Command that produces this log: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024])
>>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024])
>>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024])
>>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024])
>>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024])
>>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024])
>>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096])
>>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096])
>>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024])
>>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024])
>>> xlmr.pooler.dense.weight: torch.Size([1024, 1024])
>>> xlmr.pooler.dense.bias: torch.Size([1024])
>>> trigger_label_ffn.layers.0.weight: torch.Size([450, 1024])
>>> trigger_label_ffn.layers.0.bias: torch.Size([450])
>>> trigger_label_ffn.layers.1.weight: torch.Size([233, 450])
>>> trigger_label_ffn.layers.1.bias: torch.Size([233])
>>> trigger_crf.transition: torch.Size([235, 235])
n_trainable_params: 560511990, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:25:03.700131: step: 4/531, loss: 3.0332765579223633
2023-01-21 08:25:04.833413: step: 8/531, loss: 3.9890761375427246
2023-01-21 08:25:05.976881: step: 12/531, loss: 24.841459274291992
2023-01-21 08:25:07.087491: step: 16/531, loss: 5.859591484069824
2023-01-21 08:25:08.200395: step: 20/531, loss: 26.823410034179688
2023-01-21 08:25:09.305764: step: 24/531, loss: 4.028316497802734
2023-01-21 08:25:10.428110: step: 28/531, loss: 13.13836669921875
2023-01-21 08:25:11.545259: step: 32/531, loss: 15.800943374633789
2023-01-21 08:25:12.664501: step: 36/531, loss: 13.201178550720215
2023-01-21 08:25:13.787889: step: 40/531, loss: 18.712141036987305
2023-01-21 08:25:14.914185: step: 44/531, loss: 2.714864730834961
2023-01-21 08:25:16.060732: step: 48/531, loss: 21.38660430908203
2023-01-21 08:25:17.153490: step: 52/531, loss: 3.945868968963623
2023-01-21 08:25:18.289067: step: 56/531, loss: 11.743212699890137
2023-01-21 08:25:19.424587: step: 60/531, loss: 13.900259017944336
2023-01-21 08:25:20.538547: step: 64/531, loss: 13.357820510864258
2023-01-21 08:25:21.679832: step: 68/531, loss: 3.7479476928710938
2023-01-21 08:25:22.788996: step: 72/531, loss: 3.0918235778808594
2023-01-21 08:25:23.893361: step: 76/531, loss: 3.387728691101074
2023-01-21 08:25:25.053936: step: 80/531, loss: 36.84928894042969
2023-01-21 08:25:26.155839: step: 84/531, loss: 23.01399803161621
2023-01-21 08:25:27.267782: step: 88/531, loss: 39.12159729003906
2023-01-21 08:25:28.382888: step: 92/531, loss: 3.9193806648254395
2023-01-21 08:25:29.505497: step: 96/531, loss: 6.501638889312744
2023-01-21 08:25:30.635773: step: 100/531, loss: 9.5567626953125
2023-01-21 08:25:31.804232: step: 104/531, loss: 13.800580978393555
2023-01-21 08:25:32.918269: step: 108/531, loss: 7.207483291625977
2023-01-21 08:25:34.057265: step: 112/531, loss: 32.66229248046875
2023-01-21 08:25:35.202393: step: 116/531, loss: 3.4956822395324707
2023-01-21 08:25:36.375599: step: 120/531, loss: 3.73321533203125
2023-01-21 08:25:37.525199: step: 124/531, loss: 5.19720458984375
2023-01-21 08:25:38.648332: step: 128/531, loss: 4.249058246612549
2023-01-21 08:25:39.777153: step: 132/531, loss: 5.777254104614258
2023-01-21 08:25:40.913266: step: 136/531, loss: 12.54652214050293
2023-01-21 08:25:42.065794: step: 140/531, loss: 23.855159759521484
2023-01-21 08:25:43.223808: step: 144/531, loss: 23.652910232543945
2023-01-21 08:25:44.320668: step: 148/531, loss: 4.233834266662598
2023-01-21 08:25:45.469306: step: 152/531, loss: 25.489444732666016
2023-01-21 08:25:46.613780: step: 156/531, loss: 3.089613914489746
2023-01-21 08:25:47.719703: step: 160/531, loss: 4.675300598144531
2023-01-21 08:25:48.811801: step: 164/531, loss: 3.804196357727051
2023-01-21 08:25:49.927513: step: 168/531, loss: 6.4520368576049805
2023-01-21 08:25:51.052061: step: 172/531, loss: 3.4101152420043945
2023-01-21 08:25:52.194852: step: 176/531, loss: 3.4412355422973633
2023-01-21 08:25:53.329881: step: 180/531, loss: 14.93376350402832
2023-01-21 08:25:54.463686: step: 184/531, loss: 2.9774580001831055
2023-01-21 08:25:55.566942: step: 188/531, loss: 18.464181900024414
2023-01-21 08:25:56.674896: step: 192/531, loss: 2.5480151176452637
2023-01-21 08:25:57.811698: step: 196/531, loss: 19.042381286621094
2023-01-21 08:25:58.921747: step: 200/531, loss: 15.893377304077148
2023-01-21 08:26:00.008304: step: 204/531, loss: 1.845534324645996
2023-01-21 08:26:01.160997: step: 208/531, loss: 15.35491943359375
2023-01-21 08:26:02.294702: step: 212/531, loss: 7.65878963470459
2023-01-21 08:26:03.407490: step: 216/531, loss: 14.374588012695312
2023-01-21 08:26:04.525205: step: 220/531, loss: 18.26699447631836
2023-01-21 08:26:05.614898: step: 224/531, loss: 15.5499906539917
2023-01-21 08:26:06.737267: step: 228/531, loss: 4.617379188537598
2023-01-21 08:26:07.867525: step: 232/531, loss: 8.427047729492188
2023-01-21 08:26:09.000050: step: 236/531, loss: 16.495691299438477
2023-01-21 08:26:10.115971: step: 240/531, loss: 2.6092939376831055
2023-01-21 08:26:11.216437: step: 244/531, loss: 2.978790283203125
2023-01-21 08:26:12.323328: step: 248/531, loss: 13.746543884277344
2023-01-21 08:26:13.453805: step: 252/531, loss: 16.243314743041992
2023-01-21 08:26:14.574510: step: 256/531, loss: 7.9986371994018555
2023-01-21 08:26:15.711380: step: 260/531, loss: 16.104475021362305
2023-01-21 08:26:16.847450: step: 264/531, loss: 10.928227424621582
2023-01-21 08:26:17.970641: step: 268/531, loss: 19.04630470275879
2023-01-21 08:26:19.094329: step: 272/531, loss: 14.556979179382324
2023-01-21 08:26:20.208654: step: 276/531, loss: 17.606996536254883
2023-01-21 08:26:21.340131: step: 280/531, loss: 9.844139099121094
2023-01-21 08:26:22.473573: step: 284/531, loss: 27.90496063232422
2023-01-21 08:26:23.613532: step: 288/531, loss: 2.5847291946411133
2023-01-21 08:26:24.724194: step: 292/531, loss: 3.0382254123687744
2023-01-21 08:26:25.836546: step: 296/531, loss: 3.6176180839538574
2023-01-21 08:26:26.971875: step: 300/531, loss: 21.48680877685547
2023-01-21 08:26:28.098618: step: 304/531, loss: 3.929943561553955
2023-01-21 08:26:29.231521: step: 308/531, loss: 8.297030448913574
2023-01-21 08:26:30.372190: step: 312/531, loss: 15.864788055419922
2023-01-21 08:26:31.566154: step: 316/531, loss: 32.826087951660156
2023-01-21 08:26:32.685404: step: 320/531, loss: 6.250124931335449
2023-01-21 08:26:33.780796: step: 324/531, loss: 10.671683311462402
2023-01-21 08:26:34.916394: step: 328/531, loss: 12.687604904174805
2023-01-21 08:26:36.053420: step: 332/531, loss: 18.26819610595703
2023-01-21 08:26:37.178988: step: 336/531, loss: 2.780642509460449
2023-01-21 08:26:38.309127: step: 340/531, loss: 16.283519744873047
2023-01-21 08:26:39.426427: step: 344/531, loss: 9.130254745483398
2023-01-21 08:26:40.575613: step: 348/531, loss: 8.334065437316895
2023-01-21 08:26:41.693072: step: 352/531, loss: 10.149765968322754
2023-01-21 08:26:42.838008: step: 356/531, loss: 26.10174560546875
2023-01-21 08:26:43.987490: step: 360/531, loss: 16.297813415527344
2023-01-21 08:26:45.126208: step: 364/531, loss: 3.450869560241699
2023-01-21 08:26:46.261943: step: 368/531, loss: 5.1178507804870605
2023-01-21 08:26:47.400363: step: 372/531, loss: 2.885474443435669
2023-01-21 08:26:48.529493: step: 376/531, loss: 30.20762825012207
2023-01-21 08:26:49.690709: step: 380/531, loss: 15.562658309936523
2023-01-21 08:26:50.806478: step: 384/531, loss: 2.6462650299072266
2023-01-21 08:26:51.916812: step: 388/531, loss: 5.7757768630981445
2023-01-21 08:26:53.039709: step: 392/531, loss: 15.065591812133789
2023-01-21 08:26:54.170910: step: 396/531, loss: 10.5269136428833
2023-01-21 08:26:55.305913: step: 400/531, loss: 7.367352485656738
2023-01-21 08:26:56.434193: step: 404/531, loss: 2.811690330505371
2023-01-21 08:26:57.545078: step: 408/531, loss: 10.781352043151855
2023-01-21 08:26:58.665771: step: 412/531, loss: 3.174560070037842
2023-01-21 08:26:59.792608: step: 416/531, loss: 14.93073844909668
2023-01-21 08:27:00.931951: step: 420/531, loss: 3.3398280143737793
2023-01-21 08:27:02.080489: step: 424/531, loss: 3.4559032917022705
2023-01-21 08:27:03.199078: step: 428/531, loss: 2.799764394760132
2023-01-21 08:27:04.342219: step: 432/531, loss: 1.5183038711547852
2023-01-21 08:27:05.475089: step: 436/531, loss: 1.6708240509033203
2023-01-21 08:27:06.628661: step: 440/531, loss: 19.957786560058594
2023-01-21 08:27:07.766771: step: 444/531, loss: 2.4036645889282227
2023-01-21 08:27:08.900747: step: 448/531, loss: 11.189226150512695
2023-01-21 08:27:10.025227: step: 452/531, loss: 7.232325553894043
2023-01-21 08:27:11.154386: step: 456/531, loss: 2.113729476928711
2023-01-21 08:27:12.308762: step: 460/531, loss: 1.9179741144180298
2023-01-21 08:27:13.447738: step: 464/531, loss: 8.944046020507812
2023-01-21 08:27:14.604495: step: 468/531, loss: 16.67998695373535
2023-01-21 08:27:15.739014: step: 472/531, loss: 12.318568229675293
2023-01-21 08:27:16.870975: step: 476/531, loss: 9.781846046447754
2023-01-21 08:27:17.984092: step: 480/531, loss: 7.681807518005371
2023-01-21 08:27:19.108514: step: 484/531, loss: 12.780887603759766
2023-01-21 08:27:20.262120: step: 488/531, loss: 1.7621686458587646
2023-01-21 08:27:21.379001: step: 492/531, loss: 5.095869541168213
2023-01-21 08:27:22.501737: step: 496/531, loss: 5.915456771850586
2023-01-21 08:27:23.640510: step: 500/531, loss: 7.6137542724609375
2023-01-21 08:27:24.773820: step: 504/531, loss: 4.71314001083374
2023-01-21 08:27:25.908966: step: 508/531, loss: 1.0998773574829102
2023-01-21 08:27:27.040643: step: 512/531, loss: 1.1988365650177002
2023-01-21 08:27:28.149864: step: 516/531, loss: 0.9550460577011108
2023-01-21 08:27:29.280900: step: 520/531, loss: 1.109716773033142
2023-01-21 08:27:30.403086: step: 524/531, loss: 13.10318660736084
2023-01-21 08:27:31.517448: step: 528/531, loss: 1.030605673789978
2023-01-21 08:27:32.661572: step: 532/531, loss: 4.0358686447143555
2023-01-21 08:27:33.802292: step: 536/531, loss: 1.6712257862091064
2023-01-21 08:27:34.949507: step: 540/531, loss: 0.9523038864135742
2023-01-21 08:27:36.068253: step: 544/531, loss: 1.0028724670410156
2023-01-21 08:27:37.245176: step: 548/531, loss: 2.5961227416992188
2023-01-21 08:27:38.372037: step: 552/531, loss: 0.8206800222396851
2023-01-21 08:27:39.491404: step: 556/531, loss: 1.3381786346435547
2023-01-21 08:27:40.611520: step: 560/531, loss: 0.770328164100647
2023-01-21 08:27:41.739477: step: 564/531, loss: 0.9549591541290283
2023-01-21 08:27:42.900385: step: 568/531, loss: 3.4985733032226562
2023-01-21 08:27:44.060402: step: 572/531, loss: 1.0681061744689941
2023-01-21 08:27:45.205209: step: 576/531, loss: 3.586304187774658
2023-01-21 08:27:46.322819: step: 580/531, loss: 0.9384206533432007
2023-01-21 08:27:47.447326: step: 584/531, loss: 0.8816757202148438
2023-01-21 08:27:48.580142: step: 588/531, loss: 4.1721367835998535
2023-01-21 08:27:49.726590: step: 592/531, loss: 3.3882291316986084
2023-01-21 08:27:50.867854: step: 596/531, loss: 3.445366382598877
2023-01-21 08:27:52.021400: step: 600/531, loss: 0.7376421689987183
2023-01-21 08:27:53.170497: step: 604/531, loss: 2.8214468955993652
2023-01-21 08:27:54.291427: step: 608/531, loss: 2.00473690032959
2023-01-21 08:27:55.415714: step: 612/531, loss: 6.6643571853637695
2023-01-21 08:27:56.562804: step: 616/531, loss: 1.9179348945617676
2023-01-21 08:27:57.672714: step: 620/531, loss: 0.5742745399475098
2023-01-21 08:27:58.797296: step: 624/531, loss: 0.745516836643219
2023-01-21 08:27:59.951951: step: 628/531, loss: 0.5563780069351196
2023-01-21 08:28:01.080210: step: 632/531, loss: 0.6017870903015137
2023-01-21 08:28:02.219013: step: 636/531, loss: 1.8896949291229248
2023-01-21 08:28:03.336337: step: 640/531, loss: 0.4716556668281555
2023-01-21 08:28:04.446364: step: 644/531, loss: 1.8702508211135864
2023-01-21 08:28:05.579848: step: 648/531, loss: 0.7170490026473999
2023-01-21 08:28:06.709201: step: 652/531, loss: 0.9703950881958008
2023-01-21 08:28:07.831409: step: 656/531, loss: 0.39847180247306824
2023-01-21 08:28:08.975548: step: 660/531, loss: 1.3900601863861084
2023-01-21 08:28:10.100579: step: 664/531, loss: 3.078333616256714
2023-01-21 08:28:11.212710: step: 668/531, loss: 2.5048274993896484
2023-01-21 08:28:12.366669: step: 672/531, loss: 2.422506093978882
2023-01-21 08:28:13.480799: step: 676/531, loss: 1.824657917022705
2023-01-21 08:28:14.595253: step: 680/531, loss: 0.5725464820861816
2023-01-21 08:28:15.723387: step: 684/531, loss: 0.49483758211135864
2023-01-21 08:28:16.898230: step: 688/531, loss: 1.2039530277252197
2023-01-21 08:28:18.010490: step: 692/531, loss: 1.5589475631713867
2023-01-21 08:28:19.150433: step: 696/531, loss: 1.5279383659362793
2023-01-21 08:28:20.276032: step: 700/531, loss: 1.0019121170043945
2023-01-21 08:28:21.388194: step: 704/531, loss: 0.6314219832420349
2023-01-21 08:28:22.504634: step: 708/531, loss: 0.6624341011047363
2023-01-21 08:28:23.642747: step: 712/531, loss: 1.38822603225708
2023-01-21 08:28:24.754783: step: 716/531, loss: 0.5042579174041748
2023-01-21 08:28:25.869102: step: 720/531, loss: 2.2914187908172607
2023-01-21 08:28:26.994673: step: 724/531, loss: 1.2736380100250244
2023-01-21 08:28:28.116117: step: 728/531, loss: 1.0720560550689697
2023-01-21 08:28:29.239685: step: 732/531, loss: 0.7303277850151062
2023-01-21 08:28:30.361693: step: 736/531, loss: 1.5819597244262695
2023-01-21 08:28:31.492536: step: 740/531, loss: 1.2175713777542114
2023-01-21 08:28:32.600570: step: 744/531, loss: 1.3924689292907715
2023-01-21 08:28:33.715118: step: 748/531, loss: 1.6670432090759277
2023-01-21 08:28:34.867079: step: 752/531, loss: 1.1271965503692627
2023-01-21 08:28:36.024822: step: 756/531, loss: 1.7324247360229492
2023-01-21 08:28:37.140368: step: 760/531, loss: 0.45162907242774963
2023-01-21 08:28:38.262190: step: 764/531, loss: 0.48444193601608276
2023-01-21 08:28:39.372654: step: 768/531, loss: 0.560933530330658
2023-01-21 08:28:40.485805: step: 772/531, loss: 1.4928064346313477
2023-01-21 08:28:41.596788: step: 776/531, loss: 5.680951118469238
2023-01-21 08:28:42.727141: step: 780/531, loss: 1.7607084512710571
2023-01-21 08:28:43.868517: step: 784/531, loss: 0.48723241686820984
2023-01-21 08:28:44.994109: step: 788/531, loss: 0.18759968876838684
2023-01-21 08:28:46.115327: step: 792/531, loss: 0.9270867109298706
2023-01-21 08:28:47.243360: step: 796/531, loss: 0.6372804641723633
2023-01-21 08:28:48.435900: step: 800/531, loss: 5.777713298797607
2023-01-21 08:28:49.552580: step: 804/531, loss: 3.051236629486084
2023-01-21 08:28:50.704696: step: 808/531, loss: 0.5228690505027771
2023-01-21 08:28:51.869232: step: 812/531, loss: 1.185579538345337
2023-01-21 08:28:52.974361: step: 816/531, loss: 0.5009186267852783
2023-01-21 08:28:54.146480: step: 820/531, loss: 10.1963472366333
2023-01-21 08:28:55.298763: step: 824/531, loss: 0.5036492943763733
2023-01-21 08:28:56.432977: step: 828/531, loss: 2.3226099014282227
2023-01-21 08:28:57.564894: step: 832/531, loss: 1.3302218914031982
2023-01-21 08:28:58.694747: step: 836/531, loss: 1.4813424348831177
2023-01-21 08:28:59.811752: step: 840/531, loss: 0.4985276460647583
2023-01-21 08:29:00.921860: step: 844/531, loss: 1.1232692003250122
2023-01-21 08:29:02.049080: step: 848/531, loss: 0.8728890419006348
2023-01-21 08:29:03.160870: step: 852/531, loss: 1.6100800037384033
2023-01-21 08:29:04.289183: step: 856/531, loss: 1.1191056966781616
2023-01-21 08:29:05.443213: step: 860/531, loss: 3.284076690673828
2023-01-21 08:29:06.563523: step: 864/531, loss: 5.448684215545654
2023-01-21 08:29:07.659218: step: 868/531, loss: 1.9500758647918701
2023-01-21 08:29:08.797898: step: 872/531, loss: 6.734179973602295
2023-01-21 08:29:09.915446: step: 876/531, loss: 0.44377148151397705
2023-01-21 08:29:11.022552: step: 880/531, loss: 0.7405997514724731
2023-01-21 08:29:12.177849: step: 884/531, loss: 0.6487605571746826
2023-01-21 08:29:13.286687: step: 888/531, loss: 2.0299644470214844
2023-01-21 08:29:14.397508: step: 892/531, loss: 2.1412789821624756
2023-01-21 08:29:15.547455: step: 896/531, loss: 0.3870377242565155
2023-01-21 08:29:16.637263: step: 900/531, loss: 3.136416435241699
2023-01-21 08:29:17.761695: step: 904/531, loss: 2.141172170639038
2023-01-21 08:29:18.900500: step: 908/531, loss: 0.57072913646698
2023-01-21 08:29:20.021932: step: 912/531, loss: 0.44198426604270935
2023-01-21 08:29:21.183634: step: 916/531, loss: 0.3706693649291992
2023-01-21 08:29:22.296607: step: 920/531, loss: 0.3774597644805908
2023-01-21 08:29:23.423604: step: 924/531, loss: 0.8894097208976746
2023-01-21 08:29:24.568920: step: 928/531, loss: 2.654102325439453
2023-01-21 08:29:25.679660: step: 932/531, loss: 1.4737154245376587
2023-01-21 08:29:26.776770: step: 936/531, loss: 0.783511757850647
2023-01-21 08:29:27.899624: step: 940/531, loss: 1.106475830078125
2023-01-21 08:29:29.039205: step: 944/531, loss: 1.2096598148345947
2023-01-21 08:29:30.184421: step: 948/531, loss: 0.6061283349990845
2023-01-21 08:29:31.361849: step: 952/531, loss: 0.2911093831062317
2023-01-21 08:29:32.505584: step: 956/531, loss: 0.28803348541259766
2023-01-21 08:29:33.640296: step: 960/531, loss: 1.0073535442352295
2023-01-21 08:29:34.773077: step: 964/531, loss: 0.9820934534072876
2023-01-21 08:29:35.886847: step: 968/531, loss: 0.3536796271800995
2023-01-21 08:29:37.023246: step: 972/531, loss: 0.42519691586494446
2023-01-21 08:29:38.170997: step: 976/531, loss: 5.102304458618164
2023-01-21 08:29:39.277094: step: 980/531, loss: 0.22068482637405396
2023-01-21 08:29:40.400856: step: 984/531, loss: 0.769264817237854
2023-01-21 08:29:41.556776: step: 988/531, loss: 0.506183922290802
2023-01-21 08:29:42.709084: step: 992/531, loss: 0.9405239820480347
2023-01-21 08:29:43.829879: step: 996/531, loss: 0.47805076837539673
2023-01-21 08:29:44.994580: step: 1000/531, loss: 1.0347998142242432
2023-01-21 08:29:46.112622: step: 1004/531, loss: 0.9928960800170898
2023-01-21 08:29:47.266786: step: 1008/531, loss: 0.5030802488327026
2023-01-21 08:29:48.374699: step: 1012/531, loss: 2.2416796684265137
2023-01-21 08:29:49.505264: step: 1016/531, loss: 0.5580966472625732
2023-01-21 08:29:50.617093: step: 1020/531, loss: 1.8231711387634277
2023-01-21 08:29:51.756522: step: 1024/531, loss: 0.2565525770187378
2023-01-21 08:29:52.887558: step: 1028/531, loss: 1.5125222206115723
2023-01-21 08:29:53.988641: step: 1032/531, loss: 0.364323228597641
2023-01-21 08:29:55.122440: step: 1036/531, loss: 0.39796924591064453
2023-01-21 08:29:56.256752: step: 1040/531, loss: 1.5682728290557861
2023-01-21 08:29:57.365018: step: 1044/531, loss: 1.653188943862915
2023-01-21 08:29:58.493536: step: 1048/531, loss: 2.6216962337493896
2023-01-21 08:29:59.627078: step: 1052/531, loss: 1.4048326015472412
2023-01-21 08:30:00.777400: step: 1056/531, loss: 1.5759382247924805
2023-01-21 08:30:01.900610: step: 1060/531, loss: 0.6790085434913635
2023-01-21 08:30:03.033053: step: 1064/531, loss: 2.1952245235443115
2023-01-21 08:30:04.167825: step: 1068/531, loss: 0.8539444208145142
2023-01-21 08:30:05.311298: step: 1072/531, loss: 0.5027569532394409
2023-01-21 08:30:06.452051: step: 1076/531, loss: 2.809027671813965
2023-01-21 08:30:07.609428: step: 1080/531, loss: 1.761759638786316
2023-01-21 08:30:08.747579: step: 1084/531, loss: 0.3076581060886383
2023-01-21 08:30:09.873907: step: 1088/531, loss: 1.8024475574493408
2023-01-21 08:30:10.993889: step: 1092/531, loss: 0.9613577127456665
2023-01-21 08:30:12.133387: step: 1096/531, loss: 2.433546304702759
2023-01-21 08:30:13.256948: step: 1100/531, loss: 2.8840386867523193
2023-01-21 08:30:14.366803: step: 1104/531, loss: 1.305079698562622
2023-01-21 08:30:15.509029: step: 1108/531, loss: 0.709696352481842
2023-01-21 08:30:16.645201: step: 1112/531, loss: 0.37777137756347656
2023-01-21 08:30:17.758330: step: 1116/531, loss: 0.8038275241851807
2023-01-21 08:30:18.855020: step: 1120/531, loss: 0.39626961946487427
2023-01-21 08:30:19.991539: step: 1124/531, loss: 2.3624799251556396
2023-01-21 08:30:21.115568: step: 1128/531, loss: 0.3900138735771179
2023-01-21 08:30:22.237444: step: 1132/531, loss: 0.6979865431785583
2023-01-21 08:30:23.394115: step: 1136/531, loss: 0.6186054348945618
2023-01-21 08:30:24.506159: step: 1140/531, loss: 0.16052737832069397
2023-01-21 08:30:25.710776: step: 1144/531, loss: 0.8662946224212646
2023-01-21 08:30:26.853090: step: 1148/531, loss: 0.2455580234527588
2023-01-21 08:30:27.956412: step: 1152/531, loss: 1.0361310243606567
2023-01-21 08:30:29.069435: step: 1156/531, loss: 0.462401807308197
2023-01-21 08:30:30.228316: step: 1160/531, loss: 0.3532995283603668
2023-01-21 08:30:31.382710: step: 1164/531, loss: 1.959795594215393
2023-01-21 08:30:32.517412: step: 1168/531, loss: 1.5334808826446533
2023-01-21 08:30:33.651503: step: 1172/531, loss: 0.28836435079574585
2023-01-21 08:30:34.770085: step: 1176/531, loss: 1.1528983116149902
2023-01-21 08:30:35.915429: step: 1180/531, loss: 1.2682372331619263
2023-01-21 08:30:37.053610: step: 1184/531, loss: 0.26979345083236694
2023-01-21 08:30:38.188006: step: 1188/531, loss: 1.1078568696975708
2023-01-21 08:30:39.323119: step: 1192/531, loss: 0.6036314964294434
2023-01-21 08:30:40.462034: step: 1196/531, loss: 2.5460143089294434
2023-01-21 08:30:41.596927: step: 1200/531, loss: 3.628701686859131
2023-01-21 08:30:42.711668: step: 1204/531, loss: 1.763791799545288
2023-01-21 08:30:43.809937: step: 1208/531, loss: 0.4431189298629761
2023-01-21 08:30:44.940379: step: 1212/531, loss: 0.7327397465705872
2023-01-21 08:30:46.092576: step: 1216/531, loss: 0.4342723786830902
2023-01-21 08:30:47.208227: step: 1220/531, loss: 1.902055263519287
2023-01-21 08:30:48.313913: step: 1224/531, loss: 0.4548925459384918
2023-01-21 08:30:49.439059: step: 1228/531, loss: 0.9176959991455078
2023-01-21 08:30:50.570990: step: 1232/531, loss: 3.0312373638153076
2023-01-21 08:30:51.709027: step: 1236/531, loss: 1.475813388824463
2023-01-21 08:30:52.831415: step: 1240/531, loss: 0.528725266456604
2023-01-21 08:30:53.966917: step: 1244/531, loss: 0.40829718112945557
2023-01-21 08:30:55.097890: step: 1248/531, loss: 0.5420728921890259
2023-01-21 08:30:56.222836: step: 1252/531, loss: 0.2994222044944763
2023-01-21 08:30:57.369203: step: 1256/531, loss: 0.635415256023407
2023-01-21 08:30:58.506936: step: 1260/531, loss: 0.9323607087135315
2023-01-21 08:30:59.641449: step: 1264/531, loss: 2.6936163902282715
2023-01-21 08:31:00.769246: step: 1268/531, loss: 0.6204828023910522
2023-01-21 08:31:01.945248: step: 1272/531, loss: 0.5789872407913208
2023-01-21 08:31:03.072156: step: 1276/531, loss: 1.1375057697296143
2023-01-21 08:31:04.184305: step: 1280/531, loss: 1.0385173559188843
2023-01-21 08:31:05.311022: step: 1284/531, loss: 1.3682106733322144
2023-01-21 08:31:06.463658: step: 1288/531, loss: 4.037505626678467
2023-01-21 08:31:07.632988: step: 1292/531, loss: 0.6877168416976929
2023-01-21 08:31:08.775900: step: 1296/531, loss: 1.7743664979934692
2023-01-21 08:31:09.914042: step: 1300/531, loss: 3.430102825164795
2023-01-21 08:31:11.047589: step: 1304/531, loss: 1.777139663696289
2023-01-21 08:31:12.218654: step: 1308/531, loss: 0.3965368866920471
2023-01-21 08:31:13.341825: step: 1312/531, loss: 0.520017147064209
2023-01-21 08:31:14.448230: step: 1316/531, loss: 1.033474326133728
2023-01-21 08:31:15.555153: step: 1320/531, loss: 0.37674418091773987
2023-01-21 08:31:16.680834: step: 1324/531, loss: 0.8251477479934692
2023-01-21 08:31:17.807568: step: 1328/531, loss: 0.4165104925632477
2023-01-21 08:31:18.955088: step: 1332/531, loss: 2.0840795040130615
2023-01-21 08:31:20.052953: step: 1336/531, loss: 0.6134458780288696
2023-01-21 08:31:21.187733: step: 1340/531, loss: 0.235723078250885
2023-01-21 08:31:22.303620: step: 1344/531, loss: 0.41169464588165283
2023-01-21 08:31:23.435037: step: 1348/531, loss: 1.4164056777954102
2023-01-21 08:31:24.577318: step: 1352/531, loss: 7.537428379058838
2023-01-21 08:31:25.727825: step: 1356/531, loss: 3.568732261657715
2023-01-21 08:31:26.844180: step: 1360/531, loss: 1.5798994302749634
2023-01-21 08:31:28.001127: step: 1364/531, loss: 0.4049384593963623
2023-01-21 08:31:29.141609: step: 1368/531, loss: 1.1719298362731934
2023-01-21 08:31:30.279150: step: 1372/531, loss: 0.35880422592163086
2023-01-21 08:31:31.423313: step: 1376/531, loss: 2.994121789932251
2023-01-21 08:31:32.556091: step: 1380/531, loss: 0.9692338705062866
2023-01-21 08:31:33.691975: step: 1384/531, loss: 1.0469532012939453
2023-01-21 08:31:34.833333: step: 1388/531, loss: 0.704371452331543
2023-01-21 08:31:35.954800: step: 1392/531, loss: 1.5928230285644531
2023-01-21 08:31:37.079307: step: 1396/531, loss: 0.19797860085964203
2023-01-21 08:31:38.214438: step: 1400/531, loss: 1.1524953842163086
2023-01-21 08:31:39.373916: step: 1404/531, loss: 0.6012471318244934
2023-01-21 08:31:40.486995: step: 1408/531, loss: 2.3841757774353027
2023-01-21 08:31:41.626857: step: 1412/531, loss: 0.5171011090278625
2023-01-21 08:31:42.767094: step: 1416/531, loss: 0.5391451120376587
2023-01-21 08:31:43.894406: step: 1420/531, loss: 0.5451816916465759
2023-01-21 08:31:45.026338: step: 1424/531, loss: 0.27809175848960876
2023-01-21 08:31:46.146134: step: 1428/531, loss: 0.49407845735549927
2023-01-21 08:31:47.311710: step: 1432/531, loss: 0.13293522596359253
2023-01-21 08:31:48.479661: step: 1436/531, loss: 1.519361138343811
2023-01-21 08:31:49.593352: step: 1440/531, loss: 1.7191133499145508
2023-01-21 08:31:50.722855: step: 1444/531, loss: 0.5537688732147217
2023-01-21 08:31:51.821112: step: 1448/531, loss: 6.81881046295166
2023-01-21 08:31:52.984155: step: 1452/531, loss: 1.1535937786102295
2023-01-21 08:31:54.121849: step: 1456/531, loss: 0.5681639909744263
2023-01-21 08:31:55.247945: step: 1460/531, loss: 1.02992582321167
2023-01-21 08:31:56.367971: step: 1464/531, loss: 0.42583152651786804
2023-01-21 08:31:57.520111: step: 1468/531, loss: 0.5356565713882446
2023-01-21 08:31:58.653736: step: 1472/531, loss: 0.4080018997192383
2023-01-21 08:31:59.782749: step: 1476/531, loss: 0.22704468667507172
2023-01-21 08:32:00.931842: step: 1480/531, loss: 0.8032234907150269
2023-01-21 08:32:02.056405: step: 1484/531, loss: 0.4029533863067627
2023-01-21 08:32:03.168327: step: 1488/531, loss: 2.214237689971924
2023-01-21 08:32:04.296380: step: 1492/531, loss: 1.0937788486480713
2023-01-21 08:32:05.419110: step: 1496/531, loss: 0.18486443161964417
2023-01-21 08:32:06.593548: step: 1500/531, loss: 2.1671459674835205
2023-01-21 08:32:07.742499: step: 1504/531, loss: 0.37394145131111145
2023-01-21 08:32:08.840688: step: 1508/531, loss: 2.1639952659606934
2023-01-21 08:32:09.993974: step: 1512/531, loss: 7.445359230041504
2023-01-21 08:32:11.122966: step: 1516/531, loss: 0.6151976585388184
2023-01-21 08:32:12.261893: step: 1520/531, loss: 0.7307574152946472
2023-01-21 08:32:13.425803: step: 1524/531, loss: 0.5783308744430542
2023-01-21 08:32:14.538357: step: 1528/531, loss: 1.0292999744415283
2023-01-21 08:32:15.667970: step: 1532/531, loss: 0.2526084780693054
2023-01-21 08:32:16.774434: step: 1536/531, loss: 1.0480601787567139
2023-01-21 08:32:17.890598: step: 1540/531, loss: 2.3040876388549805
2023-01-21 08:32:19.032645: step: 1544/531, loss: 0.45953500270843506
2023-01-21 08:32:20.156699: step: 1548/531, loss: 0.726035475730896
2023-01-21 08:32:21.284897: step: 1552/531, loss: 0.7123405337333679
2023-01-21 08:32:22.414037: step: 1556/531, loss: 1.239498257637024
2023-01-21 08:32:23.525923: step: 1560/531, loss: 2.332115888595581
2023-01-21 08:32:24.619439: step: 1564/531, loss: 0.8626034259796143
2023-01-21 08:32:25.759490: step: 1568/531, loss: 0.7825387716293335
2023-01-21 08:32:26.894716: step: 1572/531, loss: 0.20002436637878418
2023-01-21 08:32:28.026007: step: 1576/531, loss: 1.0079257488250732
2023-01-21 08:32:29.130336: step: 1580/531, loss: 0.4445771276950836
2023-01-21 08:32:30.264960: step: 1584/531, loss: 1.4051389694213867
2023-01-21 08:32:31.373181: step: 1588/531, loss: 0.6725057363510132
2023-01-21 08:32:32.506335: step: 1592/531, loss: 0.9567013382911682
2023-01-21 08:32:33.667878: step: 1596/531, loss: 0.27645760774612427
2023-01-21 08:32:34.799498: step: 1600/531, loss: 1.4702401161193848
2023-01-21 08:32:35.920915: step: 1604/531, loss: 2.8450229167938232
2023-01-21 08:32:37.067943: step: 1608/531, loss: 0.1912183314561844
2023-01-21 08:32:38.221240: step: 1612/531, loss: 0.4139157235622406
2023-01-21 08:32:39.341508: step: 1616/531, loss: 1.4575409889221191
2023-01-21 08:32:40.467406: step: 1620/531, loss: 0.4374315142631531
2023-01-21 08:32:41.635870: step: 1624/531, loss: 0.40041646361351013
2023-01-21 08:32:42.781560: step: 1628/531, loss: 0.9358422160148621
2023-01-21 08:32:43.921777: step: 1632/531, loss: 0.2858022451400757
2023-01-21 08:32:45.087136: step: 1636/531, loss: 0.40463021397590637
2023-01-21 08:32:46.182553: step: 1640/531, loss: 0.27782222628593445
2023-01-21 08:32:47.297519: step: 1644/531, loss: 0.8261849284172058
2023-01-21 08:32:48.433848: step: 1648/531, loss: 0.2743852734565735
2023-01-21 08:32:49.520061: step: 1652/531, loss: 1.1915918588638306
2023-01-21 08:32:50.642906: step: 1656/531, loss: 6.563152313232422
2023-01-21 08:32:51.751972: step: 1660/531, loss: 0.2767614424228668
2023-01-21 08:32:52.909876: step: 1664/531, loss: 8.009928703308105
2023-01-21 08:32:54.014840: step: 1668/531, loss: 2.7408249378204346
2023-01-21 08:32:55.151532: step: 1672/531, loss: 1.823009967803955
2023-01-21 08:32:56.262368: step: 1676/531, loss: 1.3707501888275146
2023-01-21 08:32:57.402907: step: 1680/531, loss: 0.9346147775650024
2023-01-21 08:32:58.545267: step: 1684/531, loss: 3.644580841064453
2023-01-21 08:32:59.665801: step: 1688/531, loss: 1.5002988576889038
2023-01-21 08:33:00.778399: step: 1692/531, loss: 0.40758341550827026
2023-01-21 08:33:01.896112: step: 1696/531, loss: 0.26690512895584106
2023-01-21 08:33:03.033107: step: 1700/531, loss: 1.9627392292022705
2023-01-21 08:33:04.171939: step: 1704/531, loss: 4.548556804656982
2023-01-21 08:33:05.302321: step: 1708/531, loss: 1.4685009717941284
2023-01-21 08:33:06.394293: step: 1712/531, loss: 1.336835265159607
2023-01-21 08:33:07.520843: step: 1716/531, loss: 0.24930821359157562
2023-01-21 08:33:08.657269: step: 1720/531, loss: 6.974177837371826
2023-01-21 08:33:09.814783: step: 1724/531, loss: 1.5804717540740967
2023-01-21 08:33:10.934722: step: 1728/531, loss: 0.610162615776062
2023-01-21 08:33:12.098550: step: 1732/531, loss: 0.3148822784423828
2023-01-21 08:33:13.231138: step: 1736/531, loss: 2.1768674850463867
2023-01-21 08:33:14.365515: step: 1740/531, loss: 1.2555155754089355
2023-01-21 08:33:15.534524: step: 1744/531, loss: 1.2791881561279297
2023-01-21 08:33:16.653261: step: 1748/531, loss: 0.405431866645813
2023-01-21 08:33:17.798435: step: 1752/531, loss: 0.6121499538421631
2023-01-21 08:33:18.903182: step: 1756/531, loss: 0.8035522103309631
2023-01-21 08:33:20.034338: step: 1760/531, loss: 1.099301815032959
2023-01-21 08:33:21.168253: step: 1764/531, loss: 0.8523430824279785
2023-01-21 08:33:22.299479: step: 1768/531, loss: 0.9650673866271973
2023-01-21 08:33:23.426672: step: 1772/531, loss: 1.7846542596817017
2023-01-21 08:33:24.557921: step: 1776/531, loss: 2.0832650661468506
2023-01-21 08:33:25.711134: step: 1780/531, loss: 1.1523033380508423
2023-01-21 08:33:26.870217: step: 1784/531, loss: 1.3105982542037964
2023-01-21 08:33:27.992795: step: 1788/531, loss: 0.28089332580566406
2023-01-21 08:33:29.136043: step: 1792/531, loss: 1.5918664932250977
2023-01-21 08:33:30.297442: step: 1796/531, loss: 1.4153391122817993
2023-01-21 08:33:31.472611: step: 1800/531, loss: 0.6680206060409546
2023-01-21 08:33:32.592536: step: 1804/531, loss: 1.9647587537765503
2023-01-21 08:33:33.748762: step: 1808/531, loss: 1.0230886936187744
2023-01-21 08:33:34.877817: step: 1812/531, loss: 0.40220046043395996
2023-01-21 08:33:36.037487: step: 1816/531, loss: 0.39898940920829773
2023-01-21 08:33:37.202610: step: 1820/531, loss: 1.1538629531860352
2023-01-21 08:33:38.320413: step: 1824/531, loss: 0.9606660604476929
2023-01-21 08:33:39.460971: step: 1828/531, loss: 0.2896497845649719
2023-01-21 08:33:40.608974: step: 1832/531, loss: 1.2962169647216797
2023-01-21 08:33:41.758452: step: 1836/531, loss: 0.5317136645317078
2023-01-21 08:33:42.930813: step: 1840/531, loss: 0.5023956894874573
2023-01-21 08:33:44.065225: step: 1844/531, loss: 0.21467125415802002
2023-01-21 08:33:45.219976: step: 1848/531, loss: 0.6295309662818909
2023-01-21 08:33:46.324432: step: 1852/531, loss: 7.116159915924072
2023-01-21 08:33:47.491035: step: 1856/531, loss: 1.039978265762329
2023-01-21 08:33:48.633313: step: 1860/531, loss: 0.49906837940216064
2023-01-21 08:33:49.760802: step: 1864/531, loss: 1.0414111614227295
2023-01-21 08:33:50.860912: step: 1868/531, loss: 1.4617364406585693
2023-01-21 08:33:52.003307: step: 1872/531, loss: 0.45923924446105957
2023-01-21 08:33:53.109957: step: 1876/531, loss: 0.5880622863769531
2023-01-21 08:33:54.233186: step: 1880/531, loss: 7.1724138259887695
2023-01-21 08:33:55.389452: step: 1884/531, loss: 1.0949327945709229
2023-01-21 08:33:56.514894: step: 1888/531, loss: 0.2629883289337158
2023-01-21 08:33:57.642748: step: 1892/531, loss: 1.5492472648620605
2023-01-21 08:33:58.795486: step: 1896/531, loss: 2.168962240219116
2023-01-21 08:33:59.918834: step: 1900/531, loss: 2.447136402130127
2023-01-21 08:34:01.053456: step: 1904/531, loss: 2.9105565547943115
2023-01-21 08:34:02.206230: step: 1908/531, loss: 0.4838661253452301
2023-01-21 08:34:03.338667: step: 1912/531, loss: 0.5327164530754089
2023-01-21 08:34:04.464519: step: 1916/531, loss: 0.6271045207977295
2023-01-21 08:34:05.593565: step: 1920/531, loss: 0.342769056558609
2023-01-21 08:34:06.738522: step: 1924/531, loss: 0.44412603974342346
2023-01-21 08:34:07.865585: step: 1928/531, loss: 7.712641716003418
2023-01-21 08:34:08.997385: step: 1932/531, loss: 0.17210501432418823
2023-01-21 08:34:10.091587: step: 1936/531, loss: 0.29074543714523315
2023-01-21 08:34:11.216707: step: 1940/531, loss: 0.5579442977905273
2023-01-21 08:34:12.373419: step: 1944/531, loss: 2.413166046142578
2023-01-21 08:34:13.487068: step: 1948/531, loss: 0.15081782639026642
2023-01-21 08:34:14.603805: step: 1952/531, loss: 0.11447057873010635
2023-01-21 08:34:15.730867: step: 1956/531, loss: 0.36604928970336914
2023-01-21 08:34:16.882462: step: 1960/531, loss: 0.4121372103691101
2023-01-21 08:34:18.008987: step: 1964/531, loss: 1.1306660175323486
2023-01-21 08:34:19.106906: step: 1968/531, loss: 0.19114255905151367
2023-01-21 08:34:20.235317: step: 1972/531, loss: 1.115263819694519
2023-01-21 08:34:21.360053: step: 1976/531, loss: 0.40050989389419556
2023-01-21 08:34:22.481549: step: 1980/531, loss: 0.27480548620224
2023-01-21 08:34:23.599788: step: 1984/531, loss: 1.353050708770752
2023-01-21 08:34:24.700228: step: 1988/531, loss: 0.8090643882751465
2023-01-21 08:34:25.831146: step: 1992/531, loss: 0.9668687582015991
2023-01-21 08:34:26.946383: step: 1996/531, loss: 1.2375690937042236
2023-01-21 08:34:28.068583: step: 2000/531, loss: 0.811989426612854
2023-01-21 08:34:29.217699: step: 2004/531, loss: 0.3476330041885376
2023-01-21 08:34:30.349440: step: 2008/531, loss: 0.6789736747741699
2023-01-21 08:34:31.456351: step: 2012/531, loss: 0.9745103120803833
2023-01-21 08:34:32.609531: step: 2016/531, loss: 2.3204092979431152
2023-01-21 08:34:33.760118: step: 2020/531, loss: 0.7785778045654297
2023-01-21 08:34:34.898424: step: 2024/531, loss: 0.38837215304374695
2023-01-21 08:34:36.029019: step: 2028/531, loss: 0.6144498586654663
2023-01-21 08:34:37.157201: step: 2032/531, loss: 1.802272081375122
2023-01-21 08:34:38.267858: step: 2036/531, loss: 1.1621789932250977
2023-01-21 08:34:39.401909: step: 2040/531, loss: 18.040464401245117
2023-01-21 08:34:40.545097: step: 2044/531, loss: 0.8983226418495178
2023-01-21 08:34:41.704665: step: 2048/531, loss: 0.4278659522533417
2023-01-21 08:34:42.841527: step: 2052/531, loss: 0.33591580390930176
2023-01-21 08:34:43.952647: step: 2056/531, loss: 0.42114487290382385
2023-01-21 08:34:45.080404: step: 2060/531, loss: 0.6154437065124512
2023-01-21 08:34:46.185130: step: 2064/531, loss: 3.467343807220459
2023-01-21 08:34:47.292150: step: 2068/531, loss: 0.7770359516143799
2023-01-21 08:34:48.448046: step: 2072/531, loss: 0.46303659677505493
2023-01-21 08:34:49.556714: step: 2076/531, loss: 0.5598751902580261
2023-01-21 08:34:50.718346: step: 2080/531, loss: 0.7088748216629028
2023-01-21 08:34:51.835260: step: 2084/531, loss: 0.27088069915771484
2023-01-21 08:34:52.977786: step: 2088/531, loss: 0.6107016801834106
2023-01-21 08:34:54.124086: step: 2092/531, loss: 0.5451753735542297
2023-01-21 08:34:55.260532: step: 2096/531, loss: 0.4906690716743469
2023-01-21 08:34:56.374370: step: 2100/531, loss: 0.4330683648586273
2023-01-21 08:34:57.503698: step: 2104/531, loss: 0.5274524688720703
2023-01-21 08:34:58.634809: step: 2108/531, loss: 0.22472038865089417
2023-01-21 08:34:59.766040: step: 2112/531, loss: 0.37288033962249756
2023-01-21 08:35:00.882759: step: 2116/531, loss: 0.20569263398647308
2023-01-21 08:35:02.019828: step: 2120/531, loss: 0.17711704969406128
2023-01-21 08:35:03.186265: step: 2124/531, loss: 1.4963927268981934
==================================================
Loss: 3.639
--------------------
Dev: {'event': {'p': 0.5924170616113744, 'r': 0.4993342210386152, 'f1': 0.541907514450867}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.48865248226950353, 'r': 0.4108527131782946, 'f1': 0.44638807904114025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.37037037037037035, 'f1': 0.449438202247191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.9230769230769231, 'r': 0.19047619047619047, 'f1': 0.31578947368421056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.625, 'r': 0.1388888888888889, 'f1': 0.2272727272727273}, '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': 0.5924170616113744, 'r': 0.4993342210386152, 'f1': 0.541907514450867}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.48865248226950353, 'r': 0.4108527131782946, 'f1': 0.44638807904114025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.37037037037037035, 'f1': 0.449438202247191}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5924170616113744, 'r': 0.4993342210386152, 'f1': 0.541907514450867}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.48865248226950353, 'r': 0.4108527131782946, 'f1': 0.44638807904114025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.9230769230769231, 'r': 0.19047619047619047, 'f1': 0.31578947368421056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5924170616113744, 'r': 0.4993342210386152, 'f1': 0.541907514450867}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.48865248226950353, 'r': 0.4108527131782946, 'f1': 0.44638807904114025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.625, 'r': 0.1388888888888889, 'f1': 0.2272727272727273}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:36:03.280358: step: 4/531, loss: 1.4447047710418701
2023-01-21 08:36:04.416756: step: 8/531, loss: 1.7894995212554932
2023-01-21 08:36:05.554152: step: 12/531, loss: 1.1803804636001587
2023-01-21 08:36:06.669890: step: 16/531, loss: 0.3246711492538452
2023-01-21 08:36:07.814139: step: 20/531, loss: 1.0602116584777832
2023-01-21 08:36:08.920941: step: 24/531, loss: 0.4928525984287262
2023-01-21 08:36:10.101233: step: 28/531, loss: 0.7069123387336731
2023-01-21 08:36:11.250171: step: 32/531, loss: 0.26230937242507935
2023-01-21 08:36:12.404477: step: 36/531, loss: 0.3809455931186676
2023-01-21 08:36:13.539516: step: 40/531, loss: 1.4203050136566162
2023-01-21 08:36:14.687165: step: 44/531, loss: 0.2373761683702469
2023-01-21 08:36:15.800359: step: 48/531, loss: 0.3367355465888977
2023-01-21 08:36:16.926123: step: 52/531, loss: 0.3164003789424896
2023-01-21 08:36:18.040724: step: 56/531, loss: 0.2195574790239334
2023-01-21 08:36:19.182207: step: 60/531, loss: 0.18575087189674377
2023-01-21 08:36:20.325921: step: 64/531, loss: 0.489385724067688
2023-01-21 08:36:21.460026: step: 68/531, loss: 0.2584063410758972
2023-01-21 08:36:22.593213: step: 72/531, loss: 0.6360254287719727
2023-01-21 08:36:23.744895: step: 76/531, loss: 1.2348854541778564
2023-01-21 08:36:24.835124: step: 80/531, loss: 0.6211497187614441
2023-01-21 08:36:25.987718: step: 84/531, loss: 0.9589474201202393
2023-01-21 08:36:27.110183: step: 88/531, loss: 1.0409431457519531
2023-01-21 08:36:28.230239: step: 92/531, loss: 0.9349552392959595
2023-01-21 08:36:29.362622: step: 96/531, loss: 0.49208372831344604
2023-01-21 08:36:30.464177: step: 100/531, loss: 1.3125523328781128
2023-01-21 08:36:31.616169: step: 104/531, loss: 0.2161637395620346
2023-01-21 08:36:32.744216: step: 108/531, loss: 0.4276527762413025
2023-01-21 08:36:33.888718: step: 112/531, loss: 0.3313613533973694
2023-01-21 08:36:34.990461: step: 116/531, loss: 0.6031900644302368
2023-01-21 08:36:36.100281: step: 120/531, loss: 0.3204917907714844
2023-01-21 08:36:37.238540: step: 124/531, loss: 0.20592385530471802
2023-01-21 08:36:38.360625: step: 128/531, loss: 0.4562414288520813
2023-01-21 08:36:39.501360: step: 132/531, loss: 4.408691883087158
2023-01-21 08:36:40.628538: step: 136/531, loss: 0.3817763328552246
2023-01-21 08:36:41.784496: step: 140/531, loss: 0.5173056721687317
2023-01-21 08:36:42.925924: step: 144/531, loss: 1.3479859828948975
2023-01-21 08:36:44.050744: step: 148/531, loss: 1.0278340578079224
2023-01-21 08:36:45.154751: step: 152/531, loss: 0.10811326652765274
2023-01-21 08:36:46.270114: step: 156/531, loss: 0.43464717268943787
2023-01-21 08:36:47.381692: step: 160/531, loss: 0.7763004302978516
2023-01-21 08:36:48.498806: step: 164/531, loss: 0.2981727123260498
2023-01-21 08:36:49.628567: step: 168/531, loss: 1.2074049711227417
2023-01-21 08:36:50.737713: step: 172/531, loss: 1.7091926336288452
2023-01-21 08:36:51.833283: step: 176/531, loss: 0.40574541687965393
2023-01-21 08:36:52.937403: step: 180/531, loss: 0.2928807735443115
2023-01-21 08:36:54.066194: step: 184/531, loss: 1.7569458484649658
2023-01-21 08:36:55.177206: step: 188/531, loss: 0.2622080445289612
2023-01-21 08:36:56.348126: step: 192/531, loss: 0.32386958599090576
2023-01-21 08:36:57.454502: step: 196/531, loss: 0.36866387724876404
2023-01-21 08:36:58.610817: step: 200/531, loss: 2.2625324726104736
2023-01-21 08:36:59.758859: step: 204/531, loss: 1.0625203847885132
2023-01-21 08:37:00.891659: step: 208/531, loss: 0.29278287291526794
2023-01-21 08:37:02.025208: step: 212/531, loss: 0.8662877082824707
2023-01-21 08:37:03.174433: step: 216/531, loss: 0.6360157132148743
2023-01-21 08:37:04.288861: step: 220/531, loss: 1.511866807937622
2023-01-21 08:37:05.426845: step: 224/531, loss: 1.0980476140975952
2023-01-21 08:37:06.558541: step: 228/531, loss: 1.4812939167022705
2023-01-21 08:37:07.692891: step: 232/531, loss: 0.6922441720962524
2023-01-21 08:37:08.821695: step: 236/531, loss: 0.9902564883232117
2023-01-21 08:37:09.932716: step: 240/531, loss: 0.177326962351799
2023-01-21 08:37:11.073757: step: 244/531, loss: 0.20777606964111328
2023-01-21 08:37:12.203045: step: 248/531, loss: 1.7635724544525146
2023-01-21 08:37:13.328937: step: 252/531, loss: 0.11808653175830841
2023-01-21 08:37:14.455148: step: 256/531, loss: 0.3749334514141083
2023-01-21 08:37:15.627512: step: 260/531, loss: 1.1772258281707764
2023-01-21 08:37:16.747481: step: 264/531, loss: 0.7569869756698608
2023-01-21 08:37:17.875796: step: 268/531, loss: 0.5492221117019653
2023-01-21 08:37:19.007395: step: 272/531, loss: 0.6368181109428406
2023-01-21 08:37:20.128907: step: 276/531, loss: 0.6319532990455627
2023-01-21 08:37:21.267515: step: 280/531, loss: 1.2981876134872437
2023-01-21 08:37:22.372569: step: 284/531, loss: 0.15669222176074982
2023-01-21 08:37:23.518619: step: 288/531, loss: 0.6646470427513123
2023-01-21 08:37:24.627573: step: 292/531, loss: 0.369415283203125
2023-01-21 08:37:25.741030: step: 296/531, loss: 0.5761706233024597
2023-01-21 08:37:26.870347: step: 300/531, loss: 0.10725517570972443
2023-01-21 08:37:28.016171: step: 304/531, loss: 0.2761271595954895
2023-01-21 08:37:29.145248: step: 308/531, loss: 0.17902125418186188
2023-01-21 08:37:30.308477: step: 312/531, loss: 0.642677903175354
2023-01-21 08:37:31.427259: step: 316/531, loss: 0.32330718636512756
2023-01-21 08:37:32.963502: step: 320/531, loss: 0.31008490920066833
2023-01-21 08:37:34.097659: step: 324/531, loss: 0.1907430738210678
2023-01-21 08:37:35.225521: step: 328/531, loss: 0.41660165786743164
2023-01-21 08:37:36.337405: step: 332/531, loss: 0.20495377480983734
2023-01-21 08:37:37.480466: step: 336/531, loss: 0.34137028455734253
2023-01-21 08:37:38.620830: step: 340/531, loss: 0.5798617601394653
2023-01-21 08:37:39.746678: step: 344/531, loss: 0.37318092584609985
2023-01-21 08:37:40.883151: step: 348/531, loss: 0.21679158508777618
2023-01-21 08:37:41.984496: step: 352/531, loss: 0.5242207050323486
2023-01-21 08:37:43.107205: step: 356/531, loss: 0.2511359453201294
2023-01-21 08:37:44.258815: step: 360/531, loss: 1.7452383041381836
2023-01-21 08:37:45.369349: step: 364/531, loss: 0.5586540102958679
2023-01-21 08:37:46.493241: step: 368/531, loss: 0.34089863300323486
2023-01-21 08:37:47.617550: step: 372/531, loss: 0.2661881446838379
2023-01-21 08:37:48.763845: step: 376/531, loss: 1.7807663679122925
2023-01-21 08:37:49.922610: step: 380/531, loss: 2.899529457092285
2023-01-21 08:37:51.076454: step: 384/531, loss: 0.3713320791721344
2023-01-21 08:37:52.203629: step: 388/531, loss: 0.35799217224121094
2023-01-21 08:37:53.345287: step: 392/531, loss: 0.5195703506469727
2023-01-21 08:37:54.489303: step: 396/531, loss: 0.8480582237243652
2023-01-21 08:37:55.655264: step: 400/531, loss: 0.4078831374645233
2023-01-21 08:37:56.848040: step: 404/531, loss: 0.15243983268737793
2023-01-21 08:37:57.955025: step: 408/531, loss: 0.17399731278419495
2023-01-21 08:37:59.067142: step: 412/531, loss: 0.6364738345146179
2023-01-21 08:38:00.204253: step: 416/531, loss: 2.5777413845062256
2023-01-21 08:38:01.339420: step: 420/531, loss: 0.7492295503616333
2023-01-21 08:38:02.463527: step: 424/531, loss: 0.17711439728736877
2023-01-21 08:38:03.587412: step: 428/531, loss: 1.0871543884277344
2023-01-21 08:38:04.720172: step: 432/531, loss: 0.2248401641845703
2023-01-21 08:38:05.869473: step: 436/531, loss: 1.3650846481323242
2023-01-21 08:38:06.996687: step: 440/531, loss: 0.9823659658432007
2023-01-21 08:38:08.133421: step: 444/531, loss: 1.0744810104370117
2023-01-21 08:38:09.267858: step: 448/531, loss: 1.3013124465942383
2023-01-21 08:38:10.415475: step: 452/531, loss: 0.5785605311393738
2023-01-21 08:38:11.523749: step: 456/531, loss: 1.6107933521270752
2023-01-21 08:38:12.641381: step: 460/531, loss: 0.29660820960998535
2023-01-21 08:38:13.765224: step: 464/531, loss: 0.359740674495697
2023-01-21 08:38:14.879410: step: 468/531, loss: 0.11545324325561523
2023-01-21 08:38:16.008894: step: 472/531, loss: 0.24031469225883484
2023-01-21 08:38:17.107720: step: 476/531, loss: 0.6878279447555542
2023-01-21 08:38:18.222725: step: 480/531, loss: 1.9192399978637695
2023-01-21 08:38:19.365972: step: 484/531, loss: 0.7948795557022095
2023-01-21 08:38:20.481370: step: 488/531, loss: 1.035010814666748
2023-01-21 08:38:21.626985: step: 492/531, loss: 0.09685955196619034
2023-01-21 08:38:22.749426: step: 496/531, loss: 1.7673611640930176
2023-01-21 08:38:23.858168: step: 500/531, loss: 0.17317765951156616
2023-01-21 08:38:24.985865: step: 504/531, loss: 0.7733259797096252
2023-01-21 08:38:26.127258: step: 508/531, loss: 0.7451426982879639
2023-01-21 08:38:27.290128: step: 512/531, loss: 0.44408389925956726
2023-01-21 08:38:28.402432: step: 516/531, loss: 1.8669283390045166
2023-01-21 08:38:29.514510: step: 520/531, loss: 0.2147599756717682
2023-01-21 08:38:30.650965: step: 524/531, loss: 0.16766032576560974
2023-01-21 08:38:31.758586: step: 528/531, loss: 6.4270243644714355
2023-01-21 08:38:32.869523: step: 532/531, loss: 1.178396463394165
2023-01-21 08:38:34.001902: step: 536/531, loss: 1.7416846752166748
2023-01-21 08:38:35.127681: step: 540/531, loss: 1.717814326286316
2023-01-21 08:38:36.260434: step: 544/531, loss: 0.942686915397644
2023-01-21 08:38:37.404433: step: 548/531, loss: 1.3419599533081055
2023-01-21 08:38:38.518145: step: 552/531, loss: 0.16580715775489807
2023-01-21 08:38:39.647779: step: 556/531, loss: 0.14894671738147736
2023-01-21 08:38:40.777459: step: 560/531, loss: 0.12128090858459473
2023-01-21 08:38:41.934753: step: 564/531, loss: 0.9024069309234619
2023-01-21 08:38:43.075878: step: 568/531, loss: 0.264594167470932
2023-01-21 08:38:44.170352: step: 572/531, loss: 0.32906651496887207
2023-01-21 08:38:45.294254: step: 576/531, loss: 0.3746604025363922
2023-01-21 08:38:46.407795: step: 580/531, loss: 1.7179760932922363
2023-01-21 08:38:47.536573: step: 584/531, loss: 0.21175822615623474
2023-01-21 08:38:48.656808: step: 588/531, loss: 0.1195782870054245
2023-01-21 08:38:49.781935: step: 592/531, loss: 0.23276109993457794
2023-01-21 08:38:50.899815: step: 596/531, loss: 7.56704568862915
2023-01-21 08:38:52.022496: step: 600/531, loss: 0.6738176345825195
2023-01-21 08:38:53.154706: step: 604/531, loss: 0.5174084305763245
2023-01-21 08:38:54.278319: step: 608/531, loss: 0.24270924925804138
2023-01-21 08:38:55.420300: step: 612/531, loss: 1.7047746181488037
2023-01-21 08:38:56.536067: step: 616/531, loss: 0.8631380200386047
2023-01-21 08:38:57.667036: step: 620/531, loss: 0.09635944664478302
2023-01-21 08:38:58.800381: step: 624/531, loss: 0.8997295498847961
2023-01-21 08:38:59.926151: step: 628/531, loss: 0.23431158065795898
2023-01-21 08:39:01.056918: step: 632/531, loss: 0.4684382677078247
2023-01-21 08:39:02.160941: step: 636/531, loss: 0.24691133201122284
2023-01-21 08:39:03.310982: step: 640/531, loss: 0.5310478806495667
2023-01-21 08:39:04.412457: step: 644/531, loss: 0.34976208209991455
2023-01-21 08:39:05.518823: step: 648/531, loss: 0.566770076751709
2023-01-21 08:39:06.664368: step: 652/531, loss: 1.7421294450759888
2023-01-21 08:39:07.783571: step: 656/531, loss: 0.28855934739112854
2023-01-21 08:39:08.895569: step: 660/531, loss: 1.6107193231582642
2023-01-21 08:39:10.023181: step: 664/531, loss: 0.1847524642944336
2023-01-21 08:39:11.160977: step: 668/531, loss: 3.687346935272217
2023-01-21 08:39:12.294743: step: 672/531, loss: 1.1015892028808594
2023-01-21 08:39:13.391555: step: 676/531, loss: 0.37416964769363403
2023-01-21 08:39:14.524211: step: 680/531, loss: 0.2634064555168152
2023-01-21 08:39:15.670248: step: 684/531, loss: 0.8191621899604797
2023-01-21 08:39:16.793009: step: 688/531, loss: 1.3657824993133545
2023-01-21 08:39:17.907989: step: 692/531, loss: 0.16610869765281677
2023-01-21 08:39:19.071890: step: 696/531, loss: 0.2113826870918274
2023-01-21 08:39:20.199631: step: 700/531, loss: 0.9884800314903259
2023-01-21 08:39:21.318274: step: 704/531, loss: 1.5296320915222168
2023-01-21 08:39:22.448426: step: 708/531, loss: 0.5116531252861023
2023-01-21 08:39:23.560956: step: 712/531, loss: 1.908612608909607
2023-01-21 08:39:24.704654: step: 716/531, loss: 0.945914626121521
2023-01-21 08:39:25.872551: step: 720/531, loss: 0.44992390275001526
2023-01-21 08:39:27.004932: step: 724/531, loss: 0.41654056310653687
2023-01-21 08:39:28.130779: step: 728/531, loss: 1.8458174467086792
2023-01-21 08:39:29.253218: step: 732/531, loss: 0.9704311490058899
2023-01-21 08:39:30.380411: step: 736/531, loss: 1.451930046081543
2023-01-21 08:39:31.526821: step: 740/531, loss: 0.772199273109436
2023-01-21 08:39:32.643369: step: 744/531, loss: 6.651556491851807
2023-01-21 08:39:33.756406: step: 748/531, loss: 0.6743013858795166
2023-01-21 08:39:34.878668: step: 752/531, loss: 1.1714826822280884
2023-01-21 08:39:36.031147: step: 756/531, loss: 0.17997589707374573
2023-01-21 08:39:37.124598: step: 760/531, loss: 0.240447536110878
2023-01-21 08:39:38.252031: step: 764/531, loss: 0.18628492951393127
2023-01-21 08:39:39.397401: step: 768/531, loss: 1.2768070697784424
2023-01-21 08:39:40.553382: step: 772/531, loss: 0.9290516376495361
2023-01-21 08:39:41.673371: step: 776/531, loss: 1.3223081827163696
2023-01-21 08:39:42.804713: step: 780/531, loss: 1.5617501735687256
2023-01-21 08:39:43.927022: step: 784/531, loss: 6.992527484893799
2023-01-21 08:39:45.041004: step: 788/531, loss: 1.130629062652588
2023-01-21 08:39:46.160291: step: 792/531, loss: 0.7078399658203125
2023-01-21 08:39:47.265382: step: 796/531, loss: 0.23568393290042877
2023-01-21 08:39:48.366542: step: 800/531, loss: 0.41420382261276245
2023-01-21 08:39:49.479209: step: 804/531, loss: 0.2370687574148178
2023-01-21 08:39:50.618370: step: 808/531, loss: 0.24226799607276917
2023-01-21 08:39:51.742431: step: 812/531, loss: 1.7401185035705566
2023-01-21 08:39:52.875208: step: 816/531, loss: 0.4222102165222168
2023-01-21 08:39:53.991834: step: 820/531, loss: 1.0131925344467163
2023-01-21 08:39:55.107573: step: 824/531, loss: 0.4274725914001465
2023-01-21 08:39:56.220239: step: 828/531, loss: 1.739496111869812
2023-01-21 08:39:57.346551: step: 832/531, loss: 0.4572395384311676
2023-01-21 08:39:58.506439: step: 836/531, loss: 0.2601722776889801
2023-01-21 08:39:59.619646: step: 840/531, loss: 1.272942066192627
2023-01-21 08:40:00.751507: step: 844/531, loss: 0.3978622853755951
2023-01-21 08:40:01.889910: step: 848/531, loss: 0.2559117376804352
2023-01-21 08:40:03.023349: step: 852/531, loss: 0.11607237160205841
2023-01-21 08:40:04.183735: step: 856/531, loss: 6.901358604431152
2023-01-21 08:40:05.320670: step: 860/531, loss: 0.14067640900611877
2023-01-21 08:40:06.454226: step: 864/531, loss: 0.23895572125911713
2023-01-21 08:40:07.597153: step: 868/531, loss: 0.5042967796325684
2023-01-21 08:40:08.711889: step: 872/531, loss: 0.29004794359207153
2023-01-21 08:40:09.817705: step: 876/531, loss: 0.13914261758327484
2023-01-21 08:40:10.960798: step: 880/531, loss: 0.8387675881385803
2023-01-21 08:40:12.115222: step: 884/531, loss: 0.23050576448440552
2023-01-21 08:40:13.250158: step: 888/531, loss: 1.108525037765503
2023-01-21 08:40:14.381823: step: 892/531, loss: 0.5829653143882751
2023-01-21 08:40:15.527733: step: 896/531, loss: 0.650887668132782
2023-01-21 08:40:16.649063: step: 900/531, loss: 0.7675807476043701
2023-01-21 08:40:17.764764: step: 904/531, loss: 0.19485878944396973
2023-01-21 08:40:18.892756: step: 908/531, loss: 0.16979295015335083
2023-01-21 08:40:20.024065: step: 912/531, loss: 1.896610975265503
2023-01-21 08:40:21.140731: step: 916/531, loss: 0.7971558570861816
2023-01-21 08:40:22.259032: step: 920/531, loss: 1.45060396194458
2023-01-21 08:40:23.399272: step: 924/531, loss: 0.5280710458755493
2023-01-21 08:40:24.538279: step: 928/531, loss: 0.2047538310289383
2023-01-21 08:40:25.642880: step: 932/531, loss: 0.9925472140312195
2023-01-21 08:40:26.745637: step: 936/531, loss: 0.04657275974750519
2023-01-21 08:40:27.911470: step: 940/531, loss: 7.417726516723633
2023-01-21 08:40:29.032617: step: 944/531, loss: 2.8799166679382324
2023-01-21 08:40:30.161281: step: 948/531, loss: 0.5087589025497437
2023-01-21 08:40:31.271268: step: 952/531, loss: 1.0417362451553345
2023-01-21 08:40:32.401240: step: 956/531, loss: 0.17657442390918732
2023-01-21 08:40:33.567942: step: 960/531, loss: 0.413053423166275
2023-01-21 08:40:34.670476: step: 964/531, loss: 0.9740074276924133
2023-01-21 08:40:35.784037: step: 968/531, loss: 0.08871526271104813
2023-01-21 08:40:36.884830: step: 972/531, loss: 0.5364027619361877
2023-01-21 08:40:37.975414: step: 976/531, loss: 0.18806371092796326
2023-01-21 08:40:39.096777: step: 980/531, loss: 0.3420529365539551
2023-01-21 08:40:40.224099: step: 984/531, loss: 0.16767436265945435
2023-01-21 08:40:41.328983: step: 988/531, loss: 0.12904635071754456
2023-01-21 08:40:42.479504: step: 992/531, loss: 0.5927817821502686
2023-01-21 08:40:43.623689: step: 996/531, loss: 0.5910190343856812
2023-01-21 08:40:44.765237: step: 1000/531, loss: 0.239983469247818
2023-01-21 08:40:45.881326: step: 1004/531, loss: 1.172353744506836
2023-01-21 08:40:46.996258: step: 1008/531, loss: 0.2604988217353821
2023-01-21 08:40:48.108066: step: 1012/531, loss: 0.2758321762084961
2023-01-21 08:40:49.216269: step: 1016/531, loss: 1.3930798768997192
2023-01-21 08:40:50.349992: step: 1020/531, loss: 0.3904854953289032
2023-01-21 08:40:51.466801: step: 1024/531, loss: 1.5742791891098022
2023-01-21 08:40:52.612531: step: 1028/531, loss: 0.36612045764923096
2023-01-21 08:40:53.771683: step: 1032/531, loss: 0.46194028854370117
2023-01-21 08:40:54.890365: step: 1036/531, loss: 0.18834352493286133
2023-01-21 08:40:56.021418: step: 1040/531, loss: 0.24331551790237427
2023-01-21 08:40:57.141231: step: 1044/531, loss: 0.30071860551834106
2023-01-21 08:40:58.257795: step: 1048/531, loss: 0.1441446840763092
2023-01-21 08:40:59.353821: step: 1052/531, loss: 1.0711448192596436
2023-01-21 08:41:00.457965: step: 1056/531, loss: 0.5804270505905151
2023-01-21 08:41:01.556310: step: 1060/531, loss: 7.240081310272217
2023-01-21 08:41:02.685400: step: 1064/531, loss: 0.500418484210968
2023-01-21 08:41:03.818429: step: 1068/531, loss: 2.0883078575134277
2023-01-21 08:41:04.925448: step: 1072/531, loss: 0.23637351393699646
2023-01-21 08:41:06.028349: step: 1076/531, loss: 0.8518012762069702
2023-01-21 08:41:07.167712: step: 1080/531, loss: 0.24204093217849731
2023-01-21 08:41:08.289987: step: 1084/531, loss: 1.2486172914505005
2023-01-21 08:41:09.400787: step: 1088/531, loss: 0.16274595260620117
2023-01-21 08:41:10.529871: step: 1092/531, loss: 1.5050017833709717
2023-01-21 08:41:11.639910: step: 1096/531, loss: 0.9276976585388184
2023-01-21 08:41:12.766482: step: 1100/531, loss: 0.19396352767944336
2023-01-21 08:41:13.860447: step: 1104/531, loss: 0.21584434807300568
2023-01-21 08:41:14.995230: step: 1108/531, loss: 1.2082065343856812
2023-01-21 08:41:16.089907: step: 1112/531, loss: 0.2518351078033447
2023-01-21 08:41:17.196643: step: 1116/531, loss: 0.1923869550228119
2023-01-21 08:41:18.313570: step: 1120/531, loss: 0.26678207516670227
2023-01-21 08:41:19.427996: step: 1124/531, loss: 0.2565642297267914
2023-01-21 08:41:20.527167: step: 1128/531, loss: 0.5560347437858582
2023-01-21 08:41:21.632786: step: 1132/531, loss: 0.1654636412858963
2023-01-21 08:41:22.753856: step: 1136/531, loss: 1.2767598628997803
2023-01-21 08:41:23.882401: step: 1140/531, loss: 1.0399624109268188
2023-01-21 08:41:24.997041: step: 1144/531, loss: 0.0939173698425293
2023-01-21 08:41:26.108175: step: 1148/531, loss: 0.837897777557373
2023-01-21 08:41:27.181449: step: 1152/531, loss: 0.10107071697711945
2023-01-21 08:41:28.287142: step: 1156/531, loss: 0.24848470091819763
2023-01-21 08:41:29.390404: step: 1160/531, loss: 0.2140188217163086
2023-01-21 08:41:30.489716: step: 1164/531, loss: 0.6957235932350159
2023-01-21 08:41:31.620443: step: 1168/531, loss: 0.62116938829422
2023-01-21 08:41:32.728539: step: 1172/531, loss: 0.23200102150440216
2023-01-21 08:41:33.861794: step: 1176/531, loss: 0.23393641412258148
2023-01-21 08:41:34.964495: step: 1180/531, loss: 0.18609829246997833
2023-01-21 08:41:36.074385: step: 1184/531, loss: 0.7403040528297424
2023-01-21 08:41:37.180894: step: 1188/531, loss: 0.2572787404060364
2023-01-21 08:41:38.292644: step: 1192/531, loss: 1.2990471124649048
2023-01-21 08:41:39.423618: step: 1196/531, loss: 0.29179847240448
2023-01-21 08:41:40.523572: step: 1200/531, loss: 0.2972412109375
2023-01-21 08:41:41.632622: step: 1204/531, loss: 0.9895287752151489
2023-01-21 08:41:42.776529: step: 1208/531, loss: 0.13477206230163574
2023-01-21 08:41:43.931233: step: 1212/531, loss: 0.9927616119384766
2023-01-21 08:41:45.048908: step: 1216/531, loss: 0.2719815671443939
2023-01-21 08:41:46.172122: step: 1220/531, loss: 0.3135610520839691
2023-01-21 08:41:47.316431: step: 1224/531, loss: 1.4710155725479126
2023-01-21 08:41:48.457707: step: 1228/531, loss: 0.15041828155517578
2023-01-21 08:41:49.566062: step: 1232/531, loss: 0.7769324779510498
2023-01-21 08:41:50.730706: step: 1236/531, loss: 1.044642686843872
2023-01-21 08:41:51.870064: step: 1240/531, loss: 0.27401572465896606
2023-01-21 08:41:53.008116: step: 1244/531, loss: 0.3988594710826874
2023-01-21 08:41:54.171178: step: 1248/531, loss: 0.1301170289516449
2023-01-21 08:41:55.300976: step: 1252/531, loss: 0.4545459747314453
2023-01-21 08:41:56.393661: step: 1256/531, loss: 0.7234287858009338
2023-01-21 08:41:57.534451: step: 1260/531, loss: 1.6857560873031616
2023-01-21 08:41:58.671855: step: 1264/531, loss: 0.3886871337890625
2023-01-21 08:41:59.783804: step: 1268/531, loss: 1.5109837055206299
2023-01-21 08:42:00.885837: step: 1272/531, loss: 0.09156426787376404
2023-01-21 08:42:01.987885: step: 1276/531, loss: 0.169049471616745
2023-01-21 08:42:03.098804: step: 1280/531, loss: 0.8284401297569275
2023-01-21 08:42:04.225710: step: 1284/531, loss: 0.26794034242630005
2023-01-21 08:42:05.349529: step: 1288/531, loss: 0.3205471634864807
2023-01-21 08:42:06.514571: step: 1292/531, loss: 1.0547372102737427
2023-01-21 08:42:07.651208: step: 1296/531, loss: 0.4735472500324249
2023-01-21 08:42:08.782760: step: 1300/531, loss: 0.9224669337272644
2023-01-21 08:42:09.890793: step: 1304/531, loss: 0.2162257730960846
2023-01-21 08:42:11.013604: step: 1308/531, loss: 0.8526097536087036
2023-01-21 08:42:12.188095: step: 1312/531, loss: 0.805574893951416
2023-01-21 08:42:13.289199: step: 1316/531, loss: 0.20904913544654846
2023-01-21 08:42:14.459212: step: 1320/531, loss: 0.2312142252922058
2023-01-21 08:42:15.572475: step: 1324/531, loss: 1.9592543840408325
2023-01-21 08:42:16.650489: step: 1328/531, loss: 0.1831745207309723
2023-01-21 08:42:17.764368: step: 1332/531, loss: 0.9486944675445557
2023-01-21 08:42:18.894406: step: 1336/531, loss: 0.161957785487175
2023-01-21 08:42:19.996163: step: 1340/531, loss: 0.2659211754798889
2023-01-21 08:42:21.161738: step: 1344/531, loss: 0.8168730139732361
2023-01-21 08:42:22.298881: step: 1348/531, loss: 0.20484352111816406
2023-01-21 08:42:23.430911: step: 1352/531, loss: 2.036332845687866
2023-01-21 08:42:24.580827: step: 1356/531, loss: 1.3080036640167236
2023-01-21 08:42:25.681468: step: 1360/531, loss: 0.35485154390335083
2023-01-21 08:42:26.823332: step: 1364/531, loss: 0.2512446641921997
2023-01-21 08:42:27.925456: step: 1368/531, loss: 0.39393502473831177
2023-01-21 08:42:29.051207: step: 1372/531, loss: 0.8258788585662842
2023-01-21 08:42:30.178035: step: 1376/531, loss: 0.9475477337837219
2023-01-21 08:42:31.306830: step: 1380/531, loss: 0.5336613655090332
2023-01-21 08:42:32.406150: step: 1384/531, loss: 0.7308098077774048
2023-01-21 08:42:33.515068: step: 1388/531, loss: 0.4056418836116791
2023-01-21 08:42:34.643305: step: 1392/531, loss: 0.22033196687698364
2023-01-21 08:42:35.736607: step: 1396/531, loss: 0.7989135980606079
2023-01-21 08:42:36.886945: step: 1400/531, loss: 1.441643476486206
2023-01-21 08:42:38.002795: step: 1404/531, loss: 0.3538009524345398
2023-01-21 08:42:39.133796: step: 1408/531, loss: 1.0300137996673584
2023-01-21 08:42:40.251951: step: 1412/531, loss: 0.3359490633010864
2023-01-21 08:42:41.356520: step: 1416/531, loss: 0.17974421381950378
2023-01-21 08:42:42.473477: step: 1420/531, loss: 0.7635331749916077
2023-01-21 08:42:43.596583: step: 1424/531, loss: 2.332240104675293
2023-01-21 08:42:44.700806: step: 1428/531, loss: 1.2522529363632202
2023-01-21 08:42:45.858984: step: 1432/531, loss: 0.28223592042922974
2023-01-21 08:42:46.994797: step: 1436/531, loss: 0.2710130214691162
2023-01-21 08:42:48.109111: step: 1440/531, loss: 4.314457893371582
2023-01-21 08:42:49.243960: step: 1444/531, loss: 0.4161422848701477
2023-01-21 08:42:50.351526: step: 1448/531, loss: 0.7519227266311646
2023-01-21 08:42:51.496091: step: 1452/531, loss: 0.3558284640312195
2023-01-21 08:42:52.611352: step: 1456/531, loss: 1.498359203338623
2023-01-21 08:42:53.729470: step: 1460/531, loss: 0.6741830110549927
2023-01-21 08:42:54.871396: step: 1464/531, loss: 0.05815839767456055
2023-01-21 08:42:55.989857: step: 1468/531, loss: 0.20585794746875763
2023-01-21 08:42:57.102837: step: 1472/531, loss: 0.41033706068992615
2023-01-21 08:42:58.244742: step: 1476/531, loss: 1.3723766803741455
2023-01-21 08:42:59.389706: step: 1480/531, loss: 1.0911204814910889
2023-01-21 08:43:00.501330: step: 1484/531, loss: 0.49098461866378784
2023-01-21 08:43:01.625896: step: 1488/531, loss: 0.31540995836257935
2023-01-21 08:43:02.757051: step: 1492/531, loss: 0.1768076866865158
2023-01-21 08:43:03.893818: step: 1496/531, loss: 1.1858489513397217
2023-01-21 08:43:05.027676: step: 1500/531, loss: 0.8010136485099792
2023-01-21 08:43:06.165124: step: 1504/531, loss: 0.43002554774284363
2023-01-21 08:43:07.318189: step: 1508/531, loss: 0.13285726308822632
2023-01-21 08:43:08.440905: step: 1512/531, loss: 0.42237424850463867
2023-01-21 08:43:09.571228: step: 1516/531, loss: 0.17222046852111816
2023-01-21 08:43:10.676379: step: 1520/531, loss: 0.16028109192848206
2023-01-21 08:43:11.794362: step: 1524/531, loss: 0.35287314653396606
2023-01-21 08:43:12.908858: step: 1528/531, loss: 0.3377394378185272
2023-01-21 08:43:14.006610: step: 1532/531, loss: 0.6800830960273743
2023-01-21 08:43:15.143363: step: 1536/531, loss: 0.25599777698516846
2023-01-21 08:43:16.287004: step: 1540/531, loss: 0.2045327126979828
2023-01-21 08:43:17.406526: step: 1544/531, loss: 0.08804045617580414
2023-01-21 08:43:18.527985: step: 1548/531, loss: 0.8169205784797668
2023-01-21 08:43:19.655841: step: 1552/531, loss: 0.9265896081924438
2023-01-21 08:43:20.757220: step: 1556/531, loss: 0.2756344676017761
2023-01-21 08:43:21.871719: step: 1560/531, loss: 0.11664175987243652
2023-01-21 08:43:23.005045: step: 1564/531, loss: 0.4637576937675476
2023-01-21 08:43:24.177610: step: 1568/531, loss: 2.064606189727783
2023-01-21 08:43:25.283547: step: 1572/531, loss: 0.033939555287361145
2023-01-21 08:43:26.432322: step: 1576/531, loss: 0.9088577032089233
2023-01-21 08:43:27.544395: step: 1580/531, loss: 0.08482623100280762
2023-01-21 08:43:28.673242: step: 1584/531, loss: 0.13899503648281097
2023-01-21 08:43:29.820347: step: 1588/531, loss: 0.13772006332874298
2023-01-21 08:43:30.915957: step: 1592/531, loss: 1.553917407989502
2023-01-21 08:43:32.016764: step: 1596/531, loss: 0.4175397753715515
2023-01-21 08:43:33.142587: step: 1600/531, loss: 0.5677341222763062
2023-01-21 08:43:34.255254: step: 1604/531, loss: 0.11777696758508682
2023-01-21 08:43:35.379622: step: 1608/531, loss: 0.2342889904975891
2023-01-21 08:43:36.517980: step: 1612/531, loss: 0.18349990248680115
2023-01-21 08:43:37.644013: step: 1616/531, loss: 0.2129518687725067
2023-01-21 08:43:38.764890: step: 1620/531, loss: 0.1986038088798523
2023-01-21 08:43:39.895258: step: 1624/531, loss: 0.3257094621658325
2023-01-21 08:43:41.007562: step: 1628/531, loss: 0.6993228793144226
2023-01-21 08:43:42.128530: step: 1632/531, loss: 1.3127716779708862
2023-01-21 08:43:43.221782: step: 1636/531, loss: 0.11155405640602112
2023-01-21 08:43:44.332702: step: 1640/531, loss: 1.4729888439178467
2023-01-21 08:43:45.421363: step: 1644/531, loss: 0.0621953047811985
2023-01-21 08:43:46.535572: step: 1648/531, loss: 0.3179476857185364
2023-01-21 08:43:47.660615: step: 1652/531, loss: 7.031080722808838
2023-01-21 08:43:48.810031: step: 1656/531, loss: 7.330111503601074
2023-01-21 08:43:49.930453: step: 1660/531, loss: 0.4803520739078522
2023-01-21 08:43:51.054415: step: 1664/531, loss: 0.38560056686401367
2023-01-21 08:43:52.153547: step: 1668/531, loss: 0.24395470321178436
2023-01-21 08:43:53.296700: step: 1672/531, loss: 0.8088110685348511
2023-01-21 08:43:54.420749: step: 1676/531, loss: 0.2811763882637024
2023-01-21 08:43:55.519734: step: 1680/531, loss: 1.0032514333724976
2023-01-21 08:43:56.630254: step: 1684/531, loss: 0.21879087388515472
2023-01-21 08:43:57.768138: step: 1688/531, loss: 0.38532471656799316
2023-01-21 08:43:58.907374: step: 1692/531, loss: 0.17665715515613556
2023-01-21 08:44:00.017835: step: 1696/531, loss: 0.9016225934028625
2023-01-21 08:44:01.163533: step: 1700/531, loss: 0.5829874277114868
2023-01-21 08:44:02.274874: step: 1704/531, loss: 0.7834721803665161
2023-01-21 08:44:03.388998: step: 1708/531, loss: 0.23218432068824768
2023-01-21 08:44:04.508567: step: 1712/531, loss: 0.25406843423843384
2023-01-21 08:44:05.632244: step: 1716/531, loss: 0.9642157554626465
2023-01-21 08:44:06.773140: step: 1720/531, loss: 0.20871314406394958
2023-01-21 08:44:07.894977: step: 1724/531, loss: 0.17053963243961334
2023-01-21 08:44:09.026759: step: 1728/531, loss: 1.1743921041488647
2023-01-21 08:44:10.175318: step: 1732/531, loss: 0.23276901245117188
2023-01-21 08:44:11.271775: step: 1736/531, loss: 0.8446066379547119
2023-01-21 08:44:12.391398: step: 1740/531, loss: 1.8968336582183838
2023-01-21 08:44:13.517055: step: 1744/531, loss: 0.6809177398681641
2023-01-21 08:44:14.640339: step: 1748/531, loss: 0.40739890933036804
2023-01-21 08:44:15.782137: step: 1752/531, loss: 0.09254312515258789
2023-01-21 08:44:16.899014: step: 1756/531, loss: 0.22147217392921448
2023-01-21 08:44:18.027647: step: 1760/531, loss: 0.2090633362531662
2023-01-21 08:44:19.166667: step: 1764/531, loss: 0.20166674256324768
2023-01-21 08:44:20.292898: step: 1768/531, loss: 0.2949308753013611
2023-01-21 08:44:21.396988: step: 1772/531, loss: 0.3551998734474182
2023-01-21 08:44:22.548430: step: 1776/531, loss: 0.2173646092414856
2023-01-21 08:44:23.656605: step: 1780/531, loss: 0.25806522369384766
2023-01-21 08:44:24.773153: step: 1784/531, loss: 0.5489709973335266
2023-01-21 08:44:25.888753: step: 1788/531, loss: 0.2526020109653473
2023-01-21 08:44:27.011229: step: 1792/531, loss: 3.2206082344055176
2023-01-21 08:44:28.148088: step: 1796/531, loss: 0.8189810514450073
2023-01-21 08:44:29.259143: step: 1800/531, loss: 0.46924546360969543
2023-01-21 08:44:30.381627: step: 1804/531, loss: 0.8861564993858337
2023-01-21 08:44:31.488984: step: 1808/531, loss: 0.166741281747818
2023-01-21 08:44:32.595492: step: 1812/531, loss: 1.0572699308395386
2023-01-21 08:44:33.747788: step: 1816/531, loss: 1.3276479244232178
2023-01-21 08:44:34.898007: step: 1820/531, loss: 0.23045936226844788
2023-01-21 08:44:35.999125: step: 1824/531, loss: 0.4996519088745117
2023-01-21 08:44:37.118292: step: 1828/531, loss: 1.5433249473571777
2023-01-21 08:44:38.252817: step: 1832/531, loss: 0.3330448269844055
2023-01-21 08:44:39.355083: step: 1836/531, loss: 0.0652044266462326
2023-01-21 08:44:40.465032: step: 1840/531, loss: 0.28855496644973755
2023-01-21 08:44:41.579337: step: 1844/531, loss: 0.1495048999786377
2023-01-21 08:44:42.720046: step: 1848/531, loss: 0.6744166612625122
2023-01-21 08:44:43.861472: step: 1852/531, loss: 1.1349947452545166
2023-01-21 08:44:44.986619: step: 1856/531, loss: 0.6290029287338257
2023-01-21 08:44:46.137668: step: 1860/531, loss: 0.5774468183517456
2023-01-21 08:44:47.274047: step: 1864/531, loss: 2.1828465461730957
2023-01-21 08:44:48.434778: step: 1868/531, loss: 0.538384735584259
2023-01-21 08:44:49.549807: step: 1872/531, loss: 0.4154299795627594
2023-01-21 08:44:50.679371: step: 1876/531, loss: 2.072601795196533
2023-01-21 08:44:51.808793: step: 1880/531, loss: 0.21358928084373474
2023-01-21 08:44:52.947993: step: 1884/531, loss: 1.8182247877120972
2023-01-21 08:44:54.090400: step: 1888/531, loss: 0.28505173325538635
2023-01-21 08:44:55.206055: step: 1892/531, loss: 0.7993797063827515
2023-01-21 08:44:56.292177: step: 1896/531, loss: 1.0267996788024902
2023-01-21 08:44:57.421089: step: 1900/531, loss: 0.18323755264282227
2023-01-21 08:44:58.594068: step: 1904/531, loss: 0.7881519198417664
2023-01-21 08:44:59.729431: step: 1908/531, loss: 0.4433140754699707
2023-01-21 08:45:00.843345: step: 1912/531, loss: 0.20907936990261078
2023-01-21 08:45:01.960312: step: 1916/531, loss: 1.629726529121399
2023-01-21 08:45:03.078083: step: 1920/531, loss: 0.33906078338623047
2023-01-21 08:45:04.220004: step: 1924/531, loss: 1.1163712739944458
2023-01-21 08:45:05.351445: step: 1928/531, loss: 0.09826003015041351
2023-01-21 08:45:06.490279: step: 1932/531, loss: 0.7715063691139221
2023-01-21 08:45:07.602916: step: 1936/531, loss: 0.15876717865467072
2023-01-21 08:45:08.739330: step: 1940/531, loss: 0.42607760429382324
2023-01-21 08:45:09.874958: step: 1944/531, loss: 0.6965678930282593
2023-01-21 08:45:10.991764: step: 1948/531, loss: 0.09287256002426147
2023-01-21 08:45:12.120738: step: 1952/531, loss: 1.5991343259811401
2023-01-21 08:45:13.219541: step: 1956/531, loss: 0.19623929262161255
2023-01-21 08:45:14.309825: step: 1960/531, loss: 0.8158611059188843
2023-01-21 08:45:15.430953: step: 1964/531, loss: 2.6786370277404785
2023-01-21 08:45:16.550684: step: 1968/531, loss: 0.12565556168556213
2023-01-21 08:45:17.677539: step: 1972/531, loss: 0.04360482841730118
2023-01-21 08:45:18.828201: step: 1976/531, loss: 0.9402376413345337
2023-01-21 08:45:19.978742: step: 1980/531, loss: 0.6813391447067261
2023-01-21 08:45:21.117171: step: 1984/531, loss: 0.17815256118774414
2023-01-21 08:45:22.228264: step: 1988/531, loss: 0.5153025388717651
2023-01-21 08:45:23.327939: step: 1992/531, loss: 0.20263013243675232
2023-01-21 08:45:24.455081: step: 1996/531, loss: 0.6896774172782898
2023-01-21 08:45:25.584033: step: 2000/531, loss: 0.3980448246002197
2023-01-21 08:45:26.721510: step: 2004/531, loss: 0.48645612597465515
2023-01-21 08:45:27.822833: step: 2008/531, loss: 0.13880328834056854
2023-01-21 08:45:28.924890: step: 2012/531, loss: 2.4375839233398438
2023-01-21 08:45:30.039501: step: 2016/531, loss: 0.891746997833252
2023-01-21 08:45:31.160329: step: 2020/531, loss: 0.2686363160610199
2023-01-21 08:45:32.276481: step: 2024/531, loss: 0.9690882563591003
2023-01-21 08:45:33.385135: step: 2028/531, loss: 0.4365391731262207
2023-01-21 08:45:34.491783: step: 2032/531, loss: 0.11934394389390945
2023-01-21 08:45:35.636715: step: 2036/531, loss: 0.16340236365795135
2023-01-21 08:45:36.780813: step: 2040/531, loss: 1.2615885734558105
2023-01-21 08:45:37.930720: step: 2044/531, loss: 0.687390148639679
2023-01-21 08:45:39.040388: step: 2048/531, loss: 0.08409624546766281
2023-01-21 08:45:40.188291: step: 2052/531, loss: 0.32873356342315674
2023-01-21 08:45:41.288291: step: 2056/531, loss: 1.5646607875823975
2023-01-21 08:45:42.399259: step: 2060/531, loss: 0.8692156076431274
2023-01-21 08:45:43.527524: step: 2064/531, loss: 0.2723952531814575
2023-01-21 08:45:44.660845: step: 2068/531, loss: 0.6442745327949524
2023-01-21 08:45:45.754610: step: 2072/531, loss: 0.7862272262573242
2023-01-21 08:45:46.902702: step: 2076/531, loss: 1.035030484199524
2023-01-21 08:45:48.022958: step: 2080/531, loss: 0.6777375936508179
2023-01-21 08:45:49.187922: step: 2084/531, loss: 0.14923977851867676
2023-01-21 08:45:50.362136: step: 2088/531, loss: 0.9863994121551514
2023-01-21 08:45:51.472276: step: 2092/531, loss: 0.3320446014404297
2023-01-21 08:45:52.573772: step: 2096/531, loss: 0.39623701572418213
2023-01-21 08:45:53.686337: step: 2100/531, loss: 0.16563501954078674
2023-01-21 08:45:54.826141: step: 2104/531, loss: 0.21453677117824554
2023-01-21 08:45:55.963706: step: 2108/531, loss: 0.3409889340400696
2023-01-21 08:45:57.108245: step: 2112/531, loss: 1.567966103553772
2023-01-21 08:45:58.244898: step: 2116/531, loss: 0.8170315623283386
2023-01-21 08:45:59.341763: step: 2120/531, loss: 1.0186183452606201
2023-01-21 08:46:00.514466: step: 2124/531, loss: 0.23631054162979126
==================================================
Loss: 0.784
--------------------
Dev: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5806451612903226, 'r': 0.6666666666666666, 'f1': 0.6206896551724138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.8125, 'r': 0.4126984126984127, 'f1': 0.5473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5806451612903226, 'r': 0.6666666666666666, 'f1': 0.6206896551724138}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.8125, 'r': 0.4126984126984127, 'f1': 0.5473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:46:57.082269: step: 4/531, loss: 0.1804010421037674
2023-01-21 08:46:58.227566: step: 8/531, loss: 0.6254034042358398
2023-01-21 08:46:59.378458: step: 12/531, loss: 0.8860158920288086
2023-01-21 08:47:00.531551: step: 16/531, loss: 0.2502374053001404
2023-01-21 08:47:01.657790: step: 20/531, loss: 0.15954260528087616
2023-01-21 08:47:02.826131: step: 24/531, loss: 0.6917909383773804
2023-01-21 08:47:03.955958: step: 28/531, loss: 0.2389553189277649
2023-01-21 08:47:05.096087: step: 32/531, loss: 0.20649877190589905
2023-01-21 08:47:06.232941: step: 36/531, loss: 0.07758722454309464
2023-01-21 08:47:07.347610: step: 40/531, loss: 1.024478793144226
2023-01-21 08:47:08.479400: step: 44/531, loss: 0.41793936491012573
2023-01-21 08:47:09.621423: step: 48/531, loss: 0.23780226707458496
2023-01-21 08:47:10.735330: step: 52/531, loss: 0.06887403130531311
2023-01-21 08:47:11.873384: step: 56/531, loss: 0.15385523438453674
2023-01-21 08:47:13.002292: step: 60/531, loss: 0.50139981508255
2023-01-21 08:47:14.096239: step: 64/531, loss: 1.1274677515029907
2023-01-21 08:47:15.212873: step: 68/531, loss: 1.458704948425293
2023-01-21 08:47:16.332362: step: 72/531, loss: 0.9071649312973022
2023-01-21 08:47:17.466240: step: 76/531, loss: 0.20013427734375
2023-01-21 08:47:18.593198: step: 80/531, loss: 0.1279170960187912
2023-01-21 08:47:19.712016: step: 84/531, loss: 1.2136847972869873
2023-01-21 08:47:20.849821: step: 88/531, loss: 0.21601973474025726
2023-01-21 08:47:21.981933: step: 92/531, loss: 0.9196099638938904
2023-01-21 08:47:23.095793: step: 96/531, loss: 0.42274338006973267
2023-01-21 08:47:24.222916: step: 100/531, loss: 0.9508174657821655
2023-01-21 08:47:25.364481: step: 104/531, loss: 0.1686171591281891
2023-01-21 08:47:26.513659: step: 108/531, loss: 0.8195101022720337
2023-01-21 08:47:27.644760: step: 112/531, loss: 0.657781183719635
2023-01-21 08:47:28.771328: step: 116/531, loss: 0.19910478591918945
2023-01-21 08:47:29.955081: step: 120/531, loss: 0.27922117710113525
2023-01-21 08:47:31.068574: step: 124/531, loss: 0.038541603833436966
2023-01-21 08:47:32.204289: step: 128/531, loss: 0.08344163745641708
2023-01-21 08:47:33.316293: step: 132/531, loss: 0.1253976821899414
2023-01-21 08:47:34.442564: step: 136/531, loss: 0.0702425017952919
2023-01-21 08:47:35.548123: step: 140/531, loss: 0.32205361127853394
2023-01-21 08:47:36.660432: step: 144/531, loss: 0.2390725016593933
2023-01-21 08:47:37.785520: step: 148/531, loss: 0.17802448570728302
2023-01-21 08:47:38.930986: step: 152/531, loss: 0.29456859827041626
2023-01-21 08:47:40.036522: step: 156/531, loss: 0.7989634275436401
2023-01-21 08:47:41.186613: step: 160/531, loss: 0.16000080108642578
2023-01-21 08:47:42.346772: step: 164/531, loss: 0.08040676265954971
2023-01-21 08:47:43.447009: step: 168/531, loss: 0.08630891144275665
2023-01-21 08:47:44.592767: step: 172/531, loss: 0.17356902360916138
2023-01-21 08:47:45.727713: step: 176/531, loss: 0.532572865486145
2023-01-21 08:47:46.828816: step: 180/531, loss: 0.08776288479566574
2023-01-21 08:47:47.939038: step: 184/531, loss: 0.8369118571281433
2023-01-21 08:47:49.061893: step: 188/531, loss: 0.8102593421936035
2023-01-21 08:47:50.193518: step: 192/531, loss: 0.08340568840503693
2023-01-21 08:47:51.322467: step: 196/531, loss: 0.32099205255508423
2023-01-21 08:47:52.487986: step: 200/531, loss: 0.2582084536552429
2023-01-21 08:47:53.617354: step: 204/531, loss: 0.8237835764884949
2023-01-21 08:47:54.728265: step: 208/531, loss: 0.36807554960250854
2023-01-21 08:47:55.869235: step: 212/531, loss: 1.1978293657302856
2023-01-21 08:47:56.991145: step: 216/531, loss: 0.20412281155586243
2023-01-21 08:47:58.143956: step: 220/531, loss: 2.2512669563293457
2023-01-21 08:47:59.248130: step: 224/531, loss: 1.0043058395385742
2023-01-21 08:48:00.350934: step: 228/531, loss: 1.3984246253967285
2023-01-21 08:48:01.479369: step: 232/531, loss: 0.10905656963586807
2023-01-21 08:48:02.615478: step: 236/531, loss: 1.242911696434021
2023-01-21 08:48:03.711014: step: 240/531, loss: 0.269389808177948
2023-01-21 08:48:04.841040: step: 244/531, loss: 0.7974693179130554
2023-01-21 08:48:05.977122: step: 248/531, loss: 0.1078215166926384
2023-01-21 08:48:07.096560: step: 252/531, loss: 0.06884270161390305
2023-01-21 08:48:08.244597: step: 256/531, loss: 0.21344806253910065
2023-01-21 08:48:09.380707: step: 260/531, loss: 0.404558390378952
2023-01-21 08:48:10.485468: step: 264/531, loss: 0.0639638900756836
2023-01-21 08:48:11.626123: step: 268/531, loss: 0.10782432556152344
2023-01-21 08:48:12.781379: step: 272/531, loss: 0.2297256588935852
2023-01-21 08:48:13.888411: step: 276/531, loss: 0.5807439088821411
2023-01-21 08:48:15.005630: step: 280/531, loss: 0.14174138009548187
2023-01-21 08:48:16.114549: step: 284/531, loss: 0.17653116583824158
2023-01-21 08:48:17.239994: step: 288/531, loss: 0.2736678719520569
2023-01-21 08:48:18.372265: step: 292/531, loss: 6.68790864944458
2023-01-21 08:48:19.483420: step: 296/531, loss: 0.3079667091369629
2023-01-21 08:48:20.587622: step: 300/531, loss: 0.12260589748620987
2023-01-21 08:48:21.723635: step: 304/531, loss: 0.18704338371753693
2023-01-21 08:48:22.849415: step: 308/531, loss: 0.13155046105384827
2023-01-21 08:48:23.978241: step: 312/531, loss: 0.600986123085022
2023-01-21 08:48:25.079829: step: 316/531, loss: 0.4282132685184479
2023-01-21 08:48:26.220430: step: 320/531, loss: 0.3611065149307251
2023-01-21 08:48:27.329613: step: 324/531, loss: 0.09567099064588547
2023-01-21 08:48:28.432775: step: 328/531, loss: 0.7234969735145569
2023-01-21 08:48:29.541144: step: 332/531, loss: 0.4623526632785797
2023-01-21 08:48:30.689546: step: 336/531, loss: 0.06090545654296875
2023-01-21 08:48:31.806900: step: 340/531, loss: 0.5487068891525269
2023-01-21 08:48:32.924892: step: 344/531, loss: 0.14757975935935974
2023-01-21 08:48:34.025324: step: 348/531, loss: 0.012281417846679688
2023-01-21 08:48:35.166060: step: 352/531, loss: 0.0668662041425705
2023-01-21 08:48:36.287070: step: 356/531, loss: 0.14945173263549805
2023-01-21 08:48:37.404929: step: 360/531, loss: 0.2041628062725067
2023-01-21 08:48:38.540642: step: 364/531, loss: 0.23457203805446625
2023-01-21 08:48:39.652460: step: 368/531, loss: 0.10594773292541504
2023-01-21 08:48:40.783152: step: 372/531, loss: 0.9441040754318237
2023-01-21 08:48:41.942774: step: 376/531, loss: 0.08234281092882156
2023-01-21 08:48:43.078389: step: 380/531, loss: 0.10490860790014267
2023-01-21 08:48:44.203316: step: 384/531, loss: 0.07585316151380539
2023-01-21 08:48:45.313596: step: 388/531, loss: 0.12614183127880096
2023-01-21 08:48:46.433088: step: 392/531, loss: 0.3918529450893402
2023-01-21 08:48:47.555390: step: 396/531, loss: 0.3381730616092682
2023-01-21 08:48:48.682616: step: 400/531, loss: 1.1836628913879395
2023-01-21 08:48:49.794167: step: 404/531, loss: 0.770467221736908
2023-01-21 08:48:50.890988: step: 408/531, loss: 0.09366574883460999
2023-01-21 08:48:52.012392: step: 412/531, loss: 0.19394254684448242
2023-01-21 08:48:53.163684: step: 416/531, loss: 0.23999567329883575
2023-01-21 08:48:54.279717: step: 420/531, loss: 0.1803724318742752
2023-01-21 08:48:55.382702: step: 424/531, loss: 0.15346011519432068
2023-01-21 08:48:56.490366: step: 428/531, loss: 0.07764768600463867
2023-01-21 08:48:57.610187: step: 432/531, loss: 0.18345585465431213
2023-01-21 08:48:58.764208: step: 436/531, loss: 0.7415252327919006
2023-01-21 08:48:59.915132: step: 440/531, loss: 0.7271220684051514
2023-01-21 08:49:01.031417: step: 444/531, loss: 0.8113651275634766
2023-01-21 08:49:02.172814: step: 448/531, loss: 0.1729355901479721
2023-01-21 08:49:03.302294: step: 452/531, loss: 0.06541948765516281
2023-01-21 08:49:04.435293: step: 456/531, loss: 0.23413439095020294
2023-01-21 08:49:05.566708: step: 460/531, loss: 0.6707006096839905
2023-01-21 08:49:06.718747: step: 464/531, loss: 0.6349808573722839
2023-01-21 08:49:07.849000: step: 468/531, loss: 0.5122022032737732
2023-01-21 08:49:08.954248: step: 472/531, loss: 0.6229504942893982
2023-01-21 08:49:10.098991: step: 476/531, loss: 0.20829248428344727
2023-01-21 08:49:11.242156: step: 480/531, loss: 2.0307044982910156
2023-01-21 08:49:12.382476: step: 484/531, loss: 0.780998706817627
2023-01-21 08:49:13.518644: step: 488/531, loss: 0.3710038363933563
2023-01-21 08:49:14.645223: step: 492/531, loss: 0.698712944984436
2023-01-21 08:49:15.781385: step: 496/531, loss: 0.6875631213188171
2023-01-21 08:49:16.915121: step: 500/531, loss: 0.6885471343994141
2023-01-21 08:49:18.060165: step: 504/531, loss: 0.23836584389209747
2023-01-21 08:49:19.171710: step: 508/531, loss: 0.3633994162082672
2023-01-21 08:49:20.279085: step: 512/531, loss: 0.1445978283882141
2023-01-21 08:49:21.416767: step: 516/531, loss: 2.135205030441284
2023-01-21 08:49:22.562239: step: 520/531, loss: 0.19791412353515625
2023-01-21 08:49:23.671022: step: 524/531, loss: 0.8024535179138184
2023-01-21 08:49:24.791110: step: 528/531, loss: 0.1619952768087387
2023-01-21 08:49:25.898824: step: 532/531, loss: 0.1395251303911209
2023-01-21 08:49:27.015957: step: 536/531, loss: 0.9045207500457764
2023-01-21 08:49:28.179628: step: 540/531, loss: 0.7106897830963135
2023-01-21 08:49:29.319020: step: 544/531, loss: 0.2746366560459137
2023-01-21 08:49:30.449203: step: 548/531, loss: 0.21125774085521698
2023-01-21 08:49:31.582746: step: 552/531, loss: 0.3815675973892212
2023-01-21 08:49:32.701608: step: 556/531, loss: 0.11512966454029083
2023-01-21 08:49:33.827994: step: 560/531, loss: 0.14159874618053436
2023-01-21 08:49:34.980345: step: 564/531, loss: 0.08137235790491104
2023-01-21 08:49:36.095809: step: 568/531, loss: 0.08827038109302521
2023-01-21 08:49:37.239710: step: 572/531, loss: 0.21972376108169556
2023-01-21 08:49:38.426634: step: 576/531, loss: 0.6301490664482117
2023-01-21 08:49:39.529448: step: 580/531, loss: 0.16319340467453003
2023-01-21 08:49:40.631654: step: 584/531, loss: 0.12621183693408966
2023-01-21 08:49:41.776610: step: 588/531, loss: 0.1114928275346756
2023-01-21 08:49:42.935624: step: 592/531, loss: 0.26103147864341736
2023-01-21 08:49:44.081014: step: 596/531, loss: 0.057212162762880325
2023-01-21 08:49:45.230316: step: 600/531, loss: 0.42674845457077026
2023-01-21 08:49:46.358304: step: 604/531, loss: 0.07332558184862137
2023-01-21 08:49:47.487415: step: 608/531, loss: 0.30532127618789673
2023-01-21 08:49:48.632894: step: 612/531, loss: 0.23980112373828888
2023-01-21 08:49:49.741549: step: 616/531, loss: 0.8976439237594604
2023-01-21 08:49:50.891426: step: 620/531, loss: 2.906677007675171
2023-01-21 08:49:52.009049: step: 624/531, loss: 0.7280469536781311
2023-01-21 08:49:53.165211: step: 628/531, loss: 1.1542143821716309
2023-01-21 08:49:54.298504: step: 632/531, loss: 0.3346903920173645
2023-01-21 08:49:55.423994: step: 636/531, loss: 0.34560537338256836
2023-01-21 08:49:56.540034: step: 640/531, loss: 0.1651010513305664
2023-01-21 08:49:57.677455: step: 644/531, loss: 0.21281543374061584
2023-01-21 08:49:58.793067: step: 648/531, loss: 0.2954367399215698
2023-01-21 08:49:59.949537: step: 652/531, loss: 0.1339561492204666
2023-01-21 08:50:01.084297: step: 656/531, loss: 0.1886063665151596
2023-01-21 08:50:02.212057: step: 660/531, loss: 1.0190188884735107
2023-01-21 08:50:03.321712: step: 664/531, loss: 0.11133213341236115
2023-01-21 08:50:04.454401: step: 668/531, loss: 0.2437620311975479
2023-01-21 08:50:05.593710: step: 672/531, loss: 0.21872201561927795
2023-01-21 08:50:06.718713: step: 676/531, loss: 0.19212254881858826
2023-01-21 08:50:07.866639: step: 680/531, loss: 1.5248701572418213
2023-01-21 08:50:09.039501: step: 684/531, loss: 0.2010609209537506
2023-01-21 08:50:10.139624: step: 688/531, loss: 0.12344007939100266
2023-01-21 08:50:11.262009: step: 692/531, loss: 0.4252944886684418
2023-01-21 08:50:12.391919: step: 696/531, loss: 1.312186360359192
2023-01-21 08:50:13.514282: step: 700/531, loss: 1.0798553228378296
2023-01-21 08:50:14.637436: step: 704/531, loss: 0.5881645083427429
2023-01-21 08:50:15.757052: step: 708/531, loss: 0.10628495365381241
2023-01-21 08:50:16.905424: step: 712/531, loss: 0.159512460231781
2023-01-21 08:50:18.047798: step: 716/531, loss: 2.050825595855713
2023-01-21 08:50:19.192935: step: 720/531, loss: 0.09985098242759705
2023-01-21 08:50:20.297938: step: 724/531, loss: 0.30086416006088257
2023-01-21 08:50:21.422758: step: 728/531, loss: 0.23234796524047852
2023-01-21 08:50:22.571621: step: 732/531, loss: 0.17717213928699493
2023-01-21 08:50:23.710706: step: 736/531, loss: 0.20781327784061432
2023-01-21 08:50:24.821991: step: 740/531, loss: 0.7929614186286926
2023-01-21 08:50:25.939593: step: 744/531, loss: 0.7031111121177673
2023-01-21 08:50:27.053141: step: 748/531, loss: 0.17271780967712402
2023-01-21 08:50:28.156087: step: 752/531, loss: 0.15759292244911194
2023-01-21 08:50:29.315564: step: 756/531, loss: 0.2638086676597595
2023-01-21 08:50:30.428910: step: 760/531, loss: 0.13789749145507812
2023-01-21 08:50:31.552006: step: 764/531, loss: 1.042675256729126
2023-01-21 08:50:32.657553: step: 768/531, loss: 0.15152187645435333
2023-01-21 08:50:33.799427: step: 772/531, loss: 0.29762402176856995
2023-01-21 08:50:34.935240: step: 776/531, loss: 0.8096060752868652
2023-01-21 08:50:36.076028: step: 780/531, loss: 0.6018036007881165
2023-01-21 08:50:37.196339: step: 784/531, loss: 0.7044198513031006
2023-01-21 08:50:38.352325: step: 788/531, loss: 1.0509707927703857
2023-01-21 08:50:39.486210: step: 792/531, loss: 0.1526416838169098
2023-01-21 08:50:40.630107: step: 796/531, loss: 1.2137681245803833
2023-01-21 08:50:41.774280: step: 800/531, loss: 0.20632153749465942
2023-01-21 08:50:42.883971: step: 804/531, loss: 0.2633296847343445
2023-01-21 08:50:44.023594: step: 808/531, loss: 0.18680515885353088
2023-01-21 08:50:45.160967: step: 812/531, loss: 0.7810570001602173
2023-01-21 08:50:46.281414: step: 816/531, loss: 2.1240315437316895
2023-01-21 08:50:47.388930: step: 820/531, loss: 1.6482373476028442
2023-01-21 08:50:48.509443: step: 824/531, loss: 0.8680394291877747
2023-01-21 08:50:49.647208: step: 828/531, loss: 0.17143592238426208
2023-01-21 08:50:50.774908: step: 832/531, loss: 0.15712718665599823
2023-01-21 08:50:51.903193: step: 836/531, loss: 6.5789875984191895
2023-01-21 08:50:53.021300: step: 840/531, loss: 0.5327132940292358
2023-01-21 08:50:54.147967: step: 844/531, loss: 0.14803513884544373
2023-01-21 08:50:55.301334: step: 848/531, loss: 0.22047024965286255
2023-01-21 08:50:56.438368: step: 852/531, loss: 0.12683305144309998
2023-01-21 08:50:57.564299: step: 856/531, loss: 0.11187329143285751
2023-01-21 08:50:58.686591: step: 860/531, loss: 0.28370827436447144
2023-01-21 08:50:59.827631: step: 864/531, loss: 0.17166957259178162
2023-01-21 08:51:00.956702: step: 868/531, loss: 0.050062134861946106
2023-01-21 08:51:02.077563: step: 872/531, loss: 0.6749389171600342
2023-01-21 08:51:03.190049: step: 876/531, loss: 1.137378454208374
2023-01-21 08:51:04.299292: step: 880/531, loss: 0.20644298195838928
2023-01-21 08:51:05.446851: step: 884/531, loss: 0.06601281464099884
2023-01-21 08:51:06.528680: step: 888/531, loss: 0.7395771741867065
2023-01-21 08:51:07.646935: step: 892/531, loss: 0.06680784374475479
2023-01-21 08:51:08.800445: step: 896/531, loss: 0.25551241636276245
2023-01-21 08:51:09.911359: step: 900/531, loss: 0.11387459933757782
2023-01-21 08:51:11.025945: step: 904/531, loss: 0.2727457880973816
2023-01-21 08:51:12.155844: step: 908/531, loss: 0.13785429298877716
2023-01-21 08:51:13.263286: step: 912/531, loss: 1.1785967350006104
2023-01-21 08:51:14.377624: step: 916/531, loss: 0.1641356498003006
2023-01-21 08:51:15.515164: step: 920/531, loss: 0.5948185920715332
2023-01-21 08:51:16.640807: step: 924/531, loss: 0.2540041208267212
2023-01-21 08:51:17.777927: step: 928/531, loss: 0.6472973823547363
2023-01-21 08:51:18.921802: step: 932/531, loss: 0.10078860074281693
2023-01-21 08:51:20.049137: step: 936/531, loss: 0.3583838641643524
2023-01-21 08:51:21.153050: step: 940/531, loss: 0.07218985259532928
2023-01-21 08:51:22.266629: step: 944/531, loss: 0.17330054938793182
2023-01-21 08:51:23.409229: step: 948/531, loss: 0.3355116546154022
2023-01-21 08:51:24.529372: step: 952/531, loss: 0.25009462237358093
2023-01-21 08:51:25.650717: step: 956/531, loss: 0.13683763146400452
2023-01-21 08:51:26.779400: step: 960/531, loss: 0.38340532779693604
2023-01-21 08:51:27.891594: step: 964/531, loss: 0.3999234139919281
2023-01-21 08:51:29.035349: step: 968/531, loss: 0.22345657646656036
2023-01-21 08:51:30.161366: step: 972/531, loss: 0.9508110284805298
2023-01-21 08:51:31.314271: step: 976/531, loss: 0.8545024394989014
2023-01-21 08:51:32.429937: step: 980/531, loss: 0.17120656371116638
2023-01-21 08:51:33.605960: step: 984/531, loss: 0.11361608654260635
2023-01-21 08:51:34.717990: step: 988/531, loss: 0.20901842415332794
2023-01-21 08:51:35.832714: step: 992/531, loss: 0.6007456183433533
2023-01-21 08:51:36.970785: step: 996/531, loss: 1.1552215814590454
2023-01-21 08:51:38.102650: step: 1000/531, loss: 0.8901445269584656
2023-01-21 08:51:39.197683: step: 1004/531, loss: 0.36755266785621643
2023-01-21 08:51:40.322249: step: 1008/531, loss: 0.11657439172267914
2023-01-21 08:51:41.453682: step: 1012/531, loss: 0.7590698003768921
2023-01-21 08:51:42.581010: step: 1016/531, loss: 0.4374852180480957
2023-01-21 08:51:43.677801: step: 1020/531, loss: 0.947029709815979
2023-01-21 08:51:44.769667: step: 1024/531, loss: 0.10592050850391388
2023-01-21 08:51:45.955793: step: 1028/531, loss: 0.5956710577011108
2023-01-21 08:51:47.083424: step: 1032/531, loss: 1.4725477695465088
2023-01-21 08:51:48.206789: step: 1036/531, loss: 0.41024237871170044
2023-01-21 08:51:49.303007: step: 1040/531, loss: 0.5856024622917175
2023-01-21 08:51:50.424274: step: 1044/531, loss: 0.7835206389427185
2023-01-21 08:51:51.541245: step: 1048/531, loss: 3.6335926055908203
2023-01-21 08:51:52.681519: step: 1052/531, loss: 0.08657512813806534
2023-01-21 08:51:53.799021: step: 1056/531, loss: 0.9906864166259766
2023-01-21 08:51:54.901935: step: 1060/531, loss: 0.09550638496875763
2023-01-21 08:51:56.011453: step: 1064/531, loss: 0.11956606060266495
2023-01-21 08:51:57.148316: step: 1068/531, loss: 0.9163941144943237
2023-01-21 08:51:58.274015: step: 1072/531, loss: 0.5700295567512512
2023-01-21 08:51:59.407435: step: 1076/531, loss: 6.957311153411865
2023-01-21 08:52:00.513890: step: 1080/531, loss: 0.1573740541934967
2023-01-21 08:52:01.622633: step: 1084/531, loss: 1.2304725646972656
2023-01-21 08:52:02.738666: step: 1088/531, loss: 1.3342170715332031
2023-01-21 08:52:03.880889: step: 1092/531, loss: 0.12902946770191193
2023-01-21 08:52:05.005339: step: 1096/531, loss: 0.06106915324926376
2023-01-21 08:52:06.125087: step: 1100/531, loss: 1.06157648563385
2023-01-21 08:52:07.234911: step: 1104/531, loss: 0.06626663357019424
2023-01-21 08:52:08.347828: step: 1108/531, loss: 0.06310644000768661
2023-01-21 08:52:09.457512: step: 1112/531, loss: 0.09823315590620041
2023-01-21 08:52:10.580699: step: 1116/531, loss: 0.7527143359184265
2023-01-21 08:52:11.726510: step: 1120/531, loss: 0.74085533618927
2023-01-21 08:52:12.901524: step: 1124/531, loss: 1.3974148035049438
2023-01-21 08:52:14.010496: step: 1128/531, loss: 1.5040168762207031
2023-01-21 08:52:15.108610: step: 1132/531, loss: 0.6995537877082825
2023-01-21 08:52:16.197393: step: 1136/531, loss: 0.2084212303161621
2023-01-21 08:52:17.349434: step: 1140/531, loss: 1.5815051794052124
2023-01-21 08:52:18.443295: step: 1144/531, loss: 0.7678499817848206
2023-01-21 08:52:19.560604: step: 1148/531, loss: 0.1555301547050476
2023-01-21 08:52:20.729706: step: 1152/531, loss: 0.6561551690101624
2023-01-21 08:52:21.828058: step: 1156/531, loss: 0.034768246114254
2023-01-21 08:52:22.972811: step: 1160/531, loss: 0.9606888890266418
2023-01-21 08:52:24.078100: step: 1164/531, loss: 0.6768432855606079
2023-01-21 08:52:25.194025: step: 1168/531, loss: 0.41532501578330994
2023-01-21 08:52:26.330811: step: 1172/531, loss: 0.1155424565076828
2023-01-21 08:52:27.461462: step: 1176/531, loss: 0.4982238709926605
2023-01-21 08:52:28.579901: step: 1180/531, loss: 7.609128475189209
2023-01-21 08:52:29.704458: step: 1184/531, loss: 0.6324636340141296
2023-01-21 08:52:30.824980: step: 1188/531, loss: 0.1454913169145584
2023-01-21 08:52:31.945821: step: 1192/531, loss: 1.7525665760040283
2023-01-21 08:52:33.053824: step: 1196/531, loss: 0.2776854634284973
2023-01-21 08:52:34.185909: step: 1200/531, loss: 0.09683418273925781
2023-01-21 08:52:35.360010: step: 1204/531, loss: 1.0877107381820679
2023-01-21 08:52:36.480883: step: 1208/531, loss: 0.19226941466331482
2023-01-21 08:52:37.608491: step: 1212/531, loss: 0.2268226593732834
2023-01-21 08:52:38.726895: step: 1216/531, loss: 0.6520306468009949
2023-01-21 08:52:39.885521: step: 1220/531, loss: 0.12727731466293335
2023-01-21 08:52:41.004116: step: 1224/531, loss: 0.09743762016296387
2023-01-21 08:52:42.153196: step: 1228/531, loss: 1.691659927368164
2023-01-21 08:52:43.270444: step: 1232/531, loss: 0.6641461849212646
2023-01-21 08:52:44.384397: step: 1236/531, loss: 0.20985403656959534
2023-01-21 08:52:45.525976: step: 1240/531, loss: 0.2602899670600891
2023-01-21 08:52:46.630616: step: 1244/531, loss: 0.7859292030334473
2023-01-21 08:52:47.755692: step: 1248/531, loss: 0.08878204226493835
2023-01-21 08:52:48.859313: step: 1252/531, loss: 0.4219377338886261
2023-01-21 08:52:49.961283: step: 1256/531, loss: 0.1345120519399643
2023-01-21 08:52:51.053115: step: 1260/531, loss: 0.4237781763076782
2023-01-21 08:52:52.180505: step: 1264/531, loss: 3.7702183723449707
2023-01-21 08:52:53.304576: step: 1268/531, loss: 1.4639090299606323
2023-01-21 08:52:54.425085: step: 1272/531, loss: 0.546227753162384
2023-01-21 08:52:55.552399: step: 1276/531, loss: 0.4485281705856323
2023-01-21 08:52:56.704458: step: 1280/531, loss: 0.9650321006774902
2023-01-21 08:52:57.853427: step: 1284/531, loss: 0.37040644884109497
2023-01-21 08:52:59.022043: step: 1288/531, loss: 0.2140875607728958
2023-01-21 08:53:00.139304: step: 1292/531, loss: 0.4569013714790344
2023-01-21 08:53:01.234952: step: 1296/531, loss: 1.2681976556777954
2023-01-21 08:53:02.342682: step: 1300/531, loss: 2.1809608936309814
2023-01-21 08:53:03.468794: step: 1304/531, loss: 0.4685884714126587
2023-01-21 08:53:04.621703: step: 1308/531, loss: 0.12381152808666229
2023-01-21 08:53:05.768480: step: 1312/531, loss: 0.43081074953079224
2023-01-21 08:53:06.900293: step: 1316/531, loss: 0.17219844460487366
2023-01-21 08:53:08.025783: step: 1320/531, loss: 0.15136300027370453
2023-01-21 08:53:09.177883: step: 1324/531, loss: 1.1252928972244263
2023-01-21 08:53:10.261083: step: 1328/531, loss: 0.7586947679519653
2023-01-21 08:53:11.366593: step: 1332/531, loss: 0.049904439598321915
2023-01-21 08:53:12.490609: step: 1336/531, loss: 0.24002304673194885
2023-01-21 08:53:13.599078: step: 1340/531, loss: 0.31283408403396606
2023-01-21 08:53:14.727629: step: 1344/531, loss: 0.13884754478931427
2023-01-21 08:53:15.843453: step: 1348/531, loss: 0.21160832047462463
2023-01-21 08:53:16.957876: step: 1352/531, loss: 0.2823036313056946
2023-01-21 08:53:18.095233: step: 1356/531, loss: 0.17182999849319458
2023-01-21 08:53:19.223936: step: 1360/531, loss: 0.059093572199344635
2023-01-21 08:53:20.371204: step: 1364/531, loss: 0.2501261532306671
2023-01-21 08:53:21.487434: step: 1368/531, loss: 0.1321430206298828
2023-01-21 08:53:22.618591: step: 1372/531, loss: 0.20583033561706543
2023-01-21 08:53:23.762977: step: 1376/531, loss: 0.2908773422241211
2023-01-21 08:53:24.926480: step: 1380/531, loss: 0.138828843832016
2023-01-21 08:53:26.050999: step: 1384/531, loss: 0.590828537940979
2023-01-21 08:53:27.209252: step: 1388/531, loss: 0.9859359264373779
2023-01-21 08:53:28.330204: step: 1392/531, loss: 1.1036908626556396
2023-01-21 08:53:29.457723: step: 1396/531, loss: 0.7704716324806213
2023-01-21 08:53:30.588772: step: 1400/531, loss: 1.3098336458206177
2023-01-21 08:53:31.713031: step: 1404/531, loss: 0.9489328861236572
2023-01-21 08:53:32.834195: step: 1408/531, loss: 0.3856930136680603
2023-01-21 08:53:33.947013: step: 1412/531, loss: 0.23342999815940857
2023-01-21 08:53:35.088967: step: 1416/531, loss: 0.10315561294555664
2023-01-21 08:53:36.226198: step: 1420/531, loss: 0.4391617774963379
2023-01-21 08:53:37.359523: step: 1424/531, loss: 0.23436251282691956
2023-01-21 08:53:38.489423: step: 1428/531, loss: 0.17315179109573364
2023-01-21 08:53:39.597166: step: 1432/531, loss: 0.03181004524230957
2023-01-21 08:53:40.692784: step: 1436/531, loss: 0.21297875046730042
2023-01-21 08:53:41.823732: step: 1440/531, loss: 0.1252715140581131
2023-01-21 08:53:42.977296: step: 1444/531, loss: 1.476365566253662
2023-01-21 08:53:44.137563: step: 1448/531, loss: 0.4087343215942383
2023-01-21 08:53:45.266187: step: 1452/531, loss: 0.3203123211860657
2023-01-21 08:53:46.368536: step: 1456/531, loss: 0.21265503764152527
2023-01-21 08:53:47.493065: step: 1460/531, loss: 0.1920381486415863
2023-01-21 08:53:48.621384: step: 1464/531, loss: 0.2612139582633972
2023-01-21 08:53:49.755885: step: 1468/531, loss: 0.545148491859436
2023-01-21 08:53:50.854693: step: 1472/531, loss: 0.28278470039367676
2023-01-21 08:53:51.968579: step: 1476/531, loss: 1.2949702739715576
2023-01-21 08:53:53.084874: step: 1480/531, loss: 0.0972374975681305
2023-01-21 08:53:54.220743: step: 1484/531, loss: 0.8514845371246338
2023-01-21 08:53:55.301627: step: 1488/531, loss: 0.7473111152648926
2023-01-21 08:53:56.415375: step: 1492/531, loss: 8.381614685058594
2023-01-21 08:53:57.545725: step: 1496/531, loss: 0.5208867788314819
2023-01-21 08:53:58.701117: step: 1500/531, loss: 0.37298718094825745
2023-01-21 08:53:59.831332: step: 1504/531, loss: 0.15591751039028168
2023-01-21 08:54:00.948967: step: 1508/531, loss: 0.24155083298683167
2023-01-21 08:54:02.050689: step: 1512/531, loss: 0.14065274596214294
2023-01-21 08:54:03.185829: step: 1516/531, loss: 0.3229680061340332
2023-01-21 08:54:04.319790: step: 1520/531, loss: 0.4380077123641968
2023-01-21 08:54:05.467197: step: 1524/531, loss: 0.147398442029953
2023-01-21 08:54:06.592314: step: 1528/531, loss: 0.225171759724617
2023-01-21 08:54:07.698946: step: 1532/531, loss: 0.5240567922592163
2023-01-21 08:54:08.830471: step: 1536/531, loss: 0.7758234739303589
2023-01-21 08:54:09.947101: step: 1540/531, loss: 1.0318593978881836
2023-01-21 08:54:11.062471: step: 1544/531, loss: 0.7325069904327393
2023-01-21 08:54:12.208422: step: 1548/531, loss: 0.11525993794202805
2023-01-21 08:54:13.338070: step: 1552/531, loss: 0.8383235335350037
2023-01-21 08:54:14.473129: step: 1556/531, loss: 1.8379714488983154
2023-01-21 08:54:15.573256: step: 1560/531, loss: 0.19917169213294983
2023-01-21 08:54:16.710670: step: 1564/531, loss: 0.08856458961963654
2023-01-21 08:54:17.843847: step: 1568/531, loss: 0.7376327514648438
2023-01-21 08:54:18.953982: step: 1572/531, loss: 0.0812767967581749
2023-01-21 08:54:20.081926: step: 1576/531, loss: 0.12987622618675232
2023-01-21 08:54:21.215086: step: 1580/531, loss: 0.5027222633361816
2023-01-21 08:54:22.354943: step: 1584/531, loss: 0.442804217338562
2023-01-21 08:54:23.475359: step: 1588/531, loss: 0.8244544863700867
2023-01-21 08:54:24.600451: step: 1592/531, loss: 0.09971772134304047
2023-01-21 08:54:25.708988: step: 1596/531, loss: 0.5062020421028137
2023-01-21 08:54:26.836072: step: 1600/531, loss: 0.08735175430774689
2023-01-21 08:54:27.989190: step: 1604/531, loss: 0.13679353892803192
2023-01-21 08:54:29.171294: step: 1608/531, loss: 0.33079707622528076
2023-01-21 08:54:30.277166: step: 1612/531, loss: 0.3879395127296448
2023-01-21 08:54:31.377308: step: 1616/531, loss: 0.18667078018188477
2023-01-21 08:54:32.465675: step: 1620/531, loss: 0.36524903774261475
2023-01-21 08:54:33.613997: step: 1624/531, loss: 0.9339926242828369
2023-01-21 08:54:34.749901: step: 1628/531, loss: 0.3150537610054016
2023-01-21 08:54:35.882116: step: 1632/531, loss: 0.2344045639038086
2023-01-21 08:54:36.990311: step: 1636/531, loss: 0.3411739468574524
2023-01-21 08:54:38.097496: step: 1640/531, loss: 0.02496981807053089
2023-01-21 08:54:39.228630: step: 1644/531, loss: 0.14544254541397095
2023-01-21 08:54:40.357490: step: 1648/531, loss: 0.17730173468589783
2023-01-21 08:54:41.495121: step: 1652/531, loss: 1.1998558044433594
2023-01-21 08:54:42.645629: step: 1656/531, loss: 1.4463233947753906
2023-01-21 08:54:43.807669: step: 1660/531, loss: 0.9938532114028931
2023-01-21 08:54:44.921094: step: 1664/531, loss: 0.2296905517578125
2023-01-21 08:54:46.033403: step: 1668/531, loss: 0.7235745787620544
2023-01-21 08:54:47.139064: step: 1672/531, loss: 0.3931038975715637
2023-01-21 08:54:48.283487: step: 1676/531, loss: 0.08223333209753036
2023-01-21 08:54:49.407612: step: 1680/531, loss: 0.11543980240821838
2023-01-21 08:54:50.521380: step: 1684/531, loss: 0.23564620316028595
2023-01-21 08:54:51.667801: step: 1688/531, loss: 0.11182551085948944
2023-01-21 08:54:52.835803: step: 1692/531, loss: 0.26423460245132446
2023-01-21 08:54:53.950556: step: 1696/531, loss: 0.8914171457290649
2023-01-21 08:54:55.068731: step: 1700/531, loss: 0.2571353018283844
2023-01-21 08:54:56.190634: step: 1704/531, loss: 0.14939013123512268
2023-01-21 08:54:57.364366: step: 1708/531, loss: 0.34691277146339417
2023-01-21 08:54:58.438988: step: 1712/531, loss: 1.6872406005859375
2023-01-21 08:54:59.554216: step: 1716/531, loss: 0.7784949541091919
2023-01-21 08:55:00.705712: step: 1720/531, loss: 0.12170334160327911
2023-01-21 08:55:01.851623: step: 1724/531, loss: 0.22595274448394775
2023-01-21 08:55:02.962565: step: 1728/531, loss: 0.6139885783195496
2023-01-21 08:55:04.111470: step: 1732/531, loss: 0.33781617879867554
2023-01-21 08:55:05.231457: step: 1736/531, loss: 0.319772332906723
2023-01-21 08:55:06.367672: step: 1740/531, loss: 0.6939656138420105
2023-01-21 08:55:07.496617: step: 1744/531, loss: 0.40353959798812866
2023-01-21 08:55:08.643386: step: 1748/531, loss: 0.7860513925552368
2023-01-21 08:55:09.768059: step: 1752/531, loss: 0.07775941491127014
2023-01-21 08:55:10.864769: step: 1756/531, loss: 0.18229876458644867
2023-01-21 08:55:11.980129: step: 1760/531, loss: 0.08175616711378098
2023-01-21 08:55:13.110791: step: 1764/531, loss: 0.5313694477081299
2023-01-21 08:55:14.262420: step: 1768/531, loss: 0.29177960753440857
2023-01-21 08:55:15.387484: step: 1772/531, loss: 0.8129252791404724
2023-01-21 08:55:16.496338: step: 1776/531, loss: 0.3290082812309265
2023-01-21 08:55:17.631102: step: 1780/531, loss: 0.12709903717041016
2023-01-21 08:55:18.751229: step: 1784/531, loss: 1.948046088218689
2023-01-21 08:55:19.884284: step: 1788/531, loss: 0.39866989850997925
2023-01-21 08:55:21.005151: step: 1792/531, loss: 0.31562525033950806
2023-01-21 08:55:22.148381: step: 1796/531, loss: 6.704441070556641
2023-01-21 08:55:23.263128: step: 1800/531, loss: 0.8341490030288696
2023-01-21 08:55:24.392921: step: 1804/531, loss: 0.17107801139354706
2023-01-21 08:55:25.515141: step: 1808/531, loss: 0.6423975229263306
2023-01-21 08:55:26.638157: step: 1812/531, loss: 0.6129862070083618
2023-01-21 08:55:27.776119: step: 1816/531, loss: 1.418178915977478
2023-01-21 08:55:28.911200: step: 1820/531, loss: 0.36889734864234924
2023-01-21 08:55:30.020663: step: 1824/531, loss: 7.297482013702393
2023-01-21 08:55:31.133671: step: 1828/531, loss: 0.10019774734973907
2023-01-21 08:55:32.250687: step: 1832/531, loss: 0.46965092420578003
2023-01-21 08:55:33.368269: step: 1836/531, loss: 0.2980436384677887
2023-01-21 08:55:34.508866: step: 1840/531, loss: 1.2087880373001099
2023-01-21 08:55:35.608196: step: 1844/531, loss: 0.37208208441734314
2023-01-21 08:55:36.718904: step: 1848/531, loss: 0.1479925662279129
2023-01-21 08:55:37.840314: step: 1852/531, loss: 0.37395450472831726
2023-01-21 08:55:38.986141: step: 1856/531, loss: 0.9796489477157593
2023-01-21 08:55:40.115205: step: 1860/531, loss: 0.15056085586547852
2023-01-21 08:55:41.270299: step: 1864/531, loss: 0.11423273384571075
2023-01-21 08:55:42.404445: step: 1868/531, loss: 0.3338344693183899
2023-01-21 08:55:43.515219: step: 1872/531, loss: 0.9630193114280701
2023-01-21 08:55:44.667817: step: 1876/531, loss: 1.8121334314346313
2023-01-21 08:55:45.785663: step: 1880/531, loss: 0.11071091145277023
2023-01-21 08:55:46.931066: step: 1884/531, loss: 0.2831290066242218
2023-01-21 08:55:48.058437: step: 1888/531, loss: 0.5267331600189209
2023-01-21 08:55:49.182923: step: 1892/531, loss: 0.10727138817310333
2023-01-21 08:55:50.297317: step: 1896/531, loss: 0.06220896542072296
2023-01-21 08:55:51.421210: step: 1900/531, loss: 0.33919304609298706
2023-01-21 08:55:52.566287: step: 1904/531, loss: 0.04836144298315048
2023-01-21 08:55:53.676317: step: 1908/531, loss: 6.447678565979004
2023-01-21 08:55:54.803034: step: 1912/531, loss: 0.29288217425346375
2023-01-21 08:55:55.931625: step: 1916/531, loss: 0.3692001402378082
2023-01-21 08:55:57.028705: step: 1920/531, loss: 0.08110976219177246
2023-01-21 08:55:58.126861: step: 1924/531, loss: 0.3174844980239868
2023-01-21 08:55:59.245066: step: 1928/531, loss: 0.3076438903808594
2023-01-21 08:56:00.372490: step: 1932/531, loss: 0.299083948135376
2023-01-21 08:56:01.487579: step: 1936/531, loss: 0.35193508863449097
2023-01-21 08:56:02.595684: step: 1940/531, loss: 0.13347235321998596
2023-01-21 08:56:03.691253: step: 1944/531, loss: 0.7443598508834839
2023-01-21 08:56:04.824639: step: 1948/531, loss: 0.15762268006801605
2023-01-21 08:56:05.972153: step: 1952/531, loss: 0.8865430951118469
2023-01-21 08:56:07.091021: step: 1956/531, loss: 1.0948612689971924
2023-01-21 08:56:08.209552: step: 1960/531, loss: 0.08130589127540588
2023-01-21 08:56:09.344321: step: 1964/531, loss: 0.40301501750946045
2023-01-21 08:56:10.477915: step: 1968/531, loss: 1.0839444398880005
2023-01-21 08:56:11.586934: step: 1972/531, loss: 0.0632549300789833
2023-01-21 08:56:12.701782: step: 1976/531, loss: 0.2433350533246994
2023-01-21 08:56:13.807103: step: 1980/531, loss: 0.15397948026657104
2023-01-21 08:56:14.914787: step: 1984/531, loss: 0.251697838306427
2023-01-21 08:56:16.032592: step: 1988/531, loss: 0.15375256538391113
2023-01-21 08:56:17.161568: step: 1992/531, loss: 0.09616260975599289
2023-01-21 08:56:18.299337: step: 1996/531, loss: 1.0166057348251343
2023-01-21 08:56:19.415918: step: 2000/531, loss: 0.16484537720680237
2023-01-21 08:56:20.518080: step: 2004/531, loss: 0.04665394127368927
2023-01-21 08:56:21.639922: step: 2008/531, loss: 0.10111980140209198
2023-01-21 08:56:22.777522: step: 2012/531, loss: 2.2535128593444824
2023-01-21 08:56:23.874919: step: 2016/531, loss: 0.9195954203605652
2023-01-21 08:56:24.983050: step: 2020/531, loss: 0.10869503021240234
2023-01-21 08:56:26.113849: step: 2024/531, loss: 2.0339207649230957
2023-01-21 08:56:27.220452: step: 2028/531, loss: 6.240901947021484
2023-01-21 08:56:28.327572: step: 2032/531, loss: 0.21875745058059692
2023-01-21 08:56:29.428763: step: 2036/531, loss: 0.425650417804718
2023-01-21 08:56:30.590879: step: 2040/531, loss: 0.1376427710056305
2023-01-21 08:56:31.737050: step: 2044/531, loss: 0.304365873336792
2023-01-21 08:56:32.901847: step: 2048/531, loss: 0.09956922382116318
2023-01-21 08:56:34.018768: step: 2052/531, loss: 0.08913564682006836
2023-01-21 08:56:35.117285: step: 2056/531, loss: 0.29691264033317566
2023-01-21 08:56:36.241239: step: 2060/531, loss: 0.0633930191397667
2023-01-21 08:56:37.372490: step: 2064/531, loss: 0.13934431970119476
2023-01-21 08:56:38.486387: step: 2068/531, loss: 0.13103389739990234
2023-01-21 08:56:39.584061: step: 2072/531, loss: 0.7008161544799805
2023-01-21 08:56:40.702862: step: 2076/531, loss: 1.5216033458709717
2023-01-21 08:56:41.859071: step: 2080/531, loss: 1.4950681924819946
2023-01-21 08:56:42.992387: step: 2084/531, loss: 0.2535172402858734
2023-01-21 08:56:44.100587: step: 2088/531, loss: 1.3668227195739746
2023-01-21 08:56:45.235715: step: 2092/531, loss: 0.15920992195606232
2023-01-21 08:56:46.356259: step: 2096/531, loss: 1.681749939918518
2023-01-21 08:56:47.469493: step: 2100/531, loss: 0.15518221259117126
2023-01-21 08:56:48.601816: step: 2104/531, loss: 0.2543899416923523
2023-01-21 08:56:49.726479: step: 2108/531, loss: 0.13458938896656036
2023-01-21 08:56:50.859270: step: 2112/531, loss: 1.3520259857177734
2023-01-21 08:56:51.991155: step: 2116/531, loss: 0.2652145326137543
2023-01-21 08:56:53.118637: step: 2120/531, loss: 0.4456610679626465
2023-01-21 08:56:54.243924: step: 2124/531, loss: 0.06604361534118652
==================================================
Loss: 0.598
--------------------
Dev: {'event': {'p': 0.6514360313315927, 'r': 0.6644474034620506, 'f1': 0.6578773895847067}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6570926143024619, 'r': 0.6684555754323196, 'f1': 0.6627253916642033}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.6271186440677966, 'r': 0.6851851851851852, 'f1': 0.6548672566371682}, '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': 0.6071428571428571, 'r': 0.4722222222222222, 'f1': 0.53125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6514360313315927, 'r': 0.6644474034620506, 'f1': 0.6578773895847067}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6570926143024619, 'r': 0.6684555754323196, 'f1': 0.6627253916642033}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6271186440677966, 'r': 0.6851851851851852, 'f1': 0.6548672566371682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.8125, 'r': 0.4126984126984127, 'f1': 0.5473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6514360313315927, 'r': 0.6644474034620506, 'f1': 0.6578773895847067}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Russian: {'event': {'p': 0.6570926143024619, 'r': 0.6684555754323196, 'f1': 0.6627253916642033}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Russian: {'event': {'p': 0.6071428571428571, 'r': 0.4722222222222222, 'f1': 0.53125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 08:57:47.520533: step: 4/531, loss: 0.16662216186523438
2023-01-21 08:57:48.658313: step: 8/531, loss: 0.6138704419136047
2023-01-21 08:57:49.768567: step: 12/531, loss: 0.043197158724069595
2023-01-21 08:57:50.923023: step: 16/531, loss: 0.9986713528633118
2023-01-21 08:57:52.025890: step: 20/531, loss: 0.25728529691696167
2023-01-21 08:57:53.140515: step: 24/531, loss: 0.24201565980911255
2023-01-21 08:57:54.276983: step: 28/531, loss: 0.5085304379463196
2023-01-21 08:57:55.391420: step: 32/531, loss: 0.36001381278038025
2023-01-21 08:57:56.520060: step: 36/531, loss: 1.0557341575622559
2023-01-21 08:57:57.666971: step: 40/531, loss: 0.05920562893152237
2023-01-21 08:57:58.830182: step: 44/531, loss: 0.10665875673294067
2023-01-21 08:57:59.969982: step: 48/531, loss: 1.6024012565612793
2023-01-21 08:58:01.103113: step: 52/531, loss: 0.23823794722557068
2023-01-21 08:58:02.223519: step: 56/531, loss: 0.12140689045190811
2023-01-21 08:58:03.341541: step: 60/531, loss: 0.3833610415458679
2023-01-21 08:58:04.507925: step: 64/531, loss: 0.10561180859804153
2023-01-21 08:58:05.654682: step: 68/531, loss: 1.0837523937225342
2023-01-21 08:58:06.830776: step: 72/531, loss: 1.2641563415527344
2023-01-21 08:58:07.944749: step: 76/531, loss: 0.17548207938671112
2023-01-21 08:58:09.071051: step: 80/531, loss: 0.7715210914611816
2023-01-21 08:58:10.221933: step: 84/531, loss: 0.1898891031742096
2023-01-21 08:58:11.379082: step: 88/531, loss: 0.26800501346588135
2023-01-21 08:58:12.516367: step: 92/531, loss: 0.1271069496870041
2023-01-21 08:58:13.641066: step: 96/531, loss: 0.15137191116809845
2023-01-21 08:58:14.810090: step: 100/531, loss: 0.9224390387535095
2023-01-21 08:58:15.921525: step: 104/531, loss: 0.39085257053375244
2023-01-21 08:58:17.044200: step: 108/531, loss: 0.806428074836731
2023-01-21 08:58:18.166703: step: 112/531, loss: 0.670211672782898
2023-01-21 08:58:19.312292: step: 116/531, loss: 0.9572925567626953
2023-01-21 08:58:20.418311: step: 120/531, loss: 0.1352705955505371
2023-01-21 08:58:21.565218: step: 124/531, loss: 0.8628254532814026
2023-01-21 08:58:22.680817: step: 128/531, loss: 0.07888732105493546
2023-01-21 08:58:23.807373: step: 132/531, loss: 0.49997806549072266
2023-01-21 08:58:24.947192: step: 136/531, loss: 0.12863436341285706
2023-01-21 08:58:26.120114: step: 140/531, loss: 0.1377452313899994
2023-01-21 08:58:27.225801: step: 144/531, loss: 0.31675663590431213
2023-01-21 08:58:28.327564: step: 148/531, loss: 0.17679738998413086
2023-01-21 08:58:29.442197: step: 152/531, loss: 0.14813052117824554
2023-01-21 08:58:30.564172: step: 156/531, loss: 0.21542072296142578
2023-01-21 08:58:31.716292: step: 160/531, loss: 0.0798526257276535
2023-01-21 08:58:32.845456: step: 164/531, loss: 0.27220889925956726
2023-01-21 08:58:33.985394: step: 168/531, loss: 0.1726182997226715
2023-01-21 08:58:35.130499: step: 172/531, loss: 0.17931662499904633
2023-01-21 08:58:36.232334: step: 176/531, loss: 0.04673619568347931
2023-01-21 08:58:37.356176: step: 180/531, loss: 0.15547513961791992
2023-01-21 08:58:38.484641: step: 184/531, loss: 0.06568518280982971
2023-01-21 08:58:39.614022: step: 188/531, loss: 0.26724153757095337
2023-01-21 08:58:40.708456: step: 192/531, loss: 0.6732152104377747
2023-01-21 08:58:41.887649: step: 196/531, loss: 0.4713152050971985
2023-01-21 08:58:43.018013: step: 200/531, loss: 0.04192962870001793
2023-01-21 08:58:44.156171: step: 204/531, loss: 0.8031841516494751
2023-01-21 08:58:45.314865: step: 208/531, loss: 0.6889842748641968
2023-01-21 08:58:46.439347: step: 212/531, loss: 0.967907190322876
2023-01-21 08:58:47.565035: step: 216/531, loss: 0.8394032716751099
2023-01-21 08:58:48.656233: step: 220/531, loss: 0.12822183966636658
2023-01-21 08:58:49.770527: step: 224/531, loss: 0.22148971259593964
2023-01-21 08:58:50.907720: step: 228/531, loss: 0.11873769760131836
2023-01-21 08:58:52.023582: step: 232/531, loss: 1.1610593795776367
2023-01-21 08:58:53.133004: step: 236/531, loss: 0.6590182185173035
2023-01-21 08:58:54.269517: step: 240/531, loss: 0.6668195724487305
2023-01-21 08:58:55.381286: step: 244/531, loss: 0.8663637042045593
2023-01-21 08:58:56.497197: step: 248/531, loss: 0.21116772294044495
2023-01-21 08:58:57.604261: step: 252/531, loss: 0.5122771859169006
2023-01-21 08:58:58.721129: step: 256/531, loss: 1.1016069650650024
2023-01-21 08:58:59.846817: step: 260/531, loss: 0.3089834153652191
2023-01-21 08:59:00.942241: step: 264/531, loss: 0.3933687210083008
2023-01-21 08:59:02.064202: step: 268/531, loss: 0.1246330738067627
2023-01-21 08:59:03.152336: step: 272/531, loss: 0.21756906807422638
2023-01-21 08:59:04.281310: step: 276/531, loss: 0.735102117061615
2023-01-21 08:59:05.391347: step: 280/531, loss: 0.3586246371269226
2023-01-21 08:59:06.505405: step: 284/531, loss: 0.21320581436157227
2023-01-21 08:59:07.616040: step: 288/531, loss: 0.342446893453598
2023-01-21 08:59:08.735242: step: 292/531, loss: 0.23088237643241882
2023-01-21 08:59:09.891559: step: 296/531, loss: 0.4778937101364136
2023-01-21 08:59:11.030173: step: 300/531, loss: 0.8178250193595886
2023-01-21 08:59:12.130060: step: 304/531, loss: 0.7688889503479004
2023-01-21 08:59:13.237069: step: 308/531, loss: 0.4121326208114624
2023-01-21 08:59:14.365005: step: 312/531, loss: 0.15973415970802307
2023-01-21 08:59:15.460647: step: 316/531, loss: 0.14084920287132263
2023-01-21 08:59:16.570844: step: 320/531, loss: 0.13389372825622559
2023-01-21 08:59:17.683697: step: 324/531, loss: 0.7516636252403259
2023-01-21 08:59:18.792445: step: 328/531, loss: 0.6399877667427063
2023-01-21 08:59:19.912765: step: 332/531, loss: 0.09671802818775177
2023-01-21 08:59:21.054250: step: 336/531, loss: 0.19902664422988892
2023-01-21 08:59:22.170804: step: 340/531, loss: 0.07357347011566162
2023-01-21 08:59:23.294480: step: 344/531, loss: 0.14418679475784302
2023-01-21 08:59:24.436394: step: 348/531, loss: 0.15957948565483093
2023-01-21 08:59:25.589399: step: 352/531, loss: 0.2750186026096344
2023-01-21 08:59:26.665806: step: 356/531, loss: 6.368100166320801
2023-01-21 08:59:27.805983: step: 360/531, loss: 0.3465927839279175
2023-01-21 08:59:28.937592: step: 364/531, loss: 0.4368191957473755
2023-01-21 08:59:30.051055: step: 368/531, loss: 0.3170282244682312
2023-01-21 08:59:31.179122: step: 372/531, loss: 0.17959733307361603
2023-01-21 08:59:32.322703: step: 376/531, loss: 0.245753675699234
2023-01-21 08:59:33.454206: step: 380/531, loss: 0.23004131019115448
2023-01-21 08:59:34.598168: step: 384/531, loss: 0.11193791031837463
2023-01-21 08:59:35.713538: step: 388/531, loss: 0.20531444251537323
2023-01-21 08:59:36.836300: step: 392/531, loss: 0.18397626280784607
2023-01-21 08:59:37.955355: step: 396/531, loss: 0.1100132018327713
2023-01-21 08:59:39.046526: step: 400/531, loss: 0.30163049697875977
2023-01-21 08:59:40.169977: step: 404/531, loss: 0.6225482225418091
2023-01-21 08:59:41.285410: step: 408/531, loss: 0.4819822311401367
2023-01-21 08:59:42.423859: step: 412/531, loss: 0.14583168923854828
2023-01-21 08:59:43.545383: step: 416/531, loss: 0.5499014258384705
2023-01-21 08:59:44.734635: step: 420/531, loss: 0.19112345576286316
2023-01-21 08:59:45.875350: step: 424/531, loss: 1.0183470249176025
2023-01-21 08:59:47.005623: step: 428/531, loss: 0.19668178260326385
2023-01-21 08:59:48.123156: step: 432/531, loss: 0.5788142681121826
2023-01-21 08:59:49.247945: step: 436/531, loss: 0.8933883905410767
2023-01-21 08:59:50.387198: step: 440/531, loss: 0.10386767983436584
2023-01-21 08:59:51.500701: step: 444/531, loss: 0.07568464428186417
2023-01-21 08:59:52.637375: step: 448/531, loss: 0.17182761430740356
2023-01-21 08:59:53.760214: step: 452/531, loss: 0.44821253418922424
2023-01-21 08:59:54.883213: step: 456/531, loss: 1.8453174829483032
2023-01-21 08:59:56.002493: step: 460/531, loss: 0.36006927490234375
2023-01-21 08:59:57.114889: step: 464/531, loss: 0.12083110958337784
2023-01-21 08:59:58.251631: step: 468/531, loss: 0.47441715002059937
2023-01-21 08:59:59.350591: step: 472/531, loss: 0.060214996337890625
2023-01-21 09:00:00.441405: step: 476/531, loss: 0.05754494667053223
2023-01-21 09:00:01.561917: step: 480/531, loss: 0.0638250783085823
2023-01-21 09:00:02.672237: step: 484/531, loss: 0.7962153553962708
2023-01-21 09:00:03.819716: step: 488/531, loss: 0.3979437053203583
2023-01-21 09:00:04.934903: step: 492/531, loss: 0.5276994705200195
2023-01-21 09:00:06.071170: step: 496/531, loss: 0.1254461258649826
2023-01-21 09:00:07.185476: step: 500/531, loss: 0.10908088833093643
2023-01-21 09:00:08.306088: step: 504/531, loss: 0.1849699467420578
2023-01-21 09:00:09.405482: step: 508/531, loss: 0.1103767454624176
2023-01-21 09:00:10.546073: step: 512/531, loss: 0.2388903647661209
2023-01-21 09:00:11.656181: step: 516/531, loss: 0.08560748398303986
2023-01-21 09:00:12.785381: step: 520/531, loss: 1.113990068435669
2023-01-21 09:00:13.891145: step: 524/531, loss: 0.15884310007095337
2023-01-21 09:00:15.011881: step: 528/531, loss: 0.06486983597278595
2023-01-21 09:00:16.160041: step: 532/531, loss: 0.15931951999664307
2023-01-21 09:00:17.286101: step: 536/531, loss: 0.07498688995838165
2023-01-21 09:00:18.421176: step: 540/531, loss: 0.37991830706596375
2023-01-21 09:00:19.518935: step: 544/531, loss: 0.2313407063484192
2023-01-21 09:00:20.646102: step: 548/531, loss: 0.5404362678527832
2023-01-21 09:00:21.787909: step: 552/531, loss: 0.16544213891029358
2023-01-21 09:00:22.889629: step: 556/531, loss: 0.13815440237522125
2023-01-21 09:00:24.028119: step: 560/531, loss: 0.04776563495397568
2023-01-21 09:00:25.140141: step: 564/531, loss: 0.09709911793470383
2023-01-21 09:00:26.295032: step: 568/531, loss: 0.1378200501203537
2023-01-21 09:00:27.415357: step: 572/531, loss: 0.6328756809234619
2023-01-21 09:00:28.548409: step: 576/531, loss: 0.9069112539291382
2023-01-21 09:00:29.699839: step: 580/531, loss: 0.34874820709228516
2023-01-21 09:00:30.842234: step: 584/531, loss: 0.07492513954639435
2023-01-21 09:00:31.944718: step: 588/531, loss: 0.03363952785730362
2023-01-21 09:00:33.061013: step: 592/531, loss: 0.16928711533546448
2023-01-21 09:00:34.201160: step: 596/531, loss: 0.37546029686927795
2023-01-21 09:00:35.334674: step: 600/531, loss: 0.0743885487318039
2023-01-21 09:00:36.469585: step: 604/531, loss: 0.12271638214588165
2023-01-21 09:00:37.589613: step: 608/531, loss: 0.10387945175170898
2023-01-21 09:00:38.708623: step: 612/531, loss: 0.35221025347709656
2023-01-21 09:00:39.848526: step: 616/531, loss: 0.23270520567893982
2023-01-21 09:00:40.966560: step: 620/531, loss: 0.4657605290412903
2023-01-21 09:00:42.116302: step: 624/531, loss: 0.2584255337715149
2023-01-21 09:00:43.233177: step: 628/531, loss: 1.6028679609298706
2023-01-21 09:00:44.374299: step: 632/531, loss: 0.24047031998634338
2023-01-21 09:00:45.534773: step: 636/531, loss: 0.15306806564331055
2023-01-21 09:00:46.677551: step: 640/531, loss: 3.189697265625
2023-01-21 09:00:47.757190: step: 644/531, loss: 0.1187511458992958
2023-01-21 09:00:48.884122: step: 648/531, loss: 0.14820004999637604
2023-01-21 09:00:50.046397: step: 652/531, loss: 0.7147862911224365
2023-01-21 09:00:51.160864: step: 656/531, loss: 0.8112518191337585
2023-01-21 09:00:52.278206: step: 660/531, loss: 0.6644281148910522
2023-01-21 09:00:53.404904: step: 664/531, loss: 0.2926095724105835
2023-01-21 09:00:54.528436: step: 668/531, loss: 0.5058299899101257
2023-01-21 09:00:55.643785: step: 672/531, loss: 0.09663629531860352
2023-01-21 09:00:56.740144: step: 676/531, loss: 0.28038692474365234
2023-01-21 09:00:57.878963: step: 680/531, loss: 0.16675615310668945
2023-01-21 09:00:59.027239: step: 684/531, loss: 0.16124801337718964
2023-01-21 09:01:00.168820: step: 688/531, loss: 0.6827594041824341
2023-01-21 09:01:01.282259: step: 692/531, loss: 0.6800993084907532
2023-01-21 09:01:02.410912: step: 696/531, loss: 0.20764131844043732
2023-01-21 09:01:03.535577: step: 700/531, loss: 0.1090860366821289
2023-01-21 09:01:04.649950: step: 704/531, loss: 0.15023556351661682
2023-01-21 09:01:05.768738: step: 708/531, loss: 0.5590397119522095
2023-01-21 09:01:06.902964: step: 712/531, loss: 0.21748369932174683
2023-01-21 09:01:08.045992: step: 716/531, loss: 0.23442602157592773
2023-01-21 09:01:09.170379: step: 720/531, loss: 1.1037371158599854
2023-01-21 09:01:10.280210: step: 724/531, loss: 0.19483137130737305
2023-01-21 09:01:11.422235: step: 728/531, loss: 0.2529425621032715
2023-01-21 09:01:12.549715: step: 732/531, loss: 0.06408672034740448
2023-01-21 09:01:13.661093: step: 736/531, loss: 0.11017031967639923
2023-01-21 09:01:14.763344: step: 740/531, loss: 0.13152790069580078
2023-01-21 09:01:15.913954: step: 744/531, loss: 0.1627214550971985
2023-01-21 09:01:17.032317: step: 748/531, loss: 0.05002836883068085
2023-01-21 09:01:18.176301: step: 752/531, loss: 0.0850561186671257
2023-01-21 09:01:19.300544: step: 756/531, loss: 0.26949211955070496
2023-01-21 09:01:20.414931: step: 760/531, loss: 0.09312200546264648
2023-01-21 09:01:21.541221: step: 764/531, loss: 0.4535209536552429
2023-01-21 09:01:22.649888: step: 768/531, loss: 0.8326729536056519
2023-01-21 09:01:23.796994: step: 772/531, loss: 0.39291179180145264
2023-01-21 09:01:24.924179: step: 776/531, loss: 0.14687509834766388
2023-01-21 09:01:26.033015: step: 780/531, loss: 0.11059560626745224
2023-01-21 09:01:27.154303: step: 784/531, loss: 0.22882090508937836
2023-01-21 09:01:28.288171: step: 788/531, loss: 0.9857144355773926
2023-01-21 09:01:29.410119: step: 792/531, loss: 0.37069380283355713
2023-01-21 09:01:30.569025: step: 796/531, loss: 0.15048182010650635
2023-01-21 09:01:31.687865: step: 800/531, loss: 0.11518535763025284
2023-01-21 09:01:32.827638: step: 804/531, loss: 0.6279888153076172
2023-01-21 09:01:33.934128: step: 808/531, loss: 0.554506778717041
2023-01-21 09:01:35.097007: step: 812/531, loss: 0.17894954979419708
2023-01-21 09:01:36.220201: step: 816/531, loss: 0.37503328919410706
2023-01-21 09:01:37.340502: step: 820/531, loss: 0.12509837746620178
2023-01-21 09:01:38.448721: step: 824/531, loss: 0.2600063383579254
2023-01-21 09:01:39.561747: step: 828/531, loss: 0.16963835060596466
2023-01-21 09:01:40.675145: step: 832/531, loss: 0.25909852981567383
2023-01-21 09:01:41.805742: step: 836/531, loss: 0.0875040590763092
2023-01-21 09:01:42.938492: step: 840/531, loss: 0.04245062172412872
2023-01-21 09:01:44.056750: step: 844/531, loss: 0.49918240308761597
2023-01-21 09:01:45.198885: step: 848/531, loss: 1.3098195791244507
2023-01-21 09:01:46.309561: step: 852/531, loss: 0.16476936638355255
2023-01-21 09:01:47.449858: step: 856/531, loss: 0.134425550699234
2023-01-21 09:01:48.575418: step: 860/531, loss: 0.8511238694190979
2023-01-21 09:01:49.695648: step: 864/531, loss: 0.13095274567604065
2023-01-21 09:01:50.861696: step: 868/531, loss: 1.5890244245529175
2023-01-21 09:01:51.969896: step: 872/531, loss: 0.04851360619068146
2023-01-21 09:01:53.076088: step: 876/531, loss: 0.6740989685058594
2023-01-21 09:01:54.199786: step: 880/531, loss: 0.2112097144126892
2023-01-21 09:01:55.322967: step: 884/531, loss: 0.6060776710510254
2023-01-21 09:01:56.456884: step: 888/531, loss: 6.26407527923584
2023-01-21 09:01:57.574498: step: 892/531, loss: 0.17175836861133575
2023-01-21 09:01:58.677408: step: 896/531, loss: 0.10602875053882599
2023-01-21 09:01:59.840846: step: 900/531, loss: 0.16825968027114868
2023-01-21 09:02:00.941902: step: 904/531, loss: 0.08746328949928284
2023-01-21 09:02:02.060068: step: 908/531, loss: 0.24208231270313263
2023-01-21 09:02:03.189004: step: 912/531, loss: 0.24104900658130646
2023-01-21 09:02:04.286107: step: 916/531, loss: 0.05861306190490723
2023-01-21 09:02:05.417903: step: 920/531, loss: 0.12055106461048126
2023-01-21 09:02:06.548175: step: 924/531, loss: 0.293590247631073
2023-01-21 09:02:07.708767: step: 928/531, loss: 0.18651580810546875
2023-01-21 09:02:08.858417: step: 932/531, loss: 0.17169369757175446
2023-01-21 09:02:09.969054: step: 936/531, loss: 2.6086864471435547
2023-01-21 09:02:11.078461: step: 940/531, loss: 0.6810840964317322
2023-01-21 09:02:12.190865: step: 944/531, loss: 0.2558404803276062
2023-01-21 09:02:13.302240: step: 948/531, loss: 0.43018078804016113
2023-01-21 09:02:14.403898: step: 952/531, loss: 0.03276710584759712
2023-01-21 09:02:15.531278: step: 956/531, loss: 0.731675922870636
2023-01-21 09:02:16.712977: step: 960/531, loss: 0.31705302000045776
2023-01-21 09:02:17.832351: step: 964/531, loss: 1.105121374130249
2023-01-21 09:02:18.951665: step: 968/531, loss: 0.02999272383749485
2023-01-21 09:02:20.074057: step: 972/531, loss: 0.29633599519729614
2023-01-21 09:02:21.199595: step: 976/531, loss: 0.5533487200737
2023-01-21 09:02:22.301169: step: 980/531, loss: 0.2234947383403778
2023-01-21 09:02:23.444626: step: 984/531, loss: 0.8931765556335449
2023-01-21 09:02:24.589832: step: 988/531, loss: 0.10681305080652237
2023-01-21 09:02:25.677711: step: 992/531, loss: 0.16969099640846252
2023-01-21 09:02:26.808570: step: 996/531, loss: 0.5271251797676086
2023-01-21 09:02:27.902976: step: 1000/531, loss: 0.02947692945599556
2023-01-21 09:02:29.028009: step: 1004/531, loss: 0.21456784009933472
2023-01-21 09:02:30.151411: step: 1008/531, loss: 0.10657548904418945
2023-01-21 09:02:31.276641: step: 1012/531, loss: 0.14209675788879395
2023-01-21 09:02:32.421105: step: 1016/531, loss: 0.23482033610343933
2023-01-21 09:02:33.569996: step: 1020/531, loss: 0.3176805377006531
2023-01-21 09:02:34.706050: step: 1024/531, loss: 0.06163635477423668
2023-01-21 09:02:35.853838: step: 1028/531, loss: 0.07156524807214737
2023-01-21 09:02:36.998320: step: 1032/531, loss: 0.13432101905345917
2023-01-21 09:02:38.149183: step: 1036/531, loss: 1.5836384296417236
2023-01-21 09:02:39.271132: step: 1040/531, loss: 0.3377200961112976
2023-01-21 09:02:40.385952: step: 1044/531, loss: 0.14433574676513672
2023-01-21 09:02:41.522802: step: 1048/531, loss: 0.16090470552444458
2023-01-21 09:02:42.648971: step: 1052/531, loss: 0.6653269529342651
2023-01-21 09:02:43.783365: step: 1056/531, loss: 0.10369344055652618
2023-01-21 09:02:44.936379: step: 1060/531, loss: 0.30237817764282227
2023-01-21 09:02:46.077539: step: 1064/531, loss: 0.1858772337436676
2023-01-21 09:02:47.174297: step: 1068/531, loss: 6.350717544555664
2023-01-21 09:02:48.299152: step: 1072/531, loss: 0.6866821050643921
2023-01-21 09:02:49.438036: step: 1076/531, loss: 0.13230451941490173
2023-01-21 09:02:50.577447: step: 1080/531, loss: 0.7150003910064697
2023-01-21 09:02:51.700340: step: 1084/531, loss: 0.24188528954982758
2023-01-21 09:02:52.867937: step: 1088/531, loss: 0.2658001780509949
2023-01-21 09:02:54.010016: step: 1092/531, loss: 0.14182662963867188
2023-01-21 09:02:55.105543: step: 1096/531, loss: 0.14601083099842072
2023-01-21 09:02:56.241604: step: 1100/531, loss: 0.33536964654922485
2023-01-21 09:02:57.362537: step: 1104/531, loss: 1.2487106323242188
2023-01-21 09:02:58.469866: step: 1108/531, loss: 0.04573507606983185
2023-01-21 09:02:59.593640: step: 1112/531, loss: 0.19724483788013458
2023-01-21 09:03:00.732581: step: 1116/531, loss: 6.658953666687012
2023-01-21 09:03:01.916866: step: 1120/531, loss: 0.07531404495239258
2023-01-21 09:03:03.031605: step: 1124/531, loss: 0.2183738797903061
2023-01-21 09:03:04.151933: step: 1128/531, loss: 0.09226799011230469
2023-01-21 09:03:05.261439: step: 1132/531, loss: 0.8653135299682617
2023-01-21 09:03:06.371877: step: 1136/531, loss: 0.7104889154434204
2023-01-21 09:03:07.469510: step: 1140/531, loss: 0.26601505279541016
2023-01-21 09:03:08.609290: step: 1144/531, loss: 0.11831030994653702
2023-01-21 09:03:09.723551: step: 1148/531, loss: 0.7495932579040527
2023-01-21 09:03:10.844749: step: 1152/531, loss: 0.3176819384098053
2023-01-21 09:03:11.971822: step: 1156/531, loss: 0.28096848726272583
2023-01-21 09:03:13.138039: step: 1160/531, loss: 0.12641488015651703
2023-01-21 09:03:14.285571: step: 1164/531, loss: 0.6406083106994629
2023-01-21 09:03:15.407822: step: 1168/531, loss: 0.44876059889793396
2023-01-21 09:03:16.527539: step: 1172/531, loss: 0.08108501881361008
2023-01-21 09:03:17.656918: step: 1176/531, loss: 0.12720216810703278
2023-01-21 09:03:18.753108: step: 1180/531, loss: 1.2504231929779053
2023-01-21 09:03:19.875083: step: 1184/531, loss: 0.08104820549488068
2023-01-21 09:03:20.994164: step: 1188/531, loss: 0.2751450538635254
2023-01-21 09:03:22.127527: step: 1192/531, loss: 0.16054968535900116
2023-01-21 09:03:23.249824: step: 1196/531, loss: 0.10385838150978088
2023-01-21 09:03:24.374976: step: 1200/531, loss: 0.22699794173240662
2023-01-21 09:03:25.492809: step: 1204/531, loss: 0.06376848369836807
2023-01-21 09:03:26.599864: step: 1208/531, loss: 0.14717711508274078
2023-01-21 09:03:27.715514: step: 1212/531, loss: 0.1023891419172287
2023-01-21 09:03:28.850075: step: 1216/531, loss: 0.4369228482246399
2023-01-21 09:03:29.992592: step: 1220/531, loss: 0.48825111985206604
2023-01-21 09:03:31.144720: step: 1224/531, loss: 0.49807554483413696
2023-01-21 09:03:32.296235: step: 1228/531, loss: 0.2706001400947571
2023-01-21 09:03:33.418808: step: 1232/531, loss: 0.8898267149925232
2023-01-21 09:03:34.528936: step: 1236/531, loss: 0.6811284422874451
2023-01-21 09:03:35.665356: step: 1240/531, loss: 0.22493773698806763
2023-01-21 09:03:36.780237: step: 1244/531, loss: 0.14221876859664917
2023-01-21 09:03:37.903014: step: 1248/531, loss: 0.24322977662086487
2023-01-21 09:03:39.019932: step: 1252/531, loss: 0.12687310576438904
2023-01-21 09:03:40.125131: step: 1256/531, loss: 0.12520436942577362
2023-01-21 09:03:41.230962: step: 1260/531, loss: 0.5926680564880371
2023-01-21 09:03:42.384404: step: 1264/531, loss: 1.5512936115264893
2023-01-21 09:03:43.484574: step: 1268/531, loss: 0.2939271926879883
2023-01-21 09:03:44.612214: step: 1272/531, loss: 0.16870155930519104
2023-01-21 09:03:45.759249: step: 1276/531, loss: 0.19709309935569763
2023-01-21 09:03:46.880293: step: 1280/531, loss: 0.26249590516090393
2023-01-21 09:03:47.998428: step: 1284/531, loss: 0.3689180314540863
2023-01-21 09:03:49.115459: step: 1288/531, loss: 1.9986234903335571
2023-01-21 09:03:50.239149: step: 1292/531, loss: 0.20813560485839844
2023-01-21 09:03:51.362765: step: 1296/531, loss: 0.2829445004463196
2023-01-21 09:03:52.489448: step: 1300/531, loss: 0.46262797713279724
2023-01-21 09:03:53.614746: step: 1304/531, loss: 1.4950883388519287
2023-01-21 09:03:54.752975: step: 1308/531, loss: 0.7825860977172852
2023-01-21 09:03:55.891856: step: 1312/531, loss: 0.17398595809936523
2023-01-21 09:03:56.993894: step: 1316/531, loss: 1.5933424234390259
2023-01-21 09:03:58.107770: step: 1320/531, loss: 0.3585663139820099
2023-01-21 09:03:59.247413: step: 1324/531, loss: 6.111742973327637
2023-01-21 09:04:00.349677: step: 1328/531, loss: 6.710764408111572
2023-01-21 09:04:01.466622: step: 1332/531, loss: 0.42534637451171875
2023-01-21 09:04:02.608076: step: 1336/531, loss: 6.452024459838867
2023-01-21 09:04:03.711239: step: 1340/531, loss: 0.026490593329072
2023-01-21 09:04:04.848953: step: 1344/531, loss: 0.21514034271240234
2023-01-21 09:04:05.964431: step: 1348/531, loss: 0.11302419006824493
2023-01-21 09:04:07.085876: step: 1352/531, loss: 0.17592263221740723
2023-01-21 09:04:08.207506: step: 1356/531, loss: 0.04754643514752388
2023-01-21 09:04:09.319360: step: 1360/531, loss: 0.07143106311559677
2023-01-21 09:04:10.465278: step: 1364/531, loss: 0.10684919357299805
2023-01-21 09:04:11.584504: step: 1368/531, loss: 0.1371428519487381
2023-01-21 09:04:12.710143: step: 1372/531, loss: 0.1619555503129959
2023-01-21 09:04:13.864813: step: 1376/531, loss: 0.10991425812244415
2023-01-21 09:04:14.981972: step: 1380/531, loss: 0.18041697144508362
2023-01-21 09:04:16.084320: step: 1384/531, loss: 0.13861122727394104
2023-01-21 09:04:17.206473: step: 1388/531, loss: 1.261899471282959
2023-01-21 09:04:18.322456: step: 1392/531, loss: 0.09035201370716095
2023-01-21 09:04:19.425174: step: 1396/531, loss: 0.09430161118507385
2023-01-21 09:04:20.568881: step: 1400/531, loss: 0.2554810643196106
2023-01-21 09:04:21.719011: step: 1404/531, loss: 0.11138715595006943
2023-01-21 09:04:22.840990: step: 1408/531, loss: 0.14705419540405273
2023-01-21 09:04:23.965383: step: 1412/531, loss: 0.08975587040185928
2023-01-21 09:04:25.086368: step: 1416/531, loss: 0.17991198599338531
2023-01-21 09:04:26.201578: step: 1420/531, loss: 0.4787808656692505
2023-01-21 09:04:27.330820: step: 1424/531, loss: 0.6533840298652649
2023-01-21 09:04:28.464078: step: 1428/531, loss: 1.1327035427093506
2023-01-21 09:04:29.590946: step: 1432/531, loss: 0.31544196605682373
2023-01-21 09:04:30.725537: step: 1436/531, loss: 0.19829073548316956
2023-01-21 09:04:31.849248: step: 1440/531, loss: 0.7922886610031128
2023-01-21 09:04:32.962042: step: 1444/531, loss: 0.45242154598236084
2023-01-21 09:04:34.074315: step: 1448/531, loss: 0.0868907943367958
2023-01-21 09:04:35.199462: step: 1452/531, loss: 6.72774600982666
2023-01-21 09:04:36.319344: step: 1456/531, loss: 0.6551020741462708
2023-01-21 09:04:37.437116: step: 1460/531, loss: 0.38183632493019104
2023-01-21 09:04:38.548702: step: 1464/531, loss: 0.17334146797657013
2023-01-21 09:04:39.683751: step: 1468/531, loss: 0.06473560631275177
2023-01-21 09:04:40.816648: step: 1472/531, loss: 1.2650949954986572
2023-01-21 09:04:41.949720: step: 1476/531, loss: 0.9869539141654968
2023-01-21 09:04:43.086370: step: 1480/531, loss: 0.7808462977409363
2023-01-21 09:04:44.203961: step: 1484/531, loss: 0.29303520917892456
2023-01-21 09:04:45.340359: step: 1488/531, loss: 0.31090497970581055
2023-01-21 09:04:46.472420: step: 1492/531, loss: 0.509864091873169
2023-01-21 09:04:47.626178: step: 1496/531, loss: 0.2444847822189331
2023-01-21 09:04:48.762845: step: 1500/531, loss: 0.7062308192253113
2023-01-21 09:04:49.902146: step: 1504/531, loss: 0.12572498619556427
2023-01-21 09:04:51.006802: step: 1508/531, loss: 0.10840673744678497
2023-01-21 09:04:52.161648: step: 1512/531, loss: 0.21810230612754822
2023-01-21 09:04:53.300960: step: 1516/531, loss: 0.1108594462275505
2023-01-21 09:04:54.433545: step: 1520/531, loss: 0.13676194846630096
2023-01-21 09:04:55.550578: step: 1524/531, loss: 1.5128180980682373
2023-01-21 09:04:56.679716: step: 1528/531, loss: 0.31835395097732544
2023-01-21 09:04:57.813430: step: 1532/531, loss: 0.18029403686523438
2023-01-21 09:04:58.922449: step: 1536/531, loss: 0.0620429553091526
2023-01-21 09:05:00.033608: step: 1540/531, loss: 0.9665861129760742
2023-01-21 09:05:01.153971: step: 1544/531, loss: 0.23005767166614532
2023-01-21 09:05:02.286752: step: 1548/531, loss: 0.09529547393321991
2023-01-21 09:05:03.428307: step: 1552/531, loss: 0.15144681930541992
2023-01-21 09:05:04.550512: step: 1556/531, loss: 1.3491935729980469
2023-01-21 09:05:05.671479: step: 1560/531, loss: 0.4917375445365906
2023-01-21 09:05:06.814902: step: 1564/531, loss: 1.0351355075836182
2023-01-21 09:05:07.919682: step: 1568/531, loss: 0.24221372604370117
2023-01-21 09:05:09.058988: step: 1572/531, loss: 0.6614864468574524
2023-01-21 09:05:10.188815: step: 1576/531, loss: 0.1420409232378006
2023-01-21 09:05:11.296087: step: 1580/531, loss: 0.5234269499778748
2023-01-21 09:05:12.407481: step: 1584/531, loss: 0.2370121031999588
2023-01-21 09:05:13.553106: step: 1588/531, loss: 0.12778696417808533
2023-01-21 09:05:14.665410: step: 1592/531, loss: 0.07138128578662872
2023-01-21 09:05:15.790738: step: 1596/531, loss: 0.14819002151489258
2023-01-21 09:05:16.944346: step: 1600/531, loss: 0.6488267779350281
2023-01-21 09:05:18.076523: step: 1604/531, loss: 0.1852748841047287
2023-01-21 09:05:19.197920: step: 1608/531, loss: 1.0953336954116821
2023-01-21 09:05:20.344020: step: 1612/531, loss: 0.6988387107849121
2023-01-21 09:05:21.482733: step: 1616/531, loss: 0.14900445938110352
2023-01-21 09:05:22.665058: step: 1620/531, loss: 0.38943299651145935
2023-01-21 09:05:23.817615: step: 1624/531, loss: 0.33376407623291016
2023-01-21 09:05:24.957850: step: 1628/531, loss: 0.144989013671875
2023-01-21 09:05:26.069489: step: 1632/531, loss: 0.09367694705724716
2023-01-21 09:05:27.181268: step: 1636/531, loss: 0.9546205401420593
2023-01-21 09:05:28.296241: step: 1640/531, loss: 0.20469646155834198
2023-01-21 09:05:29.401002: step: 1644/531, loss: 0.4632951021194458
2023-01-21 09:05:30.520700: step: 1648/531, loss: 1.105305790901184
2023-01-21 09:05:31.635613: step: 1652/531, loss: 0.059732675552368164
2023-01-21 09:05:32.746544: step: 1656/531, loss: 0.736891508102417
2023-01-21 09:05:33.871956: step: 1660/531, loss: 0.0957973450422287
2023-01-21 09:05:34.991634: step: 1664/531, loss: 0.05791821703314781
