 13:21:48.963819: step: 1528/530, loss: 0.001506042550317943
2023-01-21 13:21:50.091240: step: 1532/530, loss: 0.00033979417639784515
2023-01-21 13:21:51.193904: step: 1536/530, loss: 0.011409474536776543
2023-01-21 13:21:52.306141: step: 1540/530, loss: 9.284019324695691e-05
2023-01-21 13:21:53.407334: step: 1544/530, loss: 1.182556115963962e-05
2023-01-21 13:21:54.509505: step: 1548/530, loss: 0.000279331230558455
2023-01-21 13:21:55.606495: step: 1552/530, loss: 0.06510734558105469
2023-01-21 13:21:56.710540: step: 1556/530, loss: 0.000981998397037387
2023-01-21 13:21:57.830407: step: 1560/530, loss: 0.010261536575853825
2023-01-21 13:21:58.925264: step: 1564/530, loss: 0.0194154754281044
2023-01-21 13:22:00.045052: step: 1568/530, loss: 0.009335899725556374
2023-01-21 13:22:01.186238: step: 1572/530, loss: 0.0003146171511616558
2023-01-21 13:22:02.315285: step: 1576/530, loss: 3.8814545405330136e-05
2023-01-21 13:22:03.443674: step: 1580/530, loss: 0.0006937027210369706
2023-01-21 13:22:04.570607: step: 1584/530, loss: 0.0026811601128429174
2023-01-21 13:22:05.683946: step: 1588/530, loss: 0.01054458599537611
2023-01-21 13:22:06.792937: step: 1592/530, loss: 0.0010504722595214844
2023-01-21 13:22:07.933705: step: 1596/530, loss: 0.00042090416536666453
2023-01-21 13:22:09.032054: step: 1600/530, loss: 0.00011339188495185226
2023-01-21 13:22:10.173237: step: 1604/530, loss: 0.059081267565488815
2023-01-21 13:22:11.328447: step: 1608/530, loss: 0.0006906510097905993
2023-01-21 13:22:12.438777: step: 1612/530, loss: 0.032831527292728424
2023-01-21 13:22:13.540755: step: 1616/530, loss: 1.3841722011566162
2023-01-21 13:22:14.666356: step: 1620/530, loss: 0.010154151357710361
2023-01-21 13:22:15.782643: step: 1624/530, loss: -5.245208740234375e-06
2023-01-21 13:22:16.891174: step: 1628/530, loss: 0.17993135750293732
2023-01-21 13:22:18.014766: step: 1632/530, loss: 0.00039539337740279734
2023-01-21 13:22:19.131892: step: 1636/530, loss: 0.34007197618484497
2023-01-21 13:22:20.246088: step: 1640/530, loss: 0.06948566436767578
2023-01-21 13:22:21.380610: step: 1644/530, loss: 0.0007593155023641884
2023-01-21 13:22:22.534198: step: 1648/530, loss: 0.004726982209831476
2023-01-21 13:22:23.652627: step: 1652/530, loss: 0.5473955273628235
2023-01-21 13:22:24.796700: step: 1656/530, loss: 0.675804078578949
2023-01-21 13:22:25.928618: step: 1660/530, loss: 0.0002601623709779233
2023-01-21 13:22:27.073924: step: 1664/530, loss: 0.0020437240600585938
2023-01-21 13:22:28.208269: step: 1668/530, loss: 0.0007890701526775956
2023-01-21 13:22:29.305500: step: 1672/530, loss: 0.012912606820464134
2023-01-21 13:22:30.404739: step: 1676/530, loss: 0.00030765534029342234
2023-01-21 13:22:31.552418: step: 1680/530, loss: 0.02881908416748047
2023-01-21 13:22:32.696163: step: 1684/530, loss: 1.0013580322265625e-05
2023-01-21 13:22:33.814168: step: 1688/530, loss: 0.29777488112449646
2023-01-21 13:22:34.927468: step: 1692/530, loss: 0.005026340484619141
2023-01-21 13:22:36.038830: step: 1696/530, loss: 0.0008386134868487716
2023-01-21 13:22:37.178378: step: 1700/530, loss: 0.010757828131318092
2023-01-21 13:22:38.303892: step: 1704/530, loss: 2.2506712411995977e-05
2023-01-21 13:22:39.452214: step: 1708/530, loss: 0.023312950506806374
2023-01-21 13:22:40.620321: step: 1712/530, loss: 0.0448266975581646
2023-01-21 13:22:41.770544: step: 1716/530, loss: 0.0015081405872479081
2023-01-21 13:22:42.898893: step: 1720/530, loss: 0.005154609680175781
2023-01-21 13:22:44.023073: step: 1724/530, loss: 0.010216903872787952
2023-01-21 13:22:45.137826: step: 1728/530, loss: 0.008222103118896484
2023-01-21 13:22:46.249986: step: 1732/530, loss: 0.0007456779712811112
2023-01-21 13:22:47.372235: step: 1736/530, loss: 0.046380139887332916
2023-01-21 13:22:48.474623: step: 1740/530, loss: 0.004082679748535156
2023-01-21 13:22:49.607704: step: 1744/530, loss: 0.0006488800281658769
2023-01-21 13:22:50.729725: step: 1748/530, loss: 0.05324072763323784
2023-01-21 13:22:51.899425: step: 1752/530, loss: 0.6468315124511719
2023-01-21 13:22:53.007980: step: 1756/530, loss: 0.00018033980450127274
2023-01-21 13:22:54.110018: step: 1760/530, loss: 0.004239463713020086
2023-01-21 13:22:55.275973: step: 1764/530, loss: 0.007846260443329811
2023-01-21 13:22:56.383434: step: 1768/530, loss: 0.010870934464037418
2023-01-21 13:22:57.506770: step: 1772/530, loss: 5.908012462896295e-05
2023-01-21 13:22:58.639252: step: 1776/530, loss: 0.0018302917014807463
2023-01-21 13:22:59.754729: step: 1780/530, loss: 9.021759615279734e-05
2023-01-21 13:23:00.842613: step: 1784/530, loss: 0.0002437591610942036
2023-01-21 13:23:01.941207: step: 1788/530, loss: 0.0014827251434326172
2023-01-21 13:23:03.045255: step: 1792/530, loss: 0.014362144283950329
2023-01-21 13:23:04.149619: step: 1796/530, loss: 0.001475858734920621
2023-01-21 13:23:05.266691: step: 1800/530, loss: 0.023401547223329544
2023-01-21 13:23:06.408892: step: 1804/530, loss: 0.004010010045021772
2023-01-21 13:23:07.536215: step: 1808/530, loss: 0.0038078308571130037
2023-01-21 13:23:08.661971: step: 1812/530, loss: 0.0026221275329589844
2023-01-21 13:23:09.778337: step: 1816/530, loss: 0.00026264190091751516
2023-01-21 13:23:10.902479: step: 1820/530, loss: 0.029579926282167435
2023-01-21 13:23:12.015794: step: 1824/530, loss: 6.103515625e-05
2023-01-21 13:23:13.116644: step: 1828/530, loss: 4.67777244921308e-05
2023-01-21 13:23:14.237791: step: 1832/530, loss: 0.006224250886589289
2023-01-21 13:23:15.359087: step: 1836/530, loss: 5.6838991440599784e-05
2023-01-21 13:23:16.507837: step: 1840/530, loss: 0.006007385440170765
2023-01-21 13:23:17.624864: step: 1844/530, loss: 0.00016269684419967234
2023-01-21 13:23:18.754619: step: 1848/530, loss: 0.0003838539414573461
2023-01-21 13:23:19.882524: step: 1852/530, loss: 0.0032398225739598274
2023-01-21 13:23:21.020161: step: 1856/530, loss: 0.00019121170043945312
2023-01-21 13:23:22.135445: step: 1860/530, loss: 0.002493953565135598
2023-01-21 13:23:23.270714: step: 1864/530, loss: 7.858276512706652e-05
2023-01-21 13:23:24.392218: step: 1868/530, loss: 3.337860107421875e-06
2023-01-21 13:23:25.548580: step: 1872/530, loss: 0.0026824951637536287
2023-01-21 13:23:26.688930: step: 1876/530, loss: 0.00015211105346679688
2023-01-21 13:23:27.793848: step: 1880/530, loss: -5.722046125811175e-07
2023-01-21 13:23:28.938605: step: 1884/530, loss: 0.0007213592762127519
2023-01-21 13:23:30.066686: step: 1888/530, loss: 0.009116172790527344
2023-01-21 13:23:31.172609: step: 1892/530, loss: 0.0009084701887331903
2023-01-21 13:23:32.338535: step: 1896/530, loss: 4.978180368198082e-05
2023-01-21 13:23:33.467791: step: 1900/530, loss: 1.602172778802924e-05
2023-01-21 13:23:34.581616: step: 1904/530, loss: 0.033154867589473724
2023-01-21 13:23:35.715440: step: 1908/530, loss: 0.08177509158849716
2023-01-21 13:23:36.812433: step: 1912/530, loss: 0.002113485476002097
2023-01-21 13:23:37.947711: step: 1916/530, loss: 0.0013184547424316406
2023-01-21 13:23:39.052771: step: 1920/530, loss: 0.00022907258244231343
2023-01-21 13:23:40.168021: step: 1924/530, loss: 0.3636288046836853
2023-01-21 13:23:41.293069: step: 1928/530, loss: 0.02152719534933567
2023-01-21 13:23:42.394644: step: 1932/530, loss: 0.015555381774902344
2023-01-21 13:23:43.517728: step: 1936/530, loss: 0.02086048200726509
2023-01-21 13:23:44.662793: step: 1940/530, loss: 0.013928413391113281
2023-01-21 13:23:45.745804: step: 1944/530, loss: 6.732940528308973e-05
2023-01-21 13:23:46.842460: step: 1948/530, loss: 0.019211674109101295
2023-01-21 13:23:47.975857: step: 1952/530, loss: 1.4972687495173886e-05
2023-01-21 13:23:49.075659: step: 1956/530, loss: 1.0013580322265625e-05
2023-01-21 13:23:50.224315: step: 1960/530, loss: 0.007532310672104359
2023-01-21 13:23:51.312194: step: 1964/530, loss: 2.0599363779183477e-05
2023-01-21 13:23:52.432336: step: 1968/530, loss: 0.04944858327507973
2023-01-21 13:23:53.540392: step: 1972/530, loss: 0.015220833010971546
2023-01-21 13:23:54.675656: step: 1976/530, loss: 0.005277395248413086
2023-01-21 13:23:55.787372: step: 1980/530, loss: 0.06283760815858841
2023-01-21 13:23:56.868238: step: 1984/530, loss: -1.049041748046875e-05
2023-01-21 13:23:57.997907: step: 1988/530, loss: 0.012457847595214844
2023-01-21 13:23:59.126129: step: 1992/530, loss: 7.61032133596018e-05
2023-01-21 13:24:00.257936: step: 1996/530, loss: 0.0156339630484581
2023-01-21 13:24:01.371859: step: 2000/530, loss: 0.0009899139404296875
2023-01-21 13:24:02.483145: step: 2004/530, loss: 0.048882272094488144
2023-01-21 13:24:03.582425: step: 2008/530, loss: 0.0246187224984169
2023-01-21 13:24:04.723226: step: 2012/530, loss: 0.035050392150878906
2023-01-21 13:24:05.845819: step: 2016/530, loss: 9.91821252682712e-06
2023-01-21 13:24:06.963639: step: 2020/530, loss: 0.00967397727072239
2023-01-21 13:24:08.072560: step: 2024/530, loss: 0.00017232894606422633
2023-01-21 13:24:09.195922: step: 2028/530, loss: 1.1157990229548886e-05
2023-01-21 13:24:10.349829: step: 2032/530, loss: 0.00047941209049895406
2023-01-21 13:24:11.478872: step: 2036/530, loss: 0.0005478858947753906
2023-01-21 13:24:12.581589: step: 2040/530, loss: 7.877350435592234e-05
2023-01-21 13:24:13.722457: step: 2044/530, loss: 0.017975807189941406
2023-01-21 13:24:14.842431: step: 2048/530, loss: 0.0010637283558025956
2023-01-21 13:24:15.956810: step: 2052/530, loss: 0.00040922165499068797
2023-01-21 13:24:17.060931: step: 2056/530, loss: 0.017572499811649323
2023-01-21 13:24:18.206645: step: 2060/530, loss: 0.005312442779541016
2023-01-21 13:24:19.326155: step: 2064/530, loss: 0.008203793317079544
2023-01-21 13:24:20.430793: step: 2068/530, loss: 0.017166901379823685
2023-01-21 13:24:21.541958: step: 2072/530, loss: 0.00017185212345793843
2023-01-21 13:24:22.673813: step: 2076/530, loss: 1.0538101378188003e-05
2023-01-21 13:24:23.789496: step: 2080/530, loss: 0.00055608747061342
2023-01-21 13:24:24.911273: step: 2084/530, loss: 7.133484177757055e-05
2023-01-21 13:24:26.062156: step: 2088/530, loss: 0.0014274597633630037
2023-01-21 13:24:27.195664: step: 2092/530, loss: 0.0009328365558758378
2023-01-21 13:24:28.320901: step: 2096/530, loss: -4.76837158203125e-06
2023-01-21 13:24:29.445151: step: 2100/530, loss: 0.0008809089777059853
2023-01-21 13:24:30.552775: step: 2104/530, loss: 0.0002529144403524697
2023-01-21 13:24:31.660898: step: 2108/530, loss: 0.25830966234207153
2023-01-21 13:24:32.758388: step: 2112/530, loss: 0.03186798095703125
2023-01-21 13:24:33.868814: step: 2116/530, loss: 0.00039882661076262593
2023-01-21 13:24:34.981577: step: 2120/530, loss: 1.4448166439251509e-05
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.596875, 'r': 0.762982689747004, 'f1': 0.6697837521917008}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6148678907299597, 'r': 0.7845714285714286, 'f1': 0.6894300778307809}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.6363636363636364, 'r': 0.9074074074074074, 'f1': 0.7480916030534351}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.6111111111111112, 'r': 0.5238095238095238, 'f1': 0.5641025641025642}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
