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([231, 450])
>>> trigger_label_ffn.layers.1.bias: torch.Size([231])
>>> trigger_crf.transition: torch.Size([233, 233])
n_trainable_params: 560510152, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:23:10.378500: step: 4/533, loss: 13.145635604858398
2023-01-22 23:23:11.568243: step: 8/533, loss: 19.22907829284668
2023-01-22 23:23:12.742274: step: 12/533, loss: 12.959906578063965
2023-01-22 23:23:13.896496: step: 16/533, loss: 4.805675506591797
2023-01-22 23:23:15.059742: step: 20/533, loss: 14.847404479980469
2023-01-22 23:23:16.217364: step: 24/533, loss: 25.32388687133789
2023-01-22 23:23:17.388981: step: 28/533, loss: 12.053035736083984
2023-01-22 23:23:18.560982: step: 32/533, loss: 17.16490364074707
2023-01-22 23:23:19.737047: step: 36/533, loss: 14.677508354187012
2023-01-22 23:23:20.900489: step: 40/533, loss: 3.136167049407959
2023-01-22 23:23:22.080247: step: 44/533, loss: 3.092291831970215
2023-01-22 23:23:23.261479: step: 48/533, loss: 5.116755485534668
2023-01-22 23:23:24.421805: step: 52/533, loss: 8.502379417419434
2023-01-22 23:23:25.599642: step: 56/533, loss: 16.00510025024414
2023-01-22 23:23:26.741044: step: 60/533, loss: 2.2202422618865967
2023-01-22 23:23:27.887337: step: 64/533, loss: 13.906517028808594
2023-01-22 23:23:29.087651: step: 68/533, loss: 4.964485168457031
2023-01-22 23:23:30.263714: step: 72/533, loss: 3.6854076385498047
2023-01-22 23:23:31.439994: step: 76/533, loss: 4.585338592529297
2023-01-22 23:23:32.624737: step: 80/533, loss: 20.101791381835938
2023-01-22 23:23:33.811487: step: 84/533, loss: 6.803764343261719
2023-01-22 23:23:34.998770: step: 88/533, loss: 4.213061332702637
2023-01-22 23:23:36.124872: step: 92/533, loss: 9.807540893554688
2023-01-22 23:23:37.261763: step: 96/533, loss: 3.6892173290252686
2023-01-22 23:23:38.407901: step: 100/533, loss: 14.63908576965332
2023-01-22 23:23:39.567946: step: 104/533, loss: 3.5595526695251465
2023-01-22 23:23:40.725530: step: 108/533, loss: 2.4618730545043945
2023-01-22 23:23:41.927661: step: 112/533, loss: 10.619168281555176
2023-01-22 23:23:43.122491: step: 116/533, loss: 14.758976936340332
2023-01-22 23:23:44.278097: step: 120/533, loss: 22.126323699951172
2023-01-22 23:23:45.490544: step: 124/533, loss: 14.038152694702148
2023-01-22 23:23:46.629248: step: 128/533, loss: 1.9014348983764648
2023-01-22 23:23:47.802254: step: 132/533, loss: 10.615972518920898
2023-01-22 23:23:48.953789: step: 136/533, loss: 7.768258094787598
2023-01-22 23:23:50.103977: step: 140/533, loss: 2.7860686779022217
2023-01-22 23:23:51.243370: step: 144/533, loss: 18.730642318725586
2023-01-22 23:23:52.484416: step: 148/533, loss: 3.895756483078003
2023-01-22 23:23:53.621544: step: 152/533, loss: 17.74464225769043
2023-01-22 23:23:54.794750: step: 156/533, loss: 10.170475006103516
2023-01-22 23:23:55.998248: step: 160/533, loss: 5.223288536071777
2023-01-22 23:23:57.214579: step: 164/533, loss: 2.46091890335083
2023-01-22 23:23:58.391676: step: 168/533, loss: 4.119781494140625
2023-01-22 23:23:59.590742: step: 172/533, loss: 11.421395301818848
2023-01-22 23:24:00.732290: step: 176/533, loss: 12.13332748413086
2023-01-22 23:24:01.892038: step: 180/533, loss: 13.479781150817871
2023-01-22 23:24:03.072834: step: 184/533, loss: 2.916821002960205
2023-01-22 23:24:04.253916: step: 188/533, loss: 14.945432662963867
2023-01-22 23:24:05.457127: step: 192/533, loss: 3.467480182647705
2023-01-22 23:24:06.647554: step: 196/533, loss: 19.44829750061035
2023-01-22 23:24:07.815817: step: 200/533, loss: 3.2405571937561035
2023-01-22 23:24:09.022361: step: 204/533, loss: 18.749374389648438
2023-01-22 23:24:10.187293: step: 208/533, loss: 10.947992324829102
2023-01-22 23:24:11.339057: step: 212/533, loss: 12.88017749786377
2023-01-22 23:24:12.528526: step: 216/533, loss: 11.977092742919922
2023-01-22 23:24:13.694808: step: 220/533, loss: 12.171873092651367
2023-01-22 23:24:14.916923: step: 224/533, loss: 22.430875778198242
2023-01-22 23:24:16.031378: step: 228/533, loss: 8.519892692565918
2023-01-22 23:24:17.207754: step: 232/533, loss: 10.795780181884766
2023-01-22 23:24:18.349593: step: 236/533, loss: 3.2259273529052734
2023-01-22 23:24:19.504250: step: 240/533, loss: 11.365700721740723
2023-01-22 23:24:20.684993: step: 244/533, loss: 3.0791263580322266
2023-01-22 23:24:21.847721: step: 248/533, loss: 1.945581078529358
2023-01-22 23:24:23.030812: step: 252/533, loss: 32.50908660888672
2023-01-22 23:24:24.216915: step: 256/533, loss: 19.508695602416992
2023-01-22 23:24:25.414598: step: 260/533, loss: 9.221532821655273
2023-01-22 23:24:26.603911: step: 264/533, loss: 2.031940460205078
2023-01-22 23:24:27.786954: step: 268/533, loss: 2.9496140480041504
2023-01-22 23:24:28.946079: step: 272/533, loss: 5.251761436462402
2023-01-22 23:24:30.154123: step: 276/533, loss: 2.8276400566101074
2023-01-22 23:24:31.321286: step: 280/533, loss: 5.040543556213379
2023-01-22 23:24:32.496837: step: 284/533, loss: 14.219460487365723
2023-01-22 23:24:33.690876: step: 288/533, loss: 2.935567855834961
2023-01-22 23:24:34.857745: step: 292/533, loss: 3.5496878623962402
2023-01-22 23:24:36.064710: step: 296/533, loss: 16.49407196044922
2023-01-22 23:24:37.269961: step: 300/533, loss: 19.036121368408203
2023-01-22 23:24:38.452232: step: 304/533, loss: 2.9939088821411133
2023-01-22 23:24:39.707210: step: 308/533, loss: 4.264180660247803
2023-01-22 23:24:40.901429: step: 312/533, loss: 22.403202056884766
2023-01-22 23:24:42.059002: step: 316/533, loss: 2.887939691543579
2023-01-22 23:24:43.222708: step: 320/533, loss: 4.152337074279785
2023-01-22 23:24:44.388878: step: 324/533, loss: 3.6799814701080322
2023-01-22 23:24:45.561812: step: 328/533, loss: 37.86791229248047
2023-01-22 23:24:46.748024: step: 332/533, loss: 2.171797037124634
2023-01-22 23:24:47.945461: step: 336/533, loss: 16.571880340576172
2023-01-22 23:24:49.131720: step: 340/533, loss: 25.26451873779297
2023-01-22 23:24:50.328666: step: 344/533, loss: 20.807138442993164
2023-01-22 23:24:51.497719: step: 348/533, loss: 2.651780843734741
2023-01-22 23:24:52.679539: step: 352/533, loss: 19.05449676513672
2023-01-22 23:24:53.858271: step: 356/533, loss: 19.279260635375977
2023-01-22 23:24:55.010881: step: 360/533, loss: 4.750474452972412
2023-01-22 23:24:56.182291: step: 364/533, loss: 6.298741340637207
2023-01-22 23:24:57.382582: step: 368/533, loss: 7.545099258422852
2023-01-22 23:24:58.527285: step: 372/533, loss: 2.0527303218841553
2023-01-22 23:24:59.685407: step: 376/533, loss: 7.285812854766846
2023-01-22 23:25:00.847060: step: 380/533, loss: 6.0223188400268555
2023-01-22 23:25:01.988926: step: 384/533, loss: 5.087244510650635
2023-01-22 23:25:03.186361: step: 388/533, loss: 3.4977898597717285
2023-01-22 23:25:04.369998: step: 392/533, loss: 3.954305648803711
2023-01-22 23:25:05.545486: step: 396/533, loss: 6.2261738777160645
2023-01-22 23:25:06.707351: step: 400/533, loss: 2.483565330505371
2023-01-22 23:25:07.906072: step: 404/533, loss: 3.413839817047119
2023-01-22 23:25:09.103610: step: 408/533, loss: 3.6666359901428223
2023-01-22 23:25:10.319166: step: 412/533, loss: 4.7104339599609375
2023-01-22 23:25:11.549850: step: 416/533, loss: 3.085981845855713
2023-01-22 23:25:12.730832: step: 420/533, loss: 2.365067720413208
2023-01-22 23:25:13.915799: step: 424/533, loss: 3.2868666648864746
2023-01-22 23:25:15.091683: step: 428/533, loss: 4.227965831756592
2023-01-22 23:25:16.250946: step: 432/533, loss: 8.1939115524292
2023-01-22 23:25:17.436671: step: 436/533, loss: 2.514676094055176
2023-01-22 23:25:18.596216: step: 440/533, loss: 18.518136978149414
2023-01-22 23:25:19.799522: step: 444/533, loss: 13.300690650939941
2023-01-22 23:25:20.979489: step: 448/533, loss: 15.62561321258545
2023-01-22 23:25:22.162166: step: 452/533, loss: 5.538820743560791
2023-01-22 23:25:23.317510: step: 456/533, loss: 6.011515140533447
2023-01-22 23:25:24.512142: step: 460/533, loss: 13.365700721740723
2023-01-22 23:25:25.703564: step: 464/533, loss: 16.098880767822266
2023-01-22 23:25:26.897812: step: 468/533, loss: 8.444330215454102
2023-01-22 23:25:28.112005: step: 472/533, loss: 17.922931671142578
2023-01-22 23:25:29.284822: step: 476/533, loss: 2.046785593032837
2023-01-22 23:25:30.498002: step: 480/533, loss: 13.46902084350586
2023-01-22 23:25:31.687743: step: 484/533, loss: 15.22579288482666
2023-01-22 23:25:32.835398: step: 488/533, loss: 1.474422574043274
2023-01-22 23:25:34.019216: step: 492/533, loss: 2.030651807785034
2023-01-22 23:25:35.178628: step: 496/533, loss: 7.230257987976074
2023-01-22 23:25:36.339063: step: 500/533, loss: 9.662696838378906
2023-01-22 23:25:37.500918: step: 504/533, loss: 12.307378768920898
2023-01-22 23:25:38.709322: step: 508/533, loss: 6.826079368591309
2023-01-22 23:25:39.873847: step: 512/533, loss: 2.6584668159484863
2023-01-22 23:25:41.058976: step: 516/533, loss: 6.260522842407227
2023-01-22 23:25:42.274372: step: 520/533, loss: 6.591512203216553
2023-01-22 23:25:43.427000: step: 524/533, loss: 0.7286615967750549
2023-01-22 23:25:44.609445: step: 528/533, loss: 2.6164960861206055
2023-01-22 23:25:45.798474: step: 532/533, loss: 1.4323185682296753
2023-01-22 23:25:46.923484: step: 536/533, loss: 1.4544968605041504
2023-01-22 23:25:48.144389: step: 540/533, loss: 5.8127617835998535
2023-01-22 23:25:49.331604: step: 544/533, loss: 1.2871625423431396
2023-01-22 23:25:50.497649: step: 548/533, loss: 1.926548719406128
2023-01-22 23:25:51.662154: step: 552/533, loss: 1.577078938484192
2023-01-22 23:25:52.884718: step: 556/533, loss: 4.6855998039245605
2023-01-22 23:25:54.068157: step: 560/533, loss: 5.157561779022217
2023-01-22 23:25:55.267827: step: 564/533, loss: 1.6243854761123657
2023-01-22 23:25:56.443382: step: 568/533, loss: 1.0705506801605225
2023-01-22 23:25:57.614026: step: 572/533, loss: 4.837060451507568
2023-01-22 23:25:58.790343: step: 576/533, loss: 3.3355207443237305
2023-01-22 23:25:59.967539: step: 580/533, loss: 1.5827611684799194
2023-01-22 23:26:01.129615: step: 584/533, loss: 1.5407795906066895
2023-01-22 23:26:02.316988: step: 588/533, loss: 1.5949573516845703
2023-01-22 23:26:03.468122: step: 592/533, loss: 8.876623153686523
2023-01-22 23:26:04.695962: step: 596/533, loss: 0.9607012867927551
2023-01-22 23:26:05.894798: step: 600/533, loss: 0.6043447256088257
2023-01-22 23:26:07.040214: step: 604/533, loss: 1.9733870029449463
2023-01-22 23:26:08.231243: step: 608/533, loss: 0.6224600076675415
2023-01-22 23:26:09.425701: step: 612/533, loss: 2.3000543117523193
2023-01-22 23:26:10.640646: step: 616/533, loss: 2.936113119125366
2023-01-22 23:26:11.792598: step: 620/533, loss: 0.7199267148971558
2023-01-22 23:26:12.942380: step: 624/533, loss: 1.7188756465911865
2023-01-22 23:26:14.127451: step: 628/533, loss: 3.489527702331543
2023-01-22 23:26:15.270215: step: 632/533, loss: 2.524557113647461
2023-01-22 23:26:16.436274: step: 636/533, loss: 1.7253302335739136
2023-01-22 23:26:17.583320: step: 640/533, loss: 0.2792018949985504
2023-01-22 23:26:18.734052: step: 644/533, loss: 8.905596733093262
2023-01-22 23:26:19.900619: step: 648/533, loss: 0.6786611080169678
2023-01-22 23:26:21.089597: step: 652/533, loss: 2.0452775955200195
2023-01-22 23:26:22.275188: step: 656/533, loss: 0.5380074977874756
2023-01-22 23:26:23.452142: step: 660/533, loss: 2.289801836013794
2023-01-22 23:26:24.592790: step: 664/533, loss: 0.36594659090042114
2023-01-22 23:26:25.757672: step: 668/533, loss: 2.646902084350586
2023-01-22 23:26:26.920328: step: 672/533, loss: 0.4852398931980133
2023-01-22 23:26:28.114842: step: 676/533, loss: 4.140330791473389
2023-01-22 23:26:29.287853: step: 680/533, loss: 0.5002164840698242
2023-01-22 23:26:30.450782: step: 684/533, loss: 2.7602343559265137
2023-01-22 23:26:31.622425: step: 688/533, loss: 4.075169563293457
2023-01-22 23:26:32.826362: step: 692/533, loss: 0.9605245590209961
2023-01-22 23:26:34.025932: step: 696/533, loss: 3.2553060054779053
2023-01-22 23:26:35.226441: step: 700/533, loss: 2.454166889190674
2023-01-22 23:26:36.398773: step: 704/533, loss: 0.664567768573761
2023-01-22 23:26:37.594834: step: 708/533, loss: 1.123242735862732
2023-01-22 23:26:38.727102: step: 712/533, loss: 0.6399648785591125
2023-01-22 23:26:39.901789: step: 716/533, loss: 5.524782657623291
2023-01-22 23:26:41.072615: step: 720/533, loss: 1.5474045276641846
2023-01-22 23:26:42.251361: step: 724/533, loss: 1.0461201667785645
2023-01-22 23:26:43.416952: step: 728/533, loss: 0.6861740350723267
2023-01-22 23:26:44.579965: step: 732/533, loss: 1.4719107151031494
2023-01-22 23:26:45.742273: step: 736/533, loss: 2.194241523742676
2023-01-22 23:26:46.950007: step: 740/533, loss: 0.322665274143219
2023-01-22 23:26:48.112997: step: 744/533, loss: 1.455559492111206
2023-01-22 23:26:49.282225: step: 748/533, loss: 1.8877043724060059
2023-01-22 23:26:50.455733: step: 752/533, loss: 1.974555492401123
2023-01-22 23:26:51.644271: step: 756/533, loss: 0.6265078783035278
2023-01-22 23:26:52.826912: step: 760/533, loss: 0.35264188051223755
2023-01-22 23:26:54.004675: step: 764/533, loss: 0.7506839036941528
2023-01-22 23:26:55.194224: step: 768/533, loss: 2.4636168479919434
2023-01-22 23:26:56.363072: step: 772/533, loss: 1.1075924634933472
2023-01-22 23:26:57.542973: step: 776/533, loss: 0.8517844676971436
2023-01-22 23:26:58.711062: step: 780/533, loss: 1.1073848009109497
2023-01-22 23:26:59.892766: step: 784/533, loss: 2.039799690246582
2023-01-22 23:27:01.069025: step: 788/533, loss: 0.1933211386203766
2023-01-22 23:27:02.216986: step: 792/533, loss: 6.374067783355713
2023-01-22 23:27:03.372919: step: 796/533, loss: 0.2266598343849182
2023-01-22 23:27:04.561930: step: 800/533, loss: 4.059456825256348
2023-01-22 23:27:05.743340: step: 804/533, loss: 1.0205544233322144
2023-01-22 23:27:06.897776: step: 808/533, loss: 2.309664726257324
2023-01-22 23:27:08.061080: step: 812/533, loss: 3.5434622764587402
2023-01-22 23:27:09.212506: step: 816/533, loss: 0.23684760928153992
2023-01-22 23:27:10.353774: step: 820/533, loss: 1.341080904006958
2023-01-22 23:27:11.549029: step: 824/533, loss: 0.9833893179893494
2023-01-22 23:27:12.708961: step: 828/533, loss: 1.579512596130371
2023-01-22 23:27:13.884077: step: 832/533, loss: 0.3956812024116516
2023-01-22 23:27:15.074419: step: 836/533, loss: 1.6221565008163452
2023-01-22 23:27:16.245619: step: 840/533, loss: 1.349205732345581
2023-01-22 23:27:17.485493: step: 844/533, loss: 1.8290324211120605
2023-01-22 23:27:18.611683: step: 848/533, loss: 0.8911094069480896
2023-01-22 23:27:19.779313: step: 852/533, loss: 0.6542081832885742
2023-01-22 23:27:20.955730: step: 856/533, loss: 1.627138614654541
2023-01-22 23:27:22.154312: step: 860/533, loss: 0.5866850018501282
2023-01-22 23:27:23.299427: step: 864/533, loss: 1.0946797132492065
2023-01-22 23:27:24.472640: step: 868/533, loss: 1.0102338790893555
2023-01-22 23:27:25.652452: step: 872/533, loss: 1.191148281097412
2023-01-22 23:27:26.814293: step: 876/533, loss: 0.5396867990493774
2023-01-22 23:27:28.012596: step: 880/533, loss: 2.4249701499938965
2023-01-22 23:27:29.196262: step: 884/533, loss: 7.279786109924316
2023-01-22 23:27:30.389724: step: 888/533, loss: 2.475615978240967
2023-01-22 23:27:31.521245: step: 892/533, loss: 0.5411392450332642
2023-01-22 23:27:32.731027: step: 896/533, loss: 0.5999356508255005
2023-01-22 23:27:33.926581: step: 900/533, loss: 2.413778066635132
2023-01-22 23:27:35.115251: step: 904/533, loss: 1.3172987699508667
2023-01-22 23:27:36.312239: step: 908/533, loss: 0.8468945026397705
2023-01-22 23:27:37.509451: step: 912/533, loss: 4.539299011230469
2023-01-22 23:27:38.679314: step: 916/533, loss: 1.444950819015503
2023-01-22 23:27:39.854238: step: 920/533, loss: 1.354472279548645
2023-01-22 23:27:41.040513: step: 924/533, loss: 0.6375842690467834
2023-01-22 23:27:42.218476: step: 928/533, loss: 2.4856770038604736
2023-01-22 23:27:43.400163: step: 932/533, loss: 0.8675698637962341
2023-01-22 23:27:44.605654: step: 936/533, loss: 1.526894211769104
2023-01-22 23:27:45.766052: step: 940/533, loss: 2.504338502883911
2023-01-22 23:27:46.978504: step: 944/533, loss: 0.5813045501708984
2023-01-22 23:27:48.167868: step: 948/533, loss: 0.29295188188552856
2023-01-22 23:27:49.364708: step: 952/533, loss: 7.454026222229004
2023-01-22 23:27:50.503681: step: 956/533, loss: 0.6717919111251831
2023-01-22 23:27:51.679192: step: 960/533, loss: 0.5095861554145813
2023-01-22 23:27:52.860469: step: 964/533, loss: 3.4565818309783936
2023-01-22 23:27:54.041244: step: 968/533, loss: 1.2004553079605103
2023-01-22 23:27:55.206361: step: 972/533, loss: 1.4490216970443726
2023-01-22 23:27:56.384794: step: 976/533, loss: 1.7319591045379639
2023-01-22 23:27:57.552599: step: 980/533, loss: 0.34661394357681274
2023-01-22 23:27:58.732544: step: 984/533, loss: 0.7132916450500488
2023-01-22 23:27:59.948233: step: 988/533, loss: 1.4547441005706787
2023-01-22 23:28:01.105520: step: 992/533, loss: 1.3637043237686157
2023-01-22 23:28:02.267353: step: 996/533, loss: 1.6559770107269287
2023-01-22 23:28:03.428538: step: 1000/533, loss: 1.0394364595413208
2023-01-22 23:28:04.581709: step: 1004/533, loss: 0.6348270177841187
2023-01-22 23:28:05.777252: step: 1008/533, loss: 0.40477514266967773
2023-01-22 23:28:06.998451: step: 1012/533, loss: 0.8926259875297546
2023-01-22 23:28:08.143022: step: 1016/533, loss: 0.346503883600235
2023-01-22 23:28:09.321306: step: 1020/533, loss: 0.2392118275165558
2023-01-22 23:28:10.490762: step: 1024/533, loss: 4.181270122528076
2023-01-22 23:28:11.644095: step: 1028/533, loss: 0.36705470085144043
2023-01-22 23:28:12.798346: step: 1032/533, loss: 2.478487014770508
2023-01-22 23:28:13.909872: step: 1036/533, loss: 3.8078560829162598
2023-01-22 23:28:15.073701: step: 1040/533, loss: 1.1824283599853516
2023-01-22 23:28:16.261768: step: 1044/533, loss: 1.399385690689087
2023-01-22 23:28:17.427197: step: 1048/533, loss: 2.3647425174713135
2023-01-22 23:28:18.620854: step: 1052/533, loss: 1.3252263069152832
2023-01-22 23:28:19.788498: step: 1056/533, loss: 0.5123209953308105
2023-01-22 23:28:20.948717: step: 1060/533, loss: 0.6275076270103455
2023-01-22 23:28:22.119002: step: 1064/533, loss: 1.1519665718078613
2023-01-22 23:28:23.291306: step: 1068/533, loss: 2.201920509338379
2023-01-22 23:28:24.425207: step: 1072/533, loss: 0.4908309578895569
2023-01-22 23:28:25.580151: step: 1076/533, loss: 2.691150665283203
2023-01-22 23:28:26.716927: step: 1080/533, loss: 0.522924542427063
2023-01-22 23:28:27.930024: step: 1084/533, loss: 0.7473450303077698
2023-01-22 23:28:29.101683: step: 1088/533, loss: 1.4121553897857666
2023-01-22 23:28:30.268962: step: 1092/533, loss: 1.576360821723938
2023-01-22 23:28:31.490431: step: 1096/533, loss: 0.37594738602638245
2023-01-22 23:28:32.670491: step: 1100/533, loss: 3.142935276031494
2023-01-22 23:28:33.835305: step: 1104/533, loss: 0.5358239412307739
2023-01-22 23:28:35.044672: step: 1108/533, loss: 0.6444010138511658
2023-01-22 23:28:36.232885: step: 1112/533, loss: 0.528475284576416
2023-01-22 23:28:37.388830: step: 1116/533, loss: 0.28249630331993103
2023-01-22 23:28:38.558663: step: 1120/533, loss: 0.6195205450057983
2023-01-22 23:28:39.751717: step: 1124/533, loss: 0.550328254699707
2023-01-22 23:28:40.896180: step: 1128/533, loss: 0.569743275642395
2023-01-22 23:28:42.076764: step: 1132/533, loss: 3.132331609725952
2023-01-22 23:28:43.280335: step: 1136/533, loss: 0.27634888887405396
2023-01-22 23:28:44.520665: step: 1140/533, loss: 3.176569938659668
2023-01-22 23:28:45.713815: step: 1144/533, loss: 0.6582551002502441
2023-01-22 23:28:46.854952: step: 1148/533, loss: 0.46856653690338135
2023-01-22 23:28:48.110193: step: 1152/533, loss: 1.2697393894195557
2023-01-22 23:28:49.320319: step: 1156/533, loss: 1.2549058198928833
2023-01-22 23:28:50.572547: step: 1160/533, loss: 1.1552642583847046
2023-01-22 23:28:51.726758: step: 1164/533, loss: 2.0883054733276367
2023-01-22 23:28:52.900819: step: 1168/533, loss: 1.2584812641143799
2023-01-22 23:28:54.072515: step: 1172/533, loss: 0.6239482760429382
2023-01-22 23:28:55.240349: step: 1176/533, loss: 0.8790833353996277
2023-01-22 23:28:56.399801: step: 1180/533, loss: 2.6410627365112305
2023-01-22 23:28:57.553409: step: 1184/533, loss: 1.0360885858535767
2023-01-22 23:28:58.694703: step: 1188/533, loss: 0.12752699851989746
2023-01-22 23:28:59.871785: step: 1192/533, loss: 0.23638108372688293
2023-01-22 23:29:01.097830: step: 1196/533, loss: 2.8699378967285156
2023-01-22 23:29:02.280706: step: 1200/533, loss: 0.7668875455856323
2023-01-22 23:29:03.469103: step: 1204/533, loss: 0.5818021893501282
2023-01-22 23:29:04.694542: step: 1208/533, loss: 0.13527949154376984
2023-01-22 23:29:05.860200: step: 1212/533, loss: 2.060091972351074
2023-01-22 23:29:06.995973: step: 1216/533, loss: 0.3165915608406067
2023-01-22 23:29:08.177382: step: 1220/533, loss: 2.0273361206054688
2023-01-22 23:29:09.350998: step: 1224/533, loss: 1.0736255645751953
2023-01-22 23:29:10.521911: step: 1228/533, loss: 1.0269742012023926
2023-01-22 23:29:11.700094: step: 1232/533, loss: 1.7775332927703857
2023-01-22 23:29:12.927097: step: 1236/533, loss: 1.2202086448669434
2023-01-22 23:29:14.125855: step: 1240/533, loss: 2.08382511138916
2023-01-22 23:29:15.308175: step: 1244/533, loss: 2.4972329139709473
2023-01-22 23:29:16.484870: step: 1248/533, loss: 0.4306202530860901
2023-01-22 23:29:17.668050: step: 1252/533, loss: 4.437713146209717
2023-01-22 23:29:18.797514: step: 1256/533, loss: 1.4629840850830078
2023-01-22 23:29:19.997050: step: 1260/533, loss: 2.1052424907684326
2023-01-22 23:29:21.203684: step: 1264/533, loss: 1.056288480758667
2023-01-22 23:29:22.398046: step: 1268/533, loss: 3.5432915687561035
2023-01-22 23:29:23.561084: step: 1272/533, loss: 1.5018134117126465
2023-01-22 23:29:24.774082: step: 1276/533, loss: 3.1959073543548584
2023-01-22 23:29:25.940053: step: 1280/533, loss: 3.9127073287963867
2023-01-22 23:29:27.120086: step: 1284/533, loss: 0.6725099086761475
2023-01-22 23:29:28.289958: step: 1288/533, loss: 0.5000278353691101
2023-01-22 23:29:29.487440: step: 1292/533, loss: 1.617366909980774
2023-01-22 23:29:30.683440: step: 1296/533, loss: 0.34270036220550537
2023-01-22 23:29:31.799216: step: 1300/533, loss: 0.2997363209724426
2023-01-22 23:29:32.971529: step: 1304/533, loss: 1.3547724485397339
2023-01-22 23:29:34.171717: step: 1308/533, loss: 0.3017137050628662
2023-01-22 23:29:35.320631: step: 1312/533, loss: 0.2045232355594635
2023-01-22 23:29:36.471687: step: 1316/533, loss: 1.3004283905029297
2023-01-22 23:29:37.664516: step: 1320/533, loss: 3.418627977371216
2023-01-22 23:29:38.867241: step: 1324/533, loss: 0.5456693172454834
2023-01-22 23:29:40.040402: step: 1328/533, loss: 0.9518420696258545
2023-01-22 23:29:41.258661: step: 1332/533, loss: 3.071730613708496
2023-01-22 23:29:42.424123: step: 1336/533, loss: 0.6783522367477417
2023-01-22 23:29:43.607296: step: 1340/533, loss: 0.475480318069458
2023-01-22 23:29:44.797389: step: 1344/533, loss: 0.5549815893173218
2023-01-22 23:29:45.940742: step: 1348/533, loss: 0.425025075674057
2023-01-22 23:29:47.129633: step: 1352/533, loss: 2.243117332458496
2023-01-22 23:29:48.314941: step: 1356/533, loss: 1.3087692260742188
2023-01-22 23:29:49.527311: step: 1360/533, loss: 1.550156593322754
2023-01-22 23:29:50.676009: step: 1364/533, loss: 1.8158907890319824
2023-01-22 23:29:51.866953: step: 1368/533, loss: 1.799782156944275
2023-01-22 23:29:53.035023: step: 1372/533, loss: 0.27897748351097107
2023-01-22 23:29:54.234449: step: 1376/533, loss: 0.5272464752197266
2023-01-22 23:29:55.391951: step: 1380/533, loss: 0.848552405834198
2023-01-22 23:29:56.592387: step: 1384/533, loss: 1.9821054935455322
2023-01-22 23:29:57.758343: step: 1388/533, loss: 2.0987937450408936
2023-01-22 23:29:58.933768: step: 1392/533, loss: 0.6874128580093384
2023-01-22 23:30:00.102026: step: 1396/533, loss: 7.185245037078857
2023-01-22 23:30:01.353745: step: 1400/533, loss: 0.46852028369903564
2023-01-22 23:30:02.519193: step: 1404/533, loss: 0.7313648462295532
2023-01-22 23:30:03.664871: step: 1408/533, loss: 0.3206093907356262
2023-01-22 23:30:04.823216: step: 1412/533, loss: 0.7183647155761719
2023-01-22 23:30:05.988615: step: 1416/533, loss: 1.5642496347427368
2023-01-22 23:30:07.184486: step: 1420/533, loss: 0.3313596844673157
2023-01-22 23:30:08.382099: step: 1424/533, loss: 0.8808186054229736
2023-01-22 23:30:09.560990: step: 1428/533, loss: 0.5782290697097778
2023-01-22 23:30:10.746912: step: 1432/533, loss: 0.38926661014556885
2023-01-22 23:30:11.934389: step: 1436/533, loss: 0.5657832026481628
2023-01-22 23:30:13.086426: step: 1440/533, loss: 1.0370789766311646
2023-01-22 23:30:14.258560: step: 1444/533, loss: 1.1857184171676636
2023-01-22 23:30:15.423465: step: 1448/533, loss: 0.3721585273742676
2023-01-22 23:30:16.647728: step: 1452/533, loss: 1.4785434007644653
2023-01-22 23:30:17.909529: step: 1456/533, loss: 1.6584553718566895
2023-01-22 23:30:19.095572: step: 1460/533, loss: 0.3198855519294739
2023-01-22 23:30:20.249870: step: 1464/533, loss: 0.4314543604850769
2023-01-22 23:30:21.403860: step: 1468/533, loss: 0.7182348370552063
2023-01-22 23:30:22.584330: step: 1472/533, loss: 0.4239721894264221
2023-01-22 23:30:23.741134: step: 1476/533, loss: 0.26039448380470276
2023-01-22 23:30:24.919274: step: 1480/533, loss: 0.7978843450546265
2023-01-22 23:30:26.110175: step: 1484/533, loss: 0.7496509552001953
2023-01-22 23:30:27.276237: step: 1488/533, loss: 0.46709907054901123
2023-01-22 23:30:28.441982: step: 1492/533, loss: 0.4759085774421692
2023-01-22 23:30:29.632998: step: 1496/533, loss: 0.3654235899448395
2023-01-22 23:30:30.774337: step: 1500/533, loss: 0.4483720064163208
2023-01-22 23:30:31.990160: step: 1504/533, loss: 1.3782504796981812
2023-01-22 23:30:33.206576: step: 1508/533, loss: 0.40954285860061646
2023-01-22 23:30:34.365455: step: 1512/533, loss: 1.1658687591552734
2023-01-22 23:30:35.576303: step: 1516/533, loss: 2.2199409008026123
2023-01-22 23:30:36.775787: step: 1520/533, loss: 1.2348964214324951
2023-01-22 23:30:37.964564: step: 1524/533, loss: 0.43148165941238403
2023-01-22 23:30:39.141994: step: 1528/533, loss: 0.45100802183151245
2023-01-22 23:30:40.322493: step: 1532/533, loss: 0.6193769574165344
2023-01-22 23:30:41.559652: step: 1536/533, loss: 1.130348801612854
2023-01-22 23:30:42.711578: step: 1540/533, loss: 1.2036304473876953
2023-01-22 23:30:43.926164: step: 1544/533, loss: 2.1202661991119385
2023-01-22 23:30:45.152558: step: 1548/533, loss: 2.759725332260132
2023-01-22 23:30:46.360918: step: 1552/533, loss: 0.36631566286087036
2023-01-22 23:30:47.520063: step: 1556/533, loss: 1.2751449346542358
2023-01-22 23:30:48.687813: step: 1560/533, loss: 0.5678756237030029
2023-01-22 23:30:49.857853: step: 1564/533, loss: 0.6512054204940796
2023-01-22 23:30:51.027238: step: 1568/533, loss: 0.5060820579528809
2023-01-22 23:30:52.178731: step: 1572/533, loss: 0.15566979348659515
2023-01-22 23:30:53.341046: step: 1576/533, loss: 1.3091468811035156
2023-01-22 23:30:54.573657: step: 1580/533, loss: 2.03983211517334
2023-01-22 23:30:55.760481: step: 1584/533, loss: 0.13604021072387695
2023-01-22 23:30:56.948308: step: 1588/533, loss: 0.2660253643989563
2023-01-22 23:30:58.113696: step: 1592/533, loss: 1.4109845161437988
2023-01-22 23:30:59.312328: step: 1596/533, loss: 0.35731926560401917
2023-01-22 23:31:00.493108: step: 1600/533, loss: 0.5896186828613281
2023-01-22 23:31:01.669682: step: 1604/533, loss: 0.9611473083496094
2023-01-22 23:31:02.888943: step: 1608/533, loss: 0.33070236444473267
2023-01-22 23:31:04.070917: step: 1612/533, loss: 0.9193414449691772
2023-01-22 23:31:05.195640: step: 1616/533, loss: 0.7878321409225464
2023-01-22 23:31:06.365212: step: 1620/533, loss: 3.335897445678711
2023-01-22 23:31:07.548254: step: 1624/533, loss: 1.4354864358901978
2023-01-22 23:31:08.787218: step: 1628/533, loss: 2.3773746490478516
2023-01-22 23:31:09.951012: step: 1632/533, loss: 1.2009724378585815
2023-01-22 23:31:11.169680: step: 1636/533, loss: 3.2265028953552246
2023-01-22 23:31:12.366481: step: 1640/533, loss: 1.3407931327819824
2023-01-22 23:31:13.542740: step: 1644/533, loss: 1.351318359375
2023-01-22 23:31:14.709436: step: 1648/533, loss: 0.5832690000534058
2023-01-22 23:31:15.895861: step: 1652/533, loss: 1.2264254093170166
2023-01-22 23:31:17.032628: step: 1656/533, loss: 0.9430838227272034
2023-01-22 23:31:18.201514: step: 1660/533, loss: 0.515834629535675
2023-01-22 23:31:19.372441: step: 1664/533, loss: 0.40780550241470337
2023-01-22 23:31:20.558824: step: 1668/533, loss: 7.985874652862549
2023-01-22 23:31:21.729839: step: 1672/533, loss: 0.5383089780807495
2023-01-22 23:31:22.899940: step: 1676/533, loss: 1.4420864582061768
2023-01-22 23:31:24.048726: step: 1680/533, loss: 3.4140679836273193
2023-01-22 23:31:25.199319: step: 1684/533, loss: 0.41258716583251953
2023-01-22 23:31:26.387572: step: 1688/533, loss: 0.3350537419319153
2023-01-22 23:31:27.601582: step: 1692/533, loss: 2.8005568981170654
2023-01-22 23:31:28.744189: step: 1696/533, loss: 0.838647186756134
2023-01-22 23:31:29.907589: step: 1700/533, loss: 1.7298648357391357
2023-01-22 23:31:31.072875: step: 1704/533, loss: 0.2837178707122803
2023-01-22 23:31:32.242173: step: 1708/533, loss: 0.8221243619918823
2023-01-22 23:31:33.409383: step: 1712/533, loss: 0.20631763339042664
2023-01-22 23:31:34.579932: step: 1716/533, loss: 0.4717278480529785
2023-01-22 23:31:35.764640: step: 1720/533, loss: 0.4660990834236145
2023-01-22 23:31:36.930498: step: 1724/533, loss: 1.2459135055541992
2023-01-22 23:31:38.069870: step: 1728/533, loss: 0.8349850177764893
2023-01-22 23:31:39.250397: step: 1732/533, loss: 2.735856771469116
2023-01-22 23:31:40.465025: step: 1736/533, loss: 1.6801704168319702
2023-01-22 23:31:41.623030: step: 1740/533, loss: 0.4961080551147461
2023-01-22 23:31:42.829241: step: 1744/533, loss: 2.493788719177246
2023-01-22 23:31:43.997809: step: 1748/533, loss: 0.5395064353942871
2023-01-22 23:31:45.203550: step: 1752/533, loss: 0.2596380114555359
2023-01-22 23:31:46.379469: step: 1756/533, loss: 0.8152353763580322
2023-01-22 23:31:47.530817: step: 1760/533, loss: 0.2847483158111572
2023-01-22 23:31:48.696028: step: 1764/533, loss: 0.19927635788917542
2023-01-22 23:31:49.851939: step: 1768/533, loss: 0.3931877613067627
2023-01-22 23:31:51.002754: step: 1772/533, loss: 4.3392486572265625
2023-01-22 23:31:52.194098: step: 1776/533, loss: 0.7024887800216675
2023-01-22 23:31:53.370046: step: 1780/533, loss: 0.36346569657325745
2023-01-22 23:31:54.573901: step: 1784/533, loss: 1.6709012985229492
2023-01-22 23:31:55.781072: step: 1788/533, loss: 0.3318673372268677
2023-01-22 23:31:56.961163: step: 1792/533, loss: 2.3311517238616943
2023-01-22 23:31:58.126231: step: 1796/533, loss: 0.8531425595283508
2023-01-22 23:31:59.300431: step: 1800/533, loss: 1.2707364559173584
2023-01-22 23:32:00.463839: step: 1804/533, loss: 0.40326642990112305
2023-01-22 23:32:01.644401: step: 1808/533, loss: 1.4189283847808838
2023-01-22 23:32:02.800612: step: 1812/533, loss: 0.4235231578350067
2023-01-22 23:32:03.987058: step: 1816/533, loss: 1.348684549331665
2023-01-22 23:32:05.202814: step: 1820/533, loss: 1.0400131940841675
2023-01-22 23:32:06.415704: step: 1824/533, loss: 4.387889385223389
2023-01-22 23:32:07.605939: step: 1828/533, loss: 1.3777626752853394
2023-01-22 23:32:08.801003: step: 1832/533, loss: 2.2717339992523193
2023-01-22 23:32:09.951696: step: 1836/533, loss: 0.43283140659332275
2023-01-22 23:32:11.104106: step: 1840/533, loss: 0.73629230260849
2023-01-22 23:32:12.286930: step: 1844/533, loss: 1.5241594314575195
2023-01-22 23:32:13.458338: step: 1848/533, loss: 0.41628575325012207
2023-01-22 23:32:14.670089: step: 1852/533, loss: 0.3854314684867859
2023-01-22 23:32:15.841648: step: 1856/533, loss: 0.9270620942115784
2023-01-22 23:32:17.001122: step: 1860/533, loss: 0.8662399053573608
2023-01-22 23:32:18.204627: step: 1864/533, loss: 0.8201812505722046
2023-01-22 23:32:19.380836: step: 1868/533, loss: 1.4643592834472656
2023-01-22 23:32:20.580520: step: 1872/533, loss: 0.1555122435092926
2023-01-22 23:32:21.736017: step: 1876/533, loss: 0.21470078825950623
2023-01-22 23:32:22.921352: step: 1880/533, loss: 1.4232566356658936
2023-01-22 23:32:24.111532: step: 1884/533, loss: 1.3975878953933716
2023-01-22 23:32:25.278296: step: 1888/533, loss: 0.2776089310646057
2023-01-22 23:32:26.481187: step: 1892/533, loss: 0.5662600994110107
2023-01-22 23:32:27.676457: step: 1896/533, loss: 0.4286738634109497
2023-01-22 23:32:28.844493: step: 1900/533, loss: 0.38017719984054565
2023-01-22 23:32:30.028722: step: 1904/533, loss: 0.6671310663223267
2023-01-22 23:32:31.217409: step: 1908/533, loss: 2.746434450149536
2023-01-22 23:32:32.412103: step: 1912/533, loss: 0.38533443212509155
2023-01-22 23:32:33.618740: step: 1916/533, loss: 1.6261848211288452
2023-01-22 23:32:34.765880: step: 1920/533, loss: 2.455322265625
2023-01-22 23:32:35.885435: step: 1924/533, loss: 0.8101444244384766
2023-01-22 23:32:37.091117: step: 1928/533, loss: 1.4234592914581299
2023-01-22 23:32:38.310430: step: 1932/533, loss: 0.3791810870170593
2023-01-22 23:32:39.490822: step: 1936/533, loss: 1.9108490943908691
2023-01-22 23:32:40.641692: step: 1940/533, loss: 0.273362398147583
2023-01-22 23:32:41.855570: step: 1944/533, loss: 0.7735607624053955
2023-01-22 23:32:43.050008: step: 1948/533, loss: 2.2022252082824707
2023-01-22 23:32:44.243380: step: 1952/533, loss: 0.6361154317855835
2023-01-22 23:32:45.399448: step: 1956/533, loss: 0.5247913599014282
2023-01-22 23:32:46.553078: step: 1960/533, loss: 0.39000555872917175
2023-01-22 23:32:47.735880: step: 1964/533, loss: 1.4923536777496338
2023-01-22 23:32:48.871215: step: 1968/533, loss: 0.4410415589809418
2023-01-22 23:32:50.040309: step: 1972/533, loss: 0.2872112989425659
2023-01-22 23:32:51.187110: step: 1976/533, loss: 1.3799985647201538
2023-01-22 23:32:52.336392: step: 1980/533, loss: 0.9958469271659851
2023-01-22 23:32:53.513295: step: 1984/533, loss: 0.27800047397613525
2023-01-22 23:32:54.686930: step: 1988/533, loss: 0.6145942211151123
2023-01-22 23:32:55.859209: step: 1992/533, loss: 1.2298780679702759
2023-01-22 23:32:57.042174: step: 1996/533, loss: 0.7616209983825684
2023-01-22 23:32:58.183585: step: 2000/533, loss: 0.4867037832736969
2023-01-22 23:32:59.378995: step: 2004/533, loss: 0.22924967110157013
2023-01-22 23:33:00.571170: step: 2008/533, loss: 0.18077389895915985
2023-01-22 23:33:01.738598: step: 2012/533, loss: 0.39582863450050354
2023-01-22 23:33:02.938307: step: 2016/533, loss: 0.3094213604927063
2023-01-22 23:33:04.106029: step: 2020/533, loss: 1.1123430728912354
2023-01-22 23:33:05.281154: step: 2024/533, loss: 2.7838902473449707
2023-01-22 23:33:06.419853: step: 2028/533, loss: 1.039722204208374
2023-01-22 23:33:07.569620: step: 2032/533, loss: 0.9073008894920349
2023-01-22 23:33:08.706836: step: 2036/533, loss: 0.20761491358280182
2023-01-22 23:33:09.861063: step: 2040/533, loss: 0.991794764995575
2023-01-22 23:33:11.018676: step: 2044/533, loss: 0.19815826416015625
2023-01-22 23:33:12.212326: step: 2048/533, loss: 1.2739765644073486
2023-01-22 23:33:13.405659: step: 2052/533, loss: 1.3405394554138184
2023-01-22 23:33:14.524625: step: 2056/533, loss: 1.065006136894226
2023-01-22 23:33:15.688139: step: 2060/533, loss: 1.6213529109954834
2023-01-22 23:33:16.872833: step: 2064/533, loss: 0.235340416431427
2023-01-22 23:33:18.014030: step: 2068/533, loss: 0.31616178154945374
2023-01-22 23:33:19.184724: step: 2072/533, loss: 0.8285520672798157
2023-01-22 23:33:20.371854: step: 2076/533, loss: 1.5899884700775146
2023-01-22 23:33:21.560628: step: 2080/533, loss: 1.8968029022216797
2023-01-22 23:33:22.745128: step: 2084/533, loss: 0.5193651914596558
2023-01-22 23:33:23.905759: step: 2088/533, loss: 1.701128363609314
2023-01-22 23:33:25.059905: step: 2092/533, loss: 0.5211665034294128
2023-01-22 23:33:26.194657: step: 2096/533, loss: 1.4466166496276855
2023-01-22 23:33:27.353900: step: 2100/533, loss: 0.7893010377883911
2023-01-22 23:33:28.505261: step: 2104/533, loss: 0.1537456065416336
2023-01-22 23:33:29.664736: step: 2108/533, loss: 0.9257146716117859
2023-01-22 23:33:30.836845: step: 2112/533, loss: 0.2685169279575348
2023-01-22 23:33:31.996204: step: 2116/533, loss: 0.31897249817848206
2023-01-22 23:33:33.191288: step: 2120/533, loss: 0.20759698748588562
2023-01-22 23:33:34.352704: step: 2124/533, loss: 1.727454662322998
2023-01-22 23:33:35.525815: step: 2128/533, loss: 0.9758910536766052
2023-01-22 23:33:36.715028: step: 2132/533, loss: 0.6938608288764954
==================================================
Loss: 3.352
--------------------
Dev: {'event': {'p': 0.47613636363636364, 'r': 0.5579227696404794, 'f1': 0.5137952176578787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.443666899930021, 'r': 0.4053708439897698, 'f1': 0.4236551954560641}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5384615384615384, 'r': 0.3888888888888889, 'f1': 0.45161290322580644}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.72, 'r': 0.2857142857142857, 'f1': 0.409090909090909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.42105263157894735, 'r': 0.2222222222222222, 'f1': 0.2909090909090909}, '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': 0.47613636363636364, 'r': 0.5579227696404794, 'f1': 0.5137952176578787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.443666899930021, 'r': 0.4053708439897698, 'f1': 0.4236551954560641}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5384615384615384, 'r': 0.3888888888888889, 'f1': 0.45161290322580644}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.47613636363636364, 'r': 0.5579227696404794, 'f1': 0.5137952176578787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.443666899930021, 'r': 0.4053708439897698, 'f1': 0.4236551954560641}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.72, 'r': 0.2857142857142857, 'f1': 0.409090909090909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.47613636363636364, 'r': 0.5579227696404794, 'f1': 0.5137952176578787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.443666899930021, 'r': 0.4053708439897698, 'f1': 0.4236551954560641}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.42105263157894735, 'r': 0.2222222222222222, 'f1': 0.2909090909090909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:34:44.057944: step: 4/533, loss: 1.0354243516921997
2023-01-22 23:34:45.224758: step: 8/533, loss: 0.6560386419296265
2023-01-22 23:34:46.384923: step: 12/533, loss: 0.39212942123413086
2023-01-22 23:34:47.618050: step: 16/533, loss: 2.5404789447784424
2023-01-22 23:34:48.809980: step: 20/533, loss: 0.4714636206626892
2023-01-22 23:34:49.997980: step: 24/533, loss: 0.5660895109176636
2023-01-22 23:34:51.161617: step: 28/533, loss: 0.5721099972724915
2023-01-22 23:34:52.357856: step: 32/533, loss: 2.7766735553741455
2023-01-22 23:34:53.586807: step: 36/533, loss: 0.4042859971523285
2023-01-22 23:34:54.805070: step: 40/533, loss: 0.6899076104164124
2023-01-22 23:34:56.025967: step: 44/533, loss: 0.7919952273368835
2023-01-22 23:34:57.223403: step: 48/533, loss: 6.525989532470703
2023-01-22 23:34:58.381727: step: 52/533, loss: 0.21311740577220917
2023-01-22 23:34:59.550374: step: 56/533, loss: 1.2778058052062988
2023-01-22 23:35:00.766052: step: 60/533, loss: 0.9194133877754211
2023-01-22 23:35:01.920105: step: 64/533, loss: 0.288774311542511
2023-01-22 23:35:03.098923: step: 68/533, loss: 0.13113990426063538
2023-01-22 23:35:04.297728: step: 72/533, loss: 1.1873517036437988
2023-01-22 23:35:05.463860: step: 76/533, loss: 2.0232064723968506
2023-01-22 23:35:06.647836: step: 80/533, loss: 3.1798782348632812
2023-01-22 23:35:07.784624: step: 84/533, loss: 0.3318081498146057
2023-01-22 23:35:08.952343: step: 88/533, loss: 1.6192948818206787
2023-01-22 23:35:10.133002: step: 92/533, loss: 3.523315191268921
2023-01-22 23:35:11.324051: step: 96/533, loss: 1.138803243637085
2023-01-22 23:35:12.490831: step: 100/533, loss: 1.2268428802490234
2023-01-22 23:35:13.649337: step: 104/533, loss: 0.37400999665260315
2023-01-22 23:35:14.835014: step: 108/533, loss: 0.6838157773017883
2023-01-22 23:35:15.999923: step: 112/533, loss: 0.41508930921554565
2023-01-22 23:35:17.163863: step: 116/533, loss: 0.8689453601837158
2023-01-22 23:35:18.336927: step: 120/533, loss: 0.25466614961624146
2023-01-22 23:35:19.530474: step: 124/533, loss: 0.7410454154014587
2023-01-22 23:35:20.674908: step: 128/533, loss: 0.2254638671875
2023-01-22 23:35:21.854592: step: 132/533, loss: 3.513627052307129
2023-01-22 23:35:23.010263: step: 136/533, loss: 0.8366312980651855
2023-01-22 23:35:24.225102: step: 140/533, loss: 0.20423099398612976
2023-01-22 23:35:25.419874: step: 144/533, loss: 0.4385802745819092
2023-01-22 23:35:26.639744: step: 148/533, loss: 1.250146508216858
2023-01-22 23:35:27.788466: step: 152/533, loss: 1.2558205127716064
2023-01-22 23:35:28.968316: step: 156/533, loss: 0.703910231590271
2023-01-22 23:35:30.150786: step: 160/533, loss: 0.6373254656791687
2023-01-22 23:35:31.319605: step: 164/533, loss: 0.928286075592041
2023-01-22 23:35:32.499769: step: 168/533, loss: 0.5824216604232788
2023-01-22 23:35:33.645994: step: 172/533, loss: 0.19328445196151733
2023-01-22 23:35:34.838217: step: 176/533, loss: 0.9951791167259216
2023-01-22 23:35:35.977113: step: 180/533, loss: 0.23292537033557892
2023-01-22 23:35:37.188897: step: 184/533, loss: 0.3331875205039978
2023-01-22 23:35:38.340747: step: 188/533, loss: 0.16349191963672638
2023-01-22 23:35:39.522358: step: 192/533, loss: 2.5099377632141113
2023-01-22 23:35:40.703012: step: 196/533, loss: 0.9419357180595398
2023-01-22 23:35:41.840154: step: 200/533, loss: 0.15835857391357422
2023-01-22 23:35:42.995300: step: 204/533, loss: 0.8913013935089111
2023-01-22 23:35:44.158132: step: 208/533, loss: 0.23131799697875977
2023-01-22 23:35:45.296718: step: 212/533, loss: 0.19361896812915802
2023-01-22 23:35:46.433588: step: 216/533, loss: 2.761167526245117
2023-01-22 23:35:47.602003: step: 220/533, loss: 0.34818974137306213
2023-01-22 23:35:48.761336: step: 224/533, loss: 0.1616200953722
2023-01-22 23:35:49.916124: step: 228/533, loss: 0.3424082398414612
2023-01-22 23:35:51.085693: step: 232/533, loss: 1.104100227355957
2023-01-22 23:35:52.279955: step: 236/533, loss: 0.1488325148820877
2023-01-22 23:35:53.491712: step: 240/533, loss: 0.3915451169013977
2023-01-22 23:35:54.666938: step: 244/533, loss: 0.6880553960800171
2023-01-22 23:35:55.851435: step: 248/533, loss: 0.27069178223609924
2023-01-22 23:35:57.059972: step: 252/533, loss: 0.5047810077667236
2023-01-22 23:35:58.212281: step: 256/533, loss: 2.100074052810669
2023-01-22 23:35:59.374922: step: 260/533, loss: 0.1853216141462326
2023-01-22 23:36:00.565052: step: 264/533, loss: 0.35941487550735474
2023-01-22 23:36:01.753326: step: 268/533, loss: 2.569343090057373
2023-01-22 23:36:02.912701: step: 272/533, loss: 0.566318154335022
2023-01-22 23:36:04.077889: step: 276/533, loss: 0.2727154791355133
2023-01-22 23:36:05.307055: step: 280/533, loss: 2.3410072326660156
2023-01-22 23:36:06.470190: step: 284/533, loss: 0.9303352236747742
2023-01-22 23:36:07.606246: step: 288/533, loss: 0.11808319389820099
2023-01-22 23:36:08.825591: step: 292/533, loss: 1.683610439300537
2023-01-22 23:36:10.004797: step: 296/533, loss: 1.1566574573516846
2023-01-22 23:36:11.204351: step: 300/533, loss: 0.12567663192749023
2023-01-22 23:36:12.393272: step: 304/533, loss: 0.8735305666923523
2023-01-22 23:36:13.545642: step: 308/533, loss: 0.3775220513343811
2023-01-22 23:36:14.701806: step: 312/533, loss: 0.6042418479919434
2023-01-22 23:36:15.864830: step: 316/533, loss: 0.2863849699497223
2023-01-22 23:36:17.014878: step: 320/533, loss: 0.31863218545913696
2023-01-22 23:36:18.199156: step: 324/533, loss: 0.3744821548461914
2023-01-22 23:36:19.362637: step: 328/533, loss: 0.29896843433380127
2023-01-22 23:36:20.556814: step: 332/533, loss: 0.28597211837768555
2023-01-22 23:36:21.731009: step: 336/533, loss: 1.6122771501541138
2023-01-22 23:36:22.890981: step: 340/533, loss: 1.3248423337936401
2023-01-22 23:36:24.050395: step: 344/533, loss: 0.3494013547897339
2023-01-22 23:36:25.269355: step: 348/533, loss: 0.19187764823436737
2023-01-22 23:36:26.417850: step: 352/533, loss: 0.3479959964752197
2023-01-22 23:36:27.579498: step: 356/533, loss: 0.7737563848495483
2023-01-22 23:36:28.756020: step: 360/533, loss: 1.4335170984268188
2023-01-22 23:36:29.903528: step: 364/533, loss: 1.905852198600769
2023-01-22 23:36:31.101522: step: 368/533, loss: 0.3818017244338989
2023-01-22 23:36:32.251627: step: 372/533, loss: 0.49197322130203247
2023-01-22 23:36:33.418077: step: 376/533, loss: 0.14738327264785767
2023-01-22 23:36:34.591255: step: 380/533, loss: 1.6405372619628906
2023-01-22 23:36:35.812662: step: 384/533, loss: 0.3434966206550598
2023-01-22 23:36:36.960301: step: 388/533, loss: 0.7020226716995239
2023-01-22 23:36:38.160762: step: 392/533, loss: 0.42894333600997925
2023-01-22 23:36:39.337596: step: 396/533, loss: 0.984560489654541
2023-01-22 23:36:40.518083: step: 400/533, loss: 0.1585921347141266
2023-01-22 23:36:41.683103: step: 404/533, loss: 1.4114590883255005
2023-01-22 23:36:42.869870: step: 408/533, loss: 1.7944252490997314
2023-01-22 23:36:44.041661: step: 412/533, loss: 0.2702641487121582
2023-01-22 23:36:45.163567: step: 416/533, loss: 0.8641048669815063
2023-01-22 23:36:46.378761: step: 420/533, loss: 0.27141672372817993
2023-01-22 23:36:47.574829: step: 424/533, loss: 0.8849024176597595
2023-01-22 23:36:48.746491: step: 428/533, loss: 1.5761537551879883
2023-01-22 23:36:49.914744: step: 432/533, loss: 0.24044305086135864
2023-01-22 23:36:51.088782: step: 436/533, loss: 1.4541585445404053
2023-01-22 23:36:52.268781: step: 440/533, loss: 1.3601478338241577
2023-01-22 23:36:53.455605: step: 444/533, loss: 1.650113582611084
2023-01-22 23:36:54.619604: step: 448/533, loss: 0.24510188400745392
2023-01-22 23:36:55.788610: step: 452/533, loss: 0.4233432710170746
2023-01-22 23:36:56.946567: step: 456/533, loss: 0.3117285966873169
2023-01-22 23:36:58.146856: step: 460/533, loss: 0.31069380044937134
2023-01-22 23:36:59.328264: step: 464/533, loss: 0.42756518721580505
2023-01-22 23:37:00.498743: step: 468/533, loss: 0.284812331199646
2023-01-22 23:37:01.690952: step: 472/533, loss: 0.1648479402065277
2023-01-22 23:37:02.887490: step: 476/533, loss: 0.3525228500366211
2023-01-22 23:37:04.071254: step: 480/533, loss: 0.37308454513549805
2023-01-22 23:37:05.275984: step: 484/533, loss: 0.16926679015159607
2023-01-22 23:37:06.469232: step: 488/533, loss: 0.31133148074150085
2023-01-22 23:37:07.650111: step: 492/533, loss: 0.30838558077812195
2023-01-22 23:37:08.870010: step: 496/533, loss: 1.9954447746276855
2023-01-22 23:37:10.022903: step: 500/533, loss: 1.1287389993667603
2023-01-22 23:37:11.244354: step: 504/533, loss: 4.503689289093018
2023-01-22 23:37:12.356038: step: 508/533, loss: 0.5619094371795654
2023-01-22 23:37:13.512706: step: 512/533, loss: 0.8835994005203247
2023-01-22 23:37:14.689376: step: 516/533, loss: 0.41967689990997314
2023-01-22 23:37:15.850609: step: 520/533, loss: 0.5207710266113281
2023-01-22 23:37:17.024723: step: 524/533, loss: 0.34112748503685
2023-01-22 23:37:18.210058: step: 528/533, loss: 0.30970126390457153
2023-01-22 23:37:19.352588: step: 532/533, loss: 0.21265669167041779
2023-01-22 23:37:20.552853: step: 536/533, loss: 0.636131763458252
2023-01-22 23:37:21.728354: step: 540/533, loss: 2.11444091796875
2023-01-22 23:37:22.932966: step: 544/533, loss: 2.981522560119629
2023-01-22 23:37:24.092309: step: 548/533, loss: 1.6722217798233032
2023-01-22 23:37:25.234220: step: 552/533, loss: 0.22657814621925354
2023-01-22 23:37:26.392118: step: 556/533, loss: 0.47271353006362915
2023-01-22 23:37:27.557183: step: 560/533, loss: 1.6469544172286987
2023-01-22 23:37:28.723216: step: 564/533, loss: 0.5778610706329346
2023-01-22 23:37:29.922816: step: 568/533, loss: 0.33917656540870667
2023-01-22 23:37:31.069569: step: 572/533, loss: 0.6833656430244446
2023-01-22 23:37:32.238510: step: 576/533, loss: 0.4177490472793579
2023-01-22 23:37:33.434502: step: 580/533, loss: 1.7253884077072144
2023-01-22 23:37:34.628296: step: 584/533, loss: 0.21751871705055237
2023-01-22 23:37:35.791410: step: 588/533, loss: 0.3941943049430847
2023-01-22 23:37:36.975848: step: 592/533, loss: 0.45982152223587036
2023-01-22 23:37:38.186337: step: 596/533, loss: 0.3533408045768738
2023-01-22 23:37:39.360800: step: 600/533, loss: 0.6673813462257385
2023-01-22 23:37:40.543006: step: 604/533, loss: 0.699525773525238
2023-01-22 23:37:41.737692: step: 608/533, loss: 0.1774233877658844
2023-01-22 23:37:42.908012: step: 612/533, loss: 7.702902317047119
2023-01-22 23:37:44.133189: step: 616/533, loss: 0.1863287091255188
2023-01-22 23:37:45.296313: step: 620/533, loss: 0.46469393372535706
2023-01-22 23:37:46.488324: step: 624/533, loss: 1.0272042751312256
2023-01-22 23:37:47.702187: step: 628/533, loss: 1.2684119939804077
2023-01-22 23:37:48.851619: step: 632/533, loss: 8.235013961791992
2023-01-22 23:37:50.063653: step: 636/533, loss: 1.1135437488555908
2023-01-22 23:37:51.213093: step: 640/533, loss: 0.1753322184085846
2023-01-22 23:37:52.369086: step: 644/533, loss: 0.7635591626167297
2023-01-22 23:37:53.522788: step: 648/533, loss: 1.4237725734710693
2023-01-22 23:37:54.673419: step: 652/533, loss: 1.0969231128692627
2023-01-22 23:37:55.841991: step: 656/533, loss: 0.5957016944885254
2023-01-22 23:37:56.996385: step: 660/533, loss: 0.5933224558830261
2023-01-22 23:37:58.183401: step: 664/533, loss: 0.19568271934986115
2023-01-22 23:37:59.326511: step: 668/533, loss: 0.13619375228881836
2023-01-22 23:38:00.508308: step: 672/533, loss: 0.2319856584072113
2023-01-22 23:38:01.672767: step: 676/533, loss: 0.10898929089307785
2023-01-22 23:38:02.863494: step: 680/533, loss: 0.3891049921512604
2023-01-22 23:38:04.078314: step: 684/533, loss: 1.5643413066864014
2023-01-22 23:38:05.289985: step: 688/533, loss: 0.31160032749176025
2023-01-22 23:38:06.419416: step: 692/533, loss: 0.43434616923332214
2023-01-22 23:38:07.612454: step: 696/533, loss: 0.11282258480787277
2023-01-22 23:38:08.801953: step: 700/533, loss: 0.34091776609420776
2023-01-22 23:38:09.997270: step: 704/533, loss: 1.8270622491836548
2023-01-22 23:38:11.198407: step: 708/533, loss: 0.3535654842853546
2023-01-22 23:38:12.364653: step: 712/533, loss: 3.5323214530944824
2023-01-22 23:38:13.565086: step: 716/533, loss: 0.023487448692321777
2023-01-22 23:38:14.727237: step: 720/533, loss: 0.9441156983375549
2023-01-22 23:38:15.899532: step: 724/533, loss: 0.5851117372512817
2023-01-22 23:38:17.062631: step: 728/533, loss: 0.6507365107536316
2023-01-22 23:38:18.262176: step: 732/533, loss: 0.35127145051956177
2023-01-22 23:38:19.401392: step: 736/533, loss: 0.732417643070221
2023-01-22 23:38:20.612146: step: 740/533, loss: 0.8329192996025085
2023-01-22 23:38:21.782523: step: 744/533, loss: 0.6095622181892395
2023-01-22 23:38:23.001096: step: 748/533, loss: 2.958179235458374
2023-01-22 23:38:24.151141: step: 752/533, loss: 0.21832752227783203
2023-01-22 23:38:25.331671: step: 756/533, loss: 0.212521031498909
2023-01-22 23:38:26.494495: step: 760/533, loss: 0.26764345169067383
2023-01-22 23:38:27.661586: step: 764/533, loss: 0.22837097942829132
2023-01-22 23:38:28.884584: step: 768/533, loss: 0.19268932938575745
2023-01-22 23:38:30.068178: step: 772/533, loss: 0.13291996717453003
2023-01-22 23:38:31.243369: step: 776/533, loss: 0.15635986626148224
2023-01-22 23:38:32.428911: step: 780/533, loss: 0.23405605554580688
2023-01-22 23:38:33.642232: step: 784/533, loss: 0.2388055920600891
2023-01-22 23:38:34.821355: step: 788/533, loss: 0.1785575896501541
2023-01-22 23:38:35.990254: step: 792/533, loss: 0.6539970636367798
2023-01-22 23:38:37.158673: step: 796/533, loss: 1.5934582948684692
2023-01-22 23:38:38.334746: step: 800/533, loss: 0.994404137134552
2023-01-22 23:38:39.519135: step: 804/533, loss: 0.9540376663208008
2023-01-22 23:38:40.684855: step: 808/533, loss: 0.09399070590734482
2023-01-22 23:38:41.858657: step: 812/533, loss: 1.6626752614974976
2023-01-22 23:38:43.027088: step: 816/533, loss: 2.802852153778076
2023-01-22 23:38:44.267003: step: 820/533, loss: 0.9512723684310913
2023-01-22 23:38:45.444042: step: 824/533, loss: 0.8457459211349487
2023-01-22 23:38:46.594159: step: 828/533, loss: 0.5066772699356079
2023-01-22 23:38:47.858013: step: 832/533, loss: 0.5556012988090515
2023-01-22 23:38:49.025191: step: 836/533, loss: 0.2553671896457672
2023-01-22 23:38:50.170226: step: 840/533, loss: 1.140232801437378
2023-01-22 23:38:51.351764: step: 844/533, loss: 1.0770596265792847
2023-01-22 23:38:52.534276: step: 848/533, loss: 0.1377793848514557
2023-01-22 23:38:53.684110: step: 852/533, loss: 0.21938037872314453
2023-01-22 23:38:54.860336: step: 856/533, loss: 1.3110233545303345
2023-01-22 23:38:56.025315: step: 860/533, loss: 0.9007653594017029
2023-01-22 23:38:57.216494: step: 864/533, loss: 0.2547755241394043
2023-01-22 23:38:58.379650: step: 868/533, loss: 7.441074371337891
2023-01-22 23:38:59.560481: step: 872/533, loss: 0.4394218325614929
2023-01-22 23:39:00.740033: step: 876/533, loss: 0.22106260061264038
2023-01-22 23:39:01.891028: step: 880/533, loss: 0.12388768792152405
2023-01-22 23:39:03.076927: step: 884/533, loss: 0.17823491990566254
2023-01-22 23:39:04.228207: step: 888/533, loss: 0.5554996728897095
2023-01-22 23:39:05.370097: step: 892/533, loss: 0.16692335903644562
2023-01-22 23:39:06.507514: step: 896/533, loss: 0.21521052718162537
2023-01-22 23:39:07.677250: step: 900/533, loss: 0.7005617022514343
2023-01-22 23:39:08.866866: step: 904/533, loss: 0.18899306654930115
2023-01-22 23:39:10.086668: step: 908/533, loss: 4.294531345367432
2023-01-22 23:39:11.244287: step: 912/533, loss: 0.3245202302932739
2023-01-22 23:39:12.394851: step: 916/533, loss: 0.3368349075317383
2023-01-22 23:39:13.556365: step: 920/533, loss: 0.09404177963733673
2023-01-22 23:39:14.711254: step: 924/533, loss: 0.4819769859313965
2023-01-22 23:39:15.844729: step: 928/533, loss: 3.002568483352661
2023-01-22 23:39:17.016113: step: 932/533, loss: 1.454717993736267
2023-01-22 23:39:18.236273: step: 936/533, loss: 0.328425794839859
2023-01-22 23:39:19.458778: step: 940/533, loss: 1.8779464960098267
2023-01-22 23:39:20.610788: step: 944/533, loss: 0.2418876737356186
2023-01-22 23:39:21.780373: step: 948/533, loss: 1.7883442640304565
2023-01-22 23:39:22.971008: step: 952/533, loss: 0.24025803804397583
2023-01-22 23:39:24.127825: step: 956/533, loss: 0.2860255241394043
2023-01-22 23:39:25.285003: step: 960/533, loss: 0.14447283744812012
2023-01-22 23:39:26.473767: step: 964/533, loss: 0.13047447800636292
2023-01-22 23:39:27.696477: step: 968/533, loss: 2.645369052886963
2023-01-22 23:39:28.889539: step: 972/533, loss: 0.7749943733215332
2023-01-22 23:39:30.052206: step: 976/533, loss: 0.20647449791431427
2023-01-22 23:39:31.238522: step: 980/533, loss: 0.49702727794647217
2023-01-22 23:39:32.412430: step: 984/533, loss: 0.9022245407104492
2023-01-22 23:39:33.568869: step: 988/533, loss: 0.33355823159217834
2023-01-22 23:39:34.753826: step: 992/533, loss: 0.6512640118598938
2023-01-22 23:39:35.917883: step: 996/533, loss: 1.454237937927246
2023-01-22 23:39:37.086853: step: 1000/533, loss: 0.13608050346374512
2023-01-22 23:39:38.263043: step: 1004/533, loss: 0.28959551453590393
2023-01-22 23:39:39.462066: step: 1008/533, loss: 0.6602293252944946
2023-01-22 23:39:40.619490: step: 1012/533, loss: 0.35750120878219604
2023-01-22 23:39:41.778799: step: 1016/533, loss: 1.0920332670211792
2023-01-22 23:39:43.002730: step: 1020/533, loss: 0.9741709232330322
2023-01-22 23:39:44.199117: step: 1024/533, loss: 0.29904240369796753
2023-01-22 23:39:45.410967: step: 1028/533, loss: 0.8901816010475159
2023-01-22 23:39:46.550890: step: 1032/533, loss: 0.16749007999897003
2023-01-22 23:39:47.770165: step: 1036/533, loss: 0.15685425698757172
2023-01-22 23:39:48.962505: step: 1040/533, loss: 0.47795915603637695
2023-01-22 23:39:50.141777: step: 1044/533, loss: 0.37385550141334534
2023-01-22 23:39:51.300996: step: 1048/533, loss: 0.2544828951358795
2023-01-22 23:39:52.465044: step: 1052/533, loss: 0.34292542934417725
2023-01-22 23:39:53.661256: step: 1056/533, loss: 0.17216157913208008
2023-01-22 23:39:54.824051: step: 1060/533, loss: 0.20723217725753784
2023-01-22 23:39:55.995283: step: 1064/533, loss: 0.40144920349121094
2023-01-22 23:39:57.148362: step: 1068/533, loss: 0.12985210120677948
2023-01-22 23:39:58.358660: step: 1072/533, loss: 1.9000437259674072
2023-01-22 23:39:59.559274: step: 1076/533, loss: 0.8238351345062256
2023-01-22 23:40:00.693865: step: 1080/533, loss: 0.3972499966621399
2023-01-22 23:40:01.892413: step: 1084/533, loss: 0.8402547836303711
2023-01-22 23:40:03.075883: step: 1088/533, loss: 2.5658740997314453
2023-01-22 23:40:04.267069: step: 1092/533, loss: 0.20307406783103943
2023-01-22 23:40:05.434746: step: 1096/533, loss: 0.7247675061225891
2023-01-22 23:40:06.596882: step: 1100/533, loss: 0.15931224822998047
2023-01-22 23:40:07.780500: step: 1104/533, loss: 1.7298507690429688
2023-01-22 23:40:08.955394: step: 1108/533, loss: 0.23708420991897583
2023-01-22 23:40:10.150109: step: 1112/533, loss: 1.1382371187210083
2023-01-22 23:40:11.341927: step: 1116/533, loss: 0.36733686923980713
2023-01-22 23:40:12.540456: step: 1120/533, loss: 0.12278571724891663
2023-01-22 23:40:13.720591: step: 1124/533, loss: 1.1160228252410889
2023-01-22 23:40:14.903267: step: 1128/533, loss: 0.4858914315700531
2023-01-22 23:40:16.094444: step: 1132/533, loss: 2.625290632247925
2023-01-22 23:40:17.252442: step: 1136/533, loss: 0.41810664534568787
2023-01-22 23:40:18.403786: step: 1140/533, loss: 1.226264476776123
2023-01-22 23:40:19.593223: step: 1144/533, loss: 0.3684443235397339
2023-01-22 23:40:20.772582: step: 1148/533, loss: 0.17214256525039673
2023-01-22 23:40:21.960036: step: 1152/533, loss: 0.24763727188110352
2023-01-22 23:40:23.140778: step: 1156/533, loss: 0.3016742765903473
2023-01-22 23:40:24.313647: step: 1160/533, loss: 0.3701697885990143
2023-01-22 23:40:25.480701: step: 1164/533, loss: 0.11853313446044922
2023-01-22 23:40:26.645843: step: 1168/533, loss: 0.31025782227516174
2023-01-22 23:40:27.803539: step: 1172/533, loss: 0.530258059501648
2023-01-22 23:40:28.953675: step: 1176/533, loss: 1.364376187324524
2023-01-22 23:40:30.132225: step: 1180/533, loss: 0.8632562160491943
2023-01-22 23:40:31.314675: step: 1184/533, loss: 1.4107623100280762
2023-01-22 23:40:32.467915: step: 1188/533, loss: 0.14337699115276337
2023-01-22 23:40:33.655409: step: 1192/533, loss: 2.232888698577881
2023-01-22 23:40:34.815629: step: 1196/533, loss: 0.3871815800666809
2023-01-22 23:40:35.993558: step: 1200/533, loss: 0.8312267065048218
2023-01-22 23:40:37.166621: step: 1204/533, loss: 0.2820187211036682
2023-01-22 23:40:38.340234: step: 1208/533, loss: 0.21394038200378418
2023-01-22 23:40:39.506554: step: 1212/533, loss: 0.16216059029102325
2023-01-22 23:40:40.671586: step: 1216/533, loss: 0.8990379571914673
2023-01-22 23:40:41.798557: step: 1220/533, loss: 0.13687849044799805
2023-01-22 23:40:42.974718: step: 1224/533, loss: 0.7648783326148987
2023-01-22 23:40:44.159227: step: 1228/533, loss: 0.6988527774810791
2023-01-22 23:40:45.325351: step: 1232/533, loss: 0.8141835927963257
2023-01-22 23:40:46.496851: step: 1236/533, loss: 0.06783771514892578
2023-01-22 23:40:47.692774: step: 1240/533, loss: 1.1130763292312622
2023-01-22 23:40:48.913845: step: 1244/533, loss: 0.2957499623298645
2023-01-22 23:40:50.129682: step: 1248/533, loss: 0.4456924498081207
2023-01-22 23:40:51.283025: step: 1252/533, loss: 0.47412949800491333
2023-01-22 23:40:52.425517: step: 1256/533, loss: 1.2063266038894653
2023-01-22 23:40:53.605022: step: 1260/533, loss: 1.640655517578125
2023-01-22 23:40:54.765684: step: 1264/533, loss: 0.16568291187286377
2023-01-22 23:40:55.953825: step: 1268/533, loss: 0.24979759752750397
2023-01-22 23:40:57.092617: step: 1272/533, loss: 0.13588576018810272
2023-01-22 23:40:58.315296: step: 1276/533, loss: 0.24857358634471893
2023-01-22 23:40:59.537113: step: 1280/533, loss: 0.29324567317962646
2023-01-22 23:41:00.702106: step: 1284/533, loss: 0.13492503762245178
2023-01-22 23:41:01.907655: step: 1288/533, loss: 0.383827805519104
2023-01-22 23:41:03.065307: step: 1292/533, loss: 0.3037358522415161
2023-01-22 23:41:04.241275: step: 1296/533, loss: 0.23564472794532776
2023-01-22 23:41:05.388917: step: 1300/533, loss: 0.15794897079467773
2023-01-22 23:41:06.574043: step: 1304/533, loss: 0.1066683828830719
2023-01-22 23:41:07.728840: step: 1308/533, loss: 0.4907299280166626
2023-01-22 23:41:08.909186: step: 1312/533, loss: 0.3331003189086914
2023-01-22 23:41:10.097072: step: 1316/533, loss: 0.1393260657787323
2023-01-22 23:41:11.272071: step: 1320/533, loss: 0.5686827898025513
2023-01-22 23:41:12.438322: step: 1324/533, loss: 0.7912129759788513
2023-01-22 23:41:13.593685: step: 1328/533, loss: 0.4062058925628662
2023-01-22 23:41:14.799863: step: 1332/533, loss: 0.3385017514228821
2023-01-22 23:41:15.962187: step: 1336/533, loss: 0.2562173008918762
2023-01-22 23:41:17.171317: step: 1340/533, loss: 0.20449256896972656
2023-01-22 23:41:18.343399: step: 1344/533, loss: 0.8572694063186646
2023-01-22 23:41:19.622501: step: 1348/533, loss: 0.605523407459259
2023-01-22 23:41:20.780497: step: 1352/533, loss: 0.7122437357902527
2023-01-22 23:41:21.974362: step: 1356/533, loss: 0.5115454792976379
2023-01-22 23:41:23.164736: step: 1360/533, loss: 0.3410715162754059
2023-01-22 23:41:24.384022: step: 1364/533, loss: 0.28134116530418396
2023-01-22 23:41:25.552749: step: 1368/533, loss: 0.24053707718849182
2023-01-22 23:41:26.745456: step: 1372/533, loss: 0.13209930062294006
2023-01-22 23:41:27.872647: step: 1376/533, loss: 0.6349261403083801
2023-01-22 23:41:29.048667: step: 1380/533, loss: 0.20161685347557068
2023-01-22 23:41:30.246904: step: 1384/533, loss: 1.0845767259597778
2023-01-22 23:41:31.444751: step: 1388/533, loss: 0.20318767428398132
2023-01-22 23:41:32.653393: step: 1392/533, loss: 1.6933789253234863
2023-01-22 23:41:33.813202: step: 1396/533, loss: 1.3705992698669434
2023-01-22 23:41:34.961478: step: 1400/533, loss: 0.3725167214870453
2023-01-22 23:41:36.141463: step: 1404/533, loss: 0.3230894207954407
2023-01-22 23:41:37.340252: step: 1408/533, loss: 0.19021745026111603
2023-01-22 23:41:38.500641: step: 1412/533, loss: 1.5556437969207764
2023-01-22 23:41:39.676237: step: 1416/533, loss: 1.4127694368362427
2023-01-22 23:41:40.876225: step: 1420/533, loss: 0.8863551020622253
2023-01-22 23:41:42.056278: step: 1424/533, loss: 0.11446066200733185
2023-01-22 23:41:43.216764: step: 1428/533, loss: 0.4817333221435547
2023-01-22 23:41:44.365144: step: 1432/533, loss: 0.41757750511169434
2023-01-22 23:41:45.505952: step: 1436/533, loss: 0.8214594721794128
2023-01-22 23:41:46.698597: step: 1440/533, loss: 0.3887789845466614
2023-01-22 23:41:47.871653: step: 1444/533, loss: 0.5875848531723022
2023-01-22 23:41:49.024807: step: 1448/533, loss: 7.613314628601074
2023-01-22 23:41:50.141218: step: 1452/533, loss: 0.34646815061569214
2023-01-22 23:41:51.294640: step: 1456/533, loss: 0.3636614680290222
2023-01-22 23:41:52.473013: step: 1460/533, loss: 0.5438183546066284
2023-01-22 23:41:53.627456: step: 1464/533, loss: 1.1973438262939453
2023-01-22 23:41:54.804725: step: 1468/533, loss: 0.18392372131347656
2023-01-22 23:41:55.982215: step: 1472/533, loss: 0.4506836533546448
2023-01-22 23:41:57.161103: step: 1476/533, loss: 0.1776662915945053
2023-01-22 23:41:58.297251: step: 1480/533, loss: 0.3532768189907074
2023-01-22 23:41:59.443247: step: 1484/533, loss: 0.15288801491260529
2023-01-22 23:42:00.597159: step: 1488/533, loss: 0.4506000578403473
2023-01-22 23:42:01.749522: step: 1492/533, loss: 0.51244056224823
2023-01-22 23:42:02.892587: step: 1496/533, loss: 0.2831088602542877
2023-01-22 23:42:04.069027: step: 1500/533, loss: 0.10649213939905167
2023-01-22 23:42:05.345049: step: 1504/533, loss: 0.09102578461170197
2023-01-22 23:42:06.492605: step: 1508/533, loss: 0.9720889925956726
2023-01-22 23:42:07.669987: step: 1512/533, loss: 0.5511001944541931
2023-01-22 23:42:08.899419: step: 1516/533, loss: 0.21419945359230042
2023-01-22 23:42:10.011605: step: 1520/533, loss: 0.9294561147689819
2023-01-22 23:42:11.167528: step: 1524/533, loss: 0.2315596640110016
2023-01-22 23:42:12.368651: step: 1528/533, loss: 0.1455668956041336
2023-01-22 23:42:13.560083: step: 1532/533, loss: 0.5210424661636353
2023-01-22 23:42:14.764360: step: 1536/533, loss: 0.1889040619134903
2023-01-22 23:42:15.963418: step: 1540/533, loss: 0.9127049446105957
2023-01-22 23:42:17.133517: step: 1544/533, loss: 0.13219304382801056
2023-01-22 23:42:18.298055: step: 1548/533, loss: 1.001331090927124
2023-01-22 23:42:19.480182: step: 1552/533, loss: 1.5616778135299683
2023-01-22 23:42:20.709520: step: 1556/533, loss: 1.5641981363296509
2023-01-22 23:42:21.869565: step: 1560/533, loss: 1.0800390243530273
2023-01-22 23:42:23.102145: step: 1564/533, loss: 0.19683510065078735
2023-01-22 23:42:24.293197: step: 1568/533, loss: 0.32040977478027344
2023-01-22 23:42:25.494386: step: 1572/533, loss: 0.7974711060523987
2023-01-22 23:42:26.669482: step: 1576/533, loss: 0.30020105838775635
2023-01-22 23:42:27.850930: step: 1580/533, loss: 0.18065744638442993
2023-01-22 23:42:29.012509: step: 1584/533, loss: 0.20464010536670685
2023-01-22 23:42:30.292955: step: 1588/533, loss: 0.9827674627304077
2023-01-22 23:42:31.486528: step: 1592/533, loss: 2.80283522605896
2023-01-22 23:42:32.629918: step: 1596/533, loss: 1.3079277276992798
2023-01-22 23:42:33.816953: step: 1600/533, loss: 1.040922999382019
2023-01-22 23:42:34.988567: step: 1604/533, loss: 6.412429332733154
2023-01-22 23:42:36.142111: step: 1608/533, loss: 0.1268180012702942
2023-01-22 23:42:37.331185: step: 1612/533, loss: 1.9018254280090332
2023-01-22 23:42:38.492528: step: 1616/533, loss: 0.20163805782794952
2023-01-22 23:42:39.677678: step: 1620/533, loss: 0.9594154953956604
2023-01-22 23:42:40.879298: step: 1624/533, loss: 0.5759618282318115
2023-01-22 23:42:42.039315: step: 1628/533, loss: 0.8610288500785828
2023-01-22 23:42:43.209983: step: 1632/533, loss: 0.1434132605791092
2023-01-22 23:42:44.410981: step: 1636/533, loss: 0.20625987648963928
2023-01-22 23:42:45.584068: step: 1640/533, loss: 2.2320892810821533
2023-01-22 23:42:46.745840: step: 1644/533, loss: 0.5052288174629211
2023-01-22 23:42:47.933154: step: 1648/533, loss: 0.6492370367050171
2023-01-22 23:42:49.106673: step: 1652/533, loss: 0.788342297077179
2023-01-22 23:42:50.266788: step: 1656/533, loss: 0.18628616631031036
2023-01-22 23:42:51.424848: step: 1660/533, loss: 0.18082067370414734
2023-01-22 23:42:52.588207: step: 1664/533, loss: 0.1602247655391693
2023-01-22 23:42:53.742432: step: 1668/533, loss: 0.17520609498023987
2023-01-22 23:42:54.906589: step: 1672/533, loss: 0.6110613346099854
2023-01-22 23:42:56.061006: step: 1676/533, loss: 0.6510634422302246
2023-01-22 23:42:57.231227: step: 1680/533, loss: 0.7063851356506348
2023-01-22 23:42:58.358319: step: 1684/533, loss: 0.6892544031143188
2023-01-22 23:42:59.542640: step: 1688/533, loss: 0.49946165084838867
2023-01-22 23:43:00.723742: step: 1692/533, loss: 0.7132205963134766
2023-01-22 23:43:01.944447: step: 1696/533, loss: 0.1858876347541809
2023-01-22 23:43:03.144420: step: 1700/533, loss: 1.2561460733413696
2023-01-22 23:43:04.368405: step: 1704/533, loss: 0.9905737042427063
2023-01-22 23:43:05.541898: step: 1708/533, loss: 0.33987924456596375
2023-01-22 23:43:06.697561: step: 1712/533, loss: 0.7124394774436951
2023-01-22 23:43:07.887038: step: 1716/533, loss: 0.15509900450706482
2023-01-22 23:43:09.092054: step: 1720/533, loss: 0.4252755045890808
2023-01-22 23:43:10.301760: step: 1724/533, loss: 0.21397143602371216
2023-01-22 23:43:11.464226: step: 1728/533, loss: 0.2233814150094986
2023-01-22 23:43:12.615751: step: 1732/533, loss: 0.14459353685379028
2023-01-22 23:43:13.807274: step: 1736/533, loss: 0.43625637888908386
2023-01-22 23:43:14.957372: step: 1740/533, loss: 0.18639174103736877
2023-01-22 23:43:16.113418: step: 1744/533, loss: 0.1797471046447754
2023-01-22 23:43:17.267082: step: 1748/533, loss: 0.3187692165374756
2023-01-22 23:43:18.427669: step: 1752/533, loss: 0.22615423798561096
2023-01-22 23:43:19.567370: step: 1756/533, loss: 0.8571557998657227
2023-01-22 23:43:20.753033: step: 1760/533, loss: 6.347506046295166
2023-01-22 23:43:21.954320: step: 1764/533, loss: 1.7205748558044434
2023-01-22 23:43:23.152716: step: 1768/533, loss: 1.0612514019012451
2023-01-22 23:43:24.324512: step: 1772/533, loss: 0.2512054443359375
2023-01-22 23:43:25.498636: step: 1776/533, loss: 0.8201772570610046
2023-01-22 23:43:26.701874: step: 1780/533, loss: 0.17684555053710938
2023-01-22 23:43:27.892134: step: 1784/533, loss: 0.7339959144592285
2023-01-22 23:43:29.117026: step: 1788/533, loss: 7.235861301422119
2023-01-22 23:43:30.307602: step: 1792/533, loss: 0.14361485838890076
2023-01-22 23:43:31.452385: step: 1796/533, loss: 0.20178404450416565
2023-01-22 23:43:32.624836: step: 1800/533, loss: 0.447252094745636
2023-01-22 23:43:33.773089: step: 1804/533, loss: 0.33057937026023865
2023-01-22 23:43:34.967153: step: 1808/533, loss: 0.8879483938217163
2023-01-22 23:43:36.173806: step: 1812/533, loss: 1.0193923711776733
2023-01-22 23:43:37.327389: step: 1816/533, loss: 0.553665041923523
2023-01-22 23:43:38.492319: step: 1820/533, loss: 0.8712189793586731
2023-01-22 23:43:39.679404: step: 1824/533, loss: 0.15548363327980042
2023-01-22 23:43:40.880447: step: 1828/533, loss: 0.5508195757865906
2023-01-22 23:43:42.059105: step: 1832/533, loss: 0.11083962768316269
2023-01-22 23:43:43.251152: step: 1836/533, loss: 0.3949201703071594
2023-01-22 23:43:44.396519: step: 1840/533, loss: 0.3378902077674866
2023-01-22 23:43:45.566849: step: 1844/533, loss: 0.21268385648727417
2023-01-22 23:43:46.786925: step: 1848/533, loss: 0.14636117219924927
2023-01-22 23:43:47.990487: step: 1852/533, loss: 1.2633007764816284
2023-01-22 23:43:49.216082: step: 1856/533, loss: 0.3618050813674927
2023-01-22 23:43:50.404297: step: 1860/533, loss: 0.7293722033500671
2023-01-22 23:43:51.572467: step: 1864/533, loss: 0.18918466567993164
2023-01-22 23:43:52.759257: step: 1868/533, loss: 2.40671968460083
2023-01-22 23:43:53.921330: step: 1872/533, loss: 0.11944542825222015
2023-01-22 23:43:55.075047: step: 1876/533, loss: 0.2083059400320053
2023-01-22 23:43:56.227571: step: 1880/533, loss: 0.1916859745979309
2023-01-22 23:43:57.396074: step: 1884/533, loss: 0.35312873125076294
2023-01-22 23:43:58.586792: step: 1888/533, loss: 0.5087341070175171
2023-01-22 23:43:59.735716: step: 1892/533, loss: 0.44750314950942993
2023-01-22 23:44:00.914951: step: 1896/533, loss: 0.7753688097000122
2023-01-22 23:44:02.120574: step: 1900/533, loss: 0.36229783296585083
2023-01-22 23:44:03.279880: step: 1904/533, loss: 0.6711670756340027
2023-01-22 23:44:04.443364: step: 1908/533, loss: 0.7190624475479126
2023-01-22 23:44:05.625221: step: 1912/533, loss: 1.3056414127349854
2023-01-22 23:44:06.770967: step: 1916/533, loss: 0.17223167419433594
2023-01-22 23:44:07.926264: step: 1920/533, loss: 0.07773604989051819
2023-01-22 23:44:09.113416: step: 1924/533, loss: 0.0669272243976593
2023-01-22 23:44:10.284154: step: 1928/533, loss: 0.08887290954589844
2023-01-22 23:44:11.436124: step: 1932/533, loss: 0.853316068649292
2023-01-22 23:44:12.639454: step: 1936/533, loss: 1.3761448860168457
2023-01-22 23:44:13.830928: step: 1940/533, loss: 0.2315848469734192
2023-01-22 23:44:14.983879: step: 1944/533, loss: 0.2900312542915344
2023-01-22 23:44:16.147540: step: 1948/533, loss: 0.26392853260040283
2023-01-22 23:44:17.336929: step: 1952/533, loss: 0.1180468499660492
2023-01-22 23:44:18.566046: step: 1956/533, loss: 0.49521002173423767
2023-01-22 23:44:19.826044: step: 1960/533, loss: 0.07162399590015411
2023-01-22 23:44:21.007879: step: 1964/533, loss: 0.1672719419002533
2023-01-22 23:44:22.184833: step: 1968/533, loss: 0.08329484611749649
2023-01-22 23:44:23.324862: step: 1972/533, loss: 0.05844435840845108
2023-01-22 23:44:24.501129: step: 1976/533, loss: 0.2748605012893677
2023-01-22 23:44:25.703410: step: 1980/533, loss: 0.18915005028247833
2023-01-22 23:44:26.891308: step: 1984/533, loss: 0.2961672246456146
2023-01-22 23:44:28.128468: step: 1988/533, loss: 2.322105884552002
2023-01-22 23:44:29.324374: step: 1992/533, loss: 0.9499852657318115
2023-01-22 23:44:30.492406: step: 1996/533, loss: 0.2910190224647522
2023-01-22 23:44:31.676442: step: 2000/533, loss: 0.6286906003952026
2023-01-22 23:44:32.897880: step: 2004/533, loss: 0.20375236868858337
2023-01-22 23:44:34.061999: step: 2008/533, loss: 0.16577622294425964
2023-01-22 23:44:35.301144: step: 2012/533, loss: 0.33581504225730896
2023-01-22 23:44:36.507884: step: 2016/533, loss: 1.2614092826843262
2023-01-22 23:44:37.723435: step: 2020/533, loss: 0.26006898283958435
2023-01-22 23:44:38.922254: step: 2024/533, loss: 0.21648313105106354
2023-01-22 23:44:40.078310: step: 2028/533, loss: 0.08915567398071289
2023-01-22 23:44:41.282984: step: 2032/533, loss: 0.2993401885032654
2023-01-22 23:44:42.510042: step: 2036/533, loss: 0.27792254090309143
2023-01-22 23:44:43.678521: step: 2040/533, loss: 0.5655492544174194
2023-01-22 23:44:44.881063: step: 2044/533, loss: 0.7827044725418091
2023-01-22 23:44:46.051294: step: 2048/533, loss: 0.7342962622642517
2023-01-22 23:44:47.211122: step: 2052/533, loss: 0.17950135469436646
2023-01-22 23:44:48.401979: step: 2056/533, loss: 0.570751428604126
2023-01-22 23:44:49.605893: step: 2060/533, loss: 1.1367592811584473
2023-01-22 23:44:50.771655: step: 2064/533, loss: 0.31864356994628906
2023-01-22 23:44:51.964305: step: 2068/533, loss: 0.1877949833869934
2023-01-22 23:44:53.157340: step: 2072/533, loss: 1.6193100214004517
2023-01-22 23:44:54.312689: step: 2076/533, loss: 0.4787091314792633
2023-01-22 23:44:55.483160: step: 2080/533, loss: 0.1201920285820961
2023-01-22 23:44:56.684737: step: 2084/533, loss: 1.5718034505844116
2023-01-22 23:44:57.852520: step: 2088/533, loss: 0.5335476994514465
2023-01-22 23:44:59.044412: step: 2092/533, loss: 1.9365079402923584
2023-01-22 23:45:00.217968: step: 2096/533, loss: 0.15172234177589417
2023-01-22 23:45:01.384890: step: 2100/533, loss: 0.3086782395839691
2023-01-22 23:45:02.578223: step: 2104/533, loss: 1.6743295192718506
2023-01-22 23:45:03.748513: step: 2108/533, loss: 0.2194240391254425
2023-01-22 23:45:04.913322: step: 2112/533, loss: 0.04186415672302246
2023-01-22 23:45:06.114687: step: 2116/533, loss: 2.0739517211914062
2023-01-22 23:45:07.334202: step: 2120/533, loss: 0.9264987707138062
2023-01-22 23:45:08.501855: step: 2124/533, loss: 0.15454182028770447
2023-01-22 23:45:09.681869: step: 2128/533, loss: 0.5753645896911621
2023-01-22 23:45:10.837139: step: 2132/533, loss: 0.22760553658008575
==================================================
Loss: 0.780
--------------------
Dev: {'event': {'p': 0.49306197964847365, 'r': 0.7097203728362184, 'f1': 0.5818777292576419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5165719696969697, 'r': 0.6975703324808185, 'f1': 0.5935799782372144}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.449438202247191, 'r': 0.7407407407407407, 'f1': 0.5594405594405595}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.5535714285714286, 'r': 0.49206349206349204, 'f1': 0.5210084033613446}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, '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': 0.49306197964847365, 'r': 0.7097203728362184, 'f1': 0.5818777292576419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5165719696969697, 'r': 0.6975703324808185, 'f1': 0.5935799782372144}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.449438202247191, 'r': 0.7407407407407407, 'f1': 0.5594405594405595}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.49306197964847365, 'r': 0.7097203728362184, 'f1': 0.5818777292576419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5165719696969697, 'r': 0.6975703324808185, 'f1': 0.5935799782372144}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.5535714285714286, 'r': 0.49206349206349204, 'f1': 0.5210084033613446}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.49306197964847365, 'r': 0.7097203728362184, 'f1': 0.5818777292576419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5165719696969697, 'r': 0.6975703324808185, 'f1': 0.5935799782372144}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:46:18.879951: step: 4/533, loss: 0.2273930162191391
2023-01-22 23:46:20.033344: step: 8/533, loss: 0.11745396256446838
2023-01-22 23:46:21.227751: step: 12/533, loss: 0.8195672631263733
2023-01-22 23:46:22.428900: step: 16/533, loss: 0.9431135058403015
2023-01-22 23:46:23.625746: step: 20/533, loss: 1.7726690769195557
2023-01-22 23:46:24.779732: step: 24/533, loss: 0.18240299820899963
2023-01-22 23:46:25.925556: step: 28/533, loss: 0.5393819808959961
2023-01-22 23:46:27.082319: step: 32/533, loss: 0.35707321763038635
2023-01-22 23:46:28.233694: step: 36/533, loss: 0.1625724732875824
2023-01-22 23:46:29.464400: step: 40/533, loss: 0.444752961397171
2023-01-22 23:46:30.637352: step: 44/533, loss: 0.6659727096557617
2023-01-22 23:46:31.837461: step: 48/533, loss: 0.41809549927711487
2023-01-22 23:46:33.028761: step: 52/533, loss: 0.14960438013076782
2023-01-22 23:46:34.204562: step: 56/533, loss: 0.4455803334712982
2023-01-22 23:46:35.335630: step: 60/533, loss: 0.11054739356040955
2023-01-22 23:46:36.496637: step: 64/533, loss: 0.15095539391040802
2023-01-22 23:46:37.686483: step: 68/533, loss: 0.20855793356895447
2023-01-22 23:46:38.867467: step: 72/533, loss: 0.09738487750291824
2023-01-22 23:46:40.038101: step: 76/533, loss: 0.1486688256263733
2023-01-22 23:46:41.244279: step: 80/533, loss: 0.2405291646718979
2023-01-22 23:46:42.403699: step: 84/533, loss: 0.18646469712257385
2023-01-22 23:46:43.617672: step: 88/533, loss: 0.8988907337188721
2023-01-22 23:46:44.784780: step: 92/533, loss: 0.5040372014045715
2023-01-22 23:46:45.991750: step: 96/533, loss: 1.945794701576233
2023-01-22 23:46:47.164185: step: 100/533, loss: 0.07698164135217667
2023-01-22 23:46:48.340193: step: 104/533, loss: 0.28211650252342224
2023-01-22 23:46:49.543840: step: 108/533, loss: 1.2997928857803345
2023-01-22 23:46:50.731134: step: 112/533, loss: 0.8248919248580933
2023-01-22 23:46:51.899829: step: 116/533, loss: 0.1631982922554016
2023-01-22 23:46:53.036719: step: 120/533, loss: 0.3366301655769348
2023-01-22 23:46:54.211379: step: 124/533, loss: 0.22430419921875
2023-01-22 23:46:55.379137: step: 128/533, loss: 1.0289384126663208
2023-01-22 23:46:56.536037: step: 132/533, loss: 0.3962440490722656
2023-01-22 23:46:57.696466: step: 136/533, loss: 0.24397139251232147
2023-01-22 23:46:58.877300: step: 140/533, loss: 0.9660804271697998
2023-01-22 23:47:00.074182: step: 144/533, loss: 0.35625410079956055
2023-01-22 23:47:01.302000: step: 148/533, loss: 1.0034176111221313
2023-01-22 23:47:02.497002: step: 152/533, loss: 0.060857679694890976
2023-01-22 23:47:03.710794: step: 156/533, loss: 0.2796187400817871
2023-01-22 23:47:04.863151: step: 160/533, loss: 0.06856928020715714
2023-01-22 23:47:06.039574: step: 164/533, loss: 0.42069217562675476
2023-01-22 23:47:07.232451: step: 168/533, loss: 1.717408299446106
2023-01-22 23:47:08.410393: step: 172/533, loss: 0.53558349609375
2023-01-22 23:47:09.550399: step: 176/533, loss: 0.12073850631713867
2023-01-22 23:47:10.715514: step: 180/533, loss: 0.13690312206745148
2023-01-22 23:47:11.933323: step: 184/533, loss: 1.05412757396698
2023-01-22 23:47:13.135788: step: 188/533, loss: 6.908061981201172
2023-01-22 23:47:14.272998: step: 192/533, loss: 0.5959917902946472
2023-01-22 23:47:15.414746: step: 196/533, loss: 0.07897396385669708
2023-01-22 23:47:16.601924: step: 200/533, loss: 3.012596368789673
2023-01-22 23:47:17.801691: step: 204/533, loss: 0.21523308753967285
2023-01-22 23:47:18.975959: step: 208/533, loss: 0.12647505104541779
2023-01-22 23:47:20.137055: step: 212/533, loss: 0.6816475987434387
2023-01-22 23:47:21.307143: step: 216/533, loss: 0.11413614451885223
2023-01-22 23:47:22.489381: step: 220/533, loss: 0.7274017930030823
2023-01-22 23:47:23.656866: step: 224/533, loss: 0.43675634264945984
2023-01-22 23:47:24.813494: step: 228/533, loss: 0.7292206883430481
2023-01-22 23:47:25.952530: step: 232/533, loss: 0.16568660736083984
2023-01-22 23:47:27.140122: step: 236/533, loss: 0.2401791661977768
2023-01-22 23:47:28.333301: step: 240/533, loss: 1.20443856716156
2023-01-22 23:47:29.508746: step: 244/533, loss: 0.08509984612464905
2023-01-22 23:47:30.726032: step: 248/533, loss: 1.643349528312683
2023-01-22 23:47:31.924806: step: 252/533, loss: 0.22615928947925568
2023-01-22 23:47:33.107699: step: 256/533, loss: 0.05160102993249893
2023-01-22 23:47:34.257397: step: 260/533, loss: 0.390639990568161
2023-01-22 23:47:35.439883: step: 264/533, loss: 0.14797353744506836
2023-01-22 23:47:36.639567: step: 268/533, loss: 0.9673904776573181
2023-01-22 23:47:37.860916: step: 272/533, loss: 0.3699526786804199
2023-01-22 23:47:39.041166: step: 276/533, loss: 0.636673092842102
2023-01-22 23:47:40.211776: step: 280/533, loss: 1.3742446899414062
2023-01-22 23:47:41.375315: step: 284/533, loss: 1.0109410285949707
2023-01-22 23:47:42.564978: step: 288/533, loss: 0.38311767578125
2023-01-22 23:47:43.772019: step: 292/533, loss: 0.47721540927886963
2023-01-22 23:47:44.965995: step: 296/533, loss: 1.3345869779586792
2023-01-22 23:47:46.188287: step: 300/533, loss: 0.8420354723930359
2023-01-22 23:47:47.398621: step: 304/533, loss: 0.24124260246753693
2023-01-22 23:47:48.594851: step: 308/533, loss: 0.23484164476394653
2023-01-22 23:47:49.770357: step: 312/533, loss: 0.303290456533432
2023-01-22 23:47:50.958680: step: 316/533, loss: 0.8358780145645142
2023-01-22 23:47:52.130283: step: 320/533, loss: 0.13641862571239471
2023-01-22 23:47:53.356626: step: 324/533, loss: 1.2870972156524658
2023-01-22 23:47:54.551146: step: 328/533, loss: 0.7284207940101624
2023-01-22 23:47:55.712380: step: 332/533, loss: 0.5092397928237915
2023-01-22 23:47:56.900221: step: 336/533, loss: 0.892011284828186
2023-01-22 23:47:58.099952: step: 340/533, loss: 0.8644672632217407
2023-01-22 23:47:59.305378: step: 344/533, loss: 0.04526777192950249
2023-01-22 23:48:00.490415: step: 348/533, loss: 0.3578372895717621
2023-01-22 23:48:01.680255: step: 352/533, loss: 1.10097336769104
2023-01-22 23:48:02.873633: step: 356/533, loss: 0.7220709323883057
2023-01-22 23:48:04.026312: step: 360/533, loss: 0.1650390625
2023-01-22 23:48:05.213471: step: 364/533, loss: 0.19318580627441406
2023-01-22 23:48:06.359139: step: 368/533, loss: 1.388374924659729
2023-01-22 23:48:07.486691: step: 372/533, loss: 0.20563922822475433
2023-01-22 23:48:08.692233: step: 376/533, loss: 1.1659611463546753
2023-01-22 23:48:09.863412: step: 380/533, loss: 0.49511605501174927
2023-01-22 23:48:11.010462: step: 384/533, loss: 0.08295345306396484
2023-01-22 23:48:12.184904: step: 388/533, loss: 0.7571626305580139
2023-01-22 23:48:13.377425: step: 392/533, loss: 0.6921822428703308
2023-01-22 23:48:14.558436: step: 396/533, loss: 0.17010803520679474
2023-01-22 23:48:15.737877: step: 400/533, loss: 0.20108766853809357
2023-01-22 23:48:16.955217: step: 404/533, loss: 1.3238558769226074
2023-01-22 23:48:18.152608: step: 408/533, loss: 1.0351576805114746
2023-01-22 23:48:19.323488: step: 412/533, loss: 0.37799471616744995
2023-01-22 23:48:20.471332: step: 416/533, loss: 0.7027173042297363
2023-01-22 23:48:21.629723: step: 420/533, loss: 0.11830691993236542
2023-01-22 23:48:22.807971: step: 424/533, loss: 0.2692562937736511
2023-01-22 23:48:23.988134: step: 428/533, loss: 0.0980944111943245
2023-01-22 23:48:25.174557: step: 432/533, loss: 0.372312068939209
2023-01-22 23:48:26.336752: step: 436/533, loss: 0.39765799045562744
2023-01-22 23:48:27.514182: step: 440/533, loss: 0.48756155371665955
2023-01-22 23:48:28.679698: step: 444/533, loss: 0.08249840885400772
2023-01-22 23:48:29.868881: step: 448/533, loss: 1.5067517757415771
2023-01-22 23:48:31.053057: step: 452/533, loss: 0.2680312991142273
2023-01-22 23:48:32.239533: step: 456/533, loss: 1.0247547626495361
2023-01-22 23:48:33.413977: step: 460/533, loss: 0.25795361399650574
2023-01-22 23:48:34.580274: step: 464/533, loss: 0.6210354566574097
2023-01-22 23:48:35.762876: step: 468/533, loss: 0.06505861133337021
2023-01-22 23:48:36.951176: step: 472/533, loss: 0.9583412408828735
2023-01-22 23:48:38.077213: step: 476/533, loss: 0.1402682363986969
2023-01-22 23:48:39.244919: step: 480/533, loss: 0.7231633067131042
2023-01-22 23:48:40.425959: step: 484/533, loss: 0.6232940554618835
2023-01-22 23:48:41.600459: step: 488/533, loss: 0.28297579288482666
2023-01-22 23:48:42.760723: step: 492/533, loss: 0.1705310344696045
2023-01-22 23:48:43.942980: step: 496/533, loss: 0.23556914925575256
2023-01-22 23:48:45.116319: step: 500/533, loss: 0.35297250747680664
2023-01-22 23:48:46.240336: step: 504/533, loss: 0.06654729694128036
2023-01-22 23:48:47.420472: step: 508/533, loss: 0.29731130599975586
2023-01-22 23:48:48.616324: step: 512/533, loss: 0.7469516396522522
2023-01-22 23:48:49.764382: step: 516/533, loss: 0.47540247440338135
2023-01-22 23:48:50.951708: step: 520/533, loss: 0.27656564116477966
2023-01-22 23:48:52.085786: step: 524/533, loss: 0.7852625250816345
2023-01-22 23:48:53.282047: step: 528/533, loss: 0.48299741744995117
2023-01-22 23:48:54.459992: step: 532/533, loss: 0.49583935737609863
2023-01-22 23:48:55.637888: step: 536/533, loss: 0.238701730966568
2023-01-22 23:48:56.823362: step: 540/533, loss: 0.1043207198381424
2023-01-22 23:48:58.012533: step: 544/533, loss: 1.0323508977890015
2023-01-22 23:48:59.161534: step: 548/533, loss: 0.24594631791114807
2023-01-22 23:49:00.330786: step: 552/533, loss: 0.7298108339309692
2023-01-22 23:49:01.509519: step: 556/533, loss: 0.5059745907783508
2023-01-22 23:49:02.682116: step: 560/533, loss: 0.1618526428937912
2023-01-22 23:49:03.817840: step: 564/533, loss: 0.09630686044692993
2023-01-22 23:49:05.021865: step: 568/533, loss: 0.6778080463409424
2023-01-22 23:49:06.149491: step: 572/533, loss: 0.07121472805738449
2023-01-22 23:49:07.336310: step: 576/533, loss: 0.5281625986099243
2023-01-22 23:49:08.531451: step: 580/533, loss: 0.06455035507678986
2023-01-22 23:49:09.725984: step: 584/533, loss: 7.478963851928711
2023-01-22 23:49:10.917299: step: 588/533, loss: 0.7464495897293091
2023-01-22 23:49:12.066501: step: 592/533, loss: 0.18666720390319824
2023-01-22 23:49:13.219915: step: 596/533, loss: 0.7304089665412903
2023-01-22 23:49:14.389857: step: 600/533, loss: 0.7658006548881531
2023-01-22 23:49:15.603676: step: 604/533, loss: 0.09449243545532227
2023-01-22 23:49:16.768762: step: 608/533, loss: 0.3147008419036865
2023-01-22 23:49:17.947376: step: 612/533, loss: 0.17011529207229614
2023-01-22 23:49:19.117629: step: 616/533, loss: 0.22066155076026917
2023-01-22 23:49:20.291807: step: 620/533, loss: 0.7816414833068848
2023-01-22 23:49:21.471632: step: 624/533, loss: 1.3505761623382568
2023-01-22 23:49:22.619895: step: 628/533, loss: 1.430994987487793
2023-01-22 23:49:23.810692: step: 632/533, loss: 0.2059134542942047
2023-01-22 23:49:24.968998: step: 636/533, loss: 0.6495293974876404
2023-01-22 23:49:26.160703: step: 640/533, loss: 0.7417030334472656
2023-01-22 23:49:27.323011: step: 644/533, loss: 0.4340957701206207
2023-01-22 23:49:28.456448: step: 648/533, loss: 0.3562898635864258
2023-01-22 23:49:29.602571: step: 652/533, loss: 1.0801200866699219
2023-01-22 23:49:30.766999: step: 656/533, loss: 0.21649666130542755
2023-01-22 23:49:31.925185: step: 660/533, loss: 0.1450033187866211
2023-01-22 23:49:33.066010: step: 664/533, loss: 0.8730990290641785
2023-01-22 23:49:34.235377: step: 668/533, loss: 0.17216749489307404
2023-01-22 23:49:35.397991: step: 672/533, loss: 0.16926175355911255
2023-01-22 23:49:36.567923: step: 676/533, loss: 0.6977423429489136
2023-01-22 23:49:37.746071: step: 680/533, loss: 0.4301180839538574
2023-01-22 23:49:38.931381: step: 684/533, loss: 0.199737548828125
2023-01-22 23:49:40.151480: step: 688/533, loss: 1.4486771821975708
2023-01-22 23:49:41.289562: step: 692/533, loss: 0.5181573033332825
2023-01-22 23:49:42.462606: step: 696/533, loss: 0.07946591824293137
2023-01-22 23:49:43.621278: step: 700/533, loss: 0.4264151155948639
2023-01-22 23:49:44.810415: step: 704/533, loss: 0.21281233429908752
2023-01-22 23:49:46.003233: step: 708/533, loss: 0.9650977849960327
2023-01-22 23:49:47.213778: step: 712/533, loss: 0.33989372849464417
2023-01-22 23:49:48.378184: step: 716/533, loss: 0.12522058188915253
2023-01-22 23:49:49.578221: step: 720/533, loss: 0.1704375296831131
2023-01-22 23:49:50.764247: step: 724/533, loss: 0.21190881729125977
2023-01-22 23:49:51.929203: step: 728/533, loss: 0.24946996569633484
2023-01-22 23:49:53.099744: step: 732/533, loss: 0.7441123723983765
2023-01-22 23:49:54.268631: step: 736/533, loss: 0.05891933664679527
2023-01-22 23:49:55.458915: step: 740/533, loss: 0.20319104194641113
2023-01-22 23:49:56.672853: step: 744/533, loss: 1.7787359952926636
2023-01-22 23:49:57.854121: step: 748/533, loss: 1.0156267881393433
2023-01-22 23:49:59.048384: step: 752/533, loss: 0.16084283590316772
2023-01-22 23:50:00.267623: step: 756/533, loss: 0.3467342257499695
2023-01-22 23:50:01.436291: step: 760/533, loss: 1.0924389362335205
2023-01-22 23:50:02.596742: step: 764/533, loss: 0.09603042900562286
2023-01-22 23:50:03.804465: step: 768/533, loss: 0.3103495240211487
2023-01-22 23:50:04.961215: step: 772/533, loss: 0.150017648935318
2023-01-22 23:50:06.137500: step: 776/533, loss: 0.1918269693851471
2023-01-22 23:50:07.298454: step: 780/533, loss: 0.11927299201488495
2023-01-22 23:50:08.462020: step: 784/533, loss: 0.3759794235229492
2023-01-22 23:50:09.625034: step: 788/533, loss: 0.8447084426879883
2023-01-22 23:50:10.788994: step: 792/533, loss: 0.13505783677101135
2023-01-22 23:50:11.956446: step: 796/533, loss: 0.14870567619800568
2023-01-22 23:50:13.141571: step: 800/533, loss: 0.25327959656715393
2023-01-22 23:50:14.287263: step: 804/533, loss: 0.05911578983068466
2023-01-22 23:50:15.488941: step: 808/533, loss: 1.1324101686477661
2023-01-22 23:50:16.634346: step: 812/533, loss: 0.7645180821418762
2023-01-22 23:50:17.792228: step: 816/533, loss: 0.11914453655481339
2023-01-22 23:50:18.999497: step: 820/533, loss: 0.6584722399711609
2023-01-22 23:50:20.164366: step: 824/533, loss: 0.11634072661399841
2023-01-22 23:50:21.378522: step: 828/533, loss: 0.296133816242218
2023-01-22 23:50:22.591526: step: 832/533, loss: 2.2104575634002686
2023-01-22 23:50:23.771657: step: 836/533, loss: 0.26594123244285583
2023-01-22 23:50:25.003105: step: 840/533, loss: 0.29918622970581055
2023-01-22 23:50:26.211408: step: 844/533, loss: 1.1086997985839844
2023-01-22 23:50:27.384460: step: 848/533, loss: 0.13089317083358765
2023-01-22 23:50:28.575962: step: 852/533, loss: 0.08148898929357529
2023-01-22 23:50:29.730179: step: 856/533, loss: 0.07526750862598419
2023-01-22 23:50:30.887339: step: 860/533, loss: 0.05287761986255646
2023-01-22 23:50:32.041651: step: 864/533, loss: 0.24665486812591553
2023-01-22 23:50:33.223169: step: 868/533, loss: 0.9336276650428772
2023-01-22 23:50:34.382026: step: 872/533, loss: 0.24038414657115936
2023-01-22 23:50:35.573049: step: 876/533, loss: 0.3202973008155823
2023-01-22 23:50:36.754943: step: 880/533, loss: 0.47325411438941956
2023-01-22 23:50:37.919703: step: 884/533, loss: 0.718765914440155
2023-01-22 23:50:39.073642: step: 888/533, loss: 0.05490746721625328
2023-01-22 23:50:40.214460: step: 892/533, loss: 0.4450978636741638
2023-01-22 23:50:41.412953: step: 896/533, loss: 0.13848859071731567
2023-01-22 23:50:42.574155: step: 900/533, loss: 0.4307509958744049
2023-01-22 23:50:43.711224: step: 904/533, loss: 6.461243152618408
2023-01-22 23:50:44.865634: step: 908/533, loss: 1.3066799640655518
2023-01-22 23:50:46.031375: step: 912/533, loss: 0.7175735831260681
2023-01-22 23:50:47.194763: step: 916/533, loss: 1.0465493202209473
2023-01-22 23:50:48.454485: step: 920/533, loss: 0.42484796047210693
2023-01-22 23:50:49.623875: step: 924/533, loss: 0.28290843963623047
2023-01-22 23:50:50.787995: step: 928/533, loss: 0.09106452763080597
2023-01-22 23:50:51.938867: step: 932/533, loss: 0.16259175539016724
2023-01-22 23:50:53.150416: step: 936/533, loss: 0.15368108451366425
2023-01-22 23:50:54.375956: step: 940/533, loss: 0.18690046668052673
2023-01-22 23:50:55.512448: step: 944/533, loss: 1.2590035200119019
2023-01-22 23:50:56.669396: step: 948/533, loss: 0.16667777299880981
2023-01-22 23:50:57.870434: step: 952/533, loss: 0.14748039841651917
2023-01-22 23:50:59.055879: step: 956/533, loss: 0.17940634489059448
2023-01-22 23:51:00.227171: step: 960/533, loss: 0.5820997953414917
2023-01-22 23:51:01.403924: step: 964/533, loss: 1.5327001810073853
2023-01-22 23:51:02.584212: step: 968/533, loss: 0.6402400732040405
2023-01-22 23:51:03.746278: step: 972/533, loss: 0.14987602829933167
2023-01-22 23:51:04.951726: step: 976/533, loss: 0.7734742164611816
2023-01-22 23:51:06.123561: step: 980/533, loss: 1.6735639572143555
2023-01-22 23:51:07.287536: step: 984/533, loss: 0.6829612255096436
2023-01-22 23:51:08.435746: step: 988/533, loss: 8.01281452178955
2023-01-22 23:51:09.625937: step: 992/533, loss: 0.45811301469802856
2023-01-22 23:51:10.793327: step: 996/533, loss: 0.10504613071680069
2023-01-22 23:51:11.980696: step: 1000/533, loss: 0.1916123628616333
2023-01-22 23:51:13.134825: step: 1004/533, loss: 0.23422221839427948
2023-01-22 23:51:14.342554: step: 1008/533, loss: 0.35816287994384766
2023-01-22 23:51:15.514058: step: 1012/533, loss: 0.21505865454673767
2023-01-22 23:51:16.663435: step: 1016/533, loss: 0.3315998315811157
2023-01-22 23:51:17.839316: step: 1020/533, loss: 0.08506689220666885
2023-01-22 23:51:19.019103: step: 1024/533, loss: 6.508427619934082
2023-01-22 23:51:20.171299: step: 1028/533, loss: 0.16155119240283966
2023-01-22 23:51:21.299126: step: 1032/533, loss: 0.21006269752979279
2023-01-22 23:51:22.462857: step: 1036/533, loss: 0.1542145311832428
2023-01-22 23:51:23.672663: step: 1040/533, loss: 0.24551811814308167
2023-01-22 23:51:24.843097: step: 1044/533, loss: 0.3328459858894348
2023-01-22 23:51:26.010571: step: 1048/533, loss: 0.6866517663002014
2023-01-22 23:51:27.160742: step: 1052/533, loss: 0.21656756103038788
2023-01-22 23:51:28.340858: step: 1056/533, loss: 0.16592836380004883
2023-01-22 23:51:29.529355: step: 1060/533, loss: 0.3690887689590454
2023-01-22 23:51:30.718451: step: 1064/533, loss: 0.23401856422424316
2023-01-22 23:51:31.872476: step: 1068/533, loss: 0.5108942985534668
2023-01-22 23:51:33.067187: step: 1072/533, loss: 0.09856872260570526
2023-01-22 23:51:34.212133: step: 1076/533, loss: 0.5681627988815308
2023-01-22 23:51:35.399012: step: 1080/533, loss: 0.6977648735046387
2023-01-22 23:51:36.574651: step: 1084/533, loss: 7.22731351852417
2023-01-22 23:51:37.732685: step: 1088/533, loss: 0.2014133632183075
2023-01-22 23:51:38.920686: step: 1092/533, loss: 0.28654471039772034
2023-01-22 23:51:40.088303: step: 1096/533, loss: 0.12103691697120667
2023-01-22 23:51:41.243700: step: 1100/533, loss: 0.9488382339477539
2023-01-22 23:51:42.462447: step: 1104/533, loss: 0.07610297203063965
2023-01-22 23:51:43.643492: step: 1108/533, loss: 0.16119880974292755
2023-01-22 23:51:44.837567: step: 1112/533, loss: 0.13445310294628143
2023-01-22 23:51:46.006448: step: 1116/533, loss: 0.11755600571632385
2023-01-22 23:51:47.162069: step: 1120/533, loss: 0.29532432556152344
2023-01-22 23:51:48.349377: step: 1124/533, loss: 0.8633362054824829
2023-01-22 23:51:49.535790: step: 1128/533, loss: 6.540116310119629
2023-01-22 23:51:50.683059: step: 1132/533, loss: 0.2515488266944885
2023-01-22 23:51:51.802364: step: 1136/533, loss: 0.8181860446929932
2023-01-22 23:51:52.971946: step: 1140/533, loss: 0.2142030894756317
2023-01-22 23:51:54.182937: step: 1144/533, loss: 0.3745500445365906
2023-01-22 23:51:55.361209: step: 1148/533, loss: 0.8272171020507812
2023-01-22 23:51:56.509000: step: 1152/533, loss: 0.06278391182422638
2023-01-22 23:51:57.689866: step: 1156/533, loss: 0.1989230215549469
2023-01-22 23:51:58.891398: step: 1160/533, loss: 0.27896958589553833
2023-01-22 23:52:00.076004: step: 1164/533, loss: 0.20488262176513672
2023-01-22 23:52:01.267640: step: 1168/533, loss: 0.38272780179977417
2023-01-22 23:52:02.430140: step: 1172/533, loss: 0.06994666904211044
2023-01-22 23:52:03.572149: step: 1176/533, loss: 0.18634013831615448
2023-01-22 23:52:04.703774: step: 1180/533, loss: 0.743073582649231
2023-01-22 23:52:05.876130: step: 1184/533, loss: 0.0941368043422699
2023-01-22 23:52:07.057170: step: 1188/533, loss: 0.8243561387062073
2023-01-22 23:52:08.269078: step: 1192/533, loss: 0.19166569411754608
2023-01-22 23:52:09.500155: step: 1196/533, loss: 6.266689777374268
2023-01-22 23:52:10.680614: step: 1200/533, loss: 0.06868753582239151
2023-01-22 23:52:11.883163: step: 1204/533, loss: 0.19443902373313904
2023-01-22 23:52:13.030053: step: 1208/533, loss: 0.13472004234790802
2023-01-22 23:52:14.235111: step: 1212/533, loss: 0.9054728746414185
2023-01-22 23:52:15.417943: step: 1216/533, loss: 0.12195806950330734
2023-01-22 23:52:16.588211: step: 1220/533, loss: 0.17970800399780273
2023-01-22 23:52:17.750507: step: 1224/533, loss: 0.12070713937282562
2023-01-22 23:52:18.976811: step: 1228/533, loss: 1.4752812385559082
2023-01-22 23:52:20.158761: step: 1232/533, loss: 0.7454493641853333
2023-01-22 23:52:21.320169: step: 1236/533, loss: 0.06914544105529785
2023-01-22 23:52:22.503684: step: 1240/533, loss: 1.2100070714950562
2023-01-22 23:52:23.670169: step: 1244/533, loss: 0.10302410274744034
2023-01-22 23:52:24.832640: step: 1248/533, loss: 0.21132364869117737
2023-01-22 23:52:25.990579: step: 1252/533, loss: 0.2659677565097809
2023-01-22 23:52:27.161286: step: 1256/533, loss: 0.19050368666648865
2023-01-22 23:52:28.336311: step: 1260/533, loss: 0.2024466097354889
2023-01-22 23:52:29.498521: step: 1264/533, loss: 0.5930944681167603
2023-01-22 23:52:30.693177: step: 1268/533, loss: 0.44186297059059143
2023-01-22 23:52:31.889665: step: 1272/533, loss: 0.3731943368911743
2023-01-22 23:52:33.110835: step: 1276/533, loss: 0.1335306167602539
2023-01-22 23:52:34.272486: step: 1280/533, loss: 1.0604174137115479
2023-01-22 23:52:35.453827: step: 1284/533, loss: 0.13002681732177734
2023-01-22 23:52:36.628352: step: 1288/533, loss: 0.9454756379127502
2023-01-22 23:52:37.816707: step: 1292/533, loss: 0.18780165910720825
2023-01-22 23:52:38.977640: step: 1296/533, loss: 0.20250433683395386
2023-01-22 23:52:40.163925: step: 1300/533, loss: 0.6443038582801819
2023-01-22 23:52:41.319119: step: 1304/533, loss: 0.8326841592788696
2023-01-22 23:52:42.486623: step: 1308/533, loss: 0.2797355055809021
2023-01-22 23:52:43.640203: step: 1312/533, loss: 0.09797344356775284
2023-01-22 23:52:44.827855: step: 1316/533, loss: 0.7025970220565796
2023-01-22 23:52:45.994939: step: 1320/533, loss: 0.08682501316070557
2023-01-22 23:52:47.190910: step: 1324/533, loss: 0.7677488923072815
2023-01-22 23:52:48.345472: step: 1328/533, loss: 1.3780176639556885
2023-01-22 23:52:49.502167: step: 1332/533, loss: 1.6198054552078247
2023-01-22 23:52:50.700052: step: 1336/533, loss: 0.3698953688144684
2023-01-22 23:52:51.855391: step: 1340/533, loss: 0.21812386810779572
2023-01-22 23:52:53.004964: step: 1344/533, loss: 1.2627613544464111
2023-01-22 23:52:54.167141: step: 1348/533, loss: 0.28452783823013306
2023-01-22 23:52:55.332535: step: 1352/533, loss: 0.879878580570221
2023-01-22 23:52:56.529813: step: 1356/533, loss: 0.3955039978027344
2023-01-22 23:52:57.694260: step: 1360/533, loss: 0.06800947338342667
2023-01-22 23:52:58.854927: step: 1364/533, loss: 0.04477305710315704
2023-01-22 23:53:00.014061: step: 1368/533, loss: 0.1684991866350174
2023-01-22 23:53:01.200857: step: 1372/533, loss: 0.35392212867736816
2023-01-22 23:53:02.366794: step: 1376/533, loss: 0.13616938889026642
2023-01-22 23:53:03.539765: step: 1380/533, loss: 7.286977767944336
2023-01-22 23:53:04.709510: step: 1384/533, loss: 0.15678483247756958
2023-01-22 23:53:05.919621: step: 1388/533, loss: 0.8577432036399841
2023-01-22 23:53:07.069375: step: 1392/533, loss: 0.11835689097642899
2023-01-22 23:53:08.257185: step: 1396/533, loss: 0.10267496109008789
2023-01-22 23:53:09.434912: step: 1400/533, loss: 0.6827402114868164
2023-01-22 23:53:10.626973: step: 1404/533, loss: 0.3727491497993469
2023-01-22 23:53:11.734704: step: 1408/533, loss: 0.19902926683425903
2023-01-22 23:53:12.875143: step: 1412/533, loss: 0.05669289082288742
2023-01-22 23:53:14.045797: step: 1416/533, loss: 0.4112869203090668
2023-01-22 23:53:15.229654: step: 1420/533, loss: 0.11731824278831482
2023-01-22 23:53:16.393672: step: 1424/533, loss: 0.2478063702583313
2023-01-22 23:53:17.565911: step: 1428/533, loss: 0.6963310241699219
2023-01-22 23:53:18.733657: step: 1432/533, loss: 1.1325640678405762
2023-01-22 23:53:19.952575: step: 1436/533, loss: 0.2118019163608551
2023-01-22 23:53:21.098494: step: 1440/533, loss: 0.31069833040237427
2023-01-22 23:53:22.281384: step: 1444/533, loss: 0.301180362701416
2023-01-22 23:53:23.442119: step: 1448/533, loss: 0.11280126869678497
2023-01-22 23:53:24.594387: step: 1452/533, loss: 6.658930778503418
2023-01-22 23:53:25.785914: step: 1456/533, loss: 0.20187149941921234
2023-01-22 23:53:27.008581: step: 1460/533, loss: 0.46133309602737427
2023-01-22 23:53:28.187378: step: 1464/533, loss: 0.1584792584180832
2023-01-22 23:53:29.339718: step: 1468/533, loss: 0.5543267130851746
2023-01-22 23:53:30.488828: step: 1472/533, loss: 0.8263395428657532
2023-01-22 23:53:31.694641: step: 1476/533, loss: 0.48075762391090393
2023-01-22 23:53:32.853369: step: 1480/533, loss: 0.09838028252124786
2023-01-22 23:53:34.039785: step: 1484/533, loss: 0.15344391763210297
2023-01-22 23:53:35.239096: step: 1488/533, loss: 0.737304151058197
2023-01-22 23:53:36.438338: step: 1492/533, loss: 0.8947690725326538
2023-01-22 23:53:37.638199: step: 1496/533, loss: 0.511588454246521
2023-01-22 23:53:38.788870: step: 1500/533, loss: 0.1525021642446518
2023-01-22 23:53:39.977121: step: 1504/533, loss: 0.11327085644006729
2023-01-22 23:53:41.148058: step: 1508/533, loss: 1.546418309211731
2023-01-22 23:53:42.307019: step: 1512/533, loss: 0.2898986041545868
2023-01-22 23:53:43.451740: step: 1516/533, loss: 0.7356467247009277
2023-01-22 23:53:44.599296: step: 1520/533, loss: 7.215470790863037
2023-01-22 23:53:45.778252: step: 1524/533, loss: 1.7791252136230469
2023-01-22 23:53:46.943769: step: 1528/533, loss: 0.27869662642478943
2023-01-22 23:53:48.098270: step: 1532/533, loss: 0.9292815327644348
2023-01-22 23:53:49.302944: step: 1536/533, loss: 0.2675338685512543
2023-01-22 23:53:50.474002: step: 1540/533, loss: 0.4899996817111969
2023-01-22 23:53:51.617013: step: 1544/533, loss: 0.10808859020471573
2023-01-22 23:53:52.783148: step: 1548/533, loss: 0.3228895664215088
2023-01-22 23:53:53.947672: step: 1552/533, loss: 0.06798505783081055
2023-01-22 23:53:55.149549: step: 1556/533, loss: 0.3320944905281067
2023-01-22 23:53:56.320520: step: 1560/533, loss: 1.806983232498169
2023-01-22 23:53:57.509199: step: 1564/533, loss: 1.048262119293213
2023-01-22 23:53:58.643466: step: 1568/533, loss: 0.13699588179588318
2023-01-22 23:53:59.772748: step: 1572/533, loss: 0.2673904001712799
2023-01-22 23:54:00.948374: step: 1576/533, loss: 0.8985964059829712
2023-01-22 23:54:02.147572: step: 1580/533, loss: 1.1982507705688477
2023-01-22 23:54:03.322713: step: 1584/533, loss: 0.22475290298461914
2023-01-22 23:54:04.544143: step: 1588/533, loss: 1.7302381992340088
2023-01-22 23:54:05.749279: step: 1592/533, loss: 0.8524916768074036
2023-01-22 23:54:06.949003: step: 1596/533, loss: 0.2432946264743805
2023-01-22 23:54:08.074414: step: 1600/533, loss: 13.707395553588867
2023-01-22 23:54:09.262702: step: 1604/533, loss: 0.15675364434719086
2023-01-22 23:54:10.429265: step: 1608/533, loss: 0.0466889850795269
2023-01-22 23:54:11.585417: step: 1612/533, loss: 0.4817764163017273
2023-01-22 23:54:12.786606: step: 1616/533, loss: 0.2190229445695877
2023-01-22 23:54:13.947102: step: 1620/533, loss: 0.4787437319755554
2023-01-22 23:54:15.102456: step: 1624/533, loss: 0.2182387113571167
2023-01-22 23:54:16.303029: step: 1628/533, loss: 1.2036696672439575
2023-01-22 23:54:17.477154: step: 1632/533, loss: 1.0908328294754028
2023-01-22 23:54:18.632123: step: 1636/533, loss: 0.12211751937866211
2023-01-22 23:54:19.823913: step: 1640/533, loss: 0.4149482548236847
2023-01-22 23:54:21.005034: step: 1644/533, loss: 0.34169453382492065
2023-01-22 23:54:22.217308: step: 1648/533, loss: 0.9192399978637695
2023-01-22 23:54:23.423816: step: 1652/533, loss: 0.0711483508348465
2023-01-22 23:54:24.593784: step: 1656/533, loss: 0.12819892168045044
2023-01-22 23:54:25.784740: step: 1660/533, loss: 0.052781008183956146
2023-01-22 23:54:26.943349: step: 1664/533, loss: 0.5178384780883789
2023-01-22 23:54:28.115183: step: 1668/533, loss: 0.20390301942825317
2023-01-22 23:54:29.264947: step: 1672/533, loss: 0.1226007267832756
2023-01-22 23:54:30.437354: step: 1676/533, loss: 0.16699305176734924
2023-01-22 23:54:31.622023: step: 1680/533, loss: 0.36003148555755615
2023-01-22 23:54:32.784824: step: 1684/533, loss: 0.14527592062950134
2023-01-22 23:54:33.953606: step: 1688/533, loss: 0.09590520709753036
2023-01-22 23:54:35.158574: step: 1692/533, loss: 0.11949887871742249
2023-01-22 23:54:36.337014: step: 1696/533, loss: 0.21050110459327698
2023-01-22 23:54:37.544911: step: 1700/533, loss: 0.17268845438957214
2023-01-22 23:54:38.693549: step: 1704/533, loss: 0.24717727303504944
2023-01-22 23:54:39.845758: step: 1708/533, loss: 0.38135844469070435
2023-01-22 23:54:41.018440: step: 1712/533, loss: 0.06689977645874023
2023-01-22 23:54:42.208639: step: 1716/533, loss: 0.12919697165489197
2023-01-22 23:54:43.377533: step: 1720/533, loss: 0.17385978996753693
2023-01-22 23:54:44.577999: step: 1724/533, loss: 0.4880429208278656
2023-01-22 23:54:45.798218: step: 1728/533, loss: 0.14656944572925568
2023-01-22 23:54:46.966555: step: 1732/533, loss: 0.16757328808307648
2023-01-22 23:54:48.178730: step: 1736/533, loss: 0.58705735206604
2023-01-22 23:54:49.321769: step: 1740/533, loss: 0.46039533615112305
2023-01-22 23:54:50.463233: step: 1744/533, loss: 0.08018722385168076
2023-01-22 23:54:51.656131: step: 1748/533, loss: 0.6703826785087585
2023-01-22 23:54:52.793299: step: 1752/533, loss: 0.08001342415809631
2023-01-22 23:54:53.948370: step: 1756/533, loss: 0.5173451900482178
2023-01-22 23:54:55.173154: step: 1760/533, loss: 1.1369085311889648
2023-01-22 23:54:56.363843: step: 1764/533, loss: 0.47411566972732544
2023-01-22 23:54:57.543980: step: 1768/533, loss: 0.17189660668373108
2023-01-22 23:54:58.674680: step: 1772/533, loss: 0.16097822785377502
2023-01-22 23:54:59.839616: step: 1776/533, loss: 1.8662508726119995
2023-01-22 23:55:01.013386: step: 1780/533, loss: 0.49722155928611755
2023-01-22 23:55:02.203359: step: 1784/533, loss: 0.21301144361495972
2023-01-22 23:55:03.426811: step: 1788/533, loss: 0.15982326865196228
2023-01-22 23:55:04.679815: step: 1792/533, loss: 0.17234042286872864
2023-01-22 23:55:05.834923: step: 1796/533, loss: 0.14246368408203125
2023-01-22 23:55:07.082812: step: 1800/533, loss: 0.2712755799293518
2023-01-22 23:55:08.262858: step: 1804/533, loss: 0.10894688963890076
2023-01-22 23:55:09.430032: step: 1808/533, loss: 0.8479633927345276
2023-01-22 23:55:10.595683: step: 1812/533, loss: 1.3127999305725098
2023-01-22 23:55:11.807484: step: 1816/533, loss: 0.17744627594947815
2023-01-22 23:55:12.978037: step: 1820/533, loss: 0.07554864883422852
2023-01-22 23:55:14.149224: step: 1824/533, loss: 0.34288546442985535
2023-01-22 23:55:15.339292: step: 1828/533, loss: 0.08664403110742569
2023-01-22 23:55:16.574245: step: 1832/533, loss: 0.13270169496536255
2023-01-22 23:55:17.726299: step: 1836/533, loss: 0.3446725010871887
2023-01-22 23:55:18.885703: step: 1840/533, loss: 1.8795182704925537
2023-01-22 23:55:20.082183: step: 1844/533, loss: 0.18244333565235138
2023-01-22 23:55:21.265994: step: 1848/533, loss: 0.10259667038917542
2023-01-22 23:55:22.466359: step: 1852/533, loss: 0.03538132086396217
2023-01-22 23:55:23.635895: step: 1856/533, loss: 0.45798835158348083
2023-01-22 23:55:24.834929: step: 1860/533, loss: 0.27287137508392334
2023-01-22 23:55:26.118850: step: 1864/533, loss: 0.3578135371208191
2023-01-22 23:55:27.289431: step: 1868/533, loss: 0.3007594347000122
2023-01-22 23:55:28.474892: step: 1872/533, loss: 1.4543057680130005
2023-01-22 23:55:29.676587: step: 1876/533, loss: 1.3446812629699707
2023-01-22 23:55:30.877164: step: 1880/533, loss: 0.25744399428367615
2023-01-22 23:55:32.062913: step: 1884/533, loss: 0.5162826776504517
2023-01-22 23:55:33.251835: step: 1888/533, loss: 0.42663878202438354
2023-01-22 23:55:34.432242: step: 1892/533, loss: 0.16847020387649536
2023-01-22 23:55:35.626383: step: 1896/533, loss: 0.6822004318237305
2023-01-22 23:55:36.755058: step: 1900/533, loss: 0.10992636531591415
2023-01-22 23:55:37.949130: step: 1904/533, loss: 0.14849665760993958
2023-01-22 23:55:39.104828: step: 1908/533, loss: 1.0728156566619873
2023-01-22 23:55:40.248029: step: 1912/533, loss: 0.14673951268196106
2023-01-22 23:55:41.446577: step: 1916/533, loss: 0.6810401082038879
2023-01-22 23:55:42.629013: step: 1920/533, loss: 0.07864876091480255
2023-01-22 23:55:43.800280: step: 1924/533, loss: 0.2458069920539856
2023-01-22 23:55:44.927841: step: 1928/533, loss: 0.1809266209602356
2023-01-22 23:55:46.151523: step: 1932/533, loss: 0.5229305028915405
2023-01-22 23:55:47.320474: step: 1936/533, loss: 0.21158117055892944
2023-01-22 23:55:48.464473: step: 1940/533, loss: 0.0708746463060379
2023-01-22 23:55:49.659436: step: 1944/533, loss: 0.3087455630302429
2023-01-22 23:55:50.825136: step: 1948/533, loss: 0.42598843574523926
2023-01-22 23:55:51.987696: step: 1952/533, loss: 0.907239556312561
2023-01-22 23:55:53.190344: step: 1956/533, loss: 0.10535035282373428
2023-01-22 23:55:54.332465: step: 1960/533, loss: 0.24729867279529572
2023-01-22 23:55:55.540935: step: 1964/533, loss: 0.9914241433143616
2023-01-22 23:55:56.724659: step: 1968/533, loss: 0.10492689907550812
2023-01-22 23:55:57.900884: step: 1972/533, loss: 0.8063637018203735
2023-01-22 23:55:59.095688: step: 1976/533, loss: 0.2916424870491028
2023-01-22 23:56:00.321046: step: 1980/533, loss: 0.237802654504776
2023-01-22 23:56:01.525889: step: 1984/533, loss: 0.08947930485010147
2023-01-22 23:56:02.733088: step: 1988/533, loss: 0.18570509552955627
2023-01-22 23:56:03.916234: step: 1992/533, loss: 0.5579148530960083
2023-01-22 23:56:05.059620: step: 1996/533, loss: 0.19813914597034454
2023-01-22 23:56:06.277513: step: 2000/533, loss: 1.77040696144104
2023-01-22 23:56:07.439612: step: 2004/533, loss: 0.2940627336502075
2023-01-22 23:56:08.673880: step: 2008/533, loss: 0.1400291472673416
2023-01-22 23:56:09.839567: step: 2012/533, loss: 0.2583116590976715
2023-01-22 23:56:10.978441: step: 2016/533, loss: 0.19395039975643158
2023-01-22 23:56:12.194395: step: 2020/533, loss: 1.147090196609497
2023-01-22 23:56:13.364991: step: 2024/533, loss: 0.7672001123428345
2023-01-22 23:56:14.539360: step: 2028/533, loss: 0.13498002290725708
2023-01-22 23:56:15.709419: step: 2032/533, loss: 0.22591599822044373
2023-01-22 23:56:16.920228: step: 2036/533, loss: 1.6391170024871826
2023-01-22 23:56:18.110548: step: 2040/533, loss: 0.1355711966753006
2023-01-22 23:56:19.302834: step: 2044/533, loss: 0.21271300315856934
2023-01-22 23:56:20.460215: step: 2048/533, loss: 0.11225919425487518
2023-01-22 23:56:21.627189: step: 2052/533, loss: 0.1445845067501068
2023-01-22 23:56:22.765773: step: 2056/533, loss: 0.3594485819339752
2023-01-22 23:56:23.943964: step: 2060/533, loss: 0.4189876616001129
2023-01-22 23:56:25.167479: step: 2064/533, loss: 0.13552206754684448
2023-01-22 23:56:26.306895: step: 2068/533, loss: 0.2117624282836914
2023-01-22 23:56:27.519118: step: 2072/533, loss: 0.6755533218383789
2023-01-22 23:56:28.680078: step: 2076/533, loss: 0.19395361840724945
2023-01-22 23:56:29.861169: step: 2080/533, loss: 0.7784324884414673
2023-01-22 23:56:31.068177: step: 2084/533, loss: 1.1049057245254517
2023-01-22 23:56:32.265146: step: 2088/533, loss: 0.09831076115369797
2023-01-22 23:56:33.424352: step: 2092/533, loss: 0.19836750626564026
2023-01-22 23:56:34.600112: step: 2096/533, loss: 0.18707247078418732
2023-01-22 23:56:35.813851: step: 2100/533, loss: 0.08321471512317657
2023-01-22 23:56:37.045252: step: 2104/533, loss: 0.358722448348999
2023-01-22 23:56:38.226799: step: 2108/533, loss: 0.911118745803833
2023-01-22 23:56:39.395048: step: 2112/533, loss: 0.7241929173469543
2023-01-22 23:56:40.563509: step: 2116/533, loss: 0.7691901326179504
2023-01-22 23:56:41.737490: step: 2120/533, loss: 0.2270602285861969
2023-01-22 23:56:42.910706: step: 2124/533, loss: 0.2018546164035797
2023-01-22 23:56:44.106201: step: 2128/533, loss: 0.8860490918159485
2023-01-22 23:56:45.305271: step: 2132/533, loss: 0.5212861895561218
==================================================
Loss: 0.626
--------------------
Dev: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.8, 'r': 0.31746031746031744, 'f1': 0.45454545454545453}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.45454545454545453, 'r': 0.2777777777777778, 'f1': 0.3448275862068966}, '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': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.8, 'r': 0.31746031746031744, 'f1': 0.45454545454545453}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.49306197964847365, 'r': 0.7097203728362184, 'f1': 0.5818777292576419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5165719696969697, 'r': 0.6975703324808185, 'f1': 0.5935799782372144}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:57:45.900431: step: 4/533, loss: 0.03451957553625107
2023-01-22 23:57:47.063485: step: 8/533, loss: 0.19599905610084534
2023-01-22 23:57:48.187747: step: 12/533, loss: 0.26731598377227783
2023-01-22 23:57:49.369292: step: 16/533, loss: 0.18239393830299377
2023-01-22 23:57:50.519459: step: 20/533, loss: 0.6576451659202576
2023-01-22 23:57:51.667011: step: 24/533, loss: 0.2004776895046234
2023-01-22 23:57:52.866147: step: 28/533, loss: 0.18090343475341797
2023-01-22 23:57:54.006376: step: 32/533, loss: 0.49251270294189453
2023-01-22 23:57:55.168156: step: 36/533, loss: 0.13193264603614807
2023-01-22 23:57:56.350950: step: 40/533, loss: 0.43752098083496094
2023-01-22 23:57:57.506845: step: 44/533, loss: 0.559822678565979
2023-01-22 23:57:58.670602: step: 48/533, loss: 0.15219825506210327
2023-01-22 23:57:59.846445: step: 52/533, loss: 0.9357835650444031
2023-01-22 23:58:01.025403: step: 56/533, loss: 0.6957262754440308
2023-01-22 23:58:02.209692: step: 60/533, loss: 6.301454067230225
2023-01-22 23:58:03.378470: step: 64/533, loss: 1.0453317165374756
2023-01-22 23:58:04.566242: step: 68/533, loss: 0.1851538121700287
2023-01-22 23:58:05.767585: step: 72/533, loss: 0.11183881759643555
2023-01-22 23:58:06.963242: step: 76/533, loss: 0.057894326746463776
2023-01-22 23:58:08.129223: step: 80/533, loss: 0.20177365839481354
2023-01-22 23:58:09.288455: step: 84/533, loss: 0.7120344638824463
2023-01-22 23:58:10.469006: step: 88/533, loss: 0.07235679775476456
2023-01-22 23:58:11.663939: step: 92/533, loss: 0.3799402415752411
2023-01-22 23:58:12.860680: step: 96/533, loss: 0.028688574209809303
2023-01-22 23:58:14.082889: step: 100/533, loss: 0.2685028910636902
2023-01-22 23:58:15.226023: step: 104/533, loss: 0.07654419541358948
2023-01-22 23:58:16.466931: step: 108/533, loss: 0.07747369259595871
2023-01-22 23:58:17.614259: step: 112/533, loss: 0.13297343254089355
2023-01-22 23:58:18.811900: step: 116/533, loss: 0.7147554755210876
2023-01-22 23:58:19.982928: step: 120/533, loss: 0.2567634582519531
2023-01-22 23:58:21.123024: step: 124/533, loss: 0.13873139023780823
2023-01-22 23:58:22.305366: step: 128/533, loss: 0.9747810363769531
2023-01-22 23:58:23.469261: step: 132/533, loss: 0.37831661105155945
2023-01-22 23:58:24.603359: step: 136/533, loss: 0.6275434494018555
2023-01-22 23:58:25.801120: step: 140/533, loss: 0.19439983367919922
2023-01-22 23:58:26.984517: step: 144/533, loss: 0.08895187824964523
2023-01-22 23:58:28.123796: step: 148/533, loss: 0.28726911544799805
2023-01-22 23:58:29.277256: step: 152/533, loss: 0.10586166381835938
2023-01-22 23:58:30.463343: step: 156/533, loss: 0.5252687335014343
2023-01-22 23:58:31.679291: step: 160/533, loss: 0.7363172769546509
2023-01-22 23:58:32.844021: step: 164/533, loss: 1.0096620321273804
2023-01-22 23:58:33.995989: step: 168/533, loss: 0.09869274497032166
2023-01-22 23:58:35.158943: step: 172/533, loss: 0.2539038360118866
2023-01-22 23:58:36.312556: step: 176/533, loss: 0.25012826919555664
2023-01-22 23:58:37.478021: step: 180/533, loss: 0.20629939436912537
2023-01-22 23:58:38.674372: step: 184/533, loss: 0.24908486008644104
2023-01-22 23:58:39.849477: step: 188/533, loss: 0.08796806633472443
2023-01-22 23:58:41.031063: step: 192/533, loss: 0.028368141502141953
2023-01-22 23:58:42.215312: step: 196/533, loss: 0.12687864899635315
2023-01-22 23:58:43.399255: step: 200/533, loss: 0.29567041993141174
2023-01-22 23:58:44.559305: step: 204/533, loss: 0.21308287978172302
2023-01-22 23:58:45.783120: step: 208/533, loss: 0.3525891900062561
2023-01-22 23:58:46.910361: step: 212/533, loss: 0.3552277684211731
2023-01-22 23:58:48.067315: step: 216/533, loss: 0.21406956017017365
2023-01-22 23:58:49.222177: step: 220/533, loss: 0.31315916776657104
2023-01-22 23:58:50.402811: step: 224/533, loss: 0.1957150250673294
2023-01-22 23:58:51.582927: step: 228/533, loss: 0.1896463930606842
2023-01-22 23:58:52.724413: step: 232/533, loss: 0.22514191269874573
2023-01-22 23:58:53.902986: step: 236/533, loss: 0.7129614949226379
2023-01-22 23:58:55.027765: step: 240/533, loss: 0.011224795132875443
2023-01-22 23:58:56.247281: step: 244/533, loss: 0.17230349779129028
2023-01-22 23:58:57.439585: step: 248/533, loss: 0.15486077964305878
2023-01-22 23:58:58.598675: step: 252/533, loss: 0.163020521402359
2023-01-22 23:58:59.796517: step: 256/533, loss: 0.11416491866111755
2023-01-22 23:59:00.979150: step: 260/533, loss: 0.21514463424682617
2023-01-22 23:59:02.200079: step: 264/533, loss: 0.6189179420471191
2023-01-22 23:59:03.363139: step: 268/533, loss: 0.0948396772146225
2023-01-22 23:59:04.533618: step: 272/533, loss: 0.49893808364868164
2023-01-22 23:59:05.674414: step: 276/533, loss: 0.34505051374435425
2023-01-22 23:59:06.839015: step: 280/533, loss: 1.1180148124694824
2023-01-22 23:59:08.014490: step: 284/533, loss: 0.526872456073761
2023-01-22 23:59:09.187463: step: 288/533, loss: 0.16351699829101562
2023-01-22 23:59:10.367399: step: 292/533, loss: 1.0271607637405396
2023-01-22 23:59:11.571782: step: 296/533, loss: 0.9073029160499573
2023-01-22 23:59:12.732906: step: 300/533, loss: 0.40234214067459106
2023-01-22 23:59:13.905864: step: 304/533, loss: 0.14024820923805237
2023-01-22 23:59:15.054869: step: 308/533, loss: 0.15397652983665466
2023-01-22 23:59:16.186985: step: 312/533, loss: 0.1487516462802887
2023-01-22 23:59:17.344188: step: 316/533, loss: 0.5063775777816772
2023-01-22 23:59:18.521241: step: 320/533, loss: 0.228526309132576
2023-01-22 23:59:19.804800: step: 324/533, loss: 0.9932713508605957
2023-01-22 23:59:21.021409: step: 328/533, loss: 0.29136142134666443
2023-01-22 23:59:22.204029: step: 332/533, loss: 0.46229496598243713
2023-01-22 23:59:23.374591: step: 336/533, loss: 0.14601492881774902
2023-01-22 23:59:24.544846: step: 340/533, loss: 0.0966564193367958
2023-01-22 23:59:25.741320: step: 344/533, loss: 0.31992846727371216
2023-01-22 23:59:26.916060: step: 348/533, loss: 0.09903021156787872
2023-01-22 23:59:28.089501: step: 352/533, loss: 0.047904398292303085
2023-01-22 23:59:29.232303: step: 356/533, loss: 0.0857873409986496
2023-01-22 23:59:30.381952: step: 360/533, loss: 0.7139033079147339
2023-01-22 23:59:31.583626: step: 364/533, loss: 0.1520092934370041
2023-01-22 23:59:32.755977: step: 368/533, loss: 1.0046950578689575
2023-01-22 23:59:33.893272: step: 372/533, loss: 0.11109619587659836
2023-01-22 23:59:35.055435: step: 376/533, loss: 0.7636460661888123
2023-01-22 23:59:36.244303: step: 380/533, loss: 0.22293290495872498
2023-01-22 23:59:37.478913: step: 384/533, loss: 0.3910292088985443
2023-01-22 23:59:38.677998: step: 388/533, loss: 0.8029780983924866
2023-01-22 23:59:39.864010: step: 392/533, loss: 0.08425979316234589
2023-01-22 23:59:41.033084: step: 396/533, loss: 0.4124286472797394
2023-01-22 23:59:42.202125: step: 400/533, loss: 0.807341992855072
2023-01-22 23:59:43.389762: step: 404/533, loss: 0.19572040438652039
2023-01-22 23:59:44.542286: step: 408/533, loss: 0.6098631024360657
2023-01-22 23:59:45.727894: step: 412/533, loss: 0.09129834175109863
2023-01-22 23:59:46.859787: step: 416/533, loss: 0.05229043960571289
2023-01-22 23:59:48.013816: step: 420/533, loss: 0.06809864193201065
2023-01-22 23:59:49.207954: step: 424/533, loss: 0.43989038467407227
2023-01-22 23:59:50.364077: step: 428/533, loss: 0.18254362046718597
2023-01-22 23:59:51.542806: step: 432/533, loss: 0.047667600214481354
2023-01-22 23:59:52.750257: step: 436/533, loss: 0.10156774520874023
2023-01-22 23:59:53.888273: step: 440/533, loss: 0.04419431835412979
2023-01-22 23:59:55.074384: step: 444/533, loss: 0.1719702184200287
2023-01-22 23:59:56.217894: step: 448/533, loss: 0.10167141258716583
2023-01-22 23:59:57.414687: step: 452/533, loss: 0.4255094528198242
2023-01-22 23:59:58.587819: step: 456/533, loss: 1.0728917121887207
2023-01-22 23:59:59.759611: step: 460/533, loss: 0.656667947769165
2023-01-23 00:00:00.915330: step: 464/533, loss: 0.31740856170654297
2023-01-23 00:00:02.084150: step: 468/533, loss: 0.8777336478233337
2023-01-23 00:00:03.289033: step: 472/533, loss: 0.21998901665210724
2023-01-23 00:00:04.470072: step: 476/533, loss: 0.21157197654247284
2023-01-23 00:00:05.666992: step: 480/533, loss: 0.08625831454992294
2023-01-23 00:00:06.814746: step: 484/533, loss: 0.05295391008257866
2023-01-23 00:00:07.970762: step: 488/533, loss: 1.3534992933273315
2023-01-23 00:00:09.080792: step: 492/533, loss: 0.05635356903076172
2023-01-23 00:00:10.224308: step: 496/533, loss: 0.1512811779975891
2023-01-23 00:00:11.402110: step: 500/533, loss: 1.4139525890350342
2023-01-23 00:00:12.567635: step: 504/533, loss: 0.48238927125930786
2023-01-23 00:00:13.718539: step: 508/533, loss: 1.2085622549057007
2023-01-23 00:00:14.876851: step: 512/533, loss: 0.85533607006073
2023-01-23 00:00:16.072050: step: 516/533, loss: 0.37146711349487305
2023-01-23 00:00:17.258655: step: 520/533, loss: 0.11755583435297012
2023-01-23 00:00:18.415980: step: 524/533, loss: 0.6158665418624878
2023-01-23 00:00:19.582263: step: 528/533, loss: 0.04983863979578018
2023-01-23 00:00:20.746747: step: 532/533, loss: 0.5918863415718079
2023-01-23 00:00:21.901059: step: 536/533, loss: 0.3632376492023468
2023-01-23 00:00:23.051784: step: 540/533, loss: 0.47278451919555664
2023-01-23 00:00:24.239383: step: 544/533, loss: 0.7704907655715942
2023-01-23 00:00:25.418810: step: 548/533, loss: 0.5547401309013367
2023-01-23 00:00:26.585511: step: 552/533, loss: 0.06354232132434845
2023-01-23 00:00:27.760813: step: 556/533, loss: 0.11705227196216583
2023-01-23 00:00:28.994618: step: 560/533, loss: 1.9675414562225342
2023-01-23 00:00:30.165421: step: 564/533, loss: 0.6091313362121582
2023-01-23 00:00:31.335796: step: 568/533, loss: 0.06256427615880966
2023-01-23 00:00:32.479512: step: 572/533, loss: 1.065568447113037
2023-01-23 00:00:33.682355: step: 576/533, loss: 6.238678455352783
2023-01-23 00:00:34.919700: step: 580/533, loss: 0.20755037665367126
2023-01-23 00:00:36.148787: step: 584/533, loss: 1.1084903478622437
2023-01-23 00:00:37.343537: step: 588/533, loss: 0.4266526401042938
2023-01-23 00:00:38.517902: step: 592/533, loss: 1.9573957920074463
2023-01-23 00:00:39.736989: step: 596/533, loss: 0.14478835463523865
2023-01-23 00:00:40.919476: step: 600/533, loss: 0.11911492794752121
2023-01-23 00:00:42.075468: step: 604/533, loss: 0.7593408823013306
2023-01-23 00:00:43.248886: step: 608/533, loss: 0.7655779123306274
2023-01-23 00:00:44.416599: step: 612/533, loss: 0.23260065913200378
2023-01-23 00:00:45.606032: step: 616/533, loss: 0.07270164787769318
2023-01-23 00:00:46.806926: step: 620/533, loss: 0.09500313550233841
2023-01-23 00:00:48.010129: step: 624/533, loss: 0.2175094187259674
2023-01-23 00:00:49.164940: step: 628/533, loss: 0.1838330626487732
2023-01-23 00:00:50.371135: step: 632/533, loss: 0.04129800945520401
2023-01-23 00:00:51.562799: step: 636/533, loss: 0.17840024828910828
2023-01-23 00:00:52.742110: step: 640/533, loss: 1.0283324718475342
2023-01-23 00:00:53.936398: step: 644/533, loss: 6.115992069244385
2023-01-23 00:00:55.091087: step: 648/533, loss: 0.22435492277145386
2023-01-23 00:00:56.273664: step: 652/533, loss: 0.13172969222068787
2023-01-23 00:00:57.422867: step: 656/533, loss: 0.2503325045108795
2023-01-23 00:00:58.587068: step: 660/533, loss: 0.24290724098682404
2023-01-23 00:00:59.745108: step: 664/533, loss: 0.047755979001522064
2023-01-23 00:01:00.987703: step: 668/533, loss: 0.6896345615386963
2023-01-23 00:01:02.204468: step: 672/533, loss: 0.17214851081371307
2023-01-23 00:01:03.358536: step: 676/533, loss: 0.16003593802452087
2023-01-23 00:01:04.563617: step: 680/533, loss: 0.45051613450050354
2023-01-23 00:01:05.727206: step: 684/533, loss: 0.41030359268188477
2023-01-23 00:01:06.886246: step: 688/533, loss: 0.23761333525180817
2023-01-23 00:01:08.043652: step: 692/533, loss: 0.3367490768432617
2023-01-23 00:01:09.193377: step: 696/533, loss: 0.8366636633872986
2023-01-23 00:01:10.377974: step: 700/533, loss: 0.21287240087985992
2023-01-23 00:01:11.576636: step: 704/533, loss: 0.10609011352062225
2023-01-23 00:01:12.744939: step: 708/533, loss: 0.325504869222641
2023-01-23 00:01:13.915398: step: 712/533, loss: 5.976997375488281
2023-01-23 00:01:15.076618: step: 716/533, loss: 0.07249946892261505
2023-01-23 00:01:16.242215: step: 720/533, loss: 0.5006676316261292
2023-01-23 00:01:17.409629: step: 724/533, loss: 0.09480872750282288
2023-01-23 00:01:18.579791: step: 728/533, loss: 0.08126058429479599
2023-01-23 00:01:19.763346: step: 732/533, loss: 0.18725129961967468
2023-01-23 00:01:20.912376: step: 736/533, loss: 0.6739752292633057
2023-01-23 00:01:22.146359: step: 740/533, loss: 0.10861635208129883
2023-01-23 00:01:23.281952: step: 744/533, loss: 0.4173053503036499
2023-01-23 00:01:24.465971: step: 748/533, loss: 0.5523170232772827
2023-01-23 00:01:25.626258: step: 752/533, loss: 0.1912127584218979
2023-01-23 00:01:26.820927: step: 756/533, loss: 0.1156759262084961
2023-01-23 00:01:28.012423: step: 760/533, loss: 0.06699047237634659
2023-01-23 00:01:29.177996: step: 764/533, loss: 0.08671140670776367
2023-01-23 00:01:30.319992: step: 768/533, loss: 0.13751859962940216
2023-01-23 00:01:31.489916: step: 772/533, loss: 0.514961838722229
2023-01-23 00:01:32.688195: step: 776/533, loss: 0.39676913619041443
2023-01-23 00:01:33.827114: step: 780/533, loss: 0.576019823551178
2023-01-23 00:01:34.970395: step: 784/533, loss: 0.09464402496814728
2023-01-23 00:01:36.109887: step: 788/533, loss: 0.3749733865261078
2023-01-23 00:01:37.271791: step: 792/533, loss: 0.07085695117712021
2023-01-23 00:01:38.502579: step: 796/533, loss: 0.08774380385875702
2023-01-23 00:01:39.705407: step: 800/533, loss: 0.11243218928575516
2023-01-23 00:01:40.877704: step: 804/533, loss: 0.13983449339866638
2023-01-23 00:01:42.081332: step: 808/533, loss: 0.12128515541553497
2023-01-23 00:01:43.235258: step: 812/533, loss: 0.0763828307390213
2023-01-23 00:01:44.421733: step: 816/533, loss: 0.18989324569702148
2023-01-23 00:01:45.555985: step: 820/533, loss: 0.4272615313529968
2023-01-23 00:01:46.745834: step: 824/533, loss: 1.0054242610931396
2023-01-23 00:01:47.943512: step: 828/533, loss: 0.42077115178108215
2023-01-23 00:01:49.132949: step: 832/533, loss: 0.7691338062286377
2023-01-23 00:01:50.321363: step: 836/533, loss: 0.33931148052215576
2023-01-23 00:01:51.493754: step: 840/533, loss: 0.7439698576927185
2023-01-23 00:01:52.693477: step: 844/533, loss: 0.8667982816696167
2023-01-23 00:01:53.875745: step: 848/533, loss: 0.21416302025318146
2023-01-23 00:01:55.031922: step: 852/533, loss: 0.4676376283168793
2023-01-23 00:01:56.223626: step: 856/533, loss: 0.13931503891944885
2023-01-23 00:01:57.401548: step: 860/533, loss: 0.1378774642944336
2023-01-23 00:01:58.558046: step: 864/533, loss: 0.14342756569385529
2023-01-23 00:01:59.700421: step: 868/533, loss: 0.14753732085227966
2023-01-23 00:02:00.867239: step: 872/533, loss: 0.07717466354370117
2023-01-23 00:02:02.044628: step: 876/533, loss: 0.5566136837005615
2023-01-23 00:02:03.222557: step: 880/533, loss: 0.09720521420240402
2023-01-23 00:02:04.412868: step: 884/533, loss: 0.6886968612670898
2023-01-23 00:02:05.603414: step: 888/533, loss: 6.780792236328125
2023-01-23 00:02:06.783740: step: 892/533, loss: 0.8442405462265015
2023-01-23 00:02:07.979751: step: 896/533, loss: 0.15167587995529175
2023-01-23 00:02:09.145887: step: 900/533, loss: 0.27124518156051636
2023-01-23 00:02:10.292460: step: 904/533, loss: 0.1327369660139084
2023-01-23 00:02:11.429135: step: 908/533, loss: 0.13409757614135742
2023-01-23 00:02:12.618216: step: 912/533, loss: 0.21246260404586792
2023-01-23 00:02:13.835984: step: 916/533, loss: 0.13756155967712402
2023-01-23 00:02:15.001681: step: 920/533, loss: 0.12368479371070862
2023-01-23 00:02:16.187597: step: 924/533, loss: 0.21089425683021545
2023-01-23 00:02:17.379769: step: 928/533, loss: 0.178009033203125
2023-01-23 00:02:18.547478: step: 932/533, loss: 0.18765611946582794
2023-01-23 00:02:19.723241: step: 936/533, loss: 0.7292583584785461
2023-01-23 00:02:20.885824: step: 940/533, loss: 0.41813531517982483
2023-01-23 00:02:22.049536: step: 944/533, loss: 0.4608857035636902
2023-01-23 00:02:23.245382: step: 948/533, loss: 0.07561693340539932
2023-01-23 00:02:24.410018: step: 952/533, loss: 0.19039887189865112
2023-01-23 00:02:25.575116: step: 956/533, loss: 0.34387293457984924
2023-01-23 00:02:26.759685: step: 960/533, loss: 0.26746273040771484
2023-01-23 00:02:27.928754: step: 964/533, loss: 0.7302387952804565
2023-01-23 00:02:29.095024: step: 968/533, loss: 1.9227488040924072
2023-01-23 00:02:30.246167: step: 972/533, loss: 0.5365772247314453
2023-01-23 00:02:31.503289: step: 976/533, loss: 0.439666748046875
2023-01-23 00:02:32.683745: step: 980/533, loss: 0.11347942054271698
2023-01-23 00:02:33.870987: step: 984/533, loss: 0.14102010428905487
2023-01-23 00:02:35.029886: step: 988/533, loss: 0.10964584350585938
2023-01-23 00:02:36.240918: step: 992/533, loss: 0.2236180305480957
2023-01-23 00:02:37.399130: step: 996/533, loss: 0.7999707460403442
2023-01-23 00:02:38.592146: step: 1000/533, loss: 0.06100459024310112
2023-01-23 00:02:39.753940: step: 1004/533, loss: 0.06685248017311096
2023-01-23 00:02:40.954000: step: 1008/533, loss: 0.06022777408361435
2023-01-23 00:02:42.130935: step: 1012/533, loss: 0.16972537338733673
2023-01-23 00:02:43.339145: step: 1016/533, loss: 0.30189791321754456
2023-01-23 00:02:44.533338: step: 1020/533, loss: 0.5730999708175659
2023-01-23 00:02:45.682389: step: 1024/533, loss: 0.6522205471992493
2023-01-23 00:02:46.833179: step: 1028/533, loss: 0.3931344151496887
2023-01-23 00:02:48.010240: step: 1032/533, loss: 0.5140711069107056
2023-01-23 00:02:49.181955: step: 1036/533, loss: 0.22558140754699707
2023-01-23 00:02:50.373948: step: 1040/533, loss: 0.1763581931591034
2023-01-23 00:02:51.579937: step: 1044/533, loss: 1.507238507270813
2023-01-23 00:02:52.688165: step: 1048/533, loss: 0.1031225174665451
2023-01-23 00:02:53.840767: step: 1052/533, loss: 0.19427213072776794
2023-01-23 00:02:55.019932: step: 1056/533, loss: 0.26278573274612427
2023-01-23 00:02:56.216688: step: 1060/533, loss: 0.24707774817943573
2023-01-23 00:02:57.402222: step: 1064/533, loss: 0.3065307140350342
2023-01-23 00:02:58.629122: step: 1068/533, loss: 0.5000457763671875
2023-01-23 00:02:59.780548: step: 1072/533, loss: 1.0486862659454346
2023-01-23 00:03:00.958694: step: 1076/533, loss: 0.683367133140564
2023-01-23 00:03:02.126188: step: 1080/533, loss: 0.1699684113264084
2023-01-23 00:03:03.299846: step: 1084/533, loss: 0.21722298860549927
2023-01-23 00:03:04.484808: step: 1088/533, loss: 0.13793249428272247
2023-01-23 00:03:05.669305: step: 1092/533, loss: 1.2792967557907104
2023-01-23 00:03:06.817352: step: 1096/533, loss: 0.27423784136772156
2023-01-23 00:03:08.013431: step: 1100/533, loss: 0.15517958998680115
2023-01-23 00:03:09.230331: step: 1104/533, loss: 0.9255038499832153
2023-01-23 00:03:10.383885: step: 1108/533, loss: 0.264323353767395
2023-01-23 00:03:11.529944: step: 1112/533, loss: 0.7559067010879517
2023-01-23 00:03:12.775802: step: 1116/533, loss: 1.1000087261199951
2023-01-23 00:03:13.948370: step: 1120/533, loss: 0.22105997800827026
2023-01-23 00:03:15.118039: step: 1124/533, loss: 0.8161914348602295
2023-01-23 00:03:16.287803: step: 1128/533, loss: 0.6911132335662842
2023-01-23 00:03:17.469684: step: 1132/533, loss: 0.6746658682823181
2023-01-23 00:03:18.634369: step: 1136/533, loss: 0.2609933614730835
2023-01-23 00:03:19.806959: step: 1140/533, loss: 0.35272732377052307
2023-01-23 00:03:20.996146: step: 1144/533, loss: 0.2991991937160492
2023-01-23 00:03:22.182760: step: 1148/533, loss: 0.19277286529541016
2023-01-23 00:03:23.380120: step: 1152/533, loss: 0.8033561706542969
2023-01-23 00:03:24.536391: step: 1156/533, loss: 0.051830388605594635
2023-01-23 00:03:25.763968: step: 1160/533, loss: 6.071428298950195
2023-01-23 00:03:26.976216: step: 1164/533, loss: 0.4722738265991211
2023-01-23 00:03:28.151877: step: 1168/533, loss: 0.20875605940818787
2023-01-23 00:03:29.323736: step: 1172/533, loss: 0.2725340723991394
2023-01-23 00:03:30.514256: step: 1176/533, loss: 0.7279965877532959
2023-01-23 00:03:31.665439: step: 1180/533, loss: 0.6772966384887695
2023-01-23 00:03:32.805923: step: 1184/533, loss: 0.15030308067798615
2023-01-23 00:03:33.957483: step: 1188/533, loss: 0.09388285130262375
2023-01-23 00:03:35.161341: step: 1192/533, loss: 0.29090338945388794
2023-01-23 00:03:36.320409: step: 1196/533, loss: 0.14142310619354248
2023-01-23 00:03:37.529598: step: 1200/533, loss: 0.17211371660232544
2023-01-23 00:03:38.694154: step: 1204/533, loss: 0.1851998269557953
2023-01-23 00:03:39.821140: step: 1208/533, loss: 0.4577353596687317
2023-01-23 00:03:40.976182: step: 1212/533, loss: 1.147730827331543
2023-01-23 00:03:42.168605: step: 1216/533, loss: 6.743643283843994
2023-01-23 00:03:43.344746: step: 1220/533, loss: 0.1123572364449501
2023-01-23 00:03:44.498832: step: 1224/533, loss: 0.13448172807693481
2023-01-23 00:03:45.672805: step: 1228/533, loss: 0.8281000256538391
2023-01-23 00:03:46.823586: step: 1232/533, loss: 0.26371994614601135
2023-01-23 00:03:47.970393: step: 1236/533, loss: 0.5202805399894714
2023-01-23 00:03:49.127109: step: 1240/533, loss: 0.10507631301879883
2023-01-23 00:03:50.348574: step: 1244/533, loss: 0.7237327694892883
2023-01-23 00:03:51.517001: step: 1248/533, loss: 0.11498404294252396
2023-01-23 00:03:52.674459: step: 1252/533, loss: 0.05696067959070206
2023-01-23 00:03:53.849042: step: 1256/533, loss: 0.10937843471765518
2023-01-23 00:03:55.009629: step: 1260/533, loss: 0.11326217651367188
2023-01-23 00:03:56.181140: step: 1264/533, loss: 0.09295278042554855
2023-01-23 00:03:57.391649: step: 1268/533, loss: 0.3635866641998291
2023-01-23 00:03:58.546577: step: 1272/533, loss: 0.15917611122131348
2023-01-23 00:03:59.741045: step: 1276/533, loss: 0.8526588678359985
2023-01-23 00:04:00.925556: step: 1280/533, loss: 0.13858576118946075
2023-01-23 00:04:02.090370: step: 1284/533, loss: 0.0664517879486084
2023-01-23 00:04:03.266704: step: 1288/533, loss: 0.8690705299377441
2023-01-23 00:04:04.423392: step: 1292/533, loss: 0.7336040735244751
2023-01-23 00:04:05.614911: step: 1296/533, loss: 0.26735228300094604
2023-01-23 00:04:06.766942: step: 1300/533, loss: 0.12874527275562286
2023-01-23 00:04:07.942133: step: 1304/533, loss: 0.8387083411216736
2023-01-23 00:04:09.129493: step: 1308/533, loss: 0.29012781381607056
2023-01-23 00:04:10.292775: step: 1312/533, loss: 0.29116612672805786
2023-01-23 00:04:11.440414: step: 1316/533, loss: 0.06747221946716309
2023-01-23 00:04:12.610081: step: 1320/533, loss: 0.14437732100486755
2023-01-23 00:04:13.779778: step: 1324/533, loss: 0.950222373008728
2023-01-23 00:04:14.921673: step: 1328/533, loss: 1.8799209594726562
2023-01-23 00:04:16.121333: step: 1332/533, loss: 0.10964985191822052
2023-01-23 00:04:17.290816: step: 1336/533, loss: 0.11989335715770721
2023-01-23 00:04:18.433027: step: 1340/533, loss: 0.14323726296424866
2023-01-23 00:04:19.653219: step: 1344/533, loss: 0.21820011734962463
2023-01-23 00:04:20.852891: step: 1348/533, loss: 0.9188598394393921
2023-01-23 00:04:22.052873: step: 1352/533, loss: 0.06784620881080627
2023-01-23 00:04:23.235939: step: 1356/533, loss: 0.07366757094860077
2023-01-23 00:04:24.429507: step: 1360/533, loss: 1.4543697834014893
2023-01-23 00:04:25.609816: step: 1364/533, loss: 0.2703947424888611
2023-01-23 00:04:26.784727: step: 1368/533, loss: 0.2699599266052246
2023-01-23 00:04:27.995456: step: 1372/533, loss: 0.06850510090589523
2023-01-23 00:04:29.168172: step: 1376/533, loss: 0.4204274117946625
2023-01-23 00:04:30.297579: step: 1380/533, loss: 0.1322219967842102
2023-01-23 00:04:31.501628: step: 1384/533, loss: 0.1301138997077942
2023-01-23 00:04:32.693060: step: 1388/533, loss: 0.1648695021867752
2023-01-23 00:04:33.868797: step: 1392/533, loss: 0.3226913511753082
2023-01-23 00:04:35.033630: step: 1396/533, loss: 0.027720261365175247
2023-01-23 00:04:36.208811: step: 1400/533, loss: 0.1715250462293625
2023-01-23 00:04:37.353009: step: 1404/533, loss: 0.545713484287262
2023-01-23 00:04:38.502891: step: 1408/533, loss: 0.09135523438453674
2023-01-23 00:04:39.686864: step: 1412/533, loss: 0.1428672969341278
2023-01-23 00:04:40.897312: step: 1416/533, loss: 0.04816432297229767
2023-01-23 00:04:42.071306: step: 1420/533, loss: 0.04769277945160866
2023-01-23 00:04:43.215907: step: 1424/533, loss: 0.6040971875190735
2023-01-23 00:04:44.390599: step: 1428/533, loss: 1.1631361246109009
2023-01-23 00:04:45.588557: step: 1432/533, loss: 0.6827511787414551
2023-01-23 00:04:46.750160: step: 1436/533, loss: 0.3993563652038574
2023-01-23 00:04:47.912205: step: 1440/533, loss: 0.8167518377304077
2023-01-23 00:04:49.085446: step: 1444/533, loss: 0.823337733745575
2023-01-23 00:04:50.305629: step: 1448/533, loss: 0.17267131805419922
2023-01-23 00:04:51.463790: step: 1452/533, loss: 0.060135677456855774
2023-01-23 00:04:52.594410: step: 1456/533, loss: 1.0252174139022827
2023-01-23 00:04:53.779194: step: 1460/533, loss: 0.34034109115600586
2023-01-23 00:04:54.996915: step: 1464/533, loss: 0.6563622355461121
2023-01-23 00:04:56.182445: step: 1468/533, loss: 0.32413730025291443
2023-01-23 00:04:57.372149: step: 1472/533, loss: 0.036279771476984024
2023-01-23 00:04:58.536929: step: 1476/533, loss: 0.09050703048706055
2023-01-23 00:04:59.730754: step: 1480/533, loss: 0.8064340949058533
2023-01-23 00:05:00.897392: step: 1484/533, loss: 0.7008271217346191
2023-01-23 00:05:02.078224: step: 1488/533, loss: 0.3770490884780884
2023-01-23 00:05:03.256053: step: 1492/533, loss: 0.19439055025577545
2023-01-23 00:05:04.464809: step: 1496/533, loss: 0.5236929655075073
2023-01-23 00:05:05.636180: step: 1500/533, loss: 1.528775691986084
2023-01-23 00:05:06.845360: step: 1504/533, loss: 0.1137852668762207
2023-01-23 00:05:08.061775: step: 1508/533, loss: 0.43502336740493774
2023-01-23 00:05:09.232069: step: 1512/533, loss: 0.038903046399354935
2023-01-23 00:05:10.431332: step: 1516/533, loss: 0.3854188024997711
2023-01-23 00:05:11.648615: step: 1520/533, loss: 0.251146137714386
2023-01-23 00:05:12.829181: step: 1524/533, loss: 0.12915687263011932
2023-01-23 00:05:13.966444: step: 1528/533, loss: 0.673798143863678
2023-01-23 00:05:15.142224: step: 1532/533, loss: 0.12621363997459412
2023-01-23 00:05:16.319180: step: 1536/533, loss: 0.6278102993965149
2023-01-23 00:05:17.530140: step: 1540/533, loss: 0.06361560523509979
2023-01-23 00:05:18.699093: step: 1544/533, loss: 0.13660703599452972
2023-01-23 00:05:19.908747: step: 1548/533, loss: 0.15256424248218536
2023-01-23 00:05:21.116346: step: 1552/533, loss: 0.18162879347801208
2023-01-23 00:05:22.311471: step: 1556/533, loss: 0.3840428292751312
2023-01-23 00:05:23.482037: step: 1560/533, loss: 0.8691293001174927
2023-01-23 00:05:24.689455: step: 1564/533, loss: 0.0928887352347374
2023-01-23 00:05:25.845804: step: 1568/533, loss: 0.09873300045728683
2023-01-23 00:05:27.008356: step: 1572/533, loss: 0.3925350308418274
2023-01-23 00:05:28.154655: step: 1576/533, loss: 0.0813567191362381
2023-01-23 00:05:29.309837: step: 1580/533, loss: 0.1296248435974121
2023-01-23 00:05:30.474389: step: 1584/533, loss: 0.4144035577774048
2023-01-23 00:05:31.657073: step: 1588/533, loss: 0.7897875905036926
2023-01-23 00:05:32.845595: step: 1592/533, loss: 0.21992692351341248
2023-01-23 00:05:34.020506: step: 1596/533, loss: 0.17542344331741333
2023-01-23 00:05:35.161406: step: 1600/533, loss: 0.21425633132457733
2023-01-23 00:05:36.329785: step: 1604/533, loss: 0.22274942696094513
2023-01-23 00:05:37.520602: step: 1608/533, loss: 0.6761957406997681
2023-01-23 00:05:38.706199: step: 1612/533, loss: 0.26131343841552734
2023-01-23 00:05:39.830044: step: 1616/533, loss: 0.45399951934814453
2023-01-23 00:05:41.040041: step: 1620/533, loss: 0.7500147819519043
2023-01-23 00:05:42.234925: step: 1624/533, loss: 1.0922762155532837
2023-01-23 00:05:43.388250: step: 1628/533, loss: 0.7369341254234314
2023-01-23 00:05:44.558716: step: 1632/533, loss: 0.4089612066745758
2023-01-23 00:05:45.746275: step: 1636/533, loss: 0.897318959236145
2023-01-23 00:05:46.906039: step: 1640/533, loss: 0.6893734931945801
2023-01-23 00:05:48.118830: step: 1644/533, loss: 0.1404230147600174
2023-01-23 00:05:49.377502: step: 1648/533, loss: 0.21221551299095154
2023-01-23 00:05:50.550945: step: 1652/533, loss: 0.8159072995185852
2023-01-23 00:05:51.730826: step: 1656/533, loss: 0.19141311943531036
2023-01-23 00:05:52.915051: step: 1660/533, loss: 0.08337202668190002
2023-01-23 00:05:54.067502: step: 1664/533, loss: 1.0861512422561646
2023-01-23 00:05:55.216381: step: 1668/533, loss: 1.4600284099578857
2023-01-23 00:05:56.369134: step: 1672/533, loss: 0.06867833435535431
2023-01-23 00:05:57.531750: step: 1676/533, loss: 0.09389019012451172
2023-01-23 00:05:58.702570: step: 1680/533, loss: 0.03448162227869034