2023-01-21 09:05:36.131472: step: 1668/531, loss: 0.2219129502773285
2023-01-21 09:05:37.258490: step: 1672/531, loss: 0.19374127686023712
2023-01-21 09:05:38.367281: step: 1676/531, loss: 0.10098528861999512
2023-01-21 09:05:39.484464: step: 1680/531, loss: 0.2915896475315094
2023-01-21 09:05:40.623711: step: 1684/531, loss: 0.13615313172340393
2023-01-21 09:05:41.778800: step: 1688/531, loss: 1.0060828924179077
2023-01-21 09:05:42.919358: step: 1692/531, loss: 0.7194678783416748
2023-01-21 09:05:44.043142: step: 1696/531, loss: 0.06060910224914551
2023-01-21 09:05:45.155248: step: 1700/531, loss: 0.0589454285800457
2023-01-21 09:05:46.279329: step: 1704/531, loss: 0.21398936212062836
2023-01-21 09:05:47.405431: step: 1708/531, loss: 0.118120476603508
2023-01-21 09:05:48.525303: step: 1712/531, loss: 0.2954292297363281
2023-01-21 09:05:49.646511: step: 1716/531, loss: 0.14494939148426056
2023-01-21 09:05:50.824391: step: 1720/531, loss: 0.5078255534172058
2023-01-21 09:05:51.963760: step: 1724/531, loss: 0.10290718078613281
2023-01-21 09:05:53.085538: step: 1728/531, loss: 0.1213926300406456
2023-01-21 09:05:54.170670: step: 1732/531, loss: 0.6624854803085327
2023-01-21 09:05:55.294924: step: 1736/531, loss: 0.033014774322509766
2023-01-21 09:05:56.413967: step: 1740/531, loss: 0.24623575806617737
2023-01-21 09:05:57.538436: step: 1744/531, loss: 6.728213310241699
2023-01-21 09:05:58.673776: step: 1748/531, loss: 0.049927666783332825
2023-01-21 09:05:59.777283: step: 1752/531, loss: 0.10648477077484131
2023-01-21 09:06:00.910970: step: 1756/531, loss: 0.32085666060447693
2023-01-21 09:06:02.059515: step: 1760/531, loss: 0.5215115547180176
2023-01-21 09:06:03.232076: step: 1764/531, loss: 0.0846908837556839
2023-01-21 09:06:04.373745: step: 1768/531, loss: 0.5208784341812134
2023-01-21 09:06:05.484143: step: 1772/531, loss: 0.23698830604553223
2023-01-21 09:06:06.594907: step: 1776/531, loss: 0.5973255634307861
2023-01-21 09:06:07.705435: step: 1780/531, loss: 0.4342270791530609
2023-01-21 09:06:08.841889: step: 1784/531, loss: 0.1437152922153473
2023-01-21 09:06:09.969066: step: 1788/531, loss: 0.5214222073554993
2023-01-21 09:06:11.097518: step: 1792/531, loss: 0.14058314263820648
2023-01-21 09:06:12.251916: step: 1796/531, loss: 0.23124293982982635
2023-01-21 09:06:13.356387: step: 1800/531, loss: 0.16713590919971466
2023-01-21 09:06:14.477263: step: 1804/531, loss: 0.21768590807914734
2023-01-21 09:06:15.624790: step: 1808/531, loss: 0.03388547897338867
2023-01-21 09:06:16.752024: step: 1812/531, loss: 0.43925586342811584
2023-01-21 09:06:17.879585: step: 1816/531, loss: 0.42096811532974243
2023-01-21 09:06:19.004539: step: 1820/531, loss: 0.9137694239616394
2023-01-21 09:06:20.117398: step: 1824/531, loss: 0.035216882824897766
2023-01-21 09:06:21.249270: step: 1828/531, loss: 0.12874551117420197
2023-01-21 09:06:22.361182: step: 1832/531, loss: 0.115388423204422
2023-01-21 09:06:23.459743: step: 1836/531, loss: 6.278397560119629
2023-01-21 09:06:24.564336: step: 1840/531, loss: 0.22608862817287445
2023-01-21 09:06:25.686769: step: 1844/531, loss: 0.1218988448381424
2023-01-21 09:06:26.826408: step: 1848/531, loss: 0.2171352356672287
2023-01-21 09:06:27.966766: step: 1852/531, loss: 0.05553038418292999
2023-01-21 09:06:29.076372: step: 1856/531, loss: 0.1022796630859375
2023-01-21 09:06:30.217003: step: 1860/531, loss: 0.12974414229393005
2023-01-21 09:06:31.353772: step: 1864/531, loss: 1.0389344692230225
2023-01-21 09:06:32.435286: step: 1868/531, loss: 0.10201707482337952
2023-01-21 09:06:33.554127: step: 1872/531, loss: 1.1278913021087646
2023-01-21 09:06:34.678182: step: 1876/531, loss: 0.0420563705265522
2023-01-21 09:06:35.778456: step: 1880/531, loss: 0.16171474754810333
2023-01-21 09:06:36.886712: step: 1884/531, loss: 0.058796025812625885
2023-01-21 09:06:38.001692: step: 1888/531, loss: 0.09874926507472992
2023-01-21 09:06:39.113482: step: 1892/531, loss: 0.32869645953178406
2023-01-21 09:06:40.256751: step: 1896/531, loss: 1.0184884071350098
2023-01-21 09:06:41.394532: step: 1900/531, loss: 0.05754880607128143
2023-01-21 09:06:42.538549: step: 1904/531, loss: 0.07989501953125
2023-01-21 09:06:43.671742: step: 1908/531, loss: 0.101422980427742
2023-01-21 09:06:44.785957: step: 1912/531, loss: 0.12306462228298187
2023-01-21 09:06:45.877855: step: 1916/531, loss: 0.10077142715454102
2023-01-21 09:06:47.035341: step: 1920/531, loss: 0.16026315093040466
2023-01-21 09:06:48.157699: step: 1924/531, loss: 0.15832313895225525
2023-01-21 09:06:49.283379: step: 1928/531, loss: 0.11770325154066086
2023-01-21 09:06:50.420104: step: 1932/531, loss: 0.10809460282325745
2023-01-21 09:06:51.560437: step: 1936/531, loss: 0.26179322600364685
2023-01-21 09:06:52.702187: step: 1940/531, loss: 0.04438791424036026
2023-01-21 09:06:53.821286: step: 1944/531, loss: 0.6509518027305603
2023-01-21 09:06:54.951014: step: 1948/531, loss: 0.09031243622303009
2023-01-21 09:06:56.070377: step: 1952/531, loss: 0.7060879468917847
2023-01-21 09:06:57.198048: step: 1956/531, loss: 0.05508151277899742
2023-01-21 09:06:58.309597: step: 1960/531, loss: 0.5473034381866455
2023-01-21 09:06:59.435198: step: 1964/531, loss: 0.30443769693374634
2023-01-21 09:07:00.576604: step: 1968/531, loss: 0.1759936809539795
2023-01-21 09:07:01.702243: step: 1972/531, loss: 0.14455018937587738
2023-01-21 09:07:02.850375: step: 1976/531, loss: 0.752804160118103
2023-01-21 09:07:03.988107: step: 1980/531, loss: 0.18311309814453125
2023-01-21 09:07:05.103122: step: 1984/531, loss: 0.3597634434700012
2023-01-21 09:07:06.220200: step: 1988/531, loss: 0.12116880714893341
2023-01-21 09:07:07.370210: step: 1992/531, loss: 0.9020876884460449
2023-01-21 09:07:08.511784: step: 1996/531, loss: 0.11265754699707031
2023-01-21 09:07:09.602915: step: 2000/531, loss: 0.20572224259376526
2023-01-21 09:07:10.741453: step: 2004/531, loss: 0.5403975248336792
2023-01-21 09:07:11.888751: step: 2008/531, loss: 0.4854414463043213
2023-01-21 09:07:13.034433: step: 2012/531, loss: 0.6149066090583801
2023-01-21 09:07:14.170051: step: 2016/531, loss: 0.1524006873369217
2023-01-21 09:07:15.299361: step: 2020/531, loss: 0.32329440116882324
2023-01-21 09:07:16.422020: step: 2024/531, loss: 0.08343849331140518
2023-01-21 09:07:17.529451: step: 2028/531, loss: 0.22176915407180786
2023-01-21 09:07:18.641635: step: 2032/531, loss: 0.09827204048633575
2023-01-21 09:07:19.797456: step: 2036/531, loss: 0.13515625894069672
2023-01-21 09:07:20.931252: step: 2040/531, loss: 0.16757479310035706
2023-01-21 09:07:22.061205: step: 2044/531, loss: 0.37889060378074646
2023-01-21 09:07:23.198272: step: 2048/531, loss: 0.24546527862548828
2023-01-21 09:07:24.328146: step: 2052/531, loss: 0.651732325553894
2023-01-21 09:07:25.401367: step: 2056/531, loss: 0.6140133738517761
2023-01-21 09:07:26.537303: step: 2060/531, loss: 0.3050972819328308
2023-01-21 09:07:27.662245: step: 2064/531, loss: 0.12994174659252167
2023-01-21 09:07:28.779301: step: 2068/531, loss: 0.528088390827179
2023-01-21 09:07:29.902090: step: 2072/531, loss: 0.0399443656206131
2023-01-21 09:07:31.036930: step: 2076/531, loss: 0.19521847367286682
2023-01-21 09:07:32.170782: step: 2080/531, loss: 0.3238506317138672
2023-01-21 09:07:33.281288: step: 2084/531, loss: 0.8641220331192017
2023-01-21 09:07:34.388631: step: 2088/531, loss: 0.1053767204284668
2023-01-21 09:07:35.483072: step: 2092/531, loss: 0.6582637429237366
2023-01-21 09:07:36.577322: step: 2096/531, loss: 0.12176046520471573
2023-01-21 09:07:37.701644: step: 2100/531, loss: 0.5314443111419678
2023-01-21 09:07:38.840686: step: 2104/531, loss: 0.15437598526477814
2023-01-21 09:07:39.957830: step: 2108/531, loss: 0.7992597222328186
2023-01-21 09:07:41.101424: step: 2112/531, loss: 0.13027337193489075
2023-01-21 09:07:42.220790: step: 2116/531, loss: 0.2880975604057312
2023-01-21 09:07:43.360162: step: 2120/531, loss: 0.06377029418945312
2023-01-21 09:07:44.485520: step: 2124/531, loss: 0.15702953934669495
==================================================
Loss: 0.483
--------------------
Dev: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.71875, 'r': 0.36507936507936506, 'f1': 0.4842105263157895}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.6956521739130435, 'r': 0.4444444444444444, 'f1': 0.5423728813559322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5747001090512541, 'r': 0.7017310252996005, 'f1': 0.6318944844124701}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.530718336483932, 'r': 0.6696481812760883, 'f1': 0.5921434220933298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.8125, 'r': 0.4126984126984127, 'f1': 0.5473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.6956521739130435, 'r': 0.4444444444444444, 'f1': 0.5423728813559322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:08:38.829155: step: 4/531, loss: 0.20924778282642365
2023-01-21 09:08:39.999622: step: 8/531, loss: 0.33616772294044495
2023-01-21 09:08:41.107307: step: 12/531, loss: 0.042319297790527344
2023-01-21 09:08:42.232495: step: 16/531, loss: 8.283539772033691
2023-01-21 09:08:43.328385: step: 20/531, loss: 0.04022035747766495
2023-01-21 09:08:44.450859: step: 24/531, loss: 0.06882859021425247
2023-01-21 09:08:45.589462: step: 28/531, loss: 0.12509828805923462
2023-01-21 09:08:46.721534: step: 32/531, loss: 0.6324887275695801
2023-01-21 09:08:47.852975: step: 36/531, loss: 0.11299276351928711
2023-01-21 09:08:49.002470: step: 40/531, loss: 0.07704886794090271
2023-01-21 09:08:50.116653: step: 44/531, loss: 0.32479286193847656
2023-01-21 09:08:51.249503: step: 48/531, loss: 0.0973147451877594
2023-01-21 09:08:52.395059: step: 52/531, loss: 0.19197535514831543
2023-01-21 09:08:53.532168: step: 56/531, loss: 0.1737435758113861
2023-01-21 09:08:54.663277: step: 60/531, loss: 0.097254179418087
2023-01-21 09:08:55.776444: step: 64/531, loss: 0.08131766319274902
2023-01-21 09:08:56.911620: step: 68/531, loss: 0.9577943682670593
2023-01-21 09:08:58.050953: step: 72/531, loss: 0.16581693291664124
2023-01-21 09:08:59.230909: step: 76/531, loss: 0.07871170341968536
2023-01-21 09:09:00.351419: step: 80/531, loss: 0.14577293395996094
2023-01-21 09:09:01.482160: step: 84/531, loss: 0.1412622481584549
2023-01-21 09:09:02.612354: step: 88/531, loss: 0.7363821268081665
2023-01-21 09:09:03.772834: step: 92/531, loss: 0.22683724761009216
2023-01-21 09:09:04.901179: step: 96/531, loss: 0.05515570566058159
2023-01-21 09:09:06.055293: step: 100/531, loss: 0.10706081986427307
2023-01-21 09:09:07.180215: step: 104/531, loss: 0.05919227749109268
2023-01-21 09:09:08.318868: step: 108/531, loss: 1.2315568923950195
2023-01-21 09:09:09.457825: step: 112/531, loss: 0.711255669593811
2023-01-21 09:09:10.595461: step: 116/531, loss: 1.5955922603607178
2023-01-21 09:09:11.713678: step: 120/531, loss: 0.11847896873950958
2023-01-21 09:09:12.857834: step: 124/531, loss: 0.07389245182275772
2023-01-21 09:09:13.978242: step: 128/531, loss: 0.09024009853601456
2023-01-21 09:09:15.092006: step: 132/531, loss: 0.7096128463745117
2023-01-21 09:09:16.214551: step: 136/531, loss: 0.13612642884254456
2023-01-21 09:09:17.362431: step: 140/531, loss: 0.14436140656471252
2023-01-21 09:09:18.487280: step: 144/531, loss: 0.2555411458015442
2023-01-21 09:09:19.636888: step: 148/531, loss: 0.1854534149169922
2023-01-21 09:09:20.754388: step: 152/531, loss: 5.722158432006836
2023-01-21 09:09:21.879840: step: 156/531, loss: 0.15536102652549744
2023-01-21 09:09:22.992439: step: 160/531, loss: 0.21621212363243103
2023-01-21 09:09:24.100197: step: 164/531, loss: 0.12443169951438904
2023-01-21 09:09:25.204105: step: 168/531, loss: 0.1415562629699707
2023-01-21 09:09:26.330788: step: 172/531, loss: 0.7281516790390015
2023-01-21 09:09:27.470135: step: 176/531, loss: 0.19980435073375702
2023-01-21 09:09:28.598932: step: 180/531, loss: 0.6728843450546265
2023-01-21 09:09:29.743398: step: 184/531, loss: 0.15898753702640533
2023-01-21 09:09:30.862903: step: 188/531, loss: 0.11105690151453018
2023-01-21 09:09:31.977389: step: 192/531, loss: 0.36551544070243835
2023-01-21 09:09:33.103078: step: 196/531, loss: 0.052789025008678436
2023-01-21 09:09:34.211652: step: 200/531, loss: 0.08533172309398651
2023-01-21 09:09:35.347213: step: 204/531, loss: 0.11238765716552734
2023-01-21 09:09:36.457879: step: 208/531, loss: 0.6849081516265869
2023-01-21 09:09:37.559730: step: 212/531, loss: 0.47072678804397583
2023-01-21 09:09:38.686632: step: 216/531, loss: 0.7471441030502319
2023-01-21 09:09:39.808467: step: 220/531, loss: 0.5334821939468384
2023-01-21 09:09:40.943544: step: 224/531, loss: 0.2592759132385254
2023-01-21 09:09:42.100267: step: 228/531, loss: 0.9253948926925659
2023-01-21 09:09:43.231868: step: 232/531, loss: 0.09056291729211807
2023-01-21 09:09:44.340655: step: 236/531, loss: 1.8205885887145996
2023-01-21 09:09:45.466678: step: 240/531, loss: 0.24185581505298615
2023-01-21 09:09:46.597895: step: 244/531, loss: 0.1812501847743988
2023-01-21 09:09:47.768213: step: 248/531, loss: 0.1305214911699295
2023-01-21 09:09:48.871515: step: 252/531, loss: 0.23132172226905823
2023-01-21 09:09:49.984798: step: 256/531, loss: 0.5506876111030579
2023-01-21 09:09:51.097183: step: 260/531, loss: 0.09004230797290802
2023-01-21 09:09:52.237998: step: 264/531, loss: 0.18773241341114044
2023-01-21 09:09:53.365576: step: 268/531, loss: 0.2571328580379486
2023-01-21 09:09:54.503499: step: 272/531, loss: 0.03196907043457031
2023-01-21 09:09:55.610200: step: 276/531, loss: 0.5614147186279297
2023-01-21 09:09:56.712489: step: 280/531, loss: 5.829814434051514
2023-01-21 09:09:57.822906: step: 284/531, loss: 1.4233050346374512
2023-01-21 09:09:58.949799: step: 288/531, loss: 0.14850550889968872
2023-01-21 09:10:00.084228: step: 292/531, loss: 0.031071018427610397
2023-01-21 09:10:01.236251: step: 296/531, loss: 0.08955345302820206
2023-01-21 09:10:02.370804: step: 300/531, loss: 0.135033518075943
2023-01-21 09:10:03.512876: step: 304/531, loss: 0.3570517897605896
2023-01-21 09:10:04.658605: step: 308/531, loss: 0.1132669448852539
2023-01-21 09:10:05.766669: step: 312/531, loss: 0.1917099952697754
2023-01-21 09:10:06.879423: step: 316/531, loss: 0.12852011620998383
2023-01-21 09:10:07.981071: step: 320/531, loss: 0.7748472094535828
2023-01-21 09:10:09.117163: step: 324/531, loss: 0.6677180528640747
2023-01-21 09:10:10.229482: step: 328/531, loss: 0.14297866821289062
2023-01-21 09:10:11.342272: step: 332/531, loss: 0.11147364974021912
2023-01-21 09:10:12.455649: step: 336/531, loss: 0.6438290476799011
2023-01-21 09:10:13.613675: step: 340/531, loss: 0.2291916459798813
2023-01-21 09:10:14.737452: step: 344/531, loss: 0.08800859749317169
2023-01-21 09:10:15.874515: step: 348/531, loss: 0.10606296360492706
2023-01-21 09:10:17.016068: step: 352/531, loss: 1.613391637802124
2023-01-21 09:10:18.131258: step: 356/531, loss: 0.36305904388427734
2023-01-21 09:10:19.241070: step: 360/531, loss: 0.16070961952209473
2023-01-21 09:10:20.377152: step: 364/531, loss: 0.1045873686671257
2023-01-21 09:10:21.506816: step: 368/531, loss: 0.6269897222518921
2023-01-21 09:10:22.634457: step: 372/531, loss: 0.055081795901060104
2023-01-21 09:10:23.787123: step: 376/531, loss: 0.22504273056983948
2023-01-21 09:10:24.948024: step: 380/531, loss: 0.11127491295337677
2023-01-21 09:10:26.093623: step: 384/531, loss: 0.09604225307703018
2023-01-21 09:10:27.199219: step: 388/531, loss: 0.04972877725958824
2023-01-21 09:10:28.324866: step: 392/531, loss: 0.7691006064414978
2023-01-21 09:10:29.442478: step: 396/531, loss: 0.07439041137695312
2023-01-21 09:10:30.572582: step: 400/531, loss: 0.3480495512485504
2023-01-21 09:10:31.669893: step: 404/531, loss: 0.14600592851638794
2023-01-21 09:10:32.788767: step: 408/531, loss: 0.1575869619846344
2023-01-21 09:10:33.905425: step: 412/531, loss: 0.3718557357788086
2023-01-21 09:10:35.009863: step: 416/531, loss: 0.39317190647125244
2023-01-21 09:10:36.137819: step: 420/531, loss: 0.4093666076660156
2023-01-21 09:10:37.280439: step: 424/531, loss: 1.0968222618103027
2023-01-21 09:10:38.399217: step: 428/531, loss: 0.12537908554077148
2023-01-21 09:10:39.534856: step: 432/531, loss: 0.03981904685497284
2023-01-21 09:10:40.660392: step: 436/531, loss: 0.15898437798023224
2023-01-21 09:10:41.771751: step: 440/531, loss: 0.21721288561820984
2023-01-21 09:10:42.911752: step: 444/531, loss: 0.11548252403736115
2023-01-21 09:10:44.014326: step: 448/531, loss: 0.2627193033695221
2023-01-21 09:10:45.159209: step: 452/531, loss: 0.0582522414624691
2023-01-21 09:10:46.299201: step: 456/531, loss: 0.05561819300055504
2023-01-21 09:10:47.427424: step: 460/531, loss: 0.1412040740251541
2023-01-21 09:10:48.528399: step: 464/531, loss: 0.004426288418471813
2023-01-21 09:10:49.665140: step: 468/531, loss: 0.20757563412189484
2023-01-21 09:10:50.801553: step: 472/531, loss: 0.16466303169727325
2023-01-21 09:10:51.904277: step: 476/531, loss: 0.113164521753788
2023-01-21 09:10:53.015857: step: 480/531, loss: 0.3526877760887146
2023-01-21 09:10:54.136502: step: 484/531, loss: 0.24685317277908325
2023-01-21 09:10:55.248608: step: 488/531, loss: 0.051558591425418854
2023-01-21 09:10:56.378227: step: 492/531, loss: 0.19835443794727325
2023-01-21 09:10:57.499207: step: 496/531, loss: 1.2674591541290283
2023-01-21 09:10:58.666642: step: 500/531, loss: 0.08375606685876846
2023-01-21 09:10:59.799304: step: 504/531, loss: 0.632394015789032
2023-01-21 09:11:00.911545: step: 508/531, loss: 0.2275291532278061
2023-01-21 09:11:02.025945: step: 512/531, loss: 0.11012879014015198
2023-01-21 09:11:03.122304: step: 516/531, loss: 0.5363385081291199
2023-01-21 09:11:04.261571: step: 520/531, loss: 0.15113544464111328
2023-01-21 09:11:05.400133: step: 524/531, loss: 0.09087934345006943
2023-01-21 09:11:06.486915: step: 528/531, loss: 0.026700545102357864
2023-01-21 09:11:07.629982: step: 532/531, loss: 0.2245170623064041
2023-01-21 09:11:08.766937: step: 536/531, loss: 0.2834951877593994
2023-01-21 09:11:09.906964: step: 540/531, loss: 0.6439535617828369
2023-01-21 09:11:11.064521: step: 544/531, loss: 0.02203512191772461
2023-01-21 09:11:12.196987: step: 548/531, loss: 0.15543846786022186
2023-01-21 09:11:13.303074: step: 552/531, loss: 0.09425106644630432
2023-01-21 09:11:14.431432: step: 556/531, loss: 0.3638821840286255
2023-01-21 09:11:15.575543: step: 560/531, loss: 0.07064905017614365
2023-01-21 09:11:16.714347: step: 564/531, loss: 0.7152858972549438
2023-01-21 09:11:17.866386: step: 568/531, loss: 0.047632791101932526
2023-01-21 09:11:19.001547: step: 572/531, loss: 0.16318674385547638
2023-01-21 09:11:20.138038: step: 576/531, loss: 0.12817439436912537
2023-01-21 09:11:21.259387: step: 580/531, loss: 1.096173882484436
2023-01-21 09:11:22.384568: step: 584/531, loss: 0.09704256802797318
2023-01-21 09:11:23.494690: step: 588/531, loss: 0.2589954435825348
2023-01-21 09:11:24.637939: step: 592/531, loss: 0.0656011626124382
2023-01-21 09:11:25.742118: step: 596/531, loss: 0.019220566377043724
2023-01-21 09:11:26.843264: step: 600/531, loss: 0.12142118811607361
2023-01-21 09:11:27.959059: step: 604/531, loss: 0.11405091732740402
2023-01-21 09:11:29.064841: step: 608/531, loss: 0.13228702545166016
2023-01-21 09:11:30.180118: step: 612/531, loss: 0.13077107071876526
2023-01-21 09:11:31.315577: step: 616/531, loss: 1.9059685468673706
2023-01-21 09:11:32.431593: step: 620/531, loss: 0.09871216118335724
2023-01-21 09:11:33.631132: step: 624/531, loss: 0.10402616858482361
2023-01-21 09:11:34.789089: step: 628/531, loss: 0.40327155590057373
2023-01-21 09:11:35.905159: step: 632/531, loss: 0.09236516803503036
2023-01-21 09:11:37.000721: step: 636/531, loss: 0.19326673448085785
2023-01-21 09:11:38.145354: step: 640/531, loss: 1.2940990924835205
2023-01-21 09:11:39.312344: step: 644/531, loss: 0.2951418161392212
2023-01-21 09:11:40.412954: step: 648/531, loss: 6.206678867340088
2023-01-21 09:11:41.565271: step: 652/531, loss: 0.8177210092544556
2023-01-21 09:11:42.730400: step: 656/531, loss: 0.09443321824073792
2023-01-21 09:11:43.878251: step: 660/531, loss: 0.31081074476242065
2023-01-21 09:11:44.972777: step: 664/531, loss: 0.13477078080177307
2023-01-21 09:11:46.127567: step: 668/531, loss: 0.05327220261096954
2023-01-21 09:11:47.285247: step: 672/531, loss: 0.14896708726882935
2023-01-21 09:11:48.400629: step: 676/531, loss: 0.9148578643798828
2023-01-21 09:11:49.513816: step: 680/531, loss: 0.24008570611476898
2023-01-21 09:11:50.617249: step: 684/531, loss: 0.13330745697021484
2023-01-21 09:11:51.716623: step: 688/531, loss: 0.13182926177978516
2023-01-21 09:11:52.860588: step: 692/531, loss: 0.7367156147956848
2023-01-21 09:11:53.988017: step: 696/531, loss: 0.1440873146057129
2023-01-21 09:11:55.131550: step: 700/531, loss: 0.1531650573015213
2023-01-21 09:11:56.259084: step: 704/531, loss: 0.13811349868774414
2023-01-21 09:11:57.350543: step: 708/531, loss: 0.18078504502773285
2023-01-21 09:11:58.487928: step: 712/531, loss: 0.34571951627731323
2023-01-21 09:11:59.608957: step: 716/531, loss: 0.12638406455516815
2023-01-21 09:12:00.716966: step: 720/531, loss: 0.9698561429977417
2023-01-21 09:12:01.843627: step: 724/531, loss: 0.23368030786514282
2023-01-21 09:12:02.964588: step: 728/531, loss: 0.5958910584449768
2023-01-21 09:12:04.085938: step: 732/531, loss: 0.11590452492237091
2023-01-21 09:12:05.186567: step: 736/531, loss: 0.08392305672168732
2023-01-21 09:12:06.294956: step: 740/531, loss: 0.212868794798851
2023-01-21 09:12:07.408797: step: 744/531, loss: 0.25697699189186096
2023-01-21 09:12:08.537313: step: 748/531, loss: 1.6109669208526611
2023-01-21 09:12:09.680376: step: 752/531, loss: 0.0461517795920372
2023-01-21 09:12:10.798650: step: 756/531, loss: 0.2585142254829407
2023-01-21 09:12:11.951776: step: 760/531, loss: 0.22301316261291504
2023-01-21 09:12:13.072074: step: 764/531, loss: 0.08022680133581161
2023-01-21 09:12:14.181366: step: 768/531, loss: 0.513279914855957
2023-01-21 09:12:15.315601: step: 772/531, loss: 0.2278485894203186
2023-01-21 09:12:16.437209: step: 776/531, loss: 0.1086762472987175
2023-01-21 09:12:17.552563: step: 780/531, loss: 0.13428373634815216
2023-01-21 09:12:18.652764: step: 784/531, loss: 0.12129803001880646
2023-01-21 09:12:19.778739: step: 788/531, loss: 0.049597643315792084
2023-01-21 09:12:20.899175: step: 792/531, loss: 0.1002727597951889
2023-01-21 09:12:22.041701: step: 796/531, loss: 0.7631046175956726
2023-01-21 09:12:23.176108: step: 800/531, loss: 0.08250617980957031
2023-01-21 09:12:24.310257: step: 804/531, loss: 0.15585081279277802
2023-01-21 09:12:25.449446: step: 808/531, loss: 0.12457437813282013
2023-01-21 09:12:26.570358: step: 812/531, loss: 0.14095354080200195
2023-01-21 09:12:27.713582: step: 816/531, loss: 0.24597658216953278
2023-01-21 09:12:28.862438: step: 820/531, loss: 0.061493776738643646
2023-01-21 09:12:29.974782: step: 824/531, loss: 0.14348164200782776
2023-01-21 09:12:31.110790: step: 828/531, loss: 0.06926098465919495
2023-01-21 09:12:32.228066: step: 832/531, loss: 0.14651158452033997
2023-01-21 09:12:33.369235: step: 836/531, loss: 0.6801068782806396
2023-01-21 09:12:34.509164: step: 840/531, loss: 0.07741355895996094
2023-01-21 09:12:35.641523: step: 844/531, loss: 0.11129383742809296
2023-01-21 09:12:36.757212: step: 848/531, loss: 0.13678894937038422
2023-01-21 09:12:37.880581: step: 852/531, loss: 0.09396753460168839
2023-01-21 09:12:39.023155: step: 856/531, loss: 0.17143774032592773
2023-01-21 09:12:40.171405: step: 860/531, loss: 0.14983521401882172
2023-01-21 09:12:41.262226: step: 864/531, loss: 0.03581710159778595
2023-01-21 09:12:42.385638: step: 868/531, loss: 0.060904692858457565
2023-01-21 09:12:43.566167: step: 872/531, loss: 0.7633885145187378
2023-01-21 09:12:44.682286: step: 876/531, loss: 0.8558177947998047
2023-01-21 09:12:45.824742: step: 880/531, loss: 0.649976909160614
2023-01-21 09:12:46.927453: step: 884/531, loss: 0.21141234040260315
2023-01-21 09:12:48.078308: step: 888/531, loss: 0.21001359820365906
2023-01-21 09:12:49.198206: step: 892/531, loss: 0.7254459857940674
2023-01-21 09:12:50.322654: step: 896/531, loss: 0.28088387846946716
2023-01-21 09:12:51.446883: step: 900/531, loss: 0.053021907806396484
2023-01-21 09:12:52.591908: step: 904/531, loss: 0.10650554299354553
2023-01-21 09:12:53.707131: step: 908/531, loss: 0.31854599714279175
2023-01-21 09:12:54.847098: step: 912/531, loss: 0.4917248785495758
2023-01-21 09:12:55.946443: step: 916/531, loss: 0.05721016228199005
2023-01-21 09:12:57.043178: step: 920/531, loss: 0.043104078620672226
2023-01-21 09:12:58.164619: step: 924/531, loss: 0.7895603179931641
2023-01-21 09:12:59.285597: step: 928/531, loss: 0.16299457848072052
2023-01-21 09:13:00.421714: step: 932/531, loss: 0.0969444215297699
2023-01-21 09:13:01.545460: step: 936/531, loss: 0.07045784592628479
2023-01-21 09:13:02.664550: step: 940/531, loss: 0.13676562905311584
2023-01-21 09:13:03.773646: step: 944/531, loss: 0.3364361822605133
2023-01-21 09:13:04.911372: step: 948/531, loss: 0.6041025519371033
2023-01-21 09:13:06.020078: step: 952/531, loss: 0.12712879478931427
2023-01-21 09:13:07.131840: step: 956/531, loss: 0.7844495177268982
2023-01-21 09:13:08.255126: step: 960/531, loss: 0.3680562973022461
2023-01-21 09:13:09.382713: step: 964/531, loss: 0.819412350654602
2023-01-21 09:13:10.482393: step: 968/531, loss: 0.2795478403568268
2023-01-21 09:13:11.592329: step: 972/531, loss: 0.6028388738632202
2023-01-21 09:13:12.705285: step: 976/531, loss: 0.26359063386917114
2023-01-21 09:13:13.826407: step: 980/531, loss: 0.9468530416488647
2023-01-21 09:13:14.959778: step: 984/531, loss: 0.1083495169878006
2023-01-21 09:13:16.108204: step: 988/531, loss: 0.11399345844984055
2023-01-21 09:13:17.224802: step: 992/531, loss: 1.3465616703033447
2023-01-21 09:13:18.345488: step: 996/531, loss: 0.9024931788444519
2023-01-21 09:13:19.493490: step: 1000/531, loss: 0.5502773523330688
2023-01-21 09:13:20.628294: step: 1004/531, loss: 0.8719649910926819
2023-01-21 09:13:21.792359: step: 1008/531, loss: 0.6857746243476868
2023-01-21 09:13:22.931588: step: 1012/531, loss: 0.30992692708969116
2023-01-21 09:13:24.057324: step: 1016/531, loss: 2.2987313270568848
2023-01-21 09:13:25.149521: step: 1020/531, loss: 0.04828248172998428
2023-01-21 09:13:26.291195: step: 1024/531, loss: 0.03621535748243332
2023-01-21 09:13:27.416699: step: 1028/531, loss: 0.155064195394516
2023-01-21 09:13:28.549378: step: 1032/531, loss: 0.17044906318187714
2023-01-21 09:13:29.654302: step: 1036/531, loss: 0.2105582356452942
2023-01-21 09:13:30.810822: step: 1040/531, loss: 0.6857356429100037
2023-01-21 09:13:31.951384: step: 1044/531, loss: 0.4065222144126892
2023-01-21 09:13:33.094523: step: 1048/531, loss: 0.17205926775932312
2023-01-21 09:13:34.223606: step: 1052/531, loss: 0.14728470146656036
2023-01-21 09:13:35.340569: step: 1056/531, loss: 0.8519327044487
2023-01-21 09:13:36.462595: step: 1060/531, loss: 0.11078529059886932
2023-01-21 09:13:37.585239: step: 1064/531, loss: 0.08406877517700195
2023-01-21 09:13:38.733145: step: 1068/531, loss: 0.3707761764526367
2023-01-21 09:13:39.847670: step: 1072/531, loss: 0.25494199991226196
2023-01-21 09:13:40.962898: step: 1076/531, loss: 0.14766664803028107
2023-01-21 09:13:42.098280: step: 1080/531, loss: 0.08800826221704483
2023-01-21 09:13:43.269390: step: 1084/531, loss: 0.05193691700696945
2023-01-21 09:13:44.407003: step: 1088/531, loss: 0.15417805314064026
2023-01-21 09:13:45.535566: step: 1092/531, loss: 0.7052686214447021
2023-01-21 09:13:46.698340: step: 1096/531, loss: 0.4181533753871918
2023-01-21 09:13:47.846898: step: 1100/531, loss: 0.41178396344184875
2023-01-21 09:13:48.990771: step: 1104/531, loss: 0.12480497360229492
2023-01-21 09:13:50.102787: step: 1108/531, loss: 5.68168306350708
2023-01-21 09:13:51.232532: step: 1112/531, loss: 0.014397859573364258
2023-01-21 09:13:52.374039: step: 1116/531, loss: 0.22462302446365356
2023-01-21 09:13:53.488968: step: 1120/531, loss: 0.0618349052965641
2023-01-21 09:13:54.596783: step: 1124/531, loss: 0.1266128122806549
2023-01-21 09:13:55.685536: step: 1128/531, loss: 0.0977567732334137
2023-01-21 09:13:56.810932: step: 1132/531, loss: 0.15257807075977325
2023-01-21 09:13:57.950027: step: 1136/531, loss: 0.10911617428064346
2023-01-21 09:13:59.060542: step: 1140/531, loss: 0.7101627588272095
2023-01-21 09:14:00.168986: step: 1144/531, loss: 0.2168382704257965
2023-01-21 09:14:01.282133: step: 1148/531, loss: 0.5644658207893372
2023-01-21 09:14:02.409785: step: 1152/531, loss: 0.6557202935218811
2023-01-21 09:14:03.518695: step: 1156/531, loss: 0.20778541266918182
2023-01-21 09:14:04.664257: step: 1160/531, loss: 0.14528942108154297
2023-01-21 09:14:05.796515: step: 1164/531, loss: 0.5801851749420166
2023-01-21 09:14:06.926042: step: 1168/531, loss: 0.47758749127388
2023-01-21 09:14:08.063297: step: 1172/531, loss: 0.08182573318481445
2023-01-21 09:14:09.210387: step: 1176/531, loss: 0.080461785197258
2023-01-21 09:14:10.326327: step: 1180/531, loss: 0.054553888738155365
2023-01-21 09:14:11.432335: step: 1184/531, loss: 0.04999861866235733
2023-01-21 09:14:12.548031: step: 1188/531, loss: 0.041826628148555756
2023-01-21 09:14:13.660607: step: 1192/531, loss: 0.3056960999965668
2023-01-21 09:14:14.799490: step: 1196/531, loss: 0.3413318395614624
2023-01-21 09:14:15.966897: step: 1200/531, loss: 0.0916716605424881
2023-01-21 09:14:17.084904: step: 1204/531, loss: 0.09605570137500763
2023-01-21 09:14:18.213795: step: 1208/531, loss: 0.7817696332931519
2023-01-21 09:14:19.315113: step: 1212/531, loss: 0.13069410622119904
2023-01-21 09:14:20.428707: step: 1216/531, loss: 0.5280987620353699
2023-01-21 09:14:21.528887: step: 1220/531, loss: 0.4246279001235962
2023-01-21 09:14:22.663556: step: 1224/531, loss: 0.45986607670783997
2023-01-21 09:14:23.768972: step: 1228/531, loss: 0.3266821801662445
2023-01-21 09:14:24.896225: step: 1232/531, loss: 0.29743510484695435
2023-01-21 09:14:26.008617: step: 1236/531, loss: 0.16992712020874023
2023-01-21 09:14:27.140089: step: 1240/531, loss: 0.02969083935022354
2023-01-21 09:14:28.314962: step: 1244/531, loss: 0.4778744578361511
2023-01-21 09:14:29.422810: step: 1248/531, loss: 0.088726706802845
2023-01-21 09:14:30.536841: step: 1252/531, loss: 0.17096376419067383
2023-01-21 09:14:31.664402: step: 1256/531, loss: 0.16469764709472656
2023-01-21 09:14:32.798037: step: 1260/531, loss: 1.0106450319290161
2023-01-21 09:14:33.921149: step: 1264/531, loss: 0.09521637111902237
2023-01-21 09:14:35.062140: step: 1268/531, loss: 0.4491819441318512
2023-01-21 09:14:36.193764: step: 1272/531, loss: 0.12090234458446503
2023-01-21 09:14:37.339518: step: 1276/531, loss: 0.0921357199549675
2023-01-21 09:14:38.456878: step: 1280/531, loss: 0.29400739073753357
2023-01-21 09:14:39.571905: step: 1284/531, loss: 0.1099323034286499
2023-01-21 09:14:40.702967: step: 1288/531, loss: 1.3374457359313965
2023-01-21 09:14:41.830945: step: 1292/531, loss: 0.07441673427820206
2023-01-21 09:14:42.979225: step: 1296/531, loss: 0.21961519122123718
2023-01-21 09:14:44.087826: step: 1300/531, loss: 0.21229895949363708
2023-01-21 09:14:45.206393: step: 1304/531, loss: 0.1740400195121765
2023-01-21 09:14:46.370427: step: 1308/531, loss: 0.6765531301498413
2023-01-21 09:14:47.517614: step: 1312/531, loss: 0.6090461015701294
2023-01-21 09:14:48.625406: step: 1316/531, loss: 0.06302328407764435
2023-01-21 09:14:49.734796: step: 1320/531, loss: 0.20242176949977875
2023-01-21 09:14:50.869423: step: 1324/531, loss: 0.6414319276809692
2023-01-21 09:14:52.009254: step: 1328/531, loss: 0.5580018758773804
2023-01-21 09:14:53.132149: step: 1332/531, loss: 0.03660574182868004
2023-01-21 09:14:54.241244: step: 1336/531, loss: 0.09093776345252991
2023-01-21 09:14:55.389210: step: 1340/531, loss: 0.10649824142456055
2023-01-21 09:14:56.529673: step: 1344/531, loss: 0.24700093269348145
2023-01-21 09:14:57.666317: step: 1348/531, loss: 0.1675254851579666
2023-01-21 09:14:58.788058: step: 1352/531, loss: 0.11417227238416672
2023-01-21 09:14:59.910590: step: 1356/531, loss: 0.06530604511499405
2023-01-21 09:15:01.066223: step: 1360/531, loss: 0.09662504494190216
2023-01-21 09:15:02.167402: step: 1364/531, loss: 0.09656266868114471
2023-01-21 09:15:03.285871: step: 1368/531, loss: 0.13258257508277893
2023-01-21 09:15:04.411095: step: 1372/531, loss: 0.07394042611122131
2023-01-21 09:15:05.556104: step: 1376/531, loss: 0.09123239666223526
2023-01-21 09:15:06.673368: step: 1380/531, loss: 0.3923642039299011
2023-01-21 09:15:07.814533: step: 1384/531, loss: 1.2973023653030396
2023-01-21 09:15:08.951180: step: 1388/531, loss: 0.08193626254796982
2023-01-21 09:15:10.088611: step: 1392/531, loss: 0.07066097110509872
2023-01-21 09:15:11.203988: step: 1396/531, loss: 0.5165959596633911
2023-01-21 09:15:12.383673: step: 1400/531, loss: 0.6549649238586426
2023-01-21 09:15:13.501330: step: 1404/531, loss: 0.5978779196739197
2023-01-21 09:15:14.620976: step: 1408/531, loss: 0.3496781587600708
2023-01-21 09:15:15.751044: step: 1412/531, loss: 0.5873646140098572
2023-01-21 09:15:16.862645: step: 1416/531, loss: 0.14626769721508026
2023-01-21 09:15:17.973121: step: 1420/531, loss: 0.13425074517726898
2023-01-21 09:15:19.079941: step: 1424/531, loss: 0.28182631731033325
2023-01-21 09:15:20.214976: step: 1428/531, loss: 0.6556992530822754
2023-01-21 09:15:21.337442: step: 1432/531, loss: 0.08122219890356064
2023-01-21 09:15:22.455482: step: 1436/531, loss: 3.662775754928589
2023-01-21 09:15:23.558079: step: 1440/531, loss: 0.10315761715173721
2023-01-21 09:15:24.718560: step: 1444/531, loss: 0.16700410842895508
2023-01-21 09:15:25.804440: step: 1448/531, loss: 0.139937162399292
2023-01-21 09:15:26.910254: step: 1452/531, loss: 0.4600054919719696
2023-01-21 09:15:28.028007: step: 1456/531, loss: 0.05763426050543785
2023-01-21 09:15:29.147604: step: 1460/531, loss: 0.74662846326828
2023-01-21 09:15:30.279087: step: 1464/531, loss: 0.40083014965057373
2023-01-21 09:15:31.411181: step: 1468/531, loss: 0.3536946475505829
2023-01-21 09:15:32.517376: step: 1472/531, loss: 0.10159354656934738
2023-01-21 09:15:33.634202: step: 1476/531, loss: 0.2691704332828522
2023-01-21 09:15:34.741470: step: 1480/531, loss: 0.6508985757827759
2023-01-21 09:15:35.878180: step: 1484/531, loss: 0.16213497519493103
2023-01-21 09:15:37.033684: step: 1488/531, loss: 0.13104447722434998
2023-01-21 09:15:38.175179: step: 1492/531, loss: 0.4676194190979004
2023-01-21 09:15:39.314269: step: 1496/531, loss: 0.13090524077415466
2023-01-21 09:15:40.428214: step: 1500/531, loss: 0.295690655708313
2023-01-21 09:15:41.539667: step: 1504/531, loss: 0.10624993592500687
2023-01-21 09:15:42.683870: step: 1508/531, loss: 0.3152994215488434
2023-01-21 09:15:43.786396: step: 1512/531, loss: 0.5497206449508667
2023-01-21 09:15:44.896389: step: 1516/531, loss: 0.5568131804466248
2023-01-21 09:15:46.015083: step: 1520/531, loss: 0.13320913910865784
2023-01-21 09:15:47.147601: step: 1524/531, loss: 0.37717312574386597
2023-01-21 09:15:48.288054: step: 1528/531, loss: 0.10049843788146973
2023-01-21 09:15:49.427188: step: 1532/531, loss: 0.30002593994140625
2023-01-21 09:15:50.524369: step: 1536/531, loss: 0.2790975570678711
2023-01-21 09:15:51.663361: step: 1540/531, loss: 0.19938716292381287
2023-01-21 09:15:52.797850: step: 1544/531, loss: 0.3546084761619568
2023-01-21 09:15:53.903654: step: 1548/531, loss: 0.005626106634736061
2023-01-21 09:15:55.065103: step: 1552/531, loss: 0.9757555723190308
2023-01-21 09:15:56.183807: step: 1556/531, loss: 0.7603006362915039
2023-01-21 09:15:57.335434: step: 1560/531, loss: 1.0087209939956665
2023-01-21 09:15:58.472870: step: 1564/531, loss: 2.440735340118408
2023-01-21 09:15:59.606144: step: 1568/531, loss: 0.025527238845825195
2023-01-21 09:16:00.696670: step: 1572/531, loss: 0.03502168506383896
2023-01-21 09:16:01.835798: step: 1576/531, loss: 0.23762908577919006
2023-01-21 09:16:02.955107: step: 1580/531, loss: 0.05060539394617081
2023-01-21 09:16:04.076493: step: 1584/531, loss: 0.46256598830223083
2023-01-21 09:16:05.194032: step: 1588/531, loss: 0.7527855038642883
2023-01-21 09:16:06.334706: step: 1592/531, loss: 0.700222373008728
2023-01-21 09:16:07.472582: step: 1596/531, loss: 0.1076175719499588
2023-01-21 09:16:08.578881: step: 1600/531, loss: 0.2346941977739334
2023-01-21 09:16:09.694183: step: 1604/531, loss: 0.19995194673538208
2023-01-21 09:16:10.825030: step: 1608/531, loss: 0.09300251305103302
2023-01-21 09:16:11.945521: step: 1612/531, loss: 0.7779393196105957
2023-01-21 09:16:13.068157: step: 1616/531, loss: 0.024361802265048027
2023-01-21 09:16:14.182594: step: 1620/531, loss: 0.846703827381134
2023-01-21 09:16:15.299143: step: 1624/531, loss: 0.3886374533176422
2023-01-21 09:16:16.409821: step: 1628/531, loss: 0.22510060667991638
2023-01-21 09:16:17.530716: step: 1632/531, loss: 0.10726480931043625
2023-01-21 09:16:18.644174: step: 1636/531, loss: 0.1618444323539734
2023-01-21 09:16:19.756910: step: 1640/531, loss: 0.07965681701898575
2023-01-21 09:16:20.866781: step: 1644/531, loss: 0.24817800521850586
2023-01-21 09:16:21.956191: step: 1648/531, loss: 0.39364901185035706
2023-01-21 09:16:23.077482: step: 1652/531, loss: 0.9929062724113464
2023-01-21 09:16:24.186303: step: 1656/531, loss: 2.6192328929901123
2023-01-21 09:16:25.338383: step: 1660/531, loss: 0.6866773962974548
2023-01-21 09:16:26.488569: step: 1664/531, loss: 0.1754910945892334
2023-01-21 09:16:27.587106: step: 1668/531, loss: 0.07648658752441406
2023-01-21 09:16:28.735605: step: 1672/531, loss: 0.23588821291923523
2023-01-21 09:16:29.861237: step: 1676/531, loss: 1.1988518238067627
2023-01-21 09:16:30.969521: step: 1680/531, loss: 0.266082763671875
2023-01-21 09:16:32.071027: step: 1684/531, loss: 0.16698479652404785
2023-01-21 09:16:33.190638: step: 1688/531, loss: 0.2625657320022583
2023-01-21 09:16:34.328747: step: 1692/531, loss: 0.0856928825378418
2023-01-21 09:16:35.481598: step: 1696/531, loss: 0.1346217691898346
2023-01-21 09:16:36.608682: step: 1700/531, loss: 0.20297470688819885
2023-01-21 09:16:37.734375: step: 1704/531, loss: 0.1562003195285797
2023-01-21 09:16:38.847106: step: 1708/531, loss: 0.07241010665893555
2023-01-21 09:16:39.983380: step: 1712/531, loss: 0.2211158275604248
2023-01-21 09:16:41.097590: step: 1716/531, loss: 0.02001185342669487
2023-01-21 09:16:42.186534: step: 1720/531, loss: 0.08154688030481339
2023-01-21 09:16:43.296344: step: 1724/531, loss: 0.30368930101394653
2023-01-21 09:16:44.421557: step: 1728/531, loss: 0.217662051320076
2023-01-21 09:16:45.554069: step: 1732/531, loss: 0.05589735507965088
2023-01-21 09:16:46.676990: step: 1736/531, loss: 0.22880081832408905
2023-01-21 09:16:47.813252: step: 1740/531, loss: 0.6000949144363403
2023-01-21 09:16:48.936299: step: 1744/531, loss: 0.1450720876455307
2023-01-21 09:16:50.044386: step: 1748/531, loss: 0.2290956974029541
2023-01-21 09:16:51.159190: step: 1752/531, loss: 0.022517014294862747
2023-01-21 09:16:52.277882: step: 1756/531, loss: 0.26492661237716675
2023-01-21 09:16:53.437160: step: 1760/531, loss: 0.09574466198682785
2023-01-21 09:16:54.551639: step: 1764/531, loss: 0.5451765060424805
2023-01-21 09:16:55.685753: step: 1768/531, loss: 0.23022547364234924
2023-01-21 09:16:56.850834: step: 1772/531, loss: 0.7778403759002686
2023-01-21 09:16:58.000906: step: 1776/531, loss: 0.038529351353645325
2023-01-21 09:16:59.148456: step: 1780/531, loss: 0.1612699031829834
2023-01-21 09:17:00.270138: step: 1784/531, loss: 0.11677742004394531
2023-01-21 09:17:01.402473: step: 1788/531, loss: 0.19737768173217773
2023-01-21 09:17:02.522415: step: 1792/531, loss: 0.11662693321704865
2023-01-21 09:17:03.637609: step: 1796/531, loss: 0.27351251244544983
2023-01-21 09:17:04.755785: step: 1800/531, loss: 0.08493033051490784
2023-01-21 09:17:05.875710: step: 1804/531, loss: 0.23884770274162292
2023-01-21 09:17:06.969338: step: 1808/531, loss: 0.3763754963874817
2023-01-21 09:17:08.127857: step: 1812/531, loss: 0.8610997796058655
2023-01-21 09:17:09.325540: step: 1816/531, loss: 0.28109779953956604
2023-01-21 09:17:10.438855: step: 1820/531, loss: 0.14995689690113068
2023-01-21 09:17:11.553033: step: 1824/531, loss: 0.1383594572544098
2023-01-21 09:17:12.690272: step: 1828/531, loss: 0.3315194845199585
2023-01-21 09:17:13.801048: step: 1832/531, loss: 0.6067302823066711
2023-01-21 09:17:14.923009: step: 1836/531, loss: 0.35284996032714844
2023-01-21 09:17:16.051788: step: 1840/531, loss: 0.12823915481567383
2023-01-21 09:17:17.181424: step: 1844/531, loss: 0.04045300558209419
2023-01-21 09:17:18.290314: step: 1848/531, loss: 0.24100752174854279
2023-01-21 09:17:19.408239: step: 1852/531, loss: 0.40012702345848083
2023-01-21 09:17:20.539928: step: 1856/531, loss: 0.18638353049755096
2023-01-21 09:17:21.643596: step: 1860/531, loss: 0.07514981925487518
2023-01-21 09:17:22.783205: step: 1864/531, loss: 0.2203844040632248
2023-01-21 09:17:23.923848: step: 1868/531, loss: 0.1560761034488678
2023-01-21 09:17:25.045286: step: 1872/531, loss: 0.5877777338027954
2023-01-21 09:17:26.147306: step: 1876/531, loss: 0.21020327508449554
2023-01-21 09:17:27.270895: step: 1880/531, loss: 0.4344820976257324
2023-01-21 09:17:28.412793: step: 1884/531, loss: 3.293607234954834
2023-01-21 09:17:29.514692: step: 1888/531, loss: 0.652442216873169
2023-01-21 09:17:30.613557: step: 1892/531, loss: 0.3659190535545349
2023-01-21 09:17:31.720823: step: 1896/531, loss: 0.18559308350086212
2023-01-21 09:17:32.834803: step: 1900/531, loss: 1.751516342163086
2023-01-21 09:17:33.967693: step: 1904/531, loss: 0.8812487125396729
2023-01-21 09:17:35.106238: step: 1908/531, loss: 0.40928924083709717
2023-01-21 09:17:36.241073: step: 1912/531, loss: 0.3764389157295227
2023-01-21 09:17:37.357313: step: 1916/531, loss: 0.11168127506971359
2023-01-21 09:17:38.505511: step: 1920/531, loss: 0.29050570726394653
2023-01-21 09:17:39.624423: step: 1924/531, loss: 0.31890085339546204
2023-01-21 09:17:40.735816: step: 1928/531, loss: 0.6248596906661987
2023-01-21 09:17:41.873056: step: 1932/531, loss: 0.043284133076667786
2023-01-21 09:17:42.987900: step: 1936/531, loss: 0.13437804579734802
2023-01-21 09:17:44.146972: step: 1940/531, loss: 0.23680981993675232
2023-01-21 09:17:45.275074: step: 1944/531, loss: 0.7789955139160156
2023-01-21 09:17:46.407115: step: 1948/531, loss: 0.18439841270446777
2023-01-21 09:17:47.552300: step: 1952/531, loss: 0.09562158584594727
2023-01-21 09:17:48.664458: step: 1956/531, loss: 0.250238299369812
2023-01-21 09:17:49.765274: step: 1960/531, loss: 0.007459831424057484
2023-01-21 09:17:50.888276: step: 1964/531, loss: 0.11854877322912216
2023-01-21 09:17:51.991204: step: 1968/531, loss: 1.391023874282837
2023-01-21 09:17:53.126665: step: 1972/531, loss: 0.10419883579015732
2023-01-21 09:17:54.251422: step: 1976/531, loss: 0.3989860415458679
2023-01-21 09:17:55.393303: step: 1980/531, loss: 0.16777630150318146
2023-01-21 09:17:56.528926: step: 1984/531, loss: 0.6184223294258118
2023-01-21 09:17:57.658695: step: 1988/531, loss: 0.09461212158203125
2023-01-21 09:17:58.761903: step: 1992/531, loss: 0.34774529933929443
2023-01-21 09:17:59.852563: step: 1996/531, loss: 3.4562437534332275
2023-01-21 09:18:00.968554: step: 2000/531, loss: 0.2627391815185547
2023-01-21 09:18:02.094178: step: 2004/531, loss: 1.653003454208374
2023-01-21 09:18:03.220986: step: 2008/531, loss: 0.08642206341028214
2023-01-21 09:18:04.358034: step: 2012/531, loss: 0.5813787579536438
2023-01-21 09:18:05.491304: step: 2016/531, loss: 0.6316620707511902
2023-01-21 09:18:06.622866: step: 2020/531, loss: 1.0356746912002563
2023-01-21 09:18:07.714307: step: 2024/531, loss: 0.1543656885623932
2023-01-21 09:18:08.822302: step: 2028/531, loss: 0.3369404077529907
2023-01-21 09:18:09.951459: step: 2032/531, loss: 0.24396809935569763
2023-01-21 09:18:11.065185: step: 2036/531, loss: 0.5506110191345215
2023-01-21 09:18:12.161317: step: 2040/531, loss: 0.5011934041976929
2023-01-21 09:18:13.293356: step: 2044/531, loss: 0.39471155405044556
2023-01-21 09:18:14.418056: step: 2048/531, loss: 0.14521732926368713
2023-01-21 09:18:15.532837: step: 2052/531, loss: 1.0103720426559448
2023-01-21 09:18:16.654582: step: 2056/531, loss: 1.0780736207962036
2023-01-21 09:18:17.777252: step: 2060/531, loss: 0.30792713165283203
2023-01-21 09:18:18.887901: step: 2064/531, loss: 0.5562599897384644
2023-01-21 09:18:20.001917: step: 2068/531, loss: 0.41382914781570435
2023-01-21 09:18:21.120438: step: 2072/531, loss: 0.31271201372146606
2023-01-21 09:18:22.243821: step: 2076/531, loss: 0.048189926892519
2023-01-21 09:18:23.381298: step: 2080/531, loss: 0.208033949136734
2023-01-21 09:18:24.504474: step: 2084/531, loss: 0.03415379673242569
2023-01-21 09:18:25.648878: step: 2088/531, loss: 0.18081635236740112
2023-01-21 09:18:26.778362: step: 2092/531, loss: 0.15192671120166779
2023-01-21 09:18:27.880124: step: 2096/531, loss: 0.19004955887794495
2023-01-21 09:18:28.991517: step: 2100/531, loss: 0.03775153309106827
2023-01-21 09:18:30.116974: step: 2104/531, loss: 0.498241126537323
2023-01-21 09:18:31.227072: step: 2108/531, loss: 0.1664467453956604
2023-01-21 09:18:32.321940: step: 2112/531, loss: 0.1313120424747467
2023-01-21 09:18:33.461217: step: 2116/531, loss: 0.3278893530368805
2023-01-21 09:18:34.605567: step: 2120/531, loss: 0.1384870558977127
2023-01-21 09:18:35.729215: step: 2124/531, loss: 0.14387187361717224
==================================================
Loss: 0.404
--------------------
Dev: {'event': {'p': 0.624384236453202, 'r': 0.6750998668442078, 'f1': 0.6487523992322456}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6409844836811129, 'r': 0.714370900417412, 'f1': 0.6756909193457418}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.6515151515151515, 'r': 0.7962962962962963, 'f1': 0.7166666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.34615384615384615, 'r': 0.25, 'f1': 0.2903225806451613}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.624384236453202, 'r': 0.6750998668442078, 'f1': 0.6487523992322456}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.6409844836811129, 'r': 0.714370900417412, 'f1': 0.6756909193457418}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.6956521739130435, 'r': 0.4444444444444444, 'f1': 0.5423728813559322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:19:23.663717: step: 4/531, loss: 0.13327942788600922
2023-01-21 09:19:24.796089: step: 8/531, loss: 0.07551944255828857
2023-01-21 09:19:25.916999: step: 12/531, loss: 2.286137104034424
2023-01-21 09:19:27.048405: step: 16/531, loss: 0.17033815383911133
2023-01-21 09:19:28.162098: step: 20/531, loss: 0.16239529848098755
2023-01-21 09:19:29.282044: step: 24/531, loss: 0.05642290413379669
2023-01-21 09:19:30.404152: step: 28/531, loss: 0.08547820895910263
2023-01-21 09:19:31.524529: step: 32/531, loss: 0.10226593166589737
2023-01-21 09:19:32.607952: step: 36/531, loss: 0.06672248989343643
2023-01-21 09:19:33.714065: step: 40/531, loss: 0.0877053290605545
2023-01-21 09:19:34.829762: step: 44/531, loss: 0.0523744598031044
2023-01-21 09:19:35.938023: step: 48/531, loss: 0.23877525329589844
2023-01-21 09:19:37.048954: step: 52/531, loss: 0.31593093276023865
2023-01-21 09:19:38.208543: step: 56/531, loss: 4.361067295074463
2023-01-21 09:19:39.327616: step: 60/531, loss: 0.17816415429115295
2023-01-21 09:19:40.453956: step: 64/531, loss: 0.10122337192296982
2023-01-21 09:19:41.595341: step: 68/531, loss: 0.12873688340187073
2023-01-21 09:19:42.737537: step: 72/531, loss: 0.09878092259168625
2023-01-21 09:19:43.883285: step: 76/531, loss: 0.07462453842163086
2023-01-21 09:19:45.002072: step: 80/531, loss: 1.0296183824539185
2023-01-21 09:19:46.140247: step: 84/531, loss: 0.21318235993385315
2023-01-21 09:19:47.288833: step: 88/531, loss: 0.5464677810668945
2023-01-21 09:19:48.428391: step: 92/531, loss: 0.08990707993507385
2023-01-21 09:19:49.566779: step: 96/531, loss: 0.19647157192230225
2023-01-21 09:19:50.693282: step: 100/531, loss: 0.05043353885412216
2023-01-21 09:19:51.809663: step: 104/531, loss: 0.025876427069306374
2023-01-21 09:19:52.945598: step: 108/531, loss: 0.09851732850074768
2023-01-21 09:19:54.059306: step: 112/531, loss: 0.10849341750144958
2023-01-21 09:19:55.189526: step: 116/531, loss: 0.23804521560668945
2023-01-21 09:19:56.304359: step: 120/531, loss: 0.7247149348258972
2023-01-21 09:19:57.438698: step: 124/531, loss: 0.27154821157455444
2023-01-21 09:19:58.564120: step: 128/531, loss: 0.1360892355442047
2023-01-21 09:19:59.683184: step: 132/531, loss: 0.5307134389877319
2023-01-21 09:20:00.792323: step: 136/531, loss: 0.059553682804107666
2023-01-21 09:20:01.883529: step: 140/531, loss: 0.1077481359243393
2023-01-21 09:20:03.001846: step: 144/531, loss: 0.43255600333213806
2023-01-21 09:20:04.122140: step: 148/531, loss: 0.08051643520593643
2023-01-21 09:20:05.250348: step: 152/531, loss: 0.24660225212574005
2023-01-21 09:20:06.371891: step: 156/531, loss: 0.1206233948469162
2023-01-21 09:20:07.479136: step: 160/531, loss: 0.060358334332704544
2023-01-21 09:20:08.633043: step: 164/531, loss: 0.0969579666852951
2023-01-21 09:20:09.748322: step: 168/531, loss: 0.07474646717309952
2023-01-21 09:20:10.917057: step: 172/531, loss: 0.6261759996414185
2023-01-21 09:20:12.042260: step: 176/531, loss: 0.15111775696277618
2023-01-21 09:20:13.183356: step: 180/531, loss: 0.11831426620483398
2023-01-21 09:20:14.301114: step: 184/531, loss: 0.0626072883605957
2023-01-21 09:20:15.418248: step: 188/531, loss: 1.5190863609313965
2023-01-21 09:20:16.530387: step: 192/531, loss: 0.16070805490016937
2023-01-21 09:20:17.667834: step: 196/531, loss: 0.566563606262207
2023-01-21 09:20:18.775661: step: 200/531, loss: 0.0715511366724968
2023-01-21 09:20:19.898040: step: 204/531, loss: 0.7877327799797058
2023-01-21 09:20:21.032276: step: 208/531, loss: 0.12577266991138458
2023-01-21 09:20:22.147954: step: 212/531, loss: 0.22464542090892792
2023-01-21 09:20:23.276486: step: 216/531, loss: 0.2676597535610199
2023-01-21 09:20:24.407609: step: 220/531, loss: 0.09776349365711212
2023-01-21 09:20:25.594242: step: 224/531, loss: 0.14313706755638123
2023-01-21 09:20:26.722933: step: 228/531, loss: 0.007430077064782381
2023-01-21 09:20:27.857356: step: 232/531, loss: 0.03798205778002739
2023-01-21 09:20:28.944654: step: 236/531, loss: 0.015440607443451881
2023-01-21 09:20:30.073020: step: 240/531, loss: 0.1368858367204666
2023-01-21 09:20:31.200973: step: 244/531, loss: 0.17660722136497498
2023-01-21 09:20:32.318823: step: 248/531, loss: 0.07572473585605621
2023-01-21 09:20:33.447139: step: 252/531, loss: 0.13013730943202972
2023-01-21 09:20:34.564393: step: 256/531, loss: 0.14868679642677307
2023-01-21 09:20:35.676644: step: 260/531, loss: 0.10700082778930664
2023-01-21 09:20:36.807983: step: 264/531, loss: 0.5462125539779663
2023-01-21 09:20:37.944445: step: 268/531, loss: 0.20810189843177795
2023-01-21 09:20:39.050929: step: 272/531, loss: 0.08502139896154404
2023-01-21 09:20:40.182563: step: 276/531, loss: 0.14979496598243713
2023-01-21 09:20:41.304813: step: 280/531, loss: 0.18747034668922424
2023-01-21 09:20:42.448239: step: 284/531, loss: 0.3113807737827301
2023-01-21 09:20:43.587223: step: 288/531, loss: 0.36427801847457886
2023-01-21 09:20:44.706985: step: 292/531, loss: 1.1106621026992798
2023-01-21 09:20:45.847618: step: 296/531, loss: 0.0223146453499794
2023-01-21 09:20:46.965901: step: 300/531, loss: 0.1053074300289154
2023-01-21 09:20:48.066147: step: 304/531, loss: 0.3404029905796051
2023-01-21 09:20:49.216423: step: 308/531, loss: 0.25511685013771057
2023-01-21 09:20:50.338370: step: 312/531, loss: 1.8216387033462524
2023-01-21 09:20:51.468361: step: 316/531, loss: 1.1487311124801636
2023-01-21 09:20:52.600516: step: 320/531, loss: 0.14093279838562012
2023-01-21 09:20:53.691343: step: 324/531, loss: 0.06238756328821182
2023-01-21 09:20:54.809668: step: 328/531, loss: 0.12706175446510315
2023-01-21 09:20:55.953670: step: 332/531, loss: 0.13536815345287323
2023-01-21 09:20:57.071542: step: 336/531, loss: 0.13423609733581543
2023-01-21 09:20:58.209507: step: 340/531, loss: 0.07471199333667755
2023-01-21 09:20:59.307166: step: 344/531, loss: 3.4741203784942627
2023-01-21 09:21:00.423612: step: 348/531, loss: 0.22138512134552002
2023-01-21 09:21:01.545902: step: 352/531, loss: 0.39459818601608276
2023-01-21 09:21:02.681777: step: 356/531, loss: 0.029367590323090553
2023-01-21 09:21:03.843409: step: 360/531, loss: 0.1014915481209755
2023-01-21 09:21:04.993866: step: 364/531, loss: 0.32232171297073364
2023-01-21 09:21:06.104473: step: 368/531, loss: 0.19875365495681763
2023-01-21 09:21:07.222712: step: 372/531, loss: 0.1061868667602539
2023-01-21 09:21:08.390236: step: 376/531, loss: 0.29672110080718994
2023-01-21 09:21:09.511767: step: 380/531, loss: 0.2829223573207855
2023-01-21 09:21:10.631363: step: 384/531, loss: 0.11531827598810196
2023-01-21 09:21:11.744095: step: 388/531, loss: 0.0637456402182579
2023-01-21 09:21:12.894157: step: 392/531, loss: 0.14168529212474823
2023-01-21 09:21:14.042469: step: 396/531, loss: 0.225851908326149
2023-01-21 09:21:15.152141: step: 400/531, loss: 0.4207419157028198
2023-01-21 09:21:16.276784: step: 404/531, loss: 0.12054505944252014
2023-01-21 09:21:17.407099: step: 408/531, loss: 0.21454288065433502
2023-01-21 09:21:18.536545: step: 412/531, loss: 0.005415058229118586
2023-01-21 09:21:19.647877: step: 416/531, loss: 0.1372077912092209
2023-01-21 09:21:20.806841: step: 420/531, loss: 0.06324926018714905
2023-01-21 09:21:21.918245: step: 424/531, loss: 0.5226781964302063
2023-01-21 09:21:23.037855: step: 428/531, loss: 0.11421461403369904
2023-01-21 09:21:24.166161: step: 432/531, loss: 0.17379578948020935
2023-01-21 09:21:25.278629: step: 436/531, loss: 0.7596912980079651
2023-01-21 09:21:26.384767: step: 440/531, loss: 0.32616668939590454
2023-01-21 09:21:27.504316: step: 444/531, loss: 0.1080353707075119
2023-01-21 09:21:28.617306: step: 448/531, loss: 0.11216773837804794
2023-01-21 09:21:29.741924: step: 452/531, loss: 0.08574571460485458
2023-01-21 09:21:30.823600: step: 456/531, loss: 0.12597227096557617
2023-01-21 09:21:31.931736: step: 460/531, loss: 0.2102283537387848
2023-01-21 09:21:33.075196: step: 464/531, loss: 0.3382846713066101
2023-01-21 09:21:34.212714: step: 468/531, loss: 0.7317107319831848
2023-01-21 09:21:35.342576: step: 472/531, loss: 0.20980873703956604
2023-01-21 09:21:36.470204: step: 476/531, loss: 0.06017189472913742
2023-01-21 09:21:37.600388: step: 480/531, loss: 0.22499194741249084
2023-01-21 09:21:38.728150: step: 484/531, loss: 0.2171640843153
2023-01-21 09:21:39.838482: step: 488/531, loss: 0.058008477091789246
2023-01-21 09:21:40.961388: step: 492/531, loss: 0.15389442443847656
2023-01-21 09:21:42.108886: step: 496/531, loss: 0.09659262001514435
2023-01-21 09:21:43.240105: step: 500/531, loss: 0.11291804909706116
2023-01-21 09:21:44.371129: step: 504/531, loss: 0.31916096806526184
2023-01-21 09:21:45.510590: step: 508/531, loss: 0.08025255799293518
2023-01-21 09:21:46.656558: step: 512/531, loss: 0.5968890190124512
2023-01-21 09:21:47.799482: step: 516/531, loss: 0.4367731213569641
2023-01-21 09:21:48.962626: step: 520/531, loss: 0.3811578154563904
2023-01-21 09:21:50.069509: step: 524/531, loss: 0.4929841458797455
2023-01-21 09:21:51.198150: step: 528/531, loss: 0.22546052932739258
2023-01-21 09:21:52.338353: step: 532/531, loss: 0.15466861426830292
2023-01-21 09:21:53.469778: step: 536/531, loss: 0.4843331575393677
2023-01-21 09:21:54.578551: step: 540/531, loss: 0.07414913177490234
2023-01-21 09:21:55.705285: step: 544/531, loss: 1.7784169912338257
2023-01-21 09:21:56.817420: step: 548/531, loss: 0.11431710422039032
2023-01-21 09:21:57.949277: step: 552/531, loss: 0.147385835647583
2023-01-21 09:21:59.102799: step: 556/531, loss: 0.7561390995979309
2023-01-21 09:22:00.230841: step: 560/531, loss: 0.14396890997886658
2023-01-21 09:22:01.362779: step: 564/531, loss: 0.0835152193903923
2023-01-21 09:22:02.533000: step: 568/531, loss: 0.41781753301620483
2023-01-21 09:22:03.659433: step: 572/531, loss: 0.1418953835964203
2023-01-21 09:22:04.786194: step: 576/531, loss: 0.259294331073761
2023-01-21 09:22:05.911721: step: 580/531, loss: 0.09604254364967346
2023-01-21 09:22:07.020772: step: 584/531, loss: 0.21384435892105103
2023-01-21 09:22:08.165658: step: 588/531, loss: 0.12788324058055878
2023-01-21 09:22:09.296570: step: 592/531, loss: 0.1271975040435791
2023-01-21 09:22:10.428607: step: 596/531, loss: 0.12607315182685852
2023-01-21 09:22:11.535607: step: 600/531, loss: 0.30766287446022034
2023-01-21 09:22:12.656990: step: 604/531, loss: 0.7762675285339355
2023-01-21 09:22:13.803979: step: 608/531, loss: 0.15716032683849335
2023-01-21 09:22:14.961657: step: 612/531, loss: 0.07950840145349503
2023-01-21 09:22:16.102543: step: 616/531, loss: 0.09453105926513672
2023-01-21 09:22:17.224625: step: 620/531, loss: 0.8622385263442993
2023-01-21 09:22:18.364937: step: 624/531, loss: 0.03307478502392769
2023-01-21 09:22:19.503250: step: 628/531, loss: 0.12056894600391388
2023-01-21 09:22:20.639505: step: 632/531, loss: 0.200147807598114
2023-01-21 09:22:21.771891: step: 636/531, loss: 0.15794605016708374
2023-01-21 09:22:22.913171: step: 640/531, loss: 0.12747633457183838
2023-01-21 09:22:24.024764: step: 644/531, loss: 0.3461719751358032
2023-01-21 09:22:25.146852: step: 648/531, loss: 0.03799867630004883
2023-01-21 09:22:26.266639: step: 652/531, loss: 0.7810134887695312
2023-01-21 09:22:27.399698: step: 656/531, loss: 0.08401909470558167
2023-01-21 09:22:28.494934: step: 660/531, loss: 0.1714201420545578
2023-01-21 09:22:29.598341: step: 664/531, loss: 0.39346712827682495
2023-01-21 09:22:30.726561: step: 668/531, loss: 0.09842925518751144
2023-01-21 09:22:31.847045: step: 672/531, loss: 0.2554939389228821
2023-01-21 09:22:32.984896: step: 676/531, loss: 0.01188054122030735
2023-01-21 09:22:34.091995: step: 680/531, loss: 0.11830110847949982
2023-01-21 09:22:35.235614: step: 684/531, loss: 0.7243600487709045
2023-01-21 09:22:36.378380: step: 688/531, loss: 0.2884639799594879
2023-01-21 09:22:37.510413: step: 692/531, loss: 0.0690801590681076
2023-01-21 09:22:38.608738: step: 696/531, loss: 0.10876226425170898
2023-01-21 09:22:39.765243: step: 700/531, loss: 0.07742643356323242
2023-01-21 09:22:40.881383: step: 704/531, loss: 0.039069078862667084
2023-01-21 09:22:42.004087: step: 708/531, loss: 0.1261400282382965
2023-01-21 09:22:43.125863: step: 712/531, loss: 0.10678987205028534
2023-01-21 09:22:44.226113: step: 716/531, loss: 0.21546411514282227
2023-01-21 09:22:45.363918: step: 720/531, loss: 0.6676244139671326
2023-01-21 09:22:46.479337: step: 724/531, loss: 0.4401053786277771
2023-01-21 09:22:47.618575: step: 728/531, loss: 0.018947506323456764
2023-01-21 09:22:48.760478: step: 732/531, loss: 0.4283602833747864
2023-01-21 09:22:49.886438: step: 736/531, loss: 0.11649742722511292
2023-01-21 09:22:51.044300: step: 740/531, loss: 0.14506417512893677
2023-01-21 09:22:52.173107: step: 744/531, loss: 3.3566036224365234
2023-01-21 09:22:53.287498: step: 748/531, loss: 0.4281378984451294
2023-01-21 09:22:54.370302: step: 752/531, loss: 0.023123862221837044
2023-01-21 09:22:55.494211: step: 756/531, loss: 0.09989605098962784
2023-01-21 09:22:56.612066: step: 760/531, loss: 0.06815844029188156
2023-01-21 09:22:57.721996: step: 764/531, loss: 0.07789120823144913
2023-01-21 09:22:58.860602: step: 768/531, loss: 0.05248665809631348
2023-01-21 09:23:00.015485: step: 772/531, loss: 0.3559483587741852
2023-01-21 09:23:01.171709: step: 776/531, loss: 0.6388660669326782
2023-01-21 09:23:02.277146: step: 780/531, loss: 0.13060155510902405
2023-01-21 09:23:03.431844: step: 784/531, loss: 0.5392071008682251
2023-01-21 09:23:04.554677: step: 788/531, loss: 0.4878729581832886
2023-01-21 09:23:05.698049: step: 792/531, loss: 0.1716877818107605
2023-01-21 09:23:06.831347: step: 796/531, loss: 0.38911306858062744
2023-01-21 09:23:07.952077: step: 800/531, loss: 0.09696026146411896
2023-01-21 09:23:09.059887: step: 804/531, loss: 0.3628661334514618
2023-01-21 09:23:10.192180: step: 808/531, loss: 0.1736392080783844
2023-01-21 09:23:11.306659: step: 812/531, loss: 0.34399205446243286
2023-01-21 09:23:12.481372: step: 816/531, loss: 0.1590687781572342
2023-01-21 09:23:13.624088: step: 820/531, loss: 0.5829407572746277
2023-01-21 09:23:14.780399: step: 824/531, loss: 0.4002405107021332
2023-01-21 09:23:15.915434: step: 828/531, loss: 0.13225403428077698
2023-01-21 09:23:17.060935: step: 832/531, loss: 0.1279522031545639
2023-01-21 09:23:18.148927: step: 836/531, loss: 0.09511509537696838
2023-01-21 09:23:19.298598: step: 840/531, loss: 0.13932590186595917
2023-01-21 09:23:20.468889: step: 844/531, loss: 0.13361340761184692
2023-01-21 09:23:21.568877: step: 848/531, loss: 0.5909035205841064
2023-01-21 09:23:22.669507: step: 852/531, loss: 0.17041346430778503
2023-01-21 09:23:23.803084: step: 856/531, loss: 0.11356143653392792
2023-01-21 09:23:24.931767: step: 860/531, loss: 0.2798663377761841
2023-01-21 09:23:26.079227: step: 864/531, loss: 0.18520203232765198
2023-01-21 09:23:27.180803: step: 868/531, loss: 0.22399906814098358
2023-01-21 09:23:28.282918: step: 872/531, loss: 0.4984610080718994
2023-01-21 09:23:29.452749: step: 876/531, loss: 0.06039772182703018
2023-01-21 09:23:30.564525: step: 880/531, loss: 0.28380468487739563
2023-01-21 09:23:31.682979: step: 884/531, loss: 0.3702622056007385
2023-01-21 09:23:32.805252: step: 888/531, loss: 0.18391229212284088
2023-01-21 09:23:33.910397: step: 892/531, loss: 0.012537956237792969
2023-01-21 09:23:35.039167: step: 896/531, loss: 0.10259237140417099
2023-01-21 09:23:36.160008: step: 900/531, loss: 0.07060952484607697
2023-01-21 09:23:37.282437: step: 904/531, loss: 0.19390204548835754
2023-01-21 09:23:38.393089: step: 908/531, loss: 0.2734799385070801
2023-01-21 09:23:39.497260: step: 912/531, loss: 0.04100747033953667
2023-01-21 09:23:40.617701: step: 916/531, loss: 0.43919527530670166
2023-01-21 09:23:41.744937: step: 920/531, loss: 0.09465637803077698
2023-01-21 09:23:42.907846: step: 924/531, loss: 0.28514137864112854
2023-01-21 09:23:44.028501: step: 928/531, loss: 0.15421992540359497
2023-01-21 09:23:45.161183: step: 932/531, loss: 0.12785452604293823
2023-01-21 09:23:46.270874: step: 936/531, loss: 0.5910702347755432
2023-01-21 09:23:47.415941: step: 940/531, loss: 0.299083411693573
2023-01-21 09:23:48.538001: step: 944/531, loss: 0.08141613006591797
2023-01-21 09:23:49.634147: step: 948/531, loss: 0.03309335559606552
2023-01-21 09:23:50.758770: step: 952/531, loss: 0.407720685005188
2023-01-21 09:23:51.892535: step: 956/531, loss: 0.11979393661022186
2023-01-21 09:23:53.024173: step: 960/531, loss: 0.13426253199577332
2023-01-21 09:23:54.148186: step: 964/531, loss: 0.18411245942115784
2023-01-21 09:23:55.290654: step: 968/531, loss: 0.14016684889793396
2023-01-21 09:23:56.417722: step: 972/531, loss: 0.1574666053056717
2023-01-21 09:23:57.522739: step: 976/531, loss: 0.15568019449710846
2023-01-21 09:23:58.639056: step: 980/531, loss: 0.1557566225528717
2023-01-21 09:23:59.739886: step: 984/531, loss: 0.05853700637817383
2023-01-21 09:24:00.855023: step: 988/531, loss: 0.08996076136827469
2023-01-21 09:24:01.995011: step: 992/531, loss: 0.336512953042984
2023-01-21 09:24:03.127218: step: 996/531, loss: 0.0432555228471756
2023-01-21 09:24:04.243970: step: 1000/531, loss: 0.4580022096633911
2023-01-21 09:24:05.389570: step: 1004/531, loss: 0.0792016088962555
2023-01-21 09:24:06.507490: step: 1008/531, loss: 0.23022013902664185
2023-01-21 09:24:07.627100: step: 1012/531, loss: 0.5968620181083679
2023-01-21 09:24:08.762799: step: 1016/531, loss: 0.11794266104698181
2023-01-21 09:24:09.865708: step: 1020/531, loss: 0.5145123600959778
2023-01-21 09:24:10.970145: step: 1024/531, loss: 0.0805201306939125
2023-01-21 09:24:12.096220: step: 1028/531, loss: 0.43894654512405396
2023-01-21 09:24:13.197186: step: 1032/531, loss: 0.1105382889509201
2023-01-21 09:24:14.326663: step: 1036/531, loss: 0.25686168670654297
2023-01-21 09:24:15.487791: step: 1040/531, loss: 0.1647787094116211
2023-01-21 09:24:16.606873: step: 1044/531, loss: 0.6482565999031067
2023-01-21 09:24:17.736988: step: 1048/531, loss: 0.05835747718811035
2023-01-21 09:24:18.857307: step: 1052/531, loss: 0.4489502012729645
2023-01-21 09:24:19.965870: step: 1056/531, loss: 0.12999510765075684
2023-01-21 09:24:21.119229: step: 1060/531, loss: 0.40457284450531006
2023-01-21 09:24:22.239138: step: 1064/531, loss: 0.08496780693531036
2023-01-21 09:24:23.367220: step: 1068/531, loss: 0.9429113864898682
2023-01-21 09:24:24.473361: step: 1072/531, loss: 0.07517362385988235
2023-01-21 09:24:25.612385: step: 1076/531, loss: 0.06246475130319595
2023-01-21 09:24:26.731118: step: 1080/531, loss: 0.10489077866077423
2023-01-21 09:24:27.834966: step: 1084/531, loss: 0.05943968519568443
2023-01-21 09:24:28.950379: step: 1088/531, loss: 0.15815573930740356
2023-01-21 09:24:30.077255: step: 1092/531, loss: 0.3370331823825836
2023-01-21 09:24:31.214340: step: 1096/531, loss: 0.08954358100891113
2023-01-21 09:24:32.322361: step: 1100/531, loss: 0.02264227718114853
2023-01-21 09:24:33.439683: step: 1104/531, loss: 0.44786348938941956
2023-01-21 09:24:34.551009: step: 1108/531, loss: 0.49628493189811707
2023-01-21 09:24:35.695495: step: 1112/531, loss: 0.09058018028736115
2023-01-21 09:24:36.787711: step: 1116/531, loss: 0.08966894447803497
2023-01-21 09:24:37.913836: step: 1120/531, loss: 0.20239944756031036
2023-01-21 09:24:39.015781: step: 1124/531, loss: 0.023293495178222656
2023-01-21 09:24:40.136774: step: 1128/531, loss: 0.2353372573852539
2023-01-21 09:24:41.268452: step: 1132/531, loss: 0.9897315502166748
2023-01-21 09:24:42.407648: step: 1136/531, loss: 0.03459892049431801
2023-01-21 09:24:43.545306: step: 1140/531, loss: 0.05682554095983505
2023-01-21 09:24:44.669471: step: 1144/531, loss: 0.044228505343198776
2023-01-21 09:24:45.770033: step: 1148/531, loss: 0.6215946078300476
2023-01-21 09:24:46.918332: step: 1152/531, loss: 0.4609766900539398
2023-01-21 09:24:48.052626: step: 1156/531, loss: 0.1382693350315094
2023-01-21 09:24:49.175761: step: 1160/531, loss: 0.5196768641471863
2023-01-21 09:24:50.303680: step: 1164/531, loss: 0.043473437428474426
2023-01-21 09:24:51.433913: step: 1168/531, loss: 0.21080002188682556
2023-01-21 09:24:52.569105: step: 1172/531, loss: 0.3833649754524231
2023-01-21 09:24:53.673998: step: 1176/531, loss: 0.06717577576637268
2023-01-21 09:24:54.793688: step: 1180/531, loss: 0.046009257435798645
2023-01-21 09:24:55.907373: step: 1184/531, loss: 0.03521165996789932
2023-01-21 09:24:57.012723: step: 1188/531, loss: 0.2972188889980316
2023-01-21 09:24:58.129631: step: 1192/531, loss: 0.8312904238700867
2023-01-21 09:24:59.240133: step: 1196/531, loss: 0.977934718132019
2023-01-21 09:25:00.361275: step: 1200/531, loss: 0.05278778076171875
2023-01-21 09:25:01.504935: step: 1204/531, loss: 0.12949152290821075
2023-01-21 09:25:02.627076: step: 1208/531, loss: 0.24591580033302307
2023-01-21 09:25:03.751961: step: 1212/531, loss: 0.0878174751996994
2023-01-21 09:25:04.858549: step: 1216/531, loss: 0.3329910635948181
2023-01-21 09:25:05.994005: step: 1220/531, loss: 0.4611121416091919
2023-01-21 09:25:07.127896: step: 1224/531, loss: 0.09945712238550186
2023-01-21 09:25:08.251158: step: 1228/531, loss: 0.044197943061590195
2023-01-21 09:25:09.372817: step: 1232/531, loss: 0.11266021430492401
2023-01-21 09:25:10.487984: step: 1236/531, loss: 0.1609579175710678
2023-01-21 09:25:11.613462: step: 1240/531, loss: 0.09072819352149963
2023-01-21 09:25:12.746675: step: 1244/531, loss: 5.270782947540283
2023-01-21 09:25:13.856762: step: 1248/531, loss: 0.12462158501148224
2023-01-21 09:25:14.969343: step: 1252/531, loss: 0.08513360470533371
2023-01-21 09:25:16.083303: step: 1256/531, loss: 0.1756526529788971
2023-01-21 09:25:17.235958: step: 1260/531, loss: 0.3278857469558716
2023-01-21 09:25:18.360089: step: 1264/531, loss: 0.5369536280632019
2023-01-21 09:25:19.480267: step: 1268/531, loss: 0.6144624948501587
2023-01-21 09:25:20.606502: step: 1272/531, loss: 0.5206581950187683
2023-01-21 09:25:21.717577: step: 1276/531, loss: 0.05089038610458374
2023-01-21 09:25:22.853966: step: 1280/531, loss: 0.32959622144699097
2023-01-21 09:25:23.976724: step: 1284/531, loss: 0.390646755695343
2023-01-21 09:25:25.089455: step: 1288/531, loss: 0.07557649910449982
2023-01-21 09:25:26.189938: step: 1292/531, loss: 0.20201599597930908
2023-01-21 09:25:27.324252: step: 1296/531, loss: 0.4787057638168335
2023-01-21 09:25:28.468530: step: 1300/531, loss: 0.1810092031955719
2023-01-21 09:25:29.615624: step: 1304/531, loss: 0.10041961818933487
2023-01-21 09:25:30.737852: step: 1308/531, loss: 0.18631476163864136
2023-01-21 09:25:31.839573: step: 1312/531, loss: 0.7809675335884094
2023-01-21 09:25:32.997436: step: 1316/531, loss: 0.1162814125418663
2023-01-21 09:25:34.124467: step: 1320/531, loss: 0.7988578081130981
2023-01-21 09:25:35.230054: step: 1324/531, loss: 0.13178615272045135
2023-01-21 09:25:36.363993: step: 1328/531, loss: 0.49795836210250854
2023-01-21 09:25:37.493350: step: 1332/531, loss: 0.12801781296730042
2023-01-21 09:25:38.604998: step: 1336/531, loss: 0.12133064866065979
2023-01-21 09:25:39.728459: step: 1340/531, loss: 0.036447882652282715
2023-01-21 09:25:40.883233: step: 1344/531, loss: 0.3469217121601105
2023-01-21 09:25:41.987514: step: 1348/531, loss: 0.10699406266212463
2023-01-21 09:25:43.134016: step: 1352/531, loss: 0.10263185203075409
2023-01-21 09:25:44.281974: step: 1356/531, loss: 0.03931427001953125
2023-01-21 09:25:45.411444: step: 1360/531, loss: 0.21205520629882812
2023-01-21 09:25:46.543569: step: 1364/531, loss: 0.17296457290649414
2023-01-21 09:25:47.673910: step: 1368/531, loss: 0.15259799361228943
2023-01-21 09:25:48.769515: step: 1372/531, loss: 0.0536830872297287
2023-01-21 09:25:49.896747: step: 1376/531, loss: 0.28342801332473755
2023-01-21 09:25:51.028633: step: 1380/531, loss: 0.2268989086151123
2023-01-21 09:25:52.181949: step: 1384/531, loss: 0.40731558203697205
2023-01-21 09:25:53.359461: step: 1388/531, loss: 0.3068438768386841
2023-01-21 09:25:54.501411: step: 1392/531, loss: 0.16849274933338165
2023-01-21 09:25:55.624805: step: 1396/531, loss: 0.1644456833600998
2023-01-21 09:25:56.727423: step: 1400/531, loss: 0.951788067817688
2023-01-21 09:25:57.867458: step: 1404/531, loss: 0.3371749818325043
2023-01-21 09:25:58.990338: step: 1408/531, loss: 0.43408751487731934
2023-01-21 09:26:00.100875: step: 1412/531, loss: 1.5530601739883423
2023-01-21 09:26:01.184414: step: 1416/531, loss: 0.365949422121048
2023-01-21 09:26:02.284943: step: 1420/531, loss: 0.2542448937892914
2023-01-21 09:26:03.404928: step: 1424/531, loss: 0.12949238717556
2023-01-21 09:26:04.575108: step: 1428/531, loss: 0.09009018540382385
2023-01-21 09:26:05.706275: step: 1432/531, loss: 0.1276037096977234
2023-01-21 09:26:06.829990: step: 1436/531, loss: 0.09900350868701935
2023-01-21 09:26:07.973293: step: 1440/531, loss: 0.3038250803947449
2023-01-21 09:26:09.078974: step: 1444/531, loss: 0.28426557779312134
2023-01-21 09:26:10.217292: step: 1448/531, loss: 0.4755532443523407
2023-01-21 09:26:11.340360: step: 1452/531, loss: 0.13073988258838654
2023-01-21 09:26:12.460134: step: 1456/531, loss: 0.11859126389026642
2023-01-21 09:26:13.592434: step: 1460/531, loss: 0.16933254897594452
2023-01-21 09:26:14.729614: step: 1464/531, loss: 0.060035038739442825
2023-01-21 09:26:15.850984: step: 1468/531, loss: 0.019108964130282402
2023-01-21 09:26:16.963254: step: 1472/531, loss: 0.10508136451244354
2023-01-21 09:26:18.061912: step: 1476/531, loss: 0.13732466101646423
2023-01-21 09:26:19.185787: step: 1480/531, loss: 0.22092753648757935
2023-01-21 09:26:20.300383: step: 1484/531, loss: 0.053449537605047226
2023-01-21 09:26:21.414821: step: 1488/531, loss: 0.13331981003284454
2023-01-21 09:26:22.559576: step: 1492/531, loss: 0.0746951550245285
2023-01-21 09:26:23.637320: step: 1496/531, loss: 0.12361302971839905
2023-01-21 09:26:24.723914: step: 1500/531, loss: 0.1742846518754959
2023-01-21 09:26:25.843582: step: 1504/531, loss: 0.6790333390235901
2023-01-21 09:26:26.968333: step: 1508/531, loss: 0.06733884662389755
2023-01-21 09:26:28.073730: step: 1512/531, loss: 0.19083049893379211
2023-01-21 09:26:29.183596: step: 1516/531, loss: 0.27966246008872986
2023-01-21 09:26:30.310046: step: 1520/531, loss: 0.08095188438892365
2023-01-21 09:26:31.453175: step: 1524/531, loss: 0.14948931336402893
2023-01-21 09:26:32.597878: step: 1528/531, loss: 0.7838238477706909
2023-01-21 09:26:33.702891: step: 1532/531, loss: 0.17595674097537994
2023-01-21 09:26:34.830967: step: 1536/531, loss: 0.05603218078613281
2023-01-21 09:26:35.982386: step: 1540/531, loss: 0.25855112075805664
2023-01-21 09:26:37.105338: step: 1544/531, loss: 0.10620498657226562
2023-01-21 09:26:38.230776: step: 1548/531, loss: 0.3945713937282562
2023-01-21 09:26:39.364384: step: 1552/531, loss: 0.1955706626176834
2023-01-21 09:26:40.489252: step: 1556/531, loss: 0.10373048484325409
2023-01-21 09:26:41.600787: step: 1560/531, loss: 0.056058548390865326
2023-01-21 09:26:42.729549: step: 1564/531, loss: 0.13536995649337769
2023-01-21 09:26:43.846238: step: 1568/531, loss: 0.0990375503897667
2023-01-21 09:26:45.009131: step: 1572/531, loss: 0.11423464119434357
2023-01-21 09:26:46.097851: step: 1576/531, loss: 0.17716436088085175
2023-01-21 09:26:47.231126: step: 1580/531, loss: 0.2681174874305725
2023-01-21 09:26:48.365147: step: 1584/531, loss: 0.11104698479175568
2023-01-21 09:26:49.539120: step: 1588/531, loss: 0.12791967391967773
2023-01-21 09:26:50.661308: step: 1592/531, loss: 0.08090706169605255
2023-01-21 09:26:51.797997: step: 1596/531, loss: 0.0628213882446289
2023-01-21 09:26:52.899145: step: 1600/531, loss: 0.1080193966627121
2023-01-21 09:26:54.026746: step: 1604/531, loss: 0.13725414872169495
2023-01-21 09:26:55.156426: step: 1608/531, loss: 0.12615986168384552
2023-01-21 09:26:56.281993: step: 1612/531, loss: 0.10770893096923828
2023-01-21 09:26:57.390688: step: 1616/531, loss: 0.41494157910346985
2023-01-21 09:26:58.524930: step: 1620/531, loss: 0.07492885738611221
2023-01-21 09:26:59.631739: step: 1624/531, loss: 0.09369926154613495
2023-01-21 09:27:00.748431: step: 1628/531, loss: 0.26386985182762146
2023-01-21 09:27:01.865997: step: 1632/531, loss: 0.0204620361328125
2023-01-21 09:27:02.968695: step: 1636/531, loss: 0.21918782591819763
2023-01-21 09:27:04.087575: step: 1640/531, loss: 0.08974028378725052
2023-01-21 09:27:05.165984: step: 1644/531, loss: 0.3051663041114807
2023-01-21 09:27:06.257198: step: 1648/531, loss: 0.3446905314922333
2023-01-21 09:27:07.382563: step: 1652/531, loss: 0.039138033986091614
2023-01-21 09:27:08.479921: step: 1656/531, loss: 0.19138669967651367
2023-01-21 09:27:09.592593: step: 1660/531, loss: 0.2975608706474304
2023-01-21 09:27:10.709348: step: 1664/531, loss: 0.36778098344802856
2023-01-21 09:27:11.859540: step: 1668/531, loss: 0.1063106581568718
2023-01-21 09:27:12.983995: step: 1672/531, loss: 1.1621308326721191
2023-01-21 09:27:14.097074: step: 1676/531, loss: 0.23349857330322266
2023-01-21 09:27:15.211478: step: 1680/531, loss: 0.3977741301059723
2023-01-21 09:27:16.300307: step: 1684/531, loss: 0.48294752836227417
2023-01-21 09:27:17.398089: step: 1688/531, loss: 0.13870978355407715
2023-01-21 09:27:18.490752: step: 1692/531, loss: 0.21510955691337585
2023-01-21 09:27:19.604265: step: 1696/531, loss: 0.21706832945346832
2023-01-21 09:27:20.712995: step: 1700/531, loss: 0.09922724217176437
2023-01-21 09:27:21.837313: step: 1704/531, loss: 0.06827382743358612
2023-01-21 09:27:22.968913: step: 1708/531, loss: 0.11864328384399414
2023-01-21 09:27:24.115872: step: 1712/531, loss: 0.15477409958839417
2023-01-21 09:27:25.230983: step: 1716/531, loss: 0.29711437225341797
2023-01-21 09:27:26.374146: step: 1720/531, loss: 0.20394659042358398
2023-01-21 09:27:27.466914: step: 1724/531, loss: 0.23727789521217346
2023-01-21 09:27:28.588998: step: 1728/531, loss: 0.1402730941772461
2023-01-21 09:27:29.718280: step: 1732/531, loss: 0.052642822265625
2023-01-21 09:27:30.829644: step: 1736/531, loss: 0.15474733710289001
2023-01-21 09:27:31.928946: step: 1740/531, loss: 0.42271554470062256
2023-01-21 09:27:33.046248: step: 1744/531, loss: 0.8821865916252136
2023-01-21 09:27:34.175390: step: 1748/531, loss: 0.3389485478401184
2023-01-21 09:27:35.321144: step: 1752/531, loss: 0.18968543410301208
2023-01-21 09:27:36.465468: step: 1756/531, loss: 0.06896381080150604
2023-01-21 09:27:37.582040: step: 1760/531, loss: 0.37530672550201416
2023-01-21 09:27:38.715333: step: 1764/531, loss: 0.17176242172718048
2023-01-21 09:27:39.857715: step: 1768/531, loss: 0.11363659054040909
2023-01-21 09:27:41.001877: step: 1772/531, loss: 0.08463610708713531
2023-01-21 09:27:42.155866: step: 1776/531, loss: 0.05079937353730202
2023-01-21 09:27:43.316494: step: 1780/531, loss: 0.08702945709228516
2023-01-21 09:27:44.415480: step: 1784/531, loss: 0.31351909041404724
2023-01-21 09:27:45.539828: step: 1788/531, loss: 0.08429765701293945
2023-01-21 09:27:46.688539: step: 1792/531, loss: 0.09733138233423233
2023-01-21 09:27:47.803115: step: 1796/531, loss: 0.21036525070667267
2023-01-21 09:27:48.928448: step: 1800/531, loss: 0.48478659987449646
2023-01-21 09:27:50.051511: step: 1804/531, loss: 0.17424841225147247
2023-01-21 09:27:51.170128: step: 1808/531, loss: 0.40230417251586914
2023-01-21 09:27:52.311453: step: 1812/531, loss: 2.430882453918457
2023-01-21 09:27:53.426218: step: 1816/531, loss: 0.937486469745636
2023-01-21 09:27:54.558595: step: 1820/531, loss: 0.6594923138618469
2023-01-21 09:27:55.651147: step: 1824/531, loss: 0.04879341274499893
2023-01-21 09:27:56.786917: step: 1828/531, loss: 0.2868717312812805
2023-01-21 09:27:57.889989: step: 1832/531, loss: 0.07998818159103394
2023-01-21 09:27:59.009970: step: 1836/531, loss: 0.6160796880722046
2023-01-21 09:28:00.121625: step: 1840/531, loss: 2.504883289337158
2023-01-21 09:28:01.219472: step: 1844/531, loss: 0.024641752243041992
2023-01-21 09:28:02.364745: step: 1848/531, loss: 0.25491833686828613
2023-01-21 09:28:03.540580: step: 1852/531, loss: 0.17909449338912964
2023-01-21 09:28:04.674737: step: 1856/531, loss: 0.03929818421602249
2023-01-21 09:28:05.814171: step: 1860/531, loss: 0.20805053412914276
2023-01-21 09:28:06.905507: step: 1864/531, loss: 0.3360249698162079
2023-01-21 09:28:08.049378: step: 1868/531, loss: 0.2190142571926117
2023-01-21 09:28:09.172634: step: 1872/531, loss: 0.18401947617530823
2023-01-21 09:28:10.305601: step: 1876/531, loss: 0.03933882713317871
2023-01-21 09:28:11.459070: step: 1880/531, loss: 0.5655359029769897
2023-01-21 09:28:12.567245: step: 1884/531, loss: 0.15157060325145721
2023-01-21 09:28:13.715049: step: 1888/531, loss: 0.20729702711105347
2023-01-21 09:28:14.880982: step: 1892/531, loss: 0.4299635887145996
2023-01-21 09:28:15.996498: step: 1896/531, loss: 0.2888050079345703
2023-01-21 09:28:17.157301: step: 1900/531, loss: 0.11375733464956284
2023-01-21 09:28:18.294663: step: 1904/531, loss: 0.10378637909889221
2023-01-21 09:28:19.419357: step: 1908/531, loss: 0.10378704220056534
2023-01-21 09:28:20.525027: step: 1912/531, loss: 0.22663506865501404
2023-01-21 09:28:21.644798: step: 1916/531, loss: 0.34136760234832764
2023-01-21 09:28:22.745790: step: 1920/531, loss: 0.19974803924560547
2023-01-21 09:28:23.900162: step: 1924/531, loss: 0.25381433963775635
2023-01-21 09:28:25.059608: step: 1928/531, loss: 0.13586612045764923
2023-01-21 09:28:26.167605: step: 1932/531, loss: 0.19036856293678284
2023-01-21 09:28:27.332248: step: 1936/531, loss: 1.5728070735931396
2023-01-21 09:28:28.450296: step: 1940/531, loss: 0.09194259345531464
2023-01-21 09:28:29.541339: step: 1944/531, loss: 0.06685075908899307
2023-01-21 09:28:30.639689: step: 1948/531, loss: 0.03318953514099121
2023-01-21 09:28:31.764977: step: 1952/531, loss: 0.5354709625244141
2023-01-21 09:28:32.870566: step: 1956/531, loss: 0.3382452130317688
2023-01-21 09:28:33.995688: step: 1960/531, loss: 0.11215820163488388
2023-01-21 09:28:35.124424: step: 1964/531, loss: 0.8525193333625793
2023-01-21 09:28:36.283610: step: 1968/531, loss: 0.5534533858299255
2023-01-21 09:28:37.398650: step: 1972/531, loss: 0.5061460137367249
2023-01-21 09:28:38.538207: step: 1976/531, loss: 0.6987929344177246
2023-01-21 09:28:39.673439: step: 1980/531, loss: 0.12794113159179688
2023-01-21 09:28:40.786543: step: 1984/531, loss: 0.12068863213062286
2023-01-21 09:28:41.939991: step: 1988/531, loss: 0.07859029620885849
2023-01-21 09:28:43.058025: step: 1992/531, loss: 0.3634530007839203
2023-01-21 09:28:44.191525: step: 1996/531, loss: 0.39075756072998047
2023-01-21 09:28:45.306194: step: 2000/531, loss: 0.0685429573059082
2023-01-21 09:28:46.459936: step: 2004/531, loss: 0.09246974438428879
2023-01-21 09:28:47.568938: step: 2008/531, loss: 0.3992319703102112
2023-01-21 09:28:48.734932: step: 2012/531, loss: 0.2583286166191101
2023-01-21 09:28:49.865719: step: 2016/531, loss: 1.7008168697357178
2023-01-21 09:28:51.010098: step: 2020/531, loss: 0.09999027848243713
2023-01-21 09:28:52.112430: step: 2024/531, loss: 1.4721925258636475
2023-01-21 09:28:53.235731: step: 2028/531, loss: 0.23009443283081055
2023-01-21 09:28:54.387496: step: 2032/531, loss: 0.049252700060606
2023-01-21 09:28:55.494327: step: 2036/531, loss: 0.1880214661359787
2023-01-21 09:28:56.622336: step: 2040/531, loss: 0.3344150483608246
2023-01-21 09:28:57.728457: step: 2044/531, loss: 0.1133275032043457
2023-01-21 09:28:58.824958: step: 2048/531, loss: 1.1327979564666748
2023-01-21 09:28:59.947160: step: 2052/531, loss: 0.38301506638526917
2023-01-21 09:29:01.089599: step: 2056/531, loss: 0.0619143471121788
2023-01-21 09:29:02.209035: step: 2060/531, loss: 0.2871108949184418
2023-01-21 09:29:03.346118: step: 2064/531, loss: 0.12272000312805176
2023-01-21 09:29:04.455291: step: 2068/531, loss: 0.4739369750022888
2023-01-21 09:29:05.592781: step: 2072/531, loss: 0.09282936900854111
2023-01-21 09:29:06.701043: step: 2076/531, loss: 0.5756852626800537
2023-01-21 09:29:07.849825: step: 2080/531, loss: 0.4304693639278412
2023-01-21 09:29:08.950941: step: 2084/531, loss: 0.25591841340065
2023-01-21 09:29:10.079009: step: 2088/531, loss: 0.15246042609214783
2023-01-21 09:29:11.207803: step: 2092/531, loss: 0.8338353633880615
2023-01-21 09:29:12.346897: step: 2096/531, loss: 0.1795164942741394
2023-01-21 09:29:13.482807: step: 2100/531, loss: 0.21658101677894592
2023-01-21 09:29:14.598958: step: 2104/531, loss: 0.0930359810590744
2023-01-21 09:29:15.723230: step: 2108/531, loss: 0.09251256287097931
2023-01-21 09:29:16.823989: step: 2112/531, loss: 0.1334594339132309
2023-01-21 09:29:17.941184: step: 2116/531, loss: 0.07223796844482422
2023-01-21 09:29:19.099351: step: 2120/531, loss: 0.5539063811302185
2023-01-21 09:29:20.216567: step: 2124/531, loss: 0.09299664944410324
==================================================
Loss: 0.297
--------------------
Dev: {'event': {'p': 0.5440900562851783, 'r': 0.7723035952063915, 'f1': 0.6384149697303247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.5672823218997362, 'r': 0.7692307692307693, 'f1': 0.6529992406985574}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.5108695652173914, 'r': 0.8703703703703703, 'f1': 0.6438356164383562}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.6557377049180327, 'r': 0.6349206349206349, 'f1': 0.6451612903225806}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.43478260869565216, 'r': 0.5555555555555556, 'f1': 0.4878048780487805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5440900562851783, 'r': 0.7723035952063915, 'f1': 0.6384149697303247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.5672823218997362, 'r': 0.7692307692307693, 'f1': 0.6529992406985574}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6557377049180327, 'r': 0.6349206349206349, 'f1': 0.6451612903225806}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.6956521739130435, 'r': 0.4444444444444444, 'f1': 0.5423728813559322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 6
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:30:07.036441: step: 4/531, loss: 0.15086175501346588
2023-01-21 09:30:08.159841: step: 8/531, loss: 0.44519805908203125
2023-01-21 09:30:09.328276: step: 12/531, loss: 0.058432817459106445
2023-01-21 09:30:10.450225: step: 16/531, loss: 0.10795927047729492
2023-01-21 09:30:11.542478: step: 20/531, loss: 0.11459669470787048
2023-01-21 09:30:12.681568: step: 24/531, loss: 0.21477949619293213
2023-01-21 09:30:13.819609: step: 28/531, loss: 0.02445411868393421
2023-01-21 09:30:14.939833: step: 32/531, loss: 0.6534051299095154
2023-01-21 09:30:16.086144: step: 36/531, loss: 0.10216904431581497
2023-01-21 09:30:17.213007: step: 40/531, loss: 0.12439584732055664
2023-01-21 09:30:18.312313: step: 44/531, loss: 0.1372111290693283
2023-01-21 09:30:19.418833: step: 48/531, loss: 0.31181374192237854
2023-01-21 09:30:20.540339: step: 52/531, loss: 0.07597608864307404
2023-01-21 09:30:21.667330: step: 56/531, loss: 0.18333645164966583
2023-01-21 09:30:22.782536: step: 60/531, loss: 0.10311757028102875
2023-01-21 09:30:23.929798: step: 64/531, loss: 0.15589380264282227
2023-01-21 09:30:25.055947: step: 68/531, loss: 0.10180147737264633
2023-01-21 09:30:26.189481: step: 72/531, loss: 0.02370734140276909
2023-01-21 09:30:27.306642: step: 76/531, loss: 0.04161777347326279
2023-01-21 09:30:28.419169: step: 80/531, loss: 0.3113865852355957
2023-01-21 09:30:29.550697: step: 84/531, loss: 0.3803182542324066
2023-01-21 09:30:30.673022: step: 88/531, loss: 0.08583936840295792
2023-01-21 09:30:31.792599: step: 92/531, loss: 0.13607101142406464
2023-01-21 09:30:32.908198: step: 96/531, loss: 1.4133756160736084
2023-01-21 09:30:34.043686: step: 100/531, loss: 0.34161150455474854
2023-01-21 09:30:35.144407: step: 104/531, loss: 0.066541388630867
2023-01-21 09:30:36.284984: step: 108/531, loss: 0.2006741464138031
2023-01-21 09:30:37.421564: step: 112/531, loss: 0.07147273421287537
2023-01-21 09:30:38.543809: step: 116/531, loss: 0.05142202600836754
2023-01-21 09:30:39.688829: step: 120/531, loss: 0.19109898805618286
2023-01-21 09:30:40.820170: step: 124/531, loss: 0.11739455163478851
2023-01-21 09:30:41.954761: step: 128/531, loss: 0.22635670006275177
2023-01-21 09:30:43.101294: step: 132/531, loss: 0.052965451031923294
2023-01-21 09:30:44.246111: step: 136/531, loss: 0.1725083440542221
2023-01-21 09:30:45.376126: step: 140/531, loss: 0.20802326500415802
2023-01-21 09:30:46.512625: step: 144/531, loss: 0.14394885301589966
2023-01-21 09:30:47.648532: step: 148/531, loss: 0.3046075701713562
2023-01-21 09:30:48.755301: step: 152/531, loss: 0.08211908489465714
2023-01-21 09:30:49.853901: step: 156/531, loss: 0.09998159110546112
2023-01-21 09:30:50.953468: step: 160/531, loss: 0.12419387698173523
2023-01-21 09:30:52.067220: step: 164/531, loss: 0.10426750034093857
2023-01-21 09:30:53.185047: step: 168/531, loss: 0.023827863857150078
2023-01-21 09:30:54.300830: step: 172/531, loss: 0.7307791709899902
2023-01-21 09:30:55.435912: step: 176/531, loss: 0.2617862820625305
2023-01-21 09:30:56.556183: step: 180/531, loss: 0.27173247933387756
2023-01-21 09:30:57.700625: step: 184/531, loss: 0.2729070782661438
2023-01-21 09:30:58.825032: step: 188/531, loss: 0.08730888366699219
2023-01-21 09:30:59.938842: step: 192/531, loss: 0.05043325573205948
2023-01-21 09:31:01.081711: step: 196/531, loss: 0.06647205352783203
2023-01-21 09:31:02.187557: step: 200/531, loss: 0.7661253213882446
2023-01-21 09:31:03.314384: step: 204/531, loss: 0.03455343469977379
2023-01-21 09:31:04.405084: step: 208/531, loss: 0.5179017186164856
2023-01-21 09:31:05.525633: step: 212/531, loss: 0.2024114727973938
2023-01-21 09:31:06.658198: step: 216/531, loss: 0.10241232067346573
2023-01-21 09:31:07.799838: step: 220/531, loss: 0.3304611146450043
2023-01-21 09:31:08.923894: step: 224/531, loss: 0.13528771698474884
2023-01-21 09:31:10.037933: step: 228/531, loss: 0.026763249188661575
2023-01-21 09:31:11.144056: step: 232/531, loss: 0.034537121653556824
2023-01-21 09:31:12.273119: step: 236/531, loss: 0.09236855804920197
2023-01-21 09:31:13.401084: step: 240/531, loss: 0.10965538024902344
2023-01-21 09:31:14.518046: step: 244/531, loss: 0.11902637034654617
2023-01-21 09:31:15.632853: step: 248/531, loss: 0.18522052466869354
2023-01-21 09:31:16.757529: step: 252/531, loss: 0.18175888061523438
2023-01-21 09:31:17.899336: step: 256/531, loss: 0.9082954525947571
2023-01-21 09:31:19.030222: step: 260/531, loss: 0.17686797678470612
2023-01-21 09:31:20.118944: step: 264/531, loss: 3.1346275806427
2023-01-21 09:31:21.261758: step: 268/531, loss: 0.18814867734909058
2023-01-21 09:31:22.385920: step: 272/531, loss: 0.2829253077507019
2023-01-21 09:31:23.495601: step: 276/531, loss: 0.014850925654172897
2023-01-21 09:31:24.639600: step: 280/531, loss: 0.17604750394821167
2023-01-21 09:31:25.773589: step: 284/531, loss: 0.052352048456668854
2023-01-21 09:31:26.929291: step: 288/531, loss: 0.057363320142030716
2023-01-21 09:31:28.053809: step: 292/531, loss: 0.12430057674646378
2023-01-21 09:31:29.181302: step: 296/531, loss: 0.09099988639354706
2023-01-21 09:31:30.327759: step: 300/531, loss: 0.11884613335132599
2023-01-21 09:31:31.438892: step: 304/531, loss: 0.058777764439582825
2023-01-21 09:31:32.556712: step: 308/531, loss: 0.4404264986515045
2023-01-21 09:31:33.673553: step: 312/531, loss: 0.047658681869506836
2023-01-21 09:31:34.783682: step: 316/531, loss: 0.14133863151073456
2023-01-21 09:31:35.921574: step: 320/531, loss: 0.10661507397890091
2023-01-21 09:31:37.059273: step: 324/531, loss: 0.16122861206531525
2023-01-21 09:31:38.184417: step: 328/531, loss: 0.10744023323059082
2023-01-21 09:31:39.287622: step: 332/531, loss: 0.1173584908246994
2023-01-21 09:31:40.400863: step: 336/531, loss: 0.07502040266990662
2023-01-21 09:31:41.521509: step: 340/531, loss: 0.07976703345775604
2023-01-21 09:31:42.663301: step: 344/531, loss: 0.07326493412256241
2023-01-21 09:31:43.811918: step: 348/531, loss: 0.1508421003818512
2023-01-21 09:31:44.932525: step: 352/531, loss: 0.05692138522863388
2023-01-21 09:31:46.055460: step: 356/531, loss: 0.04296588897705078
2023-01-21 09:31:47.157248: step: 360/531, loss: 0.07064338028430939
2023-01-21 09:31:48.280212: step: 364/531, loss: 0.0837317481637001
2023-01-21 09:31:49.414762: step: 368/531, loss: 0.5004148483276367
2023-01-21 09:31:50.551404: step: 372/531, loss: 0.10927124321460724
2023-01-21 09:31:51.760160: step: 376/531, loss: 0.144053652882576
2023-01-21 09:31:52.875501: step: 380/531, loss: 0.07450933754444122
2023-01-21 09:31:53.991278: step: 384/531, loss: 0.07858972251415253
2023-01-21 09:31:55.114631: step: 388/531, loss: 0.10665154457092285
2023-01-21 09:31:56.240548: step: 392/531, loss: 0.39680424332618713
2023-01-21 09:31:57.390121: step: 396/531, loss: 0.08854503929615021
2023-01-21 09:31:58.515402: step: 400/531, loss: 0.13796578347682953
2023-01-21 09:31:59.615886: step: 404/531, loss: 0.03624967113137245
2023-01-21 09:32:00.761907: step: 408/531, loss: 0.12699785828590393
2023-01-21 09:32:01.888331: step: 412/531, loss: 0.12611037492752075
2023-01-21 09:32:03.020307: step: 416/531, loss: 0.14851084351539612
2023-01-21 09:32:04.148717: step: 420/531, loss: 0.16934546828269958
2023-01-21 09:32:05.261295: step: 424/531, loss: 0.051219940185546875
2023-01-21 09:32:06.404132: step: 428/531, loss: 0.17968197166919708
2023-01-21 09:32:07.563395: step: 432/531, loss: 0.10771141946315765
2023-01-21 09:32:08.691569: step: 436/531, loss: 0.18436498939990997
2023-01-21 09:32:09.825568: step: 440/531, loss: 0.11564745754003525
2023-01-21 09:32:10.975024: step: 444/531, loss: 0.4060850739479065
2023-01-21 09:32:12.102923: step: 448/531, loss: 0.17578983306884766
2023-01-21 09:32:13.232455: step: 452/531, loss: 0.6279041767120361
2023-01-21 09:32:14.355711: step: 456/531, loss: 0.03740043565630913
2023-01-21 09:32:15.461254: step: 460/531, loss: 0.05715646594762802
2023-01-21 09:32:16.583424: step: 464/531, loss: 0.02419424243271351
2023-01-21 09:32:17.732821: step: 468/531, loss: 0.29996854066848755
2023-01-21 09:32:18.869331: step: 472/531, loss: 0.05887563154101372
2023-01-21 09:32:19.972124: step: 476/531, loss: 0.11404214054346085
2023-01-21 09:32:21.080934: step: 480/531, loss: 0.047014858573675156
2023-01-21 09:32:22.223628: step: 484/531, loss: 0.06032724305987358
2023-01-21 09:32:23.345842: step: 488/531, loss: 0.10072794556617737
2023-01-21 09:32:24.452888: step: 492/531, loss: 0.14510297775268555
2023-01-21 09:32:25.575535: step: 496/531, loss: 0.6866494417190552
2023-01-21 09:32:26.658530: step: 500/531, loss: 0.07605952769517899
2023-01-21 09:32:27.771962: step: 504/531, loss: 0.12150907516479492
2023-01-21 09:32:28.937485: step: 508/531, loss: 0.4043623208999634
2023-01-21 09:32:30.064894: step: 512/531, loss: 0.1951828896999359
2023-01-21 09:32:31.177681: step: 516/531, loss: 0.11251011490821838
2023-01-21 09:32:32.300635: step: 520/531, loss: 0.17454767227172852
2023-01-21 09:32:33.421644: step: 524/531, loss: 0.27790889143943787
2023-01-21 09:32:34.546517: step: 528/531, loss: 0.2730432450771332
2023-01-21 09:32:35.672443: step: 532/531, loss: 0.037294577807188034
2023-01-21 09:32:36.800632: step: 536/531, loss: 0.1082620620727539
2023-01-21 09:32:37.909444: step: 540/531, loss: 0.27188369631767273
2023-01-21 09:32:39.058336: step: 544/531, loss: 0.599617600440979
2023-01-21 09:32:40.180790: step: 548/531, loss: 0.13083668053150177
2023-01-21 09:32:41.341524: step: 552/531, loss: 0.13458271324634552
2023-01-21 09:32:42.449170: step: 556/531, loss: 0.21781493723392487
2023-01-21 09:32:43.616431: step: 560/531, loss: 0.17681331932544708
2023-01-21 09:32:44.750275: step: 564/531, loss: 0.18365205824375153
2023-01-21 09:32:45.897042: step: 568/531, loss: 0.051621437072753906
2023-01-21 09:32:46.994542: step: 572/531, loss: 0.16896170377731323
2023-01-21 09:32:48.126873: step: 576/531, loss: 0.05746364966034889
2023-01-21 09:32:49.266135: step: 580/531, loss: 0.2391793578863144
2023-01-21 09:32:50.360180: step: 584/531, loss: 0.033048346638679504
2023-01-21 09:32:51.468865: step: 588/531, loss: 0.14591558277606964
2023-01-21 09:32:52.595887: step: 592/531, loss: 0.12477359175682068
2023-01-21 09:32:53.728839: step: 596/531, loss: 0.04654426500201225
2023-01-21 09:32:54.848300: step: 600/531, loss: 0.16546869277954102
2023-01-21 09:32:55.982442: step: 604/531, loss: 0.1897704154253006
2023-01-21 09:32:57.091537: step: 608/531, loss: 0.2908203601837158
2023-01-21 09:32:58.236028: step: 612/531, loss: 0.18500156700611115
2023-01-21 09:32:59.342087: step: 616/531, loss: 0.07350310683250427
2023-01-21 09:33:00.503958: step: 620/531, loss: 0.769061803817749
2023-01-21 09:33:01.628195: step: 624/531, loss: 0.2006874978542328
2023-01-21 09:33:02.745256: step: 628/531, loss: 0.056610964238643646
2023-01-21 09:33:03.885487: step: 632/531, loss: 0.5713087320327759
2023-01-21 09:33:05.026556: step: 636/531, loss: 0.08168573677539825
2023-01-21 09:33:06.145641: step: 640/531, loss: 0.0675649642944336
2023-01-21 09:33:07.291615: step: 644/531, loss: 0.13331395387649536
2023-01-21 09:33:08.401424: step: 648/531, loss: 0.05531329661607742
2023-01-21 09:33:09.503323: step: 652/531, loss: 0.08608045428991318
2023-01-21 09:33:10.635263: step: 656/531, loss: 0.04052705690264702
2023-01-21 09:33:11.728383: step: 660/531, loss: 0.06458362936973572
2023-01-21 09:33:12.882083: step: 664/531, loss: 0.06878576427698135
2023-01-21 09:33:13.992544: step: 668/531, loss: 0.020014381036162376
2023-01-21 09:33:15.107768: step: 672/531, loss: 0.11570100486278534
2023-01-21 09:33:16.217969: step: 676/531, loss: 0.2233683466911316
2023-01-21 09:33:17.376058: step: 680/531, loss: 0.07184639573097229
2023-01-21 09:33:18.494412: step: 684/531, loss: 0.06851339340209961
2023-01-21 09:33:19.614975: step: 688/531, loss: 0.05257387459278107
2023-01-21 09:33:20.762833: step: 692/531, loss: 0.14796286821365356
2023-01-21 09:33:21.915350: step: 696/531, loss: 0.12064874172210693
2023-01-21 09:33:23.064776: step: 700/531, loss: 0.3232024312019348
2023-01-21 09:33:24.193117: step: 704/531, loss: 0.08355827629566193
2023-01-21 09:33:25.303744: step: 708/531, loss: 0.11572246253490448
2023-01-21 09:33:26.407981: step: 712/531, loss: 0.07285787165164948
2023-01-21 09:33:27.527405: step: 716/531, loss: 4.3935956954956055
2023-01-21 09:33:28.637743: step: 720/531, loss: 0.07533235847949982
2023-01-21 09:33:29.771048: step: 724/531, loss: 0.28046339750289917
2023-01-21 09:33:30.897558: step: 728/531, loss: 0.09323997795581818
2023-01-21 09:33:31.992934: step: 732/531, loss: 0.2850017845630646
2023-01-21 09:33:33.138139: step: 736/531, loss: 0.12449341267347336
2023-01-21 09:33:34.262409: step: 740/531, loss: 0.10894966870546341
2023-01-21 09:33:35.376496: step: 744/531, loss: 0.29797396063804626
2023-01-21 09:33:36.515138: step: 748/531, loss: 0.08677225559949875
2023-01-21 09:33:37.630236: step: 752/531, loss: 0.03188638761639595
2023-01-21 09:33:38.766528: step: 756/531, loss: 0.234467551112175
2023-01-21 09:33:39.942198: step: 760/531, loss: 0.15124782919883728
2023-01-21 09:33:41.067073: step: 764/531, loss: 0.060906603932380676
2023-01-21 09:33:42.192196: step: 768/531, loss: 0.2954982817173004
2023-01-21 09:33:43.320401: step: 772/531, loss: 1.5478538274765015
2023-01-21 09:33:44.469351: step: 776/531, loss: 0.14429546892642975
2023-01-21 09:33:45.611684: step: 780/531, loss: 0.13128575682640076
2023-01-21 09:33:46.744990: step: 784/531, loss: 0.06908436119556427
2023-01-21 09:33:47.878912: step: 788/531, loss: 0.055697061121463776
2023-01-21 09:33:49.013760: step: 792/531, loss: 0.14579400420188904
2023-01-21 09:33:50.186999: step: 796/531, loss: 0.3477696478366852
2023-01-21 09:33:51.307396: step: 800/531, loss: 0.21159076690673828
2023-01-21 09:33:52.436600: step: 804/531, loss: 0.09578704833984375
2023-01-21 09:33:53.546411: step: 808/531, loss: 0.006145763210952282
2023-01-21 09:33:54.637785: step: 812/531, loss: 0.0369715690612793
2023-01-21 09:33:55.759730: step: 816/531, loss: 0.224507138133049
2023-01-21 09:33:56.886694: step: 820/531, loss: 0.03605923801660538
2023-01-21 09:33:58.007475: step: 824/531, loss: 0.10636615753173828
2023-01-21 09:33:59.172820: step: 828/531, loss: 0.09716625511646271
2023-01-21 09:34:00.277486: step: 832/531, loss: 0.28910160064697266
2023-01-21 09:34:01.429472: step: 836/531, loss: 0.1595040261745453
2023-01-21 09:34:02.536313: step: 840/531, loss: 0.17244987189769745
2023-01-21 09:34:03.657624: step: 844/531, loss: 0.15272106230258942
2023-01-21 09:34:04.810342: step: 848/531, loss: 0.13193626701831818
2023-01-21 09:34:05.927863: step: 852/531, loss: 0.04718504101037979
2023-01-21 09:34:07.048470: step: 856/531, loss: 0.46101006865501404
2023-01-21 09:34:08.195762: step: 860/531, loss: 0.08861985057592392
2023-01-21 09:34:09.318424: step: 864/531, loss: 0.12921848893165588
2023-01-21 09:34:10.434453: step: 868/531, loss: 0.09247064590454102
2023-01-21 09:34:11.556857: step: 872/531, loss: 0.16542649269104004
2023-01-21 09:34:12.674599: step: 876/531, loss: 0.019962072372436523
2023-01-21 09:34:13.813679: step: 880/531, loss: 0.42561396956443787
2023-01-21 09:34:14.969516: step: 884/531, loss: 0.14377442002296448
2023-01-21 09:34:16.091282: step: 888/531, loss: 0.15072783827781677
2023-01-21 09:34:17.188923: step: 892/531, loss: 0.02132854424417019
2023-01-21 09:34:18.333688: step: 896/531, loss: 0.2323920577764511
2023-01-21 09:34:19.519917: step: 900/531, loss: 0.11164345592260361
2023-01-21 09:34:20.650129: step: 904/531, loss: 0.025049973279237747
2023-01-21 09:34:21.791011: step: 908/531, loss: 0.3214794099330902
2023-01-21 09:34:22.937623: step: 912/531, loss: 0.19006967544555664
2023-01-21 09:34:24.107914: step: 916/531, loss: 0.16841477155685425
2023-01-21 09:34:25.253753: step: 920/531, loss: 0.250888466835022
2023-01-21 09:34:26.385287: step: 924/531, loss: 0.12557382881641388
2023-01-21 09:34:27.505144: step: 928/531, loss: 0.35221004486083984
2023-01-21 09:34:28.601093: step: 932/531, loss: 0.2559264600276947
2023-01-21 09:34:29.746316: step: 936/531, loss: 0.06557230651378632
2023-01-21 09:34:30.871420: step: 940/531, loss: 0.1823142021894455
2023-01-21 09:34:32.012478: step: 944/531, loss: 0.07201795279979706
2023-01-21 09:34:33.145290: step: 948/531, loss: 0.10969076305627823
2023-01-21 09:34:34.249277: step: 952/531, loss: 0.08450870215892792
2023-01-21 09:34:35.356534: step: 956/531, loss: 0.14039382338523865
2023-01-21 09:34:36.476744: step: 960/531, loss: 0.31438225507736206
2023-01-21 09:34:37.618299: step: 964/531, loss: 0.052788637578487396
2023-01-21 09:34:38.760109: step: 968/531, loss: 0.2875572443008423
2023-01-21 09:34:39.881405: step: 972/531, loss: 0.29628047347068787
2023-01-21 09:34:41.004226: step: 976/531, loss: 0.20326100289821625
2023-01-21 09:34:42.144844: step: 980/531, loss: 0.056059934198856354
2023-01-21 09:34:43.296166: step: 984/531, loss: 0.3125864565372467
2023-01-21 09:34:44.416649: step: 988/531, loss: 0.12609940767288208
2023-01-21 09:34:45.522736: step: 992/531, loss: 0.11285920441150665
2023-01-21 09:34:46.653162: step: 996/531, loss: 0.2896064817905426
2023-01-21 09:34:47.784540: step: 1000/531, loss: 0.06711012870073318
2023-01-21 09:34:48.899941: step: 1004/531, loss: 0.09853621572256088
2023-01-21 09:34:50.049900: step: 1008/531, loss: 0.02158946916460991
2023-01-21 09:34:51.150235: step: 1012/531, loss: 0.11627483367919922
2023-01-21 09:34:52.291603: step: 1016/531, loss: 0.10537615418434143
2023-01-21 09:34:53.407714: step: 1020/531, loss: 0.14854831993579865
2023-01-21 09:34:54.549799: step: 1024/531, loss: 0.015804387629032135
2023-01-21 09:34:55.665352: step: 1028/531, loss: 0.015231514349579811
2023-01-21 09:34:56.764807: step: 1032/531, loss: 0.2993220388889313
2023-01-21 09:34:57.886485: step: 1036/531, loss: 0.09406204521656036
2023-01-21 09:34:59.042496: step: 1040/531, loss: 0.11330404877662659
2023-01-21 09:35:00.194418: step: 1044/531, loss: 0.1613851934671402
2023-01-21 09:35:01.320001: step: 1048/531, loss: 0.9376170039176941
2023-01-21 09:35:02.437585: step: 1052/531, loss: 0.11808130890130997
2023-01-21 09:35:03.560115: step: 1056/531, loss: 0.14249935746192932
2023-01-21 09:35:04.700890: step: 1060/531, loss: 0.11317737400531769
2023-01-21 09:35:05.789644: step: 1064/531, loss: 0.3029274046421051
2023-01-21 09:35:06.924582: step: 1068/531, loss: 0.6898200511932373
2023-01-21 09:35:08.059862: step: 1072/531, loss: 0.30431056022644043
2023-01-21 09:35:09.236332: step: 1076/531, loss: 0.4340066611766815
2023-01-21 09:35:10.391754: step: 1080/531, loss: 0.21096879243850708
2023-01-21 09:35:11.516928: step: 1084/531, loss: 0.15492820739746094
2023-01-21 09:35:12.648852: step: 1088/531, loss: 0.004761124029755592
2023-01-21 09:35:13.775146: step: 1092/531, loss: 0.32111504673957825
2023-01-21 09:35:14.902577: step: 1096/531, loss: 0.07185220718383789
2023-01-21 09:35:16.012426: step: 1100/531, loss: 0.10532474517822266
2023-01-21 09:35:17.122001: step: 1104/531, loss: 0.08373747020959854
2023-01-21 09:35:18.242474: step: 1108/531, loss: 0.08203456550836563
2023-01-21 09:35:19.359094: step: 1112/531, loss: 0.2745981216430664
2023-01-21 09:35:20.495983: step: 1116/531, loss: 0.3468250632286072
2023-01-21 09:35:21.619380: step: 1120/531, loss: 0.4775484800338745
2023-01-21 09:35:22.755041: step: 1124/531, loss: 0.06384305655956268
2023-01-21 09:35:23.896130: step: 1128/531, loss: 0.5880611538887024
2023-01-21 09:35:25.054958: step: 1132/531, loss: 0.2526895999908447
2023-01-21 09:35:26.175753: step: 1136/531, loss: 0.05344879627227783
2023-01-21 09:35:27.310718: step: 1140/531, loss: 0.4926597476005554
2023-01-21 09:35:28.432726: step: 1144/531, loss: 0.4103788137435913
2023-01-21 09:35:29.564396: step: 1148/531, loss: 0.19746990501880646
2023-01-21 09:35:30.689633: step: 1152/531, loss: 0.12178003787994385
2023-01-21 09:35:31.813896: step: 1156/531, loss: 0.01918773539364338
2023-01-21 09:35:32.925191: step: 1160/531, loss: 0.12922295928001404
2023-01-21 09:35:34.062939: step: 1164/531, loss: 0.19759425520896912
2023-01-21 09:35:35.233949: step: 1168/531, loss: 0.5998255610466003
2023-01-21 09:35:36.377658: step: 1172/531, loss: 0.15536099672317505
2023-01-21 09:35:37.480255: step: 1176/531, loss: 0.19426585733890533
2023-01-21 09:35:38.572594: step: 1180/531, loss: 0.5076694488525391
2023-01-21 09:35:39.697491: step: 1184/531, loss: 0.21503980457782745
2023-01-21 09:35:40.859110: step: 1188/531, loss: 0.32345110177993774
2023-01-21 09:35:41.978544: step: 1192/531, loss: 0.11697684228420258
2023-01-21 09:35:43.117896: step: 1196/531, loss: 0.030659865587949753
2023-01-21 09:35:44.260123: step: 1200/531, loss: 0.045653585344552994
2023-01-21 09:35:45.391174: step: 1204/531, loss: 0.44869834184646606
2023-01-21 09:35:46.515411: step: 1208/531, loss: 0.16037292778491974
2023-01-21 09:35:47.647114: step: 1212/531, loss: 0.28761324286460876
2023-01-21 09:35:48.783934: step: 1216/531, loss: 0.23707181215286255
2023-01-21 09:35:49.933165: step: 1220/531, loss: 0.2691915035247803
2023-01-21 09:35:51.071046: step: 1224/531, loss: 0.29456740617752075
2023-01-21 09:35:52.208088: step: 1228/531, loss: 0.0876397117972374
2023-01-21 09:35:53.311571: step: 1232/531, loss: 0.04653625562787056
2023-01-21 09:35:54.433773: step: 1236/531, loss: 0.14375333487987518
2023-01-21 09:35:55.592317: step: 1240/531, loss: 0.14601507782936096
2023-01-21 09:35:56.687887: step: 1244/531, loss: 0.15758351981639862
2023-01-21 09:35:57.806078: step: 1248/531, loss: 0.04013080522418022
2023-01-21 09:35:58.921364: step: 1252/531, loss: 0.27631139755249023
2023-01-21 09:36:00.015941: step: 1256/531, loss: 0.17404857277870178
2023-01-21 09:36:01.191155: step: 1260/531, loss: 0.1943032294511795
2023-01-21 09:36:02.316816: step: 1264/531, loss: 0.08693666756153107
2023-01-21 09:36:03.434804: step: 1268/531, loss: 0.13766680657863617
2023-01-21 09:36:04.567294: step: 1272/531, loss: 0.15110287070274353
2023-01-21 09:36:05.698423: step: 1276/531, loss: 0.13016252219676971
2023-01-21 09:36:06.827603: step: 1280/531, loss: 0.14342035353183746
2023-01-21 09:36:07.960644: step: 1284/531, loss: 0.3188708424568176
2023-01-21 09:36:09.079786: step: 1288/531, loss: 0.051337338984012604
2023-01-21 09:36:10.210563: step: 1292/531, loss: 0.05208597332239151
2023-01-21 09:36:11.314089: step: 1296/531, loss: 0.11120089888572693
2023-01-21 09:36:12.457309: step: 1300/531, loss: 0.06132388487458229
2023-01-21 09:36:13.571877: step: 1304/531, loss: 0.07340598106384277
2023-01-21 09:36:14.716306: step: 1308/531, loss: 0.19583159685134888
2023-01-21 09:36:15.836749: step: 1312/531, loss: 0.1412883698940277
2023-01-21 09:36:16.946458: step: 1316/531, loss: 0.9439733028411865
2023-01-21 09:36:18.087489: step: 1320/531, loss: 0.12769585847854614
2023-01-21 09:36:19.210220: step: 1324/531, loss: 0.8803343772888184
2023-01-21 09:36:20.324301: step: 1328/531, loss: 0.05707111209630966
2023-01-21 09:36:21.433203: step: 1332/531, loss: 0.09998345375061035
2023-01-21 09:36:22.568641: step: 1336/531, loss: 0.2742424011230469
2023-01-21 09:36:23.679239: step: 1340/531, loss: 0.05552246421575546
2023-01-21 09:36:24.793785: step: 1344/531, loss: 0.009540557861328125
2023-01-21 09:36:25.896216: step: 1348/531, loss: 0.2689172625541687
2023-01-21 09:36:27.005359: step: 1352/531, loss: 0.7166247367858887
2023-01-21 09:36:28.132392: step: 1356/531, loss: 0.9955601692199707
2023-01-21 09:36:29.246010: step: 1360/531, loss: 0.11669646203517914
2023-01-21 09:36:30.362483: step: 1364/531, loss: 0.06280384212732315
2023-01-21 09:36:31.486891: step: 1368/531, loss: 0.5324352383613586
2023-01-21 09:36:32.629634: step: 1372/531, loss: 0.11991424858570099
2023-01-21 09:36:33.745327: step: 1376/531, loss: 1.7557897567749023
2023-01-21 09:36:34.864170: step: 1380/531, loss: 0.022441577166318893
2023-01-21 09:36:35.987534: step: 1384/531, loss: 0.1754746437072754
2023-01-21 09:36:37.105563: step: 1388/531, loss: 0.12215381115674973
2023-01-21 09:36:38.242121: step: 1392/531, loss: 0.09779481589794159
2023-01-21 09:36:39.356492: step: 1396/531, loss: 4.513215065002441
2023-01-21 09:36:40.473174: step: 1400/531, loss: 0.11455898731946945
2023-01-21 09:36:41.601210: step: 1404/531, loss: 0.15640844404697418
2023-01-21 09:36:42.763456: step: 1408/531, loss: 0.45267730951309204
2023-01-21 09:36:43.906888: step: 1412/531, loss: 0.34884214401245117
2023-01-21 09:36:45.028791: step: 1416/531, loss: 0.1205865889787674
2023-01-21 09:36:46.141577: step: 1420/531, loss: 0.0617460235953331
2023-01-21 09:36:47.250750: step: 1424/531, loss: 0.49670809507369995
2023-01-21 09:36:48.351469: step: 1428/531, loss: 0.06849632412195206
2023-01-21 09:36:49.482790: step: 1432/531, loss: 0.05942802503705025
2023-01-21 09:36:50.635211: step: 1436/531, loss: 0.07851801067590714
2023-01-21 09:36:51.727191: step: 1440/531, loss: 0.1911487579345703
2023-01-21 09:36:52.842993: step: 1444/531, loss: 0.1471824198961258
2023-01-21 09:36:53.965961: step: 1448/531, loss: 0.30402088165283203
2023-01-21 09:36:55.088721: step: 1452/531, loss: 0.25854140520095825
2023-01-21 09:36:56.221507: step: 1456/531, loss: 0.04099883884191513
2023-01-21 09:36:57.339558: step: 1460/531, loss: 0.17804959416389465
2023-01-21 09:36:58.458101: step: 1464/531, loss: 0.14124146103858948
2023-01-21 09:36:59.578326: step: 1468/531, loss: 0.8882207274436951
2023-01-21 09:37:00.723772: step: 1472/531, loss: 0.2734433710575104
2023-01-21 09:37:01.856479: step: 1476/531, loss: 0.13528390228748322
2023-01-21 09:37:02.976096: step: 1480/531, loss: 0.10020236670970917
2023-01-21 09:37:04.120654: step: 1484/531, loss: 0.1824178844690323
2023-01-21 09:37:05.296659: step: 1488/531, loss: 0.3533852994441986
2023-01-21 09:37:06.408590: step: 1492/531, loss: 0.3690573573112488
2023-01-21 09:37:07.544554: step: 1496/531, loss: 0.12082615494728088
2023-01-21 09:37:08.687381: step: 1500/531, loss: 0.12484579533338547
2023-01-21 09:37:09.817935: step: 1504/531, loss: 0.30373719334602356
2023-01-21 09:37:10.944013: step: 1508/531, loss: 0.035973407328128815
2023-01-21 09:37:12.095554: step: 1512/531, loss: 0.03906526416540146
2023-01-21 09:37:13.235892: step: 1516/531, loss: 0.07915530353784561
2023-01-21 09:37:14.367031: step: 1520/531, loss: 0.005004453472793102
2023-01-21 09:37:15.480283: step: 1524/531, loss: 0.10526444762945175
2023-01-21 09:37:16.606181: step: 1528/531, loss: 0.08911371231079102
2023-01-21 09:37:17.764823: step: 1532/531, loss: 0.1121458038687706
2023-01-21 09:37:18.892636: step: 1536/531, loss: 0.19884338974952698
2023-01-21 09:37:19.999692: step: 1540/531, loss: 0.174523264169693
2023-01-21 09:37:21.124137: step: 1544/531, loss: 0.11093469709157944
2023-01-21 09:37:22.245627: step: 1548/531, loss: 0.26886826753616333
2023-01-21 09:37:23.376018: step: 1552/531, loss: 0.08956921100616455
2023-01-21 09:37:24.488414: step: 1556/531, loss: 0.15122194588184357
2023-01-21 09:37:25.625140: step: 1560/531, loss: 0.2928595542907715
2023-01-21 09:37:26.767991: step: 1564/531, loss: 0.18391390144824982
2023-01-21 09:37:27.902857: step: 1568/531, loss: 0.4468950927257538
2023-01-21 09:37:29.031820: step: 1572/531, loss: 0.10531225800514221
2023-01-21 09:37:30.147283: step: 1576/531, loss: 0.10413676500320435
2023-01-21 09:37:31.275631: step: 1580/531, loss: 0.1386483758687973
2023-01-21 09:37:32.387630: step: 1584/531, loss: 0.2914878726005554
2023-01-21 09:37:33.515218: step: 1588/531, loss: 0.29573917388916016
2023-01-21 09:37:34.630460: step: 1592/531, loss: 0.33285731077194214
2023-01-21 09:37:35.750495: step: 1596/531, loss: 0.49965807795524597
2023-01-21 09:37:36.866652: step: 1600/531, loss: 0.07334871590137482
2023-01-21 09:37:38.005159: step: 1604/531, loss: 0.13643741607666016
2023-01-21 09:37:39.133909: step: 1608/531, loss: 0.03537602350115776
2023-01-21 09:37:40.280617: step: 1612/531, loss: 0.30862337350845337
2023-01-21 09:37:41.415038: step: 1616/531, loss: 0.0699569582939148
2023-01-21 09:37:42.590841: step: 1620/531, loss: 0.08563575893640518
2023-01-21 09:37:43.719891: step: 1624/531, loss: 0.09937821328639984
2023-01-21 09:37:44.827043: step: 1628/531, loss: 1.1821191310882568
2023-01-21 09:37:45.949267: step: 1632/531, loss: 0.07876958698034286
2023-01-21 09:37:47.092287: step: 1636/531, loss: 0.34555259346961975
2023-01-21 09:37:48.225510: step: 1640/531, loss: 0.1000639945268631
2023-01-21 09:37:49.341429: step: 1644/531, loss: 0.23995858430862427
2023-01-21 09:37:50.501477: step: 1648/531, loss: 0.15299482643604279
2023-01-21 09:37:51.606204: step: 1652/531, loss: 0.48042032122612
2023-01-21 09:37:52.737224: step: 1656/531, loss: 0.13149146735668182
2023-01-21 09:37:53.888878: step: 1660/531, loss: 0.16275987029075623
2023-01-21 09:37:55.013238: step: 1664/531, loss: 0.6057541966438293
2023-01-21 09:37:56.163253: step: 1668/531, loss: 0.09899254143238068
2023-01-21 09:37:57.317738: step: 1672/531, loss: 0.3080213963985443
2023-01-21 09:37:58.440485: step: 1676/531, loss: 0.08646812289953232
2023-01-21 09:37:59.543378: step: 1680/531, loss: 0.47820383310317993
2023-01-21 09:38:00.663351: step: 1684/531, loss: 0.07515960186719894
2023-01-21 09:38:01.782576: step: 1688/531, loss: 0.14665627479553223
2023-01-21 09:38:02.919495: step: 1692/531, loss: 0.1035272628068924
2023-01-21 09:38:04.030078: step: 1696/531, loss: 0.06674177944660187
2023-01-21 09:38:05.165528: step: 1700/531, loss: 0.23921889066696167
2023-01-21 09:38:06.290432: step: 1704/531, loss: 0.1536807119846344
2023-01-21 09:38:07.423905: step: 1708/531, loss: 0.19392962753772736
2023-01-21 09:38:08.562745: step: 1712/531, loss: 0.07393474876880646
2023-01-21 09:38:09.682833: step: 1716/531, loss: 0.04834197834134102
2023-01-21 09:38:10.827062: step: 1720/531, loss: 0.1221797987818718
2023-01-21 09:38:11.974513: step: 1724/531, loss: 0.27693310379981995
2023-01-21 09:38:13.122258: step: 1728/531, loss: 0.07360410690307617
2023-01-21 09:38:14.243620: step: 1732/531, loss: 0.015581751242280006
2023-01-21 09:38:15.361802: step: 1736/531, loss: 0.18243809044361115
2023-01-21 09:38:16.508526: step: 1740/531, loss: 0.10712333023548126
2023-01-21 09:38:17.632761: step: 1744/531, loss: 0.10772786289453506
2023-01-21 09:38:18.734195: step: 1748/531, loss: 0.09582405537366867
2023-01-21 09:38:19.846718: step: 1752/531, loss: 0.03783788904547691
2023-01-21 09:38:20.954872: step: 1756/531, loss: 0.04986685886979103
2023-01-21 09:38:22.061414: step: 1760/531, loss: 0.14363345503807068
2023-01-21 09:38:23.186916: step: 1764/531, loss: 0.09788118302822113
2023-01-21 09:38:24.323732: step: 1768/531, loss: 0.07006435096263885
2023-01-21 09:38:25.460751: step: 1772/531, loss: 0.053702641278505325
2023-01-21 09:38:26.599957: step: 1776/531, loss: 0.21209116280078888
2023-01-21 09:38:27.740042: step: 1780/531, loss: 0.14365005493164062
2023-01-21 09:38:28.879461: step: 1784/531, loss: 0.11875534057617188
2023-01-21 09:38:30.033007: step: 1788/531, loss: 0.4750362038612366
2023-01-21 09:38:31.158253: step: 1792/531, loss: 0.20035740733146667
2023-01-21 09:38:32.299827: step: 1796/531, loss: 0.0603879950940609
2023-01-21 09:38:33.438006: step: 1800/531, loss: 0.04758801311254501
2023-01-21 09:38:34.592185: step: 1804/531, loss: 0.8994182348251343
2023-01-21 09:38:35.731084: step: 1808/531, loss: 0.3572255074977875
2023-01-21 09:38:36.885640: step: 1812/531, loss: 0.3359192907810211
2023-01-21 09:38:38.035003: step: 1816/531, loss: 0.14851704239845276
2023-01-21 09:38:39.149584: step: 1820/531, loss: 0.0450710766017437
2023-01-21 09:38:40.323010: step: 1824/531, loss: 0.16118574142456055
2023-01-21 09:38:41.454507: step: 1828/531, loss: 0.30910825729370117
2023-01-21 09:38:42.631706: step: 1832/531, loss: 0.05252084881067276
2023-01-21 09:38:43.756680: step: 1836/531, loss: 0.23340129852294922
2023-01-21 09:38:44.901563: step: 1840/531, loss: 0.13735082745552063
2023-01-21 09:38:46.021877: step: 1844/531, loss: 0.532707691192627
2023-01-21 09:38:47.150663: step: 1848/531, loss: 0.04306596517562866
2023-01-21 09:38:48.297096: step: 1852/531, loss: 0.16566598415374756
2023-01-21 09:38:49.449484: step: 1856/531, loss: 0.060712434351444244
2023-01-21 09:38:50.566488: step: 1860/531, loss: 0.4060153067111969
2023-01-21 09:38:51.694963: step: 1864/531, loss: 0.039585210382938385
2023-01-21 09:38:52.814954: step: 1868/531, loss: 0.39462631940841675
2023-01-21 09:38:53.932006: step: 1872/531, loss: 0.15696831047534943
2023-01-21 09:38:55.058501: step: 1876/531, loss: 0.8997449278831482
2023-01-21 09:38:56.183187: step: 1880/531, loss: 0.20953330397605896
2023-01-21 09:38:57.316887: step: 1884/531, loss: 0.0996655523777008
2023-01-21 09:38:58.423616: step: 1888/531, loss: 0.47123146057128906
2023-01-21 09:38:59.540340: step: 1892/531, loss: 0.13718290627002716
2023-01-21 09:39:00.679526: step: 1896/531, loss: 0.19029779732227325
2023-01-21 09:39:01.809725: step: 1900/531, loss: 0.19887980818748474
2023-01-21 09:39:02.906639: step: 1904/531, loss: 0.024227716028690338
2023-01-21 09:39:04.012569: step: 1908/531, loss: 0.13054236769676208
2023-01-21 09:39:05.141925: step: 1912/531, loss: 0.08709659427404404
2023-01-21 09:39:06.322695: step: 1916/531, loss: 0.05153237283229828
2023-01-21 09:39:07.410705: step: 1920/531, loss: 0.040041614323854446
2023-01-21 09:39:08.531649: step: 1924/531, loss: 0.08991570770740509
2023-01-21 09:39:09.690775: step: 1928/531, loss: 0.7397158145904541
2023-01-21 09:39:10.856702: step: 1932/531, loss: 0.03327503055334091
2023-01-21 09:39:12.015946: step: 1936/531, loss: 0.06251826137304306
2023-01-21 09:39:13.153678: step: 1940/531, loss: 0.29227766394615173
2023-01-21 09:39:14.278328: step: 1944/531, loss: 0.24235452711582184
2023-01-21 09:39:15.386039: step: 1948/531, loss: 0.3568245470523834
2023-01-21 09:39:16.515021: step: 1952/531, loss: 0.10946788638830185
2023-01-21 09:39:17.625544: step: 1956/531, loss: 0.17433635890483856
2023-01-21 09:39:18.723765: step: 1960/531, loss: 0.02267162874341011
2023-01-21 09:39:19.867628: step: 1964/531, loss: 0.03350190818309784
2023-01-21 09:39:21.003460: step: 1968/531, loss: 0.06581374257802963
2023-01-21 09:39:22.137797: step: 1972/531, loss: 0.48753586411476135
2023-01-21 09:39:23.274560: step: 1976/531, loss: 0.41141003370285034
2023-01-21 09:39:24.396051: step: 1980/531, loss: 0.14639610052108765
2023-01-21 09:39:25.521597: step: 1984/531, loss: 0.6341049075126648
2023-01-21 09:39:26.649470: step: 1988/531, loss: 0.327711284160614
2023-01-21 09:39:27.769869: step: 1992/531, loss: 0.016730882227420807
2023-01-21 09:39:28.896724: step: 1996/531, loss: 0.07582951337099075
2023-01-21 09:39:30.027020: step: 2000/531, loss: 0.24256345629692078
2023-01-21 09:39:31.173346: step: 2004/531, loss: 0.680566668510437
2023-01-21 09:39:32.274826: step: 2008/531, loss: 0.18523502349853516
2023-01-21 09:39:33.394692: step: 2012/531, loss: 0.1843395233154297
2023-01-21 09:39:34.518565: step: 2016/531, loss: 0.39234840869903564
2023-01-21 09:39:35.659433: step: 2020/531, loss: 0.06970968097448349
2023-01-21 09:39:36.767371: step: 2024/531, loss: 0.45255327224731445
2023-01-21 09:39:37.883434: step: 2028/531, loss: 0.04113595560193062
2023-01-21 09:39:39.008074: step: 2032/531, loss: 0.0591922290623188
2023-01-21 09:39:40.134976: step: 2036/531, loss: 0.4618026614189148
2023-01-21 09:39:41.273497: step: 2040/531, loss: 0.14358139038085938
2023-01-21 09:39:42.394747: step: 2044/531, loss: 0.06845646351575851
2023-01-21 09:39:43.509575: step: 2048/531, loss: 0.13484154641628265
2023-01-21 09:39:44.657717: step: 2052/531, loss: 0.074066162109375
2023-01-21 09:39:45.825904: step: 2056/531, loss: 0.11598539352416992
2023-01-21 09:39:46.959280: step: 2060/531, loss: 0.2781764566898346
2023-01-21 09:39:48.095352: step: 2064/531, loss: 0.13594137132167816
2023-01-21 09:39:49.224408: step: 2068/531, loss: 0.034331224858760834
2023-01-21 09:39:50.352916: step: 2072/531, loss: 0.22666719555854797
2023-01-21 09:39:51.515915: step: 2076/531, loss: 0.1427541822195053
2023-01-21 09:39:52.613130: step: 2080/531, loss: 0.05288839340209961
2023-01-21 09:39:53.731474: step: 2084/531, loss: 0.18077774345874786
2023-01-21 09:39:54.849868: step: 2088/531, loss: 0.0589456707239151
2023-01-21 09:39:55.947547: step: 2092/531, loss: 0.19929802417755127
2023-01-21 09:39:57.078778: step: 2096/531, loss: 0.06978168338537216
2023-01-21 09:39:58.162911: step: 2100/531, loss: 0.0208948515355587
2023-01-21 09:39:59.275269: step: 2104/531, loss: 0.22816124558448792
2023-01-21 09:40:00.410452: step: 2108/531, loss: 0.6041961312294006
2023-01-21 09:40:01.584599: step: 2112/531, loss: 0.277596116065979
2023-01-21 09:40:02.740742: step: 2116/531, loss: 0.20652687549591064
2023-01-21 09:40:03.901263: step: 2120/531, loss: 0.7925464510917664
2023-01-21 09:40:05.027343: step: 2124/531, loss: 0.09546632319688797
==================================================
Loss: 0.220
--------------------
Dev: {'event': {'p': 0.6341463414634146, 'r': 0.7270306258322237, 'f1': 0.6774193548387097}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6328794755421079, 'r': 0.7483601669648181, 'f1': 0.6857923497267759}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.717948717948718, 'r': 0.4444444444444444, 'f1': 0.5490196078431373}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5440900562851783, 'r': 0.7723035952063915, 'f1': 0.6384149697303247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.5672823218997362, 'r': 0.7692307692307693, 'f1': 0.6529992406985574}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6557377049180327, 'r': 0.6349206349206349, 'f1': 0.6451612903225806}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6341463414634146, 'r': 0.7270306258322237, 'f1': 0.6774193548387097}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6328794755421079, 'r': 0.7483601669648181, 'f1': 0.6857923497267759}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:40:49.810058: step: 4/531, loss: 0.07043810188770294
2023-01-21 09:40:50.916593: step: 8/531, loss: 0.10553699731826782
2023-01-21 09:40:52.048430: step: 12/531, loss: 0.09284356236457825
2023-01-21 09:40:53.233402: step: 16/531, loss: 0.07346749305725098
2023-01-21 09:40:54.350037: step: 20/531, loss: 0.0006258010980673134
2023-01-21 09:40:55.476826: step: 24/531, loss: 0.09264421463012695
2023-01-21 09:40:56.609233: step: 28/531, loss: 0.13885116577148438
2023-01-21 09:40:57.759373: step: 32/531, loss: 0.1623314619064331
2023-01-21 09:40:58.935603: step: 36/531, loss: 0.06133217737078667
2023-01-21 09:41:00.058269: step: 40/531, loss: 0.025447798892855644
2023-01-21 09:41:01.176520: step: 44/531, loss: 0.11186742782592773
2023-01-21 09:41:02.291932: step: 48/531, loss: 0.02981090545654297
2023-01-21 09:41:03.412699: step: 52/531, loss: 0.029117824509739876
2023-01-21 09:41:04.566464: step: 56/531, loss: 0.4157348871231079
2023-01-21 09:41:05.721479: step: 60/531, loss: 0.7605549097061157
2023-01-21 09:41:06.842664: step: 64/531, loss: 0.05197324603796005
2023-01-21 09:41:07.953527: step: 68/531, loss: 0.13566988706588745
2023-01-21 09:41:09.093655: step: 72/531, loss: 0.25406399369239807
2023-01-21 09:41:10.188842: step: 76/531, loss: 0.10325708240270615
2023-01-21 09:41:11.286360: step: 80/531, loss: 0.1093946024775505
2023-01-21 09:41:12.429120: step: 84/531, loss: 0.21392956376075745
2023-01-21 09:41:13.534080: step: 88/531, loss: 0.07840041816234589
2023-01-21 09:41:14.660604: step: 92/531, loss: 0.16843782365322113
2023-01-21 09:41:15.767697: step: 96/531, loss: 0.05662889778614044
2023-01-21 09:41:16.870115: step: 100/531, loss: 0.0841674879193306
2023-01-21 09:41:18.032332: step: 104/531, loss: 0.12745200097560883
2023-01-21 09:41:19.148067: step: 108/531, loss: 0.18303155899047852
2023-01-21 09:41:20.264717: step: 112/531, loss: 0.18164515495300293
2023-01-21 09:41:21.421621: step: 116/531, loss: 0.19314762949943542
2023-01-21 09:41:22.548516: step: 120/531, loss: 0.004279470071196556
2023-01-21 09:41:23.738857: step: 124/531, loss: 0.13550348579883575
2023-01-21 09:41:24.866936: step: 128/531, loss: 0.9660297632217407
2023-01-21 09:41:26.009952: step: 132/531, loss: 0.2043839544057846
2023-01-21 09:41:27.139536: step: 136/531, loss: 0.10098914802074432
2023-01-21 09:41:28.312146: step: 140/531, loss: 0.11982069164514542
2023-01-21 09:41:29.492171: step: 144/531, loss: 0.02806832268834114
2023-01-21 09:41:30.610476: step: 148/531, loss: 0.11593222618103027
2023-01-21 09:41:31.708003: step: 152/531, loss: 0.07075939327478409
2023-01-21 09:41:32.868103: step: 156/531, loss: 0.13400134444236755
2023-01-21 09:41:34.025320: step: 160/531, loss: 0.06865911185741425
2023-01-21 09:41:35.156368: step: 164/531, loss: 0.02464580535888672
2023-01-21 09:41:36.292177: step: 168/531, loss: 0.205671027302742
2023-01-21 09:41:37.415377: step: 172/531, loss: 0.03251934051513672
2023-01-21 09:41:38.531738: step: 176/531, loss: 0.07147588580846786
2023-01-21 09:41:39.659835: step: 180/531, loss: 0.06803826242685318
2023-01-21 09:41:40.779954: step: 184/531, loss: 0.13635559380054474
2023-01-21 09:41:41.940448: step: 188/531, loss: 0.03813920170068741
2023-01-21 09:41:43.048545: step: 192/531, loss: 0.19532173871994019
2023-01-21 09:41:44.178526: step: 196/531, loss: 0.036008551716804504
2023-01-21 09:41:45.302835: step: 200/531, loss: 0.028285982087254524
2023-01-21 09:41:46.394846: step: 204/531, loss: 0.1155426949262619
2023-01-21 09:41:47.504088: step: 208/531, loss: 0.43132781982421875
2023-01-21 09:41:48.612776: step: 212/531, loss: 0.216070756316185
2023-01-21 09:41:49.741897: step: 216/531, loss: 0.03134775161743164
2023-01-21 09:41:50.878559: step: 220/531, loss: 0.201005756855011
2023-01-21 09:41:52.011766: step: 224/531, loss: 0.1663801074028015
2023-01-21 09:41:53.126990: step: 228/531, loss: 0.20485468208789825
2023-01-21 09:41:54.270276: step: 232/531, loss: 0.05807044729590416
2023-01-21 09:41:55.347712: step: 236/531, loss: 0.03855285793542862
2023-01-21 09:41:56.445468: step: 240/531, loss: 0.3140796720981598
2023-01-21 09:41:57.559932: step: 244/531, loss: 0.07671451568603516
2023-01-21 09:41:58.668518: step: 248/531, loss: 0.13200493156909943
2023-01-21 09:41:59.778065: step: 252/531, loss: 0.14742641150951385
2023-01-21 09:42:00.906631: step: 256/531, loss: 0.6432132720947266
2023-01-21 09:42:02.026156: step: 260/531, loss: 0.3542617857456207
2023-01-21 09:42:03.178124: step: 264/531, loss: 0.052869513630867004
2023-01-21 09:42:04.292414: step: 268/531, loss: 0.19288387894630432
2023-01-21 09:42:05.405957: step: 272/531, loss: 0.06808986514806747
2023-01-21 09:42:06.612698: step: 276/531, loss: 0.18539771437644958
2023-01-21 09:42:07.741270: step: 280/531, loss: 0.09230299293994904
2023-01-21 09:42:08.873062: step: 284/531, loss: 0.25081387162208557
2023-01-21 09:42:10.006099: step: 288/531, loss: 0.034148551523685455
2023-01-21 09:42:11.135537: step: 292/531, loss: 0.31364166736602783
2023-01-21 09:42:12.249869: step: 296/531, loss: 0.06507282704114914
2023-01-21 09:42:13.370372: step: 300/531, loss: 0.09602861106395721
2023-01-21 09:42:14.477059: step: 304/531, loss: 0.03367586433887482
2023-01-21 09:42:15.600745: step: 308/531, loss: 0.057691290974617004
2023-01-21 09:42:16.707372: step: 312/531, loss: 0.12167918682098389
2023-01-21 09:42:17.815025: step: 316/531, loss: 0.07826504856348038
2023-01-21 09:42:18.947851: step: 320/531, loss: 0.07062100619077682
2023-01-21 09:42:20.057881: step: 324/531, loss: 0.0921703353524208
2023-01-21 09:42:21.190852: step: 328/531, loss: 0.15968933701515198
2023-01-21 09:42:22.316883: step: 332/531, loss: 0.06463050842285156
2023-01-21 09:42:23.439101: step: 336/531, loss: 0.035058051347732544
2023-01-21 09:42:24.548086: step: 340/531, loss: 0.06314316391944885
2023-01-21 09:42:25.655354: step: 344/531, loss: 0.07324714958667755
2023-01-21 09:42:26.803985: step: 348/531, loss: 0.3959523141384125
2023-01-21 09:42:27.957224: step: 352/531, loss: 0.11822903156280518
2023-01-21 09:42:29.078641: step: 356/531, loss: 0.062113240361213684
2023-01-21 09:42:30.192349: step: 360/531, loss: 0.12607058882713318
2023-01-21 09:42:31.318701: step: 364/531, loss: 0.1403324156999588
2023-01-21 09:42:32.448530: step: 368/531, loss: 0.007817650213837624
2023-01-21 09:42:33.596521: step: 372/531, loss: 0.33558589220046997
2023-01-21 09:42:34.722218: step: 376/531, loss: 0.0747016966342926
2023-01-21 09:42:35.836775: step: 380/531, loss: 0.12668228149414062
2023-01-21 09:42:36.968582: step: 384/531, loss: 0.19364416599273682
2023-01-21 09:42:38.052412: step: 388/531, loss: 0.02216210402548313
2023-01-21 09:42:39.201207: step: 392/531, loss: 0.019629955291748047
2023-01-21 09:42:40.325287: step: 396/531, loss: 0.03158894553780556
2023-01-21 09:42:41.444074: step: 400/531, loss: 0.06251172721385956
2023-01-21 09:42:42.551883: step: 404/531, loss: 0.1830941140651703
2023-01-21 09:42:43.669510: step: 408/531, loss: 0.18001490831375122
2023-01-21 09:42:44.791879: step: 412/531, loss: 0.09499998390674591
2023-01-21 09:42:45.922855: step: 416/531, loss: 0.26958349347114563
2023-01-21 09:42:47.013969: step: 420/531, loss: 0.01233301218599081
2023-01-21 09:42:48.113189: step: 424/531, loss: 0.15814343094825745
2023-01-21 09:42:49.230636: step: 428/531, loss: 0.1123630553483963
2023-01-21 09:42:50.342127: step: 432/531, loss: 0.10992403328418732
2023-01-21 09:42:51.449703: step: 436/531, loss: 0.12458506226539612
2023-01-21 09:42:52.569392: step: 440/531, loss: 0.12730321288108826
2023-01-21 09:42:53.713169: step: 444/531, loss: 0.05852989852428436
2023-01-21 09:42:54.829821: step: 448/531, loss: 0.0977010726928711
2023-01-21 09:42:55.926014: step: 452/531, loss: 0.0946040228009224
2023-01-21 09:42:57.038358: step: 456/531, loss: 0.059867192059755325
2023-01-21 09:42:58.158394: step: 460/531, loss: 0.03374843671917915
2023-01-21 09:42:59.276620: step: 464/531, loss: 0.14702625572681427
2023-01-21 09:43:00.375715: step: 468/531, loss: 0.3507455885410309
2023-01-21 09:43:01.497284: step: 472/531, loss: 0.5204029083251953
2023-01-21 09:43:02.636764: step: 476/531, loss: 0.13334789872169495
2023-01-21 09:43:03.749824: step: 480/531, loss: 0.04629345238208771
2023-01-21 09:43:04.899495: step: 484/531, loss: 0.008711290545761585
2023-01-21 09:43:06.005705: step: 488/531, loss: 0.1234511211514473
2023-01-21 09:43:07.125470: step: 492/531, loss: 0.046222761273384094
2023-01-21 09:43:08.277659: step: 496/531, loss: 0.5264490842819214
2023-01-21 09:43:09.404655: step: 500/531, loss: 0.08505754172801971
2023-01-21 09:43:10.506589: step: 504/531, loss: 0.12540502846240997
2023-01-21 09:43:11.604755: step: 508/531, loss: 0.04753284528851509
2023-01-21 09:43:12.737675: step: 512/531, loss: 0.1117459237575531
2023-01-21 09:43:13.886346: step: 516/531, loss: 0.14420872926712036
2023-01-21 09:43:15.023289: step: 520/531, loss: 0.06652151048183441
2023-01-21 09:43:16.119917: step: 524/531, loss: 0.009200763888657093
2023-01-21 09:43:17.249575: step: 528/531, loss: 0.02844679355621338
2023-01-21 09:43:18.390811: step: 532/531, loss: 0.08461914956569672
2023-01-21 09:43:19.538540: step: 536/531, loss: 0.04467616230249405
2023-01-21 09:43:20.665633: step: 540/531, loss: 0.05932598188519478
2023-01-21 09:43:21.780996: step: 544/531, loss: 0.17919273674488068
2023-01-21 09:43:22.917249: step: 548/531, loss: 0.12711143493652344
2023-01-21 09:43:24.070229: step: 552/531, loss: 0.0872282087802887
2023-01-21 09:43:25.208042: step: 556/531, loss: 0.3747473955154419
2023-01-21 09:43:26.316999: step: 560/531, loss: 0.23570489883422852
2023-01-21 09:43:27.433148: step: 564/531, loss: 0.1573580652475357
2023-01-21 09:43:28.549280: step: 568/531, loss: 0.01681988313794136
2023-01-21 09:43:29.676238: step: 572/531, loss: 0.14629077911376953
2023-01-21 09:43:30.821152: step: 576/531, loss: 0.12140703201293945
2023-01-21 09:43:31.954738: step: 580/531, loss: 0.22671937942504883
2023-01-21 09:43:33.062034: step: 584/531, loss: 0.21995753049850464
2023-01-21 09:43:34.204169: step: 588/531, loss: 0.07481873035430908
2023-01-21 09:43:35.353739: step: 592/531, loss: 0.040781259536743164
2023-01-21 09:43:36.457359: step: 596/531, loss: 0.13340292870998383
2023-01-21 09:43:37.570161: step: 600/531, loss: 0.05432162433862686
2023-01-21 09:43:38.715840: step: 604/531, loss: 0.08480659127235413
2023-01-21 09:43:39.846764: step: 608/531, loss: 0.14956489205360413
2023-01-21 09:43:40.972499: step: 612/531, loss: 0.1737562119960785
2023-01-21 09:43:42.107659: step: 616/531, loss: 0.04875154793262482
2023-01-21 09:43:43.262271: step: 620/531, loss: 0.2536260485649109
2023-01-21 09:43:44.376080: step: 624/531, loss: 0.15681058168411255
2023-01-21 09:43:45.507311: step: 628/531, loss: 0.09617605805397034
2023-01-21 09:43:46.622888: step: 632/531, loss: 0.16250906884670258
2023-01-21 09:43:47.757163: step: 636/531, loss: 0.04505458101630211
2023-01-21 09:43:48.832750: step: 640/531, loss: 0.14508800208568573
2023-01-21 09:43:49.962576: step: 644/531, loss: 0.1883261352777481
2023-01-21 09:43:51.114458: step: 648/531, loss: 0.027052687481045723
2023-01-21 09:43:52.243816: step: 652/531, loss: 0.1003628522157669
2023-01-21 09:43:53.373565: step: 656/531, loss: 0.057857707142829895
2023-01-21 09:43:54.506885: step: 660/531, loss: 0.10964766144752502
2023-01-21 09:43:55.625189: step: 664/531, loss: 0.20194792747497559
2023-01-21 09:43:56.732584: step: 668/531, loss: 0.25048828125
2023-01-21 09:43:57.840604: step: 672/531, loss: 0.12961697578430176
2023-01-21 09:43:58.989515: step: 676/531, loss: 0.27555981278419495
2023-01-21 09:44:00.136545: step: 680/531, loss: 0.2224808633327484
2023-01-21 09:44:01.254903: step: 684/531, loss: 0.15243959426879883
2023-01-21 09:44:02.375975: step: 688/531, loss: 0.07391514629125595
2023-01-21 09:44:03.494098: step: 692/531, loss: 0.2605249285697937
2023-01-21 09:44:04.637659: step: 696/531, loss: 0.3467138409614563
2023-01-21 09:44:05.762775: step: 700/531, loss: 0.07069382816553116
2023-01-21 09:44:06.896908: step: 704/531, loss: 0.9537258744239807
2023-01-21 09:44:08.024030: step: 708/531, loss: 0.3350968360900879
2023-01-21 09:44:09.141782: step: 712/531, loss: 0.14998823404312134
2023-01-21 09:44:10.262138: step: 716/531, loss: 0.16751570999622345
2023-01-21 09:44:11.397149: step: 720/531, loss: 0.03789644315838814
2023-01-21 09:44:12.523893: step: 724/531, loss: 0.018326472491025925
2023-01-21 09:44:13.624318: step: 728/531, loss: 0.11100774258375168
2023-01-21 09:44:14.732294: step: 732/531, loss: 0.036242008209228516
2023-01-21 09:44:15.880700: step: 736/531, loss: 0.3225898742675781
2023-01-21 09:44:17.002343: step: 740/531, loss: 0.1815796047449112
2023-01-21 09:44:18.149644: step: 744/531, loss: 0.09762974083423615
2023-01-21 09:44:19.276992: step: 748/531, loss: 0.023768378421664238
2023-01-21 09:44:20.411193: step: 752/531, loss: 0.4569108784198761
2023-01-21 09:44:21.527537: step: 756/531, loss: 0.08272562175989151
2023-01-21 09:44:22.658825: step: 760/531, loss: 0.10275106877088547
2023-01-21 09:44:23.784567: step: 764/531, loss: 0.140064999461174
2023-01-21 09:44:24.881524: step: 768/531, loss: 0.10238762199878693
2023-01-21 09:44:26.011796: step: 772/531, loss: 0.07606640458106995
2023-01-21 09:44:27.141573: step: 776/531, loss: 0.22227692604064941
2023-01-21 09:44:28.270934: step: 780/531, loss: 0.48534050583839417
2023-01-21 09:44:29.417032: step: 784/531, loss: 0.03770866617560387
2023-01-21 09:44:30.550265: step: 788/531, loss: 0.13308972120285034
2023-01-21 09:44:31.697793: step: 792/531, loss: 0.06787033379077911
2023-01-21 09:44:32.831489: step: 796/531, loss: 0.020800592377781868
2023-01-21 09:44:33.928560: step: 800/531, loss: 0.013608455657958984
2023-01-21 09:44:35.044945: step: 804/531, loss: 0.04169588163495064
2023-01-21 09:44:36.194752: step: 808/531, loss: 0.10209417343139648
2023-01-21 09:44:37.325249: step: 812/531, loss: 0.10331220924854279
2023-01-21 09:44:38.434662: step: 816/531, loss: 0.18031969666481018
2023-01-21 09:44:39.542731: step: 820/531, loss: 0.2590846121311188
2023-01-21 09:44:40.649503: step: 824/531, loss: 0.1501200795173645
2023-01-21 09:44:41.773563: step: 828/531, loss: 0.23756837844848633
2023-01-21 09:44:42.923772: step: 832/531, loss: 0.04336748272180557
2023-01-21 09:44:44.050712: step: 836/531, loss: 0.0832592025399208
2023-01-21 09:44:45.189928: step: 840/531, loss: 0.11387291550636292
2023-01-21 09:44:46.296188: step: 844/531, loss: 0.09098873287439346
2023-01-21 09:44:47.434058: step: 848/531, loss: 0.12483464181423187
2023-01-21 09:44:48.582443: step: 852/531, loss: 0.1567266285419464
2023-01-21 09:44:49.705313: step: 856/531, loss: 0.07843542098999023
2023-01-21 09:44:50.820159: step: 860/531, loss: 0.045104026794433594
2023-01-21 09:44:51.990077: step: 864/531, loss: 0.3480880558490753
2023-01-21 09:44:53.110274: step: 868/531, loss: 0.05490522459149361
2023-01-21 09:44:54.240099: step: 872/531, loss: 0.024423886090517044
2023-01-21 09:44:55.363942: step: 876/531, loss: 0.0413423553109169
2023-01-21 09:44:56.509455: step: 880/531, loss: 3.462635040283203
2023-01-21 09:44:57.674138: step: 884/531, loss: 0.06214094161987305
2023-01-21 09:44:58.769464: step: 888/531, loss: 0.019264603033661842
2023-01-21 09:44:59.887761: step: 892/531, loss: 0.13383379578590393
2023-01-21 09:45:01.036941: step: 896/531, loss: 1.3504865169525146
2023-01-21 09:45:02.149894: step: 900/531, loss: 0.2580377459526062
2023-01-21 09:45:03.255879: step: 904/531, loss: 0.007694053463637829
2023-01-21 09:45:04.388476: step: 908/531, loss: 0.09733685851097107
2023-01-21 09:45:05.525672: step: 912/531, loss: 0.1629856824874878
2023-01-21 09:45:06.668492: step: 916/531, loss: 0.059734441339969635
2023-01-21 09:45:07.785973: step: 920/531, loss: 0.2142011672258377
2023-01-21 09:45:08.901377: step: 924/531, loss: 0.17765305936336517
2023-01-21 09:45:10.075915: step: 928/531, loss: 0.08439116179943085
2023-01-21 09:45:11.228187: step: 932/531, loss: 0.2529619634151459
2023-01-21 09:45:12.366394: step: 936/531, loss: 0.02510538138449192
2023-01-21 09:45:13.504378: step: 940/531, loss: 0.0638599842786789
2023-01-21 09:45:14.626055: step: 944/531, loss: 0.04697451740503311
2023-01-21 09:45:15.727622: step: 948/531, loss: 0.041563842445611954
2023-01-21 09:45:16.828313: step: 952/531, loss: 0.13343146443367004
2023-01-21 09:45:17.940395: step: 956/531, loss: 0.09967027604579926
2023-01-21 09:45:19.036498: step: 960/531, loss: 0.07713194191455841
2023-01-21 09:45:20.151985: step: 964/531, loss: 0.05081605911254883
2023-01-21 09:45:21.297592: step: 968/531, loss: 0.16429057717323303
2023-01-21 09:45:22.441430: step: 972/531, loss: 0.04790535196661949
2023-01-21 09:45:23.543275: step: 976/531, loss: 0.06761045753955841
2023-01-21 09:45:24.656611: step: 980/531, loss: 0.1260969191789627
2023-01-21 09:45:25.778504: step: 984/531, loss: 0.05767088010907173
2023-01-21 09:45:26.901261: step: 988/531, loss: 0.2321719229221344
2023-01-21 09:45:27.993741: step: 992/531, loss: 0.01792454719543457
2023-01-21 09:45:29.118424: step: 996/531, loss: 0.03353476524353027
2023-01-21 09:45:30.257822: step: 1000/531, loss: 0.08557009696960449
2023-01-21 09:45:31.370489: step: 1004/531, loss: 0.11002512276172638
2023-01-21 09:45:32.480470: step: 1008/531, loss: 0.04827170819044113
2023-01-21 09:45:33.575568: step: 1012/531, loss: 0.13274335861206055
2023-01-21 09:45:34.703501: step: 1016/531, loss: 0.30336493253707886
2023-01-21 09:45:35.849097: step: 1020/531, loss: 0.10287819802761078
2023-01-21 09:45:36.989849: step: 1024/531, loss: 0.1338208168745041
2023-01-21 09:45:38.102898: step: 1028/531, loss: 0.23707932233810425
2023-01-21 09:45:39.216770: step: 1032/531, loss: 0.022287465631961823
2023-01-21 09:45:40.347167: step: 1036/531, loss: 0.10019197314977646
2023-01-21 09:45:41.472982: step: 1040/531, loss: 0.09221439063549042
2023-01-21 09:45:42.651644: step: 1044/531, loss: 0.06489257514476776
2023-01-21 09:45:43.776119: step: 1048/531, loss: 0.214176744222641
2023-01-21 09:45:44.920661: step: 1052/531, loss: 0.07543335109949112
2023-01-21 09:45:46.039953: step: 1056/531, loss: 0.14391061663627625
2023-01-21 09:45:47.196899: step: 1060/531, loss: 0.1280902922153473
2023-01-21 09:45:48.287149: step: 1064/531, loss: 0.04282693564891815
2023-01-21 09:45:49.411820: step: 1068/531, loss: 0.05827150493860245
2023-01-21 09:45:50.559613: step: 1072/531, loss: 0.14233139157295227
2023-01-21 09:45:51.686611: step: 1076/531, loss: 0.07143135368824005
2023-01-21 09:45:52.797792: step: 1080/531, loss: 0.038634397089481354
2023-01-21 09:45:53.939956: step: 1084/531, loss: 0.033639095723629
2023-01-21 09:45:55.042298: step: 1088/531, loss: 0.12870611250400543
2023-01-21 09:45:56.169908: step: 1092/531, loss: 0.13585814833641052
2023-01-21 09:45:57.285382: step: 1096/531, loss: 0.1311245709657669
2023-01-21 09:45:58.421779: step: 1100/531, loss: 0.09645405411720276
2023-01-21 09:45:59.541974: step: 1104/531, loss: 0.3717021346092224
2023-01-21 09:46:00.679383: step: 1108/531, loss: 0.3307401239871979
2023-01-21 09:46:01.778859: step: 1112/531, loss: 0.033965207636356354
2023-01-21 09:46:02.882760: step: 1116/531, loss: 0.21775293350219727
2023-01-21 09:46:04.031410: step: 1120/531, loss: 0.0483977310359478
2023-01-21 09:46:05.158643: step: 1124/531, loss: 0.21006564795970917
2023-01-21 09:46:06.274689: step: 1128/531, loss: 0.13897915184497833
2023-01-21 09:46:07.427436: step: 1132/531, loss: 0.02990732342004776
2023-01-21 09:46:08.550364: step: 1136/531, loss: 0.07611493766307831
2023-01-21 09:46:09.651607: step: 1140/531, loss: 0.16593007743358612
2023-01-21 09:46:10.776814: step: 1144/531, loss: 0.1310376077890396
2023-01-21 09:46:11.897064: step: 1148/531, loss: 0.051835253834724426
2023-01-21 09:46:13.001117: step: 1152/531, loss: 0.07659588009119034
2023-01-21 09:46:14.119373: step: 1156/531, loss: 0.1934429109096527
2023-01-21 09:46:15.253436: step: 1160/531, loss: 0.05769224092364311
2023-01-21 09:46:16.361103: step: 1164/531, loss: 0.10543718934059143
2023-01-21 09:46:17.540087: step: 1168/531, loss: 0.09350114315748215
2023-01-21 09:46:18.648251: step: 1172/531, loss: 0.10899510979652405
2023-01-21 09:46:19.771599: step: 1176/531, loss: 0.04249449074268341
2023-01-21 09:46:20.941963: step: 1180/531, loss: 0.3995322287082672
2023-01-21 09:46:22.110041: step: 1184/531, loss: 0.07186432182788849
2023-01-21 09:46:23.237876: step: 1188/531, loss: 0.0017005919944494963
2023-01-21 09:46:24.411749: step: 1192/531, loss: 0.041445113718509674
2023-01-21 09:46:25.519285: step: 1196/531, loss: 0.12923212349414825