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': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 13:25:15.725160: step: 4/530, loss: 1.61647803906817e-05
2023-01-21 13:25:16.868897: step: 8/530, loss: 0.002895450685173273
2023-01-21 13:25:18.031574: step: 12/530, loss: 0.0001123428373830393
2023-01-21 13:25:19.173723: step: 16/530, loss: 0.00017395020404364914
2023-01-21 13:25:20.272794: step: 20/530, loss: 0.0003459930594544858
2023-01-21 13:25:21.408667: step: 24/530, loss: 0.0007979392539709806
2023-01-21 13:25:22.527421: step: 28/530, loss: -7.629394644936838e-07
2023-01-21 13:25:23.618951: step: 32/530, loss: 0.00016105175018310547
2023-01-21 13:25:24.741072: step: 36/530, loss: 0.00014028549776412547
2023-01-21 13:25:25.877941: step: 40/530, loss: 0.01956052891910076
2023-01-21 13:25:27.034514: step: 44/530, loss: 0.0058405399322509766
2023-01-21 13:25:28.157381: step: 48/530, loss: 0.00042591095552779734
2023-01-21 13:25:29.283803: step: 52/530, loss: 1.9073486328125e-06
2023-01-21 13:25:30.452274: step: 56/530, loss: 1.9073559087701142e-07
2023-01-21 13:25:31.586568: step: 60/530, loss: 2.593994213384576e-05
2023-01-21 13:25:32.698365: step: 64/530, loss: 0.032859232276678085
2023-01-21 13:25:33.855185: step: 68/530, loss: 6.914139248692663e-06
2023-01-21 13:25:34.983918: step: 72/530, loss: 0.0005523681757040322
2023-01-21 13:25:36.121158: step: 76/530, loss: 0.00010128021676791832
2023-01-21 13:25:37.251002: step: 80/530, loss: 6.542205665027723e-05
2023-01-21 13:25:38.349469: step: 84/530, loss: 3.5762786865234375e-05
2023-01-21 13:25:39.460943: step: 88/530, loss: 0.0008863449329510331
2023-01-21 13:25:40.598101: step: 92/530, loss: 3.280639793956652e-05
2023-01-21 13:25:41.714223: step: 96/530, loss: 0.0014580728020519018
2023-01-21 13:25:42.825729: step: 100/530, loss: 0.010656356811523438
2023-01-21 13:25:43.952186: step: 104/530, loss: 0.002040386199951172
2023-01-21 13:25:45.051237: step: 108/530, loss: 0.0015539169544354081
2023-01-21 13:25:46.183677: step: 112/530, loss: 0.042345620691776276
2023-01-21 13:25:47.317000: step: 116/530, loss: 0.0015274047618731856
2023-01-21 13:25:48.410776: step: 120/530, loss: 3.795623706537299e-05
2023-01-21 13:25:49.543938: step: 124/530, loss: 0.00010585784912109375
2023-01-21 13:25:50.657983: step: 128/530, loss: 6.31332368357107e-05
2023-01-21 13:25:51.785258: step: 132/530, loss: 0.005732917692512274
2023-01-21 13:25:52.899634: step: 136/530, loss: 0.0027496337424963713
2023-01-21 13:25:53.985121: step: 140/530, loss: 6.256103370105848e-05
2023-01-21 13:25:55.082081: step: 144/530, loss: 9.813308861339465e-05
2023-01-21 13:25:56.188276: step: 148/530, loss: 0.014726400375366211
2023-01-21 13:25:57.334512: step: 152/530, loss: 0.005751418881118298
2023-01-21 13:25:58.450552: step: 156/530, loss: 0.0002639770682435483
2023-01-21 13:25:59.556318: step: 160/530, loss: 0.0015379906399175525
2023-01-21 13:26:00.691809: step: 164/530, loss: 0.0005727768293581903
2023-01-21 13:26:01.793027: step: 168/530, loss: 0.04943738132715225
2023-01-21 13:26:02.937016: step: 172/530, loss: 1.2111663636460435e-05
2023-01-21 13:26:04.069000: step: 176/530, loss: 0.003657054854556918
2023-01-21 13:26:05.215159: step: 180/530, loss: 0.000196361550479196
2023-01-21 13:26:06.313943: step: 184/530, loss: -1.144409225162235e-06
2023-01-21 13:26:07.451822: step: 188/530, loss: 0.00022940635972190648
2023-01-21 13:26:08.577709: step: 192/530, loss: 0.0006702422979287803
2023-01-21 13:26:09.728703: step: 196/530, loss: 0.014172744937241077
2023-01-21 13:26:10.854984: step: 200/530, loss: 0.0022460937034338713
2023-01-21 13:26:11.957466: step: 204/530, loss: 0.006929206661880016
2023-01-21 13:26:13.082277: step: 208/530, loss: 0.006089400965720415
2023-01-21 13:26:14.205337: step: 212/530, loss: 8.7738037109375e-05
2023-01-21 13:26:15.338411: step: 216/530, loss: 0.00984726008027792
2023-01-21 13:26:16.454752: step: 220/530, loss: 8.296966370835435e-06
2023-01-21 13:26:17.576005: step: 224/530, loss: 0.015216446481645107
2023-01-21 13:26:18.684608: step: 228/530, loss: 0.0031753063667565584
2023-01-21 13:26:19.866019: step: 232/530, loss: 0.0310440082103014
2023-01-21 13:26:21.017339: step: 236/530, loss: 0.006305122282356024
2023-01-21 13:26:22.125554: step: 240/530, loss: 0.0005549431079998612
2023-01-21 13:26:23.285326: step: 244/530, loss: 0.008169079199433327
2023-01-21 13:26:24.417839: step: 248/530, loss: 0.0036918639671057463
2023-01-21 13:26:25.550255: step: 252/530, loss: 4.386902219266631e-06
2023-01-21 13:26:26.657961: step: 256/530, loss: 0.015699386596679688
2023-01-21 13:26:27.771686: step: 260/530, loss: -1.33514404296875e-05
2023-01-21 13:26:28.865590: step: 264/530, loss: 0.00044374470598995686
2023-01-21 13:26:30.004156: step: 268/530, loss: 0.0037364959716796875
2023-01-21 13:26:31.134640: step: 272/530, loss: 0.0004578590451274067
2023-01-21 13:26:32.266744: step: 276/530, loss: 0.36111927032470703
2023-01-21 13:26:33.397150: step: 280/530, loss: 0.0012763977283611894
2023-01-21 13:26:34.501073: step: 284/530, loss: 0.0036357881035655737
2023-01-21 13:26:35.597714: step: 288/530, loss: 0.00019040108600165695
2023-01-21 13:26:36.738883: step: 292/530, loss: 0.01742076873779297
2023-01-21 13:26:37.883970: step: 296/530, loss: 0.002397155622020364
2023-01-21 13:26:38.991490: step: 300/530, loss: 0.022004319354891777
2023-01-21 13:26:40.119260: step: 304/530, loss: 0.0009565353393554688
2023-01-21 13:26:41.253569: step: 308/530, loss: 0.012733936309814453
2023-01-21 13:26:42.369305: step: 312/530, loss: 0.0023849487770348787
2023-01-21 13:26:43.553173: step: 316/530, loss: 1.773834264895413e-05
2023-01-21 13:26:44.687702: step: 320/530, loss: 0.004548454657196999
2023-01-21 13:26:45.835599: step: 324/530, loss: 3.919601658708416e-05
2023-01-21 13:26:46.968068: step: 328/530, loss: 0.0006677627679891884
2023-01-21 13:26:48.103684: step: 332/530, loss: 1.621246337890625e-05
2023-01-21 13:26:49.215372: step: 336/530, loss: 0.00011048316810047254
2023-01-21 13:26:50.359437: step: 340/530, loss: 0.0001567840517964214
2023-01-21 13:26:51.442676: step: 344/530, loss: 0.0007076263427734375
2023-01-21 13:26:52.574104: step: 348/530, loss: 8.0108642578125e-05
2023-01-21 13:26:53.688794: step: 352/530, loss: 0.6086832284927368
2023-01-21 13:26:54.828050: step: 356/530, loss: 0.02562532387673855
2023-01-21 13:26:55.924494: step: 360/530, loss: 0.00019035338482353836
2023-01-21 13:26:57.027449: step: 364/530, loss: 2.4795533590804553e-06
2023-01-21 13:26:58.177167: step: 368/530, loss: 0.028681470081210136
2023-01-21 13:26:59.312553: step: 372/530, loss: 0.04610119014978409
2023-01-21 13:27:00.453255: step: 376/530, loss: 0.007653284352272749
2023-01-21 13:27:01.571795: step: 380/530, loss: 1.1444092706369702e-05
2023-01-21 13:27:02.679562: step: 384/530, loss: 0.0058803558349609375
2023-01-21 13:27:03.790224: step: 388/530, loss: 0.00010013580322265625
2023-01-21 13:27:04.903195: step: 392/530, loss: 0.00013875961303710938
2023-01-21 13:27:06.051795: step: 396/530, loss: 0.14408770203590393
2023-01-21 13:27:07.180441: step: 400/530, loss: 0.007503700442612171
2023-01-21 13:27:08.271714: step: 404/530, loss: 0.00020685195340774953
2023-01-21 13:27:09.410868: step: 408/530, loss: 0.00017423629469703883
2023-01-21 13:27:10.534676: step: 412/530, loss: 0.0037204741965979338
2023-01-21 13:27:11.657897: step: 416/530, loss: 0.02051677741110325
2023-01-21 13:27:12.791210: step: 420/530, loss: 0.00021266937255859375
2023-01-21 13:27:13.876097: step: 424/530, loss: 0.010767459869384766
2023-01-21 13:27:14.974688: step: 428/530, loss: 0.0011314392322674394
2023-01-21 13:27:16.093935: step: 432/530, loss: 2.9563905172835803e-06
2023-01-21 13:27:17.239018: step: 436/530, loss: 0.023217011243104935
2023-01-21 13:27:18.362841: step: 440/530, loss: 0.007027054205536842
2023-01-21 13:27:19.471665: step: 444/530, loss: 0.005853176582604647
2023-01-21 13:27:20.575887: step: 448/530, loss: 0.0007048607221804559
2023-01-21 13:27:21.691077: step: 452/530, loss: 0.007026386447250843
2023-01-21 13:27:22.812238: step: 456/530, loss: 9.431839134776965e-05
2023-01-21 13:27:23.940531: step: 460/530, loss: 1.4972687495173886e-05
2023-01-21 13:27:25.072221: step: 464/530, loss: 0.0014553070068359375
2023-01-21 13:27:26.192442: step: 468/530, loss: 0.04153694957494736
2023-01-21 13:27:27.287418: step: 472/530, loss: 0.002308464143425226
2023-01-21 13:27:28.408400: step: 476/530, loss: 0.0004938125493936241
2023-01-21 13:27:29.542861: step: 480/530, loss: 0.049247268587350845
2023-01-21 13:27:30.657512: step: 484/530, loss: 0.00914468802511692
2023-01-21 13:27:31.816871: step: 488/530, loss: 0.032621193677186966
2023-01-21 13:27:32.916295: step: 492/530, loss: 0.005867003928869963
2023-01-21 13:27:34.025518: step: 496/530, loss: 0.0025401234161108732
2023-01-21 13:27:35.153727: step: 500/530, loss: 0.0560823455452919
2023-01-21 13:27:36.271030: step: 504/530, loss: 0.0191024299710989
2023-01-21 13:27:37.415636: step: 508/530, loss: 2.593994213384576e-05
2023-01-21 13:27:38.519632: step: 512/530, loss: 0.059711456298828125
2023-01-21 13:27:39.619112: step: 516/530, loss: 0.010155963711440563
2023-01-21 13:27:40.748614: step: 520/530, loss: 0.0002598762512207031
2023-01-21 13:27:41.879689: step: 524/530, loss: 0.004161930177360773
2023-01-21 13:27:42.996143: step: 528/530, loss: 1.3589859008789062e-05
2023-01-21 13:27:44.087119: step: 532/530, loss: 0.00012807846360374242
2023-01-21 13:27:45.192227: step: 536/530, loss: 5.34057608092553e-06
2023-01-21 13:27:46.312635: step: 540/530, loss: 0.022748898714780807
2023-01-21 13:27:47.439729: step: 544/530, loss: 0.0030088424682617188
2023-01-21 13:27:48.541352: step: 548/530, loss: 0.01999511756002903
2023-01-21 13:27:49.641028: step: 552/530, loss: 0.0001902341900859028
2023-01-21 13:27:50.740935: step: 556/530, loss: 0.262780100107193
2023-01-21 13:27:51.851258: step: 560/530, loss: 0.0006860733265057206
2023-01-21 13:27:52.973532: step: 564/530, loss: 0.00732688931748271
2023-01-21 13:27:54.080058: step: 568/530, loss: 6.322861008811742e-05
2023-01-21 13:27:55.191692: step: 572/530, loss: 0.006182384677231312
2023-01-21 13:27:56.327334: step: 576/530, loss: 0.002134656999260187
2023-01-21 13:27:57.460753: step: 580/530, loss: 0.00017662048048805445
2023-01-21 13:27:58.582839: step: 584/530, loss: 9.002686419989914e-05
2023-01-21 13:27:59.710564: step: 588/530, loss: 9.174347360385582e-05
2023-01-21 13:28:00.811190: step: 592/530, loss: 0.014150524511933327
2023-01-21 13:28:01.926979: step: 596/530, loss: 0.002223968505859375
2023-01-21 13:28:03.059642: step: 600/530, loss: 0.04023418575525284
2023-01-21 13:28:04.181061: step: 604/530, loss: 0.004775805864483118
2023-01-21 13:28:05.283713: step: 608/530, loss: 5.53131121705519e-06