2023-01-23 00:05:59.915116: step: 1684/533, loss: 0.3975580632686615
2023-01-23 00:06:01.099363: step: 1688/533, loss: 0.16914740204811096
2023-01-23 00:06:02.317798: step: 1692/533, loss: 0.20642197132110596
2023-01-23 00:06:03.487905: step: 1696/533, loss: 0.11696415394544601
2023-01-23 00:06:04.667293: step: 1700/533, loss: 0.12218408286571503
2023-01-23 00:06:05.835932: step: 1704/533, loss: 0.05383472889661789
2023-01-23 00:06:06.981703: step: 1708/533, loss: 0.12333174049854279
2023-01-23 00:06:08.158322: step: 1712/533, loss: 0.9496538639068604
2023-01-23 00:06:09.301592: step: 1716/533, loss: 0.4803905189037323
2023-01-23 00:06:10.464135: step: 1720/533, loss: 0.22776460647583008
2023-01-23 00:06:11.650613: step: 1724/533, loss: 0.26100996136665344
2023-01-23 00:06:12.872963: step: 1728/533, loss: 0.7702292799949646
2023-01-23 00:06:14.046379: step: 1732/533, loss: 0.867817759513855
2023-01-23 00:06:15.233052: step: 1736/533, loss: 0.3525756895542145
2023-01-23 00:06:16.420076: step: 1740/533, loss: 0.2566913664340973
2023-01-23 00:06:17.595478: step: 1744/533, loss: 0.6176469922065735
2023-01-23 00:06:18.796375: step: 1748/533, loss: 0.14198055863380432
2023-01-23 00:06:20.013048: step: 1752/533, loss: 0.13684920966625214
2023-01-23 00:06:21.224826: step: 1756/533, loss: 0.28108978271484375
2023-01-23 00:06:22.427099: step: 1760/533, loss: 0.18111354112625122
2023-01-23 00:06:23.616259: step: 1764/533, loss: 0.4277893006801605
2023-01-23 00:06:24.789409: step: 1768/533, loss: 0.10900545865297318
2023-01-23 00:06:25.968550: step: 1772/533, loss: 0.11225280910730362
2023-01-23 00:06:27.151486: step: 1776/533, loss: 0.1711202710866928
2023-01-23 00:06:28.316058: step: 1780/533, loss: 0.09322099387645721
2023-01-23 00:06:29.472607: step: 1784/533, loss: 0.16490697860717773
2023-01-23 00:06:30.683481: step: 1788/533, loss: 0.5194489359855652
2023-01-23 00:06:31.840200: step: 1792/533, loss: 0.1701022982597351
2023-01-23 00:06:33.039735: step: 1796/533, loss: 0.3623226284980774
2023-01-23 00:06:34.199259: step: 1800/533, loss: 0.8791519403457642
2023-01-23 00:06:35.370590: step: 1804/533, loss: 1.0270390510559082
2023-01-23 00:06:36.552497: step: 1808/533, loss: 0.02732677385210991
2023-01-23 00:06:37.714765: step: 1812/533, loss: 0.24584579467773438
2023-01-23 00:06:38.853886: step: 1816/533, loss: 0.7096970677375793
2023-01-23 00:06:40.027750: step: 1820/533, loss: 0.12158603966236115
2023-01-23 00:06:41.210752: step: 1824/533, loss: 0.23516026139259338
2023-01-23 00:06:42.411506: step: 1828/533, loss: 0.14820708334445953
2023-01-23 00:06:43.555280: step: 1832/533, loss: 0.3918459415435791
2023-01-23 00:06:44.743011: step: 1836/533, loss: 0.13952083885669708
2023-01-23 00:06:45.902888: step: 1840/533, loss: 0.13386079668998718
2023-01-23 00:06:47.090229: step: 1844/533, loss: 0.1306193321943283
2023-01-23 00:06:48.288616: step: 1848/533, loss: 0.14490899443626404
2023-01-23 00:06:49.512307: step: 1852/533, loss: 0.1578243225812912
2023-01-23 00:06:50.707700: step: 1856/533, loss: 0.5925222635269165
2023-01-23 00:06:51.901025: step: 1860/533, loss: 0.44138574600219727
2023-01-23 00:06:53.075549: step: 1864/533, loss: 0.12281332910060883
2023-01-23 00:06:54.275781: step: 1868/533, loss: 0.4627809524536133
2023-01-23 00:06:55.435212: step: 1872/533, loss: 1.246553659439087
2023-01-23 00:06:56.625048: step: 1876/533, loss: 0.1605004519224167
2023-01-23 00:06:57.827781: step: 1880/533, loss: 0.28873175382614136
2023-01-23 00:06:58.994907: step: 1884/533, loss: 0.15015211701393127
2023-01-23 00:07:00.170709: step: 1888/533, loss: 0.15393801033496857
2023-01-23 00:07:01.380041: step: 1892/533, loss: 1.2088112831115723
2023-01-23 00:07:02.554959: step: 1896/533, loss: 0.06461191177368164
2023-01-23 00:07:03.680184: step: 1900/533, loss: 0.6443314552307129
2023-01-23 00:07:04.868895: step: 1904/533, loss: 0.19854307174682617
2023-01-23 00:07:06.038682: step: 1908/533, loss: 0.09643955528736115
2023-01-23 00:07:07.255736: step: 1912/533, loss: 1.6777030229568481
2023-01-23 00:07:08.458824: step: 1916/533, loss: 0.0324217826128006
2023-01-23 00:07:09.634330: step: 1920/533, loss: 0.05962047725915909
2023-01-23 00:07:10.858529: step: 1924/533, loss: 0.36219388246536255
2023-01-23 00:07:12.063183: step: 1928/533, loss: 0.23248833417892456
2023-01-23 00:07:13.256824: step: 1932/533, loss: 0.24731898307800293
2023-01-23 00:07:14.563034: step: 1936/533, loss: 1.1649845838546753
2023-01-23 00:07:15.732350: step: 1940/533, loss: 0.14077988266944885
2023-01-23 00:07:16.892797: step: 1944/533, loss: 0.8158080577850342
2023-01-23 00:07:18.048698: step: 1948/533, loss: 0.12570805847644806
2023-01-23 00:07:19.263068: step: 1952/533, loss: 0.2574155926704407
2023-01-23 00:07:20.407484: step: 1956/533, loss: 0.09502439200878143
2023-01-23 00:07:21.560320: step: 1960/533, loss: 0.726071834564209
2023-01-23 00:07:22.701522: step: 1964/533, loss: 0.7745004296302795
2023-01-23 00:07:23.845252: step: 1968/533, loss: 0.4669771194458008
2023-01-23 00:07:25.031080: step: 1972/533, loss: 0.4462575912475586
2023-01-23 00:07:26.149381: step: 1976/533, loss: 0.08509598672389984
2023-01-23 00:07:27.366919: step: 1980/533, loss: 0.5676898956298828
2023-01-23 00:07:28.576131: step: 1984/533, loss: 0.4625686705112457
2023-01-23 00:07:29.780763: step: 1988/533, loss: 7.225518703460693
2023-01-23 00:07:30.945865: step: 1992/533, loss: 0.11657486110925674
2023-01-23 00:07:32.122082: step: 1996/533, loss: 0.18175660073757172
2023-01-23 00:07:33.279139: step: 2000/533, loss: 1.0071289539337158
2023-01-23 00:07:34.418587: step: 2004/533, loss: 0.24380053579807281
2023-01-23 00:07:35.612359: step: 2008/533, loss: 0.23419040441513062
2023-01-23 00:07:36.760064: step: 2012/533, loss: 0.3166806697845459
2023-01-23 00:07:37.944024: step: 2016/533, loss: 0.20011290907859802
2023-01-23 00:07:39.123978: step: 2020/533, loss: 0.2254011034965515
2023-01-23 00:07:40.306457: step: 2024/533, loss: 0.21801738440990448
2023-01-23 00:07:41.461619: step: 2028/533, loss: 0.40872716903686523
2023-01-23 00:07:42.656471: step: 2032/533, loss: 0.507516086101532
2023-01-23 00:07:43.873198: step: 2036/533, loss: 0.07941646873950958
2023-01-23 00:07:45.064594: step: 2040/533, loss: 0.11726884543895721
2023-01-23 00:07:46.260190: step: 2044/533, loss: 0.3451942503452301
2023-01-23 00:07:47.482812: step: 2048/533, loss: 0.3090072572231293
2023-01-23 00:07:48.645371: step: 2052/533, loss: 0.10676155239343643
2023-01-23 00:07:49.840068: step: 2056/533, loss: 0.02714524418115616
2023-01-23 00:07:50.991578: step: 2060/533, loss: 0.20507307350635529
2023-01-23 00:07:52.169112: step: 2064/533, loss: 0.08268632739782333
2023-01-23 00:07:53.340672: step: 2068/533, loss: 0.10210895538330078
2023-01-23 00:07:54.548927: step: 2072/533, loss: 0.14143720269203186
2023-01-23 00:07:55.781187: step: 2076/533, loss: 0.05337691307067871
2023-01-23 00:07:56.951173: step: 2080/533, loss: 0.35757824778556824
2023-01-23 00:07:58.112000: step: 2084/533, loss: 7.25294303894043
2023-01-23 00:07:59.341054: step: 2088/533, loss: 1.0735610723495483
2023-01-23 00:08:00.525947: step: 2092/533, loss: 0.27614539861679077
2023-01-23 00:08:01.746289: step: 2096/533, loss: 1.4364241361618042
2023-01-23 00:08:02.894370: step: 2100/533, loss: 0.09752216935157776
2023-01-23 00:08:04.177365: step: 2104/533, loss: 0.2030380219221115
2023-01-23 00:08:05.382052: step: 2108/533, loss: 0.40994346141815186
2023-01-23 00:08:06.554332: step: 2112/533, loss: 0.07958989590406418
2023-01-23 00:08:07.708625: step: 2116/533, loss: 0.07022424042224884
2023-01-23 00:08:08.862886: step: 2120/533, loss: 0.20016518235206604
2023-01-23 00:08:10.020649: step: 2124/533, loss: 0.10159797966480255
2023-01-23 00:08:11.222784: step: 2128/533, loss: 0.20515227317810059
2023-01-23 00:08:12.383818: step: 2132/533, loss: 0.0617949478328228
==================================================
Loss: 0.478
--------------------
Dev: {'event': {'p': 0.6363636363636364, 'r': 0.7456724367509987, 'f1': 0.6866952789699571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.6506849315068494, 'r': 0.7289002557544757, 'f1': 0.6875753920386006}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5394736842105263, 'r': 0.7592592592592593, 'f1': 0.6307692307692309}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6086956521739131, 'r': 0.4444444444444444, 'f1': 0.5137614678899082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.45714285714285713, 'r': 0.4444444444444444, 'f1': 0.4507042253521127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6363636363636364, 'r': 0.7456724367509987, 'f1': 0.6866952789699571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.6506849315068494, 'r': 0.7289002557544757, 'f1': 0.6875753920386006}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6086956521739131, 'r': 0.4444444444444444, 'f1': 0.5137614678899082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6363636363636364, 'r': 0.7456724367509987, 'f1': 0.6866952789699571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6506849315068494, 'r': 0.7289002557544757, 'f1': 0.6875753920386006}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.45714285714285713, 'r': 0.4444444444444444, 'f1': 0.4507042253521127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:09:10.746015: step: 4/533, loss: 0.16080769896507263
2023-01-23 00:09:11.935389: step: 8/533, loss: 0.2467871606349945
2023-01-23 00:09:13.101762: step: 12/533, loss: 0.12963686883449554
2023-01-23 00:09:14.264126: step: 16/533, loss: 0.06429843604564667
2023-01-23 00:09:15.431876: step: 20/533, loss: 1.1561965942382812
2023-01-23 00:09:16.568471: step: 24/533, loss: 0.2859885096549988
2023-01-23 00:09:17.750801: step: 28/533, loss: 0.13757991790771484
2023-01-23 00:09:18.964122: step: 32/533, loss: 0.7600545883178711
2023-01-23 00:09:20.153544: step: 36/533, loss: 0.06282529979944229
2023-01-23 00:09:21.341407: step: 40/533, loss: 0.03997869789600372
2023-01-23 00:09:22.507011: step: 44/533, loss: 0.17397208511829376
2023-01-23 00:09:23.662928: step: 48/533, loss: 0.11370354145765305
2023-01-23 00:09:24.808333: step: 52/533, loss: 0.046379707753658295
2023-01-23 00:09:25.945410: step: 56/533, loss: 0.7432664036750793
2023-01-23 00:09:27.104725: step: 60/533, loss: 0.16724443435668945
2023-01-23 00:09:28.260371: step: 64/533, loss: 0.0855528861284256
2023-01-23 00:09:29.418401: step: 68/533, loss: 0.31670600175857544
2023-01-23 00:09:30.554614: step: 72/533, loss: 0.09054632484912872
2023-01-23 00:09:31.704902: step: 76/533, loss: 0.04326023906469345
2023-01-23 00:09:32.905943: step: 80/533, loss: 0.12371959537267685
2023-01-23 00:09:34.156092: step: 84/533, loss: 0.16149845719337463
2023-01-23 00:09:35.317754: step: 88/533, loss: 0.2936019003391266
2023-01-23 00:09:36.490837: step: 92/533, loss: 0.2979351282119751
2023-01-23 00:09:37.662647: step: 96/533, loss: 0.14254418015480042
2023-01-23 00:09:38.878882: step: 100/533, loss: 0.7453964352607727
2023-01-23 00:09:40.069269: step: 104/533, loss: 0.3402903974056244
2023-01-23 00:09:41.264215: step: 108/533, loss: 0.1641683578491211
2023-01-23 00:09:42.430199: step: 112/533, loss: 0.2477407604455948
2023-01-23 00:09:43.640832: step: 116/533, loss: 0.07361679524183273
2023-01-23 00:09:44.812403: step: 120/533, loss: 0.043189048767089844
2023-01-23 00:09:45.981217: step: 124/533, loss: 0.38951969146728516
2023-01-23 00:09:47.137379: step: 128/533, loss: 1.3054147958755493
2023-01-23 00:09:48.303306: step: 132/533, loss: 0.4066828787326813
2023-01-23 00:09:49.457450: step: 136/533, loss: 0.05499096214771271
2023-01-23 00:09:50.625900: step: 140/533, loss: 0.03694338724017143
2023-01-23 00:09:51.795037: step: 144/533, loss: 0.2237229347229004
2023-01-23 00:09:52.956164: step: 148/533, loss: 0.17048291862010956
2023-01-23 00:09:54.144597: step: 152/533, loss: 0.1532120257616043
2023-01-23 00:09:55.366077: step: 156/533, loss: 0.1119285598397255
2023-01-23 00:09:56.531970: step: 160/533, loss: 0.16961650550365448
2023-01-23 00:09:57.732084: step: 164/533, loss: 0.08274183422327042
2023-01-23 00:09:58.882618: step: 168/533, loss: 0.9294984936714172
2023-01-23 00:10:00.081639: step: 172/533, loss: 0.5300347208976746
2023-01-23 00:10:01.243168: step: 176/533, loss: 0.0946936160326004
2023-01-23 00:10:02.470588: step: 180/533, loss: 0.1105434000492096
2023-01-23 00:10:03.661562: step: 184/533, loss: 0.9350584745407104
2023-01-23 00:10:04.831657: step: 188/533, loss: 0.35646992921829224
2023-01-23 00:10:06.021943: step: 192/533, loss: 0.20065680146217346
2023-01-23 00:10:07.195619: step: 196/533, loss: 0.10344738513231277
2023-01-23 00:10:08.346426: step: 200/533, loss: 0.2196740210056305
2023-01-23 00:10:09.490981: step: 204/533, loss: 7.556061267852783
2023-01-23 00:10:10.656958: step: 208/533, loss: 0.3177177309989929
2023-01-23 00:10:11.842407: step: 212/533, loss: 0.24030885100364685
2023-01-23 00:10:13.009184: step: 216/533, loss: 6.5061445236206055
2023-01-23 00:10:14.147962: step: 220/533, loss: 0.18813514709472656
2023-01-23 00:10:15.340948: step: 224/533, loss: 0.08334064483642578
2023-01-23 00:10:16.502787: step: 228/533, loss: 0.6746306419372559
2023-01-23 00:10:17.704524: step: 232/533, loss: 0.8121949434280396
2023-01-23 00:10:18.887730: step: 236/533, loss: 0.01866598054766655
2023-01-23 00:10:20.079461: step: 240/533, loss: 0.8045177459716797
2023-01-23 00:10:21.228461: step: 244/533, loss: 0.1645314246416092
2023-01-23 00:10:22.387759: step: 248/533, loss: 0.1700821816921234
2023-01-23 00:10:23.561660: step: 252/533, loss: 0.1886609047651291
2023-01-23 00:10:24.734165: step: 256/533, loss: 0.47371262311935425
2023-01-23 00:10:25.935873: step: 260/533, loss: 0.10804824531078339
2023-01-23 00:10:27.116339: step: 264/533, loss: 0.16475573182106018
2023-01-23 00:10:28.327049: step: 268/533, loss: 0.13311119377613068
2023-01-23 00:10:29.547754: step: 272/533, loss: 0.4139326214790344
2023-01-23 00:10:30.721033: step: 276/533, loss: 0.05772047117352486
2023-01-23 00:10:31.901997: step: 280/533, loss: 0.2530384063720703
2023-01-23 00:10:33.126149: step: 284/533, loss: 0.12808284163475037
2023-01-23 00:10:34.310257: step: 288/533, loss: 0.14574074745178223
2023-01-23 00:10:35.484057: step: 292/533, loss: 0.8609334826469421
2023-01-23 00:10:36.634761: step: 296/533, loss: 0.12245547771453857
2023-01-23 00:10:37.830150: step: 300/533, loss: 0.10447988659143448
2023-01-23 00:10:38.982054: step: 304/533, loss: 0.39735668897628784
2023-01-23 00:10:40.164504: step: 308/533, loss: 1.2928032875061035
2023-01-23 00:10:41.359290: step: 312/533, loss: 0.4389309883117676
2023-01-23 00:10:42.544456: step: 316/533, loss: 0.16427643597126007
2023-01-23 00:10:43.734541: step: 320/533, loss: 0.09371490776538849
2023-01-23 00:10:44.880703: step: 324/533, loss: 0.22092023491859436
2023-01-23 00:10:46.016583: step: 328/533, loss: 0.29821139574050903
2023-01-23 00:10:47.210492: step: 332/533, loss: 0.7922015190124512
2023-01-23 00:10:48.410321: step: 336/533, loss: 0.18724536895751953
2023-01-23 00:10:49.691830: step: 340/533, loss: 0.0818777084350586
2023-01-23 00:10:50.905006: step: 344/533, loss: 0.18011704087257385
2023-01-23 00:10:52.102375: step: 348/533, loss: 0.08503279834985733
2023-01-23 00:10:53.230716: step: 352/533, loss: 0.17050866782665253
2023-01-23 00:10:54.414113: step: 356/533, loss: 0.23868036270141602
2023-01-23 00:10:55.604432: step: 360/533, loss: 0.11245355755090714
2023-01-23 00:10:56.791067: step: 364/533, loss: 0.11277976632118225
2023-01-23 00:10:58.001082: step: 368/533, loss: 0.411241739988327
2023-01-23 00:10:59.183294: step: 372/533, loss: 0.7163174152374268
2023-01-23 00:11:00.368756: step: 376/533, loss: 0.09073544293642044
2023-01-23 00:11:01.536363: step: 380/533, loss: 0.7070478200912476
2023-01-23 00:11:02.711328: step: 384/533, loss: 0.46448269486427307
2023-01-23 00:11:03.910646: step: 388/533, loss: 0.1333259642124176
2023-01-23 00:11:05.085640: step: 392/533, loss: 0.36320582032203674
2023-01-23 00:11:06.275123: step: 396/533, loss: 0.38122254610061646
2023-01-23 00:11:07.483713: step: 400/533, loss: 0.3049568235874176
2023-01-23 00:11:08.693478: step: 404/533, loss: 0.23573628067970276
2023-01-23 00:11:09.862959: step: 408/533, loss: 0.6420763731002808
2023-01-23 00:11:11.015764: step: 412/533, loss: 1.008461356163025
2023-01-23 00:11:12.221628: step: 416/533, loss: 0.22769832611083984
2023-01-23 00:11:13.352257: step: 420/533, loss: 0.7806648015975952
2023-01-23 00:11:14.516947: step: 424/533, loss: 1.0949163436889648
2023-01-23 00:11:15.704451: step: 428/533, loss: 0.10100089013576508
2023-01-23 00:11:16.887315: step: 432/533, loss: 0.08356934040784836
2023-01-23 00:11:18.040754: step: 436/533, loss: 0.12097835540771484
2023-01-23 00:11:19.252847: step: 440/533, loss: 0.412949800491333
2023-01-23 00:11:20.414042: step: 444/533, loss: 0.4608314633369446
2023-01-23 00:11:21.658755: step: 448/533, loss: 0.1743953824043274
2023-01-23 00:11:22.819289: step: 452/533, loss: 0.6128075122833252
2023-01-23 00:11:24.015019: step: 456/533, loss: 0.19651412963867188
2023-01-23 00:11:25.244655: step: 460/533, loss: 0.6721065044403076
2023-01-23 00:11:26.422534: step: 464/533, loss: 0.15967969596385956
2023-01-23 00:11:27.594750: step: 468/533, loss: 0.20060434937477112
2023-01-23 00:11:28.754647: step: 472/533, loss: 0.19437763094902039
2023-01-23 00:11:29.974338: step: 476/533, loss: 0.11729685962200165
2023-01-23 00:11:31.193157: step: 480/533, loss: 0.43636640906333923
2023-01-23 00:11:32.391283: step: 484/533, loss: 0.38820579648017883
2023-01-23 00:11:33.586462: step: 488/533, loss: 0.036032892763614655
2023-01-23 00:11:34.749052: step: 492/533, loss: 0.20904521644115448
2023-01-23 00:11:35.928975: step: 496/533, loss: 0.14324331283569336
2023-01-23 00:11:37.076810: step: 500/533, loss: 0.8581582307815552
2023-01-23 00:11:38.209539: step: 504/533, loss: 0.009099816903471947
2023-01-23 00:11:39.383634: step: 508/533, loss: 6.096617698669434
2023-01-23 00:11:40.539820: step: 512/533, loss: 0.07436814159154892
2023-01-23 00:11:41.718538: step: 516/533, loss: 0.8195649981498718
2023-01-23 00:11:42.867802: step: 520/533, loss: 0.7428781390190125
2023-01-23 00:11:44.043316: step: 524/533, loss: 0.3563980460166931
2023-01-23 00:11:45.215492: step: 528/533, loss: 0.2819378972053528
2023-01-23 00:11:46.396345: step: 532/533, loss: 0.07229113578796387
2023-01-23 00:11:47.593810: step: 536/533, loss: 0.10850057750940323
2023-01-23 00:11:48.744678: step: 540/533, loss: 0.7728476524353027
2023-01-23 00:11:49.950871: step: 544/533, loss: 0.27718108892440796
2023-01-23 00:11:51.120600: step: 548/533, loss: 0.20332804322242737
2023-01-23 00:11:52.336586: step: 552/533, loss: 0.1661197692155838
2023-01-23 00:11:53.532902: step: 556/533, loss: 0.34860095381736755
2023-01-23 00:11:54.717727: step: 560/533, loss: 0.013684368692338467
2023-01-23 00:11:55.875499: step: 564/533, loss: 0.15758386254310608
2023-01-23 00:11:57.074164: step: 568/533, loss: 0.2174517810344696
2023-01-23 00:11:58.258072: step: 572/533, loss: 0.3024938702583313
2023-01-23 00:11:59.445798: step: 576/533, loss: 0.1184653490781784
2023-01-23 00:12:00.631142: step: 580/533, loss: 1.110622525215149
2023-01-23 00:12:01.800965: step: 584/533, loss: 0.16563330590724945
2023-01-23 00:12:02.978079: step: 588/533, loss: 0.6151212453842163
2023-01-23 00:12:04.167945: step: 592/533, loss: 0.11995840072631836
2023-01-23 00:12:05.375254: step: 596/533, loss: 0.07827548682689667
2023-01-23 00:12:06.515140: step: 600/533, loss: 0.2466479241847992
2023-01-23 00:12:07.712055: step: 604/533, loss: 0.8222202658653259
2023-01-23 00:12:08.890145: step: 608/533, loss: 0.10267267376184464
2023-01-23 00:12:10.004566: step: 612/533, loss: 0.17090922594070435
2023-01-23 00:12:11.191873: step: 616/533, loss: 0.338049054145813
2023-01-23 00:12:12.356340: step: 620/533, loss: 0.1157594695687294
2023-01-23 00:12:13.535349: step: 624/533, loss: 1.3425092697143555
2023-01-23 00:12:14.694201: step: 628/533, loss: 0.20160922408103943
2023-01-23 00:12:15.889154: step: 632/533, loss: 0.2886773943901062
2023-01-23 00:12:17.126796: step: 636/533, loss: 0.059935905039310455
2023-01-23 00:12:18.290028: step: 640/533, loss: 0.10588303208351135
2023-01-23 00:12:19.462469: step: 644/533, loss: 0.5502110719680786
2023-01-23 00:12:20.632724: step: 648/533, loss: 0.298610121011734
2023-01-23 00:12:21.825487: step: 652/533, loss: 0.2920886278152466
2023-01-23 00:12:23.011776: step: 656/533, loss: 0.10092958807945251
2023-01-23 00:12:24.130802: step: 660/533, loss: 0.33596089482307434
2023-01-23 00:12:25.303968: step: 664/533, loss: 0.6211967468261719
2023-01-23 00:12:26.498192: step: 668/533, loss: 0.1802423596382141
2023-01-23 00:12:27.657423: step: 672/533, loss: 0.09360642731189728
2023-01-23 00:12:28.847526: step: 676/533, loss: 0.38748520612716675
2023-01-23 00:12:30.031729: step: 680/533, loss: 0.6602237820625305
2023-01-23 00:12:31.194011: step: 684/533, loss: 0.20110264420509338
2023-01-23 00:12:32.369334: step: 688/533, loss: 6.789928436279297
2023-01-23 00:12:33.549128: step: 692/533, loss: 0.7050453424453735
2023-01-23 00:12:34.719528: step: 696/533, loss: 6.557606220245361
2023-01-23 00:12:35.885232: step: 700/533, loss: 0.2180258333683014
2023-01-23 00:12:37.039507: step: 704/533, loss: 1.156533122062683
2023-01-23 00:12:38.231123: step: 708/533, loss: 0.18626396358013153
2023-01-23 00:12:39.428944: step: 712/533, loss: 0.16130739450454712
2023-01-23 00:12:40.602739: step: 716/533, loss: 0.11807730793952942
2023-01-23 00:12:41.758534: step: 720/533, loss: 0.1919388771057129
2023-01-23 00:12:42.934491: step: 724/533, loss: 0.23629441857337952
2023-01-23 00:12:44.107558: step: 728/533, loss: 0.14452704787254333
2023-01-23 00:12:45.292718: step: 732/533, loss: 0.1256023347377777
2023-01-23 00:12:46.441501: step: 736/533, loss: 5.827259063720703
2023-01-23 00:12:47.597465: step: 740/533, loss: 0.12067222595214844
2023-01-23 00:12:48.782197: step: 744/533, loss: 0.0689108818769455
2023-01-23 00:12:49.960073: step: 748/533, loss: 0.028519347310066223
2023-01-23 00:12:51.118693: step: 752/533, loss: 0.6715900301933289
2023-01-23 00:12:52.266307: step: 756/533, loss: 0.11868033558130264
2023-01-23 00:12:53.443430: step: 760/533, loss: 0.20304298400878906
2023-01-23 00:12:54.627831: step: 764/533, loss: 0.4125555157661438
2023-01-23 00:12:55.818274: step: 768/533, loss: 0.6204870343208313
2023-01-23 00:12:57.054491: step: 772/533, loss: 0.7362143993377686
2023-01-23 00:12:58.206311: step: 776/533, loss: 0.11665868759155273
2023-01-23 00:12:59.379076: step: 780/533, loss: 0.7963329553604126
2023-01-23 00:13:00.562080: step: 784/533, loss: 0.0415625125169754
2023-01-23 00:13:01.745648: step: 788/533, loss: 0.12673553824424744
2023-01-23 00:13:02.924264: step: 792/533, loss: 1.5688321590423584
2023-01-23 00:13:04.142562: step: 796/533, loss: 0.20103083550930023
2023-01-23 00:13:05.358124: step: 800/533, loss: 0.33872976899147034
2023-01-23 00:13:06.566957: step: 804/533, loss: 0.4234919548034668
2023-01-23 00:13:07.714810: step: 808/533, loss: 0.6318029761314392
2023-01-23 00:13:08.905747: step: 812/533, loss: 0.1803821623325348
2023-01-23 00:13:10.056706: step: 816/533, loss: 0.1712852418422699
2023-01-23 00:13:11.174821: step: 820/533, loss: 0.09087991714477539
2023-01-23 00:13:12.334197: step: 824/533, loss: 0.2951028048992157
2023-01-23 00:13:13.525208: step: 828/533, loss: 0.3447265326976776
2023-01-23 00:13:14.734604: step: 832/533, loss: 0.2435164451599121
2023-01-23 00:13:15.971079: step: 836/533, loss: 0.5090039968490601
2023-01-23 00:13:17.117288: step: 840/533, loss: 0.6650123000144958
2023-01-23 00:13:18.272023: step: 844/533, loss: 0.6050577759742737
2023-01-23 00:13:19.462224: step: 848/533, loss: 0.11153145134449005
2023-01-23 00:13:20.596943: step: 852/533, loss: 0.13925257325172424
2023-01-23 00:13:21.788682: step: 856/533, loss: 0.7219201326370239
2023-01-23 00:13:22.957760: step: 860/533, loss: 0.2796954810619354
2023-01-23 00:13:24.124743: step: 864/533, loss: 0.09976521134376526
2023-01-23 00:13:25.287803: step: 868/533, loss: 0.1735800802707672
2023-01-23 00:13:26.504147: step: 872/533, loss: 0.6152204275131226
2023-01-23 00:13:27.694860: step: 876/533, loss: 0.1786670684814453
2023-01-23 00:13:28.847897: step: 880/533, loss: 0.556827962398529
2023-01-23 00:13:30.076816: step: 884/533, loss: 0.725416362285614
2023-01-23 00:13:31.258126: step: 888/533, loss: 0.9925830960273743
2023-01-23 00:13:32.414052: step: 892/533, loss: 0.0687982589006424
2023-01-23 00:13:33.577729: step: 896/533, loss: 0.04963874816894531
2023-01-23 00:13:34.721167: step: 900/533, loss: 0.09570202976465225
2023-01-23 00:13:35.888046: step: 904/533, loss: 1.0855121612548828
2023-01-23 00:13:37.070892: step: 908/533, loss: 0.08802032470703125
2023-01-23 00:13:38.268932: step: 912/533, loss: 1.807556390762329
2023-01-23 00:13:39.466264: step: 916/533, loss: 1.6945182085037231
2023-01-23 00:13:40.635626: step: 920/533, loss: 0.09521179646253586
2023-01-23 00:13:41.802037: step: 924/533, loss: 0.07061167061328888
2023-01-23 00:13:42.972694: step: 928/533, loss: 0.2166360318660736
2023-01-23 00:13:44.130962: step: 932/533, loss: 0.09166759997606277
2023-01-23 00:13:45.334827: step: 936/533, loss: 0.07578954845666885
2023-01-23 00:13:46.506413: step: 940/533, loss: 0.8715420961380005
2023-01-23 00:13:47.671105: step: 944/533, loss: 0.0767279639840126
2023-01-23 00:13:48.804183: step: 948/533, loss: 0.19810661673545837
2023-01-23 00:13:50.016518: step: 952/533, loss: 0.08481831848621368
2023-01-23 00:13:51.212811: step: 956/533, loss: 0.43105068802833557
2023-01-23 00:13:52.365196: step: 960/533, loss: 0.28990793228149414
2023-01-23 00:13:53.554718: step: 964/533, loss: 0.08686523139476776
2023-01-23 00:13:54.747224: step: 968/533, loss: 0.718145489692688
2023-01-23 00:13:55.953424: step: 972/533, loss: 0.33432263135910034
2023-01-23 00:13:57.122133: step: 976/533, loss: 0.8757674694061279
2023-01-23 00:13:58.268688: step: 980/533, loss: 0.05391073226928711
2023-01-23 00:13:59.452958: step: 984/533, loss: 0.045043185353279114
2023-01-23 00:14:00.622877: step: 988/533, loss: 0.11546371132135391
2023-01-23 00:14:01.820218: step: 992/533, loss: 0.7150843143463135
2023-01-23 00:14:02.966096: step: 996/533, loss: 0.24153746664524078
2023-01-23 00:14:04.156023: step: 1000/533, loss: 0.7552597522735596
2023-01-23 00:14:05.331814: step: 1004/533, loss: 0.6755239963531494
2023-01-23 00:14:06.465249: step: 1008/533, loss: 0.42555132508277893
2023-01-23 00:14:07.670276: step: 1012/533, loss: 0.17450609803199768
2023-01-23 00:14:08.819963: step: 1016/533, loss: 0.07074947655200958
2023-01-23 00:14:09.998522: step: 1020/533, loss: 0.25498390197753906
2023-01-23 00:14:11.209879: step: 1024/533, loss: 0.0510433204472065
2023-01-23 00:14:12.422722: step: 1028/533, loss: 0.13398166000843048
2023-01-23 00:14:13.587018: step: 1032/533, loss: 0.1743348240852356
2023-01-23 00:14:14.739309: step: 1036/533, loss: 0.2929289937019348
2023-01-23 00:14:15.895335: step: 1040/533, loss: 0.17708474397659302
2023-01-23 00:14:17.107062: step: 1044/533, loss: 0.04255685955286026
2023-01-23 00:14:18.242801: step: 1048/533, loss: 0.09301743656396866
2023-01-23 00:14:19.409572: step: 1052/533, loss: 0.35009899735450745
2023-01-23 00:14:20.618417: step: 1056/533, loss: 0.42279911041259766
2023-01-23 00:14:21.788334: step: 1060/533, loss: 0.04605751112103462
2023-01-23 00:14:22.962757: step: 1064/533, loss: 0.040482521057128906
2023-01-23 00:14:24.130854: step: 1068/533, loss: 0.7885123491287231
2023-01-23 00:14:25.286129: step: 1072/533, loss: 5.510984420776367
2023-01-23 00:14:26.428915: step: 1076/533, loss: 0.7045764923095703
2023-01-23 00:14:27.605315: step: 1080/533, loss: 0.11668120324611664
2023-01-23 00:14:28.787550: step: 1084/533, loss: 0.15884742140769958
2023-01-23 00:14:29.939354: step: 1088/533, loss: 0.14098411798477173
2023-01-23 00:14:31.162426: step: 1092/533, loss: 0.19659024477005005
2023-01-23 00:14:32.354303: step: 1096/533, loss: 1.9845985174179077
2023-01-23 00:14:33.562886: step: 1100/533, loss: 0.45900583267211914
2023-01-23 00:14:34.710776: step: 1104/533, loss: 0.7520493865013123
2023-01-23 00:14:35.887747: step: 1108/533, loss: 6.177628993988037
2023-01-23 00:14:37.091580: step: 1112/533, loss: 0.3970717489719391
2023-01-23 00:14:38.279433: step: 1116/533, loss: 0.08741851150989532
2023-01-23 00:14:39.455924: step: 1120/533, loss: 0.01384887658059597
2023-01-23 00:14:40.613387: step: 1124/533, loss: 0.0630807876586914
2023-01-23 00:14:41.836813: step: 1128/533, loss: 0.1139598861336708
2023-01-23 00:14:42.981272: step: 1132/533, loss: 0.09872536361217499
2023-01-23 00:14:44.121205: step: 1136/533, loss: 1.0366337299346924
2023-01-23 00:14:45.340015: step: 1140/533, loss: 0.6433200836181641
2023-01-23 00:14:46.539430: step: 1144/533, loss: 0.07232493907213211
2023-01-23 00:14:47.712457: step: 1148/533, loss: 0.0791909247636795
2023-01-23 00:14:48.895067: step: 1152/533, loss: 0.17272216081619263
2023-01-23 00:14:50.081946: step: 1156/533, loss: 0.3607533574104309
2023-01-23 00:14:51.261316: step: 1160/533, loss: 0.2840801477432251
2023-01-23 00:14:52.440539: step: 1164/533, loss: 0.09294863045215607
2023-01-23 00:14:53.597366: step: 1168/533, loss: 0.1951891928911209
2023-01-23 00:14:54.769955: step: 1172/533, loss: 0.23752471804618835
2023-01-23 00:14:55.922994: step: 1176/533, loss: 0.08013544231653214
2023-01-23 00:14:57.089290: step: 1180/533, loss: 0.385166734457016
2023-01-23 00:14:58.316173: step: 1184/533, loss: 0.28750577569007874
2023-01-23 00:14:59.518175: step: 1188/533, loss: 0.20149211585521698
2023-01-23 00:15:00.676640: step: 1192/533, loss: 0.06264295428991318
2023-01-23 00:15:01.865653: step: 1196/533, loss: 0.5978087186813354
2023-01-23 00:15:03.025429: step: 1200/533, loss: 0.11043882369995117
2023-01-23 00:15:04.195408: step: 1204/533, loss: 0.6323989629745483
2023-01-23 00:15:05.361271: step: 1208/533, loss: 0.541048526763916
2023-01-23 00:15:06.518654: step: 1212/533, loss: 0.14680881798267365
2023-01-23 00:15:07.690234: step: 1216/533, loss: 0.19817982614040375
2023-01-23 00:15:08.919960: step: 1220/533, loss: 0.10579681396484375
2023-01-23 00:15:10.110365: step: 1224/533, loss: 1.2712929248809814
2023-01-23 00:15:11.287574: step: 1228/533, loss: 0.5510305762290955
2023-01-23 00:15:12.478902: step: 1232/533, loss: 0.08197517693042755
2023-01-23 00:15:13.669055: step: 1236/533, loss: 0.14559394121170044
2023-01-23 00:15:14.852497: step: 1240/533, loss: 0.21898965537548065
2023-01-23 00:15:16.027341: step: 1244/533, loss: 0.11944732815027237
2023-01-23 00:15:17.262492: step: 1248/533, loss: 0.711075484752655
2023-01-23 00:15:18.517564: step: 1252/533, loss: 0.24308347702026367
2023-01-23 00:15:19.742196: step: 1256/533, loss: 0.7453237771987915
2023-01-23 00:15:20.893066: step: 1260/533, loss: 0.7348448038101196
2023-01-23 00:15:22.104303: step: 1264/533, loss: 0.5355383157730103
2023-01-23 00:15:23.255586: step: 1268/533, loss: 0.17442288994789124
2023-01-23 00:15:24.406359: step: 1272/533, loss: 0.081713005900383
2023-01-23 00:15:25.578271: step: 1276/533, loss: 5.200689315795898
2023-01-23 00:15:26.773502: step: 1280/533, loss: 0.38226261734962463
2023-01-23 00:15:27.980133: step: 1284/533, loss: 0.31229841709136963
2023-01-23 00:15:29.142819: step: 1288/533, loss: 0.0915495902299881
2023-01-23 00:15:30.315262: step: 1292/533, loss: 0.11697855591773987
2023-01-23 00:15:31.473090: step: 1296/533, loss: 0.1356651484966278
2023-01-23 00:15:32.628195: step: 1300/533, loss: 0.3107897639274597
2023-01-23 00:15:33.803998: step: 1304/533, loss: 0.32370811700820923
2023-01-23 00:15:34.984420: step: 1308/533, loss: 0.4293191432952881
2023-01-23 00:15:36.180939: step: 1312/533, loss: 0.13465996086597443
2023-01-23 00:15:37.399039: step: 1316/533, loss: 0.18126791715621948
2023-01-23 00:15:38.575602: step: 1320/533, loss: 0.16612711548805237
2023-01-23 00:15:39.735743: step: 1324/533, loss: 0.4484199583530426
2023-01-23 00:15:40.933355: step: 1328/533, loss: 0.3617344796657562
2023-01-23 00:15:42.084364: step: 1332/533, loss: 0.040073588490486145
2023-01-23 00:15:43.228773: step: 1336/533, loss: 0.25802773237228394
2023-01-23 00:15:44.373417: step: 1340/533, loss: 0.16844701766967773
2023-01-23 00:15:45.528575: step: 1344/533, loss: 0.1379452347755432
2023-01-23 00:15:46.703480: step: 1348/533, loss: 0.8102596998214722
2023-01-23 00:15:47.888249: step: 1352/533, loss: 0.029878616333007812
2023-01-23 00:15:49.072429: step: 1356/533, loss: 0.21733397245407104
2023-01-23 00:15:50.296270: step: 1360/533, loss: 0.1776810735464096
2023-01-23 00:15:51.517095: step: 1364/533, loss: 0.3859017491340637
2023-01-23 00:15:52.717402: step: 1368/533, loss: 0.2634678781032562
2023-01-23 00:15:53.883404: step: 1372/533, loss: 0.29899561405181885
2023-01-23 00:15:55.054432: step: 1376/533, loss: 0.38006791472435
2023-01-23 00:15:56.175360: step: 1380/533, loss: 0.04742402955889702
2023-01-23 00:15:57.362980: step: 1384/533, loss: 0.18840648233890533
2023-01-23 00:15:58.524027: step: 1388/533, loss: 0.03719749301671982
2023-01-23 00:15:59.681807: step: 1392/533, loss: 0.6020131707191467
2023-01-23 00:16:00.904068: step: 1396/533, loss: 0.3525051176548004
2023-01-23 00:16:02.100411: step: 1400/533, loss: 0.42236506938934326
2023-01-23 00:16:03.282086: step: 1404/533, loss: 1.0156099796295166
2023-01-23 00:16:04.414872: step: 1408/533, loss: 0.31141966581344604
2023-01-23 00:16:05.564692: step: 1412/533, loss: 0.06403665244579315
2023-01-23 00:16:06.746789: step: 1416/533, loss: 0.16745629906654358
2023-01-23 00:16:07.897261: step: 1420/533, loss: 0.20169982314109802
2023-01-23 00:16:09.106724: step: 1424/533, loss: 0.871826171875
2023-01-23 00:16:10.296188: step: 1428/533, loss: 0.8681539297103882
2023-01-23 00:16:11.465582: step: 1432/533, loss: 0.09811706840991974
2023-01-23 00:16:12.679357: step: 1436/533, loss: 0.14755316078662872
2023-01-23 00:16:13.842154: step: 1440/533, loss: 0.23911935091018677
2023-01-23 00:16:15.038725: step: 1444/533, loss: 0.3370138108730316
2023-01-23 00:16:16.209223: step: 1448/533, loss: 0.6119120717048645
2023-01-23 00:16:17.389880: step: 1452/533, loss: 0.36522483825683594
2023-01-23 00:16:18.561439: step: 1456/533, loss: 0.06301660090684891
2023-01-23 00:16:19.749122: step: 1460/533, loss: 0.10820493847131729
2023-01-23 00:16:20.898713: step: 1464/533, loss: 0.28848162293434143
2023-01-23 00:16:22.035384: step: 1468/533, loss: 0.079480841755867
2023-01-23 00:16:23.243968: step: 1472/533, loss: 0.10893673449754715
2023-01-23 00:16:24.433932: step: 1476/533, loss: 0.9639902114868164
2023-01-23 00:16:25.605041: step: 1480/533, loss: 0.6345762610435486
2023-01-23 00:16:26.741062: step: 1484/533, loss: 0.08421941101551056
2023-01-23 00:16:27.876546: step: 1488/533, loss: 0.0578124038875103
2023-01-23 00:16:29.058670: step: 1492/533, loss: 0.31327182054519653
2023-01-23 00:16:30.244115: step: 1496/533, loss: 0.08017121255397797
2023-01-23 00:16:31.447643: step: 1500/533, loss: 0.22312337160110474
2023-01-23 00:16:32.616075: step: 1504/533, loss: 0.637442409992218
2023-01-23 00:16:33.827534: step: 1508/533, loss: 1.16358482837677
2023-01-23 00:16:35.055865: step: 1512/533, loss: 0.08317212760448456
2023-01-23 00:16:36.208850: step: 1516/533, loss: 0.2635626792907715
2023-01-23 00:16:37.392756: step: 1520/533, loss: 0.11569662392139435
2023-01-23 00:16:38.592580: step: 1524/533, loss: 0.12475547939538956
2023-01-23 00:16:39.774769: step: 1528/533, loss: 0.7947450280189514
2023-01-23 00:16:40.953026: step: 1532/533, loss: 0.5174509882926941
2023-01-23 00:16:42.175665: step: 1536/533, loss: 0.14672188460826874
2023-01-23 00:16:43.332722: step: 1540/533, loss: 0.01967933215200901
2023-01-23 00:16:44.483489: step: 1544/533, loss: 0.47687575221061707
2023-01-23 00:16:45.638032: step: 1548/533, loss: 0.06152964010834694
2023-01-23 00:16:46.785360: step: 1552/533, loss: 0.09312210977077484
2023-01-23 00:16:47.953184: step: 1556/533, loss: 0.089032843708992
2023-01-23 00:16:49.176577: step: 1560/533, loss: 0.4784398078918457
2023-01-23 00:16:50.378401: step: 1564/533, loss: 0.14908543229103088
2023-01-23 00:16:51.567030: step: 1568/533, loss: 0.49519291520118713
2023-01-23 00:16:52.727820: step: 1572/533, loss: 0.20832185447216034
2023-01-23 00:16:53.870304: step: 1576/533, loss: 0.23972997069358826
2023-01-23 00:16:55.056416: step: 1580/533, loss: 0.2782464027404785
2023-01-23 00:16:56.214645: step: 1584/533, loss: 0.04326915740966797
2023-01-23 00:16:57.434531: step: 1588/533, loss: 0.08292331546545029
2023-01-23 00:16:58.632306: step: 1592/533, loss: 0.7723281383514404
2023-01-23 00:16:59.820542: step: 1596/533, loss: 0.49383050203323364
2023-01-23 00:17:00.983670: step: 1600/533, loss: 0.3659517765045166
2023-01-23 00:17:02.174443: step: 1604/533, loss: 0.06499271094799042
2023-01-23 00:17:03.351356: step: 1608/533, loss: 0.25885510444641113
2023-01-23 00:17:04.527384: step: 1612/533, loss: 0.05401439964771271
2023-01-23 00:17:05.752865: step: 1616/533, loss: 0.267822265625
2023-01-23 00:17:06.915609: step: 1620/533, loss: 0.6613141298294067
2023-01-23 00:17:08.115832: step: 1624/533, loss: 0.3519867956638336
2023-01-23 00:17:09.293974: step: 1628/533, loss: 0.22230637073516846
2023-01-23 00:17:10.437231: step: 1632/533, loss: 0.03190779685974121
2023-01-23 00:17:11.605690: step: 1636/533, loss: 1.0905355215072632
2023-01-23 00:17:12.780157: step: 1640/533, loss: 0.05632734298706055
2023-01-23 00:17:13.933229: step: 1644/533, loss: 0.18079432845115662
2023-01-23 00:17:15.126344: step: 1648/533, loss: 0.14281006157398224
2023-01-23 00:17:16.285711: step: 1652/533, loss: 1.0845324993133545
2023-01-23 00:17:17.458775: step: 1656/533, loss: 0.10688714683055878
2023-01-23 00:17:18.598407: step: 1660/533, loss: 0.08639836311340332
2023-01-23 00:17:19.832602: step: 1664/533, loss: 0.5937854647636414
2023-01-23 00:17:21.014442: step: 1668/533, loss: 0.05844841152429581
2023-01-23 00:17:22.179404: step: 1672/533, loss: 0.07084226608276367
2023-01-23 00:17:23.326577: step: 1676/533, loss: 0.10019215941429138
2023-01-23 00:17:24.521499: step: 1680/533, loss: 0.052054405212402344
2023-01-23 00:17:25.686631: step: 1684/533, loss: 0.5961360931396484
2023-01-23 00:17:26.837169: step: 1688/533, loss: 0.6336082816123962
2023-01-23 00:17:28.027019: step: 1692/533, loss: 0.17626100778579712
2023-01-23 00:17:29.206007: step: 1696/533, loss: 0.2126356065273285
2023-01-23 00:17:30.399703: step: 1700/533, loss: 0.6530532240867615
2023-01-23 00:17:31.580196: step: 1704/533, loss: 0.1026669517159462
2023-01-23 00:17:32.774707: step: 1708/533, loss: 0.06398515403270721
2023-01-23 00:17:33.951976: step: 1712/533, loss: 0.019005395472049713
2023-01-23 00:17:35.130236: step: 1716/533, loss: 0.14805489778518677
2023-01-23 00:17:36.331560: step: 1720/533, loss: 0.807794451713562
2023-01-23 00:17:37.520589: step: 1724/533, loss: 0.11912989616394043
2023-01-23 00:17:38.737958: step: 1728/533, loss: 0.19164490699768066
2023-01-23 00:17:39.871519: step: 1732/533, loss: 0.4997274875640869
2023-01-23 00:17:41.035526: step: 1736/533, loss: 0.08028631657361984
2023-01-23 00:17:42.233873: step: 1740/533, loss: 0.38860541582107544
2023-01-23 00:17:43.430512: step: 1744/533, loss: 0.7654044032096863
2023-01-23 00:17:44.579051: step: 1748/533, loss: 0.23120225965976715
2023-01-23 00:17:45.746835: step: 1752/533, loss: 0.05283026397228241
2023-01-23 00:17:46.902034: step: 1756/533, loss: 0.2377423346042633
2023-01-23 00:17:48.105853: step: 1760/533, loss: 0.09864912182092667
2023-01-23 00:17:49.279538: step: 1764/533, loss: 0.6943032741546631
2023-01-23 00:17:50.463108: step: 1768/533, loss: 0.4640032649040222
2023-01-23 00:17:51.639159: step: 1772/533, loss: 0.6499159336090088
2023-01-23 00:17:52.804796: step: 1776/533, loss: 0.136498361825943
2023-01-23 00:17:53.986964: step: 1780/533, loss: 0.7912119626998901
2023-01-23 00:17:55.153133: step: 1784/533, loss: 0.17415256798267365
2023-01-23 00:17:56.292623: step: 1788/533, loss: 0.39642849564552307
2023-01-23 00:17:57.465517: step: 1792/533, loss: 0.25583165884017944
2023-01-23 00:17:58.628162: step: 1796/533, loss: 1.0334510803222656
2023-01-23 00:17:59.793749: step: 1800/533, loss: 0.030234910547733307
2023-01-23 00:18:00.984985: step: 1804/533, loss: 0.8843833208084106
2023-01-23 00:18:02.175060: step: 1808/533, loss: 0.11465645581483841
2023-01-23 00:18:03.363342: step: 1812/533, loss: 0.29103779792785645
2023-01-23 00:18:04.547626: step: 1816/533, loss: 0.17670278251171112
2023-01-23 00:18:05.729529: step: 1820/533, loss: 0.07809782028198242
2023-01-23 00:18:06.938313: step: 1824/533, loss: 0.15545521676540375
2023-01-23 00:18:08.090357: step: 1828/533, loss: 0.21935686469078064
2023-01-23 00:18:09.275322: step: 1832/533, loss: 0.1724845916032791
2023-01-23 00:18:10.426828: step: 1836/533, loss: 0.07348985970020294
2023-01-23 00:18:11.619350: step: 1840/533, loss: 0.10673341155052185
2023-01-23 00:18:12.784957: step: 1844/533, loss: 1.6208428144454956
2023-01-23 00:18:13.922832: step: 1848/533, loss: 0.09668588638305664
2023-01-23 00:18:15.143644: step: 1852/533, loss: 0.7784967422485352
2023-01-23 00:18:16.309790: step: 1856/533, loss: 0.36850759387016296
2023-01-23 00:18:17.499661: step: 1860/533, loss: 0.2463562935590744
2023-01-23 00:18:18.700985: step: 1864/533, loss: 1.013809084892273
2023-01-23 00:18:19.904955: step: 1868/533, loss: 0.16174575686454773
2023-01-23 00:18:21.107622: step: 1872/533, loss: 0.1303505003452301
2023-01-23 00:18:22.299865: step: 1876/533, loss: 0.2305046170949936
2023-01-23 00:18:23.478428: step: 1880/533, loss: 0.44880956411361694
2023-01-23 00:18:24.666630: step: 1884/533, loss: 0.10925905406475067
2023-01-23 00:18:25.819902: step: 1888/533, loss: 0.25126829743385315
2023-01-23 00:18:27.015150: step: 1892/533, loss: 0.27894097566604614
2023-01-23 00:18:28.190503: step: 1896/533, loss: 0.5337204933166504
2023-01-23 00:18:29.373805: step: 1900/533, loss: 0.10193166136741638
2023-01-23 00:18:30.553717: step: 1904/533, loss: 0.0545649528503418
2023-01-23 00:18:31.742424: step: 1908/533, loss: 0.09411277621984482
2023-01-23 00:18:32.892481: step: 1912/533, loss: 0.12842321395874023
2023-01-23 00:18:34.063083: step: 1916/533, loss: 0.07013235241174698
2023-01-23 00:18:35.265224: step: 1920/533, loss: 0.10923346877098083
2023-01-23 00:18:36.471475: step: 1924/533, loss: 0.5884883999824524
2023-01-23 00:18:37.623129: step: 1928/533, loss: 0.2668037414550781
2023-01-23 00:18:38.784724: step: 1932/533, loss: 0.045733071863651276
2023-01-23 00:18:39.950826: step: 1936/533, loss: 0.07686290889978409
2023-01-23 00:18:41.117287: step: 1940/533, loss: 0.1623860001564026
2023-01-23 00:18:42.283895: step: 1944/533, loss: 4.371690273284912
2023-01-23 00:18:43.451883: step: 1948/533, loss: 0.049350835382938385
2023-01-23 00:18:44.623441: step: 1952/533, loss: 0.30196380615234375
2023-01-23 00:18:45.840624: step: 1956/533, loss: 0.6507329344749451
2023-01-23 00:18:46.990578: step: 1960/533, loss: 0.09905920177698135
2023-01-23 00:18:48.150613: step: 1964/533, loss: 0.047605134546756744
2023-01-23 00:18:49.303193: step: 1968/533, loss: 0.18005454540252686
2023-01-23 00:18:50.432348: step: 1972/533, loss: 0.32386618852615356
2023-01-23 00:18:51.627057: step: 1976/533, loss: 2.035412311553955
2023-01-23 00:18:52.826757: step: 1980/533, loss: 0.23445968329906464
2023-01-23 00:18:53.986670: step: 1984/533, loss: 0.06588487327098846
2023-01-23 00:18:55.140778: step: 1988/533, loss: 0.29961585998535156
2023-01-23 00:18:56.296800: step: 1992/533, loss: 0.41132137179374695
2023-01-23 00:18:57.480027: step: 1996/533, loss: 0.15920743346214294
2023-01-23 00:18:58.631518: step: 2000/533, loss: 1.2604306936264038
2023-01-23 00:18:59.812427: step: 2004/533, loss: 0.7499514222145081
2023-01-23 00:19:00.988880: step: 2008/533, loss: 0.16321706771850586
2023-01-23 00:19:02.133222: step: 2012/533, loss: 0.39645081758499146
2023-01-23 00:19:03.320690: step: 2016/533, loss: 0.1803477257490158
2023-01-23 00:19:04.458751: step: 2020/533, loss: 0.13040466606616974
2023-01-23 00:19:05.622167: step: 2024/533, loss: 0.14299148321151733
2023-01-23 00:19:06.790462: step: 2028/533, loss: 0.2886943817138672
2023-01-23 00:19:07.973859: step: 2032/533, loss: 0.05794897302985191
2023-01-23 00:19:09.138976: step: 2036/533, loss: 0.06020651012659073
2023-01-23 00:19:10.327132: step: 2040/533, loss: 0.06842012703418732
2023-01-23 00:19:11.506568: step: 2044/533, loss: 0.05030565336346626
2023-01-23 00:19:12.732238: step: 2048/533, loss: 0.28099098801612854
2023-01-23 00:19:13.887645: step: 2052/533, loss: 0.051462698727846146
2023-01-23 00:19:15.046348: step: 2056/533, loss: 0.44959595799446106
2023-01-23 00:19:16.234832: step: 2060/533, loss: 0.2987767457962036
2023-01-23 00:19:17.400250: step: 2064/533, loss: 0.4543399214744568
2023-01-23 00:19:18.558999: step: 2068/533, loss: 0.5146217346191406
2023-01-23 00:19:19.767840: step: 2072/533, loss: 5.33129358291626
2023-01-23 00:19:20.919737: step: 2076/533, loss: 0.06337728351354599
2023-01-23 00:19:22.115547: step: 2080/533, loss: 0.1781458854675293
2023-01-23 00:19:23.268632: step: 2084/533, loss: 0.15403088927268982
2023-01-23 00:19:24.428692: step: 2088/533, loss: 0.10929388552904129
2023-01-23 00:19:25.639120: step: 2092/533, loss: 0.13719424605369568
2023-01-23 00:19:26.781736: step: 2096/533, loss: 0.03629489243030548
2023-01-23 00:19:27.933779: step: 2100/533, loss: 0.3804849684238434
2023-01-23 00:19:29.085653: step: 2104/533, loss: 0.4966081380844116
2023-01-23 00:19:30.227081: step: 2108/533, loss: 0.04897712171077728
2023-01-23 00:19:31.438931: step: 2112/533, loss: 0.4192419946193695
2023-01-23 00:19:32.659237: step: 2116/533, loss: 0.11249351501464844
2023-01-23 00:19:33.838774: step: 2120/533, loss: 1.5381256341934204
2023-01-23 00:19:34.999573: step: 2124/533, loss: 0.3666750490665436
2023-01-23 00:19:36.190513: step: 2128/533, loss: 0.17426948249340057
2023-01-23 00:19:37.355882: step: 2132/533, loss: 0.09110651165246964
==================================================
Loss: 0.443
--------------------
Dev: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.5517241379310345, 'r': 0.8888888888888888, 'f1': 0.6808510638297872}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.48717948717948717, 'r': 0.5277777777777778, 'f1': 0.5066666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.48717948717948717, 'r': 0.5277777777777778, 'f1': 0.5066666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:20:28.336143: step: 4/533, loss: 0.2078016698360443
2023-01-23 00:20:29.499209: step: 8/533, loss: 0.31518229842185974
2023-01-23 00:20:30.660966: step: 12/533, loss: 0.026435114443302155
2023-01-23 00:20:31.856858: step: 16/533, loss: 0.17656183242797852
2023-01-23 00:20:33.019504: step: 20/533, loss: 0.11464977264404297
2023-01-23 00:20:34.216103: step: 24/533, loss: 0.0932437926530838
2023-01-23 00:20:35.398839: step: 28/533, loss: 0.16593581438064575
2023-01-23 00:20:36.571108: step: 32/533, loss: 0.3303230404853821
2023-01-23 00:20:37.746852: step: 36/533, loss: 0.09351110458374023
2023-01-23 00:20:38.910873: step: 40/533, loss: 0.4381864070892334
2023-01-23 00:20:40.091678: step: 44/533, loss: 0.5056236386299133
2023-01-23 00:20:41.229943: step: 48/533, loss: 0.053463414311409
2023-01-23 00:20:42.395317: step: 52/533, loss: 0.4643387794494629
2023-01-23 00:20:43.546771: step: 56/533, loss: 0.05888638645410538
2023-01-23 00:20:44.728668: step: 60/533, loss: 0.09870719909667969
2023-01-23 00:20:45.883119: step: 64/533, loss: 0.050325583666563034
2023-01-23 00:20:47.006704: step: 68/533, loss: 0.4720114469528198
2023-01-23 00:20:48.189108: step: 72/533, loss: 0.11935101449489594
2023-01-23 00:20:49.364627: step: 76/533, loss: 0.1484021246433258
2023-01-23 00:20:50.543408: step: 80/533, loss: 0.6812185049057007
2023-01-23 00:20:51.729395: step: 84/533, loss: 0.11881309002637863
2023-01-23 00:20:52.904255: step: 88/533, loss: 0.13198252022266388
2023-01-23 00:20:54.093821: step: 92/533, loss: 0.11519059538841248
2023-01-23 00:20:55.244664: step: 96/533, loss: 0.13022871315479279
2023-01-23 00:20:56.408795: step: 100/533, loss: 0.075426384806633
2023-01-23 00:20:57.576062: step: 104/533, loss: 0.6256099939346313
2023-01-23 00:20:58.779030: step: 108/533, loss: 0.5357329845428467
2023-01-23 00:20:59.956770: step: 112/533, loss: 0.25639086961746216
2023-01-23 00:21:01.107653: step: 116/533, loss: 0.2864781320095062
2023-01-23 00:21:02.368006: step: 120/533, loss: 0.11975307762622833
2023-01-23 00:21:03.538329: step: 124/533, loss: 0.13876304030418396
2023-01-23 00:21:04.720205: step: 128/533, loss: 0.0528528206050396
2023-01-23 00:21:05.887599: step: 132/533, loss: 0.07103414833545685
2023-01-23 00:21:07.056494: step: 136/533, loss: 0.1213715523481369
2023-01-23 00:21:08.180683: step: 140/533, loss: 0.2966233193874359
2023-01-23 00:21:09.364363: step: 144/533, loss: 0.33138924837112427
2023-01-23 00:21:10.511215: step: 148/533, loss: 0.8489260673522949
2023-01-23 00:21:11.705858: step: 152/533, loss: 0.12019577622413635
2023-01-23 00:21:12.852512: step: 156/533, loss: 0.14811936020851135
2023-01-23 00:21:14.001836: step: 160/533, loss: 0.03802354261279106
2023-01-23 00:21:15.183767: step: 164/533, loss: 0.07348743081092834
2023-01-23 00:21:16.356843: step: 168/533, loss: 0.7071317434310913
2023-01-23 00:21:17.535124: step: 172/533, loss: 0.5400540828704834
2023-01-23 00:21:18.690859: step: 176/533, loss: 0.329581618309021
2023-01-23 00:21:19.854638: step: 180/533, loss: 0.5030377507209778
2023-01-23 00:21:21.010130: step: 184/533, loss: 0.2839488387107849
2023-01-23 00:21:22.182070: step: 188/533, loss: 0.15923671424388885
2023-01-23 00:21:23.385091: step: 192/533, loss: 0.219902902841568
2023-01-23 00:21:24.567794: step: 196/533, loss: 2.0716328620910645
2023-01-23 00:21:25.784794: step: 200/533, loss: 0.14099450409412384
2023-01-23 00:21:26.952112: step: 204/533, loss: 0.11872296780347824
2023-01-23 00:21:28.096250: step: 208/533, loss: 0.02985839918255806
2023-01-23 00:21:29.269909: step: 212/533, loss: 0.19700823724269867
2023-01-23 00:21:30.446847: step: 216/533, loss: 0.10918435454368591
2023-01-23 00:21:31.586556: step: 220/533, loss: 0.22313785552978516
2023-01-23 00:21:32.766685: step: 224/533, loss: 0.09669509530067444
2023-01-23 00:21:33.924620: step: 228/533, loss: 0.17720898985862732
2023-01-23 00:21:35.096313: step: 232/533, loss: 1.2134418487548828
2023-01-23 00:21:36.275337: step: 236/533, loss: 0.3068639636039734
2023-01-23 00:21:37.477696: step: 240/533, loss: 0.3462057411670685
2023-01-23 00:21:38.678574: step: 244/533, loss: 0.1848122626543045
2023-01-23 00:21:39.873661: step: 248/533, loss: 1.5631258487701416
2023-01-23 00:21:41.017906: step: 252/533, loss: 0.13114280998706818
2023-01-23 00:21:42.184000: step: 256/533, loss: 0.11863727867603302
2023-01-23 00:21:43.376419: step: 260/533, loss: 0.07429871708154678
2023-01-23 00:21:44.515906: step: 264/533, loss: 0.18646402657032013
2023-01-23 00:21:45.729924: step: 268/533, loss: 0.27133816480636597
2023-01-23 00:21:46.920452: step: 272/533, loss: 0.1807132363319397
2023-01-23 00:21:48.057579: step: 276/533, loss: 0.5122114419937134
2023-01-23 00:21:49.240640: step: 280/533, loss: 0.07589464634656906
2023-01-23 00:21:50.427604: step: 284/533, loss: 0.1204366683959961
2023-01-23 00:21:51.587752: step: 288/533, loss: 0.2831389605998993
2023-01-23 00:21:52.796625: step: 292/533, loss: 0.5479009747505188
2023-01-23 00:21:53.999157: step: 296/533, loss: 0.1523316204547882
2023-01-23 00:21:55.171755: step: 300/533, loss: 0.08619347214698792
2023-01-23 00:21:56.334333: step: 304/533, loss: 0.22536487877368927
2023-01-23 00:21:57.540235: step: 308/533, loss: 0.38911542296409607
2023-01-23 00:21:58.721624: step: 312/533, loss: 0.04329654946923256
2023-01-23 00:21:59.902600: step: 316/533, loss: 0.45962390303611755
2023-01-23 00:22:01.069003: step: 320/533, loss: 0.04925408214330673
2023-01-23 00:22:02.217125: step: 324/533, loss: 0.24926291406154633
2023-01-23 00:22:03.391808: step: 328/533, loss: 0.4987621009349823
2023-01-23 00:22:04.580399: step: 332/533, loss: 0.006787109188735485
2023-01-23 00:22:05.789666: step: 336/533, loss: 0.24444876611232758
2023-01-23 00:22:06.994937: step: 340/533, loss: 0.29878556728363037
2023-01-23 00:22:08.205425: step: 344/533, loss: 0.04171190410852432
2023-01-23 00:22:09.409519: step: 348/533, loss: 0.8884342908859253
2023-01-23 00:22:10.638417: step: 352/533, loss: 0.15009284019470215
2023-01-23 00:22:11.781980: step: 356/533, loss: 0.022879624739289284
2023-01-23 00:22:12.989483: step: 360/533, loss: 0.4236254394054413
2023-01-23 00:22:14.168666: step: 364/533, loss: 0.710014283657074
2023-01-23 00:22:15.336278: step: 368/533, loss: 0.5040040612220764
2023-01-23 00:22:16.546179: step: 372/533, loss: 0.1399248093366623
2023-01-23 00:22:17.730030: step: 376/533, loss: 0.07454462349414825
2023-01-23 00:22:18.883750: step: 380/533, loss: 0.10650920867919922
2023-01-23 00:22:20.065725: step: 384/533, loss: 0.12517786026000977
2023-01-23 00:22:21.213741: step: 388/533, loss: 0.1347772628068924
2023-01-23 00:22:22.402889: step: 392/533, loss: 0.3723783493041992
2023-01-23 00:22:23.597355: step: 396/533, loss: 0.2512499988079071
2023-01-23 00:22:24.723269: step: 400/533, loss: 0.15802955627441406
2023-01-23 00:22:25.953502: step: 404/533, loss: 0.24489697813987732
2023-01-23 00:22:27.094879: step: 408/533, loss: 0.18426179885864258
2023-01-23 00:22:28.315098: step: 412/533, loss: 0.33918437361717224
2023-01-23 00:22:29.506546: step: 416/533, loss: 0.03830733522772789
2023-01-23 00:22:30.708738: step: 420/533, loss: 0.07256555557250977
2023-01-23 00:22:31.874105: step: 424/533, loss: 0.23671989142894745
2023-01-23 00:22:33.067131: step: 428/533, loss: 0.17922210693359375
2023-01-23 00:22:34.274102: step: 432/533, loss: 0.19453468918800354
2023-01-23 00:22:35.414512: step: 436/533, loss: 0.02808399125933647
2023-01-23 00:22:36.628716: step: 440/533, loss: 0.158246710896492
2023-01-23 00:22:37.802204: step: 444/533, loss: 0.7060526013374329
2023-01-23 00:22:38.934648: step: 448/533, loss: 0.07113365828990936
2023-01-23 00:22:40.102583: step: 452/533, loss: 0.13560420274734497
2023-01-23 00:22:41.272011: step: 456/533, loss: 0.39642783999443054
2023-01-23 00:22:42.416286: step: 460/533, loss: 0.21954207122325897
2023-01-23 00:22:43.602904: step: 464/533, loss: 0.48731398582458496
2023-01-23 00:22:44.788748: step: 468/533, loss: 0.4911355972290039
2023-01-23 00:22:45.933671: step: 472/533, loss: 0.1939440220594406
2023-01-23 00:22:47.118116: step: 476/533, loss: 0.1469784677028656
2023-01-23 00:22:48.255386: step: 480/533, loss: 0.12989595532417297
2023-01-23 00:22:49.422769: step: 484/533, loss: 0.8503895998001099
2023-01-23 00:22:50.605859: step: 488/533, loss: 0.5811647176742554
2023-01-23 00:22:51.780544: step: 492/533, loss: 0.16675075888633728
2023-01-23 00:22:52.991965: step: 496/533, loss: 0.11213760823011398
2023-01-23 00:22:54.134276: step: 500/533, loss: 0.07026652991771698
2023-01-23 00:22:55.326122: step: 504/533, loss: 0.2696276605129242
2023-01-23 00:22:56.475112: step: 508/533, loss: 1.6246525049209595
2023-01-23 00:22:57.610626: step: 512/533, loss: 0.19958114624023438
2023-01-23 00:22:58.766170: step: 516/533, loss: 0.2736547589302063
2023-01-23 00:23:00.003831: step: 520/533, loss: 0.4516318440437317
2023-01-23 00:23:01.183752: step: 524/533, loss: 0.09942984580993652
2023-01-23 00:23:02.314286: step: 528/533, loss: 0.1929490566253662
2023-01-23 00:23:03.554511: step: 532/533, loss: 0.12010325491428375
2023-01-23 00:23:04.708924: step: 536/533, loss: 0.8290392756462097
2023-01-23 00:23:05.885724: step: 540/533, loss: 0.03588051721453667
2023-01-23 00:23:07.024863: step: 544/533, loss: 0.6883276104927063
2023-01-23 00:23:08.214335: step: 548/533, loss: 1.1545380353927612
2023-01-23 00:23:09.378759: step: 552/533, loss: 0.06733036041259766
2023-01-23 00:23:10.494536: step: 556/533, loss: 0.07664375007152557
2023-01-23 00:23:11.686519: step: 560/533, loss: 0.16379842162132263
2023-01-23 00:23:12.880865: step: 564/533, loss: 0.24413833022117615
2023-01-23 00:23:14.049882: step: 568/533, loss: 0.13898450136184692
2023-01-23 00:23:15.220876: step: 572/533, loss: 0.30169177055358887
2023-01-23 00:23:16.399255: step: 576/533, loss: 0.44153380393981934
2023-01-23 00:23:17.610385: step: 580/533, loss: 0.18375855684280396
2023-01-23 00:23:18.792382: step: 584/533, loss: 1.6990687847137451
2023-01-23 00:23:19.938867: step: 588/533, loss: 3.2265725135803223
2023-01-23 00:23:21.132923: step: 592/533, loss: 0.10718021541833878
2023-01-23 00:23:22.313098: step: 596/533, loss: 0.2942487597465515
2023-01-23 00:23:23.484099: step: 600/533, loss: 0.07089582085609436
2023-01-23 00:23:24.606624: step: 604/533, loss: 0.29861927032470703
2023-01-23 00:23:25.785433: step: 608/533, loss: 0.5086458325386047
2023-01-23 00:23:26.938082: step: 612/533, loss: 0.17752285301685333
2023-01-23 00:23:28.099943: step: 616/533, loss: 0.2619171142578125
2023-01-23 00:23:29.293341: step: 620/533, loss: 0.26793354749679565
2023-01-23 00:23:30.446831: step: 624/533, loss: 0.15851421654224396
2023-01-23 00:23:31.623785: step: 628/533, loss: 0.14425459504127502
2023-01-23 00:23:32.829380: step: 632/533, loss: 0.5166572332382202
2023-01-23 00:23:34.063604: step: 636/533, loss: 0.05711860582232475
2023-01-23 00:23:35.205837: step: 640/533, loss: 0.9694008231163025
2023-01-23 00:23:36.339909: step: 644/533, loss: 0.10738392174243927
2023-01-23 00:23:37.493483: step: 648/533, loss: 0.027312662452459335
2023-01-23 00:23:38.688808: step: 652/533, loss: 0.1380002498626709
2023-01-23 00:23:39.874679: step: 656/533, loss: 0.0690101608633995
2023-01-23 00:23:41.074643: step: 660/533, loss: 0.04692526161670685
2023-01-23 00:23:42.233566: step: 664/533, loss: 0.36581698060035706
2023-01-23 00:23:43.364929: step: 668/533, loss: 0.05739751085639
2023-01-23 00:23:44.537571: step: 672/533, loss: 0.16228342056274414
2023-01-23 00:23:45.695467: step: 676/533, loss: 0.12853717803955078
2023-01-23 00:23:46.872412: step: 680/533, loss: 0.35547828674316406
2023-01-23 00:23:48.069987: step: 684/533, loss: 0.370439350605011
2023-01-23 00:23:49.252870: step: 688/533, loss: 0.04332399368286133
2023-01-23 00:23:50.389067: step: 692/533, loss: 0.17293567955493927
2023-01-23 00:23:51.551488: step: 696/533, loss: 0.349107563495636
2023-01-23 00:23:52.706162: step: 700/533, loss: 0.3088824450969696
2023-01-23 00:23:53.926180: step: 704/533, loss: 0.06935205310583115
2023-01-23 00:23:55.084639: step: 708/533, loss: 0.0868774950504303
2023-01-23 00:23:56.262862: step: 712/533, loss: 0.5752468705177307
2023-01-23 00:23:57.428573: step: 716/533, loss: 0.10252895951271057
2023-01-23 00:23:58.617117: step: 720/533, loss: 0.966886043548584
2023-01-23 00:23:59.811554: step: 724/533, loss: 0.14027100801467896
2023-01-23 00:24:00.972334: step: 728/533, loss: 0.0520419105887413
2023-01-23 00:24:02.154769: step: 732/533, loss: 0.07258539646863937
2023-01-23 00:24:03.319605: step: 736/533, loss: 0.37988173961639404
2023-01-23 00:24:04.496474: step: 740/533, loss: 0.03662538528442383
2023-01-23 00:24:05.694289: step: 744/533, loss: 0.04324188083410263
2023-01-23 00:24:06.881874: step: 748/533, loss: 0.3613608777523041
2023-01-23 00:24:08.027677: step: 752/533, loss: 0.12816905975341797
2023-01-23 00:24:09.223856: step: 756/533, loss: 0.0955532118678093
2023-01-23 00:24:10.451361: step: 760/533, loss: 0.06491170078516006
2023-01-23 00:24:11.631930: step: 764/533, loss: 0.2155565321445465
2023-01-23 00:24:12.842403: step: 768/533, loss: 0.17227935791015625
2023-01-23 00:24:13.995319: step: 772/533, loss: 0.17179450392723083
2023-01-23 00:24:15.168025: step: 776/533, loss: 0.27961111068725586
2023-01-23 00:24:16.352524: step: 780/533, loss: 0.16273269057273865
2023-01-23 00:24:17.510244: step: 784/533, loss: 0.11638174206018448
2023-01-23 00:24:18.706235: step: 788/533, loss: 0.0422457717359066
2023-01-23 00:24:19.898579: step: 792/533, loss: 0.2984282374382019
2023-01-23 00:24:21.068864: step: 796/533, loss: 1.4745967388153076
2023-01-23 00:24:22.232813: step: 800/533, loss: 0.22456084191799164
2023-01-23 00:24:23.410736: step: 804/533, loss: 0.07785816490650177
2023-01-23 00:24:24.632351: step: 808/533, loss: 0.14456290006637573
2023-01-23 00:24:25.813406: step: 812/533, loss: 0.10354909300804138
2023-01-23 00:24:26.955028: step: 816/533, loss: 0.04806175455451012
2023-01-23 00:24:28.117941: step: 820/533, loss: 0.1270865499973297
2023-01-23 00:24:29.294239: step: 824/533, loss: 0.1418808102607727
2023-01-23 00:24:30.452014: step: 828/533, loss: 0.08975763618946075
2023-01-23 00:24:31.586950: step: 832/533, loss: 0.0381811149418354
2023-01-23 00:24:32.757463: step: 836/533, loss: 0.08536271750926971
2023-01-23 00:24:33.914607: step: 840/533, loss: 1.3843010663986206
2023-01-23 00:24:35.121088: step: 844/533, loss: 0.163020521402359
2023-01-23 00:24:36.278489: step: 848/533, loss: 0.04792146757245064
2023-01-23 00:24:37.428659: step: 852/533, loss: 0.08335190266370773
2023-01-23 00:24:38.597702: step: 856/533, loss: 0.14321881532669067
2023-01-23 00:24:39.747490: step: 860/533, loss: 0.11247396469116211
2023-01-23 00:24:40.951139: step: 864/533, loss: 0.08266621083021164
2023-01-23 00:24:42.111936: step: 868/533, loss: 0.19085007905960083
2023-01-23 00:24:43.254923: step: 872/533, loss: 0.18547268211841583
2023-01-23 00:24:44.445020: step: 876/533, loss: 0.2471088171005249
2023-01-23 00:24:45.617306: step: 880/533, loss: 0.24844466149806976
2023-01-23 00:24:46.837810: step: 884/533, loss: 0.6363113522529602
2023-01-23 00:24:48.005214: step: 888/533, loss: 0.21207237243652344
2023-01-23 00:24:49.221711: step: 892/533, loss: 0.50953608751297
2023-01-23 00:24:50.407020: step: 896/533, loss: 0.08926382660865784
2023-01-23 00:24:51.609579: step: 900/533, loss: 0.038840580731630325
2023-01-23 00:24:52.787914: step: 904/533, loss: 0.3272953927516937
2023-01-23 00:24:53.937773: step: 908/533, loss: 0.09617023915052414
2023-01-23 00:24:55.074522: step: 912/533, loss: 0.2607877254486084
2023-01-23 00:24:56.223326: step: 916/533, loss: 0.0365811362862587
2023-01-23 00:24:57.393350: step: 920/533, loss: 0.09311385452747345
2023-01-23 00:24:58.615341: step: 924/533, loss: 0.24119792878627777
2023-01-23 00:24:59.815790: step: 928/533, loss: 0.3606806993484497
2023-01-23 00:25:00.980045: step: 932/533, loss: 0.656897246837616
2023-01-23 00:25:02.160368: step: 936/533, loss: 0.0672733336687088
2023-01-23 00:25:03.314506: step: 940/533, loss: 0.05885028839111328
2023-01-23 00:25:04.496063: step: 944/533, loss: 0.03974022716283798
2023-01-23 00:25:05.672556: step: 948/533, loss: 0.24166402220726013
2023-01-23 00:25:06.836680: step: 952/533, loss: 0.36412110924720764
2023-01-23 00:25:08.068559: step: 956/533, loss: 0.2218734323978424
2023-01-23 00:25:09.236916: step: 960/533, loss: 0.019949007779359818
2023-01-23 00:25:10.429141: step: 964/533, loss: 0.2599373757839203
2023-01-23 00:25:11.616633: step: 968/533, loss: 0.21649064123630524
2023-01-23 00:25:12.796143: step: 972/533, loss: 0.6959112882614136
2023-01-23 00:25:14.043275: step: 976/533, loss: 1.9110101461410522
2023-01-23 00:25:15.211566: step: 980/533, loss: 0.060066986829042435
2023-01-23 00:25:16.424719: step: 984/533, loss: 0.10456404834985733
2023-01-23 00:25:17.605839: step: 988/533, loss: 0.09126629680395126
2023-01-23 00:25:18.776628: step: 992/533, loss: 0.8815129399299622
2023-01-23 00:25:19.939135: step: 996/533, loss: 0.18886065483093262
2023-01-23 00:25:21.141569: step: 1000/533, loss: 0.30123645067214966
2023-01-23 00:25:22.304817: step: 1004/533, loss: 0.0677306205034256
2023-01-23 00:25:23.479499: step: 1008/533, loss: 0.24569815397262573
2023-01-23 00:25:24.653467: step: 1012/533, loss: 0.04990663379430771
2023-01-23 00:25:25.826889: step: 1016/533, loss: 0.06525164097547531
2023-01-23 00:25:27.011367: step: 1020/533, loss: 0.525295615196228
2023-01-23 00:25:28.145348: step: 1024/533, loss: 0.02988424338400364
2023-01-23 00:25:29.370024: step: 1028/533, loss: 0.021146394312381744
2023-01-23 00:25:30.533739: step: 1032/533, loss: 0.23003879189491272
2023-01-23 00:25:31.731324: step: 1036/533, loss: 0.2026832103729248
2023-01-23 00:25:32.898330: step: 1040/533, loss: 0.0364932045340538
2023-01-23 00:25:34.073437: step: 1044/533, loss: 0.30065423250198364
2023-01-23 00:25:35.224972: step: 1048/533, loss: 0.035550735890865326
2023-01-23 00:25:36.392252: step: 1052/533, loss: 0.06179413944482803
2023-01-23 00:25:37.578073: step: 1056/533, loss: 0.04478273540735245
2023-01-23 00:25:38.768987: step: 1060/533, loss: 0.5006459951400757
2023-01-23 00:25:39.951453: step: 1064/533, loss: 0.2556353211402893
2023-01-23 00:25:41.159453: step: 1068/533, loss: 0.22370100021362305
2023-01-23 00:25:42.352276: step: 1072/533, loss: 0.10955343395471573
2023-01-23 00:25:43.533811: step: 1076/533, loss: 0.2563779950141907
2023-01-23 00:25:44.733135: step: 1080/533, loss: 0.16635161638259888
2023-01-23 00:25:45.949545: step: 1084/533, loss: 0.08671098202466965
2023-01-23 00:25:47.121616: step: 1088/533, loss: 0.06804871559143066
2023-01-23 00:25:48.289919: step: 1092/533, loss: 0.5283897519111633
2023-01-23 00:25:49.484051: step: 1096/533, loss: 0.04945874214172363
2023-01-23 00:25:50.638797: step: 1100/533, loss: 0.10594506561756134
2023-01-23 00:25:51.872837: step: 1104/533, loss: 0.057581618428230286
2023-01-23 00:25:53.017893: step: 1108/533, loss: 0.3890157639980316
2023-01-23 00:25:54.210223: step: 1112/533, loss: 0.4649909436702728
2023-01-23 00:25:55.374746: step: 1116/533, loss: 0.43836021423339844
2023-01-23 00:25:56.552748: step: 1120/533, loss: 0.07939185947179794
2023-01-23 00:25:57.738474: step: 1124/533, loss: 0.11801280826330185
2023-01-23 00:25:58.932411: step: 1128/533, loss: 0.04644632339477539
2023-01-23 00:26:00.100086: step: 1132/533, loss: 0.27586880326271057
2023-01-23 00:26:01.289477: step: 1136/533, loss: 0.5773674845695496
2023-01-23 00:26:02.457155: step: 1140/533, loss: 0.09778346866369247
2023-01-23 00:26:03.671220: step: 1144/533, loss: 0.1590556651353836
2023-01-23 00:26:04.836471: step: 1148/533, loss: 0.19908609986305237
2023-01-23 00:26:06.033796: step: 1152/533, loss: 0.04899187386035919
2023-01-23 00:26:07.215633: step: 1156/533, loss: 0.41234758496284485
2023-01-23 00:26:08.365281: step: 1160/533, loss: 0.1556684970855713
2023-01-23 00:26:09.517055: step: 1164/533, loss: 1.1117031574249268
2023-01-23 00:26:10.693972: step: 1168/533, loss: 0.19716626405715942
2023-01-23 00:26:11.911700: step: 1172/533, loss: 0.0710611343383789
2023-01-23 00:26:13.096485: step: 1176/533, loss: 0.08309850841760635
2023-01-23 00:26:14.294465: step: 1180/533, loss: 0.32324203848838806
2023-01-23 00:26:15.495509: step: 1184/533, loss: 0.8226678967475891
2023-01-23 00:26:16.724631: step: 1188/533, loss: 0.4102906286716461
2023-01-23 00:26:17.912489: step: 1192/533, loss: 1.0576732158660889
2023-01-23 00:26:19.070289: step: 1196/533, loss: 0.14293083548545837
2023-01-23 00:26:20.266233: step: 1200/533, loss: 0.37836790084838867
2023-01-23 00:26:21.415465: step: 1204/533, loss: 0.1536066085100174
2023-01-23 00:26:22.549057: step: 1208/533, loss: 0.028438378125429153
2023-01-23 00:26:23.729463: step: 1212/533, loss: 0.331953763961792
2023-01-23 00:26:24.910134: step: 1216/533, loss: 0.14810489118099213
2023-01-23 00:26:26.108991: step: 1220/533, loss: 0.5138829946517944
2023-01-23 00:26:27.295118: step: 1224/533, loss: 0.1982186883687973
2023-01-23 00:26:28.468698: step: 1228/533, loss: 0.09420661628246307
2023-01-23 00:26:29.617427: step: 1232/533, loss: 0.24847650527954102
2023-01-23 00:26:30.786583: step: 1236/533, loss: 0.12884683907032013
2023-01-23 00:26:31.971350: step: 1240/533, loss: 0.18810588121414185
2023-01-23 00:26:33.140223: step: 1244/533, loss: 0.3753485679626465
2023-01-23 00:26:34.287077: step: 1248/533, loss: 0.9338828921318054
2023-01-23 00:26:35.470624: step: 1252/533, loss: 0.22380857169628143
2023-01-23 00:26:36.639020: step: 1256/533, loss: 0.6245174407958984
2023-01-23 00:26:37.816535: step: 1260/533, loss: 0.14597196877002716
2023-01-23 00:26:39.031840: step: 1264/533, loss: 0.36217156052589417
2023-01-23 00:26:40.207275: step: 1268/533, loss: 0.0613522082567215
2023-01-23 00:26:41.388598: step: 1272/533, loss: 0.09672181308269501
2023-01-23 00:26:42.567161: step: 1276/533, loss: 0.13940119743347168
2023-01-23 00:26:43.739485: step: 1280/533, loss: 0.09196672588586807
2023-01-23 00:26:44.910700: step: 1284/533, loss: 0.16214370727539062
2023-01-23 00:26:46.086110: step: 1288/533, loss: 0.18966837227344513
2023-01-23 00:26:47.294936: step: 1292/533, loss: 0.12006721645593643
2023-01-23 00:26:48.508401: step: 1296/533, loss: 0.0970979705452919
2023-01-23 00:26:49.723791: step: 1300/533, loss: 0.1135433167219162
2023-01-23 00:26:50.888758: step: 1304/533, loss: 0.029100514948368073
2023-01-23 00:26:52.076753: step: 1308/533, loss: 0.14718112349510193
2023-01-23 00:26:53.270568: step: 1312/533, loss: 1.097081184387207
2023-01-23 00:26:54.468239: step: 1316/533, loss: 0.40221983194351196
2023-01-23 00:26:55.664460: step: 1320/533, loss: 0.04940800741314888
2023-01-23 00:26:56.857462: step: 1324/533, loss: 0.6038603782653809
2023-01-23 00:26:58.000615: step: 1328/533, loss: 0.7928571701049805
2023-01-23 00:26:59.162988: step: 1332/533, loss: 0.10265494138002396
2023-01-23 00:27:00.327808: step: 1336/533, loss: 0.21025848388671875
2023-01-23 00:27:01.502527: step: 1340/533, loss: 0.41907915472984314
2023-01-23 00:27:02.688805: step: 1344/533, loss: 0.12884274125099182
2023-01-23 00:27:03.839033: step: 1348/533, loss: 0.17052879929542542
2023-01-23 00:27:05.059357: step: 1352/533, loss: 0.0990772470831871
2023-01-23 00:27:06.234172: step: 1356/533, loss: 0.06579726934432983
2023-01-23 00:27:07.421193: step: 1360/533, loss: 0.03973455727100372
2023-01-23 00:27:08.613460: step: 1364/533, loss: 0.09333725273609161
2023-01-23 00:27:09.790915: step: 1368/533, loss: 0.17254649102687836
2023-01-23 00:27:10.963701: step: 1372/533, loss: 0.2807408571243286
2023-01-23 00:27:12.106365: step: 1376/533, loss: 0.19102182984352112
2023-01-23 00:27:13.267935: step: 1380/533, loss: 0.9477138519287109
2023-01-23 00:27:14.505063: step: 1384/533, loss: 0.16673335433006287
2023-01-23 00:27:15.659496: step: 1388/533, loss: 0.5129029750823975
2023-01-23 00:27:16.864772: step: 1392/533, loss: 0.4011189043521881
2023-01-23 00:27:18.011095: step: 1396/533, loss: 0.05289926752448082
2023-01-23 00:27:19.247434: step: 1400/533, loss: 0.25938501954078674
2023-01-23 00:27:20.421421: step: 1404/533, loss: 0.13770073652267456
2023-01-23 00:27:21.599585: step: 1408/533, loss: 0.06882219016551971
2023-01-23 00:27:22.781748: step: 1412/533, loss: 0.38377562165260315
2023-01-23 00:27:23.948092: step: 1416/533, loss: 0.06996621936559677
2023-01-23 00:27:25.153776: step: 1420/533, loss: 0.14846988022327423
2023-01-23 00:27:26.318943: step: 1424/533, loss: 0.08452146500349045
2023-01-23 00:27:27.481171: step: 1428/533, loss: 0.6743655204772949
2023-01-23 00:27:28.645745: step: 1432/533, loss: 0.06838846206665039
2023-01-23 00:27:29.811872: step: 1436/533, loss: 0.691069483757019
2023-01-23 00:27:31.005077: step: 1440/533, loss: 0.09301143139600754
2023-01-23 00:27:32.207730: step: 1444/533, loss: 0.1438518613576889
2023-01-23 00:27:33.383328: step: 1448/533, loss: 0.04686949402093887
2023-01-23 00:27:34.604178: step: 1452/533, loss: 0.05652890354394913
2023-01-23 00:27:35.815667: step: 1456/533, loss: 0.10818997025489807
2023-01-23 00:27:36.976947: step: 1460/533, loss: 0.014242172241210938
2023-01-23 00:27:38.138008: step: 1464/533, loss: 0.043192245066165924
2023-01-23 00:27:39.307781: step: 1468/533, loss: 0.5309242010116577
2023-01-23 00:27:40.492130: step: 1472/533, loss: 0.457075297832489
2023-01-23 00:27:41.655035: step: 1476/533, loss: 0.1744905561208725
2023-01-23 00:27:42.836744: step: 1480/533, loss: 0.6160749793052673
2023-01-23 00:27:44.000410: step: 1484/533, loss: 0.24872151017189026
2023-01-23 00:27:45.190775: step: 1488/533, loss: 0.024968530982732773
2023-01-23 00:27:46.356830: step: 1492/533, loss: 0.14192934334278107
2023-01-23 00:27:47.567202: step: 1496/533, loss: 0.13072550296783447
2023-01-23 00:27:48.734753: step: 1500/533, loss: 1.138831615447998
2023-01-23 00:27:49.915623: step: 1504/533, loss: 0.2735590636730194
2023-01-23 00:27:51.066021: step: 1508/533, loss: 3.957540512084961
2023-01-23 00:27:52.215991: step: 1512/533, loss: 0.5816661715507507
2023-01-23 00:27:53.422025: step: 1516/533, loss: 0.023665238171815872
2023-01-23 00:27:54.570339: step: 1520/533, loss: 0.17918796837329865
2023-01-23 00:27:55.747277: step: 1524/533, loss: 0.3125152587890625
2023-01-23 00:27:57.004157: step: 1528/533, loss: 0.1004018783569336
2023-01-23 00:27:58.207293: step: 1532/533, loss: 0.3702074885368347
2023-01-23 00:27:59.393523: step: 1536/533, loss: 0.33720093965530396
2023-01-23 00:28:00.575709: step: 1540/533, loss: 0.05317385122179985
2023-01-23 00:28:01.719554: step: 1544/533, loss: 0.0034165619872510433
2023-01-23 00:28:02.868356: step: 1548/533, loss: 0.2887263298034668
2023-01-23 00:28:04.064432: step: 1552/533, loss: 0.057515766471624374
2023-01-23 00:28:05.238177: step: 1556/533, loss: 0.08571477234363556
2023-01-23 00:28:06.405677: step: 1560/533, loss: 0.2643674910068512
2023-01-23 00:28:07.617527: step: 1564/533, loss: 0.17403718829154968
2023-01-23 00:28:08.767980: step: 1568/533, loss: 0.1666909158229828
2023-01-23 00:28:09.936818: step: 1572/533, loss: 0.032784365117549896
2023-01-23 00:28:11.130343: step: 1576/533, loss: 0.2608538269996643
2023-01-23 00:28:12.297641: step: 1580/533, loss: 0.12190522998571396
2023-01-23 00:28:13.487797: step: 1584/533, loss: 0.029227543622255325
2023-01-23 00:28:14.667948: step: 1588/533, loss: 1.949853539466858
2023-01-23 00:28:15.820181: step: 1592/533, loss: 0.7524545788764954
2023-01-23 00:28:17.011359: step: 1596/533, loss: 0.25709474086761475
2023-01-23 00:28:18.135428: step: 1600/533, loss: 0.03538703918457031
2023-01-23 00:28:19.336816: step: 1604/533, loss: 1.2393126487731934
2023-01-23 00:28:20.487071: step: 1608/533, loss: 0.061524104326963425
2023-01-23 00:28:21.650396: step: 1612/533, loss: 0.05912356823682785
2023-01-23 00:28:22.808783: step: 1616/533, loss: 0.525540828704834
2023-01-23 00:28:23.985090: step: 1620/533, loss: 0.3413012623786926
2023-01-23 00:28:25.206894: step: 1624/533, loss: 0.14334268867969513
2023-01-23 00:28:26.429899: step: 1628/533, loss: 0.18554410338401794
2023-01-23 00:28:27.645951: step: 1632/533, loss: 0.08620801568031311
2023-01-23 00:28:28.814402: step: 1636/533, loss: 0.2511632442474365
2023-01-23 00:28:30.007957: step: 1640/533, loss: 0.21081668138504028
2023-01-23 00:28:31.199150: step: 1644/533, loss: 0.4084090292453766
2023-01-23 00:28:32.384585: step: 1648/533, loss: 0.04076967388391495
2023-01-23 00:28:33.556852: step: 1652/533, loss: 0.057720281183719635
2023-01-23 00:28:34.735735: step: 1656/533, loss: 0.07515545189380646
2023-01-23 00:28:35.922796: step: 1660/533, loss: 0.7464092373847961
2023-01-23 00:28:37.095767: step: 1664/533, loss: 0.06995511054992676
2023-01-23 00:28:38.318805: step: 1668/533, loss: 0.8005859851837158
2023-01-23 00:28:39.515301: step: 1672/533, loss: 0.05395703762769699
2023-01-23 00:28:40.704522: step: 1676/533, loss: 0.13379746675491333
2023-01-23 00:28:41.891280: step: 1680/533, loss: 0.205827996134758
2023-01-23 00:28:43.067253: step: 1684/533, loss: 0.05636405944824219
2023-01-23 00:28:44.215198: step: 1688/533, loss: 0.2690616846084595
2023-01-23 00:28:45.397358: step: 1692/533, loss: 0.4825805723667145
2023-01-23 00:28:46.584061: step: 1696/533, loss: 0.1953682005405426
2023-01-23 00:28:47.746183: step: 1700/533, loss: 0.029216576367616653
2023-01-23 00:28:48.985162: step: 1704/533, loss: 0.15461483597755432
2023-01-23 00:28:50.204753: step: 1708/533, loss: 0.7828990817070007
2023-01-23 00:28:51.370543: step: 1712/533, loss: 0.10142626613378525
2023-01-23 00:28:52.586889: step: 1716/533, loss: 0.05300397798418999
2023-01-23 00:28:53.718362: step: 1720/533, loss: 0.6581972241401672
2023-01-23 00:28:54.925683: step: 1724/533, loss: 0.09413953125476837
2023-01-23 00:28:56.093633: step: 1728/533, loss: 0.07101168483495712
2023-01-23 00:28:57.285446: step: 1732/533, loss: 0.2001507729291916
2023-01-23 00:28:58.468682: step: 1736/533, loss: 0.24617183208465576
2023-01-23 00:28:59.647872: step: 1740/533, loss: 0.09033975750207901
2023-01-23 00:29:00.780882: step: 1744/533, loss: 0.20538422465324402
2023-01-23 00:29:01.966005: step: 1748/533, loss: 0.1850377917289734
2023-01-23 00:29:03.234207: step: 1752/533, loss: 0.25849050283432007
2023-01-23 00:29:04.407395: step: 1756/533, loss: 0.22616156935691833
2023-01-23 00:29:05.563091: step: 1760/533, loss: 0.11476631462574005
2023-01-23 00:29:06.776992: step: 1764/533, loss: 0.1577913761138916
2023-01-23 00:29:07.939010: step: 1768/533, loss: 0.14762765169143677
2023-01-23 00:29:09.122853: step: 1772/533, loss: 0.040448904037475586
2023-01-23 00:29:10.335967: step: 1776/533, loss: 0.12067694962024689
2023-01-23 00:29:11.493155: step: 1780/533, loss: 0.0686771422624588
2023-01-23 00:29:12.690882: step: 1784/533, loss: 0.11080141365528107
2023-01-23 00:29:13.921485: step: 1788/533, loss: 0.05756950378417969
2023-01-23 00:29:15.129147: step: 1792/533, loss: 0.4624618887901306
2023-01-23 00:29:16.352151: step: 1796/533, loss: 0.12290406227111816
2023-01-23 00:29:17.532869: step: 1800/533, loss: 0.16624422371387482
2023-01-23 00:29:18.681884: step: 1804/533, loss: 0.2789624333381653
2023-01-23 00:29:19.846090: step: 1808/533, loss: 0.0747896283864975
2023-01-23 00:29:21.034996: step: 1812/533, loss: 0.3055858016014099
2023-01-23 00:29:22.220753: step: 1816/533, loss: 0.26524078845977783
2023-01-23 00:29:23.359669: step: 1820/533, loss: 0.06191863864660263
2023-01-23 00:29:24.557571: step: 1824/533, loss: 0.12996242940425873
2023-01-23 00:29:25.725030: step: 1828/533, loss: 0.34519368410110474
2023-01-23 00:29:26.912064: step: 1832/533, loss: 0.42146873474121094
2023-01-23 00:29:28.083027: step: 1836/533, loss: 0.03204717859625816
2023-01-23 00:29:29.299549: step: 1840/533, loss: 0.06813183426856995
2023-01-23 00:29:30.499072: step: 1844/533, loss: 0.9512029886245728
2023-01-23 00:29:31.686579: step: 1848/533, loss: 0.05611982196569443
2023-01-23 00:29:32.891734: step: 1852/533, loss: 0.14940910041332245
2023-01-23 00:29:34.083737: step: 1856/533, loss: 0.08887653052806854
2023-01-23 00:29:35.279074: step: 1860/533, loss: 0.01161956787109375
2023-01-23 00:29:36.488338: step: 1864/533, loss: 0.1938934326171875
2023-01-23 00:29:37.642255: step: 1868/533, loss: 0.1492149382829666
2023-01-23 00:29:38.815432: step: 1872/533, loss: 0.26267844438552856
2023-01-23 00:29:40.037426: step: 1876/533, loss: 0.12772627174854279
2023-01-23 00:29:41.225686: step: 1880/533, loss: 0.09009389579296112
2023-01-23 00:29:42.406554: step: 1884/533, loss: 0.34288281202316284
2023-01-23 00:29:43.587669: step: 1888/533, loss: 0.10200528800487518
2023-01-23 00:29:44.779766: step: 1892/533, loss: 0.49737465381622314
2023-01-23 00:29:45.912493: step: 1896/533, loss: 0.1520950347185135
2023-01-23 00:29:47.092340: step: 1900/533, loss: 0.21713094413280487
2023-01-23 00:29:48.232926: step: 1904/533, loss: 0.48465415835380554
2023-01-23 00:29:49.401133: step: 1908/533, loss: 0.13304853439331055
2023-01-23 00:29:50.557104: step: 1912/533, loss: 2.005528211593628
2023-01-23 00:29:51.732751: step: 1916/533, loss: 0.5247257351875305
2023-01-23 00:29:52.886107: step: 1920/533, loss: 0.1867447793483734
2023-01-23 00:29:54.058656: step: 1924/533, loss: 0.10536666214466095
2023-01-23 00:29:55.231934: step: 1928/533, loss: 0.6730639338493347
2023-01-23 00:29:56.392092: step: 1932/533, loss: 0.9028729200363159
2023-01-23 00:29:57.560539: step: 1936/533, loss: 2.4237864017486572
2023-01-23 00:29:58.749889: step: 1940/533, loss: 0.2181251496076584
2023-01-23 00:29:59.879921: step: 1944/533, loss: 0.03633255884051323
2023-01-23 00:30:01.041308: step: 1948/533, loss: 0.4216315448284149
2023-01-23 00:30:02.222958: step: 1952/533, loss: 0.026334190741181374
2023-01-23 00:30:03.422351: step: 1956/533, loss: 0.07945594936609268
2023-01-23 00:30:04.597307: step: 1960/533, loss: 0.12200164794921875
2023-01-23 00:30:05.768377: step: 1964/533, loss: 0.03914046287536621
2023-01-23 00:30:06.990405: step: 1968/533, loss: 0.053531549870967865
2023-01-23 00:30:08.173995: step: 1972/533, loss: 0.1782490313053131
2023-01-23 00:30:09.334029: step: 1976/533, loss: 0.0967465415596962
2023-01-23 00:30:10.540723: step: 1980/533, loss: 0.0998849868774414
2023-01-23 00:30:11.724690: step: 1984/533, loss: 0.1548910140991211
2023-01-23 00:30:12.895792: step: 1988/533, loss: 0.11932344734668732
2023-01-23 00:30:14.021331: step: 1992/533, loss: 0.2317657470703125
2023-01-23 00:30:15.217715: step: 1996/533, loss: 0.13084612786769867
2023-01-23 00:30:16.370635: step: 2000/533, loss: 0.2056548297405243
2023-01-23 00:30:17.507615: step: 2004/533, loss: 0.2298460453748703
2023-01-23 00:30:18.699107: step: 2008/533, loss: 0.12498773634433746
2023-01-23 00:30:19.875918: step: 2012/533, loss: 0.17964085936546326
2023-01-23 00:30:21.022721: step: 2016/533, loss: 0.2789931297302246
2023-01-23 00:30:22.175752: step: 2020/533, loss: 0.08965711295604706
2023-01-23 00:30:23.357456: step: 2024/533, loss: 0.17179150879383087
2023-01-23 00:30:24.542958: step: 2028/533, loss: 0.09418530762195587
2023-01-23 00:30:25.726072: step: 2032/533, loss: 0.16949692368507385
2023-01-23 00:30:26.928915: step: 2036/533, loss: 0.08645877987146378
2023-01-23 00:30:28.095015: step: 2040/533, loss: 0.0520998015999794
2023-01-23 00:30:29.263521: step: 2044/533, loss: 0.23317575454711914
2023-01-23 00:30:30.510128: step: 2048/533, loss: 0.14852294325828552
2023-01-23 00:30:31.677074: step: 2052/533, loss: 0.13098320364952087
2023-01-23 00:30:32.810813: step: 2056/533, loss: 0.03686361387372017
2023-01-23 00:30:34.022675: step: 2060/533, loss: 0.1774548590183258
2023-01-23 00:30:35.148310: step: 2064/533, loss: 0.12040863186120987
2023-01-23 00:30:36.414775: step: 2068/533, loss: 0.023991085588932037
2023-01-23 00:30:37.584290: step: 2072/533, loss: 0.26984015107154846
2023-01-23 00:30:38.745891: step: 2076/533, loss: 1.1108540296554565
2023-01-23 00:30:39.896884: step: 2080/533, loss: 0.05016741901636124
2023-01-23 00:30:41.087972: step: 2084/533, loss: 0.304918110370636
2023-01-23 00:30:42.272055: step: 2088/533, loss: 0.21580210328102112
2023-01-23 00:30:43.451032: step: 2092/533, loss: 0.28309839963912964
2023-01-23 00:30:44.621554: step: 2096/533, loss: 0.09128522872924805
2023-01-23 00:30:45.808662: step: 2100/533, loss: 0.09254761040210724
2023-01-23 00:30:46.940453: step: 2104/533, loss: 0.1728985756635666
2023-01-23 00:30:48.102220: step: 2108/533, loss: 0.028179071843624115
2023-01-23 00:30:49.298663: step: 2112/533, loss: 0.0651882141828537
2023-01-23 00:30:50.481823: step: 2116/533, loss: 0.5313538312911987
2023-01-23 00:30:51.715254: step: 2120/533, loss: 0.6243495941162109
2023-01-23 00:30:52.864412: step: 2124/533, loss: 0.23429462313652039
2023-01-23 00:30:54.013379: step: 2128/533, loss: 0.12990951538085938
2023-01-23 00:30:55.153021: step: 2132/533, loss: 0.15905046463012695
==================================================
Loss: 0.279
--------------------
Dev: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.6444444444444445, 'r': 0.4603174603174603, 'f1': 0.537037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 6
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:31:41.823367: step: 4/533, loss: 0.1402624249458313
2023-01-23 00:31:42.993297: step: 8/533, loss: 0.04164600372314453
2023-01-23 00:31:44.157750: step: 12/533, loss: 0.1231774389743805
2023-01-23 00:31:45.343897: step: 16/533, loss: 0.022655677050352097
2023-01-23 00:31:46.521404: step: 20/533, loss: 0.11645087599754333
2023-01-23 00:31:47.686961: step: 24/533, loss: 0.23251761496067047
2023-01-23 00:31:48.849234: step: 28/533, loss: 0.12609200179576874
2023-01-23 00:31:50.024800: step: 32/533, loss: 0.036342814564704895
2023-01-23 00:31:51.172486: step: 36/533, loss: 0.07379398494958878
2023-01-23 00:31:52.337126: step: 40/533, loss: 0.16314354538917542
2023-01-23 00:31:53.529757: step: 44/533, loss: 0.09132575988769531
2023-01-23 00:31:54.703050: step: 48/533, loss: 0.14595623314380646
2023-01-23 00:31:55.878037: step: 52/533, loss: 0.10838431864976883
2023-01-23 00:31:57.076048: step: 56/533, loss: 0.05974111706018448
2023-01-23 00:31:58.245094: step: 60/533, loss: 0.096981480717659
2023-01-23 00:31:59.399791: step: 64/533, loss: 0.09481563419103622
2023-01-23 00:32:00.584997: step: 68/533, loss: 0.14430314302444458
2023-01-23 00:32:01.780590: step: 72/533, loss: 0.10095834732055664
2023-01-23 00:32:02.985740: step: 76/533, loss: 0.11170845478773117
2023-01-23 00:32:04.160416: step: 80/533, loss: 0.23635263741016388
2023-01-23 00:32:05.342253: step: 84/533, loss: 0.0709206610918045
2023-01-23 00:32:06.520291: step: 88/533, loss: 0.40613335371017456
2023-01-23 00:32:07.726463: step: 92/533, loss: 0.0773090347647667
2023-01-23 00:32:08.883179: step: 96/533, loss: 0.044652268290519714
2023-01-23 00:32:10.056465: step: 100/533, loss: 0.13224896788597107
2023-01-23 00:32:11.233535: step: 104/533, loss: 0.16517484188079834
2023-01-23 00:32:12.432024: step: 108/533, loss: 0.17807331681251526
2023-01-23 00:32:13.627825: step: 112/533, loss: 0.10436401516199112
2023-01-23 00:32:14.838784: step: 116/533, loss: 0.18117032945156097
2023-01-23 00:32:16.002057: step: 120/533, loss: 0.145610511302948
2023-01-23 00:32:17.199745: step: 124/533, loss: 0.2857432961463928
2023-01-23 00:32:18.371330: step: 128/533, loss: 0.23638640344142914
2023-01-23 00:32:19.527274: step: 132/533, loss: 0.05786857753992081
2023-01-23 00:32:20.690862: step: 136/533, loss: 0.08663368225097656
2023-01-23 00:32:21.837958: step: 140/533, loss: 0.03582906723022461
2023-01-23 00:32:22.997195: step: 144/533, loss: 0.11095075309276581
2023-01-23 00:32:24.158403: step: 148/533, loss: 0.3409159481525421
2023-01-23 00:32:25.321666: step: 152/533, loss: 0.07475566864013672
2023-01-23 00:32:26.536636: step: 156/533, loss: 0.6491065621376038
2023-01-23 00:32:27.741193: step: 160/533, loss: 0.13936004042625427
2023-01-23 00:32:28.963811: step: 164/533, loss: 0.16715583205223083
2023-01-23 00:32:30.184851: step: 168/533, loss: 0.04724021255970001
2023-01-23 00:32:31.381789: step: 172/533, loss: 0.04715633764863014
2023-01-23 00:32:32.572891: step: 176/533, loss: 0.11720866709947586
2023-01-23 00:32:33.735632: step: 180/533, loss: 0.098785400390625
2023-01-23 00:32:34.890410: step: 184/533, loss: 0.13359108567237854
2023-01-23 00:32:36.070697: step: 188/533, loss: 0.34552955627441406
2023-01-23 00:32:37.266794: step: 192/533, loss: 0.4464438259601593
2023-01-23 00:32:38.487311: step: 196/533, loss: 0.08923645317554474
2023-01-23 00:32:39.650680: step: 200/533, loss: 0.31227704882621765
2023-01-23 00:32:40.841976: step: 204/533, loss: 0.26824918389320374
2023-01-23 00:32:42.040709: step: 208/533, loss: 0.020005034282803535
2023-01-23 00:32:43.196162: step: 212/533, loss: 0.1812088042497635
2023-01-23 00:32:44.369823: step: 216/533, loss: 0.039708614349365234
2023-01-23 00:32:45.556123: step: 220/533, loss: 0.4655044376850128
2023-01-23 00:32:46.727659: step: 224/533, loss: 1.5419625043869019
2023-01-23 00:32:47.931989: step: 228/533, loss: 0.15453405678272247
2023-01-23 00:32:49.198978: step: 232/533, loss: 0.2798457145690918
2023-01-23 00:32:50.373202: step: 236/533, loss: 0.015505028888583183
2023-01-23 00:32:51.644781: step: 240/533, loss: 0.11501885205507278
2023-01-23 00:32:52.799608: step: 244/533, loss: 0.2427239716053009
2023-01-23 00:32:53.974082: step: 248/533, loss: 0.20234784483909607
2023-01-23 00:32:55.152444: step: 252/533, loss: 0.2615823745727539
2023-01-23 00:32:56.310180: step: 256/533, loss: 0.09938888251781464
2023-01-23 00:32:57.464320: step: 260/533, loss: 0.13757282495498657
2023-01-23 00:32:58.641407: step: 264/533, loss: 0.16167640686035156
2023-01-23 00:32:59.874645: step: 268/533, loss: 0.2587317228317261
2023-01-23 00:33:01.042347: step: 272/533, loss: 0.24378043413162231
2023-01-23 00:33:02.224036: step: 276/533, loss: 0.05969972535967827
2023-01-23 00:33:03.388404: step: 280/533, loss: 0.15841493010520935
2023-01-23 00:33:04.561852: step: 284/533, loss: 0.312185138463974
2023-01-23 00:33:05.739466: step: 288/533, loss: 0.4866515100002289
2023-01-23 00:33:06.961886: step: 292/533, loss: 0.01793675497174263
2023-01-23 00:33:08.127404: step: 296/533, loss: 0.12395727634429932
2023-01-23 00:33:09.269532: step: 300/533, loss: 0.024558259174227715
2023-01-23 00:33:10.463006: step: 304/533, loss: 0.11003799736499786
2023-01-23 00:33:11.629178: step: 308/533, loss: 0.05248909071087837
2023-01-23 00:33:12.811597: step: 312/533, loss: 0.19564762711524963
2023-01-23 00:33:14.003157: step: 316/533, loss: 0.03859877586364746
2023-01-23 00:33:15.196053: step: 320/533, loss: 0.032102394849061966
2023-01-23 00:33:16.338233: step: 324/533, loss: 0.030251741409301758
2023-01-23 00:33:17.549513: step: 328/533, loss: 1.7634994983673096
2023-01-23 00:33:18.750180: step: 332/533, loss: 0.06786461174488068
2023-01-23 00:33:19.947784: step: 336/533, loss: 0.13286533951759338
2023-01-23 00:33:21.144157: step: 340/533, loss: 1.558632493019104
2023-01-23 00:33:22.311476: step: 344/533, loss: 0.10671892017126083
2023-01-23 00:33:23.482740: step: 348/533, loss: 0.12205901741981506
2023-01-23 00:33:24.661404: step: 352/533, loss: 0.0779503807425499
2023-01-23 00:33:25.842242: step: 356/533, loss: 0.02380542829632759
2023-01-23 00:33:27.038950: step: 360/533, loss: 0.1602693498134613
2023-01-23 00:33:28.168933: step: 364/533, loss: 0.9128307104110718
2023-01-23 00:33:29.336870: step: 368/533, loss: 0.1600487232208252
2023-01-23 00:33:30.505725: step: 372/533, loss: 0.39343318343162537
2023-01-23 00:33:31.696006: step: 376/533, loss: 0.1305026113986969
2023-01-23 00:33:32.917003: step: 380/533, loss: 0.0362975150346756
2023-01-23 00:33:34.116652: step: 384/533, loss: 0.7242580056190491
2023-01-23 00:33:35.276107: step: 388/533, loss: 0.04973917454481125
2023-01-23 00:33:36.449133: step: 392/533, loss: 0.20595207810401917
2023-01-23 00:33:37.627614: step: 396/533, loss: 0.048276614397764206
2023-01-23 00:33:38.798272: step: 400/533, loss: 0.8103103637695312
2023-01-23 00:33:39.980582: step: 404/533, loss: 0.8164023160934448
2023-01-23 00:33:41.167818: step: 408/533, loss: 0.4811538755893707
2023-01-23 00:33:42.352224: step: 412/533, loss: 0.19216632843017578
2023-01-23 00:33:43.518380: step: 416/533, loss: 0.19023312628269196
2023-01-23 00:33:44.671721: step: 420/533, loss: 0.9657771587371826
2023-01-23 00:33:45.828798: step: 424/533, loss: 0.09076862037181854
2023-01-23 00:33:47.012475: step: 428/533, loss: 0.1797008067369461
2023-01-23 00:33:48.164866: step: 432/533, loss: 0.0892309695482254
2023-01-23 00:33:49.328086: step: 436/533, loss: 0.06246676295995712
2023-01-23 00:33:50.488910: step: 440/533, loss: 0.13895034790039062
2023-01-23 00:33:51.639066: step: 444/533, loss: 0.19411660730838776
2023-01-23 00:33:52.832690: step: 448/533, loss: 0.10427618026733398
2023-01-23 00:33:53.997859: step: 452/533, loss: 0.15523472428321838
2023-01-23 00:33:55.178008: step: 456/533, loss: 0.07152634114027023
2023-01-23 00:33:56.342859: step: 460/533, loss: 0.18934230506420135
2023-01-23 00:33:57.496373: step: 464/533, loss: 0.3714737892150879
2023-01-23 00:33:58.681676: step: 468/533, loss: 0.08996625244617462
2023-01-23 00:33:59.828755: step: 472/533, loss: 0.062832310795784
2023-01-23 00:34:01.033995: step: 476/533, loss: 0.32677918672561646
2023-01-23 00:34:02.242753: step: 480/533, loss: 0.1360362470149994
2023-01-23 00:34:03.399965: step: 484/533, loss: 0.04621868580579758
2023-01-23 00:34:04.561690: step: 488/533, loss: 0.38293105363845825
2023-01-23 00:34:05.740988: step: 492/533, loss: 0.1301508992910385
2023-01-23 00:34:06.924390: step: 496/533, loss: 0.20964142680168152
2023-01-23 00:34:08.077176: step: 500/533, loss: 0.06040621176362038
2023-01-23 00:34:09.251310: step: 504/533, loss: 0.3040216565132141
2023-01-23 00:34:10.452902: step: 508/533, loss: 0.11116790771484375
2023-01-23 00:34:11.630522: step: 512/533, loss: 0.13114652037620544
2023-01-23 00:34:12.895776: step: 516/533, loss: 0.2801080346107483
2023-01-23 00:34:14.076818: step: 520/533, loss: 0.05532646179199219
2023-01-23 00:34:15.313589: step: 524/533, loss: 0.3578099012374878
2023-01-23 00:34:16.510996: step: 528/533, loss: 0.2572367787361145
2023-01-23 00:34:17.640435: step: 532/533, loss: 3.4118878841400146
2023-01-23 00:34:18.824412: step: 536/533, loss: 0.26610809564590454
2023-01-23 00:34:19.985593: step: 540/533, loss: 0.06443443894386292
2023-01-23 00:34:21.143777: step: 544/533, loss: 0.022541046142578125
2023-01-23 00:34:22.290815: step: 548/533, loss: 0.17633609473705292
2023-01-23 00:34:23.454049: step: 552/533, loss: 0.11661338806152344
2023-01-23 00:34:24.639950: step: 556/533, loss: 0.1085977554321289
2023-01-23 00:34:25.814408: step: 560/533, loss: 0.09120988845825195
2023-01-23 00:34:26.994981: step: 564/533, loss: 0.08338051289319992
2023-01-23 00:34:28.143640: step: 568/533, loss: 0.3780990540981293
2023-01-23 00:34:29.305105: step: 572/533, loss: 0.16336117684841156
2023-01-23 00:34:30.514253: step: 576/533, loss: 0.2157839834690094
2023-01-23 00:34:31.684871: step: 580/533, loss: 0.12675128877162933
2023-01-23 00:34:32.831825: step: 584/533, loss: 0.17588502168655396
2023-01-23 00:34:34.010560: step: 588/533, loss: 0.1416037678718567
2023-01-23 00:34:35.205229: step: 592/533, loss: 0.5350645780563354
2023-01-23 00:34:36.380468: step: 596/533, loss: 0.0289019588381052
2023-01-23 00:34:37.539052: step: 600/533, loss: 0.03147625923156738
2023-01-23 00:34:38.688960: step: 604/533, loss: 0.011325454339385033
2023-01-23 00:34:39.905937: step: 608/533, loss: 0.42858293652534485
2023-01-23 00:34:41.082932: step: 612/533, loss: 0.17268818616867065
2023-01-23 00:34:42.268654: step: 616/533, loss: 0.2072030007839203
2023-01-23 00:34:43.426584: step: 620/533, loss: 0.02739272080361843
2023-01-23 00:34:44.639918: step: 624/533, loss: 0.239209845662117
2023-01-23 00:34:45.815557: step: 628/533, loss: 0.157927468419075
2023-01-23 00:34:46.967087: step: 632/533, loss: 0.05565395578742027
2023-01-23 00:34:48.106349: step: 636/533, loss: 0.0764245018362999
2023-01-23 00:34:49.288296: step: 640/533, loss: 0.39503756165504456
2023-01-23 00:34:50.516831: step: 644/533, loss: 0.723455548286438
2023-01-23 00:34:51.687263: step: 648/533, loss: 0.05753688886761665
2023-01-23 00:34:52.854229: step: 652/533, loss: 0.03455867990851402
2023-01-23 00:34:54.055258: step: 656/533, loss: 0.20306864380836487
2023-01-23 00:34:55.262305: step: 660/533, loss: 0.12418485432863235
2023-01-23 00:34:56.437472: step: 664/533, loss: 0.15200595557689667
2023-01-23 00:34:57.604358: step: 668/533, loss: 0.05314607545733452
2023-01-23 00:34:58.783668: step: 672/533, loss: 0.16093826293945312
2023-01-23 00:34:59.958979: step: 676/533, loss: 0.012057686224579811
2023-01-23 00:35:01.132599: step: 680/533, loss: 0.061133477836847305
2023-01-23 00:35:02.323768: step: 684/533, loss: 0.08942899852991104
2023-01-23 00:35:03.501978: step: 688/533, loss: 0.05464329570531845
2023-01-23 00:35:04.641625: step: 692/533, loss: 0.2680133283138275
2023-01-23 00:35:05.813186: step: 696/533, loss: 0.0571599006652832
2023-01-23 00:35:06.959810: step: 700/533, loss: 0.9248478412628174
2023-01-23 00:35:08.132994: step: 704/533, loss: 0.03651714324951172
2023-01-23 00:35:09.322103: step: 708/533, loss: 0.11802182346582413
2023-01-23 00:35:10.472326: step: 712/533, loss: 0.30104243755340576
2023-01-23 00:35:11.681843: step: 716/533, loss: 0.03824158012866974
2023-01-23 00:35:12.828075: step: 720/533, loss: 0.0996273010969162
2023-01-23 00:35:14.012163: step: 724/533, loss: 0.5776216983795166
2023-01-23 00:35:15.153648: step: 728/533, loss: 0.08605937659740448
2023-01-23 00:35:16.339634: step: 732/533, loss: 0.08463068306446075
2023-01-23 00:35:17.519211: step: 736/533, loss: 0.04151606559753418
2023-01-23 00:35:18.694981: step: 740/533, loss: 0.1516055166721344
2023-01-23 00:35:19.907713: step: 744/533, loss: 0.114264115691185
2023-01-23 00:35:21.067869: step: 748/533, loss: 0.08029527962207794
2023-01-23 00:35:22.248460: step: 752/533, loss: 0.047203924506902695
2023-01-23 00:35:23.407869: step: 756/533, loss: 0.45689982175827026
2023-01-23 00:35:24.570982: step: 760/533, loss: 0.49262797832489014
2023-01-23 00:35:25.722821: step: 764/533, loss: 0.10497431457042694
2023-01-23 00:35:26.870077: step: 768/533, loss: 0.1463664174079895
2023-01-23 00:35:28.032971: step: 772/533, loss: 0.02423887327313423
2023-01-23 00:35:29.223724: step: 776/533, loss: 0.10864267498254776
2023-01-23 00:35:30.403758: step: 780/533, loss: 0.06768804043531418
2023-01-23 00:35:31.568744: step: 784/533, loss: 0.18495555222034454
2023-01-23 00:35:32.785536: step: 788/533, loss: 1.8760281801223755
2023-01-23 00:35:33.978019: step: 792/533, loss: 0.12130908668041229
2023-01-23 00:35:35.170027: step: 796/533, loss: 0.21055154502391815
2023-01-23 00:35:36.418369: step: 800/533, loss: 0.05789361149072647
2023-01-23 00:35:37.616985: step: 804/533, loss: 0.19672508537769318
2023-01-23 00:35:38.817912: step: 808/533, loss: 0.42760956287384033
2023-01-23 00:35:39.982056: step: 812/533, loss: 0.05177664756774902
2023-01-23 00:35:41.134699: step: 816/533, loss: 0.41149386763572693
2023-01-23 00:35:42.322650: step: 820/533, loss: 0.05115308612585068
2023-01-23 00:35:43.553433: step: 824/533, loss: 0.10420207679271698
2023-01-23 00:35:44.733072: step: 828/533, loss: 0.08954200893640518
2023-01-23 00:35:45.903681: step: 832/533, loss: 0.18194933235645294
2023-01-23 00:35:47.065062: step: 836/533, loss: 0.12253104150295258
2023-01-23 00:35:48.218155: step: 840/533, loss: 0.07624082267284393
2023-01-23 00:35:49.368174: step: 844/533, loss: 0.164313405752182
2023-01-23 00:35:50.514890: step: 848/533, loss: 0.023150037974119186
2023-01-23 00:35:51.682593: step: 852/533, loss: 0.11395011097192764
2023-01-23 00:35:52.844930: step: 856/533, loss: 0.23876214027404785
2023-01-23 00:35:53.972434: step: 860/533, loss: 0.05722036957740784
2023-01-23 00:35:55.141818: step: 864/533, loss: 0.1533019095659256
2023-01-23 00:35:56.299494: step: 868/533, loss: 0.04178767278790474
2023-01-23 00:35:57.444607: step: 872/533, loss: 0.4499811828136444
2023-01-23 00:35:58.645927: step: 876/533, loss: 0.13845939934253693
2023-01-23 00:35:59.825993: step: 880/533, loss: 0.09106773883104324
2023-01-23 00:36:00.963471: step: 884/533, loss: 0.07382631301879883
2023-01-23 00:36:02.143919: step: 888/533, loss: 0.16635771095752716
2023-01-23 00:36:03.307868: step: 892/533, loss: 0.1024908721446991
2023-01-23 00:36:04.481591: step: 896/533, loss: 0.29661786556243896
2023-01-23 00:36:05.677290: step: 900/533, loss: 0.1438174843788147
2023-01-23 00:36:06.897482: step: 904/533, loss: 0.16420002281665802
2023-01-23 00:36:08.056816: step: 908/533, loss: 0.11474857479333878
2023-01-23 00:36:09.216966: step: 912/533, loss: 0.04106488078832626
2023-01-23 00:36:10.440714: step: 916/533, loss: 0.23226386308670044
2023-01-23 00:36:11.569704: step: 920/533, loss: 0.0999455451965332
2023-01-23 00:36:12.764111: step: 924/533, loss: 0.06648831069469452
2023-01-23 00:36:13.925227: step: 928/533, loss: 0.08065791428089142
2023-01-23 00:36:15.129986: step: 932/533, loss: 0.2053905427455902
2023-01-23 00:36:16.318924: step: 936/533, loss: 0.1347431242465973
2023-01-23 00:36:17.540102: step: 940/533, loss: 0.09002552181482315
2023-01-23 00:36:18.796440: step: 944/533, loss: 0.06162893772125244
2023-01-23 00:36:19.973619: step: 948/533, loss: 0.17965379357337952
2023-01-23 00:36:21.148241: step: 952/533, loss: 0.16462893784046173
2023-01-23 00:36:22.314079: step: 956/533, loss: 0.0900600403547287
2023-01-23 00:36:23.528696: step: 960/533, loss: 0.12690864503383636
2023-01-23 00:36:24.707196: step: 964/533, loss: 0.015422534197568893
2023-01-23 00:36:25.850853: step: 968/533, loss: 0.4357540011405945
2023-01-23 00:36:26.988198: step: 972/533, loss: 0.10814743489027023
2023-01-23 00:36:28.106385: step: 976/533, loss: 0.06888599693775177
2023-01-23 00:36:29.283972: step: 980/533, loss: 0.033872321248054504
2023-01-23 00:36:30.438367: step: 984/533, loss: 0.1013982743024826
2023-01-23 00:36:31.609007: step: 988/533, loss: 0.036885831505060196
2023-01-23 00:36:32.840272: step: 992/533, loss: 0.320893257856369
2023-01-23 00:36:34.041207: step: 996/533, loss: 0.3332177400588989
2023-01-23 00:36:35.166400: step: 1000/533, loss: 0.3373338282108307
2023-01-23 00:36:36.376003: step: 1004/533, loss: 0.6432033777236938
2023-01-23 00:36:37.572778: step: 1008/533, loss: 0.28733140230178833
2023-01-23 00:36:38.772802: step: 1012/533, loss: 0.2184928059577942
2023-01-23 00:36:39.967774: step: 1016/533, loss: 0.08183488249778748
2023-01-23 00:36:41.135923: step: 1020/533, loss: 0.14864301681518555
2023-01-23 00:36:42.302082: step: 1024/533, loss: 0.16043797135353088
2023-01-23 00:36:43.458445: step: 1028/533, loss: 0.6593327522277832
2023-01-23 00:36:44.612167: step: 1032/533, loss: 0.13295136392116547
2023-01-23 00:36:45.761118: step: 1036/533, loss: 0.18243809044361115
2023-01-23 00:36:46.914683: step: 1040/533, loss: 0.03352494165301323
2023-01-23 00:36:48.067950: step: 1044/533, loss: 0.5756750106811523
2023-01-23 00:36:49.277953: step: 1048/533, loss: 0.5511318445205688
2023-01-23 00:36:50.496584: step: 1052/533, loss: 0.20697203278541565
2023-01-23 00:36:51.693866: step: 1056/533, loss: 0.05725250393152237
2023-01-23 00:36:52.862762: step: 1060/533, loss: 3.5092246532440186
2023-01-23 00:36:53.988084: step: 1064/533, loss: 0.2597506642341614
2023-01-23 00:36:55.204570: step: 1068/533, loss: 0.22108283638954163
2023-01-23 00:36:56.385682: step: 1072/533, loss: 0.310195654630661
2023-01-23 00:36:57.551996: step: 1076/533, loss: 0.07069483399391174
2023-01-23 00:36:58.713102: step: 1080/533, loss: 0.22458162903785706
2023-01-23 00:36:59.859940: step: 1084/533, loss: 0.02254791371524334
2023-01-23 00:37:01.042936: step: 1088/533, loss: 0.18851758539676666
2023-01-23 00:37:02.213383: step: 1092/533, loss: 0.2145695984363556
2023-01-23 00:37:03.368072: step: 1096/533, loss: 0.34991785883903503
2023-01-23 00:37:04.557648: step: 1100/533, loss: 0.12251511216163635
2023-01-23 00:37:05.782917: step: 1104/533, loss: 0.05593429133296013
2023-01-23 00:37:06.925398: step: 1108/533, loss: 0.15074720978736877
2023-01-23 00:37:08.138626: step: 1112/533, loss: 0.3482500910758972
2023-01-23 00:37:09.322141: step: 1116/533, loss: 0.11167445778846741
2023-01-23 00:37:10.470919: step: 1120/533, loss: 0.05750274658203125
2023-01-23 00:37:11.661547: step: 1124/533, loss: 0.513885498046875
2023-01-23 00:37:12.861693: step: 1128/533, loss: 0.07086972892284393
2023-01-23 00:37:14.062911: step: 1132/533, loss: 0.2156183272600174
2023-01-23 00:37:15.219291: step: 1136/533, loss: 0.2882498800754547
2023-01-23 00:37:16.387798: step: 1140/533, loss: 0.08378219604492188
2023-01-23 00:37:17.618261: step: 1144/533, loss: 0.021956156939268112
2023-01-23 00:37:18.819085: step: 1148/533, loss: 0.1018834114074707
2023-01-23 00:37:20.006619: step: 1152/533, loss: 0.5925976634025574
2023-01-23 00:37:21.189850: step: 1156/533, loss: 0.025112057104706764
2023-01-23 00:37:22.412116: step: 1160/533, loss: 0.11240149289369583
2023-01-23 00:37:23.588217: step: 1164/533, loss: 0.2043600082397461
2023-01-23 00:37:24.743714: step: 1168/533, loss: 0.3127053380012512
2023-01-23 00:37:25.917251: step: 1172/533, loss: 0.11704130470752716
2023-01-23 00:37:27.122386: step: 1176/533, loss: 0.07777661830186844
2023-01-23 00:37:28.304430: step: 1180/533, loss: 0.1534065306186676
2023-01-23 00:37:29.500385: step: 1184/533, loss: 0.09513416886329651
2023-01-23 00:37:30.702050: step: 1188/533, loss: 0.06841164082288742
2023-01-23 00:37:31.854116: step: 1192/533, loss: 0.12703752517700195
2023-01-23 00:37:33.022629: step: 1196/533, loss: 0.10455399006605148
2023-01-23 00:37:34.232723: step: 1200/533, loss: 0.07830943912267685
2023-01-23 00:37:35.425961: step: 1204/533, loss: 0.43790698051452637
2023-01-23 00:37:36.634108: step: 1208/533, loss: 0.3851598799228668
2023-01-23 00:37:37.796611: step: 1212/533, loss: 0.1309981346130371
2023-01-23 00:37:39.039556: step: 1216/533, loss: 0.13694210350513458
2023-01-23 00:37:40.243924: step: 1220/533, loss: 0.11538295447826385
2023-01-23 00:37:41.438519: step: 1224/533, loss: 0.2820868492126465
2023-01-23 00:37:42.649921: step: 1228/533, loss: 0.495748907327652
2023-01-23 00:37:43.839733: step: 1232/533, loss: 0.04419393837451935
2023-01-23 00:37:44.999342: step: 1236/533, loss: 0.11558160930871964
2023-01-23 00:37:46.156639: step: 1240/533, loss: 0.08236837387084961
2023-01-23 00:37:47.294138: step: 1244/533, loss: 0.06681094318628311
2023-01-23 00:37:48.498632: step: 1248/533, loss: 0.03396787494421005
2023-01-23 00:37:49.701488: step: 1252/533, loss: 0.07566051930189133
2023-01-23 00:37:50.871555: step: 1256/533, loss: 0.17411479353904724
2023-01-23 00:37:52.024888: step: 1260/533, loss: 0.13344541192054749
2023-01-23 00:37:53.180139: step: 1264/533, loss: 0.037888478487730026
2023-01-23 00:37:54.377740: step: 1268/533, loss: 0.2684181332588196
2023-01-23 00:37:55.583946: step: 1272/533, loss: 0.07422362267971039
2023-01-23 00:37:56.737442: step: 1276/533, loss: 0.419964075088501
2023-01-23 00:37:57.894744: step: 1280/533, loss: 0.5850145220756531
2023-01-23 00:37:59.047298: step: 1284/533, loss: 0.038173869252204895
2023-01-23 00:38:00.200574: step: 1288/533, loss: 0.1673487275838852
2023-01-23 00:38:01.364687: step: 1292/533, loss: 0.11415676772594452
2023-01-23 00:38:02.530396: step: 1296/533, loss: 0.14867329597473145
2023-01-23 00:38:03.749675: step: 1300/533, loss: 0.011673260480165482
2023-01-23 00:38:04.924523: step: 1304/533, loss: 1.3752771615982056
2023-01-23 00:38:06.090245: step: 1308/533, loss: 0.15026354789733887
2023-01-23 00:38:07.260167: step: 1312/533, loss: 0.08691949397325516
2023-01-23 00:38:08.441402: step: 1316/533, loss: 0.44630491733551025
2023-01-23 00:38:09.609329: step: 1320/533, loss: 0.04766340181231499
2023-01-23 00:38:10.821289: step: 1324/533, loss: 0.051876164972782135
2023-01-23 00:38:11.993487: step: 1328/533, loss: 0.9295927286148071
2023-01-23 00:38:13.203053: step: 1332/533, loss: 0.09872036427259445
2023-01-23 00:38:14.420787: step: 1336/533, loss: 0.16506114602088928
2023-01-23 00:38:15.619689: step: 1340/533, loss: 0.14645300805568695
2023-01-23 00:38:16.786157: step: 1344/533, loss: 1.0066637992858887
2023-01-23 00:38:17.984273: step: 1348/533, loss: 0.19292087852954865
2023-01-23 00:38:19.117062: step: 1352/533, loss: 0.11848153918981552
2023-01-23 00:38:20.336284: step: 1356/533, loss: 0.221858412027359
2023-01-23 00:38:21.620236: step: 1360/533, loss: 0.2674716114997864
2023-01-23 00:38:22.807916: step: 1364/533, loss: 0.059876635670661926
2023-01-23 00:38:23.955133: step: 1368/533, loss: 0.1604660004377365
2023-01-23 00:38:25.109562: step: 1372/533, loss: 0.12207386642694473
2023-01-23 00:38:26.267094: step: 1376/533, loss: 0.12905368208885193
2023-01-23 00:38:27.465137: step: 1380/533, loss: 0.2698141932487488
2023-01-23 00:38:28.646542: step: 1384/533, loss: 0.2435825914144516
2023-01-23 00:38:29.775493: step: 1388/533, loss: 0.06786127388477325
2023-01-23 00:38:30.930602: step: 1392/533, loss: 0.38354578614234924
2023-01-23 00:38:32.099517: step: 1396/533, loss: 0.12366710603237152
2023-01-23 00:38:33.307275: step: 1400/533, loss: 0.5397354364395142
2023-01-23 00:38:34.482918: step: 1404/533, loss: 0.028628351166844368
2023-01-23 00:38:35.734538: step: 1408/533, loss: 0.09934577345848083
2023-01-23 00:38:36.906553: step: 1412/533, loss: 0.7715206146240234
2023-01-23 00:38:38.042303: step: 1416/533, loss: 1.4465574026107788
2023-01-23 00:38:39.242159: step: 1420/533, loss: 0.1617651879787445
2023-01-23 00:38:40.421948: step: 1424/533, loss: 0.0394839309155941
2023-01-23 00:38:41.577938: step: 1428/533, loss: 0.05683021619915962
2023-01-23 00:38:42.748508: step: 1432/533, loss: 0.10786976665258408
2023-01-23 00:38:43.928517: step: 1436/533, loss: 0.027826596051454544
2023-01-23 00:38:45.138496: step: 1440/533, loss: 1.2564316987991333
2023-01-23 00:38:46.298113: step: 1444/533, loss: 0.12281899899244308
2023-01-23 00:38:47.496421: step: 1448/533, loss: 1.341007947921753
2023-01-23 00:38:48.679505: step: 1452/533, loss: 0.2766227722167969
2023-01-23 00:38:49.890400: step: 1456/533, loss: 0.17998160421848297
2023-01-23 00:38:51.028979: step: 1460/533, loss: 0.11274652928113937
2023-01-23 00:38:52.205798: step: 1464/533, loss: 0.06542710959911346
2023-01-23 00:38:53.406221: step: 1468/533, loss: 0.6500186920166016
2023-01-23 00:38:54.607311: step: 1472/533, loss: 0.11893444508314133
2023-01-23 00:38:55.788353: step: 1476/533, loss: 0.06078615039587021
2023-01-23 00:38:56.939090: step: 1480/533, loss: 0.13525590300559998
2023-01-23 00:38:58.080655: step: 1484/533, loss: 0.0734526664018631
2023-01-23 00:38:59.276577: step: 1488/533, loss: 0.402272492647171
2023-01-23 00:39:00.475904: step: 1492/533, loss: 0.10789927840232849
2023-01-23 00:39:01.646443: step: 1496/533, loss: 0.08972835540771484
2023-01-23 00:39:02.807352: step: 1500/533, loss: 0.1338546723127365
2023-01-23 00:39:03.948301: step: 1504/533, loss: 0.6546284556388855
2023-01-23 00:39:05.129607: step: 1508/533, loss: 0.09639425575733185
2023-01-23 00:39:06.311414: step: 1512/533, loss: 1.2416266202926636
2023-01-23 00:39:07.547648: step: 1516/533, loss: 0.7368118166923523
2023-01-23 00:39:08.720967: step: 1520/533, loss: 0.09771113842725754
2023-01-23 00:39:09.914005: step: 1524/533, loss: 0.163905531167984
2023-01-23 00:39:11.175269: step: 1528/533, loss: 0.13659754395484924
2023-01-23 00:39:12.352044: step: 1532/533, loss: 0.1884136199951172
2023-01-23 00:39:13.504070: step: 1536/533, loss: 0.0712137222290039
2023-01-23 00:39:14.660231: step: 1540/533, loss: 0.09784231334924698
2023-01-23 00:39:15.826266: step: 1544/533, loss: 0.39156195521354675
2023-01-23 00:39:17.033942: step: 1548/533, loss: 0.22279366850852966
2023-01-23 00:39:18.205922: step: 1552/533, loss: 0.0961771011352539
2023-01-23 00:39:19.406159: step: 1556/533, loss: 0.3711252212524414
2023-01-23 00:39:20.575840: step: 1560/533, loss: 0.11000586301088333
2023-01-23 00:39:21.755810: step: 1564/533, loss: 0.03015165403485298
2023-01-23 00:39:22.947167: step: 1568/533, loss: 0.13989749550819397
2023-01-23 00:39:24.123298: step: 1572/533, loss: 0.1575462371110916
2023-01-23 00:39:25.302263: step: 1576/533, loss: 0.1334587037563324
2023-01-23 00:39:26.490215: step: 1580/533, loss: 0.09696273505687714
2023-01-23 00:39:27.656696: step: 1584/533, loss: 0.05098571628332138
2023-01-23 00:39:28.843820: step: 1588/533, loss: 0.0862436294555664
2023-01-23 00:39:30.022947: step: 1592/533, loss: 0.04604396969079971
2023-01-23 00:39:31.191114: step: 1596/533, loss: 0.060735225677490234
2023-01-23 00:39:32.329193: step: 1600/533, loss: 0.02472858503460884
2023-01-23 00:39:33.493086: step: 1604/533, loss: 0.16002511978149414
2023-01-23 00:39:34.669106: step: 1608/533, loss: 0.5418399572372437
2023-01-23 00:39:35.852905: step: 1612/533, loss: 0.07610159367322922
2023-01-23 00:39:37.017364: step: 1616/533, loss: 0.1806151270866394
2023-01-23 00:39:38.172942: step: 1620/533, loss: 0.08388242870569229
2023-01-23 00:39:39.391694: step: 1624/533, loss: 0.2008608877658844
2023-01-23 00:39:40.585449: step: 1628/533, loss: 0.13060970604419708
2023-01-23 00:39:41.772868: step: 1632/533, loss: 0.052858926355838776
2023-01-23 00:39:42.957913: step: 1636/533, loss: 0.09687748551368713
2023-01-23 00:39:44.162773: step: 1640/533, loss: 0.615983784198761
2023-01-23 00:39:45.340968: step: 1644/533, loss: 0.2445390820503235
2023-01-23 00:39:46.473323: step: 1648/533, loss: 0.03076920472085476
2023-01-23 00:39:47.687773: step: 1652/533, loss: 0.05043325573205948
2023-01-23 00:39:48.878477: step: 1656/533, loss: 0.10877757519483566
2023-01-23 00:39:50.023414: step: 1660/533, loss: 0.17157940566539764
2023-01-23 00:39:51.204913: step: 1664/533, loss: 0.2575721740722656
2023-01-23 00:39:52.363798: step: 1668/533, loss: 0.05763950198888779
2023-01-23 00:39:53.544490: step: 1672/533, loss: 0.2720033824443817
2023-01-23 00:39:54.738752: step: 1676/533, loss: 0.22390387952327728
2023-01-23 00:39:55.935934: step: 1680/533, loss: 0.3240469992160797
2023-01-23 00:39:57.099605: step: 1684/533, loss: 0.17517486214637756
2023-01-23 00:39:58.287878: step: 1688/533, loss: 0.13015690445899963
2023-01-23 00:39:59.458724: step: 1692/533, loss: 0.45919427275657654
2023-01-23 00:40:00.618907: step: 1696/533, loss: 0.072052001953125
2023-01-23 00:40:01.827579: step: 1700/533, loss: 0.13439303636550903
2023-01-23 00:40:03.038557: step: 1704/533, loss: 0.05600857734680176
2023-01-23 00:40:04.231832: step: 1708/533, loss: 0.05688543617725372
2023-01-23 00:40:05.412575: step: 1712/533, loss: 0.14664840698242188
2023-01-23 00:40:06.571135: step: 1716/533, loss: 0.384204626083374
2023-01-23 00:40:07.743120: step: 1720/533, loss: 1.031225562095642
2023-01-23 00:40:08.951078: step: 1724/533, loss: 0.26040613651275635
2023-01-23 00:40:10.115474: step: 1728/533, loss: 0.037535667419433594
2023-01-23 00:40:11.283834: step: 1732/533, loss: 0.12251291424036026
2023-01-23 00:40:12.483697: step: 1736/533, loss: 0.07688362151384354
2023-01-23 00:40:13.665568: step: 1740/533, loss: 0.128939688205719
2023-01-23 00:40:14.855556: step: 1744/533, loss: 0.0218703281134367
2023-01-23 00:40:16.059524: step: 1748/533, loss: 0.07857814431190491
2023-01-23 00:40:17.234091: step: 1752/533, loss: 0.07582254707813263
2023-01-23 00:40:18.419698: step: 1756/533, loss: 0.067365363240242
2023-01-23 00:40:19.585640: step: 1760/533, loss: 0.10041113197803497
2023-01-23 00:40:20.773227: step: 1764/533, loss: 0.15190574526786804
2023-01-23 00:40:21.918475: step: 1768/533, loss: 0.13488759100437164
2023-01-23 00:40:23.104794: step: 1772/533, loss: 0.2523534893989563
2023-01-23 00:40:24.266726: step: 1776/533, loss: 0.15841913223266602
2023-01-23 00:40:25.430522: step: 1780/533, loss: 0.0786147192120552
2023-01-23 00:40:26.596227: step: 1784/533, loss: 0.30462560057640076
2023-01-23 00:40:27.782870: step: 1788/533, loss: 0.07425765693187714
2023-01-23 00:40:28.936227: step: 1792/533, loss: 0.020304633304476738
2023-01-23 00:40:30.127337: step: 1796/533, loss: 0.5724536180496216
2023-01-23 00:40:31.324339: step: 1800/533, loss: 0.14271003007888794
2023-01-23 00:40:32.519179: step: 1804/533, loss: 0.06013636663556099
2023-01-23 00:40:33.726126: step: 1808/533, loss: 0.14017534255981445
2023-01-23 00:40:34.928351: step: 1812/533, loss: 0.05206337571144104
2023-01-23 00:40:36.161764: step: 1816/533, loss: 0.37365150451660156
2023-01-23 00:40:37.352208: step: 1820/533, loss: 0.01740436628460884
2023-01-23 00:40:38.563130: step: 1824/533, loss: 0.27691972255706787
2023-01-23 00:40:39.740636: step: 1828/533, loss: 0.24644887447357178
2023-01-23 00:40:40.884389: step: 1832/533, loss: 0.09711380302906036
2023-01-23 00:40:42.047087: step: 1836/533, loss: 0.2083951085805893
2023-01-23 00:40:43.241082: step: 1840/533, loss: 0.0981113463640213
2023-01-23 00:40:44.435269: step: 1844/533, loss: 0.20288285613059998
2023-01-23 00:40:45.617641: step: 1848/533, loss: 0.4039088487625122
2023-01-23 00:40:46.776762: step: 1852/533, loss: 0.027602385729551315
2023-01-23 00:40:47.959795: step: 1856/533, loss: 0.14193540811538696
2023-01-23 00:40:49.103534: step: 1860/533, loss: 0.10248861461877823
2023-01-23 00:40:50.269694: step: 1864/533, loss: 0.2411825954914093
2023-01-23 00:40:51.428878: step: 1868/533, loss: 0.06684742122888565
2023-01-23 00:40:52.622286: step: 1872/533, loss: 0.009373664855957031
2023-01-23 00:40:53.766918: step: 1876/533, loss: 0.13146862387657166
2023-01-23 00:40:54.938015: step: 1880/533, loss: 0.19396571815013885
2023-01-23 00:40:56.115415: step: 1884/533, loss: 0.12971439957618713
2023-01-23 00:40:57.268410: step: 1888/533, loss: 0.08772548288106918
2023-01-23 00:40:58.453209: step: 1892/533, loss: 0.0742061585187912
2023-01-23 00:40:59.626307: step: 1896/533, loss: 0.15593385696411133
2023-01-23 00:41:00.794071: step: 1900/533, loss: 0.14757271111011505
2023-01-23 00:41:01.958083: step: 1904/533, loss: 0.27709275484085083
2023-01-23 00:41:03.154700: step: 1908/533, loss: 0.12831354141235352
2023-01-23 00:41:04.331384: step: 1912/533, loss: 0.1672619879245758
2023-01-23 00:41:05.531479: step: 1916/533, loss: 0.3313051462173462
2023-01-23 00:41:06.688632: step: 1920/533, loss: 0.19065017998218536
2023-01-23 00:41:07.887052: step: 1924/533, loss: 0.06419233977794647
2023-01-23 00:41:09.075032: step: 1928/533, loss: 0.12727728486061096
2023-01-23 00:41:10.230571: step: 1932/533, loss: 0.419650137424469
2023-01-23 00:41:11.413625: step: 1936/533, loss: 0.065036341547966
2023-01-23 00:41:12.572657: step: 1940/533, loss: 0.07918167114257812
2023-01-23 00:41:13.766246: step: 1944/533, loss: 0.07085132598876953
2023-01-23 00:41:14.924172: step: 1948/533, loss: 0.0782196968793869
2023-01-23 00:41:16.114703: step: 1952/533, loss: 0.6852022409439087
2023-01-23 00:41:17.307751: step: 1956/533, loss: 0.9026672840118408
2023-01-23 00:41:18.479923: step: 1960/533, loss: 0.11578083038330078
2023-01-23 00:41:19.656558: step: 1964/533, loss: 0.1018071174621582
2023-01-23 00:41:20.842641: step: 1968/533, loss: 0.1267421692609787
2023-01-23 00:41:21.964489: step: 1972/533, loss: 0.10802315175533295
2023-01-23 00:41:23.175520: step: 1976/533, loss: 0.0272674560546875
2023-01-23 00:41:24.324817: step: 1980/533, loss: 0.05474843084812164
2023-01-23 00:41:25.518098: step: 1984/533, loss: 0.7037945985794067
2023-01-23 00:41:26.733427: step: 1988/533, loss: 0.03250541538000107
2023-01-23 00:41:27.965387: step: 1992/533, loss: 0.019031710922718048
2023-01-23 00:41:29.161488: step: 1996/533, loss: 0.15862607955932617
2023-01-23 00:41:30.357956: step: 2000/533, loss: 0.11570720374584198
2023-01-23 00:41:31.521909: step: 2004/533, loss: 0.029933834448456764
2023-01-23 00:41:32.693518: step: 2008/533, loss: 0.18323147296905518
2023-01-23 00:41:33.877238: step: 2012/533, loss: 0.07221489399671555
2023-01-23 00:41:35.071668: step: 2016/533, loss: 0.14682435989379883
2023-01-23 00:41:36.254413: step: 2020/533, loss: 0.5569009184837341
2023-01-23 00:41:37.428182: step: 2024/533, loss: 0.01458828430622816
2023-01-23 00:41:38.590192: step: 2028/533, loss: 0.05969729647040367
2023-01-23 00:41:39.771662: step: 2032/533, loss: 0.13389864563941956
2023-01-23 00:41:40.921460: step: 2036/533, loss: 0.13498875498771667
2023-01-23 00:41:42.086824: step: 2040/533, loss: 0.09449644386768341
2023-01-23 00:41:43.260946: step: 2044/533, loss: 1.1591969728469849
2023-01-23 00:41:44.452984: step: 2048/533, loss: 0.7760132551193237
2023-01-23 00:41:45.627039: step: 2052/533, loss: 0.10990545898675919
2023-01-23 00:41:46.812151: step: 2056/533, loss: 0.05424699932336807
2023-01-23 00:41:48.014364: step: 2060/533, loss: 0.12772150337696075
2023-01-23 00:41:49.215412: step: 2064/533, loss: 0.08707280457019806
2023-01-23 00:41:50.391515: step: 2068/533, loss: 0.09374499320983887
2023-01-23 00:41:51.591718: step: 2072/533, loss: 0.06009012460708618
2023-01-23 00:41:52.760125: step: 2076/533, loss: 0.08118324726819992
2023-01-23 00:41:53.898538: step: 2080/533, loss: 1.3016350269317627
2023-01-23 00:41:55.070615: step: 2084/533, loss: 0.23098011314868927
2023-01-23 00:41:56.259676: step: 2088/533, loss: 0.01660327985882759
2023-01-23 00:41:57.428054: step: 2092/533, loss: 0.1556406021118164
2023-01-23 00:41:58.610046: step: 2096/533, loss: 0.13567021489143372
2023-01-23 00:41:59.765556: step: 2100/533, loss: 0.10422177612781525
2023-01-23 00:42:00.945871: step: 2104/533, loss: 0.16072861850261688
2023-01-23 00:42:02.112475: step: 2108/533, loss: 0.005278587341308594
2023-01-23 00:42:03.318344: step: 2112/533, loss: 0.08607663959264755
2023-01-23 00:42:04.571928: step: 2116/533, loss: 0.0637931376695633
2023-01-23 00:42:05.720821: step: 2120/533, loss: 0.0776335746049881
2023-01-23 00:42:06.925087: step: 2124/533, loss: 0.20560836791992188
2023-01-23 00:42:08.078110: step: 2128/533, loss: 0.36538657546043396
2023-01-23 00:42:09.243768: step: 2132/533, loss: 0.16393613815307617
==================================================
Loss: 0.219
--------------------
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': 6}
Test: {'event': {'p': 0.6085657370517928, 'r': 0.7813299232736572, 'f1': 0.6842105263157895}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.6233766233766234, 'r': 0.8888888888888888, 'f1': 0.732824427480916}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.6538461538461539, 'r': 0.5396825396825397, 'f1': 0.5913043478260869}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
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': 6}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:42:50.714135: step: 4/533, loss: 0.02713499218225479
2023-01-23 00:42:51.943905: step: 8/533, loss: 0.09234371781349182
2023-01-23 00:42:53.150247: step: 12/533, loss: 0.0528598316013813
2023-01-23 00:42:54.347990: step: 16/533, loss: 0.16958141326904297
2023-01-23 00:42:55.552253: step: 20/533, loss: 0.1115323081612587
2023-01-23 00:42:56.723062: step: 24/533, loss: 0.5008176565170288
2023-01-23 00:42:57.859790: step: 28/533, loss: 0.5069162845611572
2023-01-23 00:42:59.004474: step: 32/533, loss: 0.07732424885034561
2023-01-23 00:43:00.146636: step: 36/533, loss: 0.10948900878429413
2023-01-23 00:43:01.312941: step: 40/533, loss: 0.08771447837352753
2023-01-23 00:43:02.425843: step: 44/533, loss: 0.013901353813707829
2023-01-23 00:43:03.628910: step: 48/533, loss: 0.14765433967113495
2023-01-23 00:43:04.784899: step: 52/533, loss: 0.10826416313648224
2023-01-23 00:43:05.942693: step: 56/533, loss: 0.04156780242919922
2023-01-23 00:43:07.089738: step: 60/533, loss: 0.0886441245675087
2023-01-23 00:43:08.302670: step: 64/533, loss: 0.419236958026886
2023-01-23 00:43:09.436204: step: 68/533, loss: 0.051343392580747604
2023-01-23 00:43:10.636722: step: 72/533, loss: 0.3384891450405121
2023-01-23 00:43:11.783311: step: 76/533, loss: 0.15001440048217773
2023-01-23 00:43:12.971603: step: 80/533, loss: 0.08281965553760529
2023-01-23 00:43:14.126651: step: 84/533, loss: 0.027667714282870293
2023-01-23 00:43:15.294878: step: 88/533, loss: 0.0781317725777626
2023-01-23 00:43:16.507972: step: 92/533, loss: 0.6364617347717285
2023-01-23 00:43:17.667618: step: 96/533, loss: 0.007638502400368452
2023-01-23 00:43:18.811387: step: 100/533, loss: 0.04420776292681694
2023-01-23 00:43:19.998023: step: 104/533, loss: 0.08147278428077698
2023-01-23 00:43:21.148318: step: 108/533, loss: 0.022054623812437057
2023-01-23 00:43:22.342778: step: 112/533, loss: 0.17314930260181427
2023-01-23 00:43:23.536813: step: 116/533, loss: 0.283458411693573
2023-01-23 00:43:24.728399: step: 120/533, loss: 0.046570874750614166
2023-01-23 00:43:25.932956: step: 124/533, loss: 0.027858782559633255
2023-01-23 00:43:27.071093: step: 128/533, loss: 0.01189116295427084
2023-01-23 00:43:28.237037: step: 132/533, loss: 0.5573993921279907
2023-01-23 00:43:29.417088: step: 136/533, loss: 0.07571068406105042
2023-01-23 00:43:30.647068: step: 140/533, loss: 0.13586430251598358
2023-01-23 00:43:31.825693: step: 144/533, loss: 0.018926765769720078
2023-01-23 00:43:32.980089: step: 148/533, loss: 0.0792180523276329
2023-01-23 00:43:34.154836: step: 152/533, loss: 0.062178902328014374
2023-01-23 00:43:35.316133: step: 156/533, loss: 0.1420845091342926
2023-01-23 00:43:36.564422: step: 160/533, loss: 0.1116710677742958
2023-01-23 00:43:37.723122: step: 164/533, loss: 0.11904354393482208
2023-01-23 00:43:38.897703: step: 168/533, loss: 0.7697548866271973
2023-01-23 00:43:40.095128: step: 172/533, loss: 0.33512943983078003
2023-01-23 00:43:41.286452: step: 176/533, loss: 0.6424466371536255
2023-01-23 00:43:42.457613: step: 180/533, loss: 0.04398174583911896
2023-01-23 00:43:43.658885: step: 184/533, loss: 0.11134495586156845
2023-01-23 00:43:44.817570: step: 188/533, loss: 0.11911516636610031
2023-01-23 00:43:45.976448: step: 192/533, loss: 0.1014779582619667
2023-01-23 00:43:47.183236: step: 196/533, loss: 0.21229958534240723
2023-01-23 00:43:48.369311: step: 200/533, loss: 0.1393236368894577
2023-01-23 00:43:49.585686: step: 204/533, loss: 0.09390535205602646
2023-01-23 00:43:50.740276: step: 208/533, loss: 0.09418316185474396
2023-01-23 00:43:51.947736: step: 212/533, loss: 0.1424139142036438
2023-01-23 00:43:53.171344: step: 216/533, loss: 0.07017631828784943
2023-01-23 00:43:54.349188: step: 220/533, loss: 0.27648013830184937
2023-01-23 00:43:55.528421: step: 224/533, loss: 0.21756906807422638
2023-01-23 00:43:56.712953: step: 228/533, loss: 0.10032311081886292
2023-01-23 00:43:57.862283: step: 232/533, loss: 0.8077481389045715
2023-01-23 00:43:59.026216: step: 236/533, loss: 0.0897817611694336
2023-01-23 00:44:00.244368: step: 240/533, loss: 0.11320037394762039
2023-01-23 00:44:01.414593: step: 244/533, loss: 0.5346193909645081
2023-01-23 00:44:02.584601: step: 248/533, loss: 0.26862525939941406
2023-01-23 00:44:03.749558: step: 252/533, loss: 0.096012644469738
2023-01-23 00:44:04.932988: step: 256/533, loss: 0.30831077694892883
2023-01-23 00:44:06.127488: step: 260/533, loss: 0.15489159524440765
2023-01-23 00:44:07.314007: step: 264/533, loss: 0.031189823523163795
2023-01-23 00:44:08.457388: step: 268/533, loss: 0.06381230056285858
2023-01-23 00:44:09.651203: step: 272/533, loss: 0.20449256896972656
2023-01-23 00:44:10.790832: step: 276/533, loss: 0.11977416276931763
2023-01-23 00:44:12.025199: step: 280/533, loss: 0.048119544982910156
2023-01-23 00:44:13.193403: step: 284/533, loss: 0.0661199539899826
2023-01-23 00:44:14.377688: step: 288/533, loss: 0.15234041213989258
2023-01-23 00:44:15.547776: step: 292/533, loss: 0.352247416973114
2023-01-23 00:44:16.736878: step: 296/533, loss: 0.1439352035522461
2023-01-23 00:44:17.919090: step: 300/533, loss: 0.09108009934425354
2023-01-23 00:44:19.131699: step: 304/533, loss: 0.10483226925134659
2023-01-23 00:44:20.332211: step: 308/533, loss: 0.18390808999538422
2023-01-23 00:44:21.509659: step: 312/533, loss: 0.08191729336977005
2023-01-23 00:44:22.652596: step: 316/533, loss: 0.08554497361183167
2023-01-23 00:44:23.861269: step: 320/533, loss: 0.1712614744901657
2023-01-23 00:44:25.003701: step: 324/533, loss: 0.24714070558547974
2023-01-23 00:44:26.180175: step: 328/533, loss: 0.06959524005651474
2023-01-23 00:44:27.360918: step: 332/533, loss: 0.04762458801269531
2023-01-23 00:44:28.547786: step: 336/533, loss: 0.36471718549728394
2023-01-23 00:44:29.709049: step: 340/533, loss: 0.055223919451236725
2023-01-23 00:44:30.896367: step: 344/533, loss: 0.021492719650268555
2023-01-23 00:44:32.068073: step: 348/533, loss: 0.4865197241306305
2023-01-23 00:44:33.265721: step: 352/533, loss: 0.40627679228782654
2023-01-23 00:44:34.409114: step: 356/533, loss: 0.5815869569778442
2023-01-23 00:44:35.591591: step: 360/533, loss: 0.13450995087623596
2023-01-23 00:44:36.760720: step: 364/533, loss: 0.13007330894470215
2023-01-23 00:44:37.971164: step: 368/533, loss: 0.03940916061401367
2023-01-23 00:44:39.145702: step: 372/533, loss: 0.13993777334690094
2023-01-23 00:44:40.332877: step: 376/533, loss: 0.8265101313591003
2023-01-23 00:44:41.499335: step: 380/533, loss: 0.34481391310691833
2023-01-23 00:44:42.682854: step: 384/533, loss: 0.19091807305812836
2023-01-23 00:44:43.832298: step: 388/533, loss: 0.4733350872993469
2023-01-23 00:44:45.025372: step: 392/533, loss: 0.11199293285608292
2023-01-23 00:44:46.183489: step: 396/533, loss: 0.06990843266248703
2023-01-23 00:44:47.349164: step: 400/533, loss: 0.1847863495349884
2023-01-23 00:44:48.525027: step: 404/533, loss: 0.11941175907850266
2023-01-23 00:44:49.688224: step: 408/533, loss: 0.06626243889331818
2023-01-23 00:44:50.920392: step: 412/533, loss: 0.10838775336742401
2023-01-23 00:44:52.095940: step: 416/533, loss: 0.013866320252418518
2023-01-23 00:44:53.288117: step: 420/533, loss: 0.10283956676721573
2023-01-23 00:44:54.498449: step: 424/533, loss: 0.09228868782520294
2023-01-23 00:44:55.666174: step: 428/533, loss: 0.5761860013008118
2023-01-23 00:44:56.865986: step: 432/533, loss: 0.06501880288124084
2023-01-23 00:44:58.023518: step: 436/533, loss: 0.10980406403541565
2023-01-23 00:44:59.154148: step: 440/533, loss: 0.06611061096191406
2023-01-23 00:45:00.339923: step: 444/533, loss: 0.030341625213623047
2023-01-23 00:45:01.493548: step: 448/533, loss: 0.050723735243082047
2023-01-23 00:45:02.707482: step: 452/533, loss: 0.2815723419189453
2023-01-23 00:45:03.912465: step: 456/533, loss: 0.12159442901611328
2023-01-23 00:45:05.093721: step: 460/533, loss: 0.13366861641407013
2023-01-23 00:45:06.257850: step: 464/533, loss: 0.13840627670288086
2023-01-23 00:45:07.455513: step: 468/533, loss: 0.2861112356185913
2023-01-23 00:45:08.657079: step: 472/533, loss: 0.1198093444108963
2023-01-23 00:45:09.845954: step: 476/533, loss: 0.15332946181297302
2023-01-23 00:45:11.019236: step: 480/533, loss: 0.18241333961486816
2023-01-23 00:45:12.206232: step: 484/533, loss: 0.0022195817437022924
2023-01-23 00:45:13.345225: step: 488/533, loss: 0.08952093124389648
2023-01-23 00:45:14.509958: step: 492/533, loss: 0.09961710125207901
2023-01-23 00:45:15.666444: step: 496/533, loss: 0.20637111365795135
2023-01-23 00:45:16.840793: step: 500/533, loss: 0.16375738382339478
2023-01-23 00:45:18.014843: step: 504/533, loss: 0.34664592146873474
2023-01-23 00:45:19.202715: step: 508/533, loss: 0.1622917205095291
2023-01-23 00:45:20.438543: step: 512/533, loss: 0.10765047371387482
2023-01-23 00:45:21.599182: step: 516/533, loss: 0.153484046459198
2023-01-23 00:45:22.766116: step: 520/533, loss: 0.03779182583093643
2023-01-23 00:45:23.974247: step: 524/533, loss: 2.8432631492614746
2023-01-23 00:45:25.151588: step: 528/533, loss: 0.04412193223834038
2023-01-23 00:45:26.360019: step: 532/533, loss: 0.12501993775367737
2023-01-23 00:45:27.514100: step: 536/533, loss: 0.08911094814538956
2023-01-23 00:45:28.666194: step: 540/533, loss: 0.04807615280151367
2023-01-23 00:45:29.842774: step: 544/533, loss: 0.13882999122142792
2023-01-23 00:45:31.016132: step: 548/533, loss: 0.005447817035019398
2023-01-23 00:45:32.195874: step: 552/533, loss: 0.12212295830249786
2023-01-23 00:45:33.364743: step: 556/533, loss: 0.060848332941532135
2023-01-23 00:45:34.537042: step: 560/533, loss: 0.04181380197405815
2023-01-23 00:45:35.689173: step: 564/533, loss: 0.14441928267478943
2023-01-23 00:45:36.869855: step: 568/533, loss: 0.08375763893127441
2023-01-23 00:45:38.015827: step: 572/533, loss: 0.1010388433933258
2023-01-23 00:45:39.195714: step: 576/533, loss: 0.12010860443115234
2023-01-23 00:45:40.368677: step: 580/533, loss: 0.14491453766822815
2023-01-23 00:45:41.547957: step: 584/533, loss: 0.3436940312385559
2023-01-23 00:45:42.728501: step: 588/533, loss: 0.2553713917732239
2023-01-23 00:45:43.869329: step: 592/533, loss: 0.6016233563423157
2023-01-23 00:45:45.054679: step: 596/533, loss: 0.02080359496176243
2023-01-23 00:45:46.225858: step: 600/533, loss: 0.4463450014591217
2023-01-23 00:45:47.383750: step: 604/533, loss: 0.7715851664543152
2023-01-23 00:45:48.565784: step: 608/533, loss: 0.02622537687420845
2023-01-23 00:45:49.768763: step: 612/533, loss: 0.4134342074394226
2023-01-23 00:45:50.999981: step: 616/533, loss: 0.3035464286804199
2023-01-23 00:45:52.189418: step: 620/533, loss: 0.04574203863739967
2023-01-23 00:45:53.422256: step: 624/533, loss: 0.0404236800968647
2023-01-23 00:45:54.615936: step: 628/533, loss: 0.11040210723876953
2023-01-23 00:45:55.769064: step: 632/533, loss: 0.062007904052734375
2023-01-23 00:45:56.902512: step: 636/533, loss: 0.07534551620483398
2023-01-23 00:45:58.035518: step: 640/533, loss: 0.08489511162042618
2023-01-23 00:45:59.159885: step: 644/533, loss: 0.00962753314524889
2023-01-23 00:46:00.339712: step: 648/533, loss: 0.09941711276769638
2023-01-23 00:46:01.507546: step: 652/533, loss: 0.11434593051671982
2023-01-23 00:46:02.698553: step: 656/533, loss: 0.8069518208503723
2023-01-23 00:46:03.918471: step: 660/533, loss: 0.15600843727588654
2023-01-23 00:46:05.062067: step: 664/533, loss: 0.07689161598682404
2023-01-23 00:46:06.227809: step: 668/533, loss: 0.09479685872793198
2023-01-23 00:46:07.412192: step: 672/533, loss: 0.10828132182359695
2023-01-23 00:46:08.613211: step: 676/533, loss: 0.05332536622881889
2023-01-23 00:46:09.753919: step: 680/533, loss: 0.26875317096710205
2023-01-23 00:46:10.906891: step: 684/533, loss: 0.05133800581097603
2023-01-23 00:46:12.098284: step: 688/533, loss: 0.035854484885931015
2023-01-23 00:46:13.239392: step: 692/533, loss: 0.09907674789428711
2023-01-23 00:46:14.416745: step: 696/533, loss: 0.14481498301029205
2023-01-23 00:46:15.592309: step: 700/533, loss: 0.07191634178161621
2023-01-23 00:46:16.744008: step: 704/533, loss: 0.14179524779319763
2023-01-23 00:46:17.874705: step: 708/533, loss: 0.05259838327765465
2023-01-23 00:46:19.034004: step: 712/533, loss: 0.006909561343491077
2023-01-23 00:46:20.213944: step: 716/533, loss: 0.06766758114099503
2023-01-23 00:46:21.395162: step: 720/533, loss: 0.095367431640625
2023-01-23 00:46:22.595591: step: 724/533, loss: 0.3103080689907074
2023-01-23 00:46:23.813763: step: 728/533, loss: 0.06444225460290909
2023-01-23 00:46:25.032388: step: 732/533, loss: 0.24143868684768677
2023-01-23 00:46:26.191584: step: 736/533, loss: 0.07462029904127121
2023-01-23 00:46:27.403944: step: 740/533, loss: 0.17867432534694672
2023-01-23 00:46:28.557791: step: 744/533, loss: 0.0874989926815033
2023-01-23 00:46:29.764334: step: 748/533, loss: 0.04517421871423721
2023-01-23 00:46:30.926056: step: 752/533, loss: 0.3197963535785675
2023-01-23 00:46:32.102162: step: 756/533, loss: 0.062395237386226654
2023-01-23 00:46:33.266425: step: 760/533, loss: 0.007513904944062233
2023-01-23 00:46:34.427292: step: 764/533, loss: 0.06632880866527557
2023-01-23 00:46:35.625537: step: 768/533, loss: 0.014541245065629482
2023-01-23 00:46:36.773425: step: 772/533, loss: 0.20517253875732422
2023-01-23 00:46:37.995117: step: 776/533, loss: 0.04048910364508629
2023-01-23 00:46:39.174376: step: 780/533, loss: 0.1029973104596138
2023-01-23 00:46:40.360561: step: 784/533, loss: 0.41770344972610474
2023-01-23 00:46:41.518104: step: 788/533, loss: 0.13063812255859375
2023-01-23 00:46:42.668831: step: 792/533, loss: 0.058751873672008514
2023-01-23 00:46:43.847100: step: 796/533, loss: 0.1576654464006424
2023-01-23 00:46:45.028043: step: 800/533, loss: 0.020013142377138138
2023-01-23 00:46:46.201466: step: 804/533, loss: 0.17426013946533203
2023-01-23 00:46:47.385873: step: 808/533, loss: 0.10956916958093643
2023-01-23 00:46:48.543220: step: 812/533, loss: 0.031053420156240463
2023-01-23 00:46:49.763557: step: 816/533, loss: 0.040668584406375885
2023-01-23 00:46:50.913027: step: 820/533, loss: 0.04122123867273331
2023-01-23 00:46:52.107256: step: 824/533, loss: 0.0990133285522461
2023-01-23 00:46:53.232915: step: 828/533, loss: 0.14162521064281464
2023-01-23 00:46:54.399199: step: 832/533, loss: 0.11816645413637161
2023-01-23 00:46:55.569733: step: 836/533, loss: 0.05524645000696182
2023-01-23 00:46:56.717583: step: 840/533, loss: 0.0916467159986496
2023-01-23 00:46:57.891905: step: 844/533, loss: 0.1974247395992279
2023-01-23 00:46:59.073315: step: 848/533, loss: 0.7947461605072021
2023-01-23 00:47:00.248918: step: 852/533, loss: 0.15344282984733582
2023-01-23 00:47:01.466541: step: 856/533, loss: 0.3938547968864441
2023-01-23 00:47:02.651599: step: 860/533, loss: 0.06485573947429657
2023-01-23 00:47:03.816640: step: 864/533, loss: 0.05940370634198189
2023-01-23 00:47:05.003342: step: 868/533, loss: 0.022136593237519264
2023-01-23 00:47:06.198519: step: 872/533, loss: 0.12865644693374634
2023-01-23 00:47:07.353315: step: 876/533, loss: 0.3195739686489105
2023-01-23 00:47:08.538559: step: 880/533, loss: 0.39717569947242737
2023-01-23 00:47:09.727449: step: 884/533, loss: 0.05437278747558594
2023-01-23 00:47:10.873318: step: 888/533, loss: 0.3693615794181824
2023-01-23 00:47:12.061640: step: 892/533, loss: 0.4145874083042145
2023-01-23 00:47:13.247339: step: 896/533, loss: 0.10774698108434677
2023-01-23 00:47:14.399566: step: 900/533, loss: 0.01544121466577053
2023-01-23 00:47:15.563035: step: 904/533, loss: 0.35072413086891174
2023-01-23 00:47:16.747742: step: 908/533, loss: 0.399954229593277
2023-01-23 00:47:17.935784: step: 912/533, loss: 0.049668122082948685
2023-01-23 00:47:19.122779: step: 916/533, loss: 0.17268256843090057
2023-01-23 00:47:20.311526: step: 920/533, loss: 0.614274263381958
2023-01-23 00:47:21.481600: step: 924/533, loss: 0.17506122589111328
2023-01-23 00:47:22.665210: step: 928/533, loss: 0.7478906512260437
2023-01-23 00:47:23.824029: step: 932/533, loss: 0.12009774148464203
2023-01-23 00:47:25.021609: step: 936/533, loss: 0.22066831588745117
2023-01-23 00:47:26.179478: step: 940/533, loss: 0.31020450592041016
2023-01-23 00:47:27.370486: step: 944/533, loss: 0.04259634017944336
2023-01-23 00:47:28.597457: step: 948/533, loss: 0.03404679149389267
2023-01-23 00:47:29.825419: step: 952/533, loss: 0.11127567291259766
2023-01-23 00:47:31.019060: step: 956/533, loss: 0.049219321459531784
2023-01-23 00:47:32.225671: step: 960/533, loss: 0.14533177018165588
2023-01-23 00:47:33.393518: step: 964/533, loss: 0.059020426124334335
2023-01-23 00:47:34.595558: step: 968/533, loss: 0.12678509950637817
2023-01-23 00:47:35.780403: step: 972/533, loss: 0.055660344660282135
2023-01-23 00:47:36.983135: step: 976/533, loss: 0.09729135036468506
2023-01-23 00:47:38.205584: step: 980/533, loss: 0.14687786996364594
2023-01-23 00:47:39.415560: step: 984/533, loss: 0.06933341175317764
2023-01-23 00:47:40.584524: step: 988/533, loss: 0.15269014239311218
2023-01-23 00:47:41.734894: step: 992/533, loss: 0.03150606155395508
2023-01-23 00:47:42.897241: step: 996/533, loss: 0.2112255096435547
2023-01-23 00:47:44.055098: step: 1000/533, loss: 0.07571356743574142
2023-01-23 00:47:45.239981: step: 1004/533, loss: 0.031698036938905716
2023-01-23 00:47:46.431582: step: 1008/533, loss: 0.025605155155062675
2023-01-23 00:47:47.653680: step: 1012/533, loss: 0.021311093121767044
2023-01-23 00:47:48.827250: step: 1016/533, loss: 0.26800423860549927
2023-01-23 00:47:50.066911: step: 1020/533, loss: 0.18607187271118164
2023-01-23 00:47:51.271255: step: 1024/533, loss: 0.09499606490135193
2023-01-23 00:47:52.472462: step: 1028/533, loss: 0.04922132194042206
2023-01-23 00:47:53.656708: step: 1032/533, loss: 0.060540199279785156
2023-01-23 00:47:54.794000: step: 1036/533, loss: 0.013698672875761986
2023-01-23 00:47:56.017826: step: 1040/533, loss: 0.08650960773229599
2023-01-23 00:47:57.188915: step: 1044/533, loss: 0.08960485458374023
2023-01-23 00:47:58.359250: step: 1048/533, loss: 0.16634587943553925
2023-01-23 00:47:59.533431: step: 1052/533, loss: 0.14437341690063477
2023-01-23 00:48:00.726196: step: 1056/533, loss: 0.07751629501581192
2023-01-23 00:48:01.919626: step: 1060/533, loss: 0.08586493134498596
2023-01-23 00:48:03.059794: step: 1064/533, loss: 0.1762179434299469
2023-01-23 00:48:04.207402: step: 1068/533, loss: 0.03575735166668892
2023-01-23 00:48:05.447658: step: 1072/533, loss: 0.11446776241064072
2023-01-23 00:48:06.642793: step: 1076/533, loss: 0.15126128494739532
2023-01-23 00:48:07.777432: step: 1080/533, loss: 0.14959660172462463
2023-01-23 00:48:08.936252: step: 1084/533, loss: 0.07745137065649033
2023-01-23 00:48:10.113604: step: 1088/533, loss: 0.005724430549889803
2023-01-23 00:48:11.284317: step: 1092/533, loss: 0.5174845457077026
2023-01-23 00:48:12.455989: step: 1096/533, loss: 0.1122356504201889
2023-01-23 00:48:13.615944: step: 1100/533, loss: 0.10003185272216797
2023-01-23 00:48:14.739450: step: 1104/533, loss: 0.005584716796875
2023-01-23 00:48:15.957586: step: 1108/533, loss: 0.7720202207565308
2023-01-23 00:48:17.150424: step: 1112/533, loss: 0.5403192043304443
2023-01-23 00:48:18.329005: step: 1116/533, loss: 0.35966265201568604
2023-01-23 00:48:19.525288: step: 1120/533, loss: 0.12716464698314667
2023-01-23 00:48:20.716791: step: 1124/533, loss: 0.17202362418174744
2023-01-23 00:48:21.873931: step: 1128/533, loss: 0.016559697687625885
2023-01-23 00:48:23.021091: step: 1132/533, loss: 0.15614385902881622
2023-01-23 00:48:24.230089: step: 1136/533, loss: 0.9566184878349304
2023-01-23 00:48:25.466294: step: 1140/533, loss: 0.1273021250963211
2023-01-23 00:48:26.628222: step: 1144/533, loss: 0.0437101349234581
2023-01-23 00:48:27.803569: step: 1148/533, loss: 0.03266763687133789
2023-01-23 00:48:28.989025: step: 1152/533, loss: 0.06007976830005646
2023-01-23 00:48:30.172697: step: 1156/533, loss: 0.05297403410077095
2023-01-23 00:48:31.329736: step: 1160/533, loss: 0.06830110400915146
2023-01-23 00:48:32.498639: step: 1164/533, loss: 0.07320580631494522
2023-01-23 00:48:33.713406: step: 1168/533, loss: 0.40680330991744995
2023-01-23 00:48:34.877508: step: 1172/533, loss: 0.13231736421585083
2023-01-23 00:48:36.020779: step: 1176/533, loss: 0.018236160278320312
2023-01-23 00:48:37.229216: step: 1180/533, loss: 0.10143108665943146
2023-01-23 00:48:38.374298: step: 1184/533, loss: 0.26360803842544556
2023-01-23 00:48:39.526797: step: 1188/533, loss: 0.1318511962890625
2023-01-23 00:48:40.653954: step: 1192/533, loss: 0.05794224888086319
2023-01-23 00:48:41.840534: step: 1196/533, loss: 0.2904471457004547
2023-01-23 00:48:43.042321: step: 1200/533, loss: 0.08380518108606339
2023-01-23 00:48:44.249833: step: 1204/533, loss: 0.19169996678829193
2023-01-23 00:48:45.392369: step: 1208/533, loss: 0.134568989276886
2023-01-23 00:48:46.574901: step: 1212/533, loss: 0.08094777911901474
2023-01-23 00:48:47.760516: step: 1216/533, loss: 0.2527502179145813
2023-01-23 00:48:48.938442: step: 1220/533, loss: 0.09208475798368454
2023-01-23 00:48:50.124428: step: 1224/533, loss: 0.25244027376174927
2023-01-23 00:48:51.325676: step: 1228/533, loss: 0.06860509514808655
2023-01-23 00:48:52.477604: step: 1232/533, loss: 0.1862872987985611
2023-01-23 00:48:53.672961: step: 1236/533, loss: 0.7058597207069397
2023-01-23 00:48:54.834232: step: 1240/533, loss: 0.02703228034079075
2023-01-23 00:48:56.033671: step: 1244/533, loss: 0.689183235168457
2023-01-23 00:48:57.208989: step: 1248/533, loss: 0.10156326740980148
2023-01-23 00:48:58.364976: step: 1252/533, loss: 0.11410484462976456
2023-01-23 00:48:59.587503: step: 1256/533, loss: 0.14767113327980042
2023-01-23 00:49:00.768847: step: 1260/533, loss: 0.0669654831290245
2023-01-23 00:49:01.935669: step: 1264/533, loss: 0.17472442984580994