2023-01-21 09:46:26.641413: step: 1200/531, loss: 0.09676117449998856
2023-01-21 09:46:27.748431: step: 1204/531, loss: 0.04722614586353302
2023-01-21 09:46:28.873700: step: 1208/531, loss: 0.05771093815565109
2023-01-21 09:46:29.997347: step: 1212/531, loss: 0.0929323211312294
2023-01-21 09:46:31.154658: step: 1216/531, loss: 0.08821926265954971
2023-01-21 09:46:32.248316: step: 1220/531, loss: 0.19201692938804626
2023-01-21 09:46:33.357391: step: 1224/531, loss: 0.028134608641266823
2023-01-21 09:46:34.507307: step: 1228/531, loss: 0.00859603937715292
2023-01-21 09:46:35.675433: step: 1232/531, loss: 0.043401144444942474
2023-01-21 09:46:36.784641: step: 1236/531, loss: 0.08370713889598846
2023-01-21 09:46:37.928620: step: 1240/531, loss: 0.11315050721168518
2023-01-21 09:46:39.068931: step: 1244/531, loss: 0.04142189025878906
2023-01-21 09:46:40.199028: step: 1248/531, loss: 0.1623091697692871
2023-01-21 09:46:41.355018: step: 1252/531, loss: 0.05393552780151367
2023-01-21 09:46:42.486519: step: 1256/531, loss: 0.010057163424789906
2023-01-21 09:46:43.612540: step: 1260/531, loss: 0.13477346301078796
2023-01-21 09:46:44.743343: step: 1264/531, loss: 0.051331259310245514
2023-01-21 09:46:45.832041: step: 1268/531, loss: 0.0423489585518837
2023-01-21 09:46:46.968765: step: 1272/531, loss: 0.07789783179759979
2023-01-21 09:46:48.098633: step: 1276/531, loss: 0.7017719745635986
2023-01-21 09:46:49.212141: step: 1280/531, loss: 0.09573662281036377
2023-01-21 09:46:50.357212: step: 1284/531, loss: 0.13838711380958557
2023-01-21 09:46:51.483353: step: 1288/531, loss: 0.784483790397644
2023-01-21 09:46:52.614208: step: 1292/531, loss: 0.04157862812280655
2023-01-21 09:46:53.706696: step: 1296/531, loss: 0.571773886680603
2023-01-21 09:46:54.866630: step: 1300/531, loss: 0.01401672326028347
2023-01-21 09:46:56.010637: step: 1304/531, loss: 0.10879745334386826
2023-01-21 09:46:57.154090: step: 1308/531, loss: 0.20757122337818146
2023-01-21 09:46:58.290380: step: 1312/531, loss: 0.47576338052749634
2023-01-21 09:46:59.439222: step: 1316/531, loss: 0.23827214539051056
2023-01-21 09:47:00.578837: step: 1320/531, loss: 0.14400728046894073
2023-01-21 09:47:01.700281: step: 1324/531, loss: 0.24711456894874573
2023-01-21 09:47:02.826041: step: 1328/531, loss: 0.0715951919555664
2023-01-21 09:47:03.951034: step: 1332/531, loss: 0.14545460045337677
2023-01-21 09:47:05.103427: step: 1336/531, loss: 0.09485816955566406
2023-01-21 09:47:06.214140: step: 1340/531, loss: 0.25709590315818787
2023-01-21 09:47:07.347124: step: 1344/531, loss: 0.060201358050107956
2023-01-21 09:47:08.466541: step: 1348/531, loss: 0.10800275951623917
2023-01-21 09:47:09.603664: step: 1352/531, loss: 0.03048262745141983
2023-01-21 09:47:10.768672: step: 1356/531, loss: 0.7740105390548706
2023-01-21 09:47:11.933233: step: 1360/531, loss: 0.8764164447784424
2023-01-21 09:47:13.092681: step: 1364/531, loss: 0.12279796600341797
2023-01-21 09:47:14.219520: step: 1368/531, loss: 0.08460044860839844
2023-01-21 09:47:15.343147: step: 1372/531, loss: 0.057626061141490936
2023-01-21 09:47:16.473029: step: 1376/531, loss: 0.02584528923034668
2023-01-21 09:47:17.598798: step: 1380/531, loss: 0.6731345057487488
2023-01-21 09:47:18.712005: step: 1384/531, loss: 0.1666877269744873
2023-01-21 09:47:19.851527: step: 1388/531, loss: 0.037947557866573334
2023-01-21 09:47:20.960425: step: 1392/531, loss: 0.03781953081488609
2023-01-21 09:47:22.089531: step: 1396/531, loss: 0.49211588501930237
2023-01-21 09:47:23.205565: step: 1400/531, loss: 0.2098522186279297
2023-01-21 09:47:24.349490: step: 1404/531, loss: 0.3870559632778168
2023-01-21 09:47:25.462092: step: 1408/531, loss: 0.08882780373096466
2023-01-21 09:47:26.596511: step: 1412/531, loss: 0.27566489577293396
2023-01-21 09:47:27.718140: step: 1416/531, loss: 0.28264617919921875
2023-01-21 09:47:28.827178: step: 1420/531, loss: 0.08777904510498047
2023-01-21 09:47:29.943832: step: 1424/531, loss: 0.03323392942547798
2023-01-21 09:47:31.076481: step: 1428/531, loss: 0.1422245055437088
2023-01-21 09:47:32.186850: step: 1432/531, loss: 0.06089983135461807
2023-01-21 09:47:33.340105: step: 1436/531, loss: 0.0912291556596756
2023-01-21 09:47:34.475576: step: 1440/531, loss: 0.21680957078933716
2023-01-21 09:47:35.569890: step: 1444/531, loss: 0.025788212195038795
2023-01-21 09:47:36.689394: step: 1448/531, loss: 0.0727960541844368
2023-01-21 09:47:37.783584: step: 1452/531, loss: 0.17060253024101257
2023-01-21 09:47:38.895685: step: 1456/531, loss: 0.1232885867357254
2023-01-21 09:47:40.028474: step: 1460/531, loss: 0.08619175851345062
2023-01-21 09:47:41.208820: step: 1464/531, loss: 0.269447922706604
2023-01-21 09:47:42.379404: step: 1468/531, loss: 0.11458693444728851
2023-01-21 09:47:43.489882: step: 1472/531, loss: 1.254642128944397
2023-01-21 09:47:44.616996: step: 1476/531, loss: 0.10386581718921661
2023-01-21 09:47:45.755897: step: 1480/531, loss: 0.17072373628616333
2023-01-21 09:47:46.902925: step: 1484/531, loss: 0.04292626678943634
2023-01-21 09:47:48.026460: step: 1488/531, loss: 0.403641939163208
2023-01-21 09:47:49.125307: step: 1492/531, loss: 0.050987910479307175
2023-01-21 09:47:50.281581: step: 1496/531, loss: 0.11971607804298401
2023-01-21 09:47:51.401301: step: 1500/531, loss: 0.04373779520392418
2023-01-21 09:47:52.560866: step: 1504/531, loss: 0.22015738487243652
2023-01-21 09:47:53.678647: step: 1508/531, loss: 0.041093263775110245
2023-01-21 09:47:54.830557: step: 1512/531, loss: 0.22739893198013306
2023-01-21 09:47:55.948114: step: 1516/531, loss: 0.023385334759950638
2023-01-21 09:47:57.038351: step: 1520/531, loss: 0.5267195701599121
2023-01-21 09:47:58.166838: step: 1524/531, loss: 0.13907480239868164
2023-01-21 09:47:59.309874: step: 1528/531, loss: 0.12416734546422958
2023-01-21 09:48:00.454910: step: 1532/531, loss: 0.3645566999912262
2023-01-21 09:48:01.593620: step: 1536/531, loss: 0.046117447316646576
2023-01-21 09:48:02.733964: step: 1540/531, loss: 0.08457255363464355
2023-01-21 09:48:03.850402: step: 1544/531, loss: 0.05190284177660942
2023-01-21 09:48:05.009340: step: 1548/531, loss: 0.1138916015625
2023-01-21 09:48:06.147977: step: 1552/531, loss: 0.5177223086357117
2023-01-21 09:48:07.287711: step: 1556/531, loss: 0.5734477639198303
2023-01-21 09:48:08.405688: step: 1560/531, loss: 0.10317230224609375
2023-01-21 09:48:09.531075: step: 1564/531, loss: 0.045778464525938034
2023-01-21 09:48:10.728171: step: 1568/531, loss: 0.049491312354803085
2023-01-21 09:48:11.883071: step: 1572/531, loss: 0.08923673629760742
2023-01-21 09:48:13.006054: step: 1576/531, loss: 0.27718499302864075
2023-01-21 09:48:14.130879: step: 1580/531, loss: 0.16943521797657013
2023-01-21 09:48:15.252431: step: 1584/531, loss: 0.04468240961432457
2023-01-21 09:48:16.391526: step: 1588/531, loss: 0.16840925812721252
2023-01-21 09:48:17.491070: step: 1592/531, loss: 0.0574522502720356
2023-01-21 09:48:18.589594: step: 1596/531, loss: 0.0275300033390522
2023-01-21 09:48:19.726712: step: 1600/531, loss: 0.08415809273719788
2023-01-21 09:48:20.839241: step: 1604/531, loss: 0.3440810739994049
2023-01-21 09:48:21.964998: step: 1608/531, loss: 0.22018957138061523
2023-01-21 09:48:23.094246: step: 1612/531, loss: 0.03315267711877823
2023-01-21 09:48:24.236320: step: 1616/531, loss: 0.1362323760986328
2023-01-21 09:48:25.372457: step: 1620/531, loss: 0.1901501566171646
2023-01-21 09:48:26.535578: step: 1624/531, loss: 0.11003279685974121
2023-01-21 09:48:27.678670: step: 1628/531, loss: 0.06049681082367897
2023-01-21 09:48:28.793928: step: 1632/531, loss: 0.1325400322675705
2023-01-21 09:48:29.929026: step: 1636/531, loss: 0.0879817008972168
2023-01-21 09:48:31.069057: step: 1640/531, loss: 0.04208064079284668
2023-01-21 09:48:32.173781: step: 1644/531, loss: 0.050332210958004
2023-01-21 09:48:33.324667: step: 1648/531, loss: 0.14123983681201935
2023-01-21 09:48:34.452665: step: 1652/531, loss: 0.117760568857193
2023-01-21 09:48:35.599791: step: 1656/531, loss: 0.11904564499855042
2023-01-21 09:48:36.761531: step: 1660/531, loss: 0.02638225629925728
2023-01-21 09:48:37.847651: step: 1664/531, loss: 0.01613588258624077
2023-01-21 09:48:38.962332: step: 1668/531, loss: 0.24884557723999023
2023-01-21 09:48:40.079011: step: 1672/531, loss: 0.06303200870752335
2023-01-21 09:48:41.249300: step: 1676/531, loss: 0.12995930016040802
2023-01-21 09:48:42.398738: step: 1680/531, loss: 0.31771478056907654
2023-01-21 09:48:43.541641: step: 1684/531, loss: 0.1062169075012207
2023-01-21 09:48:44.653917: step: 1688/531, loss: 0.1441192626953125
2023-01-21 09:48:45.762014: step: 1692/531, loss: 0.08201823383569717
2023-01-21 09:48:46.857192: step: 1696/531, loss: 0.2671300768852234
2023-01-21 09:48:47.980852: step: 1700/531, loss: 0.08638972789049149
2023-01-21 09:48:49.112166: step: 1704/531, loss: 0.1728196144104004
2023-01-21 09:48:50.206547: step: 1708/531, loss: 0.029881764203310013
2023-01-21 09:48:51.318285: step: 1712/531, loss: 0.10439501702785492
2023-01-21 09:48:52.429870: step: 1716/531, loss: 0.01975731924176216
2023-01-21 09:48:53.556495: step: 1720/531, loss: 0.048876188695430756
2023-01-21 09:48:54.686998: step: 1724/531, loss: 0.21802587807178497
2023-01-21 09:48:55.860556: step: 1728/531, loss: 0.5060909390449524
2023-01-21 09:48:56.982983: step: 1732/531, loss: 0.6130267977714539
2023-01-21 09:48:58.094843: step: 1736/531, loss: 0.1057361587882042
2023-01-21 09:48:59.189367: step: 1740/531, loss: 0.06724705547094345
2023-01-21 09:49:00.293068: step: 1744/531, loss: 0.08268866688013077
2023-01-21 09:49:01.424690: step: 1748/531, loss: 0.09658577293157578
2023-01-21 09:49:02.559569: step: 1752/531, loss: 0.267011821269989
2023-01-21 09:49:03.684405: step: 1756/531, loss: 0.3914510905742645
2023-01-21 09:49:04.825400: step: 1760/531, loss: 0.09398870915174484
2023-01-21 09:49:05.947314: step: 1764/531, loss: 0.2301032543182373
2023-01-21 09:49:07.040804: step: 1768/531, loss: 0.05576739460229874
2023-01-21 09:49:08.170569: step: 1772/531, loss: 0.11827392876148224
2023-01-21 09:49:09.297951: step: 1776/531, loss: 0.13004884123802185
2023-01-21 09:49:10.407911: step: 1780/531, loss: 0.13228054344654083
2023-01-21 09:49:11.565325: step: 1784/531, loss: 0.15703706443309784
2023-01-21 09:49:12.674331: step: 1788/531, loss: 0.1578660011291504
2023-01-21 09:49:13.782086: step: 1792/531, loss: 0.056783199310302734
2023-01-21 09:49:14.915277: step: 1796/531, loss: 0.06593399494886398
2023-01-21 09:49:16.066297: step: 1800/531, loss: 1.5454472303390503
2023-01-21 09:49:17.197707: step: 1804/531, loss: 0.04158506542444229
2023-01-21 09:49:18.300086: step: 1808/531, loss: 1.0753564834594727
2023-01-21 09:49:19.420040: step: 1812/531, loss: 0.087615966796875
2023-01-21 09:49:20.546400: step: 1816/531, loss: 0.023408317938447
2023-01-21 09:49:21.650569: step: 1820/531, loss: 0.082577183842659
2023-01-21 09:49:22.755183: step: 1824/531, loss: 0.05507383495569229
2023-01-21 09:49:23.897790: step: 1828/531, loss: 0.4281843304634094
2023-01-21 09:49:25.008306: step: 1832/531, loss: 0.07420730590820312
2023-01-21 09:49:26.165485: step: 1836/531, loss: 1.752892255783081
2023-01-21 09:49:27.269058: step: 1840/531, loss: 0.06989984214305878
2023-01-21 09:49:28.359693: step: 1844/531, loss: 0.2567642629146576
2023-01-21 09:49:29.499435: step: 1848/531, loss: 0.057174019515514374
2023-01-21 09:49:30.645777: step: 1852/531, loss: 0.1755599081516266
2023-01-21 09:49:31.776550: step: 1856/531, loss: 0.1232757568359375
2023-01-21 09:49:32.923778: step: 1860/531, loss: 0.12502965331077576
2023-01-21 09:49:34.037814: step: 1864/531, loss: 0.029199469834566116
2023-01-21 09:49:35.165907: step: 1868/531, loss: 0.08130288124084473
2023-01-21 09:49:36.287598: step: 1872/531, loss: 0.1965988278388977
2023-01-21 09:49:37.412380: step: 1876/531, loss: 1.381486177444458
2023-01-21 09:49:38.572205: step: 1880/531, loss: 0.15052194893360138
2023-01-21 09:49:39.697656: step: 1884/531, loss: 0.2976197302341461
2023-01-21 09:49:40.822030: step: 1888/531, loss: 0.15820464491844177
2023-01-21 09:49:41.976209: step: 1892/531, loss: 0.07607245445251465
2023-01-21 09:49:43.079912: step: 1896/531, loss: 0.10969372093677521
2023-01-21 09:49:44.167425: step: 1900/531, loss: 0.2989429533481598
2023-01-21 09:49:45.299580: step: 1904/531, loss: 0.1606767773628235
2023-01-21 09:49:46.454240: step: 1908/531, loss: 0.06513051688671112
2023-01-21 09:49:47.564471: step: 1912/531, loss: 0.08248001337051392
2023-01-21 09:49:48.685103: step: 1916/531, loss: 0.29668235778808594
2023-01-21 09:49:49.818992: step: 1920/531, loss: 0.09794149547815323
2023-01-21 09:49:50.950071: step: 1924/531, loss: 0.12080007791519165
2023-01-21 09:49:52.093706: step: 1928/531, loss: 0.09691813588142395
2023-01-21 09:49:53.225497: step: 1932/531, loss: 0.4276502728462219
2023-01-21 09:49:54.353007: step: 1936/531, loss: 0.40770435333251953
2023-01-21 09:49:55.481374: step: 1940/531, loss: 0.06810712814331055
2023-01-21 09:49:56.576876: step: 1944/531, loss: 0.018558122217655182
2023-01-21 09:49:57.708194: step: 1948/531, loss: 0.2289590835571289
2023-01-21 09:49:58.849868: step: 1952/531, loss: 0.09229016304016113
2023-01-21 09:49:59.966015: step: 1956/531, loss: 0.04901190102100372
2023-01-21 09:50:01.101926: step: 1960/531, loss: 0.1415625512599945
2023-01-21 09:50:02.233497: step: 1964/531, loss: 0.12899285554885864
2023-01-21 09:50:03.355840: step: 1968/531, loss: 0.5322989821434021
2023-01-21 09:50:04.504847: step: 1972/531, loss: 0.30357494950294495
2023-01-21 09:50:05.644846: step: 1976/531, loss: 0.05293073505163193
2023-01-21 09:50:06.809562: step: 1980/531, loss: 0.7628833651542664
2023-01-21 09:50:07.942858: step: 1984/531, loss: 0.1101200133562088
2023-01-21 09:50:09.066336: step: 1988/531, loss: 1.9830515384674072
2023-01-21 09:50:10.195094: step: 1992/531, loss: 0.05994720384478569
2023-01-21 09:50:11.335907: step: 1996/531, loss: 0.12858600914478302
2023-01-21 09:50:12.457574: step: 2000/531, loss: 0.10530281811952591
2023-01-21 09:50:13.590787: step: 2004/531, loss: 0.2252178192138672
2023-01-21 09:50:14.741251: step: 2008/531, loss: 0.11051426082849503
2023-01-21 09:50:15.898320: step: 2012/531, loss: 0.09581919014453888
2023-01-21 09:50:17.002256: step: 2016/531, loss: 0.04288170486688614
2023-01-21 09:50:18.137202: step: 2020/531, loss: 0.18412618339061737
2023-01-21 09:50:19.255669: step: 2024/531, loss: 0.20220623910427094
2023-01-21 09:50:20.398562: step: 2028/531, loss: 0.12490224838256836
2023-01-21 09:50:21.523668: step: 2032/531, loss: 0.20448951423168182
2023-01-21 09:50:22.651657: step: 2036/531, loss: 0.13962887227535248
2023-01-21 09:50:23.817845: step: 2040/531, loss: 0.07309694588184357
2023-01-21 09:50:24.933503: step: 2044/531, loss: 0.08817487210035324
2023-01-21 09:50:26.075249: step: 2048/531, loss: 0.27600231766700745
2023-01-21 09:50:27.201376: step: 2052/531, loss: 0.12943366169929504
2023-01-21 09:50:28.325394: step: 2056/531, loss: 0.1355927437543869
2023-01-21 09:50:29.452798: step: 2060/531, loss: 0.058237623423337936
2023-01-21 09:50:30.577395: step: 2064/531, loss: 0.1104951724410057
2023-01-21 09:50:31.729667: step: 2068/531, loss: 0.10589724034070969
2023-01-21 09:50:32.848477: step: 2072/531, loss: 0.042347051203250885
2023-01-21 09:50:34.012234: step: 2076/531, loss: 0.1506047248840332
2023-01-21 09:50:35.131096: step: 2080/531, loss: 0.11841832101345062
2023-01-21 09:50:36.274758: step: 2084/531, loss: 0.11827349662780762
2023-01-21 09:50:37.415535: step: 2088/531, loss: 0.13589878380298615
2023-01-21 09:50:38.543389: step: 2092/531, loss: 0.02547468990087509
2023-01-21 09:50:39.697422: step: 2096/531, loss: 0.05758802965283394
2023-01-21 09:50:40.822666: step: 2100/531, loss: 0.07847519218921661
2023-01-21 09:50:41.947040: step: 2104/531, loss: 0.05289927124977112
2023-01-21 09:50:43.079904: step: 2108/531, loss: 0.10537058115005493
2023-01-21 09:50:44.202145: step: 2112/531, loss: 0.03232002258300781
2023-01-21 09:50:45.325961: step: 2116/531, loss: 0.11319885402917862
2023-01-21 09:50:46.420345: step: 2120/531, loss: 0.02126908302307129
2023-01-21 09:50:47.533791: step: 2124/531, loss: 0.05684996023774147
==================================================
Loss: 0.167
--------------------
Dev: {'event': {'p': 0.5606773283160865, 'r': 0.7936085219707057, 'f1': 0.6571113561190738}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6227316141356256, 'r': 0.7775790101371497, 'f1': 0.6915937417130734}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5, 'r': 0.8333333333333334, 'f1': 0.625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.576271186440678, 'r': 0.5396825396825397, 'f1': 0.5573770491803278}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5440900562851783, 'r': 0.7723035952063915, 'f1': 0.6384149697303247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.5672823218997362, 'r': 0.7692307692307693, 'f1': 0.6529992406985574}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6557377049180327, 'r': 0.6349206349206349, 'f1': 0.6451612903225806}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6341463414634146, 'r': 0.7270306258322237, 'f1': 0.6774193548387097}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6328794755421079, 'r': 0.7483601669648181, 'f1': 0.6857923497267759}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5588235294117647, 'r': 0.5277777777777778, 'f1': 0.5428571428571428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 09:51:27.816505: step: 4/531, loss: 0.24521350860595703
2023-01-21 09:51:28.953071: step: 8/531, loss: 0.0637439712882042
2023-01-21 09:51:30.096257: step: 12/531, loss: 0.061720848083496094
2023-01-21 09:51:31.198558: step: 16/531, loss: 0.06758013367652893
2023-01-21 09:51:32.345384: step: 20/531, loss: 0.034948062151670456
2023-01-21 09:51:33.447444: step: 24/531, loss: 0.23340940475463867
2023-01-21 09:51:34.562523: step: 28/531, loss: 0.7450456619262695
2023-01-21 09:51:35.687826: step: 32/531, loss: 0.042577553540468216
2023-01-21 09:51:36.825879: step: 36/531, loss: 0.43093380331993103
2023-01-21 09:51:37.960277: step: 40/531, loss: 0.09589161723852158
2023-01-21 09:51:39.058657: step: 44/531, loss: 0.040903665125370026
2023-01-21 09:51:40.182327: step: 48/531, loss: 0.03664741665124893
2023-01-21 09:51:41.376914: step: 52/531, loss: 0.10274062305688858
2023-01-21 09:51:42.506629: step: 56/531, loss: 0.050665855407714844
2023-01-21 09:51:43.627160: step: 60/531, loss: 0.0111229894682765
2023-01-21 09:51:44.733544: step: 64/531, loss: 0.017444707453250885
2023-01-21 09:51:45.843585: step: 68/531, loss: 0.05859022215008736
2023-01-21 09:51:46.981584: step: 72/531, loss: 0.35822564363479614
2023-01-21 09:51:48.123683: step: 76/531, loss: 0.04259061813354492
2023-01-21 09:51:49.231954: step: 80/531, loss: 0.18119025230407715
2023-01-21 09:51:50.361047: step: 84/531, loss: 0.2853566110134125
2023-01-21 09:51:51.464705: step: 88/531, loss: 0.036359503865242004
2023-01-21 09:51:52.599633: step: 92/531, loss: 0.17923030257225037
2023-01-21 09:51:53.721633: step: 96/531, loss: 0.06044473499059677
2023-01-21 09:51:54.837551: step: 100/531, loss: 0.14107543230056763
2023-01-21 09:51:55.958481: step: 104/531, loss: 0.06166019290685654
2023-01-21 09:51:57.079270: step: 108/531, loss: 0.05762805789709091
2023-01-21 09:51:58.219492: step: 112/531, loss: 0.04909314960241318
2023-01-21 09:51:59.344923: step: 116/531, loss: 0.06578508019447327
2023-01-21 09:52:00.498831: step: 120/531, loss: 0.11613292992115021
2023-01-21 09:52:01.610605: step: 124/531, loss: 0.10140958428382874
2023-01-21 09:52:02.752955: step: 128/531, loss: 0.23020735383033752
2023-01-21 09:52:03.874275: step: 132/531, loss: 0.01379852369427681
2023-01-21 09:52:04.979658: step: 136/531, loss: 0.071214959025383
2023-01-21 09:52:06.122164: step: 140/531, loss: 0.4613441526889801
2023-01-21 09:52:07.250133: step: 144/531, loss: 0.023187827318906784
2023-01-21 09:52:08.382515: step: 148/531, loss: 0.047972872853279114
2023-01-21 09:52:09.500235: step: 152/531, loss: 0.02971353381872177
2023-01-21 09:52:10.615346: step: 156/531, loss: 0.06931009143590927
2023-01-21 09:52:11.772930: step: 160/531, loss: 0.12905187904834747
2023-01-21 09:52:12.917006: step: 164/531, loss: 0.028540946543216705
2023-01-21 09:52:14.064905: step: 168/531, loss: 0.07333078980445862
2023-01-21 09:52:15.219505: step: 172/531, loss: 0.08187265694141388
2023-01-21 09:52:16.346289: step: 176/531, loss: 0.11157284677028656
2023-01-21 09:52:17.506060: step: 180/531, loss: 0.4296124279499054
2023-01-21 09:52:18.641712: step: 184/531, loss: 0.23175391554832458
2023-01-21 09:52:19.803488: step: 188/531, loss: 0.2413499802350998
2023-01-21 09:52:20.941208: step: 192/531, loss: 0.082981638610363
2023-01-21 09:52:22.098667: step: 196/531, loss: 0.024634171277284622
2023-01-21 09:52:23.205667: step: 200/531, loss: 0.06192101538181305
2023-01-21 09:52:24.340336: step: 204/531, loss: 0.07577943801879883
2023-01-21 09:52:25.453909: step: 208/531, loss: 0.18514639139175415
2023-01-21 09:52:26.555617: step: 212/531, loss: 0.059965040534734726
2023-01-21 09:52:27.689912: step: 216/531, loss: 0.0421847328543663
2023-01-21 09:52:28.826927: step: 220/531, loss: 0.08330269157886505
2023-01-21 09:52:29.944603: step: 224/531, loss: 1.1466501951217651
2023-01-21 09:52:31.068968: step: 228/531, loss: 0.41923987865448
2023-01-21 09:52:32.187104: step: 232/531, loss: 0.1362285614013672
2023-01-21 09:52:33.356922: step: 236/531, loss: 0.17704887688159943
2023-01-21 09:52:34.488291: step: 240/531, loss: 0.2890928387641907
2023-01-21 09:52:35.596301: step: 244/531, loss: 0.029705429449677467
2023-01-21 09:52:36.748010: step: 248/531, loss: 0.07625313103199005
2023-01-21 09:52:37.873115: step: 252/531, loss: 0.13213196396827698
2023-01-21 09:52:39.018652: step: 256/531, loss: 0.06964436173439026
2023-01-21 09:52:40.144523: step: 260/531, loss: 0.13338060677051544
2023-01-21 09:52:41.266637: step: 264/531, loss: 0.12334012985229492
2023-01-21 09:52:42.396596: step: 268/531, loss: 0.0038129331078380346
2023-01-21 09:52:43.538703: step: 272/531, loss: 0.10957928001880646
2023-01-21 09:52:44.665230: step: 276/531, loss: 0.07325001060962677
2023-01-21 09:52:45.809747: step: 280/531, loss: 0.07740020751953125
2023-01-21 09:52:46.947485: step: 284/531, loss: 0.030539896339178085
2023-01-21 09:52:48.075820: step: 288/531, loss: 0.013364791870117188
2023-01-21 09:52:49.223417: step: 292/531, loss: 0.06818647682666779
2023-01-21 09:52:50.334030: step: 296/531, loss: 0.07460494339466095
2023-01-21 09:52:51.464517: step: 300/531, loss: 0.04049735143780708
2023-01-21 09:52:52.579955: step: 304/531, loss: 0.05165739357471466
2023-01-21 09:52:53.704095: step: 308/531, loss: 0.07476544380187988
2023-01-21 09:52:54.848138: step: 312/531, loss: 0.11238288879394531
2023-01-21 09:52:56.001250: step: 316/531, loss: 0.13798531889915466
2023-01-21 09:52:57.123418: step: 320/531, loss: 0.002304124878719449
2023-01-21 09:52:58.263116: step: 324/531, loss: 0.023406410589814186
2023-01-21 09:52:59.422183: step: 328/531, loss: 0.09620776772499084
2023-01-21 09:53:00.555719: step: 332/531, loss: 0.41692429780960083
2023-01-21 09:53:01.683764: step: 336/531, loss: 0.3007393479347229
2023-01-21 09:53:02.822584: step: 340/531, loss: 0.03148365020751953
2023-01-21 09:53:03.935542: step: 344/531, loss: 0.023790931329131126
2023-01-21 09:53:05.056541: step: 348/531, loss: 0.02186756208539009
2023-01-21 09:53:06.186103: step: 352/531, loss: 0.500514805316925
2023-01-21 09:53:07.306643: step: 356/531, loss: 0.4334770441055298
2023-01-21 09:53:08.409395: step: 360/531, loss: 0.043232060968875885
2023-01-21 09:53:09.516994: step: 364/531, loss: 0.2623669505119324
2023-01-21 09:53:10.640410: step: 368/531, loss: 0.09848713874816895
2023-01-21 09:53:11.796425: step: 372/531, loss: 0.12542200088500977
2023-01-21 09:53:12.926996: step: 376/531, loss: 0.0418303981423378
2023-01-21 09:53:14.069994: step: 380/531, loss: 0.04276122897863388
2023-01-21 09:53:15.206935: step: 384/531, loss: 0.07473735511302948
2023-01-21 09:53:16.354299: step: 388/531, loss: 0.12753501534461975
2023-01-21 09:53:17.489305: step: 392/531, loss: 0.07406473159790039
2023-01-21 09:53:18.630184: step: 396/531, loss: 0.17697182297706604
2023-01-21 09:53:19.729821: step: 400/531, loss: 0.07076764106750488
2023-01-21 09:53:20.851615: step: 404/531, loss: 0.08918514847755432
2023-01-21 09:53:21.945976: step: 408/531, loss: 0.030029643326997757
2023-01-21 09:53:23.099555: step: 412/531, loss: 0.054741814732551575
2023-01-21 09:53:24.234439: step: 416/531, loss: 0.052515413612127304
2023-01-21 09:53:25.381128: step: 420/531, loss: 0.051069118082523346
2023-01-21 09:53:26.521858: step: 424/531, loss: 0.1179811954498291
2023-01-21 09:53:27.666313: step: 428/531, loss: 0.023988008499145508
2023-01-21 09:53:28.797442: step: 432/531, loss: 0.11671815067529678
2023-01-21 09:53:29.919259: step: 436/531, loss: 0.21174821257591248
2023-01-21 09:53:31.047857: step: 440/531, loss: 0.01924161985516548
2023-01-21 09:53:32.164098: step: 444/531, loss: 0.03493242338299751
2023-01-21 09:53:33.309351: step: 448/531, loss: 0.11870650947093964
2023-01-21 09:53:34.452807: step: 452/531, loss: 0.11427745968103409
2023-01-21 09:53:35.572891: step: 456/531, loss: 0.14556297659873962
2023-01-21 09:53:36.717966: step: 460/531, loss: 0.5253650546073914
2023-01-21 09:53:37.840175: step: 464/531, loss: 0.09302349388599396
2023-01-21 09:53:38.987264: step: 468/531, loss: 0.028496742248535156
2023-01-21 09:53:40.104661: step: 472/531, loss: 0.1322811096906662
2023-01-21 09:53:41.258797: step: 476/531, loss: 0.1962333619594574
2023-01-21 09:53:42.382450: step: 480/531, loss: 0.10265693068504333
2023-01-21 09:53:43.539133: step: 484/531, loss: 0.09085159748792648
2023-01-21 09:53:44.642853: step: 488/531, loss: 0.12242496013641357
2023-01-21 09:53:45.794098: step: 492/531, loss: 1.0959402322769165
2023-01-21 09:53:46.930299: step: 496/531, loss: 0.042792320251464844
2023-01-21 09:53:48.054392: step: 500/531, loss: 0.13432160019874573
2023-01-21 09:53:49.182189: step: 504/531, loss: 0.13506154716014862
2023-01-21 09:53:50.322424: step: 508/531, loss: 0.07583389431238174
2023-01-21 09:53:51.463278: step: 512/531, loss: 0.05381155386567116
2023-01-21 09:53:52.587602: step: 516/531, loss: 0.23388594388961792
2023-01-21 09:53:53.718965: step: 520/531, loss: 0.16427969932556152
2023-01-21 09:53:54.838238: step: 524/531, loss: 0.05261101573705673
2023-01-21 09:53:55.941624: step: 528/531, loss: 0.0637696236371994
2023-01-21 09:53:57.072112: step: 532/531, loss: 0.019101906567811966
2023-01-21 09:53:58.185471: step: 536/531, loss: 0.16299466788768768
2023-01-21 09:53:59.278692: step: 540/531, loss: 0.03241760656237602
2023-01-21 09:54:00.408546: step: 544/531, loss: 0.08427772670984268
2023-01-21 09:54:01.546609: step: 548/531, loss: 0.07498989254236221
2023-01-21 09:54:02.672081: step: 552/531, loss: 0.14200668036937714
2023-01-21 09:54:03.793546: step: 556/531, loss: 0.04064350202679634
2023-01-21 09:54:04.908893: step: 560/531, loss: 0.03512401506304741
2023-01-21 09:54:06.094879: step: 564/531, loss: 0.10931988060474396
2023-01-21 09:54:07.243111: step: 568/531, loss: 1.8063678741455078
2023-01-21 09:54:08.378014: step: 572/531, loss: 0.03486442565917969
2023-01-21 09:54:09.505604: step: 576/531, loss: 0.06649918854236603
2023-01-21 09:54:10.627795: step: 580/531, loss: 0.011412239633500576
2023-01-21 09:54:11.749101: step: 584/531, loss: 0.07249526679515839
2023-01-21 09:54:12.874758: step: 588/531, loss: 0.09728346019983292
2023-01-21 09:54:13.979768: step: 592/531, loss: 0.12365636974573135
2023-01-21 09:54:15.125556: step: 596/531, loss: 0.051905252039432526
2023-01-21 09:54:16.282177: step: 600/531, loss: 0.27257871627807617
2023-01-21 09:54:17.467449: step: 604/531, loss: 0.2695941925048828
2023-01-21 09:54:18.565768: step: 608/531, loss: 0.06744766235351562
2023-01-21 09:54:19.690126: step: 612/531, loss: 0.1624092161655426
2023-01-21 09:54:20.819303: step: 616/531, loss: 0.10697192698717117
2023-01-21 09:54:21.930585: step: 620/531, loss: 0.013153934851288795
2023-01-21 09:54:23.037861: step: 624/531, loss: 0.07322165369987488
2023-01-21 09:54:24.154403: step: 628/531, loss: 0.10920357704162598
2023-01-21 09:54:25.291894: step: 632/531, loss: 0.04836883395910263
2023-01-21 09:54:26.426544: step: 636/531, loss: 0.018249941989779472
2023-01-21 09:54:27.555583: step: 640/531, loss: 0.10932368040084839
2023-01-21 09:54:28.692616: step: 644/531, loss: 0.072850801050663
2023-01-21 09:54:29.798716: step: 648/531, loss: 0.18117637932300568
2023-01-21 09:54:30.918720: step: 652/531, loss: 0.01232462003827095
2023-01-21 09:54:32.040767: step: 656/531, loss: 0.01563425175845623
2023-01-21 09:54:33.160228: step: 660/531, loss: 0.0649867057800293
2023-01-21 09:54:34.309299: step: 664/531, loss: 0.0731443390250206
2023-01-21 09:54:35.427553: step: 668/531, loss: 0.15695782005786896
2023-01-21 09:54:36.594206: step: 672/531, loss: 0.04744892194867134
2023-01-21 09:54:37.727808: step: 676/531, loss: 0.06414695084095001
2023-01-21 09:54:38.864992: step: 680/531, loss: 0.05328016355633736
2023-01-21 09:54:40.000702: step: 684/531, loss: 0.08182373642921448
2023-01-21 09:54:41.157043: step: 688/531, loss: 0.040016986429691315
2023-01-21 09:54:42.271066: step: 692/531, loss: 0.0013580322265625
2023-01-21 09:54:43.386995: step: 696/531, loss: 0.15640011429786682
2023-01-21 09:54:44.502224: step: 700/531, loss: 0.08039741218090057
2023-01-21 09:54:45.615868: step: 704/531, loss: 0.07359619438648224
2023-01-21 09:54:46.775004: step: 708/531, loss: 0.1425948143005371
2023-01-21 09:54:47.885686: step: 712/531, loss: 0.03512106090784073
2023-01-21 09:54:49.000047: step: 716/531, loss: 0.05033493414521217
2023-01-21 09:54:50.147158: step: 720/531, loss: 0.2445165514945984
2023-01-21 09:54:51.274768: step: 724/531, loss: 0.7185272574424744
2023-01-21 09:54:52.426606: step: 728/531, loss: 0.08073179423809052
2023-01-21 09:54:53.561256: step: 732/531, loss: 0.04225664213299751
2023-01-21 09:54:54.656222: step: 736/531, loss: 0.08425255119800568
2023-01-21 09:54:55.806104: step: 740/531, loss: 0.030803300440311432
2023-01-21 09:54:56.936769: step: 744/531, loss: 0.0819791778922081
2023-01-21 09:54:58.079875: step: 748/531, loss: 0.20876997709274292
2023-01-21 09:54:59.190110: step: 752/531, loss: 0.02880225144326687
2023-01-21 09:55:00.312865: step: 756/531, loss: 0.016536330804228783
2023-01-21 09:55:01.423109: step: 760/531, loss: 0.06827898323535919
2023-01-21 09:55:02.580907: step: 764/531, loss: 0.20995837450027466
2023-01-21 09:55:03.717355: step: 768/531, loss: 0.056046295911073685
2023-01-21 09:55:04.840599: step: 772/531, loss: 0.08739929646253586
2023-01-21 09:55:05.967417: step: 776/531, loss: 0.12965135276317596
2023-01-21 09:55:07.098978: step: 780/531, loss: 0.0807647705078125
2023-01-21 09:55:08.218090: step: 784/531, loss: 0.16201750934123993
2023-01-21 09:55:09.340044: step: 788/531, loss: 0.13932104408740997
2023-01-21 09:55:10.464399: step: 792/531, loss: 0.3195396363735199
2023-01-21 09:55:11.601586: step: 796/531, loss: 0.08106646686792374
2023-01-21 09:55:12.712932: step: 800/531, loss: 0.09317875653505325
2023-01-21 09:55:13.872859: step: 804/531, loss: 0.22033005952835083
2023-01-21 09:55:15.012638: step: 808/531, loss: 0.00297031388618052
2023-01-21 09:55:16.112904: step: 812/531, loss: 0.14223118126392365
2023-01-21 09:55:17.248968: step: 816/531, loss: 0.07982216030359268
2023-01-21 09:55:18.371861: step: 820/531, loss: 0.04033965989947319
2023-01-21 09:55:19.513090: step: 824/531, loss: 0.5727187395095825
2023-01-21 09:55:20.618048: step: 828/531, loss: 0.1576448380947113
2023-01-21 09:55:21.746140: step: 832/531, loss: 0.0631125420331955
2023-01-21 09:55:22.844335: step: 836/531, loss: 0.02203233726322651
2023-01-21 09:55:23.961892: step: 840/531, loss: 0.022807979956269264
2023-01-21 09:55:25.059664: step: 844/531, loss: 0.08285131305456161
2023-01-21 09:55:26.164883: step: 848/531, loss: 0.1330675184726715
2023-01-21 09:55:27.292678: step: 852/531, loss: 0.3412402272224426
2023-01-21 09:55:28.395714: step: 856/531, loss: 0.05455436930060387
2023-01-21 09:55:29.477666: step: 860/531, loss: 0.08719502389431
2023-01-21 09:55:30.639590: step: 864/531, loss: 0.15049421787261963
2023-01-21 09:55:31.760556: step: 868/531, loss: 0.6061941385269165
2023-01-21 09:55:32.869988: step: 872/531, loss: 0.03395424038171768
2023-01-21 09:55:34.009271: step: 876/531, loss: 0.08362732082605362
2023-01-21 09:55:35.149051: step: 880/531, loss: 0.4415343403816223
2023-01-21 09:55:36.275444: step: 884/531, loss: 0.4605218768119812
2023-01-21 09:55:37.400024: step: 888/531, loss: 0.15848055481910706
2023-01-21 09:55:38.546265: step: 892/531, loss: 0.1300487518310547
2023-01-21 09:55:39.653901: step: 896/531, loss: 0.16720028221607208
2023-01-21 09:55:40.754514: step: 900/531, loss: 0.10289835929870605
2023-01-21 09:55:41.889282: step: 904/531, loss: 0.05237159878015518
2023-01-21 09:55:43.011710: step: 908/531, loss: 0.035078905522823334
2023-01-21 09:55:44.149180: step: 912/531, loss: 0.2856786847114563
2023-01-21 09:55:45.260171: step: 916/531, loss: 0.05845584720373154
2023-01-21 09:55:46.397704: step: 920/531, loss: 0.02715129777789116
2023-01-21 09:55:47.542506: step: 924/531, loss: 0.06343994289636612
2023-01-21 09:55:48.675953: step: 928/531, loss: 0.021636009216308594
2023-01-21 09:55:49.791709: step: 932/531, loss: 0.2872146666049957
2023-01-21 09:55:50.957461: step: 936/531, loss: 0.799748420715332
2023-01-21 09:55:52.062100: step: 940/531, loss: 0.028060341253876686
2023-01-21 09:55:53.191725: step: 944/531, loss: 0.07654837518930435
2023-01-21 09:55:54.328926: step: 948/531, loss: 0.2365356981754303
2023-01-21 09:55:55.463511: step: 952/531, loss: 0.11675992608070374
2023-01-21 09:55:56.600303: step: 956/531, loss: 0.18697862327098846
2023-01-21 09:55:57.743349: step: 960/531, loss: 0.06001434475183487
2023-01-21 09:55:58.844592: step: 964/531, loss: 0.02468586154282093
2023-01-21 09:55:59.974926: step: 968/531, loss: 0.13695946335792542
2023-01-21 09:56:01.089564: step: 972/531, loss: 0.07833647727966309
2023-01-21 09:56:02.210925: step: 976/531, loss: 0.1112087219953537
2023-01-21 09:56:03.312801: step: 980/531, loss: 0.1378290206193924
2023-01-21 09:56:04.441856: step: 984/531, loss: 0.12337536364793777
2023-01-21 09:56:05.578684: step: 988/531, loss: 0.1059502586722374
2023-01-21 09:56:06.691279: step: 992/531, loss: 0.04917726665735245
2023-01-21 09:56:07.817432: step: 996/531, loss: 0.10076946020126343
2023-01-21 09:56:08.940220: step: 1000/531, loss: 0.11674318462610245
2023-01-21 09:56:10.091173: step: 1004/531, loss: 0.31445178389549255
2023-01-21 09:56:11.196743: step: 1008/531, loss: 0.11476679146289825
2023-01-21 09:56:12.338808: step: 1012/531, loss: 0.6012662649154663
2023-01-21 09:56:13.507104: step: 1016/531, loss: 0.2123938649892807
2023-01-21 09:56:14.599805: step: 1020/531, loss: 0.07088909298181534
2023-01-21 09:56:15.745127: step: 1024/531, loss: 0.0908966064453125
2023-01-21 09:56:16.868499: step: 1028/531, loss: 0.07293333858251572
2023-01-21 09:56:17.997422: step: 1032/531, loss: 0.0146652702242136
2023-01-21 09:56:19.107342: step: 1036/531, loss: 0.06168394535779953
2023-01-21 09:56:20.239066: step: 1040/531, loss: 0.10019131004810333
2023-01-21 09:56:21.356889: step: 1044/531, loss: 0.1352185755968094
2023-01-21 09:56:22.468817: step: 1048/531, loss: 0.04007406532764435
2023-01-21 09:56:23.581673: step: 1052/531, loss: 0.12325391918420792
2023-01-21 09:56:24.733149: step: 1056/531, loss: 0.19440516829490662
2023-01-21 09:56:25.870201: step: 1060/531, loss: 0.07504969090223312
2023-01-21 09:56:27.010943: step: 1064/531, loss: 0.575652003288269
2023-01-21 09:56:28.152999: step: 1068/531, loss: 0.05950909107923508
2023-01-21 09:56:29.270059: step: 1072/531, loss: 0.08521442115306854
2023-01-21 09:56:30.396954: step: 1076/531, loss: 0.08552151173353195
2023-01-21 09:56:31.545731: step: 1080/531, loss: 0.13359637558460236
2023-01-21 09:56:32.659023: step: 1084/531, loss: 0.04953209310770035
2023-01-21 09:56:33.794795: step: 1088/531, loss: 0.04551658779382706
2023-01-21 09:56:34.921480: step: 1092/531, loss: 0.14216624200344086
2023-01-21 09:56:36.039685: step: 1096/531, loss: 0.016649913042783737
2023-01-21 09:56:37.154659: step: 1100/531, loss: 0.04294843599200249
2023-01-21 09:56:38.232688: step: 1104/531, loss: 0.09906189888715744
2023-01-21 09:56:39.350787: step: 1108/531, loss: 0.024163054302334785
2023-01-21 09:56:40.486293: step: 1112/531, loss: 1.226098656654358
2023-01-21 09:56:41.612598: step: 1116/531, loss: 0.05841789394617081
2023-01-21 09:56:42.725526: step: 1120/531, loss: 0.2756267488002777
2023-01-21 09:56:43.858575: step: 1124/531, loss: 0.28697648644447327
2023-01-21 09:56:44.997748: step: 1128/531, loss: 0.05700264126062393
2023-01-21 09:56:46.132065: step: 1132/531, loss: 0.0170589666813612
2023-01-21 09:56:47.246513: step: 1136/531, loss: 0.0415375679731369
2023-01-21 09:56:48.380000: step: 1140/531, loss: 0.08867931365966797
2023-01-21 09:56:49.485883: step: 1144/531, loss: 0.05796985328197479
2023-01-21 09:56:50.598692: step: 1148/531, loss: 0.10943002998828888
2023-01-21 09:56:51.711574: step: 1152/531, loss: 0.04627714306116104
2023-01-21 09:56:52.826602: step: 1156/531, loss: 0.1122528612613678
2023-01-21 09:56:53.952282: step: 1160/531, loss: 0.4377952516078949
2023-01-21 09:56:55.054497: step: 1164/531, loss: 0.08515045791864395
2023-01-21 09:56:56.170808: step: 1168/531, loss: 0.07734423130750656
2023-01-21 09:56:57.304262: step: 1172/531, loss: 0.0968279168009758
2023-01-21 09:56:58.439924: step: 1176/531, loss: 0.3050578236579895
2023-01-21 09:56:59.563533: step: 1180/531, loss: 0.19285497069358826
2023-01-21 09:57:00.696674: step: 1184/531, loss: 0.14222678542137146
2023-01-21 09:57:01.829697: step: 1188/531, loss: 0.01756925694644451
2023-01-21 09:57:02.951312: step: 1192/531, loss: 0.05800233036279678
2023-01-21 09:57:04.073710: step: 1196/531, loss: 0.2442062348127365
2023-01-21 09:57:05.184536: step: 1200/531, loss: 0.21531029045581818
2023-01-21 09:57:06.299305: step: 1204/531, loss: 0.06375684589147568
2023-01-21 09:57:07.470104: step: 1208/531, loss: 0.10060425102710724
2023-01-21 09:57:08.600619: step: 1212/531, loss: 0.3734360635280609
2023-01-21 09:57:09.712400: step: 1216/531, loss: 0.1496995985507965
2023-01-21 09:57:10.832839: step: 1220/531, loss: 0.268998920917511
2023-01-21 09:57:11.975496: step: 1224/531, loss: 0.12165851145982742
2023-01-21 09:57:13.125752: step: 1228/531, loss: 0.26144829392433167
2023-01-21 09:57:14.239932: step: 1232/531, loss: 0.12758643925189972
2023-01-21 09:57:15.363427: step: 1236/531, loss: 0.8067438006401062
2023-01-21 09:57:16.510751: step: 1240/531, loss: 0.10680641978979111
2023-01-21 09:57:17.648654: step: 1244/531, loss: 0.08535700291395187
2023-01-21 09:57:18.779879: step: 1248/531, loss: 0.0566440112888813
2023-01-21 09:57:19.900796: step: 1252/531, loss: 0.10076337307691574
2023-01-21 09:57:21.050891: step: 1256/531, loss: 0.4221707284450531
2023-01-21 09:57:22.134669: step: 1260/531, loss: 0.01611499860882759
2023-01-21 09:57:23.272544: step: 1264/531, loss: 0.27151861786842346
2023-01-21 09:57:24.401172: step: 1268/531, loss: 0.06830034404993057
2023-01-21 09:57:25.518182: step: 1272/531, loss: 0.07658328860998154
2023-01-21 09:57:26.625687: step: 1276/531, loss: 0.07827463746070862
2023-01-21 09:57:27.713397: step: 1280/531, loss: 0.11044149100780487
2023-01-21 09:57:28.830594: step: 1284/531, loss: 0.10964183509349823
2023-01-21 09:57:29.984342: step: 1288/531, loss: 0.10096164047718048
2023-01-21 09:57:31.081088: step: 1292/531, loss: 0.06555338203907013
2023-01-21 09:57:32.191508: step: 1296/531, loss: 0.03680391609668732
2023-01-21 09:57:33.324692: step: 1300/531, loss: 0.09422969818115234
2023-01-21 09:57:34.442948: step: 1304/531, loss: 0.07193374633789062
2023-01-21 09:57:35.577872: step: 1308/531, loss: 0.05417776107788086
2023-01-21 09:57:36.691586: step: 1312/531, loss: 0.1379416584968567
2023-01-21 09:57:37.842845: step: 1316/531, loss: 0.05674038082361221
2023-01-21 09:57:38.985622: step: 1320/531, loss: 0.1321527510881424
2023-01-21 09:57:40.146796: step: 1324/531, loss: 0.004388761706650257
2023-01-21 09:57:41.289678: step: 1328/531, loss: 0.04815931245684624
2023-01-21 09:57:42.447975: step: 1332/531, loss: 0.11551463603973389
2023-01-21 09:57:43.561670: step: 1336/531, loss: 0.21281471848487854
2023-01-21 09:57:44.651473: step: 1340/531, loss: 0.017727375030517578
2023-01-21 09:57:45.803518: step: 1344/531, loss: 0.0568358451128006
2023-01-21 09:57:46.903369: step: 1348/531, loss: 0.09832391142845154
2023-01-21 09:57:48.016781: step: 1352/531, loss: 0.1027216762304306
2023-01-21 09:57:49.140143: step: 1356/531, loss: 0.17875251173973083
2023-01-21 09:57:50.265828: step: 1360/531, loss: 0.16329073905944824
2023-01-21 09:57:51.391715: step: 1364/531, loss: 0.3278714716434479
2023-01-21 09:57:52.552466: step: 1368/531, loss: 0.05779998376965523
2023-01-21 09:57:53.637614: step: 1372/531, loss: 0.12646451592445374
2023-01-21 09:57:54.748059: step: 1376/531, loss: 0.12449002265930176
2023-01-21 09:57:55.869336: step: 1380/531, loss: 0.020156146958470345
2023-01-21 09:57:56.994354: step: 1384/531, loss: 0.0186938289552927
2023-01-21 09:57:58.101866: step: 1388/531, loss: 0.02045416831970215
2023-01-21 09:57:59.237401: step: 1392/531, loss: 0.07984685897827148
2023-01-21 09:58:00.388353: step: 1396/531, loss: 0.10682721436023712
2023-01-21 09:58:01.517822: step: 1400/531, loss: 0.42404088377952576
2023-01-21 09:58:02.659390: step: 1404/531, loss: 0.12215514481067657
2023-01-21 09:58:03.810653: step: 1408/531, loss: 0.09165388345718384
2023-01-21 09:58:04.946953: step: 1412/531, loss: 0.002543376525864005
2023-01-21 09:58:06.089079: step: 1416/531, loss: 0.5665777325630188
2023-01-21 09:58:07.221810: step: 1420/531, loss: 0.0015269280411303043
2023-01-21 09:58:08.332278: step: 1424/531, loss: 0.1153249740600586
2023-01-21 09:58:09.462357: step: 1428/531, loss: 0.0989016517996788
2023-01-21 09:58:10.565090: step: 1432/531, loss: 0.033327486366033554
2023-01-21 09:58:11.679656: step: 1436/531, loss: 0.05953827127814293
2023-01-21 09:58:12.779105: step: 1440/531, loss: 0.2497701644897461
2023-01-21 09:58:13.920857: step: 1444/531, loss: 0.0793834701180458
2023-01-21 09:58:15.070773: step: 1448/531, loss: 0.05613536760210991
2023-01-21 09:58:16.211961: step: 1452/531, loss: 0.25240668654441833
2023-01-21 09:58:17.352807: step: 1456/531, loss: 0.017452144995331764
2023-01-21 09:58:18.460887: step: 1460/531, loss: 0.17958489060401917
2023-01-21 09:58:19.592530: step: 1464/531, loss: 0.10113926231861115
2023-01-21 09:58:20.712324: step: 1468/531, loss: 0.13999024033546448
2023-01-21 09:58:21.836357: step: 1472/531, loss: 0.0996173843741417
2023-01-21 09:58:22.943141: step: 1476/531, loss: 0.07060623168945312
2023-01-21 09:58:24.093855: step: 1480/531, loss: 0.06714344024658203
2023-01-21 09:58:25.240567: step: 1484/531, loss: 0.08549261838197708
2023-01-21 09:58:26.356123: step: 1488/531, loss: 0.13169966638088226
2023-01-21 09:58:27.476655: step: 1492/531, loss: 0.13795089721679688
2023-01-21 09:58:28.624378: step: 1496/531, loss: 0.08925362676382065
2023-01-21 09:58:29.762366: step: 1500/531, loss: 0.7767423391342163
2023-01-21 09:58:30.885181: step: 1504/531, loss: 0.2303818166255951
2023-01-21 09:58:32.005517: step: 1508/531, loss: 0.00633630808442831
2023-01-21 09:58:33.140628: step: 1512/531, loss: 0.16380244493484497
2023-01-21 09:58:34.247982: step: 1516/531, loss: 0.021251963451504707
2023-01-21 09:58:35.363085: step: 1520/531, loss: 0.06433776766061783
2023-01-21 09:58:36.501346: step: 1524/531, loss: 0.02528095245361328
2023-01-21 09:58:37.615091: step: 1528/531, loss: 0.2898082733154297
2023-01-21 09:58:38.740577: step: 1532/531, loss: 0.019547272473573685
2023-01-21 09:58:39.861524: step: 1536/531, loss: 0.031021595001220703
2023-01-21 09:58:41.015278: step: 1540/531, loss: 0.04787087440490723
2023-01-21 09:58:42.196810: step: 1544/531, loss: 0.04735222086310387
2023-01-21 09:58:43.323692: step: 1548/531, loss: 0.20263047516345978
2023-01-21 09:58:44.472957: step: 1552/531, loss: 0.685335099697113
2023-01-21 09:58:45.613535: step: 1556/531, loss: 0.1388796865940094
2023-01-21 09:58:46.751617: step: 1560/531, loss: 0.2668720483779907
2023-01-21 09:58:47.892929: step: 1564/531, loss: 0.12971554696559906
2023-01-21 09:58:49.092954: step: 1568/531, loss: 0.27143239974975586
2023-01-21 09:58:50.216656: step: 1572/531, loss: 0.1479652374982834
2023-01-21 09:58:51.308265: step: 1576/531, loss: 0.048185061663389206
2023-01-21 09:58:52.435238: step: 1580/531, loss: 0.07632150501012802
2023-01-21 09:58:53.544696: step: 1584/531, loss: 0.02477874793112278
2023-01-21 09:58:54.715921: step: 1588/531, loss: 0.13197068870067596
2023-01-21 09:58:55.818040: step: 1592/531, loss: 0.003121018409729004
2023-01-21 09:58:56.950405: step: 1596/531, loss: 0.07607078552246094
2023-01-21 09:58:58.060399: step: 1600/531, loss: 0.4999350905418396
2023-01-21 09:58:59.164680: step: 1604/531, loss: 0.12806305289268494
2023-01-21 09:59:00.279364: step: 1608/531, loss: 0.05977220833301544
2023-01-21 09:59:01.436941: step: 1612/531, loss: 0.07361612468957901
2023-01-21 09:59:02.547541: step: 1616/531, loss: 0.1490984410047531
2023-01-21 09:59:03.653446: step: 1620/531, loss: 0.012660825625061989
2023-01-21 09:59:04.810735: step: 1624/531, loss: 0.15770864486694336
2023-01-21 09:59:05.944059: step: 1628/531, loss: 0.01678595505654812
2023-01-21 09:59:07.086261: step: 1632/531, loss: 0.48617449402809143
2023-01-21 09:59:08.205524: step: 1636/531, loss: 0.15545912086963654
2023-01-21 09:59:09.328667: step: 1640/531, loss: 0.17079493403434753
2023-01-21 09:59:10.487635: step: 1644/531, loss: 0.13841553032398224
2023-01-21 09:59:11.644380: step: 1648/531, loss: 0.15446797013282776
2023-01-21 09:59:12.800623: step: 1652/531, loss: 0.07637205719947815
2023-01-21 09:59:13.918927: step: 1656/531, loss: 0.009453678503632545
2023-01-21 09:59:15.026067: step: 1660/531, loss: 0.28441524505615234
2023-01-21 09:59:16.144834: step: 1664/531, loss: 0.04133646562695503
2023-01-21 09:59:17.280948: step: 1668/531, loss: 0.07641124725341797
2023-01-21 09:59:18.407526: step: 1672/531, loss: 0.06717157363891602
2023-01-21 09:59:19.518769: step: 1676/531, loss: 0.14095020294189453
2023-01-21 09:59:20.689697: step: 1680/531, loss: 0.33387327194213867
2023-01-21 09:59:21.802672: step: 1684/531, loss: 0.09981915354728699
2023-01-21 09:59:22.935808: step: 1688/531, loss: 1.1915531158447266
2023-01-21 09:59:24.054080: step: 1692/531, loss: 0.019327307119965553
2023-01-21 09:59:25.192254: step: 1696/531, loss: 0.02034783363342285
2023-01-21 09:59:26.318121: step: 1700/531, loss: 0.006193351931869984
2023-01-21 09:59:27.460001: step: 1704/531, loss: 0.5670868158340454
2023-01-21 09:59:28.603575: step: 1708/531, loss: 2.2158162593841553
2023-01-21 09:59:29.720930: step: 1712/531, loss: 0.10447955131530762
2023-01-21 09:59:30.829026: step: 1716/531, loss: 0.04610328748822212
2023-01-21 09:59:31.952358: step: 1720/531, loss: 0.09350728988647461
2023-01-21 09:59:33.109895: step: 1724/531, loss: 0.11373177915811539
2023-01-21 09:59:34.266116: step: 1728/531, loss: 0.10574197769165039
2023-01-21 09:59:35.436049: step: 1732/531, loss: 0.14384347200393677
2023-01-21 09:59:36.617299: step: 1736/531, loss: 0.14875225722789764
2023-01-21 09:59:37.741058: step: 1740/531, loss: 0.11043176054954529
2023-01-21 09:59:38.854047: step: 1744/531, loss: 0.0686761885881424
2023-01-21 09:59:40.001796: step: 1748/531, loss: 0.14543715119361877
2023-01-21 09:59:41.113173: step: 1752/531, loss: 0.23023854196071625
2023-01-21 09:59:42.260814: step: 1756/531, loss: 0.06384191662073135
2023-01-21 09:59:43.404987: step: 1760/531, loss: 0.0273863784968853
2023-01-21 09:59:44.544887: step: 1764/531, loss: 0.031943678855895996
2023-01-21 09:59:45.652623: step: 1768/531, loss: 0.06780986487865448
2023-01-21 09:59:46.777151: step: 1772/531, loss: 0.059722043573856354
2023-01-21 09:59:47.912170: step: 1776/531, loss: 0.09308472275733948
2023-01-21 09:59:49.045575: step: 1780/531, loss: 0.06750917434692383
2023-01-21 09:59:50.163383: step: 1784/531, loss: 0.08478861302137375
2023-01-21 09:59:51.271893: step: 1788/531, loss: 0.010016251355409622
2023-01-21 09:59:52.399843: step: 1792/531, loss: 0.07060471177101135
2023-01-21 09:59:53.502368: step: 1796/531, loss: 0.1633385717868805
2023-01-21 09:59:54.631775: step: 1800/531, loss: 0.008719349279999733
2023-01-21 09:59:55.779916: step: 1804/531, loss: 0.0678853988647461
2023-01-21 09:59:56.888759: step: 1808/531, loss: 0.5351272225379944
2023-01-21 09:59:57.967835: step: 1812/531, loss: 0.08534260094165802
2023-01-21 09:59:59.089976: step: 1816/531, loss: 0.15985670685768127
2023-01-21 10:00:00.224415: step: 1820/531, loss: 0.08133211731910706
2023-01-21 10:00:01.371688: step: 1824/531, loss: 0.026988983154296875
2023-01-21 10:00:02.513787: step: 1828/531, loss: 0.10074234008789062
2023-01-21 10:00:03.657749: step: 1832/531, loss: 0.1154978796839714
2023-01-21 10:00:04.756976: step: 1836/531, loss: 0.07311529666185379
2023-01-21 10:00:05.938575: step: 1840/531, loss: 0.0812930092215538
2023-01-21 10:00:07.072401: step: 1844/531, loss: 0.07065191864967346
2023-01-21 10:00:08.183297: step: 1848/531, loss: 0.03830909729003906
2023-01-21 10:00:09.320711: step: 1852/531, loss: 0.26345059275627136
2023-01-21 10:00:10.451787: step: 1856/531, loss: 0.2540784776210785
2023-01-21 10:00:11.552685: step: 1860/531, loss: 0.3297414779663086
2023-01-21 10:00:12.695692: step: 1864/531, loss: 0.29000750184059143
2023-01-21 10:00:13.879773: step: 1868/531, loss: 0.9680474996566772
2023-01-21 10:00:15.004302: step: 1872/531, loss: 0.05043964087963104
2023-01-21 10:00:16.152746: step: 1876/531, loss: 0.21940383315086365
2023-01-21 10:00:17.279799: step: 1880/531, loss: 0.07403242588043213
2023-01-21 10:00:18.408007: step: 1884/531, loss: 0.08945588767528534
2023-01-21 10:00:19.536177: step: 1888/531, loss: 0.08835281431674957
2023-01-21 10:00:20.694409: step: 1892/531, loss: 0.0068323370069265366
2023-01-21 10:00:21.833563: step: 1896/531, loss: 0.019809197634458542
2023-01-21 10:00:22.947407: step: 1900/531, loss: 0.059524111449718475
2023-01-21 10:00:24.053203: step: 1904/531, loss: 0.08691282570362091
2023-01-21 10:00:25.172091: step: 1908/531, loss: 0.3050805926322937
2023-01-21 10:00:26.293356: step: 1912/531, loss: 0.1144617572426796
2023-01-21 10:00:27.418272: step: 1916/531, loss: 0.15250836312770844
2023-01-21 10:00:28.514409: step: 1920/531, loss: 0.05736827850341797
2023-01-21 10:00:29.650277: step: 1924/531, loss: 0.11525671184062958
2023-01-21 10:00:30.752441: step: 1928/531, loss: 0.1003013551235199
2023-01-21 10:00:31.895512: step: 1932/531, loss: 0.06514883041381836
2023-01-21 10:00:33.019117: step: 1936/531, loss: 0.0098114013671875
2023-01-21 10:00:34.160552: step: 1940/531, loss: 0.07660255581140518
2023-01-21 10:00:35.291229: step: 1944/531, loss: 0.1701059341430664
2023-01-21 10:00:36.385689: step: 1948/531, loss: 0.1081278845667839
2023-01-21 10:00:37.495946: step: 1952/531, loss: 0.18591547012329102
2023-01-21 10:00:38.605428: step: 1956/531, loss: 0.052460767328739166
2023-01-21 10:00:39.728759: step: 1960/531, loss: 0.14924316108226776
2023-01-21 10:00:40.871894: step: 1964/531, loss: 0.22551065683364868
2023-01-21 10:00:42.004990: step: 1968/531, loss: 0.01474838238209486
2023-01-21 10:00:43.109576: step: 1972/531, loss: 0.08996324986219406
2023-01-21 10:00:44.224040: step: 1976/531, loss: 0.07870092988014221
2023-01-21 10:00:45.327301: step: 1980/531, loss: 0.12241601943969727
2023-01-21 10:00:46.457026: step: 1984/531, loss: 0.10796394944190979
2023-01-21 10:00:47.570006: step: 1988/531, loss: 0.02081594616174698
2023-01-21 10:00:48.716781: step: 1992/531, loss: 0.10027255862951279
2023-01-21 10:00:49.844219: step: 1996/531, loss: 0.08087669312953949
2023-01-21 10:00:50.975206: step: 2000/531, loss: 0.10377130657434464
2023-01-21 10:00:52.088569: step: 2004/531, loss: 0.12663955986499786
2023-01-21 10:00:53.208713: step: 2008/531, loss: 0.06766510009765625
2023-01-21 10:00:54.331360: step: 2012/531, loss: 0.0170135498046875
2023-01-21 10:00:55.453549: step: 2016/531, loss: 0.17701482772827148
2023-01-21 10:00:56.568251: step: 2020/531, loss: 0.14005009829998016
2023-01-21 10:00:57.674596: step: 2024/531, loss: 0.06755342334508896
2023-01-21 10:00:58.834172: step: 2028/531, loss: 0.09678593277931213
2023-01-21 10:00:59.953698: step: 2032/531, loss: 0.003017520997673273
2023-01-21 10:01:01.077913: step: 2036/531, loss: 0.09307806193828583
2023-01-21 10:01:02.214693: step: 2040/531, loss: 0.365352988243103
2023-01-21 10:01:03.315309: step: 2044/531, loss: 0.0351262092590332
2023-01-21 10:01:04.432389: step: 2048/531, loss: 0.1755780279636383
2023-01-21 10:01:05.530299: step: 2052/531, loss: 0.3529370427131653
2023-01-21 10:01:06.644218: step: 2056/531, loss: 0.09701728820800781
2023-01-21 10:01:07.805801: step: 2060/531, loss: 0.1922387182712555
2023-01-21 10:01:08.958056: step: 2064/531, loss: 0.10014934837818146
2023-01-21 10:01:10.055608: step: 2068/531, loss: 0.3301507234573364
2023-01-21 10:01:11.177773: step: 2072/531, loss: 0.04248299449682236
2023-01-21 10:01:12.312795: step: 2076/531, loss: 0.30544883012771606
2023-01-21 10:01:13.423076: step: 2080/531, loss: 0.23375114798545837
2023-01-21 10:01:14.554975: step: 2084/531, loss: 0.04997606575489044
2023-01-21 10:01:15.670306: step: 2088/531, loss: 0.12072034180164337
2023-01-21 10:01:16.837510: step: 2092/531, loss: 0.19212289154529572
2023-01-21 10:01:17.956484: step: 2096/531, loss: 0.07236509025096893
2023-01-21 10:01:19.080935: step: 2100/531, loss: 0.10623031854629517
2023-01-21 10:01:20.181601: step: 2104/531, loss: 0.0291458610445261
2023-01-21 10:01:21.324018: step: 2108/531, loss: 0.13434329628944397
2023-01-21 10:01:22.471595: step: 2112/531, loss: 0.07110749185085297
2023-01-21 10:01:23.600177: step: 2116/531, loss: 0.1486809253692627
2023-01-21 10:01:24.754072: step: 2120/531, loss: 0.16819463670253754
2023-01-21 10:01:25.867823: step: 2124/531, loss: 0.10602817684412003
==================================================
Loss: 0.144
--------------------
Dev: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
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': 8}
Korean: {'event': {'p': 0.5942028985507246, 'r': 0.6507936507936508, 'f1': 0.6212121212121213}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5440900562851783, 'r': 0.7723035952063915, 'f1': 0.6384149697303247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Korean: {'event': {'p': 0.5672823218997362, 'r': 0.7692307692307693, 'f1': 0.6529992406985574}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Korean: {'event': {'p': 0.6557377049180327, 'r': 0.6349206349206349, 'f1': 0.6451612903225806}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:02:12.844241: step: 4/531, loss: 0.31909045577049255
2023-01-21 10:02:13.951863: step: 8/531, loss: 0.037078142166137695
2023-01-21 10:02:15.081775: step: 12/531, loss: 0.0841670036315918
2023-01-21 10:02:16.217842: step: 16/531, loss: 0.12582865357398987
2023-01-21 10:02:17.372102: step: 20/531, loss: 0.17043820023536682
2023-01-21 10:02:18.507311: step: 24/531, loss: 0.12123699486255646
2023-01-21 10:02:19.644917: step: 28/531, loss: 0.039379313588142395
2023-01-21 10:02:20.763202: step: 32/531, loss: 0.09817925095558167
2023-01-21 10:02:21.890421: step: 36/531, loss: 0.07535353302955627
2023-01-21 10:02:23.014593: step: 40/531, loss: 0.10911738872528076
2023-01-21 10:02:24.134321: step: 44/531, loss: 0.05755939334630966
2023-01-21 10:02:25.240688: step: 48/531, loss: 0.07273159176111221
2023-01-21 10:02:26.378983: step: 52/531, loss: 0.07716216892004013
2023-01-21 10:02:27.489760: step: 56/531, loss: 0.804498553276062
2023-01-21 10:02:28.603373: step: 60/531, loss: 0.049272045493125916
2023-01-21 10:02:29.749855: step: 64/531, loss: 0.018027782440185547
2023-01-21 10:02:30.913044: step: 68/531, loss: 0.12482643872499466
2023-01-21 10:02:32.081315: step: 72/531, loss: 0.24122542142868042
2023-01-21 10:02:33.190977: step: 76/531, loss: 0.3045158386230469
2023-01-21 10:02:34.295855: step: 80/531, loss: 0.03714761883020401
2023-01-21 10:02:35.456937: step: 84/531, loss: 0.18369553983211517
2023-01-21 10:02:36.590537: step: 88/531, loss: 0.21868562698364258
2023-01-21 10:02:37.719262: step: 92/531, loss: 0.05772380903363228
2023-01-21 10:02:38.872055: step: 96/531, loss: 5.584299087524414
2023-01-21 10:02:40.027306: step: 100/531, loss: 0.027874279767274857
2023-01-21 10:02:41.148618: step: 104/531, loss: 0.01469721831381321
2023-01-21 10:02:42.271859: step: 108/531, loss: 1.1670235395431519
2023-01-21 10:02:43.374455: step: 112/531, loss: 0.18922977149486542
2023-01-21 10:02:44.479820: step: 116/531, loss: 0.08198051154613495
2023-01-21 10:02:45.641103: step: 120/531, loss: 0.1001686081290245
2023-01-21 10:02:46.792549: step: 124/531, loss: 0.06911039352416992
2023-01-21 10:02:47.950791: step: 128/531, loss: 0.09733366966247559
2023-01-21 10:02:49.066742: step: 132/531, loss: 0.016380691900849342
2023-01-21 10:02:50.197661: step: 136/531, loss: 0.10049648582935333
2023-01-21 10:02:51.380034: step: 140/531, loss: 0.11149883270263672
2023-01-21 10:02:52.554103: step: 144/531, loss: 0.23117217421531677
2023-01-21 10:02:53.699204: step: 148/531, loss: 0.05333299562335014
2023-01-21 10:02:54.836599: step: 152/531, loss: 0.037677764892578125
2023-01-21 10:02:55.979247: step: 156/531, loss: 0.04156494140625
2023-01-21 10:02:57.144348: step: 160/531, loss: 0.04186396673321724
2023-01-21 10:02:58.310617: step: 164/531, loss: 0.06371164321899414
2023-01-21 10:02:59.426864: step: 168/531, loss: 0.2132912129163742
2023-01-21 10:03:00.576538: step: 172/531, loss: 0.034682463854551315
2023-01-21 10:03:01.709187: step: 176/531, loss: 0.028105830773711205
2023-01-21 10:03:02.838964: step: 180/531, loss: 0.06054316833615303
2023-01-21 10:03:03.965476: step: 184/531, loss: 0.10442256927490234
2023-01-21 10:03:05.094543: step: 188/531, loss: 0.2509746551513672
2023-01-21 10:03:06.192240: step: 192/531, loss: 0.03860321268439293
2023-01-21 10:03:07.340037: step: 196/531, loss: 0.12578296661376953
2023-01-21 10:03:08.487413: step: 200/531, loss: 0.07383518666028976
2023-01-21 10:03:09.643105: step: 204/531, loss: 0.6116253137588501
2023-01-21 10:03:10.754647: step: 208/531, loss: 0.14551010727882385
2023-01-21 10:03:11.894190: step: 212/531, loss: 0.04541236162185669
2023-01-21 10:03:13.002911: step: 216/531, loss: 0.125435933470726
2023-01-21 10:03:14.102596: step: 220/531, loss: 0.03750262036919594
2023-01-21 10:03:15.219056: step: 224/531, loss: 0.04600963741540909
2023-01-21 10:03:16.360297: step: 228/531, loss: 0.1304098218679428
2023-01-21 10:03:17.468533: step: 232/531, loss: 0.07334728538990021
2023-01-21 10:03:18.585149: step: 236/531, loss: 0.13074293732643127
2023-01-21 10:03:19.727078: step: 240/531, loss: 0.10463714599609375
2023-01-21 10:03:20.862436: step: 244/531, loss: 0.15595942735671997
2023-01-21 10:03:21.988948: step: 248/531, loss: 0.14452801644802094
2023-01-21 10:03:23.135987: step: 252/531, loss: 0.047496773302555084
2023-01-21 10:03:24.266736: step: 256/531, loss: 0.21338015794754028
2023-01-21 10:03:25.361702: step: 260/531, loss: 0.031382083892822266
2023-01-21 10:03:26.505209: step: 264/531, loss: 0.04427752271294594
2023-01-21 10:03:27.611609: step: 268/531, loss: 0.11613781750202179
2023-01-21 10:03:28.746060: step: 272/531, loss: 0.09052430093288422
2023-01-21 10:03:29.855827: step: 276/531, loss: 0.029305458068847656
2023-01-21 10:03:30.958295: step: 280/531, loss: 0.01891002617776394
2023-01-21 10:03:32.054539: step: 284/531, loss: 0.04548092186450958
2023-01-21 10:03:33.159668: step: 288/531, loss: 0.016316795721650124
2023-01-21 10:03:34.271250: step: 292/531, loss: 0.024338459596037865
2023-01-21 10:03:35.372934: step: 296/531, loss: 0.13635587692260742
2023-01-21 10:03:36.469658: step: 300/531, loss: 0.0565369613468647
2023-01-21 10:03:37.609822: step: 304/531, loss: 0.07782649993896484
2023-01-21 10:03:38.741501: step: 308/531, loss: 0.02421417273581028
2023-01-21 10:03:39.902892: step: 312/531, loss: 0.48803621530532837
2023-01-21 10:03:41.017177: step: 316/531, loss: 0.021121645346283913
2023-01-21 10:03:42.141294: step: 320/531, loss: 0.03810405731201172
2023-01-21 10:03:43.265954: step: 324/531, loss: 0.06846747547388077
2023-01-21 10:03:44.388259: step: 328/531, loss: 0.06744422763586044
2023-01-21 10:03:45.529403: step: 332/531, loss: 0.051459599286317825
2023-01-21 10:03:46.656682: step: 336/531, loss: 0.07121706008911133
2023-01-21 10:03:47.768949: step: 340/531, loss: 0.1775798797607422
2023-01-21 10:03:48.882460: step: 344/531, loss: 0.46801018714904785
2023-01-21 10:03:49.980680: step: 348/531, loss: 0.07138261944055557
2023-01-21 10:03:51.091221: step: 352/531, loss: 0.058658890426158905
2023-01-21 10:03:52.192091: step: 356/531, loss: 0.036805249750614166
2023-01-21 10:03:53.341346: step: 360/531, loss: 0.06067600101232529
2023-01-21 10:03:54.467990: step: 364/531, loss: 0.05421276018023491
2023-01-21 10:03:55.601683: step: 368/531, loss: 0.08465640246868134
2023-01-21 10:03:56.733050: step: 372/531, loss: 0.020247556269168854
2023-01-21 10:03:57.836695: step: 376/531, loss: 0.09053757786750793
2023-01-21 10:03:58.930418: step: 380/531, loss: 0.021294688805937767
2023-01-21 10:04:00.078142: step: 384/531, loss: 0.06727886199951172
2023-01-21 10:04:01.244154: step: 388/531, loss: 0.02019805833697319
2023-01-21 10:04:02.379697: step: 392/531, loss: 0.07179603725671768
2023-01-21 10:04:03.495182: step: 396/531, loss: 0.03279180824756622
2023-01-21 10:04:04.620166: step: 400/531, loss: 0.2440163642168045
2023-01-21 10:04:05.779873: step: 404/531, loss: 0.12595805525779724
2023-01-21 10:04:06.954289: step: 408/531, loss: 0.2527076005935669
2023-01-21 10:04:08.063710: step: 412/531, loss: 0.08531894534826279
2023-01-21 10:04:09.195338: step: 416/531, loss: 0.003537422278895974
2023-01-21 10:04:10.319691: step: 420/531, loss: 0.25832539796829224
2023-01-21 10:04:11.477125: step: 424/531, loss: 0.181183859705925
2023-01-21 10:04:12.655350: step: 428/531, loss: 0.732094407081604
2023-01-21 10:04:13.793320: step: 432/531, loss: 0.08710232377052307
2023-01-21 10:04:14.933198: step: 436/531, loss: 0.15557976067066193
2023-01-21 10:04:16.088958: step: 440/531, loss: 0.07858042418956757
2023-01-21 10:04:17.203136: step: 444/531, loss: 0.022815801203250885
2023-01-21 10:04:18.340126: step: 448/531, loss: 0.32257080078125
2023-01-21 10:04:19.462098: step: 452/531, loss: 0.1284807175397873
2023-01-21 10:04:20.588422: step: 456/531, loss: 0.03366794437170029
2023-01-21 10:04:21.719037: step: 460/531, loss: 0.08315540850162506
2023-01-21 10:04:22.848498: step: 464/531, loss: 0.45114973187446594
2023-01-21 10:04:23.949046: step: 468/531, loss: 0.07650595158338547
2023-01-21 10:04:25.057299: step: 472/531, loss: 0.0158828254789114
2023-01-21 10:04:26.169166: step: 476/531, loss: 0.011155223473906517
2023-01-21 10:04:27.291557: step: 480/531, loss: 0.07284365594387054
2023-01-21 10:04:28.416649: step: 484/531, loss: 0.6783890724182129
2023-01-21 10:04:29.565634: step: 488/531, loss: 1.201550006866455
2023-01-21 10:04:30.679924: step: 492/531, loss: 0.5268360376358032
2023-01-21 10:04:31.808698: step: 496/531, loss: 0.12687844038009644
2023-01-21 10:04:32.930143: step: 500/531, loss: 0.06399841606616974
2023-01-21 10:04:34.052881: step: 504/531, loss: 0.022037316113710403
2023-01-21 10:04:35.170527: step: 508/531, loss: 0.06802206486463547
2023-01-21 10:04:36.305804: step: 512/531, loss: 0.10186205059289932
2023-01-21 10:04:37.422663: step: 516/531, loss: 0.13489818572998047
2023-01-21 10:04:38.534488: step: 520/531, loss: 0.13723459839820862
2023-01-21 10:04:39.668225: step: 524/531, loss: 0.05866193771362305
2023-01-21 10:04:40.777452: step: 528/531, loss: 0.289966881275177
2023-01-21 10:04:41.899105: step: 532/531, loss: 0.03711710125207901
2023-01-21 10:04:43.014963: step: 536/531, loss: 0.03171816095709801
2023-01-21 10:04:44.133617: step: 540/531, loss: 0.11456423252820969
2023-01-21 10:04:45.268015: step: 544/531, loss: 0.05799246206879616
2023-01-21 10:04:46.382933: step: 548/531, loss: 0.0937773734331131
2023-01-21 10:04:47.531899: step: 552/531, loss: 0.06285877525806427
2023-01-21 10:04:48.643799: step: 556/531, loss: 0.021840382367372513
2023-01-21 10:04:49.778862: step: 560/531, loss: 0.06548366695642471
2023-01-21 10:04:50.875886: step: 564/531, loss: 0.1856127828359604
2023-01-21 10:04:51.966170: step: 568/531, loss: 0.1117589920759201
2023-01-21 10:04:53.097200: step: 572/531, loss: 0.07032656669616699
2023-01-21 10:04:54.207855: step: 576/531, loss: 0.042340949177742004
2023-01-21 10:04:55.342488: step: 580/531, loss: 0.062026023864746094
2023-01-21 10:04:56.476379: step: 584/531, loss: 0.01966714859008789
2023-01-21 10:04:57.576137: step: 588/531, loss: 0.02689497545361519
2023-01-21 10:04:58.717114: step: 592/531, loss: 0.03945789486169815
2023-01-21 10:04:59.849162: step: 596/531, loss: 0.04961257055401802
2023-01-21 10:05:00.958081: step: 600/531, loss: 0.043687380850315094
2023-01-21 10:05:02.089282: step: 604/531, loss: 0.44286900758743286
2023-01-21 10:05:03.213891: step: 608/531, loss: 0.08942585438489914
2023-01-21 10:05:04.316053: step: 612/531, loss: 0.030391883105039597
2023-01-21 10:05:05.463015: step: 616/531, loss: 0.18536902964115143
2023-01-21 10:05:06.587614: step: 620/531, loss: 0.07486476749181747
2023-01-21 10:05:07.716172: step: 624/531, loss: 0.09050474315881729
2023-01-21 10:05:08.839418: step: 628/531, loss: 0.021355438977479935
2023-01-21 10:05:09.985168: step: 632/531, loss: 0.022111916914582253
2023-01-21 10:05:11.119619: step: 636/531, loss: 0.11121144145727158
2023-01-21 10:05:12.283047: step: 640/531, loss: 0.07157446444034576
2023-01-21 10:05:13.371590: step: 644/531, loss: 0.04613058641552925
2023-01-21 10:05:14.500495: step: 648/531, loss: 0.06300268322229385
2023-01-21 10:05:15.584807: step: 652/531, loss: 0.0605621337890625
2023-01-21 10:05:16.703775: step: 656/531, loss: 0.04886054992675781
2023-01-21 10:05:17.851295: step: 660/531, loss: 0.05051088333129883
2023-01-21 10:05:18.968375: step: 664/531, loss: 0.1045856699347496
2023-01-21 10:05:20.104661: step: 668/531, loss: 0.029742669314146042
2023-01-21 10:05:21.234141: step: 672/531, loss: 0.04398756101727486
2023-01-21 10:05:22.357007: step: 676/531, loss: 0.005153656005859375
2023-01-21 10:05:23.487645: step: 680/531, loss: 0.05403862148523331
2023-01-21 10:05:24.640636: step: 684/531, loss: 0.1767353117465973
2023-01-21 10:05:25.759042: step: 688/531, loss: 0.12196855992078781
2023-01-21 10:05:26.889298: step: 692/531, loss: 0.035198405385017395
2023-01-21 10:05:28.019156: step: 696/531, loss: 0.05893202871084213
2023-01-21 10:05:29.144690: step: 700/531, loss: 0.06709900498390198
2023-01-21 10:05:30.263745: step: 704/531, loss: 0.06087055057287216
2023-01-21 10:05:31.391127: step: 708/531, loss: 0.07497959583997726
2023-01-21 10:05:32.538723: step: 712/531, loss: 0.49636325240135193
2023-01-21 10:05:33.678659: step: 716/531, loss: 0.012936878018081188
2023-01-21 10:05:34.781254: step: 720/531, loss: 0.11730575561523438
2023-01-21 10:05:35.913710: step: 724/531, loss: 0.0354369655251503
2023-01-21 10:05:37.018641: step: 728/531, loss: 0.056232403963804245
2023-01-21 10:05:38.116366: step: 732/531, loss: 0.07861710339784622
2023-01-21 10:05:39.271731: step: 736/531, loss: 0.48582953214645386
2023-01-21 10:05:40.394345: step: 740/531, loss: 0.058643341064453125
2023-01-21 10:05:41.503823: step: 744/531, loss: 0.06756439059972763
2023-01-21 10:05:42.635980: step: 748/531, loss: 0.07690195739269257
2023-01-21 10:05:43.769384: step: 752/531, loss: 0.08358307182788849
2023-01-21 10:05:44.948616: step: 756/531, loss: 0.06763915717601776
2023-01-21 10:05:46.056415: step: 760/531, loss: 0.027800749987363815
2023-01-21 10:05:47.196637: step: 764/531, loss: 0.14589671790599823
2023-01-21 10:05:48.322464: step: 768/531, loss: 0.11147131770849228
2023-01-21 10:05:49.464520: step: 772/531, loss: 0.1203577071428299
2023-01-21 10:05:50.598612: step: 776/531, loss: 0.08193574100732803
2023-01-21 10:05:51.717897: step: 780/531, loss: 0.08551311492919922
2023-01-21 10:05:52.855318: step: 784/531, loss: 0.0034237862564623356
2023-01-21 10:05:53.955168: step: 788/531, loss: 0.06019439548254013
2023-01-21 10:05:55.062516: step: 792/531, loss: 0.18407364189624786
2023-01-21 10:05:56.168826: step: 796/531, loss: 0.030537035316228867
2023-01-21 10:05:57.271465: step: 800/531, loss: 0.04573202133178711
2023-01-21 10:05:58.379008: step: 804/531, loss: 0.031029606238007545
2023-01-21 10:05:59.507825: step: 808/531, loss: 0.03390789031982422
2023-01-21 10:06:00.652504: step: 812/531, loss: 0.0703950896859169
2023-01-21 10:06:01.762327: step: 816/531, loss: 0.07148733735084534
2023-01-21 10:06:02.878136: step: 820/531, loss: 0.332615464925766
2023-01-21 10:06:04.004010: step: 824/531, loss: 0.006299400236457586
2023-01-21 10:06:05.150180: step: 828/531, loss: 0.12487068772315979
2023-01-21 10:06:06.285237: step: 832/531, loss: 0.06828222423791885
2023-01-21 10:06:07.414511: step: 836/531, loss: 0.11381582170724869
2023-01-21 10:06:08.548159: step: 840/531, loss: 0.057506464421749115
2023-01-21 10:06:09.652259: step: 844/531, loss: 0.05408325418829918
2023-01-21 10:06:10.776877: step: 848/531, loss: 0.012376022525131702
2023-01-21 10:06:11.936702: step: 852/531, loss: 0.026075365021824837
2023-01-21 10:06:13.080208: step: 856/531, loss: 0.05112367123365402
2023-01-21 10:06:14.207428: step: 860/531, loss: 0.05298871919512749
2023-01-21 10:06:15.343173: step: 864/531, loss: 0.03767933323979378
2023-01-21 10:06:16.495626: step: 868/531, loss: 0.08618870377540588
2023-01-21 10:06:17.629900: step: 872/531, loss: 0.0011233807308599353
2023-01-21 10:06:18.725085: step: 876/531, loss: 0.013519859872758389
2023-01-21 10:06:19.880248: step: 880/531, loss: 0.010107326321303844
2023-01-21 10:06:21.023046: step: 884/531, loss: 0.4964072108268738
2023-01-21 10:06:22.170343: step: 888/531, loss: 0.07998915016651154
2023-01-21 10:06:23.313316: step: 892/531, loss: 0.16665571928024292
2023-01-21 10:06:24.428673: step: 896/531, loss: 0.0017509461613371968
2023-01-21 10:06:25.576400: step: 900/531, loss: 0.09706497192382812
2023-01-21 10:06:26.651508: step: 904/531, loss: 0.0925418883562088
2023-01-21 10:06:27.785284: step: 908/531, loss: 0.17431049048900604
2023-01-21 10:06:28.925230: step: 912/531, loss: 0.05579571798443794
2023-01-21 10:06:30.038745: step: 916/531, loss: 0.035646677017211914
2023-01-21 10:06:31.174684: step: 920/531, loss: 0.07259368896484375
2023-01-21 10:06:32.339131: step: 924/531, loss: 0.09151449054479599
2023-01-21 10:06:33.475147: step: 928/531, loss: 0.07399015128612518
2023-01-21 10:06:34.590678: step: 932/531, loss: 0.03648786619305611
2023-01-21 10:06:35.717033: step: 936/531, loss: 0.09260229766368866
2023-01-21 10:06:36.843869: step: 940/531, loss: 0.02603902854025364
2023-01-21 10:06:37.983553: step: 944/531, loss: 0.06427974998950958
2023-01-21 10:06:39.104500: step: 948/531, loss: 0.016600418835878372
2023-01-21 10:06:40.255634: step: 952/531, loss: 0.09395341575145721
2023-01-21 10:06:41.380693: step: 956/531, loss: 0.032543376088142395
2023-01-21 10:06:42.525207: step: 960/531, loss: 0.12543974816799164
2023-01-21 10:06:43.638389: step: 964/531, loss: 0.03914222866296768
2023-01-21 10:06:44.730951: step: 968/531, loss: 0.11849412322044373
2023-01-21 10:06:45.836096: step: 972/531, loss: 0.06281500309705734
2023-01-21 10:06:46.994121: step: 976/531, loss: 0.08752767741680145
2023-01-21 10:06:48.155827: step: 980/531, loss: 0.06272812187671661
2023-01-21 10:06:49.290999: step: 984/531, loss: 0.027181481942534447
2023-01-21 10:06:50.393723: step: 988/531, loss: 0.338143527507782
2023-01-21 10:06:51.532597: step: 992/531, loss: 0.09397459030151367
2023-01-21 10:06:52.643921: step: 996/531, loss: 0.12037691473960876
2023-01-21 10:06:53.759595: step: 1000/531, loss: 0.053514860570430756
2023-01-21 10:06:54.885808: step: 1004/531, loss: 0.009878921322524548
2023-01-21 10:06:56.021185: step: 1008/531, loss: 0.016734063625335693
2023-01-21 10:06:57.135000: step: 1012/531, loss: 0.39299219846725464
2023-01-21 10:06:58.282318: step: 1016/531, loss: 0.1138072982430458
2023-01-21 10:06:59.436826: step: 1020/531, loss: 0.1508607417345047
2023-01-21 10:07:00.549056: step: 1024/531, loss: 0.04865751415491104
2023-01-21 10:07:01.659412: step: 1028/531, loss: 0.36741331219673157
2023-01-21 10:07:02.807668: step: 1032/531, loss: 0.08409996330738068
2023-01-21 10:07:03.888528: step: 1036/531, loss: 0.037766218185424805
2023-01-21 10:07:05.011677: step: 1040/531, loss: 0.0341833122074604
2023-01-21 10:07:06.143958: step: 1044/531, loss: 0.2561612129211426
2023-01-21 10:07:07.262315: step: 1048/531, loss: 0.057497598230838776
2023-01-21 10:07:08.402324: step: 1052/531, loss: 0.03621196746826172
2023-01-21 10:07:09.571363: step: 1056/531, loss: 0.09418167918920517
2023-01-21 10:07:10.740540: step: 1060/531, loss: 0.13171425461769104
2023-01-21 10:07:11.895519: step: 1064/531, loss: 0.05039277300238609
2023-01-21 10:07:13.030013: step: 1068/531, loss: 0.007500076200813055
2023-01-21 10:07:14.143879: step: 1072/531, loss: 0.22494734823703766
2023-01-21 10:07:15.259903: step: 1076/531, loss: 0.010428810492157936
2023-01-21 10:07:16.399340: step: 1080/531, loss: 0.1318804770708084
2023-01-21 10:07:17.523400: step: 1084/531, loss: 0.07227544486522675
2023-01-21 10:07:18.637971: step: 1088/531, loss: 0.024955179542303085
2023-01-21 10:07:19.766853: step: 1092/531, loss: 0.04012352228164673
2023-01-21 10:07:20.895048: step: 1096/531, loss: 0.07499256730079651
2023-01-21 10:07:21.988855: step: 1100/531, loss: 0.06900925934314728
2023-01-21 10:07:23.107632: step: 1104/531, loss: 0.1402699500322342
2023-01-21 10:07:24.214590: step: 1108/531, loss: 0.08230245113372803
2023-01-21 10:07:25.335317: step: 1112/531, loss: 0.2658105790615082
2023-01-21 10:07:26.424773: step: 1116/531, loss: 0.10187321156263351
2023-01-21 10:07:27.627626: step: 1120/531, loss: 0.04635109752416611
2023-01-21 10:07:28.743415: step: 1124/531, loss: 0.06519933044910431
2023-01-21 10:07:29.869677: step: 1128/531, loss: 0.1938866227865219
2023-01-21 10:07:30.999003: step: 1132/531, loss: 0.060333251953125
2023-01-21 10:07:32.115636: step: 1136/531, loss: 0.030127622187137604
2023-01-21 10:07:33.254648: step: 1140/531, loss: 0.18982361257076263
2023-01-21 10:07:34.390024: step: 1144/531, loss: 0.04920043796300888
2023-01-21 10:07:35.514717: step: 1148/531, loss: 0.06450013816356659
2023-01-21 10:07:36.667716: step: 1152/531, loss: 0.05666818842291832
2023-01-21 10:07:37.797161: step: 1156/531, loss: 0.03358716890215874
2023-01-21 10:07:38.945878: step: 1160/531, loss: 1.0521191358566284
2023-01-21 10:07:40.113503: step: 1164/531, loss: 0.12741927802562714
2023-01-21 10:07:41.273436: step: 1168/531, loss: 0.054516952484846115
2023-01-21 10:07:42.391442: step: 1172/531, loss: 0.06138163059949875
2023-01-21 10:07:43.505560: step: 1176/531, loss: 0.2393409013748169
2023-01-21 10:07:44.623132: step: 1180/531, loss: 0.10070428997278214
2023-01-21 10:07:45.745993: step: 1184/531, loss: 0.003009033389389515
2023-01-21 10:07:46.871666: step: 1188/531, loss: 0.1621139496564865
2023-01-21 10:07:48.012108: step: 1192/531, loss: 0.1881113201379776
2023-01-21 10:07:49.105083: step: 1196/531, loss: 0.03025512769818306
2023-01-21 10:07:50.211933: step: 1200/531, loss: 0.08049193024635315
2023-01-21 10:07:51.298326: step: 1204/531, loss: 0.011544609442353249
2023-01-21 10:07:52.437819: step: 1208/531, loss: 0.3903922140598297
2023-01-21 10:07:53.579202: step: 1212/531, loss: 0.02210693433880806
2023-01-21 10:07:54.740438: step: 1216/531, loss: 0.10994205623865128
2023-01-21 10:07:55.881121: step: 1220/531, loss: 0.17045241594314575
2023-01-21 10:07:57.004203: step: 1224/531, loss: 0.10896234214305878
2023-01-21 10:07:58.126862: step: 1228/531, loss: 0.044367074966430664
2023-01-21 10:07:59.263418: step: 1232/531, loss: 0.03995375707745552
2023-01-21 10:08:00.391882: step: 1236/531, loss: 0.11155105382204056
2023-01-21 10:08:01.547773: step: 1240/531, loss: 0.041585251688957214
2023-01-21 10:08:02.645781: step: 1244/531, loss: 0.1555168330669403
2023-01-21 10:08:03.777656: step: 1248/531, loss: 0.05432291328907013
2023-01-21 10:08:04.930644: step: 1252/531, loss: 0.06665945053100586
2023-01-21 10:08:06.059227: step: 1256/531, loss: 0.3027457296848297
2023-01-21 10:08:07.179544: step: 1260/531, loss: 0.03419108688831329
2023-01-21 10:08:08.302654: step: 1264/531, loss: 0.03092327155172825
2023-01-21 10:08:09.426925: step: 1268/531, loss: 0.09152260422706604
2023-01-21 10:08:10.562141: step: 1272/531, loss: 0.05294923856854439
2023-01-21 10:08:11.682470: step: 1276/531, loss: 0.1418066918849945
2023-01-21 10:08:12.839038: step: 1280/531, loss: 0.045946039259433746
2023-01-21 10:08:13.956066: step: 1284/531, loss: 0.04810695722699165
2023-01-21 10:08:15.100763: step: 1288/531, loss: 0.09096412360668182
2023-01-21 10:08:16.204314: step: 1292/531, loss: 0.09424886852502823
2023-01-21 10:08:17.338225: step: 1296/531, loss: 0.1724928915500641
2023-01-21 10:08:18.505954: step: 1300/531, loss: 0.3312043249607086
2023-01-21 10:08:19.624997: step: 1304/531, loss: 0.10930080711841583
2023-01-21 10:08:20.762482: step: 1308/531, loss: 0.018151475116610527
2023-01-21 10:08:21.887460: step: 1312/531, loss: 0.23641586303710938
2023-01-21 10:08:23.003770: step: 1316/531, loss: 0.02094106748700142
2023-01-21 10:08:24.132392: step: 1320/531, loss: 0.07753334194421768
2023-01-21 10:08:25.272094: step: 1324/531, loss: 0.10565080493688583
2023-01-21 10:08:26.419822: step: 1328/531, loss: 0.1561090499162674
2023-01-21 10:08:27.535854: step: 1332/531, loss: 0.06907806545495987
2023-01-21 10:08:28.665353: step: 1336/531, loss: 0.14385661482810974
2023-01-21 10:08:29.806229: step: 1340/531, loss: 0.09367132186889648
2023-01-21 10:08:30.900157: step: 1344/531, loss: 0.06509292125701904
2023-01-21 10:08:32.000352: step: 1348/531, loss: 0.05485076829791069
2023-01-21 10:08:33.164395: step: 1352/531, loss: 0.2639181911945343
2023-01-21 10:08:34.295519: step: 1356/531, loss: 0.07145442813634872
2023-01-21 10:08:35.422829: step: 1360/531, loss: 0.06612322479486465
2023-01-21 10:08:36.548712: step: 1364/531, loss: 0.15043020248413086
2023-01-21 10:08:37.666247: step: 1368/531, loss: 0.468067467212677
2023-01-21 10:08:38.788468: step: 1372/531, loss: 0.04793062061071396
2023-01-21 10:08:39.898846: step: 1376/531, loss: 0.022897720336914062
2023-01-21 10:08:41.010234: step: 1380/531, loss: 0.061315443366765976
2023-01-21 10:08:42.152148: step: 1384/531, loss: 0.01979074440896511
2023-01-21 10:08:43.312003: step: 1388/531, loss: 0.0639532059431076
2023-01-21 10:08:44.455099: step: 1392/531, loss: 0.15867909789085388
2023-01-21 10:08:45.579160: step: 1396/531, loss: 0.11509492993354797
2023-01-21 10:08:46.743254: step: 1400/531, loss: 0.3212408125400543
2023-01-21 10:08:47.881433: step: 1404/531, loss: 0.19735059142112732
2023-01-21 10:08:49.012362: step: 1408/531, loss: 0.03058490715920925
2023-01-21 10:08:50.150498: step: 1412/531, loss: 0.08253774791955948
2023-01-21 10:08:51.288982: step: 1416/531, loss: 0.22068509459495544
2023-01-21 10:08:52.436532: step: 1420/531, loss: 0.06424064934253693
2023-01-21 10:08:53.547839: step: 1424/531, loss: 0.04112853854894638
2023-01-21 10:08:54.676397: step: 1428/531, loss: 0.12625522911548615
2023-01-21 10:08:55.833545: step: 1432/531, loss: 0.049492742866277695
2023-01-21 10:08:56.984273: step: 1436/531, loss: 0.09311608970165253
2023-01-21 10:08:58.116076: step: 1440/531, loss: 0.13868045806884766
2023-01-21 10:08:59.231414: step: 1444/531, loss: 0.0742088332772255
2023-01-21 10:09:00.372495: step: 1448/531, loss: 0.04856519773602486
2023-01-21 10:09:01.529267: step: 1452/531, loss: 0.02445363998413086
2023-01-21 10:09:02.661414: step: 1456/531, loss: 0.03946185111999512
2023-01-21 10:09:03.801796: step: 1460/531, loss: 0.13403233885765076
2023-01-21 10:09:04.927371: step: 1464/531, loss: 0.12843599915504456
2023-01-21 10:09:06.051453: step: 1468/531, loss: 0.13778942823410034
2023-01-21 10:09:07.185545: step: 1472/531, loss: 0.032407306134700775
2023-01-21 10:09:08.333013: step: 1476/531, loss: 0.016209697350859642
2023-01-21 10:09:09.477219: step: 1480/531, loss: 0.05104951933026314
2023-01-21 10:09:10.604808: step: 1484/531, loss: 0.04848307743668556
2023-01-21 10:09:11.745398: step: 1488/531, loss: 0.08278913795948029
2023-01-21 10:09:12.912417: step: 1492/531, loss: 0.11328534781932831
2023-01-21 10:09:14.026939: step: 1496/531, loss: 0.06588558852672577
2023-01-21 10:09:15.191171: step: 1500/531, loss: 0.12327533215284348
2023-01-21 10:09:16.324688: step: 1504/531, loss: 0.10412827134132385
2023-01-21 10:09:17.454272: step: 1508/531, loss: 0.04282745346426964
2023-01-21 10:09:18.555668: step: 1512/531, loss: 0.08965437859296799
2023-01-21 10:09:19.694642: step: 1516/531, loss: 0.05842337757349014
2023-01-21 10:09:20.816180: step: 1520/531, loss: 0.02496948279440403
2023-01-21 10:09:21.910394: step: 1524/531, loss: 0.04317150264978409
2023-01-21 10:09:23.035031: step: 1528/531, loss: 0.17738455533981323
2023-01-21 10:09:24.146154: step: 1532/531, loss: 0.0683690533041954
2023-01-21 10:09:25.265023: step: 1536/531, loss: 0.11062216758728027
2023-01-21 10:09:26.388808: step: 1540/531, loss: 0.06784573197364807
2023-01-21 10:09:27.509303: step: 1544/531, loss: 0.03943901136517525
2023-01-21 10:09:28.642960: step: 1548/531, loss: 0.10623788833618164
2023-01-21 10:09:29.782557: step: 1552/531, loss: 0.13369427621364594
2023-01-21 10:09:30.920045: step: 1556/531, loss: 0.12765559554100037
2023-01-21 10:09:32.064959: step: 1560/531, loss: 0.10928305983543396
2023-01-21 10:09:33.183347: step: 1564/531, loss: 0.08626241981983185
2023-01-21 10:09:34.362217: step: 1568/531, loss: 0.07066144794225693
2023-01-21 10:09:35.500452: step: 1572/531, loss: 0.15028266608715057
2023-01-21 10:09:36.639876: step: 1576/531, loss: 0.13189373910427094
2023-01-21 10:09:37.742601: step: 1580/531, loss: 0.040720224380493164
2023-01-21 10:09:38.900870: step: 1584/531, loss: 0.10490189492702484
2023-01-21 10:09:40.020480: step: 1588/531, loss: 0.11022691428661346
2023-01-21 10:09:41.150196: step: 1592/531, loss: 0.06727757304906845
2023-01-21 10:09:42.277806: step: 1596/531, loss: 0.21008263528347015
2023-01-21 10:09:43.414084: step: 1600/531, loss: 0.110480397939682
2023-01-21 10:09:44.536106: step: 1604/531, loss: 0.038848876953125
2023-01-21 10:09:45.691630: step: 1608/531, loss: 0.14333534240722656
2023-01-21 10:09:46.839196: step: 1612/531, loss: 0.012298773974180222
2023-01-21 10:09:47.967038: step: 1616/531, loss: 0.09040911495685577
2023-01-21 10:09:49.110812: step: 1620/531, loss: 0.36637288331985474
2023-01-21 10:09:50.217785: step: 1624/531, loss: 0.03619823604822159
2023-01-21 10:09:51.306513: step: 1628/531, loss: 0.12785176932811737
2023-01-21 10:09:52.481547: step: 1632/531, loss: 0.10669832676649094
2023-01-21 10:09:53.610462: step: 1636/531, loss: 0.017387963831424713
2023-01-21 10:09:54.740152: step: 1640/531, loss: 0.05115075409412384
2023-01-21 10:09:55.844607: step: 1644/531, loss: 0.025862883776426315
2023-01-21 10:09:56.988370: step: 1648/531, loss: 0.052378181368112564
2023-01-21 10:09:58.126103: step: 1652/531, loss: 0.10733203589916229
2023-01-21 10:09:59.260034: step: 1656/531, loss: 0.039488885551691055
2023-01-21 10:10:00.397228: step: 1660/531, loss: 0.23800000548362732
2023-01-21 10:10:01.532853: step: 1664/531, loss: 0.11620549857616425
2023-01-21 10:10:02.636510: step: 1668/531, loss: 0.04421696439385414
2023-01-21 10:10:03.775445: step: 1672/531, loss: 0.037122488021850586
2023-01-21 10:10:04.912461: step: 1676/531, loss: 0.157939612865448
2023-01-21 10:10:06.041496: step: 1680/531, loss: 0.13577966392040253
2023-01-21 10:10:07.178115: step: 1684/531, loss: 0.0504489429295063
2023-01-21 10:10:08.287174: step: 1688/531, loss: 0.07392968982458115
2023-01-21 10:10:09.405024: step: 1692/531, loss: 0.08688240498304367
2023-01-21 10:10:10.534389: step: 1696/531, loss: 0.0782146006822586
2023-01-21 10:10:11.619644: step: 1700/531, loss: 0.002805781550705433
2023-01-21 10:10:12.742399: step: 1704/531, loss: 0.05476422235369682
2023-01-21 10:10:13.861415: step: 1708/531, loss: 0.15776805579662323
2023-01-21 10:10:15.008671: step: 1712/531, loss: 0.06970424950122833
2023-01-21 10:10:16.134406: step: 1716/531, loss: 0.06293182820081711
2023-01-21 10:10:17.261456: step: 1720/531, loss: 0.11307448893785477
2023-01-21 10:10:18.370747: step: 1724/531, loss: 0.06442832946777344
2023-01-21 10:10:19.483116: step: 1728/531, loss: 0.13848206400871277
2023-01-21 10:10:20.597929: step: 1732/531, loss: 0.06902675330638885
2023-01-21 10:10:21.751441: step: 1736/531, loss: 0.0935390517115593
2023-01-21 10:10:22.885523: step: 1740/531, loss: 0.03362732008099556
2023-01-21 10:10:24.027867: step: 1744/531, loss: 0.07098159193992615
2023-01-21 10:10:25.143694: step: 1748/531, loss: 0.09417543560266495
2023-01-21 10:10:26.270391: step: 1752/531, loss: 0.09569878876209259
2023-01-21 10:10:27.407137: step: 1756/531, loss: 0.0673101395368576
2023-01-21 10:10:28.535114: step: 1760/531, loss: 0.04576165974140167
2023-01-21 10:10:29.654016: step: 1764/531, loss: 0.06733598560094833
2023-01-21 10:10:30.767244: step: 1768/531, loss: 0.10334434360265732
2023-01-21 10:10:31.883023: step: 1772/531, loss: 0.04893012344837189
2023-01-21 10:10:33.021380: step: 1776/531, loss: 0.4683903455734253
2023-01-21 10:10:34.204788: step: 1780/531, loss: 0.12383831292390823
2023-01-21 10:10:35.328110: step: 1784/531, loss: 0.1388513594865799
2023-01-21 10:10:36.466396: step: 1788/531, loss: 0.05231037363409996
2023-01-21 10:10:37.599550: step: 1792/531, loss: 0.25601157546043396
2023-01-21 10:10:38.735503: step: 1796/531, loss: 0.029924677684903145
2023-01-21 10:10:39.834546: step: 1800/531, loss: 0.05668769031763077
2023-01-21 10:10:40.951642: step: 1804/531, loss: 0.02938680723309517
2023-01-21 10:10:42.110694: step: 1808/531, loss: 0.07446356117725372
2023-01-21 10:10:43.254847: step: 1812/531, loss: 0.014715051278471947
2023-01-21 10:10:44.385966: step: 1816/531, loss: 0.1153407096862793
2023-01-21 10:10:45.540941: step: 1820/531, loss: 0.06602511554956436
2023-01-21 10:10:46.674621: step: 1824/531, loss: 0.1012735366821289
2023-01-21 10:10:47.843384: step: 1828/531, loss: 0.16131165623664856
2023-01-21 10:10:49.022232: step: 1832/531, loss: 0.21821995079517365
2023-01-21 10:10:50.149581: step: 1836/531, loss: 0.05337848886847496
2023-01-21 10:10:51.266561: step: 1840/531, loss: 0.03549156337976456
2023-01-21 10:10:52.389700: step: 1844/531, loss: 0.050888631492853165
2023-01-21 10:10:53.532003: step: 1848/531, loss: 0.13226155936717987
2023-01-21 10:10:54.677656: step: 1852/531, loss: 0.038954734802246094
2023-01-21 10:10:55.822149: step: 1856/531, loss: 0.10684119164943695
2023-01-21 10:10:56.985953: step: 1860/531, loss: 0.04459972679615021
2023-01-21 10:10:58.136455: step: 1864/531, loss: 0.026985742151737213
2023-01-21 10:10:59.246853: step: 1868/531, loss: 0.06536979228258133
2023-01-21 10:11:00.356724: step: 1872/531, loss: 0.0018253803718835115
2023-01-21 10:11:01.518462: step: 1876/531, loss: 0.18263044953346252
2023-01-21 10:11:02.627878: step: 1880/531, loss: 0.1416151076555252
2023-01-21 10:11:03.750359: step: 1884/531, loss: 0.16252461075782776
2023-01-21 10:11:04.856400: step: 1888/531, loss: 0.0649823397397995
2023-01-21 10:11:05.989935: step: 1892/531, loss: 1.1305994987487793
2023-01-21 10:11:07.163925: step: 1896/531, loss: 0.035987094044685364
2023-01-21 10:11:08.282344: step: 1900/531, loss: 0.4749086797237396
2023-01-21 10:11:09.408750: step: 1904/531, loss: 0.050026897341012955
2023-01-21 10:11:10.499935: step: 1908/531, loss: 0.03537178039550781
2023-01-21 10:11:11.643564: step: 1912/531, loss: 0.04737458378076553
2023-01-21 10:11:12.768237: step: 1916/531, loss: 0.13724027574062347
2023-01-21 10:11:13.910095: step: 1920/531, loss: 0.056358207017183304
2023-01-21 10:11:15.031556: step: 1924/531, loss: 0.05533742904663086
2023-01-21 10:11:16.150884: step: 1928/531, loss: 0.016994094476103783
2023-01-21 10:11:17.264992: step: 1932/531, loss: 0.06053461879491806
2023-01-21 10:11:18.398156: step: 1936/531, loss: 0.01579570770263672
2023-01-21 10:11:19.513892: step: 1940/531, loss: 0.004652261734008789
2023-01-21 10:11:20.623140: step: 1944/531, loss: 0.062317658215761185
2023-01-21 10:11:21.720243: step: 1948/531, loss: 0.16865481436252594
2023-01-21 10:11:22.847482: step: 1952/531, loss: 0.11037836223840714
2023-01-21 10:11:23.968902: step: 1956/531, loss: 0.09929104149341583
2023-01-21 10:11:25.084004: step: 1960/531, loss: 0.029140328988432884
2023-01-21 10:11:26.211560: step: 1964/531, loss: 0.47770261764526367
2023-01-21 10:11:27.335681: step: 1968/531, loss: 0.039046622812747955
2023-01-21 10:11:28.461987: step: 1972/531, loss: 0.05972623825073242
2023-01-21 10:11:29.613420: step: 1976/531, loss: 0.07596192508935928
2023-01-21 10:11:30.724887: step: 1980/531, loss: 0.04300356283783913
2023-01-21 10:11:31.845945: step: 1984/531, loss: 0.19802507758140564
2023-01-21 10:11:32.979084: step: 1988/531, loss: 0.3206310272216797
2023-01-21 10:11:34.130925: step: 1992/531, loss: 0.015581679530441761
2023-01-21 10:11:35.227587: step: 1996/531, loss: 0.13693447411060333
2023-01-21 10:11:36.351503: step: 2000/531, loss: 0.10448551177978516
2023-01-21 10:11:37.480033: step: 2004/531, loss: 0.03738908842206001
2023-01-21 10:11:38.588478: step: 2008/531, loss: 0.022568179294466972
2023-01-21 10:11:39.708240: step: 2012/531, loss: 0.071390300989151
2023-01-21 10:11:40.849803: step: 2016/531, loss: 0.1915409117937088
2023-01-21 10:11:41.994646: step: 2020/531, loss: 0.04772500693798065
2023-01-21 10:11:43.147413: step: 2024/531, loss: 0.19542759656906128
2023-01-21 10:11:44.259828: step: 2028/531, loss: 0.04015187919139862
2023-01-21 10:11:45.378979: step: 2032/531, loss: 0.017212580889463425
2023-01-21 10:11:46.537594: step: 2036/531, loss: 0.06971025466918945
2023-01-21 10:11:47.658664: step: 2040/531, loss: 0.03179655224084854
2023-01-21 10:11:48.784721: step: 2044/531, loss: 0.09848861396312714
2023-01-21 10:11:49.913587: step: 2048/531, loss: 0.05716719850897789
2023-01-21 10:11:51.066660: step: 2052/531, loss: 0.06620045006275177
2023-01-21 10:11:52.189400: step: 2056/531, loss: 0.12890753149986267
2023-01-21 10:11:53.319212: step: 2060/531, loss: 0.05382375419139862
2023-01-21 10:11:54.428531: step: 2064/531, loss: 0.33697694540023804
2023-01-21 10:11:55.562763: step: 2068/531, loss: 0.03177852928638458
2023-01-21 10:11:56.686252: step: 2072/531, loss: 0.024903679266572
2023-01-21 10:11:57.794495: step: 2076/531, loss: 0.09133139252662659
2023-01-21 10:11:58.914117: step: 2080/531, loss: 0.018282651901245117
2023-01-21 10:12:00.051726: step: 2084/531, loss: 0.0645199790596962
2023-01-21 10:12:01.171435: step: 2088/531, loss: 0.06097374111413956
2023-01-21 10:12:02.289750: step: 2092/531, loss: 0.011859512887895107
2023-01-21 10:12:03.396714: step: 2096/531, loss: 0.06787758320569992
2023-01-21 10:12:04.503703: step: 2100/531, loss: 0.07847819477319717
2023-01-21 10:12:05.627632: step: 2104/531, loss: 0.05095729976892471
2023-01-21 10:12:06.742548: step: 2108/531, loss: 0.10668793320655823
2023-01-21 10:12:07.846561: step: 2112/531, loss: 0.06331310421228409
2023-01-21 10:12:08.990701: step: 2116/531, loss: 0.10046424716711044
2023-01-21 10:12:10.140637: step: 2120/531, loss: 0.07530622184276581
2023-01-21 10:12:11.262794: step: 2124/531, loss: 0.14874349534511566
==================================================
Loss: 0.120
--------------------
Dev: {'event': {'p': 0.5725264169068204, 'r': 0.7936085219707057, 'f1': 0.6651785714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6113918236104732, 'r': 0.7936791890280263, 'f1': 0.6907109496626881}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.569620253164557, 'r': 0.8333333333333334, 'f1': 0.6766917293233082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.65625, 'r': 0.6666666666666666, 'f1': 0.6614173228346457}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.42857142857142855, 'r': 0.5833333333333334, 'f1': 0.49411764705882355}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5725264169068204, 'r': 0.7936085219707057, 'f1': 0.6651785714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6113918236104732, 'r': 0.7936791890280263, 'f1': 0.6907109496626881}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.65625, 'r': 0.6666666666666666, 'f1': 0.6614173228346457}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:12:57.761540: step: 4/531, loss: 0.21623441576957703
2023-01-21 10:12:58.873660: step: 8/531, loss: 0.020121287554502487
2023-01-21 10:12:59.989373: step: 12/531, loss: 0.08715877681970596
2023-01-21 10:13:01.114332: step: 16/531, loss: 0.026087380945682526
2023-01-21 10:13:02.221235: step: 20/531, loss: 0.051083993166685104
2023-01-21 10:13:03.377872: step: 24/531, loss: 0.028424646705389023
2023-01-21 10:13:04.530622: step: 28/531, loss: 0.008292818441987038
2023-01-21 10:13:05.674609: step: 32/531, loss: 0.04293462634086609
2023-01-21 10:13:06.777494: step: 36/531, loss: 0.05734968185424805
2023-01-21 10:13:07.885983: step: 40/531, loss: 0.026438143104314804
2023-01-21 10:13:09.009402: step: 44/531, loss: 0.04494807869195938
2023-01-21 10:13:10.161158: step: 48/531, loss: 0.18213118612766266
2023-01-21 10:13:11.263203: step: 52/531, loss: 0.04565410688519478
2023-01-21 10:13:12.393865: step: 56/531, loss: 0.05773639678955078
2023-01-21 10:13:13.521444: step: 60/531, loss: 0.052641965448856354
2023-01-21 10:13:14.637549: step: 64/531, loss: 0.0018669129349291325
2023-01-21 10:13:15.766852: step: 68/531, loss: 0.29329538345336914
2023-01-21 10:13:16.909117: step: 72/531, loss: 0.0014976500533521175
2023-01-21 10:13:18.017658: step: 76/531, loss: 0.013664532452821732
2023-01-21 10:13:19.151354: step: 80/531, loss: 0.07327013462781906
2023-01-21 10:13:20.282841: step: 84/531, loss: 0.07483325153589249
2023-01-21 10:13:21.474655: step: 88/531, loss: 0.08705577254295349
2023-01-21 10:13:22.599291: step: 92/531, loss: 0.018394364044070244
2023-01-21 10:13:23.709769: step: 96/531, loss: 0.03158698230981827
2023-01-21 10:13:24.822687: step: 100/531, loss: 0.1435195505619049
2023-01-21 10:13:25.946999: step: 104/531, loss: 0.03944563865661621
2023-01-21 10:13:27.086529: step: 108/531, loss: 0.3374462127685547
2023-01-21 10:13:28.199487: step: 112/531, loss: 0.3695562481880188
2023-01-21 10:13:29.346210: step: 116/531, loss: 0.029473688453435898
2023-01-21 10:13:30.481620: step: 120/531, loss: 0.09563598036766052
2023-01-21 10:13:31.607127: step: 124/531, loss: 0.07941122353076935
2023-01-21 10:13:32.754038: step: 128/531, loss: 0.34564247727394104
2023-01-21 10:13:33.913634: step: 132/531, loss: 0.07962484657764435
2023-01-21 10:13:35.018407: step: 136/531, loss: 0.006733751390129328
2023-01-21 10:13:36.178092: step: 140/531, loss: 0.0843932181596756
2023-01-21 10:13:37.311303: step: 144/531, loss: 0.056038569658994675
2023-01-21 10:13:38.419933: step: 148/531, loss: 0.012675905600190163
2023-01-21 10:13:39.578805: step: 152/531, loss: 0.039282940328121185
2023-01-21 10:13:40.690376: step: 156/531, loss: 0.02194995991885662
2023-01-21 10:13:41.804050: step: 160/531, loss: 0.08320216834545135
2023-01-21 10:13:42.912777: step: 164/531, loss: 0.04401605203747749
2023-01-21 10:13:44.053103: step: 168/531, loss: 0.0696466863155365
2023-01-21 10:13:45.182277: step: 172/531, loss: 0.03185214847326279
2023-01-21 10:13:46.313482: step: 176/531, loss: 0.02067866548895836
2023-01-21 10:13:47.472220: step: 180/531, loss: 0.05394601821899414
2023-01-21 10:13:48.635787: step: 184/531, loss: 0.04944973066449165
2023-01-21 10:13:49.786132: step: 188/531, loss: 0.06316594779491425
2023-01-21 10:13:50.921770: step: 192/531, loss: 0.3765878677368164
2023-01-21 10:13:52.060530: step: 196/531, loss: 0.009817123413085938
2023-01-21 10:13:53.221747: step: 200/531, loss: 0.09896345436573029
2023-01-21 10:13:54.351782: step: 204/531, loss: 0.33717355132102966
2023-01-21 10:13:55.495149: step: 208/531, loss: 0.06959133595228195
2023-01-21 10:13:56.612434: step: 212/531, loss: 0.08850102871656418
2023-01-21 10:13:57.715527: step: 216/531, loss: 0.016798116266727448
2023-01-21 10:13:58.867388: step: 220/531, loss: 0.04097968339920044
2023-01-21 10:13:59.989712: step: 224/531, loss: 0.13019585609436035
2023-01-21 10:14:01.119711: step: 228/531, loss: 0.05013582855463028
2023-01-21 10:14:02.223755: step: 232/531, loss: 0.2794569134712219
2023-01-21 10:14:03.376942: step: 236/531, loss: 0.029644489288330078
2023-01-21 10:14:04.499312: step: 240/531, loss: 0.07343072444200516
2023-01-21 10:14:05.609590: step: 244/531, loss: 0.0627521499991417
2023-01-21 10:14:06.743690: step: 248/531, loss: 0.010606097988784313
2023-01-21 10:14:07.860758: step: 252/531, loss: 0.048505548387765884
2023-01-21 10:14:08.963557: step: 256/531, loss: 0.07152329385280609
2023-01-21 10:14:10.101082: step: 260/531, loss: 0.058820534497499466
2023-01-21 10:14:11.231893: step: 264/531, loss: 0.0063720704056322575
2023-01-21 10:14:12.373046: step: 268/531, loss: 0.013552665710449219
2023-01-21 10:14:13.507859: step: 272/531, loss: 0.36703377962112427
2023-01-21 10:14:14.630765: step: 276/531, loss: 0.19733428955078125
2023-01-21 10:14:15.760479: step: 280/531, loss: 0.038312721997499466
2023-01-21 10:14:16.930218: step: 284/531, loss: 0.04330892488360405
2023-01-21 10:14:18.049124: step: 288/531, loss: 0.14655809104442596
2023-01-21 10:14:19.194392: step: 292/531, loss: 0.09843883663415909
2023-01-21 10:14:20.325384: step: 296/531, loss: 0.26909342408180237
2023-01-21 10:14:21.465968: step: 300/531, loss: 0.03592033311724663
2023-01-21 10:14:22.589014: step: 304/531, loss: 0.0702594742178917
2023-01-21 10:14:23.725043: step: 308/531, loss: 0.09555979073047638
2023-01-21 10:14:24.830369: step: 312/531, loss: 0.4399285316467285
2023-01-21 10:14:25.975550: step: 316/531, loss: 0.03937721252441406
2023-01-21 10:14:27.067502: step: 320/531, loss: 0.02788022719323635
2023-01-21 10:14:28.199939: step: 324/531, loss: 0.10528340190649033
2023-01-21 10:14:29.362447: step: 328/531, loss: 0.041455648839473724
2023-01-21 10:14:30.495346: step: 332/531, loss: 0.15865746140480042
2023-01-21 10:14:31.612251: step: 336/531, loss: 0.04110288619995117
2023-01-21 10:14:32.747356: step: 340/531, loss: 0.005844688508659601
2023-01-21 10:14:33.866761: step: 344/531, loss: 0.10154610127210617
2023-01-21 10:14:34.992717: step: 348/531, loss: 0.09441948682069778
2023-01-21 10:14:36.137731: step: 352/531, loss: 0.09893741458654404
2023-01-21 10:14:37.275168: step: 356/531, loss: 0.023644447326660156
2023-01-21 10:14:38.421530: step: 360/531, loss: 0.05272217094898224
2023-01-21 10:14:39.564954: step: 364/531, loss: 0.10865690559148788
2023-01-21 10:14:40.681939: step: 368/531, loss: 0.07566137611865997
2023-01-21 10:14:41.801718: step: 372/531, loss: 0.05899462848901749
2023-01-21 10:14:42.935853: step: 376/531, loss: 0.09528933465480804
2023-01-21 10:14:44.037707: step: 380/531, loss: 0.005741882137954235
2023-01-21 10:14:45.168360: step: 384/531, loss: 0.0318605899810791
2023-01-21 10:14:46.294385: step: 388/531, loss: 0.1636379212141037
2023-01-21 10:14:47.430666: step: 392/531, loss: 0.04427357017993927
2023-01-21 10:14:48.571162: step: 396/531, loss: 0.13655900955200195
2023-01-21 10:14:49.714784: step: 400/531, loss: 0.09229107201099396
2023-01-21 10:14:50.850371: step: 404/531, loss: 0.04023800045251846
2023-01-21 10:14:51.960520: step: 408/531, loss: 0.011039048433303833
2023-01-21 10:14:53.082599: step: 412/531, loss: 0.06464796513319016
2023-01-21 10:14:54.234924: step: 416/531, loss: 0.3171292841434479
2023-01-21 10:14:55.348993: step: 420/531, loss: 0.012929152697324753
2023-01-21 10:14:56.452874: step: 424/531, loss: 0.03202877193689346
2023-01-21 10:14:57.564373: step: 428/531, loss: 0.05081872642040253
2023-01-21 10:14:58.685732: step: 432/531, loss: 0.07394762337207794
2023-01-21 10:14:59.807631: step: 436/531, loss: 0.0629698783159256
2023-01-21 10:15:00.929687: step: 440/531, loss: 0.09848938137292862
2023-01-21 10:15:02.078981: step: 444/531, loss: 0.10481653362512589
2023-01-21 10:15:03.209263: step: 448/531, loss: 0.09322714805603027
2023-01-21 10:15:04.328773: step: 452/531, loss: 0.10081973671913147
2023-01-21 10:15:05.437005: step: 456/531, loss: 0.038343336433172226
2023-01-21 10:15:06.578885: step: 460/531, loss: 0.027730178087949753
2023-01-21 10:15:07.699832: step: 464/531, loss: 0.10366799682378769
2023-01-21 10:15:08.809061: step: 468/531, loss: 0.16739359498023987
2023-01-21 10:15:09.919067: step: 472/531, loss: 0.26914986968040466
2023-01-21 10:15:11.055255: step: 476/531, loss: 0.031618881970644
2023-01-21 10:15:12.204491: step: 480/531, loss: 0.022040940821170807
2023-01-21 10:15:13.322083: step: 484/531, loss: 0.07305736839771271
2023-01-21 10:15:14.468793: step: 488/531, loss: 0.6566334366798401
2023-01-21 10:15:15.588343: step: 492/531, loss: 0.14733240008354187
2023-01-21 10:15:16.693270: step: 496/531, loss: 0.03914584964513779
2023-01-21 10:15:17.831210: step: 500/531, loss: 0.0702170878648758
2023-01-21 10:15:18.937139: step: 504/531, loss: 0.11220322549343109
2023-01-21 10:15:20.085849: step: 508/531, loss: 0.06979923695325851
2023-01-21 10:15:21.207487: step: 512/531, loss: 0.05417288839817047
2023-01-21 10:15:22.318721: step: 516/531, loss: 0.03533516079187393
2023-01-21 10:15:23.453026: step: 520/531, loss: 0.03577156364917755
2023-01-21 10:15:24.572943: step: 524/531, loss: 0.13439102470874786
2023-01-21 10:15:25.690974: step: 528/531, loss: 0.06326007843017578
2023-01-21 10:15:26.815205: step: 532/531, loss: 0.023912906646728516
2023-01-21 10:15:27.942829: step: 536/531, loss: 0.05921498313546181
2023-01-21 10:15:29.101686: step: 540/531, loss: 0.018293287605047226
2023-01-21 10:15:30.212632: step: 544/531, loss: 0.012829208746552467
2023-01-21 10:15:31.337069: step: 548/531, loss: 0.3172028660774231
2023-01-21 10:15:32.490482: step: 552/531, loss: 0.004756164271384478
2023-01-21 10:15:33.634890: step: 556/531, loss: 0.01308374386280775
2023-01-21 10:15:34.758531: step: 560/531, loss: 0.046912387013435364
2023-01-21 10:15:35.921277: step: 564/531, loss: 0.005837440490722656
2023-01-21 10:15:37.073080: step: 568/531, loss: 0.02226100116968155
2023-01-21 10:15:38.208241: step: 572/531, loss: 0.007289028260856867
2023-01-21 10:15:39.346393: step: 576/531, loss: 0.0626005157828331
2023-01-21 10:15:40.472689: step: 580/531, loss: 0.11476173996925354
2023-01-21 10:15:41.580843: step: 584/531, loss: 0.021791744977235794
2023-01-21 10:15:42.706155: step: 588/531, loss: 0.0356481559574604
2023-01-21 10:15:43.814860: step: 592/531, loss: 0.06095151975750923
2023-01-21 10:15:44.932547: step: 596/531, loss: 0.14686232805252075
2023-01-21 10:15:46.067002: step: 600/531, loss: 0.10427875816822052
2023-01-21 10:15:47.217493: step: 604/531, loss: 0.005172777455300093
2023-01-21 10:15:48.349269: step: 608/531, loss: 0.0070788380689918995
2023-01-21 10:15:49.477750: step: 612/531, loss: 0.07341833412647247
2023-01-21 10:15:50.619982: step: 616/531, loss: 0.11404337733983994
2023-01-21 10:15:51.735368: step: 620/531, loss: 0.11168313026428223
2023-01-21 10:15:52.873493: step: 624/531, loss: 0.03533286973834038
2023-01-21 10:15:53.995152: step: 628/531, loss: 0.16926708817481995
2023-01-21 10:15:55.146832: step: 632/531, loss: 0.02252807654440403
2023-01-21 10:15:56.290975: step: 636/531, loss: 0.09222564101219177
2023-01-21 10:15:57.414305: step: 640/531, loss: 0.05632071569561958
2023-01-21 10:15:58.530258: step: 644/531, loss: 0.09267549216747284
2023-01-21 10:15:59.680637: step: 648/531, loss: 0.016103744506835938
2023-01-21 10:16:00.822216: step: 652/531, loss: 0.00413855304941535
2023-01-21 10:16:01.931020: step: 656/531, loss: 0.23023460805416107
2023-01-21 10:16:03.073609: step: 660/531, loss: 0.04975175857543945
2023-01-21 10:16:04.211184: step: 664/531, loss: 0.1383899748325348
2023-01-21 10:16:05.299719: step: 668/531, loss: 0.08326377719640732
2023-01-21 10:16:06.424800: step: 672/531, loss: 0.01661386527121067
2023-01-21 10:16:07.561137: step: 676/531, loss: 0.02125072479248047
2023-01-21 10:16:08.707721: step: 680/531, loss: 0.006105518434196711
2023-01-21 10:16:09.867636: step: 684/531, loss: 0.36228635907173157
2023-01-21 10:16:11.036384: step: 688/531, loss: 0.1943696141242981
2023-01-21 10:16:12.172185: step: 692/531, loss: 0.00706901540979743
2023-01-21 10:16:13.320503: step: 696/531, loss: 0.025682950392365456
2023-01-21 10:16:14.446460: step: 700/531, loss: 0.08898001164197922
2023-01-21 10:16:15.633501: step: 704/531, loss: 0.003070497652515769
2023-01-21 10:16:16.747548: step: 708/531, loss: 0.03321390226483345
2023-01-21 10:16:17.915786: step: 712/531, loss: 0.2003200650215149
2023-01-21 10:16:19.060699: step: 716/531, loss: 0.11334299296140671
2023-01-21 10:16:20.176657: step: 720/531, loss: 0.07198648899793625
2023-01-21 10:16:21.305252: step: 724/531, loss: 0.07582226395606995
2023-01-21 10:16:22.422952: step: 728/531, loss: 0.059401609003543854
2023-01-21 10:16:23.550569: step: 732/531, loss: 0.13553687930107117
2023-01-21 10:16:24.656047: step: 736/531, loss: 0.00605697650462389
2023-01-21 10:16:25.768526: step: 740/531, loss: 0.06719312816858292
2023-01-21 10:16:26.875985: step: 744/531, loss: 0.045046616345644
2023-01-21 10:16:27.994711: step: 748/531, loss: 0.1551249623298645
2023-01-21 10:16:29.136411: step: 752/531, loss: 0.051241420209407806
2023-01-21 10:16:30.257099: step: 756/531, loss: 0.03444976732134819
2023-01-21 10:16:31.387631: step: 760/531, loss: 0.005519390106201172
2023-01-21 10:16:32.514261: step: 764/531, loss: 0.5704889297485352
2023-01-21 10:16:33.625522: step: 768/531, loss: 0.02174239233136177
2023-01-21 10:16:34.749710: step: 772/531, loss: 0.0718604102730751
2023-01-21 10:16:35.860697: step: 776/531, loss: 0.10223827511072159
2023-01-21 10:16:36.985773: step: 780/531, loss: 0.07152089476585388
2023-01-21 10:16:38.107626: step: 784/531, loss: 0.17063112556934357
2023-01-21 10:16:39.223732: step: 788/531, loss: 0.03548021242022514
2023-01-21 10:16:40.365486: step: 792/531, loss: 0.0362551212310791
2023-01-21 10:16:41.498874: step: 796/531, loss: 0.01795806922018528
2023-01-21 10:16:42.626684: step: 800/531, loss: 0.06009354442358017
2023-01-21 10:16:43.749485: step: 804/531, loss: 0.5600084066390991
2023-01-21 10:16:44.866794: step: 808/531, loss: 0.05992145463824272
2023-01-21 10:16:45.975040: step: 812/531, loss: 0.11755962669849396
2023-01-21 10:16:47.083441: step: 816/531, loss: 0.2835141122341156
2023-01-21 10:16:48.178763: step: 820/531, loss: 0.0030007362365722656
2023-01-21 10:16:49.324510: step: 824/531, loss: 0.0632781982421875
2023-01-21 10:16:50.453161: step: 828/531, loss: 0.15143266320228577
2023-01-21 10:16:51.541337: step: 832/531, loss: 0.03235621377825737
2023-01-21 10:16:52.679791: step: 836/531, loss: 0.16603946685791016
2023-01-21 10:16:53.830464: step: 840/531, loss: 0.015852833166718483
2023-01-21 10:16:54.980318: step: 844/531, loss: 0.09591273963451385
2023-01-21 10:16:56.123911: step: 848/531, loss: 0.07614460587501526
2023-01-21 10:16:57.265587: step: 852/531, loss: 0.017177201807498932
2023-01-21 10:16:58.428529: step: 856/531, loss: 0.15117035806179047
2023-01-21 10:16:59.516345: step: 860/531, loss: 0.11116638779640198
2023-01-21 10:17:00.654485: step: 864/531, loss: 0.09981352090835571
2023-01-21 10:17:01.812404: step: 868/531, loss: 6.600597381591797
2023-01-21 10:17:02.955692: step: 872/531, loss: 0.23515033721923828
2023-01-21 10:17:04.079612: step: 876/531, loss: 0.04414348676800728
2023-01-21 10:17:05.230236: step: 880/531, loss: 0.21615906059741974
2023-01-21 10:17:06.342013: step: 884/531, loss: 0.01897592470049858
2023-01-21 10:17:07.496578: step: 888/531, loss: 0.06870318204164505
2023-01-21 10:17:08.598120: step: 892/531, loss: 0.12570691108703613
2023-01-21 10:17:09.701386: step: 896/531, loss: 0.010081482119858265
2023-01-21 10:17:10.805797: step: 900/531, loss: 0.009365749545395374
2023-01-21 10:17:11.940229: step: 904/531, loss: 0.0889807790517807
2023-01-21 10:17:13.109548: step: 908/531, loss: 0.3951340913772583
2023-01-21 10:17:14.252111: step: 912/531, loss: 0.2790369391441345
2023-01-21 10:17:15.362989: step: 916/531, loss: 0.023556184023618698
2023-01-21 10:17:16.488482: step: 920/531, loss: 0.08003024756908417
2023-01-21 10:17:17.610817: step: 924/531, loss: 0.018730737268924713
2023-01-21 10:17:18.716669: step: 928/531, loss: 0.04774751514196396
2023-01-21 10:17:19.819073: step: 932/531, loss: 0.10205135494470596
2023-01-21 10:17:20.967096: step: 936/531, loss: 0.7415167689323425
2023-01-21 10:17:22.066745: step: 940/531, loss: 0.06834926456212997
2023-01-21 10:17:23.213259: step: 944/531, loss: 0.12860898673534393
2023-01-21 10:17:24.321986: step: 948/531, loss: 0.47881144285202026
2023-01-21 10:17:25.424527: step: 952/531, loss: 0.09848156571388245
2023-01-21 10:17:26.568842: step: 956/531, loss: 0.06895532459020615
2023-01-21 10:17:27.721568: step: 960/531, loss: 0.04453601688146591
2023-01-21 10:17:28.858926: step: 964/531, loss: 0.013002299703657627
2023-01-21 10:17:30.012463: step: 968/531, loss: 0.06620798259973526
2023-01-21 10:17:31.137749: step: 972/531, loss: 0.03886881098151207
2023-01-21 10:17:32.293488: step: 976/531, loss: 0.021335698664188385
2023-01-21 10:17:33.418044: step: 980/531, loss: 0.0800880491733551
2023-01-21 10:17:34.555276: step: 984/531, loss: 0.08799200505018234
2023-01-21 10:17:35.659700: step: 988/531, loss: 0.38767823576927185
2023-01-21 10:17:36.789415: step: 992/531, loss: 0.04175548627972603
2023-01-21 10:17:37.883735: step: 996/531, loss: 0.023601436987519264
2023-01-21 10:17:38.989218: step: 1000/531, loss: 0.04929669201374054
2023-01-21 10:17:40.138433: step: 1004/531, loss: 0.11158613860607147
2023-01-21 10:17:41.264839: step: 1008/531, loss: 0.08201932907104492
2023-01-21 10:17:42.388838: step: 1012/531, loss: 0.18200074136257172
2023-01-21 10:17:43.546093: step: 1016/531, loss: 0.0829593688249588
2023-01-21 10:17:44.658913: step: 1020/531, loss: 0.017726518213748932
2023-01-21 10:17:45.783138: step: 1024/531, loss: 0.04975710064172745
2023-01-21 10:17:46.902056: step: 1028/531, loss: 0.07877931743860245
2023-01-21 10:17:48.022326: step: 1032/531, loss: 0.0431065559387207
2023-01-21 10:17:49.143741: step: 1036/531, loss: 0.05532970279455185
2023-01-21 10:17:50.287121: step: 1040/531, loss: 0.04636359214782715
2023-01-21 10:17:51.398834: step: 1044/531, loss: 0.09782705456018448
2023-01-21 10:17:52.496700: step: 1048/531, loss: 0.08972759544849396
2023-01-21 10:17:53.612026: step: 1052/531, loss: 0.07853545993566513
2023-01-21 10:17:54.748160: step: 1056/531, loss: 0.12326722592115402
2023-01-21 10:17:55.889061: step: 1060/531, loss: 0.023280715569853783
2023-01-21 10:17:57.010415: step: 1064/531, loss: 0.04248838499188423
2023-01-21 10:17:58.140330: step: 1068/531, loss: 0.0165773406624794
2023-01-21 10:17:59.239427: step: 1072/531, loss: 0.011294294148683548
2023-01-21 10:18:00.375108: step: 1076/531, loss: 0.17084245383739471
2023-01-21 10:18:01.503369: step: 1080/531, loss: 0.09570303559303284
2023-01-21 10:18:02.608579: step: 1084/531, loss: 0.014852046966552734
2023-01-21 10:18:03.742485: step: 1088/531, loss: 0.022930670529603958
2023-01-21 10:18:04.879259: step: 1092/531, loss: 0.16185075044631958
2023-01-21 10:18:06.019125: step: 1096/531, loss: 0.1440170258283615
2023-01-21 10:18:07.152765: step: 1100/531, loss: 0.03081207349896431
2023-01-21 10:18:08.289473: step: 1104/531, loss: 0.06661882251501083
2023-01-21 10:18:09.398370: step: 1108/531, loss: 0.011142825707793236
2023-01-21 10:18:10.519839: step: 1112/531, loss: 0.054775189608335495
2023-01-21 10:18:11.636869: step: 1116/531, loss: 0.037755679339170456
2023-01-21 10:18:12.746041: step: 1120/531, loss: 0.035413362085819244
2023-01-21 10:18:13.858011: step: 1124/531, loss: 0.028282545506954193
2023-01-21 10:18:14.970899: step: 1128/531, loss: 0.361624538898468
2023-01-21 10:18:16.093675: step: 1132/531, loss: 0.16452975571155548
2023-01-21 10:18:17.202899: step: 1136/531, loss: 0.058150291442871094
2023-01-21 10:18:18.305125: step: 1140/531, loss: 0.1460392028093338
2023-01-21 10:18:19.416887: step: 1144/531, loss: 0.015816306695342064
2023-01-21 10:18:20.540363: step: 1148/531, loss: 0.08659800887107849
2023-01-21 10:18:21.672997: step: 1152/531, loss: 0.16230088472366333
2023-01-21 10:18:22.808644: step: 1156/531, loss: 0.007613944821059704
2023-01-21 10:18:23.957959: step: 1160/531, loss: 0.06964094936847687
2023-01-21 10:18:25.086325: step: 1164/531, loss: 0.1682472825050354
2023-01-21 10:18:26.220340: step: 1168/531, loss: 0.013976383954286575
2023-01-21 10:18:27.351494: step: 1172/531, loss: 0.014623391442000866
2023-01-21 10:18:28.473307: step: 1176/531, loss: 0.08265195041894913
2023-01-21 10:18:29.594711: step: 1180/531, loss: 0.391972154378891
2023-01-21 10:18:30.724201: step: 1184/531, loss: 0.1276385337114334
2023-01-21 10:18:31.841575: step: 1188/531, loss: 0.5758189558982849
2023-01-21 10:18:32.958863: step: 1192/531, loss: 0.011744881048798561
2023-01-21 10:18:34.112667: step: 1196/531, loss: 0.010767650790512562
2023-01-21 10:18:35.243040: step: 1200/531, loss: 0.062334444373846054
2023-01-21 10:18:36.376259: step: 1204/531, loss: 0.21208438277244568
2023-01-21 10:18:37.517212: step: 1208/531, loss: 0.06007290259003639
2023-01-21 10:18:38.640838: step: 1212/531, loss: 0.05585651472210884
2023-01-21 10:18:39.767095: step: 1216/531, loss: 0.05054893344640732
2023-01-21 10:18:40.892934: step: 1220/531, loss: 0.08229760825634003
2023-01-21 10:18:42.005886: step: 1224/531, loss: 0.012652969919145107
2023-01-21 10:18:43.161916: step: 1228/531, loss: 0.041400909423828125
2023-01-21 10:18:44.293309: step: 1232/531, loss: 0.08686723560094833
2023-01-21 10:18:45.428928: step: 1236/531, loss: 0.03182416036725044
2023-01-21 10:18:46.575801: step: 1240/531, loss: 0.12221205234527588
2023-01-21 10:18:47.735675: step: 1244/531, loss: 0.011512613855302334
2023-01-21 10:18:48.869478: step: 1248/531, loss: 0.00769419688731432
2023-01-21 10:18:49.977138: step: 1252/531, loss: 0.04380970075726509
2023-01-21 10:18:51.130563: step: 1256/531, loss: 0.10821003466844559
2023-01-21 10:18:52.270918: step: 1260/531, loss: 0.09529123455286026
2023-01-21 10:18:53.373736: step: 1264/531, loss: 0.0686555877327919
2023-01-21 10:18:54.472208: step: 1268/531, loss: 0.016816092655062675
2023-01-21 10:18:55.601653: step: 1272/531, loss: 0.005986523814499378
2023-01-21 10:18:56.747003: step: 1276/531, loss: 0.49938222765922546
2023-01-21 10:18:57.870117: step: 1280/531, loss: 0.05700397491455078
2023-01-21 10:18:59.027105: step: 1284/531, loss: 0.09781436622142792
2023-01-21 10:19:00.164573: step: 1288/531, loss: 0.19268473982810974
2023-01-21 10:19:01.281324: step: 1292/531, loss: 0.158880814909935
2023-01-21 10:19:02.400266: step: 1296/531, loss: 0.17393112182617188
2023-01-21 10:19:03.532687: step: 1300/531, loss: 0.17259693145751953
2023-01-21 10:19:04.706216: step: 1304/531, loss: 0.0538850761950016
2023-01-21 10:19:05.822020: step: 1308/531, loss: 0.05626258626580238
2023-01-21 10:19:06.943351: step: 1312/531, loss: 0.07283325493335724
2023-01-21 10:19:08.058334: step: 1316/531, loss: 0.261345773935318
2023-01-21 10:19:09.208359: step: 1320/531, loss: 0.023939799517393112
2023-01-21 10:19:10.313919: step: 1324/531, loss: 0.07654476165771484
2023-01-21 10:19:11.436362: step: 1328/531, loss: 0.032021380960941315
2023-01-21 10:19:12.576972: step: 1332/531, loss: 0.04924974590539932
2023-01-21 10:19:13.683848: step: 1336/531, loss: 0.33833616971969604
2023-01-21 10:19:14.773252: step: 1340/531, loss: 0.11932249367237091
2023-01-21 10:19:15.871927: step: 1344/531, loss: 0.043663978576660156
2023-01-21 10:19:16.992308: step: 1348/531, loss: 0.08932981640100479
2023-01-21 10:19:18.105293: step: 1352/531, loss: 0.07595663517713547
2023-01-21 10:19:19.244821: step: 1356/531, loss: 0.1263381689786911
2023-01-21 10:19:20.361456: step: 1360/531, loss: 0.1303871124982834
2023-01-21 10:19:21.474551: step: 1364/531, loss: 0.4046003222465515
2023-01-21 10:19:22.615937: step: 1368/531, loss: 0.07024087756872177
2023-01-21 10:19:23.749389: step: 1372/531, loss: 0.04590454325079918
2023-01-21 10:19:24.871562: step: 1376/531, loss: 0.05047474056482315
2023-01-21 10:19:26.001254: step: 1380/531, loss: 0.062482595443725586
2023-01-21 10:19:27.155560: step: 1384/531, loss: 0.08354830741882324
2023-01-21 10:19:28.256639: step: 1388/531, loss: 0.04470429569482803
2023-01-21 10:19:29.363988: step: 1392/531, loss: 0.016810130327939987
2023-01-21 10:19:30.494579: step: 1396/531, loss: 0.05169057846069336
2023-01-21 10:19:31.603999: step: 1400/531, loss: 0.058431342244148254
2023-01-21 10:19:32.724335: step: 1404/531, loss: 0.06417732685804367
2023-01-21 10:19:33.862957: step: 1408/531, loss: 0.005791378207504749
2023-01-21 10:19:35.008329: step: 1412/531, loss: 0.050724029541015625
2023-01-21 10:19:36.114699: step: 1416/531, loss: 0.100092314183712
2023-01-21 10:19:37.263543: step: 1420/531, loss: 0.05062408745288849
2023-01-21 10:19:38.359890: step: 1424/531, loss: 0.033126164227724075
2023-01-21 10:19:39.524237: step: 1428/531, loss: 0.0731164962053299
2023-01-21 10:19:40.657816: step: 1432/531, loss: 0.047882940620183945
2023-01-21 10:19:41.773719: step: 1436/531, loss: 0.05545955151319504
2023-01-21 10:19:42.917130: step: 1440/531, loss: 0.04085004702210426
2023-01-21 10:19:44.070854: step: 1444/531, loss: 0.10405702888965607
2023-01-21 10:19:45.222349: step: 1448/531, loss: 0.09285449981689453
2023-01-21 10:19:46.328541: step: 1452/531, loss: 0.041260432451963425
2023-01-21 10:19:47.456210: step: 1456/531, loss: 0.01364598236978054
2023-01-21 10:19:48.582376: step: 1460/531, loss: 0.027989627793431282
2023-01-21 10:19:49.717193: step: 1464/531, loss: 0.07774285972118378
2023-01-21 10:19:50.842471: step: 1468/531, loss: 0.02292471006512642
2023-01-21 10:19:51.980208: step: 1472/531, loss: 0.17965182662010193
2023-01-21 10:19:53.098123: step: 1476/531, loss: 0.08426199108362198
2023-01-21 10:19:54.202028: step: 1480/531, loss: 0.0807638168334961
2023-01-21 10:19:55.329596: step: 1484/531, loss: 0.10578146576881409
2023-01-21 10:19:56.457492: step: 1488/531, loss: 0.12574782967567444
2023-01-21 10:19:57.567045: step: 1492/531, loss: 0.026172496378421783
2023-01-21 10:19:58.698492: step: 1496/531, loss: 0.1960858404636383
2023-01-21 10:19:59.827679: step: 1500/531, loss: 0.0625336617231369
2023-01-21 10:20:00.964859: step: 1504/531, loss: 0.03143353760242462
2023-01-21 10:20:02.104434: step: 1508/531, loss: 0.1215442568063736
2023-01-21 10:20:03.218983: step: 1512/531, loss: 0.2620088458061218
2023-01-21 10:20:04.351329: step: 1516/531, loss: 0.08306656032800674
2023-01-21 10:20:05.484475: step: 1520/531, loss: 0.0044418335892260075
2023-01-21 10:20:06.612426: step: 1524/531, loss: 0.026612281799316406
2023-01-21 10:20:07.738947: step: 1528/531, loss: 0.10181407630443573
2023-01-21 10:20:08.864491: step: 1532/531, loss: 0.09413104504346848
2023-01-21 10:20:10.008076: step: 1536/531, loss: 0.03781495243310928
2023-01-21 10:20:11.128627: step: 1540/531, loss: 0.003916787914931774
2023-01-21 10:20:12.243639: step: 1544/531, loss: 0.1770172119140625
2023-01-21 10:20:13.355146: step: 1548/531, loss: 0.006284570321440697
2023-01-21 10:20:14.509738: step: 1552/531, loss: 0.08632194995880127
2023-01-21 10:20:15.646839: step: 1556/531, loss: 0.022620487958192825
2023-01-21 10:20:16.789775: step: 1560/531, loss: 0.04532375559210777
2023-01-21 10:20:17.973208: step: 1564/531, loss: 0.04324665293097496
2023-01-21 10:20:19.157309: step: 1568/531, loss: 0.016980551183223724
2023-01-21 10:20:20.289711: step: 1572/531, loss: 0.06600189208984375
2023-01-21 10:20:21.402554: step: 1576/531, loss: 0.12555399537086487
2023-01-21 10:20:22.506846: step: 1580/531, loss: 0.14547604322433472
2023-01-21 10:20:23.620791: step: 1584/531, loss: 0.08104319870471954
2023-01-21 10:20:24.723939: step: 1588/531, loss: 0.047277260571718216
2023-01-21 10:20:25.826908: step: 1592/531, loss: 0.02387695387005806
2023-01-21 10:20:26.991217: step: 1596/531, loss: 0.0806453749537468
2023-01-21 10:20:28.145774: step: 1600/531, loss: 0.04324378818273544
2023-01-21 10:20:29.262522: step: 1604/531, loss: 0.0976925790309906
2023-01-21 10:20:30.356965: step: 1608/531, loss: 0.003158140229061246
2023-01-21 10:20:31.472172: step: 1612/531, loss: 0.051337577402591705
2023-01-21 10:20:32.599457: step: 1616/531, loss: 0.24263755977153778
2023-01-21 10:20:33.733746: step: 1620/531, loss: 0.05816173925995827
2023-01-21 10:20:34.846741: step: 1624/531, loss: 0.04355583339929581
2023-01-21 10:20:35.969806: step: 1628/531, loss: 0.14264144003391266
2023-01-21 10:20:37.093416: step: 1632/531, loss: 0.06893301010131836
2023-01-21 10:20:38.217350: step: 1636/531, loss: 0.013486465439200401
2023-01-21 10:20:39.325706: step: 1640/531, loss: 0.19555817544460297
2023-01-21 10:20:40.456475: step: 1644/531, loss: 0.03461914137005806
2023-01-21 10:20:41.571510: step: 1648/531, loss: 0.0044204238802194595
2023-01-21 10:20:42.736257: step: 1652/531, loss: 0.01669464074075222
2023-01-21 10:20:43.886577: step: 1656/531, loss: 0.038656093180179596
2023-01-21 10:20:45.054449: step: 1660/531, loss: 0.04943694919347763
2023-01-21 10:20:46.157540: step: 1664/531, loss: 0.05698385462164879
2023-01-21 10:20:47.290966: step: 1668/531, loss: 0.05592689663171768
2023-01-21 10:20:48.429765: step: 1672/531, loss: 0.05145673453807831
2023-01-21 10:20:49.561708: step: 1676/531, loss: 0.044964030385017395
2023-01-21 10:20:50.655418: step: 1680/531, loss: 0.04249439388513565
2023-01-21 10:20:51.775910: step: 1684/531, loss: 0.17572708427906036
2023-01-21 10:20:52.873764: step: 1688/531, loss: 0.041205596178770065
2023-01-21 10:20:53.996277: step: 1692/531, loss: 0.1240943968296051
2023-01-21 10:20:55.127452: step: 1696/531, loss: 0.5286551117897034
2023-01-21 10:20:56.231856: step: 1700/531, loss: 0.011068916879594326
2023-01-21 10:20:57.390119: step: 1704/531, loss: 0.126966655254364
2023-01-21 10:20:58.535103: step: 1708/531, loss: 0.06042356789112091
2023-01-21 10:20:59.633771: step: 1712/531, loss: 0.08028201758861542
2023-01-21 10:21:00.734044: step: 1716/531, loss: 0.019240237772464752
2023-01-21 10:21:01.855752: step: 1720/531, loss: 0.058541107922792435
2023-01-21 10:21:02.978989: step: 1724/531, loss: 0.388589084148407
2023-01-21 10:21:04.104070: step: 1728/531, loss: 0.016455747187137604
2023-01-21 10:21:05.234053: step: 1732/531, loss: 0.11167659610509872
2023-01-21 10:21:06.370848: step: 1736/531, loss: 0.19166278839111328
2023-01-21 10:21:07.545932: step: 1740/531, loss: 0.07711277157068253
2023-01-21 10:21:08.679104: step: 1744/531, loss: 0.06050138175487518
2023-01-21 10:21:09.864429: step: 1748/531, loss: 0.010099506005644798
2023-01-21 10:21:10.984318: step: 1752/531, loss: 0.7771268486976624
2023-01-21 10:21:12.126025: step: 1756/531, loss: 0.08279304206371307
2023-01-21 10:21:13.232294: step: 1760/531, loss: 0.038699328899383545
2023-01-21 10:21:14.348193: step: 1764/531, loss: 0.028452303260564804
2023-01-21 10:21:15.501640: step: 1768/531, loss: 0.0399787463247776
2023-01-21 10:21:16.612708: step: 1772/531, loss: 0.11855180561542511
2023-01-21 10:21:17.752168: step: 1776/531, loss: 0.05953254923224449
2023-01-21 10:21:18.860555: step: 1780/531, loss: 0.03719845041632652
2023-01-21 10:21:19.978701: step: 1784/531, loss: 0.08078131824731827
2023-01-21 10:21:21.125882: step: 1788/531, loss: 0.05043911933898926
2023-01-21 10:21:22.225804: step: 1792/531, loss: 0.09735693782567978
2023-01-21 10:21:23.342192: step: 1796/531, loss: 0.12132323533296585
2023-01-21 10:21:24.459263: step: 1800/531, loss: 0.08893604576587677
2023-01-21 10:21:25.559792: step: 1804/531, loss: 0.05169811472296715
2023-01-21 10:21:26.669200: step: 1808/531, loss: 0.11936827003955841
2023-01-21 10:21:27.821398: step: 1812/531, loss: 0.032808687537908554
2023-01-21 10:21:28.929795: step: 1816/531, loss: 0.002257442567497492
2023-01-21 10:21:30.041568: step: 1820/531, loss: 0.041516877710819244
2023-01-21 10:21:31.141195: step: 1824/531, loss: 0.08992882072925568
2023-01-21 10:21:32.272557: step: 1828/531, loss: 0.04004926607012749
2023-01-21 10:21:33.425867: step: 1832/531, loss: 0.15225887298583984
2023-01-21 10:21:34.586882: step: 1836/531, loss: 0.05785880237817764
2023-01-21 10:21:35.734266: step: 1840/531, loss: 0.03980877250432968
2023-01-21 10:21:36.926927: step: 1844/531, loss: 1.4729385375976562
2023-01-21 10:21:38.098899: step: 1848/531, loss: 0.11329560726881027
2023-01-21 10:21:39.227835: step: 1852/531, loss: 0.030247116461396217
2023-01-21 10:21:40.371961: step: 1856/531, loss: 0.061458565294742584
2023-01-21 10:21:41.496698: step: 1860/531, loss: 0.05626792833209038
2023-01-21 10:21:42.625484: step: 1864/531, loss: 0.04756994545459747
2023-01-21 10:21:43.743850: step: 1868/531, loss: 0.13331520557403564
2023-01-21 10:21:44.892712: step: 1872/531, loss: 0.022486496716737747
2023-01-21 10:21:46.038104: step: 1876/531, loss: 0.017060469835996628
2023-01-21 10:21:47.206860: step: 1880/531, loss: 0.0424840934574604
2023-01-21 10:21:48.313813: step: 1884/531, loss: 0.050362586975097656
2023-01-21 10:21:49.431694: step: 1888/531, loss: 0.14166298508644104
2023-01-21 10:21:50.580186: step: 1892/531, loss: 0.033858489245176315
2023-01-21 10:21:51.711446: step: 1896/531, loss: 0.10135313868522644
2023-01-21 10:21:52.857018: step: 1900/531, loss: 0.08659668266773224
2023-01-21 10:21:53.992572: step: 1904/531, loss: 0.036715030670166016
2023-01-21 10:21:55.133829: step: 1908/531, loss: 0.110712431371212
2023-01-21 10:21:56.239934: step: 1912/531, loss: 0.027908803895115852
2023-01-21 10:21:57.367756: step: 1916/531, loss: 0.035930585116147995
2023-01-21 10:21:58.481372: step: 1920/531, loss: 0.08405759930610657
2023-01-21 10:21:59.594771: step: 1924/531, loss: 0.026928137987852097
2023-01-21 10:22:00.727483: step: 1928/531, loss: 0.15556088089942932
2023-01-21 10:22:01.892877: step: 1932/531, loss: 0.11883096396923065
2023-01-21 10:22:03.026278: step: 1936/531, loss: 0.1011347770690918
2023-01-21 10:22:04.183265: step: 1940/531, loss: 0.12977942824363708
2023-01-21 10:22:05.314913: step: 1944/531, loss: 0.04790253937244415
2023-01-21 10:22:06.478313: step: 1948/531, loss: 0.05401799827814102
2023-01-21 10:22:07.627427: step: 1952/531, loss: 0.02795390971004963
2023-01-21 10:22:08.735897: step: 1956/531, loss: 0.1771896332502365
2023-01-21 10:22:09.845649: step: 1960/531, loss: 0.08870792388916016
2023-01-21 10:22:10.959327: step: 1964/531, loss: 0.3486073315143585
2023-01-21 10:22:12.135177: step: 1968/531, loss: 0.07131248712539673
2023-01-21 10:22:13.284632: step: 1972/531, loss: 0.03205299377441406
2023-01-21 10:22:14.408495: step: 1976/531, loss: 0.13303136825561523
2023-01-21 10:22:15.559901: step: 1980/531, loss: 0.10535793751478195
2023-01-21 10:22:16.727464: step: 1984/531, loss: 0.024078847840428352
2023-01-21 10:22:17.856111: step: 1988/531, loss: 1.4425712823867798
2023-01-21 10:22:18.975285: step: 1992/531, loss: 1.1072731018066406
2023-01-21 10:22:20.134235: step: 1996/531, loss: 0.03151216730475426
2023-01-21 10:22:21.294667: step: 2000/531, loss: 0.04063913971185684
2023-01-21 10:22:22.400648: step: 2004/531, loss: 0.028385544195771217
2023-01-21 10:22:23.528859: step: 2008/531, loss: 0.0454859733581543
2023-01-21 10:22:24.656978: step: 2012/531, loss: 0.08616266399621964
2023-01-21 10:22:25.793146: step: 2016/531, loss: 0.0756472572684288
2023-01-21 10:22:26.950363: step: 2020/531, loss: 0.1179908812046051
2023-01-21 10:22:28.130582: step: 2024/531, loss: 0.03920431062579155
2023-01-21 10:22:29.272977: step: 2028/531, loss: 0.11259995400905609
2023-01-21 10:22:30.444170: step: 2032/531, loss: 0.07037858664989471
2023-01-21 10:22:31.594870: step: 2036/531, loss: 0.02563338354229927
2023-01-21 10:22:32.745580: step: 2040/531, loss: 0.029477596282958984
2023-01-21 10:22:33.882402: step: 2044/531, loss: 0.134347602725029
2023-01-21 10:22:35.028875: step: 2048/531, loss: 0.28497275710105896
2023-01-21 10:22:36.179214: step: 2052/531, loss: 0.06466750800609589
2023-01-21 10:22:37.371474: step: 2056/531, loss: 0.04205689579248428
2023-01-21 10:22:38.504487: step: 2060/531, loss: 0.08378100395202637
2023-01-21 10:22:39.671475: step: 2064/531, loss: 0.1108739897608757
2023-01-21 10:22:40.844381: step: 2068/531, loss: 0.035460758954286575
2023-01-21 10:22:41.996127: step: 2072/531, loss: 0.06382570415735245
2023-01-21 10:22:43.166689: step: 2076/531, loss: 0.036687564104795456
2023-01-21 10:22:44.297128: step: 2080/531, loss: 0.05562110245227814
2023-01-21 10:22:45.462009: step: 2084/531, loss: 0.0508517287671566
2023-01-21 10:22:46.614188: step: 2088/531, loss: 0.021392060443758965
2023-01-21 10:22:47.735436: step: 2092/531, loss: 0.039246369153261185
2023-01-21 10:22:48.878652: step: 2096/531, loss: 0.10869696736335754
2023-01-21 10:22:50.023279: step: 2100/531, loss: 0.05337419733405113
2023-01-21 10:22:51.142486: step: 2104/531, loss: 0.0476841926574707
2023-01-21 10:22:52.291773: step: 2108/531, loss: 0.058841705322265625
2023-01-21 10:22:53.439778: step: 2112/531, loss: 0.08721671253442764
2023-01-21 10:22:54.573250: step: 2116/531, loss: 0.014968396164476871
2023-01-21 10:22:55.703904: step: 2120/531, loss: 0.06654996424913406
2023-01-21 10:22:56.850770: step: 2124/531, loss: 0.062440112233161926
==================================================
Loss: 0.110
--------------------
Dev: {'event': {'p': 0.5704500978473581, 'r': 0.7762982689747004, 'f1': 0.6576424139875917}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.61090573012939, 'r': 0.7883124627310674, 'f1': 0.6883624056235356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5632183908045977, 'r': 0.9074074074074074, 'f1': 0.6950354609929078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6481481481481481, 'r': 0.5555555555555556, 'f1': 0.5982905982905983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.4782608695652174, 'r': 0.6111111111111112, 'f1': 0.5365853658536586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5725264169068204, 'r': 0.7936085219707057, 'f1': 0.6651785714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6113918236104732, 'r': 0.7936791890280263, 'f1': 0.6907109496626881}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.65625, 'r': 0.6666666666666666, 'f1': 0.6614173228346457}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:23:39.384234: step: 4/531, loss: 0.18987540900707245
2023-01-21 10:23:40.501184: step: 8/531, loss: 0.0072501180693507195
2023-01-21 10:23:41.699693: step: 12/531, loss: 0.037050630897283554
2023-01-21 10:23:42.838493: step: 16/531, loss: 0.03488335758447647
2023-01-21 10:23:43.975532: step: 20/531, loss: 0.057396698743104935
2023-01-21 10:23:45.139361: step: 24/531, loss: 0.10559973865747452
2023-01-21 10:23:46.318260: step: 28/531, loss: 0.3329788148403168
2023-01-21 10:23:47.464853: step: 32/531, loss: 0.026273632422089577
2023-01-21 10:23:48.607237: step: 36/531, loss: 0.0021824599243700504
2023-01-21 10:23:49.748245: step: 40/531, loss: 0.07027044892311096
2023-01-21 10:23:50.884460: step: 44/531, loss: 0.04060091823339462
2023-01-21 10:23:52.014558: step: 48/531, loss: 0.004965400323271751
2023-01-21 10:23:53.151646: step: 52/531, loss: 0.21512404084205627
2023-01-21 10:23:54.306843: step: 56/531, loss: 0.18710888922214508
2023-01-21 10:23:55.439428: step: 60/531, loss: 0.005432033445686102
2023-01-21 10:23:56.560345: step: 64/531, loss: 0.02842388115823269
2023-01-21 10:23:57.730866: step: 68/531, loss: 0.0749642625451088
2023-01-21 10:23:58.864817: step: 72/531, loss: 0.018126148730516434
2023-01-21 10:24:00.003939: step: 76/531, loss: 0.003795528318732977
2023-01-21 10:24:01.145716: step: 80/531, loss: 0.06516571342945099
2023-01-21 10:24:02.286913: step: 84/531, loss: 0.02129889652132988
2023-01-21 10:24:03.423856: step: 88/531, loss: 0.03553161770105362
2023-01-21 10:24:04.567773: step: 92/531, loss: 1.1856123208999634
2023-01-21 10:24:05.723829: step: 96/531, loss: 0.34031039476394653
2023-01-21 10:24:06.874130: step: 100/531, loss: 0.014528656378388405
2023-01-21 10:24:07.990275: step: 104/531, loss: 0.05841522291302681
2023-01-21 10:24:09.157027: step: 108/531, loss: 0.061768725514411926
2023-01-21 10:24:10.298690: step: 112/531, loss: 0.003407597541809082
2023-01-21 10:24:11.392086: step: 116/531, loss: 0.0662296861410141
2023-01-21 10:24:12.569049: step: 120/531, loss: 0.014042950235307217
2023-01-21 10:24:13.759958: step: 124/531, loss: 0.020859479904174805
2023-01-21 10:24:14.921302: step: 128/531, loss: 0.01929612271487713
2023-01-21 10:24:16.063644: step: 132/531, loss: 0.05305957794189453
2023-01-21 10:24:17.229061: step: 136/531, loss: 0.04234256595373154
2023-01-21 10:24:18.385754: step: 140/531, loss: 0.019442368298768997
2023-01-21 10:24:19.516520: step: 144/531, loss: 0.016852760687470436
2023-01-21 10:24:20.665569: step: 148/531, loss: 0.01007623691111803
2023-01-21 10:24:21.804763: step: 152/531, loss: 0.05290966108441353
2023-01-21 10:24:22.970222: step: 156/531, loss: 0.3353423476219177
2023-01-21 10:24:24.103263: step: 160/531, loss: 0.021361876279115677
2023-01-21 10:24:25.315691: step: 164/531, loss: 0.354099839925766
2023-01-21 10:24:26.460501: step: 168/531, loss: 0.023737479001283646
2023-01-21 10:24:27.604867: step: 172/531, loss: 0.03588595613837242
2023-01-21 10:24:28.767277: step: 176/531, loss: 0.12529344856739044
2023-01-21 10:24:29.966193: step: 180/531, loss: 0.02104330062866211
2023-01-21 10:24:31.137045: step: 184/531, loss: 0.011593818664550781
2023-01-21 10:24:32.264274: step: 188/531, loss: 0.07578025013208389
2023-01-21 10:24:33.442481: step: 192/531, loss: 0.03191714361310005
2023-01-21 10:24:34.555479: step: 196/531, loss: 0.004897499457001686
2023-01-21 10:24:35.703189: step: 200/531, loss: 0.2933124601840973
2023-01-21 10:24:36.847179: step: 204/531, loss: 0.018488075584173203
2023-01-21 10:24:37.958441: step: 208/531, loss: 0.059687234461307526
2023-01-21 10:24:39.093607: step: 212/531, loss: 0.06043891981244087
2023-01-21 10:24:40.222260: step: 216/531, loss: 0.06790924072265625
2023-01-21 10:24:41.364692: step: 220/531, loss: 0.030646134167909622
2023-01-21 10:24:42.510680: step: 224/531, loss: 0.14025917649269104
2023-01-21 10:24:43.640310: step: 228/531, loss: 0.07133427262306213
2023-01-21 10:24:44.791533: step: 232/531, loss: 0.08211421966552734
2023-01-21 10:24:45.928333: step: 236/531, loss: 0.006190681830048561
2023-01-21 10:24:47.052193: step: 240/531, loss: 0.019986726343631744
2023-01-21 10:24:48.206488: step: 244/531, loss: 0.0880856066942215
2023-01-21 10:24:49.322412: step: 248/531, loss: 0.07127171009778976
2023-01-21 10:24:50.469970: step: 252/531, loss: 0.014315510168671608
2023-01-21 10:24:51.625088: step: 256/531, loss: 0.035547591745853424
2023-01-21 10:24:52.778764: step: 260/531, loss: 0.3115212619304657
2023-01-21 10:24:53.955820: step: 264/531, loss: 0.08876543492078781
2023-01-21 10:24:55.059360: step: 268/531, loss: 0.03832416608929634
2023-01-21 10:24:56.177887: step: 272/531, loss: 0.032218076288700104
2023-01-21 10:24:57.335790: step: 276/531, loss: 0.08227644115686417
2023-01-21 10:24:58.485133: step: 280/531, loss: 0.06085105240345001
2023-01-21 10:24:59.638244: step: 284/531, loss: 0.01662912406027317
2023-01-21 10:25:00.750468: step: 288/531, loss: 0.007895088754594326
2023-01-21 10:25:01.879394: step: 292/531, loss: 0.08230190724134445
2023-01-21 10:25:03.026603: step: 296/531, loss: 0.04370632395148277
2023-01-21 10:25:04.192627: step: 300/531, loss: 0.025006866082549095
2023-01-21 10:25:05.313752: step: 304/531, loss: 0.056152328848838806
2023-01-21 10:25:06.462475: step: 308/531, loss: 0.04372129589319229
2023-01-21 10:25:07.626953: step: 312/531, loss: 0.05147209390997887
2023-01-21 10:25:08.753393: step: 316/531, loss: 0.055887412279844284
2023-01-21 10:25:09.900224: step: 320/531, loss: 0.015970803797245026
2023-01-21 10:25:11.043002: step: 324/531, loss: 0.06616868823766708
2023-01-21 10:25:12.208140: step: 328/531, loss: 0.0749916136264801
2023-01-21 10:25:13.347451: step: 332/531, loss: 0.012963676825165749
2023-01-21 10:25:14.508784: step: 336/531, loss: 0.041699692606925964
2023-01-21 10:25:15.683969: step: 340/531, loss: 0.09000120311975479
2023-01-21 10:25:16.794319: step: 344/531, loss: 0.035185907036066055
2023-01-21 10:25:17.957590: step: 348/531, loss: 0.06844715774059296
2023-01-21 10:25:19.110701: step: 352/531, loss: 0.006012916564941406
2023-01-21 10:25:20.260598: step: 356/531, loss: 0.031853388994932175
2023-01-21 10:25:21.437197: step: 360/531, loss: 0.00910100992769003
2023-01-21 10:25:22.571178: step: 364/531, loss: 0.018318749964237213
2023-01-21 10:25:23.724548: step: 368/531, loss: 0.026638412848114967
2023-01-21 10:25:24.872633: step: 372/531, loss: 0.013840246014297009
2023-01-21 10:25:26.022223: step: 376/531, loss: 0.05256080627441406
2023-01-21 10:25:27.145743: step: 380/531, loss: 0.055220797657966614
2023-01-21 10:25:28.278546: step: 384/531, loss: 0.11647415161132812
2023-01-21 10:25:29.441203: step: 388/531, loss: 0.08593187481164932
2023-01-21 10:25:30.586486: step: 392/531, loss: 0.10279569774866104
2023-01-21 10:25:31.710769: step: 396/531, loss: 0.0340307243168354
2023-01-21 10:25:32.815425: step: 400/531, loss: 0.008854531683027744
2023-01-21 10:25:33.941485: step: 404/531, loss: 0.012184333987534046
2023-01-21 10:25:35.111377: step: 408/531, loss: 0.17254963517189026
2023-01-21 10:25:36.254591: step: 412/531, loss: 0.10960359871387482
2023-01-21 10:25:37.393438: step: 416/531, loss: 0.02779102325439453
2023-01-21 10:25:38.536151: step: 420/531, loss: 0.04721851274371147
2023-01-21 10:25:39.693566: step: 424/531, loss: 0.5016942024230957
2023-01-21 10:25:40.817377: step: 428/531, loss: 0.07115888595581055
2023-01-21 10:25:41.957709: step: 432/531, loss: 0.012452316470444202
2023-01-21 10:25:43.114714: step: 436/531, loss: 0.07896728068590164
2023-01-21 10:25:44.269665: step: 440/531, loss: 0.03048224374651909
2023-01-21 10:25:45.441106: step: 444/531, loss: 0.004890632815659046
2023-01-21 10:25:46.618799: step: 448/531, loss: 0.14467020332813263
2023-01-21 10:25:47.745980: step: 452/531, loss: 0.012338734231889248
2023-01-21 10:25:48.891391: step: 456/531, loss: 0.03182778134942055
2023-01-21 10:25:50.034646: step: 460/531, loss: 0.025916673243045807
2023-01-21 10:25:51.183651: step: 464/531, loss: 0.054062843322753906
2023-01-21 10:25:52.301073: step: 468/531, loss: 0.0019515752792358398
2023-01-21 10:25:53.450039: step: 472/531, loss: 0.41069117188453674
2023-01-21 10:25:54.596924: step: 476/531, loss: 0.06978817284107208
2023-01-21 10:25:55.738141: step: 480/531, loss: 0.012439345940947533
2023-01-21 10:25:56.873730: step: 484/531, loss: 0.013334274291992188
2023-01-21 10:25:57.987175: step: 488/531, loss: 0.02295989915728569
2023-01-21 10:25:59.168869: step: 492/531, loss: 0.02122201956808567
2023-01-21 10:26:00.327703: step: 496/531, loss: 0.144618421792984
2023-01-21 10:26:01.445148: step: 500/531, loss: 0.306057333946228
2023-01-21 10:26:02.576643: step: 504/531, loss: 0.07174110412597656
2023-01-21 10:26:03.701031: step: 508/531, loss: 0.11224012076854706
2023-01-21 10:26:04.861643: step: 512/531, loss: 0.03417778015136719
2023-01-21 10:26:06.027899: step: 516/531, loss: 0.10084018856287003
2023-01-21 10:26:07.161828: step: 520/531, loss: 0.146678626537323
2023-01-21 10:26:08.356187: step: 524/531, loss: 0.20326891541481018
2023-01-21 10:26:09.515775: step: 528/531, loss: 0.3622824251651764
2023-01-21 10:26:10.720793: step: 532/531, loss: 0.22680988907814026
2023-01-21 10:26:11.917289: step: 536/531, loss: 0.37415409088134766
2023-01-21 10:26:13.076124: step: 540/531, loss: 0.04333953559398651
2023-01-21 10:26:14.221806: step: 544/531, loss: 0.07723169773817062
2023-01-21 10:26:15.353450: step: 548/531, loss: 0.014127874746918678
2023-01-21 10:26:16.492904: step: 552/531, loss: 0.03958110883831978
2023-01-21 10:26:17.644385: step: 556/531, loss: 0.021869469434022903
2023-01-21 10:26:18.820759: step: 560/531, loss: 0.10576210170984268
2023-01-21 10:26:19.976940: step: 564/531, loss: 0.03191089630126953
2023-01-21 10:26:21.083640: step: 568/531, loss: 0.008348274976015091
2023-01-21 10:26:22.208392: step: 572/531, loss: 0.04977264627814293
2023-01-21 10:26:23.350038: step: 576/531, loss: 0.008417129516601562
2023-01-21 10:26:24.500950: step: 580/531, loss: 0.06541161239147186
2023-01-21 10:26:25.632011: step: 584/531, loss: 0.01195461768656969
2023-01-21 10:26:26.810908: step: 588/531, loss: 0.040986157953739166
2023-01-21 10:26:27.949506: step: 592/531, loss: 0.23552751541137695
2023-01-21 10:26:29.092251: step: 596/531, loss: 0.003774166340008378
2023-01-21 10:26:30.232887: step: 600/531, loss: 0.06213798373937607
2023-01-21 10:26:31.406196: step: 604/531, loss: 0.00360107421875
2023-01-21 10:26:32.559413: step: 608/531, loss: 0.017049027606844902
2023-01-21 10:26:33.707031: step: 612/531, loss: 0.005968618206679821
2023-01-21 10:26:34.905965: step: 616/531, loss: 0.22247114777565002
2023-01-21 10:26:36.045814: step: 620/531, loss: 0.02117347903549671
2023-01-21 10:26:37.192317: step: 624/531, loss: 0.016951942816376686
2023-01-21 10:26:38.311610: step: 628/531, loss: 0.0916353240609169
2023-01-21 10:26:39.477515: step: 632/531, loss: 0.014162063598632812
2023-01-21 10:26:40.624314: step: 636/531, loss: 0.1066884994506836
2023-01-21 10:26:41.763220: step: 640/531, loss: 0.0066679478622972965
2023-01-21 10:26:42.938132: step: 644/531, loss: 0.07322931289672852
2023-01-21 10:26:44.088454: step: 648/531, loss: 0.04711761325597763
2023-01-21 10:26:45.215390: step: 652/531, loss: 0.04643545299768448
2023-01-21 10:26:46.347957: step: 656/531, loss: 0.2179102897644043
2023-01-21 10:26:47.476222: step: 660/531, loss: 0.0009292125469073653
2023-01-21 10:26:48.626121: step: 664/531, loss: 0.7998761534690857
2023-01-21 10:26:49.713891: step: 668/531, loss: 0.02630983106791973
2023-01-21 10:26:50.854295: step: 672/531, loss: 0.014265251345932484
2023-01-21 10:26:51.965606: step: 676/531, loss: 0.00098590855486691
2023-01-21 10:26:53.121003: step: 680/531, loss: 0.009912585839629173
2023-01-21 10:26:54.229369: step: 684/531, loss: 0.1357942521572113