2023-01-21 13:28:06.426444: step: 612/530, loss: 0.0010930061107501388
2023-01-21 13:28:07.539775: step: 616/530, loss: 7.181167165981606e-05
2023-01-21 13:28:08.656145: step: 620/530, loss: 0.00042381288949400187
2023-01-21 13:28:09.750819: step: 624/530, loss: -4.291534423828125e-06
2023-01-21 13:28:10.858702: step: 628/530, loss: 0.00019874573627021164
2023-01-21 13:28:11.973397: step: 632/530, loss: 0.00044651032658293843
2023-01-21 13:28:13.096339: step: 636/530, loss: 0.013640307821333408
2023-01-21 13:28:14.218431: step: 640/530, loss: 0.009754180908203125
2023-01-21 13:28:15.333643: step: 644/530, loss: 0.00875711441040039
2023-01-21 13:28:16.467124: step: 648/530, loss: 0.004778098780661821
2023-01-21 13:28:17.626097: step: 652/530, loss: 6.608962576137856e-05
2023-01-21 13:28:18.743110: step: 656/530, loss: 0.0017053604824468493
2023-01-21 13:28:19.847650: step: 660/530, loss: 0.0698385238647461
2023-01-21 13:28:20.957672: step: 664/530, loss: -1.010894811770413e-05
2023-01-21 13:28:22.063782: step: 668/530, loss: 0.008668137714266777
2023-01-21 13:28:23.195818: step: 672/530, loss: 0.0006757735973224044
2023-01-21 13:28:24.309227: step: 676/530, loss: 0.0001385211944580078
2023-01-21 13:28:25.426542: step: 680/530, loss: 0.031541064381599426
2023-01-21 13:28:26.549686: step: 684/530, loss: 0.007217979524284601
2023-01-21 13:28:27.651947: step: 688/530, loss: 0.0016963959205895662
2023-01-21 13:28:28.777772: step: 692/530, loss: 0.00010528564598644152
2023-01-21 13:28:29.898242: step: 696/530, loss: 0.0011213303077965975
2023-01-21 13:28:31.032014: step: 700/530, loss: 0.006923961453139782
2023-01-21 13:28:32.192258: step: 704/530, loss: 0.00010042190842796117
2023-01-21 13:28:33.313607: step: 708/530, loss: 9.498596045887098e-05
2023-01-21 13:28:34.442773: step: 712/530, loss: 0.002708053681999445
2023-01-21 13:28:35.542148: step: 716/530, loss: 0.05470886081457138
2023-01-21 13:28:36.662839: step: 720/530, loss: 0.00021219253540039062
2023-01-21 13:28:37.743050: step: 724/530, loss: 9.431839134776965e-05
2023-01-21 13:28:38.890214: step: 728/530, loss: 0.008250999264419079
2023-01-21 13:28:40.042010: step: 732/530, loss: 0.0015811920166015625
2023-01-21 13:28:41.143276: step: 736/530, loss: 0.00401916541159153
2023-01-21 13:28:42.252983: step: 740/530, loss: 0.02395792119204998
2023-01-21 13:28:43.377930: step: 744/530, loss: 0.0009042739984579384
2023-01-21 13:28:44.515632: step: 748/530, loss: 0.000752353691495955
2023-01-21 13:28:45.623934: step: 752/530, loss: 0.795527994632721
2023-01-21 13:28:46.714742: step: 756/530, loss: 0.016500424593687057
2023-01-21 13:28:47.834806: step: 760/530, loss: 0.0014204978942871094
2023-01-21 13:28:48.959494: step: 764/530, loss: -6.103515261202119e-06
2023-01-21 13:28:50.083225: step: 768/530, loss: 0.006800651550292969
2023-01-21 13:28:51.193805: step: 772/530, loss: 0.032942771911621094
2023-01-21 13:28:52.280138: step: 776/530, loss: 0.0019129753345623612
2023-01-21 13:28:53.402758: step: 780/530, loss: 0.002397727919742465
2023-01-21 13:28:54.543639: step: 784/530, loss: 0.00051116943359375
2023-01-21 13:28:55.652210: step: 788/530, loss: 0.011448669247329235
2023-01-21 13:28:56.779527: step: 792/530, loss: 0.025690842419862747
2023-01-21 13:28:57.900532: step: 796/530, loss: 2.7287005650578067e-05
2023-01-21 13:28:59.015832: step: 800/530, loss: 1.029968279908644e-05
2023-01-21 13:29:00.131798: step: 804/530, loss: 1.182556115963962e-05
2023-01-21 13:29:01.252721: step: 808/530, loss: 0.6968754529953003
2023-01-21 13:29:02.415311: step: 812/530, loss: 0.03249816969037056
2023-01-21 13:29:03.514215: step: 816/530, loss: 0.002442741533741355
2023-01-21 13:29:04.630348: step: 820/530, loss: 0.0011867046123370528
2023-01-21 13:29:05.776138: step: 824/530, loss: 0.007768154144287109
2023-01-21 13:29:06.889669: step: 828/530, loss: 0.02147960662841797
2023-01-21 13:29:08.046177: step: 832/530, loss: 0.0002189636288676411
2023-01-21 13:29:09.168942: step: 836/530, loss: 0.03344393149018288
2023-01-21 13:29:10.300229: step: 840/530, loss: 3.2711028325138614e-05
2023-01-21 13:29:11.419347: step: 844/530, loss: 6.341934204101562e-05
2023-01-21 13:29:12.522883: step: 848/530, loss: 0.00029501915560103953
2023-01-21 13:29:13.622956: step: 852/530, loss: 0.0001030921921483241
2023-01-21 13:29:14.775815: step: 856/530, loss: 1.373290979245212e-05
2023-01-21 13:29:15.888209: step: 860/530, loss: 0.00044536590576171875
2023-01-21 13:29:17.001824: step: 864/530, loss: 0.018575668334960938
2023-01-21 13:29:18.146935: step: 868/530, loss: 0.0007208347669802606
2023-01-21 13:29:19.267498: step: 872/530, loss: 0.04862871393561363
2023-01-21 13:29:20.404880: step: 876/530, loss: 0.00033745766268111765
2023-01-21 13:29:21.510865: step: 880/530, loss: 4.27722952736076e-05
2023-01-21 13:29:22.663188: step: 884/530, loss: 0.0006854057428427041
2023-01-21 13:29:23.788048: step: 888/530, loss: 0.0011775969760492444
2023-01-21 13:29:24.941611: step: 892/530, loss: 0.0008594513055868447
2023-01-21 13:29:26.028612: step: 896/530, loss: 7.963179996295366e-06
2023-01-21 13:29:27.150417: step: 900/530, loss: 0.003631782718002796
2023-01-21 13:29:28.304956: step: 904/530, loss: 0.00031414031400345266
2023-01-21 13:29:29.425648: step: 908/530, loss: -1.9073486612342094e-07
2023-01-21 13:29:30.566737: step: 912/530, loss: 0.002008628798648715
2023-01-21 13:29:31.687699: step: 916/530, loss: 0.0008638381841592491
2023-01-21 13:29:32.843916: step: 920/530, loss: 0.0001652240753173828
2023-01-21 13:29:33.932472: step: 924/530, loss: 0.00010886192467296496
2023-01-21 13:29:35.050499: step: 928/530, loss: 0.00020947455777786672
2023-01-21 13:29:36.169766: step: 932/530, loss: 0.0015834808582440019
2023-01-21 13:29:37.299803: step: 936/530, loss: 0.007834816351532936
2023-01-21 13:29:38.422008: step: 940/530, loss: 0.0047487737610936165
2023-01-21 13:29:39.526628: step: 944/530, loss: 0.0001928329438669607
2023-01-21 13:29:40.662219: step: 948/530, loss: 0.00012836456880904734
2023-01-21 13:29:41.768454: step: 952/530, loss: 0.01651759073138237
2023-01-21 13:29:42.897877: step: 956/530, loss: 0.000850296055432409
2023-01-21 13:29:44.024423: step: 960/530, loss: 1.068115216185106e-05
2023-01-21 13:29:45.146831: step: 964/530, loss: 0.0011074066860601306
2023-01-21 13:29:46.300304: step: 968/530, loss: 0.0030498504638671875
2023-01-21 13:29:47.392631: step: 972/530, loss: 0.0011825562687590718
2023-01-21 13:29:48.463159: step: 976/530, loss: 9.822844731388614e-06
2023-01-21 13:29:49.577451: step: 980/530, loss: 0.0001998901425395161
2023-01-21 13:29:50.671516: step: 984/530, loss: 5.235672142589465e-05
2023-01-21 13:29:51.810613: step: 988/530, loss: 0.11468525230884552
2023-01-21 13:29:52.946664: step: 992/530, loss: 0.006410980597138405
2023-01-21 13:29:54.068108: step: 996/530, loss: 9.89913969533518e-05
2023-01-21 13:29:55.168216: step: 1000/530, loss: 0.0001962661772267893
2023-01-21 13:29:56.264492: step: 1004/530, loss: 1.354217511106981e-05
2023-01-21 13:29:57.399293: step: 1008/530, loss: 0.007386684417724609
2023-01-21 13:29:58.515161: step: 1012/530, loss: -1.5926361811580136e-05
2023-01-21 13:29:59.627948: step: 1016/530, loss: 7.190704491222277e-05
2023-01-21 13:30:00.764508: step: 1020/530, loss: 0.001410675118677318
2023-01-21 13:30:01.897161: step: 1024/530, loss: 1.71661376953125e-05
2023-01-21 13:30:02.988839: step: 1028/530, loss: 7.305145845748484e-05
2023-01-21 13:30:04.090230: step: 1032/530, loss: 3.528594970703125e-05
2023-01-21 13:30:05.180245: step: 1036/530, loss: 0.000873947108630091
2023-01-21 13:30:06.320077: step: 1040/530, loss: 0.004680252633988857
2023-01-21 13:30:07.473060: step: 1044/530, loss: 1.888275073724799e-05
2023-01-21 13:30:08.589429: step: 1048/530, loss: 0.004245043266564608
2023-01-21 13:30:09.712840: step: 1052/530, loss: 0.00020294189744163305
2023-01-21 13:30:10.853768: step: 1056/530, loss: 0.21936731040477753
2023-01-21 13:30:11.967405: step: 1060/530, loss: 0.012591171078383923
2023-01-21 13:30:13.091685: step: 1064/530, loss: 0.004246711730957031
2023-01-21 13:30:14.238446: step: 1068/530, loss: 0.0016354559920728207
2023-01-21 13:30:15.364740: step: 1072/530, loss: 0.017191791906952858
2023-01-21 13:30:16.487834: step: 1076/530, loss: 9.250641596736386e-06
2023-01-21 13:30:17.630182: step: 1080/530, loss: 0.045319173485040665
2023-01-21 13:30:18.731852: step: 1084/530, loss: 1.864433397713583e-05
2023-01-21 13:30:19.859303: step: 1088/530, loss: 0.00010933876183116809
2023-01-21 13:30:20.978269: step: 1092/530, loss: 3.986358569818549e-05
2023-01-21 13:30:22.139394: step: 1096/530, loss: 0.013704204931855202
2023-01-21 13:30:23.261207: step: 1100/530, loss: 0.0003279685915913433
2023-01-21 13:30:24.358076: step: 1104/530, loss: 0.0005154609680175781
2023-01-21 13:30:25.465131: step: 1108/530, loss: 0.0011608124477788806
2023-01-21 13:30:26.603694: step: 1112/530, loss: 0.00014228820509742945
2023-01-21 13:30:27.729456: step: 1116/530, loss: 0.015127467922866344
2023-01-21 13:30:28.842224: step: 1120/530, loss: 0.0012807846069335938
2023-01-21 13:30:29.955751: step: 1124/530, loss: 0.029927827417850494
2023-01-21 13:30:31.068764: step: 1128/530, loss: 0.0002655029238667339
2023-01-21 13:30:32.189379: step: 1132/530, loss: 0.00026569367037154734
2023-01-21 13:30:33.331732: step: 1136/530, loss: 0.05796490237116814
2023-01-21 13:30:34.496753: step: 1140/530, loss: 1.201629675051663e-05
2023-01-21 13:30:35.634316: step: 1144/530, loss: 0.0002628326474223286
2023-01-21 13:30:36.762794: step: 1148/530, loss: 0.005240822210907936
2023-01-21 13:30:37.874190: step: 1152/530, loss: 3.452301098150201e-05
2023-01-21 13:30:39.002292: step: 1156/530, loss: 7.057190487103071e-06
2023-01-21 13:30:40.158442: step: 1160/530, loss: 0.01654491387307644
2023-01-21 13:30:41.289237: step: 1164/530, loss: 6.866455078125e-05
2023-01-21 13:30:42.417875: step: 1168/530, loss: 1.850128137448337e-05
2023-01-21 13:30:43.551129: step: 1172/530, loss: 2.47955322265625e-05
2023-01-21 13:30:44.675290: step: 1176/530, loss: 0.05250587314367294
2023-01-21 13:30:45.840640: step: 1180/530, loss: 0.024602126330137253
2023-01-21 13:30:46.991979: step: 1184/530, loss: 0.0006070137023925781
2023-01-21 13:30:48.112880: step: 1188/530, loss: 0.0005891799810342491
2023-01-21 13:30:49.222388: step: 1192/530, loss: 0.0009168625110760331
2023-01-21 13:30:50.368105: step: 1196/530, loss: 0.003345012664794922
2023-01-21 13:30:51.476812: step: 1200/530, loss: 4.4822695599577855e-06
2023-01-21 13:30:52.601263: step: 1204/530, loss: 0.00022363662719726562
2023-01-21 13:30:53.741554: step: 1208/530, loss: 0.0014486312866210938
2023-01-21 13:30:54.856040: step: 1212/530, loss: 1.9311904907226562e-05
2023-01-21 13:30:55.969406: step: 1216/530, loss: 0.00435905484482646
2023-01-21 13:30:57.093783: step: 1220/530, loss: 5.722046125811175e-07
2023-01-21 13:30:58.194951: step: 1224/530, loss: 0.01454086322337389
2023-01-21 13:30:59.314451: step: 1228/530, loss: 0.00012530684762168676