2023-01-23 00:49:03.133613: step: 1268/533, loss: 0.07428856194019318
2023-01-23 00:49:04.301768: step: 1272/533, loss: 0.0847872719168663
2023-01-23 00:49:05.468416: step: 1276/533, loss: 0.019122647121548653
2023-01-23 00:49:06.637523: step: 1280/533, loss: 0.07606898248195648
2023-01-23 00:49:07.846449: step: 1284/533, loss: 0.6748707294464111
2023-01-23 00:49:09.045418: step: 1288/533, loss: 0.015431642532348633
2023-01-23 00:49:10.247458: step: 1292/533, loss: 0.19803038239479065
2023-01-23 00:49:11.398423: step: 1296/533, loss: 0.011018085293471813
2023-01-23 00:49:12.599828: step: 1300/533, loss: 0.2448538839817047
2023-01-23 00:49:13.737358: step: 1304/533, loss: 0.04956841468811035
2023-01-23 00:49:14.960362: step: 1308/533, loss: 0.039197683334350586
2023-01-23 00:49:16.152368: step: 1312/533, loss: 0.07702169567346573
2023-01-23 00:49:17.310824: step: 1316/533, loss: 0.2669532895088196
2023-01-23 00:49:18.466651: step: 1320/533, loss: 0.7712525725364685
2023-01-23 00:49:19.637877: step: 1324/533, loss: 0.2272128164768219
2023-01-23 00:49:20.822812: step: 1328/533, loss: 0.05593233183026314
2023-01-23 00:49:22.028235: step: 1332/533, loss: 0.04806847870349884
2023-01-23 00:49:23.197702: step: 1336/533, loss: 0.03831439092755318
2023-01-23 00:49:24.395673: step: 1340/533, loss: 0.09763441234827042
2023-01-23 00:49:25.608621: step: 1344/533, loss: 0.19350768625736237
2023-01-23 00:49:26.794473: step: 1348/533, loss: 0.22850441932678223
2023-01-23 00:49:28.085525: step: 1352/533, loss: 0.20074662566184998
2023-01-23 00:49:29.254327: step: 1356/533, loss: 0.2425546646118164
2023-01-23 00:49:30.426976: step: 1360/533, loss: 0.017459489405155182
2023-01-23 00:49:31.585125: step: 1364/533, loss: 0.12814387679100037
2023-01-23 00:49:32.791315: step: 1368/533, loss: 0.13456392288208008
2023-01-23 00:49:33.960925: step: 1372/533, loss: 0.02603388950228691
2023-01-23 00:49:35.112457: step: 1376/533, loss: 0.023082830011844635
2023-01-23 00:49:36.315601: step: 1380/533, loss: 0.85345458984375
2023-01-23 00:49:37.486805: step: 1384/533, loss: 0.05691461265087128
2023-01-23 00:49:38.681295: step: 1388/533, loss: 0.08820381760597229
2023-01-23 00:49:39.882830: step: 1392/533, loss: 0.6441293954849243
2023-01-23 00:49:41.067638: step: 1396/533, loss: 0.1557263433933258
2023-01-23 00:49:42.208945: step: 1400/533, loss: 2.3298323154449463
2023-01-23 00:49:43.351618: step: 1404/533, loss: 0.05295753479003906
2023-01-23 00:49:44.519839: step: 1408/533, loss: 0.09047737717628479
2023-01-23 00:49:45.769839: step: 1412/533, loss: 0.07927742600440979
2023-01-23 00:49:46.936544: step: 1416/533, loss: 0.01557533722370863
2023-01-23 00:49:48.112649: step: 1420/533, loss: 0.17565536499023438
2023-01-23 00:49:49.338249: step: 1424/533, loss: 0.12403789162635803
2023-01-23 00:49:50.530086: step: 1428/533, loss: 0.06530608981847763
2023-01-23 00:49:51.657477: step: 1432/533, loss: 0.11824546009302139
2023-01-23 00:49:52.828330: step: 1436/533, loss: 0.061544135212898254
2023-01-23 00:49:54.001136: step: 1440/533, loss: 0.135945126414299
2023-01-23 00:49:55.206371: step: 1444/533, loss: 0.33694860339164734
2023-01-23 00:49:56.379493: step: 1448/533, loss: 0.16456662118434906
2023-01-23 00:49:57.528940: step: 1452/533, loss: 0.0867166519165039
2023-01-23 00:49:58.696663: step: 1456/533, loss: 0.13213959336280823
2023-01-23 00:49:59.917797: step: 1460/533, loss: 0.07199926674365997
2023-01-23 00:50:01.082695: step: 1464/533, loss: 0.29781877994537354
2023-01-23 00:50:02.297725: step: 1468/533, loss: 0.056651026010513306
2023-01-23 00:50:03.477858: step: 1472/533, loss: 0.3756037652492523
2023-01-23 00:50:04.664340: step: 1476/533, loss: 0.14920340478420258
2023-01-23 00:50:05.845773: step: 1480/533, loss: 0.10907058417797089
2023-01-23 00:50:07.013091: step: 1484/533, loss: 0.3637380301952362
2023-01-23 00:50:08.199748: step: 1488/533, loss: 0.922110915184021
2023-01-23 00:50:09.377836: step: 1492/533, loss: 0.22944754362106323
2023-01-23 00:50:10.573587: step: 1496/533, loss: 0.01664004474878311
2023-01-23 00:50:11.758979: step: 1500/533, loss: 0.13072019815444946
2023-01-23 00:50:12.999133: step: 1504/533, loss: 0.14062805473804474
2023-01-23 00:50:14.179684: step: 1508/533, loss: 0.09868965297937393
2023-01-23 00:50:15.393573: step: 1512/533, loss: 0.2841409742832184
2023-01-23 00:50:16.590123: step: 1516/533, loss: 0.07551197707653046
2023-01-23 00:50:17.849261: step: 1520/533, loss: 0.26093220710754395
2023-01-23 00:50:19.042897: step: 1524/533, loss: 0.0073053836822509766
2023-01-23 00:50:20.187325: step: 1528/533, loss: 0.41684991121292114
2023-01-23 00:50:21.367189: step: 1532/533, loss: 0.077867791056633
2023-01-23 00:50:22.546245: step: 1536/533, loss: 0.2675896883010864
2023-01-23 00:50:23.748005: step: 1540/533, loss: 0.1291884481906891
2023-01-23 00:50:24.911844: step: 1544/533, loss: 0.06301793456077576
2023-01-23 00:50:26.124275: step: 1548/533, loss: 0.1364070028066635
2023-01-23 00:50:27.264673: step: 1552/533, loss: 0.10266055911779404
2023-01-23 00:50:28.451086: step: 1556/533, loss: 0.008716249838471413
2023-01-23 00:50:29.648272: step: 1560/533, loss: 0.3959083557128906
2023-01-23 00:50:30.790175: step: 1564/533, loss: 0.03552446514368057
2023-01-23 00:50:31.963998: step: 1568/533, loss: 0.061426304280757904
2023-01-23 00:50:33.165356: step: 1572/533, loss: 0.006771659944206476
2023-01-23 00:50:34.312361: step: 1576/533, loss: 0.09923876821994781
2023-01-23 00:50:35.469137: step: 1580/533, loss: 0.09676344692707062
2023-01-23 00:50:36.624604: step: 1584/533, loss: 0.0769491195678711
2023-01-23 00:50:37.804932: step: 1588/533, loss: 0.14762984216213226
2023-01-23 00:50:38.978788: step: 1592/533, loss: 0.0663335770368576
2023-01-23 00:50:40.196869: step: 1596/533, loss: 0.6944124698638916
2023-01-23 00:50:41.415619: step: 1600/533, loss: 0.08068704605102539
2023-01-23 00:50:42.573538: step: 1604/533, loss: 0.07248697429895401
2023-01-23 00:50:43.733123: step: 1608/533, loss: 0.12503671646118164
2023-01-23 00:50:44.876168: step: 1612/533, loss: 0.0302626620978117
2023-01-23 00:50:46.025000: step: 1616/533, loss: 0.06951122730970383
2023-01-23 00:50:47.212076: step: 1620/533, loss: 0.43427911400794983
2023-01-23 00:50:48.369101: step: 1624/533, loss: 0.09474726021289825
2023-01-23 00:50:49.542698: step: 1628/533, loss: 0.026811406016349792
2023-01-23 00:50:50.700464: step: 1632/533, loss: 0.11235599219799042
2023-01-23 00:50:51.893182: step: 1636/533, loss: 0.10576677322387695
2023-01-23 00:50:53.062409: step: 1640/533, loss: 0.14707250893115997
2023-01-23 00:50:54.241760: step: 1644/533, loss: 0.023218631744384766
2023-01-23 00:50:55.423709: step: 1648/533, loss: 0.04017763212323189
2023-01-23 00:50:56.606149: step: 1652/533, loss: 0.2986489236354828
2023-01-23 00:50:57.745832: step: 1656/533, loss: 0.06629820168018341
2023-01-23 00:50:58.913141: step: 1660/533, loss: 0.25984689593315125
2023-01-23 00:51:00.077416: step: 1664/533, loss: 0.10866174846887589
2023-01-23 00:51:01.228603: step: 1668/533, loss: 0.46603700518608093
2023-01-23 00:51:02.393522: step: 1672/533, loss: 0.05942163243889809
2023-01-23 00:51:03.550474: step: 1676/533, loss: 0.11981496959924698
2023-01-23 00:51:04.679463: step: 1680/533, loss: 0.17088022828102112
2023-01-23 00:51:05.885584: step: 1684/533, loss: 0.05519905686378479
2023-01-23 00:51:07.044526: step: 1688/533, loss: 0.06767778098583221
2023-01-23 00:51:08.223337: step: 1692/533, loss: 0.03444407135248184
2023-01-23 00:51:09.396049: step: 1696/533, loss: 0.0202044490724802
2023-01-23 00:51:10.582853: step: 1700/533, loss: 0.016474580392241478
2023-01-23 00:51:11.774579: step: 1704/533, loss: 0.09185848385095596
2023-01-23 00:51:12.919279: step: 1708/533, loss: 0.23659612238407135
2023-01-23 00:51:14.104034: step: 1712/533, loss: 0.5814775228500366
2023-01-23 00:51:15.286963: step: 1716/533, loss: 0.07386360317468643
2023-01-23 00:51:16.488931: step: 1720/533, loss: 1.4356608390808105
2023-01-23 00:51:17.672415: step: 1724/533, loss: 0.08315916359424591
2023-01-23 00:51:18.842592: step: 1728/533, loss: 0.34634724259376526
2023-01-23 00:51:19.990816: step: 1732/533, loss: 0.060264021158218384
2023-01-23 00:51:21.164993: step: 1736/533, loss: 0.0956021100282669
2023-01-23 00:51:22.323559: step: 1740/533, loss: 0.10569701343774796
2023-01-23 00:51:23.543287: step: 1744/533, loss: 0.14919549226760864
2023-01-23 00:51:24.711735: step: 1748/533, loss: 0.13188667595386505
2023-01-23 00:51:25.921502: step: 1752/533, loss: 0.13377352058887482
2023-01-23 00:51:27.116985: step: 1756/533, loss: 0.09226135909557343
2023-01-23 00:51:28.297283: step: 1760/533, loss: 0.12719126045703888
2023-01-23 00:51:29.480233: step: 1764/533, loss: 0.13516291975975037
2023-01-23 00:51:30.677183: step: 1768/533, loss: 0.14136266708374023
2023-01-23 00:51:31.855333: step: 1772/533, loss: 0.08780984580516815
2023-01-23 00:51:33.038022: step: 1776/533, loss: 0.09126882255077362
2023-01-23 00:51:34.240632: step: 1780/533, loss: 0.19873599708080292
2023-01-23 00:51:35.430222: step: 1784/533, loss: 0.16518214344978333
2023-01-23 00:51:36.640090: step: 1788/533, loss: 0.08995547890663147
2023-01-23 00:51:37.876449: step: 1792/533, loss: 0.1451520472764969
2023-01-23 00:51:39.065472: step: 1796/533, loss: 0.5091859698295593
2023-01-23 00:51:40.269851: step: 1800/533, loss: 0.3400367796421051
2023-01-23 00:51:41.452358: step: 1804/533, loss: 0.5751129388809204
2023-01-23 00:51:42.617123: step: 1808/533, loss: 0.13906565308570862
2023-01-23 00:51:43.815457: step: 1812/533, loss: 0.04004368931055069
2023-01-23 00:51:45.005184: step: 1816/533, loss: 0.5197814702987671
2023-01-23 00:51:46.181976: step: 1820/533, loss: 0.058991577476263046
2023-01-23 00:51:47.328495: step: 1824/533, loss: 0.19924607872962952
2023-01-23 00:51:48.554804: step: 1828/533, loss: 0.4027549922466278
2023-01-23 00:51:49.772616: step: 1832/533, loss: 0.25962895154953003
2023-01-23 00:51:50.950805: step: 1836/533, loss: 0.022650720551609993
2023-01-23 00:51:52.114429: step: 1840/533, loss: 0.10708286613225937
2023-01-23 00:51:53.286626: step: 1844/533, loss: 0.10166168212890625
2023-01-23 00:51:54.439698: step: 1848/533, loss: 0.02556152269244194
2023-01-23 00:51:55.623658: step: 1852/533, loss: 0.4256401062011719
2023-01-23 00:51:56.818108: step: 1856/533, loss: 0.06053295359015465
2023-01-23 00:51:58.011210: step: 1860/533, loss: 0.1242123693227768
2023-01-23 00:51:59.207594: step: 1864/533, loss: 0.2137494683265686
2023-01-23 00:52:00.398762: step: 1868/533, loss: 0.10713911056518555
2023-01-23 00:52:01.571691: step: 1872/533, loss: 0.13193221390247345
2023-01-23 00:52:02.758911: step: 1876/533, loss: 0.400832861661911
2023-01-23 00:52:03.910052: step: 1880/533, loss: 0.06214485317468643
2023-01-23 00:52:05.096638: step: 1884/533, loss: 0.13905023038387299
2023-01-23 00:52:06.252244: step: 1888/533, loss: 0.04362001270055771
2023-01-23 00:52:07.448848: step: 1892/533, loss: 0.3122302293777466
2023-01-23 00:52:08.640504: step: 1896/533, loss: 0.03895587846636772
2023-01-23 00:52:09.796491: step: 1900/533, loss: 0.15119047462940216
2023-01-23 00:52:10.976217: step: 1904/533, loss: 0.6767929196357727
2023-01-23 00:52:12.144849: step: 1908/533, loss: 0.25180110335350037
2023-01-23 00:52:13.326010: step: 1912/533, loss: 0.1086040511727333
2023-01-23 00:52:14.528837: step: 1916/533, loss: 0.19573555886745453
2023-01-23 00:52:15.667469: step: 1920/533, loss: 0.16889649629592896
2023-01-23 00:52:16.832692: step: 1924/533, loss: 0.3492767810821533
2023-01-23 00:52:17.979251: step: 1928/533, loss: 0.060495663434267044
2023-01-23 00:52:19.176526: step: 1932/533, loss: 0.26421308517456055
2023-01-23 00:52:20.368372: step: 1936/533, loss: 0.2601969838142395
2023-01-23 00:52:21.519092: step: 1940/533, loss: 0.09201221913099289
2023-01-23 00:52:22.704151: step: 1944/533, loss: 0.15824276208877563
2023-01-23 00:52:23.882663: step: 1948/533, loss: 0.10685815662145615
2023-01-23 00:52:25.067075: step: 1952/533, loss: 0.030006123706698418
2023-01-23 00:52:26.263396: step: 1956/533, loss: 0.3846948742866516
2023-01-23 00:52:27.461102: step: 1960/533, loss: 0.07690100371837616
2023-01-23 00:52:28.608377: step: 1964/533, loss: 0.44955766201019287
2023-01-23 00:52:29.792344: step: 1968/533, loss: 0.13609905540943146
2023-01-23 00:52:30.969725: step: 1972/533, loss: 0.11102294921875
2023-01-23 00:52:32.184765: step: 1976/533, loss: 0.12062263488769531
2023-01-23 00:52:33.329409: step: 1980/533, loss: 0.32266101241111755
2023-01-23 00:52:34.514346: step: 1984/533, loss: 0.09616956859827042
2023-01-23 00:52:35.722833: step: 1988/533, loss: 0.1433626264333725
2023-01-23 00:52:36.892093: step: 1992/533, loss: 0.02000696025788784
2023-01-23 00:52:38.007657: step: 1996/533, loss: 0.021545404568314552
2023-01-23 00:52:39.220567: step: 2000/533, loss: 0.0699489563703537
2023-01-23 00:52:40.382106: step: 2004/533, loss: 0.12893332540988922
2023-01-23 00:52:41.544204: step: 2008/533, loss: 0.05516872555017471
2023-01-23 00:52:42.699919: step: 2012/533, loss: 0.07231850922107697
2023-01-23 00:52:43.874446: step: 2016/533, loss: 0.11212797462940216
2023-01-23 00:52:45.073212: step: 2020/533, loss: 0.04125042259693146
2023-01-23 00:52:46.275900: step: 2024/533, loss: 0.13496848940849304
2023-01-23 00:52:47.461478: step: 2028/533, loss: 0.04353313520550728
2023-01-23 00:52:48.600155: step: 2032/533, loss: 0.04877294600009918
2023-01-23 00:52:49.776928: step: 2036/533, loss: 0.08072672039270401
2023-01-23 00:52:50.940316: step: 2040/533, loss: 0.4876982569694519
2023-01-23 00:52:52.088990: step: 2044/533, loss: 0.024735068902373314
2023-01-23 00:52:53.238735: step: 2048/533, loss: 0.030648136511445045
2023-01-23 00:52:54.425624: step: 2052/533, loss: 0.6002691984176636
2023-01-23 00:52:55.617115: step: 2056/533, loss: 0.04818249121308327
2023-01-23 00:52:56.839036: step: 2060/533, loss: 0.04724721983075142
2023-01-23 00:52:58.001223: step: 2064/533, loss: 0.02690756320953369
2023-01-23 00:52:59.152649: step: 2068/533, loss: 0.08322863280773163
2023-01-23 00:53:00.339807: step: 2072/533, loss: 0.1908152550458908
2023-01-23 00:53:01.547874: step: 2076/533, loss: 0.21371030807495117
2023-01-23 00:53:02.744781: step: 2080/533, loss: 0.07740859687328339
2023-01-23 00:53:03.938037: step: 2084/533, loss: 0.056576963514089584
2023-01-23 00:53:05.151377: step: 2088/533, loss: 0.09218082576990128
2023-01-23 00:53:06.363304: step: 2092/533, loss: 0.8551380038261414
2023-01-23 00:53:07.520945: step: 2096/533, loss: 0.1529284417629242
2023-01-23 00:53:08.664365: step: 2100/533, loss: 0.031125929206609726
2023-01-23 00:53:09.851233: step: 2104/533, loss: 0.041991040110588074
2023-01-23 00:53:11.045012: step: 2108/533, loss: 0.022683238610625267
2023-01-23 00:53:12.217686: step: 2112/533, loss: 0.12014572322368622
2023-01-23 00:53:13.392517: step: 2116/533, loss: 0.22935214638710022
2023-01-23 00:53:14.604170: step: 2120/533, loss: 0.07466840744018555
2023-01-23 00:53:15.772460: step: 2124/533, loss: 0.1327281892299652
2023-01-23 00:53:16.935890: step: 2128/533, loss: 0.3902902603149414
2023-01-23 00:53:18.094328: step: 2132/533, loss: 0.17620038986206055
==================================================
Loss: 0.179
--------------------
Dev: {'event': {'p': 0.5535714285714286, 'r': 0.7842876165113183, 'f1': 0.6490358126721764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6090335114133074, 'r': 0.8017902813299232, 'f1': 0.6922439966878277}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5268817204301075, 'r': 0.9074074074074074, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.5714285714285714, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.46511627906976744, 'r': 0.5555555555555556, 'f1': 0.5063291139240507}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:53:59.199243: step: 4/533, loss: 0.6840684413909912
2023-01-23 00:54:00.375292: step: 8/533, loss: 0.19611205160617828
2023-01-23 00:54:01.505250: step: 12/533, loss: 0.04957152530550957
2023-01-23 00:54:02.641579: step: 16/533, loss: 0.07229804992675781
2023-01-23 00:54:03.813130: step: 20/533, loss: 0.06724605709314346
2023-01-23 00:54:05.012002: step: 24/533, loss: 0.03101954609155655
2023-01-23 00:54:06.175683: step: 28/533, loss: 0.03050823137164116
2023-01-23 00:54:07.330846: step: 32/533, loss: 0.23211756348609924
2023-01-23 00:54:08.508106: step: 36/533, loss: 0.15388011932373047
2023-01-23 00:54:09.666586: step: 40/533, loss: 0.05956144258379936
2023-01-23 00:54:10.884278: step: 44/533, loss: 0.09288463741540909
2023-01-23 00:54:12.087057: step: 48/533, loss: 0.02809920348227024
2023-01-23 00:54:13.289704: step: 52/533, loss: 0.1705632209777832
2023-01-23 00:54:14.449243: step: 56/533, loss: 0.036454200744628906
2023-01-23 00:54:15.607422: step: 60/533, loss: 0.06403279304504395
2023-01-23 00:54:16.765480: step: 64/533, loss: 0.07089615613222122
2023-01-23 00:54:17.904655: step: 68/533, loss: 0.0332825630903244
2023-01-23 00:54:19.066032: step: 72/533, loss: 0.05311160162091255
2023-01-23 00:54:20.223564: step: 76/533, loss: 0.076184943318367
2023-01-23 00:54:21.384827: step: 80/533, loss: 0.12787123024463654
2023-01-23 00:54:22.568926: step: 84/533, loss: 0.15155789256095886
2023-01-23 00:54:23.745361: step: 88/533, loss: 0.08287163823843002
2023-01-23 00:54:24.933510: step: 92/533, loss: 0.21548710763454437
2023-01-23 00:54:26.125722: step: 96/533, loss: 0.07911403477191925
2023-01-23 00:54:27.290962: step: 100/533, loss: 0.10535149276256561
2023-01-23 00:54:28.461089: step: 104/533, loss: 0.11290760338306427
2023-01-23 00:54:29.621389: step: 108/533, loss: 0.04956026002764702
2023-01-23 00:54:30.803278: step: 112/533, loss: 0.07664909213781357
2023-01-23 00:54:31.972780: step: 116/533, loss: 0.18215522170066833
2023-01-23 00:54:33.136778: step: 120/533, loss: 0.0694248229265213
2023-01-23 00:54:34.303060: step: 124/533, loss: 0.01795663870871067
2023-01-23 00:54:35.463632: step: 128/533, loss: 0.0804353728890419
2023-01-23 00:54:36.677460: step: 132/533, loss: 0.3450789749622345
2023-01-23 00:54:37.829392: step: 136/533, loss: 0.16633854806423187
2023-01-23 00:54:38.986969: step: 140/533, loss: 0.07037067413330078
2023-01-23 00:54:40.212800: step: 144/533, loss: 0.4730842709541321
2023-01-23 00:54:41.369195: step: 148/533, loss: 0.07848282158374786
2023-01-23 00:54:42.583443: step: 152/533, loss: 0.0747932642698288
2023-01-23 00:54:43.744311: step: 156/533, loss: 0.045522309839725494
2023-01-23 00:54:44.911842: step: 160/533, loss: 0.06635656207799911
2023-01-23 00:54:46.089423: step: 164/533, loss: 0.03924846649169922
2023-01-23 00:54:47.265429: step: 168/533, loss: 0.0030699074268341064
2023-01-23 00:54:48.408249: step: 172/533, loss: 0.011506748385727406
2023-01-23 00:54:49.596225: step: 176/533, loss: 0.05214982107281685
2023-01-23 00:54:50.750241: step: 180/533, loss: 0.012051582336425781
2023-01-23 00:54:51.918549: step: 184/533, loss: 0.08306588977575302
2023-01-23 00:54:53.093404: step: 188/533, loss: 0.03041238896548748
2023-01-23 00:54:54.289681: step: 192/533, loss: 0.21867509186267853
2023-01-23 00:54:55.455938: step: 196/533, loss: 0.053096964955329895
2023-01-23 00:54:56.624771: step: 200/533, loss: 0.016430282965302467
2023-01-23 00:54:57.809780: step: 204/533, loss: 0.08459319919347763
2023-01-23 00:54:58.984958: step: 208/533, loss: 0.07347631454467773
2023-01-23 00:55:00.139597: step: 212/533, loss: 0.04259805753827095
2023-01-23 00:55:01.324023: step: 216/533, loss: 0.05538778752088547
2023-01-23 00:55:02.528797: step: 220/533, loss: 0.055837154388427734
2023-01-23 00:55:03.713568: step: 224/533, loss: 0.009785771369934082
2023-01-23 00:55:04.861480: step: 228/533, loss: 0.31007400155067444
2023-01-23 00:55:06.042447: step: 232/533, loss: 0.04368572682142258
2023-01-23 00:55:07.206886: step: 236/533, loss: 0.013491630554199219
2023-01-23 00:55:08.382148: step: 240/533, loss: 0.11121578514575958
2023-01-23 00:55:09.566866: step: 244/533, loss: 0.040283918380737305
2023-01-23 00:55:10.740706: step: 248/533, loss: 0.062049105763435364
2023-01-23 00:55:11.923662: step: 252/533, loss: 0.1786242425441742
2023-01-23 00:55:13.123693: step: 256/533, loss: 0.02454845979809761
2023-01-23 00:55:14.332743: step: 260/533, loss: 0.0715000182390213
2023-01-23 00:55:15.536416: step: 264/533, loss: 0.059846021234989166
2023-01-23 00:55:16.697965: step: 268/533, loss: 0.08256607502698898
2023-01-23 00:55:17.893346: step: 272/533, loss: 0.13933268189430237
2023-01-23 00:55:19.065787: step: 276/533, loss: 0.05463256686925888
2023-01-23 00:55:20.219547: step: 280/533, loss: 0.04744548723101616
2023-01-23 00:55:21.406511: step: 284/533, loss: 0.03658599779009819
2023-01-23 00:55:22.539584: step: 288/533, loss: 0.06907138973474503
2023-01-23 00:55:23.675465: step: 292/533, loss: 0.00803365744650364
2023-01-23 00:55:24.876666: step: 296/533, loss: 0.10439768433570862
2023-01-23 00:55:26.070901: step: 300/533, loss: 0.2719841003417969
2023-01-23 00:55:27.213749: step: 304/533, loss: 0.15916454792022705
2023-01-23 00:55:28.359716: step: 308/533, loss: 0.1406663954257965
2023-01-23 00:55:29.550739: step: 312/533, loss: 0.07233677059412003
2023-01-23 00:55:30.712378: step: 316/533, loss: 0.059840667992830276
2023-01-23 00:55:31.913600: step: 320/533, loss: 0.005750083830207586
2023-01-23 00:55:33.068152: step: 324/533, loss: 0.19576987624168396
2023-01-23 00:55:34.242625: step: 328/533, loss: 0.04022081196308136
2023-01-23 00:55:35.411844: step: 332/533, loss: 0.07618796825408936
2023-01-23 00:55:36.607854: step: 336/533, loss: 0.04661369323730469
2023-01-23 00:55:37.840996: step: 340/533, loss: 0.15816710889339447
2023-01-23 00:55:39.030010: step: 344/533, loss: 0.062172770500183105
2023-01-23 00:55:40.241765: step: 348/533, loss: 0.11814107745885849
2023-01-23 00:55:41.364457: step: 352/533, loss: 0.005133724305778742
2023-01-23 00:55:42.510186: step: 356/533, loss: 0.1578054428100586
2023-01-23 00:55:43.673158: step: 360/533, loss: 0.04465850442647934
2023-01-23 00:55:44.856503: step: 364/533, loss: 0.04959249496459961
2023-01-23 00:55:46.007493: step: 368/533, loss: 0.07189063727855682
2023-01-23 00:55:47.160791: step: 372/533, loss: 0.1457217037677765
2023-01-23 00:55:48.321052: step: 376/533, loss: 0.027528857812285423
2023-01-23 00:55:49.491499: step: 380/533, loss: 0.01366500835865736
2023-01-23 00:55:50.672003: step: 384/533, loss: 0.002990341279655695
2023-01-23 00:55:51.835802: step: 388/533, loss: 1.1891587972640991
2023-01-23 00:55:53.021983: step: 392/533, loss: 0.07135549187660217
2023-01-23 00:55:54.205424: step: 396/533, loss: 0.13265901803970337
2023-01-23 00:55:55.414142: step: 400/533, loss: 0.09585314244031906
2023-01-23 00:55:56.595464: step: 404/533, loss: 0.018650341778993607
2023-01-23 00:55:57.785840: step: 408/533, loss: 0.41071557998657227
2023-01-23 00:55:58.924917: step: 412/533, loss: 0.11216192692518234
2023-01-23 00:56:00.126511: step: 416/533, loss: 0.19438429176807404
2023-01-23 00:56:01.294912: step: 420/533, loss: 0.036748696118593216
2023-01-23 00:56:02.497182: step: 424/533, loss: 0.06768226623535156
2023-01-23 00:56:03.669898: step: 428/533, loss: 0.09394869953393936
2023-01-23 00:56:04.849253: step: 432/533, loss: 0.15862369537353516
2023-01-23 00:56:06.053305: step: 436/533, loss: 0.13674621284008026
2023-01-23 00:56:07.214910: step: 440/533, loss: 0.11397209763526917
2023-01-23 00:56:08.382840: step: 444/533, loss: 0.08727769553661346
2023-01-23 00:56:09.576048: step: 448/533, loss: 0.12621507048606873
2023-01-23 00:56:10.729182: step: 452/533, loss: 0.054107144474983215
2023-01-23 00:56:11.949748: step: 456/533, loss: 0.15346698462963104
2023-01-23 00:56:13.093731: step: 460/533, loss: 0.3318294584751129
2023-01-23 00:56:14.262548: step: 464/533, loss: 0.21256455779075623
2023-01-23 00:56:15.416213: step: 468/533, loss: 0.004202795214951038
2023-01-23 00:56:16.608377: step: 472/533, loss: 0.17262953519821167
2023-01-23 00:56:17.752660: step: 476/533, loss: 0.03719501569867134
2023-01-23 00:56:18.915243: step: 480/533, loss: 0.09452610462903976
2023-01-23 00:56:20.100351: step: 484/533, loss: 0.17246972024440765
2023-01-23 00:56:21.332820: step: 488/533, loss: 0.03460388258099556
2023-01-23 00:56:22.491891: step: 492/533, loss: 0.9785146117210388
2023-01-23 00:56:23.642504: step: 496/533, loss: 0.11171851307153702
2023-01-23 00:56:24.786861: step: 500/533, loss: 0.02204873599112034
2023-01-23 00:56:25.978350: step: 504/533, loss: 0.04498577117919922
2023-01-23 00:56:27.188636: step: 508/533, loss: 0.041539859026670456
2023-01-23 00:56:28.383843: step: 512/533, loss: 0.031057119369506836
2023-01-23 00:56:29.547557: step: 516/533, loss: 0.059025704860687256
2023-01-23 00:56:30.764236: step: 520/533, loss: 0.09988422691822052
2023-01-23 00:56:31.970689: step: 524/533, loss: 0.08969402313232422
2023-01-23 00:56:33.168499: step: 528/533, loss: 0.09846248477697372
2023-01-23 00:56:34.310429: step: 532/533, loss: 0.02994859218597412
2023-01-23 00:56:35.453490: step: 536/533, loss: 0.031388092786073685
2023-01-23 00:56:36.586865: step: 540/533, loss: 0.12991762161254883
2023-01-23 00:56:37.770616: step: 544/533, loss: 0.17067213356494904
2023-01-23 00:56:38.915632: step: 548/533, loss: 0.22777089476585388
2023-01-23 00:56:40.110346: step: 552/533, loss: 0.09216437488794327
2023-01-23 00:56:41.286889: step: 556/533, loss: 0.12074422836303711
2023-01-23 00:56:42.422850: step: 560/533, loss: 0.12821780145168304
2023-01-23 00:56:43.553630: step: 564/533, loss: 0.3531808853149414
2023-01-23 00:56:44.745412: step: 568/533, loss: 1.0519897937774658
2023-01-23 00:56:45.892635: step: 572/533, loss: 0.0063069346360862255
2023-01-23 00:56:47.053509: step: 576/533, loss: 0.04196124151349068
2023-01-23 00:56:48.245887: step: 580/533, loss: 0.17628784477710724
2023-01-23 00:56:49.406985: step: 584/533, loss: 0.12298412621021271
2023-01-23 00:56:50.559281: step: 588/533, loss: 0.1853950023651123
2023-01-23 00:56:51.749500: step: 592/533, loss: 0.11240754276514053
2023-01-23 00:56:52.898232: step: 596/533, loss: 0.16599902510643005
2023-01-23 00:56:54.103394: step: 600/533, loss: 0.1002839133143425
2023-01-23 00:56:55.265353: step: 604/533, loss: 0.03844108805060387
2023-01-23 00:56:56.413692: step: 608/533, loss: 0.0167099479585886
2023-01-23 00:56:57.661428: step: 612/533, loss: 0.03913535922765732
2023-01-23 00:56:58.804540: step: 616/533, loss: 0.08450829982757568
2023-01-23 00:57:00.012097: step: 620/533, loss: 0.012268638238310814
2023-01-23 00:57:01.184208: step: 624/533, loss: 0.056078244000673294
2023-01-23 00:57:02.366534: step: 628/533, loss: 0.48550042510032654
2023-01-23 00:57:03.543902: step: 632/533, loss: 1.5149446725845337
2023-01-23 00:57:04.732749: step: 636/533, loss: 0.28021401166915894
2023-01-23 00:57:05.924233: step: 640/533, loss: 0.07205267250537872
2023-01-23 00:57:07.108790: step: 644/533, loss: 0.14142942428588867
2023-01-23 00:57:08.304175: step: 648/533, loss: 0.3264802098274231
2023-01-23 00:57:09.497063: step: 652/533, loss: 0.17765235900878906
2023-01-23 00:57:10.646721: step: 656/533, loss: 0.005532455630600452
2023-01-23 00:57:11.838323: step: 660/533, loss: 0.03502330929040909
2023-01-23 00:57:13.025662: step: 664/533, loss: 0.7579852342605591
2023-01-23 00:57:14.204489: step: 668/533, loss: 0.1398542821407318
2023-01-23 00:57:15.366118: step: 672/533, loss: 0.05399642139673233
2023-01-23 00:57:16.550474: step: 676/533, loss: 0.19067582488059998
2023-01-23 00:57:17.721695: step: 680/533, loss: 0.24744835495948792
2023-01-23 00:57:18.880164: step: 684/533, loss: 0.11159972846508026
2023-01-23 00:57:20.060563: step: 688/533, loss: 0.02066049724817276
2023-01-23 00:57:21.233419: step: 692/533, loss: 0.06876301765441895
2023-01-23 00:57:22.390202: step: 696/533, loss: 0.03165634721517563
2023-01-23 00:57:23.572724: step: 700/533, loss: 0.07921639084815979
2023-01-23 00:57:24.739642: step: 704/533, loss: 0.010765934363007545
2023-01-23 00:57:25.942801: step: 708/533, loss: 0.21481665968894958
2023-01-23 00:57:27.098477: step: 712/533, loss: 0.24281997978687286
2023-01-23 00:57:28.293195: step: 716/533, loss: 0.11822627484798431
2023-01-23 00:57:29.492185: step: 720/533, loss: 0.6449282169342041
2023-01-23 00:57:30.667307: step: 724/533, loss: 0.35939139127731323
2023-01-23 00:57:31.827104: step: 728/533, loss: 0.24447423219680786
2023-01-23 00:57:33.007904: step: 732/533, loss: 0.016836263239383698
2023-01-23 00:57:34.189373: step: 736/533, loss: 0.044773247092962265
2023-01-23 00:57:35.384443: step: 740/533, loss: 0.018569564446806908
2023-01-23 00:57:36.501161: step: 744/533, loss: 0.0799143984913826
2023-01-23 00:57:37.690783: step: 748/533, loss: 0.09197226166725159
2023-01-23 00:57:38.865561: step: 752/533, loss: 0.1904076635837555
2023-01-23 00:57:40.058458: step: 756/533, loss: 0.3678344786167145
2023-01-23 00:57:41.225811: step: 760/533, loss: 0.015276337042450905
2023-01-23 00:57:42.432439: step: 764/533, loss: 0.09168615192174911
2023-01-23 00:57:43.619018: step: 768/533, loss: 0.08190512657165527
2023-01-23 00:57:44.813360: step: 772/533, loss: 0.175513356924057
2023-01-23 00:57:45.972424: step: 776/533, loss: 0.06053218990564346
2023-01-23 00:57:47.180435: step: 780/533, loss: 0.03240928798913956
2023-01-23 00:57:48.385220: step: 784/533, loss: 0.05183429643511772
2023-01-23 00:57:49.537606: step: 788/533, loss: 0.005655050277709961
2023-01-23 00:57:50.671457: step: 792/533, loss: 0.08929681777954102
2023-01-23 00:57:51.840382: step: 796/533, loss: 0.09898243099451065
2023-01-23 00:57:53.081266: step: 800/533, loss: 0.03399248048663139
2023-01-23 00:57:54.322785: step: 804/533, loss: 0.03037128411233425
2023-01-23 00:57:55.487375: step: 808/533, loss: 0.03187217563390732
2023-01-23 00:57:56.655401: step: 812/533, loss: 0.10390167683362961
2023-01-23 00:57:57.843072: step: 816/533, loss: 0.06381683051586151
2023-01-23 00:57:59.019655: step: 820/533, loss: 0.06803464889526367
2023-01-23 00:58:00.214149: step: 824/533, loss: 0.097596175968647
2023-01-23 00:58:01.408701: step: 828/533, loss: 0.16625767946243286
2023-01-23 00:58:02.535399: step: 832/533, loss: 0.03342418745160103
2023-01-23 00:58:03.710004: step: 836/533, loss: 0.01952815055847168
2023-01-23 00:58:04.884780: step: 840/533, loss: 0.03822450712323189
2023-01-23 00:58:06.067158: step: 844/533, loss: 0.06044311448931694
2023-01-23 00:58:07.270846: step: 848/533, loss: 0.11998863518238068
2023-01-23 00:58:08.436940: step: 852/533, loss: 0.038886167109012604
2023-01-23 00:58:09.645806: step: 856/533, loss: 0.19750748574733734
2023-01-23 00:58:10.893941: step: 860/533, loss: 0.42549440264701843
2023-01-23 00:58:12.071281: step: 864/533, loss: 0.04626961052417755
2023-01-23 00:58:13.286302: step: 868/533, loss: 0.63702392578125
2023-01-23 00:58:14.435711: step: 872/533, loss: 0.018661784008145332
2023-01-23 00:58:15.604286: step: 876/533, loss: 0.01962861977517605
2023-01-23 00:58:16.825859: step: 880/533, loss: 0.022882748395204544
2023-01-23 00:58:18.023980: step: 884/533, loss: 0.04386615753173828
2023-01-23 00:58:19.204989: step: 888/533, loss: 0.034467220306396484
2023-01-23 00:58:20.374835: step: 892/533, loss: 0.20613127946853638
2023-01-23 00:58:21.548738: step: 896/533, loss: 0.23075255751609802
2023-01-23 00:58:22.774075: step: 900/533, loss: 0.160674050450325
2023-01-23 00:58:23.974984: step: 904/533, loss: 0.2709992229938507
2023-01-23 00:58:25.153315: step: 908/533, loss: 0.02138206921517849
2023-01-23 00:58:26.318252: step: 912/533, loss: 0.9458889365196228
2023-01-23 00:58:27.478062: step: 916/533, loss: 0.038884639739990234
2023-01-23 00:58:28.640073: step: 920/533, loss: 0.08989983052015305
2023-01-23 00:58:29.801037: step: 924/533, loss: 0.0558956116437912
2023-01-23 00:58:30.972159: step: 928/533, loss: 0.09872579574584961
2023-01-23 00:58:32.150261: step: 932/533, loss: 0.039171792566776276
2023-01-23 00:58:33.315365: step: 936/533, loss: 0.15904836356639862
2023-01-23 00:58:34.480320: step: 940/533, loss: 0.019061803817749023
2023-01-23 00:58:35.680042: step: 944/533, loss: 0.0789029598236084
2023-01-23 00:58:36.832263: step: 948/533, loss: 0.05996885523200035
2023-01-23 00:58:38.040709: step: 952/533, loss: 0.16926145553588867
2023-01-23 00:58:39.206601: step: 956/533, loss: 0.035991862416267395
2023-01-23 00:58:40.363473: step: 960/533, loss: 0.03003845363855362
2023-01-23 00:58:41.562405: step: 964/533, loss: 0.2123720347881317
2023-01-23 00:58:42.723371: step: 968/533, loss: 0.7410622239112854
2023-01-23 00:58:43.887828: step: 972/533, loss: 0.017244840040802956
2023-01-23 00:58:45.047262: step: 976/533, loss: 0.05120887607336044
2023-01-23 00:58:46.241210: step: 980/533, loss: 0.04309334605932236
2023-01-23 00:58:47.412705: step: 984/533, loss: 0.3598502278327942
2023-01-23 00:58:48.606873: step: 988/533, loss: 0.4101582467556
2023-01-23 00:58:49.787289: step: 992/533, loss: 0.03446369245648384
2023-01-23 00:58:50.969016: step: 996/533, loss: 0.01908884011209011
2023-01-23 00:58:52.130824: step: 1000/533, loss: 0.029134750366210938
2023-01-23 00:58:53.347019: step: 1004/533, loss: 0.049874309450387955
2023-01-23 00:58:54.483747: step: 1008/533, loss: 0.17342795431613922
2023-01-23 00:58:55.675535: step: 1012/533, loss: 0.07612524926662445
2023-01-23 00:58:56.838135: step: 1016/533, loss: 0.047574520111083984
2023-01-23 00:58:58.014765: step: 1020/533, loss: 0.14100809395313263
2023-01-23 00:58:59.167500: step: 1024/533, loss: 0.07453164458274841
2023-01-23 00:59:00.340365: step: 1028/533, loss: 0.4932495057582855
2023-01-23 00:59:01.511313: step: 1032/533, loss: 0.017429828643798828
2023-01-23 00:59:02.668913: step: 1036/533, loss: 0.3841678500175476
2023-01-23 00:59:03.851952: step: 1040/533, loss: 0.2241520881652832
2023-01-23 00:59:05.057888: step: 1044/533, loss: 0.336454302072525
2023-01-23 00:59:06.188734: step: 1048/533, loss: 0.11091289669275284
2023-01-23 00:59:07.353372: step: 1052/533, loss: 0.04796476662158966
2023-01-23 00:59:08.516277: step: 1056/533, loss: 0.1912672072649002
2023-01-23 00:59:09.656817: step: 1060/533, loss: 0.12299275398254395
2023-01-23 00:59:10.849209: step: 1064/533, loss: 0.06454887241125107
2023-01-23 00:59:12.105052: step: 1068/533, loss: 0.09541969001293182
2023-01-23 00:59:13.300001: step: 1072/533, loss: 0.02104644849896431
2023-01-23 00:59:14.488622: step: 1076/533, loss: 0.035081129521131516
2023-01-23 00:59:15.649222: step: 1080/533, loss: 0.1482558250427246
2023-01-23 00:59:16.814997: step: 1084/533, loss: 0.05635084956884384
2023-01-23 00:59:18.031224: step: 1088/533, loss: 0.13622379302978516
2023-01-23 00:59:19.211879: step: 1092/533, loss: 0.10148197412490845
2023-01-23 00:59:20.365814: step: 1096/533, loss: 0.040871430188417435
2023-01-23 00:59:21.624474: step: 1100/533, loss: 0.1324821412563324
2023-01-23 00:59:22.800889: step: 1104/533, loss: 0.1031554713845253
2023-01-23 00:59:23.978304: step: 1108/533, loss: 0.15277177095413208
2023-01-23 00:59:25.146961: step: 1112/533, loss: 0.013832282274961472
2023-01-23 00:59:26.344191: step: 1116/533, loss: 0.151885986328125
2023-01-23 00:59:27.549111: step: 1120/533, loss: 0.06178426742553711
2023-01-23 00:59:28.708091: step: 1124/533, loss: 0.0672360435128212
2023-01-23 00:59:29.866757: step: 1128/533, loss: 0.061821937561035156
2023-01-23 00:59:31.047214: step: 1132/533, loss: 0.17634135484695435
2023-01-23 00:59:32.242326: step: 1136/533, loss: 0.2373599112033844
2023-01-23 00:59:33.416473: step: 1140/533, loss: 0.39508095383644104
2023-01-23 00:59:34.622872: step: 1144/533, loss: 0.08182048797607422
2023-01-23 00:59:35.748151: step: 1148/533, loss: 0.1069403737783432
2023-01-23 00:59:36.909402: step: 1152/533, loss: 0.01784048229455948
2023-01-23 00:59:38.122937: step: 1156/533, loss: 0.09308870136737823
2023-01-23 00:59:39.294857: step: 1160/533, loss: 0.17533540725708008
2023-01-23 00:59:40.493482: step: 1164/533, loss: 0.08245744556188583
2023-01-23 00:59:41.682510: step: 1168/533, loss: 0.1243671402335167
2023-01-23 00:59:42.890692: step: 1172/533, loss: 0.6975938677787781
2023-01-23 00:59:44.078578: step: 1176/533, loss: 0.1372303068637848
2023-01-23 00:59:45.257897: step: 1180/533, loss: 0.06776552647352219
2023-01-23 00:59:46.434095: step: 1184/533, loss: 0.18441256880760193
2023-01-23 00:59:47.587851: step: 1188/533, loss: 0.11154685169458389
2023-01-23 00:59:48.792427: step: 1192/533, loss: 0.06885939091444016
2023-01-23 00:59:49.951161: step: 1196/533, loss: 0.16055002808570862
2023-01-23 00:59:51.152896: step: 1200/533, loss: 0.14407922327518463
2023-01-23 00:59:52.329891: step: 1204/533, loss: 0.03295435756444931
2023-01-23 00:59:53.478923: step: 1208/533, loss: 0.04848499596118927
2023-01-23 00:59:54.639527: step: 1212/533, loss: 0.007522201631218195
2023-01-23 00:59:55.828968: step: 1216/533, loss: 0.30566588044166565
2023-01-23 00:59:57.033607: step: 1220/533, loss: 0.09707650542259216
2023-01-23 00:59:58.209159: step: 1224/533, loss: 0.05437551811337471
2023-01-23 00:59:59.411089: step: 1228/533, loss: 0.0364563949406147
2023-01-23 01:00:00.628464: step: 1232/533, loss: 0.051595401018857956
2023-01-23 01:00:01.804199: step: 1236/533, loss: 0.02667818032205105
2023-01-23 01:00:02.995695: step: 1240/533, loss: 0.12089768052101135
2023-01-23 01:00:04.152951: step: 1244/533, loss: 0.21270255744457245
2023-01-23 01:00:05.323621: step: 1248/533, loss: 0.0508122444152832
2023-01-23 01:00:06.504407: step: 1252/533, loss: 0.29473793506622314
2023-01-23 01:00:07.644635: step: 1256/533, loss: 0.10584226250648499
2023-01-23 01:00:08.858263: step: 1260/533, loss: 0.12005731463432312
2023-01-23 01:00:10.026948: step: 1264/533, loss: 0.4417663514614105
2023-01-23 01:00:11.176169: step: 1268/533, loss: 0.1455962210893631
2023-01-23 01:00:12.305899: step: 1272/533, loss: 0.07612204551696777
2023-01-23 01:00:13.472988: step: 1276/533, loss: 0.0481874942779541
2023-01-23 01:00:14.665656: step: 1280/533, loss: 0.1576584428548813
2023-01-23 01:00:15.876481: step: 1284/533, loss: 0.049852754920721054
2023-01-23 01:00:17.027628: step: 1288/533, loss: 0.2352529615163803
2023-01-23 01:00:18.187675: step: 1292/533, loss: 0.007737541571259499
2023-01-23 01:00:19.342590: step: 1296/533, loss: 0.0856243371963501
2023-01-23 01:00:20.522817: step: 1300/533, loss: 0.048775482922792435
2023-01-23 01:00:21.723885: step: 1304/533, loss: 0.02902846410870552
2023-01-23 01:00:22.909673: step: 1308/533, loss: 0.07591553032398224
2023-01-23 01:00:24.061210: step: 1312/533, loss: 0.06961230933666229
2023-01-23 01:00:25.225118: step: 1316/533, loss: 0.05663866922259331
2023-01-23 01:00:26.421755: step: 1320/533, loss: 0.011522769927978516
2023-01-23 01:00:27.590672: step: 1324/533, loss: 0.08625419437885284
2023-01-23 01:00:28.753363: step: 1328/533, loss: 0.1429588794708252
2023-01-23 01:00:29.925027: step: 1332/533, loss: 0.03054199367761612
2023-01-23 01:00:31.082654: step: 1336/533, loss: 0.07631373405456543
2023-01-23 01:00:32.250903: step: 1340/533, loss: 0.037290096282958984
2023-01-23 01:00:33.413698: step: 1344/533, loss: 0.038230106234550476
2023-01-23 01:00:34.615651: step: 1348/533, loss: 0.06629786640405655
2023-01-23 01:00:35.824143: step: 1352/533, loss: 0.024962520226836205
2023-01-23 01:00:37.002037: step: 1356/533, loss: 0.10138006508350372
2023-01-23 01:00:38.134247: step: 1360/533, loss: 0.11009187996387482
2023-01-23 01:00:39.293016: step: 1364/533, loss: 0.39571821689605713
2023-01-23 01:00:40.506910: step: 1368/533, loss: 0.04840097576379776
2023-01-23 01:00:41.681239: step: 1372/533, loss: 0.2133781909942627
2023-01-23 01:00:42.820089: step: 1376/533, loss: 0.23290252685546875
2023-01-23 01:00:43.984854: step: 1380/533, loss: 0.07012281566858292
2023-01-23 01:00:45.185365: step: 1384/533, loss: 0.15407808125019073
2023-01-23 01:00:46.423769: step: 1388/533, loss: 0.05259094387292862
2023-01-23 01:00:47.593125: step: 1392/533, loss: 0.11284966766834259
2023-01-23 01:00:48.726414: step: 1396/533, loss: 0.45853570103645325
2023-01-23 01:00:49.884047: step: 1400/533, loss: 0.10231009125709534
2023-01-23 01:00:51.067519: step: 1404/533, loss: 0.05192689970135689
2023-01-23 01:00:52.213583: step: 1408/533, loss: 0.013852620497345924
2023-01-23 01:00:53.393099: step: 1412/533, loss: 0.029465390369296074
2023-01-23 01:00:54.615522: step: 1416/533, loss: 0.3853006958961487
2023-01-23 01:00:55.796867: step: 1420/533, loss: 0.016729354858398438
2023-01-23 01:00:56.937713: step: 1424/533, loss: 0.17632311582565308
2023-01-23 01:00:58.114623: step: 1428/533, loss: 0.08743259310722351
2023-01-23 01:00:59.323680: step: 1432/533, loss: 0.11501336097717285
2023-01-23 01:01:00.498296: step: 1436/533, loss: 0.05981488525867462
2023-01-23 01:01:01.641395: step: 1440/533, loss: 0.07624292373657227
2023-01-23 01:01:02.830895: step: 1444/533, loss: 0.032958388328552246
2023-01-23 01:01:04.006590: step: 1448/533, loss: 0.013405894860625267
2023-01-23 01:01:05.209650: step: 1452/533, loss: 0.09428711235523224
2023-01-23 01:01:06.361600: step: 1456/533, loss: 0.07770691066980362
2023-01-23 01:01:07.557262: step: 1460/533, loss: 0.2388835847377777
2023-01-23 01:01:08.818596: step: 1464/533, loss: 0.16202107071876526
2023-01-23 01:01:09.981307: step: 1468/533, loss: 0.03350029140710831
2023-01-23 01:01:11.132530: step: 1472/533, loss: 0.04074613004922867
2023-01-23 01:01:12.305578: step: 1476/533, loss: 0.41753920912742615
2023-01-23 01:01:13.471868: step: 1480/533, loss: 0.04913058131933212
2023-01-23 01:01:14.670191: step: 1484/533, loss: 0.08075688779354095
2023-01-23 01:01:15.861241: step: 1488/533, loss: 0.1480119824409485
2023-01-23 01:01:17.053649: step: 1492/533, loss: 0.04343461990356445
2023-01-23 01:01:18.238169: step: 1496/533, loss: 0.05710973963141441
2023-01-23 01:01:19.397157: step: 1500/533, loss: 0.6117690205574036
2023-01-23 01:01:20.624056: step: 1504/533, loss: 0.5654932856559753
2023-01-23 01:01:21.790029: step: 1508/533, loss: 0.25297728180885315
2023-01-23 01:01:22.949827: step: 1512/533, loss: 0.004511928651481867
2023-01-23 01:01:24.193666: step: 1516/533, loss: 0.10465659946203232
2023-01-23 01:01:25.390469: step: 1520/533, loss: 0.33815255761146545
2023-01-23 01:01:26.544246: step: 1524/533, loss: 0.077989861369133
2023-01-23 01:01:27.721630: step: 1528/533, loss: 0.024226760491728783
2023-01-23 01:01:28.890580: step: 1532/533, loss: 0.22960643470287323
2023-01-23 01:01:30.118694: step: 1536/533, loss: 0.19098205864429474
2023-01-23 01:01:31.270067: step: 1540/533, loss: 0.1172613650560379
2023-01-23 01:01:32.469418: step: 1544/533, loss: 0.16278590261936188
2023-01-23 01:01:33.626612: step: 1548/533, loss: 0.12067241221666336
2023-01-23 01:01:34.855437: step: 1552/533, loss: 0.08397092670202255
2023-01-23 01:01:36.024137: step: 1556/533, loss: 0.08799795806407928
2023-01-23 01:01:37.156009: step: 1560/533, loss: 0.007019233889877796
2023-01-23 01:01:38.359051: step: 1564/533, loss: 0.051380157470703125
2023-01-23 01:01:39.556337: step: 1568/533, loss: 0.05458813160657883
2023-01-23 01:01:40.776897: step: 1572/533, loss: 0.05836434289813042
2023-01-23 01:01:41.973309: step: 1576/533, loss: 0.07878632843494415
2023-01-23 01:01:43.187420: step: 1580/533, loss: 0.15848851203918457
2023-01-23 01:01:44.350486: step: 1584/533, loss: 0.09809398651123047
2023-01-23 01:01:45.545871: step: 1588/533, loss: 0.10737352818250656
2023-01-23 01:01:46.728980: step: 1592/533, loss: 0.10923920571804047
2023-01-23 01:01:47.942380: step: 1596/533, loss: 0.06701450794935226
2023-01-23 01:01:49.110212: step: 1600/533, loss: 0.10820188373327255
2023-01-23 01:01:50.305973: step: 1604/533, loss: 0.5899614691734314
2023-01-23 01:01:51.466770: step: 1608/533, loss: 0.08746099472045898
2023-01-23 01:01:52.669580: step: 1612/533, loss: 0.23179256916046143
2023-01-23 01:01:53.834394: step: 1616/533, loss: 0.17375750839710236
2023-01-23 01:01:54.982437: step: 1620/533, loss: 0.8971181511878967
2023-01-23 01:01:56.145063: step: 1624/533, loss: 0.054903555661439896
2023-01-23 01:01:57.302664: step: 1628/533, loss: 0.061953071504831314
2023-01-23 01:01:58.457502: step: 1632/533, loss: 0.057358644902706146
2023-01-23 01:01:59.620528: step: 1636/533, loss: 0.09211969375610352
2023-01-23 01:02:00.848771: step: 1640/533, loss: 0.039336059242486954
2023-01-23 01:02:02.020155: step: 1644/533, loss: 0.07075109332799911
2023-01-23 01:02:03.185762: step: 1648/533, loss: 0.1728501319885254
2023-01-23 01:02:04.349200: step: 1652/533, loss: 0.11759848892688751
2023-01-23 01:02:05.547137: step: 1656/533, loss: 0.13034382462501526
2023-01-23 01:02:06.752367: step: 1660/533, loss: 0.046736910939216614
2023-01-23 01:02:07.926950: step: 1664/533, loss: 0.11750298738479614
2023-01-23 01:02:09.096337: step: 1668/533, loss: 0.177720844745636
2023-01-23 01:02:10.237167: step: 1672/533, loss: 0.1376950740814209
2023-01-23 01:02:11.429022: step: 1676/533, loss: 0.08894872665405273
2023-01-23 01:02:12.611936: step: 1680/533, loss: 0.05386357381939888
2023-01-23 01:02:13.803219: step: 1684/533, loss: 0.0661015510559082
2023-01-23 01:02:14.973065: step: 1688/533, loss: 0.07546535134315491
2023-01-23 01:02:16.112555: step: 1692/533, loss: 0.008820438757538795
2023-01-23 01:02:17.284710: step: 1696/533, loss: 0.029964257031679153
2023-01-23 01:02:18.465957: step: 1700/533, loss: 0.19186973571777344
2023-01-23 01:02:19.662131: step: 1704/533, loss: 0.5331511497497559
2023-01-23 01:02:20.823126: step: 1708/533, loss: 0.13748803734779358
2023-01-23 01:02:22.054654: step: 1712/533, loss: 0.056466102600097656
2023-01-23 01:02:23.204150: step: 1716/533, loss: 0.0015454532112926245
2023-01-23 01:02:24.400439: step: 1720/533, loss: 0.013463020324707031
2023-01-23 01:02:25.616200: step: 1724/533, loss: 0.04285430908203125
2023-01-23 01:02:26.759919: step: 1728/533, loss: 0.033825017511844635
2023-01-23 01:02:27.948496: step: 1732/533, loss: 0.08803386986255646
2023-01-23 01:02:29.125166: step: 1736/533, loss: 0.04089755937457085
2023-01-23 01:02:30.311974: step: 1740/533, loss: 0.092307448387146
2023-01-23 01:02:31.521394: step: 1744/533, loss: 0.37547388672828674
2023-01-23 01:02:32.696167: step: 1748/533, loss: 0.4492069482803345
2023-01-23 01:02:33.885480: step: 1752/533, loss: 0.03988780826330185
2023-01-23 01:02:35.097411: step: 1756/533, loss: 0.15885190665721893
2023-01-23 01:02:36.239053: step: 1760/533, loss: 0.3061714172363281
2023-01-23 01:02:37.395779: step: 1764/533, loss: 0.3835746645927429
2023-01-23 01:02:38.540843: step: 1768/533, loss: 0.27670979499816895
2023-01-23 01:02:39.760212: step: 1772/533, loss: 0.12942752242088318
2023-01-23 01:02:40.913949: step: 1776/533, loss: 0.12261597812175751
2023-01-23 01:02:42.147011: step: 1780/533, loss: 0.09932427853345871
2023-01-23 01:02:43.356864: step: 1784/533, loss: 0.118072509765625
2023-01-23 01:02:44.561645: step: 1788/533, loss: 1.369811773300171
2023-01-23 01:02:45.830022: step: 1792/533, loss: 0.06129207834601402
2023-01-23 01:02:46.967613: step: 1796/533, loss: 0.0732000395655632
2023-01-23 01:02:48.130279: step: 1800/533, loss: 0.08286122977733612
2023-01-23 01:02:49.331586: step: 1804/533, loss: 0.08141598850488663
2023-01-23 01:02:50.484524: step: 1808/533, loss: 0.12271225452423096
2023-01-23 01:02:51.635616: step: 1812/533, loss: 0.0843229815363884
2023-01-23 01:02:52.834375: step: 1816/533, loss: 0.07953443378210068
2023-01-23 01:02:54.018532: step: 1820/533, loss: 0.01404027920216322
2023-01-23 01:02:55.230711: step: 1824/533, loss: 0.14238977432250977
2023-01-23 01:02:56.388812: step: 1828/533, loss: 0.11053504794836044
2023-01-23 01:02:57.569393: step: 1832/533, loss: 0.055158376693725586
2023-01-23 01:02:58.747512: step: 1836/533, loss: 1.2640025615692139
2023-01-23 01:02:59.918455: step: 1840/533, loss: 0.01196146011352539
2023-01-23 01:03:01.068339: step: 1844/533, loss: 0.02628335915505886
2023-01-23 01:03:02.239188: step: 1848/533, loss: 0.026090241968631744
2023-01-23 01:03:03.395687: step: 1852/533, loss: 0.1779797524213791
2023-01-23 01:03:04.615115: step: 1856/533, loss: 0.09468249976634979
2023-01-23 01:03:05.778729: step: 1860/533, loss: 0.029116058722138405
2023-01-23 01:03:06.969522: step: 1864/533, loss: 0.10984411835670471
2023-01-23 01:03:08.132639: step: 1868/533, loss: 0.1984615921974182
2023-01-23 01:03:09.290640: step: 1872/533, loss: 0.009050846099853516
2023-01-23 01:03:10.458993: step: 1876/533, loss: 0.016206074506044388
2023-01-23 01:03:11.626663: step: 1880/533, loss: 0.03429281711578369
2023-01-23 01:03:12.796142: step: 1884/533, loss: 0.11189261078834534
2023-01-23 01:03:13.967535: step: 1888/533, loss: 0.13980932533740997
2023-01-23 01:03:15.143087: step: 1892/533, loss: 0.296229749917984
2023-01-23 01:03:16.336470: step: 1896/533, loss: 0.11454787105321884
2023-01-23 01:03:17.505424: step: 1900/533, loss: 0.1393490880727768
2023-01-23 01:03:18.703005: step: 1904/533, loss: 0.03891587257385254
2023-01-23 01:03:19.860312: step: 1908/533, loss: 0.0973021537065506
2023-01-23 01:03:21.059241: step: 1912/533, loss: 0.11823282390832901
2023-01-23 01:03:22.191911: step: 1916/533, loss: 0.5313553214073181
2023-01-23 01:03:23.378261: step: 1920/533, loss: 0.12328267842531204
2023-01-23 01:03:24.557320: step: 1924/533, loss: 0.07467503845691681
2023-01-23 01:03:25.746863: step: 1928/533, loss: 0.1543058454990387
2023-01-23 01:03:26.956888: step: 1932/533, loss: 0.06829843670129776
2023-01-23 01:03:28.130610: step: 1936/533, loss: 0.04492764547467232
2023-01-23 01:03:29.302201: step: 1940/533, loss: 0.07383785396814346
2023-01-23 01:03:30.440225: step: 1944/533, loss: 0.05159907415509224
2023-01-23 01:03:31.567677: step: 1948/533, loss: 0.020679570734500885
2023-01-23 01:03:32.769593: step: 1952/533, loss: 0.06067943572998047
2023-01-23 01:03:33.926004: step: 1956/533, loss: 0.10070066899061203
2023-01-23 01:03:35.126074: step: 1960/533, loss: 0.10214195400476456
2023-01-23 01:03:36.278222: step: 1964/533, loss: 0.0035020112991333008
2023-01-23 01:03:37.451921: step: 1968/533, loss: 0.3237728178501129
2023-01-23 01:03:38.645335: step: 1972/533, loss: 0.6307231187820435
2023-01-23 01:03:39.808378: step: 1976/533, loss: 0.11528892815113068
2023-01-23 01:03:41.061844: step: 1980/533, loss: 0.10718250274658203
2023-01-23 01:03:42.238663: step: 1984/533, loss: 0.3092205822467804
2023-01-23 01:03:43.446635: step: 1988/533, loss: 0.06763891875743866
2023-01-23 01:03:44.734744: step: 1992/533, loss: 0.06109762191772461
2023-01-23 01:03:45.959566: step: 1996/533, loss: 0.5236159563064575
2023-01-23 01:03:47.130736: step: 2000/533, loss: 0.036244723945856094
2023-01-23 01:03:48.347269: step: 2004/533, loss: 0.1054566353559494
2023-01-23 01:03:49.497987: step: 2008/533, loss: 0.2676524221897125
2023-01-23 01:03:50.687088: step: 2012/533, loss: 0.030649995431303978
2023-01-23 01:03:51.841968: step: 2016/533, loss: 0.43426164984703064
2023-01-23 01:03:53.031778: step: 2020/533, loss: 0.01166553609073162
2023-01-23 01:03:54.212380: step: 2024/533, loss: 0.18203334510326385
2023-01-23 01:03:55.395348: step: 2028/533, loss: 0.038648199290037155
2023-01-23 01:03:56.597505: step: 2032/533, loss: 0.08750849217176437
2023-01-23 01:03:57.788300: step: 2036/533, loss: 0.7998626232147217
2023-01-23 01:03:58.958001: step: 2040/533, loss: 0.1191432848572731
2023-01-23 01:04:00.149770: step: 2044/533, loss: 0.05177684128284454
2023-01-23 01:04:01.339760: step: 2048/533, loss: 0.04636268690228462
2023-01-23 01:04:02.516274: step: 2052/533, loss: 0.09539518505334854
2023-01-23 01:04:03.747706: step: 2056/533, loss: 0.017030049115419388
2023-01-23 01:04:04.947744: step: 2060/533, loss: 0.040022946894168854
2023-01-23 01:04:06.177588: step: 2064/533, loss: 0.3287423849105835
2023-01-23 01:04:07.341405: step: 2068/533, loss: 0.21219034492969513
2023-01-23 01:04:08.516405: step: 2072/533, loss: 0.033795833587646484
2023-01-23 01:04:09.645383: step: 2076/533, loss: 0.08236217498779297
2023-01-23 01:04:10.819518: step: 2080/533, loss: 0.07740440964698792
2023-01-23 01:04:12.014431: step: 2084/533, loss: 0.2799074649810791
2023-01-23 01:04:13.192757: step: 2088/533, loss: 0.04357290267944336
2023-01-23 01:04:14.352445: step: 2092/533, loss: 0.0749397799372673
2023-01-23 01:04:15.479598: step: 2096/533, loss: 0.25775814056396484
2023-01-23 01:04:16.653123: step: 2100/533, loss: 0.08026123046875
2023-01-23 01:04:17.850284: step: 2104/533, loss: 0.13429725170135498
2023-01-23 01:04:19.039941: step: 2108/533, loss: 0.1385565847158432
2023-01-23 01:04:20.249048: step: 2112/533, loss: 0.049806784838438034
2023-01-23 01:04:21.401167: step: 2116/533, loss: 0.03262138366699219
2023-01-23 01:04:22.567255: step: 2120/533, loss: 0.15529866516590118
2023-01-23 01:04:23.725175: step: 2124/533, loss: 0.08780555427074432
2023-01-23 01:04:24.955153: step: 2128/533, loss: 0.08337926864624023
2023-01-23 01:04:26.175769: step: 2132/533, loss: 0.10202445834875107
==================================================
Loss: 0.138
--------------------
Dev: {'event': {'p': 0.5778648383937316, 'r': 0.7856191744340879, 'f1': 0.6659142212189617}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6300893743793445, 'r': 0.8113810741687979, 'f1': 0.7093348239239798}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
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': 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': 0.4418604651162791, 'r': 0.5277777777777778, 'f1': 0.4810126582278481}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6832460732984293, 'r': 0.6950732356857523, 'f1': 0.689108910891089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6548406494287432, 'r': 0.6962915601023018, 'f1': 0.6749302757979547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.7037037037037037, 'r': 0.7037037037037037, 'f1': 0.7037037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5864197530864198, 'r': 0.758988015978695, 'f1': 0.6616366802089378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6193447737909517, 'r': 0.7615089514066496, 'f1': 0.6831086894178378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.723404255319149, 'r': 0.5396825396825397, 'f1': 0.6181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:05:07.363326: step: 4/533, loss: 0.09926968812942505
2023-01-23 01:05:08.511783: step: 8/533, loss: 0.026259899139404297
2023-01-23 01:05:09.667262: step: 12/533, loss: 0.04331560432910919
2023-01-23 01:05:10.872572: step: 16/533, loss: 0.10419845581054688
2023-01-23 01:05:12.044795: step: 20/533, loss: 0.02791421487927437
2023-01-23 01:05:13.219114: step: 24/533, loss: 0.048871614038944244
2023-01-23 01:05:14.391062: step: 28/533, loss: 0.05272989720106125
2023-01-23 01:05:15.587572: step: 32/533, loss: 0.0406985804438591
2023-01-23 01:05:16.752281: step: 36/533, loss: 0.04748249053955078
2023-01-23 01:05:17.910716: step: 40/533, loss: 0.06372527778148651
2023-01-23 01:05:19.105408: step: 44/533, loss: 0.1344389021396637
2023-01-23 01:05:20.274731: step: 48/533, loss: 0.08515739440917969
2023-01-23 01:05:21.492051: step: 52/533, loss: 0.07617368549108505
2023-01-23 01:05:22.684149: step: 56/533, loss: 0.02903785929083824
2023-01-23 01:05:23.850107: step: 60/533, loss: 0.03367490693926811
2023-01-23 01:05:24.999912: step: 64/533, loss: 0.11510520428419113
2023-01-23 01:05:26.194844: step: 68/533, loss: 0.010165119543671608
2023-01-23 01:05:27.348598: step: 72/533, loss: 0.052768900990486145
2023-01-23 01:05:28.471324: step: 76/533, loss: 0.1772814393043518
2023-01-23 01:05:29.656633: step: 80/533, loss: 0.0358455665409565
2023-01-23 01:05:30.817948: step: 84/533, loss: 0.006482315249741077
2023-01-23 01:05:32.026375: step: 88/533, loss: 0.24554085731506348
2023-01-23 01:05:33.216624: step: 92/533, loss: 0.6262931823730469
2023-01-23 01:05:34.403512: step: 96/533, loss: 0.05124311521649361
2023-01-23 01:05:35.575087: step: 100/533, loss: 0.06116313859820366
2023-01-23 01:05:36.733253: step: 104/533, loss: 0.7051877379417419
2023-01-23 01:05:37.902680: step: 108/533, loss: 0.05737247318029404
2023-01-23 01:05:39.114901: step: 112/533, loss: 0.04718508571386337
2023-01-23 01:05:40.266419: step: 116/533, loss: 0.07925932854413986
2023-01-23 01:05:41.424030: step: 120/533, loss: 0.17257767915725708
2023-01-23 01:05:42.592806: step: 124/533, loss: 0.025682760402560234
2023-01-23 01:05:43.747730: step: 128/533, loss: 0.014387511648237705
2023-01-23 01:05:44.851778: step: 132/533, loss: 0.010199499316513538
2023-01-23 01:05:46.031427: step: 136/533, loss: 0.08140130341053009
2023-01-23 01:05:47.178535: step: 140/533, loss: 0.12280035018920898
2023-01-23 01:05:48.367172: step: 144/533, loss: 0.013095760717988014
2023-01-23 01:05:49.536805: step: 148/533, loss: 0.01890258863568306
2023-01-23 01:05:50.667042: step: 152/533, loss: 0.028209973126649857
2023-01-23 01:05:51.862253: step: 156/533, loss: 0.06222410500049591
2023-01-23 01:05:53.012107: step: 160/533, loss: 0.043053437024354935
2023-01-23 01:05:54.205822: step: 164/533, loss: 0.01863894611597061
2023-01-23 01:05:55.369994: step: 168/533, loss: 0.1328442543745041
2023-01-23 01:05:56.539946: step: 172/533, loss: 0.014139366336166859
2023-01-23 01:05:57.737003: step: 176/533, loss: 0.17969512939453125
2023-01-23 01:05:58.935178: step: 180/533, loss: 0.1496437042951584
2023-01-23 01:06:00.112587: step: 184/533, loss: 0.07733212411403656
2023-01-23 01:06:01.283311: step: 188/533, loss: 0.04834775999188423
2023-01-23 01:06:02.460428: step: 192/533, loss: 0.05633850023150444
2023-01-23 01:06:03.657531: step: 196/533, loss: 0.07619714736938477
2023-01-23 01:06:04.844048: step: 200/533, loss: 0.13846178352832794
2023-01-23 01:06:06.006295: step: 204/533, loss: 0.26538050174713135
2023-01-23 01:06:07.183310: step: 208/533, loss: 0.09557390213012695
2023-01-23 01:06:08.374280: step: 212/533, loss: 0.17834702134132385
2023-01-23 01:06:09.519704: step: 216/533, loss: 0.1351640820503235
2023-01-23 01:06:10.675101: step: 220/533, loss: 0.007816505618393421
2023-01-23 01:06:11.864382: step: 224/533, loss: 0.12863358855247498
2023-01-23 01:06:13.057583: step: 228/533, loss: 0.025182437151670456
2023-01-23 01:06:14.235634: step: 232/533, loss: 0.0069138528779149055
2023-01-23 01:06:15.377494: step: 236/533, loss: 0.02809600904583931
2023-01-23 01:06:16.563895: step: 240/533, loss: 0.03894472494721413
2023-01-23 01:06:17.757795: step: 244/533, loss: 0.14274054765701294
2023-01-23 01:06:18.967332: step: 248/533, loss: 0.08537349104881287
2023-01-23 01:06:20.177528: step: 252/533, loss: 0.11126642674207687
2023-01-23 01:06:21.309791: step: 256/533, loss: 0.03346996381878853
2023-01-23 01:06:22.472913: step: 260/533, loss: 0.29826951026916504
2023-01-23 01:06:23.638671: step: 264/533, loss: 0.20949554443359375
2023-01-23 01:06:24.797652: step: 268/533, loss: 0.032239485532045364
2023-01-23 01:06:25.953185: step: 272/533, loss: 0.013752412050962448
2023-01-23 01:06:27.159332: step: 276/533, loss: 0.03142566606402397
2023-01-23 01:06:28.376666: step: 280/533, loss: 0.10265292972326279
2023-01-23 01:06:29.595914: step: 284/533, loss: 0.16017714142799377
2023-01-23 01:06:30.777586: step: 288/533, loss: 0.04518106207251549
2023-01-23 01:06:31.919875: step: 292/533, loss: 0.05074930191040039
2023-01-23 01:06:33.065290: step: 296/533, loss: 0.04854927957057953
2023-01-23 01:06:34.324685: step: 300/533, loss: 0.020022202283143997
2023-01-23 01:06:35.468864: step: 304/533, loss: 0.03747405856847763
2023-01-23 01:06:36.664707: step: 308/533, loss: 0.036989498883485794
2023-01-23 01:06:37.856652: step: 312/533, loss: 0.06270818412303925
2023-01-23 01:06:39.004204: step: 316/533, loss: 0.02303600311279297
2023-01-23 01:06:40.228697: step: 320/533, loss: 0.12723135948181152
2023-01-23 01:06:41.486737: step: 324/533, loss: 0.10956735908985138
2023-01-23 01:06:42.645216: step: 328/533, loss: 0.08900395035743713
2023-01-23 01:06:43.802936: step: 332/533, loss: 0.10268016159534454
2023-01-23 01:06:44.964881: step: 336/533, loss: 0.05550365522503853
2023-01-23 01:06:46.174958: step: 340/533, loss: 0.057116128504276276
2023-01-23 01:06:47.345757: step: 344/533, loss: 0.04482236132025719
2023-01-23 01:06:48.541583: step: 348/533, loss: 0.034926414489746094
2023-01-23 01:06:49.788548: step: 352/533, loss: 0.14513015747070312
2023-01-23 01:06:50.980877: step: 356/533, loss: 0.03851809352636337
2023-01-23 01:06:52.121448: step: 360/533, loss: 0.006290304474532604
2023-01-23 01:06:53.280445: step: 364/533, loss: 0.018521975725889206
2023-01-23 01:06:54.449295: step: 368/533, loss: 0.010516547597944736
2023-01-23 01:06:55.637151: step: 372/533, loss: 0.057587720453739166
2023-01-23 01:06:56.808279: step: 376/533, loss: 0.0536588691174984
2023-01-23 01:06:57.976116: step: 380/533, loss: 0.05293913185596466
2023-01-23 01:06:59.134539: step: 384/533, loss: 0.04788952320814133
2023-01-23 01:07:00.350437: step: 388/533, loss: 0.032726287841796875
2023-01-23 01:07:01.549548: step: 392/533, loss: 0.011357784271240234
2023-01-23 01:07:02.738142: step: 396/533, loss: 0.018758393824100494
2023-01-23 01:07:03.918067: step: 400/533, loss: 0.04614190384745598
2023-01-23 01:07:05.083310: step: 404/533, loss: 0.09147845208644867
2023-01-23 01:07:06.251664: step: 408/533, loss: 0.005666446406394243
2023-01-23 01:07:07.408242: step: 412/533, loss: 0.014667415991425514
2023-01-23 01:07:08.566411: step: 416/533, loss: 0.022772978991270065
2023-01-23 01:07:09.733063: step: 420/533, loss: 0.09483551234006882
2023-01-23 01:07:10.983921: step: 424/533, loss: 0.01939101330935955
2023-01-23 01:07:12.166505: step: 428/533, loss: 0.018538666889071465
2023-01-23 01:07:13.311118: step: 432/533, loss: 0.024607086554169655
2023-01-23 01:07:14.497155: step: 436/533, loss: 0.2652323246002197
2023-01-23 01:07:15.662832: step: 440/533, loss: 0.10097656399011612
2023-01-23 01:07:16.852453: step: 444/533, loss: 0.27409666776657104
2023-01-23 01:07:18.014488: step: 448/533, loss: 0.08909034729003906
2023-01-23 01:07:19.207846: step: 452/533, loss: 0.3133987486362457
2023-01-23 01:07:20.399385: step: 456/533, loss: 0.1810930371284485
2023-01-23 01:07:21.543365: step: 460/533, loss: 0.040762949734926224
2023-01-23 01:07:22.719238: step: 464/533, loss: 0.061676979064941406
2023-01-23 01:07:23.950341: step: 468/533, loss: 0.4010699987411499
2023-01-23 01:07:25.149045: step: 472/533, loss: 0.07260093837976456
2023-01-23 01:07:26.338405: step: 476/533, loss: 0.28557929396629333
2023-01-23 01:07:27.557204: step: 480/533, loss: 0.14278583228588104
2023-01-23 01:07:28.710138: step: 484/533, loss: 0.041107941418886185
2023-01-23 01:07:29.865431: step: 488/533, loss: 0.058317460119724274
2023-01-23 01:07:31.010042: step: 492/533, loss: 0.017256595194339752
2023-01-23 01:07:32.192404: step: 496/533, loss: 0.08629989624023438
2023-01-23 01:07:33.371544: step: 500/533, loss: 0.7166303992271423
2023-01-23 01:07:34.491108: step: 504/533, loss: 0.03475242108106613
2023-01-23 01:07:35.655245: step: 508/533, loss: 0.5990545749664307
2023-01-23 01:07:36.871705: step: 512/533, loss: 0.0847008228302002
2023-01-23 01:07:38.034418: step: 516/533, loss: 0.3145454525947571
2023-01-23 01:07:39.190084: step: 520/533, loss: 0.04445791244506836
2023-01-23 01:07:40.368419: step: 524/533, loss: 0.12211110442876816
2023-01-23 01:07:41.547557: step: 528/533, loss: 0.03650302812457085
2023-01-23 01:07:42.739075: step: 532/533, loss: 0.022868730127811432
2023-01-23 01:07:43.933151: step: 536/533, loss: 0.4974576234817505
2023-01-23 01:07:45.131489: step: 540/533, loss: 0.05934934690594673
2023-01-23 01:07:46.324661: step: 544/533, loss: 0.6201225519180298
2023-01-23 01:07:47.525001: step: 548/533, loss: 0.0677005797624588
2023-01-23 01:07:48.702143: step: 552/533, loss: 0.056618500500917435
2023-01-23 01:07:49.894378: step: 556/533, loss: 0.05579443275928497
2023-01-23 01:07:51.082817: step: 560/533, loss: 0.07386646419763565
2023-01-23 01:07:52.247338: step: 564/533, loss: 0.08603496849536896
2023-01-23 01:07:53.432294: step: 568/533, loss: 0.09671372920274734
2023-01-23 01:07:54.590447: step: 572/533, loss: 0.07626190781593323
2023-01-23 01:07:55.742164: step: 576/533, loss: 0.12589764595031738
2023-01-23 01:07:56.922186: step: 580/533, loss: 0.07626771926879883
2023-01-23 01:07:58.100300: step: 584/533, loss: 0.1767188161611557
2023-01-23 01:07:59.282979: step: 588/533, loss: 0.0031238081865012646
2023-01-23 01:08:00.465115: step: 592/533, loss: 0.05519752576947212
2023-01-23 01:08:01.675295: step: 596/533, loss: 0.042662620544433594
2023-01-23 01:08:02.850007: step: 600/533, loss: 0.16373272240161896
2023-01-23 01:08:03.996115: step: 604/533, loss: 0.012190532870590687
2023-01-23 01:08:05.156186: step: 608/533, loss: 0.20656099915504456
2023-01-23 01:08:06.295766: step: 612/533, loss: 0.025418471544981003
2023-01-23 01:08:07.455548: step: 616/533, loss: 0.005350637715309858
2023-01-23 01:08:08.628071: step: 620/533, loss: 0.12743797898292542
2023-01-23 01:08:09.808070: step: 624/533, loss: 0.1162261962890625
2023-01-23 01:08:10.983002: step: 628/533, loss: 0.03257916122674942
2023-01-23 01:08:12.115480: step: 632/533, loss: 0.004297447390854359
2023-01-23 01:08:13.288730: step: 636/533, loss: 0.15054330229759216
2023-01-23 01:08:14.419645: step: 640/533, loss: 0.058246467262506485
2023-01-23 01:08:15.585265: step: 644/533, loss: 0.047281697392463684
2023-01-23 01:08:16.764336: step: 648/533, loss: 0.013740921393036842
2023-01-23 01:08:17.966324: step: 652/533, loss: 1.265947937965393
2023-01-23 01:08:19.170294: step: 656/533, loss: 0.053545381873846054
2023-01-23 01:08:20.317129: step: 660/533, loss: 0.08232641965150833
2023-01-23 01:08:21.513297: step: 664/533, loss: 0.01431188639253378
2023-01-23 01:08:22.708606: step: 668/533, loss: 0.009477544575929642
2023-01-23 01:08:23.896049: step: 672/533, loss: 0.2790432572364807
2023-01-23 01:08:25.057582: step: 676/533, loss: 0.05599184334278107
2023-01-23 01:08:26.231815: step: 680/533, loss: 0.10838194191455841
2023-01-23 01:08:27.407917: step: 684/533, loss: 0.04290275648236275
2023-01-23 01:08:28.556271: step: 688/533, loss: 0.09902272373437881
2023-01-23 01:08:29.736713: step: 692/533, loss: 0.013250255957245827
2023-01-23 01:08:30.913998: step: 696/533, loss: 0.06524792313575745
2023-01-23 01:08:32.087427: step: 700/533, loss: 0.019201230257749557
2023-01-23 01:08:33.258982: step: 704/533, loss: 0.01433572731912136
2023-01-23 01:08:34.447662: step: 708/533, loss: 0.01153421401977539
2023-01-23 01:08:35.639609: step: 712/533, loss: 0.08900967240333557
2023-01-23 01:08:36.823829: step: 716/533, loss: 0.1447269320487976
2023-01-23 01:08:38.026866: step: 720/533, loss: 0.11871615052223206
2023-01-23 01:08:39.174908: step: 724/533, loss: 0.02577047422528267
2023-01-23 01:08:40.330063: step: 728/533, loss: 0.08094902336597443
2023-01-23 01:08:41.548353: step: 732/533, loss: 0.06724414229393005
2023-01-23 01:08:42.703405: step: 736/533, loss: 0.05045163631439209
2023-01-23 01:08:43.876322: step: 740/533, loss: 0.017099715769290924
2023-01-23 01:08:45.095929: step: 744/533, loss: 0.2363205850124359
2023-01-23 01:08:46.286302: step: 748/533, loss: 0.0421605110168457
2023-01-23 01:08:47.531295: step: 752/533, loss: 0.09516634792089462
2023-01-23 01:08:48.731640: step: 756/533, loss: 0.07830887287855148
2023-01-23 01:08:49.896857: step: 760/533, loss: 0.0657321959733963
2023-01-23 01:08:51.077811: step: 764/533, loss: 0.038173675537109375
2023-01-23 01:08:52.293474: step: 768/533, loss: 0.0770900696516037
2023-01-23 01:08:53.465091: step: 772/533, loss: 0.011811303906142712
2023-01-23 01:08:54.630496: step: 776/533, loss: 0.04569902643561363
2023-01-23 01:08:55.830274: step: 780/533, loss: 0.10124779492616653
2023-01-23 01:08:57.046195: step: 784/533, loss: 0.0378355048596859
2023-01-23 01:08:58.213701: step: 788/533, loss: 0.10238370299339294
2023-01-23 01:08:59.430099: step: 792/533, loss: 0.0881500244140625
2023-01-23 01:09:00.618976: step: 796/533, loss: 0.020652318373322487
2023-01-23 01:09:01.830991: step: 800/533, loss: 0.06561565399169922
2023-01-23 01:09:03.041743: step: 804/533, loss: 0.5448048114776611
2023-01-23 01:09:04.233880: step: 808/533, loss: 0.039614297449588776
2023-01-23 01:09:05.375869: step: 812/533, loss: 0.019077610224485397
2023-01-23 01:09:06.559089: step: 816/533, loss: 0.10220970958471298
2023-01-23 01:09:07.719354: step: 820/533, loss: 0.03624997287988663
2023-01-23 01:09:08.889109: step: 824/533, loss: 0.008788347244262695
2023-01-23 01:09:10.101278: step: 828/533, loss: 0.06470656394958496
2023-01-23 01:09:11.258720: step: 832/533, loss: 0.06646556407213211
2023-01-23 01:09:12.420354: step: 836/533, loss: 0.060130029916763306
2023-01-23 01:09:13.590288: step: 840/533, loss: 0.038254644721746445
2023-01-23 01:09:14.810808: step: 844/533, loss: 0.0641595870256424
2023-01-23 01:09:16.020367: step: 848/533, loss: 0.007167530246078968
2023-01-23 01:09:17.186106: step: 852/533, loss: 0.05634784698486328
2023-01-23 01:09:18.394964: step: 856/533, loss: 0.11353941261768341
2023-01-23 01:09:19.595034: step: 860/533, loss: 0.05974188446998596
2023-01-23 01:09:20.756269: step: 864/533, loss: 0.17184743285179138
2023-01-23 01:09:21.928935: step: 868/533, loss: 0.015978015959262848
2023-01-23 01:09:23.066188: step: 872/533, loss: 0.4191598892211914
2023-01-23 01:09:24.250692: step: 876/533, loss: 0.13737726211547852
2023-01-23 01:09:25.443865: step: 880/533, loss: 0.019935226067900658
2023-01-23 01:09:26.614980: step: 884/533, loss: 0.8298965692520142
2023-01-23 01:09:27.822601: step: 888/533, loss: 0.12010689079761505
2023-01-23 01:09:28.966622: step: 892/533, loss: 0.12362580001354218
2023-01-23 01:09:30.161814: step: 896/533, loss: 0.10992546379566193
2023-01-23 01:09:31.349331: step: 900/533, loss: 0.06212148815393448
2023-01-23 01:09:32.545648: step: 904/533, loss: 0.034334421157836914
2023-01-23 01:09:33.696546: step: 908/533, loss: 0.04552020877599716
2023-01-23 01:09:34.914521: step: 912/533, loss: 0.014476490207016468
2023-01-23 01:09:36.124795: step: 916/533, loss: 0.05216169357299805
2023-01-23 01:09:37.294890: step: 920/533, loss: 0.054259397089481354
2023-01-23 01:09:38.481650: step: 924/533, loss: 0.05218372121453285
2023-01-23 01:09:39.676074: step: 928/533, loss: 0.05224800109863281
2023-01-23 01:09:40.840681: step: 932/533, loss: 0.02460627630352974
2023-01-23 01:09:42.009217: step: 936/533, loss: 0.12872420251369476
2023-01-23 01:09:43.193698: step: 940/533, loss: 0.37724569439888
2023-01-23 01:09:44.357924: step: 944/533, loss: 0.015972351655364037
2023-01-23 01:09:45.504030: step: 948/533, loss: 0.017873143777251244
2023-01-23 01:09:46.687903: step: 952/533, loss: 0.017248056828975677
2023-01-23 01:09:47.844869: step: 956/533, loss: 0.02011718787252903
2023-01-23 01:09:48.973000: step: 960/533, loss: 0.11006336659193039
2023-01-23 01:09:50.150065: step: 964/533, loss: 0.02671186998486519
2023-01-23 01:09:51.349720: step: 968/533, loss: 0.04826552793383598
2023-01-23 01:09:52.531420: step: 972/533, loss: 0.02652893029153347
2023-01-23 01:09:53.710062: step: 976/533, loss: 0.11934099346399307
2023-01-23 01:09:54.908483: step: 980/533, loss: 0.008259296417236328
2023-01-23 01:09:56.106872: step: 984/533, loss: 0.08100166916847229
2023-01-23 01:09:57.252690: step: 988/533, loss: 0.031232452020049095
2023-01-23 01:09:58.400181: step: 992/533, loss: 0.06072964891791344
2023-01-23 01:09:59.534042: step: 996/533, loss: 0.01717977598309517
2023-01-23 01:10:00.742252: step: 1000/533, loss: 0.017211150377988815
2023-01-23 01:10:01.970649: step: 1004/533, loss: 0.034348390996456146
2023-01-23 01:10:03.141320: step: 1008/533, loss: 0.034008074551820755
2023-01-23 01:10:04.316644: step: 1012/533, loss: 0.04258880764245987
2023-01-23 01:10:05.459792: step: 1016/533, loss: 0.09461527317762375
2023-01-23 01:10:06.622106: step: 1020/533, loss: 0.1257382333278656
2023-01-23 01:10:07.768963: step: 1024/533, loss: 0.10754475742578506
2023-01-23 01:10:08.910775: step: 1028/533, loss: 0.09646854549646378
2023-01-23 01:10:10.071894: step: 1032/533, loss: 0.0010723829036578536
2023-01-23 01:10:11.265781: step: 1036/533, loss: 0.07256393879652023
2023-01-23 01:10:12.425250: step: 1040/533, loss: 0.07233639061450958
2023-01-23 01:10:13.644061: step: 1044/533, loss: 0.06914357841014862
2023-01-23 01:10:14.876921: step: 1048/533, loss: 0.03955082967877388
2023-01-23 01:10:16.054675: step: 1052/533, loss: 0.3587758243083954
2023-01-23 01:10:17.223303: step: 1056/533, loss: 0.06304188072681427
2023-01-23 01:10:18.403782: step: 1060/533, loss: 0.06420469284057617
2023-01-23 01:10:19.590890: step: 1064/533, loss: 0.057447340339422226
2023-01-23 01:10:20.756637: step: 1068/533, loss: 0.027955342084169388
2023-01-23 01:10:21.919838: step: 1072/533, loss: 0.1225438117980957
2023-01-23 01:10:23.094624: step: 1076/533, loss: 0.11520595848560333
2023-01-23 01:10:24.260384: step: 1080/533, loss: 0.16201798617839813
2023-01-23 01:10:25.448753: step: 1084/533, loss: 0.12088815867900848
2023-01-23 01:10:26.620993: step: 1088/533, loss: 0.04511423408985138
2023-01-23 01:10:27.806882: step: 1092/533, loss: 0.0017524241702631116
2023-01-23 01:10:28.957757: step: 1096/533, loss: 0.10824938118457794
2023-01-23 01:10:30.167489: step: 1100/533, loss: 0.07720164954662323
2023-01-23 01:10:31.365522: step: 1104/533, loss: 0.1040860116481781
2023-01-23 01:10:32.525721: step: 1108/533, loss: 0.034945059567689896
2023-01-23 01:10:33.665196: step: 1112/533, loss: 0.04620242491364479
2023-01-23 01:10:34.823199: step: 1116/533, loss: 0.07007589191198349
2023-01-23 01:10:35.999421: step: 1120/533, loss: 0.035433389246463776
2023-01-23 01:10:37.194930: step: 1124/533, loss: 0.008829689584672451
2023-01-23 01:10:38.427445: step: 1128/533, loss: 0.09057541191577911
2023-01-23 01:10:39.672931: step: 1132/533, loss: 0.08630113303661346
2023-01-23 01:10:40.850912: step: 1136/533, loss: 0.4293048679828644
2023-01-23 01:10:42.027663: step: 1140/533, loss: 0.029358576983213425
2023-01-23 01:10:43.204216: step: 1144/533, loss: 0.19015425443649292
2023-01-23 01:10:44.349830: step: 1148/533, loss: 0.04289841651916504
2023-01-23 01:10:45.528175: step: 1152/533, loss: 0.12921875715255737
2023-01-23 01:10:46.716563: step: 1156/533, loss: 0.08202410489320755
2023-01-23 01:10:47.893340: step: 1160/533, loss: 0.06566992402076721
2023-01-23 01:10:49.040132: step: 1164/533, loss: 0.272839218378067
2023-01-23 01:10:50.215030: step: 1168/533, loss: 0.07983341068029404
2023-01-23 01:10:51.353993: step: 1172/533, loss: 0.0463099479675293
2023-01-23 01:10:52.500054: step: 1176/533, loss: 0.5903288125991821
2023-01-23 01:10:53.635989: step: 1180/533, loss: 0.11411400139331818
2023-01-23 01:10:54.802035: step: 1184/533, loss: 0.2203051596879959
2023-01-23 01:10:55.978020: step: 1188/533, loss: 0.2530983090400696
2023-01-23 01:10:57.149131: step: 1192/533, loss: 0.06348276138305664
2023-01-23 01:10:58.314806: step: 1196/533, loss: 0.09556732326745987
2023-01-23 01:10:59.472561: step: 1200/533, loss: 0.06467476487159729
2023-01-23 01:11:00.636888: step: 1204/533, loss: 0.07003694027662277
2023-01-23 01:11:01.801719: step: 1208/533, loss: 0.019532132893800735
2023-01-23 01:11:02.962480: step: 1212/533, loss: 0.06544151157140732
2023-01-23 01:11:04.146654: step: 1216/533, loss: 0.10628766566514969
2023-01-23 01:11:05.333758: step: 1220/533, loss: 0.025108743458986282
2023-01-23 01:11:06.514813: step: 1224/533, loss: 0.046537257730960846
2023-01-23 01:11:07.669358: step: 1228/533, loss: 0.04871067777276039
2023-01-23 01:11:08.862482: step: 1232/533, loss: 0.08525543659925461
2023-01-23 01:11:10.009824: step: 1236/533, loss: 0.020444059744477272
2023-01-23 01:11:11.146652: step: 1240/533, loss: 0.026122761890292168
2023-01-23 01:11:12.376473: step: 1244/533, loss: 0.09374479949474335
2023-01-23 01:11:13.544582: step: 1248/533, loss: 0.07252321392297745
2023-01-23 01:11:14.690282: step: 1252/533, loss: 0.1519780158996582
2023-01-23 01:11:15.879347: step: 1256/533, loss: 0.22880668938159943
2023-01-23 01:11:17.082528: step: 1260/533, loss: 0.07265176624059677
2023-01-23 01:11:18.274469: step: 1264/533, loss: 0.09801264107227325
2023-01-23 01:11:19.465267: step: 1268/533, loss: 0.005519008729606867
2023-01-23 01:11:20.668543: step: 1272/533, loss: 0.01893758773803711
2023-01-23 01:11:21.868322: step: 1276/533, loss: 0.006653213407844305
2023-01-23 01:11:23.033570: step: 1280/533, loss: 0.04139719158411026
2023-01-23 01:11:24.195930: step: 1284/533, loss: 0.07049236446619034
2023-01-23 01:11:25.346305: step: 1288/533, loss: 0.08337441086769104
2023-01-23 01:11:26.528232: step: 1292/533, loss: 0.030786896124482155
2023-01-23 01:11:27.734528: step: 1296/533, loss: 0.02945718728005886
2023-01-23 01:11:28.933147: step: 1300/533, loss: 0.16059261560440063
2023-01-23 01:11:30.130307: step: 1304/533, loss: 0.11569375544786453
2023-01-23 01:11:31.343037: step: 1308/533, loss: 0.06544365733861923
2023-01-23 01:11:32.519849: step: 1312/533, loss: 0.015305234119296074
2023-01-23 01:11:33.703684: step: 1316/533, loss: 0.11670169979333878
2023-01-23 01:11:34.866993: step: 1320/533, loss: 0.028336383402347565
2023-01-23 01:11:36.059475: step: 1324/533, loss: 0.005647182464599609
2023-01-23 01:11:37.267215: step: 1328/533, loss: 0.722735583782196
2023-01-23 01:11:38.410859: step: 1332/533, loss: 0.08525466918945312
2023-01-23 01:11:39.607297: step: 1336/533, loss: 0.1007390096783638
2023-01-23 01:11:40.800576: step: 1340/533, loss: 0.04582986980676651
2023-01-23 01:11:41.955265: step: 1344/533, loss: 0.23077526688575745
2023-01-23 01:11:43.116325: step: 1348/533, loss: 0.15750399231910706
2023-01-23 01:11:44.307042: step: 1352/533, loss: 0.4472717344760895
2023-01-23 01:11:45.492774: step: 1356/533, loss: 0.05208740383386612
2023-01-23 01:11:46.688371: step: 1360/533, loss: 0.0662989616394043
2023-01-23 01:11:47.855172: step: 1364/533, loss: 0.04457426071166992
2023-01-23 01:11:49.052949: step: 1368/533, loss: 0.08263588696718216
2023-01-23 01:11:50.216434: step: 1372/533, loss: 0.0627906322479248
2023-01-23 01:11:51.366211: step: 1376/533, loss: 0.1397140920162201
2023-01-23 01:11:52.531913: step: 1380/533, loss: 0.043340303003787994
2023-01-23 01:11:53.709093: step: 1384/533, loss: 0.38710179924964905
2023-01-23 01:11:54.862943: step: 1388/533, loss: 0.01959371566772461
2023-01-23 01:11:56.015710: step: 1392/533, loss: 0.06831777095794678
2023-01-23 01:11:57.212162: step: 1396/533, loss: 0.036202672868967056
2023-01-23 01:11:58.381333: step: 1400/533, loss: 0.12237277626991272
2023-01-23 01:11:59.592893: step: 1404/533, loss: 0.06173763424158096
2023-01-23 01:12:00.775478: step: 1408/533, loss: 0.05011396482586861
2023-01-23 01:12:01.959648: step: 1412/533, loss: 0.23885507881641388
2023-01-23 01:12:03.101515: step: 1416/533, loss: 0.09139814227819443
2023-01-23 01:12:04.256907: step: 1420/533, loss: 0.42762821912765503
2023-01-23 01:12:05.433272: step: 1424/533, loss: 0.11530523747205734
2023-01-23 01:12:06.596158: step: 1428/533, loss: 0.11973657459020615
2023-01-23 01:12:07.780955: step: 1432/533, loss: 0.21258427202701569
2023-01-23 01:12:08.970320: step: 1436/533, loss: 0.04773378372192383
2023-01-23 01:12:10.190216: step: 1440/533, loss: 0.0718592181801796
2023-01-23 01:12:11.398086: step: 1444/533, loss: 0.006921005435287952
2023-01-23 01:12:12.605344: step: 1448/533, loss: 0.01573786698281765
2023-01-23 01:12:13.845593: step: 1452/533, loss: 0.33907264471054077
2023-01-23 01:12:14.988694: step: 1456/533, loss: 0.08991508185863495
2023-01-23 01:12:16.112820: step: 1460/533, loss: 0.09660325199365616
2023-01-23 01:12:17.281197: step: 1464/533, loss: 0.06763105094432831
2023-01-23 01:12:18.462352: step: 1468/533, loss: 0.2460470199584961
2023-01-23 01:12:19.613537: step: 1472/533, loss: 0.01610422134399414
2023-01-23 01:12:20.769813: step: 1476/533, loss: 0.025304174050688744
2023-01-23 01:12:21.918533: step: 1480/533, loss: 0.06752438098192215
2023-01-23 01:12:23.130055: step: 1484/533, loss: 0.09731343388557434
2023-01-23 01:12:24.352741: step: 1488/533, loss: 0.04540739208459854
2023-01-23 01:12:25.528816: step: 1492/533, loss: 0.08259592205286026
2023-01-23 01:12:26.678683: step: 1496/533, loss: 0.03957099840044975
2023-01-23 01:12:27.832198: step: 1500/533, loss: 0.06335163116455078
2023-01-23 01:12:29.018760: step: 1504/533, loss: 0.0810893103480339
2023-01-23 01:12:30.181735: step: 1508/533, loss: 0.013915968127548695
2023-01-23 01:12:31.337429: step: 1512/533, loss: 0.1194813996553421
2023-01-23 01:12:32.551107: step: 1516/533, loss: 0.0778312236070633
2023-01-23 01:12:33.713902: step: 1520/533, loss: 0.06056080013513565
2023-01-23 01:12:34.890446: step: 1524/533, loss: 0.07550602406263351
2023-01-23 01:12:36.025987: step: 1528/533, loss: 0.0341365821659565
2023-01-23 01:12:37.209608: step: 1532/533, loss: 0.12445640563964844
2023-01-23 01:12:38.388203: step: 1536/533, loss: 0.3284502923488617
2023-01-23 01:12:39.589827: step: 1540/533, loss: 0.12210474163293839
2023-01-23 01:12:40.818649: step: 1544/533, loss: 0.08749590069055557
2023-01-23 01:12:42.000971: step: 1548/533, loss: 0.13944703340530396
2023-01-23 01:12:43.194742: step: 1552/533, loss: 0.028626251965761185
2023-01-23 01:12:44.364587: step: 1556/533, loss: 0.2883397042751312
2023-01-23 01:12:45.508212: step: 1560/533, loss: 0.19004663825035095
2023-01-23 01:12:46.678239: step: 1564/533, loss: 0.17749014496803284
2023-01-23 01:12:47.862776: step: 1568/533, loss: 0.12720413506031036
2023-01-23 01:12:49.064026: step: 1572/533, loss: 0.5603672862052917
2023-01-23 01:12:50.253890: step: 1576/533, loss: 0.018171025440096855
2023-01-23 01:12:51.446161: step: 1580/533, loss: 0.40120047330856323
2023-01-23 01:12:52.672278: step: 1584/533, loss: 0.015099716372787952
2023-01-23 01:12:53.853243: step: 1588/533, loss: 0.07071518898010254
2023-01-23 01:12:54.978266: step: 1592/533, loss: 0.008141708560287952
2023-01-23 01:12:56.144020: step: 1596/533, loss: 0.09460707008838654
2023-01-23 01:12:57.324454: step: 1600/533, loss: 0.17722895741462708
2023-01-23 01:12:58.479645: step: 1604/533, loss: 0.09161920845508575
2023-01-23 01:12:59.645593: step: 1608/533, loss: 0.04561030492186546
2023-01-23 01:13:00.867239: step: 1612/533, loss: 0.15457019209861755
2023-01-23 01:13:02.066618: step: 1616/533, loss: 0.15258640050888062
2023-01-23 01:13:03.231958: step: 1620/533, loss: 0.017450714483857155
2023-01-23 01:13:04.419328: step: 1624/533, loss: 0.07702770829200745
2023-01-23 01:13:05.611782: step: 1628/533, loss: 0.08610725402832031
2023-01-23 01:13:06.767248: step: 1632/533, loss: 0.02127513848245144
2023-01-23 01:13:08.006342: step: 1636/533, loss: 0.07588864117860794
2023-01-23 01:13:09.160399: step: 1640/533, loss: 0.040285490453243256
2023-01-23 01:13:10.357635: step: 1644/533, loss: 0.06690329313278198
2023-01-23 01:13:11.515352: step: 1648/533, loss: 0.027987100183963776
2023-01-23 01:13:12.705984: step: 1652/533, loss: 0.021415090188384056
2023-01-23 01:13:13.862870: step: 1656/533, loss: 0.1005639135837555
2023-01-23 01:13:15.077078: step: 1660/533, loss: 0.6033145785331726
2023-01-23 01:13:16.262518: step: 1664/533, loss: 0.057854942977428436
2023-01-23 01:13:17.407695: step: 1668/533, loss: 0.13870087265968323
2023-01-23 01:13:18.568037: step: 1672/533, loss: 0.06631994247436523
2023-01-23 01:13:19.813776: step: 1676/533, loss: 0.04903984069824219
2023-01-23 01:13:21.023117: step: 1680/533, loss: 0.05277226120233536
2023-01-23 01:13:22.185502: step: 1684/533, loss: 0.12280307710170746
2023-01-23 01:13:23.394790: step: 1688/533, loss: 0.12222793698310852
2023-01-23 01:13:24.578092: step: 1692/533, loss: 0.0692349448800087
2023-01-23 01:13:25.778085: step: 1696/533, loss: 0.02035648748278618
2023-01-23 01:13:26.991013: step: 1700/533, loss: 0.055666401982307434
2023-01-23 01:13:28.167049: step: 1704/533, loss: 0.05515652149915695
2023-01-23 01:13:29.314200: step: 1708/533, loss: 0.09315033257007599
2023-01-23 01:13:30.486871: step: 1712/533, loss: 0.00919046439230442
2023-01-23 01:13:31.647211: step: 1716/533, loss: 0.056665562093257904
2023-01-23 01:13:32.821421: step: 1720/533, loss: 0.10833263397216797
2023-01-23 01:13:33.985647: step: 1724/533, loss: 0.08019638061523438
2023-01-23 01:13:35.162586: step: 1728/533, loss: 0.03905963897705078
2023-01-23 01:13:36.359356: step: 1732/533, loss: 0.04802331700921059
2023-01-23 01:13:37.577234: step: 1736/533, loss: 0.1047694981098175
2023-01-23 01:13:38.760053: step: 1740/533, loss: 0.039585210382938385
2023-01-23 01:13:39.919832: step: 1744/533, loss: 0.005497646518051624
2023-01-23 01:13:41.111357: step: 1748/533, loss: 0.3444347083568573
2023-01-23 01:13:42.375517: step: 1752/533, loss: 0.08689117431640625
2023-01-23 01:13:43.551811: step: 1756/533, loss: 0.016423894092440605
2023-01-23 01:13:44.744784: step: 1760/533, loss: 0.13254165649414062
2023-01-23 01:13:45.954313: step: 1764/533, loss: 0.05878373235464096
2023-01-23 01:13:47.127576: step: 1768/533, loss: 0.03589468076825142
2023-01-23 01:13:48.282301: step: 1772/533, loss: 0.6198861598968506
2023-01-23 01:13:49.445121: step: 1776/533, loss: 0.11236973106861115
2023-01-23 01:13:50.613075: step: 1780/533, loss: 0.12118339538574219
2023-01-23 01:13:51.798458: step: 1784/533, loss: 0.03707880899310112
2023-01-23 01:13:52.965367: step: 1788/533, loss: 0.004126453772187233
2023-01-23 01:13:54.124628: step: 1792/533, loss: 0.01949899084866047
2023-01-23 01:13:55.309831: step: 1796/533, loss: 0.2387535274028778
2023-01-23 01:13:56.459754: step: 1800/533, loss: 0.02178182639181614
2023-01-23 01:13:57.673948: step: 1804/533, loss: 0.1231098398566246
2023-01-23 01:13:58.836907: step: 1808/533, loss: 0.05806431919336319
2023-01-23 01:14:00.034416: step: 1812/533, loss: 0.015900611877441406
2023-01-23 01:14:01.251609: step: 1816/533, loss: 0.036623287945985794
2023-01-23 01:14:02.447806: step: 1820/533, loss: 0.044013749808073044
2023-01-23 01:14:03.632306: step: 1824/533, loss: 0.03783436119556427
2023-01-23 01:14:04.795127: step: 1828/533, loss: 0.027425026521086693
2023-01-23 01:14:05.976173: step: 1832/533, loss: 0.06180458143353462
2023-01-23 01:14:07.196753: step: 1836/533, loss: 0.025116827338933945
2023-01-23 01:14:08.415423: step: 1840/533, loss: 0.04083309322595596
2023-01-23 01:14:09.631357: step: 1844/533, loss: 0.058376505970954895
2023-01-23 01:14:10.833747: step: 1848/533, loss: 0.24160251021385193
2023-01-23 01:14:12.001265: step: 1852/533, loss: 0.013720654882490635
2023-01-23 01:14:13.189572: step: 1856/533, loss: 0.0057541849091649055
2023-01-23 01:14:14.347793: step: 1860/533, loss: 0.001074123429134488
2023-01-23 01:14:15.473481: step: 1864/533, loss: 0.03571796417236328
2023-01-23 01:14:16.633548: step: 1868/533, loss: 0.041402243077754974
2023-01-23 01:14:17.804068: step: 1872/533, loss: 0.02385539934039116
2023-01-23 01:14:19.002032: step: 1876/533, loss: 0.048597145825624466
2023-01-23 01:14:20.160052: step: 1880/533, loss: 0.08617869019508362
2023-01-23 01:14:21.347810: step: 1884/533, loss: 0.058133698999881744
2023-01-23 01:14:22.554370: step: 1888/533, loss: 0.043524548411369324
2023-01-23 01:14:23.723582: step: 1892/533, loss: 0.11809349060058594
2023-01-23 01:14:24.931670: step: 1896/533, loss: 0.12552142143249512
2023-01-23 01:14:26.103344: step: 1900/533, loss: 0.08240270614624023
2023-01-23 01:14:27.274453: step: 1904/533, loss: 0.025552939623594284
2023-01-23 01:14:28.441377: step: 1908/533, loss: 0.02073340304195881
2023-01-23 01:14:29.623901: step: 1912/533, loss: 0.12882208824157715
2023-01-23 01:14:30.816419: step: 1916/533, loss: 0.1296786367893219
2023-01-23 01:14:31.993691: step: 1920/533, loss: 0.09653263539075851
2023-01-23 01:14:33.168230: step: 1924/533, loss: 0.07321052253246307
2023-01-23 01:14:34.321224: step: 1928/533, loss: 0.12343092262744904
2023-01-23 01:14:35.522689: step: 1932/533, loss: 0.06080026552081108
2023-01-23 01:14:36.716349: step: 1936/533, loss: 0.03781747817993164
2023-01-23 01:14:37.876368: step: 1940/533, loss: 0.025562716647982597
2023-01-23 01:14:39.059010: step: 1944/533, loss: 0.11140938103199005
2023-01-23 01:14:40.245588: step: 1948/533, loss: 0.030676936730742455
2023-01-23 01:14:41.391752: step: 1952/533, loss: 0.06337670981884003
2023-01-23 01:14:42.573536: step: 1956/533, loss: 0.025703812018036842
2023-01-23 01:14:43.749217: step: 1960/533, loss: 0.11980142444372177
2023-01-23 01:14:44.907693: step: 1964/533, loss: 0.08251719921827316
2023-01-23 01:14:46.077974: step: 1968/533, loss: 0.21277998387813568
2023-01-23 01:14:47.282901: step: 1972/533, loss: 0.05088827386498451
2023-01-23 01:14:48.454012: step: 1976/533, loss: 0.3476164638996124
2023-01-23 01:14:49.613374: step: 1980/533, loss: 0.07201957702636719
2023-01-23 01:14:50.789244: step: 1984/533, loss: 0.02053804323077202
2023-01-23 01:14:51.940527: step: 1988/533, loss: 0.3541708290576935
2023-01-23 01:14:53.117654: step: 1992/533, loss: 0.04240398481488228
2023-01-23 01:14:54.315224: step: 1996/533, loss: 0.13211165368556976
2023-01-23 01:14:55.491847: step: 2000/533, loss: 0.10249615460634232
2023-01-23 01:14:56.694360: step: 2004/533, loss: 0.1062891036272049
2023-01-23 01:14:57.903539: step: 2008/533, loss: 0.16611194610595703
2023-01-23 01:14:59.079124: step: 2012/533, loss: 0.053447723388671875
2023-01-23 01:15:00.229544: step: 2016/533, loss: 1.185105562210083
2023-01-23 01:15:01.412264: step: 2020/533, loss: 0.11249179393053055
2023-01-23 01:15:02.620080: step: 2024/533, loss: 0.18461018800735474
2023-01-23 01:15:03.782460: step: 2028/533, loss: 0.07553768157958984
2023-01-23 01:15:04.946559: step: 2032/533, loss: 0.1200229674577713
2023-01-23 01:15:06.103099: step: 2036/533, loss: 0.1078365296125412
2023-01-23 01:15:07.249368: step: 2040/533, loss: 0.09825363755226135
2023-01-23 01:15:08.400245: step: 2044/533, loss: 0.023118305951356888
2023-01-23 01:15:09.592161: step: 2048/533, loss: 0.03482646867632866
2023-01-23 01:15:10.771489: step: 2052/533, loss: 0.019292794167995453
2023-01-23 01:15:12.011899: step: 2056/533, loss: 0.033036209642887115
2023-01-23 01:15:13.158638: step: 2060/533, loss: 0.03395429998636246
2023-01-23 01:15:14.348663: step: 2064/533, loss: 0.04866061359643936
2023-01-23 01:15:15.506034: step: 2068/533, loss: 0.1779816597700119
2023-01-23 01:15:16.676975: step: 2072/533, loss: 0.5045151114463806
2023-01-23 01:15:17.859567: step: 2076/533, loss: 1.1006358861923218
2023-01-23 01:15:19.029641: step: 2080/533, loss: 0.1859375685453415
2023-01-23 01:15:20.208763: step: 2084/533, loss: 0.150996595621109
2023-01-23 01:15:21.442021: step: 2088/533, loss: 0.024134159088134766
2023-01-23 01:15:22.605981: step: 2092/533, loss: 0.07079525291919708
2023-01-23 01:15:23.810535: step: 2096/533, loss: 0.10572786629199982
2023-01-23 01:15:24.960076: step: 2100/533, loss: 0.07872743904590607
2023-01-23 01:15:26.105235: step: 2104/533, loss: 0.12590566277503967
2023-01-23 01:15:27.260520: step: 2108/533, loss: 0.0893617644906044
2023-01-23 01:15:28.442773: step: 2112/533, loss: 0.054971419274806976
2023-01-23 01:15:29.594235: step: 2116/533, loss: 0.022372521460056305
2023-01-23 01:15:30.771858: step: 2120/533, loss: 0.04605302959680557
2023-01-23 01:15:31.978631: step: 2124/533, loss: 0.014611768536269665
2023-01-23 01:15:33.146688: step: 2128/533, loss: 0.1182146966457367
2023-01-23 01:15:34.288692: step: 2132/533, loss: 0.0826452299952507
==================================================
Loss: 0.104
--------------------
Dev: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.38636363636363635, 'r': 0.4722222222222222, 'f1': 0.425}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:16:32.234474: step: 4/533, loss: 0.045775607228279114
2023-01-23 01:16:33.411565: step: 8/533, loss: 0.041579537093639374
2023-01-23 01:16:34.614541: step: 12/533, loss: 0.08029906451702118
2023-01-23 01:16:35.772868: step: 16/533, loss: 0.03169608116149902
2023-01-23 01:16:36.943888: step: 20/533, loss: 0.028263472020626068
2023-01-23 01:16:38.118708: step: 24/533, loss: 0.30895429849624634
2023-01-23 01:16:39.305049: step: 28/533, loss: 0.10805211961269379
2023-01-23 01:16:40.486892: step: 32/533, loss: 0.07137098908424377
2023-01-23 01:16:41.651336: step: 36/533, loss: 0.02403836138546467
2023-01-23 01:16:42.851693: step: 40/533, loss: 0.06653881072998047
2023-01-23 01:16:44.004428: step: 44/533, loss: 0.020636750385165215
2023-01-23 01:16:45.189235: step: 48/533, loss: 0.010600566864013672
2023-01-23 01:16:46.396095: step: 52/533, loss: 0.04670543596148491
2023-01-23 01:16:47.580730: step: 56/533, loss: 0.27407702803611755
2023-01-23 01:16:48.785265: step: 60/533, loss: 0.08262339234352112
2023-01-23 01:16:49.967462: step: 64/533, loss: 0.05509508401155472
2023-01-23 01:16:51.174485: step: 68/533, loss: 0.13145074248313904
2023-01-23 01:16:52.380729: step: 72/533, loss: 0.06372890621423721
2023-01-23 01:16:53.531374: step: 76/533, loss: 0.15012378990650177
2023-01-23 01:16:54.714969: step: 80/533, loss: 0.001420688582584262
2023-01-23 01:16:55.888431: step: 84/533, loss: 0.08213672786951065
2023-01-23 01:16:57.058547: step: 88/533, loss: 0.26611536741256714
2023-01-23 01:16:58.273842: step: 92/533, loss: 0.05539955943822861
2023-01-23 01:16:59.425086: step: 96/533, loss: 0.42285194993019104
2023-01-23 01:17:00.609546: step: 100/533, loss: 0.08684978634119034
2023-01-23 01:17:01.784712: step: 104/533, loss: 0.010871458798646927
2023-01-23 01:17:02.960077: step: 108/533, loss: 0.2614063322544098
2023-01-23 01:17:04.178917: step: 112/533, loss: 0.18899306654930115
2023-01-23 01:17:05.372924: step: 116/533, loss: 0.009564495645463467
2023-01-23 01:17:06.507340: step: 120/533, loss: 0.014503668993711472
2023-01-23 01:17:07.730288: step: 124/533, loss: 0.05736379697918892
2023-01-23 01:17:08.907263: step: 128/533, loss: 0.2594629228115082
2023-01-23 01:17:10.098199: step: 132/533, loss: 0.12998512387275696
2023-01-23 01:17:11.274807: step: 136/533, loss: 0.0793793722987175
2023-01-23 01:17:12.462621: step: 140/533, loss: 0.002503824420273304
2023-01-23 01:17:13.603561: step: 144/533, loss: 0.07496003806591034
2023-01-23 01:17:14.746895: step: 148/533, loss: 0.023552369326353073
2023-01-23 01:17:15.928923: step: 152/533, loss: 0.05401415750384331
2023-01-23 01:17:17.082072: step: 156/533, loss: 0.00713500939309597
2023-01-23 01:17:18.284465: step: 160/533, loss: 0.06813764572143555
2023-01-23 01:17:19.453586: step: 164/533, loss: 0.023251915350556374
2023-01-23 01:17:20.665349: step: 168/533, loss: 0.032544899731874466
2023-01-23 01:17:21.840827: step: 172/533, loss: 0.11059360206127167
2023-01-23 01:17:22.995322: step: 176/533, loss: 0.09497089684009552
2023-01-23 01:17:24.163449: step: 180/533, loss: 0.02761373668909073
2023-01-23 01:17:25.345402: step: 184/533, loss: 0.002765703247860074
2023-01-23 01:17:26.483373: step: 188/533, loss: 0.0524420291185379
2023-01-23 01:17:27.668565: step: 192/533, loss: 0.2073441445827484
2023-01-23 01:17:28.835837: step: 196/533, loss: 0.02808818779885769
2023-01-23 01:17:30.027728: step: 200/533, loss: 0.072445347905159
2023-01-23 01:17:31.214973: step: 204/533, loss: 0.13380718231201172
2023-01-23 01:17:32.397471: step: 208/533, loss: 0.03206147998571396
2023-01-23 01:17:33.563262: step: 212/533, loss: 0.003026771591976285
2023-01-23 01:17:34.723348: step: 216/533, loss: 0.1567460149526596
2023-01-23 01:17:35.910892: step: 220/533, loss: 0.03535861894488335
2023-01-23 01:17:37.085167: step: 224/533, loss: 0.09771156311035156
2023-01-23 01:17:38.244709: step: 228/533, loss: 0.17733033001422882
2023-01-23 01:17:39.404796: step: 232/533, loss: 0.1689428836107254
2023-01-23 01:17:40.569415: step: 236/533, loss: 0.1843942105770111
2023-01-23 01:17:41.790964: step: 240/533, loss: 0.08619699627161026
2023-01-23 01:17:42.970527: step: 244/533, loss: 0.08284597098827362
2023-01-23 01:17:44.214424: step: 248/533, loss: 0.06134033203125
2023-01-23 01:17:45.405771: step: 252/533, loss: 0.09902391582727432
2023-01-23 01:17:46.546272: step: 256/533, loss: 0.06408510357141495
2023-01-23 01:17:47.709976: step: 260/533, loss: 0.2765384912490845
2023-01-23 01:17:48.884905: step: 264/533, loss: 0.061306096613407135
2023-01-23 01:17:50.068433: step: 268/533, loss: 0.02085442654788494
2023-01-23 01:17:51.203487: step: 272/533, loss: 0.04109468683600426
2023-01-23 01:17:52.395763: step: 276/533, loss: 0.02451331540942192
2023-01-23 01:17:53.585864: step: 280/533, loss: 0.005088329315185547
2023-01-23 01:17:54.815380: step: 284/533, loss: 0.01680002361536026
2023-01-23 01:17:56.033499: step: 288/533, loss: 0.18105259537696838
2023-01-23 01:17:57.199202: step: 292/533, loss: 0.02563619613647461
2023-01-23 01:17:58.338187: step: 296/533, loss: 0.07982616126537323
2023-01-23 01:17:59.499485: step: 300/533, loss: 0.09824800491333008
2023-01-23 01:18:00.657958: step: 304/533, loss: 0.11986671388149261
2023-01-23 01:18:01.850405: step: 308/533, loss: 0.03739624097943306
2023-01-23 01:18:03.011025: step: 312/533, loss: 0.06771669536828995
2023-01-23 01:18:04.181949: step: 316/533, loss: 0.0616641640663147
2023-01-23 01:18:05.341328: step: 320/533, loss: 0.02994365803897381
2023-01-23 01:18:06.495533: step: 324/533, loss: 0.017020177096128464
2023-01-23 01:18:07.670392: step: 328/533, loss: 0.06182847172021866
2023-01-23 01:18:08.830895: step: 332/533, loss: 0.021282721310853958
2023-01-23 01:18:09.964497: step: 336/533, loss: 0.01936183124780655
2023-01-23 01:18:11.177084: step: 340/533, loss: 0.08292493969202042
2023-01-23 01:18:12.360993: step: 344/533, loss: 0.02923121489584446
2023-01-23 01:18:13.540515: step: 348/533, loss: 0.01003417931497097
2023-01-23 01:18:14.695364: step: 352/533, loss: 0.04278698191046715
2023-01-23 01:18:15.902466: step: 356/533, loss: 0.0335271842777729
2023-01-23 01:18:17.113905: step: 360/533, loss: 0.06862793117761612
2023-01-23 01:18:18.294614: step: 364/533, loss: 0.016425227746367455
2023-01-23 01:18:19.454279: step: 368/533, loss: 0.038833893835544586
2023-01-23 01:18:20.642558: step: 372/533, loss: 0.16099020838737488
2023-01-23 01:18:21.837389: step: 376/533, loss: 0.08399849385023117
2023-01-23 01:18:23.017757: step: 380/533, loss: 0.06945972889661789
2023-01-23 01:18:24.177332: step: 384/533, loss: 0.08206329494714737
2023-01-23 01:18:25.362048: step: 388/533, loss: 0.001986599061638117
2023-01-23 01:18:26.536716: step: 392/533, loss: 0.09394264221191406
2023-01-23 01:18:27.696807: step: 396/533, loss: 0.05575890466570854
2023-01-23 01:18:28.914086: step: 400/533, loss: 0.0068223001435399055
2023-01-23 01:18:30.075708: step: 404/533, loss: 0.04055070877075195
2023-01-23 01:18:31.225490: step: 408/533, loss: 0.02395925484597683
2023-01-23 01:18:32.365554: step: 412/533, loss: 0.008512115105986595
2023-01-23 01:18:33.509925: step: 416/533, loss: 0.03124713897705078
2023-01-23 01:18:34.705255: step: 420/533, loss: 0.11245842278003693
2023-01-23 01:18:35.834273: step: 424/533, loss: 0.09764566272497177
2023-01-23 01:18:37.044857: step: 428/533, loss: 0.07032451778650284
2023-01-23 01:18:38.238241: step: 432/533, loss: 0.060978200286626816
2023-01-23 01:18:39.399800: step: 436/533, loss: 0.04816289246082306
2023-01-23 01:18:40.550862: step: 440/533, loss: 0.18946895003318787
2023-01-23 01:18:41.689544: step: 444/533, loss: 0.06754856556653976
2023-01-23 01:18:42.899587: step: 448/533, loss: 0.007838916964828968
2023-01-23 01:18:44.092885: step: 452/533, loss: 0.0027926205657422543
2023-01-23 01:18:45.243660: step: 456/533, loss: 0.038857340812683105
2023-01-23 01:18:46.395979: step: 460/533, loss: 0.0311871524900198
2023-01-23 01:18:47.521574: step: 464/533, loss: 0.12137894332408905
2023-01-23 01:18:48.714092: step: 468/533, loss: 0.003990650177001953
2023-01-23 01:18:49.936486: step: 472/533, loss: 0.0762060135602951
2023-01-23 01:18:51.103363: step: 476/533, loss: 0.039781905710697174
2023-01-23 01:18:52.280911: step: 480/533, loss: 0.09409356117248535
2023-01-23 01:18:53.400856: step: 484/533, loss: 0.21389159560203552
2023-01-23 01:18:54.563837: step: 488/533, loss: 0.041011907160282135
2023-01-23 01:18:55.723453: step: 492/533, loss: 0.12473776936531067
2023-01-23 01:18:56.920241: step: 496/533, loss: 0.16382838785648346
2023-01-23 01:18:58.088565: step: 500/533, loss: 0.04423399269580841
2023-01-23 01:18:59.230815: step: 504/533, loss: 0.08094783127307892
2023-01-23 01:19:00.423291: step: 508/533, loss: 0.05893287807703018
2023-01-23 01:19:01.643200: step: 512/533, loss: 0.2006063461303711
2023-01-23 01:19:02.873497: step: 516/533, loss: 0.0035518647637218237
2023-01-23 01:19:04.063287: step: 520/533, loss: 0.012249970808625221
2023-01-23 01:19:05.268237: step: 524/533, loss: 0.03733997419476509
2023-01-23 01:19:06.511251: step: 528/533, loss: 0.19792062044143677
2023-01-23 01:19:07.714896: step: 532/533, loss: 0.022332191467285156
2023-01-23 01:19:08.945824: step: 536/533, loss: 0.08081942051649094
2023-01-23 01:19:10.124833: step: 540/533, loss: 0.1203208938241005
2023-01-23 01:19:11.305937: step: 544/533, loss: 0.01227712631225586
2023-01-23 01:19:12.517642: step: 548/533, loss: 0.05710621178150177
2023-01-23 01:19:13.705201: step: 552/533, loss: 0.09651708602905273
2023-01-23 01:19:14.902560: step: 556/533, loss: 0.059904247522354126
2023-01-23 01:19:16.054618: step: 560/533, loss: 0.026563310995697975
2023-01-23 01:19:17.233289: step: 564/533, loss: 0.02484150044620037
2023-01-23 01:19:18.409988: step: 568/533, loss: 0.12736962735652924
2023-01-23 01:19:19.585655: step: 572/533, loss: 0.017676640301942825
2023-01-23 01:19:20.760738: step: 576/533, loss: 0.028828907757997513
2023-01-23 01:19:21.958910: step: 580/533, loss: 0.06970787048339844
2023-01-23 01:19:23.156166: step: 584/533, loss: 0.017116164788603783
2023-01-23 01:19:24.361736: step: 588/533, loss: 0.06243934482336044
2023-01-23 01:19:25.511635: step: 592/533, loss: 0.017549894750118256
2023-01-23 01:19:26.716264: step: 596/533, loss: 0.0860927551984787
2023-01-23 01:19:27.905214: step: 600/533, loss: 0.030481241643428802
2023-01-23 01:19:29.062524: step: 604/533, loss: 0.031983088701963425
2023-01-23 01:19:30.245981: step: 608/533, loss: 0.05323949083685875
2023-01-23 01:19:31.445478: step: 612/533, loss: 0.05301237106323242
2023-01-23 01:19:32.594569: step: 616/533, loss: 0.08764810860157013
2023-01-23 01:19:33.767222: step: 620/533, loss: 0.008958530612289906
2023-01-23 01:19:34.951082: step: 624/533, loss: 0.08596744388341904
2023-01-23 01:19:36.112279: step: 628/533, loss: 0.017841290682554245
2023-01-23 01:19:37.272592: step: 632/533, loss: 0.07892937958240509
2023-01-23 01:19:38.441107: step: 636/533, loss: 0.09280043095350266
2023-01-23 01:19:39.603519: step: 640/533, loss: 0.002223205752670765
2023-01-23 01:19:40.837789: step: 644/533, loss: 0.028485393151640892
2023-01-23 01:19:42.033425: step: 648/533, loss: 0.0022100924979895353
2023-01-23 01:19:43.184096: step: 652/533, loss: 0.005769098177552223
2023-01-23 01:19:44.359110: step: 656/533, loss: 0.04408903419971466
2023-01-23 01:19:45.527548: step: 660/533, loss: 0.06102009117603302
2023-01-23 01:19:46.727187: step: 664/533, loss: 0.10442186892032623
2023-01-23 01:19:47.877871: step: 668/533, loss: 0.17542466521263123
2023-01-23 01:19:49.032942: step: 672/533, loss: 0.04020867496728897
2023-01-23 01:19:50.199265: step: 676/533, loss: 0.14757074415683746
2023-01-23 01:19:51.360490: step: 680/533, loss: 0.017836570739746094
2023-01-23 01:19:52.537760: step: 684/533, loss: 0.01849689520895481
2023-01-23 01:19:53.700742: step: 688/533, loss: 0.0216786228120327
2023-01-23 01:19:54.939803: step: 692/533, loss: 0.05392627790570259
2023-01-23 01:19:56.140430: step: 696/533, loss: 0.21014156937599182
2023-01-23 01:19:57.294036: step: 700/533, loss: 0.021427344530820847
2023-01-23 01:19:58.457747: step: 704/533, loss: 0.04213247075676918
2023-01-23 01:19:59.604100: step: 708/533, loss: 0.08668547123670578
2023-01-23 01:20:00.822793: step: 712/533, loss: 0.3106168806552887
2023-01-23 01:20:02.028825: step: 716/533, loss: 0.017412377521395683
2023-01-23 01:20:03.264118: step: 720/533, loss: 0.059807490557432175
2023-01-23 01:20:04.417743: step: 724/533, loss: 0.028153324499726295
2023-01-23 01:20:05.587127: step: 728/533, loss: 0.003921255469322205
2023-01-23 01:20:06.767144: step: 732/533, loss: 0.02863330766558647
2023-01-23 01:20:07.961820: step: 736/533, loss: 0.005204916000366211
2023-01-23 01:20:09.128736: step: 740/533, loss: 0.029224969446659088
2023-01-23 01:20:10.284914: step: 744/533, loss: 0.02072594314813614
2023-01-23 01:20:11.463381: step: 748/533, loss: 0.11536255478858948
2023-01-23 01:20:12.633272: step: 752/533, loss: 0.1391172856092453
2023-01-23 01:20:13.824202: step: 756/533, loss: 0.0448765754699707
2023-01-23 01:20:14.963437: step: 760/533, loss: 0.026940584182739258
2023-01-23 01:20:16.122913: step: 764/533, loss: 0.01531610544770956
2023-01-23 01:20:17.308172: step: 768/533, loss: 0.0840090811252594
2023-01-23 01:20:18.465906: step: 772/533, loss: 0.21093778312206268
2023-01-23 01:20:19.618008: step: 776/533, loss: 0.15608978271484375
2023-01-23 01:20:20.785055: step: 780/533, loss: 0.007524467073380947
2023-01-23 01:20:21.972405: step: 784/533, loss: 0.2596149444580078
2023-01-23 01:20:23.164793: step: 788/533, loss: 0.03057042509317398
2023-01-23 01:20:24.349967: step: 792/533, loss: 0.034690190106630325
2023-01-23 01:20:25.545517: step: 796/533, loss: 0.09901542961597443
2023-01-23 01:20:26.761286: step: 800/533, loss: 0.013355541042983532
2023-01-23 01:20:27.938222: step: 804/533, loss: 0.013167286291718483
2023-01-23 01:20:29.137491: step: 808/533, loss: 0.0480194091796875
2023-01-23 01:20:30.292638: step: 812/533, loss: 0.02352001704275608
2023-01-23 01:20:31.465300: step: 816/533, loss: 0.037485502660274506
2023-01-23 01:20:32.726867: step: 820/533, loss: 0.06921150535345078
2023-01-23 01:20:33.918156: step: 824/533, loss: 0.40658819675445557
2023-01-23 01:20:35.067771: step: 828/533, loss: 0.039452601224184036
2023-01-23 01:20:36.238870: step: 832/533, loss: 0.017307210713624954
2023-01-23 01:20:37.398194: step: 836/533, loss: 0.1110198050737381
2023-01-23 01:20:38.643504: step: 840/533, loss: 0.04405651241540909
2023-01-23 01:20:39.817924: step: 844/533, loss: 0.28958702087402344
2023-01-23 01:20:40.982787: step: 848/533, loss: 0.0905223861336708
2023-01-23 01:20:42.165151: step: 852/533, loss: 0.03428377956151962
2023-01-23 01:20:43.367624: step: 856/533, loss: 0.2751867175102234
2023-01-23 01:20:44.583617: step: 860/533, loss: 0.056435585021972656
2023-01-23 01:20:45.756916: step: 864/533, loss: 0.004986953921616077
2023-01-23 01:20:46.921101: step: 868/533, loss: 0.05244483798742294
2023-01-23 01:20:48.124195: step: 872/533, loss: 0.018985938280820847
2023-01-23 01:20:49.327973: step: 876/533, loss: 0.1250377595424652
2023-01-23 01:20:50.506349: step: 880/533, loss: 0.07025227695703506
2023-01-23 01:20:51.698818: step: 884/533, loss: 0.0242125503718853
2023-01-23 01:20:52.901065: step: 888/533, loss: 0.05815563350915909
2023-01-23 01:20:54.048228: step: 892/533, loss: 0.04133930429816246
2023-01-23 01:20:55.315464: step: 896/533, loss: 0.0975547730922699
2023-01-23 01:20:56.472866: step: 900/533, loss: 0.08729038387537003
2023-01-23 01:20:57.650119: step: 904/533, loss: 0.09723357856273651
2023-01-23 01:20:58.779029: step: 908/533, loss: 0.08272366225719452
2023-01-23 01:20:59.956940: step: 912/533, loss: 0.27123039960861206
2023-01-23 01:21:01.115870: step: 916/533, loss: 0.07418441772460938
2023-01-23 01:21:02.295522: step: 920/533, loss: 0.02607116848230362
2023-01-23 01:21:03.479023: step: 924/533, loss: 0.08553676307201385
2023-01-23 01:21:04.661378: step: 928/533, loss: 0.08645935356616974
2023-01-23 01:21:05.829863: step: 932/533, loss: 0.23334969580173492
2023-01-23 01:21:07.015050: step: 936/533, loss: 0.07576780766248703
2023-01-23 01:21:08.171067: step: 940/533, loss: 0.12365283817052841
2023-01-23 01:21:09.327683: step: 944/533, loss: 0.0713711753487587
2023-01-23 01:21:10.481573: step: 948/533, loss: 0.05747837945818901
2023-01-23 01:21:11.667778: step: 952/533, loss: 0.009887218475341797
2023-01-23 01:21:12.853212: step: 956/533, loss: 0.03767995908856392
2023-01-23 01:21:14.029928: step: 960/533, loss: 0.019109057262539864
2023-01-23 01:21:15.222057: step: 964/533, loss: 0.08429031074047089
2023-01-23 01:21:16.373272: step: 968/533, loss: 0.6642215847969055
2023-01-23 01:21:17.517603: step: 972/533, loss: 0.05595884472131729
2023-01-23 01:21:18.707461: step: 976/533, loss: 0.11274567246437073
2023-01-23 01:21:19.898360: step: 980/533, loss: 0.027388382703065872
2023-01-23 01:21:21.079587: step: 984/533, loss: 0.012281752191483974
2023-01-23 01:21:22.285431: step: 988/533, loss: 0.06368140876293182
2023-01-23 01:21:23.413495: step: 992/533, loss: 0.07388248294591904
2023-01-23 01:21:24.621594: step: 996/533, loss: 0.016553591936826706
2023-01-23 01:21:25.766773: step: 1000/533, loss: 0.10744866728782654
2023-01-23 01:21:26.923892: step: 1004/533, loss: 0.08306851238012314
2023-01-23 01:21:28.125316: step: 1008/533, loss: 0.032976724207401276
2023-01-23 01:21:29.291817: step: 1012/533, loss: 0.05050821602344513
2023-01-23 01:21:30.496828: step: 1016/533, loss: 0.049886129796504974
2023-01-23 01:21:31.754492: step: 1020/533, loss: 0.0882379561662674
2023-01-23 01:21:32.892107: step: 1024/533, loss: 0.059326935559511185
2023-01-23 01:21:34.029496: step: 1028/533, loss: 0.045450758188962936
2023-01-23 01:21:35.241288: step: 1032/533, loss: 0.026250028982758522
2023-01-23 01:21:36.454664: step: 1036/533, loss: 0.6288866996765137
2023-01-23 01:21:37.635569: step: 1040/533, loss: 0.0344233512878418
2023-01-23 01:21:38.813603: step: 1044/533, loss: 0.7731708288192749
2023-01-23 01:21:40.006945: step: 1048/533, loss: 0.04690227657556534
2023-01-23 01:21:41.169228: step: 1052/533, loss: 0.2962002754211426
2023-01-23 01:21:42.312385: step: 1056/533, loss: 0.008244156837463379
2023-01-23 01:21:43.473629: step: 1060/533, loss: 0.11076736450195312
2023-01-23 01:21:44.647119: step: 1064/533, loss: 0.004121589940041304
2023-01-23 01:21:45.838687: step: 1068/533, loss: 0.0828530341386795
2023-01-23 01:21:47.033094: step: 1072/533, loss: 0.11859636753797531
2023-01-23 01:21:48.203583: step: 1076/533, loss: 0.06641598045825958
2023-01-23 01:21:49.373235: step: 1080/533, loss: 0.09994659572839737
2023-01-23 01:21:50.545406: step: 1084/533, loss: 0.21724766492843628
2023-01-23 01:21:51.707153: step: 1088/533, loss: 0.13935308158397675
2023-01-23 01:21:52.867071: step: 1092/533, loss: 0.03557634353637695
2023-01-23 01:21:54.075652: step: 1096/533, loss: 0.1536761373281479
2023-01-23 01:21:55.271670: step: 1100/533, loss: 0.1869945526123047
2023-01-23 01:21:56.404365: step: 1104/533, loss: 0.22792643308639526
2023-01-23 01:21:57.583465: step: 1108/533, loss: 0.9061795473098755
2023-01-23 01:21:58.784625: step: 1112/533, loss: 0.01720714569091797
2023-01-23 01:21:59.955803: step: 1116/533, loss: 0.1820284128189087
2023-01-23 01:22:01.104956: step: 1120/533, loss: 0.054145097732543945
2023-01-23 01:22:02.290125: step: 1124/533, loss: 0.6930950880050659
2023-01-23 01:22:03.460602: step: 1128/533, loss: 0.08696766197681427
2023-01-23 01:22:04.620439: step: 1132/533, loss: 0.09825573861598969
2023-01-23 01:22:05.757589: step: 1136/533, loss: 0.09787445515394211
2023-01-23 01:22:06.915757: step: 1140/533, loss: 0.038423679769039154
2023-01-23 01:22:08.079497: step: 1144/533, loss: 0.11393798887729645
2023-01-23 01:22:09.276614: step: 1148/533, loss: 0.11200561374425888
2023-01-23 01:22:10.444603: step: 1152/533, loss: 0.012944317422807217
2023-01-23 01:22:11.598570: step: 1156/533, loss: 0.03660225868225098
2023-01-23 01:22:12.747652: step: 1160/533, loss: 0.10471335053443909
2023-01-23 01:22:13.889718: step: 1164/533, loss: 0.07390861958265305
2023-01-23 01:22:15.099089: step: 1168/533, loss: 0.1529351770877838
2023-01-23 01:22:16.238359: step: 1172/533, loss: 0.004880237393081188
2023-01-23 01:22:17.425198: step: 1176/533, loss: 0.040322497487068176
2023-01-23 01:22:18.627275: step: 1180/533, loss: 0.11745148152112961
2023-01-23 01:22:19.788641: step: 1184/533, loss: 0.08561897277832031
2023-01-23 01:22:20.992690: step: 1188/533, loss: 0.034182358533144
2023-01-23 01:22:22.195502: step: 1192/533, loss: 0.4548143446445465
2023-01-23 01:22:23.376881: step: 1196/533, loss: 0.17241840064525604
2023-01-23 01:22:24.588508: step: 1200/533, loss: 0.08510598540306091
2023-01-23 01:22:25.753281: step: 1204/533, loss: 0.15125522017478943
2023-01-23 01:22:26.899396: step: 1208/533, loss: 0.0975104346871376
2023-01-23 01:22:28.080711: step: 1212/533, loss: 0.3133293092250824
2023-01-23 01:22:29.256879: step: 1216/533, loss: 0.054933834820985794
2023-01-23 01:22:30.410954: step: 1220/533, loss: 0.046628620475530624
2023-01-23 01:22:31.572311: step: 1224/533, loss: 0.024113750085234642
2023-01-23 01:22:32.733752: step: 1228/533, loss: 0.012184619903564453
2023-01-23 01:22:33.929892: step: 1232/533, loss: 0.05818767845630646
2023-01-23 01:22:35.126917: step: 1236/533, loss: 0.07443217933177948
2023-01-23 01:22:36.316618: step: 1240/533, loss: 0.2787153720855713
2023-01-23 01:22:37.491587: step: 1244/533, loss: 0.010120391845703125
2023-01-23 01:22:38.675482: step: 1248/533, loss: 0.07431783527135849
2023-01-23 01:22:39.860628: step: 1252/533, loss: 0.046751346439123154
2023-01-23 01:22:41.041487: step: 1256/533, loss: 0.11606941372156143
2023-01-23 01:22:42.205012: step: 1260/533, loss: 0.08818984031677246
2023-01-23 01:22:43.378367: step: 1264/533, loss: 0.1536249816417694
2023-01-23 01:22:44.538229: step: 1268/533, loss: 0.07218757271766663
2023-01-23 01:22:45.691519: step: 1272/533, loss: 0.10483994334936142
2023-01-23 01:22:46.833264: step: 1276/533, loss: 0.05454890802502632
2023-01-23 01:22:47.996598: step: 1280/533, loss: 0.24248504638671875
2023-01-23 01:22:49.225600: step: 1284/533, loss: 0.0508207343518734
2023-01-23 01:22:50.408912: step: 1288/533, loss: 0.12971706688404083
2023-01-23 01:22:51.571772: step: 1292/533, loss: 0.07170099765062332
2023-01-23 01:22:52.733620: step: 1296/533, loss: 0.02202749252319336
2023-01-23 01:22:53.908133: step: 1300/533, loss: 0.08108548820018768
2023-01-23 01:22:55.098135: step: 1304/533, loss: 0.011467933654785156
2023-01-23 01:22:56.274149: step: 1308/533, loss: 0.07238147407770157
2023-01-23 01:22:57.435602: step: 1312/533, loss: 0.08613242954015732
2023-01-23 01:22:58.600821: step: 1316/533, loss: 0.2801237106323242
2023-01-23 01:22:59.775586: step: 1320/533, loss: 0.013946629129350185
2023-01-23 01:23:00.983957: step: 1324/533, loss: 0.08583274483680725
2023-01-23 01:23:02.150338: step: 1328/533, loss: 0.06180715560913086
2023-01-23 01:23:03.346564: step: 1332/533, loss: 0.10338515788316727
2023-01-23 01:23:04.551914: step: 1336/533, loss: 1.0009410381317139
2023-01-23 01:23:05.731747: step: 1340/533, loss: 0.17573462426662445
2023-01-23 01:23:06.892600: step: 1344/533, loss: 0.05526895448565483
2023-01-23 01:23:08.045658: step: 1348/533, loss: 0.0029705048073083162
2023-01-23 01:23:09.238529: step: 1352/533, loss: 0.18709523975849152
2023-01-23 01:23:10.396083: step: 1356/533, loss: 0.5884739756584167
2023-01-23 01:23:11.562517: step: 1360/533, loss: 0.036551713943481445
2023-01-23 01:23:12.720536: step: 1364/533, loss: 0.036616209894418716
2023-01-23 01:23:13.885894: step: 1368/533, loss: 0.38821572065353394
2023-01-23 01:23:15.039361: step: 1372/533, loss: 0.062314461916685104
2023-01-23 01:23:16.270331: step: 1376/533, loss: 0.24531981348991394
2023-01-23 01:23:17.431067: step: 1380/533, loss: 0.026241686195135117
2023-01-23 01:23:18.610070: step: 1384/533, loss: 0.027741573750972748
2023-01-23 01:23:19.758586: step: 1388/533, loss: 0.03669700771570206
2023-01-23 01:23:20.931691: step: 1392/533, loss: 0.07896633446216583
2023-01-23 01:23:22.096694: step: 1396/533, loss: 0.027110911905765533
2023-01-23 01:23:23.269505: step: 1400/533, loss: 0.10955075919628143
2023-01-23 01:23:24.453855: step: 1404/533, loss: 0.5084964036941528
2023-01-23 01:23:25.655076: step: 1408/533, loss: 0.06081056594848633
2023-01-23 01:23:26.845746: step: 1412/533, loss: 0.043141938745975494
2023-01-23 01:23:27.990886: step: 1416/533, loss: 0.16898289322853088
2023-01-23 01:23:29.250902: step: 1420/533, loss: 0.12807735800743103
2023-01-23 01:23:30.415604: step: 1424/533, loss: 0.028343772515654564
2023-01-23 01:23:31.576862: step: 1428/533, loss: 0.010363107547163963
2023-01-23 01:23:32.733258: step: 1432/533, loss: 0.06041097640991211
2023-01-23 01:23:33.938407: step: 1436/533, loss: 0.04304962605237961
2023-01-23 01:23:35.093848: step: 1440/533, loss: 0.005700159352272749
2023-01-23 01:23:36.266267: step: 1444/533, loss: 0.03150491788983345
2023-01-23 01:23:37.558272: step: 1448/533, loss: 0.04747028648853302
2023-01-23 01:23:38.722730: step: 1452/533, loss: 0.05173196643590927
2023-01-23 01:23:39.932843: step: 1456/533, loss: 0.05852065235376358
2023-01-23 01:23:41.139758: step: 1460/533, loss: 0.12316127121448517
2023-01-23 01:23:42.300854: step: 1464/533, loss: 0.12001600116491318
2023-01-23 01:23:43.471630: step: 1468/533, loss: 0.05540933459997177
2023-01-23 01:23:44.646007: step: 1472/533, loss: 0.007329070474952459
2023-01-23 01:23:45.818586: step: 1476/533, loss: 0.051676083356142044
2023-01-23 01:23:46.986819: step: 1480/533, loss: 0.026768827810883522
2023-01-23 01:23:48.227708: step: 1484/533, loss: 0.10381804406642914
2023-01-23 01:23:49.395492: step: 1488/533, loss: 0.05727798864245415
2023-01-23 01:23:50.536876: step: 1492/533, loss: 0.5386823415756226
2023-01-23 01:23:51.697027: step: 1496/533, loss: 0.027991319075226784
2023-01-23 01:23:52.847257: step: 1500/533, loss: 0.003662109375
2023-01-23 01:23:53.996992: step: 1504/533, loss: 0.49916714429855347
2023-01-23 01:23:55.178442: step: 1508/533, loss: 0.08819127082824707
2023-01-23 01:23:56.344004: step: 1512/533, loss: 0.12923279404640198
2023-01-23 01:23:57.538594: step: 1516/533, loss: 0.010399436578154564
2023-01-23 01:23:58.721819: step: 1520/533, loss: 0.23699027299880981
2023-01-23 01:23:59.873599: step: 1524/533, loss: 0.008065986447036266
2023-01-23 01:24:01.054356: step: 1528/533, loss: 0.02567291259765625
2023-01-23 01:24:02.269106: step: 1532/533, loss: 0.04861469566822052
2023-01-23 01:24:03.448227: step: 1536/533, loss: 0.044959452003240585
2023-01-23 01:24:04.623139: step: 1540/533, loss: 0.025795841589570045
2023-01-23 01:24:05.856446: step: 1544/533, loss: 0.373870313167572
2023-01-23 01:24:07.019887: step: 1548/533, loss: 0.025064660236239433
2023-01-23 01:24:08.184818: step: 1552/533, loss: 0.0037708759773522615
2023-01-23 01:24:09.394325: step: 1556/533, loss: 0.02398090437054634
2023-01-23 01:24:10.530032: step: 1560/533, loss: 0.04906916990876198
2023-01-23 01:24:11.687811: step: 1564/533, loss: 0.1152244359254837
2023-01-23 01:24:12.809517: step: 1568/533, loss: 0.12641267478466034
2023-01-23 01:24:13.944229: step: 1572/533, loss: 0.024326419457793236
2023-01-23 01:24:15.139074: step: 1576/533, loss: 0.02207660675048828
2023-01-23 01:24:16.341458: step: 1580/533, loss: 0.0548248291015625
2023-01-23 01:24:17.538766: step: 1584/533, loss: 0.2030935287475586
2023-01-23 01:24:18.679718: step: 1588/533, loss: 0.03352651745080948
2023-01-23 01:24:19.842694: step: 1592/533, loss: 0.03094806708395481
2023-01-23 01:24:20.997431: step: 1596/533, loss: 0.06598720699548721
2023-01-23 01:24:22.186735: step: 1600/533, loss: 0.007987022399902344
2023-01-23 01:24:23.374917: step: 1604/533, loss: 0.015272426418960094
2023-01-23 01:24:24.566160: step: 1608/533, loss: 0.2675851881504059
2023-01-23 01:24:25.752401: step: 1612/533, loss: 0.10724973678588867
2023-01-23 01:24:26.955441: step: 1616/533, loss: 0.05555405840277672
2023-01-23 01:24:28.079531: step: 1620/533, loss: 0.09273891896009445
2023-01-23 01:24:29.244951: step: 1624/533, loss: 0.016599655151367188
2023-01-23 01:24:30.411754: step: 1628/533, loss: 0.07123704254627228
2023-01-23 01:24:31.584088: step: 1632/533, loss: 0.059188082814216614
2023-01-23 01:24:32.763433: step: 1636/533, loss: 0.008829879574477673
2023-01-23 01:24:33.926473: step: 1640/533, loss: 0.03722744062542915
2023-01-23 01:24:35.127966: step: 1644/533, loss: 0.16563081741333008
2023-01-23 01:24:36.297090: step: 1648/533, loss: 0.12208674103021622
2023-01-23 01:24:37.488775: step: 1652/533, loss: 0.06706981360912323
2023-01-23 01:24:38.649716: step: 1656/533, loss: 0.0668870061635971
2023-01-23 01:24:39.801975: step: 1660/533, loss: 0.015508986078202724
2023-01-23 01:24:40.965065: step: 1664/533, loss: 0.05443458631634712
2023-01-23 01:24:42.156463: step: 1668/533, loss: 0.04190950468182564
2023-01-23 01:24:43.313267: step: 1672/533, loss: 0.05709293484687805
2023-01-23 01:24:44.522061: step: 1676/533, loss: 0.06490955501794815
2023-01-23 01:24:45.675873: step: 1680/533, loss: 0.0038893460296094418
2023-01-23 01:24:46.822838: step: 1684/533, loss: 0.009616660885512829
2023-01-23 01:24:47.989473: step: 1688/533, loss: 0.07100296020507812
2023-01-23 01:24:49.142492: step: 1692/533, loss: 0.0056012156419456005
2023-01-23 01:24:50.330414: step: 1696/533, loss: 0.05840704217553139
2023-01-23 01:24:51.504172: step: 1700/533, loss: 0.12703028321266174
2023-01-23 01:24:52.680647: step: 1704/533, loss: 0.057176969945430756
2023-01-23 01:24:53.835325: step: 1708/533, loss: 0.23405419290065765
2023-01-23 01:24:55.015914: step: 1712/533, loss: 0.3543122410774231
2023-01-23 01:24:56.184226: step: 1716/533, loss: 0.021964453160762787
2023-01-23 01:24:57.360321: step: 1720/533, loss: 0.02976525016129017
2023-01-23 01:24:58.531283: step: 1724/533, loss: 0.08387728035449982
2023-01-23 01:24:59.692226: step: 1728/533, loss: 0.018842125311493874
2023-01-23 01:25:00.889688: step: 1732/533, loss: 0.07530169934034348
2023-01-23 01:25:02.051622: step: 1736/533, loss: 0.06779966503381729
2023-01-23 01:25:03.252298: step: 1740/533, loss: 0.026753904297947884
2023-01-23 01:25:04.414216: step: 1744/533, loss: 0.04340362548828125
2023-01-23 01:25:05.587575: step: 1748/533, loss: 0.12866048514842987
2023-01-23 01:25:06.743544: step: 1752/533, loss: 0.02243213728070259
2023-01-23 01:25:07.977230: step: 1756/533, loss: 0.15219421684741974
2023-01-23 01:25:09.157486: step: 1760/533, loss: 0.1093904972076416
2023-01-23 01:25:10.314424: step: 1764/533, loss: 0.0665835440158844
2023-01-23 01:25:11.537512: step: 1768/533, loss: 0.10058832168579102
2023-01-23 01:25:12.707807: step: 1772/533, loss: 0.017956828698515892
2023-01-23 01:25:13.875584: step: 1776/533, loss: 0.03499488905072212
2023-01-23 01:25:15.045345: step: 1780/533, loss: 0.014957617968320847
2023-01-23 01:25:16.197260: step: 1784/533, loss: 0.08211478590965271
2023-01-23 01:25:17.339617: step: 1788/533, loss: 0.024079417809844017
2023-01-23 01:25:18.518616: step: 1792/533, loss: 0.05085492134094238
2023-01-23 01:25:19.680987: step: 1796/533, loss: 0.02582411840558052
2023-01-23 01:25:20.861155: step: 1800/533, loss: 0.026110172271728516
2023-01-23 01:25:22.086026: step: 1804/533, loss: 0.07222280651330948
2023-01-23 01:25:23.255545: step: 1808/533, loss: 0.7108290791511536
2023-01-23 01:25:24.435208: step: 1812/533, loss: 0.005486679263412952
2023-01-23 01:25:25.600728: step: 1816/533, loss: 0.05412931740283966
2023-01-23 01:25:26.784474: step: 1820/533, loss: 0.057809069752693176
2023-01-23 01:25:27.982990: step: 1824/533, loss: 0.07038374990224838
2023-01-23 01:25:29.136858: step: 1828/533, loss: 0.05788679048418999
2023-01-23 01:25:30.332602: step: 1832/533, loss: 0.09710827469825745
2023-01-23 01:25:31.492066: step: 1836/533, loss: 0.0164810661226511
2023-01-23 01:25:32.698171: step: 1840/533, loss: 0.01407403964549303
2023-01-23 01:25:33.957612: step: 1844/533, loss: 0.20030422508716583
2023-01-23 01:25:35.133690: step: 1848/533, loss: 0.03567218780517578
2023-01-23 01:25:36.308910: step: 1852/533, loss: 0.11867332458496094
2023-01-23 01:25:37.450378: step: 1856/533, loss: 0.11448794603347778
2023-01-23 01:25:38.648395: step: 1860/533, loss: 0.08703909069299698
2023-01-23 01:25:39.815097: step: 1864/533, loss: 0.17075638473033905
2023-01-23 01:25:40.972316: step: 1868/533, loss: 0.009350347332656384
2023-01-23 01:25:42.148125: step: 1872/533, loss: 0.02880687639117241
2023-01-23 01:25:43.341181: step: 1876/533, loss: 0.06279440224170685
2023-01-23 01:25:44.494229: step: 1880/533, loss: 0.0051780701614916325
2023-01-23 01:25:45.679741: step: 1884/533, loss: 0.06368546187877655
2023-01-23 01:25:46.874247: step: 1888/533, loss: 0.01476383302360773
2023-01-23 01:25:48.045271: step: 1892/533, loss: 0.12096557766199112
2023-01-23 01:25:49.217954: step: 1896/533, loss: 0.09713239222764969
2023-01-23 01:25:50.383994: step: 1900/533, loss: 0.03229885175824165
2023-01-23 01:25:51.568873: step: 1904/533, loss: 0.1363920271396637
2023-01-23 01:25:52.747970: step: 1908/533, loss: 0.040161460638046265
2023-01-23 01:25:53.896025: step: 1912/533, loss: 0.03166034445166588
2023-01-23 01:25:55.079539: step: 1916/533, loss: 0.49534720182418823
2023-01-23 01:25:56.273796: step: 1920/533, loss: 0.05235690996050835
2023-01-23 01:25:57.535658: step: 1924/533, loss: 0.016606617718935013
2023-01-23 01:25:58.697068: step: 1928/533, loss: 0.006987619213759899
2023-01-23 01:25:59.896553: step: 1932/533, loss: 0.0011625289916992188
2023-01-23 01:26:01.061300: step: 1936/533, loss: 0.011188840493559837
2023-01-23 01:26:02.224110: step: 1940/533, loss: 0.17567414045333862
2023-01-23 01:26:03.457484: step: 1944/533, loss: 0.09800954163074493
2023-01-23 01:26:04.651340: step: 1948/533, loss: 0.05898590385913849
2023-01-23 01:26:05.827187: step: 1952/533, loss: 0.01071014441549778
2023-01-23 01:26:06.973808: step: 1956/533, loss: 0.36879587173461914
2023-01-23 01:26:08.147266: step: 1960/533, loss: 0.5534471273422241
2023-01-23 01:26:09.298328: step: 1964/533, loss: 0.016251325607299805
2023-01-23 01:26:10.444941: step: 1968/533, loss: 0.04796028137207031
2023-01-23 01:26:11.605616: step: 1972/533, loss: 0.16088706254959106
2023-01-23 01:26:12.822013: step: 1976/533, loss: 0.153499037027359
2023-01-23 01:26:14.009971: step: 1980/533, loss: 0.019681455567479134
2023-01-23 01:26:15.226183: step: 1984/533, loss: 0.11831459403038025
2023-01-23 01:26:16.389349: step: 1988/533, loss: 0.006252622697502375
2023-01-23 01:26:17.530270: step: 1992/533, loss: 0.10022459179162979
2023-01-23 01:26:18.701548: step: 1996/533, loss: 0.31878718733787537
2023-01-23 01:26:19.844963: step: 2000/533, loss: 9.713172767078504e-05
2023-01-23 01:26:21.062678: step: 2004/533, loss: 0.026334000751376152
2023-01-23 01:26:22.257965: step: 2008/533, loss: 0.04110260307788849
2023-01-23 01:26:23.459114: step: 2012/533, loss: 0.0028736114036291838
2023-01-23 01:26:24.617379: step: 2016/533, loss: 0.09804189205169678
2023-01-23 01:26:25.770152: step: 2020/533, loss: 0.05880336835980415
2023-01-23 01:26:26.961516: step: 2024/533, loss: 0.14047737419605255
2023-01-23 01:26:28.137155: step: 2028/533, loss: 0.01078042946755886
2023-01-23 01:26:29.307785: step: 2032/533, loss: 0.11109104007482529
2023-01-23 01:26:30.526730: step: 2036/533, loss: 0.013492370024323463
2023-01-23 01:26:31.671403: step: 2040/533, loss: 0.05885725095868111
2023-01-23 01:26:32.812380: step: 2044/533, loss: 0.029235459864139557
2023-01-23 01:26:33.997371: step: 2048/533, loss: 0.13680404424667358
2023-01-23 01:26:35.160400: step: 2052/533, loss: 0.28125572204589844
2023-01-23 01:26:36.332927: step: 2056/533, loss: 0.24199867248535156
2023-01-23 01:26:37.500688: step: 2060/533, loss: 0.04656543582677841
2023-01-23 01:26:38.652678: step: 2064/533, loss: 0.022696923464536667
2023-01-23 01:26:39.834713: step: 2068/533, loss: 0.0015400409465655684
2023-01-23 01:26:41.047450: step: 2072/533, loss: 0.029370786622166634
2023-01-23 01:26:42.209891: step: 2076/533, loss: 0.07193336635828018
2023-01-23 01:26:43.365542: step: 2080/533, loss: 0.025753021240234375
2023-01-23 01:26:44.585693: step: 2084/533, loss: 0.020557023584842682
2023-01-23 01:26:45.808949: step: 2088/533, loss: 0.033214569091796875
2023-01-23 01:26:47.033263: step: 2092/533, loss: 0.13563615083694458
2023-01-23 01:26:48.212244: step: 2096/533, loss: 0.017001725733280182
2023-01-23 01:26:49.433671: step: 2100/533, loss: 0.1857103407382965
2023-01-23 01:26:50.623015: step: 2104/533, loss: 0.10610218346118927
2023-01-23 01:26:51.802098: step: 2108/533, loss: 0.04030952602624893
2023-01-23 01:26:52.997167: step: 2112/533, loss: 0.04674091190099716
2023-01-23 01:26:54.178328: step: 2116/533, loss: 0.1484365016222
2023-01-23 01:26:55.316820: step: 2120/533, loss: 0.07701349258422852
2023-01-23 01:26:56.468844: step: 2124/533, loss: 0.08461757749319077
2023-01-23 01:26:57.645292: step: 2128/533, loss: 0.26792973279953003
2023-01-23 01:26:58.780204: step: 2132/533, loss: 0.06239013746380806
==================================================
Loss: 0.092
--------------------
Dev: {'event': {'p': 0.5639810426540285, 'r': 0.7922769640479361, 'f1': 0.6589147286821706}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6056812710640347, 'r': 0.8043478260869565, 'f1': 0.6910189508376821}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5777777777777777, 'r': 0.9629629629629629, 'f1': 0.7222222222222221}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6101694915254238, 'r': 0.5714285714285714, 'f1': 0.5901639344262296}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.37209302325581395, 'r': 0.4444444444444444, 'f1': 0.40506329113924044}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:27:39.925154: step: 4/533, loss: 0.11098746955394745
2023-01-23 01:27:41.078325: step: 8/533, loss: 0.11326369643211365
2023-01-23 01:27:42.268922: step: 12/533, loss: 0.015026998706161976
2023-01-23 01:27:43.458237: step: 16/533, loss: 0.04696798324584961
2023-01-23 01:27:44.601427: step: 20/533, loss: 0.006007767282426357
2023-01-23 01:27:45.728582: step: 24/533, loss: 0.036834146827459335
2023-01-23 01:27:46.923674: step: 28/533, loss: 0.05240399390459061
2023-01-23 01:27:48.086161: step: 32/533, loss: 0.005521345417946577
2023-01-23 01:27:49.296901: step: 36/533, loss: 0.08041973412036896
2023-01-23 01:27:50.523521: step: 40/533, loss: 0.010283757001161575
2023-01-23 01:27:51.715219: step: 44/533, loss: 0.02172107622027397
2023-01-23 01:27:52.873004: step: 48/533, loss: 0.02050170861184597
2023-01-23 01:27:54.050644: step: 52/533, loss: 0.2266945242881775
2023-01-23 01:27:55.203899: step: 56/533, loss: 0.005156993865966797
2023-01-23 01:27:56.422969: step: 60/533, loss: 0.049368664622306824
2023-01-23 01:27:57.621728: step: 64/533, loss: 0.06065859645605087
2023-01-23 01:27:58.789418: step: 68/533, loss: 0.02526865154504776
2023-01-23 01:28:00.016825: step: 72/533, loss: 0.02322525903582573
2023-01-23 01:28:01.238327: step: 76/533, loss: 0.03267580270767212
2023-01-23 01:28:02.393998: step: 80/533, loss: 0.04438326507806778
2023-01-23 01:28:03.572819: step: 84/533, loss: 0.009611892513930798
2023-01-23 01:28:04.743016: step: 88/533, loss: 0.02946758270263672
2023-01-23 01:28:05.914259: step: 92/533, loss: 0.019115973263978958
2023-01-23 01:28:07.062141: step: 96/533, loss: 0.22646526992321014
2023-01-23 01:28:08.272406: step: 100/533, loss: 0.061250876635313034
2023-01-23 01:28:09.455883: step: 104/533, loss: 0.00987234152853489
2023-01-23 01:28:10.640767: step: 108/533, loss: 0.02112426795065403
2023-01-23 01:28:11.808598: step: 112/533, loss: 0.0675802230834961
2023-01-23 01:28:12.983303: step: 116/533, loss: 0.017433859407901764
2023-01-23 01:28:14.119225: step: 120/533, loss: 0.06914959102869034
2023-01-23 01:28:15.282634: step: 124/533, loss: 0.04367981106042862
2023-01-23 01:28:16.430701: step: 128/533, loss: 0.006170368287712336
2023-01-23 01:28:17.633351: step: 132/533, loss: 0.02725696563720703
2023-01-23 01:28:18.822215: step: 136/533, loss: 0.11591873317956924
2023-01-23 01:28:20.039862: step: 140/533, loss: 0.0342339389026165
2023-01-23 01:28:21.233987: step: 144/533, loss: 0.03218948841094971
2023-01-23 01:28:22.386899: step: 148/533, loss: 0.020868491381406784
2023-01-23 01:28:23.569021: step: 152/533, loss: 0.07970891147851944
2023-01-23 01:28:24.766359: step: 156/533, loss: 0.07470874488353729
2023-01-23 01:28:25.930160: step: 160/533, loss: 0.06186676025390625
2023-01-23 01:28:27.109729: step: 164/533, loss: 0.026323892176151276
2023-01-23 01:28:28.267468: step: 168/533, loss: 0.011422348208725452
2023-01-23 01:28:29.469097: step: 172/533, loss: 0.023266172036528587
2023-01-23 01:28:30.653449: step: 176/533, loss: 0.006433963775634766
2023-01-23 01:28:31.801721: step: 180/533, loss: 0.05391855537891388
2023-01-23 01:28:32.953256: step: 184/533, loss: 0.004941749386489391
2023-01-23 01:28:34.119873: step: 188/533, loss: 0.04730267822742462
2023-01-23 01:28:35.312642: step: 192/533, loss: 0.06706647574901581
2023-01-23 01:28:36.488136: step: 196/533, loss: 0.010280609130859375
2023-01-23 01:28:37.667445: step: 200/533, loss: 0.08075451850891113
2023-01-23 01:28:38.835568: step: 204/533, loss: 0.06409773975610733
2023-01-23 01:28:40.038202: step: 208/533, loss: 0.024731159210205078
2023-01-23 01:28:41.212915: step: 212/533, loss: 0.09119682013988495
2023-01-23 01:28:42.367560: step: 216/533, loss: 0.032472554594278336
2023-01-23 01:28:43.576300: step: 220/533, loss: 0.16315937042236328
2023-01-23 01:28:44.710741: step: 224/533, loss: 0.046383023262023926
2023-01-23 01:28:45.924051: step: 228/533, loss: 0.020339488983154297
2023-01-23 01:28:47.078549: step: 232/533, loss: 0.043627165257930756
2023-01-23 01:28:48.270976: step: 236/533, loss: 0.011780072003602982
2023-01-23 01:28:49.407965: step: 240/533, loss: 0.03435640037059784
2023-01-23 01:28:50.580999: step: 244/533, loss: 0.12655138969421387
2023-01-23 01:28:51.756691: step: 248/533, loss: 0.03272189944982529
2023-01-23 01:28:52.906953: step: 252/533, loss: 0.012595271691679955
2023-01-23 01:28:54.091314: step: 256/533, loss: 0.15964969992637634
2023-01-23 01:28:55.267268: step: 260/533, loss: 0.03986222296953201
2023-01-23 01:28:56.429070: step: 264/533, loss: 0.07054682075977325
2023-01-23 01:28:57.561613: step: 268/533, loss: 0.40937739610671997
2023-01-23 01:28:58.729717: step: 272/533, loss: 0.15408268570899963
2023-01-23 01:28:59.909931: step: 276/533, loss: 0.023018455132842064
2023-01-23 01:29:01.069133: step: 280/533, loss: 0.06060600280761719
2023-01-23 01:29:02.210399: step: 284/533, loss: 0.03645515441894531
2023-01-23 01:29:03.370001: step: 288/533, loss: 0.06190476566553116
2023-01-23 01:29:04.538498: step: 292/533, loss: 0.016421889886260033
2023-01-23 01:29:05.686599: step: 296/533, loss: 0.08073997497558594
2023-01-23 01:29:06.868355: step: 300/533, loss: 0.04174823686480522
2023-01-23 01:29:08.023613: step: 304/533, loss: 0.03557872772216797
2023-01-23 01:29:09.165924: step: 308/533, loss: 0.03222084045410156
2023-01-23 01:29:10.366624: step: 312/533, loss: 0.05733766779303551
2023-01-23 01:29:11.537193: step: 316/533, loss: 0.00252113351598382
2023-01-23 01:29:12.752287: step: 320/533, loss: 0.06051836162805557
2023-01-23 01:29:13.934504: step: 324/533, loss: 0.16255348920822144
2023-01-23 01:29:15.110761: step: 328/533, loss: 0.0007349014631472528
2023-01-23 01:29:16.267880: step: 332/533, loss: 0.014552832581102848
2023-01-23 01:29:17.443378: step: 336/533, loss: 0.22178708016872406
2023-01-23 01:29:18.606384: step: 340/533, loss: 0.07792253792285919
2023-01-23 01:29:19.796477: step: 344/533, loss: 0.02086925506591797
2023-01-23 01:29:20.983977: step: 348/533, loss: 0.03763217851519585
2023-01-23 01:29:22.156856: step: 352/533, loss: 0.01214828435331583
2023-01-23 01:29:23.316108: step: 356/533, loss: 0.0013957977062091231
2023-01-23 01:29:24.512881: step: 360/533, loss: 0.018419837579131126
2023-01-23 01:29:25.704372: step: 364/533, loss: 0.025835610926151276
2023-01-23 01:29:26.845499: step: 368/533, loss: 0.17872829735279083
2023-01-23 01:29:28.028788: step: 372/533, loss: 0.004904317669570446
2023-01-23 01:29:29.238109: step: 376/533, loss: 0.08587322384119034
2023-01-23 01:29:30.394873: step: 380/533, loss: 0.1208728551864624
2023-01-23 01:29:31.553896: step: 384/533, loss: 0.05300531163811684
2023-01-23 01:29:32.716310: step: 388/533, loss: 0.006340742111206055
2023-01-23 01:29:33.872943: step: 392/533, loss: 0.013455485925078392
2023-01-23 01:29:34.999887: step: 396/533, loss: 0.05456986650824547
2023-01-23 01:29:36.202345: step: 400/533, loss: 0.0044717793352901936
2023-01-23 01:29:37.405164: step: 404/533, loss: 0.04871797561645508
2023-01-23 01:29:38.584015: step: 408/533, loss: 0.022593878209590912
2023-01-23 01:29:39.727087: step: 412/533, loss: 0.09443550556898117
2023-01-23 01:29:40.879728: step: 416/533, loss: 0.06721778213977814
2023-01-23 01:29:42.049364: step: 420/533, loss: 0.12110957503318787
2023-01-23 01:29:43.207612: step: 424/533, loss: 0.011982965283095837
2023-01-23 01:29:44.385164: step: 428/533, loss: 0.02914142608642578
2023-01-23 01:29:45.539025: step: 432/533, loss: 0.05497932434082031
2023-01-23 01:29:46.680543: step: 436/533, loss: 0.007151222787797451
2023-01-23 01:29:47.891216: step: 440/533, loss: 0.17595058679580688
2023-01-23 01:29:49.086798: step: 444/533, loss: 0.027852630242705345
2023-01-23 01:29:50.248663: step: 448/533, loss: 0.055014923214912415
2023-01-23 01:29:51.477007: step: 452/533, loss: 0.044091418385505676
2023-01-23 01:29:52.661403: step: 456/533, loss: 0.05246572569012642
2023-01-23 01:29:53.853446: step: 460/533, loss: 0.06380920112133026
2023-01-23 01:29:55.032459: step: 464/533, loss: 0.008252429775893688
2023-01-23 01:29:56.214335: step: 468/533, loss: 0.1192958801984787
2023-01-23 01:29:57.397766: step: 472/533, loss: 0.036467358469963074
2023-01-23 01:29:58.545201: step: 476/533, loss: 0.0562971867620945
2023-01-23 01:29:59.710031: step: 480/533, loss: 0.02591428905725479
2023-01-23 01:30:00.886087: step: 484/533, loss: 0.07569951564073563
2023-01-23 01:30:02.096115: step: 488/533, loss: 0.05282320827245712
2023-01-23 01:30:03.275040: step: 492/533, loss: 0.04266824945807457
2023-01-23 01:30:04.414188: step: 496/533, loss: 0.13862422108650208
2023-01-23 01:30:05.596556: step: 500/533, loss: 0.15836314857006073
2023-01-23 01:30:06.755533: step: 504/533, loss: 0.055207252502441406
2023-01-23 01:30:07.957199: step: 508/533, loss: 0.015988362953066826
2023-01-23 01:30:09.116372: step: 512/533, loss: 0.053771305829286575
2023-01-23 01:30:10.312015: step: 516/533, loss: 0.08956480026245117
2023-01-23 01:30:11.525402: step: 520/533, loss: 0.13842526078224182
2023-01-23 01:30:12.697099: step: 524/533, loss: 0.02561025694012642
2023-01-23 01:30:13.887924: step: 528/533, loss: 0.04951143264770508
2023-01-23 01:30:15.047609: step: 532/533, loss: 0.00173273088876158
2023-01-23 01:30:16.190125: step: 536/533, loss: 0.06415396183729172
2023-01-23 01:30:17.357249: step: 540/533, loss: 0.12729597091674805
2023-01-23 01:30:18.549310: step: 544/533, loss: 0.025625038892030716
2023-01-23 01:30:19.771628: step: 548/533, loss: 0.03579330816864967
2023-01-23 01:30:21.017512: step: 552/533, loss: 0.011406230740249157
2023-01-23 01:30:22.193837: step: 556/533, loss: 0.24583172798156738
2023-01-23 01:30:23.362315: step: 560/533, loss: 0.05475788190960884
2023-01-23 01:30:24.520335: step: 564/533, loss: 0.014833450317382812
2023-01-23 01:30:25.688276: step: 568/533, loss: 0.03657722473144531
2023-01-23 01:30:26.873730: step: 572/533, loss: 0.03354253992438316
2023-01-23 01:30:28.033424: step: 576/533, loss: 0.027268314734101295
2023-01-23 01:30:29.225612: step: 580/533, loss: 0.2000339776277542
2023-01-23 01:30:30.394714: step: 584/533, loss: 0.00023698806762695312
2023-01-23 01:30:31.636108: step: 588/533, loss: 0.02266082912683487
2023-01-23 01:30:32.831643: step: 592/533, loss: 0.09441972523927689
2023-01-23 01:30:33.956009: step: 596/533, loss: 0.18726615607738495
2023-01-23 01:30:35.118429: step: 600/533, loss: 0.005542755126953125
2023-01-23 01:30:36.306514: step: 604/533, loss: 0.0045563699677586555
2023-01-23 01:30:37.514929: step: 608/533, loss: 0.015193367376923561
2023-01-23 01:30:38.677925: step: 612/533, loss: 0.005956745240837336
2023-01-23 01:30:39.864760: step: 616/533, loss: 0.017676448449492455
2023-01-23 01:30:41.080685: step: 620/533, loss: 0.02517547644674778
2023-01-23 01:30:42.246405: step: 624/533, loss: 0.08792870491743088
2023-01-23 01:30:43.455987: step: 628/533, loss: 0.34034356474876404
2023-01-23 01:30:44.664408: step: 632/533, loss: 0.09360618889331818
2023-01-23 01:30:45.850534: step: 636/533, loss: 0.31324413418769836
2023-01-23 01:30:47.034190: step: 640/533, loss: 0.03742113336920738
2023-01-23 01:30:48.221545: step: 644/533, loss: 0.02005005069077015
2023-01-23 01:30:49.353323: step: 648/533, loss: 0.007426857948303223
2023-01-23 01:30:50.502072: step: 652/533, loss: 0.035787202417850494
2023-01-23 01:30:51.690110: step: 656/533, loss: 0.040491294115781784
2023-01-23 01:30:52.880997: step: 660/533, loss: 0.08698378503322601
2023-01-23 01:30:54.083758: step: 664/533, loss: 0.32028070092201233
2023-01-23 01:30:55.285179: step: 668/533, loss: 0.12318526208400726
2023-01-23 01:30:56.482287: step: 672/533, loss: 0.09167566150426865
2023-01-23 01:30:57.648720: step: 676/533, loss: 0.03479957580566406
2023-01-23 01:30:58.850721: step: 680/533, loss: 0.06010895222425461
2023-01-23 01:31:00.024916: step: 684/533, loss: 0.04062480852007866
2023-01-23 01:31:01.246674: step: 688/533, loss: 0.05848865583539009
2023-01-23 01:31:02.446163: step: 692/533, loss: 0.03724632412195206
2023-01-23 01:31:03.610684: step: 696/533, loss: 0.07625627517700195
2023-01-23 01:31:04.767662: step: 700/533, loss: 0.008632754907011986
2023-01-23 01:31:05.957860: step: 704/533, loss: 0.015421295538544655
2023-01-23 01:31:07.142665: step: 708/533, loss: 0.041405774652957916
2023-01-23 01:31:08.314708: step: 712/533, loss: 0.02901287004351616
2023-01-23 01:31:09.526627: step: 716/533, loss: 0.12156916409730911
2023-01-23 01:31:10.703901: step: 720/533, loss: 0.10615520924329758
2023-01-23 01:31:11.889096: step: 724/533, loss: 0.0732932984828949
2023-01-23 01:31:13.087015: step: 728/533, loss: 0.12164249271154404
2023-01-23 01:31:14.288340: step: 732/533, loss: 0.014490867033600807
2023-01-23 01:31:15.424006: step: 736/533, loss: 0.07560920715332031
2023-01-23 01:31:16.582199: step: 740/533, loss: 0.008276844397187233
2023-01-23 01:31:17.741053: step: 744/533, loss: 0.048221781849861145
2023-01-23 01:31:18.944997: step: 748/533, loss: 0.06289515644311905
2023-01-23 01:31:20.126968: step: 752/533, loss: 0.008064167574048042
2023-01-23 01:31:21.308172: step: 756/533, loss: 0.0025943757500499487
2023-01-23 01:31:22.518457: step: 760/533, loss: 0.05871171876788139
2023-01-23 01:31:23.661901: step: 764/533, loss: 0.022032355889678
2023-01-23 01:31:24.821116: step: 768/533, loss: 0.016852283850312233
2023-01-23 01:31:25.989749: step: 772/533, loss: 0.000576019287109375
2023-01-23 01:31:27.176411: step: 776/533, loss: 0.1648513376712799
2023-01-23 01:31:28.390712: step: 780/533, loss: 0.09577111899852753
2023-01-23 01:31:29.586794: step: 784/533, loss: 0.0040313247591257095
2023-01-23 01:31:30.728944: step: 788/533, loss: 0.03049830161035061
2023-01-23 01:31:31.876108: step: 792/533, loss: 0.0767643004655838
