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 08:25:18.384959: step: 4/530, loss: 2.5161194801330566
2023-01-21 08:25:19.550040: step: 8/530, loss: 4.797885417938232
2023-01-21 08:25:20.694338: step: 12/530, loss: 11.926904678344727
2023-01-21 08:25:21.898373: step: 16/530, loss: 4.0641045570373535
2023-01-21 08:25:23.054727: step: 20/530, loss: 13.01579475402832
2023-01-21 08:25:24.269722: step: 24/530, loss: 3.866377353668213
2023-01-21 08:25:25.542348: step: 28/530, loss: 22.95454978942871
2023-01-21 08:25:26.741742: step: 32/530, loss: 21.726295471191406
2023-01-21 08:25:27.917875: step: 36/530, loss: 3.471451759338379
2023-01-21 08:25:29.088218: step: 40/530, loss: 15.960955619812012
2023-01-21 08:25:30.241502: step: 44/530, loss: 3.9349400997161865
2023-01-21 08:25:31.469106: step: 48/530, loss: 20.913089752197266
2023-01-21 08:25:32.644282: step: 52/530, loss: 13.196843147277832
2023-01-21 08:25:33.824137: step: 56/530, loss: 4.372941017150879
2023-01-21 08:25:35.019081: step: 60/530, loss: 8.25861930847168
2023-01-21 08:25:36.209169: step: 64/530, loss: 4.974344730377197
2023-01-21 08:25:37.363924: step: 68/530, loss: 5.565827369689941
2023-01-21 08:25:38.548951: step: 72/530, loss: 15.985088348388672
2023-01-21 08:25:39.705343: step: 76/530, loss: 10.396745681762695
2023-01-21 08:25:40.911699: step: 80/530, loss: 10.244354248046875
2023-01-21 08:25:42.113526: step: 84/530, loss: 18.344085693359375
2023-01-21 08:25:43.285273: step: 88/530, loss: 13.439335823059082
2023-01-21 08:25:44.470244: step: 92/530, loss: 14.317118644714355
2023-01-21 08:25:45.588257: step: 96/530, loss: 2.4477803707122803
2023-01-21 08:25:46.779723: step: 100/530, loss: 37.005043029785156
2023-01-21 08:25:47.955877: step: 104/530, loss: 3.7880821228027344
2023-01-21 08:25:49.122990: step: 108/530, loss: 15.911226272583008
2023-01-21 08:25:50.347749: step: 112/530, loss: 4.127887725830078
2023-01-21 08:25:51.549308: step: 116/530, loss: 3.908759593963623
2023-01-21 08:25:52.721734: step: 120/530, loss: 13.880085945129395
2023-01-21 08:25:53.888943: step: 124/530, loss: 12.014925956726074
2023-01-21 08:25:55.073037: step: 128/530, loss: 9.153682708740234
2023-01-21 08:25:56.301659: step: 132/530, loss: 5.017300605773926
2023-01-21 08:25:57.473882: step: 136/530, loss: 3.6399130821228027
2023-01-21 08:25:58.652555: step: 140/530, loss: 15.44703483581543
2023-01-21 08:25:59.814187: step: 144/530, loss: 3.0643105506896973
2023-01-21 08:26:01.021315: step: 148/530, loss: 3.4777750968933105
2023-01-21 08:26:02.188594: step: 152/530, loss: 13.222376823425293
2023-01-21 08:26:03.368504: step: 156/530, loss: 5.787364959716797
2023-01-21 08:26:04.528329: step: 160/530, loss: 14.943460464477539
2023-01-21 08:26:05.712069: step: 164/530, loss: 40.55250549316406
2023-01-21 08:26:06.861446: step: 168/530, loss: 4.62084436416626
2023-01-21 08:26:08.045107: step: 172/530, loss: 8.43724250793457
2023-01-21 08:26:09.218611: step: 176/530, loss: 16.676973342895508
2023-01-21 08:26:10.387073: step: 180/530, loss: 6.348862648010254
2023-01-21 08:26:11.572308: step: 184/530, loss: 5.053753852844238
2023-01-21 08:26:12.737250: step: 188/530, loss: 2.9925246238708496
2023-01-21 08:26:13.926665: step: 192/530, loss: 9.537186622619629
2023-01-21 08:26:15.108391: step: 196/530, loss: 2.9689135551452637
2023-01-21 08:26:16.308123: step: 200/530, loss: 10.174930572509766
2023-01-21 08:26:17.480255: step: 204/530, loss: 9.401609420776367
2023-01-21 08:26:18.653403: step: 208/530, loss: 32.26618957519531
2023-01-21 08:26:19.817196: step: 212/530, loss: 12.614603996276855
2023-01-21 08:26:20.981053: step: 216/530, loss: 15.97144889831543
2023-01-21 08:26:22.171875: step: 220/530, loss: 15.788025856018066
2023-01-21 08:26:23.385467: step: 224/530, loss: 2.724240303039551
2023-01-21 08:26:24.590299: step: 228/530, loss: 14.002435684204102
2023-01-21 08:26:25.743056: step: 232/530, loss: 3.3141677379608154
2023-01-21 08:26:26.905798: step: 236/530, loss: 7.198806285858154
2023-01-21 08:26:28.127789: step: 240/530, loss: 7.068933486938477
2023-01-21 08:26:29.328821: step: 244/530, loss: 14.713768005371094
2023-01-21 08:26:30.491017: step: 248/530, loss: 2.278554916381836
2023-01-21 08:26:31.698805: step: 252/530, loss: 4.386191368103027
2023-01-21 08:26:32.884731: step: 256/530, loss: 2.6234817504882812
2023-01-21 08:26:34.043417: step: 260/530, loss: 2.371807098388672
2023-01-21 08:26:35.221712: step: 264/530, loss: 2.3581998348236084
2023-01-21 08:26:36.401069: step: 268/530, loss: 15.002385139465332
2023-01-21 08:26:37.550839: step: 272/530, loss: 12.71749496459961
2023-01-21 08:26:38.769209: step: 276/530, loss: 4.442104339599609
2023-01-21 08:26:39.929904: step: 280/530, loss: 2.006585121154785
2023-01-21 08:26:41.100027: step: 284/530, loss: 3.3839800357818604
2023-01-21 08:26:42.253230: step: 288/530, loss: 11.266592025756836
2023-01-21 08:26:43.432653: step: 292/530, loss: 3.737403392791748
2023-01-21 08:26:44.650317: step: 296/530, loss: 22.517480850219727
2023-01-21 08:26:45.822635: step: 300/530, loss: 16.706323623657227
2023-01-21 08:26:46.985730: step: 304/530, loss: 2.7792234420776367
2023-01-21 08:26:48.182326: step: 308/530, loss: 12.020271301269531
2023-01-21 08:26:49.441220: step: 312/530, loss: 4.782174110412598
2023-01-21 08:26:50.611450: step: 316/530, loss: 3.55352783203125
2023-01-21 08:26:51.780393: step: 320/530, loss: 27.624523162841797
2023-01-21 08:26:53.014042: step: 324/530, loss: 11.016018867492676
2023-01-21 08:26:54.146135: step: 328/530, loss: 3.1291041374206543
2023-01-21 08:26:55.347795: step: 332/530, loss: 3.4651546478271484
2023-01-21 08:26:56.519683: step: 336/530, loss: 21.539016723632812
2023-01-21 08:26:57.744772: step: 340/530, loss: 3.6725924015045166
2023-01-21 08:26:58.957219: step: 344/530, loss: 3.7882513999938965
2023-01-21 08:27:00.125630: step: 348/530, loss: 3.1051297187805176
2023-01-21 08:27:01.315495: step: 352/530, loss: 4.410858154296875
2023-01-21 08:27:02.486219: step: 356/530, loss: 2.0844953060150146
2023-01-21 08:27:03.669357: step: 360/530, loss: 12.848541259765625
2023-01-21 08:27:04.843615: step: 364/530, loss: 1.903769850730896
2023-01-21 08:27:06.046906: step: 368/530, loss: 4.888723373413086
2023-01-21 08:27:07.221178: step: 372/530, loss: 17.24649429321289
2023-01-21 08:27:08.432816: step: 376/530, loss: 8.166925430297852
2023-01-21 08:27:09.599275: step: 380/530, loss: 20.124874114990234
2023-01-21 08:27:10.751806: step: 384/530, loss: 12.455825805664062
2023-01-21 08:27:11.953092: step: 388/530, loss: 9.368526458740234
2023-01-21 08:27:13.122517: step: 392/530, loss: 2.452817440032959
2023-01-21 08:27:14.297409: step: 396/530, loss: 5.114747047424316
2023-01-21 08:27:15.475432: step: 400/530, loss: 9.535774230957031
2023-01-21 08:27:16.648281: step: 404/530, loss: 2.9233994483947754
2023-01-21 08:27:17.792813: step: 408/530, loss: 19.035572052001953
2023-01-21 08:27:18.976912: step: 412/530, loss: 13.949315071105957
2023-01-21 08:27:20.120124: step: 416/530, loss: 2.444232940673828
2023-01-21 08:27:21.275128: step: 420/530, loss: 2.2327866554260254
2023-01-21 08:27:22.473987: step: 424/530, loss: 2.627701759338379
2023-01-21 08:27:23.634155: step: 428/530, loss: 5.002713203430176
2023-01-21 08:27:24.812599: step: 432/530, loss: 3.3038406372070312
2023-01-21 08:27:25.973162: step: 436/530, loss: 2.5352187156677246
2023-01-21 08:27:27.170765: step: 440/530, loss: 19.64345359802246
2023-01-21 08:27:28.342661: step: 444/530, loss: 9.372864723205566
2023-01-21 08:27:29.554517: step: 448/530, loss: 4.161972522735596
2023-01-21 08:27:30.730591: step: 452/530, loss: 6.6680908203125
2023-01-21 08:27:31.884361: step: 456/530, loss: 2.3650639057159424
2023-01-21 08:27:33.086758: step: 460/530, loss: 13.355592727661133
2023-01-21 08:27:34.253178: step: 464/530, loss: 8.220755577087402
2023-01-21 08:27:35.404142: step: 468/530, loss: 1.9070762395858765
2023-01-21 08:27:36.605867: step: 472/530, loss: 8.14748764038086
2023-01-21 08:27:37.775272: step: 476/530, loss: 10.209144592285156
2023-01-21 08:27:38.911154: step: 480/530, loss: 1.5899099111557007
2023-01-21 08:27:40.094561: step: 484/530, loss: 2.1008899211883545
2023-01-21 08:27:41.293627: step: 488/530, loss: 2.344302177429199
2023-01-21 08:27:42.461910: step: 492/530, loss: 9.750861167907715
2023-01-21 08:27:43.626761: step: 496/530, loss: 1.621309518814087
2023-01-21 08:27:44.783946: step: 500/530, loss: 2.753882646560669
2023-01-21 08:27:45.984882: step: 504/530, loss: 4.010830402374268
2023-01-21 08:27:47.168177: step: 508/530, loss: 1.1693798303604126
2023-01-21 08:27:48.325027: step: 512/530, loss: 3.1112325191497803
2023-01-21 08:27:49.519470: step: 516/530, loss: 1.2566814422607422
2023-01-21 08:27:50.698063: step: 520/530, loss: 5.21751070022583
2023-01-21 08:27:51.858246: step: 524/530, loss: 5.255274772644043
2023-01-21 08:27:53.071465: step: 528/530, loss: 10.421780586242676
2023-01-21 08:27:54.237369: step: 532/530, loss: 2.817828893661499
2023-01-21 08:27:55.397988: step: 536/530, loss: 0.7683872580528259
2023-01-21 08:27:56.594725: step: 540/530, loss: 6.435408592224121
2023-01-21 08:27:57.770955: step: 544/530, loss: 3.2435226440429688
2023-01-21 08:27:58.946564: step: 548/530, loss: 4.753021717071533
2023-01-21 08:28:00.133011: step: 552/530, loss: 3.7606306076049805
2023-01-21 08:28:01.341179: step: 556/530, loss: 0.8844271898269653
2023-01-21 08:28:02.506775: step: 560/530, loss: 0.7438180446624756
2023-01-21 08:28:03.682289: step: 564/530, loss: 0.7047466039657593
2023-01-21 08:28:04.852746: step: 568/530, loss: 3.958590507507324
2023-01-21 08:28:06.042003: step: 572/530, loss: 3.6301538944244385
2023-01-21 08:28:07.185803: step: 576/530, loss: 4.452891826629639
2023-01-21 08:28:08.401007: step: 580/530, loss: 3.3826839923858643
2023-01-21 08:28:09.552325: step: 584/530, loss: 1.2414543628692627
2023-01-21 08:28:10.693140: step: 588/530, loss: 1.8615998029708862
2023-01-21 08:28:11.913872: step: 592/530, loss: 0.9703147411346436
2023-01-21 08:28:13.090537: step: 596/530, loss: 0.9260671138763428
2023-01-21 08:28:14.257071: step: 600/530, loss: 2.785079002380371
2023-01-21 08:28:15.424918: step: 604/530, loss: 1.8783903121948242
2023-01-21 08:28:16.602529: step: 608/530, loss: 1.935996174812317
2023-01-21 08:28:17.763785: step: 612/530, loss: 1.8300502300262451
2023-01-21 08:28:18.956114: step: 616/530, loss: 0.5617196559906006
2023-01-21 08:28:20.164957: step: 620/530, loss: 1.0309745073318481
2023-01-21 08:28:21.327106: step: 624/530, loss: 3.1078665256500244
2023-01-21 08:28:22.493397: step: 628/530, loss: 4.157384872436523
2023-01-21 08:28:23.669484: step: 632/530, loss: 1.0077488422393799
2023-01-21 08:28:24.867511: step: 636/530, loss: 0.7220383882522583
2023-01-21 08:28:26.057784: step: 640/530, loss: 1.2440093755722046
2023-01-21 08:28:27.176855: step: 644/530, loss: 0.3529917597770691
2023-01-21 08:28:28.341947: step: 648/530, loss: 0.768575131893158
2023-01-21 08:28:29.507075: step: 652/530, loss: 0.31803983449935913
2023-01-21 08:28:30.656643: step: 656/530, loss: 6.022542953491211
2023-01-21 08:28:31.817382: step: 660/530, loss: 1.6316437721252441
2023-01-21 08:28:33.002158: step: 664/530, loss: 1.0451242923736572
2023-01-21 08:28:34.194499: step: 668/530, loss: 0.5916638374328613
2023-01-21 08:28:35.368467: step: 672/530, loss: 0.6444135904312134
2023-01-21 08:28:36.539603: step: 676/530, loss: 3.8935070037841797
2023-01-21 08:28:37.704686: step: 680/530, loss: 1.9293432235717773
2023-01-21 08:28:38.834118: step: 684/530, loss: 1.006641149520874
2023-01-21 08:28:39.988929: step: 688/530, loss: 0.714217483997345
2023-01-21 08:28:41.173051: step: 692/530, loss: 4.431859016418457
2023-01-21 08:28:42.362254: step: 696/530, loss: 3.916639566421509
2023-01-21 08:28:43.506850: step: 700/530, loss: 2.7038116455078125
2023-01-21 08:28:44.704152: step: 704/530, loss: 1.762603521347046
2023-01-21 08:28:45.871753: step: 708/530, loss: 0.4076938033103943
2023-01-21 08:28:47.047695: step: 712/530, loss: 0.48345476388931274
2023-01-21 08:28:48.188860: step: 716/530, loss: 1.45754075050354
2023-01-21 08:28:49.401012: step: 720/530, loss: 0.7138513326644897
2023-01-21 08:28:50.560974: step: 724/530, loss: 0.7309765815734863
2023-01-21 08:28:51.720860: step: 728/530, loss: 1.2813173532485962
2023-01-21 08:28:52.876546: step: 732/530, loss: 2.56290602684021
2023-01-21 08:28:54.071547: step: 736/530, loss: 1.2265419960021973
2023-01-21 08:28:55.276954: step: 740/530, loss: 2.386249542236328
2023-01-21 08:28:56.431410: step: 744/530, loss: 6.997499465942383
2023-01-21 08:28:57.607249: step: 748/530, loss: 0.44485947489738464
2023-01-21 08:28:58.831877: step: 752/530, loss: 0.47446194291114807
2023-01-21 08:29:00.037052: step: 756/530, loss: 3.82497501373291
2023-01-21 08:29:01.219361: step: 760/530, loss: 1.0958218574523926
2023-01-21 08:29:02.378787: step: 764/530, loss: 0.7192956209182739
2023-01-21 08:29:03.570384: step: 768/530, loss: 0.7497055530548096
2023-01-21 08:29:04.743681: step: 772/530, loss: 3.1190707683563232
2023-01-21 08:29:05.914004: step: 776/530, loss: 2.8811700344085693
2023-01-21 08:29:07.088796: step: 780/530, loss: 2.8657805919647217
2023-01-21 08:29:08.245737: step: 784/530, loss: 1.971901774406433
2023-01-21 08:29:09.445603: step: 788/530, loss: 1.0352015495300293
2023-01-21 08:29:10.643183: step: 792/530, loss: 0.9032777547836304
2023-01-21 08:29:11.819317: step: 796/530, loss: 0.7656562924385071
2023-01-21 08:29:12.994343: step: 800/530, loss: 3.5292155742645264
2023-01-21 08:29:14.188155: step: 804/530, loss: 2.4679925441741943
2023-01-21 08:29:15.345071: step: 808/530, loss: 0.3880865275859833
2023-01-21 08:29:16.556620: step: 812/530, loss: 1.3852752447128296
2023-01-21 08:29:17.759887: step: 816/530, loss: 1.9122967720031738
2023-01-21 08:29:18.930730: step: 820/530, loss: 1.0261013507843018
2023-01-21 08:29:20.114430: step: 824/530, loss: 0.5673860311508179
2023-01-21 08:29:21.290812: step: 828/530, loss: 9.804205894470215
2023-01-21 08:29:22.474011: step: 832/530, loss: 1.009171485900879
2023-01-21 08:29:23.686033: step: 836/530, loss: 0.5999876260757446
2023-01-21 08:29:24.851168: step: 840/530, loss: 0.5948918461799622
2023-01-21 08:29:26.016382: step: 844/530, loss: 0.47238612174987793
2023-01-21 08:29:27.165512: step: 848/530, loss: 0.38903582096099854
2023-01-21 08:29:28.364954: step: 852/530, loss: 1.9784491062164307
2023-01-21 08:29:29.555153: step: 856/530, loss: 7.061280250549316
2023-01-21 08:29:30.747140: step: 860/530, loss: 1.0529119968414307
2023-01-21 08:29:31.949150: step: 864/530, loss: 0.8442457318305969
2023-01-21 08:29:33.160762: step: 868/530, loss: 3.041553497314453
2023-01-21 08:29:34.325850: step: 872/530, loss: 0.2720159888267517
2023-01-21 08:29:35.470078: step: 876/530, loss: 0.7017601728439331
2023-01-21 08:29:36.689152: step: 880/530, loss: 1.4306416511535645
2023-01-21 08:29:37.935902: step: 884/530, loss: 0.7119876146316528
2023-01-21 08:29:39.111721: step: 888/530, loss: 1.416643500328064
2023-01-21 08:29:40.278589: step: 892/530, loss: 2.188974142074585
2023-01-21 08:29:41.418159: step: 896/530, loss: 0.6373625993728638
2023-01-21 08:29:42.629885: step: 900/530, loss: 2.17868709564209
2023-01-21 08:29:43.795149: step: 904/530, loss: 0.44701725244522095
2023-01-21 08:29:44.987750: step: 908/530, loss: 0.7150293588638306
2023-01-21 08:29:46.215286: step: 912/530, loss: 7.174227714538574
2023-01-21 08:29:47.391181: step: 916/530, loss: 2.646710157394409
2023-01-21 08:29:48.546667: step: 920/530, loss: 0.8314789533615112
2023-01-21 08:29:49.673214: step: 924/530, loss: 1.1968625783920288
2023-01-21 08:29:50.887195: step: 928/530, loss: 1.7923980951309204
2023-01-21 08:29:52.046451: step: 932/530, loss: 0.30722665786743164
2023-01-21 08:29:53.243907: step: 936/530, loss: 2.4092276096343994
2023-01-21 08:29:54.379214: step: 940/530, loss: 1.95243501663208
2023-01-21 08:29:55.561211: step: 944/530, loss: 1.0235170125961304
2023-01-21 08:29:56.758564: step: 948/530, loss: 0.5962594747543335
2023-01-21 08:29:57.906303: step: 952/530, loss: 0.2668376863002777
2023-01-21 08:29:59.089518: step: 956/530, loss: 1.1881362199783325
2023-01-21 08:30:00.288388: step: 960/530, loss: 0.9031090140342712
2023-01-21 08:30:01.441270: step: 964/530, loss: 0.9046097993850708
2023-01-21 08:30:02.596994: step: 968/530, loss: 0.5459737777709961
2023-01-21 08:30:03.761245: step: 972/530, loss: 0.2694365680217743
2023-01-21 08:30:04.972042: step: 976/530, loss: 3.8331170082092285
2023-01-21 08:30:06.134823: step: 980/530, loss: 0.6028522849082947
2023-01-21 08:30:07.296646: step: 984/530, loss: 0.4941166043281555
2023-01-21 08:30:08.457134: step: 988/530, loss: 0.5745193958282471
2023-01-21 08:30:09.651454: step: 992/530, loss: 1.136129379272461
2023-01-21 08:30:10.815843: step: 996/530, loss: 0.6408124566078186
2023-01-21 08:30:11.973275: step: 1000/530, loss: 1.2257132530212402
2023-01-21 08:30:13.205952: step: 1004/530, loss: 0.49207180738449097
2023-01-21 08:30:14.422124: step: 1008/530, loss: 1.4571502208709717
2023-01-21 08:30:15.624440: step: 1012/530, loss: 1.139090895652771
2023-01-21 08:30:16.768508: step: 1016/530, loss: 1.1502777338027954
2023-01-21 08:30:17.980130: step: 1020/530, loss: 0.5020865201950073
2023-01-21 08:30:19.169614: step: 1024/530, loss: 1.5950565338134766
2023-01-21 08:30:20.344863: step: 1028/530, loss: 0.27119016647338867
2023-01-21 08:30:21.554118: step: 1032/530, loss: 0.7815744876861572
2023-01-21 08:30:22.754870: step: 1036/530, loss: 0.3496941924095154
2023-01-21 08:30:23.938189: step: 1040/530, loss: 2.5934882164001465
2023-01-21 08:30:25.076405: step: 1044/530, loss: 0.6182379722595215
2023-01-21 08:30:26.249365: step: 1048/530, loss: 0.5631403923034668
2023-01-21 08:30:27.511044: step: 1052/530, loss: 2.31282114982605
2023-01-21 08:30:28.655693: step: 1056/530, loss: 2.662299871444702
2023-01-21 08:30:29.820669: step: 1060/530, loss: 0.6531960964202881
2023-01-21 08:30:31.017573: step: 1064/530, loss: 2.829932689666748
2023-01-21 08:30:32.176927: step: 1068/530, loss: 5.218477249145508
2023-01-21 08:30:33.332534: step: 1072/530, loss: 4.102937698364258
2023-01-21 08:30:34.506753: step: 1076/530, loss: 0.6146771907806396
2023-01-21 08:30:35.713023: step: 1080/530, loss: 0.3529133200645447
2023-01-21 08:30:36.915302: step: 1084/530, loss: 0.6025075912475586
2023-01-21 08:30:38.078768: step: 1088/530, loss: 1.490753412246704
2023-01-21 08:30:39.254924: step: 1092/530, loss: 0.8239052295684814
2023-01-21 08:30:40.413933: step: 1096/530, loss: 1.2392657995224
2023-01-21 08:30:41.601060: step: 1100/530, loss: 0.23670083284378052
2023-01-21 08:30:42.823940: step: 1104/530, loss: 2.0383994579315186
2023-01-21 08:30:43.969053: step: 1108/530, loss: 0.509362518787384
2023-01-21 08:30:45.185569: step: 1112/530, loss: 1.8773927688598633
2023-01-21 08:30:46.363559: step: 1116/530, loss: 1.4129194021224976
2023-01-21 08:30:47.556181: step: 1120/530, loss: 0.8332359790802002
2023-01-21 08:30:48.791700: step: 1124/530, loss: 0.8844027519226074
2023-01-21 08:30:49.949211: step: 1128/530, loss: 1.3705568313598633
2023-01-21 08:30:51.134509: step: 1132/530, loss: 1.9089680910110474
2023-01-21 08:30:52.291483: step: 1136/530, loss: 1.832566261291504
2023-01-21 08:30:53.467264: step: 1140/530, loss: 0.34784209728240967
2023-01-21 08:30:54.627036: step: 1144/530, loss: 1.0678129196166992
2023-01-21 08:30:55.807310: step: 1148/530, loss: 0.5765253305435181
2023-01-21 08:30:56.997537: step: 1152/530, loss: 0.8868647813796997
2023-01-21 08:30:58.171815: step: 1156/530, loss: 1.7719250917434692
2023-01-21 08:30:59.306788: step: 1160/530, loss: 0.28223738074302673
2023-01-21 08:31:00.490977: step: 1164/530, loss: 1.5586905479431152
2023-01-21 08:31:01.651866: step: 1168/530, loss: 0.941847026348114
2023-01-21 08:31:02.792634: step: 1172/530, loss: 1.9285145998001099
2023-01-21 08:31:03.962905: step: 1176/530, loss: 1.6009633541107178
2023-01-21 08:31:05.163157: step: 1180/530, loss: 0.4060894846916199
2023-01-21 08:31:06.334225: step: 1184/530, loss: 1.1366400718688965
2023-01-21 08:31:07.497904: step: 1188/530, loss: 0.7903562188148499
2023-01-21 08:31:08.670896: step: 1192/530, loss: 0.43699389696121216
2023-01-21 08:31:09.835390: step: 1196/530, loss: 0.4940643906593323
2023-01-21 08:31:11.027876: step: 1200/530, loss: 7.775330066680908
2023-01-21 08:31:12.202800: step: 1204/530, loss: 0.17007428407669067
2023-01-21 08:31:13.393363: step: 1208/530, loss: 0.34428685903549194
2023-01-21 08:31:14.584617: step: 1212/530, loss: 0.7938814163208008
2023-01-21 08:31:15.786451: step: 1216/530, loss: 3.598043203353882
2023-01-21 08:31:16.954193: step: 1220/530, loss: 1.4521902799606323
2023-01-21 08:31:18.143467: step: 1224/530, loss: 1.7422288656234741
2023-01-21 08:31:19.292252: step: 1228/530, loss: 1.2381190061569214
2023-01-21 08:31:20.431093: step: 1232/530, loss: 0.27103549242019653
2023-01-21 08:31:21.589329: step: 1236/530, loss: 0.7396968007087708
2023-01-21 08:31:22.770701: step: 1240/530, loss: 0.3635512590408325
2023-01-21 08:31:23.939440: step: 1244/530, loss: 2.7506442070007324
2023-01-21 08:31:25.116405: step: 1248/530, loss: 0.4463156461715698
2023-01-21 08:31:26.291759: step: 1252/530, loss: 0.30058756470680237
2023-01-21 08:31:27.451666: step: 1256/530, loss: 0.6068265438079834
2023-01-21 08:31:28.610597: step: 1260/530, loss: 8.187128067016602
2023-01-21 08:31:29.782828: step: 1264/530, loss: 1.5500524044036865
2023-01-21 08:31:30.956264: step: 1268/530, loss: 2.888580560684204
2023-01-21 08:31:32.189497: step: 1272/530, loss: 2.5192904472351074
2023-01-21 08:31:33.367471: step: 1276/530, loss: 7.838134288787842
2023-01-21 08:31:34.518584: step: 1280/530, loss: 0.23743054270744324
2023-01-21 08:31:35.702197: step: 1284/530, loss: 1.9662806987762451
2023-01-21 08:31:36.858913: step: 1288/530, loss: 0.8476062417030334
2023-01-21 08:31:38.083694: step: 1292/530, loss: 1.777708649635315
2023-01-21 08:31:39.266622: step: 1296/530, loss: 0.3524801433086395
2023-01-21 08:31:40.468445: step: 1300/530, loss: 3.048319101333618
2023-01-21 08:31:41.668966: step: 1304/530, loss: 2.00106143951416
2023-01-21 08:31:42.852295: step: 1308/530, loss: 0.5819625854492188
2023-01-21 08:31:44.076766: step: 1312/530, loss: 0.5257468223571777
2023-01-21 08:31:45.282337: step: 1316/530, loss: 2.175075054168701
2023-01-21 08:31:46.419891: step: 1320/530, loss: 0.5954471826553345
2023-01-21 08:31:47.621287: step: 1324/530, loss: 1.0144542455673218
2023-01-21 08:31:48.789884: step: 1328/530, loss: 1.098166823387146
2023-01-21 08:31:49.965947: step: 1332/530, loss: 2.2659215927124023
2023-01-21 08:31:51.178165: step: 1336/530, loss: 2.822305202484131
2023-01-21 08:31:52.362352: step: 1340/530, loss: 0.5859823822975159
2023-01-21 08:31:53.579753: step: 1344/530, loss: 1.0970247983932495
2023-01-21 08:31:54.764479: step: 1348/530, loss: 0.2839561998844147
2023-01-21 08:31:55.978253: step: 1352/530, loss: 1.1143438816070557
2023-01-21 08:31:57.137082: step: 1356/530, loss: 0.6988218426704407
2023-01-21 08:31:58.320326: step: 1360/530, loss: 0.3243767321109772
2023-01-21 08:31:59.497440: step: 1364/530, loss: 1.795779824256897
2023-01-21 08:32:00.693425: step: 1368/530, loss: 0.4606708586215973
2023-01-21 08:32:01.848176: step: 1372/530, loss: 1.1833899021148682
2023-01-21 08:32:03.016234: step: 1376/530, loss: 0.26833319664001465
2023-01-21 08:32:04.183162: step: 1380/530, loss: 0.6115039587020874
2023-01-21 08:32:05.330291: step: 1384/530, loss: 0.32991185784339905
2023-01-21 08:32:06.539950: step: 1388/530, loss: 1.9790300130844116
2023-01-21 08:32:07.688461: step: 1392/530, loss: 1.6219842433929443
2023-01-21 08:32:08.873213: step: 1396/530, loss: 0.2364889681339264
2023-01-21 08:32:10.079883: step: 1400/530, loss: 1.5593031644821167
2023-01-21 08:32:11.272264: step: 1404/530, loss: 2.0267093181610107
2023-01-21 08:32:12.472168: step: 1408/530, loss: 0.975976288318634
2023-01-21 08:32:13.654009: step: 1412/530, loss: 0.2554343044757843
2023-01-21 08:32:14.834652: step: 1416/530, loss: 0.49041810631752014
2023-01-21 08:32:16.008505: step: 1420/530, loss: 1.1858885288238525
2023-01-21 08:32:17.193479: step: 1424/530, loss: 0.42878180742263794
2023-01-21 08:32:18.373808: step: 1428/530, loss: 0.5493103861808777
2023-01-21 08:32:19.551917: step: 1432/530, loss: 1.5281364917755127
2023-01-21 08:32:20.721628: step: 1436/530, loss: 1.5015480518341064
2023-01-21 08:32:21.881082: step: 1440/530, loss: 1.9158960580825806
2023-01-21 08:32:23.078964: step: 1444/530, loss: 1.9169243574142456
2023-01-21 08:32:24.248499: step: 1448/530, loss: 0.32771578431129456
2023-01-21 08:32:25.438318: step: 1452/530, loss: 0.5097944736480713
2023-01-21 08:32:26.587205: step: 1456/530, loss: 0.26397567987442017
2023-01-21 08:32:27.757310: step: 1460/530, loss: 0.9739590883255005
2023-01-21 08:32:29.002782: step: 1464/530, loss: 0.39235609769821167
2023-01-21 08:32:30.193729: step: 1468/530, loss: 1.3040274381637573
2023-01-21 08:32:31.349835: step: 1472/530, loss: 1.1072018146514893
2023-01-21 08:32:32.531225: step: 1476/530, loss: 2.0209405422210693
2023-01-21 08:32:33.732315: step: 1480/530, loss: 1.5498924255371094
2023-01-21 08:32:34.961716: step: 1484/530, loss: 0.2637074589729309
2023-01-21 08:32:36.150279: step: 1488/530, loss: 1.4442286491394043
2023-01-21 08:32:37.314358: step: 1492/530, loss: 0.9857972860336304
2023-01-21 08:32:38.482727: step: 1496/530, loss: 0.3248816430568695
2023-01-21 08:32:39.719353: step: 1500/530, loss: 1.0157831907272339
2023-01-21 08:32:40.923592: step: 1504/530, loss: 1.0291160345077515
2023-01-21 08:32:42.125099: step: 1508/530, loss: 0.13757237792015076
2023-01-21 08:32:43.280229: step: 1512/530, loss: 2.0784716606140137
2023-01-21 08:32:44.493218: step: 1516/530, loss: 2.0741190910339355
2023-01-21 08:32:45.710357: step: 1520/530, loss: 0.277141809463501
2023-01-21 08:32:46.891179: step: 1524/530, loss: 1.0505849123001099
2023-01-21 08:32:48.035618: step: 1528/530, loss: 1.8539321422576904
2023-01-21 08:32:49.222968: step: 1532/530, loss: 2.7188661098480225
2023-01-21 08:32:50.382806: step: 1536/530, loss: 0.35789886116981506
2023-01-21 08:32:51.548276: step: 1540/530, loss: 0.45019227266311646
2023-01-21 08:32:52.733332: step: 1544/530, loss: 2.5588836669921875
2023-01-21 08:32:53.903780: step: 1548/530, loss: 2.848616600036621
2023-01-21 08:32:55.072020: step: 1552/530, loss: 1.191169023513794
2023-01-21 08:32:56.250928: step: 1556/530, loss: 0.6516002416610718
2023-01-21 08:32:57.416522: step: 1560/530, loss: 1.4375171661376953
2023-01-21 08:32:58.557455: step: 1564/530, loss: 2.6166090965270996
2023-01-21 08:32:59.711715: step: 1568/530, loss: 0.4241008758544922
2023-01-21 08:33:00.940828: step: 1572/530, loss: 0.7075384855270386
2023-01-21 08:33:02.114271: step: 1576/530, loss: 0.30217456817626953
2023-01-21 08:33:03.249918: step: 1580/530, loss: 1.2296066284179688
2023-01-21 08:33:04.423986: step: 1584/530, loss: 0.1581396609544754
2023-01-21 08:33:05.630192: step: 1588/530, loss: 0.15544824302196503
2023-01-21 08:33:06.805544: step: 1592/530, loss: 0.9800190925598145
2023-01-21 08:33:07.983191: step: 1596/530, loss: 0.6308501362800598
2023-01-21 08:33:09.160803: step: 1600/530, loss: 1.304701566696167
2023-01-21 08:33:10.317930: step: 1604/530, loss: 0.48541295528411865
2023-01-21 08:33:11.484432: step: 1608/530, loss: 1.5686932802200317
2023-01-21 08:33:12.684330: step: 1612/530, loss: 1.1183862686157227
2023-01-21 08:33:13.888583: step: 1616/530, loss: 1.0055925846099854
2023-01-21 08:33:15.081103: step: 1620/530, loss: 1.1093666553497314
2023-01-21 08:33:16.248871: step: 1624/530, loss: 2.5413472652435303
2023-01-21 08:33:17.446807: step: 1628/530, loss: 1.0392913818359375
2023-01-21 08:33:18.588427: step: 1632/530, loss: 0.6367090344429016
2023-01-21 08:33:19.776790: step: 1636/530, loss: 0.9832679629325867
2023-01-21 08:33:20.967727: step: 1640/530, loss: 2.923659563064575
2023-01-21 08:33:22.167980: step: 1644/530, loss: 0.9545735120773315
2023-01-21 08:33:23.334685: step: 1648/530, loss: 2.4707348346710205
2023-01-21 08:33:24.478481: step: 1652/530, loss: 8.249143600463867
2023-01-21 08:33:25.714389: step: 1656/530, loss: 5.710055351257324
2023-01-21 08:33:26.869598: step: 1660/530, loss: 3.128147602081299
2023-01-21 08:33:28.075118: step: 1664/530, loss: 2.0731728076934814
2023-01-21 08:33:29.236318: step: 1668/530, loss: 1.7015742063522339
2023-01-21 08:33:30.467680: step: 1672/530, loss: 3.0843937397003174
2023-01-21 08:33:31.652400: step: 1676/530, loss: 0.5505193471908569
2023-01-21 08:33:32.812563: step: 1680/530, loss: 0.24050307273864746
2023-01-21 08:33:34.003111: step: 1684/530, loss: 2.563603401184082
2023-01-21 08:33:35.171656: step: 1688/530, loss: 0.2692674696445465
2023-01-21 08:33:36.340259: step: 1692/530, loss: 1.6214840412139893
2023-01-21 08:33:37.525766: step: 1696/530, loss: 2.4539895057678223
2023-01-21 08:33:38.670356: step: 1700/530, loss: 0.4843244254589081
2023-01-21 08:33:39.908780: step: 1704/530, loss: 0.9586536288261414
2023-01-21 08:33:41.081137: step: 1708/530, loss: 0.31897610425949097
2023-01-21 08:33:42.335078: step: 1712/530, loss: 0.6313233971595764
2023-01-21 08:33:43.510581: step: 1716/530, loss: 0.2316306233406067
2023-01-21 08:33:44.680130: step: 1720/530, loss: 2.878556251525879
2023-01-21 08:33:45.833293: step: 1724/530, loss: 0.682036280632019
2023-01-21 08:33:47.051745: step: 1728/530, loss: 2.095612049102783
2023-01-21 08:33:48.262292: step: 1732/530, loss: 0.5580075979232788
2023-01-21 08:33:49.433044: step: 1736/530, loss: 0.3293209969997406
2023-01-21 08:33:50.596068: step: 1740/530, loss: 1.3797705173492432
2023-01-21 08:33:51.799434: step: 1744/530, loss: 7.03170919418335
2023-01-21 08:33:52.956168: step: 1748/530, loss: 2.1363449096679688
2023-01-21 08:33:54.157401: step: 1752/530, loss: 1.2319419384002686
2023-01-21 08:33:55.347026: step: 1756/530, loss: 0.23436132073402405
2023-01-21 08:33:56.495021: step: 1760/530, loss: 2.2236969470977783
2023-01-21 08:33:57.676616: step: 1764/530, loss: 0.5651636123657227
2023-01-21 08:33:58.857945: step: 1768/530, loss: 2.6681671142578125
2023-01-21 08:34:00.025341: step: 1772/530, loss: 2.197348117828369
2023-01-21 08:34:01.213882: step: 1776/530, loss: 1.106221079826355
2023-01-21 08:34:02.385339: step: 1780/530, loss: 2.397181987762451
2023-01-21 08:34:03.565508: step: 1784/530, loss: 0.9104430079460144
2023-01-21 08:34:04.734816: step: 1788/530, loss: 0.5737716555595398
2023-01-21 08:34:05.903726: step: 1792/530, loss: 7.948434352874756
2023-01-21 08:34:07.086628: step: 1796/530, loss: 0.8916475176811218
2023-01-21 08:34:08.269883: step: 1800/530, loss: 1.126198649406433
2023-01-21 08:34:09.453653: step: 1804/530, loss: 1.0233383178710938
2023-01-21 08:34:10.704514: step: 1808/530, loss: 1.742366909980774
2023-01-21 08:34:11.875608: step: 1812/530, loss: 2.1947848796844482
2023-01-21 08:34:13.072507: step: 1816/530, loss: 0.20224609971046448
2023-01-21 08:34:14.239555: step: 1820/530, loss: 0.47669029235839844
2023-01-21 08:34:15.411219: step: 1824/530, loss: 1.6268694400787354
2023-01-21 08:34:16.545120: step: 1828/530, loss: 0.35870909690856934
2023-01-21 08:34:17.746975: step: 1832/530, loss: 0.2243306189775467
2023-01-21 08:34:18.906902: step: 1836/530, loss: 1.190079927444458
2023-01-21 08:34:20.104696: step: 1840/530, loss: 0.48348483443260193
2023-01-21 08:34:21.250097: step: 1844/530, loss: 0.6199809312820435
2023-01-21 08:34:22.434367: step: 1848/530, loss: 2.471400260925293
2023-01-21 08:34:23.640389: step: 1852/530, loss: 0.8697818517684937
2023-01-21 08:34:24.840374: step: 1856/530, loss: 0.256306916475296
2023-01-21 08:34:26.031579: step: 1860/530, loss: 2.5766377449035645
2023-01-21 08:34:27.181079: step: 1864/530, loss: 0.1835063397884369
2023-01-21 08:34:28.374638: step: 1868/530, loss: 0.26685434579849243
2023-01-21 08:34:29.568731: step: 1872/530, loss: 0.5715863704681396
2023-01-21 08:34:30.758930: step: 1876/530, loss: 1.0721778869628906
2023-01-21 08:34:31.920998: step: 1880/530, loss: 0.2672633230686188
2023-01-21 08:34:33.155159: step: 1884/530, loss: 0.9958361983299255
2023-01-21 08:34:34.344063: step: 1888/530, loss: 0.6078117489814758
2023-01-21 08:34:35.506079: step: 1892/530, loss: 0.16473440825939178
2023-01-21 08:34:36.736311: step: 1896/530, loss: 0.313943088054657
2023-01-21 08:34:37.913984: step: 1900/530, loss: 1.1060047149658203
2023-01-21 08:34:39.115043: step: 1904/530, loss: 0.32612329721450806
2023-01-21 08:34:40.313083: step: 1908/530, loss: 0.679754376411438
2023-01-21 08:34:41.500063: step: 1912/530, loss: 3.5244832038879395
2023-01-21 08:34:42.731160: step: 1916/530, loss: 0.6347153186798096
2023-01-21 08:34:43.909645: step: 1920/530, loss: 0.38395142555236816
2023-01-21 08:34:45.076436: step: 1924/530, loss: 0.43221569061279297
2023-01-21 08:34:46.269343: step: 1928/530, loss: 1.3999722003936768
2023-01-21 08:34:47.469007: step: 1932/530, loss: 2.0128231048583984
2023-01-21 08:34:48.664949: step: 1936/530, loss: 0.3185945451259613
2023-01-21 08:34:49.827737: step: 1940/530, loss: 0.13733787834644318
2023-01-21 08:34:51.013650: step: 1944/530, loss: 2.5620791912078857
2023-01-21 08:34:52.209606: step: 1948/530, loss: 0.35016995668411255
2023-01-21 08:34:53.351786: step: 1952/530, loss: 0.47112616896629333
2023-01-21 08:34:54.530700: step: 1956/530, loss: 0.24896173179149628
2023-01-21 08:34:55.718024: step: 1960/530, loss: 1.667509913444519
2023-01-21 08:34:56.897486: step: 1964/530, loss: 0.420863538980484
2023-01-21 08:34:58.126046: step: 1968/530, loss: 0.5923202633857727
2023-01-21 08:34:59.297305: step: 1972/530, loss: 0.6023988723754883
2023-01-21 08:35:00.455116: step: 1976/530, loss: 0.16907010972499847
2023-01-21 08:35:01.685933: step: 1980/530, loss: 1.136102557182312
2023-01-21 08:35:02.911717: step: 1984/530, loss: 0.23996008932590485
2023-01-21 08:35:04.100341: step: 1988/530, loss: 1.2824426889419556
2023-01-21 08:35:05.276079: step: 1992/530, loss: 1.0406427383422852
2023-01-21 08:35:06.444253: step: 1996/530, loss: 0.3827822208404541
2023-01-21 08:35:07.628227: step: 2000/530, loss: 0.7970246076583862
2023-01-21 08:35:08.815470: step: 2004/530, loss: 0.4341971278190613
2023-01-21 08:35:09.982586: step: 2008/530, loss: 0.6576734781265259
2023-01-21 08:35:11.169082: step: 2012/530, loss: 0.3152327537536621
2023-01-21 08:35:12.415347: step: 2016/530, loss: 0.2892214059829712
2023-01-21 08:35:13.592615: step: 2020/530, loss: 0.34775933623313904
2023-01-21 08:35:14.756397: step: 2024/530, loss: 0.6816993951797485
2023-01-21 08:35:15.895235: step: 2028/530, loss: 1.1355819702148438
2023-01-21 08:35:17.092124: step: 2032/530, loss: 0.4416075050830841
2023-01-21 08:35:18.245784: step: 2036/530, loss: 2.18332576751709
2023-01-21 08:35:19.460568: step: 2040/530, loss: 0.3988000750541687
2023-01-21 08:35:20.642857: step: 2044/530, loss: 0.9270526766777039
2023-01-21 08:35:21.815086: step: 2048/530, loss: 0.31174221634864807
2023-01-21 08:35:22.984027: step: 2052/530, loss: 1.2042081356048584
2023-01-21 08:35:24.153012: step: 2056/530, loss: 0.4926568865776062
2023-01-21 08:35:25.332313: step: 2060/530, loss: 0.9439895153045654
2023-01-21 08:35:26.577765: step: 2064/530, loss: 0.6370525360107422
2023-01-21 08:35:27.780386: step: 2068/530, loss: 0.38037627935409546
2023-01-21 08:35:28.930857: step: 2072/530, loss: 0.9322097897529602
2023-01-21 08:35:30.105154: step: 2076/530, loss: 0.3103620111942291
2023-01-21 08:35:31.299253: step: 2080/530, loss: 1.1562665700912476
2023-01-21 08:35:32.448697: step: 2084/530, loss: 1.0123546123504639
2023-01-21 08:35:33.644045: step: 2088/530, loss: 0.33552056550979614
2023-01-21 08:35:34.824811: step: 2092/530, loss: 0.4500119090080261
2023-01-21 08:35:36.008044: step: 2096/530, loss: 0.2729125916957855
2023-01-21 08:35:37.183014: step: 2100/530, loss: 0.8104250431060791
2023-01-21 08:35:38.409073: step: 2104/530, loss: 0.520806074142456
2023-01-21 08:35:39.629905: step: 2108/530, loss: 1.4512125253677368
2023-01-21 08:35:40.813177: step: 2112/530, loss: 0.4688398540019989
2023-01-21 08:35:42.071994: step: 2116/530, loss: 0.9123752117156982
2023-01-21 08:35:43.258345: step: 2120/530, loss: 0.18193435668945312
==================================================
Loss: 3.271
--------------------
Dev: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.6451612903225806, 'r': 0.37037037037037035, 'f1': 0.4705882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.875, 'r': 0.2222222222222222, 'f1': 0.3544303797468354}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.8333333333333334, 'r': 0.1388888888888889, 'f1': 0.2380952380952381}, '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': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.6451612903225806, 'r': 0.37037037037037035, 'f1': 0.4705882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.875, 'r': 0.2222222222222222, 'f1': 0.3544303797468354}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.8333333333333334, 'r': 0.1388888888888889, 'f1': 0.2380952380952381}, '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 08:36:45.710723: step: 4/530, loss: 0.855586051940918
2023-01-21 08:36:46.856996: step: 8/530, loss: 0.4452177882194519
2023-01-21 08:36:48.036934: step: 12/530, loss: 0.7808765172958374
2023-01-21 08:36:49.252403: step: 16/530, loss: 2.1084628105163574
2023-01-21 08:36:50.469691: step: 20/530, loss: 1.1509861946105957
2023-01-21 08:36:51.639135: step: 24/530, loss: 4.751423358917236
2023-01-21 08:36:52.803336: step: 28/530, loss: 1.015251874923706
2023-01-21 08:36:54.020110: step: 32/530, loss: 0.6905354261398315
2023-01-21 08:36:55.178015: step: 36/530, loss: 2.4051554203033447
2023-01-21 08:36:56.338260: step: 40/530, loss: 0.6779331564903259
2023-01-21 08:36:57.493473: step: 44/530, loss: 1.6110358238220215
2023-01-21 08:36:58.706818: step: 48/530, loss: 2.5808560848236084
2023-01-21 08:36:59.928777: step: 52/530, loss: 2.0342133045196533
2023-01-21 08:37:01.155449: step: 56/530, loss: 1.0091273784637451
2023-01-21 08:37:02.322898: step: 60/530, loss: 1.0374675989151
2023-01-21 08:37:03.479678: step: 64/530, loss: 1.0511161088943481
2023-01-21 08:37:04.643866: step: 68/530, loss: 0.7938187122344971
2023-01-21 08:37:05.846346: step: 72/530, loss: 1.57943856716156
2023-01-21 08:37:07.038056: step: 76/530, loss: 0.8337065577507019
2023-01-21 08:37:08.229676: step: 80/530, loss: 0.44812488555908203
2023-01-21 08:37:09.448982: step: 84/530, loss: 0.4170568287372589
2023-01-21 08:37:10.637848: step: 88/530, loss: 0.8539484143257141
2023-01-21 08:37:11.876096: step: 92/530, loss: 1.6921844482421875
2023-01-21 08:37:13.064150: step: 96/530, loss: 0.21476612985134125
2023-01-21 08:37:14.204948: step: 100/530, loss: 0.26030951738357544
2023-01-21 08:37:15.357371: step: 104/530, loss: 6.710485935211182
2023-01-21 08:37:16.519763: step: 108/530, loss: 1.340043544769287
2023-01-21 08:37:17.784710: step: 112/530, loss: 0.37760084867477417
2023-01-21 08:37:18.957942: step: 116/530, loss: 0.7547712922096252
2023-01-21 08:37:20.119698: step: 120/530, loss: 0.7568196058273315
2023-01-21 08:37:21.315869: step: 124/530, loss: 1.65353262424469
2023-01-21 08:37:22.488715: step: 128/530, loss: 0.8805731534957886
2023-01-21 08:37:23.670194: step: 132/530, loss: 1.305283546447754
2023-01-21 08:37:24.895985: step: 136/530, loss: 0.19624194502830505
2023-01-21 08:37:26.061858: step: 140/530, loss: 0.16028723120689392
2023-01-21 08:37:27.207127: step: 144/530, loss: 0.11081180721521378
2023-01-21 08:37:28.335757: step: 148/530, loss: 0.38658079504966736
2023-01-21 08:37:29.519190: step: 152/530, loss: 0.5124524831771851
2023-01-21 08:37:30.686376: step: 156/530, loss: 0.9850184917449951
2023-01-21 08:37:31.884774: step: 160/530, loss: 0.38996392488479614
2023-01-21 08:37:33.056438: step: 164/530, loss: 0.9529595375061035
2023-01-21 08:37:34.235723: step: 168/530, loss: 0.2647349238395691
2023-01-21 08:37:35.419804: step: 172/530, loss: 0.2961168885231018
2023-01-21 08:37:36.614603: step: 176/530, loss: 0.829142689704895
2023-01-21 08:37:37.808936: step: 180/530, loss: 0.2034660279750824
2023-01-21 08:37:38.989309: step: 184/530, loss: 0.09820985794067383
2023-01-21 08:37:40.136807: step: 188/530, loss: 0.1975582093000412
2023-01-21 08:37:41.347663: step: 192/530, loss: 0.10032311081886292
2023-01-21 08:37:42.571446: step: 196/530, loss: 0.5717596411705017
2023-01-21 08:37:43.762970: step: 200/530, loss: 0.26164865493774414
2023-01-21 08:37:44.898737: step: 204/530, loss: 0.240918830037117
2023-01-21 08:37:46.174007: step: 208/530, loss: 0.733033299446106
2023-01-21 08:37:47.369044: step: 212/530, loss: 1.5578622817993164
2023-01-21 08:37:48.530358: step: 216/530, loss: 1.1439812183380127
2023-01-21 08:37:49.739196: step: 220/530, loss: 0.10916472226381302
2023-01-21 08:37:50.871925: step: 224/530, loss: 0.219997376203537
2023-01-21 08:37:51.993498: step: 228/530, loss: 0.2788964807987213
2023-01-21 08:37:53.207854: step: 232/530, loss: 0.38707637786865234
2023-01-21 08:37:54.414080: step: 236/530, loss: 0.4448709487915039
2023-01-21 08:37:55.600908: step: 240/530, loss: 0.8720974922180176
2023-01-21 08:37:56.782044: step: 244/530, loss: 1.384368658065796
2023-01-21 08:37:57.959639: step: 248/530, loss: 0.29836687445640564
2023-01-21 08:37:59.111218: step: 252/530, loss: 0.6134076118469238
2023-01-21 08:38:00.304579: step: 256/530, loss: 0.2177387773990631
2023-01-21 08:38:01.468390: step: 260/530, loss: 1.3922553062438965
2023-01-21 08:38:02.688550: step: 264/530, loss: 0.6501887440681458
2023-01-21 08:38:03.887256: step: 268/530, loss: 0.2935255169868469
2023-01-21 08:38:05.047176: step: 272/530, loss: 0.15427465736865997
2023-01-21 08:38:06.218886: step: 276/530, loss: 1.3494079113006592
2023-01-21 08:38:07.427913: step: 280/530, loss: 0.3016176223754883
2023-01-21 08:38:08.641965: step: 284/530, loss: 1.1531164646148682
2023-01-21 08:38:09.858257: step: 288/530, loss: 0.6608260869979858
2023-01-21 08:38:11.024660: step: 292/530, loss: 0.29079669713974
2023-01-21 08:38:12.171672: step: 296/530, loss: 0.33798158168792725
2023-01-21 08:38:13.321027: step: 300/530, loss: 0.285319983959198
2023-01-21 08:38:14.530325: step: 304/530, loss: 0.35087910294532776
2023-01-21 08:38:15.689872: step: 308/530, loss: 1.0302305221557617
2023-01-21 08:38:16.835723: step: 312/530, loss: 0.7295089960098267
2023-01-21 08:38:18.045312: step: 316/530, loss: 1.2713327407836914
2023-01-21 08:38:19.231618: step: 320/530, loss: 2.478558301925659
2023-01-21 08:38:20.441501: step: 324/530, loss: 1.1010805368423462
2023-01-21 08:38:21.680627: step: 328/530, loss: 0.25483864545822144
2023-01-21 08:38:22.841596: step: 332/530, loss: 0.7715908288955688
2023-01-21 08:38:24.017064: step: 336/530, loss: 1.1186020374298096
2023-01-21 08:38:25.186712: step: 340/530, loss: 1.389279842376709
2023-01-21 08:38:26.336244: step: 344/530, loss: 0.2544185519218445
2023-01-21 08:38:27.482977: step: 348/530, loss: 1.660683274269104
2023-01-21 08:38:28.647676: step: 352/530, loss: 0.18009424209594727
2023-01-21 08:38:29.778760: step: 356/530, loss: 0.1359354555606842
2023-01-21 08:38:30.937474: step: 360/530, loss: 0.43625032901763916
2023-01-21 08:38:32.096333: step: 364/530, loss: 1.1416860818862915
2023-01-21 08:38:33.273917: step: 368/530, loss: 1.5651010274887085
2023-01-21 08:38:34.465881: step: 372/530, loss: 0.6074217557907104
2023-01-21 08:38:35.645433: step: 376/530, loss: 0.43942880630493164
2023-01-21 08:38:36.856231: step: 380/530, loss: 0.16805659234523773
2023-01-21 08:38:38.061270: step: 384/530, loss: 8.138800621032715
2023-01-21 08:38:39.291581: step: 388/530, loss: 0.12257328629493713
2023-01-21 08:38:40.504703: step: 392/530, loss: 0.5365084409713745
2023-01-21 08:38:41.685446: step: 396/530, loss: 0.43380793929100037
2023-01-21 08:38:42.909224: step: 400/530, loss: 0.4543578624725342
2023-01-21 08:38:44.065453: step: 404/530, loss: 1.8094607591629028
2023-01-21 08:38:45.266968: step: 408/530, loss: 1.2202258110046387
2023-01-21 08:38:46.454353: step: 412/530, loss: 1.421649694442749
2023-01-21 08:38:47.638527: step: 416/530, loss: 0.18434977531433105
2023-01-21 08:38:48.850490: step: 420/530, loss: 9.340108871459961
2023-01-21 08:38:50.044030: step: 424/530, loss: 0.5615571141242981
2023-01-21 08:38:51.235265: step: 428/530, loss: 0.8760896921157837
2023-01-21 08:38:52.451539: step: 432/530, loss: 1.0122190713882446
2023-01-21 08:38:53.678325: step: 436/530, loss: 0.27063122391700745
2023-01-21 08:38:54.834485: step: 440/530, loss: 7.342632293701172
2023-01-21 08:38:55.969963: step: 444/530, loss: 1.4113372564315796
2023-01-21 08:38:57.153252: step: 448/530, loss: 3.759502410888672
2023-01-21 08:38:58.307503: step: 452/530, loss: 0.32438936829566956
2023-01-21 08:38:59.458648: step: 456/530, loss: 0.8607702255249023
2023-01-21 08:39:00.644031: step: 460/530, loss: 0.07533013820648193
2023-01-21 08:39:01.843856: step: 464/530, loss: 0.2518903315067291
2023-01-21 08:39:02.989586: step: 468/530, loss: 2.029696464538574
2023-01-21 08:39:04.184918: step: 472/530, loss: 0.3324987292289734
2023-01-21 08:39:05.396029: step: 476/530, loss: 1.5389682054519653
2023-01-21 08:39:06.593180: step: 480/530, loss: 0.3384334444999695
2023-01-21 08:39:07.746239: step: 484/530, loss: 2.2825450897216797
2023-01-21 08:39:08.971269: step: 488/530, loss: 0.7989309430122375
2023-01-21 08:39:10.171582: step: 492/530, loss: 0.28409624099731445
2023-01-21 08:39:11.387762: step: 496/530, loss: 0.752198338508606
2023-01-21 08:39:12.612097: step: 500/530, loss: 0.8345478773117065
2023-01-21 08:39:13.796795: step: 504/530, loss: 0.1897333264350891
2023-01-21 08:39:14.991427: step: 508/530, loss: 1.1299785375595093
2023-01-21 08:39:16.176218: step: 512/530, loss: 0.23597225546836853
2023-01-21 08:39:17.349859: step: 516/530, loss: 0.39859825372695923
2023-01-21 08:39:18.571449: step: 520/530, loss: 4.35719633102417
2023-01-21 08:39:19.756757: step: 524/530, loss: 1.389021396636963
2023-01-21 08:39:20.940283: step: 528/530, loss: 0.16513347625732422
2023-01-21 08:39:22.144527: step: 532/530, loss: 0.0874779224395752
2023-01-21 08:39:23.356879: step: 536/530, loss: 2.670804500579834
2023-01-21 08:39:24.512753: step: 540/530, loss: 0.7235707640647888
2023-01-21 08:39:25.704150: step: 544/530, loss: 0.1981537938117981
2023-01-21 08:39:26.892864: step: 548/530, loss: 0.34508436918258667
2023-01-21 08:39:28.045929: step: 552/530, loss: 0.1716330647468567
2023-01-21 08:39:29.230376: step: 556/530, loss: 0.2664264738559723
2023-01-21 08:39:30.394824: step: 560/530, loss: 0.21540242433547974
2023-01-21 08:39:31.582824: step: 564/530, loss: 1.2255761623382568
2023-01-21 08:39:32.799611: step: 568/530, loss: 0.31872478127479553
2023-01-21 08:39:33.998322: step: 572/530, loss: 1.0184437036514282
2023-01-21 08:39:35.235189: step: 576/530, loss: 0.9865986108779907
2023-01-21 08:39:36.420853: step: 580/530, loss: 0.25358596444129944
2023-01-21 08:39:37.616853: step: 584/530, loss: 0.20358476042747498
2023-01-21 08:39:38.800856: step: 588/530, loss: 1.6305444240570068
2023-01-21 08:39:39.973895: step: 592/530, loss: 0.26738205552101135
2023-01-21 08:39:41.163849: step: 596/530, loss: 0.652937114238739
2023-01-21 08:39:42.332038: step: 600/530, loss: 1.003240704536438
2023-01-21 08:39:43.543275: step: 604/530, loss: 1.7002644538879395
2023-01-21 08:39:44.763183: step: 608/530, loss: 2.705268144607544
2023-01-21 08:39:45.929153: step: 612/530, loss: 1.6582444906234741
2023-01-21 08:39:47.101499: step: 616/530, loss: 0.2572961747646332
2023-01-21 08:39:48.261208: step: 620/530, loss: 0.3205597698688507
2023-01-21 08:39:49.448365: step: 624/530, loss: 0.25733035802841187
2023-01-21 08:39:50.634872: step: 628/530, loss: 0.40362483263015747
2023-01-21 08:39:51.789403: step: 632/530, loss: 1.9283860921859741
2023-01-21 08:39:52.950174: step: 636/530, loss: 0.7558004260063171
2023-01-21 08:39:54.052420: step: 640/530, loss: 0.8630129098892212
2023-01-21 08:39:55.205498: step: 644/530, loss: 0.2125963568687439
2023-01-21 08:39:56.360746: step: 648/530, loss: 0.714661180973053
2023-01-21 08:39:57.531740: step: 652/530, loss: 0.20170755684375763
2023-01-21 08:39:58.700332: step: 656/530, loss: 2.27115535736084
2023-01-21 08:39:59.852431: step: 660/530, loss: 0.3236314058303833
2023-01-21 08:40:00.986145: step: 664/530, loss: 0.785652220249176
2023-01-21 08:40:02.177684: step: 668/530, loss: 1.093957781791687
2023-01-21 08:40:03.394996: step: 672/530, loss: 0.21857725083827972
2023-01-21 08:40:04.583913: step: 676/530, loss: 0.37661075592041016
2023-01-21 08:40:05.783760: step: 680/530, loss: 0.49998435378074646
2023-01-21 08:40:06.966245: step: 684/530, loss: 0.583878219127655
2023-01-21 08:40:08.130726: step: 688/530, loss: 0.873389720916748
2023-01-21 08:40:09.316260: step: 692/530, loss: 3.0190699100494385
2023-01-21 08:40:10.455395: step: 696/530, loss: 0.38237205147743225
2023-01-21 08:40:11.653543: step: 700/530, loss: 0.20649003982543945
2023-01-21 08:40:12.865500: step: 704/530, loss: 0.6627522706985474
2023-01-21 08:40:13.998641: step: 708/530, loss: 0.3603910505771637
2023-01-21 08:40:15.156146: step: 712/530, loss: 0.549861490726471
2023-01-21 08:40:16.344201: step: 716/530, loss: 1.6641340255737305
2023-01-21 08:40:17.550431: step: 720/530, loss: 0.5336326360702515
2023-01-21 08:40:18.718737: step: 724/530, loss: 6.969512939453125
2023-01-21 08:40:19.904203: step: 728/530, loss: 0.5900471210479736
2023-01-21 08:40:21.084502: step: 732/530, loss: 0.8938699960708618
2023-01-21 08:40:22.280664: step: 736/530, loss: 0.38054150342941284
2023-01-21 08:40:23.430104: step: 740/530, loss: 0.13817104697227478
2023-01-21 08:40:24.620622: step: 744/530, loss: 0.4687361717224121
2023-01-21 08:40:25.779233: step: 748/530, loss: 0.23717433214187622
2023-01-21 08:40:26.933071: step: 752/530, loss: 0.23689956963062286
2023-01-21 08:40:28.091168: step: 756/530, loss: 0.11090616881847382
2023-01-21 08:40:29.292680: step: 760/530, loss: 0.2205759435892105
2023-01-21 08:40:30.437900: step: 764/530, loss: 0.7549692988395691
2023-01-21 08:40:31.565027: step: 768/530, loss: 0.5236148834228516
2023-01-21 08:40:32.750551: step: 772/530, loss: 0.34295111894607544
2023-01-21 08:40:33.928175: step: 776/530, loss: 1.338382601737976
2023-01-21 08:40:35.084896: step: 780/530, loss: 2.277797222137451
2023-01-21 08:40:36.229058: step: 784/530, loss: 0.9836255311965942
2023-01-21 08:40:37.429552: step: 788/530, loss: 0.24366359412670135
2023-01-21 08:40:38.636875: step: 792/530, loss: 1.9622857570648193
2023-01-21 08:40:39.794437: step: 796/530, loss: 0.49967890977859497
2023-01-21 08:40:40.922589: step: 800/530, loss: 0.24676236510276794
2023-01-21 08:40:42.100315: step: 804/530, loss: 0.2415885031223297
2023-01-21 08:40:43.295038: step: 808/530, loss: 0.49461764097213745
2023-01-21 08:40:44.469612: step: 812/530, loss: 0.7522754669189453
2023-01-21 08:40:45.670022: step: 816/530, loss: 0.16216811537742615
2023-01-21 08:40:46.848879: step: 820/530, loss: 0.23912134766578674
2023-01-21 08:40:48.049599: step: 824/530, loss: 0.538262665271759
2023-01-21 08:40:49.244429: step: 828/530, loss: 1.7306843996047974
2023-01-21 08:40:50.429782: step: 832/530, loss: 0.40253207087516785
2023-01-21 08:40:51.654364: step: 836/530, loss: 0.14648601412773132
2023-01-21 08:40:52.827843: step: 840/530, loss: 0.7606114149093628
2023-01-21 08:40:54.014209: step: 844/530, loss: 0.32902881503105164
2023-01-21 08:40:55.200450: step: 848/530, loss: 1.9820952415466309
2023-01-21 08:40:56.402960: step: 852/530, loss: 0.2864893972873688
2023-01-21 08:40:57.587375: step: 856/530, loss: 1.0638301372528076
2023-01-21 08:40:58.744616: step: 860/530, loss: 1.1397560834884644
2023-01-21 08:40:59.916993: step: 864/530, loss: 0.31781044602394104
2023-01-21 08:41:01.150615: step: 868/530, loss: 0.34152308106422424
2023-01-21 08:41:02.326644: step: 872/530, loss: 0.27122706174850464
2023-01-21 08:41:03.459128: step: 876/530, loss: 0.8363618850708008
2023-01-21 08:41:04.585064: step: 880/530, loss: 0.22394169867038727
2023-01-21 08:41:05.794704: step: 884/530, loss: 0.8044120073318481
2023-01-21 08:41:06.990759: step: 888/530, loss: 0.13389262557029724
2023-01-21 08:41:08.130635: step: 892/530, loss: 0.4735240042209625
2023-01-21 08:41:09.277236: step: 896/530, loss: 0.5812658071517944
2023-01-21 08:41:10.439747: step: 900/530, loss: 0.1132417693734169
2023-01-21 08:41:11.631169: step: 904/530, loss: 0.4325030744075775
2023-01-21 08:41:12.946863: step: 908/530, loss: 0.3314061164855957
2023-01-21 08:41:14.124312: step: 912/530, loss: 0.301017165184021
2023-01-21 08:41:15.323472: step: 916/530, loss: 0.32120147347450256
2023-01-21 08:41:16.490686: step: 920/530, loss: 0.483271062374115
2023-01-21 08:41:17.672401: step: 924/530, loss: 0.4006916284561157
2023-01-21 08:41:18.788088: step: 928/530, loss: 0.29290294647216797
2023-01-21 08:41:19.969193: step: 932/530, loss: 0.8069778680801392
2023-01-21 08:41:21.104225: step: 936/530, loss: 0.2538430988788605
2023-01-21 08:41:22.311351: step: 940/530, loss: 0.5062859058380127
2023-01-21 08:41:23.481937: step: 944/530, loss: 0.16179409623146057
2023-01-21 08:41:24.667252: step: 948/530, loss: 0.5537605881690979
2023-01-21 08:41:25.842217: step: 952/530, loss: 2.170041084289551
2023-01-21 08:41:27.019944: step: 956/530, loss: 0.14002355933189392
2023-01-21 08:41:28.208694: step: 960/530, loss: 0.19696339964866638
2023-01-21 08:41:29.416086: step: 964/530, loss: 0.23387423157691956
2023-01-21 08:41:30.589100: step: 968/530, loss: 0.3124666213989258
2023-01-21 08:41:31.748629: step: 972/530, loss: 0.35653600096702576
2023-01-21 08:41:32.943211: step: 976/530, loss: 0.2768324017524719
2023-01-21 08:41:34.090638: step: 980/530, loss: 0.429777592420578
2023-01-21 08:41:35.234391: step: 984/530, loss: 0.36741504073143005
2023-01-21 08:41:36.402805: step: 988/530, loss: 1.3030859231948853
2023-01-21 08:41:37.570138: step: 992/530, loss: 0.9199998378753662
2023-01-21 08:41:38.761997: step: 996/530, loss: 1.656630277633667
2023-01-21 08:41:39.918386: step: 1000/530, loss: 1.1406357288360596
2023-01-21 08:41:41.098844: step: 1004/530, loss: 0.7632325291633606
2023-01-21 08:41:42.254181: step: 1008/530, loss: 2.2819864749908447
2023-01-21 08:41:43.427826: step: 1012/530, loss: 0.3723047375679016
2023-01-21 08:41:44.573513: step: 1016/530, loss: 0.6346299052238464
2023-01-21 08:41:45.718390: step: 1020/530, loss: 1.2969610691070557
2023-01-21 08:41:46.894798: step: 1024/530, loss: 2.084010601043701
2023-01-21 08:41:48.046779: step: 1028/530, loss: 0.2546687126159668
2023-01-21 08:41:49.243880: step: 1032/530, loss: 0.31039056181907654
2023-01-21 08:41:50.439544: step: 1036/530, loss: 0.5513472557067871
2023-01-21 08:41:51.594819: step: 1040/530, loss: 0.17282705008983612
2023-01-21 08:41:52.751958: step: 1044/530, loss: 1.9321483373641968
2023-01-21 08:41:53.930797: step: 1048/530, loss: 1.239111065864563
2023-01-21 08:41:55.125058: step: 1052/530, loss: 0.09634113311767578
2023-01-21 08:41:56.340858: step: 1056/530, loss: 0.09708116203546524
2023-01-21 08:41:57.528939: step: 1060/530, loss: 1.2651984691619873
2023-01-21 08:41:58.748470: step: 1064/530, loss: 0.9781036376953125
2023-01-21 08:41:59.944146: step: 1068/530, loss: 0.4972190260887146
2023-01-21 08:42:01.080440: step: 1072/530, loss: 1.2587275505065918
2023-01-21 08:42:02.316951: step: 1076/530, loss: 0.30931395292282104
2023-01-21 08:42:03.518360: step: 1080/530, loss: 1.9697833061218262
2023-01-21 08:42:04.657047: step: 1084/530, loss: 0.5634654760360718
2023-01-21 08:42:05.818236: step: 1088/530, loss: 0.5499882698059082
2023-01-21 08:42:06.973115: step: 1092/530, loss: 0.11186311393976212
2023-01-21 08:42:08.128155: step: 1096/530, loss: 0.4333803057670593
2023-01-21 08:42:09.319221: step: 1100/530, loss: 2.1811606884002686
2023-01-21 08:42:10.524954: step: 1104/530, loss: 1.069535732269287
2023-01-21 08:42:11.687968: step: 1108/530, loss: 0.294659286737442
2023-01-21 08:42:12.862724: step: 1112/530, loss: 0.0853419303894043
2023-01-21 08:42:14.067589: step: 1116/530, loss: 0.22624774277210236
2023-01-21 08:42:15.212047: step: 1120/530, loss: 3.4426982402801514
2023-01-21 08:42:16.365314: step: 1124/530, loss: 0.15368223190307617
2023-01-21 08:42:17.565404: step: 1128/530, loss: 1.1220883131027222
2023-01-21 08:42:18.742418: step: 1132/530, loss: 1.181382179260254
2023-01-21 08:42:19.895052: step: 1136/530, loss: 1.783968448638916
2023-01-21 08:42:21.086781: step: 1140/530, loss: 1.5801727771759033
2023-01-21 08:42:22.271617: step: 1144/530, loss: 0.30916959047317505
2023-01-21 08:42:23.431032: step: 1148/530, loss: 0.11473093926906586
2023-01-21 08:42:24.575386: step: 1152/530, loss: 0.06336665153503418
2023-01-21 08:42:25.761939: step: 1156/530, loss: 2.589488983154297
2023-01-21 08:42:26.930563: step: 1160/530, loss: 0.6953050494194031
2023-01-21 08:42:28.118162: step: 1164/530, loss: 0.9822004437446594
2023-01-21 08:42:29.281619: step: 1168/530, loss: 0.18992625176906586
2023-01-21 08:42:30.415096: step: 1172/530, loss: 0.21517829596996307
2023-01-21 08:42:31.597467: step: 1176/530, loss: 0.45739316940307617
2023-01-21 08:42:32.776132: step: 1180/530, loss: 0.2898138165473938
2023-01-21 08:42:33.945237: step: 1184/530, loss: 0.4239616394042969
2023-01-21 08:42:35.107750: step: 1188/530, loss: 0.9341291785240173
2023-01-21 08:42:36.337149: step: 1192/530, loss: 0.2211524248123169
2023-01-21 08:42:37.537313: step: 1196/530, loss: 0.15282964706420898
2023-01-21 08:42:38.700495: step: 1200/530, loss: 0.44604846835136414
2023-01-21 08:42:39.895978: step: 1204/530, loss: 0.8141376376152039
2023-01-21 08:42:41.086537: step: 1208/530, loss: 0.344840407371521
2023-01-21 08:42:42.287052: step: 1212/530, loss: 0.4054010510444641
2023-01-21 08:42:43.461485: step: 1216/530, loss: 0.2823209762573242
2023-01-21 08:42:44.650163: step: 1220/530, loss: 1.0747520923614502
2023-01-21 08:42:45.815668: step: 1224/530, loss: 0.5190297961235046
2023-01-21 08:42:47.017053: step: 1228/530, loss: 0.2597466707229614
2023-01-21 08:42:48.214334: step: 1232/530, loss: 0.298832505941391
2023-01-21 08:42:49.412676: step: 1236/530, loss: 0.17823466658592224
2023-01-21 08:42:50.578874: step: 1240/530, loss: 0.20935240387916565
2023-01-21 08:42:51.777676: step: 1244/530, loss: 7.065886497497559
2023-01-21 08:42:52.986993: step: 1248/530, loss: 1.1593705415725708
2023-01-21 08:42:54.155070: step: 1252/530, loss: 0.20686674118041992
2023-01-21 08:42:55.334689: step: 1256/530, loss: 0.687012255191803
2023-01-21 08:42:56.543932: step: 1260/530, loss: 0.2044035941362381
2023-01-21 08:42:57.717672: step: 1264/530, loss: 0.5511137247085571
2023-01-21 08:42:58.922374: step: 1268/530, loss: 0.26776981353759766
2023-01-21 08:43:00.077313: step: 1272/530, loss: 0.5039999485015869
2023-01-21 08:43:01.223808: step: 1276/530, loss: 0.8315163850784302
2023-01-21 08:43:02.431800: step: 1280/530, loss: 0.16047143936157227
2023-01-21 08:43:03.628783: step: 1284/530, loss: 0.5449684858322144
2023-01-21 08:43:04.777483: step: 1288/530, loss: 1.1899182796478271
2023-01-21 08:43:05.954857: step: 1292/530, loss: 0.49589109420776367
2023-01-21 08:43:07.104190: step: 1296/530, loss: 0.12924447655677795
2023-01-21 08:43:08.264631: step: 1300/530, loss: 0.4900023937225342
2023-01-21 08:43:09.501557: step: 1304/530, loss: 1.0236679315567017
2023-01-21 08:43:10.641052: step: 1308/530, loss: 0.2753603458404541
2023-01-21 08:43:11.854768: step: 1312/530, loss: 0.7138504981994629
2023-01-21 08:43:13.015797: step: 1316/530, loss: 0.6343221664428711
2023-01-21 08:43:14.206281: step: 1320/530, loss: 0.5754326581954956
2023-01-21 08:43:15.393480: step: 1324/530, loss: 0.8345422148704529
2023-01-21 08:43:16.555929: step: 1328/530, loss: 0.973320722579956
2023-01-21 08:43:17.758781: step: 1332/530, loss: 0.2973896861076355
2023-01-21 08:43:18.952406: step: 1336/530, loss: 0.38233500719070435
2023-01-21 08:43:20.110515: step: 1340/530, loss: 0.2734871506690979
2023-01-21 08:43:21.274808: step: 1344/530, loss: 0.1499413549900055
2023-01-21 08:43:22.461233: step: 1348/530, loss: 0.377157986164093
2023-01-21 08:43:23.632348: step: 1352/530, loss: 0.280233770608902
2023-01-21 08:43:24.831433: step: 1356/530, loss: 6.821019172668457
2023-01-21 08:43:26.022926: step: 1360/530, loss: 0.6271806955337524
2023-01-21 08:43:27.244360: step: 1364/530, loss: 0.166996568441391
2023-01-21 08:43:28.418699: step: 1368/530, loss: 0.473133385181427
2023-01-21 08:43:29.570487: step: 1372/530, loss: 0.12262926995754242
2023-01-21 08:43:30.721033: step: 1376/530, loss: 0.8330333232879639
2023-01-21 08:43:31.899163: step: 1380/530, loss: 0.374843031167984
2023-01-21 08:43:33.027082: step: 1384/530, loss: 0.3352983891963959
2023-01-21 08:43:34.206494: step: 1388/530, loss: 0.2312088906764984
2023-01-21 08:43:35.379644: step: 1392/530, loss: 0.3540719151496887
2023-01-21 08:43:36.553717: step: 1396/530, loss: 0.43876639008522034
2023-01-21 08:43:37.724484: step: 1400/530, loss: 1.0939544439315796
2023-01-21 08:43:38.892079: step: 1404/530, loss: 0.12450514733791351
2023-01-21 08:43:40.066287: step: 1408/530, loss: 0.3507053256034851
2023-01-21 08:43:41.232873: step: 1412/530, loss: 0.2615653872489929
2023-01-21 08:43:42.412402: step: 1416/530, loss: 2.3222451210021973
2023-01-21 08:43:43.591877: step: 1420/530, loss: 0.18468505144119263
2023-01-21 08:43:44.839457: step: 1424/530, loss: 0.6247105598449707
2023-01-21 08:43:46.022220: step: 1428/530, loss: 0.4519351124763489
2023-01-21 08:43:47.192863: step: 1432/530, loss: 0.23634500801563263
2023-01-21 08:43:48.371826: step: 1436/530, loss: 2.7619738578796387
2023-01-21 08:43:49.528301: step: 1440/530, loss: 0.5247284173965454
2023-01-21 08:43:50.756229: step: 1444/530, loss: 0.39628496766090393
2023-01-21 08:43:51.975496: step: 1448/530, loss: 0.6105875968933105
2023-01-21 08:43:53.172684: step: 1452/530, loss: 0.9355411529541016
2023-01-21 08:43:54.404871: step: 1456/530, loss: 0.25957679748535156
2023-01-21 08:43:55.646031: step: 1460/530, loss: 0.5639216899871826
2023-01-21 08:43:56.823781: step: 1464/530, loss: 0.0953516960144043
2023-01-21 08:43:57.976624: step: 1468/530, loss: 0.2844092845916748
2023-01-21 08:43:59.128271: step: 1472/530, loss: 0.3961981236934662
2023-01-21 08:44:00.281388: step: 1476/530, loss: 0.12931624054908752
2023-01-21 08:44:01.444808: step: 1480/530, loss: 0.5368785858154297
2023-01-21 08:44:02.632221: step: 1484/530, loss: 0.8295370936393738
2023-01-21 08:44:03.856958: step: 1488/530, loss: 1.185603380203247
2023-01-21 08:44:04.981902: step: 1492/530, loss: 1.35547935962677
2023-01-21 08:44:06.166274: step: 1496/530, loss: 0.1370486319065094
2023-01-21 08:44:07.359346: step: 1500/530, loss: 0.40617600083351135
2023-01-21 08:44:08.544461: step: 1504/530, loss: 0.7772510051727295
2023-01-21 08:44:09.705358: step: 1508/530, loss: 0.3097091317176819
2023-01-21 08:44:10.866778: step: 1512/530, loss: 0.2986011803150177
2023-01-21 08:44:12.055388: step: 1516/530, loss: 0.15018320083618164
2023-01-21 08:44:13.222187: step: 1520/530, loss: 0.1444697380065918
2023-01-21 08:44:14.427281: step: 1524/530, loss: 0.41943708062171936
2023-01-21 08:44:15.608430: step: 1528/530, loss: 0.46325141191482544
2023-01-21 08:44:16.800169: step: 1532/530, loss: 0.3834190368652344
2023-01-21 08:44:17.956583: step: 1536/530, loss: 0.8704002499580383
2023-01-21 08:44:19.160542: step: 1540/530, loss: 0.9263209104537964
2023-01-21 08:44:20.303022: step: 1544/530, loss: 0.494515985250473
2023-01-21 08:44:21.487750: step: 1548/530, loss: 0.24896907806396484
2023-01-21 08:44:22.663465: step: 1552/530, loss: 0.21839872002601624
2023-01-21 08:44:23.870128: step: 1556/530, loss: 0.9395580291748047
2023-01-21 08:44:25.056002: step: 1560/530, loss: 0.40813496708869934
2023-01-21 08:44:26.217434: step: 1564/530, loss: 1.5635590553283691
2023-01-21 08:44:27.394540: step: 1568/530, loss: 0.6656662225723267
2023-01-21 08:44:28.585967: step: 1572/530, loss: 0.7001534104347229
2023-01-21 08:44:29.811064: step: 1576/530, loss: 0.21131138503551483
2023-01-21 08:44:30.994070: step: 1580/530, loss: 0.24342036247253418
2023-01-21 08:44:32.138055: step: 1584/530, loss: 0.07250013202428818
2023-01-21 08:44:33.343260: step: 1588/530, loss: 0.07300672680139542
2023-01-21 08:44:34.514274: step: 1592/530, loss: 0.26943764090538025
2023-01-21 08:44:35.733962: step: 1596/530, loss: 0.18290863931179047
2023-01-21 08:44:36.915716: step: 1600/530, loss: 1.0893621444702148
2023-01-21 08:44:38.115971: step: 1604/530, loss: 0.5250610709190369
2023-01-21 08:44:39.301633: step: 1608/530, loss: 1.76713228225708
2023-01-21 08:44:40.488804: step: 1612/530, loss: 0.7990105152130127
2023-01-21 08:44:41.684251: step: 1616/530, loss: 0.7147620916366577
2023-01-21 08:44:42.869846: step: 1620/530, loss: 2.0545449256896973
2023-01-21 08:44:44.042542: step: 1624/530, loss: 0.8507463932037354
2023-01-21 08:44:45.222193: step: 1628/530, loss: 0.5542624592781067
2023-01-21 08:44:46.367868: step: 1632/530, loss: 0.21331143379211426
2023-01-21 08:44:47.573885: step: 1636/530, loss: 0.4693852663040161
2023-01-21 08:44:48.749033: step: 1640/530, loss: 0.725791335105896
2023-01-21 08:44:49.925942: step: 1644/530, loss: 0.8215768337249756
2023-01-21 08:44:51.161518: step: 1648/530, loss: 0.1420736312866211
2023-01-21 08:44:52.324256: step: 1652/530, loss: 0.47430315613746643
2023-01-21 08:44:53.500942: step: 1656/530, loss: 1.1916295289993286
2023-01-21 08:44:54.640845: step: 1660/530, loss: 0.1517263948917389
2023-01-21 08:44:55.837159: step: 1664/530, loss: 0.3690502941608429
2023-01-21 08:44:57.013166: step: 1668/530, loss: 0.9268876314163208
2023-01-21 08:44:58.235972: step: 1672/530, loss: 0.1950494349002838
2023-01-21 08:44:59.403077: step: 1676/530, loss: 0.6339604258537292
2023-01-21 08:45:00.605108: step: 1680/530, loss: 0.17796821892261505
2023-01-21 08:45:01.773375: step: 1684/530, loss: 0.7268667221069336
2023-01-21 08:45:02.926971: step: 1688/530, loss: 0.1779256910085678
2023-01-21 08:45:04.070831: step: 1692/530, loss: 0.4604984521865845
2023-01-21 08:45:05.276838: step: 1696/530, loss: 0.1403302103281021
2023-01-21 08:45:06.473352: step: 1700/530, loss: 0.21687574684619904
2023-01-21 08:45:07.635020: step: 1704/530, loss: 0.08463907986879349
2023-01-21 08:45:08.815961: step: 1708/530, loss: 0.9153846502304077
2023-01-21 08:45:09.972751: step: 1712/530, loss: 0.20304018259048462
2023-01-21 08:45:11.179626: step: 1716/530, loss: 1.0006614923477173
2023-01-21 08:45:12.359259: step: 1720/530, loss: 0.12624338269233704
2023-01-21 08:45:13.540013: step: 1724/530, loss: 2.6002614498138428
2023-01-21 08:45:14.699694: step: 1728/530, loss: 1.468653917312622
2023-01-21 08:45:15.855903: step: 1732/530, loss: 0.3458734154701233
2023-01-21 08:45:17.072251: step: 1736/530, loss: 0.21797503530979156
2023-01-21 08:45:18.251874: step: 1740/530, loss: 0.20446515083312988
2023-01-21 08:45:19.408518: step: 1744/530, loss: 0.39187535643577576
2023-01-21 08:45:20.551153: step: 1748/530, loss: 0.17925934493541718
2023-01-21 08:45:21.798974: step: 1752/530, loss: 0.24883690476417542
2023-01-21 08:45:22.957221: step: 1756/530, loss: 0.3587840795516968
2023-01-21 08:45:24.163463: step: 1760/530, loss: 0.6691027879714966
2023-01-21 08:45:25.369771: step: 1764/530, loss: 0.15065374970436096
2023-01-21 08:45:26.540738: step: 1768/530, loss: 0.7198614478111267
2023-01-21 08:45:27.713332: step: 1772/530, loss: 0.31544363498687744
2023-01-21 08:45:28.886531: step: 1776/530, loss: 0.27717840671539307
2023-01-21 08:45:30.042018: step: 1780/530, loss: 0.8657217621803284
2023-01-21 08:45:31.228027: step: 1784/530, loss: 1.1702529191970825
2023-01-21 08:45:32.399247: step: 1788/530, loss: 0.133747860789299
2023-01-21 08:45:33.543908: step: 1792/530, loss: 0.4568883776664734
2023-01-21 08:45:34.690434: step: 1796/530, loss: 0.2110402137041092
2023-01-21 08:45:35.851638: step: 1800/530, loss: 0.7984424829483032
2023-01-21 08:45:37.045166: step: 1804/530, loss: 0.2076704055070877
2023-01-21 08:45:38.233911: step: 1808/530, loss: 0.8960598707199097
2023-01-21 08:45:39.356744: step: 1812/530, loss: 0.16908450424671173
2023-01-21 08:45:40.506236: step: 1816/530, loss: 0.049699023365974426
2023-01-21 08:45:41.714877: step: 1820/530, loss: 0.6090865135192871
2023-01-21 08:45:42.904293: step: 1824/530, loss: 0.20098371803760529
2023-01-21 08:45:44.043372: step: 1828/530, loss: 1.9670262336730957
2023-01-21 08:45:45.262277: step: 1832/530, loss: 1.6250746250152588
2023-01-21 08:45:46.432530: step: 1836/530, loss: 0.9139490127563477
2023-01-21 08:45:47.627993: step: 1840/530, loss: 1.5253500938415527
2023-01-21 08:45:48.834095: step: 1844/530, loss: 0.3234158754348755
2023-01-21 08:45:50.016709: step: 1848/530, loss: 0.13614457845687866
2023-01-21 08:45:51.215356: step: 1852/530, loss: 0.2934228777885437
2023-01-21 08:45:52.378003: step: 1856/530, loss: 0.8380802869796753
2023-01-21 08:45:53.570028: step: 1860/530, loss: 0.10628519207239151
2023-01-21 08:45:54.794354: step: 1864/530, loss: 0.2586959898471832
2023-01-21 08:45:55.971822: step: 1868/530, loss: 0.17773085832595825
2023-01-21 08:45:57.132858: step: 1872/530, loss: 0.10024365782737732
2023-01-21 08:45:58.272869: step: 1876/530, loss: 0.33093804121017456
2023-01-21 08:45:59.454566: step: 1880/530, loss: 1.1056833267211914
2023-01-21 08:46:00.640318: step: 1884/530, loss: 0.4413629472255707
2023-01-21 08:46:01.866948: step: 1888/530, loss: 0.525170624256134
2023-01-21 08:46:03.060132: step: 1892/530, loss: 2.2015750408172607
2023-01-21 08:46:04.260308: step: 1896/530, loss: 2.576280117034912
2023-01-21 08:46:05.425045: step: 1900/530, loss: 0.25769686698913574
2023-01-21 08:46:06.610933: step: 1904/530, loss: 0.20434212684631348
2023-01-21 08:46:07.764364: step: 1908/530, loss: 0.5773991942405701
2023-01-21 08:46:08.960522: step: 1912/530, loss: 0.2698260545730591
2023-01-21 08:46:10.118376: step: 1916/530, loss: 0.5288078188896179
2023-01-21 08:46:11.292166: step: 1920/530, loss: 1.4844985008239746
2023-01-21 08:46:12.499233: step: 1924/530, loss: 0.38161301612854004
2023-01-21 08:46:13.697175: step: 1928/530, loss: 0.10798406600952148
2023-01-21 08:46:14.902710: step: 1932/530, loss: 0.17363953590393066
2023-01-21 08:46:16.083844: step: 1936/530, loss: 0.371072381734848
2023-01-21 08:46:17.272991: step: 1940/530, loss: 0.15702897310256958
2023-01-21 08:46:18.441340: step: 1944/530, loss: 0.9871727228164673
2023-01-21 08:46:19.616225: step: 1948/530, loss: 2.017547845840454
2023-01-21 08:46:20.819248: step: 1952/530, loss: 0.6324816346168518
2023-01-21 08:46:22.020432: step: 1956/530, loss: 0.07774534821510315
2023-01-21 08:46:23.167255: step: 1960/530, loss: 0.11034531891345978
2023-01-21 08:46:24.349164: step: 1964/530, loss: 0.30748987197875977
2023-01-21 08:46:25.531263: step: 1968/530, loss: 0.07756614685058594
2023-01-21 08:46:26.711126: step: 1972/530, loss: 0.4122345447540283
2023-01-21 08:46:27.877464: step: 1976/530, loss: 0.1715168058872223
2023-01-21 08:46:29.035622: step: 1980/530, loss: 0.24310904741287231
2023-01-21 08:46:30.182320: step: 1984/530, loss: 0.45279818773269653
2023-01-21 08:46:31.412035: step: 1988/530, loss: 0.1560359001159668
2023-01-21 08:46:32.700422: step: 1992/530, loss: 0.11951227486133575
2023-01-21 08:46:33.866567: step: 1996/530, loss: 0.4826560914516449
2023-01-21 08:46:35.066814: step: 2000/530, loss: 0.265766441822052
2023-01-21 08:46:36.245894: step: 2004/530, loss: 0.7708759307861328
2023-01-21 08:46:37.421810: step: 2008/530, loss: 1.269675850868225
2023-01-21 08:46:38.576330: step: 2012/530, loss: 0.14589612185955048
2023-01-21 08:46:39.744470: step: 2016/530, loss: 0.6239898800849915
2023-01-21 08:46:40.932581: step: 2020/530, loss: 1.1293630599975586
2023-01-21 08:46:42.124986: step: 2024/530, loss: 2.510375738143921
2023-01-21 08:46:43.300705: step: 2028/530, loss: 0.4940025210380554
2023-01-21 08:46:44.493564: step: 2032/530, loss: 0.14799128472805023
2023-01-21 08:46:45.684915: step: 2036/530, loss: 0.11787634342908859
2023-01-21 08:46:46.827630: step: 2040/530, loss: 0.06837411224842072
2023-01-21 08:46:48.024238: step: 2044/530, loss: 6.53923225402832
2023-01-21 08:46:49.230238: step: 2048/530, loss: 1.3320908546447754
2023-01-21 08:46:50.424432: step: 2052/530, loss: 0.6101067662239075
2023-01-21 08:46:51.647163: step: 2056/530, loss: 0.5345121622085571
2023-01-21 08:46:52.826237: step: 2060/530, loss: 0.4946252703666687
2023-01-21 08:46:54.028661: step: 2064/530, loss: 1.1673516035079956
2023-01-21 08:46:55.180290: step: 2068/530, loss: 0.061652086675167084
2023-01-21 08:46:56.343372: step: 2072/530, loss: 0.2297719419002533
2023-01-21 08:46:57.544949: step: 2076/530, loss: 0.3679349422454834
2023-01-21 08:46:58.705194: step: 2080/530, loss: 0.08142280578613281
2023-01-21 08:46:59.888051: step: 2084/530, loss: 0.3446428179740906
2023-01-21 08:47:01.120170: step: 2088/530, loss: 0.05562758818268776
2023-01-21 08:47:02.325444: step: 2092/530, loss: 0.5826784372329712
2023-01-21 08:47:03.534347: step: 2096/530, loss: 0.14145630598068237
2023-01-21 08:47:04.759946: step: 2100/530, loss: 0.12854719161987305
2023-01-21 08:47:05.992189: step: 2104/530, loss: 1.0348286628723145
2023-01-21 08:47:07.190746: step: 2108/530, loss: 0.41253501176834106
2023-01-21 08:47:08.391989: step: 2112/530, loss: 0.3843706250190735
2023-01-21 08:47:09.565265: step: 2116/530, loss: 6.564247131347656
2023-01-21 08:47:10.757329: step: 2120/530, loss: 0.13367091119289398
==================================================
Loss: 0.796
--------------------
Dev: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5263157894736842, 'r': 0.7407407407407407, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.5555555555555556, 'r': 0.3968253968253968, 'f1': 0.46296296296296297}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5263157894736842, 'r': 0.7407407407407407, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.5555555555555556, 'r': 0.3968253968253968, 'f1': 0.46296296296296297}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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 08:48:10.177719: step: 4/530, loss: 0.8131009936332703
2023-01-21 08:48:11.337586: step: 8/530, loss: 0.2753911018371582
2023-01-21 08:48:12.535452: step: 12/530, loss: 0.1350574493408203
2023-01-21 08:48:13.741851: step: 16/530, loss: 0.7728590965270996
2023-01-21 08:48:14.924020: step: 20/530, loss: 0.14564308524131775
2023-01-21 08:48:16.078001: step: 24/530, loss: 0.5636929273605347
2023-01-21 08:48:17.258158: step: 28/530, loss: 0.7194770574569702
2023-01-21 08:48:18.421980: step: 32/530, loss: 0.6098282337188721
2023-01-21 08:48:19.603218: step: 36/530, loss: 0.5917724967002869
2023-01-21 08:48:20.804500: step: 40/530, loss: 0.18003712594509125
2023-01-21 08:48:21.998609: step: 44/530, loss: 1.6628830432891846
2023-01-21 08:48:23.172627: step: 48/530, loss: 0.17299708724021912
2023-01-21 08:48:24.314715: step: 52/530, loss: 0.06985471397638321
2023-01-21 08:48:25.463107: step: 56/530, loss: 0.5200003385543823
2023-01-21 08:48:26.635163: step: 60/530, loss: 0.2953694760799408
2023-01-21 08:48:27.902283: step: 64/530, loss: 1.024534821510315
2023-01-21 08:48:29.065350: step: 68/530, loss: 0.17959380149841309
2023-01-21 08:48:30.265029: step: 72/530, loss: 0.27204903960227966
2023-01-21 08:48:31.437183: step: 76/530, loss: 0.5689713954925537
2023-01-21 08:48:32.606978: step: 80/530, loss: 0.2503332197666168
2023-01-21 08:48:33.792394: step: 84/530, loss: 1.1759052276611328
2023-01-21 08:48:34.943343: step: 88/530, loss: 0.2369137704372406
2023-01-21 08:48:36.133353: step: 92/530, loss: 0.20265722274780273
2023-01-21 08:48:37.312948: step: 96/530, loss: 1.1507142782211304
2023-01-21 08:48:38.473956: step: 100/530, loss: 0.5338325500488281
2023-01-21 08:48:39.679184: step: 104/530, loss: 0.41796875
2023-01-21 08:48:40.915236: step: 108/530, loss: 0.2484571635723114
2023-01-21 08:48:42.139667: step: 112/530, loss: 6.588026523590088
2023-01-21 08:48:43.290527: step: 116/530, loss: 0.3105196952819824
2023-01-21 08:48:44.470962: step: 120/530, loss: 1.5536683797836304
2023-01-21 08:48:45.657359: step: 124/530, loss: 0.7035400867462158
2023-01-21 08:48:46.842801: step: 128/530, loss: 0.8814365267753601
2023-01-21 08:48:48.030234: step: 132/530, loss: 0.01931467093527317
2023-01-21 08:48:49.207046: step: 136/530, loss: 0.1277008056640625
2023-01-21 08:48:50.388230: step: 140/530, loss: 0.9832637310028076
2023-01-21 08:48:51.597638: step: 144/530, loss: 0.1299816220998764
2023-01-21 08:48:52.763525: step: 148/530, loss: 0.4132902920246124
2023-01-21 08:48:53.944356: step: 152/530, loss: 0.916653037071228
2023-01-21 08:48:55.108437: step: 156/530, loss: 0.1310131996870041
2023-01-21 08:48:56.282660: step: 160/530, loss: 0.29777127504348755
2023-01-21 08:48:57.536732: step: 164/530, loss: 1.2421156167984009
2023-01-21 08:48:58.684442: step: 168/530, loss: 0.7385039329528809
2023-01-21 08:48:59.856965: step: 172/530, loss: 0.22313295304775238
2023-01-21 08:49:01.050730: step: 176/530, loss: 0.9820431470870972
2023-01-21 08:49:02.231219: step: 180/530, loss: 1.0439101457595825
2023-01-21 08:49:03.396903: step: 184/530, loss: 0.21177302300930023
2023-01-21 08:49:04.560461: step: 188/530, loss: 0.3938840627670288
2023-01-21 08:49:05.763287: step: 192/530, loss: 0.3223575949668884
2023-01-21 08:49:06.936058: step: 196/530, loss: 0.2527282238006592
2023-01-21 08:49:08.095469: step: 200/530, loss: 2.1202712059020996
2023-01-21 08:49:09.270556: step: 204/530, loss: 0.23718786239624023
2023-01-21 08:49:10.438566: step: 208/530, loss: 0.32902735471725464
2023-01-21 08:49:11.618879: step: 212/530, loss: 0.2543381452560425
2023-01-21 08:49:12.772617: step: 216/530, loss: 0.8075509667396545
2023-01-21 08:49:13.963552: step: 220/530, loss: 0.32854345440864563
2023-01-21 08:49:15.158998: step: 224/530, loss: 0.0640825554728508
2023-01-21 08:49:16.313966: step: 228/530, loss: 0.16528578102588654
2023-01-21 08:49:17.460643: step: 232/530, loss: 0.12071094661951065
2023-01-21 08:49:18.668767: step: 236/530, loss: 0.7248602509498596
2023-01-21 08:49:19.901815: step: 240/530, loss: 0.3958938717842102
2023-01-21 08:49:21.079697: step: 244/530, loss: 0.2956007122993469
2023-01-21 08:49:22.227564: step: 248/530, loss: 0.0948890745639801
2023-01-21 08:49:23.371362: step: 252/530, loss: 0.30303990840911865
2023-01-21 08:49:24.583771: step: 256/530, loss: 0.276243656873703
2023-01-21 08:49:25.758374: step: 260/530, loss: 0.2590638995170593
2023-01-21 08:49:26.947995: step: 264/530, loss: 0.2553989291191101
2023-01-21 08:49:28.147213: step: 268/530, loss: 0.5618802905082703
2023-01-21 08:49:29.322096: step: 272/530, loss: 0.11624794453382492
2023-01-21 08:49:30.507288: step: 276/530, loss: 0.7249786853790283
2023-01-21 08:49:31.709780: step: 280/530, loss: 0.8657317161560059
2023-01-21 08:49:32.862301: step: 284/530, loss: 0.1536935418844223
2023-01-21 08:49:34.022315: step: 288/530, loss: 0.1114933043718338
2023-01-21 08:49:35.238935: step: 292/530, loss: 0.5105417966842651
2023-01-21 08:49:36.447469: step: 296/530, loss: 0.8160227537155151
2023-01-21 08:49:37.603717: step: 300/530, loss: 0.1807362139225006
2023-01-21 08:49:38.791994: step: 304/530, loss: 0.120049387216568
2023-01-21 08:49:40.005963: step: 308/530, loss: 0.4047604501247406
2023-01-21 08:49:41.169348: step: 312/530, loss: 0.3224331736564636
2023-01-21 08:49:42.325531: step: 316/530, loss: 0.16246314346790314
2023-01-21 08:49:43.479430: step: 320/530, loss: 0.3033720850944519
2023-01-21 08:49:44.644355: step: 324/530, loss: 0.3792285919189453
2023-01-21 08:49:45.853063: step: 328/530, loss: 0.15760020911693573
2023-01-21 08:49:47.024838: step: 332/530, loss: 0.2603931427001953
2023-01-21 08:49:48.205820: step: 336/530, loss: 0.7599878907203674
2023-01-21 08:49:49.375522: step: 340/530, loss: 0.07117342948913574
2023-01-21 08:49:50.536367: step: 344/530, loss: 0.13313297927379608
2023-01-21 08:49:51.767220: step: 348/530, loss: 0.7614139914512634
2023-01-21 08:49:52.958735: step: 352/530, loss: 0.4813288748264313
2023-01-21 08:49:54.134031: step: 356/530, loss: 0.07317791134119034
2023-01-21 08:49:55.272998: step: 360/530, loss: 0.8157491087913513
2023-01-21 08:49:56.496272: step: 364/530, loss: 0.14983519911766052
2023-01-21 08:49:57.650311: step: 368/530, loss: 0.12586575746536255
2023-01-21 08:49:58.819283: step: 372/530, loss: 0.3335806727409363
2023-01-21 08:49:59.971784: step: 376/530, loss: 0.1913493275642395
2023-01-21 08:50:01.166726: step: 380/530, loss: 1.2610762119293213
2023-01-21 08:50:02.341647: step: 384/530, loss: 0.23879270255565643
2023-01-21 08:50:03.528151: step: 388/530, loss: 0.32907745242118835
2023-01-21 08:50:04.761586: step: 392/530, loss: 0.4629434645175934
2023-01-21 08:50:05.927627: step: 396/530, loss: 0.11997786164283752
2023-01-21 08:50:07.115652: step: 400/530, loss: 6.266993522644043
2023-01-21 08:50:08.273763: step: 404/530, loss: 0.9506653547286987
2023-01-21 08:50:09.472197: step: 408/530, loss: 0.45406827330589294
2023-01-21 08:50:10.678947: step: 412/530, loss: 0.3469398021697998
2023-01-21 08:50:11.875982: step: 416/530, loss: 0.6269220113754272
2023-01-21 08:50:13.080984: step: 420/530, loss: 0.6761634945869446
2023-01-21 08:50:14.244108: step: 424/530, loss: 0.4549899101257324
2023-01-21 08:50:15.446348: step: 428/530, loss: 0.2658103108406067
2023-01-21 08:50:16.628264: step: 432/530, loss: 0.1528553068637848
2023-01-21 08:50:17.813174: step: 436/530, loss: 0.539262592792511
2023-01-21 08:50:19.013688: step: 440/530, loss: 0.31333863735198975
2023-01-21 08:50:20.205359: step: 444/530, loss: 0.11689119040966034
2023-01-21 08:50:21.417932: step: 448/530, loss: 1.137494683265686
2023-01-21 08:50:22.624272: step: 452/530, loss: 0.1895713359117508
2023-01-21 08:50:23.770043: step: 456/530, loss: 0.14369288086891174
2023-01-21 08:50:24.904618: step: 460/530, loss: 0.8174580931663513
2023-01-21 08:50:26.103638: step: 464/530, loss: 0.12201175838708878
2023-01-21 08:50:27.289484: step: 468/530, loss: 0.6958547830581665
2023-01-21 08:50:28.422747: step: 472/530, loss: 1.3475228548049927
2023-01-21 08:50:29.593482: step: 476/530, loss: 0.2060166746377945
2023-01-21 08:50:30.757383: step: 480/530, loss: 1.407651424407959
2023-01-21 08:50:31.947029: step: 484/530, loss: 0.27689677476882935
2023-01-21 08:50:33.103861: step: 488/530, loss: 0.18881730735301971
2023-01-21 08:50:34.243686: step: 492/530, loss: 0.1488383263349533
2023-01-21 08:50:35.493456: step: 496/530, loss: 0.21495437622070312
2023-01-21 08:50:36.654577: step: 500/530, loss: 0.30411404371261597
2023-01-21 08:50:37.821601: step: 504/530, loss: 0.7492003440856934
2023-01-21 08:50:39.011581: step: 508/530, loss: 0.35484811663627625
2023-01-21 08:50:40.240213: step: 512/530, loss: 0.20064754784107208
2023-01-21 08:50:41.421766: step: 516/530, loss: 0.2230207920074463
2023-01-21 08:50:42.613356: step: 520/530, loss: 0.6519554257392883
2023-01-21 08:50:43.781203: step: 524/530, loss: 0.28657275438308716
2023-01-21 08:50:44.996896: step: 528/530, loss: 0.06410565972328186
2023-01-21 08:50:46.183528: step: 532/530, loss: 0.6508861780166626
2023-01-21 08:50:47.368715: step: 536/530, loss: 0.1381603181362152
2023-01-21 08:50:48.559123: step: 540/530, loss: 0.6873812079429626
2023-01-21 08:50:49.709585: step: 544/530, loss: 0.06801362335681915
2023-01-21 08:50:50.866173: step: 548/530, loss: 0.1821175217628479
2023-01-21 08:50:52.068407: step: 552/530, loss: 0.04282717779278755
2023-01-21 08:50:53.206252: step: 556/530, loss: 0.31935185194015503
2023-01-21 08:50:54.365198: step: 560/530, loss: 0.043768785893917084
2023-01-21 08:50:55.530061: step: 564/530, loss: 0.2452186644077301
2023-01-21 08:50:56.752273: step: 568/530, loss: 0.8599094152450562
2023-01-21 08:50:57.913586: step: 572/530, loss: 1.3989853858947754
2023-01-21 08:50:59.101482: step: 576/530, loss: 0.05030636861920357
2023-01-21 08:51:00.277370: step: 580/530, loss: 0.09564314037561417
2023-01-21 08:51:01.464542: step: 584/530, loss: 0.8789792060852051
2023-01-21 08:51:02.625176: step: 588/530, loss: 0.07741013169288635
2023-01-21 08:51:03.773750: step: 592/530, loss: 0.14804983139038086
2023-01-21 08:51:04.954465: step: 596/530, loss: 0.33742353320121765
2023-01-21 08:51:06.138490: step: 600/530, loss: 0.5756341218948364
2023-01-21 08:51:07.261382: step: 604/530, loss: 0.614681601524353
2023-01-21 08:51:08.452017: step: 608/530, loss: 0.40944191813468933
2023-01-21 08:51:09.627914: step: 612/530, loss: 1.3625683784484863
2023-01-21 08:51:10.833536: step: 616/530, loss: 0.9454197883605957
2023-01-21 08:51:11.985811: step: 620/530, loss: 0.2700842022895813
2023-01-21 08:51:13.180411: step: 624/530, loss: 0.23967324197292328
2023-01-21 08:51:14.360973: step: 628/530, loss: 0.8394330143928528
2023-01-21 08:51:15.529454: step: 632/530, loss: 0.043608665466308594
2023-01-21 08:51:16.690119: step: 636/530, loss: 0.5413864850997925
2023-01-21 08:51:17.849916: step: 640/530, loss: 0.48300600051879883
2023-01-21 08:51:19.020772: step: 644/530, loss: 0.3193744719028473
2023-01-21 08:51:20.160433: step: 648/530, loss: 0.25874224305152893
2023-01-21 08:51:21.318371: step: 652/530, loss: 0.13567595183849335
2023-01-21 08:51:22.495528: step: 656/530, loss: 0.05915489047765732
2023-01-21 08:51:23.615898: step: 660/530, loss: 0.04206056520342827
2023-01-21 08:51:24.816014: step: 664/530, loss: 2.687025308609009
2023-01-21 08:51:26.007821: step: 668/530, loss: 0.09054012596607208
2023-01-21 08:51:27.198646: step: 672/530, loss: 0.14900818467140198
2023-01-21 08:51:28.398628: step: 676/530, loss: 1.380944013595581
2023-01-21 08:51:29.569735: step: 680/530, loss: 1.0504292249679565
2023-01-21 08:51:30.795286: step: 684/530, loss: 0.3370684087276459
2023-01-21 08:51:32.021284: step: 688/530, loss: 0.7799224853515625
2023-01-21 08:51:33.173252: step: 692/530, loss: 1.2012555599212646
2023-01-21 08:51:34.374064: step: 696/530, loss: 0.28496646881103516
2023-01-21 08:51:35.577641: step: 700/530, loss: 0.07615514099597931
2023-01-21 08:51:36.745523: step: 704/530, loss: 0.23797884583473206
2023-01-21 08:51:37.912804: step: 708/530, loss: 0.2721117436885834
2023-01-21 08:51:39.109128: step: 712/530, loss: 0.8619662523269653
2023-01-21 08:51:40.279142: step: 716/530, loss: 0.7956581115722656
2023-01-21 08:51:41.448027: step: 720/530, loss: 2.710904598236084
2023-01-21 08:51:42.622680: step: 724/530, loss: 0.1275218427181244
2023-01-21 08:51:43.804288: step: 728/530, loss: 0.7589025497436523
2023-01-21 08:51:44.988119: step: 732/530, loss: 0.15051718056201935
2023-01-21 08:51:46.143235: step: 736/530, loss: 0.2746492922306061
2023-01-21 08:51:47.351968: step: 740/530, loss: 0.7011812925338745
2023-01-21 08:51:48.557229: step: 744/530, loss: 0.6710712313652039
2023-01-21 08:51:49.692536: step: 748/530, loss: 0.06359276920557022
2023-01-21 08:51:50.870587: step: 752/530, loss: 0.3000645041465759
2023-01-21 08:51:52.052125: step: 756/530, loss: 0.37415334582328796
2023-01-21 08:51:53.255351: step: 760/530, loss: 0.17929087579250336
2023-01-21 08:51:54.445289: step: 764/530, loss: 0.8596959710121155
2023-01-21 08:51:55.604341: step: 768/530, loss: 0.37162408232688904
2023-01-21 08:51:56.764549: step: 772/530, loss: 0.1953103095293045
2023-01-21 08:51:57.964541: step: 776/530, loss: 0.2356177419424057
2023-01-21 08:51:59.139926: step: 780/530, loss: 0.08539637923240662
2023-01-21 08:52:00.386990: step: 784/530, loss: 0.5177396535873413
2023-01-21 08:52:01.556810: step: 788/530, loss: 0.21384677290916443
2023-01-21 08:52:02.732792: step: 792/530, loss: 0.5052059888839722
2023-01-21 08:52:03.872577: step: 796/530, loss: 0.28495168685913086
2023-01-21 08:52:05.001961: step: 800/530, loss: 1.3187782764434814
2023-01-21 08:52:06.143551: step: 804/530, loss: 0.14456062018871307
2023-01-21 08:52:07.306342: step: 808/530, loss: 0.8939498662948608
2023-01-21 08:52:08.466621: step: 812/530, loss: 0.5543131828308105
2023-01-21 08:52:09.665403: step: 816/530, loss: 0.45672476291656494
2023-01-21 08:52:10.856260: step: 820/530, loss: 0.17112235724925995
2023-01-21 08:52:12.130135: step: 824/530, loss: 0.13266411423683167
2023-01-21 08:52:13.270817: step: 828/530, loss: 0.058018967509269714
2023-01-21 08:52:14.471679: step: 832/530, loss: 7.35406494140625
2023-01-21 08:52:15.681525: step: 836/530, loss: 1.0081827640533447
2023-01-21 08:52:16.854694: step: 840/530, loss: 1.3607404232025146
2023-01-21 08:52:18.080123: step: 844/530, loss: 2.0624141693115234
2023-01-21 08:52:19.275837: step: 848/530, loss: 0.40151041746139526
2023-01-21 08:52:20.452717: step: 852/530, loss: 0.14539632201194763
2023-01-21 08:52:21.578435: step: 856/530, loss: 0.12623482942581177
2023-01-21 08:52:22.790001: step: 860/530, loss: 0.37502819299697876
2023-01-21 08:52:23.993063: step: 864/530, loss: 0.3493295907974243
2023-01-21 08:52:25.167670: step: 868/530, loss: 0.17808513343334198
2023-01-21 08:52:26.351765: step: 872/530, loss: 1.501434564590454
2023-01-21 08:52:27.561590: step: 876/530, loss: 0.7126620411872864
2023-01-21 08:52:28.764247: step: 880/530, loss: 0.9364823698997498
2023-01-21 08:52:29.970372: step: 884/530, loss: 0.26331090927124023
2023-01-21 08:52:31.142770: step: 888/530, loss: 0.671194851398468
2023-01-21 08:52:32.356033: step: 892/530, loss: 0.6448396444320679
2023-01-21 08:52:33.575901: step: 896/530, loss: 0.09248952567577362
2023-01-21 08:52:34.730438: step: 900/530, loss: 0.27679795026779175
2023-01-21 08:52:35.909173: step: 904/530, loss: 0.14033597707748413
2023-01-21 08:52:37.075601: step: 908/530, loss: 0.11329788714647293
2023-01-21 08:52:38.261680: step: 912/530, loss: 0.25210103392601013
2023-01-21 08:52:39.437829: step: 916/530, loss: 0.20909824967384338
2023-01-21 08:52:40.577401: step: 920/530, loss: 0.5642339587211609
2023-01-21 08:52:41.746066: step: 924/530, loss: 0.11197614669799805
2023-01-21 08:52:42.920233: step: 928/530, loss: 0.08525638282299042
2023-01-21 08:52:44.060419: step: 932/530, loss: 0.2746533453464508
2023-01-21 08:52:45.189646: step: 936/530, loss: 0.19244170188903809
2023-01-21 08:52:46.374685: step: 940/530, loss: 0.6105697751045227
2023-01-21 08:52:47.547507: step: 944/530, loss: 0.93476802110672
2023-01-21 08:52:48.743139: step: 948/530, loss: 0.1826503872871399
2023-01-21 08:52:49.900294: step: 952/530, loss: 0.29204684495925903
2023-01-21 08:52:51.060417: step: 956/530, loss: 0.4442242681980133
2023-01-21 08:52:52.257352: step: 960/530, loss: 6.2586493492126465
2023-01-21 08:52:53.455490: step: 964/530, loss: 0.9305421113967896
2023-01-21 08:52:54.621193: step: 968/530, loss: 0.5687618255615234
2023-01-21 08:52:55.890460: step: 972/530, loss: 7.020023345947266
2023-01-21 08:52:57.095409: step: 976/530, loss: 0.19057334959506989
2023-01-21 08:52:58.302111: step: 980/530, loss: 0.19445228576660156
2023-01-21 08:52:59.471083: step: 984/530, loss: 0.13064676523208618
2023-01-21 08:53:00.674286: step: 988/530, loss: 0.14483466744422913
2023-01-21 08:53:01.841690: step: 992/530, loss: 0.9262669086456299
2023-01-21 08:53:03.026957: step: 996/530, loss: 1.4446378946304321
2023-01-21 08:53:04.214952: step: 1000/530, loss: 0.43529972434043884
2023-01-21 08:53:05.371563: step: 1004/530, loss: 0.33877742290496826
2023-01-21 08:53:06.569445: step: 1008/530, loss: 0.243761345744133
2023-01-21 08:53:07.774755: step: 1012/530, loss: 1.2754149436950684
2023-01-21 08:53:08.955015: step: 1016/530, loss: 0.37762346863746643
2023-01-21 08:53:10.140474: step: 1020/530, loss: 0.12277646362781525
2023-01-21 08:53:11.379113: step: 1024/530, loss: 1.063736081123352
2023-01-21 08:53:12.584654: step: 1028/530, loss: 0.1324271708726883
2023-01-21 08:53:13.728011: step: 1032/530, loss: 6.387197494506836
2023-01-21 08:53:14.890177: step: 1036/530, loss: 0.06472501903772354
2023-01-21 08:53:16.034525: step: 1040/530, loss: 0.49678337574005127
2023-01-21 08:53:17.245919: step: 1044/530, loss: 0.2159431427717209
2023-01-21 08:53:18.438214: step: 1048/530, loss: 0.16186627745628357
2023-01-21 08:53:19.655116: step: 1052/530, loss: 0.07779045403003693
2023-01-21 08:53:20.815040: step: 1056/530, loss: 0.19702863693237305
2023-01-21 08:53:22.016763: step: 1060/530, loss: 0.9591590166091919
2023-01-21 08:53:23.149004: step: 1064/530, loss: 1.2540150880813599
2023-01-21 08:53:24.342967: step: 1068/530, loss: 0.14994199573993683
2023-01-21 08:53:25.544993: step: 1072/530, loss: 1.0914855003356934
2023-01-21 08:53:26.753842: step: 1076/530, loss: 0.6991499066352844
2023-01-21 08:53:27.957163: step: 1080/530, loss: 0.2397291362285614
2023-01-21 08:53:29.137931: step: 1084/530, loss: 0.09866509586572647
2023-01-21 08:53:30.284805: step: 1088/530, loss: 0.16415591537952423
2023-01-21 08:53:31.556045: step: 1092/530, loss: 0.44816991686820984
2023-01-21 08:53:32.747752: step: 1096/530, loss: 0.10744304955005646
2023-01-21 08:53:33.929956: step: 1100/530, loss: 0.33452340960502625
2023-01-21 08:53:35.101208: step: 1104/530, loss: 0.11847123503684998
2023-01-21 08:53:36.261559: step: 1108/530, loss: 0.5884709358215332
2023-01-21 08:53:37.433137: step: 1112/530, loss: 0.0523066520690918
2023-01-21 08:53:38.589338: step: 1116/530, loss: 0.10171909630298615
2023-01-21 08:53:39.794296: step: 1120/530, loss: 0.32674846053123474
2023-01-21 08:53:40.951798: step: 1124/530, loss: 0.2390117198228836
2023-01-21 08:53:42.171349: step: 1128/530, loss: 0.15587815642356873
2023-01-21 08:53:43.367697: step: 1132/530, loss: 1.5504474639892578
2023-01-21 08:53:44.555390: step: 1136/530, loss: 0.37956732511520386
2023-01-21 08:53:45.741718: step: 1140/530, loss: 0.34873953461647034
2023-01-21 08:53:46.934038: step: 1144/530, loss: 1.1070220470428467
2023-01-21 08:53:48.109955: step: 1148/530, loss: 1.104679822921753
2023-01-21 08:53:49.283930: step: 1152/530, loss: 0.29709187150001526
2023-01-21 08:53:50.492066: step: 1156/530, loss: 0.2701776623725891
2023-01-21 08:53:51.643560: step: 1160/530, loss: 0.10834258049726486
2023-01-21 08:53:52.793112: step: 1164/530, loss: 0.6779764294624329
2023-01-21 08:53:53.973129: step: 1168/530, loss: 0.9808801412582397
2023-01-21 08:53:55.163434: step: 1172/530, loss: 0.8983593583106995
2023-01-21 08:53:56.315313: step: 1176/530, loss: 0.3313419222831726
2023-01-21 08:53:57.507100: step: 1180/530, loss: 0.04407496377825737
2023-01-21 08:53:58.725354: step: 1184/530, loss: 0.14605122804641724
2023-01-21 08:53:59.887141: step: 1188/530, loss: 0.4207576513290405
2023-01-21 08:54:01.113400: step: 1192/530, loss: 0.20644119381904602
2023-01-21 08:54:02.296766: step: 1196/530, loss: 0.2758932113647461
2023-01-21 08:54:03.484931: step: 1200/530, loss: 0.1772373616695404
2023-01-21 08:54:04.621712: step: 1204/530, loss: 0.7057322859764099
2023-01-21 08:54:05.770809: step: 1208/530, loss: 0.07535575330257416
2023-01-21 08:54:06.954272: step: 1212/530, loss: 1.1347315311431885
2023-01-21 08:54:08.093892: step: 1216/530, loss: 1.030280590057373
2023-01-21 08:54:09.249959: step: 1220/530, loss: 0.2256973385810852
2023-01-21 08:54:10.432117: step: 1224/530, loss: 0.06349001079797745
2023-01-21 08:54:11.634444: step: 1228/530, loss: 0.3368093967437744
2023-01-21 08:54:12.795442: step: 1232/530, loss: 0.18343791365623474
2023-01-21 08:54:13.985777: step: 1236/530, loss: 0.7997405529022217
2023-01-21 08:54:15.149347: step: 1240/530, loss: 0.3172716200351715
2023-01-21 08:54:16.366078: step: 1244/530, loss: 0.1435273289680481
2023-01-21 08:54:17.576082: step: 1248/530, loss: 0.11778044700622559
2023-01-21 08:54:18.737192: step: 1252/530, loss: 0.23651990294456482
2023-01-21 08:54:19.913707: step: 1256/530, loss: 0.3496863543987274
2023-01-21 08:54:21.127846: step: 1260/530, loss: 0.06034908443689346
2023-01-21 08:54:22.326063: step: 1264/530, loss: 0.16582655906677246
2023-01-21 08:54:23.492211: step: 1268/530, loss: 0.051279641687870026
2023-01-21 08:54:24.675977: step: 1272/530, loss: 0.2128925919532776
2023-01-21 08:54:25.847309: step: 1276/530, loss: 0.1337498128414154
2023-01-21 08:54:27.037413: step: 1280/530, loss: 1.309667706489563
2023-01-21 08:54:28.198451: step: 1284/530, loss: 0.18239250779151917
2023-01-21 08:54:29.374579: step: 1288/530, loss: 0.9458780884742737
2023-01-21 08:54:30.556702: step: 1292/530, loss: 0.8033409714698792
2023-01-21 08:54:31.733430: step: 1296/530, loss: 1.0918159484863281
2023-01-21 08:54:32.934050: step: 1300/530, loss: 0.0733439028263092
2023-01-21 08:54:34.132614: step: 1304/530, loss: 0.48767149448394775
2023-01-21 08:54:35.322420: step: 1308/530, loss: 1.304060697555542
2023-01-21 08:54:36.499228: step: 1312/530, loss: 0.10146933048963547
2023-01-21 08:54:37.691842: step: 1316/530, loss: 0.07565192878246307
2023-01-21 08:54:38.827611: step: 1320/530, loss: 0.0383114367723465
2023-01-21 08:54:40.034717: step: 1324/530, loss: 0.8748599290847778
2023-01-21 08:54:41.222459: step: 1328/530, loss: 0.04026372358202934
2023-01-21 08:54:42.394526: step: 1332/530, loss: 0.3682217597961426
2023-01-21 08:54:43.557660: step: 1336/530, loss: 0.7549734711647034
2023-01-21 08:54:44.742380: step: 1340/530, loss: 0.7470425963401794
2023-01-21 08:54:45.899509: step: 1344/530, loss: 0.10938072949647903
2023-01-21 08:54:47.036666: step: 1348/530, loss: 0.22176331281661987
2023-01-21 08:54:48.189436: step: 1352/530, loss: 0.4832870364189148
2023-01-21 08:54:49.368600: step: 1356/530, loss: 0.09096997231245041
2023-01-21 08:54:50.549746: step: 1360/530, loss: 0.9750538468360901
2023-01-21 08:54:51.768193: step: 1364/530, loss: 0.21050973236560822
2023-01-21 08:54:52.942877: step: 1368/530, loss: 0.47874486446380615
2023-01-21 08:54:54.063337: step: 1372/530, loss: 0.11202053725719452
2023-01-21 08:54:55.242044: step: 1376/530, loss: 0.22147612273693085
2023-01-21 08:54:56.408973: step: 1380/530, loss: 0.32758206129074097
2023-01-21 08:54:57.592104: step: 1384/530, loss: 0.2593611776828766
2023-01-21 08:54:58.770447: step: 1388/530, loss: 0.499620646238327
2023-01-21 08:54:59.936204: step: 1392/530, loss: 0.41625577211380005
2023-01-21 08:55:01.118038: step: 1396/530, loss: 0.515575647354126
2023-01-21 08:55:02.274389: step: 1400/530, loss: 0.22347040474414825
2023-01-21 08:55:03.468275: step: 1404/530, loss: 0.4543072581291199
2023-01-21 08:55:04.683154: step: 1408/530, loss: 0.06269922852516174
2023-01-21 08:55:05.845630: step: 1412/530, loss: 0.8202094435691833
2023-01-21 08:55:07.018490: step: 1416/530, loss: 0.9506857991218567
2023-01-21 08:55:08.177942: step: 1420/530, loss: 0.1156138926744461
2023-01-21 08:55:09.335496: step: 1424/530, loss: 0.4783044457435608
2023-01-21 08:55:10.479717: step: 1428/530, loss: 0.16861963272094727
2023-01-21 08:55:11.645070: step: 1432/530, loss: 0.7537639141082764
2023-01-21 08:55:12.909526: step: 1436/530, loss: 0.17903974652290344
2023-01-21 08:55:14.101731: step: 1440/530, loss: 0.23431915044784546
2023-01-21 08:55:15.251588: step: 1444/530, loss: 0.13312754034996033
2023-01-21 08:55:16.419365: step: 1448/530, loss: 0.21181516349315643
2023-01-21 08:55:17.597589: step: 1452/530, loss: 0.07324037700891495
2023-01-21 08:55:18.772624: step: 1456/530, loss: 0.1949656456708908
2023-01-21 08:55:19.986835: step: 1460/530, loss: 0.37547311186790466
2023-01-21 08:55:21.151639: step: 1464/530, loss: 0.436201274394989
2023-01-21 08:55:22.311645: step: 1468/530, loss: 1.0353859663009644
2023-01-21 08:55:23.507646: step: 1472/530, loss: 0.25967320799827576
2023-01-21 08:55:24.669811: step: 1476/530, loss: 0.4616713523864746
2023-01-21 08:55:25.861831: step: 1480/530, loss: 0.9396399855613708
2023-01-21 08:55:27.007059: step: 1484/530, loss: 0.3414120674133301
2023-01-21 08:55:28.216130: step: 1488/530, loss: 0.7303752899169922
2023-01-21 08:55:29.380530: step: 1492/530, loss: 0.07259435951709747
2023-01-21 08:55:30.554355: step: 1496/530, loss: 0.6834162473678589
2023-01-21 08:55:31.747161: step: 1500/530, loss: 3.8585567474365234
2023-01-21 08:55:32.978836: step: 1504/530, loss: 0.41714781522750854
2023-01-21 08:55:34.173262: step: 1508/530, loss: 0.0361720435321331
2023-01-21 08:55:35.356866: step: 1512/530, loss: 0.1392539143562317
2023-01-21 08:55:36.565789: step: 1516/530, loss: 0.7899408340454102
2023-01-21 08:55:37.734815: step: 1520/530, loss: 0.2657398283481598
2023-01-21 08:55:38.931269: step: 1524/530, loss: 0.3879263997077942
2023-01-21 08:55:40.101886: step: 1528/530, loss: 0.26767969131469727
2023-01-21 08:55:41.263468: step: 1532/530, loss: 0.16750946640968323
2023-01-21 08:55:42.449861: step: 1536/530, loss: 0.09916935116052628
2023-01-21 08:55:43.614335: step: 1540/530, loss: 6.130626678466797
2023-01-21 08:55:44.822158: step: 1544/530, loss: 0.552817165851593
2023-01-21 08:55:46.004320: step: 1548/530, loss: 1.6418845653533936
2023-01-21 08:55:47.166683: step: 1552/530, loss: 0.7388523817062378
2023-01-21 08:55:48.327593: step: 1556/530, loss: 0.3149663805961609
2023-01-21 08:55:49.514811: step: 1560/530, loss: 0.5894988775253296
2023-01-21 08:55:50.690386: step: 1564/530, loss: 0.2805604934692383
2023-01-21 08:55:51.881042: step: 1568/530, loss: 0.19328290224075317
2023-01-21 08:55:53.022160: step: 1572/530, loss: 0.5188925862312317
2023-01-21 08:55:54.179271: step: 1576/530, loss: 0.6756436228752136
2023-01-21 08:55:55.392228: step: 1580/530, loss: 0.7145251631736755
2023-01-21 08:55:56.608366: step: 1584/530, loss: 0.777800440788269
2023-01-21 08:55:57.787590: step: 1588/530, loss: 0.3991817533969879
2023-01-21 08:55:58.952832: step: 1592/530, loss: 0.17097407579421997
2023-01-21 08:56:00.131664: step: 1596/530, loss: 0.05069741979241371
2023-01-21 08:56:01.333804: step: 1600/530, loss: 0.32514554262161255
2023-01-21 08:56:02.530148: step: 1604/530, loss: 0.8154205679893494
2023-01-21 08:56:03.750133: step: 1608/530, loss: 0.8199716806411743
2023-01-21 08:56:04.926232: step: 1612/530, loss: 0.13968773186206818
2023-01-21 08:56:06.158390: step: 1616/530, loss: 0.9974249601364136
2023-01-21 08:56:07.361539: step: 1620/530, loss: 0.19445961713790894
2023-01-21 08:56:08.505223: step: 1624/530, loss: 0.11992254108190536
2023-01-21 08:56:09.703605: step: 1628/530, loss: 0.17650556564331055
2023-01-21 08:56:10.880732: step: 1632/530, loss: 0.32293254137039185
2023-01-21 08:56:12.081021: step: 1636/530, loss: 0.41194048523902893
2023-01-21 08:56:13.253022: step: 1640/530, loss: 0.22866877913475037
2023-01-21 08:56:14.408710: step: 1644/530, loss: 0.23574122786521912
2023-01-21 08:56:15.584287: step: 1648/530, loss: 7.095818042755127
2023-01-21 08:56:16.766778: step: 1652/530, loss: 0.4307723939418793
2023-01-21 08:56:17.948785: step: 1656/530, loss: 0.2336655557155609
2023-01-21 08:56:19.156988: step: 1660/530, loss: 1.0493323802947998
2023-01-21 08:56:20.299527: step: 1664/530, loss: 0.18368035554885864
2023-01-21 08:56:21.505903: step: 1668/530, loss: 0.6307743191719055
2023-01-21 08:56:22.688808: step: 1672/530, loss: 0.12392202019691467
2023-01-21 08:56:23.899431: step: 1676/530, loss: 0.19623461365699768
2023-01-21 08:56:25.058898: step: 1680/530, loss: 0.1633135825395584
2023-01-21 08:56:26.260138: step: 1684/530, loss: 0.7161133289337158
2023-01-21 08:56:27.458661: step: 1688/530, loss: 0.17464706301689148
2023-01-21 08:56:28.655036: step: 1692/530, loss: 0.5377215147018433
2023-01-21 08:56:29.811684: step: 1696/530, loss: 0.07636852562427521
2023-01-21 08:56:30.986252: step: 1700/530, loss: 0.5019243359565735
2023-01-21 08:56:32.174407: step: 1704/530, loss: 0.48598137497901917
2023-01-21 08:56:33.330848: step: 1708/530, loss: 0.10662110149860382
2023-01-21 08:56:34.552543: step: 1712/530, loss: 0.34850093722343445
2023-01-21 08:56:35.697983: step: 1716/530, loss: 0.15613965690135956
2023-01-21 08:56:36.899022: step: 1720/530, loss: 0.26565903425216675
2023-01-21 08:56:38.110733: step: 1724/530, loss: 1.06226646900177
2023-01-21 08:56:39.299915: step: 1728/530, loss: 0.18133488297462463
2023-01-21 08:56:40.488478: step: 1732/530, loss: 0.1587659865617752
2023-01-21 08:56:41.710508: step: 1736/530, loss: 0.18643851578235626
2023-01-21 08:56:42.937309: step: 1740/530, loss: 0.2335626631975174
2023-01-21 08:56:44.110163: step: 1744/530, loss: 1.085392951965332
2023-01-21 08:56:45.239429: step: 1748/530, loss: 0.17823128402233124
2023-01-21 08:56:46.453442: step: 1752/530, loss: 0.8394138813018799
2023-01-21 08:56:47.642663: step: 1756/530, loss: 0.7023558616638184
2023-01-21 08:56:48.839394: step: 1760/530, loss: 0.21441689133644104
2023-01-21 08:56:50.036589: step: 1764/530, loss: 1.3282926082611084
2023-01-21 08:56:51.257315: step: 1768/530, loss: 1.3719189167022705
2023-01-21 08:56:52.396084: step: 1772/530, loss: 0.1980564147233963
2023-01-21 08:56:53.636753: step: 1776/530, loss: 0.10667157173156738
2023-01-21 08:56:54.846054: step: 1780/530, loss: 0.5589823722839355
2023-01-21 08:56:56.040719: step: 1784/530, loss: 0.19532231986522675
2023-01-21 08:56:57.191790: step: 1788/530, loss: 1.4473024606704712
2023-01-21 08:56:58.359924: step: 1792/530, loss: 6.4610443115234375
2023-01-21 08:56:59.525493: step: 1796/530, loss: 0.1384432315826416
2023-01-21 08:57:00.708554: step: 1800/530, loss: 0.6778097152709961
2023-01-21 08:57:01.888312: step: 1804/530, loss: 0.13512945175170898
2023-01-21 08:57:03.083566: step: 1808/530, loss: 0.25959131121635437
2023-01-21 08:57:04.242356: step: 1812/530, loss: 0.14037713408470154
2023-01-21 08:57:05.440802: step: 1816/530, loss: 0.1534731388092041
2023-01-21 08:57:06.596789: step: 1820/530, loss: 0.7548848986625671
2023-01-21 08:57:07.775711: step: 1824/530, loss: 1.7059985399246216
2023-01-21 08:57:08.983021: step: 1828/530, loss: 0.3666013777256012
2023-01-21 08:57:10.162401: step: 1832/530, loss: 2.224490165710449
2023-01-21 08:57:11.359326: step: 1836/530, loss: 0.06247539445757866
2023-01-21 08:57:12.604778: step: 1840/530, loss: 0.06426487118005753
2023-01-21 08:57:13.787790: step: 1844/530, loss: 0.10009832680225372
2023-01-21 08:57:14.997054: step: 1848/530, loss: 0.29229727387428284
2023-01-21 08:57:16.159040: step: 1852/530, loss: 0.1024850383400917
2023-01-21 08:57:17.318301: step: 1856/530, loss: 0.16965365409851074
2023-01-21 08:57:18.506529: step: 1860/530, loss: 0.3466854989528656
2023-01-21 08:57:19.672014: step: 1864/530, loss: 0.09264745563268661
2023-01-21 08:57:20.901231: step: 1868/530, loss: 0.16719265282154083
2023-01-21 08:57:22.092182: step: 1872/530, loss: 1.2806411981582642
2023-01-21 08:57:23.276536: step: 1876/530, loss: 0.10648641735315323
2023-01-21 08:57:24.454436: step: 1880/530, loss: 0.17291870713233948
2023-01-21 08:57:25.633078: step: 1884/530, loss: 0.20730113983154297
2023-01-21 08:57:26.808587: step: 1888/530, loss: 0.3161739706993103
2023-01-21 08:57:27.970432: step: 1892/530, loss: 0.1714148223400116
2023-01-21 08:57:29.114979: step: 1896/530, loss: 0.16755680739879608
2023-01-21 08:57:30.293563: step: 1900/530, loss: 0.3586142659187317
2023-01-21 08:57:31.434428: step: 1904/530, loss: 0.10557427257299423
2023-01-21 08:57:32.646656: step: 1908/530, loss: 1.698386549949646
2023-01-21 08:57:33.828610: step: 1912/530, loss: 0.43443670868873596
2023-01-21 08:57:35.023723: step: 1916/530, loss: 0.571746826171875
2023-01-21 08:57:36.236744: step: 1920/530, loss: 0.723967969417572
2023-01-21 08:57:37.447382: step: 1924/530, loss: 0.09055925160646439
2023-01-21 08:57:38.645894: step: 1928/530, loss: 0.21665973961353302
2023-01-21 08:57:39.801797: step: 1932/530, loss: 0.12338156998157501
2023-01-21 08:57:40.997466: step: 1936/530, loss: 0.32324540615081787
2023-01-21 08:57:42.224881: step: 1940/530, loss: 1.0081002712249756
2023-01-21 08:57:43.454732: step: 1944/530, loss: 1.304118037223816
2023-01-21 08:57:44.676895: step: 1948/530, loss: 2.1551320552825928
2023-01-21 08:57:45.875730: step: 1952/530, loss: 0.19658727943897247
2023-01-21 08:57:47.064544: step: 1956/530, loss: 1.5743308067321777
2023-01-21 08:57:48.262024: step: 1960/530, loss: 0.22940078377723694
2023-01-21 08:57:49.452185: step: 1964/530, loss: 0.12993459403514862
2023-01-21 08:57:50.664661: step: 1968/530, loss: 0.16153010725975037
2023-01-21 08:57:51.857608: step: 1972/530, loss: 0.7037493586540222
2023-01-21 08:57:53.033318: step: 1976/530, loss: 0.054555606096982956
2023-01-21 08:57:54.211314: step: 1980/530, loss: 0.3966211676597595
2023-01-21 08:57:55.375773: step: 1984/530, loss: 0.33418625593185425
2023-01-21 08:57:56.567485: step: 1988/530, loss: 0.8138771653175354
2023-01-21 08:57:57.755313: step: 1992/530, loss: 0.974611759185791
2023-01-21 08:57:58.924144: step: 1996/530, loss: 0.07023420184850693
2023-01-21 08:58:00.076546: step: 2000/530, loss: 1.3829149007797241
2023-01-21 08:58:01.209544: step: 2004/530, loss: 0.14137983322143555
2023-01-21 08:58:02.400859: step: 2008/530, loss: 0.15284377336502075
2023-01-21 08:58:03.616244: step: 2012/530, loss: 0.07059414684772491
2023-01-21 08:58:04.797099: step: 2016/530, loss: 0.15334263443946838
2023-01-21 08:58:05.960261: step: 2020/530, loss: 0.6841206550598145
2023-01-21 08:58:07.150804: step: 2024/530, loss: 0.3394330143928528
2023-01-21 08:58:08.361334: step: 2028/530, loss: 0.18812847137451172
2023-01-21 08:58:09.529498: step: 2032/530, loss: 0.1167324110865593
2023-01-21 08:58:10.771618: step: 2036/530, loss: 0.23449645936489105
2023-01-21 08:58:11.922111: step: 2040/530, loss: 0.09905443340539932
2023-01-21 08:58:13.105250: step: 2044/530, loss: 6.895667552947998
2023-01-21 08:58:14.313751: step: 2048/530, loss: 0.2752523422241211
2023-01-21 08:58:15.457646: step: 2052/530, loss: 0.20511013269424438
2023-01-21 08:58:16.604637: step: 2056/530, loss: 0.2611364424228668
2023-01-21 08:58:17.794599: step: 2060/530, loss: 0.34802380204200745
2023-01-21 08:58:18.953581: step: 2064/530, loss: 0.22178447246551514
2023-01-21 08:58:20.159797: step: 2068/530, loss: 0.8025556802749634
2023-01-21 08:58:21.372198: step: 2072/530, loss: 0.466240793466568
2023-01-21 08:58:22.569193: step: 2076/530, loss: 0.7449437975883484
2023-01-21 08:58:23.731920: step: 2080/530, loss: 1.3982199430465698
2023-01-21 08:58:24.904931: step: 2084/530, loss: 0.11728854477405548
2023-01-21 08:58:26.055133: step: 2088/530, loss: 0.1916791945695877
2023-01-21 08:58:27.251239: step: 2092/530, loss: 0.383246511220932
2023-01-21 08:58:28.437740: step: 2096/530, loss: 0.43894684314727783
2023-01-21 08:58:29.628152: step: 2100/530, loss: 0.2484123408794403
2023-01-21 08:58:30.785440: step: 2104/530, loss: 1.289673924446106
2023-01-21 08:58:31.955319: step: 2108/530, loss: 0.250160276889801
2023-01-21 08:58:33.149716: step: 2112/530, loss: 0.6158790588378906
2023-01-21 08:58:34.325007: step: 2116/530, loss: 0.3135722875595093
2023-01-21 08:58:35.499580: step: 2120/530, loss: 0.08418045192956924
==================================================
Loss: 0.582
--------------------
Dev: {'event': {'p': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5483870967741935, 'r': 0.6296296296296297, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.4117647058823529, 'r': 0.3888888888888889, 'f1': 0.39999999999999997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5483870967741935, 'r': 0.6296296296296297, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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 08:59:35.954873: step: 4/530, loss: 0.5191924571990967
2023-01-21 08:59:37.140314: step: 8/530, loss: 1.1706078052520752
2023-01-21 08:59:38.286047: step: 12/530, loss: 0.07949772477149963
2023-01-21 08:59:39.445449: step: 16/530, loss: 0.09682364761829376
2023-01-21 08:59:40.619623: step: 20/530, loss: 0.8770349621772766
2023-01-21 08:59:41.873995: step: 24/530, loss: 0.5905191898345947
2023-01-21 08:59:43.072499: step: 28/530, loss: 0.2906637191772461
2023-01-21 08:59:44.202896: step: 32/530, loss: 0.6441036462783813
2023-01-21 08:59:45.367607: step: 36/530, loss: 0.45494937896728516
2023-01-21 08:59:46.638599: step: 40/530, loss: 0.2761791944503784
2023-01-21 08:59:47.850667: step: 44/530, loss: 0.363181471824646
2023-01-21 08:59:48.998363: step: 48/530, loss: 0.555605411529541
2023-01-21 08:59:50.213041: step: 52/530, loss: 0.6407239437103271
2023-01-21 08:59:51.391829: step: 56/530, loss: 0.7539819478988647
2023-01-21 08:59:52.601508: step: 60/530, loss: 0.6422100067138672
2023-01-21 08:59:53.788519: step: 64/530, loss: 0.5551279187202454
2023-01-21 08:59:54.948381: step: 68/530, loss: 0.7178381085395813
2023-01-21 08:59:56.139346: step: 72/530, loss: 0.04354162514209747
2023-01-21 08:59:57.280841: step: 76/530, loss: 0.20696429908275604
2023-01-21 08:59:58.437591: step: 80/530, loss: 0.2528041899204254
2023-01-21 08:59:59.604826: step: 84/530, loss: 1.1910349130630493
2023-01-21 09:00:00.794395: step: 88/530, loss: 0.386963814496994
2023-01-21 09:00:01.957187: step: 92/530, loss: 0.23293867707252502
2023-01-21 09:00:03.096813: step: 96/530, loss: 0.25381651520729065
2023-01-21 09:00:04.282168: step: 100/530, loss: 0.2759174406528473
2023-01-21 09:00:05.437208: step: 104/530, loss: 0.2803935110569
2023-01-21 09:00:06.649183: step: 108/530, loss: 0.07051368057727814
2023-01-21 09:00:07.840830: step: 112/530, loss: 0.1895613670349121
2023-01-21 09:00:08.994222: step: 116/530, loss: 0.5699976086616516
2023-01-21 09:00:10.141791: step: 120/530, loss: 0.1027122512459755
2023-01-21 09:00:11.309011: step: 124/530, loss: 0.37537500262260437
2023-01-21 09:00:12.500728: step: 128/530, loss: 0.056505490094423294
2023-01-21 09:00:13.663469: step: 132/530, loss: 6.2937188148498535
2023-01-21 09:00:14.839098: step: 136/530, loss: 0.28658831119537354
2023-01-21 09:00:16.006097: step: 140/530, loss: 0.5731838345527649
2023-01-21 09:00:17.169433: step: 144/530, loss: 0.1502998322248459
2023-01-21 09:00:18.314737: step: 148/530, loss: 0.10899467766284943
2023-01-21 09:00:19.526660: step: 152/530, loss: 0.1422867774963379
2023-01-21 09:00:20.694061: step: 156/530, loss: 0.8451544046401978
2023-01-21 09:00:21.871726: step: 160/530, loss: 0.30751779675483704
2023-01-21 09:00:23.063308: step: 164/530, loss: 0.16143354773521423
2023-01-21 09:00:24.284774: step: 168/530, loss: 1.0905141830444336
2023-01-21 09:00:25.440005: step: 172/530, loss: 0.675628125667572
2023-01-21 09:00:26.668374: step: 176/530, loss: 0.21934472024440765
2023-01-21 09:00:27.810626: step: 180/530, loss: 0.6327414512634277
2023-01-21 09:00:28.980016: step: 184/530, loss: 0.3127192258834839
2023-01-21 09:00:30.152809: step: 188/530, loss: 0.02283940277993679
2023-01-21 09:00:31.315909: step: 192/530, loss: 0.11165190488100052
2023-01-21 09:00:32.510580: step: 196/530, loss: 0.14807024598121643
2023-01-21 09:00:33.713093: step: 200/530, loss: 0.4557231068611145
2023-01-21 09:00:34.909503: step: 204/530, loss: 0.26212817430496216
2023-01-21 09:00:36.098876: step: 208/530, loss: 7.076763153076172
2023-01-21 09:00:37.301627: step: 212/530, loss: 0.19836553931236267
2023-01-21 09:00:38.469097: step: 216/530, loss: 0.15052075684070587
2023-01-21 09:00:39.647964: step: 220/530, loss: 0.16224899888038635
2023-01-21 09:00:40.820265: step: 224/530, loss: 0.09037952870130539
2023-01-21 09:00:42.041907: step: 228/530, loss: 0.10467491298913956
2023-01-21 09:00:43.207073: step: 232/530, loss: 0.23347590863704681
2023-01-21 09:00:44.401257: step: 236/530, loss: 0.7598155736923218
2023-01-21 09:00:45.603022: step: 240/530, loss: 0.27143335342407227
2023-01-21 09:00:46.764967: step: 244/530, loss: 0.2126666009426117
2023-01-21 09:00:47.936198: step: 248/530, loss: 0.7509574890136719
2023-01-21 09:00:49.105710: step: 252/530, loss: 0.40980854630470276
2023-01-21 09:00:50.279174: step: 256/530, loss: 0.07153907418251038
2023-01-21 09:00:51.460471: step: 260/530, loss: 0.6321728229522705
2023-01-21 09:00:52.671470: step: 264/530, loss: 0.13787135481834412
2023-01-21 09:00:53.871191: step: 268/530, loss: 0.09872189164161682
2023-01-21 09:00:55.042722: step: 272/530, loss: 0.2302146852016449
2023-01-21 09:00:56.235662: step: 276/530, loss: 0.05352058634161949
2023-01-21 09:00:57.400251: step: 280/530, loss: 0.19960834085941315
2023-01-21 09:00:58.605686: step: 284/530, loss: 0.04820604622364044
2023-01-21 09:00:59.784344: step: 288/530, loss: 0.18540087342262268
2023-01-21 09:01:00.960932: step: 292/530, loss: 0.1493431031703949
2023-01-21 09:01:02.165114: step: 296/530, loss: 0.8330694437026978
2023-01-21 09:01:03.337910: step: 300/530, loss: 0.06468772888183594
2023-01-21 09:01:04.511941: step: 304/530, loss: 0.34788140654563904
2023-01-21 09:01:05.686351: step: 308/530, loss: 0.18793946504592896
2023-01-21 09:01:06.851557: step: 312/530, loss: 1.1298273801803589
2023-01-21 09:01:08.046014: step: 316/530, loss: 1.097474217414856
2023-01-21 09:01:09.190750: step: 320/530, loss: 0.10257778316736221
2023-01-21 09:01:10.374295: step: 324/530, loss: 0.6832658052444458
2023-01-21 09:01:11.545626: step: 328/530, loss: 0.10810303688049316
2023-01-21 09:01:12.717570: step: 332/530, loss: 1.2212339639663696
2023-01-21 09:01:13.851524: step: 336/530, loss: 0.8411941528320312
2023-01-21 09:01:15.012073: step: 340/530, loss: 0.20332685112953186
2023-01-21 09:01:16.173136: step: 344/530, loss: 0.5032680034637451
2023-01-21 09:01:17.418810: step: 348/530, loss: 1.0888937711715698
2023-01-21 09:01:18.644269: step: 352/530, loss: 0.2017425149679184
2023-01-21 09:01:19.808658: step: 356/530, loss: 0.14386549592018127
2023-01-21 09:01:21.002572: step: 360/530, loss: 0.33215874433517456
2023-01-21 09:01:22.175268: step: 364/530, loss: 0.1823878288269043
2023-01-21 09:01:23.383541: step: 368/530, loss: 0.33030763268470764
2023-01-21 09:01:24.599801: step: 372/530, loss: 0.17231746017932892
2023-01-21 09:01:25.827269: step: 376/530, loss: 0.40852493047714233
2023-01-21 09:01:27.017682: step: 380/530, loss: 0.11943116784095764
2023-01-21 09:01:28.199205: step: 384/530, loss: 0.04621467739343643
2023-01-21 09:01:29.380619: step: 388/530, loss: 0.38526660203933716
2023-01-21 09:01:30.513796: step: 392/530, loss: 0.15916013717651367
2023-01-21 09:01:31.704257: step: 396/530, loss: 6.311384677886963
2023-01-21 09:01:32.888640: step: 400/530, loss: 0.224155992269516
2023-01-21 09:01:34.064227: step: 404/530, loss: 0.29802682995796204
2023-01-21 09:01:35.262240: step: 408/530, loss: 0.3599209487438202
2023-01-21 09:01:36.410188: step: 412/530, loss: 0.2007201611995697
2023-01-21 09:01:37.598162: step: 416/530, loss: 0.4488944113254547
2023-01-21 09:01:38.768370: step: 420/530, loss: 1.0110517740249634
2023-01-21 09:01:39.952063: step: 424/530, loss: 0.14849528670310974
2023-01-21 09:01:41.113655: step: 428/530, loss: 0.14279747009277344
2023-01-21 09:01:42.283391: step: 432/530, loss: 0.20845270156860352
2023-01-21 09:01:43.438574: step: 436/530, loss: 0.25758370757102966
2023-01-21 09:01:44.664908: step: 440/530, loss: 0.237433061003685
2023-01-21 09:01:45.815299: step: 444/530, loss: 0.093405582010746
2023-01-21 09:01:47.058921: step: 448/530, loss: 0.054293230175971985
2023-01-21 09:01:48.211813: step: 452/530, loss: 0.09260274469852448
2023-01-21 09:01:49.382285: step: 456/530, loss: 0.0942709892988205
2023-01-21 09:01:50.539398: step: 460/530, loss: 0.3790920376777649
2023-01-21 09:01:51.778102: step: 464/530, loss: 0.13287459313869476
2023-01-21 09:01:52.956787: step: 468/530, loss: 0.5176077485084534
2023-01-21 09:01:54.134925: step: 472/530, loss: 0.09319677948951721
2023-01-21 09:01:55.270408: step: 476/530, loss: 0.0547015443444252
2023-01-21 09:01:56.474308: step: 480/530, loss: 0.3686017096042633
2023-01-21 09:01:57.669863: step: 484/530, loss: 0.11386542022228241
2023-01-21 09:01:58.836493: step: 488/530, loss: 0.6599113941192627
2023-01-21 09:02:00.017897: step: 492/530, loss: 0.22499322891235352
2023-01-21 09:02:01.243824: step: 496/530, loss: 0.3902978301048279
2023-01-21 09:02:02.427527: step: 500/530, loss: 0.24940013885498047
2023-01-21 09:02:03.607592: step: 504/530, loss: 0.2807157635688782
2023-01-21 09:02:04.790415: step: 508/530, loss: 0.22961747646331787
2023-01-21 09:02:05.940708: step: 512/530, loss: 0.05997591093182564
2023-01-21 09:02:07.094114: step: 516/530, loss: 0.1676074117422104
2023-01-21 09:02:08.297084: step: 520/530, loss: 1.066033959388733
2023-01-21 09:02:09.476044: step: 524/530, loss: 0.12823104858398438
2023-01-21 09:02:10.659392: step: 528/530, loss: 0.20828142762184143
2023-01-21 09:02:11.834873: step: 532/530, loss: 0.6198794841766357
2023-01-21 09:02:13.047708: step: 536/530, loss: 0.4361898899078369
2023-01-21 09:02:14.219210: step: 540/530, loss: 0.20145435631275177
2023-01-21 09:02:15.440319: step: 544/530, loss: 0.6686853766441345
2023-01-21 09:02:16.622572: step: 548/530, loss: 0.17464642226696014
2023-01-21 09:02:17.778491: step: 552/530, loss: 0.13746953010559082
2023-01-21 09:02:18.981942: step: 556/530, loss: 0.11354966461658478
2023-01-21 09:02:20.188835: step: 560/530, loss: 0.08568146079778671
2023-01-21 09:02:21.370930: step: 564/530, loss: 0.1313396692276001
2023-01-21 09:02:22.523216: step: 568/530, loss: 0.3456174433231354
2023-01-21 09:02:23.698133: step: 572/530, loss: 0.31579160690307617
2023-01-21 09:02:24.883202: step: 576/530, loss: 0.49187344312667847
2023-01-21 09:02:26.047394: step: 580/530, loss: 0.2015778124332428
2023-01-21 09:02:27.206164: step: 584/530, loss: 0.14697489142417908
2023-01-21 09:02:28.371686: step: 588/530, loss: 2.2941653728485107
2023-01-21 09:02:29.565498: step: 592/530, loss: 0.32093191146850586
2023-01-21 09:02:30.753326: step: 596/530, loss: 0.12202048301696777
2023-01-21 09:02:31.937260: step: 600/530, loss: 0.3250643014907837
2023-01-21 09:02:33.124613: step: 604/530, loss: 0.11785449832677841
2023-01-21 09:02:34.274566: step: 608/530, loss: 0.09085074067115784
2023-01-21 09:02:35.456137: step: 612/530, loss: 0.12013489007949829
2023-01-21 09:02:36.652531: step: 616/530, loss: 0.839863657951355
2023-01-21 09:02:37.840941: step: 620/530, loss: 0.14664916694164276
2023-01-21 09:02:38.977866: step: 624/530, loss: 0.023165225982666016
2023-01-21 09:02:40.170626: step: 628/530, loss: 0.1783846914768219
2023-01-21 09:02:41.366510: step: 632/530, loss: 0.36509278416633606
2023-01-21 09:02:42.561664: step: 636/530, loss: 0.13413682579994202
2023-01-21 09:02:43.731272: step: 640/530, loss: 0.15138070285320282
2023-01-21 09:02:44.891777: step: 644/530, loss: 0.6526864171028137
2023-01-21 09:02:46.100514: step: 648/530, loss: 0.14482823014259338
2023-01-21 09:02:47.285025: step: 652/530, loss: 1.921859860420227
2023-01-21 09:02:48.458430: step: 656/530, loss: 6.161225318908691
2023-01-21 09:02:49.662225: step: 660/530, loss: 0.12913508713245392
2023-01-21 09:02:50.847348: step: 664/530, loss: 0.6400312781333923
2023-01-21 09:02:52.044339: step: 668/530, loss: 0.7473790645599365
2023-01-21 09:02:53.223323: step: 672/530, loss: 0.2976551055908203
2023-01-21 09:02:54.372693: step: 676/530, loss: 0.13958100974559784
2023-01-21 09:02:55.521163: step: 680/530, loss: 0.10299654304981232
2023-01-21 09:02:56.669527: step: 684/530, loss: 1.0223383903503418
2023-01-21 09:02:57.859606: step: 688/530, loss: 0.10239820927381516
2023-01-21 09:02:59.061667: step: 692/530, loss: 0.1845192015171051
2023-01-21 09:03:00.219679: step: 696/530, loss: 0.025221683084964752
2023-01-21 09:03:01.417688: step: 700/530, loss: 1.3266277313232422
2023-01-21 09:03:02.593504: step: 704/530, loss: 0.18309983611106873
2023-01-21 09:03:03.758428: step: 708/530, loss: 0.37653648853302
2023-01-21 09:03:04.899648: step: 712/530, loss: 0.06200771778821945
2023-01-21 09:03:06.075002: step: 716/530, loss: 0.7784267067909241
2023-01-21 09:03:07.267035: step: 720/530, loss: 0.14865227043628693
2023-01-21 09:03:08.472170: step: 724/530, loss: 0.33311232924461365
2023-01-21 09:03:09.663727: step: 728/530, loss: 1.8277270793914795
2023-01-21 09:03:10.834934: step: 732/530, loss: 0.9166950583457947
2023-01-21 09:03:11.976610: step: 736/530, loss: 0.12873688340187073
2023-01-21 09:03:13.129967: step: 740/530, loss: 0.18474312126636505
2023-01-21 09:03:14.293599: step: 744/530, loss: 0.1621491014957428
2023-01-21 09:03:15.470257: step: 748/530, loss: 0.48359689116477966
2023-01-21 09:03:16.641713: step: 752/530, loss: 0.665831446647644
2023-01-21 09:03:17.848578: step: 756/530, loss: 0.1538044512271881
2023-01-21 09:03:19.057240: step: 760/530, loss: 0.09240970760583878
2023-01-21 09:03:20.211215: step: 764/530, loss: 0.21537938714027405
2023-01-21 09:03:21.387813: step: 768/530, loss: 0.0468110591173172
2023-01-21 09:03:22.581685: step: 772/530, loss: 0.8836272954940796
2023-01-21 09:03:23.737494: step: 776/530, loss: 0.74620521068573
2023-01-21 09:03:24.875210: step: 780/530, loss: 0.23835481703281403
2023-01-21 09:03:26.025010: step: 784/530, loss: 0.6982858180999756
2023-01-21 09:03:27.204765: step: 788/530, loss: 0.06144876405596733
2023-01-21 09:03:28.421706: step: 792/530, loss: 0.08733272552490234
2023-01-21 09:03:29.632335: step: 796/530, loss: 0.08771095424890518
2023-01-21 09:03:30.804749: step: 800/530, loss: 0.0940345823764801
2023-01-21 09:03:31.965403: step: 804/530, loss: 0.7421600818634033
2023-01-21 09:03:33.128357: step: 808/530, loss: 0.37771615386009216
2023-01-21 09:03:34.298297: step: 812/530, loss: 0.13880959153175354
2023-01-21 09:03:35.480254: step: 816/530, loss: 0.13163185119628906
2023-01-21 09:03:36.633611: step: 820/530, loss: 0.13775014877319336
2023-01-21 09:03:37.791775: step: 824/530, loss: 0.038422584533691406
2023-01-21 09:03:38.956199: step: 828/530, loss: 0.45583438873291016
2023-01-21 09:03:40.127103: step: 832/530, loss: 0.3177642822265625
2023-01-21 09:03:41.339087: step: 836/530, loss: 0.1935112625360489
2023-01-21 09:03:42.551825: step: 840/530, loss: 0.07412910461425781
2023-01-21 09:03:43.740545: step: 844/530, loss: 0.8029215931892395
2023-01-21 09:03:44.962163: step: 848/530, loss: 0.1322302371263504
2023-01-21 09:03:46.153829: step: 852/530, loss: 0.3052927851676941
2023-01-21 09:03:47.371674: step: 856/530, loss: 0.24283725023269653
2023-01-21 09:03:48.546134: step: 860/530, loss: 0.12081928551197052
2023-01-21 09:03:49.732554: step: 864/530, loss: 0.1414417326450348
2023-01-21 09:03:50.932233: step: 868/530, loss: 0.11298465728759766
2023-01-21 09:03:52.088030: step: 872/530, loss: 0.7825241684913635
2023-01-21 09:03:53.317245: step: 876/530, loss: 0.19887542724609375
2023-01-21 09:03:54.509746: step: 880/530, loss: 0.1622975766658783
2023-01-21 09:03:55.675364: step: 884/530, loss: 1.4077777862548828
2023-01-21 09:03:56.860098: step: 888/530, loss: 0.10478525608778
2023-01-21 09:03:58.026421: step: 892/530, loss: 0.12131252884864807
2023-01-21 09:03:59.232322: step: 896/530, loss: 0.18845997750759125
2023-01-21 09:04:00.434987: step: 900/530, loss: 0.021206902340054512
2023-01-21 09:04:01.616690: step: 904/530, loss: 0.09146595001220703
2023-01-21 09:04:02.817656: step: 908/530, loss: 0.5313259363174438
2023-01-21 09:04:04.012076: step: 912/530, loss: 0.17365026473999023
2023-01-21 09:04:05.187761: step: 916/530, loss: 0.1472891867160797
2023-01-21 09:04:06.360265: step: 920/530, loss: 0.04388804733753204
2023-01-21 09:04:07.515007: step: 924/530, loss: 0.09502525627613068
2023-01-21 09:04:08.699815: step: 928/530, loss: 0.7249863147735596
2023-01-21 09:04:09.888826: step: 932/530, loss: 0.16412439942359924
2023-01-21 09:04:11.072694: step: 936/530, loss: 0.9990280866622925
2023-01-21 09:04:12.256782: step: 940/530, loss: 1.5301529169082642
2023-01-21 09:04:13.414169: step: 944/530, loss: 0.07348103821277618
2023-01-21 09:04:14.565973: step: 948/530, loss: 0.08050890266895294
2023-01-21 09:04:15.722254: step: 952/530, loss: 0.11624650657176971
2023-01-21 09:04:16.907635: step: 956/530, loss: 0.11236119270324707
2023-01-21 09:04:18.095029: step: 960/530, loss: 0.9776906967163086
2023-01-21 09:04:19.256012: step: 964/530, loss: 0.40713661909103394
2023-01-21 09:04:20.436672: step: 968/530, loss: 0.7711392641067505
2023-01-21 09:04:21.609041: step: 972/530, loss: 0.13404206931591034
2023-01-21 09:04:22.772352: step: 976/530, loss: 0.4408808648586273
2023-01-21 09:04:23.927032: step: 980/530, loss: 0.13976383209228516
2023-01-21 09:04:25.083339: step: 984/530, loss: 0.6734783053398132
2023-01-21 09:04:26.275546: step: 988/530, loss: 0.4627707898616791
2023-01-21 09:04:27.460451: step: 992/530, loss: 0.597649097442627
2023-01-21 09:04:28.641000: step: 996/530, loss: 0.11303062736988068
2023-01-21 09:04:29.861164: step: 1000/530, loss: 0.2047712802886963
2023-01-21 09:04:31.021446: step: 1004/530, loss: 0.19961795210838318
2023-01-21 09:04:32.213565: step: 1008/530, loss: 0.06768689304590225
2023-01-21 09:04:33.424158: step: 1012/530, loss: 0.0863809585571289
2023-01-21 09:04:34.594811: step: 1016/530, loss: 0.3175378739833832
2023-01-21 09:04:35.792460: step: 1020/530, loss: 0.13827113807201385
2023-01-21 09:04:36.976522: step: 1024/530, loss: 0.26949015259742737
2023-01-21 09:04:38.193400: step: 1028/530, loss: 0.6692726612091064
2023-01-21 09:04:39.360072: step: 1032/530, loss: 0.3550410866737366
2023-01-21 09:04:40.511290: step: 1036/530, loss: 0.09226550906896591
2023-01-21 09:04:41.712461: step: 1040/530, loss: 0.3014012575149536
2023-01-21 09:04:42.892570: step: 1044/530, loss: 1.3666375875473022
2023-01-21 09:04:44.062203: step: 1048/530, loss: 0.10425176471471786
2023-01-21 09:04:45.237314: step: 1052/530, loss: 1.3791825771331787
2023-01-21 09:04:46.398748: step: 1056/530, loss: 1.2946498394012451
2023-01-21 09:04:47.581444: step: 1060/530, loss: 0.1721879541873932
2023-01-21 09:04:48.726548: step: 1064/530, loss: 0.11235733330249786
2023-01-21 09:04:49.876954: step: 1068/530, loss: 0.435479074716568
2023-01-21 09:04:51.027567: step: 1072/530, loss: 0.15691828727722168
2023-01-21 09:04:52.212343: step: 1076/530, loss: 1.3144248723983765
2023-01-21 09:04:53.366023: step: 1080/530, loss: 0.5212429165840149
2023-01-21 09:04:54.519682: step: 1084/530, loss: 0.14469701051712036
2023-01-21 09:04:55.691202: step: 1088/530, loss: 0.7016888856887817
2023-01-21 09:04:56.873872: step: 1092/530, loss: 0.5364924669265747
2023-01-21 09:04:58.027448: step: 1096/530, loss: 0.7248868346214294
2023-01-21 09:04:59.227871: step: 1100/530, loss: 1.0725609064102173
2023-01-21 09:05:00.418789: step: 1104/530, loss: 0.3142368197441101
2023-01-21 09:05:01.637714: step: 1108/530, loss: 0.07861433178186417
2023-01-21 09:05:02.820927: step: 1112/530, loss: 0.1779017448425293
2023-01-21 09:05:04.044106: step: 1116/530, loss: 0.25320473313331604
2023-01-21 09:05:05.267753: step: 1120/530, loss: 0.7164859771728516
2023-01-21 09:05:06.444301: step: 1124/530, loss: 0.35661038756370544
2023-01-21 09:05:07.611346: step: 1128/530, loss: 0.3326791524887085
2023-01-21 09:05:08.821233: step: 1132/530, loss: 0.9281638860702515
2023-01-21 09:05:09.987225: step: 1136/530, loss: 0.6749950051307678
2023-01-21 09:05:11.179098: step: 1140/530, loss: 0.800000786781311
2023-01-21 09:05:12.443363: step: 1144/530, loss: 0.06312818825244904
2023-01-21 09:05:13.652936: step: 1148/530, loss: 0.15952062606811523
2023-01-21 09:05:14.835454: step: 1152/530, loss: 0.42119836807250977
2023-01-21 09:05:16.014838: step: 1156/530, loss: 0.2126747965812683
2023-01-21 09:05:17.221925: step: 1160/530, loss: 0.15158167481422424
2023-01-21 09:05:18.406839: step: 1164/530, loss: 0.3569963574409485
2023-01-21 09:05:19.610570: step: 1168/530, loss: 0.3941791355609894
2023-01-21 09:05:20.814990: step: 1172/530, loss: 1.6471282243728638
2023-01-21 09:05:21.979033: step: 1176/530, loss: 0.1890300214290619
2023-01-21 09:05:23.218023: step: 1180/530, loss: 4.642889022827148
2023-01-21 09:05:24.412391: step: 1184/530, loss: 0.2530531883239746
2023-01-21 09:05:25.591826: step: 1188/530, loss: 0.09014657139778137
2023-01-21 09:05:26.774085: step: 1192/530, loss: 0.7563281059265137
2023-01-21 09:05:27.957645: step: 1196/530, loss: 7.942691802978516
2023-01-21 09:05:29.112979: step: 1200/530, loss: 0.8773500919342041
2023-01-21 09:05:30.266144: step: 1204/530, loss: 0.6622392535209656
2023-01-21 09:05:31.431084: step: 1208/530, loss: 0.1346883326768875
2023-01-21 09:05:32.632290: step: 1212/530, loss: 0.3898424208164215
2023-01-21 09:05:33.822405: step: 1216/530, loss: 0.5551837086677551
2023-01-21 09:05:35.007195: step: 1220/530, loss: 0.03483228385448456
2023-01-21 09:05:36.204131: step: 1224/530, loss: 0.10519857704639435
2023-01-21 09:05:37.352079: step: 1228/530, loss: 6.247714042663574
2023-01-21 09:05:38.542437: step: 1232/530, loss: 0.07327232509851456
2023-01-21 09:05:39.776837: step: 1236/530, loss: 0.06431026756763458
2023-01-21 09:05:40.990808: step: 1240/530, loss: 0.2630414068698883
2023-01-21 09:05:42.150354: step: 1244/530, loss: 0.7725036144256592
2023-01-21 09:05:43.375525: step: 1248/530, loss: 0.7779296636581421
2023-01-21 09:05:44.587268: step: 1252/530, loss: 0.2596513628959656
2023-01-21 09:05:45.822164: step: 1256/530, loss: 0.17486433684825897
2023-01-21 09:05:46.974644: step: 1260/530, loss: 0.20854301750659943
2023-01-21 09:05:48.148079: step: 1264/530, loss: 0.5837327241897583
2023-01-21 09:05:49.320453: step: 1268/530, loss: 0.09923320263624191
2023-01-21 09:05:50.505162: step: 1272/530, loss: 0.12830042839050293
2023-01-21 09:05:51.708925: step: 1276/530, loss: 0.07933598011732101
2023-01-21 09:05:52.905199: step: 1280/530, loss: 0.10121545195579529
2023-01-21 09:05:54.066592: step: 1284/530, loss: 0.8762174844741821
2023-01-21 09:05:55.241402: step: 1288/530, loss: 0.17349015176296234
2023-01-21 09:05:56.418280: step: 1292/530, loss: 0.23248663544654846
2023-01-21 09:05:57.579892: step: 1296/530, loss: 0.19568046927452087
2023-01-21 09:05:58.787590: step: 1300/530, loss: 0.7276216745376587
2023-01-21 09:05:59.984640: step: 1304/530, loss: 0.32748889923095703
2023-01-21 09:06:01.178787: step: 1308/530, loss: 0.2083718329668045
2023-01-21 09:06:02.405653: step: 1312/530, loss: 0.3393760621547699
2023-01-21 09:06:03.578749: step: 1316/530, loss: 6.476100921630859
2023-01-21 09:06:04.744552: step: 1320/530, loss: 2.1071600914001465
2023-01-21 09:06:05.930551: step: 1324/530, loss: 0.697489321231842
2023-01-21 09:06:07.118602: step: 1328/530, loss: 1.1273558139801025
2023-01-21 09:06:08.341876: step: 1332/530, loss: 0.468283474445343
2023-01-21 09:06:09.542975: step: 1336/530, loss: 0.0896296501159668
2023-01-21 09:06:10.733416: step: 1340/530, loss: 1.3354952335357666
2023-01-21 09:06:11.924404: step: 1344/530, loss: 0.3272493779659271
2023-01-21 09:06:13.109792: step: 1348/530, loss: 0.4466167390346527
2023-01-21 09:06:14.333174: step: 1352/530, loss: 0.10995455086231232
2023-01-21 09:06:15.481187: step: 1356/530, loss: 0.13752499222755432
2023-01-21 09:06:16.665994: step: 1360/530, loss: 0.43463876843452454
2023-01-21 09:06:17.820810: step: 1364/530, loss: 0.20803165435791016
2023-01-21 09:06:19.000395: step: 1368/530, loss: 0.20012864470481873
2023-01-21 09:06:20.177858: step: 1372/530, loss: 0.09706335514783859
2023-01-21 09:06:21.365213: step: 1376/530, loss: 0.5609232783317566
2023-01-21 09:06:22.499671: step: 1380/530, loss: 2.2602148056030273
2023-01-21 09:06:23.662402: step: 1384/530, loss: 0.7181587815284729
2023-01-21 09:06:24.849613: step: 1388/530, loss: 0.036554619669914246
2023-01-21 09:06:26.016125: step: 1392/530, loss: 0.14397478103637695
2023-01-21 09:06:27.224141: step: 1396/530, loss: 0.3144262433052063
2023-01-21 09:06:28.405855: step: 1400/530, loss: 0.12653875350952148
2023-01-21 09:06:29.585141: step: 1404/530, loss: 0.2666395306587219
2023-01-21 09:06:30.752122: step: 1408/530, loss: 0.24201267957687378
2023-01-21 09:06:31.969461: step: 1412/530, loss: 0.07698884606361389
2023-01-21 09:06:33.176360: step: 1416/530, loss: 0.05825548246502876
2023-01-21 09:06:34.365454: step: 1420/530, loss: 0.32834547758102417
2023-01-21 09:06:35.529671: step: 1424/530, loss: 0.27075016498565674
2023-01-21 09:06:36.779911: step: 1428/530, loss: 0.36395910382270813
2023-01-21 09:06:37.962372: step: 1432/530, loss: 0.4368910789489746
2023-01-21 09:06:39.138937: step: 1436/530, loss: 1.0011438131332397
2023-01-21 09:06:40.300401: step: 1440/530, loss: 0.09150008857250214
2023-01-21 09:06:41.482849: step: 1444/530, loss: 0.7740252614021301
2023-01-21 09:06:42.661189: step: 1448/530, loss: 0.08964795619249344
2023-01-21 09:06:43.838434: step: 1452/530, loss: 0.11217927932739258
2023-01-21 09:06:45.011339: step: 1456/530, loss: 0.2322949469089508
2023-01-21 09:06:46.174044: step: 1460/530, loss: 0.043490078300237656
2023-01-21 09:06:47.334260: step: 1464/530, loss: 0.6711433529853821
2023-01-21 09:06:48.491521: step: 1468/530, loss: 0.4433276951313019
2023-01-21 09:06:49.700744: step: 1472/530, loss: 0.222181037068367
2023-01-21 09:06:50.903148: step: 1476/530, loss: 0.723024845123291
2023-01-21 09:06:52.120140: step: 1480/530, loss: 0.11312341690063477
2023-01-21 09:06:53.329817: step: 1484/530, loss: 0.7232824563980103
2023-01-21 09:06:54.515196: step: 1488/530, loss: 0.7157189249992371
2023-01-21 09:06:55.700310: step: 1492/530, loss: 0.4857467710971832
2023-01-21 09:06:56.888164: step: 1496/530, loss: 0.037091925740242004
2023-01-21 09:06:58.076861: step: 1500/530, loss: 0.17124004662036896
2023-01-21 09:06:59.272383: step: 1504/530, loss: 0.3725845217704773
2023-01-21 09:07:00.447510: step: 1508/530, loss: 0.7506771087646484
2023-01-21 09:07:01.606220: step: 1512/530, loss: 1.1414482593536377
2023-01-21 09:07:02.791876: step: 1516/530, loss: 0.4713541567325592
2023-01-21 09:07:03.982953: step: 1520/530, loss: 0.9057143330574036
2023-01-21 09:07:05.184693: step: 1524/530, loss: 0.10838623344898224
2023-01-21 09:07:06.381565: step: 1528/530, loss: 0.15397867560386658
2023-01-21 09:07:07.581078: step: 1532/530, loss: 0.4569709599018097
2023-01-21 09:07:08.733013: step: 1536/530, loss: 0.09263773262500763
2023-01-21 09:07:09.962959: step: 1540/530, loss: 0.39521485567092896
2023-01-21 09:07:11.141997: step: 1544/530, loss: 0.17746220529079437
2023-01-21 09:07:12.342885: step: 1548/530, loss: 0.31682220101356506
2023-01-21 09:07:13.508844: step: 1552/530, loss: 0.21630993485450745
2023-01-21 09:07:14.696934: step: 1556/530, loss: 0.4423714876174927
2023-01-21 09:07:15.845028: step: 1560/530, loss: 0.30737465620040894
2023-01-21 09:07:17.021585: step: 1564/530, loss: 0.11255097389221191
2023-01-21 09:07:18.209281: step: 1568/530, loss: 0.08390870690345764
2023-01-21 09:07:19.405055: step: 1572/530, loss: 0.08495894074440002
2023-01-21 09:07:20.597735: step: 1576/530, loss: 0.08108730614185333
2023-01-21 09:07:21.776369: step: 1580/530, loss: 0.011083221063017845
2023-01-21 09:07:22.936392: step: 1584/530, loss: 0.7003467082977295
2023-01-21 09:07:24.136719: step: 1588/530, loss: 0.07347726821899414
2023-01-21 09:07:25.288248: step: 1592/530, loss: 0.7508512735366821
2023-01-21 09:07:26.474143: step: 1596/530, loss: 0.39373865723609924
2023-01-21 09:07:27.639942: step: 1600/530, loss: 0.2067669928073883
2023-01-21 09:07:28.811475: step: 1604/530, loss: 0.49305328726768494
2023-01-21 09:07:29.997395: step: 1608/530, loss: 0.8078652620315552
2023-01-21 09:07:31.201288: step: 1612/530, loss: 0.10917873680591583
2023-01-21 09:07:32.382558: step: 1616/530, loss: 0.11626091599464417
2023-01-21 09:07:33.507864: step: 1620/530, loss: 0.6472904682159424
2023-01-21 09:07:34.688686: step: 1624/530, loss: 0.18788547813892365
2023-01-21 09:07:35.860662: step: 1628/530, loss: 0.5658272504806519
2023-01-21 09:07:37.046696: step: 1632/530, loss: 1.4634454250335693
2023-01-21 09:07:38.192454: step: 1636/530, loss: 0.3999113440513611
2023-01-21 09:07:39.393344: step: 1640/530, loss: 0.23471951484680176
2023-01-21 09:07:40.627427: step: 1644/530, loss: 2.009218215942383
2023-01-21 09:07:41.817439: step: 1648/530, loss: 0.3491598069667816
2023-01-21 09:07:42.988550: step: 1652/530, loss: 0.8189980983734131
2023-01-21 09:07:44.221143: step: 1656/530, loss: 0.11746149510145187
2023-01-21 09:07:45.402313: step: 1660/530, loss: 0.21372228860855103
2023-01-21 09:07:46.578149: step: 1664/530, loss: 0.2093428075313568
2023-01-21 09:07:47.731298: step: 1668/530, loss: 0.6431800723075867
2023-01-21 09:07:48.924816: step: 1672/530, loss: 0.957047164440155
2023-01-21 09:07:50.088044: step: 1676/530, loss: 0.4716704487800598
2023-01-21 09:07:51.307903: step: 1680/530, loss: 0.13276395201683044
2023-01-21 09:07:52.492474: step: 1684/530, loss: 0.06600695103406906
2023-01-21 09:07:53.693020: step: 1688/530, loss: 0.2204338163137436
2023-01-21 09:07:54.922962: step: 1692/530, loss: 0.44693803787231445
2023-01-21 09:07:56.151121: step: 1696/530, loss: 0.019518518820405006
2023-01-21 09:07:57.335174: step: 1700/530, loss: 0.174461230635643
2023-01-21 09:07:58.544266: step: 1704/530, loss: 0.14608268439769745
2023-01-21 09:07:59.718763: step: 1708/530, loss: 0.8251336812973022
2023-01-21 09:08:00.894683: step: 1712/530, loss: 0.22570917010307312
2023-01-21 09:08:02.101964: step: 1716/530, loss: 0.1938481330871582
2023-01-21 09:08:03.284020: step: 1720/530, loss: 0.08189859241247177
2023-01-21 09:08:04.510937: step: 1724/530, loss: 0.029110431671142578
2023-01-21 09:08:05.661271: step: 1728/530, loss: 0.39237260818481445
2023-01-21 09:08:06.869819: step: 1732/530, loss: 0.4478951394557953
2023-01-21 09:08:08.039260: step: 1736/530, loss: 0.2682609260082245
2023-01-21 09:08:09.184847: step: 1740/530, loss: 0.10963449627161026
2023-01-21 09:08:10.390646: step: 1744/530, loss: 0.11441073566675186
2023-01-21 09:08:11.577063: step: 1748/530, loss: 0.4180283546447754