2023-01-21 13:31:00.430859: step: 1232/530, loss: 7.4386593951203395e-06
2023-01-21 13:31:01.534305: step: 1236/530, loss: 0.00303993234410882
2023-01-21 13:31:02.666625: step: 1240/530, loss: 0.022078227251768112
2023-01-21 13:31:03.799836: step: 1244/530, loss: 7.64846772653982e-05
2023-01-21 13:31:04.914874: step: 1248/530, loss: 0.000225067138671875
2023-01-21 13:31:06.083428: step: 1252/530, loss: 0.014113521203398705
2023-01-21 13:31:07.220038: step: 1256/530, loss: 0.0016180991660803556
2023-01-21 13:31:08.330395: step: 1260/530, loss: 0.000667190586682409
2023-01-21 13:31:09.425613: step: 1264/530, loss: 9.5367431640625e-06
2023-01-21 13:31:10.542354: step: 1268/530, loss: 0.0033041476272046566
2023-01-21 13:31:11.687042: step: 1272/530, loss: 0.0652918815612793
2023-01-21 13:31:12.811079: step: 1276/530, loss: 0.0017426013946533203
2023-01-21 13:31:13.945868: step: 1280/530, loss: 0.00021839141845703125
2023-01-21 13:31:15.086177: step: 1284/530, loss: 0.0005246162763796747
2023-01-21 13:31:16.203620: step: 1288/530, loss: 0.03068218193948269
2023-01-21 13:31:17.311054: step: 1292/530, loss: 0.0006031990051269531
2023-01-21 13:31:18.436508: step: 1296/530, loss: 0.0037992477882653475
2023-01-21 13:31:19.569399: step: 1300/530, loss: 0.007296753115952015
2023-01-21 13:31:20.701252: step: 1304/530, loss: 9.922981553245336e-05
2023-01-21 13:31:21.832434: step: 1308/530, loss: 0.00131397251971066
2023-01-21 13:31:22.951701: step: 1312/530, loss: 0.021523714065551758
2023-01-21 13:31:24.075038: step: 1316/530, loss: 0.006301593966782093
2023-01-21 13:31:25.194486: step: 1320/530, loss: 0.05940885469317436
2023-01-21 13:31:26.312158: step: 1324/530, loss: 8.068084571277723e-05
2023-01-21 13:31:27.394087: step: 1328/530, loss: 0.0001291275111725554
2023-01-21 13:31:28.532231: step: 1332/530, loss: 0.0001401424378855154
2023-01-21 13:31:29.646069: step: 1336/530, loss: 0.0016834258567541838
2023-01-21 13:31:30.759769: step: 1340/530, loss: 0.0017696380382403731
2023-01-21 13:31:31.896410: step: 1344/530, loss: 0.007561111822724342
2023-01-21 13:31:33.015252: step: 1348/530, loss: 3.337860107421875e-05
2023-01-21 13:31:34.181778: step: 1352/530, loss: 0.0014807701809331775
2023-01-21 13:31:35.283696: step: 1356/530, loss: 0.0010259627597406507
2023-01-21 13:31:36.402442: step: 1360/530, loss: 0.004295539576560259
2023-01-21 13:31:37.551606: step: 1364/530, loss: 0.00040435791015625
2023-01-21 13:31:38.709495: step: 1368/530, loss: 7.99179106252268e-05
2023-01-21 13:31:39.822282: step: 1372/530, loss: 3.919601658708416e-05
2023-01-21 13:31:40.954366: step: 1376/530, loss: 0.0005127430194988847
2023-01-21 13:31:42.059662: step: 1380/530, loss: 0.022951554507017136
2023-01-21 13:31:43.190574: step: 1384/530, loss: 0.03648862987756729
2023-01-21 13:31:44.329201: step: 1388/530, loss: 0.00014171600923873484
2023-01-21 13:31:45.457161: step: 1392/530, loss: 0.013144874945282936
2023-01-21 13:31:46.580740: step: 1396/530, loss: 1.430511474609375e-05
2023-01-21 13:31:47.690049: step: 1400/530, loss: 0.013997460715472698
2023-01-21 13:31:48.831474: step: 1404/530, loss: 0.0007356643909588456
2023-01-21 13:31:49.996738: step: 1408/530, loss: 0.00011672973778331652
2023-01-21 13:31:51.116911: step: 1412/530, loss: 0.00097999582067132
2023-01-21 13:31:52.248708: step: 1416/530, loss: 0.040242765098810196
2023-01-21 13:31:53.373880: step: 1420/530, loss: 0.0820918083190918
2023-01-21 13:31:54.529675: step: 1424/530, loss: 3.9386748539982364e-05
2023-01-21 13:31:55.653910: step: 1428/530, loss: 0.0012460709549486637
2023-01-21 13:31:56.777418: step: 1432/530, loss: 0.01254129409790039
2023-01-21 13:31:57.898862: step: 1436/530, loss: 1.487731969973538e-05
2023-01-21 13:31:58.997767: step: 1440/530, loss: 0.0012409210903570056
2023-01-21 13:32:00.096807: step: 1444/530, loss: 1.7023086911649443e-05
2023-01-21 13:32:01.218655: step: 1448/530, loss: 0.007244110107421875
2023-01-21 13:32:02.333279: step: 1452/530, loss: 4.863739013671875e-05
2023-01-21 13:32:03.469231: step: 1456/530, loss: 1.9073486328125e-05
2023-01-21 13:32:04.585606: step: 1460/530, loss: 2.2792815798311494e-05
2023-01-21 13:32:05.707685: step: 1464/530, loss: 0.0006019592401571572
2023-01-21 13:32:06.829188: step: 1468/530, loss: 0.0007682800060138106
2023-01-21 13:32:07.951048: step: 1472/530, loss: 0.0003310680331196636
2023-01-21 13:32:09.061307: step: 1476/530, loss: 7.467270188499242e-05
2023-01-21 13:32:10.199157: step: 1480/530, loss: 0.020303726196289062
2023-01-21 13:32:11.332717: step: 1484/530, loss: 0.027871323749423027
2023-01-21 13:32:12.474381: step: 1488/530, loss: 0.08097591251134872
2023-01-21 13:32:13.563366: step: 1492/530, loss: 8.7738037109375e-05
2023-01-21 13:32:14.684365: step: 1496/530, loss: 0.0005620956653729081
2023-01-21 13:32:15.793637: step: 1500/530, loss: 0.00018367767916060984
2023-01-21 13:32:16.917143: step: 1504/530, loss: 0.0002502441348042339
2023-01-21 13:32:18.038897: step: 1508/530, loss: 0.008749008178710938
2023-01-21 13:32:19.195806: step: 1512/530, loss: 0.00023584366135764867
2023-01-21 13:32:20.321923: step: 1516/530, loss: 0.0005668640369549394
2023-01-21 13:32:21.449262: step: 1520/530, loss: 0.0002513885556254536
2023-01-21 13:32:22.571442: step: 1524/530, loss: -8.39233416627394e-06
2023-01-21 13:32:23.699596: step: 1528/530, loss: 4.634857032215223e-05
2023-01-21 13:32:24.834805: step: 1532/530, loss: 0.0074217794463038445
2023-01-21 13:32:25.985064: step: 1536/530, loss: 0.061150550842285156
2023-01-21 13:32:27.125605: step: 1540/530, loss: 0.009557152166962624
2023-01-21 13:32:28.247844: step: 1544/530, loss: 0.029620077461004257
2023-01-21 13:32:29.393436: step: 1548/530, loss: 9.1552734375e-05
2023-01-21 13:32:30.555607: step: 1552/530, loss: 0.003959464840590954
2023-01-21 13:32:31.708814: step: 1556/530, loss: 1.2779236385540571e-05
2023-01-21 13:32:32.845329: step: 1560/530, loss: 1.850128137448337e-05
2023-01-21 13:32:33.964613: step: 1564/530, loss: 7.686615572310984e-05
2023-01-21 13:32:35.072571: step: 1568/530, loss: 1.144409225162235e-06
2023-01-21 13:32:36.194012: step: 1572/530, loss: 0.000873184239026159
2023-01-21 13:32:37.306590: step: 1576/530, loss: 0.01471166592091322
2023-01-21 13:32:38.444212: step: 1580/530, loss: 4.062652442371473e-05
2023-01-21 13:32:39.548502: step: 1584/530, loss: 1.1062621524615679e-05
2023-01-21 13:32:40.652071: step: 1588/530, loss: 0.11321940273046494
2023-01-21 13:32:41.783854: step: 1592/530, loss: 0.00165729527361691
2023-01-21 13:32:42.894235: step: 1596/530, loss: 0.00014109612675383687
2023-01-21 13:32:44.023924: step: 1600/530, loss: 0.044467777013778687
2023-01-21 13:32:45.116124: step: 1604/530, loss: 0.00013828277587890625
2023-01-21 13:32:46.224119: step: 1608/530, loss: 3.1805036996956915e-05
2023-01-21 13:32:47.368688: step: 1612/530, loss: 5.264282299322076e-05
2023-01-21 13:32:48.495505: step: 1616/530, loss: 0.0006480216979980469
2023-01-21 13:32:49.613020: step: 1620/530, loss: 0.21274375915527344
2023-01-21 13:32:50.715240: step: 1624/530, loss: 0.011458968743681908
2023-01-21 13:32:51.841915: step: 1628/530, loss: 0.3617177903652191
2023-01-21 13:32:52.975564: step: 1632/530, loss: 3.63349899998866e-05
2023-01-21 13:32:54.133690: step: 1636/530, loss: 4.959107172908261e-06
2023-01-21 13:32:55.258155: step: 1640/530, loss: 0.0006572723505087197
2023-01-21 13:32:56.368857: step: 1644/530, loss: 0.018769264221191406
2023-01-21 13:32:57.521291: step: 1648/530, loss: 0.032418251037597656
2023-01-21 13:32:58.613512: step: 1652/530, loss: 0.00014553070650435984
2023-01-21 13:32:59.735859: step: 1656/530, loss: 0.0023059844970703125
2023-01-21 13:33:00.851039: step: 1660/530, loss: 9.450913057662547e-05
2023-01-21 13:33:01.991375: step: 1664/530, loss: 0.037392616271972656
2023-01-21 13:33:03.114906: step: 1668/530, loss: 0.00015087128849700093
2023-01-21 13:33:04.224252: step: 1672/530, loss: 0.0036058425903320312
2023-01-21 13:33:05.355844: step: 1676/530, loss: 0.001372528146021068
2023-01-21 13:33:06.471540: step: 1680/530, loss: 0.001028347061946988
2023-01-21 13:33:07.600837: step: 1684/530, loss: 7.152557373046875e-06
2023-01-21 13:33:08.714242: step: 1688/530, loss: 0.0006948471418581903
2023-01-21 13:33:09.828123: step: 1692/530, loss: 0.0008212566608563066
2023-01-21 13:33:10.962354: step: 1696/530, loss: 3.707162618637085
2023-01-21 13:33:12.079084: step: 1700/530, loss: -1.010894811770413e-05
2023-01-21 13:33:13.211065: step: 1704/530, loss: 0.0007089615100994706
2023-01-21 13:33:14.351818: step: 1708/530, loss: 0.1291082352399826
2023-01-21 13:33:15.469627: step: 1712/530, loss: 0.007496833801269531
2023-01-21 13:33:16.592728: step: 1716/530, loss: 1.182556115963962e-05
2023-01-21 13:33:17.702214: step: 1720/530, loss: 0.005074024200439453
2023-01-21 13:33:18.834414: step: 1724/530, loss: 0.0012141228653490543
2023-01-21 13:33:19.961068: step: 1728/530, loss: 0.0007661819690838456
2023-01-21 13:33:21.103559: step: 1732/530, loss: 0.020349977537989616
2023-01-21 13:33:22.207501: step: 1736/530, loss: 0.0003414154052734375
2023-01-21 13:33:23.328607: step: 1740/530, loss: 0.007851791568100452
2023-01-21 13:33:24.463748: step: 1744/530, loss: 4.215240551275201e-05
2023-01-21 13:33:25.618082: step: 1748/530, loss: 0.0511111281812191
2023-01-21 13:33:26.727678: step: 1752/530, loss: 0.006505107972770929
2023-01-21 13:33:27.871439: step: 1756/530, loss: 0.0012559890747070312
2023-01-21 13:33:28.995909: step: 1760/530, loss: 0.0036535263061523438
2023-01-21 13:33:30.118388: step: 1764/530, loss: 0.00010719298734329641
2023-01-21 13:33:31.258809: step: 1768/530, loss: 0.016880227252840996
2023-01-21 13:33:32.367255: step: 1772/530, loss: 0.001476287841796875
2023-01-21 13:33:33.484565: step: 1776/530, loss: 7.352829561568797e-05
2023-01-21 13:33:34.631416: step: 1780/530, loss: 0.00015754700871184468
2023-01-21 13:33:35.749646: step: 1784/530, loss: 4.882812572759576e-05
2023-01-21 13:33:36.852207: step: 1788/530, loss: 0.005413055885583162
2023-01-21 13:33:37.995920: step: 1792/530, loss: 0.0055335042998194695
2023-01-21 13:33:39.113190: step: 1796/530, loss: 0.0014709711540490389
2023-01-21 13:33:40.234345: step: 1800/530, loss: 0.020827293395996094
2023-01-21 13:33:41.371500: step: 1804/530, loss: 0.015207291580736637
2023-01-21 13:33:42.505308: step: 1808/530, loss: 0.0009137630695477128
2023-01-21 13:33:43.622931: step: 1812/530, loss: -1.8596649624669226e-06
2023-01-21 13:33:44.728097: step: 1816/530, loss: 0.0003429412900004536
2023-01-21 13:33:45.866934: step: 1820/530, loss: 6.67572021484375e-06
2023-01-21 13:33:46.988341: step: 1824/530, loss: 7.095337059581652e-05
2023-01-21 13:33:48.111393: step: 1828/530, loss: 4.348754737293348e-05
2023-01-21 13:33:49.221012: step: 1832/530, loss: 6.904602196300402e-05
2023-01-21 13:33:50.331195: step: 1836/530, loss: 1.1444091796875e-05
2023-01-21 13:33:51.426709: step: 1840/530, loss: 2.9850007194909267e-05
2023-01-21 13:33:52.518263: step: 1844/530, loss: 0.008457946591079235