2023-01-23 01:31:33.058541: step: 796/533, loss: 0.09438591450452805
2023-01-23 01:31:34.201719: step: 800/533, loss: 0.10875463485717773
2023-01-23 01:31:35.391514: step: 804/533, loss: 0.11499723792076111
2023-01-23 01:31:36.580807: step: 808/533, loss: 0.06844482570886612
2023-01-23 01:31:37.748428: step: 812/533, loss: 0.020340634509921074
2023-01-23 01:31:38.947118: step: 816/533, loss: 0.100629523396492
2023-01-23 01:31:40.127266: step: 820/533, loss: 0.028775835409760475
2023-01-23 01:31:41.304223: step: 824/533, loss: 0.037395671010017395
2023-01-23 01:31:42.475330: step: 828/533, loss: 0.4053604304790497
2023-01-23 01:31:43.639977: step: 832/533, loss: 0.06030865013599396
2023-01-23 01:31:44.807415: step: 836/533, loss: 0.008334731683135033
2023-01-23 01:31:45.985170: step: 840/533, loss: 0.010800456628203392
2023-01-23 01:31:47.161247: step: 844/533, loss: 0.028617478907108307
2023-01-23 01:31:48.365502: step: 848/533, loss: 0.6874879598617554
2023-01-23 01:31:49.536033: step: 852/533, loss: 0.29638758301734924
2023-01-23 01:31:50.721698: step: 856/533, loss: 0.11476555466651917
2023-01-23 01:31:51.869641: step: 860/533, loss: 0.09508753567934036
2023-01-23 01:31:53.031911: step: 864/533, loss: 0.01524662971496582
2023-01-23 01:31:54.186815: step: 868/533, loss: 0.06694383919239044
2023-01-23 01:31:55.353465: step: 872/533, loss: 0.0042227269150316715
2023-01-23 01:31:56.526846: step: 876/533, loss: 0.16895513236522675
2023-01-23 01:31:57.660471: step: 880/533, loss: 0.06287021934986115
2023-01-23 01:31:58.850929: step: 884/533, loss: 0.03757200017571449
2023-01-23 01:32:00.043752: step: 888/533, loss: 0.06285929679870605
2023-01-23 01:32:01.207098: step: 892/533, loss: 0.023138046264648438
2023-01-23 01:32:02.399029: step: 896/533, loss: 0.017914963886141777
2023-01-23 01:32:03.562948: step: 900/533, loss: 0.002557039260864258
2023-01-23 01:32:04.735272: step: 904/533, loss: 0.0672997385263443
2023-01-23 01:32:05.912346: step: 908/533, loss: 0.03160591050982475
2023-01-23 01:32:07.092857: step: 912/533, loss: 0.2144254595041275
2023-01-23 01:32:08.245392: step: 916/533, loss: 0.047751907259225845
2023-01-23 01:32:09.395618: step: 920/533, loss: 0.08782310783863068
2023-01-23 01:32:10.563420: step: 924/533, loss: 0.0461915023624897
2023-01-23 01:32:11.714493: step: 928/533, loss: 0.013929082080721855
2023-01-23 01:32:12.904844: step: 932/533, loss: 0.11307516694068909
2023-01-23 01:32:14.040068: step: 936/533, loss: 0.04707388952374458
2023-01-23 01:32:15.239741: step: 940/533, loss: 0.09293480217456818
2023-01-23 01:32:16.424984: step: 944/533, loss: 0.0036401748657226562
2023-01-23 01:32:17.596341: step: 948/533, loss: 0.08520784974098206
2023-01-23 01:32:18.769791: step: 952/533, loss: 0.017494583502411842
2023-01-23 01:32:19.947505: step: 956/533, loss: 0.011858273297548294
2023-01-23 01:32:21.092418: step: 960/533, loss: 0.0019500732887536287
2023-01-23 01:32:22.239391: step: 964/533, loss: 0.06429986655712128
2023-01-23 01:32:23.426854: step: 968/533, loss: 0.12511055171489716
2023-01-23 01:32:24.629414: step: 972/533, loss: 0.02482757531106472
2023-01-23 01:32:25.803201: step: 976/533, loss: 0.01854996755719185
2023-01-23 01:32:26.957967: step: 980/533, loss: 0.033623307943344116
2023-01-23 01:32:28.155460: step: 984/533, loss: 0.06684722751379013
2023-01-23 01:32:29.346363: step: 988/533, loss: 0.02318502776324749
2023-01-23 01:32:30.518498: step: 992/533, loss: 0.02847576141357422
2023-01-23 01:32:31.692482: step: 996/533, loss: 0.08658294379711151
2023-01-23 01:32:32.872459: step: 1000/533, loss: 0.02443409152328968
2023-01-23 01:32:34.065861: step: 1004/533, loss: 0.007188225165009499
2023-01-23 01:32:35.234630: step: 1008/533, loss: 0.019654560834169388
2023-01-23 01:32:36.371062: step: 1012/533, loss: 0.053139831870794296
2023-01-23 01:32:37.580279: step: 1016/533, loss: 0.05817057937383652
2023-01-23 01:32:38.756030: step: 1020/533, loss: 0.13626976311206818
2023-01-23 01:32:39.928096: step: 1024/533, loss: 0.05506887286901474
2023-01-23 01:32:41.089784: step: 1028/533, loss: 0.027257252484560013
2023-01-23 01:32:42.293121: step: 1032/533, loss: 0.037662312388420105
2023-01-23 01:32:43.445761: step: 1036/533, loss: 0.051063500344753265
2023-01-23 01:32:44.611414: step: 1040/533, loss: 0.042043305933475494
2023-01-23 01:32:45.796590: step: 1044/533, loss: 0.05184240639209747
2023-01-23 01:32:46.957410: step: 1048/533, loss: 0.018011093139648438
2023-01-23 01:32:48.094668: step: 1052/533, loss: 0.03362541273236275
2023-01-23 01:32:49.282869: step: 1056/533, loss: 0.0038625719025731087
2023-01-23 01:32:50.436078: step: 1060/533, loss: 0.011679555289447308
2023-01-23 01:32:51.632192: step: 1064/533, loss: 0.01837022230029106
2023-01-23 01:32:52.847013: step: 1068/533, loss: 0.04417762905359268
2023-01-23 01:32:54.003873: step: 1072/533, loss: 0.010522127151489258
2023-01-23 01:32:55.196716: step: 1076/533, loss: 0.061770249158144
2023-01-23 01:32:56.337555: step: 1080/533, loss: 0.07209939509630203
2023-01-23 01:32:57.494461: step: 1084/533, loss: 0.6111618280410767
2023-01-23 01:32:58.697486: step: 1088/533, loss: 0.02486734464764595
2023-01-23 01:32:59.850816: step: 1092/533, loss: 0.010312545113265514
2023-01-23 01:33:01.052735: step: 1096/533, loss: 0.0774257630109787
2023-01-23 01:33:02.228355: step: 1100/533, loss: 0.007196473889052868
2023-01-23 01:33:03.369327: step: 1104/533, loss: 0.046445272862911224
2023-01-23 01:33:04.549299: step: 1108/533, loss: 0.03284912183880806
2023-01-23 01:33:05.745688: step: 1112/533, loss: 0.03728685528039932
2023-01-23 01:33:06.858234: step: 1116/533, loss: 0.062476254999637604
2023-01-23 01:33:08.034559: step: 1120/533, loss: 0.0112457275390625
2023-01-23 01:33:09.204529: step: 1124/533, loss: 0.0990542471408844
2023-01-23 01:33:10.407517: step: 1128/533, loss: 0.06675414741039276
2023-01-23 01:33:11.574548: step: 1132/533, loss: 0.013537216931581497
2023-01-23 01:33:12.721325: step: 1136/533, loss: 0.13270586729049683
2023-01-23 01:33:13.865574: step: 1140/533, loss: 0.07421837002038956
2023-01-23 01:33:15.021263: step: 1144/533, loss: 0.0027669547125697136
2023-01-23 01:33:16.205495: step: 1148/533, loss: 0.11421117931604385
2023-01-23 01:33:17.398246: step: 1152/533, loss: 0.054032422602176666
2023-01-23 01:33:18.589642: step: 1156/533, loss: 0.025281094014644623
2023-01-23 01:33:19.791743: step: 1160/533, loss: 0.17904329299926758
2023-01-23 01:33:20.980586: step: 1164/533, loss: 0.04856109619140625
2023-01-23 01:33:22.121458: step: 1168/533, loss: 0.058324433863162994
2023-01-23 01:33:23.319660: step: 1172/533, loss: 0.06331968307495117
2023-01-23 01:33:24.478842: step: 1176/533, loss: 0.2400626242160797
2023-01-23 01:33:25.620175: step: 1180/533, loss: 0.03560075908899307
2023-01-23 01:33:26.807565: step: 1184/533, loss: 0.009624456986784935
2023-01-23 01:33:28.009750: step: 1188/533, loss: 0.04755058512091637
2023-01-23 01:33:29.171975: step: 1192/533, loss: 0.06912145763635635
2023-01-23 01:33:30.333999: step: 1196/533, loss: 0.0572635643184185
2023-01-23 01:33:31.518081: step: 1200/533, loss: 0.0376192107796669
2023-01-23 01:33:32.716901: step: 1204/533, loss: 0.057989977300167084
2023-01-23 01:33:33.885057: step: 1208/533, loss: 0.03752708435058594
2023-01-23 01:33:35.042651: step: 1212/533, loss: 0.08052120357751846
2023-01-23 01:33:36.197662: step: 1216/533, loss: 0.003288400126621127
2023-01-23 01:33:37.371138: step: 1220/533, loss: 0.022491026669740677
2023-01-23 01:33:38.562581: step: 1224/533, loss: 0.0004567146534100175
2023-01-23 01:33:39.756732: step: 1228/533, loss: 0.15962447226047516
2023-01-23 01:33:40.914750: step: 1232/533, loss: 0.06012604385614395
2023-01-23 01:33:42.066809: step: 1236/533, loss: 0.06118650361895561
2023-01-23 01:33:43.227315: step: 1240/533, loss: 0.04592762142419815
2023-01-23 01:33:44.379257: step: 1244/533, loss: 0.01642293855547905
2023-01-23 01:33:45.559335: step: 1248/533, loss: 0.0709286704659462
2023-01-23 01:33:46.767592: step: 1252/533, loss: 0.6426746249198914
2023-01-23 01:33:47.922344: step: 1256/533, loss: 0.024199390783905983
2023-01-23 01:33:49.083016: step: 1260/533, loss: 0.029232501983642578
2023-01-23 01:33:50.236161: step: 1264/533, loss: 0.020049571990966797
2023-01-23 01:33:51.418453: step: 1268/533, loss: 0.05558958277106285
2023-01-23 01:33:52.566157: step: 1272/533, loss: 0.06585562974214554
2023-01-23 01:33:53.724900: step: 1276/533, loss: 0.0010228157043457031
2023-01-23 01:33:54.923221: step: 1280/533, loss: 0.2014915496110916
2023-01-23 01:33:56.030089: step: 1284/533, loss: 0.046613503247499466
2023-01-23 01:33:57.217175: step: 1288/533, loss: 0.044942282140254974
2023-01-23 01:33:58.381094: step: 1292/533, loss: 0.010610103607177734
2023-01-23 01:33:59.587488: step: 1296/533, loss: 0.029195215553045273
2023-01-23 01:34:00.804689: step: 1300/533, loss: 0.43042439222335815
2023-01-23 01:34:01.975202: step: 1304/533, loss: 0.018293000757694244
2023-01-23 01:34:03.214247: step: 1308/533, loss: 0.04098348692059517
2023-01-23 01:34:04.376006: step: 1312/533, loss: 0.11825218796730042
2023-01-23 01:34:05.521341: step: 1316/533, loss: 0.06375002861022949
2023-01-23 01:34:06.706464: step: 1320/533, loss: 0.08055982738733292
2023-01-23 01:34:07.891098: step: 1324/533, loss: 0.039058782160282135
2023-01-23 01:34:09.087983: step: 1328/533, loss: 0.06780214607715607
2023-01-23 01:34:10.261971: step: 1332/533, loss: 0.05446338653564453
2023-01-23 01:34:11.444025: step: 1336/533, loss: 0.05097074434161186
2023-01-23 01:34:12.619417: step: 1340/533, loss: 1.152879238128662
2023-01-23 01:34:13.778328: step: 1344/533, loss: 0.001506805419921875
2023-01-23 01:34:14.961771: step: 1348/533, loss: 0.06723959743976593
2023-01-23 01:34:16.139802: step: 1352/533, loss: 0.01587352715432644
2023-01-23 01:34:17.298473: step: 1356/533, loss: 0.035622358322143555
2023-01-23 01:34:18.494153: step: 1360/533, loss: 0.34401464462280273
2023-01-23 01:34:19.696437: step: 1364/533, loss: 0.10021839290857315
2023-01-23 01:34:20.863798: step: 1368/533, loss: 0.037081338465213776
2023-01-23 01:34:22.036091: step: 1372/533, loss: 0.03386535495519638
2023-01-23 01:34:23.216214: step: 1376/533, loss: 0.011300945654511452
2023-01-23 01:34:24.374309: step: 1380/533, loss: 0.13766269385814667
2023-01-23 01:34:25.561216: step: 1384/533, loss: 0.018306540325284004
2023-01-23 01:34:26.772153: step: 1388/533, loss: 0.00264053326100111
2023-01-23 01:34:27.935626: step: 1392/533, loss: 0.0549396276473999
2023-01-23 01:34:29.128726: step: 1396/533, loss: 0.08497276902198792
2023-01-23 01:34:30.308980: step: 1400/533, loss: 0.030950356274843216
2023-01-23 01:34:31.475271: step: 1404/533, loss: 0.049021054059267044
2023-01-23 01:34:32.617157: step: 1408/533, loss: 0.024622201919555664
2023-01-23 01:34:33.897541: step: 1412/533, loss: 0.039582788944244385
2023-01-23 01:34:35.060346: step: 1416/533, loss: 0.04685864597558975
2023-01-23 01:34:36.225442: step: 1420/533, loss: 0.014054680243134499
2023-01-23 01:34:37.410339: step: 1424/533, loss: 0.1489175409078598
2023-01-23 01:34:38.584672: step: 1428/533, loss: 0.10843181610107422
2023-01-23 01:34:39.746170: step: 1432/533, loss: 0.11393924057483673
2023-01-23 01:34:40.993444: step: 1436/533, loss: 0.025747396051883698
2023-01-23 01:34:42.217352: step: 1440/533, loss: 0.41678953170776367
2023-01-23 01:34:43.413821: step: 1444/533, loss: 0.039380647242069244
2023-01-23 01:34:44.596640: step: 1448/533, loss: 0.051689907908439636
2023-01-23 01:34:45.816411: step: 1452/533, loss: 0.535626232624054
2023-01-23 01:34:47.019922: step: 1456/533, loss: 0.1808479279279709
2023-01-23 01:34:48.178110: step: 1460/533, loss: 0.04927721247076988
2023-01-23 01:34:49.315917: step: 1464/533, loss: 0.03549213334918022
2023-01-23 01:34:50.498430: step: 1468/533, loss: 0.025571823120117188
2023-01-23 01:34:51.658319: step: 1472/533, loss: 0.01535797119140625
2023-01-23 01:34:52.812458: step: 1476/533, loss: 0.06740112602710724
2023-01-23 01:34:54.003532: step: 1480/533, loss: 0.3737823963165283
2023-01-23 01:34:55.184073: step: 1484/533, loss: 0.023802900686860085
2023-01-23 01:34:56.321643: step: 1488/533, loss: 0.015548801980912685
2023-01-23 01:34:57.468804: step: 1492/533, loss: 0.04977254942059517
2023-01-23 01:34:58.697970: step: 1496/533, loss: 0.2738347351551056
2023-01-23 01:34:59.872695: step: 1500/533, loss: 0.027628321200609207
2023-01-23 01:35:01.033460: step: 1504/533, loss: 0.011148596182465553
2023-01-23 01:35:02.267609: step: 1508/533, loss: 0.003384876297786832
2023-01-23 01:35:03.466467: step: 1512/533, loss: 0.22552672028541565
2023-01-23 01:35:04.645191: step: 1516/533, loss: 0.02197723463177681
2023-01-23 01:35:05.833472: step: 1520/533, loss: 0.3720621168613434
2023-01-23 01:35:07.021721: step: 1524/533, loss: 0.009566117078065872
2023-01-23 01:35:08.243744: step: 1528/533, loss: 0.060518693178892136
2023-01-23 01:35:09.418345: step: 1532/533, loss: 0.007303190417587757
2023-01-23 01:35:10.621096: step: 1536/533, loss: 0.07793235778808594
2023-01-23 01:35:11.783500: step: 1540/533, loss: 0.003921413328498602
2023-01-23 01:35:12.954587: step: 1544/533, loss: 0.04175548627972603
2023-01-23 01:35:14.140729: step: 1548/533, loss: 0.05214815214276314
2023-01-23 01:35:15.327938: step: 1552/533, loss: 0.013699413277208805
2023-01-23 01:35:16.576933: step: 1556/533, loss: 0.05700492858886719
2023-01-23 01:35:17.788383: step: 1560/533, loss: 0.02967863157391548
2023-01-23 01:35:19.019360: step: 1564/533, loss: 0.014600848779082298
2023-01-23 01:35:20.188382: step: 1568/533, loss: 0.10859213024377823
2023-01-23 01:35:21.426561: step: 1572/533, loss: 0.006503486540168524
2023-01-23 01:35:22.609626: step: 1576/533, loss: 0.017542744055390358
2023-01-23 01:35:23.800486: step: 1580/533, loss: 0.05604248121380806
2023-01-23 01:35:24.975170: step: 1584/533, loss: 0.08737903833389282
2023-01-23 01:35:26.163175: step: 1588/533, loss: 0.04217586666345596
2023-01-23 01:35:27.330681: step: 1592/533, loss: 0.026972675696015358
2023-01-23 01:35:28.499378: step: 1596/533, loss: 0.0016846180660650134
2023-01-23 01:35:29.704746: step: 1600/533, loss: 0.060553815215826035
2023-01-23 01:35:30.887542: step: 1604/533, loss: 0.1027032881975174
2023-01-23 01:35:32.046061: step: 1608/533, loss: 0.07762566208839417
2023-01-23 01:35:33.186964: step: 1612/533, loss: 0.005103397648781538
2023-01-23 01:35:34.374329: step: 1616/533, loss: 0.022433947771787643
2023-01-23 01:35:35.539129: step: 1620/533, loss: 0.04688744619488716
2023-01-23 01:35:36.729341: step: 1624/533, loss: 0.07281551510095596
2023-01-23 01:35:37.948737: step: 1628/533, loss: 0.131850004196167
2023-01-23 01:35:39.147568: step: 1632/533, loss: 0.013134479522705078
2023-01-23 01:35:40.347883: step: 1636/533, loss: 0.08298487961292267
2023-01-23 01:35:41.521219: step: 1640/533, loss: 0.011401604861021042
2023-01-23 01:35:42.685816: step: 1644/533, loss: 0.15960845351219177
2023-01-23 01:35:43.875440: step: 1648/533, loss: 0.05998096615076065
2023-01-23 01:35:45.052137: step: 1652/533, loss: 0.042473673820495605
2023-01-23 01:35:46.229878: step: 1656/533, loss: 0.06607169657945633
2023-01-23 01:35:47.371763: step: 1660/533, loss: 0.006520366761833429
2023-01-23 01:35:48.514716: step: 1664/533, loss: 0.02886677160859108
2023-01-23 01:35:49.671350: step: 1668/533, loss: 0.015095710754394531
2023-01-23 01:35:50.837633: step: 1672/533, loss: 0.08982840180397034
2023-01-23 01:35:52.046370: step: 1676/533, loss: 0.06776418536901474
2023-01-23 01:35:53.202087: step: 1680/533, loss: 0.061571888625621796
2023-01-23 01:35:54.437679: step: 1684/533, loss: 0.05083566904067993
2023-01-23 01:35:55.636652: step: 1688/533, loss: 0.06410541385412216
2023-01-23 01:35:56.800299: step: 1692/533, loss: 0.13023224472999573
2023-01-23 01:35:57.958141: step: 1696/533, loss: 0.03539867326617241
2023-01-23 01:35:59.130303: step: 1700/533, loss: 0.014899969100952148
2023-01-23 01:36:00.266603: step: 1704/533, loss: 0.158883735537529
2023-01-23 01:36:01.430595: step: 1708/533, loss: 0.009968948550522327
2023-01-23 01:36:02.606155: step: 1712/533, loss: 0.05930042266845703
2023-01-23 01:36:03.782457: step: 1716/533, loss: 0.019159698858857155
2023-01-23 01:36:04.934962: step: 1720/533, loss: 0.031523894518613815
2023-01-23 01:36:06.130209: step: 1724/533, loss: 0.031030654907226562
2023-01-23 01:36:07.294379: step: 1728/533, loss: 0.017488574609160423
2023-01-23 01:36:08.510936: step: 1732/533, loss: 0.09975738823413849
2023-01-23 01:36:09.683930: step: 1736/533, loss: 0.014637804590165615
2023-01-23 01:36:10.856329: step: 1740/533, loss: 0.02560257911682129
2023-01-23 01:36:12.028626: step: 1744/533, loss: 0.011232377029955387
2023-01-23 01:36:13.168590: step: 1748/533, loss: 0.035165030509233475
2023-01-23 01:36:14.344414: step: 1752/533, loss: 0.03615207597613335
2023-01-23 01:36:15.517796: step: 1756/533, loss: 0.05477473884820938
2023-01-23 01:36:16.698392: step: 1760/533, loss: 0.07021446526050568
2023-01-23 01:36:17.882238: step: 1764/533, loss: 0.029623890295624733
2023-01-23 01:36:19.061675: step: 1768/533, loss: 0.029053211212158203
2023-01-23 01:36:20.254609: step: 1772/533, loss: 0.097753144800663
2023-01-23 01:36:21.449846: step: 1776/533, loss: 0.03115224838256836
2023-01-23 01:36:22.610162: step: 1780/533, loss: 0.012836361303925514
2023-01-23 01:36:23.753820: step: 1784/533, loss: 0.8643342852592468
2023-01-23 01:36:24.922987: step: 1788/533, loss: 0.03354082256555557
2023-01-23 01:36:26.088689: step: 1792/533, loss: 0.03175721317529678
2023-01-23 01:36:27.276748: step: 1796/533, loss: 0.09133930504322052
2023-01-23 01:36:28.472238: step: 1800/533, loss: 0.12361745536327362
2023-01-23 01:36:29.623155: step: 1804/533, loss: 0.04615011066198349
2023-01-23 01:36:30.850866: step: 1808/533, loss: 0.11400061100721359
2023-01-23 01:36:31.995272: step: 1812/533, loss: 0.017228269949555397
2023-01-23 01:36:33.183109: step: 1816/533, loss: 0.08150921016931534
2023-01-23 01:36:34.397817: step: 1820/533, loss: 0.02705707587301731
2023-01-23 01:36:35.581961: step: 1824/533, loss: 0.07153358310461044
2023-01-23 01:36:36.778159: step: 1828/533, loss: 0.028616715222597122
2023-01-23 01:36:37.979959: step: 1832/533, loss: 0.015455532819032669
2023-01-23 01:36:39.233837: step: 1836/533, loss: 0.12773366272449493
2023-01-23 01:36:40.393439: step: 1840/533, loss: 0.1605411171913147
2023-01-23 01:36:41.531641: step: 1844/533, loss: 0.01254820916801691
2023-01-23 01:36:42.709394: step: 1848/533, loss: 0.04598388820886612
2023-01-23 01:36:43.906174: step: 1852/533, loss: 0.11140614002943039
2023-01-23 01:36:45.068656: step: 1856/533, loss: 0.01506586093455553
2023-01-23 01:36:46.244442: step: 1860/533, loss: 0.019997311756014824
2023-01-23 01:36:47.385898: step: 1864/533, loss: 0.03732867166399956
2023-01-23 01:36:48.501434: step: 1868/533, loss: 0.006541824899613857
2023-01-23 01:36:49.670352: step: 1872/533, loss: 0.04486050829291344
2023-01-23 01:36:50.863297: step: 1876/533, loss: 0.08218993991613388
2023-01-23 01:36:52.080764: step: 1880/533, loss: 0.015301275067031384
2023-01-23 01:36:53.233519: step: 1884/533, loss: 0.03984098136425018
2023-01-23 01:36:54.400347: step: 1888/533, loss: 0.050959013402462006
2023-01-23 01:36:55.582093: step: 1892/533, loss: 0.1539476364850998
2023-01-23 01:36:56.756216: step: 1896/533, loss: 0.03992071375250816
2023-01-23 01:36:57.910784: step: 1900/533, loss: 0.09901275485754013
2023-01-23 01:36:59.078488: step: 1904/533, loss: 0.10107841342687607
2023-01-23 01:37:00.241945: step: 1908/533, loss: 0.020864101126790047
2023-01-23 01:37:01.432391: step: 1912/533, loss: 0.07817935943603516
2023-01-23 01:37:02.629854: step: 1916/533, loss: 0.09975185245275497
2023-01-23 01:37:03.807984: step: 1920/533, loss: 0.06512641906738281
2023-01-23 01:37:05.007199: step: 1924/533, loss: 0.057581521570682526
2023-01-23 01:37:06.229790: step: 1928/533, loss: 0.03314018249511719
2023-01-23 01:37:07.389401: step: 1932/533, loss: 0.013709831982851028
2023-01-23 01:37:08.593563: step: 1936/533, loss: 0.06103997677564621
2023-01-23 01:37:09.790314: step: 1940/533, loss: 0.047936033457517624
2023-01-23 01:37:10.960820: step: 1944/533, loss: 0.040651895105838776
2023-01-23 01:37:12.146340: step: 1948/533, loss: 0.008717156015336514
2023-01-23 01:37:13.330046: step: 1952/533, loss: 0.025026893243193626
2023-01-23 01:37:14.487245: step: 1956/533, loss: 0.019580364227294922
2023-01-23 01:37:15.652409: step: 1960/533, loss: 0.014453220181167126
2023-01-23 01:37:16.829009: step: 1964/533, loss: 0.03233394771814346
2023-01-23 01:37:18.005690: step: 1968/533, loss: 0.6248613595962524
2023-01-23 01:37:19.219942: step: 1972/533, loss: 0.12208108603954315
2023-01-23 01:37:20.399138: step: 1976/533, loss: 0.04608125612139702
2023-01-23 01:37:21.589257: step: 1980/533, loss: 0.09121675789356232
2023-01-23 01:37:22.788519: step: 1984/533, loss: 0.08527243137359619
2023-01-23 01:37:23.961769: step: 1988/533, loss: 0.07880210876464844
2023-01-23 01:37:25.132205: step: 1992/533, loss: 0.06456947326660156
2023-01-23 01:37:26.328842: step: 1996/533, loss: 0.026406098157167435
2023-01-23 01:37:27.535282: step: 2000/533, loss: 0.05671081691980362
2023-01-23 01:37:28.723462: step: 2004/533, loss: 0.0009198188781738281
2023-01-23 01:37:29.874097: step: 2008/533, loss: 0.04607219621539116
2023-01-23 01:37:31.073926: step: 2012/533, loss: 0.05803294479846954
2023-01-23 01:37:32.233471: step: 2016/533, loss: 0.02836422808468342
2023-01-23 01:37:33.409752: step: 2020/533, loss: 0.06971683353185654
2023-01-23 01:37:34.619270: step: 2024/533, loss: 0.0008287429809570312
2023-01-23 01:37:35.815696: step: 2028/533, loss: 0.051264382898807526
2023-01-23 01:37:36.988779: step: 2032/533, loss: 0.0007672309875488281
2023-01-23 01:37:38.197024: step: 2036/533, loss: 0.029651736840605736
2023-01-23 01:37:39.392317: step: 2040/533, loss: 0.11418915539979935
2023-01-23 01:37:40.602399: step: 2044/533, loss: 0.033976174890995026
2023-01-23 01:37:41.781119: step: 2048/533, loss: 0.057324983179569244
2023-01-23 01:37:42.921117: step: 2052/533, loss: 0.06552743911743164
2023-01-23 01:37:44.145945: step: 2056/533, loss: 0.05742397531867027
2023-01-23 01:37:45.302501: step: 2060/533, loss: 0.034281156957149506
2023-01-23 01:37:46.480033: step: 2064/533, loss: 0.004154014401137829
2023-01-23 01:37:47.705271: step: 2068/533, loss: 0.04763736575841904
2023-01-23 01:37:48.858309: step: 2072/533, loss: 0.062172889709472656
2023-01-23 01:37:50.057350: step: 2076/533, loss: 0.03974580764770508
2023-01-23 01:37:51.243258: step: 2080/533, loss: 0.08486881107091904
2023-01-23 01:37:52.424931: step: 2084/533, loss: 0.06954784691333771
2023-01-23 01:37:53.602661: step: 2088/533, loss: 0.058583930134773254
2023-01-23 01:37:54.811844: step: 2092/533, loss: 0.04322100058197975
2023-01-23 01:37:55.971381: step: 2096/533, loss: 0.04362912476062775
2023-01-23 01:37:57.140585: step: 2100/533, loss: 0.05357861518859863
2023-01-23 01:37:58.302352: step: 2104/533, loss: 0.047242093831300735
2023-01-23 01:37:59.452770: step: 2108/533, loss: 0.04727339744567871
2023-01-23 01:38:00.643657: step: 2112/533, loss: 0.1299700289964676
2023-01-23 01:38:01.830875: step: 2116/533, loss: 0.024875832721590996
2023-01-23 01:38:03.031778: step: 2120/533, loss: 0.020792867988348007
2023-01-23 01:38:04.252326: step: 2124/533, loss: 0.08784227073192596
2023-01-23 01:38:05.413938: step: 2128/533, loss: 0.010356160812079906
2023-01-23 01:38:06.575843: step: 2132/533, loss: 0.08221583813428879
==================================================
Loss: 0.069
--------------------
Dev: {'event': {'p': 0.6244541484716157, 'r': 0.7616511318242344, 'f1': 0.6862627474505099}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6416624429802331, 'r': 0.809462915601023, 'f1': 0.7158608990670059}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
Korean: {'event': {'p': 0.5769230769230769, 'r': 0.47619047619047616, 'f1': 0.5217391304347826}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:38:47.369732: step: 4/533, loss: 0.041904352605342865
2023-01-23 01:38:48.544736: step: 8/533, loss: 0.0374697670340538
2023-01-23 01:38:49.767938: step: 12/533, loss: 0.06795825809240341
2023-01-23 01:38:50.943672: step: 16/533, loss: 0.07436218857765198
2023-01-23 01:38:52.125571: step: 20/533, loss: 0.02218928374350071
2023-01-23 01:38:53.314515: step: 24/533, loss: 0.028714274987578392
2023-01-23 01:38:54.487596: step: 28/533, loss: 0.01710367389023304
2023-01-23 01:38:55.692567: step: 32/533, loss: 0.02336578257381916
2023-01-23 01:38:56.842610: step: 36/533, loss: 0.017100047320127487
2023-01-23 01:38:58.008656: step: 40/533, loss: 0.1393013894557953
2023-01-23 01:38:59.203132: step: 44/533, loss: 0.03557715564966202
2023-01-23 01:39:00.384035: step: 48/533, loss: 0.03423051908612251
2023-01-23 01:39:01.563121: step: 52/533, loss: 0.039509013295173645
2023-01-23 01:39:02.752089: step: 56/533, loss: 0.007215403951704502
2023-01-23 01:39:03.952191: step: 60/533, loss: 0.062174417078495026
2023-01-23 01:39:05.160394: step: 64/533, loss: 0.052642252296209335
2023-01-23 01:39:06.335720: step: 68/533, loss: 0.06284160912036896
2023-01-23 01:39:07.521381: step: 72/533, loss: 0.03643188625574112
2023-01-23 01:39:08.699192: step: 76/533, loss: 0.003572177840396762
2023-01-23 01:39:09.897265: step: 80/533, loss: 0.09779243916273117
2023-01-23 01:39:11.050639: step: 84/533, loss: 0.17891749739646912
2023-01-23 01:39:12.235696: step: 88/533, loss: 0.02024994045495987
2023-01-23 01:39:13.439198: step: 92/533, loss: 0.18497686088085175
2023-01-23 01:39:14.596103: step: 96/533, loss: 0.07873706519603729
2023-01-23 01:39:15.775966: step: 100/533, loss: 0.035846613347530365
2023-01-23 01:39:16.960685: step: 104/533, loss: 0.019582651555538177
2023-01-23 01:39:18.125160: step: 108/533, loss: 0.019284486770629883
2023-01-23 01:39:19.319857: step: 112/533, loss: 0.027866506949067116
2023-01-23 01:39:20.536818: step: 116/533, loss: 0.1550152748823166
2023-01-23 01:39:21.765704: step: 120/533, loss: 0.12320385128259659
2023-01-23 01:39:22.934800: step: 124/533, loss: 0.03342805057764053
2023-01-23 01:39:24.117585: step: 128/533, loss: 0.0074793933890759945
2023-01-23 01:39:25.284192: step: 132/533, loss: 0.012518501840531826
2023-01-23 01:39:26.506608: step: 136/533, loss: 0.0877528190612793
2023-01-23 01:39:27.712296: step: 140/533, loss: 0.0618189200758934
2023-01-23 01:39:28.892201: step: 144/533, loss: 0.01933436468243599
2023-01-23 01:39:30.059501: step: 148/533, loss: 0.03780355304479599
2023-01-23 01:39:31.232116: step: 152/533, loss: 0.02359323389828205
2023-01-23 01:39:32.427871: step: 156/533, loss: 0.040283203125
2023-01-23 01:39:33.590932: step: 160/533, loss: 0.06320181488990784
2023-01-23 01:39:34.799567: step: 164/533, loss: 0.02956409379839897
2023-01-23 01:39:35.973159: step: 168/533, loss: 0.002128219697624445
2023-01-23 01:39:37.177496: step: 172/533, loss: 0.027791213244199753
2023-01-23 01:39:38.313187: step: 176/533, loss: 0.06364583969116211
2023-01-23 01:39:39.471476: step: 180/533, loss: 0.027123406529426575
2023-01-23 01:39:40.663736: step: 184/533, loss: 0.03582916408777237
2023-01-23 01:39:41.867836: step: 188/533, loss: 0.004851293750107288
2023-01-23 01:39:43.055387: step: 192/533, loss: 0.1057400330901146
2023-01-23 01:39:44.209530: step: 196/533, loss: 0.013115882873535156
2023-01-23 01:39:45.399265: step: 200/533, loss: 0.04010210186243057
2023-01-23 01:39:46.623174: step: 204/533, loss: 0.029671097174286842
2023-01-23 01:39:47.798338: step: 208/533, loss: 0.00581812858581543
2023-01-23 01:39:48.982084: step: 212/533, loss: 0.008448028936982155
2023-01-23 01:39:50.188410: step: 216/533, loss: 0.013164937496185303
2023-01-23 01:39:51.370132: step: 220/533, loss: 0.005957365036010742
2023-01-23 01:39:52.511071: step: 224/533, loss: 0.01655890978872776
2023-01-23 01:39:53.649621: step: 228/533, loss: 0.1682807058095932
2023-01-23 01:39:54.824756: step: 232/533, loss: 0.005534934811294079
2023-01-23 01:39:55.975404: step: 236/533, loss: 0.016397953033447266
2023-01-23 01:39:57.185085: step: 240/533, loss: 0.201178640127182
2023-01-23 01:39:58.335369: step: 244/533, loss: 0.00960841216146946
2023-01-23 01:39:59.506806: step: 248/533, loss: 0.057245831936597824
2023-01-23 01:40:00.691735: step: 252/533, loss: 0.020941734313964844
2023-01-23 01:40:01.880741: step: 256/533, loss: 0.051650047302246094
2023-01-23 01:40:03.048513: step: 260/533, loss: 0.005865669343620539
2023-01-23 01:40:04.204759: step: 264/533, loss: 0.1919335275888443
2023-01-23 01:40:05.360327: step: 268/533, loss: 0.16353721916675568
2023-01-23 01:40:06.502088: step: 272/533, loss: 0.0005916595691815019
2023-01-23 01:40:07.668054: step: 276/533, loss: 0.044652655720710754
2023-01-23 01:40:08.819736: step: 280/533, loss: 0.01705150678753853
2023-01-23 01:40:09.976408: step: 284/533, loss: 0.004418182652443647
2023-01-23 01:40:11.180031: step: 288/533, loss: 0.0002839088556356728
2023-01-23 01:40:12.380935: step: 292/533, loss: 0.05885763093829155
2023-01-23 01:40:13.524711: step: 296/533, loss: 0.004337406251579523
2023-01-23 01:40:14.710513: step: 300/533, loss: 0.06694946438074112
2023-01-23 01:40:15.945456: step: 304/533, loss: 0.038599491119384766
2023-01-23 01:40:17.084127: step: 308/533, loss: 0.05937004089355469
2023-01-23 01:40:18.284463: step: 312/533, loss: 0.00040993691072799265
2023-01-23 01:40:19.454953: step: 316/533, loss: 0.011014366522431374
2023-01-23 01:40:20.643468: step: 320/533, loss: 0.048088837414979935
2023-01-23 01:40:21.807068: step: 324/533, loss: 0.01701197773218155
2023-01-23 01:40:22.965751: step: 328/533, loss: 0.025472545996308327
2023-01-23 01:40:24.164104: step: 332/533, loss: 0.011154365725815296
2023-01-23 01:40:25.382342: step: 336/533, loss: 0.024979686364531517
2023-01-23 01:40:26.543830: step: 340/533, loss: 0.02335391193628311
2023-01-23 01:40:27.716659: step: 344/533, loss: 0.10278654098510742
2023-01-23 01:40:28.921411: step: 348/533, loss: 0.052660562098026276
2023-01-23 01:40:30.155575: step: 352/533, loss: 0.05932150036096573
2023-01-23 01:40:31.293179: step: 356/533, loss: 0.020996378734707832
2023-01-23 01:40:32.487631: step: 360/533, loss: 0.04142170026898384
2023-01-23 01:40:33.711747: step: 364/533, loss: 0.11402206122875214
2023-01-23 01:40:34.895304: step: 368/533, loss: 0.029016535729169846
2023-01-23 01:40:36.064848: step: 372/533, loss: 0.05256099998950958
2023-01-23 01:40:37.226819: step: 376/533, loss: 0.07133827358484268
2023-01-23 01:40:38.415416: step: 380/533, loss: 0.02216320112347603
2023-01-23 01:40:39.608861: step: 384/533, loss: 0.0813487097620964
2023-01-23 01:40:40.760715: step: 388/533, loss: 0.021233130246400833
2023-01-23 01:40:41.992049: step: 392/533, loss: 0.02132740058004856
2023-01-23 01:40:43.220476: step: 396/533, loss: 0.027507878839969635
2023-01-23 01:40:44.402069: step: 400/533, loss: 0.008081817999482155
2023-01-23 01:40:45.568970: step: 404/533, loss: 0.019214915111660957
2023-01-23 01:40:46.756309: step: 408/533, loss: 0.01882343180477619
2023-01-23 01:40:47.960287: step: 412/533, loss: 0.08627300709486008
2023-01-23 01:40:49.194816: step: 416/533, loss: 0.03166494518518448
2023-01-23 01:40:50.364130: step: 420/533, loss: 0.007539940066635609
2023-01-23 01:40:51.546388: step: 424/533, loss: 0.01225423812866211
2023-01-23 01:40:52.723683: step: 428/533, loss: 0.48720666766166687
2023-01-23 01:40:53.894508: step: 432/533, loss: 0.013778448104858398
2023-01-23 01:40:55.101893: step: 436/533, loss: 0.023970890790224075
2023-01-23 01:40:56.282445: step: 440/533, loss: 0.0032465935219079256
2023-01-23 01:40:57.467288: step: 444/533, loss: 0.06096343696117401
2023-01-23 01:40:58.681094: step: 448/533, loss: 0.02353210374712944
2023-01-23 01:40:59.844999: step: 452/533, loss: 0.03164968639612198
2023-01-23 01:41:01.039981: step: 456/533, loss: 0.21471329033374786
2023-01-23 01:41:02.211590: step: 460/533, loss: 0.04640321806073189
2023-01-23 01:41:03.374777: step: 464/533, loss: 0.02782764658331871
2023-01-23 01:41:04.549287: step: 468/533, loss: 0.0024102211464196444
2023-01-23 01:41:05.755120: step: 472/533, loss: 0.04049396514892578
2023-01-23 01:41:06.982208: step: 476/533, loss: 0.019942332059144974
2023-01-23 01:41:08.153222: step: 480/533, loss: 0.012668239884078503
2023-01-23 01:41:09.321509: step: 484/533, loss: 0.04583416134119034
2023-01-23 01:41:10.484242: step: 488/533, loss: 0.002342796418815851
2023-01-23 01:41:11.684871: step: 492/533, loss: 0.04883222654461861
2023-01-23 01:41:12.824974: step: 496/533, loss: 0.08726353943347931
2023-01-23 01:41:14.010055: step: 500/533, loss: 0.0261735450476408
2023-01-23 01:41:15.211709: step: 504/533, loss: 0.0060156588442623615
2023-01-23 01:41:16.400178: step: 508/533, loss: 0.004028129391372204
2023-01-23 01:41:17.557311: step: 512/533, loss: 0.00636897049844265
2023-01-23 01:41:18.716311: step: 516/533, loss: 0.019833946600556374
2023-01-23 01:41:19.876459: step: 520/533, loss: 0.01276550255715847
2023-01-23 01:41:21.076382: step: 524/533, loss: 0.026750564575195312
2023-01-23 01:41:22.263514: step: 528/533, loss: 0.12476720660924911
2023-01-23 01:41:23.441624: step: 532/533, loss: 0.0007033348083496094
2023-01-23 01:41:24.631519: step: 536/533, loss: 0.06892824172973633
2023-01-23 01:41:25.792202: step: 540/533, loss: 0.05283260717988014
2023-01-23 01:41:26.955279: step: 544/533, loss: 0.09020958095788956
2023-01-23 01:41:28.113199: step: 548/533, loss: 0.018908215686678886
2023-01-23 01:41:29.269029: step: 552/533, loss: 0.012073302641510963
2023-01-23 01:41:30.462541: step: 556/533, loss: 0.23959484696388245
2023-01-23 01:41:31.641238: step: 560/533, loss: 0.04039249196648598
2023-01-23 01:41:32.816836: step: 564/533, loss: 0.013921642675995827
2023-01-23 01:41:33.978245: step: 568/533, loss: 0.004255819600075483
2023-01-23 01:41:35.128191: step: 572/533, loss: 0.015288257971405983
2023-01-23 01:41:36.286839: step: 576/533, loss: 0.03288526460528374
2023-01-23 01:41:37.470847: step: 580/533, loss: 0.06351232528686523
2023-01-23 01:41:38.634911: step: 584/533, loss: 0.004592800047248602
2023-01-23 01:41:39.838511: step: 588/533, loss: 0.017434120178222656
2023-01-23 01:41:41.022147: step: 592/533, loss: 0.12036561965942383
2023-01-23 01:41:42.193447: step: 596/533, loss: 0.04384660720825195
2023-01-23 01:41:43.397008: step: 600/533, loss: 0.034758470952510834
2023-01-23 01:41:44.589635: step: 604/533, loss: 0.02042102813720703
2023-01-23 01:41:45.779631: step: 608/533, loss: 0.021448900923132896
2023-01-23 01:41:46.964125: step: 612/533, loss: 0.060921575874090195
2023-01-23 01:41:48.124554: step: 616/533, loss: 0.18937024474143982
2023-01-23 01:41:49.288802: step: 620/533, loss: 0.013827895745635033
2023-01-23 01:41:50.441074: step: 624/533, loss: 0.0035732269752770662
2023-01-23 01:41:51.616986: step: 628/533, loss: 0.014711190015077591
2023-01-23 01:41:52.768760: step: 632/533, loss: 0.03498706966638565
2023-01-23 01:41:53.956159: step: 636/533, loss: 0.0016311646904796362
2023-01-23 01:41:55.148737: step: 640/533, loss: 0.0909392386674881
2023-01-23 01:41:56.300357: step: 644/533, loss: 0.024828530848026276
2023-01-23 01:41:57.473189: step: 648/533, loss: 0.03652148321270943
2023-01-23 01:41:58.638180: step: 652/533, loss: 0.021696995943784714
2023-01-23 01:41:59.824047: step: 656/533, loss: 1.1339837312698364
2023-01-23 01:42:00.995418: step: 660/533, loss: 0.06812019646167755
2023-01-23 01:42:02.140508: step: 664/533, loss: 0.03695373609662056
2023-01-23 01:42:03.304336: step: 668/533, loss: 0.01607351377606392
2023-01-23 01:42:04.527504: step: 672/533, loss: 0.3977532684803009
2023-01-23 01:42:05.733421: step: 676/533, loss: 0.019930077716708183
2023-01-23 01:42:06.956142: step: 680/533, loss: 0.0021008490584790707
2023-01-23 01:42:08.150067: step: 684/533, loss: 0.0179348886013031
2023-01-23 01:42:09.302439: step: 688/533, loss: 0.030675314366817474
2023-01-23 01:42:10.475035: step: 692/533, loss: 0.0865689218044281
2023-01-23 01:42:11.668292: step: 696/533, loss: 0.037986092269420624
2023-01-23 01:42:12.858467: step: 700/533, loss: 0.04570160061120987
2023-01-23 01:42:14.007229: step: 704/533, loss: 0.05926094204187393
2023-01-23 01:42:15.177453: step: 708/533, loss: 0.01253213919699192
2023-01-23 01:42:16.400866: step: 712/533, loss: 0.017019128426909447
2023-01-23 01:42:17.557734: step: 716/533, loss: 0.0007432937854900956
2023-01-23 01:42:18.757571: step: 720/533, loss: 0.12261772155761719
2023-01-23 01:42:19.912261: step: 724/533, loss: 0.20159253478050232
2023-01-23 01:42:21.110997: step: 728/533, loss: 0.08737373352050781
2023-01-23 01:42:22.282467: step: 732/533, loss: 0.0029486059211194515
2023-01-23 01:42:23.429122: step: 736/533, loss: 0.04386758804321289
2023-01-23 01:42:24.562672: step: 740/533, loss: 0.08595972508192062
2023-01-23 01:42:25.715605: step: 744/533, loss: 0.10736212879419327
2023-01-23 01:42:26.891577: step: 748/533, loss: 0.04567518085241318
2023-01-23 01:42:28.079135: step: 752/533, loss: 0.011414623819291592
2023-01-23 01:42:29.249984: step: 756/533, loss: 0.004131627269089222
2023-01-23 01:42:30.473846: step: 760/533, loss: 0.02365722693502903
2023-01-23 01:42:31.700155: step: 764/533, loss: 0.032416343688964844
2023-01-23 01:42:32.867826: step: 768/533, loss: 0.04998932033777237
2023-01-23 01:42:34.077958: step: 772/533, loss: 0.09170132130384445
2023-01-23 01:42:35.260890: step: 776/533, loss: 0.01733417622745037
2023-01-23 01:42:36.456605: step: 780/533, loss: 0.02901754342019558
2023-01-23 01:42:37.651251: step: 784/533, loss: 0.007569694425910711
2023-01-23 01:42:38.818669: step: 788/533, loss: 0.008176279254257679
2023-01-23 01:42:40.004042: step: 792/533, loss: 0.00899195671081543
2023-01-23 01:42:41.166349: step: 796/533, loss: 0.06712212413549423
2023-01-23 01:42:42.349685: step: 800/533, loss: 0.14444255828857422
2023-01-23 01:42:43.520653: step: 804/533, loss: 0.04913497343659401
2023-01-23 01:42:44.723382: step: 808/533, loss: 0.05984792858362198
2023-01-23 01:42:45.906021: step: 812/533, loss: 0.043523404747247696
2023-01-23 01:42:47.056939: step: 816/533, loss: 0.1107281744480133
2023-01-23 01:42:48.228541: step: 820/533, loss: 0.03707904741168022
2023-01-23 01:42:49.407402: step: 824/533, loss: 0.012945270165801048
2023-01-23 01:42:50.583314: step: 828/533, loss: 0.01947174221277237
2023-01-23 01:42:51.761884: step: 832/533, loss: 0.02723522298038006
2023-01-23 01:42:52.910773: step: 836/533, loss: 0.020889664068818092
2023-01-23 01:42:54.072944: step: 840/533, loss: 0.017010213807225227
2023-01-23 01:42:55.251771: step: 844/533, loss: 0.017997123301029205
2023-01-23 01:42:56.388241: step: 848/533, loss: 0.005139636807143688
2023-01-23 01:42:57.546773: step: 852/533, loss: 0.03821602091193199
2023-01-23 01:42:58.710763: step: 856/533, loss: 0.028556011617183685
2023-01-23 01:42:59.899645: step: 860/533, loss: 0.043375395238399506
2023-01-23 01:43:01.093847: step: 864/533, loss: 0.03889598697423935
2023-01-23 01:43:02.239513: step: 868/533, loss: 0.07777624577283859
2023-01-23 01:43:03.446111: step: 872/533, loss: 0.007169913966208696
2023-01-23 01:43:04.618007: step: 876/533, loss: 0.031205464154481888
2023-01-23 01:43:05.827041: step: 880/533, loss: 0.0543147549033165
2023-01-23 01:43:07.030501: step: 884/533, loss: 0.023758603259921074
2023-01-23 01:43:08.241571: step: 888/533, loss: 0.25472497940063477
2023-01-23 01:43:09.397546: step: 892/533, loss: 0.14260028302669525
2023-01-23 01:43:10.575094: step: 896/533, loss: 0.019707489758729935
2023-01-23 01:43:11.735415: step: 900/533, loss: 0.002470600651577115
2023-01-23 01:43:12.886718: step: 904/533, loss: 0.05762834846973419
2023-01-23 01:43:14.069481: step: 908/533, loss: 0.17950496077537537
2023-01-23 01:43:15.260514: step: 912/533, loss: 0.03777436912059784
2023-01-23 01:43:16.461614: step: 916/533, loss: 0.05789833515882492
2023-01-23 01:43:17.632354: step: 920/533, loss: 0.033000778406858444
2023-01-23 01:43:18.825126: step: 924/533, loss: 0.016828252002596855
2023-01-23 01:43:20.050060: step: 928/533, loss: 0.0033605576027184725
2023-01-23 01:43:21.219554: step: 932/533, loss: 0.06819181144237518
2023-01-23 01:43:22.378981: step: 936/533, loss: 0.023807812482118607
2023-01-23 01:43:23.589769: step: 940/533, loss: 0.015148640610277653
2023-01-23 01:43:24.735655: step: 944/533, loss: 0.0016361236339434981
2023-01-23 01:43:25.933618: step: 948/533, loss: 0.035016633570194244
2023-01-23 01:43:27.105000: step: 952/533, loss: 0.01717844046652317
2023-01-23 01:43:28.310125: step: 956/533, loss: 0.10387001931667328
2023-01-23 01:43:29.466146: step: 960/533, loss: 0.014607143588364124
2023-01-23 01:43:30.609906: step: 964/533, loss: 0.02431488037109375
2023-01-23 01:43:31.809634: step: 968/533, loss: 0.017378902062773705
2023-01-23 01:43:32.982052: step: 972/533, loss: 0.027135562151670456
2023-01-23 01:43:34.157729: step: 976/533, loss: 0.009358692914247513
2023-01-23 01:43:35.320877: step: 980/533, loss: 0.06468673050403595
2023-01-23 01:43:36.487245: step: 984/533, loss: 0.06808729469776154
2023-01-23 01:43:37.677958: step: 988/533, loss: 0.006745166145265102
2023-01-23 01:43:38.846731: step: 992/533, loss: 0.004541206173598766
2023-01-23 01:43:40.019674: step: 996/533, loss: 0.008391380310058594
2023-01-23 01:43:41.180060: step: 1000/533, loss: 0.03845653682947159
2023-01-23 01:43:42.358557: step: 1004/533, loss: 0.08253125846385956
2023-01-23 01:43:43.531787: step: 1008/533, loss: 0.00016336439875885844
2023-01-23 01:43:44.761073: step: 1012/533, loss: 0.2629735767841339
2023-01-23 01:43:45.907951: step: 1016/533, loss: 0.6583120226860046
2023-01-23 01:43:47.095972: step: 1020/533, loss: 0.005272984504699707
2023-01-23 01:43:48.267746: step: 1024/533, loss: 0.024669364094734192
2023-01-23 01:43:49.521583: step: 1028/533, loss: 0.20830345153808594
2023-01-23 01:43:50.686045: step: 1032/533, loss: 0.009858131408691406
2023-01-23 01:43:51.842808: step: 1036/533, loss: 0.02657509036362171
2023-01-23 01:43:53.016367: step: 1040/533, loss: 0.018193816766142845
2023-01-23 01:43:54.156287: step: 1044/533, loss: 0.010870719328522682
2023-01-23 01:43:55.331357: step: 1048/533, loss: 0.0379091277718544
2023-01-23 01:43:56.466375: step: 1052/533, loss: 0.013233566656708717
2023-01-23 01:43:57.630128: step: 1056/533, loss: 0.04811582341790199
2023-01-23 01:43:58.789616: step: 1060/533, loss: 0.021058082580566406
2023-01-23 01:44:00.005012: step: 1064/533, loss: 0.0037311555352061987
2023-01-23 01:44:01.149291: step: 1068/533, loss: 0.03063049539923668
2023-01-23 01:44:02.301263: step: 1072/533, loss: 0.016056345775723457
2023-01-23 01:44:03.485419: step: 1076/533, loss: 0.01564941555261612
2023-01-23 01:44:04.717465: step: 1080/533, loss: 0.10672007501125336
2023-01-23 01:44:05.893256: step: 1084/533, loss: 0.03578929975628853
2023-01-23 01:44:07.085952: step: 1088/533, loss: 0.0438106544315815
2023-01-23 01:44:08.270408: step: 1092/533, loss: 0.021296977996826172
2023-01-23 01:44:09.505517: step: 1096/533, loss: 0.008884811773896217
2023-01-23 01:44:10.687064: step: 1100/533, loss: 0.07901906967163086
2023-01-23 01:44:11.845518: step: 1104/533, loss: 0.1819925308227539
2023-01-23 01:44:13.004557: step: 1108/533, loss: 0.029536008834838867
2023-01-23 01:44:14.203286: step: 1112/533, loss: 0.016701603308320045
2023-01-23 01:44:15.387693: step: 1116/533, loss: 0.0659646987915039
2023-01-23 01:44:16.551899: step: 1120/533, loss: 0.02088022232055664
2023-01-23 01:44:17.749991: step: 1124/533, loss: 0.013384056277573109
2023-01-23 01:44:18.899174: step: 1128/533, loss: 0.017646025866270065
2023-01-23 01:44:20.051614: step: 1132/533, loss: 0.046300508081912994
2023-01-23 01:44:21.178644: step: 1136/533, loss: 0.05372676998376846
2023-01-23 01:44:22.371519: step: 1140/533, loss: 0.02361116372048855
2023-01-23 01:44:23.556997: step: 1144/533, loss: 0.01811380498111248
2023-01-23 01:44:24.725483: step: 1148/533, loss: 0.0357694998383522
2023-01-23 01:44:25.888898: step: 1152/533, loss: 0.026819705963134766
2023-01-23 01:44:27.064605: step: 1156/533, loss: 0.07977437973022461
2023-01-23 01:44:28.236533: step: 1160/533, loss: 0.02685832977294922
2023-01-23 01:44:29.391989: step: 1164/533, loss: 0.004259300418198109
2023-01-23 01:44:30.551935: step: 1168/533, loss: 0.014326381497085094
2023-01-23 01:44:31.704562: step: 1172/533, loss: 0.06263842433691025
2023-01-23 01:44:32.870947: step: 1176/533, loss: 0.0031723796855658293
2023-01-23 01:44:34.023361: step: 1180/533, loss: 0.04707822948694229
2023-01-23 01:44:35.171777: step: 1184/533, loss: 0.007716464810073376
2023-01-23 01:44:36.343652: step: 1188/533, loss: 0.018033696338534355
2023-01-23 01:44:37.509559: step: 1192/533, loss: 0.15719851851463318
2023-01-23 01:44:38.681666: step: 1196/533, loss: 0.0605626106262207
2023-01-23 01:44:39.850403: step: 1200/533, loss: 0.007368660066276789
2023-01-23 01:44:41.028497: step: 1204/533, loss: 0.06865191459655762
2023-01-23 01:44:42.188656: step: 1208/533, loss: 0.035880088806152344
2023-01-23 01:44:43.390441: step: 1212/533, loss: 0.003882694523781538
2023-01-23 01:44:44.577093: step: 1216/533, loss: 0.049204446375370026
2023-01-23 01:44:45.739902: step: 1220/533, loss: 0.014983702450990677
2023-01-23 01:44:46.913303: step: 1224/533, loss: 0.06709900498390198
2023-01-23 01:44:48.127138: step: 1228/533, loss: 0.11667509377002716
2023-01-23 01:44:49.281740: step: 1232/533, loss: 0.028460979461669922
2023-01-23 01:44:50.468801: step: 1236/533, loss: 0.02120800130069256
2023-01-23 01:44:51.664857: step: 1240/533, loss: 0.034026432782411575
2023-01-23 01:44:52.827804: step: 1244/533, loss: 0.06484775245189667
2023-01-23 01:44:54.049464: step: 1248/533, loss: 0.06524619460105896
2023-01-23 01:44:55.204765: step: 1252/533, loss: 0.05959830433130264
2023-01-23 01:44:56.379053: step: 1256/533, loss: 0.04763012006878853
2023-01-23 01:44:57.525508: step: 1260/533, loss: 0.10088081657886505
2023-01-23 01:44:58.681166: step: 1264/533, loss: 0.03941183164715767
2023-01-23 01:44:59.828872: step: 1268/533, loss: 0.019593000411987305
2023-01-23 01:45:01.031159: step: 1272/533, loss: 0.165852352976799
2023-01-23 01:45:02.216702: step: 1276/533, loss: 0.13181647658348083
2023-01-23 01:45:03.420951: step: 1280/533, loss: 0.06385259330272675
2023-01-23 01:45:04.633206: step: 1284/533, loss: 0.14597482979297638
2023-01-23 01:45:05.814946: step: 1288/533, loss: 0.07788078486919403
2023-01-23 01:45:06.983005: step: 1292/533, loss: 0.05867443233728409
2023-01-23 01:45:08.141240: step: 1296/533, loss: 0.017969608306884766
2023-01-23 01:45:09.337185: step: 1300/533, loss: 0.09136438369750977
2023-01-23 01:45:10.530060: step: 1304/533, loss: 0.0328548438847065
2023-01-23 01:45:11.655433: step: 1308/533, loss: 0.04424486309289932
2023-01-23 01:45:12.818344: step: 1312/533, loss: 0.0019918440375477076
2023-01-23 01:45:13.994923: step: 1316/533, loss: 0.007418251130729914
2023-01-23 01:45:15.196740: step: 1320/533, loss: 0.03332176059484482
2023-01-23 01:45:16.367498: step: 1324/533, loss: 0.009627675637602806
2023-01-23 01:45:17.600306: step: 1328/533, loss: 0.08733449131250381
2023-01-23 01:45:18.781235: step: 1332/533, loss: 0.04447555914521217
2023-01-23 01:45:19.941129: step: 1336/533, loss: 0.06751923263072968
2023-01-23 01:45:21.131729: step: 1340/533, loss: 0.032973192632198334
2023-01-23 01:45:22.306412: step: 1344/533, loss: 0.005038452334702015
2023-01-23 01:45:23.468278: step: 1348/533, loss: 0.004536533262580633
2023-01-23 01:45:24.620468: step: 1352/533, loss: 0.058122068643569946
2023-01-23 01:45:25.824246: step: 1356/533, loss: 0.012687254697084427
2023-01-23 01:45:26.992956: step: 1360/533, loss: 0.00492329616099596
2023-01-23 01:45:28.150766: step: 1364/533, loss: 0.09077616035938263
2023-01-23 01:45:29.352699: step: 1368/533, loss: 0.005219841375946999
2023-01-23 01:45:30.518481: step: 1372/533, loss: 0.028905438259243965
2023-01-23 01:45:31.693372: step: 1376/533, loss: 0.009671163745224476
2023-01-23 01:45:32.868103: step: 1380/533, loss: 0.002448535058647394
2023-01-23 01:45:34.031013: step: 1384/533, loss: 0.13827520608901978
2023-01-23 01:45:35.234093: step: 1388/533, loss: 0.6082713007926941
2023-01-23 01:45:36.426775: step: 1392/533, loss: 0.0005320549244061112
2023-01-23 01:45:37.629234: step: 1396/533, loss: 0.032445717602968216
2023-01-23 01:45:38.798066: step: 1400/533, loss: 0.019359493628144264
2023-01-23 01:45:39.971980: step: 1404/533, loss: 0.05150227248668671
2023-01-23 01:45:41.154093: step: 1408/533, loss: 0.3610328733921051
2023-01-23 01:45:42.359093: step: 1412/533, loss: 0.17799559235572815
2023-01-23 01:45:43.571254: step: 1416/533, loss: 0.017168521881103516
2023-01-23 01:45:44.772215: step: 1420/533, loss: 0.201358363032341
2023-01-23 01:45:45.956776: step: 1424/533, loss: 0.06886868178844452
2023-01-23 01:45:47.118312: step: 1428/533, loss: 0.16228222846984863
2023-01-23 01:45:48.330857: step: 1432/533, loss: 0.021047307178378105
2023-01-23 01:45:49.505525: step: 1436/533, loss: 0.10263442993164062
2023-01-23 01:45:50.681774: step: 1440/533, loss: 0.2091541290283203
2023-01-23 01:45:51.823644: step: 1444/533, loss: 0.09670257568359375
2023-01-23 01:45:52.978636: step: 1448/533, loss: 0.052000902593135834
2023-01-23 01:45:54.129298: step: 1452/533, loss: 0.06897849589586258
2023-01-23 01:45:55.302245: step: 1456/533, loss: 0.00041856765164993703
2023-01-23 01:45:56.441616: step: 1460/533, loss: 0.03280916064977646
2023-01-23 01:45:57.598215: step: 1464/533, loss: 0.013363933190703392
2023-01-23 01:45:58.775061: step: 1468/533, loss: 0.09364490956068039
2023-01-23 01:45:59.948299: step: 1472/533, loss: 0.01431436650454998
2023-01-23 01:46:01.146731: step: 1476/533, loss: 0.005146122071892023
2023-01-23 01:46:02.329306: step: 1480/533, loss: 0.060553837567567825
2023-01-23 01:46:03.592297: step: 1484/533, loss: 0.30208471417427063
2023-01-23 01:46:04.742598: step: 1488/533, loss: 0.10384144634008408
2023-01-23 01:46:05.912970: step: 1492/533, loss: 0.03745314106345177
2023-01-23 01:46:07.089554: step: 1496/533, loss: 0.02348005771636963
2023-01-23 01:46:08.254961: step: 1500/533, loss: 0.008070326410233974
2023-01-23 01:46:09.399913: step: 1504/533, loss: 0.045976921916007996
2023-01-23 01:46:10.522620: step: 1508/533, loss: 0.06866731494665146
2023-01-23 01:46:11.735225: step: 1512/533, loss: 0.060430336743593216
2023-01-23 01:46:12.915536: step: 1516/533, loss: 0.04514675214886665
2023-01-23 01:46:14.142931: step: 1520/533, loss: 0.040711406618356705
2023-01-23 01:46:15.307221: step: 1524/533, loss: 0.01841134950518608
2023-01-23 01:46:16.481414: step: 1528/533, loss: 0.018446827307343483
2023-01-23 01:46:17.646390: step: 1532/533, loss: 0.01768198050558567
2023-01-23 01:46:18.840900: step: 1536/533, loss: 0.14561490714550018
2023-01-23 01:46:20.045805: step: 1540/533, loss: 0.01342697162181139
2023-01-23 01:46:21.217806: step: 1544/533, loss: 0.033490944653749466
2023-01-23 01:46:22.411968: step: 1548/533, loss: 0.02055206336081028
2023-01-23 01:46:23.553274: step: 1552/533, loss: 0.034474849700927734
2023-01-23 01:46:24.728993: step: 1556/533, loss: 0.07722511142492294
2023-01-23 01:46:25.906677: step: 1560/533, loss: 0.0552278533577919
2023-01-23 01:46:27.091653: step: 1564/533, loss: 0.06279754638671875
2023-01-23 01:46:28.240585: step: 1568/533, loss: 0.0029401779174804688
2023-01-23 01:46:29.404312: step: 1572/533, loss: 0.026673031970858574
2023-01-23 01:46:30.595917: step: 1576/533, loss: 0.05111350864171982
2023-01-23 01:46:31.801228: step: 1580/533, loss: 0.04513407498598099
2023-01-23 01:46:32.998435: step: 1584/533, loss: 0.018364334478974342
2023-01-23 01:46:34.205935: step: 1588/533, loss: 0.007852268405258656
2023-01-23 01:46:35.408359: step: 1592/533, loss: 0.1326128989458084
2023-01-23 01:46:36.584639: step: 1596/533, loss: 0.11506939679384232
2023-01-23 01:46:37.732141: step: 1600/533, loss: 0.07705860584974289
2023-01-23 01:46:38.896183: step: 1604/533, loss: 0.45621684193611145
2023-01-23 01:46:40.052823: step: 1608/533, loss: 0.05713510513305664
2023-01-23 01:46:41.246504: step: 1612/533, loss: 0.08268871158361435
2023-01-23 01:46:42.405547: step: 1616/533, loss: 0.010688400827348232
2023-01-23 01:46:43.570762: step: 1620/533, loss: 0.05480222776532173
2023-01-23 01:46:44.750014: step: 1624/533, loss: 0.006007385440170765
2023-01-23 01:46:45.903351: step: 1628/533, loss: 0.014450264163315296
2023-01-23 01:46:47.114905: step: 1632/533, loss: 0.08145341277122498
2023-01-23 01:46:48.301622: step: 1636/533, loss: 0.05900127440690994
2023-01-23 01:46:49.459885: step: 1640/533, loss: 0.0033389092423021793
2023-01-23 01:46:50.621839: step: 1644/533, loss: 0.043526653200387955
2023-01-23 01:46:51.775182: step: 1648/533, loss: 0.017824554815888405
2023-01-23 01:46:52.933186: step: 1652/533, loss: 0.04410190507769585
2023-01-23 01:46:54.070835: step: 1656/533, loss: 0.039089299738407135
2023-01-23 01:46:55.275947: step: 1660/533, loss: 0.7259637117385864
2023-01-23 01:46:56.462212: step: 1664/533, loss: 0.2234129011631012
2023-01-23 01:46:57.614343: step: 1668/533, loss: 0.057437799870967865
2023-01-23 01:46:58.807914: step: 1672/533, loss: 0.07039479911327362
2023-01-23 01:46:59.985073: step: 1676/533, loss: 0.00327472691424191
2023-01-23 01:47:01.235727: step: 1680/533, loss: 0.05289306864142418
2023-01-23 01:47:02.376283: step: 1684/533, loss: 0.019138097763061523
2023-01-23 01:47:03.561282: step: 1688/533, loss: 0.02441711537539959
2023-01-23 01:47:04.725808: step: 1692/533, loss: 0.028813552111387253
2023-01-23 01:47:05.864981: step: 1696/533, loss: 0.024274826049804688
2023-01-23 01:47:07.057726: step: 1700/533, loss: 0.03939366713166237
2023-01-23 01:47:08.217684: step: 1704/533, loss: 0.013880109414458275
2023-01-23 01:47:09.379662: step: 1708/533, loss: 0.018095040693879128
2023-01-23 01:47:10.537662: step: 1712/533, loss: 0.034016892313957214
2023-01-23 01:47:11.699273: step: 1716/533, loss: 0.027688028290867805
2023-01-23 01:47:12.864856: step: 1720/533, loss: 0.03873515501618385
2023-01-23 01:47:13.994186: step: 1724/533, loss: 0.049902867525815964
2023-01-23 01:47:15.221623: step: 1728/533, loss: 0.06859683990478516
2023-01-23 01:47:16.404909: step: 1732/533, loss: 0.029404640197753906
2023-01-23 01:47:17.564121: step: 1736/533, loss: 0.04838988929986954
2023-01-23 01:47:18.764344: step: 1740/533, loss: 0.06674300134181976
2023-01-23 01:47:19.921238: step: 1744/533, loss: 0.025876617059111595
2023-01-23 01:47:21.094310: step: 1748/533, loss: 0.0449770912528038
2023-01-23 01:47:22.257796: step: 1752/533, loss: 0.015346718020737171
2023-01-23 01:47:23.433907: step: 1756/533, loss: 0.10980740189552307
2023-01-23 01:47:24.588586: step: 1760/533, loss: 0.05595569685101509
2023-01-23 01:47:25.755730: step: 1764/533, loss: 0.05331411212682724
2023-01-23 01:47:26.930945: step: 1768/533, loss: 0.08244156837463379
2023-01-23 01:47:28.109070: step: 1772/533, loss: 0.06902127712965012
2023-01-23 01:47:29.248527: step: 1776/533, loss: 0.043268442153930664
2023-01-23 01:47:30.448113: step: 1780/533, loss: 0.07462511211633682
2023-01-23 01:47:31.628843: step: 1784/533, loss: 0.009383583441376686
2023-01-23 01:47:32.805509: step: 1788/533, loss: 0.11410693824291229
2023-01-23 01:47:34.020796: step: 1792/533, loss: 0.02843337133526802
2023-01-23 01:47:35.184273: step: 1796/533, loss: 0.03494281694293022
2023-01-23 01:47:36.397533: step: 1800/533, loss: 0.002321624895557761
2023-01-23 01:47:37.565985: step: 1804/533, loss: 0.03250131756067276
2023-01-23 01:47:38.727333: step: 1808/533, loss: 0.020795442163944244
2023-01-23 01:47:39.978369: step: 1812/533, loss: 0.02325439453125
2023-01-23 01:47:41.177915: step: 1816/533, loss: 0.006741237826645374
2023-01-23 01:47:42.357025: step: 1820/533, loss: 0.1205529272556305
2023-01-23 01:47:43.558469: step: 1824/533, loss: 0.11564426124095917
2023-01-23 01:47:44.735543: step: 1828/533, loss: 0.30382683873176575
2023-01-23 01:47:45.918237: step: 1832/533, loss: 0.056415751576423645
2023-01-23 01:47:47.067762: step: 1836/533, loss: 0.10739608108997345
2023-01-23 01:47:48.262321: step: 1840/533, loss: 0.0007989883306436241
2023-01-23 01:47:49.436989: step: 1844/533, loss: 0.02347707748413086
2023-01-23 01:47:50.606578: step: 1848/533, loss: 0.01653442531824112
2023-01-23 01:47:51.771795: step: 1852/533, loss: 0.07408218830823898
2023-01-23 01:47:52.883808: step: 1856/533, loss: 0.027668381109833717
2023-01-23 01:47:54.075236: step: 1860/533, loss: 0.15898758172988892
2023-01-23 01:47:55.216809: step: 1864/533, loss: 0.4568532109260559
2023-01-23 01:47:56.418291: step: 1868/533, loss: 0.00966711062937975
2023-01-23 01:47:57.584060: step: 1872/533, loss: 0.0014947891468182206
2023-01-23 01:47:58.732240: step: 1876/533, loss: 0.004918289370834827
2023-01-23 01:47:59.888561: step: 1880/533, loss: 0.04282064363360405
2023-01-23 01:48:01.047825: step: 1884/533, loss: 0.1184360459446907
2023-01-23 01:48:02.207801: step: 1888/533, loss: 0.3993797302246094
2023-01-23 01:48:03.357166: step: 1892/533, loss: 1.2934364080429077
2023-01-23 01:48:04.560087: step: 1896/533, loss: 0.09910546243190765
2023-01-23 01:48:05.715645: step: 1900/533, loss: 0.009246539324522018
2023-01-23 01:48:06.915938: step: 1904/533, loss: 0.08051595836877823
2023-01-23 01:48:08.070150: step: 1908/533, loss: 0.004052114672958851
2023-01-23 01:48:09.237533: step: 1912/533, loss: 0.006758785340934992
2023-01-23 01:48:10.410910: step: 1916/533, loss: 0.03931179270148277
2023-01-23 01:48:11.557403: step: 1920/533, loss: 0.07021927833557129
2023-01-23 01:48:12.717802: step: 1924/533, loss: 0.05391426384449005
2023-01-23 01:48:13.877714: step: 1928/533, loss: 0.020174002274870872
2023-01-23 01:48:15.053780: step: 1932/533, loss: 0.21702241897583008
2023-01-23 01:48:16.247168: step: 1936/533, loss: 0.0025521754287183285
2023-01-23 01:48:17.436266: step: 1940/533, loss: 0.04597644880414009
2023-01-23 01:48:18.635961: step: 1944/533, loss: 0.028826426714658737
2023-01-23 01:48:19.818110: step: 1948/533, loss: 0.022482728585600853
2023-01-23 01:48:20.993977: step: 1952/533, loss: 0.03686704859137535
2023-01-23 01:48:22.214793: step: 1956/533, loss: 0.05378265678882599
2023-01-23 01:48:23.352290: step: 1960/533, loss: 0.003544426057487726
2023-01-23 01:48:24.570911: step: 1964/533, loss: 0.10948581993579865
2023-01-23 01:48:25.778836: step: 1968/533, loss: 0.037540435791015625
2023-01-23 01:48:26.939947: step: 1972/533, loss: 0.0022695541847497225
2023-01-23 01:48:28.101355: step: 1976/533, loss: 0.056593991816043854
2023-01-23 01:48:29.277508: step: 1980/533, loss: 0.050704099237918854
2023-01-23 01:48:30.467719: step: 1984/533, loss: 0.033888839185237885
2023-01-23 01:48:31.629352: step: 1988/533, loss: 0.003427839372307062
2023-01-23 01:48:32.821936: step: 1992/533, loss: 0.035056211054325104
2023-01-23 01:48:33.984705: step: 1996/533, loss: 0.025683116167783737
2023-01-23 01:48:35.152174: step: 2000/533, loss: 0.049903109669685364
2023-01-23 01:48:36.336346: step: 2004/533, loss: 0.024570655077695847
2023-01-23 01:48:37.593871: step: 2008/533, loss: 0.05321057140827179
2023-01-23 01:48:38.777814: step: 2012/533, loss: 0.05623655766248703
2023-01-23 01:48:39.974871: step: 2016/533, loss: 0.03146815299987793
2023-01-23 01:48:41.145127: step: 2020/533, loss: 0.07843560725450516
2023-01-23 01:48:42.337784: step: 2024/533, loss: 0.0027111531235277653
2023-01-23 01:48:43.554684: step: 2028/533, loss: 0.004670906346291304
2023-01-23 01:48:44.710329: step: 2032/533, loss: 0.09960909187793732
2023-01-23 01:48:45.869300: step: 2036/533, loss: 0.4701419472694397
2023-01-23 01:48:47.106789: step: 2040/533, loss: 0.04217939451336861
2023-01-23 01:48:48.299875: step: 2044/533, loss: 0.08248773217201233
2023-01-23 01:48:49.517837: step: 2048/533, loss: 0.05019540712237358
2023-01-23 01:48:50.662802: step: 2052/533, loss: 0.030640697106719017
2023-01-23 01:48:51.826418: step: 2056/533, loss: 0.02095479890704155
2023-01-23 01:48:52.992443: step: 2060/533, loss: 0.02147965505719185
2023-01-23 01:48:54.200361: step: 2064/533, loss: 0.01578063890337944
2023-01-23 01:48:55.396703: step: 2068/533, loss: 0.04016117751598358
2023-01-23 01:48:56.562222: step: 2072/533, loss: 0.08902301639318466
2023-01-23 01:48:57.722618: step: 2076/533, loss: 0.033548880368471146
2023-01-23 01:48:58.887832: step: 2080/533, loss: 0.08504059165716171
2023-01-23 01:49:00.080727: step: 2084/533, loss: 0.06880378723144531
2023-01-23 01:49:01.268409: step: 2088/533, loss: 0.09760390222072601
2023-01-23 01:49:02.444632: step: 2092/533, loss: 0.019560767337679863
2023-01-23 01:49:03.587667: step: 2096/533, loss: 1.6983377933502197
2023-01-23 01:49:04.758040: step: 2100/533, loss: 0.046353720128536224
2023-01-23 01:49:05.902855: step: 2104/533, loss: 0.03412804752588272
2023-01-23 01:49:07.050019: step: 2108/533, loss: 0.0052394866943359375
2023-01-23 01:49:08.206222: step: 2112/533, loss: 0.05005950853228569
2023-01-23 01:49:09.397379: step: 2116/533, loss: 0.023495342582464218
2023-01-23 01:49:10.549049: step: 2120/533, loss: 0.015263080596923828
2023-01-23 01:49:11.731416: step: 2124/533, loss: 0.03577251732349396
2023-01-23 01:49:12.886897: step: 2128/533, loss: 0.28675755858421326
2023-01-23 01:49:14.049170: step: 2132/533, loss: 0.028914406895637512
==================================================
Loss: 0.064
--------------------
Dev: {'event': {'p': 0.5838206627680312, 'r': 0.7976031957390146, 'f1': 0.6741699493528419}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6255506607929515, 'r': 0.8171355498721228, 'f1': 0.7086221236484613}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5813953488372093, 'r': 0.9259259259259259, 'f1': 0.7142857142857142}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.5901639344262295, 'r': 0.5714285714285714, 'f1': 0.5806451612903226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.4090909090909091, 'r': 0.5, 'f1': 0.45}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:49:55.622085: step: 4/533, loss: 0.02113480493426323
2023-01-23 01:49:56.798117: step: 8/533, loss: 0.2180517166852951
2023-01-23 01:49:57.964582: step: 12/533, loss: 0.04204254224896431
2023-01-23 01:49:59.158276: step: 16/533, loss: 0.05729112774133682
2023-01-23 01:50:00.311898: step: 20/533, loss: 0.011809063144028187
2023-01-23 01:50:01.470773: step: 24/533, loss: 0.09803657233715057
2023-01-23 01:50:02.692688: step: 28/533, loss: 0.005874681286513805
2023-01-23 01:50:03.828044: step: 32/533, loss: 0.03490648418664932
2023-01-23 01:50:05.042282: step: 36/533, loss: 0.022076226770877838
2023-01-23 01:50:06.206790: step: 40/533, loss: 0.04399728775024414
2023-01-23 01:50:07.355087: step: 44/533, loss: 0.0050290110521018505
2023-01-23 01:50:08.573333: step: 48/533, loss: 0.13323011994361877
2023-01-23 01:50:09.740460: step: 52/533, loss: 0.010277272202074528
2023-01-23 01:50:10.927020: step: 56/533, loss: 0.03768301010131836
2023-01-23 01:50:12.079081: step: 60/533, loss: 0.04535641893744469
2023-01-23 01:50:13.282429: step: 64/533, loss: 0.009997940622270107
2023-01-23 01:50:14.479513: step: 68/533, loss: 0.015745162963867188
2023-01-23 01:50:15.664761: step: 72/533, loss: 0.08374081552028656
2023-01-23 01:50:16.830757: step: 76/533, loss: 0.07598571479320526
2023-01-23 01:50:18.004016: step: 80/533, loss: 0.002165889833122492
2023-01-23 01:50:19.190543: step: 84/533, loss: 0.34626901149749756
2023-01-23 01:50:20.362212: step: 88/533, loss: 0.01954049989581108
2023-01-23 01:50:21.526968: step: 92/533, loss: 0.0006309509044513106
2023-01-23 01:50:22.670940: step: 96/533, loss: 0.011398744769394398
2023-01-23 01:50:23.886519: step: 100/533, loss: 0.053518008440732956
2023-01-23 01:50:25.080707: step: 104/533, loss: 0.0004321098676882684
2023-01-23 01:50:26.249605: step: 108/533, loss: 0.0034241201356053352
2023-01-23 01:50:27.452227: step: 112/533, loss: 0.014015293680131435
2023-01-23 01:50:28.592137: step: 116/533, loss: 0.03946514055132866
2023-01-23 01:50:29.744598: step: 120/533, loss: 0.0601312629878521
2023-01-23 01:50:30.914978: step: 124/533, loss: 0.012287044897675514
2023-01-23 01:50:32.094193: step: 128/533, loss: 0.10448139160871506
2023-01-23 01:50:33.254506: step: 132/533, loss: 0.05132708698511124
2023-01-23 01:50:34.401246: step: 136/533, loss: 0.027512740343809128
2023-01-23 01:50:35.660373: step: 140/533, loss: 0.041411686688661575
2023-01-23 01:50:36.814865: step: 144/533, loss: 0.00450897216796875
2023-01-23 01:50:38.035397: step: 148/533, loss: 0.018312646076083183
2023-01-23 01:50:39.204962: step: 152/533, loss: 0.08904209733009338
2023-01-23 01:50:40.356282: step: 156/533, loss: 0.00920324306935072
2023-01-23 01:50:41.554801: step: 160/533, loss: 0.01207885704934597
2023-01-23 01:50:42.748967: step: 164/533, loss: 0.029880523681640625
2023-01-23 01:50:43.954752: step: 168/533, loss: 0.011577606201171875
2023-01-23 01:50:45.154495: step: 172/533, loss: 0.12033109366893768
2023-01-23 01:50:46.330292: step: 176/533, loss: 0.049056150019168854
2023-01-23 01:50:47.491957: step: 180/533, loss: 0.09324140846729279
2023-01-23 01:50:48.663333: step: 184/533, loss: 0.04524211958050728
2023-01-23 01:50:49.853761: step: 188/533, loss: 0.006444644648581743
2023-01-23 01:50:51.056983: step: 192/533, loss: 0.04369932785630226
2023-01-23 01:50:52.235489: step: 196/533, loss: 0.021640397608280182
2023-01-23 01:50:53.433268: step: 200/533, loss: 0.08095663785934448
2023-01-23 01:50:54.637529: step: 204/533, loss: 0.0007752418168820441
2023-01-23 01:50:55.798838: step: 208/533, loss: 0.019136715680360794
2023-01-23 01:50:57.012111: step: 212/533, loss: 0.06638136506080627
2023-01-23 01:50:58.214882: step: 216/533, loss: 0.041887760162353516
2023-01-23 01:50:59.380281: step: 220/533, loss: 0.0011137962574139237
2023-01-23 01:51:00.541679: step: 224/533, loss: 0.05277423933148384
2023-01-23 01:51:01.731877: step: 228/533, loss: 0.014643478207290173
2023-01-23 01:51:02.897302: step: 232/533, loss: 0.00011196137347724289
2023-01-23 01:51:04.084953: step: 236/533, loss: 0.02535724639892578
2023-01-23 01:51:05.266731: step: 240/533, loss: 0.014371919445693493
2023-01-23 01:51:06.430614: step: 244/533, loss: 0.01745319366455078
2023-01-23 01:51:07.627373: step: 248/533, loss: 0.04930629953742027
2023-01-23 01:51:08.829736: step: 252/533, loss: 0.04411773756146431
2023-01-23 01:51:09.983652: step: 256/533, loss: 0.05849814414978027
2023-01-23 01:51:11.182673: step: 260/533, loss: 0.063349150121212
2023-01-23 01:51:12.354673: step: 264/533, loss: 0.02587909810245037
2023-01-23 01:51:13.544099: step: 268/533, loss: 0.000789642333984375
2023-01-23 01:51:14.701175: step: 272/533, loss: 0.0025743008591234684
2023-01-23 01:51:15.859805: step: 276/533, loss: 0.04830064997076988
2023-01-23 01:51:17.059253: step: 280/533, loss: 0.13837222754955292
2023-01-23 01:51:18.219694: step: 284/533, loss: 0.027942851185798645
2023-01-23 01:51:19.395210: step: 288/533, loss: 0.0027311325538903475
2023-01-23 01:51:20.587134: step: 292/533, loss: 0.03370227664709091
2023-01-23 01:51:21.772154: step: 296/533, loss: 0.09649143368005753
2023-01-23 01:51:22.918843: step: 300/533, loss: 0.03746652230620384
2023-01-23 01:51:24.106564: step: 304/533, loss: 0.0020686150528490543
2023-01-23 01:51:25.283544: step: 308/533, loss: 0.03869514539837837
2023-01-23 01:51:26.390528: step: 312/533, loss: 0.04442758858203888
2023-01-23 01:51:27.618665: step: 316/533, loss: 0.011024285107851028
2023-01-23 01:51:28.750344: step: 320/533, loss: 0.04921398311853409
2023-01-23 01:51:29.887907: step: 324/533, loss: 0.007674884516745806
2023-01-23 01:51:31.093467: step: 328/533, loss: 0.05484924465417862
2023-01-23 01:51:32.246317: step: 332/533, loss: 0.005054187960922718
2023-01-23 01:51:33.377055: step: 336/533, loss: 0.0066925049759447575
2023-01-23 01:51:34.599748: step: 340/533, loss: 0.30472761392593384
2023-01-23 01:51:35.786403: step: 344/533, loss: 0.06115546450018883
2023-01-23 01:51:36.932176: step: 348/533, loss: 0.0355132594704628
2023-01-23 01:51:38.100239: step: 352/533, loss: 0.0890776664018631
2023-01-23 01:51:39.278240: step: 356/533, loss: 0.04704098775982857
2023-01-23 01:51:40.481888: step: 360/533, loss: 0.04420604556798935
2023-01-23 01:51:41.668429: step: 364/533, loss: 0.019759131595492363
2023-01-23 01:51:42.841152: step: 368/533, loss: 0.021140575408935547
2023-01-23 01:51:43.976869: step: 372/533, loss: 0.006780624855309725
2023-01-23 01:51:45.148049: step: 376/533, loss: 0.003692054655402899
2023-01-23 01:51:46.300092: step: 380/533, loss: 0.00440139789134264
2023-01-23 01:51:47.470932: step: 384/533, loss: 0.07288307696580887
2023-01-23 01:51:48.624022: step: 388/533, loss: 0.010738945566117764
2023-01-23 01:51:49.775748: step: 392/533, loss: 0.027880383655428886
2023-01-23 01:51:50.950650: step: 396/533, loss: 0.05134258419275284
2023-01-23 01:51:52.131928: step: 400/533, loss: 0.0022987842094153166
2023-01-23 01:51:53.274717: step: 404/533, loss: 0.005730914883315563
2023-01-23 01:51:54.487798: step: 408/533, loss: 0.07759633660316467
2023-01-23 01:51:55.696141: step: 412/533, loss: 0.005066728685051203
2023-01-23 01:51:56.879087: step: 416/533, loss: 0.020241450518369675
2023-01-23 01:51:58.102261: step: 420/533, loss: 0.02721252292394638
2023-01-23 01:51:59.326270: step: 424/533, loss: 0.020453788340091705
2023-01-23 01:52:00.467172: step: 428/533, loss: 0.029588891193270683
2023-01-23 01:52:01.633669: step: 432/533, loss: 0.0313752181828022
2023-01-23 01:52:02.810840: step: 436/533, loss: 0.025255393236875534
2023-01-23 01:52:04.069397: step: 440/533, loss: 0.22620391845703125
2023-01-23 01:52:05.215405: step: 444/533, loss: 0.001817131182178855
2023-01-23 01:52:06.376799: step: 448/533, loss: 0.033921051770448685
2023-01-23 01:52:07.531578: step: 452/533, loss: 0.700085461139679
2023-01-23 01:52:08.691621: step: 456/533, loss: 0.02322845533490181
2023-01-23 01:52:09.868504: step: 460/533, loss: 0.05259857326745987
2023-01-23 01:52:11.043777: step: 464/533, loss: 0.08695525676012039
2023-01-23 01:52:12.229422: step: 468/533, loss: 0.0037970542907714844
2023-01-23 01:52:13.423228: step: 472/533, loss: 0.018614768981933594
2023-01-23 01:52:14.601660: step: 476/533, loss: 0.08401613682508469
2023-01-23 01:52:15.798428: step: 480/533, loss: 0.00024237632169388235
2023-01-23 01:52:16.983788: step: 484/533, loss: 0.07679080963134766
2023-01-23 01:52:18.164075: step: 488/533, loss: 0.05887727811932564
2023-01-23 01:52:19.357362: step: 492/533, loss: 0.01378641091287136
2023-01-23 01:52:20.513571: step: 496/533, loss: 0.03404855728149414
2023-01-23 01:52:21.651331: step: 500/533, loss: 0.008977937512099743
2023-01-23 01:52:22.809390: step: 504/533, loss: 0.054403115063905716
2023-01-23 01:52:23.974898: step: 508/533, loss: 0.049040794372558594
2023-01-23 01:52:25.178935: step: 512/533, loss: 0.12543697655200958
2023-01-23 01:52:26.375168: step: 516/533, loss: 0.0028532028663903475
2023-01-23 01:52:27.503062: step: 520/533, loss: 0.04877519607543945
2023-01-23 01:52:28.680188: step: 524/533, loss: 0.020182037726044655
2023-01-23 01:52:29.807623: step: 528/533, loss: 0.038889121264219284
2023-01-23 01:52:31.010352: step: 532/533, loss: 0.007474326994270086
2023-01-23 01:52:32.142065: step: 536/533, loss: 0.0029264481272548437
2023-01-23 01:52:33.346404: step: 540/533, loss: 0.013007258996367455
2023-01-23 01:52:34.530026: step: 544/533, loss: 0.03889331966638565
2023-01-23 01:52:35.687797: step: 548/533, loss: 0.010523987002670765
2023-01-23 01:52:36.883924: step: 552/533, loss: 0.045534897595644
2023-01-23 01:52:38.077371: step: 556/533, loss: 0.0723661407828331
2023-01-23 01:52:39.279821: step: 560/533, loss: 0.07396040111780167
2023-01-23 01:52:40.427368: step: 564/533, loss: 0.10192445665597916
2023-01-23 01:52:41.577196: step: 568/533, loss: 0.07721743732690811
2023-01-23 01:52:42.767913: step: 572/533, loss: 0.03134002909064293
2023-01-23 01:52:43.930023: step: 576/533, loss: 0.004663276951760054
2023-01-23 01:52:45.127669: step: 580/533, loss: 0.07088317722082138
2023-01-23 01:52:46.343438: step: 584/533, loss: 0.03112011030316353
2023-01-23 01:52:47.543366: step: 588/533, loss: 0.1224648505449295
2023-01-23 01:52:48.743530: step: 592/533, loss: 0.14820709824562073
2023-01-23 01:52:49.891617: step: 596/533, loss: 0.0059379576705396175
2023-01-23 01:52:51.052455: step: 600/533, loss: 0.01222152728587389
2023-01-23 01:52:52.215607: step: 604/533, loss: 0.033492375165224075
2023-01-23 01:52:53.400563: step: 608/533, loss: 0.020554065704345703
2023-01-23 01:52:54.579462: step: 612/533, loss: 0.004041099455207586
2023-01-23 01:52:55.773691: step: 616/533, loss: 0.025343704968690872
2023-01-23 01:52:56.950283: step: 620/533, loss: 0.11975374817848206
2023-01-23 01:52:58.105616: step: 624/533, loss: 0.06233959645032883
2023-01-23 01:52:59.288993: step: 628/533, loss: 0.019565487280488014
2023-01-23 01:53:00.434544: step: 632/533, loss: 0.015001583844423294
2023-01-23 01:53:01.628958: step: 636/533, loss: 0.1642434149980545
2023-01-23 01:53:02.806713: step: 640/533, loss: 0.028392791748046875
2023-01-23 01:53:03.981770: step: 644/533, loss: 0.04311332851648331
2023-01-23 01:53:05.150850: step: 648/533, loss: 0.006820689886808395
2023-01-23 01:53:06.356023: step: 652/533, loss: 0.021359825506806374
2023-01-23 01:53:07.524311: step: 656/533, loss: 0.039544109255075455
2023-01-23 01:53:08.695272: step: 660/533, loss: 0.00016994477482512593
2023-01-23 01:53:09.869445: step: 664/533, loss: 0.0352630615234375
2023-01-23 01:53:11.056216: step: 668/533, loss: 0.035451509058475494
2023-01-23 01:53:12.256891: step: 672/533, loss: 0.08077006042003632
2023-01-23 01:53:13.465270: step: 676/533, loss: 0.06459636241197586
2023-01-23 01:53:14.637625: step: 680/533, loss: 0.013711739331483841
2023-01-23 01:53:15.798853: step: 684/533, loss: 0.03627767786383629
2023-01-23 01:53:16.949717: step: 688/533, loss: 0.03703594207763672
2023-01-23 01:53:18.100634: step: 692/533, loss: 0.0052512651309370995
2023-01-23 01:53:19.296580: step: 696/533, loss: 0.03257384151220322
2023-01-23 01:53:20.490184: step: 700/533, loss: 0.035390663892030716
2023-01-23 01:53:21.666621: step: 704/533, loss: 0.005215453915297985
2023-01-23 01:53:22.869572: step: 708/533, loss: 0.00872497633099556
2023-01-23 01:53:24.087548: step: 712/533, loss: 0.023395873606204987
2023-01-23 01:53:25.243096: step: 716/533, loss: 0.0072959898971021175
2023-01-23 01:53:26.441716: step: 720/533, loss: 0.029417896643280983
2023-01-23 01:53:27.612106: step: 724/533, loss: 0.03926267474889755
2023-01-23 01:53:28.785164: step: 728/533, loss: 0.01951618120074272
2023-01-23 01:53:29.956190: step: 732/533, loss: 0.00012855530076194555
2023-01-23 01:53:31.089601: step: 736/533, loss: 0.018889330327510834
2023-01-23 01:53:32.317098: step: 740/533, loss: 0.03725109249353409
2023-01-23 01:53:33.451772: step: 744/533, loss: 0.043996550142765045
2023-01-23 01:53:34.635030: step: 748/533, loss: 0.10337982326745987
2023-01-23 01:53:35.775099: step: 752/533, loss: 0.12036962807178497
2023-01-23 01:53:36.962691: step: 756/533, loss: 0.04981708526611328
2023-01-23 01:53:38.154102: step: 760/533, loss: 0.00131816859357059
2023-01-23 01:53:39.381263: step: 764/533, loss: 0.07454271614551544
2023-01-23 01:53:40.591301: step: 768/533, loss: 0.0735284835100174
2023-01-23 01:53:41.763516: step: 772/533, loss: 0.07411356270313263
2023-01-23 01:53:42.957207: step: 776/533, loss: 0.02219703048467636
2023-01-23 01:53:44.136590: step: 780/533, loss: 0.057050369679927826
2023-01-23 01:53:45.302808: step: 784/533, loss: 0.059995558112859726
2023-01-23 01:53:46.494501: step: 788/533, loss: 0.02738466113805771
2023-01-23 01:53:47.684554: step: 792/533, loss: 0.004936409182846546
2023-01-23 01:53:48.878092: step: 796/533, loss: 0.037609003484249115
2023-01-23 01:53:50.032763: step: 800/533, loss: 0.05502338707447052
2023-01-23 01:53:51.206219: step: 804/533, loss: 0.056107472628355026
2023-01-23 01:53:52.405750: step: 808/533, loss: 0.0258181095123291
2023-01-23 01:53:53.579171: step: 812/533, loss: 0.010819625109434128
2023-01-23 01:53:54.742746: step: 816/533, loss: 0.03242502361536026
2023-01-23 01:53:55.914890: step: 820/533, loss: 0.08075661957263947
2023-01-23 01:53:57.066883: step: 824/533, loss: 0.05600786209106445
2023-01-23 01:53:58.263446: step: 828/533, loss: 0.02236041985452175
2023-01-23 01:53:59.413254: step: 832/533, loss: 0.0878625437617302
2023-01-23 01:54:00.607150: step: 836/533, loss: 0.07311764359474182
2023-01-23 01:54:01.835761: step: 840/533, loss: 0.04112996906042099
2023-01-23 01:54:03.015685: step: 844/533, loss: 0.02455897442996502
2023-01-23 01:54:04.189441: step: 848/533, loss: 0.041886892169713974
2023-01-23 01:54:05.355515: step: 852/533, loss: 0.01795930787920952
2023-01-23 01:54:06.520440: step: 856/533, loss: 0.027780722826719284
2023-01-23 01:54:07.699917: step: 860/533, loss: 0.05400047451257706
2023-01-23 01:54:08.902438: step: 864/533, loss: 0.0428224578499794
2023-01-23 01:54:10.074460: step: 868/533, loss: 0.019554710015654564
2023-01-23 01:54:11.288906: step: 872/533, loss: 0.011345005594193935
2023-01-23 01:54:12.469681: step: 876/533, loss: 0.34164875745773315
2023-01-23 01:54:13.644645: step: 880/533, loss: 0.004983139224350452
2023-01-23 01:54:14.817079: step: 884/533, loss: 0.03833484649658203
2023-01-23 01:54:15.966521: step: 888/533, loss: 0.006659126374870539
2023-01-23 01:54:17.128305: step: 892/533, loss: 0.020348072052001953
2023-01-23 01:54:18.322019: step: 896/533, loss: 0.0044612884521484375
2023-01-23 01:54:19.480965: step: 900/533, loss: 0.04254169389605522
2023-01-23 01:54:20.657075: step: 904/533, loss: 0.00836181640625
2023-01-23 01:54:21.847098: step: 908/533, loss: 0.03066062740981579
2023-01-23 01:54:22.981263: step: 912/533, loss: 0.026505853980779648
2023-01-23 01:54:24.167404: step: 916/533, loss: 0.005989265628159046
2023-01-23 01:54:25.367403: step: 920/533, loss: 0.027514267712831497
2023-01-23 01:54:26.537007: step: 924/533, loss: 0.08614940941333771
2023-01-23 01:54:27.734296: step: 928/533, loss: 0.007572269532829523
2023-01-23 01:54:28.889252: step: 932/533, loss: 0.03605690225958824
2023-01-23 01:54:30.024183: step: 936/533, loss: 0.026875877752900124
2023-01-23 01:54:31.189461: step: 940/533, loss: 0.02230405993759632
2023-01-23 01:54:32.336659: step: 944/533, loss: 0.02019815519452095
2023-01-23 01:54:33.519775: step: 948/533, loss: 0.02164745330810547
2023-01-23 01:54:34.680720: step: 952/533, loss: 0.012897110544145107
2023-01-23 01:54:35.875696: step: 956/533, loss: 0.09667067974805832
2023-01-23 01:54:37.037496: step: 960/533, loss: 0.013701343908905983
2023-01-23 01:54:38.214609: step: 964/533, loss: 0.007405811455100775
2023-01-23 01:54:39.375865: step: 968/533, loss: 0.012143898755311966
2023-01-23 01:54:40.578355: step: 972/533, loss: 0.0043468475341796875
2023-01-23 01:54:41.734711: step: 976/533, loss: 0.002060031984001398
2023-01-23 01:54:42.902995: step: 980/533, loss: 0.0745355635881424
2023-01-23 01:54:44.081750: step: 984/533, loss: 0.0032449723221361637
2023-01-23 01:54:45.260641: step: 988/533, loss: 0.040094755589962006
2023-01-23 01:54:46.419084: step: 992/533, loss: 0.27566835284233093
2023-01-23 01:54:47.571150: step: 996/533, loss: 0.08316078037023544
2023-01-23 01:54:48.735075: step: 1000/533, loss: 0.052486710250377655
2023-01-23 01:54:49.877628: step: 1004/533, loss: 0.011968517675995827
2023-01-23 01:54:51.044175: step: 1008/533, loss: 0.08449907600879669
2023-01-23 01:54:52.190427: step: 1012/533, loss: 0.07400409132242203
2023-01-23 01:54:53.392020: step: 1016/533, loss: 0.07389393448829651
2023-01-23 01:54:54.594332: step: 1020/533, loss: 0.020061874762177467
2023-01-23 01:54:55.767473: step: 1024/533, loss: 0.045684244483709335
2023-01-23 01:54:56.906205: step: 1028/533, loss: 0.007948494516313076
2023-01-23 01:54:58.048587: step: 1032/533, loss: 0.0016446113586425781
2023-01-23 01:54:59.267776: step: 1036/533, loss: 0.02089214324951172
2023-01-23 01:55:00.421829: step: 1040/533, loss: 0.05728769302368164
2023-01-23 01:55:01.585920: step: 1044/533, loss: 0.004139709752053022
2023-01-23 01:55:02.784213: step: 1048/533, loss: 0.6455539464950562
2023-01-23 01:55:03.959071: step: 1052/533, loss: 0.12276172637939453
2023-01-23 01:55:05.147059: step: 1056/533, loss: 0.43716782331466675
2023-01-23 01:55:06.330633: step: 1060/533, loss: 0.06069774925708771
2023-01-23 01:55:07.501615: step: 1064/533, loss: 0.026159286499023438
2023-01-23 01:55:08.649303: step: 1068/533, loss: 4.129410081077367e-05
2023-01-23 01:55:09.827716: step: 1072/533, loss: 0.054787732660770416
2023-01-23 01:55:11.010281: step: 1076/533, loss: 0.04379386827349663
2023-01-23 01:55:12.148246: step: 1080/533, loss: 0.03880128636956215
2023-01-23 01:55:13.307037: step: 1084/533, loss: 0.04727020487189293
2023-01-23 01:55:14.475149: step: 1088/533, loss: 0.06523828953504562
2023-01-23 01:55:15.648141: step: 1092/533, loss: 0.03663768991827965
2023-01-23 01:55:16.819623: step: 1096/533, loss: 0.0030756474006921053
2023-01-23 01:55:17.965909: step: 1100/533, loss: 0.022153282538056374
2023-01-23 01:55:19.215709: step: 1104/533, loss: 0.026297569274902344
2023-01-23 01:55:20.364615: step: 1108/533, loss: 0.06271553039550781
2023-01-23 01:55:21.552345: step: 1112/533, loss: 0.03436391428112984
2023-01-23 01:55:22.707818: step: 1116/533, loss: 0.07579460740089417
2023-01-23 01:55:23.870039: step: 1120/533, loss: 0.06359796226024628
2023-01-23 01:55:25.038044: step: 1124/533, loss: 0.040679167956113815
2023-01-23 01:55:26.216638: step: 1128/533, loss: 0.029019545763731003
2023-01-23 01:55:27.410152: step: 1132/533, loss: 0.036148551851511
2023-01-23 01:55:28.611691: step: 1136/533, loss: 0.005886936094611883
2023-01-23 01:55:29.767885: step: 1140/533, loss: 0.006011772435158491
2023-01-23 01:55:30.949450: step: 1144/533, loss: 0.007932091131806374
2023-01-23 01:55:32.113976: step: 1148/533, loss: 0.003106242511421442
2023-01-23 01:55:33.328344: step: 1152/533, loss: 0.05227470397949219
2023-01-23 01:55:34.498402: step: 1156/533, loss: 0.018625259399414062
2023-01-23 01:55:35.687541: step: 1160/533, loss: 0.04417724907398224
2023-01-23 01:55:36.899263: step: 1164/533, loss: 0.09038429707288742
2023-01-23 01:55:38.099134: step: 1168/533, loss: 0.011069584637880325
2023-01-23 01:55:39.267719: step: 1172/533, loss: 0.012411308474838734
2023-01-23 01:55:40.435806: step: 1176/533, loss: 0.03125328943133354
2023-01-23 01:55:41.627205: step: 1180/533, loss: 0.007350158877670765
2023-01-23 01:55:42.814177: step: 1184/533, loss: 0.0676090270280838
2023-01-23 01:55:43.965655: step: 1188/533, loss: 0.04961109161376953
2023-01-23 01:55:45.123918: step: 1192/533, loss: 0.011720085516571999
2023-01-23 01:55:46.274013: step: 1196/533, loss: 0.02475709840655327
2023-01-23 01:55:47.415063: step: 1200/533, loss: 0.03511079400777817
2023-01-23 01:55:48.606684: step: 1204/533, loss: 0.006617927458137274
2023-01-23 01:55:49.797691: step: 1208/533, loss: 0.006246662233024836
2023-01-23 01:55:50.977136: step: 1212/533, loss: 0.0549495704472065
2023-01-23 01:55:52.150920: step: 1216/533, loss: 0.019649125635623932
2023-01-23 01:55:53.337265: step: 1220/533, loss: 0.007434082217514515
2023-01-23 01:55:54.578803: step: 1224/533, loss: 0.026411820203065872
2023-01-23 01:55:55.745672: step: 1228/533, loss: 0.06571540981531143
2023-01-23 01:55:56.979597: step: 1232/533, loss: 0.05336766317486763
2023-01-23 01:55:58.180324: step: 1236/533, loss: 0.0635339766740799
2023-01-23 01:55:59.360804: step: 1240/533, loss: 0.025406312197446823
2023-01-23 01:56:00.537514: step: 1244/533, loss: 0.0009971618419513106
2023-01-23 01:56:01.716788: step: 1248/533, loss: 0.055283788591623306
2023-01-23 01:56:02.881719: step: 1252/533, loss: 0.014269554056227207
2023-01-23 01:56:04.014687: step: 1256/533, loss: 0.0013463019859045744
2023-01-23 01:56:05.205305: step: 1260/533, loss: 0.008423805236816406
2023-01-23 01:56:06.365669: step: 1264/533, loss: 0.004395103547722101
2023-01-23 01:56:07.550842: step: 1268/533, loss: 0.08881063759326935
2023-01-23 01:56:08.705914: step: 1272/533, loss: 0.032858848571777344
2023-01-23 01:56:09.889330: step: 1276/533, loss: 0.045183755457401276
2023-01-23 01:56:11.067261: step: 1280/533, loss: 0.10130295902490616
2023-01-23 01:56:12.256306: step: 1284/533, loss: 0.0013909817207604647
2023-01-23 01:56:13.516248: step: 1288/533, loss: 0.010302829556167126
2023-01-23 01:56:14.672376: step: 1292/533, loss: 0.05099201574921608
2023-01-23 01:56:15.873533: step: 1296/533, loss: 0.1515444815158844
2023-01-23 01:56:17.033460: step: 1300/533, loss: 0.013141632080078125
2023-01-23 01:56:18.226607: step: 1304/533, loss: 0.0005883693811483681
2023-01-23 01:56:19.379260: step: 1308/533, loss: 0.01961502991616726
2023-01-23 01:56:20.556875: step: 1312/533, loss: 1.2897058725357056
2023-01-23 01:56:21.738185: step: 1316/533, loss: 0.008539343252778053
2023-01-23 01:56:22.898717: step: 1320/533, loss: 0.08233537524938583
2023-01-23 01:56:24.076445: step: 1324/533, loss: 0.0383848212659359
2023-01-23 01:56:25.251213: step: 1328/533, loss: 0.10562209784984589
2023-01-23 01:56:26.464367: step: 1332/533, loss: 0.017515946179628372
2023-01-23 01:56:27.619230: step: 1336/533, loss: 0.007807398214936256
2023-01-23 01:56:28.790213: step: 1340/533, loss: 0.040183451026678085
2023-01-23 01:56:29.952765: step: 1344/533, loss: 0.02508239820599556
2023-01-23 01:56:31.130997: step: 1348/533, loss: 0.02649688720703125
2023-01-23 01:56:32.294891: step: 1352/533, loss: 0.00017156600370071828
2023-01-23 01:56:33.477593: step: 1356/533, loss: 0.12630033493041992
2023-01-23 01:56:34.635518: step: 1360/533, loss: 0.05860919877886772
2023-01-23 01:56:35.833919: step: 1364/533, loss: 1.308081865310669
2023-01-23 01:56:37.052746: step: 1368/533, loss: 0.02837085723876953
2023-01-23 01:56:38.221889: step: 1372/533, loss: 0.053876303136348724
2023-01-23 01:56:39.364874: step: 1376/533, loss: 0.022728348150849342
2023-01-23 01:56:40.530557: step: 1380/533, loss: 0.024346735328435898
2023-01-23 01:56:41.682067: step: 1384/533, loss: 0.0023559569381177425
2023-01-23 01:56:42.818873: step: 1388/533, loss: 0.20595036447048187
2023-01-23 01:56:44.039647: step: 1392/533, loss: 0.0008267402881756425
2023-01-23 01:56:45.236601: step: 1396/533, loss: 0.04612855985760689
2023-01-23 01:56:46.425655: step: 1400/533, loss: 0.008933735080063343
2023-01-23 01:56:47.614949: step: 1404/533, loss: 0.0012525557540357113
2023-01-23 01:56:48.801497: step: 1408/533, loss: 0.015462398529052734
2023-01-23 01:56:49.996617: step: 1412/533, loss: 0.003404903458431363
2023-01-23 01:56:51.177894: step: 1416/533, loss: 0.050734709948301315
2023-01-23 01:56:52.368475: step: 1420/533, loss: 0.05393047258257866
2023-01-23 01:56:53.562348: step: 1424/533, loss: 0.0025018840096890926
2023-01-23 01:56:54.710921: step: 1428/533, loss: 0.053116071969270706
2023-01-23 01:56:55.914190: step: 1432/533, loss: 0.04021759331226349
2023-01-23 01:56:57.093600: step: 1436/533, loss: 0.008732987567782402
2023-01-23 01:56:58.301495: step: 1440/533, loss: 0.09969702363014221
2023-01-23 01:56:59.478956: step: 1444/533, loss: 0.042491450905799866
2023-01-23 01:57:00.662351: step: 1448/533, loss: 0.09365804493427277
2023-01-23 01:57:01.850278: step: 1452/533, loss: 0.03684242069721222
2023-01-23 01:57:03.038770: step: 1456/533, loss: 0.04148521274328232
2023-01-23 01:57:04.248455: step: 1460/533, loss: 0.3614819645881653
2023-01-23 01:57:05.424288: step: 1464/533, loss: 0.04030151292681694
2023-01-23 01:57:06.595035: step: 1468/533, loss: 0.040897928178310394
2023-01-23 01:57:07.815239: step: 1472/533, loss: 0.07197470963001251
2023-01-23 01:57:09.023680: step: 1476/533, loss: 0.016492558643221855
2023-01-23 01:57:10.216926: step: 1480/533, loss: 0.03463897854089737
2023-01-23 01:57:11.341271: step: 1484/533, loss: 0.0009126663208007812
2023-01-23 01:57:12.563174: step: 1488/533, loss: 0.09991320967674255
2023-01-23 01:57:13.750215: step: 1492/533, loss: 0.04668637365102768
2023-01-23 01:57:14.917696: step: 1496/533, loss: 0.008671903051435947
2023-01-23 01:57:16.142581: step: 1500/533, loss: 0.8305399417877197
2023-01-23 01:57:17.315279: step: 1504/533, loss: 0.005974197760224342
2023-01-23 01:57:18.498962: step: 1508/533, loss: 0.09068632125854492
2023-01-23 01:57:19.666459: step: 1512/533, loss: 0.034741759300231934
2023-01-23 01:57:20.821278: step: 1516/533, loss: 0.040307048708200455
2023-01-23 01:57:21.979320: step: 1520/533, loss: 0.07411651313304901
2023-01-23 01:57:23.178141: step: 1524/533, loss: 0.02290353737771511
2023-01-23 01:57:24.379992: step: 1528/533, loss: 0.014486503787338734
2023-01-23 01:57:25.541469: step: 1532/533, loss: 0.009680259972810745
2023-01-23 01:57:26.709096: step: 1536/533, loss: 0.12689457833766937
2023-01-23 01:57:27.911784: step: 1540/533, loss: 0.033223867416381836
2023-01-23 01:57:29.104055: step: 1544/533, loss: 0.002190208528190851
2023-01-23 01:57:30.265744: step: 1548/533, loss: 0.015666579827666283
2023-01-23 01:57:31.422631: step: 1552/533, loss: 0.16559754312038422
2023-01-23 01:57:32.602670: step: 1556/533, loss: 0.05890865623950958
2023-01-23 01:57:33.750473: step: 1560/533, loss: 0.015046787448227406
2023-01-23 01:57:34.904971: step: 1564/533, loss: 0.011388206854462624
2023-01-23 01:57:36.153866: step: 1568/533, loss: 0.0432308204472065
2023-01-23 01:57:37.324744: step: 1572/533, loss: 0.7456789016723633
2023-01-23 01:57:38.495547: step: 1576/533, loss: 0.0708545669913292
2023-01-23 01:57:39.664220: step: 1580/533, loss: 0.16015291213989258
2023-01-23 01:57:40.841578: step: 1584/533, loss: 0.10407057404518127
2023-01-23 01:57:41.993873: step: 1588/533, loss: 0.049579620361328125
2023-01-23 01:57:43.169841: step: 1592/533, loss: 0.002498817630112171
2023-01-23 01:57:44.342710: step: 1596/533, loss: 0.005932044703513384
2023-01-23 01:57:45.485742: step: 1600/533, loss: 0.013750839047133923
2023-01-23 01:57:46.701593: step: 1604/533, loss: 0.0308137908577919
2023-01-23 01:57:47.851309: step: 1608/533, loss: 0.01919250376522541
2023-01-23 01:57:49.055581: step: 1612/533, loss: 0.0014053345657885075
2023-01-23 01:57:50.244337: step: 1616/533, loss: 0.04550447687506676
2023-01-23 01:57:51.419529: step: 1620/533, loss: 0.004902282729744911
2023-01-23 01:57:52.587941: step: 1624/533, loss: 0.05277309566736221
2023-01-23 01:57:53.807445: step: 1628/533, loss: 0.037142276763916016
2023-01-23 01:57:54.967807: step: 1632/533, loss: 0.03200273588299751
2023-01-23 01:57:56.144379: step: 1636/533, loss: 0.07220450043678284
2023-01-23 01:57:57.334313: step: 1640/533, loss: 0.022613907232880592
2023-01-23 01:57:58.504347: step: 1644/533, loss: 0.001593732857145369
2023-01-23 01:57:59.668940: step: 1648/533, loss: 0.009949112311005592
2023-01-23 01:58:00.852763: step: 1652/533, loss: 0.0013437271118164062
2023-01-23 01:58:02.079402: step: 1656/533, loss: 0.04954414814710617
2023-01-23 01:58:03.242082: step: 1660/533, loss: 0.0308440700173378
2023-01-23 01:58:04.397760: step: 1664/533, loss: 0.05828666687011719
2023-01-23 01:58:05.591797: step: 1668/533, loss: 0.07057533413171768
2023-01-23 01:58:06.764940: step: 1672/533, loss: 0.04824848473072052
2023-01-23 01:58:07.959498: step: 1676/533, loss: 0.3716858923435211
2023-01-23 01:58:09.144223: step: 1680/533, loss: 0.004019451327621937
2023-01-23 01:58:10.309431: step: 1684/533, loss: 0.04919147491455078
2023-01-23 01:58:11.456189: step: 1688/533, loss: 0.05374279245734215
2023-01-23 01:58:12.617242: step: 1692/533, loss: 0.01891307905316353
2023-01-23 01:58:13.777705: step: 1696/533, loss: 0.021967411041259766
2023-01-23 01:58:14.940608: step: 1700/533, loss: 0.011027527041733265
2023-01-23 01:58:16.135613: step: 1704/533, loss: 0.0049224854446947575
2023-01-23 01:58:17.284374: step: 1708/533, loss: 0.04515886679291725
2023-01-23 01:58:18.468079: step: 1712/533, loss: 0.04739999771118164
2023-01-23 01:58:19.617635: step: 1716/533, loss: 0.05396304279565811
2023-01-23 01:58:20.777099: step: 1720/533, loss: 0.009928131476044655
2023-01-23 01:58:21.924858: step: 1724/533, loss: 0.056420229375362396
2023-01-23 01:58:23.118226: step: 1728/533, loss: 0.007881450466811657
2023-01-23 01:58:24.273468: step: 1732/533, loss: 0.012360621243715286
2023-01-23 01:58:25.460192: step: 1736/533, loss: 0.0024271011352539062
2023-01-23 01:58:26.609306: step: 1740/533, loss: 0.06875310093164444
2023-01-23 01:58:27.774289: step: 1744/533, loss: 0.010922432877123356
2023-01-23 01:58:28.939716: step: 1748/533, loss: 0.006643486209213734
2023-01-23 01:58:30.089674: step: 1752/533, loss: 0.04122591018676758
2023-01-23 01:58:31.238961: step: 1756/533, loss: 0.08097944408655167
2023-01-23 01:58:32.412086: step: 1760/533, loss: 0.03387737274169922
2023-01-23 01:58:33.584680: step: 1764/533, loss: 0.07992801815271378
2023-01-23 01:58:34.755664: step: 1768/533, loss: 5.626814365386963
2023-01-23 01:58:35.939848: step: 1772/533, loss: 0.023672878742218018
2023-01-23 01:58:37.105644: step: 1776/533, loss: 0.11575527489185333
2023-01-23 01:58:38.270814: step: 1780/533, loss: 0.033416748046875
2023-01-23 01:58:39.460599: step: 1784/533, loss: 0.005836295895278454
2023-01-23 01:58:40.654225: step: 1788/533, loss: 0.027249742299318314
2023-01-23 01:58:41.831603: step: 1792/533, loss: 0.1162288710474968
2023-01-23 01:58:43.021232: step: 1796/533, loss: 0.031856488436460495
2023-01-23 01:58:44.186726: step: 1800/533, loss: 0.0013091088039800525
2023-01-23 01:58:45.361215: step: 1804/533, loss: 0.03713731840252876
2023-01-23 01:58:46.551226: step: 1808/533, loss: 0.02197857014834881
2023-01-23 01:58:47.720567: step: 1812/533, loss: 0.002892112825065851
2023-01-23 01:58:48.958398: step: 1816/533, loss: 0.02422657050192356
2023-01-23 01:58:50.128316: step: 1820/533, loss: 0.0020391466096043587
2023-01-23 01:58:51.318685: step: 1824/533, loss: 0.09324569255113602
2023-01-23 01:58:52.560306: step: 1828/533, loss: 0.040514566004276276
2023-01-23 01:58:53.705036: step: 1832/533, loss: 0.015990257263183594
2023-01-23 01:58:54.866135: step: 1836/533, loss: 0.019208334386348724
2023-01-23 01:58:56.019949: step: 1840/533, loss: 0.01714625395834446
2023-01-23 01:58:57.236849: step: 1844/533, loss: 0.38581982254981995
2023-01-23 01:58:58.399677: step: 1848/533, loss: 0.039667606353759766
2023-01-23 01:58:59.576413: step: 1852/533, loss: 0.01530914381146431
2023-01-23 01:59:00.695594: step: 1856/533, loss: 0.05333404242992401
2023-01-23 01:59:01.873745: step: 1860/533, loss: 0.02271137200295925
2023-01-23 01:59:03.115348: step: 1864/533, loss: 0.03758373111486435
2023-01-23 01:59:04.343848: step: 1868/533, loss: 0.019816016778349876
2023-01-23 01:59:05.531691: step: 1872/533, loss: 0.01566324196755886
2023-01-23 01:59:06.707830: step: 1876/533, loss: 0.3339584469795227
2023-01-23 01:59:07.880789: step: 1880/533, loss: 0.06104555353522301
2023-01-23 01:59:09.019860: step: 1884/533, loss: 0.02511494979262352
2023-01-23 01:59:10.173422: step: 1888/533, loss: 0.03393096849322319
2023-01-23 01:59:11.329692: step: 1892/533, loss: 0.1022665947675705
2023-01-23 01:59:12.501556: step: 1896/533, loss: 0.022139834240078926
2023-01-23 01:59:13.654445: step: 1900/533, loss: 0.009954738430678844
2023-01-23 01:59:14.821622: step: 1904/533, loss: 0.012344075366854668
2023-01-23 01:59:15.957117: step: 1908/533, loss: 0.07537984848022461
2023-01-23 01:59:17.131290: step: 1912/533, loss: 0.016133736819028854
2023-01-23 01:59:18.308090: step: 1916/533, loss: 0.020180368795990944
2023-01-23 01:59:19.497366: step: 1920/533, loss: 0.04780330881476402
2023-01-23 01:59:20.657401: step: 1924/533, loss: 0.1405627727508545
2023-01-23 01:59:21.852623: step: 1928/533, loss: 0.060349512845277786
2023-01-23 01:59:23.062630: step: 1932/533, loss: 0.02381448820233345
2023-01-23 01:59:24.270414: step: 1936/533, loss: 0.06789477914571762
2023-01-23 01:59:25.415709: step: 1940/533, loss: 0.009193516336381435
2023-01-23 01:59:26.568818: step: 1944/533, loss: 0.019691942259669304
2023-01-23 01:59:27.757726: step: 1948/533, loss: 0.33529210090637207
2023-01-23 01:59:28.883893: step: 1952/533, loss: 0.04544544592499733
2023-01-23 01:59:30.072599: step: 1956/533, loss: 0.026929188519716263
2023-01-23 01:59:31.233775: step: 1960/533, loss: 0.059825848788022995
2023-01-23 01:59:32.420802: step: 1964/533, loss: 0.03160800784826279
2023-01-23 01:59:33.612688: step: 1968/533, loss: 0.05579938739538193
2023-01-23 01:59:34.802311: step: 1972/533, loss: 0.0343564972281456
2023-01-23 01:59:35.966091: step: 1976/533, loss: 0.3329122066497803
2023-01-23 01:59:37.154835: step: 1980/533, loss: 0.0194975845515728
2023-01-23 01:59:38.338083: step: 1984/533, loss: 0.02982030063867569
2023-01-23 01:59:39.520031: step: 1988/533, loss: 0.027073288336396217
2023-01-23 01:59:40.679200: step: 1992/533, loss: 0.0241559986025095
2023-01-23 01:59:41.869887: step: 1996/533, loss: 0.03220415115356445
2023-01-23 01:59:43.043803: step: 2000/533, loss: 0.16389961540699005
2023-01-23 01:59:44.218626: step: 2004/533, loss: 0.1568075716495514
2023-01-23 01:59:45.442538: step: 2008/533, loss: 0.008940506726503372
2023-01-23 01:59:46.615268: step: 2012/533, loss: 0.0014833450550213456
2023-01-23 01:59:47.774557: step: 2016/533, loss: 0.006083965301513672
2023-01-23 01:59:48.962718: step: 2020/533, loss: 0.009312057867646217
2023-01-23 01:59:50.144154: step: 2024/533, loss: 0.0312558189034462
2023-01-23 01:59:51.356918: step: 2028/533, loss: 0.03570146486163139
2023-01-23 01:59:52.574507: step: 2032/533, loss: 0.0021544217597693205
2023-01-23 01:59:53.742863: step: 2036/533, loss: 0.06766524165868759
2023-01-23 01:59:54.949440: step: 2040/533, loss: 0.05466528236865997
2023-01-23 01:59:56.141655: step: 2044/533, loss: 0.015527725219726562
2023-01-23 01:59:57.331400: step: 2048/533, loss: 0.044196225702762604
2023-01-23 01:59:58.498180: step: 2052/533, loss: 0.05046520382165909
2023-01-23 01:59:59.656693: step: 2056/533, loss: 0.1475900411605835
2023-01-23 02:00:00.877189: step: 2060/533, loss: 0.002491188235580921
2023-01-23 02:00:02.116040: step: 2064/533, loss: 0.006779193878173828
2023-01-23 02:00:03.238820: step: 2068/533, loss: 0.0022489072289317846
2023-01-23 02:00:04.401534: step: 2072/533, loss: 0.007942772470414639
2023-01-23 02:00:05.570815: step: 2076/533, loss: 0.04199938848614693
2023-01-23 02:00:06.731248: step: 2080/533, loss: 0.012682009488344193
2023-01-23 02:00:07.919570: step: 2084/533, loss: 0.09639053046703339
2023-01-23 02:00:09.088295: step: 2088/533, loss: 0.13996896147727966
2023-01-23 02:00:10.265100: step: 2092/533, loss: 0.006974983029067516
2023-01-23 02:00:11.433987: step: 2096/533, loss: 0.029192544519901276
2023-01-23 02:00:12.604764: step: 2100/533, loss: 0.015396308153867722
2023-01-23 02:00:13.785862: step: 2104/533, loss: 0.11576671153306961
2023-01-23 02:00:14.980608: step: 2108/533, loss: 0.12584161758422852
2023-01-23 02:00:16.172855: step: 2112/533, loss: 0.012666946277022362
2023-01-23 02:00:17.394102: step: 2116/533, loss: 0.002259921981021762
2023-01-23 02:00:18.589417: step: 2120/533, loss: 0.025191783905029297
2023-01-23 02:00:19.777614: step: 2124/533, loss: 0.02025766484439373
2023-01-23 02:00:20.981877: step: 2128/533, loss: 0.0872829481959343
2023-01-23 02:00:22.140738: step: 2132/533, loss: 0.004870033357292414
==================================================
Loss: 0.065
--------------------
Dev: {'event': {'p': 0.5871369294605809, 'r': 0.7536617842876165, 'f1': 0.660058309037901}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6406406406406406, 'r': 0.8184143222506394, 'f1': 0.7186973610331273}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
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': 13}
Korean: {'event': {'p': 0.5862068965517241, 'r': 0.5396825396825397, 'f1': 0.5619834710743802}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.42857142857142855, 'r': 0.5, 'f1': 0.4615384615384615}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:01:03.129645: step: 4/533, loss: 0.0518094077706337
2023-01-23 02:01:04.321773: step: 8/533, loss: 0.05276336893439293
2023-01-23 02:01:05.482814: step: 12/533, loss: 0.011742830276489258
2023-01-23 02:01:06.653252: step: 16/533, loss: 0.009232045151293278
2023-01-23 02:01:07.857976: step: 20/533, loss: 0.0018863677978515625
2023-01-23 02:01:09.041580: step: 24/533, loss: 0.03952836990356445
2023-01-23 02:01:10.215716: step: 28/533, loss: 1.133405327796936
2023-01-23 02:01:11.385818: step: 32/533, loss: 0.03339672088623047
2023-01-23 02:01:12.575516: step: 36/533, loss: 0.003053999040275812
2023-01-23 02:01:13.732720: step: 40/533, loss: 0.001923418021760881
2023-01-23 02:01:14.919159: step: 44/533, loss: 0.01966419257223606
2023-01-23 02:01:16.142983: step: 48/533, loss: 0.022713089361786842
2023-01-23 02:01:17.319857: step: 52/533, loss: 0.016245078295469284
2023-01-23 02:01:18.517316: step: 56/533, loss: 0.002317714737728238
2023-01-23 02:01:19.674168: step: 60/533, loss: 0.037776585668325424
2023-01-23 02:01:20.864234: step: 64/533, loss: 0.031238652765750885
2023-01-23 02:01:22.014088: step: 68/533, loss: 0.026325320824980736
2023-01-23 02:01:23.198557: step: 72/533, loss: 0.003839445300400257
2023-01-23 02:01:24.369031: step: 76/533, loss: 0.12901124358177185
2023-01-23 02:01:25.540019: step: 80/533, loss: 0.021156905218958855
2023-01-23 02:01:26.713607: step: 84/533, loss: 0.020279789343476295
2023-01-23 02:01:27.960467: step: 88/533, loss: 0.01670360565185547
2023-01-23 02:01:29.158862: step: 92/533, loss: 0.0005053520435467362
2023-01-23 02:01:30.354702: step: 96/533, loss: 0.000706577324308455
2023-01-23 02:01:31.539692: step: 100/533, loss: 0.013101291842758656
2023-01-23 02:01:32.727873: step: 104/533, loss: 0.004114056006073952
2023-01-23 02:01:33.893570: step: 108/533, loss: 0.02924833446741104
2023-01-23 02:01:35.061988: step: 112/533, loss: 0.00824208278208971
2023-01-23 02:01:36.249843: step: 116/533, loss: 0.06478758156299591
2023-01-23 02:01:37.473240: step: 120/533, loss: 0.004162550438195467
2023-01-23 02:01:38.639415: step: 124/533, loss: 0.04760627821087837
2023-01-23 02:01:39.853214: step: 128/533, loss: 0.002372550778090954
2023-01-23 02:01:41.024245: step: 132/533, loss: 0.011991691775619984
2023-01-23 02:01:42.202092: step: 136/533, loss: 0.022435570135712624
2023-01-23 02:01:43.333688: step: 140/533, loss: 0.023341942578554153
2023-01-23 02:01:44.517013: step: 144/533, loss: 0.011906379833817482
2023-01-23 02:01:45.710654: step: 148/533, loss: 0.005397891625761986
2023-01-23 02:01:46.909994: step: 152/533, loss: 0.026522351428866386
2023-01-23 02:01:48.106169: step: 156/533, loss: 0.00797882117331028
2023-01-23 02:01:49.298878: step: 160/533, loss: 0.00012578963651321828
2023-01-23 02:01:50.480523: step: 164/533, loss: 0.017604637891054153
2023-01-23 02:01:51.686129: step: 168/533, loss: 0.010859060101211071
2023-01-23 02:01:52.900427: step: 172/533, loss: 0.021741580218076706
2023-01-23 02:01:54.102813: step: 176/533, loss: 0.013530444353818893
2023-01-23 02:01:55.301074: step: 180/533, loss: 0.003749370574951172
2023-01-23 02:01:56.469218: step: 184/533, loss: 0.023764800280332565
2023-01-23 02:01:57.647991: step: 188/533, loss: 0.003438282059505582
2023-01-23 02:01:58.821802: step: 192/533, loss: 0.007263851352035999
2023-01-23 02:01:59.994815: step: 196/533, loss: 0.049765635281801224
2023-01-23 02:02:01.203848: step: 200/533, loss: 0.08769015967845917
2023-01-23 02:02:02.376628: step: 204/533, loss: 0.18049907684326172
2023-01-23 02:02:03.572060: step: 208/533, loss: 0.014322662726044655
2023-01-23 02:02:04.759459: step: 212/533, loss: 0.05369434505701065
2023-01-23 02:02:05.947861: step: 216/533, loss: 0.06156301498413086
2023-01-23 02:02:07.105271: step: 220/533, loss: 0.033228494226932526
2023-01-23 02:02:08.260686: step: 224/533, loss: 0.007882023230195045
2023-01-23 02:02:09.418391: step: 228/533, loss: 0.001933765597641468
2023-01-23 02:02:10.596826: step: 232/533, loss: 0.05712109059095383
2023-01-23 02:02:11.734908: step: 236/533, loss: 0.011195087805390358
2023-01-23 02:02:12.886147: step: 240/533, loss: 0.032080747187137604
2023-01-23 02:02:14.110093: step: 244/533, loss: 0.027440454810857773
2023-01-23 02:02:15.266798: step: 248/533, loss: 0.0005819320795126259
2023-01-23 02:02:16.421450: step: 252/533, loss: 0.036676786839962006
2023-01-23 02:02:17.628772: step: 256/533, loss: 0.05094585195183754
2023-01-23 02:02:18.811215: step: 260/533, loss: 0.0014437198406085372
2023-01-23 02:02:19.998117: step: 264/533, loss: 0.012420654296875
2023-01-23 02:02:21.143991: step: 268/533, loss: 0.002605485962703824
2023-01-23 02:02:22.310352: step: 272/533, loss: 0.00310173025354743
2023-01-23 02:02:23.436747: step: 276/533, loss: 0.002975702518597245
2023-01-23 02:02:24.608225: step: 280/533, loss: 0.04784102365374565
2023-01-23 02:02:25.778448: step: 284/533, loss: 0.0175428856164217
2023-01-23 02:02:26.913224: step: 288/533, loss: 0.004173708148300648
2023-01-23 02:02:28.090153: step: 292/533, loss: 0.2548210024833679
2023-01-23 02:02:29.263492: step: 296/533, loss: 0.0013281822903081775
2023-01-23 02:02:30.441200: step: 300/533, loss: 0.02344522438943386
2023-01-23 02:02:31.657547: step: 304/533, loss: 0.05363183096051216
2023-01-23 02:02:32.822633: step: 308/533, loss: 0.013500213623046875
2023-01-23 02:02:34.004660: step: 312/533, loss: 0.06136922910809517
2023-01-23 02:02:35.206161: step: 316/533, loss: 0.0007150173187255859
2023-01-23 02:02:36.399082: step: 320/533, loss: 0.002105522435158491
2023-01-23 02:02:37.587320: step: 324/533, loss: 0.5246507525444031
2023-01-23 02:02:38.779500: step: 328/533, loss: 0.03873424604535103
2023-01-23 02:02:39.950586: step: 332/533, loss: 0.0029366493690758944
2023-01-23 02:02:41.145474: step: 336/533, loss: 0.01386947650462389
2023-01-23 02:02:42.304674: step: 340/533, loss: 0.013595200143754482
2023-01-23 02:02:43.503695: step: 344/533, loss: 0.03603091463446617
2023-01-23 02:02:44.692960: step: 348/533, loss: 0.0012850761413574219
2023-01-23 02:02:45.900979: step: 352/533, loss: 0.004223919007927179
2023-01-23 02:02:47.102088: step: 356/533, loss: 0.03832054138183594
2023-01-23 02:02:48.280064: step: 360/533, loss: 0.04459753260016441
2023-01-23 02:02:49.488649: step: 364/533, loss: 0.0398649238049984
2023-01-23 02:02:50.642937: step: 368/533, loss: 0.03520069271326065
2023-01-23 02:02:51.812431: step: 372/533, loss: 0.03638019412755966
2023-01-23 02:02:52.944209: step: 376/533, loss: 0.05231475830078125
2023-01-23 02:02:54.127904: step: 380/533, loss: 0.4421539306640625
2023-01-23 02:02:55.363579: step: 384/533, loss: 0.20982475578784943
2023-01-23 02:02:56.486252: step: 388/533, loss: 0.07425327599048615
2023-01-23 02:02:57.674184: step: 392/533, loss: 0.0016329764621332288
2023-01-23 02:02:58.859174: step: 396/533, loss: 0.05830249935388565
2023-01-23 02:03:00.053149: step: 400/533, loss: 0.008459853939712048
2023-01-23 02:03:01.224090: step: 404/533, loss: 0.004722786135971546
2023-01-23 02:03:02.418068: step: 408/533, loss: 0.0774863213300705
2023-01-23 02:03:03.550806: step: 412/533, loss: 0.0028838159050792456
2023-01-23 02:03:04.774682: step: 416/533, loss: 0.10506601631641388
2023-01-23 02:03:05.924139: step: 420/533, loss: 0.27414941787719727
2023-01-23 02:03:07.132308: step: 424/533, loss: 0.010890627279877663
2023-01-23 02:03:08.412913: step: 428/533, loss: 0.01600799523293972
2023-01-23 02:03:09.585215: step: 432/533, loss: 0.03158445283770561
2023-01-23 02:03:10.820720: step: 436/533, loss: 0.03226461261510849
2023-01-23 02:03:11.959143: step: 440/533, loss: 0.02806882932782173
2023-01-23 02:03:13.138786: step: 444/533, loss: 0.6819657683372498
2023-01-23 02:03:14.351592: step: 448/533, loss: 0.012016487307846546
2023-01-23 02:03:15.514266: step: 452/533, loss: 0.007284260354936123
2023-01-23 02:03:16.677105: step: 456/533, loss: 0.009635353460907936
2023-01-23 02:03:17.873980: step: 460/533, loss: 0.010797214694321156
2023-01-23 02:03:19.067304: step: 464/533, loss: 0.0497320182621479
2023-01-23 02:03:20.250818: step: 468/533, loss: 0.0053924559615552425
2023-01-23 02:03:21.427702: step: 472/533, loss: 0.03964591026306152
2023-01-23 02:03:22.575769: step: 476/533, loss: 0.0021451949141919613
2023-01-23 02:03:23.737794: step: 480/533, loss: 0.02539977990090847
2023-01-23 02:03:24.920500: step: 484/533, loss: 0.0027429580222815275
2023-01-23 02:03:26.123884: step: 488/533, loss: 0.09211654216051102
2023-01-23 02:03:27.312654: step: 492/533, loss: 0.00011256933066761121
2023-01-23 02:03:28.489616: step: 496/533, loss: 0.023706912994384766
2023-01-23 02:03:29.655017: step: 500/533, loss: 0.00475311279296875
2023-01-23 02:03:30.797586: step: 504/533, loss: 0.010573959909379482
2023-01-23 02:03:32.005484: step: 508/533, loss: 0.00876550655812025
2023-01-23 02:03:33.142629: step: 512/533, loss: 0.0004525184631347656
2023-01-23 02:03:34.343317: step: 516/533, loss: 0.0011173248058184981
2023-01-23 02:03:35.510226: step: 520/533, loss: 0.009097481146454811
2023-01-23 02:03:36.659041: step: 524/533, loss: 0.2122957855463028
2023-01-23 02:03:37.847684: step: 528/533, loss: 0.37422817945480347
2023-01-23 02:03:39.006779: step: 532/533, loss: 0.03604459762573242
2023-01-23 02:03:40.192653: step: 536/533, loss: 0.023160744458436966
2023-01-23 02:03:41.369986: step: 540/533, loss: 0.003912448883056641
2023-01-23 02:03:42.534719: step: 544/533, loss: 0.009313011541962624
2023-01-23 02:03:43.662204: step: 548/533, loss: 0.006199741270393133
2023-01-23 02:03:44.845782: step: 552/533, loss: 0.006425977218896151
2023-01-23 02:03:46.081003: step: 556/533, loss: 0.01684131659567356
2023-01-23 02:03:47.242469: step: 560/533, loss: 0.00794363021850586
2023-01-23 02:03:48.404159: step: 564/533, loss: 0.04762868955731392
2023-01-23 02:03:49.588830: step: 568/533, loss: 0.0741356909275055
2023-01-23 02:03:50.774467: step: 572/533, loss: 0.0008775173919275403
2023-01-23 02:03:51.928587: step: 576/533, loss: 0.04950456693768501
2023-01-23 02:03:53.121151: step: 580/533, loss: 0.021826554089784622
2023-01-23 02:03:54.300677: step: 584/533, loss: 0.0016706467140465975
2023-01-23 02:03:55.482726: step: 588/533, loss: 0.03202934190630913
2023-01-23 02:03:56.660520: step: 592/533, loss: 0.0002475738583598286
2023-01-23 02:03:57.804255: step: 596/533, loss: 1.538374662399292
2023-01-23 02:03:58.960377: step: 600/533, loss: 0.0041249278001487255
2023-01-23 02:04:00.163489: step: 604/533, loss: 0.04962005838751793
2023-01-23 02:04:01.357800: step: 608/533, loss: 0.04288854822516441
2023-01-23 02:04:02.544523: step: 612/533, loss: 0.05195961147546768
2023-01-23 02:04:03.734225: step: 616/533, loss: 0.04928302764892578
2023-01-23 02:04:04.905127: step: 620/533, loss: 0.0015430449275299907
2023-01-23 02:04:06.052012: step: 624/533, loss: 0.005393601022660732
2023-01-23 02:04:07.255033: step: 628/533, loss: 0.01617260091006756
2023-01-23 02:04:08.405684: step: 632/533, loss: 0.023660849779844284
2023-01-23 02:04:09.531847: step: 636/533, loss: 0.00185480120126158
2023-01-23 02:04:10.695515: step: 640/533, loss: 0.04813957214355469
2023-01-23 02:04:11.883329: step: 644/533, loss: 0.0995282232761383
2023-01-23 02:04:13.020370: step: 648/533, loss: 0.073021799325943
2023-01-23 02:04:14.190250: step: 652/533, loss: 0.003402900882065296
2023-01-23 02:04:15.353583: step: 656/533, loss: 0.0019078254699707031
2023-01-23 02:04:16.510890: step: 660/533, loss: 0.004020499996840954
2023-01-23 02:04:17.708225: step: 664/533, loss: 0.06028938665986061
2023-01-23 02:04:18.893144: step: 668/533, loss: 0.09243932366371155
2023-01-23 02:04:20.103450: step: 672/533, loss: 0.009998321533203125
2023-01-23 02:04:21.267159: step: 676/533, loss: 0.020939921960234642
2023-01-23 02:04:22.412139: step: 680/533, loss: 0.004695129580795765
2023-01-23 02:04:23.553173: step: 684/533, loss: 0.010105801746249199
2023-01-23 02:04:24.772691: step: 688/533, loss: 0.007549285888671875
2023-01-23 02:04:25.971414: step: 692/533, loss: 0.0031150816939771175
2023-01-23 02:04:27.099000: step: 696/533, loss: 0.04190712049603462
2023-01-23 02:04:28.283117: step: 700/533, loss: 0.02550687827169895
2023-01-23 02:04:29.489669: step: 704/533, loss: 0.002892398973926902
2023-01-23 02:04:30.679768: step: 708/533, loss: 0.34170034527778625
2023-01-23 02:04:31.860290: step: 712/533, loss: 0.0010183334816247225
2023-01-23 02:04:33.040715: step: 716/533, loss: 0.04951591417193413
2023-01-23 02:04:34.205954: step: 720/533, loss: 0.09577446430921555
2023-01-23 02:04:35.401777: step: 724/533, loss: 0.03147487714886665
2023-01-23 02:04:36.584924: step: 728/533, loss: 0.00046219825162552297
2023-01-23 02:04:37.806387: step: 732/533, loss: 0.07083601504564285
2023-01-23 02:04:38.973234: step: 736/533, loss: 0.08560695499181747
2023-01-23 02:04:40.145618: step: 740/533, loss: 0.04132995754480362
2023-01-23 02:04:41.304485: step: 744/533, loss: 0.017970561981201172
2023-01-23 02:04:42.517124: step: 748/533, loss: 0.018801499158143997
2023-01-23 02:04:43.667878: step: 752/533, loss: 0.06247539818286896
2023-01-23 02:04:44.846002: step: 756/533, loss: 0.019234562292695045
2023-01-23 02:04:46.016909: step: 760/533, loss: 0.02002892643213272
2023-01-23 02:04:47.191755: step: 764/533, loss: 0.015103436075150967
2023-01-23 02:04:48.355755: step: 768/533, loss: 0.008491325192153454
2023-01-23 02:04:49.544097: step: 772/533, loss: 0.0006873130914755166
2023-01-23 02:04:50.734063: step: 776/533, loss: 0.0072487834841012955
2023-01-23 02:04:51.975967: step: 780/533, loss: 0.045395851135253906
2023-01-23 02:04:53.139822: step: 784/533, loss: 0.5315955877304077
2023-01-23 02:04:54.343884: step: 788/533, loss: 0.020901966840028763
2023-01-23 02:04:55.499768: step: 792/533, loss: 0.0020432472229003906
2023-01-23 02:04:56.667821: step: 796/533, loss: 0.0017360687488690019
2023-01-23 02:04:57.842067: step: 800/533, loss: 0.013344001956284046
2023-01-23 02:04:59.063838: step: 804/533, loss: 0.02614021487534046
2023-01-23 02:05:00.236346: step: 808/533, loss: 0.0005293846479617059
2023-01-23 02:05:01.401867: step: 812/533, loss: 0.0006503105396404862
2023-01-23 02:05:02.597893: step: 816/533, loss: 0.03363943099975586
2023-01-23 02:05:03.793214: step: 820/533, loss: 0.05826082453131676
2023-01-23 02:05:04.936721: step: 824/533, loss: 0.007171630859375
2023-01-23 02:05:06.131300: step: 828/533, loss: 0.00195732107385993
2023-01-23 02:05:07.274562: step: 832/533, loss: 0.012225913815200329
2023-01-23 02:05:08.472548: step: 836/533, loss: 0.025861550122499466
2023-01-23 02:05:09.686135: step: 840/533, loss: 0.009180068969726562
2023-01-23 02:05:10.866985: step: 844/533, loss: 0.0018133163684979081
2023-01-23 02:05:12.021173: step: 848/533, loss: 0.02747049368917942
2023-01-23 02:05:13.196647: step: 852/533, loss: 0.00331459054723382
2023-01-23 02:05:14.381672: step: 856/533, loss: 0.009013843722641468
2023-01-23 02:05:15.541520: step: 860/533, loss: 0.02509593963623047
2023-01-23 02:05:16.747626: step: 864/533, loss: 0.032434847205877304
2023-01-23 02:05:17.959941: step: 868/533, loss: 0.16066695749759674
2023-01-23 02:05:19.143732: step: 872/533, loss: 0.049582671374082565
2023-01-23 02:05:20.300705: step: 876/533, loss: 0.0167510025203228
2023-01-23 02:05:21.424289: step: 880/533, loss: 0.001733493758365512
2023-01-23 02:05:22.585291: step: 884/533, loss: 0.023692702874541283
2023-01-23 02:05:23.741631: step: 888/533, loss: 1.039563775062561
2023-01-23 02:05:24.884527: step: 892/533, loss: 1.1634827387752011e-05
2023-01-23 02:05:26.085236: step: 896/533, loss: 0.043808698654174805
2023-01-23 02:05:27.249423: step: 900/533, loss: 0.019817162305116653
2023-01-23 02:05:28.446572: step: 904/533, loss: 0.011703675612807274
2023-01-23 02:05:29.663461: step: 908/533, loss: 0.00259494804777205
2023-01-23 02:05:30.842039: step: 912/533, loss: 0.029726792126893997
2023-01-23 02:05:32.029021: step: 916/533, loss: 0.061312485486269
2023-01-23 02:05:33.199450: step: 920/533, loss: 0.010663175955414772
2023-01-23 02:05:34.380176: step: 924/533, loss: 0.004093170631676912
2023-01-23 02:05:35.566375: step: 928/533, loss: 0.16270485520362854
2023-01-23 02:05:36.718002: step: 932/533, loss: 0.002553558209910989
2023-01-23 02:05:37.910190: step: 936/533, loss: 0.20938794314861298
2023-01-23 02:05:39.060470: step: 940/533, loss: 0.044144246727228165
2023-01-23 02:05:40.223714: step: 944/533, loss: 0.0159467700868845
2023-01-23 02:05:41.428665: step: 948/533, loss: 0.12271471321582794
2023-01-23 02:05:42.596826: step: 952/533, loss: 0.005106735043227673
2023-01-23 02:05:43.810649: step: 956/533, loss: 0.08501043170690536
2023-01-23 02:05:44.976070: step: 960/533, loss: 0.082502081990242
2023-01-23 02:05:46.142054: step: 964/533, loss: 0.02762739732861519
2023-01-23 02:05:47.334889: step: 968/533, loss: 0.02583923563361168
2023-01-23 02:05:48.557298: step: 972/533, loss: 0.33078011870384216
2023-01-23 02:05:49.768678: step: 976/533, loss: 0.008112717419862747
2023-01-23 02:05:50.929315: step: 980/533, loss: 0.07246056199073792
2023-01-23 02:05:52.075460: step: 984/533, loss: 0.011728477664291859
2023-01-23 02:05:53.264705: step: 988/533, loss: 0.0017777920002117753
2023-01-23 02:05:54.471077: step: 992/533, loss: 0.07626251876354218
2023-01-23 02:05:55.659386: step: 996/533, loss: 0.01080942153930664
2023-01-23 02:05:56.807782: step: 1000/533, loss: 0.10545816272497177
2023-01-23 02:05:57.998107: step: 1004/533, loss: 0.005780220031738281
2023-01-23 02:05:59.197553: step: 1008/533, loss: 0.03603062778711319
2023-01-23 02:06:00.371100: step: 1012/533, loss: 0.07141857594251633
2023-01-23 02:06:01.531671: step: 1016/533, loss: 0.031074905768036842
2023-01-23 02:06:02.710485: step: 1020/533, loss: 0.0625300407409668
2023-01-23 02:06:03.907629: step: 1024/533, loss: 0.0076808929443359375
2023-01-23 02:06:05.089093: step: 1028/533, loss: 0.04914788901805878
2023-01-23 02:06:06.235263: step: 1032/533, loss: 0.0006085395580157638
2023-01-23 02:06:07.458326: step: 1036/533, loss: 0.0002342224179301411
2023-01-23 02:06:08.642546: step: 1040/533, loss: 0.08393802493810654
2023-01-23 02:06:09.785349: step: 1044/533, loss: 0.03736257553100586
2023-01-23 02:06:10.975120: step: 1048/533, loss: 0.013930320739746094
2023-01-23 02:06:12.106169: step: 1052/533, loss: 0.04577846825122833
2023-01-23 02:06:13.257070: step: 1056/533, loss: 0.00041623116703704
2023-01-23 02:06:14.423062: step: 1060/533, loss: 0.06527204811573029
2023-01-23 02:06:15.591095: step: 1064/533, loss: 0.005023288540542126
2023-01-23 02:06:16.748499: step: 1068/533, loss: 0.0074495794251561165
2023-01-23 02:06:17.955343: step: 1072/533, loss: 0.05359682813286781
2023-01-23 02:06:19.132839: step: 1076/533, loss: 0.03528108820319176
2023-01-23 02:06:20.301124: step: 1080/533, loss: 0.0033839941024780273
2023-01-23 02:06:21.482412: step: 1084/533, loss: 0.03252124786376953
2023-01-23 02:06:22.685019: step: 1088/533, loss: 0.030231047421693802
2023-01-23 02:06:23.859469: step: 1092/533, loss: 0.09924106299877167
2023-01-23 02:06:25.064225: step: 1096/533, loss: 0.005743694491684437
2023-01-23 02:06:26.249503: step: 1100/533, loss: 0.0025201798416674137
2023-01-23 02:06:27.399579: step: 1104/533, loss: 0.015850067138671875
2023-01-23 02:06:28.554859: step: 1108/533, loss: 0.021021222695708275
2023-01-23 02:06:29.720066: step: 1112/533, loss: 0.08223210275173187
2023-01-23 02:06:30.900473: step: 1116/533, loss: 0.0052163125947117805
2023-01-23 02:06:32.048009: step: 1120/533, loss: 0.014155101962387562
2023-01-23 02:06:33.212994: step: 1124/533, loss: 0.020010948181152344
2023-01-23 02:06:34.371959: step: 1128/533, loss: 0.04718637838959694
2023-01-23 02:06:35.523432: step: 1132/533, loss: 0.012091445736587048
2023-01-23 02:06:36.696661: step: 1136/533, loss: 0.06243286281824112
2023-01-23 02:06:37.849588: step: 1140/533, loss: 0.03770342096686363
2023-01-23 02:06:39.011608: step: 1144/533, loss: 0.0015277862548828125
2023-01-23 02:06:40.225128: step: 1148/533, loss: 0.07014961540699005
2023-01-23 02:06:41.399975: step: 1152/533, loss: 0.032598257064819336
2023-01-23 02:06:42.548853: step: 1156/533, loss: 0.11392717063426971
2023-01-23 02:06:43.700900: step: 1160/533, loss: 0.002681923098862171
2023-01-23 02:06:44.874563: step: 1164/533, loss: 0.0587984099984169
2023-01-23 02:06:46.063208: step: 1168/533, loss: 0.019454097375273705
2023-01-23 02:06:47.224525: step: 1172/533, loss: 0.004249954130500555
2023-01-23 02:06:48.373241: step: 1176/533, loss: 0.08586225658655167
2023-01-23 02:06:49.569030: step: 1180/533, loss: 0.04163970798254013
2023-01-23 02:06:50.751343: step: 1184/533, loss: 0.013718700036406517
2023-01-23 02:06:51.943194: step: 1188/533, loss: 0.035169318318367004
2023-01-23 02:06:53.105801: step: 1192/533, loss: 0.018397999927401543
2023-01-23 02:06:54.300748: step: 1196/533, loss: 0.09522581100463867
2023-01-23 02:06:55.513099: step: 1200/533, loss: 0.003457868006080389
2023-01-23 02:06:56.683907: step: 1204/533, loss: 0.02933807298541069
2023-01-23 02:06:57.881824: step: 1208/533, loss: 0.06172552332282066
2023-01-23 02:06:59.079103: step: 1212/533, loss: 0.026673413813114166
2023-01-23 02:07:00.238127: step: 1216/533, loss: 0.003959846682846546
2023-01-23 02:07:01.411399: step: 1220/533, loss: 0.0015020370483398438
2023-01-23 02:07:02.583821: step: 1224/533, loss: 0.0026490213349461555
2023-01-23 02:07:03.767120: step: 1228/533, loss: 0.0009955406421795487
2023-01-23 02:07:04.928300: step: 1232/533, loss: 0.0056493766605854034
2023-01-23 02:07:06.118272: step: 1236/533, loss: 0.008498001843690872
2023-01-23 02:07:07.293844: step: 1240/533, loss: 0.028267955407500267
2023-01-23 02:07:08.538893: step: 1244/533, loss: 0.24183063209056854
2023-01-23 02:07:09.716727: step: 1248/533, loss: 0.07068081200122833
2023-01-23 02:07:10.926759: step: 1252/533, loss: 0.0030951499938964844
2023-01-23 02:07:12.145844: step: 1256/533, loss: 0.08301430195569992
2023-01-23 02:07:13.307258: step: 1260/533, loss: 0.025484465062618256
2023-01-23 02:07:14.503545: step: 1264/533, loss: 0.05164022371172905
2023-01-23 02:07:15.698222: step: 1268/533, loss: 0.12735433876514435
2023-01-23 02:07:16.893425: step: 1272/533, loss: 0.042942240834236145
2023-01-23 02:07:18.118661: step: 1276/533, loss: 0.043050576001405716
2023-01-23 02:07:19.319305: step: 1280/533, loss: 0.02764721028506756
2023-01-23 02:07:20.516307: step: 1284/533, loss: 0.08372178673744202
2023-01-23 02:07:21.675873: step: 1288/533, loss: 0.22312016785144806
2023-01-23 02:07:22.856089: step: 1292/533, loss: 0.0036039352416992188
2023-01-23 02:07:24.046586: step: 1296/533, loss: 0.0007527351845055819
2023-01-23 02:07:25.257936: step: 1300/533, loss: 0.04929714277386665
2023-01-23 02:07:26.407632: step: 1304/533, loss: 0.005889320746064186
2023-01-23 02:07:27.593430: step: 1308/533, loss: 0.014123249799013138
2023-01-23 02:07:28.730904: step: 1312/533, loss: 0.00188446044921875
2023-01-23 02:07:29.901607: step: 1316/533, loss: 0.0700952559709549
2023-01-23 02:07:31.069902: step: 1320/533, loss: 0.04431352764368057
2023-01-23 02:07:32.303619: step: 1324/533, loss: 0.003768348600715399
2023-01-23 02:07:33.482797: step: 1328/533, loss: 0.18981055915355682
2023-01-23 02:07:34.745965: step: 1332/533, loss: 0.09900808334350586
2023-01-23 02:07:35.943380: step: 1336/533, loss: 0.0039764405228197575
2023-01-23 02:07:37.134168: step: 1340/533, loss: 0.022089386358857155
2023-01-23 02:07:38.383916: step: 1344/533, loss: 0.0007393836858682334
2023-01-23 02:07:39.590541: step: 1348/533, loss: 0.1096283420920372
2023-01-23 02:07:40.777388: step: 1352/533, loss: 0.03020324744284153
2023-01-23 02:07:41.960835: step: 1356/533, loss: 0.07181215286254883
2023-01-23 02:07:43.156472: step: 1360/533, loss: 0.03059682995080948
2023-01-23 02:07:44.326674: step: 1364/533, loss: 0.00811699591577053
2023-01-23 02:07:45.504073: step: 1368/533, loss: 0.0016086578834801912
2023-01-23 02:07:46.703664: step: 1372/533, loss: 0.16164740920066833
2023-01-23 02:07:47.873653: step: 1376/533, loss: 0.0023539543617516756
2023-01-23 02:07:49.038976: step: 1380/533, loss: 0.06281928718090057
2023-01-23 02:07:50.210518: step: 1384/533, loss: 0.019055986776947975
2023-01-23 02:07:51.434251: step: 1388/533, loss: 0.0008141517755575478
2023-01-23 02:07:52.604418: step: 1392/533, loss: 0.024837160483002663
2023-01-23 02:07:53.746750: step: 1396/533, loss: 0.031973838806152344
2023-01-23 02:07:54.895902: step: 1400/533, loss: 0.020502157509326935
2023-01-23 02:07:56.072967: step: 1404/533, loss: 0.01667661778628826
2023-01-23 02:07:57.250309: step: 1408/533, loss: 0.0005800724611617625
2023-01-23 02:07:58.441524: step: 1412/533, loss: 0.1979566514492035
2023-01-23 02:07:59.593456: step: 1416/533, loss: 0.03205595165491104
2023-01-23 02:08:00.772991: step: 1420/533, loss: 0.00010177493095397949
2023-01-23 02:08:02.017712: step: 1424/533, loss: 0.03745689615607262
2023-01-23 02:08:03.212473: step: 1428/533, loss: 0.0004849433898925781
2023-01-23 02:08:04.417399: step: 1432/533, loss: 0.012656641192734241
2023-01-23 02:08:05.567871: step: 1436/533, loss: 0.4612763524055481
2023-01-23 02:08:06.734216: step: 1440/533, loss: 0.0041783335618674755
2023-01-23 02:08:07.898948: step: 1444/533, loss: 0.0037330626510083675
2023-01-23 02:08:09.074856: step: 1448/533, loss: 0.07242584228515625
2023-01-23 02:08:10.297570: step: 1452/533, loss: 0.07093124091625214
2023-01-23 02:08:11.452258: step: 1456/533, loss: 0.040244292467832565
2023-01-23 02:08:12.632337: step: 1460/533, loss: 0.024210548028349876
2023-01-23 02:08:13.795088: step: 1464/533, loss: 0.0807284340262413
2023-01-23 02:08:15.006235: step: 1468/533, loss: 0.010180473327636719
2023-01-23 02:08:16.180832: step: 1472/533, loss: 0.04467420652508736
2023-01-23 02:08:17.359473: step: 1476/533, loss: 0.05566120147705078
2023-01-23 02:08:18.524516: step: 1480/533, loss: 0.03325071558356285
2023-01-23 02:08:19.714474: step: 1484/533, loss: 0.04644813388586044
2023-01-23 02:08:20.956734: step: 1488/533, loss: 0.006442260928452015
2023-01-23 02:08:22.190601: step: 1492/533, loss: 0.04137783125042915
2023-01-23 02:08:23.377879: step: 1496/533, loss: 0.002364254090934992
2023-01-23 02:08:24.540514: step: 1500/533, loss: 0.012958860956132412
2023-01-23 02:08:25.711859: step: 1504/533, loss: 0.032246969640254974
2023-01-23 02:08:26.857330: step: 1508/533, loss: 0.012474918738007545
2023-01-23 02:08:28.032927: step: 1512/533, loss: 0.005384350195527077
2023-01-23 02:08:29.246513: step: 1516/533, loss: 0.021234415471553802
2023-01-23 02:08:30.372609: step: 1520/533, loss: 0.0019318581325933337
2023-01-23 02:08:31.552573: step: 1524/533, loss: 0.10267606377601624
2023-01-23 02:08:32.737919: step: 1528/533, loss: 0.03939533233642578
2023-01-23 02:08:33.948239: step: 1532/533, loss: 0.012689972296357155
2023-01-23 02:08:35.168979: step: 1536/533, loss: 0.0326385498046875
2023-01-23 02:08:36.363195: step: 1540/533, loss: 0.009597301483154297
2023-01-23 02:08:37.522476: step: 1544/533, loss: 0.0153534896671772
2023-01-23 02:08:38.668291: step: 1548/533, loss: 0.09442967921495438
2023-01-23 02:08:39.831761: step: 1552/533, loss: 0.02636394463479519
2023-01-23 02:08:40.983439: step: 1556/533, loss: 0.008846051059663296
2023-01-23 02:08:42.150680: step: 1560/533, loss: 0.018706750124692917
2023-01-23 02:08:43.310073: step: 1564/533, loss: 0.04613618552684784
2023-01-23 02:08:44.473656: step: 1568/533, loss: 0.012685585767030716
2023-01-23 02:08:45.644810: step: 1572/533, loss: 0.02436218224465847
2023-01-23 02:08:46.806231: step: 1576/533, loss: 0.03539569675922394
2023-01-23 02:08:47.999843: step: 1580/533, loss: 0.0009920119773596525
2023-01-23 02:08:49.184915: step: 1584/533, loss: 0.009822189807891846
2023-01-23 02:08:50.339537: step: 1588/533, loss: 0.0009979248279705644
2023-01-23 02:08:51.524835: step: 1592/533, loss: 0.045466091483831406
2023-01-23 02:08:52.739887: step: 1596/533, loss: 0.0031791210640221834
2023-01-23 02:08:53.902224: step: 1600/533, loss: 0.14055366814136505
2023-01-23 02:08:55.066120: step: 1604/533, loss: 0.034258175641298294
2023-01-23 02:08:56.204583: step: 1608/533, loss: 0.04239988327026367
2023-01-23 02:08:57.367045: step: 1612/533, loss: 0.016264747828245163
2023-01-23 02:08:58.527277: step: 1616/533, loss: 0.262167751789093
2023-01-23 02:08:59.695384: step: 1620/533, loss: 0.0024843215942382812
2023-01-23 02:09:00.870843: step: 1624/533, loss: 0.025490522384643555
2023-01-23 02:09:02.035809: step: 1628/533, loss: 0.060387518256902695
2023-01-23 02:09:03.196567: step: 1632/533, loss: 0.004184436984360218
2023-01-23 02:09:04.359199: step: 1636/533, loss: 0.004380142781883478
2023-01-23 02:09:05.564238: step: 1640/533, loss: 0.00661888113245368
2023-01-23 02:09:06.728793: step: 1644/533, loss: 0.0020897863432765007
2023-01-23 02:09:07.942831: step: 1648/533, loss: 0.12932910025119781
2023-01-23 02:09:09.100090: step: 1652/533, loss: 0.0013526440598070621
2023-01-23 02:09:10.268206: step: 1656/533, loss: 0.005809688940644264
2023-01-23 02:09:11.433002: step: 1660/533, loss: 0.0036900995764881372
2023-01-23 02:09:12.623234: step: 1664/533, loss: 0.03878364711999893
2023-01-23 02:09:13.807905: step: 1668/533, loss: 0.0022054819855839014
2023-01-23 02:09:14.975812: step: 1672/533, loss: 0.03097858466207981
2023-01-23 02:09:16.202942: step: 1676/533, loss: 0.04583339765667915
2023-01-23 02:09:17.439701: step: 1680/533, loss: 0.04856610298156738
2023-01-23 02:09:18.589003: step: 1684/533, loss: 0.1337287873029709
2023-01-23 02:09:19.758152: step: 1688/533, loss: 0.015915585681796074
2023-01-23 02:09:20.969860: step: 1692/533, loss: 0.01108570210635662
2023-01-23 02:09:22.132440: step: 1696/533, loss: 0.003035640809684992
2023-01-23 02:09:23.277533: step: 1700/533, loss: 0.04025306925177574
2023-01-23 02:09:24.433808: step: 1704/533, loss: 0.0033143043983727694
2023-01-23 02:09:25.605054: step: 1708/533, loss: 0.012143706902861595
2023-01-23 02:09:26.784666: step: 1712/533, loss: 0.0008431434980593622
2023-01-23 02:09:27.928526: step: 1716/533, loss: 0.00021071435185149312
2023-01-23 02:09:29.097221: step: 1720/533, loss: 0.04438972845673561
2023-01-23 02:09:30.301137: step: 1724/533, loss: 0.10260956734418869
2023-01-23 02:09:31.472010: step: 1728/533, loss: 0.003399467561393976
2023-01-23 02:09:32.664189: step: 1732/533, loss: 0.03218822553753853
2023-01-23 02:09:33.853728: step: 1736/533, loss: 0.013613224029541016
2023-01-23 02:09:35.065130: step: 1740/533, loss: 0.023714255541563034
2023-01-23 02:09:36.223085: step: 1744/533, loss: 0.013700771145522594
2023-01-23 02:09:37.425019: step: 1748/533, loss: 0.026090431958436966
2023-01-23 02:09:38.590421: step: 1752/533, loss: 0.004889106843620539
2023-01-23 02:09:39.763006: step: 1756/533, loss: 0.01535043679177761
2023-01-23 02:09:40.916104: step: 1760/533, loss: 0.010417843237519264
2023-01-23 02:09:42.109004: step: 1764/533, loss: 0.07286892831325531
2023-01-23 02:09:43.302874: step: 1768/533, loss: 0.05481967702507973
2023-01-23 02:09:44.456188: step: 1772/533, loss: 0.05034580081701279
2023-01-23 02:09:45.665062: step: 1776/533, loss: 0.012636279687285423
2023-01-23 02:09:46.867615: step: 1780/533, loss: 0.021080780774354935
2023-01-23 02:09:48.034526: step: 1784/533, loss: 0.009203148074448109
2023-01-23 02:09:49.220325: step: 1788/533, loss: 0.02357616275548935
2023-01-23 02:09:50.377142: step: 1792/533, loss: 0.020754529163241386
2023-01-23 02:09:51.583745: step: 1796/533, loss: 0.012844180688261986
2023-01-23 02:09:52.877079: step: 1800/533, loss: 0.0021793365012854338
2023-01-23 02:09:54.032434: step: 1804/533, loss: 0.013502311892807484
2023-01-23 02:09:55.283102: step: 1808/533, loss: 0.02083413116633892
2023-01-23 02:09:56.465685: step: 1812/533, loss: 0.006758308503776789
2023-01-23 02:09:57.690164: step: 1816/533, loss: 0.08245468139648438
2023-01-23 02:09:58.871705: step: 1820/533, loss: 0.029354475438594818
2023-01-23 02:10:00.091690: step: 1824/533, loss: 0.01232290267944336
2023-01-23 02:10:01.299104: step: 1828/533, loss: 0.08789655566215515
2023-01-23 02:10:02.509355: step: 1832/533, loss: 0.05191917344927788
2023-01-23 02:10:03.705043: step: 1836/533, loss: 0.015374278649687767
2023-01-23 02:10:04.862422: step: 1840/533, loss: 0.031821396201848984
2023-01-23 02:10:06.055955: step: 1844/533, loss: 0.005908298306167126
2023-01-23 02:10:07.235567: step: 1848/533, loss: 0.05773887783288956
2023-01-23 02:10:08.408291: step: 1852/533, loss: 0.004272079560905695
2023-01-23 02:10:09.603595: step: 1856/533, loss: 0.23922786116600037
2023-01-23 02:10:10.822198: step: 1860/533, loss: 0.05212083086371422
2023-01-23 02:10:11.985145: step: 1864/533, loss: 0.06520719826221466
2023-01-23 02:10:13.217928: step: 1868/533, loss: 0.07926884293556213
2023-01-23 02:10:14.428225: step: 1872/533, loss: 0.014132505282759666
2023-01-23 02:10:15.665132: step: 1876/533, loss: 0.015330505557358265
2023-01-23 02:10:16.869835: step: 1880/533, loss: 0.023017311468720436
2023-01-23 02:10:18.058328: step: 1884/533, loss: 0.018812984228134155
2023-01-23 02:10:19.220014: step: 1888/533, loss: 0.014664220623672009
2023-01-23 02:10:20.454984: step: 1892/533, loss: 0.0025262832641601562
2023-01-23 02:10:21.694795: step: 1896/533, loss: 0.0036348344292491674
2023-01-23 02:10:22.889477: step: 1900/533, loss: 0.058869458734989166
2023-01-23 02:10:24.089591: step: 1904/533, loss: 0.05035886913537979
2023-01-23 02:10:25.295463: step: 1908/533, loss: 0.01423492468893528
2023-01-23 02:10:26.445135: step: 1912/533, loss: 0.00346794119104743
2023-01-23 02:10:27.633849: step: 1916/533, loss: 0.0018219948979094625
2023-01-23 02:10:28.889377: step: 1920/533, loss: 0.0005479812971316278
2023-01-23 02:10:30.083889: step: 1924/533, loss: 0.07553939521312714
2023-01-23 02:10:31.269544: step: 1928/533, loss: 0.017013169825077057
2023-01-23 02:10:32.439220: step: 1932/533, loss: 0.011327933520078659
2023-01-23 02:10:33.675818: step: 1936/533, loss: 0.07743445038795471
2023-01-23 02:10:34.894879: step: 1940/533, loss: 0.12663136422634125
2023-01-23 02:10:36.088881: step: 1944/533, loss: 0.009558677673339844
2023-01-23 02:10:37.330152: step: 1948/533, loss: 0.03538475185632706
2023-01-23 02:10:38.488181: step: 1952/533, loss: 0.0012446403270587325
2023-01-23 02:10:39.719409: step: 1956/533, loss: 0.025933455675840378
2023-01-23 02:10:40.912835: step: 1960/533, loss: 0.0037683488335460424
2023-01-23 02:10:42.084388: step: 1964/533, loss: 0.023306941613554955
2023-01-23 02:10:43.202367: step: 1968/533, loss: 0.010752391070127487
2023-01-23 02:10:44.403841: step: 1972/533, loss: 0.004403495695441961
2023-01-23 02:10:45.599710: step: 1976/533, loss: 0.021851349622011185
2023-01-23 02:10:46.798505: step: 1980/533, loss: 0.022672273218631744
2023-01-23 02:10:48.024369: step: 1984/533, loss: 0.0005634308326989412
2023-01-23 02:10:49.211854: step: 1988/533, loss: 0.02189350128173828
2023-01-23 02:10:50.422445: step: 1992/533, loss: 0.00907678622752428
2023-01-23 02:10:51.647236: step: 1996/533, loss: 0.06172523647546768
2023-01-23 02:10:52.834867: step: 2000/533, loss: 0.04457101970911026
2023-01-23 02:10:54.069891: step: 2004/533, loss: 0.058938220143318176
2023-01-23 02:10:55.244130: step: 2008/533, loss: 0.0027115345001220703
2023-01-23 02:10:56.452659: step: 2012/533, loss: 0.08951206505298615
2023-01-23 02:10:57.603044: step: 2016/533, loss: 0.005914401728659868
2023-01-23 02:10:58.800573: step: 2020/533, loss: 0.024036791175603867
2023-01-23 02:11:00.004283: step: 2024/533, loss: 0.07169260829687119
2023-01-23 02:11:01.152782: step: 2028/533, loss: 0.02427082136273384
2023-01-23 02:11:02.300481: step: 2032/533, loss: 0.09004479646682739
2023-01-23 02:11:03.511345: step: 2036/533, loss: 0.011097240261733532
2023-01-23 02:11:04.735928: step: 2040/533, loss: 0.015466880984604359
2023-01-23 02:11:05.900316: step: 2044/533, loss: 0.0009699821239337325
2023-01-23 02:11:07.109670: step: 2048/533, loss: 0.022615719586610794
2023-01-23 02:11:08.315349: step: 2052/533, loss: 0.02037983015179634
2023-01-23 02:11:09.495897: step: 2056/533, loss: 0.025789640843868256
2023-01-23 02:11:10.685001: step: 2060/533, loss: 0.03392486646771431
2023-01-23 02:11:11.851317: step: 2064/533, loss: 0.08136949688196182
2023-01-23 02:11:13.018837: step: 2068/533, loss: 0.024516774341464043
2023-01-23 02:11:14.184164: step: 2072/533, loss: 0.007665443699806929
2023-01-23 02:11:15.375719: step: 2076/533, loss: 0.02284068986773491
2023-01-23 02:11:16.552718: step: 2080/533, loss: 0.007357692811638117
2023-01-23 02:11:17.709287: step: 2084/533, loss: 0.00414619455114007
2023-01-23 02:11:18.871739: step: 2088/533, loss: 0.017296601086854935
2023-01-23 02:11:20.043416: step: 2092/533, loss: 0.008288383483886719
2023-01-23 02:11:21.209309: step: 2096/533, loss: 0.024480629712343216
2023-01-23 02:11:22.377414: step: 2100/533, loss: 0.062108803540468216
2023-01-23 02:11:23.597373: step: 2104/533, loss: 0.05815162882208824
2023-01-23 02:11:24.788537: step: 2108/533, loss: 0.023702431470155716
2023-01-23 02:11:25.930069: step: 2112/533, loss: 0.01562356948852539
2023-01-23 02:11:27.105670: step: 2116/533, loss: 0.0021365166176110506
2023-01-23 02:11:28.268043: step: 2120/533, loss: 0.06192522495985031
2023-01-23 02:11:29.428197: step: 2124/533, loss: 0.042099762707948685
2023-01-23 02:11:30.621323: step: 2128/533, loss: 0.014585400000214577
2023-01-23 02:11:31.805353: step: 2132/533, loss: 0.03098588064312935
==================================================
Loss: 0.046
--------------------
Dev: {'event': {'p': 0.6091954022988506, 'r': 0.7762982689747004, 'f1': 0.6826697892271664}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6437185929648241, 'r': 0.8190537084398977, 'f1': 0.7208778840742824}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5813953488372093, 'r': 0.9259259259259259, 'f1': 0.7142857142857142}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.6, 'r': 0.5238095238095238, 'f1': 0.559322033898305}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.5, 'r': 0.6111111111111112, 'f1': 0.55}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:12:13.578128: step: 4/533, loss: 0.032935142517089844
2023-01-23 02:12:14.789543: step: 8/533, loss: 0.20816020667552948
2023-01-23 02:12:15.951158: step: 12/533, loss: 0.010228538885712624
2023-01-23 02:12:17.124598: step: 16/533, loss: 0.00011982917931163684
2023-01-23 02:12:18.305159: step: 20/533, loss: 0.05382366105914116
2023-01-23 02:12:19.507206: step: 24/533, loss: 0.024899769574403763
2023-01-23 02:12:20.679712: step: 28/533, loss: 0.012189102359116077
2023-01-23 02:12:21.882142: step: 32/533, loss: 0.014241504482924938
2023-01-23 02:12:23.099409: step: 36/533, loss: 0.037456318736076355
2023-01-23 02:12:24.291151: step: 40/533, loss: 0.00794839859008789
2023-01-23 02:12:25.487174: step: 44/533, loss: 0.012491417117416859
2023-01-23 02:12:26.651097: step: 48/533, loss: 0.012137413024902344
2023-01-23 02:12:27.827080: step: 52/533, loss: 0.006480109877884388
2023-01-23 02:12:29.040210: step: 56/533, loss: 0.0018396377563476562
2023-01-23 02:12:30.218811: step: 60/533, loss: 0.03527842089533806
2023-01-23 02:12:31.368469: step: 64/533, loss: 0.028742078691720963
2023-01-23 02:12:32.581611: step: 68/533, loss: 0.0031180381774902344
2023-01-23 02:12:33.762326: step: 72/533, loss: 0.007898425683379173
2023-01-23 02:12:34.936394: step: 76/533, loss: 0.01277923583984375
2023-01-23 02:12:36.082952: step: 80/533, loss: 0.013762188144028187
2023-01-23 02:12:37.246231: step: 84/533, loss: 0.00080957415048033
2023-01-23 02:12:38.430653: step: 88/533, loss: 0.004513836000114679
2023-01-23 02:12:39.632328: step: 92/533, loss: 0.006750058848410845
2023-01-23 02:12:40.806338: step: 96/533, loss: 0.0025457381270825863
2023-01-23 02:12:41.962664: step: 100/533, loss: 0.01690845564007759
2023-01-23 02:12:43.136402: step: 104/533, loss: 0.00952682550996542
2023-01-23 02:12:44.374294: step: 108/533, loss: 0.5799604654312134
2023-01-23 02:12:45.595811: step: 112/533, loss: 0.027771949768066406
2023-01-23 02:12:46.756726: step: 116/533, loss: 0.01718606986105442
2023-01-23 02:12:47.935316: step: 120/533, loss: 0.014300156384706497
2023-01-23 02:12:49.094286: step: 124/533, loss: 0.029419898986816406
2023-01-23 02:12:50.273699: step: 128/533, loss: 0.00897455308586359
2023-01-23 02:12:51.454900: step: 132/533, loss: 0.025732040405273438
2023-01-23 02:12:52.668414: step: 136/533, loss: 0.021947670727968216
2023-01-23 02:12:53.841027: step: 140/533, loss: 0.08651962131261826
2023-01-23 02:12:55.085226: step: 144/533, loss: 0.11216086894273758
2023-01-23 02:12:56.274147: step: 148/533, loss: 0.03270130231976509
2023-01-23 02:12:57.411510: step: 152/533, loss: 0.006653499323874712
2023-01-23 02:12:58.594472: step: 156/533, loss: 0.04458275064826012
2023-01-23 02:12:59.740027: step: 160/533, loss: 0.0029197693802416325
2023-01-23 02:13:00.976659: step: 164/533, loss: 0.00010404587374068797
2023-01-23 02:13:02.147286: step: 168/533, loss: 0.006921195890754461
2023-01-23 02:13:03.344730: step: 172/533, loss: 0.015159130096435547
2023-01-23 02:13:04.561579: step: 176/533, loss: 0.053437136113643646
2023-01-23 02:13:05.767243: step: 180/533, loss: 0.010609244927763939
2023-01-23 02:13:06.918752: step: 184/533, loss: 0.00041809084359556437
2023-01-23 02:13:08.121993: step: 188/533, loss: 0.06620364636182785
2023-01-23 02:13:09.345041: step: 192/533, loss: 0.03919067233800888
2023-01-23 02:13:10.557230: step: 196/533, loss: 0.008757306262850761
2023-01-23 02:13:11.712455: step: 200/533, loss: 0.0003612518194131553
2023-01-23 02:13:12.886572: step: 204/533, loss: 0.05581951141357422
2023-01-23 02:13:14.076254: step: 208/533, loss: 0.0005365372053347528
2023-01-23 02:13:15.288094: step: 212/533, loss: 0.0021191597916185856
2023-01-23 02:13:16.472236: step: 216/533, loss: 0.0073677063919603825
2023-01-23 02:13:17.653539: step: 220/533, loss: 0.023686980828642845
2023-01-23 02:13:18.825670: step: 224/533, loss: 0.04401359707117081
2023-01-23 02:13:20.054889: step: 228/533, loss: 0.005532217212021351
2023-01-23 02:13:21.227806: step: 232/533, loss: 0.024250458925962448
2023-01-23 02:13:22.397290: step: 236/533, loss: 0.032639503479003906
2023-01-23 02:13:23.597591: step: 240/533, loss: 0.04319038614630699
2023-01-23 02:13:24.730559: step: 244/533, loss: 0.004134106449782848
2023-01-23 02:13:25.920110: step: 248/533, loss: 0.0012115002609789371
2023-01-23 02:13:27.136218: step: 252/533, loss: 0.08519001305103302
2023-01-23 02:13:28.326157: step: 256/533, loss: 0.022072412073612213
2023-01-23 02:13:29.564396: step: 260/533, loss: 0.024069691076874733
2023-01-23 02:13:30.751085: step: 264/533, loss: 0.02736072614789009
2023-01-23 02:13:31.999105: step: 268/533, loss: 0.03606872260570526
2023-01-23 02:13:33.206705: step: 272/533, loss: 0.04927101358771324
2023-01-23 02:13:34.377585: step: 276/533, loss: 0.0025703429710119963
2023-01-23 02:13:35.547106: step: 280/533, loss: 0.12955741584300995
2023-01-23 02:13:36.742175: step: 284/533, loss: 0.01866474188864231
2023-01-23 02:13:37.914877: step: 288/533, loss: 0.009340954013168812
2023-01-23 02:13:39.112838: step: 292/533, loss: 0.01603412628173828