2023-01-21 09:08:12.771404: step: 1752/530, loss: 0.09568938612937927
2023-01-21 09:08:13.971152: step: 1756/530, loss: 0.0807914212346077
2023-01-21 09:08:15.165214: step: 1760/530, loss: 0.9998427629470825
2023-01-21 09:08:16.356388: step: 1764/530, loss: 1.6703314781188965
2023-01-21 09:08:17.572887: step: 1768/530, loss: 0.6590410470962524
2023-01-21 09:08:18.741733: step: 1772/530, loss: 0.6188690066337585
2023-01-21 09:08:19.908557: step: 1776/530, loss: 0.18719124794006348
2023-01-21 09:08:21.103447: step: 1780/530, loss: 0.6701532602310181
2023-01-21 09:08:22.277983: step: 1784/530, loss: 0.7900204062461853
2023-01-21 09:08:23.503590: step: 1788/530, loss: 0.06714200973510742
2023-01-21 09:08:24.690952: step: 1792/530, loss: 0.41136473417282104
2023-01-21 09:08:25.886066: step: 1796/530, loss: 0.15187856554985046
2023-01-21 09:08:27.005392: step: 1800/530, loss: 0.2718049883842468
2023-01-21 09:08:28.202680: step: 1804/530, loss: 1.4343321323394775
2023-01-21 09:08:29.410594: step: 1808/530, loss: 0.04400014877319336
2023-01-21 09:08:30.572444: step: 1812/530, loss: 0.0534881129860878
2023-01-21 09:08:31.752252: step: 1816/530, loss: 0.6328588724136353
2023-01-21 09:08:32.921981: step: 1820/530, loss: 0.44441384077072144
2023-01-21 09:08:34.118392: step: 1824/530, loss: 0.3629192113876343
2023-01-21 09:08:35.331541: step: 1828/530, loss: 0.08184538036584854
2023-01-21 09:08:36.500042: step: 1832/530, loss: 0.9786496162414551
2023-01-21 09:08:37.693451: step: 1836/530, loss: 0.6580917835235596
2023-01-21 09:08:38.885275: step: 1840/530, loss: 0.2784944176673889
2023-01-21 09:08:40.097899: step: 1844/530, loss: 0.049902915954589844
2023-01-21 09:08:41.278539: step: 1848/530, loss: 0.48249807953834534
2023-01-21 09:08:42.458869: step: 1852/530, loss: 0.12248983979225159
2023-01-21 09:08:43.635582: step: 1856/530, loss: 0.27883464097976685
2023-01-21 09:08:44.801268: step: 1860/530, loss: 0.22698427736759186
2023-01-21 09:08:45.936430: step: 1864/530, loss: 0.07895593345165253
2023-01-21 09:08:47.143606: step: 1868/530, loss: 0.0681583434343338
2023-01-21 09:08:48.274677: step: 1872/530, loss: 0.7056682705879211
2023-01-21 09:08:49.488084: step: 1876/530, loss: 0.18610867857933044
2023-01-21 09:08:50.658527: step: 1880/530, loss: 0.18651799857616425
2023-01-21 09:08:51.851150: step: 1884/530, loss: 0.16434498131275177
2023-01-21 09:08:53.024853: step: 1888/530, loss: 0.15267057716846466
2023-01-21 09:08:54.204364: step: 1892/530, loss: 0.0771174430847168
2023-01-21 09:08:55.398047: step: 1896/530, loss: 0.09339471161365509
2023-01-21 09:08:56.551104: step: 1900/530, loss: 0.16388359665870667
2023-01-21 09:08:57.722731: step: 1904/530, loss: 0.16738960146903992
2023-01-21 09:08:58.892603: step: 1908/530, loss: 0.08777789771556854
2023-01-21 09:09:00.074235: step: 1912/530, loss: 0.4378501772880554
2023-01-21 09:09:01.245456: step: 1916/530, loss: 0.06166696920990944
2023-01-21 09:09:02.420044: step: 1920/530, loss: 0.7372552156448364
2023-01-21 09:09:03.590074: step: 1924/530, loss: 0.11108008027076721
2023-01-21 09:09:04.721288: step: 1928/530, loss: 0.5482058525085449
2023-01-21 09:09:05.883221: step: 1932/530, loss: 1.5744177103042603
2023-01-21 09:09:07.115870: step: 1936/530, loss: 0.1304381787776947
2023-01-21 09:09:08.321838: step: 1940/530, loss: 0.11318016052246094
2023-01-21 09:09:09.547716: step: 1944/530, loss: 1.0561084747314453
2023-01-21 09:09:10.713731: step: 1948/530, loss: 0.07393427193164825
2023-01-21 09:09:11.942550: step: 1952/530, loss: 0.7130127549171448
2023-01-21 09:09:13.089696: step: 1956/530, loss: 0.6980878114700317
2023-01-21 09:09:14.257797: step: 1960/530, loss: 0.1762668639421463
2023-01-21 09:09:15.431312: step: 1964/530, loss: 0.03502092510461807
2023-01-21 09:09:16.582533: step: 1968/530, loss: 0.1391678750514984
2023-01-21 09:09:17.770468: step: 1972/530, loss: 0.1952962428331375
2023-01-21 09:09:18.985068: step: 1976/530, loss: 0.06770763546228409
2023-01-21 09:09:20.208925: step: 1980/530, loss: 0.8508750200271606
2023-01-21 09:09:21.399828: step: 1984/530, loss: 0.12318773567676544
2023-01-21 09:09:22.577082: step: 1988/530, loss: 0.9986238479614258
2023-01-21 09:09:23.739959: step: 1992/530, loss: 0.09084725379943848
2023-01-21 09:09:24.905107: step: 1996/530, loss: 0.10266299545764923
2023-01-21 09:09:26.108931: step: 2000/530, loss: 0.21593937277793884
2023-01-21 09:09:27.282940: step: 2004/530, loss: 0.10083504021167755
2023-01-21 09:09:28.468875: step: 2008/530, loss: 0.1104726791381836
2023-01-21 09:09:29.607234: step: 2012/530, loss: 0.4095633625984192
2023-01-21 09:09:30.789190: step: 2016/530, loss: 1.4537510871887207
2023-01-21 09:09:31.958853: step: 2020/530, loss: 0.1197938472032547
2023-01-21 09:09:33.172634: step: 2024/530, loss: 0.7745867967605591
2023-01-21 09:09:34.336504: step: 2028/530, loss: 6.381715774536133
2023-01-21 09:09:35.488666: step: 2032/530, loss: 0.19721823930740356
2023-01-21 09:09:36.630862: step: 2036/530, loss: 0.05052614212036133
2023-01-21 09:09:37.803559: step: 2040/530, loss: 0.36113440990448
2023-01-21 09:09:38.949500: step: 2044/530, loss: 0.1440139263868332
2023-01-21 09:09:40.147953: step: 2048/530, loss: 0.7743402719497681
2023-01-21 09:09:41.308606: step: 2052/530, loss: 1.2610583305358887
2023-01-21 09:09:42.482849: step: 2056/530, loss: 0.18929719924926758
2023-01-21 09:09:43.660525: step: 2060/530, loss: 0.7542743682861328
2023-01-21 09:09:44.824105: step: 2064/530, loss: 0.397914320230484
2023-01-21 09:09:46.007145: step: 2068/530, loss: 0.6517304182052612
2023-01-21 09:09:47.214413: step: 2072/530, loss: 0.22485850751399994
2023-01-21 09:09:48.411758: step: 2076/530, loss: 0.09159145504236221
2023-01-21 09:09:49.623355: step: 2080/530, loss: 0.1678951382637024
2023-01-21 09:09:50.879896: step: 2084/530, loss: 0.33813199400901794
2023-01-21 09:09:52.076007: step: 2088/530, loss: 0.2143198847770691
2023-01-21 09:09:53.244858: step: 2092/530, loss: 0.03416404873132706
2023-01-21 09:09:54.409236: step: 2096/530, loss: 0.10673792660236359
2023-01-21 09:09:55.593978: step: 2100/530, loss: 0.4254302978515625
2023-01-21 09:09:56.773896: step: 2104/530, loss: 0.5432438850402832
2023-01-21 09:09:57.940650: step: 2108/530, loss: 1.0999172925949097
2023-01-21 09:09:59.109931: step: 2112/530, loss: 1.4006919860839844
2023-01-21 09:10:00.308925: step: 2116/530, loss: 0.03751678392291069
2023-01-21 09:10:01.471077: step: 2120/530, loss: 0.13404826819896698
==================================================
Loss: 0.489
--------------------
Dev: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:11:11.738450: step: 4/530, loss: 0.11504116654396057
2023-01-21 09:11:12.904852: step: 8/530, loss: 0.06309275329113007
2023-01-21 09:11:14.092389: step: 12/530, loss: 0.09863381087779999
2023-01-21 09:11:15.265511: step: 16/530, loss: 0.5618250966072083
2023-01-21 09:11:16.446518: step: 20/530, loss: 0.1564173698425293
2023-01-21 09:11:17.604250: step: 24/530, loss: 0.6172769665718079
2023-01-21 09:11:18.766183: step: 28/530, loss: 0.2684229016304016
2023-01-21 09:11:19.903941: step: 32/530, loss: 0.044142819941043854
2023-01-21 09:11:21.069554: step: 36/530, loss: 0.14958220720291138
2023-01-21 09:11:22.256150: step: 40/530, loss: 0.4937502145767212
2023-01-21 09:11:23.430425: step: 44/530, loss: 0.09656219184398651
2023-01-21 09:11:24.628536: step: 48/530, loss: 1.2072091102600098
2023-01-21 09:11:25.795469: step: 52/530, loss: 0.3203827738761902
2023-01-21 09:11:27.001218: step: 56/530, loss: 0.05738206207752228
2023-01-21 09:11:28.187870: step: 60/530, loss: 0.6830106973648071
2023-01-21 09:11:29.363909: step: 64/530, loss: 0.07570695877075195
2023-01-21 09:11:30.526390: step: 68/530, loss: 0.8050023913383484
2023-01-21 09:11:31.680276: step: 72/530, loss: 0.2043381780385971
2023-01-21 09:11:32.882065: step: 76/530, loss: 0.15033084154129028
2023-01-21 09:11:34.059169: step: 80/530, loss: 0.17330902814865112
2023-01-21 09:11:35.208959: step: 84/530, loss: 0.11402960121631622
2023-01-21 09:11:36.397639: step: 88/530, loss: 0.21889343857765198
2023-01-21 09:11:37.550732: step: 92/530, loss: 0.10188436508178711
2023-01-21 09:11:38.720182: step: 96/530, loss: 5.968746185302734
2023-01-21 09:11:39.880662: step: 100/530, loss: 0.3515448570251465
2023-01-21 09:11:41.052490: step: 104/530, loss: 0.1457379311323166
2023-01-21 09:11:42.306793: step: 108/530, loss: 0.10499868541955948
2023-01-21 09:11:43.454123: step: 112/530, loss: 0.0640534907579422
2023-01-21 09:11:44.628667: step: 116/530, loss: 0.33132266998291016
2023-01-21 09:11:45.836013: step: 120/530, loss: 0.11684933304786682
2023-01-21 09:11:47.032630: step: 124/530, loss: 0.37670737504959106
2023-01-21 09:11:48.205192: step: 128/530, loss: 0.44663944840431213
2023-01-21 09:11:49.362356: step: 132/530, loss: 0.4856053590774536
2023-01-21 09:11:50.514966: step: 136/530, loss: 0.09383507072925568
2023-01-21 09:11:51.688670: step: 140/530, loss: 0.1646944135427475
2023-01-21 09:11:52.870854: step: 144/530, loss: 0.24426832795143127
2023-01-21 09:11:54.048172: step: 148/530, loss: 0.3743099272251129
2023-01-21 09:11:55.195106: step: 152/530, loss: 0.18976593017578125
2023-01-21 09:11:56.397825: step: 156/530, loss: 0.21158257126808167
2023-01-21 09:11:57.568724: step: 160/530, loss: 0.6596651077270508
2023-01-21 09:11:58.753789: step: 164/530, loss: 0.2552119195461273
2023-01-21 09:11:59.939499: step: 168/530, loss: 0.46443405747413635
2023-01-21 09:12:01.138250: step: 172/530, loss: 0.06911134719848633
2023-01-21 09:12:02.310016: step: 176/530, loss: 0.3262357711791992
2023-01-21 09:12:03.502268: step: 180/530, loss: 0.12964554131031036
2023-01-21 09:12:04.640329: step: 184/530, loss: 1.215349555015564
2023-01-21 09:12:05.798280: step: 188/530, loss: 0.6032072901725769
2023-01-21 09:12:06.953704: step: 192/530, loss: 0.171454519033432
2023-01-21 09:12:08.119695: step: 196/530, loss: 0.22686359286308289
2023-01-21 09:12:09.300044: step: 200/530, loss: 0.09749040752649307
2023-01-21 09:12:10.505933: step: 204/530, loss: 0.8044226765632629
2023-01-21 09:12:11.705297: step: 208/530, loss: 0.09733162075281143
2023-01-21 09:12:12.923923: step: 212/530, loss: 0.1684611290693283
2023-01-21 09:12:14.110332: step: 216/530, loss: 0.6632862687110901
2023-01-21 09:12:15.266372: step: 220/530, loss: 0.6340490579605103
2023-01-21 09:12:16.421874: step: 224/530, loss: 0.058547019958496094
2023-01-21 09:12:17.603246: step: 228/530, loss: 0.6697985529899597
2023-01-21 09:12:18.806225: step: 232/530, loss: 0.21490922570228577
2023-01-21 09:12:20.010699: step: 236/530, loss: 0.24858587980270386
2023-01-21 09:12:21.185498: step: 240/530, loss: 0.018796920776367188
2023-01-21 09:12:22.387925: step: 244/530, loss: 0.15576982498168945
2023-01-21 09:12:23.580454: step: 248/530, loss: 0.04682798311114311
2023-01-21 09:12:24.752339: step: 252/530, loss: 0.25771158933639526
2023-01-21 09:12:25.937001: step: 256/530, loss: 0.10458288341760635
2023-01-21 09:12:27.124769: step: 260/530, loss: 0.09453883022069931
2023-01-21 09:12:28.314809: step: 264/530, loss: 0.41282740235328674
2023-01-21 09:12:29.536645: step: 268/530, loss: 0.40218687057495117
2023-01-21 09:12:30.720999: step: 272/530, loss: 0.3627673089504242
2023-01-21 09:12:31.901697: step: 276/530, loss: 0.03042449988424778
2023-01-21 09:12:33.078443: step: 280/530, loss: 0.15802831947803497
2023-01-21 09:12:34.254300: step: 284/530, loss: 0.45238763093948364
2023-01-21 09:12:35.408233: step: 288/530, loss: 0.20137998461723328
2023-01-21 09:12:36.590726: step: 292/530, loss: 0.09920788556337357
2023-01-21 09:12:37.734152: step: 296/530, loss: 0.10093660652637482
2023-01-21 09:12:38.985356: step: 300/530, loss: 0.06294488906860352
2023-01-21 09:12:40.194387: step: 304/530, loss: 0.1462322175502777
2023-01-21 09:12:41.353192: step: 308/530, loss: 0.09385000169277191
2023-01-21 09:12:42.579182: step: 312/530, loss: 0.1997065544128418
2023-01-21 09:12:43.783069: step: 316/530, loss: 0.26336878538131714
2023-01-21 09:12:44.971971: step: 320/530, loss: 0.13412360846996307
2023-01-21 09:12:46.133496: step: 324/530, loss: 0.27973833680152893
2023-01-21 09:12:47.348051: step: 328/530, loss: 0.734890878200531
2023-01-21 09:12:48.540296: step: 332/530, loss: 0.1044454574584961
2023-01-21 09:12:49.759685: step: 336/530, loss: 0.174531489610672
2023-01-21 09:12:50.918471: step: 340/530, loss: 0.27906572818756104
2023-01-21 09:12:52.095914: step: 344/530, loss: 0.1268673986196518
2023-01-21 09:12:53.251430: step: 348/530, loss: 0.08036752790212631
2023-01-21 09:12:54.418432: step: 352/530, loss: 0.08531427383422852
2023-01-21 09:12:55.565345: step: 356/530, loss: 0.14621086418628693
2023-01-21 09:12:56.716264: step: 360/530, loss: 0.16158372163772583
2023-01-21 09:12:57.921992: step: 364/530, loss: 1.0669214725494385
2023-01-21 09:12:59.104256: step: 368/530, loss: 0.0758119598031044
2023-01-21 09:13:00.283707: step: 372/530, loss: 0.19217178225517273
2023-01-21 09:13:01.481191: step: 376/530, loss: 0.28128406405448914
2023-01-21 09:13:02.716787: step: 380/530, loss: 0.17578107118606567
2023-01-21 09:13:03.874557: step: 384/530, loss: 0.13452312350273132
2023-01-21 09:13:05.078952: step: 388/530, loss: 0.3514425754547119
2023-01-21 09:13:06.254247: step: 392/530, loss: 0.17970696091651917
2023-01-21 09:13:07.418491: step: 396/530, loss: 0.1492437869310379
2023-01-21 09:13:08.635195: step: 400/530, loss: 0.09625058621168137
2023-01-21 09:13:10.071766: step: 404/530, loss: 0.38881435990333557
2023-01-21 09:13:11.243335: step: 408/530, loss: 0.0808505043387413
2023-01-21 09:13:12.473348: step: 412/530, loss: 0.532212495803833
2023-01-21 09:13:13.645171: step: 416/530, loss: 0.22090129554271698
2023-01-21 09:13:14.828595: step: 420/530, loss: 0.31859293580055237
2023-01-21 09:13:16.022328: step: 424/530, loss: 0.656646192073822
2023-01-21 09:13:17.174538: step: 428/530, loss: 0.05401954799890518
2023-01-21 09:13:18.359679: step: 432/530, loss: 0.47288310527801514
2023-01-21 09:13:19.559697: step: 436/530, loss: 0.05650625377893448
2023-01-21 09:13:20.784971: step: 440/530, loss: 0.030762672424316406
2023-01-21 09:13:21.969740: step: 444/530, loss: 0.14616747200489044
2023-01-21 09:13:23.143208: step: 448/530, loss: 0.1826891303062439
2023-01-21 09:13:24.275025: step: 452/530, loss: 0.14718708395957947
2023-01-21 09:13:25.437583: step: 456/530, loss: 0.03799152374267578
2023-01-21 09:13:26.600211: step: 460/530, loss: 0.10636691749095917
2023-01-21 09:13:27.798210: step: 464/530, loss: 0.08111181855201721
2023-01-21 09:13:28.965507: step: 468/530, loss: 0.15735287964344025
2023-01-21 09:13:30.157122: step: 472/530, loss: 0.3596492409706116
2023-01-21 09:13:31.310013: step: 476/530, loss: 0.6144568920135498
2023-01-21 09:13:32.476437: step: 480/530, loss: 0.09223838150501251
2023-01-21 09:13:33.642269: step: 484/530, loss: 0.6614484786987305
2023-01-21 09:13:34.900967: step: 488/530, loss: 0.14772701263427734
2023-01-21 09:13:36.074457: step: 492/530, loss: 0.5365071296691895
2023-01-21 09:13:37.245118: step: 496/530, loss: 0.09287528693675995
2023-01-21 09:13:38.444810: step: 500/530, loss: 0.22825641930103302
2023-01-21 09:13:39.659829: step: 504/530, loss: 0.14748725295066833
2023-01-21 09:13:40.808869: step: 508/530, loss: 0.7564055323600769
2023-01-21 09:13:42.058760: step: 512/530, loss: 0.12780657410621643
2023-01-21 09:13:43.243589: step: 516/530, loss: 0.10014358162879944
2023-01-21 09:13:44.403720: step: 520/530, loss: 0.06992387771606445
2023-01-21 09:13:45.602506: step: 524/530, loss: 2.1496894359588623
2023-01-21 09:13:46.802108: step: 528/530, loss: 0.21606865525245667
2023-01-21 09:13:47.990128: step: 532/530, loss: 0.2792799770832062
2023-01-21 09:13:49.159053: step: 536/530, loss: 0.06187028810381889
2023-01-21 09:13:50.369313: step: 540/530, loss: 0.7613747119903564
2023-01-21 09:13:51.571778: step: 544/530, loss: 0.17714548110961914
2023-01-21 09:13:52.776073: step: 548/530, loss: 0.42918330430984497
2023-01-21 09:13:53.993118: step: 552/530, loss: 0.45491230487823486
2023-01-21 09:13:55.195917: step: 556/530, loss: 0.13996772468090057
2023-01-21 09:13:56.343468: step: 560/530, loss: 0.22470645606517792
2023-01-21 09:13:57.494912: step: 564/530, loss: 2.121541976928711
2023-01-21 09:13:58.636980: step: 568/530, loss: 0.4491124749183655
2023-01-21 09:13:59.832291: step: 572/530, loss: 1.3248398303985596
2023-01-21 09:14:00.993658: step: 576/530, loss: 0.17816373705863953
2023-01-21 09:14:02.138700: step: 580/530, loss: 0.1453545093536377
2023-01-21 09:14:03.334985: step: 584/530, loss: 0.6703928112983704
2023-01-21 09:14:04.520480: step: 588/530, loss: 0.6087626218795776
2023-01-21 09:14:05.673717: step: 592/530, loss: 0.21685227751731873
2023-01-21 09:14:06.899394: step: 596/530, loss: 0.8628969192504883
2023-01-21 09:14:08.087459: step: 600/530, loss: 0.15690821409225464
2023-01-21 09:14:09.268163: step: 604/530, loss: 0.0886748805642128
2023-01-21 09:14:10.451897: step: 608/530, loss: 0.4433382749557495
2023-01-21 09:14:11.635623: step: 612/530, loss: 0.10240907967090607
2023-01-21 09:14:12.857965: step: 616/530, loss: 0.1817978024482727
2023-01-21 09:14:14.005677: step: 620/530, loss: 0.05534829944372177
2023-01-21 09:14:15.283665: step: 624/530, loss: 0.19148457050323486
2023-01-21 09:14:16.445487: step: 628/530, loss: 0.06290941685438156
2023-01-21 09:14:17.670321: step: 632/530, loss: 1.065185546875
2023-01-21 09:14:18.844613: step: 636/530, loss: 0.1368924081325531
2023-01-21 09:14:20.008548: step: 640/530, loss: 0.8383713960647583
2023-01-21 09:14:21.201854: step: 644/530, loss: 0.061547040939331055
2023-01-21 09:14:22.390136: step: 648/530, loss: 0.8709843754768372
2023-01-21 09:14:23.552518: step: 652/530, loss: 0.21643005311489105
2023-01-21 09:14:24.727852: step: 656/530, loss: 0.037795353680849075
2023-01-21 09:14:25.885471: step: 660/530, loss: 0.12889054417610168
2023-01-21 09:14:27.037339: step: 664/530, loss: 0.08923659473657608
2023-01-21 09:14:28.185967: step: 668/530, loss: 0.06104845926165581
2023-01-21 09:14:29.356261: step: 672/530, loss: 0.13848777115345
2023-01-21 09:14:30.544250: step: 676/530, loss: 0.44145089387893677
2023-01-21 09:14:31.698478: step: 680/530, loss: 0.07453594356775284
2023-01-21 09:14:32.873494: step: 684/530, loss: 0.1856156885623932
2023-01-21 09:14:34.043618: step: 688/530, loss: 0.2627621591091156
2023-01-21 09:14:35.254121: step: 692/530, loss: 0.4242572784423828
2023-01-21 09:14:36.430190: step: 696/530, loss: 0.1434219479560852
2023-01-21 09:14:37.568023: step: 700/530, loss: 6.147243022918701
2023-01-21 09:14:38.744341: step: 704/530, loss: 0.08329696953296661
2023-01-21 09:14:39.922455: step: 708/530, loss: 0.08801408112049103
2023-01-21 09:14:41.100749: step: 712/530, loss: 0.6760218739509583
2023-01-21 09:14:42.288776: step: 716/530, loss: 0.07385663688182831
2023-01-21 09:14:43.468495: step: 720/530, loss: 1.380645751953125
2023-01-21 09:14:44.662264: step: 724/530, loss: 0.9720660448074341
2023-01-21 09:14:45.841222: step: 728/530, loss: 1.3602497577667236
2023-01-21 09:14:46.999870: step: 732/530, loss: 0.019658852368593216
2023-01-21 09:14:48.167106: step: 736/530, loss: 0.0592009574174881
2023-01-21 09:14:49.349293: step: 740/530, loss: 0.440293550491333
2023-01-21 09:14:50.491074: step: 744/530, loss: 0.042652323842048645
2023-01-21 09:14:51.667830: step: 748/530, loss: 0.29746943712234497
2023-01-21 09:14:52.872603: step: 752/530, loss: 0.11276054382324219
2023-01-21 09:14:54.032842: step: 756/530, loss: 0.08613958954811096
2023-01-21 09:14:55.204868: step: 760/530, loss: 0.8293267488479614
2023-01-21 09:14:56.398855: step: 764/530, loss: 0.43857520818710327
2023-01-21 09:14:57.566625: step: 768/530, loss: 0.11570611596107483
2023-01-21 09:14:58.756766: step: 772/530, loss: 0.0676707774400711
2023-01-21 09:14:59.940190: step: 776/530, loss: 0.16486911475658417
2023-01-21 09:15:01.165541: step: 780/530, loss: 0.1847650408744812
2023-01-21 09:15:02.338064: step: 784/530, loss: 0.3430578112602234
2023-01-21 09:15:03.498196: step: 788/530, loss: 0.13232699036598206
2023-01-21 09:15:04.697203: step: 792/530, loss: 0.07170705497264862
2023-01-21 09:15:05.893621: step: 796/530, loss: 0.20572510361671448
2023-01-21 09:15:07.055222: step: 800/530, loss: 0.3940994143486023
2023-01-21 09:15:08.185809: step: 804/530, loss: 0.05810442194342613
2023-01-21 09:15:09.343275: step: 808/530, loss: 0.7176900506019592
2023-01-21 09:15:10.536047: step: 812/530, loss: 0.2623118460178375
2023-01-21 09:15:11.724460: step: 816/530, loss: 0.14615269005298615
2023-01-21 09:15:12.951370: step: 820/530, loss: 0.9185382127761841
2023-01-21 09:15:14.113086: step: 824/530, loss: 0.10808901488780975
2023-01-21 09:15:15.268611: step: 828/530, loss: 0.04682669788599014
2023-01-21 09:15:16.430399: step: 832/530, loss: 0.11039677262306213
2023-01-21 09:15:17.619149: step: 836/530, loss: 0.7290699481964111
2023-01-21 09:15:18.801879: step: 840/530, loss: 0.3871700167655945
2023-01-21 09:15:19.980580: step: 844/530, loss: 0.11321544647216797
2023-01-21 09:15:21.152654: step: 848/530, loss: 0.35745924711227417
2023-01-21 09:15:22.334305: step: 852/530, loss: 0.1340000182390213
2023-01-21 09:15:23.502712: step: 856/530, loss: 0.12056718021631241
2023-01-21 09:15:24.685841: step: 860/530, loss: 0.11855802685022354
2023-01-21 09:15:25.821619: step: 864/530, loss: 0.20643272995948792
2023-01-21 09:15:27.007139: step: 868/530, loss: 0.10815267264842987
2023-01-21 09:15:28.189569: step: 872/530, loss: 0.2466880828142166
2023-01-21 09:15:29.387619: step: 876/530, loss: 0.18173113465309143
2023-01-21 09:15:30.561775: step: 880/530, loss: 0.1590673327445984
2023-01-21 09:15:31.723284: step: 884/530, loss: 0.06208677217364311
2023-01-21 09:15:32.896122: step: 888/530, loss: 0.7460730671882629
2023-01-21 09:15:34.060154: step: 892/530, loss: 0.2585233747959137
2023-01-21 09:15:35.261848: step: 896/530, loss: 0.4020500183105469
2023-01-21 09:15:36.433395: step: 900/530, loss: 0.1591947078704834
2023-01-21 09:15:37.613631: step: 904/530, loss: 1.4053617715835571
2023-01-21 09:15:38.833538: step: 908/530, loss: 0.1977907121181488
2023-01-21 09:15:40.018659: step: 912/530, loss: 0.012968683615326881
2023-01-21 09:15:41.223187: step: 916/530, loss: 1.5474811792373657
2023-01-21 09:15:42.350011: step: 920/530, loss: 0.12492141127586365
2023-01-21 09:15:43.557913: step: 924/530, loss: 0.5811511874198914
2023-01-21 09:15:44.736506: step: 928/530, loss: 1.5806465148925781
2023-01-21 09:15:45.960660: step: 932/530, loss: 0.3058616518974304
2023-01-21 09:15:47.136954: step: 936/530, loss: 0.4506802558898926
2023-01-21 09:15:48.308107: step: 940/530, loss: 0.10405564308166504
2023-01-21 09:15:49.472046: step: 944/530, loss: 0.15208196640014648
2023-01-21 09:15:50.651892: step: 948/530, loss: 0.20085574686527252
2023-01-21 09:15:51.818257: step: 952/530, loss: 0.6145564317703247
2023-01-21 09:15:53.029339: step: 956/530, loss: 0.23521976172924042
2023-01-21 09:15:54.171308: step: 960/530, loss: 0.11118493229150772
2023-01-21 09:15:55.379849: step: 964/530, loss: 0.62773197889328
2023-01-21 09:15:56.574606: step: 968/530, loss: 0.6872185468673706
2023-01-21 09:15:57.723139: step: 972/530, loss: 0.5629729628562927
2023-01-21 09:15:58.919431: step: 976/530, loss: 0.11141099780797958
2023-01-21 09:16:00.113888: step: 980/530, loss: 0.3977198600769043
2023-01-21 09:16:01.270540: step: 984/530, loss: 0.1435260772705078
2023-01-21 09:16:02.438140: step: 988/530, loss: 0.3222193717956543
2023-01-21 09:16:03.621339: step: 992/530, loss: 0.21869002282619476
2023-01-21 09:16:04.817850: step: 996/530, loss: 1.8919576406478882
2023-01-21 09:16:05.997649: step: 1000/530, loss: 0.09504786133766174
2023-01-21 09:16:07.170684: step: 1004/530, loss: 0.18802037835121155
2023-01-21 09:16:08.368836: step: 1008/530, loss: 0.09015903621912003
2023-01-21 09:16:09.551093: step: 1012/530, loss: 0.36191725730895996
2023-01-21 09:16:10.757218: step: 1016/530, loss: 0.24782609939575195
2023-01-21 09:16:11.959185: step: 1020/530, loss: 0.6134856343269348
2023-01-21 09:16:13.153429: step: 1024/530, loss: 0.10214006900787354
2023-01-21 09:16:14.324349: step: 1028/530, loss: 0.18128728866577148
2023-01-21 09:16:15.509153: step: 1032/530, loss: 0.2213192880153656
2023-01-21 09:16:16.681307: step: 1036/530, loss: 0.15866489708423615
2023-01-21 09:16:17.887004: step: 1040/530, loss: 0.4899576008319855
2023-01-21 09:16:19.076913: step: 1044/530, loss: 0.29335105419158936
2023-01-21 09:16:20.309109: step: 1048/530, loss: 0.2760809361934662
2023-01-21 09:16:21.452243: step: 1052/530, loss: 0.5233360528945923
2023-01-21 09:16:22.626885: step: 1056/530, loss: 5.769775867462158
2023-01-21 09:16:23.839693: step: 1060/530, loss: 0.1736261397600174
2023-01-21 09:16:25.018318: step: 1064/530, loss: 0.3277997076511383
2023-01-21 09:16:26.261810: step: 1068/530, loss: 0.39767369627952576
2023-01-21 09:16:27.437001: step: 1072/530, loss: 0.5014529228210449
2023-01-21 09:16:28.633835: step: 1076/530, loss: 0.061091043055057526
2023-01-21 09:16:29.824862: step: 1080/530, loss: 0.13750171661376953
2023-01-21 09:16:31.021652: step: 1084/530, loss: 0.3384150564670563
2023-01-21 09:16:32.235556: step: 1088/530, loss: 0.7358753681182861
2023-01-21 09:16:33.396764: step: 1092/530, loss: 0.007086849771440029
2023-01-21 09:16:34.555109: step: 1096/530, loss: 0.02338133007287979
2023-01-21 09:16:35.726118: step: 1100/530, loss: 0.05637001991271973
2023-01-21 09:16:36.897390: step: 1104/530, loss: 0.07068271934986115
2023-01-21 09:16:38.049081: step: 1108/530, loss: 0.04919151961803436
2023-01-21 09:16:39.210176: step: 1112/530, loss: 0.09694957733154297
2023-01-21 09:16:40.396011: step: 1116/530, loss: 0.1630798876285553
2023-01-21 09:16:41.571072: step: 1120/530, loss: 0.26954078674316406
2023-01-21 09:16:42.753166: step: 1124/530, loss: 0.059223368763923645
2023-01-21 09:16:43.890109: step: 1128/530, loss: 0.0944088026881218
2023-01-21 09:16:45.076318: step: 1132/530, loss: 0.24949723482131958
2023-01-21 09:16:46.235607: step: 1136/530, loss: 0.3163944482803345
2023-01-21 09:16:47.377117: step: 1140/530, loss: 0.09070412814617157
2023-01-21 09:16:48.544291: step: 1144/530, loss: 0.10538311302661896
2023-01-21 09:16:49.705922: step: 1148/530, loss: 0.7500730156898499
2023-01-21 09:16:50.860996: step: 1152/530, loss: 0.5823000073432922
2023-01-21 09:16:52.024542: step: 1156/530, loss: 0.7672036290168762
2023-01-21 09:16:53.215785: step: 1160/530, loss: 0.8219207525253296
2023-01-21 09:16:54.361044: step: 1164/530, loss: 0.17678271234035492
2023-01-21 09:16:55.545954: step: 1168/530, loss: 0.14983662962913513
2023-01-21 09:16:56.696115: step: 1172/530, loss: 1.63259756565094
2023-01-21 09:16:57.883216: step: 1176/530, loss: 0.02857823483645916
2023-01-21 09:16:59.074886: step: 1180/530, loss: 0.3964815139770508
2023-01-21 09:17:00.253638: step: 1184/530, loss: 0.22624412178993225
2023-01-21 09:17:01.436945: step: 1188/530, loss: 0.12240705639123917
2023-01-21 09:17:02.581746: step: 1192/530, loss: 0.25912541151046753
2023-01-21 09:17:03.732118: step: 1196/530, loss: 0.1371825635433197
2023-01-21 09:17:04.921025: step: 1200/530, loss: 0.12665843963623047
2023-01-21 09:17:06.153568: step: 1204/530, loss: 0.158858984708786
2023-01-21 09:17:07.316244: step: 1208/530, loss: 0.20194588601589203
2023-01-21 09:17:08.502798: step: 1212/530, loss: 0.04982004314661026
2023-01-21 09:17:09.675618: step: 1216/530, loss: 0.10423240810632706
2023-01-21 09:17:10.905892: step: 1220/530, loss: 0.6155378222465515
2023-01-21 09:17:12.069486: step: 1224/530, loss: 0.19012776017189026
2023-01-21 09:17:13.263038: step: 1228/530, loss: 0.4747328758239746
2023-01-21 09:17:14.464969: step: 1232/530, loss: 0.06692662835121155
2023-01-21 09:17:15.653150: step: 1236/530, loss: 0.12054071575403214
2023-01-21 09:17:16.817068: step: 1240/530, loss: 0.08538446575403214
2023-01-21 09:17:17.977498: step: 1244/530, loss: 0.04577126353979111
2023-01-21 09:17:19.144008: step: 1248/530, loss: 0.6697562336921692
2023-01-21 09:17:20.349121: step: 1252/530, loss: 0.30219078063964844
2023-01-21 09:17:21.529200: step: 1256/530, loss: 2.5943663120269775
2023-01-21 09:17:22.707273: step: 1260/530, loss: 0.663166880607605
2023-01-21 09:17:23.871611: step: 1264/530, loss: 1.2769330739974976
2023-01-21 09:17:25.031484: step: 1268/530, loss: 0.0529206246137619
2023-01-21 09:17:26.203892: step: 1272/530, loss: 0.6857399940490723
2023-01-21 09:17:27.376581: step: 1276/530, loss: 0.4165101945400238
2023-01-21 09:17:28.570391: step: 1280/530, loss: 0.055531978607177734
2023-01-21 09:17:29.716196: step: 1284/530, loss: 0.02820272371172905
2023-01-21 09:17:30.912847: step: 1288/530, loss: 0.11238012462854385
2023-01-21 09:17:32.110301: step: 1292/530, loss: 0.31934604048728943
2023-01-21 09:17:33.282593: step: 1296/530, loss: 0.5369474291801453
2023-01-21 09:17:34.464746: step: 1300/530, loss: 0.5376827120780945
2023-01-21 09:17:35.646270: step: 1304/530, loss: 0.1251607984304428
2023-01-21 09:17:36.778353: step: 1308/530, loss: 0.4383469521999359
2023-01-21 09:17:37.997049: step: 1312/530, loss: 0.210774764418602
2023-01-21 09:17:39.168857: step: 1316/530, loss: 0.1215600073337555
2023-01-21 09:17:40.341178: step: 1320/530, loss: 0.09589624404907227
2023-01-21 09:17:41.521990: step: 1324/530, loss: 0.09111233055591583
2023-01-21 09:17:42.695439: step: 1328/530, loss: 0.5435773730278015
2023-01-21 09:17:43.850184: step: 1332/530, loss: 0.17810040712356567
2023-01-21 09:17:45.057496: step: 1336/530, loss: 0.12381229549646378
2023-01-21 09:17:46.248263: step: 1340/530, loss: 0.23709706962108612
2023-01-21 09:17:47.410404: step: 1344/530, loss: 0.5032418370246887
2023-01-21 09:17:48.586095: step: 1348/530, loss: 0.12311534583568573
2023-01-21 09:17:49.793858: step: 1352/530, loss: 0.06642594933509827
2023-01-21 09:17:50.971355: step: 1356/530, loss: 0.5493218302726746
2023-01-21 09:17:52.148411: step: 1360/530, loss: 0.35551726818084717
2023-01-21 09:17:53.344309: step: 1364/530, loss: 0.9286425113677979
2023-01-21 09:17:54.588919: step: 1368/530, loss: 0.1363869607448578
2023-01-21 09:17:55.766410: step: 1372/530, loss: 0.3926301896572113
2023-01-21 09:17:56.953217: step: 1376/530, loss: 0.07898598909378052
2023-01-21 09:17:58.121123: step: 1380/530, loss: 0.10672781616449356
2023-01-21 09:17:59.299646: step: 1384/530, loss: 0.1182304322719574
2023-01-21 09:18:00.515421: step: 1388/530, loss: 0.1244884580373764
2023-01-21 09:18:01.689262: step: 1392/530, loss: 0.05201368406414986
2023-01-21 09:18:02.850423: step: 1396/530, loss: 0.9493787884712219
2023-01-21 09:18:04.050129: step: 1400/530, loss: 0.24087773263454437
2023-01-21 09:18:05.197192: step: 1404/530, loss: 0.1619156301021576
2023-01-21 09:18:06.367116: step: 1408/530, loss: 0.9481672048568726
2023-01-21 09:18:07.550122: step: 1412/530, loss: 3.5004217624664307
2023-01-21 09:18:08.719069: step: 1416/530, loss: 0.4147112965583801
2023-01-21 09:18:09.926964: step: 1420/530, loss: 0.46288469433784485
2023-01-21 09:18:11.124757: step: 1424/530, loss: 0.23620863258838654
2023-01-21 09:18:12.333291: step: 1428/530, loss: 0.7061934471130371
2023-01-21 09:18:13.495437: step: 1432/530, loss: 0.194000244140625
2023-01-21 09:18:14.658670: step: 1436/530, loss: 0.1050286814570427
2023-01-21 09:18:15.821692: step: 1440/530, loss: 3.008226156234741
2023-01-21 09:18:16.984121: step: 1444/530, loss: 0.10117876529693604
2023-01-21 09:18:18.157695: step: 1448/530, loss: 0.5418194532394409
2023-01-21 09:18:19.325642: step: 1452/530, loss: 0.34288740158081055
2023-01-21 09:18:20.514879: step: 1456/530, loss: 0.12918530404567719
2023-01-21 09:18:21.699320: step: 1460/530, loss: 0.11440548300743103
2023-01-21 09:18:22.929165: step: 1464/530, loss: 0.2064371109008789
2023-01-21 09:18:24.096846: step: 1468/530, loss: 0.14081747829914093
2023-01-21 09:18:25.277335: step: 1472/530, loss: 0.3588187098503113
2023-01-21 09:18:26.519416: step: 1476/530, loss: 0.29937463998794556
2023-01-21 09:18:27.780303: step: 1480/530, loss: 0.7840123772621155
2023-01-21 09:18:28.987740: step: 1484/530, loss: 0.22346076369285583
2023-01-21 09:18:30.192796: step: 1488/530, loss: 0.06924515217542648
2023-01-21 09:18:31.403453: step: 1492/530, loss: 0.12561869621276855
2023-01-21 09:18:32.643108: step: 1496/530, loss: 0.1489323526620865
2023-01-21 09:18:33.820470: step: 1500/530, loss: 0.13118305802345276
2023-01-21 09:18:35.030529: step: 1504/530, loss: 0.23313789069652557
2023-01-21 09:18:36.204176: step: 1508/530, loss: 0.7606579065322876
2023-01-21 09:18:37.392490: step: 1512/530, loss: 0.11915197968482971
2023-01-21 09:18:38.570516: step: 1516/530, loss: 0.20468683540821075
2023-01-21 09:18:39.743046: step: 1520/530, loss: 0.6620468497276306
2023-01-21 09:18:40.891670: step: 1524/530, loss: 0.425516813993454
2023-01-21 09:18:42.074418: step: 1528/530, loss: 0.1416490077972412
2023-01-21 09:18:43.252389: step: 1532/530, loss: 0.08876609802246094
2023-01-21 09:18:44.450087: step: 1536/530, loss: 0.8533191084861755
2023-01-21 09:18:45.614120: step: 1540/530, loss: 0.5719424486160278
2023-01-21 09:18:46.793467: step: 1544/530, loss: 0.09907753765583038
2023-01-21 09:18:47.968641: step: 1548/530, loss: 0.5311188101768494
2023-01-21 09:18:49.187916: step: 1552/530, loss: 0.15549631416797638
2023-01-21 09:18:50.344577: step: 1556/530, loss: 0.11470623314380646
2023-01-21 09:18:51.526614: step: 1560/530, loss: 0.41116294264793396
2023-01-21 09:18:52.684884: step: 1564/530, loss: 0.03378927707672119
2023-01-21 09:18:53.855476: step: 1568/530, loss: 0.16743439435958862
2023-01-21 09:18:54.996204: step: 1572/530, loss: 0.8020839095115662
2023-01-21 09:18:56.208917: step: 1576/530, loss: 1.9527747631072998
2023-01-21 09:18:57.448727: step: 1580/530, loss: 0.7834170460700989
2023-01-21 09:18:58.628466: step: 1584/530, loss: 2.078089475631714
2023-01-21 09:18:59.784561: step: 1588/530, loss: 4.242259979248047
2023-01-21 09:19:00.983255: step: 1592/530, loss: 0.2521018981933594
2023-01-21 09:19:02.232483: step: 1596/530, loss: 0.8832618594169617
2023-01-21 09:19:03.394682: step: 1600/530, loss: 0.10305547714233398
2023-01-21 09:19:04.614844: step: 1604/530, loss: 0.5106960535049438
2023-01-21 09:19:05.783703: step: 1608/530, loss: 0.5067201256752014
2023-01-21 09:19:06.985254: step: 1612/530, loss: 0.11851165443658829
2023-01-21 09:19:08.163677: step: 1616/530, loss: 0.3757248818874359
2023-01-21 09:19:09.360862: step: 1620/530, loss: 0.1681934893131256
2023-01-21 09:19:10.577684: step: 1624/530, loss: 0.18481120467185974
2023-01-21 09:19:11.782267: step: 1628/530, loss: 0.25032997131347656
2023-01-21 09:19:12.992525: step: 1632/530, loss: 0.3608000874519348
2023-01-21 09:19:14.179304: step: 1636/530, loss: 0.07576942443847656
2023-01-21 09:19:15.381447: step: 1640/530, loss: 0.0660221129655838
2023-01-21 09:19:16.562316: step: 1644/530, loss: 0.7730379104614258
2023-01-21 09:19:17.751030: step: 1648/530, loss: 0.09511657059192657
2023-01-21 09:19:18.914253: step: 1652/530, loss: 0.14469321072101593
2023-01-21 09:19:20.121322: step: 1656/530, loss: 0.2972152829170227
2023-01-21 09:19:21.341533: step: 1660/530, loss: 0.26963576674461365
2023-01-21 09:19:22.592935: step: 1664/530, loss: 0.22328528761863708
2023-01-21 09:19:23.735035: step: 1668/530, loss: 0.13425616919994354
2023-01-21 09:19:24.927943: step: 1672/530, loss: 0.6168160438537598
2023-01-21 09:19:26.092998: step: 1676/530, loss: 0.1291390359401703
2023-01-21 09:19:27.303877: step: 1680/530, loss: 0.23894159495830536
2023-01-21 09:19:28.469790: step: 1684/530, loss: 0.2600872218608856
2023-01-21 09:19:29.644785: step: 1688/530, loss: 0.0597049742937088
2023-01-21 09:19:30.851472: step: 1692/530, loss: 0.5511213541030884
2023-01-21 09:19:32.030831: step: 1696/530, loss: 0.20396548509597778
2023-01-21 09:19:33.213361: step: 1700/530, loss: 0.4653128683567047
2023-01-21 09:19:34.387762: step: 1704/530, loss: 0.188886359333992
2023-01-21 09:19:35.544438: step: 1708/530, loss: 0.18251438438892365
2023-01-21 09:19:36.720598: step: 1712/530, loss: 0.7329471707344055
2023-01-21 09:19:37.942304: step: 1716/530, loss: 0.20204153656959534
2023-01-21 09:19:39.140218: step: 1720/530, loss: 0.14072594046592712
2023-01-21 09:19:40.284271: step: 1724/530, loss: 0.037955284118652344
2023-01-21 09:19:41.446900: step: 1728/530, loss: 0.20351390540599823
2023-01-21 09:19:42.622004: step: 1732/530, loss: 0.06529121100902557
2023-01-21 09:19:43.827113: step: 1736/530, loss: 0.21798400580883026
2023-01-21 09:19:45.002652: step: 1740/530, loss: 0.08946972340345383
2023-01-21 09:19:46.190985: step: 1744/530, loss: 0.05043621361255646
2023-01-21 09:19:47.376242: step: 1748/530, loss: 1.1845881938934326
2023-01-21 09:19:48.546601: step: 1752/530, loss: 0.29368191957473755
2023-01-21 09:19:49.804810: step: 1756/530, loss: 0.11359748989343643
2023-01-21 09:19:50.996419: step: 1760/530, loss: 0.052796266973018646
2023-01-21 09:19:52.156088: step: 1764/530, loss: 0.14209671318531036
2023-01-21 09:19:53.350684: step: 1768/530, loss: 0.22507619857788086
2023-01-21 09:19:54.529443: step: 1772/530, loss: 0.07884450256824493
2023-01-21 09:19:55.734655: step: 1776/530, loss: 0.6319993734359741
2023-01-21 09:19:56.935769: step: 1780/530, loss: 0.18795561790466309
2023-01-21 09:19:58.129305: step: 1784/530, loss: 1.055540919303894
2023-01-21 09:19:59.309856: step: 1788/530, loss: 0.12289538979530334
2023-01-21 09:20:00.484746: step: 1792/530, loss: 0.08245712518692017
2023-01-21 09:20:01.659047: step: 1796/530, loss: 0.15867328643798828
2023-01-21 09:20:02.871644: step: 1800/530, loss: 3.0935540199279785
2023-01-21 09:20:04.044574: step: 1804/530, loss: 0.09221392124891281
2023-01-21 09:20:05.208391: step: 1808/530, loss: 0.11634808033704758
2023-01-21 09:20:06.358789: step: 1812/530, loss: 0.24961858987808228
2023-01-21 09:20:07.511240: step: 1816/530, loss: 0.09525594860315323
2023-01-21 09:20:08.686781: step: 1820/530, loss: 0.05817709118127823
2023-01-21 09:20:09.823018: step: 1824/530, loss: 0.1496649831533432
2023-01-21 09:20:11.017075: step: 1828/530, loss: 0.5378350019454956
2023-01-21 09:20:12.224706: step: 1832/530, loss: 0.49689018726348877
2023-01-21 09:20:13.449668: step: 1836/530, loss: 0.3616853654384613
2023-01-21 09:20:14.634675: step: 1840/530, loss: 0.1608024686574936
2023-01-21 09:20:15.809035: step: 1844/530, loss: 2.896019220352173
2023-01-21 09:20:16.986569: step: 1848/530, loss: 0.09119803458452225
2023-01-21 09:20:18.148752: step: 1852/530, loss: 0.8853521347045898
2023-01-21 09:20:19.336011: step: 1856/530, loss: 0.12750062346458435
2023-01-21 09:20:20.498509: step: 1860/530, loss: 0.10769052803516388
2023-01-21 09:20:21.708889: step: 1864/530, loss: 0.28071194887161255
2023-01-21 09:20:22.888380: step: 1868/530, loss: 0.20003385841846466
2023-01-21 09:20:24.100603: step: 1872/530, loss: 0.15764674544334412
2023-01-21 09:20:25.286761: step: 1876/530, loss: 0.0467165932059288
2023-01-21 09:20:26.479135: step: 1880/530, loss: 0.10866604000329971
2023-01-21 09:20:27.644514: step: 1884/530, loss: 0.06531929969787598
2023-01-21 09:20:28.835744: step: 1888/530, loss: 0.4032400846481323
2023-01-21 09:20:30.058232: step: 1892/530, loss: 1.275505781173706
2023-01-21 09:20:31.230264: step: 1896/530, loss: 0.09643135219812393
2023-01-21 09:20:32.401846: step: 1900/530, loss: 0.24523526430130005
2023-01-21 09:20:33.559722: step: 1904/530, loss: 0.6152757406234741
2023-01-21 09:20:34.761992: step: 1908/530, loss: 0.12115345895290375
2023-01-21 09:20:35.963922: step: 1912/530, loss: 0.4646051526069641
2023-01-21 09:20:37.149663: step: 1916/530, loss: 0.26571282744407654
2023-01-21 09:20:38.338817: step: 1920/530, loss: 4.496382236480713
2023-01-21 09:20:39.564602: step: 1924/530, loss: 0.2892496883869171
2023-01-21 09:20:40.767851: step: 1928/530, loss: 0.04979410022497177
2023-01-21 09:20:41.954899: step: 1932/530, loss: 0.15090861916542053
2023-01-21 09:20:43.128177: step: 1936/530, loss: 2.8883774280548096
2023-01-21 09:20:44.305872: step: 1940/530, loss: 0.5007055401802063
2023-01-21 09:20:45.491371: step: 1944/530, loss: 0.1410520076751709
2023-01-21 09:20:46.619680: step: 1948/530, loss: 0.10281658172607422
2023-01-21 09:20:47.809747: step: 1952/530, loss: 0.39216700196266174
2023-01-21 09:20:49.021554: step: 1956/530, loss: 0.07823190093040466
2023-01-21 09:20:50.211114: step: 1960/530, loss: 0.11733589321374893
2023-01-21 09:20:51.384250: step: 1964/530, loss: 0.42570310831069946
2023-01-21 09:20:52.560613: step: 1968/530, loss: 0.46419888734817505
2023-01-21 09:20:53.748907: step: 1972/530, loss: 0.8393044471740723
2023-01-21 09:20:54.921288: step: 1976/530, loss: 0.14136143028736115
2023-01-21 09:20:56.090211: step: 1980/530, loss: 0.06731953471899033
2023-01-21 09:20:57.271300: step: 1984/530, loss: 0.2783690392971039
2023-01-21 09:20:58.460643: step: 1988/530, loss: 0.27179956436157227
2023-01-21 09:20:59.676855: step: 1992/530, loss: 0.3230404853820801
2023-01-21 09:21:00.821793: step: 1996/530, loss: 0.25934526324272156
2023-01-21 09:21:01.980473: step: 2000/530, loss: 0.19412866234779358
2023-01-21 09:21:03.166752: step: 2004/530, loss: 0.15328970551490784
2023-01-21 09:21:04.367197: step: 2008/530, loss: 0.08714685589075089
2023-01-21 09:21:05.566857: step: 2012/530, loss: 0.2520124316215515
2023-01-21 09:21:06.743570: step: 2016/530, loss: 0.09703502804040909
2023-01-21 09:21:07.902950: step: 2020/530, loss: 0.09186959266662598
2023-01-21 09:21:09.116280: step: 2024/530, loss: 0.08249416947364807
2023-01-21 09:21:10.322511: step: 2028/530, loss: 0.13058285415172577
2023-01-21 09:21:11.572980: step: 2032/530, loss: 0.31086570024490356
2023-01-21 09:21:12.706149: step: 2036/530, loss: 0.15235500037670135
2023-01-21 09:21:13.863641: step: 2040/530, loss: 0.04193000867962837
2023-01-21 09:21:15.094885: step: 2044/530, loss: 0.14625893533229828
2023-01-21 09:21:16.256281: step: 2048/530, loss: 0.2028767615556717
2023-01-21 09:21:17.389068: step: 2052/530, loss: 0.09789669513702393
2023-01-21 09:21:18.562980: step: 2056/530, loss: 0.9054768681526184
2023-01-21 09:21:19.711331: step: 2060/530, loss: 0.2827209234237671
2023-01-21 09:21:20.894995: step: 2064/530, loss: 0.10104601085186005
2023-01-21 09:21:22.097462: step: 2068/530, loss: 0.8684676289558411
2023-01-21 09:21:23.276224: step: 2072/530, loss: 0.8356946706771851
2023-01-21 09:21:24.461711: step: 2076/530, loss: 0.6887723803520203
2023-01-21 09:21:25.684269: step: 2080/530, loss: 0.08993025124073029
2023-01-21 09:21:26.872315: step: 2084/530, loss: 0.13519316911697388
2023-01-21 09:21:28.036629: step: 2088/530, loss: 0.17611093819141388
2023-01-21 09:21:29.217971: step: 2092/530, loss: 0.03232526034116745
2023-01-21 09:21:30.410127: step: 2096/530, loss: 0.4869275987148285
2023-01-21 09:21:31.643844: step: 2100/530, loss: 0.20564980804920197
2023-01-21 09:21:32.784070: step: 2104/530, loss: 0.2366410344839096
2023-01-21 09:21:33.991890: step: 2108/530, loss: 0.05308065563440323
2023-01-21 09:21:35.131192: step: 2112/530, loss: 0.18364979326725006
2023-01-21 09:21:36.317459: step: 2116/530, loss: 0.3367350697517395
2023-01-21 09:21:37.494995: step: 2120/530, loss: 0.7386298179626465
==================================================
Loss: 0.393
--------------------
Dev: {'event': {'p': 0.4911816578483245, 'r': 0.7416777629826897, 'f1': 0.5909814323607426}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6182416549130231, 'r': 0.7561817136285222, 'f1': 0.6802897051215727}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.4270833333333333, 'r': 0.7592592592592593, 'f1': 0.5466666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6065573770491803, 'r': 0.5873015873015873, 'f1': 0.5967741935483871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.4339622641509434, 'r': 0.6388888888888888, 'f1': 0.5168539325842696}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:22:21.505007: step: 4/530, loss: 0.3395237922668457
2023-01-21 09:22:22.678803: step: 8/530, loss: 0.14292305707931519
2023-01-21 09:22:23.875283: step: 12/530, loss: 0.048886489123106
2023-01-21 09:22:25.051297: step: 16/530, loss: 0.20861344039440155
2023-01-21 09:22:26.239034: step: 20/530, loss: 0.6296416521072388
2023-01-21 09:22:27.428951: step: 24/530, loss: 0.061091139912605286
2023-01-21 09:22:28.610895: step: 28/530, loss: 0.15461082756519318
2023-01-21 09:22:29.784358: step: 32/530, loss: 0.1430390328168869
2023-01-21 09:22:30.975163: step: 36/530, loss: 0.1796915978193283
2023-01-21 09:22:32.118178: step: 40/530, loss: 0.06257183849811554
2023-01-21 09:22:33.333952: step: 44/530, loss: 0.4593068063259125
2023-01-21 09:22:34.535308: step: 48/530, loss: 0.10563822090625763
2023-01-21 09:22:35.700106: step: 52/530, loss: 0.02028479613363743
2023-01-21 09:22:36.853018: step: 56/530, loss: 0.12357921898365021
2023-01-21 09:22:38.069390: step: 60/530, loss: 1.264628529548645
2023-01-21 09:22:39.258116: step: 64/530, loss: 0.3385503888130188
2023-01-21 09:22:40.459899: step: 68/530, loss: 0.08072176575660706
2023-01-21 09:22:41.656597: step: 72/530, loss: 0.20088501274585724
2023-01-21 09:22:42.851022: step: 76/530, loss: 0.04902315139770508
2023-01-21 09:22:44.025786: step: 80/530, loss: 0.033776093274354935
2023-01-21 09:22:45.164400: step: 84/530, loss: 0.10752268135547638
2023-01-21 09:22:46.360655: step: 88/530, loss: 0.5273001790046692
2023-01-21 09:22:47.549621: step: 92/530, loss: 0.22938717901706696
2023-01-21 09:22:48.736585: step: 96/530, loss: 0.3376498222351074
2023-01-21 09:22:49.922370: step: 100/530, loss: 0.3076295852661133
2023-01-21 09:22:51.109525: step: 104/530, loss: 0.07853376865386963
2023-01-21 09:22:52.282326: step: 108/530, loss: 0.17330913245677948
2023-01-21 09:22:53.469815: step: 112/530, loss: 0.8449240326881409
2023-01-21 09:22:54.671983: step: 116/530, loss: 0.12833939492702484
2023-01-21 09:22:55.889052: step: 120/530, loss: 0.7335178852081299
2023-01-21 09:22:57.077199: step: 124/530, loss: 0.1502002775669098
2023-01-21 09:22:58.227114: step: 128/530, loss: 0.3265603184700012
2023-01-21 09:22:59.414687: step: 132/530, loss: 0.09195976704359055
2023-01-21 09:23:00.585869: step: 136/530, loss: 0.11156454682350159
2023-01-21 09:23:01.716637: step: 140/530, loss: 0.8290325999259949
2023-01-21 09:23:02.918455: step: 144/530, loss: 0.11049118638038635
2023-01-21 09:23:04.085868: step: 148/530, loss: 0.17406292259693146
2023-01-21 09:23:05.263492: step: 152/530, loss: 0.08609409630298615
2023-01-21 09:23:06.486432: step: 156/530, loss: 0.3714890480041504
2023-01-21 09:23:07.661288: step: 160/530, loss: 0.355594277381897
2023-01-21 09:23:08.832742: step: 164/530, loss: 0.39681756496429443
2023-01-21 09:23:09.995311: step: 168/530, loss: 0.41215306520462036
2023-01-21 09:23:11.181216: step: 172/530, loss: 0.028958607465028763
2023-01-21 09:23:12.393737: step: 176/530, loss: 0.23906210064888
2023-01-21 09:23:13.537407: step: 180/530, loss: 0.0642690658569336
2023-01-21 09:23:14.750767: step: 184/530, loss: 0.024057675153017044
2023-01-21 09:23:15.939722: step: 188/530, loss: 0.19297924637794495
2023-01-21 09:23:17.119279: step: 192/530, loss: 0.26505905389785767
2023-01-21 09:23:18.267479: step: 196/530, loss: 0.10772333294153214
2023-01-21 09:23:19.475899: step: 200/530, loss: 0.19438190758228302
2023-01-21 09:23:20.670843: step: 204/530, loss: 0.13568845391273499
2023-01-21 09:23:21.832630: step: 208/530, loss: 0.06396003067493439
2023-01-21 09:23:23.035500: step: 212/530, loss: 0.1592452973127365
2023-01-21 09:23:24.195062: step: 216/530, loss: 0.22247348725795746
2023-01-21 09:23:25.357448: step: 220/530, loss: 0.10000196099281311
2023-01-21 09:23:26.544319: step: 224/530, loss: 0.13718347251415253
2023-01-21 09:23:27.748148: step: 228/530, loss: 0.23773781955242157
2023-01-21 09:23:28.922842: step: 232/530, loss: 0.09083373844623566
2023-01-21 09:23:30.083349: step: 236/530, loss: 0.16300687193870544
2023-01-21 09:23:31.292686: step: 240/530, loss: 0.732474148273468
2023-01-21 09:23:32.426379: step: 244/530, loss: 0.33389195799827576
2023-01-21 09:23:33.594821: step: 248/530, loss: 0.07171668857336044
2023-01-21 09:23:34.778656: step: 252/530, loss: 0.09313421696424484
2023-01-21 09:23:35.966001: step: 256/530, loss: 2.2392632961273193
2023-01-21 09:23:37.171013: step: 260/530, loss: 0.23304367065429688
2023-01-21 09:23:38.338999: step: 264/530, loss: 0.049810029566287994
2023-01-21 09:23:39.491605: step: 268/530, loss: 0.2002248764038086
2023-01-21 09:23:40.649814: step: 272/530, loss: 0.034461118280887604
2023-01-21 09:23:41.834794: step: 276/530, loss: 0.37291058897972107
2023-01-21 09:23:43.006604: step: 280/530, loss: 0.16013050079345703
2023-01-21 09:23:44.147716: step: 284/530, loss: 0.322002649307251
2023-01-21 09:23:45.353078: step: 288/530, loss: 0.09548010677099228
2023-01-21 09:23:46.567258: step: 292/530, loss: 0.08332128822803497
2023-01-21 09:23:47.727336: step: 296/530, loss: 0.6049390435218811
2023-01-21 09:23:48.863794: step: 300/530, loss: 0.05335254594683647
2023-01-21 09:23:50.063838: step: 304/530, loss: 0.079053595662117
2023-01-21 09:23:51.229379: step: 308/530, loss: 0.18881192803382874
2023-01-21 09:23:52.403387: step: 312/530, loss: 0.04599170759320259
2023-01-21 09:23:53.600834: step: 316/530, loss: 0.11059131473302841
2023-01-21 09:23:54.802594: step: 320/530, loss: 0.08553659915924072
2023-01-21 09:23:55.991386: step: 324/530, loss: 0.05937357246875763
2023-01-21 09:23:57.187109: step: 328/530, loss: 0.15882810950279236
2023-01-21 09:23:58.392120: step: 332/530, loss: 0.09655638039112091
2023-01-21 09:23:59.553087: step: 336/530, loss: 0.01138682384043932
2023-01-21 09:24:00.725328: step: 340/530, loss: 0.0339818000793457
2023-01-21 09:24:01.912617: step: 344/530, loss: 0.04507635906338692
2023-01-21 09:24:03.098615: step: 348/530, loss: 0.06207151710987091
2023-01-21 09:24:04.266268: step: 352/530, loss: 0.04459104686975479
2023-01-21 09:24:05.494993: step: 356/530, loss: 0.4275591969490051
2023-01-21 09:24:06.704328: step: 360/530, loss: 0.08763594925403595
2023-01-21 09:24:07.869368: step: 364/530, loss: 0.2645406723022461
2023-01-21 09:24:09.097097: step: 368/530, loss: 0.11387267708778381
2023-01-21 09:24:10.289180: step: 372/530, loss: 1.3267130851745605
2023-01-21 09:24:11.486458: step: 376/530, loss: 0.5971904993057251
2023-01-21 09:24:12.657071: step: 380/530, loss: 0.18387582898139954
2023-01-21 09:24:13.878954: step: 384/530, loss: 1.6609737873077393
2023-01-21 09:24:15.065345: step: 388/530, loss: 0.03179154545068741
2023-01-21 09:24:16.278569: step: 392/530, loss: 0.1436682641506195
2023-01-21 09:24:17.466623: step: 396/530, loss: 0.15617981553077698
2023-01-21 09:24:18.646100: step: 400/530, loss: 0.09733657538890839
2023-01-21 09:24:19.844062: step: 404/530, loss: 0.49601441621780396
2023-01-21 09:24:20.986672: step: 408/530, loss: 0.2796943783760071
2023-01-21 09:24:22.171182: step: 412/530, loss: 0.1823309063911438
2023-01-21 09:24:23.387934: step: 416/530, loss: 0.08819971233606339
2023-01-21 09:24:24.578693: step: 420/530, loss: 0.15318146347999573
2023-01-21 09:24:25.737851: step: 424/530, loss: 0.022849464789032936
2023-01-21 09:24:26.912878: step: 428/530, loss: 1.4256436824798584
2023-01-21 09:24:28.085467: step: 432/530, loss: 0.19760262966156006
2023-01-21 09:24:29.269902: step: 436/530, loss: 2.434588670730591
2023-01-21 09:24:30.451001: step: 440/530, loss: 0.1771283745765686
2023-01-21 09:24:31.633319: step: 444/530, loss: 0.06708145141601562
2023-01-21 09:24:32.805755: step: 448/530, loss: 0.9383450746536255
2023-01-21 09:24:34.048568: step: 452/530, loss: 0.04250223934650421
2023-01-21 09:24:35.243749: step: 456/530, loss: 0.07037639617919922
2023-01-21 09:24:36.412086: step: 460/530, loss: 0.1599535048007965
2023-01-21 09:24:37.607288: step: 464/530, loss: 0.05111327022314072
2023-01-21 09:24:38.779800: step: 468/530, loss: 0.6414703130722046
2023-01-21 09:24:39.931218: step: 472/530, loss: 0.10155753791332245
2023-01-21 09:24:41.120377: step: 476/530, loss: 1.2062379121780396
2023-01-21 09:24:42.331617: step: 480/530, loss: 0.1793156862258911
2023-01-21 09:24:43.487179: step: 484/530, loss: 0.08800821006298065
2023-01-21 09:24:44.640146: step: 488/530, loss: 0.12793751060962677
2023-01-21 09:24:45.822143: step: 492/530, loss: 0.17777720093727112
2023-01-21 09:24:47.036533: step: 496/530, loss: 0.8173092007637024
2023-01-21 09:24:48.203750: step: 500/530, loss: 0.38279443979263306
2023-01-21 09:24:49.402547: step: 504/530, loss: 0.9181571006774902
2023-01-21 09:24:50.602456: step: 508/530, loss: 0.348619282245636
2023-01-21 09:24:51.790765: step: 512/530, loss: 0.20670852065086365
2023-01-21 09:24:52.952048: step: 516/530, loss: 0.33444374799728394
2023-01-21 09:24:54.119336: step: 520/530, loss: 0.1402256190776825
2023-01-21 09:24:55.295530: step: 524/530, loss: 0.08646586537361145
2023-01-21 09:24:56.470163: step: 528/530, loss: 0.35968017578125
2023-01-21 09:24:57.677324: step: 532/530, loss: 0.126338392496109
2023-01-21 09:24:58.905801: step: 536/530, loss: 0.3286783993244171
2023-01-21 09:25:00.102135: step: 540/530, loss: 0.04582090675830841
2023-01-21 09:25:01.251360: step: 544/530, loss: 0.12755991518497467
2023-01-21 09:25:02.435072: step: 548/530, loss: 0.3362697660923004
2023-01-21 09:25:03.644453: step: 552/530, loss: 0.08193187415599823
2023-01-21 09:25:04.861647: step: 556/530, loss: 0.3838282823562622
2023-01-21 09:25:06.013251: step: 560/530, loss: 0.2041710913181305
2023-01-21 09:25:07.163380: step: 564/530, loss: 0.3233398497104645
2023-01-21 09:25:08.394067: step: 568/530, loss: 0.6178305149078369
2023-01-21 09:25:09.573979: step: 572/530, loss: 0.07716178894042969
2023-01-21 09:25:10.768832: step: 576/530, loss: 0.41793808341026306
2023-01-21 09:25:12.028798: step: 580/530, loss: 0.3867012858390808
2023-01-21 09:25:13.214122: step: 584/530, loss: 0.06379709392786026
2023-01-21 09:25:14.416164: step: 588/530, loss: 0.1727897673845291
2023-01-21 09:25:15.612728: step: 592/530, loss: 0.10468115657567978
2023-01-21 09:25:16.806296: step: 596/530, loss: 0.0640813335776329
2023-01-21 09:25:17.995020: step: 600/530, loss: 0.4098457396030426
2023-01-21 09:25:19.183397: step: 604/530, loss: 0.08113507926464081
2023-01-21 09:25:20.348522: step: 608/530, loss: 0.6113743185997009
2023-01-21 09:25:21.527302: step: 612/530, loss: 0.30175554752349854
2023-01-21 09:25:22.706385: step: 616/530, loss: 0.0978919044137001
2023-01-21 09:25:23.931365: step: 620/530, loss: 0.06678323447704315
2023-01-21 09:25:25.111469: step: 624/530, loss: 0.5544461607933044
2023-01-21 09:25:26.277978: step: 628/530, loss: 0.24039077758789062
2023-01-21 09:25:27.489179: step: 632/530, loss: 0.013257504440844059
2023-01-21 09:25:28.683793: step: 636/530, loss: 0.27228212356567383
2023-01-21 09:25:29.868999: step: 640/530, loss: 0.1346491426229477
2023-01-21 09:25:31.094891: step: 644/530, loss: 0.46833497285842896
2023-01-21 09:25:32.251457: step: 648/530, loss: 0.07121892273426056
2023-01-21 09:25:33.397272: step: 652/530, loss: 0.1012469157576561
2023-01-21 09:25:34.596919: step: 656/530, loss: 0.690554141998291
2023-01-21 09:25:35.738660: step: 660/530, loss: 0.07158022373914719
2023-01-21 09:25:36.988223: step: 664/530, loss: 0.3830791115760803
2023-01-21 09:25:38.157883: step: 668/530, loss: 0.19862011075019836
2023-01-21 09:25:39.368486: step: 672/530, loss: 0.08588233590126038
2023-01-21 09:25:40.601365: step: 676/530, loss: 0.3338552415370941
2023-01-21 09:25:41.779519: step: 680/530, loss: 0.1229274719953537
2023-01-21 09:25:42.996199: step: 684/530, loss: 0.07652473449707031
2023-01-21 09:25:44.174962: step: 688/530, loss: 0.07457561790943146
2023-01-21 09:25:45.324684: step: 692/530, loss: 0.7510537505149841
2023-01-21 09:25:46.506903: step: 696/530, loss: 0.4571743905544281
2023-01-21 09:25:47.675447: step: 700/530, loss: 0.07020358741283417
2023-01-21 09:25:48.819200: step: 704/530, loss: 0.1106594130396843
2023-01-21 09:25:49.973398: step: 708/530, loss: 0.07189307361841202
2023-01-21 09:25:51.167770: step: 712/530, loss: 0.06367425620555878
2023-01-21 09:25:52.328354: step: 716/530, loss: 0.1598864197731018
2023-01-21 09:25:53.560827: step: 720/530, loss: 0.8086475133895874
2023-01-21 09:25:54.749707: step: 724/530, loss: 0.07574215531349182
2023-01-21 09:25:55.931667: step: 728/530, loss: 0.08137140423059464
2023-01-21 09:25:57.107666: step: 732/530, loss: 0.09217134118080139
2023-01-21 09:25:58.279537: step: 736/530, loss: 0.06056032329797745
2023-01-21 09:25:59.477480: step: 740/530, loss: 0.3768518567085266
2023-01-21 09:26:00.673381: step: 744/530, loss: 0.0956578478217125
2023-01-21 09:26:01.839104: step: 748/530, loss: 0.5609469413757324
2023-01-21 09:26:03.064404: step: 752/530, loss: 0.1131909117102623
2023-01-21 09:26:04.255509: step: 756/530, loss: 0.2542285919189453
2023-01-21 09:26:05.417887: step: 760/530, loss: 0.3582044541835785
2023-01-21 09:26:06.637812: step: 764/530, loss: 0.15882942080497742
2023-01-21 09:26:07.786249: step: 768/530, loss: 0.08517131954431534
2023-01-21 09:26:08.969286: step: 772/530, loss: 0.25613927841186523
2023-01-21 09:26:10.137780: step: 776/530, loss: 0.02603592909872532
2023-01-21 09:26:11.327360: step: 780/530, loss: 0.3542129397392273
2023-01-21 09:26:12.471718: step: 784/530, loss: 0.20385399460792542
2023-01-21 09:26:13.619926: step: 788/530, loss: 0.21186791360378265
2023-01-21 09:26:14.815521: step: 792/530, loss: 0.22977885603904724
2023-01-21 09:26:15.983932: step: 796/530, loss: 0.08125042915344238
2023-01-21 09:26:17.188820: step: 800/530, loss: 0.046143725514411926
2023-01-21 09:26:18.374711: step: 804/530, loss: 0.16149769723415375
2023-01-21 09:26:19.528479: step: 808/530, loss: 0.1089821308851242
2023-01-21 09:26:20.688651: step: 812/530, loss: 0.17021751403808594
2023-01-21 09:26:21.847680: step: 816/530, loss: 0.05350446701049805
2023-01-21 09:26:23.012794: step: 820/530, loss: 0.07904867827892303
2023-01-21 09:26:24.153667: step: 824/530, loss: 0.03456611931324005
2023-01-21 09:26:25.364108: step: 828/530, loss: 0.07885666191577911
2023-01-21 09:26:26.529250: step: 832/530, loss: 0.17894645035266876
2023-01-21 09:26:27.710798: step: 836/530, loss: 0.05385322496294975
2023-01-21 09:26:28.851599: step: 840/530, loss: 0.18747782707214355
2023-01-21 09:26:30.051792: step: 844/530, loss: 0.2732110023498535
2023-01-21 09:26:31.273911: step: 848/530, loss: 0.07937441021203995
2023-01-21 09:26:32.440404: step: 852/530, loss: 0.11732955276966095
2023-01-21 09:26:33.606651: step: 856/530, loss: 0.12375015765428543
2023-01-21 09:26:34.761428: step: 860/530, loss: 0.09790816903114319
2023-01-21 09:26:35.969642: step: 864/530, loss: 1.5532574653625488
2023-01-21 09:26:37.156581: step: 868/530, loss: 0.5177452564239502
2023-01-21 09:26:38.346584: step: 872/530, loss: 0.1959790736436844
2023-01-21 09:26:39.547723: step: 876/530, loss: 0.050359103828668594
2023-01-21 09:26:40.717874: step: 880/530, loss: 0.10697796195745468
2023-01-21 09:26:41.917429: step: 884/530, loss: 0.0900697261095047
2023-01-21 09:26:43.104908: step: 888/530, loss: 0.14047984778881073
2023-01-21 09:26:44.315950: step: 892/530, loss: 0.6372136473655701
2023-01-21 09:26:45.468806: step: 896/530, loss: 0.04483118653297424
2023-01-21 09:26:46.676873: step: 900/530, loss: 0.07319831848144531
2023-01-21 09:26:47.840661: step: 904/530, loss: 1.0199657678604126
2023-01-21 09:26:49.035284: step: 908/530, loss: 0.18231754004955292
2023-01-21 09:26:50.219401: step: 912/530, loss: 0.37246617674827576
2023-01-21 09:26:51.427311: step: 916/530, loss: 0.48592326045036316
2023-01-21 09:26:52.580298: step: 920/530, loss: 0.5735053420066833
2023-01-21 09:26:53.723643: step: 924/530, loss: 0.08694677799940109
2023-01-21 09:26:54.884961: step: 928/530, loss: 0.3604698181152344
2023-01-21 09:26:56.039837: step: 932/530, loss: 0.20838555693626404
2023-01-21 09:26:57.215058: step: 936/530, loss: 0.16676147282123566
2023-01-21 09:26:58.399159: step: 940/530, loss: 0.1354725956916809
2023-01-21 09:26:59.572989: step: 944/530, loss: 0.08504219353199005
2023-01-21 09:27:00.755425: step: 948/530, loss: 0.39967620372772217
2023-01-21 09:27:01.956959: step: 952/530, loss: 0.08267507702112198
2023-01-21 09:27:03.206642: step: 956/530, loss: 0.0610315315425396
2023-01-21 09:27:04.381600: step: 960/530, loss: 0.2283109724521637
2023-01-21 09:27:05.549158: step: 964/530, loss: 0.12507982552051544
2023-01-21 09:27:06.735996: step: 968/530, loss: 0.5888115167617798
2023-01-21 09:27:07.889477: step: 972/530, loss: 0.11314735561609268
2023-01-21 09:27:09.063422: step: 976/530, loss: 0.8343511819839478
2023-01-21 09:27:10.249122: step: 980/530, loss: 0.5755516886711121
2023-01-21 09:27:11.415663: step: 984/530, loss: 0.012020445428788662
2023-01-21 09:27:12.650874: step: 988/530, loss: 0.06647415459156036
2023-01-21 09:27:13.872206: step: 992/530, loss: 0.2904585003852844
2023-01-21 09:27:15.056474: step: 996/530, loss: 0.292728990316391
2023-01-21 09:27:16.239215: step: 1000/530, loss: 0.6669138073921204
2023-01-21 09:27:17.413198: step: 1004/530, loss: 0.18626007437705994
2023-01-21 09:27:18.617309: step: 1008/530, loss: 2.168475389480591
2023-01-21 09:27:19.804229: step: 1012/530, loss: 1.471031904220581
2023-01-21 09:27:20.981882: step: 1016/530, loss: 0.32629913091659546
2023-01-21 09:27:22.154034: step: 1020/530, loss: 0.4751717746257782
2023-01-21 09:27:23.314435: step: 1024/530, loss: 0.2426433563232422
2023-01-21 09:27:24.498104: step: 1028/530, loss: 0.10402746498584747
2023-01-21 09:27:25.677670: step: 1032/530, loss: 0.5038238167762756
2023-01-21 09:27:26.814144: step: 1036/530, loss: 0.01148979738354683
2023-01-21 09:27:28.002629: step: 1040/530, loss: 0.8801649808883667
2023-01-21 09:27:29.135843: step: 1044/530, loss: 0.6397822499275208
2023-01-21 09:27:30.318087: step: 1048/530, loss: 0.2075888216495514
2023-01-21 09:27:31.464377: step: 1052/530, loss: 0.18571627140045166
2023-01-21 09:27:32.618752: step: 1056/530, loss: 0.04957332834601402
2023-01-21 09:27:33.853346: step: 1060/530, loss: 0.8867083787918091
2023-01-21 09:27:35.043135: step: 1064/530, loss: 0.24365095794200897
2023-01-21 09:27:36.219030: step: 1068/530, loss: 0.6125437021255493
2023-01-21 09:27:37.405299: step: 1072/530, loss: 0.43842363357543945
2023-01-21 09:27:38.574002: step: 1076/530, loss: 0.5704627633094788
2023-01-21 09:27:39.740851: step: 1080/530, loss: 0.24505653977394104
2023-01-21 09:27:40.913891: step: 1084/530, loss: 0.07791705429553986
2023-01-21 09:27:42.096805: step: 1088/530, loss: 1.9555320739746094
2023-01-21 09:27:43.265673: step: 1092/530, loss: 0.47729578614234924
2023-01-21 09:27:44.447478: step: 1096/530, loss: 0.13234680891036987
2023-01-21 09:27:45.651176: step: 1100/530, loss: 0.07763376832008362
2023-01-21 09:27:46.835424: step: 1104/530, loss: 0.2553926110267639
2023-01-21 09:27:48.001631: step: 1108/530, loss: 0.05934019386768341
2023-01-21 09:27:49.180692: step: 1112/530, loss: 1.2474793195724487
2023-01-21 09:27:50.328015: step: 1116/530, loss: 0.1332971602678299
2023-01-21 09:27:51.539860: step: 1120/530, loss: 0.4560391902923584
2023-01-21 09:27:52.736869: step: 1124/530, loss: 0.16044750809669495
2023-01-21 09:27:53.979733: step: 1128/530, loss: 0.12127628177404404
2023-01-21 09:27:55.197634: step: 1132/530, loss: 0.5991616249084473
2023-01-21 09:27:56.329696: step: 1136/530, loss: 0.2859123647212982
2023-01-21 09:27:57.475810: step: 1140/530, loss: 0.032474614679813385
2023-01-21 09:27:58.647899: step: 1144/530, loss: 0.03540482372045517
2023-01-21 09:27:59.835536: step: 1148/530, loss: 0.09580278396606445
2023-01-21 09:28:01.038851: step: 1152/530, loss: 0.16927321255207062
2023-01-21 09:28:02.214507: step: 1156/530, loss: 0.20908865332603455
2023-01-21 09:28:03.349604: step: 1160/530, loss: 0.22863316535949707
2023-01-21 09:28:04.546923: step: 1164/530, loss: 0.2704286575317383
2023-01-21 09:28:05.733653: step: 1168/530, loss: 0.18156041204929352
2023-01-21 09:28:06.933102: step: 1172/530, loss: 0.0785895362496376
2023-01-21 09:28:08.117195: step: 1176/530, loss: 0.06458039581775665
2023-01-21 09:28:09.267960: step: 1180/530, loss: 0.06516294181346893
2023-01-21 09:28:10.426078: step: 1184/530, loss: 0.07818622887134552
2023-01-21 09:28:11.595339: step: 1188/530, loss: 0.17929410934448242
2023-01-21 09:28:12.767500: step: 1192/530, loss: 0.9059211611747742
2023-01-21 09:28:13.910132: step: 1196/530, loss: 0.04472675547003746
2023-01-21 09:28:15.093520: step: 1200/530, loss: 0.1156536117196083
2023-01-21 09:28:16.262055: step: 1204/530, loss: 0.5848633646965027
2023-01-21 09:28:17.428123: step: 1208/530, loss: 0.05516824871301651
2023-01-21 09:28:18.599387: step: 1212/530, loss: 0.03132748603820801
2023-01-21 09:28:19.785850: step: 1216/530, loss: 0.051054954528808594
2023-01-21 09:28:20.988885: step: 1220/530, loss: 0.10619644820690155
2023-01-21 09:28:22.182324: step: 1224/530, loss: 0.43752241134643555
2023-01-21 09:28:23.334885: step: 1228/530, loss: 0.0352010503411293
2023-01-21 09:28:24.531201: step: 1232/530, loss: 0.18690891563892365
2023-01-21 09:28:25.732562: step: 1236/530, loss: 0.07504439353942871
2023-01-21 09:28:26.868147: step: 1240/530, loss: 0.16570618748664856
2023-01-21 09:28:28.043776: step: 1244/530, loss: 0.1733359396457672
2023-01-21 09:28:29.281307: step: 1248/530, loss: 0.4787226617336273
2023-01-21 09:28:30.449941: step: 1252/530, loss: 0.13653096556663513
2023-01-21 09:28:31.676930: step: 1256/530, loss: 0.171139195561409
2023-01-21 09:28:32.821895: step: 1260/530, loss: 0.061833858489990234
2023-01-21 09:28:33.995135: step: 1264/530, loss: 0.24273909628391266
2023-01-21 09:28:35.134632: step: 1268/530, loss: 0.04744882881641388
2023-01-21 09:28:36.267688: step: 1272/530, loss: 0.5717808604240417
2023-01-21 09:28:37.447001: step: 1276/530, loss: 0.0474054329097271
2023-01-21 09:28:38.624069: step: 1280/530, loss: 0.020391561090946198
2023-01-21 09:28:39.809206: step: 1284/530, loss: 0.15444627404212952
2023-01-21 09:28:40.997264: step: 1288/530, loss: 0.16565489768981934
2023-01-21 09:28:42.179016: step: 1292/530, loss: 0.18671393394470215
2023-01-21 09:28:43.396455: step: 1296/530, loss: 0.5503236055374146
2023-01-21 09:28:44.571838: step: 1300/530, loss: 0.13108621537685394
2023-01-21 09:28:45.767657: step: 1304/530, loss: 0.17163696885108948
2023-01-21 09:28:46.972428: step: 1308/530, loss: 0.2255449891090393
2023-01-21 09:28:48.179801: step: 1312/530, loss: 0.2358277440071106
2023-01-21 09:28:49.399568: step: 1316/530, loss: 0.4199904501438141
2023-01-21 09:28:50.545214: step: 1320/530, loss: 0.5662668347358704
2023-01-21 09:28:51.756098: step: 1324/530, loss: 0.2246697098016739
2023-01-21 09:28:52.906412: step: 1328/530, loss: 0.6220422387123108
2023-01-21 09:28:54.071462: step: 1332/530, loss: 0.48554858565330505
2023-01-21 09:28:55.233613: step: 1336/530, loss: 0.04615822061896324
2023-01-21 09:28:56.397668: step: 1340/530, loss: 0.10526285320520401
2023-01-21 09:28:57.595847: step: 1344/530, loss: 0.5885298848152161
2023-01-21 09:28:58.792989: step: 1348/530, loss: 0.2826506793498993
2023-01-21 09:28:59.914647: step: 1352/530, loss: 0.13399486243724823
2023-01-21 09:29:01.098560: step: 1356/530, loss: 1.0948952436447144
2023-01-21 09:29:02.301704: step: 1360/530, loss: 0.7194830179214478
2023-01-21 09:29:03.450550: step: 1364/530, loss: 0.04530759155750275
2023-01-21 09:29:04.657316: step: 1368/530, loss: 0.7042287588119507
2023-01-21 09:29:05.824602: step: 1372/530, loss: 0.17493458092212677
2023-01-21 09:29:07.006304: step: 1376/530, loss: 0.07183227688074112
2023-01-21 09:29:08.182178: step: 1380/530, loss: 0.08216257393360138
2023-01-21 09:29:09.355254: step: 1384/530, loss: 0.08559112250804901
2023-01-21 09:29:10.558620: step: 1388/530, loss: 0.03427858650684357
2023-01-21 09:29:11.725499: step: 1392/530, loss: 0.18191371858119965
2023-01-21 09:29:12.928941: step: 1396/530, loss: 0.026778126135468483
2023-01-21 09:29:14.112507: step: 1400/530, loss: 0.2142053246498108
2023-01-21 09:29:15.291335: step: 1404/530, loss: 0.04235114902257919
2023-01-21 09:29:16.485501: step: 1408/530, loss: 0.9389051198959351
2023-01-21 09:29:17.694232: step: 1412/530, loss: 0.19289031624794006
2023-01-21 09:29:18.895673: step: 1416/530, loss: 0.624676525592804
2023-01-21 09:29:20.042166: step: 1420/530, loss: 0.12964196503162384
2023-01-21 09:29:21.252483: step: 1424/530, loss: 0.07281980663537979
2023-01-21 09:29:22.398848: step: 1428/530, loss: 0.6434813737869263
2023-01-21 09:29:23.575657: step: 1432/530, loss: 0.393645703792572
2023-01-21 09:29:24.741409: step: 1436/530, loss: 0.6352441906929016
2023-01-21 09:29:25.950593: step: 1440/530, loss: 0.12835732102394104
2023-01-21 09:29:27.124694: step: 1444/530, loss: 0.2975778579711914
2023-01-21 09:29:28.327396: step: 1448/530, loss: 0.06826931983232498
2023-01-21 09:29:29.556125: step: 1452/530, loss: 0.18356162309646606
2023-01-21 09:29:30.726198: step: 1456/530, loss: 0.091344453394413
2023-01-21 09:29:31.903891: step: 1460/530, loss: 0.2977584898471832
2023-01-21 09:29:33.067705: step: 1464/530, loss: 0.16529908776283264
2023-01-21 09:29:34.344148: step: 1468/530, loss: 0.14218272268772125
2023-01-21 09:29:35.491023: step: 1472/530, loss: 0.3001793920993805
2023-01-21 09:29:36.700529: step: 1476/530, loss: 0.1296243667602539
2023-01-21 09:29:37.880605: step: 1480/530, loss: 0.25451919436454773
2023-01-21 09:29:39.064711: step: 1484/530, loss: 0.16674485802650452
2023-01-21 09:29:40.232369: step: 1488/530, loss: 0.09211044758558273
2023-01-21 09:29:41.391425: step: 1492/530, loss: 0.07760500907897949
2023-01-21 09:29:42.589257: step: 1496/530, loss: 0.36814916133880615
2023-01-21 09:29:43.738285: step: 1500/530, loss: 0.3086715340614319
2023-01-21 09:29:44.903574: step: 1504/530, loss: 0.31361985206604004
2023-01-21 09:29:46.065088: step: 1508/530, loss: 0.39559406042099
2023-01-21 09:29:47.251414: step: 1512/530, loss: 0.04169083014130592
2023-01-21 09:29:48.427235: step: 1516/530, loss: 0.4428962469100952
2023-01-21 09:29:49.574271: step: 1520/530, loss: 0.1047309935092926
2023-01-21 09:29:50.763465: step: 1524/530, loss: 0.049477290362119675
2023-01-21 09:29:52.004110: step: 1528/530, loss: 0.6606917381286621
2023-01-21 09:29:53.198688: step: 1532/530, loss: 0.2922571301460266
2023-01-21 09:29:54.408534: step: 1536/530, loss: 0.16509433090686798
2023-01-21 09:29:55.623858: step: 1540/530, loss: 0.14102521538734436
2023-01-21 09:29:56.826798: step: 1544/530, loss: 0.6083961725234985
2023-01-21 09:29:58.026079: step: 1548/530, loss: 0.07300844043493271
2023-01-21 09:29:59.199224: step: 1552/530, loss: 0.44000494480133057
2023-01-21 09:30:00.440420: step: 1556/530, loss: 0.009563145227730274
2023-01-21 09:30:01.639340: step: 1560/530, loss: 0.4080503582954407
2023-01-21 09:30:02.849015: step: 1564/530, loss: 0.6315172910690308
2023-01-21 09:30:04.072491: step: 1568/530, loss: 0.1180976927280426
2023-01-21 09:30:05.289698: step: 1572/530, loss: 0.10513772815465927
2023-01-21 09:30:06.450785: step: 1576/530, loss: 0.0841943770647049
2023-01-21 09:30:07.616255: step: 1580/530, loss: 0.33826887607574463
2023-01-21 09:30:08.782105: step: 1584/530, loss: 0.05056290701031685
2023-01-21 09:30:09.959513: step: 1588/530, loss: 0.9394656419754028
2023-01-21 09:30:11.126163: step: 1592/530, loss: 0.18289200961589813
2023-01-21 09:30:12.351692: step: 1596/530, loss: 0.12054203450679779
2023-01-21 09:30:13.513858: step: 1600/530, loss: 0.7090510129928589
2023-01-21 09:30:14.686202: step: 1604/530, loss: 0.2092619389295578
2023-01-21 09:30:15.812151: step: 1608/530, loss: 0.3508315682411194
2023-01-21 09:30:16.994717: step: 1612/530, loss: 0.03585987165570259
2023-01-21 09:30:18.183427: step: 1616/530, loss: 0.5515589714050293
2023-01-21 09:30:19.358700: step: 1620/530, loss: 0.15571269392967224
2023-01-21 09:30:20.511552: step: 1624/530, loss: 0.08539529144763947
2023-01-21 09:30:21.696269: step: 1628/530, loss: 0.14687862992286682
2023-01-21 09:30:22.866844: step: 1632/530, loss: 1.0682094097137451
2023-01-21 09:30:24.013284: step: 1636/530, loss: 0.23623287677764893
2023-01-21 09:30:25.175681: step: 1640/530, loss: 0.36274901032447815
2023-01-21 09:30:26.342996: step: 1644/530, loss: 0.21607714891433716
2023-01-21 09:30:27.555489: step: 1648/530, loss: 0.38459983468055725
2023-01-21 09:30:28.711957: step: 1652/530, loss: 2.671396017074585
2023-01-21 09:30:29.908589: step: 1656/530, loss: 0.3264641761779785
2023-01-21 09:30:31.099959: step: 1660/530, loss: 0.1645500659942627
2023-01-21 09:30:32.294173: step: 1664/530, loss: 0.12709493935108185
2023-01-21 09:30:33.461780: step: 1668/530, loss: 0.410942941904068
2023-01-21 09:30:34.626879: step: 1672/530, loss: 0.3050805926322937
2023-01-21 09:30:35.815697: step: 1676/530, loss: 0.1079469695687294
2023-01-21 09:30:37.006003: step: 1680/530, loss: 0.0970836654305458
2023-01-21 09:30:38.222241: step: 1684/530, loss: 0.1347736418247223
2023-01-21 09:30:39.372276: step: 1688/530, loss: 0.6043469309806824
2023-01-21 09:30:40.532322: step: 1692/530, loss: 0.7652765512466431
2023-01-21 09:30:41.701244: step: 1696/530, loss: 0.10198745131492615
2023-01-21 09:30:42.905878: step: 1700/530, loss: 0.4698176383972168
2023-01-21 09:30:44.063714: step: 1704/530, loss: 0.17421293258666992
2023-01-21 09:30:45.266101: step: 1708/530, loss: 0.39454221725463867
2023-01-21 09:30:46.424653: step: 1712/530, loss: 0.19035880267620087
2023-01-21 09:30:47.613051: step: 1716/530, loss: 0.681043803691864
2023-01-21 09:30:48.841885: step: 1720/530, loss: 0.3380935788154602
2023-01-21 09:30:50.007845: step: 1724/530, loss: 0.09006671607494354
2023-01-21 09:30:51.171988: step: 1728/530, loss: 3.8173582553863525
2023-01-21 09:30:52.376514: step: 1732/530, loss: 0.20162925124168396
2023-01-21 09:30:53.586499: step: 1736/530, loss: 0.1108190044760704
2023-01-21 09:30:54.747217: step: 1740/530, loss: 0.09658689796924591
2023-01-21 09:30:55.927243: step: 1744/530, loss: 0.1451614499092102
2023-01-21 09:30:57.139802: step: 1748/530, loss: 0.1478760838508606
2023-01-21 09:30:58.284827: step: 1752/530, loss: 0.5597879886627197
2023-01-21 09:30:59.471746: step: 1756/530, loss: 0.17262262105941772
2023-01-21 09:31:00.622992: step: 1760/530, loss: 0.08454713970422745
2023-01-21 09:31:01.771087: step: 1764/530, loss: 0.28342851996421814
2023-01-21 09:31:02.984494: step: 1768/530, loss: 0.3253527283668518
2023-01-21 09:31:04.173083: step: 1772/530, loss: 0.12964993715286255
2023-01-21 09:31:05.366035: step: 1776/530, loss: 0.17020387947559357
2023-01-21 09:31:06.517876: step: 1780/530, loss: 0.07815121114253998
2023-01-21 09:31:07.681660: step: 1784/530, loss: 0.18504615128040314
2023-01-21 09:31:08.874014: step: 1788/530, loss: 0.04820366948843002
2023-01-21 09:31:10.036724: step: 1792/530, loss: 0.0209047794342041
2023-01-21 09:31:11.227765: step: 1796/530, loss: 0.5757182836532593
2023-01-21 09:31:12.406272: step: 1800/530, loss: 0.17756973206996918
2023-01-21 09:31:13.580291: step: 1804/530, loss: 0.02128014713525772
2023-01-21 09:31:14.787021: step: 1808/530, loss: 0.5995561480522156
2023-01-21 09:31:15.931086: step: 1812/530, loss: 0.07125025242567062
2023-01-21 09:31:17.077010: step: 1816/530, loss: 0.19941289722919464
2023-01-21 09:31:18.243993: step: 1820/530, loss: 0.17385712265968323
2023-01-21 09:31:19.477274: step: 1824/530, loss: 0.16065020859241486
2023-01-21 09:31:20.664533: step: 1828/530, loss: 0.18355488777160645
2023-01-21 09:31:21.857633: step: 1832/530, loss: 0.07288698852062225
2023-01-21 09:31:23.035285: step: 1836/530, loss: 0.11582336574792862
2023-01-21 09:31:24.256864: step: 1840/530, loss: 0.23762167990207672
2023-01-21 09:31:25.454891: step: 1844/530, loss: 0.7768181562423706
2023-01-21 09:31:26.649932: step: 1848/530, loss: 0.09504041820764542
2023-01-21 09:31:27.819453: step: 1852/530, loss: 0.45964327454566956
2023-01-21 09:31:29.080546: step: 1856/530, loss: 0.12890419363975525
2023-01-21 09:31:30.262107: step: 1860/530, loss: 0.08270959556102753
2023-01-21 09:31:31.434574: step: 1864/530, loss: 0.3656943440437317
2023-01-21 09:31:32.595998: step: 1868/530, loss: 0.02837839163839817
2023-01-21 09:31:33.746081: step: 1872/530, loss: 0.06046877056360245
2023-01-21 09:31:34.916600: step: 1876/530, loss: 0.1449769139289856
2023-01-21 09:31:36.107152: step: 1880/530, loss: 0.7949851751327515
2023-01-21 09:31:37.264015: step: 1884/530, loss: 0.060991667211055756
2023-01-21 09:31:38.404708: step: 1888/530, loss: 0.3971121609210968
2023-01-21 09:31:39.574412: step: 1892/530, loss: 0.21435260772705078
2023-01-21 09:31:40.784291: step: 1896/530, loss: 0.08935561031103134
2023-01-21 09:31:41.995965: step: 1900/530, loss: 0.02246398851275444
2023-01-21 09:31:43.190702: step: 1904/530, loss: 0.12360525131225586
2023-01-21 09:31:44.355658: step: 1908/530, loss: 0.475870281457901
2023-01-21 09:31:45.517028: step: 1912/530, loss: 0.19839662313461304
2023-01-21 09:31:46.683757: step: 1916/530, loss: 0.07164087146520615
2023-01-21 09:31:47.867601: step: 1920/530, loss: 0.11918659508228302
2023-01-21 09:31:49.051742: step: 1924/530, loss: 0.11692371219396591
2023-01-21 09:31:50.268135: step: 1928/530, loss: 0.5201605558395386
2023-01-21 09:31:51.467266: step: 1932/530, loss: 0.26014289259910583
2023-01-21 09:31:52.653838: step: 1936/530, loss: 0.10092878341674805
2023-01-21 09:31:53.829305: step: 1940/530, loss: 0.3030557632446289
2023-01-21 09:31:55.031586: step: 1944/530, loss: 0.1404828131198883
2023-01-21 09:31:56.217420: step: 1948/530, loss: 0.11478271335363388
2023-01-21 09:31:57.391011: step: 1952/530, loss: 0.13196983933448792
2023-01-21 09:31:58.586944: step: 1956/530, loss: 0.17698338627815247
2023-01-21 09:31:59.780979: step: 1960/530, loss: 0.15164241194725037
2023-01-21 09:32:00.979693: step: 1964/530, loss: 0.5972582697868347
2023-01-21 09:32:02.159749: step: 1968/530, loss: 0.5600477457046509
2023-01-21 09:32:03.349720: step: 1972/530, loss: 0.021208904683589935
2023-01-21 09:32:04.540910: step: 1976/530, loss: 0.4192635416984558
2023-01-21 09:32:05.753394: step: 1980/530, loss: 0.09897632896900177
2023-01-21 09:32:06.931662: step: 1984/530, loss: 0.6683353781700134
2023-01-21 09:32:08.118710: step: 1988/530, loss: 0.21934795379638672
2023-01-21 09:32:09.294290: step: 1992/530, loss: 0.7338366508483887
2023-01-21 09:32:10.484304: step: 1996/530, loss: 0.0723641887307167
2023-01-21 09:32:11.682317: step: 2000/530, loss: 0.054695844650268555
2023-01-21 09:32:12.890205: step: 2004/530, loss: 0.6086748838424683
2023-01-21 09:32:14.094832: step: 2008/530, loss: 0.07680780440568924
2023-01-21 09:32:15.262266: step: 2012/530, loss: 0.09220962226390839
2023-01-21 09:32:16.407126: step: 2016/530, loss: 0.19119691848754883
2023-01-21 09:32:17.569457: step: 2020/530, loss: 0.34983572363853455
2023-01-21 09:32:18.731360: step: 2024/530, loss: 0.11355714499950409
2023-01-21 09:32:19.941497: step: 2028/530, loss: 0.15759029984474182
2023-01-21 09:32:21.104337: step: 2032/530, loss: 0.08128716796636581
2023-01-21 09:32:22.280043: step: 2036/530, loss: 0.6015458106994629
2023-01-21 09:32:23.423086: step: 2040/530, loss: 0.1496560126543045
2023-01-21 09:32:24.633942: step: 2044/530, loss: 0.21115809679031372
2023-01-21 09:32:25.812903: step: 2048/530, loss: 0.6047495007514954
2023-01-21 09:32:26.968865: step: 2052/530, loss: 0.006008625496178865
2023-01-21 09:32:28.188925: step: 2056/530, loss: 0.06735420227050781
2023-01-21 09:32:29.332810: step: 2060/530, loss: 0.1122509092092514
2023-01-21 09:32:30.520701: step: 2064/530, loss: 0.03537600114941597
2023-01-21 09:32:31.682242: step: 2068/530, loss: 0.1548711359500885
2023-01-21 09:32:32.838101: step: 2072/530, loss: 0.13152997195720673
2023-01-21 09:32:33.991564: step: 2076/530, loss: 0.033211804926395416
2023-01-21 09:32:35.133163: step: 2080/530, loss: 0.5364004969596863
2023-01-21 09:32:36.375179: step: 2084/530, loss: 0.052607253193855286
2023-01-21 09:32:37.585048: step: 2088/530, loss: 0.11160936951637268
2023-01-21 09:32:38.796545: step: 2092/530, loss: 0.10112962871789932
2023-01-21 09:32:39.942731: step: 2096/530, loss: 0.25139886140823364
2023-01-21 09:32:41.140466: step: 2100/530, loss: 0.07464206218719482
2023-01-21 09:32:42.351986: step: 2104/530, loss: 0.2184407263994217
2023-01-21 09:32:43.542864: step: 2108/530, loss: 0.3812035620212555
2023-01-21 09:32:44.692814: step: 2112/530, loss: 0.01790900155901909
2023-01-21 09:32:45.892333: step: 2116/530, loss: 0.20171022415161133
2023-01-21 09:32:47.080600: step: 2120/530, loss: 0.13600090146064758
==================================================
Loss: 0.284
--------------------
Dev: {'event': {'p': 0.5533333333333333, 'r': 0.7736351531291611, 'f1': 0.6451971127151582}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.618983355825461, 'r': 0.7912593444508338, 'f1': 0.6945986875315496}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
Korean: {'event': {'p': 0.6226415094339622, 'r': 0.5238095238095238, 'f1': 0.5689655172413793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.5227272727272727, 'r': 0.6388888888888888, 'f1': 0.575}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
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 09:33:30.754476: step: 4/530, loss: 0.15994276106357574
2023-01-21 09:33:31.925735: step: 8/530, loss: 0.045320890843868256
2023-01-21 09:33:33.133202: step: 12/530, loss: 0.23048695921897888
2023-01-21 09:33:34.330498: step: 16/530, loss: 0.5394615530967712
2023-01-21 09:33:35.496645: step: 20/530, loss: 0.12582692503929138
2023-01-21 09:33:36.648075: step: 24/530, loss: 0.0660005584359169
2023-01-21 09:33:37.886440: step: 28/530, loss: 0.025230027735233307
2023-01-21 09:33:39.031602: step: 32/530, loss: 0.07103128731250763
2023-01-21 09:33:40.180624: step: 36/530, loss: 0.008608436211943626
2023-01-21 09:33:41.342562: step: 40/530, loss: 0.14398737251758575
2023-01-21 09:33:42.519517: step: 44/530, loss: 0.2719116508960724
2023-01-21 09:33:43.683772: step: 48/530, loss: 0.06196288764476776
2023-01-21 09:33:44.853574: step: 52/530, loss: 0.038278769701719284
2023-01-21 09:33:46.038850: step: 56/530, loss: 0.43912628293037415
2023-01-21 09:33:47.239238: step: 60/530, loss: 0.09541139751672745
2023-01-21 09:33:48.429289: step: 64/530, loss: 0.31967926025390625
2023-01-21 09:33:49.566277: step: 68/530, loss: 0.09328780323266983
2023-01-21 09:33:50.729001: step: 72/530, loss: 0.12033358216285706
2023-01-21 09:33:51.897807: step: 76/530, loss: 0.1217704489827156
2023-01-21 09:33:53.151066: step: 80/530, loss: 1.1162290573120117
2023-01-21 09:33:54.293078: step: 84/530, loss: 0.20260782539844513
2023-01-21 09:33:55.452462: step: 88/530, loss: 0.2975834310054779
2023-01-21 09:33:56.604272: step: 92/530, loss: 0.0790904089808464
2023-01-21 09:33:57.820350: step: 96/530, loss: 0.41175052523612976
2023-01-21 09:33:58.977559: step: 100/530, loss: 0.07524947822093964
2023-01-21 09:34:00.148839: step: 104/530, loss: 0.10713760554790497
2023-01-21 09:34:01.296785: step: 108/530, loss: 0.24148236215114594
2023-01-21 09:34:02.501916: step: 112/530, loss: 0.12252034991979599
2023-01-21 09:34:03.682320: step: 116/530, loss: 0.13124337792396545
2023-01-21 09:34:04.865609: step: 120/530, loss: 0.42690467834472656
2023-01-21 09:34:06.058258: step: 124/530, loss: 0.14836172759532928
2023-01-21 09:34:07.256999: step: 128/530, loss: 0.26024800539016724
2023-01-21 09:34:08.415668: step: 132/530, loss: 0.09583864361047745
2023-01-21 09:34:09.581815: step: 136/530, loss: 0.12546278536319733
2023-01-21 09:34:10.758819: step: 140/530, loss: 0.18270738422870636
2023-01-21 09:34:11.960194: step: 144/530, loss: 0.05501508712768555
2023-01-21 09:34:13.141275: step: 148/530, loss: 0.2854381501674652
2023-01-21 09:34:14.300606: step: 152/530, loss: 0.1291239857673645
2023-01-21 09:34:15.483808: step: 156/530, loss: 0.06799326092004776
2023-01-21 09:34:16.624792: step: 160/530, loss: 0.10171270370483398
2023-01-21 09:34:17.796847: step: 164/530, loss: 0.12280149757862091
2023-01-21 09:34:18.982201: step: 168/530, loss: 0.5371148586273193
2023-01-21 09:34:20.148068: step: 172/530, loss: 0.08669638633728027
2023-01-21 09:34:21.317914: step: 176/530, loss: 0.15250855684280396
2023-01-21 09:34:22.478187: step: 180/530, loss: 0.15418720245361328
2023-01-21 09:34:23.690514: step: 184/530, loss: 0.330893337726593
2023-01-21 09:34:24.834565: step: 188/530, loss: 0.11315040290355682
2023-01-21 09:34:26.014982: step: 192/530, loss: 0.08025212585926056
2023-01-21 09:34:27.217435: step: 196/530, loss: 0.027968013659119606
2023-01-21 09:34:28.436993: step: 200/530, loss: 0.126437708735466
2023-01-21 09:34:29.600965: step: 204/530, loss: 0.1817864030599594
2023-01-21 09:34:30.789358: step: 208/530, loss: 0.01971263810992241
2023-01-21 09:34:31.975240: step: 212/530, loss: 0.01996746100485325
2023-01-21 09:34:33.187283: step: 216/530, loss: 0.09121789783239365
2023-01-21 09:34:34.377617: step: 220/530, loss: 0.47318220138549805
2023-01-21 09:34:35.535949: step: 224/530, loss: 0.07102303206920624
2023-01-21 09:34:36.735977: step: 228/530, loss: 0.10886078327894211
2023-01-21 09:34:37.948551: step: 232/530, loss: 0.1321459859609604
2023-01-21 09:34:39.174011: step: 236/530, loss: 0.11014099419116974
2023-01-21 09:34:40.370745: step: 240/530, loss: 0.41911324858665466
2023-01-21 09:34:41.554117: step: 244/530, loss: 0.1504814177751541
2023-01-21 09:34:42.739076: step: 248/530, loss: 0.06883887946605682
2023-01-21 09:34:43.892165: step: 252/530, loss: 0.0356929786503315
2023-01-21 09:34:45.096295: step: 256/530, loss: 0.013660860247910023
2023-01-21 09:34:46.264687: step: 260/530, loss: 0.18641920387744904
2023-01-21 09:34:47.466184: step: 264/530, loss: 0.06180419772863388
2023-01-21 09:34:48.631572: step: 268/530, loss: 0.08162336051464081
2023-01-21 09:34:49.763063: step: 272/530, loss: 0.17799797654151917
2023-01-21 09:34:50.906541: step: 276/530, loss: 0.0578128844499588
2023-01-21 09:34:52.079100: step: 280/530, loss: 0.09725475311279297
2023-01-21 09:34:53.260551: step: 284/530, loss: 0.08963232487440109
2023-01-21 09:34:54.417078: step: 288/530, loss: 0.37990498542785645
2023-01-21 09:34:55.578720: step: 292/530, loss: 0.03215036541223526
2023-01-21 09:34:56.761093: step: 296/530, loss: 0.064191535115242
2023-01-21 09:34:57.928670: step: 300/530, loss: 0.08762683719396591
2023-01-21 09:34:59.091245: step: 304/530, loss: 0.05148515850305557
2023-01-21 09:35:00.249165: step: 308/530, loss: 0.17682066559791565
2023-01-21 09:35:01.454255: step: 312/530, loss: 0.17495641112327576
2023-01-21 09:35:02.615769: step: 316/530, loss: 0.022137831896543503
2023-01-21 09:35:03.792403: step: 320/530, loss: 0.07729358971118927
2023-01-21 09:35:04.982368: step: 324/530, loss: 0.06603336334228516
2023-01-21 09:35:06.188974: step: 328/530, loss: 0.11373010277748108
2023-01-21 09:35:07.361825: step: 332/530, loss: 0.049485016614198685
2023-01-21 09:35:08.563263: step: 336/530, loss: 0.4607907235622406
2023-01-21 09:35:09.705495: step: 340/530, loss: 0.12253957241773605
2023-01-21 09:35:10.899070: step: 344/530, loss: 0.0044678207486867905
2023-01-21 09:35:12.079686: step: 348/530, loss: 0.0903073325753212
2023-01-21 09:35:13.244718: step: 352/530, loss: 0.06629905849695206
2023-01-21 09:35:14.427706: step: 356/530, loss: 0.14650268852710724
2023-01-21 09:35:15.591006: step: 360/530, loss: 0.08548612892627716
2023-01-21 09:35:16.763818: step: 364/530, loss: 0.35773396492004395
2023-01-21 09:35:17.913093: step: 368/530, loss: 0.01766963116824627
2023-01-21 09:35:19.102871: step: 372/530, loss: 0.016019249334931374
2023-01-21 09:35:20.306077: step: 376/530, loss: 0.09293222427368164
2023-01-21 09:35:21.456555: step: 380/530, loss: 0.030004145577549934
2023-01-21 09:35:22.639913: step: 384/530, loss: 0.12180319428443909
2023-01-21 09:35:23.832376: step: 388/530, loss: 0.9566667079925537
2023-01-21 09:35:25.013402: step: 392/530, loss: 0.024489833042025566
2023-01-21 09:35:26.252639: step: 396/530, loss: 0.1741258203983307
2023-01-21 09:35:27.411572: step: 400/530, loss: 0.06589307636022568
2023-01-21 09:35:28.576988: step: 404/530, loss: 0.6494244337081909
2023-01-21 09:35:29.744278: step: 408/530, loss: 0.09843003749847412
2023-01-21 09:35:30.911196: step: 412/530, loss: 0.10757436603307724
2023-01-21 09:35:32.082763: step: 416/530, loss: 0.025983812287449837
2023-01-21 09:35:33.258494: step: 420/530, loss: 0.08584971725940704
2023-01-21 09:35:34.425103: step: 424/530, loss: 0.13532963395118713
2023-01-21 09:35:35.548299: step: 428/530, loss: 0.003741312073543668
2023-01-21 09:35:36.798786: step: 432/530, loss: 0.5738229155540466
2023-01-21 09:35:37.996501: step: 436/530, loss: 0.1531471312046051
2023-01-21 09:35:39.232586: step: 440/530, loss: 0.1867099404335022
2023-01-21 09:35:40.397340: step: 444/530, loss: 0.02309880219399929
2023-01-21 09:35:41.588527: step: 448/530, loss: 0.6170173287391663
2023-01-21 09:35:42.736868: step: 452/530, loss: 0.4096931517124176
2023-01-21 09:35:43.885589: step: 456/530, loss: 0.08182539790868759
2023-01-21 09:35:45.059069: step: 460/530, loss: 0.0717935562133789
2023-01-21 09:35:46.212569: step: 464/530, loss: 0.05641374737024307
2023-01-21 09:35:47.396532: step: 468/530, loss: 0.08361849933862686
2023-01-21 09:35:48.579166: step: 472/530, loss: 0.15602579712867737
2023-01-21 09:35:49.736681: step: 476/530, loss: 0.34944647550582886
2023-01-21 09:35:50.926960: step: 480/530, loss: 0.10817337036132812
2023-01-21 09:35:52.113712: step: 484/530, loss: 0.057747554033994675
2023-01-21 09:35:53.301834: step: 488/530, loss: 0.05795030668377876
2023-01-21 09:35:54.430864: step: 492/530, loss: 0.02306889370083809
2023-01-21 09:35:55.656505: step: 496/530, loss: 0.1557292938232422
2023-01-21 09:35:56.816595: step: 500/530, loss: 0.1702808439731598
2023-01-21 09:35:57.955975: step: 504/530, loss: 0.11404943466186523
2023-01-21 09:35:59.142530: step: 508/530, loss: 0.2544203996658325
2023-01-21 09:36:00.367093: step: 512/530, loss: 0.03190431743860245
2023-01-21 09:36:01.555550: step: 516/530, loss: 0.07754459977149963
2023-01-21 09:36:02.737532: step: 520/530, loss: 0.06305336952209473
2023-01-21 09:36:03.886099: step: 524/530, loss: 0.17399534583091736
2023-01-21 09:36:05.098254: step: 528/530, loss: 0.2367015779018402
2023-01-21 09:36:06.261493: step: 532/530, loss: 0.05527792125940323
2023-01-21 09:36:07.468375: step: 536/530, loss: 0.12429256737232208
2023-01-21 09:36:08.657789: step: 540/530, loss: 0.09126138687133789
2023-01-21 09:36:09.841271: step: 544/530, loss: 0.11814985424280167
2023-01-21 09:36:10.979381: step: 548/530, loss: 0.07085929065942764
2023-01-21 09:36:12.177133: step: 552/530, loss: 0.6980571746826172
2023-01-21 09:36:13.386288: step: 556/530, loss: 0.035009339451789856
2023-01-21 09:36:14.574761: step: 560/530, loss: 0.06832804530858994
2023-01-21 09:36:15.773640: step: 564/530, loss: 0.14165955781936646
2023-01-21 09:36:16.980762: step: 568/530, loss: 0.21956318616867065
2023-01-21 09:36:18.165098: step: 572/530, loss: 0.2013145387172699
2023-01-21 09:36:19.325419: step: 576/530, loss: 0.03372984007000923
2023-01-21 09:36:20.470586: step: 580/530, loss: 0.0470459945499897
2023-01-21 09:36:21.629990: step: 584/530, loss: 0.08859510719776154
2023-01-21 09:36:22.821221: step: 588/530, loss: 0.04225621372461319
2023-01-21 09:36:24.055117: step: 592/530, loss: 0.02696380764245987
2023-01-21 09:36:25.235547: step: 596/530, loss: 0.21186891198158264
2023-01-21 09:36:26.404150: step: 600/530, loss: 0.3758409321308136
2023-01-21 09:36:27.574154: step: 604/530, loss: 0.5602823495864868
2023-01-21 09:36:28.746327: step: 608/530, loss: 0.245101660490036
2023-01-21 09:36:29.958969: step: 612/530, loss: 0.09078064560890198
2023-01-21 09:36:31.108464: step: 616/530, loss: 0.022649575024843216
2023-01-21 09:36:32.337147: step: 620/530, loss: 0.1233924850821495
2023-01-21 09:36:33.515689: step: 624/530, loss: 0.15088967978954315
2023-01-21 09:36:34.639784: step: 628/530, loss: 0.08727141469717026
2023-01-21 09:36:35.820152: step: 632/530, loss: 0.10299844294786453
2023-01-21 09:36:37.009216: step: 636/530, loss: 0.1713005155324936
2023-01-21 09:36:38.233759: step: 640/530, loss: 0.10300713032484055
2023-01-21 09:36:39.391393: step: 644/530, loss: 0.7526707053184509
2023-01-21 09:36:40.527543: step: 648/530, loss: 0.019948624074459076
2023-01-21 09:36:41.722302: step: 652/530, loss: 0.2461063414812088
2023-01-21 09:36:42.920073: step: 656/530, loss: 0.15502089262008667
2023-01-21 09:36:44.122899: step: 660/530, loss: 0.41894522309303284
2023-01-21 09:36:45.303700: step: 664/530, loss: 0.4066603481769562
2023-01-21 09:36:46.507299: step: 668/530, loss: 0.15502452850341797
2023-01-21 09:36:47.691064: step: 672/530, loss: 0.4313339293003082
2023-01-21 09:36:48.852804: step: 676/530, loss: 0.48768892884254456
2023-01-21 09:36:50.086894: step: 680/530, loss: 0.11617843806743622
2023-01-21 09:36:51.224120: step: 684/530, loss: 0.13444571197032928
2023-01-21 09:36:52.382112: step: 688/530, loss: 0.37437766790390015
2023-01-21 09:36:53.531347: step: 692/530, loss: 0.07187018543481827
2023-01-21 09:36:54.693704: step: 696/530, loss: 0.11756696552038193
2023-01-21 09:36:55.906245: step: 700/530, loss: 3.940164566040039
2023-01-21 09:36:57.104080: step: 704/530, loss: 0.06498441845178604
2023-01-21 09:36:58.309602: step: 708/530, loss: 0.2053930014371872
2023-01-21 09:36:59.470264: step: 712/530, loss: 0.07378659397363663
2023-01-21 09:37:00.633837: step: 716/530, loss: 0.18421611189842224
2023-01-21 09:37:01.824770: step: 720/530, loss: 0.10775584727525711
2023-01-21 09:37:03.002166: step: 724/530, loss: 0.08516879379749298
2023-01-21 09:37:04.179130: step: 728/530, loss: 0.08640408515930176
2023-01-21 09:37:05.320969: step: 732/530, loss: 0.09573392570018768
2023-01-21 09:37:06.468202: step: 736/530, loss: 0.11057873070240021
2023-01-21 09:37:07.661616: step: 740/530, loss: 0.06999216228723526
2023-01-21 09:37:08.850842: step: 744/530, loss: 0.1182766929268837
2023-01-21 09:37:10.038700: step: 748/530, loss: 0.04304523393511772
2023-01-21 09:37:11.227004: step: 752/530, loss: 0.2601346969604492
2023-01-21 09:37:12.437883: step: 756/530, loss: 0.01540765818208456
2023-01-21 09:37:13.647650: step: 760/530, loss: 0.11564979702234268
2023-01-21 09:37:14.865146: step: 764/530, loss: 0.11279264092445374
2023-01-21 09:37:16.044282: step: 768/530, loss: 0.46986180543899536
2023-01-21 09:37:17.224372: step: 772/530, loss: 0.05500664934515953
2023-01-21 09:37:18.435360: step: 776/530, loss: 0.04750258848071098
2023-01-21 09:37:19.637605: step: 780/530, loss: 0.06596078723669052
2023-01-21 09:37:20.813834: step: 784/530, loss: 0.21787172555923462
2023-01-21 09:37:21.994530: step: 788/530, loss: 0.1595068871974945
2023-01-21 09:37:23.147336: step: 792/530, loss: 0.0601864829659462
2023-01-21 09:37:24.343514: step: 796/530, loss: 0.18331070244312286
2023-01-21 09:37:25.518442: step: 800/530, loss: 0.08046464622020721
2023-01-21 09:37:26.696777: step: 804/530, loss: 0.19010934233665466
2023-01-21 09:37:27.871107: step: 808/530, loss: 1.52919340133667
2023-01-21 09:37:29.059461: step: 812/530, loss: 0.17202357947826385
2023-01-21 09:37:30.249707: step: 816/530, loss: 0.04172716289758682
2023-01-21 09:37:31.437958: step: 820/530, loss: 0.03725111484527588
2023-01-21 09:37:32.604967: step: 824/530, loss: 0.04828687012195587
2023-01-21 09:37:33.838682: step: 828/530, loss: 0.05922241136431694
2023-01-21 09:37:35.105810: step: 832/530, loss: 0.21861086785793304
2023-01-21 09:37:36.284543: step: 836/530, loss: 0.09946451336145401
2023-01-21 09:37:37.438992: step: 840/530, loss: 0.8517389297485352
2023-01-21 09:37:38.570895: step: 844/530, loss: 0.09241466969251633
2023-01-21 09:37:39.738370: step: 848/530, loss: 0.12905187904834747
2023-01-21 09:37:40.868529: step: 852/530, loss: 0.030449392274022102
2023-01-21 09:37:41.985235: step: 856/530, loss: 0.08473119884729385
2023-01-21 09:37:43.209248: step: 860/530, loss: 0.2513468861579895
2023-01-21 09:37:44.412983: step: 864/530, loss: 0.03664522245526314
2023-01-21 09:37:45.609668: step: 868/530, loss: 0.08919048309326172
2023-01-21 09:37:46.822201: step: 872/530, loss: 0.2815885543823242
2023-01-21 09:37:48.023170: step: 876/530, loss: 0.062203314155340195
2023-01-21 09:37:49.204970: step: 880/530, loss: 0.04152614623308182
2023-01-21 09:37:50.378181: step: 884/530, loss: 0.01859750598669052
2023-01-21 09:37:51.570835: step: 888/530, loss: 0.1269826889038086
2023-01-21 09:37:52.754271: step: 892/530, loss: 0.28606393933296204
2023-01-21 09:37:53.906703: step: 896/530, loss: 0.29924410581588745
2023-01-21 09:37:55.047309: step: 900/530, loss: 0.06352901458740234
2023-01-21 09:37:56.186984: step: 904/530, loss: 0.33215630054473877
2023-01-21 09:37:57.362887: step: 908/530, loss: 0.09093455970287323
2023-01-21 09:37:58.578031: step: 912/530, loss: 0.15749092400074005
2023-01-21 09:37:59.767818: step: 916/530, loss: 0.38159170746803284
2023-01-21 09:38:00.931758: step: 920/530, loss: 0.3248440623283386
2023-01-21 09:38:02.077736: step: 924/530, loss: 0.3977890908718109
2023-01-21 09:38:03.235022: step: 928/530, loss: 0.277304083108902
2023-01-21 09:38:04.427586: step: 932/530, loss: 0.17513667047023773
2023-01-21 09:38:05.607663: step: 936/530, loss: 0.12967829406261444
2023-01-21 09:38:06.800333: step: 940/530, loss: 0.1831471472978592
2023-01-21 09:38:07.981039: step: 944/530, loss: 0.30447331070899963
2023-01-21 09:38:09.160114: step: 948/530, loss: 0.07016663998365402
2023-01-21 09:38:10.359215: step: 952/530, loss: 0.22592414915561676
2023-01-21 09:38:11.528158: step: 956/530, loss: 0.3500085771083832
2023-01-21 09:38:12.700898: step: 960/530, loss: 0.16564425826072693
2023-01-21 09:38:13.901733: step: 964/530, loss: 0.08719868957996368
2023-01-21 09:38:15.063101: step: 968/530, loss: 0.04791107028722763
2023-01-21 09:38:16.238458: step: 972/530, loss: 0.104514479637146
2023-01-21 09:38:17.406626: step: 976/530, loss: 0.072528176009655
2023-01-21 09:38:18.616981: step: 980/530, loss: 0.1263895034790039
2023-01-21 09:38:19.782211: step: 984/530, loss: 0.22149062156677246
2023-01-21 09:38:20.941434: step: 988/530, loss: 0.11591244488954544
2023-01-21 09:38:22.092927: step: 992/530, loss: 0.11690769344568253
2023-01-21 09:38:23.277390: step: 996/530, loss: 0.08022499829530716
2023-01-21 09:38:24.482324: step: 1000/530, loss: 0.26442793011665344
2023-01-21 09:38:25.683475: step: 1004/530, loss: 0.5984104871749878
2023-01-21 09:38:26.890145: step: 1008/530, loss: 0.045149803161621094
2023-01-21 09:38:28.077399: step: 1012/530, loss: 0.37886887788772583
2023-01-21 09:38:29.264904: step: 1016/530, loss: 0.014014697633683681
2023-01-21 09:38:30.435195: step: 1020/530, loss: 0.25458794832229614
2023-01-21 09:38:31.609350: step: 1024/530, loss: 0.13895197212696075
2023-01-21 09:38:32.829353: step: 1028/530, loss: 0.0756019577383995
2023-01-21 09:38:34.012460: step: 1032/530, loss: 0.266292005777359
2023-01-21 09:38:35.190195: step: 1036/530, loss: 0.04258022457361221
2023-01-21 09:38:36.371369: step: 1040/530, loss: 0.001929426216520369
2023-01-21 09:38:37.572751: step: 1044/530, loss: 0.08785466849803925
2023-01-21 09:38:38.724824: step: 1048/530, loss: 0.23387575149536133
2023-01-21 09:38:39.921512: step: 1052/530, loss: 0.17601117491722107
2023-01-21 09:38:41.082020: step: 1056/530, loss: 0.3353537619113922
2023-01-21 09:38:42.257170: step: 1060/530, loss: 0.4735613763332367
2023-01-21 09:38:43.423659: step: 1064/530, loss: 0.2276001274585724
2023-01-21 09:38:44.622266: step: 1068/530, loss: 0.6217465400695801
2023-01-21 09:38:45.798616: step: 1072/530, loss: 0.7792909741401672
2023-01-21 09:38:46.943979: step: 1076/530, loss: 0.15578937530517578
2023-01-21 09:38:48.112941: step: 1080/530, loss: 0.22179098427295685
2023-01-21 09:38:49.277539: step: 1084/530, loss: 1.0540108680725098
2023-01-21 09:38:50.422508: step: 1088/530, loss: 0.21569758653640747
2023-01-21 09:38:51.685594: step: 1092/530, loss: 0.04044456407427788
2023-01-21 09:38:52.850280: step: 1096/530, loss: 0.22390252351760864
2023-01-21 09:38:54.026303: step: 1100/530, loss: 0.05426378548145294
2023-01-21 09:38:55.201192: step: 1104/530, loss: 0.11736168712377548
2023-01-21 09:38:56.360289: step: 1108/530, loss: 0.031081369146704674
2023-01-21 09:38:57.555642: step: 1112/530, loss: 0.16550886631011963
2023-01-21 09:38:58.748036: step: 1116/530, loss: 0.06916656345129013
2023-01-21 09:38:59.947896: step: 1120/530, loss: 0.4130594730377197
2023-01-21 09:39:01.120785: step: 1124/530, loss: 0.026887942105531693
2023-01-21 09:39:02.315254: step: 1128/530, loss: 0.024235010147094727
2023-01-21 09:39:03.495711: step: 1132/530, loss: 0.21376925706863403
2023-01-21 09:39:04.622151: step: 1136/530, loss: 0.07202515751123428
2023-01-21 09:39:05.792753: step: 1140/530, loss: 0.15049400925636292
2023-01-21 09:39:06.959227: step: 1144/530, loss: 0.07807321846485138
2023-01-21 09:39:08.195453: step: 1148/530, loss: 0.4974941313266754
2023-01-21 09:39:09.365727: step: 1152/530, loss: 0.08205976337194443
2023-01-21 09:39:10.547140: step: 1156/530, loss: 0.29773080348968506
2023-01-21 09:39:11.740398: step: 1160/530, loss: 0.10683698952198029
2023-01-21 09:39:12.931235: step: 1164/530, loss: 0.1837387979030609
2023-01-21 09:39:14.077804: step: 1168/530, loss: 0.0656818374991417
2023-01-21 09:39:15.265392: step: 1172/530, loss: 0.022454883903265
2023-01-21 09:39:16.435184: step: 1176/530, loss: 0.2713330388069153
2023-01-21 09:39:17.610127: step: 1180/530, loss: 0.23397935926914215
2023-01-21 09:39:18.764518: step: 1184/530, loss: 0.02392716519534588
2023-01-21 09:39:19.939385: step: 1188/530, loss: 0.18648405373096466
2023-01-21 09:39:21.152661: step: 1192/530, loss: 0.32331523299217224
2023-01-21 09:39:22.317723: step: 1196/530, loss: 0.40959683060646057
2023-01-21 09:39:23.515801: step: 1200/530, loss: 0.0525268130004406
2023-01-21 09:39:24.726689: step: 1204/530, loss: 0.10861825942993164
2023-01-21 09:39:25.912873: step: 1208/530, loss: 0.6877531409263611
2023-01-21 09:39:27.083960: step: 1212/530, loss: 0.12965837121009827
2023-01-21 09:39:28.258707: step: 1216/530, loss: 0.07224531471729279
2023-01-21 09:39:29.452731: step: 1220/530, loss: 0.11181239783763885
2023-01-21 09:39:30.658051: step: 1224/530, loss: 0.5127602815628052
2023-01-21 09:39:31.910276: step: 1228/530, loss: 0.07286586612462997
2023-01-21 09:39:33.096538: step: 1232/530, loss: 0.10349297523498535
2023-01-21 09:39:34.224767: step: 1236/530, loss: 0.17519474029541016
2023-01-21 09:39:35.434903: step: 1240/530, loss: 0.31951475143432617
2023-01-21 09:39:36.632010: step: 1244/530, loss: 0.2518370747566223
2023-01-21 09:39:37.800676: step: 1248/530, loss: 0.17135295271873474
2023-01-21 09:39:38.927085: step: 1252/530, loss: 0.10881710052490234
2023-01-21 09:39:40.149652: step: 1256/530, loss: 0.22652125358581543
2023-01-21 09:39:41.340688: step: 1260/530, loss: 0.11236973106861115
2023-01-21 09:39:42.527710: step: 1264/530, loss: 0.06836242973804474
2023-01-21 09:39:43.702375: step: 1268/530, loss: 0.24818316102027893
2023-01-21 09:39:44.890126: step: 1272/530, loss: 0.14482879638671875
2023-01-21 09:39:46.081236: step: 1276/530, loss: 0.41327062249183655
2023-01-21 09:39:47.249627: step: 1280/530, loss: 0.1635892391204834
2023-01-21 09:39:48.427101: step: 1284/530, loss: 0.2615838348865509
2023-01-21 09:39:49.597963: step: 1288/530, loss: 0.254215806722641
2023-01-21 09:39:50.829137: step: 1292/530, loss: 0.09254173934459686
2023-01-21 09:39:52.066938: step: 1296/530, loss: 0.22869205474853516
2023-01-21 09:39:53.233621: step: 1300/530, loss: 0.21679291129112244
2023-01-21 09:39:54.470837: step: 1304/530, loss: 0.2935813069343567
2023-01-21 09:39:55.617836: step: 1308/530, loss: 0.058591797947883606
2023-01-21 09:39:56.835770: step: 1312/530, loss: 0.11359415203332901
2023-01-21 09:39:57.998079: step: 1316/530, loss: 0.12141337990760803
2023-01-21 09:39:59.141061: step: 1320/530, loss: 0.04539071023464203
2023-01-21 09:40:00.308739: step: 1324/530, loss: 0.4009132385253906
2023-01-21 09:40:01.464727: step: 1328/530, loss: 0.20982302725315094
2023-01-21 09:40:02.618966: step: 1332/530, loss: 0.02230815961956978
2023-01-21 09:40:03.851566: step: 1336/530, loss: 0.17309704422950745
2023-01-21 09:40:05.055275: step: 1340/530, loss: 0.27344274520874023
2023-01-21 09:40:06.213271: step: 1344/530, loss: 0.13963204622268677
2023-01-21 09:40:07.427031: step: 1348/530, loss: 0.20550794899463654
2023-01-21 09:40:08.573888: step: 1352/530, loss: 0.06766577064990997
2023-01-21 09:40:09.741824: step: 1356/530, loss: 0.11327500641345978
2023-01-21 09:40:10.938796: step: 1360/530, loss: 0.042272426187992096
2023-01-21 09:40:12.136795: step: 1364/530, loss: 0.18981322646141052
2023-01-21 09:40:13.309433: step: 1368/530, loss: 0.13702067732810974
2023-01-21 09:40:14.495005: step: 1372/530, loss: 0.0883081704378128
2023-01-21 09:40:15.704763: step: 1376/530, loss: 0.06375580281019211
2023-01-21 09:40:16.901478: step: 1380/530, loss: 0.4949127733707428
2023-01-21 09:40:18.062305: step: 1384/530, loss: 0.18713369965553284
2023-01-21 09:40:19.274542: step: 1388/530, loss: 0.5032480955123901
2023-01-21 09:40:20.500251: step: 1392/530, loss: 0.44389107823371887
2023-01-21 09:40:21.652464: step: 1396/530, loss: 0.16145333647727966
2023-01-21 09:40:22.818600: step: 1400/530, loss: 0.11670824885368347
2023-01-21 09:40:23.977781: step: 1404/530, loss: 0.6060651540756226
2023-01-21 09:40:25.158025: step: 1408/530, loss: 0.1625884771347046
2023-01-21 09:40:26.335558: step: 1412/530, loss: 0.21657666563987732
2023-01-21 09:40:27.535524: step: 1416/530, loss: 0.3495885729789734
2023-01-21 09:40:28.761354: step: 1420/530, loss: 0.09297314286231995
2023-01-21 09:40:29.984310: step: 1424/530, loss: 0.3674611747264862
2023-01-21 09:40:31.158329: step: 1428/530, loss: 0.2757939398288727
2023-01-21 09:40:32.340141: step: 1432/530, loss: 0.05768880993127823
2023-01-21 09:40:33.530368: step: 1436/530, loss: 0.03877716138958931
2023-01-21 09:40:34.705024: step: 1440/530, loss: 0.20939913392066956
2023-01-21 09:40:35.887430: step: 1444/530, loss: 0.053881026804447174
2023-01-21 09:40:37.134848: step: 1448/530, loss: 0.15194934606552124
2023-01-21 09:40:38.348632: step: 1452/530, loss: 0.02866850048303604
2023-01-21 09:40:39.551932: step: 1456/530, loss: 0.02809877321124077
2023-01-21 09:40:40.753476: step: 1460/530, loss: 0.38257598876953125
2023-01-21 09:40:41.919267: step: 1464/530, loss: 0.09262686222791672
2023-01-21 09:40:43.139122: step: 1468/530, loss: 0.16281461715698242
2023-01-21 09:40:44.334658: step: 1472/530, loss: 0.5011531710624695
2023-01-21 09:40:45.472734: step: 1476/530, loss: 0.10147133469581604
2023-01-21 09:40:46.624280: step: 1480/530, loss: 0.18984031677246094
2023-01-21 09:40:47.834563: step: 1484/530, loss: 0.13359498977661133
2023-01-21 09:40:49.077258: step: 1488/530, loss: 0.06452690809965134
2023-01-21 09:40:50.274177: step: 1492/530, loss: 0.1623123288154602
2023-01-21 09:40:51.456230: step: 1496/530, loss: 0.21236935257911682
2023-01-21 09:40:52.608873: step: 1500/530, loss: 0.07098865509033203
2023-01-21 09:40:53.832513: step: 1504/530, loss: 0.21271392703056335
2023-01-21 09:40:54.990823: step: 1508/530, loss: 0.167958065867424
2023-01-21 09:40:56.209656: step: 1512/530, loss: 0.19202661514282227
2023-01-21 09:40:57.418893: step: 1516/530, loss: 0.05480156093835831
2023-01-21 09:40:58.572420: step: 1520/530, loss: 0.3604586720466614
2023-01-21 09:40:59.769394: step: 1524/530, loss: 0.11887330561876297
2023-01-21 09:41:00.966782: step: 1528/530, loss: 0.026724625378847122
2023-01-21 09:41:02.149229: step: 1532/530, loss: 0.05379314720630646
2023-01-21 09:41:03.341498: step: 1536/530, loss: 0.6916292309761047
2023-01-21 09:41:04.522178: step: 1540/530, loss: 0.060868166387081146
2023-01-21 09:41:05.713124: step: 1544/530, loss: 0.17217856645584106
2023-01-21 09:41:06.922614: step: 1548/530, loss: 0.06487293541431427
2023-01-21 09:41:08.139817: step: 1552/530, loss: 0.9422714710235596
2023-01-21 09:41:09.296479: step: 1556/530, loss: 0.0428529754281044
2023-01-21 09:41:10.469119: step: 1560/530, loss: 0.3080798089504242
2023-01-21 09:41:11.645557: step: 1564/530, loss: 0.11116448044776917
2023-01-21 09:41:12.840934: step: 1568/530, loss: 0.4356522560119629
2023-01-21 09:41:13.976740: step: 1572/530, loss: 0.12339887768030167
2023-01-21 09:41:15.139562: step: 1576/530, loss: 0.7481446266174316
2023-01-21 09:41:16.369010: step: 1580/530, loss: 0.2189142107963562
2023-01-21 09:41:17.513360: step: 1584/530, loss: 0.04491496458649635
2023-01-21 09:41:18.676682: step: 1588/530, loss: 0.1289730966091156
2023-01-21 09:41:19.901366: step: 1592/530, loss: 0.5015445947647095
2023-01-21 09:41:21.053756: step: 1596/530, loss: 0.1384941041469574
2023-01-21 09:41:22.259959: step: 1600/530, loss: 0.26652345061302185
2023-01-21 09:41:23.454468: step: 1604/530, loss: 0.037052348256111145
2023-01-21 09:41:24.600236: step: 1608/530, loss: 0.06890163570642471
2023-01-21 09:41:25.785567: step: 1612/530, loss: 0.1330997496843338
2023-01-21 09:41:26.988939: step: 1616/530, loss: 0.024618053808808327
2023-01-21 09:41:28.186324: step: 1620/530, loss: 0.10659518837928772
2023-01-21 09:41:29.327889: step: 1624/530, loss: 1.145443320274353
2023-01-21 09:41:30.536901: step: 1628/530, loss: 0.22101622819900513
2023-01-21 09:41:31.702483: step: 1632/530, loss: 0.0627477690577507
2023-01-21 09:41:32.844058: step: 1636/530, loss: 0.42687684297561646
2023-01-21 09:41:34.029859: step: 1640/530, loss: 0.08497443050146103
2023-01-21 09:41:35.216568: step: 1644/530, loss: 0.7222959399223328
2023-01-21 09:41:36.392797: step: 1648/530, loss: 0.25410300493240356
2023-01-21 09:41:37.560057: step: 1652/530, loss: 0.04539642482995987
2023-01-21 09:41:38.734063: step: 1656/530, loss: 0.07592014968395233
2023-01-21 09:41:39.992027: step: 1660/530, loss: 0.09428376704454422
2023-01-21 09:41:41.201943: step: 1664/530, loss: 0.09538131207227707
2023-01-21 09:41:42.381881: step: 1668/530, loss: 0.09697631001472473
2023-01-21 09:41:43.562671: step: 1672/530, loss: 0.5140761733055115
2023-01-21 09:41:44.759754: step: 1676/530, loss: 0.18768806755542755
2023-01-21 09:41:45.950731: step: 1680/530, loss: 0.1679764688014984
2023-01-21 09:41:47.136261: step: 1684/530, loss: 0.17716084420681
2023-01-21 09:41:48.333122: step: 1688/530, loss: 0.30185890197753906
2023-01-21 09:41:49.548154: step: 1692/530, loss: 0.11596088111400604
2023-01-21 09:41:50.696887: step: 1696/530, loss: 0.08103790879249573
2023-01-21 09:41:51.917517: step: 1700/530, loss: 0.2951926290988922
2023-01-21 09:41:53.110145: step: 1704/530, loss: 0.15465545654296875
2023-01-21 09:41:54.311972: step: 1708/530, loss: 0.19264689087867737
2023-01-21 09:41:55.469422: step: 1712/530, loss: 0.1892094612121582
2023-01-21 09:41:56.651653: step: 1716/530, loss: 0.18235455453395844
2023-01-21 09:41:57.840783: step: 1720/530, loss: 0.47205695509910583
2023-01-21 09:41:59.052131: step: 1724/530, loss: 0.4763912260532379
2023-01-21 09:42:00.211649: step: 1728/530, loss: 0.20937252044677734
2023-01-21 09:42:01.407708: step: 1732/530, loss: 0.08466408401727676
2023-01-21 09:42:02.589670: step: 1736/530, loss: 0.079167939722538
2023-01-21 09:42:03.771029: step: 1740/530, loss: 0.1463976800441742
2023-01-21 09:42:04.958596: step: 1744/530, loss: 0.22479954361915588
2023-01-21 09:42:06.163298: step: 1748/530, loss: 0.11581498384475708
2023-01-21 09:42:07.330698: step: 1752/530, loss: 0.07075386494398117
2023-01-21 09:42:08.494024: step: 1756/530, loss: 0.03870382532477379
2023-01-21 09:42:09.660413: step: 1760/530, loss: 0.05649767071008682
2023-01-21 09:42:10.820518: step: 1764/530, loss: 0.20501813292503357
2023-01-21 09:42:12.032197: step: 1768/530, loss: 0.45368680357933044
2023-01-21 09:42:13.263288: step: 1772/530, loss: 0.1366896629333496
2023-01-21 09:42:14.437727: step: 1776/530, loss: 0.06291971355676651
2023-01-21 09:42:15.595120: step: 1780/530, loss: 0.03423266485333443
2023-01-21 09:42:16.808452: step: 1784/530, loss: 0.358668714761734
2023-01-21 09:42:17.981969: step: 1788/530, loss: 0.1780066043138504
2023-01-21 09:42:19.141384: step: 1792/530, loss: 0.04669199138879776
2023-01-21 09:42:20.302950: step: 1796/530, loss: 0.08929596096277237
2023-01-21 09:42:21.544778: step: 1800/530, loss: 0.4923345446586609
2023-01-21 09:42:22.736574: step: 1804/530, loss: 0.18945695459842682
2023-01-21 09:42:23.877198: step: 1808/530, loss: 0.2367473542690277
2023-01-21 09:42:25.066540: step: 1812/530, loss: 0.16152162849903107
2023-01-21 09:42:26.226762: step: 1816/530, loss: 0.04120578616857529
2023-01-21 09:42:27.409143: step: 1820/530, loss: 0.010090827941894531
2023-01-21 09:42:28.635858: step: 1824/530, loss: 0.3527812063694
2023-01-21 09:42:29.807253: step: 1828/530, loss: 0.07495997101068497
2023-01-21 09:42:31.001198: step: 1832/530, loss: 0.09046153724193573
2023-01-21 09:42:32.155542: step: 1836/530, loss: 0.283687949180603
2023-01-21 09:42:33.372084: step: 1840/530, loss: 0.09865465015172958
2023-01-21 09:42:34.537829: step: 1844/530, loss: 0.03781280666589737
2023-01-21 09:42:35.735541: step: 1848/530, loss: 0.08862370997667313
2023-01-21 09:42:36.932292: step: 1852/530, loss: 0.04232124984264374
2023-01-21 09:42:38.097309: step: 1856/530, loss: 0.11981821805238724
2023-01-21 09:42:39.291966: step: 1860/530, loss: 0.07902250438928604
2023-01-21 09:42:40.438598: step: 1864/530, loss: 0.17948079109191895
2023-01-21 09:42:41.609119: step: 1868/530, loss: 0.7560935616493225
2023-01-21 09:42:42.795458: step: 1872/530, loss: 0.17908230423927307
2023-01-21 09:42:43.945744: step: 1876/530, loss: 0.0672379583120346
2023-01-21 09:42:45.101411: step: 1880/530, loss: 0.19324421882629395
2023-01-21 09:42:46.270790: step: 1884/530, loss: 0.1315620392560959
2023-01-21 09:42:47.519094: step: 1888/530, loss: 1.4661343097686768
2023-01-21 09:42:48.675966: step: 1892/530, loss: 0.04889678955078125
2023-01-21 09:42:49.865379: step: 1896/530, loss: 1.085402250289917
2023-01-21 09:42:51.047538: step: 1900/530, loss: 0.19848766922950745
2023-01-21 09:42:52.250294: step: 1904/530, loss: 0.03242054209113121
2023-01-21 09:42:53.436363: step: 1908/530, loss: 0.08120203763246536
2023-01-21 09:42:54.621928: step: 1912/530, loss: 0.16075477004051208
2023-01-21 09:42:55.747632: step: 1916/530, loss: 0.9542765021324158
2023-01-21 09:42:56.926954: step: 1920/530, loss: 0.061582375317811966
2023-01-21 09:42:58.120254: step: 1924/530, loss: 0.13597260415554047
2023-01-21 09:42:59.294702: step: 1928/530, loss: 0.3454255163669586
2023-01-21 09:43:00.480823: step: 1932/530, loss: 0.08326606452465057
2023-01-21 09:43:01.660235: step: 1936/530, loss: 0.11447310447692871
2023-01-21 09:43:02.827118: step: 1940/530, loss: 0.17711572349071503
2023-01-21 09:43:03.994401: step: 1944/530, loss: 0.0465083122253418
2023-01-21 09:43:05.174220: step: 1948/530, loss: 0.06987696141004562
2023-01-21 09:43:06.403837: step: 1952/530, loss: 0.11709193885326385
2023-01-21 09:43:07.586130: step: 1956/530, loss: 0.26295509934425354
2023-01-21 09:43:08.790427: step: 1960/530, loss: 0.022184133529663086
2023-01-21 09:43:09.956146: step: 1964/530, loss: 0.3024407625198364
2023-01-21 09:43:11.157705: step: 1968/530, loss: 0.6750398874282837
2023-01-21 09:43:12.338491: step: 1972/530, loss: 0.18277758359909058
2023-01-21 09:43:13.561496: step: 1976/530, loss: 0.2745946943759918
2023-01-21 09:43:14.728351: step: 1980/530, loss: 0.15864916145801544
2023-01-21 09:43:15.911201: step: 1984/530, loss: 0.3288671374320984
2023-01-21 09:43:17.131033: step: 1988/530, loss: 0.9767069220542908
2023-01-21 09:43:18.317889: step: 1992/530, loss: 1.5673187971115112
2023-01-21 09:43:19.538689: step: 1996/530, loss: 0.0969463363289833
2023-01-21 09:43:20.735838: step: 2000/530, loss: 0.139842227101326
2023-01-21 09:43:21.970919: step: 2004/530, loss: 0.3081510663032532
2023-01-21 09:43:23.131989: step: 2008/530, loss: 0.07534036785364151
2023-01-21 09:43:24.312733: step: 2012/530, loss: 0.18714800477027893
2023-01-21 09:43:25.481123: step: 2016/530, loss: 0.030483627691864967
2023-01-21 09:43:26.647347: step: 2020/530, loss: 0.09415969997644424
2023-01-21 09:43:27.843219: step: 2024/530, loss: 0.0832182914018631
2023-01-21 09:43:29.008266: step: 2028/530, loss: 0.08717307448387146
2023-01-21 09:43:30.202394: step: 2032/530, loss: 0.041825298219919205
2023-01-21 09:43:31.358588: step: 2036/530, loss: 0.19072560966014862
2023-01-21 09:43:32.549580: step: 2040/530, loss: 0.181163027882576
2023-01-21 09:43:33.736338: step: 2044/530, loss: 0.13531243801116943
2023-01-21 09:43:34.927627: step: 2048/530, loss: 0.27516451478004456
2023-01-21 09:43:36.070689: step: 2052/530, loss: 0.19184771180152893
2023-01-21 09:43:37.298757: step: 2056/530, loss: 0.11333389580249786
2023-01-21 09:43:38.456383: step: 2060/530, loss: 0.24420642852783203
2023-01-21 09:43:39.633093: step: 2064/530, loss: 0.18805399537086487
2023-01-21 09:43:40.822820: step: 2068/530, loss: 0.16511748731136322
2023-01-21 09:43:41.976378: step: 2072/530, loss: 0.15647053718566895
2023-01-21 09:43:43.137596: step: 2076/530, loss: 0.09461411833763123
2023-01-21 09:43:44.307902: step: 2080/530, loss: 0.2717522382736206
2023-01-21 09:43:45.472628: step: 2084/530, loss: 0.05843100696802139
2023-01-21 09:43:46.655015: step: 2088/530, loss: 0.07341928780078888
2023-01-21 09:43:47.861393: step: 2092/530, loss: 0.32600533962249756
2023-01-21 09:43:49.045728: step: 2096/530, loss: 0.013328456319868565
2023-01-21 09:43:50.238160: step: 2100/530, loss: 0.025843096897006035
2023-01-21 09:43:51.449673: step: 2104/530, loss: 0.22217494249343872
2023-01-21 09:43:52.605218: step: 2108/530, loss: 0.13391447067260742
2023-01-21 09:43:53.766759: step: 2112/530, loss: 0.1020805835723877
2023-01-21 09:43:54.928501: step: 2116/530, loss: 0.0932595282793045
2023-01-21 09:43:56.090898: step: 2120/530, loss: 0.19845615327358246
==================================================
Loss: 0.201
--------------------
Dev: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.5348837209302325, 'r': 0.8518518518518519, 'f1': 0.6571428571428571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.6226415094339622, 'r': 0.5238095238095238, 'f1': 0.5689655172413793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.5348837209302325, 'r': 0.8518518518518519, 'f1': 0.6571428571428571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:44:49.727826: step: 4/530, loss: 0.13870659470558167
2023-01-21 09:44:50.902062: step: 8/530, loss: 0.10851836204528809
2023-01-21 09:44:52.096461: step: 12/530, loss: 0.08128185570240021
2023-01-21 09:44:53.358383: step: 16/530, loss: 0.11258268356323242
2023-01-21 09:44:54.522619: step: 20/530, loss: 0.027537060901522636
2023-01-21 09:44:55.678800: step: 24/530, loss: 0.2404797524213791
2023-01-21 09:44:56.859810: step: 28/530, loss: 0.44863930344581604
2023-01-21 09:44:58.065285: step: 32/530, loss: 0.2597617506980896
2023-01-21 09:44:59.250427: step: 36/530, loss: 0.04968414083123207
2023-01-21 09:45:00.420026: step: 40/530, loss: 0.035601094365119934
2023-01-21 09:45:01.629278: step: 44/530, loss: 0.04424639046192169
2023-01-21 09:45:02.809996: step: 48/530, loss: 0.1674940139055252
2023-01-21 09:45:04.000032: step: 52/530, loss: 0.05557575076818466
2023-01-21 09:45:05.197050: step: 56/530, loss: 0.3687129616737366
2023-01-21 09:45:06.442108: step: 60/530, loss: 0.028432179242372513
2023-01-21 09:45:07.638331: step: 64/530, loss: 0.3487391471862793
2023-01-21 09:45:08.834911: step: 68/530, loss: 0.21637079119682312
2023-01-21 09:45:10.007812: step: 72/530, loss: 0.17811241745948792
2023-01-21 09:45:11.201388: step: 76/530, loss: 0.27146539092063904
2023-01-21 09:45:12.372981: step: 80/530, loss: 0.02970714494585991
2023-01-21 09:45:13.541245: step: 84/530, loss: 0.0748889371752739
2023-01-21 09:45:14.742562: step: 88/530, loss: 0.065901979804039
2023-01-21 09:45:15.907393: step: 92/530, loss: 0.05597992241382599
2023-01-21 09:45:17.036812: step: 96/530, loss: 0.048613451421260834
2023-01-21 09:45:18.226907: step: 100/530, loss: 0.1583629548549652
2023-01-21 09:45:19.367279: step: 104/530, loss: 0.02549438551068306
2023-01-21 09:45:20.540648: step: 108/530, loss: 0.1274530440568924
2023-01-21 09:45:21.760890: step: 112/530, loss: 0.035146284848451614
2023-01-21 09:45:22.966289: step: 116/530, loss: 0.1478159874677658
2023-01-21 09:45:24.157689: step: 120/530, loss: 0.05417003482580185
2023-01-21 09:45:25.322064: step: 124/530, loss: 0.043192580342292786
2023-01-21 09:45:26.528814: step: 128/530, loss: 0.11024819314479828
2023-01-21 09:45:27.703185: step: 132/530, loss: 0.13626575469970703
2023-01-21 09:45:28.894361: step: 136/530, loss: 0.1544477492570877
2023-01-21 09:45:30.069136: step: 140/530, loss: 0.1496930569410324
2023-01-21 09:45:31.209332: step: 144/530, loss: 1.1508122682571411
2023-01-21 09:45:32.367024: step: 148/530, loss: 0.009707403369247913
2023-01-21 09:45:33.561718: step: 152/530, loss: 0.09510812908411026
2023-01-21 09:45:34.748370: step: 156/530, loss: 0.17367486655712128
2023-01-21 09:45:35.918813: step: 160/530, loss: 0.0844632163643837
2023-01-21 09:45:37.088876: step: 164/530, loss: 1.5996429920196533
2023-01-21 09:45:38.284302: step: 168/530, loss: 0.14349107444286346
2023-01-21 09:45:39.433430: step: 172/530, loss: 0.023441409692168236
2023-01-21 09:45:40.627450: step: 176/530, loss: 0.047010280191898346
2023-01-21 09:45:41.854338: step: 180/530, loss: 0.12685108184814453
2023-01-21 09:45:43.025016: step: 184/530, loss: 0.08097989857196808
2023-01-21 09:45:44.283592: step: 188/530, loss: 0.048520758748054504
2023-01-21 09:45:45.442322: step: 192/530, loss: 0.2404986023902893
2023-01-21 09:45:46.630248: step: 196/530, loss: 0.08595848083496094
2023-01-21 09:45:47.834623: step: 200/530, loss: 0.31033191084861755
2023-01-21 09:45:49.031659: step: 204/530, loss: 0.08308496326208115
2023-01-21 09:45:50.191405: step: 208/530, loss: 0.07387419044971466
2023-01-21 09:45:51.375103: step: 212/530, loss: 0.10461874306201935
2023-01-21 09:45:52.513581: step: 216/530, loss: 0.1028100997209549
2023-01-21 09:45:53.701823: step: 220/530, loss: 0.45689117908477783
2023-01-21 09:45:54.844280: step: 224/530, loss: 0.08931207656860352
2023-01-21 09:45:56.030271: step: 228/530, loss: 0.048334527760744095
2023-01-21 09:45:57.205611: step: 232/530, loss: 0.036681175231933594
2023-01-21 09:45:58.450484: step: 236/530, loss: 0.20698876678943634
2023-01-21 09:45:59.647194: step: 240/530, loss: 0.13018901646137238
2023-01-21 09:46:00.806616: step: 244/530, loss: 0.06413483619689941
2023-01-21 09:46:01.988416: step: 248/530, loss: 0.05094633251428604
2023-01-21 09:46:03.187678: step: 252/530, loss: 0.0870383232831955
2023-01-21 09:46:04.374168: step: 256/530, loss: 0.0700145736336708
2023-01-21 09:46:05.563966: step: 260/530, loss: 1.4168819189071655
2023-01-21 09:46:06.748818: step: 264/530, loss: 0.020598269999027252
2023-01-21 09:46:07.931705: step: 268/530, loss: 0.5548242330551147
2023-01-21 09:46:09.108216: step: 272/530, loss: 0.1224660873413086
2023-01-21 09:46:10.261527: step: 276/530, loss: 0.11279530823230743
2023-01-21 09:46:11.474842: step: 280/530, loss: 0.2495754361152649
2023-01-21 09:46:12.638064: step: 284/530, loss: 0.08925295621156693
2023-01-21 09:46:13.779820: step: 288/530, loss: 0.16690409183502197
2023-01-21 09:46:15.005273: step: 292/530, loss: 0.12735548615455627
2023-01-21 09:46:16.185924: step: 296/530, loss: 0.04003152996301651
2023-01-21 09:46:17.369636: step: 300/530, loss: 0.023646164685487747
2023-01-21 09:46:18.544845: step: 304/530, loss: 0.06558997929096222
2023-01-21 09:46:19.711417: step: 308/530, loss: 0.08696547150611877
2023-01-21 09:46:20.900842: step: 312/530, loss: 0.12637010216712952
2023-01-21 09:46:22.100165: step: 316/530, loss: 0.03858175501227379
2023-01-21 09:46:23.266225: step: 320/530, loss: 0.5158554911613464
2023-01-21 09:46:24.456560: step: 324/530, loss: 0.011658954434096813
2023-01-21 09:46:25.635635: step: 328/530, loss: 0.08313693851232529
2023-01-21 09:46:26.863178: step: 332/530, loss: 0.07755003124475479
2023-01-21 09:46:28.090708: step: 336/530, loss: 0.2044386863708496
2023-01-21 09:46:29.233878: step: 340/530, loss: 0.15821929275989532
2023-01-21 09:46:30.485614: step: 344/530, loss: 0.1118369996547699
2023-01-21 09:46:31.693811: step: 348/530, loss: 0.02092599868774414
2023-01-21 09:46:32.841401: step: 352/530, loss: 0.06402969360351562
2023-01-21 09:46:34.070926: step: 356/530, loss: 0.02071847952902317
2023-01-21 09:46:35.280510: step: 360/530, loss: 0.14521408081054688
2023-01-21 09:46:36.466477: step: 364/530, loss: 0.08247213810682297
2023-01-21 09:46:37.662527: step: 368/530, loss: 0.060596562922000885
2023-01-21 09:46:38.813636: step: 372/530, loss: 0.6380486488342285
2023-01-21 09:46:39.984355: step: 376/530, loss: 0.4088096618652344
2023-01-21 09:46:41.141021: step: 380/530, loss: 0.06871576607227325
2023-01-21 09:46:42.331224: step: 384/530, loss: 0.15540266036987305
2023-01-21 09:46:43.508033: step: 388/530, loss: 0.18892605602741241
2023-01-21 09:46:44.725581: step: 392/530, loss: 0.11419849097728729
2023-01-21 09:46:45.873875: step: 396/530, loss: 0.10056620091199875
2023-01-21 09:46:46.977223: step: 400/530, loss: 0.13915902376174927
2023-01-21 09:46:48.163267: step: 404/530, loss: 0.10136671364307404
2023-01-21 09:46:49.391269: step: 408/530, loss: 0.07748584449291229
2023-01-21 09:46:50.596963: step: 412/530, loss: 0.024372100830078125
2023-01-21 09:46:51.779754: step: 416/530, loss: 0.11834478378295898
2023-01-21 09:46:52.978244: step: 420/530, loss: 0.024622727185487747
2023-01-21 09:46:54.154399: step: 424/530, loss: 0.14065399765968323
2023-01-21 09:46:55.321082: step: 428/530, loss: 0.09721308201551437
2023-01-21 09:46:56.492551: step: 432/530, loss: 0.08102860301733017
2023-01-21 09:46:57.692085: step: 436/530, loss: 0.048135899007320404
2023-01-21 09:46:58.814986: step: 440/530, loss: 0.1590632200241089
2023-01-21 09:47:00.002745: step: 444/530, loss: 0.2028520554304123
2023-01-21 09:47:01.219912: step: 448/530, loss: 0.1192622184753418
2023-01-21 09:47:02.443617: step: 452/530, loss: 0.7575895190238953
2023-01-21 09:47:03.613194: step: 456/530, loss: 0.08304329216480255
2023-01-21 09:47:04.777204: step: 460/530, loss: 0.0701976791024208
2023-01-21 09:47:05.956743: step: 464/530, loss: 0.19155970215797424
2023-01-21 09:47:07.132719: step: 468/530, loss: 0.06760769337415695
2023-01-21 09:47:08.302142: step: 472/530, loss: 0.5125473141670227
2023-01-21 09:47:09.441342: step: 476/530, loss: 0.13938313722610474
2023-01-21 09:47:10.620578: step: 480/530, loss: 0.05063953623175621
2023-01-21 09:47:11.862584: step: 484/530, loss: 0.1459488868713379
2023-01-21 09:47:13.033845: step: 488/530, loss: 0.14793729782104492
2023-01-21 09:47:14.233147: step: 492/530, loss: 0.10498276352882385
2023-01-21 09:47:15.383275: step: 496/530, loss: 0.1654163897037506
2023-01-21 09:47:16.560941: step: 500/530, loss: 0.10975951701402664
2023-01-21 09:47:17.796432: step: 504/530, loss: 0.7173225283622742
2023-01-21 09:47:18.960632: step: 508/530, loss: 0.05371842160820961
2023-01-21 09:47:20.172107: step: 512/530, loss: 0.22930708527565002
2023-01-21 09:47:21.334852: step: 516/530, loss: 0.051342010498046875
2023-01-21 09:47:22.539959: step: 520/530, loss: 0.07384524494409561
2023-01-21 09:47:23.682225: step: 524/530, loss: 0.0777139663696289
2023-01-21 09:47:24.804943: step: 528/530, loss: 0.11190232634544373
2023-01-21 09:47:26.033830: step: 532/530, loss: 0.2026950865983963
2023-01-21 09:47:27.186079: step: 536/530, loss: 0.3991660177707672
2023-01-21 09:47:28.399212: step: 540/530, loss: 0.11361722648143768
2023-01-21 09:47:29.554062: step: 544/530, loss: 0.04473155736923218
2023-01-21 09:47:30.734850: step: 548/530, loss: 0.0492459312081337
2023-01-21 09:47:31.914889: step: 552/530, loss: 0.6628842949867249
2023-01-21 09:47:33.050369: step: 556/530, loss: 0.05882025137543678
2023-01-21 09:47:34.233596: step: 560/530, loss: 0.21934282779693604
2023-01-21 09:47:35.409490: step: 564/530, loss: 0.05720691755414009
2023-01-21 09:47:36.561041: step: 568/530, loss: 0.05353212356567383
2023-01-21 09:47:37.762811: step: 572/530, loss: 0.14908629655838013
2023-01-21 09:47:38.934619: step: 576/530, loss: 0.033939410001039505
2023-01-21 09:47:40.112566: step: 580/530, loss: 0.09566888958215714
2023-01-21 09:47:41.296957: step: 584/530, loss: 0.09796305000782013
2023-01-21 09:47:42.451746: step: 588/530, loss: 0.03454389423131943
2023-01-21 09:47:43.618903: step: 592/530, loss: 0.07813195884227753
2023-01-21 09:47:44.792401: step: 596/530, loss: 0.07436561584472656
2023-01-21 09:47:45.972303: step: 600/530, loss: 0.029509449377655983
2023-01-21 09:47:47.164679: step: 604/530, loss: 0.03202085196971893
2023-01-21 09:47:48.373192: step: 608/530, loss: 0.15977001190185547
2023-01-21 09:47:49.521071: step: 612/530, loss: 0.03294672444462776
2023-01-21 09:47:50.700137: step: 616/530, loss: 0.07999812066555023
2023-01-21 09:47:51.864987: step: 620/530, loss: 0.43825700879096985
2023-01-21 09:47:53.026585: step: 624/530, loss: 0.0037241936661303043
2023-01-21 09:47:54.179529: step: 628/530, loss: 0.1160547286272049
2023-01-21 09:47:55.371812: step: 632/530, loss: 0.0742734968662262
2023-01-21 09:47:56.578297: step: 636/530, loss: 0.10195188969373703
2023-01-21 09:47:57.780453: step: 640/530, loss: 0.04310021176934242
2023-01-21 09:47:58.940299: step: 644/530, loss: 0.11594219505786896
2023-01-21 09:48:00.116769: step: 648/530, loss: 0.08516745269298553
2023-01-21 09:48:01.294202: step: 652/530, loss: 0.19553527235984802
2023-01-21 09:48:02.457033: step: 656/530, loss: 0.012005400843918324
2023-01-21 09:48:03.665721: step: 660/530, loss: 0.06505639851093292
2023-01-21 09:48:04.830866: step: 664/530, loss: 0.09030401706695557
2023-01-21 09:48:06.003886: step: 668/530, loss: 0.18781937658786774
2023-01-21 09:48:07.229648: step: 672/530, loss: 0.3081260621547699
2023-01-21 09:48:08.395912: step: 676/530, loss: 0.6232860088348389
2023-01-21 09:48:09.567229: step: 680/530, loss: 0.07573743164539337
2023-01-21 09:48:10.740756: step: 684/530, loss: 0.10615397244691849
2023-01-21 09:48:11.937216: step: 688/530, loss: 0.03545580059289932
2023-01-21 09:48:13.092198: step: 692/530, loss: 0.08056831359863281
2023-01-21 09:48:14.322086: step: 696/530, loss: 0.1761191487312317
2023-01-21 09:48:15.506569: step: 700/530, loss: 0.12173967808485031
2023-01-21 09:48:16.718213: step: 704/530, loss: 0.08709517121315002
2023-01-21 09:48:17.897213: step: 708/530, loss: 0.3394899368286133
2023-01-21 09:48:19.101396: step: 712/530, loss: 0.061670683324337006
2023-01-21 09:48:20.292768: step: 716/530, loss: 0.04032144695520401
2023-01-21 09:48:21.451335: step: 720/530, loss: 0.0463688038289547
2023-01-21 09:48:22.642879: step: 724/530, loss: 0.14275655150413513
2023-01-21 09:48:23.800691: step: 728/530, loss: 0.05639352649450302
2023-01-21 09:48:24.981345: step: 732/530, loss: 0.028322555124759674
2023-01-21 09:48:26.166300: step: 736/530, loss: 0.057747747749090195
2023-01-21 09:48:27.390256: step: 740/530, loss: 0.08018913865089417
2023-01-21 09:48:28.566884: step: 744/530, loss: 0.09463682025671005
2023-01-21 09:48:29.759410: step: 748/530, loss: 0.2068311721086502
2023-01-21 09:48:30.937426: step: 752/530, loss: 0.059811901301145554
2023-01-21 09:48:32.128308: step: 756/530, loss: 0.04284505918622017
2023-01-21 09:48:33.326964: step: 760/530, loss: 0.22188082337379456
2023-01-21 09:48:34.479125: step: 764/530, loss: 0.09251490235328674
2023-01-21 09:48:35.661437: step: 768/530, loss: 0.22749634087085724
2023-01-21 09:48:36.850916: step: 772/530, loss: 0.46761876344680786
2023-01-21 09:48:38.039975: step: 776/530, loss: 0.15681257843971252
2023-01-21 09:48:39.247165: step: 780/530, loss: 0.0394928939640522
2023-01-21 09:48:40.402496: step: 784/530, loss: 0.8242636919021606
2023-01-21 09:48:41.592886: step: 788/530, loss: 0.0690513551235199
2023-01-21 09:48:42.763406: step: 792/530, loss: 0.12767724692821503
2023-01-21 09:48:43.951277: step: 796/530, loss: 0.1885465681552887
2023-01-21 09:48:45.124487: step: 800/530, loss: 0.027648210525512695
2023-01-21 09:48:46.316782: step: 804/530, loss: 0.5100517272949219
2023-01-21 09:48:47.486927: step: 808/530, loss: 0.22364681959152222
2023-01-21 09:48:48.631361: step: 812/530, loss: 0.03222065046429634
2023-01-21 09:48:49.810788: step: 816/530, loss: 1.3350963592529297
2023-01-21 09:48:50.970215: step: 820/530, loss: 0.0690191239118576
2023-01-21 09:48:52.181662: step: 824/530, loss: 0.01998310163617134
2023-01-21 09:48:53.340690: step: 828/530, loss: 0.10699691623449326
2023-01-21 09:48:54.543776: step: 832/530, loss: 0.033284954726696014
2023-01-21 09:48:55.700212: step: 836/530, loss: 0.7190266251564026
2023-01-21 09:48:56.869119: step: 840/530, loss: 0.09366126358509064
2023-01-21 09:48:58.060234: step: 844/530, loss: 0.06663629412651062
2023-01-21 09:48:59.283532: step: 848/530, loss: 0.09553766250610352
2023-01-21 09:49:00.428271: step: 852/530, loss: 0.03830909729003906
2023-01-21 09:49:01.664740: step: 856/530, loss: 0.10642127692699432
2023-01-21 09:49:02.873506: step: 860/530, loss: 0.26812100410461426
2023-01-21 09:49:04.036500: step: 864/530, loss: 0.04738941416144371
2023-01-21 09:49:05.172308: step: 868/530, loss: 0.4965672492980957
2023-01-21 09:49:06.367551: step: 872/530, loss: 0.1625833958387375
2023-01-21 09:49:07.535000: step: 876/530, loss: 0.2255706787109375
2023-01-21 09:49:08.688750: step: 880/530, loss: 0.34958744049072266
2023-01-21 09:49:09.825969: step: 884/530, loss: 0.05814345180988312
2023-01-21 09:49:11.006988: step: 888/530, loss: 0.7029643654823303
2023-01-21 09:49:12.205137: step: 892/530, loss: 0.2767925262451172
2023-01-21 09:49:13.358150: step: 896/530, loss: 0.08101079612970352
2023-01-21 09:49:14.557676: step: 900/530, loss: 0.12409114837646484
2023-01-21 09:49:15.760908: step: 904/530, loss: 0.14632092416286469
2023-01-21 09:49:16.951341: step: 908/530, loss: 0.09457479417324066
2023-01-21 09:49:18.128061: step: 912/530, loss: 0.15415644645690918
2023-01-21 09:49:19.280850: step: 916/530, loss: 0.2620663642883301
2023-01-21 09:49:20.451013: step: 920/530, loss: 0.19425325095653534
2023-01-21 09:49:21.689872: step: 924/530, loss: 0.16412056982517242
2023-01-21 09:49:22.857700: step: 928/530, loss: 0.11373564600944519
2023-01-21 09:49:23.992875: step: 932/530, loss: 0.053139328956604004
2023-01-21 09:49:25.168370: step: 936/530, loss: 0.8598411679267883
2023-01-21 09:49:26.344242: step: 940/530, loss: 0.041358090937137604
2023-01-21 09:49:27.542329: step: 944/530, loss: 0.12312659621238708
2023-01-21 09:49:28.727676: step: 948/530, loss: 0.06576715409755707
2023-01-21 09:49:29.907880: step: 952/530, loss: 0.12359118461608887
2023-01-21 09:49:31.083837: step: 956/530, loss: 0.05999374762177467
2023-01-21 09:49:32.282990: step: 960/530, loss: 0.14909592270851135
2023-01-21 09:49:33.467314: step: 964/530, loss: 0.24081745743751526
2023-01-21 09:49:34.631657: step: 968/530, loss: 0.04611378163099289
2023-01-21 09:49:35.798694: step: 972/530, loss: 0.08156175911426544
2023-01-21 09:49:36.993057: step: 976/530, loss: 0.06103034317493439
2023-01-21 09:49:38.178333: step: 980/530, loss: 0.040491484105587006
2023-01-21 09:49:39.342853: step: 984/530, loss: 0.11292321234941483
2023-01-21 09:49:40.523743: step: 988/530, loss: 0.1835372895002365
2023-01-21 09:49:41.699475: step: 992/530, loss: 0.05430328845977783
2023-01-21 09:49:42.895593: step: 996/530, loss: 0.030447769910097122
2023-01-21 09:49:44.051822: step: 1000/530, loss: 0.14766322076320648
2023-01-21 09:49:45.202159: step: 1004/530, loss: 0.2515069246292114
2023-01-21 09:49:46.425814: step: 1008/530, loss: 0.1741357147693634
2023-01-21 09:49:47.614621: step: 1012/530, loss: 0.1778222918510437
2023-01-21 09:49:48.848757: step: 1016/530, loss: 0.21397018432617188
2023-01-21 09:49:50.055893: step: 1020/530, loss: 0.1313806176185608
2023-01-21 09:49:51.240757: step: 1024/530, loss: 0.11881713569164276
2023-01-21 09:49:52.457023: step: 1028/530, loss: 0.06291327625513077
2023-01-21 09:49:53.665593: step: 1032/530, loss: 0.16330285370349884
2023-01-21 09:49:54.875718: step: 1036/530, loss: 0.14504605531692505
2023-01-21 09:49:56.066156: step: 1040/530, loss: 0.16113443672657013
2023-01-21 09:49:57.258652: step: 1044/530, loss: 0.299398809671402
2023-01-21 09:49:58.434478: step: 1048/530, loss: 0.11269207298755646
2023-01-21 09:49:59.617704: step: 1052/530, loss: 0.07886343449354172
2023-01-21 09:50:00.743823: step: 1056/530, loss: 0.045914940536022186
2023-01-21 09:50:01.919466: step: 1060/530, loss: 0.25135231018066406
2023-01-21 09:50:03.083966: step: 1064/530, loss: 0.09407277405261993
2023-01-21 09:50:04.266921: step: 1068/530, loss: 0.9510295391082764
2023-01-21 09:50:05.451361: step: 1072/530, loss: 0.07523909211158752
2023-01-21 09:50:06.605933: step: 1076/530, loss: 1.2216814756393433
2023-01-21 09:50:07.818709: step: 1080/530, loss: 0.24906902015209198
2023-01-21 09:50:08.977335: step: 1084/530, loss: 0.13651637732982635
2023-01-21 09:50:10.153715: step: 1088/530, loss: 0.1675352156162262
2023-01-21 09:50:11.351663: step: 1092/530, loss: 0.03807785362005234
2023-01-21 09:50:12.555471: step: 1096/530, loss: 0.1280396282672882
2023-01-21 09:50:13.739978: step: 1100/530, loss: 0.19950920343399048
2023-01-21 09:50:14.893628: step: 1104/530, loss: 0.35442599654197693
2023-01-21 09:50:16.078413: step: 1108/530, loss: 0.05653820186853409
2023-01-21 09:50:17.236933: step: 1112/530, loss: 0.6752009391784668
2023-01-21 09:50:18.418989: step: 1116/530, loss: 0.021213434636592865
2023-01-21 09:50:19.604962: step: 1120/530, loss: 0.09452629089355469
2023-01-21 09:50:20.816026: step: 1124/530, loss: 0.04790644347667694
2023-01-21 09:50:22.006829: step: 1128/530, loss: 0.05569944158196449
2023-01-21 09:50:23.196581: step: 1132/530, loss: 0.06117839738726616
2023-01-21 09:50:24.385557: step: 1136/530, loss: 0.17896366119384766
2023-01-21 09:50:25.542408: step: 1140/530, loss: 0.2415408194065094
2023-01-21 09:50:26.735537: step: 1144/530, loss: 0.13051429390907288
2023-01-21 09:50:27.915695: step: 1148/530, loss: 0.24688206613063812
2023-01-21 09:50:29.103339: step: 1152/530, loss: 0.13463154435157776
2023-01-21 09:50:30.301010: step: 1156/530, loss: 0.01905231550335884
2023-01-21 09:50:31.495503: step: 1160/530, loss: 0.28335922956466675
2023-01-21 09:50:32.727782: step: 1164/530, loss: 0.08951287716627121
2023-01-21 09:50:33.911752: step: 1168/530, loss: 0.4913296699523926
2023-01-21 09:50:35.103549: step: 1172/530, loss: 0.0918915718793869
2023-01-21 09:50:36.265140: step: 1176/530, loss: 0.01008062344044447
2023-01-21 09:50:37.428037: step: 1180/530, loss: 0.08041343837976456
2023-01-21 09:50:38.608566: step: 1184/530, loss: 0.11672420799732208
2023-01-21 09:50:39.749170: step: 1188/530, loss: 0.08834800869226456
2023-01-21 09:50:40.903325: step: 1192/530, loss: 0.08642949908971786
2023-01-21 09:50:42.058538: step: 1196/530, loss: 0.06976857781410217
2023-01-21 09:50:43.218459: step: 1200/530, loss: 0.048917584121227264
2023-01-21 09:50:44.436934: step: 1204/530, loss: 0.16319161653518677
2023-01-21 09:50:45.588713: step: 1208/530, loss: 0.14198637008666992
2023-01-21 09:50:46.752923: step: 1212/530, loss: 0.08094444125890732
2023-01-21 09:50:47.935740: step: 1216/530, loss: 0.15412521362304688
2023-01-21 09:50:49.133412: step: 1220/530, loss: 0.050496816635131836
2023-01-21 09:50:50.294241: step: 1224/530, loss: 0.017569376155734062
2023-01-21 09:50:51.443080: step: 1228/530, loss: 0.1967329978942871
2023-01-21 09:50:52.649715: step: 1232/530, loss: 0.029148675501346588
2023-01-21 09:50:53.781275: step: 1236/530, loss: 0.06635943055152893
2023-01-21 09:50:54.997103: step: 1240/530, loss: 0.031171131879091263
2023-01-21 09:50:56.211265: step: 1244/530, loss: 0.3450516164302826
2023-01-21 09:50:57.410004: step: 1248/530, loss: 0.07146825641393661
2023-01-21 09:50:58.580395: step: 1252/530, loss: 0.02122030220925808
2023-01-21 09:50:59.755197: step: 1256/530, loss: 0.04605922847986221
2023-01-21 09:51:00.953382: step: 1260/530, loss: 0.0691690444946289
2023-01-21 09:51:02.175875: step: 1264/530, loss: 0.09634155035018921
2023-01-21 09:51:03.394096: step: 1268/530, loss: 0.3644769787788391
2023-01-21 09:51:04.574741: step: 1272/530, loss: 0.08097486197948456
2023-01-21 09:51:05.737924: step: 1276/530, loss: 0.16014719009399414
2023-01-21 09:51:06.910745: step: 1280/530, loss: 0.6281105279922485
2023-01-21 09:51:08.114142: step: 1284/530, loss: 0.08786201477050781
2023-01-21 09:51:09.275656: step: 1288/530, loss: 0.06126823276281357
2023-01-21 09:51:10.460210: step: 1292/530, loss: 0.07381415367126465
2023-01-21 09:51:11.634769: step: 1296/530, loss: 0.15044927597045898
2023-01-21 09:51:12.838036: step: 1300/530, loss: 0.08012113720178604
2023-01-21 09:51:14.057686: step: 1304/530, loss: 0.08313445746898651
2023-01-21 09:51:15.246891: step: 1308/530, loss: 0.06676559150218964
2023-01-21 09:51:16.454026: step: 1312/530, loss: 0.09964694827795029
2023-01-21 09:51:17.591546: step: 1316/530, loss: 0.6676400303840637
2023-01-21 09:51:18.758979: step: 1320/530, loss: 0.2623558044433594
2023-01-21 09:51:19.954302: step: 1324/530, loss: 0.4281969964504242
2023-01-21 09:51:21.084587: step: 1328/530, loss: 0.05522608757019043