2023-01-21 13:33:53.645081: step: 1848/530, loss: 1.9550323486328125e-05
2023-01-21 13:33:54.754991: step: 1852/530, loss: 1.5735627130197827e-06
2023-01-21 13:33:55.892145: step: 1856/530, loss: 2.0313264030846767e-05
2023-01-21 13:33:57.011385: step: 1860/530, loss: 8.20159948489163e-06
2023-01-21 13:33:58.132488: step: 1864/530, loss: 0.00018796921358443797
2023-01-21 13:33:59.234491: step: 1868/530, loss: 5.722044988942798e-07
2023-01-21 13:34:00.360314: step: 1872/530, loss: 0.0005973816150799394
2023-01-21 13:34:01.476347: step: 1876/530, loss: 4.959107172908261e-06
2023-01-21 13:34:02.589136: step: 1880/530, loss: 0.0010441780323162675
2023-01-21 13:34:03.691885: step: 1884/530, loss: 0.00104017264675349
2023-01-21 13:34:04.808158: step: 1888/530, loss: 0.007729530334472656
2023-01-21 13:34:05.939101: step: 1892/530, loss: 1.1444091796875e-05
2023-01-21 13:34:07.027163: step: 1896/530, loss: 9.536744073557202e-06
2023-01-21 13:34:08.175527: step: 1900/530, loss: 5.1212311518611386e-05
2023-01-21 13:34:09.286512: step: 1904/530, loss: 3.757476952159777e-05
2023-01-21 13:34:10.416935: step: 1908/530, loss: 0.0032654760871082544
2023-01-21 13:34:11.549108: step: 1912/530, loss: 0.00033016205998137593
2023-01-21 13:34:12.663872: step: 1916/530, loss: 0.015048027969896793
2023-01-21 13:34:13.770295: step: 1920/530, loss: 0.041097067296504974
2023-01-21 13:34:14.862633: step: 1924/530, loss: 0.012709617614746094
2023-01-21 13:34:15.979424: step: 1928/530, loss: 0.07657375186681747
2023-01-21 13:34:17.103526: step: 1932/530, loss: 0.0003211974981240928
2023-01-21 13:34:18.250777: step: 1936/530, loss: 0.0002628326474223286
2023-01-21 13:34:19.374470: step: 1940/530, loss: 0.0007530212169513106
2023-01-21 13:34:20.487169: step: 1944/530, loss: 0.0001944542018463835
2023-01-21 13:34:21.606103: step: 1948/530, loss: 4.138946678722277e-05
2023-01-21 13:34:22.754507: step: 1952/530, loss: 1.5258810890372843e-06
2023-01-21 13:34:23.869268: step: 1956/530, loss: 2.4414061044808477e-05
2023-01-21 13:34:24.984772: step: 1960/530, loss: 0.0005186080816201866
2023-01-21 13:34:26.102066: step: 1964/530, loss: 1.8596649169921875e-05
2023-01-21 13:34:27.211669: step: 1968/530, loss: 0.00014038087101653218
2023-01-21 13:34:28.359702: step: 1972/530, loss: 0.017737960442900658
2023-01-21 13:34:29.536629: step: 1976/530, loss: 0.05726933479309082
2023-01-21 13:34:30.693237: step: 1980/530, loss: 0.0063987732864916325
2023-01-21 13:34:31.806175: step: 1984/530, loss: 0.010416317731142044
2023-01-21 13:34:32.946355: step: 1988/530, loss: 1.411438006471144e-05
2023-01-21 13:34:34.057816: step: 1992/530, loss: 4.57763690064894e-06
2023-01-21 13:34:35.210032: step: 1996/530, loss: 0.0006276131025515497
2023-01-21 13:34:36.331850: step: 2000/530, loss: 0.027610303834080696
2023-01-21 13:34:37.443094: step: 2004/530, loss: 0.0029823302756994963
2023-01-21 13:34:38.556358: step: 2008/530, loss: 8.106231689453125e-06
2023-01-21 13:34:39.677520: step: 2012/530, loss: 0.007798385806381702
2023-01-21 13:34:40.796010: step: 2016/530, loss: 0.002561855362728238
2023-01-21 13:34:41.906773: step: 2020/530, loss: 0.009146117605268955
2023-01-21 13:34:43.020659: step: 2024/530, loss: 0.08603902161121368
2023-01-21 13:34:44.159208: step: 2028/530, loss: 0.0023164749145507812
2023-01-21 13:34:45.299593: step: 2032/530, loss: 0.00018539429584052414
2023-01-21 13:34:46.393331: step: 2036/530, loss: 0.0003789901966229081
2023-01-21 13:34:47.522383: step: 2040/530, loss: 0.0009212493896484375
2023-01-21 13:34:48.650537: step: 2044/530, loss: 0.0001682281435932964
2023-01-21 13:34:49.767296: step: 2048/530, loss: 0.0015082359313964844
2023-01-21 13:34:50.886182: step: 2052/530, loss: 0.0013895988231524825
2023-01-21 13:34:52.026560: step: 2056/530, loss: 5.874633643543348e-05
2023-01-21 13:34:53.143919: step: 2060/530, loss: 0.0005882263649255037
2023-01-21 13:34:54.274605: step: 2064/530, loss: 9.422301809536293e-05
2023-01-21 13:34:55.393766: step: 2068/530, loss: 0.034859661012887955
2023-01-21 13:34:56.498393: step: 2072/530, loss: 1.163482647825731e-05
2023-01-21 13:34:57.613047: step: 2076/530, loss: 4.19616708313697e-06
2023-01-21 13:34:58.733434: step: 2080/530, loss: 0.0001239776611328125
2023-01-21 13:34:59.836543: step: 2084/530, loss: 0.00015316010103560984
2023-01-21 13:35:00.944876: step: 2088/530, loss: 0.005597210023552179
2023-01-21 13:35:02.075056: step: 2092/530, loss: 0.029268836602568626
2023-01-21 13:35:03.231194: step: 2096/530, loss: 0.0008559227571822703
2023-01-21 13:35:04.339554: step: 2100/530, loss: 0.4550245404243469
2023-01-21 13:35:05.456939: step: 2104/530, loss: 0.00037784577580168843
2023-01-21 13:35:06.587928: step: 2108/530, loss: 0.0013015747535973787
2023-01-21 13:35:07.774345: step: 2112/530, loss: 6.29425048828125e-05
2023-01-21 13:35:08.891178: step: 2116/530, loss: 0.0007175445789471269
2023-01-21 13:35:10.028367: step: 2120/530, loss: 0.0687929168343544
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.7083333333333334, 'r': 0.5396825396825397, 'f1': 0.6126126126126126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.525, 'r': 0.5833333333333334, 'f1': 0.5526315789473685}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Eng Test for Chinese: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Sample Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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
2023-01-21 13:35:57.537052: step: 4/530, loss: 0.00079345703125
2023-01-21 13:35:58.687540: step: 8/530, loss: 1.5509127479163e-05
2023-01-21 13:35:59.788605: step: 12/530, loss: 0.019551753997802734
2023-01-21 13:36:00.897952: step: 16/530, loss: 0.021620750427246094
2023-01-21 13:36:02.032078: step: 20/530, loss: 1.1253358024987392e-05
2023-01-21 13:36:03.176504: step: 24/530, loss: 0.04051017761230469
2023-01-21 13:36:04.304417: step: 28/530, loss: 9.975433204090223e-05
2023-01-21 13:36:05.418572: step: 32/530, loss: 0.0012271881569176912
2023-01-21 13:36:06.546989: step: 36/530, loss: 0.0005517005920410156
2023-01-21 13:36:07.654859: step: 40/530, loss: 0.017620563507080078
2023-01-21 13:36:08.770703: step: 44/530, loss: 0.011277580633759499
2023-01-21 13:36:09.897249: step: 48/530, loss: 0.002271413803100586
2023-01-21 13:36:11.059423: step: 52/530, loss: 0.0003104209899902344
2023-01-21 13:36:12.175803: step: 56/530, loss: 0.010919761843979359
2023-01-21 13:36:13.319344: step: 60/530, loss: 0.013683080673217773
2023-01-21 13:36:14.446786: step: 64/530, loss: 0.006194401066750288
2023-01-21 13:36:15.551066: step: 68/530, loss: 1.4400481632037554e-05
2023-01-21 13:36:16.666969: step: 72/530, loss: 0.0048118592239916325
2023-01-21 13:36:17.771401: step: 76/530, loss: 2.174377368646674e-05
2023-01-21 13:36:18.883949: step: 80/530, loss: 9.536744300930877e-07
2023-01-21 13:36:20.014973: step: 84/530, loss: 0.04347953572869301
2023-01-21 13:36:21.125892: step: 88/530, loss: 0.00010375976853538305
2023-01-21 13:36:22.224931: step: 92/530, loss: 0.002568531082943082
2023-01-21 13:36:23.362345: step: 96/530, loss: 5.53131121705519e-06
2023-01-21 13:36:24.501570: step: 100/530, loss: 2.841949390131049e-05
2023-01-21 13:36:25.608222: step: 104/530, loss: 0.010214042849838734
2023-01-21 13:36:26.786992: step: 108/530, loss: 0.0001184463471872732
2023-01-21 13:36:27.936138: step: 112/530, loss: 9.460448927711695e-05
2023-01-21 13:36:29.043792: step: 116/530, loss: 0.44897136092185974
2023-01-21 13:36:30.148243: step: 120/530, loss: 8.96453857421875e-05
2023-01-21 13:36:31.275289: step: 124/530, loss: 0.007636642549186945
2023-01-21 13:36:32.404675: step: 128/530, loss: 7.314682443393394e-05
2023-01-21 13:36:33.515931: step: 132/530, loss: 1.106262243411038e-05
2023-01-21 13:36:34.654286: step: 136/530, loss: 2.460479663568549e-05
2023-01-21 13:36:35.766456: step: 140/530, loss: 2.956390289909905e-06
2023-01-21 13:36:36.868436: step: 144/530, loss: 2.288818359375e-05
2023-01-21 13:36:37.986817: step: 148/530, loss: 0.018181229010224342
2023-01-21 13:36:39.147071: step: 152/530, loss: 0.019393444061279297
2023-01-21 13:36:40.261491: step: 156/530, loss: 3.051757857974735e-06
2023-01-21 13:36:41.375189: step: 160/530, loss: 0.0005416870699264109
2023-01-21 13:36:42.505935: step: 164/530, loss: 0.012201404199004173
2023-01-21 13:36:43.650518: step: 168/530, loss: 0.054689787328243256
2023-01-21 13:36:44.780855: step: 172/530, loss: 0.12627945840358734
2023-01-21 13:36:45.890790: step: 176/530, loss: 0.0007482529035769403
2023-01-21 13:36:46.977485: step: 180/530, loss: 1.544952465337701e-05
2023-01-21 13:36:48.098502: step: 184/530, loss: 1.3828277587890625e-05
2023-01-21 13:36:49.219321: step: 188/530, loss: 8.220673043979332e-05
2023-01-21 13:36:50.333976: step: 192/530, loss: 2.670288040462765e-06
2023-01-21 13:36:51.456183: step: 196/530, loss: 0.005424118135124445
2023-01-21 13:36:52.584943: step: 200/530, loss: 2.6702882678364404e-06
2023-01-21 13:36:53.701746: step: 204/530, loss: 0.025966264307498932
2023-01-21 13:36:54.815290: step: 208/530, loss: 1.8978118532686494e-05
2023-01-21 13:36:55.958910: step: 212/530, loss: 0.00042548179044388235
2023-01-21 13:36:57.126421: step: 216/530, loss: 0.0030125619377940893
2023-01-21 13:36:58.250104: step: 220/530, loss: 0.014338708482682705
2023-01-21 13:36:59.378963: step: 224/530, loss: 0.00021138192096259445
2023-01-21 13:37:00.462639: step: 228/530, loss: 2.6702882678364404e-06
2023-01-21 13:37:01.571624: step: 232/530, loss: -5.5313107623078395e-06
2023-01-21 13:37:02.684745: step: 236/530, loss: 0.00017042159743141383
2023-01-21 13:37:03.814731: step: 240/530, loss: 1.6975405742414296e-05
2023-01-21 13:37:04.944029: step: 244/530, loss: 0.0014446259010583162
2023-01-21 13:37:06.052853: step: 248/530, loss: 8.616447303211316e-05
2023-01-21 13:37:07.139949: step: 252/530, loss: 0.0004924774402752519
2023-01-21 13:37:08.257410: step: 256/530, loss: 1.62124638336536e-06
2023-01-21 13:37:09.366270: step: 260/530, loss: 0.000396728515625
2023-01-21 13:37:10.488356: step: 264/530, loss: 4.978180004400201e-05
2023-01-21 13:37:11.618399: step: 268/530, loss: 0.0004265785391908139
2023-01-21 13:37:12.777011: step: 272/530, loss: -1.3351441339182202e-06
2023-01-21 13:37:13.879842: step: 276/530, loss: 4.38690185546875e-05
2023-01-21 13:37:14.974053: step: 280/530, loss: 0.0010662078857421875
2023-01-21 13:37:16.124897: step: 284/530, loss: 6.809234037064016e-05
2023-01-21 13:37:17.228573: step: 288/530, loss: 0.00013213157944846898
2023-01-21 13:37:18.351158: step: 292/530, loss: 0.00015316010103560984
2023-01-21 13:37:19.476333: step: 296/530, loss: 0.0009434223757125437
2023-01-21 13:37:20.629008: step: 300/530, loss: 0.007957267574965954
2023-01-21 13:37:21.757552: step: 304/530, loss: 0.11589831858873367
2023-01-21 13:37:22.886984: step: 308/530, loss: 0.002113723661750555
2023-01-21 13:37:23.998860: step: 312/530, loss: 0.00020542144193314016
2023-01-21 13:37:25.138183: step: 316/530, loss: 5.874633643543348e-05