2023-01-23 02:13:40.322240: step: 296/533, loss: 0.022847937420010567
2023-01-23 02:13:41.478322: step: 300/533, loss: 0.037826765328645706
2023-01-23 02:13:42.672294: step: 304/533, loss: 0.0024423152208328247
2023-01-23 02:13:43.870727: step: 308/533, loss: 0.04450559616088867
2023-01-23 02:13:45.066839: step: 312/533, loss: 0.05001239851117134
2023-01-23 02:13:46.246341: step: 316/533, loss: 0.0037585259415209293
2023-01-23 02:13:47.428319: step: 320/533, loss: 0.013702106662094593
2023-01-23 02:13:48.624030: step: 324/533, loss: 0.004167270381003618
2023-01-23 02:13:49.809826: step: 328/533, loss: 0.026240825653076172
2023-01-23 02:13:51.016851: step: 332/533, loss: 0.006727981381118298
2023-01-23 02:13:52.214169: step: 336/533, loss: 0.04866666719317436
2023-01-23 02:13:53.383880: step: 340/533, loss: 0.04574894905090332
2023-01-23 02:13:54.551537: step: 344/533, loss: 0.05682888254523277
2023-01-23 02:13:55.733631: step: 348/533, loss: 0.04966564103960991
2023-01-23 02:13:56.940454: step: 352/533, loss: 0.012169087305665016
2023-01-23 02:13:58.092016: step: 356/533, loss: 0.05115833133459091
2023-01-23 02:13:59.224796: step: 360/533, loss: 0.003943538758903742
2023-01-23 02:14:00.395076: step: 364/533, loss: 0.010458231903612614
2023-01-23 02:14:01.543331: step: 368/533, loss: 0.029062747955322266
2023-01-23 02:14:02.728889: step: 372/533, loss: 0.08163433521986008
2023-01-23 02:14:03.911967: step: 376/533, loss: 0.003917217254638672
2023-01-23 02:14:05.125634: step: 380/533, loss: 0.043286897242069244
2023-01-23 02:14:06.359744: step: 384/533, loss: 0.0018850326305255294
2023-01-23 02:14:07.564947: step: 388/533, loss: 0.00558547955006361
2023-01-23 02:14:08.727037: step: 392/533, loss: 0.011851501651108265
2023-01-23 02:14:09.923190: step: 396/533, loss: 0.006362342741340399
2023-01-23 02:14:11.052109: step: 400/533, loss: 0.13735751807689667
2023-01-23 02:14:12.263828: step: 404/533, loss: 0.05071859061717987
2023-01-23 02:14:13.414786: step: 408/533, loss: 0.01619955338537693
2023-01-23 02:14:14.593740: step: 412/533, loss: 0.019878387451171875
2023-01-23 02:14:15.808544: step: 416/533, loss: 0.052910711616277695
2023-01-23 02:14:16.961749: step: 420/533, loss: 0.00669331569224596
2023-01-23 02:14:18.153618: step: 424/533, loss: 0.026935769245028496
2023-01-23 02:14:19.324153: step: 428/533, loss: 0.0018197059398517013
2023-01-23 02:14:20.515775: step: 432/533, loss: 0.5512388348579407
2023-01-23 02:14:21.681445: step: 436/533, loss: 0.0006567001692019403
2023-01-23 02:14:22.844400: step: 440/533, loss: 0.022025395184755325
2023-01-23 02:14:24.021601: step: 444/533, loss: 0.004497576039284468
2023-01-23 02:14:25.205474: step: 448/533, loss: 0.006063556764274836
2023-01-23 02:14:26.389426: step: 452/533, loss: 0.23575058579444885
2023-01-23 02:14:27.564102: step: 456/533, loss: 0.020454170182347298
2023-01-23 02:14:28.755548: step: 460/533, loss: 0.011699771508574486
2023-01-23 02:14:29.922586: step: 464/533, loss: 0.01693134382367134
2023-01-23 02:14:31.096809: step: 468/533, loss: 0.01447305642068386
2023-01-23 02:14:32.242410: step: 472/533, loss: 0.00260753626935184
2023-01-23 02:14:33.427761: step: 476/533, loss: 0.006367969326674938
2023-01-23 02:14:34.694747: step: 480/533, loss: 0.0010057449107989669
2023-01-23 02:14:35.937653: step: 484/533, loss: 0.001689910888671875
2023-01-23 02:14:37.114822: step: 488/533, loss: 0.0008909225580282509
2023-01-23 02:14:38.272508: step: 492/533, loss: 0.03721008449792862
2023-01-23 02:14:39.497166: step: 496/533, loss: 0.0230318084359169
2023-01-23 02:14:40.700655: step: 500/533, loss: 0.02500610426068306
2023-01-23 02:14:41.918753: step: 504/533, loss: 0.011840629391372204
2023-01-23 02:14:43.099261: step: 508/533, loss: 0.0052495962008833885
2023-01-23 02:14:44.260089: step: 512/533, loss: 0.0015333176124840975
2023-01-23 02:14:45.451456: step: 516/533, loss: 0.0017180442810058594
2023-01-23 02:14:46.659049: step: 520/533, loss: 0.00868835486471653
2023-01-23 02:14:47.845744: step: 524/533, loss: 0.09515104442834854
2023-01-23 02:14:49.036238: step: 528/533, loss: 0.051025390625
2023-01-23 02:14:50.185794: step: 532/533, loss: 0.005434084217995405
2023-01-23 02:14:51.382634: step: 536/533, loss: 0.026868535205721855
2023-01-23 02:14:52.572833: step: 540/533, loss: 0.035859107971191406
2023-01-23 02:14:53.793474: step: 544/533, loss: 0.06793337315320969
2023-01-23 02:14:54.971325: step: 548/533, loss: 0.021899700164794922
2023-01-23 02:14:56.164886: step: 552/533, loss: 0.5063167810440063
2023-01-23 02:14:57.365218: step: 556/533, loss: 0.015806769952178
2023-01-23 02:14:58.504408: step: 560/533, loss: 0.008835411630570889
2023-01-23 02:14:59.657974: step: 564/533, loss: 0.01644115522503853
2023-01-23 02:15:00.817110: step: 568/533, loss: 0.0074520111083984375
2023-01-23 02:15:01.995586: step: 572/533, loss: 0.011236190795898438
2023-01-23 02:15:03.196287: step: 576/533, loss: 0.00153017055708915
2023-01-23 02:15:04.374245: step: 580/533, loss: 0.009859466925263405
2023-01-23 02:15:05.555246: step: 584/533, loss: 0.027907848358154297
2023-01-23 02:15:06.705886: step: 588/533, loss: 0.029274415224790573
2023-01-23 02:15:07.889803: step: 592/533, loss: 0.051645852625370026
2023-01-23 02:15:09.061463: step: 596/533, loss: 0.01381602231413126
2023-01-23 02:15:10.224229: step: 600/533, loss: 0.009810996241867542
2023-01-23 02:15:11.394704: step: 604/533, loss: 1.0538564920425415
2023-01-23 02:15:12.531232: step: 608/533, loss: 0.03410739824175835
2023-01-23 02:15:13.704699: step: 612/533, loss: 0.020374584943056107
2023-01-23 02:15:14.949152: step: 616/533, loss: 0.010302925482392311
2023-01-23 02:15:16.135413: step: 620/533, loss: 0.10747719556093216
2023-01-23 02:15:17.309060: step: 624/533, loss: 0.0033604621421545744
2023-01-23 02:15:18.454670: step: 628/533, loss: 0.005664443597197533
2023-01-23 02:15:19.643981: step: 632/533, loss: 0.010132789611816406
2023-01-23 02:15:20.815775: step: 636/533, loss: 0.007479286286979914
2023-01-23 02:15:22.010650: step: 640/533, loss: 0.00010354519326938316
2023-01-23 02:15:23.197549: step: 644/533, loss: 3.647804260253906e-05
2023-01-23 02:15:24.386663: step: 648/533, loss: 0.0018508911598473787
2023-01-23 02:15:25.570427: step: 652/533, loss: 0.025847626850008965
2023-01-23 02:15:26.722739: step: 656/533, loss: 0.001186108565889299
2023-01-23 02:15:27.963920: step: 660/533, loss: 0.009152794256806374
2023-01-23 02:15:29.132164: step: 664/533, loss: 0.0001338958682026714
2023-01-23 02:15:30.313645: step: 668/533, loss: 0.029302407056093216
2023-01-23 02:15:31.488365: step: 672/533, loss: 0.0017469406593590975
2023-01-23 02:15:32.666034: step: 676/533, loss: 0.05545921251177788
2023-01-23 02:15:33.826734: step: 680/533, loss: 0.012060356326401234
2023-01-23 02:15:34.997146: step: 684/533, loss: 0.03998775780200958
2023-01-23 02:15:36.147758: step: 688/533, loss: 0.01690850406885147
2023-01-23 02:15:37.328286: step: 692/533, loss: 0.04131384193897247
2023-01-23 02:15:38.511167: step: 696/533, loss: 0.05395827442407608
2023-01-23 02:15:39.711175: step: 700/533, loss: 0.0005521774291992188
2023-01-23 02:15:40.911971: step: 704/533, loss: 0.018268680199980736
2023-01-23 02:15:42.132849: step: 708/533, loss: 0.0668523758649826
2023-01-23 02:15:43.309061: step: 712/533, loss: 0.001416969345882535
2023-01-23 02:15:44.519346: step: 716/533, loss: 0.019535064697265625
2023-01-23 02:15:45.720505: step: 720/533, loss: 0.08260726928710938
2023-01-23 02:15:46.895230: step: 724/533, loss: 0.0035907744895666838
2023-01-23 02:15:48.047250: step: 728/533, loss: 0.028116608038544655
2023-01-23 02:15:49.184859: step: 732/533, loss: 0.052947234362363815
2023-01-23 02:15:50.413784: step: 736/533, loss: 0.007778358645737171
2023-01-23 02:15:51.580701: step: 740/533, loss: 0.05410642549395561
2023-01-23 02:15:52.758171: step: 744/533, loss: 0.003478527069091797
2023-01-23 02:15:53.943489: step: 748/533, loss: 0.07205858081579208
2023-01-23 02:15:55.150335: step: 752/533, loss: 0.011920833960175514
2023-01-23 02:15:56.309838: step: 756/533, loss: 0.0007012844434939325
2023-01-23 02:15:57.481452: step: 760/533, loss: 0.01123061217367649
2023-01-23 02:15:58.678015: step: 764/533, loss: 0.08117532730102539
2023-01-23 02:15:59.872417: step: 768/533, loss: 0.005683326628059149
2023-01-23 02:16:01.046250: step: 772/533, loss: 0.021115398034453392
2023-01-23 02:16:02.199666: step: 776/533, loss: 0.01758279651403427
2023-01-23 02:16:03.467915: step: 780/533, loss: 0.001708984375
2023-01-23 02:16:04.669799: step: 784/533, loss: 0.02628192864358425
2023-01-23 02:16:05.837905: step: 788/533, loss: 0.00523422984406352
2023-01-23 02:16:06.999925: step: 792/533, loss: 0.005763435736298561
2023-01-23 02:16:08.174595: step: 796/533, loss: 0.012892818078398705
2023-01-23 02:16:09.361634: step: 800/533, loss: 0.0067414757795631886
2023-01-23 02:16:10.542538: step: 804/533, loss: 0.04166240990161896
2023-01-23 02:16:11.732343: step: 808/533, loss: 0.042984962463378906
2023-01-23 02:16:12.903500: step: 812/533, loss: 0.02524395100772381
2023-01-23 02:16:14.083321: step: 816/533, loss: 0.06830673664808273
2023-01-23 02:16:15.322512: step: 820/533, loss: 0.018540572375059128
2023-01-23 02:16:16.515111: step: 824/533, loss: 0.012559700757265091
2023-01-23 02:16:17.714691: step: 828/533, loss: 0.06579142063856125
2023-01-23 02:16:18.938416: step: 832/533, loss: 0.030162906274199486
2023-01-23 02:16:20.133264: step: 836/533, loss: 0.031333159655332565
2023-01-23 02:16:21.287645: step: 840/533, loss: 0.01032400131225586
2023-01-23 02:16:22.445004: step: 844/533, loss: 0.005405331030488014
2023-01-23 02:16:23.624071: step: 848/533, loss: 0.004728603642433882
2023-01-23 02:16:24.826008: step: 852/533, loss: 0.03109598159790039
2023-01-23 02:16:26.041928: step: 856/533, loss: 0.003120040986686945
2023-01-23 02:16:27.267073: step: 860/533, loss: 0.010536766611039639
2023-01-23 02:16:28.423307: step: 864/533, loss: 0.00366802210919559
2023-01-23 02:16:29.588432: step: 868/533, loss: 0.0921415314078331
2023-01-23 02:16:30.787968: step: 872/533, loss: 0.011440182104706764
2023-01-23 02:16:31.965796: step: 876/533, loss: 0.0031838417053222656
2023-01-23 02:16:33.138245: step: 880/533, loss: 0.011308335699141026
2023-01-23 02:16:34.426346: step: 884/533, loss: 0.01524534821510315
2023-01-23 02:16:35.621230: step: 888/533, loss: 0.029624175280332565
2023-01-23 02:16:36.793400: step: 892/533, loss: 0.021938515827059746
2023-01-23 02:16:37.982501: step: 896/533, loss: 0.03240537643432617
2023-01-23 02:16:39.187240: step: 900/533, loss: 0.055516816675662994
2023-01-23 02:16:40.392587: step: 904/533, loss: 0.03161277621984482
2023-01-23 02:16:41.564998: step: 908/533, loss: 0.022112274542450905
2023-01-23 02:16:42.761365: step: 912/533, loss: 9.52720656641759e-05
2023-01-23 02:16:43.963861: step: 916/533, loss: 0.0011038780212402344
2023-01-23 02:16:45.139301: step: 920/533, loss: 0.023032188415527344
2023-01-23 02:16:46.320034: step: 924/533, loss: 0.005356502719223499
2023-01-23 02:16:47.534633: step: 928/533, loss: 0.03163165971636772
2023-01-23 02:16:48.758695: step: 932/533, loss: 0.007514477241784334
2023-01-23 02:16:49.948053: step: 936/533, loss: 0.015540122985839844
2023-01-23 02:16:51.115106: step: 940/533, loss: 0.11558723449707031
2023-01-23 02:16:52.274131: step: 944/533, loss: 0.002057838486507535
2023-01-23 02:16:53.434452: step: 948/533, loss: 0.01934661902487278
2023-01-23 02:16:54.699594: step: 952/533, loss: 0.11768823117017746
2023-01-23 02:16:55.889526: step: 956/533, loss: 0.020032405853271484
2023-01-23 02:16:57.096198: step: 960/533, loss: 0.25579720735549927
2023-01-23 02:16:58.302814: step: 964/533, loss: 0.010859108529984951
2023-01-23 02:16:59.501298: step: 968/533, loss: 0.06880789250135422
2023-01-23 02:17:00.688034: step: 972/533, loss: 0.018734503537416458
2023-01-23 02:17:01.855409: step: 976/533, loss: 0.2389226108789444
2023-01-23 02:17:03.040360: step: 980/533, loss: 0.05467681959271431
2023-01-23 02:17:04.214908: step: 984/533, loss: 0.09200669080018997
2023-01-23 02:17:05.390270: step: 988/533, loss: 0.03554544597864151
2023-01-23 02:17:06.554105: step: 992/533, loss: 0.017479050904512405
2023-01-23 02:17:07.722427: step: 996/533, loss: 0.016999052837491035
2023-01-23 02:17:08.908706: step: 1000/533, loss: 0.006008339114487171
2023-01-23 02:17:10.080569: step: 1004/533, loss: 0.025869179517030716
2023-01-23 02:17:11.269392: step: 1008/533, loss: 0.02622394822537899
2023-01-23 02:17:12.487768: step: 1012/533, loss: 0.0006391525384970009
2023-01-23 02:17:13.659391: step: 1016/533, loss: 0.014249706640839577
2023-01-23 02:17:14.839094: step: 1020/533, loss: 0.04812910407781601
2023-01-23 02:17:16.005136: step: 1024/533, loss: 0.03662566840648651
2023-01-23 02:17:17.181594: step: 1028/533, loss: 0.010272979736328125
2023-01-23 02:17:18.369949: step: 1032/533, loss: 0.0028142931405454874
2023-01-23 02:17:19.552370: step: 1036/533, loss: 0.05822286382317543
2023-01-23 02:17:20.709379: step: 1040/533, loss: 0.030423451215028763
2023-01-23 02:17:21.896954: step: 1044/533, loss: 0.023008251562714577
2023-01-23 02:17:23.087921: step: 1048/533, loss: 0.00150384905282408
2023-01-23 02:17:24.296169: step: 1052/533, loss: 0.10438661277294159
2023-01-23 02:17:25.476301: step: 1056/533, loss: 0.02017350308597088
2023-01-23 02:17:26.682081: step: 1060/533, loss: 0.01994161680340767
2023-01-23 02:17:27.827168: step: 1064/533, loss: 0.04570809006690979
2023-01-23 02:17:28.998564: step: 1068/533, loss: 0.01996765099465847
2023-01-23 02:17:30.148612: step: 1072/533, loss: 0.0008236885187216103
2023-01-23 02:17:31.364453: step: 1076/533, loss: 0.01607356034219265
2023-01-23 02:17:32.534699: step: 1080/533, loss: 0.06569354236125946
2023-01-23 02:17:33.717683: step: 1084/533, loss: 0.5582121014595032
2023-01-23 02:17:34.855282: step: 1088/533, loss: 0.006081867031753063
2023-01-23 02:17:36.053428: step: 1092/533, loss: 0.0364801399409771
2023-01-23 02:17:37.225445: step: 1096/533, loss: 0.002303695771843195
2023-01-23 02:17:38.419526: step: 1100/533, loss: 0.05634870380163193
2023-01-23 02:17:39.608434: step: 1104/533, loss: 0.07834739983081818
2023-01-23 02:17:40.786674: step: 1108/533, loss: 0.015307998284697533
2023-01-23 02:17:41.970459: step: 1112/533, loss: 0.02333064004778862
2023-01-23 02:17:43.166714: step: 1116/533, loss: 0.0076385498978197575
2023-01-23 02:17:44.362563: step: 1120/533, loss: 0.042043305933475494
2023-01-23 02:17:45.555257: step: 1124/533, loss: 0.0008339881896972656
2023-01-23 02:17:46.669487: step: 1128/533, loss: 0.00040121079655364156
2023-01-23 02:17:47.895986: step: 1132/533, loss: 0.019464731216430664
2023-01-23 02:17:49.077486: step: 1136/533, loss: 0.002195644425228238
2023-01-23 02:17:50.302097: step: 1140/533, loss: 0.034500885754823685
2023-01-23 02:17:51.487501: step: 1144/533, loss: 0.03498554229736328
2023-01-23 02:17:52.644590: step: 1148/533, loss: 0.0002364158717682585
2023-01-23 02:17:53.889270: step: 1152/533, loss: 0.004755592439323664
2023-01-23 02:17:55.091368: step: 1156/533, loss: 0.014267158694565296
2023-01-23 02:17:56.262405: step: 1160/533, loss: 0.08406372368335724
2023-01-23 02:17:57.437621: step: 1164/533, loss: 0.001859378768131137
2023-01-23 02:17:58.635973: step: 1168/533, loss: 0.007318973541259766
2023-01-23 02:17:59.816804: step: 1172/533, loss: 0.008948421105742455
2023-01-23 02:18:00.991858: step: 1176/533, loss: 0.025196265429258347
2023-01-23 02:18:02.196472: step: 1180/533, loss: 0.00012750625319313258
2023-01-23 02:18:03.333593: step: 1184/533, loss: 0.0464697889983654
2023-01-23 02:18:04.502521: step: 1188/533, loss: 0.00582809466868639
2023-01-23 02:18:05.708844: step: 1192/533, loss: 0.016617584973573685
2023-01-23 02:18:06.914048: step: 1196/533, loss: 0.009745216928422451
2023-01-23 02:18:08.118026: step: 1200/533, loss: 0.0041717528365552425
2023-01-23 02:18:09.296295: step: 1204/533, loss: 0.0827278196811676
2023-01-23 02:18:10.481316: step: 1208/533, loss: 0.005058670416474342
2023-01-23 02:18:11.655563: step: 1212/533, loss: 0.04741477966308594
2023-01-23 02:18:12.852194: step: 1216/533, loss: 0.04038963466882706
2023-01-23 02:18:13.986170: step: 1220/533, loss: 0.007138824090361595
2023-01-23 02:18:15.173846: step: 1224/533, loss: 0.00027523041353560984
2023-01-23 02:18:16.341324: step: 1228/533, loss: 0.0023010254371911287
2023-01-23 02:18:17.521473: step: 1232/533, loss: 0.06627855449914932
2023-01-23 02:18:18.713795: step: 1236/533, loss: 0.021790886297822
2023-01-23 02:18:19.933412: step: 1240/533, loss: 0.0030642985366284847
2023-01-23 02:18:21.136422: step: 1244/533, loss: 0.08760223537683487
2023-01-23 02:18:22.371380: step: 1248/533, loss: 0.01812133751809597
2023-01-23 02:18:23.580145: step: 1252/533, loss: 0.008239174261689186
2023-01-23 02:18:24.752911: step: 1256/533, loss: 0.005572319030761719
2023-01-23 02:18:25.957435: step: 1260/533, loss: 0.0014656067360192537
2023-01-23 02:18:27.146835: step: 1264/533, loss: 0.019694900140166283
2023-01-23 02:18:28.327023: step: 1268/533, loss: 0.008084679022431374
2023-01-23 02:18:29.544029: step: 1272/533, loss: 0.003276062197983265
2023-01-23 02:18:30.744437: step: 1276/533, loss: 0.05052213370800018
2023-01-23 02:18:31.905689: step: 1280/533, loss: 0.03057537041604519
2023-01-23 02:18:33.134621: step: 1284/533, loss: 0.021741202101111412
2023-01-23 02:18:34.319909: step: 1288/533, loss: 0.00624427804723382
2023-01-23 02:18:35.534721: step: 1292/533, loss: 0.03257598727941513
2023-01-23 02:18:36.703608: step: 1296/533, loss: 0.008803748525679111
2023-01-23 02:18:37.855010: step: 1300/533, loss: 0.00012302398681640625
2023-01-23 02:18:39.047732: step: 1304/533, loss: 0.028060341253876686
2023-01-23 02:18:40.227717: step: 1308/533, loss: 0.051899246871471405
2023-01-23 02:18:41.418084: step: 1312/533, loss: 0.06038370355963707
2023-01-23 02:18:42.615777: step: 1316/533, loss: 0.0061799525283277035
2023-01-23 02:18:43.784406: step: 1320/533, loss: 0.018686868250370026
2023-01-23 02:18:44.945297: step: 1324/533, loss: 0.0014800071949139237
2023-01-23 02:18:46.139827: step: 1328/533, loss: 0.01181702595204115
2023-01-23 02:18:47.333521: step: 1332/533, loss: 0.026486776769161224
2023-01-23 02:18:48.492751: step: 1336/533, loss: 0.015202522277832031
2023-01-23 02:18:49.683236: step: 1340/533, loss: 0.03638286888599396
2023-01-23 02:18:50.856755: step: 1344/533, loss: 0.051151469349861145
2023-01-23 02:18:52.068809: step: 1348/533, loss: 0.012768936343491077
2023-01-23 02:18:53.304283: step: 1352/533, loss: 3.23295607813634e-05
2023-01-23 02:18:54.486841: step: 1356/533, loss: 0.02454528957605362
2023-01-23 02:18:55.614833: step: 1360/533, loss: 0.022385787218809128
2023-01-23 02:18:56.802397: step: 1364/533, loss: 0.09749583899974823
2023-01-23 02:18:57.952344: step: 1368/533, loss: 0.013975143432617188
2023-01-23 02:18:59.133646: step: 1372/533, loss: 0.046065568923950195
2023-01-23 02:19:00.311902: step: 1376/533, loss: 0.0007600784301757812
2023-01-23 02:19:01.483864: step: 1380/533, loss: 0.002143955323845148
2023-01-23 02:19:02.643879: step: 1384/533, loss: 0.011771773919463158
2023-01-23 02:19:03.822982: step: 1388/533, loss: 0.008600425906479359
2023-01-23 02:19:04.992072: step: 1392/533, loss: 0.02682333067059517
2023-01-23 02:19:06.159682: step: 1396/533, loss: 0.004392004106193781
2023-01-23 02:19:07.363881: step: 1400/533, loss: 0.02995305135846138
2023-01-23 02:19:08.558230: step: 1404/533, loss: 0.024753950536251068
2023-01-23 02:19:09.740802: step: 1408/533, loss: 0.6111812591552734
2023-01-23 02:19:10.910820: step: 1412/533, loss: 0.009926986880600452
2023-01-23 02:19:12.114489: step: 1416/533, loss: 0.012932014651596546
2023-01-23 02:19:13.289149: step: 1420/533, loss: 0.40571194887161255
2023-01-23 02:19:14.462642: step: 1424/533, loss: 0.060767367482185364
2023-01-23 02:19:15.607006: step: 1428/533, loss: 0.005069160833954811
2023-01-23 02:19:16.749836: step: 1432/533, loss: 0.0010920524364337325
2023-01-23 02:19:17.924373: step: 1436/533, loss: 0.02393188513815403
2023-01-23 02:19:19.131967: step: 1440/533, loss: 0.001622200128622353
2023-01-23 02:19:20.336744: step: 1444/533, loss: 0.1077723503112793
2023-01-23 02:19:21.516236: step: 1448/533, loss: 0.0002967834589071572
2023-01-23 02:19:22.707489: step: 1452/533, loss: 0.004766655154526234
2023-01-23 02:19:23.972237: step: 1456/533, loss: 0.0057089803740382195
2023-01-23 02:19:25.184274: step: 1460/533, loss: 0.011112308129668236
2023-01-23 02:19:26.378330: step: 1464/533, loss: 0.8716068267822266
2023-01-23 02:19:27.572889: step: 1468/533, loss: 0.0208574291318655
2023-01-23 02:19:28.766275: step: 1472/533, loss: 0.0012716293567791581
2023-01-23 02:19:29.936354: step: 1476/533, loss: 0.0011721611954271793
2023-01-23 02:19:31.123451: step: 1480/533, loss: 0.041300203651189804
2023-01-23 02:19:32.297925: step: 1484/533, loss: 0.023172473534941673
2023-01-23 02:19:33.533607: step: 1488/533, loss: 0.19410498440265656
2023-01-23 02:19:34.713419: step: 1492/533, loss: 0.0006723880651406944
2023-01-23 02:19:35.874482: step: 1496/533, loss: 0.07472310215234756
2023-01-23 02:19:37.048025: step: 1500/533, loss: 0.0003501892206259072
2023-01-23 02:19:38.267410: step: 1504/533, loss: 0.005684948060661554
2023-01-23 02:19:39.451200: step: 1508/533, loss: 0.04314479976892471
2023-01-23 02:19:40.627530: step: 1512/533, loss: 0.039985354989767075
2023-01-23 02:19:41.788350: step: 1516/533, loss: 0.000335502641974017
2023-01-23 02:19:42.995623: step: 1520/533, loss: 0.04457368701696396
2023-01-23 02:19:44.176034: step: 1524/533, loss: 0.05116824805736542
2023-01-23 02:19:45.430460: step: 1528/533, loss: 0.007270717993378639
2023-01-23 02:19:46.637627: step: 1532/533, loss: 0.009715080261230469
2023-01-23 02:19:47.829440: step: 1536/533, loss: 0.07018737494945526
2023-01-23 02:19:49.026208: step: 1540/533, loss: 0.10267038643360138
2023-01-23 02:19:50.224242: step: 1544/533, loss: 0.004651117138564587
2023-01-23 02:19:51.360844: step: 1548/533, loss: 0.0390382744371891
2023-01-23 02:19:52.566870: step: 1552/533, loss: 0.05172806233167648
2023-01-23 02:19:53.722965: step: 1556/533, loss: 0.6601153612136841
2023-01-23 02:19:54.948913: step: 1560/533, loss: 0.6721023321151733
2023-01-23 02:19:56.111506: step: 1564/533, loss: 0.02232213132083416
2023-01-23 02:19:57.292979: step: 1568/533, loss: 0.05605268478393555
2023-01-23 02:19:58.470369: step: 1572/533, loss: 0.08810672909021378
2023-01-23 02:19:59.642744: step: 1576/533, loss: 0.008544350042939186
2023-01-23 02:20:00.839845: step: 1580/533, loss: 0.001749324845150113
2023-01-23 02:20:02.005347: step: 1584/533, loss: 0.039250753819942474
2023-01-23 02:20:03.215067: step: 1588/533, loss: 0.03836536407470703
2023-01-23 02:20:04.377693: step: 1592/533, loss: 0.012895394116640091
2023-01-23 02:20:05.565945: step: 1596/533, loss: 0.036333274096250534
2023-01-23 02:20:06.751667: step: 1600/533, loss: 0.09430017322301865
2023-01-23 02:20:07.930696: step: 1604/533, loss: 0.02545313909649849
2023-01-23 02:20:09.122579: step: 1608/533, loss: 0.014666581526398659
2023-01-23 02:20:10.334307: step: 1612/533, loss: 0.01267700269818306
2023-01-23 02:20:11.522011: step: 1616/533, loss: 0.002629518508911133
2023-01-23 02:20:12.675363: step: 1620/533, loss: 0.0003755807993002236
2023-01-23 02:20:13.863705: step: 1624/533, loss: 0.015447616577148438
2023-01-23 02:20:15.042586: step: 1628/533, loss: 0.06693296879529953
2023-01-23 02:20:16.198789: step: 1632/533, loss: 0.026526546105742455
2023-01-23 02:20:17.422431: step: 1636/533, loss: 0.0023128509055823088
2023-01-23 02:20:18.636263: step: 1640/533, loss: 0.030338764190673828
2023-01-23 02:20:19.844520: step: 1644/533, loss: 0.0010441303020343184
2023-01-23 02:20:21.039245: step: 1648/533, loss: 0.002232170198112726
2023-01-23 02:20:22.214419: step: 1652/533, loss: 0.05335855484008789
2023-01-23 02:20:23.393643: step: 1656/533, loss: 0.048605918884277344
2023-01-23 02:20:24.561038: step: 1660/533, loss: 0.023540209978818893
2023-01-23 02:20:25.743458: step: 1664/533, loss: 0.027623845264315605
2023-01-23 02:20:26.899514: step: 1668/533, loss: 0.05308714136481285
2023-01-23 02:20:28.114749: step: 1672/533, loss: 0.0011747360695153475
2023-01-23 02:20:29.254931: step: 1676/533, loss: 0.03023710288107395
2023-01-23 02:20:30.385679: step: 1680/533, loss: 0.018737316131591797
2023-01-23 02:20:31.557060: step: 1684/533, loss: 0.006157779600471258
2023-01-23 02:20:32.728589: step: 1688/533, loss: 0.032965995371341705
2023-01-23 02:20:33.879565: step: 1692/533, loss: 0.03528919070959091
2023-01-23 02:20:35.037092: step: 1696/533, loss: 0.024686051532626152
2023-01-23 02:20:36.219205: step: 1700/533, loss: 0.02487964555621147
2023-01-23 02:20:37.416757: step: 1704/533, loss: 0.026212597265839577
2023-01-23 02:20:38.585464: step: 1708/533, loss: 0.04367341846227646
2023-01-23 02:20:39.727251: step: 1712/533, loss: 0.002299404004588723
2023-01-23 02:20:40.934060: step: 1716/533, loss: 0.018983840942382812
2023-01-23 02:20:42.076446: step: 1720/533, loss: 0.019336320459842682
2023-01-23 02:20:43.249116: step: 1724/533, loss: 0.06380148231983185
2023-01-23 02:20:44.452586: step: 1728/533, loss: 0.026281356811523438
2023-01-23 02:20:45.609271: step: 1732/533, loss: 0.04699697345495224
2023-01-23 02:20:46.862619: step: 1736/533, loss: 0.03758583217859268
2023-01-23 02:20:48.069933: step: 1740/533, loss: 0.00016431808762717992
2023-01-23 02:20:49.287012: step: 1744/533, loss: 0.011332893744111061
2023-01-23 02:20:50.461932: step: 1748/533, loss: 0.0074713705107569695
2023-01-23 02:20:51.635986: step: 1752/533, loss: 0.04449405521154404
2023-01-23 02:20:52.790562: step: 1756/533, loss: 0.020090175792574883
2023-01-23 02:20:53.972994: step: 1760/533, loss: 0.0004707336483988911
2023-01-23 02:20:55.198275: step: 1764/533, loss: 0.008679008111357689
2023-01-23 02:20:56.389991: step: 1768/533, loss: 0.002693748567253351
2023-01-23 02:20:57.559466: step: 1772/533, loss: 0.00797424279153347
2023-01-23 02:20:58.763715: step: 1776/533, loss: 0.055773161351680756
2023-01-23 02:20:59.940894: step: 1780/533, loss: 0.011396408081054688
2023-01-23 02:21:01.113306: step: 1784/533, loss: 0.0009837150573730469
2023-01-23 02:21:02.270487: step: 1788/533, loss: 0.001769256661646068
2023-01-23 02:21:03.447991: step: 1792/533, loss: 0.20864161849021912
2023-01-23 02:21:04.635507: step: 1796/533, loss: 0.0011324883671477437
2023-01-23 02:21:05.818089: step: 1800/533, loss: 0.048406124114990234
2023-01-23 02:21:07.003504: step: 1804/533, loss: 0.04061460494995117
2023-01-23 02:21:08.199102: step: 1808/533, loss: 0.06837115436792374
2023-01-23 02:21:09.389942: step: 1812/533, loss: 0.019831180572509766
2023-01-23 02:21:10.581588: step: 1816/533, loss: 0.0007309913635253906
2023-01-23 02:21:11.729666: step: 1820/533, loss: 0.03796567767858505
2023-01-23 02:21:12.876959: step: 1824/533, loss: 0.003537082578986883
2023-01-23 02:21:14.057723: step: 1828/533, loss: 0.05063915252685547
2023-01-23 02:21:15.234024: step: 1832/533, loss: 0.06044836342334747
2023-01-23 02:21:16.427753: step: 1836/533, loss: 0.053933046758174896
2023-01-23 02:21:17.622397: step: 1840/533, loss: 0.07410397380590439
2023-01-23 02:21:18.808421: step: 1844/533, loss: 0.04561617225408554
2023-01-23 02:21:19.985576: step: 1848/533, loss: 0.001814508461393416
2023-01-23 02:21:21.182325: step: 1852/533, loss: 0.013540947809815407
2023-01-23 02:21:22.323754: step: 1856/533, loss: 0.04883613437414169
2023-01-23 02:21:23.483601: step: 1860/533, loss: 0.006354331970214844
2023-01-23 02:21:24.651966: step: 1864/533, loss: 0.03805875778198242
2023-01-23 02:21:25.845166: step: 1868/533, loss: 0.0682777389883995
2023-01-23 02:21:27.051222: step: 1872/533, loss: 0.04222317039966583
2023-01-23 02:21:28.230417: step: 1876/533, loss: 0.044712066650390625
2023-01-23 02:21:29.451587: step: 1880/533, loss: 0.008061408996582031
2023-01-23 02:21:30.627638: step: 1884/533, loss: 0.026677321642637253
2023-01-23 02:21:31.760736: step: 1888/533, loss: 0.008876991458237171
2023-01-23 02:21:32.953809: step: 1892/533, loss: 0.0035416604951024055
2023-01-23 02:21:34.169920: step: 1896/533, loss: 0.15971823036670685
2023-01-23 02:21:35.348797: step: 1900/533, loss: 0.015170670114457607
2023-01-23 02:21:36.555346: step: 1904/533, loss: 0.016233444213867188
2023-01-23 02:21:37.739353: step: 1908/533, loss: 0.0054069519974291325
2023-01-23 02:21:38.936196: step: 1912/533, loss: 0.002009582705795765
2023-01-23 02:21:40.133840: step: 1916/533, loss: 0.0009664535755291581
2023-01-23 02:21:41.312432: step: 1920/533, loss: 0.0011308669345453382
2023-01-23 02:21:42.467891: step: 1924/533, loss: 0.008218956179916859
2023-01-23 02:21:43.663980: step: 1928/533, loss: 0.07188782840967178
2023-01-23 02:21:44.834623: step: 1932/533, loss: 0.038410499691963196
2023-01-23 02:21:46.000013: step: 1936/533, loss: 0.005018759053200483
2023-01-23 02:21:47.163388: step: 1940/533, loss: 0.17368750274181366
2023-01-23 02:21:48.282661: step: 1944/533, loss: 0.004603862762451172
2023-01-23 02:21:49.502285: step: 1948/533, loss: 0.006214046385139227
2023-01-23 02:21:50.687855: step: 1952/533, loss: 0.010112953372299671
2023-01-23 02:21:51.886406: step: 1956/533, loss: 0.04880419000983238
2023-01-23 02:21:53.037299: step: 1960/533, loss: 0.004610681440681219
2023-01-23 02:21:54.261637: step: 1964/533, loss: 0.004082346335053444
2023-01-23 02:21:55.438376: step: 1968/533, loss: 0.004262733273208141
2023-01-23 02:21:56.627265: step: 1972/533, loss: 0.03580818697810173
2023-01-23 02:21:57.809849: step: 1976/533, loss: 0.003840160323306918
2023-01-23 02:21:58.953156: step: 1980/533, loss: 0.0005839825025759637
2023-01-23 02:22:00.150563: step: 1984/533, loss: 0.09142742305994034
2023-01-23 02:22:01.315485: step: 1988/533, loss: 0.000720596348401159
2023-01-23 02:22:02.467562: step: 1992/533, loss: 0.00953598041087389
2023-01-23 02:22:03.636841: step: 1996/533, loss: 0.05358543246984482
2023-01-23 02:22:04.793364: step: 2000/533, loss: 0.05969047546386719
2023-01-23 02:22:05.973032: step: 2004/533, loss: 0.012916183099150658
2023-01-23 02:22:07.201714: step: 2008/533, loss: 0.01000747736543417
2023-01-23 02:22:08.392165: step: 2012/533, loss: 0.0004625797155313194
2023-01-23 02:22:09.548748: step: 2016/533, loss: 0.008774567395448685
2023-01-23 02:22:10.700306: step: 2020/533, loss: 0.013058471493422985
2023-01-23 02:22:11.853471: step: 2024/533, loss: 0.02618112601339817
2023-01-23 02:22:13.065996: step: 2028/533, loss: 0.06427936255931854
2023-01-23 02:22:14.296503: step: 2032/533, loss: 0.032117556780576706
2023-01-23 02:22:15.513083: step: 2036/533, loss: 0.08823671191930771
2023-01-23 02:22:16.675315: step: 2040/533, loss: 0.03191203996539116
2023-01-23 02:22:17.861035: step: 2044/533, loss: 0.03502722084522247
2023-01-23 02:22:19.044992: step: 2048/533, loss: 0.0031945230439305305
2023-01-23 02:22:20.241380: step: 2052/533, loss: 0.11333017796278
2023-01-23 02:22:21.442829: step: 2056/533, loss: 0.0027659893967211246
2023-01-23 02:22:22.621142: step: 2060/533, loss: 1.087188684323337e-05
2023-01-23 02:22:23.811009: step: 2064/533, loss: 0.02297971211373806
2023-01-23 02:22:25.055306: step: 2068/533, loss: 0.033625029027462006
2023-01-23 02:22:26.264986: step: 2072/533, loss: 0.00562896765768528
2023-01-23 02:22:27.430727: step: 2076/533, loss: 0.02445383183658123
2023-01-23 02:22:28.608339: step: 2080/533, loss: 0.004440879914909601
2023-01-23 02:22:29.780274: step: 2084/533, loss: 0.03657379373908043
2023-01-23 02:22:30.969075: step: 2088/533, loss: 0.013322449289262295
2023-01-23 02:22:32.161287: step: 2092/533, loss: 0.024021148681640625
2023-01-23 02:22:33.365549: step: 2096/533, loss: 0.001678562257438898
2023-01-23 02:22:34.551885: step: 2100/533, loss: 0.0024990083184093237
2023-01-23 02:22:35.715350: step: 2104/533, loss: 0.0009291649330407381
2023-01-23 02:22:36.900138: step: 2108/533, loss: 0.04841213300824165
2023-01-23 02:22:38.103501: step: 2112/533, loss: 0.05562658607959747
2023-01-23 02:22:39.296587: step: 2116/533, loss: 0.004183387849479914
2023-01-23 02:22:40.523016: step: 2120/533, loss: 0.02273120917379856
2023-01-23 02:22:41.693160: step: 2124/533, loss: 0.022293664515018463
2023-01-23 02:22:42.886432: step: 2128/533, loss: 0.06163139268755913
2023-01-23 02:22:44.092465: step: 2132/533, loss: 0.035263922065496445
==================================================
Loss: 0.039
--------------------
Dev: {'event': {'p': 0.6156387665198237, 'r': 0.7443408788282291, 'f1': 0.6738999397227246}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6574556830031283, 'r': 0.8062659846547314, 'f1': 0.7242963813900059}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.34285714285714286, 'r': 0.3333333333333333, 'f1': 0.3380281690140845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:23:25.196566: step: 4/533, loss: 0.008470917120575905
2023-01-23 02:23:26.363265: step: 8/533, loss: 0.0465204231441021
2023-01-23 02:23:27.529663: step: 12/533, loss: 0.006655311677604914
2023-01-23 02:23:28.740359: step: 16/533, loss: 0.0010618210071697831
2023-01-23 02:23:29.926880: step: 20/533, loss: 0.15059979259967804
2023-01-23 02:23:31.090604: step: 24/533, loss: 0.23148241639137268
2023-01-23 02:23:32.228110: step: 28/533, loss: 0.021610165014863014
2023-01-23 02:23:33.407035: step: 32/533, loss: 0.030868148431181908
2023-01-23 02:23:34.585548: step: 36/533, loss: 0.03508281707763672
2023-01-23 02:23:35.729202: step: 40/533, loss: 0.001137542654760182
2023-01-23 02:23:36.943861: step: 44/533, loss: 0.020200539380311966
2023-01-23 02:23:38.093945: step: 48/533, loss: 0.011140108108520508
2023-01-23 02:23:39.266427: step: 52/533, loss: 0.028125381097197533
2023-01-23 02:23:40.437730: step: 56/533, loss: 0.003948402591049671
2023-01-23 02:23:41.624960: step: 60/533, loss: 0.0028722763527184725
2023-01-23 02:23:42.785388: step: 64/533, loss: 0.02617664448916912
2023-01-23 02:23:44.019204: step: 68/533, loss: 0.009011936374008656
2023-01-23 02:23:45.183773: step: 72/533, loss: 0.003072547959163785
2023-01-23 02:23:46.356185: step: 76/533, loss: 0.003905010409653187
2023-01-23 02:23:47.504839: step: 80/533, loss: 0.31844061613082886
2023-01-23 02:23:48.671509: step: 84/533, loss: 0.0043312073685228825
2023-01-23 02:23:49.822507: step: 88/533, loss: 0.0011698722373694181
2023-01-23 02:23:51.021719: step: 92/533, loss: 0.002591466996818781
2023-01-23 02:23:52.226355: step: 96/533, loss: 0.04778652265667915
2023-01-23 02:23:53.450213: step: 100/533, loss: 0.08303088694810867
2023-01-23 02:23:54.594338: step: 104/533, loss: 0.0005508899921551347
2023-01-23 02:23:55.800705: step: 108/533, loss: 0.09066527336835861
2023-01-23 02:23:56.970092: step: 112/533, loss: 0.027950001880526543
2023-01-23 02:23:58.145877: step: 116/533, loss: 0.07192688435316086
2023-01-23 02:23:59.368958: step: 120/533, loss: 0.011118126101791859
2023-01-23 02:24:00.528847: step: 124/533, loss: 0.01728353463113308
2023-01-23 02:24:01.660559: step: 128/533, loss: 0.011571216396987438
2023-01-23 02:24:02.908020: step: 132/533, loss: 0.027283286675810814
2023-01-23 02:24:04.140938: step: 136/533, loss: 0.018111610785126686
2023-01-23 02:24:05.298207: step: 140/533, loss: 0.04141692817211151
2023-01-23 02:24:06.489854: step: 144/533, loss: 0.0010954856406897306
2023-01-23 02:24:07.683493: step: 148/533, loss: 0.00011777877807617188
2023-01-23 02:24:08.875366: step: 152/533, loss: 0.019156837835907936
2023-01-23 02:24:10.050790: step: 156/533, loss: 0.0023279192391783
2023-01-23 02:24:11.179666: step: 160/533, loss: 0.0026392461732029915
2023-01-23 02:24:12.331849: step: 164/533, loss: 0.01635732688009739
2023-01-23 02:24:13.499729: step: 168/533, loss: 0.0048995972611010075
2023-01-23 02:24:14.673634: step: 172/533, loss: 0.01196365337818861
2023-01-23 02:24:15.829915: step: 176/533, loss: 0.0156586654484272
2023-01-23 02:24:17.015355: step: 180/533, loss: 0.0022554397583007812
2023-01-23 02:24:18.188986: step: 184/533, loss: 0.0028951645363122225
2023-01-23 02:24:19.355997: step: 188/533, loss: 0.00784082431346178
2023-01-23 02:24:20.551073: step: 192/533, loss: 0.01173181552439928
2023-01-23 02:24:21.696052: step: 196/533, loss: 0.0005043029668740928
2023-01-23 02:24:22.891818: step: 200/533, loss: 0.05573310703039169
2023-01-23 02:24:24.026972: step: 204/533, loss: 0.0011247635120525956
2023-01-23 02:24:25.218862: step: 208/533, loss: 0.035033416002988815
2023-01-23 02:24:26.380348: step: 212/533, loss: 0.009194565936923027
2023-01-23 02:24:27.586617: step: 216/533, loss: 0.04939556121826172
2023-01-23 02:24:28.767618: step: 220/533, loss: 0.008978605270385742
2023-01-23 02:24:29.923262: step: 224/533, loss: 0.026622582226991653
2023-01-23 02:24:31.159674: step: 228/533, loss: 0.07035829871892929
2023-01-23 02:24:32.310581: step: 232/533, loss: 0.023929214105010033
2023-01-23 02:24:33.493122: step: 236/533, loss: 0.0026329518295824528
2023-01-23 02:24:34.669047: step: 240/533, loss: 0.03444099426269531
2023-01-23 02:24:35.864477: step: 244/533, loss: 0.03175296634435654
2023-01-23 02:24:37.062878: step: 248/533, loss: 0.033638764172792435
2023-01-23 02:24:38.208281: step: 252/533, loss: 0.011321449652314186
2023-01-23 02:24:39.388019: step: 256/533, loss: 0.001935768174007535
2023-01-23 02:24:40.580528: step: 260/533, loss: 0.026566125452518463
2023-01-23 02:24:41.762762: step: 264/533, loss: 0.0031630517914891243
2023-01-23 02:24:42.956314: step: 268/533, loss: 0.00252532958984375
2023-01-23 02:24:44.173716: step: 272/533, loss: 0.031397342681884766
2023-01-23 02:24:45.341430: step: 276/533, loss: 0.00027408599271439016
2023-01-23 02:24:46.528726: step: 280/533, loss: 0.029116153717041016
2023-01-23 02:24:47.755587: step: 284/533, loss: 0.013803101144731045
2023-01-23 02:24:48.897061: step: 288/533, loss: 0.0073143006302416325
2023-01-23 02:24:50.067884: step: 292/533, loss: 0.013009835034608841
2023-01-23 02:24:51.239158: step: 296/533, loss: 0.003967761993408203
2023-01-23 02:24:52.422597: step: 300/533, loss: 0.0006698608631268144
2023-01-23 02:24:53.615054: step: 304/533, loss: 0.1048440933227539
2023-01-23 02:24:54.801316: step: 308/533, loss: 0.01865367963910103
2023-01-23 02:24:55.951306: step: 312/533, loss: 0.0009140968322753906
2023-01-23 02:24:57.120974: step: 316/533, loss: 0.022235143929719925
2023-01-23 02:24:58.317689: step: 320/533, loss: 0.036298468708992004
2023-01-23 02:24:59.535900: step: 324/533, loss: 0.019890213385224342
2023-01-23 02:25:00.744211: step: 328/533, loss: 0.010746574029326439
2023-01-23 02:25:01.936157: step: 332/533, loss: 0.13982105255126953
2023-01-23 02:25:03.149404: step: 336/533, loss: 0.010132885538041592
2023-01-23 02:25:04.324001: step: 340/533, loss: 1.6117095583467744e-05
2023-01-23 02:25:05.492115: step: 344/533, loss: 0.007548713590949774
2023-01-23 02:25:06.666566: step: 348/533, loss: 0.02690095826983452
2023-01-23 02:25:07.810659: step: 352/533, loss: 0.0007046699756756425
2023-01-23 02:25:08.997024: step: 356/533, loss: 0.020682239904999733
2023-01-23 02:25:10.189793: step: 360/533, loss: 0.0009099007584154606
2023-01-23 02:25:11.376920: step: 364/533, loss: 0.0006016731495037675
2023-01-23 02:25:12.580293: step: 368/533, loss: 0.018793772906064987
2023-01-23 02:25:13.778090: step: 372/533, loss: 0.08054371178150177
2023-01-23 02:25:14.935161: step: 376/533, loss: 0.0019276619423180819
2023-01-23 02:25:16.073819: step: 380/533, loss: 0.02097911946475506
2023-01-23 02:25:17.241471: step: 384/533, loss: 0.02664213255047798
2023-01-23 02:25:18.434465: step: 388/533, loss: 0.002897262806072831
2023-01-23 02:25:19.637032: step: 392/533, loss: 0.032498933374881744
2023-01-23 02:25:20.788047: step: 396/533, loss: 0.003563452046364546
2023-01-23 02:25:21.929331: step: 400/533, loss: 0.008996676653623581
2023-01-23 02:25:23.089168: step: 404/533, loss: 0.004610633943229914
2023-01-23 02:25:24.221827: step: 408/533, loss: 0.02196197584271431
2023-01-23 02:25:25.441917: step: 412/533, loss: 0.00047779083251953125
2023-01-23 02:25:26.628376: step: 416/533, loss: 0.0006655693287029862
2023-01-23 02:25:27.817839: step: 420/533, loss: 0.005791568662971258
2023-01-23 02:25:29.024590: step: 424/533, loss: 0.04312610626220703
2023-01-23 02:25:30.244934: step: 428/533, loss: 0.01964435540139675
2023-01-23 02:25:31.438024: step: 432/533, loss: 0.02618255652487278
2023-01-23 02:25:32.624208: step: 436/533, loss: 0.0003886222839355469
2023-01-23 02:25:33.841403: step: 440/533, loss: 0.018010282889008522
2023-01-23 02:25:34.989221: step: 444/533, loss: 0.00016660690016578883
2023-01-23 02:25:36.132111: step: 448/533, loss: 0.030162811279296875
2023-01-23 02:25:37.339182: step: 452/533, loss: 0.033753298223018646
2023-01-23 02:25:38.490251: step: 456/533, loss: 0.005419731140136719
2023-01-23 02:25:39.647744: step: 460/533, loss: 0.09558341652154922
2023-01-23 02:25:40.863062: step: 464/533, loss: 0.049311257898807526
2023-01-23 02:25:42.038332: step: 468/533, loss: 0.008684826083481312
2023-01-23 02:25:43.230611: step: 472/533, loss: 0.004789256956428289
2023-01-23 02:25:44.392594: step: 476/533, loss: 0.045457080006599426
2023-01-23 02:25:45.548119: step: 480/533, loss: 0.16615954041481018
2023-01-23 02:25:46.720196: step: 484/533, loss: 0.011584663763642311
2023-01-23 02:25:47.872106: step: 488/533, loss: 0.09564094245433807
2023-01-23 02:25:49.028179: step: 492/533, loss: 0.003418445587158203
2023-01-23 02:25:50.214549: step: 496/533, loss: 0.006530619226396084
2023-01-23 02:25:51.368638: step: 500/533, loss: 0.042191032320261
2023-01-23 02:25:52.533198: step: 504/533, loss: 0.018095016479492188
2023-01-23 02:25:53.736573: step: 508/533, loss: 0.028162287548184395
2023-01-23 02:25:54.972676: step: 512/533, loss: 0.0015274047618731856
2023-01-23 02:25:56.160985: step: 516/533, loss: 0.01014175359159708
2023-01-23 02:25:57.347724: step: 520/533, loss: 0.002201271243393421
2023-01-23 02:25:58.544863: step: 524/533, loss: 0.009698057547211647
2023-01-23 02:25:59.743905: step: 528/533, loss: 0.000864005065523088
2023-01-23 02:26:00.905753: step: 532/533, loss: 0.07200102508068085
2023-01-23 02:26:02.119853: step: 536/533, loss: 1.6215065717697144
2023-01-23 02:26:03.266509: step: 540/533, loss: 0.0024261474609375
2023-01-23 02:26:04.441663: step: 544/533, loss: 0.00011811256990768015
2023-01-23 02:26:05.640029: step: 548/533, loss: 0.00041313175461255014
2023-01-23 02:26:06.859859: step: 552/533, loss: 0.0007096290355548263
2023-01-23 02:26:08.088441: step: 556/533, loss: 0.023937225341796875
2023-01-23 02:26:09.273795: step: 560/533, loss: 0.00608139019459486
2023-01-23 02:26:10.457947: step: 564/533, loss: 0.01667614094913006
2023-01-23 02:26:11.630786: step: 568/533, loss: 0.04230823740363121
2023-01-23 02:26:12.812191: step: 572/533, loss: 0.005451011937111616
2023-01-23 02:26:14.003982: step: 576/533, loss: 0.0013081550132483244
2023-01-23 02:26:15.191748: step: 580/533, loss: 0.008057022467255592
2023-01-23 02:26:16.371933: step: 584/533, loss: 0.012000751681625843
2023-01-23 02:26:17.530856: step: 588/533, loss: 0.011235046200454235
2023-01-23 02:26:18.749484: step: 592/533, loss: 0.003505706787109375
2023-01-23 02:26:19.946664: step: 596/533, loss: 0.14706459641456604
2023-01-23 02:26:21.093539: step: 600/533, loss: 0.008831977844238281
2023-01-23 02:26:22.249173: step: 604/533, loss: 0.004325867164880037
2023-01-23 02:26:23.442313: step: 608/533, loss: 0.011186790652573109
2023-01-23 02:26:24.613298: step: 612/533, loss: 0.04059867933392525
2023-01-23 02:26:25.774245: step: 616/533, loss: 0.0018993377452716231
2023-01-23 02:26:26.896079: step: 620/533, loss: 0.026645947247743607
2023-01-23 02:26:28.071513: step: 624/533, loss: 0.03933725506067276
2023-01-23 02:26:29.250130: step: 628/533, loss: 0.08598098158836365
2023-01-23 02:26:30.434693: step: 632/533, loss: 0.02301044389605522
2023-01-23 02:26:31.642525: step: 636/533, loss: 0.02397918701171875
2023-01-23 02:26:32.831972: step: 640/533, loss: 0.0008863449329510331
2023-01-23 02:26:34.022203: step: 644/533, loss: 0.004969883244484663
2023-01-23 02:26:35.224701: step: 648/533, loss: 0.02785663679242134
2023-01-23 02:26:36.430380: step: 652/533, loss: 0.03374824672937393
2023-01-23 02:26:37.592423: step: 656/533, loss: 0.03947162628173828
2023-01-23 02:26:38.785948: step: 660/533, loss: 0.006059455685317516
2023-01-23 02:26:39.963100: step: 664/533, loss: 0.00020484924607444555
2023-01-23 02:26:41.125878: step: 668/533, loss: 0.010035991668701172
2023-01-23 02:26:42.289399: step: 672/533, loss: 0.0008369446150027215
2023-01-23 02:26:43.431349: step: 676/533, loss: 0.10975103080272675
2023-01-23 02:26:44.624384: step: 680/533, loss: 0.008195066824555397
2023-01-23 02:26:45.785477: step: 684/533, loss: 0.04231100529432297
2023-01-23 02:26:46.959772: step: 688/533, loss: 0.005776023957878351
2023-01-23 02:26:48.144922: step: 692/533, loss: 0.08877818286418915
2023-01-23 02:26:49.339564: step: 696/533, loss: 0.03502826765179634
2023-01-23 02:26:50.542605: step: 700/533, loss: 0.015086794272065163
2023-01-23 02:26:51.738054: step: 704/533, loss: 0.10844888538122177
2023-01-23 02:26:52.900061: step: 708/533, loss: 0.007921409793198109
2023-01-23 02:26:54.077251: step: 712/533, loss: 0.0001663207949604839
2023-01-23 02:26:55.260676: step: 716/533, loss: 0.0853106677532196
2023-01-23 02:26:56.447502: step: 720/533, loss: 0.0296204574406147
2023-01-23 02:26:57.656936: step: 724/533, loss: 0.0007078170892782509
2023-01-23 02:26:58.813535: step: 728/533, loss: 0.018746759742498398
2023-01-23 02:26:59.989210: step: 732/533, loss: 0.0012365340953692794
2023-01-23 02:27:01.167750: step: 736/533, loss: 0.008796310983598232
2023-01-23 02:27:02.336945: step: 740/533, loss: 0.06804495304822922
2023-01-23 02:27:03.507431: step: 744/533, loss: 0.09098707139492035
2023-01-23 02:27:04.693515: step: 748/533, loss: 0.0015560149913653731
2023-01-23 02:27:05.856960: step: 752/533, loss: 0.0029108047019690275
2023-01-23 02:27:07.006544: step: 756/533, loss: 0.021446991711854935
2023-01-23 02:27:08.230513: step: 760/533, loss: 0.00452499371021986
2023-01-23 02:27:09.425849: step: 764/533, loss: 0.015717601403594017
2023-01-23 02:27:10.604329: step: 768/533, loss: 0.06093960255384445
2023-01-23 02:27:11.781634: step: 772/533, loss: 0.022891521453857422
2023-01-23 02:27:12.966318: step: 776/533, loss: 0.010380077175796032
2023-01-23 02:27:14.137808: step: 780/533, loss: 0.00443954486399889
2023-01-23 02:27:15.296641: step: 784/533, loss: 0.011400127783417702
2023-01-23 02:27:16.463364: step: 788/533, loss: 0.05018024891614914
2023-01-23 02:27:17.668998: step: 792/533, loss: 0.002664852188900113
2023-01-23 02:27:18.855615: step: 796/533, loss: 9.74655122263357e-05
2023-01-23 02:27:20.024787: step: 800/533, loss: 0.003055382054299116
2023-01-23 02:27:21.189351: step: 804/533, loss: 0.061838772147893906
2023-01-23 02:27:22.391447: step: 808/533, loss: 0.003964710049331188
2023-01-23 02:27:23.541527: step: 812/533, loss: 0.0037606239784508944
2023-01-23 02:27:24.779044: step: 816/533, loss: 0.03313946723937988
2023-01-23 02:27:25.968638: step: 820/533, loss: 0.019649790599942207
2023-01-23 02:27:27.151607: step: 824/533, loss: 0.03895380347967148
2023-01-23 02:27:28.330225: step: 828/533, loss: 0.026616811752319336
2023-01-23 02:27:29.488017: step: 832/533, loss: 0.010266399942338467
2023-01-23 02:27:30.672592: step: 836/533, loss: 0.011691570281982422
2023-01-23 02:27:31.853821: step: 840/533, loss: 0.07766079902648926
2023-01-23 02:27:33.031063: step: 844/533, loss: 0.00442085275426507
2023-01-23 02:27:34.174560: step: 848/533, loss: 0.01811370998620987
2023-01-23 02:27:35.353220: step: 852/533, loss: 0.05416903644800186
2023-01-23 02:27:36.561143: step: 856/533, loss: 0.03901004418730736
2023-01-23 02:27:37.694025: step: 860/533, loss: 6.341934204101562e-05
2023-01-23 02:27:38.866710: step: 864/533, loss: 0.011152410879731178
2023-01-23 02:27:40.059990: step: 868/533, loss: 0.09143200516700745
2023-01-23 02:27:41.270976: step: 872/533, loss: 0.016480159014463425
2023-01-23 02:27:42.519821: step: 876/533, loss: 0.018391134217381477
2023-01-23 02:27:43.708320: step: 880/533, loss: 0.020070480182766914
2023-01-23 02:27:44.856818: step: 884/533, loss: 0.0003344535653013736
2023-01-23 02:27:46.020567: step: 888/533, loss: 0.027069903910160065
2023-01-23 02:27:47.205443: step: 892/533, loss: 0.03187832981348038
2023-01-23 02:27:48.355507: step: 896/533, loss: 0.00434532156214118
2023-01-23 02:27:49.520393: step: 900/533, loss: 0.004500770475715399
2023-01-23 02:27:50.705712: step: 904/533, loss: 0.0017803192604333162
2023-01-23 02:27:51.900324: step: 908/533, loss: 0.0022199153900146484
2023-01-23 02:27:53.141347: step: 912/533, loss: 0.010034753009676933
2023-01-23 02:27:54.354910: step: 916/533, loss: 0.010270786471664906
2023-01-23 02:27:55.567755: step: 920/533, loss: 0.004616737365722656
2023-01-23 02:27:56.754786: step: 924/533, loss: 0.010496329516172409
2023-01-23 02:27:57.889490: step: 928/533, loss: 0.0013918876647949219
2023-01-23 02:27:59.081060: step: 932/533, loss: 0.03287268057465553
2023-01-23 02:28:00.250294: step: 936/533, loss: 0.01556539535522461
2023-01-23 02:28:01.405627: step: 940/533, loss: 0.05309810861945152
2023-01-23 02:28:02.584001: step: 944/533, loss: 0.0014232636895030737
2023-01-23 02:28:03.737341: step: 948/533, loss: 0.018986130133271217
2023-01-23 02:28:04.917111: step: 952/533, loss: 0.015268420800566673
2023-01-23 02:28:06.093269: step: 956/533, loss: 0.14075346291065216
2023-01-23 02:28:07.266045: step: 960/533, loss: 0.05768918991088867
2023-01-23 02:28:08.387508: step: 964/533, loss: 0.0023357390891760588
2023-01-23 02:28:09.584032: step: 968/533, loss: 0.0012866973411291838
2023-01-23 02:28:10.767000: step: 972/533, loss: 0.007906151004135609
2023-01-23 02:28:11.940000: step: 976/533, loss: 0.08674231171607971
2023-01-23 02:28:13.145681: step: 980/533, loss: 0.039389897137880325
2023-01-23 02:28:14.304069: step: 984/533, loss: 0.009799767285585403
2023-01-23 02:28:15.460992: step: 988/533, loss: 0.025008518248796463
2023-01-23 02:28:16.653124: step: 992/533, loss: 0.01917734183371067
2023-01-23 02:28:17.832386: step: 996/533, loss: 0.01778383180499077
2023-01-23 02:28:19.026578: step: 1000/533, loss: 0.006135463714599609
2023-01-23 02:28:20.195762: step: 1004/533, loss: 0.008789444342255592
2023-01-23 02:28:21.354803: step: 1008/533, loss: 0.026110364124178886
2023-01-23 02:28:22.514576: step: 1012/533, loss: 0.044086359441280365
2023-01-23 02:28:23.688844: step: 1016/533, loss: 0.004754066467285156
2023-01-23 02:28:24.907281: step: 1020/533, loss: 0.03907470777630806
2023-01-23 02:28:26.068210: step: 1024/533, loss: 0.0020124674774706364
2023-01-23 02:28:27.290117: step: 1028/533, loss: 0.04017849266529083
2023-01-23 02:28:28.463618: step: 1032/533, loss: 0.012788104824721813
2023-01-23 02:28:29.615820: step: 1036/533, loss: 0.005555343814194202
2023-01-23 02:28:30.859657: step: 1040/533, loss: 0.004494285676628351
2023-01-23 02:28:32.016283: step: 1044/533, loss: 0.0002636909484863281
2023-01-23 02:28:33.219668: step: 1048/533, loss: 0.005420684814453125
2023-01-23 02:28:34.418477: step: 1052/533, loss: 0.004572534468024969
2023-01-23 02:28:35.571686: step: 1056/533, loss: 0.07770762592554092
2023-01-23 02:28:36.725515: step: 1060/533, loss: 0.014161204919219017
2023-01-23 02:28:37.896566: step: 1064/533, loss: 0.026057055220007896
2023-01-23 02:28:39.088127: step: 1068/533, loss: 7.514953904319555e-05
2023-01-23 02:28:40.326826: step: 1072/533, loss: 0.004003399517387152
2023-01-23 02:28:41.536548: step: 1076/533, loss: 0.01516580581665039
2023-01-23 02:28:42.748907: step: 1080/533, loss: 0.0058991434052586555
2023-01-23 02:28:43.954787: step: 1084/533, loss: 0.02819213829934597
2023-01-23 02:28:45.193952: step: 1088/533, loss: 0.0011773109436035156
2023-01-23 02:28:46.378985: step: 1092/533, loss: 0.020191382616758347
2023-01-23 02:28:47.553349: step: 1096/533, loss: 0.04162616655230522
2023-01-23 02:28:48.747259: step: 1100/533, loss: 0.02677922323346138
2023-01-23 02:28:49.945938: step: 1104/533, loss: 0.0011736869346350431
2023-01-23 02:28:51.134532: step: 1108/533, loss: 0.03926978260278702
2023-01-23 02:28:52.312693: step: 1112/533, loss: 0.02059917524456978
2023-01-23 02:28:53.531682: step: 1116/533, loss: 0.04444694519042969
2023-01-23 02:28:54.745137: step: 1120/533, loss: 0.1583656370639801
2023-01-23 02:28:55.939891: step: 1124/533, loss: 0.0014865398406982422
2023-01-23 02:28:57.112062: step: 1128/533, loss: 0.036760617047548294
2023-01-23 02:28:58.295924: step: 1132/533, loss: 0.017153168097138405
2023-01-23 02:28:59.471320: step: 1136/533, loss: 0.000324058550177142
2023-01-23 02:29:00.617723: step: 1140/533, loss: 0.0009197235340252519
2023-01-23 02:29:01.769764: step: 1144/533, loss: 0.016248513013124466
2023-01-23 02:29:02.964441: step: 1148/533, loss: 0.0032559395767748356
2023-01-23 02:29:04.124730: step: 1152/533, loss: 0.0001277923583984375
2023-01-23 02:29:05.278630: step: 1156/533, loss: 0.18440285325050354
2023-01-23 02:29:06.469259: step: 1160/533, loss: 0.04303378984332085
2023-01-23 02:29:07.702194: step: 1164/533, loss: 0.0405062660574913
2023-01-23 02:29:08.894795: step: 1168/533, loss: 0.01967163011431694
2023-01-23 02:29:10.075224: step: 1172/533, loss: 0.01926717907190323
2023-01-23 02:29:11.258794: step: 1176/533, loss: 0.0012675285106524825
2023-01-23 02:29:12.435418: step: 1180/533, loss: 0.03308048099279404
2023-01-23 02:29:13.620691: step: 1184/533, loss: 0.03112502209842205
2023-01-23 02:29:14.779865: step: 1188/533, loss: 0.0011125088203698397
2023-01-23 02:29:15.932847: step: 1192/533, loss: 0.0049453736282885075
2023-01-23 02:29:17.072072: step: 1196/533, loss: 0.00047240257845260203
2023-01-23 02:29:18.243130: step: 1200/533, loss: 9.841918654274195e-05
2023-01-23 02:29:19.376033: step: 1204/533, loss: 0.00141487130895257
2023-01-23 02:29:20.528055: step: 1208/533, loss: 0.009282112121582031
2023-01-23 02:29:21.728892: step: 1212/533, loss: 0.015368938446044922
2023-01-23 02:29:22.893044: step: 1216/533, loss: 0.0258820541203022
2023-01-23 02:29:24.107151: step: 1220/533, loss: 0.0005972862127237022
2023-01-23 02:29:25.273158: step: 1224/533, loss: 0.002756786299869418
2023-01-23 02:29:26.440519: step: 1228/533, loss: 0.0035709382500499487
2023-01-23 02:29:27.646826: step: 1232/533, loss: 0.005856037139892578
2023-01-23 02:29:28.849546: step: 1236/533, loss: 0.008848332799971104
2023-01-23 02:29:30.048056: step: 1240/533, loss: 0.0033036230597645044
2023-01-23 02:29:31.223086: step: 1244/533, loss: 0.0023911476600915194
2023-01-23 02:29:32.465953: step: 1248/533, loss: 0.012393951416015625
2023-01-23 02:29:33.599804: step: 1252/533, loss: 0.0021102428436279297
2023-01-23 02:29:34.795771: step: 1256/533, loss: 0.008630752563476562
2023-01-23 02:29:35.962010: step: 1260/533, loss: 0.03329286351799965
2023-01-23 02:29:37.144224: step: 1264/533, loss: 0.00894699152559042
2023-01-23 02:29:38.301127: step: 1268/533, loss: 0.07978720963001251
2023-01-23 02:29:39.536204: step: 1272/533, loss: 0.004378318786621094
2023-01-23 02:29:40.713835: step: 1276/533, loss: 0.0025140761863440275
2023-01-23 02:29:41.959918: step: 1280/533, loss: 0.04782400280237198
2023-01-23 02:29:43.166888: step: 1284/533, loss: 0.0032793045975267887
2023-01-23 02:29:44.366326: step: 1288/533, loss: 0.0032743930350989103
2023-01-23 02:29:45.552836: step: 1292/533, loss: 0.03894253075122833
2023-01-23 02:29:46.753455: step: 1296/533, loss: 0.001995944883674383
2023-01-23 02:29:47.930194: step: 1300/533, loss: 0.016109563410282135
2023-01-23 02:29:49.099673: step: 1304/533, loss: 0.008039665408432484
2023-01-23 02:29:50.280704: step: 1308/533, loss: 0.023818302899599075
2023-01-23 02:29:51.451076: step: 1312/533, loss: 0.06377563625574112
2023-01-23 02:29:52.637972: step: 1316/533, loss: 0.0023560526315122843
2023-01-23 02:29:53.835457: step: 1320/533, loss: 0.0037340165581554174
2023-01-23 02:29:54.982508: step: 1324/533, loss: 0.008930588141083717
2023-01-23 02:29:56.162127: step: 1328/533, loss: 0.008122109808027744
2023-01-23 02:29:57.395944: step: 1332/533, loss: 0.0007085800170898438
2023-01-23 02:29:58.602160: step: 1336/533, loss: 0.00172767648473382
2023-01-23 02:29:59.808968: step: 1340/533, loss: 0.008748245425522327
2023-01-23 02:30:00.959106: step: 1344/533, loss: 0.016813278198242188
2023-01-23 02:30:02.113670: step: 1348/533, loss: 0.019668007269501686
2023-01-23 02:30:03.311822: step: 1352/533, loss: 0.00862894020974636
2023-01-23 02:30:04.495280: step: 1356/533, loss: 0.03913841396570206
2023-01-23 02:30:05.710696: step: 1360/533, loss: 0.005063533782958984
2023-01-23 02:30:06.878491: step: 1364/533, loss: 0.004771709442138672
2023-01-23 02:30:08.014482: step: 1368/533, loss: 0.010756874457001686
2023-01-23 02:30:09.184789: step: 1372/533, loss: 0.004741382785141468
2023-01-23 02:30:10.366917: step: 1376/533, loss: 0.0027503492310643196
2023-01-23 02:30:11.554152: step: 1380/533, loss: 0.011645698919892311
2023-01-23 02:30:12.740821: step: 1384/533, loss: 0.016314219683408737
2023-01-23 02:30:13.908206: step: 1388/533, loss: 0.0008418560028076172
2023-01-23 02:30:15.073787: step: 1392/533, loss: 0.03683042526245117
2023-01-23 02:30:16.259741: step: 1396/533, loss: 0.011615562252700329
2023-01-23 02:30:17.511230: step: 1400/533, loss: 0.006627941038459539
2023-01-23 02:30:18.695951: step: 1404/533, loss: 0.0002004623383982107
2023-01-23 02:30:19.870935: step: 1408/533, loss: 0.06742353737354279
2023-01-23 02:30:21.062468: step: 1412/533, loss: 0.019146442413330078
2023-01-23 02:30:22.188459: step: 1416/533, loss: 0.006477737333625555
2023-01-23 02:30:23.325920: step: 1420/533, loss: 0.0006521224859170616
2023-01-23 02:30:24.512354: step: 1424/533, loss: 0.04995422437787056
2023-01-23 02:30:25.698639: step: 1428/533, loss: 0.010791946202516556
2023-01-23 02:30:26.877627: step: 1432/533, loss: 0.0004720747529063374
2023-01-23 02:30:28.106690: step: 1436/533, loss: 0.053525160998106
2023-01-23 02:30:29.280871: step: 1440/533, loss: 0.012418174184858799
2023-01-23 02:30:30.462183: step: 1444/533, loss: 0.0002233505219919607
2023-01-23 02:30:31.639100: step: 1448/533, loss: 0.01474857423454523
2023-01-23 02:30:32.844280: step: 1452/533, loss: 0.03698024898767471
2023-01-23 02:30:34.051056: step: 1456/533, loss: 0.018057728186249733
2023-01-23 02:30:35.207595: step: 1460/533, loss: 0.003914451692253351
2023-01-23 02:30:36.358900: step: 1464/533, loss: 0.002291393233463168
2023-01-23 02:30:37.551802: step: 1468/533, loss: 0.000687933003064245
2023-01-23 02:30:38.714790: step: 1472/533, loss: 0.006572341546416283
2023-01-23 02:30:39.895953: step: 1476/533, loss: 0.017885446548461914
2023-01-23 02:30:41.068559: step: 1480/533, loss: 0.070431187748909
2023-01-23 02:30:42.308764: step: 1484/533, loss: 0.07761158794164658
2023-01-23 02:30:43.478522: step: 1488/533, loss: 0.018985940143465996
2023-01-23 02:30:44.705354: step: 1492/533, loss: 0.0036679268814623356
2023-01-23 02:30:45.908285: step: 1496/533, loss: 0.001142311142757535
2023-01-23 02:30:47.118901: step: 1500/533, loss: 0.05302829667925835
2023-01-23 02:30:48.290309: step: 1504/533, loss: 0.008706331253051758
2023-01-23 02:30:49.502511: step: 1508/533, loss: 0.014579296112060547
2023-01-23 02:30:50.706053: step: 1512/533, loss: 0.03141956403851509
2023-01-23 02:30:51.879387: step: 1516/533, loss: 0.04047403484582901
2023-01-23 02:30:53.100091: step: 1520/533, loss: 0.0005851745372638106
2023-01-23 02:30:54.267342: step: 1524/533, loss: 0.06057176738977432
2023-01-23 02:30:55.477639: step: 1528/533, loss: 0.00021476745314430445
2023-01-23 02:30:56.643080: step: 1532/533, loss: 0.01809978298842907
2023-01-23 02:30:57.762958: step: 1536/533, loss: 0.02373666875064373
2023-01-23 02:30:58.947036: step: 1540/533, loss: 0.001889038016088307
2023-01-23 02:31:00.142241: step: 1544/533, loss: 0.007563877385109663
2023-01-23 02:31:01.311195: step: 1548/533, loss: 0.011583710089325905
2023-01-23 02:31:02.514991: step: 1552/533, loss: 0.006509304046630859
2023-01-23 02:31:03.706725: step: 1556/533, loss: 0.00034122465876862407
2023-01-23 02:31:04.878189: step: 1560/533, loss: 0.003436517668887973
2023-01-23 02:31:06.053778: step: 1564/533, loss: 0.023935507982969284
2023-01-23 02:31:07.235777: step: 1568/533, loss: 0.05130348354578018
2023-01-23 02:31:08.419588: step: 1572/533, loss: 0.0046652317978441715
2023-01-23 02:31:09.625599: step: 1576/533, loss: 0.006455517373979092
2023-01-23 02:31:10.836483: step: 1580/533, loss: 0.0006789207691326737
2023-01-23 02:31:12.002749: step: 1584/533, loss: 0.0489516481757164
2023-01-23 02:31:13.208190: step: 1588/533, loss: 0.004643535707145929
2023-01-23 02:31:14.374433: step: 1592/533, loss: 0.0033933641389012337
2023-01-23 02:31:15.535629: step: 1596/533, loss: 0.03144850954413414
2023-01-23 02:31:16.714674: step: 1600/533, loss: 0.0007343292818404734
2023-01-23 02:31:17.884463: step: 1604/533, loss: 0.0011828423012048006
2023-01-23 02:31:19.091347: step: 1608/533, loss: 0.024991797283291817
2023-01-23 02:31:20.276526: step: 1612/533, loss: 0.02314753644168377
2023-01-23 02:31:21.517267: step: 1616/533, loss: 0.008723830804228783
2023-01-23 02:31:22.648224: step: 1620/533, loss: 0.0005520820850506425
2023-01-23 02:31:23.803385: step: 1624/533, loss: 0.010486459359526634
2023-01-23 02:31:24.988076: step: 1628/533, loss: 0.007105732336640358
2023-01-23 02:31:26.181546: step: 1632/533, loss: 0.1719016134738922
2023-01-23 02:31:27.341831: step: 1636/533, loss: 0.00025384427863173187
2023-01-23 02:31:28.528795: step: 1640/533, loss: 7.600784010719508e-05
2023-01-23 02:31:29.743619: step: 1644/533, loss: 0.0025642395485192537
2023-01-23 02:31:30.956041: step: 1648/533, loss: 0.03659496456384659
2023-01-23 02:31:32.124132: step: 1652/533, loss: 0.004700374789535999
2023-01-23 02:31:33.307960: step: 1656/533, loss: 0.011045646853744984
2023-01-23 02:31:34.479309: step: 1660/533, loss: 0.08599185943603516
2023-01-23 02:31:35.666022: step: 1664/533, loss: 0.008962058462202549
2023-01-23 02:31:36.853128: step: 1668/533, loss: 0.03727264702320099
2023-01-23 02:31:38.055834: step: 1672/533, loss: 0.005661964416503906
2023-01-23 02:31:39.248489: step: 1676/533, loss: 5.511342525482178
2023-01-23 02:31:40.429378: step: 1680/533, loss: 0.12205095589160919
2023-01-23 02:31:41.606998: step: 1684/533, loss: 0.043882180005311966
2023-01-23 02:31:42.781547: step: 1688/533, loss: 0.007207632064819336
2023-01-23 02:31:43.987839: step: 1692/533, loss: 0.054799843579530716
2023-01-23 02:31:45.182470: step: 1696/533, loss: 0.024207402020692825
2023-01-23 02:31:46.330022: step: 1700/533, loss: 0.009629536420106888
2023-01-23 02:31:47.506421: step: 1704/533, loss: 0.029888534918427467
2023-01-23 02:31:48.676447: step: 1708/533, loss: 0.03759927675127983
2023-01-23 02:31:49.840633: step: 1712/533, loss: 0.009524344466626644
2023-01-23 02:31:51.036219: step: 1716/533, loss: 0.5328686237335205
2023-01-23 02:31:52.249492: step: 1720/533, loss: 0.0009124755742959678
2023-01-23 02:31:53.428543: step: 1724/533, loss: 0.02554798126220703
2023-01-23 02:31:54.601911: step: 1728/533, loss: 0.005244636442512274
2023-01-23 02:31:55.794608: step: 1732/533, loss: 0.01390447560697794
2023-01-23 02:31:56.992148: step: 1736/533, loss: 0.0038839338812977076
2023-01-23 02:31:58.184911: step: 1740/533, loss: 0.008599664084613323
2023-01-23 02:31:59.361602: step: 1744/533, loss: 0.026338864117860794
2023-01-23 02:32:00.598859: step: 1748/533, loss: 0.001549529959447682
2023-01-23 02:32:01.781198: step: 1752/533, loss: 0.0003589630068745464
2023-01-23 02:32:03.002951: step: 1756/533, loss: 0.0014263152843341231
2023-01-23 02:32:04.208860: step: 1760/533, loss: 0.057195089757442474
2023-01-23 02:32:05.402132: step: 1764/533, loss: 0.025406265631318092
2023-01-23 02:32:06.572927: step: 1768/533, loss: 0.0036479949485510588
2023-01-23 02:32:07.792819: step: 1772/533, loss: 0.13120490312576294
2023-01-23 02:32:08.937941: step: 1776/533, loss: 0.001035499619320035
2023-01-23 02:32:10.104831: step: 1780/533, loss: 0.001547098159790039
2023-01-23 02:32:11.317913: step: 1784/533, loss: 0.0009371757623739541
2023-01-23 02:32:12.547383: step: 1788/533, loss: 0.01241159439086914
2023-01-23 02:32:13.732740: step: 1792/533, loss: 0.16809825599193573
2023-01-23 02:32:14.932898: step: 1796/533, loss: 0.007153129670768976
2023-01-23 02:32:16.082992: step: 1800/533, loss: 0.0023974417708814144
2023-01-23 02:32:17.280774: step: 1804/533, loss: 0.04204883426427841
2023-01-23 02:32:18.431038: step: 1808/533, loss: 0.013253641314804554
2023-01-23 02:32:19.607064: step: 1812/533, loss: 0.03452930226922035
2023-01-23 02:32:20.859870: step: 1816/533, loss: 0.022757722064852715
2023-01-23 02:32:22.045822: step: 1820/533, loss: 0.03851603344082832
2023-01-23 02:32:23.195560: step: 1824/533, loss: 0.0040035247802734375
2023-01-23 02:32:24.371236: step: 1828/533, loss: 0.05450177192687988
2023-01-23 02:32:25.517710: step: 1832/533, loss: 0.007073306944221258
2023-01-23 02:32:26.677194: step: 1836/533, loss: 0.08658181130886078
2023-01-23 02:32:27.890517: step: 1840/533, loss: 0.0004989624139852822
2023-01-23 02:32:29.098779: step: 1844/533, loss: 0.012637806124985218
2023-01-23 02:32:30.367255: step: 1848/533, loss: 0.017045021057128906
2023-01-23 02:32:31.533515: step: 1852/533, loss: 0.021886637434363365
2023-01-23 02:32:32.730089: step: 1856/533, loss: 0.04786987230181694
2023-01-23 02:32:33.933128: step: 1860/533, loss: 0.04563789442181587
2023-01-23 02:32:35.103734: step: 1864/533, loss: 0.022282185032963753
2023-01-23 02:32:36.267746: step: 1868/533, loss: 0.03771495819091797
2023-01-23 02:32:37.444928: step: 1872/533, loss: 0.027369119226932526
2023-01-23 02:32:38.688278: step: 1876/533, loss: 0.6058931350708008
2023-01-23 02:32:39.841598: step: 1880/533, loss: 0.6500256657600403
2023-01-23 02:32:41.024362: step: 1884/533, loss: 0.04814014583826065
2023-01-23 02:32:42.187527: step: 1888/533, loss: 0.029430102556943893
2023-01-23 02:32:43.408005: step: 1892/533, loss: 0.0046901702880859375
2023-01-23 02:32:44.610915: step: 1896/533, loss: 0.05810112878680229
2023-01-23 02:32:45.802022: step: 1900/533, loss: 0.010535335168242455
2023-01-23 02:32:47.019168: step: 1904/533, loss: 0.0058329105377197266
2023-01-23 02:32:48.174829: step: 1908/533, loss: 0.007765769958496094
2023-01-23 02:32:49.349963: step: 1912/533, loss: 0.004822921939194202
2023-01-23 02:32:50.560521: step: 1916/533, loss: 0.000716781651135534
2023-01-23 02:32:51.765643: step: 1920/533, loss: 0.008598709478974342
2023-01-23 02:32:52.936825: step: 1924/533, loss: 0.05542631447315216
2023-01-23 02:32:54.152274: step: 1928/533, loss: 0.0026082992553710938
2023-01-23 02:32:55.327262: step: 1932/533, loss: 0.041727352887392044
2023-01-23 02:32:56.537344: step: 1936/533, loss: 0.001020717667415738
2023-01-23 02:32:57.690751: step: 1940/533, loss: 0.003590202424675226
2023-01-23 02:32:58.851420: step: 1944/533, loss: 0.009755706414580345
2023-01-23 02:33:00.067574: step: 1948/533, loss: 0.00464973459020257
2023-01-23 02:33:01.265091: step: 1952/533, loss: 0.04869265481829643
2023-01-23 02:33:02.464967: step: 1956/533, loss: 0.03931822627782822
2023-01-23 02:33:03.597749: step: 1960/533, loss: 0.03744201734662056
2023-01-23 02:33:04.760865: step: 1964/533, loss: 0.10401459038257599
2023-01-23 02:33:05.946436: step: 1968/533, loss: 0.0023281096946448088
2023-01-23 02:33:07.136489: step: 1972/533, loss: 0.0008807182312011719
2023-01-23 02:33:08.359356: step: 1976/533, loss: 0.020523929968476295
2023-01-23 02:33:09.533704: step: 1980/533, loss: 0.0007357597351074219
2023-01-23 02:33:10.726547: step: 1984/533, loss: 0.04567699506878853
2023-01-23 02:33:11.918607: step: 1988/533, loss: 0.0010856628650799394
2023-01-23 02:33:13.096778: step: 1992/533, loss: 0.003289890242740512
2023-01-23 02:33:14.265388: step: 1996/533, loss: 0.034958742558956146
2023-01-23 02:33:15.439276: step: 2000/533, loss: 0.0006689071888104081
2023-01-23 02:33:16.615261: step: 2004/533, loss: 0.05834522470831871
2023-01-23 02:33:17.810497: step: 2008/533, loss: 0.00016880035400390625
2023-01-23 02:33:18.976061: step: 2012/533, loss: 0.08300953358411789
2023-01-23 02:33:20.135738: step: 2016/533, loss: 0.0039192200638353825
2023-01-23 02:33:21.337739: step: 2020/533, loss: 0.002334976103156805
2023-01-23 02:33:22.500604: step: 2024/533, loss: 0.06384678184986115
2023-01-23 02:33:23.684288: step: 2028/533, loss: 0.011546612717211246
2023-01-23 02:33:24.877314: step: 2032/533, loss: 0.005102920811623335
2023-01-23 02:33:26.025475: step: 2036/533, loss: 0.457741916179657
2023-01-23 02:33:27.229917: step: 2040/533, loss: 0.027019884437322617
2023-01-23 02:33:28.401281: step: 2044/533, loss: 0.07772817462682724
2023-01-23 02:33:29.630017: step: 2048/533, loss: 9.927750215865672e-05
2023-01-23 02:33:30.849783: step: 2052/533, loss: 0.024082567542791367
2023-01-23 02:33:32.035828: step: 2056/533, loss: 0.02911539003252983
2023-01-23 02:33:33.226973: step: 2060/533, loss: 0.053293369710445404
2023-01-23 02:33:34.415522: step: 2064/533, loss: 0.003379488131031394
2023-01-23 02:33:35.598220: step: 2068/533, loss: 0.007106208708137274
2023-01-23 02:33:36.797212: step: 2072/533, loss: 0.03746318817138672
2023-01-23 02:33:37.991412: step: 2076/533, loss: 0.041051484644412994
2023-01-23 02:33:39.200165: step: 2080/533, loss: 0.0014678002335131168
2023-01-23 02:33:40.365935: step: 2084/533, loss: 0.023686887696385384
2023-01-23 02:33:41.543534: step: 2088/533, loss: 0.02539215050637722
2023-01-23 02:33:42.729267: step: 2092/533, loss: 0.002061557723209262
2023-01-23 02:33:43.982797: step: 2096/533, loss: 0.04375810921192169
2023-01-23 02:33:45.161772: step: 2100/533, loss: 0.019135857000947
2023-01-23 02:33:46.349047: step: 2104/533, loss: 0.0030751230660825968
2023-01-23 02:33:47.557534: step: 2108/533, loss: 0.08152560889720917
2023-01-23 02:33:48.739324: step: 2112/533, loss: 0.026894284412264824
2023-01-23 02:33:49.918712: step: 2116/533, loss: 0.04390363767743111
2023-01-23 02:33:51.097176: step: 2120/533, loss: 0.005885505583137274
2023-01-23 02:33:52.274999: step: 2124/533, loss: 0.011088562197983265
2023-01-23 02:33:53.489186: step: 2128/533, loss: 0.04149675369262695
2023-01-23 02:33:54.745566: step: 2132/533, loss: 0.061532117426395416
==================================================
Loss: 0.041
--------------------
Dev: {'event': {'p': 0.6240681576144835, 'r': 0.7802929427430093, 'f1': 0.6934911242603551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6589229144667371, 'r': 0.7979539641943734, 'f1': 0.7218045112781956}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5853658536585366, 'r': 0.8888888888888888, 'f1': 0.7058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6415094339622641, 'r': 0.5396825396825397, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.4878048780487805, 'r': 0.5555555555555556, 'f1': 0.5194805194805195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:34:36.002729: step: 4/533, loss: 0.05608072504401207
2023-01-23 02:34:37.170363: step: 8/533, loss: 0.0068302154541015625
2023-01-23 02:34:38.329777: step: 12/533, loss: 0.052759744226932526
2023-01-23 02:34:39.564154: step: 16/533, loss: 0.008755017071962357
2023-01-23 02:34:40.749700: step: 20/533, loss: 0.006179142277687788
2023-01-23 02:34:41.909896: step: 24/533, loss: 0.049042705446481705
2023-01-23 02:34:43.069802: step: 28/533, loss: 0.003762722248211503
2023-01-23 02:34:44.296602: step: 32/533, loss: 0.04843645170331001
2023-01-23 02:34:45.482200: step: 36/533, loss: 0.1207214817404747
2023-01-23 02:34:46.647498: step: 40/533, loss: 0.027240967378020287
2023-01-23 02:34:47.815017: step: 44/533, loss: 0.06505122780799866
2023-01-23 02:34:49.017894: step: 48/533, loss: 0.001573848770931363
2023-01-23 02:34:50.222641: step: 52/533, loss: 0.006667900364845991
2023-01-23 02:34:51.425389: step: 56/533, loss: 0.005202674772590399
2023-01-23 02:34:52.653255: step: 60/533, loss: 0.0001806259242584929
2023-01-23 02:34:53.819759: step: 64/533, loss: 0.008336687460541725
2023-01-23 02:34:55.043038: step: 68/533, loss: 0.0003641128714662045
2023-01-23 02:34:56.184692: step: 72/533, loss: 0.0024078369606286287
2023-01-23 02:34:57.360126: step: 76/533, loss: 0.013912821188569069
2023-01-23 02:34:58.507669: step: 80/533, loss: 0.0032484056428074837
2023-01-23 02:34:59.670419: step: 84/533, loss: 0.002562236739322543
2023-01-23 02:35:00.841280: step: 88/533, loss: 0.0006509781233035028
2023-01-23 02:35:02.007473: step: 92/533, loss: 0.011055183596909046
2023-01-23 02:35:03.166578: step: 96/533, loss: 0.00506095914170146
2023-01-23 02:35:04.373287: step: 100/533, loss: 0.015534305945038795
2023-01-23 02:35:05.583864: step: 104/533, loss: 0.028289128094911575
2023-01-23 02:35:06.760733: step: 108/533, loss: 0.02078886143863201
2023-01-23 02:35:07.939439: step: 112/533, loss: 0.004430580418556929
2023-01-23 02:35:09.119110: step: 116/533, loss: 0.0007699966663494706
2023-01-23 02:35:10.331622: step: 120/533, loss: 0.0001239776611328125
2023-01-23 02:35:11.482708: step: 124/533, loss: 2.9805119037628174
2023-01-23 02:35:12.638002: step: 128/533, loss: 0.009613228030502796
2023-01-23 02:35:13.795287: step: 132/533, loss: 0.004459572024643421
2023-01-23 02:35:14.949907: step: 136/533, loss: 0.004940084647387266
2023-01-23 02:35:16.094964: step: 140/533, loss: 0.25174829363822937
2023-01-23 02:35:17.259936: step: 144/533, loss: 0.03089718706905842
2023-01-23 02:35:18.458744: step: 148/533, loss: 0.023326683789491653
2023-01-23 02:35:19.605387: step: 152/533, loss: 0.023358916863799095
2023-01-23 02:35:20.785102: step: 156/533, loss: 0.005521631333976984
2023-01-23 02:35:21.936264: step: 160/533, loss: 0.0020106316078454256
2023-01-23 02:35:23.133265: step: 164/533, loss: 0.04149749502539635
2023-01-23 02:35:24.289116: step: 168/533, loss: 0.003925132565200329
2023-01-23 02:35:25.459987: step: 172/533, loss: 0.012125111185014248
2023-01-23 02:35:26.640729: step: 176/533, loss: 0.009181595407426357
2023-01-23 02:35:27.802766: step: 180/533, loss: 0.06652164459228516
2023-01-23 02:35:29.000870: step: 184/533, loss: 0.00015954971604514867
2023-01-23 02:35:30.177608: step: 188/533, loss: 0.001555633614771068
2023-01-23 02:35:31.383967: step: 192/533, loss: 0.003946781158447266
2023-01-23 02:35:32.565692: step: 196/533, loss: 0.00089263916015625
2023-01-23 02:35:33.696586: step: 200/533, loss: 0.10044444352388382
2023-01-23 02:35:34.832586: step: 204/533, loss: 0.0017809867858886719
2023-01-23 02:35:36.030216: step: 208/533, loss: 0.0005335807800292969
2023-01-23 02:35:37.190436: step: 212/533, loss: 0.0393100269138813
2023-01-23 02:35:38.350335: step: 216/533, loss: 0.023301126435399055
2023-01-23 02:35:39.531085: step: 220/533, loss: 0.004351234529167414
2023-01-23 02:35:40.697497: step: 224/533, loss: 0.01137557066977024
2023-01-23 02:35:41.861606: step: 228/533, loss: 0.0106497285887599
2023-01-23 02:35:43.031882: step: 232/533, loss: 0.0031280517578125
2023-01-23 02:35:44.249725: step: 236/533, loss: 0.004107809159904718
2023-01-23 02:35:45.408366: step: 240/533, loss: 0.008036613464355469
2023-01-23 02:35:46.567119: step: 244/533, loss: 0.0030488967895507812
2023-01-23 02:35:47.680408: step: 248/533, loss: 0.004109001252800226
2023-01-23 02:35:48.827521: step: 252/533, loss: 0.04989318922162056
2023-01-23 02:35:50.021141: step: 256/533, loss: 0.018237780779600143
2023-01-23 02:35:51.162367: step: 260/533, loss: 0.005792808718979359
2023-01-23 02:35:52.309359: step: 264/533, loss: 0.001018607639707625
2023-01-23 02:35:53.448003: step: 268/533, loss: 0.024995993822813034
2023-01-23 02:35:54.596762: step: 272/533, loss: 0.0034825324546545744
2023-01-23 02:35:55.742899: step: 276/533, loss: 0.18073216080665588
2023-01-23 02:35:56.960775: step: 280/533, loss: 0.009951591491699219
2023-01-23 02:35:58.115342: step: 284/533, loss: 0.0006700515514239669
2023-01-23 02:35:59.294107: step: 288/533, loss: 0.000870227871928364
2023-01-23 02:36:00.434574: step: 292/533, loss: 0.011655330657958984
2023-01-23 02:36:01.606669: step: 296/533, loss: 0.05896587669849396
2023-01-23 02:36:02.792067: step: 300/533, loss: 0.09211063385009766
2023-01-23 02:36:03.952767: step: 304/533, loss: 0.0387604720890522
2023-01-23 02:36:05.124463: step: 308/533, loss: 0.08025378733873367
2023-01-23 02:36:06.312616: step: 312/533, loss: 0.037885189056396484
2023-01-23 02:36:07.484916: step: 316/533, loss: 0.21114139258861542
2023-01-23 02:36:08.673657: step: 320/533, loss: 0.002173805143684149
2023-01-23 02:36:09.841403: step: 324/533, loss: -4.196166628389619e-06
2023-01-23 02:36:11.009540: step: 328/533, loss: 0.0019367218483239412
2023-01-23 02:36:12.176054: step: 332/533, loss: 0.05145730823278427
2023-01-23 02:36:13.352433: step: 336/533, loss: 0.006091403774917126
2023-01-23 02:36:14.500386: step: 340/533, loss: 0.006446457002311945
2023-01-23 02:36:15.672927: step: 344/533, loss: 0.00121221540030092
2023-01-23 02:36:16.861510: step: 348/533, loss: 0.018650149926543236
2023-01-23 02:36:18.006940: step: 352/533, loss: 0.0018839837284758687
2023-01-23 02:36:19.198518: step: 356/533, loss: 0.0008254051208496094
2023-01-23 02:36:20.414506: step: 360/533, loss: 0.01699669286608696
2023-01-23 02:36:21.650419: step: 364/533, loss: 0.02749962918460369
2023-01-23 02:36:22.854529: step: 368/533, loss: 0.013296891003847122
2023-01-23 02:36:24.030110: step: 372/533, loss: 0.009439850226044655
2023-01-23 02:36:25.201385: step: 376/533, loss: 0.02125081978738308
2023-01-23 02:36:26.401277: step: 380/533, loss: 0.034911155700683594
2023-01-23 02:36:27.585762: step: 384/533, loss: 0.0003604888916015625
2023-01-23 02:36:28.754348: step: 388/533, loss: 0.0019594430923461914
2023-01-23 02:36:29.941344: step: 392/533, loss: 0.08834762871265411
2023-01-23 02:36:31.094888: step: 396/533, loss: 0.014138413593173027
2023-01-23 02:36:32.282338: step: 400/533, loss: 0.003722858615219593
2023-01-23 02:36:33.439907: step: 404/533, loss: 0.01670980453491211
2023-01-23 02:36:34.591741: step: 408/533, loss: 0.013614273630082607
2023-01-23 02:36:35.768994: step: 412/533, loss: 0.10627670586109161
2023-01-23 02:36:36.956511: step: 416/533, loss: 0.03528871759772301
2023-01-23 02:36:38.127181: step: 420/533, loss: 0.00450520496815443
2023-01-23 02:36:39.304738: step: 424/533, loss: 0.0008152961963787675
2023-01-23 02:36:40.529689: step: 428/533, loss: 0.0012554168934002519
2023-01-23 02:36:41.651110: step: 432/533, loss: 0.04270394146442413
2023-01-23 02:36:42.800195: step: 436/533, loss: 0.0003074169217143208
2023-01-23 02:36:43.955864: step: 440/533, loss: 0.042651571333408356
2023-01-23 02:36:45.110363: step: 444/533, loss: 0.07190332561731339
2023-01-23 02:36:46.288870: step: 448/533, loss: 0.02822551690042019
2023-01-23 02:36:47.464480: step: 452/533, loss: 0.03028698079288006
2023-01-23 02:36:48.668366: step: 456/533, loss: 0.012123984284698963
2023-01-23 02:36:49.887358: step: 460/533, loss: 0.006522560026496649
2023-01-23 02:36:51.081776: step: 464/533, loss: 0.01727910153567791
2023-01-23 02:36:52.256974: step: 468/533, loss: 0.05306796729564667
2023-01-23 02:36:53.413513: step: 472/533, loss: 0.004248524084687233
2023-01-23 02:36:54.640230: step: 476/533, loss: 0.002651214599609375
2023-01-23 02:36:55.797966: step: 480/533, loss: 0.002184104872867465
2023-01-23 02:36:56.961721: step: 484/533, loss: 0.02514057233929634
2023-01-23 02:36:58.128612: step: 488/533, loss: 0.00786514300853014
2023-01-23 02:36:59.290991: step: 492/533, loss: 0.018297530710697174
2023-01-23 02:37:00.461792: step: 496/533, loss: 0.003752422519028187
2023-01-23 02:37:01.661239: step: 500/533, loss: 0.01578083075582981
2023-01-23 02:37:02.811770: step: 504/533, loss: 0.0007875442388467491
2023-01-23 02:37:03.983268: step: 508/533, loss: 0.00044369700481183827
2023-01-23 02:37:05.169937: step: 512/533, loss: 0.0015524388290941715
2023-01-23 02:37:06.344439: step: 516/533, loss: 0.009407234378159046
2023-01-23 02:37:07.498871: step: 520/533, loss: 0.006123637780547142
2023-01-23 02:37:08.669413: step: 524/533, loss: 0.007503509521484375
2023-01-23 02:37:09.850824: step: 528/533, loss: 0.010577201843261719
2023-01-23 02:37:11.015523: step: 532/533, loss: 0.026291703805327415
2023-01-23 02:37:12.223664: step: 536/533, loss: 0.0040225982666015625
2023-01-23 02:37:13.390995: step: 540/533, loss: 0.0010875702137127519
2023-01-23 02:37:14.598094: step: 544/533, loss: 0.07167740166187286
2023-01-23 02:37:15.763261: step: 548/533, loss: 0.00013570785813499242
2023-01-23 02:37:16.939575: step: 552/533, loss: 0.6052299737930298
2023-01-23 02:37:18.102307: step: 556/533, loss: 0.00020322800264693797
2023-01-23 02:37:19.245439: step: 560/533, loss: 0.4142410159111023
2023-01-23 02:37:20.419370: step: 564/533, loss: 0.0003871917724609375
2023-01-23 02:37:21.594492: step: 568/533, loss: 0.0008869171142578125
2023-01-23 02:37:22.785440: step: 572/533, loss: 0.012749576941132545
2023-01-23 02:37:23.953586: step: 576/533, loss: 0.02688579633831978
2023-01-23 02:37:25.125319: step: 580/533, loss: 0.06965198367834091
2023-01-23 02:37:26.286658: step: 584/533, loss: 0.012274456210434437
2023-01-23 02:37:27.456645: step: 588/533, loss: 0.0014977456303313375
2023-01-23 02:37:28.648247: step: 592/533, loss: 0.08007049560546875
2023-01-23 02:37:29.827136: step: 596/533, loss: 0.0019989013671875
2023-01-23 02:37:30.969972: step: 600/533, loss: 0.00740737933665514
2023-01-23 02:37:32.159530: step: 604/533, loss: 0.059052374213933945
2023-01-23 02:37:33.346934: step: 608/533, loss: 8.37326078908518e-05
2023-01-23 02:37:34.508643: step: 612/533, loss: 0.00994024332612753
2023-01-23 02:37:35.642155: step: 616/533, loss: 0.02215109020471573
2023-01-23 02:37:36.830047: step: 620/533, loss: 0.005905819125473499
2023-01-23 02:37:38.022101: step: 624/533, loss: 0.0372898131608963
2023-01-23 02:37:39.226710: step: 628/533, loss: 0.04229144752025604
2023-01-23 02:37:40.398349: step: 632/533, loss: 0.004037666134536266
2023-01-23 02:37:41.551879: step: 636/533, loss: 0.00018367767916060984
2023-01-23 02:37:42.732841: step: 640/533, loss: 0.03332529217004776
2023-01-23 02:37:43.915600: step: 644/533, loss: 0.018091201782226562
2023-01-23 02:37:45.077548: step: 648/533, loss: 0.016399670392274857
2023-01-23 02:37:46.255390: step: 652/533, loss: 0.0014136313693597913
2023-01-23 02:37:47.468086: step: 656/533, loss: 0.0541507825255394
2023-01-23 02:37:48.641719: step: 660/533, loss: 0.0584072582423687
2023-01-23 02:37:49.862589: step: 664/533, loss: 0.05647401884198189
2023-01-23 02:37:51.043469: step: 668/533, loss: 1.0480600595474243
2023-01-23 02:37:52.243032: step: 672/533, loss: 0.022043418139219284
2023-01-23 02:37:53.439226: step: 676/533, loss: 0.0027786255814135075
2023-01-23 02:37:54.643131: step: 680/533, loss: 0.010172463022172451
2023-01-23 02:37:55.855957: step: 684/533, loss: 0.0022869110107421875
2023-01-23 02:37:57.021417: step: 688/533, loss: 0.0011724472278729081
2023-01-23 02:37:58.196415: step: 692/533, loss: 0.005409527570009232
2023-01-23 02:37:59.349981: step: 696/533, loss: 0.009091068059206009
2023-01-23 02:38:00.498131: step: 700/533, loss: 0.03131723403930664
2023-01-23 02:38:01.695555: step: 704/533, loss: 0.017778396606445312
2023-01-23 02:38:02.866171: step: 708/533, loss: 0.002792692044749856
2023-01-23 02:38:04.028696: step: 712/533, loss: 0.021972371265292168
2023-01-23 02:38:05.205397: step: 716/533, loss: 0.030235623940825462
2023-01-23 02:38:06.379942: step: 720/533, loss: 0.05753831937909126
2023-01-23 02:38:07.534652: step: 724/533, loss: 0.028432749211788177
2023-01-23 02:38:08.727758: step: 728/533, loss: 8.76426711329259e-05
2023-01-23 02:38:09.927216: step: 732/533, loss: 0.04440498352050781
2023-01-23 02:38:11.053490: step: 736/533, loss: 7.534026735811494e-06
2023-01-23 02:38:12.230925: step: 740/533, loss: 0.0031850815284997225
2023-01-23 02:38:13.404276: step: 744/533, loss: 0.0006715774652548134
2023-01-23 02:38:14.563795: step: 748/533, loss: 0.010947704315185547
2023-01-23 02:38:15.783730: step: 752/533, loss: 0.0019267082680016756
2023-01-23 02:38:16.976341: step: 756/533, loss: 0.05553417652845383
2023-01-23 02:38:18.145778: step: 760/533, loss: 0.06920681148767471
2023-01-23 02:38:19.342471: step: 764/533, loss: 0.029787994921207428
2023-01-23 02:38:20.542127: step: 768/533, loss: 0.021555567160248756
2023-01-23 02:38:21.698560: step: 772/533, loss: 0.017038488760590553
2023-01-23 02:38:22.884071: step: 776/533, loss: 1.717919111251831
2023-01-23 02:38:24.049106: step: 780/533, loss: 0.005867290776222944
2023-01-23 02:38:25.180173: step: 784/533, loss: 0.09713178873062134
2023-01-23 02:38:26.339037: step: 788/533, loss: 0.036733344197273254
2023-01-23 02:38:27.544080: step: 792/533, loss: 0.019828511402010918
2023-01-23 02:38:28.717087: step: 796/533, loss: 0.0029081343673169613
2023-01-23 02:38:29.937448: step: 800/533, loss: 0.017275989055633545
2023-01-23 02:38:31.105319: step: 804/533, loss: 0.09756974875926971
2023-01-23 02:38:32.288583: step: 808/533, loss: 0.005640506744384766
2023-01-23 02:38:33.486840: step: 812/533, loss: 0.0070188045501708984
2023-01-23 02:38:34.649669: step: 816/533, loss: 0.007050991524010897
2023-01-23 02:38:35.862348: step: 820/533, loss: 0.00012218952178955078
2023-01-23 02:38:37.029384: step: 824/533, loss: 0.0050903321243822575
2023-01-23 02:38:38.222977: step: 828/533, loss: 0.00038170814514160156
2023-01-23 02:38:39.373768: step: 832/533, loss: 6.055832272977568e-06
2023-01-23 02:38:40.551351: step: 836/533, loss: 0.11572265625
2023-01-23 02:38:41.728633: step: 840/533, loss: 0.0002931595081463456
2023-01-23 02:38:42.892170: step: 844/533, loss: 0.03839264065027237
2023-01-23 02:38:44.111947: step: 848/533, loss: 0.0022394179832190275
2023-01-23 02:38:45.293932: step: 852/533, loss: 0.006460762117058039
2023-01-23 02:38:46.482492: step: 856/533, loss: 0.005555248819291592
2023-01-23 02:38:47.667174: step: 860/533, loss: 0.006723976228386164
2023-01-23 02:38:48.836320: step: 864/533, loss: 0.08497696369886398
2023-01-23 02:38:50.026319: step: 868/533, loss: 0.016167260706424713
2023-01-23 02:38:51.209904: step: 872/533, loss: 0.0004943847889080644
2023-01-23 02:38:52.425726: step: 876/533, loss: 0.05033750459551811
2023-01-23 02:38:53.582347: step: 880/533, loss: 0.004552364349365234
2023-01-23 02:38:54.755854: step: 884/533, loss: 0.00016300679999403656
2023-01-23 02:38:55.921539: step: 888/533, loss: 0.16002637147903442
2023-01-23 02:38:57.076828: step: 892/533, loss: 0.0014913559425622225
2023-01-23 02:38:58.224781: step: 896/533, loss: 0.005386924836784601
2023-01-23 02:38:59.401701: step: 900/533, loss: 0.015250921249389648
2023-01-23 02:39:00.593844: step: 904/533, loss: 0.01175675354897976
2023-01-23 02:39:01.800088: step: 908/533, loss: 0.04188823699951172
2023-01-23 02:39:02.962625: step: 912/533, loss: 0.023948539048433304
2023-01-23 02:39:04.158424: step: 916/533, loss: 0.011065912432968616
2023-01-23 02:39:05.355768: step: 920/533, loss: 0.0011293889256194234
2023-01-23 02:39:06.603460: step: 924/533, loss: 0.02864704094827175
2023-01-23 02:39:07.806809: step: 928/533, loss: 0.00133857736364007
2023-01-23 02:39:08.933596: step: 932/533, loss: 0.008938217535614967
2023-01-23 02:39:10.106692: step: 936/533, loss: 0.02033844031393528
2023-01-23 02:39:11.345899: step: 940/533, loss: 0.003681755159050226
2023-01-23 02:39:12.497946: step: 944/533, loss: 0.017348384484648705
2023-01-23 02:39:13.698243: step: 948/533, loss: 0.18990212678909302
2023-01-23 02:39:14.849519: step: 952/533, loss: 0.0006432533264160156
2023-01-23 02:39:16.046207: step: 956/533, loss: 0.0032904627732932568
2023-01-23 02:39:17.222539: step: 960/533, loss: 0.0005182266468182206
2023-01-23 02:39:18.384978: step: 964/533, loss: 0.003928565885871649
2023-01-23 02:39:19.589220: step: 968/533, loss: 0.029495621100068092
2023-01-23 02:39:20.762247: step: 972/533, loss: 0.00980234146118164
2023-01-23 02:39:21.949316: step: 976/533, loss: 0.01341257058084011
2023-01-23 02:39:23.111154: step: 980/533, loss: 0.16279855370521545
2023-01-23 02:39:24.309194: step: 984/533, loss: 0.1024242416024208
2023-01-23 02:39:25.428944: step: 988/533, loss: 0.0001791000395314768
2023-01-23 02:39:26.589895: step: 992/533, loss: 0.021137427538633347
2023-01-23 02:39:27.775529: step: 996/533, loss: 0.008636856451630592
2023-01-23 02:39:28.975993: step: 1000/533, loss: 0.0004884600639343262
2023-01-23 02:39:30.162731: step: 1004/533, loss: 0.08552370220422745
2023-01-23 02:39:31.375114: step: 1008/533, loss: 0.026104547083377838
2023-01-23 02:39:32.542059: step: 1012/533, loss: 0.00365715054795146
2023-01-23 02:39:33.687193: step: 1016/533, loss: 0.00258979806676507
2023-01-23 02:39:34.859175: step: 1020/533, loss: 0.01114511489868164
2023-01-23 02:39:35.998305: step: 1024/533, loss: 0.06952658295631409
2023-01-23 02:39:37.151675: step: 1028/533, loss: 0.041036225855350494
2023-01-23 02:39:38.316537: step: 1032/533, loss: 0.003975486848503351
2023-01-23 02:39:39.491145: step: 1036/533, loss: 0.009595775976777077
2023-01-23 02:39:40.697448: step: 1040/533, loss: 0.013378525152802467
2023-01-23 02:39:41.814672: step: 1044/533, loss: 0.019137000665068626
2023-01-23 02:39:42.969347: step: 1048/533, loss: 4.7969817387638614e-05
2023-01-23 02:39:44.133448: step: 1052/533, loss: 0.0026799202896654606
2023-01-23 02:39:45.290432: step: 1056/533, loss: 0.0016494751907885075
2023-01-23 02:39:46.475558: step: 1060/533, loss: 0.039968397468328476
2023-01-23 02:39:47.637563: step: 1064/533, loss: 0.0075446609407663345
2023-01-23 02:39:48.823060: step: 1068/533, loss: 0.007601452060043812
2023-01-23 02:39:50.041463: step: 1072/533, loss: 0.023512650281190872
2023-01-23 02:39:51.209028: step: 1076/533, loss: 0.06672406196594238
2023-01-23 02:39:52.371415: step: 1080/533, loss: 0.0727386474609375
2023-01-23 02:39:53.536624: step: 1084/533, loss: 0.006413841620087624
2023-01-23 02:39:54.667854: step: 1088/533, loss: 0.022216796875
2023-01-23 02:39:55.853283: step: 1092/533, loss: 0.016120338812470436
2023-01-23 02:39:57.022945: step: 1096/533, loss: 0.030898286029696465
2023-01-23 02:39:58.205205: step: 1100/533, loss: 0.011331653222441673
2023-01-23 02:39:59.437732: step: 1104/533, loss: 0.11912579834461212
2023-01-23 02:40:00.597579: step: 1108/533, loss: 0.00015935898409225047
2023-01-23 02:40:01.786162: step: 1112/533, loss: 0.00235404958948493
2023-01-23 02:40:02.947766: step: 1116/533, loss: 0.030215073376893997
2023-01-23 02:40:04.128746: step: 1120/533, loss: 0.0014148711925372481
2023-01-23 02:40:05.287078: step: 1124/533, loss: 0.0008066296577453613
2023-01-23 02:40:06.466939: step: 1128/533, loss: 0.0031019686721265316
2023-01-23 02:40:07.663337: step: 1132/533, loss: 0.0009886742336675525
2023-01-23 02:40:08.818446: step: 1136/533, loss: 0.0015953541733324528
2023-01-23 02:40:09.993633: step: 1140/533, loss: 0.02370443381369114
2023-01-23 02:40:11.137871: step: 1144/533, loss: 0.08602094650268555
2023-01-23 02:40:12.294976: step: 1148/533, loss: 0.008855437859892845
2023-01-23 02:40:13.489726: step: 1152/533, loss: 0.025487661361694336
2023-01-23 02:40:14.636270: step: 1156/533, loss: 0.0011738777393475175
2023-01-23 02:40:15.779896: step: 1160/533, loss: 0.04270558804273605
2023-01-23 02:40:16.952018: step: 1164/533, loss: 0.004864215850830078
2023-01-23 02:40:18.143620: step: 1168/533, loss: 0.020808840170502663
2023-01-23 02:40:19.353324: step: 1172/533, loss: 0.024790192022919655
2023-01-23 02:40:20.536239: step: 1176/533, loss: 0.002162837889045477
2023-01-23 02:40:21.694741: step: 1180/533, loss: 0.023140335455536842
2023-01-23 02:40:22.868540: step: 1184/533, loss: 0.04875240474939346
2023-01-23 02:40:24.051296: step: 1188/533, loss: 0.0011785507667809725
2023-01-23 02:40:25.230809: step: 1192/533, loss: 0.0038541792891919613
2023-01-23 02:40:26.406587: step: 1196/533, loss: 0.027614861726760864
2023-01-23 02:40:27.549914: step: 1200/533, loss: 0.006805134005844593
2023-01-23 02:40:28.738294: step: 1204/533, loss: 0.03253033384680748
2023-01-23 02:40:29.924023: step: 1208/533, loss: 5.6552886235294864e-05
2023-01-23 02:40:31.125595: step: 1212/533, loss: 0.03117389790713787
2023-01-23 02:40:32.320009: step: 1216/533, loss: 0.021603966131806374
2023-01-23 02:40:33.477272: step: 1220/533, loss: 0.018318558111786842
2023-01-23 02:40:34.609187: step: 1224/533, loss: 0.013022899627685547
2023-01-23 02:40:35.823892: step: 1228/533, loss: 0.009419441223144531
2023-01-23 02:40:36.984802: step: 1232/533, loss: 1.3256072634248994e-05
2023-01-23 02:40:38.176237: step: 1236/533, loss: 0.007796573918312788
2023-01-23 02:40:39.309314: step: 1240/533, loss: 0.0009675026522018015
2023-01-23 02:40:40.472065: step: 1244/533, loss: 0.0860045924782753
2023-01-23 02:40:41.669370: step: 1248/533, loss: 0.029773332178592682
2023-01-23 02:40:42.819972: step: 1252/533, loss: 0.015056420117616653
2023-01-23 02:40:43.991499: step: 1256/533, loss: 0.06025705486536026
2023-01-23 02:40:45.161858: step: 1260/533, loss: 0.01129903830587864
2023-01-23 02:40:46.326619: step: 1264/533, loss: 0.02307424508035183
2023-01-23 02:40:47.486709: step: 1268/533, loss: 0.04053802415728569
2023-01-23 02:40:48.674293: step: 1272/533, loss: 0.004135513212531805
2023-01-23 02:40:49.874851: step: 1276/533, loss: 0.035432055592536926
2023-01-23 02:40:51.050495: step: 1280/533, loss: 0.013380718417465687
2023-01-23 02:40:52.228993: step: 1284/533, loss: 0.0014565468300133944
2023-01-23 02:40:53.450102: step: 1288/533, loss: 0.009642865508794785
2023-01-23 02:40:54.668940: step: 1292/533, loss: 9.403229341842234e-05
2023-01-23 02:40:55.839442: step: 1296/533, loss: 0.038231659680604935
2023-01-23 02:40:57.034166: step: 1300/533, loss: 0.01034850999712944
2023-01-23 02:40:58.177624: step: 1304/533, loss: 0.024612808600068092
2023-01-23 02:40:59.348573: step: 1308/533, loss: 0.0072463033720850945
2023-01-23 02:41:00.542341: step: 1312/533, loss: 0.01629180833697319
2023-01-23 02:41:01.712067: step: 1316/533, loss: 0.0032887414563447237
2023-01-23 02:41:02.914594: step: 1320/533, loss: 0.0037805556785315275
2023-01-23 02:41:04.123242: step: 1324/533, loss: 0.004913234617561102
2023-01-23 02:41:05.275677: step: 1328/533, loss: 0.010395479388535023
2023-01-23 02:41:06.508203: step: 1332/533, loss: 0.7065010070800781
2023-01-23 02:41:07.704170: step: 1336/533, loss: 0.01079416275024414
2023-01-23 02:41:08.887787: step: 1340/533, loss: 0.046254731714725494
2023-01-23 02:41:10.054402: step: 1344/533, loss: 0.024059485644102097
2023-01-23 02:41:11.210299: step: 1348/533, loss: 0.08166928589344025
2023-01-23 02:41:12.360621: step: 1352/533, loss: 0.002643489744514227
2023-01-23 02:41:13.516645: step: 1356/533, loss: 0.03202419355511665
2023-01-23 02:41:14.700295: step: 1360/533, loss: 0.0095405587926507
2023-01-23 02:41:15.889926: step: 1364/533, loss: 0.0013853549025952816
2023-01-23 02:41:17.046204: step: 1368/533, loss: 0.008166885003447533
2023-01-23 02:41:18.166497: step: 1372/533, loss: 0.0072609903290867805
2023-01-23 02:41:19.367064: step: 1376/533, loss: 0.0057697300799191
2023-01-23 02:41:20.561841: step: 1380/533, loss: 0.05821714550256729
2023-01-23 02:41:21.777627: step: 1384/533, loss: 0.048148348927497864
2023-01-23 02:41:22.976522: step: 1388/533, loss: 0.0068649291060864925
2023-01-23 02:41:24.110363: step: 1392/533, loss: 0.019165897741913795
2023-01-23 02:41:25.279154: step: 1396/533, loss: 0.020553112030029297
2023-01-23 02:41:26.440334: step: 1400/533, loss: 0.04664144665002823
2023-01-23 02:41:27.663257: step: 1404/533, loss: 6.64711042190902e-05
2023-01-23 02:41:28.853823: step: 1408/533, loss: 0.010936547070741653
2023-01-23 02:41:29.999099: step: 1412/533, loss: 0.021195411682128906
2023-01-23 02:41:31.138395: step: 1416/533, loss: 0.027533099055290222
2023-01-23 02:41:32.314650: step: 1420/533, loss: 0.0031245232094079256
2023-01-23 02:41:33.485068: step: 1424/533, loss: 0.002873325487598777
2023-01-23 02:41:34.630705: step: 1428/533, loss: 0.05027656629681587
2023-01-23 02:41:35.796024: step: 1432/533, loss: 0.011453866958618164
2023-01-23 02:41:36.972868: step: 1436/533, loss: 0.003962039947509766
2023-01-23 02:41:38.123537: step: 1440/533, loss: 0.005975246429443359
2023-01-23 02:41:39.305737: step: 1444/533, loss: 0.010951423086225986
2023-01-23 02:41:40.507460: step: 1448/533, loss: 0.0022405623458325863
2023-01-23 02:41:41.681246: step: 1452/533, loss: 0.01731410063803196
2023-01-23 02:41:42.839065: step: 1456/533, loss: 0.04520225524902344
2023-01-23 02:41:44.038282: step: 1460/533, loss: 0.005767345428466797
2023-01-23 02:41:45.198759: step: 1464/533, loss: 0.014719819650053978
2023-01-23 02:41:46.376071: step: 1468/533, loss: 0.002204799558967352
2023-01-23 02:41:47.553262: step: 1472/533, loss: 0.04959557205438614
2023-01-23 02:41:48.720667: step: 1476/533, loss: 0.032160572707653046
2023-01-23 02:41:49.895339: step: 1480/533, loss: 0.028227951377630234
2023-01-23 02:41:51.085052: step: 1484/533, loss: 0.0010269165504723787
2023-01-23 02:41:52.263857: step: 1488/533, loss: 0.008346510119736195
2023-01-23 02:41:53.448709: step: 1492/533, loss: 0.004586410243064165
2023-01-23 02:41:54.606405: step: 1496/533, loss: 0.001663637231104076
2023-01-23 02:41:55.754005: step: 1500/533, loss: 0.8587007522583008
2023-01-23 02:41:56.964097: step: 1504/533, loss: 0.0015378951793536544
2023-01-23 02:41:58.161766: step: 1508/533, loss: 0.0017135620582848787
2023-01-23 02:41:59.317904: step: 1512/533, loss: 0.0026695250999182463
2023-01-23 02:42:00.508603: step: 1516/533, loss: 0.0011548995971679688
2023-01-23 02:42:01.664186: step: 1520/533, loss: 0.004550743382424116
2023-01-23 02:42:02.810482: step: 1524/533, loss: 0.04035091772675514
2023-01-23 02:42:03.975267: step: 1528/533, loss: 0.0012311935424804688
2023-01-23 02:42:05.112396: step: 1532/533, loss: 0.026397133246064186
2023-01-23 02:42:06.280605: step: 1536/533, loss: 0.002847003983333707
2023-01-23 02:42:07.459539: step: 1540/533, loss: 0.001199436141178012
2023-01-23 02:42:08.637506: step: 1544/533, loss: 0.010825681500136852
2023-01-23 02:42:09.823999: step: 1548/533, loss: 0.024338722229003906
2023-01-23 02:42:11.058207: step: 1552/533, loss: 1.5991666316986084
2023-01-23 02:42:12.240069: step: 1556/533, loss: 0.029135845601558685
2023-01-23 02:42:13.393592: step: 1560/533, loss: 0.012155341915786266
2023-01-23 02:42:14.572593: step: 1564/533, loss: 0.022369956597685814
2023-01-23 02:42:15.735103: step: 1568/533, loss: 0.045952893793582916
2023-01-23 02:42:16.908406: step: 1572/533, loss: 0.002908039139583707
2023-01-23 02:42:18.107629: step: 1576/533, loss: 0.053562358021736145
2023-01-23 02:42:19.298104: step: 1580/533, loss: 0.0067806243896484375
2023-01-23 02:42:20.490536: step: 1584/533, loss: 0.06362471729516983
2023-01-23 02:42:21.673999: step: 1588/533, loss: 0.01238708570599556
2023-01-23 02:42:22.839101: step: 1592/533, loss: 0.01600179634988308
2023-01-23 02:42:24.003113: step: 1596/533, loss: 0.01671447791159153
2023-01-23 02:42:25.181571: step: 1600/533, loss: 0.5335648059844971
2023-01-23 02:42:26.337651: step: 1604/533, loss: 0.009768676944077015
2023-01-23 02:42:27.542626: step: 1608/533, loss: 0.026198577135801315
2023-01-23 02:42:28.723686: step: 1612/533, loss: 0.10621795803308487
2023-01-23 02:42:29.882312: step: 1616/533, loss: 0.027897994965314865
2023-01-23 02:42:31.045357: step: 1620/533, loss: 0.004445361904799938
2023-01-23 02:42:32.231034: step: 1624/533, loss: 0.03170432895421982
2023-01-23 02:42:33.396579: step: 1628/533, loss: 0.03311891481280327
2023-01-23 02:42:34.562277: step: 1632/533, loss: 0.022612379863858223
2023-01-23 02:42:35.726198: step: 1636/533, loss: 0.038114309310913086
2023-01-23 02:42:36.919825: step: 1640/533, loss: 0.0055901529267430305
2023-01-23 02:42:38.103111: step: 1644/533, loss: 0.0008411050075665116
2023-01-23 02:42:39.336100: step: 1648/533, loss: 0.05695762485265732
2023-01-23 02:42:40.500642: step: 1652/533, loss: 0.06915159523487091
2023-01-23 02:42:41.666581: step: 1656/533, loss: 0.0007195472717285156
2023-01-23 02:42:42.829763: step: 1660/533, loss: 0.002749919891357422
2023-01-23 02:42:43.987329: step: 1664/533, loss: 0.018449973315000534
2023-01-23 02:42:45.176055: step: 1668/533, loss: 0.2560577392578125
2023-01-23 02:42:46.423635: step: 1672/533, loss: 5.111694190418348e-05
2023-01-23 02:42:47.630998: step: 1676/533, loss: 0.018149472773075104
2023-01-23 02:42:48.811651: step: 1680/533, loss: 0.004533195402473211
2023-01-23 02:42:50.011428: step: 1684/533, loss: 0.013851833529770374
2023-01-23 02:42:51.188504: step: 1688/533, loss: 0.002399635501205921
2023-01-23 02:42:52.356376: step: 1692/533, loss: 0.021000387147068977
2023-01-23 02:42:53.502736: step: 1696/533, loss: 0.03911762312054634
2023-01-23 02:42:54.706814: step: 1700/533, loss: 0.004843330476433039
2023-01-23 02:42:55.943159: step: 1704/533, loss: 0.06415177136659622
2023-01-23 02:42:57.151797: step: 1708/533, loss: 0.031184006482362747
2023-01-23 02:42:58.338039: step: 1712/533, loss: 0.013955879025161266
2023-01-23 02:42:59.555805: step: 1716/533, loss: 0.04959449917078018
2023-01-23 02:43:00.702813: step: 1720/533, loss: 0.0045303343795239925
2023-01-23 02:43:01.880425: step: 1724/533, loss: 0.010566044598817825
2023-01-23 02:43:03.049476: step: 1728/533, loss: 0.033652305603027344
2023-01-23 02:43:04.234825: step: 1732/533, loss: 0.023145103827118874
2023-01-23 02:43:05.414227: step: 1736/533, loss: 0.003997230436652899
2023-01-23 02:43:06.565060: step: 1740/533, loss: 9.732246689964086e-05
2023-01-23 02:43:07.724051: step: 1744/533, loss: 0.0053689004853367805
2023-01-23 02:43:08.956710: step: 1748/533, loss: 0.04672088474035263
2023-01-23 02:43:10.154393: step: 1752/533, loss: 0.01916523091495037
2023-01-23 02:43:11.318409: step: 1756/533, loss: 0.017249250784516335
2023-01-23 02:43:12.517288: step: 1760/533, loss: 0.013771915808320045
2023-01-23 02:43:13.700700: step: 1764/533, loss: 0.0003450870281085372
2023-01-23 02:43:14.874886: step: 1768/533, loss: 0.0036611079704016447
2023-01-23 02:43:16.051714: step: 1772/533, loss: 0.00032405852107331157
2023-01-23 02:43:17.209050: step: 1776/533, loss: 0.0033330442383885384
2023-01-23 02:43:18.433686: step: 1780/533, loss: 0.04648284614086151
2023-01-23 02:43:19.650104: step: 1784/533, loss: 0.0020838738419115543
2023-01-23 02:43:20.842621: step: 1788/533, loss: 0.00030288693960756063
2023-01-23 02:43:22.009840: step: 1792/533, loss: 0.08451161533594131
2023-01-23 02:43:23.216984: step: 1796/533, loss: 0.03381318971514702
2023-01-23 02:43:24.405489: step: 1800/533, loss: 0.09086885303258896
2023-01-23 02:43:25.599563: step: 1804/533, loss: 0.04130687564611435
2023-01-23 02:43:26.790231: step: 1808/533, loss: 0.0025913240388035774
2023-01-23 02:43:27.966828: step: 1812/533, loss: 0.07474642246961594
2023-01-23 02:43:29.148522: step: 1816/533, loss: 0.019781876355409622
2023-01-23 02:43:30.324562: step: 1820/533, loss: 0.000301361083984375
2023-01-23 02:43:31.506152: step: 1824/533, loss: 0.0002887725713662803
2023-01-23 02:43:32.677108: step: 1828/533, loss: 0.012577342800796032
2023-01-23 02:43:33.838310: step: 1832/533, loss: 9.441375732421875e-05
2023-01-23 02:43:35.002444: step: 1836/533, loss: 0.007608985994011164
2023-01-23 02:43:36.188203: step: 1840/533, loss: 0.0354861281812191
2023-01-23 02:43:37.394865: step: 1844/533, loss: 0.0065691471099853516
2023-01-23 02:43:38.583274: step: 1848/533, loss: 0.02790858969092369
2023-01-23 02:43:39.790642: step: 1852/533, loss: 0.022379687055945396
2023-01-23 02:43:40.995955: step: 1856/533, loss: 0.0019664764404296875
2023-01-23 02:43:42.171847: step: 1860/533, loss: 0.009407997131347656
2023-01-23 02:43:43.367093: step: 1864/533, loss: 0.0008975982782430947
2023-01-23 02:43:44.535719: step: 1868/533, loss: 0.0029234886169433594
2023-01-23 02:43:45.696791: step: 1872/533, loss: 0.05127887800335884
2023-01-23 02:43:46.936207: step: 1876/533, loss: 0.005353259854018688
2023-01-23 02:43:48.114135: step: 1880/533, loss: 0.010486721992492676
2023-01-23 02:43:49.314395: step: 1884/533, loss: 0.0009550094837322831
2023-01-23 02:43:50.484590: step: 1888/533, loss: 1.3399124327406753e-05
2023-01-23 02:43:51.609723: step: 1892/533, loss: 0.04675102233886719
2023-01-23 02:43:52.827906: step: 1896/533, loss: 0.03129234537482262
2023-01-23 02:43:54.015040: step: 1900/533, loss: 0.023981522768735886
2023-01-23 02:43:55.174162: step: 1904/533, loss: 0.0007944107055664062
2023-01-23 02:43:56.381095: step: 1908/533, loss: 0.019039299339056015
2023-01-23 02:43:57.552654: step: 1912/533, loss: 0.0014998435508459806
2023-01-23 02:43:58.752559: step: 1916/533, loss: 0.04495801776647568
2023-01-23 02:43:59.947477: step: 1920/533, loss: 0.002214336534962058
2023-01-23 02:44:01.088841: step: 1924/533, loss: 0.026740361005067825
2023-01-23 02:44:02.245517: step: 1928/533, loss: 0.09192061424255371
2023-01-23 02:44:03.423240: step: 1932/533, loss: 0.04042892903089523
2023-01-23 02:44:04.591685: step: 1936/533, loss: 0.032320547848939896
2023-01-23 02:44:05.706465: step: 1940/533, loss: 0.0020843506790697575
2023-01-23 02:44:06.884605: step: 1944/533, loss: 0.05872688442468643
2023-01-23 02:44:08.042647: step: 1948/533, loss: 0.023344803601503372
2023-01-23 02:44:09.189450: step: 1952/533, loss: 0.001634883927181363
2023-01-23 02:44:10.367777: step: 1956/533, loss: 0.07500836998224258
2023-01-23 02:44:11.577733: step: 1960/533, loss: 0.011383152566850185
2023-01-23 02:44:12.754483: step: 1964/533, loss: 0.04769134521484375
2023-01-23 02:44:13.936771: step: 1968/533, loss: 0.07409077137708664
2023-01-23 02:44:15.169444: step: 1972/533, loss: 0.0036670684348791838
2023-01-23 02:44:16.355512: step: 1976/533, loss: 0.0016620636451989412
2023-01-23 02:44:17.519927: step: 1980/533, loss: 0.013271236792206764
2023-01-23 02:44:18.700675: step: 1984/533, loss: 0.002618217607960105
2023-01-23 02:44:19.834703: step: 1988/533, loss: 0.0463135726749897
2023-01-23 02:44:21.027974: step: 1992/533, loss: 0.01051025465130806
2023-01-23 02:44:22.218327: step: 1996/533, loss: 0.025898220017552376
2023-01-23 02:44:23.379362: step: 2000/533, loss: 0.10018301010131836
2023-01-23 02:44:24.576349: step: 2004/533, loss: 0.011593151837587357
2023-01-23 02:44:25.741921: step: 2008/533, loss: 0.012183571234345436
2023-01-23 02:44:26.913672: step: 2012/533, loss: 0.0626705214381218
2023-01-23 02:44:28.073341: step: 2016/533, loss: 0.004366493318229914
2023-01-23 02:44:29.231419: step: 2020/533, loss: 0.017737198621034622
2023-01-23 02:44:30.370635: step: 2024/533, loss: 0.014255713671445847
2023-01-23 02:44:31.544623: step: 2028/533, loss: 0.025807952508330345
2023-01-23 02:44:32.679802: step: 2032/533, loss: 0.011851645074784756
2023-01-23 02:44:33.832907: step: 2036/533, loss: 0.0013482094509527087
2023-01-23 02:44:35.029393: step: 2040/533, loss: 0.007368850987404585
2023-01-23 02:44:36.187165: step: 2044/533, loss: 0.008652460761368275
2023-01-23 02:44:37.338160: step: 2048/533, loss: 0.017990780994296074
2023-01-23 02:44:38.502313: step: 2052/533, loss: 0.009862900711596012
2023-01-23 02:44:39.659581: step: 2056/533, loss: 0.10551033169031143
2023-01-23 02:44:40.844689: step: 2060/533, loss: 0.00060358049813658
2023-01-23 02:44:42.036145: step: 2064/533, loss: 0.0018243789672851562
2023-01-23 02:44:43.303354: step: 2068/533, loss: 0.07365989685058594
2023-01-23 02:44:44.573080: step: 2072/533, loss: 0.0021131515968590975
2023-01-23 02:44:45.724243: step: 2076/533, loss: 0.6265827417373657
2023-01-23 02:44:46.911959: step: 2080/533, loss: 0.010940074920654297
2023-01-23 02:44:48.087171: step: 2084/533, loss: 0.021912382915616035
2023-01-23 02:44:49.286994: step: 2088/533, loss: 0.0029693127144128084
2023-01-23 02:44:50.449680: step: 2092/533, loss: 8.726119995117188e-05
2023-01-23 02:44:51.677636: step: 2096/533, loss: 0.08318972587585449
2023-01-23 02:44:52.841686: step: 2100/533, loss: 0.02552352100610733
2023-01-23 02:44:54.026208: step: 2104/533, loss: 0.009144211187958717
2023-01-23 02:44:55.254891: step: 2108/533, loss: 0.03104572184383869
2023-01-23 02:44:56.401166: step: 2112/533, loss: 0.04920797422528267
2023-01-23 02:44:57.580181: step: 2116/533, loss: 0.019005203619599342
2023-01-23 02:44:58.713736: step: 2120/533, loss: 0.016808509826660156
2023-01-23 02:44:59.887888: step: 2124/533, loss: 0.11634770035743713
2023-01-23 02:45:01.036853: step: 2128/533, loss: 0.014425563625991344
2023-01-23 02:45:02.177831: step: 2132/533, loss: 0.030226517468690872
==================================================
Loss: 0.044
--------------------
Dev: {'event': {'p': 0.5883534136546185, 'r': 0.7802929427430093, 'f1': 0.6708643388666284}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6426029486527707, 'r': 0.8081841432225064, 'f1': 0.7159444916454262}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5185185185185185, 'r': 0.7777777777777778, 'f1': 0.6222222222222222}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.660377358490566, 'r': 0.5555555555555556, 'f1': 0.6034482758620691}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5977130977130977, 'r': 0.7656458055925432, 'f1': 0.6713368359603036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Russian: {'event': {'p': 0.6403940886699507, 'r': 0.7480818414322251, 'f1': 0.690061928634621}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Russian: {'event': {'p': 0.55, 'r': 0.6111111111111112, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:45:43.377793: step: 4/533, loss: 0.003078651614487171
2023-01-23 02:45:44.575050: step: 8/533, loss: 0.020116426050662994
2023-01-23 02:45:45.754331: step: 12/533, loss: 0.001172828720882535
2023-01-23 02:45:46.929472: step: 16/533, loss: 0.01778268814086914
2023-01-23 02:45:48.068170: step: 20/533, loss: 0.012190199457108974
2023-01-23 02:45:49.266831: step: 24/533, loss: 0.008250046521425247
2023-01-23 02:45:50.415230: step: 28/533, loss: 0.0290509220212698
2023-01-23 02:45:51.612208: step: 32/533, loss: 0.00017261505126953125
2023-01-23 02:45:52.847316: step: 36/533, loss: 0.006304740905761719
2023-01-23 02:45:53.994768: step: 40/533, loss: 7.514953904319555e-05
2023-01-23 02:45:55.147909: step: 44/533, loss: 0.009279251098632812
2023-01-23 02:45:56.401924: step: 48/533, loss: 0.044998932629823685
2023-01-23 02:45:57.555124: step: 52/533, loss: 0.04044933617115021
2023-01-23 02:45:58.735910: step: 56/533, loss: 0.0008599281427450478
2023-01-23 02:45:59.971450: step: 60/533, loss: 0.002803802490234375
2023-01-23 02:46:01.161297: step: 64/533, loss: 0.03216443210840225
2023-01-23 02:46:02.328793: step: 68/533, loss: 0.00028076174203306437
2023-01-23 02:46:03.531674: step: 72/533, loss: 0.0486719124019146
2023-01-23 02:46:04.699345: step: 76/533, loss: 0.27453774213790894
2023-01-23 02:46:05.848197: step: 80/533, loss: 0.026564789935946465
2023-01-23 02:46:07.043894: step: 84/533, loss: 0.024771692231297493
2023-01-23 02:46:08.243882: step: 88/533, loss: 0.008466911502182484
2023-01-23 02:46:09.391868: step: 92/533, loss: 0.0011946677695959806
2023-01-23 02:46:10.567064: step: 96/533, loss: 0.0038028715644031763
2023-01-23 02:46:11.778955: step: 100/533, loss: 0.0006295203929767013
2023-01-23 02:46:12.997013: step: 104/533, loss: 0.000762558018323034
2023-01-23 02:46:14.166785: step: 108/533, loss: 0.002228641649708152
2023-01-23 02:46:15.356653: step: 112/533, loss: 0.027641868218779564
2023-01-23 02:46:16.503157: step: 116/533, loss: 0.05996112525463104
2023-01-23 02:46:17.671689: step: 120/533, loss: 0.002659320831298828
2023-01-23 02:46:18.849341: step: 124/533, loss: 0.012964916415512562
2023-01-23 02:46:20.057284: step: 128/533, loss: 0.003347206162288785
2023-01-23 02:46:21.260096: step: 132/533, loss: 0.00575675955042243
2023-01-23 02:46:22.433537: step: 136/533, loss: 0.038973618298769
2023-01-23 02:46:23.574147: step: 140/533, loss: 0.00017900466627907008
2023-01-23 02:46:24.722888: step: 144/533, loss: 0.0008783340454101562
2023-01-23 02:46:25.864397: step: 148/533, loss: 0.0035134314093738794
2023-01-23 02:46:27.014904: step: 152/533, loss: 0.002569693373516202
2023-01-23 02:46:28.173601: step: 156/533, loss: 0.0291748046875
2023-01-23 02:46:29.418316: step: 160/533, loss: 0.00010786056373035535
2023-01-23 02:46:30.598244: step: 164/533, loss: 0.018441010266542435
2023-01-23 02:46:31.739002: step: 168/533, loss: 0.0010353088146075606
2023-01-23 02:46:32.910057: step: 172/533, loss: 0.03807525709271431
2023-01-23 02:46:34.097919: step: 176/533, loss: 0.013902425765991211
2023-01-23 02:46:35.229153: step: 180/533, loss: 0.02832059934735298
2023-01-23 02:46:36.435192: step: 184/533, loss: 3.06129441014491e-05
2023-01-23 02:46:37.666817: step: 188/533, loss: 0.0019176483619958162
2023-01-23 02:46:38.870823: step: 192/533, loss: 0.012591552920639515
2023-01-23 02:46:40.077753: step: 196/533, loss: 0.004140091128647327
2023-01-23 02:46:41.246042: step: 200/533, loss: 0.005182075314223766
2023-01-23 02:46:42.408513: step: 204/533, loss: 0.00023326874361373484
2023-01-23 02:46:43.559473: step: 208/533, loss: 0.2693680226802826
2023-01-23 02:46:44.705850: step: 212/533, loss: 0.007162714377045631
2023-01-23 02:46:45.889778: step: 216/533, loss: 0.08151502907276154
2023-01-23 02:46:47.094505: step: 220/533, loss: 0.016516782343387604
2023-01-23 02:46:48.286072: step: 224/533, loss: 0.011872291564941406
2023-01-23 02:46:49.486698: step: 228/533, loss: 0.020183373242616653
2023-01-23 02:46:50.660463: step: 232/533, loss: 0.0018589019309729338
2023-01-23 02:46:51.857981: step: 236/533, loss: 6.923676119185984e-05
2023-01-23 02:46:53.020667: step: 240/533, loss: 0.005663013551384211
2023-01-23 02:46:54.162405: step: 244/533, loss: 0.004565620329231024
2023-01-23 02:46:55.348924: step: 248/533, loss: 0.04617328569293022
2023-01-23 02:46:56.518727: step: 252/533, loss: 0.0018202782375738025
2023-01-23 02:46:57.725913: step: 256/533, loss: 0.024161625653505325
2023-01-23 02:46:58.859105: step: 260/533, loss: 0.0044615743681788445
2023-01-23 02:47:00.009108: step: 264/533, loss: 0.0030312538146972656
2023-01-23 02:47:01.212378: step: 268/533, loss: 0.012202071957290173
2023-01-23 02:47:02.393068: step: 272/533, loss: -1.4877317880745977e-05
2023-01-23 02:47:03.511166: step: 276/533, loss: 0.02927684783935547
2023-01-23 02:47:04.686799: step: 280/533, loss: 0.003538465593010187
2023-01-23 02:47:05.852866: step: 284/533, loss: 0.0011259079910814762
2023-01-23 02:47:07.056270: step: 288/533, loss: 0.027346229180693626
2023-01-23 02:47:08.256776: step: 292/533, loss: 0.003432083409279585
2023-01-23 02:47:09.462967: step: 296/533, loss: 0.03890342637896538
2023-01-23 02:47:10.623217: step: 300/533, loss: 0.04705004766583443
2023-01-23 02:47:11.781380: step: 304/533, loss: 0.004475212190300226
2023-01-23 02:47:12.963426: step: 308/533, loss: 0.00018997192091774195
2023-01-23 02:47:14.104225: step: 312/533, loss: 0.007609653752297163
2023-01-23 02:47:15.247898: step: 316/533, loss: 2.0360947019071318e-05
2023-01-23 02:47:16.424503: step: 320/533, loss: 0.0027098655700683594
2023-01-23 02:47:17.681697: step: 324/533, loss: 0.02936725690960884
2023-01-23 02:47:18.863850: step: 328/533, loss: 0.00278053293004632
2023-01-23 02:47:20.015954: step: 332/533, loss: 0.013946057297289371
2023-01-23 02:47:21.177092: step: 336/533, loss: 0.09047951549291611
2023-01-23 02:47:22.356743: step: 340/533, loss: 0.06602182239294052
2023-01-23 02:47:23.529925: step: 344/533, loss: 0.005893421359360218
2023-01-23 02:47:24.678647: step: 348/533, loss: 0.003125905990600586
2023-01-23 02:47:25.896711: step: 352/533, loss: 0.009057235904037952
2023-01-23 02:47:27.042484: step: 356/533, loss: 0.0009259224170818925
2023-01-23 02:47:28.213238: step: 360/533, loss: 0.011692619882524014
2023-01-23 02:47:29.419063: step: 364/533, loss: 0.026745129376649857
2023-01-23 02:47:30.587172: step: 368/533, loss: 0.0017299175960943103
2023-01-23 02:47:31.744083: step: 372/533, loss: 0.014490318484604359
2023-01-23 02:47:32.923451: step: 376/533, loss: 0.0031873704865574837
2023-01-23 02:47:34.079970: step: 380/533, loss: 0.0009585380321368575
2023-01-23 02:47:35.243745: step: 384/533, loss: 0.021773338317871094
2023-01-23 02:47:36.433382: step: 388/533, loss: 0.02523784711956978
2023-01-23 02:47:37.616474: step: 392/533, loss: 0.03062143363058567
2023-01-23 02:47:38.781120: step: 396/533, loss: 0.014317465014755726
2023-01-23 02:47:39.952030: step: 400/533, loss: 0.009530831128358841
2023-01-23 02:47:41.119261: step: 404/533, loss: 0.00107488629873842
2023-01-23 02:47:42.270374: step: 408/533, loss: 0.0005081176641397178
2023-01-23 02:47:43.447244: step: 412/533, loss: 0.04646573215723038
2023-01-23 02:47:44.628021: step: 416/533, loss: 7.286071922862902e-05
2023-01-23 02:47:45.787330: step: 420/533, loss: 0.0032161714043468237
2023-01-23 02:47:46.947927: step: 424/533, loss: 0.0007998943910934031
2023-01-23 02:47:48.124901: step: 428/533, loss: 0.02635193057358265
2023-01-23 02:47:49.320091: step: 432/533, loss: 0.06146125867962837
2023-01-23 02:47:50.508259: step: 436/533, loss: 0.01206274051219225
2023-01-23 02:47:51.655212: step: 440/533, loss: 0.015166091732680798
2023-01-23 02:47:52.841091: step: 444/533, loss: 0.034293174743652344
2023-01-23 02:47:53.994076: step: 448/533, loss: 0.008524084463715553
2023-01-23 02:47:55.151993: step: 452/533, loss: 0.005695343483239412
2023-01-23 02:47:56.326582: step: 456/533, loss: 0.0012744903797283769
2023-01-23 02:47:57.533253: step: 460/533, loss: 0.00030517578125
2023-01-23 02:47:58.719096: step: 464/533, loss: 0.0374692939221859
2023-01-23 02:47:59.913150: step: 468/533, loss: 0.008836555294692516
2023-01-23 02:48:01.118246: step: 472/533, loss: 3.8528440200025216e-05
2023-01-23 02:48:02.303203: step: 476/533, loss: 0.0033369064331054688
2023-01-23 02:48:03.484143: step: 480/533, loss: 0.01641864888370037
2023-01-23 02:48:04.641038: step: 484/533, loss: 0.04925060272216797
2023-01-23 02:48:05.806595: step: 488/533, loss: 0.008362484164536
2023-01-23 02:48:06.977866: step: 492/533, loss: 0.39628347754478455
2023-01-23 02:48:08.129130: step: 496/533, loss: 0.06452713161706924
2023-01-23 02:48:09.300823: step: 500/533, loss: 0.00809793546795845
2023-01-23 02:48:10.457579: step: 504/533, loss: 0.00017147065955214202
2023-01-23 02:48:11.626662: step: 508/533, loss: 0.035984039306640625
2023-01-23 02:48:12.832684: step: 512/533, loss: 0.08561354130506516
2023-01-23 02:48:13.998857: step: 516/533, loss: 0.0022647858131676912
2023-01-23 02:48:15.139419: step: 520/533, loss: 0.00040712355985306203
2023-01-23 02:48:16.285687: step: 524/533, loss: 0.02590971067547798
2023-01-23 02:48:17.447602: step: 528/533, loss: 0.0012377442326396704
2023-01-23 02:48:18.641843: step: 532/533, loss: 0.0007405758369714022
2023-01-23 02:48:19.813311: step: 536/533, loss: 0.0511658675968647
2023-01-23 02:48:21.000357: step: 540/533, loss: 0.0012251854641363025
2023-01-23 02:48:22.234805: step: 544/533, loss: 0.04508533328771591
2023-01-23 02:48:23.412386: step: 548/533, loss: 0.004385852720588446
2023-01-23 02:48:24.609680: step: 552/533, loss: 0.007276725955307484
2023-01-23 02:48:25.828105: step: 556/533, loss: 0.5972205400466919
2023-01-23 02:48:26.973937: step: 560/533, loss: 0.10096587985754013
2023-01-23 02:48:28.144378: step: 564/533, loss: 0.0010144234402105212
2023-01-23 02:48:29.277390: step: 568/533, loss: 0.0004378319135867059
2023-01-23 02:48:30.501013: step: 572/533, loss: 0.013380623422563076
2023-01-23 02:48:31.668718: step: 576/533, loss: 0.004177570808678865
2023-01-23 02:48:32.819350: step: 580/533, loss: 0.007358217146247625
2023-01-23 02:48:34.004433: step: 584/533, loss: 0.00415306119248271
2023-01-23 02:48:35.141959: step: 588/533, loss: 0.011286735534667969
2023-01-23 02:48:36.332141: step: 592/533, loss: 0.0008275985601358116
2023-01-23 02:48:37.486032: step: 596/533, loss: 0.0003675461048260331
2023-01-23 02:48:38.639896: step: 600/533, loss: 0.0019462585914880037
2023-01-23 02:48:39.809163: step: 604/533, loss: 0.04704933241009712
2023-01-23 02:48:40.979966: step: 608/533, loss: 0.021963119506835938
2023-01-23 02:48:42.147998: step: 612/533, loss: 0.0009529591188766062
2023-01-23 02:48:43.304303: step: 616/533, loss: 0.0005486488225869834
2023-01-23 02:48:44.503407: step: 620/533, loss: 0.0003541946643963456
2023-01-23 02:48:45.666586: step: 624/533, loss: 0.0007778167491778731
2023-01-23 02:48:46.854384: step: 628/533, loss: 0.0508481040596962
2023-01-23 02:48:48.051622: step: 632/533, loss: 0.032167911529541016
2023-01-23 02:48:49.211481: step: 636/533, loss: 0.0075897215865552425
2023-01-23 02:48:50.377085: step: 640/533, loss: 0.002895164769142866
2023-01-23 02:48:51.552277: step: 644/533, loss: 0.009769916534423828
2023-01-23 02:48:52.739882: step: 648/533, loss: 0.022771263495087624
2023-01-23 02:48:53.880653: step: 652/533, loss: 0.007764053530991077
2023-01-23 02:48:55.083843: step: 656/533, loss: 0.017029428854584694
2023-01-23 02:48:56.265285: step: 660/533, loss: 0.0016609192825853825
2023-01-23 02:48:57.448788: step: 664/533, loss: 0.001756381941959262
2023-01-23 02:48:58.662455: step: 668/533, loss: 0.021846963092684746
2023-01-23 02:48:59.852878: step: 672/533, loss: 0.05139732360839844
2023-01-23 02:49:01.026148: step: 676/533, loss: 0.10620041191577911
2023-01-23 02:49:02.196953: step: 680/533, loss: 0.0011187554337084293
2023-01-23 02:49:03.371383: step: 684/533, loss: 0.03479604795575142
2023-01-23 02:49:04.543502: step: 688/533, loss: 0.02920999750494957
2023-01-23 02:49:05.757506: step: 692/533, loss: 0.004007434472441673
2023-01-23 02:49:06.937727: step: 696/533, loss: 0.011062145233154297
2023-01-23 02:49:08.067920: step: 700/533, loss: 6.904602196300402e-05
2023-01-23 02:49:09.248860: step: 704/533, loss: 0.012273025698959827
2023-01-23 02:49:10.417114: step: 708/533, loss: 0.032195378094911575
2023-01-23 02:49:11.597784: step: 712/533, loss: 0.03704576566815376
2023-01-23 02:49:12.807365: step: 716/533, loss: 0.00537452707067132
2023-01-23 02:49:13.942792: step: 720/533, loss: 0.0506470687687397
2023-01-23 02:49:15.125560: step: 724/533, loss: -3.8146970382513246e-06
2023-01-23 02:49:16.315104: step: 728/533, loss: 0.00796289462596178
2023-01-23 02:49:17.503685: step: 732/533, loss: 0.06104631349444389
2023-01-23 02:49:18.692818: step: 736/533, loss: 0.02778659015893936
2023-01-23 02:49:19.864437: step: 740/533, loss: 0.031070711091160774
2023-01-23 02:49:21.048288: step: 744/533, loss: 0.0019535066094249487
2023-01-23 02:49:22.217760: step: 748/533, loss: 0.0007670879131183028
2023-01-23 02:49:23.385190: step: 752/533, loss: 0.012935805134475231
2023-01-23 02:49:24.584067: step: 756/533, loss: 0.006496238987892866
2023-01-23 02:49:25.769682: step: 760/533, loss: 0.05417289957404137
2023-01-23 02:49:26.949127: step: 764/533, loss: 0.016036653891205788
2023-01-23 02:49:28.126543: step: 768/533, loss: 0.0013278961414471269
2023-01-23 02:49:29.287253: step: 772/533, loss: 0.0029485702980309725
2023-01-23 02:49:30.476744: step: 776/533, loss: 0.0016141892410814762
2023-01-23 02:49:31.650215: step: 780/533, loss: 0.026542093604803085
2023-01-23 02:49:32.794516: step: 784/533, loss: 0.0016596794594079256
2023-01-23 02:49:33.992366: step: 788/533, loss: 0.00856161117553711
2023-01-23 02:49:35.162825: step: 792/533, loss: 0.010188340209424496
2023-01-23 02:49:36.369107: step: 796/533, loss: 0.03049163892865181
2023-01-23 02:49:37.509108: step: 800/533, loss: 0.016820145770907402
2023-01-23 02:49:38.682485: step: 804/533, loss: 5.7220458984375e-06
2023-01-23 02:49:39.826998: step: 808/533, loss: 0.0003688812430482358
2023-01-23 02:49:41.000782: step: 812/533, loss: 0.13359051942825317
2023-01-23 02:49:42.143945: step: 816/533, loss: 0.013157271780073643
2023-01-23 02:49:43.337344: step: 820/533, loss: 0.007832241244614124
2023-01-23 02:49:44.508011: step: 824/533, loss: 0.00125293736346066
2023-01-23 02:49:45.667983: step: 828/533, loss: 0.0002062320854747668
2023-01-23 02:49:46.815605: step: 832/533, loss: 0.028976034373044968
2023-01-23 02:49:47.971260: step: 836/533, loss: 0.00889368075877428
2023-01-23 02:49:49.122921: step: 840/533, loss: 0.02768421173095703
2023-01-23 02:49:50.259511: step: 844/533, loss: 8.010864803509321e-06
2023-01-23 02:49:51.406307: step: 848/533, loss: 0.33837267756462097
2023-01-23 02:49:52.555581: step: 852/533, loss: 0.006473541725426912
2023-01-23 02:49:53.729669: step: 856/533, loss: 0.005878258030861616
2023-01-23 02:49:54.870297: step: 860/533, loss: 0.011524581350386143
2023-01-23 02:49:56.064537: step: 864/533, loss: 0.004676878452301025
2023-01-23 02:49:57.234493: step: 868/533, loss: 0.006819725502282381
2023-01-23 02:49:58.422872: step: 872/533, loss: 0.0007096290937624872
2023-01-23 02:49:59.573054: step: 876/533, loss: 0.012262153439223766
2023-01-23 02:50:00.782306: step: 880/533, loss: 0.0032433033920824528
2023-01-23 02:50:01.938893: step: 884/533, loss: 0.06317378580570221
2023-01-23 02:50:03.137494: step: 888/533, loss: 0.022116471081972122
2023-01-23 02:50:04.289901: step: 892/533, loss: 0.001499176025390625
2023-01-23 02:50:05.427528: step: 896/533, loss: 0.02615683153271675
2023-01-23 02:50:06.585445: step: 900/533, loss: 6.780624971725047e-05
2023-01-23 02:50:07.750573: step: 904/533, loss: 0.05661144107580185
2023-01-23 02:50:08.925237: step: 908/533, loss: 0.006216239649802446
2023-01-23 02:50:10.130429: step: 912/533, loss: 0.010548114776611328
2023-01-23 02:50:11.301579: step: 916/533, loss: 0.0012091159587725997
2023-01-23 02:50:12.499558: step: 920/533, loss: 0.06478162109851837
2023-01-23 02:50:13.701377: step: 924/533, loss: 0.046471498906612396
2023-01-23 02:50:14.897312: step: 928/533, loss: 0.024771392345428467
2023-01-23 02:50:16.068519: step: 932/533, loss: 0.0794704407453537
2023-01-23 02:50:17.241993: step: 936/533, loss: 5.226135181146674e-05
2023-01-23 02:50:18.378443: step: 940/533, loss: 0.004506682977080345
2023-01-23 02:50:19.602656: step: 944/533, loss: 0.01990632526576519
2023-01-23 02:50:20.787971: step: 948/533, loss: 0.02489328570663929
2023-01-23 02:50:22.038766: step: 952/533, loss: 0.013418388552963734
2023-01-23 02:50:23.213371: step: 956/533, loss: 0.02723369561135769
2023-01-23 02:50:24.432490: step: 960/533, loss: 0.008179282769560814
2023-01-23 02:50:25.568245: step: 964/533, loss: 0.02629275433719158
2023-01-23 02:50:26.703799: step: 968/533, loss: 0.008550834842026234
2023-01-23 02:50:27.931683: step: 972/533, loss: 0.045240309089422226
2023-01-23 02:50:29.091830: step: 976/533, loss: 0.00171070103533566
2023-01-23 02:50:30.285337: step: 980/533, loss: 0.08156146854162216
2023-01-23 02:50:31.481929: step: 984/533, loss: 0.0013447761302813888
2023-01-23 02:50:32.640846: step: 988/533, loss: 0.004789638798683882
2023-01-23 02:50:33.836751: step: 992/533, loss: 0.0020843506790697575
2023-01-23 02:50:35.025987: step: 996/533, loss: 0.019885826855897903
2023-01-23 02:50:36.183776: step: 1000/533, loss: 0.007515716832131147
2023-01-23 02:50:37.381064: step: 1004/533, loss: 0.007029056549072266
2023-01-23 02:50:38.576446: step: 1008/533, loss: 0.0129852294921875
2023-01-23 02:50:39.739107: step: 1012/533, loss: 0.018865205347537994
2023-01-23 02:50:40.922859: step: 1016/533, loss: 0.00030233862344175577
2023-01-23 02:50:42.085980: step: 1020/533, loss: 0.09663896262645721
2023-01-23 02:50:43.263258: step: 1024/533, loss: 0.06732263416051865
2023-01-23 02:50:44.456028: step: 1028/533, loss: 0.01478595845401287
2023-01-23 02:50:45.586793: step: 1032/533, loss: 0.0420168861746788
2023-01-23 02:50:46.736676: step: 1036/533, loss: 0.07473564147949219
2023-01-23 02:50:47.871809: step: 1040/533, loss: 0.019064616411924362
2023-01-23 02:50:49.045273: step: 1044/533, loss: 0.13124370574951172
2023-01-23 02:50:50.182363: step: 1048/533, loss: 0.005586433224380016
2023-01-23 02:50:51.343171: step: 1052/533, loss: 0.023783493787050247
2023-01-23 02:50:52.515188: step: 1056/533, loss: 0.004500770941376686
2023-01-23 02:50:53.663272: step: 1060/533, loss: 0.06214962154626846
2023-01-23 02:50:54.813715: step: 1064/533, loss: 0.009563160128891468
2023-01-23 02:50:56.016277: step: 1068/533, loss: 0.06312179565429688
2023-01-23 02:50:57.194845: step: 1072/533, loss: 0.03809795901179314
2023-01-23 02:50:58.331205: step: 1076/533, loss: 0.004991292953491211
2023-01-23 02:50:59.464389: step: 1080/533, loss: 0.016753865405917168
2023-01-23 02:51:00.622223: step: 1084/533, loss: 0.022898579016327858
2023-01-23 02:51:01.871046: step: 1088/533, loss: 0.012741565704345703
2023-01-23 02:51:03.055663: step: 1092/533, loss: 0.15026415884494781
2023-01-23 02:51:04.227786: step: 1096/533, loss: 0.003010272979736328
2023-01-23 02:51:05.403783: step: 1100/533, loss: 0.016104698181152344
2023-01-23 02:51:06.607428: step: 1104/533, loss: 0.005273390095680952
2023-01-23 02:51:07.784209: step: 1108/533, loss: 0.0022059441544115543
2023-01-23 02:51:08.958157: step: 1112/533, loss: 0.011533929035067558
2023-01-23 02:51:10.146045: step: 1116/533, loss: 0.00527610769495368
2023-01-23 02:51:11.357656: step: 1120/533, loss: 0.008863449096679688
2023-01-23 02:51:12.535407: step: 1124/533, loss: 0.13792219758033752
2023-01-23 02:51:13.664343: step: 1128/533, loss: 0.0013053894508630037
2023-01-23 02:51:14.850897: step: 1132/533, loss: 0.004211998078972101
2023-01-23 02:51:16.053536: step: 1136/533, loss: 0.03299827501177788
2023-01-23 02:51:17.207904: step: 1140/533, loss: 0.03654613718390465
2023-01-23 02:51:18.365325: step: 1144/533, loss: 0.017261218279600143
2023-01-23 02:51:19.556903: step: 1148/533, loss: 0.024605702608823776
2023-01-23 02:51:20.726697: step: 1152/533, loss: 0.005193901248276234
2023-01-23 02:51:21.869690: step: 1156/533, loss: 0.0039022446144372225
2023-01-23 02:51:23.064181: step: 1160/533, loss: 0.016078472137451172
2023-01-23 02:51:24.268885: step: 1164/533, loss: 0.034882355481386185
2023-01-23 02:51:25.435008: step: 1168/533, loss: 0.0022861480247229338
2023-01-23 02:51:26.609343: step: 1172/533, loss: 6.87599167576991e-05
2023-01-23 02:51:27.772508: step: 1176/533, loss: 0.047203633934259415
2023-01-23 02:51:28.911750: step: 1180/533, loss: 0.012865830212831497
2023-01-23 02:51:30.086785: step: 1184/533, loss: 0.008940315805375576
2023-01-23 02:51:31.272924: step: 1188/533, loss: 0.03618317097425461
2023-01-23 02:51:32.440732: step: 1192/533, loss: 0.0059108734130859375
2023-01-23 02:51:33.612989: step: 1196/533, loss: 0.0028356551192700863
2023-01-23 02:51:34.775326: step: 1200/533, loss: 0.0007039070478640497
2023-01-23 02:51:35.940654: step: 1204/533, loss: 0.0004631996271200478
2023-01-23 02:51:37.124462: step: 1208/533, loss: 0.0008699417230673134
2023-01-23 02:51:38.325046: step: 1212/533, loss: 0.018605614081025124
2023-01-23 02:51:39.506334: step: 1216/533, loss: 0.013643073849380016
2023-01-23 02:51:40.671990: step: 1220/533, loss: 0.03987293317914009
2023-01-23 02:51:41.798561: step: 1224/533, loss: 0.005715799517929554
2023-01-23 02:51:43.001899: step: 1228/533, loss: 0.01930828206241131
2023-01-23 02:51:44.180047: step: 1232/533, loss: 0.0009300232632085681
2023-01-23 02:51:45.347760: step: 1236/533, loss: 0.03018360212445259
2023-01-23 02:51:46.525635: step: 1240/533, loss: 0.037119388580322266
2023-01-23 02:51:47.729404: step: 1244/533, loss: 0.03416137769818306
2023-01-23 02:51:48.888389: step: 1248/533, loss: 0.00020008085994049907
2023-01-23 02:51:50.029205: step: 1252/533, loss: 0.00022554397583007812
2023-01-23 02:51:51.225101: step: 1256/533, loss: 0.010517645627260208
2023-01-23 02:51:52.391515: step: 1260/533, loss: 0.01484232023358345
2023-01-23 02:51:53.594090: step: 1264/533, loss: 0.013745211996138096
2023-01-23 02:51:54.754392: step: 1268/533, loss: 5.016326758777723e-05
2023-01-23 02:51:55.920867: step: 1272/533, loss: 0.0025022507179528475
2023-01-23 02:51:57.121455: step: 1276/533, loss: 0.0003076553111895919
2023-01-23 02:51:58.300842: step: 1280/533, loss: 0.00577468890696764
2023-01-23 02:51:59.472573: step: 1284/533, loss: 0.0010597228538244963
2023-01-23 02:52:00.665016: step: 1288/533, loss: 0.005928707309067249
2023-01-23 02:52:01.851718: step: 1292/533, loss: 0.022014712914824486
2023-01-23 02:52:03.016101: step: 1296/533, loss: 0.05559501424431801
2023-01-23 02:52:04.178126: step: 1300/533, loss: 0.011143875308334827
2023-01-23 02:52:05.335053: step: 1304/533, loss: 0.006691360380500555
2023-01-23 02:52:06.503607: step: 1308/533, loss: 0.004321432206779718
2023-01-23 02:52:07.649177: step: 1312/533, loss: 0.009820937179028988
2023-01-23 02:52:08.800185: step: 1316/533, loss: 0.0040412903763353825
2023-01-23 02:52:10.008560: step: 1320/533, loss: 0.04025459289550781
2023-01-23 02:52:11.167348: step: 1324/533, loss: 0.012469768524169922
2023-01-23 02:52:12.361685: step: 1328/533, loss: 0.049068763852119446
2023-01-23 02:52:13.572322: step: 1332/533, loss: 0.016312599182128906
2023-01-23 02:52:14.759520: step: 1336/533, loss: 0.0009770393371582031
2023-01-23 02:52:15.917582: step: 1340/533, loss: 0.04604502022266388
2023-01-23 02:52:17.112539: step: 1344/533, loss: 0.03741512447595596
2023-01-23 02:52:18.298587: step: 1348/533, loss: 0.5269002914428711
2023-01-23 02:52:19.449886: step: 1352/533, loss: 0.0010107994312420487
2023-01-23 02:52:20.640247: step: 1356/533, loss: 0.0008288383833132684
2023-01-23 02:52:21.779926: step: 1360/533, loss: 0.0003665924014057964
2023-01-23 02:52:22.970055: step: 1364/533, loss: 0.00013344288163352758
2023-01-23 02:52:24.151871: step: 1368/533, loss: 0.04731407389044762
2023-01-23 02:52:25.329115: step: 1372/533, loss: 0.004719066899269819
2023-01-23 02:52:26.481030: step: 1376/533, loss: 0.002026286907494068
2023-01-23 02:52:27.615889: step: 1380/533, loss: 0.006644344422966242
2023-01-23 02:52:28.786638: step: 1384/533, loss: 0.0011403083335608244
2023-01-23 02:52:29.993570: step: 1388/533, loss: 0.03219585865736008
2023-01-23 02:52:31.164027: step: 1392/533, loss: 0.011390590108931065
2023-01-23 02:52:32.333269: step: 1396/533, loss: 0.059751417487859726
2023-01-23 02:52:33.493218: step: 1400/533, loss: 0.0038070681039243937
2023-01-23 02:52:34.673004: step: 1404/533, loss: 0.004620933905243874
2023-01-23 02:52:35.807809: step: 1408/533, loss: 0.005663537885993719
2023-01-23 02:52:37.008883: step: 1412/533, loss: 0.001876068185083568
2023-01-23 02:52:38.197838: step: 1416/533, loss: 0.07971706241369247
2023-01-23 02:52:39.393144: step: 1420/533, loss: 0.01218566857278347
2023-01-23 02:52:40.605194: step: 1424/533, loss: 0.01216878928244114
2023-01-23 02:52:41.756568: step: 1428/533, loss: 0.05049515143036842
2023-01-23 02:52:42.950838: step: 1432/533, loss: 0.048594094812870026
2023-01-23 02:52:44.121438: step: 1436/533, loss: 0.029944991692900658
2023-01-23 02:52:45.300582: step: 1440/533, loss: 0.005917740054428577
2023-01-23 02:52:46.486636: step: 1444/533, loss: 0.0016349792713299394
2023-01-23 02:52:47.670248: step: 1448/533, loss: 0.024352073669433594
2023-01-23 02:52:48.822957: step: 1452/533, loss: 0.0016530037391930819
2023-01-23 02:52:50.071107: step: 1456/533, loss: 0.002508545061573386
2023-01-23 02:52:51.236921: step: 1460/533, loss: 0.0540466345846653
2023-01-23 02:52:52.385992: step: 1464/533, loss: 0.007477569859474897
2023-01-23 02:52:53.560382: step: 1468/533, loss: 0.03422980010509491
2023-01-23 02:52:54.690830: step: 1472/533, loss: 0.0006747245788574219
2023-01-23 02:52:55.851705: step: 1476/533, loss: 0.0018912197556346655
2023-01-23 02:52:57.037187: step: 1480/533, loss: 0.0799618735909462
2023-01-23 02:52:58.156860: step: 1484/533, loss: 0.0011687278747558594
2023-01-23 02:52:59.346516: step: 1488/533, loss: 0.00216922746039927
2023-01-23 02:53:00.511585: step: 1492/533, loss: 0.04210357740521431
2023-01-23 02:53:01.679673: step: 1496/533, loss: 0.01060781441628933
2023-01-23 02:53:02.847280: step: 1500/533, loss: 0.028268814086914062
2023-01-23 02:53:04.011579: step: 1504/533, loss: 0.0071805003099143505
2023-01-23 02:53:05.184401: step: 1508/533, loss: 0.03542815148830414
2023-01-23 02:53:06.376085: step: 1512/533, loss: 0.018245410174131393
2023-01-23 02:53:07.541544: step: 1516/533, loss: 0.007300567347556353
2023-01-23 02:53:08.717645: step: 1520/533, loss: 0.004657936282455921
2023-01-23 02:53:09.891238: step: 1524/533, loss: 0.0015552521217614412
2023-01-23 02:53:11.110709: step: 1528/533, loss: 0.013571548275649548
2023-01-23 02:53:12.292514: step: 1532/533, loss: 0.00352821359410882
2023-01-23 02:53:13.486056: step: 1536/533, loss: 0.0027129172813147306
2023-01-23 02:53:14.693440: step: 1540/533, loss: 0.036319371312856674
2023-01-23 02:53:15.849340: step: 1544/533, loss: 0.03829554468393326
2023-01-23 02:53:17.021640: step: 1548/533, loss: 0.008475875481963158
2023-01-23 02:53:18.241407: step: 1552/533, loss: 0.0070514678955078125
2023-01-23 02:53:19.416608: step: 1556/533, loss: 0.0005015373462811112
2023-01-23 02:53:20.578421: step: 1560/533, loss: 0.04219703748822212
2023-01-23 02:53:21.772507: step: 1564/533, loss: 0.02217083051800728
2023-01-23 02:53:22.965187: step: 1568/533, loss: 0.004139900207519531
2023-01-23 02:53:24.122746: step: 1572/533, loss: 7.07626313669607e-05
2023-01-23 02:53:25.263107: step: 1576/533, loss: 0.027157379314303398
2023-01-23 02:53:26.421122: step: 1580/533, loss: 0.14897410571575165
2023-01-23 02:53:27.585005: step: 1584/533, loss: 0.005349826533347368
2023-01-23 02:53:28.776653: step: 1588/533, loss: 0.010769559070467949
2023-01-23 02:53:29.966180: step: 1592/533, loss: 0.02519550547003746
2023-01-23 02:53:31.152665: step: 1596/533, loss: 0.04316768795251846
2023-01-23 02:53:32.308229: step: 1600/533, loss: 0.0012823105789721012
2023-01-23 02:53:33.464687: step: 1604/533, loss: 0.015904640778899193
2023-01-23 02:53:34.631877: step: 1608/533, loss: 0.0019223212730139494
2023-01-23 02:53:35.817018: step: 1612/533, loss: 0.005879020784050226
2023-01-23 02:53:36.973589: step: 1616/533, loss: 0.0035712718963623047
2023-01-23 02:53:38.166492: step: 1620/533, loss: 0.023318292573094368
2023-01-23 02:53:39.343768: step: 1624/533, loss: 0.009914744645357132
2023-01-23 02:53:40.494786: step: 1628/533, loss: 0.0034047127701342106
2023-01-23 02:53:41.688350: step: 1632/533, loss: 0.014000892639160156
2023-01-23 02:53:42.870070: step: 1636/533, loss: 0.0201581958681345
2023-01-23 02:53:44.081045: step: 1640/533, loss: 0.0027790546882897615
2023-01-23 02:53:45.263506: step: 1644/533, loss: 0.0003223419189453125
2023-01-23 02:53:46.440056: step: 1648/533, loss: 0.008738135918974876
2023-01-23 02:53:47.598439: step: 1652/533, loss: 0.06151562184095383
2023-01-23 02:53:48.802217: step: 1656/533, loss: 0.0006672859308309853
2023-01-23 02:53:49.919162: step: 1660/533, loss: 0.006988143548369408
2023-01-23 02:53:51.113861: step: 1664/533, loss: 0.0005323886871337891
2023-01-23 02:53:52.302748: step: 1668/533, loss: 0.0012575149303302169
2023-01-23 02:53:53.469477: step: 1672/533, loss: 0.0011177064152434468
2023-01-23 02:53:54.633290: step: 1676/533, loss: 0.05244407430291176
2023-01-23 02:53:55.804673: step: 1680/533, loss: 0.006606960203498602
2023-01-23 02:53:57.032636: step: 1684/533, loss: 0.00037298203096725047
2023-01-23 02:53:58.190403: step: 1688/533, loss: 0.0564691536128521
2023-01-23 02:53:59.386422: step: 1692/533, loss: 0.015074063092470169
2023-01-23 02:54:00.585160: step: 1696/533, loss: 0.014576150104403496
2023-01-23 02:54:01.763274: step: 1700/533, loss: 0.0021986961364746094
2023-01-23 02:54:02.929941: step: 1704/533, loss: 0.003827739041298628
2023-01-23 02:54:04.115434: step: 1708/533, loss: 0.001714515732601285
2023-01-23 02:54:05.290840: step: 1712/533, loss: 0.022550201043486595
2023-01-23 02:54:06.456761: step: 1716/533, loss: 0.17543230950832367
2023-01-23 02:54:07.607713: step: 1720/533, loss: 0.014978217892348766
2023-01-23 02:54:08.770525: step: 1724/533, loss: 0.008336162194609642
2023-01-23 02:54:09.958114: step: 1728/533, loss: 0.0009703636169433594
2023-01-23 02:54:11.130981: step: 1732/533, loss: 0.0013994217151775956
2023-01-23 02:54:12.359969: step: 1736/533, loss: 0.032283976674079895
2023-01-23 02:54:13.497160: step: 1740/533, loss: 0.00791158713400364
2023-01-23 02:54:14.660335: step: 1744/533, loss: 0.0012325287098065019
2023-01-23 02:54:15.825869: step: 1748/533, loss: 0.1075240969657898
2023-01-23 02:54:17.025332: step: 1752/533, loss: 0.019856836646795273
2023-01-23 02:54:18.185598: step: 1756/533, loss: 0.005785751156508923
2023-01-23 02:54:19.327825: step: 1760/533, loss: 0.0017606735927984118
2023-01-23 02:54:20.545810: step: 1764/533, loss: 0.040729716420173645
2023-01-23 02:54:21.735205: step: 1768/533, loss: 0.0003330230829305947
2023-01-23 02:54:22.892917: step: 1772/533, loss: 0.003000545548275113
2023-01-23 02:54:24.041280: step: 1776/533, loss: 0.12473531067371368
2023-01-23 02:54:25.218575: step: 1780/533, loss: 0.011386299505829811
2023-01-23 02:54:26.382435: step: 1784/533, loss: 0.009250640869140625
2023-01-23 02:54:27.577765: step: 1788/533, loss: 0.035471536219120026
2023-01-23 02:54:28.764577: step: 1792/533, loss: 0.054877471178770065
2023-01-23 02:54:29.935114: step: 1796/533, loss: 0.009039211086928844
2023-01-23 02:54:31.139579: step: 1800/533, loss: 0.03161327913403511
2023-01-23 02:54:32.278616: step: 1804/533, loss: 0.0035272599197924137
2023-01-23 02:54:33.418251: step: 1808/533, loss: 0.012872028164565563
2023-01-23 02:54:34.598506: step: 1812/533, loss: 0.00036458970862440765
2023-01-23 02:54:35.788303: step: 1816/533, loss: 0.010746288113296032
2023-01-23 02:54:36.975810: step: 1820/533, loss: 0.04239597171545029
2023-01-23 02:54:38.113388: step: 1824/533, loss: 0.005365753546357155
2023-01-23 02:54:39.332238: step: 1828/533, loss: 0.005748176481574774
2023-01-23 02:54:40.517417: step: 1832/533, loss: 0.13444003462791443
2023-01-23 02:54:41.682199: step: 1836/533, loss: 0.038729477673769
2023-01-23 02:54:42.827845: step: 1840/533, loss: 0.004156065173447132
2023-01-23 02:54:44.022395: step: 1844/533, loss: 0.011990547180175781
2023-01-23 02:54:45.225277: step: 1848/533, loss: 0.5351228713989258
2023-01-23 02:54:46.398765: step: 1852/533, loss: 0.00042018890962935984
2023-01-23 02:54:47.547524: step: 1856/533, loss: 0.0038950920570641756
2023-01-23 02:54:48.723479: step: 1860/533, loss: 0.0020399093627929688
2023-01-23 02:54:49.896383: step: 1864/533, loss: 0.016020776703953743
2023-01-23 02:54:51.036518: step: 1868/533, loss: 0.0003823757288046181
2023-01-23 02:54:52.203549: step: 1872/533, loss: 0.160267174243927
2023-01-23 02:54:53.405026: step: 1876/533, loss: 0.055043794214725494
2023-01-23 02:54:54.547138: step: 1880/533, loss: 0.004176521208137274
2023-01-23 02:54:55.709030: step: 1884/533, loss: 0.0003499031299725175
2023-01-23 02:54:56.916536: step: 1888/533, loss: 0.03513612598180771
2023-01-23 02:54:58.087826: step: 1892/533, loss: 0.010804463177919388
2023-01-23 02:54:59.248849: step: 1896/533, loss: 0.004789483733475208
2023-01-23 02:55:00.411579: step: 1900/533, loss: 0.0002534866507630795
2023-01-23 02:55:01.585534: step: 1904/533, loss: 0.002976846881210804
2023-01-23 02:55:02.763056: step: 1908/533, loss: 0.022188186645507812