2023-01-21 10:26:55.338388: step: 688/531, loss: 0.014799404889345169
2023-01-21 10:26:56.478266: step: 692/531, loss: 0.029797174036502838
2023-01-21 10:26:57.681311: step: 696/531, loss: 0.012627029791474342
2023-01-21 10:26:58.845442: step: 700/531, loss: 0.01823272742331028
2023-01-21 10:26:59.958819: step: 704/531, loss: 0.06258168071508408
2023-01-21 10:27:01.123450: step: 708/531, loss: 0.03286170959472656
2023-01-21 10:27:02.264998: step: 712/531, loss: 0.02969665452837944
2023-01-21 10:27:03.406320: step: 716/531, loss: 0.006225496530532837
2023-01-21 10:27:04.551002: step: 720/531, loss: 0.06629371643066406
2023-01-21 10:27:05.704250: step: 724/531, loss: 0.08167973160743713
2023-01-21 10:27:06.865491: step: 728/531, loss: 0.05467739328742027
2023-01-21 10:27:08.046914: step: 732/531, loss: 0.016378212720155716
2023-01-21 10:27:09.193952: step: 736/531, loss: 0.051668357104063034
2023-01-21 10:27:10.364131: step: 740/531, loss: 0.04822579771280289
2023-01-21 10:27:11.550386: step: 744/531, loss: 0.06492596119642258
2023-01-21 10:27:12.676663: step: 748/531, loss: 0.05175819620490074
2023-01-21 10:27:13.829656: step: 752/531, loss: 0.15580235421657562
2023-01-21 10:27:15.003162: step: 756/531, loss: 0.07834777981042862
2023-01-21 10:27:16.142975: step: 760/531, loss: 0.05625486373901367
2023-01-21 10:27:17.288890: step: 764/531, loss: 0.09737630188465118
2023-01-21 10:27:18.449328: step: 768/531, loss: 0.08191872388124466
2023-01-21 10:27:19.626849: step: 772/531, loss: 0.025229312479496002
2023-01-21 10:27:20.769952: step: 776/531, loss: 0.1384994387626648
2023-01-21 10:27:21.897035: step: 780/531, loss: 0.010183000937104225
2023-01-21 10:27:23.019266: step: 784/531, loss: 0.04601306840777397
2023-01-21 10:27:24.152996: step: 788/531, loss: 0.051373135298490524
2023-01-21 10:27:25.297794: step: 792/531, loss: 0.05576353520154953
2023-01-21 10:27:26.436900: step: 796/531, loss: 0.09234924614429474
2023-01-21 10:27:27.600468: step: 800/531, loss: 0.04915919154882431
2023-01-21 10:27:28.720997: step: 804/531, loss: 0.04209165647625923
2023-01-21 10:27:29.863124: step: 808/531, loss: 0.05142030492424965
2023-01-21 10:27:30.998420: step: 812/531, loss: 0.005220318213105202
2023-01-21 10:27:32.116379: step: 816/531, loss: 0.06891937553882599
2023-01-21 10:27:33.267762: step: 820/531, loss: 0.018738461658358574
2023-01-21 10:27:34.407368: step: 824/531, loss: 0.23927488923072815
2023-01-21 10:27:35.559371: step: 828/531, loss: 0.017548561096191406
2023-01-21 10:27:36.707631: step: 832/531, loss: 0.10842597484588623
2023-01-21 10:27:37.858512: step: 836/531, loss: 0.07489724457263947
2023-01-21 10:27:38.987974: step: 840/531, loss: 0.10272105038166046
2023-01-21 10:27:40.140889: step: 844/531, loss: 0.04646625369787216
2023-01-21 10:27:41.290515: step: 848/531, loss: 0.051653482019901276
2023-01-21 10:27:42.488528: step: 852/531, loss: 0.054238513112068176
2023-01-21 10:27:43.651689: step: 856/531, loss: 0.015908241271972656
2023-01-21 10:27:44.780667: step: 860/531, loss: 0.019634723663330078
2023-01-21 10:27:45.939244: step: 864/531, loss: 0.09593596309423447
2023-01-21 10:27:47.069475: step: 868/531, loss: 0.014927363023161888
2023-01-21 10:27:48.198839: step: 872/531, loss: 0.03744788467884064
2023-01-21 10:27:49.365882: step: 876/531, loss: 0.023227693513035774
2023-01-21 10:27:50.490660: step: 880/531, loss: 0.026528455317020416
2023-01-21 10:27:51.618714: step: 884/531, loss: 0.010198403149843216
2023-01-21 10:27:52.767970: step: 888/531, loss: 0.005169820971786976
2023-01-21 10:27:53.929004: step: 892/531, loss: 0.07492761313915253
2023-01-21 10:27:55.077019: step: 896/531, loss: 0.06531677395105362
2023-01-21 10:27:56.221107: step: 900/531, loss: 0.005061245057731867
2023-01-21 10:27:57.376049: step: 904/531, loss: 1.0460602045059204
2023-01-21 10:27:58.499592: step: 908/531, loss: 0.13290157914161682
2023-01-21 10:27:59.658415: step: 912/531, loss: 0.08747921139001846
2023-01-21 10:28:00.805905: step: 916/531, loss: 0.05565004423260689
2023-01-21 10:28:01.958182: step: 920/531, loss: 0.08048954606056213
2023-01-21 10:28:03.113587: step: 924/531, loss: 0.005328941158950329
2023-01-21 10:28:04.213470: step: 928/531, loss: 0.038314905017614365
2023-01-21 10:28:05.365111: step: 932/531, loss: 0.11348043382167816
2023-01-21 10:28:06.504959: step: 936/531, loss: 0.08749179542064667
2023-01-21 10:28:07.633642: step: 940/531, loss: 0.012257575988769531
2023-01-21 10:28:08.764399: step: 944/531, loss: 0.10363617539405823
2023-01-21 10:28:09.871814: step: 948/531, loss: 0.06945953518152237
2023-01-21 10:28:10.989790: step: 952/531, loss: 0.016492843627929688
2023-01-21 10:28:12.134602: step: 956/531, loss: 0.038178253918886185
2023-01-21 10:28:13.280753: step: 960/531, loss: 0.11736125499010086
2023-01-21 10:28:14.457441: step: 964/531, loss: 0.059011079370975494
2023-01-21 10:28:15.630772: step: 968/531, loss: 0.03714399412274361
2023-01-21 10:28:16.766461: step: 972/531, loss: 0.06651488691568375
2023-01-21 10:28:17.956976: step: 976/531, loss: 0.39760273694992065
2023-01-21 10:28:19.100337: step: 980/531, loss: 0.004326629918068647
2023-01-21 10:28:20.269586: step: 984/531, loss: 0.0034225464332848787
2023-01-21 10:28:21.402042: step: 988/531, loss: 0.03228771686553955
2023-01-21 10:28:22.531327: step: 992/531, loss: 0.14333724975585938
2023-01-21 10:28:23.644269: step: 996/531, loss: 0.047245219349861145
2023-01-21 10:28:24.773040: step: 1000/531, loss: 0.14321298897266388
2023-01-21 10:28:25.926622: step: 1004/531, loss: 0.05715999752283096
2023-01-21 10:28:27.065120: step: 1008/531, loss: 0.018375109881162643
2023-01-21 10:28:28.209201: step: 1012/531, loss: 0.0494932197034359
2023-01-21 10:28:29.377090: step: 1016/531, loss: 0.04739503562450409
2023-01-21 10:28:30.510223: step: 1020/531, loss: 0.02921323850750923
2023-01-21 10:28:31.651521: step: 1024/531, loss: 0.0077949524857103825
2023-01-21 10:28:32.834879: step: 1028/531, loss: 0.027232743799686432
2023-01-21 10:28:33.986305: step: 1032/531, loss: 0.07723388820886612
2023-01-21 10:28:35.152142: step: 1036/531, loss: 0.030594348907470703
2023-01-21 10:28:36.322563: step: 1040/531, loss: 0.021930648013949394
2023-01-21 10:28:37.484328: step: 1044/531, loss: 0.06510657072067261
2023-01-21 10:28:38.591554: step: 1048/531, loss: 0.02773761749267578
2023-01-21 10:28:39.732845: step: 1052/531, loss: 0.2726472020149231
2023-01-21 10:28:40.893755: step: 1056/531, loss: 0.0855376273393631
2023-01-21 10:28:42.023791: step: 1060/531, loss: 0.0018999099265784025
2023-01-21 10:28:43.196822: step: 1064/531, loss: 0.12846003472805023
2023-01-21 10:28:44.350772: step: 1068/531, loss: 0.08939714729785919
2023-01-21 10:28:45.506012: step: 1072/531, loss: 0.15981721878051758
2023-01-21 10:28:46.640668: step: 1076/531, loss: 0.038900043815374374
2023-01-21 10:28:47.778638: step: 1080/531, loss: 0.06309547275304794
2023-01-21 10:28:48.926596: step: 1084/531, loss: 0.12618786096572876
2023-01-21 10:28:50.078288: step: 1088/531, loss: 0.09540615975856781
2023-01-21 10:28:51.236085: step: 1092/531, loss: 0.010279751382768154
2023-01-21 10:28:52.346943: step: 1096/531, loss: 0.03257796913385391
2023-01-21 10:28:53.492465: step: 1100/531, loss: 0.14710812270641327
2023-01-21 10:28:54.618762: step: 1104/531, loss: 0.008303165435791016
2023-01-21 10:28:55.785109: step: 1108/531, loss: 0.04552774503827095
2023-01-21 10:28:56.917562: step: 1112/531, loss: 0.04540209844708443
2023-01-21 10:28:58.081683: step: 1116/531, loss: 0.008212566375732422
2023-01-21 10:28:59.218684: step: 1120/531, loss: 0.024722862988710403
2023-01-21 10:29:00.337534: step: 1124/531, loss: 0.002464342163875699
2023-01-21 10:29:01.489482: step: 1128/531, loss: 0.030570555478334427
2023-01-21 10:29:02.620240: step: 1132/531, loss: 0.052817728370428085
2023-01-21 10:29:03.760227: step: 1136/531, loss: 0.1002207100391388
2023-01-21 10:29:04.922223: step: 1140/531, loss: 0.06465911865234375
2023-01-21 10:29:06.057854: step: 1144/531, loss: 0.01697215996682644
2023-01-21 10:29:07.198336: step: 1148/531, loss: 0.2452809363603592
2023-01-21 10:29:08.346380: step: 1152/531, loss: 0.055530741810798645
2023-01-21 10:29:09.481236: step: 1156/531, loss: 0.06503229588270187
2023-01-21 10:29:10.623797: step: 1160/531, loss: 0.013924885541200638
2023-01-21 10:29:11.763900: step: 1164/531, loss: 0.029801130294799805
2023-01-21 10:29:12.913047: step: 1168/531, loss: 0.04488945007324219
2023-01-21 10:29:14.053750: step: 1172/531, loss: 0.051447439938783646
2023-01-21 10:29:15.205908: step: 1176/531, loss: 0.04332561790943146
2023-01-21 10:29:16.346583: step: 1180/531, loss: 0.027602005749940872
2023-01-21 10:29:17.449856: step: 1184/531, loss: 0.011275816708803177
2023-01-21 10:29:18.583587: step: 1188/531, loss: 0.09218786656856537
2023-01-21 10:29:19.735428: step: 1192/531, loss: 0.10438642650842667
2023-01-21 10:29:20.914730: step: 1196/531, loss: 0.038543201982975006
2023-01-21 10:29:22.057899: step: 1200/531, loss: 0.10220833122730255
2023-01-21 10:29:23.212807: step: 1204/531, loss: 0.40021011233329773
2023-01-21 10:29:24.337881: step: 1208/531, loss: 0.17189693450927734
2023-01-21 10:29:25.498576: step: 1212/531, loss: 0.019986821338534355
2023-01-21 10:29:26.654204: step: 1216/531, loss: 0.04291076958179474
2023-01-21 10:29:27.793851: step: 1220/531, loss: 0.0387515053153038
2023-01-21 10:29:28.948546: step: 1224/531, loss: 0.041299011558294296
2023-01-21 10:29:30.133067: step: 1228/531, loss: 0.1474718153476715
2023-01-21 10:29:31.280446: step: 1232/531, loss: 0.06479165703058243
2023-01-21 10:29:32.388497: step: 1236/531, loss: 0.06092948839068413
2023-01-21 10:29:33.553530: step: 1240/531, loss: 0.040706731379032135
2023-01-21 10:29:34.703020: step: 1244/531, loss: 0.0832282081246376
2023-01-21 10:29:35.865244: step: 1248/531, loss: 0.0672634094953537
2023-01-21 10:29:36.991163: step: 1252/531, loss: 0.8018707036972046
2023-01-21 10:29:38.151855: step: 1256/531, loss: 0.020440055057406425
2023-01-21 10:29:39.294809: step: 1260/531, loss: 0.09119053184986115
2023-01-21 10:29:40.442495: step: 1264/531, loss: 0.05557747185230255
2023-01-21 10:29:41.594299: step: 1268/531, loss: 0.14118710160255432
2023-01-21 10:29:42.753996: step: 1272/531, loss: 0.04338102415204048
2023-01-21 10:29:43.872533: step: 1276/531, loss: 0.5367922782897949
2023-01-21 10:29:45.024512: step: 1280/531, loss: 0.04592332988977432
2023-01-21 10:29:46.167313: step: 1284/531, loss: 0.07780647277832031
2023-01-21 10:29:47.333217: step: 1288/531, loss: 0.27759668231010437
2023-01-21 10:29:48.490437: step: 1292/531, loss: 0.06564340740442276
2023-01-21 10:29:49.665367: step: 1296/531, loss: 0.15360213816165924
2023-01-21 10:29:50.789119: step: 1300/531, loss: 0.15772390365600586
2023-01-21 10:29:51.927278: step: 1304/531, loss: 0.03248763084411621
2023-01-21 10:29:53.067722: step: 1308/531, loss: 0.12499995529651642
2023-01-21 10:29:54.216208: step: 1312/531, loss: 0.09133310616016388
2023-01-21 10:29:55.442451: step: 1316/531, loss: 0.10047177970409393
2023-01-21 10:29:56.607342: step: 1320/531, loss: 0.09492664039134979
2023-01-21 10:29:57.770198: step: 1324/531, loss: 0.12200088798999786
2023-01-21 10:29:58.904120: step: 1328/531, loss: 0.0032106759026646614
2023-01-21 10:30:00.056805: step: 1332/531, loss: 0.017783308401703835
2023-01-21 10:30:01.198354: step: 1336/531, loss: 0.0718679428100586
2023-01-21 10:30:02.355945: step: 1340/531, loss: 0.04496727138757706
2023-01-21 10:30:03.490836: step: 1344/531, loss: 0.006965351291000843
2023-01-21 10:30:04.628222: step: 1348/531, loss: 0.06089191883802414
2023-01-21 10:30:05.793952: step: 1352/531, loss: 0.013176441192626953
2023-01-21 10:30:06.911960: step: 1356/531, loss: 0.08237600326538086
2023-01-21 10:30:08.038401: step: 1360/531, loss: 0.04487152397632599
2023-01-21 10:30:09.188189: step: 1364/531, loss: 0.012930680066347122
2023-01-21 10:30:10.353310: step: 1368/531, loss: 0.05785961449146271
2023-01-21 10:30:11.485493: step: 1372/531, loss: 0.005673789884895086
2023-01-21 10:30:12.647187: step: 1376/531, loss: 0.18685337901115417
2023-01-21 10:30:13.784454: step: 1380/531, loss: 0.10376176983118057
2023-01-21 10:30:14.932138: step: 1384/531, loss: 0.13303223252296448
2023-01-21 10:30:16.053048: step: 1388/531, loss: 0.06505189090967178
2023-01-21 10:30:17.182827: step: 1392/531, loss: 0.050676967948675156
2023-01-21 10:30:18.324547: step: 1396/531, loss: 0.00166740408167243
2023-01-21 10:30:19.481541: step: 1400/531, loss: 0.01211013738065958
2023-01-21 10:30:20.621684: step: 1404/531, loss: 0.12830395996570587
2023-01-21 10:30:21.793757: step: 1408/531, loss: 0.02961292304098606
2023-01-21 10:30:22.949600: step: 1412/531, loss: 0.034870196133852005
2023-01-21 10:30:24.098829: step: 1416/531, loss: 0.04339813441038132
2023-01-21 10:30:25.244476: step: 1420/531, loss: 0.11966609954833984
2023-01-21 10:30:26.421040: step: 1424/531, loss: 0.02256040647625923
2023-01-21 10:30:27.592460: step: 1428/531, loss: 0.025408554822206497
2023-01-21 10:30:28.738931: step: 1432/531, loss: 0.05446481704711914
2023-01-21 10:30:29.871520: step: 1436/531, loss: 0.012572193518280983
2023-01-21 10:30:31.027512: step: 1440/531, loss: 0.07757556438446045
2023-01-21 10:30:32.147797: step: 1444/531, loss: 0.036899056285619736
2023-01-21 10:30:33.299137: step: 1448/531, loss: 0.06191766634583473
2023-01-21 10:30:34.453407: step: 1452/531, loss: 0.07007431983947754
2023-01-21 10:30:35.611648: step: 1456/531, loss: 0.04421382024884224
2023-01-21 10:30:36.781850: step: 1460/531, loss: 0.0008575439569540322
2023-01-21 10:30:37.908706: step: 1464/531, loss: 0.020115423947572708
2023-01-21 10:30:39.054755: step: 1468/531, loss: 0.03657855838537216
2023-01-21 10:30:40.194251: step: 1472/531, loss: 0.06703939288854599
2023-01-21 10:30:41.339654: step: 1476/531, loss: 0.1048712208867073
2023-01-21 10:30:42.487613: step: 1480/531, loss: 0.015604782849550247
2023-01-21 10:30:43.650059: step: 1484/531, loss: 0.3073750138282776
2023-01-21 10:30:44.774291: step: 1488/531, loss: 0.09835891425609589
2023-01-21 10:30:45.927547: step: 1492/531, loss: 0.03867781162261963
2023-01-21 10:30:47.069895: step: 1496/531, loss: 0.0779334083199501
2023-01-21 10:30:48.230633: step: 1500/531, loss: 0.06903638690710068
2023-01-21 10:30:49.382558: step: 1504/531, loss: 0.21315795183181763
2023-01-21 10:30:50.524177: step: 1508/531, loss: 0.322004497051239
2023-01-21 10:30:51.671517: step: 1512/531, loss: 0.030344534665346146
2023-01-21 10:30:52.827637: step: 1516/531, loss: 0.10674019157886505
2023-01-21 10:30:53.951303: step: 1520/531, loss: 0.048955343663692474
2023-01-21 10:30:55.101748: step: 1524/531, loss: 0.1165475845336914
2023-01-21 10:30:56.275202: step: 1528/531, loss: 0.09774628281593323
2023-01-21 10:30:57.472075: step: 1532/531, loss: 0.1109004095196724
2023-01-21 10:30:58.614595: step: 1536/531, loss: 0.04538846015930176
2023-01-21 10:30:59.746701: step: 1540/531, loss: 0.04183550179004669
2023-01-21 10:31:00.875886: step: 1544/531, loss: 0.043260835111141205
2023-01-21 10:31:02.000825: step: 1548/531, loss: 0.22896814346313477
2023-01-21 10:31:03.118545: step: 1552/531, loss: 0.018180465325713158
2023-01-21 10:31:04.259953: step: 1556/531, loss: 0.035036277025938034
2023-01-21 10:31:05.401447: step: 1560/531, loss: 0.23148202896118164
2023-01-21 10:31:06.532375: step: 1564/531, loss: 0.08412857353687286
2023-01-21 10:31:07.693497: step: 1568/531, loss: 0.07042789459228516
2023-01-21 10:31:08.804377: step: 1572/531, loss: 0.05395574867725372
2023-01-21 10:31:09.950351: step: 1576/531, loss: 0.0663209930062294
2023-01-21 10:31:11.115487: step: 1580/531, loss: 0.05465278401970863
2023-01-21 10:31:12.240418: step: 1584/531, loss: 0.08454103767871857
2023-01-21 10:31:13.385335: step: 1588/531, loss: 0.057108692824840546
2023-01-21 10:31:14.522592: step: 1592/531, loss: 0.67942214012146
2023-01-21 10:31:15.682825: step: 1596/531, loss: 0.04212953522801399
2023-01-21 10:31:16.816786: step: 1600/531, loss: 0.06312417984008789
2023-01-21 10:31:17.938220: step: 1604/531, loss: 0.01411585882306099
2023-01-21 10:31:19.083384: step: 1608/531, loss: 0.22869928181171417
2023-01-21 10:31:20.238424: step: 1612/531, loss: 0.0613219290971756
2023-01-21 10:31:21.438252: step: 1616/531, loss: 0.4913889765739441
2023-01-21 10:31:22.571877: step: 1620/531, loss: 0.04574775695800781
2023-01-21 10:31:23.701232: step: 1624/531, loss: 0.03464813157916069
2023-01-21 10:31:24.808323: step: 1628/531, loss: 0.04906511306762695
2023-01-21 10:31:25.934176: step: 1632/531, loss: 0.03040132485330105
2023-01-21 10:31:27.075559: step: 1636/531, loss: 0.7075724601745605
2023-01-21 10:31:28.212287: step: 1640/531, loss: 0.8525973558425903
2023-01-21 10:31:29.344052: step: 1644/531, loss: 0.0013964890968054533
2023-01-21 10:31:30.508267: step: 1648/531, loss: 0.0379701629281044
2023-01-21 10:31:31.631575: step: 1652/531, loss: 0.001712799072265625
2023-01-21 10:31:32.791520: step: 1656/531, loss: 0.2171657681465149
2023-01-21 10:31:33.931379: step: 1660/531, loss: 0.019266320392489433
2023-01-21 10:31:35.023854: step: 1664/531, loss: 0.015967750921845436
2023-01-21 10:31:36.170309: step: 1668/531, loss: 0.0714021772146225
2023-01-21 10:31:37.276405: step: 1672/531, loss: 0.057566121220588684
2023-01-21 10:31:38.472251: step: 1676/531, loss: 0.0203904639929533
2023-01-21 10:31:39.638149: step: 1680/531, loss: 0.07539396733045578
2023-01-21 10:31:40.740929: step: 1684/531, loss: 0.09189968556165695
2023-01-21 10:31:41.890318: step: 1688/531, loss: 0.02228088304400444
2023-01-21 10:31:43.045144: step: 1692/531, loss: 0.11487503349781036
2023-01-21 10:31:44.217651: step: 1696/531, loss: 0.1178162544965744
2023-01-21 10:31:45.347068: step: 1700/531, loss: 0.004256772808730602
2023-01-21 10:31:46.505232: step: 1704/531, loss: 0.09162741154432297
2023-01-21 10:31:47.634308: step: 1708/531, loss: 0.13242283463478088
2023-01-21 10:31:48.785641: step: 1712/531, loss: 0.009106731973588467
2023-01-21 10:31:49.914205: step: 1716/531, loss: 0.028816986829042435
2023-01-21 10:31:51.019923: step: 1720/531, loss: 0.03114795684814453
2023-01-21 10:31:52.144926: step: 1724/531, loss: 0.18771325051784515
2023-01-21 10:31:53.264988: step: 1728/531, loss: 0.025037577375769615
2023-01-21 10:31:54.407193: step: 1732/531, loss: 0.022452164441347122
2023-01-21 10:31:55.567079: step: 1736/531, loss: 0.05461602285504341
2023-01-21 10:31:56.770653: step: 1740/531, loss: 0.1423497200012207
2023-01-21 10:31:57.878495: step: 1744/531, loss: 0.04620747268199921
2023-01-21 10:31:58.993892: step: 1748/531, loss: 0.0406682975590229
2023-01-21 10:32:00.145539: step: 1752/531, loss: 0.1025405153632164
2023-01-21 10:32:01.299794: step: 1756/531, loss: 0.15270757675170898
2023-01-21 10:32:02.468680: step: 1760/531, loss: 0.008900643326342106
2023-01-21 10:32:03.623908: step: 1764/531, loss: 0.011030149646103382
2023-01-21 10:32:04.772355: step: 1768/531, loss: 0.0023666382767260075
2023-01-21 10:32:05.945058: step: 1772/531, loss: 0.0548916831612587
2023-01-21 10:32:07.076821: step: 1776/531, loss: 0.0020505907014012337
2023-01-21 10:32:08.218034: step: 1780/531, loss: 0.03554067760705948
2023-01-21 10:32:09.384280: step: 1784/531, loss: 0.030874157324433327
2023-01-21 10:32:10.551186: step: 1788/531, loss: 0.17636089026927948
2023-01-21 10:32:11.720890: step: 1792/531, loss: 0.09419545531272888
2023-01-21 10:32:12.868305: step: 1796/531, loss: 0.03293962776660919
2023-01-21 10:32:14.021722: step: 1800/531, loss: 0.008083535358309746
2023-01-21 10:32:15.166544: step: 1804/531, loss: 0.018291760236024857
2023-01-21 10:32:16.315634: step: 1808/531, loss: 0.3487284779548645
2023-01-21 10:32:17.462276: step: 1812/531, loss: 0.03713226318359375
2023-01-21 10:32:18.607689: step: 1816/531, loss: 0.02489914931356907
2023-01-21 10:32:19.732125: step: 1820/531, loss: 0.06141247600317001
2023-01-21 10:32:20.887815: step: 1824/531, loss: 0.3006841838359833
2023-01-21 10:32:22.026399: step: 1828/531, loss: 0.019359780475497246
2023-01-21 10:32:23.163296: step: 1832/531, loss: 0.054311562329530716
2023-01-21 10:32:24.322838: step: 1836/531, loss: 0.07356911152601242
2023-01-21 10:32:25.481032: step: 1840/531, loss: 0.05465659871697426
2023-01-21 10:32:26.635797: step: 1844/531, loss: 0.8070365190505981
2023-01-21 10:32:27.737140: step: 1848/531, loss: 0.016205500811338425
2023-01-21 10:32:28.865310: step: 1852/531, loss: 0.007967568002641201
2023-01-21 10:32:30.023251: step: 1856/531, loss: 0.11349640041589737
2023-01-21 10:32:31.189827: step: 1860/531, loss: 0.13214674592018127
2023-01-21 10:32:32.320068: step: 1864/531, loss: 0.07776127010583878
2023-01-21 10:32:33.500226: step: 1868/531, loss: 0.08564339578151703
2023-01-21 10:32:34.635328: step: 1872/531, loss: 0.09141826629638672
2023-01-21 10:32:35.785386: step: 1876/531, loss: 0.5359444618225098
2023-01-21 10:32:36.929225: step: 1880/531, loss: 0.0693565383553505
2023-01-21 10:32:38.089390: step: 1884/531, loss: 0.026195909827947617
2023-01-21 10:32:39.247483: step: 1888/531, loss: 0.10916309058666229
2023-01-21 10:32:40.368141: step: 1892/531, loss: 0.024379348382353783
2023-01-21 10:32:41.478719: step: 1896/531, loss: 0.060793161392211914
2023-01-21 10:32:42.636927: step: 1900/531, loss: 0.005732154939323664
2023-01-21 10:32:43.775295: step: 1904/531, loss: 0.021378135308623314
2023-01-21 10:32:44.915621: step: 1908/531, loss: 0.1498439759016037
2023-01-21 10:32:46.073053: step: 1912/531, loss: 0.031178856268525124
2023-01-21 10:32:47.186295: step: 1916/531, loss: 0.006459998432546854
2023-01-21 10:32:48.323050: step: 1920/531, loss: 0.007043266203254461
2023-01-21 10:32:49.444421: step: 1924/531, loss: 0.031800128519535065
2023-01-21 10:32:50.572345: step: 1928/531, loss: 0.0641942024230957
2023-01-21 10:32:51.693887: step: 1932/531, loss: 0.028751373291015625
2023-01-21 10:32:52.850211: step: 1936/531, loss: 0.06740102916955948
2023-01-21 10:32:54.001202: step: 1940/531, loss: 0.05365820229053497
2023-01-21 10:32:55.145103: step: 1944/531, loss: 0.16541728377342224
2023-01-21 10:32:56.309724: step: 1948/531, loss: 0.059989165514707565
2023-01-21 10:32:57.455156: step: 1952/531, loss: 0.03951587527990341
2023-01-21 10:32:58.579708: step: 1956/531, loss: 0.125335693359375
2023-01-21 10:32:59.703132: step: 1960/531, loss: 0.129795640707016
2023-01-21 10:33:00.836410: step: 1964/531, loss: 0.12310321629047394
2023-01-21 10:33:01.960954: step: 1968/531, loss: 0.18646980822086334
2023-01-21 10:33:03.085424: step: 1972/531, loss: 0.1499319076538086
2023-01-21 10:33:04.230211: step: 1976/531, loss: 0.06747885048389435
2023-01-21 10:33:05.387832: step: 1980/531, loss: 0.019020844250917435
2023-01-21 10:33:06.499427: step: 1984/531, loss: 0.04625578224658966
2023-01-21 10:33:07.651134: step: 1988/531, loss: 0.02260427549481392
2023-01-21 10:33:08.781652: step: 1992/531, loss: 0.02519693411886692
2023-01-21 10:33:09.924223: step: 1996/531, loss: 0.02496337890625
2023-01-21 10:33:11.064523: step: 2000/531, loss: 0.0812978744506836
2023-01-21 10:33:12.227029: step: 2004/531, loss: 0.13371573388576508
2023-01-21 10:33:13.353604: step: 2008/531, loss: 0.08028726279735565
2023-01-21 10:33:14.480208: step: 2012/531, loss: 0.08460722118616104
2023-01-21 10:33:15.622797: step: 2016/531, loss: 0.3900224566459656
2023-01-21 10:33:16.796292: step: 2020/531, loss: 0.08664903789758682
2023-01-21 10:33:17.933027: step: 2024/531, loss: 0.13433456420898438
2023-01-21 10:33:19.080171: step: 2028/531, loss: 0.1564178466796875
2023-01-21 10:33:20.240675: step: 2032/531, loss: 0.006483840756118298
2023-01-21 10:33:21.393873: step: 2036/531, loss: 0.0345611572265625
2023-01-21 10:33:22.498855: step: 2040/531, loss: 0.14012479782104492
2023-01-21 10:33:23.625401: step: 2044/531, loss: 0.09803247451782227
2023-01-21 10:33:24.781878: step: 2048/531, loss: 0.007104110904037952
2023-01-21 10:33:25.912821: step: 2052/531, loss: 0.03317451477050781
2023-01-21 10:33:27.057444: step: 2056/531, loss: 0.12858638167381287
2023-01-21 10:33:28.204900: step: 2060/531, loss: 0.036590054631233215
2023-01-21 10:33:29.317072: step: 2064/531, loss: 0.0404357947409153
2023-01-21 10:33:30.442209: step: 2068/531, loss: 0.0540614128112793
2023-01-21 10:33:31.607708: step: 2072/531, loss: 0.10163593292236328
2023-01-21 10:33:32.760285: step: 2076/531, loss: 0.047170642763376236
2023-01-21 10:33:33.940167: step: 2080/531, loss: 0.025232411921024323
2023-01-21 10:33:35.089762: step: 2084/531, loss: 0.08812332153320312
2023-01-21 10:33:36.242050: step: 2088/531, loss: 0.08783034980297089
2023-01-21 10:33:37.395792: step: 2092/531, loss: 0.041292428970336914
2023-01-21 10:33:38.515028: step: 2096/531, loss: 0.021515464410185814
2023-01-21 10:33:39.662669: step: 2100/531, loss: 0.06693977117538452
2023-01-21 10:33:40.817766: step: 2104/531, loss: 0.0738416239619255
2023-01-21 10:33:41.948328: step: 2108/531, loss: 0.05874716117978096
2023-01-21 10:33:43.087224: step: 2112/531, loss: 0.6315667629241943
2023-01-21 10:33:44.196129: step: 2116/531, loss: 0.08243980258703232
2023-01-21 10:33:45.306137: step: 2120/531, loss: 0.039584919810295105
2023-01-21 10:33:46.404095: step: 2124/531, loss: 0.05166645348072052
==================================================
Loss: 0.086
--------------------
Dev: {'event': {'p': 0.5961923847695391, 'r': 0.7922769640479361, 'f1': 0.6803887935963409}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6274416388756551, 'r': 0.7853309481216458, 'f1': 0.697563559322034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5925925925925926, 'r': 0.8888888888888888, 'f1': 0.711111111111111}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.6981132075471698, 'r': 0.5873015873015873, 'f1': 0.6379310344827586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5725264169068204, 'r': 0.7936085219707057, 'f1': 0.6651785714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6113918236104732, 'r': 0.7936791890280263, 'f1': 0.6907109496626881}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.65625, 'r': 0.6666666666666666, 'f1': 0.6614173228346457}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:34:29.738759: step: 4/531, loss: 0.038973234593868256
2023-01-21 10:34:30.876600: step: 8/531, loss: 0.34092310070991516
2023-01-21 10:34:32.042007: step: 12/531, loss: 0.042228128761053085
2023-01-21 10:34:33.178049: step: 16/531, loss: 0.0032852173317223787
2023-01-21 10:34:34.324057: step: 20/531, loss: 0.10696382075548172
2023-01-21 10:34:35.462826: step: 24/531, loss: 0.005381679628044367
2023-01-21 10:34:36.598018: step: 28/531, loss: 0.02842102013528347
2023-01-21 10:34:37.764585: step: 32/531, loss: 0.35137346386909485
2023-01-21 10:34:38.915272: step: 36/531, loss: 0.02191338688135147
2023-01-21 10:34:40.090567: step: 40/531, loss: 0.07915983349084854
2023-01-21 10:34:41.244025: step: 44/531, loss: 0.036618996411561966
2023-01-21 10:34:42.411193: step: 48/531, loss: 0.007364988327026367
2023-01-21 10:34:43.549297: step: 52/531, loss: 0.03930368646979332
2023-01-21 10:34:44.702014: step: 56/531, loss: 0.023439789190888405
2023-01-21 10:34:45.834031: step: 60/531, loss: 0.02361888997256756
2023-01-21 10:34:46.996399: step: 64/531, loss: 0.023807907477021217
2023-01-21 10:34:48.125501: step: 68/531, loss: 0.1282922625541687
2023-01-21 10:34:49.275153: step: 72/531, loss: 0.04363222420215607
2023-01-21 10:34:50.419007: step: 76/531, loss: 0.0015531539684161544
2023-01-21 10:34:51.594760: step: 80/531, loss: 0.12497377395629883
2023-01-21 10:34:52.723145: step: 84/531, loss: 0.021805381402373314
2023-01-21 10:34:53.860396: step: 88/531, loss: 0.011691666208207607
2023-01-21 10:34:55.043621: step: 92/531, loss: 0.045899197459220886
2023-01-21 10:34:56.191899: step: 96/531, loss: 0.10177517682313919
2023-01-21 10:34:57.340161: step: 100/531, loss: 0.28401979804039
2023-01-21 10:34:58.475499: step: 104/531, loss: 0.017455102875828743
2023-01-21 10:34:59.636348: step: 108/531, loss: 0.04333076626062393
2023-01-21 10:35:00.780469: step: 112/531, loss: 0.04375896602869034
2023-01-21 10:35:01.900373: step: 116/531, loss: 0.026859380304813385
2023-01-21 10:35:03.060938: step: 120/531, loss: 0.04175710678100586
2023-01-21 10:35:04.224558: step: 124/531, loss: 0.04286069795489311
2023-01-21 10:35:05.378262: step: 128/531, loss: 0.013673496432602406
2023-01-21 10:35:06.538097: step: 132/531, loss: 0.020584868267178535
2023-01-21 10:35:07.682809: step: 136/531, loss: 0.02770562283694744
2023-01-21 10:35:08.855409: step: 140/531, loss: 0.16088980436325073
2023-01-21 10:35:09.999667: step: 144/531, loss: 0.010279846377670765
2023-01-21 10:35:11.108241: step: 148/531, loss: 0.03518953546881676
2023-01-21 10:35:12.232720: step: 152/531, loss: 0.03272116929292679
2023-01-21 10:35:13.394160: step: 156/531, loss: 0.07336197048425674
2023-01-21 10:35:14.550261: step: 160/531, loss: 0.054956912994384766
2023-01-21 10:35:15.707711: step: 164/531, loss: 0.017528247088193893
2023-01-21 10:35:16.807782: step: 168/531, loss: 0.03565650060772896
2023-01-21 10:35:17.972106: step: 172/531, loss: 0.06515967845916748
2023-01-21 10:35:19.138630: step: 176/531, loss: 0.02084369584918022
2023-01-21 10:35:20.290789: step: 180/531, loss: 0.020826244726777077
2023-01-21 10:35:21.443061: step: 184/531, loss: 0.026675987988710403
2023-01-21 10:35:22.577125: step: 188/531, loss: 0.0576656349003315
2023-01-21 10:35:23.736756: step: 192/531, loss: 0.09280738979578018
2023-01-21 10:35:24.876562: step: 196/531, loss: 0.21827135980129242
2023-01-21 10:35:25.998865: step: 200/531, loss: 0.05327282100915909
2023-01-21 10:35:27.130623: step: 204/531, loss: 0.033853866159915924
2023-01-21 10:35:28.273884: step: 208/531, loss: 0.08336200565099716
2023-01-21 10:35:29.431273: step: 212/531, loss: 0.012221718207001686
2023-01-21 10:35:30.604892: step: 216/531, loss: 0.012851571664214134
2023-01-21 10:35:31.739412: step: 220/531, loss: 0.008442306891083717
2023-01-21 10:35:32.898840: step: 224/531, loss: 0.025832366198301315
2023-01-21 10:35:34.021096: step: 228/531, loss: 0.020372772589325905
2023-01-21 10:35:35.140394: step: 232/531, loss: 0.034896086901426315
2023-01-21 10:35:36.282111: step: 236/531, loss: 0.0697927474975586
2023-01-21 10:35:37.403282: step: 240/531, loss: 0.038404084742069244
2023-01-21 10:35:38.541262: step: 244/531, loss: 0.028582381084561348
2023-01-21 10:35:39.675662: step: 248/531, loss: 0.09015293419361115
2023-01-21 10:35:40.787182: step: 252/531, loss: 0.006644725799560547
2023-01-21 10:35:41.946169: step: 256/531, loss: 0.04751196131110191
2023-01-21 10:35:43.082590: step: 260/531, loss: 0.30338409543037415
2023-01-21 10:35:44.263143: step: 264/531, loss: 0.018543099984526634
2023-01-21 10:35:45.400638: step: 268/531, loss: 0.0506771095097065
2023-01-21 10:35:46.532013: step: 272/531, loss: 0.005135345738381147
2023-01-21 10:35:47.667393: step: 276/531, loss: 0.01716327667236328
2023-01-21 10:35:48.831877: step: 280/531, loss: 0.26174649596214294
2023-01-21 10:35:49.997284: step: 284/531, loss: 0.036356449127197266
2023-01-21 10:35:51.126944: step: 288/531, loss: 0.006159747019410133
2023-01-21 10:35:52.285406: step: 292/531, loss: 0.046012308448553085
2023-01-21 10:35:53.435830: step: 296/531, loss: 0.09360122680664062
2023-01-21 10:35:54.562290: step: 300/531, loss: 0.006849479861557484
2023-01-21 10:35:55.701889: step: 304/531, loss: 0.14085274934768677
2023-01-21 10:35:56.843991: step: 308/531, loss: 0.03922691196203232
2023-01-21 10:35:58.000286: step: 312/531, loss: 0.02872176095843315
2023-01-21 10:35:59.179645: step: 316/531, loss: 0.032641030848026276
2023-01-21 10:36:00.345981: step: 320/531, loss: 0.052202798426151276
2023-01-21 10:36:01.502620: step: 324/531, loss: 0.034711744636297226
2023-01-21 10:36:02.662723: step: 328/531, loss: 0.1793808937072754
2023-01-21 10:36:03.815991: step: 332/531, loss: 0.017008112743496895
2023-01-21 10:36:04.971037: step: 336/531, loss: 0.052149295806884766
2023-01-21 10:36:06.126196: step: 340/531, loss: 0.05364866554737091
2023-01-21 10:36:07.295670: step: 344/531, loss: 0.09223794937133789
2023-01-21 10:36:08.443346: step: 348/531, loss: 0.019942283630371094
2023-01-21 10:36:09.610434: step: 352/531, loss: 0.04162969812750816
2023-01-21 10:36:10.761332: step: 356/531, loss: 0.041677091270685196
2023-01-21 10:36:11.935670: step: 360/531, loss: 0.06603717803955078
2023-01-21 10:36:13.079313: step: 364/531, loss: 0.008761358447372913
2023-01-21 10:36:14.223325: step: 368/531, loss: 0.11486272513866425
2023-01-21 10:36:15.350604: step: 372/531, loss: 0.10126963257789612
2023-01-21 10:36:16.507338: step: 376/531, loss: 0.01708240434527397
2023-01-21 10:36:17.673921: step: 380/531, loss: 0.004142189398407936
2023-01-21 10:36:18.803592: step: 384/531, loss: 0.00884018000215292
2023-01-21 10:36:19.950601: step: 388/531, loss: 0.01080484502017498
2023-01-21 10:36:21.110052: step: 392/531, loss: 0.019925978034734726
2023-01-21 10:36:22.242376: step: 396/531, loss: 0.011363506317138672
2023-01-21 10:36:23.383457: step: 400/531, loss: 0.1028587818145752
2023-01-21 10:36:24.520512: step: 404/531, loss: 0.04232080280780792
2023-01-21 10:36:25.680326: step: 408/531, loss: 0.2529030740261078
2023-01-21 10:36:26.833928: step: 412/531, loss: 0.015860557556152344
2023-01-21 10:36:27.963205: step: 416/531, loss: 0.03498277813196182
2023-01-21 10:36:29.089466: step: 420/531, loss: 0.14679089188575745
2023-01-21 10:36:30.235760: step: 424/531, loss: 0.02433185651898384
2023-01-21 10:36:31.388069: step: 428/531, loss: 0.025880241766572
2023-01-21 10:36:32.498596: step: 432/531, loss: 0.048050880432128906
2023-01-21 10:36:33.653582: step: 436/531, loss: 0.021410560235381126
2023-01-21 10:36:34.798881: step: 440/531, loss: 0.06916351616382599
2023-01-21 10:36:35.988991: step: 444/531, loss: 0.06000576168298721
2023-01-21 10:36:37.132239: step: 448/531, loss: 0.013830471783876419
2023-01-21 10:36:38.279019: step: 452/531, loss: 0.05849146842956543
2023-01-21 10:36:39.408666: step: 456/531, loss: 0.030888844281435013
2023-01-21 10:36:40.522210: step: 460/531, loss: 0.04168892279267311
2023-01-21 10:36:41.646790: step: 464/531, loss: 0.053305864334106445
2023-01-21 10:36:42.808330: step: 468/531, loss: 0.0145600326359272
2023-01-21 10:36:43.952378: step: 472/531, loss: 0.014923286624252796
2023-01-21 10:36:45.083784: step: 476/531, loss: 0.02691326104104519
2023-01-21 10:36:46.231116: step: 480/531, loss: 0.04722227901220322
2023-01-21 10:36:47.378950: step: 484/531, loss: 0.01708083227276802
2023-01-21 10:36:48.502036: step: 488/531, loss: 0.0630342960357666
2023-01-21 10:36:49.653325: step: 492/531, loss: 0.0018398285610601306
2023-01-21 10:36:50.784448: step: 496/531, loss: 0.0629514679312706
2023-01-21 10:36:51.948439: step: 500/531, loss: 0.009606361389160156
2023-01-21 10:36:53.075582: step: 504/531, loss: 0.00251941685564816
2023-01-21 10:36:54.213215: step: 508/531, loss: 0.05768918991088867
2023-01-21 10:36:55.372405: step: 512/531, loss: 0.005676459986716509
2023-01-21 10:36:56.534344: step: 516/531, loss: 0.033266447484493256
2023-01-21 10:36:57.706081: step: 520/531, loss: 0.05728187412023544
2023-01-21 10:36:58.872007: step: 524/531, loss: 0.23796996474266052
2023-01-21 10:37:00.014650: step: 528/531, loss: 0.04635239019989967
2023-01-21 10:37:01.166021: step: 532/531, loss: 0.1938735991716385
2023-01-21 10:37:02.356450: step: 536/531, loss: 0.048374176025390625
2023-01-21 10:37:03.516832: step: 540/531, loss: 0.04418602213263512
2023-01-21 10:37:04.636022: step: 544/531, loss: 0.023776818066835403
2023-01-21 10:37:05.788801: step: 548/531, loss: 0.02112445794045925
2023-01-21 10:37:06.911860: step: 552/531, loss: 0.012280656024813652
2023-01-21 10:37:08.048205: step: 556/531, loss: 0.056977175176143646
2023-01-21 10:37:09.169634: step: 560/531, loss: 0.10055427998304367
2023-01-21 10:37:10.297107: step: 564/531, loss: 0.012489033862948418
2023-01-21 10:37:11.434022: step: 568/531, loss: 0.06431732326745987
2023-01-21 10:37:12.571669: step: 572/531, loss: 0.01454234216362238
2023-01-21 10:37:13.723607: step: 576/531, loss: 0.010251638479530811
2023-01-21 10:37:14.864654: step: 580/531, loss: 0.013840293511748314
2023-01-21 10:37:16.017068: step: 584/531, loss: 0.036703046411275864
2023-01-21 10:37:17.139228: step: 588/531, loss: 0.07474103569984436
2023-01-21 10:37:18.321535: step: 592/531, loss: 0.06297874450683594
2023-01-21 10:37:19.461575: step: 596/531, loss: 0.1341439187526703
2023-01-21 10:37:20.584399: step: 600/531, loss: 0.011738300323486328
2023-01-21 10:37:21.708910: step: 604/531, loss: 0.06567726284265518
2023-01-21 10:37:22.840647: step: 608/531, loss: 0.01404562033712864
2023-01-21 10:37:24.011638: step: 612/531, loss: 0.11313267052173615
2023-01-21 10:37:25.153542: step: 616/531, loss: 0.012928009033203125
2023-01-21 10:37:26.283227: step: 620/531, loss: 0.07304663956165314
2023-01-21 10:37:27.402903: step: 624/531, loss: 0.02281656302511692
2023-01-21 10:37:28.571847: step: 628/531, loss: 0.024804305285215378
2023-01-21 10:37:29.755128: step: 632/531, loss: 0.07919197529554367
2023-01-21 10:37:30.912854: step: 636/531, loss: 0.09788642078638077
2023-01-21 10:37:32.051255: step: 640/531, loss: 0.17398062348365784
2023-01-21 10:37:33.200058: step: 644/531, loss: 0.03532905876636505
2023-01-21 10:37:34.337859: step: 648/531, loss: 0.04142698645591736
2023-01-21 10:37:35.479785: step: 652/531, loss: 0.022336864843964577
2023-01-21 10:37:36.631565: step: 656/531, loss: 0.1160479336977005
2023-01-21 10:37:37.804225: step: 660/531, loss: 0.01974334754049778
2023-01-21 10:37:38.939881: step: 664/531, loss: 0.08427486568689346
2023-01-21 10:37:40.069126: step: 668/531, loss: 0.056188393384218216
2023-01-21 10:37:41.222278: step: 672/531, loss: 0.03814134746789932
2023-01-21 10:37:42.389385: step: 676/531, loss: 0.009484196081757545
2023-01-21 10:37:43.540139: step: 680/531, loss: 0.11058798432350159
2023-01-21 10:37:44.707786: step: 684/531, loss: 0.002372360322624445
2023-01-21 10:37:45.852464: step: 688/531, loss: 0.004443073645234108
2023-01-21 10:37:47.011143: step: 692/531, loss: 0.018896352499723434
2023-01-21 10:37:48.152933: step: 696/531, loss: 0.1435987502336502
2023-01-21 10:37:49.273975: step: 700/531, loss: 0.00687332171946764
2023-01-21 10:37:50.406888: step: 704/531, loss: 0.04493732377886772
2023-01-21 10:37:51.580606: step: 708/531, loss: 0.030828284099698067
2023-01-21 10:37:52.723510: step: 712/531, loss: 0.10376262664794922
2023-01-21 10:37:53.886144: step: 716/531, loss: 0.027099132537841797
2023-01-21 10:37:55.010996: step: 720/531, loss: 0.0434780977666378
2023-01-21 10:37:56.144935: step: 724/531, loss: 0.06284217536449432
2023-01-21 10:37:57.307816: step: 728/531, loss: 0.14878997206687927
2023-01-21 10:37:58.446040: step: 732/531, loss: 0.03637829050421715
2023-01-21 10:37:59.585538: step: 736/531, loss: 0.025745106860995293
2023-01-21 10:38:00.734434: step: 740/531, loss: 0.0034799575805664062
2023-01-21 10:38:01.893080: step: 744/531, loss: 0.11501456052064896
2023-01-21 10:38:03.022986: step: 748/531, loss: 0.02026224136352539
2023-01-21 10:38:04.152122: step: 752/531, loss: 0.008418465033173561
2023-01-21 10:38:05.269186: step: 756/531, loss: 0.022331953048706055
2023-01-21 10:38:06.441631: step: 760/531, loss: 0.0366579033434391
2023-01-21 10:38:07.611138: step: 764/531, loss: 0.005731010343879461
2023-01-21 10:38:08.751016: step: 768/531, loss: 0.05093841627240181
2023-01-21 10:38:09.891916: step: 772/531, loss: 0.019498253241181374
2023-01-21 10:38:11.075795: step: 776/531, loss: 0.049474529922008514
2023-01-21 10:38:12.235274: step: 780/531, loss: 0.006289434619247913
2023-01-21 10:38:13.377762: step: 784/531, loss: 0.044103339314460754
2023-01-21 10:38:14.504572: step: 788/531, loss: 0.059922412037849426
2023-01-21 10:38:15.669209: step: 792/531, loss: 0.014417696744203568
2023-01-21 10:38:16.813296: step: 796/531, loss: 0.0026498795486986637
2023-01-21 10:38:17.963068: step: 800/531, loss: 0.03474941477179527
2023-01-21 10:38:19.112052: step: 804/531, loss: 0.01415939349681139
2023-01-21 10:38:20.272626: step: 808/531, loss: 0.051536086946725845
2023-01-21 10:38:21.427580: step: 812/531, loss: 0.4574885368347168
2023-01-21 10:38:22.573356: step: 816/531, loss: 0.040415383875370026
2023-01-21 10:38:23.709349: step: 820/531, loss: 0.012056541629135609
2023-01-21 10:38:24.876759: step: 824/531, loss: 0.030512237921357155
2023-01-21 10:38:26.009449: step: 828/531, loss: 0.015198040753602982
2023-01-21 10:38:27.138846: step: 832/531, loss: 0.023713206872344017
2023-01-21 10:38:28.317996: step: 836/531, loss: 0.04139909893274307
2023-01-21 10:38:29.447534: step: 840/531, loss: 0.021001243963837624
2023-01-21 10:38:30.586951: step: 844/531, loss: 0.0702524185180664
2023-01-21 10:38:31.739424: step: 848/531, loss: 0.052890945225954056
2023-01-21 10:38:32.925330: step: 852/531, loss: 0.011954927816987038
2023-01-21 10:38:34.051606: step: 856/531, loss: 0.028821755200624466
2023-01-21 10:38:35.214148: step: 860/531, loss: 0.0012111187679693103
2023-01-21 10:38:36.391842: step: 864/531, loss: 0.007202529814094305
2023-01-21 10:38:37.501867: step: 868/531, loss: 0.0023280144669115543
2023-01-21 10:38:38.658354: step: 872/531, loss: 0.4859399199485779
2023-01-21 10:38:39.827976: step: 876/531, loss: 0.08663120865821838
2023-01-21 10:38:40.980205: step: 880/531, loss: 0.019716953858733177
2023-01-21 10:38:42.132236: step: 884/531, loss: 0.06647635996341705
2023-01-21 10:38:43.255643: step: 888/531, loss: 0.021984290331602097
2023-01-21 10:38:44.440409: step: 892/531, loss: 0.017107294872403145
2023-01-21 10:38:45.561681: step: 896/531, loss: 0.0345836877822876
2023-01-21 10:38:46.723638: step: 900/531, loss: 0.05378246307373047
2023-01-21 10:38:47.866651: step: 904/531, loss: 0.02114563062787056
2023-01-21 10:38:49.006080: step: 908/531, loss: 0.026821112260222435
2023-01-21 10:38:50.129004: step: 912/531, loss: 0.0363890640437603
2023-01-21 10:38:51.248740: step: 916/531, loss: 0.03604002296924591
2023-01-21 10:38:52.405914: step: 920/531, loss: 0.026711082085967064
2023-01-21 10:38:53.549508: step: 924/531, loss: 0.08712110668420792
2023-01-21 10:38:54.749699: step: 928/531, loss: 0.46248742938041687
2023-01-21 10:38:55.895962: step: 932/531, loss: 0.030457021668553352
2023-01-21 10:38:57.049602: step: 936/531, loss: 0.0970296859741211
2023-01-21 10:38:58.186292: step: 940/531, loss: 0.027438737452030182
2023-01-21 10:38:59.294042: step: 944/531, loss: 0.029915904626250267
2023-01-21 10:39:00.431751: step: 948/531, loss: 0.027980666607618332
2023-01-21 10:39:01.587561: step: 952/531, loss: 0.10565929859876633
2023-01-21 10:39:02.726694: step: 956/531, loss: 0.06206989288330078
2023-01-21 10:39:03.841083: step: 960/531, loss: 0.08147916942834854
2023-01-21 10:39:04.998393: step: 964/531, loss: 0.014317680150270462
2023-01-21 10:39:06.137498: step: 968/531, loss: 0.04774452745914459
2023-01-21 10:39:07.314969: step: 972/531, loss: 0.008439827710390091
2023-01-21 10:39:08.432674: step: 976/531, loss: 0.02240018919110298
2023-01-21 10:39:09.590470: step: 980/531, loss: 0.09134330600500107
2023-01-21 10:39:10.768439: step: 984/531, loss: 0.006825447082519531
2023-01-21 10:39:11.935244: step: 988/531, loss: 0.050775717943906784
2023-01-21 10:39:13.091774: step: 992/531, loss: 0.01884746551513672
2023-01-21 10:39:14.232229: step: 996/531, loss: 0.10304941982030869
2023-01-21 10:39:15.397744: step: 1000/531, loss: 0.06675796210765839
2023-01-21 10:39:16.558742: step: 1004/531, loss: 0.01001830119639635
2023-01-21 10:39:17.708333: step: 1008/531, loss: 0.004202842712402344
2023-01-21 10:39:18.831180: step: 1012/531, loss: 0.04262109100818634
2023-01-21 10:39:19.975290: step: 1016/531, loss: 0.0853450819849968
2023-01-21 10:39:21.101310: step: 1020/531, loss: 0.10220298916101456
2023-01-21 10:39:22.265647: step: 1024/531, loss: 0.03408947214484215
2023-01-21 10:39:23.399577: step: 1028/531, loss: 0.10641252994537354
2023-01-21 10:39:24.589462: step: 1032/531, loss: 0.027832651510834694
2023-01-21 10:39:25.755966: step: 1036/531, loss: 0.698275625705719
2023-01-21 10:39:26.921204: step: 1040/531, loss: 0.09946541488170624
2023-01-21 10:39:28.039087: step: 1044/531, loss: 0.03708686679601669
2023-01-21 10:39:29.167637: step: 1048/531, loss: 0.022433269768953323
2023-01-21 10:39:30.318142: step: 1052/531, loss: 0.025570297613739967
2023-01-21 10:39:31.477243: step: 1056/531, loss: 0.10999850928783417
2023-01-21 10:39:32.615270: step: 1060/531, loss: 0.0662631019949913
2023-01-21 10:39:33.750483: step: 1064/531, loss: 0.01800365373492241
2023-01-21 10:39:34.923045: step: 1068/531, loss: 0.002541160676628351
2023-01-21 10:39:36.045291: step: 1072/531, loss: 0.012896394357085228
2023-01-21 10:39:37.209733: step: 1076/531, loss: 0.03825845941901207
2023-01-21 10:39:38.380504: step: 1080/531, loss: 0.05021210014820099
2023-01-21 10:39:39.505358: step: 1084/531, loss: 0.05231847986578941
2023-01-21 10:39:40.653502: step: 1088/531, loss: 0.16162744164466858
2023-01-21 10:39:41.788669: step: 1092/531, loss: 0.11827889084815979
2023-01-21 10:39:42.986987: step: 1096/531, loss: 0.019343852996826172
2023-01-21 10:39:44.140166: step: 1100/531, loss: 0.03673610836267471
2023-01-21 10:39:45.291045: step: 1104/531, loss: 0.0640331283211708
2023-01-21 10:39:46.454525: step: 1108/531, loss: 0.07004113495349884
2023-01-21 10:39:47.592134: step: 1112/531, loss: 0.02098817750811577
2023-01-21 10:39:48.720002: step: 1116/531, loss: 0.007976197637617588
2023-01-21 10:39:49.877595: step: 1120/531, loss: 0.01597442664206028
2023-01-21 10:39:51.043806: step: 1124/531, loss: 0.016730977222323418
2023-01-21 10:39:52.176348: step: 1128/531, loss: 0.04646758735179901
2023-01-21 10:39:53.315206: step: 1132/531, loss: 0.031763769686222076
2023-01-21 10:39:54.439563: step: 1136/531, loss: 0.03558769449591637
2023-01-21 10:39:55.567896: step: 1140/531, loss: 0.04510064423084259
2023-01-21 10:39:56.692866: step: 1144/531, loss: 0.047937989234924316
2023-01-21 10:39:57.843347: step: 1148/531, loss: 0.05689249187707901
2023-01-21 10:39:58.984522: step: 1152/531, loss: 0.2007051408290863
2023-01-21 10:40:00.127909: step: 1156/531, loss: 0.014181804843246937
2023-01-21 10:40:01.264294: step: 1160/531, loss: 0.0476049929857254
2023-01-21 10:40:02.434713: step: 1164/531, loss: 0.15232238173484802
2023-01-21 10:40:03.598216: step: 1168/531, loss: 0.04912414774298668
2023-01-21 10:40:04.737933: step: 1172/531, loss: 0.022928999736905098
2023-01-21 10:40:05.891920: step: 1176/531, loss: 0.08101377636194229
2023-01-21 10:40:07.029308: step: 1180/531, loss: 0.008741283789277077
2023-01-21 10:40:08.193837: step: 1184/531, loss: 0.10629777610301971
2023-01-21 10:40:09.352068: step: 1188/531, loss: 0.1857776939868927
2023-01-21 10:40:10.516687: step: 1192/531, loss: 0.02162330225110054
2023-01-21 10:40:11.648836: step: 1196/531, loss: 0.02423687092959881
2023-01-21 10:40:12.782481: step: 1200/531, loss: 0.0004979983204975724
2023-01-21 10:40:13.922782: step: 1204/531, loss: 0.00899505615234375
2023-01-21 10:40:15.064315: step: 1208/531, loss: 0.0004848003445658833
2023-01-21 10:40:16.284570: step: 1212/531, loss: 0.04509296268224716
2023-01-21 10:40:17.446080: step: 1216/531, loss: 0.06766834855079651
2023-01-21 10:40:18.607750: step: 1220/531, loss: 0.02234821207821369
2023-01-21 10:40:19.785371: step: 1224/531, loss: 0.20259609818458557
2023-01-21 10:40:20.921221: step: 1228/531, loss: 0.1478653848171234
2023-01-21 10:40:22.050939: step: 1232/531, loss: 0.01733102649450302
2023-01-21 10:40:23.172641: step: 1236/531, loss: 0.07483520358800888
2023-01-21 10:40:24.330036: step: 1240/531, loss: 0.028918646275997162
2023-01-21 10:40:25.497487: step: 1244/531, loss: 0.09021492302417755
2023-01-21 10:40:26.659987: step: 1248/531, loss: 0.04510708153247833
2023-01-21 10:40:27.798968: step: 1252/531, loss: 0.03388190269470215
2023-01-21 10:40:28.961049: step: 1256/531, loss: 0.07007598876953125
2023-01-21 10:40:30.107785: step: 1260/531, loss: 0.003340053604915738
2023-01-21 10:40:31.229176: step: 1264/531, loss: 0.012237166985869408
2023-01-21 10:40:32.362000: step: 1268/531, loss: 0.008912467397749424
2023-01-21 10:40:33.472264: step: 1272/531, loss: 0.00470013590529561
2023-01-21 10:40:34.612376: step: 1276/531, loss: 0.07364121079444885
2023-01-21 10:40:35.777433: step: 1280/531, loss: 0.0245390422642231
2023-01-21 10:40:36.916142: step: 1284/531, loss: 0.05048947408795357
2023-01-21 10:40:38.062580: step: 1288/531, loss: 0.009117030538618565
2023-01-21 10:40:39.196178: step: 1292/531, loss: 0.009619617834687233
2023-01-21 10:40:40.341583: step: 1296/531, loss: 0.014437627978622913
2023-01-21 10:40:41.493645: step: 1300/531, loss: 0.14535284042358398
2023-01-21 10:40:42.678717: step: 1304/531, loss: 0.012126964516937733
2023-01-21 10:40:43.832546: step: 1308/531, loss: 0.017809296026825905
2023-01-21 10:40:45.013775: step: 1312/531, loss: 0.046889498829841614
2023-01-21 10:40:46.129081: step: 1316/531, loss: 0.09406042098999023
2023-01-21 10:40:47.267300: step: 1320/531, loss: 0.9882091879844666
2023-01-21 10:40:48.406939: step: 1324/531, loss: 0.020993998274207115
2023-01-21 10:40:49.539122: step: 1328/531, loss: 0.06654224544763565
2023-01-21 10:40:50.725817: step: 1332/531, loss: 1.1802095174789429
2023-01-21 10:40:51.855909: step: 1336/531, loss: 0.06622724235057831
2023-01-21 10:40:52.993256: step: 1340/531, loss: 0.09898719936609268
2023-01-21 10:40:54.140579: step: 1344/531, loss: 0.07313279807567596
2023-01-21 10:40:55.259785: step: 1348/531, loss: 0.029189683496952057
2023-01-21 10:40:56.416009: step: 1352/531, loss: 0.023584628477692604
2023-01-21 10:40:57.591256: step: 1356/531, loss: 0.07253327965736389
2023-01-21 10:40:58.743132: step: 1360/531, loss: 0.016899872571229935
2023-01-21 10:40:59.904843: step: 1364/531, loss: 0.023358821868896484
2023-01-21 10:41:01.052805: step: 1368/531, loss: 0.02863626554608345
2023-01-21 10:41:02.172708: step: 1372/531, loss: 0.03712787479162216
2023-01-21 10:41:03.301379: step: 1376/531, loss: 0.01287236250936985
2023-01-21 10:41:04.505802: step: 1380/531, loss: 0.044175148010253906
2023-01-21 10:41:05.669608: step: 1384/531, loss: 0.009384251199662685
2023-01-21 10:41:06.796821: step: 1388/531, loss: 0.015148353762924671
2023-01-21 10:41:07.942906: step: 1392/531, loss: 0.18818068504333496
2023-01-21 10:41:09.082544: step: 1396/531, loss: 0.06886816024780273
2023-01-21 10:41:10.239590: step: 1400/531, loss: 0.04330310598015785
2023-01-21 10:41:11.384046: step: 1404/531, loss: 0.14418324828147888
2023-01-21 10:41:12.472781: step: 1408/531, loss: 0.040449973195791245
2023-01-21 10:41:13.616430: step: 1412/531, loss: 0.15003032982349396
2023-01-21 10:41:14.743575: step: 1416/531, loss: 0.04059848561882973
2023-01-21 10:41:15.888285: step: 1420/531, loss: 0.02403726615011692
2023-01-21 10:41:17.052077: step: 1424/531, loss: 0.014409065246582031
2023-01-21 10:41:18.187281: step: 1428/531, loss: 0.021810341626405716
2023-01-21 10:41:19.313115: step: 1432/531, loss: 0.03038501739501953
2023-01-21 10:41:20.478597: step: 1436/531, loss: 0.03841428458690643
2023-01-21 10:41:21.617945: step: 1440/531, loss: 0.05535269156098366
2023-01-21 10:41:22.752178: step: 1444/531, loss: 0.027306556701660156
2023-01-21 10:41:23.887527: step: 1448/531, loss: 0.018312575295567513
2023-01-21 10:41:25.020955: step: 1452/531, loss: 0.15522870421409607
2023-01-21 10:41:26.167480: step: 1456/531, loss: 0.12756776809692383
2023-01-21 10:41:27.291567: step: 1460/531, loss: 0.00010938644845737144
2023-01-21 10:41:28.441753: step: 1464/531, loss: 0.06287985295057297
2023-01-21 10:41:29.579225: step: 1468/531, loss: 0.000268960022367537
2023-01-21 10:41:30.706450: step: 1472/531, loss: 0.04957442358136177
2023-01-21 10:41:31.840152: step: 1476/531, loss: 0.019331075251102448
2023-01-21 10:41:32.988362: step: 1480/531, loss: 0.08308392018079758
2023-01-21 10:41:34.140407: step: 1484/531, loss: 0.0050862194038927555
2023-01-21 10:41:35.290872: step: 1488/531, loss: 0.02396850660443306
2023-01-21 10:41:36.430311: step: 1492/531, loss: 0.017570162191987038
2023-01-21 10:41:37.554444: step: 1496/531, loss: 0.2160778045654297
2023-01-21 10:41:38.683115: step: 1500/531, loss: 0.01109619066119194
2023-01-21 10:41:39.818130: step: 1504/531, loss: 0.04328777641057968
2023-01-21 10:41:40.986803: step: 1508/531, loss: 0.008468151092529297
2023-01-21 10:41:42.137767: step: 1512/531, loss: 0.05934581905603409
2023-01-21 10:41:43.272448: step: 1516/531, loss: 0.045438673347234726
2023-01-21 10:41:44.408797: step: 1520/531, loss: 0.02972431294620037
2023-01-21 10:41:45.528678: step: 1524/531, loss: 0.018481923267245293
2023-01-21 10:41:46.663942: step: 1528/531, loss: 0.008174611255526543
2023-01-21 10:41:47.778855: step: 1532/531, loss: 0.015534305945038795
2023-01-21 10:41:48.897443: step: 1536/531, loss: 0.056647732853889465
2023-01-21 10:41:50.064900: step: 1540/531, loss: 0.012342738918960094
2023-01-21 10:41:51.204950: step: 1544/531, loss: 0.0005943298456259072
2023-01-21 10:41:52.382207: step: 1548/531, loss: 0.03918495029211044
2023-01-21 10:41:53.529367: step: 1552/531, loss: 0.0056892395950853825
2023-01-21 10:41:54.667719: step: 1556/531, loss: 0.06790996342897415
2023-01-21 10:41:55.793107: step: 1560/531, loss: 0.0029452084563672543
2023-01-21 10:41:56.979537: step: 1564/531, loss: 0.19618378579616547
2023-01-21 10:41:58.098438: step: 1568/531, loss: 0.010821056552231312
2023-01-21 10:41:59.231847: step: 1572/531, loss: 0.007067108526825905
2023-01-21 10:42:00.368556: step: 1576/531, loss: 0.07634472846984863
2023-01-21 10:42:01.526225: step: 1580/531, loss: 0.020088767632842064
2023-01-21 10:42:02.699318: step: 1584/531, loss: 0.032546043395996094
2023-01-21 10:42:03.844687: step: 1588/531, loss: 0.006006479263305664
2023-01-21 10:42:04.963139: step: 1592/531, loss: 0.001477956771850586
2023-01-21 10:42:06.121997: step: 1596/531, loss: 0.09744921326637268
2023-01-21 10:42:07.258354: step: 1600/531, loss: 0.07438497245311737
2023-01-21 10:42:08.371669: step: 1604/531, loss: 0.07650060951709747
2023-01-21 10:42:09.490418: step: 1608/531, loss: 0.10595346242189407
2023-01-21 10:42:10.642422: step: 1612/531, loss: 0.06526460498571396
2023-01-21 10:42:11.774217: step: 1616/531, loss: 0.09192466735839844
2023-01-21 10:42:12.931978: step: 1620/531, loss: 0.04222307354211807
2023-01-21 10:42:14.078249: step: 1624/531, loss: 0.010996311902999878
2023-01-21 10:42:15.209852: step: 1628/531, loss: 0.009233546443283558
2023-01-21 10:42:16.349848: step: 1632/531, loss: 0.04507913440465927
2023-01-21 10:42:17.492354: step: 1636/531, loss: 0.11485419422388077
2023-01-21 10:42:18.631343: step: 1640/531, loss: 0.0775420218706131
2023-01-21 10:42:19.790741: step: 1644/531, loss: 0.10292492061853409
2023-01-21 10:42:20.923564: step: 1648/531, loss: 0.006024551577866077
2023-01-21 10:42:22.067268: step: 1652/531, loss: 0.02397298812866211
2023-01-21 10:42:23.202023: step: 1656/531, loss: 0.1017235815525055
2023-01-21 10:42:24.348624: step: 1660/531, loss: 0.06056041643023491
2023-01-21 10:42:25.530784: step: 1664/531, loss: 0.13555994629859924
2023-01-21 10:42:26.679613: step: 1668/531, loss: 0.06228942796587944
2023-01-21 10:42:27.798212: step: 1672/531, loss: 0.07841825485229492
2023-01-21 10:42:28.946730: step: 1676/531, loss: 0.05848198011517525
2023-01-21 10:42:30.092000: step: 1680/531, loss: 0.0036527158226817846
2023-01-21 10:42:31.244366: step: 1684/531, loss: 0.0028963088989257812
2023-01-21 10:42:32.377317: step: 1688/531, loss: 0.08239364624023438
2023-01-21 10:42:33.521095: step: 1692/531, loss: 0.012074685655534267
2023-01-21 10:42:34.665718: step: 1696/531, loss: 0.04532909393310547
2023-01-21 10:42:35.822188: step: 1700/531, loss: 0.0305391326546669
2023-01-21 10:42:36.938647: step: 1704/531, loss: 0.04217987135052681
2023-01-21 10:42:38.072184: step: 1708/531, loss: 0.07543668895959854
2023-01-21 10:42:39.239502: step: 1712/531, loss: 0.06074810028076172
2023-01-21 10:42:40.362280: step: 1716/531, loss: 0.021434593945741653
2023-01-21 10:42:41.523872: step: 1720/531, loss: 0.05495748668909073
2023-01-21 10:42:42.706676: step: 1724/531, loss: 0.05599823221564293
2023-01-21 10:42:43.848051: step: 1728/531, loss: 0.011588573455810547
2023-01-21 10:42:44.972010: step: 1732/531, loss: 0.013997411355376244
2023-01-21 10:42:46.120405: step: 1736/531, loss: 0.030081558972597122
2023-01-21 10:42:47.268208: step: 1740/531, loss: 0.08217716217041016
2023-01-21 10:42:48.416630: step: 1744/531, loss: 0.10544148087501526
2023-01-21 10:42:49.559182: step: 1748/531, loss: 0.015371656976640224
2023-01-21 10:42:50.706929: step: 1752/531, loss: 0.37945443391799927
2023-01-21 10:42:51.830056: step: 1756/531, loss: 0.07821617275476456
2023-01-21 10:42:52.956888: step: 1760/531, loss: 0.08327965438365936
2023-01-21 10:42:54.145692: step: 1764/531, loss: 0.018086720257997513
2023-01-21 10:42:55.271774: step: 1768/531, loss: 0.05119304731488228
2023-01-21 10:42:56.456954: step: 1772/531, loss: 0.010021782480180264
2023-01-21 10:42:57.625074: step: 1776/531, loss: 0.052277565002441406
2023-01-21 10:42:58.790612: step: 1780/531, loss: 0.12825989723205566
2023-01-21 10:42:59.957762: step: 1784/531, loss: 0.0018489838112145662
2023-01-21 10:43:01.103340: step: 1788/531, loss: 0.03022794798016548
2023-01-21 10:43:02.243505: step: 1792/531, loss: 0.042185403406620026
2023-01-21 10:43:03.376790: step: 1796/531, loss: 0.03956933319568634
2023-01-21 10:43:04.487197: step: 1800/531, loss: 0.03247842937707901
2023-01-21 10:43:05.645814: step: 1804/531, loss: 0.0048469542525708675
2023-01-21 10:43:06.775927: step: 1808/531, loss: 0.013456583023071289
2023-01-21 10:43:07.936517: step: 1812/531, loss: 0.005601215176284313
2023-01-21 10:43:09.089263: step: 1816/531, loss: 0.025394631549715996
2023-01-21 10:43:10.223778: step: 1820/531, loss: 0.02357044257223606
2023-01-21 10:43:11.348342: step: 1824/531, loss: 0.01884479634463787
2023-01-21 10:43:12.473035: step: 1828/531, loss: 0.001811218331567943
2023-01-21 10:43:13.624294: step: 1832/531, loss: 0.024689625948667526
2023-01-21 10:43:14.748557: step: 1836/531, loss: 0.05257987976074219
2023-01-21 10:43:15.902419: step: 1840/531, loss: 0.01757230795919895
2023-01-21 10:43:17.078265: step: 1844/531, loss: 0.006537914741784334
2023-01-21 10:43:18.227047: step: 1848/531, loss: 0.11457739770412445
2023-01-21 10:43:19.423014: step: 1852/531, loss: 0.05506391450762749
2023-01-21 10:43:20.575455: step: 1856/531, loss: 0.012675618752837181
2023-01-21 10:43:21.726469: step: 1860/531, loss: 0.032007407397031784
2023-01-21 10:43:22.898578: step: 1864/531, loss: 0.029535962268710136
2023-01-21 10:43:24.026451: step: 1868/531, loss: 0.01293954811990261
2023-01-21 10:43:25.184073: step: 1872/531, loss: 0.0346558578312397
2023-01-21 10:43:26.337644: step: 1876/531, loss: 0.060494616627693176
2023-01-21 10:43:27.481135: step: 1880/531, loss: 0.05873880535364151
2023-01-21 10:43:28.653106: step: 1884/531, loss: 0.13491840660572052
2023-01-21 10:43:29.776950: step: 1888/531, loss: 0.45614093542099
2023-01-21 10:43:30.904979: step: 1892/531, loss: 0.08778896182775497
2023-01-21 10:43:32.053681: step: 1896/531, loss: 0.08901634812355042
2023-01-21 10:43:33.213259: step: 1900/531, loss: 0.02306346967816353
2023-01-21 10:43:34.383480: step: 1904/531, loss: 0.004037666600197554
2023-01-21 10:43:35.534357: step: 1908/531, loss: 0.12361335754394531
2023-01-21 10:43:36.705147: step: 1912/531, loss: 0.02625408209860325
2023-01-21 10:43:37.898250: step: 1916/531, loss: 0.11926212161779404
2023-01-21 10:43:39.047993: step: 1920/531, loss: 0.06683167815208435
2023-01-21 10:43:40.213959: step: 1924/531, loss: 0.03842058405280113
2023-01-21 10:43:41.350850: step: 1928/531, loss: 0.0680788978934288
2023-01-21 10:43:42.495099: step: 1932/531, loss: 0.01659870147705078
2023-01-21 10:43:43.651018: step: 1936/531, loss: 0.008098411373794079
2023-01-21 10:43:44.819411: step: 1940/531, loss: 0.013364476151764393
2023-01-21 10:43:45.980120: step: 1944/531, loss: 0.24418029189109802
2023-01-21 10:43:47.135655: step: 1948/531, loss: 0.008128595538437366
2023-01-21 10:43:48.290826: step: 1952/531, loss: 0.10405979305505753
2023-01-21 10:43:49.410116: step: 1956/531, loss: 0.018499184399843216
2023-01-21 10:43:50.557797: step: 1960/531, loss: 0.00597461499273777
2023-01-21 10:43:51.696396: step: 1964/531, loss: 0.035898495465517044
2023-01-21 10:43:52.837028: step: 1968/531, loss: 0.03136706352233887
2023-01-21 10:43:53.963537: step: 1972/531, loss: 0.05230360105633736
2023-01-21 10:43:55.101420: step: 1976/531, loss: 0.013293028809130192
2023-01-21 10:43:56.227722: step: 1980/531, loss: 0.011597824282944202
2023-01-21 10:43:57.371888: step: 1984/531, loss: 0.0887262374162674
2023-01-21 10:43:58.523763: step: 1988/531, loss: 0.06823473423719406
2023-01-21 10:43:59.676096: step: 1992/531, loss: 0.047307778149843216
2023-01-21 10:44:00.813473: step: 1996/531, loss: 0.04340305179357529
2023-01-21 10:44:01.967462: step: 2000/531, loss: 0.0034839629661291838
2023-01-21 10:44:03.126219: step: 2004/531, loss: 0.05612316355109215
2023-01-21 10:44:04.266661: step: 2008/531, loss: 0.054436493664979935
2023-01-21 10:44:05.442880: step: 2012/531, loss: 0.05939092859625816
2023-01-21 10:44:06.586873: step: 2016/531, loss: 0.01971726305782795
2023-01-21 10:44:07.711568: step: 2020/531, loss: 0.024842167273163795
2023-01-21 10:44:08.853285: step: 2024/531, loss: 0.02219834364950657
2023-01-21 10:44:10.021906: step: 2028/531, loss: 0.04516439512372017
2023-01-21 10:44:11.164351: step: 2032/531, loss: 0.018895531073212624
2023-01-21 10:44:12.328497: step: 2036/531, loss: 0.05838470533490181
2023-01-21 10:44:13.480499: step: 2040/531, loss: 0.04346800222992897
2023-01-21 10:44:14.617228: step: 2044/531, loss: 0.05949802324175835
2023-01-21 10:44:15.769229: step: 2048/531, loss: 0.06024212762713432
2023-01-21 10:44:16.922162: step: 2052/531, loss: 0.15944595634937286
2023-01-21 10:44:18.075130: step: 2056/531, loss: 0.07171754539012909
2023-01-21 10:44:19.233869: step: 2060/531, loss: 0.04210929945111275
2023-01-21 10:44:20.376101: step: 2064/531, loss: 0.049760058522224426
2023-01-21 10:44:21.564154: step: 2068/531, loss: 0.07243957370519638
2023-01-21 10:44:22.718634: step: 2072/531, loss: 0.04726238176226616
2023-01-21 10:44:23.858564: step: 2076/531, loss: 0.002039241837337613
2023-01-21 10:44:24.975806: step: 2080/531, loss: 0.0020648480858653784
2023-01-21 10:44:26.115724: step: 2084/531, loss: 0.10527076572179794
2023-01-21 10:44:27.262693: step: 2088/531, loss: 0.02209148369729519
2023-01-21 10:44:28.396272: step: 2092/531, loss: 0.023993873968720436
2023-01-21 10:44:29.569384: step: 2096/531, loss: 0.02828502655029297
2023-01-21 10:44:30.718475: step: 2100/531, loss: 0.026215743273496628
2023-01-21 10:44:31.881113: step: 2104/531, loss: 0.008970832452178001
2023-01-21 10:44:33.010697: step: 2108/531, loss: 0.1338087022304535
2023-01-21 10:44:34.148378: step: 2112/531, loss: 0.037584494799375534
2023-01-21 10:44:35.284910: step: 2116/531, loss: 0.01471557654440403
2023-01-21 10:44:36.489075: step: 2120/531, loss: 0.006036948878318071
2023-01-21 10:44:37.642162: step: 2124/531, loss: 0.1139741912484169
==================================================
Loss: 0.059
--------------------
Dev: {'event': {'p': 0.5975733063700708, 'r': 0.7869507323568575, 'f1': 0.6793103448275862}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6186242395882078, 'r': 0.7883124627310674, 'f1': 0.6932354483481908}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
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': 12}
Korean: {'event': {'p': 0.7169811320754716, 'r': 0.6031746031746031, 'f1': 0.6551724137931034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.4666666666666667, 'r': 0.5833333333333334, 'f1': 0.5185185185185186}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5975733063700708, 'r': 0.7869507323568575, 'f1': 0.6793103448275862}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6186242395882078, 'r': 0.7883124627310674, 'f1': 0.6932354483481908}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7169811320754716, 'r': 0.6031746031746031, 'f1': 0.6551724137931034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:45:28.701993: step: 4/531, loss: 0.03342418745160103
2023-01-21 10:45:29.819104: step: 8/531, loss: 0.07771588116884232
2023-01-21 10:45:30.959869: step: 12/531, loss: 0.0912843719124794
2023-01-21 10:45:32.106516: step: 16/531, loss: 0.054195791482925415
2023-01-21 10:45:33.223810: step: 20/531, loss: 0.06615810096263885
2023-01-21 10:45:34.345452: step: 24/531, loss: 0.018315888941287994
2023-01-21 10:45:35.501739: step: 28/531, loss: 0.006016540806740522
2023-01-21 10:45:36.704223: step: 32/531, loss: 0.059362128376960754
2023-01-21 10:45:37.859051: step: 36/531, loss: 0.01581754721701145
2023-01-21 10:45:38.999373: step: 40/531, loss: 0.10967950522899628
2023-01-21 10:45:40.179083: step: 44/531, loss: 0.04458465427160263
2023-01-21 10:45:41.299132: step: 48/531, loss: 0.05173778533935547
2023-01-21 10:45:42.464170: step: 52/531, loss: 0.014670658856630325
2023-01-21 10:45:43.598060: step: 56/531, loss: 0.007902145385742188
2023-01-21 10:45:44.742568: step: 60/531, loss: 0.03858385235071182
2023-01-21 10:45:45.914079: step: 64/531, loss: 0.1147555336356163
2023-01-21 10:45:47.071544: step: 68/531, loss: 0.00781016331166029
2023-01-21 10:45:48.198390: step: 72/531, loss: 0.029988668859004974
2023-01-21 10:45:49.302598: step: 76/531, loss: 0.17744828760623932
2023-01-21 10:45:50.440614: step: 80/531, loss: 0.010762691497802734
2023-01-21 10:45:51.568619: step: 84/531, loss: 0.002446174854412675
2023-01-21 10:45:52.723606: step: 88/531, loss: 0.29659736156463623
2023-01-21 10:45:53.829059: step: 92/531, loss: 0.054776858538389206
2023-01-21 10:45:54.969756: step: 96/531, loss: 0.03169412538409233
2023-01-21 10:45:56.060721: step: 100/531, loss: 0.011609840206801891
2023-01-21 10:45:57.187389: step: 104/531, loss: 0.04917926713824272
2023-01-21 10:45:58.327565: step: 108/531, loss: 0.026915669441223145
2023-01-21 10:45:59.545052: step: 112/531, loss: 0.030089378356933594
2023-01-21 10:46:00.684363: step: 116/531, loss: 0.036695003509521484
2023-01-21 10:46:01.848039: step: 120/531, loss: 0.6868606805801392
2023-01-21 10:46:03.002336: step: 124/531, loss: 0.05361232906579971
2023-01-21 10:46:04.133436: step: 128/531, loss: 0.04308462515473366
2023-01-21 10:46:05.290326: step: 132/531, loss: 0.05794540420174599
2023-01-21 10:46:06.431107: step: 136/531, loss: 0.009990166872739792
2023-01-21 10:46:07.559092: step: 140/531, loss: 0.01703043095767498
2023-01-21 10:46:08.719164: step: 144/531, loss: 0.023775434121489525
2023-01-21 10:46:09.857438: step: 148/531, loss: 0.0005966186872683465
2023-01-21 10:46:10.991083: step: 152/531, loss: 0.008697127923369408
2023-01-21 10:46:12.134036: step: 156/531, loss: 0.05570597946643829
2023-01-21 10:46:13.287921: step: 160/531, loss: 0.03552570194005966
2023-01-21 10:46:14.444956: step: 164/531, loss: 0.030355453491210938
2023-01-21 10:46:15.554086: step: 168/531, loss: 0.19229717552661896
2023-01-21 10:46:16.684683: step: 172/531, loss: 0.0591767318546772
2023-01-21 10:46:17.826113: step: 176/531, loss: 0.020240116864442825
2023-01-21 10:46:18.994199: step: 180/531, loss: 0.04676008224487305
2023-01-21 10:46:20.148924: step: 184/531, loss: 0.0069724079221487045
2023-01-21 10:46:21.292231: step: 188/531, loss: 0.030846787616610527
2023-01-21 10:46:22.452200: step: 192/531, loss: 0.008553886786103249
2023-01-21 10:46:23.661434: step: 196/531, loss: 0.07150917500257492
2023-01-21 10:46:24.778810: step: 200/531, loss: 0.0016655921936035156
2023-01-21 10:46:25.892708: step: 204/531, loss: 0.03125810623168945
2023-01-21 10:46:27.018690: step: 208/531, loss: 0.17051377892494202
2023-01-21 10:46:28.164158: step: 212/531, loss: 0.044175341725349426
2023-01-21 10:46:29.334179: step: 216/531, loss: 0.0743008628487587
2023-01-21 10:46:30.476224: step: 220/531, loss: 0.04328365623950958
2023-01-21 10:46:31.619460: step: 224/531, loss: 0.013271236792206764
2023-01-21 10:46:32.791266: step: 228/531, loss: 0.010369528084993362
2023-01-21 10:46:33.920272: step: 232/531, loss: 0.0013322352897375822
2023-01-21 10:46:35.085703: step: 236/531, loss: 0.06214666739106178
2023-01-21 10:46:36.243142: step: 240/531, loss: 0.23943157494068146
2023-01-21 10:46:37.381982: step: 244/531, loss: 0.002432918641716242
2023-01-21 10:46:38.508482: step: 248/531, loss: 0.022056009620428085
2023-01-21 10:46:39.636193: step: 252/531, loss: 0.04144277423620224
2023-01-21 10:46:40.769224: step: 256/531, loss: 0.039461899548769
2023-01-21 10:46:41.938063: step: 260/531, loss: 0.020702458918094635
2023-01-21 10:46:43.103797: step: 264/531, loss: 0.0020713568665087223
2023-01-21 10:46:44.317378: step: 268/531, loss: 0.024099208414554596
2023-01-21 10:46:45.456421: step: 272/531, loss: 0.014520073309540749
2023-01-21 10:46:46.562810: step: 276/531, loss: 0.046061232686042786
2023-01-21 10:46:47.675104: step: 280/531, loss: 0.011994361877441406
2023-01-21 10:46:48.831877: step: 284/531, loss: 0.003659582231193781
2023-01-21 10:46:49.977390: step: 288/531, loss: 0.05892801284790039
2023-01-21 10:46:51.137446: step: 292/531, loss: 0.05326499789953232
2023-01-21 10:46:52.303738: step: 296/531, loss: 0.021243762224912643
2023-01-21 10:46:53.473164: step: 300/531, loss: 0.00707664480432868
2023-01-21 10:46:54.632878: step: 304/531, loss: 0.04495277628302574
2023-01-21 10:46:55.784429: step: 308/531, loss: 0.11237473785877228
2023-01-21 10:46:56.917662: step: 312/531, loss: 0.005398750305175781
2023-01-21 10:46:58.070384: step: 316/531, loss: 0.051763586699962616
2023-01-21 10:46:59.205286: step: 320/531, loss: 0.017431069165468216
2023-01-21 10:47:00.384541: step: 324/531, loss: 0.01579895056784153
2023-01-21 10:47:01.507404: step: 328/531, loss: 0.04519863426685333
2023-01-21 10:47:02.652676: step: 332/531, loss: 0.079498291015625
2023-01-21 10:47:03.761644: step: 336/531, loss: 0.009938192553818226
2023-01-21 10:47:04.909719: step: 340/531, loss: 0.01903686486184597
2023-01-21 10:47:06.038138: step: 344/531, loss: 0.018907546997070312
2023-01-21 10:47:07.223288: step: 348/531, loss: 0.17576994001865387
2023-01-21 10:47:08.360237: step: 352/531, loss: 0.4193234443664551
2023-01-21 10:47:09.479811: step: 356/531, loss: 0.00028274653595872223
2023-01-21 10:47:10.623650: step: 360/531, loss: 0.0034258842933923006
2023-01-21 10:47:11.740751: step: 364/531, loss: 0.09827709197998047
2023-01-21 10:47:12.935883: step: 368/531, loss: 0.021271612495183945
2023-01-21 10:47:14.065460: step: 372/531, loss: 0.08587093651294708
2023-01-21 10:47:15.186214: step: 376/531, loss: 0.00026340485783293843
2023-01-21 10:47:16.316485: step: 380/531, loss: 0.027202893048524857
2023-01-21 10:47:17.404526: step: 384/531, loss: 0.0027251243591308594
2023-01-21 10:47:18.599295: step: 388/531, loss: 0.09790420532226562
2023-01-21 10:47:19.759602: step: 392/531, loss: 0.04433570057153702
2023-01-21 10:47:20.887463: step: 396/531, loss: 0.04228248819708824
2023-01-21 10:47:22.020377: step: 400/531, loss: 0.0013032912975177169
2023-01-21 10:47:23.156796: step: 404/531, loss: 0.07800416648387909
2023-01-21 10:47:24.299875: step: 408/531, loss: 0.010413790121674538
2023-01-21 10:47:25.428408: step: 412/531, loss: 0.08815765380859375
2023-01-21 10:47:26.571945: step: 416/531, loss: 0.01145267579704523
2023-01-21 10:47:27.736176: step: 420/531, loss: 0.030092386528849602
2023-01-21 10:47:28.916455: step: 424/531, loss: 0.030657770112156868
2023-01-21 10:47:30.070824: step: 428/531, loss: 0.07740054279565811
2023-01-21 10:47:31.210987: step: 432/531, loss: 0.013010883703827858
2023-01-21 10:47:32.376695: step: 436/531, loss: 0.036742210388183594
2023-01-21 10:47:33.518599: step: 440/531, loss: 0.027120592072606087
2023-01-21 10:47:34.665482: step: 444/531, loss: 0.030752800405025482
2023-01-21 10:47:35.814917: step: 448/531, loss: 0.012925815768539906
2023-01-21 10:47:36.957365: step: 452/531, loss: 0.07271194458007812
2023-01-21 10:47:38.121581: step: 456/531, loss: 0.00043334963265806437
2023-01-21 10:47:39.279704: step: 460/531, loss: 0.0144494054839015
2023-01-21 10:47:40.477473: step: 464/531, loss: 0.01098709087818861
2023-01-21 10:47:41.672641: step: 468/531, loss: 0.009502887725830078
2023-01-21 10:47:42.820650: step: 472/531, loss: 0.00017833709716796875
2023-01-21 10:47:43.942475: step: 476/531, loss: 0.03253984451293945
2023-01-21 10:47:45.119237: step: 480/531, loss: 0.021430017426609993
2023-01-21 10:47:46.273296: step: 484/531, loss: 0.0014138699043542147
2023-01-21 10:47:47.415110: step: 488/531, loss: 0.05034312978386879
2023-01-21 10:47:48.572556: step: 492/531, loss: 0.009504175744950771
2023-01-21 10:47:49.705578: step: 496/531, loss: 0.03173184394836426
2023-01-21 10:47:50.866441: step: 500/531, loss: 0.007869720458984375
2023-01-21 10:47:51.991945: step: 504/531, loss: 0.0459136962890625
2023-01-21 10:47:53.170189: step: 508/531, loss: 0.002742767333984375
2023-01-21 10:47:54.322444: step: 512/531, loss: 0.7011368274688721
2023-01-21 10:47:55.467411: step: 516/531, loss: 0.15821295976638794
2023-01-21 10:47:56.612868: step: 520/531, loss: 0.02230234071612358
2023-01-21 10:47:57.762678: step: 524/531, loss: 0.006270122714340687
2023-01-21 10:47:58.923325: step: 528/531, loss: 0.09530754387378693
2023-01-21 10:48:00.078143: step: 532/531, loss: 0.1895495355129242
2023-01-21 10:48:01.234517: step: 536/531, loss: 0.002535009291023016
2023-01-21 10:48:02.414050: step: 540/531, loss: 0.13452157378196716
2023-01-21 10:48:03.562905: step: 544/531, loss: 0.030552292242646217
2023-01-21 10:48:04.691146: step: 548/531, loss: 0.01806468889117241
2023-01-21 10:48:05.809890: step: 552/531, loss: 0.04686622694134712
2023-01-21 10:48:06.939963: step: 556/531, loss: 0.01401600893586874
2023-01-21 10:48:08.086932: step: 560/531, loss: 0.010833073407411575
2023-01-21 10:48:09.262758: step: 564/531, loss: 0.022986507043242455
2023-01-21 10:48:10.413463: step: 568/531, loss: 0.16372212767601013
2023-01-21 10:48:11.557121: step: 572/531, loss: 0.037123680114746094
2023-01-21 10:48:12.744422: step: 576/531, loss: 0.056557562202215195
2023-01-21 10:48:13.897423: step: 580/531, loss: 0.02711467817425728
2023-01-21 10:48:15.046089: step: 584/531, loss: 0.002179050352424383
2023-01-21 10:48:16.216097: step: 588/531, loss: 0.01753520965576172
2023-01-21 10:48:17.337186: step: 592/531, loss: 0.013611030764877796
2023-01-21 10:48:18.475586: step: 596/531, loss: 0.005151939578354359
2023-01-21 10:48:19.621647: step: 600/531, loss: 0.026070812717080116
2023-01-21 10:48:20.760831: step: 604/531, loss: 0.0047456263564527035
2023-01-21 10:48:21.973635: step: 608/531, loss: 0.09499035030603409
2023-01-21 10:48:23.102639: step: 612/531, loss: 0.039414893835783005
2023-01-21 10:48:24.223179: step: 616/531, loss: 0.08239135891199112
2023-01-21 10:48:25.358982: step: 620/531, loss: 0.02663116529583931
2023-01-21 10:48:26.496222: step: 624/531, loss: 0.06980671733617783
2023-01-21 10:48:27.639635: step: 628/531, loss: 0.15307196974754333
2023-01-21 10:48:28.806219: step: 632/531, loss: 0.08188334107398987
2023-01-21 10:48:29.935662: step: 636/531, loss: 0.05046458542346954
2023-01-21 10:48:31.100965: step: 640/531, loss: 0.007607633247971535
2023-01-21 10:48:32.236258: step: 644/531, loss: 0.005102729890495539
2023-01-21 10:48:33.400329: step: 648/531, loss: 0.024686718359589577
2023-01-21 10:48:34.526286: step: 652/531, loss: 0.023961687460541725
2023-01-21 10:48:35.650627: step: 656/531, loss: 0.06716085970401764
2023-01-21 10:48:36.779557: step: 660/531, loss: 0.0819934830069542
2023-01-21 10:48:37.932690: step: 664/531, loss: 0.10636787116527557
2023-01-21 10:48:39.077459: step: 668/531, loss: 0.03016195259988308
2023-01-21 10:48:40.207965: step: 672/531, loss: 0.02282133139669895
2023-01-21 10:48:41.377942: step: 676/531, loss: 0.01348643284291029
2023-01-21 10:48:42.575202: step: 680/531, loss: 0.08069805800914764
2023-01-21 10:48:43.696877: step: 684/531, loss: 0.01345887128263712
2023-01-21 10:48:44.869971: step: 688/531, loss: 0.021828461438417435
2023-01-21 10:48:46.010097: step: 692/531, loss: 0.008779001422226429
2023-01-21 10:48:47.172433: step: 696/531, loss: 0.03604163974523544
2023-01-21 10:48:48.302393: step: 700/531, loss: 0.0004502296505961567
2023-01-21 10:48:49.419556: step: 704/531, loss: 0.026473237201571465
2023-01-21 10:48:50.558002: step: 708/531, loss: 0.14528588950634003
2023-01-21 10:48:51.679475: step: 712/531, loss: 0.005115794949233532
2023-01-21 10:48:52.842001: step: 716/531, loss: 0.04945025593042374
2023-01-21 10:48:53.987340: step: 720/531, loss: 0.00409355154260993
2023-01-21 10:48:55.117443: step: 724/531, loss: 0.113672636449337
2023-01-21 10:48:56.286839: step: 728/531, loss: 0.020709609612822533
2023-01-21 10:48:57.466830: step: 732/531, loss: 0.0019387244246900082
2023-01-21 10:48:58.622082: step: 736/531, loss: 0.10363052040338516
2023-01-21 10:48:59.780544: step: 740/531, loss: 0.0933326706290245
2023-01-21 10:49:00.955762: step: 744/531, loss: 0.05928096920251846
2023-01-21 10:49:02.114144: step: 748/531, loss: 0.050866417586803436
2023-01-21 10:49:03.238669: step: 752/531, loss: 0.04574146121740341
2023-01-21 10:49:04.398760: step: 756/531, loss: 0.002296352293342352
2023-01-21 10:49:05.533835: step: 760/531, loss: 0.010215855203568935
2023-01-21 10:49:06.686207: step: 764/531, loss: 0.0519988052546978
2023-01-21 10:49:07.843424: step: 768/531, loss: 0.06496325135231018
2023-01-21 10:49:08.952366: step: 772/531, loss: 0.0005624771001748741
2023-01-21 10:49:10.115532: step: 776/531, loss: 6.814003427280113e-05
2023-01-21 10:49:11.301886: step: 780/531, loss: 1.06647527217865
2023-01-21 10:49:12.449214: step: 784/531, loss: 0.11282125115394592
2023-01-21 10:49:13.620322: step: 788/531, loss: 0.04966096952557564
2023-01-21 10:49:14.757605: step: 792/531, loss: 0.053189992904663086
2023-01-21 10:49:15.922862: step: 796/531, loss: 0.08382201194763184
2023-01-21 10:49:17.063260: step: 800/531, loss: 0.017506027594208717
2023-01-21 10:49:18.216162: step: 804/531, loss: 0.030462075024843216
2023-01-21 10:49:19.334640: step: 808/531, loss: 0.14633405208587646
2023-01-21 10:49:20.487704: step: 812/531, loss: 0.006342947483062744
2023-01-21 10:49:21.625161: step: 816/531, loss: 0.022717952728271484
2023-01-21 10:49:22.737822: step: 820/531, loss: 0.06884551048278809
2023-01-21 10:49:23.878818: step: 824/531, loss: 0.0024641992058604956
2023-01-21 10:49:25.024619: step: 828/531, loss: 0.02037644386291504
2023-01-21 10:49:26.136528: step: 832/531, loss: 0.0428725965321064
2023-01-21 10:49:27.283220: step: 836/531, loss: 0.0067348480224609375
2023-01-21 10:49:28.395773: step: 840/531, loss: 0.02822294272482395
2023-01-21 10:49:29.577645: step: 844/531, loss: 0.03486766666173935
2023-01-21 10:49:30.736273: step: 848/531, loss: 0.04856691509485245
2023-01-21 10:49:31.882528: step: 852/531, loss: 0.02101593092083931
2023-01-21 10:49:33.020845: step: 856/531, loss: 0.00337810511700809
2023-01-21 10:49:34.174995: step: 860/531, loss: 0.01625833660364151
2023-01-21 10:49:35.308048: step: 864/531, loss: 0.05743622034788132
2023-01-21 10:49:36.448110: step: 868/531, loss: 0.020027637481689453
2023-01-21 10:49:37.615625: step: 872/531, loss: 0.01802702061831951
2023-01-21 10:49:38.736115: step: 876/531, loss: 0.004216098692268133
2023-01-21 10:49:39.871659: step: 880/531, loss: 0.0009114265558309853
2023-01-21 10:49:40.998092: step: 884/531, loss: 0.0012843608856201172
2023-01-21 10:49:42.165098: step: 888/531, loss: 0.0017143726581707597
2023-01-21 10:49:43.329404: step: 892/531, loss: 0.0466671958565712
2023-01-21 10:49:44.467625: step: 896/531, loss: 0.0147438058629632
2023-01-21 10:49:45.591528: step: 900/531, loss: 0.030875110998749733
2023-01-21 10:49:46.741191: step: 904/531, loss: 0.0057347300462424755
2023-01-21 10:49:47.875347: step: 908/531, loss: 0.0002476215304341167
2023-01-21 10:49:49.014137: step: 912/531, loss: 0.1649744063615799
2023-01-21 10:49:50.169936: step: 916/531, loss: 0.007166576571762562
2023-01-21 10:49:51.328582: step: 920/531, loss: 0.043772414326667786
2023-01-21 10:49:52.455085: step: 924/531, loss: 0.045702554285526276
2023-01-21 10:49:53.576970: step: 928/531, loss: 0.01107478141784668
2023-01-21 10:49:54.696383: step: 932/531, loss: 0.03981318324804306
2023-01-21 10:49:55.821361: step: 936/531, loss: 0.0013188362354412675
2023-01-21 10:49:56.952012: step: 940/531, loss: 0.017920970916748047
2023-01-21 10:49:58.071947: step: 944/531, loss: 0.006014728918671608
2023-01-21 10:49:59.206799: step: 948/531, loss: 0.02703695371747017
2023-01-21 10:50:00.353786: step: 952/531, loss: 0.03177695348858833
2023-01-21 10:50:01.484665: step: 956/531, loss: 0.002156543778255582
2023-01-21 10:50:02.617723: step: 960/531, loss: 0.03146219253540039
2023-01-21 10:50:03.761604: step: 964/531, loss: 0.13395065069198608
2023-01-21 10:50:04.926436: step: 968/531, loss: 0.028921127319335938
2023-01-21 10:50:06.087985: step: 972/531, loss: 0.011514521203935146
2023-01-21 10:50:07.243644: step: 976/531, loss: 0.029919244349002838
2023-01-21 10:50:08.373444: step: 980/531, loss: 0.012060356326401234
2023-01-21 10:50:09.565487: step: 984/531, loss: 0.0004733085515908897
2023-01-21 10:50:10.732706: step: 988/531, loss: 0.06068840250372887
2023-01-21 10:50:11.897256: step: 992/531, loss: 0.03981971740722656
2023-01-21 10:50:13.024461: step: 996/531, loss: 0.02660827711224556
2023-01-21 10:50:14.144780: step: 1000/531, loss: 0.04644432291388512
2023-01-21 10:50:15.286054: step: 1004/531, loss: 0.037888504564762115
2023-01-21 10:50:16.466710: step: 1008/531, loss: 0.017255783081054688
2023-01-21 10:50:17.637478: step: 1012/531, loss: 0.027460671961307526
2023-01-21 10:50:18.784687: step: 1016/531, loss: 0.02686481550335884
2023-01-21 10:50:19.935921: step: 1020/531, loss: 0.014597893692553043
2023-01-21 10:50:21.077970: step: 1024/531, loss: 0.1491573452949524
2023-01-21 10:50:22.212130: step: 1028/531, loss: 0.03290205076336861
2023-01-21 10:50:23.337717: step: 1032/531, loss: 0.06254692375659943
2023-01-21 10:50:24.487424: step: 1036/531, loss: 0.12329020351171494
2023-01-21 10:50:25.640898: step: 1040/531, loss: 0.019033242017030716
2023-01-21 10:50:26.777562: step: 1044/531, loss: 0.03615732118487358
2023-01-21 10:50:27.923271: step: 1048/531, loss: 0.35037410259246826
2023-01-21 10:50:29.059197: step: 1052/531, loss: 0.02108621597290039
2023-01-21 10:50:30.203373: step: 1056/531, loss: 0.013318061828613281
2023-01-21 10:50:31.366039: step: 1060/531, loss: 0.029770758002996445
2023-01-21 10:50:32.519068: step: 1064/531, loss: 0.9443221092224121
2023-01-21 10:50:33.671769: step: 1068/531, loss: 0.03894639015197754
2023-01-21 10:50:34.846814: step: 1072/531, loss: 0.018570804968476295
2023-01-21 10:50:36.020245: step: 1076/531, loss: 0.27470168471336365
2023-01-21 10:50:37.132428: step: 1080/531, loss: 0.035878945142030716
2023-01-21 10:50:38.259651: step: 1084/531, loss: 0.04985857009887695
2023-01-21 10:50:39.394635: step: 1088/531, loss: 0.04064450040459633
2023-01-21 10:50:40.549106: step: 1092/531, loss: 0.0366833433508873
2023-01-21 10:50:41.682851: step: 1096/531, loss: 0.018360327929258347
2023-01-21 10:50:42.816390: step: 1100/531, loss: 0.0041765691712498665
2023-01-21 10:50:43.985482: step: 1104/531, loss: 0.17107433080673218
2023-01-21 10:50:45.141883: step: 1108/531, loss: 0.0321531780064106
2023-01-21 10:50:46.303604: step: 1112/531, loss: 0.1062128096818924
2023-01-21 10:50:47.488513: step: 1116/531, loss: 0.08963050693273544
2023-01-21 10:50:48.642844: step: 1120/531, loss: 0.004250717349350452
2023-01-21 10:50:49.785323: step: 1124/531, loss: 0.004715165589004755
2023-01-21 10:50:50.914925: step: 1128/531, loss: 0.03357705846428871
2023-01-21 10:50:52.075372: step: 1132/531, loss: 0.062082864344120026
2023-01-21 10:50:53.205794: step: 1136/531, loss: 0.009208345785737038
2023-01-21 10:50:54.379523: step: 1140/531, loss: 0.0702420249581337
2023-01-21 10:50:55.505378: step: 1144/531, loss: 0.003314399626106024
2023-01-21 10:50:56.634634: step: 1148/531, loss: 0.06663379818201065
2023-01-21 10:50:57.776072: step: 1152/531, loss: 0.016517065465450287
2023-01-21 10:50:58.917677: step: 1156/531, loss: 0.03861271217465401
2023-01-21 10:51:00.048742: step: 1160/531, loss: 0.006167793646454811
2023-01-21 10:51:01.210053: step: 1164/531, loss: 0.040250446647405624
2023-01-21 10:51:02.343275: step: 1168/531, loss: 0.033430956304073334
2023-01-21 10:51:03.478226: step: 1172/531, loss: 0.05916253849864006
2023-01-21 10:51:04.594077: step: 1176/531, loss: 0.004074668977409601
2023-01-21 10:51:05.762517: step: 1180/531, loss: 0.04831714555621147
2023-01-21 10:51:06.899046: step: 1184/531, loss: 0.07649173587560654
2023-01-21 10:51:08.071023: step: 1188/531, loss: 0.03734779357910156
2023-01-21 10:51:09.198338: step: 1192/531, loss: 0.061502739787101746
2023-01-21 10:51:10.344623: step: 1196/531, loss: 0.02992735058069229
2023-01-21 10:51:11.498840: step: 1200/531, loss: 0.04019127041101456
2023-01-21 10:51:12.659068: step: 1204/531, loss: 0.030754853039979935
2023-01-21 10:51:13.819623: step: 1208/531, loss: 0.009923934936523438
2023-01-21 10:51:15.019261: step: 1212/531, loss: 0.002894782926887274
2023-01-21 10:51:16.153910: step: 1216/531, loss: 0.055169105529785156
2023-01-21 10:51:17.300399: step: 1220/531, loss: 0.011361360549926758
2023-01-21 10:51:18.487148: step: 1224/531, loss: 0.018093539401888847
2023-01-21 10:51:19.662281: step: 1228/531, loss: 0.19842030107975006
2023-01-21 10:51:20.805970: step: 1232/531, loss: 0.009335804730653763
2023-01-21 10:51:21.969137: step: 1236/531, loss: 0.009306621737778187
2023-01-21 10:51:23.126099: step: 1240/531, loss: 0.0045677185989916325
2023-01-21 10:51:24.277604: step: 1244/531, loss: 0.10325918346643448
2023-01-21 10:51:25.418627: step: 1248/531, loss: 0.03712606430053711
2023-01-21 10:51:26.602621: step: 1252/531, loss: 0.0374598503112793
2023-01-21 10:51:27.779249: step: 1256/531, loss: 0.040802858769893646
2023-01-21 10:51:28.899905: step: 1260/531, loss: 0.017055416479706764
2023-01-21 10:51:30.046138: step: 1264/531, loss: 0.0450318343937397
2023-01-21 10:51:31.223807: step: 1268/531, loss: 0.0011103630531579256
2023-01-21 10:51:32.360771: step: 1272/531, loss: 0.017812538892030716
2023-01-21 10:51:33.500542: step: 1276/531, loss: 0.06374111771583557
2023-01-21 10:51:34.640646: step: 1280/531, loss: 0.06870412826538086
2023-01-21 10:51:35.764659: step: 1284/531, loss: 0.0009293556213378906
2023-01-21 10:51:36.888966: step: 1288/531, loss: 0.036452438682317734
2023-01-21 10:51:38.049340: step: 1292/531, loss: 0.16871647536754608
2023-01-21 10:51:39.192107: step: 1296/531, loss: 0.003957176115363836
2023-01-21 10:51:40.336004: step: 1300/531, loss: 0.027661800384521484
2023-01-21 10:51:41.514158: step: 1304/531, loss: 0.02792814001441002
2023-01-21 10:51:42.658938: step: 1308/531, loss: 0.03123478963971138
2023-01-21 10:51:43.789200: step: 1312/531, loss: 0.017508696764707565
2023-01-21 10:51:44.943381: step: 1316/531, loss: 0.04125919193029404
2023-01-21 10:51:46.035112: step: 1320/531, loss: 0.001905298326164484
2023-01-21 10:51:47.190378: step: 1324/531, loss: 0.06160926818847656
2023-01-21 10:51:48.310038: step: 1328/531, loss: 0.043677713721990585
2023-01-21 10:51:49.438941: step: 1332/531, loss: 0.06846804916858673
2023-01-21 10:51:50.586362: step: 1336/531, loss: 0.03277721628546715
2023-01-21 10:51:51.747086: step: 1340/531, loss: 0.022041525691747665
2023-01-21 10:51:52.890388: step: 1344/531, loss: 0.1207401230931282
2023-01-21 10:51:54.040486: step: 1348/531, loss: 0.026521779596805573
2023-01-21 10:51:55.212786: step: 1352/531, loss: 0.0005992889637127519
2023-01-21 10:51:56.378441: step: 1356/531, loss: 0.03614196926355362
2023-01-21 10:51:57.516549: step: 1360/531, loss: 0.00382575998082757
2023-01-21 10:51:58.645838: step: 1364/531, loss: 0.04001769796013832
2023-01-21 10:51:59.799023: step: 1368/531, loss: 0.002760982606559992
2023-01-21 10:52:01.008306: step: 1372/531, loss: 0.07854413986206055
2023-01-21 10:52:02.174212: step: 1376/531, loss: 0.045685771852731705
2023-01-21 10:52:03.313233: step: 1380/531, loss: 0.014691734686493874
2023-01-21 10:52:04.454802: step: 1384/531, loss: 0.05945310741662979
2023-01-21 10:52:05.569864: step: 1388/531, loss: 0.07075748592615128
2023-01-21 10:52:06.703994: step: 1392/531, loss: 0.07616720348596573
2023-01-21 10:52:07.847046: step: 1396/531, loss: 0.02531905099749565
2023-01-21 10:52:08.981111: step: 1400/531, loss: 0.48334693908691406
2023-01-21 10:52:10.129758: step: 1404/531, loss: 0.012325716204941273
2023-01-21 10:52:11.264751: step: 1408/531, loss: 0.008347606286406517
2023-01-21 10:52:12.418402: step: 1412/531, loss: 0.004252273123711348
2023-01-21 10:52:13.567276: step: 1416/531, loss: 0.0286438949406147
2023-01-21 10:52:14.698799: step: 1420/531, loss: 0.042565345764160156
2023-01-21 10:52:15.812851: step: 1424/531, loss: 0.006934451870620251
2023-01-21 10:52:16.976230: step: 1428/531, loss: 0.06696367263793945
2023-01-21 10:52:18.129768: step: 1432/531, loss: 0.01389846857637167
2023-01-21 10:52:19.295007: step: 1436/531, loss: 0.012557793408632278
2023-01-21 10:52:20.440736: step: 1440/531, loss: 0.006352805998176336
2023-01-21 10:52:21.588038: step: 1444/531, loss: 0.06379108130931854
2023-01-21 10:52:22.747139: step: 1448/531, loss: 0.051972150802612305
2023-01-21 10:52:23.868238: step: 1452/531, loss: 0.05340252071619034
2023-01-21 10:52:25.071846: step: 1456/531, loss: 0.07439880073070526
2023-01-21 10:52:26.234453: step: 1460/531, loss: 0.039669036865234375
2023-01-21 10:52:27.392006: step: 1464/531, loss: 0.04984131082892418
2023-01-21 10:52:28.522355: step: 1468/531, loss: 0.0027611255645751953
2023-01-21 10:52:29.700265: step: 1472/531, loss: 0.02588520012795925
2023-01-21 10:52:30.833709: step: 1476/531, loss: 0.0415501594543457
2023-01-21 10:52:31.950872: step: 1480/531, loss: 0.012391758151352406
2023-01-21 10:52:33.101260: step: 1484/531, loss: 0.07968264073133469
2023-01-21 10:52:34.232422: step: 1488/531, loss: 0.15641066431999207
2023-01-21 10:52:35.371076: step: 1492/531, loss: 0.09167805314064026
2023-01-21 10:52:36.515733: step: 1496/531, loss: 0.00865640677511692
2023-01-21 10:52:37.642818: step: 1500/531, loss: 0.0176880843937397
2023-01-21 10:52:38.781471: step: 1504/531, loss: 0.13483381271362305
2023-01-21 10:52:39.934501: step: 1508/531, loss: 0.00993204116821289
2023-01-21 10:52:41.088340: step: 1512/531, loss: 0.05060825124382973
2023-01-21 10:52:42.220375: step: 1516/531, loss: 0.03865347057580948
2023-01-21 10:52:43.333744: step: 1520/531, loss: 1.930574655532837
2023-01-21 10:52:44.467520: step: 1524/531, loss: 0.012262584641575813
2023-01-21 10:52:45.593795: step: 1528/531, loss: 0.02584686316549778
2023-01-21 10:52:46.751634: step: 1532/531, loss: 0.15780936181545258
2023-01-21 10:52:47.913854: step: 1536/531, loss: 0.0006384849548339844
2023-01-21 10:52:49.070295: step: 1540/531, loss: 0.12546196579933167
2023-01-21 10:52:50.188566: step: 1544/531, loss: 0.026625968515872955
2023-01-21 10:52:51.337875: step: 1548/531, loss: 0.00419273367151618
2023-01-21 10:52:52.502424: step: 1552/531, loss: 0.004591727163642645
2023-01-21 10:52:53.653119: step: 1556/531, loss: 0.03328075259923935
2023-01-21 10:52:54.809950: step: 1560/531, loss: 0.008942950516939163
2023-01-21 10:52:55.933457: step: 1564/531, loss: 0.09567117691040039
2023-01-21 10:52:57.073892: step: 1568/531, loss: 0.07516632974147797
2023-01-21 10:52:58.195802: step: 1572/531, loss: 0.008822822943329811
2023-01-21 10:52:59.354683: step: 1576/531, loss: 0.011792660690844059
2023-01-21 10:53:00.495855: step: 1580/531, loss: 0.04632125049829483
2023-01-21 10:53:01.666193: step: 1584/531, loss: 0.03399048373103142
2023-01-21 10:53:02.841721: step: 1588/531, loss: 0.05758104473352432
2023-01-21 10:53:03.978929: step: 1592/531, loss: 0.4461662173271179
2023-01-21 10:53:05.099648: step: 1596/531, loss: 0.1877305954694748
2023-01-21 10:53:06.258178: step: 1600/531, loss: 0.012031174264848232
2023-01-21 10:53:07.390873: step: 1604/531, loss: 0.05492992699146271
2023-01-21 10:53:08.531861: step: 1608/531, loss: 0.0587894432246685
2023-01-21 10:53:09.664821: step: 1612/531, loss: 0.02501382678747177
2023-01-21 10:53:10.771276: step: 1616/531, loss: 0.003394985105842352
2023-01-21 10:53:11.943232: step: 1620/531, loss: 0.10439453274011612
2023-01-21 10:53:13.111241: step: 1624/531, loss: 0.00922689400613308
2023-01-21 10:53:14.261987: step: 1628/531, loss: 0.007351208012551069
2023-01-21 10:53:15.387810: step: 1632/531, loss: 0.0024701834190636873
2023-01-21 10:53:16.537412: step: 1636/531, loss: 0.09640665352344513
2023-01-21 10:53:17.726883: step: 1640/531, loss: 0.056862831115722656
2023-01-21 10:53:18.848445: step: 1644/531, loss: 0.15328189730644226
2023-01-21 10:53:20.003873: step: 1648/531, loss: 0.052858710289001465
2023-01-21 10:53:21.157501: step: 1652/531, loss: 0.04492168501019478
2023-01-21 10:53:22.292326: step: 1656/531, loss: 0.00041294097900390625
2023-01-21 10:53:23.434293: step: 1660/531, loss: 0.009245586581528187
2023-01-21 10:53:24.562459: step: 1664/531, loss: 0.08038024604320526
2023-01-21 10:53:25.693192: step: 1668/531, loss: 0.014008236117661
2023-01-21 10:53:26.843333: step: 1672/531, loss: 0.06971540302038193
2023-01-21 10:53:27.976862: step: 1676/531, loss: 0.00341033935546875
2023-01-21 10:53:29.142412: step: 1680/531, loss: 0.000506496406160295
2023-01-21 10:53:30.305411: step: 1684/531, loss: 0.030138205736875534
2023-01-21 10:53:31.458267: step: 1688/531, loss: 0.1150185614824295
2023-01-21 10:53:32.583239: step: 1692/531, loss: 0.055745795369148254
2023-01-21 10:53:33.714635: step: 1696/531, loss: 0.004923009779304266
2023-01-21 10:53:34.857457: step: 1700/531, loss: 0.00832443218678236
2023-01-21 10:53:36.009125: step: 1704/531, loss: 0.06748123466968536
2023-01-21 10:53:37.170170: step: 1708/531, loss: 0.02942085452377796
2023-01-21 10:53:38.328092: step: 1712/531, loss: 0.04230327904224396
2023-01-21 10:53:39.469608: step: 1716/531, loss: 0.007904243655502796
2023-01-21 10:53:40.620286: step: 1720/531, loss: 0.008150482550263405
2023-01-21 10:53:41.767271: step: 1724/531, loss: 0.017395783215761185
2023-01-21 10:53:42.919198: step: 1728/531, loss: 0.13328370451927185
2023-01-21 10:53:44.095976: step: 1732/531, loss: 0.009827995672821999
2023-01-21 10:53:45.219096: step: 1736/531, loss: 0.002374362898990512
2023-01-21 10:53:46.375413: step: 1740/531, loss: 0.1539279967546463
2023-01-21 10:53:47.522523: step: 1744/531, loss: 0.015444987453520298
2023-01-21 10:53:48.665808: step: 1748/531, loss: 0.0011411190498620272
2023-01-21 10:53:49.827037: step: 1752/531, loss: 0.022669566795229912
2023-01-21 10:53:50.970446: step: 1756/531, loss: 0.036907292902469635
2023-01-21 10:53:52.110978: step: 1760/531, loss: 0.001556396484375
2023-01-21 10:53:53.254389: step: 1764/531, loss: 0.15257439017295837
2023-01-21 10:53:54.408633: step: 1768/531, loss: 0.05498996004462242
2023-01-21 10:53:55.566066: step: 1772/531, loss: 0.04025459289550781
2023-01-21 10:53:56.724342: step: 1776/531, loss: 0.06224804371595383
2023-01-21 10:53:57.889551: step: 1780/531, loss: 0.04794476181268692
2023-01-21 10:53:59.008661: step: 1784/531, loss: 0.07785062491893768
2023-01-21 10:54:00.177037: step: 1788/531, loss: 0.046160224825143814
2023-01-21 10:54:01.319743: step: 1792/531, loss: 0.02850637398660183
2023-01-21 10:54:02.465203: step: 1796/531, loss: 0.06720910221338272
2023-01-21 10:54:03.625410: step: 1800/531, loss: 0.035118963569402695
2023-01-21 10:54:04.771880: step: 1804/531, loss: 0.03721027448773384
2023-01-21 10:54:05.934551: step: 1808/531, loss: 0.06834888458251953
2023-01-21 10:54:07.073247: step: 1812/531, loss: 0.06516013294458389
2023-01-21 10:54:08.218223: step: 1816/531, loss: 0.4123293161392212
2023-01-21 10:54:09.374714: step: 1820/531, loss: 0.05392913892865181
2023-01-21 10:54:10.541242: step: 1824/531, loss: 0.0010543824173510075
2023-01-21 10:54:11.683643: step: 1828/531, loss: 0.03467082977294922
2023-01-21 10:54:12.836116: step: 1832/531, loss: 0.007027435582131147
2023-01-21 10:54:13.980677: step: 1836/531, loss: 1.952021837234497
2023-01-21 10:54:15.126468: step: 1840/531, loss: 0.003164959140121937
2023-01-21 10:54:16.281950: step: 1844/531, loss: 0.05413856729865074
2023-01-21 10:54:17.417448: step: 1848/531, loss: 0.014834022149443626
2023-01-21 10:54:18.553128: step: 1852/531, loss: 0.027669716626405716
2023-01-21 10:54:19.683150: step: 1856/531, loss: 0.01954364776611328
2023-01-21 10:54:20.834360: step: 1860/531, loss: 0.12610477209091187
2023-01-21 10:54:21.913197: step: 1864/531, loss: 0.05196359008550644
2023-01-21 10:54:23.066866: step: 1868/531, loss: 0.03356170654296875
2023-01-21 10:54:24.215324: step: 1872/531, loss: 0.010723471641540527
2023-01-21 10:54:25.372576: step: 1876/531, loss: 0.03133249282836914
2023-01-21 10:54:26.507022: step: 1880/531, loss: 0.11030636727809906
2023-01-21 10:54:27.615244: step: 1884/531, loss: 0.3563876152038574
2023-01-21 10:54:28.730194: step: 1888/531, loss: 0.040427327156066895
2023-01-21 10:54:29.869336: step: 1892/531, loss: 0.11936015635728836
2023-01-21 10:54:31.013055: step: 1896/531, loss: 0.20236405730247498
2023-01-21 10:54:32.154731: step: 1900/531, loss: 0.009434044361114502
2023-01-21 10:54:33.305032: step: 1904/531, loss: 0.051358990371227264
2023-01-21 10:54:34.473459: step: 1908/531, loss: 0.08827072381973267
2023-01-21 10:54:35.610604: step: 1912/531, loss: 0.008693313226103783
2023-01-21 10:54:36.753080: step: 1916/531, loss: 0.0628931075334549
2023-01-21 10:54:37.880941: step: 1920/531, loss: 0.03799457475543022
2023-01-21 10:54:39.027449: step: 1924/531, loss: 0.1904619187116623
2023-01-21 10:54:40.191885: step: 1928/531, loss: 0.0058269500732421875
2023-01-21 10:54:41.345897: step: 1932/531, loss: 0.020396806299686432
2023-01-21 10:54:42.484637: step: 1936/531, loss: 0.033467911183834076
2023-01-21 10:54:43.652045: step: 1940/531, loss: 0.08446350693702698
2023-01-21 10:54:44.771186: step: 1944/531, loss: 0.014724064618349075
2023-01-21 10:54:45.905268: step: 1948/531, loss: 0.020745133981108665
2023-01-21 10:54:47.051127: step: 1952/531, loss: 0.08192062377929688
2023-01-21 10:54:48.167043: step: 1956/531, loss: 0.03562808036804199
2023-01-21 10:54:49.279507: step: 1960/531, loss: 0.0007377624278888106
2023-01-21 10:54:50.430781: step: 1964/531, loss: 0.12118415534496307
2023-01-21 10:54:51.547125: step: 1968/531, loss: 0.03675975650548935
2023-01-21 10:54:52.689768: step: 1972/531, loss: 0.13955183327198029
2023-01-21 10:54:53.825074: step: 1976/531, loss: 0.007500886917114258
2023-01-21 10:54:54.949072: step: 1980/531, loss: 0.09517045319080353
2023-01-21 10:54:56.091287: step: 1984/531, loss: 0.019038772210478783
2023-01-21 10:54:57.238390: step: 1988/531, loss: 0.05047626420855522
2023-01-21 10:54:58.369721: step: 1992/531, loss: 0.0011599541176110506
2023-01-21 10:54:59.491233: step: 1996/531, loss: 0.001729345298372209
2023-01-21 10:55:00.622521: step: 2000/531, loss: 0.03404216840863228
2023-01-21 10:55:01.740948: step: 2004/531, loss: 0.009194565005600452
2023-01-21 10:55:02.881061: step: 2008/531, loss: 0.002778434893116355
2023-01-21 10:55:04.057275: step: 2012/531, loss: 0.02047252655029297
2023-01-21 10:55:05.199164: step: 2016/531, loss: 0.11225318908691406
2023-01-21 10:55:06.321070: step: 2020/531, loss: 0.0116150863468647
2023-01-21 10:55:07.457142: step: 2024/531, loss: 0.022969722747802734
2023-01-21 10:55:08.619259: step: 2028/531, loss: 0.06064276769757271
2023-01-21 10:55:09.737265: step: 2032/531, loss: 0.05816650390625
2023-01-21 10:55:10.860843: step: 2036/531, loss: 0.025210261344909668
2023-01-21 10:55:11.994428: step: 2040/531, loss: 0.05956621468067169
2023-01-21 10:55:13.154996: step: 2044/531, loss: 0.0003121137560810894
2023-01-21 10:55:14.348698: step: 2048/531, loss: 0.03138890117406845
2023-01-21 10:55:15.465613: step: 2052/531, loss: 0.0028836012352257967
2023-01-21 10:55:16.601254: step: 2056/531, loss: 0.05264396592974663
2023-01-21 10:55:17.720714: step: 2060/531, loss: 0.08131809532642365
2023-01-21 10:55:18.868678: step: 2064/531, loss: 0.050402261316776276
2023-01-21 10:55:20.010857: step: 2068/531, loss: 0.04946918413043022
2023-01-21 10:55:21.149893: step: 2072/531, loss: 0.08591398596763611
2023-01-21 10:55:22.300687: step: 2076/531, loss: 0.025300025939941406
2023-01-21 10:55:23.423113: step: 2080/531, loss: 0.001347446464933455
2023-01-21 10:55:24.556704: step: 2084/531, loss: 0.007817077450454235
2023-01-21 10:55:25.681930: step: 2088/531, loss: 0.04361867904663086
2023-01-21 10:55:26.822292: step: 2092/531, loss: 0.007647156715393066
2023-01-21 10:55:27.955682: step: 2096/531, loss: 0.0014867782592773438
2023-01-21 10:55:29.090992: step: 2100/531, loss: 0.05043201521039009
2023-01-21 10:55:30.208269: step: 2104/531, loss: 0.014550304971635342
2023-01-21 10:55:31.346811: step: 2108/531, loss: 0.00855245627462864
2023-01-21 10:55:32.503369: step: 2112/531, loss: 0.11540967226028442
2023-01-21 10:55:33.636561: step: 2116/531, loss: 0.02228555828332901
2023-01-21 10:55:34.775136: step: 2120/531, loss: 0.001979923341423273
2023-01-21 10:55:35.880094: step: 2124/531, loss: 0.00046296120854094625
==================================================
Loss: 0.060
--------------------
Dev: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.55, 'r': 0.8148148148148148, 'f1': 0.6567164179104479}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
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': 13}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 10:56:25.608791: step: 4/531, loss: 0.1862301230430603
2023-01-21 10:56:26.731090: step: 8/531, loss: 0.03784370422363281
2023-01-21 10:56:27.839671: step: 12/531, loss: 0.0001312255917582661
2023-01-21 10:56:28.963474: step: 16/531, loss: 0.005646228790283203
2023-01-21 10:56:30.095025: step: 20/531, loss: 0.0002513647195883095
2023-01-21 10:56:31.240634: step: 24/531, loss: 0.05716114118695259
2023-01-21 10:56:32.367572: step: 28/531, loss: 0.008765793405473232
2023-01-21 10:56:33.504095: step: 32/531, loss: 0.08409976959228516
2023-01-21 10:56:34.634452: step: 36/531, loss: 0.0046863555908203125
2023-01-21 10:56:35.786170: step: 40/531, loss: 0.038842394948005676
2023-01-21 10:56:36.926646: step: 44/531, loss: 0.03919363021850586
2023-01-21 10:56:38.032313: step: 48/531, loss: 0.02682790718972683
2023-01-21 10:56:39.173031: step: 52/531, loss: 0.010151100344955921
2023-01-21 10:56:40.294654: step: 56/531, loss: 0.007682991214096546
2023-01-21 10:56:41.430846: step: 60/531, loss: 0.0046291351318359375
2023-01-21 10:56:42.626159: step: 64/531, loss: 0.035105325281620026
2023-01-21 10:56:43.759370: step: 68/531, loss: 0.13061365485191345
2023-01-21 10:56:44.906591: step: 72/531, loss: 0.11213311553001404
2023-01-21 10:56:46.056421: step: 76/531, loss: 0.045264437794685364
2023-01-21 10:56:47.189890: step: 80/531, loss: 0.014772068709135056
2023-01-21 10:56:48.374495: step: 84/531, loss: 0.013162041082978249
2023-01-21 10:56:49.525501: step: 88/531, loss: 0.011248065158724785
2023-01-21 10:56:50.675576: step: 92/531, loss: 0.02269775979220867
2023-01-21 10:56:51.805312: step: 96/531, loss: 0.0015083790058270097
2023-01-21 10:56:52.950562: step: 100/531, loss: 0.0008245468488894403
2023-01-21 10:56:54.063908: step: 104/531, loss: 0.007290299516171217
2023-01-21 10:56:55.224966: step: 108/531, loss: 0.05163154751062393
2023-01-21 10:56:56.351102: step: 112/531, loss: 0.04657135158777237
2023-01-21 10:56:57.495770: step: 116/531, loss: 0.08790865540504456
2023-01-21 10:56:58.648082: step: 120/531, loss: 0.08179759979248047
2023-01-21 10:56:59.776280: step: 124/531, loss: 0.10913095623254776
2023-01-21 10:57:00.939588: step: 128/531, loss: 0.02264099009335041
2023-01-21 10:57:02.084107: step: 132/531, loss: 0.007409191224724054
2023-01-21 10:57:03.249081: step: 136/531, loss: 0.13832911849021912
2023-01-21 10:57:04.420509: step: 140/531, loss: 0.04629650339484215
2023-01-21 10:57:05.582389: step: 144/531, loss: 0.004909324459731579
2023-01-21 10:57:06.731525: step: 148/531, loss: 0.017298413440585136
2023-01-21 10:57:07.868698: step: 152/531, loss: 0.0005558490520343184
2023-01-21 10:57:09.015554: step: 156/531, loss: 0.5295258164405823
2023-01-21 10:57:10.148695: step: 160/531, loss: 0.12251396477222443
2023-01-21 10:57:11.266057: step: 164/531, loss: 0.07428783923387527
2023-01-21 10:57:12.400021: step: 168/531, loss: 0.03385968133807182
2023-01-21 10:57:13.550014: step: 172/531, loss: 0.03745222091674805
2023-01-21 10:57:14.671317: step: 176/531, loss: 0.017795635387301445
2023-01-21 10:57:15.825539: step: 180/531, loss: 0.0130653390660882
2023-01-21 10:57:16.952888: step: 184/531, loss: 0.023881245404481888
2023-01-21 10:57:18.110844: step: 188/531, loss: 0.03159074857831001
2023-01-21 10:57:19.276344: step: 192/531, loss: 0.040824417024850845
2023-01-21 10:57:20.469245: step: 196/531, loss: 0.019517231732606888
2023-01-21 10:57:21.599210: step: 200/531, loss: 0.03165016323328018
2023-01-21 10:57:22.758193: step: 204/531, loss: 0.040506936609745026
2023-01-21 10:57:23.886434: step: 208/531, loss: 0.0012264729011803865
2023-01-21 10:57:25.014028: step: 212/531, loss: 0.012244414538145065
2023-01-21 10:57:26.134868: step: 216/531, loss: 0.0150572769343853
2023-01-21 10:57:27.275274: step: 220/531, loss: 0.035454630851745605
2023-01-21 10:57:28.420813: step: 224/531, loss: 0.014980555512011051
2023-01-21 10:57:29.577542: step: 228/531, loss: 0.02538886107504368
2023-01-21 10:57:30.733321: step: 232/531, loss: 0.049399856477975845
2023-01-21 10:57:31.882419: step: 236/531, loss: 0.05609875172376633
2023-01-21 10:57:33.019687: step: 240/531, loss: 0.022008182480931282
2023-01-21 10:57:34.189409: step: 244/531, loss: 0.026206398382782936
2023-01-21 10:57:35.333308: step: 248/531, loss: 0.016715049743652344
2023-01-21 10:57:36.476044: step: 252/531, loss: 0.06509499251842499
2023-01-21 10:57:37.644573: step: 256/531, loss: 0.031041527166962624
2023-01-21 10:57:38.778434: step: 260/531, loss: 0.0007351874955929816
2023-01-21 10:57:39.913292: step: 264/531, loss: 0.0032892227172851562
2023-01-21 10:57:41.038317: step: 268/531, loss: 0.01634979248046875
2023-01-21 10:57:42.200611: step: 272/531, loss: 0.008093548007309437
2023-01-21 10:57:43.378152: step: 276/531, loss: 0.02385406568646431
2023-01-21 10:57:44.516853: step: 280/531, loss: 0.012347603216767311
2023-01-21 10:57:45.657118: step: 284/531, loss: 0.009841347113251686
2023-01-21 10:57:46.789871: step: 288/531, loss: 0.0010462283389642835
2023-01-21 10:57:47.950620: step: 292/531, loss: 0.024961184710264206
2023-01-21 10:57:49.084557: step: 296/531, loss: 0.0011052133049815893
2023-01-21 10:57:50.262836: step: 300/531, loss: 0.002892398973926902
2023-01-21 10:57:51.408907: step: 304/531, loss: 0.012855720706284046
2023-01-21 10:57:52.562444: step: 308/531, loss: 0.011732339859008789
2023-01-21 10:57:53.696765: step: 312/531, loss: 0.006576919462531805
2023-01-21 10:57:54.821560: step: 316/531, loss: 0.0011031150352209806
2023-01-21 10:57:55.977613: step: 320/531, loss: 0.004845285322517157
2023-01-21 10:57:57.127062: step: 324/531, loss: 0.07610197365283966
2023-01-21 10:57:58.270851: step: 328/531, loss: 0.017949486151337624
2023-01-21 10:57:59.381196: step: 332/531, loss: 0.009623909369111061
2023-01-21 10:58:00.502106: step: 336/531, loss: 0.01307301502674818
2023-01-21 10:58:01.639899: step: 340/531, loss: 0.19303159415721893
2023-01-21 10:58:02.781604: step: 344/531, loss: 0.05890091508626938
2023-01-21 10:58:03.922436: step: 348/531, loss: 0.025438690558075905
2023-01-21 10:58:05.081130: step: 352/531, loss: 0.04901723936200142
2023-01-21 10:58:06.214678: step: 356/531, loss: 0.00047936441842466593
2023-01-21 10:58:07.394761: step: 360/531, loss: 0.21760545670986176
2023-01-21 10:58:08.574622: step: 364/531, loss: 0.0007781505701132119
2023-01-21 10:58:09.708003: step: 368/531, loss: 0.013126516714692116
2023-01-21 10:58:10.863112: step: 372/531, loss: 0.5478253960609436
2023-01-21 10:58:12.005365: step: 376/531, loss: 0.009425354190170765
2023-01-21 10:58:13.170967: step: 380/531, loss: 0.05175914987921715
2023-01-21 10:58:14.319810: step: 384/531, loss: 0.020055677741765976
2023-01-21 10:58:15.439180: step: 388/531, loss: 0.0038026811089366674
2023-01-21 10:58:16.596781: step: 392/531, loss: 0.031622789800167084
2023-01-21 10:58:17.714338: step: 396/531, loss: 0.014116574078798294
2023-01-21 10:58:18.835328: step: 400/531, loss: 0.010621833615005016
2023-01-21 10:58:19.963884: step: 404/531, loss: 0.007936477661132812
2023-01-21 10:58:21.117591: step: 408/531, loss: 0.012959766201674938
2023-01-21 10:58:22.228124: step: 412/531, loss: 0.02434062957763672
2023-01-21 10:58:23.368130: step: 416/531, loss: 0.034087181091308594
2023-01-21 10:58:24.502571: step: 420/531, loss: 0.029158784076571465
2023-01-21 10:58:25.663704: step: 424/531, loss: 0.07322239875793457
2023-01-21 10:58:26.812860: step: 428/531, loss: 0.012482023797929287
2023-01-21 10:58:28.004253: step: 432/531, loss: 0.036682795733213425
2023-01-21 10:58:29.137929: step: 436/531, loss: 0.013294410891830921
2023-01-21 10:58:30.289854: step: 440/531, loss: 0.012344742193818092
2023-01-21 10:58:31.422369: step: 444/531, loss: 0.4608679711818695
2023-01-21 10:58:32.563143: step: 448/531, loss: 0.0045067789033055305
2023-01-21 10:58:33.723198: step: 452/531, loss: 0.004168844316154718
2023-01-21 10:58:34.875652: step: 456/531, loss: 0.12389784306287766
2023-01-21 10:58:36.034368: step: 460/531, loss: 0.1371532380580902
2023-01-21 10:58:37.153497: step: 464/531, loss: 0.0007326602935791016
2023-01-21 10:58:38.283872: step: 468/531, loss: 0.007001447957009077
2023-01-21 10:58:39.432731: step: 472/531, loss: 0.013240909203886986
2023-01-21 10:58:40.568535: step: 476/531, loss: 0.013994836248457432
2023-01-21 10:58:41.680772: step: 480/531, loss: 0.020643234252929688
2023-01-21 10:58:42.816896: step: 484/531, loss: 0.018093157559633255
2023-01-21 10:58:43.950921: step: 488/531, loss: 0.0035318376030772924
2023-01-21 10:58:45.094979: step: 492/531, loss: 0.07602062076330185
2023-01-21 10:58:46.232227: step: 496/531, loss: 0.09833059459924698
2023-01-21 10:58:47.430158: step: 500/531, loss: 0.07449188828468323
2023-01-21 10:58:48.591347: step: 504/531, loss: 0.31471386551856995
2023-01-21 10:58:49.723283: step: 508/531, loss: 0.004318046849220991
2023-01-21 10:58:50.878676: step: 512/531, loss: 0.0010810852982103825
2023-01-21 10:58:51.999830: step: 516/531, loss: 0.049601174890995026
2023-01-21 10:58:53.119744: step: 520/531, loss: 0.006776904687285423
2023-01-21 10:58:54.276558: step: 524/531, loss: 0.00989379920065403
2023-01-21 10:58:55.401739: step: 528/531, loss: 0.0021483423188328743
2023-01-21 10:58:56.573735: step: 532/531, loss: 0.03578987345099449
2023-01-21 10:58:57.728357: step: 536/531, loss: 0.01175546646118164
2023-01-21 10:58:58.857435: step: 540/531, loss: 0.02257823944091797
2023-01-21 10:58:59.983147: step: 544/531, loss: 0.004276084713637829
2023-01-21 10:59:01.137257: step: 548/531, loss: 0.004549980163574219
2023-01-21 10:59:02.289764: step: 552/531, loss: 0.0710611343383789
2023-01-21 10:59:03.434602: step: 556/531, loss: 0.026451872661709785
2023-01-21 10:59:04.605395: step: 560/531, loss: 0.009717846289277077
2023-01-21 10:59:05.743700: step: 564/531, loss: 0.057230375707149506
2023-01-21 10:59:06.874105: step: 568/531, loss: 0.046820640563964844
2023-01-21 10:59:08.065099: step: 572/531, loss: 0.03182820975780487
2023-01-21 10:59:09.197277: step: 576/531, loss: 0.009929275140166283
2023-01-21 10:59:10.312836: step: 580/531, loss: 0.037971243262290955
2023-01-21 10:59:11.459102: step: 584/531, loss: 0.024565409868955612
2023-01-21 10:59:12.629697: step: 588/531, loss: 0.016748523339629173
2023-01-21 10:59:13.796580: step: 592/531, loss: 0.1666925996541977
2023-01-21 10:59:14.954239: step: 596/531, loss: 0.004126167856156826
2023-01-21 10:59:16.084178: step: 600/531, loss: 0.07454414665699005
2023-01-21 10:59:17.219635: step: 604/531, loss: 0.01575784757733345
2023-01-21 10:59:18.402055: step: 608/531, loss: 0.022087670862674713
2023-01-21 10:59:19.573497: step: 612/531, loss: 0.0070129395462572575
2023-01-21 10:59:20.709069: step: 616/531, loss: 0.0024917633272707462
2023-01-21 10:59:21.862823: step: 620/531, loss: 0.005737114232033491
2023-01-21 10:59:22.997342: step: 624/531, loss: 0.013321781530976295
2023-01-21 10:59:24.131978: step: 628/531, loss: 0.01276307087391615
2023-01-21 10:59:25.255968: step: 632/531, loss: 0.02257242240011692
2023-01-21 10:59:26.421973: step: 636/531, loss: 0.016452312469482422
2023-01-21 10:59:27.593057: step: 640/531, loss: 0.08585662394762039
2023-01-21 10:59:28.715048: step: 644/531, loss: 0.01965313032269478
2023-01-21 10:59:29.865507: step: 648/531, loss: 0.05277479439973831
2023-01-21 10:59:31.022688: step: 652/531, loss: 0.025231044739484787
2023-01-21 10:59:32.141881: step: 656/531, loss: 0.0006463051540777087
2023-01-21 10:59:33.283679: step: 660/531, loss: 0.027299975976347923
2023-01-21 10:59:34.451541: step: 664/531, loss: 0.003398561617359519
2023-01-21 10:59:35.591548: step: 668/531, loss: 0.01680312119424343
2023-01-21 10:59:36.734569: step: 672/531, loss: 0.008103752508759499
2023-01-21 10:59:37.861664: step: 676/531, loss: 0.0008049011812545359
2023-01-21 10:59:39.013397: step: 680/531, loss: 0.11100788414478302
2023-01-21 10:59:40.151902: step: 684/531, loss: 0.0529652014374733
2023-01-21 10:59:41.283698: step: 688/531, loss: 0.013436508364975452
2023-01-21 10:59:42.498705: step: 692/531, loss: 0.002786874771118164
2023-01-21 10:59:43.657468: step: 696/531, loss: 0.06669292598962784
2023-01-21 10:59:44.838516: step: 700/531, loss: 0.022096633911132812
2023-01-21 10:59:45.990349: step: 704/531, loss: 0.030561160296201706
2023-01-21 10:59:47.125485: step: 708/531, loss: 0.032714083790779114
2023-01-21 10:59:48.267185: step: 712/531, loss: 0.0023665428161621094
2023-01-21 10:59:49.427916: step: 716/531, loss: 0.024378299713134766
2023-01-21 10:59:50.563465: step: 720/531, loss: 0.04078855365514755
2023-01-21 10:59:51.700857: step: 724/531, loss: 0.055265042930841446
2023-01-21 10:59:52.857659: step: 728/531, loss: 0.003731346223503351
2023-01-21 10:59:53.988625: step: 732/531, loss: 0.0012718201614916325
2023-01-21 10:59:55.144650: step: 736/531, loss: 0.0411074161529541
2023-01-21 10:59:56.271845: step: 740/531, loss: 0.0008794784662313759
2023-01-21 10:59:57.399082: step: 744/531, loss: 0.011661100201308727
2023-01-21 10:59:58.552920: step: 748/531, loss: 0.05096759647130966
2023-01-21 10:59:59.711899: step: 752/531, loss: 0.028563691303133965
2023-01-21 11:00:00.864554: step: 756/531, loss: 0.0282013900578022
2023-01-21 11:00:02.002476: step: 760/531, loss: 0.05781393125653267
2023-01-21 11:00:03.134966: step: 764/531, loss: 0.03658151626586914
2023-01-21 11:00:04.321153: step: 768/531, loss: 0.02291424386203289
2023-01-21 11:00:05.443400: step: 772/531, loss: 0.06625284999608994
2023-01-21 11:00:06.616069: step: 776/531, loss: 0.05680666118860245
2023-01-21 11:00:07.772837: step: 780/531, loss: 0.0570257231593132
2023-01-21 11:00:08.959867: step: 784/531, loss: 0.13939595222473145
2023-01-21 11:00:10.098660: step: 788/531, loss: 0.0068877218291163445
2023-01-21 11:00:11.216932: step: 792/531, loss: 0.00025081634521484375
2023-01-21 11:00:12.399548: step: 796/531, loss: 0.01507587544620037
2023-01-21 11:00:13.569921: step: 800/531, loss: 0.0033044815063476562
2023-01-21 11:00:14.701855: step: 804/531, loss: 0.05417518690228462
2023-01-21 11:00:15.839469: step: 808/531, loss: 0.0012336730724200606
2023-01-21 11:00:16.977429: step: 812/531, loss: 0.008313750848174095
2023-01-21 11:00:18.117522: step: 816/531, loss: 0.0005862236139364541
2023-01-21 11:00:19.254271: step: 820/531, loss: 0.026700783520936966
2023-01-21 11:00:20.426678: step: 824/531, loss: 0.01470184326171875
2023-01-21 11:00:21.552353: step: 828/531, loss: 0.00031981465872377157
2023-01-21 11:00:22.672413: step: 832/531, loss: 0.005941391456872225
2023-01-21 11:00:23.812647: step: 836/531, loss: 0.019776344299316406
2023-01-21 11:00:24.965835: step: 840/531, loss: 0.018439341336488724
2023-01-21 11:00:26.096832: step: 844/531, loss: 0.050380755215883255
2023-01-21 11:00:27.234996: step: 848/531, loss: 0.06971149891614914
2023-01-21 11:00:28.345030: step: 852/531, loss: 0.0756916031241417
2023-01-21 11:00:29.464376: step: 856/531, loss: 0.00580630311742425
2023-01-21 11:00:30.612888: step: 860/531, loss: 0.02053380012512207
2023-01-21 11:00:31.743989: step: 864/531, loss: 0.3435155749320984
2023-01-21 11:00:32.898554: step: 868/531, loss: 0.04386739432811737
2023-01-21 11:00:34.054166: step: 872/531, loss: 0.0003262519894633442
2023-01-21 11:00:35.170609: step: 876/531, loss: 0.013667965307831764
2023-01-21 11:00:36.298410: step: 880/531, loss: 0.018120886757969856
2023-01-21 11:00:37.419475: step: 884/531, loss: 0.0036937713157385588
2023-01-21 11:00:38.565754: step: 888/531, loss: 0.03840336948633194
2023-01-21 11:00:39.680254: step: 892/531, loss: 0.07822151482105255
2023-01-21 11:00:40.806478: step: 896/531, loss: 0.00067310337908566
2023-01-21 11:00:41.943079: step: 900/531, loss: 0.012234210968017578
2023-01-21 11:00:43.068684: step: 904/531, loss: 0.05988330766558647
2023-01-21 11:00:44.261635: step: 908/531, loss: 0.03524265065789223
2023-01-21 11:00:45.384720: step: 912/531, loss: 0.033766794949769974
2023-01-21 11:00:46.548104: step: 916/531, loss: 0.03330698236823082
2023-01-21 11:00:47.691890: step: 920/531, loss: 0.010120200924575329
2023-01-21 11:00:48.825952: step: 924/531, loss: 0.0026053430046886206
2023-01-21 11:00:49.964329: step: 928/531, loss: 0.025379037484526634
2023-01-21 11:00:51.099486: step: 932/531, loss: 0.05553865432739258
2023-01-21 11:00:52.247744: step: 936/531, loss: 0.0015384674770757556
2023-01-21 11:00:53.379470: step: 940/531, loss: 0.23223046958446503
2023-01-21 11:00:54.504086: step: 944/531, loss: 0.08330072462558746
2023-01-21 11:00:55.648985: step: 948/531, loss: 0.054022595286369324
2023-01-21 11:00:56.838637: step: 952/531, loss: 0.0498262420296669
2023-01-21 11:00:57.984948: step: 956/531, loss: 0.017794419080018997
2023-01-21 11:00:59.130417: step: 960/531, loss: 0.033425092697143555
2023-01-21 11:01:00.241625: step: 964/531, loss: 0.04660363495349884
2023-01-21 11:01:01.403028: step: 968/531, loss: 0.05200345814228058
2023-01-21 11:01:02.565778: step: 972/531, loss: 0.022538568824529648
2023-01-21 11:01:03.702590: step: 976/531, loss: 0.09205341339111328
2023-01-21 11:01:04.830054: step: 980/531, loss: 0.06967110931873322
2023-01-21 11:01:05.969756: step: 984/531, loss: 0.10652492195367813
2023-01-21 11:01:07.098014: step: 988/531, loss: 0.027251340448856354
2023-01-21 11:01:08.245995: step: 992/531, loss: 0.04955878108739853
2023-01-21 11:01:09.396544: step: 996/531, loss: 0.0011944533325731754
2023-01-21 11:01:10.528090: step: 1000/531, loss: 0.031995583325624466
2023-01-21 11:01:11.661746: step: 1004/531, loss: 0.008238459005951881
2023-01-21 11:01:12.814062: step: 1008/531, loss: 0.07810582965612411
2023-01-21 11:01:13.950647: step: 1012/531, loss: 0.003288650419563055
2023-01-21 11:01:15.083315: step: 1016/531, loss: 0.013560676015913486
2023-01-21 11:01:16.220992: step: 1020/531, loss: 0.012579631991684437
2023-01-21 11:01:17.382243: step: 1024/531, loss: 0.040154457092285156
2023-01-21 11:01:18.534100: step: 1028/531, loss: 0.025856781750917435
2023-01-21 11:01:19.687308: step: 1032/531, loss: 0.03823661804199219
2023-01-21 11:01:20.856302: step: 1036/531, loss: 0.08782166987657547
2023-01-21 11:01:22.016267: step: 1040/531, loss: 0.05056295543909073
2023-01-21 11:01:23.182432: step: 1044/531, loss: 0.01663675345480442
2023-01-21 11:01:24.322387: step: 1048/531, loss: 0.00223712925799191
2023-01-21 11:01:25.486954: step: 1052/531, loss: 0.06099538877606392
2023-01-21 11:01:26.624296: step: 1056/531, loss: 0.00437583914026618
2023-01-21 11:01:27.773787: step: 1060/531, loss: 0.018632125109434128
2023-01-21 11:01:28.916125: step: 1064/531, loss: 0.014079093933105469
2023-01-21 11:01:30.044966: step: 1068/531, loss: 0.15993347764015198
2023-01-21 11:01:31.188457: step: 1072/531, loss: 0.047476619482040405
2023-01-21 11:01:32.308443: step: 1076/531, loss: 0.06234131008386612
2023-01-21 11:01:33.459144: step: 1080/531, loss: 0.002766543533653021
2023-01-21 11:01:34.641444: step: 1084/531, loss: 0.10883007943630219
2023-01-21 11:01:35.790496: step: 1088/531, loss: 0.020653629675507545
2023-01-21 11:01:36.952922: step: 1092/531, loss: 0.009971046820282936
2023-01-21 11:01:38.091301: step: 1096/531, loss: 0.028186893090605736
2023-01-21 11:01:39.235939: step: 1100/531, loss: 0.000462436699308455
2023-01-21 11:01:40.371158: step: 1104/531, loss: 0.0054476261138916016
2023-01-21 11:01:41.509845: step: 1108/531, loss: 0.02154712565243244
2023-01-21 11:01:42.664615: step: 1112/531, loss: 0.017615413293242455
2023-01-21 11:01:43.794142: step: 1116/531, loss: 0.008717519231140614
2023-01-21 11:01:44.937714: step: 1120/531, loss: 0.4149778187274933
2023-01-21 11:01:46.071306: step: 1124/531, loss: 0.02145233191549778
2023-01-21 11:01:47.230946: step: 1128/531, loss: 0.025443363934755325
2023-01-21 11:01:48.349096: step: 1132/531, loss: 0.04935042932629585
2023-01-21 11:01:49.481140: step: 1136/531, loss: 0.011218786239624023
2023-01-21 11:01:50.586942: step: 1140/531, loss: 0.024904191493988037
2023-01-21 11:01:51.712710: step: 1144/531, loss: 0.010661697015166283
2023-01-21 11:01:52.855027: step: 1148/531, loss: 0.022760486230254173
2023-01-21 11:01:54.009697: step: 1152/531, loss: 0.06754837185144424
2023-01-21 11:01:55.161842: step: 1156/531, loss: 1.0814257860183716
2023-01-21 11:01:56.301429: step: 1160/531, loss: 0.039374351501464844
2023-01-21 11:01:57.440357: step: 1164/531, loss: 0.014348221942782402
2023-01-21 11:01:58.581701: step: 1168/531, loss: 0.025826169177889824
2023-01-21 11:01:59.716598: step: 1172/531, loss: 0.09615497291088104
2023-01-21 11:02:00.846135: step: 1176/531, loss: 0.024796580895781517
2023-01-21 11:02:01.965881: step: 1180/531, loss: 0.040757086127996445
2023-01-21 11:02:03.093861: step: 1184/531, loss: 0.03466777876019478
2023-01-21 11:02:04.232022: step: 1188/531, loss: 0.013293511234223843
2023-01-21 11:02:05.376229: step: 1192/531, loss: 0.0038774493150413036
2023-01-21 11:02:06.522319: step: 1196/531, loss: 0.02116389386355877
2023-01-21 11:02:07.664577: step: 1200/531, loss: 0.011808204464614391
2023-01-21 11:02:08.809230: step: 1204/531, loss: 0.010515451431274414
2023-01-21 11:02:09.944771: step: 1208/531, loss: 0.04086942970752716
2023-01-21 11:02:11.069566: step: 1212/531, loss: 0.022040080279111862
2023-01-21 11:02:12.203277: step: 1216/531, loss: 0.0037306786980479956
2023-01-21 11:02:13.330019: step: 1220/531, loss: 0.029467202723026276
2023-01-21 11:02:14.454926: step: 1224/531, loss: 0.04621296003460884
2023-01-21 11:02:15.611800: step: 1228/531, loss: 0.0851193368434906
2023-01-21 11:02:16.757161: step: 1232/531, loss: 0.11668644845485687
2023-01-21 11:02:17.880361: step: 1236/531, loss: 0.07100821286439896
2023-01-21 11:02:19.008362: step: 1240/531, loss: 0.011982440948486328
2023-01-21 11:02:20.162005: step: 1244/531, loss: 0.05227496474981308
2023-01-21 11:02:21.305184: step: 1248/531, loss: 0.02551898919045925
2023-01-21 11:02:22.438021: step: 1252/531, loss: 0.0015578271122649312
2023-01-21 11:02:23.571502: step: 1256/531, loss: 0.04874400794506073
2023-01-21 11:02:24.719617: step: 1260/531, loss: 0.07148857414722443
2023-01-21 11:02:25.860402: step: 1264/531, loss: 0.018061388283967972
2023-01-21 11:02:26.981321: step: 1268/531, loss: 0.0036325454711914062
2023-01-21 11:02:28.081474: step: 1272/531, loss: 0.014343929477036
2023-01-21 11:02:29.225714: step: 1276/531, loss: 0.0010961532825604081
2023-01-21 11:02:30.374611: step: 1280/531, loss: 0.00013599396334029734
2023-01-21 11:02:31.511010: step: 1284/531, loss: 0.03537940979003906
2023-01-21 11:02:32.670818: step: 1288/531, loss: 0.00506248464807868
2023-01-21 11:02:33.800001: step: 1292/531, loss: 1.215659499168396
2023-01-21 11:02:34.927526: step: 1296/531, loss: 0.000366640102583915
2023-01-21 11:02:36.072543: step: 1300/531, loss: 0.011195016093552113
2023-01-21 11:02:37.195152: step: 1304/531, loss: 0.012623120099306107
2023-01-21 11:02:38.332593: step: 1308/531, loss: 0.0011882781982421875
2023-01-21 11:02:39.472610: step: 1312/531, loss: 0.0003638267517089844
2023-01-21 11:02:40.616199: step: 1316/531, loss: 0.01762266270816326
2023-01-21 11:02:41.757878: step: 1320/531, loss: 0.051662541925907135
2023-01-21 11:02:42.922920: step: 1324/531, loss: 0.058111391961574554
2023-01-21 11:02:44.103630: step: 1328/531, loss: 0.02050752565264702
2023-01-21 11:02:45.262397: step: 1332/531, loss: 0.1445474624633789
2023-01-21 11:02:46.388779: step: 1336/531, loss: 0.03603782504796982
2023-01-21 11:02:47.570820: step: 1340/531, loss: 0.030504370108246803
2023-01-21 11:02:48.699629: step: 1344/531, loss: 0.003217410994693637
2023-01-21 11:02:49.842927: step: 1348/531, loss: 0.004818725399672985
2023-01-21 11:02:50.961386: step: 1352/531, loss: 0.02006988599896431
2023-01-21 11:02:52.104079: step: 1356/531, loss: 0.007939147762954235
2023-01-21 11:02:53.215135: step: 1360/531, loss: 0.06282472610473633
2023-01-21 11:02:54.378097: step: 1364/531, loss: 0.029506146907806396
2023-01-21 11:02:55.493058: step: 1368/531, loss: 0.024111174046993256
2023-01-21 11:02:56.634374: step: 1372/531, loss: 0.020360087975859642
2023-01-21 11:02:57.765606: step: 1376/531, loss: 0.050803374499082565
2023-01-21 11:02:58.890232: step: 1380/531, loss: 0.03791790083050728
2023-01-21 11:03:00.059408: step: 1384/531, loss: 0.0006681442027911544
2023-01-21 11:03:01.197970: step: 1388/531, loss: 0.050988007336854935
2023-01-21 11:03:02.301037: step: 1392/531, loss: 0.055880263447761536
2023-01-21 11:03:03.461608: step: 1396/531, loss: 0.022161483764648438
2023-01-21 11:03:04.605772: step: 1400/531, loss: 0.23915615677833557
2023-01-21 11:03:05.738361: step: 1404/531, loss: 0.135502427816391
2023-01-21 11:03:06.856467: step: 1408/531, loss: 0.03633251413702965
2023-01-21 11:03:07.991841: step: 1412/531, loss: 0.025826549157500267
2023-01-21 11:03:09.115761: step: 1416/531, loss: 0.050603579729795456
2023-01-21 11:03:10.232336: step: 1420/531, loss: 0.025902509689331055
2023-01-21 11:03:11.384190: step: 1424/531, loss: 0.030132580548524857
2023-01-21 11:03:12.513706: step: 1428/531, loss: 0.027805522084236145
2023-01-21 11:03:13.660859: step: 1432/531, loss: 0.07184963673353195
2023-01-21 11:03:14.821481: step: 1436/531, loss: 0.29466742277145386
2023-01-21 11:03:16.020015: step: 1440/531, loss: 0.022292232140898705
2023-01-21 11:03:17.158023: step: 1444/531, loss: 0.03944540023803711
2023-01-21 11:03:18.288267: step: 1448/531, loss: 0.036181118339300156
2023-01-21 11:03:19.443630: step: 1452/531, loss: 0.01693439483642578
2023-01-21 11:03:20.601633: step: 1456/531, loss: 0.04897880554199219
2023-01-21 11:03:21.742233: step: 1460/531, loss: 0.007752609439194202
2023-01-21 11:03:22.881658: step: 1464/531, loss: 0.12552089989185333
2023-01-21 11:03:24.049119: step: 1468/531, loss: 0.017290210351347923
2023-01-21 11:03:25.156589: step: 1472/531, loss: 0.016783738508820534
2023-01-21 11:03:26.319159: step: 1476/531, loss: 0.17274942994117737
2023-01-21 11:03:27.451148: step: 1480/531, loss: 0.016007710248231888
2023-01-21 11:03:28.586236: step: 1484/531, loss: 0.005820083431899548
2023-01-21 11:03:29.749529: step: 1488/531, loss: 0.05739889293909073
2023-01-21 11:03:30.894620: step: 1492/531, loss: 0.09078197926282883
2023-01-21 11:03:32.014787: step: 1496/531, loss: 0.024973679333925247
2023-01-21 11:03:33.150769: step: 1500/531, loss: 0.1017889529466629
2023-01-21 11:03:34.289098: step: 1504/531, loss: 0.057268332690000534
2023-01-21 11:03:35.465887: step: 1508/531, loss: 0.002047634217888117
2023-01-21 11:03:36.586799: step: 1512/531, loss: 0.03226194530725479
2023-01-21 11:03:37.727594: step: 1516/531, loss: 0.022810840979218483
2023-01-21 11:03:38.879190: step: 1520/531, loss: 0.03953952714800835
2023-01-21 11:03:40.021301: step: 1524/531, loss: 0.015357017517089844
2023-01-21 11:03:41.193597: step: 1528/531, loss: 0.002298593521118164
2023-01-21 11:03:42.317944: step: 1532/531, loss: 0.0018476486438885331
2023-01-21 11:03:43.467794: step: 1536/531, loss: 0.18824882805347443
2023-01-21 11:03:44.613952: step: 1540/531, loss: 0.0353180393576622
2023-01-21 11:03:45.718959: step: 1544/531, loss: 0.0010485172970220447
2023-01-21 11:03:46.859801: step: 1548/531, loss: 0.019481182098388672
2023-01-21 11:03:48.013530: step: 1552/531, loss: 0.00020837783813476562
2023-01-21 11:03:49.159112: step: 1556/531, loss: 0.11943188309669495
2023-01-21 11:03:50.313454: step: 1560/531, loss: 0.020120905712246895
2023-01-21 11:03:51.483604: step: 1564/531, loss: 0.03205251693725586
2023-01-21 11:03:52.600135: step: 1568/531, loss: 0.01980610005557537
2023-01-21 11:03:53.742967: step: 1572/531, loss: 0.044774819165468216
2023-01-21 11:03:54.871181: step: 1576/531, loss: 0.030015183612704277
2023-01-21 11:03:56.023882: step: 1580/531, loss: 0.0004452705616131425
2023-01-21 11:03:57.157397: step: 1584/531, loss: 0.024567699059844017
2023-01-21 11:03:58.306280: step: 1588/531, loss: 0.0020863532554358244
2023-01-21 11:03:59.474662: step: 1592/531, loss: 0.13089504837989807
2023-01-21 11:04:00.623919: step: 1596/531, loss: 0.04525146260857582
2023-01-21 11:04:01.767344: step: 1600/531, loss: 0.0004418373282533139
2023-01-21 11:04:02.893244: step: 1604/531, loss: 0.0019834041595458984
2023-01-21 11:04:04.071378: step: 1608/531, loss: 0.02595672756433487
2023-01-21 11:04:05.197558: step: 1612/531, loss: 0.001940059708431363
2023-01-21 11:04:06.352939: step: 1616/531, loss: 0.004043579567223787
2023-01-21 11:04:07.496373: step: 1620/531, loss: 0.0028438568115234375
2023-01-21 11:04:08.643990: step: 1624/531, loss: 0.04108934476971626
2023-01-21 11:04:09.794624: step: 1628/531, loss: 0.04288950189948082
2023-01-21 11:04:10.929376: step: 1632/531, loss: 0.015517997555434704
2023-01-21 11:04:12.123873: step: 1636/531, loss: 0.062074847519397736
2023-01-21 11:04:13.262498: step: 1640/531, loss: 0.07899054884910583
2023-01-21 11:04:14.396697: step: 1644/531, loss: 0.00017976760864257812
2023-01-21 11:04:15.526359: step: 1648/531, loss: 0.012569713406264782
2023-01-21 11:04:16.667038: step: 1652/531, loss: 0.06321258842945099
2023-01-21 11:04:17.801265: step: 1656/531, loss: 0.005524730775505304
2023-01-21 11:04:18.951965: step: 1660/531, loss: 0.018469810485839844
2023-01-21 11:04:20.125789: step: 1664/531, loss: 0.1979011595249176
2023-01-21 11:04:21.269865: step: 1668/531, loss: 0.007015610113739967
2023-01-21 11:04:22.384255: step: 1672/531, loss: 0.055603645741939545
2023-01-21 11:04:23.556875: step: 1676/531, loss: 0.04525108262896538
2023-01-21 11:04:24.712667: step: 1680/531, loss: 0.13455677032470703
2023-01-21 11:04:25.850564: step: 1684/531, loss: 0.004053878597915173
2023-01-21 11:04:27.004431: step: 1688/531, loss: 0.10332445800304413
2023-01-21 11:04:28.149562: step: 1692/531, loss: 0.01812267303466797
2023-01-21 11:04:29.309469: step: 1696/531, loss: 0.007991981692612171
2023-01-21 11:04:30.436161: step: 1700/531, loss: 0.032444193959236145
2023-01-21 11:04:31.590352: step: 1704/531, loss: 0.03719387203454971
2023-01-21 11:04:32.727706: step: 1708/531, loss: 0.045127201825380325
2023-01-21 11:04:33.861894: step: 1712/531, loss: 0.0045719146728515625
2023-01-21 11:04:35.011469: step: 1716/531, loss: 0.009588432498276234
2023-01-21 11:04:36.172217: step: 1720/531, loss: 0.09202108532190323
2023-01-21 11:04:37.322774: step: 1724/531, loss: 0.07666854560375214
2023-01-21 11:04:38.481512: step: 1728/531, loss: 0.003655386157333851
2023-01-21 11:04:39.661627: step: 1732/531, loss: 0.003893280168995261
2023-01-21 11:04:40.784636: step: 1736/531, loss: 0.02083878591656685
2023-01-21 11:04:41.956894: step: 1740/531, loss: 0.006782913580536842
2023-01-21 11:04:43.098377: step: 1744/531, loss: 0.011380195617675781
2023-01-21 11:04:44.271775: step: 1748/531, loss: 0.00877923984080553
2023-01-21 11:04:45.379869: step: 1752/531, loss: 0.0015205859672278166
2023-01-21 11:04:46.520645: step: 1756/531, loss: 0.039209939539432526
2023-01-21 11:04:47.664877: step: 1760/531, loss: 0.13390226662158966
2023-01-21 11:04:48.824337: step: 1764/531, loss: 0.040396787226200104
2023-01-21 11:04:49.954181: step: 1768/531, loss: 0.018426276743412018
2023-01-21 11:04:51.119283: step: 1772/531, loss: 0.03485436737537384
2023-01-21 11:04:52.278922: step: 1776/531, loss: 0.0892486572265625
2023-01-21 11:04:53.461757: step: 1780/531, loss: 0.3212425112724304
2023-01-21 11:04:54.634872: step: 1784/531, loss: 0.2764738202095032
2023-01-21 11:04:55.757550: step: 1788/531, loss: 0.014712715521454811
2023-01-21 11:04:56.887369: step: 1792/531, loss: 0.009042930789291859
2023-01-21 11:04:58.036481: step: 1796/531, loss: 0.05442119017243385
2023-01-21 11:04:59.186044: step: 1800/531, loss: 0.04811840131878853
2023-01-21 11:05:00.356399: step: 1804/531, loss: 0.020531199872493744
2023-01-21 11:05:01.489217: step: 1808/531, loss: 0.02749319188296795
2023-01-21 11:05:02.668355: step: 1812/531, loss: 0.005932045169174671
2023-01-21 11:05:03.809517: step: 1816/531, loss: 0.02140631712973118
2023-01-21 11:05:04.966410: step: 1820/531, loss: 0.045037463307380676
2023-01-21 11:05:06.088443: step: 1824/531, loss: 0.001821756362915039
2023-01-21 11:05:07.229881: step: 1828/531, loss: 0.026884650811553
2023-01-21 11:05:08.385110: step: 1832/531, loss: 0.1425512135028839
2023-01-21 11:05:09.562228: step: 1836/531, loss: 0.023569153621792793
2023-01-21 11:05:10.672237: step: 1840/531, loss: 0.021918583661317825
2023-01-21 11:05:11.817339: step: 1844/531, loss: 0.08577214181423187
2023-01-21 11:05:12.948209: step: 1848/531, loss: 0.025901317596435547
2023-01-21 11:05:14.114234: step: 1852/531, loss: 0.07033157348632812
2023-01-21 11:05:15.271500: step: 1856/531, loss: 0.011713599786162376
2023-01-21 11:05:16.438713: step: 1860/531, loss: 0.02896655909717083
2023-01-21 11:05:17.580323: step: 1864/531, loss: 0.08366508781909943
2023-01-21 11:05:18.726383: step: 1868/531, loss: 0.006102364975959063
2023-01-21 11:05:19.880790: step: 1872/531, loss: 0.007165670394897461
2023-01-21 11:05:21.021714: step: 1876/531, loss: 0.01891203038394451
2023-01-21 11:05:22.128443: step: 1880/531, loss: 0.008925354108214378
2023-01-21 11:05:23.273034: step: 1884/531, loss: 0.028061555698513985
2023-01-21 11:05:24.404596: step: 1888/531, loss: 0.020200157538056374
2023-01-21 11:05:25.530043: step: 1892/531, loss: 0.11156196147203445
2023-01-21 11:05:26.682346: step: 1896/531, loss: 0.018563270568847656
2023-01-21 11:05:27.833418: step: 1900/531, loss: 0.006429863162338734
2023-01-21 11:05:28.997697: step: 1904/531, loss: 0.02931070327758789
2023-01-21 11:05:30.136746: step: 1908/531, loss: 0.5480440258979797
2023-01-21 11:05:31.319182: step: 1912/531, loss: 0.009675979614257812
2023-01-21 11:05:32.473016: step: 1916/531, loss: 0.06420154869556427
2023-01-21 11:05:33.650606: step: 1920/531, loss: 0.18291626870632172
2023-01-21 11:05:34.796837: step: 1924/531, loss: 0.14034004509449005
2023-01-21 11:05:35.962402: step: 1928/531, loss: 0.008494758978486061
2023-01-21 11:05:37.097529: step: 1932/531, loss: 0.05042114108800888
2023-01-21 11:05:38.243945: step: 1936/531, loss: 0.006862545385956764
2023-01-21 11:05:39.433203: step: 1940/531, loss: 0.4576370120048523
2023-01-21 11:05:40.556517: step: 1944/531, loss: 0.026137925684452057
2023-01-21 11:05:41.698959: step: 1948/531, loss: 0.0004225253942422569
2023-01-21 11:05:42.863714: step: 1952/531, loss: 0.3686588406562805
2023-01-21 11:05:44.031366: step: 1956/531, loss: 0.0024030685890465975
2023-01-21 11:05:45.181044: step: 1960/531, loss: 0.0737682357430458
2023-01-21 11:05:46.339710: step: 1964/531, loss: 0.0015135766007006168
2023-01-21 11:05:47.475455: step: 1968/531, loss: 0.15094709396362305
2023-01-21 11:05:48.589150: step: 1972/531, loss: 0.014699364081025124
2023-01-21 11:05:49.747224: step: 1976/531, loss: 0.025695228949189186
2023-01-21 11:05:50.922783: step: 1980/531, loss: 0.13725097477436066
2023-01-21 11:05:52.069424: step: 1984/531, loss: 0.0015345573192462325
2023-01-21 11:05:53.196174: step: 1988/531, loss: 0.03997211903333664
2023-01-21 11:05:54.382399: step: 1992/531, loss: 0.04168253019452095
2023-01-21 11:05:55.493488: step: 1996/531, loss: 0.0008494377252645791
2023-01-21 11:05:56.641884: step: 2000/531, loss: 0.040341950953006744
2023-01-21 11:05:57.783755: step: 2004/531, loss: 0.035220399498939514
2023-01-21 11:05:58.923992: step: 2008/531, loss: 0.14874200522899628
2023-01-21 11:06:00.073006: step: 2012/531, loss: 0.03396720811724663
2023-01-21 11:06:01.251870: step: 2016/531, loss: 0.05444660037755966
2023-01-21 11:06:02.425484: step: 2020/531, loss: 0.016492079943418503
2023-01-21 11:06:03.555294: step: 2024/531, loss: 0.016028976067900658
2023-01-21 11:06:04.715154: step: 2028/531, loss: 0.005664634983986616
2023-01-21 11:06:05.857015: step: 2032/531, loss: 0.004986620042473078
2023-01-21 11:06:06.997753: step: 2036/531, loss: 0.016667796298861504
2023-01-21 11:06:08.157324: step: 2040/531, loss: 0.007364082615822554
2023-01-21 11:06:09.295362: step: 2044/531, loss: 0.017289161682128906
2023-01-21 11:06:10.408621: step: 2048/531, loss: 0.011373138055205345
2023-01-21 11:06:11.557078: step: 2052/531, loss: 0.03544750064611435
2023-01-21 11:06:12.680460: step: 2056/531, loss: 0.055375199764966965
2023-01-21 11:06:13.859807: step: 2060/531, loss: 0.005490303039550781
2023-01-21 11:06:15.014268: step: 2064/531, loss: 0.009616660885512829
2023-01-21 11:06:16.169546: step: 2068/531, loss: 0.007409477140754461
2023-01-21 11:06:17.330718: step: 2072/531, loss: 0.9842849969863892
2023-01-21 11:06:18.488784: step: 2076/531, loss: 0.042870618402957916
2023-01-21 11:06:19.621040: step: 2080/531, loss: 0.023309756070375443
2023-01-21 11:06:20.766481: step: 2084/531, loss: 0.06135749816894531
2023-01-21 11:06:21.882884: step: 2088/531, loss: 0.016766738146543503
2023-01-21 11:06:23.020747: step: 2092/531, loss: 0.007159137632697821
2023-01-21 11:06:24.159540: step: 2096/531, loss: 0.02228107489645481
2023-01-21 11:06:25.313058: step: 2100/531, loss: 0.0033518315758556128
2023-01-21 11:06:26.497971: step: 2104/531, loss: 0.06552505493164062
2023-01-21 11:06:27.682462: step: 2108/531, loss: 0.05066528171300888
2023-01-21 11:06:28.828494: step: 2112/531, loss: 0.024041462689638138
2023-01-21 11:06:29.942349: step: 2116/531, loss: 0.009274578653275967
2023-01-21 11:06:31.081446: step: 2120/531, loss: 0.8296244144439697
2023-01-21 11:06:32.251594: step: 2124/531, loss: 0.07043123245239258
==================================================
Loss: 0.051
--------------------
Dev: {'event': {'p': 0.5931520644511581, 'r': 0.7842876165113183, 'f1': 0.6754587155963302}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6328200192492781, 'r': 0.7841383422778772, 'f1': 0.7003994673768309}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
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': 14}
Korean: {'event': {'p': 0.6507936507936508, 'r': 0.6507936507936508, 'f1': 0.6507936507936508}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.42592592592592593, 'r': 0.6388888888888888, 'f1': 0.5111111111111111}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:07:14.361480: step: 4/531, loss: 0.07297387719154358
2023-01-21 11:07:15.519315: step: 8/531, loss: 0.013412857428193092
2023-01-21 11:07:16.661436: step: 12/531, loss: 0.015209197998046875
2023-01-21 11:07:17.788056: step: 16/531, loss: 0.03069281578063965
2023-01-21 11:07:18.920470: step: 20/531, loss: 0.01795821264386177
2023-01-21 11:07:20.073004: step: 24/531, loss: 0.002276897430419922
2023-01-21 11:07:21.197611: step: 28/531, loss: 0.018523408100008965
2023-01-21 11:07:22.332937: step: 32/531, loss: 0.0015638351906090975
2023-01-21 11:07:23.467950: step: 36/531, loss: 0.0687246322631836
2023-01-21 11:07:24.632818: step: 40/531, loss: 0.0008004188421182334
2023-01-21 11:07:25.769006: step: 44/531, loss: 0.0111115463078022
2023-01-21 11:07:26.941889: step: 48/531, loss: 0.03748369589447975
2023-01-21 11:07:28.133602: step: 52/531, loss: 0.006137276068329811
2023-01-21 11:07:29.281011: step: 56/531, loss: 0.037613775581121445
2023-01-21 11:07:30.450023: step: 60/531, loss: 0.006903409957885742
2023-01-21 11:07:31.577106: step: 64/531, loss: 0.004289579577744007
2023-01-21 11:07:32.717407: step: 68/531, loss: 0.03767652437090874
2023-01-21 11:07:33.871138: step: 72/531, loss: 0.031062128022313118
2023-01-21 11:07:34.998585: step: 76/531, loss: 0.1479346752166748
2023-01-21 11:07:36.118121: step: 80/531, loss: 0.042601823806762695
2023-01-21 11:07:37.251304: step: 84/531, loss: 0.020467758178710938
2023-01-21 11:07:38.373740: step: 88/531, loss: 0.008285988122224808
2023-01-21 11:07:39.531855: step: 92/531, loss: 0.04952993988990784
2023-01-21 11:07:40.659091: step: 96/531, loss: 0.006884193979203701
2023-01-21 11:07:41.775281: step: 100/531, loss: 0.0018438339466229081
2023-01-21 11:07:42.952576: step: 104/531, loss: 0.030244065448641777
2023-01-21 11:07:44.082352: step: 108/531, loss: 0.003540134523063898
2023-01-21 11:07:45.207155: step: 112/531, loss: 0.042096786201000214
2023-01-21 11:07:46.321095: step: 116/531, loss: 0.05252685397863388
2023-01-21 11:07:47.460987: step: 120/531, loss: 0.012580298818647861
2023-01-21 11:07:48.633341: step: 124/531, loss: 0.0137855289503932
2023-01-21 11:07:49.772393: step: 128/531, loss: 0.013552093878388405
2023-01-21 11:07:50.893673: step: 132/531, loss: 0.0006563186761923134
2023-01-21 11:07:52.018597: step: 136/531, loss: 0.015245438553392887
2023-01-21 11:07:53.153560: step: 140/531, loss: 0.09668950736522675
2023-01-21 11:07:54.286218: step: 144/531, loss: 0.11279220134019852
2023-01-21 11:07:55.440092: step: 148/531, loss: 0.009648466482758522
2023-01-21 11:07:56.608636: step: 152/531, loss: 0.048250678926706314
2023-01-21 11:07:57.721668: step: 156/531, loss: 0.010862017050385475
2023-01-21 11:07:58.877119: step: 160/531, loss: 0.0002521038113627583
2023-01-21 11:08:00.002063: step: 164/531, loss: 0.06656661629676819
2023-01-21 11:08:01.158877: step: 168/531, loss: 0.0015022277366369963
2023-01-21 11:08:02.271498: step: 172/531, loss: 0.012348175048828125
2023-01-21 11:08:03.421433: step: 176/531, loss: 0.007479858584702015
2023-01-21 11:08:04.546242: step: 180/531, loss: 0.12902334332466125
2023-01-21 11:08:05.672921: step: 184/531, loss: 0.005042076576501131