2023-01-21 13:37:26.254290: step: 320/530, loss: 0.0035803914070129395
2023-01-21 13:37:27.385434: step: 324/530, loss: 0.0015953064430505037
2023-01-21 13:37:28.491513: step: 328/530, loss: 4.062652442371473e-05
2023-01-21 13:37:29.610474: step: 332/530, loss: 4.3487551010912284e-05
2023-01-21 13:37:30.739484: step: 336/530, loss: 8.39233416627394e-06
2023-01-21 13:37:31.886373: step: 340/530, loss: 0.0023468018043786287
2023-01-21 13:37:33.124106: step: 344/530, loss: 0.001714515732601285
2023-01-21 13:37:34.255979: step: 348/530, loss: 0.00026216506375931203
2023-01-21 13:37:35.373526: step: 352/530, loss: 0.0325162410736084
2023-01-21 13:37:36.474660: step: 356/530, loss: 0.00040836335392668843
2023-01-21 13:37:37.624344: step: 360/530, loss: 0.014062691479921341
2023-01-21 13:37:38.743655: step: 364/530, loss: 0.00017700194439385086
2023-01-21 13:37:39.851914: step: 368/530, loss: 0.0025928497780114412
2023-01-21 13:37:40.970487: step: 372/530, loss: 0.0033207894302904606
2023-01-21 13:37:42.052573: step: 376/530, loss: 2.8038026357535273e-05
2023-01-21 13:37:43.162444: step: 380/530, loss: 6.10351571594947e-06
2023-01-21 13:37:44.280253: step: 384/530, loss: 7.152557373046875e-06
2023-01-21 13:37:45.418491: step: 388/530, loss: 0.038664769381284714
2023-01-21 13:37:46.545054: step: 392/530, loss: 1.487731969973538e-05
2023-01-21 13:37:47.678782: step: 396/530, loss: 0.05026111751794815
2023-01-21 13:37:48.783457: step: 400/530, loss: 0.00047369004460051656
2023-01-21 13:37:49.900887: step: 404/530, loss: 3.3950807846849784e-05
2023-01-21 13:37:51.012838: step: 408/530, loss: 0.004271125886589289
2023-01-21 13:37:52.120612: step: 412/530, loss: 0.06146135553717613
2023-01-21 13:37:53.214954: step: 416/530, loss: 0.00027561187744140625
2023-01-21 13:37:54.339800: step: 420/530, loss: 0.013042259030044079
2023-01-21 13:37:55.435976: step: 424/530, loss: 0.027518462389707565
2023-01-21 13:37:56.528784: step: 428/530, loss: 0.0008126259199343622
2023-01-21 13:37:57.623199: step: 432/530, loss: 7.82012921263231e-06
2023-01-21 13:37:58.764804: step: 436/530, loss: 0.0009278059005737305
2023-01-21 13:37:59.923714: step: 440/530, loss: 0.0014368057018145919
2023-01-21 13:38:01.038640: step: 444/530, loss: 0.034787844866514206
2023-01-21 13:38:02.156794: step: 448/530, loss: 0.00036087038461118937
2023-01-21 13:38:03.275666: step: 452/530, loss: 0.0007333755493164062
2023-01-21 13:38:04.414050: step: 456/530, loss: 0.008822965435683727
2023-01-21 13:38:05.543270: step: 460/530, loss: 0.02304835431277752
2023-01-21 13:38:06.706497: step: 464/530, loss: 0.00293560023419559
2023-01-21 13:38:07.827376: step: 468/530, loss: 5.2738188969669864e-05
2023-01-21 13:38:08.945766: step: 472/530, loss: 0.061448004096746445
2023-01-21 13:38:10.068875: step: 476/530, loss: 0.08494148403406143
2023-01-21 13:38:11.207130: step: 480/530, loss: 0.009108400903642178
2023-01-21 13:38:12.346522: step: 484/530, loss: 0.01986703835427761
2023-01-21 13:38:13.472788: step: 488/530, loss: 0.014183616265654564
2023-01-21 13:38:14.656610: step: 492/530, loss: 0.0032669068314135075
2023-01-21 13:38:15.751525: step: 496/530, loss: 0.22437401115894318
2023-01-21 13:38:16.861284: step: 500/530, loss: 0.015742206946015358
2023-01-21 13:38:17.981964: step: 504/530, loss: 1.2302398317842744e-05
2023-01-21 13:38:19.132032: step: 508/530, loss: 0.00033054352388717234
2023-01-21 13:38:20.242748: step: 512/530, loss: 0.035310935229063034
2023-01-21 13:38:21.351715: step: 516/530, loss: 0.00014743805513717234
2023-01-21 13:38:22.443343: step: 520/530, loss: 1.659393274167087e-05
2023-01-21 13:38:23.534048: step: 524/530, loss: 0.0001928329438669607
2023-01-21 13:38:24.622340: step: 528/530, loss: 1.735687328618951e-05
2023-01-21 13:38:25.757136: step: 532/530, loss: 0.0001472473086323589
2023-01-21 13:38:26.892162: step: 536/530, loss: 0.00209388742223382
2023-01-21 13:38:27.991030: step: 540/530, loss: 0.0001644134463276714
2023-01-21 13:38:29.143417: step: 544/530, loss: 0.00508384732529521
2023-01-21 13:38:30.245974: step: 548/530, loss: 0.002101993653923273
2023-01-21 13:38:31.353300: step: 552/530, loss: 0.03772277757525444
2023-01-21 13:38:32.493283: step: 556/530, loss: 0.00019149780564475805
2023-01-21 13:38:33.618135: step: 560/530, loss: 6.942749314475805e-05
2023-01-21 13:38:34.736007: step: 564/530, loss: 0.09079819172620773
2023-01-21 13:38:35.860138: step: 568/530, loss: 0.0001126289353123866
2023-01-21 13:38:36.944359: step: 572/530, loss: 0.0027053833473473787
2023-01-21 13:38:38.036463: step: 576/530, loss: 0.0010382652981206775
2023-01-21 13:38:39.165022: step: 580/530, loss: 0.00031909943209029734
2023-01-21 13:38:40.293101: step: 584/530, loss: 0.000604820204898715
2023-01-21 13:38:41.415907: step: 588/530, loss: 5.9127810345671605e-06
2023-01-21 13:38:42.544882: step: 592/530, loss: 0.0003447532653808594
2023-01-21 13:38:43.703884: step: 596/530, loss: 0.00018482207087799907
2023-01-21 13:38:44.815158: step: 600/530, loss: 0.009919453412294388
2023-01-21 13:38:45.953294: step: 604/530, loss: 3.44276413670741e-05
2023-01-21 13:38:47.067948: step: 608/530, loss: 0.006410503294318914
2023-01-21 13:38:48.189928: step: 612/530, loss: 0.00015934706607367843
2023-01-21 13:38:49.335335: step: 616/530, loss: 0.01974477805197239
2023-01-21 13:38:50.453002: step: 620/530, loss: 0.011882972903549671
2023-01-21 13:38:51.574600: step: 624/530, loss: 1.5735631677671336e-06
2023-01-21 13:38:52.671511: step: 628/530, loss: 0.0017063141567632556
2023-01-21 13:38:53.772495: step: 632/530, loss: 0.0005319595220498741
2023-01-21 13:38:54.922930: step: 636/530, loss: 0.004999542608857155
2023-01-21 13:38:56.008007: step: 640/530, loss: 0.00010442733764648438
2023-01-21 13:38:57.133396: step: 644/530, loss: 0.04184231907129288
2023-01-21 13:38:58.243299: step: 648/530, loss: 0.00018548966909293085
2023-01-21 13:38:59.388533: step: 652/530, loss: 0.017480850219726562
2023-01-21 13:39:00.552233: step: 656/530, loss: 0.0011454581981524825
2023-01-21 13:39:01.660758: step: 660/530, loss: 1.6021729607018642e-05
2023-01-21 13:39:02.747862: step: 664/530, loss: 2.6130677724722773e-05
2023-01-21 13:39:03.880048: step: 668/530, loss: 0.03771800920367241
2023-01-21 13:39:04.981099: step: 672/530, loss: 9.226799193129409e-06
2023-01-21 13:39:06.090709: step: 676/530, loss: 7.677078974666074e-05
2023-01-21 13:39:07.214755: step: 680/530, loss: 0.04489760473370552
2023-01-21 13:39:08.310353: step: 684/530, loss: 0.015763282775878906
2023-01-21 13:39:09.454670: step: 688/530, loss: 0.0006033897516317666
2023-01-21 13:39:10.608112: step: 692/530, loss: 0.0003755569632630795
2023-01-21 13:39:11.723037: step: 696/530, loss: 0.0007669448968954384
2023-01-21 13:39:12.838160: step: 700/530, loss: 4.291534423828125e-06
2023-01-21 13:39:13.956437: step: 704/530, loss: 0.0007427215459756553
2023-01-21 13:39:15.082064: step: 708/530, loss: 0.00571098318323493
2023-01-21 13:39:16.220904: step: 712/530, loss: 0.011141491122543812
2023-01-21 13:39:17.325345: step: 716/530, loss: 1.430511474609375e-06
2023-01-21 13:39:18.439303: step: 720/530, loss: 0.20702685415744781
2023-01-21 13:39:19.568968: step: 724/530, loss: 0.012928485870361328
2023-01-21 13:39:20.689576: step: 728/530, loss: 0.002323722932487726
2023-01-21 13:39:21.795262: step: 732/530, loss: 0.020373154431581497
2023-01-21 13:39:22.913626: step: 736/530, loss: 0.008115767501294613
2023-01-21 13:39:24.014464: step: 740/530, loss: 0.0003360748232807964
2023-01-21 13:39:25.120375: step: 744/530, loss: 0.12447166442871094
2023-01-21 13:39:26.272113: step: 748/530, loss: 5.2118302846793085e-05
2023-01-21 13:39:27.393419: step: 752/530, loss: 0.0001142501860158518
2023-01-21 13:39:28.510005: step: 756/530, loss: 0.0004748344363179058
2023-01-21 13:39:29.618224: step: 760/530, loss: 0.015793515369296074
2023-01-21 13:39:30.744591: step: 764/530, loss: 0.00022301674471236765
2023-01-21 13:39:31.887568: step: 768/530, loss: 0.1791359931230545
2023-01-21 13:39:33.021145: step: 772/530, loss: 0.0017072678310796618
2023-01-21 13:39:34.132846: step: 776/530, loss: 0.0023328782990574837
2023-01-21 13:39:35.205717: step: 780/530, loss: 0.0023365020751953125
2023-01-21 13:39:36.308694: step: 784/530, loss: 8.361339860130101e-05
2023-01-21 13:39:37.420627: step: 788/530, loss: 0.006721973419189453
2023-01-21 13:39:38.569027: step: 792/530, loss: 3.2949446904240176e-05
2023-01-21 13:39:39.706849: step: 796/530, loss: 0.004120540805160999
2023-01-21 13:39:40.848437: step: 800/530, loss: 3.1805036996956915e-05
2023-01-21 13:39:41.995437: step: 804/530, loss: 0.0010140062076970935
2023-01-21 13:39:43.124973: step: 808/530, loss: 0.0009886741172522306
2023-01-21 13:39:44.233580: step: 812/530, loss: 0.0016706467140465975
2023-01-21 13:39:45.350171: step: 816/530, loss: 0.0001350402890238911
2023-01-21 13:39:46.445546: step: 820/530, loss: 0.0010343551402911544
2023-01-21 13:39:47.591191: step: 824/530, loss: 0.00015325545973610133
2023-01-21 13:39:48.717339: step: 828/530, loss: -8.96453821042087e-06
2023-01-21 13:39:49.840846: step: 832/530, loss: 0.00033946038456633687
2023-01-21 13:39:50.948176: step: 836/530, loss: 0.025153733789920807
2023-01-21 13:39:52.077106: step: 840/530, loss: 1.8882752556237392e-05
2023-01-21 13:39:53.209832: step: 844/530, loss: 0.0014745712978765368
2023-01-21 13:39:54.342577: step: 848/530, loss: 0.00015897752018645406
2023-01-21 13:39:55.456178: step: 852/530, loss: 5.574226088356227e-05
2023-01-21 13:39:56.553630: step: 856/530, loss: 0.00037593842716887593
2023-01-21 13:39:57.710054: step: 860/530, loss: 4.081726001459174e-05
2023-01-21 13:39:58.813609: step: 864/530, loss: 0.0012316703796386719
2023-01-21 13:39:59.953047: step: 868/530, loss: 0.0010339736472815275
2023-01-21 13:40:01.095348: step: 872/530, loss: 0.00020675659470725805
2023-01-21 13:40:02.201619: step: 876/530, loss: 0.004602527711540461
2023-01-21 13:40:03.341180: step: 880/530, loss: 0.00017337800818495452
2023-01-21 13:40:04.475880: step: 884/530, loss: 0.03265686333179474
2023-01-21 13:40:05.602528: step: 888/530, loss: 0.01048431359231472
2023-01-21 13:40:06.704261: step: 892/530, loss: 6.86645489622606e-06
2023-01-21 13:40:07.820602: step: 896/530, loss: 0.006386566441506147
2023-01-21 13:40:08.945731: step: 900/530, loss: 3.833770824712701e-05
2023-01-21 13:40:10.084005: step: 904/530, loss: 8.010864803509321e-06
2023-01-21 13:40:11.193585: step: 908/530, loss: 0.0010983466636389494
2023-01-21 13:40:12.327471: step: 912/530, loss: 1.5163421267061494e-05
2023-01-21 13:40:13.453275: step: 916/530, loss: 0.00011682510375976562
2023-01-21 13:40:14.595084: step: 920/530, loss: 1.583099401614163e-05
2023-01-21 13:40:15.749485: step: 924/530, loss: 2.1076200937386602e-05
2023-01-21 13:40:16.873598: step: 928/530, loss: 0.0025695799849927425
2023-01-21 13:40:18.036084: step: 932/530, loss: -3.623962356869015e-06
2023-01-21 13:40:19.148288: step: 936/530, loss: 0.0005474090576171875