2023-01-23 02:55:03.957055: step: 1912/533, loss: 0.042273327708244324
2023-01-23 02:55:05.182010: step: 1916/533, loss: 0.0001011848435155116
2023-01-23 02:55:06.384273: step: 1920/533, loss: 0.006221294403076172
2023-01-23 02:55:07.565295: step: 1924/533, loss: 0.04015479236841202
2023-01-23 02:55:08.740952: step: 1928/533, loss: 0.02574901655316353
2023-01-23 02:55:09.899488: step: 1932/533, loss: 0.03933687135577202
2023-01-23 02:55:11.064375: step: 1936/533, loss: 0.00240325927734375
2023-01-23 02:55:12.285518: step: 1940/533, loss: 0.0028482438065111637
2023-01-23 02:55:13.473110: step: 1944/533, loss: 0.013387490063905716
2023-01-23 02:55:14.643803: step: 1948/533, loss: 0.002329874085262418
2023-01-23 02:55:15.835830: step: 1952/533, loss: 0.01641235314309597
2023-01-23 02:55:17.015205: step: 1956/533, loss: 0.017055273056030273
2023-01-23 02:55:18.185365: step: 1960/533, loss: 0.0067986492067575455
2023-01-23 02:55:19.373692: step: 1964/533, loss: 0.03813019022345543
2023-01-23 02:55:20.581895: step: 1968/533, loss: 0.11629810184240341
2023-01-23 02:55:21.771680: step: 1972/533, loss: 0.002849387936294079
2023-01-23 02:55:22.950456: step: 1976/533, loss: 0.0020013332832604647
2023-01-23 02:55:24.125748: step: 1980/533, loss: 0.00494384765625
2023-01-23 02:55:25.309336: step: 1984/533, loss: 0.001073646591976285
2023-01-23 02:55:26.493659: step: 1988/533, loss: 0.04678606986999512
2023-01-23 02:55:27.666425: step: 1992/533, loss: 0.022136688232421875
2023-01-23 02:55:28.849785: step: 1996/533, loss: 0.09453306347131729
2023-01-23 02:55:29.999356: step: 2000/533, loss: 0.008246994577348232
2023-01-23 02:55:31.159236: step: 2004/533, loss: 0.002620697021484375
2023-01-23 02:55:32.322691: step: 2008/533, loss: 0.08653044700622559
2023-01-23 02:55:33.470472: step: 2012/533, loss: 0.0023775578010827303
2023-01-23 02:55:34.626047: step: 2016/533, loss: 0.023912716656923294
2023-01-23 02:55:35.781714: step: 2020/533, loss: 0.003780317259952426
2023-01-23 02:55:36.979362: step: 2024/533, loss: 0.023583412170410156
2023-01-23 02:55:38.179625: step: 2028/533, loss: 0.00495491037145257
2023-01-23 02:55:39.333381: step: 2032/533, loss: 0.03590545803308487
2023-01-23 02:55:40.517614: step: 2036/533, loss: 0.004186439327895641
2023-01-23 02:55:41.650376: step: 2040/533, loss: 0.00045447348384186625
2023-01-23 02:55:42.841609: step: 2044/533, loss: 0.015240669250488281
2023-01-23 02:55:44.040508: step: 2048/533, loss: 0.008154154755175114
2023-01-23 02:55:45.213858: step: 2052/533, loss: 6.160736666060984e-05
2023-01-23 02:55:46.406165: step: 2056/533, loss: 0.008100509643554688
2023-01-23 02:55:47.576155: step: 2060/533, loss: 0.02331714704632759
2023-01-23 02:55:48.719530: step: 2064/533, loss: 4.8344292640686035
2023-01-23 02:55:49.898981: step: 2068/533, loss: 0.0019422532059252262
2023-01-23 02:55:51.053680: step: 2072/533, loss: 0.0006623268709518015
2023-01-23 02:55:52.255692: step: 2076/533, loss: 8.454322960460559e-05
2023-01-23 02:55:53.417303: step: 2080/533, loss: 0.023875214159488678
2023-01-23 02:55:54.643987: step: 2084/533, loss: 0.0006901741144247353
2023-01-23 02:55:55.809926: step: 2088/533, loss: 0.026457881554961205
2023-01-23 02:55:56.973811: step: 2092/533, loss: 0.013144207186996937
2023-01-23 02:55:58.177672: step: 2096/533, loss: 0.011030007153749466
2023-01-23 02:55:59.375519: step: 2100/533, loss: 0.03676357492804527
2023-01-23 02:56:00.533766: step: 2104/533, loss: 0.00734214810654521
2023-01-23 02:56:01.701614: step: 2108/533, loss: 0.01333236787468195
2023-01-23 02:56:02.848010: step: 2112/533, loss: 0.0020069123711436987
2023-01-23 02:56:04.024154: step: 2116/533, loss: 0.03376322239637375
2023-01-23 02:56:05.229682: step: 2120/533, loss: 0.01103897113353014
2023-01-23 02:56:06.384267: step: 2124/533, loss: 0.0008355140453204513
2023-01-23 02:56:07.580729: step: 2128/533, loss: 0.005996895022690296
2023-01-23 02:56:08.732829: step: 2132/533, loss: 0.008705330081284046
==================================================
Loss: 0.033
--------------------
Dev: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5287356321839081, 'r': 0.8518518518518519, 'f1': 0.6524822695035462}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.7115384615384616, 'r': 0.5873015873015873, 'f1': 0.6434782608695652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 19
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:56:55.575300: step: 4/533, loss: 0.0005886077997274697
2023-01-23 02:56:56.749118: step: 8/533, loss: 0.0020846365951001644
2023-01-23 02:56:57.905973: step: 12/533, loss: 0.06853103637695312
2023-01-23 02:56:59.050015: step: 16/533, loss: 0.0003220558282919228
2023-01-23 02:57:00.204245: step: 20/533, loss: 0.013419532217085361
2023-01-23 02:57:01.373647: step: 24/533, loss: 0.004877281375229359
2023-01-23 02:57:02.554487: step: 28/533, loss: 0.04770174250006676
2023-01-23 02:57:03.794956: step: 32/533, loss: 0.002239227294921875
2023-01-23 02:57:04.969407: step: 36/533, loss: 0.00337486295029521
2023-01-23 02:57:06.177284: step: 40/533, loss: 0.005089664366096258
2023-01-23 02:57:07.355427: step: 44/533, loss: 0.0008498192764818668
2023-01-23 02:57:08.556892: step: 48/533, loss: 0.012123679742217064
2023-01-23 02:57:09.712768: step: 52/533, loss: 0.046187594532966614
2023-01-23 02:57:10.899056: step: 56/533, loss: 0.018197156488895416
2023-01-23 02:57:12.085560: step: 60/533, loss: 0.015445232391357422
2023-01-23 02:57:13.295477: step: 64/533, loss: 0.03211021423339844
2023-01-23 02:57:14.470476: step: 68/533, loss: 0.00043125153752043843
2023-01-23 02:57:15.674864: step: 72/533, loss: 5.359649730962701e-05
2023-01-23 02:57:16.844000: step: 76/533, loss: 0.0009490966913290322
2023-01-23 02:57:18.003069: step: 80/533, loss: 0.037011146545410156
2023-01-23 02:57:19.187289: step: 84/533, loss: 0.00044002532376907766
2023-01-23 02:57:20.372493: step: 88/533, loss: 0.17801494896411896
2023-01-23 02:57:21.505587: step: 92/533, loss: 0.0012642861111089587
2023-01-23 02:57:22.654531: step: 96/533, loss: 0.025786591693758965
2023-01-23 02:57:23.793630: step: 100/533, loss: 0.0003948211669921875
2023-01-23 02:57:24.973021: step: 104/533, loss: 0.0006008148193359375
2023-01-23 02:57:26.172657: step: 108/533, loss: 5.309581683832221e-05
2023-01-23 02:57:27.365191: step: 112/533, loss: 0.006973231211304665
2023-01-23 02:57:28.500714: step: 116/533, loss: 7.009506134636467e-06
2023-01-23 02:57:29.650151: step: 120/533, loss: 0.016931915655732155
2023-01-23 02:57:30.863944: step: 124/533, loss: 0.01997542567551136
2023-01-23 02:57:32.036800: step: 128/533, loss: 0.0645233616232872
2023-01-23 02:57:33.173786: step: 132/533, loss: 0.010686302557587624
2023-01-23 02:57:34.351002: step: 136/533, loss: 0.042328834533691406
2023-01-23 02:57:35.503200: step: 140/533, loss: 0.013307953253388405
2023-01-23 02:57:36.657962: step: 144/533, loss: 0.0037047863006591797
2023-01-23 02:57:37.835003: step: 148/533, loss: 0.002474021865054965
2023-01-23 02:57:38.985140: step: 152/533, loss: 0.034833334386348724
2023-01-23 02:57:40.166137: step: 156/533, loss: 0.00022029876708984375
2023-01-23 02:57:41.367130: step: 160/533, loss: 0.039119720458984375
2023-01-23 02:57:42.510629: step: 164/533, loss: 0.00017089844914153218
2023-01-23 02:57:43.703162: step: 168/533, loss: 0.002909374190494418
2023-01-23 02:57:44.868983: step: 172/533, loss: 0.002466106554493308
2023-01-23 02:57:46.022880: step: 176/533, loss: 0.0013028144603595138
2023-01-23 02:57:47.223611: step: 180/533, loss: 0.03087158128619194
2023-01-23 02:57:48.402328: step: 184/533, loss: 0.08638477325439453
2023-01-23 02:57:49.562728: step: 188/533, loss: 0.04150676727294922
2023-01-23 02:57:50.759500: step: 192/533, loss: 0.05215311422944069
2023-01-23 02:57:51.948593: step: 196/533, loss: 0.008701801300048828
2023-01-23 02:57:53.100477: step: 200/533, loss: 0.00032444001408293843
2023-01-23 02:57:54.269841: step: 204/533, loss: 0.030159424990415573
2023-01-23 02:57:55.451138: step: 208/533, loss: 0.04551716148853302
2023-01-23 02:57:56.617723: step: 212/533, loss: 0.0031419754959642887
2023-01-23 02:57:57.797843: step: 216/533, loss: 0.00016069412231445312
2023-01-23 02:57:58.987330: step: 220/533, loss: 0.0012417794205248356
2023-01-23 02:58:00.155469: step: 224/533, loss: 0.003115367842838168
2023-01-23 02:58:01.296466: step: 228/533, loss: 0.005041694734245539
2023-01-23 02:58:02.458634: step: 232/533, loss: 0.018837736919522285
2023-01-23 02:58:03.597755: step: 236/533, loss: 0.0005652428371831775
2023-01-23 02:58:04.781084: step: 240/533, loss: 0.004841423127800226
2023-01-23 02:58:05.968763: step: 244/533, loss: 0.024548912420868874
2023-01-23 02:58:07.135609: step: 248/533, loss: 0.0027175426948815584
2023-01-23 02:58:08.299946: step: 252/533, loss: 0.0006651878356933594
2023-01-23 02:58:09.493021: step: 256/533, loss: 0.051253221929073334
2023-01-23 02:58:10.668840: step: 260/533, loss: 0.0347231887280941
2023-01-23 02:58:11.848064: step: 264/533, loss: 8.420944504905492e-05
2023-01-23 02:58:13.065493: step: 268/533, loss: 0.005065918434411287
2023-01-23 02:58:14.238491: step: 272/533, loss: 0.01858234405517578
2023-01-23 02:58:15.522728: step: 276/533, loss: 0.3724966049194336
2023-01-23 02:58:16.686013: step: 280/533, loss: 0.0010100125800818205
2023-01-23 02:58:17.851805: step: 284/533, loss: 0.012977314181625843
2023-01-23 02:58:19.063850: step: 288/533, loss: 0.0003398895205464214
2023-01-23 02:58:20.219198: step: 292/533, loss: 0.04905519634485245
2023-01-23 02:58:21.376601: step: 296/533, loss: 0.11014318466186523
2023-01-23 02:58:22.616100: step: 300/533, loss: 0.0010835647117346525
2023-01-23 02:58:23.750116: step: 304/533, loss: 6.0749054682673886e-05
2023-01-23 02:58:24.912362: step: 308/533, loss: 0.00024385451979469508
2023-01-23 02:58:26.061535: step: 312/533, loss: 0.0003857612609863281
2023-01-23 02:58:27.237055: step: 316/533, loss: 0.06520500034093857
2023-01-23 02:58:28.424005: step: 320/533, loss: 0.0005734444130212069
2023-01-23 02:58:29.613591: step: 324/533, loss: 0.02917947992682457
2023-01-23 02:58:30.742045: step: 328/533, loss: 0.017774105072021484
2023-01-23 02:58:31.883816: step: 332/533, loss: 0.00014009475125931203
2023-01-23 02:58:33.074100: step: 336/533, loss: 6.723403930664062e-05
2023-01-23 02:58:34.272429: step: 340/533, loss: 0.0009504318004474044
2023-01-23 02:58:35.453644: step: 344/533, loss: 0.0014159202110022306
2023-01-23 02:58:36.629254: step: 348/533, loss: 0.006699276156723499
2023-01-23 02:58:37.790073: step: 352/533, loss: 0.02167348936200142
2023-01-23 02:58:38.963663: step: 356/533, loss: 0.00017671585374046117
2023-01-23 02:58:40.128986: step: 360/533, loss: 0.007201528642326593
2023-01-23 02:58:41.321671: step: 364/533, loss: 0.0010522842640057206
2023-01-23 02:58:42.478876: step: 368/533, loss: 0.014066696166992188
2023-01-23 02:58:43.685518: step: 372/533, loss: 0.0008108139154501259
2023-01-23 02:58:44.847967: step: 376/533, loss: 0.005213260650634766
2023-01-23 02:58:46.001436: step: 380/533, loss: 0.08440346270799637
2023-01-23 02:58:47.136338: step: 384/533, loss: 0.0059181214310228825
2023-01-23 02:58:48.339993: step: 388/533, loss: 0.0453365333378315
2023-01-23 02:58:49.478404: step: 392/533, loss: 0.02545952796936035
2023-01-23 02:58:50.666236: step: 396/533, loss: 0.0031192777678370476
2023-01-23 02:58:51.855536: step: 400/533, loss: 0.004544734954833984
2023-01-23 02:58:53.030426: step: 404/533, loss: 0.0013781547313556075
2023-01-23 02:58:54.230808: step: 408/533, loss: 0.027086447924375534
2023-01-23 02:58:55.399531: step: 412/533, loss: 0.0352291576564312
2023-01-23 02:58:56.552244: step: 416/533, loss: 0.6356148719787598
2023-01-23 02:58:57.720177: step: 420/533, loss: 0.10403952747583389
2023-01-23 02:58:58.893277: step: 424/533, loss: 0.008613109588623047
2023-01-23 02:59:00.055088: step: 428/533, loss: 0.005357981193810701
2023-01-23 02:59:01.226840: step: 432/533, loss: 0.0004409789980854839
2023-01-23 02:59:02.417421: step: 436/533, loss: 5.15937790623866e-05
2023-01-23 02:59:03.560985: step: 440/533, loss: 0.02735147438943386
2023-01-23 02:59:04.708265: step: 444/533, loss: 0.0007070541614666581
2023-01-23 02:59:05.868375: step: 448/533, loss: 0.009868335910141468
2023-01-23 02:59:07.080702: step: 452/533, loss: 0.0013532638549804688
2023-01-23 02:59:08.216843: step: 456/533, loss: 0.00036716461181640625
2023-01-23 02:59:09.383631: step: 460/533, loss: 0.021535206586122513
2023-01-23 02:59:10.557947: step: 464/533, loss: 0.00033512114896439016
2023-01-23 02:59:11.695343: step: 468/533, loss: 0.0006453990936279297
2023-01-23 02:59:12.902771: step: 472/533, loss: 0.03422722965478897
2023-01-23 02:59:14.071624: step: 476/533, loss: 0.00012903213792014867
2023-01-23 02:59:15.207192: step: 480/533, loss: 0.014339828863739967
2023-01-23 02:59:16.382374: step: 484/533, loss: 0.01044159010052681
2023-01-23 02:59:17.545503: step: 488/533, loss: 0.05192422866821289
2023-01-23 02:59:18.725805: step: 492/533, loss: 0.0005170822259970009
2023-01-23 02:59:19.904494: step: 496/533, loss: 0.0045454977080225945
2023-01-23 02:59:21.077802: step: 500/533, loss: 0.00013699532428290695
2023-01-23 02:59:22.255648: step: 504/533, loss: 0.02984147146344185
2023-01-23 02:59:23.437310: step: 508/533, loss: 0.0005741119384765625
2023-01-23 02:59:24.577846: step: 512/533, loss: 0.004507732577621937
2023-01-23 02:59:25.749664: step: 516/533, loss: 0.002103519393131137
2023-01-23 02:59:26.925231: step: 520/533, loss: 2.9277802241267636e-05
2023-01-23 02:59:28.086273: step: 524/533, loss: 0.008983231149613857
2023-01-23 02:59:29.248911: step: 528/533, loss: 0.0468318946659565
2023-01-23 02:59:30.379851: step: 532/533, loss: 0.0013917923206463456
2023-01-23 02:59:31.522399: step: 536/533, loss: 0.0016618728404864669
2023-01-23 02:59:32.667715: step: 540/533, loss: 0.0043538096360862255
2023-01-23 02:59:33.843197: step: 544/533, loss: 0.007143926806747913
2023-01-23 02:59:34.972675: step: 548/533, loss: 0.004426193423569202
2023-01-23 02:59:36.100925: step: 552/533, loss: 0.00013427734666038305
2023-01-23 02:59:37.264179: step: 556/533, loss: 0.00029239655123092234
2023-01-23 02:59:38.423143: step: 560/533, loss: 0.0009088218212127686
2023-01-23 02:59:39.606968: step: 564/533, loss: 0.0022357942070811987
2023-01-23 02:59:40.811489: step: 568/533, loss: 0.0011319637997075915
2023-01-23 02:59:42.027442: step: 572/533, loss: 0.0021406172309070826
2023-01-23 02:59:43.173409: step: 576/533, loss: 0.0006431579240597785
2023-01-23 02:59:44.334224: step: 580/533, loss: 0.00021286011906340718
2023-01-23 02:59:45.504332: step: 584/533, loss: 0.01475515402853489
2023-01-23 02:59:46.628458: step: 588/533, loss: 0.00048542022705078125
2023-01-23 02:59:47.811118: step: 592/533, loss: 0.004576161503791809
2023-01-23 02:59:49.025282: step: 596/533, loss: 0.0001426696835551411
2023-01-23 02:59:50.254754: step: 600/533, loss: 0.014153290539979935
2023-01-23 02:59:51.461165: step: 604/533, loss: 0.0007802963373251259
2023-01-23 02:59:52.621549: step: 608/533, loss: 0.00010232925706077367
2023-01-23 02:59:53.828251: step: 612/533, loss: 0.01934070698916912
2023-01-23 02:59:54.968648: step: 616/533, loss: 0.010976982302963734
2023-01-23 02:59:56.158087: step: 620/533, loss: 0.00015578270540572703
2023-01-23 02:59:57.356425: step: 624/533, loss: 0.0016590118175372481
2023-01-23 02:59:58.523916: step: 628/533, loss: 0.007845116779208183
2023-01-23 02:59:59.720063: step: 632/533, loss: 0.007744312286376953
2023-01-23 03:00:00.905261: step: 636/533, loss: 0.0002020835963776335
2023-01-23 03:00:02.084702: step: 640/533, loss: 0.001143646310083568
2023-01-23 03:00:03.260767: step: 644/533, loss: 0.0006561279296875
2023-01-23 03:00:04.428388: step: 648/533, loss: 0.004530525300651789
2023-01-23 03:00:05.608246: step: 652/533, loss: 0.001343584037385881
2023-01-23 03:00:06.787138: step: 656/533, loss: 0.00165472028311342
2023-01-23 03:00:07.939116: step: 660/533, loss: 0.0007586479769088328
2023-01-23 03:00:09.137238: step: 664/533, loss: 0.01009063795208931
2023-01-23 03:00:10.309120: step: 668/533, loss: 0.0008470535976812243
2023-01-23 03:00:11.477886: step: 672/533, loss: 0.0005537032848224044
2023-01-23 03:00:12.671175: step: 676/533, loss: 0.0009410798666067421
2023-01-23 03:00:13.834394: step: 680/533, loss: 0.30586767196655273
2023-01-23 03:00:15.029483: step: 684/533, loss: 0.0010246277088299394
2023-01-23 03:00:16.196369: step: 688/533, loss: 0.0006807327154092491
2023-01-23 03:00:17.385365: step: 692/533, loss: 0.002361869905143976
2023-01-23 03:00:18.516637: step: 696/533, loss: 0.0003974914725404233
2023-01-23 03:00:19.715877: step: 700/533, loss: 0.002469873521476984
2023-01-23 03:00:20.865784: step: 704/533, loss: 0.003798961639404297
2023-01-23 03:00:22.001564: step: 708/533, loss: 0.0011365890968590975
2023-01-23 03:00:23.148224: step: 712/533, loss: 0.07625456154346466
2023-01-23 03:00:24.292822: step: 716/533, loss: 0.00031499864417128265
2023-01-23 03:00:25.471706: step: 720/533, loss: 0.00072393415030092
2023-01-23 03:00:26.620057: step: 724/533, loss: 0.04470658302307129
2023-01-23 03:00:27.798315: step: 728/533, loss: 0.0015951157547533512
2023-01-23 03:00:28.983354: step: 732/533, loss: 0.009563303552567959
2023-01-23 03:00:30.171324: step: 736/533, loss: 0.003547382541000843
2023-01-23 03:00:31.322690: step: 740/533, loss: 0.0012043475871905684
2023-01-23 03:00:32.531260: step: 744/533, loss: 0.1874251365661621
2023-01-23 03:00:33.731051: step: 748/533, loss: 0.037401676177978516
2023-01-23 03:00:34.913783: step: 752/533, loss: 0.08503856509923935
2023-01-23 03:00:36.036746: step: 756/533, loss: 0.10025987029075623
2023-01-23 03:00:37.218646: step: 760/533, loss: 0.005613732151687145
2023-01-23 03:00:38.459850: step: 764/533, loss: 0.007354640867561102
2023-01-23 03:00:39.641526: step: 768/533, loss: 0.026511192321777344
2023-01-23 03:00:40.869088: step: 772/533, loss: 0.00554161099717021
2023-01-23 03:00:42.024946: step: 776/533, loss: 0.0007149696466512978
2023-01-23 03:00:43.183837: step: 780/533, loss: 0.004193687345832586
2023-01-23 03:00:44.376220: step: 784/533, loss: 0.04234008863568306
2023-01-23 03:00:45.551542: step: 788/533, loss: 0.0004261017020326108
2023-01-23 03:00:46.734846: step: 792/533, loss: 0.0012734413612633944
2023-01-23 03:00:47.905288: step: 796/533, loss: 0.01250085886567831
2023-01-23 03:00:49.080558: step: 800/533, loss: 0.007552337367087603
2023-01-23 03:00:50.264497: step: 804/533, loss: 0.02440948598086834
2023-01-23 03:00:51.452571: step: 808/533, loss: 0.004042148590087891
2023-01-23 03:00:52.612569: step: 812/533, loss: 4.9209596909349784e-05
2023-01-23 03:00:53.835206: step: 816/533, loss: 0.1505233347415924
2023-01-23 03:00:54.984037: step: 820/533, loss: 7.152557373046875e-05
2023-01-23 03:00:56.134288: step: 824/533, loss: 0.004483032505959272
2023-01-23 03:00:57.338535: step: 828/533, loss: 0.0030532032251358032
2023-01-23 03:00:58.490513: step: 832/533, loss: 0.00026721955509856343
2023-01-23 03:00:59.703432: step: 836/533, loss: 0.00019340515427757055
2023-01-23 03:01:00.896037: step: 840/533, loss: 0.048323437571525574
2023-01-23 03:01:02.098651: step: 844/533, loss: 0.004909897223114967
2023-01-23 03:01:03.277525: step: 848/533, loss: 0.09964561462402344
2023-01-23 03:01:04.461963: step: 852/533, loss: 0.0630183219909668
2023-01-23 03:01:05.646831: step: 856/533, loss: 0.20232120156288147
2023-01-23 03:01:06.820446: step: 860/533, loss: 0.0067619322799146175
2023-01-23 03:01:08.002190: step: 864/533, loss: 0.0007730484358035028
2023-01-23 03:01:09.209823: step: 868/533, loss: 0.026348590850830078
2023-01-23 03:01:10.380535: step: 872/533, loss: 0.022862529382109642
2023-01-23 03:01:11.553904: step: 876/533, loss: 0.00386981968767941
2023-01-23 03:01:12.709987: step: 880/533, loss: 0.0009071350214071572
2023-01-23 03:01:13.925686: step: 884/533, loss: 0.042486000806093216
2023-01-23 03:01:15.126398: step: 888/533, loss: 0.11995582282543182
2023-01-23 03:01:16.320938: step: 892/533, loss: 0.00020332336134742945
2023-01-23 03:01:17.520345: step: 896/533, loss: 0.055998802185058594
2023-01-23 03:01:18.687114: step: 900/533, loss: 0.0024772644974291325
2023-01-23 03:01:19.891126: step: 904/533, loss: 0.00737838726490736
2023-01-23 03:01:21.039425: step: 908/533, loss: 0.000621795654296875
2023-01-23 03:01:22.225522: step: 912/533, loss: 0.06251354515552521
2023-01-23 03:01:23.399447: step: 916/533, loss: 0.004185867495834827
2023-01-23 03:01:24.585113: step: 920/533, loss: 0.006374740973114967
2023-01-23 03:01:25.761928: step: 924/533, loss: 0.0002525329473428428
2023-01-23 03:01:26.934719: step: 928/533, loss: 0.02062520943582058
2023-01-23 03:01:28.108918: step: 932/533, loss: 0.002858448075130582
2023-01-23 03:01:29.265364: step: 936/533, loss: 0.005259895231574774
2023-01-23 03:01:30.434777: step: 940/533, loss: 0.0004816532018594444
2023-01-23 03:01:31.617236: step: 944/533, loss: 0.011879158206284046
2023-01-23 03:01:32.791263: step: 948/533, loss: 0.00376129150390625
2023-01-23 03:01:33.994218: step: 952/533, loss: 0.03909454494714737
2023-01-23 03:01:35.144492: step: 956/533, loss: 0.0024597167503088713
2023-01-23 03:01:36.331121: step: 960/533, loss: 0.04390716552734375
2023-01-23 03:01:37.498433: step: 964/533, loss: 0.00010299683344783261
2023-01-23 03:01:38.659632: step: 968/533, loss: 0.0005018234369345009
2023-01-23 03:01:39.848504: step: 972/533, loss: 0.03115081787109375
2023-01-23 03:01:41.000483: step: 976/533, loss: 0.0972156673669815
2023-01-23 03:01:42.177490: step: 980/533, loss: 0.009401989169418812
2023-01-23 03:01:43.356457: step: 984/533, loss: 0.004040527157485485
2023-01-23 03:01:44.549122: step: 988/533, loss: 0.049971677362918854
2023-01-23 03:01:45.707132: step: 992/533, loss: 0.0004322052118368447
2023-01-23 03:01:46.896502: step: 996/533, loss: 0.0016117095947265625
2023-01-23 03:01:48.086066: step: 1000/533, loss: 0.00027065275935456157
2023-01-23 03:01:49.241766: step: 1004/533, loss: 0.4066218435764313
2023-01-23 03:01:50.410323: step: 1008/533, loss: 0.12249297648668289
2023-01-23 03:01:51.600743: step: 1012/533, loss: 0.011709118261933327
2023-01-23 03:01:52.763215: step: 1016/533, loss: 0.007724660448729992
2023-01-23 03:01:53.952703: step: 1020/533, loss: 0.02372436597943306
2023-01-23 03:01:55.103210: step: 1024/533, loss: 1.316070574830519e-05
2023-01-23 03:01:56.278246: step: 1028/533, loss: 0.014858436770737171
2023-01-23 03:01:57.416284: step: 1032/533, loss: 0.0002283096400788054
2023-01-23 03:01:58.571672: step: 1036/533, loss: 0.09309688210487366
2023-01-23 03:01:59.710612: step: 1040/533, loss: 0.02438983879983425
2023-01-23 03:02:00.844042: step: 1044/533, loss: 0.11804670840501785
2023-01-23 03:02:02.019802: step: 1048/533, loss: 0.01589689403772354
2023-01-23 03:02:03.186797: step: 1052/533, loss: 0.011453819461166859
2023-01-23 03:02:04.338296: step: 1056/533, loss: 0.054758742451667786
2023-01-23 03:02:05.469675: step: 1060/533, loss: 0.00033435822115279734
2023-01-23 03:02:06.675488: step: 1064/533, loss: 0.0005811691517010331
2023-01-23 03:02:07.834608: step: 1068/533, loss: 0.015230655670166016
2023-01-23 03:02:09.010842: step: 1072/533, loss: 0.003242635866627097
2023-01-23 03:02:10.196352: step: 1076/533, loss: 0.007020187564194202
2023-01-23 03:02:11.374962: step: 1080/533, loss: 0.00015792845806572586
2023-01-23 03:02:12.561491: step: 1084/533, loss: 0.008802413940429688
2023-01-23 03:02:13.720306: step: 1088/533, loss: 0.018341543152928352
2023-01-23 03:02:14.950420: step: 1092/533, loss: 0.03094339370727539
2023-01-23 03:02:16.076625: step: 1096/533, loss: 0.0026141167618334293
2023-01-23 03:02:17.250638: step: 1100/533, loss: 0.08951663970947266
2023-01-23 03:02:18.492367: step: 1104/533, loss: 0.0002616286219563335
2023-01-23 03:02:19.710870: step: 1108/533, loss: 0.0001354217529296875
2023-01-23 03:02:20.890263: step: 1112/533, loss: 0.006215572357177734
2023-01-23 03:02:22.092835: step: 1116/533, loss: 0.008065510541200638
2023-01-23 03:02:23.290449: step: 1120/533, loss: 0.006081008818000555
2023-01-23 03:02:24.472767: step: 1124/533, loss: 0.0047782897017896175
2023-01-23 03:02:25.610081: step: 1128/533, loss: 0.00404701242223382
2023-01-23 03:02:26.827585: step: 1132/533, loss: 0.004487133119255304
2023-01-23 03:02:27.979450: step: 1136/533, loss: 4.0531158447265625e-06
2023-01-23 03:02:29.190387: step: 1140/533, loss: 0.05892696604132652
2023-01-23 03:02:30.385270: step: 1144/533, loss: 0.00040349960909225047
2023-01-23 03:02:31.554158: step: 1148/533, loss: 0.05106792598962784
2023-01-23 03:02:32.707205: step: 1152/533, loss: 0.001617473317310214
2023-01-23 03:02:33.883136: step: 1156/533, loss: 0.08778515458106995
2023-01-23 03:02:35.048557: step: 1160/533, loss: 0.002426719758659601
2023-01-23 03:02:36.219806: step: 1164/533, loss: 0.0054111480712890625
2023-01-23 03:02:37.448693: step: 1168/533, loss: 0.004352569580078125
2023-01-23 03:02:38.638108: step: 1172/533, loss: 0.016757775098085403
2023-01-23 03:02:39.846207: step: 1176/533, loss: 5.122110366821289
2023-01-23 03:02:41.015573: step: 1180/533, loss: 0.02698221430182457
2023-01-23 03:02:42.200458: step: 1184/533, loss: 0.004998448304831982
2023-01-23 03:02:43.374457: step: 1188/533, loss: 0.0003503799671307206
2023-01-23 03:02:44.583769: step: 1192/533, loss: 0.020367145538330078
2023-01-23 03:02:45.770595: step: 1196/533, loss: 0.2772860527038574
2023-01-23 03:02:46.994271: step: 1200/533, loss: 0.0034521103370934725
2023-01-23 03:02:48.161508: step: 1204/533, loss: 1.487731969973538e-05
2023-01-23 03:02:49.350951: step: 1208/533, loss: 0.00666203536093235
2023-01-23 03:02:50.477505: step: 1212/533, loss: 0.0018039703136309981
2023-01-23 03:02:51.645298: step: 1216/533, loss: 0.0131378173828125
2023-01-23 03:02:52.805992: step: 1220/533, loss: 0.0062576294876635075
2023-01-23 03:02:53.984126: step: 1224/533, loss: 0.0024105070624500513
2023-01-23 03:02:55.151967: step: 1228/533, loss: 0.0026803971268236637
2023-01-23 03:02:56.345645: step: 1232/533, loss: 0.005998420529067516
2023-01-23 03:02:57.518133: step: 1236/533, loss: 1.024240255355835
2023-01-23 03:02:58.689747: step: 1240/533, loss: 0.031406402587890625
2023-01-23 03:02:59.862995: step: 1244/533, loss: 0.025767900049686432
2023-01-23 03:03:01.060386: step: 1248/533, loss: 0.007350135128945112
2023-01-23 03:03:02.233388: step: 1252/533, loss: 0.01758279837667942
2023-01-23 03:03:03.380100: step: 1256/533, loss: 0.007219123654067516
2023-01-23 03:03:04.562573: step: 1260/533, loss: 0.005278205964714289
2023-01-23 03:03:05.737943: step: 1264/533, loss: 0.013664436526596546
2023-01-23 03:03:06.901434: step: 1268/533, loss: 0.19037647545337677
2023-01-23 03:03:08.065755: step: 1272/533, loss: 0.009997367858886719
2023-01-23 03:03:09.232636: step: 1276/533, loss: 0.021406935527920723
2023-01-23 03:03:10.368192: step: 1280/533, loss: 0.07100877910852432
2023-01-23 03:03:11.516993: step: 1284/533, loss: 0.0025356293190270662
2023-01-23 03:03:12.672781: step: 1288/533, loss: 0.08441966027021408
2023-01-23 03:03:13.810731: step: 1292/533, loss: 0.0005296230083331466
2023-01-23 03:03:14.977367: step: 1296/533, loss: 0.007633018773049116
2023-01-23 03:03:16.159216: step: 1300/533, loss: 0.02295827865600586
2023-01-23 03:03:17.397318: step: 1304/533, loss: 0.013332939706742764
2023-01-23 03:03:18.612077: step: 1308/533, loss: 0.033670809119939804
2023-01-23 03:03:19.782212: step: 1312/533, loss: 0.04257016256451607
2023-01-23 03:03:20.964179: step: 1316/533, loss: 0.0009433746454305947
2023-01-23 03:03:22.177927: step: 1320/533, loss: 0.008856773376464844
2023-01-23 03:03:23.348686: step: 1324/533, loss: 0.0036297799088060856
2023-01-23 03:03:24.506786: step: 1328/533, loss: 0.0019344330066815019
2023-01-23 03:03:25.667851: step: 1332/533, loss: 0.011247063055634499
2023-01-23 03:03:26.811587: step: 1336/533, loss: 0.00048666002112440765
2023-01-23 03:03:28.018474: step: 1340/533, loss: 0.003752136370167136
2023-01-23 03:03:29.228254: step: 1344/533, loss: 0.0425909049808979
2023-01-23 03:03:30.405063: step: 1348/533, loss: 0.006059551611542702
2023-01-23 03:03:31.575304: step: 1352/533, loss: 0.005645942874252796
2023-01-23 03:03:32.749451: step: 1356/533, loss: 0.03469143062829971
2023-01-23 03:03:33.926378: step: 1360/533, loss: 0.0069252969697117805
2023-01-23 03:03:35.164337: step: 1364/533, loss: 0.5461196899414062
2023-01-23 03:03:36.328154: step: 1368/533, loss: 0.07063484191894531
2023-01-23 03:03:37.533193: step: 1372/533, loss: 0.0021238327026367188
2023-01-23 03:03:38.702682: step: 1376/533, loss: 0.025496339425444603
2023-01-23 03:03:39.904496: step: 1380/533, loss: 0.2572908401489258
2023-01-23 03:03:41.067711: step: 1384/533, loss: 0.0003055572451557964
2023-01-23 03:03:42.252143: step: 1388/533, loss: 0.025017881765961647
2023-01-23 03:03:43.415305: step: 1392/533, loss: 0.0010271072387695312
2023-01-23 03:03:44.569750: step: 1396/533, loss: 0.0025419234298169613
2023-01-23 03:03:45.767219: step: 1400/533, loss: 0.022492026910185814
2023-01-23 03:03:46.968877: step: 1404/533, loss: 0.03459892421960831
2023-01-23 03:03:48.148351: step: 1408/533, loss: 0.019272994250059128
2023-01-23 03:03:49.293118: step: 1412/533, loss: 0.011844253167510033
2023-01-23 03:03:50.473602: step: 1416/533, loss: 0.02653675153851509
2023-01-23 03:03:51.635025: step: 1420/533, loss: 3.218650817871094e-05
2023-01-23 03:03:52.822562: step: 1424/533, loss: 0.00127410888671875
2023-01-23 03:03:53.997990: step: 1428/533, loss: 0.001157474471256137
2023-01-23 03:03:55.167477: step: 1432/533, loss: 0.03273334354162216
2023-01-23 03:03:56.333102: step: 1436/533, loss: 0.001287269638851285
2023-01-23 03:03:57.533710: step: 1440/533, loss: 0.02900104597210884
2023-01-23 03:03:58.710538: step: 1444/533, loss: 4.7206878662109375e-05
2023-01-23 03:03:59.866897: step: 1448/533, loss: 0.27194613218307495
2023-01-23 03:04:01.035866: step: 1452/533, loss: 0.0010843276977539062
2023-01-23 03:04:02.240370: step: 1456/533, loss: 0.0332002155482769
2023-01-23 03:04:03.483704: step: 1460/533, loss: 0.03449106216430664
2023-01-23 03:04:04.679403: step: 1464/533, loss: 0.0015352248447015882
2023-01-23 03:04:05.855995: step: 1468/533, loss: 0.0028256417717784643
2023-01-23 03:04:07.030433: step: 1472/533, loss: 0.1281047761440277
2023-01-23 03:04:08.204992: step: 1476/533, loss: 0.001175737357698381
2023-01-23 03:04:09.449286: step: 1480/533, loss: 0.006404686253517866
2023-01-23 03:04:10.611533: step: 1484/533, loss: 0.013490390963852406
2023-01-23 03:04:11.774749: step: 1488/533, loss: 0.04128146171569824
2023-01-23 03:04:12.952688: step: 1492/533, loss: 0.002332592150196433
2023-01-23 03:04:14.125125: step: 1496/533, loss: 0.017383957281708717
2023-01-23 03:04:15.266406: step: 1500/533, loss: 0.0044089797884225845
2023-01-23 03:04:16.403440: step: 1504/533, loss: 0.04332747310400009
2023-01-23 03:04:17.540753: step: 1508/533, loss: 0.021468639373779297
2023-01-23 03:04:18.712503: step: 1512/533, loss: 0.00043354035005904734
2023-01-23 03:04:19.899752: step: 1516/533, loss: 0.04013385996222496
2023-01-23 03:04:21.104358: step: 1520/533, loss: 0.012973022647202015
2023-01-23 03:04:22.266999: step: 1524/533, loss: 4.1198727558366954e-05
2023-01-23 03:04:23.415178: step: 1528/533, loss: 0.0010884524090215564
2023-01-23 03:04:24.651298: step: 1532/533, loss: 0.02466287650167942
2023-01-23 03:04:25.829332: step: 1536/533, loss: 0.03653149679303169
2023-01-23 03:04:27.012224: step: 1540/533, loss: 0.02111187018454075
2023-01-23 03:04:28.151484: step: 1544/533, loss: 0.0004723549063783139
2023-01-23 03:04:29.362152: step: 1548/533, loss: 0.0007199287647381425
2023-01-23 03:04:30.519039: step: 1552/533, loss: 0.0566747672855854
2023-01-23 03:04:31.685056: step: 1556/533, loss: 0.001899623777717352
2023-01-23 03:04:32.845848: step: 1560/533, loss: 0.5502438545227051
2023-01-23 03:04:33.990163: step: 1564/533, loss: 0.004647445864975452
2023-01-23 03:04:35.129253: step: 1568/533, loss: 0.00039348602876998484
2023-01-23 03:04:36.318340: step: 1572/533, loss: 0.0006938934093341231
2023-01-23 03:04:37.526305: step: 1576/533, loss: 0.15553809702396393
2023-01-23 03:04:38.684507: step: 1580/533, loss: 0.0007397651206701994
2023-01-23 03:04:39.868864: step: 1584/533, loss: 0.02375955693423748
2023-01-23 03:04:41.047350: step: 1588/533, loss: 0.00013420582399703562
2023-01-23 03:04:42.239569: step: 1592/533, loss: 0.01761808432638645
2023-01-23 03:04:43.415258: step: 1596/533, loss: 0.05400505289435387
2023-01-23 03:04:44.582293: step: 1600/533, loss: 0.005527639761567116
2023-01-23 03:04:45.744814: step: 1604/533, loss: 0.06259031593799591
2023-01-23 03:04:46.938761: step: 1608/533, loss: 0.07448416203260422
2023-01-23 03:04:48.087985: step: 1612/533, loss: 0.10164089500904083
2023-01-23 03:04:49.288960: step: 1616/533, loss: 0.003637647721916437
2023-01-23 03:04:50.520476: step: 1620/533, loss: 0.014238452538847923
2023-01-23 03:04:51.707940: step: 1624/533, loss: 0.06112994998693466
2023-01-23 03:04:52.905837: step: 1628/533, loss: 0.0048576355911791325
2023-01-23 03:04:54.042674: step: 1632/533, loss: 0.004140663426369429
2023-01-23 03:04:55.208386: step: 1636/533, loss: 0.0073407175950706005
2023-01-23 03:04:56.416702: step: 1640/533, loss: 0.004893111996352673
2023-01-23 03:04:57.592280: step: 1644/533, loss: 0.00447921734303236
2023-01-23 03:04:58.772107: step: 1648/533, loss: 0.030223656445741653
2023-01-23 03:04:59.998786: step: 1652/533, loss: 0.06376419216394424
2023-01-23 03:05:01.140780: step: 1656/533, loss: 0.037380170077085495
2023-01-23 03:05:02.299855: step: 1660/533, loss: 0.0037206648848950863
2023-01-23 03:05:03.480243: step: 1664/533, loss: 0.0024383545387536287
2023-01-23 03:05:04.640387: step: 1668/533, loss: 0.040135763585567474
2023-01-23 03:05:05.797176: step: 1672/533, loss: 0.00013532637967728078
2023-01-23 03:05:06.995268: step: 1676/533, loss: 0.0004868507385253906
2023-01-23 03:05:08.146602: step: 1680/533, loss: 4.9591064453125e-05
2023-01-23 03:05:09.318055: step: 1684/533, loss: 2.9373170036706142e-05
2023-01-23 03:05:10.506195: step: 1688/533, loss: 0.00013394355482887477
2023-01-23 03:05:11.678252: step: 1692/533, loss: 4.024505687993951e-05
2023-01-23 03:05:12.820824: step: 1696/533, loss: 0.017134379595518112
2023-01-23 03:05:13.986309: step: 1700/533, loss: 0.006768226623535156
2023-01-23 03:05:15.140031: step: 1704/533, loss: 0.0004404068167787045
2023-01-23 03:05:16.332182: step: 1708/533, loss: 0.008815002627670765
2023-01-23 03:05:17.476768: step: 1712/533, loss: 0.08487816154956818
2023-01-23 03:05:18.608054: step: 1716/533, loss: 0.0005656242137774825
2023-01-23 03:05:19.788030: step: 1720/533, loss: 0.0015456199180334806
2023-01-23 03:05:20.995575: step: 1724/533, loss: 0.018176937475800514
2023-01-23 03:05:22.190506: step: 1728/533, loss: 0.12450714409351349
2023-01-23 03:05:23.368240: step: 1732/533, loss: 0.006127930246293545
2023-01-23 03:05:24.559835: step: 1736/533, loss: 0.014917850494384766
2023-01-23 03:05:25.720615: step: 1740/533, loss: 0.0043621063232421875
2023-01-23 03:05:26.898264: step: 1744/533, loss: 0.004134416580200195
2023-01-23 03:05:28.095081: step: 1748/533, loss: 0.022272301837801933
2023-01-23 03:05:29.266591: step: 1752/533, loss: 0.002297639846801758
2023-01-23 03:05:30.422597: step: 1756/533, loss: 0.0017546177841722965
2023-01-23 03:05:31.578563: step: 1760/533, loss: 0.5152382850646973
2023-01-23 03:05:32.745530: step: 1764/533, loss: 0.0025721550919115543
2023-01-23 03:05:33.922652: step: 1768/533, loss: 0.0020834924653172493
2023-01-23 03:05:35.098382: step: 1772/533, loss: 0.03519783169031143
2023-01-23 03:05:36.334329: step: 1776/533, loss: 0.05718240886926651
2023-01-23 03:05:37.520666: step: 1780/533, loss: 0.029549717903137207
2023-01-23 03:05:38.697286: step: 1784/533, loss: 0.04425792768597603
2023-01-23 03:05:39.884451: step: 1788/533, loss: 0.004256058018654585
2023-01-23 03:05:41.058792: step: 1792/533, loss: 0.0013744353782385588
2023-01-23 03:05:42.214341: step: 1796/533, loss: 0.005530834197998047
2023-01-23 03:05:43.402169: step: 1800/533, loss: 0.010906601324677467
2023-01-23 03:05:44.576907: step: 1804/533, loss: 0.02026844024658203
2023-01-23 03:05:45.723461: step: 1808/533, loss: 0.02513866499066353
2023-01-23 03:05:46.842629: step: 1812/533, loss: 0.0009048461797647178
2023-01-23 03:05:48.020836: step: 1816/533, loss: 0.00675168028101325
2023-01-23 03:05:49.221782: step: 1820/533, loss: 0.0035154344514012337
2023-01-23 03:05:50.422789: step: 1824/533, loss: 0.00260505685582757
2023-01-23 03:05:51.649184: step: 1828/533, loss: 0.041312407702207565
2023-01-23 03:05:52.805998: step: 1832/533, loss: 0.0010979652870446444
2023-01-23 03:05:53.985780: step: 1836/533, loss: 0.008643600158393383
2023-01-23 03:05:55.156625: step: 1840/533, loss: 0.004321003332734108
2023-01-23 03:05:56.341076: step: 1844/533, loss: 0.003247928572818637
2023-01-23 03:05:57.504895: step: 1848/533, loss: 0.0011290073161944747
2023-01-23 03:05:58.704571: step: 1852/533, loss: 0.00388507847674191
2023-01-23 03:05:59.863992: step: 1856/533, loss: 0.00414276123046875
2023-01-23 03:06:01.033966: step: 1860/533, loss: 0.21076726913452148
2023-01-23 03:06:02.218274: step: 1864/533, loss: 0.054128263145685196
2023-01-23 03:06:03.420333: step: 1868/533, loss: 0.00983820017427206
2023-01-23 03:06:04.602492: step: 1872/533, loss: 0.04686005041003227
2023-01-23 03:06:05.740795: step: 1876/533, loss: 0.0007840156904421747
2023-01-23 03:06:06.926097: step: 1880/533, loss: 0.00798187218606472
2023-01-23 03:06:08.104141: step: 1884/533, loss: 0.005003738682717085
2023-01-23 03:06:09.284005: step: 1888/533, loss: 0.00497207697480917
2023-01-23 03:06:10.417342: step: 1892/533, loss: 0.0006148338434286416
2023-01-23 03:06:11.575033: step: 1896/533, loss: 0.03353137895464897
2023-01-23 03:06:12.767096: step: 1900/533, loss: 0.05414552986621857
2023-01-23 03:06:13.915443: step: 1904/533, loss: 0.0008921623229980469
2023-01-23 03:06:15.097006: step: 1908/533, loss: 0.0067070964723825455
2023-01-23 03:06:16.270132: step: 1912/533, loss: 0.014531135559082031
2023-01-23 03:06:17.432435: step: 1916/533, loss: 0.0013049126137048006
2023-01-23 03:06:18.576789: step: 1920/533, loss: 0.00024919508723542094
2023-01-23 03:06:19.774255: step: 1924/533, loss: 0.0003031730593647808
2023-01-23 03:06:20.967974: step: 1928/533, loss: 0.0020389556884765625
2023-01-23 03:06:22.131601: step: 1932/533, loss: 0.05325908586382866
2023-01-23 03:06:23.375336: step: 1936/533, loss: 0.09697379916906357
2023-01-23 03:06:24.553781: step: 1940/533, loss: 0.0003757476806640625
2023-01-23 03:06:25.695060: step: 1944/533, loss: 6.27517729299143e-05
2023-01-23 03:06:26.832059: step: 1948/533, loss: 4.57763690064894e-06
2023-01-23 03:06:28.018016: step: 1952/533, loss: 0.024541093036532402
2023-01-23 03:06:29.227793: step: 1956/533, loss: 0.028744984418153763
2023-01-23 03:06:30.373195: step: 1960/533, loss: 0.000919818936381489
2023-01-23 03:06:31.539896: step: 1964/533, loss: 0.0005827904096804559
2023-01-23 03:06:32.698674: step: 1968/533, loss: 0.02389349788427353
2023-01-23 03:06:33.918168: step: 1972/533, loss: 0.1714106649160385
2023-01-23 03:06:35.050990: step: 1976/533, loss: 0.0001039028211380355
2023-01-23 03:06:36.224069: step: 1980/533, loss: 0.053618624806404114
2023-01-23 03:06:37.423682: step: 1984/533, loss: 0.00476760882884264
2023-01-23 03:06:38.594108: step: 1988/533, loss: 0.0037973406724631786
2023-01-23 03:06:39.757294: step: 1992/533, loss: 0.05294475704431534
2023-01-23 03:06:40.926622: step: 1996/533, loss: 0.00338916783221066
2023-01-23 03:06:42.131930: step: 2000/533, loss: 0.0022109029814600945
2023-01-23 03:06:43.305773: step: 2004/533, loss: 0.045327283442020416
2023-01-23 03:06:44.477770: step: 2008/533, loss: 0.0035783289931714535
2023-01-23 03:06:45.666665: step: 2012/533, loss: 0.012261963449418545
2023-01-23 03:06:46.822902: step: 2016/533, loss: 0.04805422201752663
2023-01-23 03:06:47.999247: step: 2020/533, loss: 0.009329653345048428
2023-01-23 03:06:49.143098: step: 2024/533, loss: 0.0013481139903888106
2023-01-23 03:06:50.310984: step: 2028/533, loss: 0.028441905975341797
2023-01-23 03:06:51.462378: step: 2032/533, loss: 0.003007602645084262
2023-01-23 03:06:52.676309: step: 2036/533, loss: 0.010295892134308815
2023-01-23 03:06:53.854839: step: 2040/533, loss: 0.00782165490090847
2023-01-23 03:06:55.027085: step: 2044/533, loss: 0.00035581589327193797
2023-01-23 03:06:56.212376: step: 2048/533, loss: 0.008481930941343307
2023-01-23 03:06:57.359398: step: 2052/533, loss: 9.479522850597277e-05
2023-01-23 03:06:58.544388: step: 2056/533, loss: 0.02820129320025444
2023-01-23 03:06:59.703164: step: 2060/533, loss: 0.008162785321474075
2023-01-23 03:07:00.889638: step: 2064/533, loss: 0.05465507507324219
2023-01-23 03:07:02.100870: step: 2068/533, loss: 0.0004142761172261089
2023-01-23 03:07:03.275416: step: 2072/533, loss: 0.05378603935241699
2023-01-23 03:07:04.433110: step: 2076/533, loss: 0.0031736374367028475
2023-01-23 03:07:05.633198: step: 2080/533, loss: 0.02724475972354412
2023-01-23 03:07:06.752383: step: 2084/533, loss: 0.001712703611701727
2023-01-23 03:07:07.917274: step: 2088/533, loss: 0.05514903366565704
2023-01-23 03:07:09.133441: step: 2092/533, loss: 0.014711570926010609
2023-01-23 03:07:10.321583: step: 2096/533, loss: 0.007003688719123602
2023-01-23 03:07:11.521382: step: 2100/533, loss: 0.0008621216402389109
2023-01-23 03:07:12.713769: step: 2104/533, loss: 0.0004925727844238281
2023-01-23 03:07:13.849132: step: 2108/533, loss: 0.0013575553894042969
2023-01-23 03:07:14.989313: step: 2112/533, loss: 0.037487030029296875
2023-01-23 03:07:16.170439: step: 2116/533, loss: 0.009822273626923561
2023-01-23 03:07:17.337161: step: 2120/533, loss: 0.009489918127655983
2023-01-23 03:07:18.534274: step: 2124/533, loss: 0.0016937257023528218
2023-01-23 03:07:19.716683: step: 2128/533, loss: 0.01073532085865736
2023-01-23 03:07:20.920074: step: 2132/533, loss: 0.011197661980986595
==================================================
Loss: 0.038
--------------------
Dev: {'event': {'p': 0.6279594137542277, 'r': 0.7416777629826897, 'f1': 0.68009768009768}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6633663366336634, 'r': 0.8139386189258312, 'f1': 0.7309790410565605}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.5822784810126582, 'r': 0.8518518518518519, 'f1': 0.6917293233082706}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.5961538461538461, 'r': 0.49206349206349204, 'f1': 0.5391304347826087}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:08:01.796996: step: 4/533, loss: 0.2114221602678299
2023-01-23 03:08:02.950159: step: 8/533, loss: 0.0007483959197998047
2023-01-23 03:08:04.152817: step: 12/533, loss: 0.054314516484737396
2023-01-23 03:08:05.328366: step: 16/533, loss: 0.0029611587524414062
2023-01-23 03:08:06.520143: step: 20/533, loss: 0.008453655056655407
2023-01-23 03:08:07.701140: step: 24/533, loss: 0.012305354699492455
2023-01-23 03:08:08.875763: step: 28/533, loss: 0.0008993148803710938
2023-01-23 03:08:09.999040: step: 32/533, loss: 0.0005504608270712197
2023-01-23 03:08:11.158104: step: 36/533, loss: 0.00023708344087935984
2023-01-23 03:08:12.399216: step: 40/533, loss: 0.4376079738140106
2023-01-23 03:08:13.536783: step: 44/533, loss: 0.003211879637092352
2023-01-23 03:08:14.701520: step: 48/533, loss: 0.0015024185413494706
2023-01-23 03:08:15.852550: step: 52/533, loss: 0.00014915467181708664
2023-01-23 03:08:17.056214: step: 56/533, loss: 0.3636995255947113
2023-01-23 03:08:18.211530: step: 60/533, loss: 0.010753822512924671
2023-01-23 03:08:19.404633: step: 64/533, loss: 0.003022480057552457
2023-01-23 03:08:20.561611: step: 68/533, loss: 0.0028556822799146175
2023-01-23 03:08:21.736776: step: 72/533, loss: 0.018155287951231003
2023-01-23 03:08:22.916622: step: 76/533, loss: 0.0011999130947515368
2023-01-23 03:08:24.118377: step: 80/533, loss: 0.07744219154119492
2023-01-23 03:08:25.284141: step: 84/533, loss: 0.025572966784238815
2023-01-23 03:08:26.435502: step: 88/533, loss: 0.00023365022207144648
2023-01-23 03:08:27.605307: step: 92/533, loss: 0.0009333133930340409
2023-01-23 03:08:28.790594: step: 96/533, loss: 0.024586105719208717
2023-01-23 03:08:29.959143: step: 100/533, loss: 0.0007363319746218622
2023-01-23 03:08:31.153997: step: 104/533, loss: 0.0004058837948832661
2023-01-23 03:08:32.321601: step: 108/533, loss: 0.006507396697998047
2023-01-23 03:08:33.525191: step: 112/533, loss: 3.337860107421875e-06
2023-01-23 03:08:34.710052: step: 116/533, loss: 0.09514904022216797
2023-01-23 03:08:35.830012: step: 120/533, loss: 0.010058355517685413
2023-01-23 03:08:37.015927: step: 124/533, loss: 0.12287445366382599
2023-01-23 03:08:38.202257: step: 128/533, loss: 0.04804229736328125
2023-01-23 03:08:39.309764: step: 132/533, loss: 0.010461139492690563
2023-01-23 03:08:40.515117: step: 136/533, loss: 5.998611595714465e-05
2023-01-23 03:08:41.668041: step: 140/533, loss: 0.031055260449647903
2023-01-23 03:08:42.833379: step: 144/533, loss: 0.0007986068958416581
2023-01-23 03:08:43.974949: step: 148/533, loss: 0.0013193131890147924
2023-01-23 03:08:45.122535: step: 152/533, loss: 0.0019273757934570312
2023-01-23 03:08:46.297616: step: 156/533, loss: 0.053510092198848724
2023-01-23 03:08:47.487383: step: 160/533, loss: 0.00019378661818336695
2023-01-23 03:08:48.640688: step: 164/533, loss: 0.002864933107048273
2023-01-23 03:08:49.844676: step: 168/533, loss: 0.004442405886948109
2023-01-23 03:08:51.013648: step: 172/533, loss: 0.059233762323856354
2023-01-23 03:08:52.184796: step: 176/533, loss: 0.00818567257374525
2023-01-23 03:08:53.421983: step: 180/533, loss: 0.020816516131162643
2023-01-23 03:08:54.571167: step: 184/533, loss: 0.044381141662597656
2023-01-23 03:08:55.714687: step: 188/533, loss: 0.006442356389015913
2023-01-23 03:08:56.896336: step: 192/533, loss: 0.0042479513213038445
2023-01-23 03:08:58.070449: step: 196/533, loss: 0.00030841826810501516
2023-01-23 03:08:59.273613: step: 200/533, loss: 0.001988649368286133
2023-01-23 03:09:00.423018: step: 204/533, loss: 0.0006410598871298134
2023-01-23 03:09:01.528778: step: 208/533, loss: 0.06265778839588165
2023-01-23 03:09:02.696059: step: 212/533, loss: 0.029312897473573685
2023-01-23 03:09:03.856814: step: 216/533, loss: 0.00338916783221066
2023-01-23 03:09:05.011313: step: 220/533, loss: 3.06129441014491e-05
2023-01-23 03:09:06.226484: step: 224/533, loss: 0.006083297543227673
2023-01-23 03:09:07.381048: step: 228/533, loss: 0.004646826069802046
2023-01-23 03:09:08.526425: step: 232/533, loss: 0.006245899014174938
2023-01-23 03:09:09.703946: step: 236/533, loss: 0.016956519335508347
2023-01-23 03:09:10.892819: step: 240/533, loss: 0.008573818020522594
2023-01-23 03:09:12.110206: step: 244/533, loss: 0.00300350203178823
2023-01-23 03:09:13.275831: step: 248/533, loss: 0.00211334228515625
2023-01-23 03:09:14.450495: step: 252/533, loss: 0.0003257751523051411
2023-01-23 03:09:15.622495: step: 256/533, loss: 0.1889963150024414
2023-01-23 03:09:16.835592: step: 260/533, loss: 0.00031490327091887593
2023-01-23 03:09:18.058732: step: 264/533, loss: 9.660721116233617e-05
2023-01-23 03:09:19.224507: step: 268/533, loss: 0.028276730328798294
2023-01-23 03:09:20.367525: step: 272/533, loss: 0.0002155303955078125
2023-01-23 03:09:21.552822: step: 276/533, loss: 0.008719349279999733
2023-01-23 03:09:22.708073: step: 280/533, loss: 0.0025572776794433594
2023-01-23 03:09:23.874666: step: 284/533, loss: 0.025408077985048294
2023-01-23 03:09:25.038516: step: 288/533, loss: 0.0012783050769940019
2023-01-23 03:09:26.232117: step: 292/533, loss: 0.017495252192020416
2023-01-23 03:09:27.399464: step: 296/533, loss: 4.3678286601789296e-05
2023-01-23 03:09:28.612999: step: 300/533, loss: 0.031350038945674896
2023-01-23 03:09:29.799985: step: 304/533, loss: 0.01266541425138712
2023-01-23 03:09:30.998228: step: 308/533, loss: 0.03453044965863228
2023-01-23 03:09:32.152545: step: 312/533, loss: 0.03584041818976402
2023-01-23 03:09:33.370534: step: 316/533, loss: 0.031690120697021484
2023-01-23 03:09:34.567165: step: 320/533, loss: 0.008761787787079811
2023-01-23 03:09:35.697364: step: 324/533, loss: 0.007081317715346813
2023-01-23 03:09:36.878230: step: 328/533, loss: 0.00044803618220612407
2023-01-23 03:09:38.066105: step: 332/533, loss: 0.00107240688521415
2023-01-23 03:09:39.274687: step: 336/533, loss: 0.0007678032270632684
2023-01-23 03:09:40.418624: step: 340/533, loss: 0.07104358822107315
2023-01-23 03:09:41.557956: step: 344/533, loss: 2.307891918462701e-05
2023-01-23 03:09:42.738354: step: 348/533, loss: 0.01395959872752428
2023-01-23 03:09:43.967294: step: 352/533, loss: 0.00013370515080168843
2023-01-23 03:09:45.099419: step: 356/533, loss: 0.0005534171941690147
2023-01-23 03:09:46.295819: step: 360/533, loss: 0.05240488424897194
2023-01-23 03:09:47.420732: step: 364/533, loss: 3.604888843256049e-05
2023-01-23 03:09:48.574809: step: 368/533, loss: 0.0011074065696448088
2023-01-23 03:09:49.776576: step: 372/533, loss: 0.008075714111328125
2023-01-23 03:09:50.916701: step: 376/533, loss: 0.0010364532936364412
2023-01-23 03:09:52.079213: step: 380/533, loss: 0.002929878421127796
2023-01-23 03:09:53.237933: step: 384/533, loss: 1.583099401614163e-05
2023-01-23 03:09:54.434777: step: 388/533, loss: 6.427765038097277e-05
2023-01-23 03:09:55.623897: step: 392/533, loss: 0.00099945068359375
2023-01-23 03:09:56.783783: step: 396/533, loss: 1.831054760259576e-05
2023-01-23 03:09:57.912666: step: 400/533, loss: 5.664825584972277e-05
2023-01-23 03:09:59.049425: step: 404/533, loss: 0.0048836711794137955
2023-01-23 03:10:00.198004: step: 408/533, loss: 0.011579811573028564
2023-01-23 03:10:01.395577: step: 412/533, loss: 0.05727224424481392
2023-01-23 03:10:02.595924: step: 416/533, loss: 0.011657333932816982
2023-01-23 03:10:03.773918: step: 420/533, loss: 0.07051172107458115
2023-01-23 03:10:04.956519: step: 424/533, loss: 0.02228241041302681
2023-01-23 03:10:06.120879: step: 428/533, loss: 0.01579265668988228
2023-01-23 03:10:07.305440: step: 432/533, loss: 0.012528609484434128
2023-01-23 03:10:08.482717: step: 436/533, loss: 0.018306922167539597
2023-01-23 03:10:09.635105: step: 440/533, loss: 0.01898346096277237
2023-01-23 03:10:10.841759: step: 444/533, loss: 0.00022840499877929688
2023-01-23 03:10:12.023639: step: 448/533, loss: 0.014329385943710804
2023-01-23 03:10:13.165901: step: 452/533, loss: 0.019863223657011986
2023-01-23 03:10:14.364457: step: 456/533, loss: 0.005616378504782915
2023-01-23 03:10:15.556014: step: 460/533, loss: -1.0156631105928682e-05
2023-01-23 03:10:16.729123: step: 464/533, loss: 0.0011076927185058594
2023-01-23 03:10:17.937305: step: 468/533, loss: 0.04111747443675995
2023-01-23 03:10:19.098287: step: 472/533, loss: 0.0002289771946379915
2023-01-23 03:10:20.271868: step: 476/533, loss: 0.0017118453979492188
2023-01-23 03:10:21.458339: step: 480/533, loss: 0.00015544891357421875
2023-01-23 03:10:22.671981: step: 484/533, loss: 0.026804352179169655
2023-01-23 03:10:23.871299: step: 488/533, loss: 0.0007459640619345009
2023-01-23 03:10:25.072008: step: 492/533, loss: 0.027368545532226562
2023-01-23 03:10:26.218020: step: 496/533, loss: 1.926422191900201e-05
2023-01-23 03:10:27.377380: step: 500/533, loss: 0.028551483526825905
2023-01-23 03:10:28.553984: step: 504/533, loss: 0.10369911044836044
2023-01-23 03:10:29.722778: step: 508/533, loss: 0.09845905005931854
2023-01-23 03:10:30.894908: step: 512/533, loss: 7.123946852516383e-05
2023-01-23 03:10:32.052693: step: 516/533, loss: 0.051432374864816666
2023-01-23 03:10:33.198298: step: 520/533, loss: 4.7063826059456915e-05
2023-01-23 03:10:34.388166: step: 524/533, loss: 0.007857322692871094
2023-01-23 03:10:35.526323: step: 528/533, loss: 0.05198555067181587
2023-01-23 03:10:36.696954: step: 532/533, loss: 0.001773929689079523
2023-01-23 03:10:37.827362: step: 536/533, loss: 6.031990051269531e-05
2023-01-23 03:10:38.987226: step: 540/533, loss: 0.010657978244125843
2023-01-23 03:10:40.170493: step: 544/533, loss: 0.020488500595092773
2023-01-23 03:10:41.381919: step: 548/533, loss: 0.0020929814781993628
2023-01-23 03:10:42.545395: step: 552/533, loss: 0.023758888244628906
2023-01-23 03:10:43.696165: step: 556/533, loss: 0.0066515919752418995
2023-01-23 03:10:44.884750: step: 560/533, loss: 0.0038924694526940584
2023-01-23 03:10:46.070846: step: 564/533, loss: 0.013571548275649548
2023-01-23 03:10:47.224331: step: 568/533, loss: 3.089904930675402e-05
2023-01-23 03:10:48.388362: step: 572/533, loss: 0.0016660690307617188
2023-01-23 03:10:49.572097: step: 576/533, loss: 0.11463909596204758
2023-01-23 03:10:50.773814: step: 580/533, loss: 0.13136129081249237
2023-01-23 03:10:51.980496: step: 584/533, loss: 0.050052642822265625
2023-01-23 03:10:53.115431: step: 588/533, loss: 0.0009054660913534462
2023-01-23 03:10:54.243283: step: 592/533, loss: 0.0008127689943648875
2023-01-23 03:10:55.405069: step: 596/533, loss: 0.0009230375289916992
2023-01-23 03:10:56.584686: step: 600/533, loss: 0.1051357239484787
2023-01-23 03:10:57.754046: step: 604/533, loss: 0.00024251938157249242
2023-01-23 03:10:58.959246: step: 608/533, loss: 0.041836928576231
2023-01-23 03:11:00.145724: step: 612/533, loss: 0.024132154881954193
2023-01-23 03:11:01.318090: step: 616/533, loss: 0.007435894571244717
2023-01-23 03:11:02.459062: step: 620/533, loss: 0.005153465550392866
2023-01-23 03:11:03.607732: step: 624/533, loss: 0.0006205082172527909
2023-01-23 03:11:04.727467: step: 628/533, loss: 0.001353359199129045
2023-01-23 03:11:05.915429: step: 632/533, loss: 0.009461212903261185
2023-01-23 03:11:07.121494: step: 636/533, loss: 0.018471335992217064
2023-01-23 03:11:08.289896: step: 640/533, loss: 0.0191816333681345
2023-01-23 03:11:09.478236: step: 644/533, loss: 0.032549094408750534
2023-01-23 03:11:10.668565: step: 648/533, loss: 0.026899147778749466
2023-01-23 03:11:11.835119: step: 652/533, loss: 0.033650971949100494
2023-01-23 03:11:12.995502: step: 656/533, loss: 0.017066096886992455
2023-01-23 03:11:14.140331: step: 660/533, loss: 0.0011143684387207031
2023-01-23 03:11:15.308139: step: 664/533, loss: 0.01226501539349556
2023-01-23 03:11:16.463850: step: 668/533, loss: 0.00025739672128111124
2023-01-23 03:11:17.652030: step: 672/533, loss: 0.0008543014409951866
2023-01-23 03:11:18.807050: step: 676/533, loss: 0.0025899887550622225
2023-01-23 03:11:20.008553: step: 680/533, loss: 0.08083362877368927
2023-01-23 03:11:21.183307: step: 684/533, loss: 0.010121727362275124
2023-01-23 03:11:22.424789: step: 688/533, loss: 0.00011482238915050402
2023-01-23 03:11:23.584039: step: 692/533, loss: 0.0028248669113963842
2023-01-23 03:11:24.755385: step: 696/533, loss: 0.04645667225122452
2023-01-23 03:11:25.927927: step: 700/533, loss: 0.022718334570527077
2023-01-23 03:11:27.052569: step: 704/533, loss: 0.002287614392116666
2023-01-23 03:11:28.239616: step: 708/533, loss: 0.031145477667450905
2023-01-23 03:11:29.439083: step: 712/533, loss: 0.008761787787079811
2023-01-23 03:11:30.634816: step: 716/533, loss: 0.00011377334885764867
2023-01-23 03:11:31.888573: step: 720/533, loss: 0.0005422592512331903
2023-01-23 03:11:33.058022: step: 724/533, loss: 4.682540748035535e-05
2023-01-23 03:11:34.214659: step: 728/533, loss: 0.00013380050950217992
2023-01-23 03:11:35.349821: step: 732/533, loss: 0.04857831075787544
2023-01-23 03:11:36.534737: step: 736/533, loss: 0.0002054929791484028
2023-01-23 03:11:37.712747: step: 740/533, loss: 0.02416095696389675
2023-01-23 03:11:38.874097: step: 744/533, loss: 0.001089763711206615
2023-01-23 03:11:40.046507: step: 748/533, loss: 0.005036068148910999
2023-01-23 03:11:41.210890: step: 752/533, loss: 9.722709364723414e-05
2023-01-23 03:11:42.393867: step: 756/533, loss: 0.002954196883365512
2023-01-23 03:11:43.540281: step: 760/533, loss: 0.0008681297767907381
2023-01-23 03:11:44.680984: step: 764/533, loss: 0.0043032169342041016
2023-01-23 03:11:45.937175: step: 768/533, loss: 0.04064664617180824
2023-01-23 03:11:47.119463: step: 772/533, loss: 0.08902730792760849
2023-01-23 03:11:48.319038: step: 776/533, loss: 0.0171966552734375
2023-01-23 03:11:49.503665: step: 780/533, loss: 0.009490680880844593
2023-01-23 03:11:50.675352: step: 784/533, loss: 0.012571334838867188
2023-01-23 03:11:51.852111: step: 788/533, loss: 0.029239654541015625
2023-01-23 03:11:53.003962: step: 792/533, loss: 0.006228351499885321
2023-01-23 03:11:54.162214: step: 796/533, loss: 0.0014430045848712325
2023-01-23 03:11:55.295677: step: 800/533, loss: 0.04431457817554474
2023-01-23 03:11:56.465261: step: 804/533, loss: 0.000459051167126745
2023-01-23 03:11:57.646903: step: 808/533, loss: 0.009197045117616653
2023-01-23 03:11:58.802866: step: 812/533, loss: 0.03645050898194313
2023-01-23 03:12:00.005646: step: 816/533, loss: 0.003945732023566961
2023-01-23 03:12:01.149252: step: 820/533, loss: 0.03385419771075249
2023-01-23 03:12:02.296839: step: 824/533, loss: 1.2302399227337446e-05
2023-01-23 03:12:03.425894: step: 828/533, loss: 0.006670760922133923
2023-01-23 03:12:04.619535: step: 832/533, loss: 0.0007033348665572703
2023-01-23 03:12:05.760187: step: 836/533, loss: 0.039798736572265625
2023-01-23 03:12:06.963252: step: 840/533, loss: 0.004310226533561945
2023-01-23 03:12:08.139708: step: 844/533, loss: 0.0002499580441508442
2023-01-23 03:12:09.320674: step: 848/533, loss: 0.0006010055658407509
2023-01-23 03:12:10.512967: step: 852/533, loss: 0.010681104846298695
2023-01-23 03:12:11.675613: step: 856/533, loss: 0.011629200540482998
2023-01-23 03:12:12.882319: step: 860/533, loss: 0.0016603947151452303
2023-01-23 03:12:14.075529: step: 864/533, loss: 0.00121650705114007
2023-01-23 03:12:15.266233: step: 868/533, loss: 0.0017477036453783512
2023-01-23 03:12:16.453428: step: 872/533, loss: 0.006692838855087757
2023-01-23 03:12:17.650219: step: 876/533, loss: 0.006122398190200329
2023-01-23 03:12:18.871459: step: 880/533, loss: 0.0006157875177450478
2023-01-23 03:12:20.025464: step: 884/533, loss: 0.020538795739412308
2023-01-23 03:12:21.207874: step: 888/533, loss: 0.02670116536319256
2023-01-23 03:12:22.441005: step: 892/533, loss: 0.01110620517283678
2023-01-23 03:12:23.599695: step: 896/533, loss: 0.2819734215736389
2023-01-23 03:12:24.775691: step: 900/533, loss: 0.0001598358212504536
2023-01-23 03:12:25.954087: step: 904/533, loss: 0.0011553765507414937
2023-01-23 03:12:27.192966: step: 908/533, loss: 0.006258392706513405
2023-01-23 03:12:28.379500: step: 912/533, loss: 0.0023877143394201994
2023-01-23 03:12:29.553306: step: 916/533, loss: 0.0025774003006517887
2023-01-23 03:12:30.699754: step: 920/533, loss: 2.2602082026423886e-05
2023-01-23 03:12:31.865492: step: 924/533, loss: 0.005808830261230469
2023-01-23 03:12:33.061577: step: 928/533, loss: 0.018293190747499466
2023-01-23 03:12:34.215536: step: 932/533, loss: 0.03265724331140518
2023-01-23 03:12:35.373858: step: 936/533, loss: 0.020064163953065872
2023-01-23 03:12:36.517795: step: 940/533, loss: 0.003011989640071988
2023-01-23 03:12:37.685652: step: 944/533, loss: 0.0037488937377929688
2023-01-23 03:12:38.849739: step: 948/533, loss: 0.033568382263183594
2023-01-23 03:12:40.043777: step: 952/533, loss: 1.316070574830519e-05
2023-01-23 03:12:41.189277: step: 956/533, loss: 0.012466716580092907
2023-01-23 03:12:42.426156: step: 960/533, loss: 0.009816360659897327
2023-01-23 03:12:43.581690: step: 964/533, loss: 8.535385131835938e-05
2023-01-23 03:12:44.765724: step: 968/533, loss: 2.0027162008773303e-06
2023-01-23 03:12:45.954434: step: 972/533, loss: 0.0032600401900708675
2023-01-23 03:12:47.105622: step: 976/533, loss: 0.02121276967227459
2023-01-23 03:12:48.270385: step: 980/533, loss: 0.0603116974234581
2023-01-23 03:12:49.425612: step: 984/533, loss: 0.0004171371692791581
2023-01-23 03:12:50.581690: step: 988/533, loss: 5.722047262679553e-07
2023-01-23 03:12:51.751839: step: 992/533, loss: 0.0035126686561852694
2023-01-23 03:12:52.903900: step: 996/533, loss: 0.0013684272998943925
2023-01-23 03:12:54.066765: step: 1000/533, loss: 0.0013780593872070312
2023-01-23 03:12:55.211219: step: 1004/533, loss: 1.4209747860149946e-05
2023-01-23 03:12:56.360582: step: 1008/533, loss: 0.006527316756546497
2023-01-23 03:12:57.538231: step: 1012/533, loss: 0.02345886267721653
2023-01-23 03:12:58.695647: step: 1016/533, loss: 0.02124919928610325
2023-01-23 03:12:59.863843: step: 1020/533, loss: 0.010608386248350143
2023-01-23 03:13:01.139110: step: 1024/533, loss: 0.16931067407131195
2023-01-23 03:13:02.352659: step: 1028/533, loss: 0.0012843131553381681
2023-01-23 03:13:03.565543: step: 1032/533, loss: 0.0008766175014898181
2023-01-23 03:13:04.752396: step: 1036/533, loss: 0.007630157750099897
2023-01-23 03:13:05.881298: step: 1040/533, loss: 0.00045099260751158
2023-01-23 03:13:07.013801: step: 1044/533, loss: 0.0005715370643883944
2023-01-23 03:13:08.172085: step: 1048/533, loss: 0.024192430078983307
2023-01-23 03:13:09.322262: step: 1052/533, loss: 0.000790500664152205
2023-01-23 03:13:10.518276: step: 1056/533, loss: 0.0063911438919603825
2023-01-23 03:13:11.697252: step: 1060/533, loss: 0.00025405886117368937
2023-01-23 03:13:12.869930: step: 1064/533, loss: 0.06196136772632599
2023-01-23 03:13:14.059990: step: 1068/533, loss: 0.000476837158203125
2023-01-23 03:13:15.251440: step: 1072/533, loss: 0.013082504272460938
2023-01-23 03:13:16.466541: step: 1076/533, loss: 0.0014033317565917969
2023-01-23 03:13:17.645840: step: 1080/533, loss: 0.000850677490234375
2023-01-23 03:13:18.786907: step: 1084/533, loss: 0.0023277283180505037
2023-01-23 03:13:19.977064: step: 1088/533, loss: 0.004790782928466797
2023-01-23 03:13:21.157995: step: 1092/533, loss: 0.0006177902687340975
2023-01-23 03:13:22.383789: step: 1096/533, loss: 0.08150079846382141
2023-01-23 03:13:23.579196: step: 1100/533, loss: 0.006209183018654585
2023-01-23 03:13:24.732866: step: 1104/533, loss: 0.005821609403938055
2023-01-23 03:13:25.895537: step: 1108/533, loss: 0.00037744047585874796
2023-01-23 03:13:27.090290: step: 1112/533, loss: 0.021162033081054688
2023-01-23 03:13:28.234813: step: 1116/533, loss: 0.03668374940752983
2023-01-23 03:13:29.409508: step: 1120/533, loss: 0.018657110631465912
2023-01-23 03:13:30.561652: step: 1124/533, loss: 0.05146846920251846
2023-01-23 03:13:31.794350: step: 1128/533, loss: 0.0019295692909508944
2023-01-23 03:13:32.999762: step: 1132/533, loss: 0.026489736512303352
2023-01-23 03:13:34.211545: step: 1136/533, loss: 0.018149565905332565
2023-01-23 03:13:35.382972: step: 1140/533, loss: 0.007332992274314165
2023-01-23 03:13:36.595775: step: 1144/533, loss: 0.09552960097789764
2023-01-23 03:13:37.756442: step: 1148/533, loss: 0.002246379852294922
2023-01-23 03:13:39.021745: step: 1152/533, loss: 0.021952057257294655
2023-01-23 03:13:40.180170: step: 1156/533, loss: 0.0018913268577307463
2023-01-23 03:13:41.354017: step: 1160/533, loss: 0.0004182815901003778
2023-01-23 03:13:42.554249: step: 1164/533, loss: 0.006509971804916859
2023-01-23 03:13:43.726449: step: 1168/533, loss: 0.04781994968652725
2023-01-23 03:13:44.928598: step: 1172/533, loss: 0.00017130374908447266
2023-01-23 03:13:46.163119: step: 1176/533, loss: 0.18276672065258026
2023-01-23 03:13:47.323029: step: 1180/533, loss: 0.03608705848455429
2023-01-23 03:13:48.560222: step: 1184/533, loss: 0.0004178047238383442
2023-01-23 03:13:49.751442: step: 1188/533, loss: 0.001820898149162531
2023-01-23 03:13:50.900418: step: 1192/533, loss: 0.00043807030306197703
2023-01-23 03:13:52.083099: step: 1196/533, loss: 0.0058074952103197575
2023-01-23 03:13:53.282669: step: 1200/533, loss: 6.723403657815652e-06
2023-01-23 03:13:54.444601: step: 1204/533, loss: 0.004756308160722256
2023-01-23 03:13:55.625918: step: 1208/533, loss: 0.034429457038640976
2023-01-23 03:13:56.822145: step: 1212/533, loss: 0.0032428978011012077
2023-01-23 03:13:57.991880: step: 1216/533, loss: 0.014985943213105202
2023-01-23 03:13:59.141140: step: 1220/533, loss: 0.0006476640701293945
2023-01-23 03:14:00.300709: step: 1224/533, loss: 0.00029773713322356343
2023-01-23 03:14:01.487294: step: 1228/533, loss: 0.030493546277284622
2023-01-23 03:14:02.711535: step: 1232/533, loss: 0.007457160856574774
2023-01-23 03:14:03.893929: step: 1236/533, loss: 0.012656117789447308
2023-01-23 03:14:05.076486: step: 1240/533, loss: 0.014214038848876953
2023-01-23 03:14:06.285489: step: 1244/533, loss: 0.016066743060946465
2023-01-23 03:14:07.436545: step: 1248/533, loss: 0.007273959927260876
2023-01-23 03:14:08.597977: step: 1252/533, loss: 9.613037400413305e-05
2023-01-23 03:14:09.780844: step: 1256/533, loss: 4.9591064453125e-05
2023-01-23 03:14:10.959147: step: 1260/533, loss: 2.841949390131049e-05
2023-01-23 03:14:12.153875: step: 1264/533, loss: 0.15430641174316406
2023-01-23 03:14:13.301079: step: 1268/533, loss: 0.0002168655482819304
2023-01-23 03:14:14.497939: step: 1272/533, loss: 0.00010948181443382055
2023-01-23 03:14:15.676390: step: 1276/533, loss: 2.4700166250113398e-05
2023-01-23 03:14:16.882108: step: 1280/533, loss: 0.20417319238185883
2023-01-23 03:14:18.058091: step: 1284/533, loss: 0.013249779120087624
2023-01-23 03:14:19.212288: step: 1288/533, loss: 0.007322215940803289
2023-01-23 03:14:20.391744: step: 1292/533, loss: 0.00030851367046125233
2023-01-23 03:14:21.582214: step: 1296/533, loss: 0.027322864159941673
2023-01-23 03:14:22.809440: step: 1300/533, loss: 0.0010341644519940019
2023-01-23 03:14:23.982806: step: 1304/533, loss: 0.00280342111364007
2023-01-23 03:14:25.144861: step: 1308/533, loss: 0.0010660648113116622
2023-01-23 03:14:26.324901: step: 1312/533, loss: 0.00029616354731842875
2023-01-23 03:14:27.531008: step: 1316/533, loss: 0.02420072630047798
2023-01-23 03:14:28.740174: step: 1320/533, loss: 0.22925511002540588
2023-01-23 03:14:29.936921: step: 1324/533, loss: 0.003690481185913086
2023-01-23 03:14:31.210726: step: 1328/533, loss: 0.004816913977265358
2023-01-23 03:14:32.364713: step: 1332/533, loss: 0.0010329962242394686
2023-01-23 03:14:33.529268: step: 1336/533, loss: 0.02021799236536026
2023-01-23 03:14:34.742848: step: 1340/533, loss: 0.01763634756207466
2023-01-23 03:14:35.865185: step: 1344/533, loss: 7.019043550826609e-05
2023-01-23 03:14:37.000140: step: 1348/533, loss: 0.0015884400345385075
2023-01-23 03:14:38.191690: step: 1352/533, loss: 0.031409457325935364
2023-01-23 03:14:39.388929: step: 1356/533, loss: 0.23956279456615448
2023-01-23 03:14:40.555810: step: 1360/533, loss: 0.007388305850327015
2023-01-23 03:14:41.685514: step: 1364/533, loss: 0.01363153476268053
2023-01-23 03:14:42.846218: step: 1368/533, loss: 0.06320323795080185
2023-01-23 03:14:44.017108: step: 1372/533, loss: 0.011235857382416725
2023-01-23 03:14:45.186767: step: 1376/533, loss: 0.0015499591827392578
2023-01-23 03:14:46.368311: step: 1380/533, loss: 0.039724256843328476
2023-01-23 03:14:47.562626: step: 1384/533, loss: 0.021163273602724075
2023-01-23 03:14:48.750953: step: 1388/533, loss: 0.0013381005264818668
2023-01-23 03:14:49.907036: step: 1392/533, loss: 0.05538537725806236
2023-01-23 03:14:51.077295: step: 1396/533, loss: 0.00010185241262661293
2023-01-23 03:14:52.236559: step: 1400/533, loss: 0.00037603380042128265
2023-01-23 03:14:53.417447: step: 1404/533, loss: -4.482269105210435e-06
2023-01-23 03:14:54.562120: step: 1408/533, loss: 0.0010151863098144531
2023-01-23 03:14:55.724698: step: 1412/533, loss: 0.0003846168692689389
2023-01-23 03:14:56.890501: step: 1416/533, loss: 0.00011072755296481773
2023-01-23 03:14:58.062350: step: 1420/533, loss: 0.0009510040399618447
2023-01-23 03:14:59.280331: step: 1424/533, loss: 0.01688366010785103
2023-01-23 03:15:00.436708: step: 1428/533, loss: 0.03987493738532066
2023-01-23 03:15:01.599574: step: 1432/533, loss: 0.009581565856933594
2023-01-23 03:15:02.824496: step: 1436/533, loss: 0.013789081946015358
2023-01-23 03:15:04.019905: step: 1440/533, loss: 0.021574975922703743
2023-01-23 03:15:05.178692: step: 1444/533, loss: 6.942749314475805e-05
2023-01-23 03:15:06.344636: step: 1448/533, loss: 0.0017833709716796875
2023-01-23 03:15:07.525568: step: 1452/533, loss: 7.25746140233241e-05
2023-01-23 03:15:08.714340: step: 1456/533, loss: 3.62396240234375e-05
2023-01-23 03:15:09.907396: step: 1460/533, loss: 0.012083339504897594
2023-01-23 03:15:11.073981: step: 1464/533, loss: 0.014619636349380016
2023-01-23 03:15:12.278284: step: 1468/533, loss: 0.0023204803001135588
2023-01-23 03:15:13.439696: step: 1472/533, loss: 0.005540370941162109
2023-01-23 03:15:14.634148: step: 1476/533, loss: 0.040253639221191406
2023-01-23 03:15:15.771200: step: 1480/533, loss: 0.08708486706018448
2023-01-23 03:15:16.967805: step: 1484/533, loss: 0.02092895470559597
2023-01-23 03:15:18.131647: step: 1488/533, loss: 8.125304884742945e-05
2023-01-23 03:15:19.320141: step: 1492/533, loss: 0.00382823939435184
2023-01-23 03:15:20.508497: step: 1496/533, loss: 0.03235873952507973
2023-01-23 03:15:21.722705: step: 1500/533, loss: 0.03460102155804634
2023-01-23 03:15:22.867363: step: 1504/533, loss: 0.01672344282269478
2023-01-23 03:15:24.034941: step: 1508/533, loss: 0.0007333874818868935
2023-01-23 03:15:25.217209: step: 1512/533, loss: 0.14904403686523438
2023-01-23 03:15:26.393435: step: 1516/533, loss: 0.0004961013910360634
2023-01-23 03:15:27.568123: step: 1520/533, loss: 0.06422577053308487
2023-01-23 03:15:28.729221: step: 1524/533, loss: 0.003205871442332864
2023-01-23 03:15:29.963390: step: 1528/533, loss: 0.0173205379396677
2023-01-23 03:15:31.119526: step: 1532/533, loss: 0.01211938913911581
2023-01-23 03:15:32.308785: step: 1536/533, loss: 0.0001068115234375
2023-01-23 03:15:33.483854: step: 1540/533, loss: 0.004449176602065563
2023-01-23 03:15:34.656692: step: 1544/533, loss: 0.011485290713608265
2023-01-23 03:15:35.786378: step: 1548/533, loss: 0.007732868194580078
2023-01-23 03:15:36.947045: step: 1552/533, loss: 5.795508695882745e-05
2023-01-23 03:15:38.101159: step: 1556/533, loss: 0.0039581297896802425
2023-01-23 03:15:39.263037: step: 1560/533, loss: 0.0801682397723198
2023-01-23 03:15:40.446983: step: 1564/533, loss: 0.0008066177251748741
2023-01-23 03:15:41.594368: step: 1568/533, loss: 0.00022730827913619578
2023-01-23 03:15:42.744402: step: 1572/533, loss: 0.009067249484360218
2023-01-23 03:15:43.904649: step: 1576/533, loss: 0.014584064483642578
2023-01-23 03:15:45.084825: step: 1580/533, loss: 0.21547985076904297
2023-01-23 03:15:46.237523: step: 1584/533, loss: 0.007395362947136164
2023-01-23 03:15:47.381459: step: 1588/533, loss: 0.003168773604556918
2023-01-23 03:15:48.523149: step: 1592/533, loss: 0.005688357166945934
2023-01-23 03:15:49.719419: step: 1596/533, loss: 0.0075018880888819695
2023-01-23 03:15:50.901738: step: 1600/533, loss: 0.002256202744320035
2023-01-23 03:15:52.061802: step: 1604/533, loss: 0.005157852079719305
2023-01-23 03:15:53.236640: step: 1608/533, loss: 0.03178606182336807
2023-01-23 03:15:54.377640: step: 1612/533, loss: 0.06984749436378479
2023-01-23 03:15:55.548409: step: 1616/533, loss: 0.006915188394486904
2023-01-23 03:15:56.738740: step: 1620/533, loss: 0.006665086839348078
2023-01-23 03:15:57.880919: step: 1624/533, loss: 0.004380130674690008
2023-01-23 03:15:59.080409: step: 1628/533, loss: 0.0045452117919921875
2023-01-23 03:16:00.224950: step: 1632/533, loss: 8.869171142578125e-05
2023-01-23 03:16:01.380815: step: 1636/533, loss: 0.020156098529696465
2023-01-23 03:16:02.582194: step: 1640/533, loss: 7.214546349132434e-05
2023-01-23 03:16:03.710558: step: 1644/533, loss: 0.0008726119995117188
2023-01-23 03:16:04.875639: step: 1648/533, loss: 0.0004152298206463456
2023-01-23 03:16:06.019974: step: 1652/533, loss: 0.0005063056596554816
2023-01-23 03:16:07.186018: step: 1656/533, loss: 0.0020912170875817537
2023-01-23 03:16:08.360050: step: 1660/533, loss: 0.005460834596306086
2023-01-23 03:16:09.585138: step: 1664/533, loss: 0.000476837158203125
2023-01-23 03:16:10.722729: step: 1668/533, loss: 0.006083107087761164
2023-01-23 03:16:11.933716: step: 1672/533, loss: 0.0004906654357910156
2023-01-23 03:16:13.120117: step: 1676/533, loss: 0.054097943007946014
2023-01-23 03:16:14.295565: step: 1680/533, loss: 0.0013564825057983398
2023-01-23 03:16:15.442876: step: 1684/533, loss: 0.033176470547914505
2023-01-23 03:16:16.573492: step: 1688/533, loss: 0.0036859512329101562
2023-01-23 03:16:17.730485: step: 1692/533, loss: 0.0007610321044921875
2023-01-23 03:16:18.950467: step: 1696/533, loss: 0.14615498483181
2023-01-23 03:16:20.148939: step: 1700/533, loss: 0.007613563910126686
2023-01-23 03:16:21.295249: step: 1704/533, loss: 0.00026841164799407125
2023-01-23 03:16:22.444369: step: 1708/533, loss: 0.002239227294921875
2023-01-23 03:16:23.657803: step: 1712/533, loss: 0.055242352187633514
2023-01-23 03:16:24.879395: step: 1716/533, loss: 0.02281207963824272
2023-01-23 03:16:26.071396: step: 1720/533, loss: 3.857910633087158e-05
2023-01-23 03:16:27.248658: step: 1724/533, loss: 0.004992103669792414
2023-01-23 03:16:28.426623: step: 1728/533, loss: 5.826949927723035e-05
2023-01-23 03:16:29.576062: step: 1732/533, loss: 0.0025222108233720064
2023-01-23 03:16:30.715690: step: 1736/533, loss: 0.0007436752784997225
2023-01-23 03:16:31.881474: step: 1740/533, loss: 0.001551818917505443
2023-01-23 03:16:33.078775: step: 1744/533, loss: 0.0027424811851233244
2023-01-23 03:16:34.242449: step: 1748/533, loss: 0.01200180035084486
2023-01-23 03:16:35.396921: step: 1752/533, loss: 0.00654869107529521
2023-01-23 03:16:36.580727: step: 1756/533, loss: 0.12989655137062073
2023-01-23 03:16:37.722291: step: 1760/533, loss: 0.021578121930360794
2023-01-23 03:16:38.937101: step: 1764/533, loss: 0.005482363980263472
2023-01-23 03:16:40.136118: step: 1768/533, loss: 0.14501523971557617
2023-01-23 03:16:41.311302: step: 1772/533, loss: 0.006252766121178865
2023-01-23 03:16:42.484183: step: 1776/533, loss: 0.0041370391845703125
2023-01-23 03:16:43.656480: step: 1780/533, loss: 0.0011947632301598787
2023-01-23 03:16:44.796982: step: 1784/533, loss: 0.001958179520443082
2023-01-23 03:16:45.944319: step: 1788/533, loss: 0.0005060196272097528
2023-01-23 03:16:47.139396: step: 1792/533, loss: 0.027555085718631744
2023-01-23 03:16:48.307527: step: 1796/533, loss: 0.018183518201112747
2023-01-23 03:16:49.500012: step: 1800/533, loss: 0.004184532444924116
2023-01-23 03:16:50.654496: step: 1804/533, loss: 0.025298310443758965
2023-01-23 03:16:51.812173: step: 1808/533, loss: 0.01170425396412611
2023-01-23 03:16:52.950806: step: 1812/533, loss: 0.016721343621611595
2023-01-23 03:16:54.112312: step: 1816/533, loss: 0.0005083084106445312
2023-01-23 03:16:55.321324: step: 1820/533, loss: 0.031094741076231003
2023-01-23 03:16:56.478232: step: 1824/533, loss: 0.004650688264518976
2023-01-23 03:16:57.662248: step: 1828/533, loss: 0.0014319419860839844
2023-01-23 03:16:58.840445: step: 1832/533, loss: 0.0025077343452721834
2023-01-23 03:17:00.011695: step: 1836/533, loss: 0.0005243301275186241
2023-01-23 03:17:01.193288: step: 1840/533, loss: 0.0027610778342932463
2023-01-23 03:17:02.378192: step: 1844/533, loss: 0.00160560617223382
2023-01-23 03:17:03.556221: step: 1848/533, loss: 0.0021846771705895662
2023-01-23 03:17:04.719374: step: 1852/533, loss: 0.002509212587028742
2023-01-23 03:17:05.879427: step: 1856/533, loss: 0.0032723904587328434
2023-01-23 03:17:07.088227: step: 1860/533, loss: 0.00010719299461925402
2023-01-23 03:17:08.265076: step: 1864/533, loss: 0.001210975693538785
2023-01-23 03:17:09.399205: step: 1868/533, loss: 0.0691111609339714
2023-01-23 03:17:10.579791: step: 1872/533, loss: 0.0005935669178143144
2023-01-23 03:17:11.736764: step: 1876/533, loss: 0.011607361026108265
2023-01-23 03:17:12.936643: step: 1880/533, loss: 0.004014777950942516
2023-01-23 03:17:14.129871: step: 1884/533, loss: 0.0020259858574718237
2023-01-23 03:17:15.367172: step: 1888/533, loss: 3.33309180859942e-05
2023-01-23 03:17:16.538334: step: 1892/533, loss: 0.0012325287098065019
2023-01-23 03:17:17.721341: step: 1896/533, loss: 0.0015484809409826994
2023-01-23 03:17:18.880327: step: 1900/533, loss: 0.0038679123390465975
2023-01-23 03:17:20.045919: step: 1904/533, loss: 0.004544353578239679
2023-01-23 03:17:21.179676: step: 1908/533, loss: 0.0004002094210591167
2023-01-23 03:17:22.363273: step: 1912/533, loss: 0.013720226474106312
2023-01-23 03:17:23.560347: step: 1916/533, loss: 4.836684703826904
2023-01-23 03:17:24.765301: step: 1920/533, loss: 0.009340668097138405
2023-01-23 03:17:25.905686: step: 1924/533, loss: 0.0009104252094402909
2023-01-23 03:17:27.095075: step: 1928/533, loss: 0.00782699603587389
2023-01-23 03:17:28.272078: step: 1932/533, loss: 0.016136646270751953
2023-01-23 03:17:29.481586: step: 1936/533, loss: 0.01700305938720703
2023-01-23 03:17:30.691846: step: 1940/533, loss: 0.019713401794433594
2023-01-23 03:17:31.804121: step: 1944/533, loss: 0.010913277044892311
2023-01-23 03:17:32.972768: step: 1948/533, loss: 0.01380233746021986
2023-01-23 03:17:34.179393: step: 1952/533, loss: 0.015938568860292435
2023-01-23 03:17:35.362763: step: 1956/533, loss: 0.002467680023983121
2023-01-23 03:17:36.533842: step: 1960/533, loss: 0.00034103397047147155
2023-01-23 03:17:37.704404: step: 1964/533, loss: 0.0011853218311443925
2023-01-23 03:17:38.842432: step: 1968/533, loss: 4.148483185417717e-06
2023-01-23 03:17:39.979062: step: 1972/533, loss: 0.0076265339739620686
2023-01-23 03:17:41.122909: step: 1976/533, loss: 0.0030502318404614925
2023-01-23 03:17:42.363729: step: 1980/533, loss: 0.007844544015824795
2023-01-23 03:17:43.512465: step: 1984/533, loss: 0.007668781094253063
2023-01-23 03:17:44.678000: step: 1988/533, loss: 0.017430590465664864
2023-01-23 03:17:45.827336: step: 1992/533, loss: 0.0008695602300576866
2023-01-23 03:17:47.016318: step: 1996/533, loss: 0.0018198012840002775
2023-01-23 03:17:48.182998: step: 2000/533, loss: 0.031736090779304504
2023-01-23 03:17:49.323837: step: 2004/533, loss: 0.022118758410215378
2023-01-23 03:17:50.482706: step: 2008/533, loss: 0.0017561912536621094
2023-01-23 03:17:51.639855: step: 2012/533, loss: 0.0020606995094567537
2023-01-23 03:17:52.783159: step: 2016/533, loss: 0.0823429599404335
2023-01-23 03:17:53.923457: step: 2020/533, loss: 0.00012249946303199977
2023-01-23 03:17:55.116759: step: 2024/533, loss: 0.0686667189002037
2023-01-23 03:17:56.338838: step: 2028/533, loss: 0.00014419556828215718
2023-01-23 03:17:57.509963: step: 2032/533, loss: 0.005441809073090553
2023-01-23 03:17:58.665504: step: 2036/533, loss: 0.0034411430824548006
2023-01-23 03:17:59.839063: step: 2040/533, loss: 0.0027456283569335938
2023-01-23 03:18:01.025477: step: 2044/533, loss: 0.008579921908676624
2023-01-23 03:18:02.211505: step: 2048/533, loss: 0.0001771926908986643
2023-01-23 03:18:03.463805: step: 2052/533, loss: 0.11936378479003906
2023-01-23 03:18:04.642211: step: 2056/533, loss: 0.022103404626250267
2023-01-23 03:18:05.770215: step: 2060/533, loss: 0.04020385816693306
2023-01-23 03:18:06.931329: step: 2064/533, loss: 0.016656970605254173
2023-01-23 03:18:08.105996: step: 2068/533, loss: 0.03689517825841904
2023-01-23 03:18:09.296765: step: 2072/533, loss: 0.7788367867469788
2023-01-23 03:18:10.534260: step: 2076/533, loss: 0.010155201889574528
2023-01-23 03:18:11.725687: step: 2080/533, loss: 0.011760711669921875
2023-01-23 03:18:12.894636: step: 2084/533, loss: 0.011496353894472122
2023-01-23 03:18:14.081761: step: 2088/533, loss: 0.021622180938720703
2023-01-23 03:18:15.223762: step: 2092/533, loss: 0.0004516601620707661
2023-01-23 03:18:16.363900: step: 2096/533, loss: 0.0009643555385991931
2023-01-23 03:18:17.543701: step: 2100/533, loss: 0.5990684032440186
2023-01-23 03:18:18.735500: step: 2104/533, loss: 0.0037865638732910156
2023-01-23 03:18:19.890452: step: 2108/533, loss: 0.01347818411886692
2023-01-23 03:18:21.080725: step: 2112/533, loss: 0.0003016471746377647
2023-01-23 03:18:22.244489: step: 2116/533, loss: 0.1178341880440712
2023-01-23 03:18:23.417138: step: 2120/533, loss: 0.07783952355384827
2023-01-23 03:18:24.595495: step: 2124/533, loss: 0.001119422959163785
2023-01-23 03:18:25.757434: step: 2128/533, loss: 0.059322454035282135
2023-01-23 03:18:26.887745: step: 2132/533, loss: 0.005815315525978804
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.5891238670694864, 'r': 0.7789613848202397, 'f1': 0.6708715596330275}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6351626016260162, 'r': 0.7992327365728901, 'f1': 0.707814269535674}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.6, 'r': 0.8888888888888888, 'f1': 0.7164179104477612}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.55, 'r': 0.5238095238095238, 'f1': 0.5365853658536585}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.3953488372093023, 'r': 0.4722222222222222, 'f1': 0.43037974683544306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 21
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:19:08.010646: step: 4/533, loss: 0.0010752677917480469
2023-01-23 03:19:09.199560: step: 8/533, loss: 0.0005086899036541581
2023-01-23 03:19:10.357397: step: 12/533, loss: 0.05015525966882706
2023-01-23 03:19:11.554415: step: 16/533, loss: 0.0031757354736328125
2023-01-23 03:19:12.754248: step: 20/533, loss: 0.0002834320184774697
2023-01-23 03:19:13.930375: step: 24/533, loss: 0.009250640869140625
2023-01-23 03:19:15.117757: step: 28/533, loss: 0.00024132727412506938
2023-01-23 03:19:16.293730: step: 32/533, loss: 0.00344772357493639
2023-01-23 03:19:17.467181: step: 36/533, loss: 0.010338879190385342
2023-01-23 03:19:18.686145: step: 40/533, loss: 0.032149411737918854
2023-01-23 03:19:19.848316: step: 44/533, loss: 0.03542356938123703
2023-01-23 03:19:21.009390: step: 48/533, loss: 0.0007952690357342362
2023-01-23 03:19:22.194834: step: 52/533, loss: 0.0009147644159384072
2023-01-23 03:19:23.424273: step: 56/533, loss: 0.11987175792455673
2023-01-23 03:19:24.560592: step: 60/533, loss: 0.00032634736271575093
2023-01-23 03:19:25.721347: step: 64/533, loss: 0.0013103962410241365
2023-01-23 03:19:26.878152: step: 68/533, loss: 0.0482419990003109
2023-01-23 03:19:28.002086: step: 72/533, loss: 0.06710374355316162
2023-01-23 03:19:29.171147: step: 76/533, loss: 0.018765831366181374
2023-01-23 03:19:30.346430: step: 80/533, loss: 0.02208137698471546
2023-01-23 03:19:31.520401: step: 84/533, loss: 0.012534905225038528
2023-01-23 03:19:32.692431: step: 88/533, loss: 0.006365632638335228
2023-01-23 03:19:33.871495: step: 92/533, loss: 0.010386228561401367
2023-01-23 03:19:35.019669: step: 96/533, loss: 0.0027452469803392887
2023-01-23 03:19:36.181757: step: 100/533, loss: 0.08927460014820099
2023-01-23 03:19:37.365565: step: 104/533, loss: 0.015231896191835403
2023-01-23 03:19:38.549179: step: 108/533, loss: 0.011481285095214844
2023-01-23 03:19:39.728719: step: 112/533, loss: 0.0051631927490234375
2023-01-23 03:19:40.925221: step: 116/533, loss: 0.00141057965811342
2023-01-23 03:19:42.086388: step: 120/533, loss: 4.482269287109375e-05
2023-01-23 03:19:43.274801: step: 124/533, loss: 0.0001451492280466482
2023-01-23 03:19:44.456059: step: 128/533, loss: 0.0004528045828919858
2023-01-23 03:19:45.633491: step: 132/533, loss: 0.0026713372208178043
2023-01-23 03:19:46.803934: step: 136/533, loss: 0.006187820341438055
2023-01-23 03:19:48.008362: step: 140/533, loss: 9.72747802734375e-05
2023-01-23 03:19:49.181362: step: 144/533, loss: 0.03494882956147194
2023-01-23 03:19:50.354660: step: 148/533, loss: 0.010295105166733265
2023-01-23 03:19:51.511678: step: 152/533, loss: 0.00013155936903785914
2023-01-23 03:19:52.671716: step: 156/533, loss: 0.01892986334860325
2023-01-23 03:19:53.871530: step: 160/533, loss: 0.00103759765625
2023-01-23 03:19:55.038986: step: 164/533, loss: 0.003035259200260043
2023-01-23 03:19:56.200355: step: 168/533, loss: 0.005446529481559992
2023-01-23 03:19:57.369789: step: 172/533, loss: 0.0014709472889080644
2023-01-23 03:19:58.570057: step: 176/533, loss: 0.007541466038674116
2023-01-23 03:19:59.731354: step: 180/533, loss: 0.0003601074276957661
2023-01-23 03:20:00.886621: step: 184/533, loss: 0.0014446259010583162
2023-01-23 03:20:02.056456: step: 188/533, loss: 0.002903175540268421
2023-01-23 03:20:03.248757: step: 192/533, loss: 0.006575584877282381
2023-01-23 03:20:04.450232: step: 196/533, loss: 0.0003159523184876889
2023-01-23 03:20:05.637078: step: 200/533, loss: 0.0037467004731297493
2023-01-23 03:20:06.792850: step: 204/533, loss: 0.025455093011260033
2023-01-23 03:20:07.951566: step: 208/533, loss: 0.019953157752752304
2023-01-23 03:20:09.114374: step: 212/533, loss: 0.003736400743946433
2023-01-23 03:20:10.317927: step: 216/533, loss: 0.016729259863495827
2023-01-23 03:20:11.451581: step: 220/533, loss: 8.20159948489163e-06
2023-01-23 03:20:12.605215: step: 224/533, loss: 0.04910917207598686
2023-01-23 03:20:13.824955: step: 228/533, loss: 0.012179184705018997
2023-01-23 03:20:14.992926: step: 232/533, loss: 0.0005213737604208291
2023-01-23 03:20:16.154633: step: 236/533, loss: 0.01016860082745552
2023-01-23 03:20:17.323828: step: 240/533, loss: 0.0001675605890341103
2023-01-23 03:20:18.485527: step: 244/533, loss: 0.0002992630179505795
2023-01-23 03:20:19.665752: step: 248/533, loss: 0.011136901564896107
2023-01-23 03:20:20.833751: step: 252/533, loss: 1.9073486612342094e-07
2023-01-23 03:20:22.062927: step: 256/533, loss: 0.009944343939423561
2023-01-23 03:20:23.232920: step: 260/533, loss: 0.005520582664757967
2023-01-23 03:20:24.379704: step: 264/533, loss: 0.029515648260712624
2023-01-23 03:20:25.532724: step: 268/533, loss: 0.00013809204392600805
2023-01-23 03:20:26.716225: step: 272/533, loss: 0.007865333929657936
2023-01-23 03:20:27.912048: step: 276/533, loss: 0.0011631011730059981
2023-01-23 03:20:29.090057: step: 280/533, loss: 0.029093172401189804
2023-01-23 03:20:30.273205: step: 284/533, loss: 0.3226785659790039
2023-01-23 03:20:31.448729: step: 288/533, loss: 0.0004228592151775956
2023-01-23 03:20:32.684581: step: 292/533, loss: 0.019213486462831497
2023-01-23 03:20:33.894122: step: 296/533, loss: 0.014779663644731045
2023-01-23 03:20:35.082368: step: 300/533, loss: 0.008392905816435814
2023-01-23 03:20:36.272405: step: 304/533, loss: 0.015485906973481178
2023-01-23 03:20:37.465197: step: 308/533, loss: 0.00043864251347258687
2023-01-23 03:20:38.630494: step: 312/533, loss: 0.008238411508500576
2023-01-23 03:20:39.803524: step: 316/533, loss: 0.002128553343936801
2023-01-23 03:20:40.979386: step: 320/533, loss: 0.006801700685173273
2023-01-23 03:20:42.206414: step: 324/533, loss: 0.003962373826652765
2023-01-23 03:20:43.389440: step: 328/533, loss: 0.07114367187023163
2023-01-23 03:20:44.548222: step: 332/533, loss: 0.0028912543784826994
2023-01-23 03:20:45.709949: step: 336/533, loss: 0.000156402587890625
2023-01-23 03:20:46.881983: step: 340/533, loss: 0.05251359939575195
2023-01-23 03:20:48.072334: step: 344/533, loss: 0.0012472153175622225
2023-01-23 03:20:49.238463: step: 348/533, loss: 0.0014495849609375
2023-01-23 03:20:50.394142: step: 352/533, loss: 0.006665611173957586
2023-01-23 03:20:51.713828: step: 356/533, loss: 0.13494834303855896
2023-01-23 03:20:52.885283: step: 360/533, loss: 0.0005622864118777215
2023-01-23 03:20:54.042104: step: 364/533, loss: 0.05162405967712402
2023-01-23 03:20:55.185780: step: 368/533, loss: 0.01754598692059517
2023-01-23 03:20:56.384014: step: 372/533, loss: 0.003567266510799527
2023-01-23 03:20:57.584926: step: 376/533, loss: 2.250671423098538e-05
2023-01-23 03:20:58.805790: step: 380/533, loss: 0.0237839687615633
2023-01-23 03:21:00.006305: step: 384/533, loss: 0.009996986947953701
2023-01-23 03:21:01.146493: step: 388/533, loss: 0.0007330895168706775
2023-01-23 03:21:02.308022: step: 392/533, loss: 0.00145807268563658
2023-01-23 03:21:03.442006: step: 396/533, loss: 0.006991052534431219
2023-01-23 03:21:04.622248: step: 400/533, loss: 0.01845083199441433
2023-01-23 03:21:05.780443: step: 404/533, loss: 0.0005084990989416838
2023-01-23 03:21:06.928372: step: 408/533, loss: 0.054672908037900925
2023-01-23 03:21:08.084067: step: 412/533, loss: 0.001952362130396068
2023-01-23 03:21:09.253148: step: 416/533, loss: 0.00040774344233796
2023-01-23 03:21:10.421207: step: 420/533, loss: 0.004485798068344593
2023-01-23 03:21:11.605028: step: 424/533, loss: 0.0005653381813317537
2023-01-23 03:21:12.762058: step: 428/533, loss: 0.01516647357493639
2023-01-23 03:21:13.909866: step: 432/533, loss: 0.17142286896705627
2023-01-23 03:21:15.072062: step: 436/533, loss: 0.010178184136748314
2023-01-23 03:21:16.293680: step: 440/533, loss: 0.002794647356495261
2023-01-23 03:21:17.465543: step: 444/533, loss: 0.0011768341064453125
2023-01-23 03:21:18.653077: step: 448/533, loss: 6.28471389063634e-05
2023-01-23 03:21:19.828026: step: 452/533, loss: 0.0034820795990526676
2023-01-23 03:21:21.009468: step: 456/533, loss: 0.0008982181898318231
2023-01-23 03:21:22.179357: step: 460/533, loss: 0.00012836456880904734
2023-01-23 03:21:23.412053: step: 464/533, loss: 0.0581602118909359
2023-01-23 03:21:24.557069: step: 468/533, loss: 0.0005725860828533769
2023-01-23 03:21:25.719008: step: 472/533, loss: 0.0020710944663733244
2023-01-23 03:21:26.883348: step: 476/533, loss: 0.0005970954662188888
2023-01-23 03:21:28.029244: step: 480/533, loss: 0.0041342019103467464
2023-01-23 03:21:29.197672: step: 484/533, loss: 0.008154869079589844
2023-01-23 03:21:30.360014: step: 488/533, loss: 0.015286731533706188
2023-01-23 03:21:31.519140: step: 492/533, loss: 0.05025453865528107
2023-01-23 03:21:32.674542: step: 496/533, loss: 0.005192804615944624
2023-01-23 03:21:33.877361: step: 500/533, loss: 0.11076297610998154
2023-01-23 03:21:35.038697: step: 504/533, loss: 0.0039459229446947575
2023-01-23 03:21:36.261135: step: 508/533, loss: 0.02257680892944336
2023-01-23 03:21:37.458116: step: 512/533, loss: 0.07266369462013245
2023-01-23 03:21:38.622699: step: 516/533, loss: 0.02223796956241131
2023-01-23 03:21:39.805993: step: 520/533, loss: 0.014933967962861061
2023-01-23 03:21:41.036493: step: 524/533, loss: 0.0014959335094317794
2023-01-23 03:21:42.210584: step: 528/533, loss: 0.015108847990632057
2023-01-23 03:21:43.421596: step: 532/533, loss: 0.0011769295670092106
2023-01-23 03:21:44.591252: step: 536/533, loss: 0.00025663376436568797
2023-01-23 03:21:45.704690: step: 540/533, loss: 0.04293036460876465
2023-01-23 03:21:46.878962: step: 544/533, loss: 0.005969238467514515
2023-01-23 03:21:48.023034: step: 548/533, loss: 0.0011371612781658769
2023-01-23 03:21:49.177867: step: 552/533, loss: 0.0007307052728720009
2023-01-23 03:21:50.376888: step: 556/533, loss: 0.0010875702137127519
2023-01-23 03:21:51.506331: step: 560/533, loss: 1.0681153071345761e-05
2023-01-23 03:21:52.699150: step: 564/533, loss: 0.000659942626953125
2023-01-23 03:21:53.860013: step: 568/533, loss: 0.0009937286376953125
2023-01-23 03:21:55.033789: step: 572/533, loss: 0.10395746678113937
2023-01-23 03:21:56.186718: step: 576/533, loss: 0.015338420867919922
2023-01-23 03:21:57.340362: step: 580/533, loss: 0.0017696857685223222
2023-01-23 03:21:58.497838: step: 584/533, loss: 0.02059359662234783
2023-01-23 03:21:59.678081: step: 588/533, loss: 0.018854428082704544
2023-01-23 03:22:00.804375: step: 592/533, loss: 3.6716461181640625e-05
2023-01-23 03:22:02.033159: step: 596/533, loss: 0.003392982529476285
2023-01-23 03:22:03.224075: step: 600/533, loss: 9.851455979514867e-05
2023-01-23 03:22:04.410531: step: 604/533, loss: 0.026817036792635918
2023-01-23 03:22:05.605933: step: 608/533, loss: 0.028690434992313385
2023-01-23 03:22:06.802145: step: 612/533, loss: 0.01290206890553236
2023-01-23 03:22:07.970287: step: 616/533, loss: 0.004898834507912397
2023-01-23 03:22:09.134844: step: 620/533, loss: 0.012697410769760609
2023-01-23 03:22:10.304847: step: 624/533, loss: 0.03265371173620224
2023-01-23 03:22:11.459518: step: 628/533, loss: 0.24329720437526703
2023-01-23 03:22:12.645688: step: 632/533, loss: 0.007614231202751398
2023-01-23 03:22:13.786377: step: 636/533, loss: 0.005146980285644531
2023-01-23 03:22:14.939779: step: 640/533, loss: 0.00010375976853538305
2023-01-23 03:22:16.087707: step: 644/533, loss: 0.00281867990270257
2023-01-23 03:22:17.282966: step: 648/533, loss: 0.00011215210543014109
2023-01-23 03:22:18.435036: step: 652/533, loss: 0.02332477457821369
2023-01-23 03:22:19.649908: step: 656/533, loss: 0.008139610290527344
2023-01-23 03:22:20.867703: step: 660/533, loss: 0.04134407266974449
2023-01-23 03:22:22.080532: step: 664/533, loss: 0.0021888732444494963
2023-01-23 03:22:23.286325: step: 668/533, loss: 0.012498951517045498
2023-01-23 03:22:24.503321: step: 672/533, loss: 0.002067661378532648
2023-01-23 03:22:25.665848: step: 676/533, loss: 0.003961086273193359
2023-01-23 03:22:26.846784: step: 680/533, loss: 0.02997622638940811
2023-01-23 03:22:28.021334: step: 684/533, loss: -1.010894811770413e-05
2023-01-23 03:22:29.199663: step: 688/533, loss: 0.004114627838134766
2023-01-23 03:22:30.356452: step: 692/533, loss: 0.006018257234245539
2023-01-23 03:22:31.561588: step: 696/533, loss: 0.0013607025612145662
2023-01-23 03:22:32.744466: step: 700/533, loss: 0.0024507520720362663
2023-01-23 03:22:33.890786: step: 704/533, loss: 0.03011307679116726
2023-01-23 03:22:35.104743: step: 708/533, loss: 0.06468620151281357
2023-01-23 03:22:36.255780: step: 712/533, loss: 0.02297673374414444
2023-01-23 03:22:37.409903: step: 716/533, loss: 0.002057647565379739
2023-01-23 03:22:38.571471: step: 720/533, loss: 0.0001374244602629915
2023-01-23 03:22:39.764979: step: 724/533, loss: 0.0007652282947674394
2023-01-23 03:22:40.927693: step: 728/533, loss: 0.0020050047896802425
2023-01-23 03:22:42.122072: step: 732/533, loss: 0.08466528356075287
2023-01-23 03:22:43.295285: step: 736/533, loss: 0.0009654999012127519
2023-01-23 03:22:44.446116: step: 740/533, loss: 7.085800461936742e-05
2023-01-23 03:22:45.588826: step: 744/533, loss: 0.0028558732010424137
2023-01-23 03:22:46.740137: step: 748/533, loss: 0.0003326416190247983
2023-01-23 03:22:47.916368: step: 752/533, loss: 0.09139051288366318
2023-01-23 03:22:49.095756: step: 756/533, loss: 0.0011870384914800525
2023-01-23 03:22:50.303692: step: 760/533, loss: 0.0959661528468132
2023-01-23 03:22:51.470332: step: 764/533, loss: 0.0029108047019690275
2023-01-23 03:22:52.634322: step: 768/533, loss: 0.0015790463658049703
2023-01-23 03:22:53.847561: step: 772/533, loss: 0.012923812493681908
2023-01-23 03:22:54.998578: step: 776/533, loss: 0.022732067853212357
2023-01-23 03:22:56.157329: step: 780/533, loss: 0.0006853103986941278
2023-01-23 03:22:57.296395: step: 784/533, loss: 0.01432724017649889
2023-01-23 03:22:58.473316: step: 788/533, loss: 0.0016889573307707906
2023-01-23 03:22:59.693950: step: 792/533, loss: 0.00040435791015625
2023-01-23 03:23:00.847055: step: 796/533, loss: 0.010360385291278362
2023-01-23 03:23:01.982826: step: 800/533, loss: 4.091262962901965e-05
2023-01-23 03:23:03.203316: step: 804/533, loss: 0.005774307530373335
2023-01-23 03:23:04.381329: step: 808/533, loss: 0.005314636044204235
2023-01-23 03:23:05.611195: step: 812/533, loss: 0.022045612335205078
2023-01-23 03:23:06.782827: step: 816/533, loss: 0.0003689766163006425
2023-01-23 03:23:07.948250: step: 820/533, loss: 9.107589721679688e-05
2023-01-23 03:23:09.125961: step: 824/533, loss: 2.536773718020413e-05
2023-01-23 03:23:10.283399: step: 828/533, loss: 0.0548795685172081
2023-01-23 03:23:11.434214: step: 832/533, loss: 0.0016007423400878906
2023-01-23 03:23:12.605960: step: 836/533, loss: 0.005694914143532515
2023-01-23 03:23:13.841147: step: 840/533, loss: 0.04848938062787056
2023-01-23 03:23:15.035408: step: 844/533, loss: 0.00029430389986373484
2023-01-23 03:23:16.197632: step: 848/533, loss: 0.006320238579064608
2023-01-23 03:23:17.350394: step: 852/533, loss: 0.0019893646240234375
2023-01-23 03:23:18.570746: step: 856/533, loss: 0.059297751635313034
2023-01-23 03:23:19.727030: step: 860/533, loss: 0.0003581047058105469
2023-01-23 03:23:20.891535: step: 864/533, loss: 0.008666038513183594
2023-01-23 03:23:22.108119: step: 868/533, loss: 0.0025396347045898438
2023-01-23 03:23:23.281264: step: 872/533, loss: 0.000274658203125
2023-01-23 03:23:24.430634: step: 876/533, loss: 0.0016363144386559725
2023-01-23 03:23:25.612918: step: 880/533, loss: 0.03193187713623047
2023-01-23 03:23:26.775430: step: 884/533, loss: 0.1317039579153061
2023-01-23 03:23:27.932363: step: 888/533, loss: 0.05788488686084747
2023-01-23 03:23:29.133742: step: 892/533, loss: 0.019421959295868874
2023-01-23 03:23:30.327512: step: 896/533, loss: 0.0003930091916117817
2023-01-23 03:23:31.480996: step: 900/533, loss: 0.0020294189453125
2023-01-23 03:23:32.653497: step: 904/533, loss: 0.00029382703360170126
2023-01-23 03:23:33.854273: step: 908/533, loss: 0.026293182745575905
2023-01-23 03:23:35.014261: step: 912/533, loss: 0.007247066590934992
2023-01-23 03:23:36.222498: step: 916/533, loss: 0.028051234781742096
2023-01-23 03:23:37.402874: step: 920/533, loss: 0.00021848679170943797
2023-01-23 03:23:38.572606: step: 924/533, loss: 0.0006963253254070878
2023-01-23 03:23:39.768407: step: 928/533, loss: 0.002893638564273715
2023-01-23 03:23:40.924614: step: 932/533, loss: 0.0013071061111986637
2023-01-23 03:23:42.117594: step: 936/533, loss: 0.013422345742583275
2023-01-23 03:23:43.292073: step: 940/533, loss: 0.04858889803290367
2023-01-23 03:23:44.470094: step: 944/533, loss: 0.0016326905461028218
2023-01-23 03:23:45.611884: step: 948/533, loss: 3.24249276673072e-06
2023-01-23 03:23:46.867959: step: 952/533, loss: 0.0061667440459132195
2023-01-23 03:23:48.007427: step: 956/533, loss: 0.0009001732105389237
2023-01-23 03:23:49.192725: step: 960/533, loss: 0.014184570871293545
2023-01-23 03:23:50.372420: step: 964/533, loss: 0.001047372817993164
2023-01-23 03:23:51.542133: step: 968/533, loss: 0.01500549353659153
2023-01-23 03:23:52.709276: step: 972/533, loss: 0.005068588070571423
2023-01-23 03:23:53.899059: step: 976/533, loss: 0.11187916249036789
2023-01-23 03:23:55.092229: step: 980/533, loss: 0.00046386721078306437
2023-01-23 03:23:56.280760: step: 984/533, loss: 0.013736248016357422
2023-01-23 03:23:57.429229: step: 988/533, loss: 0.023029232397675514
2023-01-23 03:23:58.600325: step: 992/533, loss: 0.0005396843189373612
2023-01-23 03:23:59.748413: step: 996/533, loss: 0.0003070831298828125
2023-01-23 03:24:00.928426: step: 1000/533, loss: 0.014395141042768955
2023-01-23 03:24:02.136212: step: 1004/533, loss: 0.03348350524902344
2023-01-23 03:24:03.304617: step: 1008/533, loss: 3.32355521095451e-05
2023-01-23 03:24:04.484651: step: 1012/533, loss: 0.022552872076630592
2023-01-23 03:24:05.627659: step: 1016/533, loss: 0.0120690343901515
2023-01-23 03:24:06.771164: step: 1020/533, loss: 0.0007764816400595009
2023-01-23 03:24:07.984961: step: 1024/533, loss: 0.008112048730254173
2023-01-23 03:24:09.140303: step: 1028/533, loss: 0.009698200039565563
2023-01-23 03:24:10.306871: step: 1032/533, loss: 0.0020278929732739925
2023-01-23 03:24:11.447944: step: 1036/533, loss: 3.185272362316027e-05
2023-01-23 03:24:12.630563: step: 1040/533, loss: 0.00225658412091434
2023-01-23 03:24:13.847511: step: 1044/533, loss: 0.0024166107177734375
2023-01-23 03:24:15.015727: step: 1048/533, loss: 0.005865669809281826
2023-01-23 03:24:16.140236: step: 1052/533, loss: 0.00010905266390182078
2023-01-23 03:24:17.316011: step: 1056/533, loss: 0.0002785682736430317
2023-01-23 03:24:18.468026: step: 1060/533, loss: 0.005165576934814453
2023-01-23 03:24:19.669945: step: 1064/533, loss: 0.0017800331115722656
2023-01-23 03:24:20.836112: step: 1068/533, loss: 2.7179718017578125e-05
2023-01-23 03:24:22.019129: step: 1072/533, loss: 6.513595872092992e-05
2023-01-23 03:24:23.172513: step: 1076/533, loss: 0.0008892774349078536
2023-01-23 03:24:24.360302: step: 1080/533, loss: 0.013199138455092907
2023-01-23 03:24:25.566990: step: 1084/533, loss: 0.0036388395819813013
2023-01-23 03:24:26.721443: step: 1088/533, loss: 0.00034961701021529734
2023-01-23 03:24:27.882282: step: 1092/533, loss: 0.00227012624964118
2023-01-23 03:24:29.064823: step: 1096/533, loss: 0.004424476530402899
2023-01-23 03:24:30.302881: step: 1100/533, loss: 0.004406643100082874
2023-01-23 03:24:31.463862: step: 1104/533, loss: 0.009217835031449795
2023-01-23 03:24:32.638847: step: 1108/533, loss: 0.008301163092255592
2023-01-23 03:24:33.831990: step: 1112/533, loss: 2.9277802241267636e-05
2023-01-23 03:24:35.019972: step: 1116/533, loss: 0.020472336560487747
2023-01-23 03:24:36.191829: step: 1120/533, loss: 0.06597833335399628
2023-01-23 03:24:37.364434: step: 1124/533, loss: 0.05019645765423775
2023-01-23 03:24:38.553367: step: 1128/533, loss: 0.0011815071338787675
2023-01-23 03:24:39.730499: step: 1132/533, loss: 0.0002745628298725933
2023-01-23 03:24:40.884652: step: 1136/533, loss: 3.662109520519152e-05
2023-01-23 03:24:42.025021: step: 1140/533, loss: 0.000997686292976141
2023-01-23 03:24:43.211189: step: 1144/533, loss: 0.02737903781235218
2023-01-23 03:24:44.420245: step: 1148/533, loss: 1.640319896978326e-05
2023-01-23 03:24:45.616622: step: 1152/533, loss: 0.000651931797619909
2023-01-23 03:24:46.757518: step: 1156/533, loss: 0.000788784003816545
2023-01-23 03:24:48.003249: step: 1160/533, loss: 0.005009269807487726
2023-01-23 03:24:49.204418: step: 1164/533, loss: 0.010225200094282627
2023-01-23 03:24:50.433740: step: 1168/533, loss: 0.001161861466243863
2023-01-23 03:24:51.572154: step: 1172/533, loss: 0.00019083023653365672
2023-01-23 03:24:52.764184: step: 1176/533, loss: 0.03815264627337456
2023-01-23 03:24:53.971336: step: 1180/533, loss: 0.001218584249727428
2023-01-23 03:24:55.119035: step: 1184/533, loss: 0.00033731458825059235
2023-01-23 03:24:56.294976: step: 1188/533, loss: 0.0032871246803551912
2023-01-23 03:24:57.494976: step: 1192/533, loss: 0.002836036728695035
2023-01-23 03:24:58.674629: step: 1196/533, loss: 0.011802864260971546
2023-01-23 03:24:59.848771: step: 1200/533, loss: 0.0024247169494628906
2023-01-23 03:25:01.029189: step: 1204/533, loss: 0.02355041541159153
2023-01-23 03:25:02.206258: step: 1208/533, loss: 0.005244255065917969
2023-01-23 03:25:03.403114: step: 1212/533, loss: 0.04604225233197212
2023-01-23 03:25:04.563467: step: 1216/533, loss: 0.005480453372001648
2023-01-23 03:25:05.702092: step: 1220/533, loss: 0.054716113954782486
2023-01-23 03:25:06.842731: step: 1224/533, loss: 0.02812042087316513
2023-01-23 03:25:08.036956: step: 1228/533, loss: 0.03990650177001953
2023-01-23 03:25:09.195131: step: 1232/533, loss: 0.01297688577324152
2023-01-23 03:25:10.416836: step: 1236/533, loss: 0.0258147232234478
2023-01-23 03:25:11.602317: step: 1240/533, loss: 0.028432894498109818
2023-01-23 03:25:12.793483: step: 1244/533, loss: 0.010734654031693935
2023-01-23 03:25:13.941016: step: 1248/533, loss: 0.025060415267944336
2023-01-23 03:25:15.124644: step: 1252/533, loss: 0.044008638709783554
2023-01-23 03:25:16.289845: step: 1256/533, loss: 0.0012048721546307206
2023-01-23 03:25:17.501152: step: 1260/533, loss: 0.0008306503295898438
2023-01-23 03:25:18.694920: step: 1264/533, loss: 0.0081024169921875
2023-01-23 03:25:19.867335: step: 1268/533, loss: 0.058712102472782135
2023-01-23 03:25:21.075419: step: 1272/533, loss: 0.013739204034209251
2023-01-23 03:25:22.269904: step: 1276/533, loss: 0.0015888214111328125
2023-01-23 03:25:23.415421: step: 1280/533, loss: 0.13101644814014435
2023-01-23 03:25:24.617516: step: 1284/533, loss: 0.0021768570877611637
2023-01-23 03:25:25.782711: step: 1288/533, loss: 0.0010646821465343237
2023-01-23 03:25:26.943078: step: 1292/533, loss: 0.02703394927084446
2023-01-23 03:25:28.131662: step: 1296/533, loss: 0.005271339789032936
2023-01-23 03:25:29.331782: step: 1300/533, loss: 0.002501964569091797
2023-01-23 03:25:30.510395: step: 1304/533, loss: 0.013520240783691406
2023-01-23 03:25:31.686379: step: 1308/533, loss: 0.0021947859786450863
2023-01-23 03:25:32.857592: step: 1312/533, loss: 0.036550141870975494
2023-01-23 03:25:34.087711: step: 1316/533, loss: 0.0007497787592001259
2023-01-23 03:25:35.263407: step: 1320/533, loss: 0.0007326126797124743
2023-01-23 03:25:36.466407: step: 1324/533, loss: 0.06887874752283096
2023-01-23 03:25:37.627320: step: 1328/533, loss: 2.86102294921875e-05
2023-01-23 03:25:38.805320: step: 1332/533, loss: 0.0006643295055255294
2023-01-23 03:25:39.937436: step: 1336/533, loss: 0.00013718605623580515
2023-01-23 03:25:41.112171: step: 1340/533, loss: 0.04394559934735298
2023-01-23 03:25:42.261034: step: 1344/533, loss: 0.031722258776426315
2023-01-23 03:25:43.453018: step: 1348/533, loss: 0.0006387710454873741
2023-01-23 03:25:44.614419: step: 1352/533, loss: 0.005569267552345991
2023-01-23 03:25:45.808720: step: 1356/533, loss: 0.012485313229262829
2023-01-23 03:25:46.975103: step: 1360/533, loss: 0.0012495993869379163
2023-01-23 03:25:48.128512: step: 1364/533, loss: 0.0001277923583984375
2023-01-23 03:25:49.304462: step: 1368/533, loss: 0.003922081086784601
2023-01-23 03:25:50.498862: step: 1372/533, loss: 0.04140782356262207
2023-01-23 03:25:51.710992: step: 1376/533, loss: 6.046295311534777e-05
2023-01-23 03:25:52.894780: step: 1380/533, loss: 0.004292297642678022
2023-01-23 03:25:54.063301: step: 1384/533, loss: 5.826950291520916e-05
2023-01-23 03:25:55.286663: step: 1388/533, loss: 0.017092324793338776
2023-01-23 03:25:56.441769: step: 1392/533, loss: 0.002660989761352539
2023-01-23 03:25:57.576625: step: 1396/533, loss: 0.00088334089377895
2023-01-23 03:25:58.737301: step: 1400/533, loss: 1.2016297660011332e-05
2023-01-23 03:25:59.926368: step: 1404/533, loss: 0.0024902820587158203
2023-01-23 03:26:01.085969: step: 1408/533, loss: 0.003922462463378906
2023-01-23 03:26:02.276256: step: 1412/533, loss: 0.005764675326645374
2023-01-23 03:26:03.415033: step: 1416/533, loss: 0.004608058836311102
2023-01-23 03:26:04.621892: step: 1420/533, loss: 0.001043939497321844
2023-01-23 03:26:05.784685: step: 1424/533, loss: 0.028919031843543053
2023-01-23 03:26:06.966409: step: 1428/533, loss: 0.000705718994140625
2023-01-23 03:26:08.134183: step: 1432/533, loss: 0.011714077554643154
2023-01-23 03:26:09.333458: step: 1436/533, loss: 0.00036087038461118937
2023-01-23 03:26:10.491708: step: 1440/533, loss: -8.01086389401462e-06
2023-01-23 03:26:11.697981: step: 1444/533, loss: 1.5211106074275449e-05
2023-01-23 03:26:12.891226: step: 1448/533, loss: 0.00012025833711959422
2023-01-23 03:26:14.062313: step: 1452/533, loss: 0.00018367767916060984
2023-01-23 03:26:15.246200: step: 1456/533, loss: 0.00063581473659724
2023-01-23 03:26:16.415712: step: 1460/533, loss: 0.041513923555612564
2023-01-23 03:26:17.623764: step: 1464/533, loss: 0.007718944456428289
2023-01-23 03:26:18.828023: step: 1468/533, loss: 0.011109257116913795
2023-01-23 03:26:20.037082: step: 1472/533, loss: 0.037636902183294296
2023-01-23 03:26:21.227704: step: 1476/533, loss: 0.02476225048303604
2023-01-23 03:26:22.437592: step: 1480/533, loss: 0.00011863708641612902
2023-01-23 03:26:23.678287: step: 1484/533, loss: 0.00042591095552779734
2023-01-23 03:26:24.816612: step: 1488/533, loss: 0.011008739471435547
2023-01-23 03:26:25.999371: step: 1492/533, loss: 0.01116724032908678
2023-01-23 03:26:27.177969: step: 1496/533, loss: 2.593994213384576e-05
2023-01-23 03:26:28.322736: step: 1500/533, loss: 9.430646605324e-05
2023-01-23 03:26:29.550216: step: 1504/533, loss: 0.09664344787597656
2023-01-23 03:26:30.700874: step: 1508/533, loss: 0.033812522888183594
2023-01-23 03:26:31.911399: step: 1512/533, loss: 0.0002402305690338835
2023-01-23 03:26:33.074762: step: 1516/533, loss: 0.0005529880872927606
2023-01-23 03:26:34.206972: step: 1520/533, loss: 1.4829635802016128e-05
2023-01-23 03:26:35.360463: step: 1524/533, loss: 0.04460430145263672
2023-01-23 03:26:36.517251: step: 1528/533, loss: 0.003004360245540738
2023-01-23 03:26:37.697846: step: 1532/533, loss: 0.01606011390686035
2023-01-23 03:26:38.863693: step: 1536/533, loss: 0.012944984249770641
2023-01-23 03:26:40.012597: step: 1540/533, loss: 0.02269144169986248
2023-01-23 03:26:41.132411: step: 1544/533, loss: 0.03440279886126518
2023-01-23 03:26:42.317481: step: 1548/533, loss: 0.007594776339828968
2023-01-23 03:26:43.499099: step: 1552/533, loss: 0.013205528259277344
2023-01-23 03:26:44.642372: step: 1556/533, loss: 0.0015297889476642013
2023-01-23 03:26:45.796081: step: 1560/533, loss: 0.005613517481833696
2023-01-23 03:26:46.976329: step: 1564/533, loss: 0.00030956268892623484
2023-01-23 03:26:48.174405: step: 1568/533, loss: 0.004345702938735485
2023-01-23 03:26:49.379997: step: 1572/533, loss: 0.0006660461658611894
2023-01-23 03:26:50.562689: step: 1576/533, loss: 0.00014314652071334422
2023-01-23 03:26:51.719816: step: 1580/533, loss: 0.016733551397919655
2023-01-23 03:26:52.878820: step: 1584/533, loss: 0.00011148452904308215
2023-01-23 03:26:54.052106: step: 1588/533, loss: 8.0108642578125e-05
2023-01-23 03:26:55.239248: step: 1592/533, loss: 0.000789642333984375
2023-01-23 03:26:56.408966: step: 1596/533, loss: 0.0005065918085165322
2023-01-23 03:26:57.594373: step: 1600/533, loss: 0.004064703360199928
2023-01-23 03:26:58.747563: step: 1604/533, loss: 0.001863193465396762
2023-01-23 03:26:59.913985: step: 1608/533, loss: 0.0022901534102857113
2023-01-23 03:27:01.096530: step: 1612/533, loss: 0.0025522231590002775
2023-01-23 03:27:02.326308: step: 1616/533, loss: 0.005135727114975452
2023-01-23 03:27:03.474976: step: 1620/533, loss: 0.025900553911924362
2023-01-23 03:27:04.674277: step: 1624/533, loss: 0.0015659332275390625
2023-01-23 03:27:05.835484: step: 1628/533, loss: 0.00013856888108421117
2023-01-23 03:27:06.996615: step: 1632/533, loss: 0.008434295654296875
2023-01-23 03:27:08.165837: step: 1636/533, loss: 0.002241802401840687
2023-01-23 03:27:09.332438: step: 1640/533, loss: 4.00543194700731e-06
2023-01-23 03:27:10.487009: step: 1644/533, loss: 0.00035753249539993703
2023-01-23 03:27:11.655442: step: 1648/533, loss: 0.0006530284881591797
2023-01-23 03:27:12.844588: step: 1652/533, loss: 0.07139892876148224
2023-01-23 03:27:14.045580: step: 1656/533, loss: 2.021789623540826e-05
2023-01-23 03:27:15.236353: step: 1660/533, loss: 0.0004839897155761719
2023-01-23 03:27:16.355717: step: 1664/533, loss: 0.00011167526099598035
2023-01-23 03:27:17.524666: step: 1668/533, loss: 0.019932890310883522
2023-01-23 03:27:18.755193: step: 1672/533, loss: 0.0004402160702738911
2023-01-23 03:27:19.890517: step: 1676/533, loss: 0.0004188537714071572
2023-01-23 03:27:21.077531: step: 1680/533, loss: 1.106262243411038e-05
2023-01-23 03:27:22.215939: step: 1684/533, loss: 0.0006122589111328125
2023-01-23 03:27:23.400837: step: 1688/533, loss: 0.003991031553596258
2023-01-23 03:27:24.554427: step: 1692/533, loss: 0.002306175185367465
2023-01-23 03:27:25.706909: step: 1696/533, loss: 4.7874447773210704e-05
2023-01-23 03:27:26.848355: step: 1700/533, loss: 0.0022580146323889494
2023-01-23 03:27:28.030178: step: 1704/533, loss: 0.01635761186480522
2023-01-23 03:27:29.191124: step: 1708/533, loss: 2.622604552016128e-05
2023-01-23 03:27:30.343147: step: 1712/533, loss: 0.0005837440839968622
2023-01-23 03:27:31.540163: step: 1716/533, loss: -1.640319896978326e-05
2023-01-23 03:27:32.733142: step: 1720/533, loss: 0.00027065275935456157
2023-01-23 03:27:33.911539: step: 1724/533, loss: 0.00124950404278934
2023-01-23 03:27:35.085265: step: 1728/533, loss: 0.006613636389374733
2023-01-23 03:27:36.225188: step: 1732/533, loss: 0.0005489349132403731
2023-01-23 03:27:37.413946: step: 1736/533, loss: 0.00011410714068915695
2023-01-23 03:27:38.604045: step: 1740/533, loss: 0.02530527114868164
2023-01-23 03:27:39.771697: step: 1744/533, loss: 0.39516574144363403
2023-01-23 03:27:41.014498: step: 1748/533, loss: 0.03044586069881916
2023-01-23 03:27:42.188776: step: 1752/533, loss: 0.012116623111069202
2023-01-23 03:27:43.389759: step: 1756/533, loss: 0.026382064446806908
2023-01-23 03:27:44.560776: step: 1760/533, loss: 0.00031147003755904734
2023-01-23 03:27:45.720650: step: 1764/533, loss: 0.012786484323441982
2023-01-23 03:27:46.909580: step: 1768/533, loss: 0.00014591217041015625
2023-01-23 03:27:48.048444: step: 1772/533, loss: 0.002908134600147605
2023-01-23 03:27:49.210438: step: 1776/533, loss: 0.00021276474581100047
2023-01-23 03:27:50.349398: step: 1780/533, loss: 6.122589547885582e-05
2023-01-23 03:27:51.475577: step: 1784/533, loss: 5.354881432140246e-05
2023-01-23 03:27:52.696256: step: 1788/533, loss: 0.00426330603659153
2023-01-23 03:27:53.870581: step: 1792/533, loss: 0.003810405731201172
2023-01-23 03:27:55.020970: step: 1796/533, loss: 0.000842237495817244
2023-01-23 03:27:56.205511: step: 1800/533, loss: 0.0013736725086346269
2023-01-23 03:27:57.381323: step: 1804/533, loss: 0.05387058109045029
2023-01-23 03:27:58.545209: step: 1808/533, loss: 0.0006219864008016884
2023-01-23 03:27:59.701613: step: 1812/533, loss: 0.0009620666969567537
2023-01-23 03:28:00.869596: step: 1816/533, loss: 0.00445480365306139
2023-01-23 03:28:01.996908: step: 1820/533, loss: 8.230209641624242e-05
2023-01-23 03:28:03.169021: step: 1824/533, loss: 0.0006955146673135459
2023-01-23 03:28:04.327367: step: 1828/533, loss: 4.425048973644152e-05
2023-01-23 03:28:05.474486: step: 1832/533, loss: 5.1975250244140625e-05
2023-01-23 03:28:06.657146: step: 1836/533, loss: 0.0005017280345782638
2023-01-23 03:28:07.863052: step: 1840/533, loss: 0.00013079644122626632
2023-01-23 03:28:09.065576: step: 1844/533, loss: 0.007572496309876442
2023-01-23 03:28:10.234317: step: 1848/533, loss: 0.016297675669193268
2023-01-23 03:28:11.385388: step: 1852/533, loss: 0.004268741700798273
2023-01-23 03:28:12.530957: step: 1856/533, loss: 0.006599808111786842
2023-01-23 03:28:13.690646: step: 1860/533, loss: 0.16262473165988922
2023-01-23 03:28:14.848066: step: 1864/533, loss: 0.0015596390003338456
2023-01-23 03:28:16.013523: step: 1868/533, loss: 0.0005552291986532509
2023-01-23 03:28:17.213866: step: 1872/533, loss: 0.11578655987977982
2023-01-23 03:28:18.396870: step: 1876/533, loss: 0.029906749725341797
2023-01-23 03:28:19.550848: step: 1880/533, loss: 0.0011843681568279862
2023-01-23 03:28:20.707083: step: 1884/533, loss: 0.003837108612060547
2023-01-23 03:28:21.891982: step: 1888/533, loss: 0.0002840042288880795
2023-01-23 03:28:23.101791: step: 1892/533, loss: -4.959105353918858e-06
2023-01-23 03:28:24.260930: step: 1896/533, loss: 0.03408050537109375
2023-01-23 03:28:25.439217: step: 1900/533, loss: 0.007250118535012007
2023-01-23 03:28:26.608094: step: 1904/533, loss: 8.144378080032766e-05
2023-01-23 03:28:27.814468: step: 1908/533, loss: 0.01952528953552246
2023-01-23 03:28:29.008880: step: 1912/533, loss: 0.000389528286177665
2023-01-23 03:28:30.135888: step: 1916/533, loss: 6.880760338390246e-05
2023-01-23 03:28:31.301181: step: 1920/533, loss: 0.012068557552993298
2023-01-23 03:28:32.497563: step: 1924/533, loss: 0.00035943984403274953
2023-01-23 03:28:33.669614: step: 1928/533, loss: 0.0052436827681958675
2023-01-23 03:28:34.909644: step: 1932/533, loss: 0.007184791844338179
2023-01-23 03:28:36.102201: step: 1936/533, loss: 0.0014678954612463713
2023-01-23 03:28:37.244474: step: 1940/533, loss: 0.0016061782371252775
2023-01-23 03:28:38.429417: step: 1944/533, loss: 0.1350231170654297
2023-01-23 03:28:39.597112: step: 1948/533, loss: 0.02249317243695259
2023-01-23 03:28:40.782997: step: 1952/533, loss: 0.004653358366340399
2023-01-23 03:28:41.970892: step: 1956/533, loss: 0.016799213364720345
2023-01-23 03:28:43.155703: step: 1960/533, loss: 0.016709424555301666
2023-01-23 03:28:44.302108: step: 1964/533, loss: 0.07454991340637207
2023-01-23 03:28:45.462310: step: 1968/533, loss: 0.01202240027487278
2023-01-23 03:28:46.624654: step: 1972/533, loss: 0.0009447097545489669
2023-01-23 03:28:47.756928: step: 1976/533, loss: 0.0615813285112381
2023-01-23 03:28:48.961823: step: 1980/533, loss: 0.0004860878107137978
2023-01-23 03:28:50.137030: step: 1984/533, loss: 0.5839420557022095
2023-01-23 03:28:51.327611: step: 1988/533, loss: 0.0011266708606854081
2023-01-23 03:28:52.476272: step: 1992/533, loss: 0.05644693225622177
2023-01-23 03:28:53.627887: step: 1996/533, loss: 0.0016967772971838713
2023-01-23 03:28:54.847307: step: 2000/533, loss: 3.452301098150201e-05
2023-01-23 03:28:56.003328: step: 2004/533, loss: 0.009470843710005283
2023-01-23 03:28:57.138027: step: 2008/533, loss: 0.0005991458892822266
2023-01-23 03:28:58.296951: step: 2012/533, loss: 5.321502612787299e-05
2023-01-23 03:28:59.481515: step: 2016/533, loss: 5.3882604333921336e-06
2023-01-23 03:29:00.623493: step: 2020/533, loss: 0.001840782118961215
2023-01-23 03:29:01.768897: step: 2024/533, loss: 0.004614782519638538
2023-01-23 03:29:02.922065: step: 2028/533, loss: 2.7942656743107364e-05
2023-01-23 03:29:04.102295: step: 2032/533, loss: 0.004661274142563343
2023-01-23 03:29:05.293489: step: 2036/533, loss: 0.009046172723174095
2023-01-23 03:29:06.493908: step: 2040/533, loss: 0.0019807815551757812
2023-01-23 03:29:07.711514: step: 2044/533, loss: 0.037517644464969635
2023-01-23 03:29:08.900557: step: 2048/533, loss: 0.010144973173737526
2023-01-23 03:29:10.057143: step: 2052/533, loss: 0.3174971640110016
2023-01-23 03:29:11.228051: step: 2056/533, loss: 0.042220547795295715
2023-01-23 03:29:12.382497: step: 2060/533, loss: 6.141662743175402e-05
2023-01-23 03:29:13.543742: step: 2064/533, loss: 0.018467331305146217
2023-01-23 03:29:14.695076: step: 2068/533, loss: 0.0009114264976233244
2023-01-23 03:29:15.863794: step: 2072/533, loss: 0.02417278289794922
2023-01-23 03:29:17.058744: step: 2076/533, loss: 0.00592803955078125
2023-01-23 03:29:18.237256: step: 2080/533, loss: 0.003192997071892023
2023-01-23 03:29:19.432982: step: 2084/533, loss: 0.0006876945262774825
2023-01-23 03:29:20.581669: step: 2088/533, loss: 0.005936718080192804
2023-01-23 03:29:21.741912: step: 2092/533, loss: 0.010973739437758923
2023-01-23 03:29:22.918832: step: 2096/533, loss: 0.0002742767392192036
2023-01-23 03:29:24.086530: step: 2100/533, loss: 0.0765453353524208
2023-01-23 03:29:25.252378: step: 2104/533, loss: 0.08053645491600037
2023-01-23 03:29:26.421259: step: 2108/533, loss: 0.0009613991132937372
2023-01-23 03:29:27.606558: step: 2112/533, loss: 0.002557468367740512
2023-01-23 03:29:28.797403: step: 2116/533, loss: 0.00816116388887167
2023-01-23 03:29:29.945746: step: 2120/533, loss: 0.0049690245650708675
2023-01-23 03:29:31.108061: step: 2124/533, loss: 0.0006447792402468622
2023-01-23 03:29:32.283230: step: 2128/533, loss: 5.7220458984375e-06
2023-01-23 03:29:33.451061: step: 2132/533, loss: 4.725456528831273e-05
==================================================
Loss: 0.017
--------------------
Dev: {'event': {'p': 0.6135416666666667, 'r': 0.7842876165113183, 'f1': 0.6884862653419054}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6512583461736005, 'r': 0.8107416879795396, 'f1': 0.7223013386499573}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5542168674698795, 'r': 0.8518518518518519, 'f1': 0.6715328467153285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.6808510638297872, 'r': 0.5079365079365079, 'f1': 0.5818181818181817}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4864864864864865, 'r': 0.5, 'f1': 0.4931506849315069}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 22
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:30:14.132731: step: 4/533, loss: 4.6348573960131034e-05
2023-01-23 03:30:15.352455: step: 8/533, loss: 0.01979808881878853
2023-01-23 03:30:16.526682: step: 12/533, loss: 0.0006522178300656378
2023-01-23 03:30:17.678106: step: 16/533, loss: 0.0006101608159951866
2023-01-23 03:30:18.855770: step: 20/533, loss: 0.0013151168823242188
2023-01-23 03:30:20.044519: step: 24/533, loss: 1.3637542906508315e-05
2023-01-23 03:30:21.190586: step: 28/533, loss: 0.002569293836131692
2023-01-23 03:30:22.350382: step: 32/533, loss: 0.0043472289107739925
2023-01-23 03:30:23.572903: step: 36/533, loss: 0.0025729178451001644
2023-01-23 03:30:24.750886: step: 40/533, loss: 4.043579247081652e-05
2023-01-23 03:30:25.942899: step: 44/533, loss: 0.004203224554657936
2023-01-23 03:30:27.095533: step: 48/533, loss: 0.00024824144202284515
2023-01-23 03:30:28.242182: step: 52/533, loss: 3.814697265625e-05
2023-01-23 03:30:29.452932: step: 56/533, loss: 0.014941597357392311
2023-01-23 03:30:30.641673: step: 60/533, loss: 7.143020775401965e-05
2023-01-23 03:30:31.812763: step: 64/533, loss: 0.9156786203384399
2023-01-23 03:30:32.990939: step: 68/533, loss: 0.0006795883527956903
2023-01-23 03:30:34.170014: step: 72/533, loss: 0.003953456878662109
2023-01-23 03:30:35.339074: step: 76/533, loss: 0.01984882354736328
2023-01-23 03:30:36.470632: step: 80/533, loss: 2.47955313170678e-06
2023-01-23 03:30:37.686874: step: 84/533, loss: 0.0030334473121911287
2023-01-23 03:30:38.857359: step: 88/533, loss: 0.005707931704819202
2023-01-23 03:30:40.076132: step: 92/533, loss: 0.00021300316439010203
2023-01-23 03:30:41.198582: step: 96/533, loss: 6.270408630371094e-05
2023-01-23 03:30:42.317990: step: 100/533, loss: 0.05145569145679474
2023-01-23 03:30:43.512567: step: 104/533, loss: 0.007511043455451727
2023-01-23 03:30:44.665107: step: 108/533, loss: -4.19616708313697e-06
2023-01-23 03:30:45.829707: step: 112/533, loss: 3.62396240234375e-05
2023-01-23 03:30:46.963334: step: 116/533, loss: 0.0008966922760009766
2023-01-23 03:30:48.121946: step: 120/533, loss: 2.8610231765924254e-06
2023-01-23 03:30:49.329386: step: 124/533, loss: 0.02390899695456028
2023-01-23 03:30:50.510613: step: 128/533, loss: 0.07706312835216522
2023-01-23 03:30:51.656348: step: 132/533, loss: 1.7929078239831142e-05
2023-01-23 03:30:52.862138: step: 136/533, loss: 0.058489225804805756
2023-01-23 03:30:54.050798: step: 140/533, loss: 2.86102294921875e-06
2023-01-23 03:30:55.204366: step: 144/533, loss: 0.01895446702837944
2023-01-23 03:30:56.412244: step: 148/533, loss: 0.05796413496136665
2023-01-23 03:30:57.555107: step: 152/533, loss: 0.001422119210474193
2023-01-23 03:30:58.719929: step: 156/533, loss: 0.007993698120117188
2023-01-23 03:30:59.877339: step: 160/533, loss: 0.00015840530977584422
2023-01-23 03:31:01.019671: step: 164/533, loss: 0.0163726806640625
2023-01-23 03:31:02.176857: step: 168/533, loss: 0.004786300472915173
2023-01-23 03:31:03.327898: step: 172/533, loss: 0.012909699231386185
2023-01-23 03:31:04.536721: step: 176/533, loss: 0.0011219978332519531
2023-01-23 03:31:05.705647: step: 180/533, loss: 0.0015806198352947831
2023-01-23 03:31:06.896938: step: 184/533, loss: 4.3201445805607364e-05
2023-01-23 03:31:08.109930: step: 188/533, loss: 0.0008132934453897178
2023-01-23 03:31:09.251726: step: 192/533, loss: 5.53131121705519e-06
2023-01-23 03:31:10.465589: step: 196/533, loss: 0.00020055771165061742
2023-01-23 03:31:11.621842: step: 200/533, loss: 0.009841728955507278
2023-01-23 03:31:12.816044: step: 204/533, loss: 0.006096077151596546
2023-01-23 03:31:13.988400: step: 208/533, loss: 0.000798344612121582
2023-01-23 03:31:15.154641: step: 212/533, loss: 0.014163780957460403
2023-01-23 03:31:16.340934: step: 216/533, loss: 0.01322474516928196
2023-01-23 03:31:17.531796: step: 220/533, loss: 0.001019382500089705
2023-01-23 03:31:18.719535: step: 224/533, loss: 0.01369171217083931
2023-01-23 03:31:19.906026: step: 228/533, loss: 0.0028247833251953125
2023-01-23 03:31:21.103810: step: 232/533, loss: 0.0005532264476642013
2023-01-23 03:31:22.278909: step: 236/533, loss: 0.0021217346657067537
2023-01-23 03:31:23.417691: step: 240/533, loss: 0.0004964828258380294
2023-01-23 03:31:24.593388: step: 244/533, loss: 1.3065338862361386e-05
2023-01-23 03:31:25.747784: step: 248/533, loss: 0.01525197084993124
2023-01-23 03:31:26.906146: step: 252/533, loss: 0.0016655444633215666
2023-01-23 03:31:28.080004: step: 256/533, loss: 0.008540058508515358
2023-01-23 03:31:29.267119: step: 260/533, loss: 0.005357933230698109
2023-01-23 03:31:30.434600: step: 264/533, loss: 0.0001466751127736643
2023-01-23 03:31:31.612411: step: 268/533, loss: 0.040259361267089844
2023-01-23 03:31:32.767485: step: 272/533, loss: 0.0012897491687908769
2023-01-23 03:31:33.935365: step: 276/533, loss: 0.0006779670948162675
2023-01-23 03:31:35.091868: step: 280/533, loss: 0.0011564254527911544
2023-01-23 03:31:36.280629: step: 284/533, loss: 0.0009406090248376131
2023-01-23 03:31:37.436611: step: 288/533, loss: 6.198883056640625e-05
2023-01-23 03:31:38.693159: step: 292/533, loss: 0.001065158867277205
2023-01-23 03:31:39.882040: step: 296/533, loss: 6.64711042190902e-05
2023-01-23 03:31:41.009283: step: 300/533, loss: 0.003765964647755027
2023-01-23 03:31:42.197061: step: 304/533, loss: 0.03945455700159073
2023-01-23 03:31:43.396014: step: 308/533, loss: 0.0054145813919603825
2023-01-23 03:31:44.605264: step: 312/533, loss: 0.0028831481467932463
2023-01-23 03:31:45.781228: step: 316/533, loss: 0.00039892198401503265
2023-01-23 03:31:46.979624: step: 320/533, loss: 0.0007991790771484375
2023-01-23 03:31:48.169027: step: 324/533, loss: 0.035404156893491745
2023-01-23 03:31:49.356375: step: 328/533, loss: 0.0020177841652184725
2023-01-23 03:31:50.532683: step: 332/533, loss: 0.003953456878662109
2023-01-23 03:31:51.700063: step: 336/533, loss: 0.0003470420779194683
2023-01-23 03:31:52.886321: step: 340/533, loss: 0.00016918181790970266
2023-01-23 03:31:54.042382: step: 344/533, loss: 0.02539677731692791
2023-01-23 03:31:55.167213: step: 348/533, loss: 0.000522613525390625
2023-01-23 03:31:56.341935: step: 352/533, loss: 2.117157055181451e-05
2023-01-23 03:31:57.520061: step: 356/533, loss: 0.00034656524076126516
2023-01-23 03:31:58.687354: step: 360/533, loss: 0.04780769348144531
2023-01-23 03:31:59.872447: step: 364/533, loss: 9.5367431640625e-06
2023-01-23 03:32:01.014894: step: 368/533, loss: 0.0003541946643963456
2023-01-23 03:32:02.209000: step: 372/533, loss: 0.0038636208046227694
2023-01-23 03:32:03.399800: step: 376/533, loss: 0.010775757022202015
2023-01-23 03:32:04.564313: step: 380/533, loss: 0.007929230108857155
2023-01-23 03:32:05.734889: step: 384/533, loss: 0.0018610954284667969
2023-01-23 03:32:06.889499: step: 388/533, loss: -6.67572021484375e-06
2023-01-23 03:32:08.053828: step: 392/533, loss: 0.0009245872497558594
2023-01-23 03:32:09.226353: step: 396/533, loss: 0.0067008971236646175
2023-01-23 03:32:10.379239: step: 400/533, loss: 1.4781951449549524e-06
2023-01-23 03:32:11.589471: step: 404/533, loss: 0.0010811806423589587
2023-01-23 03:32:12.782121: step: 408/533, loss: 0.00144023890607059
2023-01-23 03:32:13.998962: step: 412/533, loss: 0.04804077371954918
2023-01-23 03:32:15.170169: step: 416/533, loss: 0.003083610674366355
2023-01-23 03:32:16.329952: step: 420/533, loss: 0.14540882408618927
2023-01-23 03:32:17.536695: step: 424/533, loss: 0.07040577381849289
2023-01-23 03:32:18.752523: step: 428/533, loss: 0.10770759731531143
2023-01-23 03:32:19.946074: step: 432/533, loss: 0.001545047853142023
2023-01-23 03:32:21.124093: step: 436/533, loss: 0.00029778480529785156
2023-01-23 03:32:22.285884: step: 440/533, loss: 0.0012248039711266756
2023-01-23 03:32:23.510910: step: 444/533, loss: 0.0018113135593011975
2023-01-23 03:32:24.685699: step: 448/533, loss: 0.0013878822792321444
2023-01-23 03:32:25.902777: step: 452/533, loss: 0.015762805938720703
2023-01-23 03:32:27.081290: step: 456/533, loss: 0.006797600071877241
2023-01-23 03:32:28.276600: step: 460/533, loss: 0.030245399102568626
2023-01-23 03:32:29.433997: step: 464/533, loss: 0.00077228550799191
2023-01-23 03:32:30.685175: step: 468/533, loss: 0.0056113312020897865
2023-01-23 03:32:31.821846: step: 472/533, loss: 0.06577315926551819
2023-01-23 03:32:32.970290: step: 476/533, loss: 7.305145118152723e-05
2023-01-23 03:32:34.112360: step: 480/533, loss: 0.043172646313905716
2023-01-23 03:32:35.297427: step: 484/533, loss: 0.003369951155036688
2023-01-23 03:32:36.488082: step: 488/533, loss: 1.889200210571289
2023-01-23 03:32:37.649948: step: 492/533, loss: 0.00013494491577148438
2023-01-23 03:32:38.852077: step: 496/533, loss: 0.03617754206061363
2023-01-23 03:32:40.057984: step: 500/533, loss: 0.002237987471744418
2023-01-23 03:32:41.256910: step: 504/533, loss: 0.009354686364531517
2023-01-23 03:32:42.389770: step: 508/533, loss: 0.04181298986077309
2023-01-23 03:32:43.568689: step: 512/533, loss: 0.09755564481019974
2023-01-23 03:32:44.768215: step: 516/533, loss: 0.016693497076630592
2023-01-23 03:32:45.936878: step: 520/533, loss: 0.006962776184082031
2023-01-23 03:32:47.132986: step: 524/533, loss: 0.0037490844260901213
2023-01-23 03:32:48.340462: step: 528/533, loss: 0.0029821395874023438
2023-01-23 03:32:49.541044: step: 532/533, loss: 0.0003068924124818295
2023-01-23 03:32:50.743466: step: 536/533, loss: 0.004728508181869984
2023-01-23 03:32:51.932863: step: 540/533, loss: 2.746581958490424e-05
2023-01-23 03:32:53.085897: step: 544/533, loss: 0.00024232864961959422
2023-01-23 03:32:54.243175: step: 548/533, loss: 0.00011367797560524195
2023-01-23 03:32:55.390266: step: 552/533, loss: 0.00011091232590842992
2023-01-23 03:32:56.594419: step: 556/533, loss: 0.006826496217399836
2023-01-23 03:32:57.769060: step: 560/533, loss: 0.034980013966560364
2023-01-23 03:32:58.965812: step: 564/533, loss: 0.022213172167539597
2023-01-23 03:33:00.142454: step: 568/533, loss: 0.02323455922305584
2023-01-23 03:33:01.341652: step: 572/533, loss: 2.1293745040893555
2023-01-23 03:33:02.494005: step: 576/533, loss: 0.005896091461181641
2023-01-23 03:33:03.656948: step: 580/533, loss: 0.002432918408885598
2023-01-23 03:33:04.810140: step: 584/533, loss: 0.0011341571807861328
2023-01-23 03:33:05.957163: step: 588/533, loss: 0.011813854798674583
2023-01-23 03:33:07.161691: step: 592/533, loss: 1.61647803906817e-05
2023-01-23 03:33:08.328684: step: 596/533, loss: 0.023606205359101295
2023-01-23 03:33:09.545248: step: 600/533, loss: 0.003218269208446145
2023-01-23 03:33:10.702642: step: 604/533, loss: 0.0007703781593590975
2023-01-23 03:33:11.917608: step: 608/533, loss: 0.036215901374816895
2023-01-23 03:33:13.084336: step: 612/533, loss: 0.9816697835922241
2023-01-23 03:33:14.228954: step: 616/533, loss: 0.0006397724500857294
2023-01-23 03:33:15.405023: step: 620/533, loss: 0.006338882725685835
2023-01-23 03:33:16.576872: step: 624/533, loss: 0.08328447490930557
2023-01-23 03:33:17.762972: step: 628/533, loss: 0.007692146580666304
2023-01-23 03:33:18.913404: step: 632/533, loss: 0.0005227089277468622
2023-01-23 03:33:20.090877: step: 636/533, loss: 6.50405854685232e-05
2023-01-23 03:33:21.270731: step: 640/533, loss: 0.00810155924409628
2023-01-23 03:33:22.463771: step: 644/533, loss: 0.04750204086303711
2023-01-23 03:33:23.616910: step: 648/533, loss: 0.0011665343772619963
2023-01-23 03:33:24.799788: step: 652/533, loss: 0.07217235863208771
2023-01-23 03:33:25.954498: step: 656/533, loss: 0.0003842354053631425
2023-01-23 03:33:27.132814: step: 660/533, loss: 0.0027728083077818155
2023-01-23 03:33:28.304114: step: 664/533, loss: 9.498596045887098e-05
2023-01-23 03:33:29.493154: step: 668/533, loss: 0.007309627719223499
2023-01-23 03:33:30.615002: step: 672/533, loss: 0.02184305153787136
2023-01-23 03:33:31.801241: step: 676/533, loss: 0.06633082032203674
2023-01-23 03:33:32.933072: step: 680/533, loss: 0.0002643585321493447
2023-01-23 03:33:34.122078: step: 684/533, loss: 0.0016119956271722913
2023-01-23 03:33:35.290526: step: 688/533, loss: 0.00028591154841706157
2023-01-23 03:33:36.459261: step: 692/533, loss: 0.021193992346525192
2023-01-23 03:33:37.598460: step: 696/533, loss: 0.0004324913024902344
2023-01-23 03:33:38.778499: step: 700/533, loss: 0.0001886367826955393
2023-01-23 03:33:39.983876: step: 704/533, loss: 0.015512657351791859
2023-01-23 03:33:41.182006: step: 708/533, loss: 0.5523599982261658
2023-01-23 03:33:42.330225: step: 712/533, loss: 0.0019481659401208162
2023-01-23 03:33:43.480755: step: 716/533, loss: 0.014204693026840687
2023-01-23 03:33:44.673537: step: 720/533, loss: 0.001001644181087613
2023-01-23 03:33:45.842748: step: 724/533, loss: 0.00131902692373842
2023-01-23 03:33:46.998065: step: 728/533, loss: 0.012248230166733265
2023-01-23 03:33:48.158659: step: 732/533, loss: 0.022366046905517578
2023-01-23 03:33:49.325588: step: 736/533, loss: 0.0021962167229503393
2023-01-23 03:33:50.475432: step: 740/533, loss: 2.346038854739163e-05
2023-01-23 03:33:51.643643: step: 744/533, loss: 0.0032279968727380037
2023-01-23 03:33:52.770484: step: 748/533, loss: 6.189346458995715e-05
2023-01-23 03:33:53.967281: step: 752/533, loss: 0.0012270926963537931
2023-01-23 03:33:55.166836: step: 756/533, loss: 0.040390968322753906
2023-01-23 03:33:56.359129: step: 760/533, loss: 0.006791782099753618
2023-01-23 03:33:57.493404: step: 764/533, loss: -3.24249276673072e-06
2023-01-23 03:33:58.688522: step: 768/533, loss: 0.04647274315357208
2023-01-23 03:33:59.859281: step: 772/533, loss: 0.014141177758574486
2023-01-23 03:34:01.039565: step: 776/533, loss: 6.67572021484375e-05
2023-01-23 03:34:02.218638: step: 780/533, loss: 0.03485088422894478
2023-01-23 03:34:03.383090: step: 784/533, loss: 0.0005096435779705644
2023-01-23 03:34:04.568388: step: 788/533, loss: 0.027565479278564453
2023-01-23 03:34:05.767916: step: 792/533, loss: 0.08724422752857208
2023-01-23 03:34:06.911761: step: 796/533, loss: 0.006330347154289484
2023-01-23 03:34:08.074738: step: 800/533, loss: 0.05926513671875
2023-01-23 03:34:09.285967: step: 804/533, loss: 0.0013380051823332906
2023-01-23 03:34:10.473810: step: 808/533, loss: 0.029644252732396126
2023-01-23 03:34:11.634165: step: 812/533, loss: 0.013859033584594727
2023-01-23 03:34:12.828383: step: 816/533, loss: 0.0990932434797287
2023-01-23 03:34:13.966985: step: 820/533, loss: 0.0036014558281749487
2023-01-23 03:34:15.161064: step: 824/533, loss: 0.021534014493227005
2023-01-23 03:34:16.309337: step: 828/533, loss: 0.09225676208734512
2023-01-23 03:34:17.430279: step: 832/533, loss: 0.00712165841832757
2023-01-23 03:34:18.607954: step: 836/533, loss: 2.059936559817288e-05
2023-01-23 03:34:19.765435: step: 840/533, loss: 0.004351520445197821
2023-01-23 03:34:20.907103: step: 844/533, loss: 0.011018180288374424
2023-01-23 03:34:22.111146: step: 848/533, loss: 0.025036906823515892
2023-01-23 03:34:23.276219: step: 852/533, loss: 0.0002452850458212197
2023-01-23 03:34:24.480545: step: 856/533, loss: 0.002333450596779585
2023-01-23 03:34:25.611961: step: 860/533, loss: 0.0005685806390829384
2023-01-23 03:34:26.840633: step: 864/533, loss: 0.00010480881610419601
2023-01-23 03:34:28.015717: step: 868/533, loss: 0.023266220465302467
2023-01-23 03:34:29.221367: step: 872/533, loss: 0.07908955216407776
2023-01-23 03:34:30.409528: step: 876/533, loss: 0.003699874971061945
2023-01-23 03:34:31.614318: step: 880/533, loss: 0.030781077221035957
2023-01-23 03:34:32.811953: step: 884/533, loss: 0.049390316009521484
2023-01-23 03:34:33.996973: step: 888/533, loss: 0.008008194155991077
2023-01-23 03:34:35.190355: step: 892/533, loss: 0.0022375108674168587
2023-01-23 03:34:36.355303: step: 896/533, loss: 0.0018934727413579822
2023-01-23 03:34:37.573147: step: 900/533, loss: 0.0015453338855877519
2023-01-23 03:34:38.731008: step: 904/533, loss: 0.10147485136985779
2023-01-23 03:34:39.930213: step: 908/533, loss: 0.010884379968047142
2023-01-23 03:34:41.082151: step: 912/533, loss: 0.0781635269522667
2023-01-23 03:34:42.212281: step: 916/533, loss: 4.100799560546875e-05
2023-01-23 03:34:43.384142: step: 920/533, loss: 0.00021457672119140625
2023-01-23 03:34:44.550174: step: 924/533, loss: 0.030443573370575905
2023-01-23 03:34:45.719481: step: 928/533, loss: 0.026337813585996628
2023-01-23 03:34:46.917742: step: 932/533, loss: 0.005729484371840954
2023-01-23 03:34:48.092116: step: 936/533, loss: 0.00021305083646439016
2023-01-23 03:34:49.305244: step: 940/533, loss: 0.026098251342773438
2023-01-23 03:34:50.469752: step: 944/533, loss: 0.045636557042598724
2023-01-23 03:34:51.623321: step: 948/533, loss: 0.043384552001953125
2023-01-23 03:34:52.789986: step: 952/533, loss: 0.009241295047104359
2023-01-23 03:34:53.980337: step: 956/533, loss: 0.000935936055611819
2023-01-23 03:34:55.114557: step: 960/533, loss: 0.05775656923651695
2023-01-23 03:34:56.274701: step: 964/533, loss: 0.11051978915929794
2023-01-23 03:34:57.435265: step: 968/533, loss: 0.05667925253510475
2023-01-23 03:34:58.657677: step: 972/533, loss: 0.006842327304184437
2023-01-23 03:34:59.883364: step: 976/533, loss: 0.04330272972583771
2023-01-23 03:35:01.065038: step: 980/533, loss: 0.001110172364860773
2023-01-23 03:35:02.300589: step: 984/533, loss: 0.07031986117362976
2023-01-23 03:35:03.509352: step: 988/533, loss: 0.0008275032741948962
2023-01-23 03:35:04.714144: step: 992/533, loss: 0.0011075020302087069
2023-01-23 03:35:05.907830: step: 996/533, loss: 0.06190691143274307
2023-01-23 03:35:07.110043: step: 1000/533, loss: 0.007774639409035444
2023-01-23 03:35:08.303811: step: 1004/533, loss: 0.0054145813919603825
2023-01-23 03:35:09.450529: step: 1008/533, loss: 0.0041713714599609375
2023-01-23 03:35:10.575150: step: 1012/533, loss: 0.00029468536376953125
2023-01-23 03:35:11.723608: step: 1016/533, loss: 0.0006761550903320312
2023-01-23 03:35:12.874102: step: 1020/533, loss: 0.03555736690759659
2023-01-23 03:35:14.044762: step: 1024/533, loss: 0.048803139477968216
2023-01-23 03:35:15.240690: step: 1028/533, loss: 1.983642505365424e-05
2023-01-23 03:35:16.411601: step: 1032/533, loss: 0.00019598007202148438
2023-01-23 03:35:17.616780: step: 1036/533, loss: 1.1171705722808838
2023-01-23 03:35:18.872649: step: 1040/533, loss: 0.001381874200887978
2023-01-23 03:35:20.085752: step: 1044/533, loss: 9.155274165095761e-05
2023-01-23 03:35:21.251899: step: 1048/533, loss: 8.106231689453125e-05
2023-01-23 03:35:22.423008: step: 1052/533, loss: 0.00841598492115736
2023-01-23 03:35:23.598561: step: 1056/533, loss: 0.00014925003051757812
2023-01-23 03:35:24.751021: step: 1060/533, loss: 0.006827068515121937
2023-01-23 03:35:25.974298: step: 1064/533, loss: 0.05668392404913902
2023-01-23 03:35:27.159204: step: 1068/533, loss: 0.004292106721550226
2023-01-23 03:35:28.355290: step: 1072/533, loss: 0.0001983642578125
2023-01-23 03:35:29.573524: step: 1076/533, loss: 0.006275367923080921
2023-01-23 03:35:30.751127: step: 1080/533, loss: 4.110336521989666e-05
2023-01-23 03:35:31.963870: step: 1084/533, loss: -1.3971328371553682e-05
2023-01-23 03:35:33.112946: step: 1088/533, loss: 0.03936729207634926
2023-01-23 03:35:34.294342: step: 1092/533, loss: 2.4700164431123994e-05
2023-01-23 03:35:35.508183: step: 1096/533, loss: 0.0028278352692723274
2023-01-23 03:35:36.664134: step: 1100/533, loss: 0.007265186402946711
2023-01-23 03:35:37.826908: step: 1104/533, loss: 0.0366390235722065
2023-01-23 03:35:38.997312: step: 1108/533, loss: 0.0009763717534951866
2023-01-23 03:35:40.164204: step: 1112/533, loss: 0.0024343968834728003
2023-01-23 03:35:41.328234: step: 1116/533, loss: 0.01678180694580078
2023-01-23 03:35:42.470867: step: 1120/533, loss: 0.0451175719499588
2023-01-23 03:35:43.619393: step: 1124/533, loss: 0.0002361297665629536
2023-01-23 03:35:44.803354: step: 1128/533, loss: 0.008493232540786266
2023-01-23 03:35:46.004725: step: 1132/533, loss: 0.03020477294921875
2023-01-23 03:35:47.200127: step: 1136/533, loss: 0.003135872073471546
2023-01-23 03:35:48.383562: step: 1140/533, loss: 0.020868968218564987
2023-01-23 03:35:49.596128: step: 1144/533, loss: 0.0019865036010742188
2023-01-23 03:35:50.765227: step: 1148/533, loss: 0.000226879128604196
2023-01-23 03:35:51.910166: step: 1152/533, loss: 0.0009277344215661287
2023-01-23 03:35:53.072857: step: 1156/533, loss: 0.0006402969593182206
2023-01-23 03:35:54.271980: step: 1160/533, loss: 0.00225658412091434
2023-01-23 03:35:55.447198: step: 1164/533, loss: 0.004957771394401789
2023-01-23 03:35:56.630878: step: 1168/533, loss: 2.727508581301663e-05
2023-01-23 03:35:57.817726: step: 1172/533, loss: 0.0015538216102868319
2023-01-23 03:35:58.960030: step: 1176/533, loss: 0.001525783445686102
2023-01-23 03:36:00.105565: step: 1180/533, loss: 0.012783623300492764
2023-01-23 03:36:01.290505: step: 1184/533, loss: 0.0001906395045807585
2023-01-23 03:36:02.434329: step: 1188/533, loss: 0.010441686026751995
2023-01-23 03:36:03.655729: step: 1192/533, loss: 0.01654043234884739
2023-01-23 03:36:04.843772: step: 1196/533, loss: 0.0035977838560938835
2023-01-23 03:36:06.001412: step: 1200/533, loss: 0.0007568359724245965
2023-01-23 03:36:07.156246: step: 1204/533, loss: 0.00042791367741301656
2023-01-23 03:36:08.333629: step: 1208/533, loss: 0.10214042663574219
2023-01-23 03:36:09.510698: step: 1212/533, loss: 1.544952465337701e-05
2023-01-23 03:36:10.651210: step: 1216/533, loss: 0.0001062512383214198
2023-01-23 03:36:11.817416: step: 1220/533, loss: 0.00014152527728583664
2023-01-23 03:36:13.013284: step: 1224/533, loss: 0.00012798310490325093
2023-01-23 03:36:14.188516: step: 1228/533, loss: 0.06654767692089081
2023-01-23 03:36:15.351765: step: 1232/533, loss: 0.001120758126489818
2023-01-23 03:36:16.577028: step: 1236/533, loss: 0.004656028933823109
2023-01-23 03:36:17.765542: step: 1240/533, loss: 0.06841182708740234
2023-01-23 03:36:18.958686: step: 1244/533, loss: 0.0008581161964684725
2023-01-23 03:36:20.099536: step: 1248/533, loss: 0.01417932566255331
2023-01-23 03:36:21.262385: step: 1252/533, loss: 0.11068897694349289
2023-01-23 03:36:22.462420: step: 1256/533, loss: 0.004182625096291304
2023-01-23 03:36:23.601341: step: 1260/533, loss: 0.00025472641573287547
2023-01-23 03:36:24.802894: step: 1264/533, loss: 0.008537864312529564
2023-01-23 03:36:25.952146: step: 1268/533, loss: 0.0010258675320073962
2023-01-23 03:36:27.116409: step: 1272/533, loss: 0.013204192742705345
2023-01-23 03:36:28.295696: step: 1276/533, loss: 0.000745582627132535
2023-01-23 03:36:29.483078: step: 1280/533, loss: 0.0014459609519690275
2023-01-23 03:36:30.648254: step: 1284/533, loss: 0.0023626326583325863
2023-01-23 03:36:31.803185: step: 1288/533, loss: 0.001220750855281949
2023-01-23 03:36:32.999759: step: 1292/533, loss: 7.810592069290578e-05
2023-01-23 03:36:34.188880: step: 1296/533, loss: 0.011261940002441406
2023-01-23 03:36:35.360567: step: 1300/533, loss: 0.012563610449433327
2023-01-23 03:36:36.496723: step: 1304/533, loss: 0.0019123078091070056
2023-01-23 03:36:37.683750: step: 1308/533, loss: 0.008049964904785156
2023-01-23 03:36:38.874579: step: 1312/533, loss: 0.0001605987490620464
2023-01-23 03:36:40.055624: step: 1316/533, loss: 0.003508329391479492
2023-01-23 03:36:41.229902: step: 1320/533, loss: 0.06928787380456924
2023-01-23 03:36:42.430017: step: 1324/533, loss: 0.0006918907165527344
2023-01-23 03:36:43.621388: step: 1328/533, loss: 0.03987693786621094
2023-01-23 03:36:44.768396: step: 1332/533, loss: 0.009356594644486904
2023-01-23 03:36:45.966064: step: 1336/533, loss: 0.002071189694106579
2023-01-23 03:36:47.128647: step: 1340/533, loss: 0.00019121171499136835