2023-01-21 09:51:22.250989: step: 1332/530, loss: 0.1036454290151596
2023-01-21 09:51:23.414202: step: 1336/530, loss: 0.7949551343917847
2023-01-21 09:51:24.624599: step: 1340/530, loss: 0.12144766747951508
2023-01-21 09:51:25.813049: step: 1344/530, loss: 8.118889808654785
2023-01-21 09:51:26.978687: step: 1348/530, loss: 0.15737371146678925
2023-01-21 09:51:28.165367: step: 1352/530, loss: 0.12530259788036346
2023-01-21 09:51:29.319792: step: 1356/530, loss: 0.37088432908058167
2023-01-21 09:51:30.521367: step: 1360/530, loss: 0.15620647370815277
2023-01-21 09:51:31.690205: step: 1364/530, loss: 0.028477145358920097
2023-01-21 09:51:32.835988: step: 1368/530, loss: 0.1475735455751419
2023-01-21 09:51:34.017968: step: 1372/530, loss: 0.15326552093029022
2023-01-21 09:51:35.246701: step: 1376/530, loss: 0.12698504328727722
2023-01-21 09:51:36.447378: step: 1380/530, loss: 0.0507938414812088
2023-01-21 09:51:37.596255: step: 1384/530, loss: 0.0787678211927414
2023-01-21 09:51:38.754228: step: 1388/530, loss: 1.235237717628479
2023-01-21 09:51:39.978436: step: 1392/530, loss: 0.11850052326917648
2023-01-21 09:51:41.136510: step: 1396/530, loss: 0.0781853199005127
2023-01-21 09:51:42.329509: step: 1400/530, loss: 0.1338120400905609
2023-01-21 09:51:43.510704: step: 1404/530, loss: 0.2014157474040985
2023-01-21 09:51:44.669528: step: 1408/530, loss: 0.37979164719581604
2023-01-21 09:51:45.828790: step: 1412/530, loss: 0.1555541455745697
2023-01-21 09:51:46.995692: step: 1416/530, loss: 0.00940637569874525
2023-01-21 09:51:48.196647: step: 1420/530, loss: 0.11018143594264984
2023-01-21 09:51:49.347864: step: 1424/530, loss: 0.05312395095825195
2023-01-21 09:51:50.546949: step: 1428/530, loss: 0.1751757562160492
2023-01-21 09:51:51.768011: step: 1432/530, loss: 0.23049183189868927
2023-01-21 09:51:52.981478: step: 1436/530, loss: 0.0061484333127737045
2023-01-21 09:51:54.140969: step: 1440/530, loss: 0.03585701063275337
2023-01-21 09:51:55.296213: step: 1444/530, loss: 0.05142708122730255
2023-01-21 09:51:56.469195: step: 1448/530, loss: 0.056695327162742615
2023-01-21 09:51:57.603388: step: 1452/530, loss: 0.05688176304101944
2023-01-21 09:51:58.750049: step: 1456/530, loss: 0.09829340130090714
2023-01-21 09:51:59.954243: step: 1460/530, loss: 0.05451097711920738
2023-01-21 09:52:01.136129: step: 1464/530, loss: 0.15306444466114044
2023-01-21 09:52:02.283458: step: 1468/530, loss: 0.7216490507125854
2023-01-21 09:52:03.519878: step: 1472/530, loss: 0.07557869702577591
2023-01-21 09:52:04.676812: step: 1476/530, loss: 0.053020574152469635
2023-01-21 09:52:05.865750: step: 1480/530, loss: 0.14299039542675018
2023-01-21 09:52:07.059451: step: 1484/530, loss: 0.030964376404881477
2023-01-21 09:52:08.254582: step: 1488/530, loss: 0.004988003056496382
2023-01-21 09:52:09.451491: step: 1492/530, loss: 0.2425040304660797
2023-01-21 09:52:10.667756: step: 1496/530, loss: 0.022293757647275925
2023-01-21 09:52:11.846965: step: 1500/530, loss: 0.11778521537780762
2023-01-21 09:52:13.015538: step: 1504/530, loss: 0.09112139046192169
2023-01-21 09:52:14.212046: step: 1508/530, loss: 0.028851225972175598
2023-01-21 09:52:15.383887: step: 1512/530, loss: 0.08409872651100159
2023-01-21 09:52:16.564489: step: 1516/530, loss: 0.09616873413324356
2023-01-21 09:52:17.738742: step: 1520/530, loss: 0.03184308856725693
2023-01-21 09:52:18.946014: step: 1524/530, loss: 0.15684834122657776
2023-01-21 09:52:20.165522: step: 1528/530, loss: 0.3821706771850586
2023-01-21 09:52:21.404476: step: 1532/530, loss: 0.13774064183235168
2023-01-21 09:52:22.590117: step: 1536/530, loss: 0.07538139820098877
2023-01-21 09:52:23.798800: step: 1540/530, loss: 0.14204131066799164
2023-01-21 09:52:24.945713: step: 1544/530, loss: 0.07960529625415802
2023-01-21 09:52:26.102803: step: 1548/530, loss: 0.08302012085914612
2023-01-21 09:52:27.270203: step: 1552/530, loss: 0.05219545587897301
2023-01-21 09:52:28.447735: step: 1556/530, loss: 0.20789460837841034
2023-01-21 09:52:29.618496: step: 1560/530, loss: 0.12437497079372406
2023-01-21 09:52:30.774830: step: 1564/530, loss: 0.6804086565971375
2023-01-21 09:52:31.957628: step: 1568/530, loss: 0.26605215668678284
2023-01-21 09:52:33.137366: step: 1572/530, loss: 0.1061069443821907
2023-01-21 09:52:34.364748: step: 1576/530, loss: 0.10087203979492188
2023-01-21 09:52:35.561291: step: 1580/530, loss: 0.23875465989112854
2023-01-21 09:52:36.769417: step: 1584/530, loss: 0.7635504603385925
2023-01-21 09:52:37.971890: step: 1588/530, loss: 0.06685705482959747
2023-01-21 09:52:39.139329: step: 1592/530, loss: 0.3336338996887207
2023-01-21 09:52:40.345395: step: 1596/530, loss: 0.33176448941230774
2023-01-21 09:52:41.514402: step: 1600/530, loss: 0.44324979186058044
2023-01-21 09:52:42.700718: step: 1604/530, loss: 0.07779455184936523
2023-01-21 09:52:43.866469: step: 1608/530, loss: 0.13275985419750214
2023-01-21 09:52:45.065265: step: 1612/530, loss: 0.23136940598487854
2023-01-21 09:52:46.223395: step: 1616/530, loss: 0.23307928442955017
2023-01-21 09:52:47.398461: step: 1620/530, loss: 0.01569380797445774
2023-01-21 09:52:48.568127: step: 1624/530, loss: 0.04010000452399254
2023-01-21 09:52:49.713542: step: 1628/530, loss: 0.08722343295812607
2023-01-21 09:52:50.904680: step: 1632/530, loss: 0.03483171761035919
2023-01-21 09:52:52.079884: step: 1636/530, loss: 0.10468673706054688
2023-01-21 09:52:53.273220: step: 1640/530, loss: 0.0700041800737381
2023-01-21 09:52:54.470328: step: 1644/530, loss: 0.09530048817396164
2023-01-21 09:52:55.645586: step: 1648/530, loss: 0.041333772242069244
2023-01-21 09:52:56.841922: step: 1652/530, loss: 0.01904582977294922
2023-01-21 09:52:58.007391: step: 1656/530, loss: 0.049504779279232025
2023-01-21 09:52:59.203422: step: 1660/530, loss: 0.13064345717430115
2023-01-21 09:53:00.361212: step: 1664/530, loss: 0.5991726517677307
2023-01-21 09:53:01.530098: step: 1668/530, loss: 0.10010337829589844
2023-01-21 09:53:02.736491: step: 1672/530, loss: 0.057242583483457565
2023-01-21 09:53:03.932085: step: 1676/530, loss: 0.04651589319109917
2023-01-21 09:53:05.111704: step: 1680/530, loss: 0.16042709350585938
2023-01-21 09:53:06.305997: step: 1684/530, loss: 0.15629100799560547
2023-01-21 09:53:07.499108: step: 1688/530, loss: 0.029331304132938385
2023-01-21 09:53:08.658971: step: 1692/530, loss: 0.05172586441040039
2023-01-21 09:53:09.868544: step: 1696/530, loss: 0.3399297893047333
2023-01-21 09:53:11.039416: step: 1700/530, loss: 0.014093208126723766
2023-01-21 09:53:12.288176: step: 1704/530, loss: 0.16087833046913147
2023-01-21 09:53:13.472064: step: 1708/530, loss: 0.06951618194580078
2023-01-21 09:53:14.622820: step: 1712/530, loss: 0.0356324203312397
2023-01-21 09:53:15.787186: step: 1716/530, loss: 0.43255701661109924
2023-01-21 09:53:16.956365: step: 1720/530, loss: 0.09145680069923401
2023-01-21 09:53:18.150809: step: 1724/530, loss: 0.0860137939453125
2023-01-21 09:53:19.378171: step: 1728/530, loss: 0.04267134517431259
2023-01-21 09:53:20.551134: step: 1732/530, loss: 0.07545671612024307
2023-01-21 09:53:21.683739: step: 1736/530, loss: 0.25702863931655884
2023-01-21 09:53:22.863018: step: 1740/530, loss: 0.3747011423110962
2023-01-21 09:53:24.073493: step: 1744/530, loss: 0.03267383575439453
2023-01-21 09:53:25.299022: step: 1748/530, loss: 0.14868488907814026
2023-01-21 09:53:26.489327: step: 1752/530, loss: 0.08251695334911346
2023-01-21 09:53:27.669397: step: 1756/530, loss: 0.06842704117298126
2023-01-21 09:53:28.897717: step: 1760/530, loss: 0.06780672073364258
2023-01-21 09:53:30.104948: step: 1764/530, loss: 0.022853948175907135
2023-01-21 09:53:31.286117: step: 1768/530, loss: 0.046235088258981705
2023-01-21 09:53:32.408465: step: 1772/530, loss: 0.14488859474658966
2023-01-21 09:53:33.589215: step: 1776/530, loss: 0.04218330234289169
2023-01-21 09:53:34.757411: step: 1780/530, loss: 0.0666736587882042
2023-01-21 09:53:35.943221: step: 1784/530, loss: 0.045351602137088776
2023-01-21 09:53:37.104150: step: 1788/530, loss: 0.024474717676639557
2023-01-21 09:53:38.290293: step: 1792/530, loss: 0.5986720323562622
2023-01-21 09:53:39.432962: step: 1796/530, loss: 0.19614830613136292
2023-01-21 09:53:40.594643: step: 1800/530, loss: 0.14424562454223633
2023-01-21 09:53:41.755679: step: 1804/530, loss: 0.03900689631700516
2023-01-21 09:53:42.967352: step: 1808/530, loss: 0.12048053741455078
2023-01-21 09:53:44.148827: step: 1812/530, loss: 0.17474976181983948
2023-01-21 09:53:45.367344: step: 1816/530, loss: 0.08219261467456818
2023-01-21 09:53:46.573147: step: 1820/530, loss: 0.21182546019554138
2023-01-21 09:53:47.836302: step: 1824/530, loss: 0.15406452119350433
2023-01-21 09:53:49.034680: step: 1828/530, loss: 0.0773673951625824
2023-01-21 09:53:50.237556: step: 1832/530, loss: 0.040265846997499466
2023-01-21 09:53:51.458805: step: 1836/530, loss: 0.5512231588363647
2023-01-21 09:53:52.615926: step: 1840/530, loss: 0.08200240135192871
2023-01-21 09:53:53.763479: step: 1844/530, loss: 0.10322335362434387
2023-01-21 09:53:54.964244: step: 1848/530, loss: 0.1038825511932373
2023-01-21 09:53:56.143920: step: 1852/530, loss: 0.1444016396999359
2023-01-21 09:53:57.318670: step: 1856/530, loss: 0.013876629061996937
2023-01-21 09:53:58.502478: step: 1860/530, loss: 0.27657708525657654
2023-01-21 09:53:59.641925: step: 1864/530, loss: 0.6079106330871582
2023-01-21 09:54:00.762209: step: 1868/530, loss: 0.06888370960950851
2023-01-21 09:54:01.931685: step: 1872/530, loss: 0.04305429756641388
2023-01-21 09:54:03.117599: step: 1876/530, loss: 0.07346191257238388
2023-01-21 09:54:04.318099: step: 1880/530, loss: 0.035425566136837006
2023-01-21 09:54:05.500602: step: 1884/530, loss: 0.08678150177001953
2023-01-21 09:54:06.674551: step: 1888/530, loss: 0.08211731910705566
2023-01-21 09:54:07.838806: step: 1892/530, loss: 0.09818267822265625
2023-01-21 09:54:09.034584: step: 1896/530, loss: 0.12733745574951172
2023-01-21 09:54:10.198711: step: 1900/530, loss: 0.04463662952184677
2023-01-21 09:54:11.422016: step: 1904/530, loss: 0.11427903920412064
2023-01-21 09:54:12.590197: step: 1908/530, loss: 0.14245247840881348
2023-01-21 09:54:13.777355: step: 1912/530, loss: 0.04493694379925728
2023-01-21 09:54:14.947897: step: 1916/530, loss: 0.07463064789772034
2023-01-21 09:54:16.127087: step: 1920/530, loss: 0.15216198563575745
2023-01-21 09:54:17.268172: step: 1924/530, loss: 0.04280037805438042
2023-01-21 09:54:18.467172: step: 1928/530, loss: 0.1652251034975052
2023-01-21 09:54:19.658464: step: 1932/530, loss: 0.03550739213824272
2023-01-21 09:54:20.866159: step: 1936/530, loss: 0.11913518607616425
2023-01-21 09:54:22.061102: step: 1940/530, loss: 0.0704570785164833
2023-01-21 09:54:23.245469: step: 1944/530, loss: 0.20811930298805237
2023-01-21 09:54:24.394370: step: 1948/530, loss: 0.07304179668426514
2023-01-21 09:54:25.600624: step: 1952/530, loss: 0.11367378383874893
2023-01-21 09:54:26.785166: step: 1956/530, loss: 0.1448986977338791
2023-01-21 09:54:27.937163: step: 1960/530, loss: 0.04355278238654137
2023-01-21 09:54:29.130366: step: 1964/530, loss: 0.1907327026128769
2023-01-21 09:54:30.300340: step: 1968/530, loss: 0.05163269490003586
2023-01-21 09:54:31.512173: step: 1972/530, loss: 0.03978443518280983
2023-01-21 09:54:32.643875: step: 1976/530, loss: 0.048858191817998886
2023-01-21 09:54:33.839576: step: 1980/530, loss: 0.11977467685937881
2023-01-21 09:54:35.008218: step: 1984/530, loss: 0.05119209364056587
2023-01-21 09:54:36.188058: step: 1988/530, loss: 0.1476486623287201
2023-01-21 09:54:37.365044: step: 1992/530, loss: 0.19440193474292755
2023-01-21 09:54:38.533945: step: 1996/530, loss: 0.09235715866088867
2023-01-21 09:54:39.703155: step: 2000/530, loss: 0.1252666413784027
2023-01-21 09:54:40.929900: step: 2004/530, loss: 0.10467414557933807
2023-01-21 09:54:42.137017: step: 2008/530, loss: 0.10535478591918945
2023-01-21 09:54:43.359753: step: 2012/530, loss: 0.30162695050239563
2023-01-21 09:54:44.548378: step: 2016/530, loss: 0.07579698413610458
2023-01-21 09:54:45.714549: step: 2020/530, loss: 0.4311635494232178
2023-01-21 09:54:46.861237: step: 2024/530, loss: 0.048597242683172226
2023-01-21 09:54:48.009208: step: 2028/530, loss: 0.16346636414527893
2023-01-21 09:54:49.180668: step: 2032/530, loss: 0.06641187518835068
2023-01-21 09:54:50.364165: step: 2036/530, loss: 0.16264715790748596
2023-01-21 09:54:51.563899: step: 2040/530, loss: 0.062119390815496445
2023-01-21 09:54:52.730401: step: 2044/530, loss: 0.1397738754749298
2023-01-21 09:54:53.976396: step: 2048/530, loss: 0.09591779112815857
2023-01-21 09:54:55.162133: step: 2052/530, loss: 0.11064257472753525
2023-01-21 09:54:56.379554: step: 2056/530, loss: 0.07639209181070328
2023-01-21 09:54:57.532764: step: 2060/530, loss: 0.39465731382369995
2023-01-21 09:54:58.687255: step: 2064/530, loss: 0.38528165221214294
2023-01-21 09:54:59.837247: step: 2068/530, loss: 0.21424904465675354
2023-01-21 09:55:00.990363: step: 2072/530, loss: 0.07137145847082138
2023-01-21 09:55:02.180831: step: 2076/530, loss: 0.025903893634676933
2023-01-21 09:55:03.343799: step: 2080/530, loss: 0.17507098615169525
2023-01-21 09:55:04.542678: step: 2084/530, loss: 0.08531332015991211
2023-01-21 09:55:05.728456: step: 2088/530, loss: 0.04731474071741104
2023-01-21 09:55:06.901442: step: 2092/530, loss: 0.847104549407959
2023-01-21 09:55:08.056958: step: 2096/530, loss: 0.25704002380371094
2023-01-21 09:55:09.258598: step: 2100/530, loss: 0.07107844948768616
2023-01-21 09:55:10.502077: step: 2104/530, loss: 0.09040975570678711
2023-01-21 09:55:11.668856: step: 2108/530, loss: 0.5130107998847961
2023-01-21 09:55:12.911008: step: 2112/530, loss: 1.0085654258728027
2023-01-21 09:55:14.083359: step: 2116/530, loss: 0.04115448147058487
2023-01-21 09:55:15.249118: step: 2120/530, loss: 0.084398552775383
==================================================
Loss: 0.179
--------------------
Dev: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
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': 7}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Chinese: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:56:08.178164: step: 4/530, loss: 0.013045120052993298
2023-01-21 09:56:09.323092: step: 8/530, loss: 0.14052416384220123
2023-01-21 09:56:10.531822: step: 12/530, loss: 0.0852198600769043
2023-01-21 09:56:11.703558: step: 16/530, loss: 0.013116646558046341
2023-01-21 09:56:12.963487: step: 20/530, loss: 0.1346844732761383
2023-01-21 09:56:14.184576: step: 24/530, loss: 0.038956452161073685
2023-01-21 09:56:15.375809: step: 28/530, loss: 0.07555808871984482
2023-01-21 09:56:16.514345: step: 32/530, loss: 0.053922273218631744
2023-01-21 09:56:17.686532: step: 36/530, loss: 0.021027278155088425
2023-01-21 09:56:18.886661: step: 40/530, loss: 0.15186342597007751
2023-01-21 09:56:20.087255: step: 44/530, loss: 0.11963143199682236
2023-01-21 09:56:21.295855: step: 48/530, loss: 0.02114858664572239
2023-01-21 09:56:22.499759: step: 52/530, loss: 0.26652461290359497
2023-01-21 09:56:23.684528: step: 56/530, loss: 0.06590834259986877
2023-01-21 09:56:24.857596: step: 60/530, loss: 0.02814197540283203
2023-01-21 09:56:26.047306: step: 64/530, loss: 0.01302804984152317
2023-01-21 09:56:27.247037: step: 68/530, loss: 0.035091400146484375
2023-01-21 09:56:28.453440: step: 72/530, loss: 0.05958350747823715
2023-01-21 09:56:29.638766: step: 76/530, loss: 0.5154921412467957
2023-01-21 09:56:30.783269: step: 80/530, loss: 0.04587617143988609
2023-01-21 09:56:31.908481: step: 84/530, loss: 0.04583015665411949
2023-01-21 09:56:33.090794: step: 88/530, loss: 0.014336585998535156
2023-01-21 09:56:34.270073: step: 92/530, loss: 0.032526396214962006
2023-01-21 09:56:35.448823: step: 96/530, loss: 0.26413780450820923
2023-01-21 09:56:36.621321: step: 100/530, loss: 0.08424311131238937
2023-01-21 09:56:37.823627: step: 104/530, loss: 0.6141337752342224
2023-01-21 09:56:38.993233: step: 108/530, loss: 0.04038744047284126
2023-01-21 09:56:40.232102: step: 112/530, loss: 0.09230895340442657
2023-01-21 09:56:41.435928: step: 116/530, loss: 0.1172037124633789
2023-01-21 09:56:42.637379: step: 120/530, loss: 0.2667948305606842
2023-01-21 09:56:43.881387: step: 124/530, loss: 0.6686827540397644
2023-01-21 09:56:45.018895: step: 128/530, loss: 0.03657274320721626
2023-01-21 09:56:46.206279: step: 132/530, loss: 0.01795358583331108
2023-01-21 09:56:47.333834: step: 136/530, loss: 0.11793716251850128
2023-01-21 09:56:48.498373: step: 140/530, loss: 0.5495710372924805
2023-01-21 09:56:49.688207: step: 144/530, loss: 0.15649351477622986
2023-01-21 09:56:50.857661: step: 148/530, loss: 0.01924934610724449
2023-01-21 09:56:52.010225: step: 152/530, loss: 0.126353457570076
2023-01-21 09:56:53.211615: step: 156/530, loss: 0.10839171707630157
2023-01-21 09:56:54.393989: step: 160/530, loss: 0.103558748960495
2023-01-21 09:56:55.564360: step: 164/530, loss: 0.03488488122820854
2023-01-21 09:56:56.733342: step: 168/530, loss: 0.07031060010194778
2023-01-21 09:56:57.916578: step: 172/530, loss: 0.11431103199720383
2023-01-21 09:56:59.100254: step: 176/530, loss: 0.14870090782642365
2023-01-21 09:57:00.309250: step: 180/530, loss: 0.07193470001220703
2023-01-21 09:57:01.481202: step: 184/530, loss: 0.05818605422973633
2023-01-21 09:57:02.635999: step: 188/530, loss: 0.06970290839672089
2023-01-21 09:57:03.825181: step: 192/530, loss: 0.0024049757048487663
2023-01-21 09:57:04.990732: step: 196/530, loss: 0.14908239245414734
2023-01-21 09:57:06.156066: step: 200/530, loss: 0.2746809124946594
2023-01-21 09:57:07.379472: step: 204/530, loss: 0.0611940398812294
2023-01-21 09:57:08.543986: step: 208/530, loss: 0.05474557727575302
2023-01-21 09:57:09.712436: step: 212/530, loss: 0.13059405982494354
2023-01-21 09:57:10.836702: step: 216/530, loss: 0.54752117395401
2023-01-21 09:57:12.093754: step: 220/530, loss: 0.11060447245836258
2023-01-21 09:57:13.243877: step: 224/530, loss: 0.0651267021894455
2023-01-21 09:57:14.456388: step: 228/530, loss: 0.03605613857507706
2023-01-21 09:57:15.697505: step: 232/530, loss: 0.016681768000125885
2023-01-21 09:57:16.945277: step: 236/530, loss: 0.057855986058712006
2023-01-21 09:57:18.085481: step: 240/530, loss: 0.03727400302886963
2023-01-21 09:57:19.236972: step: 244/530, loss: 0.02317791059613228
2023-01-21 09:57:20.415666: step: 248/530, loss: 0.08414573967456818
2023-01-21 09:57:21.594258: step: 252/530, loss: 0.1709299087524414
2023-01-21 09:57:22.774683: step: 256/530, loss: 0.1816527396440506
2023-01-21 09:57:23.907648: step: 260/530, loss: 0.40960776805877686
2023-01-21 09:57:25.090375: step: 264/530, loss: 0.10755190998315811
2023-01-21 09:57:26.234641: step: 268/530, loss: 0.09921374171972275
2023-01-21 09:57:27.420455: step: 272/530, loss: 0.04398531839251518
2023-01-21 09:57:28.605735: step: 276/530, loss: 0.037724971771240234
2023-01-21 09:57:29.820395: step: 280/530, loss: 0.21813221275806427
2023-01-21 09:57:30.980712: step: 284/530, loss: 0.008573818020522594
2023-01-21 09:57:32.138557: step: 288/530, loss: 0.057091712951660156
2023-01-21 09:57:33.295075: step: 292/530, loss: 0.017960675060749054
2023-01-21 09:57:34.449429: step: 296/530, loss: 0.39324912428855896
2023-01-21 09:57:35.609326: step: 300/530, loss: 0.08897967636585236
2023-01-21 09:57:36.773990: step: 304/530, loss: 0.04633474349975586
2023-01-21 09:57:37.976550: step: 308/530, loss: 0.09259138256311417
2023-01-21 09:57:39.177282: step: 312/530, loss: 0.08159799873828888
2023-01-21 09:57:40.378659: step: 316/530, loss: 0.11364221572875977
2023-01-21 09:57:41.589882: step: 320/530, loss: 0.05468578264117241
2023-01-21 09:57:42.798788: step: 324/530, loss: 0.11089906096458435
2023-01-21 09:57:43.987602: step: 328/530, loss: 0.10832004994153976
2023-01-21 09:57:45.185218: step: 332/530, loss: 0.16594481468200684
2023-01-21 09:57:46.395871: step: 336/530, loss: 0.03907022625207901
2023-01-21 09:57:47.581249: step: 340/530, loss: 0.23426222801208496
2023-01-21 09:57:48.772527: step: 344/530, loss: 0.21895432472229004
2023-01-21 09:57:50.000015: step: 348/530, loss: 0.07421131432056427
2023-01-21 09:57:51.139127: step: 352/530, loss: 0.07454857975244522
2023-01-21 09:57:52.310312: step: 356/530, loss: 0.11459775269031525
2023-01-21 09:57:53.531616: step: 360/530, loss: 0.11691675335168839
2023-01-21 09:57:54.664473: step: 364/530, loss: 0.028308534994721413
2023-01-21 09:57:55.833041: step: 368/530, loss: 0.07967119663953781
2023-01-21 09:57:56.994219: step: 372/530, loss: 0.7948236465454102
2023-01-21 09:57:58.190645: step: 376/530, loss: 0.10896148532629013
2023-01-21 09:57:59.395458: step: 380/530, loss: 0.07730035483837128
2023-01-21 09:58:00.555766: step: 384/530, loss: 0.11764278262853622
2023-01-21 09:58:01.742840: step: 388/530, loss: 0.4085315465927124
2023-01-21 09:58:02.940505: step: 392/530, loss: 0.06540469825267792
2023-01-21 09:58:04.145073: step: 396/530, loss: 0.05156746134161949
2023-01-21 09:58:05.325419: step: 400/530, loss: 0.3796706199645996
2023-01-21 09:58:06.461522: step: 404/530, loss: 0.04525151476264
2023-01-21 09:58:07.638200: step: 408/530, loss: 0.13885074853897095
2023-01-21 09:58:08.800359: step: 412/530, loss: 0.059441566467285156
2023-01-21 09:58:10.050381: step: 416/530, loss: 0.11389460414648056
2023-01-21 09:58:11.292389: step: 420/530, loss: 0.09221974015235901
2023-01-21 09:58:12.472262: step: 424/530, loss: 0.028554439544677734
2023-01-21 09:58:13.673858: step: 428/530, loss: 0.3380745053291321
2023-01-21 09:58:14.868443: step: 432/530, loss: 0.023958493024110794
2023-01-21 09:58:16.031429: step: 436/530, loss: 0.06500005722045898
2023-01-21 09:58:17.189014: step: 440/530, loss: 0.0658545047044754
2023-01-21 09:58:18.337548: step: 444/530, loss: 0.05891161039471626
2023-01-21 09:58:19.511839: step: 448/530, loss: 0.023718737065792084
2023-01-21 09:58:20.699176: step: 452/530, loss: 0.034954167902469635
2023-01-21 09:58:21.850772: step: 456/530, loss: 0.0340849868953228
2023-01-21 09:58:23.052644: step: 460/530, loss: 0.1800159513950348
2023-01-21 09:58:24.240356: step: 464/530, loss: 0.027072429656982422
2023-01-21 09:58:25.407284: step: 468/530, loss: 0.19576627016067505
2023-01-21 09:58:26.559025: step: 472/530, loss: 0.0490022674202919
2023-01-21 09:58:27.730279: step: 476/530, loss: 0.08780527114868164
2023-01-21 09:58:28.909562: step: 480/530, loss: 0.07503862679004669
2023-01-21 09:58:30.139492: step: 484/530, loss: 0.11762829124927521
2023-01-21 09:58:31.289188: step: 488/530, loss: 0.0416048988699913
2023-01-21 09:58:32.452081: step: 492/530, loss: 0.1955157369375229
2023-01-21 09:58:33.669504: step: 496/530, loss: 0.21065063774585724
2023-01-21 09:58:34.809111: step: 500/530, loss: 0.40678104758262634
2023-01-21 09:58:35.970768: step: 504/530, loss: 0.04530501365661621
2023-01-21 09:58:37.166117: step: 508/530, loss: 0.0852634459733963
2023-01-21 09:58:38.339491: step: 512/530, loss: 0.11491432785987854
2023-01-21 09:58:39.516114: step: 516/530, loss: 0.05294659361243248
2023-01-21 09:58:40.659998: step: 520/530, loss: 0.06817712634801865
2023-01-21 09:58:41.875688: step: 524/530, loss: 0.08993415534496307
2023-01-21 09:58:43.038859: step: 528/530, loss: 0.0556035041809082
2023-01-21 09:58:44.257794: step: 532/530, loss: 0.018457889556884766
2023-01-21 09:58:45.415678: step: 536/530, loss: 0.2707945704460144
2023-01-21 09:58:46.567618: step: 540/530, loss: 0.026917606592178345
2023-01-21 09:58:47.747319: step: 544/530, loss: 0.05884981155395508
2023-01-21 09:58:48.911138: step: 548/530, loss: 0.28797751665115356
2023-01-21 09:58:50.095997: step: 552/530, loss: 0.05277619510889053
2023-01-21 09:58:51.294611: step: 556/530, loss: 0.016150856390595436
2023-01-21 09:58:52.492281: step: 560/530, loss: 0.019348621368408203
2023-01-21 09:58:53.652998: step: 564/530, loss: 0.9106072187423706
2023-01-21 09:58:54.845631: step: 568/530, loss: 0.03239498287439346
2023-01-21 09:58:56.075267: step: 572/530, loss: 0.8493542671203613
2023-01-21 09:58:57.232173: step: 576/530, loss: 0.13186055421829224
2023-01-21 09:58:58.401791: step: 580/530, loss: 0.0899294912815094
2023-01-21 09:58:59.569249: step: 584/530, loss: 0.04232511669397354
2023-01-21 09:59:00.761453: step: 588/530, loss: 0.03737621381878853
2023-01-21 09:59:01.927485: step: 592/530, loss: 0.08451423048973083
2023-01-21 09:59:03.077170: step: 596/530, loss: 0.06950731575489044
2023-01-21 09:59:04.223407: step: 600/530, loss: 0.08066006004810333
2023-01-21 09:59:05.366224: step: 604/530, loss: 0.05632514879107475
2023-01-21 09:59:06.528275: step: 608/530, loss: 0.11548750102519989
2023-01-21 09:59:07.712022: step: 612/530, loss: 0.07566623389720917
2023-01-21 09:59:08.871968: step: 616/530, loss: 0.044866371899843216
2023-01-21 09:59:10.076376: step: 620/530, loss: 0.36357975006103516
2023-01-21 09:59:11.270366: step: 624/530, loss: 0.04405384510755539
2023-01-21 09:59:12.531083: step: 628/530, loss: 0.39372768998146057
2023-01-21 09:59:13.741665: step: 632/530, loss: 0.14358320832252502
2023-01-21 09:59:14.928310: step: 636/530, loss: 0.46996474266052246
2023-01-21 09:59:16.082442: step: 640/530, loss: 0.020949935540556908
2023-01-21 09:59:17.291787: step: 644/530, loss: 0.1604146957397461
2023-01-21 09:59:18.466800: step: 648/530, loss: 0.10612840950489044
2023-01-21 09:59:19.678471: step: 652/530, loss: 0.3621363341808319
2023-01-21 09:59:20.879476: step: 656/530, loss: 0.07020549476146698
2023-01-21 09:59:22.057570: step: 660/530, loss: 0.0519709587097168
2023-01-21 09:59:23.272562: step: 664/530, loss: 0.06753101944923401
2023-01-21 09:59:24.442310: step: 668/530, loss: 0.04194474220275879
2023-01-21 09:59:25.617790: step: 672/530, loss: 0.11760219931602478
2023-01-21 09:59:26.850446: step: 676/530, loss: 0.1327778697013855
2023-01-21 09:59:28.007914: step: 680/530, loss: 0.08648691326379776
2023-01-21 09:59:29.178636: step: 684/530, loss: 0.19290320575237274
2023-01-21 09:59:30.362741: step: 688/530, loss: 0.014221668243408203
2023-01-21 09:59:31.529287: step: 692/530, loss: 0.12658095359802246
2023-01-21 09:59:32.712710: step: 696/530, loss: 0.11362600326538086
2023-01-21 09:59:33.882496: step: 700/530, loss: 0.2863524258136749
2023-01-21 09:59:35.042711: step: 704/530, loss: 0.11817741394042969
2023-01-21 09:59:36.224571: step: 708/530, loss: 0.06823205947875977
2023-01-21 09:59:37.396851: step: 712/530, loss: 0.03991599380970001
2023-01-21 09:59:38.543101: step: 716/530, loss: 0.09215731918811798
2023-01-21 09:59:39.702747: step: 720/530, loss: 0.10536480695009232
2023-01-21 09:59:40.907357: step: 724/530, loss: 1.2240935564041138
2023-01-21 09:59:42.105802: step: 728/530, loss: 0.08709335327148438
2023-01-21 09:59:43.275613: step: 732/530, loss: 0.39023178815841675
2023-01-21 09:59:44.436194: step: 736/530, loss: 0.533431351184845
2023-01-21 09:59:45.616365: step: 740/530, loss: 0.13381260633468628
2023-01-21 09:59:46.806954: step: 744/530, loss: 0.13263873755931854
2023-01-21 09:59:47.979563: step: 748/530, loss: 0.16422347724437714
2023-01-21 09:59:49.178182: step: 752/530, loss: 0.025727272033691406
2023-01-21 09:59:50.342579: step: 756/530, loss: 0.0958210900425911
2023-01-21 09:59:51.487391: step: 760/530, loss: 0.13712501525878906
2023-01-21 09:59:52.681129: step: 764/530, loss: 0.08112931251525879
2023-01-21 09:59:53.866259: step: 768/530, loss: 0.10942325741052628
2023-01-21 09:59:55.060177: step: 772/530, loss: 0.17530114948749542
2023-01-21 09:59:56.237204: step: 776/530, loss: 0.17239519953727722
2023-01-21 09:59:57.409912: step: 780/530, loss: 0.02592456340789795
2023-01-21 09:59:58.581459: step: 784/530, loss: 0.039057470858097076
2023-01-21 09:59:59.771346: step: 788/530, loss: 0.058348558843135834
2023-01-21 10:00:00.950245: step: 792/530, loss: 0.4029165804386139
2023-01-21 10:00:02.157424: step: 796/530, loss: 0.020975828170776367
2023-01-21 10:00:03.319931: step: 800/530, loss: 0.03616919368505478
2023-01-21 10:00:04.515274: step: 804/530, loss: 0.2501760423183441
2023-01-21 10:00:05.660991: step: 808/530, loss: 0.06119508668780327
2023-01-21 10:00:06.879422: step: 812/530, loss: 0.19562816619873047
2023-01-21 10:00:08.024533: step: 816/530, loss: 0.23795709013938904
2023-01-21 10:00:09.179298: step: 820/530, loss: 0.023935556411743164
2023-01-21 10:00:10.337493: step: 824/530, loss: 0.12495122849941254
2023-01-21 10:00:11.483810: step: 828/530, loss: 0.004291725344955921
2023-01-21 10:00:12.650296: step: 832/530, loss: 0.05817871168255806
2023-01-21 10:00:13.834290: step: 836/530, loss: 0.028009986504912376
2023-01-21 10:00:15.030531: step: 840/530, loss: 0.06398141384124756
2023-01-21 10:00:16.220068: step: 844/530, loss: 0.04607763513922691
2023-01-21 10:00:17.383889: step: 848/530, loss: 0.17701320350170135
2023-01-21 10:00:18.542278: step: 852/530, loss: 0.029433155432343483
2023-01-21 10:00:19.717502: step: 856/530, loss: 0.08652222901582718
2023-01-21 10:00:20.878074: step: 860/530, loss: 0.11909443885087967
2023-01-21 10:00:22.020354: step: 864/530, loss: 0.036504171788692474
2023-01-21 10:00:23.214996: step: 868/530, loss: 0.12051931023597717
2023-01-21 10:00:24.397628: step: 872/530, loss: 0.022498322650790215
2023-01-21 10:00:25.604092: step: 876/530, loss: 0.04097125679254532
2023-01-21 10:00:26.797064: step: 880/530, loss: 0.37603139877319336
2023-01-21 10:00:27.978852: step: 884/530, loss: 0.046959877014160156
2023-01-21 10:00:29.139529: step: 888/530, loss: 0.20209531486034393
2023-01-21 10:00:30.344501: step: 892/530, loss: 0.06541232764720917
2023-01-21 10:00:31.511032: step: 896/530, loss: 0.31880244612693787
2023-01-21 10:00:32.669974: step: 900/530, loss: 0.024764299392700195
2023-01-21 10:00:33.828766: step: 904/530, loss: 0.040851689875125885
2023-01-21 10:00:35.017733: step: 908/530, loss: 0.06192808225750923
2023-01-21 10:00:36.211493: step: 912/530, loss: 0.0012679100036621094
2023-01-21 10:00:37.369142: step: 916/530, loss: 0.10110047459602356
2023-01-21 10:00:38.561530: step: 920/530, loss: 0.48553696274757385
2023-01-21 10:00:39.745265: step: 924/530, loss: 0.39482155442237854
2023-01-21 10:00:40.925044: step: 928/530, loss: 0.10315370559692383
2023-01-21 10:00:42.124362: step: 932/530, loss: 0.07056531310081482
2023-01-21 10:00:43.330794: step: 936/530, loss: 0.4381921887397766
2023-01-21 10:00:44.503649: step: 940/530, loss: 0.015747547149658203
2023-01-21 10:00:45.662614: step: 944/530, loss: 0.2618350088596344
2023-01-21 10:00:46.833989: step: 948/530, loss: 0.16479292511940002
2023-01-21 10:00:48.049519: step: 952/530, loss: 0.2234029769897461
2023-01-21 10:00:49.229165: step: 956/530, loss: 0.03433685377240181
2023-01-21 10:00:50.445976: step: 960/530, loss: 0.004579448606818914
2023-01-21 10:00:51.620864: step: 964/530, loss: 0.049104057252407074
2023-01-21 10:00:52.802494: step: 968/530, loss: 0.0518835075199604
2023-01-21 10:00:53.981932: step: 972/530, loss: 0.06821499019861221
2023-01-21 10:00:55.194492: step: 976/530, loss: 0.09833602607250214
2023-01-21 10:00:56.361540: step: 980/530, loss: 0.06892852485179901
2023-01-21 10:00:57.506643: step: 984/530, loss: 0.07818165421485901
2023-01-21 10:00:58.688197: step: 988/530, loss: 0.2109006941318512
2023-01-21 10:00:59.882332: step: 992/530, loss: 0.4272526800632477
2023-01-21 10:01:01.079893: step: 996/530, loss: 0.047452785074710846
2023-01-21 10:01:02.290949: step: 1000/530, loss: 0.15157346427440643
2023-01-21 10:01:03.477295: step: 1004/530, loss: 0.18811312317848206
2023-01-21 10:01:04.677931: step: 1008/530, loss: 0.07474146038293839
2023-01-21 10:01:05.872984: step: 1012/530, loss: 0.06701584160327911
2023-01-21 10:01:07.038580: step: 1016/530, loss: 0.13227252662181854
2023-01-21 10:01:08.255606: step: 1020/530, loss: 0.08481156826019287
2023-01-21 10:01:09.425770: step: 1024/530, loss: 0.07477331161499023
2023-01-21 10:01:10.557299: step: 1028/530, loss: 0.14963455498218536
2023-01-21 10:01:11.805596: step: 1032/530, loss: 0.26902252435684204
2023-01-21 10:01:12.997179: step: 1036/530, loss: 0.06920204311609268
2023-01-21 10:01:14.130006: step: 1040/530, loss: 0.06259097903966904
2023-01-21 10:01:15.278507: step: 1044/530, loss: 0.017882157117128372
2023-01-21 10:01:16.442158: step: 1048/530, loss: 0.16647294163703918
2023-01-21 10:01:17.623544: step: 1052/530, loss: 0.014980221167206764
2023-01-21 10:01:18.796317: step: 1056/530, loss: 0.015264511108398438
2023-01-21 10:01:19.965823: step: 1060/530, loss: 0.05593071132898331
2023-01-21 10:01:21.141034: step: 1064/530, loss: 0.21541514992713928
2023-01-21 10:01:22.318362: step: 1068/530, loss: 0.037931155413389206
2023-01-21 10:01:23.510671: step: 1072/530, loss: 0.44292184710502625
2023-01-21 10:01:24.682326: step: 1076/530, loss: 0.06857776641845703
2023-01-21 10:01:25.891005: step: 1080/530, loss: 0.07078199833631516
2023-01-21 10:01:27.080577: step: 1084/530, loss: 0.08580265194177628
2023-01-21 10:01:28.289362: step: 1088/530, loss: 0.13268999755382538
2023-01-21 10:01:29.526485: step: 1092/530, loss: 0.17966032028198242
2023-01-21 10:01:30.655873: step: 1096/530, loss: 0.05442772060632706
2023-01-21 10:01:31.826236: step: 1100/530, loss: 0.007423782255500555
2023-01-21 10:01:33.007747: step: 1104/530, loss: 0.057573892176151276
2023-01-21 10:01:34.226924: step: 1108/530, loss: 0.5918250679969788
2023-01-21 10:01:35.452796: step: 1112/530, loss: 0.09379902482032776
2023-01-21 10:01:36.648841: step: 1116/530, loss: 0.03173828125
2023-01-21 10:01:37.836562: step: 1120/530, loss: 0.027653945609927177
2023-01-21 10:01:39.011217: step: 1124/530, loss: 0.025098610669374466
2023-01-21 10:01:40.226144: step: 1128/530, loss: 0.15435296297073364
2023-01-21 10:01:41.391452: step: 1132/530, loss: 0.02274918556213379
2023-01-21 10:01:42.609103: step: 1136/530, loss: 0.026772402226924896
2023-01-21 10:01:43.839555: step: 1140/530, loss: 0.03127851337194443
2023-01-21 10:01:45.019828: step: 1144/530, loss: 0.1578589826822281
2023-01-21 10:01:46.198959: step: 1148/530, loss: 0.09690102934837341
2023-01-21 10:01:47.389193: step: 1152/530, loss: 0.09761867672204971
2023-01-21 10:01:48.572361: step: 1156/530, loss: 0.19028446078300476
2023-01-21 10:01:49.774517: step: 1160/530, loss: 0.08661022782325745
2023-01-21 10:01:50.958374: step: 1164/530, loss: 0.14662230014801025
2023-01-21 10:01:52.146982: step: 1168/530, loss: 0.06844548881053925
2023-01-21 10:01:53.328470: step: 1172/530, loss: 0.13025951385498047
2023-01-21 10:01:54.512758: step: 1176/530, loss: 0.09994945675134659
2023-01-21 10:01:55.693397: step: 1180/530, loss: 0.05450735241174698
2023-01-21 10:01:56.919773: step: 1184/530, loss: 0.056549716740846634
2023-01-21 10:01:58.077565: step: 1188/530, loss: 0.5148805379867554
2023-01-21 10:01:59.256303: step: 1192/530, loss: 0.30767592787742615
2023-01-21 10:02:00.441662: step: 1196/530, loss: 0.044800471514463425
2023-01-21 10:02:01.572893: step: 1200/530, loss: 0.04206957668066025
2023-01-21 10:02:02.717580: step: 1204/530, loss: 0.014521313831210136
2023-01-21 10:02:03.875385: step: 1208/530, loss: 0.04784660413861275
2023-01-21 10:02:05.060631: step: 1212/530, loss: 0.13512355089187622
2023-01-21 10:02:06.236510: step: 1216/530, loss: 0.0498172752559185
2023-01-21 10:02:07.371647: step: 1220/530, loss: 0.02315545082092285
2023-01-21 10:02:08.573692: step: 1224/530, loss: 0.24566583335399628
2023-01-21 10:02:09.782834: step: 1228/530, loss: 0.06925515830516815
2023-01-21 10:02:10.934661: step: 1232/530, loss: 0.14455366134643555
2023-01-21 10:02:12.127641: step: 1236/530, loss: 0.04208822175860405
2023-01-21 10:02:13.278754: step: 1240/530, loss: 0.12012634426355362
2023-01-21 10:02:14.455684: step: 1244/530, loss: 0.023621082305908203
2023-01-21 10:02:15.631319: step: 1248/530, loss: 0.03550824895501137
2023-01-21 10:02:16.803936: step: 1252/530, loss: 0.05719804763793945
2023-01-21 10:02:17.992961: step: 1256/530, loss: 0.06784696131944656
2023-01-21 10:02:19.175391: step: 1260/530, loss: 0.09180068969726562
2023-01-21 10:02:20.363859: step: 1264/530, loss: 0.1408812552690506
2023-01-21 10:02:21.555675: step: 1268/530, loss: 0.21204060316085815
2023-01-21 10:02:22.744347: step: 1272/530, loss: 0.14301013946533203
2023-01-21 10:02:23.906031: step: 1276/530, loss: 0.09710659831762314
2023-01-21 10:02:25.062813: step: 1280/530, loss: 0.07046661525964737
2023-01-21 10:02:26.216448: step: 1284/530, loss: 0.15801700949668884
2023-01-21 10:02:27.392462: step: 1288/530, loss: 0.022974874824285507
2023-01-21 10:02:28.586658: step: 1292/530, loss: 0.17636719346046448
2023-01-21 10:02:29.697366: step: 1296/530, loss: 0.033312033861875534
2023-01-21 10:02:30.900735: step: 1300/530, loss: 0.09740486741065979
2023-01-21 10:02:32.079874: step: 1304/530, loss: 0.19906625151634216
2023-01-21 10:02:33.302943: step: 1308/530, loss: 0.07131786644458771
2023-01-21 10:02:34.460344: step: 1312/530, loss: 0.037758734077215195
2023-01-21 10:02:35.615527: step: 1316/530, loss: 0.024937011301517487
2023-01-21 10:02:36.784759: step: 1320/530, loss: 0.14974196255207062
2023-01-21 10:02:37.982351: step: 1324/530, loss: 0.049985792487859726
2023-01-21 10:02:39.176441: step: 1328/530, loss: 0.19455395638942719
2023-01-21 10:02:40.395731: step: 1332/530, loss: 0.4468805193901062
2023-01-21 10:02:41.606191: step: 1336/530, loss: 0.042569350451231
2023-01-21 10:02:42.787297: step: 1340/530, loss: 0.07818488776683807
2023-01-21 10:02:43.972693: step: 1344/530, loss: 0.05048418045043945
2023-01-21 10:02:45.169584: step: 1348/530, loss: 0.024895193055272102
2023-01-21 10:02:46.344646: step: 1352/530, loss: 0.13149681687355042
2023-01-21 10:02:47.539696: step: 1356/530, loss: 0.12719860672950745
2023-01-21 10:02:48.774335: step: 1360/530, loss: 0.010184097103774548
2023-01-21 10:02:49.970844: step: 1364/530, loss: 0.1038001999258995
2023-01-21 10:02:51.137234: step: 1368/530, loss: 0.08869022130966187
2023-01-21 10:02:52.330579: step: 1372/530, loss: 0.20104819536209106
2023-01-21 10:02:53.507153: step: 1376/530, loss: 0.12108460068702698
2023-01-21 10:02:54.741258: step: 1380/530, loss: 0.1257733851671219
2023-01-21 10:02:55.902581: step: 1384/530, loss: 0.10082702338695526
2023-01-21 10:02:57.105838: step: 1388/530, loss: 0.25426143407821655
2023-01-21 10:02:58.302592: step: 1392/530, loss: 0.04248414188623428
2023-01-21 10:02:59.485731: step: 1396/530, loss: 0.09141306579113007
2023-01-21 10:03:00.672788: step: 1400/530, loss: 0.03686637803912163
2023-01-21 10:03:01.940967: step: 1404/530, loss: 0.14809313416481018
2023-01-21 10:03:03.111496: step: 1408/530, loss: 0.38216662406921387
2023-01-21 10:03:04.302510: step: 1412/530, loss: 0.17603188753128052
2023-01-21 10:03:05.461482: step: 1416/530, loss: 0.17136649787425995
2023-01-21 10:03:06.680691: step: 1420/530, loss: 0.10437572002410889
2023-01-21 10:03:07.891920: step: 1424/530, loss: 0.09972548484802246
2023-01-21 10:03:09.068606: step: 1428/530, loss: 0.08594071865081787
2023-01-21 10:03:10.260299: step: 1432/530, loss: 0.06367502361536026
2023-01-21 10:03:11.436142: step: 1436/530, loss: 0.051168348640203476
2023-01-21 10:03:12.620678: step: 1440/530, loss: 0.05116138607263565
2023-01-21 10:03:13.803808: step: 1444/530, loss: 0.38174134492874146
2023-01-21 10:03:15.000093: step: 1448/530, loss: 0.06080923229455948
2023-01-21 10:03:16.185914: step: 1452/530, loss: 0.05187497287988663
2023-01-21 10:03:17.339351: step: 1456/530, loss: 0.2548791766166687
2023-01-21 10:03:18.484234: step: 1460/530, loss: 0.12913627922534943
2023-01-21 10:03:19.662234: step: 1464/530, loss: 0.15458975732326508
2023-01-21 10:03:20.787074: step: 1468/530, loss: 0.03883795812726021
2023-01-21 10:03:21.926376: step: 1472/530, loss: 0.09312081336975098
2023-01-21 10:03:23.109332: step: 1476/530, loss: 0.18543758988380432
2023-01-21 10:03:24.277907: step: 1480/530, loss: 0.11836633831262589
2023-01-21 10:03:25.443558: step: 1484/530, loss: 0.03745298087596893
2023-01-21 10:03:26.619504: step: 1488/530, loss: 0.022816849872469902
2023-01-21 10:03:27.764198: step: 1492/530, loss: 0.11238770186901093
2023-01-21 10:03:28.977698: step: 1496/530, loss: 0.09759664535522461
2023-01-21 10:03:30.145221: step: 1500/530, loss: 0.003906822297722101
2023-01-21 10:03:31.316195: step: 1504/530, loss: 0.04060111194849014
2023-01-21 10:03:32.518311: step: 1508/530, loss: 0.04522418975830078
2023-01-21 10:03:33.728801: step: 1512/530, loss: 0.01917257346212864
2023-01-21 10:03:34.889557: step: 1516/530, loss: 0.10081377625465393
2023-01-21 10:03:36.084839: step: 1520/530, loss: 0.06978444755077362
2023-01-21 10:03:37.294210: step: 1524/530, loss: 0.0520360954105854
2023-01-21 10:03:38.463053: step: 1528/530, loss: 0.025663042441010475
2023-01-21 10:03:39.625067: step: 1532/530, loss: 0.11294908821582794
2023-01-21 10:03:40.803281: step: 1536/530, loss: 0.07499366253614426
2023-01-21 10:03:41.964861: step: 1540/530, loss: 0.13869480788707733
2023-01-21 10:03:43.157663: step: 1544/530, loss: 0.08346385508775711
2023-01-21 10:03:44.318577: step: 1548/530, loss: 0.15427446365356445
2023-01-21 10:03:45.541526: step: 1552/530, loss: 0.17748050391674042
2023-01-21 10:03:46.713214: step: 1556/530, loss: 0.6396341323852539
2023-01-21 10:03:47.878503: step: 1560/530, loss: 0.09145331382751465
2023-01-21 10:03:49.060545: step: 1564/530, loss: 0.05875282362103462
2023-01-21 10:03:50.259773: step: 1568/530, loss: 0.02896604686975479
2023-01-21 10:03:51.452436: step: 1572/530, loss: 0.04940080642700195
2023-01-21 10:03:52.639032: step: 1576/530, loss: 0.08777294307947159
2023-01-21 10:03:53.825793: step: 1580/530, loss: 0.08255481719970703
2023-01-21 10:03:55.018311: step: 1584/530, loss: 0.0699835792183876
2023-01-21 10:03:56.177977: step: 1588/530, loss: 1.2319685220718384
2023-01-21 10:03:57.336588: step: 1592/530, loss: 0.08405351638793945
2023-01-21 10:03:58.548895: step: 1596/530, loss: 0.2647155821323395
2023-01-21 10:03:59.776382: step: 1600/530, loss: 0.07167161256074905
2023-01-21 10:04:00.977749: step: 1604/530, loss: 0.09674038738012314
2023-01-21 10:04:02.114066: step: 1608/530, loss: 0.12136144936084747
2023-01-21 10:04:03.281431: step: 1612/530, loss: 0.0273877140134573
2023-01-21 10:04:04.483615: step: 1616/530, loss: 0.16425058245658875
2023-01-21 10:04:05.667258: step: 1620/530, loss: 0.3084336221218109
2023-01-21 10:04:06.810414: step: 1624/530, loss: 0.08178134262561798
2023-01-21 10:04:08.021454: step: 1628/530, loss: 0.0524139404296875
2023-01-21 10:04:09.205817: step: 1632/530, loss: 0.04134741052985191
2023-01-21 10:04:10.385339: step: 1636/530, loss: 0.09371843189001083
2023-01-21 10:04:11.563949: step: 1640/530, loss: 0.17186136543750763
2023-01-21 10:04:12.734737: step: 1644/530, loss: 0.014878702349960804
2023-01-21 10:04:13.943312: step: 1648/530, loss: 0.06573009490966797
2023-01-21 10:04:15.112107: step: 1652/530, loss: 0.15445438027381897
2023-01-21 10:04:16.298855: step: 1656/530, loss: 0.08109722286462784
2023-01-21 10:04:17.464331: step: 1660/530, loss: 0.15646134316921234
2023-01-21 10:04:18.642459: step: 1664/530, loss: 0.11655063927173615
2023-01-21 10:04:19.856138: step: 1668/530, loss: 0.11370415985584259
2023-01-21 10:04:21.053703: step: 1672/530, loss: 0.06654338538646698
2023-01-21 10:04:22.254503: step: 1676/530, loss: 0.6581330895423889
2023-01-21 10:04:23.405393: step: 1680/530, loss: 0.07632245868444443
2023-01-21 10:04:24.561275: step: 1684/530, loss: 0.037191011011600494
2023-01-21 10:04:25.701853: step: 1688/530, loss: 0.23326975107192993
2023-01-21 10:04:26.889001: step: 1692/530, loss: 0.07800118625164032
2023-01-21 10:04:28.041598: step: 1696/530, loss: 0.07112687826156616
2023-01-21 10:04:29.219570: step: 1700/530, loss: 0.06100158765912056
2023-01-21 10:04:30.396016: step: 1704/530, loss: 0.0885646790266037
2023-01-21 10:04:31.578153: step: 1708/530, loss: 0.0851224958896637
2023-01-21 10:04:32.787940: step: 1712/530, loss: 0.08866768330335617
2023-01-21 10:04:33.957141: step: 1716/530, loss: 0.04599201679229736
2023-01-21 10:04:35.118623: step: 1720/530, loss: 0.2691568434238434
2023-01-21 10:04:36.310977: step: 1724/530, loss: 0.15080443024635315
2023-01-21 10:04:37.546982: step: 1728/530, loss: 0.015879392623901367
2023-01-21 10:04:38.712389: step: 1732/530, loss: 0.0680382177233696
2023-01-21 10:04:39.899263: step: 1736/530, loss: 0.10171106457710266
2023-01-21 10:04:41.102654: step: 1740/530, loss: 0.1690216064453125
2023-01-21 10:04:42.315164: step: 1744/530, loss: 0.11473341286182404
2023-01-21 10:04:43.540189: step: 1748/530, loss: 0.2098928540945053
2023-01-21 10:04:44.677962: step: 1752/530, loss: 0.0438079833984375
2023-01-21 10:04:45.887661: step: 1756/530, loss: 0.09689980000257492
2023-01-21 10:04:47.065529: step: 1760/530, loss: 0.0667186751961708
2023-01-21 10:04:48.216357: step: 1764/530, loss: 0.030570650473237038
2023-01-21 10:04:49.414038: step: 1768/530, loss: 0.05778038501739502
2023-01-21 10:04:50.589054: step: 1772/530, loss: 0.37360525131225586
2023-01-21 10:04:51.780962: step: 1776/530, loss: 0.15706387162208557
2023-01-21 10:04:52.963038: step: 1780/530, loss: 0.11285553127527237
2023-01-21 10:04:54.135021: step: 1784/530, loss: 0.05312204360961914
2023-01-21 10:04:55.288021: step: 1788/530, loss: 0.05213608592748642
2023-01-21 10:04:56.443561: step: 1792/530, loss: 0.09958372265100479
2023-01-21 10:04:57.621634: step: 1796/530, loss: 0.06323198974132538
2023-01-21 10:04:58.816894: step: 1800/530, loss: 0.7849858999252319
2023-01-21 10:04:59.978250: step: 1804/530, loss: 0.14441372454166412
2023-01-21 10:05:01.134809: step: 1808/530, loss: 0.11752147972583771
2023-01-21 10:05:02.311179: step: 1812/530, loss: 1.7219988107681274
2023-01-21 10:05:03.512540: step: 1816/530, loss: 0.019135331735014915
2023-01-21 10:05:04.730876: step: 1820/530, loss: 0.06368637830018997
2023-01-21 10:05:05.950189: step: 1824/530, loss: 0.08287639915943146
2023-01-21 10:05:07.103269: step: 1828/530, loss: 0.12142477184534073
2023-01-21 10:05:08.333986: step: 1832/530, loss: 0.17107053101062775
2023-01-21 10:05:09.499251: step: 1836/530, loss: 0.1173306480050087
2023-01-21 10:05:10.691544: step: 1840/530, loss: 0.009785938076674938
2023-01-21 10:05:11.870075: step: 1844/530, loss: 0.09142885357141495
2023-01-21 10:05:13.051002: step: 1848/530, loss: 0.07177609205245972
2023-01-21 10:05:14.230607: step: 1852/530, loss: 0.128559872508049
2023-01-21 10:05:15.411025: step: 1856/530, loss: 0.05397796630859375
2023-01-21 10:05:16.568787: step: 1860/530, loss: 0.3483026325702667
2023-01-21 10:05:17.753991: step: 1864/530, loss: 0.1017785593867302
2023-01-21 10:05:18.936521: step: 1868/530, loss: 0.06321001052856445
2023-01-21 10:05:20.132220: step: 1872/530, loss: 0.1154613047838211
2023-01-21 10:05:21.339379: step: 1876/530, loss: 0.927815854549408
2023-01-21 10:05:22.504893: step: 1880/530, loss: 0.1866447478532791
2023-01-21 10:05:23.663197: step: 1884/530, loss: 0.05659375339746475
2023-01-21 10:05:24.848033: step: 1888/530, loss: 0.007974433712661266
2023-01-21 10:05:26.053851: step: 1892/530, loss: 0.18185310065746307
2023-01-21 10:05:27.244796: step: 1896/530, loss: 0.06220044940710068
2023-01-21 10:05:28.437666: step: 1900/530, loss: 0.07474067062139511
2023-01-21 10:05:29.616604: step: 1904/530, loss: 0.04894981533288956
2023-01-21 10:05:30.794799: step: 1908/530, loss: 0.07573194801807404
2023-01-21 10:05:31.918448: step: 1912/530, loss: 0.10847350209951401
2023-01-21 10:05:33.103919: step: 1916/530, loss: 0.05642690882086754
2023-01-21 10:05:34.332818: step: 1920/530, loss: 0.06940746307373047
2023-01-21 10:05:35.495991: step: 1924/530, loss: 0.14880256354808807
2023-01-21 10:05:36.628449: step: 1928/530, loss: 0.08731837570667267
2023-01-21 10:05:37.830704: step: 1932/530, loss: 0.2570681571960449
2023-01-21 10:05:39.025646: step: 1936/530, loss: 0.03943147882819176
2023-01-21 10:05:40.199607: step: 1940/530, loss: 0.11312108486890793
2023-01-21 10:05:41.413186: step: 1944/530, loss: 0.0878661647439003
2023-01-21 10:05:42.587017: step: 1948/530, loss: 0.002971744630485773
2023-01-21 10:05:43.756984: step: 1952/530, loss: 0.08201484382152557
2023-01-21 10:05:44.936752: step: 1956/530, loss: 0.2055068016052246
2023-01-21 10:05:46.131976: step: 1960/530, loss: 0.03998398408293724
2023-01-21 10:05:47.291877: step: 1964/530, loss: 0.03222661092877388
2023-01-21 10:05:48.478384: step: 1968/530, loss: 0.12599678337574005
2023-01-21 10:05:49.658398: step: 1972/530, loss: 0.177737295627594
2023-01-21 10:05:50.816010: step: 1976/530, loss: 0.11004161834716797
2023-01-21 10:05:52.010387: step: 1980/530, loss: 0.0833350270986557
2023-01-21 10:05:53.195597: step: 1984/530, loss: 0.025358010083436966
2023-01-21 10:05:54.367105: step: 1988/530, loss: 0.013653278350830078
2023-01-21 10:05:55.537429: step: 1992/530, loss: 0.10583829879760742
2023-01-21 10:05:56.778956: step: 1996/530, loss: 0.2545835077762604
2023-01-21 10:05:57.948299: step: 2000/530, loss: 0.08382701873779297
2023-01-21 10:05:59.106876: step: 2004/530, loss: 0.056943416595458984
2023-01-21 10:06:00.274891: step: 2008/530, loss: 0.7045565843582153
2023-01-21 10:06:01.417961: step: 2012/530, loss: 0.28513795137405396
2023-01-21 10:06:02.604604: step: 2016/530, loss: 0.0303936954587698
2023-01-21 10:06:03.787492: step: 2020/530, loss: 0.11185251176357269
2023-01-21 10:06:04.934396: step: 2024/530, loss: 0.035360146313905716
2023-01-21 10:06:06.102680: step: 2028/530, loss: 0.03566727787256241
2023-01-21 10:06:07.315491: step: 2032/530, loss: 0.0769142135977745
2023-01-21 10:06:08.504973: step: 2036/530, loss: 0.09557457268238068
2023-01-21 10:06:09.785786: step: 2040/530, loss: 0.19323205947875977
2023-01-21 10:06:10.954604: step: 2044/530, loss: 0.13688507676124573
2023-01-21 10:06:12.142215: step: 2048/530, loss: 0.05665607750415802
2023-01-21 10:06:13.330199: step: 2052/530, loss: 0.5991809964179993
2023-01-21 10:06:14.483826: step: 2056/530, loss: 0.08317652344703674
2023-01-21 10:06:15.610709: step: 2060/530, loss: 1.5039992332458496
2023-01-21 10:06:16.797258: step: 2064/530, loss: 0.5881873369216919
2023-01-21 10:06:17.995678: step: 2068/530, loss: 0.0783659964799881
2023-01-21 10:06:19.161906: step: 2072/530, loss: 1.1040942668914795
2023-01-21 10:06:20.367153: step: 2076/530, loss: 0.20615653693675995
2023-01-21 10:06:21.545570: step: 2080/530, loss: 0.30007848143577576
2023-01-21 10:06:22.690242: step: 2084/530, loss: 0.2076784372329712
2023-01-21 10:06:23.893173: step: 2088/530, loss: 0.05692634731531143
2023-01-21 10:06:25.021217: step: 2092/530, loss: 0.30436134338378906
2023-01-21 10:06:26.187033: step: 2096/530, loss: 0.04967451095581055
2023-01-21 10:06:27.359105: step: 2100/530, loss: 0.01955242082476616
2023-01-21 10:06:28.599540: step: 2104/530, loss: 0.09320392459630966
2023-01-21 10:06:29.768836: step: 2108/530, loss: 0.11518576741218567
2023-01-21 10:06:30.984260: step: 2112/530, loss: 0.0668947696685791
2023-01-21 10:06:32.196389: step: 2116/530, loss: 0.7096875309944153
2023-01-21 10:06:33.436395: step: 2120/530, loss: 0.24146023392677307
==================================================
Loss: 0.140
--------------------
Dev: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.6379310344827587, 'r': 0.5873015873015873, 'f1': 0.6115702479338844}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.40476190476190477, 'r': 0.4722222222222222, 'f1': 0.4358974358974359}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:07:23.262650: step: 4/530, loss: 0.15845279395580292
2023-01-21 10:07:24.476247: step: 8/530, loss: 1.622707724571228
2023-01-21 10:07:25.675725: step: 12/530, loss: 0.33869075775146484
2023-01-21 10:07:26.829046: step: 16/530, loss: 0.08766070008277893
2023-01-21 10:07:27.976801: step: 20/530, loss: 0.06736107170581818
2023-01-21 10:07:29.160153: step: 24/530, loss: 0.039551734924316406
2023-01-21 10:07:30.367668: step: 28/530, loss: 0.08271016925573349
2023-01-21 10:07:31.511593: step: 32/530, loss: 0.044249631464481354
2023-01-21 10:07:32.697227: step: 36/530, loss: 0.0416165366768837
2023-01-21 10:07:33.887536: step: 40/530, loss: 0.0295378677546978
2023-01-21 10:07:35.052078: step: 44/530, loss: 0.03457288816571236
2023-01-21 10:07:36.231094: step: 48/530, loss: 0.0551789253950119
2023-01-21 10:07:37.412812: step: 52/530, loss: 0.28563404083251953
2023-01-21 10:07:38.579858: step: 56/530, loss: 0.1284927874803543
2023-01-21 10:07:39.753326: step: 60/530, loss: 0.03176317363977432
2023-01-21 10:07:40.896926: step: 64/530, loss: 0.22944431006908417
2023-01-21 10:07:42.073087: step: 68/530, loss: 0.0471712090075016
2023-01-21 10:07:43.287435: step: 72/530, loss: 0.07176385819911957
2023-01-21 10:07:44.487048: step: 76/530, loss: 0.07358169555664062
2023-01-21 10:07:45.753708: step: 80/530, loss: 0.051629211753606796
2023-01-21 10:07:46.934153: step: 84/530, loss: 0.03616919368505478
2023-01-21 10:07:48.079795: step: 88/530, loss: 0.08161049336194992
2023-01-21 10:07:49.229953: step: 92/530, loss: 0.0617462694644928
2023-01-21 10:07:50.401127: step: 96/530, loss: 0.1673245131969452
2023-01-21 10:07:51.580903: step: 100/530, loss: 0.059185028076171875
2023-01-21 10:07:52.746477: step: 104/530, loss: 0.017926884815096855
2023-01-21 10:07:53.914857: step: 108/530, loss: 0.0749857947230339
2023-01-21 10:07:55.098470: step: 112/530, loss: 0.04163084179162979
2023-01-21 10:07:56.298346: step: 116/530, loss: 0.18099918961524963
2023-01-21 10:07:57.476625: step: 120/530, loss: 0.9036290049552917
2023-01-21 10:07:58.635759: step: 124/530, loss: 0.09026701748371124
2023-01-21 10:07:59.828109: step: 128/530, loss: 0.03945193439722061
2023-01-21 10:08:01.006663: step: 132/530, loss: 0.11284341663122177
2023-01-21 10:08:02.205521: step: 136/530, loss: 0.05342855677008629
2023-01-21 10:08:03.355937: step: 140/530, loss: 0.012876033782958984
2023-01-21 10:08:04.566568: step: 144/530, loss: 0.07015285640954971
2023-01-21 10:08:05.788619: step: 148/530, loss: 0.16492271423339844
2023-01-21 10:08:06.975065: step: 152/530, loss: 0.4989575445652008
2023-01-21 10:08:08.219361: step: 156/530, loss: 0.2948346436023712
2023-01-21 10:08:09.390249: step: 160/530, loss: 0.04725055769085884
2023-01-21 10:08:10.659591: step: 164/530, loss: 0.011922741308808327
2023-01-21 10:08:11.877463: step: 168/530, loss: 0.12056002765893936
2023-01-21 10:08:13.082485: step: 172/530, loss: 0.028836537152528763
2023-01-21 10:08:14.262848: step: 176/530, loss: 0.009949922561645508
2023-01-21 10:08:15.467290: step: 180/530, loss: 0.06635189056396484
2023-01-21 10:08:16.622182: step: 184/530, loss: 0.06446342170238495
2023-01-21 10:08:17.769670: step: 188/530, loss: 0.026972293853759766
2023-01-21 10:08:18.944424: step: 192/530, loss: 0.03372917324304581
2023-01-21 10:08:20.106579: step: 196/530, loss: 0.1725679486989975
2023-01-21 10:08:21.275113: step: 200/530, loss: 0.06030445173382759
2023-01-21 10:08:22.467263: step: 204/530, loss: 0.01964731328189373
2023-01-21 10:08:23.617629: step: 208/530, loss: 0.028240298852324486
2023-01-21 10:08:24.845885: step: 212/530, loss: 0.10379738360643387
2023-01-21 10:08:26.015640: step: 216/530, loss: 0.04669012874364853
2023-01-21 10:08:27.178734: step: 220/530, loss: 0.2680344581604004
2023-01-21 10:08:28.330621: step: 224/530, loss: 0.060888100415468216
2023-01-21 10:08:29.488732: step: 228/530, loss: 0.02537250518798828
2023-01-21 10:08:30.678227: step: 232/530, loss: 0.10358190536499023
2023-01-21 10:08:31.815507: step: 236/530, loss: 0.11830854415893555
2023-01-21 10:08:32.978884: step: 240/530, loss: 0.3694027066230774
2023-01-21 10:08:34.156760: step: 244/530, loss: 0.02728118933737278
2023-01-21 10:08:35.395929: step: 248/530, loss: 0.09859142452478409
2023-01-21 10:08:36.574288: step: 252/530, loss: 0.10015678405761719
2023-01-21 10:08:37.775098: step: 256/530, loss: 0.122918039560318
2023-01-21 10:08:38.973947: step: 260/530, loss: 0.018300820142030716
2023-01-21 10:08:40.110830: step: 264/530, loss: 0.02513599582016468
2023-01-21 10:08:41.317928: step: 268/530, loss: 0.0987861156463623
2023-01-21 10:08:42.505921: step: 272/530, loss: 0.09005054831504822
2023-01-21 10:08:43.644629: step: 276/530, loss: 0.007241535000503063
2023-01-21 10:08:44.819748: step: 280/530, loss: 0.044896893203258514
2023-01-21 10:08:45.963328: step: 284/530, loss: 0.007006979547441006
2023-01-21 10:08:47.131822: step: 288/530, loss: 0.05658278614282608
2023-01-21 10:08:48.288631: step: 292/530, loss: 0.026295794174075127
2023-01-21 10:08:49.502942: step: 296/530, loss: 0.013226342387497425
2023-01-21 10:08:50.650039: step: 300/530, loss: 0.02804575115442276
2023-01-21 10:08:51.880352: step: 304/530, loss: 0.044394779950380325
2023-01-21 10:08:53.055932: step: 308/530, loss: 0.22662125527858734
2023-01-21 10:08:54.224113: step: 312/530, loss: 0.043686769902706146
2023-01-21 10:08:55.421002: step: 316/530, loss: 0.058339785784482956
2023-01-21 10:08:56.648537: step: 320/530, loss: 0.20755872130393982
2023-01-21 10:08:57.786858: step: 324/530, loss: 0.10466700047254562
2023-01-21 10:08:59.008252: step: 328/530, loss: 0.06837377697229385
2023-01-21 10:09:00.165739: step: 332/530, loss: 0.07297305762767792
2023-01-21 10:09:01.310524: step: 336/530, loss: 0.03483028709888458
2023-01-21 10:09:02.514679: step: 340/530, loss: 0.06621008366346359
2023-01-21 10:09:03.700101: step: 344/530, loss: 0.3091033399105072
2023-01-21 10:09:04.855777: step: 348/530, loss: 0.015868376940488815
2023-01-21 10:09:06.002284: step: 352/530, loss: 0.019069766625761986
2023-01-21 10:09:07.173540: step: 356/530, loss: 0.014092206954956055
2023-01-21 10:09:08.383364: step: 360/530, loss: 0.010200024582445621
2023-01-21 10:09:09.562410: step: 364/530, loss: 0.04045286029577255
2023-01-21 10:09:10.727622: step: 368/530, loss: 0.10821942985057831
2023-01-21 10:09:11.877639: step: 372/530, loss: 0.04107093811035156
2023-01-21 10:09:13.036024: step: 376/530, loss: 0.13373327255249023
2023-01-21 10:09:14.237362: step: 380/530, loss: 0.01893320120871067
2023-01-21 10:09:15.404949: step: 384/530, loss: 0.09141799807548523
2023-01-21 10:09:16.559920: step: 388/530, loss: 0.015536022372543812
2023-01-21 10:09:17.699282: step: 392/530, loss: 0.060567498207092285
2023-01-21 10:09:18.886084: step: 396/530, loss: 0.04974031448364258
2023-01-21 10:09:20.079253: step: 400/530, loss: 0.06978759914636612
2023-01-21 10:09:21.258427: step: 404/530, loss: 0.07836513221263885
2023-01-21 10:09:22.413015: step: 408/530, loss: 0.048665713518857956
2023-01-21 10:09:23.581160: step: 412/530, loss: 0.03707246854901314
2023-01-21 10:09:24.770640: step: 416/530, loss: 0.03857602924108505
2023-01-21 10:09:25.922676: step: 420/530, loss: 0.04320202022790909
2023-01-21 10:09:27.061044: step: 424/530, loss: 0.06060810014605522
2023-01-21 10:09:28.239379: step: 428/530, loss: 0.032482028007507324
2023-01-21 10:09:29.417954: step: 432/530, loss: 0.021082688122987747
2023-01-21 10:09:30.598832: step: 436/530, loss: 0.006242180243134499
2023-01-21 10:09:31.782022: step: 440/530, loss: 0.03648901358246803
2023-01-21 10:09:32.942202: step: 444/530, loss: 0.10904040187597275
2023-01-21 10:09:34.130034: step: 448/530, loss: 0.04181623458862305
2023-01-21 10:09:35.340078: step: 452/530, loss: 0.06782789528369904
2023-01-21 10:09:36.536670: step: 456/530, loss: 0.04444284737110138
2023-01-21 10:09:37.769456: step: 460/530, loss: 0.08857281506061554
2023-01-21 10:09:38.960977: step: 464/530, loss: 0.015480137430131435
2023-01-21 10:09:40.183490: step: 468/530, loss: 0.04405803605914116
2023-01-21 10:09:41.413317: step: 472/530, loss: 0.06597767025232315
2023-01-21 10:09:42.644001: step: 476/530, loss: 0.25855541229248047
2023-01-21 10:09:43.842286: step: 480/530, loss: 0.09969902038574219
2023-01-21 10:09:45.018455: step: 484/530, loss: 0.07222404330968857
2023-01-21 10:09:46.190530: step: 488/530, loss: 0.05053606256842613
2023-01-21 10:09:47.368693: step: 492/530, loss: 0.8873142004013062
2023-01-21 10:09:48.577782: step: 496/530, loss: 0.1109904795885086
2023-01-21 10:09:49.754799: step: 500/530, loss: 0.1378006935119629
2023-01-21 10:09:50.933775: step: 504/530, loss: 0.031890176236629486
2023-01-21 10:09:52.079832: step: 508/530, loss: 0.021184062585234642
2023-01-21 10:09:53.309190: step: 512/530, loss: 0.07848325371742249
2023-01-21 10:09:54.457879: step: 516/530, loss: 0.1467302292585373
2023-01-21 10:09:55.627739: step: 520/530, loss: 0.10992298275232315
2023-01-21 10:09:56.801314: step: 524/530, loss: 0.0708930492401123
2023-01-21 10:09:57.982864: step: 528/530, loss: 0.08113260567188263
2023-01-21 10:09:59.121966: step: 532/530, loss: 0.06294284015893936
2023-01-21 10:10:00.287414: step: 536/530, loss: 0.134280726313591
2023-01-21 10:10:01.517374: step: 540/530, loss: 0.0459783561527729
2023-01-21 10:10:02.711647: step: 544/530, loss: 0.025130653753876686
2023-01-21 10:10:03.908326: step: 548/530, loss: 0.17327946424484253
2023-01-21 10:10:05.093934: step: 552/530, loss: 0.004549503326416016
2023-01-21 10:10:06.316588: step: 556/530, loss: 0.11944351345300674
2023-01-21 10:10:07.471593: step: 560/530, loss: 0.04510369524359703
2023-01-21 10:10:08.658398: step: 564/530, loss: 0.24413014948368073
2023-01-21 10:10:09.817528: step: 568/530, loss: 0.053214170038700104
2023-01-21 10:10:10.996626: step: 572/530, loss: 0.04179535061120987
2023-01-21 10:10:12.161756: step: 576/530, loss: 0.028563402593135834
2023-01-21 10:10:13.368467: step: 580/530, loss: 0.10005893558263779
2023-01-21 10:10:14.551717: step: 584/530, loss: 0.06685810536146164
2023-01-21 10:10:15.712577: step: 588/530, loss: 0.04205475002527237
2023-01-21 10:10:16.856659: step: 592/530, loss: 0.00614776648581028
2023-01-21 10:10:18.070415: step: 596/530, loss: 0.04956074059009552
2023-01-21 10:10:19.250448: step: 600/530, loss: 0.1447279006242752
2023-01-21 10:10:20.472333: step: 604/530, loss: 0.01263275183737278
2023-01-21 10:10:21.600989: step: 608/530, loss: 0.011170101352036
2023-01-21 10:10:22.755772: step: 612/530, loss: 0.06403732299804688
2023-01-21 10:10:23.973690: step: 616/530, loss: 0.035303402692079544
2023-01-21 10:10:25.149459: step: 620/530, loss: 0.129747673869133
2023-01-21 10:10:26.345721: step: 624/530, loss: 0.10466757416725159
2023-01-21 10:10:27.544339: step: 628/530, loss: 0.022001981735229492
2023-01-21 10:10:28.672650: step: 632/530, loss: 0.0452788844704628
2023-01-21 10:10:29.845749: step: 636/530, loss: 0.040712930262088776
2023-01-21 10:10:31.035653: step: 640/530, loss: 0.041222475469112396
2023-01-21 10:10:32.197795: step: 644/530, loss: 0.1497552990913391
2023-01-21 10:10:33.360772: step: 648/530, loss: 0.06223516911268234
2023-01-21 10:10:34.516393: step: 652/530, loss: 0.07656240463256836
2023-01-21 10:10:35.686373: step: 656/530, loss: 0.0846463292837143
2023-01-21 10:10:36.854727: step: 660/530, loss: 0.09599395096302032
2023-01-21 10:10:38.035795: step: 664/530, loss: 0.10290992259979248
2023-01-21 10:10:39.205517: step: 668/530, loss: 0.07619600743055344
2023-01-21 10:10:40.363919: step: 672/530, loss: 0.03589000552892685
2023-01-21 10:10:41.532994: step: 676/530, loss: 0.07724523544311523
2023-01-21 10:10:42.755421: step: 680/530, loss: 0.05449113994836807
2023-01-21 10:10:43.946764: step: 684/530, loss: 0.06263675540685654
2023-01-21 10:10:45.133339: step: 688/530, loss: 0.04581804573535919
2023-01-21 10:10:46.289168: step: 692/530, loss: 0.01583724096417427
2023-01-21 10:10:47.481781: step: 696/530, loss: 0.13324417173862457
2023-01-21 10:10:48.678352: step: 700/530, loss: 0.03744878992438316
2023-01-21 10:10:49.870702: step: 704/530, loss: 0.03915085643529892
2023-01-21 10:10:51.081946: step: 708/530, loss: 0.06985321640968323
2023-01-21 10:10:52.231028: step: 712/530, loss: 0.02766655758023262
2023-01-21 10:10:53.463024: step: 716/530, loss: 0.061554476618766785
2023-01-21 10:10:54.655816: step: 720/530, loss: 0.08023491501808167
2023-01-21 10:10:55.823836: step: 724/530, loss: 0.17367896437644958
2023-01-21 10:10:57.034835: step: 728/530, loss: 0.1662307232618332
2023-01-21 10:10:58.235739: step: 732/530, loss: 0.036238670349121094
2023-01-21 10:10:59.442698: step: 736/530, loss: 0.07550239562988281
2023-01-21 10:11:00.588841: step: 740/530, loss: 0.020705081522464752
2023-01-21 10:11:01.776800: step: 744/530, loss: 0.032326020300388336
2023-01-21 10:11:02.949787: step: 748/530, loss: 0.2889842987060547
2023-01-21 10:11:04.151909: step: 752/530, loss: 0.038077257573604584
2023-01-21 10:11:05.316407: step: 756/530, loss: 0.020296193659305573
2023-01-21 10:11:06.477554: step: 760/530, loss: 0.12724390625953674
2023-01-21 10:11:07.686434: step: 764/530, loss: 6.227782726287842
2023-01-21 10:11:08.883046: step: 768/530, loss: 0.0704723373055458
2023-01-21 10:11:10.033837: step: 772/530, loss: 0.010985375382006168
2023-01-21 10:11:11.230112: step: 776/530, loss: 0.035125862807035446
2023-01-21 10:11:12.441383: step: 780/530, loss: 0.02393341064453125
2023-01-21 10:11:13.621599: step: 784/530, loss: 0.03975982964038849
2023-01-21 10:11:14.763571: step: 788/530, loss: 0.1708083152770996
2023-01-21 10:11:15.933196: step: 792/530, loss: 0.547723114490509
2023-01-21 10:11:17.089846: step: 796/530, loss: 0.14834804832935333
2023-01-21 10:11:18.282289: step: 800/530, loss: 0.19332151114940643
2023-01-21 10:11:19.432605: step: 804/530, loss: 1.8239805698394775
2023-01-21 10:11:20.578081: step: 808/530, loss: 0.08215799927711487
2023-01-21 10:11:21.870531: step: 812/530, loss: 0.06138224899768829
2023-01-21 10:11:23.020215: step: 816/530, loss: 0.041655588895082474
2023-01-21 10:11:24.241714: step: 820/530, loss: 0.051939964294433594
2023-01-21 10:11:25.411825: step: 824/530, loss: 0.03875446319580078
2023-01-21 10:11:26.577005: step: 828/530, loss: 0.09748440235853195
2023-01-21 10:11:27.757655: step: 832/530, loss: 0.06202840805053711
2023-01-21 10:11:28.968045: step: 836/530, loss: 0.06961822509765625
2023-01-21 10:11:30.177487: step: 840/530, loss: 0.016143132001161575
2023-01-21 10:11:31.337776: step: 844/530, loss: 0.004495430272072554
2023-01-21 10:11:32.492746: step: 848/530, loss: 0.007852828130126
2023-01-21 10:11:33.694469: step: 852/530, loss: 0.049698878079652786
2023-01-21 10:11:34.928606: step: 856/530, loss: 0.12559108436107635
2023-01-21 10:11:36.138206: step: 860/530, loss: 0.00766568211838603
2023-01-21 10:11:37.316751: step: 864/530, loss: 0.09925498813390732
2023-01-21 10:11:38.479369: step: 868/530, loss: 0.03700599819421768
2023-01-21 10:11:39.633715: step: 872/530, loss: 0.014387035742402077
2023-01-21 10:11:40.835952: step: 876/530, loss: 0.016269970685243607
2023-01-21 10:11:42.067635: step: 880/530, loss: 0.03401973471045494
2023-01-21 10:11:43.235140: step: 884/530, loss: 0.039260294288396835
2023-01-21 10:11:44.434366: step: 888/530, loss: 0.05661635473370552
2023-01-21 10:11:45.593993: step: 892/530, loss: 0.08707509189844131
2023-01-21 10:11:46.770116: step: 896/530, loss: 0.0644037276506424
2023-01-21 10:11:47.937826: step: 900/530, loss: 0.11059337109327316
2023-01-21 10:11:49.110191: step: 904/530, loss: 0.5515964031219482
2023-01-21 10:11:50.264618: step: 908/530, loss: 0.05791626125574112
2023-01-21 10:11:51.444953: step: 912/530, loss: 0.094445139169693
2023-01-21 10:11:52.622138: step: 916/530, loss: 0.10451459884643555
2023-01-21 10:11:53.854776: step: 920/530, loss: 0.07610253989696503
2023-01-21 10:11:55.111411: step: 924/530, loss: 0.2037479430437088
2023-01-21 10:11:56.308238: step: 928/530, loss: 0.09647388756275177
2023-01-21 10:11:57.490521: step: 932/530, loss: 0.02946005016565323
2023-01-21 10:11:58.675829: step: 936/530, loss: 0.10217857360839844
2023-01-21 10:11:59.849905: step: 940/530, loss: 0.009791946038603783
2023-01-21 10:12:01.018959: step: 944/530, loss: 0.07124662399291992
2023-01-21 10:12:02.204354: step: 948/530, loss: 0.01458120346069336
2023-01-21 10:12:03.403485: step: 952/530, loss: 0.266981303691864
2023-01-21 10:12:04.635040: step: 956/530, loss: 0.07228453457355499
2023-01-21 10:12:05.807546: step: 960/530, loss: 0.022940827533602715
2023-01-21 10:12:06.959976: step: 964/530, loss: 0.15632718801498413
2023-01-21 10:12:08.151308: step: 968/530, loss: 0.16595040261745453
2023-01-21 10:12:09.317588: step: 972/530, loss: 0.02584867551922798
2023-01-21 10:12:10.477357: step: 976/530, loss: 0.040729425847530365
2023-01-21 10:12:11.676492: step: 980/530, loss: 0.06620617210865021
2023-01-21 10:12:12.870996: step: 984/530, loss: 0.6692536473274231
2023-01-21 10:12:14.012832: step: 988/530, loss: 0.10619039833545685
2023-01-21 10:12:15.202647: step: 992/530, loss: 0.021389387547969818
2023-01-21 10:12:16.397269: step: 996/530, loss: 0.09521007537841797
2023-01-21 10:12:17.563258: step: 1000/530, loss: 0.12559795379638672
2023-01-21 10:12:18.742416: step: 1004/530, loss: 0.10956211388111115
2023-01-21 10:12:19.906215: step: 1008/530, loss: 0.025915145874023438
2023-01-21 10:12:21.076006: step: 1012/530, loss: 0.7702674269676208
2023-01-21 10:12:22.214107: step: 1016/530, loss: 0.07918114960193634
2023-01-21 10:12:23.371434: step: 1020/530, loss: 0.09994392096996307
2023-01-21 10:12:24.532213: step: 1024/530, loss: 0.018405748531222343
2023-01-21 10:12:25.708145: step: 1028/530, loss: 0.06505708396434784
2023-01-21 10:12:26.855017: step: 1032/530, loss: 0.05158384144306183
2023-01-21 10:12:28.050639: step: 1036/530, loss: 0.013117790222167969
2023-01-21 10:12:29.223856: step: 1040/530, loss: 0.053784895688295364
2023-01-21 10:12:30.425123: step: 1044/530, loss: 0.0009424209711141884
2023-01-21 10:12:31.589990: step: 1048/530, loss: 0.028988217934966087
2023-01-21 10:12:32.781034: step: 1052/530, loss: 0.09882692992687225
2023-01-21 10:12:33.988453: step: 1056/530, loss: 0.10553894191980362
2023-01-21 10:12:35.171052: step: 1060/530, loss: 0.03369283676147461
2023-01-21 10:12:36.384428: step: 1064/530, loss: 0.10636568069458008
2023-01-21 10:12:37.611212: step: 1068/530, loss: 0.09341640770435333
2023-01-21 10:12:38.779693: step: 1072/530, loss: 0.0036599875893443823
2023-01-21 10:12:39.971830: step: 1076/530, loss: 0.041690826416015625
2023-01-21 10:12:41.164455: step: 1080/530, loss: 0.01931467279791832
2023-01-21 10:12:42.363684: step: 1084/530, loss: 0.07385434955358505
2023-01-21 10:12:43.556224: step: 1088/530, loss: 0.028326798230409622
2023-01-21 10:12:44.705673: step: 1092/530, loss: 0.0036805630661547184
2023-01-21 10:12:45.897263: step: 1096/530, loss: 0.06924257427453995
2023-01-21 10:12:47.016564: step: 1100/530, loss: 0.040366724133491516
2023-01-21 10:12:48.215858: step: 1104/530, loss: 0.015607595443725586
2023-01-21 10:12:49.394527: step: 1108/530, loss: 0.1588093787431717
2023-01-21 10:12:50.595892: step: 1112/530, loss: 0.021831322461366653
2023-01-21 10:12:51.755334: step: 1116/530, loss: 0.1833307147026062
2023-01-21 10:12:52.930023: step: 1120/530, loss: 0.04198112338781357
2023-01-21 10:12:54.095775: step: 1124/530, loss: 0.018747713416814804
2023-01-21 10:12:55.270722: step: 1128/530, loss: 0.058507729321718216
2023-01-21 10:12:56.470433: step: 1132/530, loss: 0.04667625576257706
2023-01-21 10:12:57.651068: step: 1136/530, loss: 0.14336252212524414
2023-01-21 10:12:58.835526: step: 1140/530, loss: 0.03824019432067871
2023-01-21 10:13:00.035103: step: 1144/530, loss: 0.039048388600349426
2023-01-21 10:13:01.246195: step: 1148/530, loss: 0.10422239452600479
2023-01-21 10:13:02.433896: step: 1152/530, loss: 0.10801353305578232
2023-01-21 10:13:03.641336: step: 1156/530, loss: 0.26632562279701233
2023-01-21 10:13:04.835718: step: 1160/530, loss: 0.07175872474908829
2023-01-21 10:13:06.054121: step: 1164/530, loss: 0.0644746795296669
2023-01-21 10:13:07.216952: step: 1168/530, loss: 0.19294533133506775
2023-01-21 10:13:08.415515: step: 1172/530, loss: 0.21934567391872406
2023-01-21 10:13:09.550691: step: 1176/530, loss: 0.022718096151947975
2023-01-21 10:13:10.727636: step: 1180/530, loss: 0.11897353827953339
2023-01-21 10:13:11.912778: step: 1184/530, loss: 0.0520656555891037
2023-01-21 10:13:13.065556: step: 1188/530, loss: 0.21914702653884888
2023-01-21 10:13:14.282414: step: 1192/530, loss: 0.09227696061134338
2023-01-21 10:13:15.459275: step: 1196/530, loss: 0.06390824168920517
2023-01-21 10:13:16.681793: step: 1200/530, loss: 0.08842983841896057
2023-01-21 10:13:17.846493: step: 1204/530, loss: 0.057123471051454544
2023-01-21 10:13:19.026046: step: 1208/530, loss: 0.1228095144033432
2023-01-21 10:13:20.200391: step: 1212/530, loss: 0.08844508975744247
2023-01-21 10:13:21.365084: step: 1216/530, loss: 0.011104035191237926
2023-01-21 10:13:22.510947: step: 1220/530, loss: 0.014559745788574219
2023-01-21 10:13:23.690295: step: 1224/530, loss: 0.09527621418237686
2023-01-21 10:13:24.863522: step: 1228/530, loss: 0.021008683368563652
2023-01-21 10:13:26.076038: step: 1232/530, loss: 0.13089609146118164
2023-01-21 10:13:27.270033: step: 1236/530, loss: 0.018972396850585938
2023-01-21 10:13:28.450620: step: 1240/530, loss: 0.12789621949195862
2023-01-21 10:13:29.665398: step: 1244/530, loss: 0.1727897673845291
2023-01-21 10:13:30.846772: step: 1248/530, loss: 0.14199848473072052
2023-01-21 10:13:32.068670: step: 1252/530, loss: 0.014613533392548561
2023-01-21 10:13:33.260924: step: 1256/530, loss: 0.08304043114185333
2023-01-21 10:13:34.447073: step: 1260/530, loss: 0.0358274020254612
2023-01-21 10:13:35.579600: step: 1264/530, loss: 0.062093257904052734
2023-01-21 10:13:36.766658: step: 1268/530, loss: 0.1521453857421875
2023-01-21 10:13:37.955827: step: 1272/530, loss: 0.41924938559532166
2023-01-21 10:13:39.137096: step: 1276/530, loss: 0.06571187824010849
2023-01-21 10:13:40.318717: step: 1280/530, loss: 0.050582122057676315
2023-01-21 10:13:41.496124: step: 1284/530, loss: 0.037352561950683594
2023-01-21 10:13:42.729436: step: 1288/530, loss: 0.1718570739030838
2023-01-21 10:13:43.923126: step: 1292/530, loss: 0.05200400575995445
2023-01-21 10:13:45.105284: step: 1296/530, loss: 0.045015908777713776
2023-01-21 10:13:46.247780: step: 1300/530, loss: 0.22699260711669922
2023-01-21 10:13:47.414325: step: 1304/530, loss: 0.05964255705475807
2023-01-21 10:13:48.640128: step: 1308/530, loss: 0.21141637861728668
2023-01-21 10:13:49.834897: step: 1312/530, loss: 0.04659365862607956
2023-01-21 10:13:50.993764: step: 1316/530, loss: 0.007095909211784601
2023-01-21 10:13:52.185082: step: 1320/530, loss: 0.009560060687363148
2023-01-21 10:13:53.380373: step: 1324/530, loss: 0.0548061840236187
2023-01-21 10:13:54.592385: step: 1328/530, loss: 0.03962211683392525
2023-01-21 10:13:55.784986: step: 1332/530, loss: 0.024711133912205696
2023-01-21 10:13:56.944762: step: 1336/530, loss: 0.014567517675459385
2023-01-21 10:13:58.116317: step: 1340/530, loss: 0.36985188722610474
2023-01-21 10:13:59.265819: step: 1344/530, loss: 0.18090248107910156
2023-01-21 10:14:00.482577: step: 1348/530, loss: 0.20969204604625702
2023-01-21 10:14:01.647271: step: 1352/530, loss: 0.12543784081935883
2023-01-21 10:14:02.814523: step: 1356/530, loss: 0.21262595057487488
2023-01-21 10:14:03.989300: step: 1360/530, loss: 0.005930805113166571
2023-01-21 10:14:05.177931: step: 1364/530, loss: 0.031262971460819244
2023-01-21 10:14:06.364815: step: 1368/530, loss: 0.054126814007759094
2023-01-21 10:14:07.494529: step: 1372/530, loss: 0.052906036376953125
2023-01-21 10:14:08.684442: step: 1376/530, loss: 0.09675750881433487
2023-01-21 10:14:09.883790: step: 1380/530, loss: 0.03650627285242081
2023-01-21 10:14:11.072595: step: 1384/530, loss: 0.14927463233470917
2023-01-21 10:14:12.234351: step: 1388/530, loss: 0.022114086896181107
2023-01-21 10:14:13.425729: step: 1392/530, loss: 0.14367036521434784
2023-01-21 10:14:14.566768: step: 1396/530, loss: 0.08893384784460068
2023-01-21 10:14:15.727018: step: 1400/530, loss: 0.036626528948545456
2023-01-21 10:14:16.898635: step: 1404/530, loss: 0.02657156065106392
2023-01-21 10:14:18.091765: step: 1408/530, loss: 0.06285410374403
2023-01-21 10:14:19.298369: step: 1412/530, loss: 0.0449947826564312
2023-01-21 10:14:20.469838: step: 1416/530, loss: 0.05079841613769531
2023-01-21 10:14:21.665660: step: 1420/530, loss: 0.007391166873276234
2023-01-21 10:14:22.899218: step: 1424/530, loss: 0.19784145057201385
2023-01-21 10:14:24.103654: step: 1428/530, loss: 0.07485189288854599
2023-01-21 10:14:25.297531: step: 1432/530, loss: 0.11022701114416122
2023-01-21 10:14:26.510191: step: 1436/530, loss: 0.14997348189353943
2023-01-21 10:14:27.686602: step: 1440/530, loss: 0.018115997314453125
2023-01-21 10:14:28.851365: step: 1444/530, loss: 0.028583623468875885
2023-01-21 10:14:30.077434: step: 1448/530, loss: 0.16174563765525818
2023-01-21 10:14:31.297310: step: 1452/530, loss: 0.07666949927806854
2023-01-21 10:14:32.472263: step: 1456/530, loss: 0.07380715757608414
2023-01-21 10:14:33.644345: step: 1460/530, loss: 0.00554580707103014
2023-01-21 10:14:34.833113: step: 1464/530, loss: 0.05170736089348793
2023-01-21 10:14:36.071619: step: 1468/530, loss: 0.06031398847699165
2023-01-21 10:14:37.257275: step: 1472/530, loss: 0.055828481912612915
2023-01-21 10:14:38.427070: step: 1476/530, loss: 0.05847177654504776
2023-01-21 10:14:39.626965: step: 1480/530, loss: 0.04697704687714577
2023-01-21 10:14:40.818181: step: 1484/530, loss: 0.057266999036073685
2023-01-21 10:14:42.041067: step: 1488/530, loss: 0.18401594460010529
2023-01-21 10:14:43.245223: step: 1492/530, loss: 0.0021869661286473274
2023-01-21 10:14:44.450026: step: 1496/530, loss: 0.1832314431667328
2023-01-21 10:14:45.650796: step: 1500/530, loss: 0.05921168625354767
2023-01-21 10:14:46.818026: step: 1504/530, loss: 0.039419081062078476
2023-01-21 10:14:48.007484: step: 1508/530, loss: 0.066564179956913
2023-01-21 10:14:49.165049: step: 1512/530, loss: 0.1521112471818924
2023-01-21 10:14:50.378635: step: 1516/530, loss: 0.17261992394924164
2023-01-21 10:14:51.535013: step: 1520/530, loss: 0.14822015166282654
2023-01-21 10:14:52.712376: step: 1524/530, loss: 0.15001411736011505
2023-01-21 10:14:53.900420: step: 1528/530, loss: 0.12929821014404297
2023-01-21 10:14:55.080140: step: 1532/530, loss: 0.008008575066924095
2023-01-21 10:14:56.256009: step: 1536/530, loss: 0.08087348937988281
2023-01-21 10:14:57.438352: step: 1540/530, loss: 0.046652697026729584
2023-01-21 10:14:58.615149: step: 1544/530, loss: 0.03032541275024414
2023-01-21 10:14:59.811762: step: 1548/530, loss: 0.018466543406248093
2023-01-21 10:15:00.951045: step: 1552/530, loss: 0.07086333632469177
2023-01-21 10:15:02.114165: step: 1556/530, loss: 0.006249618250876665
2023-01-21 10:15:03.302453: step: 1560/530, loss: 0.0755847916007042
2023-01-21 10:15:04.473510: step: 1564/530, loss: 0.1146155372262001
2023-01-21 10:15:05.671086: step: 1568/530, loss: 0.10537935048341751
2023-01-21 10:15:06.831118: step: 1572/530, loss: 0.1913030594587326
2023-01-21 10:15:08.028527: step: 1576/530, loss: 0.11692734062671661
2023-01-21 10:15:09.203374: step: 1580/530, loss: 0.014831018634140491
2023-01-21 10:15:10.368433: step: 1584/530, loss: 0.008850526995956898
2023-01-21 10:15:11.532557: step: 1588/530, loss: 0.03558092191815376
2023-01-21 10:15:12.725848: step: 1592/530, loss: 0.16514739394187927
2023-01-21 10:15:13.861870: step: 1596/530, loss: 0.008432770147919655
2023-01-21 10:15:15.001978: step: 1600/530, loss: 0.05681314319372177
2023-01-21 10:15:16.189909: step: 1604/530, loss: 0.04270324856042862
2023-01-21 10:15:17.389681: step: 1608/530, loss: 0.08593006432056427
2023-01-21 10:15:18.599307: step: 1612/530, loss: 0.08044710755348206
2023-01-21 10:15:19.825608: step: 1616/530, loss: 0.05296144634485245
2023-01-21 10:15:20.959468: step: 1620/530, loss: 0.05182352289557457
2023-01-21 10:15:22.192972: step: 1624/530, loss: 0.06678536534309387
2023-01-21 10:15:23.359184: step: 1628/530, loss: 0.061350204050540924
2023-01-21 10:15:24.543292: step: 1632/530, loss: 0.08674897998571396
2023-01-21 10:15:25.790236: step: 1636/530, loss: 0.41009101271629333
2023-01-21 10:15:27.012354: step: 1640/530, loss: 0.10833082348108292
2023-01-21 10:15:28.208155: step: 1644/530, loss: 0.02701597288250923
2023-01-21 10:15:29.380114: step: 1648/530, loss: 0.11499843746423721
2023-01-21 10:15:30.593386: step: 1652/530, loss: 0.021666662767529488
2023-01-21 10:15:31.783588: step: 1656/530, loss: 0.06022052839398384
2023-01-21 10:15:32.960308: step: 1660/530, loss: 0.05260324478149414
2023-01-21 10:15:34.146009: step: 1664/530, loss: 0.028481770306825638
2023-01-21 10:15:35.378392: step: 1668/530, loss: 0.026079367846250534
2023-01-21 10:15:36.559539: step: 1672/530, loss: 0.028040314093232155
2023-01-21 10:15:37.744536: step: 1676/530, loss: 0.038277626037597656
2023-01-21 10:15:38.920643: step: 1680/530, loss: 0.087426096200943
2023-01-21 10:15:40.120620: step: 1684/530, loss: 0.04134349897503853
2023-01-21 10:15:41.334206: step: 1688/530, loss: 0.05519428104162216
2023-01-21 10:15:42.538166: step: 1692/530, loss: 0.033372119069099426
2023-01-21 10:15:43.729579: step: 1696/530, loss: 0.3449346423149109
2023-01-21 10:15:44.882117: step: 1700/530, loss: 0.08747806400060654
2023-01-21 10:15:46.060274: step: 1704/530, loss: 0.25175362825393677
2023-01-21 10:15:47.249113: step: 1708/530, loss: 0.04997234418988228
2023-01-21 10:15:48.413435: step: 1712/530, loss: 0.04796609655022621
2023-01-21 10:15:49.612839: step: 1716/530, loss: 0.016085529699921608
2023-01-21 10:15:50.759311: step: 1720/530, loss: 0.0825173407793045
2023-01-21 10:15:51.937100: step: 1724/530, loss: 0.04569091647863388
2023-01-21 10:15:53.171299: step: 1728/530, loss: 0.24064083397388458
2023-01-21 10:15:54.341156: step: 1732/530, loss: 0.0712437629699707
2023-01-21 10:15:55.493801: step: 1736/530, loss: 0.04602022469043732
2023-01-21 10:15:56.679636: step: 1740/530, loss: 0.0920473113656044
2023-01-21 10:15:57.869296: step: 1744/530, loss: 0.05632515251636505
2023-01-21 10:15:59.042480: step: 1748/530, loss: 0.13201884925365448
2023-01-21 10:16:00.245743: step: 1752/530, loss: 0.03179903328418732
2023-01-21 10:16:01.427128: step: 1756/530, loss: 0.04840269312262535
2023-01-21 10:16:02.643184: step: 1760/530, loss: 0.03660087659955025
2023-01-21 10:16:03.824580: step: 1764/530, loss: 0.04072270542383194
2023-01-21 10:16:04.986598: step: 1768/530, loss: 0.07305145263671875
2023-01-21 10:16:06.164631: step: 1772/530, loss: 0.04337292164564133
2023-01-21 10:16:07.348109: step: 1776/530, loss: 0.1968904435634613
2023-01-21 10:16:08.566484: step: 1780/530, loss: 0.0230241771787405
2023-01-21 10:16:09.799782: step: 1784/530, loss: 0.06974849849939346
2023-01-21 10:16:10.980667: step: 1788/530, loss: 0.05908184498548508
2023-01-21 10:16:12.154512: step: 1792/530, loss: 0.36147913336753845
2023-01-21 10:16:13.385468: step: 1796/530, loss: 0.0768955796957016
2023-01-21 10:16:14.557716: step: 1800/530, loss: 0.06698283553123474
2023-01-21 10:16:15.752055: step: 1804/530, loss: 0.6433885097503662
2023-01-21 10:16:16.918195: step: 1808/530, loss: 0.10862883925437927
2023-01-21 10:16:18.111219: step: 1812/530, loss: 0.06186265870928764
2023-01-21 10:16:19.297418: step: 1816/530, loss: 0.16273097693920135
2023-01-21 10:16:20.494664: step: 1820/530, loss: 0.04408147558569908
2023-01-21 10:16:21.744190: step: 1824/530, loss: 0.025667190551757812
2023-01-21 10:16:22.883144: step: 1828/530, loss: 0.02391096204519272
2023-01-21 10:16:24.121364: step: 1832/530, loss: 0.07087206840515137
2023-01-21 10:16:25.297443: step: 1836/530, loss: 0.0404149554669857
2023-01-21 10:16:26.476359: step: 1840/530, loss: 0.02362379990518093
2023-01-21 10:16:27.679355: step: 1844/530, loss: 0.02720470353960991
2023-01-21 10:16:28.838434: step: 1848/530, loss: 0.02001953125
2023-01-21 10:16:30.019341: step: 1852/530, loss: 0.12756028771400452
2023-01-21 10:16:31.198363: step: 1856/530, loss: 0.006270814221352339
2023-01-21 10:16:32.374786: step: 1860/530, loss: 0.06130991131067276
2023-01-21 10:16:33.610948: step: 1864/530, loss: 0.013648796826601028
2023-01-21 10:16:34.813565: step: 1868/530, loss: 0.047820866107940674
2023-01-21 10:16:36.002951: step: 1872/530, loss: 0.06345033645629883
2023-01-21 10:16:37.200204: step: 1876/530, loss: 0.13459205627441406
2023-01-21 10:16:38.388940: step: 1880/530, loss: 0.034517861902713776
2023-01-21 10:16:39.549610: step: 1884/530, loss: 0.148609921336174
2023-01-21 10:16:40.761463: step: 1888/530, loss: 0.0062687876634299755
2023-01-21 10:16:41.930285: step: 1892/530, loss: 0.10174808651208878
2023-01-21 10:16:43.113909: step: 1896/530, loss: 0.18933601677417755
2023-01-21 10:16:44.263042: step: 1900/530, loss: 0.04540596157312393
2023-01-21 10:16:45.459739: step: 1904/530, loss: 0.11992726475000381
2023-01-21 10:16:46.639950: step: 1908/530, loss: 0.06002183258533478
2023-01-21 10:16:47.836252: step: 1912/530, loss: 0.11655215919017792
2023-01-21 10:16:49.085630: step: 1916/530, loss: 0.027437781915068626
2023-01-21 10:16:50.282079: step: 1920/530, loss: 0.38339102268218994
2023-01-21 10:16:51.488906: step: 1924/530, loss: 0.040841199457645416
2023-01-21 10:16:52.665147: step: 1928/530, loss: 0.16949692368507385
2023-01-21 10:16:53.816639: step: 1932/530, loss: 0.014570236206054688
2023-01-21 10:16:55.006206: step: 1936/530, loss: 0.14264750480651855
2023-01-21 10:16:56.191502: step: 1940/530, loss: 0.17664670944213867
2023-01-21 10:16:57.330624: step: 1944/530, loss: 0.04278526455163956
2023-01-21 10:16:58.482392: step: 1948/530, loss: 0.020009517669677734
2023-01-21 10:16:59.658780: step: 1952/530, loss: 0.11989088356494904
2023-01-21 10:17:00.855472: step: 1956/530, loss: 0.22997474670410156
2023-01-21 10:17:02.020097: step: 1960/530, loss: 0.003576564835384488
2023-01-21 10:17:03.229514: step: 1964/530, loss: 0.0026226998306810856
2023-01-21 10:17:04.471315: step: 1968/530, loss: 0.1358516663312912
2023-01-21 10:17:05.742230: step: 1972/530, loss: 0.0023416520562022924
2023-01-21 10:17:06.913953: step: 1976/530, loss: 0.05554056167602539
2023-01-21 10:17:08.056704: step: 1980/530, loss: 0.0629308745265007
2023-01-21 10:17:09.274145: step: 1984/530, loss: 0.038582898676395416
2023-01-21 10:17:10.428614: step: 1988/530, loss: 0.04458275064826012
2023-01-21 10:17:11.609761: step: 1992/530, loss: 0.07219496369361877
2023-01-21 10:17:12.816469: step: 1996/530, loss: 0.0581677183508873
2023-01-21 10:17:14.012772: step: 2000/530, loss: 0.057827189564704895
2023-01-21 10:17:15.173411: step: 2004/530, loss: 0.05950207635760307
2023-01-21 10:17:16.319899: step: 2008/530, loss: 0.07835781574249268
2023-01-21 10:17:17.493445: step: 2012/530, loss: 0.35049229860305786
2023-01-21 10:17:18.670140: step: 2016/530, loss: 0.24317531287670135
2023-01-21 10:17:19.874612: step: 2020/530, loss: 0.04514484480023384
2023-01-21 10:17:21.077549: step: 2024/530, loss: 0.10570144653320312
2023-01-21 10:17:22.258596: step: 2028/530, loss: 0.08636656403541565
2023-01-21 10:17:23.424918: step: 2032/530, loss: 0.18950310349464417
2023-01-21 10:17:24.615531: step: 2036/530, loss: 0.5444737076759338
2023-01-21 10:17:25.780554: step: 2040/530, loss: 0.06467919051647186
2023-01-21 10:17:26.948900: step: 2044/530, loss: 0.011122465133666992
2023-01-21 10:17:28.107212: step: 2048/530, loss: 0.05856190249323845
2023-01-21 10:17:29.296320: step: 2052/530, loss: 0.030113743618130684
2023-01-21 10:17:30.427580: step: 2056/530, loss: 0.09080362319946289
2023-01-21 10:17:31.610665: step: 2060/530, loss: 0.03609485551714897
2023-01-21 10:17:32.776881: step: 2064/530, loss: 0.07069520652294159
2023-01-21 10:17:33.948521: step: 2068/530, loss: 0.10094308853149414
2023-01-21 10:17:35.108559: step: 2072/530, loss: 0.052832603454589844
2023-01-21 10:17:36.250705: step: 2076/530, loss: 0.07048521190881729
2023-01-21 10:17:37.408234: step: 2080/530, loss: 0.03262443467974663
2023-01-21 10:17:38.611711: step: 2084/530, loss: 0.10793952643871307
2023-01-21 10:17:39.778547: step: 2088/530, loss: 0.027028562501072884
2023-01-21 10:17:40.952393: step: 2092/530, loss: 0.04333266615867615
2023-01-21 10:17:42.139708: step: 2096/530, loss: 0.47791871428489685
2023-01-21 10:17:43.365547: step: 2100/530, loss: 0.023774243891239166
2023-01-21 10:17:44.495049: step: 2104/530, loss: 0.11566973477602005
2023-01-21 10:17:45.638008: step: 2108/530, loss: 0.14222422242164612
2023-01-21 10:17:46.810762: step: 2112/530, loss: 0.2880805432796478
2023-01-21 10:17:48.005409: step: 2116/530, loss: 0.01856517791748047
2023-01-21 10:17:49.161911: step: 2120/530, loss: 0.008118415251374245
==================================================
Loss: 0.108
--------------------
Dev: {'event': {'p': 0.5834186284544524, 'r': 0.758988015978695, 'f1': 0.6597222222222223}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.623550401427297, 'r': 0.8039102932719954, 'f1': 0.7023360964581763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5930232558139535, 'r': 0.9444444444444444, 'f1': 0.7285714285714286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6060606060606061, 'r': 0.6349206349206349, 'f1': 0.62015503875969}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:18:34.647884: step: 4/530, loss: 0.01724863052368164
2023-01-21 10:18:35.817803: step: 8/530, loss: 0.02831430360674858
2023-01-21 10:18:37.010205: step: 12/530, loss: 0.12746620178222656
2023-01-21 10:18:38.208184: step: 16/530, loss: 0.1962868869304657
2023-01-21 10:18:39.386710: step: 20/530, loss: 0.05674343183636665
2023-01-21 10:18:40.633607: step: 24/530, loss: 0.03981733322143555
2023-01-21 10:18:41.828531: step: 28/530, loss: 0.04937954246997833
2023-01-21 10:18:43.032932: step: 32/530, loss: 0.008655572310090065
2023-01-21 10:18:44.216913: step: 36/530, loss: 0.2705986201763153
2023-01-21 10:18:45.343048: step: 40/530, loss: 0.013779735192656517
2023-01-21 10:18:46.490055: step: 44/530, loss: 0.03335609659552574
2023-01-21 10:18:47.620998: step: 48/530, loss: 0.10728330165147781
2023-01-21 10:18:48.782842: step: 52/530, loss: 0.01455383375287056
2023-01-21 10:18:49.969947: step: 56/530, loss: 0.007962417788803577
2023-01-21 10:18:51.162502: step: 60/530, loss: 0.018001843243837357
2023-01-21 10:18:52.378237: step: 64/530, loss: 0.050893403589725494
2023-01-21 10:18:53.535382: step: 68/530, loss: 0.020572280511260033
2023-01-21 10:18:54.708480: step: 72/530, loss: 0.06465578079223633
2023-01-21 10:18:55.896699: step: 76/530, loss: 0.592059314250946
2023-01-21 10:18:57.067159: step: 80/530, loss: 0.002903556916862726
2023-01-21 10:18:58.262007: step: 84/530, loss: 0.07494659721851349
2023-01-21 10:18:59.435133: step: 88/530, loss: 0.008433056063950062
2023-01-21 10:19:00.621694: step: 92/530, loss: 0.05218029022216797
2023-01-21 10:19:01.793971: step: 96/530, loss: 0.0011052608024328947
2023-01-21 10:19:02.996060: step: 100/530, loss: 0.0492280051112175
2023-01-21 10:19:04.196880: step: 104/530, loss: 0.08444013446569443
2023-01-21 10:19:05.390186: step: 108/530, loss: 0.015472030267119408
2023-01-21 10:19:06.542198: step: 112/530, loss: 0.006947898771613836
2023-01-21 10:19:07.735004: step: 116/530, loss: 0.07498826831579208
2023-01-21 10:19:08.917903: step: 120/530, loss: 0.03549976274371147
2023-01-21 10:19:10.090346: step: 124/530, loss: 0.0013807297218590975
2023-01-21 10:19:11.248841: step: 128/530, loss: 0.05237922817468643
2023-01-21 10:19:12.430798: step: 132/530, loss: 0.20397034287452698
2023-01-21 10:19:13.579007: step: 136/530, loss: 0.042256928980350494
2023-01-21 10:19:14.754558: step: 140/530, loss: 0.05582446977496147
2023-01-21 10:19:15.976859: step: 144/530, loss: 0.4282020032405853
2023-01-21 10:19:17.128378: step: 148/530, loss: 0.010433197021484375
2023-01-21 10:19:18.319101: step: 152/530, loss: 0.20721034705638885
2023-01-21 10:19:19.488146: step: 156/530, loss: 0.08617058396339417
2023-01-21 10:19:20.641242: step: 160/530, loss: 0.004367637448012829
2023-01-21 10:19:21.832572: step: 164/530, loss: 0.1405675858259201
2023-01-21 10:19:22.976491: step: 168/530, loss: 0.0006777763483114541
2023-01-21 10:19:24.159306: step: 172/530, loss: 0.042293451726436615
2023-01-21 10:19:25.319026: step: 176/530, loss: 0.07939940690994263
2023-01-21 10:19:26.506439: step: 180/530, loss: 0.017889689654111862
2023-01-21 10:19:27.707181: step: 184/530, loss: 0.01557769812643528
2023-01-21 10:19:28.847446: step: 188/530, loss: 0.025629043579101562
2023-01-21 10:19:30.001165: step: 192/530, loss: 0.017916537821292877
2023-01-21 10:19:31.158694: step: 196/530, loss: 0.06513328850269318
2023-01-21 10:19:32.357546: step: 200/530, loss: 0.09142618626356125
2023-01-21 10:19:33.540548: step: 204/530, loss: 0.02312469482421875
2023-01-21 10:19:34.699248: step: 208/530, loss: 0.002872276119887829
2023-01-21 10:19:35.895309: step: 212/530, loss: 0.10064974427223206
2023-01-21 10:19:37.053407: step: 216/530, loss: 0.07517509162425995
2023-01-21 10:19:38.259321: step: 220/530, loss: 0.016412019729614258
2023-01-21 10:19:39.422022: step: 224/530, loss: 0.01306695956736803
2023-01-21 10:19:40.610439: step: 228/530, loss: 0.03495984151959419
2023-01-21 10:19:41.753995: step: 232/530, loss: 0.007014179136604071
2023-01-21 10:19:42.923783: step: 236/530, loss: 0.04804863780736923
2023-01-21 10:19:44.125772: step: 240/530, loss: 0.17407149076461792
2023-01-21 10:19:45.270743: step: 244/530, loss: 0.033547498285770416
2023-01-21 10:19:46.392601: step: 248/530, loss: 0.1131671890616417
2023-01-21 10:19:47.590274: step: 252/530, loss: 0.040595244616270065
2023-01-21 10:19:48.799641: step: 256/530, loss: 0.06128682941198349
2023-01-21 10:19:49.995286: step: 260/530, loss: 0.3505368232727051
2023-01-21 10:19:51.200563: step: 264/530, loss: 0.01635713502764702
2023-01-21 10:19:52.377639: step: 268/530, loss: 0.1656968593597412
2023-01-21 10:19:53.513333: step: 272/530, loss: 0.005596351809799671
2023-01-21 10:19:54.707289: step: 276/530, loss: 0.021594811230897903
2023-01-21 10:19:55.839858: step: 280/530, loss: 0.02822094038128853
2023-01-21 10:19:56.977420: step: 284/530, loss: 0.06556282192468643
2023-01-21 10:19:58.142963: step: 288/530, loss: 0.1060771495103836
2023-01-21 10:19:59.309213: step: 292/530, loss: 0.09458567947149277
2023-01-21 10:20:00.531111: step: 296/530, loss: 0.09363172948360443
2023-01-21 10:20:01.764998: step: 300/530, loss: 0.05049190670251846
2023-01-21 10:20:02.929987: step: 304/530, loss: 0.02804236300289631
2023-01-21 10:20:04.087126: step: 308/530, loss: 0.15031220018863678
2023-01-21 10:20:05.253457: step: 312/530, loss: 0.039809297770261765
2023-01-21 10:20:06.439683: step: 316/530, loss: 0.04465942457318306
2023-01-21 10:20:07.630851: step: 320/530, loss: 0.007391166873276234
2023-01-21 10:20:08.835582: step: 324/530, loss: 0.07422886043787003
2023-01-21 10:20:09.987334: step: 328/530, loss: 0.07546120136976242
2023-01-21 10:20:11.153027: step: 332/530, loss: 0.07228565216064453
2023-01-21 10:20:12.305994: step: 336/530, loss: 0.026609230786561966
2023-01-21 10:20:13.491603: step: 340/530, loss: 0.04048290103673935
2023-01-21 10:20:14.685709: step: 344/530, loss: 0.19356565177440643
2023-01-21 10:20:15.886220: step: 348/530, loss: 0.057354070246219635
2023-01-21 10:20:17.049845: step: 352/530, loss: 0.05328512564301491
2023-01-21 10:20:18.246216: step: 356/530, loss: 0.08446156978607178
2023-01-21 10:20:19.450762: step: 360/530, loss: 0.11063873767852783
2023-01-21 10:20:20.619754: step: 364/530, loss: 0.053235720843076706
2023-01-21 10:20:21.780521: step: 368/530, loss: 0.03223447874188423
2023-01-21 10:20:23.000345: step: 372/530, loss: 0.29909753799438477
2023-01-21 10:20:24.193980: step: 376/530, loss: 0.04627084359526634
2023-01-21 10:20:25.361830: step: 380/530, loss: 0.10767688602209091
2023-01-21 10:20:26.536457: step: 384/530, loss: 0.00654982915148139
2023-01-21 10:20:27.695994: step: 388/530, loss: 0.028128528967499733
2023-01-21 10:20:28.893086: step: 392/530, loss: 0.06355457007884979
2023-01-21 10:20:30.149554: step: 396/530, loss: 0.13125677406787872
2023-01-21 10:20:31.335764: step: 400/530, loss: 0.0123145105317235
2023-01-21 10:20:32.546252: step: 404/530, loss: 0.11665716022253036
2023-01-21 10:20:33.720528: step: 408/530, loss: 0.05518064275383949
2023-01-21 10:20:34.849152: step: 412/530, loss: 0.09190237522125244
2023-01-21 10:20:36.052021: step: 416/530, loss: 0.09520454704761505
2023-01-21 10:20:37.212411: step: 420/530, loss: 0.04104652628302574
2023-01-21 10:20:38.460221: step: 424/530, loss: 0.10428936779499054
2023-01-21 10:20:39.664635: step: 428/530, loss: 0.014971543103456497
2023-01-21 10:20:40.831372: step: 432/530, loss: 0.0654086172580719
2023-01-21 10:20:42.001294: step: 436/530, loss: 0.05611314997076988
2023-01-21 10:20:43.166029: step: 440/530, loss: 0.03765372931957245
2023-01-21 10:20:44.333424: step: 444/530, loss: 0.013609791174530983
2023-01-21 10:20:45.493125: step: 448/530, loss: 0.012603759765625
2023-01-21 10:20:46.667976: step: 452/530, loss: 0.010480445809662342
2023-01-21 10:20:47.882611: step: 456/530, loss: 0.02486448362469673
2023-01-21 10:20:49.033319: step: 460/530, loss: 0.04601473733782768
2023-01-21 10:20:50.186833: step: 464/530, loss: 0.005935740657150745
2023-01-21 10:20:51.386761: step: 468/530, loss: 0.06262693554162979
2023-01-21 10:20:52.587399: step: 472/530, loss: 0.06066951900720596
2023-01-21 10:20:53.787449: step: 476/530, loss: 0.108167365193367
2023-01-21 10:20:54.942788: step: 480/530, loss: 0.013270283117890358
2023-01-21 10:20:56.125626: step: 484/530, loss: 0.08028535544872284
2023-01-21 10:20:57.323087: step: 488/530, loss: 0.010606765747070312
2023-01-21 10:20:58.478533: step: 492/530, loss: 0.029518771916627884
2023-01-21 10:20:59.659747: step: 496/530, loss: 0.020072175189852715
2023-01-21 10:21:00.833656: step: 500/530, loss: 0.028275348246097565
2023-01-21 10:21:01.996278: step: 504/530, loss: 0.011164498515427113
2023-01-21 10:21:03.219080: step: 508/530, loss: 0.18622688949108124
2023-01-21 10:21:04.409888: step: 512/530, loss: 0.07147254794836044
2023-01-21 10:21:05.578473: step: 516/530, loss: 0.040113065391778946
2023-01-21 10:21:06.758166: step: 520/530, loss: 0.07017207145690918
2023-01-21 10:21:07.918425: step: 524/530, loss: 0.12066469341516495
2023-01-21 10:21:09.144164: step: 528/530, loss: 0.1344621479511261
2023-01-21 10:21:10.374804: step: 532/530, loss: 0.13251782953739166
2023-01-21 10:21:11.569889: step: 536/530, loss: 0.033727504312992096
2023-01-21 10:21:12.745161: step: 540/530, loss: 0.011449622921645641
2023-01-21 10:21:13.948222: step: 544/530, loss: 0.056689146906137466
2023-01-21 10:21:15.086493: step: 548/530, loss: 0.03570260852575302
2023-01-21 10:21:16.240792: step: 552/530, loss: 0.12402161955833435
2023-01-21 10:21:17.462471: step: 556/530, loss: 0.04676799848675728
2023-01-21 10:21:18.632891: step: 560/530, loss: 0.04755821079015732
2023-01-21 10:21:19.821292: step: 564/530, loss: 0.05337581783533096
2023-01-21 10:21:20.987889: step: 568/530, loss: 0.14718575775623322
2023-01-21 10:21:22.178010: step: 572/530, loss: 0.12984544038772583
2023-01-21 10:21:23.382550: step: 576/530, loss: 0.033028747886419296
2023-01-21 10:21:24.548874: step: 580/530, loss: 0.06339607387781143
2023-01-21 10:21:25.731001: step: 584/530, loss: 0.0584142692387104
2023-01-21 10:21:26.947463: step: 588/530, loss: 0.03812151029706001
2023-01-21 10:21:28.132736: step: 592/530, loss: 0.19748754799365997
2023-01-21 10:21:29.304755: step: 596/530, loss: 0.025906803086400032
2023-01-21 10:21:30.488433: step: 600/530, loss: 0.023184681311249733
2023-01-21 10:21:31.673547: step: 604/530, loss: 0.06471939384937286
2023-01-21 10:21:32.823281: step: 608/530, loss: 0.22061358392238617
2023-01-21 10:21:33.980572: step: 612/530, loss: 0.04676113277673721
2023-01-21 10:21:35.180706: step: 616/530, loss: 0.008520555682480335
2023-01-21 10:21:36.382131: step: 620/530, loss: 0.12434607744216919
2023-01-21 10:21:37.540900: step: 624/530, loss: 0.012760735116899014
2023-01-21 10:21:38.780825: step: 628/530, loss: 0.013706875964999199
2023-01-21 10:21:39.965853: step: 632/530, loss: 0.008645439520478249
2023-01-21 10:21:41.150365: step: 636/530, loss: 0.06543731689453125
2023-01-21 10:21:42.355789: step: 640/530, loss: 0.03377361595630646
2023-01-21 10:21:43.602436: step: 644/530, loss: 0.04126129299402237
2023-01-21 10:21:44.782963: step: 648/530, loss: 0.13894999027252197
2023-01-21 10:21:45.958899: step: 652/530, loss: 0.04044799879193306
2023-01-21 10:21:47.160510: step: 656/530, loss: 0.0208453182131052
2023-01-21 10:21:48.366006: step: 660/530, loss: 0.1356370896100998
2023-01-21 10:21:49.526122: step: 664/530, loss: 0.05513763427734375
2023-01-21 10:21:50.733449: step: 668/530, loss: 0.1295255720615387
2023-01-21 10:21:51.900512: step: 672/530, loss: 0.06747493892908096
2023-01-21 10:21:53.078349: step: 676/530, loss: 0.020699406042695045
2023-01-21 10:21:54.253951: step: 680/530, loss: 0.05589151382446289
2023-01-21 10:21:55.441638: step: 684/530, loss: 0.027169611304998398
2023-01-21 10:21:56.662369: step: 688/530, loss: 0.07688884437084198
2023-01-21 10:21:57.848193: step: 692/530, loss: 0.05237884446978569
2023-01-21 10:21:59.004733: step: 696/530, loss: 0.04485531151294708
2023-01-21 10:22:00.182841: step: 700/530, loss: 0.052571870386600494
2023-01-21 10:22:01.368668: step: 704/530, loss: 0.035965196788311005
2023-01-21 10:22:02.516934: step: 708/530, loss: 0.024704838171601295
2023-01-21 10:22:03.665833: step: 712/530, loss: 0.11405421048402786
2023-01-21 10:22:04.864692: step: 716/530, loss: 0.023207854479551315
2023-01-21 10:22:06.047297: step: 720/530, loss: 0.0046422481536865234
2023-01-21 10:22:07.285722: step: 724/530, loss: 0.09927954524755478
2023-01-21 10:22:08.450958: step: 728/530, loss: 0.16773834824562073
2023-01-21 10:22:09.607694: step: 732/530, loss: 0.08033790439367294
2023-01-21 10:22:10.805829: step: 736/530, loss: 0.11824969947338104
2023-01-21 10:22:11.966963: step: 740/530, loss: 0.0571625679731369
2023-01-21 10:22:13.135633: step: 744/530, loss: 0.1755337119102478
2023-01-21 10:22:14.351361: step: 748/530, loss: 0.22712059319019318
2023-01-21 10:22:15.575681: step: 752/530, loss: 0.07328605651855469
2023-01-21 10:22:16.749211: step: 756/530, loss: 0.0854150801897049
2023-01-21 10:22:17.919426: step: 760/530, loss: 0.04586320370435715
2023-01-21 10:22:19.174592: step: 764/530, loss: 0.08389168232679367
2023-01-21 10:22:20.421817: step: 768/530, loss: 0.06492657959461212
2023-01-21 10:22:21.633792: step: 772/530, loss: 0.11090469360351562
2023-01-21 10:22:22.848441: step: 776/530, loss: 0.0945672020316124
2023-01-21 10:22:24.062069: step: 780/530, loss: 0.033510398119688034
2023-01-21 10:22:25.228303: step: 784/530, loss: 0.032225608825683594
2023-01-21 10:22:26.394019: step: 788/530, loss: 0.08912887424230576
2023-01-21 10:22:27.569519: step: 792/530, loss: 0.012789726257324219
2023-01-21 10:22:28.780659: step: 796/530, loss: 0.056162264198064804
2023-01-21 10:22:29.938699: step: 800/530, loss: 0.06724796444177628
2023-01-21 10:22:31.104195: step: 804/530, loss: 0.07631473243236542
2023-01-21 10:22:32.246550: step: 808/530, loss: 0.06719360500574112
2023-01-21 10:22:33.401730: step: 812/530, loss: 0.006159019656479359
2023-01-21 10:22:34.580865: step: 816/530, loss: 0.5959426164627075
2023-01-21 10:22:35.784506: step: 820/530, loss: 0.0058693294413387775
2023-01-21 10:22:36.980198: step: 824/530, loss: 0.5219763517379761
2023-01-21 10:22:38.191078: step: 828/530, loss: 0.1250920295715332
2023-01-21 10:22:39.359928: step: 832/530, loss: 0.2410951554775238
2023-01-21 10:22:40.568052: step: 836/530, loss: 0.12463503330945969
2023-01-21 10:22:41.745539: step: 840/530, loss: 0.0956411361694336
2023-01-21 10:22:42.967657: step: 844/530, loss: 0.04549875482916832
2023-01-21 10:22:44.184413: step: 848/530, loss: 0.004123210906982422
2023-01-21 10:22:45.360375: step: 852/530, loss: 0.03239774703979492
2023-01-21 10:22:46.526292: step: 856/530, loss: 0.010679817758500576
2023-01-21 10:22:47.671541: step: 860/530, loss: 0.07902240753173828
2023-01-21 10:22:48.858594: step: 864/530, loss: 0.039153192192316055
2023-01-21 10:22:50.021963: step: 868/530, loss: 0.047776032239198685
2023-01-21 10:22:51.174799: step: 872/530, loss: 0.202616885304451
2023-01-21 10:22:52.306804: step: 876/530, loss: 0.04760284349322319
2023-01-21 10:22:53.483702: step: 880/530, loss: 0.05202331766486168
2023-01-21 10:22:54.717003: step: 884/530, loss: 0.06067085266113281
2023-01-21 10:22:55.880851: step: 888/530, loss: 0.03496084362268448
2023-01-21 10:22:57.089962: step: 892/530, loss: 0.2139906883239746
2023-01-21 10:22:58.247344: step: 896/530, loss: 0.04800615459680557
2023-01-21 10:22:59.467373: step: 900/530, loss: 0.10639762878417969
2023-01-21 10:23:00.639283: step: 904/530, loss: 1.106414794921875
2023-01-21 10:23:01.862988: step: 908/530, loss: 0.020794104784727097
2023-01-21 10:23:03.041256: step: 912/530, loss: 0.00787506066262722
2023-01-21 10:23:04.212496: step: 916/530, loss: 0.032620809972286224
2023-01-21 10:23:05.403929: step: 920/530, loss: 0.11377029120922089
2023-01-21 10:23:06.577566: step: 924/530, loss: 0.054822731763124466
2023-01-21 10:23:07.770121: step: 928/530, loss: 0.08924436569213867
2023-01-21 10:23:08.970417: step: 932/530, loss: 0.04892902448773384
2023-01-21 10:23:10.123383: step: 936/530, loss: 0.01841592788696289
2023-01-21 10:23:11.284130: step: 940/530, loss: 0.03619947284460068
2023-01-21 10:23:12.495252: step: 944/530, loss: 0.035985372960567474
2023-01-21 10:23:13.663836: step: 948/530, loss: 0.09846987575292587
2023-01-21 10:23:14.867732: step: 952/530, loss: 0.07159604877233505
2023-01-21 10:23:16.021718: step: 956/530, loss: 0.05185890197753906
2023-01-21 10:23:17.192619: step: 960/530, loss: 0.026017475873231888
2023-01-21 10:23:18.388065: step: 964/530, loss: 0.05558224022388458
2023-01-21 10:23:19.556492: step: 968/530, loss: 0.02276439592242241
2023-01-21 10:23:20.765234: step: 972/530, loss: 0.0960446447134018
2023-01-21 10:23:21.949819: step: 976/530, loss: 0.2156790792942047
2023-01-21 10:23:23.183623: step: 980/530, loss: 0.0681055560708046
2023-01-21 10:23:24.354386: step: 984/530, loss: 0.003368377685546875
2023-01-21 10:23:25.514916: step: 988/530, loss: 0.1347332000732422
2023-01-21 10:23:26.685879: step: 992/530, loss: 0.05170693248510361
2023-01-21 10:23:27.848711: step: 996/530, loss: 0.07851582020521164
2023-01-21 10:23:29.054583: step: 1000/530, loss: 0.04718971252441406
2023-01-21 10:23:30.232102: step: 1004/530, loss: 0.003913402557373047
2023-01-21 10:23:31.416501: step: 1008/530, loss: 0.04754600673913956
2023-01-21 10:23:32.613870: step: 1012/530, loss: 0.20470334589481354
2023-01-21 10:23:33.806201: step: 1016/530, loss: 0.07396507263183594
2023-01-21 10:23:35.011872: step: 1020/530, loss: 0.06888275593519211
2023-01-21 10:23:36.245441: step: 1024/530, loss: 0.09839210659265518
2023-01-21 10:23:37.499905: step: 1028/530, loss: 0.09046640247106552
2023-01-21 10:23:38.677128: step: 1032/530, loss: 0.15365830063819885
2023-01-21 10:23:39.828035: step: 1036/530, loss: 0.08798447251319885
2023-01-21 10:23:41.003688: step: 1040/530, loss: 0.13328266143798828
2023-01-21 10:23:42.209567: step: 1044/530, loss: 0.030314160510897636
2023-01-21 10:23:43.381531: step: 1048/530, loss: 0.19902487099170685
2023-01-21 10:23:44.550550: step: 1052/530, loss: 0.30601128935813904
2023-01-21 10:23:45.711008: step: 1056/530, loss: 0.05362368002533913
2023-01-21 10:23:46.854561: step: 1060/530, loss: 0.024675512686371803
2023-01-21 10:23:48.035137: step: 1064/530, loss: 0.047141171991825104
2023-01-21 10:23:49.222192: step: 1068/530, loss: 0.1619092971086502
2023-01-21 10:23:50.405465: step: 1072/530, loss: 0.0459468849003315
2023-01-21 10:23:51.585649: step: 1076/530, loss: 0.014123057946562767
2023-01-21 10:23:52.769491: step: 1080/530, loss: 0.09126348793506622
2023-01-21 10:23:53.968290: step: 1084/530, loss: 0.06287689507007599
2023-01-21 10:23:55.120379: step: 1088/530, loss: 0.03245840221643448
2023-01-21 10:23:56.321065: step: 1092/530, loss: 0.06365213543176651
2023-01-21 10:23:57.450648: step: 1096/530, loss: 0.0748106986284256
2023-01-21 10:23:58.628908: step: 1100/530, loss: 0.0904294103384018
2023-01-21 10:23:59.803647: step: 1104/530, loss: 0.04335784912109375
2023-01-21 10:24:01.007115: step: 1108/530, loss: 0.04181699827313423
2023-01-21 10:24:02.211470: step: 1112/530, loss: 0.01370248757302761
2023-01-21 10:24:03.401174: step: 1116/530, loss: 0.09755287319421768
2023-01-21 10:24:04.566610: step: 1120/530, loss: 0.08494433760643005
2023-01-21 10:24:05.730912: step: 1124/530, loss: 0.07433262467384338
2023-01-21 10:24:06.916675: step: 1128/530, loss: 0.05076246336102486
2023-01-21 10:24:08.101097: step: 1132/530, loss: 0.36004361510276794
2023-01-21 10:24:09.323043: step: 1136/530, loss: 0.08949871361255646
2023-01-21 10:24:10.526559: step: 1140/530, loss: 0.05878668278455734
2023-01-21 10:24:11.723697: step: 1144/530, loss: 0.19234934449195862
2023-01-21 10:24:12.893975: step: 1148/530, loss: 0.09683246910572052
2023-01-21 10:24:14.099331: step: 1152/530, loss: 0.045394137501716614
2023-01-21 10:24:15.273737: step: 1156/530, loss: 2.4003026485443115
2023-01-21 10:24:16.479661: step: 1160/530, loss: 0.12414245307445526
2023-01-21 10:24:17.640127: step: 1164/530, loss: 0.16744832694530487
2023-01-21 10:24:18.828987: step: 1168/530, loss: 0.02402791939675808
2023-01-21 10:24:20.045231: step: 1172/530, loss: 0.05656109005212784
2023-01-21 10:24:21.235918: step: 1176/530, loss: 0.815133810043335
2023-01-21 10:24:22.503295: step: 1180/530, loss: 0.047041893005371094
2023-01-21 10:24:23.698756: step: 1184/530, loss: 0.18938890099525452
2023-01-21 10:24:24.852965: step: 1188/530, loss: 0.034436848014593124
2023-01-21 10:24:26.025301: step: 1192/530, loss: 0.029060842469334602
2023-01-21 10:24:27.220920: step: 1196/530, loss: 0.1083468422293663
2023-01-21 10:24:28.383720: step: 1200/530, loss: 0.057347677648067474
2023-01-21 10:24:29.597814: step: 1204/530, loss: 0.10239878296852112
2023-01-21 10:24:30.764294: step: 1208/530, loss: 0.051899053156375885
2023-01-21 10:24:31.945371: step: 1212/530, loss: 0.021032335236668587
2023-01-21 10:24:33.115870: step: 1216/530, loss: 0.08539314568042755
2023-01-21 10:24:34.287689: step: 1220/530, loss: 0.05260924994945526
2023-01-21 10:24:35.445117: step: 1224/530, loss: 0.010612296871840954
2023-01-21 10:24:36.611469: step: 1228/530, loss: 0.09653019905090332
2023-01-21 10:24:37.760337: step: 1232/530, loss: 0.08067398518323898
2023-01-21 10:24:38.926419: step: 1236/530, loss: 0.03993654251098633
2023-01-21 10:24:40.059702: step: 1240/530, loss: 0.014272928237915039
2023-01-21 10:24:41.238970: step: 1244/530, loss: 0.08701524883508682
2023-01-21 10:24:42.525631: step: 1248/530, loss: 0.09620419144630432
2023-01-21 10:24:43.731180: step: 1252/530, loss: 0.020607758313417435
2023-01-21 10:24:44.917532: step: 1256/530, loss: 0.06554222106933594
2023-01-21 10:24:46.095684: step: 1260/530, loss: 0.03748941421508789
2023-01-21 10:24:47.264142: step: 1264/530, loss: 0.07038598507642746
2023-01-21 10:24:48.437527: step: 1268/530, loss: 0.1546599417924881
2023-01-21 10:24:49.614686: step: 1272/530, loss: 0.05877971649169922
2023-01-21 10:24:50.797361: step: 1276/530, loss: 0.05580444261431694
2023-01-21 10:24:52.034399: step: 1280/530, loss: 0.0535161979496479
2023-01-21 10:24:53.274259: step: 1284/530, loss: 0.3063715398311615
2023-01-21 10:24:54.431707: step: 1288/530, loss: 0.06162700802087784
2023-01-21 10:24:55.602323: step: 1292/530, loss: 0.021173954010009766
2023-01-21 10:24:56.785845: step: 1296/530, loss: 0.025942610576748848
2023-01-21 10:24:57.946665: step: 1300/530, loss: 0.03369879722595215
2023-01-21 10:24:59.132748: step: 1304/530, loss: 0.041750337928533554
2023-01-21 10:25:00.296392: step: 1308/530, loss: 0.06596679985523224
2023-01-21 10:25:01.443241: step: 1312/530, loss: 0.03637304529547691
2023-01-21 10:25:02.625436: step: 1316/530, loss: 0.056120872497558594
2023-01-21 10:25:03.806537: step: 1320/530, loss: 0.16436100006103516
2023-01-21 10:25:05.023522: step: 1324/530, loss: 0.0427798293530941
2023-01-21 10:25:06.183299: step: 1328/530, loss: 0.07775650173425674
2023-01-21 10:25:07.355468: step: 1332/530, loss: 0.07776966691017151
2023-01-21 10:25:08.525027: step: 1336/530, loss: 0.03252077102661133
2023-01-21 10:25:09.711538: step: 1340/530, loss: 0.0487859733402729
2023-01-21 10:25:10.907259: step: 1344/530, loss: 0.14479666948318481
2023-01-21 10:25:12.146604: step: 1348/530, loss: 0.06095452606678009
2023-01-21 10:25:13.313320: step: 1352/530, loss: 0.05956869199872017
2023-01-21 10:25:14.483325: step: 1356/530, loss: 0.004472017288208008
2023-01-21 10:25:15.675159: step: 1360/530, loss: 0.5448311567306519
2023-01-21 10:25:16.863625: step: 1364/530, loss: 0.195135697722435
2023-01-21 10:25:18.014786: step: 1368/530, loss: 0.13340425491333008
2023-01-21 10:25:19.211183: step: 1372/530, loss: 0.025561904534697533
2023-01-21 10:25:20.363422: step: 1376/530, loss: 0.06085491180419922
2023-01-21 10:25:21.546509: step: 1380/530, loss: 0.060906507074832916
2023-01-21 10:25:22.692911: step: 1384/530, loss: 0.044223833829164505
2023-01-21 10:25:23.884492: step: 1388/530, loss: 0.010550260543823242
2023-01-21 10:25:25.093889: step: 1392/530, loss: 0.008985948748886585
2023-01-21 10:25:26.257895: step: 1396/530, loss: 0.022893667221069336
2023-01-21 10:25:27.459261: step: 1400/530, loss: 0.015783309936523438
2023-01-21 10:25:28.641218: step: 1404/530, loss: 0.059556104242801666
2023-01-21 10:25:29.794949: step: 1408/530, loss: 0.11742211878299713
2023-01-21 10:25:31.000812: step: 1412/530, loss: 0.05485473573207855
2023-01-21 10:25:32.186617: step: 1416/530, loss: 0.1685360074043274
2023-01-21 10:25:33.358551: step: 1420/530, loss: 0.008082007989287376
2023-01-21 10:25:34.527648: step: 1424/530, loss: 0.006194782443344593
2023-01-21 10:25:35.692389: step: 1428/530, loss: 0.0527895912528038
2023-01-21 10:25:36.905765: step: 1432/530, loss: 0.037615206092596054
2023-01-21 10:25:38.086683: step: 1436/530, loss: 0.03121013753116131
2023-01-21 10:25:39.274340: step: 1440/530, loss: 0.21136683225631714
2023-01-21 10:25:40.431361: step: 1444/530, loss: 0.010770178399980068
2023-01-21 10:25:41.610349: step: 1448/530, loss: 0.027344131842255592
2023-01-21 10:25:42.791128: step: 1452/530, loss: 0.08721437305212021
2023-01-21 10:25:43.983656: step: 1456/530, loss: 0.11024856567382812
2023-01-21 10:25:45.158379: step: 1460/530, loss: 0.15505246818065643
2023-01-21 10:25:46.328224: step: 1464/530, loss: 0.16056203842163086
2023-01-21 10:25:47.517245: step: 1468/530, loss: 0.06019601970911026
2023-01-21 10:25:48.721168: step: 1472/530, loss: 0.1794138252735138
2023-01-21 10:25:49.868116: step: 1476/530, loss: 0.04733027145266533
2023-01-21 10:25:51.043561: step: 1480/530, loss: 0.7828097343444824
2023-01-21 10:25:52.219803: step: 1484/530, loss: 0.011182403191924095
2023-01-21 10:25:53.423057: step: 1488/530, loss: 0.14519082009792328
2023-01-21 10:25:54.598314: step: 1492/530, loss: 0.01148910541087389
2023-01-21 10:25:55.781831: step: 1496/530, loss: 0.052773572504520416
2023-01-21 10:25:56.959486: step: 1500/530, loss: 0.14207783341407776
2023-01-21 10:25:58.169719: step: 1504/530, loss: 0.0016389846568927169
2023-01-21 10:25:59.324773: step: 1508/530, loss: 0.015827566385269165
2023-01-21 10:26:00.524100: step: 1512/530, loss: 0.025444984436035156
2023-01-21 10:26:01.705449: step: 1516/530, loss: 0.05846209451556206
2023-01-21 10:26:02.869957: step: 1520/530, loss: 0.006419730372726917
2023-01-21 10:26:04.030335: step: 1524/530, loss: 0.17258760333061218
2023-01-21 10:26:05.223862: step: 1528/530, loss: 0.004049396608024836
2023-01-21 10:26:06.401964: step: 1532/530, loss: 0.12036866694688797
2023-01-21 10:26:07.594191: step: 1536/530, loss: 0.1664033830165863
2023-01-21 10:26:08.767526: step: 1540/530, loss: 0.13083019852638245
2023-01-21 10:26:09.940226: step: 1544/530, loss: 0.054489850997924805
2023-01-21 10:26:11.137423: step: 1548/530, loss: 0.03622307628393173
2023-01-21 10:26:12.326340: step: 1552/530, loss: 0.05670313909649849
2023-01-21 10:26:13.489178: step: 1556/530, loss: 0.13988085091114044
2023-01-21 10:26:14.661790: step: 1560/530, loss: 0.12661799788475037
2023-01-21 10:26:15.849430: step: 1564/530, loss: 0.02112302929162979
2023-01-21 10:26:17.031067: step: 1568/530, loss: 0.31534630060195923
2023-01-21 10:26:18.206514: step: 1572/530, loss: 0.05383773148059845
2023-01-21 10:26:19.376262: step: 1576/530, loss: 0.001490688300691545
2023-01-21 10:26:20.580163: step: 1580/530, loss: 0.09223737567663193
2023-01-21 10:26:21.780672: step: 1584/530, loss: 0.21165180206298828
2023-01-21 10:26:22.996088: step: 1588/530, loss: 0.05581006780266762
2023-01-21 10:26:24.182742: step: 1592/530, loss: 0.17843064665794373
2023-01-21 10:26:25.362621: step: 1596/530, loss: 0.02746429480612278
2023-01-21 10:26:26.515937: step: 1600/530, loss: 0.04981479421257973
2023-01-21 10:26:27.685508: step: 1604/530, loss: 0.054897598922252655
2023-01-21 10:26:28.845538: step: 1608/530, loss: 0.05929527431726456
2023-01-21 10:26:30.034113: step: 1612/530, loss: 0.05613088980317116
2023-01-21 10:26:31.177335: step: 1616/530, loss: 0.21645468473434448
2023-01-21 10:26:32.342439: step: 1620/530, loss: 0.05460290610790253
2023-01-21 10:26:33.522952: step: 1624/530, loss: 0.3275272250175476
2023-01-21 10:26:34.768686: step: 1628/530, loss: 0.09269952774047852
2023-01-21 10:26:35.953947: step: 1632/530, loss: 0.06183989346027374
2023-01-21 10:26:37.120681: step: 1636/530, loss: 0.12125054001808167
2023-01-21 10:26:38.345078: step: 1640/530, loss: 0.07745656371116638
2023-01-21 10:26:39.531340: step: 1644/530, loss: 0.03580541908740997
2023-01-21 10:26:40.707939: step: 1648/530, loss: 0.04462175443768501
2023-01-21 10:26:41.933565: step: 1652/530, loss: 0.07698230445384979
2023-01-21 10:26:43.143001: step: 1656/530, loss: 0.005969190504401922
2023-01-21 10:26:44.336657: step: 1660/530, loss: 0.016604041680693626
2023-01-21 10:26:45.507722: step: 1664/530, loss: 0.1795859932899475
2023-01-21 10:26:46.674215: step: 1668/530, loss: 0.0058987378142774105
2023-01-21 10:26:47.862039: step: 1672/530, loss: 0.16710853576660156
2023-01-21 10:26:49.001732: step: 1676/530, loss: 0.07736340165138245
2023-01-21 10:26:50.181809: step: 1680/530, loss: 0.0938756912946701
2023-01-21 10:26:51.361993: step: 1684/530, loss: 0.01332635898143053
2023-01-21 10:26:52.531235: step: 1688/530, loss: 0.050838373601436615
2023-01-21 10:26:53.735983: step: 1692/530, loss: 0.02434730716049671
2023-01-21 10:26:54.881503: step: 1696/530, loss: 0.04740095138549805
2023-01-21 10:26:56.058436: step: 1700/530, loss: 0.13694047927856445
2023-01-21 10:26:57.233243: step: 1704/530, loss: 0.06920366734266281
2023-01-21 10:26:58.403443: step: 1708/530, loss: 0.03885803371667862
2023-01-21 10:26:59.609306: step: 1712/530, loss: 0.03403434902429581
2023-01-21 10:27:00.818423: step: 1716/530, loss: 0.18362684547901154
2023-01-21 10:27:01.994826: step: 1720/530, loss: 0.052041344344615936
2023-01-21 10:27:03.169871: step: 1724/530, loss: 0.05599212646484375
2023-01-21 10:27:04.305425: step: 1728/530, loss: 0.05550708621740341
2023-01-21 10:27:05.510759: step: 1732/530, loss: 0.14795361459255219
2023-01-21 10:27:06.699440: step: 1736/530, loss: 0.06222677230834961
2023-01-21 10:27:07.868170: step: 1740/530, loss: 0.0858069434762001
2023-01-21 10:27:09.056081: step: 1744/530, loss: 0.03363366425037384
2023-01-21 10:27:10.230461: step: 1748/530, loss: 0.04844493791460991
2023-01-21 10:27:11.402113: step: 1752/530, loss: 0.009208870120346546
2023-01-21 10:27:12.611254: step: 1756/530, loss: 0.049422647804021835
2023-01-21 10:27:13.769755: step: 1760/530, loss: 0.02544851414859295
2023-01-21 10:27:14.946272: step: 1764/530, loss: 0.07263131439685822
2023-01-21 10:27:16.126676: step: 1768/530, loss: 0.021674538031220436
2023-01-21 10:27:17.334957: step: 1772/530, loss: 0.07274136692285538
2023-01-21 10:27:18.479378: step: 1776/530, loss: 0.0262617114931345
2023-01-21 10:27:19.671020: step: 1780/530, loss: 0.02425565756857395
2023-01-21 10:27:20.831630: step: 1784/530, loss: 0.10199139267206192
2023-01-21 10:27:22.025941: step: 1788/530, loss: 0.07866096496582031
2023-01-21 10:27:23.199243: step: 1792/530, loss: 0.03235302120447159
2023-01-21 10:27:24.394065: step: 1796/530, loss: 0.043831516057252884
2023-01-21 10:27:25.606651: step: 1800/530, loss: 0.14048424363136292
2023-01-21 10:27:26.772914: step: 1804/530, loss: 0.014882564544677734
2023-01-21 10:27:28.007213: step: 1808/530, loss: 0.11039991676807404
2023-01-21 10:27:29.211148: step: 1812/530, loss: 0.03767862170934677
2023-01-21 10:27:30.359296: step: 1816/530, loss: 0.039565566927194595
2023-01-21 10:27:31.530088: step: 1820/530, loss: 0.061238765716552734
2023-01-21 10:27:32.703958: step: 1824/530, loss: 0.14865374565124512
2023-01-21 10:27:33.889425: step: 1828/530, loss: 0.14176049828529358
2023-01-21 10:27:35.077437: step: 1832/530, loss: 0.03680315241217613
2023-01-21 10:27:36.275712: step: 1836/530, loss: 0.22869043052196503
2023-01-21 10:27:37.494735: step: 1840/530, loss: 0.059095099568367004
2023-01-21 10:27:38.707877: step: 1844/530, loss: 0.1272084265947342
2023-01-21 10:27:39.904634: step: 1848/530, loss: 0.04223337024450302
2023-01-21 10:27:41.077964: step: 1852/530, loss: 0.04227743297815323
2023-01-21 10:27:42.230331: step: 1856/530, loss: 0.02473464049398899
2023-01-21 10:27:43.402729: step: 1860/530, loss: 0.05458106845617294
2023-01-21 10:27:44.553249: step: 1864/530, loss: 0.22492027282714844
2023-01-21 10:27:45.730326: step: 1868/530, loss: 0.004879808519035578
2023-01-21 10:27:46.888184: step: 1872/530, loss: 0.02873382531106472
2023-01-21 10:27:48.083377: step: 1876/530, loss: 0.08206617087125778
2023-01-21 10:27:49.216303: step: 1880/530, loss: 0.11475200951099396
2023-01-21 10:27:50.385937: step: 1884/530, loss: 0.16529321670532227
2023-01-21 10:27:51.598298: step: 1888/530, loss: 0.16822001338005066
2023-01-21 10:27:52.754239: step: 1892/530, loss: 0.08461141586303711
2023-01-21 10:27:53.961175: step: 1896/530, loss: 0.05309484153985977
2023-01-21 10:27:55.105710: step: 1900/530, loss: 0.0037692070472985506
2023-01-21 10:27:56.341555: step: 1904/530, loss: 0.03453955799341202
2023-01-21 10:27:57.483475: step: 1908/530, loss: 0.011183738708496094
2023-01-21 10:27:58.675134: step: 1912/530, loss: 0.11309614777565002
2023-01-21 10:27:59.857834: step: 1916/530, loss: 0.11008176952600479
2023-01-21 10:28:01.077685: step: 1920/530, loss: 0.05488453060388565
2023-01-21 10:28:02.234366: step: 1924/530, loss: 0.08474178612232208
2023-01-21 10:28:03.459322: step: 1928/530, loss: 0.04155416786670685
2023-01-21 10:28:04.636548: step: 1932/530, loss: 0.01725912094116211
2023-01-21 10:28:05.810360: step: 1936/530, loss: 0.1406540870666504
2023-01-21 10:28:07.013631: step: 1940/530, loss: 0.5332380533218384
2023-01-21 10:28:08.195437: step: 1944/530, loss: 0.7421558499336243
2023-01-21 10:28:09.399348: step: 1948/530, loss: 0.40126684308052063
2023-01-21 10:28:10.568666: step: 1952/530, loss: 0.07025952637195587
2023-01-21 10:28:11.722337: step: 1956/530, loss: 0.10136280953884125
2023-01-21 10:28:12.896949: step: 1960/530, loss: 0.041923485696315765
2023-01-21 10:28:14.139752: step: 1964/530, loss: 0.1143888384103775
2023-01-21 10:28:15.324965: step: 1968/530, loss: 0.0618954673409462
2023-01-21 10:28:16.493130: step: 1972/530, loss: 0.11773848533630371
2023-01-21 10:28:17.663510: step: 1976/530, loss: 0.02304256148636341
2023-01-21 10:28:18.818251: step: 1980/530, loss: 0.03841280937194824
2023-01-21 10:28:19.958838: step: 1984/530, loss: 0.11073608696460724
2023-01-21 10:28:21.139291: step: 1988/530, loss: 0.08356142044067383
2023-01-21 10:28:22.320099: step: 1992/530, loss: 0.013243008404970169
2023-01-21 10:28:23.491987: step: 1996/530, loss: 0.10953474789857864
2023-01-21 10:28:24.701897: step: 2000/530, loss: 0.08240146934986115
2023-01-21 10:28:25.898060: step: 2004/530, loss: 0.03070373460650444
2023-01-21 10:28:27.082624: step: 2008/530, loss: 0.10049595683813095
2023-01-21 10:28:28.273610: step: 2012/530, loss: 0.0011981010902673006
2023-01-21 10:28:29.483933: step: 2016/530, loss: 0.008508492261171341
2023-01-21 10:28:30.634290: step: 2020/530, loss: 1.1270250082015991
2023-01-21 10:28:31.816621: step: 2024/530, loss: 0.049528807401657104
2023-01-21 10:28:32.999948: step: 2028/530, loss: 0.012501812539994717
2023-01-21 10:28:34.191313: step: 2032/530, loss: 0.04654979705810547
2023-01-21 10:28:35.355877: step: 2036/530, loss: 0.06385155022144318
2023-01-21 10:28:36.526835: step: 2040/530, loss: 0.5583160519599915
2023-01-21 10:28:37.673376: step: 2044/530, loss: 0.03641219064593315
2023-01-21 10:28:38.856176: step: 2048/530, loss: 0.01014785747975111
2023-01-21 10:28:40.021127: step: 2052/530, loss: 0.03515911102294922
2023-01-21 10:28:41.186350: step: 2056/530, loss: 0.025452518835663795
2023-01-21 10:28:42.403234: step: 2060/530, loss: 0.040656138211488724
2023-01-21 10:28:43.572030: step: 2064/530, loss: 0.059287551790475845
2023-01-21 10:28:44.772819: step: 2068/530, loss: 0.06181994080543518
2023-01-21 10:28:45.975020: step: 2072/530, loss: 0.1264057159423828
2023-01-21 10:28:47.136453: step: 2076/530, loss: 0.04780912399291992
2023-01-21 10:28:48.348154: step: 2080/530, loss: 0.24887514114379883
2023-01-21 10:28:49.552250: step: 2084/530, loss: 0.027864838019013405
2023-01-21 10:28:50.734853: step: 2088/530, loss: 0.024231623858213425
2023-01-21 10:28:51.885552: step: 2092/530, loss: 0.01285848394036293
2023-01-21 10:28:53.065437: step: 2096/530, loss: 0.011727189645171165
2023-01-21 10:28:54.325701: step: 2100/530, loss: 1.2780228853225708
2023-01-21 10:28:55.552842: step: 2104/530, loss: 0.1730096936225891
2023-01-21 10:28:56.764949: step: 2108/530, loss: 0.009354591369628906
2023-01-21 10:28:57.946332: step: 2112/530, loss: 0.6456766128540039
2023-01-21 10:28:59.147240: step: 2116/530, loss: 0.16068105399608612
2023-01-21 10:29:00.344990: step: 2120/530, loss: 0.03443183749914169
==================================================
Loss: 0.094
--------------------
Dev: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5051546391752577, 'r': 0.9074074074074074, 'f1': 0.6490066225165563}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.425531914893617, 'r': 0.5555555555555556, 'f1': 0.48192771084337355}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:29:55.052836: step: 4/530, loss: 0.040193796157836914
2023-01-21 10:29:56.261470: step: 8/530, loss: 0.1925969123840332
2023-01-21 10:29:57.452882: step: 12/530, loss: 0.008068179711699486
2023-01-21 10:29:58.638133: step: 16/530, loss: 0.054369304329156876
2023-01-21 10:29:59.802226: step: 20/530, loss: 0.03011486493051052
2023-01-21 10:30:00.950402: step: 24/530, loss: 0.008286762982606888
2023-01-21 10:30:02.142369: step: 28/530, loss: 0.0059219361282885075
2023-01-21 10:30:03.265239: step: 32/530, loss: 0.03127327188849449
2023-01-21 10:30:04.416819: step: 36/530, loss: 0.010728931054472923
2023-01-21 10:30:05.580124: step: 40/530, loss: 0.004188823979347944
2023-01-21 10:30:06.773747: step: 44/530, loss: 0.06549644470214844
2023-01-21 10:30:07.947256: step: 48/530, loss: 0.03850555419921875
2023-01-21 10:30:09.130028: step: 52/530, loss: 0.4171985685825348
2023-01-21 10:30:10.316037: step: 56/530, loss: 0.044773101806640625
2023-01-21 10:30:11.472662: step: 60/530, loss: 0.008533382788300514
2023-01-21 10:30:12.628383: step: 64/530, loss: 0.04942756146192551
2023-01-21 10:30:13.801952: step: 68/530, loss: 0.04924755543470383
2023-01-21 10:30:14.978839: step: 72/530, loss: 0.11677218228578568
2023-01-21 10:30:16.169615: step: 76/530, loss: 0.017792511731386185
2023-01-21 10:30:17.344920: step: 80/530, loss: 0.016585683450102806
2023-01-21 10:30:18.525425: step: 84/530, loss: 0.047266677021980286
2023-01-21 10:30:19.684817: step: 88/530, loss: 0.03154829517006874
2023-01-21 10:30:20.837057: step: 92/530, loss: 0.09660597145557404
2023-01-21 10:30:21.995536: step: 96/530, loss: 0.009224509820342064
2023-01-21 10:30:23.150529: step: 100/530, loss: 0.00544586218893528
2023-01-21 10:30:24.307493: step: 104/530, loss: 0.008410096168518066
2023-01-21 10:30:25.477064: step: 108/530, loss: 0.0015298842918127775
2023-01-21 10:30:26.648391: step: 112/530, loss: 0.04512796550989151
2023-01-21 10:30:27.845333: step: 116/530, loss: 0.02275524102151394
2023-01-21 10:30:29.030853: step: 120/530, loss: 0.024181652814149857
2023-01-21 10:30:30.250813: step: 124/530, loss: 0.02689342573285103
2023-01-21 10:30:31.399405: step: 128/530, loss: 0.08269882202148438
2023-01-21 10:30:32.622865: step: 132/530, loss: 0.020416259765625
2023-01-21 10:30:33.867703: step: 136/530, loss: 0.08004073798656464
2023-01-21 10:30:35.086852: step: 140/530, loss: 0.04088592529296875
2023-01-21 10:30:36.241244: step: 144/530, loss: 0.010722160339355469
2023-01-21 10:30:37.436058: step: 148/530, loss: 0.055890750139951706
2023-01-21 10:30:38.637811: step: 152/530, loss: 0.03952045738697052
2023-01-21 10:30:39.811033: step: 156/530, loss: 0.025689315050840378
2023-01-21 10:30:40.973299: step: 160/530, loss: 0.02914433553814888
2023-01-21 10:30:42.160541: step: 164/530, loss: 0.04245796054601669
2023-01-21 10:30:43.301843: step: 168/530, loss: 0.027681540697813034
2023-01-21 10:30:44.475819: step: 172/530, loss: 0.017154311761260033
2023-01-21 10:30:45.677085: step: 176/530, loss: 0.0018316268688067794
2023-01-21 10:30:46.830685: step: 180/530, loss: 0.0682210922241211
2023-01-21 10:30:47.966393: step: 184/530, loss: 0.0075341700576245785
2023-01-21 10:30:49.146074: step: 188/530, loss: 0.006522560492157936
2023-01-21 10:30:50.296754: step: 192/530, loss: 0.005253410432487726
2023-01-21 10:30:51.512984: step: 196/530, loss: 0.05427522957324982
2023-01-21 10:30:52.701491: step: 200/530, loss: 0.0073015689849853516
2023-01-21 10:30:53.863370: step: 204/530, loss: 0.05885805934667587
2023-01-21 10:30:55.069387: step: 208/530, loss: 0.02545776404440403
2023-01-21 10:30:56.224444: step: 212/530, loss: 0.07222796231508255
2023-01-21 10:30:57.409985: step: 216/530, loss: 0.07952285557985306
2023-01-21 10:30:58.621005: step: 220/530, loss: 0.07114200294017792
2023-01-21 10:30:59.790756: step: 224/530, loss: 0.3014918565750122
2023-01-21 10:31:00.988150: step: 228/530, loss: 0.017184067517518997
2023-01-21 10:31:02.173601: step: 232/530, loss: 0.026261616498231888
2023-01-21 10:31:03.345295: step: 236/530, loss: 0.06885233521461487
2023-01-21 10:31:04.540193: step: 240/530, loss: 1.225547194480896
2023-01-21 10:31:05.704436: step: 244/530, loss: 0.026362037286162376
2023-01-21 10:31:06.939268: step: 248/530, loss: 0.13645973801612854
2023-01-21 10:31:08.141573: step: 252/530, loss: 0.018175125122070312
2023-01-21 10:31:09.330645: step: 256/530, loss: 0.046091459691524506
2023-01-21 10:31:10.522115: step: 260/530, loss: 0.02972564660012722
2023-01-21 10:31:11.692831: step: 264/530, loss: 0.6121718287467957
2023-01-21 10:31:12.879650: step: 268/530, loss: 0.004268646240234375
2023-01-21 10:31:14.039550: step: 272/530, loss: 0.04567098617553711
2023-01-21 10:31:15.210981: step: 276/530, loss: 0.05156669765710831
2023-01-21 10:31:16.358673: step: 280/530, loss: 0.016278648748993874
2023-01-21 10:31:17.497549: step: 284/530, loss: 0.07722588628530502
2023-01-21 10:31:18.654113: step: 288/530, loss: 0.06531143188476562
2023-01-21 10:31:19.838442: step: 292/530, loss: 0.04064035415649414
2023-01-21 10:31:21.055986: step: 296/530, loss: 0.018720200285315514
2023-01-21 10:31:22.224585: step: 300/530, loss: 0.06329710781574249
2023-01-21 10:31:23.436012: step: 304/530, loss: 0.16408902406692505
2023-01-21 10:31:24.630377: step: 308/530, loss: 0.01277837809175253
2023-01-21 10:31:25.823098: step: 312/530, loss: 0.033989906311035156
2023-01-21 10:31:27.011346: step: 316/530, loss: 0.01437443494796753
2023-01-21 10:31:28.166490: step: 320/530, loss: 0.02835751697421074
2023-01-21 10:31:29.329735: step: 324/530, loss: 0.844908595085144
2023-01-21 10:31:30.502996: step: 328/530, loss: 0.02436971664428711
2023-01-21 10:31:31.679170: step: 332/530, loss: 0.042284537106752396
2023-01-21 10:31:32.882627: step: 336/530, loss: 0.10146990418434143
2023-01-21 10:31:34.058079: step: 340/530, loss: 0.010786056518554688
2023-01-21 10:31:35.254768: step: 344/530, loss: 0.01684265211224556
2023-01-21 10:31:36.410220: step: 348/530, loss: 0.044982150197029114
2023-01-21 10:31:37.558449: step: 352/530, loss: 0.13811969757080078
2023-01-21 10:31:38.745482: step: 356/530, loss: 0.04064645618200302
2023-01-21 10:31:39.896787: step: 360/530, loss: 0.021478652954101562
2023-01-21 10:31:41.124353: step: 364/530, loss: 0.012730216607451439
2023-01-21 10:31:42.326811: step: 368/530, loss: 0.010828971862792969
2023-01-21 10:31:43.509457: step: 372/530, loss: 0.1215810775756836
2023-01-21 10:31:44.675688: step: 376/530, loss: 0.04316148906946182
2023-01-21 10:31:45.830547: step: 380/530, loss: 1.023289442062378
2023-01-21 10:31:46.984205: step: 384/530, loss: 0.014939587563276291
2023-01-21 10:31:48.145411: step: 388/530, loss: 0.03333263844251633
2023-01-21 10:31:49.346543: step: 392/530, loss: 0.003464949317276478
2023-01-21 10:31:50.515957: step: 396/530, loss: 0.0006778717506676912
2023-01-21 10:31:51.644497: step: 400/530, loss: 0.0017789840931072831
2023-01-21 10:31:52.785180: step: 404/530, loss: 0.09073605388402939
2023-01-21 10:31:53.943987: step: 408/530, loss: 0.008330250158905983
2023-01-21 10:31:55.106434: step: 412/530, loss: 0.0416385680437088
2023-01-21 10:31:56.284712: step: 416/530, loss: 0.022292708978056908
2023-01-21 10:31:57.489708: step: 420/530, loss: 0.04284262657165527
2023-01-21 10:31:58.691487: step: 424/530, loss: 0.032215166836977005
2023-01-21 10:31:59.845731: step: 428/530, loss: 0.07145509868860245
2023-01-21 10:32:01.076873: step: 432/530, loss: 0.03559456020593643
2023-01-21 10:32:02.232174: step: 436/530, loss: 0.03545322269201279
2023-01-21 10:32:03.383733: step: 440/530, loss: 0.07624645531177521
2023-01-21 10:32:04.556599: step: 444/530, loss: 0.040876105427742004
2023-01-21 10:32:05.731553: step: 448/530, loss: 0.007582426071166992
2023-01-21 10:32:06.911123: step: 452/530, loss: 0.06753072887659073
2023-01-21 10:32:08.072297: step: 456/530, loss: 0.09264083206653595
2023-01-21 10:32:09.282502: step: 460/530, loss: 0.11387910693883896
2023-01-21 10:32:10.469444: step: 464/530, loss: 0.012487983331084251
2023-01-21 10:32:11.627662: step: 468/530, loss: 0.021651078015565872
2023-01-21 10:32:12.796721: step: 472/530, loss: 0.013079453259706497
2023-01-21 10:32:13.983507: step: 476/530, loss: 0.05984792858362198
2023-01-21 10:32:15.170974: step: 480/530, loss: 0.054645441472530365
2023-01-21 10:32:16.331405: step: 484/530, loss: 0.05262718349695206
2023-01-21 10:32:17.482882: step: 488/530, loss: 0.08547866344451904
2023-01-21 10:32:18.657705: step: 492/530, loss: 0.010970878414809704
2023-01-21 10:32:19.859032: step: 496/530, loss: 0.07885799556970596
2023-01-21 10:32:21.009512: step: 500/530, loss: 0.008196020498871803
2023-01-21 10:32:22.178182: step: 504/530, loss: 0.08262091130018234
2023-01-21 10:32:23.333913: step: 508/530, loss: 0.20434603095054626
2023-01-21 10:32:24.538553: step: 512/530, loss: 0.1378999650478363
2023-01-21 10:32:25.703758: step: 516/530, loss: 0.07595586776733398
2023-01-21 10:32:26.866083: step: 520/530, loss: 0.0707605853676796
2023-01-21 10:32:28.098013: step: 524/530, loss: 0.025089645758271217
2023-01-21 10:32:29.281096: step: 528/530, loss: 0.028089236468076706
2023-01-21 10:32:30.453167: step: 532/530, loss: 0.039298057556152344
2023-01-21 10:32:31.628399: step: 536/530, loss: 0.03831539303064346
2023-01-21 10:32:32.821560: step: 540/530, loss: 0.035120584070682526
2023-01-21 10:32:34.014658: step: 544/530, loss: 0.04647207260131836
2023-01-21 10:32:35.256632: step: 548/530, loss: 0.037885282188653946
2023-01-21 10:32:36.399062: step: 552/530, loss: 0.001146030379459262
2023-01-21 10:32:37.565349: step: 556/530, loss: 0.02865314483642578
2023-01-21 10:32:38.730428: step: 560/530, loss: 0.06953983008861542
2023-01-21 10:32:39.919016: step: 564/530, loss: 0.11244497448205948
2023-01-21 10:32:41.099737: step: 568/530, loss: 0.12538576126098633
2023-01-21 10:32:42.305675: step: 572/530, loss: 0.02740314044058323
2023-01-21 10:32:43.487491: step: 576/530, loss: 0.026177024468779564
2023-01-21 10:32:44.707160: step: 580/530, loss: 0.022669412195682526
2023-01-21 10:32:45.852715: step: 584/530, loss: 0.030486201867461205
2023-01-21 10:32:47.044031: step: 588/530, loss: 0.2832070291042328
2023-01-21 10:32:48.223296: step: 592/530, loss: 0.006395816802978516
2023-01-21 10:32:49.427384: step: 596/530, loss: 0.03436432033777237
2023-01-21 10:32:50.626358: step: 600/530, loss: 0.0880916565656662
2023-01-21 10:32:51.812834: step: 604/530, loss: 0.12265052646398544
2023-01-21 10:32:52.988868: step: 608/530, loss: 0.13371442258358002
2023-01-21 10:32:54.183782: step: 612/530, loss: 0.051534175872802734
2023-01-21 10:32:55.377582: step: 616/530, loss: 0.12401533126831055
2023-01-21 10:32:56.578220: step: 620/530, loss: 0.08221378922462463
2023-01-21 10:32:57.751289: step: 624/530, loss: 0.0038105486892163754
2023-01-21 10:32:58.920028: step: 628/530, loss: 0.04228964075446129
2023-01-21 10:33:00.093009: step: 632/530, loss: 0.03572959825396538
2023-01-21 10:33:01.367382: step: 636/530, loss: 0.04438524320721626
2023-01-21 10:33:02.526932: step: 640/530, loss: 0.01891307905316353
2023-01-21 10:33:03.687706: step: 644/530, loss: 0.05729370191693306
2023-01-21 10:33:04.941845: step: 648/530, loss: 0.04836712032556534
2023-01-21 10:33:06.130183: step: 652/530, loss: 0.10525589436292648
2023-01-21 10:33:07.315585: step: 656/530, loss: 0.0496579185128212
2023-01-21 10:33:08.556461: step: 660/530, loss: 0.015357399359345436
2023-01-21 10:33:09.740566: step: 664/530, loss: 0.06007261201739311
2023-01-21 10:33:10.995457: step: 668/530, loss: 0.026992036029696465
2023-01-21 10:33:12.147608: step: 672/530, loss: 0.0047779087908566
2023-01-21 10:33:13.337956: step: 676/530, loss: 0.0412198081612587
2023-01-21 10:33:14.544053: step: 680/530, loss: 0.04959306865930557
2023-01-21 10:33:15.722457: step: 684/530, loss: 0.0832623541355133
2023-01-21 10:33:16.934811: step: 688/530, loss: 0.03372330591082573
2023-01-21 10:33:18.113500: step: 692/530, loss: 0.008663564920425415
2023-01-21 10:33:19.252277: step: 696/530, loss: 0.08561283349990845
2023-01-21 10:33:20.421571: step: 700/530, loss: 0.12334556877613068
2023-01-21 10:33:21.586837: step: 704/530, loss: 0.011485290713608265
2023-01-21 10:33:22.789875: step: 708/530, loss: 0.033331871032714844
2023-01-21 10:33:23.963728: step: 712/530, loss: 0.03820851445198059
2023-01-21 10:33:25.136887: step: 716/530, loss: 0.01797785796225071
2023-01-21 10:33:26.336511: step: 720/530, loss: 0.050202179700136185
2023-01-21 10:33:27.552677: step: 724/530, loss: 0.05454311519861221
2023-01-21 10:33:28.714043: step: 728/530, loss: 0.007267093751579523
2023-01-21 10:33:29.861336: step: 732/530, loss: 0.003907442092895508
2023-01-21 10:33:31.034476: step: 736/530, loss: 0.02642088010907173
2023-01-21 10:33:32.202537: step: 740/530, loss: 0.03476686775684357
2023-01-21 10:33:33.425910: step: 744/530, loss: 0.00971007440239191
2023-01-21 10:33:34.599510: step: 748/530, loss: 0.15674400329589844
2023-01-21 10:33:35.772063: step: 752/530, loss: 0.0017531871562823653
2023-01-21 10:33:36.936561: step: 756/530, loss: 0.18296855688095093
2023-01-21 10:33:38.098958: step: 760/530, loss: 0.07615260779857635
2023-01-21 10:33:39.309652: step: 764/530, loss: 0.014386367984116077
2023-01-21 10:33:40.465529: step: 768/530, loss: 0.00672540720552206
2023-01-21 10:33:41.630968: step: 772/530, loss: 0.013537502847611904
2023-01-21 10:33:42.836075: step: 776/530, loss: 0.06736688315868378
2023-01-21 10:33:44.060904: step: 780/530, loss: 0.13366222381591797
2023-01-21 10:33:45.238815: step: 784/530, loss: 0.048146724700927734
2023-01-21 10:33:46.462927: step: 788/530, loss: 0.3908994197845459
2023-01-21 10:33:47.629555: step: 792/530, loss: 0.0030434608925133944
2023-01-21 10:33:48.815525: step: 796/530, loss: 0.003957939334213734
2023-01-21 10:33:50.028907: step: 800/530, loss: 0.03417949751019478
2023-01-21 10:33:51.158618: step: 804/530, loss: 0.030261993408203125
2023-01-21 10:33:52.370027: step: 808/530, loss: 0.058305174112319946
2023-01-21 10:33:53.534346: step: 812/530, loss: 0.022214507684111595
2023-01-21 10:33:54.759852: step: 816/530, loss: 0.051863860338926315
2023-01-21 10:33:55.985282: step: 820/530, loss: 0.011324597522616386
2023-01-21 10:33:57.166924: step: 824/530, loss: 0.06011686474084854
2023-01-21 10:33:58.353689: step: 828/530, loss: 0.13771677017211914
2023-01-21 10:33:59.521353: step: 832/530, loss: 0.0388481505215168
2023-01-21 10:34:00.697834: step: 836/530, loss: 0.0248087290674448
2023-01-21 10:34:01.876197: step: 840/530, loss: 0.05014844238758087
2023-01-21 10:34:03.099114: step: 844/530, loss: 0.04474234580993652
2023-01-21 10:34:04.294240: step: 848/530, loss: 0.059267617762088776
2023-01-21 10:34:05.456993: step: 852/530, loss: 0.032663822174072266
2023-01-21 10:34:06.596161: step: 856/530, loss: 0.026125334203243256
2023-01-21 10:34:07.797246: step: 860/530, loss: 0.025179481133818626
2023-01-21 10:34:09.018535: step: 864/530, loss: 0.010769093409180641
2023-01-21 10:34:10.196767: step: 868/530, loss: 0.07975830882787704
2023-01-21 10:34:11.393811: step: 872/530, loss: 0.07185707241296768
2023-01-21 10:34:12.630545: step: 876/530, loss: 0.09335789829492569