2023-01-21 11:08:06.823361: step: 188/531, loss: 0.0935448706150055
2023-01-21 11:08:07.959189: step: 192/531, loss: 0.033365536481142044
2023-01-21 11:08:09.100342: step: 196/531, loss: 0.02251262776553631
2023-01-21 11:08:10.227311: step: 200/531, loss: 0.021362116560339928
2023-01-21 11:08:11.359083: step: 204/531, loss: 0.0004647255118470639
2023-01-21 11:08:12.508147: step: 208/531, loss: 0.02569706365466118
2023-01-21 11:08:13.640964: step: 212/531, loss: 0.018970299512147903
2023-01-21 11:08:14.773234: step: 216/531, loss: 0.12854118645191193
2023-01-21 11:08:15.922323: step: 220/531, loss: 8.144378807628527e-05
2023-01-21 11:08:17.093418: step: 224/531, loss: 0.011375046335160732
2023-01-21 11:08:18.228047: step: 228/531, loss: 0.009011732414364815
2023-01-21 11:08:19.375551: step: 232/531, loss: 0.0008374214521609247
2023-01-21 11:08:20.536703: step: 236/531, loss: 0.01612253114581108
2023-01-21 11:08:21.680071: step: 240/531, loss: 0.008736610412597656
2023-01-21 11:08:22.805916: step: 244/531, loss: 0.06907949596643448
2023-01-21 11:08:23.961054: step: 248/531, loss: 0.037722207605838776
2023-01-21 11:08:25.092338: step: 252/531, loss: 0.10357246547937393
2023-01-21 11:08:26.251167: step: 256/531, loss: 0.14661617577075958
2023-01-21 11:08:27.370543: step: 260/531, loss: 0.011484527960419655
2023-01-21 11:08:28.535740: step: 264/531, loss: 0.0010483742225915194
2023-01-21 11:08:29.686896: step: 268/531, loss: 0.028850747272372246
2023-01-21 11:08:30.827652: step: 272/531, loss: 0.04091396555304527
2023-01-21 11:08:31.986716: step: 276/531, loss: 1.617627739906311
2023-01-21 11:08:33.110841: step: 280/531, loss: 0.005697679705917835
2023-01-21 11:08:34.267393: step: 284/531, loss: 0.026979923248291016
2023-01-21 11:08:35.452183: step: 288/531, loss: 0.625706136226654
2023-01-21 11:08:36.603429: step: 292/531, loss: 0.00203361501917243
2023-01-21 11:08:37.762153: step: 296/531, loss: 0.001901817275211215
2023-01-21 11:08:38.905498: step: 300/531, loss: 0.026924418285489082
2023-01-21 11:08:40.075597: step: 304/531, loss: 0.014453030191361904
2023-01-21 11:08:41.205221: step: 308/531, loss: 0.010524844750761986
2023-01-21 11:08:42.375936: step: 312/531, loss: 0.008693265728652477
2023-01-21 11:08:43.498214: step: 316/531, loss: 0.013535117730498314
2023-01-21 11:08:44.649005: step: 320/531, loss: 0.023793887346982956
2023-01-21 11:08:45.819072: step: 324/531, loss: 0.02077198028564453
2023-01-21 11:08:46.974000: step: 328/531, loss: 0.3561738133430481
2023-01-21 11:08:48.106121: step: 332/531, loss: 0.00772705115377903
2023-01-21 11:08:49.213955: step: 336/531, loss: 0.02726011350750923
2023-01-21 11:08:50.409147: step: 340/531, loss: 0.016624832525849342
2023-01-21 11:08:51.556243: step: 344/531, loss: 0.0034530640114098787
2023-01-21 11:08:52.687296: step: 348/531, loss: 0.005270957946777344
2023-01-21 11:08:53.858648: step: 352/531, loss: 0.021298598498106003
2023-01-21 11:08:54.996094: step: 356/531, loss: 0.17823810875415802
2023-01-21 11:08:56.158362: step: 360/531, loss: 0.028551101684570312
2023-01-21 11:08:57.327204: step: 364/531, loss: 0.037265680730342865
2023-01-21 11:08:58.465705: step: 368/531, loss: 0.015255356207489967
2023-01-21 11:08:59.626062: step: 372/531, loss: 6.006948947906494
2023-01-21 11:09:00.745759: step: 376/531, loss: 0.007457924075424671
2023-01-21 11:09:01.878778: step: 380/531, loss: 0.01645503006875515
2023-01-21 11:09:03.032557: step: 384/531, loss: 0.04083900526165962
2023-01-21 11:09:04.186180: step: 388/531, loss: 0.02556142956018448
2023-01-21 11:09:05.326190: step: 392/531, loss: 0.02190418355166912
2023-01-21 11:09:06.498900: step: 396/531, loss: 0.039310503751039505
2023-01-21 11:09:07.640671: step: 400/531, loss: 0.0006350993644446135
2023-01-21 11:09:08.785367: step: 404/531, loss: 0.008841132745146751
2023-01-21 11:09:09.957166: step: 408/531, loss: 0.01730956882238388
2023-01-21 11:09:11.102822: step: 412/531, loss: 0.019231414422392845
2023-01-21 11:09:12.257165: step: 416/531, loss: 0.05506310611963272
2023-01-21 11:09:13.395303: step: 420/531, loss: 0.021189212799072266
2023-01-21 11:09:14.490665: step: 424/531, loss: 0.036109257489442825
2023-01-21 11:09:15.690175: step: 428/531, loss: 0.07757490128278732
2023-01-21 11:09:16.864824: step: 432/531, loss: 0.09568710625171661
2023-01-21 11:09:17.989983: step: 436/531, loss: 0.12306594848632812
2023-01-21 11:09:19.129324: step: 440/531, loss: 0.022646808996796608
2023-01-21 11:09:20.296464: step: 444/531, loss: 0.01720447465777397
2023-01-21 11:09:21.439723: step: 448/531, loss: 0.02071247063577175
2023-01-21 11:09:22.599795: step: 452/531, loss: 0.001737880753353238
2023-01-21 11:09:23.740042: step: 456/531, loss: 0.004914379213005304
2023-01-21 11:09:24.888019: step: 460/531, loss: 0.00042848585871979594
2023-01-21 11:09:26.036205: step: 464/531, loss: 0.0002808570861816406
2023-01-21 11:09:27.183623: step: 468/531, loss: 0.005483436863869429
2023-01-21 11:09:28.319609: step: 472/531, loss: 0.005069732666015625
2023-01-21 11:09:29.471800: step: 476/531, loss: 0.03879880905151367
2023-01-21 11:09:30.612033: step: 480/531, loss: 0.0582880973815918
2023-01-21 11:09:31.769400: step: 484/531, loss: 0.0715295821428299
2023-01-21 11:09:32.922535: step: 488/531, loss: 0.028585147112607956
2023-01-21 11:09:34.072606: step: 492/531, loss: 0.10833396762609482
2023-01-21 11:09:35.222302: step: 496/531, loss: 0.007443904876708984
2023-01-21 11:09:36.385522: step: 500/531, loss: 0.859030544757843
2023-01-21 11:09:37.515685: step: 504/531, loss: 0.0022531270515173674
2023-01-21 11:09:38.659895: step: 508/531, loss: 0.022901631891727448
2023-01-21 11:09:39.812933: step: 512/531, loss: 0.053965188562870026
2023-01-21 11:09:40.958488: step: 516/531, loss: 0.01820126734673977
2023-01-21 11:09:42.141302: step: 520/531, loss: 0.00041179655818268657
2023-01-21 11:09:43.306624: step: 524/531, loss: 0.029315471649169922
2023-01-21 11:09:44.454152: step: 528/531, loss: 0.023952674120664597
2023-01-21 11:09:45.596277: step: 532/531, loss: 0.012011121958494186
2023-01-21 11:09:46.735146: step: 536/531, loss: 0.05697031319141388
2023-01-21 11:09:47.917026: step: 540/531, loss: 0.029539775103330612
2023-01-21 11:09:49.051816: step: 544/531, loss: 0.08146047592163086
2023-01-21 11:09:50.202635: step: 548/531, loss: 0.05482606589794159
2023-01-21 11:09:51.358550: step: 552/531, loss: 0.04075346142053604
2023-01-21 11:09:52.489230: step: 556/531, loss: 0.07460375130176544
2023-01-21 11:09:53.647444: step: 560/531, loss: 0.036959078162908554
2023-01-21 11:09:54.771750: step: 564/531, loss: 0.006295204162597656
2023-01-21 11:09:55.900947: step: 568/531, loss: 0.033301543444395065
2023-01-21 11:09:57.053723: step: 572/531, loss: 0.006530857179313898
2023-01-21 11:09:58.190755: step: 576/531, loss: 0.0009083747863769531
2023-01-21 11:09:59.327850: step: 580/531, loss: 0.09212875366210938
2023-01-21 11:10:00.490195: step: 584/531, loss: 0.01833324506878853
2023-01-21 11:10:01.631524: step: 588/531, loss: 0.007298278622329235
2023-01-21 11:10:02.756573: step: 592/531, loss: 0.08208150416612625
2023-01-21 11:10:03.882137: step: 596/531, loss: 0.02361927181482315
2023-01-21 11:10:04.997993: step: 600/531, loss: 0.023557664826512337
2023-01-21 11:10:06.121695: step: 604/531, loss: 0.01991300657391548
2023-01-21 11:10:07.285090: step: 608/531, loss: 0.04050483554601669
2023-01-21 11:10:08.439946: step: 612/531, loss: 0.13273735344409943
2023-01-21 11:10:09.555950: step: 616/531, loss: 0.00942087173461914
2023-01-21 11:10:10.679930: step: 620/531, loss: 0.03134417533874512
2023-01-21 11:10:11.874892: step: 624/531, loss: 0.006497574038803577
2023-01-21 11:10:13.001236: step: 628/531, loss: 0.0054931640625
2023-01-21 11:10:14.111387: step: 632/531, loss: 0.017701338976621628
2023-01-21 11:10:15.259007: step: 636/531, loss: 0.1221260130405426
2023-01-21 11:10:16.389394: step: 640/531, loss: 0.15525609254837036
2023-01-21 11:10:17.521980: step: 644/531, loss: 0.02481985092163086
2023-01-21 11:10:18.647467: step: 648/531, loss: 0.0012698173522949219
2023-01-21 11:10:19.781453: step: 652/531, loss: 0.012583018280565739
2023-01-21 11:10:20.944255: step: 656/531, loss: 0.008814429864287376
2023-01-21 11:10:22.062661: step: 660/531, loss: 0.03627414628863335
2023-01-21 11:10:23.225413: step: 664/531, loss: 0.006097603123635054
2023-01-21 11:10:24.341837: step: 668/531, loss: 0.057888224720954895
2023-01-21 11:10:25.472960: step: 672/531, loss: 0.3089749217033386
2023-01-21 11:10:26.607952: step: 676/531, loss: 0.03994159772992134
2023-01-21 11:10:27.715567: step: 680/531, loss: 0.05654086917638779
2023-01-21 11:10:28.849152: step: 684/531, loss: 0.00441974401473999
2023-01-21 11:10:29.975489: step: 688/531, loss: 0.07937698811292648
2023-01-21 11:10:31.133485: step: 692/531, loss: 0.004258906934410334
2023-01-21 11:10:32.252181: step: 696/531, loss: 0.13562817871570587
2023-01-21 11:10:33.423309: step: 700/531, loss: 0.012343215756118298
2023-01-21 11:10:34.581936: step: 704/531, loss: 0.04665699228644371
2023-01-21 11:10:35.754367: step: 708/531, loss: 0.0029415132012218237
2023-01-21 11:10:36.901906: step: 712/531, loss: 0.011162757873535156
2023-01-21 11:10:38.036441: step: 716/531, loss: 0.006087112706154585
2023-01-21 11:10:39.164416: step: 720/531, loss: 0.011725426651537418
2023-01-21 11:10:40.309204: step: 724/531, loss: 0.0020187378395348787
2023-01-21 11:10:41.478007: step: 728/531, loss: 0.007320880889892578
2023-01-21 11:10:42.640694: step: 732/531, loss: 0.004034710116684437
2023-01-21 11:10:43.777140: step: 736/531, loss: 0.009257888421416283
2023-01-21 11:10:44.907924: step: 740/531, loss: 0.014367627911269665
2023-01-21 11:10:46.049675: step: 744/531, loss: 0.040366362780332565
2023-01-21 11:10:47.220602: step: 748/531, loss: 0.05868320167064667
2023-01-21 11:10:48.360405: step: 752/531, loss: 0.05543842166662216
2023-01-21 11:10:49.519444: step: 756/531, loss: 0.031809426844120026
2023-01-21 11:10:50.671312: step: 760/531, loss: 0.04211597517132759
2023-01-21 11:10:51.787529: step: 764/531, loss: 0.023733949288725853
2023-01-21 11:10:52.943738: step: 768/531, loss: 0.0020542144775390625
2023-01-21 11:10:54.067504: step: 772/531, loss: 0.005161953158676624
2023-01-21 11:10:55.180186: step: 776/531, loss: 0.003291606903076172
2023-01-21 11:10:56.338324: step: 780/531, loss: 0.054085634648799896
2023-01-21 11:10:57.466749: step: 784/531, loss: 0.0017705918289721012
2023-01-21 11:10:58.618682: step: 788/531, loss: 0.0028642655815929174
2023-01-21 11:10:59.791211: step: 792/531, loss: 0.017211247235536575
2023-01-21 11:11:00.920795: step: 796/531, loss: 0.042252540588378906
2023-01-21 11:11:02.025120: step: 800/531, loss: 0.03646240383386612
2023-01-21 11:11:03.155653: step: 804/531, loss: 0.014688301831483841
2023-01-21 11:11:04.288750: step: 808/531, loss: 0.0011251450050622225
2023-01-21 11:11:05.439440: step: 812/531, loss: 0.018541526049375534
2023-01-21 11:11:06.588715: step: 816/531, loss: 0.004125928971916437
2023-01-21 11:11:07.705708: step: 820/531, loss: 0.03895749896764755
2023-01-21 11:11:08.810538: step: 824/531, loss: 0.011591959744691849
2023-01-21 11:11:09.954274: step: 828/531, loss: 0.00367565150372684
2023-01-21 11:11:11.096169: step: 832/531, loss: 0.006286144256591797
2023-01-21 11:11:12.226073: step: 836/531, loss: 0.005358791910111904
2023-01-21 11:11:13.365689: step: 840/531, loss: 0.05284185707569122
2023-01-21 11:11:14.472074: step: 844/531, loss: 0.05454883351922035
2023-01-21 11:11:15.610596: step: 848/531, loss: 0.007160949986428022
2023-01-21 11:11:16.733872: step: 852/531, loss: 2.193450927734375e-05
2023-01-21 11:11:17.865476: step: 856/531, loss: 0.005218696314841509
2023-01-21 11:11:19.007146: step: 860/531, loss: 0.06339102238416672
2023-01-21 11:11:20.140267: step: 864/531, loss: 0.004090785980224609
2023-01-21 11:11:21.260037: step: 868/531, loss: 0.01420822087675333
2023-01-21 11:11:22.440204: step: 872/531, loss: 0.055559732019901276
2023-01-21 11:11:23.555980: step: 876/531, loss: 0.011470126919448376
2023-01-21 11:11:24.738155: step: 880/531, loss: 0.0335145965218544
2023-01-21 11:11:25.865705: step: 884/531, loss: 0.03201622888445854
2023-01-21 11:11:26.995705: step: 888/531, loss: 0.036260221153497696
2023-01-21 11:11:28.130017: step: 892/531, loss: 0.04789695888757706
2023-01-21 11:11:29.243802: step: 896/531, loss: 0.21066462993621826
2023-01-21 11:11:30.375606: step: 900/531, loss: 0.25753164291381836
2023-01-21 11:11:31.482851: step: 904/531, loss: 0.08119526505470276
2023-01-21 11:11:32.644403: step: 908/531, loss: 0.0073544979095458984
2023-01-21 11:11:33.784395: step: 912/531, loss: 0.015293694101274014
2023-01-21 11:11:34.932153: step: 916/531, loss: 0.027293777093291283
2023-01-21 11:11:36.075944: step: 920/531, loss: 0.045829202979803085
2023-01-21 11:11:37.277294: step: 924/531, loss: 0.005808639340102673
2023-01-21 11:11:38.398890: step: 928/531, loss: 0.023906899616122246
2023-01-21 11:11:39.509432: step: 932/531, loss: 0.013967323116958141
2023-01-21 11:11:40.634243: step: 936/531, loss: 0.004004573915153742
2023-01-21 11:11:41.752297: step: 940/531, loss: 0.005336951930075884
2023-01-21 11:11:42.918265: step: 944/531, loss: 0.04231281206011772
2023-01-21 11:11:44.031865: step: 948/531, loss: 0.014080810360610485
2023-01-21 11:11:45.153536: step: 952/531, loss: 0.0003616333124227822
2023-01-21 11:11:46.270028: step: 956/531, loss: 0.01487874984741211
2023-01-21 11:11:47.420913: step: 960/531, loss: 0.1063026487827301
2023-01-21 11:11:48.536355: step: 964/531, loss: 0.1509542465209961
2023-01-21 11:11:49.670534: step: 968/531, loss: 0.02918267250061035
2023-01-21 11:11:50.816560: step: 972/531, loss: 0.004044532775878906
2023-01-21 11:11:51.938121: step: 976/531, loss: 0.006843375973403454
2023-01-21 11:11:53.072774: step: 980/531, loss: 0.0710567981004715
2023-01-21 11:11:54.211254: step: 984/531, loss: 0.8567569851875305
2023-01-21 11:11:55.356325: step: 988/531, loss: 0.04856710508465767
2023-01-21 11:11:56.473765: step: 992/531, loss: 0.054155826568603516
2023-01-21 11:11:57.605290: step: 996/531, loss: 0.004180908203125
2023-01-21 11:11:58.722789: step: 1000/531, loss: 0.012790489941835403
2023-01-21 11:11:59.873127: step: 1004/531, loss: 0.0006172180292196572
2023-01-21 11:12:01.016904: step: 1008/531, loss: 0.0117926811799407
2023-01-21 11:12:02.162514: step: 1012/531, loss: 0.28214895725250244
2023-01-21 11:12:03.350226: step: 1016/531, loss: 0.13246899843215942
2023-01-21 11:12:04.498037: step: 1020/531, loss: 0.10410070419311523
2023-01-21 11:12:05.606980: step: 1024/531, loss: 0.014422893524169922
2023-01-21 11:12:06.779354: step: 1028/531, loss: 0.0038860561326146126
2023-01-21 11:12:07.897628: step: 1032/531, loss: 0.015799570828676224
2023-01-21 11:12:09.011980: step: 1036/531, loss: 0.062032513320446014
2023-01-21 11:12:10.170296: step: 1040/531, loss: 0.04151182249188423
2023-01-21 11:12:11.315634: step: 1044/531, loss: 0.011372757144272327
2023-01-21 11:12:12.484998: step: 1048/531, loss: 0.0026180266868323088
2023-01-21 11:12:13.629620: step: 1052/531, loss: 0.06060199812054634
2023-01-21 11:12:14.754277: step: 1056/531, loss: 0.07490377873182297
2023-01-21 11:12:15.895690: step: 1060/531, loss: 0.08485298603773117
2023-01-21 11:12:17.041773: step: 1064/531, loss: 0.020595360547304153
2023-01-21 11:12:18.199902: step: 1068/531, loss: 0.010837269015610218
2023-01-21 11:12:19.352515: step: 1072/531, loss: 3.924369957530871e-05
2023-01-21 11:12:20.501912: step: 1076/531, loss: 0.004365348722785711
2023-01-21 11:12:21.633595: step: 1080/531, loss: 0.0004356384451966733
2023-01-21 11:12:22.802548: step: 1084/531, loss: 0.01933317258954048
2023-01-21 11:12:23.956578: step: 1088/531, loss: 0.020740319043397903
2023-01-21 11:12:25.105732: step: 1092/531, loss: 0.057190895080566406
2023-01-21 11:12:26.261026: step: 1096/531, loss: 0.007929611019790173
2023-01-21 11:12:27.409964: step: 1100/531, loss: 0.023499680683016777
2023-01-21 11:12:28.569759: step: 1104/531, loss: 0.023211481049656868
2023-01-21 11:12:29.715334: step: 1108/531, loss: 0.012027645483613014
2023-01-21 11:12:30.859397: step: 1112/531, loss: 0.01068739965558052
2023-01-21 11:12:31.978899: step: 1116/531, loss: 0.000408172607421875
2023-01-21 11:12:33.122602: step: 1120/531, loss: 0.004358386620879173
2023-01-21 11:12:34.270211: step: 1124/531, loss: 0.4202941954135895
2023-01-21 11:12:35.417639: step: 1128/531, loss: 0.03831319883465767
2023-01-21 11:12:36.634113: step: 1132/531, loss: 0.019341373816132545
2023-01-21 11:12:37.780709: step: 1136/531, loss: 0.013365697115659714
2023-01-21 11:12:38.914990: step: 1140/531, loss: 0.014270162209868431
2023-01-21 11:12:40.069675: step: 1144/531, loss: 0.1033555120229721
2023-01-21 11:12:41.199133: step: 1148/531, loss: 0.00143346784170717
2023-01-21 11:12:42.366974: step: 1152/531, loss: 0.004264545626938343
2023-01-21 11:12:43.513664: step: 1156/531, loss: 0.09733843803405762
2023-01-21 11:12:44.664562: step: 1160/531, loss: 0.0415164940059185
2023-01-21 11:12:45.802915: step: 1164/531, loss: 0.017017554491758347
2023-01-21 11:12:46.965132: step: 1168/531, loss: 0.03323431313037872
2023-01-21 11:12:48.171982: step: 1172/531, loss: 0.00034008026705123484
2023-01-21 11:12:49.313222: step: 1176/531, loss: 0.007091331761330366
2023-01-21 11:12:50.472970: step: 1180/531, loss: 0.10011768341064453
2023-01-21 11:12:51.627159: step: 1184/531, loss: 0.005597543902695179
2023-01-21 11:12:52.790979: step: 1188/531, loss: 0.04480300098657608
2023-01-21 11:12:53.945550: step: 1192/531, loss: 0.018289949744939804
2023-01-21 11:12:55.117174: step: 1196/531, loss: 0.007702135946601629
2023-01-21 11:12:56.252669: step: 1200/531, loss: 0.011410808190703392
2023-01-21 11:12:57.388117: step: 1204/531, loss: 0.5520318746566772
2023-01-21 11:12:58.591450: step: 1208/531, loss: 0.01717986911535263
2023-01-21 11:12:59.759639: step: 1212/531, loss: 0.26149678230285645
2023-01-21 11:13:00.892380: step: 1216/531, loss: 0.02206115797162056
2023-01-21 11:13:02.057852: step: 1220/531, loss: 0.001935768174007535
2023-01-21 11:13:03.203993: step: 1224/531, loss: 0.030426407232880592
2023-01-21 11:13:04.326757: step: 1228/531, loss: 0.014526509679853916
2023-01-21 11:13:05.464828: step: 1232/531, loss: 0.008053588680922985
2023-01-21 11:13:06.594790: step: 1236/531, loss: 0.03564424812793732
2023-01-21 11:13:07.732415: step: 1240/531, loss: 0.0037119868211448193
2023-01-21 11:13:08.859713: step: 1244/531, loss: 0.28150081634521484
2023-01-21 11:13:10.030918: step: 1248/531, loss: 0.014241814613342285
2023-01-21 11:13:11.229776: step: 1252/531, loss: 0.010227775201201439
2023-01-21 11:13:12.387371: step: 1256/531, loss: 0.021290970966219902
2023-01-21 11:13:13.544420: step: 1260/531, loss: 0.018506528809666634
2023-01-21 11:13:14.665982: step: 1264/531, loss: 0.012568999081850052
2023-01-21 11:13:15.799866: step: 1268/531, loss: 0.02321491204202175
2023-01-21 11:13:16.947924: step: 1272/531, loss: 0.0386958122253418
2023-01-21 11:13:18.086035: step: 1276/531, loss: 0.025794124230742455
2023-01-21 11:13:19.228196: step: 1280/531, loss: 0.03951244428753853
2023-01-21 11:13:20.385018: step: 1284/531, loss: 0.018988801166415215
2023-01-21 11:13:21.510009: step: 1288/531, loss: 0.04791221395134926
2023-01-21 11:13:22.669309: step: 1292/531, loss: 0.004714107606559992
2023-01-21 11:13:23.821177: step: 1296/531, loss: 0.15160693228244781
2023-01-21 11:13:24.964778: step: 1300/531, loss: 0.0006214141612872481
2023-01-21 11:13:26.071156: step: 1304/531, loss: 0.028431225568056107
2023-01-21 11:13:27.231161: step: 1308/531, loss: 0.12417946010828018
2023-01-21 11:13:28.375147: step: 1312/531, loss: 0.023177146911621094
2023-01-21 11:13:29.514939: step: 1316/531, loss: 0.044016458094120026
2023-01-21 11:13:30.653221: step: 1320/531, loss: 0.02003050036728382
2023-01-21 11:13:31.815342: step: 1324/531, loss: 0.00012286155833862722
2023-01-21 11:13:32.988200: step: 1328/531, loss: 0.01183023490011692
2023-01-21 11:13:34.107984: step: 1332/531, loss: 0.0051094056107103825
2023-01-21 11:13:35.249197: step: 1336/531, loss: 0.0355289950966835
2023-01-21 11:13:36.371545: step: 1340/531, loss: 0.004100990481674671
2023-01-21 11:13:37.529236: step: 1344/531, loss: 0.009284497238695621
2023-01-21 11:13:38.674816: step: 1348/531, loss: 0.014715003781020641
2023-01-21 11:13:39.800254: step: 1352/531, loss: 0.0006219864008016884
2023-01-21 11:13:40.979069: step: 1356/531, loss: 0.0850229263305664
2023-01-21 11:13:42.136846: step: 1360/531, loss: 0.003867262741550803
2023-01-21 11:13:43.329651: step: 1364/531, loss: 0.7309063076972961
2023-01-21 11:13:44.437621: step: 1368/531, loss: 0.005594921298325062
2023-01-21 11:13:45.584638: step: 1372/531, loss: 0.06299133598804474
2023-01-21 11:13:46.697076: step: 1376/531, loss: 0.020908737555146217
2023-01-21 11:13:47.818430: step: 1380/531, loss: 0.010369682684540749
2023-01-21 11:13:48.963653: step: 1384/531, loss: 0.0023213387466967106
2023-01-21 11:13:50.130108: step: 1388/531, loss: 0.015612220391631126
2023-01-21 11:13:51.304783: step: 1392/531, loss: 0.0018318176735192537
2023-01-21 11:13:52.417467: step: 1396/531, loss: 0.002593779470771551
2023-01-21 11:13:53.617371: step: 1400/531, loss: 0.05279693752527237
2023-01-21 11:13:54.804235: step: 1404/531, loss: 0.019677162170410156
2023-01-21 11:13:55.948195: step: 1408/531, loss: 0.0005475044017657638
2023-01-21 11:13:57.077151: step: 1412/531, loss: 0.050246335566043854
2023-01-21 11:13:58.216306: step: 1416/531, loss: 0.027476787567138672
2023-01-21 11:13:59.331761: step: 1420/531, loss: 0.005717468447983265
2023-01-21 11:14:00.452303: step: 1424/531, loss: 0.031079886481165886
2023-01-21 11:14:01.576814: step: 1428/531, loss: 0.0009953498374670744
2023-01-21 11:14:02.710338: step: 1432/531, loss: 0.011181640438735485
2023-01-21 11:14:03.862723: step: 1436/531, loss: 0.01950206607580185
2023-01-21 11:14:05.003169: step: 1440/531, loss: 0.03135652467608452
2023-01-21 11:14:06.209937: step: 1444/531, loss: 0.029941465705633163
2023-01-21 11:14:07.341973: step: 1448/531, loss: 0.048130229115486145
2023-01-21 11:14:08.488177: step: 1452/531, loss: 0.06347064673900604
2023-01-21 11:14:09.628193: step: 1456/531, loss: 0.010523248463869095
2023-01-21 11:14:10.752882: step: 1460/531, loss: 0.07009506225585938
2023-01-21 11:14:11.897607: step: 1464/531, loss: 0.0037800788413733244
2023-01-21 11:14:13.025632: step: 1468/531, loss: 0.01076512411236763
2023-01-21 11:14:14.185521: step: 1472/531, loss: 0.004036140628159046
2023-01-21 11:14:15.333884: step: 1476/531, loss: 0.01759796217083931
2023-01-21 11:14:16.511115: step: 1480/531, loss: 0.0016837120056152344
2023-01-21 11:14:17.652200: step: 1484/531, loss: 0.00872583407908678
2023-01-21 11:14:18.765978: step: 1488/531, loss: 0.004686451051384211
2023-01-21 11:14:19.914980: step: 1492/531, loss: 0.019215773791074753
2023-01-21 11:14:21.053673: step: 1496/531, loss: 0.0013466834789142013
2023-01-21 11:14:22.201240: step: 1500/531, loss: 0.03810291737318039
2023-01-21 11:14:23.346047: step: 1504/531, loss: 0.0024088858626782894
2023-01-21 11:14:24.472077: step: 1508/531, loss: 0.004228973761200905
2023-01-21 11:14:25.633602: step: 1512/531, loss: 0.011442375369369984
2023-01-21 11:14:26.784481: step: 1516/531, loss: 0.046485330909490585
2023-01-21 11:14:27.912099: step: 1520/531, loss: 0.06269045174121857
2023-01-21 11:14:29.044699: step: 1524/531, loss: 0.02621002309024334
2023-01-21 11:14:30.186400: step: 1528/531, loss: 0.0002887725713662803
2023-01-21 11:14:31.361879: step: 1532/531, loss: 0.01461338996887207
2023-01-21 11:14:32.526342: step: 1536/531, loss: 0.023173904046416283
2023-01-21 11:14:33.667663: step: 1540/531, loss: 0.004830074496567249
2023-01-21 11:14:34.837503: step: 1544/531, loss: 0.0016841889591887593
2023-01-21 11:14:35.979219: step: 1548/531, loss: 0.07658348232507706
2023-01-21 11:14:37.118428: step: 1552/531, loss: 0.005435085389763117
2023-01-21 11:14:38.254762: step: 1556/531, loss: 0.04328766092658043
2023-01-21 11:14:39.391296: step: 1560/531, loss: 0.02664356306195259
2023-01-21 11:14:40.513848: step: 1564/531, loss: 0.04607276991009712
2023-01-21 11:14:41.640135: step: 1568/531, loss: 0.02232837677001953
2023-01-21 11:14:42.808524: step: 1572/531, loss: 0.0014587403275072575
2023-01-21 11:14:43.937893: step: 1576/531, loss: 0.005397796630859375
2023-01-21 11:14:45.070795: step: 1580/531, loss: 0.008266639895737171
2023-01-21 11:14:46.196945: step: 1584/531, loss: 0.02608470991253853
2023-01-21 11:14:47.366133: step: 1588/531, loss: 0.005488777067512274
2023-01-21 11:14:48.539623: step: 1592/531, loss: 0.007983780466020107
2023-01-21 11:14:49.652343: step: 1596/531, loss: 0.04418673366308212
2023-01-21 11:14:50.783775: step: 1600/531, loss: 0.02939739264547825
2023-01-21 11:14:51.914084: step: 1604/531, loss: 0.05591907724738121
2023-01-21 11:14:53.080408: step: 1608/531, loss: 0.031000901013612747
2023-01-21 11:14:54.232224: step: 1612/531, loss: 0.036405373364686966
2023-01-21 11:14:55.361050: step: 1616/531, loss: 0.026595687493681908
2023-01-21 11:14:56.505073: step: 1620/531, loss: 0.00045881271944381297
2023-01-21 11:14:57.683732: step: 1624/531, loss: 0.02132396772503853
2023-01-21 11:14:58.800073: step: 1628/531, loss: 0.05131196975708008
2023-01-21 11:14:59.959647: step: 1632/531, loss: 0.0006000518915243447
2023-01-21 11:15:01.074883: step: 1636/531, loss: 0.02595844306051731
2023-01-21 11:15:02.199142: step: 1640/531, loss: 0.01328048761934042
2023-01-21 11:15:03.338863: step: 1644/531, loss: 0.01994762383401394
2023-01-21 11:15:04.508074: step: 1648/531, loss: 0.0467371940612793
2023-01-21 11:15:05.633019: step: 1652/531, loss: 0.012303399853408337
2023-01-21 11:15:06.745855: step: 1656/531, loss: 0.060896873474121094
2023-01-21 11:15:07.870207: step: 1660/531, loss: 0.012256860733032227
2023-01-21 11:15:09.018367: step: 1664/531, loss: 0.0036530494689941406
2023-01-21 11:15:10.149995: step: 1668/531, loss: 0.012294769287109375
2023-01-21 11:15:11.266238: step: 1672/531, loss: 0.008628464303910732
2023-01-21 11:15:12.385388: step: 1676/531, loss: 0.008865357376635075
2023-01-21 11:15:13.488972: step: 1680/531, loss: 0.02076139487326145
2023-01-21 11:15:14.612595: step: 1684/531, loss: 0.01755077950656414
2023-01-21 11:15:15.745349: step: 1688/531, loss: 0.016353609040379524
2023-01-21 11:15:16.893353: step: 1692/531, loss: 0.07838574051856995
2023-01-21 11:15:18.028680: step: 1696/531, loss: 0.014557838439941406
2023-01-21 11:15:19.142910: step: 1700/531, loss: 0.0006496429559774697
2023-01-21 11:15:20.280832: step: 1704/531, loss: 0.019725609570741653
2023-01-21 11:15:21.426669: step: 1708/531, loss: 0.04597339779138565
2023-01-21 11:15:22.580054: step: 1712/531, loss: 0.6879486441612244
2023-01-21 11:15:23.701245: step: 1716/531, loss: 0.10511636734008789
2023-01-21 11:15:24.844093: step: 1720/531, loss: 0.001472091767936945
2023-01-21 11:15:25.987585: step: 1724/531, loss: 0.06482386589050293
2023-01-21 11:15:27.150167: step: 1728/531, loss: 0.083740234375
2023-01-21 11:15:28.301817: step: 1732/531, loss: 0.00684013357385993
2023-01-21 11:15:29.450861: step: 1736/531, loss: 0.026021480560302734
2023-01-21 11:15:30.595945: step: 1740/531, loss: 0.0027683258522301912
2023-01-21 11:15:31.751512: step: 1744/531, loss: 0.007908154278993607
2023-01-21 11:15:32.877505: step: 1748/531, loss: 0.0014129638439044356
2023-01-21 11:15:34.033248: step: 1752/531, loss: 0.02902822569012642
2023-01-21 11:15:35.173008: step: 1756/531, loss: 0.01378488540649414
2023-01-21 11:15:36.327490: step: 1760/531, loss: 0.013411951251327991
2023-01-21 11:15:37.490153: step: 1764/531, loss: 0.000992977642454207
2023-01-21 11:15:38.627622: step: 1768/531, loss: 0.015405083075165749
2023-01-21 11:15:39.745749: step: 1772/531, loss: 0.05477790907025337
2023-01-21 11:15:40.915034: step: 1776/531, loss: 0.007916450500488281
2023-01-21 11:15:42.046467: step: 1780/531, loss: 0.01865072175860405
2023-01-21 11:15:43.207564: step: 1784/531, loss: 0.020322799682617188
2023-01-21 11:15:44.334078: step: 1788/531, loss: 0.014657402411103249
2023-01-21 11:15:45.458095: step: 1792/531, loss: 0.5551536679267883
2023-01-21 11:15:46.589187: step: 1796/531, loss: 0.03054780885577202
2023-01-21 11:15:47.713101: step: 1800/531, loss: 0.020275497809052467
2023-01-21 11:15:48.835212: step: 1804/531, loss: 0.04089293256402016
2023-01-21 11:15:49.960351: step: 1808/531, loss: 0.07146720588207245
2023-01-21 11:15:51.114811: step: 1812/531, loss: 0.030412817373871803
2023-01-21 11:15:52.246867: step: 1816/531, loss: 0.022384166717529297
2023-01-21 11:15:53.380549: step: 1820/531, loss: 0.016867447644472122
2023-01-21 11:15:54.542076: step: 1824/531, loss: 0.043793488293886185
2023-01-21 11:15:55.663836: step: 1828/531, loss: 0.07372169196605682
2023-01-21 11:15:56.797189: step: 1832/531, loss: 0.00610122736543417
2023-01-21 11:15:57.935934: step: 1836/531, loss: 0.09406938403844833
2023-01-21 11:15:59.096157: step: 1840/531, loss: 0.0034509659744799137
2023-01-21 11:16:00.233347: step: 1844/531, loss: 0.00033597947913222015
2023-01-21 11:16:01.390047: step: 1848/531, loss: 0.10502815246582031
2023-01-21 11:16:02.523770: step: 1852/531, loss: 0.00011377334885764867
2023-01-21 11:16:03.668926: step: 1856/531, loss: 0.021224401891231537
2023-01-21 11:16:04.814301: step: 1860/531, loss: 0.1867271214723587
2023-01-21 11:16:05.923067: step: 1864/531, loss: 0.09906559437513351
2023-01-21 11:16:07.042065: step: 1868/531, loss: 0.054347991943359375
2023-01-21 11:16:08.227481: step: 1872/531, loss: 0.04394808039069176
2023-01-21 11:16:09.402029: step: 1876/531, loss: 0.04727435111999512
2023-01-21 11:16:10.525716: step: 1880/531, loss: 0.02191181294620037
2023-01-21 11:16:11.670642: step: 1884/531, loss: 0.00016999244689941406
2023-01-21 11:16:12.805675: step: 1888/531, loss: 0.14360013604164124
2023-01-21 11:16:13.976037: step: 1892/531, loss: 0.09328394383192062
2023-01-21 11:16:15.120374: step: 1896/531, loss: 0.02176504209637642
2023-01-21 11:16:16.269217: step: 1900/531, loss: 0.0007488250848837197
2023-01-21 11:16:17.417088: step: 1904/531, loss: 0.00410571089014411
2023-01-21 11:16:18.553781: step: 1908/531, loss: 0.0034383772872388363
2023-01-21 11:16:19.688038: step: 1912/531, loss: 0.019974900409579277
2023-01-21 11:16:20.831178: step: 1916/531, loss: 0.05625209957361221
2023-01-21 11:16:21.983496: step: 1920/531, loss: 0.03726644814014435
2023-01-21 11:16:23.117870: step: 1924/531, loss: 0.001233005546964705
2023-01-21 11:16:24.279013: step: 1928/531, loss: 0.07823486626148224
2023-01-21 11:16:25.429309: step: 1932/531, loss: 0.002031993819400668
2023-01-21 11:16:26.537363: step: 1936/531, loss: 0.00043740271939896047
2023-01-21 11:16:27.705597: step: 1940/531, loss: 0.03054656833410263
2023-01-21 11:16:28.855310: step: 1944/531, loss: 0.0013572931056842208
2023-01-21 11:16:29.975264: step: 1948/531, loss: 0.05219784006476402
2023-01-21 11:16:31.139218: step: 1952/531, loss: 0.027754690498113632
2023-01-21 11:16:32.267618: step: 1956/531, loss: 0.05327634885907173
2023-01-21 11:16:33.391582: step: 1960/531, loss: 0.06169535964727402
2023-01-21 11:16:34.508399: step: 1964/531, loss: 0.0258149616420269
2023-01-21 11:16:35.652172: step: 1968/531, loss: 0.007311439607292414
2023-01-21 11:16:36.796208: step: 1972/531, loss: 0.02728271484375
2023-01-21 11:16:37.925827: step: 1976/531, loss: 0.000264072441495955
2023-01-21 11:16:39.098532: step: 1980/531, loss: 0.030834389850497246
2023-01-21 11:16:40.236051: step: 1984/531, loss: 0.0017687797080725431
2023-01-21 11:16:41.359306: step: 1988/531, loss: 0.05214662477374077
2023-01-21 11:16:42.510938: step: 1992/531, loss: 0.007312393747270107
2023-01-21 11:16:43.673034: step: 1996/531, loss: 0.036153316497802734
2023-01-21 11:16:44.802639: step: 2000/531, loss: 0.0008543014992028475
2023-01-21 11:16:45.914280: step: 2004/531, loss: 0.06206831708550453
2023-01-21 11:16:47.057393: step: 2008/531, loss: 0.0641569122672081
2023-01-21 11:16:48.201167: step: 2012/531, loss: 0.021302510052919388
2023-01-21 11:16:49.353988: step: 2016/531, loss: 0.002459716983139515
2023-01-21 11:16:50.520886: step: 2020/531, loss: 0.04087505117058754
2023-01-21 11:16:51.661197: step: 2024/531, loss: 0.00456657400354743
2023-01-21 11:16:52.823967: step: 2028/531, loss: 0.0673370361328125
2023-01-21 11:16:53.965423: step: 2032/531, loss: 0.015209055505692959
2023-01-21 11:16:55.102362: step: 2036/531, loss: 0.0769510269165039
2023-01-21 11:16:56.233730: step: 2040/531, loss: 0.04460039362311363
2023-01-21 11:16:57.348082: step: 2044/531, loss: 0.0016989231808111072
2023-01-21 11:16:58.461220: step: 2048/531, loss: 0.022928334772586823
2023-01-21 11:16:59.596573: step: 2052/531, loss: 0.03409919887781143
2023-01-21 11:17:00.751413: step: 2056/531, loss: 0.013751983642578125
2023-01-21 11:17:01.891346: step: 2060/531, loss: 0.042627573013305664
2023-01-21 11:17:03.091256: step: 2064/531, loss: 0.03130446746945381
2023-01-21 11:17:04.243828: step: 2068/531, loss: 0.037835218012332916
2023-01-21 11:17:05.357647: step: 2072/531, loss: 0.0014135361416265368
2023-01-21 11:17:06.490042: step: 2076/531, loss: 0.0061817169189453125
2023-01-21 11:17:07.628701: step: 2080/531, loss: 0.0003016948467120528
2023-01-21 11:17:08.751813: step: 2084/531, loss: 0.05926189571619034
2023-01-21 11:17:09.921423: step: 2088/531, loss: 0.07403528690338135
2023-01-21 11:17:11.023844: step: 2092/531, loss: 0.006610870826989412
2023-01-21 11:17:12.213099: step: 2096/531, loss: 0.00043539999751374125
2023-01-21 11:17:13.337369: step: 2100/531, loss: 0.010175991803407669
2023-01-21 11:17:14.479605: step: 2104/531, loss: 0.00267620082013309
2023-01-21 11:17:15.630645: step: 2108/531, loss: 0.039144039154052734
2023-01-21 11:17:16.799317: step: 2112/531, loss: 0.037192247807979584
2023-01-21 11:17:17.968457: step: 2116/531, loss: 0.007502746302634478
2023-01-21 11:17:19.128700: step: 2120/531, loss: 0.016350459307432175
2023-01-21 11:17:20.260260: step: 2124/531, loss: 0.10162334144115448
==================================================
Loss: 0.056
--------------------
Dev: {'event': {'p': 0.5949494949494949, 'r': 0.7842876165113183, 'f1': 0.6766226306720274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6321564885496184, 'r': 0.7901013714967203, 'f1': 0.7023588656241717}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
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': 15}
Korean: {'event': {'p': 0.6071428571428571, 'r': 0.5396825396825397, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.44680851063829785, 'r': 0.5833333333333334, 'f1': 0.5060240963855422}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:18:02.364635: step: 4/531, loss: 0.2521275579929352
2023-01-21 11:18:03.475337: step: 8/531, loss: 0.006723976228386164
2023-01-21 11:18:04.615621: step: 12/531, loss: 0.0032130242325365543
2023-01-21 11:18:05.759508: step: 16/531, loss: 0.03483247756958008
2023-01-21 11:18:06.877842: step: 20/531, loss: 0.004098653793334961
2023-01-21 11:18:07.995302: step: 24/531, loss: 0.00012521744065452367
2023-01-21 11:18:09.119384: step: 28/531, loss: 0.0009501457097940147
2023-01-21 11:18:10.265219: step: 32/531, loss: 0.01824159547686577
2023-01-21 11:18:11.430149: step: 36/531, loss: 0.00128688826225698
2023-01-21 11:18:12.571900: step: 40/531, loss: 0.04172954708337784
2023-01-21 11:18:13.706829: step: 44/531, loss: 0.0052734375931322575
2023-01-21 11:18:14.804597: step: 48/531, loss: 0.0008638381841592491
2023-01-21 11:18:15.972984: step: 52/531, loss: 0.02124939113855362
2023-01-21 11:18:17.119022: step: 56/531, loss: 0.010611867532134056
2023-01-21 11:18:18.266612: step: 60/531, loss: 0.046534158289432526
2023-01-21 11:18:19.397739: step: 64/531, loss: 0.008616066537797451
2023-01-21 11:18:20.560911: step: 68/531, loss: 0.022318650037050247
2023-01-21 11:18:21.713081: step: 72/531, loss: 0.015177154913544655
2023-01-21 11:18:22.856384: step: 76/531, loss: 0.009215832687914371
2023-01-21 11:18:23.980188: step: 80/531, loss: 0.0042175292037427425
2023-01-21 11:18:25.143944: step: 84/531, loss: 0.007029390893876553
2023-01-21 11:18:26.280945: step: 88/531, loss: 0.007113838102668524
2023-01-21 11:18:27.470021: step: 92/531, loss: 0.023394394665956497
2023-01-21 11:18:28.647865: step: 96/531, loss: 0.04689941555261612
2023-01-21 11:18:29.766944: step: 100/531, loss: 0.6909419894218445
2023-01-21 11:18:30.926459: step: 104/531, loss: 0.014201641082763672
2023-01-21 11:18:32.097247: step: 108/531, loss: 0.017704010009765625
2023-01-21 11:18:33.216924: step: 112/531, loss: 0.002296066377311945
2023-01-21 11:18:34.355805: step: 116/531, loss: 0.05105840042233467
2023-01-21 11:18:35.503121: step: 120/531, loss: 0.0019364356994628906
2023-01-21 11:18:36.619434: step: 124/531, loss: 0.11028274148702621
2023-01-21 11:18:37.765008: step: 128/531, loss: 0.00010409355309093371
2023-01-21 11:18:38.955329: step: 132/531, loss: 0.038350678980350494
2023-01-21 11:18:40.091246: step: 136/531, loss: 0.005510807037353516
2023-01-21 11:18:41.223930: step: 140/531, loss: 0.021910762414336205
2023-01-21 11:18:42.400302: step: 144/531, loss: 0.011336899362504482
2023-01-21 11:18:43.512283: step: 148/531, loss: 0.0018449783092364669
2023-01-21 11:18:44.644452: step: 152/531, loss: 0.009054851718246937
2023-01-21 11:18:45.792713: step: 156/531, loss: 0.022633124142885208
2023-01-21 11:18:46.912585: step: 160/531, loss: 0.023503970354795456
2023-01-21 11:18:48.045202: step: 164/531, loss: 0.01003198605030775
2023-01-21 11:18:49.154290: step: 168/531, loss: 0.073033906519413
2023-01-21 11:18:50.300386: step: 172/531, loss: 0.00035648344783112407
2023-01-21 11:18:51.450328: step: 176/531, loss: 0.014524651691317558
2023-01-21 11:18:52.560190: step: 180/531, loss: 9.17434663278982e-05
2023-01-21 11:18:53.692248: step: 184/531, loss: 0.11682777106761932
2023-01-21 11:18:54.806940: step: 188/531, loss: 0.03980856016278267
2023-01-21 11:18:55.931133: step: 192/531, loss: 0.034307099878787994
2023-01-21 11:18:57.036092: step: 196/531, loss: 0.018357181921601295
2023-01-21 11:18:58.168171: step: 200/531, loss: 0.009448242373764515
2023-01-21 11:18:59.336875: step: 204/531, loss: 0.005802631378173828
2023-01-21 11:19:00.450817: step: 208/531, loss: 0.01721201092004776
2023-01-21 11:19:01.610213: step: 212/531, loss: 0.05015993118286133
2023-01-21 11:19:02.738068: step: 216/531, loss: 0.0062583922408521175
2023-01-21 11:19:03.881208: step: 220/531, loss: 0.6739804744720459
2023-01-21 11:19:05.018208: step: 224/531, loss: 0.0036876678932458162
2023-01-21 11:19:06.145225: step: 228/531, loss: 0.02613544464111328
2023-01-21 11:19:07.270430: step: 232/531, loss: 0.020329046994447708
2023-01-21 11:19:08.415377: step: 236/531, loss: 0.011905861087143421
2023-01-21 11:19:09.512586: step: 240/531, loss: 0.03851490095257759
2023-01-21 11:19:10.647150: step: 244/531, loss: 0.026909923180937767
2023-01-21 11:19:11.795373: step: 248/531, loss: 0.05736055597662926
2023-01-21 11:19:12.929397: step: 252/531, loss: 0.008288002572953701
2023-01-21 11:19:14.047361: step: 256/531, loss: 0.049338627606630325
2023-01-21 11:19:15.192437: step: 260/531, loss: 0.037832166999578476
2023-01-21 11:19:16.338305: step: 264/531, loss: 0.004467487335205078
2023-01-21 11:19:17.479921: step: 268/531, loss: 0.025663472712039948
2023-01-21 11:19:18.634512: step: 272/531, loss: 0.00010519028000999242
2023-01-21 11:19:19.780534: step: 276/531, loss: 0.03365039825439453
2023-01-21 11:19:20.914041: step: 280/531, loss: 0.0009822845458984375
2023-01-21 11:19:22.051798: step: 284/531, loss: 0.031194305047392845
2023-01-21 11:19:23.166742: step: 288/531, loss: 0.0016650677425786853
2023-01-21 11:19:24.288098: step: 292/531, loss: 0.24374103546142578
2023-01-21 11:19:25.452597: step: 296/531, loss: 0.035718392580747604
2023-01-21 11:19:26.605812: step: 300/531, loss: 0.06796932220458984
2023-01-21 11:19:27.793778: step: 304/531, loss: 0.2714877724647522
2023-01-21 11:19:28.976393: step: 308/531, loss: 0.027812767773866653
2023-01-21 11:19:30.110272: step: 312/531, loss: 0.03317318111658096
2023-01-21 11:19:31.269572: step: 316/531, loss: 0.03608722612261772
2023-01-21 11:19:32.374675: step: 320/531, loss: 0.06954164803028107
2023-01-21 11:19:33.509342: step: 324/531, loss: 0.024041511118412018
2023-01-21 11:19:34.664616: step: 328/531, loss: 0.0024276257026940584
2023-01-21 11:19:35.803842: step: 332/531, loss: 0.0506032258272171
2023-01-21 11:19:36.925003: step: 336/531, loss: 0.2203085869550705
2023-01-21 11:19:38.050937: step: 340/531, loss: 0.13547289371490479
2023-01-21 11:19:39.190769: step: 344/531, loss: 0.013545037247240543
2023-01-21 11:19:40.346408: step: 348/531, loss: 0.0306059829890728
2023-01-21 11:19:41.485255: step: 352/531, loss: 0.013831520453095436
2023-01-21 11:19:42.652125: step: 356/531, loss: 0.005435275845229626
2023-01-21 11:19:43.779901: step: 360/531, loss: 0.02701110951602459
2023-01-21 11:19:44.900094: step: 364/531, loss: 0.03365010395646095
2023-01-21 11:19:46.006436: step: 368/531, loss: 0.0042716506868600845
2023-01-21 11:19:47.164210: step: 372/531, loss: 0.021305084228515625
2023-01-21 11:19:48.295157: step: 376/531, loss: 0.031024647876620293
2023-01-21 11:19:49.409682: step: 380/531, loss: 0.034691907465457916
2023-01-21 11:19:50.562010: step: 384/531, loss: 0.00045037269592285156
2023-01-21 11:19:51.675974: step: 388/531, loss: 0.0058265686966478825
2023-01-21 11:19:52.814458: step: 392/531, loss: 0.00031147003755904734
2023-01-21 11:19:53.950914: step: 396/531, loss: 0.059551481157541275
2023-01-21 11:19:55.115120: step: 400/531, loss: 0.0031669619493186474
2023-01-21 11:19:56.271628: step: 404/531, loss: 0.0009012222290039062
2023-01-21 11:19:57.414114: step: 408/531, loss: 0.0007403374183923006
2023-01-21 11:19:58.557590: step: 412/531, loss: 0.09400273114442825
2023-01-21 11:19:59.744426: step: 416/531, loss: 0.01275711040943861
2023-01-21 11:20:00.898574: step: 420/531, loss: 0.016127299517393112
2023-01-21 11:20:02.051361: step: 424/531, loss: 0.007638359442353249
2023-01-21 11:20:03.199891: step: 428/531, loss: 0.0017737388843670487
2023-01-21 11:20:04.335927: step: 432/531, loss: 0.06195177882909775
2023-01-21 11:20:05.451121: step: 436/531, loss: 0.013400459662079811
2023-01-21 11:20:06.614192: step: 440/531, loss: 0.04996900632977486
2023-01-21 11:20:07.747129: step: 444/531, loss: 0.010785484686493874
2023-01-21 11:20:08.887827: step: 448/531, loss: 0.04684562608599663
2023-01-21 11:20:10.028468: step: 452/531, loss: 0.13047657907009125
2023-01-21 11:20:11.201535: step: 456/531, loss: 0.019899750128388405
2023-01-21 11:20:12.349690: step: 460/531, loss: 0.06284981220960617
2023-01-21 11:20:13.506250: step: 464/531, loss: 0.09371356666088104
2023-01-21 11:20:14.631027: step: 468/531, loss: 0.016196012496948242
2023-01-21 11:20:15.787739: step: 472/531, loss: 0.0013395310379564762
2023-01-21 11:20:16.903580: step: 476/531, loss: 0.025235557928681374
2023-01-21 11:20:18.035883: step: 480/531, loss: 0.019955921918153763
2023-01-21 11:20:19.187375: step: 484/531, loss: 0.03935671225190163
2023-01-21 11:20:20.331664: step: 488/531, loss: 0.014825058169662952
2023-01-21 11:20:21.545698: step: 492/531, loss: 0.08416537940502167
2023-01-21 11:20:22.687061: step: 496/531, loss: 0.039305686950683594
2023-01-21 11:20:23.812455: step: 500/531, loss: 0.0184999480843544
2023-01-21 11:20:24.959169: step: 504/531, loss: 0.017728902399539948
2023-01-21 11:20:26.103296: step: 508/531, loss: 0.006518745329231024
2023-01-21 11:20:27.244479: step: 512/531, loss: 0.0006950378301553428
2023-01-21 11:20:28.389329: step: 516/531, loss: 0.1484702080488205
2023-01-21 11:20:29.521744: step: 520/531, loss: 0.039586544036865234
2023-01-21 11:20:30.678503: step: 524/531, loss: 0.0001199722319142893
2023-01-21 11:20:31.838824: step: 528/531, loss: 0.007123088929802179
2023-01-21 11:20:33.017223: step: 532/531, loss: 0.08496637642383575
2023-01-21 11:20:34.151601: step: 536/531, loss: 0.014231586828827858
2023-01-21 11:20:35.302010: step: 540/531, loss: 0.0029655457474291325
2023-01-21 11:20:36.426297: step: 544/531, loss: 0.0591578483581543
2023-01-21 11:20:37.575095: step: 548/531, loss: 0.011067485436797142
2023-01-21 11:20:38.718025: step: 552/531, loss: 0.13879604637622833
2023-01-21 11:20:39.860034: step: 556/531, loss: 0.0028553009033203125
2023-01-21 11:20:40.982421: step: 560/531, loss: 0.0029915333725512028
2023-01-21 11:20:42.128391: step: 564/531, loss: 0.00028715134249068797
2023-01-21 11:20:43.246957: step: 568/531, loss: 0.02383270487189293
2023-01-21 11:20:44.409541: step: 572/531, loss: 0.04071855545043945
2023-01-21 11:20:45.546871: step: 576/531, loss: 0.0007885218365117908
2023-01-21 11:20:46.685715: step: 580/531, loss: 0.01653594896197319
2023-01-21 11:20:47.860804: step: 584/531, loss: 0.031295206397771835
2023-01-21 11:20:49.013613: step: 588/531, loss: 0.0028391839005053043
2023-01-21 11:20:50.140214: step: 592/531, loss: 0.00976715050637722
2023-01-21 11:20:51.286080: step: 596/531, loss: 0.01821594312787056
2023-01-21 11:20:52.490822: step: 600/531, loss: 0.0069814687594771385
2023-01-21 11:20:53.629493: step: 604/531, loss: 0.008567428216338158
2023-01-21 11:20:54.787147: step: 608/531, loss: 0.01463625393807888
2023-01-21 11:20:55.924254: step: 612/531, loss: 0.02741723135113716
2023-01-21 11:20:57.050027: step: 616/531, loss: 0.042025376111269
2023-01-21 11:20:58.225535: step: 620/531, loss: 0.03121819533407688
2023-01-21 11:20:59.361585: step: 624/531, loss: 0.021138859912753105
2023-01-21 11:21:00.499023: step: 628/531, loss: 0.005286884494125843
2023-01-21 11:21:01.632658: step: 632/531, loss: 0.010327721014618874
2023-01-21 11:21:02.806108: step: 636/531, loss: 0.009678078815340996
2023-01-21 11:21:03.974948: step: 640/531, loss: 0.0026352882850915194
2023-01-21 11:21:05.121328: step: 644/531, loss: 0.0016733170486986637
2023-01-21 11:21:06.270898: step: 648/531, loss: 0.00276870746165514
2023-01-21 11:21:07.422905: step: 652/531, loss: 0.00866556167602539
2023-01-21 11:21:08.572810: step: 656/531, loss: 0.01553268451243639
2023-01-21 11:21:09.714370: step: 660/531, loss: 0.04496021196246147
2023-01-21 11:21:10.877382: step: 664/531, loss: 0.009823323227465153
2023-01-21 11:21:11.999333: step: 668/531, loss: 0.019964218139648438
2023-01-21 11:21:13.128725: step: 672/531, loss: 0.018725013360381126
2023-01-21 11:21:14.277329: step: 676/531, loss: 0.049706265330314636
2023-01-21 11:21:15.390298: step: 680/531, loss: 0.041196297854185104
2023-01-21 11:21:16.575921: step: 684/531, loss: 0.005528164096176624
2023-01-21 11:21:17.761285: step: 688/531, loss: 0.04586810991168022
2023-01-21 11:21:18.896480: step: 692/531, loss: 0.028386402875185013
2023-01-21 11:21:20.035903: step: 696/531, loss: 0.05595235899090767
2023-01-21 11:21:21.188671: step: 700/531, loss: 0.00014429092698264867
2023-01-21 11:21:22.361476: step: 704/531, loss: 0.028806114569306374
2023-01-21 11:21:23.478533: step: 708/531, loss: 0.07829227298498154
2023-01-21 11:21:24.612641: step: 712/531, loss: 0.03620128706097603
2023-01-21 11:21:25.733063: step: 716/531, loss: 0.0049717905931174755
2023-01-21 11:21:26.889564: step: 720/531, loss: 0.0002758026239462197
2023-01-21 11:21:28.027011: step: 724/531, loss: 0.11680107563734055
2023-01-21 11:21:29.181367: step: 728/531, loss: 0.004488754086196423
2023-01-21 11:21:30.334557: step: 732/531, loss: 0.06606468558311462
2023-01-21 11:21:31.444549: step: 736/531, loss: 0.08832956105470657
2023-01-21 11:21:32.608319: step: 740/531, loss: 0.000797271728515625
2023-01-21 11:21:33.770376: step: 744/531, loss: 0.2113761007785797
2023-01-21 11:21:34.911216: step: 748/531, loss: 0.0008353710290975869
2023-01-21 11:21:36.058904: step: 752/531, loss: 0.004295444581657648
2023-01-21 11:21:37.215590: step: 756/531, loss: 0.056002333760261536
2023-01-21 11:21:38.400354: step: 760/531, loss: 0.01753845252096653
2023-01-21 11:21:39.529364: step: 764/531, loss: 0.006696129217743874
2023-01-21 11:21:40.672322: step: 768/531, loss: 0.08233197778463364
2023-01-21 11:21:41.820838: step: 772/531, loss: 0.009122371673583984
2023-01-21 11:21:42.998356: step: 776/531, loss: 0.01749582216143608
2023-01-21 11:21:44.116977: step: 780/531, loss: 0.0007336616399697959
2023-01-21 11:21:45.270465: step: 784/531, loss: 0.030775070190429688
2023-01-21 11:21:46.387089: step: 788/531, loss: 0.004580402746796608
2023-01-21 11:21:47.526321: step: 792/531, loss: 0.012348365969955921
2023-01-21 11:21:48.674770: step: 796/531, loss: 0.08743209391832352
2023-01-21 11:21:49.816264: step: 800/531, loss: 0.03028078004717827
2023-01-21 11:21:50.941933: step: 804/531, loss: 0.00019941330538131297
2023-01-21 11:21:52.064640: step: 808/531, loss: 0.009217072278261185
2023-01-21 11:21:53.211143: step: 812/531, loss: 0.0025737525429576635
2023-01-21 11:21:54.345311: step: 816/531, loss: 0.017647838220000267
2023-01-21 11:21:55.503951: step: 820/531, loss: 0.026299476623535156
2023-01-21 11:21:56.641990: step: 824/531, loss: 0.08873309940099716
2023-01-21 11:21:57.817544: step: 828/531, loss: 0.01612529717385769
2023-01-21 11:21:58.970720: step: 832/531, loss: 0.005986213684082031
2023-01-21 11:22:00.123620: step: 836/531, loss: 0.011033820919692516
2023-01-21 11:22:01.258382: step: 840/531, loss: 0.18404893577098846
2023-01-21 11:22:02.393529: step: 844/531, loss: 0.010575294494628906
2023-01-21 11:22:03.535692: step: 848/531, loss: 0.018220329657197
2023-01-21 11:22:04.684189: step: 852/531, loss: 0.022934913635253906
2023-01-21 11:22:05.806529: step: 856/531, loss: 0.051935575902462006
2023-01-21 11:22:06.907191: step: 860/531, loss: 0.0011620521545410156
2023-01-21 11:22:08.044740: step: 864/531, loss: 0.062047481536865234
2023-01-21 11:22:09.192939: step: 868/531, loss: 0.0014314651489257812
2023-01-21 11:22:10.304709: step: 872/531, loss: 0.008043861947953701
2023-01-21 11:22:11.456365: step: 876/531, loss: 0.02506437338888645
2023-01-21 11:22:12.646334: step: 880/531, loss: 0.2291662096977234
2023-01-21 11:22:13.774417: step: 884/531, loss: 0.11822376400232315
2023-01-21 11:22:14.903749: step: 888/531, loss: 0.04041347652673721
2023-01-21 11:22:16.047808: step: 892/531, loss: 0.08089856803417206
2023-01-21 11:22:17.187202: step: 896/531, loss: 0.00497360248118639
2023-01-21 11:22:18.327042: step: 900/531, loss: 0.0037691593170166016
2023-01-21 11:22:19.447508: step: 904/531, loss: 0.03270168602466583
2023-01-21 11:22:20.552041: step: 908/531, loss: 0.0006089209928177297
2023-01-21 11:22:21.681973: step: 912/531, loss: 0.018484115600585938
2023-01-21 11:22:22.828558: step: 916/531, loss: 0.011260032653808594
2023-01-21 11:22:23.986820: step: 920/531, loss: 0.001990461489185691
2023-01-21 11:22:25.124386: step: 924/531, loss: 8.468628220725805e-05
2023-01-21 11:22:26.285715: step: 928/531, loss: 0.014310264959931374
2023-01-21 11:22:27.466171: step: 932/531, loss: 0.004746341612190008
2023-01-21 11:22:28.589155: step: 936/531, loss: 6.699562072753906e-05
2023-01-21 11:22:29.741263: step: 940/531, loss: 0.0012751579051837325
2023-01-21 11:22:30.891395: step: 944/531, loss: 0.008514786139130592
2023-01-21 11:22:32.064796: step: 948/531, loss: 0.01791400834918022
2023-01-21 11:22:33.197155: step: 952/531, loss: 0.023016929626464844
2023-01-21 11:22:34.310892: step: 956/531, loss: 0.021587753668427467
2023-01-21 11:22:35.456760: step: 960/531, loss: 0.024913977831602097
2023-01-21 11:22:36.596786: step: 964/531, loss: 0.011025715619325638
2023-01-21 11:22:37.732463: step: 968/531, loss: 0.030767440795898438
2023-01-21 11:22:38.871317: step: 972/531, loss: 0.05347614362835884
2023-01-21 11:22:40.044757: step: 976/531, loss: 0.0028078078757971525
2023-01-21 11:22:41.202393: step: 980/531, loss: 0.023520469665527344
2023-01-21 11:22:42.370806: step: 984/531, loss: 0.3827234208583832
2023-01-21 11:22:43.542893: step: 988/531, loss: 0.01490707416087389
2023-01-21 11:22:44.704593: step: 992/531, loss: 0.024048617109656334
2023-01-21 11:22:45.863409: step: 996/531, loss: 0.00401649484410882
2023-01-21 11:22:46.978324: step: 1000/531, loss: 0.04343271628022194
2023-01-21 11:22:48.121938: step: 1004/531, loss: 0.10270857810974121
2023-01-21 11:22:49.253121: step: 1008/531, loss: 0.033948518335819244
2023-01-21 11:22:50.396858: step: 1012/531, loss: 0.008781624026596546
2023-01-21 11:22:51.510103: step: 1016/531, loss: 0.026502227410674095
2023-01-21 11:22:52.666115: step: 1020/531, loss: 0.05910911783576012
2023-01-21 11:22:53.823314: step: 1024/531, loss: 0.0040795328095555305
2023-01-21 11:22:54.950232: step: 1028/531, loss: 0.00801396369934082
2023-01-21 11:22:56.069915: step: 1032/531, loss: 0.000980377197265625
2023-01-21 11:22:57.238248: step: 1036/531, loss: 0.003254509065300226
2023-01-21 11:22:58.356669: step: 1040/531, loss: 0.00266609201207757
2023-01-21 11:22:59.477079: step: 1044/531, loss: 0.0018165111541748047
2023-01-21 11:23:00.609064: step: 1048/531, loss: 0.017932796850800514
2023-01-21 11:23:01.748301: step: 1052/531, loss: 0.0004673957882914692
2023-01-21 11:23:02.886106: step: 1056/531, loss: 0.029655171558260918
2023-01-21 11:23:04.013709: step: 1060/531, loss: 0.00557022076100111
2023-01-21 11:23:05.138876: step: 1064/531, loss: 0.005026531405746937
2023-01-21 11:23:06.266123: step: 1068/531, loss: 0.021099090576171875
2023-01-21 11:23:07.401972: step: 1072/531, loss: 0.0560942180454731
2023-01-21 11:23:08.540861: step: 1076/531, loss: 0.8823589086532593
2023-01-21 11:23:09.654480: step: 1080/531, loss: 0.7515289187431335
2023-01-21 11:23:10.775189: step: 1084/531, loss: 0.018741607666015625
2023-01-21 11:23:11.915276: step: 1088/531, loss: 0.005289173219352961
2023-01-21 11:23:13.039013: step: 1092/531, loss: 0.023261072114109993
2023-01-21 11:23:14.194925: step: 1096/531, loss: 0.33323726058006287
2023-01-21 11:23:15.333758: step: 1100/531, loss: 0.004673004150390625
2023-01-21 11:23:16.508543: step: 1104/531, loss: 0.04440317302942276
2023-01-21 11:23:17.649860: step: 1108/531, loss: 0.002774047665297985
2023-01-21 11:23:18.793043: step: 1112/531, loss: 0.012278461828827858
2023-01-21 11:23:19.921162: step: 1116/531, loss: 0.0557108148932457
2023-01-21 11:23:21.103734: step: 1120/531, loss: 0.015136814676225185
2023-01-21 11:23:22.234851: step: 1124/531, loss: 0.006009864620864391
2023-01-21 11:23:23.381849: step: 1128/531, loss: 0.011852741241455078
2023-01-21 11:23:24.512858: step: 1132/531, loss: 0.004689216613769531
2023-01-21 11:23:25.657799: step: 1136/531, loss: 0.0004371643008198589
2023-01-21 11:23:26.791142: step: 1140/531, loss: 0.0035324099007993937
2023-01-21 11:23:27.922132: step: 1144/531, loss: 0.036432839930057526
2023-01-21 11:23:29.052077: step: 1148/531, loss: 0.010029220022261143
2023-01-21 11:23:30.159639: step: 1152/531, loss: 0.0002424240083200857
2023-01-21 11:23:31.296378: step: 1156/531, loss: 0.0031097412575036287
2023-01-21 11:23:32.435274: step: 1160/531, loss: 0.02171182632446289
2023-01-21 11:23:33.571087: step: 1164/531, loss: 0.0006812096107751131
2023-01-21 11:23:34.702845: step: 1168/531, loss: 0.002594852354377508
2023-01-21 11:23:35.880620: step: 1172/531, loss: 0.020543480291962624
2023-01-21 11:23:37.034750: step: 1176/531, loss: 0.12869758903980255
2023-01-21 11:23:38.175331: step: 1180/531, loss: 0.03174304962158203
2023-01-21 11:23:39.330005: step: 1184/531, loss: 0.027428055182099342
2023-01-21 11:23:40.479751: step: 1188/531, loss: 0.00010080337233375758
2023-01-21 11:23:41.651079: step: 1192/531, loss: 0.048986244946718216
2023-01-21 11:23:42.783127: step: 1196/531, loss: 0.00484886160120368
2023-01-21 11:23:43.926108: step: 1200/531, loss: 0.0312800407409668
2023-01-21 11:23:45.089756: step: 1204/531, loss: 0.01782398298382759
2023-01-21 11:23:46.217278: step: 1208/531, loss: 0.029322339221835136
2023-01-21 11:23:47.366520: step: 1212/531, loss: 0.02630338817834854
2023-01-21 11:23:48.537168: step: 1216/531, loss: 0.028730392456054688
2023-01-21 11:23:49.662589: step: 1220/531, loss: 0.004925251007080078
2023-01-21 11:23:50.760792: step: 1224/531, loss: 0.02300058677792549
2023-01-21 11:23:51.939258: step: 1228/531, loss: 0.013107872568070889
2023-01-21 11:23:53.088485: step: 1232/531, loss: 0.011837387457489967
2023-01-21 11:23:54.253592: step: 1236/531, loss: 0.15630368888378143
2023-01-21 11:23:55.374673: step: 1240/531, loss: 0.010937786661088467
2023-01-21 11:23:56.510488: step: 1244/531, loss: 0.0007453918224200606
2023-01-21 11:23:57.685421: step: 1248/531, loss: 0.01017913781106472
2023-01-21 11:23:58.818900: step: 1252/531, loss: 0.037652015686035156
2023-01-21 11:23:59.964614: step: 1256/531, loss: 0.002389621688053012
2023-01-21 11:24:01.083324: step: 1260/531, loss: 0.003894805908203125
2023-01-21 11:24:02.228586: step: 1264/531, loss: 0.027416039258241653
2023-01-21 11:24:03.399052: step: 1268/531, loss: 0.0053002359345555305
2023-01-21 11:24:04.511242: step: 1272/531, loss: 0.02048034779727459
2023-01-21 11:24:05.673139: step: 1276/531, loss: 0.0036555291153490543
2023-01-21 11:24:06.809097: step: 1280/531, loss: 0.04128255695104599
2023-01-21 11:24:07.958895: step: 1284/531, loss: 0.0275256410241127
2023-01-21 11:24:09.099017: step: 1288/531, loss: 0.07578639686107635
2023-01-21 11:24:10.276560: step: 1292/531, loss: 0.5570371747016907
2023-01-21 11:24:11.466241: step: 1296/531, loss: 0.023293782025575638
2023-01-21 11:24:12.646424: step: 1300/531, loss: 0.13164043426513672
2023-01-21 11:24:13.773822: step: 1304/531, loss: 0.01826038397848606
2023-01-21 11:24:14.909870: step: 1308/531, loss: 0.00021269322314765304
2023-01-21 11:24:16.001070: step: 1312/531, loss: 0.005787086673080921
2023-01-21 11:24:17.136207: step: 1316/531, loss: 0.018176458775997162
2023-01-21 11:24:18.266062: step: 1320/531, loss: 0.002549457596614957
2023-01-21 11:24:19.413650: step: 1324/531, loss: 0.011810492724180222
2023-01-21 11:24:20.578161: step: 1328/531, loss: 0.02890009991824627
2023-01-21 11:24:21.723045: step: 1332/531, loss: 0.00713381776586175
2023-01-21 11:24:22.879469: step: 1336/531, loss: 0.004637718200683594
2023-01-21 11:24:24.043239: step: 1340/531, loss: 0.00917725544422865
2023-01-21 11:24:25.185051: step: 1344/531, loss: 0.007003212347626686
2023-01-21 11:24:26.337967: step: 1348/531, loss: 0.06715298444032669
2023-01-21 11:24:27.491018: step: 1352/531, loss: 0.0100204823538661
2023-01-21 11:24:28.630137: step: 1356/531, loss: 0.018655776977539062
2023-01-21 11:24:29.768561: step: 1360/531, loss: 0.027485277503728867
2023-01-21 11:24:30.908141: step: 1364/531, loss: 0.022505952045321465
2023-01-21 11:24:32.066866: step: 1368/531, loss: 0.00748596154153347
2023-01-21 11:24:33.209184: step: 1372/531, loss: 0.010336565785109997
2023-01-21 11:24:34.346554: step: 1376/531, loss: 0.025951862335205078
2023-01-21 11:24:35.513279: step: 1380/531, loss: 0.01791992224752903
2023-01-21 11:24:36.673324: step: 1384/531, loss: 0.05021476745605469
2023-01-21 11:24:37.788080: step: 1388/531, loss: 0.05160551145672798
2023-01-21 11:24:38.946519: step: 1392/531, loss: 0.005590343847870827
2023-01-21 11:24:40.100741: step: 1396/531, loss: 0.009225940331816673
2023-01-21 11:24:41.247805: step: 1400/531, loss: 0.025502199307084084
2023-01-21 11:24:42.429942: step: 1404/531, loss: 0.03535986319184303
2023-01-21 11:24:43.557313: step: 1408/531, loss: 0.04016933590173721
2023-01-21 11:24:44.683563: step: 1412/531, loss: 0.00041294097900390625
2023-01-21 11:24:45.828975: step: 1416/531, loss: 0.013364791870117188
2023-01-21 11:24:46.983664: step: 1420/531, loss: 0.07080783694982529
2023-01-21 11:24:48.111961: step: 1424/531, loss: 0.056271836161613464
2023-01-21 11:24:49.279734: step: 1428/531, loss: 0.013304853811860085
2023-01-21 11:24:50.431626: step: 1432/531, loss: 0.007565975189208984
2023-01-21 11:24:51.562419: step: 1436/531, loss: 0.06375379860401154
2023-01-21 11:24:52.699233: step: 1440/531, loss: 0.0005605697515420616
2023-01-21 11:24:53.826858: step: 1444/531, loss: 0.03965587541460991
2023-01-21 11:24:54.974410: step: 1448/531, loss: 0.01696167141199112
2023-01-21 11:24:56.118920: step: 1452/531, loss: 0.049842797219753265
2023-01-21 11:24:57.268322: step: 1456/531, loss: 0.11034837365150452
2023-01-21 11:24:58.423303: step: 1460/531, loss: 0.08664512634277344
2023-01-21 11:24:59.579623: step: 1464/531, loss: 0.04803180694580078
2023-01-21 11:25:00.704197: step: 1468/531, loss: 0.0025374414399266243
2023-01-21 11:25:01.843783: step: 1472/531, loss: 0.04747343063354492
2023-01-21 11:25:03.025131: step: 1476/531, loss: 0.03770873695611954
2023-01-21 11:25:04.184583: step: 1480/531, loss: 0.011066246777772903
2023-01-21 11:25:05.319049: step: 1484/531, loss: 0.008639907464385033
2023-01-21 11:25:06.447462: step: 1488/531, loss: 0.027574921026825905
2023-01-21 11:25:07.590981: step: 1492/531, loss: 0.008526134304702282
2023-01-21 11:25:08.752741: step: 1496/531, loss: 0.006079673767089844
2023-01-21 11:25:09.924786: step: 1500/531, loss: 0.00024662018404342234
2023-01-21 11:25:11.058908: step: 1504/531, loss: 0.0664302408695221
2023-01-21 11:25:12.232387: step: 1508/531, loss: 0.008763599209487438
2023-01-21 11:25:13.391838: step: 1512/531, loss: 0.03532352298498154
2023-01-21 11:25:14.511308: step: 1516/531, loss: 0.0046096802689135075
2023-01-21 11:25:15.680625: step: 1520/531, loss: 0.03270306438207626
2023-01-21 11:25:16.845303: step: 1524/531, loss: 0.009535981342196465
2023-01-21 11:25:17.980123: step: 1528/531, loss: 0.0007839202880859375
2023-01-21 11:25:19.122850: step: 1532/531, loss: 0.04288983345031738
2023-01-21 11:25:20.275380: step: 1536/531, loss: 0.0056164744310081005
2023-01-21 11:25:21.417412: step: 1540/531, loss: 0.0013189315795898438
2023-01-21 11:25:22.589204: step: 1544/531, loss: 0.05837249755859375
2023-01-21 11:25:23.746756: step: 1548/531, loss: 0.03498687595129013
2023-01-21 11:25:24.863048: step: 1552/531, loss: 0.00036249158438295126
2023-01-21 11:25:26.038084: step: 1556/531, loss: 0.03256988525390625
2023-01-21 11:25:27.180632: step: 1560/531, loss: 0.03097829781472683
2023-01-21 11:25:28.369902: step: 1564/531, loss: 0.02753310278058052
2023-01-21 11:25:29.495170: step: 1568/531, loss: 0.7763586044311523
2023-01-21 11:25:30.653027: step: 1572/531, loss: 0.028718186542391777
2023-01-21 11:25:31.797610: step: 1576/531, loss: 0.039102934300899506
2023-01-21 11:25:32.922656: step: 1580/531, loss: 0.2947107255458832
2023-01-21 11:25:34.086764: step: 1584/531, loss: 0.0159041415899992
2023-01-21 11:25:35.232968: step: 1588/531, loss: 0.025876998901367188
2023-01-21 11:25:36.397451: step: 1592/531, loss: 0.000474822532851249
2023-01-21 11:25:37.535301: step: 1596/531, loss: 0.004958438687026501
2023-01-21 11:25:38.672179: step: 1600/531, loss: 0.01568899117410183
2023-01-21 11:25:39.850373: step: 1604/531, loss: 0.025624370202422142
2023-01-21 11:25:41.055836: step: 1608/531, loss: 0.05420932546257973
2023-01-21 11:25:42.211411: step: 1612/531, loss: 0.07152099907398224
2023-01-21 11:25:43.332352: step: 1616/531, loss: 0.0027930261567234993
2023-01-21 11:25:44.471483: step: 1620/531, loss: 0.019649459049105644
2023-01-21 11:25:45.612790: step: 1624/531, loss: 0.0008291244739666581
2023-01-21 11:25:46.763978: step: 1628/531, loss: 0.005993843078613281
2023-01-21 11:25:47.896222: step: 1632/531, loss: 0.015912247821688652
2023-01-21 11:25:49.053879: step: 1636/531, loss: 0.12007541954517365
2023-01-21 11:25:50.185874: step: 1640/531, loss: 0.0017176627879962325
2023-01-21 11:25:51.315954: step: 1644/531, loss: 0.0002313137229066342
2023-01-21 11:25:52.462927: step: 1648/531, loss: 0.006108665373176336
2023-01-21 11:25:53.578835: step: 1652/531, loss: 0.0014146803878247738
2023-01-21 11:25:54.696845: step: 1656/531, loss: 0.008822060190141201
2023-01-21 11:25:55.797380: step: 1660/531, loss: 0.03849220275878906
2023-01-21 11:25:56.952336: step: 1664/531, loss: 0.08142280578613281
2023-01-21 11:25:58.131901: step: 1668/531, loss: 4.253387305652723e-05
2023-01-21 11:25:59.281777: step: 1672/531, loss: 0.13841933012008667
2023-01-21 11:26:00.417980: step: 1676/531, loss: 0.023546766489744186
2023-01-21 11:26:01.557563: step: 1680/531, loss: 0.04385824128985405
2023-01-21 11:26:02.704269: step: 1684/531, loss: 0.005815600976347923
2023-01-21 11:26:03.820915: step: 1688/531, loss: 0.04885225370526314
2023-01-21 11:26:04.944641: step: 1692/531, loss: 0.07603836059570312
2023-01-21 11:26:06.076651: step: 1696/531, loss: 0.010076189413666725
2023-01-21 11:26:07.228533: step: 1700/531, loss: 0.018894482403993607
2023-01-21 11:26:08.379422: step: 1704/531, loss: 0.0474395751953125
2023-01-21 11:26:09.523421: step: 1708/531, loss: 0.00023088455782271922
2023-01-21 11:26:10.668657: step: 1712/531, loss: 0.0016429901588708162
2023-01-21 11:26:11.871911: step: 1716/531, loss: 0.1495567411184311
2023-01-21 11:26:13.010360: step: 1720/531, loss: 0.07339973747730255
2023-01-21 11:26:14.149794: step: 1724/531, loss: 0.01040344312787056
2023-01-21 11:26:15.302868: step: 1728/531, loss: 0.015002298168838024
2023-01-21 11:26:16.434181: step: 1732/531, loss: 0.06674917042255402
2023-01-21 11:26:17.595487: step: 1736/531, loss: 0.05027579143643379
2023-01-21 11:26:18.750584: step: 1740/531, loss: 0.01479187048971653
2023-01-21 11:26:19.886896: step: 1744/531, loss: 0.00819168146699667
2023-01-21 11:26:21.048339: step: 1748/531, loss: 0.2440943717956543
2023-01-21 11:26:22.182188: step: 1752/531, loss: 0.040297795087099075
2023-01-21 11:26:23.302455: step: 1756/531, loss: 0.07959786057472229
2023-01-21 11:26:24.416436: step: 1760/531, loss: 0.19656601548194885
2023-01-21 11:26:25.573190: step: 1764/531, loss: 0.039853859692811966
2023-01-21 11:26:26.714395: step: 1768/531, loss: 0.08470363914966583
2023-01-21 11:26:27.831238: step: 1772/531, loss: 0.01954016648232937
2023-01-21 11:26:28.975140: step: 1776/531, loss: 0.024799538776278496
2023-01-21 11:26:30.119331: step: 1780/531, loss: 0.13329735398292542
2023-01-21 11:26:31.252489: step: 1784/531, loss: 0.011051177978515625
2023-01-21 11:26:32.393581: step: 1788/531, loss: 0.027523614466190338
2023-01-21 11:26:33.552031: step: 1792/531, loss: 0.044104576110839844
2023-01-21 11:26:34.686241: step: 1796/531, loss: 0.005805015563964844
2023-01-21 11:26:35.816097: step: 1800/531, loss: 0.015549277886748314
2023-01-21 11:26:36.978970: step: 1804/531, loss: 0.07079067081212997
2023-01-21 11:26:38.115283: step: 1808/531, loss: 0.002153110457584262
2023-01-21 11:26:39.267523: step: 1812/531, loss: 0.012756729498505592
2023-01-21 11:26:40.421415: step: 1816/531, loss: 0.12018308788537979
2023-01-21 11:26:41.544264: step: 1820/531, loss: 0.024119997397065163
2023-01-21 11:26:42.717558: step: 1824/531, loss: 0.15997090935707092
2023-01-21 11:26:43.865163: step: 1828/531, loss: 0.0011074065696448088
2023-01-21 11:26:45.017698: step: 1832/531, loss: 0.00395278912037611
2023-01-21 11:26:46.155554: step: 1836/531, loss: 0.05136556550860405
2023-01-21 11:26:47.284250: step: 1840/531, loss: 0.07652731239795685
2023-01-21 11:26:48.421386: step: 1844/531, loss: 0.019054604694247246
2023-01-21 11:26:49.551157: step: 1848/531, loss: 0.004462623968720436
2023-01-21 11:26:50.690462: step: 1852/531, loss: 0.0002476692316122353
2023-01-21 11:26:51.817088: step: 1856/531, loss: 0.009767914190888405
2023-01-21 11:26:52.948637: step: 1860/531, loss: 0.011298369616270065
2023-01-21 11:26:54.094580: step: 1864/531, loss: 0.01149454154074192
2023-01-21 11:26:55.174194: step: 1868/531, loss: 0.00012493133544921875
2023-01-21 11:26:56.319987: step: 1872/531, loss: 0.014038467779755592
2023-01-21 11:26:57.478901: step: 1876/531, loss: 0.03041086345911026
2023-01-21 11:26:58.633858: step: 1880/531, loss: 0.013987446203827858
2023-01-21 11:26:59.811964: step: 1884/531, loss: 0.03564281389117241
2023-01-21 11:27:00.989400: step: 1888/531, loss: 0.006274223793298006
2023-01-21 11:27:02.131356: step: 1892/531, loss: 0.03384409099817276
2023-01-21 11:27:03.273962: step: 1896/531, loss: 0.022681105881929398
2023-01-21 11:27:04.401467: step: 1900/531, loss: 0.0470980666577816
2023-01-21 11:27:05.538735: step: 1904/531, loss: 0.001577663468196988
2023-01-21 11:27:06.669329: step: 1908/531, loss: 0.010176277719438076
2023-01-21 11:27:07.811861: step: 1912/531, loss: 0.07056045532226562
2023-01-21 11:27:08.978042: step: 1916/531, loss: 0.04085388407111168
2023-01-21 11:27:10.102867: step: 1920/531, loss: 0.0014092446072027087
2023-01-21 11:27:11.268747: step: 1924/531, loss: 0.039504241198301315
2023-01-21 11:27:12.393878: step: 1928/531, loss: 0.09229431301355362
2023-01-21 11:27:13.519549: step: 1932/531, loss: 0.060762979090213776
2023-01-21 11:27:14.665073: step: 1936/531, loss: 0.053397275507450104
2023-01-21 11:27:15.794631: step: 1940/531, loss: 0.015315055847167969
2023-01-21 11:27:16.911789: step: 1944/531, loss: 0.002593803219497204
2023-01-21 11:27:18.066129: step: 1948/531, loss: 0.006776046939194202
2023-01-21 11:27:19.194299: step: 1952/531, loss: 0.030817175284028053
2023-01-21 11:27:20.299161: step: 1956/531, loss: 0.027423668652772903
2023-01-21 11:27:21.427090: step: 1960/531, loss: 0.03988667204976082
2023-01-21 11:27:22.578220: step: 1964/531, loss: 0.03127577528357506
2023-01-21 11:27:23.695315: step: 1968/531, loss: 0.0006717682117596269
2023-01-21 11:27:24.827838: step: 1972/531, loss: 0.005677032750099897
2023-01-21 11:27:25.950248: step: 1976/531, loss: 0.00278739957138896
2023-01-21 11:27:27.072075: step: 1980/531, loss: 0.012585902586579323
2023-01-21 11:27:28.208598: step: 1984/531, loss: 0.0019260406261309981
2023-01-21 11:27:29.325259: step: 1988/531, loss: 0.000286102294921875
2023-01-21 11:27:30.457884: step: 1992/531, loss: 0.011226083151996136
2023-01-21 11:27:31.597444: step: 1996/531, loss: 0.011379433795809746
2023-01-21 11:27:32.736243: step: 2000/531, loss: 0.06207103654742241
2023-01-21 11:27:33.908753: step: 2004/531, loss: 0.0024404525756835938
2023-01-21 11:27:35.006130: step: 2008/531, loss: 0.0077700139954686165
2023-01-21 11:27:36.136559: step: 2012/531, loss: 0.02217264100909233
2023-01-21 11:27:37.302223: step: 2016/531, loss: 0.021509552374482155
2023-01-21 11:27:38.431988: step: 2020/531, loss: 0.03579392284154892
2023-01-21 11:27:39.544840: step: 2024/531, loss: 0.0034992219880223274
2023-01-21 11:27:40.660081: step: 2028/531, loss: 0.0017119408585131168
2023-01-21 11:27:41.783411: step: 2032/531, loss: 0.06444092094898224
2023-01-21 11:27:42.923200: step: 2036/531, loss: 0.07358045876026154
2023-01-21 11:27:44.051955: step: 2040/531, loss: 0.06879615783691406
2023-01-21 11:27:45.198765: step: 2044/531, loss: 0.08124520629644394
2023-01-21 11:27:46.341294: step: 2048/531, loss: 0.010954475030303001
2023-01-21 11:27:47.476231: step: 2052/531, loss: 0.055268190801143646
2023-01-21 11:27:48.600093: step: 2056/531, loss: 0.027300072833895683
2023-01-21 11:27:49.729106: step: 2060/531, loss: 0.0009501933818683028
2023-01-21 11:27:50.885672: step: 2064/531, loss: 0.05097408592700958
2023-01-21 11:27:52.019678: step: 2068/531, loss: 0.08390650898218155
2023-01-21 11:27:53.164254: step: 2072/531, loss: 0.024344541132450104
2023-01-21 11:27:54.305273: step: 2076/531, loss: 0.0316440612077713
2023-01-21 11:27:55.426351: step: 2080/531, loss: 0.017836641520261765
2023-01-21 11:27:56.565178: step: 2084/531, loss: 0.045054152607917786
2023-01-21 11:27:57.706496: step: 2088/531, loss: 0.014429998584091663
2023-01-21 11:27:58.836689: step: 2092/531, loss: 0.03557949140667915
2023-01-21 11:28:00.003862: step: 2096/531, loss: 0.003995704464614391
2023-01-21 11:28:01.134734: step: 2100/531, loss: 0.004146385006606579
2023-01-21 11:28:02.273379: step: 2104/531, loss: 0.03479357063770294
2023-01-21 11:28:03.491267: step: 2108/531, loss: 0.0670807883143425
2023-01-21 11:28:04.634488: step: 2112/531, loss: 0.228485107421875
2023-01-21 11:28:05.804009: step: 2116/531, loss: 0.06485709547996521
2023-01-21 11:28:06.926527: step: 2120/531, loss: 0.02121448516845703
2023-01-21 11:28:08.035630: step: 2124/531, loss: 0.026298046112060547
==================================================
Loss: 0.040
--------------------
Dev: {'event': {'p': 0.5829244357212954, 'r': 0.7909454061251664, 'f1': 0.671186440677966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6184456928838952, 'r': 0.7877161598091831, 'f1': 0.6928927353789667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5568181818181818, 'r': 0.9074074074074074, 'f1': 0.6901408450704225}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.5873015873015873, 'r': 0.5873015873015873, 'f1': 0.5873015873015873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.41304347826086957, 'r': 0.5277777777777778, 'f1': 0.4634146341463415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:28:51.356294: step: 4/531, loss: 0.0031986236572265625
2023-01-21 11:28:52.529324: step: 8/531, loss: 0.5320137143135071
2023-01-21 11:28:53.698848: step: 12/531, loss: 0.5069739818572998
2023-01-21 11:28:54.816069: step: 16/531, loss: 0.009532738476991653
2023-01-21 11:28:55.957451: step: 20/531, loss: 0.0035482405219227076
2023-01-21 11:28:57.120534: step: 24/531, loss: 0.0088049890473485
2023-01-21 11:28:58.286508: step: 28/531, loss: 0.011547851376235485
2023-01-21 11:28:59.426792: step: 32/531, loss: 0.004515457432717085
2023-01-21 11:29:00.567483: step: 36/531, loss: 0.0002967834589071572
2023-01-21 11:29:01.699931: step: 40/531, loss: 0.002246254589408636
2023-01-21 11:29:02.835837: step: 44/531, loss: 0.003928470425307751
2023-01-21 11:29:03.988605: step: 48/531, loss: 0.019620036706328392
2023-01-21 11:29:05.112197: step: 52/531, loss: 0.08387431502342224
2023-01-21 11:29:06.283723: step: 56/531, loss: 0.02247028425335884
2023-01-21 11:29:07.461733: step: 60/531, loss: 0.0017900466918945312
2023-01-21 11:29:08.605388: step: 64/531, loss: 0.006113243289291859
2023-01-21 11:29:09.713667: step: 68/531, loss: 0.0006719947559759021
2023-01-21 11:29:10.840592: step: 72/531, loss: 0.0399663932621479
2023-01-21 11:29:11.995631: step: 76/531, loss: 0.0005016326904296875
2023-01-21 11:29:13.151074: step: 80/531, loss: 0.031781867146492004
2023-01-21 11:29:14.285818: step: 84/531, loss: 0.00866022054105997
2023-01-21 11:29:15.435536: step: 88/531, loss: 0.0023365020751953125
2023-01-21 11:29:16.610098: step: 92/531, loss: 0.0009809971088543534
2023-01-21 11:29:17.779567: step: 96/531, loss: 0.02555999718606472
2023-01-21 11:29:18.945865: step: 100/531, loss: 0.011400032788515091
2023-01-21 11:29:20.111676: step: 104/531, loss: 0.00790328998118639
2023-01-21 11:29:21.257938: step: 108/531, loss: 0.0219573974609375
2023-01-21 11:29:22.409151: step: 112/531, loss: 0.021747207269072533
2023-01-21 11:29:23.579752: step: 116/531, loss: 0.002005290938541293
2023-01-21 11:29:24.747755: step: 120/531, loss: 0.006027412600815296
2023-01-21 11:29:25.879498: step: 124/531, loss: 0.0036631585098803043
2023-01-21 11:29:27.012065: step: 128/531, loss: 0.05078888311982155
2023-01-21 11:29:28.169760: step: 132/531, loss: 0.0008088112226687372
2023-01-21 11:29:29.357532: step: 136/531, loss: 0.02565746381878853
2023-01-21 11:29:30.490480: step: 140/531, loss: 0.023259354755282402
2023-01-21 11:29:31.642498: step: 144/531, loss: 0.1761014759540558
2023-01-21 11:29:32.778840: step: 148/531, loss: 0.021817494183778763
2023-01-21 11:29:33.921439: step: 152/531, loss: 0.30317115783691406
2023-01-21 11:29:35.061021: step: 156/531, loss: 0.008369636721909046
2023-01-21 11:29:36.184512: step: 160/531, loss: 0.015198517590761185
2023-01-21 11:29:37.345476: step: 164/531, loss: 0.00023193359083961695
2023-01-21 11:29:38.476870: step: 168/531, loss: 0.0331784263253212
2023-01-21 11:29:39.632599: step: 172/531, loss: 0.01221532840281725
2023-01-21 11:29:40.760197: step: 176/531, loss: 0.030248405411839485
2023-01-21 11:29:41.933894: step: 180/531, loss: 0.01745452918112278
2023-01-21 11:29:43.043006: step: 184/531, loss: 0.08195304870605469
2023-01-21 11:29:44.206687: step: 188/531, loss: 0.0026899336371570826
2023-01-21 11:29:45.359687: step: 192/531, loss: 0.04017810896039009
2023-01-21 11:29:46.493116: step: 196/531, loss: 0.0007333278772421181
2023-01-21 11:29:47.637380: step: 200/531, loss: 0.05020543187856674
2023-01-21 11:29:48.767917: step: 204/531, loss: 0.0006281852838583291
2023-01-21 11:29:49.899604: step: 208/531, loss: 0.0010903358925133944
2023-01-21 11:29:51.079506: step: 212/531, loss: 0.023430442437529564
2023-01-21 11:29:52.222732: step: 216/531, loss: 0.00016498565673828125
2023-01-21 11:29:53.369853: step: 220/531, loss: 0.01691589318215847
2023-01-21 11:29:54.542906: step: 224/531, loss: 0.004601574502885342
2023-01-21 11:29:55.680121: step: 228/531, loss: 0.03575267642736435
2023-01-21 11:29:56.813345: step: 232/531, loss: 0.0010628222953528166
2023-01-21 11:29:57.961906: step: 236/531, loss: 0.03856668248772621
2023-01-21 11:29:59.081196: step: 240/531, loss: 0.013074302114546299
2023-01-21 11:30:00.261676: step: 244/531, loss: 0.015597343444824219
2023-01-21 11:30:01.411748: step: 248/531, loss: 0.006758022587746382
2023-01-21 11:30:02.528905: step: 252/531, loss: 0.002910518553107977
2023-01-21 11:30:03.705403: step: 256/531, loss: 0.060192495584487915
2023-01-21 11:30:04.840862: step: 260/531, loss: 0.002361297607421875
2023-01-21 11:30:05.978603: step: 264/531, loss: 0.040784645825624466
2023-01-21 11:30:07.105785: step: 268/531, loss: 0.08249111473560333
2023-01-21 11:30:08.251415: step: 272/531, loss: 0.0693538710474968
2023-01-21 11:30:09.381724: step: 276/531, loss: 0.017268657684326172
2023-01-21 11:30:10.494167: step: 280/531, loss: 0.04931144788861275
2023-01-21 11:30:11.643699: step: 284/531, loss: 0.00895309541374445
2023-01-21 11:30:12.730386: step: 288/531, loss: 0.03828335180878639
2023-01-21 11:30:13.871705: step: 292/531, loss: 0.012966537848114967
2023-01-21 11:30:14.985130: step: 296/531, loss: 0.11732187122106552
2023-01-21 11:30:16.094394: step: 300/531, loss: 0.0023147582542151213
2023-01-21 11:30:17.223733: step: 304/531, loss: 0.019328927621245384
2023-01-21 11:30:18.334921: step: 308/531, loss: 0.015468169003725052
2023-01-21 11:30:19.466708: step: 312/531, loss: 0.020824242383241653
2023-01-21 11:30:20.605137: step: 316/531, loss: 0.006169796455651522
2023-01-21 11:30:21.765255: step: 320/531, loss: 0.04382152855396271
2023-01-21 11:30:22.889754: step: 324/531, loss: 0.0020770072005689144
2023-01-21 11:30:23.977086: step: 328/531, loss: 0.002003932138904929
2023-01-21 11:30:25.116772: step: 332/531, loss: 0.003553199814632535
2023-01-21 11:30:26.233390: step: 336/531, loss: 0.007602119352668524
2023-01-21 11:30:27.344892: step: 340/531, loss: 0.0023725510109215975
2023-01-21 11:30:28.517414: step: 344/531, loss: 0.036425113677978516
2023-01-21 11:30:29.675928: step: 348/531, loss: 0.004952430725097656
2023-01-21 11:30:30.846755: step: 352/531, loss: 0.03351888433098793
2023-01-21 11:30:32.012611: step: 356/531, loss: 0.013051033020019531
2023-01-21 11:30:33.184517: step: 360/531, loss: 0.0611141212284565
2023-01-21 11:30:34.341399: step: 364/531, loss: 0.00011730194091796875
2023-01-21 11:30:35.480052: step: 368/531, loss: 0.025170328095555305
2023-01-21 11:30:36.614413: step: 372/531, loss: 0.007721138186752796
2023-01-21 11:30:37.735389: step: 376/531, loss: 0.3585384488105774
2023-01-21 11:30:38.851844: step: 380/531, loss: 0.004516696557402611
2023-01-21 11:30:39.967122: step: 384/531, loss: 6.804466102039441e-05
2023-01-21 11:30:41.129627: step: 388/531, loss: 0.013208294287323952
2023-01-21 11:30:42.269670: step: 392/531, loss: 0.06282816082239151
2023-01-21 11:30:43.423303: step: 396/531, loss: 0.032610226422548294
2023-01-21 11:30:44.553075: step: 400/531, loss: 0.020388901233673096
2023-01-21 11:30:45.715799: step: 404/531, loss: 7.62939453125e-05
2023-01-21 11:30:46.846734: step: 408/531, loss: 0.00119190220721066
2023-01-21 11:30:47.991538: step: 412/531, loss: 0.030810164287686348
2023-01-21 11:30:49.137832: step: 416/531, loss: 0.0690387710928917
2023-01-21 11:30:50.259143: step: 420/531, loss: 0.03976564481854439
2023-01-21 11:30:51.378494: step: 424/531, loss: 0.00027680397033691406
2023-01-21 11:30:52.508921: step: 428/531, loss: 0.0035211562644690275
2023-01-21 11:30:53.673246: step: 432/531, loss: 0.03640933334827423
2023-01-21 11:30:54.791475: step: 436/531, loss: 0.004938125144690275
2023-01-21 11:30:55.943835: step: 440/531, loss: 0.006573486141860485
2023-01-21 11:30:57.064715: step: 444/531, loss: 0.012926865369081497
2023-01-21 11:30:58.204497: step: 448/531, loss: 0.0031326294410973787
2023-01-21 11:30:59.327706: step: 452/531, loss: 0.0006568908574990928
2023-01-21 11:31:00.491140: step: 456/531, loss: 0.028955651447176933
2023-01-21 11:31:01.629527: step: 460/531, loss: 0.0002869248273782432
2023-01-21 11:31:02.788751: step: 464/531, loss: 0.021189594641327858
2023-01-21 11:31:03.929605: step: 468/531, loss: 0.0020441533997654915
2023-01-21 11:31:05.074985: step: 472/531, loss: 0.12576398253440857
2023-01-21 11:31:06.220418: step: 476/531, loss: 0.09705781936645508
2023-01-21 11:31:07.366031: step: 480/531, loss: 0.0003538132004905492
2023-01-21 11:31:08.512372: step: 484/531, loss: 0.0006099700694903731
2023-01-21 11:31:09.643399: step: 488/531, loss: 0.007028484717011452
2023-01-21 11:31:10.793029: step: 492/531, loss: 0.06639537960290909
2023-01-21 11:31:11.935877: step: 496/531, loss: 0.03950157016515732
2023-01-21 11:31:13.067622: step: 500/531, loss: 0.0003246307314839214
2023-01-21 11:31:14.214675: step: 504/531, loss: 0.00967254675924778
2023-01-21 11:31:15.328890: step: 508/531, loss: 0.03699235990643501
2023-01-21 11:31:16.497541: step: 512/531, loss: 0.003169250674545765
2023-01-21 11:31:17.666859: step: 516/531, loss: 0.008223151788115501
2023-01-21 11:31:18.868216: step: 520/531, loss: 0.0464656837284565
2023-01-21 11:31:19.996111: step: 524/531, loss: 0.021243000403046608
2023-01-21 11:31:21.139294: step: 528/531, loss: 0.0004507065168581903
2023-01-21 11:31:22.274072: step: 532/531, loss: 0.0018720626831054688
2023-01-21 11:31:23.440546: step: 536/531, loss: 0.004398250486701727
2023-01-21 11:31:24.563630: step: 540/531, loss: 0.03261289745569229
2023-01-21 11:31:25.712780: step: 544/531, loss: 0.14559994637966156
2023-01-21 11:31:26.869499: step: 548/531, loss: 0.20377102494239807
2023-01-21 11:31:27.998348: step: 552/531, loss: 0.022357940673828125
2023-01-21 11:31:29.136518: step: 556/531, loss: 0.013386642560362816
2023-01-21 11:31:30.246715: step: 560/531, loss: 0.013295555487275124
2023-01-21 11:31:31.385261: step: 564/531, loss: 0.013185120187699795
2023-01-21 11:31:32.572006: step: 568/531, loss: 0.030263328924775124
2023-01-21 11:31:33.733503: step: 572/531, loss: 0.00020799637422896922
2023-01-21 11:31:34.861945: step: 576/531, loss: 0.005970478057861328
2023-01-21 11:31:36.007484: step: 580/531, loss: 0.006392097566276789
2023-01-21 11:31:37.159852: step: 584/531, loss: 0.035562705248594284
2023-01-21 11:31:38.295627: step: 588/531, loss: 6.67572021484375e-06
2023-01-21 11:31:39.450985: step: 592/531, loss: 0.037072427570819855
2023-01-21 11:31:40.619442: step: 596/531, loss: 0.41086071729660034
2023-01-21 11:31:41.773295: step: 600/531, loss: 0.0015911102527752519
2023-01-21 11:31:42.907758: step: 604/531, loss: 0.00020041465177200735
2023-01-21 11:31:44.048171: step: 608/531, loss: 0.0020437240600585938
2023-01-21 11:31:45.157257: step: 612/531, loss: 0.0009173393482342362
2023-01-21 11:31:46.306375: step: 616/531, loss: 0.0029235840775072575
2023-01-21 11:31:47.449393: step: 620/531, loss: 0.09266014397144318
2023-01-21 11:31:48.597792: step: 624/531, loss: 0.011912918649613857
2023-01-21 11:31:49.724154: step: 628/531, loss: 0.0043045044876635075
2023-01-21 11:31:50.833912: step: 632/531, loss: 0.007423209957778454
2023-01-21 11:31:51.966155: step: 636/531, loss: 0.02342095598578453
2023-01-21 11:31:53.117305: step: 640/531, loss: 0.05944962427020073
2023-01-21 11:31:54.273346: step: 644/531, loss: 0.018491221591830254
2023-01-21 11:31:55.409931: step: 648/531, loss: 0.007088088896125555
2023-01-21 11:31:56.570262: step: 652/531, loss: 0.05974221229553223
2023-01-21 11:31:57.751115: step: 656/531, loss: 0.04714660719037056
2023-01-21 11:31:58.902314: step: 660/531, loss: 0.026032831519842148
2023-01-21 11:32:00.003915: step: 664/531, loss: 0.03264961019158363
2023-01-21 11:32:01.130568: step: 668/531, loss: 0.004107475280761719
2023-01-21 11:32:02.248406: step: 672/531, loss: 0.006307029630988836
2023-01-21 11:32:03.404017: step: 676/531, loss: 0.10223130881786346
2023-01-21 11:32:04.565069: step: 680/531, loss: 0.0007387161022052169
2023-01-21 11:32:05.731955: step: 684/531, loss: 0.05891399458050728
2023-01-21 11:32:06.881707: step: 688/531, loss: 0.008532142266631126
2023-01-21 11:32:08.053814: step: 692/531, loss: 0.03570614010095596
2023-01-21 11:32:09.217253: step: 696/531, loss: 0.001989173935726285
2023-01-21 11:32:10.372603: step: 700/531, loss: 0.05263977125287056
2023-01-21 11:32:11.480929: step: 704/531, loss: 0.00011072159395553172
2023-01-21 11:32:12.631531: step: 708/531, loss: 0.0004876971070189029
2023-01-21 11:32:13.758225: step: 712/531, loss: 0.19191202521324158
2023-01-21 11:32:14.931276: step: 716/531, loss: 2.4175644284696318e-05
2023-01-21 11:32:16.073224: step: 720/531, loss: 0.023565959185361862
2023-01-21 11:32:17.207660: step: 724/531, loss: 0.007044029422104359
2023-01-21 11:32:18.356911: step: 728/531, loss: 0.024537088349461555
2023-01-21 11:32:19.502828: step: 732/531, loss: 0.05185890197753906
2023-01-21 11:32:20.649473: step: 736/531, loss: 0.12506332993507385
2023-01-21 11:32:21.825901: step: 740/531, loss: 0.01971883699297905
2023-01-21 11:32:22.983035: step: 744/531, loss: 0.19170723855495453
2023-01-21 11:32:24.095916: step: 748/531, loss: 0.008958840742707253
2023-01-21 11:32:25.254215: step: 752/531, loss: 0.022042179480195045
2023-01-21 11:32:26.413175: step: 756/531, loss: 0.08817371726036072
2023-01-21 11:32:27.572241: step: 760/531, loss: 0.00028228759765625
2023-01-21 11:32:28.700548: step: 764/531, loss: 0.03675012290477753
2023-01-21 11:32:29.810694: step: 768/531, loss: 0.014083052054047585
2023-01-21 11:32:30.963207: step: 772/531, loss: 0.04045858606696129
2023-01-21 11:32:32.095834: step: 776/531, loss: 0.07263302803039551
2023-01-21 11:32:33.265342: step: 780/531, loss: 0.11687088012695312
2023-01-21 11:32:34.430600: step: 784/531, loss: 0.02087393030524254
2023-01-21 11:32:35.577258: step: 788/531, loss: 0.017788220196962357
2023-01-21 11:32:36.715632: step: 792/531, loss: 0.006742477882653475
2023-01-21 11:32:37.846115: step: 796/531, loss: 0.015903282910585403
2023-01-21 11:32:39.016840: step: 800/531, loss: 0.035421278327703476
2023-01-21 11:32:40.145876: step: 804/531, loss: 0.0316472165286541
2023-01-21 11:32:41.282469: step: 808/531, loss: 0.014603614807128906
2023-01-21 11:32:42.429067: step: 812/531, loss: 0.0020620347931981087
2023-01-21 11:32:43.584496: step: 816/531, loss: 0.004338884260505438
2023-01-21 11:32:44.715145: step: 820/531, loss: 0.004135322757065296
2023-01-21 11:32:45.837363: step: 824/531, loss: 0.009090399369597435
2023-01-21 11:32:46.985961: step: 828/531, loss: 0.006570053286850452
2023-01-21 11:32:48.111051: step: 832/531, loss: 0.10632772743701935
2023-01-21 11:32:49.264764: step: 836/531, loss: 0.0006173134315758944
2023-01-21 11:32:50.397028: step: 840/531, loss: 0.029095936566591263
2023-01-21 11:32:51.541465: step: 844/531, loss: 0.028853273019194603
2023-01-21 11:32:52.661137: step: 848/531, loss: 0.01092376746237278
2023-01-21 11:32:53.801710: step: 852/531, loss: 0.009807205758988857
2023-01-21 11:32:54.945066: step: 856/531, loss: 0.06452493369579315
2023-01-21 11:32:56.090326: step: 860/531, loss: 0.021578026935458183
2023-01-21 11:32:57.234825: step: 864/531, loss: 0.029333340004086494
2023-01-21 11:32:58.398840: step: 868/531, loss: 0.12489080429077148
2023-01-21 11:32:59.555837: step: 872/531, loss: 0.043154526501894
2023-01-21 11:33:00.689409: step: 876/531, loss: 0.00032444001408293843
2023-01-21 11:33:01.839588: step: 880/531, loss: 0.009951448999345303
2023-01-21 11:33:02.960083: step: 884/531, loss: 0.015851879492402077
2023-01-21 11:33:04.094648: step: 888/531, loss: 0.001773405005224049
2023-01-21 11:33:05.285602: step: 892/531, loss: 0.00020847321138717234
2023-01-21 11:33:06.404050: step: 896/531, loss: 0.0075699808076024055
2023-01-21 11:33:07.541787: step: 900/531, loss: 0.00603752164170146
2023-01-21 11:33:08.683673: step: 904/531, loss: 0.0033434866927564144
2023-01-21 11:33:09.808377: step: 908/531, loss: 0.047861289232969284
2023-01-21 11:33:10.898657: step: 912/531, loss: 4.19616708313697e-06
2023-01-21 11:33:12.010654: step: 916/531, loss: 0.04440012201666832
2023-01-21 11:33:13.132055: step: 920/531, loss: 0.006049918942153454
2023-01-21 11:33:14.292764: step: 924/531, loss: 0.0009041786543093622
2023-01-21 11:33:15.456122: step: 928/531, loss: 0.09411583095788956
2023-01-21 11:33:16.614640: step: 932/531, loss: 0.0007430076948367059
2023-01-21 11:33:17.740897: step: 936/531, loss: 0.010750055313110352
2023-01-21 11:33:18.876007: step: 940/531, loss: 0.0014025687705725431
2023-01-21 11:33:20.025489: step: 944/531, loss: 0.070703886449337
2023-01-21 11:33:21.183393: step: 948/531, loss: 0.05619654431939125
2023-01-21 11:33:22.324828: step: 952/531, loss: 0.00015192032151389867
2023-01-21 11:33:23.475341: step: 956/531, loss: 0.048120878636837006
2023-01-21 11:33:24.598241: step: 960/531, loss: 0.006114935968071222
2023-01-21 11:33:25.743603: step: 964/531, loss: 0.059396080672740936
2023-01-21 11:33:26.866276: step: 968/531, loss: 0.046480562537908554
2023-01-21 11:33:28.002921: step: 972/531, loss: 0.018199730664491653
2023-01-21 11:33:29.145599: step: 976/531, loss: 0.004629802890121937
2023-01-21 11:33:30.269421: step: 980/531, loss: 0.06770829856395721
2023-01-21 11:33:31.423234: step: 984/531, loss: 0.0492284782230854
2023-01-21 11:33:32.565963: step: 988/531, loss: 0.019356489181518555
2023-01-21 11:33:33.722200: step: 992/531, loss: 0.05121574550867081
2023-01-21 11:33:34.836964: step: 996/531, loss: 0.01897287368774414
2023-01-21 11:33:35.998275: step: 1000/531, loss: 0.026590729132294655
2023-01-21 11:33:37.149491: step: 1004/531, loss: 0.2064417004585266
2023-01-21 11:33:38.279892: step: 1008/531, loss: 0.11226468533277512
2023-01-21 11:33:39.427383: step: 1012/531, loss: 0.006961155217140913
2023-01-21 11:33:40.543858: step: 1016/531, loss: 0.0844184160232544
2023-01-21 11:33:41.664655: step: 1020/531, loss: 0.03108227252960205
2023-01-21 11:33:42.755308: step: 1024/531, loss: 0.008012198843061924
2023-01-21 11:33:43.888874: step: 1028/531, loss: 0.0230731014162302
2023-01-21 11:33:44.994926: step: 1032/531, loss: 0.0010379791492596269
2023-01-21 11:33:46.119701: step: 1036/531, loss: 0.00010013580322265625
2023-01-21 11:33:47.261056: step: 1040/531, loss: 0.02672729641199112
2023-01-21 11:33:48.388904: step: 1044/531, loss: 0.030762579292058945
2023-01-21 11:33:49.505808: step: 1048/531, loss: 0.00024585722712799907
2023-01-21 11:33:50.666562: step: 1052/531, loss: 0.07710965722799301
2023-01-21 11:33:51.826779: step: 1056/531, loss: 0.03268461301922798
2023-01-21 11:33:52.934391: step: 1060/531, loss: 0.007287788670510054
2023-01-21 11:33:54.062206: step: 1064/531, loss: 0.0023835182655602694
2023-01-21 11:33:55.197422: step: 1068/531, loss: 0.0029266357887536287
2023-01-21 11:33:56.318658: step: 1072/531, loss: 0.020317936316132545
2023-01-21 11:33:57.457238: step: 1076/531, loss: 0.009944153018295765
2023-01-21 11:33:58.601586: step: 1080/531, loss: 0.008577156811952591
2023-01-21 11:33:59.732389: step: 1084/531, loss: 0.0352330207824707
2023-01-21 11:34:00.848818: step: 1088/531, loss: 0.0334162712097168
2023-01-21 11:34:01.977199: step: 1092/531, loss: 0.03544321283698082
2023-01-21 11:34:03.115295: step: 1096/531, loss: 0.0872875228524208
2023-01-21 11:34:04.263396: step: 1100/531, loss: 0.010074043646454811
2023-01-21 11:34:05.408323: step: 1104/531, loss: 0.004648732952773571
2023-01-21 11:34:06.524748: step: 1108/531, loss: 0.0029380798805505037
2023-01-21 11:34:07.696019: step: 1112/531, loss: 0.08681049197912216
2023-01-21 11:34:08.852351: step: 1116/531, loss: 0.005612802691757679
2023-01-21 11:34:10.006993: step: 1120/531, loss: 0.02386474609375
2023-01-21 11:34:11.121520: step: 1124/531, loss: 0.002441501710563898
2023-01-21 11:34:12.283829: step: 1128/531, loss: 0.0048583983443677425
2023-01-21 11:34:13.426887: step: 1132/531, loss: 0.01808915287256241
2023-01-21 11:34:14.571432: step: 1136/531, loss: 0.06909604370594025
2023-01-21 11:34:15.695458: step: 1140/531, loss: 0.04931602627038956
2023-01-21 11:34:16.824905: step: 1144/531, loss: 0.01605062559247017
2023-01-21 11:34:17.983145: step: 1148/531, loss: 0.010746479034423828
2023-01-21 11:34:19.112719: step: 1152/531, loss: 0.03742561489343643
2023-01-21 11:34:20.221761: step: 1156/531, loss: 0.03844413906335831
2023-01-21 11:34:21.398481: step: 1160/531, loss: 0.02562236785888672
2023-01-21 11:34:22.572880: step: 1164/531, loss: 0.0006140232435427606
2023-01-21 11:34:23.727642: step: 1168/531, loss: 0.07575778663158417
2023-01-21 11:34:24.875878: step: 1172/531, loss: 0.008207941427826881
2023-01-21 11:34:26.040587: step: 1176/531, loss: 0.004946804139763117
2023-01-21 11:34:27.193448: step: 1180/531, loss: 0.006978416815400124
2023-01-21 11:34:28.320054: step: 1184/531, loss: 0.002919435501098633
2023-01-21 11:34:29.443638: step: 1188/531, loss: 0.10103556513786316
2023-01-21 11:34:30.601752: step: 1192/531, loss: 0.007282781880348921
2023-01-21 11:34:31.747387: step: 1196/531, loss: 0.02560882642865181
2023-01-21 11:34:32.897263: step: 1200/531, loss: 0.011707651428878307
2023-01-21 11:34:34.050581: step: 1204/531, loss: 0.0035593032371252775
2023-01-21 11:34:35.200580: step: 1208/531, loss: 0.010898208245635033
2023-01-21 11:34:36.347056: step: 1212/531, loss: 0.0002610206720419228
2023-01-21 11:34:37.477466: step: 1216/531, loss: 0.017278386279940605
2023-01-21 11:34:38.621359: step: 1220/531, loss: 0.00962533988058567
2023-01-21 11:34:39.758566: step: 1224/531, loss: 0.10481176525354385
2023-01-21 11:34:40.902720: step: 1228/531, loss: 0.016588782891631126
2023-01-21 11:34:42.071237: step: 1232/531, loss: 0.04270181804895401
2023-01-21 11:34:43.201635: step: 1236/531, loss: 0.014360617846250534
2023-01-21 11:34:44.334945: step: 1240/531, loss: 0.03247566521167755
2023-01-21 11:34:45.444770: step: 1244/531, loss: 0.006392478942871094
2023-01-21 11:34:46.608020: step: 1248/531, loss: 5.464554124046117e-05
2023-01-21 11:34:47.739326: step: 1252/531, loss: 0.004841423127800226
2023-01-21 11:34:48.862967: step: 1256/531, loss: 0.0003465652698650956
2023-01-21 11:34:49.991163: step: 1260/531, loss: 0.002984476275742054
2023-01-21 11:34:51.097170: step: 1264/531, loss: 0.07485266029834747
2023-01-21 11:34:52.262522: step: 1268/531, loss: 0.00509147671982646
2023-01-21 11:34:53.388395: step: 1272/531, loss: 0.02361741103231907
2023-01-21 11:34:54.525827: step: 1276/531, loss: 0.04300554841756821
2023-01-21 11:34:55.644450: step: 1280/531, loss: 0.033553026616573334
2023-01-21 11:34:56.768811: step: 1284/531, loss: 0.003080177353695035
2023-01-21 11:34:57.939316: step: 1288/531, loss: 0.052766039967536926
2023-01-21 11:34:59.120446: step: 1292/531, loss: 0.41905081272125244
2023-01-21 11:35:00.252204: step: 1296/531, loss: 0.051436807960271835
2023-01-21 11:35:01.395835: step: 1300/531, loss: 0.02467336505651474
2023-01-21 11:35:02.492117: step: 1304/531, loss: 0.004202556796371937
2023-01-21 11:35:03.613945: step: 1308/531, loss: 0.011218547821044922
2023-01-21 11:35:04.731845: step: 1312/531, loss: 1.220703143189894e-05
2023-01-21 11:35:05.852447: step: 1316/531, loss: 0.1347368359565735
2023-01-21 11:35:06.987267: step: 1320/531, loss: 0.003582596778869629
2023-01-21 11:35:08.126626: step: 1324/531, loss: 0.012189961038529873
2023-01-21 11:35:09.278405: step: 1328/531, loss: 0.022995997220277786
2023-01-21 11:35:10.433340: step: 1332/531, loss: 0.0008674621349200606
2023-01-21 11:35:11.606667: step: 1336/531, loss: 0.01600198820233345
2023-01-21 11:35:12.757458: step: 1340/531, loss: 0.03642052412033081
2023-01-21 11:35:13.919703: step: 1344/531, loss: 0.01587972790002823
2023-01-21 11:35:15.071664: step: 1348/531, loss: 0.021015549078583717
2023-01-21 11:35:16.194139: step: 1352/531, loss: 0.0028820992447435856
2023-01-21 11:35:17.362773: step: 1356/531, loss: 0.046047236770391464
2023-01-21 11:35:18.508641: step: 1360/531, loss: 0.05033550411462784
2023-01-21 11:35:19.691145: step: 1364/531, loss: 0.0029968260787427425
2023-01-21 11:35:20.823758: step: 1368/531, loss: 0.10321059077978134
2023-01-21 11:35:21.992764: step: 1372/531, loss: 0.017705153673887253
2023-01-21 11:35:23.107376: step: 1376/531, loss: 0.031148577108979225
2023-01-21 11:35:24.257687: step: 1380/531, loss: 0.003689289093017578
2023-01-21 11:35:25.385038: step: 1384/531, loss: 0.010345744900405407
2023-01-21 11:35:26.538058: step: 1388/531, loss: 0.018085099756717682
2023-01-21 11:35:27.670876: step: 1392/531, loss: 0.05871400982141495
2023-01-21 11:35:28.839968: step: 1396/531, loss: 0.022579384967684746
2023-01-21 11:35:29.983581: step: 1400/531, loss: 0.03146848827600479
2023-01-21 11:35:31.149428: step: 1404/531, loss: 0.003318405244499445
2023-01-21 11:35:32.286806: step: 1408/531, loss: 0.01587653160095215
2023-01-21 11:35:33.450704: step: 1412/531, loss: 0.021695328876376152
2023-01-21 11:35:34.649650: step: 1416/531, loss: 0.00048320292262360454
2023-01-21 11:35:35.816602: step: 1420/531, loss: 0.0008377075428143144
2023-01-21 11:35:36.953863: step: 1424/531, loss: 0.03805284574627876
2023-01-21 11:35:38.122391: step: 1428/531, loss: 0.012700892053544521
2023-01-21 11:35:39.253814: step: 1432/531, loss: 0.0009196281898766756
2023-01-21 11:35:40.372583: step: 1436/531, loss: 0.04095878824591637
2023-01-21 11:35:41.560992: step: 1440/531, loss: 0.016668032854795456
2023-01-21 11:35:42.703548: step: 1444/531, loss: 0.013554097153246403
2023-01-21 11:35:43.908013: step: 1448/531, loss: 0.031142044812440872
2023-01-21 11:35:45.037866: step: 1452/531, loss: 0.0043694498017430305
2023-01-21 11:35:46.188432: step: 1456/531, loss: 5.397796485340223e-05
2023-01-21 11:35:47.318903: step: 1460/531, loss: 0.005466270260512829
2023-01-21 11:35:48.489803: step: 1464/531, loss: 0.024178888648748398
2023-01-21 11:35:49.623861: step: 1468/531, loss: 0.04167165979743004
2023-01-21 11:35:50.747586: step: 1472/531, loss: 0.030733108520507812
2023-01-21 11:35:51.952290: step: 1476/531, loss: 0.03330421447753906
2023-01-21 11:35:53.082941: step: 1480/531, loss: 0.03384876251220703
2023-01-21 11:35:54.247771: step: 1484/531, loss: 0.043265726417303085
2023-01-21 11:35:55.427363: step: 1488/531, loss: 0.02325616031885147
2023-01-21 11:35:56.547135: step: 1492/531, loss: 0.01712975464761257
2023-01-21 11:35:57.710577: step: 1496/531, loss: 0.0035588263999670744
2023-01-21 11:35:58.880454: step: 1500/531, loss: 0.013007258996367455
2023-01-21 11:36:00.016362: step: 1504/531, loss: 0.03081197664141655
2023-01-21 11:36:01.199238: step: 1508/531, loss: 0.08359622955322266
2023-01-21 11:36:02.336148: step: 1512/531, loss: 0.11903619766235352
2023-01-21 11:36:03.467059: step: 1516/531, loss: 0.003787422087043524
2023-01-21 11:36:04.582382: step: 1520/531, loss: 0.017204951494932175
2023-01-21 11:36:05.742914: step: 1524/531, loss: 0.04301281273365021
2023-01-21 11:36:06.884926: step: 1528/531, loss: 0.020871736109256744
2023-01-21 11:36:08.025315: step: 1532/531, loss: 0.06296758353710175
2023-01-21 11:36:09.191896: step: 1536/531, loss: 0.022336198017001152
2023-01-21 11:36:10.344150: step: 1540/531, loss: 0.0026634240057319403
2023-01-21 11:36:11.455342: step: 1544/531, loss: 0.020304488018155098
2023-01-21 11:36:12.573532: step: 1548/531, loss: 0.26819151639938354
2023-01-21 11:36:13.707714: step: 1552/531, loss: 0.10329543054103851
2023-01-21 11:36:14.856793: step: 1556/531, loss: 0.06942959129810333
2023-01-21 11:36:16.022784: step: 1560/531, loss: 0.02178172953426838
2023-01-21 11:36:17.156189: step: 1564/531, loss: 0.006759166717529297
2023-01-21 11:36:18.309706: step: 1568/531, loss: 0.009154033847153187
2023-01-21 11:36:19.448069: step: 1572/531, loss: 0.00357303605414927
2023-01-21 11:36:20.611134: step: 1576/531, loss: 0.02376260794699192
2023-01-21 11:36:21.732941: step: 1580/531, loss: 0.003288459964096546
2023-01-21 11:36:22.889329: step: 1584/531, loss: 0.05271320790052414
2023-01-21 11:36:24.089051: step: 1588/531, loss: 0.00923767127096653
2023-01-21 11:36:25.222103: step: 1592/531, loss: 0.0039206743240356445
2023-01-21 11:36:26.339323: step: 1596/531, loss: 0.029753495007753372
2023-01-21 11:36:27.487712: step: 1600/531, loss: 0.002079105470329523
2023-01-21 11:36:28.613938: step: 1604/531, loss: 0.07929325103759766
2023-01-21 11:36:29.729853: step: 1608/531, loss: 0.1175076961517334
2023-01-21 11:36:30.860670: step: 1612/531, loss: 0.0063987732864916325
2023-01-21 11:36:31.998826: step: 1616/531, loss: 0.004934978671371937
2023-01-21 11:36:33.114189: step: 1620/531, loss: 0.0006974220159463584
2023-01-21 11:36:34.241935: step: 1624/531, loss: 0.007775688543915749
2023-01-21 11:36:35.372548: step: 1628/531, loss: 0.008225584402680397
2023-01-21 11:36:36.536907: step: 1632/531, loss: 0.0029627324547618628
2023-01-21 11:36:37.678375: step: 1636/531, loss: 0.007986927404999733
2023-01-21 11:36:38.810235: step: 1640/531, loss: 0.011193371377885342
2023-01-21 11:36:39.952336: step: 1644/531, loss: 0.004993439186364412
2023-01-21 11:36:41.068289: step: 1648/531, loss: 0.0030838013626635075
2023-01-21 11:36:42.202430: step: 1652/531, loss: 0.012137413024902344
2023-01-21 11:36:43.344306: step: 1656/531, loss: 0.04378509521484375
2023-01-21 11:36:44.487671: step: 1660/531, loss: 0.020855236798524857
2023-01-21 11:36:45.628117: step: 1664/531, loss: 0.01168045960366726
2023-01-21 11:36:46.744549: step: 1668/531, loss: 0.041135504841804504
2023-01-21 11:36:47.881531: step: 1672/531, loss: 0.022951697930693626
2023-01-21 11:36:49.029015: step: 1676/531, loss: 0.006878089625388384
2023-01-21 11:36:50.169106: step: 1680/531, loss: 0.04147787019610405
2023-01-21 11:36:51.309347: step: 1684/531, loss: 0.016452407464385033
2023-01-21 11:36:52.430702: step: 1688/531, loss: 0.07864789664745331
2023-01-21 11:36:53.581233: step: 1692/531, loss: 0.07175607979297638
2023-01-21 11:36:54.729971: step: 1696/531, loss: 0.011507321149110794
2023-01-21 11:36:55.863788: step: 1700/531, loss: 0.0196990966796875
2023-01-21 11:36:57.001390: step: 1704/531, loss: 0.016415024176239967
2023-01-21 11:36:58.175686: step: 1708/531, loss: 0.08067063987255096
2023-01-21 11:36:59.323014: step: 1712/531, loss: 0.00034780503483489156
2023-01-21 11:37:00.445495: step: 1716/531, loss: 0.0003574371512513608
2023-01-21 11:37:01.557749: step: 1720/531, loss: 0.052779581397771835
2023-01-21 11:37:02.712200: step: 1724/531, loss: 0.054026223719120026
2023-01-21 11:37:03.876432: step: 1728/531, loss: 1.1945576667785645
2023-01-21 11:37:05.023026: step: 1732/531, loss: 0.00395545968785882
2023-01-21 11:37:06.138256: step: 1736/531, loss: 0.0035877227783203125
2023-01-21 11:37:07.282806: step: 1740/531, loss: 0.0029854297172278166
2023-01-21 11:37:08.407487: step: 1744/531, loss: 0.015355301089584827
2023-01-21 11:37:09.540213: step: 1748/531, loss: 0.005847454071044922
2023-01-21 11:37:10.707252: step: 1752/531, loss: 0.06560830771923065
2023-01-21 11:37:11.889832: step: 1756/531, loss: 0.06070220470428467
2023-01-21 11:37:13.038011: step: 1760/531, loss: 0.02496366575360298
2023-01-21 11:37:14.194373: step: 1764/531, loss: 0.0004014253499917686
2023-01-21 11:37:15.335454: step: 1768/531, loss: 0.007133770268410444
2023-01-21 11:37:16.482277: step: 1772/531, loss: 0.006471824832260609
2023-01-21 11:37:17.625308: step: 1776/531, loss: 0.00371398963034153
2023-01-21 11:37:18.755112: step: 1780/531, loss: 0.03792600706219673
2023-01-21 11:37:19.886229: step: 1784/531, loss: 0.06512375175952911
2023-01-21 11:37:21.016127: step: 1788/531, loss: 0.28476059436798096
2023-01-21 11:37:22.154266: step: 1792/531, loss: 0.014986038208007812
2023-01-21 11:37:23.279960: step: 1796/531, loss: 9.813308861339465e-05
2023-01-21 11:37:24.395768: step: 1800/531, loss: 0.0012739181984215975
2023-01-21 11:37:25.517896: step: 1804/531, loss: 0.02565941959619522
2023-01-21 11:37:26.640876: step: 1808/531, loss: 0.00871200580149889
2023-01-21 11:37:27.795663: step: 1812/531, loss: 0.0061314585618674755
2023-01-21 11:37:28.902912: step: 1816/531, loss: 0.04541795328259468
2023-01-21 11:37:30.026811: step: 1820/531, loss: 0.002659416291862726
2023-01-21 11:37:31.175298: step: 1824/531, loss: 0.000358390825567767
2023-01-21 11:37:32.305520: step: 1828/531, loss: 0.4325523376464844
2023-01-21 11:37:33.453064: step: 1832/531, loss: 0.00283660925924778
2023-01-21 11:37:34.596476: step: 1836/531, loss: 0.0032539365347474813
2023-01-21 11:37:35.720700: step: 1840/531, loss: 0.020129824057221413
2023-01-21 11:37:36.854346: step: 1844/531, loss: 0.02207355387508869
2023-01-21 11:37:38.008500: step: 1848/531, loss: 0.02607870101928711
2023-01-21 11:37:39.158173: step: 1852/531, loss: 0.004940795712172985
2023-01-21 11:37:40.280624: step: 1856/531, loss: 0.003156471299007535
2023-01-21 11:37:41.378189: step: 1860/531, loss: 0.005729723256081343
2023-01-21 11:37:42.498716: step: 1864/531, loss: 0.0014324665535241365
2023-01-21 11:37:43.601713: step: 1868/531, loss: 0.08723773807287216
2023-01-21 11:37:44.712291: step: 1872/531, loss: 0.05804614722728729
2023-01-21 11:37:45.822444: step: 1876/531, loss: 0.0036375047639012337
2023-01-21 11:37:46.942843: step: 1880/531, loss: 0.020519733428955078
2023-01-21 11:37:48.043149: step: 1884/531, loss: 0.00825204886496067
2023-01-21 11:37:49.189619: step: 1888/531, loss: 0.014622688293457031
2023-01-21 11:37:50.337433: step: 1892/531, loss: 7.953643944347277e-05
2023-01-21 11:37:51.458013: step: 1896/531, loss: 0.03589363023638725
2023-01-21 11:37:52.583247: step: 1900/531, loss: 0.005812644958496094
2023-01-21 11:37:53.699614: step: 1904/531, loss: 0.0670391097664833
2023-01-21 11:37:54.834569: step: 1908/531, loss: 0.03451528772711754
2023-01-21 11:37:55.983057: step: 1912/531, loss: 0.0002455711364746094
2023-01-21 11:37:57.130533: step: 1916/531, loss: 0.014847183600068092
2023-01-21 11:37:58.308496: step: 1920/531, loss: 0.004889106843620539
2023-01-21 11:37:59.447888: step: 1924/531, loss: 0.0003566741943359375
2023-01-21 11:38:00.585621: step: 1928/531, loss: 0.00217609410174191
2023-01-21 11:38:01.725137: step: 1932/531, loss: 0.02753629721701145
2023-01-21 11:38:02.854328: step: 1936/531, loss: 0.002470302628353238
2023-01-21 11:38:03.979371: step: 1940/531, loss: 0.050551604479551315
2023-01-21 11:38:05.095766: step: 1944/531, loss: 0.1101495772600174
2023-01-21 11:38:06.209265: step: 1948/531, loss: 2.8467178708524443e-05
2023-01-21 11:38:07.351552: step: 1952/531, loss: 0.05049147456884384
2023-01-21 11:38:08.475916: step: 1956/531, loss: 0.047983553260564804
2023-01-21 11:38:09.645221: step: 1960/531, loss: 0.008704758249223232
2023-01-21 11:38:10.768273: step: 1964/531, loss: 0.039812374860048294
2023-01-21 11:38:11.889674: step: 1968/531, loss: 0.014674377627670765
2023-01-21 11:38:13.023075: step: 1972/531, loss: 0.03880615159869194
2023-01-21 11:38:14.163023: step: 1976/531, loss: 0.023801708593964577
2023-01-21 11:38:15.294933: step: 1980/531, loss: 0.06367473304271698
2023-01-21 11:38:16.429128: step: 1984/531, loss: 0.4308701157569885
2023-01-21 11:38:17.558386: step: 1988/531, loss: 0.03270473703742027
2023-01-21 11:38:18.705005: step: 1992/531, loss: 0.03408947214484215
2023-01-21 11:38:19.846105: step: 1996/531, loss: 0.00036849977914243937
2023-01-21 11:38:20.969001: step: 2000/531, loss: 0.05244779586791992
2023-01-21 11:38:22.089687: step: 2004/531, loss: 0.0030225752852857113
2023-01-21 11:38:23.188949: step: 2008/531, loss: 0.0031193732284009457
2023-01-21 11:38:24.354713: step: 2012/531, loss: 0.05383634567260742
2023-01-21 11:38:25.544021: step: 2016/531, loss: 0.0071891783736646175
2023-01-21 11:38:26.697181: step: 2020/531, loss: 0.004887747578322887
2023-01-21 11:38:27.840661: step: 2024/531, loss: 0.024155426770448685
2023-01-21 11:38:28.966102: step: 2028/531, loss: 0.0014318466419354081
2023-01-21 11:38:30.101158: step: 2032/531, loss: 0.004417228512465954
2023-01-21 11:38:31.261862: step: 2036/531, loss: 0.025801371783018112
2023-01-21 11:38:32.445223: step: 2040/531, loss: 0.22373075783252716
2023-01-21 11:38:33.611604: step: 2044/531, loss: 0.0161622054874897
2023-01-21 11:38:34.765899: step: 2048/531, loss: 0.0446162223815918
2023-01-21 11:38:35.908093: step: 2052/531, loss: 0.030378341674804688
2023-01-21 11:38:37.083746: step: 2056/531, loss: 0.005412006750702858
2023-01-21 11:38:38.237938: step: 2060/531, loss: 0.0014930724864825606
2023-01-21 11:38:39.387931: step: 2064/531, loss: 0.04890189319849014
2023-01-21 11:38:40.538429: step: 2068/531, loss: 0.3260103464126587
2023-01-21 11:38:41.671130: step: 2072/531, loss: 0.0030933856032788754
2023-01-21 11:38:42.794464: step: 2076/531, loss: 0.0007666110759600997
2023-01-21 11:38:43.937663: step: 2080/531, loss: 0.02080850675702095
2023-01-21 11:38:45.081767: step: 2084/531, loss: 0.006679678335785866
2023-01-21 11:38:46.303812: step: 2088/531, loss: 0.02182779461145401
2023-01-21 11:38:47.410722: step: 2092/531, loss: 0.0011119842529296875
2023-01-21 11:38:48.552378: step: 2096/531, loss: 0.0038054464384913445
2023-01-21 11:38:49.675412: step: 2100/531, loss: 0.02427225187420845
2023-01-21 11:38:50.841339: step: 2104/531, loss: 0.013285351917147636
2023-01-21 11:38:52.013188: step: 2108/531, loss: 0.05540408939123154
2023-01-21 11:38:53.148295: step: 2112/531, loss: 0.026139356195926666
2023-01-21 11:38:54.319675: step: 2116/531, loss: 0.013423491269350052
2023-01-21 11:38:55.450112: step: 2120/531, loss: 0.025715352967381477
2023-01-21 11:38:56.600154: step: 2124/531, loss: 0.017140675336122513
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.5725490196078431, 'r': 0.7776298268974701, 'f1': 0.6595143986448334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6345966958211856, 'r': 0.7787716159809183, 'f1': 0.6993306559571619}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5925925925925926, 'r': 0.8888888888888888, 'f1': 0.711111111111111}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.6206896551724138, 'r': 0.5714285714285714, 'f1': 0.5950413223140496}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.34, 'r': 0.4722222222222222, 'f1': 0.39534883720930236}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:39:39.564077: step: 4/531, loss: 0.03148212656378746
2023-01-21 11:39:40.686565: step: 8/531, loss: 0.009138393215835094
2023-01-21 11:39:41.889027: step: 12/531, loss: 0.03735532611608505
2023-01-21 11:39:43.011692: step: 16/531, loss: 0.06599961221218109
2023-01-21 11:39:44.174563: step: 20/531, loss: 0.0032851221039891243
2023-01-21 11:39:45.302507: step: 24/531, loss: 0.0003922939649783075
2023-01-21 11:39:46.435623: step: 28/531, loss: 0.0018051147926598787
2023-01-21 11:39:47.614280: step: 32/531, loss: 0.006088924594223499
2023-01-21 11:39:48.790800: step: 36/531, loss: 0.0009399413829669356
2023-01-21 11:39:49.946957: step: 40/531, loss: 0.008615875616669655
2023-01-21 11:39:51.100459: step: 44/531, loss: 0.006732272915542126
2023-01-21 11:39:52.234526: step: 48/531, loss: 0.002960777375847101
2023-01-21 11:39:53.415735: step: 52/531, loss: 0.004584789276123047
2023-01-21 11:39:54.560570: step: 56/531, loss: 0.020881080999970436
2023-01-21 11:39:55.686622: step: 60/531, loss: 0.03961324691772461
2023-01-21 11:39:56.856702: step: 64/531, loss: 0.0013036250602453947
2023-01-21 11:39:57.997861: step: 68/531, loss: 0.0003477096324786544
2023-01-21 11:39:59.146419: step: 72/531, loss: 0.008290481753647327
2023-01-21 11:40:00.309257: step: 76/531, loss: 0.0030734301544725895
2023-01-21 11:40:01.452448: step: 80/531, loss: 0.06168098375201225
2023-01-21 11:40:02.592639: step: 84/531, loss: 0.0008183956379070878
2023-01-21 11:40:03.745594: step: 88/531, loss: 0.0022891045082360506
2023-01-21 11:40:04.870860: step: 92/531, loss: 0.0003192901785951108
2023-01-21 11:40:06.031927: step: 96/531, loss: 0.03565606847405434
2023-01-21 11:40:07.156691: step: 100/531, loss: 0.011751865968108177
2023-01-21 11:40:08.288062: step: 104/531, loss: 0.0006559849134646356
2023-01-21 11:40:09.435371: step: 108/531, loss: 0.002317237900570035
2023-01-21 11:40:10.597691: step: 112/531, loss: 0.003711700439453125
2023-01-21 11:40:11.736643: step: 116/531, loss: 0.02535572089254856
2023-01-21 11:40:12.882022: step: 120/531, loss: 0.0025195598136633635
2023-01-21 11:40:14.029537: step: 124/531, loss: 0.0004847526433877647
2023-01-21 11:40:15.168294: step: 128/531, loss: 0.0026532651390880346
2023-01-21 11:40:16.317856: step: 132/531, loss: 3.2901763916015625e-05
2023-01-21 11:40:17.460862: step: 136/531, loss: 0.00017480850510764867
2023-01-21 11:40:18.606171: step: 140/531, loss: 0.03460407257080078
2023-01-21 11:40:19.766302: step: 144/531, loss: 0.01572561264038086
2023-01-21 11:40:20.914924: step: 148/531, loss: 0.011056089773774147
2023-01-21 11:40:22.045352: step: 152/531, loss: 0.013468456454575062
2023-01-21 11:40:23.179310: step: 156/531, loss: 0.010213661007583141
2023-01-21 11:40:24.324572: step: 160/531, loss: 0.014640617184340954
2023-01-21 11:40:25.462602: step: 164/531, loss: 0.036945246160030365
2023-01-21 11:40:26.634698: step: 168/531, loss: 0.06317062675952911
2023-01-21 11:40:27.763559: step: 172/531, loss: 0.033351898193359375
2023-01-21 11:40:28.911552: step: 176/531, loss: 0.012452125549316406
2023-01-21 11:40:30.023263: step: 180/531, loss: 0.006300449836999178
2023-01-21 11:40:31.168857: step: 184/531, loss: 0.002720308257266879
2023-01-21 11:40:32.287521: step: 188/531, loss: 0.0008658409351482987
2023-01-21 11:40:33.429477: step: 192/531, loss: 0.0006795406225137413
2023-01-21 11:40:34.565285: step: 196/531, loss: 0.0012495041592046618
2023-01-21 11:40:35.693553: step: 200/531, loss: 0.01313471794128418
2023-01-21 11:40:36.832682: step: 204/531, loss: 0.004545689094811678
2023-01-21 11:40:37.965389: step: 208/531, loss: 0.008954811841249466
2023-01-21 11:40:39.140549: step: 212/531, loss: 0.003331947373226285
2023-01-21 11:40:40.272273: step: 216/531, loss: 1.277923547604587e-05
2023-01-21 11:40:41.419933: step: 220/531, loss: 0.0645398199558258
2023-01-21 11:40:42.603106: step: 224/531, loss: 0.004652786068618298
2023-01-21 11:40:43.772873: step: 228/531, loss: 0.00368671421892941
2023-01-21 11:40:44.937023: step: 232/531, loss: 0.016959620639681816
2023-01-21 11:40:46.071388: step: 236/531, loss: 0.02703724056482315
2023-01-21 11:40:47.203453: step: 240/531, loss: 0.07674713432788849
2023-01-21 11:40:48.338293: step: 244/531, loss: 0.005436897277832031
2023-01-21 11:40:49.479389: step: 248/531, loss: 0.043573666363954544
2023-01-21 11:40:50.670339: step: 252/531, loss: 0.004396534059196711
2023-01-21 11:40:51.800643: step: 256/531, loss: 0.00010556057532085106
2023-01-21 11:40:52.933158: step: 260/531, loss: 0.0010340213775634766
2023-01-21 11:40:54.064644: step: 264/531, loss: 0.0028854371048510075
2023-01-21 11:40:55.197410: step: 268/531, loss: 0.003803730010986328
2023-01-21 11:40:56.317558: step: 272/531, loss: 0.03769569471478462
2023-01-21 11:40:57.477977: step: 276/531, loss: 0.004761695861816406
2023-01-21 11:40:58.627716: step: 280/531, loss: 6.027221752447076e-05
2023-01-21 11:40:59.778279: step: 284/531, loss: 0.006964683532714844
2023-01-21 11:41:00.944777: step: 288/531, loss: 0.0022860527969896793
2023-01-21 11:41:02.080447: step: 292/531, loss: 0.0256697665899992
2023-01-21 11:41:03.222150: step: 296/531, loss: 0.0028236389625817537
2023-01-21 11:41:04.352312: step: 300/531, loss: 0.9506793022155762
2023-01-21 11:41:05.451820: step: 304/531, loss: 0.035123251378536224
2023-01-21 11:41:06.612903: step: 308/531, loss: 0.027022648602724075
2023-01-21 11:41:07.750317: step: 312/531, loss: 0.018496274948120117
2023-01-21 11:41:08.889946: step: 316/531, loss: 0.0009350032196380198
2023-01-21 11:41:10.022368: step: 320/531, loss: 0.07793302834033966
2023-01-21 11:41:11.205281: step: 324/531, loss: 0.1767623871564865
2023-01-21 11:41:12.373879: step: 328/531, loss: 0.17111587524414062
2023-01-21 11:41:13.523902: step: 332/531, loss: 0.0017011642921715975
2023-01-21 11:41:14.644569: step: 336/531, loss: 0.005476903636008501
2023-01-21 11:41:15.763684: step: 340/531, loss: 0.04162655025720596
2023-01-21 11:41:16.908756: step: 344/531, loss: 0.004769611172378063
2023-01-21 11:41:18.036083: step: 348/531, loss: 0.003454208606854081
2023-01-21 11:41:19.165100: step: 352/531, loss: 0.0018506050109863281
2023-01-21 11:41:20.306259: step: 356/531, loss: 0.0025665522553026676
2023-01-21 11:41:21.461507: step: 360/531, loss: 0.012250995263457298
2023-01-21 11:41:22.604327: step: 364/531, loss: 0.006645584013313055
2023-01-21 11:41:23.802484: step: 368/531, loss: 0.0030879019759595394
2023-01-21 11:41:24.914558: step: 372/531, loss: 0.025671081617474556
2023-01-21 11:41:26.042159: step: 376/531, loss: 0.0050674439407885075
2023-01-21 11:41:27.186444: step: 380/531, loss: 0.04109544679522514
2023-01-21 11:41:28.343302: step: 384/531, loss: 0.004543876741081476
2023-01-21 11:41:29.494689: step: 388/531, loss: 0.0060402872040867805
2023-01-21 11:41:30.662305: step: 392/531, loss: 0.2047102004289627
2023-01-21 11:41:31.815800: step: 396/531, loss: 0.00027523041353560984
2023-01-21 11:41:32.974073: step: 400/531, loss: 0.0024860382545739412
2023-01-21 11:41:34.114666: step: 404/531, loss: 0.05309438705444336
2023-01-21 11:41:35.280607: step: 408/531, loss: 0.0016244888538494706
2023-01-21 11:41:36.421287: step: 412/531, loss: 0.004697990138083696
2023-01-21 11:41:37.537707: step: 416/531, loss: 0.001513147377409041
2023-01-21 11:41:38.681082: step: 420/531, loss: 0.0012660622596740723
2023-01-21 11:41:39.808414: step: 424/531, loss: 0.0015071869129315019
2023-01-21 11:41:40.969076: step: 428/531, loss: 0.01059427298605442
2023-01-21 11:41:42.130655: step: 432/531, loss: 0.0016851425170898438
2023-01-21 11:41:43.285161: step: 436/531, loss: 0.10824041813611984
2023-01-21 11:41:44.408538: step: 440/531, loss: 0.06368827819824219
2023-01-21 11:41:45.538344: step: 444/531, loss: 0.0011883736588060856
2023-01-21 11:41:46.667446: step: 448/531, loss: 0.004915905185043812
2023-01-21 11:41:47.828470: step: 452/531, loss: 0.003677892731502652
2023-01-21 11:41:48.959992: step: 456/531, loss: 0.00048294069711118937
2023-01-21 11:41:50.096941: step: 460/531, loss: 0.010367012582719326
2023-01-21 11:41:51.253873: step: 464/531, loss: 0.00116901402361691
2023-01-21 11:41:52.387283: step: 468/531, loss: 0.008903217501938343
2023-01-21 11:41:53.532945: step: 472/531, loss: 0.012033653445541859
2023-01-21 11:41:54.653630: step: 476/531, loss: 0.020710373297333717
2023-01-21 11:41:55.776229: step: 480/531, loss: 0.03330807760357857
2023-01-21 11:41:56.946076: step: 484/531, loss: 0.0028486251831054688
2023-01-21 11:41:58.063286: step: 488/531, loss: 0.0011233806144446135
2023-01-21 11:41:59.186914: step: 492/531, loss: 0.4351252615451813
2023-01-21 11:42:00.323525: step: 496/531, loss: 0.021006012335419655
2023-01-21 11:42:01.454608: step: 500/531, loss: 0.005177307408303022
2023-01-21 11:42:02.601060: step: 504/531, loss: 0.0018013000953942537
2023-01-21 11:42:03.739679: step: 508/531, loss: 0.00504646310582757
2023-01-21 11:42:04.897545: step: 512/531, loss: 0.01098618470132351
2023-01-21 11:42:06.037847: step: 516/531, loss: 0.02823019027709961
2023-01-21 11:42:07.190230: step: 520/531, loss: 0.018952036276459694
2023-01-21 11:42:08.339283: step: 524/531, loss: 0.003096246626228094
2023-01-21 11:42:09.454305: step: 528/531, loss: 0.005417061038315296
2023-01-21 11:42:10.602275: step: 532/531, loss: 1.5354156857938506e-05
2023-01-21 11:42:11.745659: step: 536/531, loss: 2.7322768801241182e-05
2023-01-21 11:42:12.903295: step: 540/531, loss: 0.0006726026767864823
2023-01-21 11:42:14.028743: step: 544/531, loss: 0.00288047781214118
2023-01-21 11:42:15.187797: step: 548/531, loss: 0.0016357897548004985
2023-01-21 11:42:16.360506: step: 552/531, loss: 0.0012948991497978568
2023-01-21 11:42:17.508549: step: 556/531, loss: 0.08109064400196075
2023-01-21 11:42:18.647683: step: 560/531, loss: 0.00536532374098897
2023-01-21 11:42:19.768293: step: 564/531, loss: 0.0013417243026196957
2023-01-21 11:42:20.895974: step: 568/531, loss: 0.008205318823456764
2023-01-21 11:42:22.000026: step: 572/531, loss: 0.005808735266327858
2023-01-21 11:42:23.093170: step: 576/531, loss: 0.04868336021900177
2023-01-21 11:42:24.240350: step: 580/531, loss: 0.06672382354736328
2023-01-21 11:42:25.343835: step: 584/531, loss: 0.010288047604262829
2023-01-21 11:42:26.464572: step: 588/531, loss: 0.006402492988854647
2023-01-21 11:42:27.606023: step: 592/531, loss: 0.00665626535192132
2023-01-21 11:42:28.725367: step: 596/531, loss: 0.01090784091502428
2023-01-21 11:42:29.843935: step: 600/531, loss: 0.0033571242820471525
2023-01-21 11:42:30.960638: step: 604/531, loss: 0.02584400214254856
2023-01-21 11:42:32.087804: step: 608/531, loss: 0.034188270568847656
2023-01-21 11:42:33.188506: step: 612/531, loss: 0.0041165826842188835
2023-01-21 11:42:34.322609: step: 616/531, loss: 0.0005871772882528603
2023-01-21 11:42:35.434810: step: 620/531, loss: 0.002373981522396207
2023-01-21 11:42:36.540544: step: 624/531, loss: 0.0195940975099802
2023-01-21 11:42:37.655858: step: 628/531, loss: 0.0017193795647472143
2023-01-21 11:42:38.782405: step: 632/531, loss: 0.009539700113236904
2023-01-21 11:42:39.892703: step: 636/531, loss: 0.008821678347885609
2023-01-21 11:42:41.009667: step: 640/531, loss: 0.0013298034900799394
2023-01-21 11:42:42.130426: step: 644/531, loss: 0.050620272755622864
2023-01-21 11:42:43.261753: step: 648/531, loss: 9.50813337112777e-05
2023-01-21 11:42:44.384102: step: 652/531, loss: 0.02529296837747097
2023-01-21 11:42:45.495989: step: 656/531, loss: 0.15853634476661682
2023-01-21 11:42:46.626919: step: 660/531, loss: 0.005134010221809149
2023-01-21 11:42:47.781097: step: 664/531, loss: 0.04036960378289223
2023-01-21 11:42:48.922161: step: 668/531, loss: 0.0036497116088867188
2023-01-21 11:42:50.066962: step: 672/531, loss: 0.0021221160423010588
2023-01-21 11:42:51.216963: step: 676/531, loss: 0.04682498052716255
2023-01-21 11:42:52.322492: step: 680/531, loss: 0.0021339417435228825
2023-01-21 11:42:53.435229: step: 684/531, loss: 0.022316742688417435
2023-01-21 11:42:54.553984: step: 688/531, loss: 0.010634375736117363
2023-01-21 11:42:55.686764: step: 692/531, loss: 0.015162086114287376
2023-01-21 11:42:56.832863: step: 696/531, loss: 0.028644420206546783
2023-01-21 11:42:57.953144: step: 700/531, loss: 0.011274337768554688
2023-01-21 11:42:59.080900: step: 704/531, loss: 0.016017531976103783
2023-01-21 11:43:00.240314: step: 708/531, loss: 0.0025228499434888363
2023-01-21 11:43:01.345251: step: 712/531, loss: 0.002355384873226285
2023-01-21 11:43:02.509478: step: 716/531, loss: 0.00970306433737278
2023-01-21 11:43:03.618521: step: 720/531, loss: 0.061035919934511185
2023-01-21 11:43:04.750187: step: 724/531, loss: 0.00026006699772551656
2023-01-21 11:43:05.878706: step: 728/531, loss: 0.06541280448436737
2023-01-21 11:43:07.026828: step: 732/531, loss: 0.04330329969525337
2023-01-21 11:43:08.138518: step: 736/531, loss: 0.006733036134392023
2023-01-21 11:43:09.281389: step: 740/531, loss: 0.08207492530345917
2023-01-21 11:43:10.406999: step: 744/531, loss: 0.010949230752885342
2023-01-21 11:43:11.539492: step: 748/531, loss: 0.003070259001106024
2023-01-21 11:43:12.685683: step: 752/531, loss: 1.8405915398034267e-05
2023-01-21 11:43:13.811981: step: 756/531, loss: 0.0004062652587890625
2023-01-21 11:43:14.960571: step: 760/531, loss: 0.6218775510787964
2023-01-21 11:43:16.089717: step: 764/531, loss: 0.043080996721982956
2023-01-21 11:43:17.209624: step: 768/531, loss: 0.02203083038330078
2023-01-21 11:43:18.356336: step: 772/531, loss: 0.005775070283561945
2023-01-21 11:43:19.491249: step: 776/531, loss: 0.023534394800662994
2023-01-21 11:43:20.650273: step: 780/531, loss: 0.007564353756606579
2023-01-21 11:43:21.790119: step: 784/531, loss: 0.022302530705928802
2023-01-21 11:43:22.932367: step: 788/531, loss: 0.004060268402099609
2023-01-21 11:43:24.048213: step: 792/531, loss: 0.014555168338119984
2023-01-21 11:43:25.169669: step: 796/531, loss: 0.0020805359818041325
2023-01-21 11:43:26.272309: step: 800/531, loss: 0.008567524142563343
2023-01-21 11:43:27.370671: step: 804/531, loss: 0.021487999707460403
2023-01-21 11:43:28.471105: step: 808/531, loss: 0.020430423319339752
2023-01-21 11:43:29.598945: step: 812/531, loss: 0.00170307164080441
2023-01-21 11:43:30.762387: step: 816/531, loss: 0.10097865760326385
2023-01-21 11:43:31.885468: step: 820/531, loss: 0.00042905809823423624
2023-01-21 11:43:33.005587: step: 824/531, loss: 0.03677425533533096
2023-01-21 11:43:34.102117: step: 828/531, loss: 0.1829545944929123
2023-01-21 11:43:35.215739: step: 832/531, loss: 0.0034366610925644636
2023-01-21 11:43:36.330110: step: 836/531, loss: 1.640319896978326e-05
2023-01-21 11:43:37.461173: step: 840/531, loss: 0.028613854199647903
2023-01-21 11:43:38.558584: step: 844/531, loss: 0.052391670644283295
2023-01-21 11:43:39.684985: step: 848/531, loss: 0.11765146255493164
2023-01-21 11:43:40.812947: step: 852/531, loss: 0.013640928082168102
2023-01-21 11:43:41.945037: step: 856/531, loss: 0.0018596648005768657
2023-01-21 11:43:43.065881: step: 860/531, loss: 0.044037818908691406
2023-01-21 11:43:44.149733: step: 864/531, loss: 0.0026501226238906384
2023-01-21 11:43:45.267913: step: 868/531, loss: 0.00021567345538642257
2023-01-21 11:43:46.394785: step: 872/531, loss: 0.01994319073855877
2023-01-21 11:43:47.497210: step: 876/531, loss: 0.017752457410097122
2023-01-21 11:43:48.632006: step: 880/531, loss: 0.0008252143743447959
2023-01-21 11:43:49.763035: step: 884/531, loss: 0.005032062530517578
2023-01-21 11:43:50.885247: step: 888/531, loss: 0.03981513902544975
2023-01-21 11:43:52.011598: step: 892/531, loss: 6.4849853515625e-05
2023-01-21 11:43:53.130761: step: 896/531, loss: 0.03224677965044975
2023-01-21 11:43:54.278711: step: 900/531, loss: 0.002524471143260598
2023-01-21 11:43:55.398071: step: 904/531, loss: 0.0009510040399618447
2023-01-21 11:43:56.536951: step: 908/531, loss: 0.005900669377297163
2023-01-21 11:43:57.652457: step: 912/531, loss: 0.03943004459142685
2023-01-21 11:43:58.792798: step: 916/531, loss: 0.010253643617033958
2023-01-21 11:43:59.911858: step: 920/531, loss: 0.0015802383422851562
2023-01-21 11:44:01.017235: step: 924/531, loss: 0.0019981383811682463
2023-01-21 11:44:02.133888: step: 928/531, loss: 0.03139305114746094
2023-01-21 11:44:03.263379: step: 932/531, loss: 0.005165481939911842
2023-01-21 11:44:04.393446: step: 936/531, loss: 0.013060332275927067
2023-01-21 11:44:05.503788: step: 940/531, loss: 0.0742708221077919
2023-01-21 11:44:06.657406: step: 944/531, loss: 0.00038471221341751516
2023-01-21 11:44:07.797432: step: 948/531, loss: 0.003289794782176614
2023-01-21 11:44:08.946180: step: 952/531, loss: 0.002192688174545765
2023-01-21 11:44:10.063754: step: 956/531, loss: 0.0007761001470498741
2023-01-21 11:44:11.185604: step: 960/531, loss: 0.0030113221146166325
2023-01-21 11:44:12.342070: step: 964/531, loss: 0.012280750088393688
2023-01-21 11:44:13.478050: step: 968/531, loss: 0.0018809319008141756
2023-01-21 11:44:14.612304: step: 972/531, loss: 0.0034415246918797493
2023-01-21 11:44:15.728263: step: 976/531, loss: 0.0027545930352061987
2023-01-21 11:44:16.863635: step: 980/531, loss: 0.029851054772734642
2023-01-21 11:44:18.004990: step: 984/531, loss: 0.0008300781482830644
2023-01-21 11:44:19.133218: step: 988/531, loss: 0.00027751922607421875
2023-01-21 11:44:20.246118: step: 992/531, loss: 0.008925247937440872
2023-01-21 11:44:21.406819: step: 996/531, loss: 0.025669574737548828
2023-01-21 11:44:22.542551: step: 1000/531, loss: 0.0010390281677246094
2023-01-21 11:44:23.686736: step: 1004/531, loss: 0.0013409615494310856
2023-01-21 11:44:24.810074: step: 1008/531, loss: 0.0231767650693655
2023-01-21 11:44:25.935532: step: 1012/531, loss: 0.01842346228659153
2023-01-21 11:44:27.033291: step: 1016/531, loss: 0.0015836716629564762
2023-01-21 11:44:28.166001: step: 1020/531, loss: 0.018020058050751686
2023-01-21 11:44:29.280490: step: 1024/531, loss: 0.0014772891299799085
2023-01-21 11:44:30.396543: step: 1028/531, loss: 0.015034866519272327
2023-01-21 11:44:31.512554: step: 1032/531, loss: 0.004685521125793457
2023-01-21 11:44:32.651048: step: 1036/531, loss: 0.02277698554098606
2023-01-21 11:44:33.785748: step: 1040/531, loss: 0.01061859168112278
2023-01-21 11:44:34.914604: step: 1044/531, loss: 0.00027976036653853953
2023-01-21 11:44:36.016846: step: 1048/531, loss: 0.014395476318895817
2023-01-21 11:44:37.139871: step: 1052/531, loss: 0.009355640038847923
2023-01-21 11:44:38.213777: step: 1056/531, loss: 0.001991176512092352
2023-01-21 11:44:39.323359: step: 1060/531, loss: 0.0010662078857421875
2023-01-21 11:44:40.443199: step: 1064/531, loss: 0.003956603817641735
2023-01-21 11:44:41.562865: step: 1068/531, loss: 0.015176678076386452
2023-01-21 11:44:42.727589: step: 1072/531, loss: 0.009981728158891201
2023-01-21 11:44:43.861389: step: 1076/531, loss: 0.00026569367037154734
2023-01-21 11:44:45.006810: step: 1080/531, loss: 0.06001472473144531
2023-01-21 11:44:46.141360: step: 1084/531, loss: 0.020830536261200905
2023-01-21 11:44:47.304179: step: 1088/531, loss: 5.2261355449445546e-05
2023-01-21 11:44:48.405439: step: 1092/531, loss: 0.039948273450136185
2023-01-21 11:44:49.572038: step: 1096/531, loss: 0.009328365325927734
2023-01-21 11:44:50.718918: step: 1100/531, loss: 0.04995737224817276
2023-01-21 11:44:51.825499: step: 1104/531, loss: 0.039972592145204544
2023-01-21 11:44:52.977856: step: 1108/531, loss: 0.12053127586841583
2023-01-21 11:44:54.156091: step: 1112/531, loss: 0.1123877540230751
2023-01-21 11:44:55.286003: step: 1116/531, loss: 0.0007764816400595009
2023-01-21 11:44:56.392962: step: 1120/531, loss: 3.4904482163256034e-05
2023-01-21 11:44:57.522841: step: 1124/531, loss: 4.435181472217664e-05
2023-01-21 11:44:58.652841: step: 1128/531, loss: 0.016382312402129173
2023-01-21 11:44:59.857877: step: 1132/531, loss: 0.005985927768051624
2023-01-21 11:45:00.967797: step: 1136/531, loss: 0.01979808881878853
2023-01-21 11:45:02.114980: step: 1140/531, loss: 0.011768150143325329
2023-01-21 11:45:03.256228: step: 1144/531, loss: 0.028656959533691406
2023-01-21 11:45:04.396582: step: 1148/531, loss: 0.01071310043334961
2023-01-21 11:45:05.507972: step: 1152/531, loss: 0.004043102264404297
2023-01-21 11:45:06.633135: step: 1156/531, loss: 0.0013257981045171618
2023-01-21 11:45:07.775792: step: 1160/531, loss: 0.01778564415872097
2023-01-21 11:45:08.903754: step: 1164/531, loss: 0.022917555645108223
2023-01-21 11:45:10.026880: step: 1168/531, loss: 0.009804916568100452
2023-01-21 11:45:11.142295: step: 1172/531, loss: 0.0028961184434592724
2023-01-21 11:45:12.253603: step: 1176/531, loss: 0.034318890422582626
2023-01-21 11:45:13.355564: step: 1180/531, loss: 0.019968032836914062
2023-01-21 11:45:14.486308: step: 1184/531, loss: 0.013418246060609818
2023-01-21 11:45:15.625101: step: 1188/531, loss: 0.00021619796461891383
2023-01-21 11:45:16.770275: step: 1192/531, loss: 0.006854534149169922
2023-01-21 11:45:17.894308: step: 1196/531, loss: 0.0023751261178404093
2023-01-21 11:45:19.052101: step: 1200/531, loss: 0.005202579312026501
2023-01-21 11:45:20.168473: step: 1204/531, loss: 0.03944401815533638
2023-01-21 11:45:21.298179: step: 1208/531, loss: 0.043874166905879974
2023-01-21 11:45:22.442485: step: 1212/531, loss: 0.02390737645328045
2023-01-21 11:45:23.588816: step: 1216/531, loss: 0.015093469992280006
2023-01-21 11:45:24.691326: step: 1220/531, loss: 0.02066631428897381
2023-01-21 11:45:25.815943: step: 1224/531, loss: 0.01851978339254856
2023-01-21 11:45:26.926482: step: 1228/531, loss: 0.0015571594703942537
2023-01-21 11:45:28.030613: step: 1232/531, loss: 0.00017633438983466476
2023-01-21 11:45:29.183181: step: 1236/531, loss: 0.002330017276108265
2023-01-21 11:45:30.315790: step: 1240/531, loss: 0.02168307453393936
2023-01-21 11:45:31.432996: step: 1244/531, loss: 0.00017604828462935984
2023-01-21 11:45:32.538255: step: 1248/531, loss: 4.225969314575195e-05
2023-01-21 11:45:33.641613: step: 1252/531, loss: 0.007478904910385609
2023-01-21 11:45:34.780709: step: 1256/531, loss: 0.008706665597856045
2023-01-21 11:45:35.882789: step: 1260/531, loss: 0.0162827018648386
2023-01-21 11:45:36.970905: step: 1264/531, loss: 0.5142583847045898
2023-01-21 11:45:38.150872: step: 1268/531, loss: 0.011841107159852982
2023-01-21 11:45:39.303285: step: 1272/531, loss: 0.12716332077980042
2023-01-21 11:45:40.406062: step: 1276/531, loss: 0.0002827644348144531
2023-01-21 11:45:41.536996: step: 1280/531, loss: 0.04491768032312393
2023-01-21 11:45:42.629350: step: 1284/531, loss: 0.0021846771705895662
2023-01-21 11:45:43.772843: step: 1288/531, loss: 0.05561580881476402
2023-01-21 11:45:44.897576: step: 1292/531, loss: 0.02542896196246147
2023-01-21 11:45:46.018574: step: 1296/531, loss: 0.011576270684599876
2023-01-21 11:45:47.125709: step: 1300/531, loss: 0.0013802527682855725
2023-01-21 11:45:48.234734: step: 1304/531, loss: 0.0012086868518963456
2023-01-21 11:45:49.340952: step: 1308/531, loss: 0.0012704730033874512
2023-01-21 11:45:50.486701: step: 1312/531, loss: 0.005118275061249733
2023-01-21 11:45:51.609510: step: 1316/531, loss: 0.016048623248934746
2023-01-21 11:45:52.725368: step: 1320/531, loss: 0.039365578442811966
2023-01-21 11:45:53.856209: step: 1324/531, loss: 0.14676152169704437
2023-01-21 11:45:54.964003: step: 1328/531, loss: 0.0005740642664022744
2023-01-21 11:45:56.088063: step: 1332/531, loss: 0.011646652594208717
2023-01-21 11:45:57.202731: step: 1336/531, loss: 0.03494701534509659
2023-01-21 11:45:58.305818: step: 1340/531, loss: 0.017216969281435013
2023-01-21 11:45:59.424264: step: 1344/531, loss: 0.0002588629722595215
2023-01-21 11:46:00.577502: step: 1348/531, loss: 0.03356371074914932
2023-01-21 11:46:01.697534: step: 1352/531, loss: 0.0009752869373187423
2023-01-21 11:46:02.799347: step: 1356/531, loss: 0.004111766815185547
2023-01-21 11:46:03.913564: step: 1360/531, loss: 0.02898387983441353
2023-01-21 11:46:05.053154: step: 1364/531, loss: 0.019160747528076172
2023-01-21 11:46:06.164223: step: 1368/531, loss: 0.008901119232177734
2023-01-21 11:46:07.289358: step: 1372/531, loss: 0.03926844522356987
2023-01-21 11:46:08.412008: step: 1376/531, loss: 0.007487107068300247
2023-01-21 11:46:09.526332: step: 1380/531, loss: 0.013589096255600452
2023-01-21 11:46:10.671510: step: 1384/531, loss: 0.0008289336692541838
2023-01-21 11:46:11.795607: step: 1388/531, loss: 0.004898262210190296
2023-01-21 11:46:12.910517: step: 1392/531, loss: 0.030797291547060013
2023-01-21 11:46:14.035760: step: 1396/531, loss: 0.032578181475400925
2023-01-21 11:46:15.175080: step: 1400/531, loss: 0.0035278319846838713
2023-01-21 11:46:16.301829: step: 1404/531, loss: 0.07108192145824432
2023-01-21 11:46:17.420874: step: 1408/531, loss: 0.0009618759504519403
2023-01-21 11:46:18.509472: step: 1412/531, loss: 0.0014719485770910978
2023-01-21 11:46:19.629363: step: 1416/531, loss: 0.014411736279726028
2023-01-21 11:46:20.735531: step: 1420/531, loss: 0.07227764278650284
2023-01-21 11:46:21.857362: step: 1424/531, loss: 0.0005627631908282638
2023-01-21 11:46:22.985634: step: 1428/531, loss: 0.002186393830925226
2023-01-21 11:46:24.111212: step: 1432/531, loss: 0.004756069276481867
2023-01-21 11:46:25.217467: step: 1436/531, loss: 0.013280868530273438
2023-01-21 11:46:26.334515: step: 1440/531, loss: 0.07637672126293182
2023-01-21 11:46:27.445696: step: 1444/531, loss: 0.00012483597674872726
2023-01-21 11:46:28.555765: step: 1448/531, loss: 0.028372764587402344
2023-01-21 11:46:29.690613: step: 1452/531, loss: 0.13273964822292328
2023-01-21 11:46:30.832301: step: 1456/531, loss: 0.004987239837646484
2023-01-21 11:46:31.950342: step: 1460/531, loss: 0.010878301225602627
2023-01-21 11:46:33.082009: step: 1464/531, loss: 0.00035729407682083547
2023-01-21 11:46:34.222354: step: 1468/531, loss: 0.008220863528549671
2023-01-21 11:46:35.345301: step: 1472/531, loss: 0.08306674659252167
2023-01-21 11:46:36.487896: step: 1476/531, loss: 0.0025267601013183594
2023-01-21 11:46:37.619904: step: 1480/531, loss: 0.002458858536556363
2023-01-21 11:46:38.766451: step: 1484/531, loss: 0.014220905490219593
2023-01-21 11:46:39.878404: step: 1488/531, loss: 0.035814955830574036
2023-01-21 11:46:40.968356: step: 1492/531, loss: 0.0010467767715454102
2023-01-21 11:46:42.110845: step: 1496/531, loss: 0.026447296142578125
2023-01-21 11:46:43.246888: step: 1500/531, loss: 0.004253196530044079
2023-01-21 11:46:44.380106: step: 1504/531, loss: 0.010828590951859951
2023-01-21 11:46:45.518300: step: 1508/531, loss: 0.012438202276825905
2023-01-21 11:46:46.655324: step: 1512/531, loss: 0.12399540096521378
2023-01-21 11:46:47.771553: step: 1516/531, loss: 0.05304145812988281
2023-01-21 11:46:48.895965: step: 1520/531, loss: 0.9977067708969116
2023-01-21 11:46:50.007537: step: 1524/531, loss: 0.0004220008850097656
2023-01-21 11:46:51.125011: step: 1528/531, loss: 0.021581172943115234
2023-01-21 11:46:52.276830: step: 1532/531, loss: 0.013091754168272018
2023-01-21 11:46:53.409543: step: 1536/531, loss: 0.0030873059295117855
2023-01-21 11:46:54.523095: step: 1540/531, loss: 0.012424659915268421
2023-01-21 11:46:55.656789: step: 1544/531, loss: 0.004489040467888117
2023-01-21 11:46:56.804606: step: 1548/531, loss: 0.06501083076000214
2023-01-21 11:46:57.927741: step: 1552/531, loss: 0.013829231262207031
2023-01-21 11:46:59.064795: step: 1556/531, loss: 0.0030202865600585938
2023-01-21 11:47:00.206722: step: 1560/531, loss: 0.030702590942382812
2023-01-21 11:47:01.329793: step: 1564/531, loss: 0.007418537512421608
2023-01-21 11:47:02.466976: step: 1568/531, loss: 0.013056755065917969
2023-01-21 11:47:03.567105: step: 1572/531, loss: 0.02622990682721138
2023-01-21 11:47:04.680556: step: 1576/531, loss: 0.00029087066650390625
2023-01-21 11:47:05.812118: step: 1580/531, loss: 0.0006665230030193925
2023-01-21 11:47:06.945050: step: 1584/531, loss: 0.020923137664794922
2023-01-21 11:47:08.067711: step: 1588/531, loss: 0.002063846681267023
2023-01-21 11:47:09.198047: step: 1592/531, loss: 0.035413406789302826
2023-01-21 11:47:10.305256: step: 1596/531, loss: 0.003982734400779009
2023-01-21 11:47:11.422758: step: 1600/531, loss: 0.015372944064438343
2023-01-21 11:47:12.565532: step: 1604/531, loss: 0.0336545966565609
2023-01-21 11:47:13.691571: step: 1608/531, loss: 0.001318645547144115
2023-01-21 11:47:14.867602: step: 1612/531, loss: 0.0953337699174881
2023-01-21 11:47:15.989502: step: 1616/531, loss: 0.013346386142075062
2023-01-21 11:47:17.144721: step: 1620/531, loss: 0.0012282371753826737
2023-01-21 11:47:18.299063: step: 1624/531, loss: 0.00912400521337986
2023-01-21 11:47:19.450819: step: 1628/531, loss: 0.017554188147187233
2023-01-21 11:47:20.605358: step: 1632/531, loss: 0.3540692925453186
2023-01-21 11:47:21.738133: step: 1636/531, loss: 0.003894519992172718
2023-01-21 11:47:22.880298: step: 1640/531, loss: 0.0267702117562294
2023-01-21 11:47:23.984559: step: 1644/531, loss: 0.02014951780438423
2023-01-21 11:47:25.102698: step: 1648/531, loss: 0.016979217529296875
2023-01-21 11:47:26.214465: step: 1652/531, loss: 0.0168896671384573
2023-01-21 11:47:27.366921: step: 1656/531, loss: 0.048267364501953125
2023-01-21 11:47:28.472642: step: 1660/531, loss: 0.009469985961914062
2023-01-21 11:47:29.614813: step: 1664/531, loss: 0.005391311831772327
2023-01-21 11:47:30.713448: step: 1668/531, loss: 0.0007425307994708419
2023-01-21 11:47:31.820580: step: 1672/531, loss: 0.0420406349003315
2023-01-21 11:47:32.934686: step: 1676/531, loss: 0.0016560613876208663
2023-01-21 11:47:34.062156: step: 1680/531, loss: 0.005781936924904585
2023-01-21 11:47:35.202421: step: 1684/531, loss: 0.013836097903549671
2023-01-21 11:47:36.327424: step: 1688/531, loss: 0.04584769159555435
2023-01-21 11:47:37.456579: step: 1692/531, loss: 0.7160861492156982
2023-01-21 11:47:38.643751: step: 1696/531, loss: 0.007689857389777899
2023-01-21 11:47:39.740027: step: 1700/531, loss: 0.025319673120975494
2023-01-21 11:47:40.887111: step: 1704/531, loss: 0.0014995576348155737
2023-01-21 11:47:41.987401: step: 1708/531, loss: 0.0001924514799611643
2023-01-21 11:47:43.177286: step: 1712/531, loss: 0.011108208447694778
2023-01-21 11:47:44.300542: step: 1716/531, loss: 2.5463104975642636e-05
2023-01-21 11:47:45.427658: step: 1720/531, loss: 0.0024192810524255037
2023-01-21 11:47:46.538521: step: 1724/531, loss: 0.005981254391372204
2023-01-21 11:47:47.662345: step: 1728/531, loss: 0.006235494278371334
2023-01-21 11:47:48.787265: step: 1732/531, loss: 0.0011915683280676603
2023-01-21 11:47:49.880004: step: 1736/531, loss: 0.02448296546936035
2023-01-21 11:47:50.997349: step: 1740/531, loss: 0.00030746462289243937
2023-01-21 11:47:52.132354: step: 1744/531, loss: 0.002175998641178012
2023-01-21 11:47:53.253994: step: 1748/531, loss: 0.014426803216338158
2023-01-21 11:47:54.399970: step: 1752/531, loss: 0.0007915496826171875
2023-01-21 11:47:55.543604: step: 1756/531, loss: 0.01966848410665989
2023-01-21 11:47:56.668633: step: 1760/531, loss: 0.0036152838729321957
2023-01-21 11:47:57.761432: step: 1764/531, loss: 0.004521941766142845
2023-01-21 11:47:58.901138: step: 1768/531, loss: 0.0029969215393066406
2023-01-21 11:48:00.003003: step: 1772/531, loss: 0.1358700692653656
2023-01-21 11:48:01.118532: step: 1776/531, loss: 0.00028514862060546875
2023-01-21 11:48:02.254325: step: 1780/531, loss: 0.05023372173309326
2023-01-21 11:48:03.388748: step: 1784/531, loss: 0.00014681815810035914
2023-01-21 11:48:04.516986: step: 1788/531, loss: 0.1009206771850586
2023-01-21 11:48:05.640611: step: 1792/531, loss: 0.008335304446518421
2023-01-21 11:48:06.754915: step: 1796/531, loss: 0.007214164361357689
2023-01-21 11:48:07.886722: step: 1800/531, loss: 0.01632719114422798
2023-01-21 11:48:09.000220: step: 1804/531, loss: 0.011091900058090687
2023-01-21 11:48:10.129464: step: 1808/531, loss: 0.009494018740952015
2023-01-21 11:48:11.228877: step: 1812/531, loss: 4.9591064453125e-05
2023-01-21 11:48:12.358915: step: 1816/531, loss: 0.0048836711794137955
2023-01-21 11:48:13.495084: step: 1820/531, loss: 0.011188220232725143
2023-01-21 11:48:14.612313: step: 1824/531, loss: 0.03418397903442383