2023-01-23 03:36:48.327650: step: 1344/533, loss: 0.0008920669206418097
2023-01-23 03:36:49.492512: step: 1348/533, loss: 0.0001051902727340348
2023-01-23 03:36:50.663012: step: 1352/533, loss: 0.00044116974459029734
2023-01-23 03:36:51.830813: step: 1356/533, loss: 0.010896396823227406
2023-01-23 03:36:52.996776: step: 1360/533, loss: 0.0002187728969147429
2023-01-23 03:36:54.176996: step: 1364/533, loss: 0.014450455084443092
2023-01-23 03:36:55.373422: step: 1368/533, loss: 2.403259350103326e-05
2023-01-23 03:36:56.570562: step: 1372/533, loss: 0.015905380249023438
2023-01-23 03:36:57.742961: step: 1376/533, loss: 0.00020828247943427414
2023-01-23 03:36:58.892596: step: 1380/533, loss: 0.0001461505889892578
2023-01-23 03:37:00.062455: step: 1384/533, loss: 0.008422470651566982
2023-01-23 03:37:01.208871: step: 1388/533, loss: 0.00789489783346653
2023-01-23 03:37:02.368983: step: 1392/533, loss: 0.018627356737852097
2023-01-23 03:37:03.503761: step: 1396/533, loss: 0.00071291922358796
2023-01-23 03:37:04.683440: step: 1400/533, loss: 2.765655517578125e-05
2023-01-23 03:37:05.856438: step: 1404/533, loss: 0.06094570457935333
2023-01-23 03:37:06.991471: step: 1408/533, loss: 7.05718994140625e-05
2023-01-23 03:37:08.150759: step: 1412/533, loss: 3.62396240234375e-05
2023-01-23 03:37:09.317850: step: 1416/533, loss: 0.0292219165712595
2023-01-23 03:37:10.463632: step: 1420/533, loss: 0.00011034011549782008
2023-01-23 03:37:11.627437: step: 1424/533, loss: 0.011471081525087357
2023-01-23 03:37:12.804981: step: 1428/533, loss: 0.006596899125725031
2023-01-23 03:37:14.066621: step: 1432/533, loss: 0.023598099127411842
2023-01-23 03:37:15.238460: step: 1436/533, loss: 0.01854524575173855
2023-01-23 03:37:16.378666: step: 1440/533, loss: 8.583069188716763e-07
2023-01-23 03:37:17.553692: step: 1444/533, loss: 0.0002729415718931705
2023-01-23 03:37:18.747108: step: 1448/533, loss: 0.0002134323149221018
2023-01-23 03:37:19.891473: step: 1452/533, loss: 0.018523788079619408
2023-01-23 03:37:21.084146: step: 1456/533, loss: 0.0010927199618890882
2023-01-23 03:37:22.278466: step: 1460/533, loss: 0.010115623474121094
2023-01-23 03:37:23.429301: step: 1464/533, loss: 0.0007582664838992059
2023-01-23 03:37:24.590243: step: 1468/533, loss: 0.000745582627132535
2023-01-23 03:37:25.795979: step: 1472/533, loss: 0.019166089594364166
2023-01-23 03:37:26.941606: step: 1476/533, loss: 0.020336437970399857
2023-01-23 03:37:28.125268: step: 1480/533, loss: 0.0014175415271893144
2023-01-23 03:37:29.279791: step: 1484/533, loss: 0.004273796454071999
2023-01-23 03:37:30.455808: step: 1488/533, loss: 0.025166893377900124
2023-01-23 03:37:31.607219: step: 1492/533, loss: 0.0003503799671307206
2023-01-23 03:37:32.744273: step: 1496/533, loss: 0.0001297950657317415
2023-01-23 03:37:33.895332: step: 1500/533, loss: 0.0010652542114257812
2023-01-23 03:37:35.127111: step: 1504/533, loss: 0.05767173692584038
2023-01-23 03:37:36.304949: step: 1508/533, loss: 0.0036220550537109375
2023-01-23 03:37:37.485318: step: 1512/533, loss: 0.00531616248190403
2023-01-23 03:37:38.642207: step: 1516/533, loss: 0.007601452060043812
2023-01-23 03:37:39.803750: step: 1520/533, loss: 0.00654182443395257
2023-01-23 03:37:41.013231: step: 1524/533, loss: 0.0023254393599927425
2023-01-23 03:37:42.223608: step: 1528/533, loss: 0.010938835330307484
2023-01-23 03:37:43.401102: step: 1532/533, loss: 0.007700061891227961
2023-01-23 03:37:44.627447: step: 1536/533, loss: 0.0013273239601403475
2023-01-23 03:37:45.783083: step: 1540/533, loss: 3.700256274896674e-05
2023-01-23 03:37:46.985307: step: 1544/533, loss: 2.384185791015625e-06
2023-01-23 03:37:48.178008: step: 1548/533, loss: 0.00159454345703125
2023-01-23 03:37:49.351511: step: 1552/533, loss: 0.0012510298984125257
2023-01-23 03:37:50.564714: step: 1556/533, loss: 0.014195061288774014
2023-01-23 03:37:51.729911: step: 1560/533, loss: 0.0009794235229492188
2023-01-23 03:37:52.875783: step: 1564/533, loss: 0.0018888532649725676
2023-01-23 03:37:54.077681: step: 1568/533, loss: 0.00152759556658566
2023-01-23 03:37:55.245333: step: 1572/533, loss: 0.0032791136763989925
2023-01-23 03:37:56.392383: step: 1576/533, loss: 6.828307959949598e-05
2023-01-23 03:37:57.554149: step: 1580/533, loss: 0.0016378402942791581
2023-01-23 03:37:58.756097: step: 1584/533, loss: 0.008200645446777344
2023-01-23 03:37:59.917080: step: 1588/533, loss: -5.817413239128655e-06
2023-01-23 03:38:01.076917: step: 1592/533, loss: 0.009557152166962624
2023-01-23 03:38:02.260600: step: 1596/533, loss: 0.011639404110610485
2023-01-23 03:38:03.446747: step: 1600/533, loss: 0.0003681182861328125
2023-01-23 03:38:04.604137: step: 1604/533, loss: 6.4849853515625e-05
2023-01-23 03:38:05.798092: step: 1608/533, loss: 0.000152587890625
2023-01-23 03:38:06.994176: step: 1612/533, loss: 0.0019096374744549394
2023-01-23 03:38:08.204915: step: 1616/533, loss: 4.596710277837701e-05
2023-01-23 03:38:09.368843: step: 1620/533, loss: 5.588531348621473e-05
2023-01-23 03:38:10.544207: step: 1624/533, loss: 0.04605436325073242
2023-01-23 03:38:11.738748: step: 1628/533, loss: 0.00020551681518554688
2023-01-23 03:38:12.916688: step: 1632/533, loss: 9.098053124034777e-05
2023-01-23 03:38:14.047487: step: 1636/533, loss: 0.00812215730547905
2023-01-23 03:38:15.189314: step: 1640/533, loss: 5.435943603515625e-05
2023-01-23 03:38:16.362266: step: 1644/533, loss: 0.023671245202422142
2023-01-23 03:38:17.531861: step: 1648/533, loss: 0.0004153251647949219
2023-01-23 03:38:18.695616: step: 1652/533, loss: 7.114410254871473e-05
2023-01-23 03:38:19.812263: step: 1656/533, loss: 0.0008428573491983116
2023-01-23 03:38:21.031818: step: 1660/533, loss: 0.00035705568734556437
2023-01-23 03:38:22.212992: step: 1664/533, loss: 0.004678058438003063
2023-01-23 03:38:23.349883: step: 1668/533, loss: 0.0011800766224041581
2023-01-23 03:38:24.562407: step: 1672/533, loss: 0.02404804155230522
2023-01-23 03:38:25.713620: step: 1676/533, loss: 0.0011755942832678556
2023-01-23 03:38:26.904303: step: 1680/533, loss: 0.0001852989080362022
2023-01-23 03:38:28.081055: step: 1684/533, loss: 0.0021029473282396793
2023-01-23 03:38:29.251776: step: 1688/533, loss: 0.01467285118997097
2023-01-23 03:38:30.422991: step: 1692/533, loss: 2.918243444582913e-05
2023-01-23 03:38:31.625859: step: 1696/533, loss: 6.723404112563003e-06
2023-01-23 03:38:32.822586: step: 1700/533, loss: 0.019610309973359108
2023-01-23 03:38:33.972079: step: 1704/533, loss: 0.04709291458129883
2023-01-23 03:38:35.124652: step: 1708/533, loss: 0.02316885255277157
2023-01-23 03:38:36.297725: step: 1712/533, loss: 4.019737389171496e-05
2023-01-23 03:38:37.449140: step: 1716/533, loss: 8.20159948489163e-06
2023-01-23 03:38:38.614488: step: 1720/533, loss: 0.0009641647338867188
2023-01-23 03:38:39.817586: step: 1724/533, loss: 0.07786465436220169
2023-01-23 03:38:40.982301: step: 1728/533, loss: 0.0015408992767333984
2023-01-23 03:38:42.169377: step: 1732/533, loss: 0.013975907117128372
2023-01-23 03:38:43.322837: step: 1736/533, loss: 0.001447486924007535
2023-01-23 03:38:44.493195: step: 1740/533, loss: 2.7084352041129023e-05
2023-01-23 03:38:45.629459: step: 1744/533, loss: -4.57763690064894e-06
2023-01-23 03:38:46.776135: step: 1748/533, loss: -4.482269105210435e-06
2023-01-23 03:38:47.926126: step: 1752/533, loss: 0.011700249277055264
2023-01-23 03:38:49.087825: step: 1756/533, loss: 0.002574157901108265
2023-01-23 03:38:50.264220: step: 1760/533, loss: 0.024260330945253372
2023-01-23 03:38:51.457497: step: 1764/533, loss: 0.0008701324695721269
2023-01-23 03:38:52.650826: step: 1768/533, loss: 0.007428646087646484
2023-01-23 03:38:53.797750: step: 1772/533, loss: 0.055863380432128906
2023-01-23 03:38:54.969411: step: 1776/533, loss: 0.02773122861981392
2023-01-23 03:38:56.098200: step: 1780/533, loss: 0.0001354217529296875
2023-01-23 03:38:57.283308: step: 1784/533, loss: 0.05065784603357315
2023-01-23 03:38:58.481881: step: 1788/533, loss: -7.4386593951203395e-06
2023-01-23 03:38:59.651959: step: 1792/533, loss: 0.0011419296497479081
2023-01-23 03:39:00.848107: step: 1796/533, loss: 0.0008434295887127519
2023-01-23 03:39:02.032331: step: 1800/533, loss: 0.014854812994599342
2023-01-23 03:39:03.173876: step: 1804/533, loss: 0.024970054626464844
2023-01-23 03:39:04.360787: step: 1808/533, loss: 0.0001202583298436366
2023-01-23 03:39:05.496310: step: 1812/533, loss: -4.00543194700731e-06
2023-01-23 03:39:06.708681: step: 1816/533, loss: 8.320808410644531e-05
2023-01-23 03:39:07.872840: step: 1820/533, loss: 0.007039832882583141
2023-01-23 03:39:09.040835: step: 1824/533, loss: 1.8358230590820312e-05
2023-01-23 03:39:10.198958: step: 1828/533, loss: 5.340576535672881e-06
2023-01-23 03:39:11.417946: step: 1832/533, loss: 0.00851221103221178
2023-01-23 03:39:12.634431: step: 1836/533, loss: 0.013712120242416859
2023-01-23 03:39:13.815159: step: 1840/533, loss: 5.664825584972277e-05
2023-01-23 03:39:14.981519: step: 1844/533, loss: 0.024763107299804688
2023-01-23 03:39:16.144933: step: 1848/533, loss: 0.0003149986150674522
2023-01-23 03:39:17.333424: step: 1852/533, loss: 2.0980836779926904e-05
2023-01-23 03:39:18.536523: step: 1856/533, loss: 0.00046830179053358734
2023-01-23 03:39:19.743712: step: 1860/533, loss: 1.6927719116210938e-05
2023-01-23 03:39:20.916094: step: 1864/533, loss: 0.017177963629364967
2023-01-23 03:39:22.130495: step: 1868/533, loss: 0.0006961823091842234
2023-01-23 03:39:23.373262: step: 1872/533, loss: 0.0007681846618652344
2023-01-23 03:39:24.551647: step: 1876/533, loss: 0.0012486458290368319
2023-01-23 03:39:25.770477: step: 1880/533, loss: 0.0022342682350426912
2023-01-23 03:39:26.965363: step: 1884/533, loss: 0.029091835021972656
2023-01-23 03:39:28.131383: step: 1888/533, loss: 0.0012881278526037931
2023-01-23 03:39:29.256339: step: 1892/533, loss: 0.020928192883729935
2023-01-23 03:39:30.457434: step: 1896/533, loss: 0.007745838258415461
2023-01-23 03:39:31.650797: step: 1900/533, loss: 0.0026636123657226562
2023-01-23 03:39:32.850037: step: 1904/533, loss: 0.02485194243490696
2023-01-23 03:39:34.050990: step: 1908/533, loss: -4.00543194700731e-06
2023-01-23 03:39:35.206549: step: 1912/533, loss: 0.003954124636948109
2023-01-23 03:39:36.375714: step: 1916/533, loss: 5.607604907709174e-05
2023-01-23 03:39:37.631537: step: 1920/533, loss: 1.0204315003647935e-05
2023-01-23 03:39:38.799918: step: 1924/533, loss: 0.0020041943062096834
2023-01-23 03:39:39.985414: step: 1928/533, loss: 0.00025773048400878906
2023-01-23 03:39:41.133782: step: 1932/533, loss: 0.02681426890194416
2023-01-23 03:39:42.322342: step: 1936/533, loss: 0.016598891466856003
2023-01-23 03:39:43.484117: step: 1940/533, loss: 0.01302194595336914
2023-01-23 03:39:44.643335: step: 1944/533, loss: 0.025763513520359993
2023-01-23 03:39:45.789181: step: 1948/533, loss: 0.02256469801068306
2023-01-23 03:39:46.955864: step: 1952/533, loss: 0.004913234617561102
2023-01-23 03:39:48.119045: step: 1956/533, loss: 0.0017461776733398438
2023-01-23 03:39:49.290408: step: 1960/533, loss: 0.039456557482481
2023-01-23 03:39:50.483749: step: 1964/533, loss: 0.009808349423110485
2023-01-23 03:39:51.618195: step: 1968/533, loss: 0.004604053683578968
2023-01-23 03:39:52.793970: step: 1972/533, loss: 0.019207384437322617
2023-01-23 03:39:53.970762: step: 1976/533, loss: 0.00277194962836802
2023-01-23 03:39:55.135476: step: 1980/533, loss: -2.0885467165498994e-05
2023-01-23 03:39:56.302260: step: 1984/533, loss: 1.4019012269272935e-05
2023-01-23 03:39:57.493887: step: 1988/533, loss: 6.46591215627268e-05
2023-01-23 03:39:58.650877: step: 1992/533, loss: 0.006814527790993452
2023-01-23 03:39:59.830522: step: 1996/533, loss: 0.021334027871489525
2023-01-23 03:40:00.990767: step: 2000/533, loss: 0.009670543484389782
2023-01-23 03:40:02.155650: step: 2004/533, loss: 0.002830171724781394
2023-01-23 03:40:03.355637: step: 2008/533, loss: 0.01386880874633789
2023-01-23 03:40:04.516626: step: 2012/533, loss: 0.0037967683747410774
2023-01-23 03:40:05.700816: step: 2016/533, loss: 0.006990909576416016
2023-01-23 03:40:06.876852: step: 2020/533, loss: 0.0005186080816201866
2023-01-23 03:40:08.051007: step: 2024/533, loss: 0.00025320128770545125
2023-01-23 03:40:09.248400: step: 2028/533, loss: 0.00026721955509856343
2023-01-23 03:40:10.434680: step: 2032/533, loss: 0.00011672973778331652
2023-01-23 03:40:11.595706: step: 2036/533, loss: 0.006080150604248047
2023-01-23 03:40:12.773364: step: 2040/533, loss: 0.7187438011169434
2023-01-23 03:40:13.951260: step: 2044/533, loss: 0.00107240688521415
2023-01-23 03:40:15.100228: step: 2048/533, loss: 0.0003261566162109375
2023-01-23 03:40:16.266185: step: 2052/533, loss: 0.0005474090576171875
2023-01-23 03:40:17.461106: step: 2056/533, loss: 7.476806786144152e-05
2023-01-23 03:40:18.663977: step: 2060/533, loss: 0.016642285510897636
2023-01-23 03:40:19.845462: step: 2064/533, loss: 0.0021890641655772924
2023-01-23 03:40:21.047707: step: 2068/533, loss: 0.0004442215140443295
2023-01-23 03:40:22.186572: step: 2072/533, loss: 0.00383586878888309
2023-01-23 03:40:23.384121: step: 2076/533, loss: 0.003705692244693637
2023-01-23 03:40:24.559138: step: 2080/533, loss: 0.0005316734313964844
2023-01-23 03:40:25.757688: step: 2084/533, loss: 0.002096223644912243
2023-01-23 03:40:26.974663: step: 2088/533, loss: 0.0032352448906749487
2023-01-23 03:40:28.142621: step: 2092/533, loss: 0.008084392175078392
2023-01-23 03:40:29.338695: step: 2096/533, loss: 0.0405704490840435
2023-01-23 03:40:30.525098: step: 2100/533, loss: 0.029516983777284622
2023-01-23 03:40:31.701428: step: 2104/533, loss: 0.019709492102265358
2023-01-23 03:40:32.867014: step: 2108/533, loss: 0.00034705401048995554
2023-01-23 03:40:34.027666: step: 2112/533, loss: 0.02143106609582901
2023-01-23 03:40:35.245337: step: 2116/533, loss: 0.08330383151769638
2023-01-23 03:40:36.454427: step: 2120/533, loss: 0.00034933091956190765
2023-01-23 03:40:37.657626: step: 2124/533, loss: 6.752014451194555e-05
2023-01-23 03:40:38.833987: step: 2128/533, loss: 0.0017266273498535156
2023-01-23 03:40:39.991880: step: 2132/533, loss: 0.0057968138717114925
==================================================
Loss: 0.028
--------------------
Dev: {'event': {'p': 0.6149789029535865, 'r': 0.7762982689747004, 'f1': 0.6862860506180106}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6622760800842993, 'r': 0.8037084398976982, 'f1': 0.7261698440207972}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5662650602409639, 'r': 0.8703703703703703, 'f1': 0.6861313868613138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.3902439024390244, 'r': 0.4444444444444444, 'f1': 0.4155844155844156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 23
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:41:20.806061: step: 4/533, loss: 4.367828296381049e-05
2023-01-23 03:41:21.959105: step: 8/533, loss: 0.004833698738366365
2023-01-23 03:41:23.151874: step: 12/533, loss: -1.5258788153005298e-06
2023-01-23 03:41:24.331994: step: 16/533, loss: 0.0010787963401526213
2023-01-23 03:41:25.518138: step: 20/533, loss: 0.01408369466662407
2023-01-23 03:41:26.724082: step: 24/533, loss: 0.5773662328720093
2023-01-23 03:41:27.932497: step: 28/533, loss: 0.0076806070283055305
2023-01-23 03:41:29.120632: step: 32/533, loss: 0.00199718470685184
2023-01-23 03:41:30.289804: step: 36/533, loss: 0.010397911071777344
2023-01-23 03:41:31.455089: step: 40/533, loss: 0.00027551650418899953
2023-01-23 03:41:32.647745: step: 44/533, loss: 0.011960124596953392
2023-01-23 03:41:33.840827: step: 48/533, loss: 0.0021364688873291016
2023-01-23 03:41:35.011214: step: 52/533, loss: 0.0010891437996178865
2023-01-23 03:41:36.198342: step: 56/533, loss: 0.00436820974573493
2023-01-23 03:41:37.387503: step: 60/533, loss: 0.0032970430329442024
2023-01-23 03:41:38.531204: step: 64/533, loss: 0.001438140869140625
2023-01-23 03:41:39.677219: step: 68/533, loss: 1.3685226804227568e-05
2023-01-23 03:41:40.829223: step: 72/533, loss: -4.00543194700731e-06
2023-01-23 03:41:42.024394: step: 76/533, loss: 0.018964387476444244
2023-01-23 03:41:43.166518: step: 80/533, loss: 0.013823652639985085
2023-01-23 03:41:44.322993: step: 84/533, loss: 0.000173473366885446
2023-01-23 03:41:45.485861: step: 88/533, loss: 0.11178937554359436
2023-01-23 03:41:46.632361: step: 92/533, loss: 0.002576160477474332
2023-01-23 03:41:47.856940: step: 96/533, loss: 0.0018013000953942537
2023-01-23 03:41:49.018676: step: 100/533, loss: -9.5367431640625e-07
2023-01-23 03:41:50.177794: step: 104/533, loss: 2.1743775505456142e-05
2023-01-23 03:41:51.375440: step: 108/533, loss: 0.0002487182500772178
2023-01-23 03:41:52.612087: step: 112/533, loss: 0.003396320389583707
2023-01-23 03:41:53.810298: step: 116/533, loss: 0.0013130188453942537
2023-01-23 03:41:55.017705: step: 120/533, loss: 0.002260589739307761
2023-01-23 03:41:56.149035: step: 124/533, loss: 0.00011034011549782008
2023-01-23 03:41:57.348906: step: 128/533, loss: 0.00017328262038063258
2023-01-23 03:41:58.511256: step: 132/533, loss: 0.022417353466153145
2023-01-23 03:41:59.654495: step: 136/533, loss: 0.00011119843111373484
2023-01-23 03:42:00.880051: step: 140/533, loss: 0.0045659542083740234
2023-01-23 03:42:02.029480: step: 144/533, loss: 0.012973308563232422
2023-01-23 03:42:03.208064: step: 148/533, loss: -1.697540210443549e-05
2023-01-23 03:42:04.385510: step: 152/533, loss: 0.0008994102827273309
2023-01-23 03:42:05.525512: step: 156/533, loss: 0.0024919509887695312
2023-01-23 03:42:06.668520: step: 160/533, loss: 0.0009292602771893144
2023-01-23 03:42:07.834127: step: 164/533, loss: 0.00080108642578125
2023-01-23 03:42:09.012489: step: 168/533, loss: 0.003117084503173828
2023-01-23 03:42:10.169829: step: 172/533, loss: 0.015945052728056908
2023-01-23 03:42:11.385465: step: 176/533, loss: 2.250671423098538e-05
2023-01-23 03:42:12.546814: step: 180/533, loss: 9.150505502475426e-05
2023-01-23 03:42:13.737458: step: 184/533, loss: 7.295608611457283e-06
2023-01-23 03:42:14.924707: step: 188/533, loss: 0.049378011375665665
2023-01-23 03:42:16.066210: step: 192/533, loss: 0.04559612274169922
2023-01-23 03:42:17.231841: step: 196/533, loss: 0.0034296035300940275
2023-01-23 03:42:18.404042: step: 200/533, loss: 0.0013187408912926912
2023-01-23 03:42:19.583730: step: 204/533, loss: 0.0005696296575479209
2023-01-23 03:42:20.744295: step: 208/533, loss: 0.01294555701315403
2023-01-23 03:42:21.983545: step: 212/533, loss: 0.0030471801292151213
2023-01-23 03:42:23.182290: step: 216/533, loss: 0.015167427249252796
2023-01-23 03:42:24.355024: step: 220/533, loss: 0.0001539230433991179
2023-01-23 03:42:25.514638: step: 224/533, loss: 0.0017995834350585938
2023-01-23 03:42:26.694340: step: 228/533, loss: 0.026882745325565338
2023-01-23 03:42:27.835436: step: 232/533, loss: 0.0005903244018554688
2023-01-23 03:42:28.979218: step: 236/533, loss: 5.33103957423009e-05
2023-01-23 03:42:30.148098: step: 240/533, loss: 0.0048084259033203125
2023-01-23 03:42:31.413793: step: 244/533, loss: 0.006752967834472656
2023-01-23 03:42:32.554341: step: 248/533, loss: 0.01136703509837389
2023-01-23 03:42:33.712429: step: 252/533, loss: 0.0007987976423464715
2023-01-23 03:42:34.875546: step: 256/533, loss: 0.0003628730773925781
2023-01-23 03:42:36.038748: step: 260/533, loss: 0.0075005535036325455
2023-01-23 03:42:37.185726: step: 264/533, loss: 0.01676158793270588
2023-01-23 03:42:38.295708: step: 268/533, loss: 0.5639263987541199
2023-01-23 03:42:39.450704: step: 272/533, loss: 0.007390069775283337
2023-01-23 03:42:40.645384: step: 276/533, loss: 0.0006742477999068797
2023-01-23 03:42:41.873483: step: 280/533, loss: 3.223419116693549e-05
2023-01-23 03:42:43.082410: step: 284/533, loss: 0.0007882118807174265
2023-01-23 03:42:44.220615: step: 288/533, loss: 0.02160205878317356
2023-01-23 03:42:45.448481: step: 292/533, loss: 0.0036558150313794613
2023-01-23 03:42:46.659327: step: 296/533, loss: 0.0003621101495809853
2023-01-23 03:42:47.806906: step: 300/533, loss: 0.017501259222626686
2023-01-23 03:42:48.973744: step: 304/533, loss: 0.008803939446806908
2023-01-23 03:42:50.139226: step: 308/533, loss: 0.0008853912586346269
2023-01-23 03:42:51.321805: step: 312/533, loss: 3.204345557605848e-05
2023-01-23 03:42:52.550925: step: 316/533, loss: 0.0013242721324786544
2023-01-23 03:42:53.688920: step: 320/533, loss: 0.01422338467091322
2023-01-23 03:42:54.891593: step: 324/533, loss: 0.007374000269919634
2023-01-23 03:42:56.107787: step: 328/533, loss: 0.02530651167035103
2023-01-23 03:42:57.280722: step: 332/533, loss: 0.0005330085987225175
2023-01-23 03:42:58.430358: step: 336/533, loss: 0.005850601475685835
2023-01-23 03:42:59.586118: step: 340/533, loss: 0.006619072053581476
2023-01-23 03:43:00.824446: step: 344/533, loss: 0.0011375427711755037
2023-01-23 03:43:02.009945: step: 348/533, loss: 0.004350757692009211
2023-01-23 03:43:03.185899: step: 352/533, loss: 0.013763475231826305
2023-01-23 03:43:04.317703: step: 356/533, loss: 3.1757354008732364e-05
2023-01-23 03:43:05.495149: step: 360/533, loss: 0.01386342104524374
2023-01-23 03:43:06.673119: step: 364/533, loss: 0.010579300113022327
2023-01-23 03:43:07.859370: step: 368/533, loss: 0.0001661300630075857
2023-01-23 03:43:08.999614: step: 372/533, loss: 0.0073909759521484375
2023-01-23 03:43:10.157201: step: 376/533, loss: 0.014061165042221546
2023-01-23 03:43:11.300348: step: 380/533, loss: 3.452301098150201e-05
2023-01-23 03:43:12.475800: step: 384/533, loss: 4.95910626341356e-06
2023-01-23 03:43:13.728595: step: 388/533, loss: 0.006706476677209139
2023-01-23 03:43:14.893160: step: 392/533, loss: 0.00013456345186568797
2023-01-23 03:43:16.043910: step: 396/533, loss: 0.0027136802673339844
2023-01-23 03:43:17.175154: step: 400/533, loss: 0.0012274743057787418
2023-01-23 03:43:18.341254: step: 404/533, loss: 0.0027151107788085938
2023-01-23 03:43:19.550708: step: 408/533, loss: 0.0020917891524732113
2023-01-23 03:43:20.754056: step: 412/533, loss: 0.0005847931024618447
2023-01-23 03:43:21.954562: step: 416/533, loss: 0.0001483917294535786
2023-01-23 03:43:23.109871: step: 420/533, loss: 0.0032260895241051912
2023-01-23 03:43:24.297489: step: 424/533, loss: 0.008239937014877796
2023-01-23 03:43:25.502977: step: 428/533, loss: 0.0019099235069006681
2023-01-23 03:43:26.666495: step: 432/533, loss: 8.049011375987902e-05
2023-01-23 03:43:27.843280: step: 436/533, loss: 0.00030984877957962453
2023-01-23 03:43:28.976861: step: 440/533, loss: 0.0001843452628236264
2023-01-23 03:43:30.140664: step: 444/533, loss: 2.2602082026423886e-05
2023-01-23 03:43:31.315727: step: 448/533, loss: 5.917549424339086e-05
2023-01-23 03:43:32.519523: step: 452/533, loss: 0.0009412765502929688
2023-01-23 03:43:33.706959: step: 456/533, loss: 0.0033445358276367188
2023-01-23 03:43:34.917685: step: 460/533, loss: 0.020433617755770683
2023-01-23 03:43:36.117737: step: 464/533, loss: 0.004730605985969305
2023-01-23 03:43:37.299656: step: 468/533, loss: 0.0006296157953329384
2023-01-23 03:43:38.447914: step: 472/533, loss: 0.00010242462303722277
2023-01-23 03:43:39.605200: step: 476/533, loss: 0.030965041369199753
2023-01-23 03:43:40.784084: step: 480/533, loss: 0.0010493517620489001
2023-01-23 03:43:41.993378: step: 484/533, loss: 0.0013270378112792969
2023-01-23 03:43:43.153873: step: 488/533, loss: 0.00020847321138717234
2023-01-23 03:43:44.332207: step: 492/533, loss: 0.0003181457577738911
2023-01-23 03:43:45.543971: step: 496/533, loss: 6.771087555534905e-06
2023-01-23 03:43:46.700073: step: 500/533, loss: 0.0013645172584801912
2023-01-23 03:43:47.884446: step: 504/533, loss: 0.02997570112347603
2023-01-23 03:43:49.063453: step: 508/533, loss: 0.028525162488222122
2023-01-23 03:43:50.242794: step: 512/533, loss: 3.237724376958795e-05
2023-01-23 03:43:51.421211: step: 516/533, loss: 7.62939453125e-06
2023-01-23 03:43:52.629051: step: 520/533, loss: 0.7232208251953125
2023-01-23 03:43:53.835920: step: 524/533, loss: 0.14858703315258026
2023-01-23 03:43:54.997798: step: 528/533, loss: 0.03774090111255646
2023-01-23 03:43:56.199054: step: 532/533, loss: 0.0007862091297283769
2023-01-23 03:43:57.379907: step: 536/533, loss: 0.05137762799859047
2023-01-23 03:43:58.524438: step: 540/533, loss: 0.0007997513166628778
2023-01-23 03:43:59.723926: step: 544/533, loss: 0.026436423882842064
2023-01-23 03:44:00.904952: step: 548/533, loss: 0.0015860558487474918
2023-01-23 03:44:02.109342: step: 552/533, loss: 0.038579367101192474
2023-01-23 03:44:03.267583: step: 556/533, loss: 0.00045642853365279734
2023-01-23 03:44:04.452415: step: 560/533, loss: 0.003823947859928012
2023-01-23 03:44:05.641670: step: 564/533, loss: 0.00037822723970748484
2023-01-23 03:44:06.798700: step: 568/533, loss: 0.1228710189461708
2023-01-23 03:44:07.961810: step: 572/533, loss: 0.061507608741521835
2023-01-23 03:44:09.117533: step: 576/533, loss: 0.14891338348388672
2023-01-23 03:44:10.273369: step: 580/533, loss: 8.37326078908518e-05
2023-01-23 03:44:11.488151: step: 584/533, loss: 0.016631508246064186
2023-01-23 03:44:12.665220: step: 588/533, loss: 0.01926266774535179
2023-01-23 03:44:13.833917: step: 592/533, loss: 0.004851913545280695
2023-01-23 03:44:15.029730: step: 596/533, loss: 0.06506597995758057
2023-01-23 03:44:16.205773: step: 600/533, loss: 0.0013857842423021793
2023-01-23 03:44:17.350067: step: 604/533, loss: 0.051195334643125534
2023-01-23 03:44:18.532217: step: 608/533, loss: 0.00739550543949008
2023-01-23 03:44:19.746921: step: 612/533, loss: 0.13472633063793182
2023-01-23 03:44:20.933448: step: 616/533, loss: 0.014884376898407936
2023-01-23 03:44:22.081912: step: 620/533, loss: 0.027770044282078743
2023-01-23 03:44:23.241032: step: 624/533, loss: 0.008984469808638096
2023-01-23 03:44:24.396990: step: 628/533, loss: 0.0031900405883789062
2023-01-23 03:44:25.553232: step: 632/533, loss: 0.0038488388527184725
2023-01-23 03:44:26.766645: step: 636/533, loss: 0.06429142504930496
2023-01-23 03:44:27.963978: step: 640/533, loss: 0.024149131029844284
2023-01-23 03:44:29.121148: step: 644/533, loss: 5.14984139954322e-06
2023-01-23 03:44:30.299087: step: 648/533, loss: 0.010907459072768688
2023-01-23 03:44:31.493974: step: 652/533, loss: 0.00024356841458939016
2023-01-23 03:44:32.642918: step: 656/533, loss: 0.00762863177806139
2023-01-23 03:44:33.817255: step: 660/533, loss: 4.272460864740424e-05
2023-01-23 03:44:34.992746: step: 664/533, loss: 0.0015058518620207906
2023-01-23 03:44:36.225212: step: 668/533, loss: 1.3703391551971436
2023-01-23 03:44:37.393566: step: 672/533, loss: 0.002596283098682761
2023-01-23 03:44:38.574843: step: 676/533, loss: 0.0028486251831054688
2023-01-23 03:44:39.772702: step: 680/533, loss: 0.03347458690404892
2023-01-23 03:44:40.955314: step: 684/533, loss: 0.006866455078125
2023-01-23 03:44:42.117175: step: 688/533, loss: 0.012720465660095215
2023-01-23 03:44:43.293297: step: 692/533, loss: 0.008841896429657936
2023-01-23 03:44:44.525272: step: 696/533, loss: 0.001014661742374301
2023-01-23 03:44:45.689990: step: 700/533, loss: 0.0015799523098394275
2023-01-23 03:44:46.877234: step: 704/533, loss: 0.00843434315174818
2023-01-23 03:44:48.025127: step: 708/533, loss: 0.02506399154663086
2023-01-23 03:44:49.222302: step: 712/533, loss: 0.00012054442777298391
2023-01-23 03:44:50.396959: step: 716/533, loss: -1.7166130419354886e-06
2023-01-23 03:44:51.561406: step: 720/533, loss: 0.0081055648624897
2023-01-23 03:44:52.684076: step: 724/533, loss: 0.004156970884650946
2023-01-23 03:44:53.871161: step: 728/533, loss: 0.01972188986837864
2023-01-23 03:44:55.058835: step: 732/533, loss: 0.025399019941687584
2023-01-23 03:44:56.225211: step: 736/533, loss: 0.01169891282916069
2023-01-23 03:44:57.419325: step: 740/533, loss: 0.042191121727228165
2023-01-23 03:44:58.563695: step: 744/533, loss: 0.0007309913635253906
2023-01-23 03:44:59.776397: step: 748/533, loss: 0.0024110793601721525
2023-01-23 03:45:00.978796: step: 752/533, loss: 0.015259361825883389
2023-01-23 03:45:02.124244: step: 756/533, loss: 0.002070522168651223
2023-01-23 03:45:03.269825: step: 760/533, loss: 0.008665180765092373
2023-01-23 03:45:04.464137: step: 764/533, loss: 0.0001693725644145161
2023-01-23 03:45:05.620764: step: 768/533, loss: 0.02346820756793022
2023-01-23 03:45:06.787200: step: 772/533, loss: 0.0014692307449877262
2023-01-23 03:45:07.960161: step: 776/533, loss: 0.0006662369123660028
2023-01-23 03:45:09.117904: step: 780/533, loss: 0.0003328800085000694
2023-01-23 03:45:10.258696: step: 784/533, loss: 0.0017113685607910156
2023-01-23 03:45:11.440245: step: 788/533, loss: 0.009048175998032093
2023-01-23 03:45:12.607820: step: 792/533, loss: 0.00018091201491188258
2023-01-23 03:45:13.802786: step: 796/533, loss: 0.0008546829340048134
2023-01-23 03:45:14.950372: step: 800/533, loss: 0.005116653628647327
2023-01-23 03:45:16.135430: step: 804/533, loss: 0.011718940921127796
2023-01-23 03:45:17.315964: step: 808/533, loss: 0.0022395611740648746
2023-01-23 03:45:18.501312: step: 812/533, loss: 0.00012645722017623484
2023-01-23 03:45:19.685057: step: 816/533, loss: 0.0007635116344317794
2023-01-23 03:45:20.872010: step: 820/533, loss: 0.011646557599306107
2023-01-23 03:45:22.042549: step: 824/533, loss: 0.00012969970703125
2023-01-23 03:45:23.234350: step: 828/533, loss: 0.032987214624881744
2023-01-23 03:45:24.440350: step: 832/533, loss: 0.0005928516620770097
2023-01-23 03:45:25.652758: step: 836/533, loss: 0.021815728396177292
2023-01-23 03:45:26.800328: step: 840/533, loss: 0.00014200211444403976
2023-01-23 03:45:27.943308: step: 844/533, loss: 0.0036428452003747225
2023-01-23 03:45:29.104633: step: 848/533, loss: 0.0002111435023834929
2023-01-23 03:45:30.340867: step: 852/533, loss: 0.03106403537094593
2023-01-23 03:45:31.529408: step: 856/533, loss: 0.0004092007875442505
2023-01-23 03:45:32.702120: step: 860/533, loss: 0.015527820214629173
2023-01-23 03:45:33.882396: step: 864/533, loss: 0.021834183484315872
2023-01-23 03:45:35.027451: step: 868/533, loss: 0.005451297853142023
2023-01-23 03:45:36.186858: step: 872/533, loss: 0.0022825240157544613
2023-01-23 03:45:37.341288: step: 876/533, loss: 0.0010254860389977694
2023-01-23 03:45:38.533310: step: 880/533, loss: 0.004307175055146217
2023-01-23 03:45:39.754883: step: 884/533, loss: 0.030779076740145683
2023-01-23 03:45:40.930036: step: 888/533, loss: 5.7888031733455136e-05
2023-01-23 03:45:42.081897: step: 892/533, loss: 0.00014953613572288305
2023-01-23 03:45:43.279756: step: 896/533, loss: 0.0017480850219726562
2023-01-23 03:45:44.461809: step: 900/533, loss: 0.016500188037753105
2023-01-23 03:45:45.643948: step: 904/533, loss: 0.0003707885625772178
2023-01-23 03:45:46.838242: step: 908/533, loss: 0.025084495544433594
2023-01-23 03:45:48.025587: step: 912/533, loss: 0.00115375523455441
2023-01-23 03:45:49.191770: step: 916/533, loss: 0.03572063520550728
2023-01-23 03:45:50.335361: step: 920/533, loss: 4.997253563487902e-05
2023-01-23 03:45:51.491979: step: 924/533, loss: 0.0014259337913244963
2023-01-23 03:45:52.667291: step: 928/533, loss: 0.0014012337196618319
2023-01-23 03:45:53.811078: step: 932/533, loss: 0.05708455666899681
2023-01-23 03:45:55.047796: step: 936/533, loss: 0.020565509796142578
2023-01-23 03:45:56.247183: step: 940/533, loss: 0.24678516387939453
2023-01-23 03:45:57.433591: step: 944/533, loss: 0.0027359009254723787
2023-01-23 03:45:58.589548: step: 948/533, loss: 0.0003315925714559853
2023-01-23 03:45:59.764363: step: 952/533, loss: 0.00045986176701262593
2023-01-23 03:46:00.933396: step: 956/533, loss: 0.0006501436000689864
2023-01-23 03:46:02.135761: step: 960/533, loss: 2.441406286379788e-05
2023-01-23 03:46:03.341664: step: 964/533, loss: 0.0015298009384423494
2023-01-23 03:46:04.470851: step: 968/533, loss: 3.24249276673072e-06
2023-01-23 03:46:05.644389: step: 972/533, loss: 0.21640262007713318
2023-01-23 03:46:06.845240: step: 976/533, loss: 0.036772727966308594
2023-01-23 03:46:08.040140: step: 980/533, loss: 0.06259270012378693
2023-01-23 03:46:09.216243: step: 984/533, loss: 6.637573096668348e-05
2023-01-23 03:46:10.399254: step: 988/533, loss: 0.002273750491440296
2023-01-23 03:46:11.571569: step: 992/533, loss: 0.0649871826171875
2023-01-23 03:46:12.722961: step: 996/533, loss: 0.0004590034659486264
2023-01-23 03:46:13.978606: step: 1000/533, loss: 0.007580948062241077
2023-01-23 03:46:15.117754: step: 1004/533, loss: 0.00927047710865736
2023-01-23 03:46:16.285303: step: 1008/533, loss: 0.05645904690027237
2023-01-23 03:46:17.485239: step: 1012/533, loss: 0.01929454877972603
2023-01-23 03:46:18.683647: step: 1016/533, loss: 2.7132035029353574e-05
2023-01-23 03:46:19.851600: step: 1020/533, loss: 0.056095123291015625
2023-01-23 03:46:21.024765: step: 1024/533, loss: 0.0004031181160826236
2023-01-23 03:46:22.207173: step: 1028/533, loss: 0.0003883361932821572
2023-01-23 03:46:23.355384: step: 1032/533, loss: 0.2314375787973404
2023-01-23 03:46:24.538634: step: 1036/533, loss: 0.021697998046875
2023-01-23 03:46:25.739199: step: 1040/533, loss: 0.008711433969438076
2023-01-23 03:46:26.932954: step: 1044/533, loss: 0.0008431434980593622
2023-01-23 03:46:28.087476: step: 1048/533, loss: 0.00032129290048033
2023-01-23 03:46:29.254318: step: 1052/533, loss: 0.0010913849109783769
2023-01-23 03:46:30.398086: step: 1056/533, loss: 0.001083970069885254
2023-01-23 03:46:31.563406: step: 1060/533, loss: 0.2573177218437195
2023-01-23 03:46:32.712831: step: 1064/533, loss: 0.09269677102565765
2023-01-23 03:46:33.896380: step: 1068/533, loss: 0.05773629993200302
2023-01-23 03:46:35.008423: step: 1072/533, loss: 0.0183271411806345
2023-01-23 03:46:36.186262: step: 1076/533, loss: 0.006753826513886452
2023-01-23 03:46:37.377293: step: 1080/533, loss: 0.0029914856422692537
2023-01-23 03:46:38.585514: step: 1084/533, loss: 0.001609754515811801
2023-01-23 03:46:39.742755: step: 1088/533, loss: 0.004450416658073664
2023-01-23 03:46:40.918162: step: 1092/533, loss: 0.243892103433609
2023-01-23 03:46:42.062416: step: 1096/533, loss: 0.0043305871076881886
2023-01-23 03:46:43.208628: step: 1100/533, loss: 2.47955313170678e-06
2023-01-23 03:46:44.377129: step: 1104/533, loss: 0.010229015722870827
2023-01-23 03:46:45.549075: step: 1108/533, loss: 0.010856819339096546
2023-01-23 03:46:46.748911: step: 1112/533, loss: 0.05640153959393501
2023-01-23 03:46:47.894529: step: 1116/533, loss: 0.0008594513055868447
2023-01-23 03:46:49.047677: step: 1120/533, loss: 8.697509474586695e-05
2023-01-23 03:46:50.239536: step: 1124/533, loss: 0.00024261475482489914
2023-01-23 03:46:51.457997: step: 1128/533, loss: 0.0005855560302734375
2023-01-23 03:46:52.573399: step: 1132/533, loss: 0.4725748896598816
2023-01-23 03:46:53.770374: step: 1136/533, loss: 0.0004037380567751825
2023-01-23 03:46:54.972872: step: 1140/533, loss: 0.003464603563770652
2023-01-23 03:46:56.131689: step: 1144/533, loss: 0.00033664703369140625
2023-01-23 03:46:57.337949: step: 1148/533, loss: 0.00016498565673828125
2023-01-23 03:46:58.539933: step: 1152/533, loss: 0.002050781389698386
2023-01-23 03:46:59.696514: step: 1156/533, loss: 0.002957296557724476
2023-01-23 03:47:00.894395: step: 1160/533, loss: 0.0021316527854651213
2023-01-23 03:47:02.085785: step: 1164/533, loss: 0.0026208877097815275
2023-01-23 03:47:03.242763: step: 1168/533, loss: 0.0025114058516919613
2023-01-23 03:47:04.435067: step: 1172/533, loss: 0.00016860962205100805
2023-01-23 03:47:05.587077: step: 1176/533, loss: 0.0015295027988031507
2023-01-23 03:47:06.788428: step: 1180/533, loss: 0.010804367251694202
2023-01-23 03:47:08.002524: step: 1184/533, loss: 0.005790138151496649
2023-01-23 03:47:09.145078: step: 1188/533, loss: 0.05527706444263458
2023-01-23 03:47:10.342491: step: 1192/533, loss: 0.0040986062958836555
2023-01-23 03:47:11.531578: step: 1196/533, loss: 0.4861486554145813
2023-01-23 03:47:12.730900: step: 1200/533, loss: 0.0005045891157351434
2023-01-23 03:47:13.959548: step: 1204/533, loss: 0.00016527176194358617
2023-01-23 03:47:15.139768: step: 1208/533, loss: 0.00028266909066587687
2023-01-23 03:47:16.309500: step: 1212/533, loss: 0.0005316734313964844
2023-01-23 03:47:17.502278: step: 1216/533, loss: 0.003757762722671032
2023-01-23 03:47:18.652983: step: 1220/533, loss: 0.00011310577247058973
2023-01-23 03:47:19.885039: step: 1224/533, loss: 0.496656596660614
2023-01-23 03:47:21.075519: step: 1228/533, loss: 0.02617950551211834
2023-01-23 03:47:22.247147: step: 1232/533, loss: 0.00017681121244095266
2023-01-23 03:47:23.419111: step: 1236/533, loss: 0.0004814147832803428
2023-01-23 03:47:24.644406: step: 1240/533, loss: 0.02547617070376873
2023-01-23 03:47:25.788033: step: 1244/533, loss: 0.009776783175766468
2023-01-23 03:47:26.903757: step: 1248/533, loss: 6.217956251930445e-05
2023-01-23 03:47:28.160028: step: 1252/533, loss: 4.028190612792969
2023-01-23 03:47:29.335100: step: 1256/533, loss: 0.07298431545495987
2023-01-23 03:47:30.544135: step: 1260/533, loss: 0.0029594420921057463
2023-01-23 03:47:31.740359: step: 1264/533, loss: 0.000111627574369777
2023-01-23 03:47:32.914621: step: 1268/533, loss: 0.014233589172363281
2023-01-23 03:47:34.073918: step: 1272/533, loss: 3.4168362617492676e-05
2023-01-23 03:47:35.225618: step: 1276/533, loss: 0.00037889485247433186
2023-01-23 03:47:36.407906: step: 1280/533, loss: 0.057022858411073685
2023-01-23 03:47:37.600619: step: 1284/533, loss: 0.02221984975039959
2023-01-23 03:47:38.774217: step: 1288/533, loss: 0.0013111113803461194
2023-01-23 03:47:39.967109: step: 1292/533, loss: 0.07339143753051758
2023-01-23 03:47:41.121895: step: 1296/533, loss: 0.00025682448176667094
2023-01-23 03:47:42.280489: step: 1300/533, loss: 0.0005340576171875
2023-01-23 03:47:43.467183: step: 1304/533, loss: 0.008294487372040749
2023-01-23 03:47:44.646377: step: 1308/533, loss: 0.00045070648775435984
2023-01-23 03:47:45.818460: step: 1312/533, loss: 9.918212890625e-05
2023-01-23 03:47:47.015626: step: 1316/533, loss: 0.004061460494995117
2023-01-23 03:47:48.208503: step: 1320/533, loss: 0.002850818680599332
2023-01-23 03:47:49.380947: step: 1324/533, loss: 0.021628951653838158
2023-01-23 03:47:50.549300: step: 1328/533, loss: 0.04279213026165962
2023-01-23 03:47:51.685439: step: 1332/533, loss: 0.0003364562871865928
2023-01-23 03:47:52.865174: step: 1336/533, loss: 0.08291897922754288
2023-01-23 03:47:54.018007: step: 1340/533, loss: 3.271103196311742e-05
2023-01-23 03:47:55.198756: step: 1344/533, loss: 4.444122168933973e-05
2023-01-23 03:47:56.325312: step: 1348/533, loss: 0.0006788730970583856
2023-01-23 03:47:57.504891: step: 1352/533, loss: 0.013336753472685814
2023-01-23 03:47:58.675587: step: 1356/533, loss: 0.0570068359375
2023-01-23 03:47:59.814913: step: 1360/533, loss: 3.561973790056072e-05
2023-01-23 03:48:01.050386: step: 1364/533, loss: 0.013704109936952591
2023-01-23 03:48:02.254979: step: 1368/533, loss: 0.0008209228981286287
2023-01-23 03:48:03.438020: step: 1372/533, loss: 0.08327322453260422
2023-01-23 03:48:04.622720: step: 1376/533, loss: 0.0008445740095339715
2023-01-23 03:48:05.783456: step: 1380/533, loss: 0.05320386588573456
2023-01-23 03:48:06.956891: step: 1384/533, loss: 0.002938842633739114
2023-01-23 03:48:08.135596: step: 1388/533, loss: 6.84738188283518e-05
2023-01-23 03:48:09.281755: step: 1392/533, loss: 0.00256004324182868
2023-01-23 03:48:10.447531: step: 1396/533, loss: 3.552436828613281e-05
2023-01-23 03:48:11.608252: step: 1400/533, loss: 0.00030241013155318797
2023-01-23 03:48:12.754352: step: 1404/533, loss: 0.06723956763744354
2023-01-23 03:48:13.917374: step: 1408/533, loss: 0.0002961158752441406
2023-01-23 03:48:15.117410: step: 1412/533, loss: 0.027453135699033737
2023-01-23 03:48:16.281280: step: 1416/533, loss: 0.0010979652870446444
2023-01-23 03:48:17.439137: step: 1420/533, loss: 0.00952377263456583
2023-01-23 03:48:18.604691: step: 1424/533, loss: 0.0015462875599041581
2023-01-23 03:48:19.776111: step: 1428/533, loss: 0.008257769979536533
2023-01-23 03:48:20.961141: step: 1432/533, loss: 9.765625145519152e-05
2023-01-23 03:48:22.162696: step: 1436/533, loss: 8.239746239269152e-05
2023-01-23 03:48:23.295924: step: 1440/533, loss: 0.00243780598975718
2023-01-23 03:48:24.465778: step: 1444/533, loss: 0.022835826501250267
2023-01-23 03:48:25.645074: step: 1448/533, loss: 0.00011386872211005539
2023-01-23 03:48:26.814931: step: 1452/533, loss: 0.0006555557483807206
2023-01-23 03:48:27.950465: step: 1456/533, loss: 0.004465865902602673
2023-01-23 03:48:29.116741: step: 1460/533, loss: 0.001409387681633234
2023-01-23 03:48:30.287375: step: 1464/533, loss: 0.0009399414411745965
2023-01-23 03:48:31.458357: step: 1468/533, loss: 0.0008329391130246222
2023-01-23 03:48:32.617910: step: 1472/533, loss: 0.0006933696568012238
2023-01-23 03:48:33.790894: step: 1476/533, loss: 0.005269050598144531
2023-01-23 03:48:34.955359: step: 1480/533, loss: 0.014586448669433594
2023-01-23 03:48:36.098255: step: 1484/533, loss: 0.0021942139137536287
2023-01-23 03:48:37.260913: step: 1488/533, loss: 1.583099401614163e-05
2023-01-23 03:48:38.431355: step: 1492/533, loss: 0.00037889479426667094
2023-01-23 03:48:39.593773: step: 1496/533, loss: 0.01611328125
2023-01-23 03:48:40.784686: step: 1500/533, loss: 0.00028998852940276265
2023-01-23 03:48:41.959761: step: 1504/533, loss: 0.003301429795101285
2023-01-23 03:48:43.137923: step: 1508/533, loss: 0.0011800765059888363
2023-01-23 03:48:44.284336: step: 1512/533, loss: 0.0052337646484375
2023-01-23 03:48:45.488781: step: 1516/533, loss: 0.004521846771240234
2023-01-23 03:48:46.672048: step: 1520/533, loss: 0.0034716606605798006
2023-01-23 03:48:47.833384: step: 1524/533, loss: 7.21931501175277e-05
2023-01-23 03:48:49.043387: step: 1528/533, loss: 0.0005996703985147178
2023-01-23 03:48:50.230148: step: 1532/533, loss: 0.004365730099380016
2023-01-23 03:48:51.387951: step: 1536/533, loss: 0.0011579514248296618
2023-01-23 03:48:52.549843: step: 1540/533, loss: 4.2629242670955136e-05
2023-01-23 03:48:53.750137: step: 1544/533, loss: 0.006268214900046587
2023-01-23 03:48:54.895738: step: 1548/533, loss: 1.5926361811580136e-05
2023-01-23 03:48:56.045095: step: 1552/533, loss: 0.0029651641380041838
2023-01-23 03:48:57.261235: step: 1556/533, loss: 0.0060555459931492805
2023-01-23 03:48:58.432761: step: 1560/533, loss: 0.012828826904296875
2023-01-23 03:48:59.589080: step: 1564/533, loss: 0.017372703179717064
2023-01-23 03:49:00.781417: step: 1568/533, loss: 0.0002750396670307964
2023-01-23 03:49:01.934158: step: 1572/533, loss: 6.370543997036293e-05
2023-01-23 03:49:03.095090: step: 1576/533, loss: 0.004369258880615234
2023-01-23 03:49:04.272575: step: 1580/533, loss: 0.025567438453435898
2023-01-23 03:49:05.449722: step: 1584/533, loss: 0.009633255191147327
2023-01-23 03:49:06.669923: step: 1588/533, loss: 0.0020591735374182463
2023-01-23 03:49:07.843124: step: 1592/533, loss: 0.011599158868193626
2023-01-23 03:49:09.050991: step: 1596/533, loss: 0.0035119056701660156
2023-01-23 03:49:10.173366: step: 1600/533, loss: 0.00023536682419944555
2023-01-23 03:49:11.416916: step: 1604/533, loss: 0.04906482622027397
2023-01-23 03:49:12.594643: step: 1608/533, loss: 0.00012674331082962453
2023-01-23 03:49:13.817533: step: 1612/533, loss: 0.0005786895635537803
2023-01-23 03:49:14.976677: step: 1616/533, loss: 0.008405876345932484
2023-01-23 03:49:16.157331: step: 1620/533, loss: 0.0001960754452738911
2023-01-23 03:49:17.321284: step: 1624/533, loss: 3.0040740966796875e-05
2023-01-23 03:49:18.513063: step: 1628/533, loss: 0.0006561279878951609
2023-01-23 03:49:19.682840: step: 1632/533, loss: 0.0015196801396086812
2023-01-23 03:49:20.856695: step: 1636/533, loss: 0.04878272861242294
2023-01-23 03:49:22.003834: step: 1640/533, loss: 0.002242469694465399
2023-01-23 03:49:23.184341: step: 1644/533, loss: 1.5163421267061494e-05
2023-01-23 03:49:24.382252: step: 1648/533, loss: 0.05905933305621147
2023-01-23 03:49:25.594505: step: 1652/533, loss: 0.009740972891449928
2023-01-23 03:49:26.773876: step: 1656/533, loss: 0.06339530646800995
2023-01-23 03:49:27.902520: step: 1660/533, loss: 0.023625755682587624
2023-01-23 03:49:29.117636: step: 1664/533, loss: 0.0003610610729083419
2023-01-23 03:49:30.324790: step: 1668/533, loss: 0.004610252566635609
2023-01-23 03:49:31.479125: step: 1672/533, loss: 0.02607612870633602
2023-01-23 03:49:32.630450: step: 1676/533, loss: 0.00010704994929255918
2023-01-23 03:49:33.772186: step: 1680/533, loss: 0.0007863044738769531
2023-01-23 03:49:34.934950: step: 1684/533, loss: 0.0424046516418457
2023-01-23 03:49:36.112515: step: 1688/533, loss: 0.0006410598871298134
2023-01-23 03:49:37.298377: step: 1692/533, loss: 0.001499176025390625
2023-01-23 03:49:38.498718: step: 1696/533, loss: 0.0027582645416259766
2023-01-23 03:49:39.651020: step: 1700/533, loss: 1.7452239262638614e-05
2023-01-23 03:49:40.850620: step: 1704/533, loss: 0.03904452174901962
2023-01-23 03:49:41.996468: step: 1708/533, loss: 0.00035881996154785156
2023-01-23 03:49:43.163804: step: 1712/533, loss: 0.0007788657676428556
2023-01-23 03:49:44.302405: step: 1716/533, loss: 0.014426421374082565
2023-01-23 03:49:45.428746: step: 1720/533, loss: 1.7452239262638614e-05
2023-01-23 03:49:46.587575: step: 1724/533, loss: 0.00018796921358443797
2023-01-23 03:49:47.710531: step: 1728/533, loss: 0.0021246911492198706
2023-01-23 03:49:48.865930: step: 1732/533, loss: 2.722740282479208e-05
2023-01-23 03:49:50.024828: step: 1736/533, loss: 0.0004248619079589844
2023-01-23 03:49:51.194731: step: 1740/533, loss: 0.00027742385282181203
2023-01-23 03:49:52.321474: step: 1744/533, loss: 0.013812637887895107
2023-01-23 03:49:53.462409: step: 1748/533, loss: 0.000461387651739642
2023-01-23 03:49:54.687741: step: 1752/533, loss: 0.050911761820316315
2023-01-23 03:49:55.885131: step: 1756/533, loss: 0.0004821777401957661
2023-01-23 03:49:57.051482: step: 1760/533, loss: 0.14102792739868164
2023-01-23 03:49:58.184476: step: 1764/533, loss: 0.001533126924186945
2023-01-23 03:49:59.339073: step: 1768/533, loss: 0.028049850836396217
2023-01-23 03:50:00.533450: step: 1772/533, loss: 0.030653953552246094
2023-01-23 03:50:01.687426: step: 1776/533, loss: 3.8719179428881034e-05
2023-01-23 03:50:02.880349: step: 1780/533, loss: 0.005081558134406805
2023-01-23 03:50:04.003562: step: 1784/533, loss: 5.602836608886719e-05
2023-01-23 03:50:05.178537: step: 1788/533, loss: 0.0060096741653978825
2023-01-23 03:50:06.344014: step: 1792/533, loss: 3.247260974603705e-05
2023-01-23 03:50:07.546667: step: 1796/533, loss: 0.0004333496035542339
2023-01-23 03:50:08.720927: step: 1800/533, loss: 0.00029277801513671875
2023-01-23 03:50:09.917119: step: 1804/533, loss: 0.00944442767649889
2023-01-23 03:50:11.126957: step: 1808/533, loss: 0.13763079047203064
2023-01-23 03:50:12.291848: step: 1812/533, loss: 0.028946973383426666
2023-01-23 03:50:13.433301: step: 1816/533, loss: 0.002588272327557206
2023-01-23 03:50:14.616871: step: 1820/533, loss: 0.0024524687323719263
2023-01-23 03:50:15.786499: step: 1824/533, loss: 0.02628307417035103
2023-01-23 03:50:16.934705: step: 1828/533, loss: 0.0023279190063476562
2023-01-23 03:50:18.095853: step: 1832/533, loss: 0.012312699109315872
2023-01-23 03:50:19.253222: step: 1836/533, loss: 0.04829578474164009
2023-01-23 03:50:20.438216: step: 1840/533, loss: 0.09863433241844177
2023-01-23 03:50:21.609550: step: 1844/533, loss: 0.031348228454589844
2023-01-23 03:50:22.773124: step: 1848/533, loss: 0.00034146307734772563
2023-01-23 03:50:23.927448: step: 1852/533, loss: 0.01343150157481432
2023-01-23 03:50:25.063210: step: 1856/533, loss: 3.7813188100699335e-05
2023-01-23 03:50:26.228834: step: 1860/533, loss: 0.0021717071067541838
2023-01-23 03:50:27.406131: step: 1864/533, loss: 0.01147542055696249
2023-01-23 03:50:28.606656: step: 1868/533, loss: 1.0278065204620361
2023-01-23 03:50:29.755823: step: 1872/533, loss: 0.0061668395064771175
2023-01-23 03:50:30.947050: step: 1876/533, loss: 0.044216301292181015
2023-01-23 03:50:32.101478: step: 1880/533, loss: 0.016011809930205345
2023-01-23 03:50:33.295672: step: 1884/533, loss: 0.0029096603393554688
2023-01-23 03:50:34.461259: step: 1888/533, loss: 0.02132740058004856
2023-01-23 03:50:35.620477: step: 1892/533, loss: 0.0008987426408566535
2023-01-23 03:50:36.790333: step: 1896/533, loss: 0.004156399052590132
2023-01-23 03:50:37.962161: step: 1900/533, loss: 0.00032887462293729186
2023-01-23 03:50:39.067214: step: 1904/533, loss: 1.792907642084174e-05
2023-01-23 03:50:40.259445: step: 1908/533, loss: 0.012526893988251686
2023-01-23 03:50:41.461763: step: 1912/533, loss: 0.031160498037934303
2023-01-23 03:50:42.645053: step: 1916/533, loss: 0.014987754635512829
2023-01-23 03:50:43.879621: step: 1920/533, loss: 0.11016568541526794
2023-01-23 03:50:45.052571: step: 1924/533, loss: 0.004780960269272327
2023-01-23 03:50:46.211449: step: 1928/533, loss: 0.008588695898652077
2023-01-23 03:50:47.390488: step: 1932/533, loss: 0.002572488971054554
2023-01-23 03:50:48.549714: step: 1936/533, loss: 0.008165550418198109
2023-01-23 03:50:49.775643: step: 1940/533, loss: 0.026792287826538086
2023-01-23 03:50:50.942700: step: 1944/533, loss: 0.00024280548677779734
2023-01-23 03:50:52.106822: step: 1948/533, loss: 0.000796413398347795
2023-01-23 03:50:53.318183: step: 1952/533, loss: 0.0007739067077636719
2023-01-23 03:50:54.480352: step: 1956/533, loss: 0.01584186591207981
2023-01-23 03:50:55.713101: step: 1960/533, loss: 0.01906299591064453
2023-01-23 03:50:56.878098: step: 1964/533, loss: 0.001792526338249445
2023-01-23 03:50:58.047222: step: 1968/533, loss: 0.0002571106015238911
2023-01-23 03:50:59.239388: step: 1972/533, loss: 0.005412483587861061
2023-01-23 03:51:00.427500: step: 1976/533, loss: 0.027904702350497246
2023-01-23 03:51:01.637146: step: 1980/533, loss: 0.0051780701614916325
2023-01-23 03:51:02.873167: step: 1984/533, loss: 0.0005664110649377108
2023-01-23 03:51:04.057399: step: 1988/533, loss: 0.027359582483768463
2023-01-23 03:51:05.245888: step: 1992/533, loss: 0.06540117412805557
2023-01-23 03:51:06.447929: step: 1996/533, loss: 7.162094698287547e-05
2023-01-23 03:51:07.617657: step: 2000/533, loss: 4.243850980856223e-06
2023-01-23 03:51:08.848158: step: 2004/533, loss: 0.5318679213523865
2023-01-23 03:51:10.049894: step: 2008/533, loss: 0.45101621747016907
2023-01-23 03:51:11.212317: step: 2012/533, loss: 0.00593195017427206
2023-01-23 03:51:12.365982: step: 2016/533, loss: 2.746581958490424e-05
2023-01-23 03:51:13.512138: step: 2020/533, loss: 0.01992168463766575
2023-01-23 03:51:14.715248: step: 2024/533, loss: 0.005261612124741077
2023-01-23 03:51:15.889866: step: 2028/533, loss: 0.0010038375621661544
2023-01-23 03:51:17.105931: step: 2032/533, loss: 0.006363296881318092
2023-01-23 03:51:18.280175: step: 2036/533, loss: 0.009067535400390625
2023-01-23 03:51:19.509487: step: 2040/533, loss: 0.015846826136112213
2023-01-23 03:51:20.691422: step: 2044/533, loss: 4.711151268566027e-05
2023-01-23 03:51:21.885024: step: 2048/533, loss: 0.005828666500747204
2023-01-23 03:51:23.070212: step: 2052/533, loss: 0.04320545122027397
2023-01-23 03:51:24.266200: step: 2056/533, loss: -4.38690176451928e-06
2023-01-23 03:51:25.445681: step: 2060/533, loss: 4.243851071805693e-05
2023-01-23 03:51:26.605795: step: 2064/533, loss: 0.044243812561035156
2023-01-23 03:51:27.758754: step: 2068/533, loss: 0.03879880905151367
2023-01-23 03:51:28.932928: step: 2072/533, loss: 0.7287365794181824
2023-01-23 03:51:30.080187: step: 2076/533, loss: 0.013099098578095436
2023-01-23 03:51:31.252127: step: 2080/533, loss: 0.00027809146558865905
2023-01-23 03:51:32.429251: step: 2084/533, loss: 6.961822691664565e-06
2023-01-23 03:51:33.574603: step: 2088/533, loss: 0.008771514520049095
2023-01-23 03:51:34.742225: step: 2092/533, loss: 0.0011700630420818925
2023-01-23 03:51:35.928322: step: 2096/533, loss: 0.006569195073097944
2023-01-23 03:51:37.080438: step: 2100/533, loss: 0.0061782835982739925
2023-01-23 03:51:38.318753: step: 2104/533, loss: 0.007445717230439186
2023-01-23 03:51:39.457932: step: 2108/533, loss: 0.024918079376220703
2023-01-23 03:51:40.655155: step: 2112/533, loss: 0.0028689862228929996
2023-01-23 03:51:41.799158: step: 2116/533, loss: 0.0009232998127117753
2023-01-23 03:51:42.960363: step: 2120/533, loss: 0.0002359390346100554
2023-01-23 03:51:44.137178: step: 2124/533, loss: 0.00056629185564816
2023-01-23 03:51:45.341153: step: 2128/533, loss: 0.00014734268188476562
2023-01-23 03:51:46.471302: step: 2132/533, loss: 0.0004146099090576172
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6143162393162394, 'r': 0.7656458055925432, 'f1': 0.6816834617664493}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6556870818322182, 'r': 0.8145780051150895, 'f1': 0.7265469061876247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.5411764705882353, 'r': 0.8518518518518519, 'f1': 0.6618705035971222}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.6590909090909091, 'r': 0.4603174603174603, 'f1': 0.5420560747663551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.43243243243243246, 'r': 0.4444444444444444, 'f1': 0.4383561643835616}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 24
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:52:27.703194: step: 4/533, loss: 0.0014982223510742188
2023-01-23 03:52:28.844913: step: 8/533, loss: 2.117157055181451e-05
2023-01-23 03:52:30.009425: step: 12/533, loss: 0.004729080013930798
2023-01-23 03:52:31.233141: step: 16/533, loss: 0.003379392670467496
2023-01-23 03:52:32.450716: step: 20/533, loss: 0.0043249609880149364
2023-01-23 03:52:33.606941: step: 24/533, loss: 0.010345363058149815
2023-01-23 03:52:34.734699: step: 28/533, loss: -5.7220458984375e-06
2023-01-23 03:52:35.901015: step: 32/533, loss: 0.018908215686678886
2023-01-23 03:52:37.077678: step: 36/533, loss: 0.006651115603744984
2023-01-23 03:52:38.240494: step: 40/533, loss: 5.321502612787299e-05
2023-01-23 03:52:39.432981: step: 44/533, loss: 0.0044120075181126595
2023-01-23 03:52:40.598826: step: 48/533, loss: 0.0025789260398596525
2023-01-23 03:52:41.790912: step: 52/533, loss: 0.0016567230923101306
2023-01-23 03:52:42.964315: step: 56/533, loss: 0.005040633957833052
2023-01-23 03:52:44.201384: step: 60/533, loss: 0.00017986298189498484
2023-01-23 03:52:45.403197: step: 64/533, loss: 0.021048355847597122
2023-01-23 03:52:46.595941: step: 68/533, loss: 3.9577484130859375e-05
2023-01-23 03:52:47.738557: step: 72/533, loss: 0.0019787789788097143
2023-01-23 03:52:48.881646: step: 76/533, loss: 0.0010746002662926912
2023-01-23 03:52:50.060478: step: 80/533, loss: 9.460449655307457e-05
2023-01-23 03:52:51.243883: step: 84/533, loss: 0.004900455474853516
2023-01-23 03:52:52.435376: step: 88/533, loss: 0.017937565222382545
2023-01-23 03:52:53.602722: step: 92/533, loss: 0.0011552810901775956
2023-01-23 03:52:54.884705: step: 96/533, loss: 3.490447852527723e-05
2023-01-23 03:52:56.033275: step: 100/533, loss: 0.00010614395432639867
2023-01-23 03:52:57.177525: step: 104/533, loss: 0.0002875328063964844
2023-01-23 03:52:58.330524: step: 108/533, loss: 0.004686927888542414
2023-01-23 03:52:59.514358: step: 112/533, loss: 5.145073009771295e-05
2023-01-23 03:53:00.677838: step: 116/533, loss: 0.0008823394891805947
2023-01-23 03:53:01.859020: step: 120/533, loss: 0.015026092529296875
2023-01-23 03:53:03.018794: step: 124/533, loss: 7.152557373046875e-06
2023-01-23 03:53:04.174199: step: 128/533, loss: 5.836486889165826e-05
2023-01-23 03:53:05.367966: step: 132/533, loss: 0.043589115142822266
2023-01-23 03:53:06.563912: step: 136/533, loss: 0.00158519740216434
2023-01-23 03:53:07.749393: step: 140/533, loss: 0.001020240830257535
2023-01-23 03:53:08.958132: step: 144/533, loss: 0.012314415536820889
2023-01-23 03:53:10.107237: step: 148/533, loss: 0.49116066098213196
2023-01-23 03:53:11.301312: step: 152/533, loss: 0.026417160406708717
2023-01-23 03:53:12.461229: step: 156/533, loss: 0.00011157989501953125
2023-01-23 03:53:13.666012: step: 160/533, loss: 0.009055137634277344
2023-01-23 03:53:14.827068: step: 164/533, loss: 0.0026679993607103825
2023-01-23 03:53:15.985226: step: 168/533, loss: 0.6604849100112915
2023-01-23 03:53:17.113541: step: 172/533, loss: 0.0007463455549441278
2023-01-23 03:53:18.276009: step: 176/533, loss: 0.18963924050331116
2023-01-23 03:53:19.454011: step: 180/533, loss: 0.0006026267656125128
2023-01-23 03:53:20.640374: step: 184/533, loss: 0.0003443718305788934
2023-01-23 03:53:21.793060: step: 188/533, loss: 0.002713107969611883
2023-01-23 03:53:22.956025: step: 192/533, loss: 0.07361268997192383
2023-01-23 03:53:24.114131: step: 196/533, loss: 0.2587224841117859
2023-01-23 03:53:25.268155: step: 200/533, loss: 0.010776519775390625
2023-01-23 03:53:26.417465: step: 204/533, loss: 0.0046325684525072575
2023-01-23 03:53:27.584745: step: 208/533, loss: -4.2915345943583816e-07
2023-01-23 03:53:28.767823: step: 212/533, loss: 0.0023481370881199837
2023-01-23 03:53:29.966583: step: 216/533, loss: 7.743835885776207e-05
2023-01-23 03:53:31.199249: step: 220/533, loss: 7.596016075694934e-05
2023-01-23 03:53:32.303355: step: 224/533, loss: 0.00010766983177745715
2023-01-23 03:53:33.501859: step: 228/533, loss: 0.001570892403833568
2023-01-23 03:53:34.680658: step: 232/533, loss: 0.00017271042452193797
2023-01-23 03:53:35.849530: step: 236/533, loss: 0.00013027191744185984
2023-01-23 03:53:37.009172: step: 240/533, loss: 0.0488218329846859
2023-01-23 03:53:38.214478: step: 244/533, loss: 0.17562231421470642
2023-01-23 03:53:39.403054: step: 248/533, loss: 0.0055484771728515625
2023-01-23 03:53:40.645256: step: 252/533, loss: 0.003929710481315851
2023-01-23 03:53:41.874880: step: 256/533, loss: 0.0005680083995684981
2023-01-23 03:53:43.021575: step: 260/533, loss: 0.00023746490478515625
2023-01-23 03:53:44.242495: step: 264/533, loss: 0.005959606263786554
2023-01-23 03:53:45.395982: step: 268/533, loss: 0.00901808775961399
2023-01-23 03:53:46.604136: step: 272/533, loss: 0.037245895713567734
2023-01-23 03:53:47.786541: step: 276/533, loss: 1.3065338862361386e-05
2023-01-23 03:53:48.953540: step: 280/533, loss: 0.00537528982385993
2023-01-23 03:53:50.151348: step: 284/533, loss: 0.0012947083450853825
2023-01-23 03:53:51.320392: step: 288/533, loss: 0.010526848025619984
2023-01-23 03:53:52.520957: step: 292/533, loss: 0.00020656586275435984
2023-01-23 03:53:53.726382: step: 296/533, loss: 0.0017289519309997559
2023-01-23 03:53:54.874698: step: 300/533, loss: 3.080368333030492e-05
2023-01-23 03:53:56.052995: step: 304/533, loss: 0.02760915830731392
2023-01-23 03:53:57.248976: step: 308/533, loss: 0.00186500558629632
2023-01-23 03:53:58.382599: step: 312/533, loss: 0.0007704735035076737
2023-01-23 03:53:59.603796: step: 316/533, loss: 0.00027847292949445546
2023-01-23 03:54:00.744096: step: 320/533, loss: 0.03551159054040909
2023-01-23 03:54:01.957207: step: 324/533, loss: 0.07000233978033066
2023-01-23 03:54:03.098822: step: 328/533, loss: 0.0018533708062022924
2023-01-23 03:54:04.290737: step: 332/533, loss: 5.9890749980695546e-05
2023-01-23 03:54:05.475620: step: 336/533, loss: 4.38690185546875e-05
2023-01-23 03:54:06.633929: step: 340/533, loss: 5.016326758777723e-05
2023-01-23 03:54:07.755395: step: 344/533, loss: 0.016464997082948685
2023-01-23 03:54:08.972845: step: 348/533, loss: 0.015217496082186699
2023-01-23 03:54:10.151857: step: 352/533, loss: 0.0009018898126669228
2023-01-23 03:54:11.354727: step: 356/533, loss: 0.00095028878422454
2023-01-23 03:54:12.509198: step: 360/533, loss: 0.004959774203598499
2023-01-23 03:54:13.709176: step: 364/533, loss: 0.0031316757667809725
2023-01-23 03:54:14.845225: step: 368/533, loss: 9.012222108140122e-06
2023-01-23 03:54:15.963468: step: 372/533, loss: 0.0005079269758425653
2023-01-23 03:54:17.146950: step: 376/533, loss: 0.027384473010897636
2023-01-23 03:54:18.318739: step: 380/533, loss: 0.0008356571197509766
2023-01-23 03:54:19.486470: step: 384/533, loss: 5.684867574018426e-05
2023-01-23 03:54:20.654157: step: 388/533, loss: 2.193450927734375e-05
2023-01-23 03:54:21.810514: step: 392/533, loss: 0.0004699706914834678
2023-01-23 03:54:22.969383: step: 396/533, loss: 0.040029145777225494
2023-01-23 03:54:24.147749: step: 400/533, loss: 4.5490265620173886e-05
2023-01-23 03:54:25.291985: step: 404/533, loss: 0.017969371750950813
2023-01-23 03:54:26.461342: step: 408/533, loss: 0.0003772735653910786
2023-01-23 03:54:27.639303: step: 412/533, loss: 0.005244255065917969
2023-01-23 03:54:28.827105: step: 416/533, loss: 0.00014572143845725805
2023-01-23 03:54:30.006510: step: 420/533, loss: 0.0002780914364848286
2023-01-23 03:54:31.179485: step: 424/533, loss: 0.016827965155243874
2023-01-23 03:54:32.381990: step: 428/533, loss: 0.011587334796786308
2023-01-23 03:54:33.610497: step: 432/533, loss: 0.0019344331230968237
2023-01-23 03:54:34.815739: step: 436/533, loss: 0.17042502760887146
2023-01-23 03:54:36.009742: step: 440/533, loss: 0.00025768281193450093
2023-01-23 03:54:37.169089: step: 444/533, loss: 0.03531613573431969
2023-01-23 03:54:38.323284: step: 448/533, loss: 0.21429137885570526
2023-01-23 03:54:39.509626: step: 452/533, loss: 0.0023428918793797493
2023-01-23 03:54:40.680811: step: 456/533, loss: 0.003290414810180664
2023-01-23 03:54:41.865278: step: 460/533, loss: 0.037320517003536224
2023-01-23 03:54:43.098629: step: 464/533, loss: 0.044169191271066666
2023-01-23 03:54:44.284620: step: 468/533, loss: 0.002331733936443925
2023-01-23 03:54:45.488651: step: 472/533, loss: 0.03938446193933487
2023-01-23 03:54:46.699986: step: 476/533, loss: 0.002490520477294922
2023-01-23 03:54:47.872567: step: 480/533, loss: 0.005198383703827858
2023-01-23 03:54:49.053633: step: 484/533, loss: 0.0333745963871479
2023-01-23 03:54:50.183503: step: 488/533, loss: 3.290176664449973e-06
2023-01-23 03:54:51.342773: step: 492/533, loss: 0.0028717040549963713
2023-01-23 03:54:52.485620: step: 496/533, loss: 0.0167559627443552
2023-01-23 03:54:53.670610: step: 500/533, loss: 0.0025938034523278475
2023-01-23 03:54:54.871095: step: 504/533, loss: 0.05666179582476616
2023-01-23 03:54:56.073084: step: 508/533, loss: 0.006939411163330078
2023-01-23 03:54:57.242363: step: 512/533, loss: 0.00011105537851108238
2023-01-23 03:54:58.418981: step: 516/533, loss: 0.005019569303840399
2023-01-23 03:54:59.576156: step: 520/533, loss: 0.26031914353370667
2023-01-23 03:55:00.790118: step: 524/533, loss: -1.9073468138230965e-07
2023-01-23 03:55:01.982699: step: 528/533, loss: 1.5258789289873675e-06
2023-01-23 03:55:03.135644: step: 532/533, loss: 0.0020549774635583162
2023-01-23 03:55:04.300792: step: 536/533, loss: 7.629395258845761e-05
2023-01-23 03:55:05.441362: step: 540/533, loss: 0.002950048539787531
2023-01-23 03:55:06.590357: step: 544/533, loss: 0.08048410713672638
2023-01-23 03:55:07.777843: step: 548/533, loss: 0.00038318632869049907
2023-01-23 03:55:08.982464: step: 552/533, loss: 0.001358986017294228
2023-01-23 03:55:10.155397: step: 556/533, loss: -8.583068620282575e-07
2023-01-23 03:55:11.319242: step: 560/533, loss: 0.03986091539263725
2023-01-23 03:55:12.462510: step: 564/533, loss: 2.937316821771674e-05
2023-01-23 03:55:13.635699: step: 568/533, loss: 0.016434669494628906
2023-01-23 03:55:14.811027: step: 572/533, loss: 0.004740905947983265
2023-01-23 03:55:15.987615: step: 576/533, loss: 8.01086389401462e-06
2023-01-23 03:55:17.143835: step: 580/533, loss: 0.0002947807079181075
2023-01-23 03:55:18.334661: step: 584/533, loss: 0.01135711744427681
2023-01-23 03:55:19.508730: step: 588/533, loss: 2.448723554611206
2023-01-23 03:55:20.665822: step: 592/533, loss: 0.011686992831528187
2023-01-23 03:55:21.815219: step: 596/533, loss: 0.020264243707060814
2023-01-23 03:55:22.973630: step: 600/533, loss: 0.002237558364868164
2023-01-23 03:55:24.147420: step: 604/533, loss: 0.00012111663818359375
2023-01-23 03:55:25.365407: step: 608/533, loss: 0.002114773029461503
2023-01-23 03:55:26.591833: step: 612/533, loss: 4.38690185546875e-05
2023-01-23 03:55:27.772789: step: 616/533, loss: 0.0010427475208416581
2023-01-23 03:55:28.936949: step: 620/533, loss: 8.96453857421875e-05
2023-01-23 03:55:30.108029: step: 624/533, loss: 0.01702127419412136
2023-01-23 03:55:31.264654: step: 628/533, loss: 0.02596092037856579
2023-01-23 03:55:32.446640: step: 632/533, loss: 0.00015163421630859375
2023-01-23 03:55:33.612287: step: 636/533, loss: 0.0008037567604333162
2023-01-23 03:55:34.794447: step: 640/533, loss: 0.0015946388011798263
2023-01-23 03:55:35.940638: step: 644/533, loss: 7.033348083496094e-05
2023-01-23 03:55:37.144916: step: 648/533, loss: 0.0001253843365702778
2023-01-23 03:55:38.303219: step: 652/533, loss: 0.0597134605050087
2023-01-23 03:55:39.480816: step: 656/533, loss: 0.006297588814049959
2023-01-23 03:55:40.631215: step: 660/533, loss: 0.0007574081537313759
2023-01-23 03:55:41.786172: step: 664/533, loss: 0.033930208534002304
2023-01-23 03:55:42.959945: step: 668/533, loss: 7.286071922862902e-05
2023-01-23 03:55:44.123902: step: 672/533, loss: 0.026606369763612747
2023-01-23 03:55:45.290655: step: 676/533, loss: 7.286071922862902e-05
2023-01-23 03:55:46.482343: step: 680/533, loss: 0.0002827644348144531
2023-01-23 03:55:47.678878: step: 684/533, loss: 0.03730640560388565
2023-01-23 03:55:48.861581: step: 688/533, loss: 0.00074176792986691
2023-01-23 03:55:50.049700: step: 692/533, loss: 3.23295607813634e-05
2023-01-23 03:55:51.336737: step: 696/533, loss: 0.004149341490119696
2023-01-23 03:55:52.491948: step: 700/533, loss: 0.00017681121244095266
2023-01-23 03:55:53.670490: step: 704/533, loss: 0.0032795907463878393
2023-01-23 03:55:54.834285: step: 708/533, loss: 5.645752025884576e-05
2023-01-23 03:55:56.065593: step: 712/533, loss: 0.003503084182739258
2023-01-23 03:55:57.213968: step: 716/533, loss: 0.01647644303739071
2023-01-23 03:55:58.402226: step: 720/533, loss: 0.00027370452880859375
2023-01-23 03:55:59.559366: step: 724/533, loss: 0.00021629335242323577
2023-01-23 03:56:00.724105: step: 728/533, loss: 0.0017112254863604903
2023-01-23 03:56:01.913654: step: 732/533, loss: 0.0016474724980071187
2023-01-23 03:56:03.142745: step: 736/533, loss: 0.00041790009709075093
2023-01-23 03:56:04.351223: step: 740/533, loss: 0.006649160757660866
2023-01-23 03:56:05.492325: step: 744/533, loss: 4.353523036115803e-05
2023-01-23 03:56:06.673732: step: 748/533, loss: 0.021708868443965912
2023-01-23 03:56:07.836929: step: 752/533, loss: 0.005659389775246382
2023-01-23 03:56:08.986417: step: 756/533, loss: 0.0002841949462890625
2023-01-23 03:56:10.151400: step: 760/533, loss: 9.021758887683973e-05
2023-01-23 03:56:11.332296: step: 764/533, loss: 0.0033752440940588713
2023-01-23 03:56:12.503897: step: 768/533, loss: 0.008475112728774548
2023-01-23 03:56:13.723850: step: 772/533, loss: 0.05258503183722496
2023-01-23 03:56:14.902983: step: 776/533, loss: 0.018725205212831497
2023-01-23 03:56:16.048107: step: 780/533, loss: 0.0021941661834716797
2023-01-23 03:56:17.206162: step: 784/533, loss: 0.006798935122787952
2023-01-23 03:56:18.378781: step: 788/533, loss: 0.0001029014601954259
2023-01-23 03:56:19.640187: step: 792/533, loss: 0.14094963669776917
2023-01-23 03:56:20.799896: step: 796/533, loss: 0.00047369004460051656
2023-01-23 03:56:21.987514: step: 800/533, loss: 0.0003575325245037675
2023-01-23 03:56:23.180890: step: 804/533, loss: 0.0017885209526866674
2023-01-23 03:56:24.299704: step: 808/533, loss: 1.2683868590102065e-05
2023-01-23 03:56:25.513646: step: 812/533, loss: 1.4868286848068237
2023-01-23 03:56:26.656280: step: 816/533, loss: 0.009005260653793812
2023-01-23 03:56:27.847194: step: 820/533, loss: 9.269714064430445e-05
2023-01-23 03:56:28.999668: step: 824/533, loss: 0.01559295691549778
2023-01-23 03:56:30.167315: step: 828/533, loss: 0.0008003234979696572
2023-01-23 03:56:31.356861: step: 832/533, loss: 0.0001672744838288054
2023-01-23 03:56:32.541029: step: 836/533, loss: 0.01175780314952135
2023-01-23 03:56:33.671946: step: 840/533, loss: 0.016665076836943626
2023-01-23 03:56:34.865582: step: 844/533, loss: 8.711814734851941e-05
2023-01-23 03:56:36.031146: step: 848/533, loss: 0.03712005913257599
2023-01-23 03:56:37.197935: step: 852/533, loss: 0.0038500784430652857
2023-01-23 03:56:38.328746: step: 856/533, loss: 0.0008716583251953125
2023-01-23 03:56:39.477105: step: 860/533, loss: 6.67572021484375e-05
2023-01-23 03:56:40.661616: step: 864/533, loss: 0.039530184119939804
2023-01-23 03:56:41.840830: step: 868/533, loss: 0.006504202261567116
2023-01-23 03:56:43.011194: step: 872/533, loss: 1.0967254638671875e-05
2023-01-23 03:56:44.224693: step: 876/533, loss: 0.0012950897216796875
2023-01-23 03:56:45.383765: step: 880/533, loss: 0.0003065109485760331
2023-01-23 03:56:46.531876: step: 884/533, loss: 0.0003217697376385331
2023-01-23 03:56:47.718555: step: 888/533, loss: 0.03380412980914116
2023-01-23 03:56:48.880869: step: 892/533, loss: 0.004138564690947533
2023-01-23 03:56:50.085819: step: 896/533, loss: 0.013583374209702015
2023-01-23 03:56:51.263317: step: 900/533, loss: 0.0009149551624432206
2023-01-23 03:56:52.446928: step: 904/533, loss: 0.0003045797348022461
2023-01-23 03:56:53.626778: step: 908/533, loss: 8.759499178268015e-05
2023-01-23 03:56:54.793432: step: 912/533, loss: 0.0005922317504882812
2023-01-23 03:56:55.966701: step: 916/533, loss: 0.011572790332138538
2023-01-23 03:56:57.182148: step: 920/533, loss: 0.036786459386348724
2023-01-23 03:56:58.376760: step: 924/533, loss: 0.0003307342412881553
2023-01-23 03:56:59.577405: step: 928/533, loss: 0.0009876250987872481
2023-01-23 03:57:00.716796: step: 932/533, loss: 0.11505375057458878
2023-01-23 03:57:01.896204: step: 936/533, loss: 0.0005016326904296875
2023-01-23 03:57:03.048495: step: 940/533, loss: 0.027603626251220703
2023-01-23 03:57:04.226448: step: 944/533, loss: 0.0115814208984375
2023-01-23 03:57:05.413093: step: 948/533, loss: 0.0003444671747274697
2023-01-23 03:57:06.598866: step: 952/533, loss: 0.002324962755665183
2023-01-23 03:57:07.817007: step: 956/533, loss: 0.014894676394760609
2023-01-23 03:57:09.011313: step: 960/533, loss: 0.05403175204992294
2023-01-23 03:57:10.182462: step: 964/533, loss: 0.0507262721657753
2023-01-23 03:57:11.344427: step: 968/533, loss: 0.0005002021789550781
2023-01-23 03:57:12.559802: step: 972/533, loss: 0.001088905381038785
2023-01-23 03:57:13.738720: step: 976/533, loss: 0.001658630440942943
2023-01-23 03:57:14.911234: step: 980/533, loss: 0.002433204557746649
2023-01-23 03:57:16.082087: step: 984/533, loss: 0.0034229280427098274
2023-01-23 03:57:17.247554: step: 988/533, loss: 0.002062988467514515
2023-01-23 03:57:18.418633: step: 992/533, loss: 0.04250679165124893
2023-01-23 03:57:19.574265: step: 996/533, loss: 0.00473316153511405
2023-01-23 03:57:20.743247: step: 1000/533, loss: 0.001293182373046875
2023-01-23 03:57:21.945263: step: 1004/533, loss: 0.00026597976102493703
2023-01-23 03:57:23.080831: step: 1008/533, loss: 0.010640907101333141
2023-01-23 03:57:24.267650: step: 1012/533, loss: 0.014592457562685013
2023-01-23 03:57:25.455919: step: 1016/533, loss: 0.0036890029441565275
2023-01-23 03:57:26.586477: step: 1020/533, loss: 0.00022878646268509328
2023-01-23 03:57:27.733839: step: 1024/533, loss: 0.20881108939647675
2023-01-23 03:57:28.900189: step: 1028/533, loss: 0.0181534755975008
2023-01-23 03:57:30.055215: step: 1032/533, loss: 0.39380112290382385
2023-01-23 03:57:31.237642: step: 1036/533, loss: 0.000217437744140625
2023-01-23 03:57:32.417241: step: 1040/533, loss: 0.00019626619177870452
2023-01-23 03:57:33.593298: step: 1044/533, loss: 0.0017273903358727694
2023-01-23 03:57:34.764794: step: 1048/533, loss: 0.0006781101692467928
2023-01-23 03:57:35.926734: step: 1052/533, loss: 0.0786321684718132
2023-01-23 03:57:37.065047: step: 1056/533, loss: 3.204345557605848e-05
2023-01-23 03:57:38.234440: step: 1060/533, loss: 0.06606197357177734
2023-01-23 03:57:39.390306: step: 1064/533, loss: 0.014790629968047142
2023-01-23 03:57:40.570621: step: 1068/533, loss: 0.0026713847182691097
2023-01-23 03:57:41.745606: step: 1072/533, loss: 0.000154399880557321
2023-01-23 03:57:42.952022: step: 1076/533, loss: 0.0007165909046307206
2023-01-23 03:57:44.117681: step: 1080/533, loss: 0.009022235870361328
2023-01-23 03:57:45.270411: step: 1084/533, loss: 0.0007832527044229209
2023-01-23 03:57:46.477326: step: 1088/533, loss: 0.002002716064453125
2023-01-23 03:57:47.609319: step: 1092/533, loss: 0.002108240034431219
2023-01-23 03:57:48.778979: step: 1096/533, loss: 0.0008775711175985634
2023-01-23 03:57:50.009715: step: 1100/533, loss: 0.01584758795797825
2023-01-23 03:57:51.188947: step: 1104/533, loss: 0.01760435290634632
2023-01-23 03:57:52.414277: step: 1108/533, loss: 0.0007223129505291581
2023-01-23 03:57:53.555079: step: 1112/533, loss: 0.001470375107601285
2023-01-23 03:57:54.734415: step: 1116/533, loss: 7.939338684082031e-05
2023-01-23 03:57:55.965266: step: 1120/533, loss: 0.02177581936120987
2023-01-23 03:57:57.090215: step: 1124/533, loss: 0.0007461547502316535
2023-01-23 03:57:58.231030: step: 1128/533, loss: 5.054474058852065e-06
2023-01-23 03:57:59.380647: step: 1132/533, loss: 4.940032886224799e-05
2023-01-23 03:58:00.584266: step: 1136/533, loss: 0.00809392984956503
2023-01-23 03:58:01.755151: step: 1140/533, loss: 6.341934204101562e-05
2023-01-23 03:58:02.884068: step: 1144/533, loss: 0.007476234808564186
2023-01-23 03:58:04.050564: step: 1148/533, loss: 0.0005296707386150956
2023-01-23 03:58:05.229374: step: 1152/533, loss: 0.004399109166115522
2023-01-23 03:58:06.410127: step: 1156/533, loss: 0.014605332165956497
2023-01-23 03:58:07.589632: step: 1160/533, loss: 0.012473869137465954
2023-01-23 03:58:08.731077: step: 1164/533, loss: 0.009981537237763405
2023-01-23 03:58:09.866377: step: 1168/533, loss: 0.0016018867027014494
2023-01-23 03:58:11.069743: step: 1172/533, loss: 0.0006052017561160028
2023-01-23 03:58:12.211875: step: 1176/533, loss: 0.0015629768604412675
2023-01-23 03:58:13.354938: step: 1180/533, loss: 0.021303748711943626
2023-01-23 03:58:14.544720: step: 1184/533, loss: 0.004734134767204523
2023-01-23 03:58:15.710989: step: 1188/533, loss: 0.0010828971862792969
2023-01-23 03:58:16.905848: step: 1192/533, loss: 0.013994026929140091
2023-01-23 03:58:18.078533: step: 1196/533, loss: 0.00028057099552825093
2023-01-23 03:58:19.252507: step: 1200/533, loss: 0.002509593963623047
2023-01-23 03:58:20.436508: step: 1204/533, loss: 0.0016264915466308594
2023-01-23 03:58:21.596168: step: 1208/533, loss: 0.0005393981700763106
2023-01-23 03:58:22.836928: step: 1212/533, loss: 0.01260986365377903
2023-01-23 03:58:24.008475: step: 1216/533, loss: 0.05681347846984863
2023-01-23 03:58:25.168300: step: 1220/533, loss: 0.00026760101900435984
2023-01-23 03:58:26.385089: step: 1224/533, loss: 0.0006829261546954513
2023-01-23 03:58:27.551069: step: 1228/533, loss: 0.0022098543122410774
2023-01-23 03:58:28.728925: step: 1232/533, loss: 0.04069128260016441
2023-01-23 03:58:29.927247: step: 1236/533, loss: 0.0013536453479900956
2023-01-23 03:58:31.082041: step: 1240/533, loss: 0.0004873752477578819
2023-01-23 03:58:32.264346: step: 1244/533, loss: 0.029383039101958275
2023-01-23 03:58:33.404183: step: 1248/533, loss: 0.0016596914501860738
2023-01-23 03:58:34.628383: step: 1252/533, loss: 7.82012921263231e-06
2023-01-23 03:58:35.823729: step: 1256/533, loss: 8.239746239269152e-05
2023-01-23 03:58:36.987986: step: 1260/533, loss: 0.00013425351062323898
2023-01-23 03:58:38.128603: step: 1264/533, loss: 0.0007048130501061678
2023-01-23 03:58:39.319812: step: 1268/533, loss: 0.008801555261015892
2023-01-23 03:58:40.447269: step: 1272/533, loss: 0.00040836335392668843
2023-01-23 03:58:41.591086: step: 1276/533, loss: 0.0011699676979333162
2023-01-23 03:58:42.766644: step: 1280/533, loss: 0.007870912551879883
2023-01-23 03:58:43.892531: step: 1284/533, loss: 0.027782440185546875
2023-01-23 03:58:45.045870: step: 1288/533, loss: 3.571510751498863e-05
2023-01-23 03:58:46.230700: step: 1292/533, loss: 0.0010124206310138106
2023-01-23 03:58:47.405567: step: 1296/533, loss: 6.799697439419106e-05
2023-01-23 03:58:48.594677: step: 1300/533, loss: 0.00496673583984375
2023-01-23 03:58:49.760971: step: 1304/533, loss: 0.0011420012451708317
2023-01-23 03:58:50.948676: step: 1308/533, loss: 0.2273712158203125
2023-01-23 03:58:52.086768: step: 1312/533, loss: 0.03544168919324875
2023-01-23 03:58:53.222616: step: 1316/533, loss: 0.0009374141809530556
2023-01-23 03:58:54.381659: step: 1320/533, loss: 0.0007168293814174831
2023-01-23 03:58:55.535328: step: 1324/533, loss: 0.026342440396547318
2023-01-23 03:58:56.712156: step: 1328/533, loss: 0.006759834475815296
2023-01-23 03:58:57.898128: step: 1332/533, loss: 5.0258637202205136e-05
2023-01-23 03:58:59.100257: step: 1336/533, loss: 8.144378807628527e-05
2023-01-23 03:59:00.255819: step: 1340/533, loss: 0.0002568245108705014
2023-01-23 03:59:01.435534: step: 1344/533, loss: 0.0033945085015147924
2023-01-23 03:59:02.577532: step: 1348/533, loss: 0.0196043960750103
2023-01-23 03:59:03.730906: step: 1352/533, loss: 0.08306007832288742
2023-01-23 03:59:04.896033: step: 1356/533, loss: 0.009069060906767845
2023-01-23 03:59:06.049770: step: 1360/533, loss: 0.00041980744572356343
2023-01-23 03:59:07.230128: step: 1364/533, loss: 0.0005861282697878778
2023-01-23 03:59:08.439557: step: 1368/533, loss: 0.0033693313598632812
2023-01-23 03:59:09.596814: step: 1372/533, loss: 0.020530126988887787
2023-01-23 03:59:10.742411: step: 1376/533, loss: 0.0007372855907306075
2023-01-23 03:59:11.912129: step: 1380/533, loss: 0.002046871231868863
2023-01-23 03:59:13.057414: step: 1384/533, loss: 9.15527380129788e-06
2023-01-23 03:59:14.231225: step: 1388/533, loss: 1.0681153071345761e-05
2023-01-23 03:59:15.410779: step: 1392/533, loss: 1.2922286259708926e-05
2023-01-23 03:59:16.616530: step: 1396/533, loss: 0.0009120941394940019
2023-01-23 03:59:17.787473: step: 1400/533, loss: 0.0014757155440747738
2023-01-23 03:59:18.974381: step: 1404/533, loss: 0.03947634994983673
2023-01-23 03:59:20.124764: step: 1408/533, loss: 5.8650975915952586e-06
2023-01-23 03:59:21.332645: step: 1412/533, loss: 0.002025031950324774
2023-01-23 03:59:22.497564: step: 1416/533, loss: 0.03777818754315376
2023-01-23 03:59:23.695493: step: 1420/533, loss: 0.004207038786262274
2023-01-23 03:59:24.895348: step: 1424/533, loss: 0.0033987045753747225
2023-01-23 03:59:26.054710: step: 1428/533, loss: 1.3508878946304321
2023-01-23 03:59:27.206001: step: 1432/533, loss: 6.237030174816027e-05
2023-01-23 03:59:28.328645: step: 1436/533, loss: 0.030152320861816406
2023-01-23 03:59:29.468015: step: 1440/533, loss: 6.999969627941027e-05
2023-01-23 03:59:30.653390: step: 1444/533, loss: 0.09783058613538742
2023-01-23 03:59:31.810284: step: 1448/533, loss: 6.27517729299143e-05
2023-01-23 03:59:32.964508: step: 1452/533, loss: 0.0020839690696448088
2023-01-23 03:59:34.149673: step: 1456/533, loss: 0.0014142037834972143
2023-01-23 03:59:35.323503: step: 1460/533, loss: 0.002233791397884488
2023-01-23 03:59:36.506289: step: 1464/533, loss: 0.00030918122502043843
2023-01-23 03:59:37.626404: step: 1468/533, loss: 0.012582874856889248
2023-01-23 03:59:38.811255: step: 1472/533, loss: 0.010568427853286266
2023-01-23 03:59:39.973429: step: 1476/533, loss: 0.00021409988403320312
2023-01-23 03:59:41.160381: step: 1480/533, loss: 0.00041370390681549907
2023-01-23 03:59:42.327598: step: 1484/533, loss: 0.02518758736550808
2023-01-23 03:59:43.470994: step: 1488/533, loss: 0.00594520615413785
2023-01-23 03:59:44.638450: step: 1492/533, loss: 0.0007223129505291581
2023-01-23 03:59:45.783290: step: 1496/533, loss: 0.00371971121057868
2023-01-23 03:59:46.956105: step: 1500/533, loss: 2.9850005375919864e-05
2023-01-23 03:59:48.101420: step: 1504/533, loss: 7.996558997547254e-05
2023-01-23 03:59:49.262542: step: 1508/533, loss: 0.007046890445053577
2023-01-23 03:59:50.400639: step: 1512/533, loss: 0.01240387000143528
2023-01-23 03:59:51.549410: step: 1516/533, loss: 0.004190349485725164
2023-01-23 03:59:52.741742: step: 1520/533, loss: 0.0005035400390625
2023-01-23 03:59:53.918341: step: 1524/533, loss: 0.005941963288933039
2023-01-23 03:59:55.079655: step: 1528/533, loss: 0.011968541890382767
2023-01-23 03:59:56.263489: step: 1532/533, loss: 0.0006523132906295359
2023-01-23 03:59:57.425177: step: 1536/533, loss: 0.003118753433227539
2023-01-23 03:59:58.603329: step: 1540/533, loss: 0.013037538155913353
2023-01-23 03:59:59.780418: step: 1544/533, loss: 0.015993595123291016
2023-01-23 04:00:00.967406: step: 1548/533, loss: 0.0017304421635344625
2023-01-23 04:00:02.163891: step: 1552/533, loss: 0.000209808349609375
2023-01-23 04:00:03.327537: step: 1556/533, loss: 0.0011954070068895817
2023-01-23 04:00:04.485663: step: 1560/533, loss: -2.4795533590804553e-06
2023-01-23 04:00:05.647405: step: 1564/533, loss: 0.021761227399110794
2023-01-23 04:00:06.794655: step: 1568/533, loss: 0.0016402244800701737
2023-01-23 04:00:07.961953: step: 1572/533, loss: 0.027640342712402344
2023-01-23 04:00:09.140182: step: 1576/533, loss: 0.05317964777350426
2023-01-23 04:00:10.351968: step: 1580/533, loss: 0.015453719533979893
2023-01-23 04:00:11.519298: step: 1584/533, loss: 0.004646873567253351
2023-01-23 04:00:12.678857: step: 1588/533, loss: 0.0002182483731303364
2023-01-23 04:00:13.874999: step: 1592/533, loss: 0.00022077560424804688
2023-01-23 04:00:15.038627: step: 1596/533, loss: 0.03993396833539009
2023-01-23 04:00:16.269049: step: 1600/533, loss: 0.03127565234899521
2023-01-23 04:00:17.391695: step: 1604/533, loss: 0.00031414031400345266
2023-01-23 04:00:18.570962: step: 1608/533, loss: 0.014753628522157669
2023-01-23 04:00:19.765331: step: 1612/533, loss: 0.004345322027802467
2023-01-23 04:00:20.899319: step: 1616/533, loss: 0.00010051728168036789
2023-01-23 04:00:22.074408: step: 1620/533, loss: 0.03536186367273331
2023-01-23 04:00:23.263014: step: 1624/533, loss: 0.015340805053710938
2023-01-23 04:00:24.447637: step: 1628/533, loss: 0.004257774446159601
2023-01-23 04:00:25.623408: step: 1632/533, loss: 0.0011619568103924394
2023-01-23 04:00:26.829433: step: 1636/533, loss: 0.0029239654541015625
2023-01-23 04:00:28.014966: step: 1640/533, loss: 0.004975604824721813
2023-01-23 04:00:29.187236: step: 1644/533, loss: 0.005943679716438055
2023-01-23 04:00:30.347973: step: 1648/533, loss: 0.006720066070556641
2023-01-23 04:00:31.546195: step: 1652/533, loss: 0.00027964115724898875
2023-01-23 04:00:32.678526: step: 1656/533, loss: 8.869170414982364e-06
2023-01-23 04:00:33.874154: step: 1660/533, loss: 5.7220458984375e-06
2023-01-23 04:00:35.044296: step: 1664/533, loss: 0.06058015674352646
2023-01-23 04:00:36.159754: step: 1668/533, loss: 0.00027742385282181203
2023-01-23 04:00:37.372518: step: 1672/533, loss: 0.0005420685047283769
2023-01-23 04:00:38.520464: step: 1676/533, loss: 0.00010056496103061363
2023-01-23 04:00:39.664780: step: 1680/533, loss: 0.00025577546330168843
2023-01-23 04:00:40.826827: step: 1684/533, loss: 0.0041335588321089745
2023-01-23 04:00:41.960682: step: 1688/533, loss: 0.003565979190170765
2023-01-23 04:00:43.147862: step: 1692/533, loss: 0.06697248667478561
2023-01-23 04:00:44.380372: step: 1696/533, loss: 0.0018962860340252519
2023-01-23 04:00:45.571876: step: 1700/533, loss: 0.0030312540475279093
2023-01-23 04:00:46.780935: step: 1704/533, loss: 0.00044269562931731343
2023-01-23 04:00:47.926524: step: 1708/533, loss: 0.027163410559296608
2023-01-23 04:00:49.104424: step: 1712/533, loss: 0.00010833740816451609
2023-01-23 04:00:50.286882: step: 1716/533, loss: 0.03129911422729492
2023-01-23 04:00:51.466706: step: 1720/533, loss: 1.9073488033427566e-07
2023-01-23 04:00:52.649404: step: 1724/533, loss: 0.0001616478111827746
2023-01-23 04:00:53.851556: step: 1728/533, loss: 0.008506583981215954
2023-01-23 04:00:55.041572: step: 1732/533, loss: 0.00022010803513694555
2023-01-23 04:00:56.249251: step: 1736/533, loss: 0.0564180389046669
2023-01-23 04:00:57.430442: step: 1740/533, loss: 0.00010404586646473035
2023-01-23 04:00:58.571172: step: 1744/533, loss: 0.0002197742578573525
2023-01-23 04:00:59.743337: step: 1748/533, loss: 0.08783798664808273
2023-01-23 04:01:00.873657: step: 1752/533, loss: 0.004085349850356579
2023-01-23 04:01:02.050608: step: 1756/533, loss: 7.324219041038305e-05
2023-01-23 04:01:03.231418: step: 1760/533, loss: 0.014804650098085403
2023-01-23 04:01:04.387726: step: 1764/533, loss: 0.04349031671881676
2023-01-23 04:01:05.576319: step: 1768/533, loss: 1.1920930774067529e-05
2023-01-23 04:01:06.765253: step: 1772/533, loss: 9.15527380129788e-06
2023-01-23 04:01:07.944010: step: 1776/533, loss: 0.0006799697875976562
2023-01-23 04:01:09.094631: step: 1780/533, loss: 0.00044841767521575093
2023-01-23 04:01:10.264966: step: 1784/533, loss: 4.310607982915826e-05
2023-01-23 04:01:11.433219: step: 1788/533, loss: 0.04329051822423935
2023-01-23 04:01:12.637617: step: 1792/533, loss: 0.010746193118393421
2023-01-23 04:01:13.843415: step: 1796/533, loss: 0.00022792816162109375
2023-01-23 04:01:15.008836: step: 1800/533, loss: 0.003046226454898715
2023-01-23 04:01:16.152195: step: 1804/533, loss: 0.00012149810208939016
2023-01-23 04:01:17.330693: step: 1808/533, loss: 0.01930561102926731
2023-01-23 04:01:18.524012: step: 1812/533, loss: 4.234314110362902e-05
2023-01-23 04:01:19.692956: step: 1816/533, loss: 5.445480564958416e-05
2023-01-23 04:01:20.862619: step: 1820/533, loss: 0.003831768175587058
2023-01-23 04:01:22.039062: step: 1824/533, loss: 0.0299745574593544
2023-01-23 04:01:23.215940: step: 1828/533, loss: 9.717942157294601e-05
2023-01-23 04:01:24.402909: step: 1832/533, loss: 0.045876119285821915
2023-01-23 04:01:25.595815: step: 1836/533, loss: 0.00013175010099075735
2023-01-23 04:01:26.766542: step: 1840/533, loss: 0.00037260056706145406
2023-01-23 04:01:27.941622: step: 1844/533, loss: 0.030855130404233932
2023-01-23 04:01:29.092909: step: 1848/533, loss: 0.0003955840948037803
2023-01-23 04:01:30.248728: step: 1852/533, loss: 0.0023347854148596525
2023-01-23 04:01:31.442806: step: 1856/533, loss: 0.0037843703757971525
2023-01-23 04:01:32.573768: step: 1860/533, loss: -1.7166134966828395e-06
2023-01-23 04:01:33.765264: step: 1864/533, loss: 0.0440642386674881
2023-01-23 04:01:34.916976: step: 1868/533, loss: 0.05874033272266388
2023-01-23 04:01:36.113843: step: 1872/533, loss: 2.880096508306451e-05
2023-01-23 04:01:37.266246: step: 1876/533, loss: 0.003457927843555808
2023-01-23 04:01:38.444414: step: 1880/533, loss: 0.008210564032196999
2023-01-23 04:01:39.640239: step: 1884/533, loss: 0.007722091861069202
2023-01-23 04:01:40.782647: step: 1888/533, loss: 0.0012625694507732987
2023-01-23 04:01:41.989668: step: 1892/533, loss: 0.0007431030389852822
2023-01-23 04:01:43.152104: step: 1896/533, loss: 0.009793472476303577
2023-01-23 04:01:44.337107: step: 1900/533, loss: 8.611679368186742e-05
2023-01-23 04:01:45.547127: step: 1904/533, loss: 0.0005155563703738153
2023-01-23 04:01:46.738152: step: 1908/533, loss: 0.009315108880400658
2023-01-23 04:01:47.951793: step: 1912/533, loss: 0.0002994537353515625
2023-01-23 04:01:49.143144: step: 1916/533, loss: 0.016551781445741653
2023-01-23 04:01:50.305302: step: 1920/533, loss: 0.00035457609919831157
2023-01-23 04:01:51.451955: step: 1924/533, loss: 0.00037097930908203125
2023-01-23 04:01:52.612342: step: 1928/533, loss: 0.0001262664736714214
2023-01-23 04:01:53.790191: step: 1932/533, loss: 0.001853180001489818
2023-01-23 04:01:54.954431: step: 1936/533, loss: 0.001208400703035295
2023-01-23 04:01:56.098011: step: 1940/533, loss: 8.592977974331006e-05
2023-01-23 04:01:57.268796: step: 1944/533, loss: 0.05228424072265625
2023-01-23 04:01:58.425627: step: 1948/533, loss: 0.03904237970709801
2023-01-23 04:01:59.589642: step: 1952/533, loss: 3.519058373058215e-05
2023-01-23 04:02:00.698363: step: 1956/533, loss: 0.008115005679428577
2023-01-23 04:02:01.884800: step: 1960/533, loss: 4.010200791526586e-05
2023-01-23 04:02:03.053369: step: 1964/533, loss: 3.471374657237902e-05
2023-01-23 04:02:04.228621: step: 1968/533, loss: 0.016849135980010033
2023-01-23 04:02:05.399745: step: 1972/533, loss: 0.005553150083869696
2023-01-23 04:02:06.606762: step: 1976/533, loss: 0.013669204898178577
2023-01-23 04:02:07.751970: step: 1980/533, loss: 0.0012292861938476562
2023-01-23 04:02:08.938083: step: 1984/533, loss: 0.0021957396529614925
2023-01-23 04:02:10.150543: step: 1988/533, loss: 0.010261917486786842
2023-01-23 04:02:11.316671: step: 1992/533, loss: 0.0032817842438817024
2023-01-23 04:02:12.477518: step: 1996/533, loss: 0.003951930906623602
2023-01-23 04:02:13.627782: step: 2000/533, loss: 0.0030815124046057463
2023-01-23 04:02:14.851515: step: 2004/533, loss: 3.232955714338459e-05
2023-01-23 04:02:16.022096: step: 2008/533, loss: 0.0003964424249716103
2023-01-23 04:02:17.186629: step: 2012/533, loss: 0.0013454437721520662
2023-01-23 04:02:18.377261: step: 2016/533, loss: 0.0006504058837890625
2023-01-23 04:02:19.537367: step: 2020/533, loss: 0.005679011344909668
2023-01-23 04:02:20.718538: step: 2024/533, loss: 0.0008004665724001825
2023-01-23 04:02:21.909795: step: 2028/533, loss: 0.006409263703972101
2023-01-23 04:02:23.127596: step: 2032/533, loss: 0.0013885498046875
2023-01-23 04:02:24.271853: step: 2036/533, loss: 0.001469946000725031
2023-01-23 04:02:25.406804: step: 2040/533, loss: 9.17434663278982e-05
2023-01-23 04:02:26.586647: step: 2044/533, loss: 6.294250852079131e-06
2023-01-23 04:02:27.806888: step: 2048/533, loss: 0.00026197434635832906
2023-01-23 04:02:29.004744: step: 2052/533, loss: 0.0003758430539164692
2023-01-23 04:02:30.207520: step: 2056/533, loss: 2.6226043701171875e-06
2023-01-23 04:02:31.362083: step: 2060/533, loss: 5.53131121705519e-06
2023-01-23 04:02:32.555126: step: 2064/533, loss: 0.00010986327833961695
2023-01-23 04:02:33.709491: step: 2068/533, loss: 0.0020662308670580387
2023-01-23 04:02:34.894737: step: 2072/533, loss: -1.316070574830519e-05
2023-01-23 04:02:36.064467: step: 2076/533, loss: 5.378723290050402e-05
2023-01-23 04:02:37.234851: step: 2080/533, loss: 0.010884500108659267
2023-01-23 04:02:38.403636: step: 2084/533, loss: 0.005922507960349321
2023-01-23 04:02:39.576482: step: 2088/533, loss: 0.0003299713134765625
2023-01-23 04:02:40.741036: step: 2092/533, loss: 0.0008209228981286287
2023-01-23 04:02:41.896079: step: 2096/533, loss: 0.0015687941340729594
2023-01-23 04:02:43.052537: step: 2100/533, loss: 0.02914581447839737
2023-01-23 04:02:44.243685: step: 2104/533, loss: 0.006865215487778187
2023-01-23 04:02:45.475168: step: 2108/533, loss: 0.0027782439719885588
2023-01-23 04:02:46.663677: step: 2112/533, loss: 0.010496318340301514
2023-01-23 04:02:47.888348: step: 2116/533, loss: 0.013097573071718216
2023-01-23 04:02:49.046227: step: 2120/533, loss: 0.014444352127611637
2023-01-23 04:02:50.228433: step: 2124/533, loss: 0.03334693983197212
2023-01-23 04:02:51.472071: step: 2128/533, loss: 8.020401583053172e-05
2023-01-23 04:02:52.631441: step: 2132/533, loss: 4.673004241340095e-06
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.6048472075869337, 'r': 0.7643142476697736, 'f1': 0.6752941176470589}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6530612244897959, 'r': 0.7979539641943734, 'f1': 0.718273381294964}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5647058823529412, 'r': 0.8888888888888888, 'f1': 0.6906474820143885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6530612244897959, 'r': 0.5079365079365079, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.3953488372093023, 'r': 0.4722222222222222, 'f1': 0.43037974683544306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:03:33.419793: step: 4/533, loss: 0.11187629401683807
2023-01-23 04:03:34.613467: step: 8/533, loss: 0.0007357597351074219
2023-01-23 04:03:35.808947: step: 12/533, loss: 0.0008819579961709678
2023-01-23 04:03:36.962823: step: 16/533, loss: 0.0005161285516805947
2023-01-23 04:03:38.102195: step: 20/533, loss: 0.0001636505185160786
2023-01-23 04:03:39.277045: step: 24/533, loss: 0.007214903831481934
2023-01-23 04:03:40.436402: step: 28/533, loss: 0.00075616838876158
2023-01-23 04:03:41.635939: step: 32/533, loss: 0.02224902994930744
2023-01-23 04:03:42.801982: step: 36/533, loss: 0.00033230779808945954
2023-01-23 04:03:43.981362: step: 40/533, loss: 0.0005222320323809981
2023-01-23 04:03:45.151055: step: 44/533, loss: 0.0003184318484272808
2023-01-23 04:03:46.316632: step: 48/533, loss: 0.0045608519576489925
2023-01-23 04:03:47.465547: step: 52/533, loss: 0.00021038056001998484
2023-01-23 04:03:48.621322: step: 56/533, loss: 9.298324584960938e-05
2023-01-23 04:03:49.770053: step: 60/533, loss: 6.115436553955078e-05
2023-01-23 04:03:50.931164: step: 64/533, loss: 7.133484177757055e-05
2023-01-23 04:03:52.130881: step: 68/533, loss: 0.057862281799316406
2023-01-23 04:03:53.272327: step: 72/533, loss: 0.035753536969423294
2023-01-23 04:03:54.461065: step: 76/533, loss: 0.00014028548321221024
2023-01-23 04:03:55.623341: step: 80/533, loss: 0.0010984421242028475
2023-01-23 04:03:56.782667: step: 84/533, loss: 0.03076777420938015
2023-01-23 04:03:57.914225: step: 88/533, loss: 0.0024822235573083162
2023-01-23 04:03:59.063988: step: 92/533, loss: 0.009707736782729626
2023-01-23 04:04:00.216556: step: 96/533, loss: 0.032755278050899506
2023-01-23 04:04:01.400542: step: 100/533, loss: 0.014388466253876686
2023-01-23 04:04:02.579824: step: 104/533, loss: 0.0012490273220464587
2023-01-23 04:04:03.796849: step: 108/533, loss: 0.01947803422808647
2023-01-23 04:04:04.972036: step: 112/533, loss: 0.00010051727440441027
2023-01-23 04:04:06.113865: step: 116/533, loss: 0.0011391640873625875
2023-01-23 04:04:07.262909: step: 120/533, loss: 0.0001617431698832661
2023-01-23 04:04:08.442244: step: 124/533, loss: 0.013813018798828125
2023-01-23 04:04:09.595012: step: 128/533, loss: 0.001083803130313754
2023-01-23 04:04:10.773769: step: 132/533, loss: 4.27722952736076e-05
2023-01-23 04:04:11.926082: step: 136/533, loss: 6.814003427280113e-05
2023-01-23 04:04:13.094644: step: 140/533, loss: 0.0005793571472167969
2023-01-23 04:04:14.289013: step: 144/533, loss: 0.015749169513583183
2023-01-23 04:04:15.507078: step: 148/533, loss: 0.019277572631835938
2023-01-23 04:04:16.684339: step: 152/533, loss: 0.00017080307588912547
2023-01-23 04:04:17.819933: step: 156/533, loss: 0.0004277229309082031
2023-01-23 04:04:19.025609: step: 160/533, loss: 0.0004178047238383442
2023-01-23 04:04:20.191360: step: 164/533, loss: 0.027348613366484642
2023-01-23 04:04:21.344178: step: 168/533, loss: 0.0006777763483114541
2023-01-23 04:04:22.504914: step: 172/533, loss: 0.0006651878356933594
2023-01-23 04:04:23.700016: step: 176/533, loss: 0.0005069732433184981
2023-01-23 04:04:24.934696: step: 180/533, loss: 0.008580387569963932
2023-01-23 04:04:26.112962: step: 184/533, loss: 0.00039348602876998484
2023-01-23 04:04:27.274269: step: 188/533, loss: 1.0626280307769775
2023-01-23 04:04:28.453144: step: 192/533, loss: 0.0007314682006835938
2023-01-23 04:04:29.681715: step: 196/533, loss: 7.41958647267893e-05
2023-01-23 04:04:30.876533: step: 200/533, loss: 0.01301670167595148
2023-01-23 04:04:32.048597: step: 204/533, loss: 0.0005212783580645919
2023-01-23 04:04:33.251123: step: 208/533, loss: 0.003574275877326727
2023-01-23 04:04:34.398619: step: 212/533, loss: 0.0015644074883311987
2023-01-23 04:04:35.615074: step: 216/533, loss: 0.02648754231631756
2023-01-23 04:04:36.797887: step: 220/533, loss: 0.0005815983167849481
2023-01-23 04:04:38.044844: step: 224/533, loss: 0.04251975938677788
2023-01-23 04:04:39.263908: step: 228/533, loss: 0.005886840634047985
2023-01-23 04:04:40.423391: step: 232/533, loss: 0.00017662048048805445
2023-01-23 04:04:41.583634: step: 236/533, loss: 0.010887622833251953
2023-01-23 04:04:42.737484: step: 240/533, loss: 0.004258537199348211
2023-01-23 04:04:43.941197: step: 244/533, loss: 0.0005887985462322831
2023-01-23 04:04:45.100940: step: 248/533, loss: 0.05128965526819229
2023-01-23 04:04:46.261465: step: 252/533, loss: 0.0010391235118731856
2023-01-23 04:04:47.415580: step: 256/533, loss: 0.0002510070917196572
2023-01-23 04:04:48.596122: step: 260/533, loss: 3.71456153516192e-05
2023-01-23 04:04:49.781864: step: 264/533, loss: 0.0056063649244606495
2023-01-23 04:04:50.929590: step: 268/533, loss: 0.0002210617094533518
2023-01-23 04:04:52.078012: step: 272/533, loss: 1.5211105164780747e-05
2023-01-23 04:04:53.240120: step: 276/533, loss: 0.0035533905029296875
2023-01-23 04:04:54.431000: step: 280/533, loss: 4.0817263652570546e-05
2023-01-23 04:04:55.587691: step: 284/533, loss: 0.003212356474250555
2023-01-23 04:04:56.747496: step: 288/533, loss: 0.0012172699207440019
2023-01-23 04:04:57.905194: step: 292/533, loss: 1.62601463671308e-05
2023-01-23 04:04:59.108287: step: 296/533, loss: 0.05152120813727379
2023-01-23 04:05:00.287393: step: 300/533, loss: 0.00019426345534157008
2023-01-23 04:05:01.467815: step: 304/533, loss: 0.011230086907744408
2023-01-23 04:05:02.657062: step: 308/533, loss: 0.04899730533361435
2023-01-23 04:05:03.802053: step: 312/533, loss: 0.008487128652632236
2023-01-23 04:05:04.938565: step: 316/533, loss: 0.0018607140518724918
2023-01-23 04:05:06.162926: step: 320/533, loss: 0.002101325895637274
2023-01-23 04:05:07.334002: step: 324/533, loss: 0.006189728155732155
2023-01-23 04:05:08.519112: step: 328/533, loss: 3.863573510898277e-05
2023-01-23 04:05:09.693464: step: 332/533, loss: 0.00797185953706503
2023-01-23 04:05:10.861567: step: 336/533, loss: 8.39233416627394e-06
2023-01-23 04:05:12.048026: step: 340/533, loss: 0.0007979392539709806
2023-01-23 04:05:13.268367: step: 344/533, loss: 0.03519124910235405
2023-01-23 04:05:14.404577: step: 348/533, loss: 0.0005229950184002519
2023-01-23 04:05:15.558352: step: 352/533, loss: 0.0005412101745605469
2023-01-23 04:05:16.695597: step: 356/533, loss: 0.0002808570861816406
2023-01-23 04:05:17.816787: step: 360/533, loss: 0.0005090713384561241
2023-01-23 04:05:18.973540: step: 364/533, loss: 8.964539119915571e-06
2023-01-23 04:05:20.135144: step: 368/533, loss: 5.3787229262525216e-05
2023-01-23 04:05:21.310036: step: 372/533, loss: 0.0006996155134402215
2023-01-23 04:05:22.521213: step: 376/533, loss: 7.724762326688506e-06
2023-01-23 04:05:23.687968: step: 380/533, loss: 0.06823787838220596
2023-01-23 04:05:24.824406: step: 384/533, loss: 0.001269864966161549
2023-01-23 04:05:26.028669: step: 388/533, loss: 3.147125244140625e-05
2023-01-23 04:05:27.214186: step: 392/533, loss: 3.767013913602568e-05
2023-01-23 04:05:28.409073: step: 396/533, loss: 0.00026063917903229594
2023-01-23 04:05:29.572648: step: 400/533, loss: -5.34057608092553e-06
2023-01-23 04:05:30.745127: step: 404/533, loss: 8.311271812999621e-05
2023-01-23 04:05:31.910426: step: 408/533, loss: 0.011280441656708717
2023-01-23 04:05:33.059837: step: 412/533, loss: 0.0004051208670716733
2023-01-23 04:05:34.226004: step: 416/533, loss: 0.0001504898100392893
2023-01-23 04:05:35.406206: step: 420/533, loss: 3.6239625842426904e-06
2023-01-23 04:05:36.556443: step: 424/533, loss: 0.010908221825957298
2023-01-23 04:05:37.705246: step: 428/533, loss: 0.03046722337603569
2023-01-23 04:05:38.850875: step: 432/533, loss: 0.004014777950942516
2023-01-23 04:05:40.014257: step: 436/533, loss: 5.912781489314511e-06
2023-01-23 04:05:41.173050: step: 440/533, loss: 0.044097900390625
2023-01-23 04:05:42.346624: step: 444/533, loss: 0.00017986298189498484
2023-01-23 04:05:43.493275: step: 448/533, loss: 0.0013586044078692794
2023-01-23 04:05:44.687398: step: 452/533, loss: 0.0005167007329873741
2023-01-23 04:05:45.891382: step: 456/533, loss: 0.000335693359375
2023-01-23 04:05:47.076683: step: 460/533, loss: 0.00014629363431595266
2023-01-23 04:05:48.256132: step: 464/533, loss: 0.0005573272937908769
2023-01-23 04:05:49.514650: step: 468/533, loss: 0.04576678201556206
2023-01-23 04:05:50.692258: step: 472/533, loss: 0.04335803911089897
2023-01-23 04:05:51.856907: step: 476/533, loss: -4.386902219266631e-06
2023-01-23 04:05:53.053681: step: 480/533, loss: 0.00110206613317132
2023-01-23 04:05:54.201424: step: 484/533, loss: 0.00012626648822333664
2023-01-23 04:05:55.384871: step: 488/533, loss: 0.005187797360122204
2023-01-23 04:05:56.576340: step: 492/533, loss: 0.0012491225497797132
2023-01-23 04:05:57.786367: step: 496/533, loss: 0.048845864832401276
2023-01-23 04:05:58.973634: step: 500/533, loss: 0.0017173767555505037
2023-01-23 04:06:00.149684: step: 504/533, loss: 0.00175132742151618
2023-01-23 04:06:01.339479: step: 508/533, loss: 0.03961363062262535
2023-01-23 04:06:02.529577: step: 512/533, loss: 0.005207347683608532
2023-01-23 04:06:03.727167: step: 516/533, loss: 0.010910320095717907
2023-01-23 04:06:04.911278: step: 520/533, loss: 0.0005066872108727694
2023-01-23 04:06:06.058182: step: 524/533, loss: 8.554458327125758e-05
2023-01-23 04:06:07.215450: step: 528/533, loss: 0.04548225551843643
2023-01-23 04:06:08.392367: step: 532/533, loss: 3.185272362316027e-05
2023-01-23 04:06:09.539509: step: 536/533, loss: 6.809234764659777e-05
2023-01-23 04:06:10.738576: step: 540/533, loss: 0.0005782127263955772
2023-01-23 04:06:11.920273: step: 544/533, loss: 0.0005617141723632812
2023-01-23 04:06:13.112130: step: 548/533, loss: 0.005755377002060413
2023-01-23 04:06:14.325601: step: 552/533, loss: 0.00954656582325697
2023-01-23 04:06:15.551350: step: 556/533, loss: 0.026959801092743874
2023-01-23 04:06:16.726122: step: 560/533, loss: 0.07968740910291672
2023-01-23 04:06:17.900713: step: 564/533, loss: 0.024430274963378906
2023-01-23 04:06:19.094142: step: 568/533, loss: -6.198882601893274e-06
2023-01-23 04:06:20.235016: step: 572/533, loss: 0.05496664345264435
2023-01-23 04:06:21.429525: step: 576/533, loss: 0.033574867993593216
2023-01-23 04:06:22.606659: step: 580/533, loss: 0.006825065705925226
2023-01-23 04:06:23.780532: step: 584/533, loss: 2.3555756342830136e-05
2023-01-23 04:06:24.968795: step: 588/533, loss: 0.09605465084314346
2023-01-23 04:06:26.094032: step: 592/533, loss: 0.019091034308075905
2023-01-23 04:06:27.262093: step: 596/533, loss: 7.658005051780492e-05
2023-01-23 04:06:28.446691: step: 600/533, loss: 0.002284526824951172
2023-01-23 04:06:29.618445: step: 604/533, loss: 0.009167099371552467
2023-01-23 04:06:30.833716: step: 608/533, loss: 2.765655517578125e-05
2023-01-23 04:06:32.003162: step: 612/533, loss: 0.0008384704706259072
2023-01-23 04:06:33.168303: step: 616/533, loss: 0.044295214116573334
2023-01-23 04:06:34.355715: step: 620/533, loss: 0.0038341046310961246
2023-01-23 04:06:35.536173: step: 624/533, loss: 0.0005313873407430947
2023-01-23 04:06:36.712180: step: 628/533, loss: 0.0007600784301757812
2023-01-23 04:06:37.886379: step: 632/533, loss: 0.01061263494193554
2023-01-23 04:06:39.122402: step: 636/533, loss: 0.009187126532196999
2023-01-23 04:06:40.358156: step: 640/533, loss: 8.845329284667969e-05
2023-01-23 04:06:41.550767: step: 644/533, loss: 0.010899257846176624
2023-01-23 04:06:42.762402: step: 648/533, loss: 0.0005669593228958547
2023-01-23 04:06:43.942029: step: 652/533, loss: 0.04291486740112305
2023-01-23 04:06:45.176792: step: 656/533, loss: 0.0007602691766805947
2023-01-23 04:06:46.349523: step: 660/533, loss: 2.079009937006049e-05
2023-01-23 04:06:47.527244: step: 664/533, loss: 0.0001142501860158518
2023-01-23 04:06:48.672815: step: 668/533, loss: 4.95910626341356e-06
2023-01-23 04:06:49.879740: step: 672/533, loss: 0.0002685069921426475
2023-01-23 04:06:51.051778: step: 676/533, loss: 0.024470187723636627
2023-01-23 04:06:52.241991: step: 680/533, loss: 0.004728889558464289
2023-01-23 04:06:53.362287: step: 684/533, loss: 4.76837158203125e-07
2023-01-23 04:06:54.550600: step: 688/533, loss: 0.00017051695613190532
2023-01-23 04:06:55.730157: step: 692/533, loss: 0.006273365113884211
2023-01-23 04:06:56.882560: step: 696/533, loss: 9.565353684592992e-05
2023-01-23 04:06:58.072811: step: 700/533, loss: 0.001807403634302318
2023-01-23 04:06:59.205167: step: 704/533, loss: 2.7084352041129023e-05
2023-01-23 04:07:00.396847: step: 708/533, loss: 0.044736552983522415
2023-01-23 04:07:01.575559: step: 712/533, loss: 0.1034703254699707
2023-01-23 04:07:02.761212: step: 716/533, loss: 0.003424358321353793
2023-01-23 04:07:03.942105: step: 720/533, loss: 0.25962716341018677
2023-01-23 04:07:05.123439: step: 724/533, loss: 0.0012144566280767322
2023-01-23 04:07:06.287786: step: 728/533, loss: 0.001938820001669228
2023-01-23 04:07:07.482091: step: 732/533, loss: 0.015377044677734375
2023-01-23 04:07:08.609149: step: 736/533, loss: 0.0173155777156353
2023-01-23 04:07:09.818006: step: 740/533, loss: 0.001611268613487482
2023-01-23 04:07:10.980143: step: 744/533, loss: 0.005706692114472389
2023-01-23 04:07:12.128859: step: 748/533, loss: 0.027206992730498314
2023-01-23 04:07:13.306710: step: 752/533, loss: 5.6648252211743966e-05
2023-01-23 04:07:14.464681: step: 756/533, loss: 0.0010866641532629728
2023-01-23 04:07:15.610327: step: 760/533, loss: 0.0010593414772301912
2023-01-23 04:07:16.797974: step: 764/533, loss: 0.009982443414628506
2023-01-23 04:07:18.017181: step: 768/533, loss: 0.035612963140010834
2023-01-23 04:07:19.184369: step: 772/533, loss: 0.003970527555793524
2023-01-23 04:07:20.355602: step: 776/533, loss: 0.011561202816665173
2023-01-23 04:07:21.519529: step: 780/533, loss: 0.003782367566600442
2023-01-23 04:07:22.690180: step: 784/533, loss: 0.0054168701171875
2023-01-23 04:07:23.877450: step: 788/533, loss: 0.01558761578053236
2023-01-23 04:07:25.065306: step: 792/533, loss: 0.004012966062873602
2023-01-23 04:07:26.236652: step: 796/533, loss: 0.07053347676992416
2023-01-23 04:07:27.398393: step: 800/533, loss: 0.03857855871319771
2023-01-23 04:07:28.554868: step: 804/533, loss: 0.002723312471061945
2023-01-23 04:07:29.733864: step: 808/533, loss: 0.0044186594896018505
2023-01-23 04:07:30.887874: step: 812/533, loss: 1.0013580322265625e-05
2023-01-23 04:07:32.024591: step: 816/533, loss: 8.325576345669106e-05
2023-01-23 04:07:33.210721: step: 820/533, loss: 0.0002503395080566406
2023-01-23 04:07:34.370140: step: 824/533, loss: 0.0004323005850892514
2023-01-23 04:07:35.540817: step: 828/533, loss: 7.82012939453125e-05
2023-01-23 04:07:36.712718: step: 832/533, loss: 0.0005410194862633944
2023-01-23 04:07:37.889530: step: 836/533, loss: 0.005740070249885321
2023-01-23 04:07:39.052418: step: 840/533, loss: 1.9073486328125e-05
2023-01-23 04:07:40.217898: step: 844/533, loss: 0.00019674302893690765
2023-01-23 04:07:41.394773: step: 848/533, loss: 0.020435143262147903
2023-01-23 04:07:42.561660: step: 852/533, loss: 0.057543568313121796
2023-01-23 04:07:43.710620: step: 856/533, loss: 0.00160560617223382
2023-01-23 04:07:44.949288: step: 860/533, loss: 1.7499922250863165e-05
2023-01-23 04:07:46.081747: step: 864/533, loss: 0.00021610260591842234
2023-01-23 04:07:47.206361: step: 868/533, loss: 0.00015373229689430445
2023-01-23 04:07:48.406504: step: 872/533, loss: 0.00016098022751975805
2023-01-23 04:07:49.541531: step: 876/533, loss: 0.00025768281193450093
2023-01-23 04:07:50.717092: step: 880/533, loss: 0.00939950905740261
2023-01-23 04:07:51.873116: step: 884/533, loss: 0.14021149277687073
2023-01-23 04:07:53.014600: step: 888/533, loss: 3.23295607813634e-05
2023-01-23 04:07:54.173772: step: 892/533, loss: 0.09389925003051758
2023-01-23 04:07:55.361618: step: 896/533, loss: 0.0006057739374227822
2023-01-23 04:07:56.536755: step: 900/533, loss: 1.144409225162235e-06
2023-01-23 04:07:57.712178: step: 904/533, loss: 0.004372787661850452
2023-01-23 04:07:58.869853: step: 908/533, loss: 3.185272362316027e-05
2023-01-23 04:08:00.030099: step: 912/533, loss: 0.0025501251220703125
2023-01-23 04:08:01.145501: step: 916/533, loss: 0.0006044865003786981
2023-01-23 04:08:02.303384: step: 920/533, loss: 0.019122600555419922
2023-01-23 04:08:03.463469: step: 924/533, loss: 0.005641079042106867
2023-01-23 04:08:04.612192: step: 928/533, loss: 0.00014085769362282008
2023-01-23 04:08:05.757351: step: 932/533, loss: 1.4781951904296875e-05
2023-01-23 04:08:06.947156: step: 936/533, loss: 0.0013290406204760075
2023-01-23 04:08:08.152419: step: 940/533, loss: 0.003409004071727395
2023-01-23 04:08:09.327971: step: 944/533, loss: 0.007462692447006702
2023-01-23 04:08:10.495870: step: 948/533, loss: 0.005602407269179821
2023-01-23 04:08:11.696348: step: 952/533, loss: 0.004732513800263405
2023-01-23 04:08:12.901449: step: 956/533, loss: 0.0025073052383959293
2023-01-23 04:08:14.080788: step: 960/533, loss: 0.003074741456657648
2023-01-23 04:08:15.225908: step: 964/533, loss: 3.4999848139705136e-05
2023-01-23 04:08:16.381689: step: 968/533, loss: 0.00028791429940611124
2023-01-23 04:08:17.525714: step: 972/533, loss: 1.1157990229548886e-05
2023-01-23 04:08:18.678697: step: 976/533, loss: 0.00041961669921875
2023-01-23 04:08:19.873490: step: 980/533, loss: 6.246566772460938e-05
2023-01-23 04:08:21.066967: step: 984/533, loss: 0.021274566650390625
2023-01-23 04:08:22.245050: step: 988/533, loss: 0.0003974914725404233
2023-01-23 04:08:23.430720: step: 992/533, loss: 0.002517604734748602
2023-01-23 04:08:24.619105: step: 996/533, loss: 0.007695198059082031
2023-01-23 04:08:25.780961: step: 1000/533, loss: 1.4114380974206142e-05
2023-01-23 04:08:26.946017: step: 1004/533, loss: 0.0017191886436194181
2023-01-23 04:08:28.076329: step: 1008/533, loss: 0.006597613915801048
2023-01-23 04:08:29.227319: step: 1012/533, loss: 8.134842209983617e-05
2023-01-23 04:08:30.388690: step: 1016/533, loss: 0.045996859669685364
2023-01-23 04:08:31.572709: step: 1020/533, loss: 1.5640260244254023e-05
2023-01-23 04:08:32.730284: step: 1024/533, loss: 0.000274658203125
2023-01-23 04:08:33.923727: step: 1028/533, loss: 0.0004460334894247353
2023-01-23 04:08:35.092412: step: 1032/533, loss: 0.005132771097123623
2023-01-23 04:08:36.275515: step: 1036/533, loss: 0.00021157263836357743
2023-01-23 04:08:37.464757: step: 1040/533, loss: 0.013942909426987171
2023-01-23 04:08:38.646251: step: 1044/533, loss: 0.0032739639282226562
2023-01-23 04:08:39.851021: step: 1048/533, loss: 0.001295375870540738
2023-01-23 04:08:41.038645: step: 1052/533, loss: 0.0023937225341796875
2023-01-23 04:08:42.280344: step: 1056/533, loss: 0.0003565788210835308
2023-01-23 04:08:43.412656: step: 1060/533, loss: 0.08198156952857971
2023-01-23 04:08:44.637160: step: 1064/533, loss: 0.023420333862304688
2023-01-23 04:08:45.838159: step: 1068/533, loss: 0.0005703926435671747
2023-01-23 04:08:47.030254: step: 1072/533, loss: 0.005052519030869007
2023-01-23 04:08:48.183414: step: 1076/533, loss: 0.004059124272316694
2023-01-23 04:08:49.348737: step: 1080/533, loss: 0.022756576538085938
2023-01-23 04:08:50.532262: step: 1084/533, loss: 0.0025980949867516756
2023-01-23 04:08:51.679539: step: 1088/533, loss: 0.00041370390681549907
2023-01-23 04:08:52.881322: step: 1092/533, loss: 0.010689354501664639
2023-01-23 04:08:54.060599: step: 1096/533, loss: 0.012452316470444202
2023-01-23 04:08:55.196060: step: 1100/533, loss: 0.0003386497846804559
2023-01-23 04:08:56.389125: step: 1104/533, loss: 0.010661983862519264
2023-01-23 04:08:57.539582: step: 1108/533, loss: 0.0008134842501021922
2023-01-23 04:08:58.688134: step: 1112/533, loss: 0.0011558354599401355
2023-01-23 04:08:59.810719: step: 1116/533, loss: 4.444122168933973e-05
2023-01-23 04:09:01.017994: step: 1120/533, loss: 0.00040092470590025187
2023-01-23 04:09:02.223143: step: 1124/533, loss: 0.009002303704619408
2023-01-23 04:09:03.352932: step: 1128/533, loss: 0.013695811852812767
2023-01-23 04:09:04.551848: step: 1132/533, loss: 0.0006999969482421875
2023-01-23 04:09:05.674884: step: 1136/533, loss: 0.0010070801945403218
2023-01-23 04:09:06.865485: step: 1140/533, loss: 0.029296113178133965
2023-01-23 04:09:08.059065: step: 1144/533, loss: 6.0272213886491954e-05
2023-01-23 04:09:09.195939: step: 1148/533, loss: 0.0015497207641601562
2023-01-23 04:09:10.361146: step: 1152/533, loss: 0.004676247015595436
2023-01-23 04:09:11.518942: step: 1156/533, loss: 0.011130047030746937
2023-01-23 04:09:12.710021: step: 1160/533, loss: 8.988380432128906e-05
2023-01-23 04:09:13.894574: step: 1164/533, loss: 1.76429750808893e-06
2023-01-23 04:09:15.066394: step: 1168/533, loss: 1.1634827387752011e-05
2023-01-23 04:09:16.252946: step: 1172/533, loss: 0.030812358483672142
2023-01-23 04:09:17.444578: step: 1176/533, loss: 4.310607982915826e-05
2023-01-23 04:09:18.609207: step: 1180/533, loss: 0.002107906388118863
2023-01-23 04:09:19.757128: step: 1184/533, loss: 0.018909836187958717
2023-01-23 04:09:20.920083: step: 1188/533, loss: 0.0052969930693507195
2023-01-23 04:09:22.060482: step: 1192/533, loss: 0.00013313292583916336
2023-01-23 04:09:23.258751: step: 1196/533, loss: 0.046775247901678085
2023-01-23 04:09:24.445454: step: 1200/533, loss: 0.00278987898491323
2023-01-23 04:09:25.621258: step: 1204/533, loss: 2.384185791015625e-05
2023-01-23 04:09:26.812250: step: 1208/533, loss: 0.003305053571239114
2023-01-23 04:09:27.969353: step: 1212/533, loss: 0.013186216354370117
2023-01-23 04:09:29.143728: step: 1216/533, loss: 0.0031128881964832544
2023-01-23 04:09:30.332850: step: 1220/533, loss: 0.0005787849659100175
2023-01-23 04:09:31.488402: step: 1224/533, loss: 0.00012273788161110133
2023-01-23 04:09:32.671290: step: 1228/533, loss: 0.0012176514137536287
2023-01-23 04:09:33.838282: step: 1232/533, loss: 7.400513277389109e-05
2023-01-23 04:09:35.026004: step: 1236/533, loss: 0.0033599853049963713
2023-01-23 04:09:36.180742: step: 1240/533, loss: 1.7166138377433526e-06
2023-01-23 04:09:37.335064: step: 1244/533, loss: 6.332397606456652e-05
2023-01-23 04:09:38.467198: step: 1248/533, loss: 0.05436830595135689
2023-01-23 04:09:39.650342: step: 1252/533, loss: 0.0068357475101947784
2023-01-23 04:09:40.826187: step: 1256/533, loss: -6.48498553346144e-06
2023-01-23 04:09:41.965664: step: 1260/533, loss: 0.04023933410644531
2023-01-23 04:09:43.126656: step: 1264/533, loss: 0.02508525922894478
2023-01-23 04:09:44.281284: step: 1268/533, loss: 0.029063226655125618
2023-01-23 04:09:45.491693: step: 1272/533, loss: 0.0005532264476642013
2023-01-23 04:09:46.635366: step: 1276/533, loss: 0.0001367569057038054
2023-01-23 04:09:47.808171: step: 1280/533, loss: 0.0017366409301757812
2023-01-23 04:09:49.024965: step: 1284/533, loss: 0.022514915093779564
2023-01-23 04:09:50.190045: step: 1288/533, loss: 0.0881490707397461
2023-01-23 04:09:51.439041: step: 1292/533, loss: 6.237030174816027e-05
2023-01-23 04:09:52.618122: step: 1296/533, loss: 0.010213851928710938
2023-01-23 04:09:53.814233: step: 1300/533, loss: 0.03126201778650284
2023-01-23 04:09:54.936271: step: 1304/533, loss: 0.004970932379364967
2023-01-23 04:09:56.103748: step: 1308/533, loss: 5.7220458984375e-06
2023-01-23 04:09:57.311536: step: 1312/533, loss: 0.023522090166807175
2023-01-23 04:09:58.476593: step: 1316/533, loss: 0.00018234254093840718
2023-01-23 04:09:59.680036: step: 1320/533, loss: 0.00069088937016204
2023-01-23 04:10:00.833791: step: 1324/533, loss: 0.015287209302186966
2023-01-23 04:10:02.002854: step: 1328/533, loss: 0.0001544952392578125
2023-01-23 04:10:03.144892: step: 1332/533, loss: 9.34600848268019e-06
2023-01-23 04:10:04.297717: step: 1336/533, loss: 0.044062234461307526
2023-01-23 04:10:05.447385: step: 1340/533, loss: 0.007546902168542147
2023-01-23 04:10:06.625088: step: 1344/533, loss: 4.2343137465650216e-05
2023-01-23 04:10:07.778566: step: 1348/533, loss: 3.681182715808973e-05
2023-01-23 04:10:08.977010: step: 1352/533, loss: 3.070831371587701e-05
2023-01-23 04:10:10.190541: step: 1356/533, loss: 0.000644683837890625
2023-01-23 04:10:11.347212: step: 1360/533, loss: 8.39233416627394e-06
2023-01-23 04:10:12.528982: step: 1364/533, loss: 0.00973806343972683
2023-01-23 04:10:13.702793: step: 1368/533, loss: 0.00025281906710006297
2023-01-23 04:10:14.859629: step: 1372/533, loss: 0.0015600204933434725
2023-01-23 04:10:16.015063: step: 1376/533, loss: 0.009256219491362572
2023-01-23 04:10:17.170964: step: 1380/533, loss: 0.009183120913803577
2023-01-23 04:10:18.345257: step: 1384/533, loss: 5.893707202631049e-05
2023-01-23 04:10:19.497723: step: 1388/533, loss: 0.00030236245947889984
2023-01-23 04:10:20.662855: step: 1392/533, loss: 0.004322052001953125
2023-01-23 04:10:21.826833: step: 1396/533, loss: 0.0019245147705078125
2023-01-23 04:10:22.985766: step: 1400/533, loss: 0.0005702972412109375
2023-01-23 04:10:24.208925: step: 1404/533, loss: 0.0007865906227380037
2023-01-23 04:10:25.408410: step: 1408/533, loss: 0.003495597979053855
2023-01-23 04:10:26.625872: step: 1412/533, loss: 0.00019149782019667327
2023-01-23 04:10:27.849422: step: 1416/533, loss: 1.62601463671308e-05
2023-01-23 04:10:29.063267: step: 1420/533, loss: 0.016955852508544922
2023-01-23 04:10:30.247640: step: 1424/533, loss: 0.0009185791132040322
2023-01-23 04:10:31.383829: step: 1428/533, loss: 0.015378189273178577
2023-01-23 04:10:32.552095: step: 1432/533, loss: 0.005722379311919212
2023-01-23 04:10:33.733999: step: 1436/533, loss: 6.999969627941027e-05
2023-01-23 04:10:34.881823: step: 1440/533, loss: 7.43865966796875e-05
2023-01-23 04:10:36.056293: step: 1444/533, loss: 0.0013107300037518144
2023-01-23 04:10:37.244507: step: 1448/533, loss: 1.144409225162235e-06
2023-01-23 04:10:38.443272: step: 1452/533, loss: -7.05719003235572e-06
2023-01-23 04:10:39.609590: step: 1456/533, loss: 0.012697791680693626
2023-01-23 04:10:40.804208: step: 1460/533, loss: 3.757476952159777e-05
2023-01-23 04:10:41.950803: step: 1464/533, loss: 0.0001029014601954259
2023-01-23 04:10:43.153058: step: 1468/533, loss: 0.0032018660567700863
2023-01-23 04:10:44.306920: step: 1472/533, loss: 0.03953571245074272
2023-01-23 04:10:45.444116: step: 1476/533, loss: 9.059906005859375e-05
2023-01-23 04:10:46.609437: step: 1480/533, loss: 0.0004643440479412675
2023-01-23 04:10:47.771654: step: 1484/533, loss: 0.1530340164899826
2023-01-23 04:10:48.944568: step: 1488/533, loss: 0.0010137557983398438
2023-01-23 04:10:50.105521: step: 1492/533, loss: 6.337165541481227e-05
2023-01-23 04:10:51.250124: step: 1496/533, loss: 0.002912807511165738
2023-01-23 04:10:52.390487: step: 1500/533, loss: 0.0008403778192587197
2023-01-23 04:10:53.555904: step: 1504/533, loss: 0.0038170814514160156
2023-01-23 04:10:54.719149: step: 1508/533, loss: 0.008150959387421608
2023-01-23 04:10:55.850475: step: 1512/533, loss: 0.00011172294762218371
2023-01-23 04:10:57.030308: step: 1516/533, loss: 0.022918129339814186
2023-01-23 04:10:58.194083: step: 1520/533, loss: 0.011520194821059704
2023-01-23 04:10:59.400819: step: 1524/533, loss: 0.0005056381342001259
2023-01-23 04:11:00.569339: step: 1528/533, loss: 0.0002267837553517893
2023-01-23 04:11:01.767370: step: 1532/533, loss: 0.027029801160097122
2023-01-23 04:11:02.925306: step: 1536/533, loss: 0.004332542419433594
2023-01-23 04:11:04.136892: step: 1540/533, loss: 0.0001625060976948589
2023-01-23 04:11:05.308879: step: 1544/533, loss: 0.4024145007133484
2023-01-23 04:11:06.501727: step: 1548/533, loss: 0.0007131577003747225
2023-01-23 04:11:07.654140: step: 1552/533, loss: 0.048481278121471405
2023-01-23 04:11:08.790057: step: 1556/533, loss: 0.027990151196718216
2023-01-23 04:11:09.969327: step: 1560/533, loss: 0.0007340431329794228
2023-01-23 04:11:11.139968: step: 1564/533, loss: 0.014251136220991611
2023-01-23 04:11:12.309654: step: 1568/533, loss: 0.048250962048769
2023-01-23 04:11:13.484758: step: 1572/533, loss: 0.0034626247361302376
2023-01-23 04:11:14.660628: step: 1576/533, loss: 6.999969627941027e-05
2023-01-23 04:11:15.850938: step: 1580/533, loss: 0.01412420254200697
2023-01-23 04:11:17.004665: step: 1584/533, loss: 9.212493750965223e-05
2023-01-23 04:11:18.165585: step: 1588/533, loss: 0.0006238937494345009
2023-01-23 04:11:19.365904: step: 1592/533, loss: 0.013140678405761719
2023-01-23 04:11:20.592839: step: 1596/533, loss: 0.002686786698177457
2023-01-23 04:11:21.843325: step: 1600/533, loss: 0.005118751898407936
2023-01-23 04:11:23.039910: step: 1604/533, loss: 0.008208608254790306
2023-01-23 04:11:24.216109: step: 1608/533, loss: 0.00014591217041015625
2023-01-23 04:11:25.392510: step: 1612/533, loss: 0.006329535972326994
2023-01-23 04:11:26.591114: step: 1616/533, loss: 0.012324143201112747
2023-01-23 04:11:27.795028: step: 1620/533, loss: 0.07143593579530716
2023-01-23 04:11:28.972015: step: 1624/533, loss: 3.852844383800402e-05
2023-01-23 04:11:30.116443: step: 1628/533, loss: 0.0004291534423828125
2023-01-23 04:11:31.289775: step: 1632/533, loss: 0.03128309175372124
2023-01-23 04:11:32.434063: step: 1636/533, loss: 0.05012550204992294
2023-01-23 04:11:33.611567: step: 1640/533, loss: 0.0017783165676519275
2023-01-23 04:11:34.793817: step: 1644/533, loss: 0.004736137576401234
2023-01-23 04:11:36.001659: step: 1648/533, loss: 0.0016430855030193925
2023-01-23 04:11:37.169160: step: 1652/533, loss: 0.0004444122314453125
2023-01-23 04:11:38.349740: step: 1656/533, loss: 0.006460190284997225
2023-01-23 04:11:39.538044: step: 1660/533, loss: 2.9468537832144648e-05
2023-01-23 04:11:40.714742: step: 1664/533, loss: 0.0019041537307202816
2023-01-23 04:11:41.841876: step: 1668/533, loss: 0.002951717469841242
2023-01-23 04:11:43.015886: step: 1672/533, loss: 8.411407907260582e-05
2023-01-23 04:11:44.216737: step: 1676/533, loss: 0.013868285343050957
2023-01-23 04:11:45.357509: step: 1680/533, loss: 0.0009562492487020791
2023-01-23 04:11:46.529043: step: 1684/533, loss: 0.0038997649680823088
2023-01-23 04:11:47.697307: step: 1688/533, loss: 4.501342846197076e-05
2023-01-23 04:11:48.882132: step: 1692/533, loss: 0.0030788423027843237
2023-01-23 04:11:50.042920: step: 1696/533, loss: 0.00024003982252907008
2023-01-23 04:11:51.215390: step: 1700/533, loss: 0.00046606065006926656
2023-01-23 04:11:52.456242: step: 1704/533, loss: 0.001483058906160295
2023-01-23 04:11:53.628920: step: 1708/533, loss: 0.0007295608520507812
2023-01-23 04:11:54.814912: step: 1712/533, loss: 0.026917647570371628
2023-01-23 04:11:55.994548: step: 1716/533, loss: 0.0028310774359852076
2023-01-23 04:11:57.149125: step: 1720/533, loss: 0.00023860932560637593
2023-01-23 04:11:58.311454: step: 1724/533, loss: 0.0017264842754229903
2023-01-23 04:11:59.514543: step: 1728/533, loss: 0.0003843307786155492
2023-01-23 04:12:00.708876: step: 1732/533, loss: 0.007222652435302734
2023-01-23 04:12:01.844681: step: 1736/533, loss: 3.395378735149279e-05
2023-01-23 04:12:02.982722: step: 1740/533, loss: 4.034042649436742e-05
2023-01-23 04:12:04.183910: step: 1744/533, loss: 0.0003303527773823589
2023-01-23 04:12:05.370610: step: 1748/533, loss: 3.986358569818549e-05
2023-01-23 04:12:06.537524: step: 1752/533, loss: 9.975433204090223e-05
2023-01-23 04:12:07.684827: step: 1756/533, loss: 0.015137768350541592
2023-01-23 04:12:08.845099: step: 1760/533, loss: 0.0007786750793457031
2023-01-23 04:12:09.984757: step: 1764/533, loss: 0.005710697267204523
2023-01-23 04:12:11.125822: step: 1768/533, loss: 1.6498564946232364e-05
2023-01-23 04:12:12.271695: step: 1772/533, loss: 0.0006136417505331337
2023-01-23 04:12:13.440442: step: 1776/533, loss: 2.059936559817288e-05
2023-01-23 04:12:14.586511: step: 1780/533, loss: 0.0007009506225585938
2023-01-23 04:12:15.777789: step: 1784/533, loss: 0.006754684261977673
2023-01-23 04:12:16.898452: step: 1788/533, loss: 0.0013906479580327868
2023-01-23 04:12:18.105772: step: 1792/533, loss: 0.0007092476007528603
2023-01-23 04:12:19.298718: step: 1796/533, loss: 0.02512378618121147
2023-01-23 04:12:20.463882: step: 1800/533, loss: 0.004793929867446423
2023-01-23 04:12:21.591259: step: 1804/533, loss: 2.9373170036706142e-05
2023-01-23 04:12:22.793926: step: 1808/533, loss: 0.005444717593491077
2023-01-23 04:12:23.978284: step: 1812/533, loss: 8.544922457076609e-05
2023-01-23 04:12:25.147851: step: 1816/533, loss: 0.000518798828125
2023-01-23 04:12:26.274458: step: 1820/533, loss: 0.013496875762939453
2023-01-23 04:12:27.455602: step: 1824/533, loss: 0.009257126599550247
2023-01-23 04:12:28.590628: step: 1828/533, loss: 0.013383245095610619
2023-01-23 04:12:29.800296: step: 1832/533, loss: 0.0001522064267192036
2023-01-23 04:12:30.981477: step: 1836/533, loss: 1.7642974853515625e-05
2023-01-23 04:12:32.144172: step: 1840/533, loss: 0.003491020295768976
2023-01-23 04:12:33.323332: step: 1844/533, loss: 0.005664658732712269
2023-01-23 04:12:34.488281: step: 1848/533, loss: 0.05427103117108345
2023-01-23 04:12:35.661831: step: 1852/533, loss: 0.03789882734417915
2023-01-23 04:12:36.867577: step: 1856/533, loss: 0.021619606763124466
2023-01-23 04:12:38.019938: step: 1860/533, loss: 0.015170765109360218
2023-01-23 04:12:39.198891: step: 1864/533, loss: 0.00214805593714118
2023-01-23 04:12:40.447453: step: 1868/533, loss: 0.0010038375621661544
2023-01-23 04:12:41.627729: step: 1872/533, loss: 0.0052665709517896175
2023-01-23 04:12:42.799001: step: 1876/533, loss: 0.017368890345096588
2023-01-23 04:12:43.974596: step: 1880/533, loss: 0.003692722413688898
2023-01-23 04:12:45.172684: step: 1884/533, loss: 0.06499912589788437
2023-01-23 04:12:46.362097: step: 1888/533, loss: 0.0008035659557208419
2023-01-23 04:12:47.529302: step: 1892/533, loss: 0.0019177437061443925
2023-01-23 04:12:48.715635: step: 1896/533, loss: 7.41958647267893e-05
2023-01-23 04:12:49.892242: step: 1900/533, loss: 0.001054143882356584
2023-01-23 04:12:51.061334: step: 1904/533, loss: 0.003231239505112171
2023-01-23 04:12:52.203113: step: 1908/533, loss: 0.0005390167352743447
2023-01-23 04:12:53.408789: step: 1912/533, loss: 0.000940561352763325
2023-01-23 04:12:54.592682: step: 1916/533, loss: 0.007178878877311945
2023-01-23 04:12:55.730974: step: 1920/533, loss: 0.0060096741653978825
2023-01-23 04:12:56.884521: step: 1924/533, loss: 0.009455871768295765
2023-01-23 04:12:58.061630: step: 1928/533, loss: 0.03778943791985512
2023-01-23 04:12:59.240171: step: 1932/533, loss: 0.0014142990112304688
2023-01-23 04:13:00.421651: step: 1936/533, loss: 0.002552604768425226
2023-01-23 04:13:01.586500: step: 1940/533, loss: 0.0017974853981286287
2023-01-23 04:13:02.737397: step: 1944/533, loss: 0.07040510326623917
2023-01-23 04:13:03.890672: step: 1948/533, loss: 0.0019392013782635331
2023-01-23 04:13:05.039382: step: 1952/533, loss: 0.00138511648401618
2023-01-23 04:13:06.242802: step: 1956/533, loss: 0.0006892204401083291
2023-01-23 04:13:07.430058: step: 1960/533, loss: 0.0014643669128417969
2023-01-23 04:13:08.586208: step: 1964/533, loss: 0.0018978120060637593
2023-01-23 04:13:09.727231: step: 1968/533, loss: 0.00013651848712470382
2023-01-23 04:13:10.890082: step: 1972/533, loss: 0.008381461724638939
2023-01-23 04:13:12.063526: step: 1976/533, loss: 0.0005361631629057229
2023-01-23 04:13:13.220419: step: 1980/533, loss: 0.002209186553955078
2023-01-23 04:13:14.408648: step: 1984/533, loss: 1.1405349141568877e-05
2023-01-23 04:13:15.564075: step: 1988/533, loss: 0.005408096592873335
2023-01-23 04:13:16.747081: step: 1992/533, loss: 0.0002956390380859375
2023-01-23 04:13:17.896215: step: 1996/533, loss: 0.0031279087997972965
2023-01-23 04:13:19.054666: step: 2000/533, loss: 0.0012835502857342362
2023-01-23 04:13:20.240930: step: 2004/533, loss: 0.0001204729123855941
2023-01-23 04:13:21.436116: step: 2008/533, loss: 0.0006654739263467491
2023-01-23 04:13:22.679821: step: 2012/533, loss: 0.013453292660415173
2023-01-23 04:13:23.863688: step: 2016/533, loss: 0.0010333069367334247
2023-01-23 04:13:25.077145: step: 2020/533, loss: 6.122589547885582e-05
2023-01-23 04:13:26.278275: step: 2024/533, loss: 0.0063915252685546875
2023-01-23 04:13:27.467620: step: 2028/533, loss: 0.0021713257301598787
2023-01-23 04:13:28.706316: step: 2032/533, loss: 0.09097137302160263
2023-01-23 04:13:29.846937: step: 2036/533, loss: 0.00018024444580078125
2023-01-23 04:13:31.006650: step: 2040/533, loss: 0.0010258674155920744
2023-01-23 04:13:32.161042: step: 2044/533, loss: 0.002700996585190296
2023-01-23 04:13:33.358546: step: 2048/533, loss: 2.117157055181451e-05
2023-01-23 04:13:34.518684: step: 2052/533, loss: 0.07578067481517792
2023-01-23 04:13:35.721752: step: 2056/533, loss: 3.581047349143773e-05
2023-01-23 04:13:36.887643: step: 2060/533, loss: 0.004752730950713158
2023-01-23 04:13:38.095901: step: 2064/533, loss: 0.020041847601532936
2023-01-23 04:13:39.288981: step: 2068/533, loss: 0.00010447502427268773
2023-01-23 04:13:40.466255: step: 2072/533, loss: 0.00010900497727561742
2023-01-23 04:13:41.641371: step: 2076/533, loss: 0.012491464614868164
2023-01-23 04:13:42.823229: step: 2080/533, loss: 0.0030254365410655737
2023-01-23 04:13:44.017600: step: 2084/533, loss: 0.01447000540792942
2023-01-23 04:13:45.156608: step: 2088/533, loss: 0.0015224457019940019
2023-01-23 04:13:46.295044: step: 2092/533, loss: 0.0006699622026644647
2023-01-23 04:13:47.490866: step: 2096/533, loss: 0.00600776681676507
2023-01-23 04:13:48.658755: step: 2100/533, loss: 0.018784618005156517
2023-01-23 04:13:49.877464: step: 2104/533, loss: 0.04771747440099716
2023-01-23 04:13:51.040271: step: 2108/533, loss: 0.008324814029037952
2023-01-23 04:13:52.238703: step: 2112/533, loss: 0.00017213821411132812
2023-01-23 04:13:53.380087: step: 2116/533, loss: 0.013968085870146751
2023-01-23 04:13:54.594497: step: 2120/533, loss: 0.0004980087396688759
2023-01-23 04:13:55.767148: step: 2124/533, loss: 3.42369094141759e-05
2023-01-23 04:13:56.948516: step: 2128/533, loss: 0.00022010803513694555
2023-01-23 04:13:58.082099: step: 2132/533, loss: 0.0018367290031164885
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.6161934805467929, 'r': 0.7802929427430093, 'f1': 0.6886016451233843}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.643223819301848, 'r': 0.801150895140665, 'f1': 0.7135535307517085}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.5747126436781609, 'r': 0.9259259259259259, 'f1': 0.7092198581560283}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6140350877192983, 'r': 0.5555555555555556, 'f1': 0.5833333333333335}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.45714285714285713, 'r': 0.4444444444444444, 'f1': 0.4507042253521127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 26
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:14:38.950369: step: 4/533, loss: 0.017394160851836205
2023-01-23 04:14:40.085970: step: 8/533, loss: 0.0012245177058503032
2023-01-23 04:14:41.262023: step: 12/533, loss: 0.0001485824614064768
2023-01-23 04:14:42.449950: step: 16/533, loss: 2.899169885495212e-05
2023-01-23 04:14:43.604548: step: 20/533, loss: 0.0005673408741131425
2023-01-23 04:14:44.758591: step: 24/533, loss: 0.008204269222915173
2023-01-23 04:14:45.937717: step: 28/533, loss: 0.09262824058532715
2023-01-23 04:14:47.095344: step: 32/533, loss: 0.04372682422399521
2023-01-23 04:14:48.243936: step: 36/533, loss: 0.0021409988403320312
2023-01-23 04:14:49.396872: step: 40/533, loss: 0.00638427771627903
2023-01-23 04:14:50.572584: step: 44/533, loss: 0.014252089895308018
2023-01-23 04:14:51.736406: step: 48/533, loss: 2.384185791015625e-05
2023-01-23 04:14:52.873112: step: 52/533, loss: 0.0006363391294144094
2023-01-23 04:14:54.047282: step: 56/533, loss: 0.006514930631965399
2023-01-23 04:14:55.211760: step: 60/533, loss: 0.0009164810180664062
2023-01-23 04:14:56.396943: step: 64/533, loss: 0.00033988954965025187
2023-01-23 04:14:57.558102: step: 68/533, loss: 0.0011954307556152344
2023-01-23 04:14:58.739700: step: 72/533, loss: 0.0009373784414492548
2023-01-23 04:14:59.935011: step: 76/533, loss: 0.002245187759399414
2023-01-23 04:15:01.089429: step: 80/533, loss: 0.02531757391989231
2023-01-23 04:15:02.254570: step: 84/533, loss: 0.0006640434148721397
2023-01-23 04:15:03.407796: step: 88/533, loss: 0.009225464425981045
2023-01-23 04:15:04.590268: step: 92/533, loss: 0.0005470275646075606
2023-01-23 04:15:05.779694: step: 96/533, loss: 0.00023269654775504023
2023-01-23 04:15:06.976592: step: 100/533, loss: 0.0004094124014955014
2023-01-23 04:15:08.170111: step: 104/533, loss: 0.0009828568436205387
2023-01-23 04:15:09.346283: step: 108/533, loss: 0.018595505505800247
2023-01-23 04:15:10.515138: step: 112/533, loss: 6.0558319091796875e-05
2023-01-23 04:15:11.694153: step: 116/533, loss: -6.10351571594947e-06
2023-01-23 04:15:12.841699: step: 120/533, loss: 0.00015726088895462453
2023-01-23 04:15:13.980849: step: 124/533, loss: 0.0009961128234863281
2023-01-23 04:15:15.163413: step: 128/533, loss: 0.0007328033680096269
2023-01-23 04:15:16.328350: step: 132/533, loss: 8.497238013660535e-05
2023-01-23 04:15:17.515744: step: 136/533, loss: 0.004687499720603228
2023-01-23 04:15:18.706401: step: 140/533, loss: 0.023482512682676315
2023-01-23 04:15:19.833581: step: 144/533, loss: 0.03089323081076145
2023-01-23 04:15:21.016597: step: 148/533, loss: 3.0231476557673886e-05
2023-01-23 04:15:22.198010: step: 152/533, loss: 0.00011148453631903976
2023-01-23 04:15:23.368823: step: 156/533, loss: 0.010329199023544788
2023-01-23 04:15:24.522553: step: 160/533, loss: 0.012707972899079323
2023-01-23 04:15:25.690776: step: 164/533, loss: 0.0033180236350744963
2023-01-23 04:15:26.874293: step: 168/533, loss: 2.6798248654813506e-05
2023-01-23 04:15:28.083505: step: 172/533, loss: 0.001982307294383645
2023-01-23 04:15:29.265129: step: 176/533, loss: 5.187988426769152e-05
2023-01-23 04:15:30.475988: step: 180/533, loss: 0.0009992599952965975
2023-01-23 04:15:31.639660: step: 184/533, loss: 0.002347278641536832
2023-01-23 04:15:32.827202: step: 188/533, loss: 6.256103370105848e-05
2023-01-23 04:15:33.986392: step: 192/533, loss: 0.0021039010025560856
2023-01-23 04:15:35.194074: step: 196/533, loss: 0.007149219512939453
2023-01-23 04:15:36.367443: step: 200/533, loss: 0.0005437851068563759
2023-01-23 04:15:37.593555: step: 204/533, loss: 0.00038356782170012593
2023-01-23 04:15:38.734801: step: 208/533, loss: 7.152557373046875e-06
2023-01-23 04:15:39.965518: step: 212/533, loss: 0.00013747216144111007
2023-01-23 04:15:41.130083: step: 216/533, loss: 0.00045843125553801656
2023-01-23 04:15:42.301016: step: 220/533, loss: 0.0004973411560058594
2023-01-23 04:15:43.475870: step: 224/533, loss: 0.00015544892812613398
2023-01-23 04:15:44.614710: step: 228/533, loss: 4.6253204345703125e-05
2023-01-23 04:15:45.810397: step: 232/533, loss: 0.005884838290512562
2023-01-23 04:15:47.011687: step: 236/533, loss: 0.0001049041748046875
2023-01-23 04:15:48.163274: step: 240/533, loss: -5.91278057981981e-06
2023-01-23 04:15:49.353259: step: 244/533, loss: 0.017470359802246094
2023-01-23 04:15:50.488195: step: 248/533, loss: 1.1825562069134321e-05
2023-01-23 04:15:51.637181: step: 252/533, loss: 1.9073486612342094e-07
2023-01-23 04:15:52.839157: step: 256/533, loss: 2.689361645025201e-05
2023-01-23 04:15:53.999976: step: 260/533, loss: 0.0010174751514568925
2023-01-23 04:15:55.129562: step: 264/533, loss: 0.0001680374116403982
2023-01-23 04:15:56.275282: step: 268/533, loss: 1.0681153071345761e-05
2023-01-23 04:15:57.406561: step: 272/533, loss: 0.014096545986831188
2023-01-23 04:15:58.557525: step: 276/533, loss: 0.002058601239696145
2023-01-23 04:15:59.727249: step: 280/533, loss: 9.91821252682712e-06
2023-01-23 04:16:00.940805: step: 284/533, loss: 0.026860618963837624
2023-01-23 04:16:02.090002: step: 288/533, loss: 0.0037556171882897615
2023-01-23 04:16:03.260840: step: 292/533, loss: 0.004272937774658203
2023-01-23 04:16:04.474738: step: 296/533, loss: 9.727478754939511e-06
2023-01-23 04:16:05.750223: step: 300/533, loss: 3.395080420887098e-05
2023-01-23 04:16:06.928769: step: 304/533, loss: 0.0026064871344715357
2023-01-23 04:16:08.058179: step: 308/533, loss: 0.0009754180791787803
2023-01-23 04:16:09.224401: step: 312/533, loss: 1.678466833254788e-05
2023-01-23 04:16:10.367286: step: 316/533, loss: 0.001332950545474887
2023-01-23 04:16:11.529631: step: 320/533, loss: 0.00213794712908566
2023-01-23 04:16:12.693883: step: 324/533, loss: 2.5749204723979346e-06
2023-01-23 04:16:13.883504: step: 328/533, loss: 0.009528731927275658
2023-01-23 04:16:15.016672: step: 332/533, loss: 0.00036535263643600047
2023-01-23 04:16:16.150695: step: 336/533, loss: 0.022148799151182175
2023-01-23 04:16:17.324296: step: 340/533, loss: 0.07264023274183273
2023-01-23 04:16:18.503297: step: 344/533, loss: 0.00027370452880859375
2023-01-23 04:16:19.655384: step: 348/533, loss: 0.0017305373912677169
2023-01-23 04:16:20.832806: step: 352/533, loss: 0.0002513885556254536
2023-01-23 04:16:22.018312: step: 356/533, loss: 0.00596542377024889
2023-01-23 04:16:23.203293: step: 360/533, loss: 0.0019187451107427478
2023-01-23 04:16:24.385255: step: 364/533, loss: 0.0021162035409361124
2023-01-23 04:16:25.550270: step: 368/533, loss: 0.011855793185532093
2023-01-23 04:16:26.717624: step: 372/533, loss: 0.021173572167754173
2023-01-23 04:16:27.866600: step: 376/533, loss: -4.38690176451928e-06
2023-01-23 04:16:29.037653: step: 380/533, loss: 0.0404851920902729
2023-01-23 04:16:30.256092: step: 384/533, loss: 0.04347210004925728
2023-01-23 04:16:31.411637: step: 388/533, loss: 0.005990028381347656
2023-01-23 04:16:32.621398: step: 392/533, loss: 2.059936559817288e-05
2023-01-23 04:16:33.778114: step: 396/533, loss: 0.010973549447953701
2023-01-23 04:16:34.957688: step: 400/533, loss: 5.455017162603326e-05
2023-01-23 04:16:36.118450: step: 404/533, loss: 7.45773286325857e-05
2023-01-23 04:16:37.296017: step: 408/533, loss: 0.00027141571626998484
2023-01-23 04:16:38.480356: step: 412/533, loss: 0.006593286991119385
2023-01-23 04:16:39.721376: step: 416/533, loss: 0.00036237240419723094
2023-01-23 04:16:40.842830: step: 420/533, loss: 1.7833710444392636e-05
2023-01-23 04:16:42.034438: step: 424/533, loss: 0.011798190884292126
2023-01-23 04:16:43.230705: step: 428/533, loss: 0.0002721786731854081
2023-01-23 04:16:44.404427: step: 432/533, loss: 0.4555656909942627
2023-01-23 04:16:45.556751: step: 436/533, loss: -1.5616417385899695e-06
2023-01-23 04:16:46.780521: step: 440/533, loss: 0.0016931057907640934
2023-01-23 04:16:47.971465: step: 444/533, loss: 0.01959824748337269
2023-01-23 04:16:49.193586: step: 448/533, loss: 0.0029212951194494963
2023-01-23 04:16:50.374079: step: 452/533, loss: 0.012137794867157936
2023-01-23 04:16:51.591343: step: 456/533, loss: 0.019290734082460403
2023-01-23 04:16:52.734564: step: 460/533, loss: 0.0007053375011309981
2023-01-23 04:16:53.867034: step: 464/533, loss: 0.00020515918731689453
2023-01-23 04:16:55.024288: step: 468/533, loss: 0.00018568038649391383
2023-01-23 04:16:56.197037: step: 472/533, loss: 0.7206413745880127
2023-01-23 04:16:57.378264: step: 476/533, loss: 8.468627493130043e-05
2023-01-23 04:16:58.569308: step: 480/533, loss: 0.004154682159423828
2023-01-23 04:16:59.810824: step: 484/533, loss: 0.03941326215863228
2023-01-23 04:17:00.991173: step: 488/533, loss: 0.004136324394494295
2023-01-23 04:17:02.169908: step: 492/533, loss: 0.0002960205019917339
2023-01-23 04:17:03.350077: step: 496/533, loss: 0.0004982947721146047
2023-01-23 04:17:04.536772: step: 500/533, loss: 0.076807402074337
2023-01-23 04:17:05.700427: step: 504/533, loss: 0.00012149810936534777
2023-01-23 04:17:06.876986: step: 508/533, loss: 0.004178046714514494
2023-01-23 04:17:08.037590: step: 512/533, loss: 0.0025717734824866056
2023-01-23 04:17:09.197107: step: 516/533, loss: 0.03859663009643555
2023-01-23 04:17:10.336026: step: 520/533, loss: 0.0017368317348882556
2023-01-23 04:17:11.635315: step: 524/533, loss: 2.593994213384576e-05
2023-01-23 04:17:12.863300: step: 528/533, loss: 0.00013647080049850047
2023-01-23 04:17:14.071855: step: 532/533, loss: 0.01704278215765953
2023-01-23 04:17:15.255394: step: 536/533, loss: 0.0002662658807821572
2023-01-23 04:17:16.402712: step: 540/533, loss: 0.00027885439340025187
2023-01-23 04:17:17.601500: step: 544/533, loss: 0.0009891510708257556
2023-01-23 04:17:18.783047: step: 548/533, loss: 2.746581958490424e-05
2023-01-23 04:17:19.953027: step: 552/533, loss: 0.00013837814913131297
2023-01-23 04:17:21.130088: step: 556/533, loss: 0.02695159986615181
2023-01-23 04:17:22.287094: step: 560/533, loss: 0.000798988388851285
2023-01-23 04:17:23.469235: step: 564/533, loss: 0.01008386630564928
2023-01-23 04:17:24.657840: step: 568/533, loss: 0.0001522064267192036
2023-01-23 04:17:25.821092: step: 572/533, loss: 0.010600757785141468
2023-01-23 04:17:26.938365: step: 576/533, loss: 0.00015230178541969508
2023-01-23 04:17:28.107648: step: 580/533, loss: 0.0007265090825967491
2023-01-23 04:17:29.288824: step: 584/533, loss: 0.5062990188598633
2023-01-23 04:17:30.445460: step: 588/533, loss: 0.06403694301843643
2023-01-23 04:17:31.653475: step: 592/533, loss: 0.0001540184166515246
2023-01-23 04:17:32.838464: step: 596/533, loss: 0.0007529258728027344
2023-01-23 04:17:33.991632: step: 600/533, loss: 0.03568553924560547
2023-01-23 04:17:35.166606: step: 604/533, loss: 0.02764911763370037
2023-01-23 04:17:36.330916: step: 608/533, loss: 0.0014818668132647872
2023-01-23 04:17:37.537625: step: 612/533, loss: 0.0014579773414880037
2023-01-23 04:17:38.690159: step: 616/533, loss: 4.117488788324408e-05
2023-01-23 04:17:39.910650: step: 620/533, loss: 0.017935562878847122
2023-01-23 04:17:41.093887: step: 624/533, loss: 0.0016592026222497225
2023-01-23 04:17:42.247520: step: 628/533, loss: 0.0003465652698650956
2023-01-23 04:17:43.411492: step: 632/533, loss: 0.03862953558564186
2023-01-23 04:17:44.597621: step: 636/533, loss: 0.012893295846879482
2023-01-23 04:17:45.778588: step: 640/533, loss: 0.006782150361686945
2023-01-23 04:17:46.932278: step: 644/533, loss: 9.250640869140625e-05
2023-01-23 04:17:48.076381: step: 648/533, loss: 0.0032339096069335938
2023-01-23 04:17:49.259021: step: 652/533, loss: 0.08789139240980148
2023-01-23 04:17:50.440297: step: 656/533, loss: 0.0018465996254235506
2023-01-23 04:17:51.634162: step: 660/533, loss: 0.01641969569027424
2023-01-23 04:17:52.815712: step: 664/533, loss: 1.4019013178767636e-05
2023-01-23 04:17:54.002616: step: 668/533, loss: 0.006941699888557196
2023-01-23 04:17:55.163513: step: 672/533, loss: 0.00023593902005814016
2023-01-23 04:17:56.359448: step: 676/533, loss: 0.009453010745346546
2023-01-23 04:17:57.565447: step: 680/533, loss: 0.0004684448358602822
2023-01-23 04:17:58.736470: step: 684/533, loss: 6.790161569369957e-05
2023-01-23 04:17:59.909431: step: 688/533, loss: 0.013985968194901943
2023-01-23 04:18:01.110972: step: 692/533, loss: 0.0026304246857762337
2023-01-23 04:18:02.296594: step: 696/533, loss: 0.00792837142944336
2023-01-23 04:18:03.527663: step: 700/533, loss: 0.015484190545976162
2023-01-23 04:18:04.687129: step: 704/533, loss: 0.00025806427584029734
2023-01-23 04:18:05.883803: step: 708/533, loss: 2.245903124276083e-05
2023-01-23 04:18:07.070716: step: 712/533, loss: 0.03350868448615074
2023-01-23 04:18:08.245614: step: 716/533, loss: 4.6253204345703125e-05
2023-01-23 04:18:09.373393: step: 720/533, loss: 0.02397127076983452
2023-01-23 04:18:10.510633: step: 724/533, loss: 0.0016825676430016756