2023-01-21 10:34:13.851814: step: 880/530, loss: 0.01723327860236168
2023-01-21 10:34:15.049843: step: 884/530, loss: 0.04452686384320259
2023-01-21 10:34:16.212730: step: 888/530, loss: 0.024522019550204277
2023-01-21 10:34:17.399034: step: 892/530, loss: 0.016650009900331497
2023-01-21 10:34:18.585857: step: 896/530, loss: 0.12502537667751312
2023-01-21 10:34:19.734656: step: 900/530, loss: 0.0653235912322998
2023-01-21 10:34:20.898002: step: 904/530, loss: 0.01581707037985325
2023-01-21 10:34:22.082939: step: 908/530, loss: 0.03271684795618057
2023-01-21 10:34:23.265361: step: 912/530, loss: 0.6562553644180298
2023-01-21 10:34:24.454094: step: 916/530, loss: 0.036132145673036575
2023-01-21 10:34:25.636017: step: 920/530, loss: 0.0026128769386559725
2023-01-21 10:34:26.839379: step: 924/530, loss: 0.01007752399891615
2023-01-21 10:34:28.059402: step: 928/530, loss: 0.05231647565960884
2023-01-21 10:34:29.221474: step: 932/530, loss: 0.025013351812958717
2023-01-21 10:34:30.404891: step: 936/530, loss: 0.13412514328956604
2023-01-21 10:34:31.577486: step: 940/530, loss: 0.15119361877441406
2023-01-21 10:34:32.771145: step: 944/530, loss: 0.07803191989660263
2023-01-21 10:34:33.947333: step: 948/530, loss: 0.0067005157470703125
2023-01-21 10:34:35.134366: step: 952/530, loss: 0.036341384053230286
2023-01-21 10:34:36.324629: step: 956/530, loss: 0.04508399963378906
2023-01-21 10:34:37.562531: step: 960/530, loss: 0.10063686966896057
2023-01-21 10:34:38.735976: step: 964/530, loss: 0.00360512756742537
2023-01-21 10:34:39.896389: step: 968/530, loss: 0.020470619201660156
2023-01-21 10:34:41.095271: step: 972/530, loss: 0.006973457522690296
2023-01-21 10:34:42.307767: step: 976/530, loss: 0.023480558767914772
2023-01-21 10:34:43.489010: step: 980/530, loss: 0.029812907800078392
2023-01-21 10:34:44.665425: step: 984/530, loss: 0.04470071941614151
2023-01-21 10:34:45.820557: step: 988/530, loss: 0.03359051048755646
2023-01-21 10:34:47.048029: step: 992/530, loss: 0.4126303195953369
2023-01-21 10:34:48.244327: step: 996/530, loss: 0.018140316009521484
2023-01-21 10:34:49.388697: step: 1000/530, loss: 0.05247020721435547
2023-01-21 10:34:50.578519: step: 1004/530, loss: 0.061660218983888626
2023-01-21 10:34:51.771487: step: 1008/530, loss: 0.027158355340361595
2023-01-21 10:34:52.955382: step: 1012/530, loss: 0.016544818878173828
2023-01-21 10:34:54.189519: step: 1016/530, loss: 0.05646038055419922
2023-01-21 10:34:55.308616: step: 1020/530, loss: 0.017916489392518997
2023-01-21 10:34:56.491794: step: 1024/530, loss: 0.02293720282614231
2023-01-21 10:34:57.691617: step: 1028/530, loss: 0.21399955451488495
2023-01-21 10:34:58.895851: step: 1032/530, loss: 0.06986560672521591
2023-01-21 10:35:00.079085: step: 1036/530, loss: 0.020253753289580345
2023-01-21 10:35:01.262467: step: 1040/530, loss: 0.027814103290438652
2023-01-21 10:35:02.430122: step: 1044/530, loss: 0.26092958450317383
2023-01-21 10:35:03.630447: step: 1048/530, loss: 0.05469389259815216
2023-01-21 10:35:04.802706: step: 1052/530, loss: 0.0655149444937706
2023-01-21 10:35:06.014196: step: 1056/530, loss: 0.15257254242897034
2023-01-21 10:35:07.191377: step: 1060/530, loss: 0.04388999938964844
2023-01-21 10:35:08.375386: step: 1064/530, loss: 0.0736115425825119
2023-01-21 10:35:09.562894: step: 1068/530, loss: 0.040364883840084076
2023-01-21 10:35:10.774291: step: 1072/530, loss: 0.051200296729803085
2023-01-21 10:35:11.966739: step: 1076/530, loss: 0.18050844967365265
2023-01-21 10:35:13.102560: step: 1080/530, loss: 0.01931166648864746
2023-01-21 10:35:14.260553: step: 1084/530, loss: 0.0028374672401696444
2023-01-21 10:35:15.416400: step: 1088/530, loss: 0.025735855102539062
2023-01-21 10:35:16.609791: step: 1092/530, loss: 0.12311353534460068
2023-01-21 10:35:17.842378: step: 1096/530, loss: 0.10393076390028
2023-01-21 10:35:19.042670: step: 1100/530, loss: 0.05007191002368927
2023-01-21 10:35:20.224216: step: 1104/530, loss: 0.03162822872400284
2023-01-21 10:35:21.400831: step: 1108/530, loss: 0.01460571214556694
2023-01-21 10:35:22.572017: step: 1112/530, loss: 0.081229068338871
2023-01-21 10:35:23.757687: step: 1116/530, loss: 0.3075721263885498
2023-01-21 10:35:24.965165: step: 1120/530, loss: 0.09793069213628769
2023-01-21 10:35:26.132299: step: 1124/530, loss: 0.010797500610351562
2023-01-21 10:35:27.271392: step: 1128/530, loss: 0.009747028350830078
2023-01-21 10:35:28.472378: step: 1132/530, loss: 0.03980827331542969
2023-01-21 10:35:29.657279: step: 1136/530, loss: 0.06436280906200409
2023-01-21 10:35:30.829144: step: 1140/530, loss: 0.06997604668140411
2023-01-21 10:35:31.983613: step: 1144/530, loss: 0.0021999599412083626
2023-01-21 10:35:33.123922: step: 1148/530, loss: 0.004562473390251398
2023-01-21 10:35:34.324667: step: 1152/530, loss: 0.012472153641283512
2023-01-21 10:35:35.470417: step: 1156/530, loss: 0.008253097534179688
2023-01-21 10:35:36.639041: step: 1160/530, loss: 0.027341270819306374
2023-01-21 10:35:37.803392: step: 1164/530, loss: 0.024799823760986328
2023-01-21 10:35:38.946214: step: 1168/530, loss: 0.038684748113155365
2023-01-21 10:35:40.098142: step: 1172/530, loss: 0.24883747100830078
2023-01-21 10:35:41.257190: step: 1176/530, loss: 0.07423864305019379
2023-01-21 10:35:42.467007: step: 1180/530, loss: 0.04277057573199272
2023-01-21 10:35:43.647589: step: 1184/530, loss: 0.007458400912582874
2023-01-21 10:35:44.808868: step: 1188/530, loss: 0.0056517599150538445
2023-01-21 10:35:45.969690: step: 1192/530, loss: 0.02722902223467827
2023-01-21 10:35:47.159866: step: 1196/530, loss: 0.14411425590515137
2023-01-21 10:35:48.319682: step: 1200/530, loss: 0.06798720359802246
2023-01-21 10:35:49.502273: step: 1204/530, loss: 0.21190214157104492
2023-01-21 10:35:50.661563: step: 1208/530, loss: 0.04999339580535889
2023-01-21 10:35:51.863614: step: 1212/530, loss: 0.3592701852321625
2023-01-21 10:35:53.040319: step: 1216/530, loss: 0.0421878844499588
2023-01-21 10:35:54.241310: step: 1220/530, loss: 0.05697841942310333
2023-01-21 10:35:55.424102: step: 1224/530, loss: 0.02662830427289009
2023-01-21 10:35:56.693905: step: 1228/530, loss: 0.38961562514305115
2023-01-21 10:35:57.893602: step: 1232/530, loss: 0.014125823974609375
2023-01-21 10:35:59.074752: step: 1236/530, loss: 0.049326326698064804
2023-01-21 10:36:00.293644: step: 1240/530, loss: 0.023943709209561348
2023-01-21 10:36:01.489238: step: 1244/530, loss: 0.0799466148018837
2023-01-21 10:36:02.678343: step: 1248/530, loss: 0.05999784171581268
2023-01-21 10:36:03.880846: step: 1252/530, loss: 0.05664873495697975
2023-01-21 10:36:05.059040: step: 1256/530, loss: 0.06613197177648544
2023-01-21 10:36:06.242680: step: 1260/530, loss: 0.06309938430786133
2023-01-21 10:36:07.440765: step: 1264/530, loss: 0.006645870395004749
2023-01-21 10:36:08.685398: step: 1268/530, loss: 0.041959669440984726
2023-01-21 10:36:09.890443: step: 1272/530, loss: 0.09657907485961914
2023-01-21 10:36:11.050005: step: 1276/530, loss: 0.025110816583037376
2023-01-21 10:36:12.232100: step: 1280/530, loss: 0.05965852737426758
2023-01-21 10:36:13.408161: step: 1284/530, loss: 0.05253257602453232
2023-01-21 10:36:14.619818: step: 1288/530, loss: 0.27936476469039917
2023-01-21 10:36:15.816896: step: 1292/530, loss: 0.0941135436296463
2023-01-21 10:36:17.013566: step: 1296/530, loss: 0.006976413540542126
2023-01-21 10:36:18.196547: step: 1300/530, loss: 0.05810394510626793
2023-01-21 10:36:19.371824: step: 1304/530, loss: 0.051522161811590195
2023-01-21 10:36:20.540268: step: 1308/530, loss: 0.06858482956886292
2023-01-21 10:36:21.739493: step: 1312/530, loss: 0.018082808703184128
2023-01-21 10:36:22.940037: step: 1316/530, loss: 0.01313791237771511
2023-01-21 10:36:24.129373: step: 1320/530, loss: 0.08888392150402069
2023-01-21 10:36:25.338918: step: 1324/530, loss: 0.0287035945802927
2023-01-21 10:36:26.498881: step: 1328/530, loss: 0.10513058304786682
2023-01-21 10:36:27.698033: step: 1332/530, loss: 0.08273611217737198
2023-01-21 10:36:28.895437: step: 1336/530, loss: 0.04304981976747513
2023-01-21 10:36:30.059326: step: 1340/530, loss: 0.014644431881606579
2023-01-21 10:36:31.242015: step: 1344/530, loss: 0.03971881791949272
2023-01-21 10:36:32.420180: step: 1348/530, loss: 0.0632256492972374
2023-01-21 10:36:33.601149: step: 1352/530, loss: 0.12699586153030396
2023-01-21 10:36:34.787727: step: 1356/530, loss: 0.02354593202471733
2023-01-21 10:36:35.949646: step: 1360/530, loss: 0.04231557995080948
2023-01-21 10:36:37.111468: step: 1364/530, loss: 0.03652925416827202
2023-01-21 10:36:38.315679: step: 1368/530, loss: 0.06089644506573677
2023-01-21 10:36:39.479562: step: 1372/530, loss: 0.012512017041444778
2023-01-21 10:36:40.635693: step: 1376/530, loss: 0.0172574520111084
2023-01-21 10:36:41.752031: step: 1380/530, loss: 0.009197902865707874
2023-01-21 10:36:42.947003: step: 1384/530, loss: 0.05680666118860245
2023-01-21 10:36:44.141044: step: 1388/530, loss: 0.021976470947265625
2023-01-21 10:36:45.397771: step: 1392/530, loss: 0.05697183310985565
2023-01-21 10:36:46.540449: step: 1396/530, loss: 0.0026158331893384457
2023-01-21 10:36:47.709078: step: 1400/530, loss: 0.015715217217803
2023-01-21 10:36:48.895996: step: 1404/530, loss: 0.09058323502540588
2023-01-21 10:36:50.114241: step: 1408/530, loss: 0.29007381200790405
2023-01-21 10:36:51.263649: step: 1412/530, loss: 1.439026117324829
2023-01-21 10:36:52.439929: step: 1416/530, loss: 0.08220891654491425
2023-01-21 10:36:53.599885: step: 1420/530, loss: 0.11348428577184677
2023-01-21 10:36:54.823037: step: 1424/530, loss: 0.031708527356386185
2023-01-21 10:36:56.031425: step: 1428/530, loss: 0.30097341537475586
2023-01-21 10:36:57.182348: step: 1432/530, loss: 0.01700286753475666
2023-01-21 10:36:58.352493: step: 1436/530, loss: 0.01936321333050728
2023-01-21 10:36:59.536899: step: 1440/530, loss: 0.02789301984012127
2023-01-21 10:37:00.728227: step: 1444/530, loss: 0.04058055952191353
2023-01-21 10:37:01.895697: step: 1448/530, loss: 0.014706611633300781
2023-01-21 10:37:03.102440: step: 1452/530, loss: 0.06454400718212128
2023-01-21 10:37:04.253865: step: 1456/530, loss: 0.04108614847064018
2023-01-21 10:37:05.417658: step: 1460/530, loss: 0.029926490038633347
2023-01-21 10:37:06.640666: step: 1464/530, loss: 0.041158296167850494
2023-01-21 10:37:07.825977: step: 1468/530, loss: 0.10778876394033432
2023-01-21 10:37:09.025719: step: 1472/530, loss: 0.027494337409734726
2023-01-21 10:37:10.180805: step: 1476/530, loss: 0.020072031766176224
2023-01-21 10:37:11.384431: step: 1480/530, loss: 0.05857563018798828
2023-01-21 10:37:12.600374: step: 1484/530, loss: 0.06425486505031586
2023-01-21 10:37:13.774933: step: 1488/530, loss: 0.2647492289543152
2023-01-21 10:37:14.957823: step: 1492/530, loss: 0.0670381560921669
2023-01-21 10:37:16.144054: step: 1496/530, loss: 0.03156747668981552
2023-01-21 10:37:17.324542: step: 1500/530, loss: 0.0004258156113792211
2023-01-21 10:37:18.544919: step: 1504/530, loss: 0.002929210662841797
2023-01-21 10:37:19.715971: step: 1508/530, loss: 0.0641416609287262
2023-01-21 10:37:20.888633: step: 1512/530, loss: 0.0788789764046669
2023-01-21 10:37:22.044382: step: 1516/530, loss: 0.019392013549804688
2023-01-21 10:37:23.245455: step: 1520/530, loss: 0.35581105947494507
2023-01-21 10:37:24.443214: step: 1524/530, loss: 0.05329761654138565
2023-01-21 10:37:25.625505: step: 1528/530, loss: 0.03252973407506943
2023-01-21 10:37:26.809707: step: 1532/530, loss: 0.03524503856897354
2023-01-21 10:37:28.028883: step: 1536/530, loss: 0.043288663029670715
2023-01-21 10:37:29.225479: step: 1540/530, loss: 0.030834197998046875
2023-01-21 10:37:30.408735: step: 1544/530, loss: 0.017821885645389557
2023-01-21 10:37:31.609612: step: 1548/530, loss: 0.04443841055035591
2023-01-21 10:37:32.811721: step: 1552/530, loss: 0.11334028095006943
2023-01-21 10:37:33.972026: step: 1556/530, loss: 0.02788219414651394
2023-01-21 10:37:35.160964: step: 1560/530, loss: 0.062150001525878906
2023-01-21 10:37:36.359602: step: 1564/530, loss: 0.04017162322998047
2023-01-21 10:37:37.613957: step: 1568/530, loss: 0.05305814743041992
2023-01-21 10:37:38.834558: step: 1572/530, loss: 0.043811991810798645
2023-01-21 10:37:40.021359: step: 1576/530, loss: 0.02407817915081978
2023-01-21 10:37:41.200635: step: 1580/530, loss: 0.22694797813892365
2023-01-21 10:37:42.361362: step: 1584/530, loss: 0.04466314613819122
2023-01-21 10:37:43.517532: step: 1588/530, loss: 0.026455307379364967
2023-01-21 10:37:44.717486: step: 1592/530, loss: 0.25087910890579224
2023-01-21 10:37:45.887902: step: 1596/530, loss: 0.0790504440665245
2023-01-21 10:37:47.068181: step: 1600/530, loss: 0.0269167423248291
2023-01-21 10:37:48.250530: step: 1604/530, loss: 0.025547217577695847
2023-01-21 10:37:49.460780: step: 1608/530, loss: 0.07659397274255753
2023-01-21 10:37:50.652143: step: 1612/530, loss: 0.03527393564581871
2023-01-21 10:37:51.851188: step: 1616/530, loss: 0.07311735302209854
2023-01-21 10:37:53.035140: step: 1620/530, loss: 0.04003019258379936
2023-01-21 10:37:54.233317: step: 1624/530, loss: 0.004047393798828125
2023-01-21 10:37:55.409936: step: 1628/530, loss: 0.08315735310316086
2023-01-21 10:37:56.552895: step: 1632/530, loss: 0.09470382332801819
2023-01-21 10:37:57.762104: step: 1636/530, loss: 0.055933333933353424
2023-01-21 10:37:59.002687: step: 1640/530, loss: 0.0070473672822117805
2023-01-21 10:38:00.187715: step: 1644/530, loss: 0.034024428576231
2023-01-21 10:38:01.340735: step: 1648/530, loss: 0.08158489316701889
2023-01-21 10:38:02.497494: step: 1652/530, loss: 0.033138107508420944
2023-01-21 10:38:03.637294: step: 1656/530, loss: 0.0032841681968420744
2023-01-21 10:38:04.826977: step: 1660/530, loss: 0.0026679039001464844
2023-01-21 10:38:06.064521: step: 1664/530, loss: 0.07529354840517044
2023-01-21 10:38:07.258210: step: 1668/530, loss: 0.0316782221198082
2023-01-21 10:38:08.420870: step: 1672/530, loss: 0.03076343610882759
2023-01-21 10:38:09.563795: step: 1676/530, loss: 0.07990200817584991
2023-01-21 10:38:10.731107: step: 1680/530, loss: 0.002024746034294367
2023-01-21 10:38:11.933798: step: 1684/530, loss: 0.053371235728263855
2023-01-21 10:38:13.144675: step: 1688/530, loss: 0.003030919935554266
2023-01-21 10:38:14.302966: step: 1692/530, loss: 0.011446857824921608
2023-01-21 10:38:15.451309: step: 1696/530, loss: 0.017545366659760475
2023-01-21 10:38:16.616737: step: 1700/530, loss: 0.04211931303143501
2023-01-21 10:38:17.820345: step: 1704/530, loss: 0.09288759529590607
2023-01-21 10:38:19.026720: step: 1708/530, loss: 0.039089396595954895
2023-01-21 10:38:20.217490: step: 1712/530, loss: 0.09768429398536682
2023-01-21 10:38:21.414912: step: 1716/530, loss: 0.005444908048957586
2023-01-21 10:38:22.590934: step: 1720/530, loss: 0.042947910726070404
2023-01-21 10:38:23.789069: step: 1724/530, loss: 0.14172887802124023
2023-01-21 10:38:25.006910: step: 1728/530, loss: 0.013875866308808327
2023-01-21 10:38:26.155865: step: 1732/530, loss: 0.006092834752053022
2023-01-21 10:38:27.338855: step: 1736/530, loss: 0.12989740073680878
2023-01-21 10:38:28.518752: step: 1740/530, loss: 0.09237499535083771
2023-01-21 10:38:29.680832: step: 1744/530, loss: 0.018376445397734642
2023-01-21 10:38:30.874420: step: 1748/530, loss: 0.002489757491275668
2023-01-21 10:38:32.040487: step: 1752/530, loss: 0.026789667084813118
2023-01-21 10:38:33.177842: step: 1756/530, loss: 0.06102064624428749
2023-01-21 10:38:34.326151: step: 1760/530, loss: 0.04107780382037163
2023-01-21 10:38:35.499599: step: 1764/530, loss: 0.015265846624970436
2023-01-21 10:38:36.703770: step: 1768/530, loss: 0.010283184237778187
2023-01-21 10:38:37.881049: step: 1772/530, loss: 0.030953610315918922
2023-01-21 10:38:39.022450: step: 1776/530, loss: 0.09752622246742249
2023-01-21 10:38:40.201434: step: 1780/530, loss: 0.09758854657411575
2023-01-21 10:38:41.415375: step: 1784/530, loss: 0.07034482806921005
2023-01-21 10:38:42.654581: step: 1788/530, loss: 0.08178377151489258
2023-01-21 10:38:43.865602: step: 1792/530, loss: 0.016475582495331764
2023-01-21 10:38:45.022843: step: 1796/530, loss: 0.006459140684455633
2023-01-21 10:38:46.215455: step: 1800/530, loss: 0.0015003443695604801
2023-01-21 10:38:47.359688: step: 1804/530, loss: 0.0034512400161474943
2023-01-21 10:38:48.534364: step: 1808/530, loss: 0.0734289139509201
2023-01-21 10:38:49.747881: step: 1812/530, loss: 0.11434536427259445
2023-01-21 10:38:50.933220: step: 1816/530, loss: 0.13031813502311707
2023-01-21 10:38:52.091321: step: 1820/530, loss: 0.006575929932296276
2023-01-21 10:38:53.300687: step: 1824/530, loss: 0.201338529586792
2023-01-21 10:38:54.484255: step: 1828/530, loss: 0.009511947631835938
2023-01-21 10:38:55.656635: step: 1832/530, loss: 0.1060938835144043
2023-01-21 10:38:56.847806: step: 1836/530, loss: 0.02113560400903225
2023-01-21 10:38:58.029235: step: 1840/530, loss: 0.11078128218650818
2023-01-21 10:38:59.208322: step: 1844/530, loss: 0.013461923226714134
2023-01-21 10:39:00.466744: step: 1848/530, loss: 0.05008862167596817
2023-01-21 10:39:01.652743: step: 1852/530, loss: 0.06582939624786377
2023-01-21 10:39:02.837969: step: 1856/530, loss: 0.009858131408691406
2023-01-21 10:39:04.019006: step: 1860/530, loss: 0.060059450566768646
2023-01-21 10:39:05.196935: step: 1864/530, loss: 0.06390972435474396
2023-01-21 10:39:06.358981: step: 1868/530, loss: 0.041956402361392975
2023-01-21 10:39:07.543711: step: 1872/530, loss: 0.04145832359790802
2023-01-21 10:39:08.714052: step: 1876/530, loss: 0.016301751136779785
2023-01-21 10:39:09.895295: step: 1880/530, loss: 0.021349811926484108
2023-01-21 10:39:11.111684: step: 1884/530, loss: 0.06501074135303497
2023-01-21 10:39:12.305317: step: 1888/530, loss: 0.0013097763294354081
2023-01-21 10:39:13.493393: step: 1892/530, loss: 0.042084887623786926
2023-01-21 10:39:14.707011: step: 1896/530, loss: 0.041356779634952545
2023-01-21 10:39:15.866675: step: 1900/530, loss: 0.01663064956665039
2023-01-21 10:39:17.044170: step: 1904/530, loss: 0.07321052253246307
2023-01-21 10:39:18.210538: step: 1908/530, loss: 0.0691106766462326
2023-01-21 10:39:19.384708: step: 1912/530, loss: 0.023871900513768196
2023-01-21 10:39:20.541129: step: 1916/530, loss: 0.032453037798404694
2023-01-21 10:39:21.768553: step: 1920/530, loss: 0.10434424877166748
2023-01-21 10:39:22.978786: step: 1924/530, loss: 0.041181087493896484
2023-01-21 10:39:24.131187: step: 1928/530, loss: 0.4977661967277527
2023-01-21 10:39:25.336070: step: 1932/530, loss: 0.6903577446937561
2023-01-21 10:39:26.512678: step: 1936/530, loss: 0.016359902918338776
2023-01-21 10:39:27.691595: step: 1940/530, loss: 0.031145095825195312
2023-01-21 10:39:28.884993: step: 1944/530, loss: 0.019084835425019264
2023-01-21 10:39:30.124440: step: 1948/530, loss: 0.007791615091264248
2023-01-21 10:39:31.324294: step: 1952/530, loss: 0.093549445271492
2023-01-21 10:39:32.524701: step: 1956/530, loss: 0.08363190293312073
2023-01-21 10:39:33.713495: step: 1960/530, loss: 0.05023627355694771
2023-01-21 10:39:34.870356: step: 1964/530, loss: 0.02221975289285183
2023-01-21 10:39:36.039869: step: 1968/530, loss: 0.0067608836106956005
2023-01-21 10:39:37.232907: step: 1972/530, loss: 0.02654724195599556
2023-01-21 10:39:38.388879: step: 1976/530, loss: 0.04441361501812935
2023-01-21 10:39:39.543522: step: 1980/530, loss: 0.03865647315979004
2023-01-21 10:39:40.718138: step: 1984/530, loss: 0.09422292560338974
2023-01-21 10:39:41.905232: step: 1988/530, loss: 0.20209617912769318
2023-01-21 10:39:43.076178: step: 1992/530, loss: 0.05284881591796875
2023-01-21 10:39:44.247397: step: 1996/530, loss: 0.11346082389354706
2023-01-21 10:39:45.417540: step: 2000/530, loss: 1.0265063047409058
2023-01-21 10:39:46.602056: step: 2004/530, loss: 0.1546923667192459
2023-01-21 10:39:47.816509: step: 2008/530, loss: 0.010292625986039639
2023-01-21 10:39:49.059152: step: 2012/530, loss: 0.030474377796053886
2023-01-21 10:39:50.206402: step: 2016/530, loss: 0.050510697066783905
2023-01-21 10:39:51.403872: step: 2020/530, loss: 0.011582328006625175
2023-01-21 10:39:52.582810: step: 2024/530, loss: 0.01223988551646471
2023-01-21 10:39:53.765309: step: 2028/530, loss: 0.019549179822206497
2023-01-21 10:39:54.941882: step: 2032/530, loss: 0.06044311821460724
2023-01-21 10:39:56.153176: step: 2036/530, loss: 0.0010472774738445878
2023-01-21 10:39:57.345551: step: 2040/530, loss: 0.06650523841381073
2023-01-21 10:39:58.473523: step: 2044/530, loss: 0.0215531587600708
2023-01-21 10:39:59.689609: step: 2048/530, loss: 0.013756370171904564
2023-01-21 10:40:00.906477: step: 2052/530, loss: 0.2573811411857605
2023-01-21 10:40:02.132001: step: 2056/530, loss: 0.08275695145130157
2023-01-21 10:40:03.317436: step: 2060/530, loss: 0.023038674145936966
2023-01-21 10:40:04.503608: step: 2064/530, loss: 0.011835267767310143
2023-01-21 10:40:05.687123: step: 2068/530, loss: 0.058629799634218216
2023-01-21 10:40:06.833714: step: 2072/530, loss: 0.06076188012957573
2023-01-21 10:40:08.055307: step: 2076/530, loss: 0.08940734714269638
2023-01-21 10:40:09.260268: step: 2080/530, loss: 0.15059271454811096
2023-01-21 10:40:10.398301: step: 2084/530, loss: 0.060669708997011185
2023-01-21 10:40:11.599398: step: 2088/530, loss: 0.032352544367313385
2023-01-21 10:40:12.778791: step: 2092/530, loss: 0.04268999397754669
2023-01-21 10:40:13.941387: step: 2096/530, loss: 0.0324406661093235
2023-01-21 10:40:15.123269: step: 2100/530, loss: 0.013764763250946999
2023-01-21 10:40:16.285083: step: 2104/530, loss: 0.060739897191524506
2023-01-21 10:40:17.431115: step: 2108/530, loss: 0.05356001853942871
2023-01-21 10:40:18.597035: step: 2112/530, loss: 0.025655508041381836
2023-01-21 10:40:19.749812: step: 2116/530, loss: 0.08313503861427307
2023-01-21 10:40:20.946386: step: 2120/530, loss: 0.03332100063562393
==================================================
Loss: 0.071
--------------------
Dev: {'event': {'p': 0.5696078431372549, 'r': 0.7736351531291611, 'f1': 0.6561264822134386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6341030195381883, 'r': 0.821161587119034, 'f1': 0.7156101227762465}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.6440677966101694, 'r': 0.6031746031746031, 'f1': 0.6229508196721311}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.40816326530612246, 'r': 0.5555555555555556, 'f1': 0.47058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:41:07.651624: step: 4/530, loss: 0.024462318047881126
2023-01-21 10:41:08.833094: step: 8/530, loss: 0.03063955530524254
2023-01-21 10:41:09.992210: step: 12/530, loss: 0.059737205505371094
2023-01-21 10:41:11.142746: step: 16/530, loss: 0.0403805747628212
2023-01-21 10:41:12.349244: step: 20/530, loss: 0.06500382721424103
2023-01-21 10:41:13.522252: step: 24/530, loss: 0.04639950022101402
2023-01-21 10:41:14.675863: step: 28/530, loss: 0.019774341955780983
2023-01-21 10:41:15.836891: step: 32/530, loss: 0.0008297919994220138
2023-01-21 10:41:17.007178: step: 36/530, loss: 0.05206584930419922
2023-01-21 10:41:18.193411: step: 40/530, loss: 0.04238710552453995
2023-01-21 10:41:19.360557: step: 44/530, loss: 0.0064720152877271175
2023-01-21 10:41:20.519836: step: 48/530, loss: 0.013050651177763939
2023-01-21 10:41:21.726388: step: 52/530, loss: 0.0268115047365427
2023-01-21 10:41:22.896406: step: 56/530, loss: 0.07062749564647675
2023-01-21 10:41:24.070354: step: 60/530, loss: 0.011003971099853516
2023-01-21 10:41:25.239831: step: 64/530, loss: 0.04203391075134277
2023-01-21 10:41:26.442834: step: 68/530, loss: 0.06764745712280273
2023-01-21 10:41:27.631236: step: 72/530, loss: 0.005010748282074928
2023-01-21 10:41:28.799325: step: 76/530, loss: 0.0831761360168457
2023-01-21 10:41:29.992571: step: 80/530, loss: 0.03619890287518501
2023-01-21 10:41:31.155948: step: 84/530, loss: 0.2614557147026062
2023-01-21 10:41:32.377895: step: 88/530, loss: 0.1391127109527588
2023-01-21 10:41:33.526149: step: 92/530, loss: 0.19704437255859375
2023-01-21 10:41:34.742950: step: 96/530, loss: 0.06112007796764374
2023-01-21 10:41:35.926839: step: 100/530, loss: 0.013515233993530273
2023-01-21 10:41:37.121529: step: 104/530, loss: 0.008998489938676357
2023-01-21 10:41:38.293581: step: 108/530, loss: 0.03343706205487251
2023-01-21 10:41:39.453310: step: 112/530, loss: 0.045110419392585754
2023-01-21 10:41:40.655796: step: 116/530, loss: 0.03110809437930584
2023-01-21 10:41:41.876450: step: 120/530, loss: 0.045696452260017395
2023-01-21 10:41:43.068829: step: 124/530, loss: 0.01875128783285618
2023-01-21 10:41:44.280490: step: 128/530, loss: 0.10756778717041016
2023-01-21 10:41:45.494748: step: 132/530, loss: 0.03836381435394287
2023-01-21 10:41:46.678112: step: 136/530, loss: 0.013095664791762829
2023-01-21 10:41:47.849008: step: 140/530, loss: 0.022331714630126953
2023-01-21 10:41:49.010651: step: 144/530, loss: 0.09740018844604492
2023-01-21 10:41:50.186849: step: 148/530, loss: 0.04224729537963867
2023-01-21 10:41:51.352584: step: 152/530, loss: 0.04394712671637535
2023-01-21 10:41:52.564239: step: 156/530, loss: 0.010960674844682217
2023-01-21 10:41:53.716976: step: 160/530, loss: 0.019486237317323685
2023-01-21 10:41:54.874858: step: 164/530, loss: 0.0024688243865966797
2023-01-21 10:41:56.051131: step: 168/530, loss: 0.12375736236572266
2023-01-21 10:41:57.233058: step: 172/530, loss: 0.3049488067626953
2023-01-21 10:41:58.430605: step: 176/530, loss: 0.034240055829286575
2023-01-21 10:41:59.638862: step: 180/530, loss: 0.0414159782230854
2023-01-21 10:42:00.828536: step: 184/530, loss: 0.004829215817153454
2023-01-21 10:42:02.030399: step: 188/530, loss: 0.024098610505461693
2023-01-21 10:42:03.214951: step: 192/530, loss: 0.003087806748226285
2023-01-21 10:42:04.400879: step: 196/530, loss: 0.00571055430918932
2023-01-21 10:42:05.550575: step: 200/530, loss: 0.1995992660522461
2023-01-21 10:42:06.716681: step: 204/530, loss: 0.00910644605755806
2023-01-21 10:42:07.874959: step: 208/530, loss: 0.01604452170431614
2023-01-21 10:42:09.014870: step: 212/530, loss: 0.008992671966552734
2023-01-21 10:42:10.244347: step: 216/530, loss: 0.002522754715755582
2023-01-21 10:42:11.424700: step: 220/530, loss: 0.008598709478974342
2023-01-21 10:42:12.635297: step: 224/530, loss: 0.003578758332878351
2023-01-21 10:42:13.800408: step: 228/530, loss: 0.4370637834072113
2023-01-21 10:42:14.973426: step: 232/530, loss: 0.042026713490486145
2023-01-21 10:42:16.137005: step: 236/530, loss: 0.010769224725663662
2023-01-21 10:42:17.317276: step: 240/530, loss: 0.21128864586353302
2023-01-21 10:42:18.508444: step: 244/530, loss: 0.03635769337415695
2023-01-21 10:42:19.725451: step: 248/530, loss: 0.43219661712646484
2023-01-21 10:42:20.915993: step: 252/530, loss: 0.017505455762147903
2023-01-21 10:42:22.111229: step: 256/530, loss: 0.10922101140022278
2023-01-21 10:42:23.303013: step: 260/530, loss: 0.12193422019481659
2023-01-21 10:42:24.459257: step: 264/530, loss: 0.01462103147059679
2023-01-21 10:42:25.694185: step: 268/530, loss: 0.0011726856464520097
2023-01-21 10:42:26.854319: step: 272/530, loss: 0.028221370652318
2023-01-21 10:42:28.055306: step: 276/530, loss: 0.06637678295373917
2023-01-21 10:42:29.238175: step: 280/530, loss: 0.030428696423768997
2023-01-21 10:42:30.420148: step: 284/530, loss: 0.0801229476928711
2023-01-21 10:42:31.575776: step: 288/530, loss: 0.06152982637286186
2023-01-21 10:42:32.739381: step: 292/530, loss: 0.0646093338727951
2023-01-21 10:42:33.875244: step: 296/530, loss: 0.20765258371829987
2023-01-21 10:42:35.018584: step: 300/530, loss: 0.0019983293022960424
2023-01-21 10:42:36.218735: step: 304/530, loss: 0.10155663639307022
2023-01-21 10:42:37.439328: step: 308/530, loss: 0.04324297979474068
2023-01-21 10:42:38.608920: step: 312/530, loss: 0.06972108036279678
2023-01-21 10:42:39.783184: step: 316/530, loss: 0.002707576612010598
2023-01-21 10:42:40.942983: step: 320/530, loss: 0.00304832449182868
2023-01-21 10:42:42.125127: step: 324/530, loss: 0.051827143877744675
2023-01-21 10:42:43.303649: step: 328/530, loss: 0.001095676445402205
2023-01-21 10:42:44.482866: step: 332/530, loss: 0.0332825668156147
2023-01-21 10:42:45.675862: step: 336/530, loss: 0.2149837464094162
2023-01-21 10:42:46.818196: step: 340/530, loss: 0.011190223507583141
2023-01-21 10:42:47.966709: step: 344/530, loss: 0.03393860533833504
2023-01-21 10:42:49.126096: step: 348/530, loss: 0.0016100406646728516
2023-01-21 10:42:50.291102: step: 352/530, loss: 0.06353874504566193
2023-01-21 10:42:51.444718: step: 356/530, loss: 0.1105077788233757
2023-01-21 10:42:52.593136: step: 360/530, loss: 0.07435036450624466
2023-01-21 10:42:53.792410: step: 364/530, loss: 0.1421651989221573
2023-01-21 10:42:55.023015: step: 368/530, loss: 0.04711031913757324
2023-01-21 10:42:56.219124: step: 372/530, loss: 0.07570686936378479
2023-01-21 10:42:57.464102: step: 376/530, loss: 0.02117910422384739
2023-01-21 10:42:58.626069: step: 380/530, loss: 0.042621612548828125
2023-01-21 10:42:59.797003: step: 384/530, loss: 0.016769981011748314
2023-01-21 10:43:01.019871: step: 388/530, loss: 0.020130634307861328
2023-01-21 10:43:02.221137: step: 392/530, loss: 0.05519914627075195
2023-01-21 10:43:03.400405: step: 396/530, loss: 0.009591380134224892
2023-01-21 10:43:04.610965: step: 400/530, loss: 0.007009029854089022
2023-01-21 10:43:05.804038: step: 404/530, loss: 0.012728119269013405
2023-01-21 10:43:06.969936: step: 408/530, loss: 0.28795239329338074
2023-01-21 10:43:08.144849: step: 412/530, loss: 0.11612376570701599
2023-01-21 10:43:09.353584: step: 416/530, loss: 0.019542407244443893
2023-01-21 10:43:10.535065: step: 420/530, loss: 0.038088224828243256
2023-01-21 10:43:11.674842: step: 424/530, loss: 0.05726051330566406
2023-01-21 10:43:12.866836: step: 428/530, loss: 0.08280525356531143
2023-01-21 10:43:14.110178: step: 432/530, loss: 0.005053329281508923
2023-01-21 10:43:15.318155: step: 436/530, loss: 0.021277904510498047
2023-01-21 10:43:16.554105: step: 440/530, loss: 0.022490881383419037
2023-01-21 10:43:17.814200: step: 444/530, loss: 0.034426119178533554
2023-01-21 10:43:19.014338: step: 448/530, loss: 0.057691000401973724
2023-01-21 10:43:20.149734: step: 452/530, loss: 0.006224251352250576
2023-01-21 10:43:21.320527: step: 456/530, loss: 0.02741699293255806
2023-01-21 10:43:22.515910: step: 460/530, loss: 0.022504711523652077
2023-01-21 10:43:23.694100: step: 464/530, loss: 0.07245273888111115
2023-01-21 10:43:24.855578: step: 468/530, loss: 0.02529410645365715
2023-01-21 10:43:26.098540: step: 472/530, loss: 0.11218996345996857
2023-01-21 10:43:27.337695: step: 476/530, loss: 0.026621198281645775
2023-01-21 10:43:28.466006: step: 480/530, loss: 0.05628928542137146
2023-01-21 10:43:29.696308: step: 484/530, loss: 0.037410296499729156
2023-01-21 10:43:30.861267: step: 488/530, loss: 0.02455887757241726
2023-01-21 10:43:32.054994: step: 492/530, loss: 0.016309548169374466
2023-01-21 10:43:33.273975: step: 496/530, loss: 0.020999910309910774
2023-01-21 10:43:34.485807: step: 500/530, loss: 0.03327415883541107
2023-01-21 10:43:35.662919: step: 504/530, loss: 0.003995752427726984
2023-01-21 10:43:36.841025: step: 508/530, loss: 0.026255905628204346
2023-01-21 10:43:38.067414: step: 512/530, loss: 0.016110897064208984
2023-01-21 10:43:39.306616: step: 516/530, loss: 0.0024173737037926912
2023-01-21 10:43:40.468165: step: 520/530, loss: 0.04227790981531143
2023-01-21 10:43:41.644030: step: 524/530, loss: 0.1289207488298416
2023-01-21 10:43:42.832552: step: 528/530, loss: 0.008456182666122913
2023-01-21 10:43:44.022624: step: 532/530, loss: 0.027797795832157135
2023-01-21 10:43:45.202600: step: 536/530, loss: 0.3915892541408539
2023-01-21 10:43:46.433875: step: 540/530, loss: 0.05391325801610947
2023-01-21 10:43:47.609704: step: 544/530, loss: 0.03055262565612793
2023-01-21 10:43:48.767168: step: 548/530, loss: 0.034409474581480026
2023-01-21 10:43:49.959604: step: 552/530, loss: 0.05485954508185387
2023-01-21 10:43:51.138578: step: 556/530, loss: 0.004934406373649836
2023-01-21 10:43:52.342101: step: 560/530, loss: 0.020502185449004173
2023-01-21 10:43:53.518933: step: 564/530, loss: 0.0009262085077352822
2023-01-21 10:43:54.666422: step: 568/530, loss: 0.024689245969057083
2023-01-21 10:43:55.845139: step: 572/530, loss: 0.0005736351013183594
2023-01-21 10:43:57.026582: step: 576/530, loss: 0.0663721114397049
2023-01-21 10:43:58.232903: step: 580/530, loss: 0.035083651542663574
2023-01-21 10:43:59.394949: step: 584/530, loss: 0.12485088407993317
2023-01-21 10:44:00.640403: step: 588/530, loss: 0.036413952708244324
2023-01-21 10:44:01.806801: step: 592/530, loss: 0.06369476020336151
2023-01-21 10:44:03.017025: step: 596/530, loss: 0.4337177276611328
2023-01-21 10:44:04.184792: step: 600/530, loss: 0.03700428083539009
2023-01-21 10:44:05.340413: step: 604/530, loss: 0.0948781967163086
2023-01-21 10:44:06.513151: step: 608/530, loss: 0.040070436894893646
2023-01-21 10:44:07.678362: step: 612/530, loss: 0.01448822021484375
2023-01-21 10:44:08.857341: step: 616/530, loss: 0.09405727684497833
2023-01-21 10:44:10.033546: step: 620/530, loss: 0.07676973193883896
2023-01-21 10:44:11.199981: step: 624/530, loss: 0.03575315326452255
2023-01-21 10:44:12.411023: step: 628/530, loss: 0.01336002442985773
2023-01-21 10:44:13.611555: step: 632/530, loss: 0.09158401191234589
2023-01-21 10:44:14.813195: step: 636/530, loss: 0.1506001502275467
2023-01-21 10:44:16.006044: step: 640/530, loss: 0.00036334991455078125
2023-01-21 10:44:17.197357: step: 644/530, loss: 0.017335128039121628
2023-01-21 10:44:18.414645: step: 648/530, loss: 0.07724962383508682
2023-01-21 10:44:19.649887: step: 652/530, loss: 0.03686952590942383
2023-01-21 10:44:20.800536: step: 656/530, loss: 0.007498836610466242
2023-01-21 10:44:21.948216: step: 660/530, loss: 0.0023681640159338713
2023-01-21 10:44:23.130630: step: 664/530, loss: 0.09923629462718964
2023-01-21 10:44:24.357651: step: 668/530, loss: 0.1940900832414627
2023-01-21 10:44:25.510517: step: 672/530, loss: 0.3107105791568756
2023-01-21 10:44:26.727377: step: 676/530, loss: 0.040271710604429245
2023-01-21 10:44:27.897183: step: 680/530, loss: 0.07214327156543732
2023-01-21 10:44:29.101752: step: 684/530, loss: 0.05121020972728729
2023-01-21 10:44:30.324271: step: 688/530, loss: 0.16968250274658203
2023-01-21 10:44:31.497704: step: 692/530, loss: 0.03649099916219711
2023-01-21 10:44:32.652240: step: 696/530, loss: 0.014024162665009499
2023-01-21 10:44:33.831350: step: 700/530, loss: 0.08287516236305237
2023-01-21 10:44:35.007766: step: 704/530, loss: 0.08042984455823898
2023-01-21 10:44:36.159462: step: 708/530, loss: 0.017436029389500618
2023-01-21 10:44:37.325262: step: 712/530, loss: 0.04657535254955292
2023-01-21 10:44:38.554017: step: 716/530, loss: 0.007133293431252241
2023-01-21 10:44:39.753252: step: 720/530, loss: 0.09057764708995819
2023-01-21 10:44:40.887140: step: 724/530, loss: 0.38073357939720154
2023-01-21 10:44:42.043395: step: 728/530, loss: 0.027993202209472656
2023-01-21 10:44:43.279944: step: 732/530, loss: 0.01594400405883789
2023-01-21 10:44:44.462528: step: 736/530, loss: 0.08512210845947266
2023-01-21 10:44:45.624073: step: 740/530, loss: 0.08581963181495667
2023-01-21 10:44:46.793192: step: 744/530, loss: 0.011951255612075329
2023-01-21 10:44:47.937518: step: 748/530, loss: 0.025553178042173386
2023-01-21 10:44:49.079989: step: 752/530, loss: 0.015233802609145641
2023-01-21 10:44:50.268845: step: 756/530, loss: 0.14278145134449005
2023-01-21 10:44:51.424829: step: 760/530, loss: 0.02860584296286106
2023-01-21 10:44:52.641163: step: 764/530, loss: 0.031369470059871674
2023-01-21 10:44:53.848829: step: 768/530, loss: 0.006991863716393709
2023-01-21 10:44:55.043871: step: 772/530, loss: 0.03998298943042755
2023-01-21 10:44:56.226116: step: 776/530, loss: 0.09617214649915695
2023-01-21 10:44:57.387987: step: 780/530, loss: 0.022068094462156296
2023-01-21 10:44:58.562230: step: 784/530, loss: 0.03673537075519562
2023-01-21 10:44:59.788498: step: 788/530, loss: 0.05624890327453613
2023-01-21 10:45:00.978918: step: 792/530, loss: 0.09052152931690216
2023-01-21 10:45:02.175328: step: 796/530, loss: 0.028404809534549713
2023-01-21 10:45:03.369063: step: 800/530, loss: 0.02178099751472473
2023-01-21 10:45:04.569185: step: 804/530, loss: 0.08674298226833344
2023-01-21 10:45:05.709798: step: 808/530, loss: 0.028924845159053802
2023-01-21 10:45:06.879244: step: 812/530, loss: 0.016021061688661575
2023-01-21 10:45:08.044406: step: 816/530, loss: 0.010581493377685547
2023-01-21 10:45:09.232265: step: 820/530, loss: 0.0057665822096168995
2023-01-21 10:45:10.391590: step: 824/530, loss: 0.0019457817543298006
2023-01-21 10:45:11.546555: step: 828/530, loss: 0.025056075304746628
2023-01-21 10:45:12.719113: step: 832/530, loss: 0.01484451349824667
2023-01-21 10:45:13.889577: step: 836/530, loss: 0.01619718223810196
2023-01-21 10:45:15.075616: step: 840/530, loss: 0.6925919055938721
2023-01-21 10:45:16.238928: step: 844/530, loss: 0.022851943969726562
2023-01-21 10:45:17.382926: step: 848/530, loss: 0.025740433484315872
2023-01-21 10:45:18.549983: step: 852/530, loss: 0.02863183058798313
2023-01-21 10:45:19.743319: step: 856/530, loss: 0.04468078538775444
2023-01-21 10:45:20.912003: step: 860/530, loss: 0.6452530026435852
2023-01-21 10:45:22.073432: step: 864/530, loss: 0.10894642025232315
2023-01-21 10:45:23.232619: step: 868/530, loss: 0.03668703883886337
2023-01-21 10:45:24.485011: step: 872/530, loss: 0.019786452874541283
2023-01-21 10:45:25.650246: step: 876/530, loss: 0.178480327129364
2023-01-21 10:45:26.821472: step: 880/530, loss: 0.041542910039424896
2023-01-21 10:45:28.013548: step: 884/530, loss: 0.06218691170215607
2023-01-21 10:45:29.198619: step: 888/530, loss: 0.13452640175819397
2023-01-21 10:45:30.369719: step: 892/530, loss: 0.00818262156099081
2023-01-21 10:45:31.510737: step: 896/530, loss: 0.0510527640581131
2023-01-21 10:45:32.686806: step: 900/530, loss: 0.015603447332978249
2023-01-21 10:45:33.847180: step: 904/530, loss: 0.01901698112487793
2023-01-21 10:45:34.984528: step: 908/530, loss: 0.025200653821229935
2023-01-21 10:45:36.200035: step: 912/530, loss: 0.21242503821849823
2023-01-21 10:45:37.353339: step: 916/530, loss: 0.09054295718669891
2023-01-21 10:45:38.577403: step: 920/530, loss: 0.02290968969464302
2023-01-21 10:45:39.745884: step: 924/530, loss: 0.006038284860551357
2023-01-21 10:45:40.951743: step: 928/530, loss: 0.03223858028650284
2023-01-21 10:45:42.144385: step: 932/530, loss: 0.01874389685690403
2023-01-21 10:45:43.314588: step: 936/530, loss: 0.01884441450238228
2023-01-21 10:45:44.492215: step: 940/530, loss: 0.1289457380771637
2023-01-21 10:45:45.670961: step: 944/530, loss: 0.027230119332671165
2023-01-21 10:45:46.828844: step: 948/530, loss: 0.01578826829791069
2023-01-21 10:45:47.993275: step: 952/530, loss: 0.03889884799718857
2023-01-21 10:45:49.193773: step: 956/530, loss: 0.0486997589468956
2023-01-21 10:45:50.349959: step: 960/530, loss: 0.015480756759643555
2023-01-21 10:45:51.491530: step: 964/530, loss: 0.030515480786561966
2023-01-21 10:45:52.687416: step: 968/530, loss: 0.01985769346356392
2023-01-21 10:45:53.860870: step: 972/530, loss: 0.010434722527861595
2023-01-21 10:45:55.015659: step: 976/530, loss: 0.03141918033361435
2023-01-21 10:45:56.184495: step: 980/530, loss: 0.11138935387134552
2023-01-21 10:45:57.374746: step: 984/530, loss: 0.09267683327198029
2023-01-21 10:45:58.599916: step: 988/530, loss: 0.1321854591369629
2023-01-21 10:45:59.759556: step: 992/530, loss: 0.03175229951739311
2023-01-21 10:46:00.901405: step: 996/530, loss: 0.0025769234634935856
2023-01-21 10:46:02.104080: step: 1000/530, loss: 0.044530682265758514
2023-01-21 10:46:03.300483: step: 1004/530, loss: 0.06598120182752609
2023-01-21 10:46:04.461448: step: 1008/530, loss: 0.04920005798339844
2023-01-21 10:46:05.631684: step: 1012/530, loss: 0.11480160057544708
2023-01-21 10:46:06.813608: step: 1016/530, loss: 0.059511661529541016
2023-01-21 10:46:08.001134: step: 1020/530, loss: 0.05797595903277397
2023-01-21 10:46:09.140503: step: 1024/530, loss: 0.3179432153701782
2023-01-21 10:46:10.329026: step: 1028/530, loss: 0.0350956916809082
2023-01-21 10:46:11.552230: step: 1032/530, loss: 0.05184021592140198
2023-01-21 10:46:12.707306: step: 1036/530, loss: 0.6203622221946716
2023-01-21 10:46:13.890296: step: 1040/530, loss: 0.027121830731630325
2023-01-21 10:46:15.084255: step: 1044/530, loss: 0.028993798419833183
2023-01-21 10:46:16.268622: step: 1048/530, loss: 0.009817314334213734
2023-01-21 10:46:17.488298: step: 1052/530, loss: 0.007053375244140625
2023-01-21 10:46:18.651652: step: 1056/530, loss: 0.0008881569374352694
2023-01-21 10:46:19.844046: step: 1060/530, loss: 0.00042247772216796875
2023-01-21 10:46:21.024469: step: 1064/530, loss: 0.026148509234189987
2023-01-21 10:46:22.186281: step: 1068/530, loss: 0.03257717937231064
2023-01-21 10:46:23.370686: step: 1072/530, loss: 0.028539754450321198
2023-01-21 10:46:24.565470: step: 1076/530, loss: 0.029815007001161575
2023-01-21 10:46:25.769935: step: 1080/530, loss: 0.042229365557432175
2023-01-21 10:46:26.962027: step: 1084/530, loss: 0.021835900843143463
2023-01-21 10:46:28.148950: step: 1088/530, loss: 0.022199153900146484
2023-01-21 10:46:29.418100: step: 1092/530, loss: 0.059502504765987396
2023-01-21 10:46:30.555859: step: 1096/530, loss: 0.013970565982162952
2023-01-21 10:46:31.745990: step: 1100/530, loss: 0.037641432136297226
2023-01-21 10:46:32.908545: step: 1104/530, loss: 0.02053070068359375
2023-01-21 10:46:34.127573: step: 1108/530, loss: 0.06871071457862854
2023-01-21 10:46:35.310553: step: 1112/530, loss: 0.028432369232177734
2023-01-21 10:46:36.484480: step: 1116/530, loss: 0.0015053749084472656
2023-01-21 10:46:37.695472: step: 1120/530, loss: 0.03856716305017471
2023-01-21 10:46:38.852811: step: 1124/530, loss: 0.3286478817462921
2023-01-21 10:46:40.037432: step: 1128/530, loss: 0.09284524619579315
2023-01-21 10:46:41.211471: step: 1132/530, loss: 0.1529906690120697
2023-01-21 10:46:42.479938: step: 1136/530, loss: 0.05006694793701172
2023-01-21 10:46:43.679147: step: 1140/530, loss: 0.03011941909790039
2023-01-21 10:46:44.855752: step: 1144/530, loss: 0.027724076062440872
2023-01-21 10:46:46.042701: step: 1148/530, loss: 0.010067653842270374
2023-01-21 10:46:47.220704: step: 1152/530, loss: 0.08774032443761826
2023-01-21 10:46:48.392915: step: 1156/530, loss: 0.014690971933305264
2023-01-21 10:46:49.570865: step: 1160/530, loss: 0.04390373453497887
2023-01-21 10:46:50.722873: step: 1164/530, loss: 0.014396476559340954
2023-01-21 10:46:51.910514: step: 1168/530, loss: 0.0015263557434082031
2023-01-21 10:46:53.081526: step: 1172/530, loss: 0.3092660903930664
2023-01-21 10:46:54.236261: step: 1176/530, loss: 0.07040061801671982
2023-01-21 10:46:55.401762: step: 1180/530, loss: 0.06930504739284515
2023-01-21 10:46:56.619288: step: 1184/530, loss: 0.12530136108398438
2023-01-21 10:46:57.811257: step: 1188/530, loss: 0.02728099748492241
2023-01-21 10:46:59.060313: step: 1192/530, loss: 0.023624612018465996
2023-01-21 10:47:00.254278: step: 1196/530, loss: 0.011436653323471546
2023-01-21 10:47:01.453426: step: 1200/530, loss: 0.13145150244235992
2023-01-21 10:47:02.674682: step: 1204/530, loss: 0.027723979204893112
2023-01-21 10:47:03.849308: step: 1208/530, loss: 0.03562593460083008
2023-01-21 10:47:05.040183: step: 1212/530, loss: 0.03561554104089737
2023-01-21 10:47:06.267553: step: 1216/530, loss: 0.14709243178367615
2023-01-21 10:47:07.415397: step: 1220/530, loss: 0.018868446350097656
2023-01-21 10:47:08.595600: step: 1224/530, loss: 0.12849688529968262
2023-01-21 10:47:09.688215: step: 1228/530, loss: 0.24895787239074707
2023-01-21 10:47:10.876006: step: 1232/530, loss: 0.057883549481630325
2023-01-21 10:47:12.054831: step: 1236/530, loss: 0.01187057513743639
2023-01-21 10:47:13.289477: step: 1240/530, loss: 0.08269357681274414
2023-01-21 10:47:14.465812: step: 1244/530, loss: 0.13768616318702698
2023-01-21 10:47:15.616770: step: 1248/530, loss: 0.058997154235839844
2023-01-21 10:47:16.742302: step: 1252/530, loss: 0.006998920813202858
2023-01-21 10:47:17.918516: step: 1256/530, loss: 0.0534726157784462
2023-01-21 10:47:19.107571: step: 1260/530, loss: 0.06270293891429901
2023-01-21 10:47:20.337340: step: 1264/530, loss: 0.03356628492474556
2023-01-21 10:47:21.526523: step: 1268/530, loss: 0.04385986551642418
2023-01-21 10:47:22.732955: step: 1272/530, loss: 0.04401206970214844
2023-01-21 10:47:23.917444: step: 1276/530, loss: 0.05171527713537216
2023-01-21 10:47:25.121430: step: 1280/530, loss: 0.0045986175537109375
2023-01-21 10:47:26.285851: step: 1284/530, loss: 0.11496009677648544
2023-01-21 10:47:27.486391: step: 1288/530, loss: 0.49679192900657654
2023-01-21 10:47:28.694167: step: 1292/530, loss: 0.053171444684267044
2023-01-21 10:47:29.827004: step: 1296/530, loss: 0.0331995002925396
2023-01-21 10:47:31.014771: step: 1300/530, loss: 0.04196282476186752
2023-01-21 10:47:32.196225: step: 1304/530, loss: 0.046031951904296875
2023-01-21 10:47:33.392580: step: 1308/530, loss: 0.05271158367395401
2023-01-21 10:47:34.525297: step: 1312/530, loss: 0.014488077722489834
2023-01-21 10:47:35.716058: step: 1316/530, loss: 0.12147287279367447
2023-01-21 10:47:36.874731: step: 1320/530, loss: 0.015043068677186966
2023-01-21 10:47:38.098548: step: 1324/530, loss: 0.007552719675004482
2023-01-21 10:47:39.281002: step: 1328/530, loss: 0.0784931629896164
2023-01-21 10:47:40.470145: step: 1332/530, loss: 0.03740081936120987
2023-01-21 10:47:41.683530: step: 1336/530, loss: 0.08213372528553009
2023-01-21 10:47:42.871907: step: 1340/530, loss: 0.0034474849235266447
2023-01-21 10:47:44.042701: step: 1344/530, loss: 0.023669052869081497
2023-01-21 10:47:45.221034: step: 1348/530, loss: 0.02259860187768936
2023-01-21 10:47:46.380257: step: 1352/530, loss: 0.0017702102195471525
2023-01-21 10:47:47.599757: step: 1356/530, loss: 0.01809997484087944
2023-01-21 10:47:48.751071: step: 1360/530, loss: 0.009166574105620384
2023-01-21 10:47:49.952325: step: 1364/530, loss: 0.0018199920887127519
2023-01-21 10:47:51.145679: step: 1368/530, loss: 0.036254025995731354
2023-01-21 10:47:52.304747: step: 1372/530, loss: 0.14995098114013672
2023-01-21 10:47:53.481004: step: 1376/530, loss: 0.049860481172800064
2023-01-21 10:47:54.672467: step: 1380/530, loss: 0.09892406314611435
2023-01-21 10:47:55.891232: step: 1384/530, loss: 0.051728107035160065
2023-01-21 10:47:57.073198: step: 1388/530, loss: 0.03571796417236328
2023-01-21 10:47:58.316699: step: 1392/530, loss: 0.01592540740966797
2023-01-21 10:47:59.508477: step: 1396/530, loss: 0.10455093532800674
2023-01-21 10:48:00.700930: step: 1400/530, loss: 0.0336456298828125
2023-01-21 10:48:01.921770: step: 1404/530, loss: 0.00734257698059082
2023-01-21 10:48:03.048557: step: 1408/530, loss: 0.0019296170212328434
2023-01-21 10:48:04.258043: step: 1412/530, loss: 0.04238548129796982
2023-01-21 10:48:05.422521: step: 1416/530, loss: 0.01978015899658203
2023-01-21 10:48:06.614702: step: 1420/530, loss: 0.003333187196403742
2023-01-21 10:48:07.785914: step: 1424/530, loss: 0.032706644386053085
2023-01-21 10:48:08.959568: step: 1428/530, loss: 0.03811168670654297
2023-01-21 10:48:10.165077: step: 1432/530, loss: 0.04100990295410156
2023-01-21 10:48:11.354672: step: 1436/530, loss: 0.04443030431866646
2023-01-21 10:48:12.555730: step: 1440/530, loss: 0.11495628952980042
2023-01-21 10:48:13.737172: step: 1444/530, loss: 0.06092806160449982
2023-01-21 10:48:14.985504: step: 1448/530, loss: 0.005843162536621094
2023-01-21 10:48:16.172981: step: 1452/530, loss: 0.01743488386273384
2023-01-21 10:48:17.389725: step: 1456/530, loss: 0.01626911200582981
2023-01-21 10:48:18.552947: step: 1460/530, loss: 0.0010963440872728825
2023-01-21 10:48:19.685480: step: 1464/530, loss: 0.12800416350364685
2023-01-21 10:48:20.859057: step: 1468/530, loss: 0.1337384283542633
2023-01-21 10:48:22.034965: step: 1472/530, loss: 0.08809986710548401
2023-01-21 10:48:23.206189: step: 1476/530, loss: 0.009561014361679554
2023-01-21 10:48:24.384430: step: 1480/530, loss: 0.008875560946762562
2023-01-21 10:48:25.632139: step: 1484/530, loss: 0.05440826714038849
2023-01-21 10:48:26.813573: step: 1488/530, loss: 0.006898260209709406
2023-01-21 10:48:27.958976: step: 1492/530, loss: 0.0025392533279955387
2023-01-21 10:48:29.134086: step: 1496/530, loss: 0.04414825513958931
2023-01-21 10:48:30.328082: step: 1500/530, loss: 0.06434217095375061
2023-01-21 10:48:31.479344: step: 1504/530, loss: 0.0708681121468544
2023-01-21 10:48:32.659178: step: 1508/530, loss: 0.010440731421113014
2023-01-21 10:48:33.825795: step: 1512/530, loss: 0.020683003589510918
2023-01-21 10:48:34.987214: step: 1516/530, loss: 0.042055319994688034
2023-01-21 10:48:36.157986: step: 1520/530, loss: 0.002170658204704523
2023-01-21 10:48:37.344216: step: 1524/530, loss: 0.007885932922363281
2023-01-21 10:48:38.551469: step: 1528/530, loss: 0.060408446937799454
2023-01-21 10:48:39.744360: step: 1532/530, loss: 0.30674201250076294
2023-01-21 10:48:40.932110: step: 1536/530, loss: 0.045743562281131744
2023-01-21 10:48:42.176532: step: 1540/530, loss: 0.003758716629818082
2023-01-21 10:48:43.328921: step: 1544/530, loss: 0.20081281661987305
2023-01-21 10:48:44.546085: step: 1548/530, loss: 0.0011451721657067537
2023-01-21 10:48:45.704820: step: 1552/530, loss: 0.010481643490493298
2023-01-21 10:48:46.904738: step: 1556/530, loss: 0.05293922498822212
2023-01-21 10:48:48.071718: step: 1560/530, loss: 0.05506305396556854
2023-01-21 10:48:49.250735: step: 1564/530, loss: 0.2520160675048828
2023-01-21 10:48:50.395573: step: 1568/530, loss: 0.008435058407485485
2023-01-21 10:48:51.586713: step: 1572/530, loss: 0.11139583587646484
2023-01-21 10:48:52.754560: step: 1576/530, loss: 0.07586231827735901
2023-01-21 10:48:53.949876: step: 1580/530, loss: 0.05974731594324112
2023-01-21 10:48:55.152105: step: 1584/530, loss: 0.137461856007576
2023-01-21 10:48:56.311649: step: 1588/530, loss: 0.003940105438232422
2023-01-21 10:48:57.502947: step: 1592/530, loss: 0.23871584236621857
2023-01-21 10:48:58.656973: step: 1596/530, loss: 0.03643636777997017
2023-01-21 10:48:59.851088: step: 1600/530, loss: 0.08828411996364594
2023-01-21 10:49:00.998121: step: 1604/530, loss: 0.022249555215239525
2023-01-21 10:49:02.185547: step: 1608/530, loss: 0.03384866565465927
2023-01-21 10:49:03.393424: step: 1612/530, loss: 0.024793434888124466
2023-01-21 10:49:04.555737: step: 1616/530, loss: 0.026638220995664597
2023-01-21 10:49:05.711216: step: 1620/530, loss: 0.03290840610861778
2023-01-21 10:49:06.899768: step: 1624/530, loss: 0.0743323341012001
2023-01-21 10:49:08.062889: step: 1628/530, loss: 0.007764172274619341
2023-01-21 10:49:09.230707: step: 1632/530, loss: 0.023153383284807205
2023-01-21 10:49:10.395244: step: 1636/530, loss: 0.03600792959332466
2023-01-21 10:49:11.592938: step: 1640/530, loss: 0.019744111225008965
2023-01-21 10:49:12.768093: step: 1644/530, loss: 0.7204625606536865
2023-01-21 10:49:13.966014: step: 1648/530, loss: 0.009069632738828659
2023-01-21 10:49:15.130231: step: 1652/530, loss: 0.031119156628847122
2023-01-21 10:49:16.299612: step: 1656/530, loss: 0.06660900264978409
2023-01-21 10:49:17.505200: step: 1660/530, loss: 0.03832855448126793
2023-01-21 10:49:18.659837: step: 1664/530, loss: 0.003734111785888672
2023-01-21 10:49:19.810439: step: 1668/530, loss: 0.019800137728452682
2023-01-21 10:49:20.979539: step: 1672/530, loss: 0.030502988025546074
2023-01-21 10:49:22.156786: step: 1676/530, loss: 0.025876712054014206
2023-01-21 10:49:23.289475: step: 1680/530, loss: 1.0191471576690674
2023-01-21 10:49:24.466460: step: 1684/530, loss: 0.2799045443534851
2023-01-21 10:49:25.643299: step: 1688/530, loss: 0.00604515103623271
2023-01-21 10:49:26.811105: step: 1692/530, loss: 0.03718767315149307
2023-01-21 10:49:27.980536: step: 1696/530, loss: 0.0032772065605968237
2023-01-21 10:49:29.198429: step: 1700/530, loss: 0.004082870204001665
2023-01-21 10:49:30.381765: step: 1704/530, loss: 0.017443466931581497
2023-01-21 10:49:31.555080: step: 1708/530, loss: 0.01168594416230917
2023-01-21 10:49:32.698276: step: 1712/530, loss: 0.04617633670568466
2023-01-21 10:49:33.907858: step: 1716/530, loss: 0.007175922393798828
2023-01-21 10:49:35.083783: step: 1720/530, loss: 0.06403732299804688
2023-01-21 10:49:36.257522: step: 1724/530, loss: 0.05706648901104927
2023-01-21 10:49:37.430897: step: 1728/530, loss: 0.06196889653801918
2023-01-21 10:49:38.638557: step: 1732/530, loss: 0.03970861807465553
2023-01-21 10:49:39.831048: step: 1736/530, loss: 0.037124063819646835
2023-01-21 10:49:41.019387: step: 1740/530, loss: 0.1004679948091507
2023-01-21 10:49:42.244489: step: 1744/530, loss: 0.05444078519940376
2023-01-21 10:49:43.418572: step: 1748/530, loss: 0.001445674803107977
2023-01-21 10:49:44.580620: step: 1752/530, loss: 0.0017767907120287418
2023-01-21 10:49:45.787687: step: 1756/530, loss: 0.10406875610351562
2023-01-21 10:49:46.969520: step: 1760/530, loss: 0.06995449215173721
2023-01-21 10:49:48.153262: step: 1764/530, loss: 0.048447802662849426
2023-01-21 10:49:49.314286: step: 1768/530, loss: 0.006215381436049938
2023-01-21 10:49:50.527064: step: 1772/530, loss: 0.017821885645389557
2023-01-21 10:49:51.664418: step: 1776/530, loss: 0.06677103042602539
2023-01-21 10:49:52.842716: step: 1780/530, loss: 0.04962186887860298
2023-01-21 10:49:54.012415: step: 1784/530, loss: 0.05091610178351402
2023-01-21 10:49:55.208709: step: 1788/530, loss: 0.0028972148429602385
2023-01-21 10:49:56.393012: step: 1792/530, loss: 0.04090538248419762
2023-01-21 10:49:57.590949: step: 1796/530, loss: 0.08588724583387375
2023-01-21 10:49:58.761388: step: 1800/530, loss: 0.03419294208288193
2023-01-21 10:50:00.002102: step: 1804/530, loss: 0.07059574872255325
2023-01-21 10:50:01.230328: step: 1808/530, loss: 0.0495111458003521
2023-01-21 10:50:02.371828: step: 1812/530, loss: 0.025900650769472122
2023-01-21 10:50:03.532308: step: 1816/530, loss: 0.007955646142363548
2023-01-21 10:50:04.689524: step: 1820/530, loss: 0.25032874941825867
2023-01-21 10:50:05.863403: step: 1824/530, loss: 0.04907378926873207
2023-01-21 10:50:06.988787: step: 1828/530, loss: 0.046205878257751465
2023-01-21 10:50:08.185456: step: 1832/530, loss: 0.012538003735244274
2023-01-21 10:50:09.382697: step: 1836/530, loss: 0.02088012732565403
2023-01-21 10:50:10.550567: step: 1840/530, loss: 0.11699561774730682
2023-01-21 10:50:11.706810: step: 1844/530, loss: 0.07212080806493759
2023-01-21 10:50:12.884200: step: 1848/530, loss: 0.05207099765539169
2023-01-21 10:50:14.066883: step: 1852/530, loss: 0.2666931748390198
2023-01-21 10:50:15.281624: step: 1856/530, loss: 0.00173187255859375
2023-01-21 10:50:16.457727: step: 1860/530, loss: 0.014516020193696022
2023-01-21 10:50:17.614652: step: 1864/530, loss: 0.028429605066776276
2023-01-21 10:50:18.789312: step: 1868/530, loss: 0.11363282054662704
2023-01-21 10:50:19.991577: step: 1872/530, loss: 0.0284334197640419
2023-01-21 10:50:21.223634: step: 1876/530, loss: 0.12160587310791016
2023-01-21 10:50:22.392355: step: 1880/530, loss: 0.005965805146843195
2023-01-21 10:50:23.592546: step: 1884/530, loss: 0.02010345458984375
2023-01-21 10:50:24.806958: step: 1888/530, loss: 0.16943226754665375
2023-01-21 10:50:25.970810: step: 1892/530, loss: 0.04083843156695366
2023-01-21 10:50:27.135395: step: 1896/530, loss: 0.02916259877383709
2023-01-21 10:50:28.350352: step: 1900/530, loss: 0.041333675384521484
2023-01-21 10:50:29.530941: step: 1904/530, loss: 0.029887771233916283
2023-01-21 10:50:30.722626: step: 1908/530, loss: 0.005649471189826727
2023-01-21 10:50:31.943371: step: 1912/530, loss: 0.004815483465790749
2023-01-21 10:50:33.087465: step: 1916/530, loss: 0.05436267703771591
2023-01-21 10:50:34.268831: step: 1920/530, loss: 0.030610179528594017
2023-01-21 10:50:35.456445: step: 1924/530, loss: 0.0032792091369628906
2023-01-21 10:50:36.680087: step: 1928/530, loss: 0.10347528755664825
2023-01-21 10:50:37.855831: step: 1932/530, loss: 0.0426909439265728
2023-01-21 10:50:39.060361: step: 1936/530, loss: 0.029197216033935547
2023-01-21 10:50:40.226312: step: 1940/530, loss: 0.03308119997382164
2023-01-21 10:50:41.414464: step: 1944/530, loss: 0.02516203001141548
2023-01-21 10:50:42.593286: step: 1948/530, loss: 0.003335380693897605
2023-01-21 10:50:43.762927: step: 1952/530, loss: 0.08260011672973633
2023-01-21 10:50:44.996085: step: 1956/530, loss: 0.03425408899784088
2023-01-21 10:50:46.220222: step: 1960/530, loss: 0.04768028110265732
2023-01-21 10:50:47.396605: step: 1964/530, loss: 0.0680142417550087
2023-01-21 10:50:48.594443: step: 1968/530, loss: 0.12147045135498047
2023-01-21 10:50:49.780040: step: 1972/530, loss: 0.014282465912401676
2023-01-21 10:50:50.944131: step: 1976/530, loss: 0.014441777020692825
2023-01-21 10:50:52.080349: step: 1980/530, loss: 0.029783153906464577
2023-01-21 10:50:53.262881: step: 1984/530, loss: 0.07527198642492294
2023-01-21 10:50:54.448201: step: 1988/530, loss: 0.1627923995256424
2023-01-21 10:50:55.634302: step: 1992/530, loss: 0.01703643798828125
2023-01-21 10:50:56.827658: step: 1996/530, loss: 0.04784107208251953
2023-01-21 10:50:57.979555: step: 2000/530, loss: 0.03609418869018555
2023-01-21 10:50:59.168724: step: 2004/530, loss: 0.00937950611114502
2023-01-21 10:51:00.350240: step: 2008/530, loss: 0.04931154474616051
2023-01-21 10:51:01.558336: step: 2012/530, loss: 0.049268245697021484
2023-01-21 10:51:02.754080: step: 2016/530, loss: 0.2753294110298157
2023-01-21 10:51:03.953699: step: 2020/530, loss: 0.024842072278261185
2023-01-21 10:51:05.139134: step: 2024/530, loss: 0.007775783538818359
2023-01-21 10:51:06.267678: step: 2028/530, loss: 0.04651632159948349
2023-01-21 10:51:07.470768: step: 2032/530, loss: 0.015264129266142845
2023-01-21 10:51:08.658686: step: 2036/530, loss: 0.05563822016119957
2023-01-21 10:51:09.828544: step: 2040/530, loss: 0.020015764981508255
2023-01-21 10:51:11.021332: step: 2044/530, loss: 0.023726463317871094
2023-01-21 10:51:12.227120: step: 2048/530, loss: 0.06632719188928604
2023-01-21 10:51:13.375514: step: 2052/530, loss: 0.01572251319885254
2023-01-21 10:51:14.521846: step: 2056/530, loss: 0.004071235656738281
2023-01-21 10:51:15.678216: step: 2060/530, loss: 0.03538046032190323
2023-01-21 10:51:16.880150: step: 2064/530, loss: 0.021763324737548828
2023-01-21 10:51:18.059354: step: 2068/530, loss: 0.11623821407556534
2023-01-21 10:51:19.289606: step: 2072/530, loss: 0.07619114220142365
2023-01-21 10:51:20.551184: step: 2076/530, loss: 0.002701377961784601
2023-01-21 10:51:21.767064: step: 2080/530, loss: 0.10796938091516495
2023-01-21 10:51:22.981523: step: 2084/530, loss: 0.015152215957641602
2023-01-21 10:51:24.136667: step: 2088/530, loss: 0.06803421676158905
2023-01-21 10:51:25.318762: step: 2092/530, loss: 0.0671718567609787
2023-01-21 10:51:26.511296: step: 2096/530, loss: 0.026571083813905716
2023-01-21 10:51:27.688348: step: 2100/530, loss: 0.004444885067641735
2023-01-21 10:51:28.928591: step: 2104/530, loss: 0.08730068057775497
2023-01-21 10:51:30.157573: step: 2108/530, loss: 0.028656387701630592
2023-01-21 10:51:31.298989: step: 2112/530, loss: 0.19828014075756073
2023-01-21 10:51:32.500218: step: 2116/530, loss: 0.11132355034351349
2023-01-21 10:51:33.693318: step: 2120/530, loss: 0.08427419513463974
==================================================
Loss: 0.063
--------------------
Dev: {'event': {'p': 0.5873493975903614, 'r': 0.7789613848202397, 'f1': 0.6697195191757298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6369020501138952, 'r': 0.8039102932719954, 'f1': 0.7107269954245043}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5280898876404494, 'r': 0.8703703703703703, 'f1': 0.6573426573426573}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.5230769230769231, 'r': 0.5396825396825397, 'f1': 0.53125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.44, 'r': 0.6111111111111112, 'f1': 0.5116279069767442}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:52:19.796207: step: 4/530, loss: 0.10004901885986328
2023-01-21 10:52:20.958326: step: 8/530, loss: 0.0032314301934093237
2023-01-21 10:52:22.267248: step: 12/530, loss: 0.01663847081363201
2023-01-21 10:52:23.473388: step: 16/530, loss: 0.050066664814949036
2023-01-21 10:52:24.650339: step: 20/530, loss: 0.006414985749870539
2023-01-21 10:52:25.805571: step: 24/530, loss: 0.03378744050860405
2023-01-21 10:52:27.010416: step: 28/530, loss: 0.05332126468420029
2023-01-21 10:52:28.213917: step: 32/530, loss: 0.018777180463075638
2023-01-21 10:52:29.351078: step: 36/530, loss: 0.022528838366270065
2023-01-21 10:52:30.547613: step: 40/530, loss: 0.0068946839310228825
2023-01-21 10:52:31.718070: step: 44/530, loss: 0.0207716953009367
2023-01-21 10:52:32.879616: step: 48/530, loss: 0.04573841020464897
2023-01-21 10:52:34.070955: step: 52/530, loss: 0.0004903793451376259
2023-01-21 10:52:35.285834: step: 56/530, loss: 0.05951228365302086
2023-01-21 10:52:36.441671: step: 60/530, loss: 0.027296876534819603
2023-01-21 10:52:37.659858: step: 64/530, loss: 0.13644734025001526
2023-01-21 10:52:38.828982: step: 68/530, loss: 0.08791694790124893
2023-01-21 10:52:40.007954: step: 72/530, loss: 0.0009687423589639366
2023-01-21 10:52:41.130831: step: 76/530, loss: 0.016785193234682083
2023-01-21 10:52:42.335831: step: 80/530, loss: 0.0002639770391397178
2023-01-21 10:52:43.544026: step: 84/530, loss: 0.06766338646411896
2023-01-21 10:52:44.727512: step: 88/530, loss: 0.018208885565400124
2023-01-21 10:52:45.933688: step: 92/530, loss: 0.003375721164047718
2023-01-21 10:52:47.104636: step: 96/530, loss: 0.018230963498353958
2023-01-21 10:52:48.284045: step: 100/530, loss: 0.009283924475312233
2023-01-21 10:52:49.398939: step: 104/530, loss: 0.007732391823083162
2023-01-21 10:52:50.591139: step: 108/530, loss: 0.004638290032744408
2023-01-21 10:52:51.750542: step: 112/530, loss: 0.015256499871611595
2023-01-21 10:52:52.921080: step: 116/530, loss: 0.02787327766418457
2023-01-21 10:52:54.098421: step: 120/530, loss: 0.053221896290779114
2023-01-21 10:52:55.275213: step: 124/530, loss: 0.4339471757411957
2023-01-21 10:52:56.476328: step: 128/530, loss: 0.013323593884706497
2023-01-21 10:52:57.639652: step: 132/530, loss: 0.013069534674286842
2023-01-21 10:52:58.831149: step: 136/530, loss: 0.011860084719955921
2023-01-21 10:52:59.965834: step: 140/530, loss: 0.00010271072096657008
2023-01-21 10:53:01.115338: step: 144/530, loss: 7.853508577682078e-05
2023-01-21 10:53:02.342531: step: 148/530, loss: 0.072441965341568
2023-01-21 10:53:03.503899: step: 152/530, loss: 0.010389899834990501
2023-01-21 10:53:04.667717: step: 156/530, loss: 0.001139831612817943
2023-01-21 10:53:05.833622: step: 160/530, loss: 0.002760601229965687
2023-01-21 10:53:07.004067: step: 164/530, loss: 0.013921737670898438
2023-01-21 10:53:08.151281: step: 168/530, loss: 0.060849953442811966
2023-01-21 10:53:09.354436: step: 172/530, loss: 0.0037219999358057976
2023-01-21 10:53:10.537587: step: 176/530, loss: 0.014375877566635609
2023-01-21 10:53:11.800655: step: 180/530, loss: 0.006615448277443647
2023-01-21 10:53:12.976257: step: 184/530, loss: 0.005596637260168791
2023-01-21 10:53:14.118235: step: 188/530, loss: 0.008048344403505325
2023-01-21 10:53:15.287167: step: 192/530, loss: 0.0310808178037405
2023-01-21 10:53:16.435196: step: 196/530, loss: 0.01149530429393053
2023-01-21 10:53:17.624917: step: 200/530, loss: 0.522605836391449
2023-01-21 10:53:18.800223: step: 204/530, loss: 0.004442119505256414
2023-01-21 10:53:19.990324: step: 208/530, loss: 0.024345552548766136
2023-01-21 10:53:21.166855: step: 212/530, loss: 0.03595466911792755
2023-01-21 10:53:22.385975: step: 216/530, loss: 0.028559112921357155
2023-01-21 10:53:23.658344: step: 220/530, loss: 0.008593273349106312
2023-01-21 10:53:24.819125: step: 224/530, loss: 0.005396169610321522
2023-01-21 10:53:26.020369: step: 228/530, loss: 0.002710628556087613
2023-01-21 10:53:27.201599: step: 232/530, loss: 0.007542658131569624
2023-01-21 10:53:28.417534: step: 236/530, loss: 0.02953367307782173
2023-01-21 10:53:29.593063: step: 240/530, loss: 0.06640129536390305
2023-01-21 10:53:30.818522: step: 244/530, loss: 0.24774475395679474
2023-01-21 10:53:32.029661: step: 248/530, loss: 0.17289294302463531
2023-01-21 10:53:33.195757: step: 252/530, loss: 0.012560653500258923
2023-01-21 10:53:34.371668: step: 256/530, loss: 0.029000377282500267
2023-01-21 10:53:35.522133: step: 260/530, loss: 0.2869914174079895
2023-01-21 10:53:36.696212: step: 264/530, loss: 0.0010747909545898438
2023-01-21 10:53:37.863396: step: 268/530, loss: 0.012018776498734951
2023-01-21 10:53:39.011924: step: 272/530, loss: 0.01170129794627428
2023-01-21 10:53:40.196972: step: 276/530, loss: 0.019718552008271217
2023-01-21 10:53:41.383985: step: 280/530, loss: 0.017036771401762962
2023-01-21 10:53:42.592672: step: 284/530, loss: 0.05658683925867081
2023-01-21 10:53:43.750389: step: 288/530, loss: 0.010839272290468216
2023-01-21 10:53:44.899886: step: 292/530, loss: 0.0033249855041503906
2023-01-21 10:53:46.047743: step: 296/530, loss: 0.03097391128540039
2023-01-21 10:53:47.220127: step: 300/530, loss: 0.10082073509693146
2023-01-21 10:53:48.425346: step: 304/530, loss: 0.019155312329530716
2023-01-21 10:53:49.584721: step: 308/530, loss: 0.018297338858246803
2023-01-21 10:53:50.805730: step: 312/530, loss: 0.0992591381072998
2023-01-21 10:53:51.948255: step: 316/530, loss: 0.04467001557350159
2023-01-21 10:53:53.111890: step: 320/530, loss: 0.02350912056863308
2023-01-21 10:53:54.305894: step: 324/530, loss: 0.02422504313290119
2023-01-21 10:53:55.544189: step: 328/530, loss: 0.14950066804885864
2023-01-21 10:53:56.723393: step: 332/530, loss: 0.00955190695822239
2023-01-21 10:53:57.944900: step: 336/530, loss: 0.2741892337799072
2023-01-21 10:53:59.162798: step: 340/530, loss: 0.012942124158143997
2023-01-21 10:54:00.391548: step: 344/530, loss: 0.07776851952075958
2023-01-21 10:54:01.582240: step: 348/530, loss: 0.04230346530675888
2023-01-21 10:54:02.809201: step: 352/530, loss: 0.024175453931093216
2023-01-21 10:54:04.018751: step: 356/530, loss: 0.029779816046357155
2023-01-21 10:54:05.200950: step: 360/530, loss: 0.03215289115905762
2023-01-21 10:54:06.334882: step: 364/530, loss: 0.03753085061907768
2023-01-21 10:54:07.493664: step: 368/530, loss: 0.0011881828540936112
2023-01-21 10:54:08.682840: step: 372/530, loss: 0.045100972056388855
2023-01-21 10:54:09.852648: step: 376/530, loss: 0.001973915146663785
2023-01-21 10:54:11.032838: step: 380/530, loss: 0.013695812784135342
2023-01-21 10:54:12.259080: step: 384/530, loss: 0.002600813051685691
2023-01-21 10:54:13.456364: step: 388/530, loss: 5.380776882171631
2023-01-21 10:54:14.659752: step: 392/530, loss: 0.00581812858581543
2023-01-21 10:54:15.839823: step: 396/530, loss: 0.0007762908935546875
2023-01-21 10:54:16.993469: step: 400/530, loss: 0.07800697535276413
2023-01-21 10:54:18.168607: step: 404/530, loss: 0.0460878387093544
2023-01-21 10:54:19.343035: step: 408/530, loss: 0.010218143463134766
2023-01-21 10:54:20.525283: step: 412/530, loss: 0.012431908398866653
2023-01-21 10:54:21.704548: step: 416/530, loss: 0.03949098661541939
2023-01-21 10:54:22.943809: step: 420/530, loss: 0.037775516510009766
2023-01-21 10:54:24.124900: step: 424/530, loss: 0.06238670274615288
2023-01-21 10:54:25.309017: step: 428/530, loss: 0.09127922356128693
2023-01-21 10:54:26.490308: step: 432/530, loss: 0.042136095464229584
2023-01-21 10:54:27.636926: step: 436/530, loss: 0.0070014954544603825
2023-01-21 10:54:28.795211: step: 440/530, loss: 0.019686413928866386
2023-01-21 10:54:29.938636: step: 444/530, loss: 0.002402782440185547
2023-01-21 10:54:31.124322: step: 448/530, loss: 0.006447506137192249
2023-01-21 10:54:32.266819: step: 452/530, loss: 0.014334345236420631
2023-01-21 10:54:33.466529: step: 456/530, loss: 0.049262333661317825
2023-01-21 10:54:34.632901: step: 460/530, loss: 0.009968224912881851
2023-01-21 10:54:35.792687: step: 464/530, loss: 0.006039619445800781
2023-01-21 10:54:36.992915: step: 468/530, loss: 0.00283393869176507
2023-01-21 10:54:38.172008: step: 472/530, loss: 0.010063457302749157
2023-01-21 10:54:39.376381: step: 476/530, loss: 0.04533147066831589
2023-01-21 10:54:40.564042: step: 480/530, loss: 0.0342344269156456
2023-01-21 10:54:41.707324: step: 484/530, loss: 0.041109848767519
2023-01-21 10:54:42.845738: step: 488/530, loss: 0.002376079559326172
2023-01-21 10:54:44.039066: step: 492/530, loss: 0.10553179681301117
2023-01-21 10:54:45.215598: step: 496/530, loss: 0.002952003385871649
2023-01-21 10:54:46.354850: step: 500/530, loss: 0.06091776490211487
2023-01-21 10:54:47.556562: step: 504/530, loss: 0.0035951617173850536
2023-01-21 10:54:48.719614: step: 508/530, loss: 0.0022552490700036287
2023-01-21 10:54:49.893606: step: 512/530, loss: 0.015830958262085915
2023-01-21 10:54:51.058026: step: 516/530, loss: 0.07178954780101776
2023-01-21 10:54:52.251060: step: 520/530, loss: 0.0045768022537231445
2023-01-21 10:54:53.436512: step: 524/530, loss: 0.04773874208331108
2023-01-21 10:54:54.607718: step: 528/530, loss: 0.09525977075099945
2023-01-21 10:54:55.800360: step: 532/530, loss: 0.013391494750976562
2023-01-21 10:54:57.008002: step: 536/530, loss: 0.16305142641067505
2023-01-21 10:54:58.180723: step: 540/530, loss: 0.15200833976268768
2023-01-21 10:54:59.348691: step: 544/530, loss: 0.08344488590955734
2023-01-21 10:55:00.528257: step: 548/530, loss: 0.06466970592737198
2023-01-21 10:55:01.689791: step: 552/530, loss: 0.008684491738677025
2023-01-21 10:55:02.877361: step: 556/530, loss: 0.05092290788888931
2023-01-21 10:55:04.065894: step: 560/530, loss: 0.03428792580962181
2023-01-21 10:55:05.244360: step: 564/530, loss: 0.04535084217786789
2023-01-21 10:55:06.420054: step: 568/530, loss: 0.06685533374547958
2023-01-21 10:55:07.618654: step: 572/530, loss: 0.03615257143974304
2023-01-21 10:55:08.783564: step: 576/530, loss: 0.014024496078491211
2023-01-21 10:55:09.975967: step: 580/530, loss: 0.008629703894257545
2023-01-21 10:55:11.180178: step: 584/530, loss: 0.010449028573930264
2023-01-21 10:55:12.333818: step: 588/530, loss: 0.0018483161693438888
2023-01-21 10:55:13.479675: step: 592/530, loss: 0.07983622699975967
2023-01-21 10:55:14.646931: step: 596/530, loss: 0.0014098406536504626
2023-01-21 10:55:15.809485: step: 600/530, loss: 0.046735286712646484
2023-01-21 10:55:16.962081: step: 604/530, loss: 0.041312411427497864
2023-01-21 10:55:18.122041: step: 608/530, loss: 0.005254650022834539
2023-01-21 10:55:19.332158: step: 612/530, loss: 0.006469822023063898
2023-01-21 10:55:20.531122: step: 616/530, loss: 0.023212242871522903
2023-01-21 10:55:21.712585: step: 620/530, loss: 0.023560047149658203
2023-01-21 10:55:22.891529: step: 624/530, loss: 0.00410385150462389
2023-01-21 10:55:24.048800: step: 628/530, loss: 0.0017523765563964844
2023-01-21 10:55:25.224629: step: 632/530, loss: 0.03904438018798828
2023-01-21 10:55:26.412384: step: 636/530, loss: 0.006707191467285156
2023-01-21 10:55:27.594441: step: 640/530, loss: 0.016329193487763405
2023-01-21 10:55:28.865768: step: 644/530, loss: 0.016475772485136986
2023-01-21 10:55:30.027416: step: 648/530, loss: 0.02250981330871582
2023-01-21 10:55:31.234321: step: 652/530, loss: 0.08036527037620544
2023-01-21 10:55:32.386922: step: 656/530, loss: 0.0514252632856369
2023-01-21 10:55:33.590551: step: 660/530, loss: 0.027327824383974075
2023-01-21 10:55:34.770614: step: 664/530, loss: 0.01322789117693901
2023-01-21 10:55:36.007141: step: 668/530, loss: 0.08221215754747391
2023-01-21 10:55:37.178625: step: 672/530, loss: 0.047343090176582336
2023-01-21 10:55:38.345858: step: 676/530, loss: 0.12078670412302017
2023-01-21 10:55:39.507479: step: 680/530, loss: 0.18680067360401154
2023-01-21 10:55:40.735855: step: 684/530, loss: 0.0060790060088038445
2023-01-21 10:55:41.940611: step: 688/530, loss: 0.07895335555076599
2023-01-21 10:55:43.141896: step: 692/530, loss: 0.0226606372743845
2023-01-21 10:55:44.263744: step: 696/530, loss: 0.020711231976747513
2023-01-21 10:55:45.454429: step: 700/530, loss: 0.014370870776474476
2023-01-21 10:55:46.625950: step: 704/530, loss: 0.022214699536561966
2023-01-21 10:55:47.777302: step: 708/530, loss: 0.008092308416962624
2023-01-21 10:55:48.921308: step: 712/530, loss: 0.01620025746524334
2023-01-21 10:55:50.121813: step: 716/530, loss: 0.031725216656923294
2023-01-21 10:55:51.301310: step: 720/530, loss: 0.22083044052124023
2023-01-21 10:55:52.508507: step: 724/530, loss: 0.04113359749317169
2023-01-21 10:55:53.668494: step: 728/530, loss: 0.0027060983702540398
2023-01-21 10:55:54.866460: step: 732/530, loss: 0.059975381940603256
2023-01-21 10:55:56.038816: step: 736/530, loss: 0.01000213623046875
2023-01-21 10:55:57.238413: step: 740/530, loss: 0.03115234524011612
2023-01-21 10:55:58.428415: step: 744/530, loss: 0.03276796638965607
2023-01-21 10:55:59.608895: step: 748/530, loss: 0.011308098211884499
2023-01-21 10:56:00.802545: step: 752/530, loss: 0.06421995162963867
2023-01-21 10:56:01.965931: step: 756/530, loss: 0.004058361053466797
2023-01-21 10:56:03.160396: step: 760/530, loss: 0.4870767593383789
2023-01-21 10:56:04.373197: step: 764/530, loss: 0.04728507995605469
2023-01-21 10:56:05.539880: step: 768/530, loss: 0.004268193151801825
2023-01-21 10:56:06.732789: step: 772/530, loss: 0.030767250806093216
2023-01-21 10:56:07.920419: step: 776/530, loss: 0.05232071876525879
2023-01-21 10:56:09.108604: step: 780/530, loss: 0.1106410026550293
2023-01-21 10:56:10.311224: step: 784/530, loss: 0.020158957690000534
2023-01-21 10:56:11.514752: step: 788/530, loss: 0.012179374694824219
2023-01-21 10:56:12.778263: step: 792/530, loss: 0.036643028259277344
2023-01-21 10:56:13.917986: step: 796/530, loss: 0.0234514232724905
2023-01-21 10:56:15.116720: step: 800/530, loss: 0.05611305311322212
2023-01-21 10:56:16.304367: step: 804/530, loss: 0.020201683044433594
2023-01-21 10:56:17.512537: step: 808/530, loss: 0.0027421952690929174
2023-01-21 10:56:18.685018: step: 812/530, loss: 0.05255298689007759
2023-01-21 10:56:19.887107: step: 816/530, loss: 0.05241432413458824
2023-01-21 10:56:21.147296: step: 820/530, loss: 0.030003929510712624
2023-01-21 10:56:22.315674: step: 824/530, loss: 0.00626482954248786
2023-01-21 10:56:23.556487: step: 828/530, loss: 0.04351654276251793
2023-01-21 10:56:24.725729: step: 832/530, loss: 0.07517804950475693
2023-01-21 10:56:25.885814: step: 836/530, loss: 0.012499428354203701
2023-01-21 10:56:27.066684: step: 840/530, loss: 0.014498806558549404
2023-01-21 10:56:28.268077: step: 844/530, loss: 0.03977778181433678
2023-01-21 10:56:29.452118: step: 848/530, loss: 0.028492452576756477
2023-01-21 10:56:30.639928: step: 852/530, loss: 0.015743732452392578
2023-01-21 10:56:31.814597: step: 856/530, loss: 0.015134715475142002
2023-01-21 10:56:33.017051: step: 860/530, loss: 0.08751964569091797
2023-01-21 10:56:34.170483: step: 864/530, loss: 0.1088382676243782
2023-01-21 10:56:35.377333: step: 868/530, loss: 0.0007902145152911544
2023-01-21 10:56:36.543319: step: 872/530, loss: 0.06449051201343536
2023-01-21 10:56:37.773288: step: 876/530, loss: 0.06290464848279953
2023-01-21 10:56:38.974353: step: 880/530, loss: 0.03508930280804634
2023-01-21 10:56:40.161598: step: 884/530, loss: 0.016158677637577057
2023-01-21 10:56:41.337879: step: 888/530, loss: 0.023266160860657692
2023-01-21 10:56:42.501832: step: 892/530, loss: 0.02097930945456028
2023-01-21 10:56:43.755098: step: 896/530, loss: 0.04954729229211807
2023-01-21 10:56:44.910997: step: 900/530, loss: 0.0018979072337970138
2023-01-21 10:56:46.085021: step: 904/530, loss: 0.0040073394775390625
2023-01-21 10:56:47.273543: step: 908/530, loss: 0.06982593238353729
2023-01-21 10:56:48.459115: step: 912/530, loss: 0.05851898342370987
2023-01-21 10:56:49.632075: step: 916/530, loss: 0.019919872283935547
2023-01-21 10:56:50.833810: step: 920/530, loss: 0.014957617968320847
2023-01-21 10:56:52.002652: step: 924/530, loss: 0.013622093014419079
2023-01-21 10:56:53.198751: step: 928/530, loss: 0.09099216014146805
2023-01-21 10:56:54.377183: step: 932/530, loss: 0.6720672249794006
2023-01-21 10:56:55.559813: step: 936/530, loss: 0.9447656869888306
2023-01-21 10:56:56.766637: step: 940/530, loss: 0.019492723047733307
2023-01-21 10:56:57.921168: step: 944/530, loss: 0.02751283533871174
2023-01-21 10:56:59.090545: step: 948/530, loss: 0.029192639514803886
2023-01-21 10:57:00.247754: step: 952/530, loss: 0.015758514404296875
2023-01-21 10:57:01.434828: step: 956/530, loss: 0.062221623957157135
2023-01-21 10:57:02.597902: step: 960/530, loss: 0.015386056154966354
2023-01-21 10:57:03.854829: step: 964/530, loss: 0.018376445397734642
2023-01-21 10:57:05.054656: step: 968/530, loss: 0.020078659057617188
2023-01-21 10:57:06.238654: step: 972/530, loss: 0.0668155699968338
2023-01-21 10:57:07.426544: step: 976/530, loss: 0.005804157815873623
2023-01-21 10:57:08.580460: step: 980/530, loss: 0.02291693538427353
2023-01-21 10:57:09.777037: step: 984/530, loss: 0.029445840045809746
2023-01-21 10:57:10.940612: step: 988/530, loss: 0.05299568176269531
2023-01-21 10:57:12.121033: step: 992/530, loss: 0.008049249649047852
2023-01-21 10:57:13.281742: step: 996/530, loss: 0.06351175159215927
2023-01-21 10:57:14.490248: step: 1000/530, loss: 0.013764381408691406
2023-01-21 10:57:15.644421: step: 1004/530, loss: 0.10248871147632599
2023-01-21 10:57:16.799385: step: 1008/530, loss: 0.05187620967626572
2023-01-21 10:57:17.968397: step: 1012/530, loss: 0.04626312106847763
2023-01-21 10:57:19.119591: step: 1016/530, loss: 0.10064688324928284
2023-01-21 10:57:20.284053: step: 1020/530, loss: 0.0583617240190506
2023-01-21 10:57:21.427720: step: 1024/530, loss: 0.038388825953006744
2023-01-21 10:57:22.574813: step: 1028/530, loss: 0.0027133943513035774
2023-01-21 10:57:23.722147: step: 1032/530, loss: 1.5873178243637085
2023-01-21 10:57:24.871702: step: 1036/530, loss: 0.002054405165836215
2023-01-21 10:57:26.041300: step: 1040/530, loss: 0.0008842468378134072
2023-01-21 10:57:27.272769: step: 1044/530, loss: 0.036200523376464844
2023-01-21 10:57:28.438156: step: 1048/530, loss: 0.03912096098065376
2023-01-21 10:57:29.599913: step: 1052/530, loss: 0.014590168371796608
2023-01-21 10:57:30.775392: step: 1056/530, loss: 0.004029273986816406
2023-01-21 10:57:32.021124: step: 1060/530, loss: 0.10773029923439026
2023-01-21 10:57:33.195777: step: 1064/530, loss: 0.0009130954276770353
2023-01-21 10:57:34.373979: step: 1068/530, loss: 0.0750865712761879
2023-01-21 10:57:35.532189: step: 1072/530, loss: 0.0032346248626708984
2023-01-21 10:57:36.715227: step: 1076/530, loss: 0.024076366797089577
2023-01-21 10:57:37.912468: step: 1080/530, loss: 0.052799418568611145
2023-01-21 10:57:39.096849: step: 1084/530, loss: 0.08912745118141174
2023-01-21 10:57:40.296195: step: 1088/530, loss: 0.0533411018550396
2023-01-21 10:57:41.457088: step: 1092/530, loss: 0.009787846356630325
2023-01-21 10:57:42.643686: step: 1096/530, loss: 0.05474109947681427
2023-01-21 10:57:43.787113: step: 1100/530, loss: 0.03139081224799156
2023-01-21 10:57:44.953147: step: 1104/530, loss: 0.04499571770429611
2023-01-21 10:57:46.156770: step: 1108/530, loss: 0.06426601111888885
2023-01-21 10:57:47.360507: step: 1112/530, loss: 0.0022789002396166325
2023-01-21 10:57:48.525981: step: 1116/530, loss: 0.007829046808183193
2023-01-21 10:57:49.672609: step: 1120/530, loss: 0.04881773144006729
2023-01-21 10:57:50.871040: step: 1124/530, loss: 0.017742061987519264
2023-01-21 10:57:52.021641: step: 1128/530, loss: 0.0024471282958984375
2023-01-21 10:57:53.167190: step: 1132/530, loss: 0.0405152402818203
2023-01-21 10:57:54.375140: step: 1136/530, loss: 0.004213142208755016
2023-01-21 10:57:55.559608: step: 1140/530, loss: 0.04712200164794922
2023-01-21 10:57:56.747927: step: 1144/530, loss: 0.04386615753173828
2023-01-21 10:57:57.893671: step: 1148/530, loss: 0.029075050726532936
2023-01-21 10:57:59.055754: step: 1152/530, loss: 0.0013036727905273438
2023-01-21 10:58:00.240085: step: 1156/530, loss: 0.1572185605764389
2023-01-21 10:58:01.413515: step: 1160/530, loss: 0.015713881701231003
2023-01-21 10:58:02.568061: step: 1164/530, loss: 0.15891484916210175
2023-01-21 10:58:03.773331: step: 1168/530, loss: 0.01745147630572319
2023-01-21 10:58:04.958848: step: 1172/530, loss: 0.22228102385997772
2023-01-21 10:58:06.200040: step: 1176/530, loss: 0.06579075008630753
2023-01-21 10:58:07.371845: step: 1180/530, loss: 0.030608560889959335
2023-01-21 10:58:08.579114: step: 1184/530, loss: 0.005961370188742876
2023-01-21 10:58:09.735595: step: 1188/530, loss: 0.01275491714477539
2023-01-21 10:58:10.948807: step: 1192/530, loss: 0.028139973059296608
2023-01-21 10:58:12.138151: step: 1196/530, loss: 0.0005164146423339844
2023-01-21 10:58:13.320012: step: 1200/530, loss: 0.09835916012525558
2023-01-21 10:58:14.465985: step: 1204/530, loss: 0.07554474472999573
2023-01-21 10:58:15.660354: step: 1208/530, loss: 0.060419656336307526
2023-01-21 10:58:16.863388: step: 1212/530, loss: 0.01329116802662611
2023-01-21 10:58:18.049488: step: 1216/530, loss: 0.28663673996925354
2023-01-21 10:58:19.210766: step: 1220/530, loss: 0.05301990732550621
2023-01-21 10:58:20.400963: step: 1224/530, loss: 0.006135368254035711
2023-01-21 10:58:21.556590: step: 1228/530, loss: 0.053505513817071915
2023-01-21 10:58:22.734395: step: 1232/530, loss: 0.02897033840417862
2023-01-21 10:58:23.884955: step: 1236/530, loss: 0.04241809993982315
2023-01-21 10:58:25.073271: step: 1240/530, loss: 0.08190841972827911
2023-01-21 10:58:26.270255: step: 1244/530, loss: 0.01678771898150444
2023-01-21 10:58:27.467558: step: 1248/530, loss: 0.08135394752025604
2023-01-21 10:58:28.615302: step: 1252/530, loss: 0.00514831580221653
2023-01-21 10:58:29.824805: step: 1256/530, loss: 0.0794924721121788
2023-01-21 10:58:30.987892: step: 1260/530, loss: 0.10486526787281036
2023-01-21 10:58:32.149383: step: 1264/530, loss: 0.011802387423813343
2023-01-21 10:58:33.339343: step: 1268/530, loss: 0.06461963802576065
2023-01-21 10:58:34.515959: step: 1272/530, loss: 0.024094581604003906
2023-01-21 10:58:35.714435: step: 1276/530, loss: 0.29612845182418823
2023-01-21 10:58:36.863473: step: 1280/530, loss: 0.015963125973939896
2023-01-21 10:58:38.008987: step: 1284/530, loss: 0.14036236703395844
2023-01-21 10:58:39.189462: step: 1288/530, loss: 0.02286829985678196
2023-01-21 10:58:40.398191: step: 1292/530, loss: 0.08441717177629471
2023-01-21 10:58:41.557507: step: 1296/530, loss: 0.13040542602539062
2023-01-21 10:58:42.750646: step: 1300/530, loss: 0.046560097485780716
2023-01-21 10:58:43.909947: step: 1304/530, loss: 0.057631492614746094
2023-01-21 10:58:45.092261: step: 1308/530, loss: 0.05217113718390465
2023-01-21 10:58:46.268852: step: 1312/530, loss: 0.01954355277121067
2023-01-21 10:58:47.447757: step: 1316/530, loss: 0.018437959253787994
2023-01-21 10:58:48.715503: step: 1320/530, loss: 0.10287466645240784
2023-01-21 10:58:49.892231: step: 1324/530, loss: 0.010599995031952858
2023-01-21 10:58:51.088156: step: 1328/530, loss: 0.005822325125336647
2023-01-21 10:58:52.314473: step: 1332/530, loss: 0.0163711067289114
2023-01-21 10:58:53.491989: step: 1336/530, loss: 0.009173489175736904
2023-01-21 10:58:54.700412: step: 1340/530, loss: 0.0920533686876297
2023-01-21 10:58:55.879103: step: 1344/530, loss: 0.09542389214038849
2023-01-21 10:58:57.080984: step: 1348/530, loss: 0.010265350341796875
2023-01-21 10:58:58.239921: step: 1352/530, loss: 0.022735118865966797
2023-01-21 10:58:59.390225: step: 1356/530, loss: 0.011389637365937233
2023-01-21 10:59:00.552924: step: 1360/530, loss: 0.4217488467693329
2023-01-21 10:59:01.758256: step: 1364/530, loss: 0.027636338025331497
2023-01-21 10:59:02.906420: step: 1368/530, loss: 0.010472583584487438
2023-01-21 10:59:04.103902: step: 1372/530, loss: 0.03571949154138565
2023-01-21 10:59:05.260326: step: 1376/530, loss: 0.0035711764357984066
2023-01-21 10:59:06.459272: step: 1380/530, loss: 0.03551464155316353
2023-01-21 10:59:07.656924: step: 1384/530, loss: 0.010649300180375576
2023-01-21 10:59:08.806920: step: 1388/530, loss: 0.021372605115175247
2023-01-21 10:59:09.977380: step: 1392/530, loss: 0.02072601392865181
2023-01-21 10:59:11.130058: step: 1396/530, loss: 0.00197601318359375
2023-01-21 10:59:12.345122: step: 1400/530, loss: 0.03057580068707466
2023-01-21 10:59:13.503352: step: 1404/530, loss: 0.0018190384143963456
2023-01-21 10:59:14.652633: step: 1408/530, loss: 0.00015096664719749242
2023-01-21 10:59:15.822968: step: 1412/530, loss: 0.01744537428021431
2023-01-21 10:59:16.967677: step: 1416/530, loss: 0.002832174301147461
2023-01-21 10:59:18.152657: step: 1420/530, loss: 0.09745007008314133
2023-01-21 10:59:19.357044: step: 1424/530, loss: 0.06458606570959091
2023-01-21 10:59:20.575176: step: 1428/530, loss: 0.041750334203243256
2023-01-21 10:59:21.766053: step: 1432/530, loss: 0.004408073145896196
2023-01-21 10:59:22.960395: step: 1436/530, loss: 0.048647500574588776
2023-01-21 10:59:24.106502: step: 1440/530, loss: 0.01678643375635147
2023-01-21 10:59:25.330344: step: 1444/530, loss: 0.028554726392030716
2023-01-21 10:59:26.535396: step: 1448/530, loss: 0.03467092290520668
2023-01-21 10:59:27.697256: step: 1452/530, loss: 0.10060329735279083
2023-01-21 10:59:28.909817: step: 1456/530, loss: 0.05347652733325958
2023-01-21 10:59:30.076360: step: 1460/530, loss: 0.022730637341737747
2023-01-21 10:59:31.276899: step: 1464/530, loss: 0.07542820274829865
2023-01-21 10:59:32.454860: step: 1468/530, loss: 0.07027512043714523
2023-01-21 10:59:33.619613: step: 1472/530, loss: 0.005811500828713179
2023-01-21 10:59:34.746794: step: 1476/530, loss: 0.006807804107666016
2023-01-21 10:59:35.898873: step: 1480/530, loss: 0.07120266556739807
2023-01-21 10:59:37.056603: step: 1484/530, loss: 0.03455333784222603
2023-01-21 10:59:38.216125: step: 1488/530, loss: 0.01606917381286621
2023-01-21 10:59:39.362241: step: 1492/530, loss: 0.001522064208984375
2023-01-21 10:59:40.525761: step: 1496/530, loss: 0.01781024970114231
2023-01-21 10:59:41.683989: step: 1500/530, loss: 0.00594177283346653
2023-01-21 10:59:42.879795: step: 1504/530, loss: 0.03657646104693413
2023-01-21 10:59:44.065135: step: 1508/530, loss: 0.00032749175443314016
2023-01-21 10:59:45.293268: step: 1512/530, loss: 0.055272672325372696
2023-01-21 10:59:46.504038: step: 1516/530, loss: 0.021250629797577858
2023-01-21 10:59:47.695001: step: 1520/530, loss: 0.14078053832054138
2023-01-21 10:59:48.889930: step: 1524/530, loss: 0.020298361778259277
2023-01-21 10:59:50.102451: step: 1528/530, loss: 0.011423206888139248
2023-01-21 10:59:51.306308: step: 1532/530, loss: 0.002498626708984375
2023-01-21 10:59:52.464924: step: 1536/530, loss: 0.264875590801239
2023-01-21 10:59:53.666620: step: 1540/530, loss: 0.10807070881128311
2023-01-21 10:59:54.826390: step: 1544/530, loss: 0.009528923779726028
2023-01-21 10:59:55.984008: step: 1548/530, loss: 0.04711608961224556
2023-01-21 10:59:57.187629: step: 1552/530, loss: 0.03205166012048721
2023-01-21 10:59:58.371472: step: 1556/530, loss: 0.014445686712861061
2023-01-21 10:59:59.577277: step: 1560/530, loss: 0.03359420225024223
2023-01-21 11:00:00.782881: step: 1564/530, loss: 0.10994544625282288
2023-01-21 11:00:01.961012: step: 1568/530, loss: 0.01910562440752983
2023-01-21 11:00:03.139857: step: 1572/530, loss: 0.05439586937427521
2023-01-21 11:00:04.329590: step: 1576/530, loss: 0.08284874260425568
2023-01-21 11:00:05.533007: step: 1580/530, loss: 0.030953358858823776
2023-01-21 11:00:06.700815: step: 1584/530, loss: 0.004668903537094593
2023-01-21 11:00:07.861474: step: 1588/530, loss: 0.0002803802490234375
2023-01-21 11:00:09.078046: step: 1592/530, loss: 0.02082977443933487
2023-01-21 11:00:10.290323: step: 1596/530, loss: 0.02744166925549507
2023-01-21 11:00:11.475348: step: 1600/530, loss: 0.012082099914550781
2023-01-21 11:00:12.628212: step: 1604/530, loss: 0.03174562379717827
2023-01-21 11:00:13.795554: step: 1608/530, loss: 0.0059739588759839535
2023-01-21 11:00:14.974895: step: 1612/530, loss: 0.028591632843017578
2023-01-21 11:00:16.170082: step: 1616/530, loss: 0.03705187141895294
2023-01-21 11:00:17.333580: step: 1620/530, loss: 0.008844435214996338
2023-01-21 11:00:18.535523: step: 1624/530, loss: 0.03221893310546875
2023-01-21 11:00:19.733602: step: 1628/530, loss: 0.04294948652386665
2023-01-21 11:00:20.889113: step: 1632/530, loss: 0.06609401851892471
2023-01-21 11:00:22.092443: step: 1636/530, loss: 0.04906740039587021
2023-01-21 11:00:23.273123: step: 1640/530, loss: 0.009540081024169922
2023-01-21 11:00:24.408459: step: 1644/530, loss: 0.15140044689178467
2023-01-21 11:00:25.566969: step: 1648/530, loss: 0.0717153549194336
2023-01-21 11:00:26.760374: step: 1652/530, loss: 0.12203264236450195
2023-01-21 11:00:27.944355: step: 1656/530, loss: 0.02027897723019123
2023-01-21 11:00:29.113319: step: 1660/530, loss: 0.03621573746204376
2023-01-21 11:00:30.278658: step: 1664/530, loss: 0.01602344587445259
2023-01-21 11:00:31.481854: step: 1668/530, loss: 0.003793239826336503
2023-01-21 11:00:32.682049: step: 1672/530, loss: 0.1169290542602539
2023-01-21 11:00:33.928263: step: 1676/530, loss: 0.05004744604229927
2023-01-21 11:00:35.128857: step: 1680/530, loss: 0.006236935034394264
2023-01-21 11:00:36.362566: step: 1684/530, loss: 0.01991911046206951
2023-01-21 11:00:37.521106: step: 1688/530, loss: 0.02226683869957924
2023-01-21 11:00:38.750094: step: 1692/530, loss: 0.015440368093550205
2023-01-21 11:00:39.904001: step: 1696/530, loss: 0.08121337741613388
2023-01-21 11:00:41.092917: step: 1700/530, loss: 0.0019536970648914576
2023-01-21 11:00:42.341731: step: 1704/530, loss: 0.1464221477508545
2023-01-21 11:00:43.514253: step: 1708/530, loss: 0.04672107845544815
2023-01-21 11:00:44.682215: step: 1712/530, loss: 0.01932978630065918
2023-01-21 11:00:45.876173: step: 1716/530, loss: 0.07145671546459198
2023-01-21 11:00:47.016387: step: 1720/530, loss: 0.004661274142563343
2023-01-21 11:00:48.187042: step: 1724/530, loss: 0.037697192281484604
2023-01-21 11:00:49.335176: step: 1728/530, loss: 0.04180178791284561
2023-01-21 11:00:50.596486: step: 1732/530, loss: 0.06022663414478302
2023-01-21 11:00:51.778176: step: 1736/530, loss: 0.02742767333984375
2023-01-21 11:00:52.927412: step: 1740/530, loss: 0.021106483414769173
2023-01-21 11:00:54.124736: step: 1744/530, loss: 0.028363609686493874
2023-01-21 11:00:55.324689: step: 1748/530, loss: 0.0025877952575683594
2023-01-21 11:00:56.512353: step: 1752/530, loss: 0.008541298098862171
2023-01-21 11:00:57.698179: step: 1756/530, loss: 0.00593718932941556
2023-01-21 11:00:58.834507: step: 1760/530, loss: 0.028662586584687233
2023-01-21 11:01:00.027614: step: 1764/530, loss: 0.00020494460477493703
2023-01-21 11:01:01.185413: step: 1768/530, loss: 0.14434394240379333
2023-01-21 11:01:02.392239: step: 1772/530, loss: 0.030316734686493874
2023-01-21 11:01:03.603197: step: 1776/530, loss: 0.0392146110534668
2023-01-21 11:01:04.767461: step: 1780/530, loss: 0.0064931875094771385
2023-01-21 11:01:05.979541: step: 1784/530, loss: 0.006567955017089844
2023-01-21 11:01:07.163498: step: 1788/530, loss: 0.08336534351110458
2023-01-21 11:01:08.318488: step: 1792/530, loss: 0.007630825042724609
2023-01-21 11:01:09.487803: step: 1796/530, loss: 0.10943537205457687
2023-01-21 11:01:10.680234: step: 1800/530, loss: 0.007854938507080078
2023-01-21 11:01:11.876367: step: 1804/530, loss: 0.025266695767641068
2023-01-21 11:01:13.050668: step: 1808/530, loss: 0.09107495099306107
2023-01-21 11:01:14.260732: step: 1812/530, loss: 0.026578523218631744
2023-01-21 11:01:15.480991: step: 1816/530, loss: 0.0011942863930016756
2023-01-21 11:01:16.722276: step: 1820/530, loss: 0.010960960760712624
2023-01-21 11:01:17.901461: step: 1824/530, loss: 0.021959686651825905
2023-01-21 11:01:19.131965: step: 1828/530, loss: 0.005299925804138184
2023-01-21 11:01:20.305463: step: 1832/530, loss: 0.030454635620117188
2023-01-21 11:01:21.458449: step: 1836/530, loss: 0.005831241607666016
2023-01-21 11:01:22.587505: step: 1840/530, loss: 0.028088664636015892
2023-01-21 11:01:23.786892: step: 1844/530, loss: 0.038376886397600174
2023-01-21 11:01:24.965037: step: 1848/530, loss: 0.004767322447150946
2023-01-21 11:01:26.176387: step: 1852/530, loss: 0.04879160225391388
2023-01-21 11:01:27.357606: step: 1856/530, loss: 0.0028648721054196358
2023-01-21 11:01:28.553611: step: 1860/530, loss: 0.11395607888698578
2023-01-21 11:01:29.748420: step: 1864/530, loss: 0.010779762640595436
2023-01-21 11:01:30.874964: step: 1868/530, loss: 0.8157111406326294
2023-01-21 11:01:32.027654: step: 1872/530, loss: 0.07138185948133469
2023-01-21 11:01:33.249626: step: 1876/530, loss: 0.0043167113326489925
2023-01-21 11:01:34.441909: step: 1880/530, loss: 0.006344032008200884
2023-01-21 11:01:35.683556: step: 1884/530, loss: 0.20362864434719086
2023-01-21 11:01:36.870914: step: 1888/530, loss: 0.004898118786513805
2023-01-21 11:01:38.079773: step: 1892/530, loss: 0.022330617532134056
2023-01-21 11:01:39.261570: step: 1896/530, loss: 0.004425049293786287
2023-01-21 11:01:40.413165: step: 1900/530, loss: 0.6054101586341858
2023-01-21 11:01:41.582339: step: 1904/530, loss: 0.049509335309267044
2023-01-21 11:01:42.811806: step: 1908/530, loss: 0.07069572061300278
2023-01-21 11:01:43.982865: step: 1912/530, loss: 0.06323103606700897
2023-01-21 11:01:45.156608: step: 1916/530, loss: 0.12586307525634766
2023-01-21 11:01:46.350239: step: 1920/530, loss: 0.014882659539580345
2023-01-21 11:01:47.516648: step: 1924/530, loss: 0.026545144617557526
2023-01-21 11:01:48.694831: step: 1928/530, loss: 0.0905529037117958
2023-01-21 11:01:49.865276: step: 1932/530, loss: 0.0048423768021166325
2023-01-21 11:01:51.046060: step: 1936/530, loss: 0.06902284920215607
2023-01-21 11:01:52.268863: step: 1940/530, loss: 0.028437232598662376
2023-01-21 11:01:53.425396: step: 1944/530, loss: 0.2937842309474945
2023-01-21 11:01:54.615368: step: 1948/530, loss: 0.03400421142578125
2023-01-21 11:01:55.804903: step: 1952/530, loss: 0.047776319086551666
2023-01-21 11:01:56.941204: step: 1956/530, loss: 0.34312230348587036
2023-01-21 11:01:58.154851: step: 1960/530, loss: 0.011840534396469593
2023-01-21 11:01:59.323669: step: 1964/530, loss: 0.004528999328613281
2023-01-21 11:02:00.480976: step: 1968/530, loss: 0.016599083319306374
2023-01-21 11:02:01.633145: step: 1972/530, loss: 0.008021545596420765
2023-01-21 11:02:02.802584: step: 1976/530, loss: 0.03904872015118599
2023-01-21 11:02:03.986015: step: 1980/530, loss: 0.2406059205532074
2023-01-21 11:02:05.175765: step: 1984/530, loss: 0.09173736721277237
2023-01-21 11:02:06.321889: step: 1988/530, loss: 0.07246027141809464
2023-01-21 11:02:07.466605: step: 1992/530, loss: 0.0022140503861010075
2023-01-21 11:02:08.613390: step: 1996/530, loss: 0.0005724430084228516
2023-01-21 11:02:09.749278: step: 2000/530, loss: 0.0006843566661700606
2023-01-21 11:02:10.928372: step: 2004/530, loss: 0.006539082620292902
2023-01-21 11:02:12.126087: step: 2008/530, loss: 0.021462690085172653
2023-01-21 11:02:13.318344: step: 2012/530, loss: 0.0559362918138504
2023-01-21 11:02:14.453891: step: 2016/530, loss: 0.010561943054199219
2023-01-21 11:02:15.648423: step: 2020/530, loss: 0.0350530631840229
2023-01-21 11:02:16.835199: step: 2024/530, loss: 0.014557457529008389
2023-01-21 11:02:18.029290: step: 2028/530, loss: 0.15231746435165405
2023-01-21 11:02:19.189915: step: 2032/530, loss: 0.06092491373419762
2023-01-21 11:02:20.359625: step: 2036/530, loss: 0.05775924026966095
2023-01-21 11:02:21.550520: step: 2040/530, loss: 0.12214555591344833
2023-01-21 11:02:22.688619: step: 2044/530, loss: 0.12388335168361664
2023-01-21 11:02:23.870015: step: 2048/530, loss: 1.0693259239196777
2023-01-21 11:02:25.101752: step: 2052/530, loss: 0.05169949680566788
2023-01-21 11:02:26.315817: step: 2056/530, loss: 0.006696128752082586
2023-01-21 11:02:27.499426: step: 2060/530, loss: 0.03417492285370827
2023-01-21 11:02:28.714174: step: 2064/530, loss: 0.04913969337940216
2023-01-21 11:02:29.918319: step: 2068/530, loss: 0.0028133392333984375
2023-01-21 11:02:31.102277: step: 2072/530, loss: 0.005373859778046608
2023-01-21 11:02:32.285360: step: 2076/530, loss: 0.050955869257450104
2023-01-21 11:02:33.450238: step: 2080/530, loss: 0.012179946526885033
2023-01-21 11:02:34.650680: step: 2084/530, loss: 0.057327937334775925
2023-01-21 11:02:35.842007: step: 2088/530, loss: 0.15411490201950073
2023-01-21 11:02:37.038494: step: 2092/530, loss: 0.028712939471006393
2023-01-21 11:02:38.240396: step: 2096/530, loss: 0.02039518393576145
2023-01-21 11:02:39.474331: step: 2100/530, loss: 0.04087676852941513
2023-01-21 11:02:40.678211: step: 2104/530, loss: 0.0045900107361376286
2023-01-21 11:02:41.912882: step: 2108/530, loss: 0.08083444088697433
2023-01-21 11:02:43.087128: step: 2112/530, loss: 0.7785191535949707
2023-01-21 11:02:44.242297: step: 2116/530, loss: 0.02292471006512642
2023-01-21 11:02:45.444342: step: 2120/530, loss: 0.046098992228507996
==================================================
Loss: 0.067
--------------------
Dev: {'event': {'p': 0.613588110403397, 'r': 0.7696404793608522, 'f1': 0.6828115770821027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6631878557874763, 'r': 0.8039102932719954, 'f1': 0.726800103977125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.6326530612244898, 'r': 0.49206349206349204, 'f1': 0.5535714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.4888888888888889, 'r': 0.6111111111111112, 'f1': 0.5432098765432098}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:03:30.382791: step: 4/530, loss: 0.02861766889691353
2023-01-21 11:03:31.539038: step: 8/530, loss: 0.007576751988381147
2023-01-21 11:03:32.700902: step: 12/530, loss: 0.009433556348085403
2023-01-21 11:03:33.849904: step: 16/530, loss: 0.048389531672000885
2023-01-21 11:03:35.009942: step: 20/530, loss: 0.015052604489028454
2023-01-21 11:03:36.239567: step: 24/530, loss: 0.025703048333525658
2023-01-21 11:03:37.428244: step: 28/530, loss: 0.06493663787841797
2023-01-21 11:03:38.646813: step: 32/530, loss: 0.03152313083410263
2023-01-21 11:03:39.821839: step: 36/530, loss: 0.006931495852768421
2023-01-21 11:03:40.996517: step: 40/530, loss: 0.018326856195926666
2023-01-21 11:03:42.180019: step: 44/530, loss: 0.016199683770537376
2023-01-21 11:03:43.367228: step: 48/530, loss: 0.05742035061120987
2023-01-21 11:03:44.579684: step: 52/530, loss: 0.05046539381146431
2023-01-21 11:03:45.800127: step: 56/530, loss: 0.022667884826660156
2023-01-21 11:03:46.901938: step: 60/530, loss: 0.010160446166992188
2023-01-21 11:03:48.083066: step: 64/530, loss: 0.0015917777782306075
2023-01-21 11:03:49.230656: step: 68/530, loss: 0.01690683513879776
2023-01-21 11:03:50.404745: step: 72/530, loss: 0.02967357635498047
2023-01-21 11:03:51.597459: step: 76/530, loss: 0.05246458202600479
2023-01-21 11:03:52.789189: step: 80/530, loss: 0.0419306755065918
2023-01-21 11:03:53.943491: step: 84/530, loss: 0.04666309431195259
2023-01-21 11:03:55.154478: step: 88/530, loss: 0.001583099365234375
2023-01-21 11:03:56.318365: step: 92/530, loss: 0.0532168410718441
2023-01-21 11:03:57.516667: step: 96/530, loss: 0.2235923707485199
2023-01-21 11:03:58.672645: step: 100/530, loss: 0.12930116057395935
2023-01-21 11:03:59.846026: step: 104/530, loss: 0.0007921606302261353
2023-01-21 11:04:01.041233: step: 108/530, loss: 0.022526836022734642
2023-01-21 11:04:02.197866: step: 112/530, loss: 0.00994100607931614
2023-01-21 11:04:03.412586: step: 116/530, loss: 0.036127280443906784
2023-01-21 11:04:04.568383: step: 120/530, loss: 0.001628446625545621
2023-01-21 11:04:05.794568: step: 124/530, loss: 0.03671570122241974
2023-01-21 11:04:06.987801: step: 128/530, loss: 0.0697443038225174
2023-01-21 11:04:08.165616: step: 132/530, loss: 0.014757538214325905
2023-01-21 11:04:09.344591: step: 136/530, loss: 0.04543915018439293
2023-01-21 11:04:10.517317: step: 140/530, loss: 0.032637644559144974
2023-01-21 11:04:11.682140: step: 144/530, loss: 0.019971562549471855
2023-01-21 11:04:12.916508: step: 148/530, loss: 0.3105713725090027
2023-01-21 11:04:14.079822: step: 152/530, loss: 0.010465716943144798
2023-01-21 11:04:15.279550: step: 156/530, loss: 0.007421970367431641
2023-01-21 11:04:16.464995: step: 160/530, loss: 0.024837683886289597
2023-01-21 11:04:17.667464: step: 164/530, loss: 0.05188927799463272
2023-01-21 11:04:18.828222: step: 168/530, loss: 0.019368935376405716
2023-01-21 11:04:20.013242: step: 172/530, loss: 0.010196780785918236
2023-01-21 11:04:21.208843: step: 176/530, loss: 0.03295879438519478
2023-01-21 11:04:22.407533: step: 180/530, loss: 0.014865444973111153
2023-01-21 11:04:23.570168: step: 184/530, loss: 0.02180042304098606
2023-01-21 11:04:24.746282: step: 188/530, loss: 0.011869240552186966
2023-01-21 11:04:25.910108: step: 192/530, loss: 0.013792610727250576
2023-01-21 11:04:27.103517: step: 196/530, loss: 0.004962635226547718
2023-01-21 11:04:28.363666: step: 200/530, loss: 0.435743510723114
2023-01-21 11:04:29.533534: step: 204/530, loss: 0.16979655623435974
2023-01-21 11:04:30.728067: step: 208/530, loss: 0.0030931474175304174
2023-01-21 11:04:31.931877: step: 212/530, loss: 0.04576960578560829
2023-01-21 11:04:33.106321: step: 216/530, loss: 0.00040149688720703125
2023-01-21 11:04:34.315466: step: 220/530, loss: 0.03708569332957268
2023-01-21 11:04:35.491093: step: 224/530, loss: 0.0022191046737134457
2023-01-21 11:04:36.714191: step: 228/530, loss: 0.0016133307944983244
2023-01-21 11:04:37.916908: step: 232/530, loss: 0.0034082415513694286
2023-01-21 11:04:39.096386: step: 236/530, loss: 0.01021347101777792
2023-01-21 11:04:40.256075: step: 240/530, loss: 0.011389371007680893
2023-01-21 11:04:41.448738: step: 244/530, loss: 0.0029294968117028475
2023-01-21 11:04:42.639556: step: 248/530, loss: 0.009447479620575905
2023-01-21 11:04:43.809323: step: 252/530, loss: 0.01544799841940403
2023-01-21 11:04:45.029847: step: 256/530, loss: 0.06333966553211212
2023-01-21 11:04:46.204381: step: 260/530, loss: 0.06411246955394745
2023-01-21 11:04:47.378299: step: 264/530, loss: 0.03105149231851101
2023-01-21 11:04:48.545869: step: 268/530, loss: 0.0003105163632426411
2023-01-21 11:04:49.764048: step: 272/530, loss: 0.02781658060848713
2023-01-21 11:04:50.963820: step: 276/530, loss: 0.03851080313324928
2023-01-21 11:04:52.121141: step: 280/530, loss: 0.014957237057387829
2023-01-21 11:04:53.320242: step: 284/530, loss: 0.05188131704926491
2023-01-21 11:04:54.513388: step: 288/530, loss: 0.03757172077894211
2023-01-21 11:04:55.691696: step: 292/530, loss: 0.02761058881878853
2023-01-21 11:04:56.913180: step: 296/530, loss: 0.01653881184756756
2023-01-21 11:04:58.094646: step: 300/530, loss: 0.016524937003850937
2023-01-21 11:04:59.239910: step: 304/530, loss: 0.008461189456284046
2023-01-21 11:05:00.449818: step: 308/530, loss: 8.053779311012477e-05
2023-01-21 11:05:01.619676: step: 312/530, loss: 0.0366273894906044
2023-01-21 11:05:02.794094: step: 316/530, loss: 0.0012909173965454102
2023-01-21 11:05:04.012351: step: 320/530, loss: 0.023801803588867188
2023-01-21 11:05:05.176585: step: 324/530, loss: 0.0008293151622638106
2023-01-21 11:05:06.365692: step: 328/530, loss: 0.03199362754821777
2023-01-21 11:05:07.538463: step: 332/530, loss: 0.13491645455360413
2023-01-21 11:05:08.729906: step: 336/530, loss: 0.011737728491425514
2023-01-21 11:05:09.878951: step: 340/530, loss: 0.024299239739775658
2023-01-21 11:05:11.026204: step: 344/530, loss: 0.09101152420043945
2023-01-21 11:05:12.188982: step: 348/530, loss: 0.026349259540438652
2023-01-21 11:05:13.378179: step: 352/530, loss: 0.031373120844364166
2023-01-21 11:05:14.568490: step: 356/530, loss: 0.03548755869269371
2023-01-21 11:05:15.734931: step: 360/530, loss: 0.00036029814509674907
2023-01-21 11:05:16.911249: step: 364/530, loss: 0.00864486675709486
2023-01-21 11:05:18.091114: step: 368/530, loss: 0.009332561865448952
2023-01-21 11:05:19.354743: step: 372/530, loss: 0.07937565445899963
2023-01-21 11:05:20.520518: step: 376/530, loss: 0.0010450363624840975
2023-01-21 11:05:21.683834: step: 380/530, loss: 0.06399812549352646
2023-01-21 11:05:22.869508: step: 384/530, loss: 0.0003124237118754536
2023-01-21 11:05:24.064436: step: 388/530, loss: 0.01813633367419243
2023-01-21 11:05:25.226714: step: 392/530, loss: 0.01724863052368164
2023-01-21 11:05:26.399126: step: 396/530, loss: 0.011632204055786133
2023-01-21 11:05:27.598299: step: 400/530, loss: 0.01971001736819744
2023-01-21 11:05:28.774366: step: 404/530, loss: 0.046515464782714844
2023-01-21 11:05:29.885440: step: 408/530, loss: 0.030553722754120827
2023-01-21 11:05:31.066604: step: 412/530, loss: 0.07802248001098633
2023-01-21 11:05:32.277455: step: 416/530, loss: 0.08156929165124893
2023-01-21 11:05:33.458792: step: 420/530, loss: 0.05500011891126633
2023-01-21 11:05:34.667116: step: 424/530, loss: 0.003023648401722312
2023-01-21 11:05:35.837043: step: 428/530, loss: 0.007271194364875555
2023-01-21 11:05:37.016101: step: 432/530, loss: 0.006418276112526655
2023-01-21 11:05:38.201688: step: 436/530, loss: 9.250640869140625e-05
2023-01-21 11:05:39.371385: step: 440/530, loss: 0.018711091950535774
2023-01-21 11:05:40.583756: step: 444/530, loss: 0.002716541290283203
2023-01-21 11:05:41.756122: step: 448/530, loss: 0.12147793918848038
2023-01-21 11:05:42.993406: step: 452/530, loss: 0.018365859985351562
2023-01-21 11:05:44.181654: step: 456/530, loss: 0.044822487980127335
2023-01-21 11:05:45.338236: step: 460/530, loss: 0.003572750138118863
2023-01-21 11:05:46.530306: step: 464/530, loss: 0.7648254632949829
2023-01-21 11:05:47.718813: step: 468/530, loss: 0.03791303560137749
2023-01-21 11:05:48.892251: step: 472/530, loss: 0.21308287978172302
2023-01-21 11:05:50.059014: step: 476/530, loss: 0.041108131408691406
2023-01-21 11:05:51.221013: step: 480/530, loss: 0.007944297976791859
2023-01-21 11:05:52.375189: step: 484/530, loss: 0.9014477133750916
2023-01-21 11:05:53.565245: step: 488/530, loss: 0.00682024983689189
2023-01-21 11:05:54.731135: step: 492/530, loss: 0.030964158475399017
2023-01-21 11:05:55.896881: step: 496/530, loss: 0.05017905309796333
2023-01-21 11:05:57.074193: step: 500/530, loss: 0.0033727409318089485
2023-01-21 11:05:58.266465: step: 504/530, loss: 0.016001766547560692
2023-01-21 11:05:59.460904: step: 508/530, loss: 0.0001224517764057964
2023-01-21 11:06:00.655673: step: 512/530, loss: 0.07434673607349396
2023-01-21 11:06:01.842116: step: 516/530, loss: 0.04481200873851776
2023-01-21 11:06:03.054445: step: 520/530, loss: 0.0011455535423010588
2023-01-21 11:06:04.231052: step: 524/530, loss: 0.021541310474276543
2023-01-21 11:06:05.435539: step: 528/530, loss: 0.043240927159786224
2023-01-21 11:06:06.622724: step: 532/530, loss: 0.030040359124541283
2023-01-21 11:06:07.820742: step: 536/530, loss: 0.04299335554242134
2023-01-21 11:06:09.070531: step: 540/530, loss: 0.003161621280014515
2023-01-21 11:06:10.236184: step: 544/530, loss: 0.006895989179611206
2023-01-21 11:06:11.377688: step: 548/530, loss: 0.005281686782836914
2023-01-21 11:06:12.587315: step: 552/530, loss: 0.00727005023509264
2023-01-21 11:06:13.777034: step: 556/530, loss: 0.003036069916561246
2023-01-21 11:06:14.962516: step: 560/530, loss: 0.2000894546508789
2023-01-21 11:06:16.150936: step: 564/530, loss: 0.0015523433685302734
2023-01-21 11:06:17.391358: step: 568/530, loss: 0.03081808239221573
2023-01-21 11:06:18.579406: step: 572/530, loss: 0.04420357197523117
2023-01-21 11:06:19.760221: step: 576/530, loss: 0.09724970161914825
2023-01-21 11:06:20.956652: step: 580/530, loss: 0.0021519423462450504
2023-01-21 11:06:22.170636: step: 584/530, loss: 0.04981289058923721
2023-01-21 11:06:23.364322: step: 588/530, loss: 0.0010624408023431897
2023-01-21 11:06:24.541151: step: 592/530, loss: 0.15844625234603882
2023-01-21 11:06:25.709208: step: 596/530, loss: 0.1504998356103897
2023-01-21 11:06:26.853921: step: 600/530, loss: 0.08084221184253693
2023-01-21 11:06:28.019876: step: 604/530, loss: 0.00318489084020257
2023-01-21 11:06:29.204821: step: 608/530, loss: 0.036949921399354935
2023-01-21 11:06:30.408068: step: 612/530, loss: 0.016592122614383698
2023-01-21 11:06:31.595575: step: 616/530, loss: 0.08017349243164062
2023-01-21 11:06:32.771499: step: 620/530, loss: 0.06752233952283859
2023-01-21 11:06:33.935225: step: 624/530, loss: 0.0604739673435688
2023-01-21 11:06:35.112869: step: 628/530, loss: 0.08401575684547424
2023-01-21 11:06:36.341727: step: 632/530, loss: 0.05499892309308052
2023-01-21 11:06:37.538532: step: 636/530, loss: 0.031900547444820404
2023-01-21 11:06:38.738541: step: 640/530, loss: 0.002302026841789484
2023-01-21 11:06:39.933109: step: 644/530, loss: 0.009116267785429955
2023-01-21 11:06:41.134753: step: 648/530, loss: 0.07885608822107315
2023-01-21 11:06:42.319017: step: 652/530, loss: 0.02750530280172825
2023-01-21 11:06:43.490329: step: 656/530, loss: 0.012879181653261185
2023-01-21 11:06:44.679240: step: 660/530, loss: 0.03186340257525444
2023-01-21 11:06:45.870538: step: 664/530, loss: 0.005229854956269264
2023-01-21 11:06:47.044343: step: 668/530, loss: 0.0010556221241131425
2023-01-21 11:06:48.240184: step: 672/530, loss: 0.19363000988960266
2023-01-21 11:06:49.418519: step: 676/530, loss: 0.04679255187511444
2023-01-21 11:06:50.590341: step: 680/530, loss: 0.05420274659991264
2023-01-21 11:06:51.769291: step: 684/530, loss: 0.018144989386200905
2023-01-21 11:06:52.974634: step: 688/530, loss: 0.02951631508767605
2023-01-21 11:06:54.190602: step: 692/530, loss: 0.01581134833395481
2023-01-21 11:06:55.370347: step: 696/530, loss: 0.056913089007139206
2023-01-21 11:06:56.553468: step: 700/530, loss: 0.02740616723895073
2023-01-21 11:06:57.726374: step: 704/530, loss: 0.0027685165405273438
2023-01-21 11:06:58.925529: step: 708/530, loss: 0.02155456691980362
2023-01-21 11:07:00.097175: step: 712/530, loss: 0.5384508967399597
2023-01-21 11:07:01.346852: step: 716/530, loss: 0.057607077062129974
2023-01-21 11:07:02.550208: step: 720/530, loss: 0.03325338289141655
2023-01-21 11:07:03.736290: step: 724/530, loss: 0.06819362938404083
2023-01-21 11:07:04.897792: step: 728/530, loss: 0.01794595830142498
2023-01-21 11:07:06.085429: step: 732/530, loss: 0.047089386731386185
2023-01-21 11:07:07.263797: step: 736/530, loss: 0.039314351975917816
2023-01-21 11:07:08.472431: step: 740/530, loss: 0.1279180943965912
2023-01-21 11:07:09.687431: step: 744/530, loss: 0.025859545916318893
2023-01-21 11:07:10.839478: step: 748/530, loss: 0.008913707919418812
2023-01-21 11:07:12.024816: step: 752/530, loss: 0.01743330992758274
2023-01-21 11:07:13.220234: step: 756/530, loss: 0.0414886474609375
2023-01-21 11:07:14.391815: step: 760/530, loss: 0.0010725022293627262
2023-01-21 11:07:15.571545: step: 764/530, loss: 0.04817771911621094
2023-01-21 11:07:16.767946: step: 768/530, loss: 0.003217315534129739
2023-01-21 11:07:17.959611: step: 772/530, loss: 0.07857837527990341
2023-01-21 11:07:19.159764: step: 776/530, loss: 0.017726801335811615
2023-01-21 11:07:20.343736: step: 780/530, loss: 0.030484486371278763
2023-01-21 11:07:21.522389: step: 784/530, loss: 0.02863159216940403
2023-01-21 11:07:22.701447: step: 788/530, loss: 0.0013018609024584293
2023-01-21 11:07:23.858022: step: 792/530, loss: 0.010592461563646793
2023-01-21 11:07:25.082751: step: 796/530, loss: 0.01967344433069229
2023-01-21 11:07:26.256059: step: 800/530, loss: 0.04925537109375
2023-01-21 11:07:27.454689: step: 804/530, loss: 0.0899820402264595
2023-01-21 11:07:28.605881: step: 808/530, loss: 0.03359708935022354
2023-01-21 11:07:29.802051: step: 812/530, loss: 0.00382652273401618
2023-01-21 11:07:30.965855: step: 816/530, loss: 0.05983119085431099
2023-01-21 11:07:32.159209: step: 820/530, loss: 0.003077983856201172
2023-01-21 11:07:33.328160: step: 824/530, loss: 0.05077343061566353
2023-01-21 11:07:34.485291: step: 828/530, loss: 0.006889295764267445
2023-01-21 11:07:35.670574: step: 832/530, loss: 0.09661149978637695
2023-01-21 11:07:36.829804: step: 836/530, loss: 0.031653691083192825
2023-01-21 11:07:38.026597: step: 840/530, loss: 0.04574785381555557
2023-01-21 11:07:39.230638: step: 844/530, loss: 0.044326018542051315
2023-01-21 11:07:40.387655: step: 848/530, loss: 0.005500888917595148
2023-01-21 11:07:41.569095: step: 852/530, loss: 0.003118896624073386
2023-01-21 11:07:42.731927: step: 856/530, loss: 0.0013906002277508378
2023-01-21 11:07:43.951328: step: 860/530, loss: 0.0016504287486895919
2023-01-21 11:07:45.136055: step: 864/530, loss: 0.5100079774856567
2023-01-21 11:07:46.336333: step: 868/530, loss: 0.022423982620239258
2023-01-21 11:07:47.575241: step: 872/530, loss: 0.027982044965028763
2023-01-21 11:07:48.788003: step: 876/530, loss: 0.14508409798145294
2023-01-21 11:07:49.969263: step: 880/530, loss: 0.04071082919836044
2023-01-21 11:07:51.143510: step: 884/530, loss: 0.06281118094921112
2023-01-21 11:07:52.383832: step: 888/530, loss: 0.04635439068078995
2023-01-21 11:07:53.571660: step: 892/530, loss: 0.0015818595420569181
2023-01-21 11:07:54.700532: step: 896/530, loss: 0.06765918433666229
2023-01-21 11:07:55.891239: step: 900/530, loss: 0.0043177129700779915
2023-01-21 11:07:57.046346: step: 904/530, loss: 0.0007412910345010459
2023-01-21 11:07:58.218190: step: 908/530, loss: 0.004104328341782093
2023-01-21 11:07:59.439293: step: 912/530, loss: 0.1634574830532074
2023-01-21 11:08:00.588596: step: 916/530, loss: 0.015868186950683594
2023-01-21 11:08:01.756126: step: 920/530, loss: 0.1938001662492752
2023-01-21 11:08:02.922849: step: 924/530, loss: 0.005743575282394886
2023-01-21 11:08:04.072616: step: 928/530, loss: 0.01637239381670952
2023-01-21 11:08:05.226556: step: 932/530, loss: 0.12501315772533417
2023-01-21 11:08:06.374127: step: 936/530, loss: 0.07079906761646271
2023-01-21 11:08:07.523671: step: 940/530, loss: 0.022710038349032402
2023-01-21 11:08:08.774096: step: 944/530, loss: 0.00318660750053823
2023-01-21 11:08:09.947635: step: 948/530, loss: 0.05477261543273926
2023-01-21 11:08:11.118119: step: 952/530, loss: 0.005396461579948664
2023-01-21 11:08:12.364987: step: 956/530, loss: 0.022456789389252663
2023-01-21 11:08:13.561880: step: 960/530, loss: 0.0454380065202713
2023-01-21 11:08:14.749275: step: 964/530, loss: 0.0349576473236084
2023-01-21 11:08:15.908702: step: 968/530, loss: 0.2040906846523285
2023-01-21 11:08:17.085511: step: 972/530, loss: 0.03086109273135662
2023-01-21 11:08:18.270134: step: 976/530, loss: 0.001462745713070035
2023-01-21 11:08:19.462444: step: 980/530, loss: 0.006218624301254749
2023-01-21 11:08:20.636654: step: 984/530, loss: 0.012676960788667202
2023-01-21 11:08:21.806017: step: 988/530, loss: 0.030625535175204277
2023-01-21 11:08:22.964885: step: 992/530, loss: 0.006389808841049671
2023-01-21 11:08:24.127609: step: 996/530, loss: 0.03521919250488281
2023-01-21 11:08:25.335028: step: 1000/530, loss: 0.0711248368024826
2023-01-21 11:08:26.533192: step: 1004/530, loss: 0.4516476094722748
2023-01-21 11:08:27.704251: step: 1008/530, loss: 0.08084497600793839
2023-01-21 11:08:28.868147: step: 1012/530, loss: 0.037183571606874466
2023-01-21 11:08:30.087540: step: 1016/530, loss: 0.02343006245791912
2023-01-21 11:08:31.229978: step: 1020/530, loss: 0.030205916613340378
2023-01-21 11:08:32.408782: step: 1024/530, loss: 0.0069265603087842464
2023-01-21 11:08:33.592398: step: 1028/530, loss: 0.03138399124145508
2023-01-21 11:08:34.762980: step: 1032/530, loss: 0.2080448567867279
2023-01-21 11:08:35.937762: step: 1036/530, loss: 0.016057683154940605
2023-01-21 11:08:37.107004: step: 1040/530, loss: 0.009854758158326149
2023-01-21 11:08:38.295971: step: 1044/530, loss: 0.0025699613615870476
2023-01-21 11:08:39.496522: step: 1048/530, loss: 0.007089519873261452
2023-01-21 11:08:40.690082: step: 1052/530, loss: 0.001720094820484519
2023-01-21 11:08:41.913755: step: 1056/530, loss: 0.03613109886646271
2023-01-21 11:08:43.106851: step: 1060/530, loss: 0.05500316619873047
2023-01-21 11:08:44.290512: step: 1064/530, loss: 0.02976360358297825
2023-01-21 11:08:45.442902: step: 1068/530, loss: 0.04345393180847168
2023-01-21 11:08:46.614467: step: 1072/530, loss: 0.018426895141601562
2023-01-21 11:08:47.792358: step: 1076/530, loss: 0.027219295501708984
2023-01-21 11:08:48.980878: step: 1080/530, loss: 0.05236215889453888
2023-01-21 11:08:50.148254: step: 1084/530, loss: 0.004300212953239679
2023-01-21 11:08:51.325644: step: 1088/530, loss: 0.008438682183623314
2023-01-21 11:08:52.489058: step: 1092/530, loss: 0.05838584899902344
2023-01-21 11:08:53.633907: step: 1096/530, loss: 0.015949105843901634
2023-01-21 11:08:54.797674: step: 1100/530, loss: 0.018606949597597122
2023-01-21 11:08:55.969383: step: 1104/530, loss: 0.01111612282693386
2023-01-21 11:08:57.164085: step: 1108/530, loss: 0.034040018916130066
2023-01-21 11:08:58.361212: step: 1112/530, loss: 0.02906627580523491
2023-01-21 11:08:59.499419: step: 1116/530, loss: 0.0007879257318563759
2023-01-21 11:09:00.651074: step: 1120/530, loss: 0.026818467304110527
2023-01-21 11:09:01.818627: step: 1124/530, loss: 0.011390876956284046
2023-01-21 11:09:02.995891: step: 1128/530, loss: 0.07379169017076492
2023-01-21 11:09:04.190433: step: 1132/530, loss: 0.027565576136112213
2023-01-21 11:09:05.339638: step: 1136/530, loss: 0.04830484092235565
2023-01-21 11:09:06.487487: step: 1140/530, loss: 0.011463964357972145
2023-01-21 11:09:07.647489: step: 1144/530, loss: 0.0051781656220555305
2023-01-21 11:09:08.847414: step: 1148/530, loss: 0.028452303260564804
2023-01-21 11:09:10.013775: step: 1152/530, loss: 0.0016143799293786287
2023-01-21 11:09:11.198168: step: 1156/530, loss: 0.0073677063919603825
2023-01-21 11:09:12.366713: step: 1160/530, loss: 0.004320573527365923
2023-01-21 11:09:13.548659: step: 1164/530, loss: 0.0498235709965229
2023-01-21 11:09:14.671752: step: 1168/530, loss: 0.02599926106631756
2023-01-21 11:09:15.912467: step: 1172/530, loss: 0.006445980165153742
2023-01-21 11:09:17.061386: step: 1176/530, loss: 0.06946630775928497
2023-01-21 11:09:18.223359: step: 1180/530, loss: 0.04059161990880966
2023-01-21 11:09:19.421466: step: 1184/530, loss: 0.7745113372802734
2023-01-21 11:09:20.623603: step: 1188/530, loss: 0.004688644781708717
2023-01-21 11:09:21.780689: step: 1192/530, loss: 0.05381498485803604
2023-01-21 11:09:22.933106: step: 1196/530, loss: 0.12576213479042053
2023-01-21 11:09:24.144515: step: 1200/530, loss: 0.055941104888916016
2023-01-21 11:09:25.312705: step: 1204/530, loss: 0.0019638061057776213
2023-01-21 11:09:26.504508: step: 1208/530, loss: 0.0069900513626635075
2023-01-21 11:09:27.678616: step: 1212/530, loss: 0.025630176067352295
2023-01-21 11:09:28.841907: step: 1216/530, loss: 0.008081626147031784
2023-01-21 11:09:30.028407: step: 1220/530, loss: 0.197139173746109
2023-01-21 11:09:31.220099: step: 1224/530, loss: 0.21018867194652557
2023-01-21 11:09:32.453790: step: 1228/530, loss: 0.03912658616900444
2023-01-21 11:09:33.680242: step: 1232/530, loss: 0.009834576398134232
2023-01-21 11:09:34.862545: step: 1236/530, loss: 0.022298814728856087
2023-01-21 11:09:36.110959: step: 1240/530, loss: 0.04949913173913956
2023-01-21 11:09:37.343889: step: 1244/530, loss: 0.0898275375366211
2023-01-21 11:09:38.507444: step: 1248/530, loss: 0.015247059054672718
2023-01-21 11:09:39.634998: step: 1252/530, loss: 0.0723399668931961
2023-01-21 11:09:40.807475: step: 1256/530, loss: 0.06293907016515732
2023-01-21 11:09:42.005289: step: 1260/530, loss: 0.0009050369262695312
2023-01-21 11:09:43.209483: step: 1264/530, loss: 0.002594518708065152
2023-01-21 11:09:44.335411: step: 1268/530, loss: 0.002685463521629572
2023-01-21 11:09:45.547881: step: 1272/530, loss: 0.057027675211429596
2023-01-21 11:09:46.720804: step: 1276/530, loss: 0.08052831143140793
2023-01-21 11:09:47.864652: step: 1280/530, loss: 0.01505060214549303
2023-01-21 11:09:49.006736: step: 1284/530, loss: 0.029803801327943802
2023-01-21 11:09:50.209325: step: 1288/530, loss: 0.025468112900853157
2023-01-21 11:09:51.350276: step: 1292/530, loss: 0.00043969156104139984
2023-01-21 11:09:52.515801: step: 1296/530, loss: 0.010682773776352406
2023-01-21 11:09:53.689164: step: 1300/530, loss: 0.1137937605381012
2023-01-21 11:09:54.891484: step: 1304/530, loss: 0.027657128870487213
2023-01-21 11:09:56.058325: step: 1308/530, loss: 0.011874580755829811
2023-01-21 11:09:57.271140: step: 1312/530, loss: 0.04600878059864044
2023-01-21 11:09:58.482085: step: 1316/530, loss: 0.0014074326027184725
2023-01-21 11:09:59.628112: step: 1320/530, loss: 0.021350719034671783
2023-01-21 11:10:00.822149: step: 1324/530, loss: 0.012481975369155407
2023-01-21 11:10:01.998319: step: 1328/530, loss: 0.0025527954567223787
2023-01-21 11:10:03.169241: step: 1332/530, loss: 0.047113802284002304
2023-01-21 11:10:04.326646: step: 1336/530, loss: 0.0023443223908543587
2023-01-21 11:10:05.507884: step: 1340/530, loss: 0.008775711059570312
2023-01-21 11:10:06.696281: step: 1344/530, loss: 0.0011129856575280428
2023-01-21 11:10:07.879617: step: 1348/530, loss: 0.009422589093446732
2023-01-21 11:10:09.034341: step: 1352/530, loss: 0.018490411341190338
2023-01-21 11:10:10.203029: step: 1356/530, loss: 0.09592895954847336
2023-01-21 11:10:11.392305: step: 1360/530, loss: 0.012968159280717373
2023-01-21 11:10:12.637954: step: 1364/530, loss: 0.030870914459228516
2023-01-21 11:10:13.820501: step: 1368/530, loss: 0.0030160904861986637
2023-01-21 11:10:15.007900: step: 1372/530, loss: 0.055434610694646835
2023-01-21 11:10:16.226393: step: 1376/530, loss: 0.016527557745575905
2023-01-21 11:10:17.455207: step: 1380/530, loss: 0.020285796374082565
2023-01-21 11:10:18.654617: step: 1384/530, loss: 0.004257965367287397
2023-01-21 11:10:19.872128: step: 1388/530, loss: 0.07973413169384003
2023-01-21 11:10:21.008135: step: 1392/530, loss: 0.015843581408262253
2023-01-21 11:10:22.181206: step: 1396/530, loss: 0.035280752927064896
2023-01-21 11:10:23.371253: step: 1400/530, loss: 0.05140829086303711
2023-01-21 11:10:24.541905: step: 1404/530, loss: 0.024033930152654648
2023-01-21 11:10:25.741973: step: 1408/530, loss: 0.02801494486629963
2023-01-21 11:10:26.914164: step: 1412/530, loss: 0.01301121711730957
2023-01-21 11:10:28.108518: step: 1416/530, loss: 0.03600273281335831
2023-01-21 11:10:29.285742: step: 1420/530, loss: 0.013945722952485085
2023-01-21 11:10:30.509710: step: 1424/530, loss: 0.02272195927798748
2023-01-21 11:10:31.697641: step: 1428/530, loss: 0.006911754608154297
2023-01-21 11:10:32.854945: step: 1432/530, loss: 0.0638633742928505
2023-01-21 11:10:34.031806: step: 1436/530, loss: 0.04619426652789116
2023-01-21 11:10:35.194552: step: 1440/530, loss: 0.07546253502368927
2023-01-21 11:10:36.428926: step: 1444/530, loss: 0.02346172370016575
2023-01-21 11:10:37.575100: step: 1448/530, loss: 6.341934204101562e-05
2023-01-21 11:10:38.774345: step: 1452/530, loss: 0.0018310786690562963
2023-01-21 11:10:39.998674: step: 1456/530, loss: 0.031105805188417435
2023-01-21 11:10:41.179005: step: 1460/530, loss: 0.02681441232562065
2023-01-21 11:10:42.334649: step: 1464/530, loss: 0.0038092555478215218
2023-01-21 11:10:43.525129: step: 1468/530, loss: 0.05331917107105255
2023-01-21 11:10:44.700605: step: 1472/530, loss: 0.03397655487060547
2023-01-21 11:10:45.853646: step: 1476/530, loss: 0.015234089456498623
2023-01-21 11:10:47.016659: step: 1480/530, loss: 0.026860762387514114
2023-01-21 11:10:48.254650: step: 1484/530, loss: 0.027602292597293854
2023-01-21 11:10:49.419505: step: 1488/530, loss: 0.0027087214402854443
2023-01-21 11:10:50.567244: step: 1492/530, loss: 0.024042701348662376
2023-01-21 11:10:51.736720: step: 1496/530, loss: 0.038811683654785156
2023-01-21 11:10:52.931675: step: 1500/530, loss: 0.1528741866350174
2023-01-21 11:10:54.119641: step: 1504/530, loss: 0.00217189802788198
2023-01-21 11:10:55.380733: step: 1508/530, loss: 0.06387176364660263
2023-01-21 11:10:56.605325: step: 1512/530, loss: 0.0021766661666333675
2023-01-21 11:10:57.824095: step: 1516/530, loss: 0.1542484313249588
2023-01-21 11:10:59.002952: step: 1520/530, loss: 0.010139275342226028
2023-01-21 11:11:00.155429: step: 1524/530, loss: 0.011534690856933594
2023-01-21 11:11:01.330074: step: 1528/530, loss: 0.0005631446838378906
2023-01-21 11:11:02.447177: step: 1532/530, loss: 0.004104232881218195
2023-01-21 11:11:03.774122: step: 1536/530, loss: 0.009630585089325905
2023-01-21 11:11:04.965942: step: 1540/530, loss: 0.0017056465148925781
2023-01-21 11:11:06.107172: step: 1544/530, loss: 0.0388704314827919
2023-01-21 11:11:07.287555: step: 1548/530, loss: 0.033559419214725494
2023-01-21 11:11:08.471921: step: 1552/530, loss: 0.018369292840361595
2023-01-21 11:11:09.680420: step: 1556/530, loss: 0.043837834149599075
2023-01-21 11:11:10.824656: step: 1560/530, loss: 0.03452129662036896
2023-01-21 11:11:11.957250: step: 1564/530, loss: 0.0033347131684422493
2023-01-21 11:11:13.099986: step: 1568/530, loss: 0.012446403503417969
2023-01-21 11:11:14.301652: step: 1572/530, loss: 0.0006779670948162675
2023-01-21 11:11:15.491957: step: 1576/530, loss: 0.043444253504276276
2023-01-21 11:11:16.663381: step: 1580/530, loss: 0.03304595872759819
2023-01-21 11:11:17.843558: step: 1584/530, loss: 0.03993959352374077
2023-01-21 11:11:18.970435: step: 1588/530, loss: 0.08206450939178467
2023-01-21 11:11:20.148406: step: 1592/530, loss: 0.10245351493358612
2023-01-21 11:11:21.334511: step: 1596/530, loss: 0.08339233696460724
2023-01-21 11:11:22.490312: step: 1600/530, loss: 0.18985921144485474
2023-01-21 11:11:23.674927: step: 1604/530, loss: 0.033182334154844284
2023-01-21 11:11:24.827105: step: 1608/530, loss: 0.02825145795941353
2023-01-21 11:11:26.008045: step: 1612/530, loss: 0.021605681627988815
2023-01-21 11:11:27.183883: step: 1616/530, loss: 0.003261566162109375
2023-01-21 11:11:28.352206: step: 1620/530, loss: 0.03140435367822647
2023-01-21 11:11:29.561486: step: 1624/530, loss: 0.04887790605425835
2023-01-21 11:11:30.730008: step: 1628/530, loss: 0.08900509029626846
2023-01-21 11:11:31.904578: step: 1632/530, loss: 0.05209656059741974
2023-01-21 11:11:33.084522: step: 1636/530, loss: 0.0017317772144451737
2023-01-21 11:11:34.271252: step: 1640/530, loss: 0.004494285676628351
2023-01-21 11:11:35.469195: step: 1644/530, loss: 0.003970908932387829
2023-01-21 11:11:36.654871: step: 1648/530, loss: 0.45489102602005005
2023-01-21 11:11:37.858437: step: 1652/530, loss: 0.06994466483592987
2023-01-21 11:11:39.024630: step: 1656/530, loss: 0.001082003116607666
2023-01-21 11:11:40.212110: step: 1660/530, loss: 0.0005039215320721269
2023-01-21 11:11:41.372181: step: 1664/530, loss: 0.3520415127277374
2023-01-21 11:11:42.598802: step: 1668/530, loss: 0.19139176607131958
2023-01-21 11:11:43.754152: step: 1672/530, loss: 0.0066697122529149055
2023-01-21 11:11:44.937194: step: 1676/530, loss: 0.039824679493904114
2023-01-21 11:11:46.078721: step: 1680/530, loss: 0.011526679620146751
2023-01-21 11:11:47.272226: step: 1684/530, loss: 0.0436711311340332
2023-01-21 11:11:48.437487: step: 1688/530, loss: 0.0016387939685955644
2023-01-21 11:11:49.611365: step: 1692/530, loss: 0.05077200010418892
2023-01-21 11:11:50.803547: step: 1696/530, loss: 0.3122484087944031
2023-01-21 11:11:51.982706: step: 1700/530, loss: 0.012789345346391201
2023-01-21 11:11:53.218570: step: 1704/530, loss: 0.0004842162015847862
2023-01-21 11:11:54.463938: step: 1708/530, loss: 0.040705014020204544
2023-01-21 11:11:55.666600: step: 1712/530, loss: 0.002182579133659601
2023-01-21 11:11:56.852671: step: 1716/530, loss: 0.006494331639260054
2023-01-21 11:11:58.015462: step: 1720/530, loss: 0.04466447979211807
2023-01-21 11:11:59.200963: step: 1724/530, loss: 0.031276896595954895
2023-01-21 11:12:00.427610: step: 1728/530, loss: 0.019397640600800514
2023-01-21 11:12:01.594487: step: 1732/530, loss: 0.00012817383685614914
2023-01-21 11:12:02.809577: step: 1736/530, loss: 0.05592556297779083
2023-01-21 11:12:03.961929: step: 1740/530, loss: 0.009619355201721191
2023-01-21 11:12:05.111577: step: 1744/530, loss: 0.012849295511841774
2023-01-21 11:12:06.326584: step: 1748/530, loss: 0.09731273353099823
2023-01-21 11:12:07.504046: step: 1752/530, loss: 0.008343554101884365
2023-01-21 11:12:08.685727: step: 1756/530, loss: 0.021152783185243607
2023-01-21 11:12:09.904178: step: 1760/530, loss: 0.10981273651123047
2023-01-21 11:12:11.049926: step: 1764/530, loss: 0.020770955830812454
2023-01-21 11:12:12.219447: step: 1768/530, loss: 0.00115547189489007
2023-01-21 11:12:13.438406: step: 1772/530, loss: 0.0037407875061035156
2023-01-21 11:12:14.573478: step: 1776/530, loss: 0.32936277985572815
2023-01-21 11:12:15.746815: step: 1780/530, loss: 0.0162995345890522
2023-01-21 11:12:16.959028: step: 1784/530, loss: 0.029982376843690872
2023-01-21 11:12:18.083723: step: 1788/530, loss: 0.02543935924768448
2023-01-21 11:12:19.304184: step: 1792/530, loss: 0.37025895714759827
2023-01-21 11:12:20.453413: step: 1796/530, loss: 0.05530863255262375
2023-01-21 11:12:21.619193: step: 1800/530, loss: 0.01102457009255886
2023-01-21 11:12:22.780079: step: 1804/530, loss: 0.04209136962890625
2023-01-21 11:12:24.031294: step: 1808/530, loss: 0.08808784186840057
2023-01-21 11:12:25.225772: step: 1812/530, loss: 0.0662657767534256
2023-01-21 11:12:26.414901: step: 1816/530, loss: 0.03845701366662979
2023-01-21 11:12:27.589652: step: 1820/530, loss: 0.2588590979576111
2023-01-21 11:12:28.742407: step: 1824/530, loss: 0.010533714666962624
2023-01-21 11:12:29.952409: step: 1828/530, loss: 0.06527681648731232
2023-01-21 11:12:31.107712: step: 1832/530, loss: 0.03574400022625923
2023-01-21 11:12:32.299305: step: 1836/530, loss: 0.006679725833237171
2023-01-21 11:12:33.524151: step: 1840/530, loss: 0.07653055340051651
2023-01-21 11:12:34.736535: step: 1844/530, loss: 0.039412688463926315
2023-01-21 11:12:35.917704: step: 1848/530, loss: 0.10504503548145294
2023-01-21 11:12:37.106148: step: 1852/530, loss: 0.03179464116692543
2023-01-21 11:12:38.273240: step: 1856/530, loss: 0.002290058182552457
2023-01-21 11:12:39.458834: step: 1860/530, loss: 0.046096041798591614
2023-01-21 11:12:40.672602: step: 1864/530, loss: 0.008079242892563343
2023-01-21 11:12:41.876714: step: 1868/530, loss: 0.050446607172489166
2023-01-21 11:12:43.028876: step: 1872/530, loss: 0.02783660776913166
2023-01-21 11:12:44.206472: step: 1876/530, loss: 0.35977888107299805
2023-01-21 11:12:45.373705: step: 1880/530, loss: 0.003995847888290882
2023-01-21 11:12:46.538801: step: 1884/530, loss: 0.0009283066028729081
2023-01-21 11:12:47.703259: step: 1888/530, loss: 0.0012603760696947575
2023-01-21 11:12:48.888611: step: 1892/530, loss: 0.0046125175431370735
2023-01-21 11:12:50.076119: step: 1896/530, loss: 0.043888092041015625
2023-01-21 11:12:51.285573: step: 1900/530, loss: 0.045587629079818726
2023-01-21 11:12:52.470795: step: 1904/530, loss: 0.028281785547733307
2023-01-21 11:12:53.637996: step: 1908/530, loss: 0.05299057811498642
2023-01-21 11:12:54.812249: step: 1912/530, loss: 0.0056397439911961555
2023-01-21 11:12:56.005102: step: 1916/530, loss: 0.038083840161561966
2023-01-21 11:12:57.242577: step: 1920/530, loss: 0.017345238476991653
2023-01-21 11:12:58.404656: step: 1924/530, loss: 0.012544489465653896
2023-01-21 11:12:59.549468: step: 1928/530, loss: 0.0034304617438465357
2023-01-21 11:13:00.686605: step: 1932/530, loss: 0.020808935165405273
2023-01-21 11:13:01.879154: step: 1936/530, loss: 0.18250125646591187
2023-01-21 11:13:03.067512: step: 1940/530, loss: 0.09156279265880585
2023-01-21 11:13:04.240268: step: 1944/530, loss: 0.0009279251098632812
2023-01-21 11:13:05.447552: step: 1948/530, loss: 5.1116945542162284e-05
2023-01-21 11:13:06.665738: step: 1952/530, loss: 0.0040187835693359375
2023-01-21 11:13:07.815049: step: 1956/530, loss: 0.07841896265745163
2023-01-21 11:13:08.988906: step: 1960/530, loss: 0.007194042205810547
2023-01-21 11:13:10.167213: step: 1964/530, loss: 0.19128721952438354
2023-01-21 11:13:11.357986: step: 1968/530, loss: 0.12925635278224945
2023-01-21 11:13:12.573334: step: 1972/530, loss: 0.02354593202471733
2023-01-21 11:13:13.738577: step: 1976/530, loss: 0.010048103518784046
2023-01-21 11:13:14.889198: step: 1980/530, loss: 0.027831651270389557
2023-01-21 11:13:16.043473: step: 1984/530, loss: 0.006035804748535156
2023-01-21 11:13:17.239740: step: 1988/530, loss: 0.02407665178179741
2023-01-21 11:13:18.449133: step: 1992/530, loss: 0.004284668248146772
2023-01-21 11:13:19.574203: step: 1996/530, loss: 0.01672450266778469
2023-01-21 11:13:20.787190: step: 2000/530, loss: 0.08963127434253693
2023-01-21 11:13:22.001825: step: 2004/530, loss: 0.07505510747432709
2023-01-21 11:13:23.185171: step: 2008/530, loss: 0.02849707566201687
2023-01-21 11:13:24.329929: step: 2012/530, loss: 0.029717542231082916
2023-01-21 11:13:25.528666: step: 2016/530, loss: 0.06522579491138458
2023-01-21 11:13:26.735087: step: 2020/530, loss: 0.009841347113251686
2023-01-21 11:13:27.898383: step: 2024/530, loss: 0.0014075279468670487
2023-01-21 11:13:29.076822: step: 2028/530, loss: 0.06392069160938263
2023-01-21 11:13:30.241020: step: 2032/530, loss: 0.0010433197021484375
2023-01-21 11:13:31.434581: step: 2036/530, loss: 0.0015927791828289628
2023-01-21 11:13:32.588952: step: 2040/530, loss: 0.035505104809999466
2023-01-21 11:13:33.724730: step: 2044/530, loss: 0.0015538216102868319
2023-01-21 11:13:34.917280: step: 2048/530, loss: 0.01734161376953125
2023-01-21 11:13:36.116489: step: 2052/530, loss: 0.02013712003827095
2023-01-21 11:13:37.301444: step: 2056/530, loss: 0.02535095438361168
2023-01-21 11:13:38.482609: step: 2060/530, loss: 0.051574040204286575
2023-01-21 11:13:39.642704: step: 2064/530, loss: 0.00611190777271986
2023-01-21 11:13:40.862850: step: 2068/530, loss: 0.006221341900527477
2023-01-21 11:13:42.055946: step: 2072/530, loss: 0.006866836920380592
2023-01-21 11:13:43.263405: step: 2076/530, loss: 0.004740429110825062
2023-01-21 11:13:44.433585: step: 2080/530, loss: 0.002010345458984375
2023-01-21 11:13:45.569889: step: 2084/530, loss: 0.01877002604305744
2023-01-21 11:13:46.773241: step: 2088/530, loss: 0.03775526210665703
2023-01-21 11:13:47.965623: step: 2092/530, loss: 0.5075481534004211
2023-01-21 11:13:49.197513: step: 2096/530, loss: 0.005015468690544367
2023-01-21 11:13:50.338855: step: 2100/530, loss: 0.08266053348779678
2023-01-21 11:13:51.505750: step: 2104/530, loss: 0.05380840227007866
2023-01-21 11:13:52.702792: step: 2108/530, loss: 0.07045798748731613
2023-01-21 11:13:53.877392: step: 2112/530, loss: 0.09061752259731293
2023-01-21 11:13:55.037407: step: 2116/530, loss: 0.008649301715195179
2023-01-21 11:13:56.243911: step: 2120/530, loss: 0.10937127470970154
==================================================
Loss: 0.049
--------------------
Dev: {'event': {'p': 0.5811088295687885, 'r': 0.7536617842876165, 'f1': 0.6562318840579711}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6560747663551402, 'r': 0.8073605520414031, 'f1': 0.7238979118329466}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5632183908045977, 'r': 0.9074074074074074, 'f1': 0.6950354609929078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.631578947368421, 'r': 0.5714285714285714, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.40384615384615385, 'r': 0.5833333333333334, 'f1': 0.4772727272727273}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:14:41.906077: step: 4/530, loss: 0.012654876336455345
2023-01-21 11:14:43.060885: step: 8/530, loss: 0.031279660761356354
2023-01-21 11:14:44.274572: step: 12/530, loss: 0.0005647659418173134
2023-01-21 11:14:45.444260: step: 16/530, loss: 0.03277578204870224
2023-01-21 11:14:46.625146: step: 20/530, loss: 0.00781717337667942
2023-01-21 11:14:47.805788: step: 24/530, loss: 0.014646721072494984
2023-01-21 11:14:48.965220: step: 28/530, loss: 0.05620861425995827
2023-01-21 11:14:50.120418: step: 32/530, loss: 0.0042243958450853825
2023-01-21 11:14:51.289038: step: 36/530, loss: 0.0020406723488122225
2023-01-21 11:14:52.473810: step: 40/530, loss: 0.2573424279689789
2023-01-21 11:14:53.674751: step: 44/530, loss: 0.026294900104403496
2023-01-21 11:14:54.858000: step: 48/530, loss: 0.037817955017089844
2023-01-21 11:14:56.048135: step: 52/530, loss: 0.021404219791293144
2023-01-21 11:14:57.202990: step: 56/530, loss: 0.008617496117949486
2023-01-21 11:14:58.367627: step: 60/530, loss: 0.002383756684139371
2023-01-21 11:14:59.553694: step: 64/530, loss: 0.009491157718002796
2023-01-21 11:15:00.738050: step: 68/530, loss: 0.002452754881232977
2023-01-21 11:15:01.953098: step: 72/530, loss: 0.008034229278564453
2023-01-21 11:15:03.177505: step: 76/530, loss: 0.011966134421527386
2023-01-21 11:15:04.356262: step: 80/530, loss: 0.0012308120494708419
2023-01-21 11:15:05.518343: step: 84/530, loss: 0.03331294283270836
2023-01-21 11:15:06.701679: step: 88/530, loss: 0.015697766095399857
2023-01-21 11:15:07.890101: step: 92/530, loss: 0.00083074567373842
2023-01-21 11:15:09.060839: step: 96/530, loss: 0.0025950432755053043
2023-01-21 11:15:10.237735: step: 100/530, loss: 0.025836946442723274
2023-01-21 11:15:11.432583: step: 104/530, loss: 0.016163254156708717
2023-01-21 11:15:12.648442: step: 108/530, loss: 0.011761380359530449
2023-01-21 11:15:13.857070: step: 112/530, loss: 0.011208630166947842
2023-01-21 11:15:15.061647: step: 116/530, loss: 0.017702102661132812
2023-01-21 11:15:16.241325: step: 120/530, loss: 0.008686828427016735
2023-01-21 11:15:17.409497: step: 124/530, loss: 0.048345375806093216
2023-01-21 11:15:18.572835: step: 128/530, loss: 0.015298986807465553
2023-01-21 11:15:19.750732: step: 132/530, loss: 0.00019350052752997726
2023-01-21 11:15:20.907245: step: 136/530, loss: 0.04834280163049698
2023-01-21 11:15:22.075828: step: 140/530, loss: 0.004429721739143133
2023-01-21 11:15:23.251543: step: 144/530, loss: 0.004958629608154297
2023-01-21 11:15:24.430913: step: 148/530, loss: 0.018026161938905716
2023-01-21 11:15:25.579504: step: 152/530, loss: 0.010579586029052734
2023-01-21 11:15:26.738623: step: 156/530, loss: 0.05545216053724289
2023-01-21 11:15:27.913700: step: 160/530, loss: 0.06578245759010315
2023-01-21 11:15:29.114448: step: 164/530, loss: 0.006092071998864412
2023-01-21 11:15:30.281855: step: 168/530, loss: 0.002249217126518488
2023-01-21 11:15:31.419442: step: 172/530, loss: 0.16732731461524963
2023-01-21 11:15:32.595854: step: 176/530, loss: 0.0009834289085119963
2023-01-21 11:15:33.794475: step: 180/530, loss: 0.04420214146375656
2023-01-21 11:15:35.000260: step: 184/530, loss: 0.009236622601747513
2023-01-21 11:15:36.195806: step: 188/530, loss: 0.006926822941750288
2023-01-21 11:15:37.351198: step: 192/530, loss: 0.08704390376806259
2023-01-21 11:15:38.506693: step: 196/530, loss: 0.23478154838085175
2023-01-21 11:15:39.667742: step: 200/530, loss: 0.0037170888390392065
2023-01-21 11:15:40.848460: step: 204/530, loss: 0.01519470289349556
2023-01-21 11:15:42.052958: step: 208/530, loss: 0.0004727363702841103
2023-01-21 11:15:43.211327: step: 212/530, loss: 0.0274276752024889
2023-01-21 11:15:44.363623: step: 216/530, loss: 0.009050226770341396
2023-01-21 11:15:45.545072: step: 220/530, loss: 0.0006450176006183028
2023-01-21 11:15:46.752068: step: 224/530, loss: 0.02561969682574272
2023-01-21 11:15:47.907700: step: 228/530, loss: 0.3448448181152344
2023-01-21 11:15:49.143409: step: 232/530, loss: 0.006799316965043545
2023-01-21 11:15:50.324578: step: 236/530, loss: 0.009489583782851696
2023-01-21 11:15:51.541024: step: 240/530, loss: 0.07019881904125214
2023-01-21 11:15:52.715666: step: 244/530, loss: 0.05946674197912216
2023-01-21 11:15:53.915748: step: 248/530, loss: 0.016806412488222122
2023-01-21 11:15:55.054059: step: 252/530, loss: 0.009386825375258923
2023-01-21 11:15:56.227282: step: 256/530, loss: 0.01936502568423748
2023-01-21 11:15:57.422520: step: 260/530, loss: 0.017323780804872513
2023-01-21 11:15:58.643139: step: 264/530, loss: 0.05763149634003639
2023-01-21 11:15:59.817544: step: 268/530, loss: 0.04225483164191246
2023-01-21 11:16:01.026205: step: 272/530, loss: 0.04228649288415909
2023-01-21 11:16:02.243416: step: 276/530, loss: 0.0956106185913086
2023-01-21 11:16:03.427505: step: 280/530, loss: 0.008332252502441406
2023-01-21 11:16:04.605261: step: 284/530, loss: 0.00016369820514228195
2023-01-21 11:16:05.747400: step: 288/530, loss: 0.02782316319644451
2023-01-21 11:16:06.968169: step: 292/530, loss: 0.0020324706565588713
2023-01-21 11:16:08.132801: step: 296/530, loss: 0.0034954072907567024
2023-01-21 11:16:09.326675: step: 300/530, loss: 0.023395443335175514
2023-01-21 11:16:10.495452: step: 304/530, loss: 0.2527715563774109
2023-01-21 11:16:11.678462: step: 308/530, loss: 0.05603041499853134
2023-01-21 11:16:12.864607: step: 312/530, loss: 0.047674939036369324
2023-01-21 11:16:14.063037: step: 316/530, loss: 0.0010286332108080387
2023-01-21 11:16:15.237353: step: 320/530, loss: 0.014490891247987747
2023-01-21 11:16:16.399910: step: 324/530, loss: 0.04193086549639702