2023-01-21 13:40:20.253203: step: 940/530, loss: 8.292197890114039e-05
2023-01-21 13:40:21.370842: step: 944/530, loss: 0.0005310059059411287
2023-01-21 13:40:22.538978: step: 948/530, loss: -3.814698175119702e-07
2023-01-21 13:40:23.656201: step: 952/530, loss: 0.0001771926908986643
2023-01-21 13:40:24.770386: step: 956/530, loss: 0.01968097686767578
2023-01-21 13:40:25.867263: step: 960/530, loss: 0.0007839202880859375
2023-01-21 13:40:27.000799: step: 964/530, loss: 0.006590843666344881
2023-01-21 13:40:28.086205: step: 968/530, loss: -6.29425039733178e-06
2023-01-21 13:40:29.197336: step: 972/530, loss: 0.7183490991592407
2023-01-21 13:40:30.349837: step: 976/530, loss: -5.722045557376987e-07
2023-01-21 13:40:31.467345: step: 980/530, loss: 2.765655608527595e-06
2023-01-21 13:40:32.599471: step: 984/530, loss: 0.00017633438983466476
2023-01-21 13:40:33.722791: step: 988/530, loss: 6.523132469737902e-05
2023-01-21 13:40:34.822231: step: 992/530, loss: 3.2138825190486386e-05
2023-01-21 13:40:35.950017: step: 996/530, loss: 0.00048065185546875
2023-01-21 13:40:37.068481: step: 1000/530, loss: 2.4795533590804553e-06
2023-01-21 13:40:38.193560: step: 1004/530, loss: 0.011059284210205078
2023-01-21 13:40:39.293053: step: 1008/530, loss: 4.940032886224799e-05
2023-01-21 13:40:40.429709: step: 1012/530, loss: 3.814697265625e-05
2023-01-21 13:40:41.555065: step: 1016/530, loss: 3.509521411615424e-05
2023-01-21 13:40:42.678431: step: 1020/530, loss: 0.0050761220045387745
2023-01-21 13:40:43.852920: step: 1024/530, loss: 0.011490631848573685
2023-01-21 13:40:44.977119: step: 1028/530, loss: 0.00021901131549384445
2023-01-21 13:40:46.083098: step: 1032/530, loss: 0.09355153888463974
2023-01-21 13:40:47.200224: step: 1036/530, loss: 4.9591064453125e-05
2023-01-21 13:40:48.307682: step: 1040/530, loss: 3.414153979974799e-05
2023-01-21 13:40:49.448896: step: 1044/530, loss: 0.009853744879364967
2023-01-21 13:40:50.584300: step: 1048/530, loss: 0.011802864260971546
2023-01-21 13:40:51.696529: step: 1052/530, loss: 0.0032684325706213713
2023-01-21 13:40:52.819376: step: 1056/530, loss: 0.0016590118175372481
2023-01-21 13:40:53.926279: step: 1060/530, loss: 0.04302871227264404
2023-01-21 13:40:55.039987: step: 1064/530, loss: 2.422332727292087e-05
2023-01-21 13:40:56.152813: step: 1068/530, loss: 1.583099401614163e-05
2023-01-21 13:40:57.263043: step: 1072/530, loss: 0.00019731521024368703
2023-01-21 13:40:58.390163: step: 1076/530, loss: 0.00016350747318938375
2023-01-21 13:40:59.489632: step: 1080/530, loss: 1.71661376953125e-05
2023-01-21 13:41:00.585960: step: 1084/530, loss: 0.4312833547592163
2023-01-21 13:41:01.707552: step: 1088/530, loss: 0.0005179405561648309
2023-01-21 13:41:02.875038: step: 1092/530, loss: 0.0004741668817587197
2023-01-21 13:41:04.035941: step: 1096/530, loss: 0.005675507243722677
2023-01-21 13:41:05.151206: step: 1100/530, loss: 0.031122399494051933
2023-01-21 13:41:06.285258: step: 1104/530, loss: 0.0034559250343590975
2023-01-21 13:41:07.405663: step: 1108/530, loss: 0.0001655578671488911
2023-01-21 13:41:08.537237: step: 1112/530, loss: -4.00543194700731e-06
2023-01-21 13:41:09.654451: step: 1116/530, loss: 1.9073486328125e-06
2023-01-21 13:41:10.762439: step: 1120/530, loss: 2.3937225705594756e-05
2023-01-21 13:41:11.894413: step: 1124/530, loss: 0.00945138931274414
2023-01-21 13:41:13.037452: step: 1128/530, loss: 0.08567800372838974
2023-01-21 13:41:14.165026: step: 1132/530, loss: 0.020180892199277878
2023-01-21 13:41:15.298587: step: 1136/530, loss: 0.0748104527592659
2023-01-21 13:41:16.395468: step: 1140/530, loss: 0.0011360167991369963
2023-01-21 13:41:17.496263: step: 1144/530, loss: 0.0010410308605059981
2023-01-21 13:41:18.600732: step: 1148/530, loss: 3.8623809814453125e-05
2023-01-21 13:41:19.741293: step: 1152/530, loss: 0.005289745517075062
2023-01-21 13:41:20.837884: step: 1156/530, loss: 0.00014171600923873484
2023-01-21 13:41:21.973656: step: 1160/530, loss: 0.01902141608297825
2023-01-21 13:41:23.081766: step: 1164/530, loss: 0.0044425963424146175
2023-01-21 13:41:24.226605: step: 1168/530, loss: 0.0018917083507403731
2023-01-21 13:41:25.363128: step: 1172/530, loss: -1.9073486328125e-06
2023-01-21 13:41:26.496885: step: 1176/530, loss: 9.183883958030492e-05
2023-01-21 13:41:27.617921: step: 1180/530, loss: 5.226135181146674e-05
2023-01-21 13:41:28.745202: step: 1184/530, loss: 0.00020675659470725805
2023-01-21 13:41:29.880921: step: 1188/530, loss: 0.003336047986522317
2023-01-21 13:41:31.006673: step: 1192/530, loss: 0.011052894406020641
2023-01-21 13:41:32.149334: step: 1196/530, loss: 7.705688767600805e-05
2023-01-21 13:41:33.286332: step: 1200/530, loss: 0.0025212287437170744
2023-01-21 13:41:34.436792: step: 1204/530, loss: 1.487731969973538e-05
2023-01-21 13:41:35.535605: step: 1208/530, loss: 0.016433142125606537
2023-01-21 13:41:36.637102: step: 1212/530, loss: 3.1471254260395654e-06
2023-01-21 13:41:37.766453: step: 1216/530, loss: 0.030451392754912376
2023-01-21 13:41:38.856160: step: 1220/530, loss: 0.016788482666015625
2023-01-21 13:41:39.987092: step: 1224/530, loss: 0.00016136169142555445
2023-01-21 13:41:41.144084: step: 1228/530, loss: 2.9373170036706142e-05
2023-01-21 13:41:42.266815: step: 1232/530, loss: 0.6264863610267639
2023-01-21 13:41:43.410467: step: 1236/530, loss: 0.0001085281401174143
2023-01-21 13:41:44.519691: step: 1240/530, loss: 0.0015645980602130294
2023-01-21 13:41:45.631816: step: 1244/530, loss: 0.0003445625479798764
2023-01-21 13:41:46.743727: step: 1248/530, loss: 0.0004322052118368447
2023-01-21 13:41:47.867966: step: 1252/530, loss: 0.012646770104765892
2023-01-21 13:41:48.996020: step: 1256/530, loss: 0.17248135805130005
2023-01-21 13:41:50.093760: step: 1260/530, loss: 0.00039463042048737407
2023-01-21 13:41:51.226201: step: 1264/530, loss: 0.008760261349380016
2023-01-21 13:41:52.376149: step: 1268/530, loss: 0.021333791315555573
2023-01-21 13:41:53.519603: step: 1272/530, loss: 0.0022455216385424137
2023-01-21 13:41:54.645145: step: 1276/530, loss: 7.343292963923886e-05
2023-01-21 13:41:55.773539: step: 1280/530, loss: 0.0006988525274209678
2023-01-21 13:41:56.887338: step: 1284/530, loss: 1.506805438111769e-05
2023-01-21 13:41:57.995348: step: 1288/530, loss: 0.12216072529554367
2023-01-21 13:41:59.134476: step: 1292/530, loss: 0.23700428009033203
2023-01-21 13:42:00.261741: step: 1296/530, loss: 2.6702882678364404e-06
2023-01-21 13:42:01.409371: step: 1300/530, loss: 2.354684829711914
2023-01-21 13:42:02.514430: step: 1304/530, loss: 0.00035858154296875
2023-01-21 13:42:03.669645: step: 1308/530, loss: 1.5926361811580136e-05
2023-01-21 13:42:04.773801: step: 1312/530, loss: 3.757476952159777e-05
2023-01-21 13:42:05.913065: step: 1316/530, loss: 1.9073486328125e-05
2023-01-21 13:42:07.035631: step: 1320/530, loss: 0.001146507216617465
2023-01-21 13:42:08.155343: step: 1324/530, loss: 0.08950471878051758
2023-01-21 13:42:09.279379: step: 1328/530, loss: 0.0017413139576092362
2023-01-21 13:42:10.391619: step: 1332/530, loss: 6.0653688706224784e-05
2023-01-21 13:42:11.561579: step: 1336/530, loss: 0.002889251569285989
2023-01-21 13:42:12.703339: step: 1340/530, loss: 3.814697265625e-06
2023-01-21 13:42:13.798554: step: 1344/530, loss: 2.5153160095214844e-05
2023-01-21 13:42:14.937579: step: 1348/530, loss: 0.0005192756652832031
2023-01-21 13:42:16.061224: step: 1352/530, loss: 0.0018189430702477694
2023-01-21 13:42:17.174264: step: 1356/530, loss: 0.04093179851770401
2023-01-21 13:42:18.283081: step: 1360/530, loss: -6.389617738022935e-06
2023-01-21 13:42:19.378389: step: 1364/530, loss: 9.078979201149195e-05
2023-01-21 13:42:20.507378: step: 1368/530, loss: 2.9659271604032256e-05
2023-01-21 13:42:21.625005: step: 1372/530, loss: 0.03148021548986435
2023-01-21 13:42:22.752126: step: 1376/530, loss: 0.04650874435901642
2023-01-21 13:42:23.876280: step: 1380/530, loss: 0.06006135791540146
2023-01-21 13:42:25.028625: step: 1384/530, loss: 0.18733759224414825
2023-01-21 13:42:26.136120: step: 1388/530, loss: 8.201598575396929e-06
2023-01-21 13:42:27.260185: step: 1392/530, loss: 6.055831818230217e-06
2023-01-21 13:42:28.398859: step: 1396/530, loss: 0.03217601776123047
2023-01-21 13:42:29.560155: step: 1400/530, loss: 0.00035724640474654734
2023-01-21 13:42:30.677621: step: 1404/530, loss: 0.0002681732294149697
2023-01-21 13:42:31.814143: step: 1408/530, loss: 6.67572021484375e-05
2023-01-21 13:42:32.955606: step: 1412/530, loss: 0.013782024383544922
2023-01-21 13:42:34.072445: step: 1416/530, loss: 0.0007758140563964844
2023-01-21 13:42:35.168081: step: 1420/530, loss: 0.00846567191183567
2023-01-21 13:42:36.311574: step: 1424/530, loss: 0.004046440124511719
2023-01-21 13:42:37.463696: step: 1428/530, loss: 1.6784666513558477e-05
2023-01-21 13:42:38.587537: step: 1432/530, loss: 3.814697265625e-05
2023-01-21 13:42:39.744369: step: 1436/530, loss: 0.00046529772225767374
2023-01-21 13:42:40.855401: step: 1440/530, loss: 0.00018682479276321828
2023-01-21 13:42:42.002692: step: 1444/530, loss: 0.0010677337413653731
2023-01-21 13:42:43.147528: step: 1448/530, loss: 4.014969090349041e-05
2023-01-21 13:42:44.308347: step: 1452/530, loss: 0.10161977261304855
2023-01-21 13:42:45.423238: step: 1456/530, loss: 0.0007867813110351562
2023-01-21 13:42:46.574443: step: 1460/530, loss: 0.001186370849609375
2023-01-21 13:42:47.695242: step: 1464/530, loss: 1.277923547604587e-05
2023-01-21 13:42:48.830392: step: 1468/530, loss: 0.010891342535614967
2023-01-21 13:42:49.958317: step: 1472/530, loss: 0.00031557082547806203
2023-01-21 13:42:51.078960: step: 1476/530, loss: 0.018378637731075287
2023-01-21 13:42:52.227864: step: 1480/530, loss: 0.00950632058084011
2023-01-21 13:42:53.380158: step: 1484/530, loss: 0.012335587292909622
2023-01-21 13:42:54.532103: step: 1488/530, loss: 6.179809861350805e-05
2023-01-21 13:42:55.662465: step: 1492/530, loss: 0.00035648344783112407
2023-01-21 13:42:56.802893: step: 1496/530, loss: 2.0694733393611386e-05
2023-01-21 13:42:57.947540: step: 1500/530, loss: 6.923675391590223e-05
2023-01-21 13:42:59.105202: step: 1504/530, loss: -5.435943421616685e-06
2023-01-21 13:43:00.240499: step: 1508/530, loss: 3.1757354008732364e-05
2023-01-21 13:43:01.376756: step: 1512/530, loss: 0.024010848253965378
2023-01-21 13:43:02.548212: step: 1516/530, loss: 0.062677763402462
2023-01-21 13:43:03.672497: step: 1520/530, loss: 2.2697449821862392e-05
2023-01-21 13:43:04.795738: step: 1524/530, loss: 0.0012394428486004472
2023-01-21 13:43:05.925270: step: 1528/530, loss: 0.00821762066334486
2023-01-21 13:43:07.084566: step: 1532/530, loss: 0.000427055376349017
2023-01-21 13:43:08.199202: step: 1536/530, loss: 0.05485858768224716
2023-01-21 13:43:09.333189: step: 1540/530, loss: 0.024939347058534622
2023-01-21 13:43:10.467472: step: 1544/530, loss: 0.0018972395919263363
2023-01-21 13:43:11.607631: step: 1548/530, loss: 8.926391456043348e-05
2023-01-21 13:43:12.714363: step: 1552/530, loss: 1.2588501704158261e-05