2023-01-21 11:48:15.725372: step: 1828/531, loss: 0.006816101260483265
2023-01-21 11:48:16.868205: step: 1832/531, loss: 0.014355897903442383
2023-01-21 11:48:17.996606: step: 1836/531, loss: 0.012384224683046341
2023-01-21 11:48:19.124566: step: 1840/531, loss: 0.015866853296756744
2023-01-21 11:48:20.244378: step: 1844/531, loss: 0.005111503414809704
2023-01-21 11:48:21.358837: step: 1848/531, loss: 0.0036849023308604956
2023-01-21 11:48:22.459232: step: 1852/531, loss: 0.00725555419921875
2023-01-21 11:48:23.575039: step: 1856/531, loss: 0.006637954618781805
2023-01-21 11:48:24.692287: step: 1860/531, loss: 0.027082158252596855
2023-01-21 11:48:25.840904: step: 1864/531, loss: 6.027221752447076e-05
2023-01-21 11:48:26.975112: step: 1868/531, loss: 0.004913997836410999
2023-01-21 11:48:28.099706: step: 1872/531, loss: 0.01860027387738228
2023-01-21 11:48:29.185637: step: 1876/531, loss: 0.0009579658508300781
2023-01-21 11:48:30.315239: step: 1880/531, loss: 0.013873673044145107
2023-01-21 11:48:31.448818: step: 1884/531, loss: 0.0077481744810938835
2023-01-21 11:48:32.572235: step: 1888/531, loss: 0.0016108512645587325
2023-01-21 11:48:33.690508: step: 1892/531, loss: 0.02321157418191433
2023-01-21 11:48:34.800104: step: 1896/531, loss: 0.00941934622824192
2023-01-21 11:48:35.937909: step: 1900/531, loss: 0.012918282300233841
2023-01-21 11:48:37.077205: step: 1904/531, loss: 0.09151711314916611
2023-01-21 11:48:38.224790: step: 1908/531, loss: 0.023932266980409622
2023-01-21 11:48:39.363310: step: 1912/531, loss: 0.0008336066966876388
2023-01-21 11:48:40.499471: step: 1916/531, loss: 0.0006187439430505037
2023-01-21 11:48:41.614047: step: 1920/531, loss: 0.03745322674512863
2023-01-21 11:48:42.731652: step: 1924/531, loss: 0.0685700923204422
2023-01-21 11:48:43.890563: step: 1928/531, loss: 0.03850212320685387
2023-01-21 11:48:45.047081: step: 1932/531, loss: 0.03474188223481178
2023-01-21 11:48:46.189797: step: 1936/531, loss: 0.07472896575927734
2023-01-21 11:48:47.309489: step: 1940/531, loss: 0.0002773284795694053
2023-01-21 11:48:48.429917: step: 1944/531, loss: 0.01052703894674778
2023-01-21 11:48:49.557659: step: 1948/531, loss: 0.002759838243946433
2023-01-21 11:48:50.694225: step: 1952/531, loss: 0.01571073569357395
2023-01-21 11:48:51.803172: step: 1956/531, loss: 0.019237900152802467
2023-01-21 11:48:52.975954: step: 1960/531, loss: 0.006918144412338734
2023-01-21 11:48:54.102456: step: 1964/531, loss: 0.0060765743255615234
2023-01-21 11:48:55.231964: step: 1968/531, loss: 0.203074648976326
2023-01-21 11:48:56.354219: step: 1972/531, loss: 0.02259836345911026
2023-01-21 11:48:57.480407: step: 1976/531, loss: 0.05362844839692116
2023-01-21 11:48:58.662357: step: 1980/531, loss: 0.04101886600255966
2023-01-21 11:48:59.792919: step: 1984/531, loss: 0.10275831818580627
2023-01-21 11:49:00.913505: step: 1988/531, loss: 0.005096626468002796
2023-01-21 11:49:02.062060: step: 1992/531, loss: 0.04721679538488388
2023-01-21 11:49:03.205717: step: 1996/531, loss: 0.00303573627024889
2023-01-21 11:49:04.344642: step: 2000/531, loss: 0.004309463780373335
2023-01-21 11:49:05.465687: step: 2004/531, loss: 0.0004177093505859375
2023-01-21 11:49:06.581402: step: 2008/531, loss: 0.04394808039069176
2023-01-21 11:49:07.722376: step: 2012/531, loss: 0.004927921574562788
2023-01-21 11:49:08.844117: step: 2016/531, loss: 0.010747337713837624
2023-01-21 11:49:09.956848: step: 2020/531, loss: 0.007941722869873047
2023-01-21 11:49:11.113293: step: 2024/531, loss: 0.0010666847229003906
2023-01-21 11:49:12.242384: step: 2028/531, loss: 0.01838255114853382
2023-01-21 11:49:13.363986: step: 2032/531, loss: 0.013684415258467197
2023-01-21 11:49:14.476028: step: 2036/531, loss: 0.041971590369939804
2023-01-21 11:49:15.597221: step: 2040/531, loss: 0.04240410402417183
2023-01-21 11:49:16.724607: step: 2044/531, loss: 0.0019712448120117188
2023-01-21 11:49:17.892597: step: 2048/531, loss: 0.028433896601200104
2023-01-21 11:49:19.031197: step: 2052/531, loss: 0.0034172057639807463
2023-01-21 11:49:20.142048: step: 2056/531, loss: 0.00012826919555664062
2023-01-21 11:49:21.292248: step: 2060/531, loss: 0.0026869773864746094
2023-01-21 11:49:22.416943: step: 2064/531, loss: 0.006666278932243586
2023-01-21 11:49:23.534368: step: 2068/531, loss: 0.03172168880701065
2023-01-21 11:49:24.660057: step: 2072/531, loss: 0.001980256987735629
2023-01-21 11:49:25.788218: step: 2076/531, loss: 0.04443387687206268
2023-01-21 11:49:26.914579: step: 2080/531, loss: 0.029921580106019974
2023-01-21 11:49:28.016251: step: 2084/531, loss: 0.004064416978508234
2023-01-21 11:49:29.141655: step: 2088/531, loss: 0.02584085613489151
2023-01-21 11:49:30.251447: step: 2092/531, loss: 0.05431981384754181
2023-01-21 11:49:31.414771: step: 2096/531, loss: 0.0022117614280432463
2023-01-21 11:49:32.534189: step: 2100/531, loss: 5.0139427912654355e-05
2023-01-21 11:49:33.630922: step: 2104/531, loss: 0.16524915397167206
2023-01-21 11:49:34.740411: step: 2108/531, loss: 0.0037687302101403475
2023-01-21 11:49:35.883166: step: 2112/531, loss: 0.00509986886754632
2023-01-21 11:49:36.991962: step: 2116/531, loss: 0.023537253960967064
2023-01-21 11:49:38.110997: step: 2120/531, loss: 6.151199340820312e-05
2023-01-21 11:49:39.265152: step: 2124/531, loss: 0.00567970285192132
==================================================
Loss: 0.028
--------------------
Dev: {'event': {'p': 0.6068111455108359, 'r': 0.7829560585885486, 'f1': 0.6837209302325582}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6335282651072125, 'r': 0.7751937984496124, 'f1': 0.6972378653794583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
Korean: {'event': {'p': 0.6981132075471698, 'r': 0.5873015873015873, 'f1': 0.6379310344827586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4186046511627907, 'r': 0.5, 'f1': 0.45569620253164556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 19
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 11:50:19.310090: step: 4/531, loss: 0.021774865686893463
2023-01-21 11:50:20.440465: step: 8/531, loss: 0.003297806018963456
2023-01-21 11:50:21.567006: step: 12/531, loss: 0.0008193016401492059
2023-01-21 11:50:22.686607: step: 16/531, loss: 0.004964637570083141
2023-01-21 11:50:23.887047: step: 20/531, loss: 0.026790238916873932
2023-01-21 11:50:25.035118: step: 24/531, loss: 0.004458617884665728
2023-01-21 11:50:26.175671: step: 28/531, loss: 0.0053986553102731705
2023-01-21 11:50:27.281972: step: 32/531, loss: 0.00088586809579283
2023-01-21 11:50:28.416168: step: 36/531, loss: 0.001613616943359375
2023-01-21 11:50:29.581875: step: 40/531, loss: 0.002263720380142331
2023-01-21 11:50:30.703099: step: 44/531, loss: 0.009144973941147327
2023-01-21 11:50:31.820188: step: 48/531, loss: 0.019995499402284622
2023-01-21 11:50:32.960740: step: 52/531, loss: 0.01346435584127903
2023-01-21 11:50:34.068138: step: 56/531, loss: 0.00715184211730957
2023-01-21 11:50:35.175066: step: 60/531, loss: 0.0001561522512929514
2023-01-21 11:50:36.286465: step: 64/531, loss: 0.00826277770102024
2023-01-21 11:50:37.420873: step: 68/531, loss: 0.00022821426682639867
2023-01-21 11:50:38.533043: step: 72/531, loss: 0.0005769729614257812
2023-01-21 11:50:39.650841: step: 76/531, loss: 0.0006278991932049394
2023-01-21 11:50:40.769801: step: 80/531, loss: 0.0016788482898846269
2023-01-21 11:50:41.936142: step: 84/531, loss: 0.02372589334845543
2023-01-21 11:50:43.030908: step: 88/531, loss: 0.04442644119262695
2023-01-21 11:50:44.140667: step: 92/531, loss: 0.03994712978601456
2023-01-21 11:50:45.265411: step: 96/531, loss: 8.316040475619957e-05
2023-01-21 11:50:46.405094: step: 100/531, loss: 0.001708173775114119
2023-01-21 11:50:47.529725: step: 104/531, loss: 0.009626675397157669
2023-01-21 11:50:48.652770: step: 108/531, loss: 0.023299027234315872
2023-01-21 11:50:49.822137: step: 112/531, loss: 0.0004995345952920616
2023-01-21 11:50:50.924315: step: 116/531, loss: 0.00029392243595793843
2023-01-21 11:50:52.047681: step: 120/531, loss: 0.08871670067310333
2023-01-21 11:50:53.185757: step: 124/531, loss: 0.02886180952191353
2023-01-21 11:50:54.326700: step: 128/531, loss: 0.005850434303283691
2023-01-21 11:50:55.451984: step: 132/531, loss: 0.0003031254163943231
2023-01-21 11:50:56.574831: step: 136/531, loss: 0.007513666059821844
2023-01-21 11:50:57.710782: step: 140/531, loss: 0.014364433474838734
2023-01-21 11:50:58.830990: step: 144/531, loss: 1.621246337890625e-05
2023-01-21 11:51:00.016904: step: 148/531, loss: 0.016949845477938652
2023-01-21 11:51:01.140196: step: 152/531, loss: 0.03637523949146271
2023-01-21 11:51:02.272120: step: 156/531, loss: 0.008419609628617764
2023-01-21 11:51:03.400700: step: 160/531, loss: 0.009605360217392445
2023-01-21 11:51:04.520268: step: 164/531, loss: 0.0005672454717569053
2023-01-21 11:51:05.640654: step: 168/531, loss: 9.479522850597277e-05
2023-01-21 11:51:06.768042: step: 172/531, loss: 0.004299068823456764
2023-01-21 11:51:07.899808: step: 176/531, loss: 0.010895348154008389
2023-01-21 11:51:09.048175: step: 180/531, loss: 0.022380853071808815
2023-01-21 11:51:10.162825: step: 184/531, loss: 0.03881235048174858
2023-01-21 11:51:11.260180: step: 188/531, loss: 0.0012378693791106343
2023-01-21 11:51:12.418851: step: 192/531, loss: 0.0003843307786155492
2023-01-21 11:51:13.548660: step: 196/531, loss: 4.014969090349041e-05
2023-01-21 11:51:14.656662: step: 200/531, loss: 1.7309188478975557e-05
2023-01-21 11:51:15.786414: step: 204/531, loss: 0.0024289132561534643
2023-01-21 11:51:16.955830: step: 208/531, loss: 0.023194218054413795
2023-01-21 11:51:18.059251: step: 212/531, loss: 0.0009517669677734375
2023-01-21 11:51:19.180115: step: 216/531, loss: 0.0016796112759038806
2023-01-21 11:51:20.308392: step: 220/531, loss: 0.00046072006807662547
2023-01-21 11:51:21.431645: step: 224/531, loss: 0.0037144662346690893
2023-01-21 11:51:22.578924: step: 228/531, loss: 0.011960029602050781
2023-01-21 11:51:23.724979: step: 232/531, loss: 0.04152221605181694
2023-01-21 11:51:24.848857: step: 236/531, loss: 0.007193088531494141
2023-01-21 11:51:25.966801: step: 240/531, loss: 0.029358768835663795
2023-01-21 11:51:27.069237: step: 244/531, loss: 0.00495758093893528
2023-01-21 11:51:28.170268: step: 248/531, loss: 0.019596051424741745
2023-01-21 11:51:29.290587: step: 252/531, loss: 0.026639176532626152
2023-01-21 11:51:30.413553: step: 256/531, loss: 0.026469087228178978
2023-01-21 11:51:31.515032: step: 260/531, loss: 0.0074745179153978825
2023-01-21 11:51:32.645452: step: 264/531, loss: 9.298324584960938e-05
2023-01-21 11:51:33.742422: step: 268/531, loss: 0.01766366884112358
2023-01-21 11:51:34.913514: step: 272/531, loss: 0.00015125275240279734
2023-01-21 11:51:36.036574: step: 276/531, loss: 7.233619544422254e-05
2023-01-21 11:51:37.195687: step: 280/531, loss: 0.0015003205044195056
2023-01-21 11:51:38.314195: step: 284/531, loss: 0.007439041044563055
2023-01-21 11:51:39.436213: step: 288/531, loss: 0.00200061802752316
2023-01-21 11:51:40.598766: step: 292/531, loss: 0.007681847084313631
2023-01-21 11:51:41.725621: step: 296/531, loss: 0.07629070430994034
2023-01-21 11:51:42.899519: step: 300/531, loss: 7.085800461936742e-05
2023-01-21 11:51:44.027492: step: 304/531, loss: 0.022782612591981888
2023-01-21 11:51:45.173393: step: 308/531, loss: 0.01322860736399889
2023-01-21 11:51:46.300644: step: 312/531, loss: 0.0021564005874097347
2023-01-21 11:51:47.410974: step: 316/531, loss: 0.00033664703369140625
2023-01-21 11:51:48.555024: step: 320/531, loss: 6.408691842807457e-05
2023-01-21 11:51:49.670418: step: 324/531, loss: 0.015746403485536575
2023-01-21 11:51:50.838861: step: 328/531, loss: 0.0006113052368164062
2023-01-21 11:51:51.957186: step: 332/531, loss: 0.0001567840517964214
2023-01-21 11:51:53.138244: step: 336/531, loss: 0.0001987457217182964
2023-01-21 11:51:54.298665: step: 340/531, loss: 0.002033424563705921
2023-01-21 11:51:55.455064: step: 344/531, loss: 0.006628227420151234
2023-01-21 11:51:56.572345: step: 348/531, loss: 0.00033245087251998484
2023-01-21 11:51:57.718668: step: 352/531, loss: 0.0070993900299072266
2023-01-21 11:51:58.812257: step: 356/531, loss: 0.0002586364862509072
2023-01-21 11:51:59.954867: step: 360/531, loss: 0.00681352661922574
2023-01-21 11:52:01.074974: step: 364/531, loss: 0.0006393432850018144
2023-01-21 11:52:02.178450: step: 368/531, loss: 0.00043745042057707906
2023-01-21 11:52:03.298007: step: 372/531, loss: 0.016713649034500122
2023-01-21 11:52:04.402062: step: 376/531, loss: 6.008148193359375e-05
2023-01-21 11:52:05.523619: step: 380/531, loss: 0.0001295089750783518
2023-01-21 11:52:06.674652: step: 384/531, loss: 4.09603126172442e-05
2023-01-21 11:52:07.790520: step: 388/531, loss: 0.02054738998413086
2023-01-21 11:52:08.883624: step: 392/531, loss: 0.012370300479233265
2023-01-21 11:52:10.009670: step: 396/531, loss: 0.0016174317570403218
2023-01-21 11:52:11.128852: step: 400/531, loss: 0.004982471466064453
2023-01-21 11:52:12.254648: step: 404/531, loss: 0.020618915557861328
2023-01-21 11:52:13.378133: step: 408/531, loss: 0.0016371726524084806
2023-01-21 11:52:14.516658: step: 412/531, loss: 0.009154129773378372
2023-01-21 11:52:15.647753: step: 416/531, loss: 0.0031499862670898438
2023-01-21 11:52:16.769064: step: 420/531, loss: 0.009401131421327591
2023-01-21 11:52:17.897519: step: 424/531, loss: 0.03657817840576172
2023-01-21 11:52:19.041349: step: 428/531, loss: 0.004002475645393133
2023-01-21 11:52:20.160012: step: 432/531, loss: 0.03427467495203018
2023-01-21 11:52:21.294809: step: 436/531, loss: 0.0012998580932617188
2023-01-21 11:52:22.415598: step: 440/531, loss: 0.008352660574018955
2023-01-21 11:52:23.530196: step: 444/531, loss: 0.010051536373794079
2023-01-21 11:52:24.662691: step: 448/531, loss: 0.023071765899658203
2023-01-21 11:52:25.776998: step: 452/531, loss: 0.0051774028688669205
2023-01-21 11:52:26.922450: step: 456/531, loss: 0.047353506088256836
2023-01-21 11:52:28.020806: step: 460/531, loss: 0.0015575409634038806
2023-01-21 11:52:29.148166: step: 464/531, loss: 0.028129005804657936
2023-01-21 11:52:30.269880: step: 468/531, loss: 0.10703869163990021
2023-01-21 11:52:31.397696: step: 472/531, loss: 2.150845766067505
2023-01-21 11:52:32.510873: step: 476/531, loss: 0.08871117234230042
2023-01-21 11:52:33.630352: step: 480/531, loss: 0.02733917161822319
2023-01-21 11:52:34.748312: step: 484/531, loss: 0.0016666412120684981
2023-01-21 11:52:35.854487: step: 488/531, loss: 0.038111019879579544
2023-01-21 11:52:36.975307: step: 492/531, loss: 0.0211913101375103
2023-01-21 11:52:38.116788: step: 496/531, loss: 0.040123939514160156
2023-01-21 11:52:39.204046: step: 500/531, loss: 0.001449155854061246
2023-01-21 11:52:40.360785: step: 504/531, loss: 0.010195351205766201
2023-01-21 11:52:41.486555: step: 508/531, loss: 0.014333915896713734
2023-01-21 11:52:42.639656: step: 512/531, loss: 0.009818458929657936
2023-01-21 11:52:43.747938: step: 516/531, loss: 0.0017593861557543278
2023-01-21 11:52:44.878986: step: 520/531, loss: 0.03319110721349716
2023-01-21 11:52:46.000845: step: 524/531, loss: 0.001635646796785295
2023-01-21 11:52:47.149802: step: 528/531, loss: 0.0005859375232830644
2023-01-21 11:52:48.275132: step: 532/531, loss: 0.004174709320068359
2023-01-21 11:52:49.376056: step: 536/531, loss: 1.4686585018353071e-05
2023-01-21 11:52:50.470267: step: 540/531, loss: 0.02717127837240696
2023-01-21 11:52:51.581348: step: 544/531, loss: 0.07589860260486603
2023-01-21 11:52:52.702477: step: 548/531, loss: 0.0011615753173828125
2023-01-21 11:52:53.853844: step: 552/531, loss: 6.50405854685232e-05
2023-01-21 11:52:54.993651: step: 556/531, loss: 0.0038873672019690275
2023-01-21 11:52:56.148620: step: 560/531, loss: 0.002979278564453125
2023-01-21 11:52:57.260695: step: 564/531, loss: 0.01357269287109375
2023-01-21 11:52:58.360301: step: 568/531, loss: 0.0006916999700479209
2023-01-21 11:52:59.489478: step: 572/531, loss: 0.037612345069646835
2023-01-21 11:53:00.627509: step: 576/531, loss: 0.061872102320194244
2023-01-21 11:53:01.751995: step: 580/531, loss: 0.0006643772358074784
2023-01-21 11:53:02.855650: step: 584/531, loss: 0.0032600881531834602
2023-01-21 11:53:03.950555: step: 588/531, loss: 0.018627069890499115
2023-01-21 11:53:05.123226: step: 592/531, loss: 0.006424427032470703
2023-01-21 11:53:06.259220: step: 596/531, loss: 0.028169060125947
2023-01-21 11:53:07.375498: step: 600/531, loss: 0.00293979630805552
2023-01-21 11:53:08.497875: step: 604/531, loss: 0.00856781005859375
2023-01-21 11:53:09.607480: step: 608/531, loss: 0.0031015395652502775
2023-01-21 11:53:10.724295: step: 612/531, loss: 0.11968812346458435
2023-01-21 11:53:11.886896: step: 616/531, loss: 0.002677345182746649
2023-01-21 11:53:13.011634: step: 620/531, loss: 0.010006952099502087
2023-01-21 11:53:14.143532: step: 624/531, loss: 7.791518874000758e-05
2023-01-21 11:53:15.244840: step: 628/531, loss: 0.09418831020593643
2023-01-21 11:53:16.373308: step: 632/531, loss: 0.0015654563903808594
2023-01-21 11:53:17.498378: step: 636/531, loss: 0.038721658289432526
2023-01-21 11:53:18.659181: step: 640/531, loss: 0.0008864403353072703
2023-01-21 11:53:19.744958: step: 644/531, loss: 0.009693908505141735
2023-01-21 11:53:20.862963: step: 648/531, loss: 0.004512977320700884
2023-01-21 11:53:21.981643: step: 652/531, loss: 0.08417234569787979
2023-01-21 11:53:23.089534: step: 656/531, loss: 0.05561542510986328
2023-01-21 11:53:24.232816: step: 660/531, loss: 0.03448457643389702
2023-01-21 11:53:25.356281: step: 664/531, loss: 0.006698226556181908
2023-01-21 11:53:26.474441: step: 668/531, loss: 0.0004410743713378906
2023-01-21 11:53:27.587376: step: 672/531, loss: 0.0008738517644815147
2023-01-21 11:53:28.731514: step: 676/531, loss: 0.012852382846176624
2023-01-21 11:53:29.850959: step: 680/531, loss: 0.00514068640768528
2023-01-21 11:53:30.988523: step: 684/531, loss: 0.013738918118178844
2023-01-21 11:53:32.101568: step: 688/531, loss: 0.003887748811393976
2023-01-21 11:53:33.209943: step: 692/531, loss: 0.004408836364746094
2023-01-21 11:53:34.321483: step: 696/531, loss: 0.0009400367271155119
2023-01-21 11:53:35.463899: step: 700/531, loss: 0.005610466003417969
2023-01-21 11:53:36.569780: step: 704/531, loss: 0.046169281005859375
2023-01-21 11:53:37.723492: step: 708/531, loss: 0.0016885282238945365
2023-01-21 11:53:38.838140: step: 712/531, loss: 0.07701750099658966
2023-01-21 11:53:39.946383: step: 716/531, loss: 0.00010318756540073082
2023-01-21 11:53:41.065281: step: 720/531, loss: 0.034327082335948944
2023-01-21 11:53:42.189398: step: 724/531, loss: 0.039343737065792084
2023-01-21 11:53:43.356111: step: 728/531, loss: 0.001779746962711215
2023-01-21 11:53:44.496790: step: 732/531, loss: 0.0003326416190247983
2023-01-21 11:53:45.616498: step: 736/531, loss: 0.01098089199513197
2023-01-21 11:53:46.726824: step: 740/531, loss: 0.00043025019112974405
2023-01-21 11:53:47.836602: step: 744/531, loss: 0.004878139588981867
2023-01-21 11:53:48.990107: step: 748/531, loss: 0.16960486769676208
2023-01-21 11:53:50.121994: step: 752/531, loss: 0.007018971722573042
2023-01-21 11:53:51.283021: step: 756/531, loss: 0.27476367354393005
2023-01-21 11:53:52.430063: step: 760/531, loss: 0.010851479135453701
2023-01-21 11:53:53.579378: step: 764/531, loss: 0.0008899689419195056
2023-01-21 11:53:54.712649: step: 768/531, loss: 0.07832906395196915
2023-01-21 11:53:55.832783: step: 772/531, loss: 0.006233406253159046
2023-01-21 11:53:56.949685: step: 776/531, loss: 0.02190704457461834
2023-01-21 11:53:58.040639: step: 780/531, loss: 0.009016704745590687
2023-01-21 11:53:59.150738: step: 784/531, loss: 0.004018593113869429
2023-01-21 11:54:00.269251: step: 788/531, loss: 0.12882958352565765
2023-01-21 11:54:01.381219: step: 792/531, loss: 0.03900623321533203
2023-01-21 11:54:02.526369: step: 796/531, loss: 0.003976059146225452
2023-01-21 11:54:03.624032: step: 800/531, loss: 0.003622150281444192
2023-01-21 11:54:04.717859: step: 804/531, loss: 0.000869369541760534
2023-01-21 11:54:05.847985: step: 808/531, loss: 0.0006271362653933465
2023-01-21 11:54:06.974891: step: 812/531, loss: 0.001170349190942943
2023-01-21 11:54:08.140317: step: 816/531, loss: 0.005314064212143421
2023-01-21 11:54:09.249625: step: 820/531, loss: 0.01682577282190323
2023-01-21 11:54:10.414135: step: 824/531, loss: 0.09665050357580185
2023-01-21 11:54:11.506911: step: 828/531, loss: 0.010643578134477139
2023-01-21 11:54:12.644650: step: 832/531, loss: 0.004461956210434437
2023-01-21 11:54:13.788378: step: 836/531, loss: 0.025493621826171875
2023-01-21 11:54:14.898288: step: 840/531, loss: 0.00021114348783157766
2023-01-21 11:54:16.002294: step: 844/531, loss: 0.0010432243579998612
2023-01-21 11:54:17.128956: step: 848/531, loss: 0.0006978035089559853
2023-01-21 11:54:18.219518: step: 852/531, loss: 0.0020401955116540194
2023-01-21 11:54:19.354724: step: 856/531, loss: 0.007204628083854914
2023-01-21 11:54:20.516143: step: 860/531, loss: 0.00022249220637604594
2023-01-21 11:54:21.628451: step: 864/531, loss: 0.0034241676330566406
2023-01-21 11:54:22.759661: step: 868/531, loss: 0.015542030334472656
2023-01-21 11:54:23.866908: step: 872/531, loss: 0.014749717898666859
2023-01-21 11:54:24.997984: step: 876/531, loss: 0.2659747004508972
2023-01-21 11:54:26.152134: step: 880/531, loss: 0.0003009796200785786
2023-01-21 11:54:27.311211: step: 884/531, loss: 0.0334935188293457
2023-01-21 11:54:28.449428: step: 888/531, loss: 0.00046634674072265625
2023-01-21 11:54:29.580408: step: 892/531, loss: 0.0377628318965435
2023-01-21 11:54:30.703883: step: 896/531, loss: 0.0030347825959324837
2023-01-21 11:54:31.830320: step: 900/531, loss: 0.0003682136593852192
2023-01-21 11:54:32.940218: step: 904/531, loss: 0.001639080117456615
2023-01-21 11:54:34.034198: step: 908/531, loss: 0.00545191764831543
2023-01-21 11:54:35.199483: step: 912/531, loss: 5.9413909184513614e-05
2023-01-21 11:54:36.314561: step: 916/531, loss: 0.011179161258041859
2023-01-21 11:54:37.419038: step: 920/531, loss: 0.02012462541460991
2023-01-21 11:54:38.549873: step: 924/531, loss: 0.0021423338912427425
2023-01-21 11:54:39.660605: step: 928/531, loss: 0.0006941795581951737
2023-01-21 11:54:40.765913: step: 932/531, loss: 0.016993045806884766
2023-01-21 11:54:41.927718: step: 936/531, loss: 0.0271956454962492
2023-01-21 11:54:43.026119: step: 940/531, loss: 0.009504509158432484
2023-01-21 11:54:44.116531: step: 944/531, loss: 7.572174217784777e-05
2023-01-21 11:54:45.273313: step: 948/531, loss: 0.003237152239307761
2023-01-21 11:54:46.392506: step: 952/531, loss: 0.001349163125269115
2023-01-21 11:54:47.519067: step: 956/531, loss: 0.0029471160378307104
2023-01-21 11:54:48.616896: step: 960/531, loss: 0.0008769988780841231
2023-01-21 11:54:49.752047: step: 964/531, loss: 0.0027378082741051912
2023-01-21 11:54:50.871782: step: 968/531, loss: 6.790161569369957e-05
2023-01-21 11:54:52.017968: step: 972/531, loss: 0.007440376095473766
2023-01-21 11:54:53.143352: step: 976/531, loss: 2.212524486822076e-05
2023-01-21 11:54:54.235886: step: 980/531, loss: 0.0023380278144031763
2023-01-21 11:54:55.345764: step: 984/531, loss: 0.01171875
2023-01-21 11:54:56.482566: step: 988/531, loss: 0.08126763999462128
2023-01-21 11:54:57.635067: step: 992/531, loss: 0.005520439241081476
2023-01-21 11:54:58.758956: step: 996/531, loss: 0.02872181124985218
2023-01-21 11:54:59.872276: step: 1000/531, loss: 0.00659027136862278
2023-01-21 11:55:00.992903: step: 1004/531, loss: 0.002119636395946145
2023-01-21 11:55:02.122265: step: 1008/531, loss: 0.023251915350556374
2023-01-21 11:55:03.226488: step: 1012/531, loss: 0.007507658097893
2023-01-21 11:55:04.349859: step: 1016/531, loss: 0.009218406863510609
2023-01-21 11:55:05.487443: step: 1020/531, loss: 7.848739915061742e-05
2023-01-21 11:55:06.613886: step: 1024/531, loss: 0.023998452350497246
2023-01-21 11:55:07.711688: step: 1028/531, loss: 0.0024919509887695312
2023-01-21 11:55:08.820402: step: 1032/531, loss: 0.3282504975795746
2023-01-21 11:55:09.940978: step: 1036/531, loss: 0.07005710899829865
2023-01-21 11:55:11.064889: step: 1040/531, loss: 0.002349138492718339
2023-01-21 11:55:12.193148: step: 1044/531, loss: 0.014036941342055798
2023-01-21 11:55:13.334356: step: 1048/531, loss: 0.9460031390190125
2023-01-21 11:55:14.454559: step: 1052/531, loss: 0.0005957603571005166
2023-01-21 11:55:15.615765: step: 1056/531, loss: 0.0005673408741131425
2023-01-21 11:55:16.753452: step: 1060/531, loss: 0.022977065294981003
2023-01-21 11:55:17.926635: step: 1064/531, loss: 0.0015851021744310856
2023-01-21 11:55:19.089535: step: 1068/531, loss: 0.0017631531227380037
2023-01-21 11:55:20.195568: step: 1072/531, loss: 0.010807324200868607
2023-01-21 11:55:21.307514: step: 1076/531, loss: 0.0019211769104003906
2023-01-21 11:55:22.452331: step: 1080/531, loss: 0.01241006888449192
2023-01-21 11:55:23.570921: step: 1084/531, loss: 0.001371192978695035
2023-01-21 11:55:24.733276: step: 1088/531, loss: 0.022568846121430397
2023-01-21 11:55:25.881578: step: 1092/531, loss: 0.0575714111328125
2023-01-21 11:55:26.965169: step: 1096/531, loss: 0.00023736954608466476
2023-01-21 11:55:28.098993: step: 1100/531, loss: 0.0002596855047158897
2023-01-21 11:55:29.210171: step: 1104/531, loss: 0.02332897298038006
2023-01-21 11:55:30.346553: step: 1108/531, loss: 0.0010480880737304688
2023-01-21 11:55:31.483921: step: 1112/531, loss: 0.025191783905029297
2023-01-21 11:55:32.608912: step: 1116/531, loss: 0.002181148622184992
2023-01-21 11:55:33.722454: step: 1120/531, loss: 0.06768856197595596
2023-01-21 11:55:34.832548: step: 1124/531, loss: 0.02094268798828125
2023-01-21 11:55:35.967353: step: 1128/531, loss: 0.0018142700428143144
2023-01-21 11:55:37.091938: step: 1132/531, loss: 0.0005220413440838456
2023-01-21 11:55:38.218471: step: 1136/531, loss: 0.004665279295295477
2023-01-21 11:55:39.349054: step: 1140/531, loss: 0.004373789299279451
2023-01-21 11:55:40.455714: step: 1144/531, loss: 0.0011593819363042712
2023-01-21 11:55:41.592480: step: 1148/531, loss: 0.01715850830078125
2023-01-21 11:55:42.723905: step: 1152/531, loss: 0.014469528570771217
2023-01-21 11:55:43.828980: step: 1156/531, loss: 0.06168556213378906
2023-01-21 11:55:44.952364: step: 1160/531, loss: 0.017923450097441673
2023-01-21 11:55:46.083575: step: 1164/531, loss: 7.877350435592234e-05
2023-01-21 11:55:47.188222: step: 1168/531, loss: 0.15074072778224945
2023-01-21 11:55:48.303497: step: 1172/531, loss: 0.003982043359428644
2023-01-21 11:55:49.427416: step: 1176/531, loss: 0.0001735687255859375
2023-01-21 11:55:50.534826: step: 1180/531, loss: 0.013539505191147327
2023-01-21 11:55:51.636198: step: 1184/531, loss: 0.00222358712926507
2023-01-21 11:55:52.732267: step: 1188/531, loss: 0.06036806106567383
2023-01-21 11:55:53.847857: step: 1192/531, loss: 0.02926473505795002
2023-01-21 11:55:54.963772: step: 1196/531, loss: 0.005973434541374445
2023-01-21 11:55:56.091644: step: 1200/531, loss: 0.07603234797716141
2023-01-21 11:55:57.221659: step: 1204/531, loss: 0.08309116214513779
2023-01-21 11:55:58.353488: step: 1208/531, loss: 0.001554298447445035
2023-01-21 11:55:59.463492: step: 1212/531, loss: 0.016304684802889824
2023-01-21 11:56:00.590722: step: 1216/531, loss: 0.0026255608536303043
2023-01-21 11:56:01.706010: step: 1220/531, loss: 0.005945563316345215
2023-01-21 11:56:02.844752: step: 1224/531, loss: 0.011342979036271572
2023-01-21 11:56:03.982485: step: 1228/531, loss: 0.0019277870887890458
2023-01-21 11:56:05.146323: step: 1232/531, loss: 0.004613018594682217
2023-01-21 11:56:06.258542: step: 1236/531, loss: 0.008495235815644264
2023-01-21 11:56:07.387871: step: 1240/531, loss: 0.0004703998565673828
2023-01-21 11:56:08.529166: step: 1244/531, loss: 0.009263992309570312
2023-01-21 11:56:09.643469: step: 1248/531, loss: 0.026507757604122162
2023-01-21 11:56:10.760496: step: 1252/531, loss: 0.0037362095899879932
2023-01-21 11:56:11.889210: step: 1256/531, loss: 0.00014877320791129023
2023-01-21 11:56:13.054746: step: 1260/531, loss: 0.025048065930604935
2023-01-21 11:56:14.181029: step: 1264/531, loss: 0.015803813934326172
2023-01-21 11:56:15.292020: step: 1268/531, loss: 0.019459737464785576
2023-01-21 11:56:16.404207: step: 1272/531, loss: 5.708222389221191
2023-01-21 11:56:17.528520: step: 1276/531, loss: 0.006019210908561945
2023-01-21 11:56:18.640246: step: 1280/531, loss: 0.0006554603460244834
2023-01-21 11:56:19.757354: step: 1284/531, loss: 0.025496290996670723
2023-01-21 11:56:20.888025: step: 1288/531, loss: 0.0019849776290357113
2023-01-21 11:56:21.994446: step: 1292/531, loss: 0.0039237975142896175
2023-01-21 11:56:23.102493: step: 1296/531, loss: 0.002945423126220703
2023-01-21 11:56:24.239147: step: 1300/531, loss: 0.0004101276572328061
2023-01-21 11:56:25.356176: step: 1304/531, loss: 0.01688413694500923
2023-01-21 11:56:26.480098: step: 1308/531, loss: 0.006579685490578413
2023-01-21 11:56:27.595575: step: 1312/531, loss: 0.0008119583362713456
2023-01-21 11:56:28.697855: step: 1316/531, loss: 0.03907661512494087
2023-01-21 11:56:29.810669: step: 1320/531, loss: 0.06547622382640839
2023-01-21 11:56:30.977837: step: 1324/531, loss: 0.0116767892614007
2023-01-21 11:56:32.103446: step: 1328/531, loss: 0.0016048431862145662
2023-01-21 11:56:33.227449: step: 1332/531, loss: 0.0022387029603123665
2023-01-21 11:56:34.347616: step: 1336/531, loss: 0.05269908905029297
2023-01-21 11:56:35.479137: step: 1340/531, loss: 0.00705718994140625
2023-01-21 11:56:36.598600: step: 1344/531, loss: 0.01972327195107937
2023-01-21 11:56:37.726982: step: 1348/531, loss: 0.010999679565429688
2023-01-21 11:56:38.858333: step: 1352/531, loss: 7.190704491222277e-05
2023-01-21 11:56:40.005548: step: 1356/531, loss: 0.05779323726892471
2023-01-21 11:56:41.123366: step: 1360/531, loss: 0.10737772285938263
2023-01-21 11:56:42.243620: step: 1364/531, loss: 0.011308384127914906
2023-01-21 11:56:43.359453: step: 1368/531, loss: 0.005716132931411266
2023-01-21 11:56:44.449949: step: 1372/531, loss: 0.002205276396125555
2023-01-21 11:56:45.571865: step: 1376/531, loss: 0.11157312989234924
2023-01-21 11:56:46.710512: step: 1380/531, loss: 0.039624977856874466
2023-01-21 11:56:47.832451: step: 1384/531, loss: 0.0033893585205078125
2023-01-21 11:56:48.955057: step: 1388/531, loss: 0.02301044389605522
2023-01-21 11:56:50.073383: step: 1392/531, loss: 1.4877320609230082e-05
2023-01-21 11:56:51.196544: step: 1396/531, loss: 0.016780473291873932
2023-01-21 11:56:52.301828: step: 1400/531, loss: 0.0001243591250386089
2023-01-21 11:56:53.422029: step: 1404/531, loss: 0.00256862654350698
2023-01-21 11:56:54.532067: step: 1408/531, loss: 0.02869243733584881
2023-01-21 11:56:55.682191: step: 1412/531, loss: 0.0808895081281662
2023-01-21 11:56:56.804811: step: 1416/531, loss: 0.005414771847426891
2023-01-21 11:56:57.911157: step: 1420/531, loss: 0.026924896985292435
2023-01-21 11:56:59.079213: step: 1424/531, loss: 0.005845832638442516
2023-01-21 11:57:00.212319: step: 1428/531, loss: 0.019009782001376152
2023-01-21 11:57:01.338766: step: 1432/531, loss: 0.010701370425522327
2023-01-21 11:57:02.443155: step: 1436/531, loss: 0.00855798739939928
2023-01-21 11:57:03.583974: step: 1440/531, loss: 0.07895880192518234
2023-01-21 11:57:04.699776: step: 1444/531, loss: 0.0001310408115386963
2023-01-21 11:57:05.779573: step: 1448/531, loss: 6.456374831032008e-05
2023-01-21 11:57:06.901318: step: 1452/531, loss: 0.027254678308963776
2023-01-21 11:57:08.010430: step: 1456/531, loss: 8.285045623779297e-06
2023-01-21 11:57:09.161971: step: 1460/531, loss: 0.0012935638660565019
2023-01-21 11:57:10.364018: step: 1464/531, loss: 5.92231735936366e-05
2023-01-21 11:57:11.474950: step: 1468/531, loss: 0.00257530203089118
2023-01-21 11:57:12.615860: step: 1472/531, loss: 0.0187561996281147
2023-01-21 11:57:13.725116: step: 1476/531, loss: 0.0022233964409679174
2023-01-21 11:57:14.837782: step: 1480/531, loss: 0.033853914588689804
2023-01-21 11:57:15.966303: step: 1484/531, loss: 0.008032608777284622
2023-01-21 11:57:17.083698: step: 1488/531, loss: 0.058172985911369324
2023-01-21 11:57:18.206235: step: 1492/531, loss: 0.01960144005715847
2023-01-21 11:57:19.323048: step: 1496/531, loss: 0.0006505012279376388
2023-01-21 11:57:20.475047: step: 1500/531, loss: 0.03543548658490181
2023-01-21 11:57:21.608317: step: 1504/531, loss: 0.020316410809755325
2023-01-21 11:57:22.749788: step: 1508/531, loss: 0.0008294105646200478
2023-01-21 11:57:23.890456: step: 1512/531, loss: 0.0038497925270348787
2023-01-21 11:57:25.010116: step: 1516/531, loss: 0.00017452239990234375
2023-01-21 11:57:26.107889: step: 1520/531, loss: 0.025977134704589844
2023-01-21 11:57:27.233686: step: 1524/531, loss: 0.19000402092933655
2023-01-21 11:57:28.353572: step: 1528/531, loss: 0.0007034302107058465
2023-01-21 11:57:29.442900: step: 1532/531, loss: 0.0004435062292031944
2023-01-21 11:57:30.576786: step: 1536/531, loss: 0.038680270314216614
2023-01-21 11:57:31.697704: step: 1540/531, loss: 0.0119050033390522
2023-01-21 11:57:32.808247: step: 1544/531, loss: 0.009246635250747204
2023-01-21 11:57:33.963229: step: 1548/531, loss: 0.0768747329711914
2023-01-21 11:57:35.089921: step: 1552/531, loss: 0.002993679139763117
2023-01-21 11:57:36.198591: step: 1556/531, loss: 0.009084701538085938
2023-01-21 11:57:37.320267: step: 1560/531, loss: 0.026015853509306908
2023-01-21 11:57:38.474754: step: 1564/531, loss: 0.025530051440000534
2023-01-21 11:57:39.631962: step: 1568/531, loss: 0.00481414794921875
2023-01-21 11:57:40.755189: step: 1572/531, loss: 0.0170959010720253
2023-01-21 11:57:41.888818: step: 1576/531, loss: 0.0021110535599291325
2023-01-21 11:57:43.021625: step: 1580/531, loss: 0.003279113909229636
2023-01-21 11:57:44.166979: step: 1584/531, loss: 0.013786125928163528
2023-01-21 11:57:45.302716: step: 1588/531, loss: 0.4355245530605316
2023-01-21 11:57:46.416000: step: 1592/531, loss: 0.02680683322250843
2023-01-21 11:57:47.548891: step: 1596/531, loss: 0.001596164656803012
2023-01-21 11:57:48.711556: step: 1600/531, loss: 0.044547270983457565
2023-01-21 11:57:49.866537: step: 1604/531, loss: 0.0033332600723952055
2023-01-21 11:57:50.963556: step: 1608/531, loss: 0.0007431983831338584
2023-01-21 11:57:52.114590: step: 1612/531, loss: 0.05588526651263237
2023-01-21 11:57:53.213398: step: 1616/531, loss: 0.01378555316478014
2023-01-21 11:57:54.377509: step: 1620/531, loss: 0.007518768310546875
2023-01-21 11:57:55.486455: step: 1624/531, loss: 0.5234982371330261
2023-01-21 11:57:56.616140: step: 1628/531, loss: 0.03787059709429741
2023-01-21 11:57:57.740384: step: 1632/531, loss: 0.033288098871707916
2023-01-21 11:57:58.846080: step: 1636/531, loss: 0.06309814751148224
2023-01-21 11:57:59.982053: step: 1640/531, loss: 0.0019058703910559416
2023-01-21 11:58:01.127129: step: 1644/531, loss: 0.00012168884131824598
2023-01-21 11:58:02.269389: step: 1648/531, loss: 0.01869392767548561
2023-01-21 11:58:03.407469: step: 1652/531, loss: 0.011718559078872204
2023-01-21 11:58:04.510202: step: 1656/531, loss: 0.08411464095115662
2023-01-21 11:58:05.642580: step: 1660/531, loss: 0.10163459926843643
2023-01-21 11:58:06.782586: step: 1664/531, loss: 0.0006858825217932463
2023-01-21 11:58:07.918490: step: 1668/531, loss: 0.00040068625821731985
2023-01-21 11:58:09.059048: step: 1672/531, loss: 0.006806755438446999
2023-01-21 11:58:10.211552: step: 1676/531, loss: 0.022788619622588158
2023-01-21 11:58:11.345045: step: 1680/531, loss: 0.0009676933404989541
2023-01-21 11:58:12.455111: step: 1684/531, loss: 0.0006309509626589715
2023-01-21 11:58:13.601822: step: 1688/531, loss: 0.021967411041259766
2023-01-21 11:58:14.740891: step: 1692/531, loss: 0.0069030760787427425
2023-01-21 11:58:15.825528: step: 1696/531, loss: 0.024108124896883965
2023-01-21 11:58:16.935805: step: 1700/531, loss: 0.011985397897660732
2023-01-21 11:58:18.049238: step: 1704/531, loss: 0.0008909702301025391
2023-01-21 11:58:19.162844: step: 1708/531, loss: 0.028653526678681374
2023-01-21 11:58:20.286318: step: 1712/531, loss: 0.0013363838661462069
2023-01-21 11:58:21.404481: step: 1716/531, loss: 0.0009044647449627519
2023-01-21 11:58:22.581026: step: 1720/531, loss: 0.40769681334495544
2023-01-21 11:58:23.675572: step: 1724/531, loss: 0.01176919974386692
2023-01-21 11:58:24.799972: step: 1728/531, loss: 0.0016537666087970138
2023-01-21 11:58:25.945608: step: 1732/531, loss: 0.002243518829345703
2023-01-21 11:58:27.090575: step: 1736/531, loss: 0.0081787109375
2023-01-21 11:58:28.235307: step: 1740/531, loss: 0.023046303540468216
2023-01-21 11:58:29.352740: step: 1744/531, loss: 0.0001750946103129536
2023-01-21 11:58:30.479037: step: 1748/531, loss: 0.018784141167998314
2023-01-21 11:58:31.579746: step: 1752/531, loss: 0.0007564544794149697
2023-01-21 11:58:32.690621: step: 1756/531, loss: 0.0015965461498126388
2023-01-21 11:58:33.838892: step: 1760/531, loss: 0.04813232645392418
2023-01-21 11:58:34.957606: step: 1764/531, loss: 0.01738262176513672
2023-01-21 11:58:36.072382: step: 1768/531, loss: 0.016205787658691406
2023-01-21 11:58:37.239822: step: 1772/531, loss: 0.015374946407973766
2023-01-21 11:58:38.365605: step: 1776/531, loss: 0.09460468590259552
2023-01-21 11:58:39.498918: step: 1780/531, loss: 0.03217830881476402
2023-01-21 11:58:40.619481: step: 1784/531, loss: 0.0019771577790379524
2023-01-21 11:58:41.729138: step: 1788/531, loss: 0.045255471020936966
2023-01-21 11:58:42.896265: step: 1792/531, loss: 0.5086870193481445
2023-01-21 11:58:44.021162: step: 1796/531, loss: 0.00323238386772573
2023-01-21 11:58:45.168931: step: 1800/531, loss: 0.01699838787317276
2023-01-21 11:58:46.314332: step: 1804/531, loss: 0.0033195496071130037
2023-01-21 11:58:47.446939: step: 1808/531, loss: 0.009302711114287376
2023-01-21 11:58:48.562251: step: 1812/531, loss: 0.01246786117553711
2023-01-21 11:58:49.710103: step: 1816/531, loss: 0.018048763275146484
2023-01-21 11:58:50.821337: step: 1820/531, loss: 0.021665286272764206
2023-01-21 11:58:51.930555: step: 1824/531, loss: 0.05903530493378639
2023-01-21 11:58:53.079017: step: 1828/531, loss: 0.002219820162281394
2023-01-21 11:58:54.206722: step: 1832/531, loss: 0.0009521216270513833
2023-01-21 11:58:55.360905: step: 1836/531, loss: 0.0267473217099905
2023-01-21 11:58:56.493840: step: 1840/531, loss: 3.442764500505291e-05
2023-01-21 11:58:57.625077: step: 1844/531, loss: 0.0003047943173442036
2023-01-21 11:58:58.765541: step: 1848/531, loss: 0.0029417993500828743
2023-01-21 11:58:59.894533: step: 1852/531, loss: 0.0022022249177098274
2023-01-21 11:59:00.987589: step: 1856/531, loss: 0.008856392465531826
2023-01-21 11:59:02.141103: step: 1860/531, loss: 0.024514103308320045
2023-01-21 11:59:03.262679: step: 1864/531, loss: 0.010797357186675072
2023-01-21 11:59:04.428200: step: 1868/531, loss: 0.008493900299072266
2023-01-21 11:59:05.565069: step: 1872/531, loss: 0.0013776780106127262
2023-01-21 11:59:06.700175: step: 1876/531, loss: 0.008048439398407936
2023-01-21 11:59:07.838330: step: 1880/531, loss: 0.011584472842514515
2023-01-21 11:59:08.940475: step: 1884/531, loss: 0.020602131262421608
2023-01-21 11:59:10.045035: step: 1888/531, loss: 0.000511550868395716
2023-01-21 11:59:11.188137: step: 1892/531, loss: 0.00052471156232059
2023-01-21 11:59:12.311193: step: 1896/531, loss: 0.023732900619506836
2023-01-21 11:59:13.423900: step: 1900/531, loss: 0.0006944656488485634
2023-01-21 11:59:14.556672: step: 1904/531, loss: 0.017507171258330345
2023-01-21 11:59:15.674064: step: 1908/531, loss: 0.0008890152093954384
2023-01-21 11:59:16.800499: step: 1912/531, loss: 0.521493136882782
2023-01-21 11:59:17.928744: step: 1916/531, loss: 0.006575965788215399
2023-01-21 11:59:19.081970: step: 1920/531, loss: 0.03630819171667099
2023-01-21 11:59:20.203211: step: 1924/531, loss: 0.0015388488536700606
2023-01-21 11:59:21.332328: step: 1928/531, loss: 0.0010128498543053865
2023-01-21 11:59:22.469785: step: 1932/531, loss: 9.243488602805883e-05
2023-01-21 11:59:23.588723: step: 1936/531, loss: 0.04502449184656143
2023-01-21 11:59:24.684106: step: 1940/531, loss: 0.024698257446289062
2023-01-21 11:59:25.785018: step: 1944/531, loss: 0.049653541296720505
2023-01-21 11:59:26.923956: step: 1948/531, loss: 0.007354449946433306
2023-01-21 11:59:28.023307: step: 1952/531, loss: 0.0004199981631245464
2023-01-21 11:59:29.155616: step: 1956/531, loss: 0.03657131269574165
2023-01-21 11:59:30.269531: step: 1960/531, loss: 0.02404041402041912
2023-01-21 11:59:31.412999: step: 1964/531, loss: 0.003380298614501953
2023-01-21 11:59:32.554115: step: 1968/531, loss: 0.04798908159136772
2023-01-21 11:59:33.684920: step: 1972/531, loss: 6.561279587913305e-05
2023-01-21 11:59:34.801380: step: 1976/531, loss: 0.06883364170789719
2023-01-21 11:59:35.931311: step: 1980/531, loss: 0.105682373046875
2023-01-21 11:59:37.053565: step: 1984/531, loss: 0.03601713478565216
2023-01-21 11:59:38.179017: step: 1988/531, loss: 0.05721559748053551
2023-01-21 11:59:39.321977: step: 1992/531, loss: 0.001248264336027205
2023-01-21 11:59:40.452782: step: 1996/531, loss: 0.004532671067863703
2023-01-21 11:59:41.536723: step: 2000/531, loss: 0.009381581097841263
2023-01-21 11:59:42.623320: step: 2004/531, loss: 0.007079505827277899
2023-01-21 11:59:43.765178: step: 2008/531, loss: 0.027020836248993874
2023-01-21 11:59:44.877931: step: 2012/531, loss: 0.005078315734863281
2023-01-21 11:59:45.978798: step: 2016/531, loss: 0.07335501164197922
2023-01-21 11:59:47.089794: step: 2020/531, loss: 0.0004953384632244706
2023-01-21 11:59:48.218710: step: 2024/531, loss: 0.015381241217255592
2023-01-21 11:59:49.345902: step: 2028/531, loss: 0.04582581669092178
2023-01-21 11:59:50.470072: step: 2032/531, loss: 0.00015506744966842234
2023-01-21 11:59:51.611672: step: 2036/531, loss: 0.0020740509498864412
2023-01-21 11:59:52.760388: step: 2040/531, loss: 0.731652021408081
2023-01-21 11:59:53.898462: step: 2044/531, loss: 0.016856957226991653
2023-01-21 11:59:55.041126: step: 2048/531, loss: 0.036249447613954544
2023-01-21 11:59:56.156634: step: 2052/531, loss: 0.3892022967338562
2023-01-21 11:59:57.286062: step: 2056/531, loss: 0.0001808166562113911
2023-01-21 11:59:58.418367: step: 2060/531, loss: 0.05925578996539116
2023-01-21 11:59:59.563489: step: 2064/531, loss: 0.002898311708122492
2023-01-21 12:00:00.682047: step: 2068/531, loss: 0.19325199723243713
2023-01-21 12:00:01.845653: step: 2072/531, loss: 0.006012630648910999
2023-01-21 12:00:02.969963: step: 2076/531, loss: 0.0014399291248992085
2023-01-21 12:00:04.092685: step: 2080/531, loss: 0.063079833984375
2023-01-21 12:00:05.212080: step: 2084/531, loss: 0.025150300934910774
2023-01-21 12:00:06.348136: step: 2088/531, loss: 0.0005260050529614091
2023-01-21 12:00:07.488083: step: 2092/531, loss: 0.06699495017528534
2023-01-21 12:00:08.608681: step: 2096/531, loss: 0.0049537657760083675
2023-01-21 12:00:09.745358: step: 2100/531, loss: 0.0001588821323821321
2023-01-21 12:00:10.869294: step: 2104/531, loss: 0.0003912449174094945
2023-01-21 12:00:11.957183: step: 2108/531, loss: 0.007337617687880993
2023-01-21 12:00:13.099716: step: 2112/531, loss: 0.10829510539770126
2023-01-21 12:00:14.261947: step: 2116/531, loss: 0.056516267359256744
2023-01-21 12:00:15.394246: step: 2120/531, loss: 0.05558471754193306
2023-01-21 12:00:16.496474: step: 2124/531, loss: 0.009617852978408337
==================================================
Loss: 0.042
--------------------
Dev: {'event': {'p': 0.5828343313373253, 'r': 0.7776298268974701, 'f1': 0.6662863662293211}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6200832947709394, 'r': 0.7990459153249851, 'f1': 0.6982803543512246}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
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': 19}
Korean: {'event': {'p': 0.68, 'r': 0.5396825396825397, 'f1': 0.6017699115044247}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.40476190476190477, 'r': 0.4722222222222222, 'f1': 0.4358974358974359}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:00:56.819386: step: 4/531, loss: 0.0042684078216552734
2023-01-21 12:00:57.944407: step: 8/531, loss: 0.00369839696213603
2023-01-21 12:00:59.077780: step: 12/531, loss: 0.005042648408561945
2023-01-21 12:01:00.213575: step: 16/531, loss: 0.0013494491577148438
2023-01-21 12:01:01.322617: step: 20/531, loss: 0.012805701233446598
2023-01-21 12:01:02.463558: step: 24/531, loss: 0.3416140079498291
2023-01-21 12:01:03.548421: step: 28/531, loss: 0.0012895584804937243
2023-01-21 12:01:04.665792: step: 32/531, loss: 0.012044906616210938
2023-01-21 12:01:05.767855: step: 36/531, loss: 0.0002877235529012978
2023-01-21 12:01:06.884857: step: 40/531, loss: 0.0004231453058309853
2023-01-21 12:01:08.004859: step: 44/531, loss: 0.0647466629743576
2023-01-21 12:01:09.144844: step: 48/531, loss: 0.029975654557347298
2023-01-21 12:01:10.285751: step: 52/531, loss: 0.0002577781560830772
2023-01-21 12:01:11.421251: step: 56/531, loss: 0.010384988971054554
2023-01-21 12:01:12.552802: step: 60/531, loss: 0.003957128617912531
2023-01-21 12:01:13.671549: step: 64/531, loss: 0.0008245467906817794
2023-01-21 12:01:14.803109: step: 68/531, loss: 0.0007278442499227822
2023-01-21 12:01:15.937031: step: 72/531, loss: 0.019107341766357422
2023-01-21 12:01:17.090577: step: 76/531, loss: 0.008124161511659622
2023-01-21 12:01:18.195227: step: 80/531, loss: 0.005074691958725452
2023-01-21 12:01:19.303897: step: 84/531, loss: 0.0038271904923021793
2023-01-21 12:01:20.405317: step: 88/531, loss: 0.0018447876209393144
2023-01-21 12:01:21.559721: step: 92/531, loss: 0.004069709684699774
2023-01-21 12:01:22.683392: step: 96/531, loss: 0.009900283999741077
2023-01-21 12:01:23.807592: step: 100/531, loss: 0.009450817480683327
2023-01-21 12:01:24.950284: step: 104/531, loss: 0.023413658142089844
2023-01-21 12:01:26.093355: step: 108/531, loss: 0.01458053570240736
2023-01-21 12:01:27.213400: step: 112/531, loss: 0.001660156180150807
2023-01-21 12:01:28.327326: step: 116/531, loss: 0.06835594028234482
2023-01-21 12:01:29.451971: step: 120/531, loss: 0.0029195547103881836
2023-01-21 12:01:30.601864: step: 124/531, loss: 0.020675089210271835
2023-01-21 12:01:31.744601: step: 128/531, loss: 0.0027666091918945312
2023-01-21 12:01:32.868720: step: 132/531, loss: 0.00020875930204056203
2023-01-21 12:01:33.977241: step: 136/531, loss: 0.0036311151925474405
2023-01-21 12:01:35.128757: step: 140/531, loss: 0.0023852349258959293
2023-01-21 12:01:36.255848: step: 144/531, loss: 0.0293103214353323
2023-01-21 12:01:37.373295: step: 148/531, loss: 0.014716720208525658
2023-01-21 12:01:38.532638: step: 152/531, loss: 2.727508581301663e-05
2023-01-21 12:01:39.627443: step: 156/531, loss: 0.001646280288696289
2023-01-21 12:01:40.745616: step: 160/531, loss: 0.00989227369427681
2023-01-21 12:01:41.926429: step: 164/531, loss: 3.228187779313885e-05
2023-01-21 12:01:43.071859: step: 168/531, loss: 0.013320541009306908
2023-01-21 12:01:44.189551: step: 172/531, loss: 0.019048595800995827
2023-01-21 12:01:45.310694: step: 176/531, loss: 0.0021677017211914062
2023-01-21 12:01:46.437522: step: 180/531, loss: 0.011674595065414906
2023-01-21 12:01:47.552028: step: 184/531, loss: 0.014705467969179153
2023-01-21 12:01:48.694707: step: 188/531, loss: 0.04396438971161842
2023-01-21 12:01:49.850723: step: 192/531, loss: 0.017233848571777344
2023-01-21 12:01:50.978478: step: 196/531, loss: 0.00020437240891624242
2023-01-21 12:01:52.101353: step: 200/531, loss: 0.006771183107048273
2023-01-21 12:01:53.231861: step: 204/531, loss: 0.030660247430205345
2023-01-21 12:01:54.338198: step: 208/531, loss: 0.039941027760505676
2023-01-21 12:01:55.449227: step: 212/531, loss: 0.017331313341856003
2023-01-21 12:01:56.578662: step: 216/531, loss: 0.0004978657234460115
2023-01-21 12:01:57.682074: step: 220/531, loss: 0.02194214053452015
2023-01-21 12:01:58.800117: step: 224/531, loss: 0.0006645202520303428
2023-01-21 12:01:59.956014: step: 228/531, loss: 0.0003487587091512978
2023-01-21 12:02:01.081692: step: 232/531, loss: 0.00278053293004632
2023-01-21 12:02:02.210298: step: 236/531, loss: 0.004224204923957586
2023-01-21 12:02:03.336557: step: 240/531, loss: 0.011733436957001686
2023-01-21 12:02:04.469330: step: 244/531, loss: 0.004566955845803022
2023-01-21 12:02:05.578020: step: 248/531, loss: 0.004250908270478249
2023-01-21 12:02:06.733651: step: 252/531, loss: 0.05702371522784233
2023-01-21 12:02:07.913953: step: 256/531, loss: 0.020575236529111862
2023-01-21 12:02:09.031301: step: 260/531, loss: 5.3596493671648204e-05
2023-01-21 12:02:10.179576: step: 264/531, loss: 0.03170504420995712
2023-01-21 12:02:11.308119: step: 268/531, loss: 0.0038485052064061165
2023-01-21 12:02:12.446756: step: 272/531, loss: 0.0015896796248853207
2023-01-21 12:02:13.546168: step: 276/531, loss: 9.32693510549143e-05
2023-01-21 12:02:14.694066: step: 280/531, loss: 0.020946789532899857
2023-01-21 12:02:15.844816: step: 284/531, loss: 0.006133079994469881
2023-01-21 12:02:16.974843: step: 288/531, loss: 0.00022163391986396164
2023-01-21 12:02:18.084108: step: 292/531, loss: 0.006408786866813898
2023-01-21 12:02:19.176481: step: 296/531, loss: 0.0061737061478197575
2023-01-21 12:02:20.332553: step: 300/531, loss: 0.012976265512406826
2023-01-21 12:02:21.486811: step: 304/531, loss: 0.007125473581254482
2023-01-21 12:02:22.621499: step: 308/531, loss: 0.0043090819381177425
2023-01-21 12:02:23.747513: step: 312/531, loss: 0.0018391608027741313
2023-01-21 12:02:24.894186: step: 316/531, loss: 0.03563044220209122
2023-01-21 12:02:26.024927: step: 320/531, loss: 0.012878989800810814
2023-01-21 12:02:27.167989: step: 324/531, loss: 0.0625690445303917
2023-01-21 12:02:28.295907: step: 328/531, loss: 0.012818765826523304
2023-01-21 12:02:29.438913: step: 332/531, loss: 0.00028896331787109375
2023-01-21 12:02:30.560532: step: 336/531, loss: 0.013665581122040749
2023-01-21 12:02:31.653708: step: 340/531, loss: 0.0013178824447095394
2023-01-21 12:02:32.769908: step: 344/531, loss: 0.05526390299201012
2023-01-21 12:02:33.897423: step: 348/531, loss: 0.1336648017168045
2023-01-21 12:02:35.043946: step: 352/531, loss: 0.02966899797320366
2023-01-21 12:02:36.196967: step: 356/531, loss: 0.01762561686336994
2023-01-21 12:02:37.325597: step: 360/531, loss: 3.24249276673072e-06
2023-01-21 12:02:38.472548: step: 364/531, loss: 0.03783607482910156
2023-01-21 12:02:39.583615: step: 368/531, loss: 0.0004861831839662045
2023-01-21 12:02:40.690668: step: 372/531, loss: 0.021983718499541283
2023-01-21 12:02:41.819357: step: 376/531, loss: 0.00438003521412611
2023-01-21 12:02:42.950782: step: 380/531, loss: 0.026051903143525124
2023-01-21 12:02:44.060973: step: 384/531, loss: 0.0002876281796488911
2023-01-21 12:02:45.171204: step: 388/531, loss: 3.805160304182209e-05
2023-01-21 12:02:46.276434: step: 392/531, loss: 0.0014912605984136462
2023-01-21 12:02:47.366447: step: 396/531, loss: 0.02807464636862278
2023-01-21 12:02:48.506120: step: 400/531, loss: 4.684925079345703e-05
2023-01-21 12:02:49.695960: step: 404/531, loss: -9.15527380129788e-06
2023-01-21 12:02:50.820154: step: 408/531, loss: 0.0007923126104287803
2023-01-21 12:02:51.976796: step: 412/531, loss: 0.06204424053430557
2023-01-21 12:02:53.084961: step: 416/531, loss: 0.03123779408633709
2023-01-21 12:02:54.195289: step: 420/531, loss: 0.03875160217285156
2023-01-21 12:02:55.329028: step: 424/531, loss: 0.022251605987548828
2023-01-21 12:02:56.465349: step: 428/531, loss: 0.0013034821022301912
2023-01-21 12:02:57.612566: step: 432/531, loss: 0.022576000541448593
2023-01-21 12:02:58.708449: step: 436/531, loss: 0.06838814914226532
2023-01-21 12:02:59.870178: step: 440/531, loss: 0.007851028814911842
2023-01-21 12:03:01.011359: step: 444/531, loss: 0.03305073082447052
2023-01-21 12:03:02.173077: step: 448/531, loss: 3.662109520519152e-05
2023-01-21 12:03:03.309139: step: 452/531, loss: 0.023189593106508255
2023-01-21 12:03:04.488612: step: 456/531, loss: 7.314681715797633e-05
2023-01-21 12:03:05.613651: step: 460/531, loss: 0.012070274911820889
2023-01-21 12:03:06.703715: step: 464/531, loss: 0.161982923746109
2023-01-21 12:03:07.834110: step: 468/531, loss: 0.01486282330006361
2023-01-21 12:03:08.965957: step: 472/531, loss: 0.04620418697595596
2023-01-21 12:03:10.122678: step: 476/531, loss: 0.034688565880060196
2023-01-21 12:03:11.288950: step: 480/531, loss: 0.00039467812166549265
2023-01-21 12:03:12.396127: step: 484/531, loss: 0.01094350777566433
2023-01-21 12:03:13.536979: step: 488/531, loss: 0.00190229422878474
2023-01-21 12:03:14.642611: step: 492/531, loss: 0.0003351211780682206
2023-01-21 12:03:15.767534: step: 496/531, loss: 0.00015544891357421875
2023-01-21 12:03:16.876486: step: 500/531, loss: 0.017740439623594284
2023-01-21 12:03:18.022090: step: 504/531, loss: 0.008106040768325329
2023-01-21 12:03:19.122608: step: 508/531, loss: 0.002338457154110074
2023-01-21 12:03:20.225771: step: 512/531, loss: 0.0009860038990154862
2023-01-21 12:03:21.357741: step: 516/531, loss: 0.004951191134750843
2023-01-21 12:03:22.470085: step: 520/531, loss: 0.004124474711716175
2023-01-21 12:03:23.611994: step: 524/531, loss: 0.005018138792365789
2023-01-21 12:03:24.726513: step: 528/531, loss: 0.030269861221313477
2023-01-21 12:03:25.829566: step: 532/531, loss: 0.0020617484115064144
2023-01-21 12:03:26.945811: step: 536/531, loss: 0.020287513732910156
2023-01-21 12:03:28.057582: step: 540/531, loss: 0.0015100956661626697
2023-01-21 12:03:29.202675: step: 544/531, loss: 0.010562137700617313
2023-01-21 12:03:30.382831: step: 548/531, loss: 0.022211646661162376
2023-01-21 12:03:31.504935: step: 552/531, loss: 0.02851085737347603
2023-01-21 12:03:32.652079: step: 556/531, loss: 0.013420294970273972
2023-01-21 12:03:33.775691: step: 560/531, loss: 0.007181072607636452
2023-01-21 12:03:34.913642: step: 564/531, loss: 0.0031265737488865852
2023-01-21 12:03:36.009413: step: 568/531, loss: 0.0005976438988000154
2023-01-21 12:03:37.124495: step: 572/531, loss: 0.029396438971161842
2023-01-21 12:03:38.235266: step: 576/531, loss: 0.017939282581210136
2023-01-21 12:03:39.395754: step: 580/531, loss: 0.0003444671747274697
2023-01-21 12:03:40.502164: step: 584/531, loss: 0.0017328262329101562
2023-01-21 12:03:41.613641: step: 588/531, loss: 0.03702230378985405
2023-01-21 12:03:42.750873: step: 592/531, loss: 0.03456936031579971
2023-01-21 12:03:43.874924: step: 596/531, loss: 7.944107346702367e-05
2023-01-21 12:03:44.992538: step: 600/531, loss: 2.0408631826285273e-05
2023-01-21 12:03:46.108977: step: 604/531, loss: 0.0016758800484240055
2023-01-21 12:03:47.221712: step: 608/531, loss: 7.820128666935489e-05
2023-01-21 12:03:48.339214: step: 612/531, loss: 0.7401914596557617
2023-01-21 12:03:49.440377: step: 616/531, loss: 1.3780593690171372e-05
2023-01-21 12:03:50.576518: step: 620/531, loss: 0.05583017319440842
2023-01-21 12:03:51.713144: step: 624/531, loss: 0.05132894963026047
2023-01-21 12:03:52.841118: step: 628/531, loss: 0.02747788466513157
2023-01-21 12:03:53.960370: step: 632/531, loss: 0.008495330810546875
2023-01-21 12:03:55.084535: step: 636/531, loss: 0.014155673794448376
2023-01-21 12:03:56.222935: step: 640/531, loss: 0.01801624335348606
2023-01-21 12:03:57.332904: step: 644/531, loss: 0.009556293487548828
2023-01-21 12:03:58.435613: step: 648/531, loss: 0.005221748258918524
2023-01-21 12:03:59.571067: step: 652/531, loss: 0.0032155036460608244
2023-01-21 12:04:00.673305: step: 656/531, loss: 0.0009287834400311112
2023-01-21 12:04:01.784824: step: 660/531, loss: 0.0001548767031636089
2023-01-21 12:04:02.906222: step: 664/531, loss: 0.14776574075222015
2023-01-21 12:04:04.062183: step: 668/531, loss: 0.009481430053710938
2023-01-21 12:04:05.179558: step: 672/531, loss: 0.0005083084106445312
2023-01-21 12:04:06.321463: step: 676/531, loss: 0.01818552054464817
2023-01-21 12:04:07.454793: step: 680/531, loss: 0.013166999444365501
2023-01-21 12:04:08.576100: step: 684/531, loss: 0.004916286561638117
2023-01-21 12:04:09.718596: step: 688/531, loss: 0.11361849308013916
2023-01-21 12:04:10.828043: step: 692/531, loss: 0.009963035583496094
2023-01-21 12:04:11.959201: step: 696/531, loss: 0.010951138101518154
2023-01-21 12:04:13.078192: step: 700/531, loss: 0.009215355850756168
2023-01-21 12:04:14.220884: step: 704/531, loss: 0.013612176291644573
2023-01-21 12:04:15.355514: step: 708/531, loss: 0.037805747240781784
2023-01-21 12:04:16.487550: step: 712/531, loss: 0.00729260453954339
2023-01-21 12:04:17.631544: step: 716/531, loss: 0.0005199909210205078
2023-01-21 12:04:18.785291: step: 720/531, loss: 0.04019484296441078
2023-01-21 12:04:19.906018: step: 724/531, loss: 0.0002541542053222656
2023-01-21 12:04:21.024000: step: 728/531, loss: 0.05018596723675728
2023-01-21 12:04:22.146211: step: 732/531, loss: 0.006511020474135876
2023-01-21 12:04:23.275003: step: 736/531, loss: 0.02578449249267578
2023-01-21 12:04:24.387730: step: 740/531, loss: 0.002951240399852395
2023-01-21 12:04:25.521745: step: 744/531, loss: 0.0661001205444336
2023-01-21 12:04:26.638323: step: 748/531, loss: 0.00022172929311636835
2023-01-21 12:04:27.779971: step: 752/531, loss: 0.01023883931338787
2023-01-21 12:04:28.920040: step: 756/531, loss: 0.010994339361786842
2023-01-21 12:04:30.044627: step: 760/531, loss: 0.08174996823072433
2023-01-21 12:04:31.191042: step: 764/531, loss: 0.0003194332239218056
2023-01-21 12:04:32.333678: step: 768/531, loss: 0.0016126633854582906
2023-01-21 12:04:33.471354: step: 772/531, loss: 0.0016916274325922132
2023-01-21 12:04:34.602329: step: 776/531, loss: 0.04539242014288902
2023-01-21 12:04:35.736755: step: 780/531, loss: 0.064208984375
2023-01-21 12:04:36.911291: step: 784/531, loss: 0.012694835662841797
2023-01-21 12:04:38.040493: step: 788/531, loss: 0.027092458680272102
2023-01-21 12:04:39.159931: step: 792/531, loss: 9.694100299384445e-05
2023-01-21 12:04:40.278925: step: 796/531, loss: 0.017609262838959694
2023-01-21 12:04:41.400147: step: 800/531, loss: 0.03239727020263672
2023-01-21 12:04:42.505878: step: 804/531, loss: 0.05240011215209961
2023-01-21 12:04:43.639142: step: 808/531, loss: 0.0032236098777502775
2023-01-21 12:04:44.725381: step: 812/531, loss: 0.004499530885368586
2023-01-21 12:04:45.834044: step: 816/531, loss: 0.07213011384010315
2023-01-21 12:04:46.936069: step: 820/531, loss: 4.110336521989666e-05
2023-01-21 12:04:48.045187: step: 824/531, loss: 0.10355091094970703
2023-01-21 12:04:49.144215: step: 828/531, loss: 0.028632069006562233
2023-01-21 12:04:50.283537: step: 832/531, loss: 0.0016375542618334293
2023-01-21 12:04:51.389730: step: 836/531, loss: 0.011282539926469326
2023-01-21 12:04:52.520616: step: 840/531, loss: 0.01265411451458931
2023-01-21 12:04:53.667552: step: 844/531, loss: 0.0001771926908986643
2023-01-21 12:04:54.791899: step: 848/531, loss: 0.0029514310881495476
2023-01-21 12:04:55.942036: step: 852/531, loss: 0.0058231353759765625
2023-01-21 12:04:57.059020: step: 856/531, loss: 0.045072462409734726
2023-01-21 12:04:58.167440: step: 860/531, loss: 0.0525270476937294
2023-01-21 12:04:59.280675: step: 864/531, loss: 0.053490832448005676
2023-01-21 12:05:00.396416: step: 868/531, loss: 0.024404335767030716
2023-01-21 12:05:01.522577: step: 872/531, loss: 0.01981201209127903
2023-01-21 12:05:02.647146: step: 876/531, loss: 7.743835885776207e-05
2023-01-21 12:05:03.802311: step: 880/531, loss: 0.022589493542909622
2023-01-21 12:05:04.947682: step: 884/531, loss: 0.02989177778363228
2023-01-21 12:05:06.057815: step: 888/531, loss: 0.009578084573149681
2023-01-21 12:05:07.177400: step: 892/531, loss: 0.0008292675483971834
2023-01-21 12:05:08.316495: step: 896/531, loss: 0.00026760101900435984
2023-01-21 12:05:09.451390: step: 900/531, loss: 0.00034728049649856985
2023-01-21 12:05:10.572810: step: 904/531, loss: 0.03461713716387749
2023-01-21 12:05:11.681926: step: 908/531, loss: 0.03369007259607315
2023-01-21 12:05:12.822509: step: 912/531, loss: 0.009516382589936256
2023-01-21 12:05:13.964631: step: 916/531, loss: 8.916855222196318e-06
2023-01-21 12:05:15.095059: step: 920/531, loss: 3.2234194804914296e-05
2023-01-21 12:05:16.204806: step: 924/531, loss: 0.0039116861298680305
2023-01-21 12:05:17.351481: step: 928/531, loss: 0.0034274100326001644
2023-01-21 12:05:18.495367: step: 932/531, loss: 0.025771331042051315
2023-01-21 12:05:19.631963: step: 936/531, loss: 6.332397606456652e-05
2023-01-21 12:05:20.761173: step: 940/531, loss: 0.03230180963873863
2023-01-21 12:05:21.907045: step: 944/531, loss: 0.04185495525598526
2023-01-21 12:05:23.020045: step: 948/531, loss: 0.0006002665031701326
2023-01-21 12:05:24.170195: step: 952/531, loss: 0.0015363693237304688
2023-01-21 12:05:25.321269: step: 956/531, loss: 0.001834869384765625
2023-01-21 12:05:26.454288: step: 960/531, loss: 0.0002623796754051
2023-01-21 12:05:27.596420: step: 964/531, loss: 0.004636573605239391
2023-01-21 12:05:28.713891: step: 968/531, loss: 0.005076503846794367
2023-01-21 12:05:29.845340: step: 972/531, loss: 0.0037137032486498356
2023-01-21 12:05:30.983048: step: 976/531, loss: 0.001048183417879045
2023-01-21 12:05:32.137734: step: 980/531, loss: 0.284993439912796
2023-01-21 12:05:33.274754: step: 984/531, loss: 0.05883808434009552
2023-01-21 12:05:34.401553: step: 988/531, loss: 0.05026283115148544
2023-01-21 12:05:35.547131: step: 992/531, loss: 7.514953904319555e-05
2023-01-21 12:05:36.683004: step: 996/531, loss: 0.0011873244075104594
2023-01-21 12:05:37.786241: step: 1000/531, loss: 0.0012302398681640625
2023-01-21 12:05:38.930930: step: 1004/531, loss: 0.04406299814581871
2023-01-21 12:05:40.034798: step: 1008/531, loss: 7.05719003235572e-06
2023-01-21 12:05:41.149999: step: 1012/531, loss: 0.0010879517067223787
2023-01-21 12:05:42.283251: step: 1016/531, loss: 0.04696397855877876
2023-01-21 12:05:43.440737: step: 1020/531, loss: 0.05769595876336098
2023-01-21 12:05:44.568807: step: 1024/531, loss: 0.011763953603804111
2023-01-21 12:05:45.736590: step: 1028/531, loss: 0.08096809685230255
2023-01-21 12:05:46.864759: step: 1032/531, loss: 0.0016600609524175525
2023-01-21 12:05:47.980295: step: 1036/531, loss: 0.0026065825950354338
2023-01-21 12:05:49.101474: step: 1040/531, loss: 0.044809531420469284
2023-01-21 12:05:50.203010: step: 1044/531, loss: -5.14984139954322e-06
2023-01-21 12:05:51.321021: step: 1048/531, loss: 0.01935424841940403
2023-01-21 12:05:52.454722: step: 1052/531, loss: 0.008493566885590553
2023-01-21 12:05:53.583884: step: 1056/531, loss: 0.027629852294921875
2023-01-21 12:05:54.702732: step: 1060/531, loss: 0.04375104978680611
2023-01-21 12:05:55.825757: step: 1064/531, loss: 0.05173168331384659
2023-01-21 12:05:56.932000: step: 1068/531, loss: 0.007929420098662376
2023-01-21 12:05:58.057769: step: 1072/531, loss: 0.005633068270981312
2023-01-21 12:05:59.164459: step: 1076/531, loss: 0.0002724170626606792
2023-01-21 12:06:00.283401: step: 1080/531, loss: 0.025803662836551666
2023-01-21 12:06:01.395548: step: 1084/531, loss: 0.02024364471435547
2023-01-21 12:06:02.517856: step: 1088/531, loss: 0.015231132507324219
2023-01-21 12:06:03.634715: step: 1092/531, loss: 0.0738285630941391
2023-01-21 12:06:04.747499: step: 1096/531, loss: 0.008661603555083275
2023-01-21 12:06:05.881500: step: 1100/531, loss: 0.04922294616699219
2023-01-21 12:06:07.014650: step: 1104/531, loss: 0.16663475334644318
2023-01-21 12:06:08.131778: step: 1108/531, loss: 0.023339366540312767
2023-01-21 12:06:09.256274: step: 1112/531, loss: 0.00014371871657203883
2023-01-21 12:06:10.420660: step: 1116/531, loss: 0.010211181826889515
2023-01-21 12:06:11.563454: step: 1120/531, loss: 0.005398273468017578
2023-01-21 12:06:12.702319: step: 1124/531, loss: 0.03627920150756836
2023-01-21 12:06:13.814806: step: 1128/531, loss: 0.0025251389015465975
2023-01-21 12:06:14.951336: step: 1132/531, loss: 0.05681133642792702
2023-01-21 12:06:16.064993: step: 1136/531, loss: 0.0036290884017944336
2023-01-21 12:06:17.164835: step: 1140/531, loss: 0.000954055751208216
2023-01-21 12:06:18.242081: step: 1144/531, loss: 0.0013440132606774569
2023-01-21 12:06:19.359503: step: 1148/531, loss: 0.09740272164344788
2023-01-21 12:06:20.481072: step: 1152/531, loss: 0.009726906195282936
2023-01-21 12:06:21.583180: step: 1156/531, loss: 0.01283731497824192
2023-01-21 12:06:22.741289: step: 1160/531, loss: 0.18539848923683167
2023-01-21 12:06:23.885094: step: 1164/531, loss: 0.0008284568903036416
2023-01-21 12:06:25.008442: step: 1168/531, loss: 0.03062448464334011
2023-01-21 12:06:26.134804: step: 1172/531, loss: 0.03205757215619087
2023-01-21 12:06:27.273095: step: 1176/531, loss: 0.0003143310605082661
2023-01-21 12:06:28.386459: step: 1180/531, loss: 0.001223659492097795
2023-01-21 12:06:29.509826: step: 1184/531, loss: 0.0013794898986816406
2023-01-21 12:06:30.629505: step: 1188/531, loss: 0.0566675178706646
2023-01-21 12:06:31.753561: step: 1192/531, loss: 0.005577277857810259
2023-01-21 12:06:32.899498: step: 1196/531, loss: 0.00086383824236691
2023-01-21 12:06:34.011207: step: 1200/531, loss: 0.0007397652370855212
2023-01-21 12:06:35.150717: step: 1204/531, loss: 0.013715553097426891
2023-01-21 12:06:36.285990: step: 1208/531, loss: 0.0007748603820800781
2023-01-21 12:06:37.385956: step: 1212/531, loss: 0.0014644861221313477
2023-01-21 12:06:38.499418: step: 1216/531, loss: 0.0001615524379303679
2023-01-21 12:06:39.629531: step: 1220/531, loss: 0.004193687811493874
2023-01-21 12:06:40.748633: step: 1224/531, loss: 0.027457524091005325
2023-01-21 12:06:41.894593: step: 1228/531, loss: 0.05862589180469513
2023-01-21 12:06:42.997394: step: 1232/531, loss: 0.00013465881056617945
2023-01-21 12:06:44.149749: step: 1236/531, loss: 0.009566117078065872
2023-01-21 12:06:45.312352: step: 1240/531, loss: 0.008403015322983265
2023-01-21 12:06:46.445966: step: 1244/531, loss: 0.12102308869361877
2023-01-21 12:06:47.561203: step: 1248/531, loss: 0.011609697714447975
2023-01-21 12:06:48.659813: step: 1252/531, loss: 0.00329170236364007
2023-01-21 12:06:49.795071: step: 1256/531, loss: 0.00012073516700183973
2023-01-21 12:06:50.956320: step: 1260/531, loss: 0.01811056211590767
2023-01-21 12:06:52.077152: step: 1264/531, loss: 0.0027015686500817537
2023-01-21 12:06:53.178006: step: 1268/531, loss: 0.030917834490537643
2023-01-21 12:06:54.346597: step: 1272/531, loss: 0.06088867038488388
2023-01-21 12:06:55.471812: step: 1276/531, loss: 0.004056167788803577
2023-01-21 12:06:56.609661: step: 1280/531, loss: 6.256103370105848e-05
2023-01-21 12:06:57.748903: step: 1284/531, loss: 0.00182933802716434
2023-01-21 12:06:58.869216: step: 1288/531, loss: 0.022030258551239967
2023-01-21 12:07:00.007736: step: 1292/531, loss: 0.01325597707182169
2023-01-21 12:07:01.120507: step: 1296/531, loss: 0.0031570433638989925
2023-01-21 12:07:02.236862: step: 1300/531, loss: 0.019679641351103783
2023-01-21 12:07:03.361382: step: 1304/531, loss: 0.019195174798369408
2023-01-21 12:07:04.463773: step: 1308/531, loss: 0.019798660650849342
2023-01-21 12:07:05.606950: step: 1312/531, loss: 0.06110658869147301
2023-01-21 12:07:06.740335: step: 1316/531, loss: 1.4257430848374497e-05
2023-01-21 12:07:07.849021: step: 1320/531, loss: 0.01452417392283678
2023-01-21 12:07:08.967488: step: 1324/531, loss: 0.0004093170282430947
2023-01-21 12:07:10.090646: step: 1328/531, loss: 0.0006435394170694053
2023-01-21 12:07:11.215872: step: 1332/531, loss: 0.002630615374073386
2023-01-21 12:07:12.387025: step: 1336/531, loss: 0.012231254950165749
2023-01-21 12:07:13.490588: step: 1340/531, loss: 0.009826661087572575
2023-01-21 12:07:14.597953: step: 1344/531, loss: 0.007898139767348766
2023-01-21 12:07:15.732045: step: 1348/531, loss: 0.0005296707386150956
2023-01-21 12:07:16.849265: step: 1352/531, loss: 0.0034811021760106087
2023-01-21 12:07:17.995313: step: 1356/531, loss: 0.00015001297288108617
2023-01-21 12:07:19.126157: step: 1360/531, loss: 5.035400317865424e-05
2023-01-21 12:07:20.273685: step: 1364/531, loss: 0.08050546795129776
2023-01-21 12:07:21.408473: step: 1368/531, loss: 0.00036306382389739156
2023-01-21 12:07:22.510870: step: 1372/531, loss: 0.007416200824081898
2023-01-21 12:07:23.632887: step: 1376/531, loss: 0.00243301410228014
2023-01-21 12:07:24.758927: step: 1380/531, loss: 0.0012866974575445056
2023-01-21 12:07:25.872384: step: 1384/531, loss: 0.005496311001479626
2023-01-21 12:07:27.005861: step: 1388/531, loss: 0.012728882022202015
2023-01-21 12:07:28.160775: step: 1392/531, loss: 0.008410453796386719
2023-01-21 12:07:29.271214: step: 1396/531, loss: 0.0006304740672931075
2023-01-21 12:07:30.352477: step: 1400/531, loss: 0.0028811455704271793
2023-01-21 12:07:31.464068: step: 1404/531, loss: 0.032659340649843216
2023-01-21 12:07:32.582378: step: 1408/531, loss: 6.4849853515625e-05
2023-01-21 12:07:33.712960: step: 1412/531, loss: 0.0002590179501567036
2023-01-21 12:07:34.832328: step: 1416/531, loss: 0.0003361702256370336
2023-01-21 12:07:35.927287: step: 1420/531, loss: 0.0027702334336936474
2023-01-21 12:07:37.072399: step: 1424/531, loss: 0.00035161973210051656
2023-01-21 12:07:38.237359: step: 1428/531, loss: 0.03153223916888237
2023-01-21 12:07:39.361160: step: 1432/531, loss: 0.1308523267507553
2023-01-21 12:07:40.465866: step: 1436/531, loss: 8.535385131835938e-05
2023-01-21 12:07:41.586993: step: 1440/531, loss: 0.002167320344597101
2023-01-21 12:07:42.717688: step: 1444/531, loss: 0.05468940734863281
2023-01-21 12:07:43.870926: step: 1448/531, loss: 0.0017781734932214022
2023-01-21 12:07:45.023737: step: 1452/531, loss: 0.00983057077974081
2023-01-21 12:07:46.136315: step: 1456/531, loss: 0.0014261245960369706
2023-01-21 12:07:47.346903: step: 1460/531, loss: 0.020213890820741653
2023-01-21 12:07:48.451456: step: 1464/531, loss: 0.0014238357543945312
2023-01-21 12:07:49.599011: step: 1468/531, loss: 0.0012582779163494706
2023-01-21 12:07:50.750620: step: 1472/531, loss: 0.06024932861328125
2023-01-21 12:07:51.903987: step: 1476/531, loss: 0.0026653290260583162
2023-01-21 12:07:53.034223: step: 1480/531, loss: 0.0003662109375
2023-01-21 12:07:54.171894: step: 1484/531, loss: 0.019578194245696068
2023-01-21 12:07:55.311168: step: 1488/531, loss: 0.7144562602043152
2023-01-21 12:07:56.426462: step: 1492/531, loss: 0.022637223824858665
2023-01-21 12:07:57.537965: step: 1496/531, loss: 0.0021830559708178043
2023-01-21 12:07:58.647570: step: 1500/531, loss: 0.06123180687427521
2023-01-21 12:07:59.782724: step: 1504/531, loss: 0.13065338134765625
2023-01-21 12:08:00.913635: step: 1508/531, loss: 0.009461641311645508
2023-01-21 12:08:02.051763: step: 1512/531, loss: 0.0020399093627929688
2023-01-21 12:08:03.167302: step: 1516/531, loss: 2.6512147087487392e-05
2023-01-21 12:08:04.330432: step: 1520/531, loss: 0.004387474153190851
2023-01-21 12:08:05.454684: step: 1524/531, loss: 8.02040085545741e-05
2023-01-21 12:08:06.585730: step: 1528/531, loss: 0.0429140105843544
2023-01-21 12:08:07.716776: step: 1532/531, loss: 0.026005173102021217
2023-01-21 12:08:08.854931: step: 1536/531, loss: 0.00029506682767532766
2023-01-21 12:08:10.017556: step: 1540/531, loss: 0.003241634229198098
2023-01-21 12:08:11.139803: step: 1544/531, loss: 0.013512182049453259
2023-01-21 12:08:12.275718: step: 1548/531, loss: 0.011196708306670189
2023-01-21 12:08:13.417584: step: 1552/531, loss: 0.03624091297388077
2023-01-21 12:08:14.557299: step: 1556/531, loss: 0.005675077438354492
2023-01-21 12:08:15.700210: step: 1560/531, loss: 0.389894962310791
2023-01-21 12:08:16.817966: step: 1564/531, loss: 0.05377388000488281
2023-01-21 12:08:17.945952: step: 1568/531, loss: 4.692077709478326e-05
2023-01-21 12:08:19.069172: step: 1572/531, loss: 0.005256080999970436
2023-01-21 12:08:20.244368: step: 1576/531, loss: 0.06646442413330078
2023-01-21 12:08:21.417626: step: 1580/531, loss: 0.025849809870123863
2023-01-21 12:08:22.572259: step: 1584/531, loss: 0.002214813372120261
2023-01-21 12:08:23.716512: step: 1588/531, loss: 0.010465431958436966
2023-01-21 12:08:24.833063: step: 1592/531, loss: 0.001987457275390625
2023-01-21 12:08:25.957736: step: 1596/531, loss: 0.03647336736321449
2023-01-21 12:08:27.085532: step: 1600/531, loss: 0.03838767856359482
2023-01-21 12:08:28.263591: step: 1604/531, loss: 0.0023769380059093237
2023-01-21 12:08:29.381665: step: 1608/531, loss: 0.0491090752184391
2023-01-21 12:08:30.490537: step: 1612/531, loss: 0.004688739776611328
2023-01-21 12:08:31.602973: step: 1616/531, loss: 0.02584237977862358
2023-01-21 12:08:32.705802: step: 1620/531, loss: 0.003821754362434149
2023-01-21 12:08:33.838846: step: 1624/531, loss: 0.0035602569114416838
2023-01-21 12:08:34.971412: step: 1628/531, loss: 0.02424316480755806
2023-01-21 12:08:36.059663: step: 1632/531, loss: 0.0003437995910644531
2023-01-21 12:08:37.186176: step: 1636/531, loss: 0.00293045025318861
2023-01-21 12:08:38.299098: step: 1640/531, loss: 0.009319783188402653
2023-01-21 12:08:39.441567: step: 1644/531, loss: 0.0001636505185160786
2023-01-21 12:08:40.590447: step: 1648/531, loss: 0.0028985023964196444
2023-01-21 12:08:41.711687: step: 1652/531, loss: 0.006133651826530695
2023-01-21 12:08:42.879353: step: 1656/531, loss: 0.07312975078821182
2023-01-21 12:08:44.013023: step: 1660/531, loss: 0.0003799438418354839
2023-01-21 12:08:45.140774: step: 1664/531, loss: 0.06162299960851669
2023-01-21 12:08:46.293885: step: 1668/531, loss: 0.2518285810947418
2023-01-21 12:08:47.438528: step: 1672/531, loss: 0.019063664600253105
2023-01-21 12:08:48.526884: step: 1676/531, loss: 0.0037837030831724405
2023-01-21 12:08:49.642144: step: 1680/531, loss: 0.006030035205185413
2023-01-21 12:08:50.761455: step: 1684/531, loss: 0.0010579109657555819
2023-01-21 12:08:51.875411: step: 1688/531, loss: 0.0010961532825604081
2023-01-21 12:08:52.996713: step: 1692/531, loss: 0.001509475870989263
2023-01-21 12:08:54.124817: step: 1696/531, loss: 0.0951637253165245
2023-01-21 12:08:55.230084: step: 1700/531, loss: 0.0021266937255859375
2023-01-21 12:08:56.365467: step: 1704/531, loss: 0.05188446119427681
2023-01-21 12:08:57.483956: step: 1708/531, loss: 0.015315246768295765
2023-01-21 12:08:58.618477: step: 1712/531, loss: 0.0017190932994708419
2023-01-21 12:08:59.745412: step: 1716/531, loss: 0.0050140381790697575
2023-01-21 12:09:00.860379: step: 1720/531, loss: 0.010280800983309746
2023-01-21 12:09:01.981633: step: 1724/531, loss: 0.001546669052913785
2023-01-21 12:09:03.083415: step: 1728/531, loss: 0.0005205154302529991
2023-01-21 12:09:04.226644: step: 1732/531, loss: 0.015781210735440254
2023-01-21 12:09:05.401516: step: 1736/531, loss: 0.0031764984596520662
2023-01-21 12:09:06.517162: step: 1740/531, loss: 0.00025262832059524953
2023-01-21 12:09:07.651616: step: 1744/531, loss: 0.0007285118335857987
2023-01-21 12:09:08.777219: step: 1748/531, loss: 0.009483146481215954
2023-01-21 12:09:09.857706: step: 1752/531, loss: 0.02316894568502903
2023-01-21 12:09:10.967170: step: 1756/531, loss: 0.002701664110645652
2023-01-21 12:09:12.108876: step: 1760/531, loss: 0.04713869094848633
2023-01-21 12:09:13.237097: step: 1764/531, loss: 0.02914752997457981
2023-01-21 12:09:14.355673: step: 1768/531, loss: 0.02108459547162056
2023-01-21 12:09:15.498157: step: 1772/531, loss: 0.009310532361268997
2023-01-21 12:09:16.640757: step: 1776/531, loss: 8.449554297840223e-05
2023-01-21 12:09:17.760553: step: 1780/531, loss: 0.014852524735033512
2023-01-21 12:09:18.868517: step: 1784/531, loss: 0.00016794205293990672
2023-01-21 12:09:19.981043: step: 1788/531, loss: 0.0005270958063192666
2023-01-21 12:09:21.094656: step: 1792/531, loss: 0.025333786383271217
2023-01-21 12:09:22.234821: step: 1796/531, loss: 0.004635669756680727
2023-01-21 12:09:23.359784: step: 1800/531, loss: 0.0591367706656456
2023-01-21 12:09:24.489300: step: 1804/531, loss: 0.002317118691280484
2023-01-21 12:09:25.632970: step: 1808/531, loss: 0.03819999843835831
2023-01-21 12:09:26.747903: step: 1812/531, loss: 0.004540347959846258
2023-01-21 12:09:27.874964: step: 1816/531, loss: 0.03649768978357315
2023-01-21 12:09:29.008567: step: 1820/531, loss: 0.0001979827939067036
2023-01-21 12:09:30.131319: step: 1824/531, loss: 0.0007092476007528603
2023-01-21 12:09:31.237982: step: 1828/531, loss: 0.05888576805591583
2023-01-21 12:09:32.387108: step: 1832/531, loss: 0.0001443863002350554
2023-01-21 12:09:33.503308: step: 1836/531, loss: 0.023372652009129524
2023-01-21 12:09:34.629073: step: 1840/531, loss: 0.005185222718864679
2023-01-21 12:09:35.737942: step: 1844/531, loss: 0.0047592162154614925
2023-01-21 12:09:36.872118: step: 1848/531, loss: 0.00039634708082303405
2023-01-21 12:09:37.994307: step: 1852/531, loss: 0.04666700214147568
2023-01-21 12:09:39.108749: step: 1856/531, loss: 0.036513231694698334
2023-01-21 12:09:40.230689: step: 1860/531, loss: 0.0015548706287518144
2023-01-21 12:09:41.352777: step: 1864/531, loss: 0.005625820253044367
2023-01-21 12:09:42.459220: step: 1868/531, loss: 0.0010433197021484375
2023-01-21 12:09:43.547132: step: 1872/531, loss: 0.0011726379161700606
2023-01-21 12:09:44.690038: step: 1876/531, loss: 0.002943325089290738
2023-01-21 12:09:45.809380: step: 1880/531, loss: 0.06522709131240845
2023-01-21 12:09:46.966954: step: 1884/531, loss: 0.01231012400239706
2023-01-21 12:09:48.105241: step: 1888/531, loss: 0.02914581261575222
2023-01-21 12:09:49.214648: step: 1892/531, loss: 0.011760901659727097
2023-01-21 12:09:50.303531: step: 1896/531, loss: 0.017786217853426933
2023-01-21 12:09:51.440121: step: 1900/531, loss: 0.0454469695687294
2023-01-21 12:09:52.560928: step: 1904/531, loss: 0.032624050974845886
2023-01-21 12:09:53.680405: step: 1908/531, loss: 0.0006206512334756553
2023-01-21 12:09:54.781925: step: 1912/531, loss: 1.1730194273695815e-05
2023-01-21 12:09:55.884406: step: 1916/531, loss: 0.002918291138485074
2023-01-21 12:09:56.985198: step: 1920/531, loss: 0.0014688491355627775
2023-01-21 12:09:58.105008: step: 1924/531, loss: 0.0140831945464015
2023-01-21 12:09:59.236060: step: 1928/531, loss: 0.047412872314453125
2023-01-21 12:10:00.379660: step: 1932/531, loss: 0.007380438037216663
2023-01-21 12:10:01.499627: step: 1936/531, loss: 0.1811823844909668
2023-01-21 12:10:02.654458: step: 1940/531, loss: 0.0011631011730059981
2023-01-21 12:10:03.822718: step: 1944/531, loss: 0.004854393191635609
2023-01-21 12:10:04.958370: step: 1948/531, loss: 0.04157309606671333
2023-01-21 12:10:06.095337: step: 1952/531, loss: 0.0320344939827919
2023-01-21 12:10:07.210523: step: 1956/531, loss: 0.00010437965829623863
2023-01-21 12:10:08.328411: step: 1960/531, loss: 0.04512915760278702
2023-01-21 12:10:09.408293: step: 1964/531, loss: 0.0011899947421625257
2023-01-21 12:10:10.543259: step: 1968/531, loss: 9.679794311523438e-05
2023-01-21 12:10:11.671637: step: 1972/531, loss: 0.04750671237707138
2023-01-21 12:10:12.810390: step: 1976/531, loss: 0.010211371816694736
2023-01-21 12:10:13.922596: step: 1980/531, loss: 0.050099946558475494
2023-01-21 12:10:15.053811: step: 1984/531, loss: 0.12275819480419159
2023-01-21 12:10:16.191698: step: 1988/531, loss: 0.005821800325065851
2023-01-21 12:10:17.305508: step: 1992/531, loss: 0.003816795302554965
2023-01-21 12:10:18.427413: step: 1996/531, loss: 0.04299984127283096
2023-01-21 12:10:19.547671: step: 2000/531, loss: 0.012952995486557484
2023-01-21 12:10:20.657725: step: 2004/531, loss: 0.008868217468261719
2023-01-21 12:10:21.836839: step: 2008/531, loss: 0.006070422939956188
2023-01-21 12:10:22.956768: step: 2012/531, loss: 0.02142333984375
2023-01-21 12:10:24.100651: step: 2016/531, loss: 0.04205293580889702
2023-01-21 12:10:25.232592: step: 2020/531, loss: 0.0023247720673680305
2023-01-21 12:10:26.330301: step: 2024/531, loss: 0.0001031875581247732
2023-01-21 12:10:27.467539: step: 2028/531, loss: 0.007774734869599342
2023-01-21 12:10:28.584018: step: 2032/531, loss: 0.023336218670010567
2023-01-21 12:10:29.715186: step: 2036/531, loss: 0.07117538154125214
2023-01-21 12:10:30.841703: step: 2040/531, loss: 9.72747784544481e-06
2023-01-21 12:10:31.998725: step: 2044/531, loss: 0.7680648565292358
2023-01-21 12:10:33.127566: step: 2048/531, loss: 0.01672239415347576
2023-01-21 12:10:34.233946: step: 2052/531, loss: 0.04720611870288849
2023-01-21 12:10:35.362086: step: 2056/531, loss: 0.003008556552231312
2023-01-21 12:10:36.461308: step: 2060/531, loss: 0.002344799228012562
2023-01-21 12:10:37.572025: step: 2064/531, loss: 0.003798294346779585
2023-01-21 12:10:38.682158: step: 2068/531, loss: 0.002208709716796875
2023-01-21 12:10:39.800124: step: 2072/531, loss: 0.0554235465824604
2023-01-21 12:10:40.904858: step: 2076/531, loss: 0.04692363739013672
2023-01-21 12:10:42.033101: step: 2080/531, loss: 0.01076283399015665
2023-01-21 12:10:43.156820: step: 2084/531, loss: 0.007159805856645107
2023-01-21 12:10:44.285910: step: 2088/531, loss: 0.013034534640610218
2023-01-21 12:10:45.404814: step: 2092/531, loss: 0.0003288745938334614
2023-01-21 12:10:46.507473: step: 2096/531, loss: 0.0013932227157056332
2023-01-21 12:10:47.606777: step: 2100/531, loss: 1.9073513612966053e-07
2023-01-21 12:10:48.736675: step: 2104/531, loss: 0.0057579996064305305
2023-01-21 12:10:49.853814: step: 2108/531, loss: 1.640319896978326e-05
2023-01-21 12:10:50.975924: step: 2112/531, loss: 0.04350471496582031
2023-01-21 12:10:52.133705: step: 2116/531, loss: 0.027050448581576347
2023-01-21 12:10:53.254665: step: 2120/531, loss: 0.01781024970114231
2023-01-21 12:10:54.372952: step: 2124/531, loss: 0.0002718210162129253
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.6014492753623188, 'r': 0.7736351531291611, 'f1': 0.6767617938264415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6327710843373494, 'r': 0.7829457364341085, 'f1': 0.6998933901918976}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5697674418604651, 'r': 0.9074074074074074, 'f1': 0.7}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.6923076923076923, 'r': 0.5714285714285714, 'f1': 0.6260869565217392}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.4666666666666667, 'r': 0.5833333333333334, 'f1': 0.5185185185185186}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 21
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:11:34.671301: step: 4/531, loss: 0.00146484375
2023-01-21 12:11:35.778842: step: 8/531, loss: 0.0020875930786132812
2023-01-21 12:11:36.896100: step: 12/531, loss: 0.0012967109214514494
2023-01-21 12:11:38.039065: step: 16/531, loss: 0.013607836328446865
2023-01-21 12:11:39.145351: step: 20/531, loss: 0.00043334963265806437
2023-01-21 12:11:40.294466: step: 24/531, loss: 1.9073486328125e-05
2023-01-21 12:11:41.431201: step: 28/531, loss: 0.0003990173281636089
2023-01-21 12:11:42.580084: step: 32/531, loss: 0.0001104354887502268
2023-01-21 12:11:43.688554: step: 36/531, loss: 0.0005913734203204513
2023-01-21 12:11:44.811025: step: 40/531, loss: 0.13356667757034302
2023-01-21 12:11:45.914888: step: 44/531, loss: 0.005254173651337624
2023-01-21 12:11:47.079039: step: 48/531, loss: 0.051177024841308594
2023-01-21 12:11:48.246036: step: 52/531, loss: 0.023906327784061432
2023-01-21 12:11:49.355742: step: 56/531, loss: 0.0020660876762121916
2023-01-21 12:11:50.495215: step: 60/531, loss: 0.005906486418098211
2023-01-21 12:11:51.630610: step: 64/531, loss: 0.004739284515380859
2023-01-21 12:11:52.749622: step: 68/531, loss: 0.0002316475147381425
2023-01-21 12:11:53.892100: step: 72/531, loss: 0.0008271217811852694
2023-01-21 12:11:54.995437: step: 76/531, loss: 0.00032782554626464844
2023-01-21 12:11:56.110859: step: 80/531, loss: 0.0009369850158691406
2023-01-21 12:11:57.226269: step: 84/531, loss: 0.00010261536226607859
2023-01-21 12:11:58.376220: step: 88/531, loss: 6.47544875391759e-05
2023-01-21 12:11:59.478038: step: 92/531, loss: 0.0006538868183270097
2023-01-21 12:12:00.616812: step: 96/531, loss: 0.016814231872558594
2023-01-21 12:12:01.772218: step: 100/531, loss: 0.0439663901925087
2023-01-21 12:12:02.870119: step: 104/531, loss: 0.0002846717834472656
2023-01-21 12:12:04.002076: step: 108/531, loss: 0.020621873438358307
2023-01-21 12:12:05.149516: step: 112/531, loss: 0.012073660269379616
2023-01-21 12:12:06.277960: step: 116/531, loss: 6.141662743175402e-05
2023-01-21 12:12:07.410029: step: 120/531, loss: 0.022858619689941406
2023-01-21 12:12:08.518946: step: 124/531, loss: 0.0006330490577965975
2023-01-21 12:12:09.638564: step: 128/531, loss: 0.016435718163847923
2023-01-21 12:12:10.757920: step: 132/531, loss: 4.9591067181609105e-06
2023-01-21 12:12:11.940258: step: 136/531, loss: 0.0004067897971253842
2023-01-21 12:12:13.074452: step: 140/531, loss: 0.00202598562464118
2023-01-21 12:12:14.191154: step: 144/531, loss: 0.0033483505249023438
2023-01-21 12:12:15.305771: step: 148/531, loss: 0.014723777770996094
2023-01-21 12:12:16.450596: step: 152/531, loss: 0.04154505580663681
2023-01-21 12:12:17.566778: step: 156/531, loss: 0.001240205834619701
2023-01-21 12:12:18.672200: step: 160/531, loss: 0.0006565094226971269
2023-01-21 12:12:19.801739: step: 164/531, loss: 0.0018360138637945056
2023-01-21 12:12:20.957665: step: 168/531, loss: 0.006486702244728804
2023-01-21 12:12:22.109704: step: 172/531, loss: 0.014039230532944202
2023-01-21 12:12:23.229912: step: 176/531, loss: 0.018541861325502396
2023-01-21 12:12:24.366899: step: 180/531, loss: 0.026401232928037643
2023-01-21 12:12:25.506535: step: 184/531, loss: -4.5490265620173886e-05
2023-01-21 12:12:26.626385: step: 188/531, loss: 0.005261516664177179
2023-01-21 12:12:27.760518: step: 192/531, loss: 0.025089550763368607
2023-01-21 12:12:28.883422: step: 196/531, loss: 0.0013472557766363025
2023-01-21 12:12:29.997864: step: 200/531, loss: 0.0096772201359272
2023-01-21 12:12:31.175318: step: 204/531, loss: 0.040186215192079544
2023-01-21 12:12:32.266501: step: 208/531, loss: 0.00039920807466842234
2023-01-21 12:12:33.398356: step: 212/531, loss: 0.003230953123420477
2023-01-21 12:12:34.506264: step: 216/531, loss: 6.828307959949598e-05
2023-01-21 12:12:35.609807: step: 220/531, loss: 0.01564493216574192
2023-01-21 12:12:36.727051: step: 224/531, loss: 0.00013256072998046875
2023-01-21 12:12:37.819906: step: 228/531, loss: 1.0204315003647935e-05
2023-01-21 12:12:38.929601: step: 232/531, loss: 0.0025107385590672493
2023-01-21 12:12:40.050194: step: 236/531, loss: 0.0042258743196725845
2023-01-21 12:12:41.194860: step: 240/531, loss: 0.04343080148100853
2023-01-21 12:12:42.397007: step: 244/531, loss: 0.11086282879114151
2023-01-21 12:12:43.533506: step: 248/531, loss: 0.035529520362615585
2023-01-21 12:12:44.662018: step: 252/531, loss: 0.00010232925706077367
2023-01-21 12:12:45.782562: step: 256/531, loss: 7.162093970691785e-05
2023-01-21 12:12:46.861520: step: 260/531, loss: 5.91278076171875e-05
2023-01-21 12:12:47.983748: step: 264/531, loss: 0.047910213470458984
2023-01-21 12:12:49.126955: step: 268/531, loss: 0.02231750451028347
2023-01-21 12:12:50.256306: step: 272/531, loss: 0.02125406265258789
2023-01-21 12:12:51.430290: step: 276/531, loss: 0.05889244005084038
2023-01-21 12:12:52.547820: step: 280/531, loss: 0.0010015488369390368
2023-01-21 12:12:53.669712: step: 284/531, loss: 0.02187175862491131
2023-01-21 12:12:54.806479: step: 288/531, loss: 0.044797711074352264
2023-01-21 12:12:55.913914: step: 292/531, loss: 0.003364086151123047
2023-01-21 12:12:57.019119: step: 296/531, loss: 0.0004421234189067036
2023-01-21 12:12:58.138140: step: 300/531, loss: 0.010637665167450905
2023-01-21 12:12:59.247309: step: 304/531, loss: 0.00030364992562681437
2023-01-21 12:13:00.362094: step: 308/531, loss: 0.0019585611298680305
2023-01-21 12:13:01.500238: step: 312/531, loss: 0.0017821788787841797
2023-01-21 12:13:02.640576: step: 316/531, loss: 0.02088318020105362
2023-01-21 12:13:03.753052: step: 320/531, loss: 0.046460725367069244
2023-01-21 12:13:04.872914: step: 324/531, loss: 0.013900232501327991
2023-01-21 12:13:05.998054: step: 328/531, loss: 0.0014139175182208419
2023-01-21 12:13:07.157260: step: 332/531, loss: 0.0013911246787756681
2023-01-21 12:13:08.298287: step: 336/531, loss: 0.001390647841617465
2023-01-21 12:13:09.421394: step: 340/531, loss: 0.0015871047507971525
2023-01-21 12:13:10.534359: step: 344/531, loss: 0.03544578701257706
2023-01-21 12:13:11.648226: step: 348/531, loss: 0.003041553543880582
2023-01-21 12:13:12.753385: step: 352/531, loss: 0.0003403901937417686
2023-01-21 12:13:13.860851: step: 356/531, loss: 0.0008621216402389109
2023-01-21 12:13:14.968423: step: 360/531, loss: 0.004464340396225452
2023-01-21 12:13:16.085866: step: 364/531, loss: 0.01719536818563938
2023-01-21 12:13:17.207350: step: 368/531, loss: 0.00042705534724518657
2023-01-21 12:13:18.324199: step: 372/531, loss: 0.020365525037050247
2023-01-21 12:13:19.446984: step: 376/531, loss: 0.006990456487983465
2023-01-21 12:13:20.597603: step: 380/531, loss: 0.0030241012573242188
2023-01-21 12:13:21.729167: step: 384/531, loss: 0.003670120146125555
2023-01-21 12:13:22.870351: step: 388/531, loss: 0.0026265145279467106
2023-01-21 12:13:23.977340: step: 392/531, loss: 0.0006460666772909462
2023-01-21 12:13:25.099804: step: 396/531, loss: 0.01367797888815403
2023-01-21 12:13:26.241928: step: 400/531, loss: 0.0006935120327398181
2023-01-21 12:13:27.361236: step: 404/531, loss: 0.0001470565766794607
2023-01-21 12:13:28.484769: step: 408/531, loss: 0.0013921738136559725
2023-01-21 12:13:29.613154: step: 412/531, loss: 0.0008535385131835938
2023-01-21 12:13:30.787165: step: 416/531, loss: 0.0018232346046715975
2023-01-21 12:13:31.904552: step: 420/531, loss: 0.06915612518787384
2023-01-21 12:13:33.029654: step: 424/531, loss: 1.659393274167087e-05
2023-01-21 12:13:34.171637: step: 428/531, loss: 0.010183239355683327
2023-01-21 12:13:35.322507: step: 432/531, loss: 0.10106963664293289
2023-01-21 12:13:36.481395: step: 436/531, loss: 0.0005860805977135897
2023-01-21 12:13:37.592148: step: 440/531, loss: 0.000606536865234375
2023-01-21 12:13:38.727746: step: 444/531, loss: 0.003342056181281805
2023-01-21 12:13:39.890545: step: 448/531, loss: 0.02114391326904297
2023-01-21 12:13:41.032042: step: 452/531, loss: 0.010066414251923561
2023-01-21 12:13:42.197661: step: 456/531, loss: 0.00310516357421875
2023-01-21 12:13:43.347267: step: 460/531, loss: 0.009950828738510609
2023-01-21 12:13:44.476370: step: 464/531, loss: 0.013081550598144531
2023-01-21 12:13:45.596879: step: 468/531, loss: 0.02598094940185547
2023-01-21 12:13:46.743919: step: 472/531, loss: 0.004311180207878351
2023-01-21 12:13:47.880952: step: 476/531, loss: 0.0015502929454669356
2023-01-21 12:13:49.005254: step: 480/531, loss: 0.010531758889555931
2023-01-21 12:13:50.109665: step: 484/531, loss: 0.0016803741455078125
2023-01-21 12:13:51.201969: step: 488/531, loss: 0.0012009143829345703
2023-01-21 12:13:52.327944: step: 492/531, loss: 0.008922958746552467
2023-01-21 12:13:53.431211: step: 496/531, loss: 0.0038921355735510588
2023-01-21 12:13:54.571305: step: 500/531, loss: 0.03865957260131836
2023-01-21 12:13:55.692331: step: 504/531, loss: 0.061750032007694244
2023-01-21 12:13:56.813932: step: 508/531, loss: 0.05350237339735031
2023-01-21 12:13:57.950092: step: 512/531, loss: 0.0003196716425009072
2023-01-21 12:13:59.064795: step: 516/531, loss: 0.002222061390057206
2023-01-21 12:14:00.169809: step: 520/531, loss: 0.0030922412406653166
2023-01-21 12:14:01.312828: step: 524/531, loss: 0.006308854091912508
2023-01-21 12:14:02.412961: step: 528/531, loss: 0.00019273758516646922
2023-01-21 12:14:03.526547: step: 532/531, loss: 0.002003574278205633
2023-01-21 12:14:04.656099: step: 536/531, loss: 0.0009062767494469881
2023-01-21 12:14:05.781098: step: 540/531, loss: 0.019324254244565964
2023-01-21 12:14:06.930713: step: 544/531, loss: 0.05106038972735405
2023-01-21 12:14:08.046164: step: 548/531, loss: 0.005242157261818647
2023-01-21 12:14:09.177209: step: 552/531, loss: 0.006154107861220837
2023-01-21 12:14:10.281836: step: 556/531, loss: 0.00226593017578125
2023-01-21 12:14:11.418237: step: 560/531, loss: 0.0009725570562295616
2023-01-21 12:14:12.556558: step: 564/531, loss: 0.013335037976503372
2023-01-21 12:14:13.701071: step: 568/531, loss: 0.01642150990664959
2023-01-21 12:14:14.819881: step: 572/531, loss: 0.023996639996767044
2023-01-21 12:14:15.973058: step: 576/531, loss: 0.007940865121781826
2023-01-21 12:14:17.117408: step: 580/531, loss: 0.0250091552734375
2023-01-21 12:14:18.251913: step: 584/531, loss: 0.0006420135614462197
2023-01-21 12:14:19.372613: step: 588/531, loss: 0.003153037978336215
2023-01-21 12:14:20.484890: step: 592/531, loss: 0.015019607730209827
2023-01-21 12:14:21.587175: step: 596/531, loss: 0.0002541974245104939
2023-01-21 12:14:22.711984: step: 600/531, loss: 0.02427959442138672
2023-01-21 12:14:23.843471: step: 604/531, loss: 3.1948088690114673e-06
2023-01-21 12:14:24.984346: step: 608/531, loss: 0.007500267121940851
2023-01-21 12:14:26.115896: step: 612/531, loss: 0.029379844665527344
2023-01-21 12:14:27.256919: step: 616/531, loss: 0.015662861987948418
2023-01-21 12:14:28.345430: step: 620/531, loss: 9.031295485328883e-05
2023-01-21 12:14:29.482790: step: 624/531, loss: 0.0016520499484613538
2023-01-21 12:14:30.649673: step: 628/531, loss: 0.0005409240839071572
2023-01-21 12:14:31.812417: step: 632/531, loss: 6.103515261202119e-06
2023-01-21 12:14:32.942894: step: 636/531, loss: 0.00010414123971713707
2023-01-21 12:14:34.079274: step: 640/531, loss: 0.0018703535897657275
2023-01-21 12:14:35.187796: step: 644/531, loss: 0.1352323442697525
2023-01-21 12:14:36.336613: step: 648/531, loss: 0.00041370390681549907
2023-01-21 12:14:37.458130: step: 652/531, loss: 0.0060867308638989925
2023-01-21 12:14:38.580832: step: 656/531, loss: 0.005110740661621094
2023-01-21 12:14:39.741010: step: 660/531, loss: 0.006535148713737726
2023-01-21 12:14:40.884715: step: 664/531, loss: 6.866455805720761e-06
2023-01-21 12:14:42.003893: step: 668/531, loss: 0.001667022705078125
2023-01-21 12:14:43.129122: step: 672/531, loss: 0.0010066985851153731
2023-01-21 12:14:44.249189: step: 676/531, loss: 0.003857183502987027
2023-01-21 12:14:45.408486: step: 680/531, loss: 0.024642562493681908
2023-01-21 12:14:46.528085: step: 684/531, loss: 0.00031766892061568797
2023-01-21 12:14:47.629021: step: 688/531, loss: 0.001850032713264227
2023-01-21 12:14:48.747088: step: 692/531, loss: 0.0009451866499148309
2023-01-21 12:14:49.873709: step: 696/531, loss: 0.8067765235900879
2023-01-21 12:14:51.005501: step: 700/531, loss: 0.006209373474121094
2023-01-21 12:14:52.120623: step: 704/531, loss: 0.007160186767578125
2023-01-21 12:14:53.234506: step: 708/531, loss: 0.02107868157327175
2023-01-21 12:14:54.349553: step: 712/531, loss: 0.002664947649464011
2023-01-21 12:14:55.520602: step: 716/531, loss: 0.004686165135353804
2023-01-21 12:14:56.636212: step: 720/531, loss: 1.1253358024987392e-05
2023-01-21 12:14:57.749597: step: 724/531, loss: 0.00550346402451396
2023-01-21 12:14:58.866563: step: 728/531, loss: 0.004561042878776789
2023-01-21 12:14:59.994461: step: 732/531, loss: 9.5367431640625e-07
2023-01-21 12:15:01.128431: step: 736/531, loss: 0.01009903009980917
2023-01-21 12:15:02.230785: step: 740/531, loss: 0.004872035700827837
2023-01-21 12:15:03.386238: step: 744/531, loss: 0.0005254745483398438
2023-01-21 12:15:04.505467: step: 748/531, loss: 0.0020072937477380037
2023-01-21 12:15:05.627700: step: 752/531, loss: 0.24814629554748535
2023-01-21 12:15:06.754504: step: 756/531, loss: 0.047196581959724426
2023-01-21 12:15:07.875419: step: 760/531, loss: 0.01591968536376953
2023-01-21 12:15:09.011627: step: 764/531, loss: 0.06380748748779297
2023-01-21 12:15:10.119117: step: 768/531, loss: 0.0012100220192223787
2023-01-21 12:15:11.265378: step: 772/531, loss: 0.008951187133789062
2023-01-21 12:15:12.397147: step: 776/531, loss: 0.0027610778342932463
2023-01-21 12:15:13.520359: step: 780/531, loss: 5.474090721691027e-05
2023-01-21 12:15:14.667193: step: 784/531, loss: 0.017109109088778496
2023-01-21 12:15:15.803420: step: 788/531, loss: 0.03129778057336807
2023-01-21 12:15:16.911133: step: 792/531, loss: 6.790160841774195e-05
2023-01-21 12:15:18.058410: step: 796/531, loss: 0.10087509453296661
2023-01-21 12:15:19.162995: step: 800/531, loss: 0.0007387161022052169
2023-01-21 12:15:20.293342: step: 804/531, loss: 0.00988006591796875
2023-01-21 12:15:21.439746: step: 808/531, loss: 0.01801433600485325
2023-01-21 12:15:22.575439: step: 812/531, loss: 0.04567756503820419
2023-01-21 12:15:23.676391: step: 816/531, loss: 0.00035381317138671875
2023-01-21 12:15:24.798204: step: 820/531, loss: 0.0003025055048055947
2023-01-21 12:15:25.919091: step: 824/531, loss: 0.10238619148731232
2023-01-21 12:15:27.050239: step: 828/531, loss: 0.00135459890589118
2023-01-21 12:15:28.162140: step: 832/531, loss: 6.64711042190902e-05
2023-01-21 12:15:29.292014: step: 836/531, loss: 5.7220458984375e-05
2023-01-21 12:15:30.401931: step: 840/531, loss: 0.03538379818201065
2023-01-21 12:15:31.545925: step: 844/531, loss: 2.0694731574621983e-05
2023-01-21 12:15:32.676266: step: 848/531, loss: 0.0050491332076489925
2023-01-21 12:15:33.779335: step: 852/531, loss: 4.5490265620173886e-05
2023-01-21 12:15:34.932860: step: 856/531, loss: 0.007400035858154297
2023-01-21 12:15:36.044720: step: 860/531, loss: 0.003403949784114957
2023-01-21 12:15:37.157710: step: 864/531, loss: 0.0034372329246252775
2023-01-21 12:15:38.287632: step: 868/531, loss: 0.010037804022431374
2023-01-21 12:15:39.418099: step: 872/531, loss: 0.02905855141580105
2023-01-21 12:15:40.575380: step: 876/531, loss: 0.013191891834139824
2023-01-21 12:15:41.677620: step: 880/531, loss: 0.03658923879265785
2023-01-21 12:15:42.806907: step: 884/531, loss: 0.09703254699707031
2023-01-21 12:15:43.938329: step: 888/531, loss: 0.08679771423339844
2023-01-21 12:15:45.057154: step: 892/531, loss: 0.002456950955092907
2023-01-21 12:15:46.160992: step: 896/531, loss: 0.0008205414051190019
2023-01-21 12:15:47.295626: step: 900/531, loss: 0.0001329422084381804
2023-01-21 12:15:48.429786: step: 904/531, loss: 0.0007326126215048134
2023-01-21 12:15:49.553388: step: 908/531, loss: 0.0014490127796307206
2023-01-21 12:15:50.691700: step: 912/531, loss: 0.0018097878200933337
2023-01-21 12:15:51.809055: step: 916/531, loss: 0.011127281934022903
2023-01-21 12:15:52.921095: step: 920/531, loss: 0.0047990805469453335
2023-01-21 12:15:54.020217: step: 924/531, loss: 0.0009864807361736894
2023-01-21 12:15:55.130860: step: 928/531, loss: 0.00030226705712266266
2023-01-21 12:15:56.239599: step: 932/531, loss: 0.03904876857995987
2023-01-21 12:15:57.373815: step: 936/531, loss: 0.007645892910659313
2023-01-21 12:15:58.480070: step: 940/531, loss: 3.7860871088923886e-05
2023-01-21 12:15:59.625214: step: 944/531, loss: 0.0008703232160769403
2023-01-21 12:16:00.736847: step: 948/531, loss: 0.014857864007353783
2023-01-21 12:16:01.843513: step: 952/531, loss: 0.026413489133119583
2023-01-21 12:16:02.991045: step: 956/531, loss: 0.0027343749534338713
2023-01-21 12:16:04.094294: step: 960/531, loss: 0.0012426376342773438
2023-01-21 12:16:05.234506: step: 964/531, loss: 0.03441353142261505
2023-01-21 12:16:06.368174: step: 968/531, loss: 1.5926361811580136e-05
2023-01-21 12:16:07.471436: step: 972/531, loss: 0.00088415143545717
2023-01-21 12:16:08.600964: step: 976/531, loss: 0.002712822053581476
2023-01-21 12:16:09.717648: step: 980/531, loss: 0.002924347063526511
2023-01-21 12:16:10.867023: step: 984/531, loss: 0.0028717995155602694
2023-01-21 12:16:11.964976: step: 988/531, loss: 2.3078917365637608e-05
2023-01-21 12:16:13.089777: step: 992/531, loss: 0.007679557893425226
2023-01-21 12:16:14.201540: step: 996/531, loss: 2.384185791015625e-07
2023-01-21 12:16:15.315760: step: 1000/531, loss: 0.018398379907011986
2023-01-21 12:16:16.414863: step: 1004/531, loss: 0.005536174867302179
2023-01-21 12:16:17.548602: step: 1008/531, loss: 0.07396488636732101
2023-01-21 12:16:18.695422: step: 1012/531, loss: 0.01290912739932537
2023-01-21 12:16:19.852701: step: 1016/531, loss: 0.0480104461312294
2023-01-21 12:16:20.983596: step: 1020/531, loss: 0.004693222232162952
2023-01-21 12:16:22.096060: step: 1024/531, loss: 0.09185962378978729
2023-01-21 12:16:23.208375: step: 1028/531, loss: 0.03025207668542862
2023-01-21 12:16:24.312648: step: 1032/531, loss: 0.0014249802334234118
2023-01-21 12:16:25.409545: step: 1036/531, loss: 0.0010518074268475175
2023-01-21 12:16:26.540055: step: 1040/531, loss: 0.023694612085819244
2023-01-21 12:16:27.653191: step: 1044/531, loss: 0.009563731960952282
2023-01-21 12:16:28.841404: step: 1048/531, loss: 0.0575651153922081
2023-01-21 12:16:29.992339: step: 1052/531, loss: 0.0002812385791912675
2023-01-21 12:16:31.092490: step: 1056/531, loss: 0.02248263545334339
2023-01-21 12:16:32.202272: step: 1060/531, loss: 0.0036524771712720394
2023-01-21 12:16:33.319523: step: 1064/531, loss: 0.015282250009477139
2023-01-21 12:16:34.450719: step: 1068/531, loss: 0.00022683144197799265
2023-01-21 12:16:35.578132: step: 1072/531, loss: 0.004895114805549383
2023-01-21 12:16:36.694244: step: 1076/531, loss: 0.007122325710952282
2023-01-21 12:16:37.849070: step: 1080/531, loss: 0.003162384033203125
2023-01-21 12:16:38.983460: step: 1084/531, loss: 0.0004028320254292339
2023-01-21 12:16:40.161824: step: 1088/531, loss: 0.010314464569091797
2023-01-21 12:16:41.301700: step: 1092/531, loss: 0.03436090052127838
2023-01-21 12:16:42.395034: step: 1096/531, loss: 0.0002773284795694053
2023-01-21 12:16:43.543061: step: 1100/531, loss: 0.0539461150765419
2023-01-21 12:16:44.649290: step: 1104/531, loss: 0.013398217968642712
2023-01-21 12:16:45.777354: step: 1108/531, loss: 0.05912666395306587
2023-01-21 12:16:46.880838: step: 1112/531, loss: 0.00031495094299316406
2023-01-21 12:16:48.005475: step: 1116/531, loss: 0.00014991759962867945
2023-01-21 12:16:49.124064: step: 1120/531, loss: 0.014097308740019798
2023-01-21 12:16:50.234871: step: 1124/531, loss: 0.004456711001694202
2023-01-21 12:16:51.364521: step: 1128/531, loss: 0.00144023890607059
2023-01-21 12:16:52.528777: step: 1132/531, loss: 0.020263100042939186
2023-01-21 12:16:53.677893: step: 1136/531, loss: 0.0009884476894512773
2023-01-21 12:16:54.782412: step: 1140/531, loss: 0.0029548644088208675
2023-01-21 12:16:55.888966: step: 1144/531, loss: 0.00010752677917480469
2023-01-21 12:16:57.010753: step: 1148/531, loss: 0.0015525819035246968
2023-01-21 12:16:58.123163: step: 1152/531, loss: 0.009813498705625534
2023-01-21 12:16:59.242146: step: 1156/531, loss: 0.14392872154712677
2023-01-21 12:17:00.361754: step: 1160/531, loss: 0.016886424273252487
2023-01-21 12:17:01.485446: step: 1164/531, loss: 0.002191734267398715
2023-01-21 12:17:02.618259: step: 1168/531, loss: 0.4961088299751282
2023-01-21 12:17:03.762458: step: 1172/531, loss: 0.003760910127311945
2023-01-21 12:17:04.908269: step: 1176/531, loss: 0.04500961676239967
2023-01-21 12:17:06.037657: step: 1180/531, loss: 0.00046291350736282766
2023-01-21 12:17:07.165479: step: 1184/531, loss: 0.014890193939208984
2023-01-21 12:17:08.296307: step: 1188/531, loss: 0.003946161363273859
2023-01-21 12:17:09.415636: step: 1192/531, loss: 0.025676345452666283
2023-01-21 12:17:10.557052: step: 1196/531, loss: 0.00022430419630836695
2023-01-21 12:17:11.717105: step: 1200/531, loss: 0.0009365081787109375
2023-01-21 12:17:12.835333: step: 1204/531, loss: 0.09767065197229385
2023-01-21 12:17:13.943066: step: 1208/531, loss: 0.010264492593705654
2023-01-21 12:17:15.062255: step: 1212/531, loss: 0.0013503074878826737
2023-01-21 12:17:16.218397: step: 1216/531, loss: 0.0004410266992636025
2023-01-21 12:17:17.362947: step: 1220/531, loss: 0.013649463653564453
2023-01-21 12:17:18.490106: step: 1224/531, loss: 0.04093818739056587
2023-01-21 12:17:19.613640: step: 1228/531, loss: 0.0016511917347088456
2023-01-21 12:17:20.748053: step: 1232/531, loss: 0.00041027070255950093
2023-01-21 12:17:21.866496: step: 1236/531, loss: 0.0008877754444256425
2023-01-21 12:17:22.985926: step: 1240/531, loss: 0.0006544113275595009
2023-01-21 12:17:24.099429: step: 1244/531, loss: 0.0018414973746985197
2023-01-21 12:17:25.257986: step: 1248/531, loss: 0.022600937634706497
2023-01-21 12:17:26.393864: step: 1252/531, loss: 0.0005557060358114541
2023-01-21 12:17:27.533682: step: 1256/531, loss: 0.051259662955999374
2023-01-21 12:17:28.637896: step: 1260/531, loss: 0.012520790100097656
2023-01-21 12:17:29.758887: step: 1264/531, loss: 0.000640869140625
2023-01-21 12:17:30.875613: step: 1268/531, loss: 0.00015935898409225047
2023-01-21 12:17:32.003734: step: 1272/531, loss: 0.003366661025211215
2023-01-21 12:17:33.109531: step: 1276/531, loss: 0.008142232894897461
2023-01-21 12:17:34.224477: step: 1280/531, loss: 0.008933067321777344
2023-01-21 12:17:35.370514: step: 1284/531, loss: 0.0006323814741335809
2023-01-21 12:17:36.486519: step: 1288/531, loss: 0.0003190040588378906
2023-01-21 12:17:37.636405: step: 1292/531, loss: 0.0005426406860351562
2023-01-21 12:17:38.759400: step: 1296/531, loss: 0.029558563604950905
2023-01-21 12:17:39.873850: step: 1300/531, loss: 0.0012809752952307463
2023-01-21 12:17:41.009239: step: 1304/531, loss: 4.420280674821697e-05
2023-01-21 12:17:42.143040: step: 1308/531, loss: 0.0018699646461755037
2023-01-21 12:17:43.263558: step: 1312/531, loss: 0.011875820346176624
2023-01-21 12:17:44.398995: step: 1316/531, loss: 6.217956251930445e-05
2023-01-21 12:17:45.523834: step: 1320/531, loss: 0.016339685767889023
2023-01-21 12:17:46.620439: step: 1324/531, loss: 0.0027258514892309904
2023-01-21 12:17:47.779745: step: 1328/531, loss: 0.009500885382294655
2023-01-21 12:17:48.923472: step: 1332/531, loss: 0.06279821693897247
2023-01-21 12:17:50.059142: step: 1336/531, loss: 0.0006595611339434981
2023-01-21 12:17:51.202951: step: 1340/531, loss: 0.00013465881056617945
2023-01-21 12:17:52.338445: step: 1344/531, loss: 0.03590374067425728
2023-01-21 12:17:53.450221: step: 1348/531, loss: 0.010112190619111061
2023-01-21 12:17:54.562627: step: 1352/531, loss: 0.002113437745720148
2023-01-21 12:17:55.658734: step: 1356/531, loss: 0.004073619842529297
2023-01-21 12:17:56.786855: step: 1360/531, loss: 0.005312538240104914
2023-01-21 12:17:57.897235: step: 1364/531, loss: 0.00039082765579223633
2023-01-21 12:17:59.060633: step: 1368/531, loss: 0.02067432552576065
2023-01-21 12:18:00.197987: step: 1372/531, loss: 0.0008126497268676758
2023-01-21 12:18:01.303817: step: 1376/531, loss: 0.0003488540824037045
2023-01-21 12:18:02.438788: step: 1380/531, loss: 0.00210742955096066
2023-01-21 12:18:03.571771: step: 1384/531, loss: 0.04609685018658638
2023-01-21 12:18:04.698185: step: 1388/531, loss: 0.01796741597354412
2023-01-21 12:18:05.829640: step: 1392/531, loss: 0.4730847477912903
2023-01-21 12:18:06.943362: step: 1396/531, loss: 0.0002134323149221018
2023-01-21 12:18:08.072266: step: 1400/531, loss: 0.055722616612911224
2023-01-21 12:18:09.182703: step: 1404/531, loss: 0.00030803680419921875
2023-01-21 12:18:10.300021: step: 1408/531, loss: 0.0014691352844238281
2023-01-21 12:18:11.435284: step: 1412/531, loss: 0.029279422014951706
2023-01-21 12:18:12.570723: step: 1416/531, loss: 0.01132297609001398
2023-01-21 12:18:13.686218: step: 1420/531, loss: 0.007129383273422718
2023-01-21 12:18:14.850677: step: 1424/531, loss: 0.00130462646484375
2023-01-21 12:18:15.995090: step: 1428/531, loss: 0.009108830243349075
2023-01-21 12:18:17.121311: step: 1432/531, loss: 0.0004878044128417969
2023-01-21 12:18:18.254150: step: 1436/531, loss: 0.0058769225142896175
2023-01-21 12:18:19.403710: step: 1440/531, loss: 0.00014991761418059468
2023-01-21 12:18:20.511489: step: 1444/531, loss: 0.02115612104535103
2023-01-21 12:18:21.650988: step: 1448/531, loss: 0.0010305404430255294
2023-01-21 12:18:22.794405: step: 1452/531, loss: 0.018008803948760033
2023-01-21 12:18:23.926612: step: 1456/531, loss: 0.005129051394760609
2023-01-21 12:18:25.074395: step: 1460/531, loss: 0.10103468596935272
2023-01-21 12:18:26.219454: step: 1464/531, loss: 0.022390173748135567
2023-01-21 12:18:27.333984: step: 1468/531, loss: 0.00415878277271986
2023-01-21 12:18:28.492707: step: 1472/531, loss: 0.03391876071691513
2023-01-21 12:18:29.586360: step: 1476/531, loss: 0.00482788123190403
2023-01-21 12:18:30.689200: step: 1480/531, loss: 5.254745337879285e-05
2023-01-21 12:18:31.799546: step: 1484/531, loss: 0.03279914706945419
2023-01-21 12:18:32.921944: step: 1488/531, loss: 0.0030317306518554688
2023-01-21 12:18:34.038436: step: 1492/531, loss: 0.00019760131544899195
2023-01-21 12:18:35.159982: step: 1496/531, loss: 0.01295461691915989
2023-01-21 12:18:36.279223: step: 1500/531, loss: 0.0004896164173260331
2023-01-21 12:18:37.402324: step: 1504/531, loss: 0.00054889329476282
2023-01-21 12:18:38.493746: step: 1508/531, loss: 0.01773662678897381
2023-01-21 12:18:39.621221: step: 1512/531, loss: 0.00033740996150299907
2023-01-21 12:18:40.722022: step: 1516/531, loss: 0.004768943414092064
2023-01-21 12:18:41.861384: step: 1520/531, loss: 0.03475676104426384
2023-01-21 12:18:42.980552: step: 1524/531, loss: 0.0009329319000244141
2023-01-21 12:18:44.083634: step: 1528/531, loss: 0.00011625289334915578
2023-01-21 12:18:45.201147: step: 1532/531, loss: 0.0006427764892578125
2023-01-21 12:18:46.362865: step: 1536/531, loss: 0.06848545372486115
2023-01-21 12:18:47.517503: step: 1540/531, loss: 0.5803816914558411
2023-01-21 12:18:48.654034: step: 1544/531, loss: 7.615089998580515e-05
2023-01-21 12:18:49.785919: step: 1548/531, loss: 0.001247406005859375
2023-01-21 12:18:50.951835: step: 1552/531, loss: 0.024210358038544655
2023-01-21 12:18:52.071404: step: 1556/531, loss: 0.0819338783621788
2023-01-21 12:18:53.222875: step: 1560/531, loss: 0.00032300950260832906
2023-01-21 12:18:54.345293: step: 1564/531, loss: 0.00016479492478538305
2023-01-21 12:18:55.443990: step: 1568/531, loss: 0.008023262023925781
2023-01-21 12:18:56.539023: step: 1572/531, loss: 0.00020880700321868062
2023-01-21 12:18:57.667916: step: 1576/531, loss: 0.0007566452259197831
2023-01-21 12:18:58.808782: step: 1580/531, loss: 0.0019371032249182463
2023-01-21 12:18:59.941259: step: 1584/531, loss: 0.030925419181585312
2023-01-21 12:19:01.049061: step: 1588/531, loss: 0.0006134033319540322
2023-01-21 12:19:02.185672: step: 1592/531, loss: 0.010429573245346546
2023-01-21 12:19:03.330194: step: 1596/531, loss: 0.05681400001049042
2023-01-21 12:19:04.445448: step: 1600/531, loss: 0.00024051667423918843
2023-01-21 12:19:05.559385: step: 1604/531, loss: -7.534027190558845e-06
2023-01-21 12:19:06.691806: step: 1608/531, loss: 0.0036504745949059725
2023-01-21 12:19:07.815761: step: 1612/531, loss: 0.007227051071822643
2023-01-21 12:19:08.937304: step: 1616/531, loss: 0.0005006790161132812
2023-01-21 12:19:10.057066: step: 1620/531, loss: 0.004570198245346546
2023-01-21 12:19:11.152731: step: 1624/531, loss: 0.000118255615234375
2023-01-21 12:19:12.270536: step: 1628/531, loss: 0.004357719793915749
2023-01-21 12:19:13.423373: step: 1632/531, loss: 0.007411765865981579
2023-01-21 12:19:14.522386: step: 1636/531, loss: 0.0010627746814861894
2023-01-21 12:19:15.633506: step: 1640/531, loss: 0.010985566303133965
2023-01-21 12:19:16.763693: step: 1644/531, loss: 0.002540492918342352
2023-01-21 12:19:17.880602: step: 1648/531, loss: 0.003048801328986883
2023-01-21 12:19:19.003037: step: 1652/531, loss: 0.010051059536635876
2023-01-21 12:19:20.117799: step: 1656/531, loss: 0.0037695884238928556
2023-01-21 12:19:21.226745: step: 1660/531, loss: 0.35198134183883667
2023-01-21 12:19:22.336526: step: 1664/531, loss: 0.001451206160709262
2023-01-21 12:19:23.420991: step: 1668/531, loss: 8.831024024402723e-05
2023-01-21 12:19:24.530347: step: 1672/531, loss: 0.003943252377212048
2023-01-21 12:19:25.641384: step: 1676/531, loss: 0.006049108691513538
2023-01-21 12:19:26.752127: step: 1680/531, loss: 1.6689300537109375e-06
2023-01-21 12:19:27.905370: step: 1684/531, loss: 0.016969136893749237
2023-01-21 12:19:29.020922: step: 1688/531, loss: 0.013136005029082298
2023-01-21 12:19:30.139406: step: 1692/531, loss: 0.00012054443504894152
2023-01-21 12:19:31.252973: step: 1696/531, loss: 0.03838710859417915
2023-01-21 12:19:32.395891: step: 1700/531, loss: 0.10964298993349075
2023-01-21 12:19:33.516558: step: 1704/531, loss: 0.12334060668945312
2023-01-21 12:19:34.623018: step: 1708/531, loss: 0.002704620361328125
2023-01-21 12:19:35.732592: step: 1712/531, loss: 0.04771919175982475
2023-01-21 12:19:36.853392: step: 1716/531, loss: 0.0032807348761707544
2023-01-21 12:19:37.972812: step: 1720/531, loss: 0.00015978813462425023
2023-01-21 12:19:39.070460: step: 1724/531, loss: 0.014946985058486462
2023-01-21 12:19:40.204084: step: 1728/531, loss: 0.019005775451660156
2023-01-21 12:19:41.307755: step: 1732/531, loss: 0.10810118168592453
2023-01-21 12:19:42.445758: step: 1736/531, loss: 0.05720863491296768
2023-01-21 12:19:43.562794: step: 1740/531, loss: 0.006876516621559858
2023-01-21 12:19:44.674106: step: 1744/531, loss: 0.03406667709350586
2023-01-21 12:19:45.820446: step: 1748/531, loss: 0.03202657774090767
2023-01-21 12:19:46.920244: step: 1752/531, loss: 0.004449415020644665
2023-01-21 12:19:48.044806: step: 1756/531, loss: 0.008105278015136719
2023-01-21 12:19:49.154476: step: 1760/531, loss: 0.04930820316076279
2023-01-21 12:19:50.243014: step: 1764/531, loss: 0.002547550480812788
2023-01-21 12:19:51.372257: step: 1768/531, loss: 0.026983069255948067
2023-01-21 12:19:52.495591: step: 1772/531, loss: 0.002289199735969305
2023-01-21 12:19:53.655532: step: 1776/531, loss: 0.026494454592466354
2023-01-21 12:19:54.762523: step: 1780/531, loss: 0.05965833738446236
2023-01-21 12:19:55.897800: step: 1784/531, loss: 0.0032626150641590357
2023-01-21 12:19:57.060502: step: 1788/531, loss: 0.02072601392865181
2023-01-21 12:19:58.179322: step: 1792/531, loss: 0.028166770935058594
2023-01-21 12:19:59.298971: step: 1796/531, loss: 0.0029715539421886206
2023-01-21 12:20:00.413858: step: 1800/531, loss: 0.04965553060173988
2023-01-21 12:20:01.539620: step: 1804/531, loss: 1.1444091796875e-05
2023-01-21 12:20:02.664476: step: 1808/531, loss: 0.002735710237175226
2023-01-21 12:20:03.812999: step: 1812/531, loss: 0.016646387055516243
2023-01-21 12:20:04.941675: step: 1816/531, loss: 0.0002789497375488281
2023-01-21 12:20:06.073151: step: 1820/531, loss: 0.0028167725540697575
2023-01-21 12:20:07.204808: step: 1824/531, loss: 0.004387092776596546
2023-01-21 12:20:08.346824: step: 1828/531, loss: 0.008446693420410156
2023-01-21 12:20:09.467158: step: 1832/531, loss: 0.09166374802589417
2023-01-21 12:20:10.609253: step: 1836/531, loss: 0.021665288135409355
2023-01-21 12:20:11.756482: step: 1840/531, loss: 2.956390380859375e-05
2023-01-21 12:20:12.904262: step: 1844/531, loss: 0.003444194793701172
2023-01-21 12:20:14.026126: step: 1848/531, loss: 0.04512529447674751
2023-01-21 12:20:15.132584: step: 1852/531, loss: 0.0004996299976482987
2023-01-21 12:20:16.282251: step: 1856/531, loss: 0.0010347366333007812
2023-01-21 12:20:17.419119: step: 1860/531, loss: 0.051970481872558594
2023-01-21 12:20:18.555034: step: 1864/531, loss: 0.014038467779755592
2023-01-21 12:20:19.709339: step: 1868/531, loss: 0.008013535290956497
2023-01-21 12:20:20.830016: step: 1872/531, loss: 0.0016998292412608862
2023-01-21 12:20:21.995091: step: 1876/531, loss: 0.005942249670624733
2023-01-21 12:20:23.124242: step: 1880/531, loss: 0.02713184244930744
2023-01-21 12:20:24.279971: step: 1884/531, loss: 0.011976242065429688
2023-01-21 12:20:25.390660: step: 1888/531, loss: 4.4345855712890625e-05
2023-01-21 12:20:26.503725: step: 1892/531, loss: 0.000531101250089705
2023-01-21 12:20:27.651743: step: 1896/531, loss: 3.0040740966796875e-05
2023-01-21 12:20:28.776686: step: 1900/531, loss: 0.0017988205654546618
2023-01-21 12:20:29.918474: step: 1904/531, loss: 0.0015722275711596012
2023-01-21 12:20:31.056009: step: 1908/531, loss: 0.017586326226592064
2023-01-21 12:20:32.201586: step: 1912/531, loss: 0.002399945165961981
2023-01-21 12:20:33.346547: step: 1916/531, loss: 9.942054748535156e-05
2023-01-21 12:20:34.477187: step: 1920/531, loss: 0.00029621124849654734
2023-01-21 12:20:35.617143: step: 1924/531, loss: 0.000118255615234375
2023-01-21 12:20:36.762926: step: 1928/531, loss: 0.0016471862327307463
2023-01-21 12:20:37.880298: step: 1932/531, loss: 0.021920204162597656
2023-01-21 12:20:38.998585: step: 1936/531, loss: 0.005694103427231312
2023-01-21 12:20:40.132925: step: 1940/531, loss: 0.00018787384033203125
2023-01-21 12:20:41.249058: step: 1944/531, loss: 0.017901327461004257
2023-01-21 12:20:42.388088: step: 1948/531, loss: 0.04023037105798721
2023-01-21 12:20:43.524046: step: 1952/531, loss: 0.002662849612534046
2023-01-21 12:20:44.653250: step: 1956/531, loss: 0.03124532662332058
2023-01-21 12:20:45.802609: step: 1960/531, loss: 0.0007418632740154862
2023-01-21 12:20:46.957498: step: 1964/531, loss: 0.000194549560546875
2023-01-21 12:20:48.111048: step: 1968/531, loss: 0.012388801202178001
2023-01-21 12:20:49.244347: step: 1972/531, loss: 0.0242493636906147
2023-01-21 12:20:50.362843: step: 1976/531, loss: 0.017926692962646484
2023-01-21 12:20:51.478796: step: 1980/531, loss: 0.026798248291015625
2023-01-21 12:20:52.594519: step: 1984/531, loss: 0.014082526788115501
2023-01-21 12:20:53.726658: step: 1988/531, loss: 0.0021657943725585938
2023-01-21 12:20:54.844074: step: 1992/531, loss: 0.015585088171064854
2023-01-21 12:20:56.004124: step: 1996/531, loss: 0.0418248176574707
2023-01-21 12:20:57.135809: step: 2000/531, loss: 0.0003028869687113911
2023-01-21 12:20:58.288138: step: 2004/531, loss: 0.01108398474752903
2023-01-21 12:20:59.398226: step: 2008/531, loss: 9.651184518588707e-05
2023-01-21 12:21:00.508302: step: 2012/531, loss: 0.0002839088556356728
2023-01-21 12:21:01.642348: step: 2016/531, loss: 0.0951557606458664
2023-01-21 12:21:02.745862: step: 2020/531, loss: 0.1912635713815689
2023-01-21 12:21:03.864168: step: 2024/531, loss: 0.0003766060108318925
2023-01-21 12:21:04.962765: step: 2028/531, loss: 0.46143627166748047
2023-01-21 12:21:06.080470: step: 2032/531, loss: 0.0015483855968341231
2023-01-21 12:21:07.166194: step: 2036/531, loss: 0.0018707275157794356
2023-01-21 12:21:08.300202: step: 2040/531, loss: 0.00037803652230650187
2023-01-21 12:21:09.423312: step: 2044/531, loss: 0.0051177977584302425
2023-01-21 12:21:10.586961: step: 2048/531, loss: 1.8215179807157256e-05
2023-01-21 12:21:11.719502: step: 2052/531, loss: 0.0002663612540345639
2023-01-21 12:21:12.864497: step: 2056/531, loss: 0.0006105899810791016
2023-01-21 12:21:13.979145: step: 2060/531, loss: 6.809234764659777e-05
2023-01-21 12:21:15.095731: step: 2064/531, loss: 0.0005039215320721269
2023-01-21 12:21:16.202384: step: 2068/531, loss: 0.00024032594228629023
2023-01-21 12:21:17.323987: step: 2072/531, loss: 0.0005002021789550781
2023-01-21 12:21:18.433494: step: 2076/531, loss: 0.001376342843286693
2023-01-21 12:21:19.581757: step: 2080/531, loss: 0.011607170104980469
2023-01-21 12:21:20.715927: step: 2084/531, loss: 0.0532136932015419
2023-01-21 12:21:21.860447: step: 2088/531, loss: 0.0009836197132244706
2023-01-21 12:21:23.031969: step: 2092/531, loss: 0.013960391283035278
2023-01-21 12:21:24.183574: step: 2096/531, loss: 0.027484990656375885
2023-01-21 12:21:25.315261: step: 2100/531, loss: 0.01514358539134264
2023-01-21 12:21:26.440384: step: 2104/531, loss: 0.015422630123794079
2023-01-21 12:21:27.563892: step: 2108/531, loss: 0.007812690921127796
2023-01-21 12:21:28.691271: step: 2112/531, loss: 0.06453514844179153
2023-01-21 12:21:29.810521: step: 2116/531, loss: 0.007500458043068647
2023-01-21 12:21:30.917580: step: 2120/531, loss: 0.008971215225756168
2023-01-21 12:21:32.049361: step: 2124/531, loss: 0.0004103660467080772
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5917948717948718, 'r': 0.7683089214380826, 'f1': 0.6685979142526071}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6333656644034917, 'r': 0.7787716159809183, 'f1': 0.6985825086921637}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.6595744680851063, 'r': 0.49206349206349204, 'f1': 0.5636363636363635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 22
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:22:12.142125: step: 4/531, loss: 0.0018997193546965718
2023-01-21 12:22:13.275468: step: 8/531, loss: 0.0044491770677268505
2023-01-21 12:22:14.436191: step: 12/531, loss: 0.0006845474126748741
2023-01-21 12:22:15.540549: step: 16/531, loss: 0.0003575325245037675
2023-01-21 12:22:16.657039: step: 20/531, loss: 0.0024196626618504524
2023-01-21 12:22:17.783183: step: 24/531, loss: 0.00042047502938658
2023-01-21 12:22:18.897090: step: 28/531, loss: 5.769729978055693e-05
2023-01-21 12:22:20.054504: step: 32/531, loss: 0.016727877780795097
2023-01-21 12:22:21.169382: step: 36/531, loss: 0.3487062454223633
2023-01-21 12:22:22.277905: step: 40/531, loss: 0.060029126703739166
2023-01-21 12:22:23.383366: step: 44/531, loss: 0.00387401576153934
2023-01-21 12:22:24.503489: step: 48/531, loss: 0.001007080078125
2023-01-21 12:22:25.603810: step: 52/531, loss: 0.0370633602142334
2023-01-21 12:22:26.703887: step: 56/531, loss: 0.006470871157944202
2023-01-21 12:22:27.869180: step: 60/531, loss: 0.0017126083839684725
2023-01-21 12:22:29.031304: step: 64/531, loss: 0.0011920928955078125
2023-01-21 12:22:30.158329: step: 68/531, loss: 9.5367431640625e-06
2023-01-21 12:22:31.278209: step: 72/531, loss: 0.07960548251867294
2023-01-21 12:22:32.395389: step: 76/531, loss: 0.0006762504926882684
2023-01-21 12:22:33.532635: step: 80/531, loss: 0.00035643577575683594
2023-01-21 12:22:34.649860: step: 84/531, loss: 4.1007992876984645e-06
2023-01-21 12:22:35.794056: step: 88/531, loss: 0.002665901090949774
2023-01-21 12:22:36.901223: step: 92/531, loss: 0.0012102127075195312
2023-01-21 12:22:38.036094: step: 96/531, loss: 0.010812587104737759
2023-01-21 12:22:39.150198: step: 100/531, loss: 0.0003010451910085976
2023-01-21 12:22:40.310882: step: 104/531, loss: 0.0054826741106808186
2023-01-21 12:22:41.455161: step: 108/531, loss: 0.019179726019501686
2023-01-21 12:22:42.571975: step: 112/531, loss: 0.0010495185852050781
2023-01-21 12:22:43.714211: step: 116/531, loss: 0.011016845703125
2023-01-21 12:22:44.860702: step: 120/531, loss: 0.16760531067848206
2023-01-21 12:22:45.994135: step: 124/531, loss: 0.0018293381435796618
2023-01-21 12:22:47.114421: step: 128/531, loss: 0.08307604491710663
2023-01-21 12:22:48.238564: step: 132/531, loss: 0.0032601356506347656
2023-01-21 12:22:49.364676: step: 136/531, loss: 0.0004682541184592992
2023-01-21 12:22:50.483297: step: 140/531, loss: 0.0013774872059002519
2023-01-21 12:22:51.614886: step: 144/531, loss: 0.00011558532423805445
2023-01-21 12:22:52.716052: step: 148/531, loss: 0.0033724785316735506
2023-01-21 12:22:53.839858: step: 152/531, loss: 0.00027179718017578125
2023-01-21 12:22:54.985783: step: 156/531, loss: 0.11645297706127167
2023-01-21 12:22:56.121689: step: 160/531, loss: 0.0010637283558025956
2023-01-21 12:22:57.228607: step: 164/531, loss: 0.0067164418287575245
2023-01-21 12:22:58.332133: step: 168/531, loss: 0.00036110877408646047
2023-01-21 12:22:59.498893: step: 172/531, loss: 0.014166069217026234
2023-01-21 12:23:00.617803: step: 176/531, loss: 9.822845458984375e-05
2023-01-21 12:23:01.746920: step: 180/531, loss: 0.08979358524084091
2023-01-21 12:23:02.893307: step: 184/531, loss: 0.0018795967334881425
2023-01-21 12:23:04.030999: step: 188/531, loss: 0.03762493282556534
2023-01-21 12:23:05.142947: step: 192/531, loss: 0.009085465222597122
2023-01-21 12:23:06.295778: step: 196/531, loss: 0.01636505126953125
2023-01-21 12:23:07.447313: step: 200/531, loss: 0.006860542576760054
2023-01-21 12:23:08.592710: step: 204/531, loss: 0.004508781712502241
2023-01-21 12:23:09.736433: step: 208/531, loss: 0.004056548699736595
2023-01-21 12:23:10.826755: step: 212/531, loss: 0.00035839079646393657
2023-01-21 12:23:11.990619: step: 216/531, loss: 0.00569496164098382
2023-01-21 12:23:13.111912: step: 220/531, loss: 0.0006122112390585244
2023-01-21 12:23:14.245896: step: 224/531, loss: 0.010429192334413528
2023-01-21 12:23:15.379713: step: 228/531, loss: 0.009557723999023438
2023-01-21 12:23:16.500853: step: 232/531, loss: 0.005618095397949219
2023-01-21 12:23:17.620362: step: 236/531, loss: 0.004314994905143976
2023-01-21 12:23:18.733103: step: 240/531, loss: 0.0004443645302671939
2023-01-21 12:23:19.873502: step: 244/531, loss: 0.0015382766723632812
2023-01-21 12:23:20.992501: step: 248/531, loss: 0.0931055098772049
2023-01-21 12:23:22.104067: step: 252/531, loss: 0.036287691444158554
2023-01-21 12:23:23.273530: step: 256/531, loss: 0.12040519714355469
2023-01-21 12:23:24.412521: step: 260/531, loss: 0.00010242462303722277
2023-01-21 12:23:25.515722: step: 264/531, loss: 0.016102219000458717
2023-01-21 12:23:26.619371: step: 268/531, loss: 0.009535598568618298
2023-01-21 12:23:27.730190: step: 272/531, loss: 0.00019993782916571945
2023-01-21 12:23:28.834789: step: 276/531, loss: 0.03116626851260662
2023-01-21 12:23:29.946045: step: 280/531, loss: 0.006656837649643421
2023-01-21 12:23:31.039780: step: 284/531, loss: 0.0061404225416481495
2023-01-21 12:23:32.211817: step: 288/531, loss: 0.04730252921581268
2023-01-21 12:23:33.356169: step: 292/531, loss: 0.044647980481386185
2023-01-21 12:23:34.480264: step: 296/531, loss: 0.04547290876507759
2023-01-21 12:23:35.608423: step: 300/531, loss: 0.012807703576982021
2023-01-21 12:23:36.739296: step: 304/531, loss: 0.0037442208267748356
2023-01-21 12:23:37.879820: step: 308/531, loss: 0.0045761107467114925
2023-01-21 12:23:39.004460: step: 312/531, loss: 0.03157777711749077
2023-01-21 12:23:40.140833: step: 316/531, loss: 0.002334976103156805
2023-01-21 12:23:41.281271: step: 320/531, loss: 0.005282497499138117
2023-01-21 12:23:42.448861: step: 324/531, loss: 0.03480219841003418
2023-01-21 12:23:43.573533: step: 328/531, loss: 0.0017469405429437757
2023-01-21 12:23:44.694007: step: 332/531, loss: 0.0015405655140057206
2023-01-21 12:23:45.832597: step: 336/531, loss: 9.860992577159777e-05
2023-01-21 12:23:46.974753: step: 340/531, loss: 0.0017723082564771175
2023-01-21 12:23:48.091431: step: 344/531, loss: 0.08843688666820526
2023-01-21 12:23:49.222772: step: 348/531, loss: 0.0003970146062783897
2023-01-21 12:23:50.356183: step: 352/531, loss: 8.964539119915571e-06
2023-01-21 12:23:51.517647: step: 356/531, loss: 0.00156402587890625
2023-01-21 12:23:52.646881: step: 360/531, loss: 0.0002193450927734375
2023-01-21 12:23:53.781121: step: 364/531, loss: 0.015962792560458183
2023-01-21 12:23:54.909956: step: 368/531, loss: 0.003342247102409601
2023-01-21 12:23:56.067831: step: 372/531, loss: 0.09523721039295197
2023-01-21 12:23:57.193504: step: 376/531, loss: -1.087188684323337e-05
2023-01-21 12:23:58.320450: step: 380/531, loss: 0.030991556122899055
2023-01-21 12:23:59.440335: step: 384/531, loss: 0.0007013797876425087
2023-01-21 12:24:00.543069: step: 388/531, loss: 0.00013599396334029734
2023-01-21 12:24:01.658904: step: 392/531, loss: 0.021628953516483307
2023-01-21 12:24:02.785956: step: 396/531, loss: 0.0026985169388353825
2023-01-21 12:24:03.877971: step: 400/531, loss: 0.000194549560546875
2023-01-21 12:24:04.999853: step: 404/531, loss: 0.0016930580604821444
2023-01-21 12:24:06.116520: step: 408/531, loss: 0.00022363662719726562
2023-01-21 12:24:07.254971: step: 412/531, loss: 0.003548908280208707
2023-01-21 12:24:08.397392: step: 416/531, loss: 0.22406716644763947
2023-01-21 12:24:09.503440: step: 420/531, loss: 0.037186816334724426
2023-01-21 12:24:10.635355: step: 424/531, loss: 0.00013580323138739914
2023-01-21 12:24:11.770821: step: 428/531, loss: 0.0006946563953533769
2023-01-21 12:24:12.873867: step: 432/531, loss: 1.602172778802924e-05
2023-01-21 12:24:14.019658: step: 436/531, loss: 0.03517146036028862
2023-01-21 12:24:15.146232: step: 440/531, loss: 0.018936539068818092
2023-01-21 12:24:16.289103: step: 444/531, loss: 0.028105545789003372
2023-01-21 12:24:17.407563: step: 448/531, loss: 0.0002340316859772429
2023-01-21 12:24:18.566910: step: 452/531, loss: 0.013898754492402077
2023-01-21 12:24:19.694609: step: 456/531, loss: 0.002858114195987582
2023-01-21 12:24:20.773983: step: 460/531, loss: 0.0003093719424214214
2023-01-21 12:24:21.920767: step: 464/531, loss: 0.0010966301197186112
2023-01-21 12:24:23.031142: step: 468/531, loss: 0.0002840042288880795
2023-01-21 12:24:24.189516: step: 472/531, loss: 0.01746678352355957
2023-01-21 12:24:25.329346: step: 476/531, loss: 0.012918663211166859
2023-01-21 12:24:26.460028: step: 480/531, loss: 0.0009792328346520662
2023-01-21 12:24:27.578584: step: 484/531, loss: 0.4155428111553192
2023-01-21 12:24:28.695497: step: 488/531, loss: 0.01971261575818062
2023-01-21 12:24:29.826148: step: 492/531, loss: 0.0010366439819335938
2023-01-21 12:24:30.941941: step: 496/531, loss: 0.00246009835973382
2023-01-21 12:24:32.092122: step: 500/531, loss: 0.0013407707447186112
2023-01-21 12:24:33.203045: step: 504/531, loss: 0.042410414665937424
2023-01-21 12:24:34.325379: step: 508/531, loss: 0.00012774467177223414
2023-01-21 12:24:35.465285: step: 512/531, loss: 0.035250473767519
2023-01-21 12:24:36.600560: step: 516/531, loss: 0.030462075024843216
2023-01-21 12:24:37.744223: step: 520/531, loss: 0.039939213544130325
2023-01-21 12:24:38.864629: step: 524/531, loss: 0.0749690979719162
2023-01-21 12:24:39.998545: step: 528/531, loss: 0.17607556283473969
2023-01-21 12:24:41.121107: step: 532/531, loss: 0.0008087158203125
2023-01-21 12:24:42.228140: step: 536/531, loss: 0.01723170280456543
2023-01-21 12:24:43.365387: step: 540/531, loss: 0.0003152370627503842
2023-01-21 12:24:44.494671: step: 544/531, loss: 0.03000025823712349
2023-01-21 12:24:45.590053: step: 548/531, loss: 0.0008251190301962197
2023-01-21 12:24:46.704584: step: 552/531, loss: 0.00015945434279274195
2023-01-21 12:24:47.825012: step: 556/531, loss: 0.028332805261015892
2023-01-21 12:24:48.989177: step: 560/531, loss: 0.0003824234299827367
2023-01-21 12:24:50.123745: step: 564/531, loss: 0.003098392393440008
2023-01-21 12:24:51.241788: step: 568/531, loss: 0.05826697498559952
2023-01-21 12:24:52.352161: step: 572/531, loss: 0.0016804696060717106
2023-01-21 12:24:53.506813: step: 576/531, loss: 0.6191143989562988
2023-01-21 12:24:54.645933: step: 580/531, loss: 0.011426257900893688
2023-01-21 12:24:55.753260: step: 584/531, loss: 0.010584450326859951
2023-01-21 12:24:56.862115: step: 588/531, loss: 0.07742176204919815
2023-01-21 12:24:57.990176: step: 592/531, loss: 0.0008602141751907766
2023-01-21 12:24:59.126537: step: 596/531, loss: 0.0007082939264364541
2023-01-21 12:25:00.243923: step: 600/531, loss: 0.017056941986083984
2023-01-21 12:25:01.396426: step: 604/531, loss: 0.00039281847421079874
2023-01-21 12:25:02.536201: step: 608/531, loss: 0.017569446936249733
2023-01-21 12:25:03.651442: step: 612/531, loss: 0.020808743312954903
2023-01-21 12:25:04.791716: step: 616/531, loss: 3.1042098271427676e-05
2023-01-21 12:25:05.886150: step: 620/531, loss: 0.003881740616634488
2023-01-21 12:25:07.006080: step: 624/531, loss: 0.014773941598832607
2023-01-21 12:25:08.128178: step: 628/531, loss: 0.04332322999835014
2023-01-21 12:25:09.272462: step: 632/531, loss: 0.033548545092344284
2023-01-21 12:25:10.420384: step: 636/531, loss: 0.0005468368763104081
2023-01-21 12:25:11.541258: step: 640/531, loss: 0.026336288079619408
2023-01-21 12:25:12.664473: step: 644/531, loss: 0.0011162757873535156
2023-01-21 12:25:13.791606: step: 648/531, loss: 0.026674319058656693
2023-01-21 12:25:14.932689: step: 652/531, loss: 0.003020334290340543
2023-01-21 12:25:16.039554: step: 656/531, loss: 0.0015174865256994963
2023-01-21 12:25:17.193169: step: 660/531, loss: 0.04860839992761612
2023-01-21 12:25:18.320819: step: 664/531, loss: 1.0395050594524946e-05
2023-01-21 12:25:19.422522: step: 668/531, loss: 0.0017058372031897306
2023-01-21 12:25:20.542765: step: 672/531, loss: 0.011866712011396885
2023-01-21 12:25:21.689844: step: 676/531, loss: 0.0011932372581213713
2023-01-21 12:25:22.797000: step: 680/531, loss: 0.0006091117975302041
2023-01-21 12:25:23.908067: step: 684/531, loss: 0.0790988951921463
2023-01-21 12:25:25.044551: step: 688/531, loss: 0.00023298263840842992
2023-01-21 12:25:26.209683: step: 692/531, loss: 0.00281696324236691
2023-01-21 12:25:27.332038: step: 696/531, loss: 0.000725269375834614
2023-01-21 12:25:28.440312: step: 700/531, loss: 0.0004669189511332661
2023-01-21 12:25:29.559559: step: 704/531, loss: 0.0002814293256960809
2023-01-21 12:25:30.684162: step: 708/531, loss: 0.0026995183434337378
2023-01-21 12:25:31.795734: step: 712/531, loss: 0.008170509710907936
2023-01-21 12:25:32.940086: step: 716/531, loss: 0.006976318545639515
2023-01-21 12:25:34.078049: step: 720/531, loss: 0.0005917549133300781
2023-01-21 12:25:35.180054: step: 724/531, loss: 4.882812572759576e-05
2023-01-21 12:25:36.320033: step: 728/531, loss: 0.0004124641418457031
2023-01-21 12:25:37.446926: step: 732/531, loss: 0.013591480441391468
2023-01-21 12:25:38.546681: step: 736/531, loss: 0.012377548962831497
2023-01-21 12:25:39.717676: step: 740/531, loss: 0.03476162254810333
2023-01-21 12:25:40.824041: step: 744/531, loss: 0.004398823250085115
2023-01-21 12:25:41.962935: step: 748/531, loss: 2.4604798454674892e-05
2023-01-21 12:25:43.098505: step: 752/531, loss: 0.013671494089066982
2023-01-21 12:25:44.219392: step: 756/531, loss: 0.0011943817371502519
2023-01-21 12:25:45.349426: step: 760/531, loss: 0.001507663750089705
2023-01-21 12:25:46.543227: step: 764/531, loss: 0.03401928022503853
2023-01-21 12:25:47.642071: step: 768/531, loss: 0.0713188648223877
2023-01-21 12:25:48.737468: step: 772/531, loss: 0.05470247566699982
2023-01-21 12:25:49.852124: step: 776/531, loss: 0.0004675865056924522
2023-01-21 12:25:50.951088: step: 780/531, loss: 7.171630568336695e-05
2023-01-21 12:25:52.115543: step: 784/531, loss: 0.03242187574505806
2023-01-21 12:25:53.242029: step: 788/531, loss: 0.058813001960515976
2023-01-21 12:25:54.365958: step: 792/531, loss: 4.472732325666584e-05
2023-01-21 12:25:55.481800: step: 796/531, loss: 0.0002915382501669228
2023-01-21 12:25:56.611824: step: 800/531, loss: 0.0014373778831213713
2023-01-21 12:25:57.734917: step: 804/531, loss: 2.2268297470873222e-05
2023-01-21 12:25:58.847878: step: 808/531, loss: 0.003915023989975452
2023-01-21 12:26:00.002276: step: 812/531, loss: 6.723403930664062e-05
2023-01-21 12:26:01.132836: step: 816/531, loss: 0.11374874413013458
2023-01-21 12:26:02.280414: step: 820/531, loss: 0.00211410503834486
2023-01-21 12:26:03.386641: step: 824/531, loss: 0.020637132227420807
2023-01-21 12:26:04.507591: step: 828/531, loss: 0.007857704535126686
2023-01-21 12:26:05.606523: step: 832/531, loss: 0.0005828857538290322
2023-01-21 12:26:06.724747: step: 836/531, loss: 0.0018834115471690893
2023-01-21 12:26:07.889835: step: 840/531, loss: 0.08020758628845215
2023-01-21 12:26:09.046733: step: 844/531, loss: 6.542205665027723e-05
2023-01-21 12:26:10.160071: step: 848/531, loss: 0.002821350237354636
2023-01-21 12:26:11.265231: step: 852/531, loss: 0.010622597299516201
2023-01-21 12:26:12.403803: step: 856/531, loss: 0.00035839079646393657
2023-01-21 12:26:13.502242: step: 860/531, loss: 0.05974989011883736
2023-01-21 12:26:14.662226: step: 864/531, loss: 0.0011190414661541581
2023-01-21 12:26:15.766039: step: 868/531, loss: 0.020493507385253906
2023-01-21 12:26:16.892632: step: 872/531, loss: 0.0014724732609465718
2023-01-21 12:26:18.008683: step: 876/531, loss: 0.013752556405961514
2023-01-21 12:26:19.168258: step: 880/531, loss: 0.1369609832763672
2023-01-21 12:26:20.273903: step: 884/531, loss: 0.00010938644845737144
2023-01-21 12:26:21.411767: step: 888/531, loss: 0.0010993957985192537
2023-01-21 12:26:22.536538: step: 892/531, loss: 0.3618907928466797
2023-01-21 12:26:23.650830: step: 896/531, loss: 0.0010310172801837325
2023-01-21 12:26:24.797015: step: 900/531, loss: 0.0013763427268713713
2023-01-21 12:26:25.908376: step: 904/531, loss: 0.00030961036100052297
2023-01-21 12:26:27.020769: step: 908/531, loss: 0.015498543158173561
2023-01-21 12:26:28.132561: step: 912/531, loss: 0.0022365569602698088
2023-01-21 12:26:29.287423: step: 916/531, loss: 0.00829381961375475
2023-01-21 12:26:30.420758: step: 920/531, loss: 0.00824518222361803
2023-01-21 12:26:31.552282: step: 924/531, loss: 0.00010433196439407766
2023-01-21 12:26:32.657929: step: 928/531, loss: 1.6498564946232364e-05
2023-01-21 12:26:33.762403: step: 932/531, loss: 0.0361081101000309
2023-01-21 12:26:34.865008: step: 936/531, loss: 0.0017801284557208419
2023-01-21 12:26:35.971455: step: 940/531, loss: 0.015580940060317516
2023-01-21 12:26:37.088701: step: 944/531, loss: 0.004696464631706476
2023-01-21 12:26:38.210719: step: 948/531, loss: 0.00025310515775345266
2023-01-21 12:26:39.337597: step: 952/531, loss: 0.051716484129428864
2023-01-21 12:26:40.476041: step: 956/531, loss: 0.0018837929237633944
2023-01-21 12:26:41.621612: step: 960/531, loss: 0.01030039880424738
2023-01-21 12:26:42.748690: step: 964/531, loss: 0.002150249434635043
2023-01-21 12:26:43.925176: step: 968/531, loss: 0.007288313005119562
2023-01-21 12:26:45.059681: step: 972/531, loss: 0.0005840301746502519
2023-01-21 12:26:46.195366: step: 976/531, loss: 0.0006574630970135331
2023-01-21 12:26:47.325088: step: 980/531, loss: 0.009013509377837181
2023-01-21 12:26:48.466523: step: 984/531, loss: 0.000600624131038785
2023-01-21 12:26:49.566336: step: 988/531, loss: 0.00046863555326126516
2023-01-21 12:26:50.674904: step: 992/531, loss: 0.0009137153974734247
2023-01-21 12:26:51.833875: step: 996/531, loss: 0.005797004792839289
2023-01-21 12:26:52.984657: step: 1000/531, loss: 0.0015172958374023438
2023-01-21 12:26:54.101807: step: 1004/531, loss: 0.030331803485751152
2023-01-21 12:26:55.219203: step: 1008/531, loss: 0.34022796154022217
2023-01-21 12:26:56.360041: step: 1012/531, loss: 0.00017375947209075093
2023-01-21 12:26:57.503652: step: 1016/531, loss: 0.00011119843111373484
2023-01-21 12:26:58.633177: step: 1020/531, loss: 0.025585317984223366
2023-01-21 12:26:59.762292: step: 1024/531, loss: 0.012732314877212048
2023-01-21 12:27:00.877364: step: 1028/531, loss: 0.014472484588623047
2023-01-21 12:27:02.032427: step: 1032/531, loss: 0.004925251007080078
2023-01-21 12:27:03.173089: step: 1036/531, loss: 0.012321091257035732
2023-01-21 12:27:04.315571: step: 1040/531, loss: 0.008662796579301357
2023-01-21 12:27:05.415815: step: 1044/531, loss: 0.0004496574401855469
2023-01-21 12:27:06.592056: step: 1048/531, loss: 0.0006292343023233116
2023-01-21 12:27:07.684699: step: 1052/531, loss: 0.011067581363022327
2023-01-21 12:27:08.808943: step: 1056/531, loss: 0.007999992929399014
2023-01-21 12:27:09.919804: step: 1060/531, loss: 1.3065338862361386e-05
2023-01-21 12:27:11.070792: step: 1064/531, loss: 0.007838821038603783
2023-01-21 12:27:12.218370: step: 1068/531, loss: 0.00381641392596066
2023-01-21 12:27:13.343173: step: 1072/531, loss: 0.0006130457040853798
2023-01-21 12:27:14.486407: step: 1076/531, loss: 6.65664701955393e-05
2023-01-21 12:27:15.603575: step: 1080/531, loss: -3.623962356869015e-06
2023-01-21 12:27:16.727857: step: 1084/531, loss: 0.005475044250488281
2023-01-21 12:27:17.838712: step: 1088/531, loss: 8.568763587391004e-05
2023-01-21 12:27:18.964981: step: 1092/531, loss: 0.006172323599457741
2023-01-21 12:27:20.085658: step: 1096/531, loss: 0.020245075225830078
2023-01-21 12:27:21.194474: step: 1100/531, loss: 0.0008183479658327997
2023-01-21 12:27:22.328286: step: 1104/531, loss: 0.03612127527594566
2023-01-21 12:27:23.472876: step: 1108/531, loss: 0.03242497146129608
2023-01-21 12:27:24.596364: step: 1112/531, loss: 0.0028014183044433594
2023-01-21 12:27:25.716874: step: 1116/531, loss: 0.001052951905876398
2023-01-21 12:27:26.856294: step: 1120/531, loss: 0.004205513279885054
2023-01-21 12:27:28.022976: step: 1124/531, loss: 0.01369323767721653
2023-01-21 12:27:29.159148: step: 1128/531, loss: 0.030561350286006927
2023-01-21 12:27:30.254340: step: 1132/531, loss: 0.009946252219378948
2023-01-21 12:27:31.385099: step: 1136/531, loss: 0.005287313833832741
2023-01-21 12:27:32.499336: step: 1140/531, loss: 0.002252006670460105
2023-01-21 12:27:33.611953: step: 1144/531, loss: 0.0007434844737872481
2023-01-21 12:27:34.718267: step: 1148/531, loss: 0.0003534912830218673
2023-01-21 12:27:35.827941: step: 1152/531, loss: 0.010028839111328125
2023-01-21 12:27:36.975552: step: 1156/531, loss: 0.003820228623226285
2023-01-21 12:27:38.115694: step: 1160/531, loss: 0.005708575714379549
2023-01-21 12:27:39.232174: step: 1164/531, loss: 0.0005479812389239669
2023-01-21 12:27:40.376772: step: 1168/531, loss: 0.0013969421852380037
2023-01-21 12:27:41.495438: step: 1172/531, loss: 0.002073001815006137
2023-01-21 12:27:42.612216: step: 1176/531, loss: 0.03377051651477814
2023-01-21 12:27:43.745158: step: 1180/531, loss: 0.1140756607055664
2023-01-21 12:27:44.875438: step: 1184/531, loss: 0.02752857282757759
2023-01-21 12:27:46.001687: step: 1188/531, loss: 0.03992490842938423
2023-01-21 12:27:47.122517: step: 1192/531, loss: 0.03566722944378853
2023-01-21 12:27:48.240207: step: 1196/531, loss: 0.08096656203269958
2023-01-21 12:27:49.376487: step: 1200/531, loss: 0.1128566786646843
2023-01-21 12:27:50.487424: step: 1204/531, loss: 0.00015373231144621968
2023-01-21 12:27:51.606541: step: 1208/531, loss: 0.0013044835068285465
2023-01-21 12:27:52.734830: step: 1212/531, loss: 0.002299833344295621
2023-01-21 12:27:53.858807: step: 1216/531, loss: 0.0016788482898846269
2023-01-21 12:27:54.987870: step: 1220/531, loss: 0.02349414862692356
2023-01-21 12:27:56.103927: step: 1224/531, loss: 0.002075767610222101
2023-01-21 12:27:57.229308: step: 1228/531, loss: 5.545616295421496e-05
2023-01-21 12:27:58.341816: step: 1232/531, loss: 0.00147924420889467
2023-01-21 12:27:59.439661: step: 1236/531, loss: 0.00024356841458939016
2023-01-21 12:28:00.569650: step: 1240/531, loss: 0.05311603471636772
2023-01-21 12:28:01.685428: step: 1244/531, loss: 0.0010235816007480025
2023-01-21 12:28:02.814537: step: 1248/531, loss: 0.0018507003551349044
2023-01-21 12:28:03.928994: step: 1252/531, loss: 0.00023155212693382055
2023-01-21 12:28:05.040558: step: 1256/531, loss: 0.0077453614212572575
2023-01-21 12:28:06.218015: step: 1260/531, loss: 0.00018708706193137914
2023-01-21 12:28:07.356721: step: 1264/531, loss: 0.002448654267936945
2023-01-21 12:28:08.498140: step: 1268/531, loss: 0.011070298962295055
2023-01-21 12:28:09.622195: step: 1272/531, loss: 0.00357818603515625
2023-01-21 12:28:10.758848: step: 1276/531, loss: 0.0006844520685262978
2023-01-21 12:28:11.889182: step: 1280/531, loss: 0.007412720005959272