2023-01-21 11:16:17.606857: step: 328/530, loss: 0.0021026611793786287
2023-01-21 11:16:18.763250: step: 332/530, loss: 0.0035626888275146484
2023-01-21 11:16:19.936655: step: 336/530, loss: 0.005678844638168812
2023-01-21 11:16:21.106787: step: 340/530, loss: 0.004150486085563898
2023-01-21 11:16:22.302519: step: 344/530, loss: 0.04954977333545685
2023-01-21 11:16:23.488683: step: 348/530, loss: 0.02667227014899254
2023-01-21 11:16:24.631938: step: 352/530, loss: 0.01735091209411621
2023-01-21 11:16:25.762862: step: 356/530, loss: 4.625320798368193e-06
2023-01-21 11:16:26.947080: step: 360/530, loss: 0.015119648538529873
2023-01-21 11:16:28.112704: step: 364/530, loss: 0.010033035650849342
2023-01-21 11:16:29.274759: step: 368/530, loss: 0.0030927658081054688
2023-01-21 11:16:30.420849: step: 372/530, loss: 0.0001960754452738911
2023-01-21 11:16:31.576907: step: 376/530, loss: 0.03287315368652344
2023-01-21 11:16:32.803755: step: 380/530, loss: 0.00011978149996139109
2023-01-21 11:16:33.963082: step: 384/530, loss: 0.0042085652239620686
2023-01-21 11:16:35.190554: step: 388/530, loss: 0.21089357137680054
2023-01-21 11:16:36.350552: step: 392/530, loss: 0.003231048583984375
2023-01-21 11:16:37.502244: step: 396/530, loss: 0.015334648080170155
2023-01-21 11:16:38.691824: step: 400/530, loss: 0.07846460491418839
2023-01-21 11:16:39.869214: step: 404/530, loss: 0.006622791290283203
2023-01-21 11:16:41.090049: step: 408/530, loss: 0.013403129763901234
2023-01-21 11:16:42.248261: step: 412/530, loss: 0.009992408566176891
2023-01-21 11:16:43.422968: step: 416/530, loss: 0.004206848330795765
2023-01-21 11:16:44.639761: step: 420/530, loss: 0.05643749237060547
2023-01-21 11:16:45.781926: step: 424/530, loss: 0.003478717990219593
2023-01-21 11:16:46.950960: step: 428/530, loss: 0.1259908676147461
2023-01-21 11:16:48.130534: step: 432/530, loss: 0.0066762929782271385
2023-01-21 11:16:49.261077: step: 436/530, loss: 0.0040524485521018505
2023-01-21 11:16:50.442094: step: 440/530, loss: 0.43678951263427734
2023-01-21 11:16:51.633400: step: 444/530, loss: 0.0006047248607501388
2023-01-21 11:16:52.794209: step: 448/530, loss: 0.012568474747240543
2023-01-21 11:16:53.978762: step: 452/530, loss: 0.03447742387652397
2023-01-21 11:16:55.141318: step: 456/530, loss: 0.04041357338428497
2023-01-21 11:16:56.340776: step: 460/530, loss: 0.05601387098431587
2023-01-21 11:16:57.543563: step: 464/530, loss: 0.037675097584724426
2023-01-21 11:16:58.680024: step: 468/530, loss: 0.013876628130674362
2023-01-21 11:16:59.865509: step: 472/530, loss: 0.022797204554080963
2023-01-21 11:17:01.095641: step: 476/530, loss: 0.0006576537853106856
2023-01-21 11:17:02.267484: step: 480/530, loss: 0.0031648636795580387
2023-01-21 11:17:03.486849: step: 484/530, loss: 0.005390929989516735
2023-01-21 11:17:04.656437: step: 488/530, loss: 0.012403489090502262
2023-01-21 11:17:05.834710: step: 492/530, loss: 0.00010180473327636719
2023-01-21 11:17:06.987014: step: 496/530, loss: 0.0017448425060138106
2023-01-21 11:17:08.175795: step: 500/530, loss: 0.043985940515995026
2023-01-21 11:17:09.396268: step: 504/530, loss: 0.10576958954334259
2023-01-21 11:17:10.573828: step: 508/530, loss: 0.014014530926942825
2023-01-21 11:17:11.740148: step: 512/530, loss: 0.006882572080940008
2023-01-21 11:17:12.901692: step: 516/530, loss: 0.007848501205444336
2023-01-21 11:17:14.129958: step: 520/530, loss: 0.030147362500429153
2023-01-21 11:17:15.293184: step: 524/530, loss: 0.0665828213095665
2023-01-21 11:17:16.512267: step: 528/530, loss: 0.08908043056726456
2023-01-21 11:17:17.692527: step: 532/530, loss: 0.07072629779577255
2023-01-21 11:17:18.841250: step: 536/530, loss: 0.001459753606468439
2023-01-21 11:17:20.021386: step: 540/530, loss: 0.005664253607392311
2023-01-21 11:17:21.202038: step: 544/530, loss: 0.018787814304232597
2023-01-21 11:17:22.381568: step: 548/530, loss: 0.004755973815917969
2023-01-21 11:17:23.570418: step: 552/530, loss: 0.011046791449189186
2023-01-21 11:17:24.703118: step: 556/530, loss: 0.0003834724775515497
2023-01-21 11:17:25.885725: step: 560/530, loss: 0.0006870270008221269
2023-01-21 11:17:27.102384: step: 564/530, loss: 0.14744997024536133
2023-01-21 11:17:28.280908: step: 568/530, loss: 0.013215637765824795
2023-01-21 11:17:29.485698: step: 572/530, loss: 0.003654909087345004
2023-01-21 11:17:30.715742: step: 576/530, loss: 0.03262438625097275
2023-01-21 11:17:31.863128: step: 580/530, loss: 0.0033113479148596525
2023-01-21 11:17:33.076299: step: 584/530, loss: 0.005275154486298561
2023-01-21 11:17:34.271162: step: 588/530, loss: 0.035724833607673645
2023-01-21 11:17:35.443350: step: 592/530, loss: 0.0021162033081054688
2023-01-21 11:17:36.609329: step: 596/530, loss: 0.00311279296875
2023-01-21 11:17:37.783273: step: 600/530, loss: 0.03542747348546982
2023-01-21 11:17:39.009552: step: 604/530, loss: 0.01597623899579048
2023-01-21 11:17:40.178842: step: 608/530, loss: 0.09174209833145142
2023-01-21 11:17:41.387339: step: 612/530, loss: 0.00562818069010973
2023-01-21 11:17:42.584451: step: 616/530, loss: 0.17554599046707153
2023-01-21 11:17:43.748728: step: 620/530, loss: 0.0260409377515316
2023-01-21 11:17:44.916118: step: 624/530, loss: 0.01264200173318386
2023-01-21 11:17:46.110634: step: 628/530, loss: 0.030210303142666817
2023-01-21 11:17:47.259851: step: 632/530, loss: 0.010682869702577591
2023-01-21 11:17:48.447743: step: 636/530, loss: 0.007931518368422985
2023-01-21 11:17:49.603714: step: 640/530, loss: 0.0005447864532470703
2023-01-21 11:17:50.783225: step: 644/530, loss: 0.06788110733032227
2023-01-21 11:17:52.028629: step: 648/530, loss: 0.02107849158346653
2023-01-21 11:17:53.186269: step: 652/530, loss: 0.007168483920395374
2023-01-21 11:17:54.336800: step: 656/530, loss: 0.04241933673620224
2023-01-21 11:17:55.509755: step: 660/530, loss: 0.006088686175644398
2023-01-21 11:17:56.703537: step: 664/530, loss: 0.025698376819491386
2023-01-21 11:17:57.892748: step: 668/530, loss: 0.0009649277199059725
2023-01-21 11:17:59.047463: step: 672/530, loss: 0.04045810550451279
2023-01-21 11:18:00.226235: step: 676/530, loss: 0.010532474145293236
2023-01-21 11:18:01.415830: step: 680/530, loss: 0.09343662858009338
2023-01-21 11:18:02.611456: step: 684/530, loss: 0.10690422356128693
2023-01-21 11:18:03.797639: step: 688/530, loss: 0.0028802871238440275
2023-01-21 11:18:04.997619: step: 692/530, loss: 0.02251739613711834
2023-01-21 11:18:06.184772: step: 696/530, loss: 0.03548593819141388
2023-01-21 11:18:07.374421: step: 700/530, loss: 0.017038345336914062
2023-01-21 11:18:08.528267: step: 704/530, loss: 0.05795764923095703
2023-01-21 11:18:09.714208: step: 708/530, loss: 0.00128765101544559
2023-01-21 11:18:10.894703: step: 712/530, loss: 0.0012988090747967362
2023-01-21 11:18:12.079040: step: 716/530, loss: 0.024661827832460403
2023-01-21 11:18:13.271704: step: 720/530, loss: 0.009413433261215687
2023-01-21 11:18:14.486617: step: 724/530, loss: 0.019054986536502838
2023-01-21 11:18:15.655195: step: 728/530, loss: 0.00013999939255882055
2023-01-21 11:18:16.893133: step: 732/530, loss: 0.020264435559511185
2023-01-21 11:18:18.076638: step: 736/530, loss: 0.0062163835391402245
2023-01-21 11:18:19.238264: step: 740/530, loss: 0.011188221164047718
2023-01-21 11:18:20.431236: step: 744/530, loss: 0.038249969482421875
2023-01-21 11:18:21.672738: step: 748/530, loss: 0.036637209355831146
2023-01-21 11:18:22.873888: step: 752/530, loss: 0.018723011016845703
2023-01-21 11:18:24.082419: step: 756/530, loss: 0.0005800247308798134
2023-01-21 11:18:25.257701: step: 760/530, loss: 0.0024306653067469597
2023-01-21 11:18:26.417472: step: 764/530, loss: 0.06122121959924698
2023-01-21 11:18:27.614551: step: 768/530, loss: 0.0048798564821481705
2023-01-21 11:18:28.806516: step: 772/530, loss: 0.006002235226333141
2023-01-21 11:18:29.994230: step: 776/530, loss: 0.01686248928308487
2023-01-21 11:18:31.186581: step: 780/530, loss: 0.051540806889534
2023-01-21 11:18:32.351586: step: 784/530, loss: 0.0017980575794354081
2023-01-21 11:18:33.550009: step: 788/530, loss: 0.06205444410443306
2023-01-21 11:18:34.763874: step: 792/530, loss: 0.04071769490838051
2023-01-21 11:18:35.915474: step: 796/530, loss: 0.009892559610307217
2023-01-21 11:18:37.080795: step: 800/530, loss: 0.02321958728134632
2023-01-21 11:18:38.237721: step: 804/530, loss: 0.0025775909889489412
2023-01-21 11:18:39.444236: step: 808/530, loss: 0.041968539357185364
2023-01-21 11:18:40.662347: step: 812/530, loss: 0.025341510772705078
2023-01-21 11:18:41.874263: step: 816/530, loss: 0.02298135682940483
2023-01-21 11:18:43.080789: step: 820/530, loss: 0.07093129307031631
2023-01-21 11:18:44.213936: step: 824/530, loss: 0.0012752532493323088
2023-01-21 11:18:45.419096: step: 828/530, loss: 0.01823444291949272
2023-01-21 11:18:46.583848: step: 832/530, loss: 0.004504871554672718
2023-01-21 11:18:47.766073: step: 836/530, loss: 0.000941848789807409
2023-01-21 11:18:48.922260: step: 840/530, loss: 0.0036214827559888363
2023-01-21 11:18:50.116781: step: 844/530, loss: 0.01453180331736803
2023-01-21 11:18:51.305781: step: 848/530, loss: 0.002618122147396207
2023-01-21 11:18:52.517246: step: 852/530, loss: 0.02101287804543972
2023-01-21 11:18:53.690765: step: 856/530, loss: 0.02105426788330078
2023-01-21 11:18:54.873055: step: 860/530, loss: 0.028368568047881126
2023-01-21 11:18:56.047412: step: 864/530, loss: 0.03912219777703285
2023-01-21 11:18:57.233248: step: 868/530, loss: 0.013689327985048294
2023-01-21 11:18:58.481180: step: 872/530, loss: 0.004489898681640625
2023-01-21 11:18:59.664319: step: 876/530, loss: 0.017798805609345436
2023-01-21 11:19:00.866534: step: 880/530, loss: 0.0041713714599609375
2023-01-21 11:19:02.092149: step: 884/530, loss: 0.020096778869628906
2023-01-21 11:19:03.309551: step: 888/530, loss: 0.01844024658203125
2023-01-21 11:19:04.568629: step: 892/530, loss: 0.0007258414989337325
2023-01-21 11:19:05.779027: step: 896/530, loss: 0.0017194747924804688
2023-01-21 11:19:06.979199: step: 900/530, loss: 0.024099256843328476
2023-01-21 11:19:08.127942: step: 904/530, loss: 0.07320012897253036
2023-01-21 11:19:09.310829: step: 908/530, loss: 0.00770492572337389
2023-01-21 11:19:10.452364: step: 912/530, loss: 0.042348992079496384
2023-01-21 11:19:11.579907: step: 916/530, loss: 0.0009481400484219193
2023-01-21 11:19:12.694795: step: 920/530, loss: 0.02439560927450657
2023-01-21 11:19:13.889640: step: 924/530, loss: 0.005425167270004749
2023-01-21 11:19:15.064650: step: 928/530, loss: 0.039430998265743256
2023-01-21 11:19:16.234110: step: 932/530, loss: 0.0010271549690514803
2023-01-21 11:19:17.410355: step: 936/530, loss: 0.306428998708725
2023-01-21 11:19:18.599066: step: 940/530, loss: 0.005414772313088179
2023-01-21 11:19:19.807476: step: 944/530, loss: 0.003547191619873047
2023-01-21 11:19:20.970284: step: 948/530, loss: 0.0031862258911132812
2023-01-21 11:19:22.179893: step: 952/530, loss: 0.01693754270672798
2023-01-21 11:19:23.371268: step: 956/530, loss: 0.00015716553025413305
2023-01-21 11:19:24.538074: step: 960/530, loss: 0.04472498968243599
2023-01-21 11:19:25.696017: step: 964/530, loss: 0.034920599311590195
2023-01-21 11:19:26.863333: step: 968/530, loss: 0.0015779496170580387
2023-01-21 11:19:28.041198: step: 972/530, loss: 0.00012636184692382812
2023-01-21 11:19:29.203466: step: 976/530, loss: 0.07393258064985275
2023-01-21 11:19:30.421858: step: 980/530, loss: 0.010555935092270374
2023-01-21 11:19:31.609038: step: 984/530, loss: 0.020491981878876686
2023-01-21 11:19:32.774546: step: 988/530, loss: 0.011789131909608841
2023-01-21 11:19:33.991787: step: 992/530, loss: 0.6844971179962158
2023-01-21 11:19:35.174070: step: 996/530, loss: 0.04599914699792862
2023-01-21 11:19:36.347641: step: 1000/530, loss: 0.058066368103027344
2023-01-21 11:19:37.495637: step: 1004/530, loss: 0.0029382705688476562
2023-01-21 11:19:38.718758: step: 1008/530, loss: 0.09489412605762482
2023-01-21 11:19:39.907015: step: 1012/530, loss: 0.019968414679169655
2023-01-21 11:19:41.105370: step: 1016/530, loss: 0.011318398639559746
2023-01-21 11:19:42.312275: step: 1020/530, loss: 0.03294200822710991
2023-01-21 11:19:43.515277: step: 1024/530, loss: 0.003685188479721546
2023-01-21 11:19:44.673040: step: 1028/530, loss: 0.00701828021556139
2023-01-21 11:19:45.824987: step: 1032/530, loss: 0.03197135776281357
2023-01-21 11:19:46.992315: step: 1036/530, loss: 0.09321308135986328
2023-01-21 11:19:48.155649: step: 1040/530, loss: 0.013440227136015892
2023-01-21 11:19:49.330955: step: 1044/530, loss: 0.055948637425899506
2023-01-21 11:19:50.520218: step: 1048/530, loss: 0.019626524299383163
2023-01-21 11:19:51.667947: step: 1052/530, loss: 0.036977577954530716
2023-01-21 11:19:52.841212: step: 1056/530, loss: 0.1333375871181488
2023-01-21 11:19:54.050485: step: 1060/530, loss: 0.05495653301477432
2023-01-21 11:19:55.253987: step: 1064/530, loss: 0.0007682800642214715
2023-01-21 11:19:56.378706: step: 1068/530, loss: 0.006464672274887562
2023-01-21 11:19:57.558752: step: 1072/530, loss: 0.022063732147216797
2023-01-21 11:19:58.733187: step: 1076/530, loss: 0.008932113647460938
2023-01-21 11:19:59.925607: step: 1080/530, loss: 0.05643606185913086
2023-01-21 11:20:01.073666: step: 1084/530, loss: 0.008454227820038795
2023-01-21 11:20:02.265163: step: 1088/530, loss: 0.020166300237178802
2023-01-21 11:20:03.458853: step: 1092/530, loss: 0.0007686614990234375
2023-01-21 11:20:04.637387: step: 1096/530, loss: 0.04031772539019585
2023-01-21 11:20:05.825197: step: 1100/530, loss: 0.12108192592859268
2023-01-21 11:20:07.013115: step: 1104/530, loss: 0.03692259639501572
2023-01-21 11:20:08.201235: step: 1108/530, loss: 0.011994552798569202
2023-01-21 11:20:09.408228: step: 1112/530, loss: 0.0023777009919285774
2023-01-21 11:20:10.548064: step: 1116/530, loss: 0.0017195702530443668
2023-01-21 11:20:11.734934: step: 1120/530, loss: 0.1961696743965149
2023-01-21 11:20:12.927365: step: 1124/530, loss: 0.01551288366317749
2023-01-21 11:20:14.114751: step: 1128/530, loss: 0.004374122712761164
2023-01-21 11:20:15.312849: step: 1132/530, loss: 0.005787849426269531
2023-01-21 11:20:16.588262: step: 1136/530, loss: 0.0037231924943625927
2023-01-21 11:20:17.800505: step: 1140/530, loss: 0.027016736567020416
2023-01-21 11:20:18.988971: step: 1144/530, loss: 0.03674974665045738
2023-01-21 11:20:20.153790: step: 1148/530, loss: 0.012103271670639515
2023-01-21 11:20:21.324630: step: 1152/530, loss: 0.013294410891830921
2023-01-21 11:20:22.478809: step: 1156/530, loss: 0.027155304327607155
2023-01-21 11:20:23.678669: step: 1160/530, loss: 0.04994478076696396
2023-01-21 11:20:24.884703: step: 1164/530, loss: 0.02293793112039566
2023-01-21 11:20:26.046234: step: 1168/530, loss: 0.001960182096809149
2023-01-21 11:20:27.216541: step: 1172/530, loss: 0.007164096925407648
2023-01-21 11:20:28.338348: step: 1176/530, loss: 0.03467082977294922
2023-01-21 11:20:29.505710: step: 1180/530, loss: 0.01048965472728014
2023-01-21 11:20:30.711157: step: 1184/530, loss: 0.0013591767055913806
2023-01-21 11:20:31.884325: step: 1188/530, loss: 6.84738188283518e-05
2023-01-21 11:20:33.109665: step: 1192/530, loss: 0.04931678622961044
2023-01-21 11:20:34.283374: step: 1196/530, loss: 0.005214023403823376
2023-01-21 11:20:35.470575: step: 1200/530, loss: 0.005885124206542969
2023-01-21 11:20:36.631383: step: 1204/530, loss: 0.023368261754512787
2023-01-21 11:20:37.799317: step: 1208/530, loss: 0.013084601610898972
2023-01-21 11:20:38.985394: step: 1212/530, loss: 0.1076413244009018
2023-01-21 11:20:40.124609: step: 1216/530, loss: 0.015424060635268688
2023-01-21 11:20:41.296821: step: 1220/530, loss: 0.001622915267944336
2023-01-21 11:20:42.461557: step: 1224/530, loss: 0.012215042486786842
2023-01-21 11:20:43.617498: step: 1228/530, loss: 0.004709053318947554
2023-01-21 11:20:44.855354: step: 1232/530, loss: 0.0017198562854900956
2023-01-21 11:20:46.035455: step: 1236/530, loss: 0.0006405830499716103
2023-01-21 11:20:47.182474: step: 1240/530, loss: 0.010349464602768421
2023-01-21 11:20:48.387719: step: 1244/530, loss: 0.021033668890595436
2023-01-21 11:20:49.569548: step: 1248/530, loss: 0.04518537595868111
2023-01-21 11:20:50.781772: step: 1252/530, loss: 0.625317394733429
2023-01-21 11:20:51.981448: step: 1256/530, loss: 0.005292702000588179
2023-01-21 11:20:53.151419: step: 1260/530, loss: 0.012545967474579811
2023-01-21 11:20:54.365406: step: 1264/530, loss: 0.02051258087158203
2023-01-21 11:20:55.535743: step: 1268/530, loss: 0.021819496527314186
2023-01-21 11:20:56.676291: step: 1272/530, loss: 0.09733696281909943
2023-01-21 11:20:57.820255: step: 1276/530, loss: 0.005890846252441406
2023-01-21 11:20:58.977449: step: 1280/530, loss: 0.00023155212693382055
2023-01-21 11:21:00.132613: step: 1284/530, loss: 0.0027832984924316406
2023-01-21 11:21:01.283363: step: 1288/530, loss: 0.029402637854218483
2023-01-21 11:21:02.429801: step: 1292/530, loss: 0.02575240284204483
2023-01-21 11:21:03.599103: step: 1296/530, loss: 0.0042739869095385075
2023-01-21 11:21:04.764821: step: 1300/530, loss: 0.0070213316939771175
2023-01-21 11:21:05.938437: step: 1304/530, loss: 0.11288128048181534
2023-01-21 11:21:07.105960: step: 1308/530, loss: 0.056291960179805756
2023-01-21 11:21:08.274260: step: 1312/530, loss: 0.005570841021835804
2023-01-21 11:21:09.506558: step: 1316/530, loss: 0.022466612979769707
2023-01-21 11:21:10.715748: step: 1320/530, loss: 0.008124351501464844
2023-01-21 11:21:11.883385: step: 1324/530, loss: 0.007206821348518133
2023-01-21 11:21:13.055125: step: 1328/530, loss: 0.024521350860595703
2023-01-21 11:21:14.271173: step: 1332/530, loss: 0.008456707000732422
2023-01-21 11:21:15.469758: step: 1336/530, loss: 0.015303420834243298
2023-01-21 11:21:16.607703: step: 1340/530, loss: 0.010968446731567383
2023-01-21 11:21:17.779554: step: 1344/530, loss: 0.00046405792818404734
2023-01-21 11:21:18.942374: step: 1348/530, loss: 0.0011665343772619963
2023-01-21 11:21:20.144290: step: 1352/530, loss: 0.027378272265195847
2023-01-21 11:21:21.296467: step: 1356/530, loss: 0.00821993313729763
2023-01-21 11:21:22.527223: step: 1360/530, loss: 0.00512771587818861
2023-01-21 11:21:23.689468: step: 1364/530, loss: 0.04418068006634712
2023-01-21 11:21:24.855880: step: 1368/530, loss: 0.04472227394580841
2023-01-21 11:21:26.015689: step: 1372/530, loss: 0.005098152440041304
2023-01-21 11:21:27.248531: step: 1376/530, loss: 0.0019210814498364925
2023-01-21 11:21:28.439240: step: 1380/530, loss: 0.002780771115794778
2023-01-21 11:21:29.620122: step: 1384/530, loss: 0.01731429062783718
2023-01-21 11:21:30.765724: step: 1388/530, loss: 0.00202598562464118
2023-01-21 11:21:31.939046: step: 1392/530, loss: 0.0401521660387516
2023-01-21 11:21:33.147279: step: 1396/530, loss: 0.005263328552246094
2023-01-21 11:21:34.354749: step: 1400/530, loss: 0.03058786317706108
2023-01-21 11:21:35.556017: step: 1404/530, loss: 0.006046962924301624
2023-01-21 11:21:36.779400: step: 1408/530, loss: 0.0058114053681492805
2023-01-21 11:21:37.980371: step: 1412/530, loss: 0.011354636400938034
2023-01-21 11:21:39.197420: step: 1416/530, loss: 0.003282785415649414
2023-01-21 11:21:40.359574: step: 1420/530, loss: 0.02545480988919735
2023-01-21 11:21:41.551473: step: 1424/530, loss: 0.034707069396972656
2023-01-21 11:21:42.713380: step: 1428/530, loss: 0.012260722927749157
2023-01-21 11:21:43.886312: step: 1432/530, loss: 0.02743072435259819
2023-01-21 11:21:45.055162: step: 1436/530, loss: 0.022022631019353867
2023-01-21 11:21:46.223219: step: 1440/530, loss: 0.0008210659143514931
2023-01-21 11:21:47.424532: step: 1444/530, loss: 0.04298248142004013
2023-01-21 11:21:48.608548: step: 1448/530, loss: 0.04845009371638298
2023-01-21 11:21:49.832481: step: 1452/530, loss: 0.01199264544993639
2023-01-21 11:21:51.049577: step: 1456/530, loss: 0.013561058789491653
2023-01-21 11:21:52.266837: step: 1460/530, loss: 0.16061095893383026
2023-01-21 11:21:53.460605: step: 1464/530, loss: 0.009313154965639114
2023-01-21 11:21:54.641309: step: 1468/530, loss: 0.02491474151611328
2023-01-21 11:21:55.819688: step: 1472/530, loss: 0.044518373906612396
2023-01-21 11:21:57.030536: step: 1476/530, loss: 0.004079150967299938
2023-01-21 11:21:58.249015: step: 1480/530, loss: 0.05116147920489311
2023-01-21 11:21:59.408648: step: 1484/530, loss: 0.00825490988790989
2023-01-21 11:22:00.618024: step: 1488/530, loss: 0.2474052459001541
2023-01-21 11:22:01.833580: step: 1492/530, loss: 0.02437744289636612
2023-01-21 11:22:02.953337: step: 1496/530, loss: 0.006059599108994007
2023-01-21 11:22:04.111576: step: 1500/530, loss: 0.011619377881288528
2023-01-21 11:22:05.270764: step: 1504/530, loss: 0.011385059915482998
2023-01-21 11:22:06.481673: step: 1508/530, loss: 0.019226456061005592
2023-01-21 11:22:07.694341: step: 1512/530, loss: 0.009076881222426891
2023-01-21 11:22:08.876695: step: 1516/530, loss: 0.02951965481042862
2023-01-21 11:22:10.060646: step: 1520/530, loss: 0.0048542022705078125
2023-01-21 11:22:11.246897: step: 1524/530, loss: 0.0008575438987463713
2023-01-21 11:22:12.436262: step: 1528/530, loss: 0.0030071260407567024
2023-01-21 11:22:13.621555: step: 1532/530, loss: 0.00035090447636321187
2023-01-21 11:22:14.812936: step: 1536/530, loss: 0.4376121759414673
2023-01-21 11:22:16.070391: step: 1540/530, loss: 0.01397705078125
2023-01-21 11:22:17.239475: step: 1544/530, loss: 0.0660494863986969
2023-01-21 11:22:18.416833: step: 1548/530, loss: 0.006846904754638672
2023-01-21 11:22:19.593272: step: 1552/530, loss: 0.028004836291074753
2023-01-21 11:22:20.785034: step: 1556/530, loss: 0.13076430559158325
2023-01-21 11:22:21.961054: step: 1560/530, loss: 3.346204903209582e-05
2023-01-21 11:22:23.154622: step: 1564/530, loss: 0.09946969151496887
2023-01-21 11:22:24.337360: step: 1568/530, loss: 0.014598274603486061
2023-01-21 11:22:25.513161: step: 1572/530, loss: 0.06793287396430969
2023-01-21 11:22:26.724462: step: 1576/530, loss: 0.0005762100336141884
2023-01-21 11:22:27.868780: step: 1580/530, loss: 0.01329183578491211
2023-01-21 11:22:29.060697: step: 1584/530, loss: 0.002945327665656805
2023-01-21 11:22:30.216839: step: 1588/530, loss: 0.03671465069055557
2023-01-21 11:22:31.408597: step: 1592/530, loss: 0.061001114547252655
2023-01-21 11:22:32.564865: step: 1596/530, loss: 0.011157846078276634
2023-01-21 11:22:33.752435: step: 1600/530, loss: 0.056175995618104935
2023-01-21 11:22:34.961389: step: 1604/530, loss: 0.06539420038461685
2023-01-21 11:22:36.089813: step: 1608/530, loss: 0.02539801597595215
2023-01-21 11:22:37.233098: step: 1612/530, loss: 0.005995273590087891
2023-01-21 11:22:38.359576: step: 1616/530, loss: 0.030515670776367188
2023-01-21 11:22:39.528285: step: 1620/530, loss: 0.0030109405051916838
2023-01-21 11:22:40.744551: step: 1624/530, loss: 0.004905032925307751
2023-01-21 11:22:41.939975: step: 1628/530, loss: 0.002255058381706476
2023-01-21 11:22:43.121408: step: 1632/530, loss: 0.0013852119445800781
2023-01-21 11:22:44.269308: step: 1636/530, loss: 0.006510257720947266
2023-01-21 11:22:45.449990: step: 1640/530, loss: 0.03111858293414116
2023-01-21 11:22:46.612058: step: 1644/530, loss: 0.018669437617063522
2023-01-21 11:22:47.812288: step: 1648/530, loss: 0.017412565648555756
2023-01-21 11:22:49.056929: step: 1652/530, loss: 0.07824277877807617
2023-01-21 11:22:50.236893: step: 1656/530, loss: 0.03162670135498047
2023-01-21 11:22:51.433144: step: 1660/530, loss: 0.012016773223876953
2023-01-21 11:22:52.669329: step: 1664/530, loss: 0.035002708435058594
2023-01-21 11:22:53.839061: step: 1668/530, loss: 0.007636070717126131
2023-01-21 11:22:54.993651: step: 1672/530, loss: 0.021028518676757812
2023-01-21 11:22:56.175386: step: 1676/530, loss: 0.02408733405172825
2023-01-21 11:22:57.342051: step: 1680/530, loss: 0.018557453528046608
2023-01-21 11:22:58.510202: step: 1684/530, loss: 0.05541520193219185
2023-01-21 11:22:59.657282: step: 1688/530, loss: 0.046256162226200104
2023-01-21 11:23:00.858430: step: 1692/530, loss: 0.04626293107867241
2023-01-21 11:23:02.085839: step: 1696/530, loss: 0.0016172886826097965
2023-01-21 11:23:03.300163: step: 1700/530, loss: 0.015532302670180798
2023-01-21 11:23:04.474593: step: 1704/530, loss: 0.03680257871747017
2023-01-21 11:23:05.671728: step: 1708/530, loss: 0.0017576217651367188
2023-01-21 11:23:06.834466: step: 1712/530, loss: 0.011650944128632545
2023-01-21 11:23:08.013312: step: 1716/530, loss: 0.012157249264419079
2023-01-21 11:23:09.156719: step: 1720/530, loss: 0.07267945259809494
2023-01-21 11:23:10.348516: step: 1724/530, loss: 0.11174774169921875
2023-01-21 11:23:11.530223: step: 1728/530, loss: 0.059250928461551666
2023-01-21 11:23:12.738384: step: 1732/530, loss: 0.0023828507401049137
2023-01-21 11:23:13.900644: step: 1736/530, loss: 0.028647232800722122
2023-01-21 11:23:15.091183: step: 1740/530, loss: 0.02377491071820259
2023-01-21 11:23:16.281434: step: 1744/530, loss: 0.026944447308778763
2023-01-21 11:23:17.472498: step: 1748/530, loss: 0.04197101667523384
2023-01-21 11:23:18.667159: step: 1752/530, loss: 0.009521770291030407
2023-01-21 11:23:19.864009: step: 1756/530, loss: 0.015687942504882812
2023-01-21 11:23:21.057198: step: 1760/530, loss: 0.0007885455852374434
2023-01-21 11:23:22.301373: step: 1764/530, loss: 0.017133712768554688
2023-01-21 11:23:23.480208: step: 1768/530, loss: 0.06792526692152023
2023-01-21 11:23:24.650608: step: 1772/530, loss: 0.04724464565515518
2023-01-21 11:23:25.864297: step: 1776/530, loss: 0.00868368148803711
2023-01-21 11:23:27.041115: step: 1780/530, loss: 0.058907441794872284
2023-01-21 11:23:28.257329: step: 1784/530, loss: 0.03559083864092827
2023-01-21 11:23:29.406560: step: 1788/530, loss: 0.003754949662834406
2023-01-21 11:23:30.589840: step: 1792/530, loss: 0.02006373554468155
2023-01-21 11:23:31.804468: step: 1796/530, loss: 0.16541346907615662
2023-01-21 11:23:32.947653: step: 1800/530, loss: 0.014510631561279297
2023-01-21 11:23:34.149557: step: 1804/530, loss: 0.06074199452996254
2023-01-21 11:23:35.377279: step: 1808/530, loss: 0.06244392693042755
2023-01-21 11:23:36.530226: step: 1812/530, loss: 0.0705965980887413
2023-01-21 11:23:37.682295: step: 1816/530, loss: 0.01542677916586399
2023-01-21 11:23:38.853160: step: 1820/530, loss: 0.008545017801225185
2023-01-21 11:23:40.013128: step: 1824/530, loss: 0.04546041414141655
2023-01-21 11:23:41.200217: step: 1828/530, loss: 0.0012052536476403475
2023-01-21 11:23:42.425750: step: 1832/530, loss: 0.0013606548309326172
2023-01-21 11:23:43.585475: step: 1836/530, loss: 0.009883594699203968
2023-01-21 11:23:44.768542: step: 1840/530, loss: 0.027675915509462357
2023-01-21 11:23:45.936100: step: 1844/530, loss: 0.02069096639752388
2023-01-21 11:23:47.126887: step: 1848/530, loss: 0.01460037287324667
2023-01-21 11:23:48.319776: step: 1852/530, loss: 0.02677288092672825
2023-01-21 11:23:49.491513: step: 1856/530, loss: 0.05374555662274361
2023-01-21 11:23:50.690899: step: 1860/530, loss: 0.00589985866099596
2023-01-21 11:23:51.864598: step: 1864/530, loss: 0.20721390843391418
2023-01-21 11:23:53.029120: step: 1868/530, loss: 0.003643464995548129
2023-01-21 11:23:54.233492: step: 1872/530, loss: 0.2724662721157074
2023-01-21 11:23:55.402594: step: 1876/530, loss: 0.14786000549793243
2023-01-21 11:23:56.582644: step: 1880/530, loss: 0.044640734791755676
2023-01-21 11:23:57.766710: step: 1884/530, loss: 0.01991119422018528
2023-01-21 11:23:58.930101: step: 1888/530, loss: 0.05913801118731499
2023-01-21 11:24:00.071408: step: 1892/530, loss: 0.015214063227176666
2023-01-21 11:24:01.220617: step: 1896/530, loss: 0.0004913330194540322
2023-01-21 11:24:02.387020: step: 1900/530, loss: 0.04687690734863281
2023-01-21 11:24:03.602236: step: 1904/530, loss: 0.041098594665527344
2023-01-21 11:24:04.748398: step: 1908/530, loss: 0.0007665634038858116
2023-01-21 11:24:05.956001: step: 1912/530, loss: 0.5281286239624023
2023-01-21 11:24:07.108765: step: 1916/530, loss: 0.013698577880859375
2023-01-21 11:24:08.254321: step: 1920/530, loss: 0.002680110977962613
2023-01-21 11:24:09.475281: step: 1924/530, loss: 0.015740156173706055
2023-01-21 11:24:10.640200: step: 1928/530, loss: 0.06741566956043243
2023-01-21 11:24:11.865763: step: 1932/530, loss: 0.0037709237076342106
2023-01-21 11:24:13.028576: step: 1936/530, loss: 0.03297100216150284
2023-01-21 11:24:14.218702: step: 1940/530, loss: 0.1535823792219162
2023-01-21 11:24:15.385753: step: 1944/530, loss: 0.0005600929143838584
2023-01-21 11:24:16.606503: step: 1948/530, loss: 0.043232060968875885
2023-01-21 11:24:17.784767: step: 1952/530, loss: 0.06583947688341141
2023-01-21 11:24:18.950835: step: 1956/530, loss: 0.015571403317153454
2023-01-21 11:24:20.087312: step: 1960/530, loss: 0.04037804529070854
2023-01-21 11:24:21.250432: step: 1964/530, loss: 0.0501251220703125
2023-01-21 11:24:22.407169: step: 1968/530, loss: 0.05025177076458931
2023-01-21 11:24:23.594410: step: 1972/530, loss: 0.08445396274328232
2023-01-21 11:24:24.780530: step: 1976/530, loss: 0.0317777618765831
2023-01-21 11:24:25.944166: step: 1980/530, loss: 0.006000423803925514
2023-01-21 11:24:27.097479: step: 1984/530, loss: 0.002723979763686657
2023-01-21 11:24:28.280700: step: 1988/530, loss: 0.004843807313591242
2023-01-21 11:24:29.453408: step: 1992/530, loss: 0.00908117275685072
2023-01-21 11:24:30.597191: step: 1996/530, loss: 0.0045393467880785465
2023-01-21 11:24:31.758337: step: 2000/530, loss: 0.008316230960190296
2023-01-21 11:24:32.936349: step: 2004/530, loss: 0.0024831772316247225
2023-01-21 11:24:34.212110: step: 2008/530, loss: 0.04654483497142792
2023-01-21 11:24:35.396734: step: 2012/530, loss: 0.020674800500273705
2023-01-21 11:24:36.611849: step: 2016/530, loss: 0.0249481201171875
2023-01-21 11:24:37.742987: step: 2020/530, loss: 0.026296233758330345
2023-01-21 11:24:38.949954: step: 2024/530, loss: 0.003978157415986061
2023-01-21 11:24:40.142847: step: 2028/530, loss: 0.063909150660038
2023-01-21 11:24:41.323002: step: 2032/530, loss: 0.08801212906837463
2023-01-21 11:24:42.486719: step: 2036/530, loss: 0.06461877375841141
2023-01-21 11:24:43.654516: step: 2040/530, loss: 0.01748828962445259
2023-01-21 11:24:44.850834: step: 2044/530, loss: 0.04268608242273331
2023-01-21 11:24:46.054483: step: 2048/530, loss: 0.013233756646513939
2023-01-21 11:24:47.281997: step: 2052/530, loss: 0.0363675095140934
2023-01-21 11:24:48.443014: step: 2056/530, loss: 0.024119187146425247
2023-01-21 11:24:49.608778: step: 2060/530, loss: 0.009925365447998047
2023-01-21 11:24:50.759391: step: 2064/530, loss: 0.23151855170726776
2023-01-21 11:24:51.937036: step: 2068/530, loss: 0.003927039913833141
2023-01-21 11:24:53.111745: step: 2072/530, loss: 1.1240531206130981
2023-01-21 11:24:54.314558: step: 2076/530, loss: 0.04476910084486008
2023-01-21 11:24:55.468529: step: 2080/530, loss: 0.06811833381652832
2023-01-21 11:24:56.686258: step: 2084/530, loss: 0.02093934826552868
2023-01-21 11:24:57.890066: step: 2088/530, loss: 0.1123688668012619
2023-01-21 11:24:59.072959: step: 2092/530, loss: 0.03959079086780548
2023-01-21 11:25:00.289476: step: 2096/530, loss: 0.10957165062427521
2023-01-21 11:25:01.454106: step: 2100/530, loss: 0.026591815054416656
2023-01-21 11:25:02.614453: step: 2104/530, loss: 0.009633541107177734
2023-01-21 11:25:03.788342: step: 2108/530, loss: 0.0009563446510583162
2023-01-21 11:25:04.961279: step: 2112/530, loss: 0.24887028336524963
2023-01-21 11:25:06.138599: step: 2116/530, loss: 0.021060658618807793
2023-01-21 11:25:07.297836: step: 2120/530, loss: 0.10740356892347336
==================================================
Loss: 0.038
--------------------
Dev: {'event': {'p': 0.6142241379310345, 'r': 0.758988015978695, 'f1': 0.6789755807027993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6543671181690799, 'r': 0.8056354226566993, 'f1': 0.7221649484536083}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6875, 'r': 0.5238095238095238, 'f1': 0.5945945945945946}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4318181818181818, 'r': 0.5277777777777778, 'f1': 0.47500000000000003}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:25:50.988360: step: 4/530, loss: 0.011803912930190563
2023-01-21 11:25:52.167441: step: 8/530, loss: 0.0008389592403545976
2023-01-21 11:25:53.363970: step: 12/530, loss: 0.08594093471765518
2023-01-21 11:25:54.577479: step: 16/530, loss: 0.046112824231386185
2023-01-21 11:25:55.742389: step: 20/530, loss: 0.03667163848876953
2023-01-21 11:25:56.962916: step: 24/530, loss: 0.016068458557128906
2023-01-21 11:25:58.165426: step: 28/530, loss: 0.017540359869599342
2023-01-21 11:25:59.399196: step: 32/530, loss: 0.02059049718081951
2023-01-21 11:26:00.592621: step: 36/530, loss: 0.036649420857429504
2023-01-21 11:26:01.817619: step: 40/530, loss: 0.07989444583654404
2023-01-21 11:26:02.992269: step: 44/530, loss: 0.007925743237137794
2023-01-21 11:26:04.201520: step: 48/530, loss: 0.010995388962328434
2023-01-21 11:26:05.376604: step: 52/530, loss: 0.008009719662368298
2023-01-21 11:26:06.581366: step: 56/530, loss: 0.02074756659567356
2023-01-21 11:26:07.772730: step: 60/530, loss: 0.0020765303634107113
2023-01-21 11:26:08.938403: step: 64/530, loss: 0.001609897706657648
2023-01-21 11:26:10.112797: step: 68/530, loss: 0.008221626281738281
2023-01-21 11:26:11.257157: step: 72/530, loss: 0.0015018940903246403
2023-01-21 11:26:12.487714: step: 76/530, loss: 0.05179624259471893
2023-01-21 11:26:13.684026: step: 80/530, loss: 0.044583775103092194
2023-01-21 11:26:14.894998: step: 84/530, loss: 0.013353920541703701
2023-01-21 11:26:16.090758: step: 88/530, loss: 2.2262661457061768
2023-01-21 11:26:17.288476: step: 92/530, loss: 0.03757190704345703
2023-01-21 11:26:18.504671: step: 96/530, loss: 0.2614215314388275
2023-01-21 11:26:19.653129: step: 100/530, loss: 0.04515361785888672
2023-01-21 11:26:20.822304: step: 104/530, loss: 0.06762409210205078
2023-01-21 11:26:21.982679: step: 108/530, loss: 0.09645986557006836
2023-01-21 11:26:23.157915: step: 112/530, loss: 0.02139577828347683
2023-01-21 11:26:24.366711: step: 116/530, loss: 0.008649397641420364
2023-01-21 11:26:25.542838: step: 120/530, loss: 0.04417705535888672
2023-01-21 11:26:26.716551: step: 124/530, loss: 0.016556167975068092
2023-01-21 11:26:27.928399: step: 128/530, loss: 0.0041713714599609375
2023-01-21 11:26:29.114398: step: 132/530, loss: 0.0005018234369345009
2023-01-21 11:26:30.324526: step: 136/530, loss: 0.05917387083172798
2023-01-21 11:26:31.510524: step: 140/530, loss: 0.002476310823112726
2023-01-21 11:26:32.661978: step: 144/530, loss: 0.34436577558517456
2023-01-21 11:26:33.900642: step: 148/530, loss: 0.008627128787338734
2023-01-21 11:26:35.129238: step: 152/530, loss: 0.018680192530155182
2023-01-21 11:26:36.272264: step: 156/530, loss: 0.008930588141083717
2023-01-21 11:26:37.456197: step: 160/530, loss: 0.001251316163688898
2023-01-21 11:26:38.598477: step: 164/530, loss: 0.03687248006463051
2023-01-21 11:26:39.848094: step: 168/530, loss: 0.035062503069639206
2023-01-21 11:26:41.057015: step: 172/530, loss: 0.013500022701919079
2023-01-21 11:26:42.258520: step: 176/530, loss: 0.006989479064941406
2023-01-21 11:26:43.426523: step: 180/530, loss: 0.007652187719941139
2023-01-21 11:26:44.583506: step: 184/530, loss: 0.03099050372838974
2023-01-21 11:26:45.758339: step: 188/530, loss: 0.01855926588177681
2023-01-21 11:26:46.910461: step: 192/530, loss: 0.017152214422822
2023-01-21 11:26:48.062044: step: 196/530, loss: 0.014323902316391468
2023-01-21 11:26:49.291074: step: 200/530, loss: 0.13445129990577698
2023-01-21 11:26:50.485167: step: 204/530, loss: 0.00038757326547056437
2023-01-21 11:26:51.667831: step: 208/530, loss: 0.03909549489617348
2023-01-21 11:26:52.837823: step: 212/530, loss: 0.05595111846923828
2023-01-21 11:26:53.965329: step: 216/530, loss: 0.0001028060942189768
2023-01-21 11:26:55.166616: step: 220/530, loss: 0.0017253875266760588
2023-01-21 11:26:56.329923: step: 224/530, loss: 0.006760692689567804
2023-01-21 11:26:57.506137: step: 228/530, loss: 0.08616295456886292
2023-01-21 11:26:58.684844: step: 232/530, loss: 0.00025434495182707906
2023-01-21 11:26:59.824531: step: 236/530, loss: 0.010575294494628906
2023-01-21 11:27:01.032686: step: 240/530, loss: 0.027211381122469902
2023-01-21 11:27:02.209269: step: 244/530, loss: 0.0077280523255467415
2023-01-21 11:27:03.396608: step: 248/530, loss: 0.007067251019179821
2023-01-21 11:27:04.567051: step: 252/530, loss: 0.02329707145690918
2023-01-21 11:27:05.765163: step: 256/530, loss: 0.1268574744462967
2023-01-21 11:27:06.914432: step: 260/530, loss: 0.020870016887784004
2023-01-21 11:27:08.101564: step: 264/530, loss: 0.010355949401855469
2023-01-21 11:27:09.288607: step: 268/530, loss: 0.0039345743134617805
2023-01-21 11:27:10.526255: step: 272/530, loss: 0.012414741329848766
2023-01-21 11:27:11.656217: step: 276/530, loss: 0.003600740572437644
2023-01-21 11:27:12.805930: step: 280/530, loss: 0.0095360754057765
2023-01-21 11:27:14.007498: step: 284/530, loss: 0.0007090568542480469
2023-01-21 11:27:15.157773: step: 288/530, loss: 0.0001019001065287739
2023-01-21 11:27:16.387374: step: 292/530, loss: 0.012156590819358826
2023-01-21 11:27:17.548401: step: 296/530, loss: 0.004515647888183594
2023-01-21 11:27:18.737390: step: 300/530, loss: 0.0005843163235113025
2023-01-21 11:27:19.912404: step: 304/530, loss: 5.326271275407635e-05
2023-01-21 11:27:21.084202: step: 308/530, loss: 0.04109363630414009
2023-01-21 11:27:22.260234: step: 312/530, loss: 0.005698967259377241
2023-01-21 11:27:23.476682: step: 316/530, loss: 0.0011418343055993319
2023-01-21 11:27:24.634846: step: 320/530, loss: 0.06436445564031601
2023-01-21 11:27:25.828941: step: 324/530, loss: 0.002170562744140625
2023-01-21 11:27:27.015753: step: 328/530, loss: 0.007808208465576172
2023-01-21 11:27:28.147840: step: 332/530, loss: 0.014445877633988857
2023-01-21 11:27:29.376370: step: 336/530, loss: 0.01573162153363228
2023-01-21 11:27:30.566580: step: 340/530, loss: 0.02624797821044922
2023-01-21 11:27:31.746584: step: 344/530, loss: 0.0690792128443718
2023-01-21 11:27:32.931875: step: 348/530, loss: 0.04187946766614914
2023-01-21 11:27:34.096155: step: 352/530, loss: 0.06370649486780167
2023-01-21 11:27:35.278222: step: 356/530, loss: 0.0015368462773039937
2023-01-21 11:27:36.471933: step: 360/530, loss: 0.00043430327787064016
2023-01-21 11:27:37.652889: step: 364/530, loss: 0.03036670759320259
2023-01-21 11:27:38.861943: step: 368/530, loss: 0.010527038015425205
2023-01-21 11:27:40.023932: step: 372/530, loss: 0.014672852121293545
2023-01-21 11:27:41.226504: step: 376/530, loss: 0.032254885882139206
2023-01-21 11:27:42.414402: step: 380/530, loss: 0.14931999146938324
2023-01-21 11:27:43.617732: step: 384/530, loss: 0.001505136489868164
2023-01-21 11:27:44.762564: step: 388/530, loss: 0.0009296417119912803
2023-01-21 11:27:45.914210: step: 392/530, loss: 0.003215217497199774
2023-01-21 11:27:47.113584: step: 396/530, loss: 0.013692855834960938
2023-01-21 11:27:48.266127: step: 400/530, loss: 0.031210042536258698
2023-01-21 11:27:49.412773: step: 404/530, loss: 0.004226493649184704
2023-01-21 11:27:50.605676: step: 408/530, loss: 0.023108195513486862
2023-01-21 11:27:51.810468: step: 412/530, loss: 0.037575531750917435
2023-01-21 11:27:52.960782: step: 416/530, loss: 0.0019168853759765625
2023-01-21 11:27:54.103891: step: 420/530, loss: 0.015109062194824219
2023-01-21 11:27:55.265940: step: 424/530, loss: 0.010098935104906559
2023-01-21 11:27:56.444336: step: 428/530, loss: 0.01007843017578125
2023-01-21 11:27:57.629122: step: 432/530, loss: 0.005023574456572533
2023-01-21 11:27:58.783328: step: 436/530, loss: 0.054714396595954895
2023-01-21 11:27:59.981966: step: 440/530, loss: 0.0005581856239587069
2023-01-21 11:28:01.199679: step: 444/530, loss: 0.056307412683963776
2023-01-21 11:28:02.395087: step: 448/530, loss: 0.04155702888965607
2023-01-21 11:28:03.564281: step: 452/530, loss: 0.039597511291503906
2023-01-21 11:28:04.784676: step: 456/530, loss: 0.011385154910385609
2023-01-21 11:28:05.966871: step: 460/530, loss: 0.018801212310791016
2023-01-21 11:28:07.159487: step: 464/530, loss: 0.005802154541015625
2023-01-21 11:28:08.332398: step: 468/530, loss: 0.013228941708803177
2023-01-21 11:28:09.501078: step: 472/530, loss: 0.1714356392621994
2023-01-21 11:28:10.649365: step: 476/530, loss: 0.010793971829116344
2023-01-21 11:28:11.821856: step: 480/530, loss: 0.0006269455188885331
2023-01-21 11:28:13.020471: step: 484/530, loss: 0.06122856214642525
2023-01-21 11:28:14.195609: step: 488/530, loss: 0.024777555838227272
2023-01-21 11:28:15.355426: step: 492/530, loss: 0.0045528411865234375
2023-01-21 11:28:16.541637: step: 496/530, loss: 0.0003942489856854081
2023-01-21 11:28:17.714837: step: 500/530, loss: 0.08202056586742401
2023-01-21 11:28:18.879981: step: 504/530, loss: 0.0008361339569091797
2023-01-21 11:28:20.092218: step: 508/530, loss: 0.0027695419266819954
2023-01-21 11:28:21.272233: step: 512/530, loss: 0.04146299511194229
2023-01-21 11:28:22.430292: step: 516/530, loss: 0.0013261317508295178
2023-01-21 11:28:23.604495: step: 520/530, loss: 0.01635294035077095
2023-01-21 11:28:24.817224: step: 524/530, loss: 0.01120605506002903
2023-01-21 11:28:25.970709: step: 528/530, loss: 0.0028503418434411287
2023-01-21 11:28:27.133593: step: 532/530, loss: 0.004157161805778742
2023-01-21 11:28:28.298931: step: 536/530, loss: 0.0003058433358091861
2023-01-21 11:28:29.469141: step: 540/530, loss: 0.02652874030172825
2023-01-21 11:28:30.610199: step: 544/530, loss: 0.035640716552734375
2023-01-21 11:28:31.804286: step: 548/530, loss: 0.0001773834228515625
2023-01-21 11:28:33.038093: step: 552/530, loss: 0.008179092779755592
2023-01-21 11:28:34.188984: step: 556/530, loss: 0.008895683102309704
2023-01-21 11:28:35.352098: step: 560/530, loss: 0.08431173115968704
2023-01-21 11:28:36.555637: step: 564/530, loss: 0.017026519402861595
2023-01-21 11:28:37.795636: step: 568/530, loss: 0.0015573024284094572
2023-01-21 11:28:38.950411: step: 572/530, loss: 0.0261293426156044
2023-01-21 11:28:40.103148: step: 576/530, loss: 0.044504743069410324
2023-01-21 11:28:41.266680: step: 580/530, loss: 0.03055286407470703
2023-01-21 11:28:42.430732: step: 584/530, loss: 0.027416467666625977
2023-01-21 11:28:43.607415: step: 588/530, loss: 0.0003868580097332597
2023-01-21 11:28:44.776499: step: 592/530, loss: 0.13542652130126953
2023-01-21 11:28:45.981278: step: 596/530, loss: 0.006299400236457586
2023-01-21 11:28:47.173133: step: 600/530, loss: 0.0032575682271271944
2023-01-21 11:28:48.383552: step: 604/530, loss: 0.012951850891113281
2023-01-21 11:28:49.560010: step: 608/530, loss: 0.07056315243244171
2023-01-21 11:28:50.820358: step: 612/530, loss: 0.010294770821928978
2023-01-21 11:28:52.008248: step: 616/530, loss: 0.0098451878875494
2023-01-21 11:28:53.187458: step: 620/530, loss: 0.004827023018151522
2023-01-21 11:28:54.364951: step: 624/530, loss: 0.0022405623458325863
2023-01-21 11:28:55.544694: step: 628/530, loss: 0.0433996208012104
2023-01-21 11:28:56.729664: step: 632/530, loss: 0.024373246356844902
2023-01-21 11:28:57.902352: step: 636/530, loss: 0.020254040136933327
2023-01-21 11:28:59.122402: step: 640/530, loss: 0.009142017923295498
2023-01-21 11:29:00.323722: step: 644/530, loss: 0.005822372157126665
2023-01-21 11:29:01.497286: step: 648/530, loss: 0.0026299478486180305
2023-01-21 11:29:02.660063: step: 652/530, loss: 0.0027402881532907486
2023-01-21 11:29:03.857492: step: 656/530, loss: 0.01474304310977459
2023-01-21 11:29:05.067819: step: 660/530, loss: 0.02172079123556614
2023-01-21 11:29:06.234453: step: 664/530, loss: 0.053358934819698334
2023-01-21 11:29:07.447643: step: 668/530, loss: 0.009865951724350452
2023-01-21 11:29:08.627974: step: 672/530, loss: 0.0001432418794138357
2023-01-21 11:29:09.794365: step: 676/530, loss: 0.0013968468410894275
2023-01-21 11:29:10.960079: step: 680/530, loss: 0.0016103744274005294
2023-01-21 11:29:12.135371: step: 684/530, loss: 0.012549687176942825
2023-01-21 11:29:13.278692: step: 688/530, loss: 0.08399419486522675
2023-01-21 11:29:14.459361: step: 692/530, loss: 0.10415535420179367
2023-01-21 11:29:15.614759: step: 696/530, loss: 0.0022276879753917456
2023-01-21 11:29:16.775013: step: 700/530, loss: 0.020398329943418503
2023-01-21 11:29:17.942539: step: 704/530, loss: 0.0015520096058025956
2023-01-21 11:29:19.115597: step: 708/530, loss: 0.0034155845642089844
2023-01-21 11:29:20.285612: step: 712/530, loss: 0.006957626435905695
2023-01-21 11:29:21.452933: step: 716/530, loss: 0.011006355285644531
2023-01-21 11:29:22.613404: step: 720/530, loss: 0.010660839267075062
2023-01-21 11:29:23.835086: step: 724/530, loss: 0.008368397131562233
2023-01-21 11:29:25.038846: step: 728/530, loss: 0.0035962106194347143
2023-01-21 11:29:26.186364: step: 732/530, loss: 0.006811189465224743
2023-01-21 11:29:27.339742: step: 736/530, loss: 0.0031302450224757195
2023-01-21 11:29:28.506054: step: 740/530, loss: 0.0013644217979162931
2023-01-21 11:29:29.683056: step: 744/530, loss: 0.11601953208446503
2023-01-21 11:29:30.856947: step: 748/530, loss: 0.03023376502096653
2023-01-21 11:29:32.036719: step: 752/530, loss: 0.017046205699443817
2023-01-21 11:29:33.207589: step: 756/530, loss: 0.07289314270019531
2023-01-21 11:29:34.400165: step: 760/530, loss: 0.03202419355511665
2023-01-21 11:29:35.597292: step: 764/530, loss: 0.03344287723302841
2023-01-21 11:29:36.780537: step: 768/530, loss: 0.0030727863777428865
2023-01-21 11:29:38.030109: step: 772/530, loss: 0.026743507012724876
2023-01-21 11:29:39.189228: step: 776/530, loss: 0.04842090979218483
2023-01-21 11:29:40.358058: step: 780/530, loss: 0.02066974714398384
2023-01-21 11:29:41.546635: step: 784/530, loss: 0.005280685611069202
2023-01-21 11:29:42.732022: step: 788/530, loss: 0.008036899380385876
2023-01-21 11:29:43.896968: step: 792/530, loss: 0.013729572296142578
2023-01-21 11:29:45.111942: step: 796/530, loss: 0.022278975695371628
2023-01-21 11:29:46.295833: step: 800/530, loss: 0.027057457715272903
2023-01-21 11:29:47.473361: step: 804/530, loss: 0.018549634143710136
2023-01-21 11:29:48.672100: step: 808/530, loss: 0.007126140873879194
2023-01-21 11:29:49.877947: step: 812/530, loss: 0.018884658813476562
2023-01-21 11:29:51.073598: step: 816/530, loss: 0.0002930402697529644
2023-01-21 11:29:52.249025: step: 820/530, loss: 0.04835167154669762
2023-01-21 11:29:53.395094: step: 824/530, loss: 0.020741652697324753
2023-01-21 11:29:54.540666: step: 828/530, loss: 0.07707051932811737
2023-01-21 11:29:55.708777: step: 832/530, loss: 0.07047387957572937
2023-01-21 11:29:56.852454: step: 836/530, loss: 0.0033155917190015316
2023-01-21 11:29:58.035069: step: 840/530, loss: 0.001608562539331615
2023-01-21 11:29:59.168449: step: 844/530, loss: 0.0012276651104912162
2023-01-21 11:30:00.412413: step: 848/530, loss: 0.0017636299598962069
2023-01-21 11:30:01.591923: step: 852/530, loss: 0.05711803585290909
2023-01-21 11:30:02.769875: step: 856/530, loss: 0.018064118921756744
2023-01-21 11:30:04.014989: step: 860/530, loss: 0.00036964414175599813
2023-01-21 11:30:05.222888: step: 864/530, loss: 0.2907162308692932
2023-01-21 11:30:06.413205: step: 868/530, loss: 0.002490425016731024
2023-01-21 11:30:07.576298: step: 872/530, loss: 0.0352783203125
2023-01-21 11:30:08.749560: step: 876/530, loss: 0.0019029617542400956
2023-01-21 11:30:09.924540: step: 880/530, loss: 0.04857172816991806
2023-01-21 11:30:11.074928: step: 884/530, loss: 0.0005317211616784334
2023-01-21 11:30:12.278801: step: 888/530, loss: 0.05900631099939346
2023-01-21 11:30:13.448393: step: 892/530, loss: 0.003645277116447687
2023-01-21 11:30:14.624149: step: 896/530, loss: 0.052827075123786926
2023-01-21 11:30:15.769808: step: 900/530, loss: 0.004794598091393709
2023-01-21 11:30:16.926350: step: 904/530, loss: 0.0007216454250738025
2023-01-21 11:30:18.088523: step: 908/530, loss: 0.03386583551764488
2023-01-21 11:30:19.270238: step: 912/530, loss: 0.009466457180678844
2023-01-21 11:30:20.434689: step: 916/530, loss: 0.0433141253888607
2023-01-21 11:30:21.615880: step: 920/530, loss: 0.0036919594276696444
2023-01-21 11:30:22.810349: step: 924/530, loss: 0.00019907952810171992
2023-01-21 11:30:24.007284: step: 928/530, loss: 0.01747150532901287
2023-01-21 11:30:25.185705: step: 932/530, loss: 0.6426636576652527
2023-01-21 11:30:26.298146: step: 936/530, loss: 0.026026152074337006
2023-01-21 11:30:27.505147: step: 940/530, loss: 0.052445221692323685
2023-01-21 11:30:28.666636: step: 944/530, loss: 5.838871220475994e-05
2023-01-21 11:30:29.873390: step: 948/530, loss: 0.019314004108309746
2023-01-21 11:30:31.031306: step: 952/530, loss: 0.00019109249114990234
2023-01-21 11:30:32.191086: step: 956/530, loss: 0.0008402348030358553
2023-01-21 11:30:33.434084: step: 960/530, loss: 0.0036657333839684725
2023-01-21 11:30:34.623774: step: 964/530, loss: 0.012752722948789597
2023-01-21 11:30:35.814277: step: 968/530, loss: 0.03093414194881916
2023-01-21 11:30:37.040949: step: 972/530, loss: 0.06144285202026367
2023-01-21 11:30:38.172805: step: 976/530, loss: 0.06936054676771164
2023-01-21 11:30:39.415991: step: 980/530, loss: 0.025339510291814804
2023-01-21 11:30:40.621739: step: 984/530, loss: 0.01734151877462864
2023-01-21 11:30:41.824180: step: 988/530, loss: 0.036733053624629974
2023-01-21 11:30:43.017754: step: 992/530, loss: 0.019701385870575905
2023-01-21 11:30:44.251634: step: 996/530, loss: 0.025998689234256744
2023-01-21 11:30:45.439122: step: 1000/530, loss: 0.043432045727968216
2023-01-21 11:30:46.623218: step: 1004/530, loss: 0.039957426488399506
2023-01-21 11:30:47.811370: step: 1008/530, loss: 0.03496399149298668
2023-01-21 11:30:48.959037: step: 1012/530, loss: 0.017052460461854935
2023-01-21 11:30:50.186934: step: 1016/530, loss: 0.024935530498623848
2023-01-21 11:30:51.364268: step: 1020/530, loss: 0.0010368346702307463
2023-01-21 11:30:52.560455: step: 1024/530, loss: 0.026552438735961914
2023-01-21 11:30:53.753804: step: 1028/530, loss: 0.0009861945873126388
2023-01-21 11:30:54.917556: step: 1032/530, loss: 0.008784865960478783
2023-01-21 11:30:56.114610: step: 1036/530, loss: 0.1455141007900238
2023-01-21 11:30:57.283840: step: 1040/530, loss: 0.19695281982421875
2023-01-21 11:30:58.459522: step: 1044/530, loss: 0.010457802563905716
2023-01-21 11:30:59.589129: step: 1048/530, loss: 0.004074573516845703
2023-01-21 11:31:00.785058: step: 1052/530, loss: 0.0352146178483963
2023-01-21 11:31:02.025390: step: 1056/530, loss: 0.03600216284394264
2023-01-21 11:31:03.188475: step: 1060/530, loss: 0.07290458679199219
2023-01-21 11:31:04.345380: step: 1064/530, loss: 0.0008146286127157509
2023-01-21 11:31:05.505181: step: 1068/530, loss: 0.0027271269354969263
2023-01-21 11:31:06.707760: step: 1072/530, loss: 0.02322540245950222
2023-01-21 11:31:07.840228: step: 1076/530, loss: 0.012006091885268688
2023-01-21 11:31:09.026343: step: 1080/530, loss: 0.024133967235684395
2023-01-21 11:31:10.262558: step: 1084/530, loss: 0.014663697220385075
2023-01-21 11:31:11.437054: step: 1088/530, loss: 0.016333580017089844
2023-01-21 11:31:12.598912: step: 1092/530, loss: 0.008843421936035156
2023-01-21 11:31:13.771556: step: 1096/530, loss: 0.000602340733166784
2023-01-21 11:31:14.979238: step: 1100/530, loss: 0.0003247261047363281
2023-01-21 11:31:16.155115: step: 1104/530, loss: 0.010089969262480736
2023-01-21 11:31:17.354078: step: 1108/530, loss: 0.015249919146299362
2023-01-21 11:31:18.555308: step: 1112/530, loss: 0.00025005341740325093
2023-01-21 11:31:19.801395: step: 1116/530, loss: 0.5382595658302307
2023-01-21 11:31:20.987318: step: 1120/530, loss: 0.0032939910888671875
2023-01-21 11:31:22.201861: step: 1124/530, loss: 0.000779485737439245
2023-01-21 11:31:23.352231: step: 1128/530, loss: 0.008435631170868874
2023-01-21 11:31:24.552601: step: 1132/530, loss: 0.0423458106815815
2023-01-21 11:31:25.720168: step: 1136/530, loss: 0.0008742332574911416
2023-01-21 11:31:26.867575: step: 1140/530, loss: 0.06773968040943146
2023-01-21 11:31:28.057051: step: 1144/530, loss: 0.013946724124252796
2023-01-21 11:31:29.270138: step: 1148/530, loss: 0.013174057006835938
2023-01-21 11:31:30.431796: step: 1152/530, loss: 0.012566459365189075
2023-01-21 11:31:31.604994: step: 1156/530, loss: 1.621246337890625e-05
2023-01-21 11:31:32.834374: step: 1160/530, loss: 0.004331255331635475
2023-01-21 11:31:33.994997: step: 1164/530, loss: 0.01078033447265625
2023-01-21 11:31:35.183884: step: 1168/530, loss: 0.0037264826241880655
2023-01-21 11:31:36.398502: step: 1172/530, loss: 0.012298393063247204
2023-01-21 11:31:37.554453: step: 1176/530, loss: 0.005705452058464289
2023-01-21 11:31:38.741005: step: 1180/530, loss: 0.03402690961956978
2023-01-21 11:31:39.940078: step: 1184/530, loss: 0.05775032192468643
2023-01-21 11:31:41.088495: step: 1188/530, loss: 0.001377403736114502
2023-01-21 11:31:42.253593: step: 1192/530, loss: 0.02831859514117241
2023-01-21 11:31:43.448368: step: 1196/530, loss: 0.017070865258574486
2023-01-21 11:31:44.655618: step: 1200/530, loss: 0.008883858099579811
2023-01-21 11:31:45.874619: step: 1204/530, loss: 0.011878211051225662
2023-01-21 11:31:47.026580: step: 1208/530, loss: 0.002170658204704523
2023-01-21 11:31:48.215893: step: 1212/530, loss: 0.02340860292315483
2023-01-21 11:31:49.424110: step: 1216/530, loss: 8.325576345669106e-05
2023-01-21 11:31:50.579383: step: 1220/530, loss: 0.11175356060266495
2023-01-21 11:31:51.763072: step: 1224/530, loss: 0.001722145127132535
2023-01-21 11:31:52.930947: step: 1228/530, loss: 0.00021820068650413305
2023-01-21 11:31:54.111080: step: 1232/530, loss: 0.042913056910037994
2023-01-21 11:31:55.291294: step: 1236/530, loss: 0.0015806198352947831
2023-01-21 11:31:56.433661: step: 1240/530, loss: 0.0016660690307617188
2023-01-21 11:31:57.605101: step: 1244/530, loss: 0.005749988369643688
2023-01-21 11:31:58.809035: step: 1248/530, loss: 0.025263022631406784
2023-01-21 11:31:59.972269: step: 1252/530, loss: 0.015886783599853516
2023-01-21 11:32:01.121302: step: 1256/530, loss: 0.009708595462143421
2023-01-21 11:32:02.331932: step: 1260/530, loss: 0.0017901421524584293
2023-01-21 11:32:03.476110: step: 1264/530, loss: 0.1504424512386322
2023-01-21 11:32:04.654202: step: 1268/530, loss: 0.016597747802734375
2023-01-21 11:32:05.839344: step: 1272/530, loss: 6.065368506824598e-05
2023-01-21 11:32:07.031975: step: 1276/530, loss: 0.008184432983398438
2023-01-21 11:32:08.231293: step: 1280/530, loss: 0.0037690596655011177
2023-01-21 11:32:09.407775: step: 1284/530, loss: 0.007947158999741077
2023-01-21 11:32:10.620427: step: 1288/530, loss: 0.06081543117761612
2023-01-21 11:32:11.805352: step: 1292/530, loss: 0.009768009185791016
2023-01-21 11:32:12.987269: step: 1296/530, loss: 0.007707023527473211
2023-01-21 11:32:14.208746: step: 1300/530, loss: 0.0012138367164880037
2023-01-21 11:32:15.465700: step: 1304/530, loss: 0.015604686923325062
2023-01-21 11:32:16.673238: step: 1308/530, loss: 0.0006648540729656816
2023-01-21 11:32:17.892545: step: 1312/530, loss: 0.07854995876550674
2023-01-21 11:32:19.065723: step: 1316/530, loss: 0.037283897399902344
2023-01-21 11:32:20.267055: step: 1320/530, loss: 0.003159046173095703
2023-01-21 11:32:21.491275: step: 1324/530, loss: 0.0773005485534668
2023-01-21 11:32:22.664955: step: 1328/530, loss: 0.05927448347210884
2023-01-21 11:32:23.836685: step: 1332/530, loss: 0.010669517330825329
2023-01-21 11:32:25.007787: step: 1336/530, loss: 0.04663993418216705
2023-01-21 11:32:26.187763: step: 1340/530, loss: 0.03563842922449112
2023-01-21 11:32:27.363231: step: 1344/530, loss: 0.021506501361727715
2023-01-21 11:32:28.542105: step: 1348/530, loss: 0.000225067138671875
2023-01-21 11:32:29.696949: step: 1352/530, loss: 0.004286480136215687
2023-01-21 11:32:30.912498: step: 1356/530, loss: 0.02083444595336914
2023-01-21 11:32:32.113495: step: 1360/530, loss: 0.025443362072110176
2023-01-21 11:32:33.279466: step: 1364/530, loss: 0.0661352202296257
2023-01-21 11:32:34.491106: step: 1368/530, loss: 0.030336380004882812
2023-01-21 11:32:35.675301: step: 1372/530, loss: 0.0747671127319336
2023-01-21 11:32:36.854788: step: 1376/530, loss: 0.03721001371741295
2023-01-21 11:32:38.033520: step: 1380/530, loss: 0.005052948370575905
2023-01-21 11:32:39.247351: step: 1384/530, loss: 0.016537094488739967
2023-01-21 11:32:40.403201: step: 1388/530, loss: 0.03815498575568199
2023-01-21 11:32:41.623136: step: 1392/530, loss: 0.007051658816635609
2023-01-21 11:32:42.816454: step: 1396/530, loss: 0.05862021818757057
2023-01-21 11:32:43.987648: step: 1400/530, loss: 0.018903635442256927
2023-01-21 11:32:45.165548: step: 1404/530, loss: 0.0003411293146200478
2023-01-21 11:32:46.356320: step: 1408/530, loss: 0.04003643989562988
2023-01-21 11:32:47.534387: step: 1412/530, loss: 0.1779453307390213
2023-01-21 11:32:48.744249: step: 1416/530, loss: 0.03536586835980415
2023-01-21 11:32:49.919422: step: 1420/530, loss: 0.0015798569656908512
2023-01-21 11:32:51.073719: step: 1424/530, loss: 0.026375198736786842
2023-01-21 11:32:52.251033: step: 1428/530, loss: 0.0008258819580078125
2023-01-21 11:32:53.402820: step: 1432/530, loss: 0.01930971071124077
2023-01-21 11:32:54.577523: step: 1436/530, loss: 0.012260055169463158
2023-01-21 11:32:55.770483: step: 1440/530, loss: 0.06031780317425728
2023-01-21 11:32:56.922140: step: 1444/530, loss: 0.03060302883386612
2023-01-21 11:32:58.074363: step: 1448/530, loss: 0.002894878387451172
2023-01-21 11:32:59.243650: step: 1452/530, loss: 0.09255209565162659
2023-01-21 11:33:00.438471: step: 1456/530, loss: 0.014461898244917393
2023-01-21 11:33:01.626587: step: 1460/530, loss: 0.08630600571632385
2023-01-21 11:33:02.780149: step: 1464/530, loss: 0.014962387271225452
2023-01-21 11:33:03.961847: step: 1468/530, loss: 0.05495567247271538
2023-01-21 11:33:05.150600: step: 1472/530, loss: 0.00026302336482331157
2023-01-21 11:33:06.326066: step: 1476/530, loss: 0.0022361755836755037
2023-01-21 11:33:07.497554: step: 1480/530, loss: 0.009579122066497803
2023-01-21 11:33:08.679916: step: 1484/530, loss: 0.0024454116355627775
2023-01-21 11:33:09.870883: step: 1488/530, loss: 0.0028814375400543213
2023-01-21 11:33:11.041400: step: 1492/530, loss: 0.0005291939014568925
2023-01-21 11:33:12.204104: step: 1496/530, loss: 0.015950776636600494
2023-01-21 11:33:13.389171: step: 1500/530, loss: 0.004330158233642578
2023-01-21 11:33:14.571135: step: 1504/530, loss: 0.016999626532197
2023-01-21 11:33:15.706273: step: 1508/530, loss: 0.009596633724868298
2023-01-21 11:33:16.905518: step: 1512/530, loss: 0.025943376123905182
2023-01-21 11:33:18.107147: step: 1516/530, loss: 0.055799342691898346
2023-01-21 11:33:19.278311: step: 1520/530, loss: 0.00123939523473382
2023-01-21 11:33:20.522087: step: 1524/530, loss: 0.07560892403125763
2023-01-21 11:33:21.678271: step: 1528/530, loss: 0.049118999391794205
2023-01-21 11:33:22.849936: step: 1532/530, loss: 0.032479479908943176
2023-01-21 11:33:24.028399: step: 1536/530, loss: 0.1612628996372223
2023-01-21 11:33:25.194065: step: 1540/530, loss: 0.009149551391601562
2023-01-21 11:33:26.361258: step: 1544/530, loss: 0.0006500243907794356
2023-01-21 11:33:27.517610: step: 1548/530, loss: 0.018253136426210403
2023-01-21 11:33:28.732809: step: 1552/530, loss: 0.004974746610969305
2023-01-21 11:33:29.902772: step: 1556/530, loss: 0.0029735565185546875
2023-01-21 11:33:31.070551: step: 1560/530, loss: 0.013292980380356312
2023-01-21 11:33:32.252196: step: 1564/530, loss: 0.029894258826971054
2023-01-21 11:33:33.459324: step: 1568/530, loss: 0.09666679054498672
2023-01-21 11:33:34.605401: step: 1572/530, loss: 0.00869064312428236
2023-01-21 11:33:35.764831: step: 1576/530, loss: 0.04767752066254616
2023-01-21 11:33:36.930906: step: 1580/530, loss: 0.0014657974243164062
2023-01-21 11:33:38.125016: step: 1584/530, loss: 0.0024819374084472656
2023-01-21 11:33:39.361062: step: 1588/530, loss: 0.03092365339398384
2023-01-21 11:33:40.548154: step: 1592/530, loss: 0.03775196149945259
2023-01-21 11:33:41.719689: step: 1596/530, loss: 0.004747009836137295
2023-01-21 11:33:42.895514: step: 1600/530, loss: 0.0010620116954669356
2023-01-21 11:33:44.089895: step: 1604/530, loss: 0.054379653185606
2023-01-21 11:33:45.288717: step: 1608/530, loss: 0.017207050696015358
2023-01-21 11:33:46.474224: step: 1612/530, loss: 2.102851794916205e-05
2023-01-21 11:33:47.618628: step: 1616/530, loss: 0.0002582550223451108
2023-01-21 11:33:48.818152: step: 1620/530, loss: 0.0923502966761589
2023-01-21 11:33:50.015255: step: 1624/530, loss: 0.00016021728515625
2023-01-21 11:33:51.214763: step: 1628/530, loss: 0.03983049467206001
2023-01-21 11:33:52.393416: step: 1632/530, loss: 0.0005466461298055947
2023-01-21 11:33:53.589602: step: 1636/530, loss: 0.031905677169561386
2023-01-21 11:33:54.777668: step: 1640/530, loss: 2.384185791015625e-05
2023-01-21 11:33:56.014312: step: 1644/530, loss: 0.04746303707361221
2023-01-21 11:33:57.217445: step: 1648/530, loss: 0.004205894190818071
2023-01-21 11:33:58.391710: step: 1652/530, loss: 0.03114910237491131
2023-01-21 11:33:59.625049: step: 1656/530, loss: 0.006469440646469593
2023-01-21 11:34:00.802244: step: 1660/530, loss: 0.0570828914642334
2023-01-21 11:34:01.963043: step: 1664/530, loss: 0.009840392507612705
2023-01-21 11:34:03.130424: step: 1668/530, loss: 0.05516967549920082
2023-01-21 11:34:04.343267: step: 1672/530, loss: 0.04099029302597046
2023-01-21 11:34:05.491853: step: 1676/530, loss: 0.0006539345486089587
2023-01-21 11:34:06.637218: step: 1680/530, loss: 0.006010902114212513
2023-01-21 11:34:07.772135: step: 1684/530, loss: 0.3167191445827484
2023-01-21 11:34:08.957001: step: 1688/530, loss: 0.0024128914810717106
2023-01-21 11:34:10.131620: step: 1692/530, loss: 0.01779909059405327
2023-01-21 11:34:11.290306: step: 1696/530, loss: 0.021826840937137604
2023-01-21 11:34:12.483734: step: 1700/530, loss: 0.0077072144486010075
2023-01-21 11:34:13.687436: step: 1704/530, loss: 0.08192399144172668
2023-01-21 11:34:14.897353: step: 1708/530, loss: 0.0054261209443211555
2023-01-21 11:34:16.054173: step: 1712/530, loss: 0.0033092498779296875
2023-01-21 11:34:17.246170: step: 1716/530, loss: 0.015625381842255592
2023-01-21 11:34:18.409637: step: 1720/530, loss: 0.022611241787672043
2023-01-21 11:34:19.584877: step: 1724/530, loss: 0.006053256802260876
2023-01-21 11:34:20.734367: step: 1728/530, loss: 0.006259727291762829
2023-01-21 11:34:21.879139: step: 1732/530, loss: 0.016308307647705078
2023-01-21 11:34:23.058785: step: 1736/530, loss: 0.0623074509203434
2023-01-21 11:34:24.259746: step: 1740/530, loss: 0.004148387815803289
2023-01-21 11:34:25.457230: step: 1744/530, loss: 0.0021419525146484375
2023-01-21 11:34:26.619944: step: 1748/530, loss: 0.00035152435884810984
2023-01-21 11:34:27.817419: step: 1752/530, loss: 0.11254310607910156
2023-01-21 11:34:29.051876: step: 1756/530, loss: 0.003956222906708717
2023-01-21 11:34:30.182471: step: 1760/530, loss: 0.11659526824951172
2023-01-21 11:34:31.383293: step: 1764/530, loss: 0.006517505738884211
2023-01-21 11:34:32.562984: step: 1768/530, loss: 0.002696418669074774
2023-01-21 11:34:33.765637: step: 1772/530, loss: 0.00025858881417661905
2023-01-21 11:34:34.926539: step: 1776/530, loss: 0.11178121715784073
2023-01-21 11:34:36.123661: step: 1780/530, loss: 0.014124107547104359
2023-01-21 11:34:37.283713: step: 1784/530, loss: 0.003504133317619562
2023-01-21 11:34:38.445532: step: 1788/530, loss: 0.06887169182300568
2023-01-21 11:34:39.652513: step: 1792/530, loss: 0.011696148663759232
2023-01-21 11:34:40.819274: step: 1796/530, loss: 0.000327873247442767
2023-01-21 11:34:42.012003: step: 1800/530, loss: 0.006048870272934437
2023-01-21 11:34:43.198930: step: 1804/530, loss: 0.00042724609375
2023-01-21 11:34:44.387860: step: 1808/530, loss: 0.042813874781131744
2023-01-21 11:34:45.559560: step: 1812/530, loss: 0.0016523362137377262
2023-01-21 11:34:46.758698: step: 1816/530, loss: 0.0038652420043945312
2023-01-21 11:34:47.960625: step: 1820/530, loss: 0.013066863641142845
2023-01-21 11:34:49.119935: step: 1824/530, loss: 0.01873188093304634
2023-01-21 11:34:50.299346: step: 1828/530, loss: 0.0333070307970047
2023-01-21 11:34:51.469974: step: 1832/530, loss: 0.008406544104218483
2023-01-21 11:34:52.669275: step: 1836/530, loss: 0.00029211046057753265
2023-01-21 11:34:53.867386: step: 1840/530, loss: 0.06285267323255539
2023-01-21 11:34:55.067510: step: 1844/530, loss: 0.008530807681381702
2023-01-21 11:34:56.225468: step: 1848/530, loss: 0.03209518641233444
2023-01-21 11:34:57.433086: step: 1852/530, loss: 0.06368818134069443
2023-01-21 11:34:58.661313: step: 1856/530, loss: 0.06327047199010849
2023-01-21 11:34:59.858914: step: 1860/530, loss: 0.01629047468304634
2023-01-21 11:35:00.999805: step: 1864/530, loss: 0.00112323765642941
2023-01-21 11:35:02.186225: step: 1868/530, loss: 0.025887776166200638
2023-01-21 11:35:03.340574: step: 1872/530, loss: 0.002650642301887274
2023-01-21 11:35:04.543602: step: 1876/530, loss: 0.011905098333954811
2023-01-21 11:35:05.723634: step: 1880/530, loss: 0.06725392490625381
2023-01-21 11:35:06.888504: step: 1884/530, loss: 0.00947804469615221
2023-01-21 11:35:08.096353: step: 1888/530, loss: 0.002638149308040738
2023-01-21 11:35:09.284505: step: 1892/530, loss: 0.042471691966056824
2023-01-21 11:35:10.454187: step: 1896/530, loss: 0.0111083984375
2023-01-21 11:35:11.651402: step: 1900/530, loss: 0.015712358057498932
2023-01-21 11:35:12.809794: step: 1904/530, loss: 0.01514902152121067
2023-01-21 11:35:13.949262: step: 1908/530, loss: 0.004777717404067516
2023-01-21 11:35:15.104576: step: 1912/530, loss: 0.001821804093196988
2023-01-21 11:35:16.283491: step: 1916/530, loss: 0.011377525515854359
2023-01-21 11:35:17.474708: step: 1920/530, loss: 0.003170871874317527
2023-01-21 11:35:18.673510: step: 1924/530, loss: 0.016153812408447266
2023-01-21 11:35:19.901085: step: 1928/530, loss: 0.12940844893455505
2023-01-21 11:35:21.075838: step: 1932/530, loss: 0.06450223922729492
2023-01-21 11:35:22.239262: step: 1936/530, loss: 0.003084373427554965
2023-01-21 11:35:23.409008: step: 1940/530, loss: 0.02369213104248047
2023-01-21 11:35:24.637773: step: 1944/530, loss: 0.01616687700152397
2023-01-21 11:35:25.796620: step: 1948/530, loss: 0.0005153656238690019
2023-01-21 11:35:27.020979: step: 1952/530, loss: 0.049954984337091446
2023-01-21 11:35:28.178071: step: 1956/530, loss: 0.033426474779844284
2023-01-21 11:35:29.376843: step: 1960/530, loss: 0.02971637435257435
2023-01-21 11:35:30.544721: step: 1964/530, loss: 0.014287757687270641
2023-01-21 11:35:31.704003: step: 1968/530, loss: 0.10565529018640518
2023-01-21 11:35:32.829067: step: 1972/530, loss: 0.04786510393023491
2023-01-21 11:35:34.040733: step: 1976/530, loss: 0.011258697137236595
2023-01-21 11:35:35.197701: step: 1980/530, loss: 0.0031207085121423006
2023-01-21 11:35:36.380353: step: 1984/530, loss: 0.05266456678509712
2023-01-21 11:35:37.542456: step: 1988/530, loss: 0.006815433502197266
2023-01-21 11:35:38.729909: step: 1992/530, loss: 0.008387184701859951
2023-01-21 11:35:39.886566: step: 1996/530, loss: 0.004331779666244984
2023-01-21 11:35:41.086685: step: 2000/530, loss: 0.013284874148666859
2023-01-21 11:35:42.292302: step: 2004/530, loss: 0.012166202068328857
2023-01-21 11:35:43.459183: step: 2008/530, loss: 0.007929325103759766
2023-01-21 11:35:44.632301: step: 2012/530, loss: 0.004205608740448952
2023-01-21 11:35:45.838058: step: 2016/530, loss: 0.007957840338349342
2023-01-21 11:35:47.081325: step: 2020/530, loss: 0.07635222375392914
2023-01-21 11:35:48.284788: step: 2024/530, loss: 0.00010805130295921117
2023-01-21 11:35:49.421733: step: 2028/530, loss: 0.0020953179337084293
2023-01-21 11:35:50.618242: step: 2032/530, loss: 0.004692792892456055
2023-01-21 11:35:51.750405: step: 2036/530, loss: 0.06972961872816086
2023-01-21 11:35:52.940068: step: 2040/530, loss: 0.48789748549461365
2023-01-21 11:35:54.097073: step: 2044/530, loss: 0.03279144689440727
2023-01-21 11:35:55.267259: step: 2048/530, loss: 0.02361736260354519
2023-01-21 11:35:56.419654: step: 2052/530, loss: 0.00763206509873271
2023-01-21 11:35:57.589682: step: 2056/530, loss: 0.001575040863826871
2023-01-21 11:35:58.822785: step: 2060/530, loss: 0.015694810077548027
2023-01-21 11:36:00.010459: step: 2064/530, loss: 0.00690960930660367
2023-01-21 11:36:01.177706: step: 2068/530, loss: 0.016270829364657402
2023-01-21 11:36:02.368729: step: 2072/530, loss: 0.4153619706630707
2023-01-21 11:36:03.523045: step: 2076/530, loss: 0.016048477962613106
2023-01-21 11:36:04.704163: step: 2080/530, loss: 0.014982796274125576
2023-01-21 11:36:05.855818: step: 2084/530, loss: 0.023361969739198685
2023-01-21 11:36:07.041207: step: 2088/530, loss: 0.677126407623291
2023-01-21 11:36:08.283276: step: 2092/530, loss: 0.027340127155184746
2023-01-21 11:36:09.499822: step: 2096/530, loss: 0.004211426246911287
2023-01-21 11:36:10.687395: step: 2100/530, loss: 0.19484834372997284
2023-01-21 11:36:11.879843: step: 2104/530, loss: 0.26508501172065735
2023-01-21 11:36:13.088445: step: 2108/530, loss: 0.08909378200769424
2023-01-21 11:36:14.256060: step: 2112/530, loss: 0.003685093019157648
2023-01-21 11:36:15.439797: step: 2116/530, loss: 0.013727569952607155
2023-01-21 11:36:16.611646: step: 2120/530, loss: 0.008339500054717064
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.5718475073313783, 'r': 0.7789613848202397, 'f1': 0.6595264937993235}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6357110812023329, 'r': 0.8148361127084531, 'f1': 0.7142137096774194}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6481481481481481, 'r': 0.5555555555555556, 'f1': 0.5982905982905983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.39622641509433965, 'r': 0.5833333333333334, 'f1': 0.4719101123595506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:37:00.552967: step: 4/530, loss: 0.03409166261553764
2023-01-21 11:37:01.736119: step: 8/530, loss: 0.03193025663495064
2023-01-21 11:37:02.908473: step: 12/530, loss: 0.0058532715775072575
2023-01-21 11:37:04.045473: step: 16/530, loss: 0.0021389008034020662
2023-01-21 11:37:05.226256: step: 20/530, loss: 0.018410874530673027
2023-01-21 11:37:06.366637: step: 24/530, loss: 0.07471618801355362
2023-01-21 11:37:07.538424: step: 28/530, loss: 0.014126110821962357
2023-01-21 11:37:08.706047: step: 32/530, loss: 0.0005076408269815147
2023-01-21 11:37:09.896838: step: 36/530, loss: 0.01622305065393448
2023-01-21 11:37:11.124146: step: 40/530, loss: 0.02559223212301731
2023-01-21 11:37:12.382029: step: 44/530, loss: 0.05685615539550781
2023-01-21 11:37:13.603140: step: 48/530, loss: 2.4127959477482364e-05
2023-01-21 11:37:14.765117: step: 52/530, loss: 0.361195832490921
2023-01-21 11:37:15.900589: step: 56/530, loss: 0.0036674258299171925
2023-01-21 11:37:17.101054: step: 60/530, loss: 0.002258205320686102
2023-01-21 11:37:18.276971: step: 64/530, loss: 0.0048542022705078125
2023-01-21 11:37:19.525245: step: 68/530, loss: 0.712786078453064
2023-01-21 11:37:20.735500: step: 72/530, loss: 0.00347404507920146
2023-01-21 11:37:21.885736: step: 76/530, loss: 0.020935440436005592
2023-01-21 11:37:23.047387: step: 80/530, loss: 0.02510075643658638
2023-01-21 11:37:24.224583: step: 84/530, loss: 0.027249718084931374
2023-01-21 11:37:25.393230: step: 88/530, loss: 9.51766996877268e-05
2023-01-21 11:37:26.608648: step: 92/530, loss: 0.007130766287446022
2023-01-21 11:37:27.829230: step: 96/530, loss: 0.011723709292709827
2023-01-21 11:37:29.056367: step: 100/530, loss: 0.0028701783157885075
2023-01-21 11:37:30.240024: step: 104/530, loss: 0.09053116291761398
2023-01-21 11:37:31.411971: step: 108/530, loss: 0.0027308466378599405
2023-01-21 11:37:32.561321: step: 112/530, loss: 0.020466994494199753
2023-01-21 11:37:33.744724: step: 116/530, loss: 0.0215651523321867
2023-01-21 11:37:34.891882: step: 120/530, loss: 0.0008586883777752519
2023-01-21 11:37:36.075376: step: 124/530, loss: 0.0005118370172567666
2023-01-21 11:37:37.222677: step: 128/530, loss: 0.001217794488184154
2023-01-21 11:37:38.402988: step: 132/530, loss: 0.023675061762332916
2023-01-21 11:37:39.575604: step: 136/530, loss: 5.418656349182129
2023-01-21 11:37:40.776865: step: 140/530, loss: 0.01898517645895481
2023-01-21 11:37:41.982758: step: 144/530, loss: 0.18063677847385406
2023-01-21 11:37:43.224452: step: 148/530, loss: 0.005933571141213179
2023-01-21 11:37:44.359982: step: 152/530, loss: 0.24706535041332245
2023-01-21 11:37:45.520651: step: 156/530, loss: 0.0018049239879474044
2023-01-21 11:37:46.691800: step: 160/530, loss: 0.005853462032973766
2023-01-21 11:37:47.895446: step: 164/530, loss: 0.040555190294981
2023-01-21 11:37:49.065296: step: 168/530, loss: 0.008160400204360485
2023-01-21 11:37:50.237863: step: 172/530, loss: 0.003976630978286266
2023-01-21 11:37:51.379630: step: 176/530, loss: 0.00018596649169921875
2023-01-21 11:37:52.539840: step: 180/530, loss: 0.02903003618121147
2023-01-21 11:37:53.728547: step: 184/530, loss: 0.0016951560974121094
2023-01-21 11:37:54.914647: step: 188/530, loss: 0.0027680397033691406
2023-01-21 11:37:56.100389: step: 192/530, loss: 0.010685205459594727
2023-01-21 11:37:57.307092: step: 196/530, loss: 0.025789452716708183
2023-01-21 11:37:58.458520: step: 200/530, loss: 0.0025676728691905737
2023-01-21 11:37:59.693235: step: 204/530, loss: 9.460448927711695e-05
2023-01-21 11:38:00.866808: step: 208/530, loss: 0.040413569658994675
2023-01-21 11:38:02.048881: step: 212/530, loss: 0.0002845764101948589
2023-01-21 11:38:03.211980: step: 216/530, loss: 5.550384594243951e-05
2023-01-21 11:38:04.370360: step: 220/530, loss: 0.038589004427194595
2023-01-21 11:38:05.545668: step: 224/530, loss: 0.5917990207672119
2023-01-21 11:38:06.722184: step: 228/530, loss: 0.058554936200380325
2023-01-21 11:38:07.889722: step: 232/530, loss: 0.021830368787050247
2023-01-21 11:38:09.056445: step: 236/530, loss: 0.023868178948760033
2023-01-21 11:38:10.235054: step: 240/530, loss: 0.0064521790482103825
2023-01-21 11:38:11.410284: step: 244/530, loss: 0.009249306283891201
2023-01-21 11:38:12.614745: step: 248/530, loss: 0.00765189528465271
2023-01-21 11:38:13.750344: step: 252/530, loss: 0.0023962499108165503
2023-01-21 11:38:14.972696: step: 256/530, loss: 0.023401450365781784
2023-01-21 11:38:16.154414: step: 260/530, loss: 0.1560174822807312
2023-01-21 11:38:17.332507: step: 264/530, loss: 0.012804031372070312
2023-01-21 11:38:18.554315: step: 268/530, loss: 0.027866840362548828
2023-01-21 11:38:19.753157: step: 272/530, loss: 0.00036277773324400187
2023-01-21 11:38:20.938696: step: 276/530, loss: 0.05291710048913956
2023-01-21 11:38:22.153345: step: 280/530, loss: 0.027625083923339844
2023-01-21 11:38:23.322200: step: 284/530, loss: 0.7572216987609863
2023-01-21 11:38:24.499081: step: 288/530, loss: 0.019618989899754524
2023-01-21 11:38:25.722958: step: 292/530, loss: 0.0032339096069335938
2023-01-21 11:38:26.917786: step: 296/530, loss: 0.06748094409704208
2023-01-21 11:38:28.109845: step: 300/530, loss: 0.013437843881547451
2023-01-21 11:38:29.291135: step: 304/530, loss: 0.00042190554086118937
2023-01-21 11:38:30.461451: step: 308/530, loss: 0.10079803317785263
2023-01-21 11:38:31.619339: step: 312/530, loss: 0.025503158569335938
2023-01-21 11:38:32.765452: step: 316/530, loss: 0.04629535600543022
2023-01-21 11:38:33.944316: step: 320/530, loss: 0.0031642913818359375
2023-01-21 11:38:35.108919: step: 324/530, loss: 0.01624126359820366
2023-01-21 11:38:36.320753: step: 328/530, loss: 0.02054891549050808
2023-01-21 11:38:37.469618: step: 332/530, loss: 0.0045104981400072575
2023-01-21 11:38:38.658217: step: 336/530, loss: 0.019738389179110527
2023-01-21 11:38:39.872271: step: 340/530, loss: 0.007002639584243298
2023-01-21 11:38:41.026584: step: 344/530, loss: 0.027447987347841263
2023-01-21 11:38:42.229324: step: 348/530, loss: 0.029940320178866386
2023-01-21 11:38:43.399341: step: 352/530, loss: 0.02381744422018528
2023-01-21 11:38:44.568564: step: 356/530, loss: 0.0008230209350585938
2023-01-21 11:38:45.772766: step: 360/530, loss: 0.07859973609447479
2023-01-21 11:38:46.966736: step: 364/530, loss: 0.16619901359081268
2023-01-21 11:38:48.155246: step: 368/530, loss: 0.06649179756641388
2023-01-21 11:38:49.318484: step: 372/530, loss: 0.018617724999785423
2023-01-21 11:38:50.511997: step: 376/530, loss: 0.020396994426846504
2023-01-21 11:38:51.673401: step: 380/530, loss: 0.06969738006591797
2023-01-21 11:38:52.844654: step: 384/530, loss: 0.05618009343743324
2023-01-21 11:38:54.009144: step: 388/530, loss: 0.0010696410899981856
2023-01-21 11:38:55.212311: step: 392/530, loss: 0.019032049924135208
2023-01-21 11:38:56.389732: step: 396/530, loss: 0.0017854690086096525
2023-01-21 11:38:57.550437: step: 400/530, loss: 0.017742633819580078
2023-01-21 11:38:58.697350: step: 404/530, loss: 9.34600830078125e-05
2023-01-21 11:38:59.856866: step: 408/530, loss: 0.0009266853448934853
2023-01-21 11:39:01.038053: step: 412/530, loss: 0.3445890545845032
2023-01-21 11:39:02.200096: step: 416/530, loss: 0.013064194470643997
2023-01-21 11:39:03.361314: step: 420/530, loss: 0.06865697354078293
2023-01-21 11:39:04.556812: step: 424/530, loss: 0.011952400207519531
2023-01-21 11:39:05.800703: step: 428/530, loss: 0.018743276596069336
2023-01-21 11:39:06.959146: step: 432/530, loss: 0.036884307861328125
2023-01-21 11:39:08.155228: step: 436/530, loss: 0.011086653918027878
2023-01-21 11:39:09.319531: step: 440/530, loss: 0.025307463482022285
2023-01-21 11:39:10.512210: step: 444/530, loss: 0.19674663245677948
2023-01-21 11:39:11.705940: step: 448/530, loss: 0.01050043199211359
2023-01-21 11:39:12.862282: step: 452/530, loss: 3.8433074223576114e-05
2023-01-21 11:39:14.069519: step: 456/530, loss: 0.014889050275087357
2023-01-21 11:39:15.251482: step: 460/530, loss: 0.00867157056927681
2023-01-21 11:39:16.396791: step: 464/530, loss: 0.00893030222505331
2023-01-21 11:39:17.608285: step: 468/530, loss: 0.07373370975255966
2023-01-21 11:39:18.804906: step: 472/530, loss: 0.0002017974911723286
2023-01-21 11:39:19.954778: step: 476/530, loss: 8.554458327125758e-05
2023-01-21 11:39:21.123916: step: 480/530, loss: 0.0007474839221686125
2023-01-21 11:39:22.291731: step: 484/530, loss: 0.03641033545136452
2023-01-21 11:39:23.460437: step: 488/530, loss: 0.11632471531629562
2023-01-21 11:39:24.691607: step: 492/530, loss: 0.0019572018645703793
2023-01-21 11:39:25.846350: step: 496/530, loss: 0.0012701035011559725
2023-01-21 11:39:27.044161: step: 500/530, loss: 0.001673889230005443
2023-01-21 11:39:28.230740: step: 504/530, loss: 0.026025772094726562
2023-01-21 11:39:29.403747: step: 508/530, loss: 0.10651111602783203
2023-01-21 11:39:30.585251: step: 512/530, loss: 0.02816600725054741
2023-01-21 11:39:31.761265: step: 516/530, loss: 0.028992462903261185
2023-01-21 11:39:32.963847: step: 520/530, loss: 0.0013288498157635331
2023-01-21 11:39:34.115134: step: 524/530, loss: 0.0013687133323401213
2023-01-21 11:39:35.260899: step: 528/530, loss: 0.017392253503203392
2023-01-21 11:39:36.452050: step: 532/530, loss: 0.012844085693359375
2023-01-21 11:39:37.608327: step: 536/530, loss: 0.0003517150762490928
2023-01-21 11:39:38.836742: step: 540/530, loss: 0.0005889892345294356
2023-01-21 11:39:40.030512: step: 544/530, loss: 0.0009160995250567794
2023-01-21 11:39:41.219534: step: 548/530, loss: 4.081726001459174e-05
2023-01-21 11:39:42.376647: step: 552/530, loss: 0.0008733749273233116
2023-01-21 11:39:43.556822: step: 556/530, loss: 0.0006784438737668097
2023-01-21 11:39:44.753188: step: 560/530, loss: 0.0002115249662892893
2023-01-21 11:39:45.936642: step: 564/530, loss: 0.02852792665362358
2023-01-21 11:39:47.129806: step: 568/530, loss: 0.09874648600816727
2023-01-21 11:39:48.289172: step: 572/530, loss: 0.02537374570965767
2023-01-21 11:39:49.453835: step: 576/530, loss: 0.004939270205795765
2023-01-21 11:39:50.648513: step: 580/530, loss: 0.0022682189010083675
2023-01-21 11:39:51.839422: step: 584/530, loss: 0.02480793185532093
2023-01-21 11:39:53.014097: step: 588/530, loss: 0.0007406235090456903
2023-01-21 11:39:54.206611: step: 592/530, loss: 0.0005002975813113153
2023-01-21 11:39:55.384180: step: 596/530, loss: 0.24968652427196503
2023-01-21 11:39:56.586620: step: 600/530, loss: 0.03022770956158638
2023-01-21 11:39:57.758674: step: 604/530, loss: 0.00012073517427779734
2023-01-21 11:39:58.949095: step: 608/530, loss: 0.007216072175651789
2023-01-21 11:40:00.160456: step: 612/530, loss: 0.04644498974084854
2023-01-21 11:40:01.316798: step: 616/530, loss: 0.014883232302963734
2023-01-21 11:40:02.492832: step: 620/530, loss: 0.0011398314964026213
2023-01-21 11:40:03.657818: step: 624/530, loss: 0.02005157619714737
2023-01-21 11:40:04.826461: step: 628/530, loss: 0.00032124522840604186
2023-01-21 11:40:06.050337: step: 632/530, loss: 0.00857076607644558
2023-01-21 11:40:07.228954: step: 636/530, loss: 0.07529878616333008
2023-01-21 11:40:08.367778: step: 640/530, loss: 0.0004155159112997353
2023-01-21 11:40:09.538627: step: 644/530, loss: 0.46210968494415283
2023-01-21 11:40:10.748238: step: 648/530, loss: 0.016603946685791016
2023-01-21 11:40:11.959123: step: 652/530, loss: 0.03349647670984268
2023-01-21 11:40:13.124268: step: 656/530, loss: 0.0006025314796715975
2023-01-21 11:40:14.388521: step: 660/530, loss: 0.0027688026893883944
2023-01-21 11:40:15.524509: step: 664/530, loss: 0.00572891253978014
2023-01-21 11:40:16.698509: step: 668/530, loss: 0.009322834201157093
2023-01-21 11:40:17.902968: step: 672/530, loss: 0.029540730640292168
2023-01-21 11:40:19.104443: step: 676/530, loss: 0.004547500982880592
2023-01-21 11:40:20.302653: step: 680/530, loss: 0.025919485837221146
2023-01-21 11:40:21.477968: step: 684/530, loss: 0.00589828472584486
2023-01-21 11:40:22.642548: step: 688/530, loss: 0.0010640145046636462
2023-01-21 11:40:23.808351: step: 692/530, loss: 0.0022254944778978825
2023-01-21 11:40:24.950763: step: 696/530, loss: 0.0025725364685058594
2023-01-21 11:40:26.097868: step: 700/530, loss: 0.01551666297018528
2023-01-21 11:40:27.288554: step: 704/530, loss: 0.015275193378329277
2023-01-21 11:40:28.437412: step: 708/530, loss: 0.0029155730735510588
2023-01-21 11:40:29.612833: step: 712/530, loss: 0.002224445343017578
2023-01-21 11:40:30.843491: step: 716/530, loss: 0.007357120513916016
2023-01-21 11:40:32.007343: step: 720/530, loss: 0.005003166384994984
2023-01-21 11:40:33.222963: step: 724/530, loss: 0.012697601690888405
2023-01-21 11:40:34.387895: step: 728/530, loss: 0.00424881000071764
2023-01-21 11:40:35.593233: step: 732/530, loss: 0.0032243728637695312
2023-01-21 11:40:36.829985: step: 736/530, loss: 0.009167480282485485
2023-01-21 11:40:38.003316: step: 740/530, loss: 0.01875457912683487
2023-01-21 11:40:39.164773: step: 744/530, loss: 0.005012893583625555
2023-01-21 11:40:40.328995: step: 748/530, loss: 0.02488241344690323
2023-01-21 11:40:41.500303: step: 752/530, loss: 0.00024280548677779734
2023-01-21 11:40:42.749100: step: 756/530, loss: 0.012627220712602139
2023-01-21 11:40:43.928864: step: 760/530, loss: 0.0006450653309002519
2023-01-21 11:40:45.056197: step: 764/530, loss: 0.01956338994204998
2023-01-21 11:40:46.216658: step: 768/530, loss: 0.01053008995950222
2023-01-21 11:40:47.394973: step: 772/530, loss: 0.017417192459106445
2023-01-21 11:40:48.663741: step: 776/530, loss: 0.00564079312607646
2023-01-21 11:40:49.849029: step: 780/530, loss: 0.013112401589751244
2023-01-21 11:40:51.040901: step: 784/530, loss: 0.06111655384302139
2023-01-21 11:40:52.175503: step: 788/530, loss: 0.0050394535064697266
2023-01-21 11:40:53.348390: step: 792/530, loss: 0.05225839838385582
2023-01-21 11:40:54.496229: step: 796/530, loss: 0.0040902611799538136
2023-01-21 11:40:55.677921: step: 800/530, loss: 0.04330252483487129
2023-01-21 11:40:56.841692: step: 804/530, loss: 0.007888412103056908
2023-01-21 11:40:58.000082: step: 808/530, loss: 0.004364013671875
2023-01-21 11:40:59.253888: step: 812/530, loss: 0.07257270812988281
2023-01-21 11:41:00.439987: step: 816/530, loss: 0.02567659690976143
2023-01-21 11:41:01.626796: step: 820/530, loss: 0.03379053995013237
2023-01-21 11:41:02.788146: step: 824/530, loss: 0.002023029373958707
2023-01-21 11:41:03.987528: step: 828/530, loss: 0.3274766206741333
2023-01-21 11:41:05.139624: step: 832/530, loss: 0.07246441394090652
2023-01-21 11:41:06.322015: step: 836/530, loss: 0.0022808073554188013
2023-01-21 11:41:07.515956: step: 840/530, loss: 0.003610801650211215
2023-01-21 11:41:08.659230: step: 844/530, loss: 0.05038166046142578
2023-01-21 11:41:09.814368: step: 848/530, loss: 0.0072740791365504265
2023-01-21 11:41:10.959965: step: 852/530, loss: 0.006577110383659601
2023-01-21 11:41:12.189416: step: 856/530, loss: 0.0019723891746252775
2023-01-21 11:41:13.328887: step: 860/530, loss: 0.018727827817201614
2023-01-21 11:41:14.533982: step: 864/530, loss: 0.0038949965965002775
2023-01-21 11:41:15.664887: step: 868/530, loss: 0.0062927245162427425
2023-01-21 11:41:16.864596: step: 872/530, loss: 0.0012542724143713713
2023-01-21 11:41:18.039268: step: 876/530, loss: 0.006850815378129482
2023-01-21 11:41:19.189251: step: 880/530, loss: 0.0003421783621888608
2023-01-21 11:41:20.386738: step: 884/530, loss: 0.016699600964784622
2023-01-21 11:41:21.554635: step: 888/530, loss: 0.0003110409015789628
2023-01-21 11:41:22.740266: step: 892/530, loss: 0.013224220834672451
2023-01-21 11:41:23.929072: step: 896/530, loss: 0.011777782812714577
2023-01-21 11:41:25.125831: step: 900/530, loss: 0.026536274701356888
2023-01-21 11:41:26.301938: step: 904/530, loss: 0.04967556148767471
2023-01-21 11:41:27.437326: step: 908/530, loss: 0.025925733149051666
2023-01-21 11:41:28.644170: step: 912/530, loss: 0.03671465069055557
2023-01-21 11:41:29.810966: step: 916/530, loss: 0.0023569108452647924
2023-01-21 11:41:30.988634: step: 920/530, loss: 0.03594684973359108
2023-01-21 11:41:32.163040: step: 924/530, loss: 0.0007244587177410722
2023-01-21 11:41:33.336321: step: 928/530, loss: 0.0003900528245139867
2023-01-21 11:41:34.484361: step: 932/530, loss: 0.0003909588267561048
2023-01-21 11:41:35.669739: step: 936/530, loss: 6.008148193359375e-05
2023-01-21 11:41:36.838645: step: 940/530, loss: 0.0012351989280432463
2023-01-21 11:41:38.054729: step: 944/530, loss: 0.07258529961109161
2023-01-21 11:41:39.240192: step: 948/530, loss: 0.48776674270629883
2023-01-21 11:41:40.419540: step: 952/530, loss: 0.028760481625795364
2023-01-21 11:41:41.575104: step: 956/530, loss: 0.04018354415893555
2023-01-21 11:41:42.749412: step: 960/530, loss: 0.09177380055189133
2023-01-21 11:41:43.902155: step: 964/530, loss: 0.005367851350456476
2023-01-21 11:41:45.101825: step: 968/530, loss: 0.005866051185876131
2023-01-21 11:41:46.279017: step: 972/530, loss: 0.0022155761253088713
2023-01-21 11:41:47.499107: step: 976/530, loss: 0.009877204895019531
2023-01-21 11:41:48.656851: step: 980/530, loss: 0.01565866358578205
2023-01-21 11:41:49.847059: step: 984/530, loss: 0.016060637310147285
2023-01-21 11:41:50.980895: step: 988/530, loss: 0.0008542060968466103
2023-01-21 11:41:52.148443: step: 992/530, loss: 0.008973121643066406
2023-01-21 11:41:53.343327: step: 996/530, loss: 0.024879170581698418
2023-01-21 11:41:54.517101: step: 1000/530, loss: 0.007134533021599054
2023-01-21 11:41:55.756203: step: 1004/530, loss: 0.014979267492890358
2023-01-21 11:41:56.925355: step: 1008/530, loss: 0.001429542899131775
2023-01-21 11:41:58.056828: step: 1012/530, loss: 0.00026121141854673624
2023-01-21 11:41:59.200300: step: 1016/530, loss: 0.027822017669677734
2023-01-21 11:42:00.396261: step: 1020/530, loss: 3.2043459214037284e-05
2023-01-21 11:42:01.571469: step: 1024/530, loss: 0.027243996039032936
2023-01-21 11:42:02.748754: step: 1028/530, loss: 0.029395580291748047
2023-01-21 11:42:03.966504: step: 1032/530, loss: 0.025845492258667946
2023-01-21 11:42:05.142927: step: 1036/530, loss: 0.19599103927612305
2023-01-21 11:42:06.294957: step: 1040/530, loss: 0.02287006564438343
2023-01-21 11:42:07.475599: step: 1044/530, loss: 0.010676383972167969
2023-01-21 11:42:08.672605: step: 1048/530, loss: 0.020765114575624466
2023-01-21 11:42:09.797265: step: 1052/530, loss: 0.004429960623383522
2023-01-21 11:42:10.964192: step: 1056/530, loss: 0.10266468673944473
2023-01-21 11:42:12.147654: step: 1060/530, loss: 0.1548130214214325
2023-01-21 11:42:13.345228: step: 1064/530, loss: 0.056841567158699036
2023-01-21 11:42:14.537492: step: 1068/530, loss: 0.025782013311982155
2023-01-21 11:42:15.703263: step: 1072/530, loss: 0.012751614674925804
2023-01-21 11:42:16.889193: step: 1076/530, loss: 0.014635086059570312
2023-01-21 11:42:17.995381: step: 1080/530, loss: 0.00025453566922806203
2023-01-21 11:42:19.145611: step: 1084/530, loss: 0.030837249010801315
2023-01-21 11:42:20.356136: step: 1088/530, loss: 0.008731460198760033
2023-01-21 11:42:21.523673: step: 1092/530, loss: 0.012356853112578392
2023-01-21 11:42:22.700515: step: 1096/530, loss: 0.002835512161254883
2023-01-21 11:42:23.853678: step: 1100/530, loss: 0.0010138035286217928
2023-01-21 11:42:25.064840: step: 1104/530, loss: 0.0768800750374794
2023-01-21 11:42:26.212645: step: 1108/530, loss: 0.029697705060243607
2023-01-21 11:42:27.403243: step: 1112/530, loss: 0.009760475717484951
2023-01-21 11:42:28.586981: step: 1116/530, loss: 0.0021529197692871094
2023-01-21 11:42:29.748344: step: 1120/530, loss: 0.0017699719173833728
2023-01-21 11:42:30.998252: step: 1124/530, loss: 0.0008200168376788497
2023-01-21 11:42:32.240608: step: 1128/530, loss: 0.03922557830810547
2023-01-21 11:42:33.379130: step: 1132/530, loss: 0.00019550323486328125
2023-01-21 11:42:34.531514: step: 1136/530, loss: 0.016022611409425735
2023-01-21 11:42:35.723860: step: 1140/530, loss: 0.0006153106805868447
2023-01-21 11:42:36.899755: step: 1144/530, loss: 0.016709137707948685
2023-01-21 11:42:38.120827: step: 1148/530, loss: 0.006598090752959251
2023-01-21 11:42:39.318032: step: 1152/530, loss: 0.0005770683055743575
2023-01-21 11:42:40.519142: step: 1156/530, loss: 0.006673336029052734
2023-01-21 11:42:41.687050: step: 1160/530, loss: 0.054181672632694244
2023-01-21 11:42:42.867306: step: 1164/530, loss: 0.07523231208324432
2023-01-21 11:42:44.074984: step: 1168/530, loss: 0.01913623884320259
2023-01-21 11:42:45.258572: step: 1172/530, loss: 0.018793296068906784
2023-01-21 11:42:46.457673: step: 1176/530, loss: 0.08867178112268448
2023-01-21 11:42:47.611681: step: 1180/530, loss: 0.015080690383911133
2023-01-21 11:42:48.821458: step: 1184/530, loss: 0.005277061369270086
2023-01-21 11:42:49.986536: step: 1188/530, loss: 0.0006712913163937628
2023-01-21 11:42:51.183999: step: 1192/530, loss: 0.014921379275619984
2023-01-21 11:42:52.343468: step: 1196/530, loss: 0.010855864733457565
2023-01-21 11:42:53.547533: step: 1200/530, loss: 0.0003086090146098286
2023-01-21 11:42:54.707474: step: 1204/530, loss: 0.006305694580078125
2023-01-21 11:42:55.908355: step: 1208/530, loss: 0.35740986466407776
2023-01-21 11:42:57.063366: step: 1212/530, loss: 0.00034770966158248484
2023-01-21 11:42:58.243564: step: 1216/530, loss: 0.030100345611572266
2023-01-21 11:42:59.466662: step: 1220/530, loss: 0.00037059784517623484
2023-01-21 11:43:00.641532: step: 1224/530, loss: 0.0021636963356286287
2023-01-21 11:43:01.799871: step: 1228/530, loss: 0.08790435642004013
2023-01-21 11:43:02.970606: step: 1232/530, loss: 0.011873054318130016
2023-01-21 11:43:04.177371: step: 1236/530, loss: 0.038666918873786926
2023-01-21 11:43:05.349535: step: 1240/530, loss: 0.03247880935668945
2023-01-21 11:43:06.488861: step: 1244/530, loss: 0.01125960424542427
2023-01-21 11:43:07.703536: step: 1248/530, loss: 0.042960360646247864
2023-01-21 11:43:08.915989: step: 1252/530, loss: 0.006751346401870251
2023-01-21 11:43:10.069956: step: 1256/530, loss: 0.0007349014631472528
2023-01-21 11:43:11.255798: step: 1260/530, loss: 0.036782003939151764
2023-01-21 11:43:12.446576: step: 1264/530, loss: 0.021926403045654297
2023-01-21 11:43:13.612136: step: 1268/530, loss: 0.05921068415045738
2023-01-21 11:43:14.803363: step: 1272/530, loss: 0.01248469389975071
2023-01-21 11:43:16.005333: step: 1276/530, loss: 0.004160786047577858
2023-01-21 11:43:17.197832: step: 1280/530, loss: 0.0003606796090025455
2023-01-21 11:43:18.397020: step: 1284/530, loss: 0.04645023122429848
2023-01-21 11:43:19.597555: step: 1288/530, loss: 0.0006767272716388106
2023-01-21 11:43:20.770950: step: 1292/530, loss: 0.014310074038803577
2023-01-21 11:43:21.936611: step: 1296/530, loss: 0.03072500415146351
2023-01-21 11:43:23.125190: step: 1300/530, loss: 0.02213277667760849
2023-01-21 11:43:24.275746: step: 1304/530, loss: 7.019042823230848e-05
2023-01-21 11:43:25.472467: step: 1308/530, loss: 0.008624744601547718
2023-01-21 11:43:26.640662: step: 1312/530, loss: 0.018869400024414062
2023-01-21 11:43:27.846586: step: 1316/530, loss: 0.03334398195147514
2023-01-21 11:43:29.025433: step: 1320/530, loss: 0.10556736588478088
2023-01-21 11:43:30.219829: step: 1324/530, loss: 0.0023458481300622225
2023-01-21 11:43:31.414466: step: 1328/530, loss: 0.23438234627246857
2023-01-21 11:43:32.607042: step: 1332/530, loss: 0.027270697057247162
2023-01-21 11:43:33.860065: step: 1336/530, loss: 0.0030594351701438427
2023-01-21 11:43:35.038023: step: 1340/530, loss: 0.09040413051843643
2023-01-21 11:43:36.266163: step: 1344/530, loss: 0.013030719943344593
2023-01-21 11:43:37.446016: step: 1348/530, loss: 0.015890885144472122
2023-01-21 11:43:38.641752: step: 1352/530, loss: 0.00022902488126419485
2023-01-21 11:43:39.813281: step: 1356/530, loss: 0.0072998045943677425
2023-01-21 11:43:41.014162: step: 1360/530, loss: 0.0012067795032635331
2023-01-21 11:43:42.213468: step: 1364/530, loss: 0.05865049362182617
2023-01-21 11:43:43.389030: step: 1368/530, loss: 0.0024105070624500513
2023-01-21 11:43:44.610735: step: 1372/530, loss: 0.09917287528514862
2023-01-21 11:43:45.769149: step: 1376/530, loss: 0.0225190632045269
2023-01-21 11:43:46.951174: step: 1380/530, loss: 0.028338052332401276
2023-01-21 11:43:48.158344: step: 1384/530, loss: 0.003952884580940008
2023-01-21 11:43:49.342263: step: 1388/530, loss: 0.021691275760531425
2023-01-21 11:43:50.549596: step: 1392/530, loss: 0.007308769505470991
2023-01-21 11:43:51.735025: step: 1396/530, loss: 0.025660326704382896
2023-01-21 11:43:52.909173: step: 1400/530, loss: 0.0019244194263592362
2023-01-21 11:43:54.107994: step: 1404/530, loss: 0.017899896949529648
2023-01-21 11:43:55.281046: step: 1408/530, loss: 0.0030311583541333675
2023-01-21 11:43:56.462240: step: 1412/530, loss: 0.11538705974817276
2023-01-21 11:43:57.655160: step: 1416/530, loss: 0.0010082245571538806
2023-01-21 11:43:58.829555: step: 1420/530, loss: 0.007002830505371094
2023-01-21 11:44:00.025332: step: 1424/530, loss: 0.011046027764678001
2023-01-21 11:44:01.199709: step: 1428/530, loss: 0.006727063562721014
2023-01-21 11:44:02.387689: step: 1432/530, loss: 0.01045694388449192
2023-01-21 11:44:03.596275: step: 1436/530, loss: 0.009931564331054688
2023-01-21 11:44:04.773336: step: 1440/530, loss: 0.011141682043671608
2023-01-21 11:44:05.972710: step: 1444/530, loss: 0.05917654186487198
2023-01-21 11:44:07.160379: step: 1448/530, loss: 0.015395546332001686
2023-01-21 11:44:08.349563: step: 1452/530, loss: 0.004696083255112171
2023-01-21 11:44:09.532124: step: 1456/530, loss: 0.005094051361083984
2023-01-21 11:44:10.687975: step: 1460/530, loss: 0.06597013771533966
2023-01-21 11:44:11.871563: step: 1464/530, loss: 0.007323646452277899
2023-01-21 11:44:13.007658: step: 1468/530, loss: 0.0031986236572265625
2023-01-21 11:44:14.117628: step: 1472/530, loss: 0.00027751922607421875
2023-01-21 11:44:15.288347: step: 1476/530, loss: 0.0037458420265465975
2023-01-21 11:44:16.448801: step: 1480/530, loss: 0.015252591110765934
2023-01-21 11:44:17.590110: step: 1484/530, loss: 0.08825837075710297
2023-01-21 11:44:18.750216: step: 1488/530, loss: 0.00542717007920146
2023-01-21 11:44:19.956038: step: 1492/530, loss: 0.004946994595229626
2023-01-21 11:44:21.149143: step: 1496/530, loss: 0.009145736694335938
2023-01-21 11:44:22.380317: step: 1500/530, loss: 0.014439105987548828
2023-01-21 11:44:23.537593: step: 1504/530, loss: 0.027216052636504173
2023-01-21 11:44:24.745510: step: 1508/530, loss: 0.0015636443858966231
2023-01-21 11:44:25.943862: step: 1512/530, loss: 0.0009281158563680947
2023-01-21 11:44:27.109996: step: 1516/530, loss: 0.012662316672503948
2023-01-21 11:44:28.295216: step: 1520/530, loss: 0.0018008232582360506
2023-01-21 11:44:29.474518: step: 1524/530, loss: 0.008422087877988815
2023-01-21 11:44:30.650043: step: 1528/530, loss: 0.004255390260368586
2023-01-21 11:44:31.812954: step: 1532/530, loss: 0.0756072998046875
2023-01-21 11:44:33.069336: step: 1536/530, loss: 0.00725059537217021
2023-01-21 11:44:34.227948: step: 1540/530, loss: 0.043248940259218216
2023-01-21 11:44:35.435266: step: 1544/530, loss: 0.008237838745117188
2023-01-21 11:44:36.617401: step: 1548/530, loss: 0.058585021644830704
2023-01-21 11:44:37.842887: step: 1552/530, loss: 0.003091430990025401
2023-01-21 11:44:39.053113: step: 1556/530, loss: 0.013186454772949219
2023-01-21 11:44:40.218783: step: 1560/530, loss: 0.0006245136610232294
2023-01-21 11:44:41.369315: step: 1564/530, loss: 0.2169443666934967
2023-01-21 11:44:42.599252: step: 1568/530, loss: 0.003769779345020652
2023-01-21 11:44:43.786207: step: 1572/530, loss: 0.06667595356702805
2023-01-21 11:44:44.963324: step: 1576/530, loss: 0.0017553330399096012
2023-01-21 11:44:46.141859: step: 1580/530, loss: 0.0017334461444988847
2023-01-21 11:44:47.267817: step: 1584/530, loss: 0.00016732215590309352
2023-01-21 11:44:48.434000: step: 1588/530, loss: 0.005676889326423407
2023-01-21 11:44:49.641488: step: 1592/530, loss: 0.007348823361098766
2023-01-21 11:44:50.794237: step: 1596/530, loss: 0.004650783725082874
2023-01-21 11:44:51.982666: step: 1600/530, loss: 0.0018041610019281507
2023-01-21 11:44:53.142159: step: 1604/530, loss: 0.0005546570173464715
2023-01-21 11:44:54.308399: step: 1608/530, loss: 0.04350147396326065
2023-01-21 11:44:55.529179: step: 1612/530, loss: 0.07148732990026474
2023-01-21 11:44:56.709179: step: 1616/530, loss: 0.009390450082719326
2023-01-21 11:44:57.859760: step: 1620/530, loss: 0.008351897820830345
2023-01-21 11:44:59.006073: step: 1624/530, loss: 0.03175945207476616
2023-01-21 11:45:00.208551: step: 1628/530, loss: 0.006941413506865501
2023-01-21 11:45:01.384436: step: 1632/530, loss: 0.00262966169975698
2023-01-21 11:45:02.553627: step: 1636/530, loss: 0.05688037723302841
2023-01-21 11:45:03.736412: step: 1640/530, loss: 0.011173725128173828
2023-01-21 11:45:04.961809: step: 1644/530, loss: 0.021231651306152344
2023-01-21 11:45:06.158119: step: 1648/530, loss: 0.03823218494653702
2023-01-21 11:45:07.305714: step: 1652/530, loss: 0.14542102813720703
2023-01-21 11:45:08.470631: step: 1656/530, loss: 0.019134044647216797
2023-01-21 11:45:09.695525: step: 1660/530, loss: 0.048342134803533554
2023-01-21 11:45:10.845441: step: 1664/530, loss: 0.0018748283619061112
2023-01-21 11:45:12.038214: step: 1668/530, loss: 0.004034996498376131
2023-01-21 11:45:13.174483: step: 1672/530, loss: 0.009898758493363857
2023-01-21 11:45:14.332629: step: 1676/530, loss: 0.011515664868056774
2023-01-21 11:45:15.521913: step: 1680/530, loss: 0.020786762237548828
2023-01-21 11:45:16.683132: step: 1684/530, loss: 0.0028880122117698193
2023-01-21 11:45:17.856233: step: 1688/530, loss: 0.07844944298267365
2023-01-21 11:45:19.050171: step: 1692/530, loss: 0.0007944107055664062
2023-01-21 11:45:20.249216: step: 1696/530, loss: 0.0032321931794285774
2023-01-21 11:45:21.453549: step: 1700/530, loss: 0.042591288685798645
2023-01-21 11:45:22.639883: step: 1704/530, loss: 0.006742668338119984
2023-01-21 11:45:23.817443: step: 1708/530, loss: 0.017470741644501686
2023-01-21 11:45:24.987443: step: 1712/530, loss: 0.047254037111997604
2023-01-21 11:45:26.157812: step: 1716/530, loss: 0.0626431480050087
2023-01-21 11:45:27.371584: step: 1720/530, loss: 0.022672070190310478
2023-01-21 11:45:28.582186: step: 1724/530, loss: 0.0005521774874068797
2023-01-21 11:45:29.767096: step: 1728/530, loss: 0.05224495008587837
2023-01-21 11:45:30.961037: step: 1732/530, loss: 0.01851348951458931
2023-01-21 11:45:32.142896: step: 1736/530, loss: 0.00036687852116301656
2023-01-21 11:45:33.317484: step: 1740/530, loss: 1.8119812921213452e-06
2023-01-21 11:45:34.467459: step: 1744/530, loss: 0.019431257620453835
2023-01-21 11:45:35.608871: step: 1748/530, loss: 0.0014821053482592106
2023-01-21 11:45:36.754263: step: 1752/530, loss: 0.04274740070104599
2023-01-21 11:45:37.879260: step: 1756/530, loss: 8.673667616676539e-05
2023-01-21 11:45:39.062786: step: 1760/530, loss: 0.010945415124297142
2023-01-21 11:45:40.236548: step: 1764/530, loss: 0.02131347730755806
2023-01-21 11:45:41.427859: step: 1768/530, loss: 0.07749070972204208
2023-01-21 11:45:42.646095: step: 1772/530, loss: 0.04401283338665962
2023-01-21 11:45:43.862344: step: 1776/530, loss: 0.0020021439995616674
2023-01-21 11:45:45.064685: step: 1780/530, loss: 0.07927074283361435
2023-01-21 11:45:46.225668: step: 1784/530, loss: 0.04289231449365616
2023-01-21 11:45:47.413108: step: 1788/530, loss: 9.603500075172633e-05
2023-01-21 11:45:48.568074: step: 1792/530, loss: 0.00315513601526618
2023-01-21 11:45:49.747321: step: 1796/530, loss: 0.01003656443208456
2023-01-21 11:45:50.898585: step: 1800/530, loss: 0.0033452988136559725
2023-01-21 11:45:52.081996: step: 1804/530, loss: 0.026613807305693626
2023-01-21 11:45:53.255462: step: 1808/530, loss: 0.006705951876938343
2023-01-21 11:45:54.405067: step: 1812/530, loss: 0.0038832426071166992
2023-01-21 11:45:55.568915: step: 1816/530, loss: 0.0028166770935058594
2023-01-21 11:45:56.743388: step: 1820/530, loss: 0.004704857245087624
2023-01-21 11:45:57.961763: step: 1824/530, loss: 0.2028055191040039
2023-01-21 11:45:59.121080: step: 1828/530, loss: 0.0028890608809888363
2023-01-21 11:46:00.300863: step: 1832/530, loss: 0.02939453162252903
2023-01-21 11:46:01.478701: step: 1836/530, loss: 0.004063406493514776
2023-01-21 11:46:02.636111: step: 1840/530, loss: 0.0002134323149221018
2023-01-21 11:46:03.799202: step: 1844/530, loss: 0.012526988983154297
2023-01-21 11:46:04.953503: step: 1848/530, loss: 0.00046472548274323344
2023-01-21 11:46:06.108210: step: 1852/530, loss: 0.035840511322021484
2023-01-21 11:46:07.302243: step: 1856/530, loss: 0.03174581751227379
2023-01-21 11:46:08.479565: step: 1860/530, loss: 0.005585860926657915
2023-01-21 11:46:09.606039: step: 1864/530, loss: 0.056595515459775925
2023-01-21 11:46:10.785864: step: 1868/530, loss: 0.00035982130793854594
2023-01-21 11:46:11.962048: step: 1872/530, loss: 0.02503204345703125
2023-01-21 11:46:13.177780: step: 1876/530, loss: 0.0021556855645030737
2023-01-21 11:46:14.348642: step: 1880/530, loss: 0.047197818756103516
2023-01-21 11:46:15.573261: step: 1884/530, loss: 0.044970132410526276
2023-01-21 11:46:16.768077: step: 1888/530, loss: 0.0019651411566883326
2023-01-21 11:46:17.959175: step: 1892/530, loss: 0.0014049530727788806
2023-01-21 11:46:19.102029: step: 1896/530, loss: 0.007244301028549671
2023-01-21 11:46:20.246245: step: 1900/530, loss: 0.009137631393969059
2023-01-21 11:46:21.388941: step: 1904/530, loss: 0.010827827267348766
2023-01-21 11:46:22.546498: step: 1908/530, loss: 0.03342094644904137
2023-01-21 11:46:23.701265: step: 1912/530, loss: 0.021536540240049362
2023-01-21 11:46:24.858944: step: 1916/530, loss: 0.0064296722412109375
2023-01-21 11:46:26.031646: step: 1920/530, loss: 0.000888443028088659
2023-01-21 11:46:27.242616: step: 1924/530, loss: 0.2318347990512848
2023-01-21 11:46:28.432444: step: 1928/530, loss: 0.3979606330394745
2023-01-21 11:46:29.625044: step: 1932/530, loss: 0.011769676581025124
2023-01-21 11:46:30.799947: step: 1936/530, loss: 0.06081228330731392
2023-01-21 11:46:31.996841: step: 1940/530, loss: 0.00014829635620117188
2023-01-21 11:46:33.184979: step: 1944/530, loss: 0.09364471584558487
2023-01-21 11:46:34.377095: step: 1948/530, loss: 0.003618431044742465
2023-01-21 11:46:35.561737: step: 1952/530, loss: 0.0012670516734942794
2023-01-21 11:46:36.724295: step: 1956/530, loss: 0.007540226448327303
2023-01-21 11:46:37.934184: step: 1960/530, loss: 0.08635301142930984
2023-01-21 11:46:39.078073: step: 1964/530, loss: 0.00147247314453125
2023-01-21 11:46:40.251002: step: 1968/530, loss: 0.05287675932049751
2023-01-21 11:46:41.426783: step: 1972/530, loss: 0.012066555209457874
2023-01-21 11:46:42.600168: step: 1976/530, loss: 0.6425977349281311
2023-01-21 11:46:43.779873: step: 1980/530, loss: 0.018410682678222656
2023-01-21 11:46:44.941154: step: 1984/530, loss: 0.008228874765336514
2023-01-21 11:46:46.140382: step: 1988/530, loss: 0.01911945454776287
2023-01-21 11:46:47.371780: step: 1992/530, loss: 0.013846587389707565
2023-01-21 11:46:48.535657: step: 1996/530, loss: 0.004326343536376953
2023-01-21 11:46:49.725929: step: 2000/530, loss: 0.03020191192626953
2023-01-21 11:46:50.879624: step: 2004/530, loss: 0.011449813842773438
2023-01-21 11:46:52.069881: step: 2008/530, loss: 0.010785293765366077
2023-01-21 11:46:53.251526: step: 2012/530, loss: 0.0035800933837890625
2023-01-21 11:46:54.488221: step: 2016/530, loss: 0.0015200615162029862
2023-01-21 11:46:55.660706: step: 2020/530, loss: 0.1085285171866417
2023-01-21 11:46:56.840473: step: 2024/530, loss: 0.06195516511797905
2023-01-21 11:46:58.007712: step: 2028/530, loss: 0.0003504753112792969
2023-01-21 11:46:59.213479: step: 2032/530, loss: 0.03095712512731552
2023-01-21 11:47:00.417611: step: 2036/530, loss: 0.6720864772796631
2023-01-21 11:47:01.616501: step: 2040/530, loss: 0.006118678953498602
2023-01-21 11:47:02.784353: step: 2044/530, loss: 0.0020154984667897224
2023-01-21 11:47:03.995945: step: 2048/530, loss: 0.007496452424675226
2023-01-21 11:47:05.196168: step: 2052/530, loss: 0.005424309056252241
2023-01-21 11:47:06.404599: step: 2056/530, loss: 0.0023258209694176912
2023-01-21 11:47:07.573068: step: 2060/530, loss: 0.0790325179696083
2023-01-21 11:47:08.740546: step: 2064/530, loss: 0.018455268815159798
2023-01-21 11:47:09.889414: step: 2068/530, loss: 0.01391830574721098
2023-01-21 11:47:11.050666: step: 2072/530, loss: 0.0005587577470578253
2023-01-21 11:47:12.235276: step: 2076/530, loss: 0.006535434629768133
2023-01-21 11:47:13.385927: step: 2080/530, loss: 0.004719066433608532
2023-01-21 11:47:14.612927: step: 2084/530, loss: 0.005223512649536133
2023-01-21 11:47:15.804040: step: 2088/530, loss: 0.05034293979406357
2023-01-21 11:47:16.952489: step: 2092/530, loss: 0.06583500653505325
2023-01-21 11:47:18.108842: step: 2096/530, loss: 0.5655586123466492
2023-01-21 11:47:19.397966: step: 2100/530, loss: 0.010055827908217907
2023-01-21 11:47:20.574758: step: 2104/530, loss: 0.06341762840747833
2023-01-21 11:47:21.743830: step: 2108/530, loss: 0.011020947247743607
2023-01-21 11:47:22.886623: step: 2112/530, loss: 0.016041899099946022
2023-01-21 11:47:24.038120: step: 2116/530, loss: 0.03329448774456978
2023-01-21 11:47:25.209251: step: 2120/530, loss: 0.013577270321547985
==================================================
Loss: 0.046
--------------------
Dev: {'event': {'p': 0.6067297581493165, 'r': 0.7683089214380826, 'f1': 0.6780258519388953}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6593252108716027, 'r': 0.8090856814261069, 'f1': 0.7265685515104571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5444444444444444, 'r': 0.9074074074074074, 'f1': 0.6805555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.64, 'r': 0.5079365079365079, 'f1': 0.5663716814159292}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.4222222222222222, 'r': 0.5277777777777778, 'f1': 0.46913580246913583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:48:09.039554: step: 4/530, loss: 0.08731546252965927
2023-01-21 11:48:10.235212: step: 8/530, loss: 0.003211593721061945
2023-01-21 11:48:11.384286: step: 12/530, loss: 0.004882622044533491
2023-01-21 11:48:12.548168: step: 16/530, loss: 0.01626458205282688
2023-01-21 11:48:13.703313: step: 20/530, loss: 0.029093457385897636
2023-01-21 11:48:14.879876: step: 24/530, loss: 0.002319574588909745
2023-01-21 11:48:16.030001: step: 28/530, loss: 0.0018962860340252519
2023-01-21 11:48:17.211044: step: 32/530, loss: 0.06318245083093643
2023-01-21 11:48:18.455067: step: 36/530, loss: 0.011015892028808594
2023-01-21 11:48:19.644718: step: 40/530, loss: 0.012590408325195312
2023-01-21 11:48:20.833895: step: 44/530, loss: 0.0428735725581646
2023-01-21 11:48:22.019080: step: 48/530, loss: 0.00112323765642941
2023-01-21 11:48:23.176419: step: 52/530, loss: 0.0013307571643963456
2023-01-21 11:48:24.357085: step: 56/530, loss: 0.0027105333283543587
2023-01-21 11:48:25.538195: step: 60/530, loss: 0.013242721557617188
2023-01-21 11:48:26.725613: step: 64/530, loss: 0.0004644870641641319
2023-01-21 11:48:27.894353: step: 68/530, loss: 0.03787526860833168
2023-01-21 11:48:29.080892: step: 72/530, loss: 0.02538614347577095
2023-01-21 11:48:30.241990: step: 76/530, loss: 0.0003286361461505294
2023-01-21 11:48:31.442503: step: 80/530, loss: 0.05097828060388565
2023-01-21 11:48:32.663758: step: 84/530, loss: 0.021771525964140892
2023-01-21 11:48:33.832559: step: 88/530, loss: 0.009287453256547451
2023-01-21 11:48:35.004706: step: 92/530, loss: 0.005253029055893421
2023-01-21 11:48:36.204301: step: 96/530, loss: 0.0002498626708984375
2023-01-21 11:48:37.367525: step: 100/530, loss: 0.013746262528002262
2023-01-21 11:48:38.552512: step: 104/530, loss: 0.03593464195728302
2023-01-21 11:48:39.713624: step: 108/530, loss: 0.0006011963123455644
2023-01-21 11:48:40.886526: step: 112/530, loss: 0.030145931988954544
2023-01-21 11:48:42.078647: step: 116/530, loss: 0.017331600189208984
2023-01-21 11:48:43.267995: step: 120/530, loss: 0.05127163231372833
2023-01-21 11:48:44.491403: step: 124/530, loss: 0.018137622624635696
2023-01-21 11:48:45.671854: step: 128/530, loss: 0.0030530933290719986
2023-01-21 11:48:46.866052: step: 132/530, loss: 0.019689178094267845
2023-01-21 11:48:48.044207: step: 136/530, loss: 3.356933666509576e-05
2023-01-21 11:48:49.273052: step: 140/530, loss: 0.1989917755126953
2023-01-21 11:48:50.456003: step: 144/530, loss: 0.002773189451545477
2023-01-21 11:48:51.600613: step: 148/530, loss: 0.0034418106079101562
2023-01-21 11:48:52.801619: step: 152/530, loss: 0.03624439612030983
2023-01-21 11:48:53.974244: step: 156/530, loss: 0.009095477871596813
2023-01-21 11:48:55.150673: step: 160/530, loss: 0.0038116455543786287
2023-01-21 11:48:56.309292: step: 164/530, loss: 0.08015841990709305
2023-01-21 11:48:57.494645: step: 168/530, loss: 5.254745701677166e-05
2023-01-21 11:48:58.657431: step: 172/530, loss: 0.0006334304925985634
2023-01-21 11:48:59.823184: step: 176/530, loss: 0.00020904542179778218
2023-01-21 11:49:01.000178: step: 180/530, loss: 0.0017430305015295744
2023-01-21 11:49:02.207039: step: 184/530, loss: 0.02249755896627903
2023-01-21 11:49:03.379004: step: 188/530, loss: 4.19616708313697e-06
2023-01-21 11:49:04.579926: step: 192/530, loss: 0.07040786743164062
2023-01-21 11:49:05.796613: step: 196/530, loss: 2.8133392333984375e-05
2023-01-21 11:49:06.959631: step: 200/530, loss: 0.022907830774784088
2023-01-21 11:49:08.096238: step: 204/530, loss: 0.02579517476260662
2023-01-21 11:49:09.286794: step: 208/530, loss: 9.250640869140625e-05
2023-01-21 11:49:10.462717: step: 212/530, loss: 0.0026067732833325863
2023-01-21 11:49:11.635584: step: 216/530, loss: 0.002763843396678567
2023-01-21 11:49:12.844528: step: 220/530, loss: 0.0003650665166787803
2023-01-21 11:49:14.004097: step: 224/530, loss: 0.00014553070650435984
2023-01-21 11:49:15.205745: step: 228/530, loss: 0.44648706912994385
2023-01-21 11:49:16.435983: step: 232/530, loss: 0.010247325524687767
2023-01-21 11:49:17.649687: step: 236/530, loss: 0.02717571146786213
2023-01-21 11:49:18.850753: step: 240/530, loss: 0.045014671981334686
2023-01-21 11:49:20.017003: step: 244/530, loss: 0.01828632317483425
2023-01-21 11:49:21.200914: step: 248/530, loss: 0.019773244857788086
2023-01-21 11:49:22.405100: step: 252/530, loss: 0.0400753989815712
2023-01-21 11:49:23.589290: step: 256/530, loss: 0.0039421082474291325
2023-01-21 11:49:24.777995: step: 260/530, loss: 0.000270843505859375
2023-01-21 11:49:25.950621: step: 264/530, loss: 0.0023492814507335424
2023-01-21 11:49:27.167797: step: 268/530, loss: 0.0022143363021314144
2023-01-21 11:49:28.306348: step: 272/530, loss: 0.012600421905517578
2023-01-21 11:49:29.503058: step: 276/530, loss: 0.007098579779267311
2023-01-21 11:49:30.693287: step: 280/530, loss: 0.029225779697299004
2023-01-21 11:49:31.895645: step: 284/530, loss: 0.014193153008818626
2023-01-21 11:49:33.031545: step: 288/530, loss: 0.006578278727829456
2023-01-21 11:49:34.268702: step: 292/530, loss: 0.024323465302586555
2023-01-21 11:49:35.468183: step: 296/530, loss: 0.010714054107666016
2023-01-21 11:49:36.644116: step: 300/530, loss: 0.0016795634292066097
2023-01-21 11:49:37.821945: step: 304/530, loss: 0.007739448919892311
2023-01-21 11:49:39.045514: step: 308/530, loss: 0.03632774204015732
2023-01-21 11:49:40.278940: step: 312/530, loss: 0.07028522342443466
2023-01-21 11:49:41.464238: step: 316/530, loss: 0.01283121109008789
2023-01-21 11:49:42.625355: step: 320/530, loss: 1.7976761228055693e-05
2023-01-21 11:49:43.799695: step: 324/530, loss: 0.005475426092743874
2023-01-21 11:49:44.981513: step: 328/530, loss: 0.001795101212337613
2023-01-21 11:49:46.171132: step: 332/530, loss: 0.05574951320886612
2023-01-21 11:49:47.329272: step: 336/530, loss: 0.0024168016389012337
2023-01-21 11:49:48.463569: step: 340/530, loss: 0.0015208721160888672
2023-01-21 11:49:49.641846: step: 344/530, loss: 0.018105316907167435
2023-01-21 11:49:50.893355: step: 348/530, loss: 0.022140122950077057
2023-01-21 11:49:52.054056: step: 352/530, loss: 0.00022935867309570312
2023-01-21 11:49:53.286332: step: 356/530, loss: 0.010883904062211514
2023-01-21 11:49:54.433033: step: 360/530, loss: 0.0033596036955714226
2023-01-21 11:49:55.578960: step: 364/530, loss: 0.0018317699432373047
2023-01-21 11:49:56.765342: step: 368/530, loss: 0.00045940876589156687
2023-01-21 11:49:57.944643: step: 372/530, loss: 0.025650693103671074
2023-01-21 11:49:59.075388: step: 376/530, loss: 0.0007993221515789628
2023-01-21 11:50:00.233379: step: 380/530, loss: 0.0006184577941894531
2023-01-21 11:50:01.416053: step: 384/530, loss: 0.04763927683234215
2023-01-21 11:50:02.624181: step: 388/530, loss: 0.020582865923643112
2023-01-21 11:50:03.798530: step: 392/530, loss: 0.014975547790527344
2023-01-21 11:50:04.975900: step: 396/530, loss: 0.007151699159294367
2023-01-21 11:50:06.166673: step: 400/530, loss: 0.03446569666266441
2023-01-21 11:50:07.334998: step: 404/530, loss: 0.00044422148494049907
2023-01-21 11:50:08.528062: step: 408/530, loss: 0.01243667583912611
2023-01-21 11:50:09.690822: step: 412/530, loss: 0.004374218173325062
2023-01-21 11:50:10.882633: step: 416/530, loss: 0.04748735576868057
2023-01-21 11:50:12.087591: step: 420/530, loss: 0.004000854678452015
2023-01-21 11:50:13.275891: step: 424/530, loss: 0.08920669555664062
2023-01-21 11:50:14.439144: step: 428/530, loss: 0.012965393252670765
2023-01-21 11:50:15.639118: step: 432/530, loss: 0.002680206438526511
2023-01-21 11:50:16.847581: step: 436/530, loss: 0.0006181717035360634
2023-01-21 11:50:18.020333: step: 440/530, loss: 0.00045413972111418843
2023-01-21 11:50:19.163652: step: 444/530, loss: 0.018158435821533203
2023-01-21 11:50:20.336537: step: 448/530, loss: 0.011905098333954811
2023-01-21 11:50:21.507605: step: 452/530, loss: 0.05325489118695259
2023-01-21 11:50:22.696925: step: 456/530, loss: 0.0315457358956337
2023-01-21 11:50:23.887971: step: 460/530, loss: 0.012611865997314453
2023-01-21 11:50:25.071523: step: 464/530, loss: 0.05681488662958145
2023-01-21 11:50:26.196587: step: 468/530, loss: 0.00366554269567132
2023-01-21 11:50:27.390351: step: 472/530, loss: 0.04110336676239967
2023-01-21 11:50:28.544097: step: 476/530, loss: 0.04525642469525337
2023-01-21 11:50:29.742043: step: 480/530, loss: 0.02527942694723606
2023-01-21 11:50:30.883789: step: 484/530, loss: 0.010525322519242764
2023-01-21 11:50:32.070946: step: 488/530, loss: 0.0024753091856837273
2023-01-21 11:50:33.249730: step: 492/530, loss: 0.04845710098743439
2023-01-21 11:50:34.474775: step: 496/530, loss: 0.010241317562758923
2023-01-21 11:50:35.655585: step: 500/530, loss: 0.001226663589477539
2023-01-21 11:50:36.844565: step: 504/530, loss: 0.0040802001021802425
2023-01-21 11:50:38.012236: step: 508/530, loss: 0.023234035819768906
2023-01-21 11:50:39.220329: step: 512/530, loss: 0.0009370446787215769
2023-01-21 11:50:40.406373: step: 516/530, loss: 0.015886306762695312
2023-01-21 11:50:41.548559: step: 520/530, loss: 2.2792815798311494e-05
2023-01-21 11:50:42.748948: step: 524/530, loss: 0.00012149810208939016
2023-01-21 11:50:43.916569: step: 528/530, loss: 0.0004351377720013261
2023-01-21 11:50:45.090414: step: 532/530, loss: 0.004988384433090687
2023-01-21 11:50:46.261465: step: 536/530, loss: 0.009182549081742764
2023-01-21 11:50:47.482952: step: 540/530, loss: 0.006745719816535711
2023-01-21 11:50:48.673559: step: 544/530, loss: 0.00202102679759264
2023-01-21 11:50:49.841198: step: 548/530, loss: 0.012156868353486061
2023-01-21 11:50:51.031136: step: 552/530, loss: 0.0357661247253418
2023-01-21 11:50:52.215363: step: 556/530, loss: 0.0006166935199871659
2023-01-21 11:50:53.383844: step: 560/530, loss: 0.0005097389221191406
2023-01-21 11:50:54.567655: step: 564/530, loss: 0.05349559709429741
2023-01-21 11:50:55.708009: step: 568/530, loss: 0.0304655060172081
2023-01-21 11:50:56.869222: step: 572/530, loss: 0.0022071837447583675
2023-01-21 11:50:58.053073: step: 576/530, loss: 0.0023141861893236637
2023-01-21 11:50:59.236058: step: 580/530, loss: 0.11306900531053543
2023-01-21 11:51:00.425824: step: 584/530, loss: 0.03875579684972763
2023-01-21 11:51:01.579668: step: 588/530, loss: 0.0009201050270348787
2023-01-21 11:51:02.804917: step: 592/530, loss: 0.07497863471508026
2023-01-21 11:51:03.989111: step: 596/530, loss: 0.02681136131286621
2023-01-21 11:51:05.160435: step: 600/530, loss: 0.0032764433417469263
2023-01-21 11:51:06.320886: step: 604/530, loss: 0.0005930424085818231
2023-01-21 11:51:07.484355: step: 608/530, loss: 0.010728120803833008
2023-01-21 11:51:08.637361: step: 612/530, loss: 0.03666238859295845
2023-01-21 11:51:09.812580: step: 616/530, loss: 0.0005529404152184725
2023-01-21 11:51:11.039350: step: 620/530, loss: 0.006221580319106579
2023-01-21 11:51:12.202879: step: 624/530, loss: 0.0005045890575274825
2023-01-21 11:51:13.384570: step: 628/530, loss: 0.009937859140336514
2023-01-21 11:51:14.589671: step: 632/530, loss: 0.022013474255800247
2023-01-21 11:51:15.775140: step: 636/530, loss: 0.03591747209429741
2023-01-21 11:51:16.963038: step: 640/530, loss: 0.001807880587875843
2023-01-21 11:51:18.135232: step: 644/530, loss: 0.0043773651123046875
2023-01-21 11:51:19.275068: step: 648/530, loss: 0.001859378768131137
2023-01-21 11:51:20.473879: step: 652/530, loss: 8.296967280330136e-06
2023-01-21 11:51:21.651971: step: 656/530, loss: 0.0009300231467932463
2023-01-21 11:51:22.816463: step: 660/530, loss: 0.0044667720794677734
2023-01-21 11:51:23.973494: step: 664/530, loss: 0.0028631212189793587
2023-01-21 11:51:25.159323: step: 668/530, loss: 0.003362464951351285
2023-01-21 11:51:26.318093: step: 672/530, loss: 0.0015993118286132812
2023-01-21 11:51:27.515054: step: 676/530, loss: 0.013833427801728249
2023-01-21 11:51:28.757298: step: 680/530, loss: 0.015366935171186924
2023-01-21 11:51:30.011711: step: 684/530, loss: 0.0005098343244753778
2023-01-21 11:51:31.266461: step: 688/530, loss: 0.030342651531100273
2023-01-21 11:51:32.438957: step: 692/530, loss: 0.0005279064062051475
2023-01-21 11:51:33.605492: step: 696/530, loss: 0.0009313583723269403
2023-01-21 11:51:34.760949: step: 700/530, loss: 0.05742311477661133
2023-01-21 11:51:35.979097: step: 704/530, loss: 0.0004680633719544858
2023-01-21 11:51:37.132805: step: 708/530, loss: 0.04494500532746315
2023-01-21 11:51:38.326517: step: 712/530, loss: 0.007596970070153475
2023-01-21 11:51:39.471094: step: 716/530, loss: 0.00036344528780318797
2023-01-21 11:51:40.652328: step: 720/530, loss: 0.020467663183808327
2023-01-21 11:51:41.855213: step: 724/530, loss: 0.001432228134945035
2023-01-21 11:51:43.069211: step: 728/530, loss: 0.031464576721191406
2023-01-21 11:51:44.256376: step: 732/530, loss: 0.0005321502685546875
2023-01-21 11:51:45.478145: step: 736/530, loss: 5.0163271225756034e-05
2023-01-21 11:51:46.669979: step: 740/530, loss: 0.0016584396362304688
2023-01-21 11:51:47.817178: step: 744/530, loss: 0.0016854286659508944
2023-01-21 11:51:49.018934: step: 748/530, loss: 0.0001693725644145161
2023-01-21 11:51:50.214112: step: 752/530, loss: 0.00048160552978515625
2023-01-21 11:51:51.383844: step: 756/530, loss: 0.03294429928064346
2023-01-21 11:51:52.563977: step: 760/530, loss: 0.008556365966796875
2023-01-21 11:51:53.747868: step: 764/530, loss: 0.008806896395981312
2023-01-21 11:51:54.940140: step: 768/530, loss: 0.00031452177790924907
2023-01-21 11:51:56.108368: step: 772/530, loss: 0.0009295940399169922
2023-01-21 11:51:57.260130: step: 776/530, loss: 0.0005523681757040322
2023-01-21 11:51:58.441076: step: 780/530, loss: 0.0008453846094198525
2023-01-21 11:51:59.620764: step: 784/530, loss: 2.784729076665826e-05
2023-01-21 11:52:00.871820: step: 788/530, loss: 0.0005505561712197959
2023-01-21 11:52:02.031321: step: 792/530, loss: 0.026918793097138405
2023-01-21 11:52:03.193171: step: 796/530, loss: 0.049049947410821915
2023-01-21 11:52:04.402769: step: 800/530, loss: 0.03280448913574219
2023-01-21 11:52:05.554393: step: 804/530, loss: 0.0008927464368753135
2023-01-21 11:52:06.728014: step: 808/530, loss: 0.08511290699243546
2023-01-21 11:52:07.884657: step: 812/530, loss: 0.014259815216064453
2023-01-21 11:52:09.142029: step: 816/530, loss: 5.110228061676025
2023-01-21 11:52:10.305702: step: 820/530, loss: 0.015688898041844368
2023-01-21 11:52:11.500589: step: 824/530, loss: 0.034385014325380325
2023-01-21 11:52:12.719692: step: 828/530, loss: 0.001645851181820035
2023-01-21 11:52:13.936876: step: 832/530, loss: 0.0894143134355545
2023-01-21 11:52:15.184505: step: 836/530, loss: 0.09483623504638672
2023-01-21 11:52:16.330038: step: 840/530, loss: 2.746581958490424e-05
2023-01-21 11:52:17.488119: step: 844/530, loss: 0.020100880414247513
2023-01-21 11:52:18.658245: step: 848/530, loss: 0.00029392243595793843
2023-01-21 11:52:19.864939: step: 852/530, loss: 0.005130100529640913
2023-01-21 11:52:21.048324: step: 856/530, loss: 0.0003288268926553428
2023-01-21 11:52:22.208954: step: 860/530, loss: 0.00045032502384856343
2023-01-21 11:52:23.439483: step: 864/530, loss: 0.0014226913917809725
2023-01-21 11:52:24.580925: step: 868/530, loss: 0.0004946053377352655
2023-01-21 11:52:25.754395: step: 872/530, loss: 0.03552541881799698
2023-01-21 11:52:26.944023: step: 876/530, loss: 0.022655868902802467
2023-01-21 11:52:28.105633: step: 880/530, loss: 0.03164510801434517
2023-01-21 11:52:29.274173: step: 884/530, loss: 0.004130268469452858
2023-01-21 11:52:30.439677: step: 888/530, loss: 0.03041095659136772
2023-01-21 11:52:31.595689: step: 892/530, loss: 0.0012725830310955644
2023-01-21 11:52:32.760161: step: 896/530, loss: 0.015390015207231045
2023-01-21 11:52:33.932978: step: 900/530, loss: 0.0036167146172374487
2023-01-21 11:52:35.097937: step: 904/530, loss: 0.0016943454975262284
2023-01-21 11:52:36.262551: step: 908/530, loss: 0.004737281706184149
2023-01-21 11:52:37.448869: step: 912/530, loss: 0.048510171473026276
2023-01-21 11:52:38.631789: step: 916/530, loss: 0.006301784422248602
2023-01-21 11:52:39.811820: step: 920/530, loss: 0.023771096020936966
2023-01-21 11:52:40.980550: step: 924/530, loss: 0.0030157091096043587
2023-01-21 11:52:42.156640: step: 928/530, loss: 0.005428886506706476
2023-01-21 11:52:43.346682: step: 932/530, loss: 0.0027680397033691406
2023-01-21 11:52:44.524768: step: 936/530, loss: 0.19505634903907776
2023-01-21 11:52:45.711134: step: 940/530, loss: 0.0029285431373864412
2023-01-21 11:52:46.853317: step: 944/530, loss: 0.0002811432059388608
2023-01-21 11:52:48.009140: step: 948/530, loss: 0.021420670673251152
2023-01-21 11:52:49.183922: step: 952/530, loss: 0.27518805861473083
2023-01-21 11:52:50.357362: step: 956/530, loss: 0.004327869508415461
2023-01-21 11:52:51.510816: step: 960/530, loss: 0.05240326002240181
2023-01-21 11:52:52.691950: step: 964/530, loss: 0.02823205105960369
2023-01-21 11:52:53.848298: step: 968/530, loss: 0.0302321445196867
2023-01-21 11:52:55.037656: step: 972/530, loss: 7.162094698287547e-05
2023-01-21 11:52:56.194668: step: 976/530, loss: 0.005374336615204811
2023-01-21 11:52:57.393373: step: 980/530, loss: 0.004407835192978382
2023-01-21 11:52:58.544668: step: 984/530, loss: 0.00928354263305664
2023-01-21 11:52:59.716229: step: 988/530, loss: 0.008812809363007545
2023-01-21 11:53:00.906857: step: 992/530, loss: 0.0013688087929040194
2023-01-21 11:53:02.085270: step: 996/530, loss: 0.008172322064638138
2023-01-21 11:53:03.241534: step: 1000/530, loss: 0.019528580829501152
2023-01-21 11:53:04.408041: step: 1004/530, loss: 0.06174096837639809
2023-01-21 11:53:05.595283: step: 1008/530, loss: 0.049163054674863815
2023-01-21 11:53:06.786951: step: 1012/530, loss: 0.04819812998175621
2023-01-21 11:53:07.955564: step: 1016/530, loss: 0.0008571624639444053
2023-01-21 11:53:09.142332: step: 1020/530, loss: 0.044623661786317825
2023-01-21 11:53:10.348736: step: 1024/530, loss: 0.03869228437542915
2023-01-21 11:53:11.494784: step: 1028/530, loss: 3.1137467885855585e-05
2023-01-21 11:53:12.698612: step: 1032/530, loss: 0.0003068924124818295
2023-01-21 11:53:13.838097: step: 1036/530, loss: 0.16441403329372406
2023-01-21 11:53:14.995199: step: 1040/530, loss: 0.01044769398868084
2023-01-21 11:53:16.165235: step: 1044/530, loss: 0.027341080829501152
2023-01-21 11:53:17.303415: step: 1048/530, loss: 9.140968177234754e-05
2023-01-21 11:53:18.476706: step: 1052/530, loss: 9.956360008800402e-05
2023-01-21 11:53:19.649616: step: 1056/530, loss: 0.008964228443801403
2023-01-21 11:53:20.801561: step: 1060/530, loss: 0.005856752395629883
2023-01-21 11:53:21.979095: step: 1064/530, loss: 0.006365204229950905
2023-01-21 11:53:23.144065: step: 1068/530, loss: 0.05787096172571182
2023-01-21 11:53:24.292628: step: 1072/530, loss: 0.02026653289794922
2023-01-21 11:53:25.477144: step: 1076/530, loss: 0.002571678254753351
2023-01-21 11:53:26.659898: step: 1080/530, loss: 0.019018160179257393
2023-01-21 11:53:27.807590: step: 1084/530, loss: 0.049323271960020065
2023-01-21 11:53:29.109064: step: 1088/530, loss: 0.010681820102036
2023-01-21 11:53:30.258810: step: 1092/530, loss: 0.1152862161397934
2023-01-21 11:53:31.495374: step: 1096/530, loss: 0.0026620866265147924
2023-01-21 11:53:32.682627: step: 1100/530, loss: 0.0006658554193563759
2023-01-21 11:53:33.856236: step: 1104/530, loss: 0.024102210998535156
2023-01-21 11:53:35.023623: step: 1108/530, loss: 0.000375127827282995
2023-01-21 11:53:36.198124: step: 1112/530, loss: 0.0016592026222497225
2023-01-21 11:53:37.357335: step: 1116/530, loss: 0.01584625244140625
2023-01-21 11:53:38.469474: step: 1120/530, loss: 0.0037805556785315275
2023-01-21 11:53:39.657434: step: 1124/530, loss: 0.0397428534924984
2023-01-21 11:53:40.814943: step: 1128/530, loss: 0.03263077884912491
2023-01-21 11:53:41.980814: step: 1132/530, loss: 0.007448005955666304
2023-01-21 11:53:43.150154: step: 1136/530, loss: 0.0503830686211586
2023-01-21 11:53:44.339847: step: 1140/530, loss: 0.0007847309461794794
2023-01-21 11:53:45.520104: step: 1144/530, loss: 0.021022368222475052
2023-01-21 11:53:46.767738: step: 1148/530, loss: 0.018467046320438385
2023-01-21 11:53:47.952545: step: 1152/530, loss: 1.409002661705017
2023-01-21 11:53:49.158680: step: 1156/530, loss: 0.001998090883716941
2023-01-21 11:53:50.294269: step: 1160/530, loss: 0.0002550125354900956
2023-01-21 11:53:51.502695: step: 1164/530, loss: 0.0013589859008789062
2023-01-21 11:53:52.712341: step: 1168/530, loss: 0.0034727095626294613
2023-01-21 11:53:53.879306: step: 1172/530, loss: 0.016455460339784622
2023-01-21 11:53:55.067977: step: 1176/530, loss: 0.016565322875976562
2023-01-21 11:53:56.211343: step: 1180/530, loss: 0.000928688095882535
2023-01-21 11:53:57.386232: step: 1184/530, loss: 0.03171367570757866
2023-01-21 11:53:58.585411: step: 1188/530, loss: 0.0445556640625
2023-01-21 11:53:59.751595: step: 1192/530, loss: 0.049439430236816406
2023-01-21 11:54:00.898631: step: 1196/530, loss: 0.045542143285274506
2023-01-21 11:54:02.069573: step: 1200/530, loss: 0.000340366386808455
2023-01-21 11:54:03.241589: step: 1204/530, loss: 0.0007524490356445312
2023-01-21 11:54:04.429581: step: 1208/530, loss: 0.9727697372436523
2023-01-21 11:54:05.635293: step: 1212/530, loss: 0.0008098125690594316
2023-01-21 11:54:06.815699: step: 1216/530, loss: 0.018622493371367455
2023-01-21 11:54:07.998286: step: 1220/530, loss: 0.002280807588249445
2023-01-21 11:54:09.177994: step: 1224/530, loss: 0.0019449234241619706
2023-01-21 11:54:10.321567: step: 1228/530, loss: 0.026145650073885918
2023-01-21 11:54:11.489930: step: 1232/530, loss: 0.004445314407348633
2023-01-21 11:54:12.703682: step: 1236/530, loss: 0.00715904263779521
2023-01-21 11:54:13.858344: step: 1240/530, loss: 0.02207021601498127
2023-01-21 11:54:15.026444: step: 1244/530, loss: 0.002135658171027899
2023-01-21 11:54:16.195483: step: 1248/530, loss: 0.26870614290237427
2023-01-21 11:54:17.407245: step: 1252/530, loss: 0.0390925407409668
2023-01-21 11:54:18.567030: step: 1256/530, loss: 0.08327951282262802
2023-01-21 11:54:19.745519: step: 1260/530, loss: 0.03345184400677681
2023-01-21 11:54:20.929321: step: 1264/530, loss: 0.005735874176025391
2023-01-21 11:54:22.094960: step: 1268/530, loss: 0.024141598492860794
2023-01-21 11:54:23.242235: step: 1272/530, loss: 0.0002511978382244706
2023-01-21 11:54:24.437411: step: 1276/530, loss: 0.012088775634765625
2023-01-21 11:54:25.635326: step: 1280/530, loss: 0.007942485623061657
2023-01-21 11:54:26.831716: step: 1284/530, loss: 0.0340055488049984
2023-01-21 11:54:28.015143: step: 1288/530, loss: 0.013054942712187767
2023-01-21 11:54:29.268832: step: 1292/530, loss: 0.004992294125258923
2023-01-21 11:54:30.437391: step: 1296/530, loss: 0.011607075110077858
2023-01-21 11:54:31.607325: step: 1300/530, loss: 0.027545548975467682
2023-01-21 11:54:32.793262: step: 1304/530, loss: 0.10063318908214569
2023-01-21 11:54:33.983027: step: 1308/530, loss: 0.01221618615090847
2023-01-21 11:54:35.141355: step: 1312/530, loss: 0.00024127960205078125
2023-01-21 11:54:36.303718: step: 1316/530, loss: 0.06658754497766495
2023-01-21 11:54:37.482327: step: 1320/530, loss: 0.0036728859413415194
2023-01-21 11:54:38.605603: step: 1324/530, loss: 0.017569541931152344
2023-01-21 11:54:39.847176: step: 1328/530, loss: 0.000995635986328125
2023-01-21 11:54:41.069075: step: 1332/530, loss: 0.0017778397304937243
2023-01-21 11:54:42.303616: step: 1336/530, loss: 0.000975322793237865
2023-01-21 11:54:43.486429: step: 1340/530, loss: 0.03961505740880966
2023-01-21 11:54:44.727168: step: 1344/530, loss: 0.012908171862363815
2023-01-21 11:54:45.933584: step: 1348/530, loss: 0.002530860947445035
2023-01-21 11:54:47.056253: step: 1352/530, loss: 0.005012703128159046
2023-01-21 11:54:48.286960: step: 1356/530, loss: 0.00020532608323264867
2023-01-21 11:54:49.491413: step: 1360/530, loss: 1.602172778802924e-05
2023-01-21 11:54:50.705096: step: 1364/530, loss: 0.06287936866283417
2023-01-21 11:54:51.882793: step: 1368/530, loss: 0.0008691787952557206
2023-01-21 11:54:53.122987: step: 1372/530, loss: 0.0019065856467932463
2023-01-21 11:54:54.271161: step: 1376/530, loss: 0.0002633094845805317
2023-01-21 11:54:55.478746: step: 1380/530, loss: 0.0257142074406147
2023-01-21 11:54:56.689070: step: 1384/530, loss: 0.006311893463134766
2023-01-21 11:54:57.863697: step: 1388/530, loss: 0.0022490499541163445
2023-01-21 11:54:59.028369: step: 1392/530, loss: 0.04547720029950142
2023-01-21 11:55:00.216534: step: 1396/530, loss: 0.020011521875858307
2023-01-21 11:55:01.353272: step: 1400/530, loss: 0.004957866854965687
2023-01-21 11:55:02.545947: step: 1404/530, loss: 0.023298360407352448
2023-01-21 11:55:03.709162: step: 1408/530, loss: 0.042855359613895416
2023-01-21 11:55:04.883632: step: 1412/530, loss: 0.003172206925228238
2023-01-21 11:55:06.065446: step: 1416/530, loss: 0.002076101489365101
2023-01-21 11:55:07.242821: step: 1420/530, loss: 0.021920491009950638
2023-01-21 11:55:08.421145: step: 1424/530, loss: 5.3119660151423886e-05
2023-01-21 11:55:09.602696: step: 1428/530, loss: 0.011325454339385033
2023-01-21 11:55:10.757578: step: 1432/530, loss: 0.006413173861801624
2023-01-21 11:55:11.917620: step: 1436/530, loss: 0.004166030790656805
2023-01-21 11:55:13.073874: step: 1440/530, loss: 0.000537872314453125
2023-01-21 11:55:14.234994: step: 1444/530, loss: 0.00027441978454589844
2023-01-21 11:55:15.403131: step: 1448/530, loss: 0.0006131172413006425
2023-01-21 11:55:16.585289: step: 1452/530, loss: 0.01329431589692831
2023-01-21 11:55:17.778299: step: 1456/530, loss: 0.0172044038772583
2023-01-21 11:55:18.947363: step: 1460/530, loss: 0.042227938771247864
2023-01-21 11:55:20.133356: step: 1464/530, loss: 0.030699919909238815
2023-01-21 11:55:21.356172: step: 1468/530, loss: 4.301071021473035e-05
2023-01-21 11:55:22.502574: step: 1472/530, loss: 0.0022124291863292456
2023-01-21 11:55:23.683732: step: 1476/530, loss: 0.05648408085107803
2023-01-21 11:55:24.865688: step: 1480/530, loss: 0.0002058513491647318
2023-01-21 11:55:26.046177: step: 1484/530, loss: 0.07944860309362411
2023-01-21 11:55:27.211990: step: 1488/530, loss: 0.0008404732216149569
2023-01-21 11:55:28.381562: step: 1492/530, loss: 0.00016269684419967234
2023-01-21 11:55:29.544692: step: 1496/530, loss: 0.0008409500005654991
2023-01-21 11:55:30.720166: step: 1500/530, loss: 0.023110484704375267
2023-01-21 11:55:31.892015: step: 1504/530, loss: 0.049431610852479935
2023-01-21 11:55:33.109980: step: 1508/530, loss: 0.0046066283248364925
2023-01-21 11:55:34.254787: step: 1512/530, loss: 0.00780754117295146
2023-01-21 11:55:35.413309: step: 1516/530, loss: 0.03497086092829704
2023-01-21 11:55:36.564855: step: 1520/530, loss: 0.0018076419364660978
2023-01-21 11:55:37.723357: step: 1524/530, loss: 0.03642215579748154
2023-01-21 11:55:38.922858: step: 1528/530, loss: 0.04146786034107208
2023-01-21 11:55:40.098790: step: 1532/530, loss: 0.00039768218994140625
2023-01-21 11:55:41.385289: step: 1536/530, loss: 0.0009428501361981034
2023-01-21 11:55:42.605756: step: 1540/530, loss: 0.0026311874389648438
2023-01-21 11:55:43.787764: step: 1544/530, loss: 0.0003707885625772178
2023-01-21 11:55:44.932208: step: 1548/530, loss: 0.008408975787460804
2023-01-21 11:55:46.080407: step: 1552/530, loss: 0.10661526024341583
2023-01-21 11:55:47.281130: step: 1556/530, loss: 0.0005186080816201866
2023-01-21 11:55:48.468713: step: 1560/530, loss: 0.00997066404670477
2023-01-21 11:55:49.610589: step: 1564/530, loss: 0.00014500618271995336
2023-01-21 11:55:50.783687: step: 1568/530, loss: 0.07678823918104172
2023-01-21 11:55:51.950339: step: 1572/530, loss: 0.0006864547613076866
2023-01-21 11:55:53.107879: step: 1576/530, loss: 5.2070619858568534e-05
2023-01-21 11:55:54.295117: step: 1580/530, loss: 0.012794685550034046
2023-01-21 11:55:55.488443: step: 1584/530, loss: 0.01699066162109375
2023-01-21 11:55:56.678951: step: 1588/530, loss: 0.056519508361816406
2023-01-21 11:55:57.864319: step: 1592/530, loss: 0.029676057398319244
2023-01-21 11:55:59.012179: step: 1596/530, loss: 0.002719879150390625
2023-01-21 11:56:00.168898: step: 1600/530, loss: 0.0036157132126390934
2023-01-21 11:56:01.333145: step: 1604/530, loss: 0.013831853866577148
2023-01-21 11:56:02.480022: step: 1608/530, loss: 0.009747696109116077
2023-01-21 11:56:03.642273: step: 1612/530, loss: 0.08169078826904297
2023-01-21 11:56:04.815697: step: 1616/530, loss: 0.012155246920883656
2023-01-21 11:56:05.993088: step: 1620/530, loss: 0.0034214023035019636
2023-01-21 11:56:07.158138: step: 1624/530, loss: 0.29299378395080566
2023-01-21 11:56:08.327788: step: 1628/530, loss: 0.046714067459106445
2023-01-21 11:56:09.499600: step: 1632/530, loss: 0.007000541780143976
2023-01-21 11:56:10.678056: step: 1636/530, loss: 0.01271047629415989
2023-01-21 11:56:11.876467: step: 1640/530, loss: 0.040493011474609375
2023-01-21 11:56:13.058968: step: 1644/530, loss: 0.0008849144214764237
2023-01-21 11:56:14.242423: step: 1648/530, loss: 0.0005269050598144531
2023-01-21 11:56:15.416521: step: 1652/530, loss: 0.030748462304472923
2023-01-21 11:56:16.586367: step: 1656/530, loss: 0.00012483597674872726
2023-01-21 11:56:17.747597: step: 1660/530, loss: 0.03260154649615288
2023-01-21 11:56:18.929443: step: 1664/530, loss: 0.00016431808762717992
2023-01-21 11:56:20.068630: step: 1668/530, loss: 0.04968414455652237
2023-01-21 11:56:21.241860: step: 1672/530, loss: 0.009979916736483574
2023-01-21 11:56:22.414352: step: 1676/530, loss: 0.0027227401733398438
2023-01-21 11:56:23.613083: step: 1680/530, loss: 0.02227640151977539
2023-01-21 11:56:24.813573: step: 1684/530, loss: 0.004439449869096279
2023-01-21 11:56:25.985730: step: 1688/530, loss: 0.0019729614723473787
2023-01-21 11:56:27.154615: step: 1692/530, loss: 0.0036115646362304688
2023-01-21 11:56:28.367832: step: 1696/530, loss: 0.0011323929065838456
2023-01-21 11:56:29.561421: step: 1700/530, loss: 0.0008643150213174522
2023-01-21 11:56:30.690276: step: 1704/530, loss: 0.0008229255327023566
2023-01-21 11:56:31.867985: step: 1708/530, loss: 0.020559310913085938
2023-01-21 11:56:33.059925: step: 1712/530, loss: 0.021995067596435547
2023-01-21 11:56:34.254988: step: 1716/530, loss: 0.004757118411362171
2023-01-21 11:56:35.417629: step: 1720/530, loss: 0.005992698483169079
2023-01-21 11:56:36.590911: step: 1724/530, loss: 0.014645003713667393
2023-01-21 11:56:37.766044: step: 1728/530, loss: 0.011148547753691673
2023-01-21 11:56:38.944838: step: 1732/530, loss: 0.09624643623828888
2023-01-21 11:56:40.109525: step: 1736/530, loss: 0.0002323150692973286
2023-01-21 11:56:41.298447: step: 1740/530, loss: 0.008537006564438343
2023-01-21 11:56:42.462655: step: 1744/530, loss: 0.005873298738151789
2023-01-21 11:56:43.637273: step: 1748/530, loss: 0.015085887163877487
2023-01-21 11:56:44.812555: step: 1752/530, loss: 0.015697669237852097
2023-01-21 11:56:45.982270: step: 1756/530, loss: 0.04855794832110405
2023-01-21 11:56:47.124403: step: 1760/530, loss: 0.01418523769825697
2023-01-21 11:56:48.323185: step: 1764/530, loss: 0.004877185914665461
2023-01-21 11:56:49.523150: step: 1768/530, loss: 0.002104091690853238
2023-01-21 11:56:50.748087: step: 1772/530, loss: 0.007519721984863281
2023-01-21 11:56:51.958479: step: 1776/530, loss: 0.0007884979131631553
2023-01-21 11:56:53.082206: step: 1780/530, loss: 0.055056486278772354
2023-01-21 11:56:54.257228: step: 1784/530, loss: 0.0006911277887411416
2023-01-21 11:56:55.439172: step: 1788/530, loss: 0.004710960201919079
2023-01-21 11:56:56.714108: step: 1792/530, loss: 0.0025168806314468384
2023-01-21 11:56:57.891426: step: 1796/530, loss: 0.0013077259063720703
2023-01-21 11:56:59.074768: step: 1800/530, loss: 0.0004760742303915322
2023-01-21 11:57:00.254611: step: 1804/530, loss: 0.0010419845348224044
2023-01-21 11:57:01.405272: step: 1808/530, loss: 0.0015901564620435238
2023-01-21 11:57:02.591526: step: 1812/530, loss: 0.0009578705066815019
2023-01-21 11:57:03.763403: step: 1816/530, loss: 0.05409584194421768
2023-01-21 11:57:04.913907: step: 1820/530, loss: 0.010852241888642311
2023-01-21 11:57:06.072769: step: 1824/530, loss: 0.04352989047765732
2023-01-21 11:57:07.266511: step: 1828/530, loss: 0.00035147665766999125
2023-01-21 11:57:08.451410: step: 1832/530, loss: 0.03391599655151367
2023-01-21 11:57:09.642258: step: 1836/530, loss: 0.011319829151034355
2023-01-21 11:57:10.825957: step: 1840/530, loss: 0.05328173562884331
2023-01-21 11:57:12.104419: step: 1844/530, loss: 0.014373970218002796
2023-01-21 11:57:13.312376: step: 1848/530, loss: 0.0025221826508641243
2023-01-21 11:57:14.502886: step: 1852/530, loss: 0.016671180725097656
2023-01-21 11:57:15.701866: step: 1856/530, loss: 0.0016723632579669356
2023-01-21 11:57:16.900008: step: 1860/530, loss: 0.009774875827133656
2023-01-21 11:57:18.088336: step: 1864/530, loss: 0.0005865097045898438
2023-01-21 11:57:19.242264: step: 1868/530, loss: 0.03930320590734482
2023-01-21 11:57:20.421744: step: 1872/530, loss: 0.015630245208740234
2023-01-21 11:57:21.629443: step: 1876/530, loss: 0.016068650409579277
2023-01-21 11:57:22.815597: step: 1880/530, loss: 0.019454479217529297
2023-01-21 11:57:23.967675: step: 1884/530, loss: 0.0010760307777673006