2023-01-23 04:18:11.711365: step: 728/533, loss: 9.088516526389867e-05
2023-01-23 04:18:12.910407: step: 732/533, loss: 0.013457870110869408
2023-01-23 04:18:14.069108: step: 736/533, loss: 0.0016349792713299394
2023-01-23 04:18:15.236296: step: 740/533, loss: 0.001959133194759488
2023-01-23 04:18:16.448591: step: 744/533, loss: 0.0008723259088583291
2023-01-23 04:18:17.634546: step: 748/533, loss: 0.0002521514834370464
2023-01-23 04:18:18.816128: step: 752/533, loss: 0.0005171776283532381
2023-01-23 04:18:19.987729: step: 756/533, loss: 0.024413015693426132
2023-01-23 04:18:21.123595: step: 760/533, loss: 2.098083541568485e-06
2023-01-23 04:18:22.287948: step: 764/533, loss: 0.00033254624577239156
2023-01-23 04:18:23.469289: step: 768/533, loss: 7.4386593951203395e-06
2023-01-23 04:18:24.683100: step: 772/533, loss: 0.0003940582391805947
2023-01-23 04:18:25.855737: step: 776/533, loss: 0.0003329276805743575
2023-01-23 04:18:27.043707: step: 780/533, loss: 0.0011396408081054688
2023-01-23 04:18:28.212208: step: 784/533, loss: 0.08072586357593536
2023-01-23 04:18:29.406766: step: 788/533, loss: 0.0035265921615064144
2023-01-23 04:18:30.612436: step: 792/533, loss: 0.0005336761241778731
2023-01-23 04:18:31.761277: step: 796/533, loss: 0.009946012869477272
2023-01-23 04:18:32.937251: step: 800/533, loss: 0.0023246766068041325
2023-01-23 04:18:34.105126: step: 804/533, loss: 0.004134082701057196
2023-01-23 04:18:35.298416: step: 808/533, loss: 0.00019073486328125
2023-01-23 04:18:36.524263: step: 812/533, loss: 0.03328218311071396
2023-01-23 04:18:37.708957: step: 816/533, loss: 0.01727275922894478
2023-01-23 04:18:38.910154: step: 820/533, loss: 0.12867556512355804
2023-01-23 04:18:40.054954: step: 824/533, loss: 0.0018402099376544356
2023-01-23 04:18:41.270849: step: 828/533, loss: 0.05869045481085777
2023-01-23 04:18:42.458889: step: 832/533, loss: 0.038787271827459335
2023-01-23 04:18:43.644305: step: 836/533, loss: 0.010917281731963158
2023-01-23 04:18:44.761345: step: 840/533, loss: 0.0007252693176269531
2023-01-23 04:18:45.941170: step: 844/533, loss: 0.9349040985107422
2023-01-23 04:18:47.104471: step: 848/533, loss: 8.03947405074723e-05
2023-01-23 04:18:48.289927: step: 852/533, loss: 0.0007444858201779425
2023-01-23 04:18:49.500493: step: 856/533, loss: 0.015094757080078125
2023-01-23 04:18:50.637757: step: 860/533, loss: 0.0014700889587402344
2023-01-23 04:18:51.799700: step: 864/533, loss: 2.403259350103326e-05
2023-01-23 04:18:52.934136: step: 868/533, loss: 0.0002386093110544607
2023-01-23 04:18:54.132573: step: 872/533, loss: 1.3208388736529741e-05
2023-01-23 04:18:55.343563: step: 876/533, loss: 0.0007001876947470009
2023-01-23 04:18:56.525299: step: 880/533, loss: 0.0047089578583836555
2023-01-23 04:18:57.701849: step: 884/533, loss: 3.814697265625e-06
2023-01-23 04:18:58.861817: step: 888/533, loss: 7.781983003951609e-05
2023-01-23 04:18:59.996931: step: 892/533, loss: 0.020638607442378998
2023-01-23 04:19:01.141427: step: 896/533, loss: 0.0002821922244038433
2023-01-23 04:19:02.267793: step: 900/533, loss: 0.0010000229813158512
2023-01-23 04:19:03.450508: step: 904/533, loss: 0.013739585876464844
2023-01-23 04:19:04.603338: step: 908/533, loss: 0.0005388259887695312
2023-01-23 04:19:05.831561: step: 912/533, loss: 0.0003123283386230469
2023-01-23 04:19:07.009277: step: 916/533, loss: 0.0003717422659974545
2023-01-23 04:19:08.255712: step: 920/533, loss: 0.0005903244018554688
2023-01-23 04:19:09.386707: step: 924/533, loss: 0.01337890699505806
2023-01-23 04:19:10.545192: step: 928/533, loss: 0.00024890899658203125
2023-01-23 04:19:11.688168: step: 932/533, loss: 5.340576535672881e-06
2023-01-23 04:19:12.878850: step: 936/533, loss: 0.0008636951679363847
2023-01-23 04:19:14.059387: step: 940/533, loss: 0.001029872801154852
2023-01-23 04:19:15.204982: step: 944/533, loss: 0.00025329593336209655
2023-01-23 04:19:16.365260: step: 948/533, loss: 1.0681153071345761e-05
2023-01-23 04:19:17.549771: step: 952/533, loss: 1.0013579867518274e-06
2023-01-23 04:19:18.744954: step: 956/533, loss: 1.0871887752728071e-05
2023-01-23 04:19:19.915972: step: 960/533, loss: 0.599378764629364
2023-01-23 04:19:21.114675: step: 964/533, loss: 0.045965004712343216
2023-01-23 04:19:22.294572: step: 968/533, loss: 0.006877326872199774
2023-01-23 04:19:23.482500: step: 972/533, loss: 0.0017168044578284025
2023-01-23 04:19:24.665545: step: 976/533, loss: 0.015292549505829811
2023-01-23 04:19:25.836740: step: 980/533, loss: 0.010364246554672718
2023-01-23 04:19:26.997709: step: 984/533, loss: 0.0005341529613360763
2023-01-23 04:19:28.136441: step: 988/533, loss: 0.0003478527069091797
2023-01-23 04:19:29.271158: step: 992/533, loss: 0.0008901596302166581
2023-01-23 04:19:30.416806: step: 996/533, loss: 0.051703836768865585
2023-01-23 04:19:31.603666: step: 1000/533, loss: 2.6226043701171875e-05
2023-01-23 04:19:32.847765: step: 1004/533, loss: 0.0009669304126873612
2023-01-23 04:19:33.996142: step: 1008/533, loss: 0.002134704729542136
2023-01-23 04:19:35.178515: step: 1012/533, loss: 0.005488729570060968
2023-01-23 04:19:36.390601: step: 1016/533, loss: 0.0002879142703022808
2023-01-23 04:19:37.581289: step: 1020/533, loss: 0.0007899284246377647
2023-01-23 04:19:38.713656: step: 1024/533, loss: 0.00017375947209075093
2023-01-23 04:19:39.892189: step: 1028/533, loss: 0.0008118629921227694
2023-01-23 04:19:41.100954: step: 1032/533, loss: 0.01477889996021986
2023-01-23 04:19:42.295181: step: 1036/533, loss: 0.0010653972858563066
2023-01-23 04:19:43.466645: step: 1040/533, loss: 0.004500294104218483
2023-01-23 04:19:44.620959: step: 1044/533, loss: 0.0009019851568154991
2023-01-23 04:19:45.782846: step: 1048/533, loss: 0.034046366810798645
2023-01-23 04:19:46.978463: step: 1052/533, loss: 0.0005244255298748612
2023-01-23 04:19:48.200996: step: 1056/533, loss: 0.0019186020363122225
2023-01-23 04:19:49.396813: step: 1060/533, loss: 1.8930435544461943e-05
2023-01-23 04:19:50.584517: step: 1064/533, loss: 0.0006726741557940841
2023-01-23 04:19:51.744208: step: 1068/533, loss: 0.0031662462279200554
2023-01-23 04:19:52.965890: step: 1072/533, loss: 0.0001829147367971018
2023-01-23 04:19:54.158519: step: 1076/533, loss: 0.02013077773153782
2023-01-23 04:19:55.315135: step: 1080/533, loss: 7.314682443393394e-05
2023-01-23 04:19:56.497709: step: 1084/533, loss: 0.006153106689453125
2023-01-23 04:19:57.660290: step: 1088/533, loss: 0.00039653776912018657
2023-01-23 04:19:58.829508: step: 1092/533, loss: 0.0010359525913372636
2023-01-23 04:19:59.979145: step: 1096/533, loss: 1.1587142580538057e-05
2023-01-23 04:20:01.105481: step: 1100/533, loss: 0.011453533545136452
2023-01-23 04:20:02.293210: step: 1104/533, loss: 0.004266834352165461
2023-01-23 04:20:03.470341: step: 1108/533, loss: 0.6015817523002625
2023-01-23 04:20:04.650575: step: 1112/533, loss: 0.00026664737379178405
2023-01-23 04:20:05.824475: step: 1116/533, loss: 5.607604907709174e-05
2023-01-23 04:20:07.022115: step: 1120/533, loss: 0.03093128278851509
2023-01-23 04:20:08.208778: step: 1124/533, loss: 0.46698227524757385
2023-01-23 04:20:09.412474: step: 1128/533, loss: 0.4058647155761719
2023-01-23 04:20:10.583270: step: 1132/533, loss: 0.0016777992714196444
2023-01-23 04:20:11.725113: step: 1136/533, loss: 0.00014381408982444555
2023-01-23 04:20:12.909252: step: 1140/533, loss: 0.013336563482880592
2023-01-23 04:20:14.100048: step: 1144/533, loss: 0.0003948211669921875
2023-01-23 04:20:15.309564: step: 1148/533, loss: 8.20159948489163e-06
2023-01-23 04:20:16.475208: step: 1152/533, loss: 7.953644671943039e-05
2023-01-23 04:20:17.706598: step: 1156/533, loss: 6.70433000777848e-05
2023-01-23 04:20:18.854973: step: 1160/533, loss: 0.20153702795505524
2023-01-23 04:20:20.048521: step: 1164/533, loss: 0.02801218070089817
2023-01-23 04:20:21.185184: step: 1168/533, loss: 0.051758669316768646
2023-01-23 04:20:22.351341: step: 1172/533, loss: 0.007121944800019264
2023-01-23 04:20:23.498787: step: 1176/533, loss: 4.5442582631949335e-05
2023-01-23 04:20:24.711680: step: 1180/533, loss: 0.005846786312758923
2023-01-23 04:20:25.868315: step: 1184/533, loss: 0.0016781806480139494
2023-01-23 04:20:27.056560: step: 1188/533, loss: 0.00016689300537109375
2023-01-23 04:20:28.239465: step: 1192/533, loss: 0.012545204721391201
2023-01-23 04:20:29.408245: step: 1196/533, loss: 0.0010945319663733244
2023-01-23 04:20:30.608266: step: 1200/533, loss: 0.03044452704489231
2023-01-23 04:20:31.833436: step: 1204/533, loss: 0.005610752385109663
2023-01-23 04:20:32.993363: step: 1208/533, loss: 4.5347213017521426e-05
2023-01-23 04:20:34.183345: step: 1212/533, loss: 0.0028774261008948088
2023-01-23 04:20:35.363383: step: 1216/533, loss: 0.029937315732240677
2023-01-23 04:20:36.541537: step: 1220/533, loss: 0.00047178269596770406
2023-01-23 04:20:37.726892: step: 1224/533, loss: 2.727508581301663e-05
2023-01-23 04:20:38.902706: step: 1228/533, loss: 1.9836426872643642e-05
2023-01-23 04:20:40.109218: step: 1232/533, loss: 0.00942077673971653
2023-01-23 04:20:41.257987: step: 1236/533, loss: 0.0005599975702352822
2023-01-23 04:20:42.434429: step: 1240/533, loss: 0.03793029487133026
2023-01-23 04:20:43.594501: step: 1244/533, loss: 0.001160144922323525
2023-01-23 04:20:44.789593: step: 1248/533, loss: 0.0005642891046591103
2023-01-23 04:20:45.983809: step: 1252/533, loss: 0.12300319969654083
2023-01-23 04:20:47.179830: step: 1256/533, loss: 0.0025081634521484375
2023-01-23 04:20:48.330877: step: 1260/533, loss: 0.00015316010103560984
2023-01-23 04:20:49.517376: step: 1264/533, loss: 0.0003952980041503906
2023-01-23 04:20:50.693245: step: 1268/533, loss: 0.04303998872637749
2023-01-23 04:20:51.869047: step: 1272/533, loss: 0.009730529971420765
2023-01-23 04:20:53.051205: step: 1276/533, loss: 0.011086845770478249
2023-01-23 04:20:54.233556: step: 1280/533, loss: 0.000935459160245955
2023-01-23 04:20:55.404896: step: 1284/533, loss: 8.659363084007055e-05
2023-01-23 04:20:56.558124: step: 1288/533, loss: 0.040098000317811966
2023-01-23 04:20:57.742922: step: 1292/533, loss: 0.026552582159638405
2023-01-23 04:20:58.901333: step: 1296/533, loss: 1.6331673577951733e-06
2023-01-23 04:21:00.070378: step: 1300/533, loss: 0.00018215179443359375
2023-01-23 04:21:01.244575: step: 1304/533, loss: 1.010894811770413e-05
2023-01-23 04:21:02.434432: step: 1308/533, loss: 0.0017570494674146175
2023-01-23 04:21:03.561227: step: 1312/533, loss: 0.0001998901425395161
2023-01-23 04:21:04.729028: step: 1316/533, loss: 0.00016136169142555445
2023-01-23 04:21:05.947413: step: 1320/533, loss: 0.013141632080078125
2023-01-23 04:21:07.103828: step: 1324/533, loss: 0.0237717404961586
2023-01-23 04:21:08.230589: step: 1328/533, loss: 0.0001028060942189768
2023-01-23 04:21:09.424910: step: 1332/533, loss: 1.3065337952866685e-05
2023-01-23 04:21:10.571569: step: 1336/533, loss: 0.0016981124645099044
2023-01-23 04:21:11.711615: step: 1340/533, loss: 5.855560448253527e-05
2023-01-23 04:21:12.900603: step: 1344/533, loss: 0.001315641449764371
2023-01-23 04:21:14.061422: step: 1348/533, loss: 0.015293121337890625
2023-01-23 04:21:15.243465: step: 1352/533, loss: 8.449554297840223e-05
2023-01-23 04:21:16.454452: step: 1356/533, loss: 0.01225423812866211
2023-01-23 04:21:17.662668: step: 1360/533, loss: 0.0001655578671488911
2023-01-23 04:21:18.831368: step: 1364/533, loss: 4.024505687993951e-05
2023-01-23 04:21:20.003080: step: 1368/533, loss: 0.0024289607536047697
2023-01-23 04:21:21.239180: step: 1372/533, loss: 5.9700014389818534e-05
2023-01-23 04:21:22.425626: step: 1376/533, loss: 0.001974773360416293
2023-01-23 04:21:23.625667: step: 1380/533, loss: 3.1471254260395654e-06
2023-01-23 04:21:24.808917: step: 1384/533, loss: 0.0027975081466138363
2023-01-23 04:21:26.023632: step: 1388/533, loss: 1.1682510375976562e-05
2023-01-23 04:21:27.176786: step: 1392/533, loss: 0.0029973983764648438
2023-01-23 04:21:28.325608: step: 1396/533, loss: 0.0010484710801392794
2023-01-23 04:21:29.513380: step: 1400/533, loss: 0.032292939722537994
2023-01-23 04:21:30.673338: step: 1404/533, loss: 0.05029275640845299
2023-01-23 04:21:31.860171: step: 1408/533, loss: 0.0003791809140238911
2023-01-23 04:21:33.033780: step: 1412/533, loss: 1.6117097402457148e-05
2023-01-23 04:21:34.177890: step: 1416/533, loss: 0.0002233505219919607
2023-01-23 04:21:35.370106: step: 1420/533, loss: 2.6798248654813506e-05
2023-01-23 04:21:36.557362: step: 1424/533, loss: 0.07446031272411346
2023-01-23 04:21:37.720834: step: 1428/533, loss: 0.11768770962953568
2023-01-23 04:21:38.895155: step: 1432/533, loss: 0.02891254611313343
2023-01-23 04:21:40.107347: step: 1436/533, loss: 1.869201696536038e-05
2023-01-23 04:21:41.277640: step: 1440/533, loss: 8.401871309615672e-05
2023-01-23 04:21:42.476489: step: 1444/533, loss: 0.038555338978767395
2023-01-23 04:21:43.606815: step: 1448/533, loss: 0.0002514839288778603
2023-01-23 04:21:44.790444: step: 1452/533, loss: 4.138946678722277e-05
2023-01-23 04:21:45.962394: step: 1456/533, loss: 0.01672077178955078
2023-01-23 04:21:47.141238: step: 1460/533, loss: 0.010339641943573952
2023-01-23 04:21:48.330351: step: 1464/533, loss: 0.0001712799130473286
2023-01-23 04:21:49.545861: step: 1468/533, loss: 0.06185588985681534
2023-01-23 04:21:50.680518: step: 1472/533, loss: 1.0013580322265625e-05
2023-01-23 04:21:51.837933: step: 1476/533, loss: 0.008479214273393154
2023-01-23 04:21:53.004804: step: 1480/533, loss: 0.0011293411953374743
2023-01-23 04:21:54.158443: step: 1484/533, loss: 0.02370147779583931
2023-01-23 04:21:55.338506: step: 1488/533, loss: 0.0016771316295489669
2023-01-23 04:21:56.508826: step: 1492/533, loss: 0.0001272201625397429
2023-01-23 04:21:57.685742: step: 1496/533, loss: 0.009363556280732155
2023-01-23 04:21:58.854084: step: 1500/533, loss: 0.00040836335392668843
2023-01-23 04:21:59.976886: step: 1504/533, loss: 0.00010375976853538305
2023-01-23 04:22:01.205177: step: 1508/533, loss: 0.0006948471418581903
2023-01-23 04:22:02.395228: step: 1512/533, loss: 0.00017180443683173507
2023-01-23 04:22:03.564564: step: 1516/533, loss: 0.0001964569091796875
2023-01-23 04:22:04.694140: step: 1520/533, loss: 0.0019647120498120785
2023-01-23 04:22:05.907040: step: 1524/533, loss: 4.310607982915826e-05
2023-01-23 04:22:07.091507: step: 1528/533, loss: 3.490447852527723e-05
2023-01-23 04:22:08.284044: step: 1532/533, loss: 0.00022830962552689016
2023-01-23 04:22:09.402407: step: 1536/533, loss: 0.0016679763793945312
2023-01-23 04:22:10.553028: step: 1540/533, loss: 0.002149868058040738
2023-01-23 04:22:11.770238: step: 1544/533, loss: 0.00040092470590025187
2023-01-23 04:22:12.935093: step: 1548/533, loss: 0.006554603576660156
2023-01-23 04:22:14.105246: step: 1552/533, loss: 5.722046125811175e-07
2023-01-23 04:22:15.233151: step: 1556/533, loss: 0.0026386261451989412
2023-01-23 04:22:16.382286: step: 1560/533, loss: 0.002605438232421875
2023-01-23 04:22:17.555335: step: 1564/533, loss: 0.007409798912703991
2023-01-23 04:22:18.749537: step: 1568/533, loss: 2.117157055181451e-05
2023-01-23 04:22:19.943583: step: 1572/533, loss: 0.0017765044467523694
2023-01-23 04:22:21.110183: step: 1576/533, loss: 0.014275645837187767
2023-01-23 04:22:22.245066: step: 1580/533, loss: 7.872581045376137e-05
2023-01-23 04:22:23.396482: step: 1584/533, loss: 2.498626781743951e-05
2023-01-23 04:22:24.566793: step: 1588/533, loss: 0.00115795130841434
2023-01-23 04:22:25.736046: step: 1592/533, loss: 5.145073009771295e-05
2023-01-23 04:22:26.965246: step: 1596/533, loss: 0.0002783775271382183
2023-01-23 04:22:28.126386: step: 1600/533, loss: 0.0013859749305993319
2023-01-23 04:22:29.315654: step: 1604/533, loss: 0.09344358742237091
2023-01-23 04:22:30.477795: step: 1608/533, loss: 0.0003075599670410156
2023-01-23 04:22:31.683197: step: 1612/533, loss: 0.0008344650268554688
2023-01-23 04:22:32.876000: step: 1616/533, loss: 0.001014804933220148
2023-01-23 04:22:34.049499: step: 1620/533, loss: 0.0007132529863156378
2023-01-23 04:22:35.221969: step: 1624/533, loss: 9.689331636764109e-05
2023-01-23 04:22:36.442293: step: 1628/533, loss: 0.5569049715995789
2023-01-23 04:22:37.617120: step: 1632/533, loss: 0.04131278768181801
2023-01-23 04:22:38.785665: step: 1636/533, loss: 0.0006598949548788369
2023-01-23 04:22:39.969135: step: 1640/533, loss: 0.8051006197929382
2023-01-23 04:22:41.121714: step: 1644/533, loss: 0.0003419399436097592
2023-01-23 04:22:42.278035: step: 1648/533, loss: 0.00048828125
2023-01-23 04:22:43.459808: step: 1652/533, loss: 0.015282916836440563
2023-01-23 04:22:44.648420: step: 1656/533, loss: 0.0034267425071448088
2023-01-23 04:22:45.784243: step: 1660/533, loss: 0.00016379357839468867
2023-01-23 04:22:46.954036: step: 1664/533, loss: 0.00534820556640625
2023-01-23 04:22:48.113420: step: 1668/533, loss: 0.00021829605975653976
2023-01-23 04:22:49.291673: step: 1672/533, loss: 0.004005813971161842
2023-01-23 04:22:50.474915: step: 1676/533, loss: -1.316070574830519e-05
2023-01-23 04:22:51.614967: step: 1680/533, loss: 4.348754737293348e-05
2023-01-23 04:22:52.834327: step: 1684/533, loss: 5.378723290050402e-05
2023-01-23 04:22:53.976922: step: 1688/533, loss: 0.004181433003395796
2023-01-23 04:22:55.139910: step: 1692/533, loss: 5.292892637953628e-06
2023-01-23 04:22:56.302837: step: 1696/533, loss: 0.0015766143333166838
2023-01-23 04:22:57.470695: step: 1700/533, loss: 0.0006336212391033769
2023-01-23 04:22:58.642233: step: 1704/533, loss: 0.00013790131197310984
2023-01-23 04:22:59.788463: step: 1708/533, loss: 0.00092315673828125
2023-01-23 04:23:00.970595: step: 1712/533, loss: 0.009691429324448109
2023-01-23 04:23:02.121080: step: 1716/533, loss: 0.00014019013906363398
2023-01-23 04:23:03.271976: step: 1720/533, loss: 0.0008672714466229081
2023-01-23 04:23:04.413682: step: 1724/533, loss: 2.9087066195643274e-06
2023-01-23 04:23:05.583580: step: 1728/533, loss: 3.4141543437726796e-05
2023-01-23 04:23:06.809334: step: 1732/533, loss: 7.724762690486386e-05
2023-01-23 04:23:08.008678: step: 1736/533, loss: 0.0018504143226891756
2023-01-23 04:23:09.158213: step: 1740/533, loss: 0.0002808570861816406
2023-01-23 04:23:10.303041: step: 1744/533, loss: 0.03470306470990181
2023-01-23 04:23:11.497352: step: 1748/533, loss: 0.0001253128139069304
2023-01-23 04:23:12.701150: step: 1752/533, loss: 0.0007068634149618447
2023-01-23 04:23:13.906859: step: 1756/533, loss: 3.61442580469884e-05
2023-01-23 04:23:15.034882: step: 1760/533, loss: 3.25202927342616e-05
2023-01-23 04:23:16.232158: step: 1764/533, loss: 9.241104271495715e-05
2023-01-23 04:23:17.416007: step: 1768/533, loss: 0.0008534431108273566
2023-01-23 04:23:18.587972: step: 1772/533, loss: 0.004237615969032049
2023-01-23 04:23:19.778762: step: 1776/533, loss: 0.005154228303581476
2023-01-23 04:23:20.916691: step: 1780/533, loss: 0.30229464173316956
2023-01-23 04:23:22.077385: step: 1784/533, loss: 0.0005659103626385331
2023-01-23 04:23:23.223223: step: 1788/533, loss: 0.0009385109296999872
2023-01-23 04:23:24.356863: step: 1792/533, loss: 2.6941299438476562e-05
2023-01-23 04:23:25.555236: step: 1796/533, loss: 0.0019096375908702612
2023-01-23 04:23:26.712046: step: 1800/533, loss: 0.00014696121797896922
2023-01-23 04:23:27.896893: step: 1804/533, loss: 0.00023689270892646164
2023-01-23 04:23:29.059780: step: 1808/533, loss: 8.39233416627394e-06
2023-01-23 04:23:30.188206: step: 1812/533, loss: 0.030894756317138672
2023-01-23 04:23:31.358448: step: 1816/533, loss: 0.0019169808365404606
2023-01-23 04:23:32.530072: step: 1820/533, loss: -1.106262243411038e-05
2023-01-23 04:23:33.750633: step: 1824/533, loss: 0.0003183365042787045
2023-01-23 04:23:34.991628: step: 1828/533, loss: 6.50405854685232e-05
2023-01-23 04:23:36.155899: step: 1832/533, loss: 0.0013456344604492188
2023-01-23 04:23:37.308345: step: 1836/533, loss: 6.961822509765625e-05
2023-01-23 04:23:38.478809: step: 1840/533, loss: 0.017479753121733665
2023-01-23 04:23:39.632584: step: 1844/533, loss: 5.970001075183973e-05
2023-01-23 04:23:40.777531: step: 1848/533, loss: -4.95910626341356e-06
2023-01-23 04:23:41.993443: step: 1852/533, loss: 1.5354156857938506e-05
2023-01-23 04:23:43.173141: step: 1856/533, loss: 0.00021991730318404734
2023-01-23 04:23:44.369494: step: 1860/533, loss: 3.409385681152344e-05
2023-01-23 04:23:45.555457: step: 1864/533, loss: 0.04563913494348526
2023-01-23 04:23:46.786171: step: 1868/533, loss: 0.0006259918445721269
2023-01-23 04:23:47.935330: step: 1872/533, loss: 0.0003208160342182964
2023-01-23 04:23:49.115493: step: 1876/533, loss: 4.38690176451928e-06
2023-01-23 04:23:50.298791: step: 1880/533, loss: 0.016524506732821465
2023-01-23 04:23:51.464818: step: 1884/533, loss: 0.0010344504844397306
2023-01-23 04:23:52.577656: step: 1888/533, loss: 9.727478754939511e-06
2023-01-23 04:23:53.732148: step: 1892/533, loss: 0.0054416656494140625
2023-01-23 04:23:54.884937: step: 1896/533, loss: 0.0007518768543377519
2023-01-23 04:23:56.097843: step: 1900/533, loss: 0.00045452118501998484
2023-01-23 04:23:57.270883: step: 1904/533, loss: 3.814697265625e-06
2023-01-23 04:23:58.428240: step: 1908/533, loss: 3.5762786865234375e-06
2023-01-23 04:23:59.605645: step: 1912/533, loss: 0.013080311007797718
2023-01-23 04:24:00.799882: step: 1916/533, loss: 5.8650970458984375e-05
2023-01-23 04:24:01.937396: step: 1920/533, loss: 0.006737709045410156
2023-01-23 04:24:03.099179: step: 1924/533, loss: 0.00010623932757880539
2023-01-23 04:24:04.249497: step: 1928/533, loss: 0.006479215808212757
2023-01-23 04:24:05.417690: step: 1932/533, loss: 0.0008396149496547878
2023-01-23 04:24:06.601507: step: 1936/533, loss: 2.384185791015625e-05
2023-01-23 04:24:07.772425: step: 1940/533, loss: 0.0038040163926780224
2023-01-23 04:24:08.963149: step: 1944/533, loss: 2.7275087632006034e-05
2023-01-23 04:24:10.127224: step: 1948/533, loss: 0.00019674302893690765
2023-01-23 04:24:11.298766: step: 1952/533, loss: 4.276037361705676e-05
2023-01-23 04:24:12.436465: step: 1956/533, loss: 0.002428436418995261
2023-01-23 04:24:13.626557: step: 1960/533, loss: 0.0007152557955123484
2023-01-23 04:24:14.805069: step: 1964/533, loss: 6.198883056640625e-05
2023-01-23 04:24:15.968413: step: 1968/533, loss: 7.057190487103071e-06
2023-01-23 04:24:17.137454: step: 1972/533, loss: 0.0029434680473059416
2023-01-23 04:24:18.318236: step: 1976/533, loss: 0.0020652771927416325
2023-01-23 04:24:19.531976: step: 1980/533, loss: 0.02981853485107422
2023-01-23 04:24:20.718020: step: 1984/533, loss: 0.00014734269643668085
2023-01-23 04:24:21.873346: step: 1988/533, loss: 0.00014128685870673507
2023-01-23 04:24:23.059337: step: 1992/533, loss: 1.296997106692288e-05
2023-01-23 04:24:24.229303: step: 1996/533, loss: 0.00013809204392600805
2023-01-23 04:24:25.375862: step: 2000/533, loss: 0.008411980234086514
2023-01-23 04:24:26.575611: step: 2004/533, loss: 0.06284943222999573
2023-01-23 04:24:27.701541: step: 2008/533, loss: 0.0012033461825922132
2023-01-23 04:24:28.880142: step: 2012/533, loss: 2.5320052372990176e-05
2023-01-23 04:24:30.057690: step: 2016/533, loss: 0.006291294004768133
2023-01-23 04:24:31.223888: step: 2020/533, loss: 0.0004938125493936241
2023-01-23 04:24:32.398881: step: 2024/533, loss: 0.0012397767277434468
2023-01-23 04:24:33.592631: step: 2028/533, loss: 0.011632729321718216
2023-01-23 04:24:34.797762: step: 2032/533, loss: 0.005409622564911842
2023-01-23 04:24:35.968787: step: 2036/533, loss: 7.095337059581652e-05
2023-01-23 04:24:37.154687: step: 2040/533, loss: 0.0026950836181640625
2023-01-23 04:24:38.354262: step: 2044/533, loss: 0.0006472587701864541
2023-01-23 04:24:39.507409: step: 2048/533, loss: 1.4686585018353071e-05
2023-01-23 04:24:40.706282: step: 2052/533, loss: 0.02822704240679741
2023-01-23 04:24:41.887954: step: 2056/533, loss: 4.487037949729711e-05
2023-01-23 04:24:43.022759: step: 2060/533, loss: 0.0025330542121082544
2023-01-23 04:24:44.180481: step: 2064/533, loss: 4.954338146490045e-05
2023-01-23 04:24:45.342513: step: 2068/533, loss: 0.02870206907391548
2023-01-23 04:24:46.447396: step: 2072/533, loss: 0.00018787382578011602
2023-01-23 04:24:47.647460: step: 2076/533, loss: 4.38690176451928e-06
2023-01-23 04:24:48.848335: step: 2080/533, loss: 0.012172508984804153
2023-01-23 04:24:50.043694: step: 2084/533, loss: 0.09059123694896698
2023-01-23 04:24:51.180497: step: 2088/533, loss: 0.0024335861671715975
2023-01-23 04:24:52.321029: step: 2092/533, loss: 4.0435788832837716e-05
2023-01-23 04:24:53.509348: step: 2096/533, loss: 0.0021583556663244963
2023-01-23 04:24:54.685634: step: 2100/533, loss: 0.0218061450868845
2023-01-23 04:24:55.864737: step: 2104/533, loss: 0.01072168443351984
2023-01-23 04:24:57.027796: step: 2108/533, loss: -4.19616708313697e-06
2023-01-23 04:24:58.224112: step: 2112/533, loss: 0.00042304996168240905
2023-01-23 04:24:59.403042: step: 2116/533, loss: 0.0009634971502237022
2023-01-23 04:25:00.571956: step: 2120/533, loss: 0.00010538101196289062
2023-01-23 04:25:01.713906: step: 2124/533, loss: 0.012665748596191406
2023-01-23 04:25:02.899111: step: 2128/533, loss: 0.048429109156131744
2023-01-23 04:25:04.037538: step: 2132/533, loss: 1.5354156857938506e-05
==================================================
Loss: 0.020
--------------------
Dev: {'event': {'p': 0.6211453744493393, 'r': 0.7509986684420772, 'f1': 0.6799276672694394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6510660426417056, 'r': 0.8005115089514067, 'f1': 0.7180957843418411}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5357142857142857, 'r': 0.8333333333333334, 'f1': 0.6521739130434783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.6, 'r': 0.5714285714285714, 'f1': 0.5853658536585366}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.48484848484848486, 'r': 0.4444444444444444, 'f1': 0.463768115942029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Chinese: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Chinese: {'event': {'p': 0.618421052631579, 'r': 0.8703703703703703, 'f1': 0.723076923076923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 27
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:25:45.298670: step: 4/533, loss: 3.807544999290258e-05
2023-01-23 04:25:46.460618: step: 8/533, loss: 0.00021266937255859375
2023-01-23 04:25:47.620562: step: 12/533, loss: 5.5837630497990176e-05
2023-01-23 04:25:48.807375: step: 16/533, loss: 0.007767486851662397
2023-01-23 04:25:50.023898: step: 20/533, loss: 0.9967159032821655
2023-01-23 04:25:51.222099: step: 24/533, loss: 0.0017751693958416581
2023-01-23 04:25:52.376244: step: 28/533, loss: 0.00023698806762695312
2023-01-23 04:25:53.563228: step: 32/533, loss: 0.022069884464144707
2023-01-23 04:25:54.747979: step: 36/533, loss: 0.0028072355780750513
2023-01-23 04:25:55.924756: step: 40/533, loss: 0.0034592628944665194
2023-01-23 04:25:57.098011: step: 44/533, loss: 0.006538105197250843
2023-01-23 04:25:58.300644: step: 48/533, loss: 0.51051926612854
2023-01-23 04:25:59.510085: step: 52/533, loss: 0.0002382278471486643
2023-01-23 04:26:00.629543: step: 56/533, loss: -1.9073485191256623e-07
2023-01-23 04:26:01.841330: step: 60/533, loss: 0.00017662049503996968
2023-01-23 04:26:03.033433: step: 64/533, loss: 7.700920104980469e-05
2023-01-23 04:26:04.214742: step: 68/533, loss: 0.009666157886385918
2023-01-23 04:26:05.376404: step: 72/533, loss: 0.014373588375747204
2023-01-23 04:26:06.541709: step: 76/533, loss: 0.001781463623046875
2023-01-23 04:26:07.682005: step: 80/533, loss: 0.0014844894176349044
2023-01-23 04:26:08.833258: step: 84/533, loss: 0.0009613037109375
2023-01-23 04:26:09.997849: step: 88/533, loss: 0.015164375305175781
2023-01-23 04:26:11.170895: step: 92/533, loss: 0.0005056381342001259
2023-01-23 04:26:12.360683: step: 96/533, loss: 0.05765227973461151
2023-01-23 04:26:13.486436: step: 100/533, loss: 0.00011482238915050402
2023-01-23 04:26:14.683079: step: 104/533, loss: 0.00018968583026435226
2023-01-23 04:26:15.866321: step: 108/533, loss: 0.002274131868034601
2023-01-23 04:26:17.003220: step: 112/533, loss: 0.026640035212039948
2023-01-23 04:26:18.192782: step: 116/533, loss: 0.012826728634536266
2023-01-23 04:26:19.393120: step: 120/533, loss: 0.03502178564667702
2023-01-23 04:26:20.576811: step: 124/533, loss: 0.00028486252995207906
2023-01-23 04:26:21.769824: step: 128/533, loss: 0.010875320062041283
2023-01-23 04:26:22.940718: step: 132/533, loss: 9.794234938453883e-05
2023-01-23 04:26:24.105306: step: 136/533, loss: 0.0014381409855559468
2023-01-23 04:26:25.268223: step: 140/533, loss: 4.692077709478326e-05
2023-01-23 04:26:26.427477: step: 144/533, loss: 2.3937225705594756e-05
2023-01-23 04:26:27.630243: step: 148/533, loss: 0.07252006232738495
2023-01-23 04:26:28.790880: step: 152/533, loss: 0.0008319854969158769
2023-01-23 04:26:29.945958: step: 156/533, loss: 0.41022226214408875
2023-01-23 04:26:31.080569: step: 160/533, loss: 4.806518700206652e-05
2023-01-23 04:26:32.272338: step: 164/533, loss: 0.00023412704467773438
2023-01-23 04:26:33.441844: step: 168/533, loss: 0.0007537842029705644
2023-01-23 04:26:34.566491: step: 172/533, loss: -5.14984139954322e-06
2023-01-23 04:26:35.726914: step: 176/533, loss: 0.0002980232238769531
2023-01-23 04:26:36.962879: step: 180/533, loss: 0.001044464181177318
2023-01-23 04:26:38.134909: step: 184/533, loss: 0.01426782552152872
2023-01-23 04:26:39.262969: step: 188/533, loss: 3.566742088878527e-05
2023-01-23 04:26:40.465661: step: 192/533, loss: 0.0010480880737304688
2023-01-23 04:26:41.650270: step: 196/533, loss: 0.03789710998535156
2023-01-23 04:26:42.883898: step: 200/533, loss: 0.0044303894974291325
2023-01-23 04:26:44.071356: step: 204/533, loss: 7.295608611457283e-06
2023-01-23 04:26:45.272126: step: 208/533, loss: 2.0027162463520654e-05
2023-01-23 04:26:46.444474: step: 212/533, loss: 0.00035085680428892374
2023-01-23 04:26:47.633525: step: 216/533, loss: 0.00884027499705553
2023-01-23 04:26:48.854134: step: 220/533, loss: 0.00045452118501998484
2023-01-23 04:26:50.039936: step: 224/533, loss: 0.001056671142578125
2023-01-23 04:26:51.201387: step: 228/533, loss: 0.000720977783203125
2023-01-23 04:26:52.359302: step: 232/533, loss: 0.0004276275576557964
2023-01-23 04:26:53.572630: step: 236/533, loss: 0.02678699605166912
2023-01-23 04:26:54.793845: step: 240/533, loss: 0.0009007453918457031
2023-01-23 04:26:55.997228: step: 244/533, loss: 0.0023681640159338713
2023-01-23 04:26:57.172198: step: 248/533, loss: 0.007801055442541838
2023-01-23 04:26:58.340905: step: 252/533, loss: 0.0017336845630779862
2023-01-23 04:26:59.536483: step: 256/533, loss: 0.06660271435976028
2023-01-23 04:27:00.724177: step: 260/533, loss: 0.00033373833866789937
2023-01-23 04:27:01.904147: step: 264/533, loss: 1.0824203855008818e-05
2023-01-23 04:27:03.118087: step: 268/533, loss: 0.00015802383131813258
2023-01-23 04:27:04.288266: step: 272/533, loss: 0.020971108227968216
2023-01-23 04:27:05.452511: step: 276/533, loss: 3.8814545405330136e-05
2023-01-23 04:27:06.631935: step: 280/533, loss: 0.000720596348401159
2023-01-23 04:27:07.812723: step: 284/533, loss: 0.002125263214111328
2023-01-23 04:27:09.035206: step: 288/533, loss: 0.00043773651123046875
2023-01-23 04:27:10.194514: step: 292/533, loss: 1.106262243411038e-05
2023-01-23 04:27:11.350484: step: 296/533, loss: 0.0004241943533997983
2023-01-23 04:27:12.475247: step: 300/533, loss: 3.147125607938506e-05
2023-01-23 04:27:13.602075: step: 304/533, loss: 0.000173473366885446
2023-01-23 04:27:14.781215: step: 308/533, loss: 0.024636555463075638
2023-01-23 04:27:15.952543: step: 312/533, loss: 0.01586446911096573
2023-01-23 04:27:17.116655: step: 316/533, loss: 0.0009374618530273438
2023-01-23 04:27:18.326385: step: 320/533, loss: 0.013634777627885342
2023-01-23 04:27:19.495248: step: 324/533, loss: 0.00011720657494151965
2023-01-23 04:27:20.626048: step: 328/533, loss: 2.813339506246848e-06
2023-01-23 04:27:21.795795: step: 332/533, loss: 4.482269287109375e-05
2023-01-23 04:27:22.994065: step: 336/533, loss: 6.3896181927702855e-06
2023-01-23 04:27:24.182714: step: 340/533, loss: 0.0015603393549099565
2023-01-23 04:27:25.365757: step: 344/533, loss: 0.00388164515607059
2023-01-23 04:27:26.549247: step: 348/533, loss: 0.01164708100259304
2023-01-23 04:27:27.709101: step: 352/533, loss: 0.01867714151740074
2023-01-23 04:27:28.898836: step: 356/533, loss: 0.00010871887934627011
2023-01-23 04:27:30.064796: step: 360/533, loss: 1.792907642084174e-05
2023-01-23 04:27:31.240360: step: 364/533, loss: 4.806518700206652e-05
2023-01-23 04:27:32.409545: step: 368/533, loss: 0.007267188746482134
2023-01-23 04:27:33.579213: step: 372/533, loss: 0.0607847198843956
2023-01-23 04:27:34.729632: step: 376/533, loss: -8.583069188716763e-07
2023-01-23 04:27:35.924220: step: 380/533, loss: 0.011996460147202015
2023-01-23 04:27:37.162234: step: 384/533, loss: 0.03175077587366104
2023-01-23 04:27:38.324188: step: 388/533, loss: 0.003375244326889515
2023-01-23 04:27:39.469793: step: 392/533, loss: 4.215240551275201e-05
2023-01-23 04:27:40.638388: step: 396/533, loss: 9.918212890625e-05
2023-01-23 04:27:41.786413: step: 400/533, loss: 5.8937075664289296e-05
2023-01-23 04:27:42.934193: step: 404/533, loss: -5.91278057981981e-06
2023-01-23 04:27:44.108759: step: 408/533, loss: 0.005866623017936945
2023-01-23 04:27:45.258068: step: 412/533, loss: -2.0503998712229077e-06
2023-01-23 04:27:46.460563: step: 416/533, loss: 0.0063298228196799755
2023-01-23 04:27:47.628561: step: 420/533, loss: 0.000274658203125
2023-01-23 04:27:48.834169: step: 424/533, loss: 0.005877113435417414
2023-01-23 04:27:50.020574: step: 428/533, loss: 0.0067727090790867805
2023-01-23 04:27:51.187728: step: 432/533, loss: 7.772445678710938e-05
2023-01-23 04:27:52.379900: step: 436/533, loss: 3.910065061063506e-05
2023-01-23 04:27:53.537445: step: 440/533, loss: 0.004544067196547985
2023-01-23 04:27:54.720842: step: 444/533, loss: 1.2493133908719756e-05
2023-01-23 04:27:55.863769: step: 448/533, loss: 6.046295311534777e-05
2023-01-23 04:27:57.039003: step: 452/533, loss: 0.0002361297665629536
2023-01-23 04:27:58.209730: step: 456/533, loss: 0.00035190582275390625
2023-01-23 04:27:59.364494: step: 460/533, loss: 0.0003218650817871094
2023-01-23 04:28:00.520485: step: 464/533, loss: 0.010560035705566406
2023-01-23 04:28:01.731762: step: 468/533, loss: 0.006488990969955921
2023-01-23 04:28:02.892372: step: 472/533, loss: 0.005353736691176891
2023-01-23 04:28:04.041152: step: 476/533, loss: 0.0019417285220697522
2023-01-23 04:28:05.216479: step: 480/533, loss: 6.294249942584429e-06
2023-01-23 04:28:06.402012: step: 484/533, loss: 0.0026119232643395662
2023-01-23 04:28:07.554775: step: 488/533, loss: 1.0490417707842425e-06
2023-01-23 04:28:08.764159: step: 492/533, loss: 0.013564681634306908
2023-01-23 04:28:09.957901: step: 496/533, loss: 2.9563905172835803e-06
2023-01-23 04:28:11.143679: step: 500/533, loss: 0.023888587951660156
2023-01-23 04:28:12.320267: step: 504/533, loss: 0.04116563871502876
2023-01-23 04:28:13.480260: step: 508/533, loss: 0.00047068597632460296
2023-01-23 04:28:14.655003: step: 512/533, loss: 1.1205673217773438e-05
2023-01-23 04:28:15.897853: step: 516/533, loss: 0.0050483704544603825
2023-01-23 04:28:17.063990: step: 520/533, loss: 0.0015597344608977437
2023-01-23 04:28:18.212201: step: 524/533, loss: 0.0035635950043797493
2023-01-23 04:28:19.372041: step: 528/533, loss: 2.28881845032447e-06
2023-01-23 04:28:20.500713: step: 532/533, loss: 0.0015805244911462069
2023-01-23 04:28:21.668483: step: 536/533, loss: 0.00013208390737418085
2023-01-23 04:28:22.822232: step: 540/533, loss: 0.000285911577520892
2023-01-23 04:28:23.973912: step: 544/533, loss: 9.51766996877268e-05
2023-01-23 04:28:25.183070: step: 548/533, loss: 0.006950855255126953
2023-01-23 04:28:26.364842: step: 552/533, loss: 3.6811830796068534e-05
2023-01-23 04:28:27.553715: step: 556/533, loss: 6.446838233387098e-05
2023-01-23 04:28:28.774736: step: 560/533, loss: 4.920959327137098e-05
2023-01-23 04:28:29.984052: step: 564/533, loss: 0.001375484513118863
2023-01-23 04:28:31.148416: step: 568/533, loss: 0.03983908146619797
2023-01-23 04:28:32.303190: step: 572/533, loss: 4.043579247081652e-05
2023-01-23 04:28:33.490771: step: 576/533, loss: 0.006997585296630859
2023-01-23 04:28:34.651279: step: 580/533, loss: 0.0030935765244066715
2023-01-23 04:28:35.788963: step: 584/533, loss: 5.7220458984375e-05
2023-01-23 04:28:36.981201: step: 588/533, loss: 0.0029630661010742188
2023-01-23 04:28:38.159149: step: 592/533, loss: 0.03827390819787979
2023-01-23 04:28:39.351824: step: 596/533, loss: 0.06122303009033203
2023-01-23 04:28:40.507072: step: 600/533, loss: 0.00024874211521819234
2023-01-23 04:28:41.655731: step: 604/533, loss: 0.00014429092698264867
2023-01-23 04:28:42.859184: step: 608/533, loss: 0.005464363377541304
2023-01-23 04:28:44.035091: step: 612/533, loss: 1.5258789289873675e-06
2023-01-23 04:28:45.255374: step: 616/533, loss: 0.0035102844703942537
2023-01-23 04:28:46.407401: step: 620/533, loss: 0.00526008615270257
2023-01-23 04:28:47.576011: step: 624/533, loss: 0.0005893707275390625
2023-01-23 04:28:48.792407: step: 628/533, loss: 0.0026865960098803043
2023-01-23 04:28:49.992955: step: 632/533, loss: 0.0006772995693609118
2023-01-23 04:28:51.185444: step: 636/533, loss: 0.00025959016056731343
2023-01-23 04:28:52.405680: step: 640/533, loss: 0.0017457961803302169
2023-01-23 04:28:53.530098: step: 644/533, loss: 0.006958675570785999
2023-01-23 04:28:54.683286: step: 648/533, loss: 2.0313264030846767e-05
2023-01-23 04:28:55.853851: step: 652/533, loss: 0.00019569396681617945
2023-01-23 04:28:57.021934: step: 656/533, loss: 0.0028858184814453125
2023-01-23 04:28:58.185311: step: 660/533, loss: 0.0032699585426598787
2023-01-23 04:28:59.410329: step: 664/533, loss: 0.0007886886596679688
2023-01-23 04:29:00.600765: step: 668/533, loss: 0.013704395852982998
2023-01-23 04:29:01.740297: step: 672/533, loss: 0.0003761291445698589
2023-01-23 04:29:02.900709: step: 676/533, loss: 0.0061893463134765625
2023-01-23 04:29:04.098546: step: 680/533, loss: 0.0010457038879394531
2023-01-23 04:29:05.270365: step: 684/533, loss: 4.177093433099799e-05
2023-01-23 04:29:06.444125: step: 688/533, loss: 2.975463939947076e-05
2023-01-23 04:29:07.621179: step: 692/533, loss: 0.0013466834789142013
2023-01-23 04:29:08.775728: step: 696/533, loss: 0.00013155341730453074
2023-01-23 04:29:09.934742: step: 700/533, loss: 3.6525725590763614e-05
2023-01-23 04:29:11.082483: step: 704/533, loss: 0.0008505344158038497
2023-01-23 04:29:12.273668: step: 708/533, loss: 0.0019144058460369706
2023-01-23 04:29:13.449699: step: 712/533, loss: 0.0015656471950933337
2023-01-23 04:29:14.617849: step: 716/533, loss: 1.544952465337701e-05
2023-01-23 04:29:15.779742: step: 720/533, loss: 8.106231689453125e-06
2023-01-23 04:29:16.942808: step: 724/533, loss: 2.6702880859375e-05
2023-01-23 04:29:18.130562: step: 728/533, loss: 0.04627342149615288
2023-01-23 04:29:19.310362: step: 732/533, loss: 0.0053611756302416325
2023-01-23 04:29:20.475092: step: 736/533, loss: 0.0007402420742437243
2023-01-23 04:29:21.593321: step: 740/533, loss: 0.0005681038019247353
2023-01-23 04:29:22.757200: step: 744/533, loss: 0.009149361401796341
2023-01-23 04:29:23.929859: step: 748/533, loss: 0.0006128310924395919
2023-01-23 04:29:25.099651: step: 752/533, loss: 6.88552827341482e-05
2023-01-23 04:29:26.267177: step: 756/533, loss: 0.013961220160126686
2023-01-23 04:29:27.470748: step: 760/533, loss: 0.007540511898696423
2023-01-23 04:29:28.664133: step: 764/533, loss: 0.0015172958374023438
2023-01-23 04:29:29.831533: step: 768/533, loss: 2.117157055181451e-05
2023-01-23 04:29:30.996926: step: 772/533, loss: 0.00021724702673964202
2023-01-23 04:29:32.154714: step: 776/533, loss: 0.0002311706484761089
2023-01-23 04:29:33.373710: step: 780/533, loss: 0.05750885233283043
2023-01-23 04:29:34.515029: step: 784/533, loss: 0.0005660057067871094
2023-01-23 04:29:35.671282: step: 788/533, loss: 2.0647050405386835e-05
2023-01-23 04:29:36.837916: step: 792/533, loss: 0.00044736862764693797
2023-01-23 04:29:37.985307: step: 796/533, loss: 0.0006258010980673134
2023-01-23 04:29:39.144151: step: 800/533, loss: 0.0001451492280466482
2023-01-23 04:29:40.332325: step: 804/533, loss: 0.00026073455228470266
2023-01-23 04:29:41.511319: step: 808/533, loss: 0.02436218410730362
2023-01-23 04:29:42.664644: step: 812/533, loss: 0.0007188796880654991
2023-01-23 04:29:43.849255: step: 816/533, loss: 0.0661131888628006
2023-01-23 04:29:45.056630: step: 820/533, loss: 0.0003314971982035786
2023-01-23 04:29:46.232081: step: 824/533, loss: 7.686614844715223e-05
2023-01-23 04:29:47.397560: step: 828/533, loss: 0.0005083084106445312
2023-01-23 04:29:48.533974: step: 832/533, loss: 0.037106703966856
2023-01-23 04:29:49.757189: step: 836/533, loss: 0.02768269181251526
2023-01-23 04:29:50.919050: step: 840/533, loss: 0.0011528492905199528
2023-01-23 04:29:52.128461: step: 844/533, loss: 1.1634827387752011e-05
2023-01-23 04:29:53.347761: step: 848/533, loss: 0.0006323814741335809
2023-01-23 04:29:54.541264: step: 852/533, loss: 0.0011382102966308594
2023-01-23 04:29:55.686840: step: 856/533, loss: 1.8119812921213452e-06
2023-01-23 04:29:56.844837: step: 860/533, loss: 0.0001122474714065902
2023-01-23 04:29:57.991801: step: 864/533, loss: 0.030983783304691315
2023-01-23 04:29:59.159909: step: 868/533, loss: 0.01650695875287056
2023-01-23 04:30:00.348420: step: 872/533, loss: 0.01674938201904297
2023-01-23 04:30:01.516156: step: 876/533, loss: 8.220673043979332e-05
2023-01-23 04:30:02.682814: step: 880/533, loss: 7.400512549793348e-05
2023-01-23 04:30:03.833109: step: 884/533, loss: 5.817413239128655e-06
2023-01-23 04:30:04.990186: step: 888/533, loss: 0.014087105169892311
2023-01-23 04:30:06.162905: step: 892/533, loss: 0.030108071863651276
2023-01-23 04:30:07.339320: step: 896/533, loss: 4.091262962901965e-05
2023-01-23 04:30:08.588336: step: 900/533, loss: 1.296997106692288e-05
2023-01-23 04:30:09.723876: step: 904/533, loss: 0.0024122237227857113
2023-01-23 04:30:10.880288: step: 908/533, loss: 0.0006353378412313759
2023-01-23 04:30:12.060986: step: 912/533, loss: 0.018374014645814896
2023-01-23 04:30:13.223733: step: 916/533, loss: 0.012214088812470436
2023-01-23 04:30:14.393970: step: 920/533, loss: 0.03250427171587944
2023-01-23 04:30:15.598971: step: 924/533, loss: 2.0503997802734375e-05
2023-01-23 04:30:16.781485: step: 928/533, loss: 0.0008580207941122353
2023-01-23 04:30:17.980462: step: 932/533, loss: 0.0991085022687912
2023-01-23 04:30:19.124879: step: 936/533, loss: 0.11838188022375107
2023-01-23 04:30:20.301317: step: 940/533, loss: 0.03463344648480415
2023-01-23 04:30:21.466190: step: 944/533, loss: 3.4809112548828125e-05
2023-01-23 04:30:22.600525: step: 948/533, loss: 0.0001669883931754157
2023-01-23 04:30:23.797420: step: 952/533, loss: 0.0011203765170648694
2023-01-23 04:30:24.937156: step: 956/533, loss: 2.0790101189049892e-05
2023-01-23 04:30:26.117976: step: 960/533, loss: 0.0002492904895916581
2023-01-23 04:30:27.258256: step: 964/533, loss: 0.0057006836868822575
2023-01-23 04:30:28.424027: step: 968/533, loss: 0.0070161824114620686
2023-01-23 04:30:29.572591: step: 972/533, loss: 0.0001336097629973665
2023-01-23 04:30:30.758277: step: 976/533, loss: 0.05814504623413086
2023-01-23 04:30:31.914769: step: 980/533, loss: 7.877349707996473e-05
2023-01-23 04:30:33.082253: step: 984/533, loss: 5.4168704082258046e-05
2023-01-23 04:30:34.250687: step: 988/533, loss: 0.0009250640869140625
2023-01-23 04:30:35.402688: step: 992/533, loss: 0.0037965774536132812
2023-01-23 04:30:36.572407: step: 996/533, loss: 0.0011080740951001644
2023-01-23 04:30:37.737215: step: 1000/533, loss: 0.0014207839267328382
2023-01-23 04:30:38.910468: step: 1004/533, loss: 0.016039753332734108
2023-01-23 04:30:40.072155: step: 1008/533, loss: 0.0005547046894207597
2023-01-23 04:30:41.229642: step: 1012/533, loss: 2.6702880859375e-05
2023-01-23 04:30:42.431436: step: 1016/533, loss: 0.05676741898059845
2023-01-23 04:30:43.568684: step: 1020/533, loss: 0.017014503479003906
2023-01-23 04:30:44.710189: step: 1024/533, loss: 5.569458153331652e-05
2023-01-23 04:30:45.903862: step: 1028/533, loss: 7.42912307032384e-05
2023-01-23 04:30:47.085576: step: 1032/533, loss: 0.0021759034134447575
2023-01-23 04:30:48.239213: step: 1036/533, loss: 0.0002665519714355469
2023-01-23 04:30:49.398326: step: 1040/533, loss: 0.011576080694794655
2023-01-23 04:30:50.573260: step: 1044/533, loss: 0.004502486903220415
2023-01-23 04:30:51.735700: step: 1048/533, loss: 8.354187593795359e-05
2023-01-23 04:30:52.914681: step: 1052/533, loss: 0.001936578773893416
2023-01-23 04:30:54.063202: step: 1056/533, loss: 0.0008191585657186806
2023-01-23 04:30:55.226208: step: 1060/533, loss: 0.0017066956497728825
2023-01-23 04:30:56.395005: step: 1064/533, loss: 0.00045566557673737407
2023-01-23 04:30:57.539088: step: 1068/533, loss: 5.3787229262525216e-05
2023-01-23 04:30:58.718323: step: 1072/533, loss: 0.006452894303947687
2023-01-23 04:30:59.933196: step: 1076/533, loss: 0.0017498015658929944
2023-01-23 04:31:01.140359: step: 1080/533, loss: 0.09159460663795471
2023-01-23 04:31:02.285167: step: 1084/533, loss: 3.72409813280683e-05
2023-01-23 04:31:03.505708: step: 1088/533, loss: -9.15527380129788e-06
2023-01-23 04:31:04.673396: step: 1092/533, loss: 0.0010288238991051912
2023-01-23 04:31:05.807381: step: 1096/533, loss: 3.5285947888041846e-06
2023-01-23 04:31:06.952667: step: 1100/533, loss: 0.0006485939375124872
2023-01-23 04:31:08.133852: step: 1104/533, loss: 1.0442733582749497e-05
2023-01-23 04:31:09.300270: step: 1108/533, loss: 0.132389634847641
2023-01-23 04:31:10.450327: step: 1112/533, loss: 0.0003182411310262978
2023-01-23 04:31:11.575951: step: 1116/533, loss: 0.0048274993896484375
2023-01-23 04:31:12.775689: step: 1120/533, loss: 0.006980514619499445
2023-01-23 04:31:13.985113: step: 1124/533, loss: 0.001069354941137135
2023-01-23 04:31:15.150137: step: 1128/533, loss: 0.0010107040870934725
2023-01-23 04:31:16.328268: step: 1132/533, loss: 0.0009754180791787803
2023-01-23 04:31:17.528581: step: 1136/533, loss: 1.9073486328125e-06
2023-01-23 04:31:18.694981: step: 1140/533, loss: 0.00041484832763671875
2023-01-23 04:31:19.900075: step: 1144/533, loss: 0.0007080078357830644
2023-01-23 04:31:21.086943: step: 1148/533, loss: 5.34057608092553e-06
2023-01-23 04:31:22.244207: step: 1152/533, loss: 0.0040458678267896175
2023-01-23 04:31:23.410227: step: 1156/533, loss: 0.04434919357299805
2023-01-23 04:31:24.597747: step: 1160/533, loss: 3.8623809814453125e-05
2023-01-23 04:31:25.733928: step: 1164/533, loss: 0.0002884864807128906
2023-01-23 04:31:26.924162: step: 1168/533, loss: 0.0005552291986532509
2023-01-23 04:31:28.139248: step: 1172/533, loss: 0.06897010654211044
2023-01-23 04:31:29.322482: step: 1176/533, loss: 0.00013504027447197586
2023-01-23 04:31:30.494941: step: 1180/533, loss: 0.06146087870001793
2023-01-23 04:31:31.645531: step: 1184/533, loss: 5.53131121705519e-06
2023-01-23 04:31:32.803646: step: 1188/533, loss: 0.009692477993667126
2023-01-23 04:31:33.958012: step: 1192/533, loss: 4.85897071484942e-05
2023-01-23 04:31:35.112203: step: 1196/533, loss: 0.06887397915124893
2023-01-23 04:31:36.343630: step: 1200/533, loss: 3.638267662608996e-05
2023-01-23 04:31:37.501864: step: 1204/533, loss: 0.0002434253692626953
2023-01-23 04:31:38.682776: step: 1208/533, loss: 1.52587890625e-05
2023-01-23 04:31:39.850219: step: 1212/533, loss: 0.043121337890625
2023-01-23 04:31:41.029761: step: 1216/533, loss: 0.02290048636496067
2023-01-23 04:31:42.177164: step: 1220/533, loss: 0.00018668771372176707
2023-01-23 04:31:43.354506: step: 1224/533, loss: 0.0028312683571130037
2023-01-23 04:31:44.499484: step: 1228/533, loss: 0.00012245179095771164
2023-01-23 04:31:45.656139: step: 1232/533, loss: 0.36537235975265503
2023-01-23 04:31:46.803247: step: 1236/533, loss: 2.775192479020916e-05
2023-01-23 04:31:47.944912: step: 1240/533, loss: 0.00021872521028853953
2023-01-23 04:31:49.107961: step: 1244/533, loss: 0.002084016799926758
2023-01-23 04:31:50.311284: step: 1248/533, loss: 0.00045843125553801656
2023-01-23 04:31:51.471467: step: 1252/533, loss: 0.0015971660614013672
2023-01-23 04:31:52.621270: step: 1256/533, loss: 0.04697055742144585
2023-01-23 04:31:53.826339: step: 1260/533, loss: 0.017285728827118874
2023-01-23 04:31:54.991250: step: 1264/533, loss: 4.29630272265058e-05
2023-01-23 04:31:56.172159: step: 1268/533, loss: 0.006230545230209827
2023-01-23 04:31:57.352254: step: 1272/533, loss: -1.010894811770413e-05
2023-01-23 04:31:58.552884: step: 1276/533, loss: 0.041637323796749115
2023-01-23 04:31:59.721203: step: 1280/533, loss: 0.0001161575346486643
2023-01-23 04:32:00.866886: step: 1284/533, loss: 0.00017299651517532766
2023-01-23 04:32:02.081236: step: 1288/533, loss: 0.001446628593839705
2023-01-23 04:32:03.226188: step: 1292/533, loss: 0.00021438598923850805
2023-01-23 04:32:04.388693: step: 1296/533, loss: 0.0003723144473042339
2023-01-23 04:32:05.532190: step: 1300/533, loss: 0.0004852295096497983
2023-01-23 04:32:06.676237: step: 1304/533, loss: 0.0005516052478924394
2023-01-23 04:32:07.865041: step: 1308/533, loss: 0.004182147793471813
2023-01-23 04:32:09.033218: step: 1312/533, loss: 1.9073486328125e-05
2023-01-23 04:32:10.215474: step: 1316/533, loss: 0.012036323547363281
2023-01-23 04:32:11.327036: step: 1320/533, loss: 0.0009317874792031944
2023-01-23 04:32:12.509256: step: 1324/533, loss: 7.2479248046875e-05
2023-01-23 04:32:13.680096: step: 1328/533, loss: 0.002017498016357422
2023-01-23 04:32:14.867988: step: 1332/533, loss: 0.005322456359863281
2023-01-23 04:32:16.067075: step: 1336/533, loss: 0.002285194583237171
2023-01-23 04:32:17.224178: step: 1340/533, loss: 0.006087875925004482
2023-01-23 04:32:18.410277: step: 1344/533, loss: 0.05332136154174805
2023-01-23 04:32:19.583833: step: 1348/533, loss: 0.0036059380508959293
2023-01-23 04:32:20.753178: step: 1352/533, loss: 0.009685516357421875
2023-01-23 04:32:21.923512: step: 1356/533, loss: 0.0020960806868970394
2023-01-23 04:32:23.126809: step: 1360/533, loss: 0.0010589599842205644
2023-01-23 04:32:24.234970: step: 1364/533, loss: 0.001273727510124445
2023-01-23 04:32:25.391883: step: 1368/533, loss: 0.0007979393121786416
2023-01-23 04:32:26.576205: step: 1372/533, loss: 0.0006975174183025956
2023-01-23 04:32:27.699616: step: 1376/533, loss: 0.01880960538983345
2023-01-23 04:32:28.879480: step: 1380/533, loss: 0.030681611970067024
2023-01-23 04:32:30.085802: step: 1384/533, loss: 8.640289888717234e-05
2023-01-23 04:32:31.277639: step: 1388/533, loss: 0.0021041869185864925
2023-01-23 04:32:32.432456: step: 1392/533, loss: 3.5858156479662284e-05
2023-01-23 04:32:33.609601: step: 1396/533, loss: -1.430511474609375e-06
2023-01-23 04:32:34.755271: step: 1400/533, loss: 0.00374088273383677
2023-01-23 04:32:35.931248: step: 1404/533, loss: 0.013428688049316406
2023-01-23 04:32:37.094346: step: 1408/533, loss: 0.008450508117675781
2023-01-23 04:32:38.252003: step: 1412/533, loss: 7.82012939453125e-05
2023-01-23 04:32:39.403575: step: 1416/533, loss: 0.0005204200861044228
2023-01-23 04:32:40.573741: step: 1420/533, loss: 0.01613311842083931
2023-01-23 04:32:41.735217: step: 1424/533, loss: 1.4400482541532256e-05
2023-01-23 04:32:42.882581: step: 1428/533, loss: 0.00037846562918275595
2023-01-23 04:32:44.039994: step: 1432/533, loss: 0.028551960363984108
2023-01-23 04:32:45.254869: step: 1436/533, loss: 0.0005429268348962069
2023-01-23 04:32:46.463077: step: 1440/533, loss: 0.013313674367964268
2023-01-23 04:32:47.634621: step: 1444/533, loss: 0.0022737502586096525
2023-01-23 04:32:48.800937: step: 1448/533, loss: 0.0027341842651367188
2023-01-23 04:32:50.014214: step: 1452/533, loss: 0.00194549560546875
2023-01-23 04:32:51.176796: step: 1456/533, loss: 0.006162834353744984
2023-01-23 04:32:52.339007: step: 1460/533, loss: 3.204345557605848e-05
2023-01-23 04:32:53.552811: step: 1464/533, loss: 0.007847595028579235
2023-01-23 04:32:54.713163: step: 1468/533, loss: 0.0015055655967444181
2023-01-23 04:32:55.874927: step: 1472/533, loss: 2.059936559817288e-05
2023-01-23 04:32:57.068327: step: 1476/533, loss: 0.016317415982484818
2023-01-23 04:32:58.202951: step: 1480/533, loss: 2.9373170036706142e-05
2023-01-23 04:32:59.377488: step: 1484/533, loss: 1.2683868590102065e-05
2023-01-23 04:33:00.581062: step: 1488/533, loss: 0.003624534700065851
2023-01-23 04:33:01.807146: step: 1492/533, loss: 4.100799742445815e-06
2023-01-23 04:33:02.966863: step: 1496/533, loss: 2.632141149661038e-05
2023-01-23 04:33:04.140403: step: 1500/533, loss: 0.052933502942323685
2023-01-23 04:33:05.292401: step: 1504/533, loss: 0.0001771926908986643
2023-01-23 04:33:06.436678: step: 1508/533, loss: 0.003331470536068082
2023-01-23 04:33:07.637568: step: 1512/533, loss: 0.00020513535127975047
2023-01-23 04:33:08.849595: step: 1516/533, loss: 0.00304241175763309
2023-01-23 04:33:10.047163: step: 1520/533, loss: 0.0025769234634935856
2023-01-23 04:33:11.205001: step: 1524/533, loss: 0.00026569367037154734
2023-01-23 04:33:12.423427: step: 1528/533, loss: 6.10351571594947e-06
2023-01-23 04:33:13.578001: step: 1532/533, loss: 0.002432107925415039
2023-01-23 04:33:14.751327: step: 1536/533, loss: 0.0015659332275390625
2023-01-23 04:33:15.915376: step: 1540/533, loss: 0.0002457142109051347
2023-01-23 04:33:17.097797: step: 1544/533, loss: 0.0016598702641204
2023-01-23 04:33:18.260486: step: 1548/533, loss: 0.00038299558218568563
2023-01-23 04:33:19.491821: step: 1552/533, loss: 7.534026735811494e-06
2023-01-23 04:33:20.662019: step: 1556/533, loss: 0.010682192631065845
2023-01-23 04:33:21.882135: step: 1560/533, loss: 0.006688976194709539
2023-01-23 04:33:23.048012: step: 1564/533, loss: 2.2113323211669922e-05
2023-01-23 04:33:24.205925: step: 1568/533, loss: 5.655288987327367e-05
2023-01-23 04:33:25.396766: step: 1572/533, loss: 0.025667190551757812
2023-01-23 04:33:26.576188: step: 1576/533, loss: 0.02109069749712944
2023-01-23 04:33:27.742545: step: 1580/533, loss: 0.015968991443514824
2023-01-23 04:33:28.916030: step: 1584/533, loss: 0.0007537603378295898
2023-01-23 04:33:30.094153: step: 1588/533, loss: 0.00017671585374046117
2023-01-23 04:33:31.261665: step: 1592/533, loss: 0.006217861548066139
2023-01-23 04:33:32.442886: step: 1596/533, loss: 0.0044998168013989925
2023-01-23 04:33:33.594590: step: 1600/533, loss: 0.0004170417960267514
2023-01-23 04:33:34.742329: step: 1604/533, loss: 0.020654775202274323
2023-01-23 04:33:35.892532: step: 1608/533, loss: 0.001601791474968195
2023-01-23 04:33:37.074054: step: 1612/533, loss: 0.0013985633850097656
2023-01-23 04:33:38.214797: step: 1616/533, loss: 7.209778414107859e-05
2023-01-23 04:33:39.389562: step: 1620/533, loss: 0.005980396643280983
2023-01-23 04:33:40.600762: step: 1624/533, loss: 3.1280520488508046e-05
2023-01-23 04:33:41.750274: step: 1628/533, loss: 0.005026912782341242
2023-01-23 04:33:42.899937: step: 1632/533, loss: 4.96864304295741e-05
2023-01-23 04:33:44.095090: step: 1636/533, loss: 0.0001162529006251134
2023-01-23 04:33:45.242613: step: 1640/533, loss: 2.86102294921875e-05
2023-01-23 04:33:46.425394: step: 1644/533, loss: 0.0011852264869958162
2023-01-23 04:33:47.629611: step: 1648/533, loss: 0.03663644567131996
2023-01-23 04:33:48.814305: step: 1652/533, loss: 0.00025539397029206157
2023-01-23 04:33:50.046346: step: 1656/533, loss: 0.013941383920609951
2023-01-23 04:33:51.237078: step: 1660/533, loss: 0.0005298614269122481
2023-01-23 04:33:52.387180: step: 1664/533, loss: 0.0001453399599995464
2023-01-23 04:33:53.576626: step: 1668/533, loss: 0.021195530891418457
2023-01-23 04:33:54.710523: step: 1672/533, loss: 0.010399436578154564
2023-01-23 04:33:55.856919: step: 1676/533, loss: 0.002645206404849887
2023-01-23 04:33:57.025775: step: 1680/533, loss: 0.058966636657714844
2023-01-23 04:33:58.190033: step: 1684/533, loss: 0.01644315756857395
2023-01-23 04:33:59.375088: step: 1688/533, loss: 0.00021677017502952367
2023-01-23 04:34:00.531171: step: 1692/533, loss: 0.2044660598039627
2023-01-23 04:34:01.709975: step: 1696/533, loss: 0.0032224655151367188
2023-01-23 04:34:02.895622: step: 1700/533, loss: 0.0013557435013353825
2023-01-23 04:34:04.042607: step: 1704/533, loss: 0.00016217232041526586
2023-01-23 04:34:05.223855: step: 1708/533, loss: 0.00020866394334007055
2023-01-23 04:34:06.398038: step: 1712/533, loss: 0.11762447655200958
2023-01-23 04:34:07.517433: step: 1716/533, loss: -7.629396350239404e-07
2023-01-23 04:34:08.754474: step: 1720/533, loss: 0.0019397735595703125
2023-01-23 04:34:09.929896: step: 1724/533, loss: 0.010009956546127796
2023-01-23 04:34:11.117152: step: 1728/533, loss: 0.06170034781098366
2023-01-23 04:34:12.291641: step: 1732/533, loss: 0.0002636909775901586
2023-01-23 04:34:13.407778: step: 1736/533, loss: 0.0002613067626953125
2023-01-23 04:34:14.577197: step: 1740/533, loss: -1.468658410885837e-05
2023-01-23 04:34:15.836741: step: 1744/533, loss: 0.0012242316734045744
2023-01-23 04:34:17.031903: step: 1748/533, loss: 0.0003984451468568295
2023-01-23 04:34:18.257427: step: 1752/533, loss: 0.0017774105072021484
2023-01-23 04:34:19.498238: step: 1756/533, loss: 2.294331898156088e-05
2023-01-23 04:34:20.682929: step: 1760/533, loss: 0.010045815259218216
2023-01-23 04:34:21.879417: step: 1764/533, loss: 0.042183876037597656
2023-01-23 04:34:23.027085: step: 1768/533, loss: 0.0514240525662899
2023-01-23 04:34:24.200832: step: 1772/533, loss: 0.008601188659667969
2023-01-23 04:34:25.417117: step: 1776/533, loss: 0.014454650692641735
2023-01-23 04:34:26.572563: step: 1780/533, loss: 0.017203712835907936
2023-01-23 04:34:27.743683: step: 1784/533, loss: 0.0014197349082678556
2023-01-23 04:34:28.901006: step: 1788/533, loss: 0.00025691985501907766
2023-01-23 04:34:30.031280: step: 1792/533, loss: 0.0017223358154296875
2023-01-23 04:34:31.186205: step: 1796/533, loss: 5.204826811677776e-05
2023-01-23 04:34:32.373620: step: 1800/533, loss: 1.0728836059570312e-05
2023-01-23 04:34:33.540474: step: 1804/533, loss: 1.0681153071345761e-05
2023-01-23 04:34:34.708835: step: 1808/533, loss: 0.0005338668706826866
2023-01-23 04:34:35.854394: step: 1812/533, loss: 0.0004192352353129536
2023-01-23 04:34:37.052781: step: 1816/533, loss: 0.0018618584144860506
2023-01-23 04:34:38.227726: step: 1820/533, loss: 0.0008495807996951044
2023-01-23 04:34:39.432721: step: 1824/533, loss: 0.042612459510564804
2023-01-23 04:34:40.611097: step: 1828/533, loss: 0.00043506623478606343
2023-01-23 04:34:41.812831: step: 1832/533, loss: 0.0023750304244458675
2023-01-23 04:34:43.001366: step: 1836/533, loss: 9.965896606445312e-05
2023-01-23 04:34:44.173485: step: 1840/533, loss: 0.0002407073916401714
2023-01-23 04:34:45.351102: step: 1844/533, loss: 0.04739675298333168
2023-01-23 04:34:46.518789: step: 1848/533, loss: 8.087158494163305e-05
2023-01-23 04:34:47.703663: step: 1852/533, loss: 8.869171142578125e-05
2023-01-23 04:34:48.912132: step: 1856/533, loss: 0.004744147881865501
2023-01-23 04:34:50.106061: step: 1860/533, loss: 1.3732911611441523e-05
2023-01-23 04:34:51.277787: step: 1864/533, loss: 0.023932980373501778
2023-01-23 04:34:52.456115: step: 1868/533, loss: 0.004844284150749445
2023-01-23 04:34:53.651345: step: 1872/533, loss: 0.02382946014404297
2023-01-23 04:34:54.805829: step: 1876/533, loss: 0.00027885439340025187
2023-01-23 04:34:55.978180: step: 1880/533, loss: 0.0016535759204998612
2023-01-23 04:34:57.170624: step: 1884/533, loss: 0.026770973578095436
2023-01-23 04:34:58.343545: step: 1888/533, loss: 0.045336056500673294
2023-01-23 04:34:59.486593: step: 1892/533, loss: 0.0038851737044751644
2023-01-23 04:35:00.617911: step: 1896/533, loss: 0.0002075195370707661
2023-01-23 04:35:01.802813: step: 1900/533, loss: 0.01721658743917942
2023-01-23 04:35:03.035186: step: 1904/533, loss: 0.03827933967113495
2023-01-23 04:35:04.231529: step: 1908/533, loss: 0.0021682740189135075
2023-01-23 04:35:05.422701: step: 1912/533, loss: 0.0011571884388104081
2023-01-23 04:35:06.547874: step: 1916/533, loss: 0.028677750378847122
2023-01-23 04:35:07.716918: step: 1920/533, loss: 1.2397766795402276e-06
2023-01-23 04:35:08.908841: step: 1924/533, loss: 0.00036411284236237407
2023-01-23 04:35:10.074647: step: 1928/533, loss: 0.00029792787972837687
2023-01-23 04:35:11.266459: step: 1932/533, loss: 0.007142257876694202
2023-01-23 04:35:12.464237: step: 1936/533, loss: 0.0006432533264160156
2023-01-23 04:35:13.632992: step: 1940/533, loss: -8.77380352903856e-06
2023-01-23 04:35:14.795870: step: 1944/533, loss: 0.016586685553193092
2023-01-23 04:35:16.025015: step: 1948/533, loss: 0.0001255035458598286
2023-01-23 04:35:17.177965: step: 1952/533, loss: 9.679793947725557e-06
2023-01-23 04:35:18.330247: step: 1956/533, loss: 0.039911746978759766
2023-01-23 04:35:19.498041: step: 1960/533, loss: 0.051844026893377304
2023-01-23 04:35:20.665787: step: 1964/533, loss: 0.001210975693538785
2023-01-23 04:35:21.838138: step: 1968/533, loss: 0.00010075569298351184
2023-01-23 04:35:23.055055: step: 1972/533, loss: 3.8528440200025216e-05
2023-01-23 04:35:24.211600: step: 1976/533, loss: 0.00030765534029342234
2023-01-23 04:35:25.422341: step: 1980/533, loss: 0.06222648546099663
2023-01-23 04:35:26.582074: step: 1984/533, loss: 0.023264123126864433
2023-01-23 04:35:27.756887: step: 1988/533, loss: 0.006372451316565275
2023-01-23 04:35:28.953549: step: 1992/533, loss: 3.862380708596902e-06
2023-01-23 04:35:30.100008: step: 1996/533, loss: 0.0002157211274607107
2023-01-23 04:35:31.269986: step: 2000/533, loss: 0.03579854965209961
2023-01-23 04:35:32.455448: step: 2004/533, loss: 0.000868940376676619
2023-01-23 04:35:33.631580: step: 2008/533, loss: 0.002105140592902899
2023-01-23 04:35:34.815974: step: 2012/533, loss: 9.250640687241685e-06
2023-01-23 04:35:35.978027: step: 2016/533, loss: 0.0036342618986964226
2023-01-23 04:35:37.174586: step: 2020/533, loss: 0.00029354094294831157
2023-01-23 04:35:38.341823: step: 2024/533, loss: -1.4591217222914565e-05
2023-01-23 04:35:39.486417: step: 2028/533, loss: 0.005563068203628063
2023-01-23 04:35:40.620865: step: 2032/533, loss: 0.0003765106375794858
2023-01-23 04:35:41.835051: step: 2036/533, loss: 4.367828296381049e-05
2023-01-23 04:35:43.017631: step: 2040/533, loss: 0.003053188556805253
2023-01-23 04:35:44.201831: step: 2044/533, loss: 0.007087517064064741
2023-01-23 04:35:45.382683: step: 2048/533, loss: 0.011091899126768112
2023-01-23 04:35:46.579992: step: 2052/533, loss: 3.061294773942791e-05
2023-01-23 04:35:47.789718: step: 2056/533, loss: 0.006381988525390625
2023-01-23 04:35:48.963984: step: 2060/533, loss: 0.001312255859375
2023-01-23 04:35:50.157049: step: 2064/533, loss: 0.0008981704595498741
2023-01-23 04:35:51.308721: step: 2068/533, loss: 3.356933666509576e-05
2023-01-23 04:35:52.484123: step: 2072/533, loss: -1.5258774510584772e-06
2023-01-23 04:35:53.711621: step: 2076/533, loss: 0.0002628326474223286
2023-01-23 04:35:54.859042: step: 2080/533, loss: 0.0009059906587935984
2023-01-23 04:35:56.062618: step: 2084/533, loss: 0.0008560181013308465
2023-01-23 04:35:57.210645: step: 2088/533, loss: 0.00017938614473678172
2023-01-23 04:35:58.373454: step: 2092/533, loss: 1.773834264895413e-05
2023-01-23 04:35:59.539332: step: 2096/533, loss: 2.9945374990347773e-05
2023-01-23 04:36:00.746707: step: 2100/533, loss: 1.8290832042694092
2023-01-23 04:36:01.918813: step: 2104/533, loss: 0.005245590582489967
2023-01-23 04:36:03.053799: step: 2108/533, loss: 9.34600848268019e-06
2023-01-23 04:36:04.196937: step: 2112/533, loss: 7.05719003235572e-06
2023-01-23 04:36:05.340504: step: 2116/533, loss: 0.00044631960918195546
2023-01-23 04:36:06.507506: step: 2120/533, loss: 0.0003170013369526714
2023-01-23 04:36:07.675598: step: 2124/533, loss: 0.003554105758666992
2023-01-23 04:36:08.856311: step: 2128/533, loss: 1.392364538332913e-05
2023-01-23 04:36:10.027635: step: 2132/533, loss: 0.002403307007625699
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.6183206106870229, 'r': 0.7549933422103862, 'f1': 0.6798561151079138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6558164354322306, 'r': 0.7858056265984654, 'f1': 0.7149505526468877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.6428571428571429, 'r': 0.5714285714285714, 'f1': 0.6050420168067226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6183206106870229, 'r': 0.7549933422103862, 'f1': 0.6798561151079138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Chinese: {'event': {'p': 0.6558164354322306, 'r': 0.7858056265984654, 'f1': 0.7149505526468877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 28
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:36:56.421228: step: 4/533, loss: 7.534028554800898e-06
2023-01-23 04:36:57.578812: step: 8/533, loss: 7.896423630882055e-05
2023-01-23 04:36:58.736180: step: 12/533, loss: 0.0013439179165288806
2023-01-23 04:36:59.896864: step: 16/533, loss: 0.013418961316347122
2023-01-23 04:37:01.040960: step: 20/533, loss: 0.004796028137207031
2023-01-23 04:37:02.279973: step: 24/533, loss: 0.0005672455299645662
2023-01-23 04:37:03.483694: step: 28/533, loss: 0.019650841131806374
2023-01-23 04:37:04.702145: step: 32/533, loss: 0.006049156654626131
2023-01-23 04:37:05.941954: step: 36/533, loss: 3.628731064964086e-05
2023-01-23 04:37:07.090306: step: 40/533, loss: 0.004432487301528454
2023-01-23 04:37:08.249791: step: 44/533, loss: 9.078979928744957e-05
2023-01-23 04:37:09.424159: step: 48/533, loss: 0.0009373664506711066
2023-01-23 04:37:10.577423: step: 52/533, loss: 0.0012390136253088713
2023-01-23 04:37:11.723749: step: 56/533, loss: 0.00015735626220703125
2023-01-23 04:37:12.918092: step: 60/533, loss: 7.781982276355848e-05
2023-01-23 04:37:14.102245: step: 64/533, loss: 0.03666190803050995
2023-01-23 04:37:15.256513: step: 68/533, loss: 0.0004473209264688194
2023-01-23 04:37:16.428791: step: 72/533, loss: 0.001277923583984375
2023-01-23 04:37:17.547592: step: 76/533, loss: -1.1920928955078125e-06
2023-01-23 04:37:18.717806: step: 80/533, loss: 0.02877168543636799
2023-01-23 04:37:19.935226: step: 84/533, loss: 0.0004143714904785156
2023-01-23 04:37:21.129594: step: 88/533, loss: 0.001654815743677318
2023-01-23 04:37:22.323259: step: 92/533, loss: 0.008838463574647903
2023-01-23 04:37:23.515412: step: 96/533, loss: 3.166198803228326e-05
2023-01-23 04:37:24.719602: step: 100/533, loss: 0.06480560451745987
2023-01-23 04:37:25.859896: step: 104/533, loss: 7.247925168485381e-06
2023-01-23 04:37:27.061730: step: 108/533, loss: 0.0008224487537518144
2023-01-23 04:37:28.293254: step: 112/533, loss: 0.00101642613299191
2023-01-23 04:37:29.458267: step: 116/533, loss: 2.880096508306451e-05
2023-01-23 04:37:30.633607: step: 120/533, loss: 0.0006071090465411544
2023-01-23 04:37:31.792799: step: 124/533, loss: 5.092620995128527e-05
2023-01-23 04:37:32.977132: step: 128/533, loss: -8.678436643094756e-06
2023-01-23 04:37:34.111830: step: 132/533, loss: 0.002089214278385043
2023-01-23 04:37:35.304457: step: 136/533, loss: 0.11586780846118927
2023-01-23 04:37:36.508193: step: 140/533, loss: 0.029987145215272903
2023-01-23 04:37:37.691793: step: 144/533, loss: 0.0008866310818120837
2023-01-23 04:37:38.885248: step: 148/533, loss: 0.0030837536323815584
2023-01-23 04:37:40.096775: step: 152/533, loss: 0.5049497485160828
2023-01-23 04:37:41.277970: step: 156/533, loss: 0.0014310836559161544
2023-01-23 04:37:42.440175: step: 160/533, loss: 1.0681153071345761e-05
2023-01-23 04:37:43.603868: step: 164/533, loss: 1.2111663636460435e-05
2023-01-23 04:37:44.803885: step: 168/533, loss: 3.056526111322455e-05
2023-01-23 04:37:45.952482: step: 172/533, loss: 0.0006353378412313759
2023-01-23 04:37:47.174703: step: 176/533, loss: 0.0001543045073049143
2023-01-23 04:37:48.382784: step: 180/533, loss: 9.493828110862523e-05
2023-01-23 04:37:49.565512: step: 184/533, loss: 0.00387668632902205
2023-01-23 04:37:50.772851: step: 188/533, loss: 5.0258637202205136e-05
2023-01-23 04:37:51.924983: step: 192/533, loss: 2.8419495720299892e-05
2023-01-23 04:37:53.101924: step: 196/533, loss: 0.02336139604449272
2023-01-23 04:37:54.290798: step: 200/533, loss: 0.00423088064417243
2023-01-23 04:37:55.473284: step: 204/533, loss: 0.00907211285084486
2023-01-23 04:37:56.666480: step: 208/533, loss: 0.0005422591930255294
2023-01-23 04:37:57.811876: step: 212/533, loss: 0.00043468474177643657
2023-01-23 04:37:59.007011: step: 216/533, loss: -1.1444091796875e-05
2023-01-23 04:38:00.144870: step: 220/533, loss: 0.03506450727581978
2023-01-23 04:38:01.320685: step: 224/533, loss: -3.337860050578456e-07
2023-01-23 04:38:02.517432: step: 228/533, loss: 0.0006381034618243575
2023-01-23 04:38:03.689273: step: 232/533, loss: 2.47955322265625e-05
2023-01-23 04:38:04.855811: step: 236/533, loss: 0.10172824561595917
2023-01-23 04:38:06.034440: step: 240/533, loss: 0.0008962184656411409
2023-01-23 04:38:07.189664: step: 244/533, loss: 0.0015045166946947575
2023-01-23 04:38:08.408032: step: 248/533, loss: 0.0007680415874347091
2023-01-23 04:38:09.585409: step: 252/533, loss: 0.03281812742352486
2023-01-23 04:38:10.752554: step: 256/533, loss: 0.005105876829475164
2023-01-23 04:38:11.916347: step: 260/533, loss: 0.036783602088689804
2023-01-23 04:38:13.067913: step: 264/533, loss: 0.0008500099065713584
2023-01-23 04:38:14.253396: step: 268/533, loss: 1.568794141348917e-05
2023-01-23 04:38:15.453126: step: 272/533, loss: 0.03252124786376953
2023-01-23 04:38:16.647127: step: 276/533, loss: 0.005089378450065851
2023-01-23 04:38:17.846700: step: 280/533, loss: 0.00024280548677779734
2023-01-23 04:38:19.073966: step: 284/533, loss: 0.00330772390589118
2023-01-23 04:38:20.248844: step: 288/533, loss: 0.004314422607421875
2023-01-23 04:38:21.462011: step: 292/533, loss: 0.006544876378029585
2023-01-23 04:38:22.690521: step: 296/533, loss: 0.002794456435367465
2023-01-23 04:38:23.878589: step: 300/533, loss: 0.038854122161865234
2023-01-23 04:38:25.041851: step: 304/533, loss: 0.059088896960020065
2023-01-23 04:38:26.230311: step: 308/533, loss: 3.8623809814453125e-05
2023-01-23 04:38:27.389013: step: 312/533, loss: 6.86645489622606e-06
2023-01-23 04:38:28.580321: step: 316/533, loss: 0.005772209260612726
2023-01-23 04:38:29.742539: step: 320/533, loss: 0.0005887032020837069
2023-01-23 04:38:30.911775: step: 324/533, loss: 5.378723290050402e-05
2023-01-23 04:38:32.112522: step: 328/533, loss: 0.0012348175514489412
2023-01-23 04:38:33.293541: step: 332/533, loss: 0.0017560959095135331
2023-01-23 04:38:34.517538: step: 336/533, loss: 0.009603691287338734
2023-01-23 04:38:35.694313: step: 340/533, loss: 0.025124521926045418
2023-01-23 04:38:36.890214: step: 344/533, loss: 0.0001396179141011089
2023-01-23 04:38:38.123104: step: 348/533, loss: 0.0002620696905069053
2023-01-23 04:38:39.303861: step: 352/533, loss: 0.011796570383012295
2023-01-23 04:38:40.462979: step: 356/533, loss: 4.56810012110509e-05
2023-01-23 04:38:41.658409: step: 360/533, loss: 0.0041792867705225945
2023-01-23 04:38:42.820228: step: 364/533, loss: 1.411438006471144e-05
2023-01-23 04:38:44.070193: step: 368/533, loss: 1.9502640498103574e-05
2023-01-23 04:38:45.270979: step: 372/533, loss: 4.901886131847277e-05
2023-01-23 04:38:46.486872: step: 376/533, loss: 3.24249276673072e-06
2023-01-23 04:38:47.663229: step: 380/533, loss: 0.003913307096809149
2023-01-23 04:38:48.844088: step: 384/533, loss: 0.0003589630068745464
2023-01-23 04:38:50.022492: step: 388/533, loss: 1.907348234908568e-07
2023-01-23 04:38:51.189767: step: 392/533, loss: 0.05034380033612251
2023-01-23 04:38:52.384005: step: 396/533, loss: 0.0002077102690236643
2023-01-23 04:38:53.570804: step: 400/533, loss: 0.0006966590299271047
2023-01-23 04:38:54.736998: step: 404/533, loss: 2.19345088225964e-06
2023-01-23 04:38:55.929487: step: 408/533, loss: 0.0029265405610203743
2023-01-23 04:38:57.177164: step: 412/533, loss: 0.04236021265387535
2023-01-23 04:38:58.378055: step: 416/533, loss: 1.5544892448815517e-05
2023-01-23 04:38:59.573529: step: 420/533, loss: 1.1825562069134321e-05
2023-01-23 04:39:00.754754: step: 424/533, loss: 6.8664553509734105e-06
2023-01-23 04:39:01.966223: step: 428/533, loss: 0.00042285918607376516
2023-01-23 04:39:03.163980: step: 432/533, loss: 0.0018085479969158769
2023-01-23 04:39:04.417005: step: 436/533, loss: 0.0022339820861816406
2023-01-23 04:39:05.612285: step: 440/533, loss: 0.0012959956657141447
2023-01-23 04:39:06.767940: step: 444/533, loss: 0.00014696121797896922
2023-01-23 04:39:07.979750: step: 448/533, loss: 0.022188376635313034
2023-01-23 04:39:09.157884: step: 452/533, loss: 0.0009449005010537803
2023-01-23 04:39:10.341304: step: 456/533, loss: 0.00046324729919433594
2023-01-23 04:39:11.519515: step: 460/533, loss: 0.016710758209228516
2023-01-23 04:39:12.695827: step: 464/533, loss: 0.0005097389221191406
2023-01-23 04:39:13.861244: step: 468/533, loss: 0.0002099990815622732
2023-01-23 04:39:15.023402: step: 472/533, loss: 0.008814096450805664
2023-01-23 04:39:16.197390: step: 476/533, loss: 9.012222290039062e-05
2023-01-23 04:39:17.389957: step: 480/533, loss: 0.00017547608877066523
2023-01-23 04:39:18.562963: step: 484/533, loss: 0.002627849578857422
2023-01-23 04:39:19.796052: step: 488/533, loss: 0.0024357796646654606
2023-01-23 04:39:20.978325: step: 492/533, loss: 0.00024127960205078125
2023-01-23 04:39:22.216807: step: 496/533, loss: 0.015493392944335938
2023-01-23 04:39:23.406639: step: 500/533, loss: 4.7206878662109375e-05
2023-01-23 04:39:24.599700: step: 504/533, loss: 7.009506589383818e-06
2023-01-23 04:39:25.788798: step: 508/533, loss: 3.662109520519152e-05
2023-01-23 04:39:26.948987: step: 512/533, loss: 0.004395675845444202
2023-01-23 04:39:28.198220: step: 516/533, loss: 0.060263827443122864
2023-01-23 04:39:29.362919: step: 520/533, loss: 0.00018377303786110133
2023-01-23 04:39:30.612541: step: 524/533, loss: 0.002733421279117465
2023-01-23 04:39:31.802792: step: 528/533, loss: 0.009518241509795189
2023-01-23 04:39:33.020030: step: 532/533, loss: 0.0005384445539675653
2023-01-23 04:39:34.212114: step: 536/533, loss: 0.0003921031893696636
2023-01-23 04:39:35.399612: step: 540/533, loss: 3.643035961431451e-05
2023-01-23 04:39:36.551032: step: 544/533, loss: 0.0008705139625817537
2023-01-23 04:39:37.777022: step: 548/533, loss: 0.04143171012401581
2023-01-23 04:39:38.974392: step: 552/533, loss: 0.14688262343406677
2023-01-23 04:39:40.149505: step: 556/533, loss: 0.00016708375187590718
2023-01-23 04:39:41.308987: step: 560/533, loss: 0.0003758430539164692
2023-01-23 04:39:42.449310: step: 564/533, loss: 0.024804307147860527
2023-01-23 04:39:43.711054: step: 568/533, loss: 3.7193301523075206e-06
2023-01-23 04:39:44.911576: step: 572/533, loss: 0.0008938789833337069
2023-01-23 04:39:46.115356: step: 576/533, loss: 0.0005808830610476434
2023-01-23 04:39:47.340729: step: 580/533, loss: 0.0007548332214355469
2023-01-23 04:39:48.552888: step: 584/533, loss: 0.037284087389707565
2023-01-23 04:39:49.748969: step: 588/533, loss: 0.00010795592970680445
2023-01-23 04:39:50.931116: step: 592/533, loss: 0.0010578156216070056
2023-01-23 04:39:52.138508: step: 596/533, loss: 0.0027248861733824015
2023-01-23 04:39:53.309091: step: 600/533, loss: 0.005249595735222101
2023-01-23 04:39:54.455680: step: 604/533, loss: 8.02993745310232e-05
2023-01-23 04:39:55.669500: step: 608/533, loss: 0.0167097095400095
2023-01-23 04:39:56.858084: step: 612/533, loss: 0.02184000052511692
2023-01-23 04:39:58.072185: step: 616/533, loss: 0.0019045353401452303
2023-01-23 04:39:59.227487: step: 620/533, loss: 0.00011730194091796875
2023-01-23 04:40:00.413276: step: 624/533, loss: 0.00767097482457757
2023-01-23 04:40:01.602392: step: 628/533, loss: 0.00014634133549407125
2023-01-23 04:40:02.775856: step: 632/533, loss: 0.00572891253978014
2023-01-23 04:40:03.978676: step: 636/533, loss: 5.111694190418348e-05
2023-01-23 04:40:05.182226: step: 640/533, loss: 0.0001430511474609375
2023-01-23 04:40:06.369437: step: 644/533, loss: 0.00017509459576103836
2023-01-23 04:40:07.558478: step: 648/533, loss: 0.0009133339044637978
2023-01-23 04:40:08.723972: step: 652/533, loss: 5.6934357417048886e-05
2023-01-23 04:40:09.909809: step: 656/533, loss: 0.0014568328624591231
2023-01-23 04:40:11.089901: step: 660/533, loss: 0.0003809928894042969
2023-01-23 04:40:12.261372: step: 664/533, loss: 1.3256073543743696e-05
2023-01-23 04:40:13.445569: step: 668/533, loss: 0.0012298584915697575
2023-01-23 04:40:14.616917: step: 672/533, loss: 0.0037435530684888363
2023-01-23 04:40:15.786803: step: 676/533, loss: 0.0036605834029614925
2023-01-23 04:40:16.969801: step: 680/533, loss: 0.0015289306174963713
2023-01-23 04:40:18.158394: step: 684/533, loss: 0.0008705139625817537
2023-01-23 04:40:19.373320: step: 688/533, loss: 0.0019101144280284643
2023-01-23 04:40:20.538420: step: 692/533, loss: 3.43322744811303e-06
2023-01-23 04:40:21.740772: step: 696/533, loss: 0.0003459453582763672
2023-01-23 04:40:22.927619: step: 700/533, loss: 0.00263042445294559
2023-01-23 04:40:24.087968: step: 704/533, loss: 0.0017639159923419356
2023-01-23 04:40:25.249440: step: 708/533, loss: 3.356933666509576e-05
2023-01-23 04:40:26.417366: step: 712/533, loss: 3.490447852527723e-05
2023-01-23 04:40:27.638653: step: 716/533, loss: 2.574920654296875e-05
2023-01-23 04:40:28.817712: step: 720/533, loss: 0.00217266078107059
2023-01-23 04:40:30.017180: step: 724/533, loss: 0.001885795732960105
2023-01-23 04:40:31.199596: step: 728/533, loss: 0.0061120036989450455
2023-01-23 04:40:32.385292: step: 732/533, loss: 0.00022430419630836695
2023-01-23 04:40:33.575591: step: 736/533, loss: 0.0016601084498688579
2023-01-23 04:40:34.773809: step: 740/533, loss: 0.004161739256232977
2023-01-23 04:40:35.961662: step: 744/533, loss: 0.0015872955555096269
2023-01-23 04:40:37.156142: step: 748/533, loss: 3.538131932145916e-05
2023-01-23 04:40:38.349805: step: 752/533, loss: 0.0001951217564055696
2023-01-23 04:40:39.521610: step: 756/533, loss: 1.907349087559851e-07
2023-01-23 04:40:40.701437: step: 760/533, loss: 0.0009496688726358116
2023-01-23 04:40:41.842270: step: 764/533, loss: 0.0004805564822163433
2023-01-23 04:40:43.028700: step: 768/533, loss: 0.002004146808758378
2023-01-23 04:40:44.215095: step: 772/533, loss: 0.0023417354095727205
2023-01-23 04:40:45.402849: step: 776/533, loss: 0.013773537240922451
2023-01-23 04:40:46.589050: step: 780/533, loss: 0.00018539429584052414
2023-01-23 04:40:47.773098: step: 784/533, loss: 0.47250357270240784
2023-01-23 04:40:48.969937: step: 788/533, loss: -9.536743306171047e-08
2023-01-23 04:40:50.123700: step: 792/533, loss: 6.198883056640625e-06
2023-01-23 04:40:51.299707: step: 796/533, loss: 0.003001594450324774
2023-01-23 04:40:52.439847: step: 800/533, loss: 1.106262243411038e-05
2023-01-23 04:40:53.595498: step: 804/533, loss: 2.95162208203692e-05
2023-01-23 04:40:54.759454: step: 808/533, loss: 0.013832474127411842
2023-01-23 04:40:55.941739: step: 812/533, loss: 0.0277315154671669
2023-01-23 04:40:57.108003: step: 816/533, loss: 0.05567779764533043
2023-01-23 04:40:58.268703: step: 820/533, loss: 8.893013728084043e-05
2023-01-23 04:40:59.435242: step: 824/533, loss: 6.351471529342234e-05
2023-01-23 04:41:00.641523: step: 828/533, loss: 6.46591215627268e-05
2023-01-23 04:41:01.820366: step: 832/533, loss: 0.0013504029484465718
2023-01-23 04:41:03.033028: step: 836/533, loss: 0.00016469955153297633
2023-01-23 04:41:04.191321: step: 840/533, loss: 1.773834264895413e-05
2023-01-23 04:41:05.362684: step: 844/533, loss: 0.004299211781471968
2023-01-23 04:41:06.542807: step: 848/533, loss: 0.007451486308127642
2023-01-23 04:41:07.701579: step: 852/533, loss: 0.000179290771484375
2023-01-23 04:41:08.888673: step: 856/533, loss: 0.0008804321405477822
2023-01-23 04:41:10.051595: step: 860/533, loss: 0.0007562637329101562
2023-01-23 04:41:11.238294: step: 864/533, loss: 0.4774315655231476
2023-01-23 04:41:12.451298: step: 868/533, loss: 0.007146644406020641
2023-01-23 04:41:13.647961: step: 872/533, loss: 0.0006508827209472656
2023-01-23 04:41:14.829864: step: 876/533, loss: 0.00016288757615257055
2023-01-23 04:41:16.007276: step: 880/533, loss: 0.008348274044692516
2023-01-23 04:41:17.194412: step: 884/533, loss: 4.00543212890625e-05
2023-01-23 04:41:18.359426: step: 888/533, loss: 0.0050824168138206005
2023-01-23 04:41:19.558075: step: 892/533, loss: 0.0004955768818035722
2023-01-23 04:41:20.752122: step: 896/533, loss: 0.03819713369011879
2023-01-23 04:41:21.980186: step: 900/533, loss: 0.0019178390502929688
2023-01-23 04:41:23.134823: step: 904/533, loss: 0.0057343486696481705
2023-01-23 04:41:24.324038: step: 908/533, loss: 1.9931792849092744e-05
2023-01-23 04:41:25.470509: step: 912/533, loss: -5.245208853921213e-07
2023-01-23 04:41:26.618185: step: 916/533, loss: 0.00013856888108421117
2023-01-23 04:41:27.812398: step: 920/533, loss: 0.002774286549538374
2023-01-23 04:41:28.986909: step: 924/533, loss: 1.697540210443549e-05
2023-01-23 04:41:30.138549: step: 928/533, loss: 0.008076668716967106
2023-01-23 04:41:31.326173: step: 932/533, loss: 2.86102294921875e-06
2023-01-23 04:41:32.493477: step: 936/533, loss: 2.8419495720299892e-05
2023-01-23 04:41:33.622706: step: 940/533, loss: 0.0008134842501021922
2023-01-23 04:41:34.792459: step: 944/533, loss: 0.0012616157764568925
2023-01-23 04:41:35.984724: step: 948/533, loss: 9.040832810569555e-05
2023-01-23 04:41:37.138043: step: 952/533, loss: 0.0010336876148357987
2023-01-23 04:41:38.328101: step: 956/533, loss: 0.0003501892206259072
2023-01-23 04:41:39.494781: step: 960/533, loss: 0.0036535265389829874
2023-01-23 04:41:40.689126: step: 964/533, loss: 0.00019607543072197586
2023-01-23 04:41:41.856984: step: 968/533, loss: 2.1123885744600557e-05
2023-01-23 04:41:43.066314: step: 972/533, loss: 0.00491986284032464
2023-01-23 04:41:44.237945: step: 976/533, loss: 0.007938195019960403
2023-01-23 04:41:45.387067: step: 980/533, loss: 4.653930591302924e-05
2023-01-23 04:41:46.589855: step: 984/533, loss: 0.00041484832763671875
2023-01-23 04:41:47.754801: step: 988/533, loss: 0.048197317868471146
2023-01-23 04:41:48.876408: step: 992/533, loss: 0.025508642196655273
2023-01-23 04:41:50.035046: step: 996/533, loss: 0.021366501227021217
2023-01-23 04:41:51.226300: step: 1000/533, loss: 4.95910626341356e-06
2023-01-23 04:41:52.404183: step: 1004/533, loss: 0.000618457852397114
2023-01-23 04:41:53.601476: step: 1008/533, loss: 0.07714968174695969
2023-01-23 04:41:54.775246: step: 1012/533, loss: 5.14984130859375e-05
2023-01-23 04:41:55.962667: step: 1016/533, loss: 1.6021729607018642e-05
2023-01-23 04:41:57.147675: step: 1020/533, loss: 2.346038854739163e-05
2023-01-23 04:41:58.338239: step: 1024/533, loss: 0.0005279540782794356
2023-01-23 04:41:59.493445: step: 1028/533, loss: 1.697540210443549e-05
2023-01-23 04:42:00.660004: step: 1032/533, loss: 1.3303756531968247e-05
2023-01-23 04:42:01.833931: step: 1036/533, loss: 9.078979201149195e-05
2023-01-23 04:42:03.013617: step: 1040/533, loss: 0.00485992431640625
2023-01-23 04:42:04.192160: step: 1044/533, loss: 0.004650878719985485
2023-01-23 04:42:05.374056: step: 1048/533, loss: 0.0032660483848303556
2023-01-23 04:42:06.553056: step: 1052/533, loss: 0.03774967044591904
2023-01-23 04:42:07.708304: step: 1056/533, loss: 0.023192785680294037
2023-01-23 04:42:08.903421: step: 1060/533, loss: 0.007928658276796341
2023-01-23 04:42:10.059868: step: 1064/533, loss: 0.00019159316434524953
2023-01-23 04:42:11.253734: step: 1068/533, loss: 0.028194429352879524
2023-01-23 04:42:12.422289: step: 1072/533, loss: 0.00010051727440441027
2023-01-23 04:42:13.580947: step: 1076/533, loss: 3.376007225597277e-05
2023-01-23 04:42:14.739608: step: 1080/533, loss: 2.207756187999621e-05
2023-01-23 04:42:15.901541: step: 1084/533, loss: 0.0008795738103799522
2023-01-23 04:42:17.057785: step: 1088/533, loss: 9.784698340808973e-05
2023-01-23 04:42:18.232647: step: 1092/533, loss: 0.012301064096391201
2023-01-23 04:42:19.386583: step: 1096/533, loss: 1.3446808225126006e-05
2023-01-23 04:42:20.561260: step: 1100/533, loss: 1.5258789289873675e-06
2023-01-23 04:42:21.745078: step: 1104/533, loss: 0.014218902215361595
2023-01-23 04:42:22.917284: step: 1108/533, loss: 0.0026243210304528475
2023-01-23 04:42:24.070967: step: 1112/533, loss: 7.152557373046875e-06
2023-01-23 04:42:25.291296: step: 1116/533, loss: 0.0006278991932049394
2023-01-23 04:42:26.475699: step: 1120/533, loss: 0.00031414031400345266
2023-01-23 04:42:27.630970: step: 1124/533, loss: 8.087158494163305e-05
2023-01-23 04:42:28.821803: step: 1128/533, loss: 5.397796485340223e-05
2023-01-23 04:42:30.002102: step: 1132/533, loss: 0.010439587756991386
2023-01-23 04:42:31.185298: step: 1136/533, loss: 2.47955322265625e-05
2023-01-23 04:42:32.422129: step: 1140/533, loss: 0.007459640968590975
2023-01-23 04:42:33.624852: step: 1144/533, loss: 0.0021137238945811987
2023-01-23 04:42:34.852244: step: 1148/533, loss: 4.129410081077367e-05
2023-01-23 04:42:36.042425: step: 1152/533, loss: 1.5163421267061494e-05
2023-01-23 04:42:37.258710: step: 1156/533, loss: 1.7166138377433526e-06
2023-01-23 04:42:38.440856: step: 1160/533, loss: 0.03963002935051918
2023-01-23 04:42:39.612103: step: 1164/533, loss: 0.08506827056407928
2023-01-23 04:42:40.789368: step: 1168/533, loss: 0.0009277343633584678
2023-01-23 04:42:41.919800: step: 1172/533, loss: 0.011252212338149548
2023-01-23 04:42:43.055400: step: 1176/533, loss: 0.0007089615100994706
2023-01-23 04:42:44.230714: step: 1180/533, loss: 0.0010353088146075606
2023-01-23 04:42:45.406515: step: 1184/533, loss: 0.0006683349492959678
2023-01-23 04:42:46.618497: step: 1188/533, loss: 0.592664897441864
2023-01-23 04:42:47.797389: step: 1192/533, loss: 0.0042938231490552425
2023-01-23 04:42:48.973776: step: 1196/533, loss: 0.012715148739516735
2023-01-23 04:42:50.185500: step: 1200/533, loss: 0.1252616047859192
2023-01-23 04:42:51.370549: step: 1204/533, loss: 0.0007080078357830644
2023-01-23 04:42:52.542018: step: 1208/533, loss: 0.006268978118896484
2023-01-23 04:42:53.714150: step: 1212/533, loss: 7.534027099609375e-05
2023-01-23 04:42:54.928802: step: 1216/533, loss: 0.02620716206729412
2023-01-23 04:42:56.129233: step: 1220/533, loss: 0.033933356404304504
2023-01-23 04:42:57.354506: step: 1224/533, loss: 5.617141869151965e-05
2023-01-23 04:42:58.511595: step: 1228/533, loss: 0.0019325256580486894
2023-01-23 04:42:59.707520: step: 1232/533, loss: 2.3555756342830136e-05
2023-01-23 04:43:00.886281: step: 1236/533, loss: 0.0031822205055505037
2023-01-23 04:43:02.052947: step: 1240/533, loss: 1.1157988410559483e-05
2023-01-23 04:43:03.240579: step: 1244/533, loss: 0.0002727508544921875
2023-01-23 04:43:04.369520: step: 1248/533, loss: 0.00011658668518066406
2023-01-23 04:43:05.571403: step: 1252/533, loss: 0.054642681032419205
2023-01-23 04:43:06.700882: step: 1256/533, loss: 0.00229721050709486
2023-01-23 04:43:07.874240: step: 1260/533, loss: 0.002063751220703125
2023-01-23 04:43:09.045269: step: 1264/533, loss: 0.06561774760484695
2023-01-23 04:43:10.262140: step: 1268/533, loss: 0.00047388079110533
2023-01-23 04:43:11.436802: step: 1272/533, loss: 0.00015816689119674265
2023-01-23 04:43:12.616352: step: 1276/533, loss: 2.593994213384576e-05
2023-01-23 04:43:13.817312: step: 1280/533, loss: 0.01809406280517578
2023-01-23 04:43:15.000586: step: 1284/533, loss: 0.00015687942504882812
2023-01-23 04:43:16.166702: step: 1288/533, loss: 0.0005552291986532509
2023-01-23 04:43:17.330648: step: 1292/533, loss: 0.008483218960464
2023-01-23 04:43:18.448474: step: 1296/533, loss: 6.084441702114418e-05
2023-01-23 04:43:19.657021: step: 1300/533, loss: -3.6239616747479886e-06
2023-01-23 04:43:20.820883: step: 1304/533, loss: 8.687973604537547e-05
2023-01-23 04:43:21.982136: step: 1308/533, loss: 4.0626528061693534e-05
2023-01-23 04:43:23.183845: step: 1312/533, loss: 0.008015441708266735
2023-01-23 04:43:24.339855: step: 1316/533, loss: 0.0031057356391102076
2023-01-23 04:43:25.551178: step: 1320/533, loss: 4.634857032215223e-05
2023-01-23 04:43:26.697217: step: 1324/533, loss: 0.0013029099209234118
2023-01-23 04:43:27.892566: step: 1328/533, loss: 1.4686585018353071e-05
2023-01-23 04:43:29.080895: step: 1332/533, loss: 8.454322960460559e-05
2023-01-23 04:43:30.267251: step: 1336/533, loss: 0.001157474471256137
2023-01-23 04:43:31.455353: step: 1340/533, loss: 0.06334400177001953
2023-01-23 04:43:32.629923: step: 1344/533, loss: 0.004132700152695179
2023-01-23 04:43:33.754227: step: 1348/533, loss: 8.525847806595266e-05
2023-01-23 04:43:34.992693: step: 1352/533, loss: 0.0012422562576830387
2023-01-23 04:43:36.178702: step: 1356/533, loss: 0.00020294189744163305
2023-01-23 04:43:37.362047: step: 1360/533, loss: 0.01821422576904297
2023-01-23 04:43:38.537238: step: 1364/533, loss: 0.00543289165943861
2023-01-23 04:43:39.724684: step: 1368/533, loss: 0.0052276612259447575
2023-01-23 04:43:40.893990: step: 1372/533, loss: 0.0002896309015341103
2023-01-23 04:43:42.004169: step: 1376/533, loss: 3.337860107421875e-05
2023-01-23 04:43:43.179350: step: 1380/533, loss: 0.006535553839057684
2023-01-23 04:43:44.331442: step: 1384/533, loss: 6.198883511387976e-06
2023-01-23 04:43:45.479838: step: 1388/533, loss: 5.340576171875e-05
2023-01-23 04:43:46.685761: step: 1392/533, loss: 0.004298400599509478
2023-01-23 04:43:47.837061: step: 1396/533, loss: 5.664825584972277e-05
2023-01-23 04:43:48.974508: step: 1400/533, loss: 0.00010757446580100805
2023-01-23 04:43:50.162144: step: 1404/533, loss: 0.018986891955137253
2023-01-23 04:43:51.308900: step: 1408/533, loss: 0.00041837693424895406
2023-01-23 04:43:52.448124: step: 1412/533, loss: 0.023760223761200905
2023-01-23 04:43:53.603445: step: 1416/533, loss: 0.0023074152413755655
2023-01-23 04:43:54.781288: step: 1420/533, loss: 0.0027145384810864925
2023-01-23 04:43:55.979949: step: 1424/533, loss: 0.0033185959327965975
2023-01-23 04:43:57.146904: step: 1428/533, loss: 0.002271270612254739
2023-01-23 04:43:58.316567: step: 1432/533, loss: 7.371902756858617e-05
2023-01-23 04:43:59.461478: step: 1436/533, loss: 0.0003232002491131425
2023-01-23 04:44:00.619991: step: 1440/533, loss: 0.00011377334885764867
2023-01-23 04:44:01.769888: step: 1444/533, loss: 0.0015453338855877519
2023-01-23 04:44:02.906427: step: 1448/533, loss: 0.0002846241113729775
2023-01-23 04:44:04.163653: step: 1452/533, loss: 0.0038608552422374487
2023-01-23 04:44:05.337412: step: 1456/533, loss: 0.0005678177112713456
2023-01-23 04:44:06.541152: step: 1460/533, loss: 0.01827402226626873
2023-01-23 04:44:07.691236: step: 1464/533, loss: 0.04267864301800728
2023-01-23 04:44:08.822917: step: 1468/533, loss: 2.002716064453125e-05
2023-01-23 04:44:10.010361: step: 1472/533, loss: 0.000370216352166608
2023-01-23 04:44:11.179445: step: 1476/533, loss: 0.0009328365558758378
2023-01-23 04:44:12.383715: step: 1480/533, loss: -9.536742595628311e-08
2023-01-23 04:44:13.550698: step: 1484/533, loss: 0.017430400475859642
2023-01-23 04:44:14.780280: step: 1488/533, loss: 0.00017061232938431203
2023-01-23 04:44:16.007564: step: 1492/533, loss: 0.000292873359285295
2023-01-23 04:44:17.177831: step: 1496/533, loss: 0.00029964448185637593
2023-01-23 04:44:18.356213: step: 1500/533, loss: 0.00011558533151401207
2023-01-23 04:44:19.561353: step: 1504/533, loss: 0.0001277923583984375
2023-01-23 04:44:20.799035: step: 1508/533, loss: 0.00012931822857353836
2023-01-23 04:44:22.011305: step: 1512/533, loss: 0.009451198391616344
2023-01-23 04:44:23.198813: step: 1516/533, loss: 0.029564427211880684
2023-01-23 04:44:24.358543: step: 1520/533, loss: 0.0017645478947088122
2023-01-23 04:44:25.497130: step: 1524/533, loss: 1.9073486328125e-05
2023-01-23 04:44:26.709505: step: 1528/533, loss: 5.769729796156753e-06
2023-01-23 04:44:27.880108: step: 1532/533, loss: -9.5367431640625e-06
2023-01-23 04:44:29.064229: step: 1536/533, loss: 0.0004646778106689453
2023-01-23 04:44:30.251403: step: 1540/533, loss: 1.9359587895451114e-05
2023-01-23 04:44:31.431330: step: 1544/533, loss: 7.400513277389109e-05
2023-01-23 04:44:32.640752: step: 1548/533, loss: 0.05515308305621147
2023-01-23 04:44:33.819691: step: 1552/533, loss: 0.00010905266390182078
2023-01-23 04:44:34.978968: step: 1556/533, loss: 4.38690176451928e-06
2023-01-23 04:44:36.152056: step: 1560/533, loss: 3.5905839467886835e-05
2023-01-23 04:44:37.302465: step: 1564/533, loss: 2.613067590573337e-05
2023-01-23 04:44:38.496724: step: 1568/533, loss: 2.1457681214087643e-06
2023-01-23 04:44:39.678673: step: 1572/533, loss: 0.0020317076705396175
2023-01-23 04:44:40.912364: step: 1576/533, loss: 0.0002750396670307964
2023-01-23 04:44:42.070937: step: 1580/533, loss: 0.0011255263816565275
2023-01-23 04:44:43.256845: step: 1584/533, loss: 1.049041748046875e-05
2023-01-23 04:44:44.434742: step: 1588/533, loss: 3.6716461181640625e-05
2023-01-23 04:44:45.633393: step: 1592/533, loss: 0.00021114348783157766
2023-01-23 04:44:46.839227: step: 1596/533, loss: 0.10731296986341476
2023-01-23 04:44:48.028795: step: 1600/533, loss: 1.621246337890625e-05
2023-01-23 04:44:49.244284: step: 1604/533, loss: -4.19616708313697e-06
2023-01-23 04:44:50.402187: step: 1608/533, loss: 2.3174285161076114e-05
2023-01-23 04:44:51.563473: step: 1612/533, loss: 1.8787384760798886e-05
2023-01-23 04:44:52.763215: step: 1616/533, loss: 0.0007943630334921181
2023-01-23 04:44:53.945731: step: 1620/533, loss: 4.615783836925402e-05
2023-01-23 04:44:55.158844: step: 1624/533, loss: 0.0007746696355752647
2023-01-23 04:44:56.350611: step: 1628/533, loss: 0.0026132583152502775
2023-01-23 04:44:57.519368: step: 1632/533, loss: 0.17014513909816742
2023-01-23 04:44:58.719264: step: 1636/533, loss: -1.029968279908644e-05
2023-01-23 04:44:59.881041: step: 1640/533, loss: 0.0020588873885571957
2023-01-23 04:45:01.098425: step: 1644/533, loss: -9.346007573185489e-06
2023-01-23 04:45:02.280548: step: 1648/533, loss: 1.392364538332913e-05
2023-01-23 04:45:03.471818: step: 1652/533, loss: 0.0018345832359045744
2023-01-23 04:45:04.638776: step: 1656/533, loss: 1.449584942747606e-05
2023-01-23 04:45:05.785931: step: 1660/533, loss: -1.8119811784345075e-06
2023-01-23 04:45:06.945493: step: 1664/533, loss: 0.00015630721463821828
2023-01-23 04:45:08.155419: step: 1668/533, loss: 2.4223329091910273e-05
2023-01-23 04:45:09.351660: step: 1672/533, loss: 0.0002478599490132183
2023-01-23 04:45:10.525402: step: 1676/533, loss: 0.0008592605590820312
2023-01-23 04:45:11.692335: step: 1680/533, loss: 0.00012741087994072586
2023-01-23 04:45:12.894569: step: 1684/533, loss: 0.017216874286532402
2023-01-23 04:45:14.044135: step: 1688/533, loss: -1.1348724001436494e-05
2023-01-23 04:45:15.196499: step: 1692/533, loss: 4.472732689464465e-05
2023-01-23 04:45:16.372097: step: 1696/533, loss: 1.7929078239831142e-05
2023-01-23 04:45:17.530964: step: 1700/533, loss: 0.0003194809250999242
2023-01-23 04:45:18.715909: step: 1704/533, loss: 0.01260919589549303
2023-01-23 04:45:19.889821: step: 1708/533, loss: 0.06233177334070206
2023-01-23 04:45:21.097105: step: 1712/533, loss: 0.0012255193432793021
2023-01-23 04:45:22.259343: step: 1716/533, loss: 0.00013828277587890625
2023-01-23 04:45:23.449716: step: 1720/533, loss: 4.024505687993951e-05
2023-01-23 04:45:24.642844: step: 1724/533, loss: 0.01676464080810547
2023-01-23 04:45:25.824838: step: 1728/533, loss: 6.45637555862777e-05
2023-01-23 04:45:26.989629: step: 1732/533, loss: 0.023438740521669388
2023-01-23 04:45:28.143422: step: 1736/533, loss: 0.011902046389877796
2023-01-23 04:45:29.329303: step: 1740/533, loss: 0.10964813083410263
2023-01-23 04:45:30.530187: step: 1744/533, loss: 4.806518700206652e-05
2023-01-23 04:45:31.726782: step: 1748/533, loss: 0.0003323554992675781
2023-01-23 04:45:32.897251: step: 1752/533, loss: 0.006012439727783203
2023-01-23 04:45:34.064484: step: 1756/533, loss: 0.00010862351336982101
2023-01-23 04:45:35.253470: step: 1760/533, loss: 4.148483185417717e-06
2023-01-23 04:45:36.431182: step: 1764/533, loss: 0.011141777038574219
2023-01-23 04:45:37.599768: step: 1768/533, loss: 0.0028526782989501953
2023-01-23 04:45:38.768661: step: 1772/533, loss: 0.007021522149443626
2023-01-23 04:45:39.946488: step: 1776/533, loss: 0.03824453428387642
2023-01-23 04:45:41.149282: step: 1780/533, loss: 0.0009559631580486894
2023-01-23 04:45:42.331707: step: 1784/533, loss: 0.0009809493785724044
2023-01-23 04:45:43.483611: step: 1788/533, loss: 0.0008879661909304559
2023-01-23 04:45:44.709380: step: 1792/533, loss: 0.00031299592228606343
2023-01-23 04:45:45.892872: step: 1796/533, loss: 2.3412703740177676e-05
2023-01-23 04:45:47.090976: step: 1800/533, loss: 0.023003196343779564
2023-01-23 04:45:48.279951: step: 1804/533, loss: 0.059653475880622864
2023-01-23 04:45:49.508203: step: 1808/533, loss: 0.00021667480177711695
2023-01-23 04:45:50.708823: step: 1812/533, loss: 0.02505521848797798
2023-01-23 04:45:51.944507: step: 1816/533, loss: 3.776550147449598e-05
2023-01-23 04:45:53.089996: step: 1820/533, loss: 5.826950291520916e-05
2023-01-23 04:45:54.325898: step: 1824/533, loss: 0.03996095806360245
2023-01-23 04:45:55.499087: step: 1828/533, loss: 0.04258919134736061
2023-01-23 04:45:56.675213: step: 1832/533, loss: 0.00017242431931663305
2023-01-23 04:45:57.908528: step: 1836/533, loss: 0.00022563934908248484
2023-01-23 04:45:59.105888: step: 1840/533, loss: 2.6893614631262608e-05
2023-01-23 04:46:00.288461: step: 1844/533, loss: 0.02109680138528347
2023-01-23 04:46:01.469241: step: 1848/533, loss: 5.168914867681451e-05
2023-01-23 04:46:02.649573: step: 1852/533, loss: 0.0014940262772142887
2023-01-23 04:46:03.914914: step: 1856/533, loss: 0.0011319160694256425
2023-01-23 04:46:05.108963: step: 1860/533, loss: 0.002082443330436945
2023-01-23 04:46:06.256916: step: 1864/533, loss: 9.536745437799254e-08
2023-01-23 04:46:07.474217: step: 1868/533, loss: 1.564025842526462e-05
2023-01-23 04:46:08.637297: step: 1872/533, loss: 0.03885927051305771
2023-01-23 04:46:09.808674: step: 1876/533, loss: 0.00048704148503020406
2023-01-23 04:46:10.986307: step: 1880/533, loss: 9.813308861339465e-05
2023-01-23 04:46:12.119690: step: 1884/533, loss: 6.446838960982859e-05
2023-01-23 04:46:13.300324: step: 1888/533, loss: 0.004540538880974054
2023-01-23 04:46:14.512933: step: 1892/533, loss: 2.040863000729587e-05
2023-01-23 04:46:15.676740: step: 1896/533, loss: 0.0002704620419535786
2023-01-23 04:46:16.851330: step: 1900/533, loss: 1.9073468138230965e-07
2023-01-23 04:46:18.022484: step: 1904/533, loss: 0.0018741608364507556
2023-01-23 04:46:19.217500: step: 1908/533, loss: 5.455017526401207e-05
2023-01-23 04:46:20.371179: step: 1912/533, loss: 0.001864624093286693
2023-01-23 04:46:21.554382: step: 1916/533, loss: 5.1164628530386835e-05
2023-01-23 04:46:22.716343: step: 1920/533, loss: 3.2138825190486386e-05
2023-01-23 04:46:23.906421: step: 1924/533, loss: 0.007644557394087315
2023-01-23 04:46:25.101723: step: 1928/533, loss: 0.012665558606386185
2023-01-23 04:46:26.277118: step: 1932/533, loss: 1.4972687495173886e-05
2023-01-23 04:46:27.432269: step: 1936/533, loss: 0.0006610869895666838
2023-01-23 04:46:28.561707: step: 1940/533, loss: 3.299712989246473e-05
2023-01-23 04:46:29.702877: step: 1944/533, loss: -1.573562599332945e-06
2023-01-23 04:46:30.847136: step: 1948/533, loss: 3.9601327443961054e-05
2023-01-23 04:46:32.024671: step: 1952/533, loss: 0.0003427505725994706
2023-01-23 04:46:33.207053: step: 1956/533, loss: 0.014409447088837624
2023-01-23 04:46:34.385007: step: 1960/533, loss: 0.026736069470643997
2023-01-23 04:46:35.580426: step: 1964/533, loss: 0.0008687973604537547
2023-01-23 04:46:36.783843: step: 1968/533, loss: 0.0003067016659770161
2023-01-23 04:46:37.936059: step: 1972/533, loss: 2.6702880859375e-05
2023-01-23 04:46:39.104541: step: 1976/533, loss: 0.0012264251708984375
2023-01-23 04:46:40.253560: step: 1980/533, loss: 2.9659271604032256e-05
2023-01-23 04:46:41.465783: step: 1984/533, loss: 0.0006897926214151084
2023-01-23 04:46:42.626263: step: 1988/533, loss: 0.01601553149521351
2023-01-23 04:46:43.849960: step: 1992/533, loss: 0.03540649637579918
2023-01-23 04:46:45.018567: step: 1996/533, loss: 0.0002895355282817036
2023-01-23 04:46:46.197657: step: 2000/533, loss: 0.00019130707369185984
2023-01-23 04:46:47.414630: step: 2004/533, loss: 0.0019168853759765625
2023-01-23 04:46:48.564702: step: 2008/533, loss: 1.964569128176663e-05
2023-01-23 04:46:49.761876: step: 2012/533, loss: 0.00013847350783180445
2023-01-23 04:46:50.948330: step: 2016/533, loss: 0.0010629654861986637
2023-01-23 04:46:52.129500: step: 2020/533, loss: 0.005642128176987171
2023-01-23 04:46:53.283068: step: 2024/533, loss: 0.004029464907944202
2023-01-23 04:46:54.452134: step: 2028/533, loss: 0.0009443283197470009
2023-01-23 04:46:55.636895: step: 2032/533, loss: 0.00011205673217773438
2023-01-23 04:46:56.786126: step: 2036/533, loss: 0.00021800995455123484
2023-01-23 04:46:57.964823: step: 2040/533, loss: 6.294250852079131e-06
2023-01-23 04:46:59.114240: step: 2044/533, loss: 0.005199051462113857
2023-01-23 04:47:00.355669: step: 2048/533, loss: 0.01759166643023491
2023-01-23 04:47:01.535384: step: 2052/533, loss: 0.013919640332460403
2023-01-23 04:47:02.702304: step: 2056/533, loss: 0.39671382308006287
2023-01-23 04:47:03.839241: step: 2060/533, loss: 1.430511474609375e-06
2023-01-23 04:47:05.020914: step: 2064/533, loss: 5.297661118675023e-05
2023-01-23 04:47:06.202523: step: 2068/533, loss: 4.95910626341356e-06
2023-01-23 04:47:07.387621: step: 2072/533, loss: 7.543563697254285e-05
2023-01-23 04:47:08.543923: step: 2076/533, loss: 0.04627237096428871
2023-01-23 04:47:09.708141: step: 2080/533, loss: 0.003780079074203968
2023-01-23 04:47:10.953364: step: 2084/533, loss: 6.014108657836914e-05
2023-01-23 04:47:12.115062: step: 2088/533, loss: 0.0005304336664266884
2023-01-23 04:47:13.306974: step: 2092/533, loss: 0.0005899906391277909
2023-01-23 04:47:14.509914: step: 2096/533, loss: 0.0004552841419354081
2023-01-23 04:47:15.695609: step: 2100/533, loss: 0.00018424988957121968
2023-01-23 04:47:16.862577: step: 2104/533, loss: 0.028882216662168503
2023-01-23 04:47:18.038027: step: 2108/533, loss: 6.151199340820312e-05
2023-01-23 04:47:19.217653: step: 2112/533, loss: 0.002463913056999445
2023-01-23 04:47:20.415471: step: 2116/533, loss: 0.012499427422881126
2023-01-23 04:47:21.546190: step: 2120/533, loss: 1.3494492122845259e-05
2023-01-23 04:47:22.749926: step: 2124/533, loss: 0.026134587824344635
2023-01-23 04:47:23.891047: step: 2128/533, loss: -8.416175660386216e-06
2023-01-23 04:47:25.040142: step: 2132/533, loss: 2.059936559817288e-05
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.5916496945010183, 'r': 0.7736351531291611, 'f1': 0.6705135603000577}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6411167512690356, 'r': 0.8075447570332481, 'f1': 0.7147707979626485}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.5833333333333334, 'r': 0.9074074074074074, 'f1': 0.7101449275362318}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.5238095238095238, 'r': 0.5238095238095238, 'f1': 0.5238095238095238}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.3684210526315789, 'r': 0.3888888888888889, 'f1': 0.37837837837837834}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6183206106870229, 'r': 0.7549933422103862, 'f1': 0.6798561151079138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Chinese: {'event': {'p': 0.6558164354322306, 'r': 0.7858056265984654, 'f1': 0.7149505526468877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
******************************
Epoch: 29
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:48:07.115860: step: 4/533, loss: 7.963180541992188e-05
2023-01-23 04:48:08.317306: step: 8/533, loss: 0.0004528045537881553
2023-01-23 04:48:09.478933: step: 12/533, loss: 2.6798248654813506e-05
2023-01-23 04:48:10.646204: step: 16/533, loss: 0.0009815215598791838
2023-01-23 04:48:11.870010: step: 20/533, loss: 0.021444130688905716
2023-01-23 04:48:13.051713: step: 24/533, loss: 0.003556156065315008
2023-01-23 04:48:14.235215: step: 28/533, loss: -4.00543194700731e-06
2023-01-23 04:48:15.455141: step: 32/533, loss: 0.004832458682358265
2023-01-23 04:48:16.613727: step: 36/533, loss: 7.362365431617945e-05
2023-01-23 04:48:17.793082: step: 40/533, loss: 1.487731969973538e-05
2023-01-23 04:48:18.982623: step: 44/533, loss: 5.798339770990424e-05
2023-01-23 04:48:20.129522: step: 48/533, loss: 0.001138973282650113
2023-01-23 04:48:21.318321: step: 52/533, loss: 0.001449632691219449
2023-01-23 04:48:22.499805: step: 56/533, loss: 0.014890670776367188
2023-01-23 04:48:23.649921: step: 60/533, loss: 0.005891228094696999
2023-01-23 04:48:24.824558: step: 64/533, loss: 0.014198875986039639
2023-01-23 04:48:26.016941: step: 68/533, loss: 5.855560448253527e-05
2023-01-23 04:48:27.179430: step: 72/533, loss: 0.003890609834343195
2023-01-23 04:48:28.383266: step: 76/533, loss: 3.128051685052924e-05
2023-01-23 04:48:29.586703: step: 80/533, loss: 0.008204556070268154
2023-01-23 04:48:30.755648: step: 84/533, loss: 0.0004915714380331337
2023-01-23 04:48:31.890167: step: 88/533, loss: 0.006618499755859375
2023-01-23 04:48:33.056272: step: 92/533, loss: 8.125305612338707e-05
2023-01-23 04:48:34.255051: step: 96/533, loss: 0.00039987562922760844
2023-01-23 04:48:35.398667: step: 100/533, loss: 0.02913045883178711
2023-01-23 04:48:36.571810: step: 104/533, loss: 2.670288040462765e-06
2023-01-23 04:48:37.743662: step: 108/533, loss: 0.00022010803513694555
2023-01-23 04:48:38.856061: step: 112/533, loss: 5.42163870704826e-05
2023-01-23 04:48:40.027312: step: 116/533, loss: 1.9264220100012608e-05
2023-01-23 04:48:41.189609: step: 120/533, loss: 0.0003942489856854081
2023-01-23 04:48:42.356271: step: 124/533, loss: 1.1730194273695815e-05
2023-01-23 04:48:43.535984: step: 128/533, loss: -1.0490418844710803e-06
2023-01-23 04:48:44.736790: step: 132/533, loss: 0.003448104951530695
2023-01-23 04:48:45.911756: step: 136/533, loss: 2.346038854739163e-05
2023-01-23 04:48:47.084926: step: 140/533, loss: 1.220703143189894e-05
2023-01-23 04:48:48.206542: step: 144/533, loss: 0.0005262374761514366
2023-01-23 04:48:49.382933: step: 148/533, loss: 0.005027580540627241
2023-01-23 04:48:50.621982: step: 152/533, loss: 0.00013599396334029734
2023-01-23 04:48:51.822407: step: 156/533, loss: 0.00015163421630859375
2023-01-23 04:48:52.987242: step: 160/533, loss: 3.0040741876291577e-06
2023-01-23 04:48:54.150454: step: 164/533, loss: 2.474784923833795e-05
2023-01-23 04:48:55.322367: step: 168/533, loss: 7.672310312045738e-05
2023-01-23 04:48:56.484097: step: 172/533, loss: 2.8038026357535273e-05
2023-01-23 04:48:57.667681: step: 176/533, loss: -2.86102294921875e-06
2023-01-23 04:48:58.821257: step: 180/533, loss: 6.84738188283518e-05
2023-01-23 04:49:00.016879: step: 184/533, loss: 0.37682199478149414
2023-01-23 04:49:01.182093: step: 188/533, loss: 1.7642974853515625e-05
2023-01-23 04:49:02.394945: step: 192/533, loss: 1.0442733582749497e-05
2023-01-23 04:49:03.574991: step: 196/533, loss: 5.073547436040826e-05
2023-01-23 04:49:04.739843: step: 200/533, loss: 0.0001874923618743196
2023-01-23 04:49:05.933284: step: 204/533, loss: 2.6512147087487392e-05
2023-01-23 04:49:07.083636: step: 208/533, loss: 0.0018810273613780737
2023-01-23 04:49:08.228873: step: 212/533, loss: 0.00013179780216887593
2023-01-23 04:49:09.414790: step: 216/533, loss: 0.0004856109735555947
2023-01-23 04:49:10.586584: step: 220/533, loss: 0.06237411871552467
2023-01-23 04:49:11.789788: step: 224/533, loss: 0.011865615844726562
2023-01-23 04:49:12.963720: step: 228/533, loss: 0.005190658383071423
2023-01-23 04:49:14.111443: step: 232/533, loss: 5.664825584972277e-05
2023-01-23 04:49:15.288506: step: 236/533, loss: 1.0967255548166577e-05
2023-01-23 04:49:16.466619: step: 240/533, loss: 1.7642974853515625e-05
2023-01-23 04:49:17.624916: step: 244/533, loss: 6.67572021484375e-06
2023-01-23 04:49:18.823139: step: 248/533, loss: 0.0003154754813294858
2023-01-23 04:49:20.022957: step: 252/533, loss: 0.00016288757615257055
2023-01-23 04:49:21.194975: step: 256/533, loss: 2.021789623540826e-05
2023-01-23 04:49:22.363433: step: 260/533, loss: 5.1116945542162284e-05
2023-01-23 04:49:23.504964: step: 264/533, loss: 7.724762326688506e-06
2023-01-23 04:49:24.642247: step: 268/533, loss: 0.0011365890968590975
2023-01-23 04:49:25.767362: step: 272/533, loss: 0.001000261283479631
2023-01-23 04:49:26.914301: step: 276/533, loss: 0.012322806753218174
2023-01-23 04:49:28.088480: step: 280/533, loss: 0.004737759009003639
2023-01-23 04:49:29.245412: step: 284/533, loss: -5.7220458984375e-06
2023-01-23 04:49:30.445041: step: 288/533, loss: -3.814697265625e-06
2023-01-23 04:49:31.579630: step: 292/533, loss: 2.3269654775504023e-05
2023-01-23 04:49:32.762796: step: 296/533, loss: -4.2343137465650216e-05
2023-01-23 04:49:33.982835: step: 300/533, loss: 0.01856079138815403
2023-01-23 04:49:35.184887: step: 304/533, loss: 0.0003593444998841733
2023-01-23 04:49:36.389379: step: 308/533, loss: 0.009319210425019264
2023-01-23 04:49:37.598284: step: 312/533, loss: 0.0005790710565634072
2023-01-23 04:49:38.782161: step: 316/533, loss: 0.011573279276490211
2023-01-23 04:49:39.964713: step: 320/533, loss: 0.0005815505865029991
2023-01-23 04:49:41.156739: step: 324/533, loss: 4.653930591302924e-05
2023-01-23 04:49:42.358731: step: 328/533, loss: 0.0021497728303074837
2023-01-23 04:49:43.555799: step: 332/533, loss: 3.1805036996956915e-05
2023-01-23 04:49:44.713566: step: 336/533, loss: 0.0003741264226846397
2023-01-23 04:49:45.903821: step: 340/533, loss: -1.201629675051663e-05
2023-01-23 04:49:47.088621: step: 344/533, loss: 0.0018428802723065019
2023-01-23 04:49:48.257534: step: 348/533, loss: 3.261566234868951e-05
2023-01-23 04:49:49.422971: step: 352/533, loss: 0.026845265179872513
2023-01-23 04:49:50.557728: step: 356/533, loss: 0.00016660690016578883
2023-01-23 04:49:51.754140: step: 360/533, loss: 0.010023879818618298
2023-01-23 04:49:53.008458: step: 364/533, loss: 0.00011177062697242945
2023-01-23 04:49:54.194153: step: 368/533, loss: 0.03643150255084038
2023-01-23 04:49:55.356761: step: 372/533, loss: 0.008087730966508389
2023-01-23 04:49:56.519921: step: 376/533, loss: 3.2424925393570447e-06
2023-01-23 04:49:57.691880: step: 380/533, loss: 7.286071922862902e-05
2023-01-23 04:49:58.905567: step: 384/533, loss: 8.678436643094756e-06
2023-01-23 04:50:00.099433: step: 388/533, loss: 0.0009160518529824913
2023-01-23 04:50:01.278385: step: 392/533, loss: 0.0005702972412109375
2023-01-23 04:50:02.456874: step: 396/533, loss: 0.04440345615148544
2023-01-23 04:50:03.628579: step: 400/533, loss: 4.653930591302924e-05
2023-01-23 04:50:04.830078: step: 404/533, loss: 0.0009916304843500257
2023-01-23 04:50:06.052111: step: 408/533, loss: 0.0004911422729492188
2023-01-23 04:50:07.219012: step: 412/533, loss: 0.01899242401123047
2023-01-23 04:50:08.384813: step: 416/533, loss: 0.00021104811457917094
2023-01-23 04:50:09.555722: step: 420/533, loss: 0.00021486282639671117
2023-01-23 04:50:10.718827: step: 424/533, loss: 0.002027368638664484
2023-01-23 04:50:11.857534: step: 428/533, loss: 0.0003986835654359311
2023-01-23 04:50:13.127951: step: 432/533, loss: 0.00330352783203125
2023-01-23 04:50:14.291535: step: 436/533, loss: 0.013103485107421875
2023-01-23 04:50:15.449488: step: 440/533, loss: 8.220673043979332e-05
2023-01-23 04:50:16.630712: step: 444/533, loss: 0.006476211827248335
2023-01-23 04:50:17.813736: step: 448/533, loss: -4.57763690064894e-06
2023-01-23 04:50:19.004008: step: 452/533, loss: -0.0
2023-01-23 04:50:20.142712: step: 456/533, loss: 3.7765505112474784e-05
2023-01-23 04:50:21.319449: step: 460/533, loss: 3.395080420887098e-05
2023-01-23 04:50:22.476868: step: 464/533, loss: 4.310607982915826e-05
2023-01-23 04:50:23.668756: step: 468/533, loss: 0.004195690155029297
2023-01-23 04:50:24.816235: step: 472/533, loss: 0.00789022445678711
2023-01-23 04:50:25.973204: step: 476/533, loss: 5.91278057981981e-06
2023-01-23 04:50:27.135103: step: 480/533, loss: 1.3351440202313825e-06
2023-01-23 04:50:28.304855: step: 484/533, loss: 0.0003985404910054058
2023-01-23 04:50:29.498846: step: 488/533, loss: 0.06752987205982208
2023-01-23 04:50:30.641631: step: 492/533, loss: 0.008328819647431374
2023-01-23 04:50:31.793386: step: 496/533, loss: 0.015819359570741653
2023-01-23 04:50:33.053572: step: 500/533, loss: 0.019759178161621094
2023-01-23 04:50:34.218717: step: 504/533, loss: 0.00322723388671875
2023-01-23 04:50:35.385227: step: 508/533, loss: 0.00013881921768188477
2023-01-23 04:50:36.583628: step: 512/533, loss: 0.00067815778311342
2023-01-23 04:50:37.735793: step: 516/533, loss: -8.96453821042087e-06
2023-01-23 04:50:38.906742: step: 520/533, loss: 7.696151442360133e-05
2023-01-23 04:50:40.067930: step: 524/533, loss: 0.0009431838989257812
2023-01-23 04:50:41.248170: step: 528/533, loss: 7.686614844715223e-05
2023-01-23 04:50:42.395134: step: 532/533, loss: 1.106262243411038e-05
2023-01-23 04:50:43.519221: step: 536/533, loss: 0.004604148678481579
2023-01-23 04:50:44.697516: step: 540/533, loss: 0.3151291012763977
2023-01-23 04:50:45.858237: step: 544/533, loss: -7.62939453125e-06
2023-01-23 04:50:47.065433: step: 548/533, loss: 0.006260585971176624
2023-01-23 04:50:48.244828: step: 552/533, loss: 0.00654838141053915
2023-01-23 04:50:49.425359: step: 556/533, loss: 1.9073495423072018e-06
2023-01-23 04:50:50.624700: step: 560/533, loss: 0.0005549431079998612
2023-01-23 04:50:51.790616: step: 564/533, loss: 0.0011314392322674394
2023-01-23 04:50:52.950589: step: 568/533, loss: 0.00021576881408691406
2023-01-23 04:50:54.137398: step: 572/533, loss: 0.005048561375588179
2023-01-23 04:50:55.331776: step: 576/533, loss: 4.95910626341356e-06
2023-01-23 04:50:56.486036: step: 580/533, loss: 0.00028133392333984375
2023-01-23 04:50:57.662599: step: 584/533, loss: 6.0844424297101796e-05
2023-01-23 04:50:58.843124: step: 588/533, loss: 0.0031113624572753906
2023-01-23 04:50:59.984132: step: 592/533, loss: 0.011923504061996937
2023-01-23 04:51:01.146477: step: 596/533, loss: 0.013973427005112171
2023-01-23 04:51:02.332673: step: 600/533, loss: 0.048525430262088776
2023-01-23 04:51:03.535243: step: 604/533, loss: 0.0027065277099609375
2023-01-23 04:51:04.692686: step: 608/533, loss: 8.75473051564768e-05
2023-01-23 04:51:05.859725: step: 612/533, loss: 0.0033147812355309725
2023-01-23 04:51:07.026893: step: 616/533, loss: 0.03016185760498047
2023-01-23 04:51:08.221080: step: 620/533, loss: 0.00013847352238371968
2023-01-23 04:51:09.390370: step: 624/533, loss: 0.0020377635955810547
2023-01-23 04:51:10.597901: step: 628/533, loss: 0.00010318756540073082
2023-01-23 04:51:11.724039: step: 632/533, loss: 0.00015163421630859375
2023-01-23 04:51:12.902095: step: 636/533, loss: 0.05630455166101456
2023-01-23 04:51:14.084835: step: 640/533, loss: 0.007293033413589001
2023-01-23 04:51:15.222007: step: 644/533, loss: -6.86645489622606e-06
2023-01-23 04:51:16.361947: step: 648/533, loss: 3.3664702641544864e-05
2023-01-23 04:51:17.514813: step: 652/533, loss: 6.771088010282256e-06
2023-01-23 04:51:18.681595: step: 656/533, loss: 0.003407812211662531
2023-01-23 04:51:19.828851: step: 660/533, loss: -1.382828031637473e-06
2023-01-23 04:51:20.973684: step: 664/533, loss: 0.021144604310393333
2023-01-23 04:51:22.155083: step: 668/533, loss: 6.580352419405244e-06
2023-01-23 04:51:23.340575: step: 672/533, loss: 3.013610876223538e-05
2023-01-23 04:51:24.521719: step: 676/533, loss: 0.0015642166836187243
2023-01-23 04:51:25.672998: step: 680/533, loss: 3.967285010730848e-05
2023-01-23 04:51:26.845590: step: 684/533, loss: -1.907349087559851e-06
2023-01-23 04:51:28.002992: step: 688/533, loss: 0.01734914816915989
2023-01-23 04:51:29.175000: step: 692/533, loss: 0.00022182465181685984
2023-01-23 04:51:30.371879: step: 696/533, loss: 0.00023326874361373484
2023-01-23 04:51:31.542279: step: 700/533, loss: 0.00026979445829056203
2023-01-23 04:51:32.675176: step: 704/533, loss: 2.012253025895916e-05
2023-01-23 04:51:33.821256: step: 708/533, loss: 1.1110305422334932e-05
2023-01-23 04:51:34.991763: step: 712/533, loss: 0.04693937301635742
2023-01-23 04:51:36.097968: step: 716/533, loss: 2.4795533590804553e-06
2023-01-23 04:51:37.270497: step: 720/533, loss: 0.0017507553566247225
2023-01-23 04:51:38.423758: step: 724/533, loss: -1.4591217222914565e-05
2023-01-23 04:51:39.636245: step: 728/533, loss: 2.346038854739163e-05
2023-01-23 04:51:40.787677: step: 732/533, loss: 0.000988006591796875
2023-01-23 04:51:41.966583: step: 736/533, loss: 0.08970393985509872
2023-01-23 04:51:43.152826: step: 740/533, loss: 0.025391673669219017
2023-01-23 04:51:44.318241: step: 744/533, loss: 0.0323491096496582
2023-01-23 04:51:45.588204: step: 748/533, loss: 0.017469406127929688
2023-01-23 04:51:46.776164: step: 752/533, loss: 4.130596160888672
2023-01-23 04:51:47.933713: step: 756/533, loss: 0.030504608526825905
2023-01-23 04:51:49.080070: step: 760/533, loss: 0.0010730744106695056
2023-01-23 04:51:50.240224: step: 764/533, loss: 9.346007573185489e-06
2023-01-23 04:51:51.469575: step: 768/533, loss: 1.316070574830519e-05
2023-01-23 04:51:52.613535: step: 772/533, loss: 7.64846772653982e-05
2023-01-23 04:51:53.743489: step: 776/533, loss: 0.000743865966796875
2023-01-23 04:51:54.926651: step: 780/533, loss: 0.0004986286512576044
2023-01-23 04:51:56.116985: step: 784/533, loss: 0.003444671630859375
2023-01-23 04:51:57.361347: step: 788/533, loss: 0.05000896379351616
2023-01-23 04:51:58.532966: step: 792/533, loss: 0.000462436699308455
2023-01-23 04:51:59.701643: step: 796/533, loss: 3.743171691894531e-05
2023-01-23 04:52:00.897021: step: 800/533, loss: 0.01708526536822319
2023-01-23 04:52:02.092647: step: 804/533, loss: 0.0003654480096884072
2023-01-23 04:52:03.253708: step: 808/533, loss: 0.0001984596165129915
2023-01-23 04:52:04.427359: step: 812/533, loss: 0.0005933761713095009
2023-01-23 04:52:05.603391: step: 816/533, loss: 9.193421283271164e-05
2023-01-23 04:52:06.767956: step: 820/533, loss: 0.0007369995582848787
2023-01-23 04:52:07.930805: step: 824/533, loss: 0.0017513275379315019
2023-01-23 04:52:09.083759: step: 828/533, loss: 4.76837158203125e-06
2023-01-23 04:52:10.220440: step: 832/533, loss: 2.7465821403893642e-05
2023-01-23 04:52:11.440914: step: 836/533, loss: 0.0003027915954589844
2023-01-23 04:52:12.604003: step: 840/533, loss: 9.202957153320312e-05
2023-01-23 04:52:13.761442: step: 844/533, loss: 0.0002960205019917339
2023-01-23 04:52:14.919935: step: 848/533, loss: 4.959106809110381e-05
2023-01-23 04:52:16.125376: step: 852/533, loss: 0.0026914598420262337
2023-01-23 04:52:17.283321: step: 856/533, loss: 7.328986976062879e-05
2023-01-23 04:52:18.439900: step: 860/533, loss: 0.002540302462875843
2023-01-23 04:52:19.601681: step: 864/533, loss: 5.097389657748863e-05
2023-01-23 04:52:20.741574: step: 868/533, loss: 0.00167675013653934
2023-01-23 04:52:21.958909: step: 872/533, loss: 0.0019192696781829
2023-01-23 04:52:23.096739: step: 876/533, loss: 0.00300426478497684
2023-01-23 04:52:24.313323: step: 880/533, loss: 1.1348724001436494e-05
2023-01-23 04:52:25.492688: step: 884/533, loss: 0.00228805560618639
2023-01-23 04:52:26.631937: step: 888/533, loss: 8.583068620282575e-07
2023-01-23 04:52:27.808732: step: 892/533, loss: 0.0011803627712652087
2023-01-23 04:52:29.010727: step: 896/533, loss: 0.0001911163271870464
2023-01-23 04:52:30.170919: step: 900/533, loss: 0.005280113313347101
2023-01-23 04:52:31.327112: step: 904/533, loss: 2.403259350103326e-05
2023-01-23 04:52:32.490675: step: 908/533, loss: 0.02379913441836834
2023-01-23 04:52:33.672232: step: 912/533, loss: 1.201629675051663e-05
2023-01-23 04:52:34.843161: step: 916/533, loss: 0.00927658099681139
2023-01-23 04:52:36.042049: step: 920/533, loss: 8.96453821042087e-06
2023-01-23 04:52:37.177160: step: 924/533, loss: 1.144409225162235e-06
2023-01-23 04:52:38.356152: step: 928/533, loss: -2.7179717108083423e-06
2023-01-23 04:52:39.537831: step: 932/533, loss: 4.711151268566027e-05
2023-01-23 04:52:40.718496: step: 936/533, loss: 0.00026340485783293843
2023-01-23 04:52:41.901075: step: 940/533, loss: 0.0008029937744140625
2023-01-23 04:52:43.105633: step: 944/533, loss: 0.006027603521943092
2023-01-23 04:52:44.275951: step: 948/533, loss: 0.009347820654511452
2023-01-23 04:52:45.478811: step: 952/533, loss: 9.641647193348035e-05
2023-01-23 04:52:46.676025: step: 956/533, loss: 1.602172778802924e-05
2023-01-23 04:52:47.855764: step: 960/533, loss: 0.00015525818162132055
2023-01-23 04:52:49.026969: step: 964/533, loss: -3.6865474157821154e-06
2023-01-23 04:52:50.196462: step: 968/533, loss: 0.0006953001138754189
2023-01-23 04:52:51.410844: step: 972/533, loss: 4.234314110362902e-05
2023-01-23 04:52:52.557079: step: 976/533, loss: 0.03715667873620987
2023-01-23 04:52:53.736962: step: 980/533, loss: 0.09836140275001526
2023-01-23 04:52:54.913828: step: 984/533, loss: 0.04682312160730362
2023-01-23 04:52:56.067951: step: 988/533, loss: 0.0005405425908975303
2023-01-23 04:52:57.270517: step: 992/533, loss: 0.0016632080078125
2023-01-23 04:52:58.417374: step: 996/533, loss: 0.0006349563482217491
2023-01-23 04:52:59.604272: step: 1000/533, loss: 0.00038509367732331157
2023-01-23 04:53:00.757180: step: 1004/533, loss: 0.055867768824100494
2023-01-23 04:53:01.936544: step: 1008/533, loss: 1.2111663636460435e-05
2023-01-23 04:53:03.107973: step: 1012/533, loss: 0.0002483367861714214
2023-01-23 04:53:04.267236: step: 1016/533, loss: 0.0001218795805471018
2023-01-23 04:53:05.419425: step: 1020/533, loss: 0.00724868755787611
2023-01-23 04:53:06.629582: step: 1024/533, loss: 0.00033988954965025187
2023-01-23 04:53:07.785433: step: 1028/533, loss: 0.0335543118417263
2023-01-23 04:53:08.981084: step: 1032/533, loss: 3.63349899998866e-05
2023-01-23 04:53:10.182434: step: 1036/533, loss: 0.006031036376953125
2023-01-23 04:53:11.357411: step: 1040/533, loss: 8.58306884765625e-06
2023-01-23 04:53:12.518487: step: 1044/533, loss: 1.8119808373739943e-06
2023-01-23 04:53:13.703363: step: 1048/533, loss: 0.019656943157315254
2023-01-23 04:53:14.876664: step: 1052/533, loss: -1.6689295989635866e-06
2023-01-23 04:53:16.066092: step: 1056/533, loss: 2.250671423098538e-05
2023-01-23 04:53:17.253941: step: 1060/533, loss: 0.9803696870803833
2023-01-23 04:53:18.431787: step: 1064/533, loss: 0.0001221656712004915
2023-01-23 04:53:19.617618: step: 1068/533, loss: 6.618499901378527e-05
2023-01-23 04:53:20.740352: step: 1072/533, loss: 4.9591067181609105e-06
2023-01-23 04:53:21.902693: step: 1076/533, loss: 0.2125784009695053
2023-01-23 04:53:23.136800: step: 1080/533, loss: 0.00014238357834983617
2023-01-23 04:53:24.309246: step: 1084/533, loss: 3.9672853745287284e-05
2023-01-23 04:53:25.502030: step: 1088/533, loss: 0.0005665779463015497
2023-01-23 04:53:26.659539: step: 1092/533, loss: 0.009566307067871094
2023-01-23 04:53:27.852944: step: 1096/533, loss: 0.00021522045426536351
2023-01-23 04:53:29.015549: step: 1100/533, loss: 0.00147333147469908
2023-01-23 04:53:30.208846: step: 1104/533, loss: 0.014426995068788528
2023-01-23 04:53:31.407526: step: 1108/533, loss: 0.0001589298335602507
2023-01-23 04:53:32.579680: step: 1112/533, loss: 4.57763690064894e-06
2023-01-23 04:53:33.767019: step: 1116/533, loss: 0.00017995835514739156
2023-01-23 04:53:34.911153: step: 1120/533, loss: 0.0002035141078522429
2023-01-23 04:53:36.110282: step: 1124/533, loss: 0.7335087060928345
2023-01-23 04:53:37.300084: step: 1128/533, loss: 0.004726409446448088
2023-01-23 04:53:38.468771: step: 1132/533, loss: 1.9359587895451114e-05
2023-01-23 04:53:39.647102: step: 1136/533, loss: 0.06349802017211914
2023-01-23 04:53:40.811957: step: 1140/533, loss: 0.016556929796934128
2023-01-23 04:53:41.965428: step: 1144/533, loss: 1.0776519957289565e-05
2023-01-23 04:53:43.112961: step: 1148/533, loss: 1.6498564946232364e-05
2023-01-23 04:53:44.257523: step: 1152/533, loss: 0.0007374763954430819
2023-01-23 04:53:45.414489: step: 1156/533, loss: 8.77380352903856e-06
2023-01-23 04:53:46.586388: step: 1160/533, loss: 0.018012046813964844
2023-01-23 04:53:47.768447: step: 1164/533, loss: 0.00022640227689407766
2023-01-23 04:53:48.913359: step: 1168/533, loss: 0.0001028060942189768
2023-01-23 04:53:50.102976: step: 1172/533, loss: 0.0008440017700195312
2023-01-23 04:53:51.254652: step: 1176/533, loss: 0.0001661300630075857
2023-01-23 04:53:52.409762: step: 1180/533, loss: 0.00020494461932685226
2023-01-23 04:53:53.585213: step: 1184/533, loss: 0.00011949539475608617
2023-01-23 04:53:54.746920: step: 1188/533, loss: 0.00013704299635719508
2023-01-23 04:53:55.906929: step: 1192/533, loss: 0.04097404703497887
2023-01-23 04:53:57.074715: step: 1196/533, loss: 0.0008673667325638235
2023-01-23 04:53:58.249924: step: 1200/533, loss: 0.0002759933704510331
2023-01-23 04:53:59.469276: step: 1204/533, loss: 4.653930591302924e-05
2023-01-23 04:54:00.624904: step: 1208/533, loss: 0.002628421876579523
2023-01-23 04:54:01.813846: step: 1212/533, loss: 0.00014371873112395406
2023-01-23 04:54:03.009008: step: 1216/533, loss: 0.028267668560147285
2023-01-23 04:54:04.190661: step: 1220/533, loss: 0.007448578253388405
2023-01-23 04:54:05.344917: step: 1224/533, loss: 0.010971451178193092
2023-01-23 04:54:06.485548: step: 1228/533, loss: 0.00033292770967818797
2023-01-23 04:54:07.678961: step: 1232/533, loss: 0.001904296805150807
2023-01-23 04:54:08.860166: step: 1236/533, loss: 8.668899681651965e-05
2023-01-23 04:54:10.047870: step: 1240/533, loss: 0.009830474853515625
2023-01-23 04:54:11.243832: step: 1244/533, loss: 0.00023908616276457906
2023-01-23 04:54:12.428228: step: 1248/533, loss: 7.43865984986769e-06
2023-01-23 04:54:13.605444: step: 1252/533, loss: 1.3351441339182202e-06
2023-01-23 04:54:14.762741: step: 1256/533, loss: 0.0018934250110760331
2023-01-23 04:54:15.925599: step: 1260/533, loss: 0.01131963636726141
2023-01-23 04:54:17.106629: step: 1264/533, loss: 3.99589553126134e-05
2023-01-23 04:54:18.272058: step: 1268/533, loss: 0.0003822326543740928
2023-01-23 04:54:19.472372: step: 1272/533, loss: 0.02717895433306694
2023-01-23 04:54:20.646354: step: 1276/533, loss: 0.031896304339170456
2023-01-23 04:54:21.820637: step: 1280/533, loss: 0.08291064202785492
2023-01-23 04:54:23.000051: step: 1284/533, loss: 0.01981964148581028
2023-01-23 04:54:24.165849: step: 1288/533, loss: 0.005047607235610485
2023-01-23 04:54:25.281869: step: 1292/533, loss: 0.0006946563953533769
2023-01-23 04:54:26.456692: step: 1296/533, loss: 0.009035111404955387
2023-01-23 04:54:27.647316: step: 1300/533, loss: 0.0017980575794354081
2023-01-23 04:54:28.789818: step: 1304/533, loss: 0.008378982543945312
2023-01-23 04:54:29.960402: step: 1308/533, loss: 0.014710140414536
2023-01-23 04:54:31.146585: step: 1312/533, loss: 8.487701052217744e-06
2023-01-23 04:54:32.334353: step: 1316/533, loss: 1.8787384760798886e-05
2023-01-23 04:54:33.472057: step: 1320/533, loss: 0.002651214599609375
2023-01-23 04:54:34.660761: step: 1324/533, loss: 8.850097947288305e-05
2023-01-23 04:54:35.816201: step: 1328/533, loss: 0.005335903260856867
2023-01-23 04:54:36.984351: step: 1332/533, loss: 0.0066134450025856495
2023-01-23 04:54:38.177665: step: 1336/533, loss: 2.7227401005802676e-05
2023-01-23 04:54:39.326289: step: 1340/533, loss: 0.08215832710266113
2023-01-23 04:54:40.491426: step: 1344/533, loss: 6.29425039733178e-06
2023-01-23 04:54:41.660201: step: 1348/533, loss: 0.3367481231689453
2023-01-23 04:54:42.853804: step: 1352/533, loss: 0.05454311519861221
2023-01-23 04:54:44.049732: step: 1356/533, loss: 0.17127694189548492
2023-01-23 04:54:45.189596: step: 1360/533, loss: 0.011753655038774014
2023-01-23 04:54:46.344573: step: 1364/533, loss: 1.5735626220703125e-05
2023-01-23 04:54:47.484280: step: 1368/533, loss: 0.001644134521484375
2023-01-23 04:54:48.676120: step: 1372/533, loss: 0.02727527730166912
2023-01-23 04:54:49.845051: step: 1376/533, loss: 0.0006443978054448962
2023-01-23 04:54:50.992727: step: 1380/533, loss: 0.002175712725147605
2023-01-23 04:54:52.162368: step: 1384/533, loss: 0.0008421898237429559
2023-01-23 04:54:53.327256: step: 1388/533, loss: 0.03786773607134819
2023-01-23 04:54:54.482599: step: 1392/533, loss: 0.004493999294936657
2023-01-23 04:54:55.682517: step: 1396/533, loss: 0.0005971908685751259
2023-01-23 04:54:56.857868: step: 1400/533, loss: -3.871917579090223e-05
2023-01-23 04:54:58.034449: step: 1404/533, loss: 0.004050064366310835
2023-01-23 04:54:59.231734: step: 1408/533, loss: 5.416870044427924e-05
2023-01-23 04:55:00.500946: step: 1412/533, loss: 7.419585745083168e-05
2023-01-23 04:55:01.708557: step: 1416/533, loss: 0.00016250611224677414
2023-01-23 04:55:02.890852: step: 1420/533, loss: 0.0002401351957814768
2023-01-23 04:55:04.091343: step: 1424/533, loss: 0.0506587028503418
2023-01-23 04:55:05.262691: step: 1428/533, loss: 0.0009137153392657638
2023-01-23 04:55:06.444361: step: 1432/533, loss: 0.00253467564471066
2023-01-23 04:55:07.582087: step: 1436/533, loss: 0.00018959045701194555
2023-01-23 04:55:08.724932: step: 1440/533, loss: 0.2060968279838562
2023-01-23 04:55:09.952665: step: 1444/533, loss: 0.0008440017700195312
2023-01-23 04:55:11.131173: step: 1448/533, loss: 0.0007823944324627519
2023-01-23 04:55:12.271789: step: 1452/533, loss: 0.004110145848244429
2023-01-23 04:55:13.445663: step: 1456/533, loss: 0.000278472900390625
2023-01-23 04:55:14.609613: step: 1460/533, loss: 3.5929682780988514e-05
2023-01-23 04:55:15.776523: step: 1464/533, loss: 0.014162182807922363
2023-01-23 04:55:16.931489: step: 1468/533, loss: 0.0003181457577738911
2023-01-23 04:55:18.084897: step: 1472/533, loss: 4.95910626341356e-06
2023-01-23 04:55:19.317664: step: 1476/533, loss: 0.0009329795720987022
2023-01-23 04:55:20.487231: step: 1480/533, loss: 6.008148375258315e-06
2023-01-23 04:55:21.666600: step: 1484/533, loss: 0.10419555008411407
2023-01-23 04:55:22.843952: step: 1488/533, loss: 1.7547608877066523e-05
2023-01-23 04:55:24.011949: step: 1492/533, loss: 0.0022815705742686987
2023-01-23 04:55:25.184702: step: 1496/533, loss: -1.4209746950655244e-05
2023-01-23 04:55:26.424890: step: 1500/533, loss: 3.3664702641544864e-05
2023-01-23 04:55:27.574966: step: 1504/533, loss: 0.00010995864431606606
2023-01-23 04:55:28.713514: step: 1508/533, loss: 0.004834878724068403
2023-01-23 04:55:29.907602: step: 1512/533, loss: 0.00010757446580100805
2023-01-23 04:55:31.080602: step: 1516/533, loss: 0.0011323929065838456
2023-01-23 04:55:32.265267: step: 1520/533, loss: 0.001860809396021068
2023-01-23 04:55:33.519078: step: 1524/533, loss: 0.011013126000761986
2023-01-23 04:55:34.662698: step: 1528/533, loss: 0.00016269684419967234
2023-01-23 04:55:35.830366: step: 1532/533, loss: 0.0019326210021972656
2023-01-23 04:55:37.032076: step: 1536/533, loss: 0.11945199966430664
2023-01-23 04:55:38.199819: step: 1540/533, loss: 0.0001066207914846018
2023-01-23 04:55:39.418657: step: 1544/533, loss: 0.00934305228292942
2023-01-23 04:55:40.585652: step: 1548/533, loss: 0.0007795334095135331
2023-01-23 04:55:41.755140: step: 1552/533, loss: 0.04730243980884552
2023-01-23 04:55:42.914071: step: 1556/533, loss: 9.5367431640625e-07
2023-01-23 04:55:44.099138: step: 1560/533, loss: 0.00014905929856467992
2023-01-23 04:55:45.250365: step: 1564/533, loss: 0.02530956268310547
2023-01-23 04:55:46.488776: step: 1568/533, loss: 0.00016403199697379023
2023-01-23 04:55:47.678838: step: 1572/533, loss: 0.00035371779813431203
2023-01-23 04:55:48.881342: step: 1576/533, loss: 0.0015872002113610506
2023-01-23 04:55:50.043991: step: 1580/533, loss: 3.4046173823298886e-05
2023-01-23 04:55:51.212177: step: 1584/533, loss: 0.004333305638283491
2023-01-23 04:55:52.379475: step: 1588/533, loss: 0.0031821727752685547
2023-01-23 04:55:53.588006: step: 1592/533, loss: 0.005445766728371382
2023-01-23 04:55:54.736978: step: 1596/533, loss: 2.117157055181451e-05
2023-01-23 04:55:55.928708: step: 1600/533, loss: -7.343292054429185e-06
2023-01-23 04:55:57.099605: step: 1604/533, loss: 0.003073024796321988
2023-01-23 04:55:58.223799: step: 1608/533, loss: 0.014204598031938076
2023-01-23 04:55:59.370341: step: 1612/533, loss: 0.0127601632848382
2023-01-23 04:56:00.477904: step: 1616/533, loss: 0.0013735414249822497
2023-01-23 04:56:01.649445: step: 1620/533, loss: 0.003961372654885054
2023-01-23 04:56:02.820169: step: 1624/533, loss: 0.004844475071877241
2023-01-23 04:56:03.994913: step: 1628/533, loss: 0.022129535675048828
2023-01-23 04:56:05.165012: step: 1632/533, loss: 0.08166561275720596
2023-01-23 04:56:06.346492: step: 1636/533, loss: 0.00010881424532271922
2023-01-23 04:56:07.532841: step: 1640/533, loss: 2.574920654296875e-05
2023-01-23 04:56:08.745589: step: 1644/533, loss: 0.004196357913315296
2023-01-23 04:56:09.929316: step: 1648/533, loss: 4.9924849008675665e-05
2023-01-23 04:56:11.101821: step: 1652/533, loss: 0.025603104382753372
2023-01-23 04:56:12.334844: step: 1656/533, loss: 0.00566940288990736
2023-01-23 04:56:13.508624: step: 1660/533, loss: 0.004317379090934992
2023-01-23 04:56:14.689253: step: 1664/533, loss: 0.002075386233627796
2023-01-23 04:56:15.870704: step: 1668/533, loss: 0.00019884110952261835
2023-01-23 04:56:17.065931: step: 1672/533, loss: 0.11667118221521378
2023-01-23 04:56:18.237954: step: 1676/533, loss: 0.0006956100114621222
2023-01-23 04:56:19.422146: step: 1680/533, loss: 0.0003963470517192036
2023-01-23 04:56:20.585848: step: 1684/533, loss: 1.2493133908719756e-05
2023-01-23 04:56:21.758034: step: 1688/533, loss: 0.2241135537624359
2023-01-23 04:56:22.936928: step: 1692/533, loss: 0.0001409530668752268
2023-01-23 04:56:24.099682: step: 1696/533, loss: 2.3651124138268642e-05
2023-01-23 04:56:25.261380: step: 1700/533, loss: 0.0007869720575399697
2023-01-23 04:56:26.482305: step: 1704/533, loss: 0.0007658004760742188
2023-01-23 04:56:27.654999: step: 1708/533, loss: 0.11649684607982635
2023-01-23 04:56:28.806888: step: 1712/533, loss: 0.0012390136253088713
2023-01-23 04:56:29.951145: step: 1716/533, loss: 3.070831371587701e-05
2023-01-23 04:56:31.169472: step: 1720/533, loss: 0.008800124749541283
2023-01-23 04:56:32.315611: step: 1724/533, loss: 0.006130409426987171
2023-01-23 04:56:33.538593: step: 1728/533, loss: 0.00027709006099030375
2023-01-23 04:56:34.707925: step: 1732/533, loss: 0.012064743787050247
2023-01-23 04:56:35.891242: step: 1736/533, loss: 0.00026836394681595266
2023-01-23 04:56:37.115973: step: 1740/533, loss: 0.012546730227768421
2023-01-23 04:56:38.254500: step: 1744/533, loss: 0.00032796862069517374
2023-01-23 04:56:39.399001: step: 1748/533, loss: 0.8723475933074951
2023-01-23 04:56:40.544645: step: 1752/533, loss: 0.0007363319164142013
2023-01-23 04:56:41.722510: step: 1756/533, loss: 2.0980833141948096e-06
2023-01-23 04:56:42.873966: step: 1760/533, loss: 0.0038959502708166838
2023-01-23 04:56:44.001991: step: 1764/533, loss: -2.28881845032447e-06
2023-01-23 04:56:45.163501: step: 1768/533, loss: -2.86102294921875e-06
2023-01-23 04:56:46.355567: step: 1772/533, loss: 0.0002876758517231792
2023-01-23 04:56:47.540010: step: 1776/533, loss: 3.318786548334174e-05
2023-01-23 04:56:48.733637: step: 1780/533, loss: 8.583069188716763e-07
2023-01-23 04:56:49.922464: step: 1784/533, loss: 0.0015190124977380037
2023-01-23 04:56:51.078370: step: 1788/533, loss: 2.1743777324445546e-05
2023-01-23 04:56:52.213308: step: 1792/533, loss: 3.2901764370762976e-06
2023-01-23 04:56:53.371385: step: 1796/533, loss: -9.34600848268019e-06
2023-01-23 04:56:54.501366: step: 1800/533, loss: 0.00046949388342909515
2023-01-23 04:56:55.689310: step: 1804/533, loss: 0.00037751198397018015
2023-01-23 04:56:56.887869: step: 1808/533, loss: 0.05875739827752113
2023-01-23 04:56:58.071037: step: 1812/533, loss: 0.000251579302130267
2023-01-23 04:56:59.246708: step: 1816/533, loss: 9.794235666049644e-05
2023-01-23 04:57:00.415460: step: 1820/533, loss: 0.0001445770321879536
2023-01-23 04:57:01.558014: step: 1824/533, loss: 0.0004661559942178428
2023-01-23 04:57:02.731326: step: 1828/533, loss: 4.081726001459174e-05
2023-01-23 04:57:03.950090: step: 1832/533, loss: 0.004021263215690851
2023-01-23 04:57:05.129137: step: 1836/533, loss: 0.18091773986816406
2023-01-23 04:57:06.281042: step: 1840/533, loss: 0.008635115809738636
2023-01-23 04:57:07.443604: step: 1844/533, loss: 0.0007866382948122919
2023-01-23 04:57:08.599072: step: 1848/533, loss: 0.000278282182989642
2023-01-23 04:57:09.733068: step: 1852/533, loss: 5.7029727031476796e-05
2023-01-23 04:57:10.904820: step: 1856/533, loss: 0.00012121201143600047
2023-01-23 04:57:12.092782: step: 1860/533, loss: 0.012169933877885342
2023-01-23 04:57:13.270571: step: 1864/533, loss: 7.629394644936838e-07
2023-01-23 04:57:14.453072: step: 1868/533, loss: 2.1457672119140625e-06
2023-01-23 04:57:15.601644: step: 1872/533, loss: 0.0015893937088549137
2023-01-23 04:57:16.742266: step: 1876/533, loss: 2.384185791015625e-05
2023-01-23 04:57:17.917798: step: 1880/533, loss: 0.05921308323740959
2023-01-23 04:57:19.082832: step: 1884/533, loss: 0.0787748321890831
2023-01-23 04:57:20.265561: step: 1888/533, loss: 0.017388343811035156
2023-01-23 04:57:21.411580: step: 1892/533, loss: 0.0003908157523255795
2023-01-23 04:57:22.614961: step: 1896/533, loss: 1.0013580322265625e-05
2023-01-23 04:57:23.809953: step: 1900/533, loss: 0.0004707336483988911
2023-01-23 04:57:25.003049: step: 1904/533, loss: -8.583068620282575e-07
2023-01-23 04:57:26.154281: step: 1908/533, loss: 0.0005311965942382812
2023-01-23 04:57:27.364232: step: 1912/533, loss: 8.859634544933215e-05
2023-01-23 04:57:28.539582: step: 1916/533, loss: 0.017566299065947533
2023-01-23 04:57:29.746229: step: 1920/533, loss: 5.7029727031476796e-05
2023-01-23 04:57:30.945349: step: 1924/533, loss: 0.00013599396334029734
2023-01-23 04:57:32.118447: step: 1928/533, loss: 8.745193190407008e-05
2023-01-23 04:57:33.274379: step: 1932/533, loss: 0.0009029388311319053
2023-01-23 04:57:34.458097: step: 1936/533, loss: 0.00646400498226285
2023-01-23 04:57:35.619351: step: 1940/533, loss: 7.324219041038305e-05
2023-01-23 04:57:36.766520: step: 1944/533, loss: 0.0006534576532430947
2023-01-23 04:57:37.963871: step: 1948/533, loss: -3.814697265625e-06
2023-01-23 04:57:39.134170: step: 1952/533, loss: 5.7220458984375e-06
2023-01-23 04:57:40.295541: step: 1956/533, loss: 0.005449104588478804
2023-01-23 04:57:41.422716: step: 1960/533, loss: 0.00021533967810682952
2023-01-23 04:57:42.605393: step: 1964/533, loss: 4.510879807639867e-05
2023-01-23 04:57:43.800684: step: 1968/533, loss: 0.0032398223411291838
2023-01-23 04:57:44.959269: step: 1972/533, loss: 0.003849601838737726
2023-01-23 04:57:46.122485: step: 1976/533, loss: 0.028018666431307793
2023-01-23 04:57:47.317042: step: 1980/533, loss: 0.0008300781482830644
2023-01-23 04:57:48.533961: step: 1984/533, loss: 0.0006818771362304688
2023-01-23 04:57:49.715499: step: 1988/533, loss: 2.3365020751953125e-05
2023-01-23 04:57:50.895982: step: 1992/533, loss: 0.013470840640366077
2023-01-23 04:57:52.046765: step: 1996/533, loss: 0.004361343570053577
2023-01-23 04:57:53.236712: step: 2000/533, loss: 2.3365021206700476e-06
2023-01-23 04:57:54.442050: step: 2004/533, loss: 0.006718588061630726
2023-01-23 04:57:55.626680: step: 2008/533, loss: 0.0021800994873046875
2023-01-23 04:57:56.808737: step: 2012/533, loss: 0.0013469696277752519
2023-01-23 04:57:57.978154: step: 2016/533, loss: 2.708435022213962e-05
2023-01-23 04:57:59.182226: step: 2020/533, loss: 0.0006650924915447831
2023-01-23 04:58:00.396883: step: 2024/533, loss: 0.009285212494432926
2023-01-23 04:58:01.581065: step: 2028/533, loss: 2.7358531951904297e-05
2023-01-23 04:58:02.736407: step: 2032/533, loss: 0.006835746578872204
2023-01-23 04:58:03.895905: step: 2036/533, loss: 2.7751922971219756e-05
2023-01-23 04:58:05.079365: step: 2040/533, loss: 0.0006422043079510331
2023-01-23 04:58:06.227779: step: 2044/533, loss: 0.0018190385308116674
2023-01-23 04:58:07.447493: step: 2048/533, loss: 0.0017075538635253906
2023-01-23 04:58:08.614397: step: 2052/533, loss: 0.008793830871582031
2023-01-23 04:58:09.791592: step: 2056/533, loss: 0.0747842788696289
2023-01-23 04:58:10.968351: step: 2060/533, loss: 0.0003153800789732486
2023-01-23 04:58:12.159273: step: 2064/533, loss: 0.000965118408203125
2023-01-23 04:58:13.296505: step: 2068/533, loss: 0.0011789321433752775
2023-01-23 04:58:14.498853: step: 2072/533, loss: 0.0024553299881517887
2023-01-23 04:58:15.700268: step: 2076/533, loss: 0.002536964602768421
2023-01-23 04:58:16.891693: step: 2080/533, loss: 0.010658025741577148
2023-01-23 04:58:18.067190: step: 2084/533, loss: 0.0002533912775106728
2023-01-23 04:58:19.245053: step: 2088/533, loss: 3.0326846172101796e-05
2023-01-23 04:58:20.426512: step: 2092/533, loss: 0.022591495886445045
2023-01-23 04:58:21.575074: step: 2096/533, loss: 0.004225540440529585
2023-01-23 04:58:22.741854: step: 2100/533, loss: 3.538131568348035e-05
2023-01-23 04:58:23.931438: step: 2104/533, loss: 3.328323509776965e-05
2023-01-23 04:58:25.111368: step: 2108/533, loss: 0.0013039589393883944
2023-01-23 04:58:26.306217: step: 2112/533, loss: 0.07391653209924698
2023-01-23 04:58:27.465918: step: 2116/533, loss: 5.865097409696318e-05
2023-01-23 04:58:28.636843: step: 2120/533, loss: 0.00950164720416069
2023-01-23 04:58:29.786563: step: 2124/533, loss: 0.04941196367144585
2023-01-23 04:58:30.961336: step: 2128/533, loss: 0.010000801645219326
2023-01-23 04:58:32.154946: step: 2132/533, loss: 6.399155245162547e-05
==================================================
Loss: 0.023
--------------------
Dev: {'event': {'p': 0.5993914807302231, 'r': 0.7869507323568575, 'f1': 0.6804835924006909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6507447354904982, 'r': 0.8101023017902813, 'f1': 0.7217317003702648}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
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': 29}
Korean: {'event': {'p': 0.6, 'r': 0.5238095238095238, 'f1': 0.559322033898305}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.5555555555555556, 'f1': 0.49382716049382713}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6183206106870229, 'r': 0.7549933422103862, 'f1': 0.6798561151079138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Eng Test for Chinese: {'event': {'p': 0.6558164354322306, 'r': 0.7858056265984654, 'f1': 0.7149505526468877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6301969365426696, 'r': 0.7669773635153129, 'f1': 0.6918918918918918}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6444444444444445, 'r': 0.7787723785166241, 'f1': 0.7052692530399536}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5875984251968503, 'r': 0.7949400798934754, 'f1': 0.6757215619694397}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Eng Test for Russian: {'event': {'p': 0.643248629795715, 'r': 0.8254475703324808, 'f1': 0.7230467656118734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}