2023-01-21 12:28:13.018743: step: 1284/531, loss: 0.018950367346405983
2023-01-21 12:28:14.150913: step: 1288/531, loss: 4.258155604475178e-05
2023-01-21 12:28:15.258892: step: 1292/531, loss: 0.02897520177066326
2023-01-21 12:28:16.380411: step: 1296/531, loss: 0.007234001066535711
2023-01-21 12:28:17.533116: step: 1300/531, loss: 0.09483995288610458
2023-01-21 12:28:18.675081: step: 1304/531, loss: 0.06255817413330078
2023-01-21 12:28:19.804125: step: 1308/531, loss: 0.00010280608694301918
2023-01-21 12:28:20.950107: step: 1312/531, loss: 0.004844760987907648
2023-01-21 12:28:22.057574: step: 1316/531, loss: 0.0015634536975994706
2023-01-21 12:28:23.186607: step: 1320/531, loss: 0.009601974859833717
2023-01-21 12:28:24.293605: step: 1324/531, loss: 0.005086708348244429
2023-01-21 12:28:25.473893: step: 1328/531, loss: 0.00031538010807707906
2023-01-21 12:28:26.613306: step: 1332/531, loss: 0.00020675659470725805
2023-01-21 12:28:27.701195: step: 1336/531, loss: 1.087188684323337e-05
2023-01-21 12:28:28.831548: step: 1340/531, loss: 0.005674839019775391
2023-01-21 12:28:29.974834: step: 1344/531, loss: 2.2983551389188506e-05
2023-01-21 12:28:31.099544: step: 1348/531, loss: 0.0052394866943359375
2023-01-21 12:28:32.218583: step: 1352/531, loss: 0.003440380096435547
2023-01-21 12:28:33.324798: step: 1356/531, loss: 0.10207786411046982
2023-01-21 12:28:34.470970: step: 1360/531, loss: 0.021319866180419922
2023-01-21 12:28:35.614199: step: 1364/531, loss: 0.0007732391823083162
2023-01-21 12:28:36.750994: step: 1368/531, loss: 0.009522723965346813
2023-01-21 12:28:37.881481: step: 1372/531, loss: 0.0037151335272938013
2023-01-21 12:28:39.029573: step: 1376/531, loss: 0.00010452270362293348
2023-01-21 12:28:40.152423: step: 1380/531, loss: 0.0198618546128273
2023-01-21 12:28:41.287439: step: 1384/531, loss: 0.0002891540643759072
2023-01-21 12:28:42.402233: step: 1388/531, loss: 0.02489948458969593
2023-01-21 12:28:43.499048: step: 1392/531, loss: 0.0014639378059655428
2023-01-21 12:28:44.609389: step: 1396/531, loss: 0.004904556553810835
2023-01-21 12:28:45.765787: step: 1400/531, loss: 0.004082775209099054
2023-01-21 12:28:46.900626: step: 1404/531, loss: 0.0001811981201171875
2023-01-21 12:28:48.010273: step: 1408/531, loss: 0.0020814896561205387
2023-01-21 12:28:49.142540: step: 1412/531, loss: 0.046598151326179504
2023-01-21 12:28:50.258696: step: 1416/531, loss: 3.5667417250806466e-05
2023-01-21 12:28:51.381153: step: 1420/531, loss: 0.04678173363208771
2023-01-21 12:28:52.482927: step: 1424/531, loss: 0.036341190338134766
2023-01-21 12:28:53.601886: step: 1428/531, loss: 0.013762093149125576
2023-01-21 12:28:54.750702: step: 1432/531, loss: 0.016721153631806374
2023-01-21 12:28:55.863656: step: 1436/531, loss: 0.013793754391372204
2023-01-21 12:28:56.987421: step: 1440/531, loss: 0.0004946708795614541
2023-01-21 12:28:58.107341: step: 1444/531, loss: 0.014902686700224876
2023-01-21 12:28:59.226259: step: 1448/531, loss: 0.004966163542121649
2023-01-21 12:29:00.346360: step: 1452/531, loss: 0.0028114321175962687
2023-01-21 12:29:01.502301: step: 1456/531, loss: 0.00023365020751953125
2023-01-21 12:29:02.680856: step: 1460/531, loss: 0.0013624191051349044
2023-01-21 12:29:03.817249: step: 1464/531, loss: 0.0048957825638353825
2023-01-21 12:29:04.977771: step: 1468/531, loss: 0.017310334369540215
2023-01-21 12:29:06.096732: step: 1472/531, loss: 0.00020084381685592234
2023-01-21 12:29:07.234964: step: 1476/531, loss: 2.202987889177166e-05
2023-01-21 12:29:08.359205: step: 1480/531, loss: 0.006887245457619429
2023-01-21 12:29:09.483493: step: 1484/531, loss: 0.0036351203452795744
2023-01-21 12:29:10.585259: step: 1488/531, loss: 0.0008919716347008944
2023-01-21 12:29:11.708057: step: 1492/531, loss: 1.4972686585679185e-05
2023-01-21 12:29:12.824835: step: 1496/531, loss: 0.00113677978515625
2023-01-21 12:29:13.940094: step: 1500/531, loss: 0.03809032589197159
2023-01-21 12:29:15.080742: step: 1504/531, loss: 5.149841672391631e-05
2023-01-21 12:29:16.208694: step: 1508/531, loss: 3.592967914300971e-05
2023-01-21 12:29:17.350954: step: 1512/531, loss: 0.00013780593872070312
2023-01-21 12:29:18.496866: step: 1516/531, loss: 0.0876707062125206
2023-01-21 12:29:19.645889: step: 1520/531, loss: 0.006524849217385054
2023-01-21 12:29:20.769409: step: 1524/531, loss: 0.0142395980656147
2023-01-21 12:29:21.916431: step: 1528/531, loss: 0.21990585327148438
2023-01-21 12:29:23.017532: step: 1532/531, loss: 0.05859050527215004
2023-01-21 12:29:24.126162: step: 1536/531, loss: 0.11898240447044373
2023-01-21 12:29:25.295132: step: 1540/531, loss: 0.023908233270049095
2023-01-21 12:29:26.442832: step: 1544/531, loss: 0.011330222710967064
2023-01-21 12:29:27.535735: step: 1548/531, loss: 0.0031680106185376644
2023-01-21 12:29:28.645630: step: 1552/531, loss: 0.0049527171067893505
2023-01-21 12:29:29.745419: step: 1556/531, loss: 0.013262081891298294
2023-01-21 12:29:30.911324: step: 1560/531, loss: 0.03152790293097496
2023-01-21 12:29:32.026923: step: 1564/531, loss: 0.005958748050034046
2023-01-21 12:29:33.161285: step: 1568/531, loss: 0.014830875210464
2023-01-21 12:29:34.276734: step: 1572/531, loss: 0.006167793646454811
2023-01-21 12:29:35.429629: step: 1576/531, loss: 0.006929779425263405
2023-01-21 12:29:36.543123: step: 1580/531, loss: 0.043218232691287994
2023-01-21 12:29:37.672977: step: 1584/531, loss: 0.04324054718017578
2023-01-21 12:29:38.807265: step: 1588/531, loss: 0.027252960950136185
2023-01-21 12:29:39.937038: step: 1592/531, loss: 0.004952907562255859
2023-01-21 12:29:41.053504: step: 1596/531, loss: 0.04693203419446945
2023-01-21 12:29:42.219887: step: 1600/531, loss: 0.0032629012130200863
2023-01-21 12:29:43.368042: step: 1604/531, loss: 0.004635715391486883
2023-01-21 12:29:44.497993: step: 1608/531, loss: 6.408691842807457e-05
2023-01-21 12:29:45.611257: step: 1612/531, loss: 0.0008629798539914191
2023-01-21 12:29:46.730805: step: 1616/531, loss: 0.0017566204769536853
2023-01-21 12:29:47.874525: step: 1620/531, loss: 0.026446105912327766
2023-01-21 12:29:49.018444: step: 1624/531, loss: 0.00035581589327193797
2023-01-21 12:29:50.147073: step: 1628/531, loss: 0.00023602842702530324
2023-01-21 12:29:51.250006: step: 1632/531, loss: 0.0008705139043740928
2023-01-21 12:29:52.391384: step: 1636/531, loss: 0.015746308490633965
2023-01-21 12:29:53.518633: step: 1640/531, loss: 0.0003379821719136089
2023-01-21 12:29:54.649534: step: 1644/531, loss: 0.0027925490867346525
2023-01-21 12:29:55.787409: step: 1648/531, loss: 0.022362733259797096
2023-01-21 12:29:56.930451: step: 1652/531, loss: 0.023240281268954277
2023-01-21 12:29:58.080180: step: 1656/531, loss: 0.00033321380033157766
2023-01-21 12:29:59.192912: step: 1660/531, loss: 4.062652442371473e-05
2023-01-21 12:30:00.345774: step: 1664/531, loss: 0.006613921839743853
2023-01-21 12:30:01.445456: step: 1668/531, loss: 0.0006512642139568925
2023-01-21 12:30:02.572584: step: 1672/531, loss: 0.0011952400673180819
2023-01-21 12:30:03.743778: step: 1676/531, loss: 0.0021736144553869963
2023-01-21 12:30:04.873233: step: 1680/531, loss: 0.0003326415899209678
2023-01-21 12:30:05.988173: step: 1684/531, loss: 0.0017589093185961246
2023-01-21 12:30:07.111650: step: 1688/531, loss: 0.022540735080838203
2023-01-21 12:30:08.211979: step: 1692/531, loss: 0.0006381988641805947
2023-01-21 12:30:09.331835: step: 1696/531, loss: 0.0010938644409179688
2023-01-21 12:30:10.467649: step: 1700/531, loss: 0.04744997248053551
2023-01-21 12:30:11.609792: step: 1704/531, loss: 0.006247234530746937
2023-01-21 12:30:12.751782: step: 1708/531, loss: 0.028505802154541016
2023-01-21 12:30:13.847339: step: 1712/531, loss: 0.004985189530998468
2023-01-21 12:30:14.981306: step: 1716/531, loss: 0.0009893417591229081
2023-01-21 12:30:16.106437: step: 1720/531, loss: 0.008517075330018997
2023-01-21 12:30:17.209157: step: 1724/531, loss: 0.010876084677875042
2023-01-21 12:30:18.335705: step: 1728/531, loss: 0.05873575061559677
2023-01-21 12:30:19.469634: step: 1732/531, loss: 0.0022992135491222143
2023-01-21 12:30:20.586459: step: 1736/531, loss: 0.013177204877138138
2023-01-21 12:30:21.721571: step: 1740/531, loss: 0.002798366593196988
2023-01-21 12:30:22.834100: step: 1744/531, loss: 0.002790260361507535
2023-01-21 12:30:23.958042: step: 1748/531, loss: 0.012932490557432175
2023-01-21 12:30:25.064768: step: 1752/531, loss: 0.012326211668550968
2023-01-21 12:30:26.178891: step: 1756/531, loss: 0.0008872032631188631
2023-01-21 12:30:27.330409: step: 1760/531, loss: 0.010002708993852139
2023-01-21 12:30:28.418187: step: 1764/531, loss: 0.0005664349300786853
2023-01-21 12:30:29.534824: step: 1768/531, loss: 0.003896522568538785
2023-01-21 12:30:30.643803: step: 1772/531, loss: 0.008837461471557617
2023-01-21 12:30:31.750998: step: 1776/531, loss: 0.01585855334997177
2023-01-21 12:30:32.866321: step: 1780/531, loss: 0.002283334732055664
2023-01-21 12:30:34.018019: step: 1784/531, loss: 0.03453655168414116
2023-01-21 12:30:35.166554: step: 1788/531, loss: 0.043459560722112656
2023-01-21 12:30:36.290789: step: 1792/531, loss: 0.033576298505067825
2023-01-21 12:30:37.416290: step: 1796/531, loss: 4.062652442371473e-05
2023-01-21 12:30:38.552154: step: 1800/531, loss: 0.009509564377367496
2023-01-21 12:30:39.637976: step: 1804/531, loss: 0.0009515762212686241
2023-01-21 12:30:40.771159: step: 1808/531, loss: 0.005295086186379194
2023-01-21 12:30:41.888675: step: 1812/531, loss: 0.10067968815565109
2023-01-21 12:30:42.988381: step: 1816/531, loss: 0.0003171921125613153
2023-01-21 12:30:44.083966: step: 1820/531, loss: 0.03629465028643608
2023-01-21 12:30:45.196761: step: 1824/531, loss: 0.0012722969986498356
2023-01-21 12:30:46.322480: step: 1828/531, loss: 0.013050603680312634
2023-01-21 12:30:47.456599: step: 1832/531, loss: 0.1384061872959137
2023-01-21 12:30:48.602600: step: 1836/531, loss: 0.14968930184841156
2023-01-21 12:30:49.730151: step: 1840/531, loss: 0.0395696684718132
2023-01-21 12:30:50.846721: step: 1844/531, loss: 2.6988982426701114e-05
2023-01-21 12:30:51.991128: step: 1848/531, loss: 0.4747430384159088
2023-01-21 12:30:53.105066: step: 1852/531, loss: 0.006366729736328125
2023-01-21 12:30:54.243519: step: 1856/531, loss: 7.24792471373803e-06
2023-01-21 12:30:55.358747: step: 1860/531, loss: 0.0019212722545489669
2023-01-21 12:30:56.478363: step: 1864/531, loss: 0.018688775599002838
2023-01-21 12:30:57.579567: step: 1868/531, loss: 6.561278860317543e-05
2023-01-21 12:30:58.695002: step: 1872/531, loss: 1.4591218132409267e-05
2023-01-21 12:30:59.794100: step: 1876/531, loss: 0.0025844573974609375
2023-01-21 12:31:00.900382: step: 1880/531, loss: 0.0009521484607830644
2023-01-21 12:31:02.045164: step: 1884/531, loss: 0.0005189895164221525
2023-01-21 12:31:03.146438: step: 1888/531, loss: 0.03042163886129856
2023-01-21 12:31:04.255348: step: 1892/531, loss: 0.0009130955440923572
2023-01-21 12:31:05.373258: step: 1896/531, loss: 0.03568878397345543
2023-01-21 12:31:06.489792: step: 1900/531, loss: 0.0004989624139852822
2023-01-21 12:31:07.619044: step: 1904/531, loss: 0.0001180648832814768
2023-01-21 12:31:08.743900: step: 1908/531, loss: 0.000634050345979631
2023-01-21 12:31:09.892828: step: 1912/531, loss: 0.002976703690364957
2023-01-21 12:31:11.023699: step: 1916/531, loss: 0.0048653604462742805
2023-01-21 12:31:12.165679: step: 1920/531, loss: 0.00113849644549191
2023-01-21 12:31:13.290101: step: 1924/531, loss: 0.00011630058725131676
2023-01-21 12:31:14.404330: step: 1928/531, loss: 0.003735160920768976
2023-01-21 12:31:15.551718: step: 1932/531, loss: 0.00038471221341751516
2023-01-21 12:31:16.672054: step: 1936/531, loss: 0.01751251146197319
2023-01-21 12:31:17.789519: step: 1940/531, loss: 0.0010505676036700606
2023-01-21 12:31:18.938484: step: 1944/531, loss: 0.0010538101196289062
2023-01-21 12:31:20.063241: step: 1948/531, loss: 0.09430637210607529
2023-01-21 12:31:21.185543: step: 1952/531, loss: 0.006407737731933594
2023-01-21 12:31:22.288721: step: 1956/531, loss: 0.015543365851044655
2023-01-21 12:31:23.422067: step: 1960/531, loss: 0.0006081700557842851
2023-01-21 12:31:24.536922: step: 1964/531, loss: 0.0005928039317950606
2023-01-21 12:31:25.665288: step: 1968/531, loss: 0.03567361831665039
2023-01-21 12:31:26.777356: step: 1972/531, loss: 0.03439774364233017
2023-01-21 12:31:27.902651: step: 1976/531, loss: 0.00010366439528297633
2023-01-21 12:31:29.002579: step: 1980/531, loss: 0.015834618359804153
2023-01-21 12:31:30.143437: step: 1984/531, loss: 0.002125310944393277
2023-01-21 12:31:31.298351: step: 1988/531, loss: 4.9591064453125e-05
2023-01-21 12:31:32.457329: step: 1992/531, loss: 0.0073604583740234375
2023-01-21 12:31:33.589496: step: 1996/531, loss: 0.004454994108527899
2023-01-21 12:31:34.740688: step: 2000/531, loss: 0.024219512939453125
2023-01-21 12:31:35.878407: step: 2004/531, loss: 0.0023954391945153475
2023-01-21 12:31:37.027002: step: 2008/531, loss: 0.02621944062411785
2023-01-21 12:31:38.150016: step: 2012/531, loss: 0.006780100055038929
2023-01-21 12:31:39.268023: step: 2016/531, loss: 0.1432262510061264
2023-01-21 12:31:40.413656: step: 2020/531, loss: 0.04514102637767792
2023-01-21 12:31:41.544849: step: 2024/531, loss: 0.02908172644674778
2023-01-21 12:31:42.640427: step: 2028/531, loss: 2.956390380859375e-05
2023-01-21 12:31:43.741469: step: 2032/531, loss: 0.00086126325186342
2023-01-21 12:31:44.837202: step: 2036/531, loss: 0.3446231782436371
2023-01-21 12:31:45.971045: step: 2040/531, loss: 4.768380676978268e-07
2023-01-21 12:31:47.085967: step: 2044/531, loss: 0.0012499808799475431
2023-01-21 12:31:48.215544: step: 2048/531, loss: 1.2969970157428179e-05
2023-01-21 12:31:49.338588: step: 2052/531, loss: 0.0001203536958200857
2023-01-21 12:31:50.465904: step: 2056/531, loss: 0.0004585743008647114
2023-01-21 12:31:51.557648: step: 2060/531, loss: 0.005822944920510054
2023-01-21 12:31:52.680215: step: 2064/531, loss: 0.00727424630895257
2023-01-21 12:31:53.795454: step: 2068/531, loss: 0.00022459030151367188
2023-01-21 12:31:54.904962: step: 2072/531, loss: 0.015064621344208717
2023-01-21 12:31:56.005557: step: 2076/531, loss: 0.025440121069550514
2023-01-21 12:31:57.128372: step: 2080/531, loss: 0.002681923098862171
2023-01-21 12:31:58.245745: step: 2084/531, loss: 0.007973670959472656
2023-01-21 12:31:59.366327: step: 2088/531, loss: 0.0054111480712890625
2023-01-21 12:32:00.491222: step: 2092/531, loss: 0.03980541229248047
2023-01-21 12:32:01.644038: step: 2096/531, loss: 0.02603158913552761
2023-01-21 12:32:02.788928: step: 2100/531, loss: 0.0002674102724995464
2023-01-21 12:32:03.940077: step: 2104/531, loss: 0.0009061813470907509
2023-01-21 12:32:05.041423: step: 2108/531, loss: 0.00402336148545146
2023-01-21 12:32:06.144626: step: 2112/531, loss: 0.0015176773304119706
2023-01-21 12:32:07.302265: step: 2116/531, loss: 0.00011763573274947703
2023-01-21 12:32:08.395844: step: 2120/531, loss: 0.00029010773869231343
2023-01-21 12:32:09.526529: step: 2124/531, loss: 0.5303184390068054
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.5696324951644101, 'r': 0.7842876165113183, 'f1': 0.6599439775910365}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6037906137184116, 'r': 0.7978533094812165, 'f1': 0.6873876188029797}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5333333333333333, 'r': 0.8888888888888888, 'f1': 0.6666666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.631578947368421, 'r': 0.5714285714285714, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.3488372093023256, 'r': 0.4166666666666667, 'f1': 0.379746835443038}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 23
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:32:49.988953: step: 4/531, loss: 0.014155960641801357
2023-01-21 12:32:51.101092: step: 8/531, loss: 0.018351102247834206
2023-01-21 12:32:52.243555: step: 12/531, loss: 0.00032978056697174907
2023-01-21 12:32:53.354717: step: 16/531, loss: 1.697540210443549e-05
2023-01-21 12:32:54.502974: step: 20/531, loss: 0.0007347107166424394
2023-01-21 12:32:55.643072: step: 24/531, loss: 0.003898429684340954
2023-01-21 12:32:56.772015: step: 28/531, loss: 0.004001712426543236
2023-01-21 12:32:57.889154: step: 32/531, loss: 0.00012407303438521922
2023-01-21 12:32:59.021913: step: 36/531, loss: 0.0002633094845805317
2023-01-21 12:33:00.157852: step: 40/531, loss: 0.01026611402630806
2023-01-21 12:33:01.267083: step: 44/531, loss: 0.009000015445053577
2023-01-21 12:33:02.403157: step: 48/531, loss: 0.001984548754990101
2023-01-21 12:33:03.527457: step: 52/531, loss: 0.009127807803452015
2023-01-21 12:33:04.665679: step: 56/531, loss: 0.01872711256146431
2023-01-21 12:33:05.795661: step: 60/531, loss: 0.005709266755729914
2023-01-21 12:33:06.930032: step: 64/531, loss: 0.0011022568214684725
2023-01-21 12:33:08.058137: step: 68/531, loss: 0.013421153649687767
2023-01-21 12:33:09.181930: step: 72/531, loss: 0.01851673237979412
2023-01-21 12:33:10.322346: step: 76/531, loss: 1.773834264895413e-05
2023-01-21 12:33:11.433653: step: 80/531, loss: 0.0001794815034372732
2023-01-21 12:33:12.548322: step: 84/531, loss: 0.0006766319274902344
2023-01-21 12:33:13.686961: step: 88/531, loss: 0.019933607429265976
2023-01-21 12:33:14.810622: step: 92/531, loss: 0.0012557983864098787
2023-01-21 12:33:15.957349: step: 96/531, loss: 0.0032648087944835424
2023-01-21 12:33:17.077830: step: 100/531, loss: 0.0245832446962595
2023-01-21 12:33:18.189342: step: 104/531, loss: 0.1237730011343956
2023-01-21 12:33:19.335987: step: 108/531, loss: 0.14036230742931366
2023-01-21 12:33:20.495536: step: 112/531, loss: 0.0012830734485760331
2023-01-21 12:33:21.640639: step: 116/531, loss: 0.007854461669921875
2023-01-21 12:33:22.775480: step: 120/531, loss: 8.525848534191027e-05
2023-01-21 12:33:23.922230: step: 124/531, loss: 0.08302974700927734
2023-01-21 12:33:25.052297: step: 128/531, loss: 0.013432217761874199
2023-01-21 12:33:26.217860: step: 132/531, loss: 0.0020078658126294613
2023-01-21 12:33:27.357990: step: 136/531, loss: 0.019022800028324127
2023-01-21 12:33:28.500625: step: 140/531, loss: 0.011188602074980736
2023-01-21 12:33:29.622442: step: 144/531, loss: 0.03532681614160538
2023-01-21 12:33:30.731188: step: 148/531, loss: 1.468658410885837e-05
2023-01-21 12:33:31.842122: step: 152/531, loss: 0.08642387390136719
2023-01-21 12:33:32.964271: step: 156/531, loss: 0.0011396408081054688
2023-01-21 12:33:34.090005: step: 160/531, loss: 0.01595134660601616
2023-01-21 12:33:35.207373: step: 164/531, loss: 0.005595779977738857
2023-01-21 12:33:36.332430: step: 168/531, loss: 0.0075889588333666325
2023-01-21 12:33:37.447973: step: 172/531, loss: 0.0066123963333666325
2023-01-21 12:33:38.585329: step: 176/531, loss: 0.212663933634758
2023-01-21 12:33:39.734598: step: 180/531, loss: 0.02056121826171875
2023-01-21 12:33:40.853246: step: 184/531, loss: 0.0004181861877441406
2023-01-21 12:33:41.963860: step: 188/531, loss: 0.0013456344604492188
2023-01-21 12:33:43.090486: step: 192/531, loss: 0.0006208419799804688
2023-01-21 12:33:44.195024: step: 196/531, loss: 4.951202392578125
2023-01-21 12:33:45.315342: step: 200/531, loss: 0.018161773681640625
2023-01-21 12:33:46.438288: step: 204/531, loss: 0.0003700733359437436
2023-01-21 12:33:47.568141: step: 208/531, loss: 0.003593635745346546
2023-01-21 12:33:48.716409: step: 212/531, loss: 0.000194549560546875
2023-01-21 12:33:49.841150: step: 216/531, loss: 0.0006067276117391884
2023-01-21 12:33:50.965867: step: 220/531, loss: 0.03721323236823082
2023-01-21 12:33:52.092285: step: 224/531, loss: 0.03303928300738335
2023-01-21 12:33:53.221938: step: 228/531, loss: 0.004172325599938631
2023-01-21 12:33:54.326351: step: 232/531, loss: 0.006166363134980202
2023-01-21 12:33:55.450085: step: 236/531, loss: 5.531310307560489e-06
2023-01-21 12:33:56.571043: step: 240/531, loss: 0.00019979476928710938
2023-01-21 12:33:57.713703: step: 244/531, loss: 8.292197890114039e-05
2023-01-21 12:33:58.901670: step: 248/531, loss: 0.013271713629364967
2023-01-21 12:34:00.018304: step: 252/531, loss: 6.28471389063634e-05
2023-01-21 12:34:01.154978: step: 256/531, loss: 0.005969524849206209
2023-01-21 12:34:02.296583: step: 260/531, loss: 0.015056610107421875
2023-01-21 12:34:03.428614: step: 264/531, loss: 0.0005757331382483244
2023-01-21 12:34:04.584155: step: 268/531, loss: 0.00018186570378020406
2023-01-21 12:34:05.696351: step: 272/531, loss: 0.00077228550799191
2023-01-21 12:34:06.829553: step: 276/531, loss: 0.0010875702137127519
2023-01-21 12:34:08.016138: step: 280/531, loss: 5.3215029765851796e-05
2023-01-21 12:34:09.184946: step: 284/531, loss: 0.01006469689309597
2023-01-21 12:34:10.309069: step: 288/531, loss: 0.048592664301395416
2023-01-21 12:34:11.436643: step: 292/531, loss: 0.00031981468782760203
2023-01-21 12:34:12.553462: step: 296/531, loss: -9.34600848268019e-06
2023-01-21 12:34:13.699090: step: 300/531, loss: 5.426407005870715e-05
2023-01-21 12:34:14.822617: step: 304/531, loss: 0.0022500993218272924
2023-01-21 12:34:15.958954: step: 308/531, loss: 0.0005060672992840409
2023-01-21 12:34:17.115148: step: 312/531, loss: 0.0074062347412109375
2023-01-21 12:34:18.264233: step: 316/531, loss: 0.03669862449169159
2023-01-21 12:34:19.368092: step: 320/531, loss: 0.0012549400562420487
2023-01-21 12:34:20.487334: step: 324/531, loss: 0.0030506134498864412
2023-01-21 12:34:21.602156: step: 328/531, loss: 0.0025323869194835424
2023-01-21 12:34:22.727963: step: 332/531, loss: 0.00105448963586241
2023-01-21 12:34:23.866633: step: 336/531, loss: 0.007851219736039639
2023-01-21 12:34:24.975081: step: 340/531, loss: 0.0020708085503429174
2023-01-21 12:34:26.062157: step: 344/531, loss: 0.0003681182861328125
2023-01-21 12:34:27.155873: step: 348/531, loss: 0.0027888298500329256
2023-01-21 12:34:28.295669: step: 352/531, loss: 5.2070619858568534e-05
2023-01-21 12:34:29.454944: step: 356/531, loss: 0.0018109322991222143
2023-01-21 12:34:30.595749: step: 360/531, loss: 8.678436643094756e-06
2023-01-21 12:34:31.708318: step: 364/531, loss: 0.08064880967140198
2023-01-21 12:34:32.839525: step: 368/531, loss: 0.02924184873700142
2023-01-21 12:34:33.971182: step: 372/531, loss: 0.0004991531604900956
2023-01-21 12:34:35.107808: step: 376/531, loss: 0.004985904786735773
2023-01-21 12:34:36.233742: step: 380/531, loss: 0.004901027772575617
2023-01-21 12:34:37.317126: step: 384/531, loss: 0.0015162467025220394
2023-01-21 12:34:38.454298: step: 388/531, loss: 0.0005450248718261719
2023-01-21 12:34:39.545377: step: 392/531, loss: 0.00048251153202727437
2023-01-21 12:34:40.672462: step: 396/531, loss: 0.000983762787654996
2023-01-21 12:34:41.831930: step: 400/531, loss: 0.00043621062650345266
2023-01-21 12:34:42.968075: step: 404/531, loss: 0.00012392997450660914
2023-01-21 12:34:44.084586: step: 408/531, loss: 0.03224897384643555
2023-01-21 12:34:45.187559: step: 412/531, loss: 0.0037012577522546053
2023-01-21 12:34:46.358406: step: 416/531, loss: 0.05334148555994034
2023-01-21 12:34:47.489141: step: 420/531, loss: 0.0002004623383982107
2023-01-21 12:34:48.601766: step: 424/531, loss: 0.038133811205625534
2023-01-21 12:34:49.730172: step: 428/531, loss: 0.009861373342573643
2023-01-21 12:34:50.859167: step: 432/531, loss: 0.004862594418227673
2023-01-21 12:34:51.974419: step: 436/531, loss: 0.0012729645241051912
2023-01-21 12:34:53.070662: step: 440/531, loss: 4.901886131847277e-05
2023-01-21 12:34:54.214770: step: 444/531, loss: 0.00227947230450809
2023-01-21 12:34:55.332651: step: 448/531, loss: 0.0020626068580895662
2023-01-21 12:34:56.447372: step: 452/531, loss: 0.0050210957415401936
2023-01-21 12:34:57.555451: step: 456/531, loss: 0.00011596680269576609
2023-01-21 12:34:58.699856: step: 460/531, loss: 0.0012561798794195056
2023-01-21 12:34:59.816334: step: 464/531, loss: 1.9073486328125e-05
2023-01-21 12:35:00.960613: step: 468/531, loss: 0.2448255568742752
2023-01-21 12:35:02.086501: step: 472/531, loss: 0.0027361870743334293
2023-01-21 12:35:03.199213: step: 476/531, loss: 0.0004818916495423764
2023-01-21 12:35:04.307076: step: 480/531, loss: 0.03991289436817169
2023-01-21 12:35:05.433396: step: 484/531, loss: 0.011562966741621494
2023-01-21 12:35:06.592007: step: 488/531, loss: 0.015391826629638672
2023-01-21 12:35:07.693657: step: 492/531, loss: 0.02075357548892498
2023-01-21 12:35:08.834018: step: 496/531, loss: 0.23147784173488617
2023-01-21 12:35:09.998020: step: 500/531, loss: 0.0007053375011309981
2023-01-21 12:35:11.104380: step: 504/531, loss: 0.08710562437772751
2023-01-21 12:35:12.241528: step: 508/531, loss: 0.00012264252291060984
2023-01-21 12:35:13.353202: step: 512/531, loss: 0.00115547189489007
2023-01-21 12:35:14.454899: step: 516/531, loss: 0.006896304897964001
2023-01-21 12:35:15.580613: step: 520/531, loss: 0.02773761935532093
2023-01-21 12:35:16.719349: step: 524/531, loss: 0.001696634222753346
2023-01-21 12:35:17.845748: step: 528/531, loss: 0.00768699636682868
2023-01-21 12:35:18.989775: step: 532/531, loss: 0.05229339748620987
2023-01-21 12:35:20.116051: step: 536/531, loss: 0.05944023281335831
2023-01-21 12:35:21.285651: step: 540/531, loss: 0.0003666877746582031
2023-01-21 12:35:22.411554: step: 544/531, loss: 0.0038587572053074837
2023-01-21 12:35:23.514823: step: 548/531, loss: 0.0013689040206372738
2023-01-21 12:35:24.615695: step: 552/531, loss: 2.517700158932712e-05
2023-01-21 12:35:25.732693: step: 556/531, loss: 0.018257809802889824
2023-01-21 12:35:26.851724: step: 560/531, loss: 3.471374657237902e-05
2023-01-21 12:35:27.974150: step: 564/531, loss: 0.0005690574762411416
2023-01-21 12:35:29.121259: step: 568/531, loss: 0.6041606664657593
2023-01-21 12:35:30.258458: step: 572/531, loss: 0.05984220653772354
2023-01-21 12:35:31.395878: step: 576/531, loss: 0.005154419224709272
2023-01-21 12:35:32.529906: step: 580/531, loss: 0.001689910888671875
2023-01-21 12:35:33.681918: step: 584/531, loss: 0.016596509143710136
2023-01-21 12:35:34.833645: step: 588/531, loss: 0.0020378590561449528
2023-01-21 12:35:35.971198: step: 592/531, loss: 0.10165248066186905
2023-01-21 12:35:37.080403: step: 596/531, loss: 0.002917909761890769
2023-01-21 12:35:38.208341: step: 600/531, loss: 0.0006826877943240106
2023-01-21 12:35:39.323032: step: 604/531, loss: 2.4557113647460938e-05
2023-01-21 12:35:40.456206: step: 608/531, loss: 6.86645489622606e-06
2023-01-21 12:35:41.567897: step: 612/531, loss: 8.869171324477065e-06
2023-01-21 12:35:42.736975: step: 616/531, loss: 0.0009454727405682206
2023-01-21 12:35:43.877040: step: 620/531, loss: 0.0007668494945392013
2023-01-21 12:35:45.012099: step: 624/531, loss: 0.00785064697265625
2023-01-21 12:35:46.168150: step: 628/531, loss: 0.011459732428193092
2023-01-21 12:35:47.291592: step: 632/531, loss: 0.0004564285627566278
2023-01-21 12:35:48.411613: step: 636/531, loss: 0.0001750946103129536
2023-01-21 12:35:49.545906: step: 640/531, loss: 7.734298560535535e-05
2023-01-21 12:35:50.662253: step: 644/531, loss: 0.0006910323863849044
2023-01-21 12:35:51.852503: step: 648/531, loss: 0.008035564795136452
2023-01-21 12:35:52.981860: step: 652/531, loss: 0.0004639625549316406
2023-01-21 12:35:54.138528: step: 656/531, loss: 0.0037055970169603825
2023-01-21 12:35:55.256059: step: 660/531, loss: 0.019382189959287643
2023-01-21 12:35:56.399492: step: 664/531, loss: 0.001360177993774414
2023-01-21 12:35:57.514014: step: 668/531, loss: 0.06304216384887695
2023-01-21 12:35:58.668949: step: 672/531, loss: 0.06542596966028214
2023-01-21 12:35:59.812093: step: 676/531, loss: 0.00964651070535183
2023-01-21 12:36:00.942753: step: 680/531, loss: 0.0011067390441894531
2023-01-21 12:36:02.064601: step: 684/531, loss: 0.00021018982806708664
2023-01-21 12:36:03.182843: step: 688/531, loss: 0.0006690978771075606
2023-01-21 12:36:04.300661: step: 692/531, loss: 0.011448478326201439
2023-01-21 12:36:05.400532: step: 696/531, loss: 0.00011162758164573461
2023-01-21 12:36:06.514505: step: 700/531, loss: 0.009367180056869984
2023-01-21 12:36:07.653662: step: 704/531, loss: 0.011383724398911
2023-01-21 12:36:08.803127: step: 708/531, loss: 0.003972912207245827
2023-01-21 12:36:09.933582: step: 712/531, loss: 0.00030007364694029093
2023-01-21 12:36:11.052221: step: 716/531, loss: 0.00017089843458961695
2023-01-21 12:36:12.209968: step: 720/531, loss: 0.00745391845703125
2023-01-21 12:36:13.327535: step: 724/531, loss: 0.016063308343291283
2023-01-21 12:36:14.468917: step: 728/531, loss: 0.0016088485717773438
2023-01-21 12:36:15.614559: step: 732/531, loss: 0.03598365560173988
2023-01-21 12:36:16.745546: step: 736/531, loss: 0.010575485415756702
2023-01-21 12:36:17.885724: step: 740/531, loss: 2.5558472771081142e-05
2023-01-21 12:36:19.013782: step: 744/531, loss: 0.05165262147784233
2023-01-21 12:36:20.138590: step: 748/531, loss: 1.792907642084174e-05
2023-01-21 12:36:21.257792: step: 752/531, loss: 0.0004368305380921811
2023-01-21 12:36:22.476293: step: 756/531, loss: 0.0033084868919104338
2023-01-21 12:36:23.606502: step: 760/531, loss: 0.028829099610447884
2023-01-21 12:36:24.742671: step: 764/531, loss: 7.567405555164441e-05
2023-01-21 12:36:25.874571: step: 768/531, loss: 0.00034708977909758687
2023-01-21 12:36:27.054998: step: 772/531, loss: 0.0001330375816905871
2023-01-21 12:36:28.180807: step: 776/531, loss: -5.662441253662109e-06
2023-01-21 12:36:29.313166: step: 780/531, loss: 0.0021949768997728825
2023-01-21 12:36:30.427691: step: 784/531, loss: 0.017023611813783646
2023-01-21 12:36:31.568201: step: 788/531, loss: 0.00017278196173720062
2023-01-21 12:36:32.676448: step: 792/531, loss: 0.00433616666123271
2023-01-21 12:36:33.776078: step: 796/531, loss: 0.023058509454131126
2023-01-21 12:36:34.915187: step: 800/531, loss: 4.8351288569392636e-05
2023-01-21 12:36:36.047196: step: 804/531, loss: 0.004530906677246094
2023-01-21 12:36:37.153242: step: 808/531, loss: 0.0002655029238667339
2023-01-21 12:36:38.298038: step: 812/531, loss: 0.005262470338493586
2023-01-21 12:36:39.447159: step: 816/531, loss: 0.0008194923866540194
2023-01-21 12:36:40.597936: step: 820/531, loss: 7.915496826171875e-05
2023-01-21 12:36:41.721870: step: 824/531, loss: 0.0032746316865086555
2023-01-21 12:36:42.847308: step: 828/531, loss: 0.002218961948528886
2023-01-21 12:36:43.974792: step: 832/531, loss: 0.0012674331665039062
2023-01-21 12:36:45.078122: step: 836/531, loss: -2.956390289909905e-06
2023-01-21 12:36:46.234448: step: 840/531, loss: 0.0005959570407867432
2023-01-21 12:36:47.361393: step: 844/531, loss: 4.920959327137098e-05
2023-01-21 12:36:48.488482: step: 848/531, loss: 0.003874874208122492
2023-01-21 12:36:49.619986: step: 852/531, loss: 0.03710046038031578
2023-01-21 12:36:50.734650: step: 856/531, loss: 0.40577390789985657
2023-01-21 12:36:51.882470: step: 860/531, loss: 0.009037780575454235
2023-01-21 12:36:52.999748: step: 864/531, loss: 0.0011695862049236894
2023-01-21 12:36:54.108498: step: 868/531, loss: 0.0027116776909679174
2023-01-21 12:36:55.247650: step: 872/531, loss: 0.008507300168275833
2023-01-21 12:36:56.331134: step: 876/531, loss: 0.0006824493175372481
2023-01-21 12:36:57.434361: step: 880/531, loss: 5.216598219703883e-05
2023-01-21 12:36:58.566521: step: 884/531, loss: 0.002790260361507535
2023-01-21 12:36:59.698297: step: 888/531, loss: 0.001773834228515625
2023-01-21 12:37:00.816863: step: 892/531, loss: 0.0009116172441281378
2023-01-21 12:37:01.935376: step: 896/531, loss: 0.006837082095444202
2023-01-21 12:37:03.038906: step: 900/531, loss: 6.69479341013357e-05
2023-01-21 12:37:04.143939: step: 904/531, loss: 0.009524155408143997
2023-01-21 12:37:05.276498: step: 908/531, loss: 0.0004962921375408769
2023-01-21 12:37:06.429244: step: 912/531, loss: 0.0024506093468517065
2023-01-21 12:37:07.580022: step: 916/531, loss: 0.010242462158203125
2023-01-21 12:37:08.699958: step: 920/531, loss: 0.0008728028042241931
2023-01-21 12:37:09.822947: step: 924/531, loss: 0.04297580569982529
2023-01-21 12:37:10.939815: step: 928/531, loss: 0.004692649934440851
2023-01-21 12:37:12.101107: step: 932/531, loss: 0.0034207822754979134
2023-01-21 12:37:13.216064: step: 936/531, loss: 0.001046848250553012
2023-01-21 12:37:14.348479: step: 940/531, loss: 0.0026942254044115543
2023-01-21 12:37:15.449273: step: 944/531, loss: 2.09808349609375e-05
2023-01-21 12:37:16.870522: step: 948/531, loss: 0.005017089657485485
2023-01-21 12:37:17.987988: step: 952/531, loss: 0.00486679095774889
2023-01-21 12:37:19.110880: step: 956/531, loss: 0.05214891582727432
2023-01-21 12:37:20.246141: step: 960/531, loss: 0.0012584686046466231
2023-01-21 12:37:21.366304: step: 964/531, loss: 1.8596649169921875e-05
2023-01-21 12:37:22.471239: step: 968/531, loss: 0.0005046844598837197
2023-01-21 12:37:23.587261: step: 972/531, loss: 1.3351440202313825e-06
2023-01-21 12:37:24.681362: step: 976/531, loss: 0.0004749298095703125
2023-01-21 12:37:25.796568: step: 980/531, loss: 0.020760728046298027
2023-01-21 12:37:26.909644: step: 984/531, loss: 0.0002468109014444053
2023-01-21 12:37:28.009810: step: 988/531, loss: 0.006173896603286266
2023-01-21 12:37:29.110126: step: 992/531, loss: 0.020803451538085938
2023-01-21 12:37:30.222636: step: 996/531, loss: 0.00044536590576171875
2023-01-21 12:37:31.362653: step: 1000/531, loss: 0.024645615369081497
2023-01-21 12:37:32.467681: step: 1004/531, loss: 0.00020122528076171875
2023-01-21 12:37:33.565037: step: 1008/531, loss: 6.10351571594947e-06
2023-01-21 12:37:34.712094: step: 1012/531, loss: 0.02942485921084881
2023-01-21 12:37:35.842113: step: 1016/531, loss: 0.0002265930233988911
2023-01-21 12:37:36.962862: step: 1020/531, loss: 0.0004514694446697831
2023-01-21 12:37:38.105005: step: 1024/531, loss: 0.706406831741333
2023-01-21 12:37:39.243485: step: 1028/531, loss: 0.0001472473086323589
2023-01-21 12:37:40.374253: step: 1032/531, loss: 0.04700794443488121
2023-01-21 12:37:41.511612: step: 1036/531, loss: 0.0004622936248779297
2023-01-21 12:37:42.637426: step: 1040/531, loss: 0.0005142212030477822
2023-01-21 12:37:43.766795: step: 1044/531, loss: 4.942416853737086e-05
2023-01-21 12:37:44.903589: step: 1048/531, loss: 0.0005645751953125
2023-01-21 12:37:46.038882: step: 1052/531, loss: 0.011251830495893955
2023-01-21 12:37:47.194738: step: 1056/531, loss: 0.00916380900889635
2023-01-21 12:37:48.305030: step: 1060/531, loss: 0.013793659396469593
2023-01-21 12:37:49.422276: step: 1064/531, loss: 0.04953594505786896
2023-01-21 12:37:50.523195: step: 1068/531, loss: 0.0032609940972179174
2023-01-21 12:37:51.647672: step: 1072/531, loss: 0.05135021358728409
2023-01-21 12:37:52.767785: step: 1076/531, loss: 0.024227142333984375
2023-01-21 12:37:53.915212: step: 1080/531, loss: 0.05784149095416069
2023-01-21 12:37:55.044949: step: 1084/531, loss: 0.049965668469667435
2023-01-21 12:37:56.163354: step: 1088/531, loss: 0.00086212158203125
2023-01-21 12:37:57.273879: step: 1092/531, loss: 0.0021753313485533
2023-01-21 12:37:58.409954: step: 1096/531, loss: -6.675720669591101e-07
2023-01-21 12:37:59.520392: step: 1100/531, loss: 0.00010528564598644152
2023-01-21 12:38:00.648772: step: 1104/531, loss: 0.00014543533325195312
2023-01-21 12:38:01.765367: step: 1108/531, loss: 0.0014732361305505037
2023-01-21 12:38:02.854202: step: 1112/531, loss: 5.435943421616685e-06
2023-01-21 12:38:03.963279: step: 1116/531, loss: 0.0009437561384402215
2023-01-21 12:38:05.080212: step: 1120/531, loss: 1.2111663636460435e-05
2023-01-21 12:38:06.256257: step: 1124/531, loss: 0.011473273858428001
2023-01-21 12:38:07.400778: step: 1128/531, loss: 0.004797745030373335
2023-01-21 12:38:08.503763: step: 1132/531, loss: 6.341934204101562e-05
2023-01-21 12:38:09.610603: step: 1136/531, loss: 0.006159878335893154
2023-01-21 12:38:10.723340: step: 1140/531, loss: 0.0014754296280443668
2023-01-21 12:38:11.815262: step: 1144/531, loss: 0.06059751659631729
2023-01-21 12:38:12.928817: step: 1148/531, loss: 0.0008047700393944979
2023-01-21 12:38:14.040884: step: 1152/531, loss: 0.0003410816425457597
2023-01-21 12:38:15.152762: step: 1156/531, loss: 0.022004509344697
2023-01-21 12:38:16.338222: step: 1160/531, loss: 0.001546669052913785
2023-01-21 12:38:17.436910: step: 1164/531, loss: 0.0003765106375794858
2023-01-21 12:38:18.557995: step: 1168/531, loss: 0.0021356584038585424
2023-01-21 12:38:19.703748: step: 1172/531, loss: 0.0011013986077159643
2023-01-21 12:38:20.836255: step: 1176/531, loss: 0.003407096955925226
2023-01-21 12:38:21.951034: step: 1180/531, loss: 9.16481003514491e-05
2023-01-21 12:38:23.093340: step: 1184/531, loss: 0.0174116138368845
2023-01-21 12:38:24.230641: step: 1188/531, loss: 0.01302433107048273
2023-01-21 12:38:25.353443: step: 1192/531, loss: -2.384185791015625e-06
2023-01-21 12:38:26.464707: step: 1196/531, loss: 0.020924091339111328
2023-01-21 12:38:27.600739: step: 1200/531, loss: 0.0019758224952965975
2023-01-21 12:38:28.727894: step: 1204/531, loss: 0.011371231637895107
2023-01-21 12:38:29.850986: step: 1208/531, loss: 0.0015244930982589722
2023-01-21 12:38:30.979776: step: 1212/531, loss: 0.00042953493539243937
2023-01-21 12:38:32.087048: step: 1216/531, loss: 1.7261505490751006e-05
2023-01-21 12:38:33.229118: step: 1220/531, loss: 1.8119811784345075e-06
2023-01-21 12:38:34.341459: step: 1224/531, loss: 0.03948669508099556
2023-01-21 12:38:35.473833: step: 1228/531, loss: 0.0005420685047283769
2023-01-21 12:38:36.572103: step: 1232/531, loss: 0.0049370769411325455
2023-01-21 12:38:37.683296: step: 1236/531, loss: 1.926422191900201e-05
2023-01-21 12:38:38.809651: step: 1240/531, loss: 0.003025245852768421
2023-01-21 12:38:39.950269: step: 1244/531, loss: 0.007724761962890625
2023-01-21 12:38:41.097590: step: 1248/531, loss: 0.004211998078972101
2023-01-21 12:38:42.227169: step: 1252/531, loss: 0.00016860962205100805
2023-01-21 12:38:43.370819: step: 1256/531, loss: 0.002432918641716242
2023-01-21 12:38:44.476390: step: 1260/531, loss: 0.0008771896245889366
2023-01-21 12:38:45.568580: step: 1264/531, loss: 0.015062427148222923
2023-01-21 12:38:46.683576: step: 1268/531, loss: 0.00035834312438964844
2023-01-21 12:38:47.797686: step: 1272/531, loss: 0.0025428771041333675
2023-01-21 12:38:48.926062: step: 1276/531, loss: 0.00023069381131790578
2023-01-21 12:38:50.059822: step: 1280/531, loss: 0.0004006385861430317
2023-01-21 12:38:51.215961: step: 1284/531, loss: 0.0011306763626635075
2023-01-21 12:38:52.338845: step: 1288/531, loss: 0.0016908645629882812
2023-01-21 12:38:53.466960: step: 1292/531, loss: 0.0010279655689373612
2023-01-21 12:38:54.610787: step: 1296/531, loss: 3.9768219721736386e-05
2023-01-21 12:38:55.734588: step: 1300/531, loss: 0.003213882679119706
2023-01-21 12:38:56.885072: step: 1304/531, loss: 0.005150032229721546
2023-01-21 12:38:57.995813: step: 1308/531, loss: 0.0001581192045705393
2023-01-21 12:38:59.141820: step: 1312/531, loss: 0.007987165823578835
2023-01-21 12:39:00.265566: step: 1316/531, loss: 0.000255584716796875
2023-01-21 12:39:01.417967: step: 1320/531, loss: 0.002286529401317239
2023-01-21 12:39:02.531044: step: 1324/531, loss: 0.0013268471229821444
2023-01-21 12:39:03.666545: step: 1328/531, loss: 0.6295409798622131
2023-01-21 12:39:04.781593: step: 1332/531, loss: 0.014552021399140358
2023-01-21 12:39:05.935520: step: 1336/531, loss: 0.0006862640148028731
2023-01-21 12:39:07.059740: step: 1340/531, loss: 0.0015329361194744706
2023-01-21 12:39:08.175336: step: 1344/531, loss: 2.803802453854587e-05
2023-01-21 12:39:09.307081: step: 1348/531, loss: 0.015396691858768463
2023-01-21 12:39:10.427105: step: 1352/531, loss: 0.0010770796798169613
2023-01-21 12:39:11.577927: step: 1356/531, loss: 0.0003342151758261025
2023-01-21 12:39:12.742499: step: 1360/531, loss: 0.0010797501308843493
2023-01-21 12:39:13.863783: step: 1364/531, loss: 0.014882469549775124
2023-01-21 12:39:15.011024: step: 1368/531, loss: 0.0029285431373864412
2023-01-21 12:39:16.124771: step: 1372/531, loss: 0.008823776617646217
2023-01-21 12:39:17.242354: step: 1376/531, loss: 6.50405854685232e-05
2023-01-21 12:39:18.367667: step: 1380/531, loss: 0.002798462053760886
2023-01-21 12:39:19.468120: step: 1384/531, loss: 0.0006093024858273566
2023-01-21 12:39:20.600508: step: 1388/531, loss: 0.0018859029514715075
2023-01-21 12:39:21.729691: step: 1392/531, loss: 0.0017148017650470138
2023-01-21 12:39:22.866200: step: 1396/531, loss: 0.15394507348537445
2023-01-21 12:39:24.018864: step: 1400/531, loss: 0.0023052217438817024
2023-01-21 12:39:25.157324: step: 1404/531, loss: 1.1301040103717241e-05
2023-01-21 12:39:26.274884: step: 1408/531, loss: 0.0001277923583984375
2023-01-21 12:39:27.390203: step: 1412/531, loss: 0.02342100255191326
2023-01-21 12:39:28.521176: step: 1416/531, loss: 0.006754875183105469
2023-01-21 12:39:29.628190: step: 1420/531, loss: 0.00017118453979492188
2023-01-21 12:39:30.751127: step: 1424/531, loss: 0.025450468063354492
2023-01-21 12:39:31.896066: step: 1428/531, loss: 0.0002709388791117817
2023-01-21 12:39:33.018679: step: 1432/531, loss: 0.09664926677942276
2023-01-21 12:39:34.125321: step: 1436/531, loss: 0.004719638731330633
2023-01-21 12:39:35.242035: step: 1440/531, loss: 0.0011406898265704513
2023-01-21 12:39:36.375385: step: 1444/531, loss: 0.0016133309109136462
2023-01-21 12:39:37.505540: step: 1448/531, loss: 0.006688308902084827
2023-01-21 12:39:38.622504: step: 1452/531, loss: 0.000404167192755267
2023-01-21 12:39:39.751203: step: 1456/531, loss: 0.09490318596363068
2023-01-21 12:39:40.872051: step: 1460/531, loss: 7.953643944347277e-05
2023-01-21 12:39:42.021509: step: 1464/531, loss: 0.2200479507446289
2023-01-21 12:39:43.132125: step: 1468/531, loss: 0.0008084297878667712
2023-01-21 12:39:44.269027: step: 1472/531, loss: 0.02826089784502983
2023-01-21 12:39:45.392480: step: 1476/531, loss: 0.08072948455810547
2023-01-21 12:39:46.499945: step: 1480/531, loss: 0.010100364685058594
2023-01-21 12:39:47.607545: step: 1484/531, loss: 0.001026153564453125
2023-01-21 12:39:48.724211: step: 1488/531, loss: 0.000878667866345495
2023-01-21 12:39:49.846623: step: 1492/531, loss: 0.0006102085462771356
2023-01-21 12:39:50.976491: step: 1496/531, loss: 0.03264160454273224
2023-01-21 12:39:52.100463: step: 1500/531, loss: 0.001094055245630443
2023-01-21 12:39:53.212853: step: 1504/531, loss: 0.0006366729503497481
2023-01-21 12:39:54.341612: step: 1508/531, loss: 6.799698167014867e-05
2023-01-21 12:39:55.424803: step: 1512/531, loss: 0.007296538446098566
2023-01-21 12:39:56.529315: step: 1516/531, loss: 9.813308861339465e-05
2023-01-21 12:39:57.680919: step: 1520/531, loss: 0.004828357603400946
2023-01-21 12:39:58.802465: step: 1524/531, loss: 0.001416969345882535
2023-01-21 12:39:59.946651: step: 1528/531, loss: 0.049439240247011185
2023-01-21 12:40:01.050100: step: 1532/531, loss: 0.0028072833083570004
2023-01-21 12:40:02.185816: step: 1536/531, loss: 2.0790101189049892e-05
2023-01-21 12:40:03.300285: step: 1540/531, loss: 0.0069519043900072575
2023-01-21 12:40:04.433613: step: 1544/531, loss: 0.0017322540516033769
2023-01-21 12:40:05.564882: step: 1548/531, loss: 0.002494430635124445
2023-01-21 12:40:06.712106: step: 1552/531, loss: 0.0015844255685806274
2023-01-21 12:40:07.825663: step: 1556/531, loss: 0.0004020690976176411
2023-01-21 12:40:08.981533: step: 1560/531, loss: 0.0031066895462572575
2023-01-21 12:40:10.118908: step: 1564/531, loss: 0.07174170017242432
2023-01-21 12:40:11.217037: step: 1568/531, loss: 0.01071691419929266
2023-01-21 12:40:12.355720: step: 1572/531, loss: 0.013907814398407936
2023-01-21 12:40:13.472055: step: 1576/531, loss: 0.002496433211490512
2023-01-21 12:40:14.607514: step: 1580/531, loss: 0.0029046060517430305
2023-01-21 12:40:15.726502: step: 1584/531, loss: 0.018844319507479668
2023-01-21 12:40:16.842629: step: 1588/531, loss: 6.351470801746473e-05
2023-01-21 12:40:17.973514: step: 1592/531, loss: 0.028675103560090065
2023-01-21 12:40:19.095348: step: 1596/531, loss: 0.04164304956793785
2023-01-21 12:40:20.212817: step: 1600/531, loss: 0.02446146123111248
2023-01-21 12:40:21.349260: step: 1604/531, loss: 0.007489681243896484
2023-01-21 12:40:22.476668: step: 1608/531, loss: 0.16683831810951233
2023-01-21 12:40:23.621902: step: 1612/531, loss: 0.00019459724717307836
2023-01-21 12:40:24.726780: step: 1616/531, loss: 0.05150318145751953
2023-01-21 12:40:25.875419: step: 1620/531, loss: 4.2629246308933944e-05
2023-01-21 12:40:27.038209: step: 1624/531, loss: 0.0036334991455078125
2023-01-21 12:40:28.157963: step: 1628/531, loss: 0.01684246025979519
2023-01-21 12:40:29.273604: step: 1632/531, loss: 3.3378603347955504e-06
2023-01-21 12:40:30.407497: step: 1636/531, loss: 0.0028789518401026726
2023-01-21 12:40:31.506244: step: 1640/531, loss: 0.0023194788955152035
2023-01-21 12:40:32.629703: step: 1644/531, loss: 0.01586456410586834
2023-01-21 12:40:33.751385: step: 1648/531, loss: 0.09746570140123367
2023-01-21 12:40:34.827306: step: 1652/531, loss: 0.06596937030553818
2023-01-21 12:40:35.947361: step: 1656/531, loss: 0.022096730768680573
2023-01-21 12:40:37.087551: step: 1660/531, loss: 0.0021263123489916325
2023-01-21 12:40:38.220117: step: 1664/531, loss: 8.296966552734375e-05
2023-01-21 12:40:39.352091: step: 1668/531, loss: 0.00015087128849700093
2023-01-21 12:40:40.494017: step: 1672/531, loss: 0.018308257684111595
2023-01-21 12:40:41.611884: step: 1676/531, loss: 9.279251389671117e-05
2023-01-21 12:40:42.747401: step: 1680/531, loss: 0.0003056526475120336
2023-01-21 12:40:43.895338: step: 1684/531, loss: 0.000118255615234375
2023-01-21 12:40:45.020550: step: 1688/531, loss: 0.489303320646286
2023-01-21 12:40:46.124860: step: 1692/531, loss: 0.000506496406160295
2023-01-21 12:40:47.263932: step: 1696/531, loss: 0.4020484983921051
2023-01-21 12:40:48.375750: step: 1700/531, loss: 0.017195701599121094
2023-01-21 12:40:49.501014: step: 1704/531, loss: 1.659393274167087e-05
2023-01-21 12:40:50.622120: step: 1708/531, loss: 0.00032138824462890625
2023-01-21 12:40:51.738216: step: 1712/531, loss: 0.11515121161937714
2023-01-21 12:40:52.866682: step: 1716/531, loss: 0.000286293012322858
2023-01-21 12:40:53.986315: step: 1720/531, loss: 0.0013742446899414062
2023-01-21 12:40:55.130480: step: 1724/531, loss: 0.004477310460060835
2023-01-21 12:40:56.243653: step: 1728/531, loss: 0.004259681794792414
2023-01-21 12:40:57.373260: step: 1732/531, loss: 0.05674934387207031
2023-01-21 12:40:58.469207: step: 1736/531, loss: 0.03366789594292641
2023-01-21 12:40:59.615616: step: 1740/531, loss: 0.0017023086547851562
2023-01-21 12:41:00.725753: step: 1744/531, loss: 0.007914924994111061
2023-01-21 12:41:01.864916: step: 1748/531, loss: 0.016933251172304153
2023-01-21 12:41:02.974297: step: 1752/531, loss: 0.00015182494826149195
2023-01-21 12:41:04.082943: step: 1756/531, loss: 9.107589721679688e-05
2023-01-21 12:41:05.192969: step: 1760/531, loss: 0.00017179847054649144
2023-01-21 12:41:06.356813: step: 1764/531, loss: 0.00015707015700172633
2023-01-21 12:41:07.452215: step: 1768/531, loss: 2.021789623540826e-05
2023-01-21 12:41:08.610692: step: 1772/531, loss: 0.08329629898071289
2023-01-21 12:41:09.767543: step: 1776/531, loss: 0.0007694244850426912
2023-01-21 12:41:10.882751: step: 1780/531, loss: 0.0012290955055505037
2023-01-21 12:41:12.036944: step: 1784/531, loss: 0.10531673580408096
2023-01-21 12:41:13.169114: step: 1788/531, loss: 0.021512603387236595
2023-01-21 12:41:14.314509: step: 1792/531, loss: 0.09801311790943146
2023-01-21 12:41:15.440832: step: 1796/531, loss: 5.898475501453504e-05
2023-01-21 12:41:16.601383: step: 1800/531, loss: 0.0384368896484375
2023-01-21 12:41:17.735653: step: 1804/531, loss: 0.00011668205843307078
2023-01-21 12:41:18.860965: step: 1808/531, loss: 0.0009202957153320312
2023-01-21 12:41:19.965080: step: 1812/531, loss: 0.011274528689682484
2023-01-21 12:41:21.135860: step: 1816/531, loss: 0.03567848354578018
2023-01-21 12:41:22.251178: step: 1820/531, loss: 0.011447524651885033
2023-01-21 12:41:23.415093: step: 1824/531, loss: 0.0008705139043740928
2023-01-21 12:41:24.549363: step: 1828/531, loss: 0.011373138055205345
2023-01-21 12:41:25.664928: step: 1832/531, loss: 0.019310856238007545
2023-01-21 12:41:26.772613: step: 1836/531, loss: 0.002705478807911277
2023-01-21 12:41:27.914320: step: 1840/531, loss: 0.00416412390768528
2023-01-21 12:41:29.052747: step: 1844/531, loss: 0.0006786346202716231
2023-01-21 12:41:30.204604: step: 1848/531, loss: 0.27540796995162964
2023-01-21 12:41:31.341242: step: 1852/531, loss: 7.247925168485381e-06
2023-01-21 12:41:32.486798: step: 1856/531, loss: 0.011501980014145374
2023-01-21 12:41:33.619546: step: 1860/531, loss: 0.00017232894606422633
2023-01-21 12:41:34.739432: step: 1864/531, loss: 0.0001307010679738596
2023-01-21 12:41:35.867830: step: 1868/531, loss: 0.10891075432300568
2023-01-21 12:41:36.993795: step: 1872/531, loss: 0.0023916244972497225
2023-01-21 12:41:38.116634: step: 1876/531, loss: 0.006252288818359375
2023-01-21 12:41:39.252155: step: 1880/531, loss: 0.027922438457608223
2023-01-21 12:41:40.375442: step: 1884/531, loss: 0.03657875210046768
2023-01-21 12:41:41.476824: step: 1888/531, loss: 0.07212285697460175
2023-01-21 12:41:42.602022: step: 1892/531, loss: 0.0004203796270303428
2023-01-21 12:41:43.724578: step: 1896/531, loss: 0.0017456054920330644
2023-01-21 12:41:44.852014: step: 1900/531, loss: 0.02304067648947239
2023-01-21 12:41:45.989740: step: 1904/531, loss: 0.14250606298446655
2023-01-21 12:41:47.137443: step: 1908/531, loss: 0.005561447236686945
2023-01-21 12:41:48.292189: step: 1912/531, loss: 0.011288642883300781
2023-01-21 12:41:49.432054: step: 1916/531, loss: 0.018338680267333984
2023-01-21 12:41:50.549179: step: 1920/531, loss: 0.0005675316206179559
2023-01-21 12:41:51.664493: step: 1924/531, loss: 0.002506256103515625
2023-01-21 12:41:52.823518: step: 1928/531, loss: 0.023679541423916817
2023-01-21 12:41:53.944493: step: 1932/531, loss: 0.0019109725253656507
2023-01-21 12:41:55.058915: step: 1936/531, loss: 0.00011405944678699598
2023-01-21 12:41:56.211034: step: 1940/531, loss: 0.00012311934551689774
2023-01-21 12:41:57.330958: step: 1944/531, loss: 0.03940429911017418
2023-01-21 12:41:58.448557: step: 1948/531, loss: 0.0012498856522142887
2023-01-21 12:41:59.593527: step: 1952/531, loss: 0.0001930236758198589
2023-01-21 12:42:00.732470: step: 1956/531, loss: 0.010274887084960938
2023-01-21 12:42:01.857097: step: 1960/531, loss: 0.005497169215232134
2023-01-21 12:42:02.965605: step: 1964/531, loss: 5.7506560551701114e-05
2023-01-21 12:42:04.074095: step: 1968/531, loss: 2.6702882678364404e-06
2023-01-21 12:42:05.191753: step: 1972/531, loss: 0.00031719208345748484
2023-01-21 12:42:06.328070: step: 1976/531, loss: 0.0002713203430175781
2023-01-21 12:42:07.454677: step: 1980/531, loss: 0.05206799507141113
2023-01-21 12:42:08.570160: step: 1984/531, loss: 0.0017215729458257556
2023-01-21 12:42:09.686063: step: 1988/531, loss: 0.0010931015713140368
2023-01-21 12:42:10.801580: step: 1992/531, loss: 0.01668539084494114
2023-01-21 12:42:11.892368: step: 1996/531, loss: 0.00020408631826285273
2023-01-21 12:42:12.989803: step: 2000/531, loss: 0.004532241728156805
2023-01-21 12:42:14.115837: step: 2004/531, loss: 0.010374260134994984
2023-01-21 12:42:15.246700: step: 2008/531, loss: 0.01088948268443346
2023-01-21 12:42:16.378005: step: 2012/531, loss: 0.005203056149184704
2023-01-21 12:42:17.492801: step: 2016/531, loss: 9.832382784225047e-05
2023-01-21 12:42:18.646738: step: 2020/531, loss: 0.0008849144214764237
2023-01-21 12:42:19.790108: step: 2024/531, loss: 0.0002753257576841861
2023-01-21 12:42:20.881995: step: 2028/531, loss: 0.0008844375261105597
2023-01-21 12:42:22.005067: step: 2032/531, loss: 0.05789985880255699
2023-01-21 12:42:23.133877: step: 2036/531, loss: 0.0009868622291833162
2023-01-21 12:42:24.237918: step: 2040/531, loss: 0.0005660175811499357
2023-01-21 12:42:25.401206: step: 2044/531, loss: 0.01151733472943306
2023-01-21 12:42:26.530765: step: 2048/531, loss: 0.001330471015535295
2023-01-21 12:42:27.668558: step: 2052/531, loss: 0.0026617050170898438
2023-01-21 12:42:28.783798: step: 2056/531, loss: 0.004637623205780983
2023-01-21 12:42:29.886847: step: 2060/531, loss: 0.06763839721679688
2023-01-21 12:42:30.979524: step: 2064/531, loss: 0.002140092896297574
2023-01-21 12:42:32.089492: step: 2068/531, loss: 0.004965877626091242
2023-01-21 12:42:33.201961: step: 2072/531, loss: 0.0002796054177451879
2023-01-21 12:42:34.313381: step: 2076/531, loss: 1.3732910701946821e-05
2023-01-21 12:42:35.483208: step: 2080/531, loss: 0.008048057556152344
2023-01-21 12:42:36.603164: step: 2084/531, loss: 0.004024315159767866
2023-01-21 12:42:37.719058: step: 2088/531, loss: 0.006915092468261719
2023-01-21 12:42:38.845993: step: 2092/531, loss: 0.0008516311645507812
2023-01-21 12:42:39.977456: step: 2096/531, loss: 0.00036945342435501516
2023-01-21 12:42:41.094857: step: 2100/531, loss: 0.01400852296501398
2023-01-21 12:42:42.210518: step: 2104/531, loss: 0.0004715919494628906
2023-01-21 12:42:43.331643: step: 2108/531, loss: 0.05077171325683594
2023-01-21 12:42:44.436430: step: 2112/531, loss: 0.012525559403002262
2023-01-21 12:42:45.577327: step: 2116/531, loss: 0.020716095343232155
2023-01-21 12:42:46.735290: step: 2120/531, loss: 0.016623878851532936
2023-01-21 12:42:47.883843: step: 2124/531, loss: 0.0005946159362792969
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5730994152046783, 'r': 0.7829560585885486, 'f1': 0.6617895329206528}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6226240148354195, 'r': 0.800834824090638, 'f1': 0.7005738132498694}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.550561797752809, 'r': 0.9074074074074074, 'f1': 0.6853146853146853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.576271186440678, 'r': 0.5396825396825397, 'f1': 0.5573770491803278}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.3333333333333333, 'r': 0.4166666666666667, 'f1': 0.3703703703703704}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 24
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:43:28.224429: step: 4/531, loss: 5.91278076171875e-05
2023-01-21 12:43:29.334019: step: 8/531, loss: 1.831054760259576e-05
2023-01-21 12:43:30.450878: step: 12/531, loss: 0.0008469581371173263
2023-01-21 12:43:31.562218: step: 16/531, loss: 0.0002536773681640625
2023-01-21 12:43:32.669336: step: 20/531, loss: 0.009461021982133389
2023-01-21 12:43:33.777277: step: 24/531, loss: 0.012678338214755058
2023-01-21 12:43:34.941866: step: 28/531, loss: 0.003930473234504461
2023-01-21 12:43:36.068446: step: 32/531, loss: 0.013451588340103626
2023-01-21 12:43:37.190813: step: 36/531, loss: 0.001220703125
2023-01-21 12:43:38.326478: step: 40/531, loss: 0.02112560346722603
2023-01-21 12:43:39.438022: step: 44/531, loss: 0.01291732769459486
2023-01-21 12:43:40.579403: step: 48/531, loss: 2.6035308110294864e-05
2023-01-21 12:43:41.686102: step: 52/531, loss: 2.269744800287299e-05
2023-01-21 12:43:42.810763: step: 56/531, loss: 0.000653171562589705
2023-01-21 12:43:43.930809: step: 60/531, loss: 0.0018260478973388672
2023-01-21 12:43:45.083487: step: 64/531, loss: 0.0030193328857421875
2023-01-21 12:43:46.203923: step: 68/531, loss: 0.0008449554443359375
2023-01-21 12:43:47.333060: step: 72/531, loss: 0.0014793395530432463
2023-01-21 12:43:48.452423: step: 76/531, loss: 0.0010267734760418534
2023-01-21 12:43:49.583145: step: 80/531, loss: 0.0005099296686239541
2023-01-21 12:43:50.743503: step: 84/531, loss: 0.021720124408602715
2023-01-21 12:43:51.861582: step: 88/531, loss: 0.004712295718491077
2023-01-21 12:43:53.019765: step: 92/531, loss: 0.006507682614028454
2023-01-21 12:43:54.132824: step: 96/531, loss: 0.035111621022224426
2023-01-21 12:43:55.243841: step: 100/531, loss: 0.008625412359833717
2023-01-21 12:43:56.393777: step: 104/531, loss: 0.007600593380630016
2023-01-21 12:43:57.555584: step: 108/531, loss: 0.00042738913907669485
2023-01-21 12:43:58.686690: step: 112/531, loss: 0.00487442035228014
2023-01-21 12:43:59.827969: step: 116/531, loss: 1.716613724056515e-06
2023-01-21 12:44:00.949057: step: 120/531, loss: 0.0002675056457519531
2023-01-21 12:44:02.089256: step: 124/531, loss: 0.0005996704567223787
2023-01-21 12:44:03.201609: step: 128/531, loss: 0.0005227089277468622
2023-01-21 12:44:04.295861: step: 132/531, loss: 0.0004280090506654233
2023-01-21 12:44:05.407304: step: 136/531, loss: 0.0025522231590002775
2023-01-21 12:44:06.534710: step: 140/531, loss: 0.00040922165499068797
2023-01-21 12:44:07.650842: step: 144/531, loss: 0.0004783660115208477
2023-01-21 12:44:08.743537: step: 148/531, loss: 0.00023488998704124242
2023-01-21 12:44:09.858052: step: 152/531, loss: 0.5094490647315979
2023-01-21 12:44:10.961069: step: 156/531, loss: 0.036812786012887955
2023-01-21 12:44:12.123692: step: 160/531, loss: 0.0022897720336914062
2023-01-21 12:44:13.245381: step: 164/531, loss: 0.000346946733770892
2023-01-21 12:44:14.367697: step: 168/531, loss: 0.01707305945456028
2023-01-21 12:44:15.518559: step: 172/531, loss: 0.001058387802913785
2023-01-21 12:44:16.686180: step: 176/531, loss: 0.002761268522590399
2023-01-21 12:44:17.814596: step: 180/531, loss: 0.017061805352568626
2023-01-21 12:44:18.937551: step: 184/531, loss: 3.6430355976335704e-05
2023-01-21 12:44:20.083073: step: 188/531, loss: 0.009377861395478249
2023-01-21 12:44:21.212242: step: 192/531, loss: 0.018456079065799713
2023-01-21 12:44:22.329143: step: 196/531, loss: 0.010912704281508923
2023-01-21 12:44:23.462093: step: 200/531, loss: 2.1553041733568534e-05
2023-01-21 12:44:24.567415: step: 204/531, loss: 0.006747436244040728
2023-01-21 12:44:25.686680: step: 208/531, loss: 0.025938605889678
2023-01-21 12:44:26.808062: step: 212/531, loss: 0.007895183749496937
2023-01-21 12:44:27.915966: step: 216/531, loss: 0.22869530320167542
2023-01-21 12:44:29.065544: step: 220/531, loss: 0.0002742767392192036
2023-01-21 12:44:30.212347: step: 224/531, loss: 0.011216926388442516
2023-01-21 12:44:31.329835: step: 228/531, loss: 0.00012130737741244957
2023-01-21 12:44:32.460467: step: 232/531, loss: 0.004027175717055798
2023-01-21 12:44:33.567245: step: 236/531, loss: 0.0002709388791117817
2023-01-21 12:44:34.696698: step: 240/531, loss: 1.277923547604587e-05
2023-01-21 12:44:35.828369: step: 244/531, loss: 0.0001714706450002268
2023-01-21 12:44:36.940657: step: 248/531, loss: 0.1385120451450348
2023-01-21 12:44:38.032838: step: 252/531, loss: 0.00979690533131361
2023-01-21 12:44:39.145222: step: 256/531, loss: 0.011391067877411842
2023-01-21 12:44:40.294079: step: 260/531, loss: 0.0003238678036723286
2023-01-21 12:44:41.447035: step: 264/531, loss: 0.002680647186934948
2023-01-21 12:44:42.595852: step: 268/531, loss: 0.00028934478177689016
2023-01-21 12:44:43.706166: step: 272/531, loss: 0.00019693374633789062
2023-01-21 12:44:44.818227: step: 276/531, loss: 0.00013113021850585938
2023-01-21 12:44:45.971382: step: 280/531, loss: 0.004318142309784889
2023-01-21 12:44:47.106865: step: 284/531, loss: 0.016063785180449486
2023-01-21 12:44:48.231844: step: 288/531, loss: 0.006782626733183861
2023-01-21 12:44:49.388249: step: 292/531, loss: 0.0017033576732501388
2023-01-21 12:44:50.517097: step: 296/531, loss: 0.23460941016674042
2023-01-21 12:44:51.639012: step: 300/531, loss: 0.0007954597822390497
2023-01-21 12:44:52.771658: step: 304/531, loss: 0.002703094622120261
2023-01-21 12:44:53.907936: step: 308/531, loss: 0.060344792902469635
2023-01-21 12:44:55.039407: step: 312/531, loss: 0.00044622423592954874
2023-01-21 12:44:56.144295: step: 316/531, loss: 0.0005597114795818925
2023-01-21 12:44:57.292545: step: 320/531, loss: 0.015132714062929153
2023-01-21 12:44:58.419714: step: 324/531, loss: 0.019302034750580788
2023-01-21 12:44:59.556313: step: 328/531, loss: 0.0009077072609215975
2023-01-21 12:45:00.702660: step: 332/531, loss: 0.00030555727425962687
2023-01-21 12:45:01.830189: step: 336/531, loss: 0.0007661819690838456
2023-01-21 12:45:02.966939: step: 340/531, loss: 0.01809101179242134
2023-01-21 12:45:04.083492: step: 344/531, loss: -5.722046125811175e-07
2023-01-21 12:45:05.228726: step: 348/531, loss: 0.0018939971923828125
2023-01-21 12:45:06.327263: step: 352/531, loss: 0.0004322051827330142
2023-01-21 12:45:07.475938: step: 356/531, loss: 0.0002918243408203125
2023-01-21 12:45:08.625842: step: 360/531, loss: 0.0002749919949565083
2023-01-21 12:45:09.747521: step: 364/531, loss: 3.361701965332031e-05
2023-01-21 12:45:10.876682: step: 368/531, loss: 0.02384319342672825
2023-01-21 12:45:12.105125: step: 372/531, loss: 0.0008242130279541016
2023-01-21 12:45:13.234190: step: 376/531, loss: 0.00022363662719726562
2023-01-21 12:45:14.362762: step: 380/531, loss: 0.0006729125743731856
2023-01-21 12:45:15.480450: step: 384/531, loss: 9.012223017634824e-06
2023-01-21 12:45:16.578045: step: 388/531, loss: 8.58306884765625e-06
2023-01-21 12:45:17.696926: step: 392/531, loss: 0.0009639739873819053
2023-01-21 12:45:18.844789: step: 396/531, loss: 2.861026587197557e-06
2023-01-21 12:45:19.990053: step: 400/531, loss: 0.627214789390564
2023-01-21 12:45:21.147464: step: 404/531, loss: 0.00015325547428801656
2023-01-21 12:45:22.250764: step: 408/531, loss: 6.866455805720761e-06
2023-01-21 12:45:23.363685: step: 412/531, loss: 0.0007921218639239669
2023-01-21 12:45:24.485836: step: 416/531, loss: 0.00011711120896507055
2023-01-21 12:45:25.611589: step: 420/531, loss: 0.00011200905282748863
2023-01-21 12:45:26.728441: step: 424/531, loss: 0.00010223388380836695
2023-01-21 12:45:27.877605: step: 428/531, loss: 0.003694153157994151
2023-01-21 12:45:28.973481: step: 432/531, loss: 0.01503686886280775
2023-01-21 12:45:30.082337: step: 436/531, loss: 0.036676835268735886
2023-01-21 12:45:31.217453: step: 440/531, loss: 0.05137920752167702
2023-01-21 12:45:32.361038: step: 444/531, loss: 1.5068053471622989e-05
2023-01-21 12:45:33.507638: step: 448/531, loss: 0.0003145694499835372
2023-01-21 12:45:34.648468: step: 452/531, loss: 4.281997826183215e-05
2023-01-21 12:45:35.772485: step: 456/531, loss: 0.0053497315384447575
2023-01-21 12:45:36.898618: step: 460/531, loss: 2.4795533590804553e-06
2023-01-21 12:45:38.045651: step: 464/531, loss: 0.014058399014174938
2023-01-21 12:45:39.171009: step: 468/531, loss: 4.00543194700731e-06
2023-01-21 12:45:40.310920: step: 472/531, loss: 0.017551803961396217
2023-01-21 12:45:41.418582: step: 476/531, loss: 0.005578565876930952
2023-01-21 12:45:42.577520: step: 480/531, loss: 0.061332669109106064
2023-01-21 12:45:43.720344: step: 484/531, loss: 0.008698082529008389
2023-01-21 12:45:44.847532: step: 488/531, loss: 0.002961730817332864
2023-01-21 12:45:45.976936: step: 492/531, loss: 0.08084259182214737
2023-01-21 12:45:47.097426: step: 496/531, loss: 0.18942995369434357
2023-01-21 12:45:48.253713: step: 500/531, loss: 0.0003366470627952367
2023-01-21 12:45:49.364970: step: 504/531, loss: 0.0028450011741369963
2023-01-21 12:45:50.495062: step: 508/531, loss: 0.009164047427475452
2023-01-21 12:45:51.629320: step: 512/531, loss: 0.44605007767677307
2023-01-21 12:45:52.771905: step: 516/531, loss: 7.25746140233241e-05
2023-01-21 12:45:53.898972: step: 520/531, loss: 0.002776241395622492
2023-01-21 12:45:55.025525: step: 524/531, loss: 0.0012580871116369963
2023-01-21 12:45:56.136516: step: 528/531, loss: 0.00284652691334486
2023-01-21 12:45:57.250286: step: 532/531, loss: 0.0011589049827307463
2023-01-21 12:45:58.384144: step: 536/531, loss: 0.002253913786262274
2023-01-21 12:45:59.506498: step: 540/531, loss: 0.002480888506397605
2023-01-21 12:46:00.631681: step: 544/531, loss: 0.018663406372070312
2023-01-21 12:46:01.762052: step: 548/531, loss: 9.34600830078125e-05
2023-01-21 12:46:02.886121: step: 552/531, loss: 0.0072227478958666325
2023-01-21 12:46:04.008963: step: 556/531, loss: 0.0007403374183923006
2023-01-21 12:46:05.137062: step: 560/531, loss: 6.141662743175402e-05
2023-01-21 12:46:06.238590: step: 564/531, loss: 5.054473876953125e-05
2023-01-21 12:46:07.384591: step: 568/531, loss: 0.0018516541458666325
2023-01-21 12:46:08.506076: step: 572/531, loss: 6.67572021484375e-06
2023-01-21 12:46:09.613822: step: 576/531, loss: 0.001562654972076416
2023-01-21 12:46:10.742604: step: 580/531, loss: 0.09368829429149628
2023-01-21 12:46:11.898258: step: 584/531, loss: 0.018031883984804153
2023-01-21 12:46:13.038882: step: 588/531, loss: 7.858276512706652e-05
2023-01-21 12:46:14.149034: step: 592/531, loss: 0.002198505448177457
2023-01-21 12:46:15.283108: step: 596/531, loss: 1.0395050594524946e-05
2023-01-21 12:46:16.409566: step: 600/531, loss: 0.006389045622199774
2023-01-21 12:46:17.529641: step: 604/531, loss: 5.73158249608241e-05
2023-01-21 12:46:18.642865: step: 608/531, loss: 7.705688767600805e-05
2023-01-21 12:46:19.802753: step: 612/531, loss: 0.005303001496940851
2023-01-21 12:46:20.917753: step: 616/531, loss: 0.004048157017678022
2023-01-21 12:46:22.031289: step: 620/531, loss: 0.008164596743881702
2023-01-21 12:46:23.153637: step: 624/531, loss: 5.7697296142578125e-05
2023-01-21 12:46:24.281545: step: 628/531, loss: 0.004396772477775812
2023-01-21 12:46:25.383949: step: 632/531, loss: 0.018535137176513672
2023-01-21 12:46:26.498838: step: 636/531, loss: 0.00033063889713957906
2023-01-21 12:46:27.623391: step: 640/531, loss: 0.17800946533679962
2023-01-21 12:46:28.743221: step: 644/531, loss: 0.00014419556828215718
2023-01-21 12:46:29.880938: step: 648/531, loss: 0.03164225071668625
2023-01-21 12:46:31.017680: step: 652/531, loss: 0.0004584789276123047
2023-01-21 12:46:32.137634: step: 656/531, loss: 0.00013151168241165578
2023-01-21 12:46:33.251961: step: 660/531, loss: 0.00012903213792014867
2023-01-21 12:46:34.376263: step: 664/531, loss: 3.62396240234375e-05
2023-01-21 12:46:35.531648: step: 668/531, loss: 0.01884288713335991
2023-01-21 12:46:36.645343: step: 672/531, loss: 0.0045454977080225945
2023-01-21 12:46:37.779933: step: 676/531, loss: 0.0008653640979900956
2023-01-21 12:46:38.896720: step: 680/531, loss: 0.0001649379701120779
2023-01-21 12:46:40.028354: step: 684/531, loss: 0.0012868881458416581
2023-01-21 12:46:41.163637: step: 688/531, loss: 0.000354766845703125
2023-01-21 12:46:42.311467: step: 692/531, loss: 0.0005753517034463584
2023-01-21 12:46:43.430798: step: 696/531, loss: 0.020474813878536224
2023-01-21 12:46:44.571694: step: 700/531, loss: 0.001491117523983121
2023-01-21 12:46:45.705424: step: 704/531, loss: 3.461838059592992e-05
2023-01-21 12:46:46.824745: step: 708/531, loss: 0.0020816803444176912
2023-01-21 12:46:47.930970: step: 712/531, loss: 0.033225249499082565
2023-01-21 12:46:49.049855: step: 716/531, loss: 0.0010701180435717106
2023-01-21 12:46:50.165081: step: 720/531, loss: 0.014149665832519531
2023-01-21 12:46:51.281903: step: 724/531, loss: 0.0013815879356116056
2023-01-21 12:46:52.440837: step: 728/531, loss: 0.013937091454863548
2023-01-21 12:46:53.582060: step: 732/531, loss: 7.858276512706652e-05
2023-01-21 12:46:54.697319: step: 736/531, loss: 0.0002490997430868447
2023-01-21 12:46:55.832492: step: 740/531, loss: 0.0001737594575388357
2023-01-21 12:46:56.956346: step: 744/531, loss: 0.004236412234604359
2023-01-21 12:46:58.063882: step: 748/531, loss: 0.013752556405961514
2023-01-21 12:46:59.165589: step: 752/531, loss: 7.07626313669607e-05
2023-01-21 12:47:00.286692: step: 756/531, loss: 0.0006228744750842452
2023-01-21 12:47:01.385486: step: 760/531, loss: 0.0013320923317223787
2023-01-21 12:47:02.555301: step: 764/531, loss: 0.004911232274025679
2023-01-21 12:47:03.693745: step: 768/531, loss: 0.016339445486664772
2023-01-21 12:47:04.811827: step: 772/531, loss: 7.705688767600805e-05
2023-01-21 12:47:05.973499: step: 776/531, loss: 8.049011375987902e-05
2023-01-21 12:47:07.090857: step: 780/531, loss: 0.001172399497590959
2023-01-21 12:47:08.209382: step: 784/531, loss: 0.0005744933732785285
2023-01-21 12:47:09.324228: step: 788/531, loss: 0.00043392181396484375
2023-01-21 12:47:10.453147: step: 792/531, loss: 0.0024810314644128084
2023-01-21 12:47:11.574376: step: 796/531, loss: 0.0003286361461505294
2023-01-21 12:47:12.717516: step: 800/531, loss: 0.0010199546813964844
2023-01-21 12:47:13.845425: step: 804/531, loss: 0.00018186568922828883
2023-01-21 12:47:14.990261: step: 808/531, loss: 0.002832603408023715
2023-01-21 12:47:16.099267: step: 812/531, loss: 0.011869430541992188
2023-01-21 12:47:17.202626: step: 816/531, loss: 0.06693868339061737
2023-01-21 12:47:18.357292: step: 820/531, loss: 0.007252788636833429
2023-01-21 12:47:19.508865: step: 824/531, loss: 0.006060886662453413
2023-01-21 12:47:20.621323: step: 828/531, loss: 0.0031021118629723787
2023-01-21 12:47:21.730600: step: 832/531, loss: 0.017304040491580963
2023-01-21 12:47:22.841740: step: 836/531, loss: 0.06982836872339249
2023-01-21 12:47:23.978584: step: 840/531, loss: 0.004384422209113836
2023-01-21 12:47:25.102266: step: 844/531, loss: 0.005603218451142311
2023-01-21 12:47:26.233624: step: 848/531, loss: 0.001747727394104004
2023-01-21 12:47:27.365501: step: 852/531, loss: 0.011030388064682484
2023-01-21 12:47:28.519992: step: 856/531, loss: 0.0003007889026775956
2023-01-21 12:47:29.643582: step: 860/531, loss: 0.00020572246285155416
2023-01-21 12:47:30.802325: step: 864/531, loss: 0.0020354269072413445
2023-01-21 12:47:31.922825: step: 868/531, loss: 0.21678677201271057
2023-01-21 12:47:33.056387: step: 872/531, loss: 0.0005395889165811241
2023-01-21 12:47:34.205928: step: 876/531, loss: 0.0001865387021098286
2023-01-21 12:47:35.324240: step: 880/531, loss: -2.28881845032447e-06
2023-01-21 12:47:36.437229: step: 884/531, loss: 7.772445678710938e-05
2023-01-21 12:47:37.554673: step: 888/531, loss: 0.002215576358139515
2023-01-21 12:47:38.665213: step: 892/531, loss: 4.4345855712890625e-05
2023-01-21 12:47:39.786687: step: 896/531, loss: 0.07345886528491974
2023-01-21 12:47:40.909345: step: 900/531, loss: 0.03985557705163956
2023-01-21 12:47:42.049600: step: 904/531, loss: 8.392333984375e-05
2023-01-21 12:47:43.175585: step: 908/531, loss: -6.86645489622606e-06
2023-01-21 12:47:44.310392: step: 912/531, loss: 0.008864021860063076
2023-01-21 12:47:45.436080: step: 916/531, loss: 0.004531288519501686
2023-01-21 12:47:46.571797: step: 920/531, loss: 0.00027437208336777985
2023-01-21 12:47:47.666762: step: 924/531, loss: 0.0005645751953125
2023-01-21 12:47:48.792304: step: 928/531, loss: 0.0003319740353617817
2023-01-21 12:47:49.922503: step: 932/531, loss: 0.005953979212790728
2023-01-21 12:47:51.094619: step: 936/531, loss: 0.013526917435228825
2023-01-21 12:47:52.211784: step: 940/531, loss: 0.0007686614990234375
2023-01-21 12:47:53.347963: step: 944/531, loss: 0.001796674681827426
2023-01-21 12:47:54.497604: step: 948/531, loss: 0.01682434231042862
2023-01-21 12:47:55.654843: step: 952/531, loss: 0.02594909630715847
2023-01-21 12:47:56.767162: step: 956/531, loss: 0.0012048721546307206
2023-01-21 12:47:57.908686: step: 960/531, loss: 0.0005853652837686241
2023-01-21 12:47:59.099339: step: 964/531, loss: 0.0023124695289880037
2023-01-21 12:48:00.218721: step: 968/531, loss: 0.0025557042099535465
2023-01-21 12:48:01.364142: step: 972/531, loss: 0.002075147582218051
2023-01-21 12:48:02.486970: step: 976/531, loss: 0.0009582997299730778
2023-01-21 12:48:03.600679: step: 980/531, loss: 0.000590419746004045
2023-01-21 12:48:04.712933: step: 984/531, loss: 0.008892536163330078
2023-01-21 12:48:05.832043: step: 988/531, loss: 0.0005836010095663369
2023-01-21 12:48:06.934365: step: 992/531, loss: 0.008130836300551891
2023-01-21 12:48:08.044891: step: 996/531, loss: 0.003543853759765625
2023-01-21 12:48:09.176335: step: 1000/531, loss: 0.0013212204212322831
2023-01-21 12:48:10.265110: step: 1004/531, loss: 7.43865984986769e-06
2023-01-21 12:48:11.390887: step: 1008/531, loss: 0.00164794921875
2023-01-21 12:48:12.519907: step: 1012/531, loss: 0.14066238701343536
2023-01-21 12:48:13.650018: step: 1016/531, loss: 3.7527082895394415e-05
2023-01-21 12:48:14.742215: step: 1020/531, loss: -1.8119811784345075e-06
2023-01-21 12:48:15.901848: step: 1024/531, loss: 0.00037288665771484375
2023-01-21 12:48:17.023494: step: 1028/531, loss: 0.009696769528090954
2023-01-21 12:48:18.145990: step: 1032/531, loss: 0.03124275431036949
2023-01-21 12:48:19.272035: step: 1036/531, loss: 7.41004987503402e-05
2023-01-21 12:48:20.417547: step: 1040/531, loss: 0.00027179718017578125
2023-01-21 12:48:21.524840: step: 1044/531, loss: 3.7670135498046875e-05
2023-01-21 12:48:22.656879: step: 1048/531, loss: 0.0005243778578005731
2023-01-21 12:48:23.794176: step: 1052/531, loss: 0.0004273414670024067
2023-01-21 12:48:24.906503: step: 1056/531, loss: 0.0010843276977539062
2023-01-21 12:48:26.024334: step: 1060/531, loss: 3.24249276673072e-06
2023-01-21 12:48:27.161977: step: 1064/531, loss: 0.11719933152198792
2023-01-21 12:48:28.263691: step: 1068/531, loss: 0.0021984099876135588
2023-01-21 12:48:29.406894: step: 1072/531, loss: 0.004708480555564165
2023-01-21 12:48:30.532492: step: 1076/531, loss: 0.0026920319069176912
2023-01-21 12:48:31.677654: step: 1080/531, loss: 0.13162268698215485
2023-01-21 12:48:32.782423: step: 1084/531, loss: 0.02029895968735218
2023-01-21 12:48:33.901061: step: 1088/531, loss: 1.5163422176556196e-05
2023-01-21 12:48:35.025653: step: 1092/531, loss: 0.028029512614011765
2023-01-21 12:48:36.152629: step: 1096/531, loss: 0.011315584182739258
2023-01-21 12:48:37.272936: step: 1100/531, loss: 0.005497408099472523
2023-01-21 12:48:38.375605: step: 1104/531, loss: 0.005373812280595303
2023-01-21 12:48:39.503402: step: 1108/531, loss: 0.022137021645903587
2023-01-21 12:48:40.634158: step: 1112/531, loss: 0.23715955018997192
2023-01-21 12:48:41.751978: step: 1116/531, loss: 0.0008046150323934853
2023-01-21 12:48:42.896121: step: 1120/531, loss: 0.0012140274047851562
2023-01-21 12:48:44.049052: step: 1124/531, loss: 0.006359672639518976
2023-01-21 12:48:45.180544: step: 1128/531, loss: 0.021683311089873314
2023-01-21 12:48:46.317982: step: 1132/531, loss: 0.003791427705436945
2023-01-21 12:48:47.431831: step: 1136/531, loss: 0.0020242691971361637
2023-01-21 12:48:48.547538: step: 1140/531, loss: 0.00011944771540584043
2023-01-21 12:48:49.668608: step: 1144/531, loss: 0.02358236536383629
2023-01-21 12:48:50.794999: step: 1148/531, loss: 0.13448219001293182
2023-01-21 12:48:51.919517: step: 1152/531, loss: 0.16106128692626953
2023-01-21 12:48:53.039758: step: 1156/531, loss: 4.9591064453125e-05
2023-01-21 12:48:54.157529: step: 1160/531, loss: 0.005859756376594305
2023-01-21 12:48:55.255537: step: 1164/531, loss: 5.817413693876006e-06
2023-01-21 12:48:56.349063: step: 1168/531, loss: 0.00014743805513717234
2023-01-21 12:48:57.476950: step: 1172/531, loss: 0.02166595496237278
2023-01-21 12:48:58.578524: step: 1176/531, loss: 0.017145730555057526
2023-01-21 12:48:59.674479: step: 1180/531, loss: 6.961822691664565e-06
2023-01-21 12:49:00.775782: step: 1184/531, loss: 0.003286743303760886
2023-01-21 12:49:01.872890: step: 1188/531, loss: 0.0010373115073889494
2023-01-21 12:49:02.991149: step: 1192/531, loss: 0.0002922058047261089
2023-01-21 12:49:04.127819: step: 1196/531, loss: 0.03240489959716797
2023-01-21 12:49:05.276748: step: 1200/531, loss: 0.0322783961892128
2023-01-21 12:49:06.413974: step: 1204/531, loss: 1.888275073724799e-05
2023-01-21 12:49:07.545691: step: 1208/531, loss: 0.023116111755371094
2023-01-21 12:49:08.685564: step: 1212/531, loss: 0.0017627716297283769
2023-01-21 12:49:09.811132: step: 1216/531, loss: 5.474090721691027e-05
2023-01-21 12:49:10.913827: step: 1220/531, loss: 0.006732320878654718
2023-01-21 12:49:12.042778: step: 1224/531, loss: 0.0022884116042405367
2023-01-21 12:49:13.175562: step: 1228/531, loss: 0.0002704620419535786
2023-01-21 12:49:14.303216: step: 1232/531, loss: 0.00037488937960006297
2023-01-21 12:49:15.406921: step: 1236/531, loss: 0.012486266903579235
2023-01-21 12:49:16.518593: step: 1240/531, loss: 2.1934511096333154e-05
2023-01-21 12:49:17.609431: step: 1244/531, loss: 0.010217857547104359
2023-01-21 12:49:18.734298: step: 1248/531, loss: 2.560615394031629e-05
2023-01-21 12:49:19.851506: step: 1252/531, loss: 3.14712519866589e-06
2023-01-21 12:49:20.979383: step: 1256/531, loss: 0.019257163628935814
2023-01-21 12:49:22.125400: step: 1260/531, loss: 9.431838407181203e-05
2023-01-21 12:49:23.221796: step: 1264/531, loss: 0.002758169313892722
2023-01-21 12:49:24.350219: step: 1268/531, loss: 0.05671043321490288
2023-01-21 12:49:25.449877: step: 1272/531, loss: 3.261566234868951e-05
2023-01-21 12:49:26.568679: step: 1276/531, loss: 4.673004241340095e-06
2023-01-21 12:49:27.687483: step: 1280/531, loss: 4.291534423828125e-05
2023-01-21 12:49:28.794865: step: 1284/531, loss: -8.01086389401462e-06
2023-01-21 12:49:29.886967: step: 1288/531, loss: 0.0027475357055664062
2023-01-21 12:49:31.018122: step: 1292/531, loss: 0.00011177063424838707
2023-01-21 12:49:32.169895: step: 1296/531, loss: 0.08426089584827423
2023-01-21 12:49:33.324573: step: 1300/531, loss: 0.07674475014209747
2023-01-21 12:49:34.472279: step: 1304/531, loss: 0.004261589143425226
2023-01-21 12:49:35.588056: step: 1308/531, loss: 0.007454085163772106
2023-01-21 12:49:36.718223: step: 1312/531, loss: 0.0021406172309070826
2023-01-21 12:49:37.845884: step: 1316/531, loss: 0.0002738952753134072
2023-01-21 12:49:38.989448: step: 1320/531, loss: 0.023512747138738632
2023-01-21 12:49:40.126538: step: 1324/531, loss: 0.020349694415926933
2023-01-21 12:49:41.279046: step: 1328/531, loss: 0.0031551362480968237
2023-01-21 12:49:42.409871: step: 1332/531, loss: 0.00012092590623069555
2023-01-21 12:49:43.543216: step: 1336/531, loss: 0.004311466123908758
2023-01-21 12:49:44.668937: step: 1340/531, loss: 0.00036487579927779734
2023-01-21 12:49:45.781723: step: 1344/531, loss: 0.04719598591327667
2023-01-21 12:49:46.886254: step: 1348/531, loss: 0.007465839851647615
2023-01-21 12:49:48.029311: step: 1352/531, loss: 9.250640869140625e-05
2023-01-21 12:49:49.154288: step: 1356/531, loss: -1.826286461437121e-05
2023-01-21 12:49:50.276547: step: 1360/531, loss: 0.0006107331137172878
2023-01-21 12:49:51.388792: step: 1364/531, loss: 0.001025342964567244
2023-01-21 12:49:52.482494: step: 1368/531, loss: 0.026270676404237747
2023-01-21 12:49:53.630667: step: 1372/531, loss: 0.007968711666762829
2023-01-21 12:49:54.756313: step: 1376/531, loss: 0.014845657162368298
2023-01-21 12:49:55.865737: step: 1380/531, loss: 1.4400482541532256e-05
2023-01-21 12:49:56.982858: step: 1384/531, loss: 0.014618396759033203
2023-01-21 12:49:58.114069: step: 1388/531, loss: 0.014489746652543545
2023-01-21 12:49:59.243283: step: 1392/531, loss: 0.0010992049938067794
2023-01-21 12:50:00.382435: step: 1396/531, loss: 0.003054332919418812
2023-01-21 12:50:01.531539: step: 1400/531, loss: 0.024099349975585938
2023-01-21 12:50:02.639907: step: 1404/531, loss: 0.00011539459228515625
2023-01-21 12:50:03.723165: step: 1408/531, loss: 1.1920930774067529e-05
2023-01-21 12:50:04.859811: step: 1412/531, loss: 0.001798439072445035
2023-01-21 12:50:05.986678: step: 1416/531, loss: 0.0023027898278087378
2023-01-21 12:50:07.093733: step: 1420/531, loss: 2.250671423098538e-05
2023-01-21 12:50:08.232362: step: 1424/531, loss: 0.017932415008544922
2023-01-21 12:50:09.348409: step: 1428/531, loss: 2.117157055181451e-05
2023-01-21 12:50:10.484828: step: 1432/531, loss: 0.09610423445701599
2023-01-21 12:50:11.599704: step: 1436/531, loss: 0.0016328811179846525
2023-01-21 12:50:12.709448: step: 1440/531, loss: 0.0014927983283996582
2023-01-21 12:50:13.802385: step: 1444/531, loss: 3.2615658710710704e-05
2023-01-21 12:50:14.937867: step: 1448/531, loss: 0.0029414177406579256
2023-01-21 12:50:16.038951: step: 1452/531, loss: 0.00042066574678756297
2023-01-21 12:50:17.192296: step: 1456/531, loss: 0.17343387007713318
2023-01-21 12:50:18.310672: step: 1460/531, loss: 0.5168283581733704
2023-01-21 12:50:19.420162: step: 1464/531, loss: 0.0032763960771262646
2023-01-21 12:50:20.545424: step: 1468/531, loss: 1.9978411197662354
2023-01-21 12:50:21.652845: step: 1472/531, loss: 7.886887033237144e-05
2023-01-21 12:50:22.804863: step: 1476/531, loss: 0.0017276763683184981
2023-01-21 12:50:23.905256: step: 1480/531, loss: 0.008297347463667393
2023-01-21 12:50:25.033294: step: 1484/531, loss: 5.2261355449445546e-05
2023-01-21 12:50:26.170484: step: 1488/531, loss: 0.01113500539213419
2023-01-21 12:50:27.310787: step: 1492/531, loss: 0.05220966413617134
2023-01-21 12:50:28.471045: step: 1496/531, loss: 0.00022125244140625
2023-01-21 12:50:29.605871: step: 1500/531, loss: 0.04092588648200035
2023-01-21 12:50:30.719649: step: 1504/531, loss: 0.0023328305687755346
2023-01-21 12:50:31.843813: step: 1508/531, loss: 0.06254033744335175
2023-01-21 12:50:33.011761: step: 1512/531, loss: 0.0006333351484499872
2023-01-21 12:50:34.140970: step: 1516/531, loss: 0.049677420407533646
2023-01-21 12:50:35.275794: step: 1520/531, loss: 0.0010841370094567537
2023-01-21 12:50:36.402062: step: 1524/531, loss: 0.003187978407368064
2023-01-21 12:50:37.524290: step: 1528/531, loss: 0.015378189273178577
2023-01-21 12:50:38.646298: step: 1532/531, loss: 0.0010898590553551912
2023-01-21 12:50:39.765109: step: 1536/531, loss: 0.003979777917265892
2023-01-21 12:50:40.874139: step: 1540/531, loss: 0.00020428001880645752
2023-01-21 12:50:41.989061: step: 1544/531, loss: 0.00026788710965774953
2023-01-21 12:50:43.114442: step: 1548/531, loss: 0.00018596649169921875
2023-01-21 12:50:44.251491: step: 1552/531, loss: 5.836486889165826e-05
2023-01-21 12:50:45.355062: step: 1556/531, loss: 4.062652442371473e-05
2023-01-21 12:50:46.475155: step: 1560/531, loss: 0.0003044128534384072
2023-01-21 12:50:47.630173: step: 1564/531, loss: 0.016448449343442917
2023-01-21 12:50:48.733497: step: 1568/531, loss: 0.0006078720325604081
2023-01-21 12:50:49.859930: step: 1572/531, loss: 0.2753753960132599
2023-01-21 12:50:50.981217: step: 1576/531, loss: 0.013185406103730202
2023-01-21 12:50:52.126395: step: 1580/531, loss: 0.0004893302684649825
2023-01-21 12:50:53.241488: step: 1584/531, loss: 0.03410310670733452
2023-01-21 12:50:54.391938: step: 1588/531, loss: 0.6755965352058411
2023-01-21 12:50:55.531830: step: 1592/531, loss: 0.004021358676254749
2023-01-21 12:50:56.646520: step: 1596/531, loss: 0.00010814667621161789
2023-01-21 12:50:57.755925: step: 1600/531, loss: 0.02467174455523491
2023-01-21 12:50:58.891970: step: 1604/531, loss: 0.004039192106574774
2023-01-21 12:51:00.011526: step: 1608/531, loss: 0.0001583099365234375
2023-01-21 12:51:01.136406: step: 1612/531, loss: 0.021172380074858665
2023-01-21 12:51:02.305879: step: 1616/531, loss: 0.006282710935920477
2023-01-21 12:51:03.442734: step: 1620/531, loss: 0.0017760753398761153
2023-01-21 12:51:04.573233: step: 1624/531, loss: 0.0035886764526367188
2023-01-21 12:51:05.725878: step: 1628/531, loss: 0.0011241913307458162
2023-01-21 12:51:06.842588: step: 1632/531, loss: 0.021419525146484375
2023-01-21 12:51:07.962244: step: 1636/531, loss: 0.0009461403242312372
2023-01-21 12:51:09.082540: step: 1640/531, loss: 0.0006842613220214844
2023-01-21 12:51:10.208554: step: 1644/531, loss: 0.1723162680864334
2023-01-21 12:51:11.312447: step: 1648/531, loss: 0.020807411521673203
2023-01-21 12:51:12.451959: step: 1652/531, loss: 0.00020484924607444555
2023-01-21 12:51:13.558097: step: 1656/531, loss: 0.0029966356232762337
2023-01-21 12:51:14.675709: step: 1660/531, loss: 0.003917026799172163
2023-01-21 12:51:15.816329: step: 1664/531, loss: 0.014870263636112213
2023-01-21 12:51:16.950505: step: 1668/531, loss: 0.02199258841574192
2023-01-21 12:51:18.117707: step: 1672/531, loss: 0.00030956268892623484
2023-01-21 12:51:19.263075: step: 1676/531, loss: 8.77380352903856e-06
2023-01-21 12:51:20.382716: step: 1680/531, loss: 0.006533431820571423
2023-01-21 12:51:21.524928: step: 1684/531, loss: 0.004490470979362726
2023-01-21 12:51:22.647615: step: 1688/531, loss: 0.06544437259435654
2023-01-21 12:51:23.779653: step: 1692/531, loss: 0.002435016678646207
2023-01-21 12:51:24.880513: step: 1696/531, loss: 0.0013275147648528218
2023-01-21 12:51:26.022097: step: 1700/531, loss: 0.0035051347222179174
2023-01-21 12:51:27.181168: step: 1704/531, loss: 2.975463939947076e-05
2023-01-21 12:51:28.301606: step: 1708/531, loss: 0.01707991398870945
2023-01-21 12:51:29.458431: step: 1712/531, loss: 0.012486553750932217
2023-01-21 12:51:30.580359: step: 1716/531, loss: 0.0023081779945641756
2023-01-21 12:51:31.702202: step: 1720/531, loss: 0.0003156662278342992
2023-01-21 12:51:32.824524: step: 1724/531, loss: 3.833770824712701e-05
2023-01-21 12:51:33.957933: step: 1728/531, loss: 0.0001930236758198589
2023-01-21 12:51:35.064359: step: 1732/531, loss: 0.057274624705314636
2023-01-21 12:51:36.193722: step: 1736/531, loss: 0.013962173834443092
2023-01-21 12:51:37.343074: step: 1740/531, loss: 0.022211171686649323
2023-01-21 12:51:38.472845: step: 1744/531, loss: 0.012823772616684437
2023-01-21 12:51:39.612551: step: 1748/531, loss: 0.012158584780991077
2023-01-21 12:51:40.736076: step: 1752/531, loss: 7.24792471373803e-06
2023-01-21 12:51:41.873176: step: 1756/531, loss: 0.0038221837021410465
2023-01-21 12:51:42.966310: step: 1760/531, loss: 0.00025424957857467234
2023-01-21 12:51:44.107069: step: 1764/531, loss: 0.015503883361816406
2023-01-21 12:51:45.216529: step: 1768/531, loss: 0.003568649524822831
2023-01-21 12:51:46.341414: step: 1772/531, loss: 0.0033905983436852694
2023-01-21 12:51:47.462513: step: 1776/531, loss: 0.10421008616685867
2023-01-21 12:51:48.592838: step: 1780/531, loss: 0.000776100205257535
2023-01-21 12:51:49.704731: step: 1784/531, loss: 0.0011583329178392887
2023-01-21 12:51:50.841511: step: 1788/531, loss: 0.010939407162368298
2023-01-21 12:51:51.969751: step: 1792/531, loss: 0.0007143020629882812
2023-01-21 12:51:53.078666: step: 1796/531, loss: 0.01907653920352459
2023-01-21 12:51:54.199604: step: 1800/531, loss: 0.00012941360182594508
2023-01-21 12:51:55.321237: step: 1804/531, loss: 0.0002992272493429482
2023-01-21 12:51:56.437787: step: 1808/531, loss: 0.011938858777284622
2023-01-21 12:51:57.555842: step: 1812/531, loss: 0.016828538849949837
2023-01-21 12:51:58.713808: step: 1816/531, loss: 0.01117630023509264
2023-01-21 12:51:59.847610: step: 1820/531, loss: 0.24527034163475037
2023-01-21 12:52:00.968819: step: 1824/531, loss: 0.005370235536247492
2023-01-21 12:52:02.116917: step: 1828/531, loss: 0.0003772735653910786
2023-01-21 12:52:03.229330: step: 1832/531, loss: 0.00011901855759788305
2023-01-21 12:52:04.362566: step: 1836/531, loss: 0.0060482025146484375
2023-01-21 12:52:05.492032: step: 1840/531, loss: 9.52720656641759e-05
2023-01-21 12:52:06.599900: step: 1844/531, loss: 0.0031517029274255037
2023-01-21 12:52:07.730463: step: 1848/531, loss: 0.007832765579223633
2023-01-21 12:52:08.907643: step: 1852/531, loss: 0.0004680633428506553
2023-01-21 12:52:10.050220: step: 1856/531, loss: 0.020852327346801758
2023-01-21 12:52:11.185486: step: 1860/531, loss: 0.2709079682826996
2023-01-21 12:52:12.306511: step: 1864/531, loss: 0.03138594329357147
2023-01-21 12:52:13.433257: step: 1868/531, loss: 0.02486400678753853
2023-01-21 12:52:14.531697: step: 1872/531, loss: 0.00231170654296875
2023-01-21 12:52:15.699647: step: 1876/531, loss: 0.005629729945212603
2023-01-21 12:52:16.816327: step: 1880/531, loss: 0.0009407043689861894
2023-01-21 12:52:17.973573: step: 1884/531, loss: 2.059936559817288e-05
2023-01-21 12:52:19.139151: step: 1888/531, loss: 0.01094665564596653
2023-01-21 12:52:20.298339: step: 1892/531, loss: 0.002063274383544922
2023-01-21 12:52:21.423614: step: 1896/531, loss: 0.0023759843315929174
2023-01-21 12:52:22.560230: step: 1900/531, loss: 0.0014505386352539062
2023-01-21 12:52:23.689890: step: 1904/531, loss: 0.0006941794999875128
2023-01-21 12:52:24.826471: step: 1908/531, loss: 0.1358344554901123
2023-01-21 12:52:25.948610: step: 1912/531, loss: 0.0018725395202636719
2023-01-21 12:52:27.087782: step: 1916/531, loss: 0.00012922286987304688
2023-01-21 12:52:28.204985: step: 1920/531, loss: 3.337860107421875e-05
2023-01-21 12:52:29.332661: step: 1924/531, loss: -2.47955313170678e-06
2023-01-21 12:52:30.493059: step: 1928/531, loss: 0.0037004470359534025
2023-01-21 12:52:31.618582: step: 1932/531, loss: 0.00874023512005806
2023-01-21 12:52:32.745464: step: 1936/531, loss: 0.02477288246154785
2023-01-21 12:52:33.860742: step: 1940/531, loss: 4.76837158203125e-06
2023-01-21 12:52:34.978548: step: 1944/531, loss: 0.03425197675824165
2023-01-21 12:52:36.088096: step: 1948/531, loss: 0.011546325869858265
2023-01-21 12:52:37.239510: step: 1952/531, loss: 0.01705913618206978
2023-01-21 12:52:38.391904: step: 1956/531, loss: 0.0004614829958882183
2023-01-21 12:52:39.509137: step: 1960/531, loss: 0.0015539169544354081
2023-01-21 12:52:40.634830: step: 1964/531, loss: 0.08339511603116989
2023-01-21 12:52:41.758037: step: 1968/531, loss: 0.06810970604419708
2023-01-21 12:52:42.913560: step: 1972/531, loss: 0.006753015331923962
2023-01-21 12:52:44.030681: step: 1976/531, loss: 0.0014304905198514462
2023-01-21 12:52:45.178895: step: 1980/531, loss: 0.00022920667834114283
2023-01-21 12:52:46.299208: step: 1984/531, loss: 0.00021257401385810226
2023-01-21 12:52:47.420050: step: 1988/531, loss: 0.005514240358024836
2023-01-21 12:52:48.549375: step: 1992/531, loss: 0.042029574513435364
2023-01-21 12:52:49.666129: step: 1996/531, loss: 8.459090895485133e-05
2023-01-21 12:52:50.779434: step: 2000/531, loss: 0.06822490692138672
2023-01-21 12:52:51.907885: step: 2004/531, loss: 0.003777408739551902
2023-01-21 12:52:53.036112: step: 2008/531, loss: 0.0009963036281988025
2023-01-21 12:52:54.164842: step: 2012/531, loss: 0.00019874573627021164
2023-01-21 12:52:55.326550: step: 2016/531, loss: 0.13633279502391815
2023-01-21 12:52:56.424986: step: 2020/531, loss: 0.01930980756878853
2023-01-21 12:52:57.559746: step: 2024/531, loss: 0.004443645477294922
2023-01-21 12:52:58.690897: step: 2028/531, loss: 0.04711952432990074
2023-01-21 12:52:59.888414: step: 2032/531, loss: 0.02450275421142578
2023-01-21 12:53:01.011226: step: 2036/531, loss: 0.00010251998901367188
2023-01-21 12:53:02.133710: step: 2040/531, loss: 0.026918604969978333
2023-01-21 12:53:03.258590: step: 2044/531, loss: 0.1010231003165245
2023-01-21 12:53:04.388581: step: 2048/531, loss: 5.818209171295166
2023-01-21 12:53:05.515811: step: 2052/531, loss: 0.003371572820469737
2023-01-21 12:53:06.640539: step: 2056/531, loss: 0.00259475689381361
2023-01-21 12:53:07.759510: step: 2060/531, loss: 0.015487289056181908
2023-01-21 12:53:08.901736: step: 2064/531, loss: 0.0007555008050985634
2023-01-21 12:53:10.010975: step: 2068/531, loss: 0.11212190985679626
2023-01-21 12:53:11.149806: step: 2072/531, loss: 0.015349293127655983
2023-01-21 12:53:12.261121: step: 2076/531, loss: 0.01198873482644558
2023-01-21 12:53:13.403174: step: 2080/531, loss: 4.4345861169858836e-06
2023-01-21 12:53:14.536052: step: 2084/531, loss: 0.03282823786139488
2023-01-21 12:53:15.650006: step: 2088/531, loss: 0.002299356274306774
2023-01-21 12:53:16.803027: step: 2092/531, loss: 0.028997136279940605
2023-01-21 12:53:17.924262: step: 2096/531, loss: 0.0005409240256994963
2023-01-21 12:53:19.064124: step: 2100/531, loss: 0.0026992796920239925
2023-01-21 12:53:20.181697: step: 2104/531, loss: 0.0022093772422522306
2023-01-21 12:53:21.328140: step: 2108/531, loss: 0.00027599334134720266
2023-01-21 12:53:22.423503: step: 2112/531, loss: 0.005663490388542414
2023-01-21 12:53:23.566808: step: 2116/531, loss: 0.001531410263851285
2023-01-21 12:53:24.711317: step: 2120/531, loss: 0.000476837158203125
2023-01-21 12:53:25.853213: step: 2124/531, loss: 0.022632265463471413
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6110520722635494, 'r': 0.7656458055925432, 'f1': 0.6796690307328604}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6368015414258189, 'r': 0.7883124627310674, 'f1': 0.7045030642152945}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5925925925925926, 'r': 0.8888888888888888, 'f1': 0.711111111111111}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6585365853658537, 'r': 0.42857142857142855, 'f1': 0.5192307692307693}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
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': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 12:54:05.800380: step: 4/531, loss: 0.032988931983709335
2023-01-21 12:54:06.938003: step: 8/531, loss: 3.5762786865234375e-05
2023-01-21 12:54:08.072152: step: 12/531, loss: 0.0005677223089151084
2023-01-21 12:54:09.187307: step: 16/531, loss: 0.006481218617409468
2023-01-21 12:54:10.285712: step: 20/531, loss: 0.02497086673974991
2023-01-21 12:54:11.406682: step: 24/531, loss: 0.0042969705536961555
2023-01-21 12:54:12.545308: step: 28/531, loss: 0.0009853362571448088
2023-01-21 12:54:13.652872: step: 32/531, loss: 0.0012187004322186112
2023-01-21 12:54:14.775560: step: 36/531, loss: 0.006720161531120539
2023-01-21 12:54:15.903969: step: 40/531, loss: 8.57353225001134e-05
2023-01-21 12:54:17.021928: step: 44/531, loss: 0.010281180962920189
2023-01-21 12:54:18.159597: step: 48/531, loss: 0.0014828682178631425
2023-01-21 12:54:19.290166: step: 52/531, loss: 0.000152587890625
2023-01-21 12:54:20.396617: step: 56/531, loss: 0.0025002481415867805
2023-01-21 12:54:21.511909: step: 60/531, loss: 9.72747784544481e-06
2023-01-21 12:54:22.634542: step: 64/531, loss: 0.00015115737915039062
2023-01-21 12:54:23.728112: step: 68/531, loss: 0.0012115478748455644
2023-01-21 12:54:24.846712: step: 72/531, loss: 0.026049185544252396
2023-01-21 12:54:25.978835: step: 76/531, loss: 0.00029411318246275187
2023-01-21 12:54:27.153166: step: 80/531, loss: 0.03990078344941139
2023-01-21 12:54:28.292810: step: 84/531, loss: 1.8787384760798886e-05
2023-01-21 12:54:29.420923: step: 88/531, loss: 0.006272793281823397
2023-01-21 12:54:30.593059: step: 92/531, loss: 1.125335711549269e-05
2023-01-21 12:54:31.725837: step: 96/531, loss: 0.0016862868797034025
2023-01-21 12:54:32.854832: step: 100/531, loss: 0.009882260113954544
2023-01-21 12:54:33.954009: step: 104/531, loss: 0.06958713382482529
2023-01-21 12:54:35.110969: step: 108/531, loss: 0.1126624122262001
2023-01-21 12:54:36.231566: step: 112/531, loss: 0.0014297484885901213
2023-01-21 12:54:37.347189: step: 116/531, loss: 0.0012443542946130037
2023-01-21 12:54:38.497094: step: 120/531, loss: -2.8610202207346447e-07
2023-01-21 12:54:39.623314: step: 124/531, loss: 0.05489387363195419
2023-01-21 12:54:40.772435: step: 128/531, loss: 0.0013509751297533512
2023-01-21 12:54:41.933724: step: 132/531, loss: 1.2588501704158261e-05
2023-01-21 12:54:43.096423: step: 136/531, loss: 0.0018597602611407638
2023-01-21 12:54:44.239003: step: 140/531, loss: 0.0075054168701171875
2023-01-21 12:54:45.365321: step: 144/531, loss: 0.0011123657459393144
2023-01-21 12:54:46.479838: step: 148/531, loss: 8.392333256779239e-06
2023-01-21 12:54:47.625115: step: 152/531, loss: 0.009091091342270374
2023-01-21 12:54:48.736108: step: 156/531, loss: 0.00015382767014671117
2023-01-21 12:54:49.852622: step: 160/531, loss: 3.328323145979084e-05
2023-01-21 12:54:50.987766: step: 164/531, loss: 1.9931792849092744e-05
2023-01-21 12:54:52.142976: step: 168/531, loss: 0.03233089670538902
2023-01-21 12:54:53.298908: step: 172/531, loss: 0.0481935515999794
2023-01-21 12:54:54.450269: step: 176/531, loss: 0.00025272369384765625
2023-01-21 12:54:55.564331: step: 180/531, loss: 0.013467979617416859
2023-01-21 12:54:56.683498: step: 184/531, loss: 0.006554984953254461
2023-01-21 12:54:57.799791: step: 188/531, loss: 1.3446808225126006e-05
2023-01-21 12:54:58.948929: step: 192/531, loss: 0.02058105543255806
2023-01-21 12:55:00.090116: step: 196/531, loss: 0.006235265638679266
2023-01-21 12:55:01.230714: step: 200/531, loss: 0.021974945440888405
2023-01-21 12:55:02.361969: step: 204/531, loss: 0.00020799637422896922
2023-01-21 12:55:03.484387: step: 208/531, loss: 0.002738761715590954
2023-01-21 12:55:04.602110: step: 212/531, loss: 1.5544890629826114e-05
2023-01-21 12:55:05.741929: step: 216/531, loss: 0.22516824305057526
2023-01-21 12:55:06.865752: step: 220/531, loss: 0.00028567315894179046
2023-01-21 12:55:08.011312: step: 224/531, loss: 0.016933728009462357
2023-01-21 12:55:09.124881: step: 228/531, loss: 0.0013299941783770919
2023-01-21 12:55:10.246908: step: 232/531, loss: 2.0122528439969756e-05
2023-01-21 12:55:11.339492: step: 236/531, loss: 0.0017433167668059468
2023-01-21 12:55:12.512625: step: 240/531, loss: 0.22139672935009003
2023-01-21 12:55:13.662492: step: 244/531, loss: 7.07626313669607e-05
2023-01-21 12:55:14.780170: step: 248/531, loss: 0.003290367079898715
2023-01-21 12:55:15.882905: step: 252/531, loss: 0.00015249251737259328
2023-01-21 12:55:17.040194: step: 256/531, loss: 0.0002323150692973286
2023-01-21 12:55:18.148224: step: 260/531, loss: 0.111589714884758
2023-01-21 12:55:19.281355: step: 264/531, loss: 0.017264558002352715
2023-01-21 12:55:20.412149: step: 268/531, loss: 0.006297302432358265
2023-01-21 12:55:21.565783: step: 272/531, loss: 0.0006596565362997353
2023-01-21 12:55:22.689125: step: 276/531, loss: 7.882118370616809e-05
2023-01-21 12:55:23.816951: step: 280/531, loss: 0.000331878662109375
2023-01-21 12:55:24.988568: step: 284/531, loss: 0.018483351916074753
2023-01-21 12:55:26.106961: step: 288/531, loss: 1.640319896978326e-05
2023-01-21 12:55:27.259034: step: 292/531, loss: 8.010864803509321e-06
2023-01-21 12:55:28.363852: step: 296/531, loss: 6.380081322276965e-05
2023-01-21 12:55:29.504206: step: 300/531, loss: 0.002920818515121937
2023-01-21 12:55:30.628386: step: 304/531, loss: 0.002807808108627796
2023-01-21 12:55:31.794992: step: 308/531, loss: 7.047654071357101e-05
2023-01-21 12:55:32.926207: step: 312/531, loss: 4.749298022943549e-05
2023-01-21 12:55:34.056967: step: 316/531, loss: 0.09273949265480042
2023-01-21 12:55:35.169342: step: 320/531, loss: 6.198883056640625e-06
2023-01-21 12:55:36.302738: step: 324/531, loss: 0.015950489789247513
2023-01-21 12:55:37.435069: step: 328/531, loss: 0.0003574848233256489
2023-01-21 12:55:38.568481: step: 332/531, loss: 6.523132469737902e-05
2023-01-21 12:55:39.695752: step: 336/531, loss: 0.0012815475929528475
2023-01-21 12:55:40.809855: step: 340/531, loss: 0.00044374464778229594
2023-01-21 12:55:41.946874: step: 344/531, loss: 0.00048694611177779734
2023-01-21 12:55:43.059157: step: 348/531, loss: 2.6416779292048886e-05
2023-01-21 12:55:44.202527: step: 352/531, loss: 0.0003872871457133442
2023-01-21 12:55:45.329542: step: 356/531, loss: 1.2207032341393642e-05
2023-01-21 12:55:46.464169: step: 360/531, loss: 0.00017385483079124242
2023-01-21 12:55:47.555259: step: 364/531, loss: 0.00020160674466751516
2023-01-21 12:55:48.689672: step: 368/531, loss: 0.11150521785020828
2023-01-21 12:55:49.864603: step: 372/531, loss: 0.004104232881218195
2023-01-21 12:55:50.985575: step: 376/531, loss: 0.002468585968017578
2023-01-21 12:55:52.114964: step: 380/531, loss: 0.001498317695222795
2023-01-21 12:55:53.235388: step: 384/531, loss: 0.030260277912020683
2023-01-21 12:55:54.375946: step: 388/531, loss: 0.01050491351634264
2023-01-21 12:55:55.512719: step: 392/531, loss: 0.10444565117359161
2023-01-21 12:55:56.612592: step: 396/531, loss: 0.0016338349087163806
2023-01-21 12:55:57.770613: step: 400/531, loss: 5.245209194981726e-06
2023-01-21 12:55:58.908256: step: 404/531, loss: 0.008989429101347923
2023-01-21 12:56:00.040464: step: 408/531, loss: 0.010001182556152344
2023-01-21 12:56:01.197110: step: 412/531, loss: 0.015207194723188877
2023-01-21 12:56:02.331237: step: 416/531, loss: 0.018520642071962357
2023-01-21 12:56:03.442377: step: 420/531, loss: 0.036756038665771484
2023-01-21 12:56:04.586320: step: 424/531, loss: 0.015356063842773438
2023-01-21 12:56:05.734698: step: 428/531, loss: 0.00039386749267578125
2023-01-21 12:56:06.863228: step: 432/531, loss: 0.0002860069216694683
2023-01-21 12:56:07.991623: step: 436/531, loss: 0.0005212783580645919
2023-01-21 12:56:09.180403: step: 440/531, loss: 0.0030637739691883326
2023-01-21 12:56:10.322931: step: 444/531, loss: 0.0009532928233966231
2023-01-21 12:56:11.489513: step: 448/531, loss: 0.02402172051370144
2023-01-21 12:56:12.657235: step: 452/531, loss: 0.021465493366122246
2023-01-21 12:56:13.809884: step: 456/531, loss: 0.026410698890686035
2023-01-21 12:56:14.938722: step: 460/531, loss: 0.018983269110322
2023-01-21 12:56:16.081752: step: 464/531, loss: 0.0003779888211283833
2023-01-21 12:56:17.214094: step: 468/531, loss: 0.03937859460711479
2023-01-21 12:56:18.335411: step: 472/531, loss: 0.002205467317253351
2023-01-21 12:56:19.447339: step: 476/531, loss: 0.00021839141845703125
2023-01-21 12:56:20.556291: step: 480/531, loss: 0.005312061402946711
2023-01-21 12:56:21.698438: step: 484/531, loss: 0.00025768281193450093
2023-01-21 12:56:22.842499: step: 488/531, loss: 0.044963642954826355
2023-01-21 12:56:23.970458: step: 492/531, loss: 0.0008768081897869706
2023-01-21 12:56:25.098731: step: 496/531, loss: 4.119873119634576e-05
2023-01-21 12:56:26.251597: step: 500/531, loss: 0.035985566675662994
2023-01-21 12:56:27.379348: step: 504/531, loss: 0.0539371520280838
2023-01-21 12:56:28.486223: step: 508/531, loss: 0.005373192019760609
2023-01-21 12:56:29.594015: step: 512/531, loss: 0.06608381122350693
2023-01-21 12:56:30.750755: step: 516/531, loss: 8.39233416627394e-06
2023-01-21 12:56:31.860045: step: 520/531, loss: -2.4795535864541307e-06
2023-01-21 12:56:32.972804: step: 524/531, loss: 0.00039033888606354594
2023-01-21 12:56:34.099104: step: 528/531, loss: 1.2874603271484375e-05
2023-01-21 12:56:35.226211: step: 532/531, loss: 0.0033060074783861637
2023-01-21 12:56:36.364351: step: 536/531, loss: 0.00011219978478038684
2023-01-21 12:56:37.490824: step: 540/531, loss: 0.012881851755082607
2023-01-21 12:56:38.593246: step: 544/531, loss: 7.362366159213707e-05
2023-01-21 12:56:39.715316: step: 548/531, loss: 0.0037229538429528475
2023-01-21 12:56:40.822833: step: 552/531, loss: 0.0003684043767862022
2023-01-21 12:56:41.966761: step: 556/531, loss: 0.05353298410773277
2023-01-21 12:56:43.076835: step: 560/531, loss: 2.7418136596679688e-05
2023-01-21 12:56:44.191236: step: 564/531, loss: -1.1444091796875e-05
2023-01-21 12:56:45.309175: step: 568/531, loss: 0.0003900528245139867
2023-01-21 12:56:46.428926: step: 572/531, loss: 0.011457158252596855
2023-01-21 12:56:47.547252: step: 576/531, loss: 2.0694733393611386e-05
2023-01-21 12:56:48.675943: step: 580/531, loss: 0.0008852005121298134
2023-01-21 12:56:49.794233: step: 584/531, loss: 0.0017203331226482987
2023-01-21 12:56:50.891137: step: 588/531, loss: 0.00034694670466706157
2023-01-21 12:56:52.054913: step: 592/531, loss: 8.034706843318418e-05
2023-01-21 12:56:53.174186: step: 596/531, loss: -4.482268195715733e-06
2023-01-21 12:56:54.327169: step: 600/531, loss: 0.005230140872299671
2023-01-21 12:56:55.459264: step: 604/531, loss: 0.0014334202278405428
2023-01-21 12:56:56.566802: step: 608/531, loss: 0.019589615985751152
2023-01-21 12:56:57.711906: step: 612/531, loss: 0.0001410484401276335
2023-01-21 12:56:58.811564: step: 616/531, loss: 0.0009629249689169228
2023-01-21 12:56:59.945667: step: 620/531, loss: 0.0028882978949695826
2023-01-21 12:57:01.058798: step: 624/531, loss: 0.004574775695800781
2023-01-21 12:57:02.207196: step: 628/531, loss: 0.004901457112282515
2023-01-21 12:57:03.320051: step: 632/531, loss: -9.536743306171047e-08
2023-01-21 12:57:04.429781: step: 636/531, loss: 0.02161111868917942
2023-01-21 12:57:05.552346: step: 640/531, loss: 0.0019255639053881168
2023-01-21 12:57:06.649843: step: 644/531, loss: 0.005345821380615234
2023-01-21 12:57:07.742601: step: 648/531, loss: 0.006084251217544079
2023-01-21 12:57:08.865871: step: 652/531, loss: 0.00032253266545012593
2023-01-21 12:57:09.949768: step: 656/531, loss: 0.011688184924423695
2023-01-21 12:57:11.097751: step: 660/531, loss: 0.00028862952603958547
2023-01-21 12:57:12.259561: step: 664/531, loss: 0.04719047620892525
2023-01-21 12:57:13.391316: step: 668/531, loss: 0.00037722886190749705
2023-01-21 12:57:14.517786: step: 672/531, loss: 0.0001333236723439768
2023-01-21 12:57:15.642969: step: 676/531, loss: 0.0027381896506994963
2023-01-21 12:57:16.801847: step: 680/531, loss: 0.011364174075424671
2023-01-21 12:57:17.926823: step: 684/531, loss: 0.00041828156099654734
2023-01-21 12:57:19.027157: step: 688/531, loss: 7.171630568336695e-05
2023-01-21 12:57:20.152097: step: 692/531, loss: 0.001556777860969305
2023-01-21 12:57:21.290784: step: 696/531, loss: 0.00251255021430552
2023-01-21 12:57:22.415726: step: 700/531, loss: 0.0028877260629087687
2023-01-21 12:57:23.580126: step: 704/531, loss: 0.004551267717033625
2023-01-21 12:57:24.701943: step: 708/531, loss: 1.5449522834387608e-05
2023-01-21 12:57:25.855511: step: 712/531, loss: 0.0038997652009129524
2023-01-21 12:57:26.966051: step: 716/531, loss: 0.02510681003332138
2023-01-21 12:57:28.067031: step: 720/531, loss: 0.003014731453731656
2023-01-21 12:57:29.282122: step: 724/531, loss: 0.0022031785920262337
2023-01-21 12:57:30.467879: step: 728/531, loss: 0.018454933539032936
2023-01-21 12:57:31.561422: step: 732/531, loss: 0.0005566597101278603
2023-01-21 12:57:32.676102: step: 736/531, loss: 0.0005632400861941278
2023-01-21 12:57:33.801537: step: 740/531, loss: 9.098053124034777e-05
2023-01-21 12:57:34.916494: step: 744/531, loss: 0.003599548479542136
2023-01-21 12:57:36.050889: step: 748/531, loss: 2.212524486822076e-05
2023-01-21 12:57:37.192960: step: 752/531, loss: 0.049063682556152344
2023-01-21 12:57:38.331870: step: 756/531, loss: 0.0011266708606854081
2023-01-21 12:57:39.472385: step: 760/531, loss: 1.014467716217041
2023-01-21 12:57:40.620852: step: 764/531, loss: 0.0012990952236577868
2023-01-21 12:57:41.732514: step: 768/531, loss: 0.01313924789428711
2023-01-21 12:57:42.880140: step: 772/531, loss: 0.00031824110192246735
2023-01-21 12:57:44.009226: step: 776/531, loss: 0.04759189859032631
2023-01-21 12:57:45.107687: step: 780/531, loss: 0.0013168335426598787
2023-01-21 12:57:46.238096: step: 784/531, loss: 0.0008058547973632812
2023-01-21 12:57:47.338782: step: 788/531, loss: 0.0012062669266015291
2023-01-21 12:57:48.436146: step: 792/531, loss: 0.0012069225776940584
2023-01-21 12:57:49.584521: step: 796/531, loss: 0.0011704444186761975
2023-01-21 12:57:50.689760: step: 800/531, loss: 0.00019512177095748484
2023-01-21 12:57:51.805632: step: 804/531, loss: 5.6076052715070546e-05
2023-01-21 12:57:52.917791: step: 808/531, loss: 0.01063003484159708
2023-01-21 12:57:54.044805: step: 812/531, loss: 0.0019748688209801912
2023-01-21 12:57:55.178588: step: 816/531, loss: 5.91278057981981e-06
2023-01-21 12:57:56.300052: step: 820/531, loss: 0.0033419609535485506
2023-01-21 12:57:57.424999: step: 824/531, loss: 0.0016244889702647924
2023-01-21 12:57:58.564047: step: 828/531, loss: 0.0007963180541992188
2023-01-21 12:57:59.680458: step: 832/531, loss: 0.01685648038983345
2023-01-21 12:58:00.813008: step: 836/531, loss: 0.004652786068618298
2023-01-21 12:58:01.958211: step: 840/531, loss: 0.47675180435180664
2023-01-21 12:58:03.083625: step: 844/531, loss: 0.031041432172060013
2023-01-21 12:58:04.177316: step: 848/531, loss: 0.0008979797712527215
2023-01-21 12:58:05.321025: step: 852/531, loss: 0.0057926177978515625
2023-01-21 12:58:06.428852: step: 856/531, loss: 0.000316619873046875
2023-01-21 12:58:07.550510: step: 860/531, loss: 0.00021085739717818797
2023-01-21 12:58:08.669034: step: 864/531, loss: 0.04318409040570259
2023-01-21 12:58:09.795955: step: 868/531, loss: 0.00518035888671875
2023-01-21 12:58:10.913070: step: 872/531, loss: 0.004272746853530407
2023-01-21 12:58:12.012251: step: 876/531, loss: 0.013213921338319778
2023-01-21 12:58:13.131353: step: 880/531, loss: 2.326965295651462e-05
2023-01-21 12:58:14.261606: step: 884/531, loss: 1.7881393432617188e-05
2023-01-21 12:58:15.355449: step: 888/531, loss: 0.00012092590623069555
2023-01-21 12:58:16.471001: step: 892/531, loss: 0.0015928269131109118
2023-01-21 12:58:17.583968: step: 896/531, loss: 0.0016504288651049137
2023-01-21 12:58:18.706058: step: 900/531, loss: 0.0006597518804483116
2023-01-21 12:58:19.847358: step: 904/531, loss: 0.006245994474738836
2023-01-21 12:58:20.962610: step: 908/531, loss: -2.822876012942288e-05
2023-01-21 12:58:22.074429: step: 912/531, loss: 8.55445905472152e-05
2023-01-21 12:58:23.209791: step: 916/531, loss: 0.00015182494826149195
2023-01-21 12:58:24.322941: step: 920/531, loss: 0.001562786172144115
2023-01-21 12:58:25.471087: step: 924/531, loss: 0.008929251693189144
2023-01-21 12:58:26.569685: step: 928/531, loss: 1.1634827387752011e-05
2023-01-21 12:58:27.686267: step: 932/531, loss: 0.011922646313905716
2023-01-21 12:58:28.784839: step: 936/531, loss: 0.00032491685124114156
2023-01-21 12:58:29.889022: step: 940/531, loss: 0.020729923620820045
2023-01-21 12:58:31.014024: step: 944/531, loss: 0.0006745338323526084
2023-01-21 12:58:32.140413: step: 948/531, loss: 0.008918190374970436
2023-01-21 12:58:33.262974: step: 952/531, loss: 0.0005529403570108116
2023-01-21 12:58:34.391633: step: 956/531, loss: 0.0022972107399255037
2023-01-21 12:58:35.519073: step: 960/531, loss: 0.005454063415527344
2023-01-21 12:58:36.644934: step: 964/531, loss: 0.0020036697387695312
2023-01-21 12:58:37.771456: step: 968/531, loss: 0.0004918098566122353
2023-01-21 12:58:38.897438: step: 972/531, loss: 0.2412470281124115
2023-01-21 12:58:40.017931: step: 976/531, loss: 5.4931642807787284e-05
2023-01-21 12:58:41.117949: step: 980/531, loss: 0.0005280360346660018
2023-01-21 12:58:42.267367: step: 984/531, loss: 0.010000323876738548
2023-01-21 12:58:43.361093: step: 988/531, loss: 0.002407550811767578
2023-01-21 12:58:44.496701: step: 992/531, loss: 0.005508804228156805
2023-01-21 12:58:45.602047: step: 996/531, loss: 2.0885468984488398e-05
2023-01-21 12:58:46.742907: step: 1000/531, loss: 0.023827172815799713
2023-01-21 12:58:47.884435: step: 1004/531, loss: 0.023612594231963158
2023-01-21 12:58:48.986095: step: 1008/531, loss: 0.00010824203491210938
2023-01-21 12:58:50.149075: step: 1012/531, loss: 0.0015560149913653731
2023-01-21 12:58:51.269202: step: 1016/531, loss: 0.007282542996108532
2023-01-21 12:58:52.380913: step: 1020/531, loss: 0.040325406938791275
2023-01-21 12:58:53.505740: step: 1024/531, loss: 5.264282299322076e-05
2023-01-21 12:58:54.638732: step: 1028/531, loss: 0.009829758666455746
2023-01-21 12:58:55.766566: step: 1032/531, loss: 0.00015773772611282766
2023-01-21 12:58:56.878062: step: 1036/531, loss: 0.0020146372262388468
2023-01-21 12:58:58.021191: step: 1040/531, loss: 0.005702400580048561
2023-01-21 12:58:59.164253: step: 1044/531, loss: 0.000550901866517961
2023-01-21 12:59:00.314192: step: 1048/531, loss: 0.026949310675263405
2023-01-21 12:59:01.436712: step: 1052/531, loss: 0.00015797615924384445
2023-01-21 12:59:02.536588: step: 1056/531, loss: 0.00018539429584052414
2023-01-21 12:59:03.669971: step: 1060/531, loss: 0.0007648468017578125
2023-01-21 12:59:04.814018: step: 1064/531, loss: 3.337860562169226e-06
2023-01-21 12:59:05.937548: step: 1068/531, loss: 0.07659760117530823
2023-01-21 12:59:07.074938: step: 1072/531, loss: 0.001273679779842496
2023-01-21 12:59:08.199199: step: 1076/531, loss: 0.0001922607480082661
2023-01-21 12:59:09.324898: step: 1080/531, loss: 0.026928521692752838
2023-01-21 12:59:10.512913: step: 1084/531, loss: 0.00029792787972837687
2023-01-21 12:59:11.643028: step: 1088/531, loss: 0.01058197021484375
2023-01-21 12:59:12.789269: step: 1092/531, loss: 6.88552827341482e-05
2023-01-21 12:59:13.906008: step: 1096/531, loss: 0.0004398346063680947
2023-01-21 12:59:15.046569: step: 1100/531, loss: 0.004431343171745539
2023-01-21 12:59:16.181148: step: 1104/531, loss: 0.012441063299775124
2023-01-21 12:59:17.343261: step: 1108/531, loss: 0.00021057129197288305
2023-01-21 12:59:18.474859: step: 1112/531, loss: 0.0002458572562318295
2023-01-21 12:59:19.589646: step: 1116/531, loss: 0.0171648021787405
2023-01-21 12:59:20.719973: step: 1120/531, loss: 2.517700158932712e-05
2023-01-21 12:59:21.824953: step: 1124/531, loss: 3.2424929941043956e-06
2023-01-21 12:59:22.942243: step: 1128/531, loss: 0.0006754875648766756
2023-01-21 12:59:24.090238: step: 1132/531, loss: -1.9073486328125e-06
2023-01-21 12:59:25.199094: step: 1136/531, loss: 1.182556115963962e-05
2023-01-21 12:59:26.325671: step: 1140/531, loss: 0.00010833739361260086
2023-01-21 12:59:27.425333: step: 1144/531, loss: 0.002923393389210105
2023-01-21 12:59:28.537718: step: 1148/531, loss: 0.3141302168369293
2023-01-21 12:59:29.642433: step: 1152/531, loss: 0.027521325275301933
2023-01-21 12:59:30.773970: step: 1156/531, loss: 0.0006405830499716103
2023-01-21 12:59:31.880279: step: 1160/531, loss: 0.02390575408935547
2023-01-21 12:59:32.990002: step: 1164/531, loss: 0.011572551913559437
2023-01-21 12:59:34.097636: step: 1168/531, loss: 0.06204252317547798
2023-01-21 12:59:35.223384: step: 1172/531, loss: 0.009407997131347656
2023-01-21 12:59:36.367869: step: 1176/531, loss: 8.773804438533261e-06
2023-01-21 12:59:37.460141: step: 1180/531, loss: 0.015708064660429955
2023-01-21 12:59:38.592697: step: 1184/531, loss: 0.0008949279435910285
2023-01-21 12:59:39.719374: step: 1188/531, loss: 0.0006538390880450606
2023-01-21 12:59:40.819382: step: 1192/531, loss: 6.9618222369172145e-06
2023-01-21 12:59:41.947010: step: 1196/531, loss: 0.002063560765236616
2023-01-21 12:59:43.055121: step: 1200/531, loss: 0.0012581349583342671
2023-01-21 12:59:44.192351: step: 1204/531, loss: 9.661913645686582e-05
2023-01-21 12:59:45.320455: step: 1208/531, loss: 1.773834264895413e-05
2023-01-21 12:59:46.478487: step: 1212/531, loss: 0.03893623128533363
2023-01-21 12:59:47.622661: step: 1216/531, loss: -1.4066696166992188e-05
2023-01-21 12:59:48.757938: step: 1220/531, loss: 0.00017309188842773438
2023-01-21 12:59:49.872451: step: 1224/531, loss: 0.022786427289247513
2023-01-21 12:59:50.979648: step: 1228/531, loss: 0.002492666244506836
2023-01-21 12:59:52.081933: step: 1232/531, loss: 0.00020456314086914062
2023-01-21 12:59:53.167513: step: 1236/531, loss: 0.0006899833679199219
2023-01-21 12:59:54.324742: step: 1240/531, loss: 0.0014776230091229081
2023-01-21 12:59:55.435219: step: 1244/531, loss: 0.004159402567893267
2023-01-21 12:59:56.555959: step: 1248/531, loss: 0.012343978509306908
2023-01-21 12:59:57.682638: step: 1252/531, loss: 0.002485656877979636
2023-01-21 12:59:58.833174: step: 1256/531, loss: 0.08677548915147781
2023-01-21 12:59:59.960240: step: 1260/531, loss: 0.0012414931552484632
2023-01-21 13:00:01.104354: step: 1264/531, loss: 1.33514404296875e-05
2023-01-21 13:00:02.216907: step: 1268/531, loss: 0.00011601448932196945
2023-01-21 13:00:03.346244: step: 1272/531, loss: 0.023260975256562233
2023-01-21 13:00:04.482866: step: 1276/531, loss: 0.00025663376436568797
2023-01-21 13:00:05.591333: step: 1280/531, loss: 0.0023916244972497225
2023-01-21 13:00:06.732191: step: 1284/531, loss: 0.000912189541850239
2023-01-21 13:00:07.869806: step: 1288/531, loss: 0.00010032653517555445
2023-01-21 13:00:08.978342: step: 1292/531, loss: 0.0008419037330895662
2023-01-21 13:00:10.105675: step: 1296/531, loss: 3.24249267578125e-05
2023-01-21 13:00:11.245090: step: 1300/531, loss: 0.05444631725549698
2023-01-21 13:00:12.394980: step: 1304/531, loss: 0.03429603576660156
2023-01-21 13:00:13.532481: step: 1308/531, loss: 3.814697265625e-06
2023-01-21 13:00:14.662137: step: 1312/531, loss: 0.002637767931446433
2023-01-21 13:00:15.792670: step: 1316/531, loss: 0.0008985042804852128
2023-01-21 13:00:16.933747: step: 1320/531, loss: 0.00013408661470748484
2023-01-21 13:00:18.081370: step: 1324/531, loss: 0.0054336548782885075
2023-01-21 13:00:19.196130: step: 1328/531, loss: 1.106262243411038e-05
2023-01-21 13:00:20.323420: step: 1332/531, loss: 0.013496018014848232
2023-01-21 13:00:21.466308: step: 1336/531, loss: 0.007743263617157936
2023-01-21 13:00:22.587908: step: 1340/531, loss: 0.015787268057465553
2023-01-21 13:00:23.719034: step: 1344/531, loss: 1.144409225162235e-06
2023-01-21 13:00:24.816579: step: 1348/531, loss: 0.0005481719854287803
2023-01-21 13:00:25.931266: step: 1352/531, loss: 4.787445141118951e-05
2023-01-21 13:00:27.127048: step: 1356/531, loss: 6.50405854685232e-05
2023-01-21 13:00:28.252613: step: 1360/531, loss: 0.004395985510200262
2023-01-21 13:00:29.404500: step: 1364/531, loss: 0.00157337193377316
2023-01-21 13:00:30.536878: step: 1368/531, loss: 0.005836129654198885
2023-01-21 13:00:31.647108: step: 1372/531, loss: 4.9114227294921875e-05
2023-01-21 13:00:32.767528: step: 1376/531, loss: 0.013924216851592064
2023-01-21 13:00:33.906877: step: 1380/531, loss: 0.00018959045701194555
2023-01-21 13:00:35.016381: step: 1384/531, loss: 7.266998727573082e-05
2023-01-21 13:00:36.163668: step: 1388/531, loss: 0.0009172439458779991
2023-01-21 13:00:37.284820: step: 1392/531, loss: 0.0034059525933116674
2023-01-21 13:00:38.409914: step: 1396/531, loss: 0.0017912863986566663
2023-01-21 13:00:39.515704: step: 1400/531, loss: 0.0004226684686727822
2023-01-21 13:00:40.652349: step: 1404/531, loss: 0.00026454924955032766
2023-01-21 13:00:41.765659: step: 1408/531, loss: 0.21079564094543457
2023-01-21 13:00:42.878143: step: 1412/531, loss: 4.711151268566027e-05
2023-01-21 13:00:44.023704: step: 1416/531, loss: 0.0005231857649050653
2023-01-21 13:00:45.147294: step: 1420/531, loss: 0.01396102923899889
2023-01-21 13:00:46.313287: step: 1424/531, loss: 0.07530689239501953
2023-01-21 13:00:47.470468: step: 1428/531, loss: 0.006221294868737459
2023-01-21 13:00:48.590282: step: 1432/531, loss: 0.011235427111387253
2023-01-21 13:00:49.728889: step: 1436/531, loss: 0.011354828253388405
2023-01-21 13:00:50.878487: step: 1440/531, loss: 0.015910720452666283
2023-01-21 13:00:52.004655: step: 1444/531, loss: 0.007373619358986616
2023-01-21 13:00:53.141174: step: 1448/531, loss: 0.014717578887939453
2023-01-21 13:00:54.261008: step: 1452/531, loss: 0.010570145212113857
2023-01-21 13:00:55.378979: step: 1456/531, loss: 0.006151771638542414
2023-01-21 13:00:56.537298: step: 1460/531, loss: 0.00028104783268645406
2023-01-21 13:00:57.696065: step: 1464/531, loss: 0.0011564254527911544
2023-01-21 13:00:58.812606: step: 1468/531, loss: 0.0002611160452943295
2023-01-21 13:00:59.940883: step: 1472/531, loss: 0.03071126900613308
2023-01-21 13:01:01.065606: step: 1476/531, loss: 0.3324892222881317
2023-01-21 13:01:02.180859: step: 1480/531, loss: 0.00020713805861305445
2023-01-21 13:01:03.326567: step: 1484/531, loss: 0.07565231621265411
2023-01-21 13:01:04.456761: step: 1488/531, loss: 0.006416225340217352
2023-01-21 13:01:05.556142: step: 1492/531, loss: 0.007015132810920477
2023-01-21 13:01:06.700267: step: 1496/531, loss: 0.00022058487229514867
2023-01-21 13:01:07.790261: step: 1500/531, loss: 0.00217094412073493
2023-01-21 13:01:08.901694: step: 1504/531, loss: 0.00021066665067337453
2023-01-21 13:01:10.045513: step: 1508/531, loss: 1.430511474609375e-05
2023-01-21 13:01:11.155700: step: 1512/531, loss: 0.0016808509826660156
2023-01-21 13:01:12.263521: step: 1516/531, loss: 0.0004983901744708419
2023-01-21 13:01:13.359670: step: 1520/531, loss: 0.05423259735107422
2023-01-21 13:01:14.474633: step: 1524/531, loss: 0.0007426739321090281
2023-01-21 13:01:15.587858: step: 1528/531, loss: 0.02074751816689968
2023-01-21 13:01:16.699936: step: 1532/531, loss: 0.0033749579451978207
2023-01-21 13:01:17.813852: step: 1536/531, loss: 0.0012913703685626388
2023-01-21 13:01:18.919010: step: 1540/531, loss: 0.0019307136535644531
2023-01-21 13:01:20.055354: step: 1544/531, loss: 0.0008337974431924522
2023-01-21 13:01:21.170034: step: 1548/531, loss: 0.01390991173684597
2023-01-21 13:01:22.311002: step: 1552/531, loss: 0.001444149063900113
2023-01-21 13:01:23.436273: step: 1556/531, loss: 0.03240060806274414
2023-01-21 13:01:24.539210: step: 1560/531, loss: 0.006424617953598499
2023-01-21 13:01:25.695450: step: 1564/531, loss: 0.0003888130304403603
2023-01-21 13:01:26.841666: step: 1568/531, loss: 0.0005902290577068925
2023-01-21 13:01:27.975445: step: 1572/531, loss: 0.008753872476518154
2023-01-21 13:01:29.094750: step: 1576/531, loss: 0.0009785651927813888
2023-01-21 13:01:30.232647: step: 1580/531, loss: 0.031662750989198685
2023-01-21 13:01:31.368456: step: 1584/531, loss: 0.036309242248535156
2023-01-21 13:01:32.521188: step: 1588/531, loss: 4.9877166020451114e-05
2023-01-21 13:01:33.616371: step: 1592/531, loss: 0.002708530519157648
2023-01-21 13:01:34.756430: step: 1596/531, loss: 0.041326142847537994
2023-01-21 13:01:35.927307: step: 1600/531, loss: 0.006421852391213179
2023-01-21 13:01:37.046583: step: 1604/531, loss: 2.0408631826285273e-05
2023-01-21 13:01:38.180363: step: 1608/531, loss: 0.00016663075075484812
2023-01-21 13:01:39.312742: step: 1612/531, loss: 0.0023912431206554174
2023-01-21 13:01:40.420320: step: 1616/531, loss: 0.0002895355282817036
2023-01-21 13:01:41.524506: step: 1620/531, loss: 0.04916572570800781
2023-01-21 13:01:42.624831: step: 1624/531, loss: 0.008287524804472923
2023-01-21 13:01:43.737583: step: 1628/531, loss: 0.0009645462268963456
2023-01-21 13:01:44.894442: step: 1632/531, loss: 0.05920391157269478
2023-01-21 13:01:46.009862: step: 1636/531, loss: 0.0001069068894139491
2023-01-21 13:01:47.130302: step: 1640/531, loss: 0.04209880903363228
2023-01-21 13:01:48.262303: step: 1644/531, loss: 0.0009475707774981856
2023-01-21 13:01:49.364746: step: 1648/531, loss: 0.000211620339541696
2023-01-21 13:01:50.511281: step: 1652/531, loss: 0.000320243852911517
2023-01-21 13:01:51.662930: step: 1656/531, loss: 0.23246383666992188
2023-01-21 13:01:52.774502: step: 1660/531, loss: 0.1031288206577301
2023-01-21 13:01:53.920518: step: 1664/531, loss: 0.06617667526006699
2023-01-21 13:01:55.028579: step: 1668/531, loss: 0.0009390831692144275
2023-01-21 13:01:56.146696: step: 1672/531, loss: 0.11262092739343643
2023-01-21 13:01:57.281424: step: 1676/531, loss: 0.0010297298431396484
2023-01-21 13:01:58.424999: step: 1680/531, loss: 0.004846763797104359
2023-01-21 13:01:59.526426: step: 1684/531, loss: 3.175735764671117e-05
2023-01-21 13:02:00.640910: step: 1688/531, loss: 0.0006113052368164062
2023-01-21 13:02:01.754156: step: 1692/531, loss: 0.0007187515147961676
2023-01-21 13:02:02.830348: step: 1696/531, loss: 5.226135181146674e-05
2023-01-21 13:02:03.954104: step: 1700/531, loss: 7.371902756858617e-05
2023-01-21 13:02:05.088875: step: 1704/531, loss: 0.00794219970703125
2023-01-21 13:02:06.216104: step: 1708/531, loss: 0.007822847925126553
2023-01-21 13:02:07.332893: step: 1712/531, loss: 0.01797313801944256
2023-01-21 13:02:08.452666: step: 1716/531, loss: 0.002474498702213168
2023-01-21 13:02:09.573141: step: 1720/531, loss: 0.0002582549932412803
2023-01-21 13:02:10.690883: step: 1724/531, loss: 0.022548770532011986
2023-01-21 13:02:11.832200: step: 1728/531, loss: 0.01644744910299778
2023-01-21 13:02:13.023091: step: 1732/531, loss: 0.0008003234979696572
2023-01-21 13:02:14.143331: step: 1736/531, loss: 0.005929755978286266
2023-01-21 13:02:15.278458: step: 1740/531, loss: 5.53131121705519e-06
2023-01-21 13:02:16.453555: step: 1744/531, loss: 0.0031376841943711042
2023-01-21 13:02:17.578303: step: 1748/531, loss: 5.5313107623078395e-06
2023-01-21 13:02:18.692734: step: 1752/531, loss: 3.161430504405871e-05
2023-01-21 13:02:19.791320: step: 1756/531, loss: 0.027098752558231354
2023-01-21 13:02:20.887537: step: 1760/531, loss: 5.540847996599041e-05
2023-01-21 13:02:22.002903: step: 1764/531, loss: 9.910017979564145e-05
2023-01-21 13:02:23.121978: step: 1768/531, loss: 0.00046882632886990905
2023-01-21 13:02:24.236957: step: 1772/531, loss: 0.0038802148774266243
2023-01-21 13:02:25.361961: step: 1776/531, loss: 0.0005563736194744706
2023-01-21 13:02:26.485342: step: 1780/531, loss: 0.0007347107166424394
2023-01-21 13:02:27.618078: step: 1784/531, loss: 0.02941417694091797
2023-01-21 13:02:28.745330: step: 1788/531, loss: 0.0036274672020226717
2023-01-21 13:02:29.850776: step: 1792/531, loss: 0.015027904883027077
2023-01-21 13:02:31.004963: step: 1796/531, loss: 0.015047645196318626
2023-01-21 13:02:32.131144: step: 1800/531, loss: 0.00018138886662200093
2023-01-21 13:02:33.238826: step: 1804/531, loss: 0.009407997131347656
2023-01-21 13:02:34.394764: step: 1808/531, loss: 0.002166652586311102
2023-01-21 13:02:35.540026: step: 1812/531, loss: 0.0004493713495321572
2023-01-21 13:02:36.670752: step: 1816/531, loss: 0.010866832919418812
2023-01-21 13:02:37.788024: step: 1820/531, loss: 0.11321182548999786
2023-01-21 13:02:38.919648: step: 1824/531, loss: 0.0016396522987633944
2023-01-21 13:02:40.029752: step: 1828/531, loss: 0.00016479493933729827
2023-01-21 13:02:41.166558: step: 1832/531, loss: 0.0028811455704271793
2023-01-21 13:02:42.279609: step: 1836/531, loss: 0.0001412391575286165
2023-01-21 13:02:43.388793: step: 1840/531, loss: 0.0001396656152792275
2023-01-21 13:02:44.477993: step: 1844/531, loss: 0.003260803408920765
2023-01-21 13:02:45.601182: step: 1848/531, loss: 1.4019012269272935e-05
2023-01-21 13:02:46.688852: step: 1852/531, loss: 0.016576098278164864
2023-01-21 13:02:47.826592: step: 1856/531, loss: 1.4781951904296875e-05
2023-01-21 13:02:48.967253: step: 1860/531, loss: 0.024943161755800247
2023-01-21 13:02:50.122380: step: 1864/531, loss: 0.044161032885313034
2023-01-21 13:02:51.270349: step: 1868/531, loss: 0.029897499829530716
2023-01-21 13:02:52.387968: step: 1872/531, loss: 0.00079517369158566
2023-01-21 13:02:53.502044: step: 1876/531, loss: 0.0002688407839741558
2023-01-21 13:02:54.610077: step: 1880/531, loss: 0.000251340854447335
2023-01-21 13:02:55.738364: step: 1884/531, loss: 0.009488009847700596
2023-01-21 13:02:56.874736: step: 1888/531, loss: 0.0004185676807537675
2023-01-21 13:02:58.005719: step: 1892/531, loss: 0.0014828682178631425
2023-01-21 13:02:59.147217: step: 1896/531, loss: 0.010054397396743298
2023-01-21 13:03:00.273854: step: 1900/531, loss: 0.00030498503474518657
2023-01-21 13:03:01.370900: step: 1904/531, loss: 0.00819253921508789
2023-01-21 13:03:02.481276: step: 1908/531, loss: 0.0027527809143066406
2023-01-21 13:03:03.618055: step: 1912/531, loss: 0.0002662658807821572
2023-01-21 13:03:04.736075: step: 1916/531, loss: 0.018985271453857422
2023-01-21 13:03:05.886436: step: 1920/531, loss: 1.7452241081628017e-05
2023-01-21 13:03:06.977897: step: 1924/531, loss: 5.016327486373484e-05
2023-01-21 13:03:08.097754: step: 1928/531, loss: 0.04257850721478462
2023-01-21 13:03:09.216680: step: 1932/531, loss: 0.0003082275507040322
2023-01-21 13:03:10.343690: step: 1936/531, loss: 0.0008853912586346269
2023-01-21 13:03:11.512415: step: 1940/531, loss: 0.003740501357242465
2023-01-21 13:03:12.639288: step: 1944/531, loss: 5.245208740234375e-05
2023-01-21 13:03:13.762902: step: 1948/531, loss: 0.0013359070289880037
2023-01-21 13:03:14.875759: step: 1952/531, loss: 0.0005120754358358681
2023-01-21 13:03:15.985158: step: 1956/531, loss: 0.002509784884750843
2023-01-21 13:03:17.099387: step: 1960/531, loss: 6.785392906749621e-05
2023-01-21 13:03:18.240903: step: 1964/531, loss: 7.591248140670359e-05
2023-01-21 13:03:19.394080: step: 1968/531, loss: 0.0034355639945715666
2023-01-21 13:03:20.513560: step: 1972/531, loss: 0.07772121578454971
2023-01-21 13:03:21.630943: step: 1976/531, loss: 0.02805786207318306
2023-01-21 13:03:22.750700: step: 1980/531, loss: 0.003248119493946433
2023-01-21 13:03:23.882673: step: 1984/531, loss: 0.0015300750965252519
2023-01-21 13:03:25.012529: step: 1988/531, loss: 0.021108437329530716
2023-01-21 13:03:26.128223: step: 1992/531, loss: 0.005775833036750555
2023-01-21 13:03:27.240518: step: 1996/531, loss: 0.007290506269782782
2023-01-21 13:03:28.381042: step: 2000/531, loss: 9.021758887683973e-05
2023-01-21 13:03:29.492357: step: 2004/531, loss: 0.0032418249174952507
2023-01-21 13:03:30.597362: step: 2008/531, loss: 0.013883685693144798
2023-01-21 13:03:31.741075: step: 2012/531, loss: 0.0002465248107910156
2023-01-21 13:03:32.841636: step: 2016/531, loss: 0.0011563062435016036
2023-01-21 13:03:33.985974: step: 2020/531, loss: 0.004359436221420765
2023-01-21 13:03:35.110792: step: 2024/531, loss: 0.0018100739689543843
2023-01-21 13:03:36.230695: step: 2028/531, loss: 0.0007214070064947009
2023-01-21 13:03:37.402751: step: 2032/531, loss: 0.012652111239731312
2023-01-21 13:03:38.519445: step: 2036/531, loss: 0.0005445242277346551
2023-01-21 13:03:39.658069: step: 2040/531, loss: 0.0241335891187191
2023-01-21 13:03:40.794437: step: 2044/531, loss: 0.0007307052728720009
2023-01-21 13:03:41.933759: step: 2048/531, loss: 0.0012901306618005037
2023-01-21 13:03:43.045805: step: 2052/531, loss: 0.0036148070357739925
2023-01-21 13:03:44.164212: step: 2056/531, loss: 0.04683256149291992
2023-01-21 13:03:45.283262: step: 2060/531, loss: 0.0006697654607705772
2023-01-21 13:03:46.402472: step: 2064/531, loss: 0.0007224082946777344
2023-01-21 13:03:47.529439: step: 2068/531, loss: 0.000293731689453125
2023-01-21 13:03:48.645031: step: 2072/531, loss: 0.002260398818179965
2023-01-21 13:03:49.757276: step: 2076/531, loss: 0.0008077621459960938
2023-01-21 13:03:50.889500: step: 2080/531, loss: 7.25746140233241e-05
2023-01-21 13:03:52.020588: step: 2084/531, loss: 0.0035633088555186987
2023-01-21 13:03:53.136232: step: 2088/531, loss: 0.00157337193377316
2023-01-21 13:03:54.272480: step: 2092/531, loss: 0.00011596679541980848
2023-01-21 13:03:55.373234: step: 2096/531, loss: 1.3828278497385327e-05
2023-01-21 13:03:56.471754: step: 2100/531, loss: 1.62124638336536e-06
2023-01-21 13:03:57.604852: step: 2104/531, loss: 0.011295795440673828
2023-01-21 13:03:58.734527: step: 2108/531, loss: 0.003174114041030407
2023-01-21 13:03:59.839831: step: 2112/531, loss: 1.068115216185106e-05
2023-01-21 13:04:00.929700: step: 2116/531, loss: 0.00024347304133698344
2023-01-21 13:04:02.091010: step: 2120/531, loss: 0.00036296845064498484
2023-01-21 13:04:03.220938: step: 2124/531, loss: 6.67572021484375e-06
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5973360655737705, 'r': 0.7762982689747004, 'f1': 0.6751592356687898}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6263632053105738, 'r': 0.7877161598091831, 'f1': 0.6978341257263604}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.5697674418604651, 'r': 0.9074074074074074, 'f1': 0.7}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.5344827586206896, 'r': 0.49206349206349204, 'f1': 0.512396694214876}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.4666666666666667, 'r': 0.5833333333333334, 'f1': 0.5185185185185186}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 26
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 13:04:43.648813: step: 4/531, loss: 0.00045347216655500233
2023-01-21 13:04:44.775433: step: 8/531, loss: 0.04642972722649574
2023-01-21 13:04:45.929764: step: 12/531, loss: 0.0029207230545580387
2023-01-21 13:04:47.071153: step: 16/531, loss: 0.03157081454992294
2023-01-21 13:04:48.199220: step: 20/531, loss: 0.001370334648527205
2023-01-21 13:04:49.323395: step: 24/531, loss: 0.0006361007690429688
2023-01-21 13:04:50.437582: step: 28/531, loss: 2.6226043701171875e-05
2023-01-21 13:04:51.547913: step: 32/531, loss: 0.00036277773324400187
2023-01-21 13:04:52.677543: step: 36/531, loss: 0.0066581727005541325
2023-01-21 13:04:53.812098: step: 40/531, loss: 0.01384277455508709
2023-01-21 13:04:54.912448: step: 44/531, loss: 0.007408905308693647
2023-01-21 13:04:56.060314: step: 48/531, loss: 0.018971920013427734
2023-01-21 13:04:57.167233: step: 52/531, loss: 6.866455078125e-05
2023-01-21 13:04:58.256940: step: 56/531, loss: 7.629394076502649e-06
2023-01-21 13:04:59.370177: step: 60/531, loss: 0.004829817917197943
2023-01-21 13:05:00.516562: step: 64/531, loss: 0.03000030666589737
2023-01-21 13:05:01.663430: step: 68/531, loss: 0.0023136138916015625
2023-01-21 13:05:02.790235: step: 72/531, loss: 1.5354156857938506e-05
2023-01-21 13:05:03.883274: step: 76/531, loss: 1.2397767022775952e-05
2023-01-21 13:05:05.015623: step: 80/531, loss: -9.5367431640625e-07
2023-01-21 13:05:06.136427: step: 84/531, loss: 0.0015115260612219572
2023-01-21 13:05:07.255567: step: 88/531, loss: 0.0003132820129394531
2023-01-21 13:05:08.398395: step: 92/531, loss: 2.765655517578125e-05
2023-01-21 13:05:09.522085: step: 96/531, loss: 0.12018032371997833
2023-01-21 13:05:10.629619: step: 100/531, loss: 0.06277842819690704
2023-01-21 13:05:11.785442: step: 104/531, loss: 0.0002703666687011719
2023-01-21 13:05:12.900593: step: 108/531, loss: 0.015691854059696198
2023-01-21 13:05:14.031889: step: 112/531, loss: 0.3374547064304352
2023-01-21 13:05:15.151366: step: 116/531, loss: 0.00046200753422454
2023-01-21 13:05:16.302121: step: 120/531, loss: 0.0026158334221690893
2023-01-21 13:05:17.420004: step: 124/531, loss: 0.0001748085196595639
2023-01-21 13:05:18.569343: step: 128/531, loss: 0.0006259918445721269
2023-01-21 13:05:19.694774: step: 132/531, loss: 0.004377841949462891
2023-01-21 13:05:20.812793: step: 136/531, loss: 0.0008360862266272306
2023-01-21 13:05:21.921514: step: 140/531, loss: 0.011205673217773438
2023-01-21 13:05:23.052658: step: 144/531, loss: 2.1022558939876035e-05
2023-01-21 13:05:24.213773: step: 148/531, loss: 0.0019003868801519275
2023-01-21 13:05:25.327407: step: 152/531, loss: 3.814697720372351e-06
2023-01-21 13:05:26.481606: step: 156/531, loss: 0.00014352799917105585
2023-01-21 13:05:27.611391: step: 160/531, loss: 0.022900773212313652
2023-01-21 13:05:28.714802: step: 164/531, loss: 7.2479248046875e-05
2023-01-21 13:05:29.824049: step: 168/531, loss: 0.00036110877408646047
2023-01-21 13:05:30.952456: step: 172/531, loss: 0.016541291028261185
2023-01-21 13:05:32.091694: step: 176/531, loss: 0.0001334190455963835
2023-01-21 13:05:33.222895: step: 180/531, loss: 0.06560993194580078
2023-01-21 13:05:34.363195: step: 184/531, loss: 0.009336281567811966
2023-01-21 13:05:35.490593: step: 188/531, loss: 0.00011510849435580894
2023-01-21 13:05:36.637391: step: 192/531, loss: 4.0054324017546605e-06
2023-01-21 13:05:37.778281: step: 196/531, loss: 0.11933369934558868
2023-01-21 13:05:38.925914: step: 200/531, loss: 4.75883498438634e-05
2023-01-21 13:05:40.018571: step: 204/531, loss: 0.011086845770478249
2023-01-21 13:05:41.133072: step: 208/531, loss: 0.000162029275088571
2023-01-21 13:05:42.259586: step: 212/531, loss: 0.13398189842700958
2023-01-21 13:05:43.395472: step: 216/531, loss: 4.3582916987361386e-05
2023-01-21 13:05:44.527224: step: 220/531, loss: 0.0003517150762490928
2023-01-21 13:05:45.631307: step: 224/531, loss: -3.8146970382513246e-07
2023-01-21 13:05:46.763079: step: 228/531, loss: 0.00023288727970793843
2023-01-21 13:05:47.895347: step: 232/531, loss: 0.0023923872504383326
2023-01-21 13:05:48.992561: step: 236/531, loss: 0.0022612097673118114
2023-01-21 13:05:50.100769: step: 240/531, loss: 0.0009933114051818848
2023-01-21 13:05:51.206834: step: 244/531, loss: 0.0006024837493896484
2023-01-21 13:05:52.315502: step: 248/531, loss: 0.0012908459175378084
2023-01-21 13:05:53.448161: step: 252/531, loss: 4.816055661649443e-05
2023-01-21 13:05:54.571319: step: 256/531, loss: 0.01306462287902832
2023-01-21 13:05:55.712073: step: 260/531, loss: 0.008605623617768288
2023-01-21 13:05:56.805947: step: 264/531, loss: 0.011499309912323952
2023-01-21 13:05:57.947118: step: 268/531, loss: 1.640319896978326e-05
2023-01-21 13:05:59.062811: step: 272/531, loss: 0.00666274968534708
2023-01-21 13:06:00.193844: step: 276/531, loss: 4.8255922592943534e-05
2023-01-21 13:06:01.312009: step: 280/531, loss: 0.006525421515107155
2023-01-21 13:06:02.418760: step: 284/531, loss: 5.6838991440599784e-05
2023-01-21 13:06:03.524298: step: 288/531, loss: 3.070831371587701e-05
2023-01-21 13:06:04.652303: step: 292/531, loss: 0.014255332760512829
2023-01-21 13:06:05.777767: step: 296/531, loss: 0.0013267993927001953
2023-01-21 13:06:06.914115: step: 300/531, loss: 0.000812530517578125
2023-01-21 13:06:08.076373: step: 304/531, loss: 0.017866231501102448
2023-01-21 13:06:09.187832: step: 308/531, loss: 0.04280805587768555
2023-01-21 13:06:10.308007: step: 312/531, loss: 0.0016048431862145662
2023-01-21 13:06:11.439055: step: 316/531, loss: 0.016740798950195312
2023-01-21 13:06:12.600917: step: 320/531, loss: 0.03598659113049507
2023-01-21 13:06:13.721107: step: 324/531, loss: 0.0008739471668377519
2023-01-21 13:06:14.835584: step: 328/531, loss: 0.0016384958289563656
2023-01-21 13:06:15.965446: step: 332/531, loss: 0.013918494805693626
2023-01-21 13:06:17.055035: step: 336/531, loss: 0.00021538735018111765
2023-01-21 13:06:18.179022: step: 340/531, loss: 0.002173042157664895
2023-01-21 13:06:19.321044: step: 344/531, loss: 0.016356898471713066
2023-01-21 13:06:20.426612: step: 348/531, loss: 0.006673621945083141
2023-01-21 13:06:21.526750: step: 352/531, loss: 0.007123851682990789
2023-01-21 13:06:22.640258: step: 356/531, loss: 0.0312746986746788
2023-01-21 13:06:23.764939: step: 360/531, loss: 0.0008863449329510331
2023-01-21 13:06:24.900709: step: 364/531, loss: 0.009633064270019531
2023-01-21 13:06:26.028285: step: 368/531, loss: 3.71456153516192e-05
2023-01-21 13:06:27.164202: step: 372/531, loss: 0.07318115234375
2023-01-21 13:06:28.284930: step: 376/531, loss: 0.007025718688964844
2023-01-21 13:06:29.420214: step: 380/531, loss: 0.033063411712646484
2023-01-21 13:06:30.547738: step: 384/531, loss: 0.0004489898565225303
2023-01-21 13:06:31.696885: step: 388/531, loss: 0.01707463338971138
2023-01-21 13:06:32.822299: step: 392/531, loss: 0.0017786026000976562
2023-01-21 13:06:33.978091: step: 396/531, loss: 0.03592662885785103
2023-01-21 13:06:35.099275: step: 400/531, loss: 0.004657649900764227
2023-01-21 13:06:36.281157: step: 404/531, loss: 0.0020380020141601562
2023-01-21 13:06:37.414884: step: 408/531, loss: 0.0003277778741903603
2023-01-21 13:06:38.519492: step: 412/531, loss: 0.6080552935600281
2023-01-21 13:06:39.640304: step: 416/531, loss: 0.011705970391631126
2023-01-21 13:06:40.765971: step: 420/531, loss: 7.247924258990679e-06
2023-01-21 13:06:41.896024: step: 424/531, loss: 0.0031394960824400187
2023-01-21 13:06:42.992800: step: 428/531, loss: 0.007942582480609417
2023-01-21 13:06:44.133063: step: 432/531, loss: 0.012568164616823196
2023-01-21 13:06:45.250803: step: 436/531, loss: 3.089904930675402e-05
2023-01-21 13:06:46.386823: step: 440/531, loss: 0.007097339723259211
2023-01-21 13:06:47.489598: step: 444/531, loss: 0.0030575632117688656
2023-01-21 13:06:48.661187: step: 448/531, loss: 7.286071922862902e-05
2023-01-21 13:06:49.792771: step: 452/531, loss: 0.00032863617525435984
2023-01-21 13:06:50.908107: step: 456/531, loss: 0.00044736862764693797
2023-01-21 13:06:52.059396: step: 460/531, loss: 0.00019073486328125
2023-01-21 13:06:53.198283: step: 464/531, loss: 1.354217511106981e-05
2023-01-21 13:06:54.332460: step: 468/531, loss: 0.016560936346650124
2023-01-21 13:06:55.448140: step: 472/531, loss: 0.002007007598876953
2023-01-21 13:06:56.596719: step: 476/531, loss: 1.3351440202313825e-06
2023-01-21 13:06:57.709597: step: 480/531, loss: 0.00781702995300293
2023-01-21 13:06:58.840083: step: 484/531, loss: 0.00022134781465865672
2023-01-21 13:06:59.966784: step: 488/531, loss: 0.00020151138596702367
2023-01-21 13:07:01.097122: step: 492/531, loss: 0.003185463137924671
2023-01-21 13:07:02.222765: step: 496/531, loss: 5.0067901611328125e-06
2023-01-21 13:07:03.353115: step: 500/531, loss: 0.0003032684326171875
2023-01-21 13:07:04.495442: step: 504/531, loss: 0.0001671314239501953
2023-01-21 13:07:05.610862: step: 508/531, loss: 0.00022974015155341476
2023-01-21 13:07:06.717001: step: 512/531, loss: 0.00025300978450104594
2023-01-21 13:07:07.821600: step: 516/531, loss: 4.4155120122013614e-05
2023-01-21 13:07:08.971861: step: 520/531, loss: 0.00039443973219022155
2023-01-21 13:07:10.106891: step: 524/531, loss: 9.918212890625e-05
2023-01-21 13:07:11.202494: step: 528/531, loss: 0.00037636756314896047
2023-01-21 13:07:12.388632: step: 532/531, loss: 0.0008621931774541736
2023-01-21 13:07:13.486803: step: 536/531, loss: 0.0004096984921488911
2023-01-21 13:07:14.626699: step: 540/531, loss: 0.0005216598510742188
2023-01-21 13:07:15.725520: step: 544/531, loss: 3.643035961431451e-05
2023-01-21 13:07:16.835126: step: 548/531, loss: 0.06685161590576172
2023-01-21 13:07:17.984260: step: 552/531, loss: 0.0007217407692223787
2023-01-21 13:07:19.099061: step: 556/531, loss: 0.00027179718017578125
2023-01-21 13:07:20.236716: step: 560/531, loss: 3.9577484130859375e-05
2023-01-21 13:07:21.355286: step: 564/531, loss: 0.03394961357116699
2023-01-21 13:07:22.481268: step: 568/531, loss: 0.036714743822813034
2023-01-21 13:07:23.622658: step: 572/531, loss: 0.00029969215393066406
2023-01-21 13:07:24.779092: step: 576/531, loss: 0.008076095953583717
2023-01-21 13:07:25.944478: step: 580/531, loss: 0.09984445571899414
2023-01-21 13:07:27.097002: step: 584/531, loss: 0.0019512176513671875
2023-01-21 13:07:28.228927: step: 588/531, loss: 0.004755592904984951
2023-01-21 13:07:29.330383: step: 592/531, loss: 0.00016365050396416336
2023-01-21 13:07:30.452213: step: 596/531, loss: 0.01605072058737278
2023-01-21 13:07:31.535246: step: 600/531, loss: 0.06844277679920197
2023-01-21 13:07:32.685465: step: 604/531, loss: 0.011874770745635033
2023-01-21 13:07:33.818057: step: 608/531, loss: 9.269714064430445e-05
2023-01-21 13:07:34.926958: step: 612/531, loss: 0.0005998134147375822
2023-01-21 13:07:36.066316: step: 616/531, loss: 0.0004364013730082661
2023-01-21 13:07:37.210123: step: 620/531, loss: 0.001398277236148715
2023-01-21 13:07:38.360380: step: 624/531, loss: 1.0776519957289565e-05
2023-01-21 13:07:39.475621: step: 628/531, loss: 0.0007604599231854081
2023-01-21 13:07:40.612780: step: 632/531, loss: 2.689361645025201e-05
2023-01-21 13:07:41.754633: step: 636/531, loss: 0.02329440228641033
2023-01-21 13:07:42.923052: step: 640/531, loss: 0.0021452903747558594
2023-01-21 13:07:44.064870: step: 644/531, loss: 0.0023331642150878906
2023-01-21 13:07:45.179429: step: 648/531, loss: 0.00031533243600279093
2023-01-21 13:07:46.294035: step: 652/531, loss: 0.0074738506227731705
2023-01-21 13:07:47.440562: step: 656/531, loss: 0.0002904892317019403
2023-01-21 13:07:48.547579: step: 660/531, loss: 2.09808349609375e-05
2023-01-21 13:07:49.665828: step: 664/531, loss: 5.91278076171875e-05
2023-01-21 13:07:50.780580: step: 668/531, loss: 0.24091139435768127
2023-01-21 13:07:51.903473: step: 672/531, loss: 0.0017959356773644686
2023-01-21 13:07:53.063571: step: 676/531, loss: 0.0005227088695392013
2023-01-21 13:07:54.214536: step: 680/531, loss: 0.012591361999511719
2023-01-21 13:07:55.329315: step: 684/531, loss: 0.052199557423591614
2023-01-21 13:07:56.453862: step: 688/531, loss: 0.013944435864686966