2023-01-21 11:57:25.152154: step: 1888/530, loss: 0.0010229110484942794
2023-01-21 11:57:26.373686: step: 1892/530, loss: 0.0022780895233154297
2023-01-21 11:57:27.579106: step: 1896/530, loss: 0.00028991702129133046
2023-01-21 11:57:28.755485: step: 1900/530, loss: 0.07015733420848846
2023-01-21 11:57:29.932345: step: 1904/530, loss: 0.014220619574189186
2023-01-21 11:57:31.098977: step: 1908/530, loss: 0.00106048583984375
2023-01-21 11:57:32.270189: step: 1912/530, loss: 0.0021484375465661287
2023-01-21 11:57:33.426392: step: 1916/530, loss: 0.02708902396261692
2023-01-21 11:57:34.563908: step: 1920/530, loss: 0.004189205355942249
2023-01-21 11:57:35.813346: step: 1924/530, loss: 0.007980250753462315
2023-01-21 11:57:37.034870: step: 1928/530, loss: 0.006542205810546875
2023-01-21 11:57:38.238074: step: 1932/530, loss: 0.06604842841625214
2023-01-21 11:57:39.379272: step: 1936/530, loss: 0.021529199555516243
2023-01-21 11:57:40.617364: step: 1940/530, loss: 0.005999374203383923
2023-01-21 11:57:41.857627: step: 1944/530, loss: 0.021640300750732422
2023-01-21 11:57:43.040902: step: 1948/530, loss: 0.0018211365677416325
2023-01-21 11:57:44.228438: step: 1952/530, loss: 0.05754471197724342
2023-01-21 11:57:45.400452: step: 1956/530, loss: 0.02467641979455948
2023-01-21 11:57:46.561219: step: 1960/530, loss: 0.009199715219438076
2023-01-21 11:57:47.718990: step: 1964/530, loss: 0.03348889201879501
2023-01-21 11:57:48.931121: step: 1968/530, loss: 0.003810358000919223
2023-01-21 11:57:50.107842: step: 1972/530, loss: 0.0021333694458007812
2023-01-21 11:57:51.269525: step: 1976/530, loss: 0.009641265496611595
2023-01-21 11:57:52.454812: step: 1980/530, loss: 0.15017947554588318
2023-01-21 11:57:53.629297: step: 1984/530, loss: 0.0017242431640625
2023-01-21 11:57:54.794574: step: 1988/530, loss: 0.0030120848678052425
2023-01-21 11:57:55.979280: step: 1992/530, loss: 6.542206392623484e-05
2023-01-21 11:57:57.180600: step: 1996/530, loss: 0.020133592188358307
2023-01-21 11:57:58.311023: step: 2000/530, loss: 0.024538516998291016
2023-01-21 11:57:59.476087: step: 2004/530, loss: 0.04491119459271431
2023-01-21 11:58:00.649990: step: 2008/530, loss: 0.00015878677368164062
2023-01-21 11:58:01.855844: step: 2012/530, loss: 0.06429443508386612
2023-01-21 11:58:03.070875: step: 2016/530, loss: 0.014173698611557484
2023-01-21 11:58:04.225325: step: 2020/530, loss: 0.0010260583367198706
2023-01-21 11:58:05.464446: step: 2024/530, loss: 0.003909301944077015
2023-01-21 11:58:06.675919: step: 2028/530, loss: 0.09355764091014862
2023-01-21 11:58:07.881115: step: 2032/530, loss: 0.08838023990392685
2023-01-21 11:58:09.041444: step: 2036/530, loss: 0.000682020210660994
2023-01-21 11:58:10.264282: step: 2040/530, loss: 0.010965347290039062
2023-01-21 11:58:11.445304: step: 2044/530, loss: 0.03920421749353409
2023-01-21 11:58:12.601390: step: 2048/530, loss: 0.00015046595945023
2023-01-21 11:58:13.748651: step: 2052/530, loss: 0.05347251892089844
2023-01-21 11:58:14.930636: step: 2056/530, loss: 0.003849220462143421
2023-01-21 11:58:16.101440: step: 2060/530, loss: 0.004295540042221546
2023-01-21 11:58:17.268468: step: 2064/530, loss: 0.00018529893714003265
2023-01-21 11:58:18.468941: step: 2068/530, loss: 0.05057726055383682
2023-01-21 11:58:19.637629: step: 2072/530, loss: 0.010421657003462315
2023-01-21 11:58:20.827282: step: 2076/530, loss: 0.027713680639863014
2023-01-21 11:58:21.995024: step: 2080/530, loss: 0.0021997452713549137
2023-01-21 11:58:23.253066: step: 2084/530, loss: 0.00946950912475586
2023-01-21 11:58:24.406069: step: 2088/530, loss: 0.042563535273075104
2023-01-21 11:58:25.580008: step: 2092/530, loss: 0.006267261225730181
2023-01-21 11:58:26.764028: step: 2096/530, loss: 0.02116994746029377
2023-01-21 11:58:27.928408: step: 2100/530, loss: 1.0490417707842425e-06
2023-01-21 11:58:29.067296: step: 2104/530, loss: 0.0016088008414953947
2023-01-21 11:58:30.255448: step: 2108/530, loss: 0.00010561943054199219
2023-01-21 11:58:31.465789: step: 2112/530, loss: 0.037711624056100845
2023-01-21 11:58:32.674832: step: 2116/530, loss: 0.0007719993591308594
2023-01-21 11:58:33.849317: step: 2120/530, loss: 0.009385490790009499
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6120507399577167, 'r': 0.7709720372836218, 'f1': 0.6823806717737184}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6701872299567931, 'r': 0.8027602070155262, 'f1': 0.7305075876504449}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.6041666666666666, 'r': 0.4603174603174603, 'f1': 0.5225225225225225}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4318181818181818, 'r': 0.5277777777777778, 'f1': 0.47500000000000003}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 11:59:16.848602: step: 4/530, loss: 3.5285952435515355e-06
2023-01-21 11:59:18.008731: step: 8/530, loss: 0.004494857974350452
2023-01-21 11:59:19.146079: step: 12/530, loss: 0.009712601080536842
2023-01-21 11:59:20.326807: step: 16/530, loss: 0.017217254266142845
2023-01-21 11:59:21.500329: step: 20/530, loss: 0.017223168164491653
2023-01-21 11:59:22.725233: step: 24/530, loss: 0.007773017510771751
2023-01-21 11:59:23.905980: step: 28/530, loss: 0.024262238293886185
2023-01-21 11:59:25.085257: step: 32/530, loss: 0.01746959798038006
2023-01-21 11:59:26.308169: step: 36/530, loss: 0.015763377770781517
2023-01-21 11:59:27.480114: step: 40/530, loss: 0.016458988189697266
2023-01-21 11:59:28.691334: step: 44/530, loss: 0.0013010025722905993
2023-01-21 11:59:29.851726: step: 48/530, loss: 0.00341377267614007
2023-01-21 11:59:31.072926: step: 52/530, loss: 0.02081756666302681
2023-01-21 11:59:32.233021: step: 56/530, loss: 0.009267354384064674
2023-01-21 11:59:33.421020: step: 60/530, loss: 0.02803630940616131
2023-01-21 11:59:34.588275: step: 64/530, loss: 0.022510243579745293
2023-01-21 11:59:35.783606: step: 68/530, loss: 2.5749204723979346e-06
2023-01-21 11:59:36.950183: step: 72/530, loss: 0.016012001782655716
2023-01-21 11:59:38.153623: step: 76/530, loss: 0.007861233316361904
2023-01-21 11:59:39.329926: step: 80/530, loss: 0.0009715080377645791
2023-01-21 11:59:40.477072: step: 84/530, loss: 0.008212089538574219
2023-01-21 11:59:41.653580: step: 88/530, loss: 0.028080463409423828
2023-01-21 11:59:42.858157: step: 92/530, loss: 0.0011782168876379728
2023-01-21 11:59:44.044930: step: 96/530, loss: 0.020347023382782936
2023-01-21 11:59:45.226394: step: 100/530, loss: 0.0031574249733239412
2023-01-21 11:59:46.456048: step: 104/530, loss: 0.0009094238630495965
2023-01-21 11:59:47.701330: step: 108/530, loss: 0.0061584473587572575
2023-01-21 11:59:48.880912: step: 112/530, loss: 0.02565603330731392
2023-01-21 11:59:50.090977: step: 116/530, loss: 0.012187957763671875
2023-01-21 11:59:51.242345: step: 120/530, loss: 0.0007822036277502775
2023-01-21 11:59:52.391904: step: 124/530, loss: 0.0015838623512536287
2023-01-21 11:59:53.567330: step: 128/530, loss: 0.0011169493664056063
2023-01-21 11:59:54.733817: step: 132/530, loss: 0.00036659243050962687
2023-01-21 11:59:55.878188: step: 136/530, loss: 0.00016479491023346782
2023-01-21 11:59:57.109838: step: 140/530, loss: 0.0007848739624023438
2023-01-21 11:59:58.275037: step: 144/530, loss: 0.00011167526099598035
2023-01-21 11:59:59.446346: step: 148/530, loss: 0.048809148371219635
2023-01-21 12:00:00.615117: step: 152/530, loss: 0.001256752060726285
2023-01-21 12:00:01.780687: step: 156/530, loss: 8.301735215354711e-05
2023-01-21 12:00:02.962823: step: 160/530, loss: 0.0301374439150095
2023-01-21 12:00:04.158441: step: 164/530, loss: 0.005618393421173096
2023-01-21 12:00:05.358244: step: 168/530, loss: 0.004328918643295765
2023-01-21 12:00:06.520882: step: 172/530, loss: 0.0005311965942382812
2023-01-21 12:00:07.680527: step: 176/530, loss: 6.675720101156912e-07
2023-01-21 12:00:08.831289: step: 180/530, loss: 0.003245329950004816
2023-01-21 12:00:10.038250: step: 184/530, loss: 6.189346458995715e-05
2023-01-21 12:00:11.186019: step: 188/530, loss: 0.008834934793412685
2023-01-21 12:00:12.344312: step: 192/530, loss: 0.208173468708992
2023-01-21 12:00:13.489142: step: 196/530, loss: 0.00015182496281340718
2023-01-21 12:00:14.642926: step: 200/530, loss: 3.852844383800402e-05
2023-01-21 12:00:15.851022: step: 204/530, loss: 0.0003869056818075478
2023-01-21 12:00:17.035864: step: 208/530, loss: 0.003646707395091653
2023-01-21 12:00:18.184057: step: 212/530, loss: 0.008428382687270641
2023-01-21 12:00:19.350781: step: 216/530, loss: 0.014367103576660156
2023-01-21 12:00:20.535061: step: 220/530, loss: 0.003682899521663785
2023-01-21 12:00:21.681639: step: 224/530, loss: 0.07329835742712021
2023-01-21 12:00:22.963963: step: 228/530, loss: 0.007677114102989435
2023-01-21 12:00:24.137594: step: 232/530, loss: 0.04851233959197998
2023-01-21 12:00:25.302449: step: 236/530, loss: 0.00024595262948423624
2023-01-21 12:00:26.486221: step: 240/530, loss: 0.009625816717743874
2023-01-21 12:00:27.657747: step: 244/530, loss: 0.0015760421520099044
2023-01-21 12:00:28.778805: step: 248/530, loss: 0.3921127915382385
2023-01-21 12:00:29.962581: step: 252/530, loss: 8.440017700195312e-05
2023-01-21 12:00:31.141925: step: 256/530, loss: 0.007750320713967085
2023-01-21 12:00:32.323201: step: 260/530, loss: 0.01088562048971653
2023-01-21 12:00:33.526320: step: 264/530, loss: 0.019208908081054688
2023-01-21 12:00:34.677031: step: 268/530, loss: 0.012321185320615768
2023-01-21 12:00:35.867050: step: 272/530, loss: 0.000782394374255091
2023-01-21 12:00:37.085007: step: 276/530, loss: 0.06163006275892258
2023-01-21 12:00:38.240574: step: 280/530, loss: 0.0003364324802532792
2023-01-21 12:00:39.398227: step: 284/530, loss: 0.00047407150850631297
2023-01-21 12:00:40.561324: step: 288/530, loss: 0.003242444945499301
2023-01-21 12:00:41.744759: step: 292/530, loss: 0.015432453714311123
2023-01-21 12:00:42.923095: step: 296/530, loss: 0.012733840383589268
2023-01-21 12:00:44.050086: step: 300/530, loss: 0.0007595241186209023
2023-01-21 12:00:45.246202: step: 304/530, loss: 0.007056236267089844
2023-01-21 12:00:46.394949: step: 308/530, loss: 6.027222116244957e-05
2023-01-21 12:00:47.542564: step: 312/530, loss: 1.9550323486328125e-05
2023-01-21 12:00:48.715505: step: 316/530, loss: 0.01812438853085041
2023-01-21 12:00:49.892792: step: 320/530, loss: 0.014356661587953568
2023-01-21 12:00:50.997217: step: 324/530, loss: 0.001021957490593195
2023-01-21 12:00:52.179969: step: 328/530, loss: 0.0027439119294285774
2023-01-21 12:00:53.349486: step: 332/530, loss: 0.06676959991455078
2023-01-21 12:00:54.518666: step: 336/530, loss: 3.3140181585622486e-06
2023-01-21 12:00:55.682045: step: 340/530, loss: 6.952285912120715e-05
2023-01-21 12:00:56.867977: step: 344/530, loss: 0.0003010749933309853
2023-01-21 12:00:58.028334: step: 348/530, loss: 0.001771831652149558
2023-01-21 12:00:59.218967: step: 352/530, loss: 0.0743328109383583
2023-01-21 12:01:00.387456: step: 356/530, loss: 0.19436712563037872
2023-01-21 12:01:01.532682: step: 360/530, loss: 0.046106718480587006
2023-01-21 12:01:02.712852: step: 364/530, loss: 0.01660776138305664
2023-01-21 12:01:03.849608: step: 368/530, loss: 0.0001832962007028982
2023-01-21 12:01:05.024986: step: 372/530, loss: -1.316070574830519e-05
2023-01-21 12:01:06.215764: step: 376/530, loss: 5.5027012422215194e-05
2023-01-21 12:01:07.421631: step: 380/530, loss: 0.0018413544166833162
2023-01-21 12:01:08.604438: step: 384/530, loss: 8.997917757369578e-05
2023-01-21 12:01:09.786100: step: 388/530, loss: 0.05882210657000542
2023-01-21 12:01:10.968820: step: 392/530, loss: 0.0004989624139852822
2023-01-21 12:01:12.159785: step: 396/530, loss: 0.0647214874625206
2023-01-21 12:01:13.346204: step: 400/530, loss: 0.00033435822115279734
2023-01-21 12:01:14.543446: step: 404/530, loss: 0.007675552275031805
2023-01-21 12:01:15.698582: step: 408/530, loss: 0.00044431688729673624
2023-01-21 12:01:16.885467: step: 412/530, loss: 0.00017051697068382055
2023-01-21 12:01:18.076628: step: 416/530, loss: 0.0007219314575195312
2023-01-21 12:01:19.252621: step: 420/530, loss: 0.0005723953363485634
2023-01-21 12:01:20.421313: step: 424/530, loss: 0.08560800552368164
2023-01-21 12:01:21.580333: step: 428/530, loss: 0.0006450176588259637
2023-01-21 12:01:22.730670: step: 432/530, loss: 0.0032886506523936987
2023-01-21 12:01:23.924098: step: 436/530, loss: 0.021869469434022903
2023-01-21 12:01:25.111933: step: 440/530, loss: 0.0006940364837646484
2023-01-21 12:01:26.255375: step: 444/530, loss: 0.002557945204898715
2023-01-21 12:01:27.416498: step: 448/530, loss: 0.0019124984974041581
2023-01-21 12:01:28.572334: step: 452/530, loss: 0.005414772778749466
2023-01-21 12:01:29.769567: step: 456/530, loss: 0.006275749299675226
2023-01-21 12:01:30.938707: step: 460/530, loss: 0.0008335114107467234
2023-01-21 12:01:32.083628: step: 464/530, loss: 0.00014209747314453125
2023-01-21 12:01:33.294349: step: 468/530, loss: 0.0007354736444540322
2023-01-21 12:01:34.489405: step: 472/530, loss: 0.001516151474788785
2023-01-21 12:01:35.669993: step: 476/530, loss: 0.0055089956149458885
2023-01-21 12:01:36.843260: step: 480/530, loss: 0.00229644775390625
2023-01-21 12:01:38.012154: step: 484/530, loss: 0.0053501129150390625
2023-01-21 12:01:39.181819: step: 488/530, loss: 0.0249465461820364
2023-01-21 12:01:40.337417: step: 492/530, loss: 0.047649770975112915
2023-01-21 12:01:41.512768: step: 496/530, loss: 0.01101017091423273
2023-01-21 12:01:42.745362: step: 500/530, loss: 0.004105091094970703
2023-01-21 12:01:43.924719: step: 504/530, loss: 0.0019854544661939144
2023-01-21 12:01:45.093318: step: 508/530, loss: 0.03286914899945259
2023-01-21 12:01:46.272717: step: 512/530, loss: 0.0023729801177978516
2023-01-21 12:01:47.468027: step: 516/530, loss: 0.0030362128745764494
2023-01-21 12:01:48.628813: step: 520/530, loss: 0.00029792787972837687
2023-01-21 12:01:49.790332: step: 524/530, loss: 0.0005630493396893144
2023-01-21 12:01:50.947389: step: 528/530, loss: 0.02714099921286106
2023-01-21 12:01:52.151930: step: 532/530, loss: 0.007863807491958141
2023-01-21 12:01:53.322146: step: 536/530, loss: 0.000579833984375
2023-01-21 12:01:54.484102: step: 540/530, loss: 0.007014655973762274
2023-01-21 12:01:55.659163: step: 544/530, loss: 3.0517578125e-05
2023-01-21 12:01:56.850342: step: 548/530, loss: 0.014221764169633389
2023-01-21 12:01:57.996008: step: 552/530, loss: 0.002309560775756836
2023-01-21 12:01:59.225937: step: 556/530, loss: 0.0017877579666674137
2023-01-21 12:02:00.401490: step: 560/530, loss: 0.004434681031852961
2023-01-21 12:02:01.543447: step: 564/530, loss: 0.019142532721161842
2023-01-21 12:02:02.695751: step: 568/530, loss: -1.678466833254788e-05
2023-01-21 12:02:03.842434: step: 572/530, loss: 0.00014145375462248921
2023-01-21 12:02:04.984830: step: 576/530, loss: 0.0015735626220703125
2023-01-21 12:02:06.151025: step: 580/530, loss: 0.0017051697941496968
2023-01-21 12:02:07.330138: step: 584/530, loss: 0.0005186081398278475
2023-01-21 12:02:08.499003: step: 588/530, loss: 0.0030353544279932976
2023-01-21 12:02:09.658223: step: 592/530, loss: 9.450912330066785e-05
2023-01-21 12:02:10.832932: step: 596/530, loss: 0.006428718566894531
2023-01-21 12:02:11.983288: step: 600/530, loss: 0.0006405830499716103
2023-01-21 12:02:13.190941: step: 604/530, loss: 0.007863521575927734
2023-01-21 12:02:14.355793: step: 608/530, loss: 0.01780986785888672
2023-01-21 12:02:15.511940: step: 612/530, loss: 0.040480803698301315
2023-01-21 12:02:16.697536: step: 616/530, loss: 0.010878182016313076
2023-01-21 12:02:17.876364: step: 620/530, loss: 0.036622099578380585
2023-01-21 12:02:19.021686: step: 624/530, loss: 1.162734866142273
2023-01-21 12:02:20.190652: step: 628/530, loss: 0.00361289968714118
2023-01-21 12:02:21.328171: step: 632/530, loss: 0.00045795441837981343
2023-01-21 12:02:22.477626: step: 636/530, loss: 0.09098635613918304
2023-01-21 12:02:23.664479: step: 640/530, loss: 0.003033924149349332
2023-01-21 12:02:24.772435: step: 644/530, loss: 0.09502916038036346
2023-01-21 12:02:25.937257: step: 648/530, loss: 4.5490269258152694e-05
2023-01-21 12:02:27.092181: step: 652/530, loss: 0.009157276712357998
2023-01-21 12:02:28.251195: step: 656/530, loss: 0.007767105475068092
2023-01-21 12:02:29.383693: step: 660/530, loss: 0.0004553794860839844
2023-01-21 12:02:30.566757: step: 664/530, loss: 0.05796780437231064
2023-01-21 12:02:31.814958: step: 668/530, loss: 0.019757939502596855
2023-01-21 12:02:32.974126: step: 672/530, loss: 0.011412429623305798
2023-01-21 12:02:34.154854: step: 676/530, loss: 0.007752036675810814
2023-01-21 12:02:35.320677: step: 680/530, loss: 0.002031040145084262
2023-01-21 12:02:36.502791: step: 684/530, loss: 0.0005773544544354081
2023-01-21 12:02:37.730429: step: 688/530, loss: 0.007434464059770107
2023-01-21 12:02:38.876419: step: 692/530, loss: 0.0029165151063352823
2023-01-21 12:02:40.077050: step: 696/530, loss: 3.5691260563908145e-05
2023-01-21 12:02:41.288027: step: 700/530, loss: 0.0006225585821084678
2023-01-21 12:02:42.485726: step: 704/530, loss: 0.0008599281427450478
2023-01-21 12:02:43.653690: step: 708/530, loss: 0.14407701790332794
2023-01-21 12:02:44.838300: step: 712/530, loss: 0.000984287355095148
2023-01-21 12:02:46.019282: step: 716/530, loss: 0.015123367309570312
2023-01-21 12:02:47.197189: step: 720/530, loss: 0.05423898622393608
2023-01-21 12:02:48.359402: step: 724/530, loss: 5.7029727031476796e-05
2023-01-21 12:02:49.553155: step: 728/530, loss: 0.0016246795421466231
2023-01-21 12:02:50.745139: step: 732/530, loss: 0.0006534576532430947
2023-01-21 12:02:51.900676: step: 736/530, loss: 0.000548934971448034
2023-01-21 12:02:53.085362: step: 740/530, loss: 0.004404926206916571
2023-01-21 12:02:54.272826: step: 744/530, loss: 0.0017291069962084293
2023-01-21 12:02:55.472186: step: 748/530, loss: 0.007610893342643976
2023-01-21 12:02:56.630826: step: 752/530, loss: 0.003435039659962058
2023-01-21 12:02:57.810578: step: 756/530, loss: 0.014569473452866077
2023-01-21 12:02:59.017574: step: 760/530, loss: 0.020407389849424362
2023-01-21 12:03:00.245812: step: 764/530, loss: 0.03406648710370064
2023-01-21 12:03:01.414752: step: 768/530, loss: 0.4402596354484558
2023-01-21 12:03:02.589857: step: 772/530, loss: 0.005612373352050781
2023-01-21 12:03:03.801963: step: 776/530, loss: 0.0007963181124068797
2023-01-21 12:03:04.977158: step: 780/530, loss: 0.019199658185243607
2023-01-21 12:03:06.158417: step: 784/530, loss: 0.0001506805419921875
2023-01-21 12:03:07.326396: step: 788/530, loss: 0.0002320289786439389
2023-01-21 12:03:08.520833: step: 792/530, loss: 0.09661455452442169
2023-01-21 12:03:09.703584: step: 796/530, loss: 0.0020971298217773438
2023-01-21 12:03:10.849605: step: 800/530, loss: 0.007229995913803577
2023-01-21 12:03:12.051785: step: 804/530, loss: 0.003390503115952015
2023-01-21 12:03:13.217145: step: 808/530, loss: 0.022574711591005325
2023-01-21 12:03:14.402625: step: 812/530, loss: 0.03010106086730957
2023-01-21 12:03:15.565198: step: 816/530, loss: 0.03401822969317436
2023-01-21 12:03:16.716773: step: 820/530, loss: 0.09475937485694885
2023-01-21 12:03:17.908828: step: 824/530, loss: 0.0011989593040198088
2023-01-21 12:03:19.073588: step: 828/530, loss: 0.005826234817504883
2023-01-21 12:03:20.275933: step: 832/530, loss: 0.0003656387561932206
2023-01-21 12:03:21.479185: step: 836/530, loss: 0.003420066786929965
2023-01-21 12:03:22.672667: step: 840/530, loss: 0.00039882661076262593
2023-01-21 12:03:23.860043: step: 844/530, loss: 0.013754845596849918
2023-01-21 12:03:25.048050: step: 848/530, loss: 0.0014840603107586503
2023-01-21 12:03:26.238411: step: 852/530, loss: 0.02922821044921875
2023-01-21 12:03:27.385013: step: 856/530, loss: 0.0008815765613690019
2023-01-21 12:03:28.529929: step: 860/530, loss: 0.002232170198112726
2023-01-21 12:03:29.715158: step: 864/530, loss: 0.01718893088400364
2023-01-21 12:03:30.909765: step: 868/530, loss: 0.00629157992079854
2023-01-21 12:03:32.067277: step: 872/530, loss: 0.013038254342973232
2023-01-21 12:03:33.240996: step: 876/530, loss: 0.0005726814270019531
2023-01-21 12:03:34.424989: step: 880/530, loss: 0.007781696505844593
2023-01-21 12:03:35.617231: step: 884/530, loss: 0.013808107934892178
2023-01-21 12:03:36.766533: step: 888/530, loss: 0.023785972967743874
2023-01-21 12:03:37.943249: step: 892/530, loss: 0.030319882556796074
2023-01-21 12:03:39.132629: step: 896/530, loss: 0.02408876270055771
2023-01-21 12:03:40.310159: step: 900/530, loss: 0.018917370587587357
2023-01-21 12:03:41.456150: step: 904/530, loss: 0.005561495199799538
2023-01-21 12:03:42.659379: step: 908/530, loss: 0.05368461832404137
2023-01-21 12:03:43.835108: step: 912/530, loss: 0.0004751205269712955
2023-01-21 12:03:44.970363: step: 916/530, loss: 0.0015298842918127775
2023-01-21 12:03:46.108407: step: 920/530, loss: 0.0015491247177124023
2023-01-21 12:03:47.277247: step: 924/530, loss: 0.009456825442612171
2023-01-21 12:03:48.460180: step: 928/530, loss: 0.004016113001853228
2023-01-21 12:03:49.644610: step: 932/530, loss: 0.08811359852552414
2023-01-21 12:03:50.850040: step: 936/530, loss: 0.011536311358213425
2023-01-21 12:03:52.025620: step: 940/530, loss: 0.00014495849609375
2023-01-21 12:03:53.227019: step: 944/530, loss: 0.009525870904326439
2023-01-21 12:03:54.371772: step: 948/530, loss: 0.010910797864198685
2023-01-21 12:03:55.564268: step: 952/530, loss: 0.16003188490867615
2023-01-21 12:03:56.762726: step: 956/530, loss: 0.01636524312198162
2023-01-21 12:03:57.928138: step: 960/530, loss: 0.038251589983701706
2023-01-21 12:03:59.104883: step: 964/530, loss: 0.030727673321962357
2023-01-21 12:04:00.281340: step: 968/530, loss: 9.424686868442222e-05
2023-01-21 12:04:01.448239: step: 972/530, loss: 0.00821156520396471
2023-01-21 12:04:02.611704: step: 976/530, loss: 0.06272802501916885
2023-01-21 12:04:03.771146: step: 980/530, loss: 0.0019258500542491674
2023-01-21 12:04:04.966472: step: 984/530, loss: 0.0074707032181322575
2023-01-21 12:04:06.153965: step: 988/530, loss: 0.0007600784301757812
2023-01-21 12:04:07.289854: step: 992/530, loss: 0.002627205802127719
2023-01-21 12:04:08.415199: step: 996/530, loss: 0.0006809234619140625
2023-01-21 12:04:09.582942: step: 1000/530, loss: 0.05459868907928467
2023-01-21 12:04:10.782292: step: 1004/530, loss: 0.001634883927181363
2023-01-21 12:04:12.025334: step: 1008/530, loss: 0.004923057742416859
2023-01-21 12:04:13.182383: step: 1012/530, loss: 2.155303991457913e-05
2023-01-21 12:04:14.378105: step: 1016/530, loss: 0.00969161931425333
2023-01-21 12:04:15.590205: step: 1020/530, loss: 0.007298565004020929
2023-01-21 12:04:16.745943: step: 1024/530, loss: 0.03919525071978569
2023-01-21 12:04:17.928882: step: 1028/530, loss: 0.04719958454370499
2023-01-21 12:04:19.084675: step: 1032/530, loss: 0.018381500616669655
2023-01-21 12:04:20.241162: step: 1036/530, loss: 0.01364822406321764
2023-01-21 12:04:21.430237: step: 1040/530, loss: 0.001079988433048129
2023-01-21 12:04:22.665797: step: 1044/530, loss: 0.004852390382438898
2023-01-21 12:04:23.869291: step: 1048/530, loss: 0.0007318496936932206
2023-01-21 12:04:25.052263: step: 1052/530, loss: 0.0005678177112713456
2023-01-21 12:04:26.252455: step: 1056/530, loss: 0.03227615728974342
2023-01-21 12:04:27.419817: step: 1060/530, loss: 0.029921723529696465
2023-01-21 12:04:28.574395: step: 1064/530, loss: 0.008886338211596012
2023-01-21 12:04:29.702843: step: 1068/530, loss: 0.045716091990470886
2023-01-21 12:04:30.893738: step: 1072/530, loss: 0.00033826829167082906
2023-01-21 12:04:32.051053: step: 1076/530, loss: 0.0039396765641868114
2023-01-21 12:04:33.271748: step: 1080/530, loss: 4.043579247081652e-05
2023-01-21 12:04:34.455311: step: 1084/530, loss: 0.01632690615952015
2023-01-21 12:04:35.689882: step: 1088/530, loss: 0.006623649969696999
2023-01-21 12:04:36.883338: step: 1092/530, loss: 0.0041179656982421875
2023-01-21 12:04:38.054667: step: 1096/530, loss: 0.017409324645996094
2023-01-21 12:04:39.268989: step: 1100/530, loss: 0.0010496140457689762
2023-01-21 12:04:40.484617: step: 1104/530, loss: 0.0028597356285899878
2023-01-21 12:04:41.682593: step: 1108/530, loss: 0.0005098819965496659
2023-01-21 12:04:42.923798: step: 1112/530, loss: 0.08675575256347656
2023-01-21 12:04:44.109303: step: 1116/530, loss: 0.08679638057947159
2023-01-21 12:04:45.294144: step: 1120/530, loss: 0.006492996588349342
2023-01-21 12:04:46.457346: step: 1124/530, loss: 0.040943436324596405
2023-01-21 12:04:47.612576: step: 1128/530, loss: 0.0032581686973571777
2023-01-21 12:04:48.791350: step: 1132/530, loss: 0.0015054702525958419
2023-01-21 12:04:49.980642: step: 1136/530, loss: 0.00575304077938199
2023-01-21 12:04:51.132231: step: 1140/530, loss: 0.030535221099853516
2023-01-21 12:04:52.279761: step: 1144/530, loss: 0.0016894340515136719
2023-01-21 12:04:53.447981: step: 1148/530, loss: 0.0001939773646881804
2023-01-21 12:04:54.646434: step: 1152/530, loss: 0.0030698776245117188
2023-01-21 12:04:55.844946: step: 1156/530, loss: 0.00989003200083971
2023-01-21 12:04:57.029513: step: 1160/530, loss: 0.00016164779663085938
2023-01-21 12:04:58.201743: step: 1164/530, loss: 0.010471916757524014
2023-01-21 12:04:59.363992: step: 1168/530, loss: 0.0011441231472417712
2023-01-21 12:05:00.588896: step: 1172/530, loss: 0.028838159516453743
2023-01-21 12:05:01.814008: step: 1176/530, loss: 0.009549331851303577
2023-01-21 12:05:02.983207: step: 1180/530, loss: 0.00010185241990257055
2023-01-21 12:05:04.185194: step: 1184/530, loss: 0.047628212720155716
2023-01-21 12:05:05.340056: step: 1188/530, loss: 0.00048055651132017374
2023-01-21 12:05:06.541108: step: 1192/530, loss: 4.6157834731275216e-05
2023-01-21 12:05:07.695072: step: 1196/530, loss: 0.046483419835567474
2023-01-21 12:05:08.878612: step: 1200/530, loss: 0.030712412670254707
2023-01-21 12:05:10.060965: step: 1204/530, loss: 0.01286230143159628
2023-01-21 12:05:11.226712: step: 1208/530, loss: 0.02996654435992241
2023-01-21 12:05:12.421044: step: 1212/530, loss: 0.0013994218315929174
2023-01-21 12:05:13.626301: step: 1216/530, loss: 2.5177003408316523e-05
2023-01-21 12:05:14.782929: step: 1220/530, loss: 0.0007638931274414062
2023-01-21 12:05:16.000097: step: 1224/530, loss: 0.03564567491412163
2023-01-21 12:05:17.184534: step: 1228/530, loss: 0.0005281448247842491
2023-01-21 12:05:18.358227: step: 1232/530, loss: 0.03731689602136612
2023-01-21 12:05:19.534395: step: 1236/530, loss: 0.005178642459213734
2023-01-21 12:05:20.687803: step: 1240/530, loss: 0.07758168876171112
2023-01-21 12:05:21.877784: step: 1244/530, loss: 0.07812522351741791
2023-01-21 12:05:23.052297: step: 1248/530, loss: 0.017845438793301582
2023-01-21 12:05:24.241016: step: 1252/530, loss: 0.01222839392721653
2023-01-21 12:05:25.479228: step: 1256/530, loss: 5.974803447723389
2023-01-21 12:05:26.625132: step: 1260/530, loss: 3.5953522456111386e-05
2023-01-21 12:05:27.854613: step: 1264/530, loss: 0.0014590263599529862
2023-01-21 12:05:29.073072: step: 1268/530, loss: 0.003410005709156394
2023-01-21 12:05:30.272233: step: 1272/530, loss: 0.008798694238066673
2023-01-21 12:05:31.441281: step: 1276/530, loss: 0.0023822784423828125
2023-01-21 12:05:32.619540: step: 1280/530, loss: 0.0023009299766272306
2023-01-21 12:05:33.788734: step: 1284/530, loss: 0.0002038955717580393
2023-01-21 12:05:34.940397: step: 1288/530, loss: 0.061708737164735794
2023-01-21 12:05:36.179072: step: 1292/530, loss: 5.617141869151965e-05
2023-01-21 12:05:37.355301: step: 1296/530, loss: 4.7016143071232364e-05
2023-01-21 12:05:38.503936: step: 1300/530, loss: 0.0015858174301683903
2023-01-21 12:05:39.660507: step: 1304/530, loss: 0.027640486136078835
2023-01-21 12:05:40.840422: step: 1308/530, loss: 0.002192878630012274
2023-01-21 12:05:42.018476: step: 1312/530, loss: 0.006818199064582586
2023-01-21 12:05:43.212354: step: 1316/530, loss: 0.05095253139734268
2023-01-21 12:05:44.353168: step: 1320/530, loss: 9.918212890625e-05
2023-01-21 12:05:45.564536: step: 1324/530, loss: 0.005904293153434992
2023-01-21 12:05:46.723275: step: 1328/530, loss: 0.009035158902406693
2023-01-21 12:05:47.917772: step: 1332/530, loss: 0.06499442458152771
2023-01-21 12:05:49.124533: step: 1336/530, loss: 0.00032792091951705515
2023-01-21 12:05:50.358752: step: 1340/530, loss: 0.0007309913635253906
2023-01-21 12:05:51.500302: step: 1344/530, loss: 0.00011429786536609754
2023-01-21 12:05:52.647629: step: 1348/530, loss: 8.687973604537547e-05
2023-01-21 12:05:53.840312: step: 1352/530, loss: 0.0002700805780477822
2023-01-21 12:05:55.081026: step: 1356/530, loss: 0.005312728695571423
2023-01-21 12:05:56.221983: step: 1360/530, loss: 0.0005973816150799394
2023-01-21 12:05:57.382575: step: 1364/530, loss: 0.002830123994499445
2023-01-21 12:05:58.543723: step: 1368/530, loss: 0.03579740598797798
2023-01-21 12:05:59.672071: step: 1372/530, loss: 0.008071518503129482
2023-01-21 12:06:00.866664: step: 1376/530, loss: 0.029038619250059128
2023-01-21 12:06:02.061669: step: 1380/530, loss: 0.00737762451171875
2023-01-21 12:06:03.249552: step: 1384/530, loss: 0.0005518912803381681
2023-01-21 12:06:04.488042: step: 1388/530, loss: 0.052643775939941406
2023-01-21 12:06:05.707372: step: 1392/530, loss: 0.018905067816376686
2023-01-21 12:06:06.891414: step: 1396/530, loss: 0.009289824403822422
2023-01-21 12:06:08.065215: step: 1400/530, loss: 0.14495983719825745
2023-01-21 12:06:09.273222: step: 1404/530, loss: 0.004733848851174116
2023-01-21 12:06:10.447606: step: 1408/530, loss: 0.0007394790882244706
2023-01-21 12:06:11.645921: step: 1412/530, loss: 0.013779259286820889
2023-01-21 12:06:12.804754: step: 1416/530, loss: 0.003085231641307473
2023-01-21 12:06:13.988080: step: 1420/530, loss: 0.025857020169496536
2023-01-21 12:06:15.190680: step: 1424/530, loss: 0.00035037993802689016
2023-01-21 12:06:16.369503: step: 1428/530, loss: 0.00039310456486418843
2023-01-21 12:06:17.549195: step: 1432/530, loss: 0.013794517144560814
2023-01-21 12:06:18.699340: step: 1436/530, loss: 0.0002681732294149697
2023-01-21 12:06:19.866839: step: 1440/530, loss: 0.0009615898597985506
2023-01-21 12:06:21.069813: step: 1444/530, loss: 0.014445829205214977
2023-01-21 12:06:22.221211: step: 1448/530, loss: 0.00698509206995368
2023-01-21 12:06:23.408362: step: 1452/530, loss: 0.0188203826546669
2023-01-21 12:06:24.612148: step: 1456/530, loss: 0.0033960342407226562
2023-01-21 12:06:25.776528: step: 1460/530, loss: 0.0044970037415623665
2023-01-21 12:06:26.920890: step: 1464/530, loss: 0.05821037292480469
2023-01-21 12:06:28.064676: step: 1468/530, loss: 0.02616710588335991
2023-01-21 12:06:29.251120: step: 1472/530, loss: 0.0002674102724995464
2023-01-21 12:06:30.435621: step: 1476/530, loss: 0.020495224744081497
2023-01-21 12:06:31.694465: step: 1480/530, loss: 0.08616162091493607
2023-01-21 12:06:32.884274: step: 1484/530, loss: 0.06972980499267578
2023-01-21 12:06:34.054362: step: 1488/530, loss: 0.0006031036609783769
2023-01-21 12:06:35.272000: step: 1492/530, loss: 1.9359587895451114e-05
2023-01-21 12:06:36.469562: step: 1496/530, loss: 0.0029044151306152344
2023-01-21 12:06:37.652017: step: 1500/530, loss: 0.007088374812155962
2023-01-21 12:06:38.808313: step: 1504/530, loss: 0.01528091449290514
2023-01-21 12:06:39.975725: step: 1508/530, loss: 0.0008367538684979081
2023-01-21 12:06:41.142802: step: 1512/530, loss: 0.003276729490607977
2023-01-21 12:06:42.351193: step: 1516/530, loss: 0.01809234544634819
2023-01-21 12:06:43.563107: step: 1520/530, loss: 0.0004050254647154361
2023-01-21 12:06:44.700886: step: 1524/530, loss: 0.003694248152896762
2023-01-21 12:06:45.841292: step: 1528/530, loss: 0.004168796353042126
2023-01-21 12:06:47.037501: step: 1532/530, loss: 0.0005702972412109375
2023-01-21 12:06:48.186936: step: 1536/530, loss: 0.00012292861356399953
2023-01-21 12:06:49.372676: step: 1540/530, loss: 0.10180526226758957
2023-01-21 12:06:50.504447: step: 1544/530, loss: 0.01912846788764
2023-01-21 12:06:51.651074: step: 1548/530, loss: 0.0002604961337056011
2023-01-21 12:06:52.821865: step: 1552/530, loss: 0.01832704432308674
2023-01-21 12:06:54.000981: step: 1556/530, loss: 0.2695252001285553
2023-01-21 12:06:55.171647: step: 1560/530, loss: 0.004031944088637829
2023-01-21 12:06:56.345519: step: 1564/530, loss: 0.0027374266646802425
2023-01-21 12:06:57.575621: step: 1568/530, loss: 0.0073188780806958675
2023-01-21 12:06:58.738253: step: 1572/530, loss: 0.0001731872616801411
2023-01-21 12:06:59.900135: step: 1576/530, loss: 0.04115085303783417
2023-01-21 12:07:01.100796: step: 1580/530, loss: 0.0012755156494677067
2023-01-21 12:07:02.287839: step: 1584/530, loss: 0.0008054733625613153
2023-01-21 12:07:03.486363: step: 1588/530, loss: 0.04562988504767418
2023-01-21 12:07:04.657537: step: 1592/530, loss: 0.00011024474952137098
2023-01-21 12:07:05.825391: step: 1596/530, loss: 0.0761910229921341
2023-01-21 12:07:06.981356: step: 1600/530, loss: 0.014288950711488724
2023-01-21 12:07:08.138170: step: 1604/530, loss: 0.038820937275886536
2023-01-21 12:07:09.331101: step: 1608/530, loss: 0.002949589630588889
2023-01-21 12:07:10.537884: step: 1612/530, loss: 0.0019914626609534025
2023-01-21 12:07:11.710079: step: 1616/530, loss: 0.029420530423521996
2023-01-21 12:07:12.951468: step: 1620/530, loss: 0.03519554063677788
2023-01-21 12:07:14.123638: step: 1624/530, loss: 0.008805847726762295
2023-01-21 12:07:15.295560: step: 1628/530, loss: 0.010153960436582565
2023-01-21 12:07:16.491199: step: 1632/530, loss: 0.039067938923835754
2023-01-21 12:07:17.658458: step: 1636/530, loss: 0.06935997307300568
2023-01-21 12:07:18.851100: step: 1640/530, loss: 0.007793044671416283
2023-01-21 12:07:20.027260: step: 1644/530, loss: 0.018748190253973007
2023-01-21 12:07:21.222519: step: 1648/530, loss: 0.0021436691749840975
2023-01-21 12:07:22.406249: step: 1652/530, loss: 0.010505914688110352
2023-01-21 12:07:23.562495: step: 1656/530, loss: 0.021545004099607468
2023-01-21 12:07:24.761094: step: 1660/530, loss: 0.0010385513305664062
2023-01-21 12:07:25.958269: step: 1664/530, loss: 0.005652427673339844
2023-01-21 12:07:27.142581: step: 1668/530, loss: 0.00029277801513671875
2023-01-21 12:07:28.319369: step: 1672/530, loss: 0.001043129013851285
2023-01-21 12:07:29.498654: step: 1676/530, loss: 0.028532786294817924
2023-01-21 12:07:30.713945: step: 1680/530, loss: 0.10484028607606888
2023-01-21 12:07:31.896898: step: 1684/530, loss: 0.016578197479248047
2023-01-21 12:07:33.086709: step: 1688/530, loss: 0.0016023635398596525
2023-01-21 12:07:34.271025: step: 1692/530, loss: 0.01886424981057644
2023-01-21 12:07:35.464010: step: 1696/530, loss: 0.06792030483484268
2023-01-21 12:07:36.644467: step: 1700/530, loss: 0.0007139205699786544
2023-01-21 12:07:37.846802: step: 1704/530, loss: 0.00135040283203125
2023-01-21 12:07:39.046124: step: 1708/530, loss: 0.02439441718161106
2023-01-21 12:07:40.260148: step: 1712/530, loss: 0.007346153259277344
2023-01-21 12:07:41.412027: step: 1716/530, loss: 0.023163223639130592
2023-01-21 12:07:42.621979: step: 1720/530, loss: 0.03194904327392578
2023-01-21 12:07:43.842409: step: 1724/530, loss: 0.025572776794433594
2023-01-21 12:07:45.019028: step: 1728/530, loss: 0.0333222895860672
2023-01-21 12:07:46.140231: step: 1732/530, loss: 0.004378700163215399
2023-01-21 12:07:47.339472: step: 1736/530, loss: 0.03282938152551651
2023-01-21 12:07:48.535045: step: 1740/530, loss: 0.00011339188495185226
2023-01-21 12:07:49.708549: step: 1744/530, loss: 0.003886604215949774
2023-01-21 12:07:50.841718: step: 1748/530, loss: 0.000819349312223494
2023-01-21 12:07:52.048369: step: 1752/530, loss: 0.029551029205322266
2023-01-21 12:07:53.179218: step: 1756/530, loss: 1.1420250302762724e-05
2023-01-21 12:07:54.364732: step: 1760/530, loss: 0.01574401929974556
2023-01-21 12:07:55.529593: step: 1764/530, loss: 0.007483029738068581
2023-01-21 12:07:56.655788: step: 1768/530, loss: 0.0001947402924997732
2023-01-21 12:07:57.828609: step: 1772/530, loss: 0.02593708038330078
2023-01-21 12:07:59.099706: step: 1776/530, loss: 0.00200996408239007
2023-01-21 12:08:00.294163: step: 1780/530, loss: 0.006249618716537952
2023-01-21 12:08:01.478751: step: 1784/530, loss: 0.0024644851218909025
2023-01-21 12:08:02.650087: step: 1788/530, loss: 0.0032048227731138468
2023-01-21 12:08:03.813632: step: 1792/530, loss: 3.80516066798009e-05
2023-01-21 12:08:05.005195: step: 1796/530, loss: 0.043852902948856354
2023-01-21 12:08:06.228014: step: 1800/530, loss: 0.00013151168241165578
2023-01-21 12:08:07.440610: step: 1804/530, loss: 0.016939258202910423
2023-01-21 12:08:08.602409: step: 1808/530, loss: 0.00015897752018645406
2023-01-21 12:08:09.745866: step: 1812/530, loss: 0.0039543150924146175
2023-01-21 12:08:10.988744: step: 1816/530, loss: 0.41771575808525085
2023-01-21 12:08:12.201145: step: 1820/530, loss: 0.0004191398620605469
2023-01-21 12:08:13.450693: step: 1824/530, loss: 0.2355606108903885
2023-01-21 12:08:14.621104: step: 1828/530, loss: 0.23792299628257751
2023-01-21 12:08:15.800709: step: 1832/530, loss: 0.035604145377874374
2023-01-21 12:08:16.940829: step: 1836/530, loss: 0.0004975319025106728
2023-01-21 12:08:18.104099: step: 1840/530, loss: 0.010256576351821423
2023-01-21 12:08:19.315022: step: 1844/530, loss: 0.0014173508388921618
2023-01-21 12:08:20.469865: step: 1848/530, loss: 0.034442998468875885
2023-01-21 12:08:21.637948: step: 1852/530, loss: 0.005626392550766468
2023-01-21 12:08:22.806752: step: 1856/530, loss: 0.01870574988424778
2023-01-21 12:08:23.989617: step: 1860/530, loss: 0.0005195618141442537
2023-01-21 12:08:25.151578: step: 1864/530, loss: 0.032444193959236145
2023-01-21 12:08:26.349156: step: 1868/530, loss: 0.0003391265927348286
2023-01-21 12:08:27.544642: step: 1872/530, loss: 0.01906614378094673
2023-01-21 12:08:28.827068: step: 1876/530, loss: 0.0019253729842603207
2023-01-21 12:08:29.989251: step: 1880/530, loss: 0.015119553543627262
2023-01-21 12:08:31.194082: step: 1884/530, loss: 0.0006293296464718878
2023-01-21 12:08:32.374474: step: 1888/530, loss: 0.009006357751786709
2023-01-21 12:08:33.582323: step: 1892/530, loss: 0.0011419296497479081
2023-01-21 12:08:34.776492: step: 1896/530, loss: 0.00022153854661155492
2023-01-21 12:08:35.982827: step: 1900/530, loss: 0.0037729262840002775
2023-01-21 12:08:37.115426: step: 1904/530, loss: 0.007874870672821999
2023-01-21 12:08:38.266491: step: 1908/530, loss: 0.0003532409609761089
2023-01-21 12:08:39.458891: step: 1912/530, loss: 0.0029369352851063013
2023-01-21 12:08:40.643583: step: 1916/530, loss: 2.136230432370212e-05
2023-01-21 12:08:41.826914: step: 1920/530, loss: 0.03233680501580238
2023-01-21 12:08:43.011502: step: 1924/530, loss: 0.007155799772590399
2023-01-21 12:08:44.157484: step: 1928/530, loss: 0.004911637399345636
2023-01-21 12:08:45.342610: step: 1932/530, loss: 8.449554297840223e-05
2023-01-21 12:08:46.522218: step: 1936/530, loss: 0.03290577232837677
2023-01-21 12:08:47.676222: step: 1940/530, loss: 0.006567764095962048
2023-01-21 12:08:48.864554: step: 1944/530, loss: 0.12615303695201874
2023-01-21 12:08:50.045930: step: 1948/530, loss: 0.0009716987842693925
2023-01-21 12:08:51.233486: step: 1952/530, loss: 0.0007730245124548674
2023-01-21 12:08:52.410229: step: 1956/530, loss: 0.0009432792430743575
2023-01-21 12:08:53.608794: step: 1960/530, loss: 0.00143260951153934
2023-01-21 12:08:54.782444: step: 1964/530, loss: 0.16355854272842407
2023-01-21 12:08:55.964264: step: 1968/530, loss: 0.0006039619911462069
2023-01-21 12:08:57.152967: step: 1972/530, loss: 0.04809780418872833
2023-01-21 12:08:58.304221: step: 1976/530, loss: 0.012504005804657936
2023-01-21 12:08:59.448025: step: 1980/530, loss: 0.2107163369655609
2023-01-21 12:09:00.674711: step: 1984/530, loss: 0.0021579742897301912
2023-01-21 12:09:01.887433: step: 1988/530, loss: 0.0004529953293967992
2023-01-21 12:09:03.035617: step: 1992/530, loss: 0.025238037109375
2023-01-21 12:09:04.255570: step: 1996/530, loss: 9.613037400413305e-05
2023-01-21 12:09:05.418639: step: 2000/530, loss: 0.01381530798971653
2023-01-21 12:09:06.590113: step: 2004/530, loss: 0.0007887363317422569
2023-01-21 12:09:07.770966: step: 2008/530, loss: 0.001117706298828125
2023-01-21 12:09:08.982572: step: 2012/530, loss: 0.007008457090705633
2023-01-21 12:09:10.109084: step: 2016/530, loss: 8.859634544933215e-05
2023-01-21 12:09:11.277868: step: 2020/530, loss: 0.006595611572265625
2023-01-21 12:09:12.440003: step: 2024/530, loss: 0.08102016896009445
2023-01-21 12:09:13.633546: step: 2028/530, loss: 0.0006907939678058028
2023-01-21 12:09:14.845839: step: 2032/530, loss: 0.11535453796386719
2023-01-21 12:09:16.006540: step: 2036/530, loss: 0.03095979616045952
2023-01-21 12:09:17.160979: step: 2040/530, loss: 0.0002171516534872353
2023-01-21 12:09:18.332001: step: 2044/530, loss: 0.0011821746593341231
2023-01-21 12:09:19.484071: step: 2048/530, loss: 0.008242607116699219
2023-01-21 12:09:20.651338: step: 2052/530, loss: 0.031734466552734375
2023-01-21 12:09:21.833673: step: 2056/530, loss: 0.003280591918155551
2023-01-21 12:09:22.984338: step: 2060/530, loss: 1.7023086911649443e-05
2023-01-21 12:09:24.174848: step: 2064/530, loss: 0.015797805041074753
2023-01-21 12:09:25.357311: step: 2068/530, loss: 0.0018525600899010897
2023-01-21 12:09:26.519643: step: 2072/530, loss: 0.0034498213790357113
2023-01-21 12:09:27.722682: step: 2076/530, loss: 0.16373948752880096
2023-01-21 12:09:28.903782: step: 2080/530, loss: 5.7697296142578125e-05
2023-01-21 12:09:30.121770: step: 2084/530, loss: 0.029844429343938828
2023-01-21 12:09:31.368472: step: 2088/530, loss: 0.010340690612792969
2023-01-21 12:09:32.608171: step: 2092/530, loss: 0.051587868481874466
2023-01-21 12:09:33.783258: step: 2096/530, loss: 0.005192280281335115
2023-01-21 12:09:34.946264: step: 2100/530, loss: 0.008917141705751419
2023-01-21 12:09:36.149242: step: 2104/530, loss: 0.004713344853371382
2023-01-21 12:09:37.345440: step: 2108/530, loss: 0.0028250697068870068
2023-01-21 12:09:38.539616: step: 2112/530, loss: 0.015909289941191673
2023-01-21 12:09:39.732532: step: 2116/530, loss: 0.004019832704216242
2023-01-21 12:09:40.874424: step: 2120/530, loss: 0.00087909703142941
==================================================
Loss: 0.033
--------------------
Dev: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.5, 'r': 0.42857142857142855, 'f1': 0.4615384615384615}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.4489795918367347, 'r': 0.6111111111111112, 'f1': 0.5176470588235293}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 12:10:30.500506: step: 4/530, loss: 0.0009859561687335372
2023-01-21 12:10:31.675144: step: 8/530, loss: 0.0004611969052348286
2023-01-21 12:10:32.838786: step: 12/530, loss: 0.005803633015602827
2023-01-21 12:10:34.027326: step: 16/530, loss: 0.0024608613457530737
2023-01-21 12:10:35.191831: step: 20/530, loss: 0.00018253325833939016
2023-01-21 12:10:36.341608: step: 24/530, loss: 0.00025453566922806203
2023-01-21 12:10:37.494542: step: 28/530, loss: 0.00448951730504632
2023-01-21 12:10:38.671142: step: 32/530, loss: 0.020351599901914597
2023-01-21 12:10:39.843134: step: 36/530, loss: 0.0007308960193768144
2023-01-21 12:10:41.043926: step: 40/530, loss: 0.030013561248779297
2023-01-21 12:10:42.223025: step: 44/530, loss: 0.010929679498076439
2023-01-21 12:10:43.367729: step: 48/530, loss: 0.057430051267147064
2023-01-21 12:10:44.560084: step: 52/530, loss: 0.009071302600204945
2023-01-21 12:10:45.775887: step: 56/530, loss: 0.12401314079761505
2023-01-21 12:10:46.965210: step: 60/530, loss: 0.0057014464400708675
2023-01-21 12:10:48.107081: step: 64/530, loss: 0.00044317246647551656
2023-01-21 12:10:49.298265: step: 68/530, loss: 0.0001362323819193989
2023-01-21 12:10:50.500656: step: 72/530, loss: 0.005087662022560835
2023-01-21 12:10:51.685601: step: 76/530, loss: 0.000615882920101285
2023-01-21 12:10:52.829811: step: 80/530, loss: 0.0031612396705895662
2023-01-21 12:10:54.001723: step: 84/530, loss: 0.0023467063438147306
2023-01-21 12:10:55.165503: step: 88/530, loss: 0.002280712127685547
2023-01-21 12:10:56.353949: step: 92/530, loss: 0.011156369000673294
2023-01-21 12:10:57.525675: step: 96/530, loss: 0.0005113601800985634
2023-01-21 12:10:58.690400: step: 100/530, loss: 0.0493042953312397
2023-01-21 12:10:59.887131: step: 104/530, loss: 0.02254772186279297
2023-01-21 12:11:01.127185: step: 108/530, loss: 0.04014463350176811
2023-01-21 12:11:02.345373: step: 112/530, loss: 0.006560993380844593
2023-01-21 12:11:03.494950: step: 116/530, loss: 0.023336125537753105
2023-01-21 12:11:04.667203: step: 120/530, loss: 0.0033494948875159025
2023-01-21 12:11:05.862146: step: 124/530, loss: 0.014647483825683594
2023-01-21 12:11:07.032354: step: 128/530, loss: 0.0006462097517214715
2023-01-21 12:11:08.193455: step: 132/530, loss: 0.00549087580293417
2023-01-21 12:11:09.429126: step: 136/530, loss: 0.003354978747665882
2023-01-21 12:11:10.621791: step: 140/530, loss: 0.0038183212745934725
2023-01-21 12:11:11.808305: step: 144/530, loss: 0.014656543731689453
2023-01-21 12:11:12.975405: step: 148/530, loss: 0.03089284896850586
2023-01-21 12:11:14.134702: step: 152/530, loss: 0.00040435791015625
2023-01-21 12:11:15.369326: step: 156/530, loss: 0.05603504553437233
2023-01-21 12:11:16.572306: step: 160/530, loss: 0.002738380338996649
2023-01-21 12:11:17.739264: step: 164/530, loss: 0.008289813995361328
2023-01-21 12:11:18.947040: step: 168/530, loss: 0.02258281782269478
2023-01-21 12:11:20.136010: step: 172/530, loss: 0.01887073554098606
2023-01-21 12:11:21.267003: step: 176/530, loss: 0.0010669901967048645
2023-01-21 12:11:22.401623: step: 180/530, loss: 4.8923491704044864e-05
2023-01-21 12:11:23.596440: step: 184/530, loss: 0.00024056434631347656
2023-01-21 12:11:24.770397: step: 188/530, loss: 0.0003066062927246094
2023-01-21 12:11:25.934045: step: 192/530, loss: 0.00014791489229537547
2023-01-21 12:11:27.120919: step: 196/530, loss: 0.00019302369037177414
2023-01-21 12:11:28.301989: step: 200/530, loss: 0.03316116705536842
2023-01-21 12:11:29.481865: step: 204/530, loss: 0.0014345645904541016
2023-01-21 12:11:30.663692: step: 208/530, loss: 0.024320602416992188
2023-01-21 12:11:31.827525: step: 212/530, loss: 0.5507655739784241
2023-01-21 12:11:33.017508: step: 216/530, loss: 0.01583881489932537
2023-01-21 12:11:34.234951: step: 220/530, loss: 0.001750183175317943
2023-01-21 12:11:35.416253: step: 224/530, loss: 0.027118206024169922
2023-01-21 12:11:36.583286: step: 228/530, loss: 0.0023624422028660774
2023-01-21 12:11:37.813654: step: 232/530, loss: 0.0038647176697850227
2023-01-21 12:11:38.967000: step: 236/530, loss: 0.006709098815917969
2023-01-21 12:11:40.143945: step: 240/530, loss: 0.0038623097352683544
2023-01-21 12:11:41.348300: step: 244/530, loss: 0.011791229248046875
2023-01-21 12:11:42.512055: step: 248/530, loss: 0.002817440079525113
2023-01-21 12:11:43.684639: step: 252/530, loss: 0.024173451587557793
2023-01-21 12:11:44.891738: step: 256/530, loss: 0.5827440619468689
2023-01-21 12:11:46.070555: step: 260/530, loss: 0.005282783415168524
2023-01-21 12:11:47.273097: step: 264/530, loss: 0.003753280732780695
2023-01-21 12:11:48.433235: step: 268/530, loss: 0.003345489501953125
2023-01-21 12:11:49.640442: step: 272/530, loss: 0.010146046057343483
2023-01-21 12:11:50.826004: step: 276/530, loss: 0.0002209663507528603
2023-01-21 12:11:52.008286: step: 280/530, loss: 0.04923315346240997
2023-01-21 12:11:53.160767: step: 284/530, loss: 0.01746654510498047
2023-01-21 12:11:54.358380: step: 288/530, loss: 6.160735938465223e-05
2023-01-21 12:11:55.553583: step: 292/530, loss: 0.026699448004364967
2023-01-21 12:11:56.741430: step: 296/530, loss: 0.17639006674289703
2023-01-21 12:11:57.957978: step: 300/530, loss: 0.07514934241771698
2023-01-21 12:11:59.138886: step: 304/530, loss: 0.003847312880679965
2023-01-21 12:12:00.381739: step: 308/530, loss: 0.08900833129882812
2023-01-21 12:12:01.561891: step: 312/530, loss: 0.021594716235995293
2023-01-21 12:12:02.721825: step: 316/530, loss: 0.013129020109772682
2023-01-21 12:12:03.889802: step: 320/530, loss: 0.031817153096199036
2023-01-21 12:12:05.064789: step: 324/530, loss: 9.72747784544481e-06
2023-01-21 12:12:06.228960: step: 328/530, loss: 0.003936099819839001
2023-01-21 12:12:07.444644: step: 332/530, loss: 0.004711913876235485
2023-01-21 12:12:08.585942: step: 336/530, loss: 0.00019912720017600805
2023-01-21 12:12:09.748241: step: 340/530, loss: 0.012041473761200905
2023-01-21 12:12:10.942176: step: 344/530, loss: 0.2827800512313843
2023-01-21 12:12:12.103181: step: 348/530, loss: 0.026802493259310722
2023-01-21 12:12:13.250271: step: 352/530, loss: 0.0007115363841876388
2023-01-21 12:12:14.428989: step: 356/530, loss: 0.006585312075912952
2023-01-21 12:12:15.643323: step: 360/530, loss: 0.07212667912244797
2023-01-21 12:12:16.879712: step: 364/530, loss: 0.007594108581542969
2023-01-21 12:12:18.069613: step: 368/530, loss: 0.006410980597138405
2023-01-21 12:12:19.258670: step: 372/530, loss: 0.008087086491286755
2023-01-21 12:12:20.449708: step: 376/530, loss: 0.028519250452518463
2023-01-21 12:12:21.641950: step: 380/530, loss: 0.028273582458496094
2023-01-21 12:12:22.837950: step: 384/530, loss: 0.011097913607954979
2023-01-21 12:12:24.009655: step: 388/530, loss: 0.0006882667657919228
2023-01-21 12:12:25.179111: step: 392/530, loss: 0.006953144446015358
2023-01-21 12:12:26.348175: step: 396/530, loss: 0.0012041091686114669
2023-01-21 12:12:27.524890: step: 400/530, loss: 6.66618361719884e-05
2023-01-21 12:12:28.699930: step: 404/530, loss: 5.073547799838707e-05
2023-01-21 12:12:29.821738: step: 408/530, loss: 0.0004280090215615928
2023-01-21 12:12:30.966658: step: 412/530, loss: 2.0265579223632812e-05
2023-01-21 12:12:32.155878: step: 416/530, loss: 0.022930337116122246
2023-01-21 12:12:33.306483: step: 420/530, loss: 0.006448840722441673
2023-01-21 12:12:34.481075: step: 424/530, loss: 0.035825636237859726
2023-01-21 12:12:35.636046: step: 428/530, loss: 3.6239625842426904e-06
2023-01-21 12:12:36.783908: step: 432/530, loss: 0.0040260315872728825
2023-01-21 12:12:37.966599: step: 436/530, loss: 0.0009148597600869834
2023-01-21 12:12:39.143558: step: 440/530, loss: 0.0013803958427160978
2023-01-21 12:12:40.348985: step: 444/530, loss: 0.0010945319663733244
2023-01-21 12:12:41.489300: step: 448/530, loss: 0.08560142666101456
2023-01-21 12:12:42.701855: step: 452/530, loss: 0.00021238328190520406
2023-01-21 12:12:43.931613: step: 456/530, loss: 0.0009457588312216103
2023-01-21 12:12:45.106612: step: 460/530, loss: 7.472038851119578e-05
2023-01-21 12:12:46.301833: step: 464/530, loss: 0.04912886768579483
2023-01-21 12:12:47.471346: step: 468/530, loss: 0.08537034690380096
2023-01-21 12:12:48.638477: step: 472/530, loss: 0.00047364234342239797
2023-01-21 12:12:49.800313: step: 476/530, loss: 0.0024349212180823088
2023-01-21 12:12:50.966836: step: 480/530, loss: 0.0003097534354310483
2023-01-21 12:12:52.162771: step: 484/530, loss: 0.03272075951099396
2023-01-21 12:12:53.348619: step: 488/530, loss: 0.0009326458093710244
2023-01-21 12:12:54.527328: step: 492/530, loss: 0.0007757187122479081
2023-01-21 12:12:55.702952: step: 496/530, loss: 0.04452495649456978
2023-01-21 12:12:56.874577: step: 500/530, loss: 0.004549121949821711
2023-01-21 12:12:58.036332: step: 504/530, loss: 0.008488083258271217
2023-01-21 12:12:59.184719: step: 508/530, loss: 0.08782634139060974
2023-01-21 12:13:00.353499: step: 512/530, loss: 0.009482193738222122
2023-01-21 12:13:01.505359: step: 516/530, loss: 0.0004820823669433594
2023-01-21 12:13:02.712659: step: 520/530, loss: 0.0007883548969402909
2023-01-21 12:13:03.846635: step: 524/530, loss: 0.007688951212912798
2023-01-21 12:13:05.090106: step: 528/530, loss: 0.028808021917939186
2023-01-21 12:13:06.225561: step: 532/530, loss: 0.00036077501135878265
2023-01-21 12:13:07.410461: step: 536/530, loss: 0.000591659510973841
2023-01-21 12:13:08.559197: step: 540/530, loss: 0.00047707557678222656
2023-01-21 12:13:09.779563: step: 544/530, loss: 8.593202073825523e-05
2023-01-21 12:13:10.962311: step: 548/530, loss: -5.53131121705519e-06
2023-01-21 12:13:12.153727: step: 552/530, loss: 0.003246402833610773
2023-01-21 12:13:13.348758: step: 556/530, loss: 0.0013695716625079513
2023-01-21 12:13:14.532753: step: 560/530, loss: 0.019749164581298828
2023-01-21 12:13:15.725974: step: 564/530, loss: 0.007194709964096546
2023-01-21 12:13:16.904646: step: 568/530, loss: 0.03823671489953995
2023-01-21 12:13:18.095185: step: 572/530, loss: 1.9836426872643642e-05
2023-01-21 12:13:19.275597: step: 576/530, loss: 0.00440483121201396
2023-01-21 12:13:20.394248: step: 580/530, loss: 0.009120178408920765
2023-01-21 12:13:21.542524: step: 584/530, loss: 0.011865091510117054
2023-01-21 12:13:22.733207: step: 588/530, loss: 0.00045948027400299907
2023-01-21 12:13:23.904606: step: 592/530, loss: 0.008075332269072533
2023-01-21 12:13:25.100725: step: 596/530, loss: 0.0032255174592137337
2023-01-21 12:13:26.305288: step: 600/530, loss: 0.002500343369320035
2023-01-21 12:13:27.450347: step: 604/530, loss: 0.0057840351946651936
2023-01-21 12:13:28.626662: step: 608/530, loss: 0.0650629997253418
2023-01-21 12:13:29.835923: step: 612/530, loss: 0.0005336761241778731
2023-01-21 12:13:31.028454: step: 616/530, loss: 0.017735673114657402
2023-01-21 12:13:32.191992: step: 620/530, loss: 0.015848923474550247
2023-01-21 12:13:33.353070: step: 624/530, loss: 0.05562668293714523
2023-01-21 12:13:34.538324: step: 628/530, loss: 0.003261327976360917
2023-01-21 12:13:35.741167: step: 632/530, loss: 0.0018414974911138415
2023-01-21 12:13:36.971230: step: 636/530, loss: 0.007472801487892866
2023-01-21 12:13:38.142324: step: 640/530, loss: 0.0008853912586346269
2023-01-21 12:13:39.340715: step: 644/530, loss: 0.0006452560774050653
2023-01-21 12:13:40.534674: step: 648/530, loss: 0.0010772706009447575
2023-01-21 12:13:41.748138: step: 652/530, loss: 5.674362000718247e-06
2023-01-21 12:13:43.003573: step: 656/530, loss: 0.03204202651977539
2023-01-21 12:13:44.156413: step: 660/530, loss: 0.0006127357482910156
2023-01-21 12:13:45.341080: step: 664/530, loss: 0.024794865399599075
2023-01-21 12:13:46.604810: step: 668/530, loss: 0.025270653888583183
2023-01-21 12:13:47.826101: step: 672/530, loss: 0.006105613894760609
2023-01-21 12:13:48.998418: step: 676/530, loss: 0.000266599643509835
2023-01-21 12:13:50.185163: step: 680/530, loss: 0.00750236539170146
2023-01-21 12:13:51.349517: step: 684/530, loss: 0.0028096199966967106
2023-01-21 12:13:52.518998: step: 688/530, loss: 0.0007131576421670616
2023-01-21 12:13:53.684432: step: 692/530, loss: 0.011946440674364567
2023-01-21 12:13:54.909141: step: 696/530, loss: 0.0083770751953125
2023-01-21 12:13:56.100189: step: 700/530, loss: 0.0035104751586914062
2023-01-21 12:13:57.292387: step: 704/530, loss: 0.003795719239860773
2023-01-21 12:13:58.478282: step: 708/530, loss: 0.00023136139498092234
2023-01-21 12:13:59.645132: step: 712/530, loss: 0.03469734266400337
2023-01-21 12:14:00.843055: step: 716/530, loss: 2.9659271604032256e-05
2023-01-21 12:14:02.008217: step: 720/530, loss: 0.06569528579711914
2023-01-21 12:14:03.146643: step: 724/530, loss: 0.003808403154835105
2023-01-21 12:14:04.336967: step: 728/530, loss: 0.008320235647261143
2023-01-21 12:14:05.532830: step: 732/530, loss: 0.13509120047092438
2023-01-21 12:14:06.749673: step: 736/530, loss: 0.006180953700095415
2023-01-21 12:14:07.896081: step: 740/530, loss: 0.005294227506965399
2023-01-21 12:14:09.064529: step: 744/530, loss: 0.06433287262916565
2023-01-21 12:14:10.233347: step: 748/530, loss: 0.013258743099868298
2023-01-21 12:14:11.392457: step: 752/530, loss: 0.008850479498505592
2023-01-21 12:14:12.582524: step: 756/530, loss: 0.01265049073845148
2023-01-21 12:14:13.752509: step: 760/530, loss: 0.08736009150743484
2023-01-21 12:14:14.924904: step: 764/530, loss: 0.0016738891135901213
2023-01-21 12:14:16.062504: step: 768/530, loss: 0.02806701697409153
2023-01-21 12:14:17.260985: step: 772/530, loss: 0.009701776318252087
2023-01-21 12:14:18.435364: step: 776/530, loss: 0.053648948669433594
2023-01-21 12:14:19.590716: step: 780/530, loss: 0.027636529877781868
2023-01-21 12:14:20.824081: step: 784/530, loss: 0.002396202180534601
2023-01-21 12:14:21.981515: step: 788/530, loss: 0.025104140862822533
2023-01-21 12:14:23.158735: step: 792/530, loss: 2.055168260994833e-05
2023-01-21 12:14:24.332133: step: 796/530, loss: 0.0004852295096497983
2023-01-21 12:14:25.479247: step: 800/530, loss: 0.021076299250125885
2023-01-21 12:14:26.647994: step: 804/530, loss: 0.00682754535228014
2023-01-21 12:14:27.812963: step: 808/530, loss: 0.037038229405879974
2023-01-21 12:14:29.022290: step: 812/530, loss: 0.01936950720846653
2023-01-21 12:14:30.232388: step: 816/530, loss: 0.020950699225068092
2023-01-21 12:14:31.396594: step: 820/530, loss: 0.002401161240413785
2023-01-21 12:14:32.574181: step: 824/530, loss: 0.038561251014471054
2023-01-21 12:14:33.774246: step: 828/530, loss: 0.013357257470488548
2023-01-21 12:14:34.911786: step: 832/530, loss: 3.6907196772517636e-05
2023-01-21 12:14:36.073459: step: 836/530, loss: 0.0016307830810546875
2023-01-21 12:14:37.250274: step: 840/530, loss: 0.012838936410844326
2023-01-21 12:14:38.447957: step: 844/530, loss: 0.00908727664500475
2023-01-21 12:14:39.595715: step: 848/530, loss: 0.00014972686767578125
2023-01-21 12:14:40.838542: step: 852/530, loss: 0.012853623367846012
2023-01-21 12:14:42.037681: step: 856/530, loss: 0.03035755082964897
2023-01-21 12:14:43.215248: step: 860/530, loss: 0.004576778504997492
2023-01-21 12:14:44.443070: step: 864/530, loss: 0.010898018255829811
2023-01-21 12:14:45.639043: step: 868/530, loss: 0.0003510475216899067
2023-01-21 12:14:46.800509: step: 872/530, loss: 0.00162172329146415
2023-01-21 12:14:48.003602: step: 876/530, loss: 0.015260887332260609
2023-01-21 12:14:49.196640: step: 880/530, loss: 0.007266998756676912
2023-01-21 12:14:50.353777: step: 884/530, loss: 0.030022908002138138
2023-01-21 12:14:51.518939: step: 888/530, loss: 0.030643461272120476
2023-01-21 12:14:52.693906: step: 892/530, loss: 0.008118057623505592
2023-01-21 12:14:53.876734: step: 896/530, loss: 0.006501388736069202
2023-01-21 12:14:55.082541: step: 900/530, loss: 0.00011749268014682457
2023-01-21 12:14:56.257730: step: 904/530, loss: 0.017227554693818092
2023-01-21 12:14:57.429702: step: 908/530, loss: 0.0004072189622092992
2023-01-21 12:14:58.579139: step: 912/530, loss: 0.023754358291625977
2023-01-21 12:14:59.734087: step: 916/530, loss: 2.6035308110294864e-05
2023-01-21 12:15:00.935618: step: 920/530, loss: 0.003057861467823386
2023-01-21 12:15:02.094375: step: 924/530, loss: 0.0198122039437294
2023-01-21 12:15:03.277804: step: 928/530, loss: 0.013790702447295189
2023-01-21 12:15:04.471439: step: 932/530, loss: 0.019167518243193626
2023-01-21 12:15:05.632615: step: 936/530, loss: 0.00020608902559615672
2023-01-21 12:15:06.815048: step: 940/530, loss: 0.025532031431794167
2023-01-21 12:15:07.960521: step: 944/530, loss: 0.0013461114140227437
2023-01-21 12:15:09.150834: step: 948/530, loss: 0.008386611938476562
2023-01-21 12:15:10.345233: step: 952/530, loss: 0.0004618644597940147
2023-01-21 12:15:11.500623: step: 956/530, loss: 0.005612373352050781
2023-01-21 12:15:12.683405: step: 960/530, loss: 7.104873475327622e-06
2023-01-21 12:15:13.895809: step: 964/530, loss: 0.021570492535829544
2023-01-21 12:15:15.108173: step: 968/530, loss: 5.8746340073412284e-05
2023-01-21 12:15:16.319492: step: 972/530, loss: 0.07768039405345917
2023-01-21 12:15:17.481898: step: 976/530, loss: 0.1064678207039833
2023-01-21 12:15:18.735676: step: 980/530, loss: 0.02261219173669815
2023-01-21 12:15:19.935408: step: 984/530, loss: 0.048804618418216705
2023-01-21 12:15:21.089959: step: 988/530, loss: 0.006248092278838158
2023-01-21 12:15:22.259098: step: 992/530, loss: 0.0010195731883868575
2023-01-21 12:15:23.439794: step: 996/530, loss: 0.07508783787488937
2023-01-21 12:15:24.590692: step: 1000/530, loss: 5.722046125811175e-07
2023-01-21 12:15:25.790912: step: 1004/530, loss: 4.091262962901965e-05
2023-01-21 12:15:26.996694: step: 1008/530, loss: 0.02834959141910076
2023-01-21 12:15:28.174296: step: 1012/530, loss: 9.307861182605848e-05
2023-01-21 12:15:29.339224: step: 1016/530, loss: 0.0012316703796386719
2023-01-21 12:15:30.496503: step: 1020/530, loss: 0.009230202995240688
2023-01-21 12:15:31.673996: step: 1024/530, loss: 0.006628227420151234
2023-01-21 12:15:32.885457: step: 1028/530, loss: 0.03822221979498863
2023-01-21 12:15:34.032114: step: 1032/530, loss: 0.0041792867705225945
2023-01-21 12:15:35.228591: step: 1036/530, loss: 0.008895493112504482
2023-01-21 12:15:36.419243: step: 1040/530, loss: 0.0030621530022472143
2023-01-21 12:15:37.587230: step: 1044/530, loss: 0.016025353223085403
2023-01-21 12:15:38.752790: step: 1048/530, loss: 0.008230209350585938
2023-01-21 12:15:39.964826: step: 1052/530, loss: 0.0006102562183514237
2023-01-21 12:15:41.105550: step: 1056/530, loss: 2.6893614631262608e-05
2023-01-21 12:15:42.307403: step: 1060/530, loss: 0.011555385775864124
2023-01-21 12:15:43.461872: step: 1064/530, loss: 9.250640869140625e-05
2023-01-21 12:15:44.623843: step: 1068/530, loss: 0.0006545067299157381
2023-01-21 12:15:45.823848: step: 1072/530, loss: 0.0007943630334921181
2023-01-21 12:15:46.964841: step: 1076/530, loss: 0.028077127411961555
2023-01-21 12:15:48.159309: step: 1080/530, loss: 0.015691090375185013
2023-01-21 12:15:49.336748: step: 1084/530, loss: 0.00042181016760878265
2023-01-21 12:15:50.505066: step: 1088/530, loss: 0.002599430037662387
2023-01-21 12:15:51.693095: step: 1092/530, loss: 0.0004177093505859375
2023-01-21 12:15:52.866328: step: 1096/530, loss: 0.0009422302828170359
2023-01-21 12:15:54.050940: step: 1100/530, loss: 0.005600595846772194
2023-01-21 12:15:55.200959: step: 1104/530, loss: 0.0012667656410485506
2023-01-21 12:15:56.378322: step: 1108/530, loss: 0.057733204215765
2023-01-21 12:15:57.568731: step: 1112/530, loss: 0.013042068108916283
2023-01-21 12:15:58.734532: step: 1116/530, loss: 0.038478996604681015
2023-01-21 12:15:59.940818: step: 1120/530, loss: 0.0031649114098399878
2023-01-21 12:16:01.160897: step: 1124/530, loss: 0.00018358232046011835
2023-01-21 12:16:02.332983: step: 1128/530, loss: 0.00019969939603470266
2023-01-21 12:16:03.540081: step: 1132/530, loss: 1.869201696536038e-05
2023-01-21 12:16:04.713794: step: 1136/530, loss: 0.04739074781537056
2023-01-21 12:16:05.926196: step: 1140/530, loss: 0.014592265710234642
2023-01-21 12:16:07.086786: step: 1144/530, loss: 0.00036449433537200093
2023-01-21 12:16:08.244950: step: 1148/530, loss: 0.0008961677667684853
2023-01-21 12:16:09.426543: step: 1152/530, loss: 0.007920980453491211
2023-01-21 12:16:10.588340: step: 1156/530, loss: 0.007328605744987726
2023-01-21 12:16:11.758620: step: 1160/530, loss: 0.0293426513671875
2023-01-21 12:16:12.972677: step: 1164/530, loss: 0.019978905096650124
2023-01-21 12:16:14.139712: step: 1168/530, loss: 0.00258979806676507
2023-01-21 12:16:15.312115: step: 1172/530, loss: 0.03161735460162163
2023-01-21 12:16:16.465625: step: 1176/530, loss: 0.004947376437485218
2023-01-21 12:16:17.612250: step: 1180/530, loss: 0.00047860146150924265
2023-01-21 12:16:18.754793: step: 1184/530, loss: 0.0007875442388467491
2023-01-21 12:16:19.912203: step: 1188/530, loss: 0.004349708557128906
2023-01-21 12:16:21.087285: step: 1192/530, loss: 0.0018177032470703125
2023-01-21 12:16:22.282178: step: 1196/530, loss: 0.0017662049503996968
2023-01-21 12:16:23.436223: step: 1200/530, loss: 0.003905773162841797
2023-01-21 12:16:24.562921: step: 1204/530, loss: 0.003988456912338734
2023-01-21 12:16:25.778455: step: 1208/530, loss: 0.0016990661388263106
2023-01-21 12:16:26.948477: step: 1212/530, loss: 0.0002038955717580393
2023-01-21 12:16:28.138396: step: 1216/530, loss: 0.0037208558060228825
2023-01-21 12:16:29.309783: step: 1220/530, loss: 0.00017161370487883687
2023-01-21 12:16:30.539263: step: 1224/530, loss: 0.0182023998349905
2023-01-21 12:16:31.708559: step: 1228/530, loss: 0.020683765411376953
2023-01-21 12:16:32.870718: step: 1232/530, loss: 0.008129501715302467
2023-01-21 12:16:34.031325: step: 1236/530, loss: 0.008852005936205387
2023-01-21 12:16:35.205233: step: 1240/530, loss: 0.02244281768798828
2023-01-21 12:16:36.344481: step: 1244/530, loss: 0.04608936235308647
2023-01-21 12:16:37.525575: step: 1248/530, loss: 0.0015254972968250513
2023-01-21 12:16:38.706472: step: 1252/530, loss: 0.007021427154541016
2023-01-21 12:16:39.921054: step: 1256/530, loss: 0.0054569244384765625
2023-01-21 12:16:41.122151: step: 1260/530, loss: 0.00021114348783157766
2023-01-21 12:16:42.322376: step: 1264/530, loss: 0.007398843765258789
2023-01-21 12:16:43.475590: step: 1268/530, loss: 0.00024337768263649195
2023-01-21 12:16:44.644093: step: 1272/530, loss: 0.00011262894258834422
2023-01-21 12:16:45.830223: step: 1276/530, loss: 0.0491454154253006
2023-01-21 12:16:47.048455: step: 1280/530, loss: 0.0002900123945437372
2023-01-21 12:16:48.185619: step: 1284/530, loss: 0.012590598315000534
2023-01-21 12:16:49.381194: step: 1288/530, loss: 0.18321160972118378
2023-01-21 12:16:50.553905: step: 1292/530, loss: 0.020140647888183594
2023-01-21 12:16:51.731794: step: 1296/530, loss: 0.03394355624914169
2023-01-21 12:16:52.906992: step: 1300/530, loss: 2.3460386728402227e-05
2023-01-21 12:16:54.070915: step: 1304/530, loss: 0.06991196423768997
2023-01-21 12:16:55.280402: step: 1308/530, loss: 0.021816732361912727
2023-01-21 12:16:56.468009: step: 1312/530, loss: 0.009323501028120518
2023-01-21 12:16:57.633937: step: 1316/530, loss: 0.022315694019198418
2023-01-21 12:16:58.804416: step: 1320/530, loss: 0.0010746002662926912
2023-01-21 12:16:59.991913: step: 1324/530, loss: 0.0009769439930096269
2023-01-21 12:17:01.108550: step: 1328/530, loss: 0.0003716468927450478
2023-01-21 12:17:02.407823: step: 1332/530, loss: 0.0005878448719158769
2023-01-21 12:17:03.593554: step: 1336/530, loss: 0.005566311068832874
2023-01-21 12:17:04.782945: step: 1340/530, loss: 0.02081451378762722
2023-01-21 12:17:05.968687: step: 1344/530, loss: 0.0004314422549214214
2023-01-21 12:17:07.140152: step: 1348/530, loss: 0.05808582156896591
2023-01-21 12:17:08.334587: step: 1352/530, loss: 7.023811485851184e-05
2023-01-21 12:17:09.519748: step: 1356/530, loss: 0.005383777432143688
2023-01-21 12:17:10.656753: step: 1360/530, loss: 0.00406837509945035
2023-01-21 12:17:11.832945: step: 1364/530, loss: 0.015238761901855469
2023-01-21 12:17:13.006267: step: 1368/530, loss: 0.10889206826686859
2023-01-21 12:17:14.179906: step: 1372/530, loss: 0.009109783917665482
2023-01-21 12:17:15.360528: step: 1376/530, loss: 0.0020843506790697575
2023-01-21 12:17:16.516030: step: 1380/530, loss: 0.013313103467226028
2023-01-21 12:17:17.693502: step: 1384/530, loss: 0.061997320502996445
2023-01-21 12:17:18.908299: step: 1388/530, loss: 0.018683088943362236
2023-01-21 12:17:20.050646: step: 1392/530, loss: 0.008904362097382545
2023-01-21 12:17:21.229614: step: 1396/530, loss: 0.01609659194946289
2023-01-21 12:17:22.444714: step: 1400/530, loss: 0.0019936561584472656
2023-01-21 12:17:23.648182: step: 1404/530, loss: 0.0008223534096032381
2023-01-21 12:17:24.828022: step: 1408/530, loss: 0.011760997585952282
2023-01-21 12:17:25.970499: step: 1412/530, loss: 0.00026607513427734375
2023-01-21 12:17:27.172357: step: 1416/530, loss: 0.017190933227539062
2023-01-21 12:17:28.340526: step: 1420/530, loss: 0.08052539825439453
2023-01-21 12:17:29.500640: step: 1424/530, loss: 0.0015691757434979081
2023-01-21 12:17:30.670472: step: 1428/530, loss: 0.01707172580063343
2023-01-21 12:17:31.846069: step: 1432/530, loss: 0.000419425981817767
2023-01-21 12:17:33.005110: step: 1436/530, loss: 0.0001367092045256868
2023-01-21 12:17:34.183562: step: 1440/530, loss: 0.008555039763450623
2023-01-21 12:17:35.378725: step: 1444/530, loss: 0.026746369898319244
2023-01-21 12:17:36.568382: step: 1448/530, loss: 0.015646720305085182
2023-01-21 12:17:37.771334: step: 1452/530, loss: 0.05076298862695694
2023-01-21 12:17:38.965441: step: 1456/530, loss: 0.4115432798862457
2023-01-21 12:17:40.112043: step: 1460/530, loss: 0.00010528565326239914
2023-01-21 12:17:41.318019: step: 1464/530, loss: 1.65043044090271
2023-01-21 12:17:42.515590: step: 1468/530, loss: 0.000682449375744909
2023-01-21 12:17:43.723548: step: 1472/530, loss: 0.0018374442588537931
2023-01-21 12:17:44.963848: step: 1476/530, loss: 0.0004932403680868447
2023-01-21 12:17:46.135862: step: 1480/530, loss: 8.60214204294607e-05
2023-01-21 12:17:47.312131: step: 1484/530, loss: 0.011019039899110794
2023-01-21 12:17:48.510890: step: 1488/530, loss: 0.06644248217344284
2023-01-21 12:17:49.676319: step: 1492/530, loss: 0.0017852783203125
2023-01-21 12:17:50.851294: step: 1496/530, loss: 0.007105064578354359
2023-01-21 12:17:51.984735: step: 1500/530, loss: 5.254745337879285e-05
2023-01-21 12:17:53.150913: step: 1504/530, loss: 0.0010986328125
2023-01-21 12:17:54.326145: step: 1508/530, loss: 0.00033750536385923624
2023-01-21 12:17:55.496949: step: 1512/530, loss: 0.005956745240837336
2023-01-21 12:17:56.679018: step: 1516/530, loss: 0.00362224574200809
2023-01-21 12:17:57.831649: step: 1520/530, loss: 9.946823411155492e-05
2023-01-21 12:17:59.016242: step: 1524/530, loss: 0.027692366391420364
2023-01-21 12:18:00.175212: step: 1528/530, loss: 0.020485782995820045
2023-01-21 12:18:01.350000: step: 1532/530, loss: 6.790161569369957e-05
2023-01-21 12:18:02.510378: step: 1536/530, loss: 0.01285934541374445
2023-01-21 12:18:03.703067: step: 1540/530, loss: 0.0024919509887695312
2023-01-21 12:18:04.882367: step: 1544/530, loss: 0.009604454040527344
2023-01-21 12:18:06.068812: step: 1548/530, loss: 0.0012637138133868575
2023-01-21 12:18:07.245096: step: 1552/530, loss: 0.006312465760856867
2023-01-21 12:18:08.414586: step: 1556/530, loss: 0.0005198002327233553
2023-01-21 12:18:09.581336: step: 1560/530, loss: 0.001466464949771762
2023-01-21 12:18:10.730566: step: 1564/530, loss: 0.05649099498987198
2023-01-21 12:18:11.871162: step: 1568/530, loss: 0.004805660340934992
2023-01-21 12:18:13.045373: step: 1572/530, loss: 0.0033572197426110506
2023-01-21 12:18:14.223229: step: 1576/530, loss: 0.019612504169344902
2023-01-21 12:18:15.366967: step: 1580/530, loss: 0.013346290215849876
2023-01-21 12:18:16.538438: step: 1584/530, loss: 0.018196679651737213
2023-01-21 12:18:17.749667: step: 1588/530, loss: 0.002219676971435547
2023-01-21 12:18:18.910732: step: 1592/530, loss: 0.06623125076293945
2023-01-21 12:18:20.071367: step: 1596/530, loss: 0.020299913361668587
2023-01-21 12:18:21.253417: step: 1600/530, loss: 0.0023983002174645662
2023-01-21 12:18:22.414478: step: 1604/530, loss: 0.0004515647888183594
2023-01-21 12:18:23.600669: step: 1608/530, loss: 0.009576797485351562
2023-01-21 12:18:24.836909: step: 1612/530, loss: 0.0004172325134277344
2023-01-21 12:18:26.062393: step: 1616/530, loss: 0.045198824256658554
2023-01-21 12:18:27.247008: step: 1620/530, loss: 0.001467204187065363
2023-01-21 12:18:28.446027: step: 1624/530, loss: 2.517700158932712e-05
2023-01-21 12:18:29.625839: step: 1628/530, loss: 0.0011226654751226306
2023-01-21 12:18:30.803013: step: 1632/530, loss: 0.0025594711769372225
2023-01-21 12:18:31.969626: step: 1636/530, loss: 0.09730224311351776
2023-01-21 12:18:33.179592: step: 1640/530, loss: 0.03456687927246094
2023-01-21 12:18:34.335996: step: 1644/530, loss: 1.4400482541532256e-05
2023-01-21 12:18:35.498793: step: 1648/530, loss: 0.005744457244873047
2023-01-21 12:18:36.666587: step: 1652/530, loss: 0.12579460442066193
2023-01-21 12:18:37.869004: step: 1656/530, loss: 0.007267761509865522
2023-01-21 12:18:39.065134: step: 1660/530, loss: 0.06963996589183807
2023-01-21 12:18:40.246236: step: 1664/530, loss: 0.022086717188358307
2023-01-21 12:18:41.408208: step: 1668/530, loss: 0.0005795002216473222
2023-01-21 12:18:42.598587: step: 1672/530, loss: 0.1747472733259201
2023-01-21 12:18:43.797222: step: 1676/530, loss: 0.10909853875637054
2023-01-21 12:18:45.022303: step: 1680/530, loss: 0.04020848125219345
2023-01-21 12:18:46.185410: step: 1684/530, loss: 0.002763891126960516
2023-01-21 12:18:47.350597: step: 1688/530, loss: 0.00013256072998046875
2023-01-21 12:18:48.506123: step: 1692/530, loss: 0.0007474899757653475
2023-01-21 12:18:49.690720: step: 1696/530, loss: 0.08283176273107529
2023-01-21 12:18:50.898476: step: 1700/530, loss: 0.02291278727352619
2023-01-21 12:18:52.124354: step: 1704/530, loss: 0.01754322089254856
2023-01-21 12:18:53.294280: step: 1708/530, loss: 0.00372142787091434
2023-01-21 12:18:54.447875: step: 1712/530, loss: 0.01638164557516575
2023-01-21 12:18:55.652914: step: 1716/530, loss: 0.020516490563750267
2023-01-21 12:18:56.815918: step: 1720/530, loss: 0.0001412391575286165
2023-01-21 12:18:58.014348: step: 1724/530, loss: 0.041799817234277725
2023-01-21 12:18:59.183110: step: 1728/530, loss: 0.005722093395888805
2023-01-21 12:19:00.393501: step: 1732/530, loss: 0.6590420007705688
2023-01-21 12:19:01.581646: step: 1736/530, loss: 0.033585548400878906
2023-01-21 12:19:02.757757: step: 1740/530, loss: 0.12217274308204651
2023-01-21 12:19:03.943728: step: 1744/530, loss: 5.2988529205322266e-05
2023-01-21 12:19:05.095372: step: 1748/530, loss: 0.035793498158454895
2023-01-21 12:19:06.287589: step: 1752/530, loss: 0.0636606216430664
2023-01-21 12:19:07.438428: step: 1756/530, loss: 0.006601619999855757
2023-01-21 12:19:08.636857: step: 1760/530, loss: 0.00021650790586136281
2023-01-21 12:19:09.812573: step: 1764/530, loss: 0.0004972219467163086
2023-01-21 12:19:11.064586: step: 1768/530, loss: 0.043898582458496094
2023-01-21 12:19:12.227962: step: 1772/530, loss: 0.06102113798260689
2023-01-21 12:19:13.360280: step: 1776/530, loss: 0.00043125153752043843
2023-01-21 12:19:14.527670: step: 1780/530, loss: 0.0008471012115478516
2023-01-21 12:19:15.694363: step: 1784/530, loss: 0.03125715255737305
2023-01-21 12:19:16.862870: step: 1788/530, loss: 0.007453442085534334
2023-01-21 12:19:18.087082: step: 1792/530, loss: 0.06212577968835831
2023-01-21 12:19:19.288434: step: 1796/530, loss: 0.001355934189632535
2023-01-21 12:19:20.455327: step: 1800/530, loss: 0.011693191714584827
2023-01-21 12:19:21.609412: step: 1804/530, loss: 0.16507187485694885
2023-01-21 12:19:22.778339: step: 1808/530, loss: 0.0025229454040527344
2023-01-21 12:19:23.985485: step: 1812/530, loss: 0.003869295120239258
2023-01-21 12:19:25.175493: step: 1816/530, loss: 0.009980487637221813
2023-01-21 12:19:26.373845: step: 1820/530, loss: 0.0013246536254882812
2023-01-21 12:19:27.568233: step: 1824/530, loss: 0.0005734444130212069
2023-01-21 12:19:28.782169: step: 1828/530, loss: 0.004064178094267845
2023-01-21 12:19:29.933464: step: 1832/530, loss: 0.05234880745410919
2023-01-21 12:19:31.092724: step: 1836/530, loss: 0.004139041993767023
2023-01-21 12:19:32.244478: step: 1840/530, loss: 0.00028662680415436625
2023-01-21 12:19:33.448594: step: 1844/530, loss: 0.16543789207935333
2023-01-21 12:19:34.632257: step: 1848/530, loss: 0.0007221221458166838
2023-01-21 12:19:35.894878: step: 1852/530, loss: 0.013888930901885033
2023-01-21 12:19:37.075984: step: 1856/530, loss: 0.007541084196418524
2023-01-21 12:19:38.297173: step: 1860/530, loss: 0.010792732238769531
2023-01-21 12:19:39.495699: step: 1864/530, loss: 0.006150341127067804
2023-01-21 12:19:40.683856: step: 1868/530, loss: 0.7755119204521179
2023-01-21 12:19:41.876308: step: 1872/530, loss: 0.008628464303910732
2023-01-21 12:19:43.018481: step: 1876/530, loss: 0.0010536194313317537
2023-01-21 12:19:44.196943: step: 1880/530, loss: 0.003494834993034601
2023-01-21 12:19:45.350311: step: 1884/530, loss: 7.61032133596018e-05
2023-01-21 12:19:46.521222: step: 1888/530, loss: 0.008405113592743874
2023-01-21 12:19:47.688008: step: 1892/530, loss: 0.00044484136742539704
2023-01-21 12:19:48.879560: step: 1896/530, loss: 0.021352767944335938
2023-01-21 12:19:50.064527: step: 1900/530, loss: 0.0013708114856854081
2023-01-21 12:19:51.232230: step: 1904/530, loss: 0.0006736755603924394
2023-01-21 12:19:52.409522: step: 1908/530, loss: 0.00013999939255882055
2023-01-21 12:19:53.536531: step: 1912/530, loss: 0.013002777472138405
2023-01-21 12:19:54.725403: step: 1916/530, loss: 0.004801368806511164
2023-01-21 12:19:55.923697: step: 1920/530, loss: 0.04571075364947319
2023-01-21 12:19:57.076123: step: 1924/530, loss: 0.00974273681640625
2023-01-21 12:19:58.272439: step: 1928/530, loss: 0.09742498397827148
2023-01-21 12:19:59.494891: step: 1932/530, loss: 0.05283212661743164
2023-01-21 12:20:00.672220: step: 1936/530, loss: 0.0009844780433923006
2023-01-21 12:20:01.847527: step: 1940/530, loss: 0.0005422591930255294
2023-01-21 12:20:02.998544: step: 1944/530, loss: 1.049041748046875e-05
2023-01-21 12:20:04.171635: step: 1948/530, loss: 0.00788955669850111
2023-01-21 12:20:05.368796: step: 1952/530, loss: 0.0006093978881835938
2023-01-21 12:20:06.556569: step: 1956/530, loss: 0.01922302320599556
2023-01-21 12:20:07.711640: step: 1960/530, loss: 0.01354312989860773
2023-01-21 12:20:08.858359: step: 1964/530, loss: 0.0006777763483114541
2023-01-21 12:20:10.012351: step: 1968/530, loss: 0.011162662878632545
2023-01-21 12:20:11.187352: step: 1972/530, loss: 0.013269996270537376
2023-01-21 12:20:12.401098: step: 1976/530, loss: 0.01797962374985218
2023-01-21 12:20:13.544276: step: 1980/530, loss: 0.020705606788396835
2023-01-21 12:20:14.739656: step: 1984/530, loss: 0.0014919281238690019
2023-01-21 12:20:15.903418: step: 1988/530, loss: 0.0012494086986407638
2023-01-21 12:20:17.103628: step: 1992/530, loss: 0.00022964477830100805
2023-01-21 12:20:18.251075: step: 1996/530, loss: 0.08007641136646271
2023-01-21 12:20:19.452113: step: 2000/530, loss: 9.603500802768394e-05
2023-01-21 12:20:20.641996: step: 2004/530, loss: 0.005882644560188055
2023-01-21 12:20:21.837026: step: 2008/530, loss: 0.001674652099609375
2023-01-21 12:20:23.052702: step: 2012/530, loss: 0.3758220672607422
2023-01-21 12:20:24.211796: step: 2016/530, loss: 0.04876318201422691
2023-01-21 12:20:25.421197: step: 2020/530, loss: 0.0038507464341819286
2023-01-21 12:20:26.583991: step: 2024/530, loss: 0.06845073401927948
2023-01-21 12:20:27.724261: step: 2028/530, loss: 0.002036666963249445
2023-01-21 12:20:28.926139: step: 2032/530, loss: 0.024755287915468216
2023-01-21 12:20:30.101493: step: 2036/530, loss: 0.0005062103155069053
2023-01-21 12:20:31.283724: step: 2040/530, loss: 0.00430984515696764
2023-01-21 12:20:32.479169: step: 2044/530, loss: 0.02907733991742134
2023-01-21 12:20:33.611792: step: 2048/530, loss: 1.754760705807712e-05
2023-01-21 12:20:34.770271: step: 2052/530, loss: 0.0004219055117573589
2023-01-21 12:20:35.969354: step: 2056/530, loss: 0.03699970245361328
2023-01-21 12:20:37.142689: step: 2060/530, loss: 0.01606121100485325
2023-01-21 12:20:38.326194: step: 2064/530, loss: 0.05028242990374565
2023-01-21 12:20:39.501940: step: 2068/530, loss: 0.006548118777573109
2023-01-21 12:20:40.667126: step: 2072/530, loss: 0.0005677699809893966
2023-01-21 12:20:41.865401: step: 2076/530, loss: 0.0325685515999794
2023-01-21 12:20:43.073058: step: 2080/530, loss: 0.004090690519660711
2023-01-21 12:20:44.233499: step: 2084/530, loss: 0.2901313900947571
2023-01-21 12:20:45.448637: step: 2088/530, loss: 0.0026451589073985815
2023-01-21 12:20:46.645474: step: 2092/530, loss: 0.00032224657479673624
2023-01-21 12:20:47.814894: step: 2096/530, loss: 1.0603395700454712
2023-01-21 12:20:48.980005: step: 2100/530, loss: 0.05462236329913139
2023-01-21 12:20:50.208346: step: 2104/530, loss: 0.0004228711186442524
2023-01-21 12:20:51.357716: step: 2108/530, loss: 0.1792866289615631
2023-01-21 12:20:52.536932: step: 2112/530, loss: 0.023072529584169388
2023-01-21 12:20:53.671415: step: 2116/530, loss: 0.00445899972692132
2023-01-21 12:20:54.842901: step: 2120/530, loss: 0.00666046142578125
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.576271186440678, 'r': 0.7696404793608522, 'f1': 0.6590649942987458}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6543778801843319, 'r': 0.816561242093157, 'f1': 0.7265285239191609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5652173913043478, 'r': 0.9629629629629629, 'f1': 0.7123287671232876}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.576271186440678, 'r': 0.5396825396825397, 'f1': 0.5573770491803278}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.32, 'r': 0.4444444444444444, 'f1': 0.37209302325581395}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 12:21:38.303185: step: 4/530, loss: 0.00022544861712958664
2023-01-21 12:21:39.508853: step: 8/530, loss: 0.00010385513451183215
2023-01-21 12:21:40.653063: step: 12/530, loss: 0.004794311709702015
2023-01-21 12:21:41.875651: step: 16/530, loss: 0.03369102254509926
2023-01-21 12:21:43.030541: step: 20/530, loss: 0.0003787994501180947
2023-01-21 12:21:44.203234: step: 24/530, loss: 0.0006971359252929688
2023-01-21 12:21:45.363127: step: 28/530, loss: 0.015932369977235794
2023-01-21 12:21:46.571671: step: 32/530, loss: 0.00010662078420864418
2023-01-21 12:21:47.773511: step: 36/530, loss: 0.00012683868408203125
2023-01-21 12:21:48.960029: step: 40/530, loss: 0.00041790009709075093
2023-01-21 12:21:50.126218: step: 44/530, loss: 0.002053546952083707
2023-01-21 12:21:51.316861: step: 48/530, loss: 0.03153686597943306
2023-01-21 12:21:52.512985: step: 52/530, loss: 0.00965042132884264
2023-01-21 12:21:53.691843: step: 56/530, loss: 0.0003934860578738153
2023-01-21 12:21:54.899594: step: 60/530, loss: 0.0003167152754031122
2023-01-21 12:21:56.091704: step: 64/530, loss: 0.0008425712585449219
2023-01-21 12:21:57.300427: step: 68/530, loss: 0.0015649795532226562
2023-01-21 12:21:58.468935: step: 72/530, loss: 0.00030832289485260844
2023-01-21 12:21:59.631369: step: 76/530, loss: 0.001506805419921875
2023-01-21 12:22:00.845882: step: 80/530, loss: 0.00019693374633789062
2023-01-21 12:22:02.011040: step: 84/530, loss: 0.00872650183737278
2023-01-21 12:22:03.166729: step: 88/530, loss: 0.032575178891420364
2023-01-21 12:22:04.320907: step: 92/530, loss: 0.00780487060546875
2023-01-21 12:22:05.502283: step: 96/530, loss: 7.290840585483238e-05
2023-01-21 12:22:06.655583: step: 100/530, loss: -1.9073486328125e-06
2023-01-21 12:22:07.788168: step: 104/530, loss: 0.0010035515297204256
2023-01-21 12:22:08.968434: step: 108/530, loss: 0.41664770245552063
2023-01-21 12:22:10.156612: step: 112/530, loss: 0.021617509424686432
2023-01-21 12:22:11.341357: step: 116/530, loss: 0.008367538452148438
2023-01-21 12:22:12.528290: step: 120/530, loss: 0.04301929473876953
2023-01-21 12:22:13.696614: step: 124/530, loss: 0.0036594390403479338
2023-01-21 12:22:14.879743: step: 128/530, loss: 0.002813148545101285
2023-01-21 12:22:16.042342: step: 132/530, loss: 0.07530871033668518
2023-01-21 12:22:17.204370: step: 136/530, loss: 0.2991907000541687
2023-01-21 12:22:18.427115: step: 140/530, loss: 0.0011005401611328125
2023-01-21 12:22:19.601647: step: 144/530, loss: 0.00027327536372467875
2023-01-21 12:22:20.770468: step: 148/530, loss: 0.0002777099725790322
2023-01-21 12:22:21.941112: step: 152/530, loss: 0.0033702850341796875
2023-01-21 12:22:23.098077: step: 156/530, loss: 0.00286960625089705
2023-01-21 12:22:24.309667: step: 160/530, loss: 0.004630756564438343
2023-01-21 12:22:25.453822: step: 164/530, loss: 0.006375408265739679
2023-01-21 12:22:26.624151: step: 168/530, loss: 0.0008205414051190019
2023-01-21 12:22:27.804952: step: 172/530, loss: 0.010860252194106579
2023-01-21 12:22:28.973448: step: 176/530, loss: 0.0017423630924895406
2023-01-21 12:22:30.193598: step: 180/530, loss: 0.06566419452428818
2023-01-21 12:22:31.386638: step: 184/530, loss: 0.004422569647431374
2023-01-21 12:22:32.529733: step: 188/530, loss: 0.0034994124434888363
2023-01-21 12:22:33.730750: step: 192/530, loss: 0.017185211181640625
2023-01-21 12:22:34.911571: step: 196/530, loss: 0.013257408514618874
2023-01-21 12:22:36.043181: step: 200/530, loss: 0.0019195557106286287
2023-01-21 12:22:37.204072: step: 204/530, loss: 0.025051262229681015
2023-01-21 12:22:38.376372: step: 208/530, loss: 0.010174370370805264
2023-01-21 12:22:39.553500: step: 212/530, loss: 0.0030391693580895662
2023-01-21 12:22:40.720316: step: 216/530, loss: 0.005788612179458141
2023-01-21 12:22:41.899667: step: 220/530, loss: 0.025357436388731003
2023-01-21 12:22:43.083150: step: 224/530, loss: 0.02130146138370037
2023-01-21 12:22:44.239600: step: 228/530, loss: 0.0031027316581457853
2023-01-21 12:22:45.413634: step: 232/530, loss: 0.0005702972412109375
2023-01-21 12:22:46.599795: step: 236/530, loss: 0.002884006593376398
2023-01-21 12:22:47.782901: step: 240/530, loss: 0.0018054962856695056
2023-01-21 12:22:48.968327: step: 244/530, loss: 0.0008661747560836375
2023-01-21 12:22:50.169549: step: 248/530, loss: 0.0006205082172527909
2023-01-21 12:22:51.366442: step: 252/530, loss: 0.00012426376633811742
2023-01-21 12:22:52.533516: step: 256/530, loss: 0.01732473447918892
2023-01-21 12:22:53.687491: step: 260/530, loss: 0.00013537406630348414
2023-01-21 12:22:54.867627: step: 264/530, loss: 0.0021300793159753084
2023-01-21 12:22:56.018360: step: 268/530, loss: 0.0003980636829510331
2023-01-21 12:22:57.193286: step: 272/530, loss: 0.0020854950416833162
2023-01-21 12:22:58.397907: step: 276/530, loss: 0.006554889492690563
2023-01-21 12:22:59.544900: step: 280/530, loss: 0.002033805940300226
2023-01-21 12:23:00.726861: step: 284/530, loss: 0.012477397918701172
2023-01-21 12:23:01.913297: step: 288/530, loss: 0.0038387300446629524
2023-01-21 12:23:03.067243: step: 292/530, loss: 0.00016641616821289062
2023-01-21 12:23:04.215964: step: 296/530, loss: 0.026497460901737213
2023-01-21 12:23:05.396767: step: 300/530, loss: 0.03892707824707031
2023-01-21 12:23:06.576836: step: 304/530, loss: 0.06496113538742065
2023-01-21 12:23:07.714938: step: 308/530, loss: 2.47955313170678e-06
2023-01-21 12:23:08.878087: step: 312/530, loss: 0.07023658603429794
2023-01-21 12:23:10.065829: step: 316/530, loss: 0.30156898498535156
2023-01-21 12:23:11.227681: step: 320/530, loss: 0.017316604033112526
2023-01-21 12:23:12.422512: step: 324/530, loss: 0.0011844635009765625
2023-01-21 12:23:13.623645: step: 328/530, loss: 0.0005579948774538934
2023-01-21 12:23:14.781078: step: 332/530, loss: 0.00010375976853538305
2023-01-21 12:23:15.963418: step: 336/530, loss: 0.008565330877900124
2023-01-21 12:23:17.137760: step: 340/530, loss: 0.000873184239026159
2023-01-21 12:23:18.282068: step: 344/530, loss: 0.03654494509100914
2023-01-21 12:23:19.451316: step: 348/530, loss: 0.005431937985122204
2023-01-21 12:23:20.648470: step: 352/530, loss: 0.5572018623352051
2023-01-21 12:23:21.825693: step: 356/530, loss: 0.011644936166703701
2023-01-21 12:23:23.005767: step: 360/530, loss: 0.015163802541792393
2023-01-21 12:23:24.190305: step: 364/530, loss: 0.0002283096400788054
2023-01-21 12:23:25.361695: step: 368/530, loss: 0.00139789585955441
2023-01-21 12:23:26.584457: step: 372/530, loss: 0.006923676002770662
2023-01-21 12:23:27.802764: step: 376/530, loss: 0.002502632327377796
2023-01-21 12:23:28.959657: step: 380/530, loss: 0.0006104469066485763
2023-01-21 12:23:30.133415: step: 384/530, loss: 0.023661326617002487
2023-01-21 12:23:31.311069: step: 388/530, loss: 0.0037982941139489412
2023-01-21 12:23:32.481198: step: 392/530, loss: 0.017516423016786575
2023-01-21 12:23:33.681321: step: 396/530, loss: 0.0073608397506177425
2023-01-21 12:23:34.885595: step: 400/530, loss: 0.01524648629128933
2023-01-21 12:23:36.061753: step: 404/530, loss: 0.0013905524974688888
2023-01-21 12:23:37.223223: step: 408/530, loss: 0.0073544979095458984
2023-01-21 12:23:38.412166: step: 412/530, loss: 5.226135181146674e-05
2023-01-21 12:23:39.578335: step: 416/530, loss: 0.008092212490737438
2023-01-21 12:23:40.746476: step: 420/530, loss: 0.06045146286487579
2023-01-21 12:23:41.925700: step: 424/530, loss: 0.02800917811691761
2023-01-21 12:23:43.131666: step: 428/530, loss: 0.005451393313705921
2023-01-21 12:23:44.333761: step: 432/530, loss: 0.0014471054309979081
2023-01-21 12:23:45.516763: step: 436/530, loss: 0.11318083107471466
2023-01-21 12:23:46.676492: step: 440/530, loss: 0.0011535645462572575
2023-01-21 12:23:47.859509: step: 444/530, loss: 0.0001038074551615864
2023-01-21 12:23:49.009408: step: 448/530, loss: 0.000736713467631489
2023-01-21 12:23:50.193779: step: 452/530, loss: 0.0007370948442257941
2023-01-21 12:23:51.372248: step: 456/530, loss: 0.018181132152676582
2023-01-21 12:23:52.569070: step: 460/530, loss: 4.3487551010912284e-05
2023-01-21 12:23:53.773880: step: 464/530, loss: 0.000263214111328125
2023-01-21 12:23:54.916514: step: 468/530, loss: 0.0003094673156738281
2023-01-21 12:23:56.059679: step: 472/530, loss: 7.677078247070312e-05
2023-01-21 12:23:57.232015: step: 476/530, loss: 0.00023751257685944438
2023-01-21 12:23:58.389811: step: 480/530, loss: 0.029003430157899857
2023-01-21 12:23:59.575337: step: 484/530, loss: 0.01321487408131361
2023-01-21 12:24:00.762997: step: 488/530, loss: 0.0027103424072265625
2023-01-21 12:24:01.953984: step: 492/530, loss: 0.0086402902379632
2023-01-21 12:24:03.114143: step: 496/530, loss: 0.0009473800892010331
2023-01-21 12:24:04.256016: step: 500/530, loss: 0.29113462567329407
2023-01-21 12:24:05.453614: step: 504/530, loss: 0.01332998275756836
2023-01-21 12:24:06.606174: step: 508/530, loss: 9.317397780250758e-05
2023-01-21 12:24:07.759182: step: 512/530, loss: 1.1873245966853574e-05
2023-01-21 12:24:08.903684: step: 516/530, loss: 4.4631960918195546e-05
2023-01-21 12:24:10.067402: step: 520/530, loss: 0.005668449681252241
2023-01-21 12:24:11.217425: step: 524/530, loss: 0.005369758699089289
2023-01-21 12:24:12.428248: step: 528/530, loss: 0.00043358802213333547
2023-01-21 12:24:13.691714: step: 532/530, loss: 0.012942886911332607
2023-01-21 12:24:14.868493: step: 536/530, loss: 0.019423531368374825
2023-01-21 12:24:16.025750: step: 540/530, loss: 0.009538078680634499
2023-01-21 12:24:17.224267: step: 544/530, loss: 0.0006220817449502647
2023-01-21 12:24:18.440792: step: 548/530, loss: 0.033678580075502396
2023-01-21 12:24:19.612283: step: 552/530, loss: 0.0038746357895433903
2023-01-21 12:24:20.786609: step: 556/530, loss: 0.03186088055372238
2023-01-21 12:24:21.910512: step: 560/530, loss: 0.00124359130859375
2023-01-21 12:24:23.143263: step: 564/530, loss: 0.017687320709228516
2023-01-21 12:24:24.316347: step: 568/530, loss: 0.03152046352624893
2023-01-21 12:24:25.434857: step: 572/530, loss: 0.0008993148803710938
2023-01-21 12:24:26.618869: step: 576/530, loss: 0.00567283621057868
2023-01-21 12:24:27.790306: step: 580/530, loss: 0.0018933296669274569
2023-01-21 12:24:28.949963: step: 584/530, loss: 0.0005732536665163934
2023-01-21 12:24:30.115228: step: 588/530, loss: 0.0028955459129065275
2023-01-21 12:24:31.297719: step: 592/530, loss: 0.00383510603569448
2023-01-21 12:24:32.434320: step: 596/530, loss: 0.0005003213882446289
2023-01-21 12:24:33.591864: step: 600/530, loss: 0.038018230348825455
2023-01-21 12:24:34.797946: step: 604/530, loss: 0.06990861892700195
2023-01-21 12:24:35.982129: step: 608/530, loss: 0.05002880096435547
2023-01-21 12:24:37.116588: step: 612/530, loss: 0.02055969275534153
2023-01-21 12:24:38.286009: step: 616/530, loss: 0.01705198548734188
2023-01-21 12:24:39.414872: step: 620/530, loss: 0.0005360603099688888
2023-01-21 12:24:40.599835: step: 624/530, loss: 0.3124147355556488
2023-01-21 12:24:41.795087: step: 628/530, loss: 0.0058685303665697575
2023-01-21 12:24:42.983354: step: 632/530, loss: 0.015434646978974342
2023-01-21 12:24:44.201785: step: 636/530, loss: 0.01999836042523384
2023-01-21 12:24:45.346528: step: 640/530, loss: 0.02104015462100506
2023-01-21 12:24:46.496279: step: 644/530, loss: 0.009812641888856888
2023-01-21 12:24:47.665474: step: 648/530, loss: 0.0021873475052416325
2023-01-21 12:24:48.878843: step: 652/530, loss: 0.00022878649178892374
2023-01-21 12:24:50.038589: step: 656/530, loss: 0.00044288637582212687
2023-01-21 12:24:51.183652: step: 660/530, loss: 0.0016105652321130037
2023-01-21 12:24:52.398930: step: 664/530, loss: 0.014573002234101295
2023-01-21 12:24:53.570552: step: 668/530, loss: 4.77790817967616e-05
2023-01-21 12:24:54.737920: step: 672/530, loss: 0.00555000314489007
2023-01-21 12:24:55.916000: step: 676/530, loss: 0.0013641357654705644
2023-01-21 12:24:57.094600: step: 680/530, loss: 0.051749229431152344
2023-01-21 12:24:58.293737: step: 684/530, loss: 0.0006423949962481856
2023-01-21 12:24:59.515418: step: 688/530, loss: 0.08304862678050995
2023-01-21 12:25:00.703383: step: 692/530, loss: 0.0011313437717035413
2023-01-21 12:25:01.885940: step: 696/530, loss: 0.04104633256793022
2023-01-21 12:25:03.099895: step: 700/530, loss: 0.04244270548224449
2023-01-21 12:25:04.251320: step: 704/530, loss: 0.01815938949584961
2023-01-21 12:25:05.447546: step: 708/530, loss: 0.016731834039092064
2023-01-21 12:25:06.670487: step: 712/530, loss: 0.030443955212831497
2023-01-21 12:25:07.871898: step: 716/530, loss: 0.040987778455019
2023-01-21 12:25:09.063707: step: 720/530, loss: 0.08112120628356934
2023-01-21 12:25:10.178494: step: 724/530, loss: 0.009659003466367722
2023-01-21 12:25:11.368973: step: 728/530, loss: 0.0007363319164142013
2023-01-21 12:25:12.573506: step: 732/530, loss: 0.0635766014456749
2023-01-21 12:25:13.749291: step: 736/530, loss: 0.004429626744240522
2023-01-21 12:25:14.912239: step: 740/530, loss: 0.01755695417523384
2023-01-21 12:25:16.101175: step: 744/530, loss: 0.030556773766875267
2023-01-21 12:25:17.282266: step: 748/530, loss: 0.005811882205307484
2023-01-21 12:25:18.447316: step: 752/530, loss: -2.765655517578125e-05
2023-01-21 12:25:19.632237: step: 756/530, loss: 0.008227873593568802
2023-01-21 12:25:20.763604: step: 760/530, loss: 0.0046897889114916325
2023-01-21 12:25:21.960215: step: 764/530, loss: 0.0001104354887502268
2023-01-21 12:25:23.131305: step: 768/530, loss: 0.0017789840931072831
2023-01-21 12:25:24.315730: step: 772/530, loss: 0.0018478394486010075
2023-01-21 12:25:25.486185: step: 776/530, loss: 0.03618679195642471
2023-01-21 12:25:26.676578: step: 780/530, loss: 0.018131066113710403
2023-01-21 12:25:27.885494: step: 784/530, loss: 0.034902192652225494
2023-01-21 12:25:29.060695: step: 788/530, loss: 0.0006243705865927041
2023-01-21 12:25:30.267020: step: 792/530, loss: 0.0643729642033577
2023-01-21 12:25:31.468034: step: 796/530, loss: 0.03406066820025444
2023-01-21 12:25:32.687402: step: 800/530, loss: 0.026997948065400124
2023-01-21 12:25:33.842463: step: 804/530, loss: 0.005030632484704256
2023-01-21 12:25:35.010013: step: 808/530, loss: 0.003253269474953413
2023-01-21 12:25:36.160695: step: 812/530, loss: 0.020756054669618607
2023-01-21 12:25:37.322406: step: 816/530, loss: 0.0016414641868323088
2023-01-21 12:25:38.464479: step: 820/530, loss: 0.04311408847570419
2023-01-21 12:25:39.666243: step: 824/530, loss: 4.4822695599577855e-06
2023-01-21 12:25:40.871467: step: 828/530, loss: 0.0008703708299435675
2023-01-21 12:25:42.163822: step: 832/530, loss: 0.0015067100757732987
2023-01-21 12:25:43.293954: step: 836/530, loss: 0.00022792816162109375
2023-01-21 12:25:44.470303: step: 840/530, loss: 0.014737176708877087
2023-01-21 12:25:45.646874: step: 844/530, loss: 0.001051950384862721
2023-01-21 12:25:46.807514: step: 848/530, loss: 0.0041065216064453125
2023-01-21 12:25:48.006782: step: 852/530, loss: 0.04677295684814453
2023-01-21 12:25:49.194225: step: 856/530, loss: 0.0018159865867346525
2023-01-21 12:25:50.386847: step: 860/530, loss: 0.007681942544877529
2023-01-21 12:25:51.547012: step: 864/530, loss: 8.316040475619957e-05
2023-01-21 12:25:52.700784: step: 868/530, loss: 0.0026844025123864412
2023-01-21 12:25:53.889806: step: 872/530, loss: 0.0024504661560058594
2023-01-21 12:25:55.053763: step: 876/530, loss: 0.00020074844360351562
2023-01-21 12:25:56.262388: step: 880/530, loss: 0.0007545471307821572
2023-01-21 12:25:57.427809: step: 884/530, loss: 0.005092716310173273
2023-01-21 12:25:58.637027: step: 888/530, loss: 0.0020111084450036287
2023-01-21 12:25:59.815549: step: 892/530, loss: 0.002813720842823386
2023-01-21 12:26:00.975139: step: 896/530, loss: 0.003751564072445035
2023-01-21 12:26:02.148656: step: 900/530, loss: 0.0003544807550497353
2023-01-21 12:26:03.368165: step: 904/530, loss: 0.005286312196403742
2023-01-21 12:26:04.587696: step: 908/530, loss: 0.03681468963623047
2023-01-21 12:26:05.786020: step: 912/530, loss: 0.014543152414262295
2023-01-21 12:26:06.933044: step: 916/530, loss: 0.026371479034423828
2023-01-21 12:26:08.140668: step: 920/530, loss: 0.0037866593338549137
2023-01-21 12:26:09.337587: step: 924/530, loss: 0.001305580255575478
2023-01-21 12:26:10.531722: step: 928/530, loss: 0.007343864534050226
2023-01-21 12:26:11.759040: step: 932/530, loss: 0.0003808975452557206
2023-01-21 12:26:13.001472: step: 936/530, loss: 8.630752563476562e-05
2023-01-21 12:26:14.236844: step: 940/530, loss: 0.005280685611069202
2023-01-21 12:26:15.385618: step: 944/530, loss: 0.03523607552051544
2023-01-21 12:26:16.551769: step: 948/530, loss: 0.007588863838464022
2023-01-21 12:26:17.738412: step: 952/530, loss: 0.024454500526189804
2023-01-21 12:26:18.936721: step: 956/530, loss: 0.00014591217041015625
2023-01-21 12:26:20.112648: step: 960/530, loss: 0.0022132874000817537
2023-01-21 12:26:21.271227: step: 964/530, loss: 0.0037399292923510075
2023-01-21 12:26:22.444919: step: 968/530, loss: 0.002145147416740656
2023-01-21 12:26:23.615568: step: 972/530, loss: 0.019171716645359993
2023-01-21 12:26:24.856057: step: 976/530, loss: 0.00036525726318359375
2023-01-21 12:26:26.051120: step: 980/530, loss: 6.442069570766762e-05
2023-01-21 12:26:27.223463: step: 984/530, loss: 0.0010175704956054688
2023-01-21 12:26:28.482471: step: 988/530, loss: 0.003712558886036277
2023-01-21 12:26:29.654782: step: 992/530, loss: 0.006087112706154585
2023-01-21 12:26:30.863363: step: 996/530, loss: -3.6716460272145923e-06
2023-01-21 12:26:32.056538: step: 1000/530, loss: 0.02530221827328205
2023-01-21 12:26:33.239582: step: 1004/530, loss: 0.0005221366882324219
2023-01-21 12:26:34.408274: step: 1008/530, loss: 9.51766996877268e-05
2023-01-21 12:26:35.589458: step: 1012/530, loss: 0.022327804937958717
2023-01-21 12:26:36.743560: step: 1016/530, loss: 0.0017938613891601562
2023-01-21 12:26:37.909884: step: 1020/530, loss: 0.0002803802490234375
2023-01-21 12:26:39.066356: step: 1024/530, loss: 0.0038398741744458675
2023-01-21 12:26:40.237110: step: 1028/530, loss: 0.0003364562871865928
2023-01-21 12:26:41.420520: step: 1032/530, loss: 0.002929878421127796
2023-01-21 12:26:42.598057: step: 1036/530, loss: 0.00024881362332962453
2023-01-21 12:26:43.816120: step: 1040/530, loss: 0.00012168884859420359
2023-01-21 12:26:44.953863: step: 1044/530, loss: 0.00022702215937897563
2023-01-21 12:26:46.140811: step: 1048/530, loss: 0.025398733094334602
2023-01-21 12:26:47.318860: step: 1052/530, loss: 0.16058588027954102
2023-01-21 12:26:48.455678: step: 1056/530, loss: 1.735687328618951e-05
2023-01-21 12:26:49.613545: step: 1060/530, loss: 0.009137011133134365
2023-01-21 12:26:50.809044: step: 1064/530, loss: 0.002721595810726285
2023-01-21 12:26:51.997158: step: 1068/530, loss: 0.020731544122099876
2023-01-21 12:26:53.198792: step: 1072/530, loss: 0.002322292421013117
2023-01-21 12:26:54.390130: step: 1076/530, loss: 0.0025777816772460938
2023-01-21 12:26:55.591157: step: 1080/530, loss: 0.00026159288245253265
2023-01-21 12:26:56.759279: step: 1084/530, loss: 3.1948089599609375e-05
2023-01-21 12:26:57.953243: step: 1088/530, loss: 0.021294020116329193
2023-01-21 12:26:59.141062: step: 1092/530, loss: 0.04923572763800621
2023-01-21 12:27:00.365252: step: 1096/530, loss: 0.004612350836396217
2023-01-21 12:27:01.629187: step: 1100/530, loss: 9.498596045887098e-05
2023-01-21 12:27:02.789844: step: 1104/530, loss: 0.004296588711440563
2023-01-21 12:27:03.986337: step: 1108/530, loss: 0.0004343986511230469
2023-01-21 12:27:05.153938: step: 1112/530, loss: 0.00036277773324400187
2023-01-21 12:27:06.333041: step: 1116/530, loss: 0.20355768501758575
2023-01-21 12:27:07.499967: step: 1120/530, loss: 0.0001848220854299143
2023-01-21 12:27:08.672905: step: 1124/530, loss: 0.0007444382063113153
2023-01-21 12:27:09.893408: step: 1128/530, loss: 0.00036296845064498484
2023-01-21 12:27:11.090878: step: 1132/530, loss: 2.0885467165498994e-05
2023-01-21 12:27:12.315904: step: 1136/530, loss: 0.0006978035089559853
2023-01-21 12:27:13.509240: step: 1140/530, loss: 0.00013573169417213649
2023-01-21 12:27:14.668672: step: 1144/530, loss: 0.012542152777314186
2023-01-21 12:27:15.822267: step: 1148/530, loss: 0.00011076927330577746
2023-01-21 12:27:16.979928: step: 1152/530, loss: 0.008348274044692516
2023-01-21 12:27:18.182585: step: 1156/530, loss: 0.0007147789583541453
2023-01-21 12:27:19.374319: step: 1160/530, loss: 0.011353492736816406
2023-01-21 12:27:20.564739: step: 1164/530, loss: 0.021475983783602715
2023-01-21 12:27:21.732778: step: 1168/530, loss: 7.009506225585938e-05
2023-01-21 12:27:22.890111: step: 1172/530, loss: 0.0011430740123614669
2023-01-21 12:27:24.073809: step: 1176/530, loss: 0.028866050764918327
2023-01-21 12:27:25.281527: step: 1180/530, loss: 8.516311936546117e-05
2023-01-21 12:27:26.438641: step: 1184/530, loss: 0.0003108978271484375
2023-01-21 12:27:27.577305: step: 1188/530, loss: 5.860329110873863e-05
2023-01-21 12:27:28.751184: step: 1192/530, loss: 0.00028548241243697703
2023-01-21 12:27:29.888314: step: 1196/530, loss: 0.006782818119972944
2023-01-21 12:27:31.035108: step: 1200/530, loss: 0.0011333465809002519
2023-01-21 12:27:32.230459: step: 1204/530, loss: 0.023638440296053886
2023-01-21 12:27:33.380675: step: 1208/530, loss: 4.901886131847277e-05
2023-01-21 12:27:34.630692: step: 1212/530, loss: 0.008943939581513405
2023-01-21 12:27:35.771538: step: 1216/530, loss: 0.021670913323760033
2023-01-21 12:27:36.914933: step: 1220/530, loss: 0.007708454504609108
2023-01-21 12:27:38.150783: step: 1224/530, loss: 0.004290103912353516
2023-01-21 12:27:39.340040: step: 1228/530, loss: 0.05924654006958008
2023-01-21 12:27:40.530851: step: 1232/530, loss: 0.0024260522332042456
2023-01-21 12:27:41.670471: step: 1236/530, loss: 0.00013074875460006297
2023-01-21 12:27:42.897794: step: 1240/530, loss: 0.011115646921098232
2023-01-21 12:27:44.136300: step: 1244/530, loss: 0.01061868667602539
2023-01-21 12:27:45.358451: step: 1248/530, loss: 0.0015537738800048828
2023-01-21 12:27:46.549517: step: 1252/530, loss: 0.0038841248024255037
2023-01-21 12:27:47.701515: step: 1256/530, loss: 0.10177478939294815
2023-01-21 12:27:48.877006: step: 1260/530, loss: 0.0012756347423419356
2023-01-21 12:27:50.040618: step: 1264/530, loss: 0.0008525848388671875
2023-01-21 12:27:51.248143: step: 1268/530, loss: 0.028227806091308594
2023-01-21 12:27:52.440281: step: 1272/530, loss: 0.0022107125259935856
2023-01-21 12:27:53.626245: step: 1276/530, loss: 0.002467632293701172
2023-01-21 12:27:54.788321: step: 1280/530, loss: 0.04509372636675835
2023-01-21 12:27:55.988076: step: 1284/530, loss: 0.0008831977611407638
2023-01-21 12:27:57.180190: step: 1288/530, loss: 0.00166149134747684
2023-01-21 12:27:58.353525: step: 1292/530, loss: 0.029405975714325905
2023-01-21 12:27:59.526028: step: 1296/530, loss: 0.0039193155243992805
2023-01-21 12:28:00.731020: step: 1300/530, loss: 0.014392471872270107
2023-01-21 12:28:01.912271: step: 1304/530, loss: 0.001334381173364818
2023-01-21 12:28:03.110892: step: 1308/530, loss: 0.03337745741009712
2023-01-21 12:28:04.288128: step: 1312/530, loss: 6.341934204101562e-05
2023-01-21 12:28:05.446509: step: 1316/530, loss: 0.27916595339775085
2023-01-21 12:28:06.635014: step: 1320/530, loss: 0.00081806187517941
2023-01-21 12:28:07.812637: step: 1324/530, loss: 0.008203888311982155
2023-01-21 12:28:08.984347: step: 1328/530, loss: 0.0007153988117352128
2023-01-21 12:28:10.166552: step: 1332/530, loss: 0.003934287931770086
2023-01-21 12:28:11.334988: step: 1336/530, loss: 0.009502124972641468
2023-01-21 12:28:12.505062: step: 1340/530, loss: 8.106231689453125e-05
2023-01-21 12:28:13.714801: step: 1344/530, loss: 0.19960841536521912
2023-01-21 12:28:14.989046: step: 1348/530, loss: 0.01688537746667862
2023-01-21 12:28:16.160593: step: 1352/530, loss: 0.0016566276317462325
2023-01-21 12:28:17.320510: step: 1356/530, loss: 0.06125936657190323
2023-01-21 12:28:18.542332: step: 1360/530, loss: 0.011808013543486595
2023-01-21 12:28:19.720295: step: 1364/530, loss: 0.0034175217151641846
2023-01-21 12:28:20.891681: step: 1368/530, loss: 0.0020648958161473274
2023-01-21 12:28:22.069267: step: 1372/530, loss: 0.0003074645937886089
2023-01-21 12:28:23.227562: step: 1376/530, loss: 0.1559613198041916
2023-01-21 12:28:24.418685: step: 1380/530, loss: 0.0005715370061807334
2023-01-21 12:28:25.572311: step: 1384/530, loss: 1.5544890629826114e-05
2023-01-21 12:28:26.764305: step: 1388/530, loss: 7.820130122127011e-06
2023-01-21 12:28:27.938999: step: 1392/530, loss: 0.001327133271843195
2023-01-21 12:28:29.109409: step: 1396/530, loss: 0.003715706057846546
2023-01-21 12:28:30.276053: step: 1400/530, loss: 5.054473876953125e-05
2023-01-21 12:28:31.488404: step: 1404/530, loss: 0.012380409985780716
2023-01-21 12:28:32.637710: step: 1408/530, loss: 0.006866169162094593
2023-01-21 12:28:33.801981: step: 1412/530, loss: 0.03629784658551216
2023-01-21 12:28:34.990270: step: 1416/530, loss: 0.0019253729842603207
2023-01-21 12:28:36.176061: step: 1420/530, loss: 0.00010805130295921117
2023-01-21 12:28:37.373265: step: 1424/530, loss: 0.06991958618164062
2023-01-21 12:28:38.541464: step: 1428/530, loss: 0.0049078939482569695
2023-01-21 12:28:39.696067: step: 1432/530, loss: 0.07744617015123367
2023-01-21 12:28:40.861451: step: 1436/530, loss: 0.00035533905611373484
2023-01-21 12:28:42.082817: step: 1440/530, loss: 0.04077615961432457
2023-01-21 12:28:43.264298: step: 1444/530, loss: 0.00399284390732646
2023-01-21 12:28:44.451712: step: 1448/530, loss: 0.0034280777908861637
2023-01-21 12:28:45.616881: step: 1452/530, loss: 0.008730793371796608
2023-01-21 12:28:46.764992: step: 1456/530, loss: 0.0009521484607830644
2023-01-21 12:28:47.955885: step: 1460/530, loss: 0.018700361251831055
2023-01-21 12:28:49.162944: step: 1464/530, loss: 0.004648399073630571
2023-01-21 12:28:50.340488: step: 1468/530, loss: 0.004745769780129194
2023-01-21 12:28:51.475128: step: 1472/530, loss: 0.023762892931699753
2023-01-21 12:28:52.673086: step: 1476/530, loss: 2.28881845032447e-06
2023-01-21 12:28:53.815957: step: 1480/530, loss: 0.0011127472389489412
2023-01-21 12:28:55.030780: step: 1484/530, loss: 0.007662534713745117
2023-01-21 12:28:56.275846: step: 1488/530, loss: 0.0008435249328613281
2023-01-21 12:28:57.424063: step: 1492/530, loss: 0.00045281497295945883
2023-01-21 12:28:58.571053: step: 1496/530, loss: 0.017081070691347122
2023-01-21 12:28:59.779665: step: 1500/530, loss: 0.007808685302734375
2023-01-21 12:29:00.919415: step: 1504/530, loss: 0.0007936477777548134
2023-01-21 12:29:02.123347: step: 1508/530, loss: 0.04832973703742027
2023-01-21 12:29:03.315976: step: 1512/530, loss: 0.08074036240577698
2023-01-21 12:29:04.494386: step: 1516/530, loss: 0.00397148123010993
2023-01-21 12:29:05.644538: step: 1520/530, loss: 0.012388801202178001
2023-01-21 12:29:06.830822: step: 1524/530, loss: 0.03733024746179581
2023-01-21 12:29:07.996702: step: 1528/530, loss: 0.05975513160228729
2023-01-21 12:29:09.215546: step: 1532/530, loss: 4.1651728679426014e-05
2023-01-21 12:29:10.389587: step: 1536/530, loss: 0.011095809750258923
2023-01-21 12:29:11.607343: step: 1540/530, loss: 0.0012161254417151213
2023-01-21 12:29:12.841900: step: 1544/530, loss: 0.0009416580433025956
2023-01-21 12:29:13.987137: step: 1548/530, loss: 0.001074504922144115
2023-01-21 12:29:15.158019: step: 1552/530, loss: 0.009495258331298828
2023-01-21 12:29:16.305369: step: 1556/530, loss: 0.004488920792937279
2023-01-21 12:29:17.491949: step: 1560/530, loss: 0.00022668838209938258
2023-01-21 12:29:18.676189: step: 1564/530, loss: 0.005683327093720436
2023-01-21 12:29:19.831035: step: 1568/530, loss: 0.02956237830221653
2023-01-21 12:29:21.014484: step: 1572/530, loss: 3.929138256353326e-05
2023-01-21 12:29:22.204000: step: 1576/530, loss: 0.0024566650390625
2023-01-21 12:29:23.362276: step: 1580/530, loss: 0.00012607575627043843
2023-01-21 12:29:24.629850: step: 1584/530, loss: 0.0028226852882653475
2023-01-21 12:29:25.811764: step: 1588/530, loss: 0.005423259921371937
2023-01-21 12:29:27.009938: step: 1592/530, loss: 0.0004559516964945942
2023-01-21 12:29:28.179059: step: 1596/530, loss: 0.00016479492478538305
2023-01-21 12:29:29.366073: step: 1600/530, loss: 0.0024972916580736637
2023-01-21 12:29:30.537208: step: 1604/530, loss: 0.0044796462170779705
2023-01-21 12:29:31.709004: step: 1608/530, loss: 0.003361702198162675
2023-01-21 12:29:32.888209: step: 1612/530, loss: 1.964569128176663e-05
2023-01-21 12:29:34.048457: step: 1616/530, loss: 0.02086505852639675
2023-01-21 12:29:35.263389: step: 1620/530, loss: 0.0014811038272455335
2023-01-21 12:29:36.426531: step: 1624/530, loss: 4.692077709478326e-05
2023-01-21 12:29:37.590385: step: 1628/530, loss: 0.001530551933683455
2023-01-21 12:29:38.797295: step: 1632/530, loss: 5.4645537602482364e-05
2023-01-21 12:29:39.968334: step: 1636/530, loss: 0.028560448437929153
2023-01-21 12:29:41.123945: step: 1640/530, loss: 0.000335884076775983
2023-01-21 12:29:42.308868: step: 1644/530, loss: 0.0003836631658487022
2023-01-21 12:29:43.443765: step: 1648/530, loss: 5.722045557376987e-07
2023-01-21 12:29:44.639210: step: 1652/530, loss: 0.03167577460408211
2023-01-21 12:29:45.782493: step: 1656/530, loss: 0.011873818002641201
2023-01-21 12:29:46.941405: step: 1660/530, loss: 0.0022684098221361637
2023-01-21 12:29:48.148064: step: 1664/530, loss: 3.6716461181640625e-05
2023-01-21 12:29:49.350742: step: 1668/530, loss: 0.007731437683105469
2023-01-21 12:29:50.523582: step: 1672/530, loss: 0.0006959915044717491
2023-01-21 12:29:51.672575: step: 1676/530, loss: 0.0001160621686722152
2023-01-21 12:29:52.857330: step: 1680/530, loss: 0.003297233721241355
2023-01-21 12:29:54.078396: step: 1684/530, loss: 0.07754363864660263
2023-01-21 12:29:55.258261: step: 1688/530, loss: 0.01988682709634304
2023-01-21 12:29:56.424374: step: 1692/530, loss: 0.6587401628494263
2023-01-21 12:29:57.590050: step: 1696/530, loss: 2.4890900022001006e-05
2023-01-21 12:29:58.754684: step: 1700/530, loss: 0.07908801734447479
2023-01-21 12:29:59.986767: step: 1704/530, loss: 0.00016698836407158524
2023-01-21 12:30:01.177954: step: 1708/530, loss: 0.010745239444077015
2023-01-21 12:30:02.385858: step: 1712/530, loss: 0.0034881592728197575
2023-01-21 12:30:03.565909: step: 1716/530, loss: 0.006335449405014515
2023-01-21 12:30:04.790037: step: 1720/530, loss: 1.087188684323337e-05
2023-01-21 12:30:05.978828: step: 1724/530, loss: 0.0004985809209756553
2023-01-21 12:30:07.118034: step: 1728/530, loss: 0.0007890701526775956
2023-01-21 12:30:08.288854: step: 1732/530, loss: 0.00017390251741744578
2023-01-21 12:30:09.486949: step: 1736/530, loss: 0.004042911808937788
2023-01-21 12:30:10.682595: step: 1740/530, loss: 0.010141182690858841
2023-01-21 12:30:11.876522: step: 1744/530, loss: 2.398491051280871e-05
2023-01-21 12:30:13.094616: step: 1748/530, loss: 0.0002347946137888357
2023-01-21 12:30:14.280518: step: 1752/530, loss: 0.010663891211152077
2023-01-21 12:30:15.432271: step: 1756/530, loss: 0.007246876135468483
2023-01-21 12:30:16.676702: step: 1760/530, loss: 0.18355527520179749
2023-01-21 12:30:17.849199: step: 1764/530, loss: 0.0003510475507937372
2023-01-21 12:30:19.023367: step: 1768/530, loss: 0.00040884019108489156
2023-01-21 12:30:20.220531: step: 1772/530, loss: 0.002647495362907648
2023-01-21 12:30:21.411643: step: 1776/530, loss: 0.01062865275889635
2023-01-21 12:30:22.575447: step: 1780/530, loss: 0.0031936645973473787
2023-01-21 12:30:23.773667: step: 1784/530, loss: 0.0019193649059161544
2023-01-21 12:30:24.977083: step: 1788/530, loss: -4.196167537884321e-06
2023-01-21 12:30:26.155941: step: 1792/530, loss: 0.00018072128295898438
2023-01-21 12:30:27.333108: step: 1796/530, loss: 0.010405254550278187
2023-01-21 12:30:28.524778: step: 1800/530, loss: 0.0006045341724529862
2023-01-21 12:30:29.690318: step: 1804/530, loss: 0.0001813888520700857
2023-01-21 12:30:30.934965: step: 1808/530, loss: 0.0020097733940929174
2023-01-21 12:30:32.125490: step: 1812/530, loss: 0.0071659088134765625
2023-01-21 12:30:33.359428: step: 1816/530, loss: 0.08185024559497833
2023-01-21 12:30:34.531459: step: 1820/530, loss: 0.00233039865270257
2023-01-21 12:30:35.725194: step: 1824/530, loss: 0.0022067308891564608
2023-01-21 12:30:36.915888: step: 1828/530, loss: 0.015968896448612213
2023-01-21 12:30:38.106426: step: 1832/530, loss: 6.546974327648059e-05
2023-01-21 12:30:39.249045: step: 1836/530, loss: 0.00022449492826126516
2023-01-21 12:30:40.450360: step: 1840/530, loss: -6.9141387939453125e-06
2023-01-21 12:30:41.638872: step: 1844/530, loss: 0.0005926132434979081
2023-01-21 12:30:42.833784: step: 1848/530, loss: 0.0011260986793786287
2023-01-21 12:30:43.987368: step: 1852/530, loss: 0.0034766674507409334
2023-01-21 12:30:45.133193: step: 1856/530, loss: 0.011931801214814186
2023-01-21 12:30:46.281511: step: 1860/530, loss: 0.017504312098026276
2023-01-21 12:30:47.458095: step: 1864/530, loss: 0.00032329559326171875
2023-01-21 12:30:48.623254: step: 1868/530, loss: 3.63349899998866e-05
2023-01-21 12:30:49.799722: step: 1872/530, loss: 0.017606163397431374
2023-01-21 12:30:50.988289: step: 1876/530, loss: 0.0029344558715820312
2023-01-21 12:30:52.175158: step: 1880/530, loss: 2.6607514882925898e-05
2023-01-21 12:30:53.379592: step: 1884/530, loss: 0.00019378663273528218
2023-01-21 12:30:54.581347: step: 1888/530, loss: 0.00064849853515625
2023-01-21 12:30:55.780529: step: 1892/530, loss: 0.10974311828613281
2023-01-21 12:30:56.926549: step: 1896/530, loss: 0.0019610405433923006
2023-01-21 12:30:58.114523: step: 1900/530, loss: 0.0015119552845135331
2023-01-21 12:30:59.293257: step: 1904/530, loss: 0.00703353900462389
2023-01-21 12:31:00.458728: step: 1908/530, loss: 0.002143478486686945
2023-01-21 12:31:01.692692: step: 1912/530, loss: 0.03368987888097763
2023-01-21 12:31:02.847110: step: 1916/530, loss: 0.0006131172413006425
2023-01-21 12:31:04.035538: step: 1920/530, loss: 0.0030071258079260588
2023-01-21 12:31:05.203302: step: 1924/530, loss: 0.02026844024658203
2023-01-21 12:31:06.377801: step: 1928/530, loss: 0.0004669189511332661
2023-01-21 12:31:07.564958: step: 1932/530, loss: 0.06076173856854439
2023-01-21 12:31:08.747985: step: 1936/530, loss: 0.006413459777832031
2023-01-21 12:31:09.946786: step: 1940/530, loss: 0.0016765595646575093
2023-01-21 12:31:11.161349: step: 1944/530, loss: 0.3521394729614258
2023-01-21 12:31:12.319374: step: 1948/530, loss: 0.025275137275457382
2023-01-21 12:31:13.500493: step: 1952/530, loss: 0.0017601012950763106
2023-01-21 12:31:14.669339: step: 1956/530, loss: 0.001084995223209262
2023-01-21 12:31:15.854875: step: 1960/530, loss: 0.0307159423828125
2023-01-21 12:31:17.007226: step: 1964/530, loss: 0.03825478255748749
2023-01-21 12:31:18.188696: step: 1968/530, loss: 0.01157302875071764
2023-01-21 12:31:19.319367: step: 1972/530, loss: 0.37308740615844727
2023-01-21 12:31:20.496052: step: 1976/530, loss: 0.00114269251935184
2023-01-21 12:31:21.692861: step: 1980/530, loss: 0.0013395309215411544
2023-01-21 12:31:22.871457: step: 1984/530, loss: 2.1457672119140625e-06
2023-01-21 12:31:24.033494: step: 1988/530, loss: 0.0010505676036700606
2023-01-21 12:31:25.217651: step: 1992/530, loss: 0.00013828279043082148
2023-01-21 12:31:26.381213: step: 1996/530, loss: 4.196166628389619e-06
2023-01-21 12:31:27.556366: step: 2000/530, loss: 0.0009437561384402215
2023-01-21 12:31:28.742218: step: 2004/530, loss: 0.016751958057284355
2023-01-21 12:31:29.938676: step: 2008/530, loss: 0.0018543243641033769
2023-01-21 12:31:31.066111: step: 2012/530, loss: 0.001955318497493863
2023-01-21 12:31:32.278755: step: 2016/530, loss: 0.0036637308076024055
2023-01-21 12:31:33.479775: step: 2020/530, loss: 0.007431983947753906
2023-01-21 12:31:34.652957: step: 2024/530, loss: 0.0022258758544921875
2023-01-21 12:31:35.807836: step: 2028/530, loss: 0.004039120860397816
2023-01-21 12:31:36.991487: step: 2032/530, loss: 0.08428115397691727
2023-01-21 12:31:38.188223: step: 2036/530, loss: 0.013484669849276543
2023-01-21 12:31:39.360272: step: 2040/530, loss: 0.06308307498693466
2023-01-21 12:31:40.581585: step: 2044/530, loss: 0.6312940716743469
2023-01-21 12:31:41.720663: step: 2048/530, loss: 4.100799742445815e-06
2023-01-21 12:31:42.923970: step: 2052/530, loss: 0.00032596586970612407
2023-01-21 12:31:44.090708: step: 2056/530, loss: 0.0023956298828125
2023-01-21 12:31:45.276328: step: 2060/530, loss: 0.005625915713608265
2023-01-21 12:31:46.432553: step: 2064/530, loss: 8.935928053688258e-05
2023-01-21 12:31:47.573185: step: 2068/530, loss: 0.283809095621109
2023-01-21 12:31:48.780727: step: 2072/530, loss: 0.006003189366310835
2023-01-21 12:31:49.942526: step: 2076/530, loss: 0.007678413763642311
2023-01-21 12:31:51.092303: step: 2080/530, loss: 0.0034894943237304688
2023-01-21 12:31:52.284640: step: 2084/530, loss: 0.0008052826160565019
2023-01-21 12:31:53.463728: step: 2088/530, loss: 0.01092443522065878
2023-01-21 12:31:54.657960: step: 2092/530, loss: 0.001795959542505443
2023-01-21 12:31:55.857658: step: 2096/530, loss: 0.007378959562629461
2023-01-21 12:31:57.051104: step: 2100/530, loss: 0.007089043036103249
2023-01-21 12:31:58.255944: step: 2104/530, loss: 0.023382043465971947
2023-01-21 12:31:59.442439: step: 2108/530, loss: 0.0007674216758459806
2023-01-21 12:32:00.667914: step: 2112/530, loss: 0.020740794017910957
2023-01-21 12:32:01.870502: step: 2116/530, loss: 0.0013728141784667969
2023-01-21 12:32:03.042643: step: 2120/530, loss: 0.00037031175452284515
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5765765765765766, 'r': 0.7669773635153129, 'f1': 0.6582857142857143}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6460622710622711, 'r': 0.8113858539390454, 'f1': 0.7193474381850625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.5454545454545454, 'r': 0.5714285714285714, 'f1': 0.5581395348837208}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.41818181818181815, 'r': 0.6388888888888888, 'f1': 0.5054945054945054}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 12:32:46.557379: step: 4/530, loss: 0.0014701844193041325
2023-01-21 12:32:47.735654: step: 8/530, loss: 1.0967254638671875e-05
2023-01-21 12:32:48.897920: step: 12/530, loss: 8.916854858398438e-05
2023-01-21 12:32:50.106751: step: 16/530, loss: 9.040832810569555e-05
2023-01-21 12:32:51.275741: step: 20/530, loss: 0.004154628608375788
2023-01-21 12:32:52.450559: step: 24/530, loss: 5.235671778791584e-05
2023-01-21 12:32:53.625183: step: 28/530, loss: 0.0028720854315906763
2023-01-21 12:32:54.793440: step: 32/530, loss: 0.0003357887326274067
2023-01-21 12:32:55.985525: step: 36/530, loss: 0.009093094617128372
2023-01-21 12:32:57.134794: step: 40/530, loss: 0.003338289214298129
2023-01-21 12:32:58.312344: step: 44/530, loss: 0.0037233352195471525
2023-01-21 12:32:59.488472: step: 48/530, loss: 1.5449522834387608e-05
2023-01-21 12:33:00.656440: step: 52/530, loss: 7.095337059581652e-05
2023-01-21 12:33:01.824587: step: 56/530, loss: 0.004692649934440851
2023-01-21 12:33:03.018950: step: 60/530, loss: 0.0011865616543218493
2023-01-21 12:33:04.160410: step: 64/530, loss: 0.023685075342655182
2023-01-21 12:33:05.351320: step: 68/530, loss: 0.008388710208237171
2023-01-21 12:33:06.535456: step: 72/530, loss: 0.014268017373979092
2023-01-21 12:33:07.716615: step: 76/530, loss: 0.0016756057739257812
2023-01-21 12:33:08.880500: step: 80/530, loss: 4.29630272265058e-05
2023-01-21 12:33:10.045483: step: 84/530, loss: 0.0005746841197833419
2023-01-21 12:33:11.193825: step: 88/530, loss: 0.5348788499832153
2023-01-21 12:33:12.395689: step: 92/530, loss: 0.03282108157873154
2023-01-21 12:33:13.580432: step: 96/530, loss: 3.509521411615424e-05
2023-01-21 12:33:14.754184: step: 100/530, loss: 0.005488014314323664
2023-01-21 12:33:15.915282: step: 104/530, loss: 0.00036916733370162547
2023-01-21 12:33:17.154305: step: 108/530, loss: 0.03900289535522461
2023-01-21 12:33:18.332538: step: 112/530, loss: 0.010463238693773746
2023-01-21 12:33:19.520057: step: 116/530, loss: 0.010022545233368874
2023-01-21 12:33:20.657506: step: 120/530, loss: 1.6880036127986386e-05
2023-01-21 12:33:21.827244: step: 124/530, loss: 0.0005819320795126259
2023-01-21 12:33:22.983832: step: 128/530, loss: 0.013443994335830212
2023-01-21 12:33:24.127363: step: 132/530, loss: 0.014048386365175247
2023-01-21 12:33:25.315809: step: 136/530, loss: 0.009867859072983265
2023-01-21 12:33:26.469760: step: 140/530, loss: 0.005676746368408203
2023-01-21 12:33:27.629847: step: 144/530, loss: 0.02029280550777912
2023-01-21 12:33:28.786333: step: 148/530, loss: 3.4761429560603574e-05
2023-01-21 12:33:29.991874: step: 152/530, loss: 0.009539413265883923
2023-01-21 12:33:31.192290: step: 156/530, loss: 0.049428846687078476
2023-01-21 12:33:32.365949: step: 160/530, loss: 0.00010929108248092234
2023-01-21 12:33:33.582529: step: 164/530, loss: 0.011634635739028454
2023-01-21 12:33:34.769145: step: 168/530, loss: 0.005303573794662952
2023-01-21 12:33:35.969065: step: 172/530, loss: 0.0002442359982524067
2023-01-21 12:33:37.215217: step: 176/530, loss: 0.004111289978027344
2023-01-21 12:33:38.404058: step: 180/530, loss: 0.033786870539188385
2023-01-21 12:33:39.557241: step: 184/530, loss: 0.0001243591250386089
2023-01-21 12:33:40.690082: step: 188/530, loss: 0.00015544891357421875
2023-01-21 12:33:41.868452: step: 192/530, loss: 0.03639201819896698
2023-01-21 12:33:43.062724: step: 196/530, loss: 0.0003463744942564517
2023-01-21 12:33:44.288495: step: 200/530, loss: 0.05901079252362251
2023-01-21 12:33:45.463466: step: 204/530, loss: 1.672506368777249e-05
2023-01-21 12:33:46.622033: step: 208/530, loss: 0.0016666412120684981
2023-01-21 12:33:47.805552: step: 212/530, loss: 0.002579975174739957
2023-01-21 12:33:48.982257: step: 216/530, loss: 2.7322768801241182e-05
2023-01-21 12:33:50.143813: step: 220/530, loss: 3.418922642595135e-05
2023-01-21 12:33:51.354472: step: 224/530, loss: 0.12445631623268127
2023-01-21 12:33:52.506942: step: 228/530, loss: 2.1839143300894648e-05
2023-01-21 12:33:53.737202: step: 232/530, loss: 0.033011723309755325
2023-01-21 12:33:54.930330: step: 236/530, loss: 8.97407517186366e-05
2023-01-21 12:33:56.115355: step: 240/530, loss: 0.003277301788330078
2023-01-21 12:33:57.273370: step: 244/530, loss: 0.0028509378898888826
2023-01-21 12:33:58.460534: step: 248/530, loss: 0.033632662147283554
2023-01-21 12:33:59.627075: step: 252/530, loss: 0.053069114685058594
2023-01-21 12:34:00.784991: step: 256/530, loss: 0.0007869720575399697
2023-01-21 12:34:01.970290: step: 260/530, loss: 0.0009078025468625128
2023-01-21 12:34:03.195819: step: 264/530, loss: 0.0075768474489450455
2023-01-21 12:34:04.375021: step: 268/530, loss: 0.0003010749933309853
2023-01-21 12:34:05.538347: step: 272/530, loss: 0.0003259658988099545
2023-01-21 12:34:06.694692: step: 276/530, loss: 0.004863929934799671
2023-01-21 12:34:07.865938: step: 280/530, loss: 0.06417150050401688
2023-01-21 12:34:09.114999: step: 284/530, loss: 0.007483053021132946
2023-01-21 12:34:10.269698: step: 288/530, loss: 0.0030393600463867188
2023-01-21 12:34:11.459884: step: 292/530, loss: 0.005133247934281826
2023-01-21 12:34:12.640115: step: 296/530, loss: 0.017632102593779564
2023-01-21 12:34:13.813706: step: 300/530, loss: 0.04000253975391388
2023-01-21 12:34:14.981602: step: 304/530, loss: 0.0014787673717364669
2023-01-21 12:34:16.178743: step: 308/530, loss: 0.0016761779552325606
2023-01-21 12:34:17.326186: step: 312/530, loss: 0.0029859542846679688
2023-01-21 12:34:18.524760: step: 316/530, loss: 7.343292054429185e-06
2023-01-21 12:34:19.709775: step: 320/530, loss: 0.00011539459228515625
2023-01-21 12:34:20.900621: step: 324/530, loss: 0.0003215789911337197
2023-01-21 12:34:22.072851: step: 328/530, loss: 0.0032497404608875513
2023-01-21 12:34:23.236465: step: 332/530, loss: 0.00034971238346770406
2023-01-21 12:34:24.460154: step: 336/530, loss: 0.0008471489418298006
2023-01-21 12:34:25.629687: step: 340/530, loss: 0.0012094498379155993
2023-01-21 12:34:26.807199: step: 344/530, loss: 0.0029775621369481087
2023-01-21 12:34:27.979285: step: 348/530, loss: 0.000530242919921875
2023-01-21 12:34:29.138147: step: 352/530, loss: 0.0820433646440506
2023-01-21 12:34:30.322387: step: 356/530, loss: 0.007937431335449219
2023-01-21 12:34:31.498676: step: 360/530, loss: 0.006622695829719305
2023-01-21 12:34:32.699971: step: 364/530, loss: 0.007391166873276234
2023-01-21 12:34:33.864759: step: 368/530, loss: 0.0011903762351721525
2023-01-21 12:34:35.002094: step: 372/530, loss: 0.00038013458834029734
2023-01-21 12:34:36.166423: step: 376/530, loss: 0.0021543502807617188
2023-01-21 12:34:37.316546: step: 380/530, loss: 0.005744743626564741
2023-01-21 12:34:38.498334: step: 384/530, loss: 0.07745113223791122
2023-01-21 12:34:39.648818: step: 388/530, loss: 0.0005623817560262978
2023-01-21 12:34:40.864896: step: 392/530, loss: 0.035173892974853516
2023-01-21 12:34:42.066104: step: 396/530, loss: 0.0489748977124691
2023-01-21 12:34:43.266738: step: 400/530, loss: 0.001634359359741211
2023-01-21 12:34:44.440400: step: 404/530, loss: 0.006951427552849054
2023-01-21 12:34:45.613972: step: 408/530, loss: 0.0011802196968346834
2023-01-21 12:34:46.790829: step: 412/530, loss: 0.012400436215102673
2023-01-21 12:34:48.034183: step: 416/530, loss: 0.03774872049689293
2023-01-21 12:34:49.215787: step: 420/530, loss: 0.01274251937866211
2023-01-21 12:34:50.390356: step: 424/530, loss: 0.006424236577004194
2023-01-21 12:34:51.566976: step: 428/530, loss: 0.0006192207220010459
2023-01-21 12:34:52.750345: step: 432/530, loss: 0.003768539521843195
2023-01-21 12:34:53.918304: step: 436/530, loss: 0.0005600929143838584
2023-01-21 12:34:55.113685: step: 440/530, loss: 9.918212890625e-05
2023-01-21 12:34:56.266892: step: 444/530, loss: 0.003454923629760742
2023-01-21 12:34:57.417335: step: 448/530, loss: 0.004976654425263405
2023-01-21 12:34:58.601717: step: 452/530, loss: 0.0025743485894054174
2023-01-21 12:34:59.743683: step: 456/530, loss: 0.0011004448169842362
2023-01-21 12:35:00.899032: step: 460/530, loss: 0.0015920639270916581
2023-01-21 12:35:02.041493: step: 464/530, loss: 0.004820060916244984
2023-01-21 12:35:03.198502: step: 468/530, loss: 0.0027841210830956697
2023-01-21 12:35:04.377664: step: 472/530, loss: 0.0010772228706628084
2023-01-21 12:35:05.558304: step: 476/530, loss: 0.10511579364538193
2023-01-21 12:35:06.753732: step: 480/530, loss: 0.009735107421875
2023-01-21 12:35:07.890800: step: 484/530, loss: 0.001150417374446988
2023-01-21 12:35:09.045965: step: 488/530, loss: 0.47361665964126587
2023-01-21 12:35:10.207290: step: 492/530, loss: 1.659393274167087e-05
2023-01-21 12:35:11.374298: step: 496/530, loss: 0.020464323461055756
2023-01-21 12:35:12.615201: step: 500/530, loss: 0.01638164557516575
2023-01-21 12:35:13.768503: step: 504/530, loss: 0.0013010979164391756
2023-01-21 12:35:14.948182: step: 508/530, loss: 0.005679654888808727
2023-01-21 12:35:16.149716: step: 512/530, loss: 0.00033941271249204874
2023-01-21 12:35:17.317035: step: 516/530, loss: 0.00011940002877963707
2023-01-21 12:35:18.476693: step: 520/530, loss: 9.632110959501006e-06
2023-01-21 12:35:19.637619: step: 524/530, loss: 0.005273151211440563
2023-01-21 12:35:20.863503: step: 528/530, loss: 0.023619651794433594
2023-01-21 12:35:21.981834: step: 532/530, loss: 0.0018474578391760588
2023-01-21 12:35:23.195275: step: 536/530, loss: 0.012527274899184704
2023-01-21 12:35:24.376315: step: 540/530, loss: 0.047043945640325546
2023-01-21 12:35:25.603236: step: 544/530, loss: 0.013675117865204811
2023-01-21 12:35:26.739305: step: 548/530, loss: 0.0006269455188885331
2023-01-21 12:35:27.898831: step: 552/530, loss: 0.0001562118559377268
2023-01-21 12:35:29.048454: step: 556/530, loss: 0.000125885009765625
2023-01-21 12:35:30.232195: step: 560/530, loss: 0.054869841784238815
2023-01-21 12:35:31.394850: step: 564/530, loss: 0.0012381552951410413
2023-01-21 12:35:32.561469: step: 568/530, loss: 0.0024313449393957853
2023-01-21 12:35:33.714723: step: 572/530, loss: 0.0017583846347406507
2023-01-21 12:35:34.925556: step: 576/530, loss: 1.7261505490751006e-05
2023-01-21 12:35:36.067506: step: 580/530, loss: 0.031575966626405716
2023-01-21 12:35:37.271811: step: 584/530, loss: 1.392364538332913e-05
2023-01-21 12:35:38.450683: step: 588/530, loss: 0.004573631100356579
2023-01-21 12:35:39.640630: step: 592/530, loss: 0.0180511474609375
2023-01-21 12:35:40.824342: step: 596/530, loss: 0.006071948911994696
2023-01-21 12:35:41.984301: step: 600/530, loss: 0.030272865667939186
2023-01-21 12:35:43.123431: step: 604/530, loss: 0.0009492874378338456
2023-01-21 12:35:44.281497: step: 608/530, loss: 9.946823411155492e-05
2023-01-21 12:35:45.467150: step: 612/530, loss: 0.009868240915238857
2023-01-21 12:35:46.667661: step: 616/530, loss: 0.05019426718354225
2023-01-21 12:35:47.860202: step: 620/530, loss: 0.0007445336086675525
2023-01-21 12:35:49.035429: step: 624/530, loss: 0.03754863515496254
2023-01-21 12:35:50.185601: step: 628/530, loss: 0.0002620696905069053
2023-01-21 12:35:51.396003: step: 632/530, loss: 4.39643845311366e-05
2023-01-21 12:35:52.586719: step: 636/530, loss: 0.0051344153471291065
2023-01-21 12:35:53.742394: step: 640/530, loss: 0.0004296302795410156
2023-01-21 12:35:54.916066: step: 644/530, loss: 7.877349707996473e-05
2023-01-21 12:35:56.096736: step: 648/530, loss: 0.010566520504653454
2023-01-21 12:35:57.286543: step: 652/530, loss: 0.0008101463317871094
2023-01-21 12:35:58.430162: step: 656/530, loss: 9.709596633911133e-05
2023-01-21 12:35:59.645432: step: 660/530, loss: 0.024234723299741745
2023-01-21 12:36:00.907959: step: 664/530, loss: 0.014329529367387295
2023-01-21 12:36:02.074933: step: 668/530, loss: 0.00010221004777122289
2023-01-21 12:36:03.214164: step: 672/530, loss: 0.00029020311194472015
2023-01-21 12:36:04.363597: step: 676/530, loss: 0.0035304068587720394
2023-01-21 12:36:05.592787: step: 680/530, loss: 0.00017032623873092234
2023-01-21 12:36:06.814661: step: 684/530, loss: 0.039608001708984375
2023-01-21 12:36:08.008690: step: 688/530, loss: 0.08978991210460663
2023-01-21 12:36:09.183649: step: 692/530, loss: 0.009096909314393997
2023-01-21 12:36:10.357238: step: 696/530, loss: 0.004308891016989946
2023-01-21 12:36:11.576495: step: 700/530, loss: 0.010627173818647861
2023-01-21 12:36:12.792687: step: 704/530, loss: 0.0014354706509038806
2023-01-21 12:36:13.951793: step: 708/530, loss: 0.0012062073219567537
2023-01-21 12:36:15.137605: step: 712/530, loss: -3.46153956343187e-06
2023-01-21 12:36:16.279622: step: 716/530, loss: 0.000312614458380267
2023-01-21 12:36:17.474730: step: 720/530, loss: 0.013672161847352982
2023-01-21 12:36:18.641468: step: 724/530, loss: 0.0004307747003622353
2023-01-21 12:36:19.818093: step: 728/530, loss: 0.0114281065762043
2023-01-21 12:36:20.976230: step: 732/530, loss: 0.0009140968322753906
2023-01-21 12:36:22.134533: step: 736/530, loss: 0.008310128003358841
2023-01-21 12:36:23.360421: step: 740/530, loss: 0.004988241475075483
2023-01-21 12:36:24.530112: step: 744/530, loss: 8.907317533157766e-05
2023-01-21 12:36:25.708934: step: 748/530, loss: 0.00041608812171034515
2023-01-21 12:36:26.855078: step: 752/530, loss: 0.04133319854736328
2023-01-21 12:36:28.047498: step: 756/530, loss: 0.0003288269217591733
2023-01-21 12:36:29.212470: step: 760/530, loss: 0.005394697189331055
2023-01-21 12:36:30.362623: step: 764/530, loss: 0.0019208908779546618
2023-01-21 12:36:31.600076: step: 768/530, loss: 0.00014419556828215718
2023-01-21 12:36:32.784284: step: 772/530, loss: 0.010583209805190563
2023-01-21 12:36:33.977407: step: 776/530, loss: 0.0008448601001873612
2023-01-21 12:36:35.135117: step: 780/530, loss: 8.144378807628527e-05
2023-01-21 12:36:36.314070: step: 784/530, loss: 0.0014475345378741622
2023-01-21 12:36:37.478030: step: 788/530, loss: 7.62939453125e-06
2023-01-21 12:36:38.686829: step: 792/530, loss: 0.05154099315404892
2023-01-21 12:36:39.879706: step: 796/530, loss: 0.021154213696718216
2023-01-21 12:36:41.046643: step: 800/530, loss: 0.0024848938919603825
2023-01-21 12:36:42.210672: step: 804/530, loss: 0.0038153647910803556
2023-01-21 12:36:43.378355: step: 808/530, loss: 0.06039123982191086
2023-01-21 12:36:44.616730: step: 812/530, loss: 0.007724094670265913
2023-01-21 12:36:45.818126: step: 816/530, loss: 0.0030528069473803043
2023-01-21 12:36:46.983986: step: 820/530, loss: 0.009526634588837624
2023-01-21 12:36:48.168976: step: 824/530, loss: 4.806518700206652e-05
2023-01-21 12:36:49.341268: step: 828/530, loss: 0.00848617684096098
2023-01-21 12:36:50.468584: step: 832/530, loss: 0.012754536233842373
2023-01-21 12:36:51.747352: step: 836/530, loss: 0.0004299163701944053
2023-01-21 12:36:52.870959: step: 840/530, loss: 0.0015683174133300781
2023-01-21 12:36:54.031185: step: 844/530, loss: 0.0032050609588623047
2023-01-21 12:36:55.169194: step: 848/530, loss: 0.005408573430031538
2023-01-21 12:36:56.357382: step: 852/530, loss: 3.700256274896674e-05
2023-01-21 12:36:57.531999: step: 856/530, loss: 0.011404801160097122
2023-01-21 12:36:58.709453: step: 860/530, loss: 0.007604170124977827
2023-01-21 12:36:59.972366: step: 864/530, loss: 0.0003216743643861264
2023-01-21 12:37:01.160428: step: 868/530, loss: 0.0001183509812108241
2023-01-21 12:37:02.356536: step: 872/530, loss: 0.01935749128460884
2023-01-21 12:37:03.543504: step: 876/530, loss: 0.0028211595490574837
2023-01-21 12:37:04.746152: step: 880/530, loss: 0.00755805941298604
2023-01-21 12:37:05.897589: step: 884/530, loss: 0.003159427549690008
2023-01-21 12:37:07.078247: step: 888/530, loss: 0.037175893783569336
2023-01-21 12:37:08.299399: step: 892/530, loss: 0.015821266919374466
2023-01-21 12:37:09.511965: step: 896/530, loss: 0.0014829635620117188
2023-01-21 12:37:10.723244: step: 900/530, loss: 0.00900039728730917
2023-01-21 12:37:11.948399: step: 904/530, loss: 9.262561798095703e-05
2023-01-21 12:37:13.112049: step: 908/530, loss: 0.001655149506404996
2023-01-21 12:37:14.274197: step: 912/530, loss: 0.015964603051543236
2023-01-21 12:37:15.435039: step: 916/530, loss: 0.00024623872013762593
2023-01-21 12:37:16.549627: step: 920/530, loss: 2.1266936528263614e-05
2023-01-21 12:37:17.718225: step: 924/530, loss: 7.762909081066027e-05
2023-01-21 12:37:18.871985: step: 928/530, loss: 2.5749209271452855e-06
2023-01-21 12:37:20.086841: step: 932/530, loss: 0.009514904581010342
2023-01-21 12:37:21.268766: step: 936/530, loss: 0.019620705395936966
2023-01-21 12:37:22.483565: step: 940/530, loss: 0.0007677078247070312
2023-01-21 12:37:23.641008: step: 944/530, loss: 1.697540210443549e-05
2023-01-21 12:37:24.828135: step: 948/530, loss: 0.05004329979419708
2023-01-21 12:37:26.003730: step: 952/530, loss: 0.020263671875
2023-01-21 12:37:27.164358: step: 956/530, loss: 0.022067641839385033
2023-01-21 12:37:28.351869: step: 960/530, loss: 0.006657171528786421
2023-01-21 12:37:29.536039: step: 964/530, loss: 0.006328964605927467
2023-01-21 12:37:30.700278: step: 968/530, loss: 0.0002513885556254536
2023-01-21 12:37:31.876289: step: 972/530, loss: 0.009434843435883522
2023-01-21 12:37:33.067168: step: 976/530, loss: 0.06498666107654572
2023-01-21 12:37:34.238278: step: 980/530, loss: 0.0012529372470453382
2023-01-21 12:37:35.443685: step: 984/530, loss: 0.012515640817582607
2023-01-21 12:37:36.632260: step: 988/530, loss: 1.6307831174344756e-05
2023-01-21 12:37:37.829047: step: 992/530, loss: 0.0017027854919433594
2023-01-21 12:37:38.981485: step: 996/530, loss: 0.002058005426079035
2023-01-21 12:37:40.184307: step: 1000/530, loss: 0.011433720588684082
2023-01-21 12:37:41.357414: step: 1004/530, loss: 0.000885009765625
2023-01-21 12:37:42.585806: step: 1008/530, loss: 0.001210021902807057
2023-01-21 12:37:43.762487: step: 1012/530, loss: 1.392364538332913e-05
2023-01-21 12:37:44.956191: step: 1016/530, loss: 3.62396240234375e-05
2023-01-21 12:37:46.104281: step: 1020/530, loss: 0.007728290744125843
2023-01-21 12:37:47.278536: step: 1024/530, loss: 0.05792379379272461
2023-01-21 12:37:48.462803: step: 1028/530, loss: 0.00032062531681731343
2023-01-21 12:37:49.665834: step: 1032/530, loss: 0.006886482238769531
2023-01-21 12:37:50.853265: step: 1036/530, loss: 0.014691448770463467
2023-01-21 12:37:52.055892: step: 1040/530, loss: 0.005779266357421875
2023-01-21 12:37:53.253249: step: 1044/530, loss: 0.00018901826115325093
2023-01-21 12:37:54.477098: step: 1048/530, loss: 0.0035127641167491674
2023-01-21 12:37:55.635948: step: 1052/530, loss: 0.014005947858095169
2023-01-21 12:37:56.769797: step: 1056/530, loss: 9.555817086948082e-05
2023-01-21 12:37:58.030450: step: 1060/530, loss: -8.77380352903856e-06
2023-01-21 12:37:59.208332: step: 1064/530, loss: 0.001686143921688199
2023-01-21 12:38:00.377597: step: 1068/530, loss: 0.02495570294559002
2023-01-21 12:38:01.560637: step: 1072/530, loss: 0.0002761840878520161
2023-01-21 12:38:02.753392: step: 1076/530, loss: 0.0030611041001975536
2023-01-21 12:38:03.929918: step: 1080/530, loss: 0.0011238097213208675
2023-01-21 12:38:05.083024: step: 1084/530, loss: 0.0015411378117278218
2023-01-21 12:38:06.258953: step: 1088/530, loss: 0.0008461237302981317
2023-01-21 12:38:07.428016: step: 1092/530, loss: 0.0164521224796772
2023-01-21 12:38:08.609784: step: 1096/530, loss: 0.00014743805513717234
2023-01-21 12:38:09.744891: step: 1100/530, loss: 4.301071385270916e-05
2023-01-21 12:38:10.952320: step: 1104/530, loss: 0.0015448570484295487
2023-01-21 12:38:12.161255: step: 1108/530, loss: 0.010260599665343761
2023-01-21 12:38:13.315132: step: 1112/530, loss: 0.009003067389130592
2023-01-21 12:38:14.470721: step: 1116/530, loss: 0.08434911072254181
2023-01-21 12:38:15.650646: step: 1120/530, loss: 0.007406425662338734
2023-01-21 12:38:16.824812: step: 1124/530, loss: 0.004745578393340111
2023-01-21 12:38:18.027351: step: 1128/530, loss: 0.03506889566779137
2023-01-21 12:38:19.190504: step: 1132/530, loss: 0.5541387796401978
2023-01-21 12:38:20.392461: step: 1136/530, loss: 0.0067115784622728825
2023-01-21 12:38:21.548151: step: 1140/530, loss: 0.0021336558274924755
2023-01-21 12:38:22.715857: step: 1144/530, loss: 0.0051889424212276936
2023-01-21 12:38:23.857453: step: 1148/530, loss: 0.05879192799329758
2023-01-21 12:38:25.047316: step: 1152/530, loss: 0.011456489562988281
2023-01-21 12:38:26.221624: step: 1156/530, loss: 4.730224463855848e-05
2023-01-21 12:38:27.393688: step: 1160/530, loss: 0.008330726064741611
2023-01-21 12:38:28.554600: step: 1164/530, loss: 0.00033226015511900187
2023-01-21 12:38:29.698493: step: 1168/530, loss: 0.05797901377081871
2023-01-21 12:38:30.889190: step: 1172/530, loss: 0.019885780289769173
2023-01-21 12:38:32.042571: step: 1176/530, loss: 0.0030896186362951994
2023-01-21 12:38:33.236825: step: 1180/530, loss: 0.0006618499755859375
2023-01-21 12:38:34.420968: step: 1184/530, loss: 2.2602082026423886e-05
2023-01-21 12:38:35.599235: step: 1188/530, loss: 0.0017972945934161544
2023-01-21 12:38:36.780050: step: 1192/530, loss: 0.006542601156979799
2023-01-21 12:38:38.007283: step: 1196/530, loss: 0.014737558551132679
2023-01-21 12:38:39.194832: step: 1200/530, loss: 0.0018316268688067794
2023-01-21 12:38:40.380411: step: 1204/530, loss: 0.028890609741210938
2023-01-21 12:38:41.539336: step: 1208/530, loss: 0.00779228238388896
2023-01-21 12:38:42.705377: step: 1212/530, loss: 0.004622649867087603
2023-01-21 12:38:43.892646: step: 1216/530, loss: 0.06822347640991211
2023-01-21 12:38:45.106180: step: 1220/530, loss: 3.337860107421875e-05
2023-01-21 12:38:46.257164: step: 1224/530, loss: 0.022996138781309128
2023-01-21 12:38:47.413179: step: 1228/530, loss: 0.020897196605801582
2023-01-21 12:38:48.573158: step: 1232/530, loss: 0.0004893302684649825
2023-01-21 12:38:49.747025: step: 1236/530, loss: 0.007553481962531805
2023-01-21 12:38:50.932305: step: 1240/530, loss: 0.014276409521698952
2023-01-21 12:38:52.120924: step: 1244/530, loss: 0.004218960180878639
2023-01-21 12:38:53.278058: step: 1248/530, loss: 0.029697038233280182
2023-01-21 12:38:54.480561: step: 1252/530, loss: 7.524490501964465e-05
2023-01-21 12:38:55.654960: step: 1256/530, loss: 0.08282909542322159
2023-01-21 12:38:56.801684: step: 1260/530, loss: 0.008394146338105202
2023-01-21 12:38:57.981675: step: 1264/530, loss: 0.0020895004272460938
2023-01-21 12:38:59.161420: step: 1268/530, loss: 0.0007704735035076737
2023-01-21 12:39:00.357106: step: 1272/530, loss: 0.00031147003755904734
2023-01-21 12:39:01.596640: step: 1276/530, loss: 0.001314449356868863