2023-01-21 13:43:13.866299: step: 1556/530, loss: 7.095337059581652e-05
2023-01-21 13:43:14.980336: step: 1560/530, loss: 3.728866795427166e-05
2023-01-21 13:43:16.100483: step: 1564/530, loss: 9.646416583564132e-05
2023-01-21 13:43:17.210286: step: 1568/530, loss: 5.4836273193359375e-05
2023-01-21 13:43:18.345975: step: 1572/530, loss: 0.001531410263851285
2023-01-21 13:43:19.457906: step: 1576/530, loss: 0.045307449996471405
2023-01-21 13:43:20.614710: step: 1580/530, loss: 0.00022716523380950093
2023-01-21 13:43:21.746515: step: 1584/530, loss: 0.0007770538795739412
2023-01-21 13:43:22.873840: step: 1588/530, loss: 0.002796649932861328
2023-01-21 13:43:24.009102: step: 1592/530, loss: 0.0022030831314623356
2023-01-21 13:43:25.123232: step: 1596/530, loss: 0.0009593963623046875
2023-01-21 13:43:26.258328: step: 1600/530, loss: 0.003910255618393421
2023-01-21 13:43:27.404563: step: 1604/530, loss: 0.01869049109518528
2023-01-21 13:43:28.523449: step: 1608/530, loss: 0.01817293092608452
2023-01-21 13:43:29.664478: step: 1612/530, loss: -1.926422191900201e-05
2023-01-21 13:43:30.799351: step: 1616/530, loss: 4.434585662238533e-06
2023-01-21 13:43:31.939889: step: 1620/530, loss: 0.06271228939294815
2023-01-21 13:43:33.085436: step: 1624/530, loss: 4.587173680192791e-05
2023-01-21 13:43:34.210741: step: 1628/530, loss: 0.0002096176176564768
2023-01-21 13:43:35.363145: step: 1632/530, loss: 0.015357781201601028
2023-01-21 13:43:36.448375: step: 1636/530, loss: 7.104873657226562e-05
2023-01-21 13:43:37.587569: step: 1640/530, loss: 0.0002233505219919607
2023-01-21 13:43:38.741439: step: 1644/530, loss: 2.193450927734375e-05
2023-01-21 13:43:39.862194: step: 1648/530, loss: 0.010013389401137829
2023-01-21 13:43:40.985771: step: 1652/530, loss: 0.005037689581513405
2023-01-21 13:43:42.151505: step: 1656/530, loss: 7.62939453125e-06
2023-01-21 13:43:43.312563: step: 1660/530, loss: 0.00010166168794967234
2023-01-21 13:43:44.461540: step: 1664/530, loss: 0.017991257831454277
2023-01-21 13:43:45.590527: step: 1668/530, loss: 0.00015373229689430445
2023-01-21 13:43:46.744342: step: 1672/530, loss: 0.7769744992256165
2023-01-21 13:43:47.898065: step: 1676/530, loss: 9.15527380129788e-06
2023-01-21 13:43:49.012750: step: 1680/530, loss: 5.8555600844556466e-05
2023-01-21 13:43:50.104022: step: 1684/530, loss: -6.675720669591101e-07
2023-01-21 13:43:51.208627: step: 1688/530, loss: 1.1539459592313506e-05
2023-01-21 13:43:52.359016: step: 1692/530, loss: 0.006903648376464844
2023-01-21 13:43:53.464731: step: 1696/530, loss: 0.0006614684825763106
2023-01-21 13:43:54.596949: step: 1700/530, loss: 0.01711397059261799
2023-01-21 13:43:55.714750: step: 1704/530, loss: 0.00030069350032135844
2023-01-21 13:43:56.830963: step: 1708/530, loss: 0.00013742447481490672
2023-01-21 13:43:57.932511: step: 1712/530, loss: 0.0006753921625204384
2023-01-21 13:43:59.054778: step: 1716/530, loss: 0.0037540437187999487
2023-01-21 13:44:00.199413: step: 1720/530, loss: 0.00014820098294876516
2023-01-21 13:44:01.326117: step: 1724/530, loss: 0.007804203312844038
2023-01-21 13:44:02.442224: step: 1728/530, loss: 0.005549097433686256
2023-01-21 13:44:03.586041: step: 1732/530, loss: 0.04431319236755371
2023-01-21 13:44:04.723960: step: 1736/530, loss: 0.0322418212890625
2023-01-21 13:44:05.875248: step: 1740/530, loss: 0.0321170836687088
2023-01-21 13:44:06.996744: step: 1744/530, loss: 3.4332276754867053e-06
2023-01-21 13:44:08.158838: step: 1748/530, loss: 0.0006090164533816278
2023-01-21 13:44:09.265728: step: 1752/530, loss: 0.007384109776467085
2023-01-21 13:44:10.402659: step: 1756/530, loss: 2.6130677724722773e-05
2023-01-21 13:44:11.533855: step: 1760/530, loss: 0.009052658453583717
2023-01-21 13:44:12.634844: step: 1764/530, loss: 6.303787813521922e-05
2023-01-21 13:44:13.787408: step: 1768/530, loss: 0.00020713805861305445
2023-01-21 13:44:14.925953: step: 1772/530, loss: 4.673004514188506e-05
2023-01-21 13:44:16.079591: step: 1776/530, loss: 0.011557579971849918
2023-01-21 13:44:17.204688: step: 1780/530, loss: 2.1362306142691523e-05
2023-01-21 13:44:18.321950: step: 1784/530, loss: 0.0005896568181924522
2023-01-21 13:44:19.493295: step: 1788/530, loss: 0.007252311799675226
2023-01-21 13:44:20.632906: step: 1792/530, loss: 0.012494659051299095
2023-01-21 13:44:21.758585: step: 1796/530, loss: 0.006176948547363281
2023-01-21 13:44:22.922758: step: 1800/530, loss: 0.0003561973571777344
2023-01-21 13:44:24.059457: step: 1804/530, loss: 0.0012302398681640625
2023-01-21 13:44:25.194846: step: 1808/530, loss: 8.435249765170738e-05
2023-01-21 13:44:26.346104: step: 1812/530, loss: 0.014499283395707607
2023-01-21 13:44:27.453729: step: 1816/530, loss: 0.004173469729721546
2023-01-21 13:44:28.607101: step: 1820/530, loss: 2.093315197271295e-05
2023-01-21 13:44:29.699960: step: 1824/530, loss: 0.0005592346424236894
2023-01-21 13:44:30.790969: step: 1828/530, loss: 0.00696220388635993
2023-01-21 13:44:31.917027: step: 1832/530, loss: 0.0006017685518600047
2023-01-21 13:44:33.068654: step: 1836/530, loss: 9.899138967739418e-05
2023-01-21 13:44:34.206927: step: 1840/530, loss: 6.637573096668348e-05
2023-01-21 13:44:35.330917: step: 1844/530, loss: 1.1444092706369702e-05
2023-01-21 13:44:36.452336: step: 1848/530, loss: 2.28881845032447e-06
2023-01-21 13:44:37.552462: step: 1852/530, loss: 0.0051666260696947575
2023-01-21 13:44:38.647375: step: 1856/530, loss: 0.005717277526855469
2023-01-21 13:44:39.771470: step: 1860/530, loss: 3.080368333030492e-05
2023-01-21 13:44:40.886338: step: 1864/530, loss: 0.00042028428288176656
2023-01-21 13:44:41.993328: step: 1868/530, loss: 1.6880036127986386e-05
2023-01-21 13:44:43.088495: step: 1872/530, loss: 0.08003588020801544
2023-01-21 13:44:44.195229: step: 1876/530, loss: 3.0517580853484105e-06
2023-01-21 13:44:45.322140: step: 1880/530, loss: 0.03461189568042755
2023-01-21 13:44:46.482170: step: 1884/530, loss: 0.0018207550747320056
2023-01-21 13:44:47.617749: step: 1888/530, loss: 0.010653972625732422
2023-01-21 13:44:48.705370: step: 1892/530, loss: 2.384185791015625e-07
2023-01-21 13:44:49.811866: step: 1896/530, loss: -0.0
2023-01-21 13:44:50.958890: step: 1900/530, loss: 0.00644683837890625
2023-01-21 13:44:52.066016: step: 1904/530, loss: 0.00018730164447333664
2023-01-21 13:44:53.172507: step: 1908/530, loss: 2.6035309929284267e-05
2023-01-21 13:44:54.264966: step: 1912/530, loss: -5.948543730482925e-06
2023-01-21 13:44:55.378786: step: 1916/530, loss: 0.0016862869961187243
2023-01-21 13:44:56.565444: step: 1920/530, loss: 1.0294657945632935
2023-01-21 13:44:57.676727: step: 1924/530, loss: 1.8119812921213452e-06
2023-01-21 13:44:58.788990: step: 1928/530, loss: 0.012655830942094326
2023-01-21 13:44:59.911987: step: 1932/530, loss: 0.0010618210071697831
2023-01-21 13:45:01.041204: step: 1936/530, loss: 0.0877775177359581
2023-01-21 13:45:02.155970: step: 1940/530, loss: 0.0005313873407430947
2023-01-21 13:45:03.274130: step: 1944/530, loss: 3.2424925393570447e-06
2023-01-21 13:45:04.414560: step: 1948/530, loss: 7.286071922862902e-05
2023-01-21 13:45:05.523372: step: 1952/530, loss: 0.0007328033680096269
2023-01-21 13:45:06.649784: step: 1956/530, loss: 0.0003553390852175653
2023-01-21 13:45:07.799428: step: 1960/530, loss: 0.0001773834228515625
2023-01-21 13:45:08.926636: step: 1964/530, loss: 0.0019729614723473787
2023-01-21 13:45:10.076294: step: 1968/530, loss: 0.006718444637954235
2023-01-21 13:45:11.190760: step: 1972/530, loss: 0.0022602081298828125
2023-01-21 13:45:12.306913: step: 1976/530, loss: 0.00017051697068382055
2023-01-21 13:45:13.422544: step: 1980/530, loss: 0.0003715515194926411
2023-01-21 13:45:14.553401: step: 1984/530, loss: 0.0006301880348473787
2023-01-21 13:45:15.694055: step: 1988/530, loss: 0.0002187728969147429
2023-01-21 13:45:16.805871: step: 1992/530, loss: 3.886222839355469e-05
2023-01-21 13:45:17.914264: step: 1996/530, loss: 6.666182889603078e-05
2023-01-21 13:45:19.050669: step: 2000/530, loss: 0.0007330895168706775
2023-01-21 13:45:20.160665: step: 2004/530, loss: 0.040247153490781784
2023-01-21 13:45:21.279662: step: 2008/530, loss: 3.852844383800402e-05
2023-01-21 13:45:22.418351: step: 2012/530, loss: 0.004876041319221258
2023-01-21 13:45:23.567093: step: 2016/530, loss: -2.918243444582913e-05
2023-01-21 13:45:24.713287: step: 2020/530, loss: 0.0013820647727698088
2023-01-21 13:45:25.811550: step: 2024/530, loss: 0.0023657798301428556
2023-01-21 13:45:26.926881: step: 2028/530, loss: 0.2879234552383423
2023-01-21 13:45:28.044512: step: 2032/530, loss: 0.012592888437211514
2023-01-21 13:45:29.163558: step: 2036/530, loss: 0.00013198853412177414
2023-01-21 13:45:30.272370: step: 2040/530, loss: 0.007924270816147327
2023-01-21 13:45:31.403329: step: 2044/530, loss: -1.220703143189894e-05
2023-01-21 13:45:32.560714: step: 2048/530, loss: 2.86102294921875e-05
2023-01-21 13:45:33.705793: step: 2052/530, loss: 0.0011165140895172954
2023-01-21 13:45:34.857657: step: 2056/530, loss: 4.673004241340095e-06
2023-01-21 13:45:35.979780: step: 2060/530, loss: 0.01006460189819336
2023-01-21 13:45:37.103309: step: 2064/530, loss: 0.004045606125146151
2023-01-21 13:45:38.221841: step: 2068/530, loss: 6.160735938465223e-05
2023-01-21 13:45:39.325771: step: 2072/530, loss: 0.0007658004760742188
2023-01-21 13:45:40.448842: step: 2076/530, loss: 1.2731552487821318e-05
2023-01-21 13:45:41.556570: step: 2080/530, loss: 0.00309066753834486
2023-01-21 13:45:42.658278: step: 2084/530, loss: 0.009735775180161
2023-01-21 13:45:43.769763: step: 2088/530, loss: 0.006229114718735218
2023-01-21 13:45:44.887043: step: 2092/530, loss: 0.0019541741348803043
2023-01-21 13:45:45.981794: step: 2096/530, loss: 1.831054760259576e-05
2023-01-21 13:45:47.120592: step: 2100/530, loss: 0.0003796577511820942
2023-01-21 13:45:48.241605: step: 2104/530, loss: 0.005587578285485506
2023-01-21 13:45:49.361176: step: 2108/530, loss: 0.00028820039005950093
2023-01-21 13:45:50.467407: step: 2112/530, loss: 9.088516526389867e-05
2023-01-21 13:45:51.600021: step: 2116/530, loss: 0.00019569396681617945
2023-01-21 13:45:52.718170: step: 2120/530, loss: 0.0038644790183752775
==================================================
Loss: 0.023
--------------------
Dev: {'event': {'p': 0.6082251082251082, 'r': 0.748335552596538, 'f1': 0.6710447761194029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6490004649000465, 'r': 0.7977142857142857, 'f1': 0.7157139195078186}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.6071428571428571, 'r': 0.9444444444444444, 'f1': 0.7391304347826088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.5901639344262295, 'r': 0.5714285714285714, 'f1': 0.5806451612903226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.3953488372093023, 'r': 0.4722222222222222, 'f1': 0.43037974683544306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Eng Test for Chinese: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Sample Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}