2023-01-21 13:07:57.577037: step: 692/531, loss: 0.0065622334368526936
2023-01-21 13:07:58.707090: step: 696/531, loss: 0.0008890152093954384
2023-01-21 13:07:59.824964: step: 700/531, loss: 0.0008566856267862022
2023-01-21 13:08:00.951394: step: 704/531, loss: 6.065368506824598e-05
2023-01-21 13:08:02.113699: step: 708/531, loss: 6.637573096668348e-05
2023-01-21 13:08:03.216439: step: 712/531, loss: 9.469986252952367e-05
2023-01-21 13:08:04.349142: step: 716/531, loss: 0.021500492468476295
2023-01-21 13:08:05.468115: step: 720/531, loss: 0.00020332337589934468
2023-01-21 13:08:06.579788: step: 724/531, loss: 0.1680024415254593
2023-01-21 13:08:07.681873: step: 728/531, loss: 0.0004405975341796875
2023-01-21 13:08:08.814069: step: 732/531, loss: 2.8038026357535273e-05
2023-01-21 13:08:09.957527: step: 736/531, loss: 0.0002522468566894531
2023-01-21 13:08:11.076738: step: 740/531, loss: 0.011303901672363281
2023-01-21 13:08:12.196186: step: 744/531, loss: 5.14984130859375e-05
2023-01-21 13:08:13.347478: step: 748/531, loss: 8.39233416627394e-06
2023-01-21 13:08:14.474423: step: 752/531, loss: 0.0006374359363690019
2023-01-21 13:08:15.613459: step: 756/531, loss: 4.005432856502011e-06
2023-01-21 13:08:16.747649: step: 760/531, loss: 0.01929759979248047
2023-01-21 13:08:17.920726: step: 764/531, loss: 0.010619450360536575
2023-01-21 13:08:19.047917: step: 768/531, loss: 9.70840483205393e-05
2023-01-21 13:08:20.174291: step: 772/531, loss: 0.005786705296486616
2023-01-21 13:08:21.332422: step: 776/531, loss: 0.013478660956025124
2023-01-21 13:08:22.525414: step: 780/531, loss: 0.004138183780014515
2023-01-21 13:08:23.641451: step: 784/531, loss: 0.0006269455188885331
2023-01-21 13:08:24.766164: step: 788/531, loss: 0.012637711130082607
2023-01-21 13:08:25.917677: step: 792/531, loss: 1.640319896978326e-05
2023-01-21 13:08:27.002820: step: 796/531, loss: 0.012727499008178711
2023-01-21 13:08:28.126702: step: 800/531, loss: 0.056548118591308594
2023-01-21 13:08:29.209140: step: 804/531, loss: 0.017975712195038795
2023-01-21 13:08:30.323434: step: 808/531, loss: 0.00017213822866324335
2023-01-21 13:08:31.443675: step: 812/531, loss: 0.00028123855008743703
2023-01-21 13:08:32.581314: step: 816/531, loss: 0.00037679672823287547
2023-01-21 13:08:33.714494: step: 820/531, loss: 1.5354156857938506e-05
2023-01-21 13:08:34.811003: step: 824/531, loss: 1.31011011035298e-05
2023-01-21 13:08:35.930605: step: 828/531, loss: 0.00274314871057868
2023-01-21 13:08:37.034938: step: 832/531, loss: 0.011080265045166016
2023-01-21 13:08:38.167771: step: 836/531, loss: 0.003657436463981867
2023-01-21 13:08:39.268252: step: 840/531, loss: 0.0004027366521768272
2023-01-21 13:08:40.404166: step: 844/531, loss: 0.00470733642578125
2023-01-21 13:08:41.531243: step: 848/531, loss: 0.0006496429559774697
2023-01-21 13:08:42.668982: step: 852/531, loss: 0.003203868865966797
2023-01-21 13:08:43.786025: step: 856/531, loss: 0.009075308218598366
2023-01-21 13:08:44.895483: step: 860/531, loss: 0.019313620403409004
2023-01-21 13:08:46.027460: step: 864/531, loss: 0.008193779736757278
2023-01-21 13:08:47.144161: step: 868/531, loss: 0.03574848175048828
2023-01-21 13:08:48.275623: step: 872/531, loss: 0.0023950578179210424
2023-01-21 13:08:49.374746: step: 876/531, loss: 0.0006591796409338713
2023-01-21 13:08:50.520693: step: 880/531, loss: 0.00881881732493639
2023-01-21 13:08:51.678094: step: 884/531, loss: 0.07266216725111008
2023-01-21 13:08:52.788992: step: 888/531, loss: 0.011291885748505592
2023-01-21 13:08:53.940934: step: 892/531, loss: 0.002259636064991355
2023-01-21 13:08:55.026846: step: 896/531, loss: 0.00216255197301507
2023-01-21 13:08:56.164538: step: 900/531, loss: 5.5646894907113165e-05
2023-01-21 13:08:57.311847: step: 904/531, loss: 0.0024394034408032894
2023-01-21 13:08:58.453797: step: 908/531, loss: 0.020668601617217064
2023-01-21 13:08:59.588399: step: 912/531, loss: 0.00051116943359375
2023-01-21 13:09:00.694095: step: 916/531, loss: 8.20159912109375e-05
2023-01-21 13:09:01.813807: step: 920/531, loss: 7.057190487103071e-06
2023-01-21 13:09:02.926911: step: 924/531, loss: 3.318786548334174e-05
2023-01-21 13:09:04.069075: step: 928/531, loss: 0.0051863668486475945
2023-01-21 13:09:05.196588: step: 932/531, loss: 5.9795380366267636e-05
2023-01-21 13:09:06.361319: step: 936/531, loss: 0.02184162102639675
2023-01-21 13:09:07.458529: step: 940/531, loss: 0.0004673004150390625
2023-01-21 13:09:08.575901: step: 944/531, loss: 0.01511306781321764
2023-01-21 13:09:09.688956: step: 948/531, loss: -1.5258788153005298e-06
2023-01-21 13:09:10.790870: step: 952/531, loss: 1.621246337890625e-05
2023-01-21 13:09:11.933609: step: 956/531, loss: 5.197525388211943e-05
2023-01-21 13:09:13.025135: step: 960/531, loss: 0.0028282166458666325
2023-01-21 13:09:14.120199: step: 964/531, loss: 0.004936886020004749
2023-01-21 13:09:15.205489: step: 968/531, loss: 5.741119457525201e-05
2023-01-21 13:09:16.329003: step: 972/531, loss: 1.316070574830519e-05
2023-01-21 13:09:17.452016: step: 976/531, loss: 0.0014938354725018144
2023-01-21 13:09:18.568540: step: 980/531, loss: 0.003910636994987726
2023-01-21 13:09:19.703865: step: 984/531, loss: 0.0003662109375
2023-01-21 13:09:20.833563: step: 988/531, loss: 0.0031481743790209293
2023-01-21 13:09:21.966465: step: 992/531, loss: 4.482269287109375e-05
2023-01-21 13:09:23.104441: step: 996/531, loss: 0.0003397941472940147
2023-01-21 13:09:24.247326: step: 1000/531, loss: 0.027684977278113365
2023-01-21 13:09:25.347833: step: 1004/531, loss: 0.009808349423110485
2023-01-21 13:09:26.449594: step: 1008/531, loss: 0.00030994415283203125
2023-01-21 13:09:27.600453: step: 1012/531, loss: 7.867813110351562e-05
2023-01-21 13:09:28.711156: step: 1016/531, loss: 0.00014672279939986765
2023-01-21 13:09:29.849591: step: 1020/531, loss: 0.0056816102005541325
2023-01-21 13:09:31.012189: step: 1024/531, loss: 0.005644512362778187
2023-01-21 13:09:32.099311: step: 1028/531, loss: 0.0015291214222088456
2023-01-21 13:09:33.216644: step: 1032/531, loss: 0.0031047819647938013
2023-01-21 13:09:34.363730: step: 1036/531, loss: 0.004734706599265337
2023-01-21 13:09:35.453343: step: 1040/531, loss: 0.0012608527904376388
2023-01-21 13:09:36.569637: step: 1044/531, loss: 0.0011785507667809725
2023-01-21 13:09:37.693222: step: 1048/531, loss: 0.00010185241990257055
2023-01-21 13:09:38.827347: step: 1052/531, loss: 0.00018005371384788305
2023-01-21 13:09:39.970994: step: 1056/531, loss: 0.00399932824075222
2023-01-21 13:09:41.091442: step: 1060/531, loss: 0.0003186225949320942
2023-01-21 13:09:42.221129: step: 1064/531, loss: 0.021273041144013405
2023-01-21 13:09:43.335953: step: 1068/531, loss: 0.00015754700871184468
2023-01-21 13:09:44.448492: step: 1072/531, loss: 0.002571582794189453
2023-01-21 13:09:45.608493: step: 1076/531, loss: 0.015506600961089134
2023-01-21 13:09:46.737616: step: 1080/531, loss: 6.408691115211695e-05
2023-01-21 13:09:47.888199: step: 1084/531, loss: 0.0038730620872229338
2023-01-21 13:09:49.013594: step: 1088/531, loss: 0.0008067131275311112
2023-01-21 13:09:50.112541: step: 1092/531, loss: 8.869171324477065e-06
2023-01-21 13:09:51.263922: step: 1096/531, loss: 0.004353523254394531
2023-01-21 13:09:52.339793: step: 1100/531, loss: 1.5735626220703125e-05
2023-01-21 13:09:53.457905: step: 1104/531, loss: 0.0033899785485118628
2023-01-21 13:09:54.581756: step: 1108/531, loss: 3.1900406611384824e-05
2023-01-21 13:09:55.701301: step: 1112/531, loss: 0.007274532224982977
2023-01-21 13:09:56.845060: step: 1116/531, loss: 4.673004514188506e-05
2023-01-21 13:09:57.983867: step: 1120/531, loss: 0.0005188941722735763
2023-01-21 13:09:59.067453: step: 1124/531, loss: 1.9073486328125e-05
2023-01-21 13:10:00.207350: step: 1128/531, loss: 0.0006818771362304688
2023-01-21 13:10:01.327617: step: 1132/531, loss: 0.007822990417480469
2023-01-21 13:10:02.470444: step: 1136/531, loss: 7.99179106252268e-05
2023-01-21 13:10:03.594507: step: 1140/531, loss: 0.019560718908905983
2023-01-21 13:10:04.708872: step: 1144/531, loss: 0.03733978420495987
2023-01-21 13:10:05.801506: step: 1148/531, loss: 0.0001755714329192415
2023-01-21 13:10:06.945404: step: 1152/531, loss: 0.000896453857421875
2023-01-21 13:10:08.038287: step: 1156/531, loss: 1.792907642084174e-05
2023-01-21 13:10:09.148570: step: 1160/531, loss: 0.13368311524391174
2023-01-21 13:10:10.268985: step: 1164/531, loss: 0.0001253128139069304
2023-01-21 13:10:11.383031: step: 1168/531, loss: 5.245209194981726e-06
2023-01-21 13:10:12.489051: step: 1172/531, loss: 0.0005786657566204667
2023-01-21 13:10:13.619831: step: 1176/531, loss: 0.00032787321833893657
2023-01-21 13:10:14.731389: step: 1180/531, loss: 0.000876569771207869
2023-01-21 13:10:15.853558: step: 1184/531, loss: 0.010364532470703125
2023-01-21 13:10:16.973803: step: 1188/531, loss: 0.017445851117372513
2023-01-21 13:10:18.088238: step: 1192/531, loss: 0.0006666183471679688
2023-01-21 13:10:19.205566: step: 1196/531, loss: 0.0006077766302041709
2023-01-21 13:10:20.341692: step: 1200/531, loss: 0.016824819147586823
2023-01-21 13:10:21.474953: step: 1204/531, loss: 0.0013669967884197831
2023-01-21 13:10:22.590502: step: 1208/531, loss: 0.00171489710919559
2023-01-21 13:10:23.700260: step: 1212/531, loss: 0.0003632068692240864
2023-01-21 13:10:24.836633: step: 1216/531, loss: 0.006293964572250843
2023-01-21 13:10:25.962609: step: 1220/531, loss: 0.026813222095370293
2023-01-21 13:10:27.099466: step: 1224/531, loss: 0.0004943371168337762
2023-01-21 13:10:28.229960: step: 1228/531, loss: 0.0018658638000488281
2023-01-21 13:10:29.336293: step: 1232/531, loss: 0.00010814666893566027
2023-01-21 13:10:30.474547: step: 1236/531, loss: 0.0005912781343795359
2023-01-21 13:10:31.563939: step: 1240/531, loss: 5.257129669189453e-05
2023-01-21 13:10:32.670426: step: 1244/531, loss: 0.0009036064147949219
2023-01-21 13:10:33.805942: step: 1248/531, loss: 0.0002368926943745464
2023-01-21 13:10:34.922233: step: 1252/531, loss: 0.0025201798416674137
2023-01-21 13:10:36.075677: step: 1256/531, loss: 0.008607483468949795
2023-01-21 13:10:37.212815: step: 1260/531, loss: 0.004907465074211359
2023-01-21 13:10:38.314790: step: 1264/531, loss: 5.14984130859375e-05
2023-01-21 13:10:39.426390: step: 1268/531, loss: 3.185272362316027e-05
2023-01-21 13:10:40.553292: step: 1272/531, loss: 0.0006665230030193925
2023-01-21 13:10:41.673717: step: 1276/531, loss: 0.0028783800080418587
2023-01-21 13:10:42.798158: step: 1280/531, loss: 0.012724113650619984
2023-01-21 13:10:43.921792: step: 1284/531, loss: 1.6689300537109375e-05
2023-01-21 13:10:45.017456: step: 1288/531, loss: 5.14984139954322e-06
2023-01-21 13:10:46.151123: step: 1292/531, loss: 0.00038313865661621094
2023-01-21 13:10:47.266277: step: 1296/531, loss: 0.0003246307314839214
2023-01-21 13:10:48.356207: step: 1300/531, loss: 0.0014455795753747225
2023-01-21 13:10:49.501676: step: 1304/531, loss: 1.1444094525359105e-06
2023-01-21 13:10:50.625377: step: 1308/531, loss: 0.011186599731445312
2023-01-21 13:10:51.761627: step: 1312/531, loss: 7.591247413074598e-05
2023-01-21 13:10:52.882284: step: 1316/531, loss: 9.603500075172633e-05
2023-01-21 13:10:53.998077: step: 1320/531, loss: 0.00023784636869095266
2023-01-21 13:10:55.135023: step: 1324/531, loss: 0.005619430914521217
2023-01-21 13:10:56.262506: step: 1328/531, loss: 4.844665454584174e-05
2023-01-21 13:10:57.423097: step: 1332/531, loss: 3.99589553126134e-05
2023-01-21 13:10:58.590739: step: 1336/531, loss: 0.0009550094837322831
2023-01-21 13:10:59.740419: step: 1340/531, loss: 0.00047512055607512593
2023-01-21 13:11:00.916395: step: 1344/531, loss: 7.22885160939768e-05
2023-01-21 13:11:02.031486: step: 1348/531, loss: 0.00516121368855238
2023-01-21 13:11:03.148315: step: 1352/531, loss: 0.008965874090790749
2023-01-21 13:11:04.293423: step: 1356/531, loss: 0.0012616158928722143
2023-01-21 13:11:05.401096: step: 1360/531, loss: 3.0994415283203125e-05
2023-01-21 13:11:06.541867: step: 1364/531, loss: 8.487701052217744e-06
2023-01-21 13:11:07.659942: step: 1368/531, loss: 0.00011940002877963707
2023-01-21 13:11:08.816777: step: 1372/531, loss: 0.0003047943173442036
2023-01-21 13:11:09.958901: step: 1376/531, loss: 0.000244140625
2023-01-21 13:11:11.055050: step: 1380/531, loss: 0.0003014564572367817
2023-01-21 13:11:12.193869: step: 1384/531, loss: 1.850128137448337e-05
2023-01-21 13:11:13.300064: step: 1388/531, loss: 4.0054324017546605e-06
2023-01-21 13:11:14.436870: step: 1392/531, loss: 0.0003837585391011089
2023-01-21 13:11:15.554509: step: 1396/531, loss: 0.0009661674266681075
2023-01-21 13:11:16.704516: step: 1400/531, loss: 0.004594612400978804
2023-01-21 13:11:17.803153: step: 1404/531, loss: 0.00023975371732376516
2023-01-21 13:11:18.927278: step: 1408/531, loss: 0.0028760910499840975
2023-01-21 13:11:20.026172: step: 1412/531, loss: 0.002426338382065296
2023-01-21 13:11:21.137732: step: 1416/531, loss: 0.005239391699433327
2023-01-21 13:11:22.252782: step: 1420/531, loss: 0.0023806095123291016
2023-01-21 13:11:23.389097: step: 1424/531, loss: 0.0005450248718261719
2023-01-21 13:11:24.529277: step: 1428/531, loss: 0.05249834060668945
2023-01-21 13:11:25.686835: step: 1432/531, loss: 0.007484626956284046
2023-01-21 13:11:26.808610: step: 1436/531, loss: 0.0014860153896734118
2023-01-21 13:11:27.933791: step: 1440/531, loss: 0.00012235641770530492
2023-01-21 13:11:29.072697: step: 1444/531, loss: 0.04383678361773491
2023-01-21 13:11:30.166385: step: 1448/531, loss: 8.602142770541832e-05
2023-01-21 13:11:31.312274: step: 1452/531, loss: 0.00787649117410183
2023-01-21 13:11:32.432339: step: 1456/531, loss: 0.0013366700150072575
2023-01-21 13:11:33.566683: step: 1460/531, loss: 9.51766996877268e-05
2023-01-21 13:11:34.689471: step: 1464/531, loss: 0.0008792877197265625
2023-01-21 13:11:35.838157: step: 1468/531, loss: 0.01833334006369114
2023-01-21 13:11:36.938103: step: 1472/531, loss: 0.00472869910299778
2023-01-21 13:11:38.090588: step: 1476/531, loss: 0.0004978656652383506
2023-01-21 13:11:39.199934: step: 1480/531, loss: 0.00022697450185660273
2023-01-21 13:11:40.336881: step: 1484/531, loss: 0.014154244214296341
2023-01-21 13:11:41.486556: step: 1488/531, loss: 9.059906005859375e-06
2023-01-21 13:11:42.617443: step: 1492/531, loss: 0.0001750946103129536
2023-01-21 13:11:43.753233: step: 1496/531, loss: 0.001508522080257535
2023-01-21 13:11:44.872114: step: 1500/531, loss: 0.020079948008060455
2023-01-21 13:11:45.983648: step: 1504/531, loss: 0.001806068466976285
2023-01-21 13:11:47.134422: step: 1508/531, loss: 0.0003389358753338456
2023-01-21 13:11:48.249906: step: 1512/531, loss: 0.00014200211444403976
2023-01-21 13:11:49.397986: step: 1516/531, loss: 0.0082848547026515
2023-01-21 13:11:50.487744: step: 1520/531, loss: 1.5735627130197827e-06
2023-01-21 13:11:51.639211: step: 1524/531, loss: 8.792877633823082e-05
2023-01-21 13:11:52.735095: step: 1528/531, loss: 1.2493133908719756e-05
2023-01-21 13:11:53.891855: step: 1532/531, loss: 0.0059944153763353825
2023-01-21 13:11:55.010224: step: 1536/531, loss: 1.3685226804227568e-05
2023-01-21 13:11:56.146931: step: 1540/531, loss: 0.0004153251647949219
2023-01-21 13:11:57.244440: step: 1544/531, loss: 6.8664553509734105e-06
2023-01-21 13:11:58.369771: step: 1548/531, loss: 9.565354412188753e-05
2023-01-21 13:11:59.497458: step: 1552/531, loss: 0.00021209717669989914
2023-01-21 13:12:00.603434: step: 1556/531, loss: 0.00229053501971066
2023-01-21 13:12:01.730553: step: 1560/531, loss: 5.8650970458984375e-05
2023-01-21 13:12:02.847422: step: 1564/531, loss: 0.25569456815719604
2023-01-21 13:12:03.968262: step: 1568/531, loss: 0.0006315231439657509
2023-01-21 13:12:05.053961: step: 1572/531, loss: 4.091262962901965e-05
2023-01-21 13:12:06.215732: step: 1576/531, loss: 0.03510742262005806
2023-01-21 13:12:07.345228: step: 1580/531, loss: 0.00010614394705044106
2023-01-21 13:12:08.481051: step: 1584/531, loss: 0.020201491191983223
2023-01-21 13:12:09.636281: step: 1588/531, loss: 0.05397796630859375
2023-01-21 13:12:10.768734: step: 1592/531, loss: 0.00043249133159406483
2023-01-21 13:12:11.892383: step: 1596/531, loss: 0.0014174937969073653
2023-01-21 13:12:13.031547: step: 1600/531, loss: 0.051859185099601746
2023-01-21 13:12:14.167663: step: 1604/531, loss: 0.0003941536124330014
2023-01-21 13:12:15.291160: step: 1608/531, loss: 0.0037469866219908
2023-01-21 13:12:16.392782: step: 1612/531, loss: 5.168914867681451e-05
2023-01-21 13:12:17.508844: step: 1616/531, loss: 0.00011749268014682457
2023-01-21 13:12:18.637170: step: 1620/531, loss: 1.9073486328125e-06
2023-01-21 13:12:19.745754: step: 1624/531, loss: 0.00046076776925474405
2023-01-21 13:12:20.899068: step: 1628/531, loss: -2.498626781743951e-05
2023-01-21 13:12:21.998601: step: 1632/531, loss: 0.0126069076359272
2023-01-21 13:12:23.117780: step: 1636/531, loss: 0.00014972686767578125
2023-01-21 13:12:24.227788: step: 1640/531, loss: 0.010813714005053043
2023-01-21 13:12:25.382385: step: 1644/531, loss: 0.00025177001953125
2023-01-21 13:12:26.522103: step: 1648/531, loss: 0.0017105102306231856
2023-01-21 13:12:27.627268: step: 1652/531, loss: 0.0006741523975506425
2023-01-21 13:12:28.727514: step: 1656/531, loss: 0.00034923554630950093
2023-01-21 13:12:29.864543: step: 1660/531, loss: 0.004012489225715399
2023-01-21 13:12:30.973205: step: 1664/531, loss: -1.1444091114753974e-06
2023-01-21 13:12:32.090070: step: 1668/531, loss: 0.03929634019732475
2023-01-21 13:12:33.210235: step: 1672/531, loss: 0.005597400479018688
2023-01-21 13:12:34.320465: step: 1676/531, loss: 0.029470443725585938
2023-01-21 13:12:35.477810: step: 1680/531, loss: 6.866455078125e-05
2023-01-21 13:12:36.575568: step: 1684/531, loss: 0.02064990997314453
2023-01-21 13:12:37.682900: step: 1688/531, loss: 0.0011292457347735763
2023-01-21 13:12:38.830313: step: 1692/531, loss: 0.18194931745529175
2023-01-21 13:12:39.974173: step: 1696/531, loss: 0.0006795883527956903
2023-01-21 13:12:41.085348: step: 1700/531, loss: 0.06164684519171715
2023-01-21 13:12:42.181114: step: 1704/531, loss: 0.00022420883760787547
2023-01-21 13:12:43.299478: step: 1708/531, loss: 6.12258882028982e-05
2023-01-21 13:12:44.445869: step: 1712/531, loss: 0.5242816805839539
2023-01-21 13:12:45.594360: step: 1716/531, loss: 0.00068836216814816
2023-01-21 13:12:46.730924: step: 1720/531, loss: 0.00018177033052779734
2023-01-21 13:12:47.828200: step: 1724/531, loss: 0.0023394108284264803
2023-01-21 13:12:48.969870: step: 1728/531, loss: 0.001183509943075478
2023-01-21 13:12:50.071077: step: 1732/531, loss: 0.027262257412075996
2023-01-21 13:12:51.186412: step: 1736/531, loss: 0.0010611058678478003
2023-01-21 13:12:52.330516: step: 1740/531, loss: 0.017176246270537376
2023-01-21 13:12:53.433982: step: 1744/531, loss: 0.00023422243248205632
2023-01-21 13:12:54.575468: step: 1748/531, loss: 0.06627864390611649
2023-01-21 13:12:55.702437: step: 1752/531, loss: 0.04366188123822212
2023-01-21 13:12:56.803548: step: 1756/531, loss: 6.0653688706224784e-05
2023-01-21 13:12:57.927134: step: 1760/531, loss: 8.878708467818797e-05
2023-01-21 13:12:59.081232: step: 1764/531, loss: 0.006194115150719881
2023-01-21 13:13:00.183911: step: 1768/531, loss: 9.5367431640625e-07
2023-01-21 13:13:01.293359: step: 1772/531, loss: 0.0012831687927246094
2023-01-21 13:13:02.419377: step: 1776/531, loss: 0.000175046909134835
2023-01-21 13:13:03.546610: step: 1780/531, loss: 2.6702882678364404e-06
2023-01-21 13:13:04.643029: step: 1784/531, loss: 0.0063908579759299755
2023-01-21 13:13:05.775380: step: 1788/531, loss: 0.013032151386141777
2023-01-21 13:13:06.912821: step: 1792/531, loss: 0.00047588348388671875
2023-01-21 13:13:08.051300: step: 1796/531, loss: 0.0012002944713458419
2023-01-21 13:13:09.162090: step: 1800/531, loss: 0.0009578705066815019
2023-01-21 13:13:10.288985: step: 1804/531, loss: 0.004888630472123623
2023-01-21 13:13:11.398856: step: 1808/531, loss: 0.011440277099609375
2023-01-21 13:13:12.517885: step: 1812/531, loss: 0.0028636932838708162
2023-01-21 13:13:13.657464: step: 1816/531, loss: 0.002319050021469593
2023-01-21 13:13:14.769948: step: 1820/531, loss: 0.010092162527143955
2023-01-21 13:13:15.915228: step: 1824/531, loss: 0.012401724234223366
2023-01-21 13:13:17.034375: step: 1828/531, loss: 0.05125083774328232
2023-01-21 13:13:18.165581: step: 1832/531, loss: 0.13479185104370117
2023-01-21 13:13:19.296476: step: 1836/531, loss: 0.00039329531136900187
2023-01-21 13:13:20.417663: step: 1840/531, loss: 6.29425039733178e-06
2023-01-21 13:13:21.552046: step: 1844/531, loss: 0.006687641143798828
2023-01-21 13:13:22.664357: step: 1848/531, loss: 0.010218525305390358
2023-01-21 13:13:23.808291: step: 1852/531, loss: 0.0022821426391601562
2023-01-21 13:13:24.953014: step: 1856/531, loss: 0.0009283066028729081
2023-01-21 13:13:26.090812: step: 1860/531, loss: 0.003015375230461359
2023-01-21 13:13:27.214274: step: 1864/531, loss: 0.017287828028202057
2023-01-21 13:13:28.347642: step: 1868/531, loss: 0.00264072441495955
2023-01-21 13:13:29.481300: step: 1872/531, loss: 4.57763671875e-05
2023-01-21 13:13:30.626517: step: 1876/531, loss: 9.80854092631489e-05
2023-01-21 13:13:31.731401: step: 1880/531, loss: 4.863738922722405e-06
2023-01-21 13:13:32.865352: step: 1884/531, loss: 6.389617738022935e-06
2023-01-21 13:13:33.973760: step: 1888/531, loss: 0.0016894340515136719
2023-01-21 13:13:35.096751: step: 1892/531, loss: 0.02133622020483017
2023-01-21 13:13:36.224256: step: 1896/531, loss: 2.9468537832144648e-05
2023-01-21 13:13:37.357099: step: 1900/531, loss: 0.0552794449031353
2023-01-21 13:13:38.466824: step: 1904/531, loss: 0.12874050438404083
2023-01-21 13:13:39.597454: step: 1908/531, loss: 0.01023874245584011
2023-01-21 13:13:40.748589: step: 1912/531, loss: 0.0005775452009402215
2023-01-21 13:13:41.938809: step: 1916/531, loss: 7.963180541992188e-05
2023-01-21 13:13:43.077974: step: 1920/531, loss: 0.000913197873160243
2023-01-21 13:13:44.196514: step: 1924/531, loss: 9.446144395042211e-05
2023-01-21 13:13:45.310356: step: 1928/531, loss: 0.04133796691894531
2023-01-21 13:13:46.450281: step: 1932/531, loss: 4.372596595203504e-05
2023-01-21 13:13:47.590968: step: 1936/531, loss: 0.04000205919146538
2023-01-21 13:13:48.708690: step: 1940/531, loss: 0.0007588386652059853
2023-01-21 13:13:49.847303: step: 1944/531, loss: 0.00013265610323287547
2023-01-21 13:13:50.958271: step: 1948/531, loss: 0.021369459107518196
2023-01-21 13:13:52.094559: step: 1952/531, loss: 0.0002723693905863911
2023-01-21 13:13:53.211671: step: 1956/531, loss: 0.0004154682392254472
2023-01-21 13:13:54.358230: step: 1960/531, loss: 0.0014532089699059725
2023-01-21 13:13:55.504863: step: 1964/531, loss: 0.08775182068347931
2023-01-21 13:13:56.619065: step: 1968/531, loss: 0.026155663654208183
2023-01-21 13:13:57.725671: step: 1972/531, loss: 0.0004389762762002647
2023-01-21 13:13:58.832356: step: 1976/531, loss: 0.026421070098876953
2023-01-21 13:13:59.939950: step: 1980/531, loss: 0.003487825393676758
2023-01-21 13:14:01.061545: step: 1984/531, loss: 0.0011960983974859118
2023-01-21 13:14:02.183843: step: 1988/531, loss: 0.00344505300745368
2023-01-21 13:14:03.295748: step: 1992/531, loss: 0.0004194736829958856
2023-01-21 13:14:04.407041: step: 1996/531, loss: 0.07059655338525772
2023-01-21 13:14:05.512414: step: 2000/531, loss: 0.00010774135444080457
2023-01-21 13:14:06.630088: step: 2004/531, loss: 0.0015066147316247225
2023-01-21 13:14:07.768608: step: 2008/531, loss: 6.198883056640625e-05
2023-01-21 13:14:08.915658: step: 2012/531, loss: 0.00017194748215842992
2023-01-21 13:14:10.054782: step: 2016/531, loss: 0.00011730194091796875
2023-01-21 13:14:11.173909: step: 2020/531, loss: 0.00019559860811568797
2023-01-21 13:14:12.291836: step: 2024/531, loss: 0.0018524168990552425
2023-01-21 13:14:13.483511: step: 2028/531, loss: -3.910064606316155e-06
2023-01-21 13:14:14.608085: step: 2032/531, loss: 0.03407545015215874
2023-01-21 13:14:15.713976: step: 2036/531, loss: 0.00023360253544524312
2023-01-21 13:14:16.822795: step: 2040/531, loss: 0.0008902549743652344
2023-01-21 13:14:17.960964: step: 2044/531, loss: 4.568099757307209e-05
2023-01-21 13:14:19.101116: step: 2048/531, loss: 0.0017230988014489412
2023-01-21 13:14:20.230979: step: 2052/531, loss: 0.5555196404457092
2023-01-21 13:14:21.348929: step: 2056/531, loss: 0.02086200751364231
2023-01-21 13:14:22.487903: step: 2060/531, loss: 0.00061798095703125
2023-01-21 13:14:23.657807: step: 2064/531, loss: 0.04857692867517471
2023-01-21 13:14:24.780906: step: 2068/531, loss: 3.2711028325138614e-05
2023-01-21 13:14:25.923171: step: 2072/531, loss: 6.771087555534905e-06
2023-01-21 13:14:27.064845: step: 2076/531, loss: 0.0002229690580861643
2023-01-21 13:14:28.184912: step: 2080/531, loss: 0.00030436518136411905
2023-01-21 13:14:29.353866: step: 2084/531, loss: 0.019772911444306374
2023-01-21 13:14:30.494160: step: 2088/531, loss: 0.0003482818428892642
2023-01-21 13:14:31.643524: step: 2092/531, loss: 0.008302878588438034
2023-01-21 13:14:32.753668: step: 2096/531, loss: 0.03240451589226723
2023-01-21 13:14:33.879468: step: 2100/531, loss: 0.014634991064667702
2023-01-21 13:14:34.970888: step: 2104/531, loss: 0.00015134812565520406
2023-01-21 13:14:36.105938: step: 2108/531, loss: 0.004219627473503351
2023-01-21 13:14:37.234077: step: 2112/531, loss: 0.01053011417388916
2023-01-21 13:14:38.334010: step: 2116/531, loss: 5.607604907709174e-05
2023-01-21 13:14:39.476768: step: 2120/531, loss: 0.00022482872009277344
2023-01-21 13:14:40.614022: step: 2124/531, loss: 0.027836419641971588
==================================================
Loss: 0.014
--------------------
Dev: {'event': {'p': 0.5681381957773513, 'r': 0.7882822902796272, 'f1': 0.660345789180145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6137299771167049, 'r': 0.7996422182468694, 'f1': 0.6944588296219576}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5679012345679012, 'r': 0.8518518518518519, 'f1': 0.6814814814814814}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.6349206349206349, 'f1': 0.6015037593984962}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.28846153846153844, 'r': 0.4166666666666667, 'f1': 0.3409090909090909}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 27
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 13:15:21.014216: step: 4/531, loss: 0.032869912683963776
2023-01-21 13:15:22.132659: step: 8/531, loss: 0.01137313898652792
2023-01-21 13:15:23.262262: step: 12/531, loss: 0.0008121490245684981
2023-01-21 13:15:24.371768: step: 16/531, loss: 1.640319896978326e-05
2023-01-21 13:15:25.491667: step: 20/531, loss: 0.011584949679672718
2023-01-21 13:15:26.599977: step: 24/531, loss: 0.007736015599220991
2023-01-21 13:15:27.712610: step: 28/531, loss: 0.013990783132612705
2023-01-21 13:15:28.896742: step: 32/531, loss: 0.0017811775906011462
2023-01-21 13:15:29.995726: step: 36/531, loss: 0.003659153124317527
2023-01-21 13:15:31.153961: step: 40/531, loss: 0.00013484954251907766
2023-01-21 13:15:32.289462: step: 44/531, loss: 0.12456703186035156
2023-01-21 13:15:33.395748: step: 48/531, loss: 0.001987648196518421
2023-01-21 13:15:34.542042: step: 52/531, loss: 0.00011539459228515625
2023-01-21 13:15:35.641556: step: 56/531, loss: 0.15163154900074005
2023-01-21 13:15:36.771253: step: 60/531, loss: 0.00109100341796875
2023-01-21 13:15:37.882697: step: 64/531, loss: 0.003566217375919223
2023-01-21 13:15:39.013514: step: 68/531, loss: 0.003479576203972101
2023-01-21 13:15:40.161654: step: 72/531, loss: 3.914833359885961e-05
2023-01-21 13:15:41.300529: step: 76/531, loss: 0.010857963934540749
2023-01-21 13:15:42.413886: step: 80/531, loss: 0.011627960950136185
2023-01-21 13:15:43.554911: step: 84/531, loss: 0.00428009033203125
2023-01-21 13:15:44.699205: step: 88/531, loss: -3.2424925393570447e-06
2023-01-21 13:15:45.812754: step: 92/531, loss: 0.006854820065200329
2023-01-21 13:15:46.921891: step: 96/531, loss: 0.007114696316421032
2023-01-21 13:15:48.055497: step: 100/531, loss: 0.0016622543334960938
2023-01-21 13:15:49.174244: step: 104/531, loss: 0.0006792068597860634
2023-01-21 13:15:50.258410: step: 108/531, loss: 0.0022104859817773104
2023-01-21 13:15:51.399551: step: 112/531, loss: 0.039315417408943176
2023-01-21 13:15:52.494308: step: 116/531, loss: 0.00018577575974632055
2023-01-21 13:15:53.630979: step: 120/531, loss: 0.006172371096909046
2023-01-21 13:15:54.749678: step: 124/531, loss: 0.0001924514799611643
2023-01-21 13:15:55.846072: step: 128/531, loss: 0.053377628326416016
2023-01-21 13:15:56.953154: step: 132/531, loss: 0.0035102844703942537
2023-01-21 13:15:58.067458: step: 136/531, loss: 1.163482647825731e-05
2023-01-21 13:15:59.177450: step: 140/531, loss: 0.0008392333984375
2023-01-21 13:16:00.296094: step: 144/531, loss: 2.708435022213962e-05
2023-01-21 13:16:01.418131: step: 148/531, loss: 0.00012254714965820312
2023-01-21 13:16:02.560127: step: 152/531, loss: 3.43322744811303e-06
2023-01-21 13:16:03.700361: step: 156/531, loss: 0.00011100769916083664
2023-01-21 13:16:04.831227: step: 160/531, loss: 0.03128385543823242
2023-01-21 13:16:05.967141: step: 164/531, loss: 0.03144221007823944
2023-01-21 13:16:07.083819: step: 168/531, loss: 6.828308687545359e-05
2023-01-21 13:16:08.200137: step: 172/531, loss: 0.024213124066591263
2023-01-21 13:16:09.324837: step: 176/531, loss: 3.8480757211800665e-05
2023-01-21 13:16:10.467335: step: 180/531, loss: 0.00016117097402457148
2023-01-21 13:16:11.566723: step: 184/531, loss: 0.00038757326547056437
2023-01-21 13:16:12.712260: step: 188/531, loss: 0.03155650943517685
2023-01-21 13:16:13.830152: step: 192/531, loss: 0.0013959885109215975
2023-01-21 13:16:14.949509: step: 196/531, loss: 0.002661085221916437
2023-01-21 13:16:16.037253: step: 200/531, loss: 0.020292092114686966
2023-01-21 13:16:17.165086: step: 204/531, loss: 0.005685615353286266
2023-01-21 13:16:18.296186: step: 208/531, loss: 0.33903443813323975
2023-01-21 13:16:19.414787: step: 212/531, loss: 1.869201696536038e-05
2023-01-21 13:16:20.530482: step: 216/531, loss: 0.0003068924124818295
2023-01-21 13:16:21.691369: step: 220/531, loss: 0.0036836625076830387
2023-01-21 13:16:22.829661: step: 224/531, loss: 0.0013276099925860763
2023-01-21 13:16:23.936813: step: 228/531, loss: 0.0012371063930913806
2023-01-21 13:16:25.081095: step: 232/531, loss: 0.01437530480325222
2023-01-21 13:16:26.232517: step: 236/531, loss: 0.030065536499023438
2023-01-21 13:16:27.379331: step: 240/531, loss: 0.012996578589081764
2023-01-21 13:16:28.486652: step: 244/531, loss: 0.0002751350693870336
2023-01-21 13:16:29.604594: step: 248/531, loss: 0.01992177963256836
2023-01-21 13:16:30.723687: step: 252/531, loss: 0.0002990722714457661
2023-01-21 13:16:31.869474: step: 256/531, loss: 0.026076793670654297
2023-01-21 13:16:32.986225: step: 260/531, loss: 0.015161419287323952
2023-01-21 13:16:34.110674: step: 264/531, loss: 0.012009048834443092
2023-01-21 13:16:35.265866: step: 268/531, loss: 0.00163946149405092
2023-01-21 13:16:36.396275: step: 272/531, loss: 0.02469616010785103
2023-01-21 13:16:37.539342: step: 276/531, loss: 0.014821052551269531
2023-01-21 13:16:38.655867: step: 280/531, loss: 0.018169784918427467
2023-01-21 13:16:39.786092: step: 284/531, loss: 0.006551647558808327
2023-01-21 13:16:40.943853: step: 288/531, loss: 0.0009578705066815019
2023-01-21 13:16:42.067611: step: 292/531, loss: 3.4141543437726796e-05
2023-01-21 13:16:43.229242: step: 296/531, loss: 0.022285079583525658
2023-01-21 13:16:44.334085: step: 300/531, loss: 0.0014776230091229081
2023-01-21 13:16:45.445820: step: 304/531, loss: 0.00114860525354743
2023-01-21 13:16:46.573937: step: 308/531, loss: 0.0004520416259765625
2023-01-21 13:16:47.713212: step: 312/531, loss: 9.450913057662547e-05
2023-01-21 13:16:48.836263: step: 316/531, loss: 0.2662227749824524
2023-01-21 13:16:49.960795: step: 320/531, loss: 0.0005800247308798134
2023-01-21 13:16:51.063633: step: 324/531, loss: 0.018753720447421074
2023-01-21 13:16:52.211869: step: 328/531, loss: 0.0412229560315609
2023-01-21 13:16:53.347807: step: 332/531, loss: 2.6130677724722773e-05
2023-01-21 13:16:54.501718: step: 336/531, loss: -4.7683716530855236e-08
2023-01-21 13:16:55.616319: step: 340/531, loss: 1.7786025637178682e-05
2023-01-21 13:16:56.707489: step: 344/531, loss: 6.663352542091161e-05
2023-01-21 13:16:57.840853: step: 348/531, loss: 0.12062511593103409
2023-01-21 13:16:58.956651: step: 352/531, loss: 0.023876190185546875
2023-01-21 13:17:00.068844: step: 356/531, loss: 0.005062866024672985
2023-01-21 13:17:01.173697: step: 360/531, loss: 6.581246998393908e-05
2023-01-21 13:17:02.313315: step: 364/531, loss: 0.05022259056568146
2023-01-21 13:17:03.433635: step: 368/531, loss: 0.00013942719670012593
2023-01-21 13:17:04.571549: step: 372/531, loss: 0.0028100013732910156
2023-01-21 13:17:05.741371: step: 376/531, loss: -7.534026735811494e-06
2023-01-21 13:17:06.894415: step: 380/531, loss: 0.0001866340753622353
2023-01-21 13:17:08.052156: step: 384/531, loss: 0.0005877495277673006
2023-01-21 13:17:09.191642: step: 388/531, loss: 0.007878398522734642
2023-01-21 13:17:10.317801: step: 392/531, loss: 0.010847663506865501
2023-01-21 13:17:11.488435: step: 396/531, loss: 0.08948802947998047
2023-01-21 13:17:12.645597: step: 400/531, loss: 0.0006517409929074347
2023-01-21 13:17:13.817282: step: 404/531, loss: 0.0004644394211936742
2023-01-21 13:17:14.929061: step: 408/531, loss: 0.00035839079646393657
2023-01-21 13:17:16.066780: step: 412/531, loss: 1.3828278042637976e-06
2023-01-21 13:17:17.205333: step: 416/531, loss: 0.009991645812988281
2023-01-21 13:17:18.319855: step: 420/531, loss: 0.00010013580322265625
2023-01-21 13:17:19.451434: step: 424/531, loss: 0.007972145453095436
2023-01-21 13:17:20.574380: step: 428/531, loss: 0.003837204072624445
2023-01-21 13:17:21.702119: step: 432/531, loss: 0.014476395212113857
2023-01-21 13:17:22.822279: step: 436/531, loss: 0.013527489267289639
2023-01-21 13:17:23.956334: step: 440/531, loss: 0.006007385440170765
2023-01-21 13:17:25.085572: step: 444/531, loss: 1.411438006471144e-05
2023-01-21 13:17:26.202500: step: 448/531, loss: 0.0007270813221111894
2023-01-21 13:17:27.297685: step: 452/531, loss: 0.01282720547169447
2023-01-21 13:17:28.460603: step: 456/531, loss: 0.000610732997301966
2023-01-21 13:17:29.619379: step: 460/531, loss: 0.00016469955153297633
2023-01-21 13:17:30.728467: step: 464/531, loss: 0.009271049872040749
2023-01-21 13:17:31.851310: step: 468/531, loss: 0.005040311720222235
2023-01-21 13:17:32.985117: step: 472/531, loss: 0.00562477158382535
2023-01-21 13:17:34.110759: step: 476/531, loss: 0.0023674010299146175
2023-01-21 13:17:35.235508: step: 480/531, loss: 0.008716393262147903
2023-01-21 13:17:36.382305: step: 484/531, loss: 1.3637542906508315e-05
2023-01-21 13:17:37.514127: step: 488/531, loss: 0.0015808106400072575
2023-01-21 13:17:38.653034: step: 492/531, loss: 0.00034332278301008046
2023-01-21 13:17:39.783556: step: 496/531, loss: 0.008898163214325905
2023-01-21 13:17:40.923255: step: 500/531, loss: 0.021915435791015625
2023-01-21 13:17:42.014695: step: 504/531, loss: 8.163452002918348e-05
2023-01-21 13:17:43.123120: step: 508/531, loss: 0.00023155214148573577
2023-01-21 13:17:44.243680: step: 512/531, loss: 0.00039711000863462687
2023-01-21 13:17:45.343055: step: 516/531, loss: 0.0008734703296795487
2023-01-21 13:17:46.492126: step: 520/531, loss: 0.00014181136793922633
2023-01-21 13:17:47.613852: step: 524/531, loss: 8.39531458041165e-06
2023-01-21 13:17:48.743536: step: 528/531, loss: 8.20159948489163e-06
2023-01-21 13:17:49.886524: step: 532/531, loss: 2.6512147087487392e-05
2023-01-21 13:17:50.998126: step: 536/531, loss: 0.0020344748627394438
2023-01-21 13:17:52.130855: step: 540/531, loss: 0.05070533603429794
2023-01-21 13:17:53.280453: step: 544/531, loss: 0.006438541691750288
2023-01-21 13:17:54.404280: step: 548/531, loss: 0.00014414788165595382
2023-01-21 13:17:55.522776: step: 552/531, loss: 0.028077125549316406
2023-01-21 13:17:56.661535: step: 556/531, loss: 0.20700938999652863
2023-01-21 13:17:57.821488: step: 560/531, loss: 0.09249468147754669
2023-01-21 13:17:58.948914: step: 564/531, loss: 0.0003253936592955142
2023-01-21 13:18:00.050818: step: 568/531, loss: 0.00022964477830100805
2023-01-21 13:18:01.176251: step: 572/531, loss: 3.471374657237902e-05
2023-01-21 13:18:02.318197: step: 576/531, loss: 0.010111141949892044
2023-01-21 13:18:03.453741: step: 580/531, loss: 2.4223329091910273e-05
2023-01-21 13:18:04.574618: step: 584/531, loss: 0.0017568588955327868
2023-01-21 13:18:05.671182: step: 588/531, loss: 3.547668529790826e-05
2023-01-21 13:18:06.794163: step: 592/531, loss: 5.569458153331652e-05
2023-01-21 13:18:07.914814: step: 596/531, loss: 0.018486596643924713
2023-01-21 13:18:09.014034: step: 600/531, loss: 3.719329833984375e-05
2023-01-21 13:18:10.138190: step: 604/531, loss: 0.0002512931823730469
2023-01-21 13:18:11.258600: step: 608/531, loss: 0.010549736209213734
2023-01-21 13:18:12.381478: step: 612/531, loss: 0.03506297990679741
2023-01-21 13:18:13.491745: step: 616/531, loss: 7.209778414107859e-05
2023-01-21 13:18:14.621764: step: 620/531, loss: 3.108978125965223e-05
2023-01-21 13:18:15.763555: step: 624/531, loss: 0.009072494693100452
2023-01-21 13:18:16.921725: step: 628/531, loss: 0.007215404417365789
2023-01-21 13:18:18.059712: step: 632/531, loss: 0.0004233360232319683
2023-01-21 13:18:19.182035: step: 636/531, loss: 0.044142913073301315
2023-01-21 13:18:20.310475: step: 640/531, loss: 0.00036535260733217
2023-01-21 13:18:21.414416: step: 644/531, loss: 0.002957153134047985
2023-01-21 13:18:22.543234: step: 648/531, loss: 0.00016708375187590718
2023-01-21 13:18:23.691910: step: 652/531, loss: 0.00025196076603606343
2023-01-21 13:18:24.820437: step: 656/531, loss: 0.00043201446533203125
2023-01-21 13:18:25.958807: step: 660/531, loss: 0.0026784895453602076
2023-01-21 13:18:27.091404: step: 664/531, loss: 0.0004905700916424394
2023-01-21 13:18:28.230032: step: 668/531, loss: 0.0006551742553710938
2023-01-21 13:18:29.343241: step: 672/531, loss: -2.7179717108083423e-06
2023-01-21 13:18:30.507312: step: 676/531, loss: 5.316734313964844e-05
2023-01-21 13:18:31.618516: step: 680/531, loss: 0.00174541468732059
2023-01-21 13:18:32.736433: step: 684/531, loss: 0.000821018242277205
2023-01-21 13:18:33.879189: step: 688/531, loss: 0.00010328293137717992
2023-01-21 13:18:34.973754: step: 692/531, loss: 0.007507896516472101
2023-01-21 13:18:36.104910: step: 696/531, loss: 0.00809936597943306
2023-01-21 13:18:37.237075: step: 700/531, loss: 0.00024790765019133687
2023-01-21 13:18:38.356099: step: 704/531, loss: 8.39233416627394e-06
2023-01-21 13:18:39.470876: step: 708/531, loss: 4.696846190199722e-06
2023-01-21 13:18:40.612774: step: 712/531, loss: 0.011433983221650124
2023-01-21 13:18:41.753204: step: 716/531, loss: 9.431838407181203e-05
2023-01-21 13:18:42.889958: step: 720/531, loss: 5.7220458984375e-06
2023-01-21 13:18:44.036067: step: 724/531, loss: 0.00012941360182594508
2023-01-21 13:18:45.174555: step: 728/531, loss: 0.016379930078983307
2023-01-21 13:18:46.270268: step: 732/531, loss: 0.0003966331423725933
2023-01-21 13:18:47.380409: step: 736/531, loss: 0.0005819320795126259
2023-01-21 13:18:48.512889: step: 740/531, loss: 0.00239906320348382
2023-01-21 13:18:49.626987: step: 744/531, loss: 7.863045175326988e-05
2023-01-21 13:18:50.755509: step: 748/531, loss: 0.00263385777361691
2023-01-21 13:18:51.861876: step: 752/531, loss: 0.013336754404008389
2023-01-21 13:18:52.986467: step: 756/531, loss: 0.017293168231844902
2023-01-21 13:18:54.152895: step: 760/531, loss: 0.0017330170376226306
2023-01-21 13:18:55.271231: step: 764/531, loss: 0.0007416725275106728
2023-01-21 13:18:56.425202: step: 768/531, loss: 0.03218469396233559
2023-01-21 13:18:57.542482: step: 772/531, loss: 1.8119812921213452e-06
2023-01-21 13:18:58.663445: step: 776/531, loss: 5.970001075183973e-05
2023-01-21 13:18:59.801541: step: 780/531, loss: 2.9349326723604463e-05
2023-01-21 13:19:00.941256: step: 784/531, loss: 0.29564762115478516
2023-01-21 13:19:02.058402: step: 788/531, loss: 0.027411652728915215
2023-01-21 13:19:03.142858: step: 792/531, loss: 3.814697265625e-06
2023-01-21 13:19:04.270407: step: 796/531, loss: 8.916854312701616e-06
2023-01-21 13:19:05.373054: step: 800/531, loss: 0.0001122474714065902
2023-01-21 13:19:06.484230: step: 804/531, loss: 1.182556115963962e-05
2023-01-21 13:19:07.611858: step: 808/531, loss: 0.0025780678261071444
2023-01-21 13:19:08.731952: step: 812/531, loss: 0.0016448020469397306
2023-01-21 13:19:09.859770: step: 816/531, loss: 0.002602481748908758
2023-01-21 13:19:11.001504: step: 820/531, loss: 0.027302933856844902
2023-01-21 13:19:12.160935: step: 824/531, loss: 0.005278587341308594
2023-01-21 13:19:13.244567: step: 828/531, loss: 0.007113552186638117
2023-01-21 13:19:14.362153: step: 832/531, loss: 0.02209172397851944
2023-01-21 13:19:15.508386: step: 836/531, loss: 0.00026569367037154734
2023-01-21 13:19:16.670258: step: 840/531, loss: 0.00014038085646461695
2023-01-21 13:19:17.761550: step: 844/531, loss: 7.758141146041453e-05
2023-01-21 13:19:18.929843: step: 848/531, loss: 0.008357048965990543
2023-01-21 13:19:20.062154: step: 852/531, loss: 0.006354332435876131
2023-01-21 13:19:21.171090: step: 856/531, loss: 0.0002624511835165322
2023-01-21 13:19:22.307919: step: 860/531, loss: 0.02940206602215767
2023-01-21 13:19:23.431972: step: 864/531, loss: 0.0004516601620707661
2023-01-21 13:19:24.564931: step: 868/531, loss: 0.018115997314453125
2023-01-21 13:19:25.691485: step: 872/531, loss: 0.027750682085752487
2023-01-21 13:19:26.831506: step: 876/531, loss: 6.961822509765625e-05
2023-01-21 13:19:27.948076: step: 880/531, loss: 0.003585338592529297
2023-01-21 13:19:29.081519: step: 884/531, loss: -1.7833710444392636e-05
2023-01-21 13:19:30.198136: step: 888/531, loss: 0.005775928497314453
2023-01-21 13:19:31.334616: step: 892/531, loss: 0.0016241073608398438
2023-01-21 13:19:32.467978: step: 896/531, loss: 0.02279062382876873
2023-01-21 13:19:33.573873: step: 900/531, loss: 2.1219253540039062e-05
2023-01-21 13:19:34.697393: step: 904/531, loss: 8.678436279296875e-05
2023-01-21 13:19:35.819168: step: 908/531, loss: 0.000606155430432409
2023-01-21 13:19:36.935237: step: 912/531, loss: 7.4386593951203395e-06
2023-01-21 13:19:38.063042: step: 916/531, loss: 0.008005904965102673
2023-01-21 13:19:39.212653: step: 920/531, loss: 0.0012835502857342362
2023-01-21 13:19:40.323004: step: 924/531, loss: 0.00035848619882017374
2023-01-21 13:19:41.429106: step: 928/531, loss: 2.86102294921875e-06
2023-01-21 13:19:42.563319: step: 932/531, loss: 9.069442603504285e-05
2023-01-21 13:19:43.696368: step: 936/531, loss: 0.00040578845073468983
2023-01-21 13:19:44.838906: step: 940/531, loss: 0.01350097730755806
2023-01-21 13:19:45.938186: step: 944/531, loss: 0.0004211425839457661
2023-01-21 13:19:47.061091: step: 948/531, loss: 0.0013070107670500875
2023-01-21 13:19:48.202533: step: 952/531, loss: 0.0015855790115892887
2023-01-21 13:19:49.330861: step: 956/531, loss: 0.004326820373535156
2023-01-21 13:19:50.465583: step: 960/531, loss: 0.041608620434999466
2023-01-21 13:19:51.604718: step: 964/531, loss: 0.014751816168427467
2023-01-21 13:19:52.715880: step: 968/531, loss: 0.009824848733842373
2023-01-21 13:19:53.878001: step: 972/531, loss: 0.003799057099968195
2023-01-21 13:19:55.009091: step: 976/531, loss: 0.022680187597870827
2023-01-21 13:19:56.123346: step: 980/531, loss: 0.0005342483636923134
2023-01-21 13:19:57.223968: step: 984/531, loss: 0.014588928781449795
2023-01-21 13:19:58.324133: step: 988/531, loss: 7.915497008070815e-06
2023-01-21 13:19:59.451795: step: 992/531, loss: 0.003313350724056363
2023-01-21 13:20:00.588719: step: 996/531, loss: 0.20702151954174042
2023-01-21 13:20:01.753744: step: 1000/531, loss: 2.536773718020413e-05
2023-01-21 13:20:02.906596: step: 1004/531, loss: 0.0031054497230798006
2023-01-21 13:20:04.036138: step: 1008/531, loss: 0.017128562554717064
2023-01-21 13:20:05.158821: step: 1012/531, loss: 0.0001161575346486643
2023-01-21 13:20:06.278297: step: 1016/531, loss: 0.025709105655550957
2023-01-21 13:20:07.405268: step: 1020/531, loss: 0.0026129246689379215
2023-01-21 13:20:08.505689: step: 1024/531, loss: 0.0002593994140625
2023-01-21 13:20:09.641439: step: 1028/531, loss: 0.0020751000847667456
2023-01-21 13:20:10.784351: step: 1032/531, loss: 0.01820697821676731
2023-01-21 13:20:11.940282: step: 1036/531, loss: 0.0007259369012899697
2023-01-21 13:20:13.059500: step: 1040/531, loss: 0.015400601550936699
2023-01-21 13:20:14.195097: step: 1044/531, loss: 7.9107288911473e-05
2023-01-21 13:20:15.298470: step: 1048/531, loss: 5.3024294174974784e-05
2023-01-21 13:20:16.428500: step: 1052/531, loss: 0.00101556780282408
2023-01-21 13:20:17.602533: step: 1056/531, loss: 0.02218799665570259
2023-01-21 13:20:18.724249: step: 1060/531, loss: 0.026259994134306908
2023-01-21 13:20:19.861933: step: 1064/531, loss: 0.013966751284897327
2023-01-21 13:20:20.961131: step: 1068/531, loss: 0.00045413972111418843
2023-01-21 13:20:22.094138: step: 1072/531, loss: 0.0023661614395678043
2023-01-21 13:20:23.215722: step: 1076/531, loss: 0.005993461702018976
2023-01-21 13:20:24.343884: step: 1080/531, loss: 0.02153310924768448
2023-01-21 13:20:25.487298: step: 1084/531, loss: 0.004776477813720703
2023-01-21 13:20:26.597086: step: 1088/531, loss: 0.0001930236758198589
2023-01-21 13:20:27.728053: step: 1092/531, loss: -4.148483185417717e-06
2023-01-21 13:20:28.846392: step: 1096/531, loss: 9.479522850597277e-05
2023-01-21 13:20:29.995716: step: 1100/531, loss: 0.00266265869140625
2023-01-21 13:20:31.097485: step: 1104/531, loss: 0.007720566354691982
2023-01-21 13:20:32.231642: step: 1108/531, loss: 0.004929161164909601
2023-01-21 13:20:33.341129: step: 1112/531, loss: 0.0001089096040232107
2023-01-21 13:20:34.451745: step: 1116/531, loss: 0.07059125602245331
2023-01-21 13:20:35.559099: step: 1120/531, loss: 2.3269654775504023e-05
2023-01-21 13:20:36.676602: step: 1124/531, loss: 0.01633920706808567
2023-01-21 13:20:37.803190: step: 1128/531, loss: 0.0043392181396484375
2023-01-21 13:20:38.917173: step: 1132/531, loss: 0.00028929710970260203
2023-01-21 13:20:40.018209: step: 1136/531, loss: 0.00821685791015625
2023-01-21 13:20:41.156892: step: 1140/531, loss: 0.004209041595458984
2023-01-21 13:20:42.274641: step: 1144/531, loss: 0.00011234283010708168
2023-01-21 13:20:43.391469: step: 1148/531, loss: 0.0002739906485658139
2023-01-21 13:20:44.538951: step: 1152/531, loss: 0.015117360278964043
2023-01-21 13:20:45.652943: step: 1156/531, loss: 0.0002511024649720639
2023-01-21 13:20:46.767037: step: 1160/531, loss: 0.0004574775812216103
2023-01-21 13:20:47.866765: step: 1164/531, loss: 0.004498672671616077
2023-01-21 13:20:48.985779: step: 1168/531, loss: 0.02213726006448269
2023-01-21 13:20:50.094030: step: 1172/531, loss: 0.00012111663818359375
2023-01-21 13:20:51.234482: step: 1176/531, loss: 2.098083541568485e-06
2023-01-21 13:20:52.384181: step: 1180/531, loss: 0.00018043519230559468
2023-01-21 13:20:53.486413: step: 1184/531, loss: 1.23977656585339e-06
2023-01-21 13:20:54.619407: step: 1188/531, loss: 8.401871309615672e-05
2023-01-21 13:20:55.767689: step: 1192/531, loss: 0.018071364611387253
2023-01-21 13:20:56.891641: step: 1196/531, loss: 8.58306884765625e-06
2023-01-21 13:20:57.986876: step: 1200/531, loss: 0.0033739092759788036
2023-01-21 13:20:59.087142: step: 1204/531, loss: 0.0014198303688317537
2023-01-21 13:21:00.225242: step: 1208/531, loss: 0.007958030328154564
2023-01-21 13:21:01.355271: step: 1212/531, loss: 1.678466833254788e-05
2023-01-21 13:21:02.481706: step: 1216/531, loss: 0.0005546570173464715
2023-01-21 13:21:03.602867: step: 1220/531, loss: 0.0019398690201342106
2023-01-21 13:21:04.741369: step: 1224/531, loss: 0.0013425827492028475
2023-01-21 13:21:05.893303: step: 1228/531, loss: 0.023987198248505592
2023-01-21 13:21:07.028047: step: 1232/531, loss: 0.006106758490204811
2023-01-21 13:21:08.163069: step: 1236/531, loss: 0.004833793733268976
2023-01-21 13:21:09.304909: step: 1240/531, loss: 0.0038857460021972656
2023-01-21 13:21:10.452989: step: 1244/531, loss: 0.025882530957460403
2023-01-21 13:21:11.561481: step: 1248/531, loss: 0.002964019775390625
2023-01-21 13:21:12.723419: step: 1252/531, loss: 6.10351571594947e-06
2023-01-21 13:21:13.906979: step: 1256/531, loss: 0.03321528807282448
2023-01-21 13:21:15.033895: step: 1260/531, loss: 7.686615572310984e-05
2023-01-21 13:21:16.171561: step: 1264/531, loss: 5.7220458984375e-06
2023-01-21 13:21:17.285358: step: 1268/531, loss: 0.0004215240478515625
2023-01-21 13:21:18.416022: step: 1272/531, loss: 2.28881845032447e-06
2023-01-21 13:21:19.548931: step: 1276/531, loss: 5.626678466796875e-05
2023-01-21 13:21:20.678786: step: 1280/531, loss: 0.006225490476936102
2023-01-21 13:21:21.802929: step: 1284/531, loss: 0.04358420521020889
2023-01-21 13:21:22.925323: step: 1288/531, loss: 0.013238477520644665
2023-01-21 13:21:24.077766: step: 1292/531, loss: 5.2833554946118966e-05
2023-01-21 13:21:25.200415: step: 1296/531, loss: 2.155303991457913e-05
2023-01-21 13:21:26.346946: step: 1300/531, loss: 0.004207992926239967
2023-01-21 13:21:27.455018: step: 1304/531, loss: 0.0008137702825479209
2023-01-21 13:21:28.579509: step: 1308/531, loss: 2.3412703740177676e-05
2023-01-21 13:21:29.707064: step: 1312/531, loss: 8.840561349643394e-05
2023-01-21 13:21:30.837423: step: 1316/531, loss: 0.0001884460507426411
2023-01-21 13:21:31.991531: step: 1320/531, loss: 4.57763690064894e-06
2023-01-21 13:21:33.133864: step: 1324/531, loss: 0.00011520386033225805
2023-01-21 13:21:34.275642: step: 1328/531, loss: 0.0070549012161791325
2023-01-21 13:21:35.428073: step: 1332/531, loss: 0.0007776260608807206
2023-01-21 13:21:36.605768: step: 1336/531, loss: 7.677823305130005e-06
2023-01-21 13:21:37.735111: step: 1340/531, loss: 1.5068053471622989e-05
2023-01-21 13:21:38.867109: step: 1344/531, loss: 0.0001941680966410786
2023-01-21 13:21:40.001074: step: 1348/531, loss: 0.04260826110839844
2023-01-21 13:21:41.127691: step: 1352/531, loss: 0.00030994415283203125
2023-01-21 13:21:42.284796: step: 1356/531, loss: 0.00022239686222746968
2023-01-21 13:21:43.395380: step: 1360/531, loss: 0.022145235911011696
2023-01-21 13:21:44.505354: step: 1364/531, loss: 0.02117137983441353
2023-01-21 13:21:45.630450: step: 1368/531, loss: 0.0033872604835778475
2023-01-21 13:21:46.759845: step: 1372/531, loss: 0.03773879632353783
2023-01-21 13:21:47.871585: step: 1376/531, loss: 0.0007390021928586066
2023-01-21 13:21:48.987642: step: 1380/531, loss: 0.0001729965297272429
2023-01-21 13:21:50.114352: step: 1384/531, loss: 0.0005800247308798134
2023-01-21 13:21:51.203567: step: 1388/531, loss: 2.6226043701171875e-05
2023-01-21 13:21:52.375385: step: 1392/531, loss: 0.00010404587374068797
2023-01-21 13:21:53.558193: step: 1396/531, loss: 0.0001596450892975554
2023-01-21 13:21:54.647509: step: 1400/531, loss: 0.011488009244203568
2023-01-21 13:21:55.759393: step: 1404/531, loss: 0.0032346725929528475
2023-01-21 13:21:56.931969: step: 1408/531, loss: 0.060723211616277695
2023-01-21 13:21:58.058783: step: 1412/531, loss: 0.00080108642578125
2023-01-21 13:21:59.192562: step: 1416/531, loss: 0.008340835571289062
2023-01-21 13:22:00.299026: step: 1420/531, loss: 0.00047836307203397155
2023-01-21 13:22:01.411320: step: 1424/531, loss: 0.0009883880848065019
2023-01-21 13:22:02.559122: step: 1428/531, loss: 0.00024509429931640625
2023-01-21 13:22:03.683312: step: 1432/531, loss: 0.0003125190851278603
2023-01-21 13:22:04.812007: step: 1436/531, loss: 4.673004150390625e-05
2023-01-21 13:22:05.976452: step: 1440/531, loss: 0.005370807833969593
2023-01-21 13:22:07.116362: step: 1444/531, loss: 0.0233046542853117
2023-01-21 13:22:08.243897: step: 1448/531, loss: 0.00013008118548896164
2023-01-21 13:22:09.338348: step: 1452/531, loss: 0.0004642486455850303
2023-01-21 13:22:10.450981: step: 1456/531, loss: 0.0006960868486203253
2023-01-21 13:22:11.583759: step: 1460/531, loss: 0.023892974480986595
2023-01-21 13:22:12.722891: step: 1464/531, loss: 2.765656063274946e-06
2023-01-21 13:22:13.853997: step: 1468/531, loss: 0.01681060716509819
2023-01-21 13:22:14.980174: step: 1472/531, loss: 0.0021217346657067537
2023-01-21 13:22:16.118363: step: 1476/531, loss: 7.2479248046875e-05
2023-01-21 13:22:17.247910: step: 1480/531, loss: 0.018645094707608223
2023-01-21 13:22:18.349109: step: 1484/531, loss: 1.0490417707842425e-06
2023-01-21 13:22:19.469836: step: 1488/531, loss: 6.389617919921875e-05
2023-01-21 13:22:20.577588: step: 1492/531, loss: 0.0037463190965354443
2023-01-21 13:22:21.721410: step: 1496/531, loss: 0.0002151489316020161
2023-01-21 13:22:22.870273: step: 1500/531, loss: 0.0007448196993209422
2023-01-21 13:22:24.008666: step: 1504/531, loss: 0.00015525816706940532
2023-01-21 13:22:25.137185: step: 1508/531, loss: 1.1157989320054185e-05
2023-01-21 13:22:26.278494: step: 1512/531, loss: 0.0005368232959881425
2023-01-21 13:22:27.399663: step: 1516/531, loss: 0.002760982373729348
2023-01-21 13:22:28.522184: step: 1520/531, loss: 0.0002831935998983681
2023-01-21 13:22:29.643446: step: 1524/531, loss: 5.927085658186115e-05
2023-01-21 13:22:30.783993: step: 1528/531, loss: 0.012388181872665882
2023-01-21 13:22:31.903382: step: 1532/531, loss: 0.0011230468517169356
2023-01-21 13:22:33.027817: step: 1536/531, loss: 0.002504062606021762
2023-01-21 13:22:34.153968: step: 1540/531, loss: 0.007088852114975452
2023-01-21 13:22:35.274009: step: 1544/531, loss: 0.001753950142301619
2023-01-21 13:22:36.439437: step: 1548/531, loss: 0.00023450850858353078
2023-01-21 13:22:37.582359: step: 1552/531, loss: 0.002294349716976285
2023-01-21 13:22:38.711168: step: 1556/531, loss: 3.128051685052924e-05
2023-01-21 13:22:39.825470: step: 1560/531, loss: -1.144409225162235e-06
2023-01-21 13:22:40.974914: step: 1564/531, loss: 0.00031647682772018015
2023-01-21 13:22:42.049742: step: 1568/531, loss: 0.03847246244549751
2023-01-21 13:22:43.193317: step: 1572/531, loss: 1.2397766795402276e-06
2023-01-21 13:22:44.343240: step: 1576/531, loss: 0.054741859436035156
2023-01-21 13:22:45.499475: step: 1580/531, loss: 0.0008403778774663806
2023-01-21 13:22:46.615425: step: 1584/531, loss: 0.0003098964807577431
2023-01-21 13:22:47.739165: step: 1588/531, loss: 4.1627885366324335e-05
2023-01-21 13:22:48.845937: step: 1592/531, loss: 0.006285286042839289
2023-01-21 13:22:49.991821: step: 1596/531, loss: 0.00282115931622684
2023-01-21 13:22:51.130251: step: 1600/531, loss: 0.08352365344762802
2023-01-21 13:22:52.266994: step: 1604/531, loss: 0.0003783702850341797
2023-01-21 13:22:53.372832: step: 1608/531, loss: 5.435943603515625e-05
2023-01-21 13:22:54.498570: step: 1612/531, loss: 2.574920654296875e-05
2023-01-21 13:22:55.617351: step: 1616/531, loss: -4.100799742445815e-06
2023-01-21 13:22:56.730873: step: 1620/531, loss: 0.00026025774423033
2023-01-21 13:22:57.864102: step: 1624/531, loss: 2.384185791015625e-06
2023-01-21 13:22:58.994187: step: 1628/531, loss: 3.380775160621852e-05
2023-01-21 13:23:00.142148: step: 1632/531, loss: 7.400512549793348e-05
2023-01-21 13:23:01.274951: step: 1636/531, loss: 4.692077709478326e-05
2023-01-21 13:23:02.394447: step: 1640/531, loss: 0.42092058062553406
2023-01-21 13:23:03.509175: step: 1644/531, loss: 0.24106641113758087
2023-01-21 13:23:04.630978: step: 1648/531, loss: 0.0036483765579760075
2023-01-21 13:23:05.779831: step: 1652/531, loss: 0.0003770828479900956
2023-01-21 13:23:06.886151: step: 1656/531, loss: 0.0006292343023233116
2023-01-21 13:23:08.017875: step: 1660/531, loss: 0.013663101010024548
2023-01-21 13:23:09.130542: step: 1664/531, loss: 0.020683003589510918
2023-01-21 13:23:10.239916: step: 1668/531, loss: 0.009380340576171875
2023-01-21 13:23:11.370206: step: 1672/531, loss: 6.675720669591101e-06
2023-01-21 13:23:12.505585: step: 1676/531, loss: 0.007296848110854626
2023-01-21 13:23:13.646397: step: 1680/531, loss: 0.0007396697765216231
2023-01-21 13:23:14.787660: step: 1684/531, loss: 4.0626528061693534e-05
2023-01-21 13:23:15.914662: step: 1688/531, loss: 0.010335540398955345
2023-01-21 13:23:17.053826: step: 1692/531, loss: 7.82012939453125e-05
2023-01-21 13:23:18.181668: step: 1696/531, loss: 0.0024898527190089226
2023-01-21 13:23:19.275977: step: 1700/531, loss: 0.0002401351957814768
2023-01-21 13:23:20.395931: step: 1704/531, loss: 0.00022721290588378906
2023-01-21 13:23:21.525245: step: 1708/531, loss: 0.002048683352768421
2023-01-21 13:23:22.669509: step: 1712/531, loss: 8.964539119915571e-06
2023-01-21 13:23:23.786484: step: 1716/531, loss: 0.0006032944074831903
2023-01-21 13:23:24.930793: step: 1720/531, loss: 0.010449791327118874
2023-01-21 13:23:26.031198: step: 1724/531, loss: 3.52859501617786e-06
2023-01-21 13:23:27.128921: step: 1728/531, loss: 0.0011196136474609375
2023-01-21 13:23:28.238168: step: 1732/531, loss: 0.00024547576322220266
2023-01-21 13:23:29.334620: step: 1736/531, loss: 5.149840944795869e-06
2023-01-21 13:23:30.489008: step: 1740/531, loss: 0.3806924819946289
2023-01-21 13:23:31.646711: step: 1744/531, loss: 0.045430660247802734
2023-01-21 13:23:32.760905: step: 1748/531, loss: 4.901886131847277e-05
2023-01-21 13:23:33.894756: step: 1752/531, loss: 0.00022697450185660273
2023-01-21 13:23:35.012557: step: 1756/531, loss: 0.000573706638533622
2023-01-21 13:23:36.150849: step: 1760/531, loss: 0.0004383087216410786
2023-01-21 13:23:37.293954: step: 1764/531, loss: 2.5653840566519648e-05
2023-01-21 13:23:38.468601: step: 1768/531, loss: 4.2629242670955136e-05
2023-01-21 13:23:39.605855: step: 1772/531, loss: 9.62108388193883e-05
2023-01-21 13:23:40.743824: step: 1776/531, loss: 0.01283888891339302
2023-01-21 13:23:41.924424: step: 1780/531, loss: 2.0885467165498994e-05
2023-01-21 13:23:43.036925: step: 1784/531, loss: 5.14984139954322e-06
2023-01-21 13:23:44.157426: step: 1788/531, loss: 6.518364534713328e-05
2023-01-21 13:23:45.270739: step: 1792/531, loss: 0.0001871108979685232
2023-01-21 13:23:46.401990: step: 1796/531, loss: 0.10783214867115021
2023-01-21 13:23:47.518369: step: 1800/531, loss: 0.0047248839400708675
2023-01-21 13:23:48.628722: step: 1804/531, loss: 0.0028430938255041838
2023-01-21 13:23:49.766794: step: 1808/531, loss: 0.09369969367980957
2023-01-21 13:23:50.882281: step: 1812/531, loss: 0.00015335081843659282
2023-01-21 13:23:52.017163: step: 1816/531, loss: 0.04500322416424751
2023-01-21 13:23:53.150091: step: 1820/531, loss: 0.0003167152462992817
2023-01-21 13:23:54.260127: step: 1824/531, loss: 3.051757857974735e-06
2023-01-21 13:23:55.371842: step: 1828/531, loss: 0.00010747909982455894
2023-01-21 13:23:56.498804: step: 1832/531, loss: 0.0003711700555868447
2023-01-21 13:23:57.626070: step: 1836/531, loss: 3.871917579090223e-05
2023-01-21 13:23:58.728401: step: 1840/531, loss: 0.02488117292523384
2023-01-21 13:23:59.819919: step: 1844/531, loss: 0.0032421110663563013
2023-01-21 13:24:00.990966: step: 1848/531, loss: 0.0074443817138671875
2023-01-21 13:24:02.128146: step: 1852/531, loss: 7.305145118152723e-05
2023-01-21 13:24:03.255008: step: 1856/531, loss: 0.004403972532600164
2023-01-21 13:24:04.389592: step: 1860/531, loss: 0.06438350677490234
2023-01-21 13:24:05.517012: step: 1864/531, loss: 0.0074637411162257195
2023-01-21 13:24:06.655748: step: 1868/531, loss: 0.004278755281120539
2023-01-21 13:24:07.787237: step: 1872/531, loss: 0.0014993667136877775
2023-01-21 13:24:08.917651: step: 1876/531, loss: 1.316070574830519e-05
2023-01-21 13:24:10.026746: step: 1880/531, loss: 5.912781125516631e-05
2023-01-21 13:24:11.147246: step: 1884/531, loss: 0.0011793137528002262
2023-01-21 13:24:12.251849: step: 1888/531, loss: -1.621246337890625e-05
2023-01-21 13:24:13.400504: step: 1892/531, loss: 4.4345855712890625e-05
2023-01-21 13:24:14.515186: step: 1896/531, loss: 0.012486649677157402
2023-01-21 13:24:15.656497: step: 1900/531, loss: 0.004736042115837336
2023-01-21 13:24:16.788647: step: 1904/531, loss: 0.00022182465181685984
2023-01-21 13:24:17.907772: step: 1908/531, loss: 2.174377368646674e-05
2023-01-21 13:24:19.022258: step: 1912/531, loss: 2.3365020751953125e-05
2023-01-21 13:24:20.147404: step: 1916/531, loss: 0.008999919518828392
2023-01-21 13:24:21.278844: step: 1920/531, loss: 0.0002548217889852822
2023-01-21 13:24:22.384095: step: 1924/531, loss: 0.02043762430548668
2023-01-21 13:24:23.529192: step: 1928/531, loss: 0.010158729739487171
2023-01-21 13:24:24.771012: step: 1932/531, loss: 0.027324294671416283
2023-01-21 13:24:25.893946: step: 1936/531, loss: 8.22067231638357e-05
2023-01-21 13:24:26.994975: step: 1940/531, loss: 0.0005418777000159025
2023-01-21 13:24:28.114818: step: 1944/531, loss: 1.373290979245212e-05
2023-01-21 13:24:29.269180: step: 1948/531, loss: 0.00910201109945774
2023-01-21 13:24:30.405412: step: 1952/531, loss: 0.032892417162656784
2023-01-21 13:24:31.505559: step: 1956/531, loss: 0.0015090942615643144
2023-01-21 13:24:32.633247: step: 1960/531, loss: 0.00014009476581122726
2023-01-21 13:24:33.756313: step: 1964/531, loss: 0.00041751860408112407
2023-01-21 13:24:34.909654: step: 1968/531, loss: 0.06038255617022514
2023-01-21 13:24:36.052696: step: 1972/531, loss: 0.01559219416230917
2023-01-21 13:24:37.160554: step: 1976/531, loss: 0.004004573915153742
2023-01-21 13:24:38.284359: step: 1980/531, loss: 0.0007836341974325478
2023-01-21 13:24:39.379954: step: 1984/531, loss: 0.0003679275687318295
2023-01-21 13:24:40.491621: step: 1988/531, loss: 0.0022205354180186987
2023-01-21 13:24:41.640145: step: 1992/531, loss: 0.0010107994312420487
2023-01-21 13:24:42.809221: step: 1996/531, loss: 0.0005348205449990928
2023-01-21 13:24:43.921953: step: 2000/531, loss: 0.0001381397305522114
2023-01-21 13:24:45.062879: step: 2004/531, loss: 0.018889904022216797
2023-01-21 13:24:46.193106: step: 2008/531, loss: 0.00020360946655273438
2023-01-21 13:24:47.326068: step: 2012/531, loss: 0.012942076660692692
2023-01-21 13:24:48.463486: step: 2016/531, loss: -5.722046125811175e-07
2023-01-21 13:24:49.574027: step: 2020/531, loss: 0.03893766552209854
2023-01-21 13:24:50.716911: step: 2024/531, loss: 0.011793326586484909
2023-01-21 13:24:51.862236: step: 2028/531, loss: 0.0036993026733398438
2023-01-21 13:24:52.992360: step: 2032/531, loss: -8.296966370835435e-06
2023-01-21 13:24:54.112645: step: 2036/531, loss: 0.009547615423798561
2023-01-21 13:24:55.267751: step: 2040/531, loss: 0.0011316300369799137
2023-01-21 13:24:56.420465: step: 2044/531, loss: 0.03160962834954262
2023-01-21 13:24:57.558548: step: 2048/531, loss: 0.00853576697409153
2023-01-21 13:24:58.685149: step: 2052/531, loss: 7.104873930074973e-06
2023-01-21 13:24:59.812468: step: 2056/531, loss: 0.007495594210922718
2023-01-21 13:25:00.916481: step: 2060/531, loss: 0.00033202170743606985
2023-01-21 13:25:02.032262: step: 2064/531, loss: 0.012041855603456497
2023-01-21 13:25:03.132279: step: 2068/531, loss: 0.0003266334533691406
2023-01-21 13:25:04.238689: step: 2072/531, loss: 3.890991138177924e-05
2023-01-21 13:25:05.330363: step: 2076/531, loss: 2.1648407710017636e-05
2023-01-21 13:25:06.440265: step: 2080/531, loss: 1.902580333990045e-05
2023-01-21 13:25:07.541950: step: 2084/531, loss: 0.018280887976288795
2023-01-21 13:25:08.646996: step: 2088/531, loss: 0.012325095944106579
2023-01-21 13:25:09.796033: step: 2092/531, loss: 0.00011081696720793843
2023-01-21 13:25:10.891602: step: 2096/531, loss: 0.0012516023125499487
2023-01-21 13:25:12.013221: step: 2100/531, loss: 0.0034067153465002775
2023-01-21 13:25:13.127624: step: 2104/531, loss: 0.019527912139892578
2023-01-21 13:25:14.289022: step: 2108/531, loss: 0.0006746292347088456
2023-01-21 13:25:15.435053: step: 2112/531, loss: 1.8978118532686494e-05
2023-01-21 13:25:16.556782: step: 2116/531, loss: 0.00045690534170717
2023-01-21 13:25:17.703417: step: 2120/531, loss: 0.0008192539680749178
2023-01-21 13:25:18.853801: step: 2124/531, loss: 0.026607418432831764
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.5611164581328201, 'r': 0.7762982689747004, 'f1': 0.6513966480446928}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6030534351145038, 'r': 0.800834824090638, 'f1': 0.6880122950819673}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5681818181818182, 'r': 0.9259259259259259, 'f1': 0.7042253521126761}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.5423728813559322, 'r': 0.5079365079365079, 'f1': 0.5245901639344263}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.32653061224489793, 'r': 0.4444444444444444, 'f1': 0.3764705882352941}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 28
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 13:25:59.402422: step: 4/531, loss: 0.0006275177001953125
2023-01-21 13:26:00.501042: step: 8/531, loss: 0.028791142627596855
2023-01-21 13:26:01.617963: step: 12/531, loss: 0.0001349449303233996
2023-01-21 13:26:02.716002: step: 16/531, loss: 0.0019812583923339844
2023-01-21 13:26:03.834207: step: 20/531, loss: 8.983612497104332e-05
2023-01-21 13:26:04.951904: step: 24/531, loss: 0.00016198158846236765
2023-01-21 13:26:06.062801: step: 28/531, loss: 0.0012340545654296875
2023-01-21 13:26:07.204828: step: 32/531, loss: 0.00019979476928710938
2023-01-21 13:26:08.310545: step: 36/531, loss: 0.007952691055834293
2023-01-21 13:26:09.396980: step: 40/531, loss: 0.0002736568567343056
2023-01-21 13:26:10.528307: step: 44/531, loss: 0.0031127932015806437
2023-01-21 13:26:11.639306: step: 48/531, loss: 0.002771759172901511
2023-01-21 13:26:12.765677: step: 52/531, loss: 0.00010395050048828125
2023-01-21 13:26:13.881918: step: 56/531, loss: 0.0006320953834801912
2023-01-21 13:26:15.020207: step: 60/531, loss: 0.027740001678466797
2023-01-21 13:26:16.168142: step: 64/531, loss: 0.03337583690881729
2023-01-21 13:26:17.299501: step: 68/531, loss: 0.036821987479925156
2023-01-21 13:26:18.434856: step: 72/531, loss: 0.00028929710970260203
2023-01-21 13:26:19.551770: step: 76/531, loss: 0.006862735841423273
2023-01-21 13:26:20.670056: step: 80/531, loss: 0.00020446778216864914
2023-01-21 13:26:21.792355: step: 84/531, loss: 0.009822655469179153
2023-01-21 13:26:22.943609: step: 88/531, loss: 0.0024022103752940893
2023-01-21 13:26:24.044064: step: 92/531, loss: 7.214546349132434e-05
2023-01-21 13:26:25.199764: step: 96/531, loss: 0.0005019187810830772
2023-01-21 13:26:26.385303: step: 100/531, loss: 9.994507126975805e-05
2023-01-21 13:26:27.518799: step: 104/531, loss: -1.52587890625e-05
2023-01-21 13:26:28.659998: step: 108/531, loss: 0.00011463165719760582
2023-01-21 13:26:29.768470: step: 112/531, loss: 0.026998519897460938
2023-01-21 13:26:30.893960: step: 116/531, loss: 2.7656553811539197e-06
2023-01-21 13:26:31.999818: step: 120/531, loss: 0.0004839897155761719
2023-01-21 13:26:33.128933: step: 124/531, loss: 1.1920928955078125e-06
2023-01-21 13:26:34.318679: step: 128/531, loss: 6.30378708592616e-05
2023-01-21 13:26:35.449969: step: 132/531, loss: 0.0050300597213208675
2023-01-21 13:26:36.612457: step: 136/531, loss: 0.0007247925386764109
2023-01-21 13:26:37.755470: step: 140/531, loss: 0.006578660104423761
2023-01-21 13:26:38.874878: step: 144/531, loss: 8.277893357444555e-05
2023-01-21 13:26:39.986239: step: 148/531, loss: 0.0004604339774232358
2023-01-21 13:26:41.144735: step: 152/531, loss: 0.006082343868911266
2023-01-21 13:26:42.253846: step: 156/531, loss: 4.158019874012098e-05
2023-01-21 13:26:43.373758: step: 160/531, loss: 8.535384949936997e-06
2023-01-21 13:26:44.534122: step: 164/531, loss: 0.0004722595331259072
2023-01-21 13:26:45.647001: step: 168/531, loss: 0.0003643989621195942
2023-01-21 13:26:46.797052: step: 172/531, loss: 0.0011552810901775956
2023-01-21 13:26:47.940575: step: 176/531, loss: 0.007882309146225452
2023-01-21 13:26:49.071615: step: 180/531, loss: 0.0005466461298055947
2023-01-21 13:26:50.200515: step: 184/531, loss: 0.0002628326474223286
2023-01-21 13:26:51.289010: step: 188/531, loss: 5.578995114774443e-06
2023-01-21 13:26:52.394715: step: 192/531, loss: 9.822845640883315e-06
2023-01-21 13:26:53.537171: step: 196/531, loss: 0.00012459754361771047
2023-01-21 13:26:54.668472: step: 200/531, loss: 4.08649466407951e-05
2023-01-21 13:26:55.787307: step: 204/531, loss: 0.0016778946155682206
2023-01-21 13:26:56.887644: step: 208/531, loss: 0.0025581358931958675
2023-01-21 13:26:58.003636: step: 212/531, loss: 0.0029953003395348787
2023-01-21 13:26:59.134092: step: 216/531, loss: 2.47955313170678e-06
2023-01-21 13:27:00.266580: step: 220/531, loss: 0.008331107906997204
2023-01-21 13:27:01.374226: step: 224/531, loss: 0.0006005287286825478
2023-01-21 13:27:02.472860: step: 228/531, loss: 0.002193450927734375
2023-01-21 13:27:03.593184: step: 232/531, loss: 0.0006574630970135331
2023-01-21 13:27:04.706877: step: 236/531, loss: 0.010582923889160156
2023-01-21 13:27:05.823844: step: 240/531, loss: 0.0018580436008051038
2023-01-21 13:27:06.935053: step: 244/531, loss: 3.604888843256049e-05
2023-01-21 13:27:08.056785: step: 248/531, loss: 1.33514404296875e-05
2023-01-21 13:27:09.185670: step: 252/531, loss: 0.0003647804260253906
2023-01-21 13:27:10.315679: step: 256/531, loss: 0.003345298580825329
2023-01-21 13:27:11.403369: step: 260/531, loss: 0.00014553070650435984
2023-01-21 13:27:12.498114: step: 264/531, loss: 0.0002353191375732422
2023-01-21 13:27:13.628880: step: 268/531, loss: 0.0002189636288676411
2023-01-21 13:27:14.746200: step: 272/531, loss: 3.0422212148550898e-05
2023-01-21 13:27:15.880258: step: 276/531, loss: 0.0053914072923362255
2023-01-21 13:27:17.011396: step: 280/531, loss: 0.00017261505126953125
2023-01-21 13:27:18.137523: step: 284/531, loss: 0.005187606904655695
2023-01-21 13:27:19.270233: step: 288/531, loss: 2.670288040462765e-06
2023-01-21 13:27:20.392494: step: 292/531, loss: 0.005283260252326727
2023-01-21 13:27:21.509841: step: 296/531, loss: 0.01437301654368639
2023-01-21 13:27:22.619934: step: 300/531, loss: 0.001302480697631836
2023-01-21 13:27:23.757145: step: 304/531, loss: 0.0005994797102175653
2023-01-21 13:27:24.885934: step: 308/531, loss: 0.00015754700871184468
2023-01-21 13:27:26.027077: step: 312/531, loss: 0.00027971266536042094
2023-01-21 13:27:27.151046: step: 316/531, loss: 0.0273303035646677
2023-01-21 13:27:28.274997: step: 320/531, loss: 0.0008176803821697831
2023-01-21 13:27:29.417088: step: 324/531, loss: 0.00035114289494231343
2023-01-21 13:27:30.550633: step: 328/531, loss: 0.009064388461411
2023-01-21 13:27:31.674085: step: 332/531, loss: 0.387355238199234
2023-01-21 13:27:32.775483: step: 336/531, loss: 0.0007592201582156122
2023-01-21 13:27:33.911323: step: 340/531, loss: 4.1484832763671875e-05
2023-01-21 13:27:35.017400: step: 344/531, loss: 1.8119813830708154e-05
2023-01-21 13:27:36.114576: step: 348/531, loss: 5.626678557746345e-06
2023-01-21 13:27:37.220026: step: 352/531, loss: 2.193450927734375e-05
2023-01-21 13:27:38.344698: step: 356/531, loss: 0.00015535354032181203
2023-01-21 13:27:39.429446: step: 360/531, loss: 6.413459777832031e-05
2023-01-21 13:27:40.554342: step: 364/531, loss: 0.005117225926369429
2023-01-21 13:27:41.672517: step: 368/531, loss: 0.0014378547202795744
2023-01-21 13:27:42.818878: step: 372/531, loss: 0.0001203536958200857
2023-01-21 13:27:43.940208: step: 376/531, loss: 0.008551979437470436
2023-01-21 13:27:45.068784: step: 380/531, loss: 1.697540210443549e-05
2023-01-21 13:27:46.239058: step: 384/531, loss: 4.234314110362902e-05
2023-01-21 13:27:47.388452: step: 388/531, loss: 0.0012197495670989156
2023-01-21 13:27:48.529271: step: 392/531, loss: 7.081032526912168e-05
2023-01-21 13:27:49.663143: step: 396/531, loss: 0.0003067970392294228
2023-01-21 13:27:50.796682: step: 400/531, loss: 0.00039272307185456157
2023-01-21 13:27:51.905097: step: 404/531, loss: 0.010199165903031826
2023-01-21 13:27:53.000794: step: 408/531, loss: 2.6702882678364404e-06
2023-01-21 13:27:54.124550: step: 412/531, loss: 0.00025196076603606343
2023-01-21 13:27:55.244078: step: 416/531, loss: 2.431869688734878e-05
2023-01-21 13:27:56.392845: step: 420/531, loss: 0.00035200119600631297
2023-01-21 13:27:57.516150: step: 424/531, loss: 0.050284769386053085
2023-01-21 13:27:58.673625: step: 428/531, loss: 1.0681153071345761e-05
2023-01-21 13:27:59.791245: step: 432/531, loss: 0.0037250518798828125
2023-01-21 13:28:00.904706: step: 436/531, loss: 0.006777572445571423
2023-01-21 13:28:02.025865: step: 440/531, loss: 0.00025234222994185984
2023-01-21 13:28:03.162868: step: 444/531, loss: 0.0021465301979333162
2023-01-21 13:28:04.276373: step: 448/531, loss: 0.00035257337731309235
2023-01-21 13:28:05.392127: step: 452/531, loss: 0.013058042153716087
2023-01-21 13:28:06.517204: step: 456/531, loss: 0.002982520963996649
2023-01-21 13:28:07.643440: step: 460/531, loss: -6.675719532722724e-07
2023-01-21 13:28:08.769429: step: 464/531, loss: 7.553100294899195e-05
2023-01-21 13:28:09.907845: step: 468/531, loss: 2.384185791015625e-05
2023-01-21 13:28:11.044111: step: 472/531, loss: 0.00028066636878065765
2023-01-21 13:28:12.216843: step: 476/531, loss: 0.00016356707783415914
2023-01-21 13:28:13.338750: step: 480/531, loss: 0.0002578735293354839
2023-01-21 13:28:14.499825: step: 484/531, loss: 0.004223346244543791
2023-01-21 13:28:15.607522: step: 488/531, loss: 0.0002828121359925717
2023-01-21 13:28:16.782747: step: 492/531, loss: 0.006344795227050781
2023-01-21 13:28:17.912566: step: 496/531, loss: 0.0006813049549236894
2023-01-21 13:28:19.044712: step: 500/531, loss: 0.00041036607581190765
2023-01-21 13:28:20.173950: step: 504/531, loss: 0.017905807122588158
2023-01-21 13:28:21.288846: step: 508/531, loss: -7.3909759521484375e-06
2023-01-21 13:28:22.413138: step: 512/531, loss: 8.19206252344884e-05
2023-01-21 13:28:23.540091: step: 516/531, loss: 0.026958562433719635
2023-01-21 13:28:24.670822: step: 520/531, loss: 0.00355281843803823
2023-01-21 13:28:25.851276: step: 524/531, loss: 6.67572021484375e-05
2023-01-21 13:28:26.979491: step: 528/531, loss: 0.0011706352233886719
2023-01-21 13:28:28.103105: step: 532/531, loss: 0.0007376670837402344
2023-01-21 13:28:29.242854: step: 536/531, loss: 0.12850303947925568
2023-01-21 13:28:30.358451: step: 540/531, loss: 5.626679012493696e-06
2023-01-21 13:28:31.492614: step: 544/531, loss: 0.0002131462242687121
2023-01-21 13:28:32.613250: step: 548/531, loss: 0.0006744861602783203
2023-01-21 13:28:33.741220: step: 552/531, loss: 0.1536209136247635
2023-01-21 13:28:34.854492: step: 556/531, loss: 7.22885160939768e-05
2023-01-21 13:28:35.986346: step: 560/531, loss: 0.02694263495504856
2023-01-21 13:28:37.118613: step: 564/531, loss: 0.04169035330414772
2023-01-21 13:28:38.262637: step: 568/531, loss: 0.00014758111501578242
2023-01-21 13:28:39.359064: step: 572/531, loss: 0.016062546521425247
2023-01-21 13:28:40.503428: step: 576/531, loss: 2.1457672119140625e-05
2023-01-21 13:28:41.628504: step: 580/531, loss: 0.0025464058853685856
2023-01-21 13:28:42.778118: step: 584/531, loss: 0.07575168460607529
2023-01-21 13:28:43.877250: step: 588/531, loss: 0.00017507077427580953
2023-01-21 13:28:44.990077: step: 592/531, loss: 0.000419425981817767
2023-01-21 13:28:46.106795: step: 596/531, loss: 0.0002468586026225239
2023-01-21 13:28:47.224958: step: 600/531, loss: 2.0694733393611386e-05
2023-01-21 13:28:48.324547: step: 604/531, loss: -4.76837158203125e-07
2023-01-21 13:28:49.427791: step: 608/531, loss: 0.12374935299158096
2023-01-21 13:28:50.537661: step: 612/531, loss: 0.003525242442265153
2023-01-21 13:28:51.644516: step: 616/531, loss: 0.0032036779448390007
2023-01-21 13:28:52.773807: step: 620/531, loss: 9.756088547874242e-05
2023-01-21 13:28:53.907457: step: 624/531, loss: 0.0003226280095987022
2023-01-21 13:28:55.021492: step: 628/531, loss: 0.24145831167697906
2023-01-21 13:28:56.175188: step: 632/531, loss: 0.00030498503474518657
2023-01-21 13:28:57.306971: step: 636/531, loss: 0.004517651163041592
2023-01-21 13:28:58.451608: step: 640/531, loss: 0.006214332301169634
2023-01-21 13:28:59.572358: step: 644/531, loss: 0.1092003807425499
2023-01-21 13:29:00.711722: step: 648/531, loss: 1.3637543816003017e-05
2023-01-21 13:29:01.851285: step: 652/531, loss: 9.34600830078125e-05
2023-01-21 13:29:02.969831: step: 656/531, loss: 0.002922630403190851
2023-01-21 13:29:04.097807: step: 660/531, loss: 0.00040616991464048624
2023-01-21 13:29:05.210301: step: 664/531, loss: 0.025318719446659088
2023-01-21 13:29:06.332348: step: 668/531, loss: 0.00018568038649391383
2023-01-21 13:29:07.455786: step: 672/531, loss: 0.00024623872013762593
2023-01-21 13:29:08.572308: step: 676/531, loss: 0.00030894280644133687
2023-01-21 13:29:09.709238: step: 680/531, loss: 0.002146816346794367
2023-01-21 13:29:10.823110: step: 684/531, loss: 7.114410254871473e-05
2023-01-21 13:29:11.966439: step: 688/531, loss: 0.024901390075683594
2023-01-21 13:29:13.076891: step: 692/531, loss: 0.03612246364355087
2023-01-21 13:29:14.257508: step: 696/531, loss: 3.528594970703125e-05
2023-01-21 13:29:15.370855: step: 700/531, loss: 0.003978920169174671
2023-01-21 13:29:16.493013: step: 704/531, loss: 0.00023670197697356343
2023-01-21 13:29:17.621242: step: 708/531, loss: 2.8705595468636602e-05
2023-01-21 13:29:18.756537: step: 712/531, loss: 0.021152114495635033
2023-01-21 13:29:19.924407: step: 716/531, loss: 0.00015449525380972773
2023-01-21 13:29:21.056555: step: 720/531, loss: 6.389617738022935e-06
2023-01-21 13:29:22.192038: step: 724/531, loss: 0.049501992762088776
2023-01-21 13:29:23.319569: step: 728/531, loss: 0.007954979315400124
2023-01-21 13:29:24.435319: step: 732/531, loss: 0.0003467559872660786
2023-01-21 13:29:25.575345: step: 736/531, loss: 0.0006144046783447266
2023-01-21 13:29:26.687080: step: 740/531, loss: 0.0006265639676712453
2023-01-21 13:29:27.836601: step: 744/531, loss: 0.0001218795805471018
2023-01-21 13:29:28.973592: step: 748/531, loss: 4.997253563487902e-05
2023-01-21 13:29:30.124005: step: 752/531, loss: 2.47955313170678e-06
2023-01-21 13:29:31.224992: step: 756/531, loss: 0.0007749557844363153
2023-01-21 13:29:32.381795: step: 760/531, loss: 0.006569290068000555
2023-01-21 13:29:33.492663: step: 764/531, loss: -2.384185791015625e-07
2023-01-21 13:29:34.634868: step: 768/531, loss: 0.028141213580965996
2023-01-21 13:29:35.763161: step: 772/531, loss: 1.3446808225126006e-05
2023-01-21 13:29:36.923796: step: 776/531, loss: 0.0006719589000567794
2023-01-21 13:29:38.053074: step: 780/531, loss: 5.340576535672881e-06
2023-01-21 13:29:39.171696: step: 784/531, loss: 0.0001621246337890625
2023-01-21 13:29:40.320431: step: 788/531, loss: 0.00015354156494140625
2023-01-21 13:29:41.469467: step: 792/531, loss: 0.053298093378543854
2023-01-21 13:29:42.635886: step: 796/531, loss: 0.01825723610818386
2023-01-21 13:29:43.829129: step: 800/531, loss: 0.003969001583755016
2023-01-21 13:29:44.993872: step: 804/531, loss: 1.71661376953125e-05
2023-01-21 13:29:46.099845: step: 808/531, loss: 5.9890749980695546e-05
2023-01-21 13:29:47.234437: step: 812/531, loss: 0.0004479408380575478
2023-01-21 13:29:48.358097: step: 816/531, loss: 0.00014057158841751516
2023-01-21 13:29:49.546671: step: 820/531, loss: 0.04956188425421715
2023-01-21 13:29:50.667711: step: 824/531, loss: 0.0006712913163937628
2023-01-21 13:29:51.801628: step: 828/531, loss: 0.004286480136215687
2023-01-21 13:29:52.928868: step: 832/531, loss: 2.4890900022001006e-05
2023-01-21 13:29:54.054982: step: 836/531, loss: 0.0023303984198719263
2023-01-21 13:29:55.193788: step: 840/531, loss: 0.0004444122314453125
2023-01-21 13:29:56.319681: step: 844/531, loss: 0.0026824951637536287
2023-01-21 13:29:57.456201: step: 848/531, loss: 0.00048246385995298624
2023-01-21 13:29:58.542547: step: 852/531, loss: 8.459091623080894e-05
2023-01-21 13:29:59.665218: step: 856/531, loss: 0.024524878710508347
2023-01-21 13:30:00.785557: step: 860/531, loss: 0.001531314803287387
2023-01-21 13:30:01.904134: step: 864/531, loss: 0.0035223006270825863
2023-01-21 13:30:03.054912: step: 868/531, loss: 0.0002191543608205393
2023-01-21 13:30:04.160499: step: 872/531, loss: 8.649825758766383e-05
2023-01-21 13:30:05.246719: step: 876/531, loss: 0.00010013581049861386
2023-01-21 13:30:06.347688: step: 880/531, loss: 0.0480194091796875
2023-01-21 13:30:07.448595: step: 884/531, loss: 0.0009717941284179688
2023-01-21 13:30:08.574816: step: 888/531, loss: 0.04506396874785423
2023-01-21 13:30:09.680084: step: 892/531, loss: 1.811981201171875e-05
2023-01-21 13:30:10.794626: step: 896/531, loss: 5.5980683100642636e-05
2023-01-21 13:30:11.933569: step: 900/531, loss: 0.0012220382923260331
2023-01-21 13:30:13.053212: step: 904/531, loss: 2.040863000729587e-05
2023-01-21 13:30:14.229303: step: 908/531, loss: 0.008162117563188076
2023-01-21 13:30:15.328768: step: 912/531, loss: 0.0025362493470311165
2023-01-21 13:30:16.477619: step: 916/531, loss: 0.005315971560776234
2023-01-21 13:30:17.572063: step: 920/531, loss: 5.164146205061115e-05
2023-01-21 13:30:18.724258: step: 924/531, loss: 0.0030103682074695826
2023-01-21 13:30:19.828388: step: 928/531, loss: 0.013195991516113281
2023-01-21 13:30:20.951779: step: 932/531, loss: 3.156661841785535e-05
2023-01-21 13:30:22.091358: step: 936/531, loss: 8.668899681651965e-05
2023-01-21 13:30:23.210007: step: 940/531, loss: 0.0025838850997388363
2023-01-21 13:30:24.308915: step: 944/531, loss: 0.0019424438942223787
2023-01-21 13:30:25.427615: step: 948/531, loss: 4.162192271905951e-05
2023-01-21 13:30:26.553678: step: 952/531, loss: 0.0014663697220385075
2023-01-21 13:30:27.687962: step: 956/531, loss: 0.0003228187561035156
2023-01-21 13:30:28.811513: step: 960/531, loss: 0.0006592751014977694
2023-01-21 13:30:29.921038: step: 964/531, loss: 0.0011466980213299394
2023-01-21 13:30:31.050522: step: 968/531, loss: 0.0023582458961755037
2023-01-21 13:30:32.164734: step: 972/531, loss: 0.0003616333124227822
2023-01-21 13:30:33.284571: step: 976/531, loss: 4.6348573960131034e-05
2023-01-21 13:30:34.370096: step: 980/531, loss: 5.4359438763640355e-06
2023-01-21 13:30:35.506867: step: 984/531, loss: 0.0003030777152162045
2023-01-21 13:30:36.662803: step: 988/531, loss: 0.00016098022751975805
2023-01-21 13:30:37.797538: step: 992/531, loss: 0.002762222196906805
2023-01-21 13:30:38.909087: step: 996/531, loss: 0.0001794815034372732
2023-01-21 13:30:40.058361: step: 1000/531, loss: 1.1539459592313506e-05
2023-01-21 13:30:41.177264: step: 1004/531, loss: 0.0001548767031636089
2023-01-21 13:30:42.312460: step: 1008/531, loss: 0.00472679128870368
2023-01-21 13:30:43.436651: step: 1012/531, loss: 3.528594970703125e-05
2023-01-21 13:30:44.590867: step: 1016/531, loss: 0.004105186555534601
2023-01-21 13:30:45.691699: step: 1020/531, loss: 6.3896181927702855e-06
2023-01-21 13:30:46.809140: step: 1024/531, loss: 0.0002396106719970703
2023-01-21 13:30:47.925660: step: 1028/531, loss: 0.0048239706084132195
2023-01-21 13:30:49.051871: step: 1032/531, loss: 0.0006738663068972528
2023-01-21 13:30:50.217456: step: 1036/531, loss: 0.05202064663171768
2023-01-21 13:30:51.349027: step: 1040/531, loss: 1.0967255548166577e-05
2023-01-21 13:30:52.481722: step: 1044/531, loss: 1.8024444216280244e-05
2023-01-21 13:30:53.595261: step: 1048/531, loss: 0.010198498144745827
2023-01-21 13:30:54.715250: step: 1052/531, loss: 0.0006591796991415322
2023-01-21 13:30:55.877182: step: 1056/531, loss: 6.389617919921875e-05
2023-01-21 13:30:56.999962: step: 1060/531, loss: 0.004205131437629461
2023-01-21 13:30:58.164661: step: 1064/531, loss: 0.0002487182500772178
2023-01-21 13:30:59.286895: step: 1068/531, loss: 0.0003993988211732358
2023-01-21 13:31:00.430622: step: 1072/531, loss: 0.0020080567337572575
2023-01-21 13:31:01.533794: step: 1076/531, loss: 2.7084352041129023e-05
2023-01-21 13:31:02.674113: step: 1080/531, loss: 0.02887124940752983
2023-01-21 13:31:03.787100: step: 1084/531, loss: 0.0010878562461584806
2023-01-21 13:31:04.913484: step: 1088/531, loss: 0.0023478507064282894
2023-01-21 13:31:06.052479: step: 1092/531, loss: 0.0006430625799112022
2023-01-21 13:31:07.197102: step: 1096/531, loss: 0.021694278344511986
2023-01-21 13:31:08.310514: step: 1100/531, loss: 1.9550323486328125e-05
2023-01-21 13:31:09.445961: step: 1104/531, loss: 0.44525790214538574
2023-01-21 13:31:10.557425: step: 1108/531, loss: 0.0010629654861986637
2023-01-21 13:31:11.694350: step: 1112/531, loss: 8.869171324477065e-06
2023-01-21 13:31:12.813896: step: 1116/531, loss: 0.008517743088304996
2023-01-21 13:31:13.987482: step: 1120/531, loss: 0.05313320457935333
2023-01-21 13:31:15.093719: step: 1124/531, loss: 0.0593930222094059
2023-01-21 13:31:16.208529: step: 1128/531, loss: 4.0531158447265625e-05
2023-01-21 13:31:17.303634: step: 1132/531, loss: 5.569458153331652e-05
2023-01-21 13:31:18.420671: step: 1136/531, loss: 0.0003452301025390625
2023-01-21 13:31:19.554830: step: 1140/531, loss: 8.788705599727109e-06
2023-01-21 13:31:20.671504: step: 1144/531, loss: 0.00179290771484375
2023-01-21 13:31:21.816844: step: 1148/531, loss: 0.025395013391971588
2023-01-21 13:31:22.950530: step: 1152/531, loss: 4.96864304295741e-05
2023-01-21 13:31:24.072741: step: 1156/531, loss: 0.0003906250058207661
2023-01-21 13:31:25.210343: step: 1160/531, loss: 0.015845583751797676
2023-01-21 13:31:26.327740: step: 1164/531, loss: 2.86102294921875e-06
2023-01-21 13:31:27.447832: step: 1168/531, loss: 0.00900735892355442
2023-01-21 13:31:28.567199: step: 1172/531, loss: 0.0360538475215435
2023-01-21 13:31:29.682804: step: 1176/531, loss: 0.007651138585060835
2023-01-21 13:31:30.804380: step: 1180/531, loss: 1.7166139514301904e-05
2023-01-21 13:31:31.934219: step: 1184/531, loss: 0.019014835357666016
2023-01-21 13:31:33.035450: step: 1188/531, loss: 2.288818359375e-05
2023-01-21 13:31:34.178471: step: 1192/531, loss: 0.00558395404368639
2023-01-21 13:31:35.305107: step: 1196/531, loss: 2.6988982426701114e-05
2023-01-21 13:31:36.406801: step: 1200/531, loss: 0.19798269867897034
2023-01-21 13:31:37.534800: step: 1204/531, loss: 0.005815219599753618
2023-01-21 13:31:38.688458: step: 1208/531, loss: 0.0716014876961708
2023-01-21 13:31:39.799777: step: 1212/531, loss: 0.050624847412109375
2023-01-21 13:31:40.930150: step: 1216/531, loss: 0.027128983289003372
2023-01-21 13:31:42.034393: step: 1220/531, loss: 0.00086297991219908
2023-01-21 13:31:43.189290: step: 1224/531, loss: 1.831054760259576e-05
2023-01-21 13:31:44.328959: step: 1228/531, loss: 0.0074364664033055305
2023-01-21 13:31:45.514184: step: 1232/531, loss: 0.234603151679039
2023-01-21 13:31:46.637445: step: 1236/531, loss: 2.5415420168428682e-05
2023-01-21 13:31:47.725626: step: 1240/531, loss: 4.6443943574558944e-05
2023-01-21 13:31:48.854230: step: 1244/531, loss: 0.01067581120878458
2023-01-21 13:31:49.985328: step: 1248/531, loss: 0.05488729476928711
2023-01-21 13:31:51.091839: step: 1252/531, loss: 0.00031147003755904734
2023-01-21 13:31:52.232910: step: 1256/531, loss: 0.0013028144603595138
2023-01-21 13:31:53.355674: step: 1260/531, loss: 8.096695091808215e-05
2023-01-21 13:31:54.538746: step: 1264/531, loss: 0.0037929534446448088
2023-01-21 13:31:55.642572: step: 1268/531, loss: 0.009043884463608265
2023-01-21 13:31:56.786265: step: 1272/531, loss: 0.00036554335383698344
2023-01-21 13:31:57.882333: step: 1276/531, loss: 0.00019073487783316523
2023-01-21 13:31:59.010994: step: 1280/531, loss: 0.004482317250221968
2023-01-21 13:32:00.100939: step: 1284/531, loss: 0.0016658783424645662
2023-01-21 13:32:01.253799: step: 1288/531, loss: 7.06672653905116e-05
2023-01-21 13:32:02.396379: step: 1292/531, loss: 0.00017938614473678172
2023-01-21 13:32:03.511662: step: 1296/531, loss: 0.001176547957584262
2023-01-21 13:32:04.628671: step: 1300/531, loss: 0.01898946985602379
2023-01-21 13:32:05.757844: step: 1304/531, loss: 0.008185530081391335
2023-01-21 13:32:06.874696: step: 1308/531, loss: 0.0017718315357342362
2023-01-21 13:32:08.002339: step: 1312/531, loss: 0.005686188116669655
2023-01-21 13:32:09.103068: step: 1316/531, loss: 0.2636191248893738
2023-01-21 13:32:10.226373: step: 1320/531, loss: 0.006782532203942537
2023-01-21 13:32:11.335645: step: 1324/531, loss: 0.017702199518680573
2023-01-21 13:32:12.469698: step: 1328/531, loss: 0.049163054674863815
2023-01-21 13:32:13.604746: step: 1332/531, loss: 5.984306335449219e-05
2023-01-21 13:32:14.707943: step: 1336/531, loss: 0.0001834869326557964
2023-01-21 13:32:15.830034: step: 1340/531, loss: 0.0005691528785973787
2023-01-21 13:32:16.951991: step: 1344/531, loss: 0.0005155563703738153
2023-01-21 13:32:18.087065: step: 1348/531, loss: 0.4969814419746399
2023-01-21 13:32:19.230082: step: 1352/531, loss: 0.0010271072387695312
2023-01-21 13:32:20.370879: step: 1356/531, loss: 0.0006879806751385331
2023-01-21 13:32:21.497587: step: 1360/531, loss: 1.0776519957289565e-05
2023-01-21 13:32:22.621760: step: 1364/531, loss: 0.005980110261589289
2023-01-21 13:32:23.726482: step: 1368/531, loss: 0.0027632713317871094
2023-01-21 13:32:24.843223: step: 1372/531, loss: 0.0001032829241012223
2023-01-21 13:32:26.007133: step: 1376/531, loss: 0.00030269622220657766
2023-01-21 13:32:27.147944: step: 1380/531, loss: 0.010082913562655449
2023-01-21 13:32:28.286214: step: 1384/531, loss: 2.3508073354605585e-05
2023-01-21 13:32:29.415423: step: 1388/531, loss: 0.0002986908075399697
2023-01-21 13:32:30.535643: step: 1392/531, loss: 6.408691115211695e-05
2023-01-21 13:32:31.650233: step: 1396/531, loss: 0.006342983338981867
2023-01-21 13:32:32.772234: step: 1400/531, loss: 0.0005537032848224044
2023-01-21 13:32:33.870034: step: 1404/531, loss: 1.7452239262638614e-05
2023-01-21 13:32:35.052196: step: 1408/531, loss: 0.0005129814380779862
2023-01-21 13:32:36.180412: step: 1412/531, loss: 0.016759777441620827
2023-01-21 13:32:37.288983: step: 1416/531, loss: 0.022570062428712845
2023-01-21 13:32:38.436620: step: 1420/531, loss: 0.0007602691766805947
2023-01-21 13:32:39.577711: step: 1424/531, loss: 0.0034173966851085424
2023-01-21 13:32:40.699293: step: 1428/531, loss: 0.0012047768104821444
2023-01-21 13:32:41.812764: step: 1432/531, loss: 0.0007106781122274697
2023-01-21 13:32:42.914704: step: 1436/531, loss: 0.00017709731764625758
2023-01-21 13:32:44.080021: step: 1440/531, loss: 0.05722656473517418
2023-01-21 13:32:45.184465: step: 1444/531, loss: 0.000150585183291696
2023-01-21 13:32:46.313441: step: 1448/531, loss: 0.002532958984375
2023-01-21 13:32:47.422140: step: 1452/531, loss: 0.0002384185791015625
2023-01-21 13:32:48.529052: step: 1456/531, loss: 0.12424660474061966
2023-01-21 13:32:49.690326: step: 1460/531, loss: 0.0006864547613076866
2023-01-21 13:32:50.839123: step: 1464/531, loss: 0.06259050220251083
2023-01-21 13:32:51.983862: step: 1468/531, loss: 0.02921314351260662
2023-01-21 13:32:53.085461: step: 1472/531, loss: 0.05714721605181694
2023-01-21 13:32:54.210226: step: 1476/531, loss: 0.0008366584661416709
2023-01-21 13:32:55.320538: step: 1480/531, loss: 0.001455593155696988
2023-01-21 13:32:56.476799: step: 1484/531, loss: 0.018951939418911934
2023-01-21 13:32:57.596044: step: 1488/531, loss: 0.0001108169526560232
2023-01-21 13:32:58.702899: step: 1492/531, loss: 0.003665161319077015
2023-01-21 13:32:59.805009: step: 1496/531, loss: 0.0005284309154376388
2023-01-21 13:33:00.933564: step: 1500/531, loss: 0.001697969390079379
2023-01-21 13:33:02.054952: step: 1504/531, loss: 7.572174217784777e-05
2023-01-21 13:33:03.174958: step: 1508/531, loss: 0.003948211669921875
2023-01-21 13:33:04.306997: step: 1512/531, loss: 0.00846786517649889
2023-01-21 13:33:05.425641: step: 1516/531, loss: 0.0001069068894139491
2023-01-21 13:33:06.509049: step: 1520/531, loss: 1.0967255548166577e-06
2023-01-21 13:33:07.651545: step: 1524/531, loss: 0.019928455352783203
2023-01-21 13:33:08.775057: step: 1528/531, loss: 0.00030608175438828766
2023-01-21 13:33:09.904583: step: 1532/531, loss: 0.0037707327865064144
2023-01-21 13:33:11.059777: step: 1536/531, loss: 0.0005949020269326866
2023-01-21 13:33:12.187677: step: 1540/531, loss: 0.0007134437328204513
2023-01-21 13:33:13.358288: step: 1544/531, loss: 0.005471706390380859
2023-01-21 13:33:14.456980: step: 1548/531, loss: 0.00018711091252043843
2023-01-21 13:33:15.586974: step: 1552/531, loss: 0.005074119661003351
2023-01-21 13:33:16.710486: step: 1556/531, loss: 0.00048246385995298624
2023-01-21 13:33:17.833955: step: 1560/531, loss: 0.0010433674324303865
2023-01-21 13:33:18.950438: step: 1564/531, loss: 8.430481102550402e-05
2023-01-21 13:33:20.067638: step: 1568/531, loss: 0.0010838985908776522
2023-01-21 13:33:21.175425: step: 1572/531, loss: 0.0006448745843954384
2023-01-21 13:33:22.284917: step: 1576/531, loss: 0.017004871740937233
2023-01-21 13:33:23.449855: step: 1580/531, loss: 0.024933815002441406
2023-01-21 13:33:24.570445: step: 1584/531, loss: 0.01393432728946209
2023-01-21 13:33:25.710518: step: 1588/531, loss: 0.0001682281435932964
2023-01-21 13:33:26.840429: step: 1592/531, loss: 0.00042490960913710296
2023-01-21 13:33:27.990971: step: 1596/531, loss: 0.022207261994481087
2023-01-21 13:33:29.121044: step: 1600/531, loss: 0.050908852368593216
2023-01-21 13:33:30.239403: step: 1604/531, loss: 0.05037698522210121
2023-01-21 13:33:31.338488: step: 1608/531, loss: 0.00016498567129019648
2023-01-21 13:33:32.481530: step: 1612/531, loss: 0.04270875081419945
2023-01-21 13:33:33.595798: step: 1616/531, loss: 0.023236369714140892
2023-01-21 13:33:34.713305: step: 1620/531, loss: 0.00011291504051769152
2023-01-21 13:33:35.820089: step: 1624/531, loss: 0.00031476019648835063
2023-01-21 13:33:36.944161: step: 1628/531, loss: 7.781982276355848e-05
2023-01-21 13:33:38.092631: step: 1632/531, loss: 0.0023525238502770662
2023-01-21 13:33:39.236441: step: 1636/531, loss: 0.011433601379394531
2023-01-21 13:33:40.368677: step: 1640/531, loss: 0.004158496856689453
2023-01-21 13:33:41.484497: step: 1644/531, loss: 0.012745380401611328
2023-01-21 13:33:42.631802: step: 1648/531, loss: 0.015035247430205345
2023-01-21 13:33:43.778839: step: 1652/531, loss: 0.0007318020216189325
2023-01-21 13:33:44.891125: step: 1656/531, loss: 0.05518350750207901
2023-01-21 13:33:46.001645: step: 1660/531, loss: 0.0008961677667684853
2023-01-21 13:33:47.123315: step: 1664/531, loss: 0.0011484622955322266
2023-01-21 13:33:48.260922: step: 1668/531, loss: 0.004088640213012695
2023-01-21 13:33:49.396794: step: 1672/531, loss: 0.4882128834724426
2023-01-21 13:33:50.515077: step: 1676/531, loss: 0.007285499945282936
2023-01-21 13:33:51.633102: step: 1680/531, loss: 0.015175247564911842
2023-01-21 13:33:52.746282: step: 1684/531, loss: 0.006510543636977673
2023-01-21 13:33:53.846652: step: 1688/531, loss: 5.154609607416205e-05
2023-01-21 13:33:54.941661: step: 1692/531, loss: 0.007799339480698109
2023-01-21 13:33:56.044642: step: 1696/531, loss: 0.003286647843196988
2023-01-21 13:33:57.162368: step: 1700/531, loss: 0.014508056454360485
2023-01-21 13:33:58.281443: step: 1704/531, loss: 0.013638973236083984
2023-01-21 13:33:59.395002: step: 1708/531, loss: 0.0020320890471339226
2023-01-21 13:34:00.512647: step: 1712/531, loss: 0.011674500070512295
2023-01-21 13:34:01.620410: step: 1716/531, loss: 0.007084751036018133
2023-01-21 13:34:02.769438: step: 1720/531, loss: 0.00011281967454124242
2023-01-21 13:34:03.913050: step: 1724/531, loss: 0.016599273309111595
2023-01-21 13:34:05.030198: step: 1728/531, loss: 0.015539360232651234
2023-01-21 13:34:06.141744: step: 1732/531, loss: 0.006419277284294367
2023-01-21 13:34:07.275855: step: 1736/531, loss: 0.0050182342529296875
2023-01-21 13:34:08.403595: step: 1740/531, loss: 0.00027952194795943797
2023-01-21 13:34:09.521913: step: 1744/531, loss: 5.779266211902723e-05
2023-01-21 13:34:10.638956: step: 1748/531, loss: 1.4638900211139116e-05
2023-01-21 13:34:11.771878: step: 1752/531, loss: 0.06650781631469727
2023-01-21 13:34:12.918608: step: 1756/531, loss: 0.004096793942153454
2023-01-21 13:34:14.056311: step: 1760/531, loss: 0.0002225875941803679
2023-01-21 13:34:15.187878: step: 1764/531, loss: 0.006667566020041704
2023-01-21 13:34:16.321324: step: 1768/531, loss: 0.058296963572502136
2023-01-21 13:34:17.440511: step: 1772/531, loss: 0.0013595580821856856
2023-01-21 13:34:18.558629: step: 1776/531, loss: 2.384185791015625e-06
2023-01-21 13:34:19.697175: step: 1780/531, loss: 0.01043548621237278
2023-01-21 13:34:20.785119: step: 1784/531, loss: 0.0002168655482819304
2023-01-21 13:34:21.950642: step: 1788/531, loss: 7.200240816018777e-06
2023-01-21 13:34:23.093584: step: 1792/531, loss: 0.006196784786880016
2023-01-21 13:34:24.220403: step: 1796/531, loss: 0.007871055975556374
2023-01-21 13:34:25.371868: step: 1800/531, loss: 0.0109748849645257
2023-01-21 13:34:26.510376: step: 1804/531, loss: 0.0007970333681441844
2023-01-21 13:34:27.603367: step: 1808/531, loss: 5.073547436040826e-05
2023-01-21 13:34:28.722755: step: 1812/531, loss: 0.042394354939460754
2023-01-21 13:34:29.834745: step: 1816/531, loss: 0.026506900787353516
2023-01-21 13:34:30.986031: step: 1820/531, loss: 0.0004114151233807206
2023-01-21 13:34:32.109879: step: 1824/531, loss: 0.12249825149774551
2023-01-21 13:34:33.218948: step: 1828/531, loss: 0.06791038066148758
2023-01-21 13:34:34.341907: step: 1832/531, loss: 7.286071922862902e-05
2023-01-21 13:34:35.453752: step: 1836/531, loss: 0.005318641662597656
2023-01-21 13:34:36.553574: step: 1840/531, loss: 0.0014286041259765625
2023-01-21 13:34:37.671720: step: 1844/531, loss: 0.03651876747608185
2023-01-21 13:34:38.811476: step: 1848/531, loss: 0.008816909976303577
2023-01-21 13:34:39.922888: step: 1852/531, loss: 0.004405403044074774
2023-01-21 13:34:41.058103: step: 1856/531, loss: 0.0003368377801962197
2023-01-21 13:34:42.194599: step: 1860/531, loss: 0.0007091521983966231
2023-01-21 13:34:43.313543: step: 1864/531, loss: 0.0005462646950036287
2023-01-21 13:34:44.452952: step: 1868/531, loss: 0.003952980041503906
2023-01-21 13:34:45.602054: step: 1872/531, loss: 0.008650732226669788
2023-01-21 13:34:46.751863: step: 1876/531, loss: 0.00034160615177825093
2023-01-21 13:34:47.872269: step: 1880/531, loss: 0.000929546426050365
2023-01-21 13:34:49.015461: step: 1884/531, loss: 0.019374657422304153
2023-01-21 13:34:50.130710: step: 1888/531, loss: 0.00424990663304925
2023-01-21 13:34:51.236463: step: 1892/531, loss: 0.0002956390380859375
2023-01-21 13:34:52.353641: step: 1896/531, loss: 0.0001506805419921875
2023-01-21 13:34:53.481416: step: 1900/531, loss: 3.24249267578125e-05
2023-01-21 13:34:54.628671: step: 1904/531, loss: 0.0462704636156559
2023-01-21 13:34:55.768073: step: 1908/531, loss: 0.17189064621925354
2023-01-21 13:34:56.896781: step: 1912/531, loss: 0.00206413259729743
2023-01-21 13:34:58.043038: step: 1916/531, loss: 0.00014228820509742945
2023-01-21 13:34:59.193198: step: 1920/531, loss: 5.874633643543348e-05
2023-01-21 13:35:00.325246: step: 1924/531, loss: 0.006545448210090399
2023-01-21 13:35:01.455543: step: 1928/531, loss: 0.0008230209350585938
2023-01-21 13:35:02.554250: step: 1932/531, loss: 0.0035373687278479338
2023-01-21 13:35:03.668528: step: 1936/531, loss: 1.4019013178767636e-05
2023-01-21 13:35:04.801331: step: 1940/531, loss: 2.8419495720299892e-05
2023-01-21 13:35:05.927222: step: 1944/531, loss: 0.00018520356388762593
2023-01-21 13:35:07.049034: step: 1948/531, loss: 6.68525681248866e-05
2023-01-21 13:35:08.178484: step: 1952/531, loss: -1.144409225162235e-06
2023-01-21 13:35:09.316008: step: 1956/531, loss: 1.5258788153005298e-06
2023-01-21 13:35:10.462731: step: 1960/531, loss: 0.0025363920722156763
2023-01-21 13:35:11.595275: step: 1964/531, loss: 0.00012540817260742188
2023-01-21 13:35:12.738908: step: 1968/531, loss: -3.337860107421875e-06
2023-01-21 13:35:13.877639: step: 1972/531, loss: 0.1348293274641037
2023-01-21 13:35:14.990965: step: 1976/531, loss: 0.1118554174900055
2023-01-21 13:35:16.128145: step: 1980/531, loss: 0.008698750287294388
2023-01-21 13:35:17.258824: step: 1984/531, loss: 0.0007928848499432206
2023-01-21 13:35:18.391398: step: 1988/531, loss: 0.0004413604619912803
2023-01-21 13:35:19.512310: step: 1992/531, loss: 0.01868290826678276
2023-01-21 13:35:20.626084: step: 1996/531, loss: -7.62939453125e-06
2023-01-21 13:35:21.782443: step: 2000/531, loss: 1.3542176020564511e-05
2023-01-21 13:35:22.909776: step: 2004/531, loss: 5.836486889165826e-05
2023-01-21 13:35:24.011900: step: 2008/531, loss: 0.0001342296600341797
2023-01-21 13:35:25.165141: step: 2012/531, loss: 0.009788322262465954
2023-01-21 13:35:26.276428: step: 2016/531, loss: 0.015025138854980469
2023-01-21 13:35:27.405100: step: 2020/531, loss: 0.0004955291515216231
2023-01-21 13:35:28.560147: step: 2024/531, loss: 0.0027963160537183285
2023-01-21 13:35:29.695256: step: 2028/531, loss: 0.00017876624769996852
2023-01-21 13:35:30.841268: step: 2032/531, loss: 0.0012434959644451737
2023-01-21 13:35:32.001590: step: 2036/531, loss: 0.00025424957857467234
2023-01-21 13:35:33.085918: step: 2040/531, loss: 0.0023969649337232113
2023-01-21 13:35:34.206812: step: 2044/531, loss: 8.56399565236643e-05
2023-01-21 13:35:35.313924: step: 2048/531, loss: 0.0001846313534770161
2023-01-21 13:35:36.415584: step: 2052/531, loss: 0.011302662082016468
2023-01-21 13:35:37.517090: step: 2056/531, loss: 1.4781951904296875e-05
2023-01-21 13:35:38.654316: step: 2060/531, loss: 0.00016460419283248484
2023-01-21 13:35:39.789730: step: 2064/531, loss: 0.004124450962990522
2023-01-21 13:35:40.917797: step: 2068/531, loss: 0.02116584964096546
2023-01-21 13:35:42.044073: step: 2072/531, loss: 0.026836587116122246
2023-01-21 13:35:43.162355: step: 2076/531, loss: 2.8324127924861386e-05
2023-01-21 13:35:44.316208: step: 2080/531, loss: 0.02808237075805664
2023-01-21 13:35:45.452380: step: 2084/531, loss: 0.003188800998032093
2023-01-21 13:35:46.603618: step: 2088/531, loss: 0.0003784179862122983
2023-01-21 13:35:47.719565: step: 2092/531, loss: 0.0013854980934411287
2023-01-21 13:35:48.863756: step: 2096/531, loss: 0.0006001472938805819
2023-01-21 13:35:49.996262: step: 2100/531, loss: 0.015095424838364124
2023-01-21 13:35:51.136305: step: 2104/531, loss: 0.0004020690976176411
2023-01-21 13:35:52.259568: step: 2108/531, loss: 3.156662205583416e-05
2023-01-21 13:35:53.369966: step: 2112/531, loss: 7.801055471645668e-05
2023-01-21 13:35:54.498782: step: 2116/531, loss: 0.04162111133337021
2023-01-21 13:35:55.605584: step: 2120/531, loss: 0.028938865289092064
2023-01-21 13:35:56.720050: step: 2124/531, loss: 5.4359438763640355e-06
==================================================
Loss: 0.014
--------------------
Dev: {'event': {'p': 0.5852674066599395, 'r': 0.7723035952063915, 'f1': 0.6659012629161883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6288561936402468, 'r': 0.7901013714967203, 'f1': 0.7003171247357294}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.5697674418604651, 'r': 0.9074074074074074, 'f1': 0.7}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.5614035087719298, 'r': 0.5079365079365079, 'f1': 0.5333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.40816326530612246, 'r': 0.5555555555555556, 'f1': 0.47058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 29
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-21 13:36:37.251984: step: 4/531, loss: 0.0025509835686534643
2023-01-21 13:36:38.361955: step: 8/531, loss: 0.00034246445284225047
2023-01-21 13:36:39.463142: step: 12/531, loss: 0.11987762153148651
2023-01-21 13:36:40.604197: step: 16/531, loss: 8.96453821042087e-06
2023-01-21 13:36:41.758906: step: 20/531, loss: 0.0030508041381835938
2023-01-21 13:36:42.877054: step: 24/531, loss: 0.0001088142380467616
2023-01-21 13:36:43.981141: step: 28/531, loss: 0.0001069068894139491
2023-01-21 13:36:45.096372: step: 32/531, loss: 0.020453929901123047
2023-01-21 13:36:46.251514: step: 36/531, loss: 0.00250587472692132
2023-01-21 13:36:47.363635: step: 40/531, loss: 0.00016345977201126516
2023-01-21 13:36:48.479314: step: 44/531, loss: 0.0005069732433184981
2023-01-21 13:36:49.602255: step: 48/531, loss: 5.2261355449445546e-05
2023-01-21 13:36:50.703691: step: 52/531, loss: 0.012812805362045765
2023-01-21 13:36:51.861335: step: 56/531, loss: 0.0005630493978969753
2023-01-21 13:36:52.976352: step: 60/531, loss: 0.005355262663215399
2023-01-21 13:36:54.083986: step: 64/531, loss: 4.8208235966740176e-05
2023-01-21 13:36:55.216214: step: 68/531, loss: 0.004857540130615234
2023-01-21 13:36:56.332182: step: 72/531, loss: 0.024040794000029564
2023-01-21 13:36:57.435756: step: 76/531, loss: 0.001294040703214705
2023-01-21 13:36:58.587265: step: 80/531, loss: 1.5163423086050898e-05
2023-01-21 13:36:59.728846: step: 84/531, loss: 0.0001426696835551411
2023-01-21 13:37:00.848382: step: 88/531, loss: 0.01425857562571764
2023-01-21 13:37:01.960943: step: 92/531, loss: 0.0014289856189861894
2023-01-21 13:37:03.088378: step: 96/531, loss: 0.028946973383426666
2023-01-21 13:37:04.217094: step: 100/531, loss: 0.0007213592762127519
2023-01-21 13:37:05.362259: step: 104/531, loss: 0.0002178192080464214
2023-01-21 13:37:06.468873: step: 108/531, loss: 3.5953522456111386e-05
2023-01-21 13:37:07.577129: step: 112/531, loss: 0.06125025823712349
2023-01-21 13:37:08.696161: step: 116/531, loss: 0.005682135000824928
2023-01-21 13:37:09.829971: step: 120/531, loss: 0.00015163421630859375
2023-01-21 13:37:10.943580: step: 124/531, loss: 0.00011920928955078125
2023-01-21 13:37:12.103338: step: 128/531, loss: 2.4223329091910273e-05
2023-01-21 13:37:13.236794: step: 132/531, loss: 0.00037784577580168843
2023-01-21 13:37:14.386081: step: 136/531, loss: 0.0016256810631603003
2023-01-21 13:37:15.514843: step: 140/531, loss: 0.0010035515297204256
2023-01-21 13:37:16.636806: step: 144/531, loss: 0.0015749931335449219
2023-01-21 13:37:17.753931: step: 148/531, loss: 5.4836273193359375e-05
2023-01-21 13:37:18.899532: step: 152/531, loss: 0.0009161948692053556
2023-01-21 13:37:20.011494: step: 156/531, loss: 8.39233416627394e-06
2023-01-21 13:37:21.172400: step: 160/531, loss: 0.06011023372411728
2023-01-21 13:37:22.286747: step: 164/531, loss: 0.0018825532170012593
2023-01-21 13:37:23.418680: step: 168/531, loss: 0.46514949202537537
2023-01-21 13:37:24.569849: step: 172/531, loss: 0.0125891687348485
2023-01-21 13:37:25.717623: step: 176/531, loss: 0.0005283832433633506
2023-01-21 13:37:26.839281: step: 180/531, loss: 0.00036940575228072703
2023-01-21 13:37:27.936752: step: 184/531, loss: 0.0002588748757261783
2023-01-21 13:37:29.052342: step: 188/531, loss: 0.0009900570148602128
2023-01-21 13:37:30.187877: step: 192/531, loss: 0.0072325230576097965
2023-01-21 13:37:31.342482: step: 196/531, loss: 0.9481627345085144
2023-01-21 13:37:32.497128: step: 200/531, loss: 0.00028543471125885844
2023-01-21 13:37:33.616234: step: 204/531, loss: 0.03043527714908123
2023-01-21 13:37:34.738033: step: 208/531, loss: 0.02886362187564373
2023-01-21 13:37:35.880871: step: 212/531, loss: 0.007921266369521618
2023-01-21 13:37:36.998606: step: 216/531, loss: 0.002102756407111883
2023-01-21 13:37:38.134500: step: 220/531, loss: 7.127523713279516e-05
2023-01-21 13:37:39.256251: step: 224/531, loss: 0.007027149200439453
2023-01-21 13:37:40.369761: step: 228/531, loss: 0.00030188559321686625
2023-01-21 13:37:41.485611: step: 232/531, loss: 0.002290153643116355
2023-01-21 13:37:42.652105: step: 236/531, loss: 0.00013484954251907766
2023-01-21 13:37:43.759936: step: 240/531, loss: 0.0022546767722815275
2023-01-21 13:37:44.885882: step: 244/531, loss: 0.0007330894586630166
2023-01-21 13:37:46.013967: step: 248/531, loss: 0.00046391485375352204
2023-01-21 13:37:47.177502: step: 252/531, loss: 0.06503858417272568
2023-01-21 13:37:48.301913: step: 256/531, loss: 0.008624649606645107
2023-01-21 13:37:49.404123: step: 260/531, loss: 5.7220458984375e-06
2023-01-21 13:37:50.513155: step: 264/531, loss: 0.031436823308467865
2023-01-21 13:37:51.608182: step: 268/531, loss: 0.025232218205928802
2023-01-21 13:37:52.754301: step: 272/531, loss: 0.08242025226354599
2023-01-21 13:37:53.873326: step: 276/531, loss: 0.0024717331398278475
2023-01-21 13:37:54.996042: step: 280/531, loss: 0.010301684960722923
2023-01-21 13:37:56.138109: step: 284/531, loss: 2.4318694613612024e-06
2023-01-21 13:37:57.285877: step: 288/531, loss: 0.001957368804141879
2023-01-21 13:37:58.406742: step: 292/531, loss: 0.0001146316499216482
2023-01-21 13:37:59.535641: step: 296/531, loss: 0.008628464303910732
2023-01-21 13:38:00.658805: step: 300/531, loss: 0.0004521369992289692
2023-01-21 13:38:01.790939: step: 304/531, loss: 0.002352142473682761
2023-01-21 13:38:02.888188: step: 308/531, loss: 1.2874603271484375e-05
2023-01-21 13:38:04.000361: step: 312/531, loss: 2.57492069977161e-06
2023-01-21 13:38:05.124098: step: 316/531, loss: 1.1444091114753974e-06
2023-01-21 13:38:06.225472: step: 320/531, loss: 0.00024433137150481343
2023-01-21 13:38:07.370467: step: 324/531, loss: 0.0005514145013876259
2023-01-21 13:38:08.480047: step: 328/531, loss: 0.0002881050168070942
2023-01-21 13:38:09.589371: step: 332/531, loss: 0.0010843276977539062
2023-01-21 13:38:10.710888: step: 336/531, loss: 0.005403232295066118
2023-01-21 13:38:11.871215: step: 340/531, loss: 0.00910263042896986
2023-01-21 13:38:12.976893: step: 344/531, loss: -3.43322744811303e-06
2023-01-21 13:38:14.075711: step: 348/531, loss: -3.43322744811303e-06
2023-01-21 13:38:15.182209: step: 352/531, loss: 3.185272362316027e-05
2023-01-21 13:38:16.309070: step: 356/531, loss: 1.6307831174344756e-05
2023-01-21 13:38:17.431931: step: 360/531, loss: 0.0008256912115029991
2023-01-21 13:38:18.546675: step: 364/531, loss: 0.0001316070556640625
2023-01-21 13:38:19.681339: step: 368/531, loss: 0.00012140274338889867
2023-01-21 13:38:20.829786: step: 372/531, loss: 8.96453821042087e-06
2023-01-21 13:38:21.936944: step: 376/531, loss: 0.00683670025318861
2023-01-21 13:38:23.019243: step: 380/531, loss: 3.24249276673072e-06
2023-01-21 13:38:24.131605: step: 384/531, loss: 6.408691842807457e-05
2023-01-21 13:38:25.254855: step: 388/531, loss: 0.047516822814941406
2023-01-21 13:38:26.392164: step: 392/531, loss: 0.038408663123846054
2023-01-21 13:38:27.518770: step: 396/531, loss: -2.2411345526052173e-06
2023-01-21 13:38:28.654768: step: 400/531, loss: 0.0006032944074831903
2023-01-21 13:38:29.775918: step: 404/531, loss: 5.464554124046117e-05
2023-01-21 13:38:30.915802: step: 408/531, loss: 0.0002157211274607107
2023-01-21 13:38:32.033816: step: 412/531, loss: 0.030631449073553085
2023-01-21 13:38:33.176226: step: 416/531, loss: 4.138946678722277e-05
2023-01-21 13:38:34.344831: step: 420/531, loss: 0.04975862428545952
2023-01-21 13:38:35.485114: step: 424/531, loss: 0.00068836216814816
2023-01-21 13:38:36.634139: step: 428/531, loss: 0.02055676095187664
2023-01-21 13:38:37.802761: step: 432/531, loss: 0.00014319419278763235
2023-01-21 13:38:38.952035: step: 436/531, loss: 0.00010337829735362902
2023-01-21 13:38:40.062835: step: 440/531, loss: 4.6062468754826114e-05
2023-01-21 13:38:41.187113: step: 444/531, loss: 9.441375368623994e-06
2023-01-21 13:38:42.318256: step: 448/531, loss: 0.947634220123291
2023-01-21 13:38:43.422986: step: 452/531, loss: 0.0023738860618323088
2023-01-21 13:38:44.529493: step: 456/531, loss: 0.0002551078796386719
2023-01-21 13:38:45.657050: step: 460/531, loss: 0.008489036932587624
2023-01-21 13:38:46.788385: step: 464/531, loss: 0.0013393402332440019
2023-01-21 13:38:47.906120: step: 468/531, loss: 0.011681747622787952
2023-01-21 13:38:49.035425: step: 472/531, loss: 0.005531406961381435
2023-01-21 13:38:50.167543: step: 476/531, loss: 0.051253318786621094
2023-01-21 13:38:51.297934: step: 480/531, loss: 3.6716461181640625e-05
2023-01-21 13:38:52.428247: step: 484/531, loss: 0.0033349990844726562
2023-01-21 13:38:53.555320: step: 488/531, loss: 0.05388984829187393
2023-01-21 13:38:54.690372: step: 492/531, loss: 0.002191257430240512
2023-01-21 13:38:55.840474: step: 496/531, loss: 1.220703143189894e-05
2023-01-21 13:38:56.980889: step: 500/531, loss: 0.00561566324904561
2023-01-21 13:38:58.150806: step: 504/531, loss: 0.01273345947265625
2023-01-21 13:38:59.329716: step: 508/531, loss: 0.054681967943906784
2023-01-21 13:39:00.454938: step: 512/531, loss: 2.841949390131049e-05
2023-01-21 13:39:01.583876: step: 516/531, loss: 0.0009076118585653603
2023-01-21 13:39:02.720296: step: 520/531, loss: 0.0005132675287313759
2023-01-21 13:39:03.846565: step: 524/531, loss: 0.007507037837058306
2023-01-21 13:39:04.961859: step: 528/531, loss: 0.00024452211800962687
2023-01-21 13:39:06.107768: step: 532/531, loss: 0.015096664428710938
2023-01-21 13:39:07.219726: step: 536/531, loss: 2.2315980459097773e-05
2023-01-21 13:39:08.330595: step: 540/531, loss: 5.073547436040826e-05
2023-01-21 13:39:09.447444: step: 544/531, loss: 0.0015371324261650443
2023-01-21 13:39:10.618954: step: 548/531, loss: 0.022781943902373314
2023-01-21 13:39:11.751021: step: 552/531, loss: 0.0002980232238769531
2023-01-21 13:39:12.921112: step: 556/531, loss: 0.001135158585384488
2023-01-21 13:39:14.061491: step: 560/531, loss: 0.00031719208345748484
2023-01-21 13:39:15.182609: step: 564/531, loss: 1.6975403923424892e-05
2023-01-21 13:39:16.339206: step: 568/531, loss: 0.001083850977011025
2023-01-21 13:39:17.477807: step: 572/531, loss: 0.029671192169189453
2023-01-21 13:39:18.589281: step: 576/531, loss: 0.0007109642610885203
2023-01-21 13:39:19.723796: step: 580/531, loss: 0.0014524459838867188
2023-01-21 13:39:20.837243: step: 584/531, loss: 0.02809906005859375
2023-01-21 13:39:22.036148: step: 588/531, loss: 4.806518700206652e-05
2023-01-21 13:39:23.162958: step: 592/531, loss: 0.000721836113370955
2023-01-21 13:39:24.316908: step: 596/531, loss: 0.005446815863251686
2023-01-21 13:39:25.446049: step: 600/531, loss: 5.91278076171875e-05
2023-01-21 13:39:26.552798: step: 604/531, loss: 0.01587248034775257
2023-01-21 13:39:27.707384: step: 608/531, loss: 0.004073906224220991
2023-01-21 13:39:28.868059: step: 612/531, loss: 7.009506225585938e-05
2023-01-21 13:39:30.017440: step: 616/531, loss: 0.00017499923706054688
2023-01-21 13:39:31.121250: step: 620/531, loss: 0.019237900152802467
2023-01-21 13:39:32.256374: step: 624/531, loss: 0.006781387608498335
2023-01-21 13:39:33.377957: step: 628/531, loss: 8.430481102550402e-05
2023-01-21 13:39:34.512236: step: 632/531, loss: 0.001216030097566545
2023-01-21 13:39:35.636434: step: 636/531, loss: 8.106231689453125e-06
2023-01-21 13:39:36.856205: step: 640/531, loss: 0.0002494812069926411
2023-01-21 13:39:37.967646: step: 644/531, loss: 0.0004675865056924522
2023-01-21 13:39:39.096667: step: 648/531, loss: 0.0058078765869140625
2023-01-21 13:39:40.222555: step: 652/531, loss: 0.05218668282032013
2023-01-21 13:39:41.345136: step: 656/531, loss: 0.0011812209850177169
2023-01-21 13:39:42.496342: step: 660/531, loss: 0.004022025968879461
2023-01-21 13:39:43.606766: step: 664/531, loss: 9.5367431640625e-06
2023-01-21 13:39:44.778656: step: 668/531, loss: 0.012993049807846546
2023-01-21 13:39:45.894894: step: 672/531, loss: 0.004771995823830366
2023-01-21 13:39:47.050734: step: 676/531, loss: 0.001386451767757535
2023-01-21 13:39:48.163007: step: 680/531, loss: 3.170967102050781e-05
2023-01-21 13:39:49.265640: step: 684/531, loss: 0.004673290532082319
2023-01-21 13:39:50.391474: step: 688/531, loss: 0.02231273613870144
2023-01-21 13:39:51.503225: step: 692/531, loss: 0.06851554661989212
2023-01-21 13:39:52.643731: step: 696/531, loss: 3.490447852527723e-05
2023-01-21 13:39:53.751500: step: 700/531, loss: 6.198883056640625e-05
2023-01-21 13:39:54.880896: step: 704/531, loss: 5.6457516620866954e-05
2023-01-21 13:39:55.993347: step: 708/531, loss: 0.002029895782470703
2023-01-21 13:39:57.120232: step: 712/531, loss: 0.0063069346360862255
2023-01-21 13:39:58.236736: step: 716/531, loss: 1.602172778802924e-05
2023-01-21 13:39:59.362654: step: 720/531, loss: 0.0016890049446374178
2023-01-21 13:40:00.517094: step: 724/531, loss: 1.0395049685030244e-05
2023-01-21 13:40:01.670449: step: 728/531, loss: 0.013375855050981045
2023-01-21 13:40:02.821984: step: 732/531, loss: 0.058811575174331665
2023-01-21 13:40:03.951598: step: 736/531, loss: 0.00027751922607421875
2023-01-21 13:40:05.092073: step: 740/531, loss: 0.03550739586353302
2023-01-21 13:40:06.233549: step: 744/531, loss: 0.11045493930578232
2023-01-21 13:40:07.379462: step: 748/531, loss: 0.008289719000458717
2023-01-21 13:40:08.521916: step: 752/531, loss: 9.422302537132055e-05
2023-01-21 13:40:09.642926: step: 756/531, loss: 0.0001981735258596018
2023-01-21 13:40:10.757780: step: 760/531, loss: 0.026142168790102005
2023-01-21 13:40:11.895601: step: 764/531, loss: 0.0065392497926950455
2023-01-21 13:40:13.030171: step: 768/531, loss: 0.0001352310209767893
2023-01-21 13:40:14.175385: step: 772/531, loss: 0.003180217929184437
2023-01-21 13:40:15.283619: step: 776/531, loss: 0.0003345966397318989
2023-01-21 13:40:16.400498: step: 780/531, loss: 0.00020141602726653218
2023-01-21 13:40:17.504508: step: 784/531, loss: 0.00010433197894599289
2023-01-21 13:40:18.634986: step: 788/531, loss: -3.6239625842426904e-06
2023-01-21 13:40:19.719959: step: 792/531, loss: 0.01801004447042942
2023-01-21 13:40:20.836260: step: 796/531, loss: 4.6348573960131034e-05
2023-01-21 13:40:21.938906: step: 800/531, loss: 1.3351441339182202e-06
2023-01-21 13:40:23.110508: step: 804/531, loss: 0.013704968616366386
2023-01-21 13:40:24.224867: step: 808/531, loss: 2.250671423098538e-05
2023-01-21 13:40:25.354183: step: 812/531, loss: 0.0023981095291674137
2023-01-21 13:40:26.471552: step: 816/531, loss: 0.0024518491700291634
2023-01-21 13:40:27.609338: step: 820/531, loss: 0.003085517790168524
2023-01-21 13:40:28.746922: step: 824/531, loss: 3.5762786865234375e-05
2023-01-21 13:40:29.867979: step: 828/531, loss: 0.027862071990966797
2023-01-21 13:40:31.017601: step: 832/531, loss: 0.010223960503935814
2023-01-21 13:40:32.135700: step: 836/531, loss: 0.016177557408809662
2023-01-21 13:40:33.270798: step: 840/531, loss: 0.012003231793642044
2023-01-21 13:40:34.389431: step: 844/531, loss: 0.02688327059149742
2023-01-21 13:40:35.544854: step: 848/531, loss: 0.003919505979865789
2023-01-21 13:40:36.698135: step: 852/531, loss: 0.06739606708288193
2023-01-21 13:40:37.826972: step: 856/531, loss: 0.005322265438735485
2023-01-21 13:40:38.950101: step: 860/531, loss: 0.06640568375587463
2023-01-21 13:40:40.051261: step: 864/531, loss: 0.0015245437389239669
2023-01-21 13:40:41.189474: step: 868/531, loss: 0.0010734081733971834
2023-01-21 13:40:42.324384: step: 872/531, loss: 0.029058076441287994
2023-01-21 13:40:43.488024: step: 876/531, loss: 0.0002967834589071572
2023-01-21 13:40:44.622232: step: 880/531, loss: 5.7744979130802676e-05
2023-01-21 13:40:45.731657: step: 884/531, loss: 0.0025772093795239925
2023-01-21 13:40:46.850994: step: 888/531, loss: 2.288818359375e-05
2023-01-21 13:40:47.986772: step: 892/531, loss: 2.231597864010837e-05
2023-01-21 13:40:49.102346: step: 896/531, loss: 4.706382969743572e-05
2023-01-21 13:40:50.234869: step: 900/531, loss: 0.0006538391462527215
2023-01-21 13:40:51.340282: step: 904/531, loss: 0.0008965493179857731
2023-01-21 13:40:52.489585: step: 908/531, loss: 0.00011024475679732859
2023-01-21 13:40:53.588197: step: 912/531, loss: 7.438660304615041e-06
2023-01-21 13:40:54.709677: step: 916/531, loss: 9.765624417923391e-05
2023-01-21 13:40:55.829101: step: 920/531, loss: -1.0967255548166577e-06
2023-01-21 13:40:56.924714: step: 924/531, loss: -0.0
2023-01-21 13:40:58.017052: step: 928/531, loss: 9.393692380399443e-06
2023-01-21 13:40:59.112379: step: 932/531, loss: 2.3365021206700476e-06
2023-01-21 13:41:00.230653: step: 936/531, loss: 3.7765505112474784e-05
2023-01-21 13:41:01.416700: step: 940/531, loss: 0.0010574341285973787
2023-01-21 13:41:02.521839: step: 944/531, loss: 0.0022607804276049137
2023-01-21 13:41:03.680633: step: 948/531, loss: 0.0010807036887854338
2023-01-21 13:41:04.818626: step: 952/531, loss: 6.904602196300402e-05
2023-01-21 13:41:05.928894: step: 956/531, loss: 0.00017280578322242945
2023-01-21 13:41:07.054245: step: 960/531, loss: 0.00015873908705543727
2023-01-21 13:41:08.186314: step: 964/531, loss: 0.03656425699591637
2023-01-21 13:41:09.308746: step: 968/531, loss: 0.0006323814741335809
2023-01-21 13:41:10.436874: step: 972/531, loss: 0.0001966476411325857
2023-01-21 13:41:11.542410: step: 976/531, loss: 1.4638901120633818e-05
2023-01-21 13:41:12.677351: step: 980/531, loss: 0.020313262939453125
2023-01-21 13:41:13.794414: step: 984/531, loss: 0.006087875459343195
2023-01-21 13:41:14.942469: step: 988/531, loss: 0.0005690574762411416
2023-01-21 13:41:16.075931: step: 992/531, loss: 0.056046582758426666
2023-01-21 13:41:17.170977: step: 996/531, loss: 3.414153979974799e-05
2023-01-21 13:41:18.291781: step: 1000/531, loss: 0.0016624450217932463
2023-01-21 13:41:19.418071: step: 1004/531, loss: 0.0012004852760583162
2023-01-21 13:41:20.541276: step: 1008/531, loss: 0.004714012145996094
2023-01-21 13:41:21.696074: step: 1012/531, loss: 0.024550437927246094
2023-01-21 13:41:22.804753: step: 1016/531, loss: 0.012376213446259499
2023-01-21 13:41:23.935185: step: 1020/531, loss: 0.008895112201571465
2023-01-21 13:41:25.064187: step: 1024/531, loss: 0.009144734591245651
2023-01-21 13:41:26.184660: step: 1028/531, loss: 0.00043668749276548624
2023-01-21 13:41:27.325388: step: 1032/531, loss: 3.938675217796117e-05
2023-01-21 13:41:28.497794: step: 1036/531, loss: 0.00045261383638717234
2023-01-21 13:41:29.642510: step: 1040/531, loss: 0.000240325927734375
2023-01-21 13:41:30.778861: step: 1044/531, loss: 1.888275073724799e-05
2023-01-21 13:41:31.878193: step: 1048/531, loss: -4.0054324017546605e-06
2023-01-21 13:41:33.013269: step: 1052/531, loss: 0.037900160998106
2023-01-21 13:41:34.136601: step: 1056/531, loss: 0.013981628231704235
2023-01-21 13:41:35.239160: step: 1060/531, loss: 1.0395049685030244e-05
2023-01-21 13:41:36.353943: step: 1064/531, loss: 2.765655517578125e-05
2023-01-21 13:41:37.489112: step: 1068/531, loss: 0.00029139520484022796
2023-01-21 13:41:38.601968: step: 1072/531, loss: 0.0021213532891124487
2023-01-21 13:41:39.706574: step: 1076/531, loss: 0.04845290258526802
2023-01-21 13:41:40.857095: step: 1080/531, loss: -2.1457672119140625e-06
2023-01-21 13:41:41.970428: step: 1084/531, loss: 0.008490849286317825
2023-01-21 13:41:43.081866: step: 1088/531, loss: 0.002239799592643976
2023-01-21 13:41:44.211755: step: 1092/531, loss: 0.008220577612519264
2023-01-21 13:41:45.308467: step: 1096/531, loss: 0.0003144264337606728
2023-01-21 13:41:46.442544: step: 1100/531, loss: 6.170273263705894e-05
2023-01-21 13:41:47.548206: step: 1104/531, loss: 2.9277802241267636e-05
2023-01-21 13:41:48.676862: step: 1108/531, loss: 7.724762326688506e-06
2023-01-21 13:41:49.807574: step: 1112/531, loss: 0.0011811256408691406
2023-01-21 13:41:50.940770: step: 1116/531, loss: 0.0074310302734375
2023-01-21 13:41:52.047061: step: 1120/531, loss: 0.024226855486631393
2023-01-21 13:41:53.175186: step: 1124/531, loss: 0.0081291189417243
2023-01-21 13:41:54.298557: step: 1128/531, loss: 0.002590179443359375
2023-01-21 13:41:55.427517: step: 1132/531, loss: 1.296997106692288e-05
2023-01-21 13:41:56.537628: step: 1136/531, loss: 9.651183790992945e-05
2023-01-21 13:41:57.678673: step: 1140/531, loss: 3.700256274896674e-05
2023-01-21 13:41:58.804495: step: 1144/531, loss: 0.4072877764701843
2023-01-21 13:41:59.919897: step: 1148/531, loss: 1.4019012269272935e-05
2023-01-21 13:42:01.023157: step: 1152/531, loss: 0.05686759948730469
2023-01-21 13:42:02.117068: step: 1156/531, loss: 0.01558542251586914
2023-01-21 13:42:03.239259: step: 1160/531, loss: 0.000504183757584542
2023-01-21 13:42:04.334858: step: 1164/531, loss: 9.222031076205894e-05
2023-01-21 13:42:05.443668: step: 1168/531, loss: 0.000812530517578125
2023-01-21 13:42:06.598270: step: 1172/531, loss: 0.009466457180678844
2023-01-21 13:42:07.743698: step: 1176/531, loss: 0.0001279830903513357
2023-01-21 13:42:08.871932: step: 1180/531, loss: 0.00021228790865279734
2023-01-21 13:42:10.001092: step: 1184/531, loss: 1.583099401614163e-05
2023-01-21 13:42:11.157183: step: 1188/531, loss: 0.023228121921420097
2023-01-21 13:42:12.277431: step: 1192/531, loss: 0.0003137111780233681
2023-01-21 13:42:13.427055: step: 1196/531, loss: 9.97066599666141e-05
2023-01-21 13:42:14.555285: step: 1200/531, loss: 0.00044965746928937733
2023-01-21 13:42:15.662295: step: 1204/531, loss: 0.005221414379775524
2023-01-21 13:42:16.777552: step: 1208/531, loss: 1.773834264895413e-05
2023-01-21 13:42:17.909039: step: 1212/531, loss: 0.07778330147266388
2023-01-21 13:42:19.020327: step: 1216/531, loss: 4.2724612285383046e-05
2023-01-21 13:42:20.129054: step: 1220/531, loss: 0.0025962828658521175
2023-01-21 13:42:21.241553: step: 1224/531, loss: 0.0004519462527241558
2023-01-21 13:42:22.393835: step: 1228/531, loss: -8.630751835880801e-06
2023-01-21 13:42:23.528308: step: 1232/531, loss: 0.0004171848122496158
2023-01-21 13:42:24.622016: step: 1236/531, loss: 1.8501283193472773e-05
2023-01-21 13:42:25.766183: step: 1240/531, loss: 0.033056020736694336
2023-01-21 13:42:26.908265: step: 1244/531, loss: 0.0008514404762536287
2023-01-21 13:42:28.035707: step: 1248/531, loss: 1.0681153071345761e-05
2023-01-21 13:42:29.185100: step: 1252/531, loss: 0.01489028986543417
2023-01-21 13:42:30.295309: step: 1256/531, loss: 4.4631960918195546e-05
2023-01-21 13:42:31.412842: step: 1260/531, loss: 8.916855222196318e-06
2023-01-21 13:42:32.508280: step: 1264/531, loss: 0.00166835798881948
2023-01-21 13:42:33.633987: step: 1268/531, loss: 0.005706119816750288
2023-01-21 13:42:34.768973: step: 1272/531, loss: 0.0023047449067234993
2023-01-21 13:42:35.916527: step: 1276/531, loss: 0.0018450261559337378
2023-01-21 13:42:37.050370: step: 1280/531, loss: 0.00107917794957757
2023-01-21 13:42:38.186326: step: 1284/531, loss: 0.002374029252678156
2023-01-21 13:42:39.325334: step: 1288/531, loss: 0.06363458931446075
2023-01-21 13:42:40.429264: step: 1292/531, loss: 0.0006917953724041581
2023-01-21 13:42:41.561144: step: 1296/531, loss: 0.0015007973415777087
2023-01-21 13:42:42.677209: step: 1300/531, loss: 0.0024959563743323088
2023-01-21 13:42:43.778023: step: 1304/531, loss: 0.00024662018404342234
2023-01-21 13:42:44.924541: step: 1308/531, loss: 0.05018739774823189
2023-01-21 13:42:46.049785: step: 1312/531, loss: 3.6478043057286413e-06
2023-01-21 13:42:47.183196: step: 1316/531, loss: 0.003646993776783347
2023-01-21 13:42:48.290837: step: 1320/531, loss: 1.3351441339182202e-05
2023-01-21 13:42:49.403431: step: 1324/531, loss: 0.0019901276100426912
2023-01-21 13:42:50.517825: step: 1328/531, loss: 0.003984689712524414
2023-01-21 13:42:51.648994: step: 1332/531, loss: 0.029755594208836555
2023-01-21 13:42:52.733258: step: 1336/531, loss: 0.00015778541273903102
2023-01-21 13:42:53.865243: step: 1340/531, loss: 7.190704491222277e-05
2023-01-21 13:42:54.974187: step: 1344/531, loss: 0.00046091078547760844
2023-01-21 13:42:56.124401: step: 1348/531, loss: 0.015927555039525032
2023-01-21 13:42:57.222741: step: 1352/531, loss: 0.0021800994873046875
2023-01-21 13:42:58.315705: step: 1356/531, loss: 3.490447852527723e-05
2023-01-21 13:42:59.491310: step: 1360/531, loss: 0.01369552593678236
2023-01-21 13:43:00.637682: step: 1364/531, loss: 0.028188277035951614
2023-01-21 13:43:01.749982: step: 1368/531, loss: 0.0005002975813113153
2023-01-21 13:43:02.874989: step: 1372/531, loss: 0.00038375856820493937
2023-01-21 13:43:03.981059: step: 1376/531, loss: 0.00012722014798782766
2023-01-21 13:43:05.094106: step: 1380/531, loss: 4.1484832763671875e-05
2023-01-21 13:43:06.198754: step: 1384/531, loss: 0.005601120181381702
2023-01-21 13:43:07.314712: step: 1388/531, loss: -9.5367431640625e-07
2023-01-21 13:43:08.428812: step: 1392/531, loss: 1.602172778802924e-05
2023-01-21 13:43:09.545758: step: 1396/531, loss: 9.5367431640625e-07
2023-01-21 13:43:10.667023: step: 1400/531, loss: 0.0012981415493413806
2023-01-21 13:43:11.787230: step: 1404/531, loss: 0.0013186454307287931
2023-01-21 13:43:12.937351: step: 1408/531, loss: 0.0022861480247229338
2023-01-21 13:43:14.052688: step: 1412/531, loss: 1.182556115963962e-05
2023-01-21 13:43:15.169664: step: 1416/531, loss: 0.008926964364945889
2023-01-21 13:43:16.280568: step: 1420/531, loss: 0.18557921051979065
2023-01-21 13:43:17.386751: step: 1424/531, loss: 0.002209282014518976
2023-01-21 13:43:18.514604: step: 1428/531, loss: 2.7942656743107364e-05
2023-01-21 13:43:19.645561: step: 1432/531, loss: 0.0011861324310302734
2023-01-21 13:43:20.771759: step: 1436/531, loss: 1.3351441339182202e-06
2023-01-21 13:43:21.867960: step: 1440/531, loss: 1.2397767022775952e-05
2023-01-21 13:43:22.988314: step: 1444/531, loss: 0.0011178969871252775
2023-01-21 13:43:24.084542: step: 1448/531, loss: 4.673003786592744e-06
2023-01-21 13:43:25.218258: step: 1452/531, loss: 4.301071021473035e-05
2023-01-21 13:43:26.345612: step: 1456/531, loss: 0.00025653839111328125
2023-01-21 13:43:27.469188: step: 1460/531, loss: 0.0005153656238690019
2023-01-21 13:43:28.598956: step: 1464/531, loss: 0.003677845001220703
2023-01-21 13:43:29.712886: step: 1468/531, loss: 0.019048118963837624
2023-01-21 13:43:30.841819: step: 1472/531, loss: 0.003568267682567239
2023-01-21 13:43:31.951758: step: 1476/531, loss: 0.0010761261219158769
2023-01-21 13:43:33.055576: step: 1480/531, loss: 0.000274848920525983
2023-01-21 13:43:34.192754: step: 1484/531, loss: 0.00606040982529521
2023-01-21 13:43:35.295837: step: 1488/531, loss: 0.11348118633031845
2023-01-21 13:43:36.432626: step: 1492/531, loss: 0.02407226711511612
2023-01-21 13:43:37.537871: step: 1496/531, loss: 2.47955313170678e-06
2023-01-21 13:43:38.665171: step: 1500/531, loss: 0.0001659393310546875
2023-01-21 13:43:39.822577: step: 1504/531, loss: 0.0012492657406255603
2023-01-21 13:43:40.949599: step: 1508/531, loss: 0.0015710830921307206
2023-01-21 13:43:42.104212: step: 1512/531, loss: 3.271103196311742e-05
2023-01-21 13:43:43.235568: step: 1516/531, loss: -8.01086389401462e-06
2023-01-21 13:43:44.388963: step: 1520/531, loss: 0.05632324516773224
2023-01-21 13:43:45.519913: step: 1524/531, loss: 0.00045714378939010203
2023-01-21 13:43:46.660633: step: 1528/531, loss: 0.00028333664522506297
2023-01-21 13:43:47.788143: step: 1532/531, loss: 0.00015163421630859375
2023-01-21 13:43:48.887195: step: 1536/531, loss: 0.0019630431197583675
2023-01-21 13:43:50.064538: step: 1540/531, loss: 0.0010982513194903731
2023-01-21 13:43:51.174048: step: 1544/531, loss: 0.03984341025352478
2023-01-21 13:43:52.316075: step: 1548/531, loss: 2.0122528439969756e-05
2023-01-21 13:43:53.459430: step: 1552/531, loss: 3.166198803228326e-05
2023-01-21 13:43:54.618064: step: 1556/531, loss: 0.06506137549877167
2023-01-21 13:43:55.716367: step: 1560/531, loss: 1.7070769899873994e-05
2023-01-21 13:43:56.825415: step: 1564/531, loss: 7.44819626561366e-05
2023-01-21 13:43:57.965342: step: 1568/531, loss: 0.00012493133544921875
2023-01-21 13:43:59.108912: step: 1572/531, loss: 0.012578964233398438
2023-01-21 13:44:00.258233: step: 1576/531, loss: 0.0027603148482739925
2023-01-21 13:44:01.341131: step: 1580/531, loss: 6.017685154802166e-05
2023-01-21 13:44:02.463839: step: 1584/531, loss: 9.536747711536009e-07
2023-01-21 13:44:03.600766: step: 1588/531, loss: 0.0011640548473224044
2023-01-21 13:44:04.727344: step: 1592/531, loss: 0.00033283233642578125
2023-01-21 13:44:05.858343: step: 1596/531, loss: 0.003079319139942527
2023-01-21 13:44:06.992406: step: 1600/531, loss: 0.000200176247744821
2023-01-21 13:44:08.124349: step: 1604/531, loss: 3.108978125965223e-05
2023-01-21 13:44:09.267706: step: 1608/531, loss: 0.012112236581742764
2023-01-21 13:44:10.399617: step: 1612/531, loss: 0.2612442076206207
2023-01-21 13:44:11.516314: step: 1616/531, loss: 0.039405059069395065
2023-01-21 13:44:12.673138: step: 1620/531, loss: 0.005214118864387274
2023-01-21 13:44:13.791038: step: 1624/531, loss: 0.033624839037656784
2023-01-21 13:44:14.925501: step: 1628/531, loss: 0.006922101601958275
2023-01-21 13:44:16.045455: step: 1632/531, loss: 0.0015802383422851562
2023-01-21 13:44:17.166929: step: 1636/531, loss: 0.010342169553041458
2023-01-21 13:44:18.280600: step: 1640/531, loss: 6.8664553509734105e-06
2023-01-21 13:44:19.378092: step: 1644/531, loss: 0.007073927205055952
2023-01-21 13:44:20.536624: step: 1648/531, loss: 0.0008792877197265625
2023-01-21 13:44:21.674123: step: 1652/531, loss: 0.0024515152908861637
2023-01-21 13:44:22.805471: step: 1656/531, loss: 0.0013290405040606856
2023-01-21 13:44:23.926617: step: 1660/531, loss: 5.1212311518611386e-05
2023-01-21 13:44:25.066834: step: 1664/531, loss: 0.00011134147644042969
2023-01-21 13:44:26.186194: step: 1668/531, loss: 4.301071021473035e-05
2023-01-21 13:44:27.336376: step: 1672/531, loss: 0.0014890669845044613
2023-01-21 13:44:28.466654: step: 1676/531, loss: 0.0007377624278888106
2023-01-21 13:44:29.613344: step: 1680/531, loss: 0.03756523132324219
2023-01-21 13:44:30.730930: step: 1684/531, loss: 0.008022690191864967
2023-01-21 13:44:31.864409: step: 1688/531, loss: 0.011565589345991611
2023-01-21 13:44:33.068316: step: 1692/531, loss: 3.242493221478071e-06
2023-01-21 13:44:34.199541: step: 1696/531, loss: 5.187988426769152e-05
2023-01-21 13:44:35.336538: step: 1700/531, loss: 0.0014257431030273438
2023-01-21 13:44:36.469282: step: 1704/531, loss: 0.00040473940316587687
2023-01-21 13:44:37.611545: step: 1708/531, loss: 0.20126645267009735
2023-01-21 13:44:38.708537: step: 1712/531, loss: -1.5258789289873675e-06
2023-01-21 13:44:39.821383: step: 1716/531, loss: 5.14984139954322e-06
2023-01-21 13:44:40.947394: step: 1720/531, loss: 0.0004879951593466103
2023-01-21 13:44:42.041065: step: 1724/531, loss: -5.14984139954322e-06
2023-01-21 13:44:43.166318: step: 1728/531, loss: 5.626678557746345e-06
2023-01-21 13:44:44.265524: step: 1732/531, loss: 0.0013959885109215975
2023-01-21 13:44:45.400685: step: 1736/531, loss: 0.0009515762212686241
2023-01-21 13:44:46.548999: step: 1740/531, loss: 0.038869474083185196
2023-01-21 13:44:47.712531: step: 1744/531, loss: 7.548332359874621e-05
2023-01-21 13:44:48.858578: step: 1748/531, loss: 1.3160706657799892e-05
2023-01-21 13:44:49.981342: step: 1752/531, loss: 0.011229324154555798
2023-01-21 13:44:51.120653: step: 1756/531, loss: 0.007871055975556374
2023-01-21 13:44:52.225325: step: 1760/531, loss: 7.62939453125e-06
2023-01-21 13:44:53.306379: step: 1764/531, loss: 0.00031294822110794485
2023-01-21 13:44:54.406273: step: 1768/531, loss: 0.06326790153980255
2023-01-21 13:44:55.531620: step: 1772/531, loss: 0.008076286874711514
2023-01-21 13:44:56.681657: step: 1776/531, loss: 1.0204315003647935e-05
2023-01-21 13:44:57.793310: step: 1780/531, loss: 8.77380352903856e-06
2023-01-21 13:44:58.917119: step: 1784/531, loss: 0.01799907721579075
2023-01-21 13:45:00.099119: step: 1788/531, loss: 1.5163422176556196e-05
2023-01-21 13:45:01.211740: step: 1792/531, loss: 0.00021448134793899953
2023-01-21 13:45:02.342817: step: 1796/531, loss: 9.059906005859375e-06
2023-01-21 13:45:03.476356: step: 1800/531, loss: 0.00017852782912086695
2023-01-21 13:45:04.567843: step: 1804/531, loss: 9.336472430732101e-05
2023-01-21 13:45:05.703014: step: 1808/531, loss: 0.005179357249289751
2023-01-21 13:45:06.841367: step: 1812/531, loss: 0.0002711295965127647
2023-01-21 13:45:07.957107: step: 1816/531, loss: 0.004403496161103249
2023-01-21 13:45:09.046717: step: 1820/531, loss: 0.0013646126026287675
2023-01-21 13:45:10.186900: step: 1824/531, loss: 6.0367583500919864e-05
2023-01-21 13:45:11.274275: step: 1828/531, loss: 0.0002537727414164692
2023-01-21 13:45:12.418186: step: 1832/531, loss: 0.06229753792285919
2023-01-21 13:45:13.523068: step: 1836/531, loss: 0.013969684019684792
2023-01-21 13:45:14.640422: step: 1840/531, loss: 0.029348278418183327
2023-01-21 13:45:15.752937: step: 1844/531, loss: 0.0003563881036825478
2023-01-21 13:45:16.863191: step: 1848/531, loss: 0.0006028652423992753
2023-01-21 13:45:17.976234: step: 1852/531, loss: 1.430511474609375e-05
2023-01-21 13:45:19.078524: step: 1856/531, loss: 9.155272891803179e-06
2023-01-21 13:45:20.195656: step: 1860/531, loss: 0.000637912773527205
2023-01-21 13:45:21.342184: step: 1864/531, loss: 0.0011831284500658512
2023-01-21 13:45:22.461658: step: 1868/531, loss: 3.4713742934400216e-05
2023-01-21 13:45:23.589571: step: 1872/531, loss: -6.67572021484375e-06
2023-01-21 13:45:24.743034: step: 1876/531, loss: -1.6403197150793858e-05
2023-01-21 13:45:25.845434: step: 1880/531, loss: 0.0006703853723593056
2023-01-21 13:45:26.958609: step: 1884/531, loss: 0.003070879029110074
2023-01-21 13:45:28.091250: step: 1888/531, loss: 0.0059950826689600945
2023-01-21 13:45:29.207600: step: 1892/531, loss: 0.008964157663285732
2023-01-21 13:45:30.336167: step: 1896/531, loss: 0.02835979498922825
2023-01-21 13:45:31.495793: step: 1900/531, loss: 2.002716064453125e-05
2023-01-21 13:45:32.600528: step: 1904/531, loss: 0.00601086625829339
2023-01-21 13:45:33.738259: step: 1908/531, loss: 0.015177535824477673
2023-01-21 13:45:34.870256: step: 1912/531, loss: 3.585815284168348e-05
2023-01-21 13:45:36.018960: step: 1916/531, loss: 0.00032367705716751516
2023-01-21 13:45:37.131178: step: 1920/531, loss: 5.044937279308215e-05
2023-01-21 13:45:38.253346: step: 1924/531, loss: 2.0027162008773303e-06
2023-01-21 13:45:39.371212: step: 1928/531, loss: 0.03934779018163681
2023-01-21 13:45:40.515299: step: 1932/531, loss: 5.8460234868107364e-05
2023-01-21 13:45:41.645218: step: 1936/531, loss: 3.814697265625e-06
2023-01-21 13:45:42.776879: step: 1940/531, loss: 0.056699562817811966
2023-01-21 13:45:43.906916: step: 1944/531, loss: 0.01460113562643528
2023-01-21 13:45:45.039719: step: 1948/531, loss: 1.029968279908644e-05
2023-01-21 13:45:46.167866: step: 1952/531, loss: 0.15948066115379333
2023-01-21 13:45:47.297121: step: 1956/531, loss: 0.0003173828299622983
2023-01-21 13:45:48.415357: step: 1960/531, loss: 0.0003345012664794922
2023-01-21 13:45:49.534047: step: 1964/531, loss: 0.0008962631109170616
2023-01-21 13:45:50.694093: step: 1968/531, loss: 0.00035457609919831157
2023-01-21 13:45:51.831685: step: 1972/531, loss: 0.004614639561623335
2023-01-21 13:45:52.933584: step: 1976/531, loss: 0.0005940437549725175
2023-01-21 13:45:54.040134: step: 1980/531, loss: 0.0007096290937624872
2023-01-21 13:45:55.156650: step: 1984/531, loss: 0.00011162758164573461
2023-01-21 13:45:56.303987: step: 1988/531, loss: 0.0014090538024902344
2023-01-21 13:45:57.426416: step: 1992/531, loss: 0.00277366628870368
2023-01-21 13:45:58.575842: step: 1996/531, loss: 0.0002563476446084678
2023-01-21 13:45:59.730303: step: 2000/531, loss: 0.04197826609015465
2023-01-21 13:46:00.815653: step: 2004/531, loss: 4.7302248276537284e-05
2023-01-21 13:46:01.986292: step: 2008/531, loss: 6.732940528308973e-05
2023-01-21 13:46:03.137747: step: 2012/531, loss: 0.0011829376453533769
2023-01-21 13:46:04.297345: step: 2016/531, loss: 0.004150581546127796
2023-01-21 13:46:05.425712: step: 2020/531, loss: 0.012096690945327282
2023-01-21 13:46:06.539196: step: 2024/531, loss: 0.064447782933712
2023-01-21 13:46:07.664905: step: 2028/531, loss: 5.6743621826171875e-05
2023-01-21 13:46:08.760510: step: 2032/531, loss: 0.00031003952608443797
2023-01-21 13:46:09.872594: step: 2036/531, loss: 0.006014919839799404
2023-01-21 13:46:10.991946: step: 2040/531, loss: 0.0021823407150804996
2023-01-21 13:46:12.117957: step: 2044/531, loss: 0.013766050338745117
2023-01-21 13:46:13.251963: step: 2048/531, loss: 0.0007156371721066535
2023-01-21 13:46:14.376496: step: 2052/531, loss: 0.0020761489868164062
2023-01-21 13:46:15.523637: step: 2056/531, loss: 0.007338905241340399
2023-01-21 13:46:16.674333: step: 2060/531, loss: 0.0005844116094522178
2023-01-21 13:46:17.801504: step: 2064/531, loss: 0.0003313064808025956
2023-01-21 13:46:18.929909: step: 2068/531, loss: 0.010087205097079277
2023-01-21 13:46:20.038513: step: 2072/531, loss: 0.0001329422084381804
2023-01-21 13:46:21.190750: step: 2076/531, loss: 0.019666101783514023
2023-01-21 13:46:22.294494: step: 2080/531, loss: 0.0005884170532226562
2023-01-21 13:46:23.418074: step: 2084/531, loss: 0.15691107511520386
2023-01-21 13:46:24.549418: step: 2088/531, loss: 0.0007205962901934981
2023-01-21 13:46:25.705610: step: 2092/531, loss: 0.010035133920609951
2023-01-21 13:46:26.814498: step: 2096/531, loss: 0.0005013942718505859
2023-01-21 13:46:27.951420: step: 2100/531, loss: -1.010894811770413e-05
2023-01-21 13:46:29.092391: step: 2104/531, loss: 0.008501911535859108
2023-01-21 13:46:30.220248: step: 2108/531, loss: 0.02015857584774494
2023-01-21 13:46:31.367715: step: 2112/531, loss: 1.8548966181697324e-05
2023-01-21 13:46:32.477732: step: 2116/531, loss: 0.0002402305690338835
2023-01-21 13:46:33.600960: step: 2120/531, loss: 0.02184896543622017
2023-01-21 13:46:34.715182: step: 2124/531, loss: 0.0030816078651696444
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5923309788092835, 'r': 0.7816245006657789, 'f1': 0.6739380022962113}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6377159309021113, 'r': 0.7924865831842576, 'f1': 0.706726934325977}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5882352941176471, 'r': 0.9259259259259259, 'f1': 0.7194244604316546}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6730769230769231, 'r': 0.5555555555555556, 'f1': 0.6086956521739131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
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': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6472819216182049, 'r': 0.681757656458056, 'f1': 0.6640726329442282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.6192226890756303, 'r': 0.7030411449016101, 'f1': 0.6584752862328959}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.7272727272727273, 'r': 0.7407407407407407, 'f1': 0.7339449541284404}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6066597294484911, 'r': 0.7762982689747004, 'f1': 0.6810747663551402}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Korean: {'event': {'p': 0.6443575964826576, 'r': 0.7865235539654144, 'f1': 0.708378088077336}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Korean: {'event': {'p': 0.7755102040816326, 'r': 0.6031746031746031, 'f1': 0.6785714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5520361990950227, 'r': 0.8122503328894807, 'f1': 0.6573275862068966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.591710758377425, 'r': 0.8002385211687537, 'f1': 0.6803548795944233}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.48148148148148145, 'r': 0.7222222222222222, 'f1': 0.5777777777777777}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}