2023-01-21 12:39:02.771806: step: 1280/530, loss: 0.00013256072998046875
2023-01-21 12:39:04.000439: step: 1284/530, loss: 3.44276413670741e-05
2023-01-21 12:39:05.213453: step: 1288/530, loss: 0.0028358460403978825
2023-01-21 12:39:06.372856: step: 1292/530, loss: 0.0018567085498943925
2023-01-21 12:39:07.600984: step: 1296/530, loss: 0.0002290725678903982
2023-01-21 12:39:08.739740: step: 1300/530, loss: 0.00034055710420943797
2023-01-21 12:39:09.945956: step: 1304/530, loss: 0.00014047622971702367
2023-01-21 12:39:11.086130: step: 1308/530, loss: 0.0190140251070261
2023-01-21 12:39:12.232475: step: 1312/530, loss: 0.0007493019220419228
2023-01-21 12:39:13.384528: step: 1316/530, loss: 0.021253205835819244
2023-01-21 12:39:14.547888: step: 1320/530, loss: 0.0007530212169513106
2023-01-21 12:39:15.686919: step: 1324/530, loss: 0.004752159118652344
2023-01-21 12:39:16.884345: step: 1328/530, loss: 0.0007967948913574219
2023-01-21 12:39:18.080255: step: 1332/530, loss: 0.043637800961732864
2023-01-21 12:39:19.278989: step: 1336/530, loss: 0.009446716867387295
2023-01-21 12:39:20.494182: step: 1340/530, loss: 0.006819725502282381
2023-01-21 12:39:21.696178: step: 1344/530, loss: 0.0009269714937545359
2023-01-21 12:39:22.853243: step: 1348/530, loss: 0.005797004792839289
2023-01-21 12:39:24.044518: step: 1352/530, loss: 0.008511209860444069
2023-01-21 12:39:25.226839: step: 1356/530, loss: 0.0006796836969442666
2023-01-21 12:39:26.410189: step: 1360/530, loss: 0.0008857726934365928
2023-01-21 12:39:27.654649: step: 1364/530, loss: 0.009960937313735485
2023-01-21 12:39:28.827979: step: 1368/530, loss: 0.0021012306679040194
2023-01-21 12:39:29.990960: step: 1372/530, loss: 0.00013246537127997726
2023-01-21 12:39:31.192730: step: 1376/530, loss: 5.2070619858568534e-05
2023-01-21 12:39:32.355293: step: 1380/530, loss: 0.06548728793859482
2023-01-21 12:39:33.567268: step: 1384/530, loss: 2.155303991457913e-05
2023-01-21 12:39:34.746244: step: 1388/530, loss: 0.004328870680183172
2023-01-21 12:39:35.933711: step: 1392/530, loss: 0.0002286911039846018
2023-01-21 12:39:37.087162: step: 1396/530, loss: -1.7642976217757678e-06
2023-01-21 12:39:38.273158: step: 1400/530, loss: 0.0009002685546875
2023-01-21 12:39:39.477721: step: 1404/530, loss: 0.013399315066635609
2023-01-21 12:39:40.650853: step: 1408/530, loss: 0.017896080389618874
2023-01-21 12:39:41.880558: step: 1412/530, loss: 0.034514620900154114
2023-01-21 12:39:43.103774: step: 1416/530, loss: 0.003491687821224332
2023-01-21 12:39:44.296563: step: 1420/530, loss: 0.004248619079589844
2023-01-21 12:39:45.474129: step: 1424/530, loss: 0.00629157992079854
2023-01-21 12:39:46.620784: step: 1428/530, loss: 0.05060386657714844
2023-01-21 12:39:47.839397: step: 1432/530, loss: 0.0019865036010742188
2023-01-21 12:39:48.965396: step: 1436/530, loss: 0.0010718345874920487
2023-01-21 12:39:50.160294: step: 1440/530, loss: 0.00940332468599081
2023-01-21 12:39:51.389433: step: 1444/530, loss: 4.158019874012098e-05
2023-01-21 12:39:52.535050: step: 1448/530, loss: 0.018683433532714844
2023-01-21 12:39:53.696141: step: 1452/530, loss: 0.01313552912324667
2023-01-21 12:39:54.848606: step: 1456/530, loss: 0.0004421710909809917
2023-01-21 12:39:56.049851: step: 1460/530, loss: 0.0009889602661132812
2023-01-21 12:39:57.242261: step: 1464/530, loss: 0.024580860510468483
2023-01-21 12:39:58.411850: step: 1468/530, loss: 0.0045175557024776936
2023-01-21 12:39:59.576373: step: 1472/530, loss: 0.28092309832572937
2023-01-21 12:40:00.746871: step: 1476/530, loss: 0.00019836427236441523
2023-01-21 12:40:01.927296: step: 1480/530, loss: -4.7683897719252855e-08
2023-01-21 12:40:03.125557: step: 1484/530, loss: 0.0009140014881268144
2023-01-21 12:40:04.309236: step: 1488/530, loss: 0.0036263468209654093
2023-01-21 12:40:05.504244: step: 1492/530, loss: 0.004390430171042681
2023-01-21 12:40:06.709055: step: 1496/530, loss: 0.08982839435338974
2023-01-21 12:40:07.876138: step: 1500/530, loss: 0.022475814446806908
2023-01-21 12:40:09.076402: step: 1504/530, loss: 0.0007926941034384072
2023-01-21 12:40:10.262175: step: 1508/530, loss: 0.005611419677734375
2023-01-21 12:40:11.429344: step: 1512/530, loss: 0.043725013732910156
2023-01-21 12:40:12.601278: step: 1516/530, loss: 0.00036373137845657766
2023-01-21 12:40:13.777400: step: 1520/530, loss: 0.0011141776340082288
2023-01-21 12:40:14.943840: step: 1524/530, loss: 2.7275083994027227e-05
2023-01-21 12:40:16.127264: step: 1528/530, loss: 0.004909897223114967
2023-01-21 12:40:17.315551: step: 1532/530, loss: 0.02686906047165394
2023-01-21 12:40:18.476600: step: 1536/530, loss: 0.03424873575568199
2023-01-21 12:40:19.650250: step: 1540/530, loss: 0.0008774757734499872
2023-01-21 12:40:20.831153: step: 1544/530, loss: 0.0003266334533691406
2023-01-21 12:40:21.983990: step: 1548/530, loss: 1.0013580322265625e-05
2023-01-21 12:40:23.185992: step: 1552/530, loss: 0.0026200294960290194
2023-01-21 12:40:24.360281: step: 1556/530, loss: 0.0070549012161791325
2023-01-21 12:40:25.514455: step: 1560/530, loss: 0.01136865559965372
2023-01-21 12:40:26.711558: step: 1564/530, loss: 9.822845458984375e-05
2023-01-21 12:40:27.867626: step: 1568/530, loss: 0.02331266552209854
2023-01-21 12:40:29.059088: step: 1572/530, loss: 1.1444089977885596e-06
2023-01-21 12:40:30.208047: step: 1576/530, loss: 0.0058283330872654915
2023-01-21 12:40:31.344116: step: 1580/530, loss: 0.03490380942821503
2023-01-21 12:40:32.525425: step: 1584/530, loss: 0.004513788037002087
2023-01-21 12:40:33.684256: step: 1588/530, loss: 0.0018037796253338456
2023-01-21 12:40:34.831693: step: 1592/530, loss: 0.005067348480224609
2023-01-21 12:40:36.032595: step: 1596/530, loss: 1.068115216185106e-05
2023-01-21 12:40:37.200020: step: 1600/530, loss: 0.00022296904353424907
2023-01-21 12:40:38.387034: step: 1604/530, loss: 2.117157055181451e-05
2023-01-21 12:40:39.593281: step: 1608/530, loss: 0.015858221799135208
2023-01-21 12:40:40.735377: step: 1612/530, loss: 1.4019013178767636e-05
2023-01-21 12:40:41.902672: step: 1616/530, loss: 0.0002799034118652344
2023-01-21 12:40:43.104014: step: 1620/530, loss: 0.0002558708074502647
2023-01-21 12:40:44.288458: step: 1624/530, loss: 0.00590591412037611
2023-01-21 12:40:45.450137: step: 1628/530, loss: 0.005512046627700329
2023-01-21 12:40:46.673360: step: 1632/530, loss: 0.07719950377941132
2023-01-21 12:40:47.845675: step: 1636/530, loss: 0.013679122552275658
2023-01-21 12:40:48.977178: step: 1640/530, loss: 0.05072479322552681
2023-01-21 12:40:50.177717: step: 1644/530, loss: 0.022053956985473633
2023-01-21 12:40:51.350679: step: 1648/530, loss: 0.0007184505229815841
2023-01-21 12:40:52.587191: step: 1652/530, loss: 0.000417795788962394
2023-01-21 12:40:53.835481: step: 1656/530, loss: 0.009464453905820847
2023-01-21 12:40:55.125792: step: 1660/530, loss: 0.04511604458093643
2023-01-21 12:40:56.319691: step: 1664/530, loss: 0.03674044832587242
2023-01-21 12:40:57.484333: step: 1668/530, loss: 0.00019321442232467234
2023-01-21 12:40:58.673210: step: 1672/530, loss: 0.0008433341863565147
2023-01-21 12:40:59.845604: step: 1676/530, loss: 0.008237838745117188
2023-01-21 12:41:01.038214: step: 1680/530, loss: 0.057820796966552734
2023-01-21 12:41:02.270213: step: 1684/530, loss: 0.015452957712113857
2023-01-21 12:41:03.461994: step: 1688/530, loss: 0.002544879913330078
2023-01-21 12:41:04.644637: step: 1692/530, loss: 0.013648772612214088
2023-01-21 12:41:05.816300: step: 1696/530, loss: 0.194017231464386
2023-01-21 12:41:07.016890: step: 1700/530, loss: 0.00018358230590820312
2023-01-21 12:41:08.161112: step: 1704/530, loss: 0.001372528146021068
2023-01-21 12:41:09.306036: step: 1708/530, loss: 0.020580768585205078
2023-01-21 12:41:10.449602: step: 1712/530, loss: 0.000981235527433455
2023-01-21 12:41:11.607171: step: 1716/530, loss: 0.004852390848100185
2023-01-21 12:41:12.764082: step: 1720/530, loss: 0.015310479328036308
2023-01-21 12:41:13.988726: step: 1724/530, loss: 0.023380279541015625
2023-01-21 12:41:15.198754: step: 1728/530, loss: 0.00010576248314464465
2023-01-21 12:41:16.348688: step: 1732/530, loss: 0.0026194097008556128
2023-01-21 12:41:17.542418: step: 1736/530, loss: 0.0059715271927416325
2023-01-21 12:41:18.701476: step: 1740/530, loss: 0.0016260147094726562
2023-01-21 12:41:19.871620: step: 1744/530, loss: 0.003533935407176614
2023-01-21 12:41:21.049755: step: 1748/530, loss: 0.0035459520295262337
2023-01-21 12:41:22.287287: step: 1752/530, loss: 0.04165840148925781
2023-01-21 12:41:23.439117: step: 1756/530, loss: 0.01239700336009264
2023-01-21 12:41:24.610789: step: 1760/530, loss: 0.00011367798288119957
2023-01-21 12:41:25.804820: step: 1764/530, loss: 0.00020933151245117188
2023-01-21 12:41:26.986510: step: 1768/530, loss: 0.01231927890330553
2023-01-21 12:41:28.184561: step: 1772/530, loss: 0.0012462616432458162
2023-01-21 12:41:29.422729: step: 1776/530, loss: 0.021958064287900925
2023-01-21 12:41:30.527556: step: 1780/530, loss: 0.0005257606972008944
2023-01-21 12:41:31.687766: step: 1784/530, loss: 0.0007620811811648309
2023-01-21 12:41:32.857358: step: 1788/530, loss: 9.822846186580136e-05
2023-01-21 12:41:34.034804: step: 1792/530, loss: 0.01444787997752428
2023-01-21 12:41:35.206216: step: 1796/530, loss: 0.011604023166000843
2023-01-21 12:41:36.402246: step: 1800/530, loss: 0.0021286250557750463
2023-01-21 12:41:37.593956: step: 1804/530, loss: 0.02203369140625
2023-01-21 12:41:38.765172: step: 1808/530, loss: 0.09160070866346359
2023-01-21 12:41:39.919572: step: 1812/530, loss: 0.0006944656488485634
2023-01-21 12:41:41.087517: step: 1816/530, loss: 0.0673886314034462
2023-01-21 12:41:42.273912: step: 1820/530, loss: 0.002995395567268133
2023-01-21 12:41:43.450361: step: 1824/530, loss: 0.003184699919074774
2023-01-21 12:41:44.604519: step: 1828/530, loss: 0.004975604824721813
2023-01-21 12:41:45.778999: step: 1832/530, loss: 0.0010208130115643144
2023-01-21 12:41:46.966829: step: 1836/530, loss: 0.004937982652336359
2023-01-21 12:41:48.170443: step: 1840/530, loss: 0.000186920166015625
2023-01-21 12:41:49.362597: step: 1844/530, loss: 0.004055976867675781
2023-01-21 12:41:50.547529: step: 1848/530, loss: 0.0027333260513842106
2023-01-21 12:41:51.715831: step: 1852/530, loss: 0.0010071754222735763
2023-01-21 12:41:52.903107: step: 1856/530, loss: 0.0011112213833257556
2023-01-21 12:41:54.048691: step: 1860/530, loss: 0.026075219735503197
2023-01-21 12:41:55.158150: step: 1864/530, loss: 0.003545474959537387
2023-01-21 12:41:56.322642: step: 1868/530, loss: 0.0871007964015007
2023-01-21 12:41:57.466558: step: 1872/530, loss: 4.37736525782384e-05
2023-01-21 12:41:58.666260: step: 1876/530, loss: 0.03094806708395481
2023-01-21 12:41:59.820459: step: 1880/530, loss: 0.004812241066247225
2023-01-21 12:42:01.044432: step: 1884/530, loss: 0.004081630613654852
2023-01-21 12:42:02.232864: step: 1888/530, loss: 0.03372840955853462
2023-01-21 12:42:03.418763: step: 1892/530, loss: 0.0009820937411859632
2023-01-21 12:42:04.621341: step: 1896/530, loss: 0.05806773900985718
2023-01-21 12:42:05.765063: step: 1900/530, loss: 0.0023453712929040194
2023-01-21 12:42:06.985485: step: 1904/530, loss: 0.014659976586699486
2023-01-21 12:42:08.184605: step: 1908/530, loss: 0.0034152986481785774
2023-01-21 12:42:09.348328: step: 1912/530, loss: 0.0011112213833257556
2023-01-21 12:42:10.506482: step: 1916/530, loss: 0.010769081301987171
2023-01-21 12:42:11.671899: step: 1920/530, loss: 0.050217293202877045
2023-01-21 12:42:12.923829: step: 1924/530, loss: 0.0021835328079760075
2023-01-21 12:42:14.118519: step: 1928/530, loss: 0.0014083862770348787
2023-01-21 12:42:15.257954: step: 1932/530, loss: 0.0004518509085755795
2023-01-21 12:42:16.470110: step: 1936/530, loss: 0.0013151168823242188
2023-01-21 12:42:17.665688: step: 1940/530, loss: 0.0003743171691894531
2023-01-21 12:42:18.845167: step: 1944/530, loss: 0.0037317750975489616
2023-01-21 12:42:20.056379: step: 1948/530, loss: 0.0014743804931640625
2023-01-21 12:42:21.200099: step: 1952/530, loss: 7.400512549793348e-05
2023-01-21 12:42:22.387074: step: 1956/530, loss: 0.00670623779296875
2023-01-21 12:42:23.545512: step: 1960/530, loss: 0.01037659589201212
2023-01-21 12:42:24.735640: step: 1964/530, loss: 0.08839912712574005
2023-01-21 12:42:25.948930: step: 1968/530, loss: 0.0008859634399414062
2023-01-21 12:42:27.131284: step: 1972/530, loss: 0.002801323076710105
2023-01-21 12:42:28.271592: step: 1976/530, loss: 0.0005109787452965975
2023-01-21 12:42:29.447741: step: 1980/530, loss: 0.41833528876304626
2023-01-21 12:42:30.578380: step: 1984/530, loss: 0.0005877971998415887
2023-01-21 12:42:31.743412: step: 1988/530, loss: 0.044048406183719635
2023-01-21 12:42:32.893668: step: 1992/530, loss: 0.0008211136446334422
2023-01-21 12:42:34.060082: step: 1996/530, loss: 0.0005893707275390625
2023-01-21 12:42:35.237643: step: 2000/530, loss: 0.04506273195147514
2023-01-21 12:42:36.397885: step: 2004/530, loss: 0.016488265246152878
2023-01-21 12:42:37.548131: step: 2008/530, loss: 0.06820683181285858
2023-01-21 12:42:38.687657: step: 2012/530, loss: 0.2930595278739929
2023-01-21 12:42:39.895029: step: 2016/530, loss: 0.08129578083753586
2023-01-21 12:42:41.052983: step: 2020/530, loss: 0.0015571117401123047
2023-01-21 12:42:42.237792: step: 2024/530, loss: 0.004266262520104647
2023-01-21 12:42:43.462052: step: 2028/530, loss: 0.023415755480527878
2023-01-21 12:42:44.650008: step: 2032/530, loss: 0.00029535291832871735
2023-01-21 12:42:45.894827: step: 2036/530, loss: 0.002544593997299671
2023-01-21 12:42:47.098006: step: 2040/530, loss: 0.01532745361328125
2023-01-21 12:42:48.262788: step: 2044/530, loss: 0.02802753448486328
2023-01-21 12:42:49.458060: step: 2048/530, loss: 0.09281416237354279
2023-01-21 12:42:50.629654: step: 2052/530, loss: 0.0054483418352901936
2023-01-21 12:42:51.788584: step: 2056/530, loss: 0.006575680337846279
2023-01-21 12:42:52.973238: step: 2060/530, loss: 0.0006768226739950478
2023-01-21 12:42:54.138257: step: 2064/530, loss: 0.00012712478928733617
2023-01-21 12:42:55.312605: step: 2068/530, loss: 0.0015028000343590975
2023-01-21 12:42:56.533448: step: 2072/530, loss: 1.3160706657799892e-05
2023-01-21 12:42:57.718363: step: 2076/530, loss: 0.00200996408239007
2023-01-21 12:42:58.862009: step: 2080/530, loss: 0.0028454780112951994
2023-01-21 12:43:00.029155: step: 2084/530, loss: 0.001373386476188898
2023-01-21 12:43:01.236290: step: 2088/530, loss: 0.0005094528314657509
2023-01-21 12:43:02.448548: step: 2092/530, loss: 0.01798381842672825
2023-01-21 12:43:03.688130: step: 2096/530, loss: 0.01404180470854044
2023-01-21 12:43:04.849810: step: 2100/530, loss: 0.006818962283432484
2023-01-21 12:43:06.023480: step: 2104/530, loss: 0.0044081686064600945
2023-01-21 12:43:07.157062: step: 2108/530, loss: 0.004641341976821423
2023-01-21 12:43:08.386487: step: 2112/530, loss: 0.0015964508056640625
2023-01-21 12:43:09.552065: step: 2116/530, loss: 0.011506086215376854
2023-01-21 12:43:10.739994: step: 2120/530, loss: 0.001605945872142911
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
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': 22}
Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Chinese: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 12:44:05.860658: step: 4/530, loss: 0.003424739930778742
2023-01-21 12:44:07.051189: step: 8/530, loss: 0.004018020816147327
2023-01-21 12:44:08.198548: step: 12/530, loss: 0.004458618350327015
2023-01-21 12:44:09.386209: step: 16/530, loss: 5.340576171875e-05
2023-01-21 12:44:10.562376: step: 20/530, loss: 0.012980175204575062
2023-01-21 12:44:11.715617: step: 24/530, loss: 0.0033050538040697575
2023-01-21 12:44:12.939777: step: 28/530, loss: 0.00045351980952546
2023-01-21 12:44:14.084414: step: 32/530, loss: 1.0538101378188003e-05
2023-01-21 12:44:15.241885: step: 36/530, loss: 9.527207294013351e-05
2023-01-21 12:44:16.382379: step: 40/530, loss: 3.6525725590763614e-05
2023-01-21 12:44:17.555094: step: 44/530, loss: 0.012993239797651768
2023-01-21 12:44:18.725853: step: 48/530, loss: 0.010903931222856045
2023-01-21 12:44:19.889285: step: 52/530, loss: 0.00037097930908203125
2023-01-21 12:44:21.058913: step: 56/530, loss: 0.0013163567055016756
2023-01-21 12:44:22.246349: step: 60/530, loss: 0.02053070068359375
2023-01-21 12:44:23.427771: step: 64/530, loss: 0.00100116734392941
2023-01-21 12:44:24.570173: step: 68/530, loss: 0.00011148452904308215
2023-01-21 12:44:25.715888: step: 72/530, loss: 0.008852195926010609
2023-01-21 12:44:26.885626: step: 76/530, loss: 0.013536644168198109
2023-01-21 12:44:28.036409: step: 80/530, loss: 8.239746239269152e-05
2023-01-21 12:44:29.198433: step: 84/530, loss: 7.22885160939768e-05
2023-01-21 12:44:30.388452: step: 88/530, loss: 0.011665153317153454
2023-01-21 12:44:31.600298: step: 92/530, loss: 0.007336711976677179
2023-01-21 12:44:32.749662: step: 96/530, loss: 7.23838820704259e-05
2023-01-21 12:44:33.947009: step: 100/530, loss: 4.272460864740424e-05
2023-01-21 12:44:35.146505: step: 104/530, loss: 3.137588646495715e-05
2023-01-21 12:44:36.324785: step: 108/530, loss: 0.00027918818523176014
2023-01-21 12:44:37.482998: step: 112/530, loss: 9.136199514614418e-05
2023-01-21 12:44:38.671851: step: 116/530, loss: -1.5258788153005298e-06
2023-01-21 12:44:39.893294: step: 120/530, loss: 5.378723290050402e-05
2023-01-21 12:44:41.061279: step: 124/530, loss: 0.00127239222638309
2023-01-21 12:44:42.255610: step: 128/530, loss: 0.012261008843779564
2023-01-21 12:44:43.417137: step: 132/530, loss: 0.038495443761348724
2023-01-21 12:44:44.599545: step: 136/530, loss: 0.008259868249297142
2023-01-21 12:44:45.763973: step: 140/530, loss: 0.0006150722620077431
2023-01-21 12:44:46.920986: step: 144/530, loss: 0.0029197693802416325
2023-01-21 12:44:48.075484: step: 148/530, loss: 0.00023794174194335938
2023-01-21 12:44:49.270896: step: 152/530, loss: 0.02695331536233425
2023-01-21 12:44:50.469471: step: 156/530, loss: 0.07549522817134857
2023-01-21 12:44:51.588775: step: 160/530, loss: 0.0029567719902843237
2023-01-21 12:44:52.727757: step: 164/530, loss: 2.059936559817288e-05
2023-01-21 12:44:53.916610: step: 168/530, loss: 0.001317787216976285
2023-01-21 12:44:55.070378: step: 172/530, loss: 0.0003772735653910786
2023-01-21 12:44:56.255764: step: 176/530, loss: 9.34600830078125e-05
2023-01-21 12:44:57.430387: step: 180/530, loss: 0.0011773108271881938
2023-01-21 12:44:58.608985: step: 184/530, loss: 0.002960681915283203
2023-01-21 12:44:59.788466: step: 188/530, loss: 0.034941960126161575
2023-01-21 12:45:00.959794: step: 192/530, loss: 0.00020637513080146164
2023-01-21 12:45:02.166284: step: 196/530, loss: 0.0005014419439248741
2023-01-21 12:45:03.367263: step: 200/530, loss: 0.04156685248017311
2023-01-21 12:45:04.528742: step: 204/530, loss: 2.8085709345759824e-05
2023-01-21 12:45:05.705445: step: 208/530, loss: 0.0003295898495707661
2023-01-21 12:45:06.864240: step: 212/530, loss: 0.0008407592540606856
2023-01-21 12:45:08.048417: step: 216/530, loss: 0.018683435395359993
2023-01-21 12:45:09.156342: step: 220/530, loss: 7.123946852516383e-05
2023-01-21 12:45:10.368074: step: 224/530, loss: 0.00022833794355392456
2023-01-21 12:45:11.527408: step: 228/530, loss: 0.0008405685075558722
2023-01-21 12:45:12.669851: step: 232/530, loss: 0.0003780364932026714
2023-01-21 12:45:13.817731: step: 236/530, loss: 0.0002020835963776335
2023-01-21 12:45:14.947347: step: 240/530, loss: 0.0025697709061205387
2023-01-21 12:45:16.129371: step: 244/530, loss: 0.06228943169116974
2023-01-21 12:45:17.356762: step: 248/530, loss: 0.005413437262177467
2023-01-21 12:45:18.561341: step: 252/530, loss: 0.00015182494826149195
2023-01-21 12:45:19.731703: step: 256/530, loss: 0.0018491744995117188
2023-01-21 12:45:20.883498: step: 260/530, loss: 3.0517578125e-05
2023-01-21 12:45:22.130509: step: 264/530, loss: 0.004176139831542969
2023-01-21 12:45:23.310285: step: 268/530, loss: 0.029385756701231003
2023-01-21 12:45:24.473577: step: 272/530, loss: 0.00019865036301780492
2023-01-21 12:45:25.661781: step: 276/530, loss: 0.010694503784179688
2023-01-21 12:45:26.861104: step: 280/530, loss: 0.04029655456542969
2023-01-21 12:45:28.000475: step: 284/530, loss: 0.0018493651878088713
2023-01-21 12:45:29.160505: step: 288/530, loss: 0.003316688584163785
2023-01-21 12:45:30.342554: step: 292/530, loss: 0.012442111037671566
2023-01-21 12:45:31.524790: step: 296/530, loss: 0.000630283378995955
2023-01-21 12:45:32.695944: step: 300/530, loss: 0.0062122349627316
2023-01-21 12:45:33.877892: step: 304/530, loss: 0.042719174176454544
2023-01-21 12:45:35.102044: step: 308/530, loss: -3.051757857974735e-06
2023-01-21 12:45:36.333225: step: 312/530, loss: 0.0012497903080657125
2023-01-21 12:45:37.533283: step: 316/530, loss: 0.03459300845861435
2023-01-21 12:45:38.757683: step: 320/530, loss: 0.04709320142865181
2023-01-21 12:45:39.944577: step: 324/530, loss: 0.016632556915283203
2023-01-21 12:45:41.141333: step: 328/530, loss: 0.000469207763671875
2023-01-21 12:45:42.322856: step: 332/530, loss: 0.028017044067382812
2023-01-21 12:45:43.529606: step: 336/530, loss: 0.0040229796431958675
2023-01-21 12:45:44.658946: step: 340/530, loss: 0.0012210846180096269
2023-01-21 12:45:45.836387: step: 344/530, loss: 0.10255460441112518
2023-01-21 12:45:46.995930: step: 348/530, loss: -2.1934511096333154e-06
2023-01-21 12:45:48.145629: step: 352/530, loss: 7.190705218818039e-05
2023-01-21 12:45:49.309694: step: 356/530, loss: 0.00010929108248092234
2023-01-21 12:45:50.471610: step: 360/530, loss: 0.020425032824277878
2023-01-21 12:45:51.667195: step: 364/530, loss: 0.004412079229950905
2023-01-21 12:45:52.861112: step: 368/530, loss: 0.05528130754828453
2023-01-21 12:45:54.049593: step: 372/530, loss: 5.445480201160535e-05
2023-01-21 12:45:55.234506: step: 376/530, loss: 0.0001678466796875
2023-01-21 12:45:56.414452: step: 380/530, loss: 0.006081533618271351
2023-01-21 12:45:57.601393: step: 384/530, loss: 0.005450630094856024
2023-01-21 12:45:58.758485: step: 388/530, loss: 0.004245090764015913
2023-01-21 12:45:59.966847: step: 392/530, loss: 0.02884502336382866
2023-01-21 12:46:01.185502: step: 396/530, loss: 0.1141141876578331
2023-01-21 12:46:02.345731: step: 400/530, loss: 0.009141446091234684
2023-01-21 12:46:03.496847: step: 404/530, loss: 1.9073479506914737e-07
2023-01-21 12:46:04.659897: step: 408/530, loss: 0.14864583313465118
2023-01-21 12:46:05.811216: step: 412/530, loss: 0.013268853537738323
2023-01-21 12:46:07.040562: step: 416/530, loss: 0.003097248263657093
2023-01-21 12:46:08.214735: step: 420/530, loss: 0.00128345494158566
2023-01-21 12:46:09.399247: step: 424/530, loss: 1.220703143189894e-05
2023-01-21 12:46:10.592520: step: 428/530, loss: 0.0031614303588867188
2023-01-21 12:46:11.800095: step: 432/530, loss: 0.0001514911709818989
2023-01-21 12:46:12.993747: step: 436/530, loss: 0.02956867218017578
2023-01-21 12:46:14.170436: step: 440/530, loss: 2.2602082026423886e-05
2023-01-21 12:46:15.353614: step: 444/530, loss: 9.403228614246473e-05
2023-01-21 12:46:16.528989: step: 448/530, loss: 0.018086815252900124
2023-01-21 12:46:17.654169: step: 452/530, loss: 6.28471389063634e-05
2023-01-21 12:46:18.799741: step: 456/530, loss: 0.014873409643769264
2023-01-21 12:46:19.975023: step: 460/530, loss: 8.0108642578125e-05
2023-01-21 12:46:21.165022: step: 464/530, loss: 0.018649864941835403
2023-01-21 12:46:22.320973: step: 468/530, loss: 6.11305222264491e-05
2023-01-21 12:46:23.528452: step: 472/530, loss: 0.010495376773178577
2023-01-21 12:46:24.707864: step: 476/530, loss: 0.0023288726806640625
2023-01-21 12:46:25.896814: step: 480/530, loss: 0.01381759624928236
2023-01-21 12:46:27.071383: step: 484/530, loss: 0.004343274515122175
2023-01-21 12:46:28.256789: step: 488/530, loss: 0.2963119447231293
2023-01-21 12:46:29.414081: step: 492/530, loss: 0.016789723187685013
2023-01-21 12:46:30.600047: step: 496/530, loss: 0.005762734916061163
2023-01-21 12:46:31.789565: step: 500/530, loss: 0.019247055053710938
2023-01-21 12:46:32.977400: step: 504/530, loss: 0.11031127721071243
2023-01-21 12:46:34.199719: step: 508/530, loss: 0.002789497608318925
2023-01-21 12:46:35.354918: step: 512/530, loss: 0.04680890962481499
2023-01-21 12:46:36.542996: step: 516/530, loss: 0.00012893676466774195
2023-01-21 12:46:37.768080: step: 520/530, loss: 0.005897474475204945
2023-01-21 12:46:38.926509: step: 524/530, loss: 0.0003764152352232486
2023-01-21 12:46:40.124646: step: 528/530, loss: 0.01007699966430664
2023-01-21 12:46:41.298167: step: 532/530, loss: 0.006680965423583984
2023-01-21 12:46:42.483299: step: 536/530, loss: 0.00040912628173828125
2023-01-21 12:46:43.684783: step: 540/530, loss: 4.978180004400201e-05
2023-01-21 12:46:44.881118: step: 544/530, loss: 0.0003132820420432836
2023-01-21 12:46:46.066610: step: 548/530, loss: 0.004288482945412397
2023-01-21 12:46:47.233697: step: 552/530, loss: 0.0003602028009481728
2023-01-21 12:46:48.432645: step: 556/530, loss: 0.007989502511918545
2023-01-21 12:46:49.587172: step: 560/530, loss: 0.0012689590221270919
2023-01-21 12:46:50.756565: step: 564/530, loss: 0.005208635702729225
2023-01-21 12:46:51.930529: step: 568/530, loss: 0.0009551048278808594
2023-01-21 12:46:53.119189: step: 572/530, loss: 0.005188846495002508
2023-01-21 12:46:54.304561: step: 576/530, loss: 0.02417469210922718
2023-01-21 12:46:55.507693: step: 580/530, loss: 4.9400332500226796e-05
2023-01-21 12:46:56.696216: step: 584/530, loss: 0.00015773772611282766
2023-01-21 12:46:57.896768: step: 588/530, loss: 0.0002110004425048828
2023-01-21 12:46:59.062203: step: 592/530, loss: 0.0015655518509447575
2023-01-21 12:47:00.211704: step: 596/530, loss: 1.850128137448337e-05
2023-01-21 12:47:01.500658: step: 600/530, loss: 0.0031991959549486637
2023-01-21 12:47:02.687351: step: 604/530, loss: 0.0034526826348155737
2023-01-21 12:47:03.831189: step: 608/530, loss: 0.018709946423768997
2023-01-21 12:47:05.035758: step: 612/530, loss: 0.010827064514160156
2023-01-21 12:47:06.225410: step: 616/530, loss: 0.0048656463623046875
2023-01-21 12:47:07.417534: step: 620/530, loss: 0.005568885710090399
2023-01-21 12:47:08.632310: step: 624/530, loss: 0.00010585784912109375
2023-01-21 12:47:09.818498: step: 628/530, loss: 0.0006314277998171747
2023-01-21 12:47:11.000871: step: 632/530, loss: 0.054948996752500534
2023-01-21 12:47:12.214417: step: 636/530, loss: 0.0015434265369549394
2023-01-21 12:47:13.384680: step: 640/530, loss: 0.023142529651522636
2023-01-21 12:47:14.597171: step: 644/530, loss: 0.018304824829101562
2023-01-21 12:47:15.787250: step: 648/530, loss: 0.0011981964344158769
2023-01-21 12:47:16.974660: step: 652/530, loss: 0.007338809780776501
2023-01-21 12:47:18.130613: step: 656/530, loss: 0.0020253180991858244
2023-01-21 12:47:19.286329: step: 660/530, loss: -7.629394644936838e-07
2023-01-21 12:47:20.481451: step: 664/530, loss: 0.0057255979627370834
2023-01-21 12:47:21.644077: step: 668/530, loss: 0.0007538318750448525
2023-01-21 12:47:22.833972: step: 672/530, loss: 0.00047397613525390625
2023-01-21 12:47:24.021743: step: 676/530, loss: 0.0005088806501589715
2023-01-21 12:47:25.196559: step: 680/530, loss: 0.0016721725696697831
2023-01-21 12:47:26.383912: step: 684/530, loss: 3.967285010730848e-05
2023-01-21 12:47:27.585716: step: 688/530, loss: 0.00017299651517532766
2023-01-21 12:47:28.793942: step: 692/530, loss: 0.025927353650331497
2023-01-21 12:47:29.945577: step: 696/530, loss: 0.01835918426513672
2023-01-21 12:47:31.117595: step: 700/530, loss: 0.03897666931152344
2023-01-21 12:47:32.304729: step: 704/530, loss: 0.02163524553179741
2023-01-21 12:47:33.515244: step: 708/530, loss: 0.0012620926136150956
2023-01-21 12:47:34.674154: step: 712/530, loss: 0.00028858185396529734
2023-01-21 12:47:35.894607: step: 716/530, loss: 0.015540754422545433
2023-01-21 12:47:37.042268: step: 720/530, loss: 3.069639205932617e-06
2023-01-21 12:47:38.280875: step: 724/530, loss: 0.0012387275928631425
2023-01-21 12:47:39.440172: step: 728/530, loss: 0.00011291504051769152
2023-01-21 12:47:40.599880: step: 732/530, loss: 5.9150161177967675e-06
2023-01-21 12:47:41.822011: step: 736/530, loss: 0.00010328293137717992
2023-01-21 12:47:42.990732: step: 740/530, loss: 0.0010553359752520919
2023-01-21 12:47:44.166280: step: 744/530, loss: 0.005288219545036554
2023-01-21 12:47:45.381304: step: 748/530, loss: 1.4495850336970761e-05
2023-01-21 12:47:46.524762: step: 752/530, loss: 3.14712519866589e-06
2023-01-21 12:47:47.657936: step: 756/530, loss: 0.0045181275345385075
2023-01-21 12:47:48.856023: step: 760/530, loss: 0.013479471206665039
2023-01-21 12:47:50.056685: step: 764/530, loss: 0.060167886316776276
2023-01-21 12:47:51.205110: step: 768/530, loss: 0.02922964096069336
2023-01-21 12:47:52.364339: step: 772/530, loss: 0.0001808166562113911
2023-01-21 12:47:53.541645: step: 776/530, loss: 0.0025566101539880037
2023-01-21 12:47:54.696002: step: 780/530, loss: 6.179809861350805e-05
2023-01-21 12:47:55.881365: step: 784/530, loss: 2.9039383662166074e-05
2023-01-21 12:47:57.091785: step: 788/530, loss: 0.0418337844312191
2023-01-21 12:47:58.251902: step: 792/530, loss: 0.09356942027807236
2023-01-21 12:47:59.453955: step: 796/530, loss: 0.018194295465946198
2023-01-21 12:48:00.586186: step: 800/530, loss: 0.0008517265086993575
2023-01-21 12:48:01.772991: step: 804/530, loss: 1.6880036127986386e-05
2023-01-21 12:48:02.949528: step: 808/530, loss: 0.021120835095643997
2023-01-21 12:48:04.129008: step: 812/530, loss: 0.15958061814308167
2023-01-21 12:48:05.283731: step: 816/530, loss: 0.00013704299635719508
2023-01-21 12:48:06.439565: step: 820/530, loss: 0.00041797160520218313
2023-01-21 12:48:07.585857: step: 824/530, loss: 0.003691387362778187
2023-01-21 12:48:08.780606: step: 828/530, loss: 0.012251567095518112
2023-01-21 12:48:09.948896: step: 832/530, loss: 9.632110959501006e-06
2023-01-21 12:48:11.228979: step: 836/530, loss: 0.001038551446981728
2023-01-21 12:48:12.397228: step: 840/530, loss: 0.0001832962007028982
2023-01-21 12:48:13.602670: step: 844/530, loss: 0.017710590735077858
2023-01-21 12:48:14.833914: step: 848/530, loss: 0.014767074026167393
2023-01-21 12:48:15.985134: step: 852/530, loss: 0.0002273559512104839
2023-01-21 12:48:17.150405: step: 856/530, loss: 6.046295311534777e-05
2023-01-21 12:48:18.368671: step: 860/530, loss: 8.010865713004023e-06
2023-01-21 12:48:19.528345: step: 864/530, loss: 0.001394128892570734
2023-01-21 12:48:20.690672: step: 868/530, loss: 1.4400481632037554e-05
2023-01-21 12:48:21.861747: step: 872/530, loss: 2.002715973503655e-06
2023-01-21 12:48:23.029389: step: 876/530, loss: 0.00047912599984556437
2023-01-21 12:48:24.201081: step: 880/530, loss: 0.07759761810302734
2023-01-21 12:48:25.379760: step: 884/530, loss: 3.547668529790826e-05
2023-01-21 12:48:26.562150: step: 888/530, loss: 0.0688687339425087
2023-01-21 12:48:27.733164: step: 892/530, loss: 0.026904869824647903
2023-01-21 12:48:28.929797: step: 896/530, loss: -3.6621091567212716e-05
2023-01-21 12:48:30.140784: step: 900/530, loss: 0.00119609828107059
2023-01-21 12:48:31.290000: step: 904/530, loss: 0.0021844864822924137
2023-01-21 12:48:32.423464: step: 908/530, loss: 8.387566049350426e-05
2023-01-21 12:48:33.598901: step: 912/530, loss: 0.00261192349717021
2023-01-21 12:48:34.738809: step: 916/530, loss: 0.005834389012306929
2023-01-21 12:48:35.934325: step: 920/530, loss: -2.098083541568485e-06
2023-01-21 12:48:37.145096: step: 924/530, loss: 0.0010517120826989412
2023-01-21 12:48:38.316737: step: 928/530, loss: 0.0006122589111328125
2023-01-21 12:48:39.503531: step: 932/530, loss: 0.006759834475815296
2023-01-21 12:48:40.663989: step: 936/530, loss: 0.0006929397350177169
2023-01-21 12:48:41.880707: step: 940/530, loss: 0.002057981677353382
2023-01-21 12:48:43.025309: step: 944/530, loss: 0.0024179460015147924
2023-01-21 12:48:44.192140: step: 948/530, loss: 0.00021333694166969508
2023-01-21 12:48:45.349605: step: 952/530, loss: 0.000305539375403896
2023-01-21 12:48:46.504317: step: 956/530, loss: 0.004509163089096546
2023-01-21 12:48:47.668134: step: 960/530, loss: 0.01748066022992134
2023-01-21 12:48:48.927040: step: 964/530, loss: 0.0003255844349041581
2023-01-21 12:48:50.105421: step: 968/530, loss: 0.00025391578674316406
2023-01-21 12:48:51.256552: step: 972/530, loss: 0.0030090808868408203
2023-01-21 12:48:52.471663: step: 976/530, loss: 0.005576896481215954
2023-01-21 12:48:53.664411: step: 980/530, loss: 3.719329833984375e-05
2023-01-21 12:48:54.941352: step: 984/530, loss: 0.009737014770507812
2023-01-21 12:48:56.101124: step: 988/530, loss: 0.00018544196791481227
2023-01-21 12:48:57.276707: step: 992/530, loss: 0.0004286766052246094
2023-01-21 12:48:58.483562: step: 996/530, loss: 1.8692018784349784e-05
2023-01-21 12:48:59.633399: step: 1000/530, loss: 0.025798607617616653
2023-01-21 12:49:00.809243: step: 1004/530, loss: 0.01819467544555664
2023-01-21 12:49:01.986289: step: 1008/530, loss: 0.004063606262207031
2023-01-21 12:49:03.164032: step: 1012/530, loss: 0.0146621223539114
2023-01-21 12:49:04.356263: step: 1016/530, loss: 0.005760956089943647
2023-01-21 12:49:05.542759: step: 1020/530, loss: 0.0004344940243754536
2023-01-21 12:49:06.659777: step: 1024/530, loss: 0.0017871379386633635
2023-01-21 12:49:07.859662: step: 1028/530, loss: 0.00201835623010993
2023-01-21 12:49:09.036155: step: 1032/530, loss: 0.00036077501135878265
2023-01-21 12:49:10.206205: step: 1036/530, loss: 0.0021250725258141756
2023-01-21 12:49:11.367517: step: 1040/530, loss: 7.152557827794226e-06
2023-01-21 12:49:12.557257: step: 1044/530, loss: -1.068115216185106e-05
2023-01-21 12:49:13.747975: step: 1048/530, loss: 0.004632544703781605
2023-01-21 12:49:14.941555: step: 1052/530, loss: 0.032651904970407486
2023-01-21 12:49:16.162784: step: 1056/530, loss: 9.231566946255043e-05
2023-01-21 12:49:17.347847: step: 1060/530, loss: 0.00125293736346066
2023-01-21 12:49:18.596411: step: 1064/530, loss: 0.007747459691017866
2023-01-21 12:49:19.751873: step: 1068/530, loss: 0.0006618500337935984
2023-01-21 12:49:20.897163: step: 1072/530, loss: 0.011079597286880016
2023-01-21 12:49:22.063965: step: 1076/530, loss: 5.4073334467830136e-05
2023-01-21 12:49:23.233017: step: 1080/530, loss: 2.250671423098538e-05
2023-01-21 12:49:24.408576: step: 1084/530, loss: 0.0020433426834642887
2023-01-21 12:49:25.596068: step: 1088/530, loss: 4.100799560546875e-05
2023-01-21 12:49:26.832269: step: 1092/530, loss: 1.640319896978326e-05
2023-01-21 12:49:27.994469: step: 1096/530, loss: 0.00039358140202239156
2023-01-21 12:49:29.163601: step: 1100/530, loss: 0.00023345947556663305
2023-01-21 12:49:30.315861: step: 1104/530, loss: 0.022386642172932625
2023-01-21 12:49:31.522986: step: 1108/530, loss: 0.005397797096520662
2023-01-21 12:49:32.718438: step: 1112/530, loss: 0.05992889776825905
2023-01-21 12:49:33.894530: step: 1116/530, loss: 0.00010395050048828125
2023-01-21 12:49:35.056457: step: 1120/530, loss: 0.0007589340093545616
2023-01-21 12:49:36.271410: step: 1124/530, loss: 1.9931794668082148e-05
2023-01-21 12:49:37.433717: step: 1128/530, loss: 2.8610227218450746e-06
2023-01-21 12:49:38.626955: step: 1132/530, loss: 0.021286966279149055
2023-01-21 12:49:39.875244: step: 1136/530, loss: 0.00011281967454124242
2023-01-21 12:49:41.024084: step: 1140/530, loss: -1.9073486328125e-06
2023-01-21 12:49:42.290496: step: 1144/530, loss: 2.4318694613612024e-06
2023-01-21 12:49:43.486157: step: 1148/530, loss: 0.0006731033208779991
2023-01-21 12:49:44.650541: step: 1152/530, loss: 0.025429202243685722
2023-01-21 12:49:45.782063: step: 1156/530, loss: 0.0006122589111328125
2023-01-21 12:49:46.961911: step: 1160/530, loss: 5.4645537602482364e-05
2023-01-21 12:49:48.154327: step: 1164/530, loss: 0.046225644648075104
2023-01-21 12:49:49.328908: step: 1168/530, loss: 0.004306030459702015
2023-01-21 12:49:50.463757: step: 1172/530, loss: 0.0003841400030069053
2023-01-21 12:49:51.647371: step: 1176/530, loss: 0.12259978801012039
2023-01-21 12:49:52.821412: step: 1180/530, loss: 2.727508581301663e-05
2023-01-21 12:49:54.021077: step: 1184/530, loss: 0.0022701264824718237
2023-01-21 12:49:55.252992: step: 1188/530, loss: 4.405975414556451e-05
2023-01-21 12:49:56.440566: step: 1192/530, loss: 0.010464095510542393
2023-01-21 12:49:57.627297: step: 1196/530, loss: 0.02464168146252632
2023-01-21 12:49:58.784208: step: 1200/530, loss: 0.003505229949951172
2023-01-21 12:49:59.942720: step: 1204/530, loss: 0.012092113494873047
2023-01-21 12:50:01.157352: step: 1208/530, loss: 0.0017627477645874023
2023-01-21 12:50:02.355838: step: 1212/530, loss: 0.08307018876075745
2023-01-21 12:50:03.555962: step: 1216/530, loss: 0.029086114838719368
2023-01-21 12:50:04.731665: step: 1220/530, loss: 0.00015144348435569555
2023-01-21 12:50:05.877410: step: 1224/530, loss: 0.019352149218320847
2023-01-21 12:50:07.084685: step: 1228/530, loss: 0.0001125335693359375
2023-01-21 12:50:08.194179: step: 1232/530, loss: 0.007159900851547718
2023-01-21 12:50:09.366469: step: 1236/530, loss: 0.017534637823700905
2023-01-21 12:50:10.552411: step: 1240/530, loss: 0.0006711006280966103
2023-01-21 12:50:11.662445: step: 1244/530, loss: 0.0016992568271234632
2023-01-21 12:50:12.867072: step: 1248/530, loss: 0.00010290146747138351
2023-01-21 12:50:14.042130: step: 1252/530, loss: 0.013883877545595169
2023-01-21 12:50:15.259104: step: 1256/530, loss: 0.002599811414256692
2023-01-21 12:50:16.411311: step: 1260/530, loss: 2.040863000729587e-05
2023-01-21 12:50:17.597441: step: 1264/530, loss: 2.079009937006049e-05
2023-01-21 12:50:18.731129: step: 1268/530, loss: 0.00031408070935867727
2023-01-21 12:50:19.866837: step: 1272/530, loss: 0.05851106718182564
2023-01-21 12:50:21.084053: step: 1276/530, loss: 0.01069183461368084
2023-01-21 12:50:22.238184: step: 1280/530, loss: 0.001836681505665183
2023-01-21 12:50:23.415322: step: 1284/530, loss: 0.0003002166922669858
2023-01-21 12:50:24.567413: step: 1288/530, loss: 0.02693486213684082
2023-01-21 12:50:25.751947: step: 1292/530, loss: 0.00148267752956599
2023-01-21 12:50:26.920641: step: 1296/530, loss: 3.3855437777674524e-06
2023-01-21 12:50:28.101215: step: 1300/530, loss: 0.00547714252024889
2023-01-21 12:50:29.311340: step: 1304/530, loss: 0.022827625274658203
2023-01-21 12:50:30.478554: step: 1308/530, loss: 0.0025603293906897306
2023-01-21 12:50:31.635300: step: 1312/530, loss: 1.9669532775878906e-05
2023-01-21 12:50:32.784815: step: 1316/530, loss: 0.05727529525756836
2023-01-21 12:50:33.949971: step: 1320/530, loss: 0.0001794815034372732
2023-01-21 12:50:35.135766: step: 1324/530, loss: 0.0029422759544104338
2023-01-21 12:50:36.325123: step: 1328/530, loss: 0.007952690124511719
2023-01-21 12:50:37.500727: step: 1332/530, loss: 0.006788825616240501
2023-01-21 12:50:38.677303: step: 1336/530, loss: 0.0005025863647460938
2023-01-21 12:50:39.880800: step: 1340/530, loss: 0.001758575439453125
2023-01-21 12:50:41.108049: step: 1344/530, loss: 0.003667640732601285
2023-01-21 12:50:42.325294: step: 1348/530, loss: 0.0007131577003747225
2023-01-21 12:50:43.516597: step: 1352/530, loss: 0.02998518943786621
2023-01-21 12:50:44.700893: step: 1356/530, loss: 0.008506203070282936
2023-01-21 12:50:45.864324: step: 1360/530, loss: 3.4809113458322827e-06
2023-01-21 12:50:47.072532: step: 1364/530, loss: 0.0016820906894281507
2023-01-21 12:50:48.257069: step: 1368/530, loss: 0.0035636902321130037
2023-01-21 12:50:49.412545: step: 1372/530, loss: 6.217956251930445e-05
2023-01-21 12:50:50.632140: step: 1376/530, loss: 0.03614712134003639
2023-01-21 12:50:51.827660: step: 1380/530, loss: 0.00024657248286530375
2023-01-21 12:50:52.994073: step: 1384/530, loss: 0.00037784577580168843
2023-01-21 12:50:54.186454: step: 1388/530, loss: 0.04331236332654953
2023-01-21 12:50:55.350256: step: 1392/530, loss: 5.817413693876006e-06
2023-01-21 12:50:56.559634: step: 1396/530, loss: 0.0016355514526367188
2023-01-21 12:50:57.740597: step: 1400/530, loss: 8.120536949718371e-05
2023-01-21 12:50:58.922038: step: 1404/530, loss: 0.0002738833427429199
2023-01-21 12:51:00.117921: step: 1408/530, loss: 2.822876012942288e-05
2023-01-21 12:51:01.264567: step: 1412/530, loss: 0.0004620552354026586
2023-01-21 12:51:02.419388: step: 1416/530, loss: 4.322528911870904e-05
2023-01-21 12:51:03.592882: step: 1420/530, loss: 1.3256072634248994e-05
2023-01-21 12:51:04.753180: step: 1424/530, loss: 5.53131121705519e-06
2023-01-21 12:51:05.951703: step: 1428/530, loss: 0.0005479812389239669
2023-01-21 12:51:07.158428: step: 1432/530, loss: 0.0001502990780863911
2023-01-21 12:51:08.301238: step: 1436/530, loss: 0.04714584723114967
2023-01-21 12:51:09.521208: step: 1440/530, loss: 0.021670151501893997
2023-01-21 12:51:10.717586: step: 1444/530, loss: 0.000869536364916712
2023-01-21 12:51:11.885159: step: 1448/530, loss: 0.46847161650657654
2023-01-21 12:51:13.054038: step: 1452/530, loss: 0.035117149353027344
2023-01-21 12:51:14.213773: step: 1456/530, loss: 0.02888631820678711
2023-01-21 12:51:15.355523: step: 1460/530, loss: 0.0011163711315020919
2023-01-21 12:51:16.533354: step: 1464/530, loss: 3.547668529790826e-05
2023-01-21 12:51:17.704833: step: 1468/530, loss: 0.01249632891267538
2023-01-21 12:51:18.924368: step: 1472/530, loss: 8.668899681651965e-05
2023-01-21 12:51:20.081446: step: 1476/530, loss: 0.0004951477167196572
2023-01-21 12:51:21.237630: step: 1480/530, loss: 0.0003058433358091861
2023-01-21 12:51:22.428947: step: 1484/530, loss: 0.0032613754738122225
2023-01-21 12:51:23.666486: step: 1488/530, loss: 5.53131121705519e-06
2023-01-21 12:51:24.858147: step: 1492/530, loss: 0.012811660766601562
2023-01-21 12:51:26.039069: step: 1496/530, loss: 0.00046129230759106576
2023-01-21 12:51:27.226532: step: 1500/530, loss: 0.008317947387695312
2023-01-21 12:51:28.393196: step: 1504/530, loss: 0.0001320362207479775
2023-01-21 12:51:29.587319: step: 1508/530, loss: 0.0006953239790163934
2023-01-21 12:51:30.764854: step: 1512/530, loss: 6.10351571594947e-06
2023-01-21 12:51:31.923117: step: 1516/530, loss: 0.005542946048080921
2023-01-21 12:51:33.091058: step: 1520/530, loss: 0.009789466857910156
2023-01-21 12:51:34.266534: step: 1524/530, loss: 4.978180368198082e-05
2023-01-21 12:51:35.474639: step: 1528/530, loss: 0.0003383636649232358
2023-01-21 12:51:36.638083: step: 1532/530, loss: 0.00104522705078125
2023-01-21 12:51:37.838653: step: 1536/530, loss: 0.0003890037478413433
2023-01-21 12:51:39.047531: step: 1540/530, loss: 0.10388441383838654
2023-01-21 12:51:40.230271: step: 1544/530, loss: 0.0036623000632971525
2023-01-21 12:51:41.430419: step: 1548/530, loss: 0.026074599474668503
2023-01-21 12:51:42.658192: step: 1552/530, loss: 0.0011375427711755037
2023-01-21 12:51:43.817518: step: 1556/530, loss: 0.0007243156433105469
2023-01-21 12:51:44.957602: step: 1560/530, loss: 0.03665218502283096
2023-01-21 12:51:46.145270: step: 1564/530, loss: 0.0010131836170330644
2023-01-21 12:51:47.308489: step: 1568/530, loss: 0.06963463127613068
2023-01-21 12:51:48.468714: step: 1572/530, loss: 0.006336784455925226
2023-01-21 12:51:49.663307: step: 1576/530, loss: 8.535384949936997e-06
2023-01-21 12:51:50.868614: step: 1580/530, loss: 0.0002690315304789692
2023-01-21 12:51:52.081312: step: 1584/530, loss: 0.059790898114442825
2023-01-21 12:51:53.241400: step: 1588/530, loss: 0.009599113836884499
2023-01-21 12:51:54.399958: step: 1592/530, loss: 0.004770755767822266
2023-01-21 12:51:55.588837: step: 1596/530, loss: 0.006071853917092085
2023-01-21 12:51:56.736858: step: 1600/530, loss: 0.0009387970203533769
2023-01-21 12:51:57.937226: step: 1604/530, loss: 0.011533546261489391
2023-01-21 12:51:59.116977: step: 1608/530, loss: 0.0001070022553903982
2023-01-21 12:52:00.300050: step: 1612/530, loss: 0.004736470989882946
2023-01-21 12:52:01.491564: step: 1616/530, loss: 0.017360592260956764
2023-01-21 12:52:02.676906: step: 1620/530, loss: 0.03340759500861168
2023-01-21 12:52:03.813932: step: 1624/530, loss: 1.2969970157428179e-05
2023-01-21 12:52:04.980576: step: 1628/530, loss: 0.02504558488726616
2023-01-21 12:52:06.124970: step: 1632/530, loss: 0.01328191813081503
2023-01-21 12:52:07.291366: step: 1636/530, loss: 0.00024662018404342234
2023-01-21 12:52:08.470198: step: 1640/530, loss: 0.0028443338815122843
2023-01-21 12:52:09.635277: step: 1644/530, loss: 0.00019845963106490672
2023-01-21 12:52:10.785751: step: 1648/530, loss: 0.005619239993393421
2023-01-21 12:52:11.972840: step: 1652/530, loss: 0.010685157962143421
2023-01-21 12:52:13.139355: step: 1656/530, loss: 0.007655525114387274
2023-01-21 12:52:14.307371: step: 1660/530, loss: 0.01723175123333931
2023-01-21 12:52:15.502786: step: 1664/530, loss: 0.0029481889214366674
2023-01-21 12:52:16.693308: step: 1668/530, loss: 0.0009908676147460938
2023-01-21 12:52:17.855326: step: 1672/530, loss: 0.004089737311005592
2023-01-21 12:52:19.024133: step: 1676/530, loss: 0.01135864295065403
2023-01-21 12:52:20.200767: step: 1680/530, loss: 0.0005916595691815019
2023-01-21 12:52:21.397728: step: 1684/530, loss: 0.006215095520019531
2023-01-21 12:52:22.594214: step: 1688/530, loss: 0.03696784749627113
2023-01-21 12:52:23.769612: step: 1692/530, loss: 0.04552946239709854
2023-01-21 12:52:24.949900: step: 1696/530, loss: 0.011257028207182884
2023-01-21 12:52:26.145802: step: 1700/530, loss: 0.003250312991440296
2023-01-21 12:52:27.357980: step: 1704/530, loss: 0.02100525051355362
2023-01-21 12:52:28.493172: step: 1708/530, loss: 0.01047439593821764
2023-01-21 12:52:29.638847: step: 1712/530, loss: 0.0016035079024732113
2023-01-21 12:52:30.807895: step: 1716/530, loss: 0.0007534027099609375
2023-01-21 12:52:32.070162: step: 1720/530, loss: 0.005093193147331476
2023-01-21 12:52:33.266669: step: 1724/530, loss: 0.0381532683968544
2023-01-21 12:52:34.421859: step: 1728/530, loss: 0.007084846496582031
2023-01-21 12:52:35.587245: step: 1732/530, loss: 3.0136110581224784e-05
2023-01-21 12:52:36.834176: step: 1736/530, loss: 3.056526111322455e-05
2023-01-21 12:52:38.041774: step: 1740/530, loss: 0.012841987423598766
2023-01-21 12:52:39.216690: step: 1744/530, loss: 2.0122528439969756e-05
2023-01-21 12:52:40.412159: step: 1748/530, loss: 4.38690176451928e-06
2023-01-21 12:52:41.622947: step: 1752/530, loss: 0.010372733697295189
2023-01-21 12:52:42.806114: step: 1756/530, loss: 0.0001239776611328125
2023-01-21 12:52:44.025656: step: 1760/530, loss: 0.00013790131197310984
2023-01-21 12:52:45.201696: step: 1764/530, loss: 0.017101097851991653
2023-01-21 12:52:46.382927: step: 1768/530, loss: 0.01523437537252903
2023-01-21 12:52:47.573566: step: 1772/530, loss: 0.0005068779573775828
2023-01-21 12:52:48.810139: step: 1776/530, loss: 0.041847798973321915
2023-01-21 12:52:49.953428: step: 1780/530, loss: 0.003219032194465399
2023-01-21 12:52:51.144033: step: 1784/530, loss: 0.009685707278549671
2023-01-21 12:52:52.317274: step: 1788/530, loss: 0.06047554314136505
2023-01-21 12:52:53.489908: step: 1792/530, loss: 0.002909088274464011
2023-01-21 12:52:54.664499: step: 1796/530, loss: 0.00017547607421875
2023-01-21 12:52:55.889636: step: 1800/530, loss: 0.0016261100536212325
2023-01-21 12:52:57.092728: step: 1804/530, loss: 0.0014720142353326082
2023-01-21 12:52:58.292886: step: 1808/530, loss: 0.004967927932739258
2023-01-21 12:52:59.431279: step: 1812/530, loss: 0.022266961634159088
2023-01-21 12:53:00.604882: step: 1816/530, loss: 0.0004787445068359375
2023-01-21 12:53:01.800424: step: 1820/530, loss: 0.021136663854122162
2023-01-21 12:53:02.989022: step: 1824/530, loss: 4.5490265620173886e-05
2023-01-21 12:53:04.157319: step: 1828/530, loss: 0.015691757202148438
2023-01-21 12:53:05.308139: step: 1832/530, loss: 0.0002340316859772429
2023-01-21 12:53:06.459784: step: 1836/530, loss: 3.204345557605848e-05
2023-01-21 12:53:07.602739: step: 1840/530, loss: 0.0004479408380575478
2023-01-21 12:53:08.812700: step: 1844/530, loss: 1.6689300537109375e-05
2023-01-21 12:53:09.990621: step: 1848/530, loss: 0.00197104224935174
2023-01-21 12:53:11.161780: step: 1852/530, loss: 1.754760705807712e-05
2023-01-21 12:53:12.352205: step: 1856/530, loss: 0.0062202452681958675
2023-01-21 12:53:13.530803: step: 1860/530, loss: 0.1797536015510559
2023-01-21 12:53:14.693541: step: 1864/530, loss: 0.01392068900167942
2023-01-21 12:53:15.905795: step: 1868/530, loss: 0.0005453109624795616
2023-01-21 12:53:17.104907: step: 1872/530, loss: 5.149840944795869e-06
2023-01-21 12:53:18.294724: step: 1876/530, loss: 0.0009885788895189762
2023-01-21 12:53:19.473623: step: 1880/530, loss: 0.021121788769960403
2023-01-21 12:53:20.669850: step: 1884/530, loss: 0.00025844573974609375
2023-01-21 12:53:21.807612: step: 1888/530, loss: 0.012636709958314896
2023-01-21 12:53:23.022633: step: 1892/530, loss: 0.0004238128603901714
2023-01-21 12:53:24.171324: step: 1896/530, loss: 0.0006933212280273438
2023-01-21 12:53:25.355650: step: 1900/530, loss: 0.36515775322914124
2023-01-21 12:53:26.540045: step: 1904/530, loss: 0.004790115635842085
2023-01-21 12:53:27.686270: step: 1908/530, loss: 0.007931709289550781
2023-01-21 12:53:28.848980: step: 1912/530, loss: 2.6416777473059483e-05
2023-01-21 12:53:30.031007: step: 1916/530, loss: -5.14984139954322e-06
2023-01-21 12:53:31.250417: step: 1920/530, loss: 0.0028755187522619963
2023-01-21 12:53:32.399922: step: 1924/530, loss: 0.00011577606346691027
2023-01-21 12:53:33.569978: step: 1928/530, loss: 0.0026265145279467106
2023-01-21 12:53:34.761784: step: 1932/530, loss: 0.026862526312470436
2023-01-21 12:53:35.933362: step: 1936/530, loss: 0.00019812583923339844
2023-01-21 12:53:37.150627: step: 1940/530, loss: 0.002017402555793524
2023-01-21 12:53:38.331367: step: 1944/530, loss: 0.019564246758818626
2023-01-21 12:53:39.510742: step: 1948/530, loss: 2.717971983656753e-05
2023-01-21 12:53:40.673721: step: 1952/530, loss: 3.623962356869015e-06
2023-01-21 12:53:41.830149: step: 1956/530, loss: 6.895065598655492e-05
2023-01-21 12:53:42.991948: step: 1960/530, loss: 0.0003321647527627647
2023-01-21 12:53:44.136796: step: 1964/530, loss: 0.0006653785821981728
2023-01-21 12:53:45.334935: step: 1968/530, loss: 0.009163380600512028
2023-01-21 12:53:46.509728: step: 1972/530, loss: 0.012134457007050514
2023-01-21 12:53:47.650205: step: 1976/530, loss: 0.0007505416870117188
2023-01-21 12:53:48.828046: step: 1980/530, loss: 0.0051285745576024055
2023-01-21 12:53:49.979436: step: 1984/530, loss: 0.05881378799676895
2023-01-21 12:53:51.146113: step: 1988/530, loss: 0.005851173307746649
2023-01-21 12:53:52.311471: step: 1992/530, loss: 5.092620995128527e-05
2023-01-21 12:53:53.455215: step: 1996/530, loss: 0.02148609235882759
2023-01-21 12:53:54.600422: step: 2000/530, loss: 1.544952465337701e-05
2023-01-21 12:53:55.744719: step: 2004/530, loss: 0.002046298934146762
2023-01-21 12:53:56.888744: step: 2008/530, loss: 0.00047178269596770406
2023-01-21 12:53:58.033245: step: 2012/530, loss: 0.003085231874138117
2023-01-21 12:53:59.219966: step: 2016/530, loss: 0.0004485130193643272
2023-01-21 12:54:00.401254: step: 2020/530, loss: 0.00022335053654387593
2023-01-21 12:54:01.588330: step: 2024/530, loss: 0.0019073486328125
2023-01-21 12:54:02.772986: step: 2028/530, loss: 0.018143033608794212
2023-01-21 12:54:03.985190: step: 2032/530, loss: 0.04486484453082085
2023-01-21 12:54:05.215374: step: 2036/530, loss: 0.10240411758422852
2023-01-21 12:54:06.368814: step: 2040/530, loss: 0.0013899803161621094
2023-01-21 12:54:07.571151: step: 2044/530, loss: 0.008051108568906784
2023-01-21 12:54:08.789419: step: 2048/530, loss: 9.70840483205393e-05
2023-01-21 12:54:09.962291: step: 2052/530, loss: 0.01144037302583456
2023-01-21 12:54:11.134561: step: 2056/530, loss: 0.0005726814270019531
2023-01-21 12:54:12.300835: step: 2060/530, loss: 0.00018634795560501516
2023-01-21 12:54:13.472346: step: 2064/530, loss: 0.17143535614013672
2023-01-21 12:54:14.695875: step: 2068/530, loss: 0.0010038375621661544
2023-01-21 12:54:15.899553: step: 2072/530, loss: 0.029504967853426933
2023-01-21 12:54:17.096670: step: 2076/530, loss: 0.002227306365966797
2023-01-21 12:54:18.250806: step: 2080/530, loss: 0.03633098676800728
2023-01-21 12:54:19.460615: step: 2084/530, loss: 0.008029365912079811
2023-01-21 12:54:20.626852: step: 2088/530, loss: 0.0002578735293354839
2023-01-21 12:54:21.846597: step: 2092/530, loss: 0.0011538505787029862
2023-01-21 12:54:23.032465: step: 2096/530, loss: 0.0033519745338708162
2023-01-21 12:54:24.232445: step: 2100/530, loss: 2.536773718020413e-05
2023-01-21 12:54:25.424230: step: 2104/530, loss: 0.009519577026367188
2023-01-21 12:54:26.604792: step: 2108/530, loss: 0.0391053669154644
2023-01-21 12:54:27.751744: step: 2112/530, loss: 0.0018769741291180253
2023-01-21 12:54:28.941337: step: 2116/530, loss: 0.0025014877319335938
2023-01-21 12:54:30.077776: step: 2120/530, loss: 0.0002906799491029233
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.5740740740740741, 'r': 0.49206349206349204, 'f1': 0.5299145299145299}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.4583333333333333, 'r': 0.6111111111111112, 'f1': 0.5238095238095238}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 12:55:20.933810: step: 4/530, loss: 0.0006740569951944053
2023-01-21 12:55:22.163274: step: 8/530, loss: 7.295608520507812e-05
2023-01-21 12:55:23.332569: step: 12/530, loss: 2.002715973503655e-06
2023-01-21 12:55:24.529675: step: 16/530, loss: 0.46518364548683167
2023-01-21 12:55:25.697394: step: 20/530, loss: 0.012784719467163086
2023-01-21 12:55:26.862258: step: 24/530, loss: 2.288818359375e-05
2023-01-21 12:55:28.076569: step: 28/530, loss: 0.0009852409129962325
2023-01-21 12:55:29.254505: step: 32/530, loss: 0.005530357360839844
2023-01-21 12:55:30.488646: step: 36/530, loss: 0.0014236450660973787
2023-01-21 12:55:31.677447: step: 40/530, loss: 0.0001847267267294228
2023-01-21 12:55:32.840521: step: 44/530, loss: 0.0018189430702477694
2023-01-21 12:55:34.029509: step: 48/530, loss: 0.0001865387021098286
2023-01-21 12:55:35.194361: step: 52/530, loss: 0.008963692933321
2023-01-21 12:55:36.362970: step: 56/530, loss: 0.019423676654696465
2023-01-21 12:55:37.557428: step: 60/530, loss: 0.009451580233871937
2023-01-21 12:55:38.732077: step: 64/530, loss: 1.964569128176663e-05
2023-01-21 12:55:39.904094: step: 68/530, loss: 0.043291185051202774
2023-01-21 12:55:41.083809: step: 72/530, loss: 0.003860521363094449
2023-01-21 12:55:42.230841: step: 76/530, loss: 2.3651124138268642e-05
2023-01-21 12:55:43.361367: step: 80/530, loss: 4.634857032215223e-05
2023-01-21 12:55:44.574687: step: 84/530, loss: 0.0029699327424168587
2023-01-21 12:55:45.750848: step: 88/530, loss: 3.185272362316027e-05
2023-01-21 12:55:46.956244: step: 92/530, loss: 3.051757857974735e-06
2023-01-21 12:55:48.098134: step: 96/530, loss: 0.0005241394392214715
2023-01-21 12:55:49.294069: step: 100/530, loss: 0.015805864706635475
2023-01-21 12:55:50.459419: step: 104/530, loss: 0.0055706980638206005
2023-01-21 12:55:51.646093: step: 108/530, loss: 6.160735938465223e-05
2023-01-21 12:55:52.784747: step: 112/530, loss: 0.0009018898708745837
2023-01-21 12:55:53.957081: step: 116/530, loss: 0.05310382694005966
2023-01-21 12:55:55.143352: step: 120/530, loss: 0.013140535913407803
2023-01-21 12:55:56.325554: step: 124/530, loss: 0.0003645896795205772
2023-01-21 12:55:57.513122: step: 128/530, loss: 0.0032705306075513363
2023-01-21 12:55:58.690715: step: 132/530, loss: 0.00047168732271529734
2023-01-21 12:55:59.839142: step: 136/530, loss: 0.008203315548598766
2023-01-21 12:56:01.004027: step: 140/530, loss: 0.00031948089599609375
2023-01-21 12:56:02.194832: step: 144/530, loss: 0.0029963492415845394
2023-01-21 12:56:03.362494: step: 148/530, loss: 0.0009487151983194053
2023-01-21 12:56:04.534289: step: 152/530, loss: 5.817413239128655e-06
2023-01-21 12:56:05.761144: step: 156/530, loss: 7.600784010719508e-05
2023-01-21 12:56:06.931770: step: 160/530, loss: 0.0006208419799804688
2023-01-21 12:56:08.136352: step: 164/530, loss: 0.012035656720399857
2023-01-21 12:56:09.316917: step: 168/530, loss: 0.007426643744111061
2023-01-21 12:56:10.516987: step: 172/530, loss: 1.201629675051663e-05
2023-01-21 12:56:11.694169: step: 176/530, loss: 0.011675453744828701
2023-01-21 12:56:12.867587: step: 180/530, loss: 0.010170172899961472
2023-01-21 12:56:14.035215: step: 184/530, loss: 0.0017167091136798263
2023-01-21 12:56:15.240976: step: 188/530, loss: 0.004544639959931374
2023-01-21 12:56:16.411699: step: 192/530, loss: 0.06287956237792969
2023-01-21 12:56:17.568015: step: 196/530, loss: 0.04869117960333824
2023-01-21 12:56:18.736957: step: 200/530, loss: 0.0006194591405801475
2023-01-21 12:56:19.948820: step: 204/530, loss: 0.0009937286376953125
2023-01-21 12:56:21.110691: step: 208/530, loss: 0.006678664591163397
2023-01-21 12:56:22.294002: step: 212/530, loss: 0.0019138335483148694
2023-01-21 12:56:23.476315: step: 216/530, loss: 0.04346428066492081
2023-01-21 12:56:24.660662: step: 220/530, loss: 0.006625556852668524
2023-01-21 12:56:25.862374: step: 224/530, loss: 0.027075672522187233
2023-01-21 12:56:27.053863: step: 228/530, loss: 1.583099401614163e-05
2023-01-21 12:56:28.289635: step: 232/530, loss: 0.02287750132381916
2023-01-21 12:56:29.504519: step: 236/530, loss: 0.013226223178207874
2023-01-21 12:56:30.653710: step: 240/530, loss: 0.0020423890091478825
2023-01-21 12:56:31.820277: step: 244/530, loss: 0.006968498695641756
2023-01-21 12:56:32.996613: step: 248/530, loss: 0.00022125244140625
2023-01-21 12:56:34.165849: step: 252/530, loss: 1.7166139514301904e-06
2023-01-21 12:56:35.361994: step: 256/530, loss: 0.0290051456540823
2023-01-21 12:56:36.500477: step: 260/530, loss: 0.009728336706757545
2023-01-21 12:56:37.653595: step: 264/530, loss: 0.0008256912115029991
2023-01-21 12:56:38.795544: step: 268/530, loss: 0.004562854766845703
2023-01-21 12:56:40.018522: step: 272/530, loss: 0.002161407610401511
2023-01-21 12:56:41.201117: step: 276/530, loss: 0.00025234222994185984
2023-01-21 12:56:42.419802: step: 280/530, loss: 0.0039386749267578125
2023-01-21 12:56:43.601408: step: 284/530, loss: 0.0054306029342114925
2023-01-21 12:56:44.781441: step: 288/530, loss: 0.00012674331082962453
2023-01-21 12:56:46.007700: step: 292/530, loss: 4.00543212890625e-05
2023-01-21 12:56:47.170626: step: 296/530, loss: 0.0003856658877339214
2023-01-21 12:56:48.348032: step: 300/530, loss: 0.0019322395091876388
2023-01-21 12:56:49.513746: step: 304/530, loss: 0.0006701469537802041
2023-01-21 12:56:50.707870: step: 308/530, loss: 0.008366823196411133
2023-01-21 12:56:51.877164: step: 312/530, loss: 0.0012504577171057463
2023-01-21 12:56:53.035680: step: 316/530, loss: 0.018553685396909714
2023-01-21 12:56:54.214318: step: 320/530, loss: 0.0001993656187551096
2023-01-21 12:56:55.352717: step: 324/530, loss: 0.0007571220630779862
2023-01-21 12:56:56.562784: step: 328/530, loss: -3.4809111184586072e-06
2023-01-21 12:56:57.724317: step: 332/530, loss: 0.0003067016659770161
2023-01-21 12:56:58.869416: step: 336/530, loss: 0.013459968380630016
2023-01-21 12:57:00.055323: step: 340/530, loss: 0.00576672563329339
2023-01-21 12:57:01.250292: step: 344/530, loss: 0.0013429642422124743
2023-01-21 12:57:02.450562: step: 348/530, loss: 0.0196272861212492
2023-01-21 12:57:03.630755: step: 352/530, loss: 0.00039253238355740905
2023-01-21 12:57:04.791419: step: 356/530, loss: 0.006956195924431086
2023-01-21 12:57:06.017655: step: 360/530, loss: 0.011643314734101295
2023-01-21 12:57:07.210200: step: 364/530, loss: 0.00018749237642623484
2023-01-21 12:57:08.346844: step: 368/530, loss: 0.030957603827118874
2023-01-21 12:57:09.533307: step: 372/530, loss: 0.008719539269804955
2023-01-21 12:57:10.763795: step: 376/530, loss: 0.2043663114309311
2023-01-21 12:57:11.971621: step: 380/530, loss: 0.010303784161806107
2023-01-21 12:57:13.172574: step: 384/530, loss: 0.0002574920654296875
2023-01-21 12:57:14.377824: step: 388/530, loss: 0.00010809898958541453
2023-01-21 12:57:15.517226: step: 392/530, loss: 0.03522491827607155
2023-01-21 12:57:16.707133: step: 396/530, loss: 0.0021526338532567024
2023-01-21 12:57:17.894169: step: 400/530, loss: 0.00030069350032135844
2023-01-21 12:57:19.055036: step: 404/530, loss: 0.0008027076837606728
2023-01-21 12:57:20.211358: step: 408/530, loss: 6.4849853515625e-05
2023-01-21 12:57:21.395889: step: 412/530, loss: 0.00031785963801667094
2023-01-21 12:57:22.584643: step: 416/530, loss: 1.850128137448337e-05
2023-01-21 12:57:23.758066: step: 420/530, loss: 0.011610651388764381
2023-01-21 12:57:24.913960: step: 424/530, loss: 0.0002832413010764867
2023-01-21 12:57:26.083646: step: 428/530, loss: 0.009240913204848766
2023-01-21 12:57:27.276031: step: 432/530, loss: 0.021496916189789772
2023-01-21 12:57:28.414339: step: 436/530, loss: 1.1539459592313506e-05
2023-01-21 12:57:29.596847: step: 440/530, loss: 0.023509692400693893
2023-01-21 12:57:30.798627: step: 444/530, loss: 8.583068620282575e-07
2023-01-21 12:57:32.027063: step: 448/530, loss: 0.0003246307314839214
2023-01-21 12:57:33.210677: step: 452/530, loss: 0.00047140123206190765
2023-01-21 12:57:34.398011: step: 456/530, loss: 0.02174091339111328
2023-01-21 12:57:35.586880: step: 460/530, loss: 0.05800876393914223
2023-01-21 12:57:36.755215: step: 464/530, loss: 1.8775463104248047e-05
2023-01-21 12:57:38.030465: step: 468/530, loss: 0.0005529404152184725
2023-01-21 12:57:39.167216: step: 472/530, loss: -5.722046125811175e-07
2023-01-21 12:57:40.342623: step: 476/530, loss: 0.0008450031746178865
2023-01-21 12:57:41.516622: step: 480/530, loss: 0.040723226964473724
2023-01-21 12:57:42.702413: step: 484/530, loss: 0.025408267974853516
2023-01-21 12:57:43.878451: step: 488/530, loss: 0.0025696754455566406
2023-01-21 12:57:45.078531: step: 492/530, loss: 0.0008945465087890625
2023-01-21 12:57:46.242022: step: 496/530, loss: 0.00018768310837913305
2023-01-21 12:57:47.373554: step: 500/530, loss: 0.00019459723262116313
2023-01-21 12:57:48.574689: step: 504/530, loss: 0.0008348465198650956
2023-01-21 12:57:49.750381: step: 508/530, loss: 0.002517747925594449
2023-01-21 12:57:50.889241: step: 512/530, loss: 0.026071738451719284
2023-01-21 12:57:52.040759: step: 516/530, loss: 0.00955886859446764
2023-01-21 12:57:53.222823: step: 520/530, loss: 0.0028583526145666838
2023-01-21 12:57:54.380496: step: 524/530, loss: 0.045081425458192825
2023-01-21 12:57:55.582952: step: 528/530, loss: 0.028779126703739166
2023-01-21 12:57:56.757743: step: 532/530, loss: 0.0012316703796386719
2023-01-21 12:57:57.890409: step: 536/530, loss: 0.009562588296830654
2023-01-21 12:57:59.103914: step: 540/530, loss: 4.8255922592943534e-05
2023-01-21 12:58:00.288278: step: 544/530, loss: 0.0045378683134913445
2023-01-21 12:58:01.475670: step: 548/530, loss: 0.008693314157426357
2023-01-21 12:58:02.642699: step: 552/530, loss: 0.001110076904296875
2023-01-21 12:58:03.803057: step: 556/530, loss: 0.038436368107795715
2023-01-21 12:58:04.962486: step: 560/530, loss: 0.001132714794948697
2023-01-21 12:58:06.121576: step: 564/530, loss: 0.00012683868408203125
2023-01-21 12:58:07.306753: step: 568/530, loss: 0.010332107543945312
2023-01-21 12:58:08.457955: step: 572/530, loss: 0.00013303756713867188
2023-01-21 12:58:09.631564: step: 576/530, loss: 0.08344526588916779
2023-01-21 12:58:10.825008: step: 580/530, loss: 0.000332736992277205
2023-01-21 12:58:11.965526: step: 584/530, loss: 0.005936527159065008
2023-01-21 12:58:13.142849: step: 588/530, loss: 0.005217742640525103
2023-01-21 12:58:14.332617: step: 592/530, loss: 0.03415513038635254
2023-01-21 12:58:15.484696: step: 596/530, loss: 0.0014522552955895662
2023-01-21 12:58:16.632214: step: 600/530, loss: 0.0443662628531456
2023-01-21 12:58:17.788801: step: 604/530, loss: 0.003227138426154852
2023-01-21 12:58:18.941961: step: 608/530, loss: 0.0006905555492267013
2023-01-21 12:58:20.117012: step: 612/530, loss: 0.00015659333439543843
2023-01-21 12:58:21.288785: step: 616/530, loss: 0.0003570556582417339
2023-01-21 12:58:22.459509: step: 620/530, loss: 0.027857590466737747
2023-01-21 12:58:23.640794: step: 624/530, loss: 0.014815999194979668
2023-01-21 12:58:24.814333: step: 628/530, loss: 0.00278224959038198
2023-01-21 12:58:26.003857: step: 632/530, loss: 3.623962811616366e-06
2023-01-21 12:58:27.156543: step: 636/530, loss: 0.0005414963234215975
2023-01-21 12:58:28.332694: step: 640/530, loss: 0.00013637544179800898
2023-01-21 12:58:29.495798: step: 644/530, loss: 7.45773286325857e-05
2023-01-21 12:58:30.671815: step: 648/530, loss: 0.00028553008451126516
2023-01-21 12:58:31.886204: step: 652/530, loss: 0.005470085423439741
2023-01-21 12:58:33.096371: step: 656/530, loss: 0.0020800591446459293
2023-01-21 12:58:34.256145: step: 660/530, loss: 0.018434524536132812
2023-01-21 12:58:35.460794: step: 664/530, loss: 0.0002639770682435483
2023-01-21 12:58:36.634553: step: 668/530, loss: 5.197524842515122e-06
2023-01-21 12:58:37.860719: step: 672/530, loss: 0.00237197894603014
2023-01-21 12:58:39.003226: step: 676/530, loss: 0.00010032654245151207
2023-01-21 12:58:40.109627: step: 680/530, loss: 0.0005856514326296747
2023-01-21 12:58:41.308114: step: 684/530, loss: 0.003860855009406805
2023-01-21 12:58:42.518190: step: 688/530, loss: 0.007921313866972923
2023-01-21 12:58:43.650667: step: 692/530, loss: 0.02006354369223118
2023-01-21 12:58:44.851522: step: 696/530, loss: 0.08081436157226562
2023-01-21 12:58:46.088496: step: 700/530, loss: 0.0035410881973803043
2023-01-21 12:58:47.236632: step: 704/530, loss: 0.009917736053466797
2023-01-21 12:58:48.488921: step: 708/530, loss: 0.00015592575073242188
2023-01-21 12:58:49.673471: step: 712/530, loss: 0.10614929348230362
2023-01-21 12:58:50.873214: step: 716/530, loss: 1.6641617548884824e-05
2023-01-21 12:58:52.071227: step: 720/530, loss: 0.05105409398674965
2023-01-21 12:58:53.216621: step: 724/530, loss: 0.00033216478186659515
2023-01-21 12:58:54.423115: step: 728/530, loss: 0.009569644927978516
2023-01-21 12:58:55.598417: step: 732/530, loss: 0.00016813278489280492
2023-01-21 12:58:56.747182: step: 736/530, loss: 0.00020885467529296875
2023-01-21 12:58:57.915821: step: 740/530, loss: 0.024511337280273438
2023-01-21 12:58:59.073607: step: 744/530, loss: 0.03788242116570473
2023-01-21 12:59:00.263304: step: 748/530, loss: 0.0008025169372558594
2023-01-21 12:59:01.418372: step: 752/530, loss: 0.004583549685776234
2023-01-21 12:59:02.587083: step: 756/530, loss: 0.014370251446962357
2023-01-21 12:59:03.784838: step: 760/530, loss: 0.007969665341079235
2023-01-21 12:59:05.008592: step: 764/530, loss: 0.001255798269994557
2023-01-21 12:59:06.178452: step: 768/530, loss: 6.246567500056699e-05
2023-01-21 12:59:07.338742: step: 772/530, loss: 0.010210228152573109
2023-01-21 12:59:08.523283: step: 776/530, loss: 3.075599670410156e-05
2023-01-21 12:59:09.757271: step: 780/530, loss: 0.0077866557985544205
2023-01-21 12:59:10.942178: step: 784/530, loss: 8.435249037574977e-05
2023-01-21 12:59:12.157342: step: 788/530, loss: 0.00010852813284145668
2023-01-21 12:59:13.360443: step: 792/530, loss: 0.00587120046839118
2023-01-21 12:59:14.538798: step: 796/530, loss: 0.006425237748771906
2023-01-21 12:59:15.681897: step: 800/530, loss: 0.029317380860447884
2023-01-21 12:59:16.847856: step: 804/530, loss: 0.44524702429771423
2023-01-21 12:59:18.014159: step: 808/530, loss: 9.829997725319117e-05
2023-01-21 12:59:19.206642: step: 812/530, loss: 0.0011178969871252775
2023-01-21 12:59:20.443768: step: 816/530, loss: 2.9325485229492188e-05
2023-01-21 12:59:21.605282: step: 820/530, loss: 0.007728386204689741
2023-01-21 12:59:22.795528: step: 824/530, loss: 8.42094377730973e-05
2023-01-21 12:59:23.999261: step: 828/530, loss: 0.007036400027573109
2023-01-21 12:59:25.219743: step: 832/530, loss: 0.0013431073166429996
2023-01-21 12:59:26.413554: step: 836/530, loss: 0.0010127543937414885
2023-01-21 12:59:27.557074: step: 840/530, loss: 0.0026439668145030737
2023-01-21 12:59:28.757395: step: 844/530, loss: 0.01310262642800808
2023-01-21 12:59:29.885793: step: 848/530, loss: 4.7445296331716236e-06
2023-01-21 12:59:31.064566: step: 852/530, loss: 0.002571487333625555
2023-01-21 12:59:32.240081: step: 856/530, loss: 0.005652046296745539
2023-01-21 12:59:33.451476: step: 860/530, loss: 0.0010980606311932206
2023-01-21 12:59:34.659108: step: 864/530, loss: 0.0022942544892430305
2023-01-21 12:59:35.832906: step: 868/530, loss: 0.025679968297481537
2023-01-21 12:59:37.053387: step: 872/530, loss: 0.014879417605698109
2023-01-21 12:59:38.231997: step: 876/530, loss: 0.0015710832085460424
2023-01-21 12:59:39.399343: step: 880/530, loss: 3.24249276673072e-06
2023-01-21 12:59:40.570929: step: 884/530, loss: 0.006766891106963158
2023-01-21 12:59:41.754054: step: 888/530, loss: 0.0001432418794138357
2023-01-21 12:59:42.989987: step: 892/530, loss: 5.550384594243951e-05
2023-01-21 12:59:44.169589: step: 896/530, loss: 0.003029441926628351
2023-01-21 12:59:45.361410: step: 900/530, loss: 1.792907642084174e-05
2023-01-21 12:59:46.512175: step: 904/530, loss: 0.019577981904149055
2023-01-21 12:59:47.674040: step: 908/530, loss: 0.011146735399961472
2023-01-21 12:59:48.828779: step: 912/530, loss: 2.231597864010837e-05
2023-01-21 12:59:49.991495: step: 916/530, loss: 5.53131121705519e-06
2023-01-21 12:59:51.175408: step: 920/530, loss: 0.03512993082404137
2023-01-21 12:59:52.325457: step: 924/530, loss: 0.04661102220416069
2023-01-21 12:59:53.495394: step: 928/530, loss: 0.04242458567023277
2023-01-21 12:59:54.635220: step: 932/530, loss: -1.277923547604587e-05
2023-01-21 12:59:55.816845: step: 936/530, loss: 0.0012426376342773438
2023-01-21 12:59:56.962867: step: 940/530, loss: 0.0002252578706247732
2023-01-21 12:59:58.100054: step: 944/530, loss: 0.00174627301748842
2023-01-21 12:59:59.245409: step: 948/530, loss: 0.0011163236340507865
2023-01-21 13:00:00.450504: step: 952/530, loss: 0.0080099580809474
2023-01-21 13:00:01.628281: step: 956/530, loss: 0.00010657311213435605
2023-01-21 13:00:02.778366: step: 960/530, loss: 0.0003981590270996094
2023-01-21 13:00:03.956940: step: 964/530, loss: 4.39643845311366e-05
2023-01-21 13:00:05.135742: step: 968/530, loss: 9.355843212688342e-05
2023-01-21 13:00:06.314608: step: 972/530, loss: 0.00485153216868639
2023-01-21 13:00:07.498638: step: 976/530, loss: 0.00027189255342818797
2023-01-21 13:00:08.687686: step: 980/530, loss: 0.035962868481874466
2023-01-21 13:00:09.899261: step: 984/530, loss: 0.046094752848148346
2023-01-21 13:00:11.115736: step: 988/530, loss: 0.001702976180240512
2023-01-21 13:00:12.334584: step: 992/530, loss: 0.006884765811264515
2023-01-21 13:00:13.471336: step: 996/530, loss: 0.07497740536928177
2023-01-21 13:00:14.668774: step: 1000/530, loss: 0.007089042570441961
2023-01-21 13:00:15.839714: step: 1004/530, loss: 9.33647170313634e-05
2023-01-21 13:00:17.042685: step: 1008/530, loss: 0.00031538010807707906
2023-01-21 13:00:18.247861: step: 1012/530, loss: 7.915497008070815e-06
2023-01-21 13:00:19.426061: step: 1016/530, loss: 0.012768586166203022
2023-01-21 13:00:20.604592: step: 1020/530, loss: 0.00975713785737753
2023-01-21 13:00:21.788203: step: 1024/530, loss: 0.00567894009873271
2023-01-21 13:00:22.969258: step: 1028/530, loss: 0.00019588469876907766
2023-01-21 13:00:24.174111: step: 1032/530, loss: 0.050194643437862396
2023-01-21 13:00:25.380976: step: 1036/530, loss: 0.03354144096374512
2023-01-21 13:00:26.567359: step: 1040/530, loss: 0.024974346160888672
2023-01-21 13:00:27.713776: step: 1044/530, loss: 9.450912330066785e-05
2023-01-21 13:00:28.985978: step: 1048/530, loss: 0.13647671043872833
2023-01-21 13:00:30.152232: step: 1052/530, loss: 0.03473663330078125
2023-01-21 13:00:31.354807: step: 1056/530, loss: 2.9182432626839727e-05
2023-01-21 13:00:32.562353: step: 1060/530, loss: 0.008570862002670765
2023-01-21 13:00:33.739401: step: 1064/530, loss: 0.00018696785264182836
2023-01-21 13:00:34.919320: step: 1068/530, loss: 0.0032999992836266756
2023-01-21 13:00:36.080405: step: 1072/530, loss: 0.0005920410039834678
2023-01-21 13:00:37.236173: step: 1076/530, loss: 0.0022314072120934725
2023-01-21 13:00:38.446416: step: 1080/530, loss: 0.020543480291962624
2023-01-21 13:00:39.610370: step: 1084/530, loss: 0.029347991570830345
2023-01-21 13:00:40.809869: step: 1088/530, loss: 0.04615059122443199
2023-01-21 13:00:42.047538: step: 1092/530, loss: 0.0012877463595941663
2023-01-21 13:00:43.216223: step: 1096/530, loss: 0.0014866829151287675
2023-01-21 13:00:44.398618: step: 1100/530, loss: 0.0016661644913256168
2023-01-21 13:00:45.621133: step: 1104/530, loss: 0.0003555297735147178
2023-01-21 13:00:46.792790: step: 1108/530, loss: 0.00023202896409202367
2023-01-21 13:00:47.988436: step: 1112/530, loss: 0.009560585021972656
2023-01-21 13:00:49.150095: step: 1116/530, loss: 0.01760578155517578
2023-01-21 13:00:50.305788: step: 1120/530, loss: 0.000244140625
2023-01-21 13:00:51.473260: step: 1124/530, loss: 0.03168916702270508
2023-01-21 13:00:52.650258: step: 1128/530, loss: 3.3092499506892636e-05
2023-01-21 13:00:53.821195: step: 1132/530, loss: 0.0003772735653910786
2023-01-21 13:00:54.986066: step: 1136/530, loss: 6.008148375258315e-06
2023-01-21 13:00:56.157439: step: 1140/530, loss: 0.00023326874361373484
2023-01-21 13:00:57.333547: step: 1144/530, loss: 0.00015196800814010203
2023-01-21 13:00:58.505972: step: 1148/530, loss: 7.152557373046875e-07
2023-01-21 13:00:59.744054: step: 1152/530, loss: 0.05049953609704971
2023-01-21 13:01:00.936649: step: 1156/530, loss: 0.0037563324440270662
2023-01-21 13:01:02.140800: step: 1160/530, loss: 0.028315259143710136
2023-01-21 13:01:03.344037: step: 1164/530, loss: 2.4795533590804553e-06
2023-01-21 13:01:04.483948: step: 1168/530, loss: 0.008877134881913662
2023-01-21 13:01:05.684594: step: 1172/530, loss: 0.00611801166087389
2023-01-21 13:01:06.847571: step: 1176/530, loss: 0.0030728341080248356
2023-01-21 13:01:07.991060: step: 1180/530, loss: 0.023630525916814804
2023-01-21 13:01:09.153970: step: 1184/530, loss: 0.012866735458374023
2023-01-21 13:01:10.323601: step: 1188/530, loss: 0.016594409942626953
2023-01-21 13:01:11.498545: step: 1192/530, loss: 0.7331809997558594
2023-01-21 13:01:12.706192: step: 1196/530, loss: 0.023678209632635117
2023-01-21 13:01:13.875574: step: 1200/530, loss: 0.00012874603271484375
2023-01-21 13:01:15.068830: step: 1204/530, loss: 0.06244392320513725
2023-01-21 13:01:16.266778: step: 1208/530, loss: 0.001530295587144792
2023-01-21 13:01:17.469567: step: 1212/530, loss: 0.0306854248046875
2023-01-21 13:01:18.656968: step: 1216/530, loss: 0.009037780575454235
2023-01-21 13:01:19.839026: step: 1220/530, loss: 0.0001447677641408518
2023-01-21 13:01:21.012640: step: 1224/530, loss: 2.1266936528263614e-05
2023-01-21 13:01:22.172983: step: 1228/530, loss: 0.0014192580711096525
2023-01-21 13:01:23.325324: step: 1232/530, loss: 0.0001623153657419607
2023-01-21 13:01:24.494804: step: 1236/530, loss: 6.10351571594947e-06
2023-01-21 13:01:25.673797: step: 1240/530, loss: 0.009286880493164062
2023-01-21 13:01:26.844274: step: 1244/530, loss: 0.00759048480540514
2023-01-21 13:01:27.991773: step: 1248/530, loss: 0.2149791717529297
2023-01-21 13:01:29.143743: step: 1252/530, loss: 0.004594040103256702
2023-01-21 13:01:30.291621: step: 1256/530, loss: 0.010485362261533737
2023-01-21 13:01:31.496981: step: 1260/530, loss: 0.00025777818518690765
2023-01-21 13:01:32.651119: step: 1264/530, loss: 3.108978125965223e-05
2023-01-21 13:01:33.797922: step: 1268/530, loss: 3.724098496604711e-05
2023-01-21 13:01:34.987698: step: 1272/530, loss: 0.02824382856488228
2023-01-21 13:01:36.159886: step: 1276/530, loss: 0.0008536339155398309
2023-01-21 13:01:37.315008: step: 1280/530, loss: 0.021918296813964844
2023-01-21 13:01:38.510286: step: 1284/530, loss: 2.8896331059513614e-05
2023-01-21 13:01:39.677889: step: 1288/530, loss: 0.002739048097282648
2023-01-21 13:01:40.820762: step: 1292/530, loss: 0.0001479625643696636
2023-01-21 13:01:42.034128: step: 1296/530, loss: 0.006362724583595991
2023-01-21 13:01:43.156956: step: 1300/530, loss: 6.618500628974289e-05
2023-01-21 13:01:44.346227: step: 1304/530, loss: 0.00021419525728560984
2023-01-21 13:01:45.538138: step: 1308/530, loss: 6.29425039733178e-06
2023-01-21 13:01:46.740376: step: 1312/530, loss: 0.08460979163646698
2023-01-21 13:01:47.949531: step: 1316/530, loss: 7.562637620139867e-05
2023-01-21 13:01:49.094812: step: 1320/530, loss: 0.014352512545883656
2023-01-21 13:01:50.274665: step: 1324/530, loss: 0.02317953109741211
2023-01-21 13:01:51.451247: step: 1328/530, loss: 0.0035579681862145662
2023-01-21 13:01:52.652802: step: 1332/530, loss: 0.07616596668958664
2023-01-21 13:01:53.848582: step: 1336/530, loss: 0.03576679527759552
2023-01-21 13:01:54.989541: step: 1340/530, loss: 0.012133312411606312
2023-01-21 13:01:56.110550: step: 1344/530, loss: 1.5258789289873675e-06
2023-01-21 13:01:57.303201: step: 1348/530, loss: 0.00012559890456032008
2023-01-21 13:01:58.501507: step: 1352/530, loss: 5.292892819852568e-05
2023-01-21 13:01:59.684022: step: 1356/530, loss: 0.0052702901884913445
2023-01-21 13:02:00.895148: step: 1360/530, loss: 0.029619980603456497
2023-01-21 13:02:02.066814: step: 1364/530, loss: 0.01212606392800808
2023-01-21 13:02:03.286557: step: 1368/530, loss: 0.0018018722767010331
2023-01-21 13:02:04.447523: step: 1372/530, loss: 0.0028234960045665503
2023-01-21 13:02:05.616006: step: 1376/530, loss: 0.00011181831359863281
2023-01-21 13:02:06.751282: step: 1380/530, loss: 0.0032169341575354338
2023-01-21 13:02:07.903653: step: 1384/530, loss: 0.03360586240887642
2023-01-21 13:02:09.124738: step: 1388/530, loss: 3.032684253412299e-05
2023-01-21 13:02:10.283404: step: 1392/530, loss: 0.0016109467251226306
2023-01-21 13:02:11.461145: step: 1396/530, loss: 0.0010810851817950606
2023-01-21 13:02:12.666525: step: 1400/530, loss: 0.006634521298110485
2023-01-21 13:02:13.830389: step: 1404/530, loss: 0.0003199577331542969
2023-01-21 13:02:15.044726: step: 1408/530, loss: 0.0006072759279049933
2023-01-21 13:02:16.191195: step: 1412/530, loss: 0.06238015368580818
2023-01-21 13:02:17.427648: step: 1416/530, loss: 0.0003296852228231728
2023-01-21 13:02:18.618171: step: 1420/530, loss: 0.0027104378677904606
2023-01-21 13:02:19.827341: step: 1424/530, loss: 0.006822013761848211
2023-01-21 13:02:21.021368: step: 1428/530, loss: 1.3828277587890625e-05
2023-01-21 13:02:22.162677: step: 1432/530, loss: 0.010188483633100986
2023-01-21 13:02:23.346247: step: 1436/530, loss: 0.004301690962165594
2023-01-21 13:02:24.556504: step: 1440/530, loss: 0.001052045845426619
2023-01-21 13:02:25.719971: step: 1444/530, loss: 0.003041595220565796
2023-01-21 13:02:26.902782: step: 1448/530, loss: 0.0009585380903445184
2023-01-21 13:02:28.089060: step: 1452/530, loss: 0.00013246537127997726
2023-01-21 13:02:29.307258: step: 1456/530, loss: 6.246566954359878e-06
2023-01-21 13:02:30.468462: step: 1460/530, loss: 0.0012956619029864669
2023-01-21 13:02:31.652499: step: 1464/530, loss: 0.0021375655196607113
2023-01-21 13:02:32.841733: step: 1468/530, loss: 8.783341036178172e-05
2023-01-21 13:02:34.021022: step: 1472/530, loss: 0.023109912872314453
2023-01-21 13:02:35.138314: step: 1476/530, loss: 0.001922702882438898
2023-01-21 13:02:36.344674: step: 1480/530, loss: 0.0004650116025004536
2023-01-21 13:02:37.525773: step: 1484/530, loss: 6.85691848048009e-05
2023-01-21 13:02:38.676764: step: 1488/530, loss: 8.277893357444555e-05
2023-01-21 13:02:39.837825: step: 1492/530, loss: 0.011076449416577816
2023-01-21 13:02:40.994135: step: 1496/530, loss: 3.1471245165448636e-06
2023-01-21 13:02:42.189503: step: 1500/530, loss: 0.03397378697991371
2023-01-21 13:02:43.377933: step: 1504/530, loss: 0.0004516601620707661
2023-01-21 13:02:44.594625: step: 1508/530, loss: 0.0021149637177586555
2023-01-21 13:02:45.747103: step: 1512/530, loss: 0.002013301942497492
2023-01-21 13:02:46.922165: step: 1516/530, loss: 9.803772263694555e-05
2023-01-21 13:02:48.094644: step: 1520/530, loss: 0.025347614660859108
2023-01-21 13:02:49.247059: step: 1524/530, loss: 0.0056841373443603516
2023-01-21 13:02:50.430942: step: 1528/530, loss: 0.0022999763023108244
2023-01-21 13:02:51.586445: step: 1532/530, loss: 1.544952465337701e-05
2023-01-21 13:02:52.744490: step: 1536/530, loss: 0.0358307845890522
2023-01-21 13:02:53.935703: step: 1540/530, loss: 0.00011887550499523059
2023-01-21 13:02:55.119275: step: 1544/530, loss: 0.006964207161217928
2023-01-21 13:02:56.279880: step: 1548/530, loss: 0.03176441043615341
2023-01-21 13:02:57.472405: step: 1552/530, loss: 0.002363491104915738
2023-01-21 13:02:58.615576: step: 1556/530, loss: 0.004384422674775124
2023-01-21 13:02:59.784080: step: 1560/530, loss: 0.001578474068082869
2023-01-21 13:03:00.981749: step: 1564/530, loss: 0.0002208709775004536
2023-01-21 13:03:02.172809: step: 1568/530, loss: 0.0006872176891192794
2023-01-21 13:03:03.371225: step: 1572/530, loss: 8.735656592762098e-05
2023-01-21 13:03:04.527944: step: 1576/530, loss: 0.012870502658188343
2023-01-21 13:03:05.717267: step: 1580/530, loss: 1.2111663636460435e-05
2023-01-21 13:03:06.923965: step: 1584/530, loss: 0.00031700136605650187
2023-01-21 13:03:08.125910: step: 1588/530, loss: 0.00013303756713867188
2023-01-21 13:03:09.314047: step: 1592/530, loss: 0.01388464029878378
2023-01-21 13:03:10.508309: step: 1596/530, loss: 0.002241134876385331
2023-01-21 13:03:11.678370: step: 1600/530, loss: 0.005175304599106312
2023-01-21 13:03:12.892318: step: 1604/530, loss: 0.0003341674746479839
2023-01-21 13:03:14.037792: step: 1608/530, loss: 0.0003044128534384072
2023-01-21 13:03:15.226774: step: 1612/530, loss: 0.030898094177246094
2023-01-21 13:03:16.425456: step: 1616/530, loss: 0.05405378341674805
2023-01-21 13:03:17.576053: step: 1620/530, loss: 0.00025281906710006297
2023-01-21 13:03:18.777767: step: 1624/530, loss: 0.012464333325624466
2023-01-21 13:03:19.971268: step: 1628/530, loss: 0.005871963687241077
2023-01-21 13:03:21.118905: step: 1632/530, loss: 0.0002311706484761089
2023-01-21 13:03:22.304130: step: 1636/530, loss: 0.0046561239287257195
2023-01-21 13:03:23.460275: step: 1640/530, loss: 0.0007787704234942794
2023-01-21 13:03:24.647770: step: 1644/530, loss: 0.05828724056482315
2023-01-21 13:03:25.827669: step: 1648/530, loss: 0.005613517947494984
2023-01-21 13:03:27.013244: step: 1652/530, loss: 8.859634544933215e-05
2023-01-21 13:03:28.166620: step: 1656/530, loss: 0.014995479956269264
2023-01-21 13:03:29.355396: step: 1660/530, loss: 0.0005239486927166581
2023-01-21 13:03:30.519405: step: 1664/530, loss: 0.0035930632147938013
2023-01-21 13:03:31.704673: step: 1668/530, loss: 0.0002971649228129536
2023-01-21 13:03:32.840250: step: 1672/530, loss: 0.008928203955292702
2023-01-21 13:03:34.015518: step: 1676/530, loss: 0.026163674890995026
2023-01-21 13:03:35.152083: step: 1680/530, loss: 0.0001846313534770161
2023-01-21 13:03:36.309720: step: 1684/530, loss: 0.001850128173828125
2023-01-21 13:03:37.446919: step: 1688/530, loss: 0.01158752478659153
2023-01-21 13:03:38.616663: step: 1692/530, loss: 0.00013198853412177414
2023-01-21 13:03:39.791133: step: 1696/530, loss: 7.629394644936838e-07
2023-01-21 13:03:40.990814: step: 1700/530, loss: 0.06135311350226402
2023-01-21 13:03:42.209391: step: 1704/530, loss: 0.00010347366333007812
2023-01-21 13:03:43.355348: step: 1708/530, loss: 0.010078048333525658
2023-01-21 13:03:44.593270: step: 1712/530, loss: -2.0694733393611386e-05
2023-01-21 13:03:45.774758: step: 1716/530, loss: 0.03971848264336586
2023-01-21 13:03:46.977715: step: 1720/530, loss: 0.005565356928855181
2023-01-21 13:03:48.160132: step: 1724/530, loss: 0.00013256072998046875
2023-01-21 13:03:49.312288: step: 1728/530, loss: 0.0007171630859375
2023-01-21 13:03:50.488762: step: 1732/530, loss: 0.011522389017045498
2023-01-21 13:03:51.631565: step: 1736/530, loss: 0.0003811836359091103
2023-01-21 13:03:52.802130: step: 1740/530, loss: 9.117127046920359e-05
2023-01-21 13:03:53.982853: step: 1744/530, loss: 0.04341239854693413
2023-01-21 13:03:55.159063: step: 1748/530, loss: 0.00011978149996139109
2023-01-21 13:03:56.331399: step: 1752/530, loss: 0.0016124247340485454
2023-01-21 13:03:57.480051: step: 1756/530, loss: 0.026941873133182526
2023-01-21 13:03:58.646547: step: 1760/530, loss: 0.0016798973083496094
2023-01-21 13:03:59.828874: step: 1764/530, loss: 0.0005294799921102822
2023-01-21 13:04:01.025213: step: 1768/530, loss: 0.0002500057453289628
2023-01-21 13:04:02.188311: step: 1772/530, loss: 0.0006555557483807206
2023-01-21 13:04:03.347870: step: 1776/530, loss: 0.0005375385517254472
2023-01-21 13:04:04.525919: step: 1780/530, loss: 0.00018386841111350805
2023-01-21 13:04:05.692683: step: 1784/530, loss: 0.006489753723144531
2023-01-21 13:04:06.895533: step: 1788/530, loss: 0.00165138253942132
2023-01-21 13:04:08.061125: step: 1792/530, loss: 0.020051386207342148
2023-01-21 13:04:09.244979: step: 1796/530, loss: 0.0018508911598473787
2023-01-21 13:04:10.396140: step: 1800/530, loss: 2.384185791015625e-05
2023-01-21 13:04:11.566093: step: 1804/530, loss: 0.022998999804258347
2023-01-21 13:04:12.706256: step: 1808/530, loss: 0.07964038848876953
2023-01-21 13:04:13.852803: step: 1812/530, loss: 0.00139369978569448
2023-01-21 13:04:15.040752: step: 1816/530, loss: 0.0007360458257608116
2023-01-21 13:04:16.213739: step: 1820/530, loss: 0.010867023840546608
2023-01-21 13:04:17.354116: step: 1824/530, loss: 7.62939453125e-06
2023-01-21 13:04:18.510641: step: 1828/530, loss: 0.0028465271461755037
2023-01-21 13:04:19.666710: step: 1832/530, loss: 0.0019508362747728825
2023-01-21 13:04:20.890620: step: 1836/530, loss: 0.0008322715875692666
2023-01-21 13:04:22.044582: step: 1840/530, loss: -1.697540210443549e-05
2023-01-21 13:04:23.181499: step: 1844/530, loss: 0.03522701561450958
2023-01-21 13:04:24.348816: step: 1848/530, loss: 0.045407772064208984
2023-01-21 13:04:25.514466: step: 1852/530, loss: 0.0006903648609295487
2023-01-21 13:04:26.712419: step: 1856/530, loss: 0.00048170090303756297
2023-01-21 13:04:27.883805: step: 1860/530, loss: 0.0032573698554188013
2023-01-21 13:04:29.077247: step: 1864/530, loss: 0.00097570416983217
2023-01-21 13:04:30.217324: step: 1868/530, loss: 1.4352799553307705e-05
2023-01-21 13:04:31.402032: step: 1872/530, loss: 7.324219041038305e-05
2023-01-21 13:04:32.577968: step: 1876/530, loss: 0.0012922286987304688
2023-01-21 13:04:33.765291: step: 1880/530, loss: 0.06396484375
2023-01-21 13:04:34.946678: step: 1884/530, loss: 9.684562974143773e-05
2023-01-21 13:04:36.162712: step: 1888/530, loss: 0.00028438569279387593
2023-01-21 13:04:37.346038: step: 1892/530, loss: 0.0044876099564135075
2023-01-21 13:04:38.547822: step: 1896/530, loss: 0.00038166047306731343
2023-01-21 13:04:39.730569: step: 1900/530, loss: 0.011277103796601295
2023-01-21 13:04:40.935462: step: 1904/530, loss: 0.0171876922249794
2023-01-21 13:04:42.115787: step: 1908/530, loss: 0.008937835693359375
2023-01-21 13:04:43.281779: step: 1912/530, loss: 0.001917076064273715
2023-01-21 13:04:44.466697: step: 1916/530, loss: 0.044335268437862396
2023-01-21 13:04:45.591219: step: 1920/530, loss: 0.0001510620058979839
2023-01-21 13:04:46.807313: step: 1924/530, loss: 0.022577762603759766
2023-01-21 13:04:48.003828: step: 1928/530, loss: 0.0007621765835210681
2023-01-21 13:04:49.180732: step: 1932/530, loss: 0.00020885468984488398
2023-01-21 13:04:50.365406: step: 1936/530, loss: 0.6109886169433594
2023-01-21 13:04:51.569498: step: 1940/530, loss: 1.4972687495173886e-05
2023-01-21 13:04:52.715402: step: 1944/530, loss: 5.53131121705519e-06
2023-01-21 13:04:53.889588: step: 1948/530, loss: 0.004287147428840399
2023-01-21 13:04:55.073025: step: 1952/530, loss: 0.004920387174934149
2023-01-21 13:04:56.243135: step: 1956/530, loss: 0.00034208298893645406
2023-01-21 13:04:57.408707: step: 1960/530, loss: 0.015040588565170765
2023-01-21 13:04:58.591604: step: 1964/530, loss: 7.820130122127011e-06
2023-01-21 13:04:59.755208: step: 1968/530, loss: 9.012222290039062e-05
2023-01-21 13:05:00.977354: step: 1972/530, loss: 0.0004574775812216103
2023-01-21 13:05:02.149791: step: 1976/530, loss: 0.0016291618812829256
2023-01-21 13:05:03.326564: step: 1980/530, loss: 0.0843442901968956
2023-01-21 13:05:04.487693: step: 1984/530, loss: 8.306503877975047e-05
2023-01-21 13:05:05.663610: step: 1988/530, loss: 0.02689075469970703
2023-01-21 13:05:06.831125: step: 1992/530, loss: 1.430511474609375e-05
2023-01-21 13:05:08.008004: step: 1996/530, loss: 0.012757301330566406
2023-01-21 13:05:09.158321: step: 2000/530, loss: 3.519058373058215e-05
2023-01-21 13:05:10.318630: step: 2004/530, loss: 0.0058303833939135075
2023-01-21 13:05:11.462493: step: 2008/530, loss: 0.001104641007259488
2023-01-21 13:05:12.647957: step: 2012/530, loss: 3.399848719709553e-05
2023-01-21 13:05:13.878424: step: 2016/530, loss: 4.2629242670955136e-05
2023-01-21 13:05:15.069597: step: 2020/530, loss: 0.01100218202918768
2023-01-21 13:05:16.225846: step: 2024/530, loss: 0.13027158379554749
2023-01-21 13:05:17.428594: step: 2028/530, loss: 0.0009748458978720009
2023-01-21 13:05:18.635185: step: 2032/530, loss: 0.05574851110577583
2023-01-21 13:05:19.802849: step: 2036/530, loss: 0.009688759222626686
2023-01-21 13:05:21.054906: step: 2040/530, loss: 0.00873866118490696
2023-01-21 13:05:22.223299: step: 2044/530, loss: 3.24249276673072e-06
2023-01-21 13:05:23.362984: step: 2048/530, loss: 0.00049676897469908
2023-01-21 13:05:24.557508: step: 2052/530, loss: 0.008192062377929688
2023-01-21 13:05:25.764424: step: 2056/530, loss: 0.00023956299992278218
2023-01-21 13:05:26.964627: step: 2060/530, loss: 0.019434548914432526
2023-01-21 13:05:28.163374: step: 2064/530, loss: 0.007743454072624445
2023-01-21 13:05:29.436928: step: 2068/530, loss: 0.0006824017036706209
2023-01-21 13:05:30.617286: step: 2072/530, loss: 0.013895797543227673
2023-01-21 13:05:31.839182: step: 2076/530, loss: 0.0012094498379155993
2023-01-21 13:05:33.033833: step: 2080/530, loss: 0.010045862756669521
2023-01-21 13:05:34.188027: step: 2084/530, loss: 0.014191294088959694
2023-01-21 13:05:35.355816: step: 2088/530, loss: 0.020464038476347923
2023-01-21 13:05:36.564580: step: 2092/530, loss: 0.026391983032226562
2023-01-21 13:05:37.741791: step: 2096/530, loss: 0.03534698486328125
2023-01-21 13:05:38.978348: step: 2100/530, loss: 0.00110797886736691
2023-01-21 13:05:40.150481: step: 2104/530, loss: 0.26089000701904297
2023-01-21 13:05:41.287830: step: 2108/530, loss: 1.602172778802924e-05
2023-01-21 13:05:42.470045: step: 2112/530, loss: 8.296966552734375e-05
2023-01-21 13:05:43.706228: step: 2116/530, loss: 0.004843521397560835
2023-01-21 13:05:44.829142: step: 2120/530, loss: 0.00043315888615325093
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5966562173458725, 'r': 0.7603195739014648, 'f1': 0.6686182669789228}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.660672030288689, 'r': 0.8027602070155262, 'f1': 0.7248182762201454}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
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': 24}
Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 13:06:28.039816: step: 4/530, loss: 2.8610231311176904e-05
2023-01-21 13:06:29.199945: step: 8/530, loss: 0.00030112266540527344
2023-01-21 13:06:30.440473: step: 12/530, loss: 4.920959327137098e-05
2023-01-21 13:06:31.575898: step: 16/530, loss: 0.0013895034790039062
2023-01-21 13:06:32.742393: step: 20/530, loss: 2.4700164431123994e-05
2023-01-21 13:06:33.924892: step: 24/530, loss: 0.002346229739487171
2023-01-21 13:06:35.058546: step: 28/530, loss: 4.501342846197076e-05
2023-01-21 13:06:36.220393: step: 32/530, loss: 0.0016015053261071444
2023-01-21 13:06:37.379469: step: 36/530, loss: 1.735687328618951e-05
2023-01-21 13:06:38.588668: step: 40/530, loss: 0.003616523928940296
2023-01-21 13:06:39.748287: step: 44/530, loss: 0.0013772010570392013
2023-01-21 13:06:40.901844: step: 48/530, loss: 0.0013776780106127262
2023-01-21 13:06:42.117583: step: 52/530, loss: 0.0005647659418173134
2023-01-21 13:06:43.258524: step: 56/530, loss: 0.017456578090786934
2023-01-21 13:06:44.415988: step: 60/530, loss: 0.3524666428565979
2023-01-21 13:06:45.575094: step: 64/530, loss: 0.03489341586828232
2023-01-21 13:06:46.788365: step: 68/530, loss: 0.008141708560287952
2023-01-21 13:06:47.984921: step: 72/530, loss: 9.059906005859375e-06
2023-01-21 13:06:49.153619: step: 76/530, loss: 0.0006840705755166709
2023-01-21 13:06:50.307917: step: 80/530, loss: 4.410744077176787e-05
2023-01-21 13:06:51.482987: step: 84/530, loss: 0.0004075646575074643
2023-01-21 13:06:52.639527: step: 88/530, loss: 0.00022687914315611124
2023-01-21 13:06:53.810282: step: 92/530, loss: 0.00473442068323493
2023-01-21 13:06:55.026007: step: 96/530, loss: 0.00018739700317382812
2023-01-21 13:06:56.187703: step: 100/530, loss: 0.020488977432250977
2023-01-21 13:06:57.312128: step: 104/530, loss: 0.00012311936006881297
2023-01-21 13:06:58.466940: step: 108/530, loss: 0.00228118896484375
2023-01-21 13:06:59.632105: step: 112/530, loss: 5.14984139954322e-06
2023-01-21 13:07:00.768222: step: 116/530, loss: 0.042673587799072266
2023-01-21 13:07:01.981507: step: 120/530, loss: 0.004301262088119984
2023-01-21 13:07:03.167122: step: 124/530, loss: 0.005278730299323797
2023-01-21 13:07:04.295348: step: 128/530, loss: 0.00015459061251021922
2023-01-21 13:07:05.490983: step: 132/530, loss: 0.0064051151275634766
2023-01-21 13:07:06.642970: step: 136/530, loss: 0.00020074844360351562
2023-01-21 13:07:07.797254: step: 140/530, loss: 0.00320091238245368
2023-01-21 13:07:08.949985: step: 144/530, loss: 0.0005567550542764366
2023-01-21 13:07:10.128226: step: 148/530, loss: 0.005089759360998869
2023-01-21 13:07:11.317778: step: 152/530, loss: 0.0013366222847253084
2023-01-21 13:07:12.471445: step: 156/530, loss: 0.0005156517145223916
2023-01-21 13:07:13.689966: step: 160/530, loss: 0.07894507050514221
2023-01-21 13:07:14.848086: step: 164/530, loss: 0.002525425050407648
2023-01-21 13:07:15.989714: step: 168/530, loss: 8.153916132869199e-05
2023-01-21 13:07:17.198757: step: 172/530, loss: 0.005180740263313055
2023-01-21 13:07:18.378437: step: 176/530, loss: 3.137588646495715e-05
2023-01-21 13:07:19.584648: step: 180/530, loss: 0.00013055802264716476
2023-01-21 13:07:20.774312: step: 184/530, loss: 0.007346916012465954
2023-01-21 13:07:21.936409: step: 188/530, loss: 1.831054760259576e-05
2023-01-21 13:07:23.105403: step: 192/530, loss: 0.0013288498157635331
2023-01-21 13:07:24.267232: step: 196/530, loss: 9.74655122263357e-05
2023-01-21 13:07:25.423518: step: 200/530, loss: 0.002631122013553977
2023-01-21 13:07:26.616803: step: 204/530, loss: 0.0023022652603685856
2023-01-21 13:07:27.828033: step: 208/530, loss: 0.028542518615722656
2023-01-21 13:07:28.997407: step: 212/530, loss: 0.0020797729957848787
2023-01-21 13:07:30.190429: step: 216/530, loss: 0.01642742194235325
2023-01-21 13:07:31.479150: step: 220/530, loss: 7.41004987503402e-05
2023-01-21 13:07:32.684987: step: 224/530, loss: 0.0009593010181561112
2023-01-21 13:07:33.851579: step: 228/530, loss: 6.48498553346144e-06
2023-01-21 13:07:35.037639: step: 232/530, loss: 7.476806786144152e-05
2023-01-21 13:07:36.290004: step: 236/530, loss: 0.010511589236557484
2023-01-21 13:07:37.452815: step: 240/530, loss: 0.0020109207835048437
2023-01-21 13:07:38.629154: step: 244/530, loss: 0.016209030523896217
2023-01-21 13:07:39.812970: step: 248/530, loss: 0.0001601219264557585
2023-01-21 13:07:40.973163: step: 252/530, loss: 0.0037382126320153475
2023-01-21 13:07:42.166183: step: 256/530, loss: 0.04468689113855362
2023-01-21 13:07:43.365689: step: 260/530, loss: 7.333754911087453e-05
2023-01-21 13:07:44.528826: step: 264/530, loss: 0.0015219688648357987
2023-01-21 13:07:45.689333: step: 268/530, loss: 0.002352809999138117
2023-01-21 13:07:46.876329: step: 272/530, loss: 0.007522773928940296
2023-01-21 13:07:48.062194: step: 276/530, loss: 0.00037469863309524953
2023-01-21 13:07:49.219538: step: 280/530, loss: 0.0010393142001703382
2023-01-21 13:07:50.415804: step: 284/530, loss: 0.0002165794576285407
2023-01-21 13:07:51.586184: step: 288/530, loss: 0.0004205704026389867
2023-01-21 13:07:52.762138: step: 292/530, loss: 0.009319496341049671
2023-01-21 13:07:53.917776: step: 296/530, loss: 0.0013811112148687243
2023-01-21 13:07:55.117804: step: 300/530, loss: 0.004154205322265625
2023-01-21 13:07:56.317500: step: 304/530, loss: 0.0006717205396853387
2023-01-21 13:07:57.473470: step: 308/530, loss: 0.025911331176757812
2023-01-21 13:07:58.627608: step: 312/530, loss: 0.011598111130297184
2023-01-21 13:07:59.787117: step: 316/530, loss: 0.00010623932030284777
2023-01-21 13:08:00.978454: step: 320/530, loss: 0.0020164488814771175
2023-01-21 13:08:02.149341: step: 324/530, loss: 8.39233416627394e-06
2023-01-21 13:08:03.360719: step: 328/530, loss: 0.0016307830810546875
2023-01-21 13:08:04.602641: step: 332/530, loss: 0.005638694856315851
2023-01-21 13:08:05.741437: step: 336/530, loss: 5.455017162603326e-05
2023-01-21 13:08:06.942693: step: 340/530, loss: 7.915496826171875e-05
2023-01-21 13:08:08.081357: step: 344/530, loss: 0.00010924339585471898
2023-01-21 13:08:09.289436: step: 348/530, loss: 0.001330900238826871
2023-01-21 13:08:10.457954: step: 352/530, loss: 0.03559169918298721
2023-01-21 13:08:11.617771: step: 356/530, loss: 0.0019571303855627775
2023-01-21 13:08:12.823032: step: 360/530, loss: 0.004663276951760054
2023-01-21 13:08:14.004285: step: 364/530, loss: 0.01383962668478489
2023-01-21 13:08:15.160115: step: 368/530, loss: 0.02313375473022461
2023-01-21 13:08:16.291003: step: 372/530, loss: 0.0007349014631472528
2023-01-21 13:08:17.464299: step: 376/530, loss: 0.0002777099434752017
2023-01-21 13:08:18.659492: step: 380/530, loss: 0.005493354983627796
2023-01-21 13:08:19.826758: step: 384/530, loss: 0.011819315142929554
2023-01-21 13:08:20.983436: step: 388/530, loss: 0.00010414123244117945
2023-01-21 13:08:22.165553: step: 392/530, loss: 0.017976760864257812
2023-01-21 13:08:23.315739: step: 396/530, loss: 0.028553390875458717
2023-01-21 13:08:24.483481: step: 400/530, loss: 0.009997558780014515
2023-01-21 13:08:25.639277: step: 404/530, loss: 0.0003131866396870464
2023-01-21 13:08:26.824853: step: 408/530, loss: 0.0001901626674225554
2023-01-21 13:08:28.010761: step: 412/530, loss: 0.013402557000517845
2023-01-21 13:08:29.188287: step: 416/530, loss: 0.011005974374711514
2023-01-21 13:08:30.417135: step: 420/530, loss: 0.017657851800322533
2023-01-21 13:08:31.581728: step: 424/530, loss: 3.8787944316864014
2023-01-21 13:08:32.773879: step: 428/530, loss: 0.0010305405594408512
2023-01-21 13:08:33.955770: step: 432/530, loss: 1.811981201171875e-05
2023-01-21 13:08:35.138129: step: 436/530, loss: 0.002593135926872492
2023-01-21 13:08:36.303399: step: 440/530, loss: 0.0010244370205327868
2023-01-21 13:08:37.501532: step: 444/530, loss: 0.006948661990463734
2023-01-21 13:08:38.691719: step: 448/530, loss: 0.0049953460693359375
2023-01-21 13:08:39.889021: step: 452/530, loss: 0.00032596586970612407
2023-01-21 13:08:41.097043: step: 456/530, loss: 4.625320343620842e-06
2023-01-21 13:08:42.298423: step: 460/530, loss: 1.3780593690171372e-05
2023-01-21 13:08:43.488892: step: 464/530, loss: 0.004208659753203392
2023-01-21 13:08:44.627454: step: 468/530, loss: 9.703636169433594e-05
2023-01-21 13:08:45.844910: step: 472/530, loss: 0.0031389237847179174
2023-01-21 13:08:47.018994: step: 476/530, loss: 0.00023431777663063258
2023-01-21 13:08:48.158268: step: 480/530, loss: 0.006004285998642445
2023-01-21 13:08:49.346239: step: 484/530, loss: 0.0002674102724995464
2023-01-21 13:08:50.477881: step: 488/530, loss: -1.144409225162235e-06
2023-01-21 13:08:51.656187: step: 492/530, loss: 0.002213001251220703
2023-01-21 13:08:52.811856: step: 496/530, loss: 0.10098133236169815
2023-01-21 13:08:53.983636: step: 500/530, loss: 0.001959896180778742
2023-01-21 13:08:55.178899: step: 504/530, loss: 0.12911739945411682
2023-01-21 13:08:56.309268: step: 508/530, loss: 0.000282096880255267
2023-01-21 13:08:57.513805: step: 512/530, loss: 0.013754653744399548
2023-01-21 13:08:58.652294: step: 516/530, loss: 0.00013847350783180445
2023-01-21 13:08:59.802054: step: 520/530, loss: 0.0002933502255473286
2023-01-21 13:09:00.955353: step: 524/530, loss: 0.002707862760871649
2023-01-21 13:09:02.143303: step: 528/530, loss: 0.06650009006261826
2023-01-21 13:09:03.324301: step: 532/530, loss: 0.018381405621767044
2023-01-21 13:09:04.510644: step: 536/530, loss: 0.0006687164423055947
2023-01-21 13:09:05.664981: step: 540/530, loss: 0.0001873016299214214
2023-01-21 13:09:06.871407: step: 544/530, loss: 0.0003247261338401586
2023-01-21 13:09:08.090833: step: 548/530, loss: 0.021899795159697533
2023-01-21 13:09:09.281347: step: 552/530, loss: 0.00013939141354057938
2023-01-21 13:09:10.453919: step: 556/530, loss: 0.07399959117174149
2023-01-21 13:09:11.623419: step: 560/530, loss: 8.254051499534398e-05
2023-01-21 13:09:12.764727: step: 564/530, loss: 5.316734313964844e-05
2023-01-21 13:09:13.933419: step: 568/530, loss: 0.0491674430668354
2023-01-21 13:09:15.119197: step: 572/530, loss: 0.00020227432833053172
2023-01-21 13:09:16.301566: step: 576/530, loss: 0.016153907403349876
2023-01-21 13:09:17.477255: step: 580/530, loss: 0.037256333976984024
2023-01-21 13:09:18.663370: step: 584/530, loss: 5.626678102998994e-06
2023-01-21 13:09:19.794588: step: 588/530, loss: 0.0015472412342205644
2023-01-21 13:09:20.980153: step: 592/530, loss: 0.00028896331787109375
2023-01-21 13:09:22.152138: step: 596/530, loss: 0.0006258010980673134
2023-01-21 13:09:23.340606: step: 600/530, loss: 0.00015382767014671117
2023-01-21 13:09:24.539472: step: 604/530, loss: 0.0009347915765829384
2023-01-21 13:09:25.674522: step: 608/530, loss: 0.0010693550575524569
2023-01-21 13:09:26.837028: step: 612/530, loss: 4.3487551010912284e-05
2023-01-21 13:09:28.042792: step: 616/530, loss: 0.004958534613251686
2023-01-21 13:09:29.238521: step: 620/530, loss: 0.0035626410972326994
2023-01-21 13:09:30.373114: step: 624/530, loss: 5.170107033336535e-05
2023-01-21 13:09:31.552531: step: 628/530, loss: 0.0010870933765545487
2023-01-21 13:09:32.747247: step: 632/530, loss: 0.01930713653564453
2023-01-21 13:09:33.942088: step: 636/530, loss: 0.0350315123796463
2023-01-21 13:09:35.098198: step: 640/530, loss: 2.431869688734878e-06
2023-01-21 13:09:36.247134: step: 644/530, loss: 2.86102294921875e-06
2023-01-21 13:09:37.427532: step: 648/530, loss: 0.005962944123893976
2023-01-21 13:09:38.619406: step: 652/530, loss: 0.03679676353931427
2023-01-21 13:09:39.792841: step: 656/530, loss: 0.0029224397148936987
2023-01-21 13:09:40.956528: step: 660/530, loss: 0.0005386352422647178
2023-01-21 13:09:42.172005: step: 664/530, loss: 0.0001626968296477571
2023-01-21 13:09:43.329688: step: 668/530, loss: 0.0038320065941661596
2023-01-21 13:09:44.545614: step: 672/530, loss: 3.5953522456111386e-05
2023-01-21 13:09:45.723885: step: 676/530, loss: 0.03695201873779297
2023-01-21 13:09:46.906727: step: 680/530, loss: 0.0002428054722258821
2023-01-21 13:09:48.128510: step: 684/530, loss: 0.0013056278694421053
2023-01-21 13:09:49.285990: step: 688/530, loss: 2.7990341550321318e-05
2023-01-21 13:09:50.506008: step: 692/530, loss: 0.00013294219388626516
2023-01-21 13:09:51.721236: step: 696/530, loss: 0.006185817997902632
2023-01-21 13:09:52.891685: step: 700/530, loss: 0.01731119118630886
2023-01-21 13:09:54.072580: step: 704/530, loss: 0.001958179520443082
2023-01-21 13:09:55.224269: step: 708/530, loss: 0.0034168243873864412
2023-01-21 13:09:56.385100: step: 712/530, loss: 0.013438224792480469
2023-01-21 13:09:57.558463: step: 716/530, loss: 3.80516066798009e-05
2023-01-21 13:09:58.760313: step: 720/530, loss: 0.0004945755354128778
2023-01-21 13:09:59.956974: step: 724/530, loss: 0.00011692046973621473
2023-01-21 13:10:01.113192: step: 728/530, loss: 0.00026569367037154734
2023-01-21 13:10:02.267341: step: 732/530, loss: 0.0017206192715093493
2023-01-21 13:10:03.475502: step: 736/530, loss: 0.06024417653679848
2023-01-21 13:10:04.664846: step: 740/530, loss: 9.193420555675402e-05
2023-01-21 13:10:05.797808: step: 744/530, loss: 0.004082441329956055
2023-01-21 13:10:07.021475: step: 748/530, loss: 3.128051685052924e-05
2023-01-21 13:10:08.171901: step: 752/530, loss: 0.00048484804574400187
2023-01-21 13:10:09.340444: step: 756/530, loss: 0.0011425971752032638
2023-01-21 13:10:10.513494: step: 760/530, loss: 0.0004642009735107422
2023-01-21 13:10:11.741659: step: 764/530, loss: 2.1076202756376006e-05
2023-01-21 13:10:12.887012: step: 768/530, loss: 1.258850079466356e-05
2023-01-21 13:10:14.047112: step: 772/530, loss: 3.7860871088923886e-05
2023-01-21 13:10:15.260538: step: 776/530, loss: 0.04156646877527237
2023-01-21 13:10:16.485718: step: 780/530, loss: 7.200241088867188e-05
2023-01-21 13:10:17.678921: step: 784/530, loss: 3.2711028325138614e-05
2023-01-21 13:10:18.868245: step: 788/530, loss: 0.0013545990223065019
2023-01-21 13:10:20.056995: step: 792/530, loss: 0.348680317401886
2023-01-21 13:10:21.219901: step: 796/530, loss: 0.00010690689668990672
2023-01-21 13:10:22.420733: step: 800/530, loss: 0.010894298553466797
2023-01-21 13:10:23.581809: step: 804/530, loss: 0.0027828216552734375
2023-01-21 13:10:24.774517: step: 808/530, loss: 1.0328563451766968
2023-01-21 13:10:25.926790: step: 812/530, loss: 0.04568615183234215
2023-01-21 13:10:27.085247: step: 816/530, loss: 1.9931792849092744e-05
2023-01-21 13:10:28.246322: step: 820/530, loss: 0.005255031865090132
2023-01-21 13:10:29.430242: step: 824/530, loss: 1.2874604180979077e-05
2023-01-21 13:10:30.561462: step: 828/530, loss: 3.80516066798009e-05
2023-01-21 13:10:31.726534: step: 832/530, loss: 8.106232598947827e-06
2023-01-21 13:10:32.925630: step: 836/530, loss: 0.0001008987455861643
2023-01-21 13:10:34.076788: step: 840/530, loss: 0.003927039913833141
2023-01-21 13:10:35.238137: step: 844/530, loss: 0.014068317599594593
2023-01-21 13:10:36.437483: step: 848/530, loss: 7.51018596929498e-05
2023-01-21 13:10:37.589072: step: 852/530, loss: 2.0980837689421605e-06
2023-01-21 13:10:38.762643: step: 856/530, loss: 7.06017017364502e-05
2023-01-21 13:10:39.943289: step: 860/530, loss: 0.01698770374059677
2023-01-21 13:10:41.118900: step: 864/530, loss: 3.3855438232421875e-05
2023-01-21 13:10:42.358004: step: 868/530, loss: 2.679825047380291e-05
2023-01-21 13:10:43.561278: step: 872/530, loss: 0.057471469044685364
2023-01-21 13:10:44.734463: step: 876/530, loss: 0.0015130043029785156
2023-01-21 13:10:45.912142: step: 880/530, loss: 6.237030174816027e-05
2023-01-21 13:10:47.072628: step: 884/530, loss: 0.012771129608154297
2023-01-21 13:10:48.248267: step: 888/530, loss: 5.702972339349799e-05
2023-01-21 13:10:49.400330: step: 892/530, loss: 0.004717064090073109
2023-01-21 13:10:50.559213: step: 896/530, loss: 0.08671274781227112
2023-01-21 13:10:51.759906: step: 900/530, loss: 2.689361645025201e-05
2023-01-21 13:10:52.937579: step: 904/530, loss: 0.0001701354922261089
2023-01-21 13:10:54.134484: step: 908/530, loss: 0.00448651285842061
2023-01-21 13:10:55.351430: step: 912/530, loss: 0.005318641662597656
2023-01-21 13:10:56.606017: step: 916/530, loss: 0.04563131555914879
2023-01-21 13:10:57.812323: step: 920/530, loss: 0.0001272201625397429
2023-01-21 13:10:58.987225: step: 924/530, loss: 8.811950829112902e-05
2023-01-21 13:11:00.170292: step: 928/530, loss: 0.00016098022751975805
2023-01-21 13:11:01.350621: step: 932/530, loss: 0.03024015575647354
2023-01-21 13:11:02.636254: step: 936/530, loss: -1.0490418844710803e-06
2023-01-21 13:11:03.777466: step: 940/530, loss: 0.03760671615600586
2023-01-21 13:11:04.935331: step: 944/530, loss: 7.915497008070815e-06
2023-01-21 13:11:06.101727: step: 948/530, loss: 0.010150527581572533
2023-01-21 13:11:07.301512: step: 952/530, loss: -2.6226043701171875e-06
2023-01-21 13:11:08.510932: step: 956/530, loss: 0.031029893085360527
2023-01-21 13:11:09.742339: step: 960/530, loss: 1.9454957509879023e-05
2023-01-21 13:11:10.946429: step: 964/530, loss: 0.00800857599824667
2023-01-21 13:11:12.125472: step: 968/530, loss: 0.0007581710815429688
2023-01-21 13:11:13.309526: step: 972/530, loss: 0.0022471428383141756
2023-01-21 13:11:14.474817: step: 976/530, loss: 5.2261355449445546e-05
2023-01-21 13:11:15.685595: step: 980/530, loss: 3.652572922874242e-05
2023-01-21 13:11:16.833186: step: 984/530, loss: 6.618499901378527e-05
2023-01-21 13:11:18.013682: step: 988/530, loss: 0.0010714532108977437
2023-01-21 13:11:19.156028: step: 992/530, loss: 0.0011800766224041581
2023-01-21 13:11:20.312871: step: 996/530, loss: 0.009926033206284046
2023-01-21 13:11:21.476018: step: 1000/530, loss: 0.0003354072687216103
2023-01-21 13:11:22.664756: step: 1004/530, loss: 0.004562282469123602
2023-01-21 13:11:23.849217: step: 1008/530, loss: 4.482269105210435e-06
2023-01-21 13:11:25.026391: step: 1012/530, loss: 0.017740631476044655
2023-01-21 13:11:26.166785: step: 1016/530, loss: 0.00041332244290970266
2023-01-21 13:11:27.365265: step: 1020/530, loss: 0.013396358117461205
2023-01-21 13:11:28.527055: step: 1024/530, loss: 2.3174286980065517e-05
2023-01-21 13:11:29.735495: step: 1028/530, loss: 9.5367431640625e-06
2023-01-21 13:11:30.905471: step: 1032/530, loss: 0.0002525329764466733
2023-01-21 13:11:32.078167: step: 1036/530, loss: 0.0011200904846191406
2023-01-21 13:11:33.275926: step: 1040/530, loss: 0.0007210731273517013
2023-01-21 13:11:34.455036: step: 1044/530, loss: 0.024316787719726562
2023-01-21 13:11:35.579584: step: 1048/530, loss: 0.0033081055153161287
2023-01-21 13:11:36.746086: step: 1052/530, loss: 0.023715544492006302
2023-01-21 13:11:37.987595: step: 1056/530, loss: 0.0011663436889648438
2023-01-21 13:11:39.166060: step: 1060/530, loss: 9.059906005859375e-06
2023-01-21 13:11:40.367720: step: 1064/530, loss: 0.003678607987239957
2023-01-21 13:11:41.546035: step: 1068/530, loss: 3.5095217754133046e-05
2023-01-21 13:11:42.710548: step: 1072/530, loss: 0.000904083251953125
2023-01-21 13:11:43.906670: step: 1076/530, loss: 0.00022010803513694555
2023-01-21 13:11:45.099260: step: 1080/530, loss: 0.0051860809326171875
2023-01-21 13:11:46.264961: step: 1084/530, loss: 5.645752025884576e-05
2023-01-21 13:11:47.440932: step: 1088/530, loss: 0.005726623814553022
2023-01-21 13:11:48.631163: step: 1092/530, loss: 0.0002117156982421875
2023-01-21 13:11:49.803599: step: 1096/530, loss: 0.003433704376220703
2023-01-21 13:11:50.961901: step: 1100/530, loss: 8.17298932815902e-05
2023-01-21 13:11:52.156248: step: 1104/530, loss: 0.002113819122314453
2023-01-21 13:11:53.330003: step: 1108/530, loss: 0.010368680581450462
2023-01-21 13:11:54.528410: step: 1112/530, loss: 0.00024094581021927297
2023-01-21 13:11:55.719748: step: 1116/530, loss: 0.007313537411391735
2023-01-21 13:11:56.984242: step: 1120/530, loss: 0.014876746572554111
2023-01-21 13:11:58.166152: step: 1124/530, loss: 0.017028523609042168
2023-01-21 13:11:59.337330: step: 1128/530, loss: 0.004668808076530695
2023-01-21 13:12:00.488947: step: 1132/530, loss: 0.06572303920984268
2023-01-21 13:12:01.655733: step: 1136/530, loss: 0.0008529662736691535
2023-01-21 13:12:02.872719: step: 1140/530, loss: 0.032503318041563034
2023-01-21 13:12:04.053791: step: 1144/530, loss: 0.0007240295526571572
2023-01-21 13:12:05.260250: step: 1148/530, loss: -2.241135007352568e-06
2023-01-21 13:12:06.481101: step: 1152/530, loss: 0.008105326443910599
2023-01-21 13:12:07.629948: step: 1156/530, loss: 0.0008573532104492188
2023-01-21 13:12:08.793226: step: 1160/530, loss: 0.03178920969367027
2023-01-21 13:12:09.959467: step: 1164/530, loss: 0.005588531494140625
2023-01-21 13:12:11.128570: step: 1168/530, loss: 0.0027174949645996094
2023-01-21 13:12:12.350319: step: 1172/530, loss: 3.986358569818549e-05
2023-01-21 13:12:13.521623: step: 1176/530, loss: 0.00017042159743141383
2023-01-21 13:12:14.662194: step: 1180/530, loss: 1.62124638336536e-06
2023-01-21 13:12:15.865437: step: 1184/530, loss: 7.114410982467234e-05
2023-01-21 13:12:17.050231: step: 1188/530, loss: 0.00031423717155121267
2023-01-21 13:12:18.171475: step: 1192/530, loss: 4.997253563487902e-05
2023-01-21 13:12:19.334491: step: 1196/530, loss: 0.015460587106645107
2023-01-21 13:12:20.491918: step: 1200/530, loss: 0.0008395195472985506
2023-01-21 13:12:21.648787: step: 1204/530, loss: 0.2750614285469055
2023-01-21 13:12:22.832497: step: 1208/530, loss: 0.01067962683737278
2023-01-21 13:12:23.981476: step: 1212/530, loss: 0.0009273529285565019
2023-01-21 13:12:25.210448: step: 1216/530, loss: 0.0005411148304119706
2023-01-21 13:12:26.369373: step: 1220/530, loss: 0.0001255035458598286
2023-01-21 13:12:27.522758: step: 1224/530, loss: 0.013475227169692516
2023-01-21 13:12:28.673984: step: 1228/530, loss: 0.10015039891004562
2023-01-21 13:12:29.803372: step: 1232/530, loss: 0.00964660756289959
2023-01-21 13:12:30.967170: step: 1236/530, loss: 0.008114432916045189
2023-01-21 13:12:32.129373: step: 1240/530, loss: 0.0003173828299622983
2023-01-21 13:12:33.268547: step: 1244/530, loss: 1.9836426872643642e-05
2023-01-21 13:12:34.485576: step: 1248/530, loss: 0.0001046180768753402
2023-01-21 13:12:35.731136: step: 1252/530, loss: 0.0021859167609363794
2023-01-21 13:12:36.912441: step: 1256/530, loss: 0.007715749554336071
2023-01-21 13:12:38.083521: step: 1260/530, loss: 0.009414386935532093
2023-01-21 13:12:39.255835: step: 1264/530, loss: 0.03513622283935547
2023-01-21 13:12:40.490242: step: 1268/530, loss: 0.0027791978791356087
2023-01-21 13:12:41.689283: step: 1272/530, loss: 0.0009056091075763106
2023-01-21 13:12:42.899297: step: 1276/530, loss: 0.0024213790893554688
2023-01-21 13:12:44.043307: step: 1280/530, loss: 0.0014198303688317537
2023-01-21 13:12:45.205833: step: 1284/530, loss: 0.004444694146513939
2023-01-21 13:12:46.419639: step: 1288/530, loss: 0.003329944796860218
2023-01-21 13:12:47.567552: step: 1292/530, loss: 0.0009348869207315147
2023-01-21 13:12:48.745199: step: 1296/530, loss: 0.00026702880859375
2023-01-21 13:12:49.914104: step: 1300/530, loss: 0.00299835205078125
2023-01-21 13:12:51.065410: step: 1304/530, loss: 0.00018482207087799907
2023-01-21 13:12:52.295580: step: 1308/530, loss: 0.0005199432489462197
2023-01-21 13:12:53.451390: step: 1312/530, loss: 0.012120533734560013
2023-01-21 13:12:54.612897: step: 1316/530, loss: 0.05013008415699005
2023-01-21 13:12:55.753930: step: 1320/530, loss: 0.002054882235825062
2023-01-21 13:12:56.923950: step: 1324/530, loss: 0.0003935813729185611
2023-01-21 13:12:58.092741: step: 1328/530, loss: 4.863738922722405e-06
2023-01-21 13:12:59.248409: step: 1332/530, loss: 0.016919897869229317
2023-01-21 13:13:00.424282: step: 1336/530, loss: 0.024862386286258698
2023-01-21 13:13:01.622837: step: 1340/530, loss: 0.00015563966007903218
2023-01-21 13:13:02.762687: step: 1344/530, loss: 0.00042514799861237407
2023-01-21 13:13:03.946215: step: 1348/530, loss: 0.01694164238870144
2023-01-21 13:13:05.114425: step: 1352/530, loss: 0.0005329131963662803
2023-01-21 13:13:06.283732: step: 1356/530, loss: 0.0009568214300088584
2023-01-21 13:13:07.437638: step: 1360/530, loss: 0.022759154438972473
2023-01-21 13:13:08.593292: step: 1364/530, loss: 0.020641708746552467
2023-01-21 13:13:09.797530: step: 1368/530, loss: 6.370544724632055e-05
2023-01-21 13:13:10.944857: step: 1372/530, loss: 0.05861835554242134
2023-01-21 13:13:12.159969: step: 1376/530, loss: 0.003581809811294079
2023-01-21 13:13:13.379692: step: 1380/530, loss: 0.0006729125743731856
2023-01-21 13:13:14.602674: step: 1384/530, loss: 0.01955127902328968
2023-01-21 13:13:15.780509: step: 1388/530, loss: 0.0031902315095067024
2023-01-21 13:13:16.965172: step: 1392/530, loss: 0.12280026078224182
2023-01-21 13:13:18.123792: step: 1396/530, loss: 0.0033663748763501644
2023-01-21 13:13:19.293742: step: 1400/530, loss: 0.0012676238548010588
2023-01-21 13:13:20.561917: step: 1404/530, loss: 0.001957464264705777
2023-01-21 13:13:21.714171: step: 1408/530, loss: 0.0006841659778729081
2023-01-21 13:13:22.917344: step: 1412/530, loss: 0.003468799637630582
2023-01-21 13:13:24.083938: step: 1416/530, loss: 5.683898780262098e-05
2023-01-21 13:13:25.233989: step: 1420/530, loss: 0.0003314971982035786
2023-01-21 13:13:26.395346: step: 1424/530, loss: 1.1825562978629023e-05
2023-01-21 13:13:27.577525: step: 1428/530, loss: 0.0072282785549759865
2023-01-21 13:13:28.734446: step: 1432/530, loss: 2.117157055181451e-05
2023-01-21 13:13:29.930566: step: 1436/530, loss: 1.392364538332913e-05
2023-01-21 13:13:31.100368: step: 1440/530, loss: 0.00032300950260832906
2023-01-21 13:13:32.285367: step: 1444/530, loss: 0.029506873339414597
2023-01-21 13:13:33.483058: step: 1448/530, loss: 0.00043296816875226796
2023-01-21 13:13:34.678690: step: 1452/530, loss: 0.002433300018310547
2023-01-21 13:13:35.866590: step: 1456/530, loss: 2.2411345526052173e-06
2023-01-21 13:13:37.059451: step: 1460/530, loss: 0.002944088075309992
2023-01-21 13:13:38.196390: step: 1464/530, loss: 0.005879783537238836
2023-01-21 13:13:39.367608: step: 1468/530, loss: 0.01812162436544895
2023-01-21 13:13:40.539480: step: 1472/530, loss: 0.0010649681789800525
2023-01-21 13:13:41.699935: step: 1476/530, loss: 6.198883056640625e-06
2023-01-21 13:13:42.924949: step: 1480/530, loss: 0.0006489753723144531
2023-01-21 13:13:44.120187: step: 1484/530, loss: 1.4305115314527939e-07
2023-01-21 13:13:45.291756: step: 1488/530, loss: 0.1085321381688118
2023-01-21 13:13:46.463049: step: 1492/530, loss: 0.0005033492925576866
2023-01-21 13:13:47.669887: step: 1496/530, loss: 4.0054324017546605e-06
2023-01-21 13:13:48.815411: step: 1500/530, loss: 0.00018973351689055562
2023-01-21 13:13:49.943192: step: 1504/530, loss: 0.0008160591241903603
2023-01-21 13:13:51.150459: step: 1508/530, loss: 0.04935717210173607
2023-01-21 13:13:52.328079: step: 1512/530, loss: 0.024823378771543503
2023-01-21 13:13:53.490350: step: 1516/530, loss: 0.009255743585526943
2023-01-21 13:13:54.661442: step: 1520/530, loss: 8.106231689453125e-05
2023-01-21 13:13:55.823010: step: 1524/530, loss: 2.6798248654813506e-05
2023-01-21 13:13:56.994041: step: 1528/530, loss: 0.00024538038996979594
2023-01-21 13:13:58.185372: step: 1532/530, loss: 0.0011971474159508944
2023-01-21 13:13:59.348800: step: 1536/530, loss: 7.629396350239404e-07
2023-01-21 13:14:00.541315: step: 1540/530, loss: 0.0003688812139444053
2023-01-21 13:14:01.715154: step: 1544/530, loss: 0.001695919083431363
2023-01-21 13:14:02.887126: step: 1548/530, loss: 0.0007320403819903731
2023-01-21 13:14:04.023307: step: 1552/530, loss: 0.0021512031089514494
2023-01-21 13:14:05.213866: step: 1556/530, loss: 0.0037168501876294613
2023-01-21 13:14:06.417517: step: 1560/530, loss: 0.13877636194229126
2023-01-21 13:14:07.608029: step: 1564/530, loss: 0.0021050453651696444
2023-01-21 13:14:08.805751: step: 1568/530, loss: 0.00802688580006361
2023-01-21 13:14:10.003203: step: 1572/530, loss: 0.00025815964909270406
2023-01-21 13:14:11.190835: step: 1576/530, loss: 0.0014194488758221269
2023-01-21 13:14:12.343588: step: 1580/530, loss: -1.258850079466356e-05
2023-01-21 13:14:13.504664: step: 1584/530, loss: 0.0004368782101664692
2023-01-21 13:14:14.698467: step: 1588/530, loss: 0.039253998547792435
2023-01-21 13:14:15.851062: step: 1592/530, loss: 0.00030221938504837453
2023-01-21 13:14:17.061145: step: 1596/530, loss: 0.0011402129894122481
2023-01-21 13:14:18.234745: step: 1600/530, loss: 3.4999848139705136e-05
2023-01-21 13:14:19.388687: step: 1604/530, loss: 8.58306884765625e-06
2023-01-21 13:14:20.591099: step: 1608/530, loss: 0.007841110229492188
2023-01-21 13:14:21.776425: step: 1612/530, loss: 0.0008140564314089715
2023-01-21 13:14:22.945778: step: 1616/530, loss: 0.0003173828008584678
2023-01-21 13:14:24.125408: step: 1620/530, loss: 0.00022583008103538305
2023-01-21 13:14:25.356180: step: 1624/530, loss: 0.0006501197931356728
2023-01-21 13:14:26.547021: step: 1628/530, loss: 0.017969703301787376
2023-01-21 13:14:27.751874: step: 1632/530, loss: 0.0007604599231854081
2023-01-21 13:14:28.907337: step: 1636/530, loss: 3.347396705066785e-05
2023-01-21 13:14:30.114301: step: 1640/530, loss: 0.09605789929628372
2023-01-21 13:14:31.281947: step: 1644/530, loss: 6.8664553509734105e-06
2023-01-21 13:14:32.470491: step: 1648/530, loss: 0.008725167252123356
2023-01-21 13:14:33.663201: step: 1652/530, loss: 3.280639793956652e-05
2023-01-21 13:14:34.798154: step: 1656/530, loss: 0.0008182525634765625
2023-01-21 13:14:35.971417: step: 1660/530, loss: 0.0010366917122155428
2023-01-21 13:14:37.179074: step: 1664/530, loss: 0.00048828125
2023-01-21 13:14:38.392250: step: 1668/530, loss: 0.0008810996660031378
2023-01-21 13:14:39.578279: step: 1672/530, loss: 1.716613724056515e-06
2023-01-21 13:14:40.769481: step: 1676/530, loss: 0.0028417587745934725
2023-01-21 13:14:41.933764: step: 1680/530, loss: 0.032867431640625
2023-01-21 13:14:43.114476: step: 1684/530, loss: 0.00012092589895473793
2023-01-21 13:14:44.290417: step: 1688/530, loss: 0.0030490877106785774
2023-01-21 13:14:45.453868: step: 1692/530, loss: -6.389617738022935e-06
2023-01-21 13:14:46.630621: step: 1696/530, loss: -8.01086389401462e-06
2023-01-21 13:14:47.875011: step: 1700/530, loss: 0.005925178527832031
2023-01-21 13:14:49.061385: step: 1704/530, loss: 0.02528972551226616
2023-01-21 13:14:50.278036: step: 1708/530, loss: 0.01662302017211914
2023-01-21 13:14:51.440269: step: 1712/530, loss: 0.005824279971420765
2023-01-21 13:14:52.641578: step: 1716/530, loss: 0.002816915512084961
2023-01-21 13:14:53.830514: step: 1720/530, loss: 0.0006657720077782869
2023-01-21 13:14:55.029826: step: 1724/530, loss: 0.0036499022971838713
2023-01-21 13:14:56.212462: step: 1728/530, loss: 2.1457672119140625e-05
2023-01-21 13:14:57.427415: step: 1732/530, loss: 9.32693510549143e-05
2023-01-21 13:14:58.677957: step: 1736/530, loss: 0.021967792883515358
2023-01-21 13:14:59.864760: step: 1740/530, loss: 0.016535663977265358
2023-01-21 13:15:01.064824: step: 1744/530, loss: 0.02796478383243084
2023-01-21 13:15:02.262493: step: 1748/530, loss: 1.2063980648235884e-05
2023-01-21 13:15:03.476192: step: 1752/530, loss: 0.01540374755859375
2023-01-21 13:15:04.675233: step: 1756/530, loss: 5.168914867681451e-05
2023-01-21 13:15:05.856082: step: 1760/530, loss: 0.004541588015854359
2023-01-21 13:15:07.007034: step: 1764/530, loss: 6.906985800014809e-05
2023-01-21 13:15:08.223045: step: 1768/530, loss: 0.018044328317046165
2023-01-21 13:15:09.449393: step: 1772/530, loss: 2.8610230629055877e-07
2023-01-21 13:15:10.650135: step: 1776/530, loss: 0.0005989075289107859
2023-01-21 13:15:11.834340: step: 1780/530, loss: 1.983642505365424e-05
2023-01-21 13:15:13.123814: step: 1784/530, loss: 0.002282810164615512
2023-01-21 13:15:14.299719: step: 1788/530, loss: 5.626678466796875e-05
2023-01-21 13:15:15.453648: step: 1792/530, loss: 0.0004341125604696572
2023-01-21 13:15:16.665853: step: 1796/530, loss: 0.0007532119634561241
2023-01-21 13:15:17.913171: step: 1800/530, loss: 0.07870350033044815
2023-01-21 13:15:19.095757: step: 1804/530, loss: 0.0013563156826421618
2023-01-21 13:15:20.255393: step: 1808/530, loss: 0.00024003982252907008
2023-01-21 13:15:21.469518: step: 1812/530, loss: 4.968643406755291e-05
2023-01-21 13:15:22.612958: step: 1816/530, loss: 0.0013772487873211503
2023-01-21 13:15:23.753188: step: 1820/530, loss: 0.00015192032151389867
2023-01-21 13:15:24.919510: step: 1824/530, loss: 0.03337249904870987
2023-01-21 13:15:26.116589: step: 1828/530, loss: 5.2261355449445546e-05
2023-01-21 13:15:27.308221: step: 1832/530, loss: 0.0005826950073242188
2023-01-21 13:15:28.531367: step: 1836/530, loss: 0.01380131859332323
2023-01-21 13:15:29.710402: step: 1840/530, loss: 0.00044078828068450093
2023-01-21 13:15:30.908371: step: 1844/530, loss: 0.0010494232410565019
2023-01-21 13:15:32.100552: step: 1848/530, loss: 0.0054892064072191715
2023-01-21 13:15:33.239082: step: 1852/530, loss: 5.14984130859375e-05
2023-01-21 13:15:34.409722: step: 1856/530, loss: 0.00040121079655364156
2023-01-21 13:15:35.548707: step: 1860/530, loss: 0.0018254281021654606
2023-01-21 13:15:36.709742: step: 1864/530, loss: 0.1102914810180664
2023-01-21 13:15:37.924785: step: 1868/530, loss: 0.0018491744995117188
2023-01-21 13:15:39.090935: step: 1872/530, loss: 0.06604178249835968
2023-01-21 13:15:40.258613: step: 1876/530, loss: 0.0002149581996491179
2023-01-21 13:15:41.407727: step: 1880/530, loss: 2.5272369384765625e-05
2023-01-21 13:15:42.589955: step: 1884/530, loss: 0.010656642727553844
2023-01-21 13:15:43.734057: step: 1888/530, loss: 2.708435022213962e-05
2023-01-21 13:15:44.887905: step: 1892/530, loss: 0.0021576881408691406
2023-01-21 13:15:46.071191: step: 1896/530, loss: 0.0027456283569335938
2023-01-21 13:15:47.242956: step: 1900/530, loss: 0.0024428367614746094
2023-01-21 13:15:48.377355: step: 1904/530, loss: 9.72747784544481e-06
2023-01-21 13:15:49.596407: step: 1908/530, loss: 0.000358390825567767
2023-01-21 13:15:50.840106: step: 1912/530, loss: 0.0005353927845135331
2023-01-21 13:15:52.005493: step: 1916/530, loss: 0.08630505204200745
2023-01-21 13:15:53.179684: step: 1920/530, loss: 0.00055017473641783
2023-01-21 13:15:54.386286: step: 1924/530, loss: 0.0001198768659378402
2023-01-21 13:15:55.582413: step: 1928/530, loss: 0.0011196136474609375
2023-01-21 13:15:56.745375: step: 1932/530, loss: 0.01929626613855362
2023-01-21 13:15:57.966075: step: 1936/530, loss: 0.00058999058092013
2023-01-21 13:15:59.125172: step: 1940/530, loss: 0.0008335113525390625
2023-01-21 13:16:00.275651: step: 1944/530, loss: 0.00021028520131949335
2023-01-21 13:16:01.505766: step: 1948/530, loss: 0.013557148166000843
2023-01-21 13:16:02.711230: step: 1952/530, loss: 0.009141159243881702
2023-01-21 13:16:03.913886: step: 1956/530, loss: 0.001148223876953125
2023-01-21 13:16:05.104743: step: 1960/530, loss: 0.17177735269069672
2023-01-21 13:16:06.292552: step: 1964/530, loss: 0.005257606506347656
2023-01-21 13:16:07.466831: step: 1968/530, loss: 0.018319321796298027
2023-01-21 13:16:08.742382: step: 1972/530, loss: 0.0002735138114076108
2023-01-21 13:16:09.958169: step: 1976/530, loss: 0.009503745473921299
2023-01-21 13:16:11.099952: step: 1980/530, loss: 0.0019828795921057463
2023-01-21 13:16:12.318047: step: 1984/530, loss: 0.0013078689808025956
2023-01-21 13:16:13.491484: step: 1988/530, loss: 0.011764240451157093
2023-01-21 13:16:14.696657: step: 1992/530, loss: 2.9230119253043085e-05
2023-01-21 13:16:15.871591: step: 1996/530, loss: 4.825591895496473e-05
2023-01-21 13:16:17.067359: step: 2000/530, loss: 0.004332542419433594
2023-01-21 13:16:18.232727: step: 2004/530, loss: 0.006155204493552446
2023-01-21 13:16:19.385107: step: 2008/530, loss: 0.00040073395939543843
2023-01-21 13:16:20.583452: step: 2012/530, loss: 4.38690185546875e-05
2023-01-21 13:16:21.739801: step: 2016/530, loss: 0.00033674240694381297
2023-01-21 13:16:22.905172: step: 2020/530, loss: 0.0028434754349291325
2023-01-21 13:16:24.077776: step: 2024/530, loss: 0.0004271507204975933
2023-01-21 13:16:25.262324: step: 2028/530, loss: 0.005650329403579235
2023-01-21 13:16:26.387310: step: 2032/530, loss: 0.004430484492331743
2023-01-21 13:16:27.542672: step: 2036/530, loss: 0.00422325124964118
2023-01-21 13:16:28.717687: step: 2040/530, loss: 0.059149935841560364
2023-01-21 13:16:29.866003: step: 2044/530, loss: 0.0010932922596111894
2023-01-21 13:16:31.047098: step: 2048/530, loss: 0.031925298273563385
2023-01-21 13:16:32.262249: step: 2052/530, loss: 0.00017223358736373484
2023-01-21 13:16:33.423406: step: 2056/530, loss: 0.007066082675009966
2023-01-21 13:16:34.621646: step: 2060/530, loss: 0.00026264190091751516
2023-01-21 13:16:35.795909: step: 2064/530, loss: 0.5322442650794983
2023-01-21 13:16:36.986202: step: 2068/530, loss: 0.0003354072687216103
2023-01-21 13:16:38.182857: step: 2072/530, loss: 0.0006837844848632812
2023-01-21 13:16:39.345359: step: 2076/530, loss: 9.059906005859375e-06
2023-01-21 13:16:40.491338: step: 2080/530, loss: 1.6689300537109375e-06
2023-01-21 13:16:41.667115: step: 2084/530, loss: 0.02824115753173828
2023-01-21 13:16:42.852033: step: 2088/530, loss: 0.016320228576660156
2023-01-21 13:16:44.054738: step: 2092/530, loss: 0.00010118485079146922
2023-01-21 13:16:45.234816: step: 2096/530, loss: 1.106262243411038e-05
2023-01-21 13:16:46.414615: step: 2100/530, loss: 0.004332924261689186
2023-01-21 13:16:47.621822: step: 2104/530, loss: 0.0001888275146484375
2023-01-21 13:16:48.781024: step: 2108/530, loss: 0.005513286683708429
2023-01-21 13:16:49.934815: step: 2112/530, loss: 8.726119995117188e-05
2023-01-21 13:16:51.103383: step: 2116/530, loss: -2.8610230629055877e-07
2023-01-21 13:16:52.235064: step: 2120/530, loss: 0.0013326645130291581
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5603864734299517, 'r': 0.7723035952063915, 'f1': 0.6494960806270997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6428893905191874, 'r': 0.8188614146060954, 'f1': 0.7202832574607991}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.5319148936170213, 'r': 0.9259259259259259, 'f1': 0.6756756756756757}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6181818181818182, 'r': 0.5396825396825397, 'f1': 0.576271186440678}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
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': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 13:17:36.064845: step: 4/530, loss: 0.0007568359724245965
2023-01-21 13:17:37.230844: step: 8/530, loss: 0.000789642333984375
2023-01-21 13:17:38.438301: step: 12/530, loss: 0.007081222720444202
2023-01-21 13:17:39.619097: step: 16/530, loss: 0.02008648030459881
2023-01-21 13:17:40.791474: step: 20/530, loss: 1.5640260244254023e-05
2023-01-21 13:17:41.984960: step: 24/530, loss: 0.0005744934314861894
2023-01-21 13:17:43.155026: step: 28/530, loss: 0.00030517578125
2023-01-21 13:17:44.347313: step: 32/530, loss: 0.0013067246181890368
2023-01-21 13:17:45.497045: step: 36/530, loss: 2.8514861696748994e-05
2023-01-21 13:17:46.629106: step: 40/530, loss: 0.013948059640824795
2023-01-21 13:17:47.871998: step: 44/530, loss: 0.0015874862438067794
2023-01-21 13:17:48.988761: step: 48/530, loss: 9.384155418956652e-05
2023-01-21 13:17:50.183534: step: 52/530, loss: 0.004475307650864124
2023-01-21 13:17:51.351990: step: 56/530, loss: 0.005197715945541859
2023-01-21 13:17:52.534094: step: 60/530, loss: 0.0002473831409588456
2023-01-21 13:17:53.698362: step: 64/530, loss: 0.017169570550322533
2023-01-21 13:17:54.865611: step: 68/530, loss: 0.0059562684036791325
2023-01-21 13:17:56.025384: step: 72/530, loss: 1.9168854123563506e-05
2023-01-21 13:17:57.207754: step: 76/530, loss: 0.03314227983355522
2023-01-21 13:17:58.381411: step: 80/530, loss: 0.003228855086490512
2023-01-21 13:17:59.606557: step: 84/530, loss: 0.014593602158129215
2023-01-21 13:18:00.771270: step: 88/530, loss: 0.0008642196771688759
2023-01-21 13:18:01.941977: step: 92/530, loss: 0.028277970850467682
2023-01-21 13:18:03.108580: step: 96/530, loss: 0.013110924512147903
2023-01-21 13:18:04.300942: step: 100/530, loss: -7.629394076502649e-06
2023-01-21 13:18:05.530109: step: 104/530, loss: -2.47955313170678e-06
2023-01-21 13:18:06.725592: step: 108/530, loss: 0.00126142508815974
2023-01-21 13:18:07.866166: step: 112/530, loss: 1.5258792700478807e-06
2023-01-21 13:18:09.045171: step: 116/530, loss: 0.0017021179664880037
2023-01-21 13:18:10.173797: step: 120/530, loss: 0.001508426619693637
2023-01-21 13:18:11.352768: step: 124/530, loss: 0.002375364303588867
2023-01-21 13:18:12.541417: step: 128/530, loss: 0.0025171281304210424
2023-01-21 13:18:13.719613: step: 132/530, loss: 0.0010322571033611894
2023-01-21 13:18:14.870118: step: 136/530, loss: 0.007959938608109951
2023-01-21 13:18:16.017046: step: 140/530, loss: 0.003632068634033203
2023-01-21 13:18:17.183427: step: 144/530, loss: 0.16893978416919708
2023-01-21 13:18:18.380062: step: 148/530, loss: 0.003363037249073386
2023-01-21 13:18:19.563241: step: 152/530, loss: 0.0062608723528683186
2023-01-21 13:18:20.717960: step: 156/530, loss: 0.012283516116440296
2023-01-21 13:18:21.883506: step: 160/530, loss: -4.911422365694307e-06
2023-01-21 13:18:23.069734: step: 164/530, loss: 0.024712370708584785
2023-01-21 13:18:24.272966: step: 168/530, loss: 0.00021839141845703125
2023-01-21 13:18:25.461699: step: 172/530, loss: 0.02800884284079075
2023-01-21 13:18:26.603782: step: 176/530, loss: 0.0009626864921301603
2023-01-21 13:18:27.804026: step: 180/530, loss: 0.0008506655576638877
2023-01-21 13:18:28.973548: step: 184/530, loss: 0.0005820274236612022
2023-01-21 13:18:30.139274: step: 188/530, loss: 0.02467288449406624
2023-01-21 13:18:31.290322: step: 192/530, loss: 5.855560448253527e-05
2023-01-21 13:18:32.448329: step: 196/530, loss: 0.0018627167446538806
2023-01-21 13:18:33.638167: step: 200/530, loss: 0.0003234863397665322
2023-01-21 13:18:34.879569: step: 204/530, loss: 0.03568696975708008
2023-01-21 13:18:36.116210: step: 208/530, loss: 0.009022235870361328
2023-01-21 13:18:37.282740: step: 212/530, loss: 0.00020465851412154734
2023-01-21 13:18:38.416011: step: 216/530, loss: 0.0031142234802246094
2023-01-21 13:18:39.561104: step: 220/530, loss: 0.00057306292001158
2023-01-21 13:18:40.758600: step: 224/530, loss: 1.659393274167087e-05
2023-01-21 13:18:41.957556: step: 228/530, loss: 0.00822978001087904
2023-01-21 13:18:43.111284: step: 232/530, loss: 0.06761913001537323
2023-01-21 13:18:44.317279: step: 236/530, loss: 0.00013666153245139867
2023-01-21 13:18:45.441262: step: 240/530, loss: 0.00016946792311500758
2023-01-21 13:18:46.632449: step: 244/530, loss: 0.0008533478248864412
2023-01-21 13:18:47.800576: step: 248/530, loss: 0.005192756652832031
2023-01-21 13:18:48.977219: step: 252/530, loss: 0.00134449009783566
2023-01-21 13:18:50.155687: step: 256/530, loss: 0.003793763928115368
2023-01-21 13:18:51.326184: step: 260/530, loss: 1.640319896978326e-05
2023-01-21 13:18:52.482965: step: 264/530, loss: 7.972717139637098e-05
2023-01-21 13:18:53.650841: step: 268/530, loss: 0.011298180557787418
2023-01-21 13:18:54.793120: step: 272/530, loss: 8.64267349243164e-05
2023-01-21 13:18:55.944474: step: 276/530, loss: 0.0003021717129740864
2023-01-21 13:18:57.066230: step: 280/530, loss: 0.003907394595444202
2023-01-21 13:18:58.270615: step: 284/530, loss: 0.000901556049939245
2023-01-21 13:18:59.386002: step: 288/530, loss: 0.000935459160245955
2023-01-21 13:19:00.569726: step: 292/530, loss: 0.006976318545639515
2023-01-21 13:19:01.758673: step: 296/530, loss: 0.002673340030014515
2023-01-21 13:19:02.924182: step: 300/530, loss: 0.0051259989850223064
2023-01-21 13:19:04.100563: step: 304/530, loss: 4.4441225327318534e-05
2023-01-21 13:19:05.261362: step: 308/530, loss: 3.070831371587701e-05
2023-01-21 13:19:06.450340: step: 312/530, loss: 0.042662426829338074
2023-01-21 13:19:07.675038: step: 316/530, loss: 3.61442580469884e-05
2023-01-21 13:19:08.825987: step: 320/530, loss: 2.0122528439969756e-05
2023-01-21 13:19:10.023674: step: 324/530, loss: 0.0007370948442257941
2023-01-21 13:19:11.205570: step: 328/530, loss: 0.003315162844955921
2023-01-21 13:19:12.379079: step: 332/530, loss: 0.2565120458602905
2023-01-21 13:19:13.592829: step: 336/530, loss: 0.00016322211013175547
2023-01-21 13:19:14.760230: step: 340/530, loss: 0.0003981590270996094
2023-01-21 13:19:15.943425: step: 344/530, loss: 4.043579247081652e-05
2023-01-21 13:19:17.102582: step: 348/530, loss: 0.012861061841249466
2023-01-21 13:19:18.310487: step: 352/530, loss: 0.021822737529873848
2023-01-21 13:19:19.529476: step: 356/530, loss: 0.004702186677604914
2023-01-21 13:19:20.685999: step: 360/530, loss: 8.621215965831652e-05
2023-01-21 13:19:21.917052: step: 364/530, loss: 0.0001369476376567036
2023-01-21 13:19:23.077521: step: 368/530, loss: 8.77380352903856e-06
2023-01-21 13:19:24.255845: step: 372/530, loss: 0.0008996963733807206
2023-01-21 13:19:25.429706: step: 376/530, loss: 0.000244590628426522
2023-01-21 13:19:26.569791: step: 380/530, loss: 0.0032007216941565275
2023-01-21 13:19:27.766888: step: 384/530, loss: 0.000171661376953125
2023-01-21 13:19:28.949960: step: 388/530, loss: 0.0002132415829692036
2023-01-21 13:19:30.149214: step: 392/530, loss: 6.999969627941027e-05
2023-01-21 13:19:31.317284: step: 396/530, loss: 7.343292054429185e-06
2023-01-21 13:19:32.489130: step: 400/530, loss: 0.02237539365887642
2023-01-21 13:19:33.666347: step: 404/530, loss: 0.025648878887295723
2023-01-21 13:19:34.889325: step: 408/530, loss: 0.09307050704956055
2023-01-21 13:19:36.070959: step: 412/530, loss: 0.016724204644560814
2023-01-21 13:19:37.237048: step: 416/530, loss: 0.00046606065006926656
2023-01-21 13:19:38.371801: step: 420/530, loss: 0.002266311552375555
2023-01-21 13:19:39.531957: step: 424/530, loss: 0.0010375023121014237
2023-01-21 13:19:40.733353: step: 428/530, loss: 0.0015836716629564762
2023-01-21 13:19:41.898171: step: 432/530, loss: 0.001078271889127791
2023-01-21 13:19:43.074271: step: 436/530, loss: 0.0008712768321856856
2023-01-21 13:19:44.244129: step: 440/530, loss: 1.3732910701946821e-05
2023-01-21 13:19:45.413476: step: 444/530, loss: 7.24792471373803e-06
2023-01-21 13:19:46.597076: step: 448/530, loss: 0.012126159854233265
2023-01-21 13:19:47.788789: step: 452/530, loss: 0.007420015055686235
2023-01-21 13:19:48.997256: step: 456/530, loss: 0.004495430272072554
2023-01-21 13:19:50.187028: step: 460/530, loss: 0.0011464118724688888
2023-01-21 13:19:51.353961: step: 464/530, loss: 0.039704132825136185
2023-01-21 13:19:52.524100: step: 468/530, loss: 0.001136398408561945
2023-01-21 13:19:53.689486: step: 472/530, loss: 0.00037107468233443797
2023-01-21 13:19:54.895062: step: 476/530, loss: 0.33526134490966797
2023-01-21 13:19:56.044021: step: 480/530, loss: 0.0004972458118572831
2023-01-21 13:19:57.235501: step: 484/530, loss: -1.52587890625e-05
2023-01-21 13:19:58.395961: step: 488/530, loss: 0.03555698320269585
2023-01-21 13:19:59.539302: step: 492/530, loss: 1.4305115655588452e-05
2023-01-21 13:20:00.744824: step: 496/530, loss: 0.026581954210996628
2023-01-21 13:20:01.918192: step: 500/530, loss: 4.00543194700731e-06
2023-01-21 13:20:03.092378: step: 504/530, loss: 0.03551435470581055
2023-01-21 13:20:04.267076: step: 508/530, loss: 0.032139018177986145
2023-01-21 13:20:05.451888: step: 512/530, loss: 0.00390892056748271
2023-01-21 13:20:06.650583: step: 516/530, loss: 1.71661376953125e-05
2023-01-21 13:20:07.807117: step: 520/530, loss: 0.00043010711669921875
2023-01-21 13:20:08.991313: step: 524/530, loss: 0.04823443293571472
2023-01-21 13:20:10.180849: step: 528/530, loss: 0.00024199485778808594
2023-01-21 13:20:11.313523: step: 532/530, loss: 0.003749799681827426
2023-01-21 13:20:12.496796: step: 536/530, loss: 0.003295517060905695
2023-01-21 13:20:13.667988: step: 540/530, loss: 0.0003692627069540322
2023-01-21 13:20:14.862820: step: 544/530, loss: 2.6607514882925898e-05
2023-01-21 13:20:16.027501: step: 548/530, loss: 8.525848534191027e-05
2023-01-21 13:20:17.261970: step: 552/530, loss: 0.01848583295941353
2023-01-21 13:20:18.451694: step: 556/530, loss: 6.904602196300402e-05
2023-01-21 13:20:19.619448: step: 560/530, loss: 2.288818359375e-05
2023-01-21 13:20:20.827125: step: 564/530, loss: 0.004246520809829235
2023-01-21 13:20:22.024365: step: 568/530, loss: 0.011366653256118298
2023-01-21 13:20:23.176245: step: 572/530, loss: 0.021131135523319244
2023-01-21 13:20:24.374798: step: 576/530, loss: 0.06805382668972015
2023-01-21 13:20:25.583060: step: 580/530, loss: 0.00032863617525435984
2023-01-21 13:20:26.758500: step: 584/530, loss: 0.01811981201171875
2023-01-21 13:20:27.927187: step: 588/530, loss: 6.68525681248866e-05
2023-01-21 13:20:29.088825: step: 592/530, loss: 9.32693510549143e-05
2023-01-21 13:20:30.254750: step: 596/530, loss: 0.00023641585721634328
2023-01-21 13:20:31.393058: step: 600/530, loss: 4.100799742445815e-06
2023-01-21 13:20:32.535492: step: 604/530, loss: 0.0018379210960119963
2023-01-21 13:20:33.676077: step: 608/530, loss: 0.0013702393043786287
2023-01-21 13:20:34.881842: step: 612/530, loss: 0.0008249283418990672
2023-01-21 13:20:36.081723: step: 616/530, loss: 0.000719261122867465
2023-01-21 13:20:37.263245: step: 620/530, loss: 0.000911331211682409
2023-01-21 13:20:38.486569: step: 624/530, loss: 0.04983940348029137
2023-01-21 13:20:39.631155: step: 628/530, loss: 8.96453821042087e-06
2023-01-21 13:20:40.835132: step: 632/530, loss: 0.0003658771456684917
2023-01-21 13:20:42.075923: step: 636/530, loss: 0.0015933990944176912
2023-01-21 13:20:43.304443: step: 640/530, loss: 0.0035876273177564144
2023-01-21 13:20:44.526842: step: 644/530, loss: 0.0003837585391011089
2023-01-21 13:20:45.688945: step: 648/530, loss: 4.959107172908261e-06
2023-01-21 13:20:46.861191: step: 652/530, loss: 0.00549659738317132
2023-01-21 13:20:48.048642: step: 656/530, loss: 0.0005027293809689581
2023-01-21 13:20:49.206026: step: 660/530, loss: 0.0028153895400464535
2023-01-21 13:20:50.409429: step: 664/530, loss: 0.00101137172896415
2023-01-21 13:20:51.585555: step: 668/530, loss: 0.0016317367553710938
2023-01-21 13:20:52.733211: step: 672/530, loss: 0.00011301040649414062
2023-01-21 13:20:53.902734: step: 676/530, loss: 0.0020776749588549137
2023-01-21 13:20:55.062951: step: 680/530, loss: 0.00027637480525299907
2023-01-21 13:20:56.287696: step: 684/530, loss: 1.087188684323337e-05
2023-01-21 13:20:57.457904: step: 688/530, loss: 0.032381821423769
2023-01-21 13:20:58.616559: step: 692/530, loss: 5.53131121705519e-06
2023-01-21 13:20:59.793361: step: 696/530, loss: 0.02615508995950222
2023-01-21 13:21:01.017532: step: 700/530, loss: 0.00012254714965820312
2023-01-21 13:21:02.170476: step: 704/530, loss: 0.04984540864825249
2023-01-21 13:21:03.367173: step: 708/530, loss: 0.0004677772521972656
2023-01-21 13:21:04.546051: step: 712/530, loss: 0.00036115647526457906
2023-01-21 13:21:05.716221: step: 716/530, loss: 0.0002439498930471018
2023-01-21 13:21:06.858173: step: 720/530, loss: 0.0007411956903524697
2023-01-21 13:21:08.031396: step: 724/530, loss: 0.04214467853307724
2023-01-21 13:21:09.198195: step: 728/530, loss: 0.01281723938882351
2023-01-21 13:21:10.337144: step: 732/530, loss: 0.0002998351992573589
2023-01-21 13:21:11.544298: step: 736/530, loss: 5.999803397571668e-05
2023-01-21 13:21:12.713287: step: 740/530, loss: 0.0005027771112509072
2023-01-21 13:21:13.884807: step: 744/530, loss: 0.0597267672419548
2023-01-21 13:21:15.066266: step: 748/530, loss: 2.28881845032447e-06
2023-01-21 13:21:16.243271: step: 752/530, loss: 0.0033818245865404606
2023-01-21 13:21:17.446785: step: 756/530, loss: 0.0004976272466592491
2023-01-21 13:21:18.604427: step: 760/530, loss: 0.0044303894974291325
2023-01-21 13:21:19.778806: step: 764/530, loss: 0.5494731664657593
2023-01-21 13:21:20.952272: step: 768/530, loss: 0.00227012624964118
2023-01-21 13:21:22.121811: step: 772/530, loss: 0.001123714493587613
2023-01-21 13:21:23.297415: step: 776/530, loss: 0.010221481323242188
2023-01-21 13:21:24.515332: step: 780/530, loss: 7.843971616239287e-06
2023-01-21 13:21:25.696442: step: 784/530, loss: 0.005095290951430798
2023-01-21 13:21:26.872845: step: 788/530, loss: 0.026606272906064987
2023-01-21 13:21:28.038204: step: 792/530, loss: 9.870528447208926e-05
2023-01-21 13:21:29.217387: step: 796/530, loss: 0.03448162227869034
2023-01-21 13:21:30.399364: step: 800/530, loss: 8.678435733600054e-06
2023-01-21 13:21:31.570602: step: 804/530, loss: 0.001176905701868236
2023-01-21 13:21:32.719395: step: 808/530, loss: -4.57763690064894e-06
2023-01-21 13:21:33.911248: step: 812/530, loss: 0.00015993117995094508
2023-01-21 13:21:35.093895: step: 816/530, loss: 0.04126386716961861
2023-01-21 13:21:36.292323: step: 820/530, loss: 0.0003602981742005795
2023-01-21 13:21:37.459913: step: 824/530, loss: 0.0006037711864337325
2023-01-21 13:21:38.646446: step: 828/530, loss: 0.003129387041553855
2023-01-21 13:21:39.852434: step: 832/530, loss: 0.04142417758703232
2023-01-21 13:21:41.020229: step: 836/530, loss: 0.003353309817612171
2023-01-21 13:21:42.221395: step: 840/530, loss: 0.022490119561553
2023-01-21 13:21:43.375297: step: 844/530, loss: 0.00012054444232489914
2023-01-21 13:21:44.563941: step: 848/530, loss: 0.0005702018970623612
2023-01-21 13:21:45.749145: step: 852/530, loss: 0.003967476077377796
2023-01-21 13:21:46.985309: step: 856/530, loss: -2.574920654296875e-05
2023-01-21 13:21:48.200875: step: 860/530, loss: 0.6077167391777039
2023-01-21 13:21:49.367006: step: 864/530, loss: -1.602172778802924e-05
2023-01-21 13:21:50.529750: step: 868/530, loss: 3.337860050578456e-07
2023-01-21 13:21:51.686075: step: 872/530, loss: 9.72747784544481e-06
2023-01-21 13:21:52.840925: step: 876/530, loss: 0.0011521339183673263
2023-01-21 13:21:54.041301: step: 880/530, loss: 0.0014534472720697522
2023-01-21 13:21:55.228801: step: 884/530, loss: 0.0003037452697753906
2023-01-21 13:21:56.415414: step: 888/530, loss: 1.811981201171875e-05
2023-01-21 13:21:57.578518: step: 892/530, loss: 0.060346126556396484
2023-01-21 13:21:58.774619: step: 896/530, loss: 0.017130661755800247
2023-01-21 13:21:59.937984: step: 900/530, loss: 0.006789970677345991
2023-01-21 13:22:01.100031: step: 904/530, loss: 0.006602096371352673
2023-01-21 13:22:02.302042: step: 908/530, loss: 0.0019224167335778475
2023-01-21 13:22:03.461015: step: 912/530, loss: 0.002901363419368863
2023-01-21 13:22:04.638510: step: 916/530, loss: 0.0003399848937988281
2023-01-21 13:22:05.870343: step: 920/530, loss: 0.008092307485640049
2023-01-21 13:22:07.028978: step: 924/530, loss: 0.00016107558622024953
2023-01-21 13:22:08.209796: step: 928/530, loss: 0.0010921478969976306
2023-01-21 13:22:09.349125: step: 932/530, loss: 0.006289577577263117
2023-01-21 13:22:10.565339: step: 936/530, loss: 0.011955118738114834
2023-01-21 13:22:11.736983: step: 940/530, loss: 0.02442169189453125
2023-01-21 13:22:12.928442: step: 944/530, loss: 0.00762100238353014
2023-01-21 13:22:14.194835: step: 948/530, loss: 0.0023729323875159025
2023-01-21 13:22:15.368924: step: 952/530, loss: 0.002636528108268976
2023-01-21 13:22:16.563510: step: 956/530, loss: 0.00024480820866301656
2023-01-21 13:22:17.750568: step: 960/530, loss: 5.445480201160535e-05
2023-01-21 13:22:18.898921: step: 964/530, loss: 0.006041908171027899
2023-01-21 13:22:20.074753: step: 968/530, loss: 0.00015468598576262593
2023-01-21 13:22:21.246896: step: 972/530, loss: 0.000392913818359375
2023-01-21 13:22:22.461588: step: 976/530, loss: 0.04430718347430229
2023-01-21 13:22:23.695813: step: 980/530, loss: 0.0004947215784341097
2023-01-21 13:22:24.870725: step: 984/530, loss: 0.0018101693131029606
2023-01-21 13:22:26.053002: step: 988/530, loss: 0.0009911536471918225
2023-01-21 13:22:27.207156: step: 992/530, loss: 0.00022783280292060226
2023-01-21 13:22:28.423059: step: 996/530, loss: 0.0017267226940020919
2023-01-21 13:22:29.647640: step: 1000/530, loss: 0.0005803108215332031
2023-01-21 13:22:30.799701: step: 1004/530, loss: 2.403259350103326e-05
2023-01-21 13:22:32.036498: step: 1008/530, loss: 0.0022466660011559725
2023-01-21 13:22:33.234194: step: 1012/530, loss: 0.0019380568992346525
2023-01-21 13:22:34.403103: step: 1016/530, loss: 0.0002027511509368196
2023-01-21 13:22:35.596362: step: 1020/530, loss: 0.015423774719238281
2023-01-21 13:22:36.752655: step: 1024/530, loss: 1.1825562069134321e-05
2023-01-21 13:22:37.924224: step: 1028/530, loss: 0.005142593290656805
2023-01-21 13:22:39.119600: step: 1032/530, loss: 0.06525135040283203
2023-01-21 13:22:40.307158: step: 1036/530, loss: 0.08869529515504837
2023-01-21 13:22:41.480468: step: 1040/530, loss: 0.008227539248764515
2023-01-21 13:22:42.668919: step: 1044/530, loss: 0.10853490233421326
2023-01-21 13:22:43.896824: step: 1048/530, loss: 0.0004175186331849545
2023-01-21 13:22:45.055322: step: 1052/530, loss: 0.006182861514389515
2023-01-21 13:22:46.199516: step: 1056/530, loss: 0.022937975823879242
2023-01-21 13:22:47.375278: step: 1060/530, loss: 2.689361645025201e-05
2023-01-21 13:22:48.557223: step: 1064/530, loss: 0.00026302336482331157
2023-01-21 13:22:49.743137: step: 1068/530, loss: 2.6798248654813506e-05
2023-01-21 13:22:50.984952: step: 1072/530, loss: 3.814697265625e-05
2023-01-21 13:22:52.111378: step: 1076/530, loss: 1.029968279908644e-05
2023-01-21 13:22:53.285577: step: 1080/530, loss: 0.03255882114171982
2023-01-21 13:22:54.482061: step: 1084/530, loss: 1.6689300537109375e-05
2023-01-21 13:22:55.721725: step: 1088/530, loss: -5.626678557746345e-06
2023-01-21 13:22:56.902282: step: 1092/530, loss: 0.001160097192041576
2023-01-21 13:22:58.085849: step: 1096/530, loss: 0.0005065918085165322
2023-01-21 13:22:59.326950: step: 1100/530, loss: 0.03304634243249893
2023-01-21 13:23:00.541075: step: 1104/530, loss: 0.013874339871108532
2023-01-21 13:23:01.716041: step: 1108/530, loss: 0.0012496948475018144
2023-01-21 13:23:02.925489: step: 1112/530, loss: 0.010713387280702591
2023-01-21 13:23:04.109085: step: 1116/530, loss: 2.2077560061006807e-05
2023-01-21 13:23:05.274699: step: 1120/530, loss: 0.0011201859451830387
2023-01-21 13:23:06.461467: step: 1124/530, loss: 0.0011579514248296618
2023-01-21 13:23:07.589728: step: 1128/530, loss: 9.269714064430445e-05
2023-01-21 13:23:08.763380: step: 1132/530, loss: 0.014981555752456188
2023-01-21 13:23:09.950468: step: 1136/530, loss: 0.012707042507827282
2023-01-21 13:23:11.131795: step: 1140/530, loss: 0.00010375976853538305
2023-01-21 13:23:12.304419: step: 1144/530, loss: 0.004528141114860773
2023-01-21 13:23:13.516553: step: 1148/530, loss: 0.028721999377012253
2023-01-21 13:23:14.675884: step: 1152/530, loss: 6.4849850787140895e-06
2023-01-21 13:23:15.858143: step: 1156/530, loss: 0.00014867782010696828
2023-01-21 13:23:17.050373: step: 1160/530, loss: 0.00014743805513717234
2023-01-21 13:23:18.227423: step: 1164/530, loss: 0.24661773443222046
2023-01-21 13:23:19.442859: step: 1168/530, loss: 0.029487991705536842
2023-01-21 13:23:20.642740: step: 1172/530, loss: 8.296966370835435e-06
2023-01-21 13:23:21.871164: step: 1176/530, loss: 5.5122378398664296e-05
2023-01-21 13:23:23.083568: step: 1180/530, loss: -1.9073513612966053e-07
2023-01-21 13:23:24.281796: step: 1184/530, loss: 5.664825584972277e-05
2023-01-21 13:23:25.458533: step: 1188/530, loss: 3.8719179428881034e-05
2023-01-21 13:23:26.641419: step: 1192/530, loss: 0.005318927578628063
2023-01-21 13:23:27.826342: step: 1196/530, loss: 0.0010579109657555819
2023-01-21 13:23:29.044152: step: 1200/530, loss: 5.0020218623103574e-05
2023-01-21 13:23:30.193296: step: 1204/530, loss: 0.006645965855568647
2023-01-21 13:23:31.400880: step: 1208/530, loss: 0.0002490997430868447
2023-01-21 13:23:32.558457: step: 1212/530, loss: 1.3351441339182202e-06
2023-01-21 13:23:33.761088: step: 1216/530, loss: 0.10840167850255966
2023-01-21 13:23:35.026436: step: 1220/530, loss: 0.009071588516235352
2023-01-21 13:23:36.201900: step: 1224/530, loss: 0.009002208709716797
2023-01-21 13:23:37.362720: step: 1228/530, loss: -1.430511474609375e-06
2023-01-21 13:23:38.517925: step: 1232/530, loss: 1.9550323486328125e-05
2023-01-21 13:23:39.760851: step: 1236/530, loss: 2.86102294921875e-06
2023-01-21 13:23:40.962323: step: 1240/530, loss: 7.734299288131297e-05
2023-01-21 13:23:42.122274: step: 1244/530, loss: 0.017638398334383965
2023-01-21 13:23:43.306926: step: 1248/530, loss: 0.001321983290836215
2023-01-21 13:23:44.507301: step: 1252/530, loss: 0.0007258415571413934
2023-01-21 13:23:45.671575: step: 1256/530, loss: 0.07361221313476562
2023-01-21 13:23:46.813666: step: 1260/530, loss: 0.0014802933437749743
2023-01-21 13:23:48.019801: step: 1264/530, loss: 0.03154754638671875
2023-01-21 13:23:49.187568: step: 1268/530, loss: 2.517700158932712e-05
2023-01-21 13:23:50.364113: step: 1272/530, loss: 0.020094681531190872
2023-01-21 13:23:51.539246: step: 1276/530, loss: 0.015736008062958717
2023-01-21 13:23:52.709116: step: 1280/530, loss: 0.000560760498046875
2023-01-21 13:23:53.915526: step: 1284/530, loss: 0.004497718531638384
2023-01-21 13:23:55.153808: step: 1288/530, loss: 0.03965797647833824
2023-01-21 13:23:56.340897: step: 1292/530, loss: 0.00014240741438698024
2023-01-21 13:23:57.505394: step: 1296/530, loss: 0.0038696289993822575
2023-01-21 13:23:58.651021: step: 1300/530, loss: -5.722046125811175e-07
2023-01-21 13:23:59.838023: step: 1304/530, loss: 0.02644939348101616
2023-01-21 13:24:01.036175: step: 1308/530, loss: 0.0005460738902911544
2023-01-21 13:24:02.184933: step: 1312/530, loss: 0.005497550591826439
2023-01-21 13:24:03.373965: step: 1316/530, loss: 0.00822525005787611
2023-01-21 13:24:04.550960: step: 1320/530, loss: 0.0001352310209767893
2023-01-21 13:24:05.712230: step: 1324/530, loss: 0.00020141602726653218
2023-01-21 13:24:06.862177: step: 1328/530, loss: 0.0007658004178665578
2023-01-21 13:24:08.031645: step: 1332/530, loss: 0.0002704620419535786
2023-01-21 13:24:09.189488: step: 1336/530, loss: 0.02989816665649414
2023-01-21 13:24:10.400347: step: 1340/530, loss: 0.00987462978810072
2023-01-21 13:24:11.570411: step: 1344/530, loss: 7.629394076502649e-07
2023-01-21 13:24:12.731654: step: 1348/530, loss: 4.062652442371473e-05
2023-01-21 13:24:13.885895: step: 1352/530, loss: 0.030718136578798294
2023-01-21 13:24:15.029862: step: 1356/530, loss: 0.005306530278176069
2023-01-21 13:24:16.202846: step: 1360/530, loss: 4.95910626341356e-06
2023-01-21 13:24:17.403033: step: 1364/530, loss: 0.00403175363317132
2023-01-21 13:24:18.611794: step: 1368/530, loss: 0.03531799092888832
2023-01-21 13:24:19.772626: step: 1372/530, loss: 0.18708762526512146
2023-01-21 13:24:20.931842: step: 1376/530, loss: 1.0871887752728071e-05
2023-01-21 13:24:22.118252: step: 1380/530, loss: 0.005984306335449219
2023-01-21 13:24:23.322581: step: 1384/530, loss: 0.04849529266357422
2023-01-21 13:24:24.557021: step: 1388/530, loss: -1.2016295841021929e-05
2023-01-21 13:24:25.728699: step: 1392/530, loss: 0.012498856522142887
2023-01-21 13:24:26.974221: step: 1396/530, loss: 0.02756214141845703
2023-01-21 13:24:28.153232: step: 1400/530, loss: 0.002640151884406805
2023-01-21 13:24:29.345548: step: 1404/530, loss: 0.0022094727028161287
2023-01-21 13:24:30.479369: step: 1408/530, loss: 0.0017432213062420487
2023-01-21 13:24:31.630911: step: 1412/530, loss: 2.4795533590804553e-06
2023-01-21 13:24:32.772767: step: 1416/530, loss: 0.0006325722206383944
2023-01-21 13:24:33.989638: step: 1420/530, loss: 0.006892586126923561
2023-01-21 13:24:35.160984: step: 1424/530, loss: 1.5926361811580136e-05
2023-01-21 13:24:36.309298: step: 1428/530, loss: 2.2983551389188506e-05
2023-01-21 13:24:37.505997: step: 1432/530, loss: 9.303689148509875e-05
2023-01-21 13:24:38.685046: step: 1436/530, loss: 0.005741882603615522
2023-01-21 13:24:39.860994: step: 1440/530, loss: 0.6808220148086548
2023-01-21 13:24:41.019834: step: 1444/530, loss: 1.964569128176663e-05
2023-01-21 13:24:42.184864: step: 1448/530, loss: 2.5177003408316523e-05
2023-01-21 13:24:43.365485: step: 1452/530, loss: 0.008117723278701305
2023-01-21 13:24:44.516110: step: 1456/530, loss: -2.47955313170678e-06
2023-01-21 13:24:45.701076: step: 1460/530, loss: 0.007694053463637829
2023-01-21 13:24:46.849798: step: 1464/530, loss: 7.953643944347277e-05
2023-01-21 13:24:48.069316: step: 1468/530, loss: 0.0006851673242636025
2023-01-21 13:24:49.241359: step: 1472/530, loss: 0.27452126145362854
2023-01-21 13:24:50.384007: step: 1476/530, loss: 0.0002521514834370464
2023-01-21 13:24:51.537296: step: 1480/530, loss: 0.0004478454648051411
2023-01-21 13:24:52.705536: step: 1484/530, loss: 6.380080594681203e-05
2023-01-21 13:24:53.868004: step: 1488/530, loss: 1.3208389646024443e-05
2023-01-21 13:24:55.084021: step: 1492/530, loss: 0.008752251043915749
2023-01-21 13:24:56.281913: step: 1496/530, loss: 4.7290326619986445e-05
2023-01-21 13:24:57.473352: step: 1500/530, loss: 0.00012643336958717555
2023-01-21 13:24:58.670240: step: 1504/530, loss: 0.06284723430871964
2023-01-21 13:24:59.860142: step: 1508/530, loss: 0.009980965405702591
2023-01-21 13:25:01.052098: step: 1512/530, loss: 0.00010881424532271922
2023-01-21 13:25:02.219155: step: 1516/530, loss: 0.00030765534029342234
2023-01-21 13:25:03.433894: step: 1520/530, loss: 9.441375732421875e-05
2023-01-21 13:25:04.666153: step: 1524/530, loss: 0.0007264137384481728
2023-01-21 13:25:05.820914: step: 1528/530, loss: 2.403259350103326e-05
2023-01-21 13:25:07.074294: step: 1532/530, loss: 0.0004508972051553428
2023-01-21 13:25:08.282962: step: 1536/530, loss: 0.00015439986600540578
2023-01-21 13:25:09.523467: step: 1540/530, loss: 0.26156723499298096
2023-01-21 13:25:10.709565: step: 1544/530, loss: 0.008775139227509499
2023-01-21 13:25:11.867326: step: 1548/530, loss: 5.9604644775390625e-05
2023-01-21 13:25:13.017499: step: 1552/530, loss: 0.0002475738583598286
2023-01-21 13:25:14.154437: step: 1556/530, loss: -7.24792471373803e-06
2023-01-21 13:25:15.322736: step: 1560/530, loss: 0.0008518219110555947
2023-01-21 13:25:16.488848: step: 1564/530, loss: 0.0015647888649255037
2023-01-21 13:25:17.699096: step: 1568/530, loss: 0.01835193671286106
2023-01-21 13:25:18.843206: step: 1572/530, loss: 0.0004593849298544228
2023-01-21 13:25:20.026928: step: 1576/530, loss: 0.013573646545410156
2023-01-21 13:25:21.192381: step: 1580/530, loss: 0.03272509574890137
2023-01-21 13:25:22.367815: step: 1584/530, loss: 3.1089784897631034e-05
2023-01-21 13:25:23.511251: step: 1588/530, loss: 0.017539408057928085
2023-01-21 13:25:24.667195: step: 1592/530, loss: 2.9706954592256807e-05
2023-01-21 13:25:25.845880: step: 1596/530, loss: 0.10423310846090317
2023-01-21 13:25:27.040515: step: 1600/530, loss: 1.068115216185106e-05
2023-01-21 13:25:28.209194: step: 1604/530, loss: 0.00011692046973621473
2023-01-21 13:25:29.376063: step: 1608/530, loss: 0.001994896214455366
2023-01-21 13:25:30.640962: step: 1612/530, loss: 0.010228920727968216
2023-01-21 13:25:31.822732: step: 1616/530, loss: 0.0009129524114541709
2023-01-21 13:25:33.025416: step: 1620/530, loss: 0.00224552140571177
2023-01-21 13:25:34.220432: step: 1624/530, loss: 0.01322717685252428
2023-01-21 13:25:35.430456: step: 1628/530, loss: 0.0002165317564504221
2023-01-21 13:25:36.619898: step: 1632/530, loss: 4.19616708313697e-06
2023-01-21 13:25:37.850636: step: 1636/530, loss: 0.0011947632301598787
2023-01-21 13:25:39.038327: step: 1640/530, loss: 5.187988426769152e-05
2023-01-21 13:25:40.184880: step: 1644/530, loss: 7.04765334376134e-05
2023-01-21 13:25:41.363086: step: 1648/530, loss: 0.015824509784579277
2023-01-21 13:25:42.570338: step: 1652/530, loss: 0.005257987882941961
2023-01-21 13:25:43.810064: step: 1656/530, loss: 0.00292720808647573
2023-01-21 13:25:44.958557: step: 1660/530, loss: 0.0020580291748046875
2023-01-21 13:25:46.131443: step: 1664/530, loss: 6.27517729299143e-05
2023-01-21 13:25:47.313759: step: 1668/530, loss: 4.692077709478326e-05
2023-01-21 13:25:48.435047: step: 1672/530, loss: 0.00011215210543014109
2023-01-21 13:25:49.630613: step: 1676/530, loss: 0.00032701491727493703
2023-01-21 13:25:50.784514: step: 1680/530, loss: 6.151199340820312e-05
2023-01-21 13:25:51.946443: step: 1684/530, loss: 0.0881689041852951
2023-01-21 13:25:53.163688: step: 1688/530, loss: 1.955032530531753e-06
2023-01-21 13:25:54.318802: step: 1692/530, loss: 7.119178189896047e-05
2023-01-21 13:25:55.571556: step: 1696/530, loss: 0.001602554228156805
2023-01-21 13:25:56.745419: step: 1700/530, loss: 9.74655122263357e-05
2023-01-21 13:25:57.956723: step: 1704/530, loss: 2.002716064453125e-05
2023-01-21 13:25:59.122872: step: 1708/530, loss: 4.367828296381049e-05
2023-01-21 13:26:00.283408: step: 1712/530, loss: 0.012990475632250309
2023-01-21 13:26:01.433939: step: 1716/530, loss: 0.011924361810088158
2023-01-21 13:26:02.607429: step: 1720/530, loss: 8.01086389401462e-06
2023-01-21 13:26:03.828008: step: 1724/530, loss: 0.00032167433528229594
2023-01-21 13:26:05.006290: step: 1728/530, loss: 0.0011802673107013106
2023-01-21 13:26:06.186447: step: 1732/530, loss: 0.0004791259707417339
2023-01-21 13:26:07.351407: step: 1736/530, loss: 0.00028867722721770406
2023-01-21 13:26:08.497520: step: 1740/530, loss: 0.008658124133944511
2023-01-21 13:26:09.664380: step: 1744/530, loss: 0.2613298296928406
2023-01-21 13:26:10.834047: step: 1748/530, loss: 0.004587268922477961
2023-01-21 13:26:12.072073: step: 1752/530, loss: 0.0003921508905477822
2023-01-21 13:26:13.295495: step: 1756/530, loss: 0.06064901500940323
2023-01-21 13:26:14.511487: step: 1760/530, loss: 0.002286243485286832
2023-01-21 13:26:15.659531: step: 1764/530, loss: 0.00023480058007407933
2023-01-21 13:26:16.830752: step: 1768/530, loss: 0.010594654828310013
2023-01-21 13:26:17.990375: step: 1772/530, loss: 0.0012146950466558337
2023-01-21 13:26:19.161465: step: 1776/530, loss: 2.393722752458416e-05
2023-01-21 13:26:20.290378: step: 1780/530, loss: 2.880096508306451e-05
2023-01-21 13:26:21.484706: step: 1784/530, loss: 6.10351571594947e-06
2023-01-21 13:26:22.673994: step: 1788/530, loss: 0.0014347076648846269
2023-01-21 13:26:23.816685: step: 1792/530, loss: 0.0022736547980457544
2023-01-21 13:26:24.990190: step: 1796/530, loss: 0.0001733779936330393
2023-01-21 13:26:26.173298: step: 1800/530, loss: 7.05718994140625e-05
2023-01-21 13:26:27.346828: step: 1804/530, loss: 0.00040340423583984375
2023-01-21 13:26:28.497378: step: 1808/530, loss: 4.215240551275201e-05
2023-01-21 13:26:29.659677: step: 1812/530, loss: 0.004420280456542969
2023-01-21 13:26:30.840211: step: 1816/530, loss: 0.00019912720017600805
2023-01-21 13:26:32.047860: step: 1820/530, loss: 0.002767372177913785
2023-01-21 13:26:33.244634: step: 1824/530, loss: 0.0004207611200399697
2023-01-21 13:26:34.447667: step: 1828/530, loss: 1.7833710444392636e-05
2023-01-21 13:26:35.598884: step: 1832/530, loss: 0.0003097057342529297
2023-01-21 13:26:36.781584: step: 1836/530, loss: 5.817413693876006e-06
2023-01-21 13:26:38.004965: step: 1840/530, loss: 3.0994415283203125e-06
2023-01-21 13:26:39.177921: step: 1844/530, loss: 0.020272446796298027
2023-01-21 13:26:40.372423: step: 1848/530, loss: 0.00018959045701194555
2023-01-21 13:26:41.570373: step: 1852/530, loss: -4.100799742445815e-06
2023-01-21 13:26:42.750613: step: 1856/530, loss: 1.5258789289873675e-06
2023-01-21 13:26:43.941989: step: 1860/530, loss: 0.00044155120849609375
2023-01-21 13:26:45.112551: step: 1864/530, loss: 1.4257431757869199e-05
2023-01-21 13:26:46.226265: step: 1868/530, loss: 0.0008022308466024697
2023-01-21 13:26:47.422904: step: 1872/530, loss: 3.61442580469884e-05
2023-01-21 13:26:48.595736: step: 1876/530, loss: 0.0013172150356695056
2023-01-21 13:26:49.780872: step: 1880/530, loss: 0.031190158799290657
2023-01-21 13:26:50.908295: step: 1884/530, loss: -1.9073486328125e-06
2023-01-21 13:26:52.107099: step: 1888/530, loss: 0.012263918295502663
2023-01-21 13:26:53.276144: step: 1892/530, loss: 0.005146598909050226
2023-01-21 13:26:54.475823: step: 1896/530, loss: 0.030160902068018913
2023-01-21 13:26:55.627408: step: 1900/530, loss: 0.019657708704471588
2023-01-21 13:26:56.808485: step: 1904/530, loss: 0.005186653230339289
2023-01-21 13:26:57.983633: step: 1908/530, loss: 0.00033636094303801656
2023-01-21 13:26:59.165338: step: 1912/530, loss: 0.0002037048398051411
2023-01-21 13:27:00.322631: step: 1916/530, loss: 3.814697265625e-05
2023-01-21 13:27:01.510761: step: 1920/530, loss: 0.00023794174194335938
2023-01-21 13:27:02.671490: step: 1924/530, loss: 2.4414064682787284e-05
2023-01-21 13:27:03.911436: step: 1928/530, loss: 0.0017952442867681384
2023-01-21 13:27:05.046413: step: 1932/530, loss: 0.017080020159482956
2023-01-21 13:27:06.214358: step: 1936/530, loss: 0.01831073872745037
2023-01-21 13:27:07.370859: step: 1940/530, loss: 0.03422556072473526
2023-01-21 13:27:08.547556: step: 1944/530, loss: 0.007584571838378906
2023-01-21 13:27:09.697831: step: 1948/530, loss: 5.1212311518611386e-05
2023-01-21 13:27:10.877817: step: 1952/530, loss: 0.00025196076603606343
2023-01-21 13:27:12.080693: step: 1956/530, loss: 3.0326844353112392e-05
2023-01-21 13:27:13.339942: step: 1960/530, loss: 0.013930893503129482
2023-01-21 13:27:14.507508: step: 1964/530, loss: 0.0002763748343568295
2023-01-21 13:27:15.665950: step: 1968/530, loss: 7.152557373046875e-05
2023-01-21 13:27:16.842718: step: 1972/530, loss: 0.0011129379272460938
2023-01-21 13:27:17.993150: step: 1976/530, loss: 0.00010190009925281629
2023-01-21 13:27:19.153458: step: 1980/530, loss: 0.00531616248190403
2023-01-21 13:27:20.326954: step: 1984/530, loss: 6.448030035244301e-05
2023-01-21 13:27:21.491831: step: 1988/530, loss: 0.0011472703190520406
2023-01-21 13:27:22.656580: step: 1992/530, loss: 0.0029087066650390625
2023-01-21 13:27:23.870541: step: 1996/530, loss: 0.013268089853227139
2023-01-21 13:27:25.077324: step: 2000/530, loss: 0.06974449008703232
2023-01-21 13:27:26.216618: step: 2004/530, loss: 0.00023012161545921117
2023-01-21 13:27:27.446357: step: 2008/530, loss: 0.0004161834658589214
2023-01-21 13:27:28.578414: step: 2012/530, loss: 0.04718197509646416
2023-01-21 13:27:29.695285: step: 2016/530, loss: 4.76837158203125e-07
2023-01-21 13:27:30.856328: step: 2020/530, loss: 0.015970278531312943
2023-01-21 13:27:32.017803: step: 2024/530, loss: 0.024612711742520332
2023-01-21 13:27:33.173246: step: 2028/530, loss: 7.891654968261719e-05
2023-01-21 13:27:34.307096: step: 2032/530, loss: 0.00558891287073493
2023-01-21 13:27:35.498703: step: 2036/530, loss: 0.0020313262939453125
2023-01-21 13:27:36.699504: step: 2040/530, loss: 0.013216019608080387
2023-01-21 13:27:37.881086: step: 2044/530, loss: 3.4618376957951114e-05
2023-01-21 13:27:39.034191: step: 2048/530, loss: 5.9556961787166074e-05
2023-01-21 13:27:40.182597: step: 2052/530, loss: 0.00029430389986373484
2023-01-21 13:27:41.345422: step: 2056/530, loss: 3.24249276673072e-06
2023-01-21 13:27:42.522003: step: 2060/530, loss: 0.0004739254654850811
2023-01-21 13:27:43.715871: step: 2064/530, loss: 0.02978820726275444
2023-01-21 13:27:44.876013: step: 2068/530, loss: 0.000949859619140625
2023-01-21 13:27:46.065580: step: 2072/530, loss: 0.16993635892868042
2023-01-21 13:27:47.231295: step: 2076/530, loss: 0.005030251108109951
2023-01-21 13:27:48.417564: step: 2080/530, loss: 0.0006069183582440019
2023-01-21 13:27:49.630722: step: 2084/530, loss: 0.0015707015991210938
2023-01-21 13:27:50.821827: step: 2088/530, loss: 1.52587890625e-05
2023-01-21 13:27:51.973534: step: 2092/530, loss: 7.190704491222277e-05
2023-01-21 13:27:53.185292: step: 2096/530, loss: 0.009448433294892311
2023-01-21 13:27:54.392116: step: 2100/530, loss: 0.02007303200662136
2023-01-21 13:27:55.601497: step: 2104/530, loss: 3.957748776883818e-05
2023-01-21 13:27:56.721966: step: 2108/530, loss: 0.00011758804612327367
2023-01-21 13:27:57.887674: step: 2112/530, loss: 0.0006860733265057206
2023-01-21 13:27:59.049624: step: 2116/530, loss: 3.14712519866589e-06
2023-01-21 13:28:00.199435: step: 2120/530, loss: 0.0009111881372518837
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5703048180924287, 'r': 0.7723035952063915, 'f1': 0.6561085972850678}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6487471526195899, 'r': 0.8188614146060954, 'f1': 0.7239450940518556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
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': 26}
Korean: {'event': {'p': 0.6071428571428571, 'r': 0.5396825396825397, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
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': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 13:28:43.685274: step: 4/530, loss: 0.000652313232421875
2023-01-21 13:28:44.858284: step: 8/530, loss: 0.04241752624511719
2023-01-21 13:28:45.981897: step: 12/530, loss: 0.00018243789963889867
2023-01-21 13:28:47.175987: step: 16/530, loss: 0.0008916854858398438
2023-01-21 13:28:48.328027: step: 20/530, loss: 0.0002452850458212197
2023-01-21 13:28:49.500628: step: 24/530, loss: 0.0049461605958640575
2023-01-21 13:28:50.672425: step: 28/530, loss: 0.007714462466537952
2023-01-21 13:28:51.834792: step: 32/530, loss: 0.0009332657209597528
2023-01-21 13:28:53.011323: step: 36/530, loss: 0.0002077102690236643
2023-01-21 13:28:54.128533: step: 40/530, loss: 7.82012921263231e-06
2023-01-21 13:28:55.306898: step: 44/530, loss: 0.021197892725467682
2023-01-21 13:28:56.481218: step: 48/530, loss: 0.0004343986511230469
2023-01-21 13:28:57.640380: step: 52/530, loss: 0.027161406353116035
2023-01-21 13:28:58.819627: step: 56/530, loss: 2.09808349609375e-05
2023-01-21 13:29:00.015633: step: 60/530, loss: 0.6663224101066589
2023-01-21 13:29:01.188594: step: 64/530, loss: 0.0018278599018231034
2023-01-21 13:29:02.396480: step: 68/530, loss: 0.00020141601271461695
2023-01-21 13:29:03.540430: step: 72/530, loss: 0.0012106895446777344
2023-01-21 13:29:04.733364: step: 76/530, loss: 0.0032207490876317024
2023-01-21 13:29:05.935435: step: 80/530, loss: 0.0019592284224927425
2023-01-21 13:29:07.128308: step: 84/530, loss: 0.3091375529766083
2023-01-21 13:29:08.297841: step: 88/530, loss: 0.0045620440505445
2023-01-21 13:29:09.457858: step: 92/530, loss: 0.001122856279835105
2023-01-21 13:29:10.651843: step: 96/530, loss: 0.000551801931578666
2023-01-21 13:29:11.845428: step: 100/530, loss: 0.00569992046803236
2023-01-21 13:29:12.980744: step: 104/530, loss: 0.003243064973503351
2023-01-21 13:29:14.117164: step: 108/530, loss: 0.0007908821571618319
2023-01-21 13:29:15.292600: step: 112/530, loss: 0.04158763960003853
2023-01-21 13:29:16.484032: step: 116/530, loss: -2.6416777473059483e-05
2023-01-21 13:29:17.642245: step: 120/530, loss: 0.00010452271089889109
2023-01-21 13:29:18.801441: step: 124/530, loss: 0.00032429693965241313
2023-01-21 13:29:19.970009: step: 128/530, loss: 0.005371475592255592
2023-01-21 13:29:21.117677: step: 132/530, loss: 0.0002779960632324219
2023-01-21 13:29:22.270571: step: 136/530, loss: 0.0015871048672124743
2023-01-21 13:29:23.445173: step: 140/530, loss: 0.000629043614026159
2023-01-21 13:29:24.631448: step: 144/530, loss: 0.00011520386033225805
2023-01-21 13:29:25.809157: step: 148/530, loss: 0.0076586720533668995
2023-01-21 13:29:26.993394: step: 152/530, loss: 0.006493282504379749
2023-01-21 13:29:28.179329: step: 156/530, loss: 0.00032024382380768657
2023-01-21 13:29:29.295750: step: 160/530, loss: 0.00016860962205100805
2023-01-21 13:29:30.468779: step: 164/530, loss: 0.0026494027115404606
2023-01-21 13:29:31.632991: step: 168/530, loss: 3.1280520488508046e-05
2023-01-21 13:29:32.794922: step: 172/530, loss: 0.024794865399599075
2023-01-21 13:29:33.988629: step: 176/530, loss: 0.0024705887772142887
2023-01-21 13:29:35.170855: step: 180/530, loss: 0.0002193450927734375
2023-01-21 13:29:36.294456: step: 184/530, loss: 1.2874603271484375e-05
2023-01-21 13:29:37.484422: step: 188/530, loss: 6.608963303733617e-05
2023-01-21 13:29:38.627286: step: 192/530, loss: 0.00037822723970748484
2023-01-21 13:29:39.788189: step: 196/530, loss: -1.1539459592313506e-05
2023-01-21 13:29:41.067171: step: 200/530, loss: 0.06555958092212677
2023-01-21 13:29:42.246674: step: 204/530, loss: 3.4809112548828125e-05
2023-01-21 13:29:43.431735: step: 208/530, loss: 0.022398566827178
2023-01-21 13:29:44.605171: step: 212/530, loss: 7.07626313669607e-05
2023-01-21 13:29:45.780579: step: 216/530, loss: 0.0002288818359375
2023-01-21 13:29:46.983257: step: 220/530, loss: -1.9073486328125e-06
2023-01-21 13:29:48.208019: step: 224/530, loss: 0.00019006729417014867
2023-01-21 13:29:49.411443: step: 228/530, loss: 0.00888590794056654
2023-01-21 13:29:50.601485: step: 232/530, loss: 3.1280520488508046e-05
2023-01-21 13:29:51.770060: step: 236/530, loss: 0.0013383865589275956
2023-01-21 13:29:52.969294: step: 240/530, loss: 0.0020571709610521793
2023-01-21 13:29:54.138195: step: 244/530, loss: 0.0011640548473224044
2023-01-21 13:29:55.305190: step: 248/530, loss: 0.0001386642543366179
2023-01-21 13:29:56.463664: step: 252/530, loss: 0.0011583329178392887
2023-01-21 13:29:57.657186: step: 256/530, loss: 0.005512142553925514
2023-01-21 13:29:58.855202: step: 260/530, loss: 0.00018596649169921875
2023-01-21 13:30:00.077230: step: 264/530, loss: 0.00275421142578125
2023-01-21 13:30:01.241044: step: 268/530, loss: 0.0002172470121877268
2023-01-21 13:30:02.409476: step: 272/530, loss: 3.814697265625e-06
2023-01-21 13:30:03.582489: step: 276/530, loss: 0.05360012128949165
2023-01-21 13:30:04.781065: step: 280/530, loss: 0.0003742217959370464
2023-01-21 13:30:05.947931: step: 284/530, loss: 0.0005376815679483116
2023-01-21 13:30:07.123092: step: 288/530, loss: 0.0009409904014319181
2023-01-21 13:30:08.296877: step: 292/530, loss: 0.1426229476928711
2023-01-21 13:30:09.450822: step: 296/530, loss: 0.00012464524479582906
2023-01-21 13:30:10.595426: step: 300/530, loss: 0.003947449382394552
2023-01-21 13:30:11.825247: step: 304/530, loss: 0.020606566220521927
2023-01-21 13:30:13.034483: step: 308/530, loss: 0.11624108254909515
2023-01-21 13:30:14.217010: step: 312/530, loss: 0.005692481994628906
2023-01-21 13:30:15.373809: step: 316/530, loss: 0.008369731716811657
2023-01-21 13:30:16.572209: step: 320/530, loss: 0.7331158518791199
2023-01-21 13:30:17.782820: step: 324/530, loss: 3.6716462545882678e-06
2023-01-21 13:30:18.999243: step: 328/530, loss: 0.0017117501702159643
2023-01-21 13:30:20.184287: step: 332/530, loss: 4.863739013671875e-05
2023-01-21 13:30:21.343022: step: 336/530, loss: 0.0005509853363037109
2023-01-21 13:30:22.497857: step: 340/530, loss: 4.024505687993951e-05
2023-01-21 13:30:23.642131: step: 344/530, loss: 0.0009725571144372225
2023-01-21 13:30:24.830702: step: 348/530, loss: 0.0049304962158203125
2023-01-21 13:30:26.054823: step: 352/530, loss: 0.01746549643576145
2023-01-21 13:30:27.239054: step: 356/530, loss: 0.00017108916654251516
2023-01-21 13:30:28.445886: step: 360/530, loss: 0.0007452011341229081
2023-01-21 13:30:29.599067: step: 364/530, loss: 0.1918550431728363
2023-01-21 13:30:30.771054: step: 368/530, loss: 0.0003002166631631553
2023-01-21 13:30:31.964016: step: 372/530, loss: 0.0014599800342693925
2023-01-21 13:30:33.129076: step: 376/530, loss: 0.00024375914654228836
2023-01-21 13:30:34.293657: step: 380/530, loss: 0.0032867430709302425
2023-01-21 13:30:35.460260: step: 384/530, loss: 0.00017766952805686742
2023-01-21 13:30:36.664481: step: 388/530, loss: 0.0005496978992596269
2023-01-21 13:30:37.860779: step: 392/530, loss: 0.0015678406925871968
2023-01-21 13:30:39.071041: step: 396/530, loss: 0.0015939712757244706
2023-01-21 13:30:40.267667: step: 400/530, loss: 0.0054035186767578125
2023-01-21 13:30:41.442320: step: 404/530, loss: 0.0004133224720135331
2023-01-21 13:30:42.630170: step: 408/530, loss: 0.0001386642543366179
2023-01-21 13:30:43.808494: step: 412/530, loss: 0.025389863178133965
2023-01-21 13:30:44.970020: step: 416/530, loss: 6.10351571594947e-06
2023-01-21 13:30:46.141779: step: 420/530, loss: 0.0011966705787926912
2023-01-21 13:30:47.301296: step: 424/530, loss: 0.0023927688598632812
2023-01-21 13:30:48.457144: step: 428/530, loss: 0.001926422119140625
2023-01-21 13:30:49.615951: step: 432/530, loss: 0.00010261536226607859
2023-01-21 13:30:50.781641: step: 436/530, loss: 0.02662210538983345
2023-01-21 13:30:51.945368: step: 440/530, loss: 2.6607513063936494e-05
2023-01-21 13:30:53.116668: step: 444/530, loss: 0.00012855531531386077
2023-01-21 13:30:54.294299: step: 448/530, loss: 0.003286266466602683
2023-01-21 13:30:55.491294: step: 452/530, loss: 0.00022544861712958664
2023-01-21 13:30:56.656217: step: 456/530, loss: 0.00159282679669559
2023-01-21 13:30:57.825668: step: 460/530, loss: 0.00022296904353424907
2023-01-21 13:30:59.005013: step: 464/530, loss: 0.0004608154413290322
2023-01-21 13:31:00.202873: step: 468/530, loss: 0.0009136199951171875
2023-01-21 13:31:01.390626: step: 472/530, loss: 0.00028371813823468983
2023-01-21 13:31:02.551547: step: 476/530, loss: 0.00032901763916015625
2023-01-21 13:31:03.745578: step: 480/530, loss: 0.03972644731402397
2023-01-21 13:31:04.928860: step: 484/530, loss: 0.0004926681285724044
2023-01-21 13:31:06.098892: step: 488/530, loss: 0.01566906087100506
2023-01-21 13:31:07.266352: step: 492/530, loss: 3.814697322468419e-07
2023-01-21 13:31:08.441507: step: 496/530, loss: 0.00011901855759788305
2023-01-21 13:31:09.601005: step: 500/530, loss: 2.5367738999193534e-05
2023-01-21 13:31:10.784814: step: 504/530, loss: 0.026016617193818092
2023-01-21 13:31:11.972224: step: 508/530, loss: 1.0871887752728071e-05
2023-01-21 13:31:13.152352: step: 512/530, loss: 0.004142093472182751
2023-01-21 13:31:14.314281: step: 516/530, loss: 0.0015645980602130294
2023-01-21 13:31:15.514099: step: 520/530, loss: 0.005073929205536842
2023-01-21 13:31:16.697384: step: 524/530, loss: 0.00011363029625499621
2023-01-21 13:31:17.846215: step: 528/530, loss: 1.1396407899155747e-05
2023-01-21 13:31:19.060333: step: 532/530, loss: 0.00016498565673828125
2023-01-21 13:31:20.243919: step: 536/530, loss: 0.0005448341253213584
2023-01-21 13:31:21.417949: step: 540/530, loss: 0.0011166572803631425
2023-01-21 13:31:22.579211: step: 544/530, loss: 0.06685008853673935
2023-01-21 13:31:23.777758: step: 548/530, loss: 0.015690326690673828
2023-01-21 13:31:24.974826: step: 552/530, loss: 0.004598522558808327
2023-01-21 13:31:26.159599: step: 556/530, loss: 0.00011863708641612902
2023-01-21 13:31:27.364743: step: 560/530, loss: 0.0001617431698832661
2023-01-21 13:31:28.588473: step: 564/530, loss: 0.011500931344926357
2023-01-21 13:31:29.765790: step: 568/530, loss: 0.012121009640395641
2023-01-21 13:31:30.979455: step: 572/530, loss: 0.0027837753295898438
2023-01-21 13:31:32.197389: step: 576/530, loss: 0.03747894614934921
2023-01-21 13:31:33.392205: step: 580/530, loss: 0.004900932312011719
2023-01-21 13:31:34.563782: step: 584/530, loss: 0.021369457244873047
2023-01-21 13:31:35.742727: step: 588/530, loss: 0.0007748603820800781
2023-01-21 13:31:36.920807: step: 592/530, loss: 8.306503150379285e-05
2023-01-21 13:31:38.190568: step: 596/530, loss: 0.0034616473130881786
2023-01-21 13:31:39.353873: step: 600/530, loss: -1.716613724056515e-06
2023-01-21 13:31:40.499679: step: 604/530, loss: 0.00012016297114314511
2023-01-21 13:31:41.623599: step: 608/530, loss: 0.0003517151053529233
2023-01-21 13:31:42.814449: step: 612/530, loss: 0.0009232521406374872
2023-01-21 13:31:44.032691: step: 616/530, loss: 0.1094297543168068
2023-01-21 13:31:45.203258: step: 620/530, loss: 0.0047598364762961864
2023-01-21 13:31:46.413163: step: 624/530, loss: 0.00019631386385299265
2023-01-21 13:31:47.615235: step: 628/530, loss: 4.6396256948355585e-05
2023-01-21 13:31:48.831827: step: 632/530, loss: 0.0024840356782078743
2023-01-21 13:31:50.018487: step: 636/530, loss: 5.645752025884576e-05
2023-01-21 13:31:51.198612: step: 640/530, loss: 0.005050182808190584
2023-01-21 13:31:52.357133: step: 644/530, loss: 0.03261242061853409
2023-01-21 13:31:53.529722: step: 648/530, loss: 0.007231330499053001
2023-01-21 13:31:54.690754: step: 652/530, loss: 0.013742828741669655
2023-01-21 13:31:55.907700: step: 656/530, loss: -3.814697720372351e-06
2023-01-21 13:31:57.061616: step: 660/530, loss: 0.0019468307727947831
2023-01-21 13:31:58.259841: step: 664/530, loss: 2.956390289909905e-06
2023-01-21 13:31:59.471603: step: 668/530, loss: 3.662109520519152e-05
2023-01-21 13:32:00.607584: step: 672/530, loss: 0.0012308121658861637
2023-01-21 13:32:01.823488: step: 676/530, loss: 0.014968300238251686
2023-01-21 13:32:02.994119: step: 680/530, loss: 0.022825241088867188
2023-01-21 13:32:04.166809: step: 684/530, loss: 5.9700014389818534e-05
2023-01-21 13:32:05.365147: step: 688/530, loss: 2.746581958490424e-05
2023-01-21 13:32:06.515111: step: 692/530, loss: 0.0004076957702636719
2023-01-21 13:32:07.744890: step: 696/530, loss: 5.493163916980848e-05
2023-01-21 13:32:08.927625: step: 700/530, loss: 0.0104224206879735
2023-01-21 13:32:10.119118: step: 704/530, loss: 0.0008493423811160028
2023-01-21 13:32:11.317733: step: 708/530, loss: 0.00011444091796875
2023-01-21 13:32:12.472971: step: 712/530, loss: 9.508132643532008e-05
2023-01-21 13:32:13.659628: step: 716/530, loss: 0.0005712509155273438
2023-01-21 13:32:14.889844: step: 720/530, loss: 0.00039472582284361124
2023-01-21 13:32:16.038519: step: 724/530, loss: 0.0003915310080628842
2023-01-21 13:32:17.178210: step: 728/530, loss: 0.0009037494892254472
2023-01-21 13:32:18.351425: step: 732/530, loss: 0.0009094238630495965
2023-01-21 13:32:19.463297: step: 736/530, loss: 1.7166138377433526e-06
2023-01-21 13:32:20.655547: step: 740/530, loss: 0.0009223938104696572
2023-01-21 13:32:21.846283: step: 744/530, loss: 1.735687328618951e-05
2023-01-21 13:32:23.011127: step: 748/530, loss: 0.0017135620582848787
2023-01-21 13:32:24.166610: step: 752/530, loss: 0.00047740936861373484
2023-01-21 13:32:25.337302: step: 756/530, loss: 0.0002415657218080014
2023-01-21 13:32:26.494234: step: 760/530, loss: 7.314681715797633e-05
2023-01-21 13:32:27.657556: step: 764/530, loss: 6.0653688706224784e-05
2023-01-21 13:32:28.822580: step: 768/530, loss: 6.771087646484375e-05
2023-01-21 13:32:30.002851: step: 772/530, loss: 7.62939453125e-05
2023-01-21 13:32:31.160209: step: 776/530, loss: 0.0002066135493805632
2023-01-21 13:32:32.361350: step: 780/530, loss: 4.291534423828125e-06
2023-01-21 13:32:33.532325: step: 784/530, loss: 0.0063911438919603825
2023-01-21 13:32:34.688315: step: 788/530, loss: 0.009363556280732155
2023-01-21 13:32:35.847132: step: 792/530, loss: 0.00013513564772438258
2023-01-21 13:32:37.026113: step: 796/530, loss: 0.02267284318804741
2023-01-21 13:32:38.191159: step: 800/530, loss: 0.005314063746482134
2023-01-21 13:32:39.336048: step: 804/530, loss: 3.719329833984375e-05
2023-01-21 13:32:40.490881: step: 808/530, loss: 6.12258882028982e-05
2023-01-21 13:32:41.676727: step: 812/530, loss: 7.820128666935489e-05
2023-01-21 13:32:42.891869: step: 816/530, loss: -1.3065337043371983e-05
2023-01-21 13:32:44.069908: step: 820/530, loss: 0.0003643035888671875
2023-01-21 13:32:45.196357: step: 824/530, loss: 2.040863000729587e-05
2023-01-21 13:32:46.399029: step: 828/530, loss: 0.00294666294939816
2023-01-21 13:32:47.567778: step: 832/530, loss: -4.57763690064894e-06
2023-01-21 13:32:48.746852: step: 836/530, loss: 0.00037555693415924907
2023-01-21 13:32:49.921229: step: 840/530, loss: 0.0009501457680016756
2023-01-21 13:32:51.124162: step: 844/530, loss: 0.02007884904742241
2023-01-21 13:32:52.267620: step: 848/530, loss: 0.1260012686252594
2023-01-21 13:32:53.442042: step: 852/530, loss: 2.8514861696748994e-05
2023-01-21 13:32:54.609284: step: 856/530, loss: 0.054146863520145416
2023-01-21 13:32:55.754009: step: 860/530, loss: 8.96453821042087e-06
2023-01-21 13:32:56.920202: step: 864/530, loss: 1.0937668085098267
2023-01-21 13:32:58.069972: step: 868/530, loss: 9.5367431640625e-06
2023-01-21 13:32:59.282506: step: 872/530, loss: 0.020180320367217064
2023-01-21 13:33:00.460345: step: 876/530, loss: 6.008148193359375e-05
2023-01-21 13:33:01.619999: step: 880/530, loss: 2.0980833141948096e-06
2023-01-21 13:33:02.804165: step: 884/530, loss: 0.00044384002103470266
2023-01-21 13:33:03.998521: step: 888/530, loss: 6.27517729299143e-05
2023-01-21 13:33:05.206312: step: 892/530, loss: 0.2867233157157898
2023-01-21 13:33:06.421258: step: 896/530, loss: 0.04669523239135742
2023-01-21 13:33:07.566357: step: 900/530, loss: 0.004283714573830366
2023-01-21 13:33:08.737920: step: 904/530, loss: 2.86102294921875e-06
2023-01-21 13:33:09.885735: step: 908/530, loss: 2.09808349609375e-05
2023-01-21 13:33:11.074333: step: 912/530, loss: 0.0654270127415657
2023-01-21 13:33:12.248726: step: 916/530, loss: 0.0008623883477412164
2023-01-21 13:33:13.377937: step: 920/530, loss: 0.0012042999733239412
2023-01-21 13:33:14.548590: step: 924/530, loss: 2.536773718020413e-05
2023-01-21 13:33:15.766540: step: 928/530, loss: 0.009328269399702549
2023-01-21 13:33:16.916451: step: 932/530, loss: 0.00010900497727561742
2023-01-21 13:33:18.074132: step: 936/530, loss: 0.018418503925204277
2023-01-21 13:33:19.243854: step: 940/530, loss: 0.0004088401619810611
2023-01-21 13:33:20.403606: step: 944/530, loss: 2.19345088225964e-06
2023-01-21 13:33:21.575142: step: 948/530, loss: 0.05818052217364311
2023-01-21 13:33:22.745500: step: 952/530, loss: 0.0006552219274453819
2023-01-21 13:33:23.973021: step: 956/530, loss: 0.022797392681241035
2023-01-21 13:33:25.168015: step: 960/530, loss: 6.809234764659777e-05
2023-01-21 13:33:26.304551: step: 964/530, loss: 0.0003148078976664692
2023-01-21 13:33:27.524543: step: 968/530, loss: 0.005818271543830633
2023-01-21 13:33:28.761408: step: 972/530, loss: 0.0008106231689453125
2023-01-21 13:33:29.962074: step: 976/530, loss: 0.02296772040426731
2023-01-21 13:33:31.170559: step: 980/530, loss: 0.0008661270258016884
2023-01-21 13:33:32.337050: step: 984/530, loss: 0.014449119567871094
2023-01-21 13:33:33.526584: step: 988/530, loss: 0.0003707885625772178
2023-01-21 13:33:34.761967: step: 992/530, loss: 0.06511564552783966
2023-01-21 13:33:35.927888: step: 996/530, loss: 0.0417327880859375
2023-01-21 13:33:37.091893: step: 1000/530, loss: 2.574920654296875e-05
2023-01-21 13:33:38.276579: step: 1004/530, loss: 0.00013999939255882055
2023-01-21 13:33:39.473152: step: 1008/530, loss: 0.0027029039338231087
2023-01-21 13:33:40.635531: step: 1012/530, loss: 1.564025842526462e-05
2023-01-21 13:33:41.781879: step: 1016/530, loss: 0.03310136869549751
2023-01-21 13:33:42.924886: step: 1020/530, loss: 0.0008900642278604209
2023-01-21 13:33:44.114649: step: 1024/530, loss: 0.00037167072878219187
2023-01-21 13:33:45.325688: step: 1028/530, loss: 0.005944252014160156
2023-01-21 13:33:46.531551: step: 1032/530, loss: 0.0632532611489296
2023-01-21 13:33:47.710061: step: 1036/530, loss: 2.1648407710017636e-05
2023-01-21 13:33:48.892584: step: 1040/530, loss: 0.012198258191347122
2023-01-21 13:33:50.079463: step: 1044/530, loss: 3.9863589336164296e-05
2023-01-21 13:33:51.227837: step: 1048/530, loss: 2.4032591682043858e-05
2023-01-21 13:33:52.401499: step: 1052/530, loss: 1.9168854123563506e-05
2023-01-21 13:33:53.579994: step: 1056/530, loss: 0.001992607256397605
2023-01-21 13:33:54.753569: step: 1060/530, loss: 0.04386749118566513
2023-01-21 13:33:55.992422: step: 1064/530, loss: 0.0008985519525595009
2023-01-21 13:33:57.193872: step: 1068/530, loss: 0.0007492065196856856
2023-01-21 13:33:58.373413: step: 1072/530, loss: 2.7561189199332148e-05
2023-01-21 13:33:59.583349: step: 1076/530, loss: 9.994507126975805e-05
2023-01-21 13:34:00.747833: step: 1080/530, loss: 0.0005281448247842491
2023-01-21 13:34:01.962254: step: 1084/530, loss: 0.009174728766083717
2023-01-21 13:34:03.163776: step: 1088/530, loss: 0.0003482818719930947
2023-01-21 13:34:04.328831: step: 1092/530, loss: 0.024530887603759766
2023-01-21 13:34:05.509075: step: 1096/530, loss: 0.0004904747474938631
2023-01-21 13:34:06.731585: step: 1100/530, loss: 0.021392822265625
2023-01-21 13:34:07.907618: step: 1104/530, loss: 0.12941399216651917
2023-01-21 13:34:09.132219: step: 1108/530, loss: 0.0005178452120162547
2023-01-21 13:34:10.308570: step: 1112/530, loss: 0.01640205644071102
2023-01-21 13:34:11.539662: step: 1116/530, loss: 0.0015214920276775956
2023-01-21 13:34:12.763565: step: 1120/530, loss: 0.03469962999224663
2023-01-21 13:34:13.950369: step: 1124/530, loss: 9.465218317927793e-05
2023-01-21 13:34:15.130949: step: 1128/530, loss: 0.02155141718685627
2023-01-21 13:34:16.344106: step: 1132/530, loss: 0.0699758529663086
2023-01-21 13:34:17.539637: step: 1136/530, loss: 0.0002003193076234311
2023-01-21 13:34:18.740183: step: 1140/530, loss: 0.0001405716029694304
2023-01-21 13:34:19.910061: step: 1144/530, loss: 0.00013895034499000758
2023-01-21 13:34:21.069888: step: 1148/530, loss: 0.0009246826521120965
2023-01-21 13:34:22.253263: step: 1152/530, loss: 0.0033431528136134148
2023-01-21 13:34:23.430537: step: 1156/530, loss: 0.005737495142966509
2023-01-21 13:34:24.576064: step: 1160/530, loss: 0.0003601074276957661
2023-01-21 13:34:25.766111: step: 1164/530, loss: 8.568763587391004e-05
2023-01-21 13:34:26.951212: step: 1168/530, loss: 0.04725942760705948
2023-01-21 13:34:28.114398: step: 1172/530, loss: 0.041841890662908554
2023-01-21 13:34:29.335699: step: 1176/530, loss: 1.8024444216280244e-05
2023-01-21 13:34:30.523353: step: 1180/530, loss: 0.0011386871337890625
2023-01-21 13:34:31.682490: step: 1184/530, loss: 9.737015352584422e-05
2023-01-21 13:34:32.894794: step: 1188/530, loss: 0.024085618555545807
2023-01-21 13:34:34.075976: step: 1192/530, loss: 0.021039199084043503
2023-01-21 13:34:35.231570: step: 1196/530, loss: 0.00024835168733261526
2023-01-21 13:34:36.422455: step: 1200/530, loss: 0.0002582550223451108
2023-01-21 13:34:37.641683: step: 1204/530, loss: 0.0008246421930380166
2023-01-21 13:34:38.796118: step: 1208/530, loss: 0.0001012802094919607
2023-01-21 13:34:39.970410: step: 1212/530, loss: 5.3882598876953125e-05
2023-01-21 13:34:41.201165: step: 1216/530, loss: 0.0017414093017578125
2023-01-21 13:34:42.397513: step: 1220/530, loss: 0.04070444032549858
2023-01-21 13:34:43.567616: step: 1224/530, loss: 0.00042743684025481343
2023-01-21 13:34:44.745221: step: 1228/530, loss: 8.525848534191027e-05
2023-01-21 13:34:45.882350: step: 1232/530, loss: 0.011065292172133923
2023-01-21 13:34:47.099882: step: 1236/530, loss: 0.0008114814991131425
2023-01-21 13:34:48.259437: step: 1240/530, loss: 0.0041748047806322575
2023-01-21 13:34:49.446554: step: 1244/530, loss: 0.4805641174316406
2023-01-21 13:34:50.619385: step: 1248/530, loss: 0.0022430419921875
2023-01-21 13:34:51.789943: step: 1252/530, loss: 0.008849906735122204
2023-01-21 13:34:52.908653: step: 1256/530, loss: 6.914139521541074e-05
2023-01-21 13:34:54.063671: step: 1260/530, loss: 7.576942880405113e-05
2023-01-21 13:34:55.216872: step: 1264/530, loss: 0.0035113333724439144
2023-01-21 13:34:56.454904: step: 1268/530, loss: 0.003048515412956476
2023-01-21 13:34:57.639848: step: 1272/530, loss: 0.04379329830408096
2023-01-21 13:34:58.788154: step: 1276/530, loss: 0.0038431170396506786
2023-01-21 13:34:59.927398: step: 1280/530, loss: 0.00012903212336823344
2023-01-21 13:35:01.112863: step: 1284/530, loss: 0.023546408861875534
2023-01-21 13:35:02.323417: step: 1288/530, loss: 4.1580202378099784e-05
2023-01-21 13:35:03.510651: step: 1292/530, loss: 0.0004962921375408769
2023-01-21 13:35:04.661463: step: 1296/530, loss: 0.0007173537742346525
2023-01-21 13:35:05.851610: step: 1300/530, loss: 0.06420421600341797
2023-01-21 13:35:07.023680: step: 1304/530, loss: 0.0006399154663085938
2023-01-21 13:35:08.150609: step: 1308/530, loss: 0.0009020805009640753
2023-01-21 13:35:09.332629: step: 1312/530, loss: 0.0006678581121377647
2023-01-21 13:35:10.474297: step: 1316/530, loss: 8.468628220725805e-05
2023-01-21 13:35:11.656556: step: 1320/530, loss: -4.425048973644152e-05
2023-01-21 13:35:12.901752: step: 1324/530, loss: 0.013179397210478783
2023-01-21 13:35:14.055500: step: 1328/530, loss: 0.16914503276348114
2023-01-21 13:35:15.204401: step: 1332/530, loss: 0.00017867088899947703
2023-01-21 13:35:16.390636: step: 1336/530, loss: 1.773834264895413e-05
2023-01-21 13:35:17.575477: step: 1340/530, loss: 0.004110908601433039
2023-01-21 13:35:18.767505: step: 1344/530, loss: 0.009069251827895641
2023-01-21 13:35:19.969872: step: 1348/530, loss: 5.53131121705519e-06
2023-01-21 13:35:21.182635: step: 1352/530, loss: 0.0009420394781045616
2023-01-21 13:35:22.362290: step: 1356/530, loss: -2.6702878130890895e-06
2023-01-21 13:35:23.550749: step: 1360/530, loss: 0.0013238906394690275
2023-01-21 13:35:24.769495: step: 1364/530, loss: 0.0012136459117755294
2023-01-21 13:35:25.925457: step: 1368/530, loss: 4.110336158191785e-05
2023-01-21 13:35:27.114700: step: 1372/530, loss: 2.4795533590804553e-06
2023-01-21 13:35:28.274816: step: 1376/530, loss: 0.10059070587158203
2023-01-21 13:35:29.420703: step: 1380/530, loss: 0.00042552949162200093
2023-01-21 13:35:30.568419: step: 1384/530, loss: 0.006117343902587891
2023-01-21 13:35:31.740200: step: 1388/530, loss: 0.05645294114947319
2023-01-21 13:35:32.906651: step: 1392/530, loss: 0.00015325547428801656
2023-01-21 13:35:34.101261: step: 1396/530, loss: 1.049041748046875e-05
2023-01-21 13:35:35.263963: step: 1400/530, loss: 1.430511474609375e-06
2023-01-21 13:35:36.447945: step: 1404/530, loss: 0.0007281303405761719
2023-01-21 13:35:37.614209: step: 1408/530, loss: 1.1444092706369702e-05
2023-01-21 13:35:38.831372: step: 1412/530, loss: 0.0068569183349609375
2023-01-21 13:35:40.030403: step: 1416/530, loss: 0.023429013788700104
2023-01-21 13:35:41.224531: step: 1420/530, loss: 0.020067404955625534
2023-01-21 13:35:42.416993: step: 1424/530, loss: 0.00022239686222746968
2023-01-21 13:35:43.608965: step: 1428/530, loss: 0.01184997521340847
2023-01-21 13:35:44.821015: step: 1432/530, loss: 0.0011535644298419356
2023-01-21 13:35:45.997829: step: 1436/530, loss: 0.031447697430849075
2023-01-21 13:35:47.188427: step: 1440/530, loss: 1.945495569088962e-05
2023-01-21 13:35:48.369529: step: 1444/530, loss: 0.00011568070476641878
2023-01-21 13:35:49.560428: step: 1448/530, loss: 9.34600848268019e-06
2023-01-21 13:35:50.778618: step: 1452/530, loss: 8.41140717966482e-05
2023-01-21 13:35:51.951163: step: 1456/530, loss: 0.0009826660389080644
2023-01-21 13:35:53.136637: step: 1460/530, loss: 0.09364718943834305
2023-01-21 13:35:54.283482: step: 1464/530, loss: 0.3904864192008972
2023-01-21 13:35:55.433861: step: 1468/530, loss: 0.021575165912508965
2023-01-21 13:35:56.617062: step: 1472/530, loss: 0.0010513304732739925
2023-01-21 13:35:57.781195: step: 1476/530, loss: 0.020025253295898438
2023-01-21 13:35:58.942362: step: 1480/530, loss: 0.0161909107118845
2023-01-21 13:36:00.133593: step: 1484/530, loss: 1.4972686585679185e-05
2023-01-21 13:36:01.333358: step: 1488/530, loss: 0.04743757098913193
2023-01-21 13:36:02.523992: step: 1492/530, loss: 0.0004596233193296939
2023-01-21 13:36:03.698372: step: 1496/530, loss: 9.5367431640625e-06
2023-01-21 13:36:04.884196: step: 1500/530, loss: 5.2261355449445546e-05
2023-01-21 13:36:06.051031: step: 1504/530, loss: 0.04272441938519478
2023-01-21 13:36:07.240221: step: 1508/530, loss: 0.0622737891972065
2023-01-21 13:36:08.462936: step: 1512/530, loss: 0.04793167486786842
2023-01-21 13:36:09.637279: step: 1516/530, loss: 0.001499176025390625
2023-01-21 13:36:10.817082: step: 1520/530, loss: 0.001739072846248746
2023-01-21 13:36:11.971764: step: 1524/530, loss: 0.03913154453039169
2023-01-21 13:36:13.183742: step: 1528/530, loss: 0.00031528473482467234
2023-01-21 13:36:14.350938: step: 1532/530, loss: 0.008660029619932175
2023-01-21 13:36:15.533950: step: 1536/530, loss: 0.0001298904389841482
2023-01-21 13:36:16.729812: step: 1540/530, loss: 0.7714803814888
2023-01-21 13:36:17.867614: step: 1544/530, loss: 2.861023403966101e-06
2023-01-21 13:36:19.054918: step: 1548/530, loss: 0.017801284790039062
2023-01-21 13:36:20.248409: step: 1552/530, loss: 0.5545670390129089
2023-01-21 13:36:21.394160: step: 1556/530, loss: -5.340575626178179e-06
2023-01-21 13:36:22.586563: step: 1560/530, loss: 0.012270832434296608
2023-01-21 13:36:23.777025: step: 1564/530, loss: 2.3508071535616182e-05
2023-01-21 13:36:24.925532: step: 1568/530, loss: 8.678435733600054e-06
2023-01-21 13:36:26.093361: step: 1572/530, loss: 4.119873119634576e-05
2023-01-21 13:36:27.264770: step: 1576/530, loss: 0.514556884765625
2023-01-21 13:36:28.433943: step: 1580/530, loss: 0.0011501312255859375
2023-01-21 13:36:29.651259: step: 1584/530, loss: 0.05809364467859268
2023-01-21 13:36:30.790486: step: 1588/530, loss: 0.06097240746021271
2023-01-21 13:36:31.997337: step: 1592/530, loss: 0.00040950774564407766
2023-01-21 13:36:33.169753: step: 1596/530, loss: 0.0023648261558264494
2023-01-21 13:36:34.391993: step: 1600/530, loss: 0.0027667998801916838
2023-01-21 13:36:35.578108: step: 1604/530, loss: 0.0003456115664448589
2023-01-21 13:36:36.767001: step: 1608/530, loss: 0.003501415252685547
2023-01-21 13:36:37.942844: step: 1612/530, loss: 0.002284145448356867
2023-01-21 13:36:39.132668: step: 1616/530, loss: 0.02496662177145481
2023-01-21 13:36:40.320339: step: 1620/530, loss: 7.43865984986769e-06
2023-01-21 13:36:41.493112: step: 1624/530, loss: 0.0054302215576171875
2023-01-21 13:36:42.667601: step: 1628/530, loss: 0.00013294219388626516
2023-01-21 13:36:43.838082: step: 1632/530, loss: 0.00744781456887722
2023-01-21 13:36:45.017707: step: 1636/530, loss: 5.34057608092553e-06
2023-01-21 13:36:46.206117: step: 1640/530, loss: 1.583099401614163e-05
2023-01-21 13:36:47.383422: step: 1644/530, loss: 9.212493750965223e-05
2023-01-21 13:36:48.542006: step: 1648/530, loss: 0.003195476485416293
2023-01-21 13:36:49.728427: step: 1652/530, loss: 0.007518577389419079
2023-01-21 13:36:50.868133: step: 1656/530, loss: 0.02119617536664009
2023-01-21 13:36:52.029786: step: 1660/530, loss: 8.869171870173886e-05
2023-01-21 13:36:53.206039: step: 1664/530, loss: 3.528595334501006e-05
2023-01-21 13:36:54.429541: step: 1668/530, loss: 8.58306884765625e-06
2023-01-21 13:36:55.591100: step: 1672/530, loss: 0.0006631851429119706
2023-01-21 13:36:56.723129: step: 1676/530, loss: 8.7738037109375e-05
2023-01-21 13:36:57.872725: step: 1680/530, loss: 0.05201740562915802
2023-01-21 13:36:59.088137: step: 1684/530, loss: 0.3211304545402527
2023-01-21 13:37:00.259022: step: 1688/530, loss: 2.746581958490424e-05
2023-01-21 13:37:01.484543: step: 1692/530, loss: 0.6078338623046875
2023-01-21 13:37:02.607236: step: 1696/530, loss: 3.719329924933845e-06
2023-01-21 13:37:03.779099: step: 1700/530, loss: 0.008941460400819778
2023-01-21 13:37:04.998372: step: 1704/530, loss: 0.011018562130630016
2023-01-21 13:37:06.162453: step: 1708/530, loss: 4.529952639131807e-05
2023-01-21 13:37:07.335313: step: 1712/530, loss: 0.034650806337594986
2023-01-21 13:37:08.518525: step: 1716/530, loss: 3.337860107421875e-06
2023-01-21 13:37:09.710833: step: 1720/530, loss: 0.0003250122244935483
2023-01-21 13:37:10.936875: step: 1724/530, loss: 0.004837989807128906
2023-01-21 13:37:12.149412: step: 1728/530, loss: 0.004127121064811945
2023-01-21 13:37:13.291361: step: 1732/530, loss: 0.00225830078125
2023-01-21 13:37:14.496952: step: 1736/530, loss: 0.01828174665570259
2023-01-21 13:37:15.674367: step: 1740/530, loss: 1.71661376953125e-05
2023-01-21 13:37:16.847051: step: 1744/530, loss: 0.004638671875
2023-01-21 13:37:18.033448: step: 1748/530, loss: 0.4977077543735504
2023-01-21 13:37:19.243386: step: 1752/530, loss: 0.1226491928100586
2023-01-21 13:37:20.447401: step: 1756/530, loss: 6.84738188283518e-05
2023-01-21 13:37:21.628016: step: 1760/530, loss: 0.007302188780158758
2023-01-21 13:37:22.832268: step: 1764/530, loss: 0.004945182707160711
2023-01-21 13:37:24.003589: step: 1768/530, loss: 0.0008996963733807206
2023-01-21 13:37:25.167486: step: 1772/530, loss: 0.00038013458834029734
2023-01-21 13:37:26.336188: step: 1776/530, loss: 0.420545756816864
2023-01-21 13:37:27.514236: step: 1780/530, loss: 0.0004016876046080142
2023-01-21 13:37:28.679960: step: 1784/530, loss: 0.08477678894996643
2023-01-21 13:37:29.891819: step: 1788/530, loss: 0.03332257270812988
2023-01-21 13:37:31.064194: step: 1792/530, loss: 0.03261518478393555
2023-01-21 13:37:32.220422: step: 1796/530, loss: 3.3092499506892636e-05
2023-01-21 13:37:33.366475: step: 1800/530, loss: 7.43865984986769e-06
2023-01-21 13:37:34.567586: step: 1804/530, loss: 0.01912212371826172
2023-01-21 13:37:35.856712: step: 1808/530, loss: 0.03701825439929962
2023-01-21 13:37:37.036617: step: 1812/530, loss: 0.028536034747958183
2023-01-21 13:37:38.188830: step: 1816/530, loss: 0.010234450921416283
2023-01-21 13:37:39.382128: step: 1820/530, loss: 0.0033693313598632812
2023-01-21 13:37:40.577830: step: 1824/530, loss: 0.017996788024902344
2023-01-21 13:37:41.816391: step: 1828/530, loss: 6.256103370105848e-05
2023-01-21 13:37:42.976900: step: 1832/530, loss: 0.00023679735022597015
2023-01-21 13:37:44.169678: step: 1836/530, loss: 0.0003586769162211567
2023-01-21 13:37:45.366780: step: 1840/530, loss: 0.0008254767162725329
2023-01-21 13:37:46.528367: step: 1844/530, loss: 0.027808047831058502
2023-01-21 13:37:47.726572: step: 1848/530, loss: 0.0001522064267192036
2023-01-21 13:37:48.895667: step: 1852/530, loss: 0.009389973245561123
2023-01-21 13:37:50.115530: step: 1856/530, loss: 0.00022439956956077367
2023-01-21 13:37:51.285415: step: 1860/530, loss: 0.007344245910644531
2023-01-21 13:37:52.467632: step: 1864/530, loss: 0.0031612396705895662
2023-01-21 13:37:53.661589: step: 1868/530, loss: 0.011002159677445889
2023-01-21 13:37:54.853299: step: 1872/530, loss: 0.20148134231567383
2023-01-21 13:37:56.039137: step: 1876/530, loss: 0.008301354013383389
2023-01-21 13:37:57.239671: step: 1880/530, loss: 0.00038938524085097015
2023-01-21 13:37:58.386613: step: 1884/530, loss: 0.00013890267291571945
2023-01-21 13:37:59.556105: step: 1888/530, loss: 0.005334234796464443
2023-01-21 13:38:00.725982: step: 1892/530, loss: 0.006791305728256702
2023-01-21 13:38:01.881604: step: 1896/530, loss: 0.00507245073094964
2023-01-21 13:38:03.070230: step: 1900/530, loss: 0.001680231187492609
2023-01-21 13:38:04.250571: step: 1904/530, loss: 5.9556961787166074e-05
2023-01-21 13:38:05.424419: step: 1908/530, loss: 0.019367694854736328
2023-01-21 13:38:06.600978: step: 1912/530, loss: 0.0010700225830078125
2023-01-21 13:38:07.782979: step: 1916/530, loss: 0.00015869141498114914
2023-01-21 13:38:08.929400: step: 1920/530, loss: -6.008148375258315e-06
2023-01-21 13:38:10.109495: step: 1924/530, loss: 0.06260509788990021
2023-01-21 13:38:11.295590: step: 1928/530, loss: 0.007757091429084539
2023-01-21 13:38:12.477596: step: 1932/530, loss: 0.004966640379279852
2023-01-21 13:38:13.675621: step: 1936/530, loss: 0.00013999939255882055
2023-01-21 13:38:14.880817: step: 1940/530, loss: 8.726119631319307e-06
2023-01-21 13:38:16.070641: step: 1944/530, loss: 0.03010082244873047
2023-01-21 13:38:17.251930: step: 1948/530, loss: 6.599425978492945e-05
2023-01-21 13:38:18.450513: step: 1952/530, loss: 0.04095101356506348
2023-01-21 13:38:19.619275: step: 1956/530, loss: 0.0036619186867028475
2023-01-21 13:38:20.797729: step: 1960/530, loss: 3.623962811616366e-06
2023-01-21 13:38:21.957271: step: 1964/530, loss: 9.689330909168348e-05
2023-01-21 13:38:23.117733: step: 1968/530, loss: 0.004737568087875843
2023-01-21 13:38:24.288080: step: 1972/530, loss: 0.0053186421282589436
2023-01-21 13:38:25.517167: step: 1976/530, loss: 0.0003681182861328125
2023-01-21 13:38:26.711575: step: 1980/530, loss: 0.008392333984375
2023-01-21 13:38:27.886909: step: 1984/530, loss: 0.0004643261490855366
2023-01-21 13:38:29.064840: step: 1988/530, loss: 0.0018993377452716231
2023-01-21 13:38:30.216631: step: 1992/530, loss: 0.00027289389981888235
2023-01-21 13:38:31.373403: step: 1996/530, loss: 0.00516433734446764
2023-01-21 13:38:32.604525: step: 2000/530, loss: 7.43865984986769e-06
2023-01-21 13:38:33.806436: step: 2004/530, loss: 1.71661376953125e-05
2023-01-21 13:38:34.995869: step: 2008/530, loss: 8.668899681651965e-05
2023-01-21 13:38:36.225206: step: 2012/530, loss: 0.00010356902930652723
2023-01-21 13:38:37.415328: step: 2016/530, loss: 0.004231262486428022
2023-01-21 13:38:38.566000: step: 2020/530, loss: 0.010181237012147903
2023-01-21 13:38:39.726552: step: 2024/530, loss: 6.532669067382812e-05
2023-01-21 13:38:40.933094: step: 2028/530, loss: 0.009036826901137829
2023-01-21 13:38:42.150819: step: 2032/530, loss: 0.028632165864109993
2023-01-21 13:38:43.302580: step: 2036/530, loss: 0.00042476653470657766
2023-01-21 13:38:44.486619: step: 2040/530, loss: 0.030996322631835938
2023-01-21 13:38:45.641915: step: 2044/530, loss: 0.00026035308837890625
2023-01-21 13:38:46.847909: step: 2048/530, loss: 0.00032420159550383687
2023-01-21 13:38:48.036319: step: 2052/530, loss: 0.09732723236083984
2023-01-21 13:38:49.185096: step: 2056/530, loss: 3.948211815441027e-05
2023-01-21 13:38:50.389923: step: 2060/530, loss: 0.0001239776611328125
2023-01-21 13:38:51.574164: step: 2064/530, loss: 0.013938712887465954
2023-01-21 13:38:52.757698: step: 2068/530, loss: 0.0001979827939067036
2023-01-21 13:38:53.942288: step: 2072/530, loss: 7.629394644936838e-07
2023-01-21 13:38:55.089941: step: 2076/530, loss: 0.01680145226418972
2023-01-21 13:38:56.253578: step: 2080/530, loss: 0.011154365725815296
2023-01-21 13:38:57.424950: step: 2084/530, loss: 0.013043785467743874
2023-01-21 13:38:58.585236: step: 2088/530, loss: 0.0038467408157885075
2023-01-21 13:38:59.749385: step: 2092/530, loss: 0.0002492904895916581
2023-01-21 13:39:00.909672: step: 2096/530, loss: 0.3864928185939789
2023-01-21 13:39:02.176773: step: 2100/530, loss: 0.00013008118548896164
2023-01-21 13:39:03.369499: step: 2104/530, loss: 5.717277599615045e-05
2023-01-21 13:39:04.529635: step: 2108/530, loss: 0.0015916824340820312
2023-01-21 13:39:05.708629: step: 2112/530, loss: 0.005071067716926336
2023-01-21 13:39:06.872695: step: 2116/530, loss: 0.022485733032226562
2023-01-21 13:39:08.034527: step: 2120/530, loss: 0.0004511833540163934
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.5920651068158698, 'r': 0.7749667110519307, 'f1': 0.671280276816609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6632510479739171, 'r': 0.8188614146060954, 'f1': 0.7328872876994339}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5384615384615384, 'r': 0.9074074074074074, 'f1': 0.6758620689655174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.5636363636363636, 'r': 0.49206349206349204, 'f1': 0.5254237288135594}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.44680851063829785, 'r': 0.5833333333333334, 'f1': 0.5060240963855422}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 13:39:51.674863: step: 4/530, loss: -1.411438006471144e-05
2023-01-21 13:39:52.871811: step: 8/530, loss: 0.005829238798469305
2023-01-21 13:39:54.073404: step: 12/530, loss: 0.0022008896339684725
2023-01-21 13:39:55.272188: step: 16/530, loss: 0.00023756027803756297
2023-01-21 13:39:56.466390: step: 20/530, loss: 6.523132469737902e-05
2023-01-21 13:39:57.641921: step: 24/530, loss: 0.0021169662941247225
2023-01-21 13:39:58.823007: step: 28/530, loss: 3.9672853745287284e-05
2023-01-21 13:39:59.975052: step: 32/530, loss: 0.0016769410576671362
2023-01-21 13:40:01.186350: step: 36/530, loss: 0.0018096923595294356
2023-01-21 13:40:02.347186: step: 40/530, loss: -1.5258788153005298e-06
2023-01-21 13:40:03.526604: step: 44/530, loss: 0.03781404346227646
2023-01-21 13:40:04.714545: step: 48/530, loss: 4.3296811782056466e-05
2023-01-21 13:40:05.905082: step: 52/530, loss: 0.011431884951889515
2023-01-21 13:40:07.084873: step: 56/530, loss: 5.283355858409777e-05
2023-01-21 13:40:08.289785: step: 60/530, loss: 8.20159948489163e-06
2023-01-21 13:40:09.452229: step: 64/530, loss: 0.05240192636847496
2023-01-21 13:40:10.636981: step: 68/530, loss: 0.015002822503447533
2023-01-21 13:40:11.758771: step: 72/530, loss: 0.003928661346435547
2023-01-21 13:40:12.962880: step: 76/530, loss: 4.4345855712890625e-05
2023-01-21 13:40:14.122039: step: 80/530, loss: 2.5272369384765625e-05
2023-01-21 13:40:15.289174: step: 84/530, loss: 5.9890749980695546e-05
2023-01-21 13:40:16.448119: step: 88/530, loss: 0.008724022656679153
2023-01-21 13:40:17.633437: step: 92/530, loss: 0.030758477747440338
2023-01-21 13:40:18.794668: step: 96/530, loss: 0.522162675857544
2023-01-21 13:40:19.996176: step: 100/530, loss: 0.0011777877807617188
2023-01-21 13:40:21.170472: step: 104/530, loss: 0.013872909359633923
2023-01-21 13:40:22.389440: step: 108/530, loss: 0.00011672973050735891
2023-01-21 13:40:23.569702: step: 112/530, loss: 0.01543350238353014
2023-01-21 13:40:24.736750: step: 116/530, loss: 0.004726219456642866
2023-01-21 13:40:25.891533: step: 120/530, loss: 0.0005173683166503906
2023-01-21 13:40:27.096543: step: 124/530, loss: 0.00018844603619072586
2023-01-21 13:40:28.254545: step: 128/530, loss: 0.012730026617646217
2023-01-21 13:40:29.439996: step: 132/530, loss: 0.0008310317643918097
2023-01-21 13:40:30.634000: step: 136/530, loss: 0.0010021210182458162
2023-01-21 13:40:31.811793: step: 140/530, loss: 0.0005702972412109375
2023-01-21 13:40:32.963712: step: 144/530, loss: 2.4795534045551904e-05
2023-01-21 13:40:34.128615: step: 148/530, loss: 0.0012784958817064762
2023-01-21 13:40:35.268061: step: 152/530, loss: 0.006991386413574219
2023-01-21 13:40:36.437145: step: 156/530, loss: 0.0006891250959597528
2023-01-21 13:40:37.636460: step: 160/530, loss: 3.4809113458322827e-06
2023-01-21 13:40:38.840694: step: 164/530, loss: 5.34057608092553e-06
2023-01-21 13:40:40.018642: step: 168/530, loss: 0.0011166095500811934
2023-01-21 13:40:41.182811: step: 172/530, loss: 0.009955216199159622
2023-01-21 13:40:42.428180: step: 176/530, loss: 0.003135299775749445
2023-01-21 13:40:43.649766: step: 180/530, loss: -0.0
2023-01-21 13:40:44.852628: step: 184/530, loss: 0.11247196793556213
2023-01-21 13:40:46.059677: step: 188/530, loss: 0.0133819580078125
2023-01-21 13:40:47.254184: step: 192/530, loss: 0.03193207085132599
2023-01-21 13:40:48.454460: step: 196/530, loss: -2.098083541568485e-06
2023-01-21 13:40:49.647561: step: 200/530, loss: 2.47955313170678e-06
2023-01-21 13:40:50.769492: step: 204/530, loss: 0.021140672266483307
2023-01-21 13:40:51.936743: step: 208/530, loss: 3.14712519866589e-06
2023-01-21 13:40:53.120749: step: 212/530, loss: 0.005852794740349054
2023-01-21 13:40:54.325227: step: 216/530, loss: 0.00011329651169944555
2023-01-21 13:40:55.525238: step: 220/530, loss: 0.012430763803422451
2023-01-21 13:40:56.765045: step: 224/530, loss: 0.0016486168606206775
2023-01-21 13:40:57.970748: step: 228/530, loss: 0.007553291507065296
2023-01-21 13:40:59.165745: step: 232/530, loss: 7.009506225585938e-05
2023-01-21 13:41:00.385821: step: 236/530, loss: 0.0026180266868323088
2023-01-21 13:41:01.552929: step: 240/530, loss: 0.000709152256604284
2023-01-21 13:41:02.729315: step: 244/530, loss: 0.0011796951293945312
2023-01-21 13:41:03.911372: step: 248/530, loss: 0.0001911163271870464
2023-01-21 13:41:05.094354: step: 252/530, loss: 6.351470801746473e-05
2023-01-21 13:41:06.320943: step: 256/530, loss: 0.00014419556828215718
2023-01-21 13:41:07.522425: step: 260/530, loss: 0.02088947221636772
2023-01-21 13:41:08.689775: step: 264/530, loss: 0.00022888182138558477
2023-01-21 13:41:09.844263: step: 268/530, loss: 0.10502319037914276
2023-01-21 13:41:10.993008: step: 272/530, loss: 5.7220458984375e-06
2023-01-21 13:41:12.139398: step: 276/530, loss: 0.002025604248046875
2023-01-21 13:41:13.350319: step: 280/530, loss: 0.0003971099795307964
2023-01-21 13:41:14.540054: step: 284/530, loss: 0.0021179199684411287
2023-01-21 13:41:15.670172: step: 288/530, loss: 3.929138256353326e-05
2023-01-21 13:41:16.837055: step: 292/530, loss: 0.00011672973778331652
2023-01-21 13:41:18.016172: step: 296/530, loss: 0.011717605404555798
2023-01-21 13:41:19.252423: step: 300/530, loss: 0.0038456919137388468
2023-01-21 13:41:20.469369: step: 304/530, loss: 0.0001558303920319304
2023-01-21 13:41:21.628380: step: 308/530, loss: 0.9889169931411743
2023-01-21 13:41:22.809763: step: 312/530, loss: 2.86102294921875e-05
2023-01-21 13:41:23.971482: step: 316/530, loss: 0.000629043614026159
2023-01-21 13:41:25.156971: step: 320/530, loss: 0.0002006530703511089
2023-01-21 13:41:26.361033: step: 324/530, loss: 9.546280489303172e-05
2023-01-21 13:41:27.557207: step: 328/530, loss: 0.004076194949448109
2023-01-21 13:41:28.793539: step: 332/530, loss: 0.009505748748779297
2023-01-21 13:41:29.995667: step: 336/530, loss: 0.00015592575073242188
2023-01-21 13:41:31.164602: step: 340/530, loss: 2.5558472771081142e-05
2023-01-21 13:41:32.351672: step: 344/530, loss: 0.10532741993665695
2023-01-21 13:41:33.534625: step: 348/530, loss: 0.0023677826393395662
2023-01-21 13:41:34.706875: step: 352/530, loss: 2.9277802241267636e-05
2023-01-21 13:41:35.865895: step: 356/530, loss: 0.0007671356434002519
2023-01-21 13:41:37.067902: step: 360/530, loss: 7.340907905017957e-05
2023-01-21 13:41:38.252534: step: 364/530, loss: 0.01973876915872097
2023-01-21 13:41:39.391381: step: 368/530, loss: 0.0006958008161745965
2023-01-21 13:41:40.595907: step: 372/530, loss: 5.5885317124193534e-05
2023-01-21 13:41:41.816859: step: 376/530, loss: 0.0007942199590615928
2023-01-21 13:41:43.065096: step: 380/530, loss: 0.0001218795805471018
2023-01-21 13:41:44.265589: step: 384/530, loss: 0.0007528782007284462
2023-01-21 13:41:45.467591: step: 388/530, loss: 0.008753967471420765
2023-01-21 13:41:46.673201: step: 392/530, loss: 0.011868476867675781
2023-01-21 13:41:47.889754: step: 396/530, loss: -3.051757857974735e-06
2023-01-21 13:41:49.047420: step: 400/530, loss: 8.058547973632812e-05
2023-01-21 13:41:50.230876: step: 404/530, loss: 0.001388931181281805
2023-01-21 13:41:51.472649: step: 408/530, loss: 0.002764415927231312
2023-01-21 13:41:52.661232: step: 412/530, loss: 0.12310740351676941
2023-01-21 13:41:53.791856: step: 416/530, loss: 1.6403197150793858e-05
2023-01-21 13:41:54.960401: step: 420/530, loss: 1.468658410885837e-05
2023-01-21 13:41:56.104116: step: 424/530, loss: 1.1634829206741415e-05
2023-01-21 13:41:57.274484: step: 428/530, loss: 0.0002911567862611264
2023-01-21 13:41:58.422338: step: 432/530, loss: 0.0027927877381443977
2023-01-21 13:41:59.597496: step: 436/530, loss: 0.013282060623168945
2023-01-21 13:42:00.773306: step: 440/530, loss: 0.00015926361083984375
2023-01-21 13:42:01.927683: step: 444/530, loss: 3.166198803228326e-05
2023-01-21 13:42:03.145344: step: 448/530, loss: 4.38690185546875e-05
2023-01-21 13:42:04.422017: step: 452/530, loss: 0.00017023086547851562
2023-01-21 13:42:05.600174: step: 456/530, loss: 0.02713337168097496
2023-01-21 13:42:06.795314: step: 460/530, loss: 0.0024721145164221525
2023-01-21 13:42:07.966184: step: 464/530, loss: 0.008486270904541016
2023-01-21 13:42:09.162431: step: 468/530, loss: 0.00018768310837913305
2023-01-21 13:42:10.336868: step: 472/530, loss: 0.0006136894226074219
2023-01-21 13:42:11.502125: step: 476/530, loss: 0.0005424499977380037
2023-01-21 13:42:12.652967: step: 480/530, loss: 5.259514000499621e-05
2023-01-21 13:42:13.811770: step: 484/530, loss: 4.119873119634576e-05
2023-01-21 13:42:15.013656: step: 488/530, loss: 0.011005019769072533
2023-01-21 13:42:16.189425: step: 492/530, loss: 4.043579247081652e-05
2023-01-21 13:42:17.362985: step: 496/530, loss: 0.024452686309814453
2023-01-21 13:42:18.532604: step: 500/530, loss: -1.5258789289873675e-06
2023-01-21 13:42:19.748135: step: 504/530, loss: 0.09538283199071884
2023-01-21 13:42:20.941449: step: 508/530, loss: -9.5367431640625e-07
2023-01-21 13:42:22.135420: step: 512/530, loss: 0.05043812096118927
2023-01-21 13:42:23.302950: step: 516/530, loss: 0.009728622622787952
2023-01-21 13:42:24.524942: step: 520/530, loss: 0.0059486390091478825
2023-01-21 13:42:25.709723: step: 524/530, loss: 0.0002765655517578125
2023-01-21 13:42:26.884112: step: 528/530, loss: 0.00093841552734375
2023-01-21 13:42:28.072933: step: 532/530, loss: 0.007543755229562521
2023-01-21 13:42:29.276018: step: 536/530, loss: 0.00015363693819381297
2023-01-21 13:42:30.465825: step: 540/530, loss: 0.006043815519660711
2023-01-21 13:42:31.679488: step: 544/530, loss: 0.02072477526962757
2023-01-21 13:42:32.863910: step: 548/530, loss: 0.004043388180434704
2023-01-21 13:42:34.054246: step: 552/530, loss: 0.00010719299461925402
2023-01-21 13:42:35.226362: step: 556/530, loss: 5.817413330078125e-05
2023-01-21 13:42:36.409921: step: 560/530, loss: 4.100799560546875e-05
2023-01-21 13:42:37.609506: step: 564/530, loss: 0.020451830700039864
2023-01-21 13:42:38.811719: step: 568/530, loss: 0.00010986328561557457
2023-01-21 13:42:39.996537: step: 572/530, loss: 0.0011040688259527087
2023-01-21 13:42:41.163507: step: 576/530, loss: 2.86102294921875e-05
2023-01-21 13:42:42.350429: step: 580/530, loss: 0.0011440276866778731
2023-01-21 13:42:43.553641: step: 584/530, loss: 0.07844734191894531
2023-01-21 13:42:44.743533: step: 588/530, loss: 3.051757857974735e-06
2023-01-21 13:42:45.949720: step: 592/530, loss: 0.018649006262421608
2023-01-21 13:42:47.167472: step: 596/530, loss: 0.025931738317012787
2023-01-21 13:42:48.344062: step: 600/530, loss: 4.091262962901965e-05
2023-01-21 13:42:49.521485: step: 604/530, loss: 0.00020704269991256297
2023-01-21 13:42:50.748373: step: 608/530, loss: 9.059906005859375e-06
2023-01-21 13:42:52.008056: step: 612/530, loss: 1.8501283193472773e-05
2023-01-21 13:42:53.225525: step: 616/530, loss: 0.021941184997558594
2023-01-21 13:42:54.446142: step: 620/530, loss: 0.022238541394472122
2023-01-21 13:42:55.622059: step: 624/530, loss: 6.484985988208791e-06
2023-01-21 13:42:56.798585: step: 628/530, loss: 0.0023048878647387028
2023-01-21 13:42:57.995240: step: 632/530, loss: 5.226135181146674e-05
2023-01-21 13:42:59.163698: step: 636/530, loss: 3.471374657237902e-05
2023-01-21 13:43:00.326130: step: 640/530, loss: 0.0001127243012888357
2023-01-21 13:43:01.514411: step: 644/530, loss: 0.00019428730593062937
2023-01-21 13:43:02.675356: step: 648/530, loss: 0.0004571914905682206
2023-01-21 13:43:03.825608: step: 652/530, loss: 0.005955314729362726
2023-01-21 13:43:05.039105: step: 656/530, loss: 7.82012921263231e-06
2023-01-21 13:43:06.207947: step: 660/530, loss: 0.00432586669921875
2023-01-21 13:43:07.389377: step: 664/530, loss: 0.00024204252986237407
2023-01-21 13:43:08.555088: step: 668/530, loss: 4.7206878662109375e-05
2023-01-21 13:43:09.722707: step: 672/530, loss: 9.269714792026207e-05
2023-01-21 13:43:10.857844: step: 676/530, loss: 0.0001852035493357107
2023-01-21 13:43:12.016540: step: 680/530, loss: 0.0034044268541038036
2023-01-21 13:43:13.200656: step: 684/530, loss: 3.814698175119702e-07
2023-01-21 13:43:14.389393: step: 688/530, loss: 0.011425400152802467
2023-01-21 13:43:15.537356: step: 692/530, loss: 3.7002566386945546e-05
2023-01-21 13:43:16.706993: step: 696/530, loss: 0.003380012698471546
2023-01-21 13:43:17.906131: step: 700/530, loss: 0.017837142571806908
2023-01-21 13:43:19.094671: step: 704/530, loss: 0.00694541959092021
2023-01-21 13:43:20.298191: step: 708/530, loss: 0.00041370390681549907
2023-01-21 13:43:21.490585: step: 712/530, loss: 0.0023647306952625513
2023-01-21 13:43:22.729400: step: 716/530, loss: 0.0005698204040527344
2023-01-21 13:43:23.931203: step: 720/530, loss: 0.00197772984392941
2023-01-21 13:43:25.205920: step: 724/530, loss: 0.019533729180693626
2023-01-21 13:43:26.369678: step: 728/530, loss: 0.00031414031400345266
2023-01-21 13:43:27.569526: step: 732/530, loss: 7.629395213371026e-07
2023-01-21 13:43:28.746617: step: 736/530, loss: 9.212494478560984e-05
2023-01-21 13:43:29.921198: step: 740/530, loss: 0.005208874121308327
2023-01-21 13:43:31.117407: step: 744/530, loss: 0.00032062531681731343
2023-01-21 13:43:32.298857: step: 748/530, loss: 0.00017604828462935984
2023-01-21 13:43:33.470439: step: 752/530, loss: 0.006326961796730757
2023-01-21 13:43:34.652016: step: 756/530, loss: 0.00015506744966842234
2023-01-21 13:43:35.843592: step: 760/530, loss: 0.0501561313867569
2023-01-21 13:43:37.017866: step: 764/530, loss: 0.0518682487308979
2023-01-21 13:43:38.218265: step: 768/530, loss: 0.00028028490487486124
2023-01-21 13:43:39.447377: step: 772/530, loss: 0.024476338177919388
2023-01-21 13:43:40.633339: step: 776/530, loss: 7.553101022494957e-05
2023-01-21 13:43:41.799073: step: 780/530, loss: 9.765625145519152e-05
2023-01-21 13:43:43.005306: step: 784/530, loss: 1.468658410885837e-05
2023-01-21 13:43:44.181257: step: 788/530, loss: 0.0009940625168383121
2023-01-21 13:43:45.318212: step: 792/530, loss: 0.0026735307183116674
2023-01-21 13:43:46.481749: step: 796/530, loss: 0.00018615722365211695
2023-01-21 13:43:47.674254: step: 800/530, loss: -2.7942656743107364e-05
2023-01-21 13:43:48.821933: step: 804/530, loss: 0.18169337511062622
2023-01-21 13:43:49.963331: step: 808/530, loss: 0.00030517578125
2023-01-21 13:43:51.166869: step: 812/530, loss: 0.0002914428769145161
2023-01-21 13:43:52.362581: step: 816/530, loss: 0.00486259488388896
2023-01-21 13:43:53.542434: step: 820/530, loss: 6.160735938465223e-05
2023-01-21 13:43:54.746164: step: 824/530, loss: 0.024407386779785156
2023-01-21 13:43:55.942557: step: 828/530, loss: 0.0040107727982103825
2023-01-21 13:43:57.078944: step: 832/530, loss: 0.000316619873046875
2023-01-21 13:43:58.253671: step: 836/530, loss: 0.0010696410899981856
2023-01-21 13:43:59.443684: step: 840/530, loss: 5.435943421616685e-06
2023-01-21 13:44:00.628077: step: 844/530, loss: 0.01974639855325222
2023-01-21 13:44:01.807064: step: 848/530, loss: 0.0012443542946130037
2023-01-21 13:44:02.962975: step: 852/530, loss: 7.266998727573082e-05
2023-01-21 13:44:04.137914: step: 856/530, loss: 0.000118255615234375
2023-01-21 13:44:05.389715: step: 860/530, loss: 0.0012861251598224044
2023-01-21 13:44:06.586526: step: 864/530, loss: 0.010896540246903896
2023-01-21 13:44:07.744544: step: 868/530, loss: 0.001472568605095148
2023-01-21 13:44:08.945623: step: 872/530, loss: 0.00396232632920146
2023-01-21 13:44:10.150483: step: 876/530, loss: 0.010645628906786442
2023-01-21 13:44:11.308257: step: 880/530, loss: 0.0005401611560955644
2023-01-21 13:44:12.476808: step: 884/530, loss: 0.00780754117295146
2023-01-21 13:44:13.699627: step: 888/530, loss: 2.751350257312879e-05
2023-01-21 13:44:14.909301: step: 892/530, loss: -7.62939453125e-06
2023-01-21 13:44:16.145574: step: 896/530, loss: 0.009859276004135609
2023-01-21 13:44:17.294977: step: 900/530, loss: 0.008296012878417969
2023-01-21 13:44:18.536188: step: 904/530, loss: -3.051757857974735e-06
2023-01-21 13:44:19.750660: step: 908/530, loss: 3.0517576306010596e-06
2023-01-21 13:44:20.923909: step: 912/530, loss: 3.4666059946175665e-05
2023-01-21 13:44:22.166414: step: 916/530, loss: 0.06484317779541016
2023-01-21 13:44:23.361001: step: 920/530, loss: 0.2999833822250366
2023-01-21 13:44:24.509292: step: 924/530, loss: -1.7166138377433526e-06
2023-01-21 13:44:25.684165: step: 928/530, loss: 0.00015506744966842234
2023-01-21 13:44:26.863600: step: 932/530, loss: 0.00039272307185456157
2023-01-21 13:44:28.045789: step: 936/530, loss: 0.00027523041353560984
2023-01-21 13:44:29.212311: step: 940/530, loss: 0.019242476671934128
2023-01-21 13:44:30.400901: step: 944/530, loss: 0.011103439144790173
2023-01-21 13:44:31.576676: step: 948/530, loss: 0.0004304886097088456
2023-01-21 13:44:32.797482: step: 952/530, loss: 0.00046329497126862407
2023-01-21 13:44:33.945869: step: 956/530, loss: 5.34057608092553e-06
2023-01-21 13:44:35.144881: step: 960/530, loss: 0.0023315430153161287
2023-01-21 13:44:36.309621: step: 964/530, loss: 0.018631935119628906
2023-01-21 13:44:37.476765: step: 968/530, loss: 4.57763671875e-05
2023-01-21 13:44:38.674882: step: 972/530, loss: 0.004718780983239412
2023-01-21 13:44:39.863829: step: 976/530, loss: 9.136199514614418e-05
2023-01-21 13:44:41.034544: step: 980/530, loss: -9.15527380129788e-06
2023-01-21 13:44:42.178764: step: 984/530, loss: 2.117157055181451e-05
2023-01-21 13:44:43.344855: step: 988/530, loss: 6.45637555862777e-05
2023-01-21 13:44:44.518149: step: 992/530, loss: 2.0027162008773303e-06
2023-01-21 13:44:45.678176: step: 996/530, loss: 0.004752159118652344
2023-01-21 13:44:46.847943: step: 1000/530, loss: 1.3351441339182202e-06
2023-01-21 13:44:48.000396: step: 1004/530, loss: 2.0503997802734375e-05
2023-01-21 13:44:49.161021: step: 1008/530, loss: 0.004763985052704811
2023-01-21 13:44:50.346491: step: 1012/530, loss: 0.0013132095336914062
2023-01-21 13:44:51.506539: step: 1016/530, loss: 4.0054324017546605e-06
2023-01-21 13:44:52.647632: step: 1020/530, loss: 6.47544875391759e-05
2023-01-21 13:44:53.805134: step: 1024/530, loss: 0.00011501312110340223
2023-01-21 13:44:55.008675: step: 1028/530, loss: 6.389617919921875e-05
2023-01-21 13:44:56.219065: step: 1032/530, loss: 0.007443428039550781
2023-01-21 13:44:57.406929: step: 1036/530, loss: 0.0003108978271484375
2023-01-21 13:44:58.576530: step: 1040/530, loss: 0.04680442810058594
2023-01-21 13:44:59.741557: step: 1044/530, loss: 0.009980392642319202
2023-01-21 13:45:00.913131: step: 1048/530, loss: 0.004717922303825617
2023-01-21 13:45:02.090080: step: 1052/530, loss: 4.768367034557741e-08
2023-01-21 13:45:03.270796: step: 1056/530, loss: 0.0005322456127032638
2023-01-21 13:45:04.448960: step: 1060/530, loss: 0.0006889343494549394
2023-01-21 13:45:05.623973: step: 1064/530, loss: 0.005567741580307484
2023-01-21 13:45:06.796139: step: 1068/530, loss: 4.730224463855848e-05
2023-01-21 13:45:07.938836: step: 1072/530, loss: 0.03714475780725479
2023-01-21 13:45:09.106380: step: 1076/530, loss: 7.629394644936838e-07
2023-01-21 13:45:10.282295: step: 1080/530, loss: 6.675722943327855e-07
2023-01-21 13:45:11.436981: step: 1084/530, loss: 5.054474058852065e-06
2023-01-21 13:45:12.635043: step: 1088/530, loss: 0.013685226440429688
2023-01-21 13:45:13.792272: step: 1092/530, loss: 6.618499901378527e-05
2023-01-21 13:45:14.985106: step: 1096/530, loss: 0.005281352903693914
2023-01-21 13:45:16.150960: step: 1100/530, loss: 0.015789033845067024
2023-01-21 13:45:17.345952: step: 1104/530, loss: 0.21039943397045135
2023-01-21 13:45:18.507574: step: 1108/530, loss: 9.264946129405871e-05
2023-01-21 13:45:19.662167: step: 1112/530, loss: 0.0021619796752929688
2023-01-21 13:45:20.790851: step: 1116/530, loss: 0.00043430327787064016
2023-01-21 13:45:21.946673: step: 1120/530, loss: 0.00020642280287574977
2023-01-21 13:45:23.085930: step: 1124/530, loss: 0.005421829409897327
2023-01-21 13:45:24.257923: step: 1128/530, loss: 0.00016880035400390625
2023-01-21 13:45:25.395196: step: 1132/530, loss: 0.03523435816168785
2023-01-21 13:45:26.573944: step: 1136/530, loss: 0.0001575946807861328
2023-01-21 13:45:27.749119: step: 1140/530, loss: 0.00011196136620128527
2023-01-21 13:45:28.931107: step: 1144/530, loss: 3.0517578125e-05
2023-01-21 13:45:30.144000: step: 1148/530, loss: 0.004398345947265625
2023-01-21 13:45:31.348983: step: 1152/530, loss: 1.9121171135338955e-05
2023-01-21 13:45:32.516681: step: 1156/530, loss: 0.00014057158841751516
2023-01-21 13:45:33.661901: step: 1160/530, loss: 3.662109884317033e-05
2023-01-21 13:45:34.811808: step: 1164/530, loss: 0.00027408599271439016
2023-01-21 13:45:36.002240: step: 1168/530, loss: 0.012848759070038795
2023-01-21 13:45:37.196604: step: 1172/530, loss: 0.03924904018640518
2023-01-21 13:45:38.347031: step: 1176/530, loss: 0.0001693725644145161
2023-01-21 13:45:39.531172: step: 1180/530, loss: 6.67572021484375e-05
2023-01-21 13:45:40.690858: step: 1184/530, loss: 3.452301098150201e-05
2023-01-21 13:45:41.909738: step: 1188/530, loss: 0.0005263328785076737
2023-01-21 13:45:43.128352: step: 1192/530, loss: 7.05719003235572e-06
2023-01-21 13:45:44.306248: step: 1196/530, loss: 0.00010337829735362902
2023-01-21 13:45:45.508704: step: 1200/530, loss: 0.00014381408982444555
2023-01-21 13:45:46.662321: step: 1204/530, loss: 5.245208740234375e-05
2023-01-21 13:45:47.833753: step: 1208/530, loss: 0.00010166168067371473
2023-01-21 13:45:49.011220: step: 1212/530, loss: 0.2588704228401184
2023-01-21 13:45:50.181611: step: 1216/530, loss: 0.0010334014659747481
2023-01-21 13:45:51.393171: step: 1220/530, loss: 0.07205124199390411
2023-01-21 13:45:52.558138: step: 1224/530, loss: 0.00019655228243209422
2023-01-21 13:45:53.736573: step: 1228/530, loss: 0.00027723313542082906
2023-01-21 13:45:54.935046: step: 1232/530, loss: 0.010649108327925205
2023-01-21 13:45:56.100839: step: 1236/530, loss: -2.8610247682081535e-07
2023-01-21 13:45:57.268355: step: 1240/530, loss: -5.149840944795869e-06
2023-01-21 13:45:58.456399: step: 1244/530, loss: 2.212524486822076e-05
2023-01-21 13:45:59.614818: step: 1248/530, loss: 0.0014511108165606856
2023-01-21 13:46:00.815711: step: 1252/530, loss: 0.000644683837890625
2023-01-21 13:46:01.958255: step: 1256/530, loss: 0.11577071994543076
2023-01-21 13:46:03.139728: step: 1260/530, loss: 0.0029537200462073088
2023-01-21 13:46:04.312433: step: 1264/530, loss: 0.0004999160883016884
2023-01-21 13:46:05.480659: step: 1268/530, loss: 0.04533729702234268
2023-01-21 13:46:06.614780: step: 1272/530, loss: 0.0013213157653808594
2023-01-21 13:46:07.804378: step: 1276/530, loss: 3.719329924933845e-06
2023-01-21 13:46:09.002805: step: 1280/530, loss: -3.7193294701864943e-06
2023-01-21 13:46:10.135771: step: 1284/530, loss: 4.501343209994957e-05
2023-01-21 13:46:11.364514: step: 1288/530, loss: 0.0007952689775265753
2023-01-21 13:46:12.619433: step: 1292/530, loss: 0.0002464294375386089
2023-01-21 13:46:13.809799: step: 1296/530, loss: 2.4795534045551904e-05
2023-01-21 13:46:14.915265: step: 1300/530, loss: 0.0003879547293763608
2023-01-21 13:46:16.092553: step: 1304/530, loss: -8.96453821042087e-06
2023-01-21 13:46:17.275311: step: 1308/530, loss: 0.000449943559942767
2023-01-21 13:46:18.402376: step: 1312/530, loss: 0.020659064874053
2023-01-21 13:46:19.543998: step: 1316/530, loss: 0.01578044891357422
2023-01-21 13:46:20.719756: step: 1320/530, loss: 0.056273460388183594
2023-01-21 13:46:21.936935: step: 1324/530, loss: 3.852844383800402e-05
2023-01-21 13:46:23.099729: step: 1328/530, loss: 0.41256943345069885
2023-01-21 13:46:24.303259: step: 1332/530, loss: 0.0485655777156353
2023-01-21 13:46:25.481440: step: 1336/530, loss: 0.0007797241560183465
2023-01-21 13:46:26.617857: step: 1340/530, loss: 0.0013965606922283769
2023-01-21 13:46:27.800619: step: 1344/530, loss: 2.956390380859375e-05
2023-01-21 13:46:29.007772: step: 1348/530, loss: 2.1839143300894648e-05
2023-01-21 13:46:30.175340: step: 1352/530, loss: 0.006017494481056929
2023-01-21 13:46:31.344722: step: 1356/530, loss: 1.068115216185106e-05
2023-01-21 13:46:32.503403: step: 1360/530, loss: -1.4495850336970761e-05
2023-01-21 13:46:33.703399: step: 1364/530, loss: 5.549192792386748e-06
2023-01-21 13:46:34.857943: step: 1368/530, loss: 0.0001067161574610509
2023-01-21 13:46:36.011897: step: 1372/530, loss: 8.296966370835435e-06
2023-01-21 13:46:37.216795: step: 1376/530, loss: 0.009438419714570045
2023-01-21 13:46:38.397118: step: 1380/530, loss: 2.2792815798311494e-05
2023-01-21 13:46:39.555973: step: 1384/530, loss: 0.012886714190244675
2023-01-21 13:46:40.740497: step: 1388/530, loss: 4.243850526108872e-06
2023-01-21 13:46:41.919615: step: 1392/530, loss: 0.0007118224748410285
2023-01-21 13:46:43.132553: step: 1396/530, loss: 0.000377464311895892
2023-01-21 13:46:44.340217: step: 1400/530, loss: 0.0002514839288778603
2023-01-21 13:46:45.538212: step: 1404/530, loss: 1.187875747680664
2023-01-21 13:46:46.764284: step: 1408/530, loss: 0.09320488572120667
2023-01-21 13:46:47.966441: step: 1412/530, loss: 2.86102294921875e-06
2023-01-21 13:46:49.104595: step: 1416/530, loss: 0.0017673491965979338
2023-01-21 13:46:50.267645: step: 1420/530, loss: 0.010086918249726295
2023-01-21 13:46:51.424775: step: 1424/530, loss: 0.0006376266828738153
2023-01-21 13:46:52.564695: step: 1428/530, loss: 0.011838329024612904
2023-01-21 13:46:53.747733: step: 1432/530, loss: 0.00014142990403342992
2023-01-21 13:46:55.000574: step: 1436/530, loss: 0.012244224548339844
2023-01-21 13:46:56.157760: step: 1440/530, loss: 4.854202416026965e-05
2023-01-21 13:46:57.346145: step: 1444/530, loss: 0.0002248764067189768
2023-01-21 13:46:58.563875: step: 1448/530, loss: 0.0015636443858966231
2023-01-21 13:46:59.772180: step: 1452/530, loss: 0.0005785942194052041
2023-01-21 13:47:00.948779: step: 1456/530, loss: 0.008548641577363014
2023-01-21 13:47:02.095165: step: 1460/530, loss: 0.06243762746453285
2023-01-21 13:47:03.260820: step: 1464/530, loss: 0.00026111601619049907
2023-01-21 13:47:04.427807: step: 1468/530, loss: 0.0014337539905682206
2023-01-21 13:47:05.561080: step: 1472/530, loss: 1.621246337890625e-05
2023-01-21 13:47:06.729555: step: 1476/530, loss: -1.583099401614163e-05
2023-01-21 13:47:07.911133: step: 1480/530, loss: 0.0001445770321879536
2023-01-21 13:47:09.096690: step: 1484/530, loss: 2.331733594473917e-05
2023-01-21 13:47:10.261179: step: 1488/530, loss: -4.482268650463084e-06
2023-01-21 13:47:11.433093: step: 1492/530, loss: 0.005095291417092085
2023-01-21 13:47:12.606884: step: 1496/530, loss: 0.0022885799407958984
2023-01-21 13:47:13.795813: step: 1500/530, loss: 0.019936610013246536
2023-01-21 13:47:14.970013: step: 1504/530, loss: 0.0018334866035729647
2023-01-21 13:47:16.103096: step: 1508/530, loss: 0.1090051680803299
2023-01-21 13:47:17.328653: step: 1512/530, loss: 0.0007868766551837325
2023-01-21 13:47:18.542528: step: 1516/530, loss: -2.28881845032447e-06
2023-01-21 13:47:19.758266: step: 1520/530, loss: 1.049041748046875e-05
2023-01-21 13:47:20.930019: step: 1524/530, loss: 0.0005147933843545616
2023-01-21 13:47:22.137058: step: 1528/530, loss: 0.00010366439528297633
2023-01-21 13:47:23.316261: step: 1532/530, loss: 0.001170849776826799
2023-01-21 13:47:24.483197: step: 1536/530, loss: 0.0039466856978833675
2023-01-21 13:47:25.647256: step: 1540/530, loss: 0.00123004917986691
2023-01-21 13:47:26.827790: step: 1544/530, loss: 0.00287132291123271
2023-01-21 13:47:28.039456: step: 1548/530, loss: 1.4591217222914565e-05
2023-01-21 13:47:29.205008: step: 1552/530, loss: 0.00010967254638671875
2023-01-21 13:47:30.431637: step: 1556/530, loss: 0.0016574859619140625
2023-01-21 13:47:31.613735: step: 1560/530, loss: 1.6212464970521978e-06
2023-01-21 13:47:32.763542: step: 1564/530, loss: 4.38690185546875e-05
2023-01-21 13:47:33.970283: step: 1568/530, loss: 6.198883056640625e-06
2023-01-21 13:47:35.163241: step: 1572/530, loss: 6.084442065912299e-05
2023-01-21 13:47:36.375580: step: 1576/530, loss: -1.201629675051663e-05
2023-01-21 13:47:37.526152: step: 1580/530, loss: 2.384185791015625e-05
2023-01-21 13:47:38.745622: step: 1584/530, loss: 4.7111509047681466e-05
2023-01-21 13:47:39.929968: step: 1588/530, loss: 0.0018552780384197831
2023-01-21 13:47:41.092441: step: 1592/530, loss: 0.00010452270362293348
2023-01-21 13:47:42.324107: step: 1596/530, loss: 0.0035234452225267887
2023-01-21 13:47:43.544420: step: 1600/530, loss: 0.00045490264892578125
2023-01-21 13:47:44.728785: step: 1604/530, loss: 0.00014319420733954757
2023-01-21 13:47:45.899906: step: 1608/530, loss: 0.0006534576532430947
2023-01-21 13:47:47.108647: step: 1612/530, loss: 8.392333984375e-05
2023-01-21 13:47:48.299747: step: 1616/530, loss: 9.72747784544481e-06
2023-01-21 13:47:49.470073: step: 1620/530, loss: 0.0004037857288494706
2023-01-21 13:47:50.639135: step: 1624/530, loss: 5.359649730962701e-05
2023-01-21 13:47:51.821297: step: 1628/530, loss: 0.0005096435779705644
2023-01-21 13:47:52.952300: step: 1632/530, loss: 0.0010642051929607987
2023-01-21 13:47:54.160339: step: 1636/530, loss: 0.00016441346087958664
2023-01-21 13:47:55.308532: step: 1640/530, loss: 1.2636184692382812e-05
2023-01-21 13:47:56.516936: step: 1644/530, loss: 0.0025866508949548006
2023-01-21 13:47:57.707101: step: 1648/530, loss: 8.58306884765625e-06
2023-01-21 13:47:58.903676: step: 1652/530, loss: 0.009610939770936966
2023-01-21 13:48:00.122026: step: 1656/530, loss: 1.9471209049224854
2023-01-21 13:48:01.288939: step: 1660/530, loss: 0.0010099411010742188
2023-01-21 13:48:02.445974: step: 1664/530, loss: 0.0005261421320028603
2023-01-21 13:48:03.613627: step: 1668/530, loss: 0.003709983779117465
2023-01-21 13:48:04.813000: step: 1672/530, loss: 0.009287643246352673
2023-01-21 13:48:05.955528: step: 1676/530, loss: -5.722045557376987e-07
2023-01-21 13:48:07.130201: step: 1680/530, loss: 0.0017478943336755037
2023-01-21 13:48:08.279242: step: 1684/530, loss: 0.026054099202156067
2023-01-21 13:48:09.478605: step: 1688/530, loss: 8.697509474586695e-05
2023-01-21 13:48:10.637251: step: 1692/530, loss: 0.00012302398681640625
2023-01-21 13:48:11.822721: step: 1696/530, loss: 0.00021066665067337453
2023-01-21 13:48:13.021432: step: 1700/530, loss: 0.0002636909484863281
2023-01-21 13:48:14.197670: step: 1704/530, loss: 0.012686824426054955
2023-01-21 13:48:15.316795: step: 1708/530, loss: 3.62396240234375e-05
2023-01-21 13:48:16.501135: step: 1712/530, loss: 0.0033990859519690275
2023-01-21 13:48:17.755955: step: 1716/530, loss: 3.0517578125e-05
2023-01-21 13:48:18.948289: step: 1720/530, loss: 9.51766996877268e-05
2023-01-21 13:48:20.140289: step: 1724/530, loss: 0.004762554541230202
2023-01-21 13:48:21.303468: step: 1728/530, loss: -2.86102294921875e-06
2023-01-21 13:48:22.466531: step: 1732/530, loss: 1.2874604180979077e-05
2023-01-21 13:48:23.656056: step: 1736/530, loss: 0.0002754211309365928
2023-01-21 13:48:24.826614: step: 1740/530, loss: -5.5313107623078395e-06
2023-01-21 13:48:26.019622: step: 1744/530, loss: 0.0009949683444574475
2023-01-21 13:48:27.188238: step: 1748/530, loss: 0.02216815948486328
2023-01-21 13:48:28.423690: step: 1752/530, loss: 0.003179454943165183
2023-01-21 13:48:29.595738: step: 1756/530, loss: 0.0002360344078624621
2023-01-21 13:48:30.768286: step: 1760/530, loss: 0.0007087707635946572
2023-01-21 13:48:31.976651: step: 1764/530, loss: 0.01787385903298855
2023-01-21 13:48:33.147262: step: 1768/530, loss: 0.0024094581604003906
2023-01-21 13:48:34.359983: step: 1772/530, loss: 0.007044506259262562
2023-01-21 13:48:35.548052: step: 1776/530, loss: 8.869171324477065e-06
2023-01-21 13:48:36.731577: step: 1780/530, loss: 1.5258789289873675e-06
2023-01-21 13:48:37.895195: step: 1784/530, loss: 0.00026226043701171875
2023-01-21 13:48:39.081170: step: 1788/530, loss: -1.716613724056515e-06
2023-01-21 13:48:40.262767: step: 1792/530, loss: 0.04228496551513672
2023-01-21 13:48:41.432399: step: 1796/530, loss: 0.00020380019850563258
2023-01-21 13:48:42.685426: step: 1800/530, loss: -3.42369094141759e-05
2023-01-21 13:48:43.863394: step: 1804/530, loss: 0.00028705596923828125
2023-01-21 13:48:45.043602: step: 1808/530, loss: 0.0005010605091229081
2023-01-21 13:48:46.252057: step: 1812/530, loss: -3.337859652674524e-06
2023-01-21 13:48:47.432638: step: 1816/530, loss: 0.00019178391085006297
2023-01-21 13:48:48.624929: step: 1820/530, loss: 0.058434486389160156
2023-01-21 13:48:49.817406: step: 1824/530, loss: 0.0049758912064135075
2023-01-21 13:48:51.005394: step: 1828/530, loss: 0.0064424993470311165
2023-01-21 13:48:52.239586: step: 1832/530, loss: 0.0012840271228924394
2023-01-21 13:48:53.451132: step: 1836/530, loss: 2.4318695068359375e-05
2023-01-21 13:48:54.663167: step: 1840/530, loss: 0.04388141632080078
2023-01-21 13:48:55.843218: step: 1844/530, loss: 0.005647850222885609
2023-01-21 13:48:57.034755: step: 1848/530, loss: 0.00037641526432707906
2023-01-21 13:48:58.191806: step: 1852/530, loss: 0.00090961460955441
2023-01-21 13:48:59.395399: step: 1856/530, loss: -7.82012921263231e-06
2023-01-21 13:49:00.558072: step: 1860/530, loss: 0.006428528111428022
2023-01-21 13:49:01.755801: step: 1864/530, loss: 0.1455366015434265
2023-01-21 13:49:02.934970: step: 1868/530, loss: 0.0027129175141453743
2023-01-21 13:49:04.116007: step: 1872/530, loss: 0.009030342102050781
2023-01-21 13:49:05.320640: step: 1876/530, loss: 0.003905868623405695
2023-01-21 13:49:06.539370: step: 1880/530, loss: 0.009376334957778454
2023-01-21 13:49:07.718057: step: 1884/530, loss: 4.7206878662109375e-05
2023-01-21 13:49:08.929039: step: 1888/530, loss: 0.00034770966158248484
2023-01-21 13:49:10.131069: step: 1892/530, loss: 0.0007037162431515753
2023-01-21 13:49:11.294103: step: 1896/530, loss: 0.0005411148304119706
2023-01-21 13:49:12.520665: step: 1900/530, loss: -1.7642974853515625e-05
2023-01-21 13:49:13.715906: step: 1904/530, loss: 2.517700158932712e-05
2023-01-21 13:49:14.929220: step: 1908/530, loss: 0.00028171538724564016
2023-01-21 13:49:16.116321: step: 1912/530, loss: 0.002069854876026511
2023-01-21 13:49:17.332707: step: 1916/530, loss: 0.0005008697626180947
2023-01-21 13:49:18.502371: step: 1920/530, loss: 0.012419892475008965
2023-01-21 13:49:19.652356: step: 1924/530, loss: 9.54627976170741e-05
2023-01-21 13:49:20.830318: step: 1928/530, loss: 0.0007087350240908563
2023-01-21 13:49:22.044932: step: 1932/530, loss: 1.239776611328125e-05
2023-01-21 13:49:23.304524: step: 1936/530, loss: 0.0006891250959597528
2023-01-21 13:49:24.534677: step: 1940/530, loss: 3.63349899998866e-05
2023-01-21 13:49:25.715640: step: 1944/530, loss: 0.0014512062771245837
2023-01-21 13:49:26.917064: step: 1948/530, loss: 0.0005121231079101562
2023-01-21 13:49:28.116898: step: 1952/530, loss: 0.0002449035819154233
2023-01-21 13:49:29.298588: step: 1956/530, loss: 0.0005399704095907509
2023-01-21 13:49:30.508800: step: 1960/530, loss: 0.013637542724609375
2023-01-21 13:49:31.679478: step: 1964/530, loss: 4.019737389171496e-05
2023-01-21 13:49:32.868863: step: 1968/530, loss: 0.007344054989516735
2023-01-21 13:49:34.015576: step: 1972/530, loss: 3.43322744811303e-06
2023-01-21 13:49:35.208393: step: 1976/530, loss: 9.021758887683973e-05
2023-01-21 13:49:36.343571: step: 1980/530, loss: 0.0034140588250011206
2023-01-21 13:49:37.540808: step: 1984/530, loss: 0.023987771943211555
2023-01-21 13:49:38.747016: step: 1988/530, loss: 0.0003339767863508314
2023-01-21 13:49:39.916594: step: 1992/530, loss: 0.007114219479262829
2023-01-21 13:49:41.093067: step: 1996/530, loss: 6.198883056640625e-06
2023-01-21 13:49:42.304157: step: 2000/530, loss: 3.528594970703125e-05
2023-01-21 13:49:43.454118: step: 2004/530, loss: 0.05183382332324982
2023-01-21 13:49:44.602936: step: 2008/530, loss: 0.00010976791963912547
2023-01-21 13:49:45.769805: step: 2012/530, loss: 0.0005473137134686112
2023-01-21 13:49:46.997458: step: 2016/530, loss: 0.00012130737013649195
2023-01-21 13:49:48.214546: step: 2020/530, loss: 0.053607940673828125
2023-01-21 13:49:49.388982: step: 2024/530, loss: 0.00015263557725120336
2023-01-21 13:49:50.560327: step: 2028/530, loss: 2.341270555916708e-05
2023-01-21 13:49:51.772935: step: 2032/530, loss: 0.0008840560913085938
2023-01-21 13:49:52.968628: step: 2036/530, loss: 0.00039920807466842234
2023-01-21 13:49:54.172126: step: 2040/530, loss: 0.0005187034839764237
2023-01-21 13:49:55.374197: step: 2044/530, loss: 0.002173256827518344
2023-01-21 13:49:56.562382: step: 2048/530, loss: 4.711151268566027e-05
2023-01-21 13:49:57.703224: step: 2052/530, loss: 0.00014344156079459935
2023-01-21 13:49:58.870190: step: 2056/530, loss: 0.004884147550910711
2023-01-21 13:50:00.062985: step: 2060/530, loss: 0.011502837762236595
2023-01-21 13:50:01.242909: step: 2064/530, loss: 0.004092359449714422
2023-01-21 13:50:02.421126: step: 2068/530, loss: 0.0008064269786700606
2023-01-21 13:50:03.579817: step: 2072/530, loss: 2.4461747671011835e-05
2023-01-21 13:50:04.761885: step: 2076/530, loss: 0.011409771628677845
2023-01-21 13:50:05.953587: step: 2080/530, loss: 0.020146608352661133
2023-01-21 13:50:07.116867: step: 2084/530, loss: 0.014391040429472923
2023-01-21 13:50:08.299600: step: 2088/530, loss: 0.00011110305786132812
2023-01-21 13:50:09.471231: step: 2092/530, loss: -3.24249276673072e-06
2023-01-21 13:50:10.654467: step: 2096/530, loss: 2.2792815798311494e-05
2023-01-21 13:50:11.876374: step: 2100/530, loss: 0.06636810302734375
2023-01-21 13:50:13.021185: step: 2104/530, loss: 0.36463260650634766
2023-01-21 13:50:14.181767: step: 2108/530, loss: 0.010037994012236595
2023-01-21 13:50:15.346346: step: 2112/530, loss: 3.128051685052924e-05
2023-01-21 13:50:16.506225: step: 2116/530, loss: -2.708435022213962e-05
2023-01-21 13:50:17.643449: step: 2120/530, loss: 0.0002667427179403603
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.608421052631579, 'r': 0.7696404793608522, 'f1': 0.6796002351557907}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6660377358490566, 'r': 0.81196089706728, 'f1': 0.731795802021249}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.5666666666666667, 'r': 0.9444444444444444, 'f1': 0.7083333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.6170212765957447, 'r': 0.4603174603174603, 'f1': 0.5272727272727272}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
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': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 13:51:01.149990: step: 4/530, loss: 0.0008842467796057463
2023-01-21 13:51:02.299583: step: 8/530, loss: 3.5667417250806466e-05
2023-01-21 13:51:03.492344: step: 12/530, loss: 3.24249276673072e-06
2023-01-21 13:51:04.664036: step: 16/530, loss: 0.0023732187692075968
2023-01-21 13:51:05.818273: step: 20/530, loss: 2.86102294921875e-06
2023-01-21 13:51:07.005254: step: 24/530, loss: 4.38690176451928e-06
2023-01-21 13:51:08.199758: step: 28/530, loss: 1.0108947208209429e-05
2023-01-21 13:51:09.361104: step: 32/530, loss: 0.018539810553193092
2023-01-21 13:51:10.567789: step: 36/530, loss: 0.0005767822731286287
2023-01-21 13:51:11.735282: step: 40/530, loss: -2.6702882678364404e-06
2023-01-21 13:51:12.892819: step: 44/530, loss: 7.62939453125e-06
2023-01-21 13:51:14.092132: step: 48/530, loss: 0.0004245758173055947
2023-01-21 13:51:15.260544: step: 52/530, loss: 5.7220458984375e-06
2023-01-21 13:51:16.453873: step: 56/530, loss: 0.025035668164491653
2023-01-21 13:51:17.648674: step: 60/530, loss: 3.662109520519152e-05
2023-01-21 13:51:18.838701: step: 64/530, loss: 3.0517580853484105e-06
2023-01-21 13:51:19.989112: step: 68/530, loss: 0.0008785247919149697
2023-01-21 13:51:21.146353: step: 72/530, loss: 1.1730195183190517e-05
2023-01-21 13:51:22.419920: step: 76/530, loss: 0.11610870808362961
2023-01-21 13:51:23.615849: step: 80/530, loss: 7.915496098576114e-06
2023-01-21 13:51:24.795369: step: 84/530, loss: 0.00016508101543877274
2023-01-21 13:51:26.004425: step: 88/530, loss: -6.580352874152595e-06
2023-01-21 13:51:27.194486: step: 92/530, loss: 7.629387255292386e-07
2023-01-21 13:51:28.387144: step: 96/530, loss: 0.0005901336553506553
2023-01-21 13:51:29.540840: step: 100/530, loss: 0.024289704859256744
2023-01-21 13:51:30.719078: step: 104/530, loss: 0.0012409210903570056
2023-01-21 13:51:31.878183: step: 108/530, loss: 0.0002658844168763608
2023-01-21 13:51:33.084269: step: 112/530, loss: 9.059906005859375e-06
2023-01-21 13:51:34.259469: step: 116/530, loss: 6.885529001010582e-05
2023-01-21 13:51:35.421874: step: 120/530, loss: 3.929138256353326e-05
2023-01-21 13:51:36.590361: step: 124/530, loss: 0.000301170366583392
2023-01-21 13:51:37.766133: step: 128/530, loss: 0.0020597458351403475
2023-01-21 13:51:38.951857: step: 132/530, loss: 1.6880036127986386e-05
2023-01-21 13:51:40.142518: step: 136/530, loss: 4.9114232751890086e-06
2023-01-21 13:51:41.319245: step: 140/530, loss: 0.00022525788517668843
2023-01-21 13:51:42.541083: step: 144/530, loss: 0.00028362273587845266
2023-01-21 13:51:43.742941: step: 148/530, loss: 0.00023651123046875
2023-01-21 13:51:44.870739: step: 152/530, loss: -8.39233416627394e-06
2023-01-21 13:51:46.036437: step: 156/530, loss: 3.4809112548828125e-05
2023-01-21 13:51:47.193800: step: 160/530, loss: 0.014372444711625576
2023-01-21 13:51:48.376522: step: 164/530, loss: 0.0003044605255126953
2023-01-21 13:51:49.563091: step: 168/530, loss: 0.0006437301635742188
2023-01-21 13:51:50.740416: step: 172/530, loss: 0.012850952334702015
2023-01-21 13:51:51.922267: step: 176/530, loss: 2.8610227218450746e-06
2023-01-21 13:51:53.118047: step: 180/530, loss: 0.00577621441334486
2023-01-21 13:51:54.359928: step: 184/530, loss: 0.0009630203130654991
2023-01-21 13:51:55.534560: step: 188/530, loss: 0.0001680374116403982
2023-01-21 13:51:56.671532: step: 192/530, loss: 8.096695091808215e-05
2023-01-21 13:51:57.843571: step: 196/530, loss: 0.00010147094872081652
2023-01-21 13:51:59.034979: step: 200/530, loss: 0.0022326470352709293
2023-01-21 13:52:00.229812: step: 204/530, loss: 0.032537125051021576
2023-01-21 13:52:01.369624: step: 208/530, loss: 7.019042823230848e-05
2023-01-21 13:52:02.549380: step: 212/530, loss: 0.0013736726250499487
2023-01-21 13:52:03.714158: step: 216/530, loss: 0.0007306575425900519
2023-01-21 13:52:04.927729: step: 220/530, loss: 0.00033226015511900187
2023-01-21 13:52:06.093777: step: 224/530, loss: 5.7220458984375e-05
2023-01-21 13:52:07.280831: step: 228/530, loss: -3.24249276673072e-06
2023-01-21 13:52:08.442423: step: 232/530, loss: 0.0001653671351959929
2023-01-21 13:52:09.632525: step: 236/530, loss: 0.00037860870361328125
2023-01-21 13:52:10.865850: step: 240/530, loss: 0.0007821083418093622
2023-01-21 13:52:12.048337: step: 244/530, loss: 0.0029730796813964844
2023-01-21 13:52:13.274761: step: 248/530, loss: 6.65664701955393e-05
2023-01-21 13:52:14.441780: step: 252/530, loss: 0.009882736951112747
2023-01-21 13:52:15.625028: step: 256/530, loss: 5.2833554946118966e-05
2023-01-21 13:52:16.828708: step: 260/530, loss: 0.0005966186290606856
2023-01-21 13:52:17.956819: step: 264/530, loss: 1.6498566765221767e-05
2023-01-21 13:52:19.132937: step: 268/530, loss: 0.0024673461448401213
2023-01-21 13:52:20.303519: step: 272/530, loss: 0.005174827296286821
2023-01-21 13:52:21.479364: step: 276/530, loss: 3.089904930675402e-05
2023-01-21 13:52:22.652938: step: 280/530, loss: 0.024163484573364258
2023-01-21 13:52:23.814884: step: 284/530, loss: 0.0002408981235930696
2023-01-21 13:52:25.023171: step: 288/530, loss: 7.43865984986769e-06
2023-01-21 13:52:26.170989: step: 292/530, loss: 0.013293981552124023
2023-01-21 13:52:27.357016: step: 296/530, loss: 4.0817263652570546e-05
2023-01-21 13:52:28.498755: step: 300/530, loss: 0.0014567375183105469
2023-01-21 13:52:29.745981: step: 304/530, loss: 0.0006543159252032638
2023-01-21 13:52:30.875758: step: 308/530, loss: 8.211136446334422e-05
2023-01-21 13:52:32.037373: step: 312/530, loss: 0.004639816470444202
2023-01-21 13:52:33.269165: step: 316/530, loss: 6.628037226619199e-06
2023-01-21 13:52:34.478788: step: 320/530, loss: 0.00024890899658203125
2023-01-21 13:52:35.711469: step: 324/530, loss: 0.008576965890824795
2023-01-21 13:52:36.932546: step: 328/530, loss: 0.0008941650739870965
2023-01-21 13:52:38.110116: step: 332/530, loss: 0.009537887759506702
2023-01-21 13:52:39.330420: step: 336/530, loss: 0.0052429200150072575
2023-01-21 13:52:40.506534: step: 340/530, loss: 0.0012697218917310238
2023-01-21 13:52:41.693191: step: 344/530, loss: -3.814697322468419e-07
2023-01-21 13:52:42.881425: step: 348/530, loss: 0.00011100769916083664
2023-01-21 13:52:44.090935: step: 352/530, loss: 0.05011463165283203
2023-01-21 13:52:45.292579: step: 356/530, loss: 0.00014781951904296875
2023-01-21 13:52:46.457826: step: 360/530, loss: 7.171630568336695e-05
2023-01-21 13:52:47.626563: step: 364/530, loss: 0.014308357611298561
2023-01-21 13:52:48.816344: step: 368/530, loss: 0.0017265320057049394
2023-01-21 13:52:50.003515: step: 372/530, loss: 0.0004422187921591103
2023-01-21 13:52:51.176945: step: 376/530, loss: 0.0004518509085755795
2023-01-21 13:52:52.373967: step: 380/530, loss: 0.020642662420868874
2023-01-21 13:52:53.541288: step: 384/530, loss: 0.0028545379173010588
2023-01-21 13:52:54.732146: step: 388/530, loss: 0.048616793006658554
2023-01-21 13:52:55.964156: step: 392/530, loss: 0.06614677608013153
2023-01-21 13:52:57.138106: step: 396/530, loss: 0.04632611200213432
2023-01-21 13:52:58.350622: step: 400/530, loss: 0.0011794089805334806
2023-01-21 13:52:59.494862: step: 404/530, loss: 0.0017919540405273438
2023-01-21 13:53:00.730795: step: 408/530, loss: 0.10392151027917862
2023-01-21 13:53:01.883137: step: 412/530, loss: 0.011982726864516735
2023-01-21 13:53:03.067127: step: 416/530, loss: 6.961822691664565e-06
2023-01-21 13:53:04.230599: step: 420/530, loss: 9.16481003514491e-05
2023-01-21 13:53:05.420703: step: 424/530, loss: 0.00059933663578704
2023-01-21 13:53:06.595709: step: 428/530, loss: 1.354217511106981e-05
2023-01-21 13:53:07.739916: step: 432/530, loss: 8.96453821042087e-06
2023-01-21 13:53:08.878159: step: 436/530, loss: 0.006188583560287952
2023-01-21 13:53:10.067775: step: 440/530, loss: 1.296997106692288e-05
2023-01-21 13:53:11.225521: step: 444/530, loss: 0.00043315888615325093
2023-01-21 13:53:12.440360: step: 448/530, loss: 0.014470291323959827
2023-01-21 13:53:13.610119: step: 452/530, loss: 0.00013236999802757055
2023-01-21 13:53:14.802552: step: 456/530, loss: 0.0029067995492368937
2023-01-21 13:53:15.995935: step: 460/530, loss: 0.0010534286266192794
2023-01-21 13:53:17.179842: step: 464/530, loss: 1.9073485191256623e-06
2023-01-21 13:53:18.418167: step: 468/530, loss: 0.0004135131894145161
2023-01-21 13:53:19.671446: step: 472/530, loss: 0.0010515212779864669
2023-01-21 13:53:20.813089: step: 476/530, loss: 6.10351571594947e-06
2023-01-21 13:53:22.001518: step: 480/530, loss: 0.0002742767392192036
2023-01-21 13:53:23.162716: step: 484/530, loss: 0.005839633755385876
2023-01-21 13:53:24.340094: step: 488/530, loss: 0.0009885787731036544
2023-01-21 13:53:25.522897: step: 492/530, loss: 2.059936559817288e-05
2023-01-21 13:53:26.724234: step: 496/530, loss: -1.430511474609375e-05
2023-01-21 13:53:27.910588: step: 500/530, loss: 0.004357337951660156
2023-01-21 13:53:29.101207: step: 504/530, loss: 0.00020256043353583664
2023-01-21 13:53:30.272810: step: 508/530, loss: 0.00032167433528229594
2023-01-21 13:53:31.445512: step: 512/530, loss: 3.1948089599609375e-05
2023-01-21 13:53:32.600059: step: 516/530, loss: 0.0009796142112463713
2023-01-21 13:53:33.804945: step: 520/530, loss: 2.8371810913085938e-05
2023-01-21 13:53:34.962530: step: 524/530, loss: 0.0570131354033947
2023-01-21 13:53:36.163277: step: 528/530, loss: 4.081726001459174e-05
2023-01-21 13:53:37.373296: step: 532/530, loss: 1.8787384760798886e-05
2023-01-21 13:53:38.553002: step: 536/530, loss: 0.004150390625
2023-01-21 13:53:39.721804: step: 540/530, loss: 3.14712519866589e-06
2023-01-21 13:53:40.897682: step: 544/530, loss: 9.5367431640625e-07
2023-01-21 13:53:42.073146: step: 548/530, loss: 0.0017355919117107987
2023-01-21 13:53:43.234358: step: 552/530, loss: 0.04094123840332031
2023-01-21 13:53:44.402248: step: 556/530, loss: 3.0517585400957614e-06
2023-01-21 13:53:45.607656: step: 560/530, loss: 0.08593368530273438
2023-01-21 13:53:46.770711: step: 564/530, loss: 0.00010757445852505043
2023-01-21 13:53:47.937726: step: 568/530, loss: 6.675720101156912e-07
2023-01-21 13:53:49.092180: step: 572/530, loss: 1.0204315003647935e-05
2023-01-21 13:53:50.270051: step: 576/530, loss: 0.0035228729248046875
2023-01-21 13:53:51.463738: step: 580/530, loss: 0.24749116599559784
2023-01-21 13:53:52.621935: step: 584/530, loss: 0.003583812853321433
2023-01-21 13:53:53.787666: step: 588/530, loss: -4.2915345943583816e-07
2023-01-21 13:53:54.956248: step: 592/530, loss: 0.04141292721033096
2023-01-21 13:53:56.126402: step: 596/530, loss: 0.0002520561101846397
2023-01-21 13:53:57.265121: step: 600/530, loss: 0.0040562632493674755
2023-01-21 13:53:58.437578: step: 604/530, loss: 0.0001661300630075857
2023-01-21 13:53:59.598741: step: 608/530, loss: 1.7070769899873994e-05
2023-01-21 13:54:00.779572: step: 612/530, loss: 0.0006566047668457031
2023-01-21 13:54:01.954905: step: 616/530, loss: -1.373290979245212e-05
2023-01-21 13:54:03.117878: step: 620/530, loss: 8.754729788051918e-05
2023-01-21 13:54:04.288659: step: 624/530, loss: 0.02286529541015625
2023-01-21 13:54:05.453810: step: 628/530, loss: 0.001042366144247353
2023-01-21 13:54:06.654820: step: 632/530, loss: 0.004548836033791304
2023-01-21 13:54:07.839527: step: 636/530, loss: 6.84738188283518e-05
2023-01-21 13:54:08.984548: step: 640/530, loss: 0.0026903152465820312
2023-01-21 13:54:10.166036: step: 644/530, loss: 0.030205916613340378
2023-01-21 13:54:11.360563: step: 648/530, loss: 0.04602985456585884
2023-01-21 13:54:12.575439: step: 652/530, loss: 0.10034985095262527
2023-01-21 13:54:13.735000: step: 656/530, loss: 3.0517578125e-05
2023-01-21 13:54:14.883659: step: 660/530, loss: 0.00026607513427734375
2023-01-21 13:54:16.086224: step: 664/530, loss: 0.00036792753962799907
2023-01-21 13:54:17.239149: step: 668/530, loss: 0.06706103682518005
2023-01-21 13:54:18.378884: step: 672/530, loss: 0.006276160478591919
2023-01-21 13:54:19.555977: step: 676/530, loss: 9.346009392174892e-06
2023-01-21 13:54:20.713332: step: 680/530, loss: 8.182526653399691e-05
2023-01-21 13:54:21.926113: step: 684/530, loss: 0.00019803046598099172
2023-01-21 13:54:23.030124: step: 688/530, loss: 0.0021015643142163754
2023-01-21 13:54:24.223940: step: 692/530, loss: 0.00011692046973621473
2023-01-21 13:54:25.374626: step: 696/530, loss: 0.001840019365772605
2023-01-21 13:54:26.555315: step: 700/530, loss: 0.007706690113991499
2023-01-21 13:54:27.801400: step: 704/530, loss: 0.00015344620624091476
2023-01-21 13:54:28.984290: step: 708/530, loss: 6.065368506824598e-05
2023-01-21 13:54:30.145372: step: 712/530, loss: 0.01141433697193861
2023-01-21 13:54:31.329792: step: 716/530, loss: 0.02528552897274494
2023-01-21 13:54:32.534416: step: 720/530, loss: 0.0014438629150390625
2023-01-21 13:54:33.756501: step: 724/530, loss: 5.0830840336857364e-05
2023-01-21 13:54:34.957259: step: 728/530, loss: -2.2983551389188506e-05
2023-01-21 13:54:36.132012: step: 732/530, loss: 2.1934511096333154e-06
2023-01-21 13:54:37.314094: step: 736/530, loss: 1.5354156857938506e-05
2023-01-21 13:54:38.501640: step: 740/530, loss: 0.0019367217319086194
2023-01-21 13:54:39.655421: step: 744/530, loss: 0.04069080203771591
2023-01-21 13:54:40.837928: step: 748/530, loss: 0.0002922058047261089
2023-01-21 13:54:42.018577: step: 752/530, loss: 0.001455593155696988
2023-01-21 13:54:43.197607: step: 756/530, loss: 0.00019226073345635086
2023-01-21 13:54:44.381017: step: 760/530, loss: 0.02594890631735325
2023-01-21 13:54:45.590972: step: 764/530, loss: 0.0003811836359091103
2023-01-21 13:54:46.766188: step: 768/530, loss: 0.00017986298189498484
2023-01-21 13:54:47.930140: step: 772/530, loss: 0.0012166977394372225
2023-01-21 13:54:49.147861: step: 776/530, loss: 8.010864985408261e-05
2023-01-21 13:54:50.281839: step: 780/530, loss: 0.00016984940157271922
2023-01-21 13:54:51.459407: step: 784/530, loss: 0.0003554344002623111
2023-01-21 13:54:52.641803: step: 788/530, loss: 0.00036554335383698344
2023-01-21 13:54:53.792623: step: 792/530, loss: 0.0010256767272949219
2023-01-21 13:54:54.948952: step: 796/530, loss: 0.0005213349941186607
2023-01-21 13:54:56.096033: step: 800/530, loss: 1.602172778802924e-05
2023-01-21 13:54:57.235494: step: 804/530, loss: 1.8215179807157256e-05
2023-01-21 13:54:58.396623: step: 808/530, loss: -6.771088010282256e-06
2023-01-21 13:54:59.569655: step: 812/530, loss: 0.00036449433537200093
2023-01-21 13:55:00.721907: step: 816/530, loss: 0.0028724311850965023
2023-01-21 13:55:01.894448: step: 820/530, loss: 4.38690176451928e-06
2023-01-21 13:55:03.103935: step: 824/530, loss: 0.0005382538074627519
2023-01-21 13:55:04.326300: step: 828/530, loss: 0.006535148713737726
2023-01-21 13:55:05.478142: step: 832/530, loss: 5.722046125811175e-07
2023-01-21 13:55:06.677331: step: 836/530, loss: 2.136230432370212e-05
2023-01-21 13:55:07.856592: step: 840/530, loss: 1.9073486328125e-05
2023-01-21 13:55:09.059260: step: 844/530, loss: 0.2399924397468567
2023-01-21 13:55:10.224466: step: 848/530, loss: 0.00017642974853515625
2023-01-21 13:55:11.370316: step: 852/530, loss: 0.0009315491188317537
2023-01-21 13:55:12.523905: step: 856/530, loss: 3.814697265625e-06
2023-01-21 13:55:13.690071: step: 860/530, loss: 7.772445314913057e-06
2023-01-21 13:55:14.842603: step: 864/530, loss: 0.08931998908519745
2023-01-21 13:55:16.024699: step: 868/530, loss: 0.00010604858834994957
2023-01-21 13:55:17.223795: step: 872/530, loss: 0.06591244041919708
2023-01-21 13:55:18.413972: step: 876/530, loss: 0.00011148452904308215
2023-01-21 13:55:19.624655: step: 880/530, loss: 1.6975403923424892e-05
2023-01-21 13:55:20.815151: step: 884/530, loss: 0.013180924579501152
2023-01-21 13:55:22.002291: step: 888/530, loss: 2.4223329091910273e-05
2023-01-21 13:55:23.163898: step: 892/530, loss: 0.0005052566411904991
2023-01-21 13:55:24.372636: step: 896/530, loss: 8.068084571277723e-05
2023-01-21 13:55:25.482854: step: 900/530, loss: 0.13582110404968262
2023-01-21 13:55:26.638374: step: 904/530, loss: 0.00046348574687726796
2023-01-21 13:55:27.835204: step: 908/530, loss: 0.00021095277043059468
2023-01-21 13:55:28.994586: step: 912/530, loss: 0.00795822124928236
2023-01-21 13:55:30.122172: step: 916/530, loss: 0.16425706446170807
2023-01-21 13:55:31.281867: step: 920/530, loss: 0.21882934868335724
2023-01-21 13:55:32.464838: step: 924/530, loss: 1.7547608877066523e-05
2023-01-21 13:55:33.630780: step: 928/530, loss: 0.00507087679579854
2023-01-21 13:55:34.821545: step: 932/530, loss: 0.004935646429657936
2023-01-21 13:55:36.005027: step: 936/530, loss: 0.0003787994501180947
2023-01-21 13:55:37.201207: step: 940/530, loss: 0.0007572174072265625
2023-01-21 13:55:38.404176: step: 944/530, loss: 0.036307621747255325
2023-01-21 13:55:39.585320: step: 948/530, loss: 4.196167537884321e-06
2023-01-21 13:55:40.758376: step: 952/530, loss: 0.01940155029296875
2023-01-21 13:55:41.942486: step: 956/530, loss: 0.0023254393599927425
2023-01-21 13:55:43.152073: step: 960/530, loss: 0.00016078949556685984
2023-01-21 13:55:44.318370: step: 964/530, loss: 0.00016059876361396164
2023-01-21 13:55:45.522635: step: 968/530, loss: 0.004443454556167126
2023-01-21 13:55:46.702833: step: 972/530, loss: 0.01424484234303236
2023-01-21 13:55:47.901484: step: 976/530, loss: 0.040998175740242004
2023-01-21 13:55:49.112024: step: 980/530, loss: 0.013793183490633965
2023-01-21 13:55:50.312138: step: 984/530, loss: 3.328323509776965e-05
2023-01-21 13:55:51.464968: step: 988/530, loss: 7.028579420875758e-05
2023-01-21 13:55:52.653791: step: 992/530, loss: 0.005992317106574774
2023-01-21 13:55:53.840057: step: 996/530, loss: 1.2588501704158261e-05
2023-01-21 13:55:55.036228: step: 1000/530, loss: 0.0009240627405233681
2023-01-21 13:55:56.184894: step: 1004/530, loss: 9.5367431640625e-07
2023-01-21 13:55:57.369885: step: 1008/530, loss: 0.024341583251953125
2023-01-21 13:55:58.571084: step: 1012/530, loss: 0.05434875562787056
2023-01-21 13:55:59.787752: step: 1016/530, loss: 1.659393274167087e-05
2023-01-21 13:56:00.961216: step: 1020/530, loss: 0.001986599061638117
2023-01-21 13:56:02.131258: step: 1024/530, loss: 0.0003702164103742689
2023-01-21 13:56:03.300370: step: 1028/530, loss: -4.76837158203125e-07
2023-01-21 13:56:04.467342: step: 1032/530, loss: 0.002497005509212613
2023-01-21 13:56:05.653792: step: 1036/530, loss: 0.008041191846132278
2023-01-21 13:56:06.813621: step: 1040/530, loss: 0.0037450790405273438
2023-01-21 13:56:08.023860: step: 1044/530, loss: 3.032684253412299e-05
2023-01-21 13:56:09.179032: step: 1048/530, loss: 0.0004096984921488911
2023-01-21 13:56:10.362697: step: 1052/530, loss: 0.0015766144497320056
2023-01-21 13:56:11.539846: step: 1056/530, loss: 0.013672351837158203
2023-01-21 13:56:12.748956: step: 1060/530, loss: 0.0008726119995117188
2023-01-21 13:56:13.929071: step: 1064/530, loss: 8.778572373557836e-05
2023-01-21 13:56:15.146927: step: 1068/530, loss: 0.04264412075281143
2023-01-21 13:56:16.330931: step: 1072/530, loss: 1.7166138377433526e-06
2023-01-21 13:56:17.479105: step: 1076/530, loss: 0.03991241380572319
2023-01-21 13:56:18.630824: step: 1080/530, loss: 2.498626781743951e-05
2023-01-21 13:56:19.796719: step: 1084/530, loss: 9.5367431640625e-07
2023-01-21 13:56:20.955423: step: 1088/530, loss: 0.00010881424532271922
2023-01-21 13:56:22.121106: step: 1092/530, loss: 0.00028629304142668843
2023-01-21 13:56:23.351548: step: 1096/530, loss: 0.0003783225838560611
2023-01-21 13:56:24.554189: step: 1100/530, loss: 0.00022563934908248484
2023-01-21 13:56:25.680778: step: 1104/530, loss: 0.0025642395485192537
2023-01-21 13:56:26.838569: step: 1108/530, loss: 0.0002099990815622732
2023-01-21 13:56:28.028476: step: 1112/530, loss: 0.0004987716674804688
2023-01-21 13:56:29.226076: step: 1116/530, loss: -1.9073486328125e-06
2023-01-21 13:56:30.385627: step: 1120/530, loss: 0.003844356629997492
2023-01-21 13:56:31.565291: step: 1124/530, loss: 0.11600160598754883
2023-01-21 13:56:32.728519: step: 1128/530, loss: 0.002038288163021207
2023-01-21 13:56:33.874224: step: 1132/530, loss: 0.005327797029167414
2023-01-21 13:56:35.086916: step: 1136/530, loss: -5.722044988942798e-07
2023-01-21 13:56:36.230368: step: 1140/530, loss: 0.014038467779755592
2023-01-21 13:56:37.435522: step: 1144/530, loss: 0.017444420605897903
2023-01-21 13:56:38.598129: step: 1148/530, loss: 6.637573096668348e-05
2023-01-21 13:56:39.774981: step: 1152/530, loss: 0.00552978552877903
2023-01-21 13:56:40.957349: step: 1156/530, loss: 1.411438006471144e-05
2023-01-21 13:56:42.097845: step: 1160/530, loss: 0.0004173278866801411
2023-01-21 13:56:43.246474: step: 1164/530, loss: 0.0005161285516805947
2023-01-21 13:56:44.407776: step: 1168/530, loss: 1.831054760259576e-05
2023-01-21 13:56:45.603575: step: 1172/530, loss: 0.0017156600952148438
2023-01-21 13:56:46.829482: step: 1176/530, loss: 9.460448927711695e-05
2023-01-21 13:56:47.959548: step: 1180/530, loss: 0.0008845329284667969
2023-01-21 13:56:49.150306: step: 1184/530, loss: 7.305145118152723e-05
2023-01-21 13:56:50.351107: step: 1188/530, loss: 0.013806152157485485
2023-01-21 13:56:51.522233: step: 1192/530, loss: 0.1845572590827942
2023-01-21 13:56:52.683700: step: 1196/530, loss: 0.0011671066749840975
2023-01-21 13:56:53.888784: step: 1200/530, loss: 0.00014991761418059468
2023-01-21 13:56:55.096041: step: 1204/530, loss: 0.003384542418643832
2023-01-21 13:56:56.270995: step: 1208/530, loss: 0.00027980803861282766
2023-01-21 13:56:57.386662: step: 1212/530, loss: 0.022311020642518997
2023-01-21 13:56:58.575232: step: 1216/530, loss: 4.4822695599577855e-06
2023-01-21 13:56:59.823110: step: 1220/530, loss: 0.00020141602726653218
2023-01-21 13:57:01.029315: step: 1224/530, loss: 7.085800461936742e-05
2023-01-21 13:57:02.229363: step: 1228/530, loss: 0.001888275146484375
2023-01-21 13:57:03.438631: step: 1232/530, loss: 0.023880766704678535
2023-01-21 13:57:04.590510: step: 1236/530, loss: 0.0007135391933843493
2023-01-21 13:57:05.754024: step: 1240/530, loss: 0.00010433197167003527
2023-01-21 13:57:06.919760: step: 1244/530, loss: 6.332397606456652e-05
2023-01-21 13:57:08.113302: step: 1248/530, loss: 0.02476673200726509
2023-01-21 13:57:09.251020: step: 1252/530, loss: 0.0003673553292173892
2023-01-21 13:57:10.433700: step: 1256/530, loss: 0.0006803512806072831
2023-01-21 13:57:11.575286: step: 1260/530, loss: 0.00018367767916060984
2023-01-21 13:57:12.771140: step: 1264/530, loss: 6.294250852079131e-06
2023-01-21 13:57:13.949040: step: 1268/530, loss: 0.0031463622581213713
2023-01-21 13:57:15.113038: step: 1272/530, loss: 0.0005197525024414062
2023-01-21 13:57:16.329598: step: 1276/530, loss: 0.00027718543424271047
2023-01-21 13:57:17.493041: step: 1280/530, loss: -1.9073486612342094e-07
2023-01-21 13:57:18.627556: step: 1284/530, loss: 9.346007573185489e-06
2023-01-21 13:57:19.793376: step: 1288/530, loss: 1.1444091796875e-05
2023-01-21 13:57:20.974843: step: 1292/530, loss: 8.125304884742945e-05
2023-01-21 13:57:22.147151: step: 1296/530, loss: 0.0008970260387286544
2023-01-21 13:57:23.351962: step: 1300/530, loss: 0.0032665252219885588
2023-01-21 13:57:24.505249: step: 1304/530, loss: 0.01168289128690958
2023-01-21 13:57:25.701359: step: 1308/530, loss: 0.004407310858368874
2023-01-21 13:57:26.918688: step: 1312/530, loss: 0.005623626988381147
2023-01-21 13:57:28.127957: step: 1316/530, loss: 0.0002190590021200478
2023-01-21 13:57:29.294037: step: 1320/530, loss: 3.657341221696697e-05
2023-01-21 13:57:30.490979: step: 1324/530, loss: 0.00010948181443382055
2023-01-21 13:57:31.617007: step: 1328/530, loss: 0.007991408929228783
2023-01-21 13:57:32.765019: step: 1332/530, loss: 0.00017862320237327367
2023-01-21 13:57:33.947232: step: 1336/530, loss: 0.0006183624500408769
2023-01-21 13:57:35.186227: step: 1340/530, loss: 0.00026721955509856343
2023-01-21 13:57:36.334239: step: 1344/530, loss: 7.61032133596018e-05
2023-01-21 13:57:37.526657: step: 1348/530, loss: 0.00025501250638626516
2023-01-21 13:57:38.722977: step: 1352/530, loss: 0.02398242987692356
2023-01-21 13:57:39.920050: step: 1356/530, loss: 0.005943107884377241
2023-01-21 13:57:41.129541: step: 1360/530, loss: 0.0102081298828125
2023-01-21 13:57:42.321003: step: 1364/530, loss: 0.011873865500092506
2023-01-21 13:57:43.479646: step: 1368/530, loss: 6.29425048828125e-05
2023-01-21 13:57:44.665995: step: 1372/530, loss: 0.0014804840320721269
2023-01-21 13:57:45.863465: step: 1376/530, loss: 0.0049648284912109375
2023-01-21 13:57:47.038768: step: 1380/530, loss: 5.145073009771295e-05
2023-01-21 13:57:48.222371: step: 1384/530, loss: 3.995895167463459e-05
2023-01-21 13:57:49.377694: step: 1388/530, loss: 2.7084352041129023e-05
2023-01-21 13:57:50.544161: step: 1392/530, loss: 0.0013572692405432463
2023-01-21 13:57:51.717287: step: 1396/530, loss: 9.440183930564672e-05
2023-01-21 13:57:52.868808: step: 1400/530, loss: 0.0005758285406045616
2023-01-21 13:57:54.052734: step: 1404/530, loss: 0.0029203894082456827
2023-01-21 13:57:55.253497: step: 1408/530, loss: 0.0056747435592114925
2023-01-21 13:57:56.495651: step: 1412/530, loss: 0.0018299103248864412
2023-01-21 13:57:57.671620: step: 1416/530, loss: 0.00022201538376975805
2023-01-21 13:57:58.830313: step: 1420/530, loss: -6.532669431180693e-06
2023-01-21 13:57:59.955714: step: 1424/530, loss: 1.430511474609375e-06
2023-01-21 13:58:01.114341: step: 1428/530, loss: 0.0007806777721270919
2023-01-21 13:58:02.321326: step: 1432/530, loss: 0.0001430511474609375
2023-01-21 13:58:03.562346: step: 1436/530, loss: 0.025507165119051933
2023-01-21 13:58:04.730645: step: 1440/530, loss: 0.005219364073127508
2023-01-21 13:58:05.915134: step: 1444/530, loss: 0.003677559085190296
2023-01-21 13:58:07.103983: step: 1448/530, loss: 1.4781952813791577e-05
2023-01-21 13:58:08.251813: step: 1452/530, loss: 1.5258789289873675e-06
2023-01-21 13:58:09.449691: step: 1456/530, loss: 9.298324584960938e-05
2023-01-21 13:58:10.602792: step: 1460/530, loss: -6.675720669591101e-07
2023-01-21 13:58:11.821848: step: 1464/530, loss: -9.059906005859375e-06
2023-01-21 13:58:13.025075: step: 1468/530, loss: 0.008012866601347923
2023-01-21 13:58:14.236752: step: 1472/530, loss: 0.00022373200044967234
2023-01-21 13:58:15.433552: step: 1476/530, loss: 0.007389616686850786
2023-01-21 13:58:16.578242: step: 1480/530, loss: 0.02299499697983265
2023-01-21 13:58:17.763016: step: 1484/530, loss: 0.0001958847133209929
2023-01-21 13:58:18.971517: step: 1488/530, loss: 0.004261589143425226
2023-01-21 13:58:20.186505: step: 1492/530, loss: 0.00020780562772415578
2023-01-21 13:58:21.338629: step: 1496/530, loss: 8.139610145008191e-05
2023-01-21 13:58:22.484795: step: 1500/530, loss: 0.0020116805098950863
2023-01-21 13:58:23.706153: step: 1504/530, loss: 0.03600320965051651
2023-01-21 13:58:24.891813: step: 1508/530, loss: 0.009292221628129482
2023-01-21 13:58:26.085309: step: 1512/530, loss: 0.0004786968056578189
2023-01-21 13:58:27.267009: step: 1516/530, loss: 0.019435741007328033
2023-01-21 13:58:28.427121: step: 1520/530, loss: 0.0002419471857137978
2023-01-21 13:58:29.617283: step: 1524/530, loss: 0.004563617520034313
2023-01-21 13:58:30.830862: step: 1528/530, loss: 0.04167766496539116
2023-01-21 13:58:31.992664: step: 1532/530, loss: 9.841918654274195e-05
2023-01-21 13:58:33.123370: step: 1536/530, loss: 0.00012369155592750758
2023-01-21 13:58:34.301474: step: 1540/530, loss: 0.0001038074551615864
2023-01-21 13:58:35.469178: step: 1544/530, loss: 0.08750343322753906
2023-01-21 13:58:36.656682: step: 1548/530, loss: 0.0005702972994185984
2023-01-21 13:58:37.889913: step: 1552/530, loss: 0.00012092590623069555
2023-01-21 13:58:39.081408: step: 1556/530, loss: 0.0005222320323809981
2023-01-21 13:58:40.244586: step: 1560/530, loss: 1.7547608877066523e-05
2023-01-21 13:58:41.383181: step: 1564/530, loss: 0.0005163192981854081
2023-01-21 13:58:42.583804: step: 1568/530, loss: 3.8814549043308944e-05
2023-01-21 13:58:43.711851: step: 1572/530, loss: 0.00011787414405262098
2023-01-21 13:58:44.880382: step: 1576/530, loss: 0.015435123816132545
2023-01-21 13:58:46.038776: step: 1580/530, loss: 0.0011412620078772306
2023-01-21 13:58:47.255124: step: 1584/530, loss: 0.07253475487232208
2023-01-21 13:58:48.447623: step: 1588/530, loss: 0.0007831574184820056
2023-01-21 13:58:49.589105: step: 1592/530, loss: 0.0033389092423021793
2023-01-21 13:58:50.756182: step: 1596/530, loss: 0.0004299163992982358
2023-01-21 13:58:51.976887: step: 1600/530, loss: 0.0006494522094726562
2023-01-21 13:58:53.169203: step: 1604/530, loss: 0.0002834320184774697
2023-01-21 13:58:54.344792: step: 1608/530, loss: 0.00012321471876930445
2023-01-21 13:58:55.557647: step: 1612/530, loss: 0.04742469638586044
2023-01-21 13:58:56.753984: step: 1616/530, loss: 0.000179290771484375
2023-01-21 13:58:57.892165: step: 1620/530, loss: 1.773834264895413e-05
2023-01-21 13:58:59.054693: step: 1624/530, loss: 0.08136377483606339
2023-01-21 13:59:00.206359: step: 1628/530, loss: 0.00038900377694517374
2023-01-21 13:59:01.412163: step: 1632/530, loss: 0.030256273224949837
2023-01-21 13:59:02.578947: step: 1636/530, loss: 0.0012609482510015368
2023-01-21 13:59:03.743135: step: 1640/530, loss: 0.003018951276317239
2023-01-21 13:59:04.914721: step: 1644/530, loss: 0.0014301299815997481
2023-01-21 13:59:06.190708: step: 1648/530, loss: 0.00031490327091887593
2023-01-21 13:59:07.363815: step: 1652/530, loss: 0.0003257751523051411
2023-01-21 13:59:08.505369: step: 1656/530, loss: 7.133484177757055e-05
2023-01-21 13:59:09.687640: step: 1660/530, loss: 0.0004219055117573589
2023-01-21 13:59:10.828020: step: 1664/530, loss: 0.039891913533210754
2023-01-21 13:59:12.103440: step: 1668/530, loss: 0.0017008304130285978
2023-01-21 13:59:13.309442: step: 1672/530, loss: 0.02526683919131756
2023-01-21 13:59:14.485640: step: 1676/530, loss: 2.4271012080134824e-05
2023-01-21 13:59:15.649562: step: 1680/530, loss: 8.640289161121473e-05
2023-01-21 13:59:16.794157: step: 1684/530, loss: 0.00032749175443314016
2023-01-21 13:59:17.999593: step: 1688/530, loss: 2.326965295651462e-05
2023-01-21 13:59:19.210460: step: 1692/530, loss: 0.006415272131562233
2023-01-21 13:59:20.364263: step: 1696/530, loss: 0.0003487110079731792
2023-01-21 13:59:21.562294: step: 1700/530, loss: 2.9850007194909267e-05
2023-01-21 13:59:22.731340: step: 1704/530, loss: 0.01628255844116211
2023-01-21 13:59:23.920442: step: 1708/530, loss: 0.048612214624881744
2023-01-21 13:59:25.098330: step: 1712/530, loss: 2.3412703740177676e-05
2023-01-21 13:59:26.282301: step: 1716/530, loss: 0.00526504497975111
2023-01-21 13:59:27.471271: step: 1720/530, loss: 0.00026836394681595266
2023-01-21 13:59:28.663372: step: 1724/530, loss: 0.0010107040870934725
2023-01-21 13:59:29.827433: step: 1728/530, loss: 0.007612800691276789
2023-01-21 13:59:30.961665: step: 1732/530, loss: 2.47955322265625e-05
2023-01-21 13:59:32.151759: step: 1736/530, loss: 9.117126319324598e-05
2023-01-21 13:59:33.338835: step: 1740/530, loss: 0.0017866134876385331
2023-01-21 13:59:34.539635: step: 1744/530, loss: 0.013206672854721546
2023-01-21 13:59:35.721593: step: 1748/530, loss: 1.144409225162235e-06
2023-01-21 13:59:36.922922: step: 1752/530, loss: 1.506805438111769e-05
2023-01-21 13:59:38.082463: step: 1756/530, loss: 1.8215179807157256e-05
2023-01-21 13:59:39.272922: step: 1760/530, loss: 0.000735855137463659
2023-01-21 13:59:40.442700: step: 1764/530, loss: 5.702972339349799e-05
2023-01-21 13:59:41.627597: step: 1768/530, loss: 0.031631093472242355
2023-01-21 13:59:42.841246: step: 1772/530, loss: 0.029294490814208984
2023-01-21 13:59:44.010296: step: 1776/530, loss: 0.040686845779418945
2023-01-21 13:59:45.141816: step: 1780/530, loss: 5.6934357417048886e-05
2023-01-21 13:59:46.308924: step: 1784/530, loss: 0.022653676569461823
2023-01-21 13:59:47.524527: step: 1788/530, loss: 0.0002642631297931075
2023-01-21 13:59:48.651065: step: 1792/530, loss: 0.006672334857285023
2023-01-21 13:59:49.810337: step: 1796/530, loss: 0.041307639330625534
2023-01-21 13:59:51.002480: step: 1800/530, loss: 0.0008560181013308465
2023-01-21 13:59:52.152780: step: 1804/530, loss: 4.911423093290068e-05
2023-01-21 13:59:53.355216: step: 1808/530, loss: 4.0531158447265625e-06
2023-01-21 13:59:54.543732: step: 1812/530, loss: 0.002923965686932206
2023-01-21 13:59:55.733929: step: 1816/530, loss: 0.00022010803513694555
2023-01-21 13:59:56.883524: step: 1820/530, loss: 0.052977368235588074
2023-01-21 13:59:58.040644: step: 1824/530, loss: 6.29425048828125e-05
2023-01-21 13:59:59.214079: step: 1828/530, loss: 0.04450187832117081
2023-01-21 14:00:00.401505: step: 1832/530, loss: 0.0009071350796148181
2023-01-21 14:00:01.595562: step: 1836/530, loss: 0.005719495005905628
2023-01-21 14:00:02.778539: step: 1840/530, loss: 0.0035389901604503393
2023-01-21 14:00:03.948559: step: 1844/530, loss: 0.00225582136772573
2023-01-21 14:00:05.127354: step: 1848/530, loss: 0.00020542144193314016
2023-01-21 14:00:06.318095: step: 1852/530, loss: 0.0027408599853515625
2023-01-21 14:00:07.507808: step: 1856/530, loss: -0.0
2023-01-21 14:00:08.722436: step: 1860/530, loss: 0.0010612488258630037
2023-01-21 14:00:09.895861: step: 1864/530, loss: 0.0031875609420239925
2023-01-21 14:00:11.177135: step: 1868/530, loss: 0.024716569110751152
2023-01-21 14:00:12.349648: step: 1872/530, loss: 0.003655815264210105
2023-01-21 14:00:13.545171: step: 1876/530, loss: 0.0016331672668457031
2023-01-21 14:00:14.715077: step: 1880/530, loss: 0.0018974303966388106
2023-01-21 14:00:15.887217: step: 1884/530, loss: 0.0013987065758556128
2023-01-21 14:00:17.079008: step: 1888/530, loss: 0.0005106925964355469
2023-01-21 14:00:18.298667: step: 1892/530, loss: -1.392364538332913e-05
2023-01-21 14:00:19.442182: step: 1896/530, loss: 0.00018005371384788305
2023-01-21 14:00:20.640487: step: 1900/530, loss: 0.01983346976339817
2023-01-21 14:00:21.872915: step: 1904/530, loss: 5.8460234868107364e-05
2023-01-21 14:00:23.107630: step: 1908/530, loss: -2.708435022213962e-05
2023-01-21 14:00:24.285002: step: 1912/530, loss: 0.0031436921562999487
2023-01-21 14:00:25.475062: step: 1916/530, loss: 0.03290868178009987
2023-01-21 14:00:26.694023: step: 1920/530, loss: 0.03983325883746147
2023-01-21 14:00:27.854913: step: 1924/530, loss: 0.010126017965376377
2023-01-21 14:00:29.023881: step: 1928/530, loss: 0.01784348487854004
2023-01-21 14:00:30.227421: step: 1932/530, loss: 0.012363815680146217
2023-01-21 14:00:31.395107: step: 1936/530, loss: 0.0004967689164914191
2023-01-21 14:00:32.564497: step: 1940/530, loss: 0.0001873016299214214
2023-01-21 14:00:33.760169: step: 1944/530, loss: 0.0019415856804698706
2023-01-21 14:00:34.924965: step: 1948/530, loss: 9.298324584960938e-05
2023-01-21 14:00:36.116075: step: 1952/530, loss: 5.683898780262098e-05
2023-01-21 14:00:37.268656: step: 1956/530, loss: 0.00019340515427757055
2023-01-21 14:00:38.401738: step: 1960/530, loss: 0.030147897079586983
2023-01-21 14:00:39.602756: step: 1964/530, loss: 0.07901906967163086
2023-01-21 14:00:40.778111: step: 1968/530, loss: 0.0003911018429789692
2023-01-21 14:00:41.979187: step: 1972/530, loss: 0.00030362606048583984
2023-01-21 14:00:43.145301: step: 1976/530, loss: 0.04544582590460777
2023-01-21 14:00:44.294423: step: 1980/530, loss: 0.0032825469970703125
2023-01-21 14:00:45.435794: step: 1984/530, loss: 0.043270111083984375
2023-01-21 14:00:46.640949: step: 1988/530, loss: 7.801055471645668e-05
2023-01-21 14:00:47.838581: step: 1992/530, loss: 0.03510646894574165
2023-01-21 14:00:49.006718: step: 1996/530, loss: 0.0034122467041015625
2023-01-21 14:00:50.184829: step: 2000/530, loss: 0.0005594253307208419
2023-01-21 14:00:51.352017: step: 2004/530, loss: 5.493163916980848e-05
2023-01-21 14:00:52.521532: step: 2008/530, loss: 2.1457672119140625e-06
2023-01-21 14:00:53.698977: step: 2012/530, loss: 0.047719959169626236
2023-01-21 14:00:54.828277: step: 2016/530, loss: 0.00013847350783180445
2023-01-21 14:00:55.976786: step: 2020/530, loss: 7.762909081066027e-05
2023-01-21 14:00:57.115472: step: 2024/530, loss: 0.00016536712064407766
2023-01-21 14:00:58.294967: step: 2028/530, loss: 0.00013652147026732564
2023-01-21 14:00:59.466086: step: 2032/530, loss: 0.000762939453125
2023-01-21 14:01:00.656896: step: 2036/530, loss: -1.811981746868696e-06
2023-01-21 14:01:01.832536: step: 2040/530, loss: 9.241103543899953e-05
2023-01-21 14:01:03.031495: step: 2044/530, loss: 0.005942249670624733
2023-01-21 14:01:04.183829: step: 2048/530, loss: 0.0001508712739450857
2023-01-21 14:01:05.402822: step: 2052/530, loss: 0.04231433942914009
2023-01-21 14:01:06.558771: step: 2056/530, loss: 0.0025626658461987972
2023-01-21 14:01:07.771229: step: 2060/530, loss: 0.017107581719756126
2023-01-21 14:01:08.957831: step: 2064/530, loss: 0.0030672072898596525
2023-01-21 14:01:10.110741: step: 2068/530, loss: 0.4188602566719055
2023-01-21 14:01:11.277321: step: 2072/530, loss: -9.536742595628311e-08
2023-01-21 14:01:12.491438: step: 2076/530, loss: 5.302429053699598e-05
2023-01-21 14:01:13.663093: step: 2080/530, loss: 0.5609552264213562
2023-01-21 14:01:14.840511: step: 2084/530, loss: 0.026812173426151276
2023-01-21 14:01:16.037555: step: 2088/530, loss: 0.006197548005729914
2023-01-21 14:01:17.149148: step: 2092/530, loss: 8.668899681651965e-05
2023-01-21 14:01:18.336896: step: 2096/530, loss: 0.05037679523229599
2023-01-21 14:01:19.520165: step: 2100/530, loss: 1.711845470708795e-05
2023-01-21 14:01:20.727303: step: 2104/530, loss: 7.62939453125e-06
2023-01-21 14:01:21.892663: step: 2108/530, loss: 1.287460349885805e-06
2023-01-21 14:01:23.077811: step: 2112/530, loss: -1.716613724056515e-06
2023-01-21 14:01:24.263921: step: 2116/530, loss: 0.0001663207949604839
2023-01-21 14:01:25.448571: step: 2120/530, loss: 0.02290496975183487
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.6156316916488223, 'r': 0.7656458055925432, 'f1': 0.6824925816023738}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6636665087636191, 'r': 0.8056354226566993, 'f1': 0.7277922077922078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.550561797752809, 'r': 0.9074074074074074, 'f1': 0.6853146853146853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.47619047619047616, 'f1': 0.5555555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}